diff options
769 files changed, 7400 insertions, 3863 deletions
diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu index f54867cadb0f..13c01b641dc7 100644 --- a/Documentation/ABI/testing/sysfs-devices-system-cpu +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu @@ -513,17 +513,18 @@ Description: information about CPUs heterogeneity. cpu_capacity: capacity of cpuX. What: /sys/devices/system/cpu/vulnerabilities + /sys/devices/system/cpu/vulnerabilities/gather_data_sampling + /sys/devices/system/cpu/vulnerabilities/itlb_multihit + /sys/devices/system/cpu/vulnerabilities/l1tf + /sys/devices/system/cpu/vulnerabilities/mds /sys/devices/system/cpu/vulnerabilities/meltdown + /sys/devices/system/cpu/vulnerabilities/mmio_stale_data + /sys/devices/system/cpu/vulnerabilities/retbleed + /sys/devices/system/cpu/vulnerabilities/spec_store_bypass /sys/devices/system/cpu/vulnerabilities/spectre_v1 /sys/devices/system/cpu/vulnerabilities/spectre_v2 - /sys/devices/system/cpu/vulnerabilities/spec_store_bypass - /sys/devices/system/cpu/vulnerabilities/l1tf - /sys/devices/system/cpu/vulnerabilities/mds /sys/devices/system/cpu/vulnerabilities/srbds /sys/devices/system/cpu/vulnerabilities/tsx_async_abort - /sys/devices/system/cpu/vulnerabilities/itlb_multihit - /sys/devices/system/cpu/vulnerabilities/mmio_stale_data - /sys/devices/system/cpu/vulnerabilities/retbleed Date: January 2018 Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org> Description: Information about CPU vulnerabilities diff --git a/Documentation/admin-guide/hw-vuln/gather_data_sampling.rst b/Documentation/admin-guide/hw-vuln/gather_data_sampling.rst new file mode 100644 index 000000000000..264bfa937f7d --- /dev/null +++ b/Documentation/admin-guide/hw-vuln/gather_data_sampling.rst @@ -0,0 +1,109 @@ +.. SPDX-License-Identifier: GPL-2.0 + +GDS - Gather Data Sampling +========================== + +Gather Data Sampling is a hardware vulnerability which allows unprivileged +speculative access to data which was previously stored in vector registers. + +Problem +------- +When a gather instruction performs loads from memory, different data elements +are merged into the destination vector register. However, when a gather +instruction that is transiently executed encounters a fault, stale data from +architectural or internal vector registers may get transiently forwarded to the +destination vector register instead. This will allow a malicious attacker to +infer stale data using typical side channel techniques like cache timing +attacks. GDS is a purely sampling-based attack. + +The attacker uses gather instructions to infer the stale vector register data. +The victim does not need to do anything special other than use the vector +registers. The victim does not need to use gather instructions to be +vulnerable. + +Because the buffers are shared between Hyper-Threads cross Hyper-Thread attacks +are possible. + +Attack scenarios +---------------- +Without mitigation, GDS can infer stale data across virtually all +permission boundaries: + + Non-enclaves can infer SGX enclave data + Userspace can infer kernel data + Guests can infer data from hosts + Guest can infer guest from other guests + Users can infer data from other users + +Because of this, it is important to ensure that the mitigation stays enabled in +lower-privilege contexts like guests and when running outside SGX enclaves. + +The hardware enforces the mitigation for SGX. Likewise, VMMs should ensure +that guests are not allowed to disable the GDS mitigation. If a host erred and +allowed this, a guest could theoretically disable GDS mitigation, mount an +attack, and re-enable it. + +Mitigation mechanism +-------------------- +This issue is mitigated in microcode. The microcode defines the following new +bits: + + ================================ === ============================ + IA32_ARCH_CAPABILITIES[GDS_CTRL] R/O Enumerates GDS vulnerability + and mitigation support. + IA32_ARCH_CAPABILITIES[GDS_NO] R/O Processor is not vulnerable. + IA32_MCU_OPT_CTRL[GDS_MITG_DIS] R/W Disables the mitigation + 0 by default. + IA32_MCU_OPT_CTRL[GDS_MITG_LOCK] R/W Locks GDS_MITG_DIS=0. Writes + to GDS_MITG_DIS are ignored + Can't be cleared once set. + ================================ === ============================ + +GDS can also be mitigated on systems that don't have updated microcode by +disabling AVX. This can be done by setting gather_data_sampling="force" or +"clearcpuid=avx" on the kernel command-line. + +If used, these options will disable AVX use by turning off XSAVE YMM support. +However, the processor will still enumerate AVX support. Userspace that +does not follow proper AVX enumeration to check both AVX *and* XSAVE YMM +support will break. + +Mitigation control on the kernel command line +--------------------------------------------- +The mitigation can be disabled by setting "gather_data_sampling=off" or +"mitigations=off" on the kernel command line. Not specifying either will default +to the mitigation being enabled. Specifying "gather_data_sampling=force" will +use the microcode mitigation when available or disable AVX on affected systems +where the microcode hasn't been updated to include the mitigation. + +GDS System Information +------------------------ +The kernel provides vulnerability status information through sysfs. For +GDS this can be accessed by the following sysfs file: + +/sys/devices/system/cpu/vulnerabilities/gather_data_sampling + +The possible values contained in this file are: + + ============================== ============================================= + Not affected Processor not vulnerable. + Vulnerable Processor vulnerable and mitigation disabled. + Vulnerable: No microcode Processor vulnerable and microcode is missing + mitigation. + Mitigation: AVX disabled, + no microcode Processor is vulnerable and microcode is missing + mitigation. AVX disabled as mitigation. + Mitigation: Microcode Processor is vulnerable and mitigation is in + effect. + Mitigation: Microcode (locked) Processor is vulnerable and mitigation is in + effect and cannot be disabled. + Unknown: Dependent on + hypervisor status Running on a virtual guest processor that is + affected but with no way to know if host + processor is mitigated or vulnerable. + ============================== ============================================= + +GDS Default mitigation +---------------------- +The updated microcode will enable the mitigation by default. The kernel's +default action is to leave the mitigation enabled. diff --git a/Documentation/admin-guide/hw-vuln/index.rst b/Documentation/admin-guide/hw-vuln/index.rst index e0614760a99e..6828102baaa7 100644 --- a/Documentation/admin-guide/hw-vuln/index.rst +++ b/Documentation/admin-guide/hw-vuln/index.rst @@ -19,3 +19,5 @@ are configurable at compile, boot or run time. l1d_flush.rst processor_mmio_stale_data.rst cross-thread-rsb.rst + gather_data_sampling.rst + srso diff --git a/Documentation/admin-guide/hw-vuln/srso.rst b/Documentation/admin-guide/hw-vuln/srso.rst new file mode 100644 index 000000000000..f79cb11b080f --- /dev/null +++ b/Documentation/admin-guide/hw-vuln/srso.rst @@ -0,0 +1,133 @@ +.. SPDX-License-Identifier: GPL-2.0 + +Speculative Return Stack Overflow (SRSO) +======================================== + +This is a mitigation for the speculative return stack overflow (SRSO) +vulnerability found on AMD processors. The mechanism is by now the well +known scenario of poisoning CPU functional units - the Branch Target +Buffer (BTB) and Return Address Predictor (RAP) in this case - and then +tricking the elevated privilege domain (the kernel) into leaking +sensitive data. + +AMD CPUs predict RET instructions using a Return Address Predictor (aka +Return Address Stack/Return Stack Buffer). In some cases, a non-architectural +CALL instruction (i.e., an instruction predicted to be a CALL but is +not actually a CALL) can create an entry in the RAP which may be used +to predict the target of a subsequent RET instruction. + +The specific circumstances that lead to this varies by microarchitecture +but the concern is that an attacker can mis-train the CPU BTB to predict +non-architectural CALL instructions in kernel space and use this to +control the speculative target of a subsequent kernel RET, potentially +leading to information disclosure via a speculative side-channel. + +The issue is tracked under CVE-2023-20569. + +Affected processors +------------------- + +AMD Zen, generations 1-4. That is, all families 0x17 and 0x19. Older +processors have not been investigated. + +System information and options +------------------------------ + +First of all, it is required that the latest microcode be loaded for +mitigations to be effective. + +The sysfs file showing SRSO mitigation status is: + + /sys/devices/system/cpu/vulnerabilities/spec_rstack_overflow + +The possible values in this file are: + + - 'Not affected' The processor is not vulnerable + + - 'Vulnerable: no microcode' The processor is vulnerable, no + microcode extending IBPB functionality + to address the vulnerability has been + applied. + + - 'Mitigation: microcode' Extended IBPB functionality microcode + patch has been applied. It does not + address User->Kernel and Guest->Host + transitions protection but it does + address User->User and VM->VM attack + vectors. + + (spec_rstack_overflow=microcode) + + - 'Mitigation: safe RET' Software-only mitigation. It complements + the extended IBPB microcode patch + functionality by addressing User->Kernel + and Guest->Host transitions protection. + + Selected by default or by + spec_rstack_overflow=safe-ret + + - 'Mitigation: IBPB' Similar protection as "safe RET" above + but employs an IBPB barrier on privilege + domain crossings (User->Kernel, + Guest->Host). + + (spec_rstack_overflow=ibpb) + + - 'Mitigation: IBPB on VMEXIT' Mitigation addressing the cloud provider + scenario - the Guest->Host transitions + only. + + (spec_rstack_overflow=ibpb-vmexit) + +In order to exploit vulnerability, an attacker needs to: + + - gain local access on the machine + + - break kASLR + + - find gadgets in the running kernel in order to use them in the exploit + + - potentially create and pin an additional workload on the sibling + thread, depending on the microarchitecture (not necessary on fam 0x19) + + - run the exploit + +Considering the performance implications of each mitigation type, the +default one is 'Mitigation: safe RET' which should take care of most +attack vectors, including the local User->Kernel one. + +As always, the user is advised to keep her/his system up-to-date by +applying software updates regularly. + +The default setting will be reevaluated when needed and especially when +new attack vectors appear. + +As one can surmise, 'Mitigation: safe RET' does come at the cost of some +performance depending on the workload. If one trusts her/his userspace +and does not want to suffer the performance impact, one can always +disable the mitigation with spec_rstack_overflow=off. + +Similarly, 'Mitigation: IBPB' is another full mitigation type employing +an indrect branch prediction barrier after having applied the required +microcode patch for one's system. This mitigation comes also at +a performance cost. + +Mitigation: safe RET +-------------------- + +The mitigation works by ensuring all RET instructions speculate to +a controlled location, similar to how speculation is controlled in the +retpoline sequence. To accomplish this, the __x86_return_thunk forces +the CPU to mispredict every function return using a 'safe return' +sequence. + +To ensure the safety of this mitigation, the kernel must ensure that the +safe return sequence is itself free from attacker interference. In Zen3 +and Zen4, this is accomplished by creating a BTB alias between the +untraining function srso_alias_untrain_ret() and the safe return +function srso_alias_safe_ret() which results in evicting a potentially +poisoned BTB entry and using that safe one for all function returns. + +In older Zen1 and Zen2, this is accomplished using a reinterpretation +technique similar to Retbleed one: srso_untrain_ret() and +srso_safe_ret(). diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 7ec93ae6757f..00c10b9ea8dc 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -323,6 +323,7 @@ option with care. pgtbl_v1 - Use v1 page table for DMA-API (Default). pgtbl_v2 - Use v2 page table for DMA-API. + irtcachedis - Disable Interrupt Remapping Table (IRT) caching. amd_iommu_dump= [HW,X86-64] Enable AMD IOMMU driver option to dump the ACPI table @@ -1593,6 +1594,26 @@ Format: off | on default: on + gather_data_sampling= + [X86,INTEL] Control the Gather Data Sampling (GDS) + mitigation. + + Gather Data Sampling is a hardware vulnerability which + allows unprivileged speculative access to data which was + previously stored in vector registers. + + This issue is mitigated by default in updated microcode. + The mitigation may have a performance impact but can be + disabled. On systems without the microcode mitigation + disabling AVX serves as a mitigation. + + force: Disable AVX to mitigate systems without + microcode mitigation. No effect if the microcode + mitigation is present. Known to cause crashes in + userspace with buggy AVX enumeration. + + off: Disable GDS mitigation. + gcov_persist= [GCOV] When non-zero (default), profiling data for kernel modules is saved and remains accessible via debugfs, even when the module is unloaded/reloaded. @@ -3228,24 +3249,25 @@ Disable all optional CPU mitigations. This improves system performance, but it may also expose users to several CPU vulnerabilities. - Equivalent to: nopti [X86,PPC] - if nokaslr then kpti=0 [ARM64] - nospectre_v1 [X86,PPC] - nobp=0 [S390] - nospectre_v2 [X86,PPC,S390,ARM64] - spectre_v2_user=off [X86] - spec_store_bypass_disable=off [X86,PPC] - ssbd=force-off [ARM64] - nospectre_bhb [ARM64] + Equivalent to: if nokaslr then kpti=0 [ARM64] + gather_data_sampling=off [X86] + kvm.nx_huge_pages=off [X86] l1tf=off [X86] mds=off [X86] - tsx_async_abort=off [X86] - kvm.nx_huge_pages=off [X86] - srbds=off [X86,INTEL] + mmio_stale_data=off [X86] no_entry_flush [PPC] no_uaccess_flush [PPC] - mmio_stale_data=off [X86] + nobp=0 [S390] + nopti [X86,PPC] + nospectre_bhb [ARM64] + nospectre_v1 [X86,PPC] + nospectre_v2 [X86,PPC,S390,ARM64] retbleed=off [X86] + spec_store_bypass_disable=off [X86,PPC] + spectre_v2_user=off [X86] + srbds=off [X86,INTEL] + ssbd=force-off [ARM64] + tsx_async_abort=off [X86] Exceptions: This does not have any effect on @@ -5767,6 +5789,17 @@ Not specifying this option is equivalent to spectre_v2_user=auto. + spec_rstack_overflow= + [X86] Control RAS overflow mitigation on AMD Zen CPUs + + off - Disable mitigation + microcode - Enable microcode mitigation only + safe-ret - Enable sw-only safe RET mitigation (default) + ibpb - Enable mitigation by issuing IBPB on + kernel entry + ibpb-vmexit - Issue IBPB only on VMEXIT + (cloud-specific mitigation) + spec_store_bypass_disable= [HW] Control Speculative Store Bypass (SSB) Disable mitigation (Speculative Store Bypass vulnerability) @@ -6134,10 +6167,6 @@ -1: disable all critical trip points in all thermal zones <degrees C>: override all critical trip points - thermal.nocrt= [HW,ACPI] - Set to disable actions on ACPI thermal zone - critical and hot trip points. - thermal.off= [HW,ACPI] 1: disable ACPI thermal control diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst index bbc80eff03f9..b3c8ac6a2c38 100644 --- a/Documentation/arm64/silicon-errata.rst +++ b/Documentation/arm64/silicon-errata.rst @@ -141,6 +141,10 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | ARM | MMU-500 | #841119,826419 | N/A | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | MMU-600 | #1076982,1209401| N/A | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | MMU-700 | #2268618,2812531| N/A | ++----------------+-----------------+-----------------+-----------------------------+ +----------------+-----------------+-----------------+-----------------------------+ | Broadcom | Brahma-B53 | N/A | ARM64_ERRATUM_845719 | +----------------+-----------------+-----------------+-----------------------------+ diff --git a/Documentation/devicetree/bindings/serial/nxp,sc16is7xx.txt b/Documentation/devicetree/bindings/serial/nxp,sc16is7xx.txt index 0fa8e3e43bf8..1a7e4bff0456 100644 --- a/Documentation/devicetree/bindings/serial/nxp,sc16is7xx.txt +++ b/Documentation/devicetree/bindings/serial/nxp,sc16is7xx.txt @@ -23,6 +23,9 @@ Optional properties: 1 = active low. - irda-mode-ports: An array that lists the indices of the port that should operate in IrDA mode. +- nxp,modem-control-line-ports: An array that lists the indices of the port that + should have shared GPIO lines configured as + modem control lines. Example: sc16is750: sc16is750@51 { @@ -35,6 +38,26 @@ Example: #gpio-cells = <2>; }; + sc16is752: sc16is752@53 { + compatible = "nxp,sc16is752"; + reg = <0x53>; + clocks = <&clk20m>; + interrupt-parent = <&gpio3>; + interrupts = <7 IRQ_TYPE_EDGE_FALLING>; + nxp,modem-control-line-ports = <1>; /* Port 1 as modem control lines */ + gpio-controller; /* Port 0 as GPIOs */ + #gpio-cells = <2>; + }; + + sc16is752: sc16is752@54 { + compatible = "nxp,sc16is752"; + reg = <0x54>; + clocks = <&clk20m>; + interrupt-parent = <&gpio3>; + interrupts = <7 IRQ_TYPE_EDGE_FALLING>; + nxp,modem-control-line-ports = <0 1>; /* Ports 0 and 1 as modem control lines */ + }; + * spi as bus Required properties: @@ -59,6 +82,9 @@ Optional properties: 1 = active low. - irda-mode-ports: An array that lists the indices of the port that should operate in IrDA mode. +- nxp,modem-control-line-ports: An array that lists the indices of the port that + should have shared GPIO lines configured as + modem control lines. Example: sc16is750: sc16is750@0 { @@ -70,3 +96,23 @@ Example: gpio-controller; #gpio-cells = <2>; }; + + sc16is752: sc16is752@1 { + compatible = "nxp,sc16is752"; + reg = <1>; + clocks = <&clk20m>; + interrupt-parent = <&gpio3>; + interrupts = <7 IRQ_TYPE_EDGE_FALLING>; + nxp,modem-control-line-ports = <1>; /* Port 1 as modem control lines */ + gpio-controller; /* Port 0 as GPIOs */ + #gpio-cells = <2>; + }; + + sc16is752: sc16is752@2 { + compatible = "nxp,sc16is752"; + reg = <2>; + clocks = <&clk20m>; + interrupt-parent = <&gpio3>; + interrupts = <7 IRQ_TYPE_EDGE_FALLING>; + nxp,modem-control-line-ports = <0 1>; /* Ports 0 and 1 as modem control lines */ + }; diff --git a/MAINTAINERS b/MAINTAINERS index 56b35b182092..1263e0361593 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6027,7 +6027,7 @@ S: Supported F: Documentation/networking/devlink F: include/net/devlink.h F: include/uapi/linux/devlink.h -F: net/core/devlink.c +F: net/devlink/ DH ELECTRONICS IMX6 DHCOM BOARD SUPPORT M: Christoph Niedermaier <cniedermaier@dh-electronics.com> diff --git a/Makefile b/Makefile index 69cdd0d2946c..82aaa3ae7395 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 PATCHLEVEL = 1 -SUBLEVEL = 43 +SUBLEVEL = 52 EXTRAVERSION = NAME = Curry Ramen diff --git a/arch/Kconfig b/arch/Kconfig index 81599f5c17b0..b60d271bf76a 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -285,6 +285,9 @@ config ARCH_HAS_DMA_SET_UNCACHED config ARCH_HAS_DMA_CLEAR_UNCACHED bool +config ARCH_HAS_CPU_FINALIZE_INIT + bool + # Select if arch init_task must go in the __init_task_data section config ARCH_TASK_STRUCT_ON_STACK bool diff --git a/arch/alpha/include/asm/bugs.h b/arch/alpha/include/asm/bugs.h deleted file mode 100644 index 78030d1c7e7e..000000000000 --- a/arch/alpha/include/asm/bugs.h +++ /dev/null @@ -1,20 +0,0 @@ -/* - * include/asm-alpha/bugs.h - * - * Copyright (C) 1994 Linus Torvalds - */ - -/* - * This is included by init/main.c to check for architecture-dependent bugs. - * - * Needs: - * void check_bugs(void); - */ - -/* - * I don't know of any alpha bugs yet.. Nice chip - */ - -static void check_bugs(void) -{ -} diff --git a/arch/alpha/kernel/setup.c b/arch/alpha/kernel/setup.c index 33bf3a627002..45a920ba4921 100644 --- a/arch/alpha/kernel/setup.c +++ b/arch/alpha/kernel/setup.c @@ -385,8 +385,7 @@ setup_memory(void *kernel_end) #endif /* CONFIG_BLK_DEV_INITRD */ } -int __init -page_is_ram(unsigned long pfn) +int page_is_ram(unsigned long pfn) { struct memclust_struct * cluster; struct memdesc_struct * memdesc; diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 0202e48e7a20..6d5afe2e6ba3 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -5,6 +5,7 @@ config ARM select ARCH_32BIT_OFF_T select ARCH_CORRECT_STACKTRACE_ON_KRETPROBE if HAVE_KRETPROBES && FRAME_POINTER && !ARM_UNWIND select ARCH_HAS_BINFMT_FLAT + select ARCH_HAS_CPU_FINALIZE_INIT if MMU select ARCH_HAS_CURRENT_STACK_POINTER select ARCH_HAS_DEBUG_VIRTUAL if MMU select ARCH_HAS_DMA_WRITE_COMBINE if !ARM_DMA_MEM_BUFFERABLE diff --git a/arch/arm/boot/dts/imx50-kobo-aura.dts b/arch/arm/boot/dts/imx50-kobo-aura.dts index 51bf6117fb12..467db6b4ed7f 100644 --- a/arch/arm/boot/dts/imx50-kobo-aura.dts +++ b/arch/arm/boot/dts/imx50-kobo-aura.dts @@ -26,7 +26,7 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_leds>; - on { + led-on { label = "kobo_aura:orange:on"; gpios = <&gpio6 24 GPIO_ACTIVE_LOW>; panic-indicator; diff --git a/arch/arm/boot/dts/imx53-cx9020.dts b/arch/arm/boot/dts/imx53-cx9020.dts index cfb18849a92b..055d23a9aee7 100644 --- a/arch/arm/boot/dts/imx53-cx9020.dts +++ b/arch/arm/boot/dts/imx53-cx9020.dts @@ -86,27 +86,27 @@ leds { compatible = "gpio-leds"; - pwr-r { + led-pwr-r { gpios = <&gpio3 22 GPIO_ACTIVE_HIGH>; default-state = "off"; }; - pwr-g { + led-pwr-g { gpios = <&gpio3 24 GPIO_ACTIVE_HIGH>; default-state = "on"; }; - pwr-b { + led-pwr-b { gpios = <&gpio3 23 GPIO_ACTIVE_HIGH>; default-state = "off"; }; - sd1-b { + led-sd1-b { linux,default-trigger = "mmc0"; gpios = <&gpio3 20 GPIO_ACTIVE_HIGH>; }; - sd2-b { + led-sd2-b { linux,default-trigger = "mmc1"; gpios = <&gpio3 17 GPIO_ACTIVE_HIGH>; }; diff --git a/arch/arm/boot/dts/imx53-m53evk.dts b/arch/arm/boot/dts/imx53-m53evk.dts index a1a6228d1aa6..2bd2432d317f 100644 --- a/arch/arm/boot/dts/imx53-m53evk.dts +++ b/arch/arm/boot/dts/imx53-m53evk.dts @@ -52,13 +52,13 @@ pinctrl-names = "default"; pinctrl-0 = <&led_pin_gpio>; - user1 { + led-user1 { label = "user1"; gpios = <&gpio2 8 0>; linux,default-trigger = "heartbeat"; }; - user2 { + led-user2 { label = "user2"; gpios = <&gpio2 9 0>; linux,default-trigger = "heartbeat"; diff --git a/arch/arm/boot/dts/imx53-m53menlo.dts b/arch/arm/boot/dts/imx53-m53menlo.dts index d5c68d1ea707..4d77b6077fc1 100644 --- a/arch/arm/boot/dts/imx53-m53menlo.dts +++ b/arch/arm/boot/dts/imx53-m53menlo.dts @@ -34,19 +34,19 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_led>; - user1 { + led-user1 { label = "TestLed601"; gpios = <&gpio6 1 GPIO_ACTIVE_HIGH>; linux,default-trigger = "mmc0"; }; - user2 { + led-user2 { label = "TestLed602"; gpios = <&gpio6 2 GPIO_ACTIVE_HIGH>; linux,default-trigger = "heartbeat"; }; - eth { + led-eth { label = "EthLedYe"; gpios = <&gpio2 11 GPIO_ACTIVE_LOW>; linux,default-trigger = "netdev"; diff --git a/arch/arm/boot/dts/imx53-tx53.dtsi b/arch/arm/boot/dts/imx53-tx53.dtsi index 892dd1a4bac3..a439a47fb65a 100644 --- a/arch/arm/boot/dts/imx53-tx53.dtsi +++ b/arch/arm/boot/dts/imx53-tx53.dtsi @@ -94,7 +94,7 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_stk5led>; - user { + led-user { label = "Heartbeat"; gpios = <&gpio2 20 GPIO_ACTIVE_HIGH>; linux,default-trigger = "heartbeat"; diff --git a/arch/arm/boot/dts/imx53-usbarmory.dts b/arch/arm/boot/dts/imx53-usbarmory.dts index f34993a490ee..acc44010d510 100644 --- a/arch/arm/boot/dts/imx53-usbarmory.dts +++ b/arch/arm/boot/dts/imx53-usbarmory.dts @@ -67,7 +67,7 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_led>; - user { + led-user { label = "LED"; gpios = <&gpio4 27 GPIO_ACTIVE_LOW>; linux,default-trigger = "heartbeat"; diff --git a/arch/arm/boot/dts/imx6dl-b1x5pv2.dtsi b/arch/arm/boot/dts/imx6dl-b1x5pv2.dtsi index 337db29b0010..37697fac9dea 100644 --- a/arch/arm/boot/dts/imx6dl-b1x5pv2.dtsi +++ b/arch/arm/boot/dts/imx6dl-b1x5pv2.dtsi @@ -211,17 +211,17 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_q7_gpio1 &pinctrl_q7_gpio3 &pinctrl_q7_gpio5>; - alarm1 { + led-alarm1 { label = "alarm:red"; gpios = <&gpio1 8 GPIO_ACTIVE_HIGH>; }; - alarm2 { + led-alarm2 { label = "alarm:yellow"; gpios = <&gpio4 27 GPIO_ACTIVE_HIGH>; }; - alarm3 { + led-alarm3 { label = "alarm:blue"; gpios = <&gpio4 15 GPIO_ACTIVE_HIGH>; }; diff --git a/arch/arm/boot/dts/imx6dl-prtrvt.dts b/arch/arm/boot/dts/imx6dl-prtrvt.dts index 56bb1ca56a2d..36b031236e47 100644 --- a/arch/arm/boot/dts/imx6dl-prtrvt.dts +++ b/arch/arm/boot/dts/imx6dl-prtrvt.dts @@ -124,6 +124,10 @@ status = "disabled"; }; +&usbotg { + disable-over-current; +}; + &vpu { status = "disabled"; }; diff --git a/arch/arm/boot/dts/imx6dl-riotboard.dts b/arch/arm/boot/dts/imx6dl-riotboard.dts index e7be05f205d3..24c7f535f63b 100644 --- a/arch/arm/boot/dts/imx6dl-riotboard.dts +++ b/arch/arm/boot/dts/imx6dl-riotboard.dts @@ -25,14 +25,14 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_led>; - led0: user1 { + led0: led-user1 { label = "user1"; gpios = <&gpio5 2 GPIO_ACTIVE_LOW>; default-state = "on"; linux,default-trigger = "heartbeat"; }; - led1: user2 { + led1: led-user2 { label = "user2"; gpios = <&gpio3 28 GPIO_ACTIVE_LOW>; default-state = "off"; diff --git a/arch/arm/boot/dts/imx6dl-yapp4-common.dtsi b/arch/arm/boot/dts/imx6dl-yapp4-common.dtsi index 52162e8c7274..aacbf317feea 100644 --- a/arch/arm/boot/dts/imx6dl-yapp4-common.dtsi +++ b/arch/arm/boot/dts/imx6dl-yapp4-common.dtsi @@ -274,7 +274,7 @@ #address-cells = <1>; #size-cells = <0>; - chan@0 { + led@0 { chan-name = "R"; led-cur = /bits/ 8 <0x20>; max-cur = /bits/ 8 <0x60>; @@ -282,7 +282,7 @@ color = <LED_COLOR_ID_RED>; }; - chan@1 { + led@1 { chan-name = "G"; led-cur = /bits/ 8 <0x20>; max-cur = /bits/ 8 <0x60>; @@ -290,7 +290,7 @@ color = <LED_COLOR_ID_GREEN>; }; - chan@2 { + led@2 { chan-name = "B"; led-cur = /bits/ 8 <0x20>; max-cur = /bits/ 8 <0x60>; diff --git a/arch/arm/boot/dts/imx6q-gw5400-a.dts b/arch/arm/boot/dts/imx6q-gw5400-a.dts index e894faba571f..522a51042965 100644 --- a/arch/arm/boot/dts/imx6q-gw5400-a.dts +++ b/arch/arm/boot/dts/imx6q-gw5400-a.dts @@ -34,20 +34,20 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_gpio_leds>; - led0: user1 { + led0: led-user1 { label = "user1"; gpios = <&gpio4 6 GPIO_ACTIVE_HIGH>; /* 102 -> MX6_PANLEDG */ default-state = "on"; linux,default-trigger = "heartbeat"; }; - led1: user2 { + led1: led-user2 { label = "user2"; gpios = <&gpio4 10 GPIO_ACTIVE_HIGH>; /* 106 -> MX6_PANLEDR */ default-state = "off"; }; - led2: user3 { + led2: led-user3 { label = "user3"; gpios = <&gpio4 15 GPIO_ACTIVE_LOW>; /* 111 -> MX6_LOCLED# */ default-state = "off"; diff --git a/arch/arm/boot/dts/imx6q-h100.dts b/arch/arm/boot/dts/imx6q-h100.dts index b8feadbff967..6406ade14f57 100644 --- a/arch/arm/boot/dts/imx6q-h100.dts +++ b/arch/arm/boot/dts/imx6q-h100.dts @@ -76,19 +76,19 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_h100_leds>; - led0: power { + led0: led-power { label = "power"; gpios = <&gpio3 0 GPIO_ACTIVE_LOW>; default-state = "on"; }; - led1: stream { + led1: led-stream { label = "stream"; gpios = <&gpio2 29 GPIO_ACTIVE_LOW>; default-state = "off"; }; - led2: rec { + led2: led-rec { label = "rec"; gpios = <&gpio2 28 GPIO_ACTIVE_LOW>; default-state = "off"; diff --git a/arch/arm/boot/dts/imx6q-kp.dtsi b/arch/arm/boot/dts/imx6q-kp.dtsi index 1ade0bff681d..5e0ed5560040 100644 --- a/arch/arm/boot/dts/imx6q-kp.dtsi +++ b/arch/arm/boot/dts/imx6q-kp.dtsi @@ -66,14 +66,14 @@ leds { compatible = "gpio-leds"; - green { + led-green { label = "led1"; gpios = <&gpio3 16 GPIO_ACTIVE_HIGH>; linux,default-trigger = "gpio"; default-state = "off"; }; - red { + led-red { label = "led0"; gpios = <&gpio3 23 GPIO_ACTIVE_HIGH>; linux,default-trigger = "gpio"; diff --git a/arch/arm/boot/dts/imx6q-marsboard.dts b/arch/arm/boot/dts/imx6q-marsboard.dts index cc1801002394..2c9961333b0a 100644 --- a/arch/arm/boot/dts/imx6q-marsboard.dts +++ b/arch/arm/boot/dts/imx6q-marsboard.dts @@ -73,14 +73,14 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_led>; - user1 { + led-user1 { label = "imx6:green:user1"; gpios = <&gpio5 2 GPIO_ACTIVE_LOW>; default-state = "off"; linux,default-trigger = "heartbeat"; }; - user2 { + led-user2 { label = "imx6:green:user2"; gpios = <&gpio3 28 GPIO_ACTIVE_LOW>; default-state = "off"; diff --git a/arch/arm/boot/dts/imx6q-tbs2910.dts b/arch/arm/boot/dts/imx6q-tbs2910.dts index 8daef65d5bb3..2f576e2ce73f 100644 --- a/arch/arm/boot/dts/imx6q-tbs2910.dts +++ b/arch/arm/boot/dts/imx6q-tbs2910.dts @@ -49,7 +49,7 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_gpio_leds>; - blue { + led-blue { label = "blue_status_led"; gpios = <&gpio1 2 GPIO_ACTIVE_HIGH>; default-state = "keep"; diff --git a/arch/arm/boot/dts/imx6qdl-emcon.dtsi b/arch/arm/boot/dts/imx6qdl-emcon.dtsi index 7228b894a763..ee2dd75cead6 100644 --- a/arch/arm/boot/dts/imx6qdl-emcon.dtsi +++ b/arch/arm/boot/dts/imx6qdl-emcon.dtsi @@ -46,14 +46,14 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_som_leds>; - green { + led-green { label = "som:green"; gpios = <&gpio3 0 GPIO_ACTIVE_HIGH>; linux,default-trigger = "heartbeat"; default-state = "on"; }; - red { + led-red { label = "som:red"; gpios = <&gpio3 1 GPIO_ACTIVE_LOW>; default-state = "keep"; diff --git a/arch/arm/boot/dts/imx6qdl-gw51xx.dtsi b/arch/arm/boot/dts/imx6qdl-gw51xx.dtsi index 069c27fab432..e75e1a5364b8 100644 --- a/arch/arm/boot/dts/imx6qdl-gw51xx.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw51xx.dtsi @@ -71,14 +71,14 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_gpio_leds>; - led0: user1 { + led0: led-user1 { label = "user1"; gpios = <&gpio4 6 GPIO_ACTIVE_HIGH>; /* MX6_PANLEDG */ default-state = "on"; linux,default-trigger = "heartbeat"; }; - led1: user2 { + led1: led-user2 { label = "user2"; gpios = <&gpio4 7 GPIO_ACTIVE_HIGH>; /* MX6_PANLEDR */ default-state = "off"; diff --git a/arch/arm/boot/dts/imx6qdl-gw52xx.dtsi b/arch/arm/boot/dts/imx6qdl-gw52xx.dtsi index 728810b9d677..47d9a8d08197 100644 --- a/arch/arm/boot/dts/imx6qdl-gw52xx.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw52xx.dtsi @@ -80,20 +80,20 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_gpio_leds>; - led0: user1 { + led0: led-user1 { label = "user1"; gpios = <&gpio4 6 GPIO_ACTIVE_HIGH>; /* MX6_PANLEDG */ default-state = "on"; linux,default-trigger = "heartbeat"; }; - led1: user2 { + led1: led-user2 { label = "user2"; gpios = <&gpio4 7 GPIO_ACTIVE_HIGH>; /* MX6_PANLEDR */ default-state = "off"; }; - led2: user3 { + led2: led-user3 { label = "user3"; gpios = <&gpio4 15 GPIO_ACTIVE_LOW>; /* MX6_LOCLED# */ default-state = "off"; diff --git a/arch/arm/boot/dts/imx6qdl-gw53xx.dtsi b/arch/arm/boot/dts/imx6qdl-gw53xx.dtsi index 6c0c109046d8..fb1d29abe099 100644 --- a/arch/arm/boot/dts/imx6qdl-gw53xx.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw53xx.dtsi @@ -80,20 +80,20 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_gpio_leds>; - led0: user1 { + led0: led-user1 { label = "user1"; gpios = <&gpio4 6 GPIO_ACTIVE_HIGH>; /* MX6_PANLEDG */ default-state = "on"; linux,default-trigger = "heartbeat"; }; - led1: user2 { + led1: led-user2 { label = "user2"; gpios = <&gpio4 7 GPIO_ACTIVE_HIGH>; /* MX6_PANLEDR */ default-state = "off"; }; - led2: user3 { + led2: led-user3 { label = "user3"; gpios = <&gpio4 15 GPIO_ACTIVE_LOW>; /* MX6_LOCLED# */ default-state = "off"; diff --git a/arch/arm/boot/dts/imx6qdl-gw54xx.dtsi b/arch/arm/boot/dts/imx6qdl-gw54xx.dtsi index a9b04f9f1c2b..4e20cb97058e 100644 --- a/arch/arm/boot/dts/imx6qdl-gw54xx.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw54xx.dtsi @@ -81,20 +81,20 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_gpio_leds>; - led0: user1 { + led0: led-user1 { label = "user1"; gpios = <&gpio4 6 GPIO_ACTIVE_HIGH>; /* MX6_PANLEDG */ default-state = "on"; linux,default-trigger = "heartbeat"; }; - led1: user2 { + led1: led-user2 { label = "user2"; gpios = <&gpio4 7 GPIO_ACTIVE_HIGH>; /* MX6_PANLEDR */ default-state = "off"; }; - led2: user3 { + led2: led-user3 { label = "user3"; gpios = <&gpio4 15 GPIO_ACTIVE_LOW>; /* MX6_LOCLED# */ default-state = "off"; diff --git a/arch/arm/boot/dts/imx6qdl-gw551x.dtsi b/arch/arm/boot/dts/imx6qdl-gw551x.dtsi index 435dec6338fe..0fa4b8eeddee 100644 --- a/arch/arm/boot/dts/imx6qdl-gw551x.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw551x.dtsi @@ -115,7 +115,7 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_gpio_leds>; - led0: user1 { + led0: led-user1 { label = "user1"; gpios = <&gpio4 7 GPIO_ACTIVE_LOW>; default-state = "on"; diff --git a/arch/arm/boot/dts/imx6qdl-gw552x.dtsi b/arch/arm/boot/dts/imx6qdl-gw552x.dtsi index 2e61102ae694..77ae611b817a 100644 --- a/arch/arm/boot/dts/imx6qdl-gw552x.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw552x.dtsi @@ -72,20 +72,20 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_gpio_leds>; - led0: user1 { + led0: led-user1 { label = "user1"; gpios = <&gpio4 6 GPIO_ACTIVE_HIGH>; /* MX6_PANLEDG */ default-state = "on"; linux,default-trigger = "heartbeat"; }; - led1: user2 { + led1: led-user2 { label = "user2"; gpios = <&gpio4 7 GPIO_ACTIVE_HIGH>; /* MX6_PANLEDR */ default-state = "off"; }; - led2: user3 { + led2: led-user3 { label = "user3"; gpios = <&gpio4 15 GPIO_ACTIVE_LOW>; /* MX6_LOCLED# */ default-state = "off"; diff --git a/arch/arm/boot/dts/imx6qdl-gw553x.dtsi b/arch/arm/boot/dts/imx6qdl-gw553x.dtsi index 4662408b225a..7f16c602cc07 100644 --- a/arch/arm/boot/dts/imx6qdl-gw553x.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw553x.dtsi @@ -113,14 +113,14 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_gpio_leds>; - led0: user1 { + led0: led-user1 { label = "user1"; gpios = <&gpio4 10 GPIO_ACTIVE_HIGH>; /* MX6_PANLEDG */ default-state = "on"; linux,default-trigger = "heartbeat"; }; - led1: user2 { + led1: led-user2 { label = "user2"; gpios = <&gpio4 11 GPIO_ACTIVE_HIGH>; /* MX6_PANLEDR */ default-state = "off"; diff --git a/arch/arm/boot/dts/imx6qdl-gw560x.dtsi b/arch/arm/boot/dts/imx6qdl-gw560x.dtsi index 4b81a975c979..46cf4080fec3 100644 --- a/arch/arm/boot/dts/imx6qdl-gw560x.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw560x.dtsi @@ -139,20 +139,20 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_gpio_leds>; - led0: user1 { + led0: led-user1 { label = "user1"; gpios = <&gpio4 6 GPIO_ACTIVE_HIGH>; /* MX6_PANLEDG */ default-state = "on"; linux,default-trigger = "heartbeat"; }; - led1: user2 { + led1: led-user2 { label = "user2"; gpios = <&gpio4 7 GPIO_ACTIVE_HIGH>; /* MX6_PANLEDR */ default-state = "off"; }; - led2: user3 { + led2: led-user3 { label = "user3"; gpios = <&gpio4 15 GPIO_ACTIVE_LOW>; /* MX6_LOCLED# */ default-state = "off"; diff --git a/arch/arm/boot/dts/imx6qdl-gw5903.dtsi b/arch/arm/boot/dts/imx6qdl-gw5903.dtsi index 1fdb7ba630f1..a74cde050158 100644 --- a/arch/arm/boot/dts/imx6qdl-gw5903.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw5903.dtsi @@ -123,7 +123,7 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_gpio_leds>; - led0: user1 { + led0: led-user1 { label = "user1"; gpios = <&gpio6 14 GPIO_ACTIVE_LOW>; /* MX6_LOCLED# */ default-state = "off"; diff --git a/arch/arm/boot/dts/imx6qdl-gw5904.dtsi b/arch/arm/boot/dts/imx6qdl-gw5904.dtsi index 612b6e068e28..9fc79af2bc9a 100644 --- a/arch/arm/boot/dts/imx6qdl-gw5904.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw5904.dtsi @@ -120,20 +120,20 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_gpio_leds>; - led0: user1 { + led0: led-user1 { label = "user1"; gpios = <&gpio4 6 GPIO_ACTIVE_HIGH>; /* MX6_PANLEDG */ default-state = "on"; linux,default-trigger = "heartbeat"; }; - led1: user2 { + led1: led-user2 { label = "user2"; gpios = <&gpio4 7 GPIO_ACTIVE_HIGH>; /* MX6_PANLEDR */ default-state = "off"; }; - led2: user3 { + led2: led-user3 { label = "user3"; gpios = <&gpio4 15 GPIO_ACTIVE_LOW>; /* MX6_LOCLED# */ default-state = "off"; diff --git a/arch/arm/boot/dts/imx6qdl-gw5907.dtsi b/arch/arm/boot/dts/imx6qdl-gw5907.dtsi index fcd3bdfd6182..955a51226eda 100644 --- a/arch/arm/boot/dts/imx6qdl-gw5907.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw5907.dtsi @@ -71,14 +71,14 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_gpio_leds>; - led0: user1 { + led0: led-user1 { label = "user1"; gpios = <&gpio4 6 GPIO_ACTIVE_HIGH>; /* MX6_PANLEDG */ default-state = "on"; linux,default-trigger = "heartbeat"; }; - led1: user2 { + led1: led-user2 { label = "user2"; gpios = <&gpio4 7 GPIO_ACTIVE_HIGH>; /* MX6_PANLEDR */ default-state = "off"; diff --git a/arch/arm/boot/dts/imx6qdl-gw5910.dtsi b/arch/arm/boot/dts/imx6qdl-gw5910.dtsi index 6bb4855d13ce..218d6e667ed2 100644 --- a/arch/arm/boot/dts/imx6qdl-gw5910.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw5910.dtsi @@ -74,20 +74,20 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_gpio_leds>; - led0: user1 { + led0: led-user1 { label = "user1"; gpios = <&gpio4 6 GPIO_ACTIVE_HIGH>; /* MX6_PANLEDG */ default-state = "on"; linux,default-trigger = "heartbeat"; }; - led1: user2 { + led1: led-user2 { label = "user2"; gpios = <&gpio4 7 GPIO_ACTIVE_HIGH>; /* MX6_PANLEDR */ default-state = "off"; }; - led2: user3 { + led2: led-user3 { label = "user3"; gpios = <&gpio4 15 GPIO_ACTIVE_LOW>; /* MX6_LOCLED# */ default-state = "off"; diff --git a/arch/arm/boot/dts/imx6qdl-gw5912.dtsi b/arch/arm/boot/dts/imx6qdl-gw5912.dtsi index 0415bcb41640..40e235e315cc 100644 --- a/arch/arm/boot/dts/imx6qdl-gw5912.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw5912.dtsi @@ -72,20 +72,20 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_gpio_leds>; - led0: user1 { + led0: led-user1 { label = "user1"; gpios = <&gpio4 6 GPIO_ACTIVE_HIGH>; /* MX6_PANLEDG */ default-state = "on"; linux,default-trigger = "heartbeat"; }; - led1: user2 { + led1: led-user2 { label = "user2"; gpios = <&gpio4 7 GPIO_ACTIVE_HIGH>; /* MX6_PANLEDR */ default-state = "off"; }; - led2: user3 { + led2: led-user3 { label = "user3"; gpios = <&gpio4 15 GPIO_ACTIVE_LOW>; /* MX6_LOCLED# */ default-state = "off"; diff --git a/arch/arm/boot/dts/imx6qdl-gw5913.dtsi b/arch/arm/boot/dts/imx6qdl-gw5913.dtsi index 696427b487f0..82f47c295b08 100644 --- a/arch/arm/boot/dts/imx6qdl-gw5913.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw5913.dtsi @@ -71,14 +71,14 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_gpio_leds>; - led0: user1 { + led0: led-user1 { label = "user1"; gpios = <&gpio4 6 GPIO_ACTIVE_HIGH>; /* MX6_PANLEDG */ default-state = "on"; linux,default-trigger = "heartbeat"; }; - led1: user2 { + led1: led-user2 { label = "user2"; gpios = <&gpio4 7 GPIO_ACTIVE_HIGH>; /* MX6_PANLEDR */ default-state = "off"; diff --git a/arch/arm/boot/dts/imx6qdl-nit6xlite.dtsi b/arch/arm/boot/dts/imx6qdl-nit6xlite.dtsi index a53a5d0766a5..6d4eab1942b9 100644 --- a/arch/arm/boot/dts/imx6qdl-nit6xlite.dtsi +++ b/arch/arm/boot/dts/imx6qdl-nit6xlite.dtsi @@ -85,31 +85,31 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_leds>; - j14-pin1 { + led-j14-pin1 { gpios = <&gpio1 2 GPIO_ACTIVE_LOW>; retain-state-suspended; default-state = "off"; }; - j14-pin3 { + led-j14-pin3 { gpios = <&gpio1 3 GPIO_ACTIVE_LOW>; retain-state-suspended; default-state = "off"; }; - j14-pins8-9 { + led-j14-pins8-9 { gpios = <&gpio3 29 GPIO_ACTIVE_LOW>; retain-state-suspended; default-state = "off"; }; - j46-pin2 { + led-j46-pin2 { gpios = <&gpio1 7 GPIO_ACTIVE_LOW>; retain-state-suspended; default-state = "off"; }; - j46-pin3 { + led-j46-pin3 { gpios = <&gpio1 8 GPIO_ACTIVE_LOW>; retain-state-suspended; default-state = "off"; diff --git a/arch/arm/boot/dts/imx6qdl-nitrogen6_max.dtsi b/arch/arm/boot/dts/imx6qdl-nitrogen6_max.dtsi index 57c21a01f126..81a9a302aec1 100644 --- a/arch/arm/boot/dts/imx6qdl-nitrogen6_max.dtsi +++ b/arch/arm/boot/dts/imx6qdl-nitrogen6_max.dtsi @@ -181,13 +181,13 @@ leds { compatible = "gpio-leds"; - speaker-enable { + led-speaker-enable { gpios = <&gpio1 29 GPIO_ACTIVE_HIGH>; retain-state-suspended; default-state = "off"; }; - ttymxc4-rs232 { + led-ttymxc4-rs232 { gpios = <&gpio6 10 GPIO_ACTIVE_HIGH>; retain-state-suspended; default-state = "on"; diff --git a/arch/arm/boot/dts/imx6qdl-phytec-mira.dtsi b/arch/arm/boot/dts/imx6qdl-phytec-mira.dtsi index 120d6e997a4c..1ca4d219609f 100644 --- a/arch/arm/boot/dts/imx6qdl-phytec-mira.dtsi +++ b/arch/arm/boot/dts/imx6qdl-phytec-mira.dtsi @@ -25,17 +25,17 @@ pinctrl-0 = <&pinctrl_gpioleds>; status = "disabled"; - red { + led-red { label = "phyboard-mira:red"; gpios = <&gpio5 22 GPIO_ACTIVE_HIGH>; }; - green { + led-green { label = "phyboard-mira:green"; gpios = <&gpio5 23 GPIO_ACTIVE_HIGH>; }; - blue { + led-blue { label = "phyboard-mira:blue"; gpios = <&gpio5 24 GPIO_ACTIVE_HIGH>; linux,default-trigger = "mmc0"; @@ -182,7 +182,7 @@ pinctrl-0 = <&pinctrl_rtc_int>; reg = <0x68>; interrupt-parent = <&gpio7>; - interrupts = <8 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <8 IRQ_TYPE_LEVEL_LOW>; status = "disabled"; }; }; diff --git a/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi b/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi index 768bc0e3a2b3..80adb2a02cc9 100644 --- a/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi +++ b/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi @@ -47,12 +47,12 @@ pinctrl-0 = <&pinctrl_leds>; compatible = "gpio-leds"; - led_green: green { + led_green: led-green { label = "phyflex:green"; gpios = <&gpio1 30 0>; }; - led_red: red { + led_red: led-red { label = "phyflex:red"; gpios = <&gpio2 31 0>; }; diff --git a/arch/arm/boot/dts/imx6qdl-prti6q.dtsi b/arch/arm/boot/dts/imx6qdl-prti6q.dtsi index f0db0d4471f4..36f84f4da6b0 100644 --- a/arch/arm/boot/dts/imx6qdl-prti6q.dtsi +++ b/arch/arm/boot/dts/imx6qdl-prti6q.dtsi @@ -69,6 +69,7 @@ vbus-supply = <®_usb_h1_vbus>; phy_type = "utmi"; dr_mode = "host"; + disable-over-current; status = "okay"; }; @@ -78,10 +79,18 @@ pinctrl-0 = <&pinctrl_usbotg>; phy_type = "utmi"; dr_mode = "host"; - disable-over-current; + over-current-active-low; status = "okay"; }; +&usbphynop1 { + status = "disabled"; +}; + +&usbphynop2 { + status = "disabled"; +}; + &usdhc1 { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_usdhc1>; diff --git a/arch/arm/boot/dts/imx6qdl-rex.dtsi b/arch/arm/boot/dts/imx6qdl-rex.dtsi index de514eb5aa99..f804ff95a6ad 100644 --- a/arch/arm/boot/dts/imx6qdl-rex.dtsi +++ b/arch/arm/boot/dts/imx6qdl-rex.dtsi @@ -55,7 +55,7 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_led>; - led0: usr { + led0: led-usr { label = "usr"; gpios = <&gpio1 2 GPIO_ACTIVE_LOW>; default-state = "off"; diff --git a/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi b/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi index 3dbb460ef102..10886a1461bf 100644 --- a/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi +++ b/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi @@ -21,7 +21,7 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_gpio_leds>; - user { + led-user { label = "debug"; gpios = <&gpio5 15 GPIO_ACTIVE_HIGH>; }; diff --git a/arch/arm/boot/dts/imx6qdl-sabresd.dtsi b/arch/arm/boot/dts/imx6qdl-sabresd.dtsi index 37482a9023fc..bcb83d52e26e 100644 --- a/arch/arm/boot/dts/imx6qdl-sabresd.dtsi +++ b/arch/arm/boot/dts/imx6qdl-sabresd.dtsi @@ -130,7 +130,7 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_gpio_leds>; - red { + led-red { gpios = <&gpio1 2 0>; default-state = "on"; }; diff --git a/arch/arm/boot/dts/imx6qdl-ts7970.dtsi b/arch/arm/boot/dts/imx6qdl-ts7970.dtsi index c096d25a6f5b..1e0a041e9f60 100644 --- a/arch/arm/boot/dts/imx6qdl-ts7970.dtsi +++ b/arch/arm/boot/dts/imx6qdl-ts7970.dtsi @@ -73,13 +73,13 @@ default-state = "off"; }; - en-usb-5v { + en-usb-5v-led { label = "en-usb-5v"; gpios = <&gpio2 22 GPIO_ACTIVE_HIGH>; default-state = "on"; }; - sel_dc_usb { + sel-dc-usb-led { label = "sel_dc_usb"; gpios = <&gpio5 17 GPIO_ACTIVE_HIGH>; default-state = "off"; diff --git a/arch/arm/boot/dts/imx6qdl-tx6.dtsi b/arch/arm/boot/dts/imx6qdl-tx6.dtsi index f41f86a76ea9..a197bac95cba 100644 --- a/arch/arm/boot/dts/imx6qdl-tx6.dtsi +++ b/arch/arm/boot/dts/imx6qdl-tx6.dtsi @@ -92,7 +92,7 @@ leds { compatible = "gpio-leds"; - user_led: user { + user_led: led-user { label = "Heartbeat"; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_user_led>; diff --git a/arch/arm/boot/dts/imx6sl-evk.dts b/arch/arm/boot/dts/imx6sl-evk.dts index f16c830f1e91..dc5d596c18db 100644 --- a/arch/arm/boot/dts/imx6sl-evk.dts +++ b/arch/arm/boot/dts/imx6sl-evk.dts @@ -33,7 +33,7 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_led>; - user { + led-user { label = "debug"; gpios = <&gpio3 20 GPIO_ACTIVE_HIGH>; linux,default-trigger = "heartbeat"; diff --git a/arch/arm/boot/dts/imx6sll-evk.dts b/arch/arm/boot/dts/imx6sll-evk.dts index 32b3d82fec53..269092ac881c 100644 --- a/arch/arm/boot/dts/imx6sll-evk.dts +++ b/arch/arm/boot/dts/imx6sll-evk.dts @@ -37,7 +37,7 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_led>; - user { + led-user { label = "debug"; gpios = <&gpio2 4 GPIO_ACTIVE_HIGH>; linux,default-trigger = "heartbeat"; diff --git a/arch/arm/boot/dts/imx6sll.dtsi b/arch/arm/boot/dts/imx6sll.dtsi index 2873369a57c0..3659fd5ecfa6 100644 --- a/arch/arm/boot/dts/imx6sll.dtsi +++ b/arch/arm/boot/dts/imx6sll.dtsi @@ -552,7 +552,7 @@ reg = <0x020ca000 0x1000>; interrupts = <GIC_SPI 41 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clks IMX6SLL_CLK_USBPHY2>; - phy-reg_3p0-supply = <®_3p0>; + phy-3p0-supply = <®_3p0>; fsl,anatop = <&anatop>; }; diff --git a/arch/arm/boot/dts/imx6sx-sabreauto.dts b/arch/arm/boot/dts/imx6sx-sabreauto.dts index 83ee97252ff1..b0c27b9b0244 100644 --- a/arch/arm/boot/dts/imx6sx-sabreauto.dts +++ b/arch/arm/boot/dts/imx6sx-sabreauto.dts @@ -20,7 +20,7 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_led>; - user { + led-user { label = "debug"; gpios = <&gpio1 24 GPIO_ACTIVE_HIGH>; linux,default-trigger = "heartbeat"; diff --git a/arch/arm/boot/dts/imx6sx-udoo-neo.dtsi b/arch/arm/boot/dts/imx6sx-udoo-neo.dtsi index c84ea1fac5e9..725d0b5cb55f 100644 --- a/arch/arm/boot/dts/imx6sx-udoo-neo.dtsi +++ b/arch/arm/boot/dts/imx6sx-udoo-neo.dtsi @@ -15,14 +15,14 @@ leds { compatible = "gpio-leds"; - red { + led-red { label = "udoo-neo:red:mmc"; gpios = <&gpio6 0 GPIO_ACTIVE_HIGH>; default-state = "off"; linux,default-trigger = "mmc0"; }; - orange { + led-orange { label = "udoo-neo:orange:user"; gpios = <&gpio4 6 GPIO_ACTIVE_HIGH>; default-state = "keep"; diff --git a/arch/arm/boot/dts/imx6sx.dtsi b/arch/arm/boot/dts/imx6sx.dtsi index abc3572d699e..1f1053a898fb 100644 --- a/arch/arm/boot/dts/imx6sx.dtsi +++ b/arch/arm/boot/dts/imx6sx.dtsi @@ -981,6 +981,8 @@ <&clks IMX6SX_CLK_USDHC1>; clock-names = "ipg", "ahb", "per"; bus-width = <4>; + fsl,tuning-start-tap = <20>; + fsl,tuning-step= <2>; status = "disabled"; }; @@ -993,6 +995,8 @@ <&clks IMX6SX_CLK_USDHC2>; clock-names = "ipg", "ahb", "per"; bus-width = <4>; + fsl,tuning-start-tap = <20>; + fsl,tuning-step= <2>; status = "disabled"; }; @@ -1005,6 +1009,8 @@ <&clks IMX6SX_CLK_USDHC3>; clock-names = "ipg", "ahb", "per"; bus-width = <4>; + fsl,tuning-start-tap = <20>; + fsl,tuning-step= <2>; status = "disabled"; }; diff --git a/arch/arm/boot/dts/imx6ul-phytec-phycore-som.dtsi b/arch/arm/boot/dts/imx6ul-phytec-phycore-som.dtsi index 3cddc68917a0..e4d2652a75c0 100644 --- a/arch/arm/boot/dts/imx6ul-phytec-phycore-som.dtsi +++ b/arch/arm/boot/dts/imx6ul-phytec-phycore-som.dtsi @@ -30,7 +30,7 @@ pinctrl-0 = <&pinctrl_gpioleds_som>; compatible = "gpio-leds"; - phycore-green { + led-phycore-green { gpios = <&gpio5 4 GPIO_ACTIVE_HIGH>; linux,default-trigger = "heartbeat"; }; diff --git a/arch/arm/boot/dts/imx6ul-tx6ul.dtsi b/arch/arm/boot/dts/imx6ul-tx6ul.dtsi index 15ee0275feaf..70cef5e817bd 100644 --- a/arch/arm/boot/dts/imx6ul-tx6ul.dtsi +++ b/arch/arm/boot/dts/imx6ul-tx6ul.dtsi @@ -131,7 +131,7 @@ leds { compatible = "gpio-leds"; - user_led: user { + user_led: led-user { label = "Heartbeat"; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_led>; diff --git a/arch/arm/include/asm/bugs.h b/arch/arm/include/asm/bugs.h index 97a312ba0840..fe385551edec 100644 --- a/arch/arm/include/asm/bugs.h +++ b/arch/arm/include/asm/bugs.h @@ -1,7 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * arch/arm/include/asm/bugs.h - * * Copyright (C) 1995-2003 Russell King */ #ifndef __ASM_BUGS_H @@ -10,10 +8,8 @@ extern void check_writebuffer_bugs(void); #ifdef CONFIG_MMU -extern void check_bugs(void); extern void check_other_bugs(void); #else -#define check_bugs() do { } while (0) #define check_other_bugs() do { } while (0) #endif diff --git a/arch/arm/kernel/bugs.c b/arch/arm/kernel/bugs.c index 14c8dbbb7d2d..087bce6ec8e9 100644 --- a/arch/arm/kernel/bugs.c +++ b/arch/arm/kernel/bugs.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/init.h> +#include <linux/cpu.h> #include <asm/bugs.h> #include <asm/proc-fns.h> @@ -11,7 +12,7 @@ void check_other_bugs(void) #endif } -void __init check_bugs(void) +void __init arch_cpu_finalize_init(void) { check_writebuffer_bugs(); check_other_bugs(); diff --git a/arch/arm/kernel/module-plts.c b/arch/arm/kernel/module-plts.c index 1fc309b41f94..8d809724cde5 100644 --- a/arch/arm/kernel/module-plts.c +++ b/arch/arm/kernel/module-plts.c @@ -256,7 +256,7 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, /* sort by type and symbol index */ sort(rels, numrels, sizeof(Elf32_Rel), cmp_rel, NULL); - if (strncmp(secstrings + dstsec->sh_name, ".init", 5) != 0) + if (!module_init_layout_section(secstrings + dstsec->sh_name)) core_plts += count_plts(syms, dstsec->sh_addr, rels, numrels, s->sh_info); else diff --git a/arch/arm/mach-pxa/sharpsl_pm.c b/arch/arm/mach-pxa/sharpsl_pm.c index a829baf8d922..05c0a0f6fe63 100644 --- a/arch/arm/mach-pxa/sharpsl_pm.c +++ b/arch/arm/mach-pxa/sharpsl_pm.c @@ -220,8 +220,6 @@ void sharpsl_battery_kick(void) { schedule_delayed_work(&sharpsl_bat, msecs_to_jiffies(125)); } -EXPORT_SYMBOL(sharpsl_battery_kick); - static void sharpsl_battery_thread(struct work_struct *private_) { diff --git a/arch/arm/mach-pxa/spitz.c b/arch/arm/mach-pxa/spitz.c index 9964729cd428..937f56bbaf6c 100644 --- a/arch/arm/mach-pxa/spitz.c +++ b/arch/arm/mach-pxa/spitz.c @@ -9,7 +9,6 @@ */ #include <linux/kernel.h> -#include <linux/module.h> /* symbol_get ; symbol_put */ #include <linux/platform_device.h> #include <linux/delay.h> #include <linux/gpio_keys.h> @@ -510,17 +509,6 @@ static struct ads7846_platform_data spitz_ads7846_info = { .wait_for_sync = spitz_ads7846_wait_for_hsync, }; -static void spitz_bl_kick_battery(void) -{ - void (*kick_batt)(void); - - kick_batt = symbol_get(sharpsl_battery_kick); - if (kick_batt) { - kick_batt(); - symbol_put(sharpsl_battery_kick); - } -} - static struct gpiod_lookup_table spitz_lcdcon_gpio_table = { .dev_id = "spi2.1", .table = { @@ -548,7 +536,7 @@ static struct corgi_lcd_platform_data spitz_lcdcon_info = { .max_intensity = 0x2f, .default_intensity = 0x1f, .limit_mask = 0x0b, - .kick_battery = spitz_bl_kick_battery, + .kick_battery = sharpsl_battery_kick, }; static struct spi_board_info spitz_spi_devices[] = { diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts index 48424e459f12..15b5651b88d0 100644 --- a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts +++ b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts @@ -128,7 +128,7 @@ status = "okay"; clock-frequency = <100000>; i2c-sda-falling-time-ns = <890>; /* hcnt */ - i2c-sdl-falling-time-ns = <890>; /* lcnt */ + i2c-scl-falling-time-ns = <890>; /* lcnt */ adc@14 { compatible = "lltc,ltc2497"; diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts index 847a7c01f5af..fcf640de90b6 100644 --- a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts +++ b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts @@ -141,7 +141,7 @@ status = "okay"; clock-frequency = <100000>; i2c-sda-falling-time-ns = <890>; /* hcnt */ - i2c-sdl-falling-time-ns = <890>; /* lcnt */ + i2c-scl-falling-time-ns = <890>; /* lcnt */ adc@14 { compatible = "lltc,ltc2497"; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-phyboard-polis-rdk.dts b/arch/arm64/boot/dts/freescale/imx8mm-phyboard-polis-rdk.dts index 4a3df2b77b0b..6720ddf59783 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-phyboard-polis-rdk.dts +++ b/arch/arm64/boot/dts/freescale/imx8mm-phyboard-polis-rdk.dts @@ -141,7 +141,7 @@ }; &gpio1 { - gpio-line-names = "nINT_ETHPHY", "LED_RED", "WDOG_INT", "X_RTC_INT", + gpio-line-names = "", "LED_RED", "WDOG_INT", "X_RTC_INT", "", "", "", "RESET_ETHPHY", "CAN_nINT", "CAN_EN", "nENABLE_FLATLINK", "", "USB_OTG_VBUS_EN", "", "LED_GREEN", "LED_BLUE"; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-phycore-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-phycore-som.dtsi index 995b44efb1b6..9d9b103c79c7 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-phycore-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-phycore-som.dtsi @@ -111,7 +111,7 @@ }; &gpio1 { - gpio-line-names = "nINT_ETHPHY", "", "WDOG_INT", "X_RTC_INT", + gpio-line-names = "", "", "WDOG_INT", "X_RTC_INT", "", "", "", "RESET_ETHPHY", "", "", "nENABLE_FLATLINK"; }; @@ -210,7 +210,7 @@ }; }; - reg_vdd_gpu: buck3 { + reg_vdd_vpu: buck3 { regulator-always-on; regulator-boot-on; regulator-max-microvolt = <1000000>; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7903.dts b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7903.dts index 8e861b920d09..7c9b60f4da92 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7903.dts +++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7903.dts @@ -559,6 +559,10 @@ status = "okay"; }; +&disp_blk_ctrl { + status = "disabled"; +}; + &pgc_mipi { status = "disabled"; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7904.dts b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7904.dts index a67771d02146..46a07dfc0086 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7904.dts +++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7904.dts @@ -617,6 +617,10 @@ status = "okay"; }; +&disp_blk_ctrl { + status = "disabled"; +}; + &pgc_mipi { status = "disabled"; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm.dtsi b/arch/arm64/boot/dts/freescale/imx8mm.dtsi index 420ba0d6f134..12c82bb1bb7a 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm.dtsi @@ -1145,10 +1145,9 @@ compatible = "fsl,imx8mm-mipi-csi2"; reg = <0x32e30000 0x1000>; interrupts = <GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH>; - assigned-clocks = <&clk IMX8MM_CLK_CSI1_CORE>, - <&clk IMX8MM_CLK_CSI1_PHY_REF>; - assigned-clock-parents = <&clk IMX8MM_SYS_PLL2_1000M>, - <&clk IMX8MM_SYS_PLL2_1000M>; + assigned-clocks = <&clk IMX8MM_CLK_CSI1_CORE>; + assigned-clock-parents = <&clk IMX8MM_SYS_PLL2_1000M>; + clock-frequency = <333000000>; clocks = <&clk IMX8MM_CLK_DISP_APB_ROOT>, <&clk IMX8MM_CLK_CSI1_ROOT>, diff --git a/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi index d053ef302fb8..faafefe562e4 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi @@ -351,7 +351,7 @@ MX8MN_IOMUXC_ENET_RXC_ENET1_RGMII_RXC 0x91 MX8MN_IOMUXC_ENET_RX_CTL_ENET1_RGMII_RX_CTL 0x91 MX8MN_IOMUXC_ENET_TX_CTL_ENET1_RGMII_TX_CTL 0x1f - MX8MN_IOMUXC_GPIO1_IO09_GPIO1_IO9 0x19 + MX8MN_IOMUXC_GPIO1_IO09_GPIO1_IO9 0x159 >; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mq.dtsi b/arch/arm64/boot/dts/freescale/imx8mq.dtsi index 4724ed0cbff9..bf8f02c1535c 100644 --- a/arch/arm64/boot/dts/freescale/imx8mq.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mq.dtsi @@ -756,7 +756,7 @@ <&clk IMX8MQ_SYS1_PLL_800M>, <&clk IMX8MQ_VPU_PLL>; assigned-clock-rates = <600000000>, - <600000000>, + <300000000>, <800000000>, <0>; }; diff --git a/arch/arm64/boot/dts/freescale/imx93.dtsi b/arch/arm64/boot/dts/freescale/imx93.dtsi index 8ab9f8194702..c2f60d41d6fd 100644 --- a/arch/arm64/boot/dts/freescale/imx93.dtsi +++ b/arch/arm64/boot/dts/freescale/imx93.dtsi @@ -254,7 +254,7 @@ anatop: anatop@44480000 { compatible = "fsl,imx93-anatop", "syscon"; - reg = <0x44480000 0x10000>; + reg = <0x44480000 0x2000>; }; }; diff --git a/arch/arm64/boot/dts/qcom/qrb5165-rb5.dts b/arch/arm64/boot/dts/qcom/qrb5165-rb5.dts index bf8077a1cf9a..9731a7c63d53 100644 --- a/arch/arm64/boot/dts/qcom/qrb5165-rb5.dts +++ b/arch/arm64/boot/dts/qcom/qrb5165-rb5.dts @@ -121,7 +121,7 @@ }; }; - pm8150l-thermal { + pm8150l-pcb-thermal { polling-delay-passive = <0>; polling-delay = <0>; thermal-sensors = <&pm8150l_adc_tm 1>; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-rock-4c-plus.dts b/arch/arm64/boot/dts/rockchip/rk3399-rock-4c-plus.dts index f9884902f874..c3f53aa1ea4a 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-rock-4c-plus.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-rock-4c-plus.dts @@ -548,9 +548,8 @@ &sdhci { max-frequency = <150000000>; bus-width = <8>; - mmc-hs400-1_8v; + mmc-hs200-1_8v; non-removable; - mmc-hs400-enhanced-strobe; status = "okay"; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi index 1f76d3501bda..9bdc0b93001f 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi @@ -45,7 +45,7 @@ sdio_pwrseq: sdio-pwrseq { compatible = "mmc-pwrseq-simple"; clocks = <&rk808 1>; - clock-names = "ext_clock"; + clock-names = "lpo"; pinctrl-names = "default"; pinctrl-0 = <&wifi_enable_h>; reset-gpios = <&gpio0 RK_PB2 GPIO_ACTIVE_LOW>; @@ -645,9 +645,9 @@ }; &sdhci { + max-frequency = <150000000>; bus-width = <8>; - mmc-hs400-1_8v; - mmc-hs400-enhanced-strobe; + mmc-hs200-1_8v; non-removable; status = "okay"; }; diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h index 6f86b7ab6c28..d720b6f7e5f9 100644 --- a/arch/arm64/include/asm/fpsimd.h +++ b/arch/arm64/include/asm/fpsimd.h @@ -339,7 +339,7 @@ static inline int sme_max_virtualisable_vl(void) return vec_max_virtualisable_vl(ARM64_VEC_SME); } -extern void sme_alloc(struct task_struct *task); +extern void sme_alloc(struct task_struct *task, bool flush); extern unsigned int sme_get_vl(void); extern int sme_set_current_vl(unsigned long arg); extern int sme_get_current_vl(void); @@ -365,7 +365,7 @@ static inline void sme_smstart_sm(void) { } static inline void sme_smstop_sm(void) { } static inline void sme_smstop(void) { } -static inline void sme_alloc(struct task_struct *task) { } +static inline void sme_alloc(struct task_struct *task, bool flush) { } static inline void sme_setup(void) { } static inline unsigned int sme_get_vl(void) { return 0; } static inline int sme_max_vl(void) { return 0; } diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index b5a8e8b3c691..577cf444c113 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -559,6 +559,8 @@ struct kvm_vcpu_arch { #define SYSREGS_ON_CPU __vcpu_single_flag(sflags, BIT(4)) /* Software step state is Active-pending */ #define DBG_SS_ACTIVE_PENDING __vcpu_single_flag(sflags, BIT(5)) +/* WFI instruction trapped */ +#define IN_WFI __vcpu_single_flag(sflags, BIT(7)) /* Pointer to the vcpu's SVE FFR for sve_{save,load}_state() */ diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 59aaf2e68833..8cd59d387b90 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -634,7 +634,7 @@ static void fpsimd_to_sve(struct task_struct *task) void *sst = task->thread.sve_state; struct user_fpsimd_state const *fst = &task->thread.uw.fpsimd_state; - if (!system_supports_sve()) + if (!system_supports_sve() && !system_supports_sme()) return; vq = sve_vq_from_vl(thread_get_cur_vl(&task->thread)); @@ -660,7 +660,7 @@ static void sve_to_fpsimd(struct task_struct *task) unsigned int i; __uint128_t const *p; - if (!system_supports_sve()) + if (!system_supports_sve() && !system_supports_sme()) return; vl = thread_get_cur_vl(&task->thread); @@ -791,7 +791,8 @@ void sve_sync_from_fpsimd_zeropad(struct task_struct *task) void *sst = task->thread.sve_state; struct user_fpsimd_state const *fst = &task->thread.uw.fpsimd_state; - if (!test_tsk_thread_flag(task, TIF_SVE)) + if (!test_tsk_thread_flag(task, TIF_SVE) && + !thread_sm_enabled(&task->thread)) return; vq = sve_vq_from_vl(thread_get_cur_vl(&task->thread)); @@ -863,7 +864,7 @@ int vec_set_vector_length(struct task_struct *task, enum vec_type type, */ task->thread.svcr &= ~(SVCR_SM_MASK | SVCR_ZA_MASK); - clear_thread_flag(TIF_SME); + clear_tsk_thread_flag(task, TIF_SME); free_sme = true; } } @@ -1238,9 +1239,9 @@ void fpsimd_release_task(struct task_struct *dead_task) * the interest of testability and predictability, the architecture * guarantees that when ZA is enabled it will be zeroed. */ -void sme_alloc(struct task_struct *task) +void sme_alloc(struct task_struct *task, bool flush) { - if (task->thread.za_state) { + if (task->thread.za_state && flush) { memset(task->thread.za_state, 0, za_state_size(task)); return; } @@ -1459,7 +1460,7 @@ void do_sme_acc(unsigned long esr, struct pt_regs *regs) } sve_alloc(current, false); - sme_alloc(current); + sme_alloc(current, true); if (!current->thread.sve_state || !current->thread.za_state) { force_sig(SIGKILL); return; diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c index 5a0a8f552a61..c703b5db8eb1 100644 --- a/arch/arm64/kernel/module-plts.c +++ b/arch/arm64/kernel/module-plts.c @@ -7,6 +7,7 @@ #include <linux/ftrace.h> #include <linux/kernel.h> #include <linux/module.h> +#include <linux/moduleloader.h> #include <linux/sort.h> static struct plt_entry __get_adrp_add_pair(u64 dst, u64 pc, @@ -343,7 +344,7 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, if (nents) sort(rels, nents, sizeof(Elf64_Rela), cmp_rela, NULL); - if (!str_has_prefix(secstrings + dstsec->sh_name, ".init")) + if (!module_init_layout_section(secstrings + dstsec->sh_name)) core_plts += count_plts(syms, rels, numrels, sechdrs[i].sh_info, dstsec); else diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 92bc9a2d702c..f606c942f514 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -886,6 +886,13 @@ static int sve_set_common(struct task_struct *target, break; case ARM64_VEC_SME: target->thread.svcr |= SVCR_SM_MASK; + + /* + * Disable traps and ensure there is SME storage but + * preserve any currently set values in ZA/ZT. + */ + sme_alloc(target, false); + set_tsk_thread_flag(target, TIF_SME); break; default: WARN_ON_ONCE(1); @@ -937,11 +944,13 @@ static int sve_set_common(struct task_struct *target, /* * Ensure target->thread.sve_state is up to date with target's * FPSIMD regs, so that a short copyin leaves trailing - * registers unmodified. Always enable SVE even if going into - * streaming mode. + * registers unmodified. Only enable SVE if we are + * configuring normal SVE, a system with streaming SVE may not + * have normal SVE. */ fpsimd_sync_to_sve(target); - set_tsk_thread_flag(target, TIF_SVE); + if (type == ARM64_VEC_SVE) + set_tsk_thread_flag(target, TIF_SVE); BUILD_BUG_ON(SVE_PT_SVE_OFFSET != sizeof(header)); start = SVE_PT_SVE_OFFSET; @@ -1105,7 +1114,7 @@ static int za_set(struct task_struct *target, } /* Allocate/reinit ZA storage */ - sme_alloc(target); + sme_alloc(target, true); if (!target->thread.za_state) { ret = -ENOMEM; goto out; diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 43adbfa5ead7..82f4572c8ddf 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -430,7 +430,7 @@ static int restore_za_context(struct user_ctxs *user) fpsimd_flush_task_state(current); /* From now, fpsimd_thread_switch() won't touch thread.sve_state */ - sme_alloc(current); + sme_alloc(current, true); if (!current->thread.za_state) { current->thread.svcr &= ~SVCR_ZA_MASK; clear_thread_flag(TIF_SME); diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 35481d51aada..6cc380a15eb7 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -692,13 +692,15 @@ void kvm_vcpu_wfi(struct kvm_vcpu *vcpu) */ preempt_disable(); kvm_vgic_vmcr_sync(vcpu); - vgic_v4_put(vcpu, true); + vcpu_set_flag(vcpu, IN_WFI); + vgic_v4_put(vcpu); preempt_enable(); kvm_vcpu_halt(vcpu); vcpu_clear_flag(vcpu, IN_WFIT); preempt_disable(); + vcpu_clear_flag(vcpu, IN_WFI); vgic_v4_load(vcpu); preempt_enable(); } @@ -766,7 +768,7 @@ static int check_vcpu_requests(struct kvm_vcpu *vcpu) if (kvm_check_request(KVM_REQ_RELOAD_GICv4, vcpu)) { /* The distributor enable bits were changed */ preempt_disable(); - vgic_v4_put(vcpu, false); + vgic_v4_put(vcpu); vgic_v4_load(vcpu); preempt_enable(); } diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c index f86c3007a319..1f8eea53e982 100644 --- a/arch/arm64/kvm/vgic/vgic-v3.c +++ b/arch/arm64/kvm/vgic/vgic-v3.c @@ -742,7 +742,7 @@ void vgic_v3_put(struct kvm_vcpu *vcpu) { struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3; - WARN_ON(vgic_v4_put(vcpu, false)); + WARN_ON(vgic_v4_put(vcpu)); vgic_v3_vmcr_sync(vcpu); diff --git a/arch/arm64/kvm/vgic/vgic-v4.c b/arch/arm64/kvm/vgic/vgic-v4.c index c1c28fe680ba..339a55194b2c 100644 --- a/arch/arm64/kvm/vgic/vgic-v4.c +++ b/arch/arm64/kvm/vgic/vgic-v4.c @@ -336,14 +336,14 @@ void vgic_v4_teardown(struct kvm *kvm) its_vm->vpes = NULL; } -int vgic_v4_put(struct kvm_vcpu *vcpu, bool need_db) +int vgic_v4_put(struct kvm_vcpu *vcpu) { struct its_vpe *vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe; if (!vgic_supports_direct_msis(vcpu->kvm) || !vpe->resident) return 0; - return its_make_vpe_non_resident(vpe, need_db); + return its_make_vpe_non_resident(vpe, !!vcpu_get_flag(vcpu, IN_WFI)); } int vgic_v4_load(struct kvm_vcpu *vcpu) @@ -354,6 +354,9 @@ int vgic_v4_load(struct kvm_vcpu *vcpu) if (!vgic_supports_direct_msis(vcpu->kvm) || vpe->resident) return 0; + if (vcpu_get_flag(vcpu, IN_WFI)) + return 0; + /* * Before making the VPE resident, make sure the redistributor * corresponding to our current CPU expects us here. See the diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index c6e06cdc738f..283b751cbf6a 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -9,6 +9,7 @@ menu "Processor type and features" config IA64 bool select ARCH_BINFMT_ELF_EXTRA_PHDRS + select ARCH_HAS_CPU_FINALIZE_INIT select ARCH_HAS_DMA_MARK_CLEAN select ARCH_HAS_STRNCPY_FROM_USER select ARCH_HAS_STRNLEN_USER diff --git a/arch/ia64/include/asm/bugs.h b/arch/ia64/include/asm/bugs.h deleted file mode 100644 index 0d6b9bded56c..000000000000 --- a/arch/ia64/include/asm/bugs.h +++ /dev/null @@ -1,20 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * This is included by init/main.c to check for architecture-dependent bugs. - * - * Needs: - * void check_bugs(void); - * - * Based on <asm-alpha/bugs.h>. - * - * Modified 1998, 1999, 2003 - * David Mosberger-Tang <davidm@hpl.hp.com>, Hewlett-Packard Co. - */ -#ifndef _ASM_IA64_BUGS_H -#define _ASM_IA64_BUGS_H - -#include <asm/processor.h> - -extern void check_bugs (void); - -#endif /* _ASM_IA64_BUGS_H */ diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c index c05728044272..9009f1871e3b 100644 --- a/arch/ia64/kernel/setup.c +++ b/arch/ia64/kernel/setup.c @@ -1067,8 +1067,7 @@ cpu_init (void) } } -void __init -check_bugs (void) +void __init arch_cpu_finalize_init(void) { ia64_patch_mckinley_e9((unsigned long) __start___mckinley_e9_bundles, (unsigned long) __end___mckinley_e9_bundles); diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig index 7bff88118507..1fe5b2018745 100644 --- a/arch/m68k/Kconfig +++ b/arch/m68k/Kconfig @@ -4,6 +4,7 @@ config M68K default y select ARCH_32BIT_OFF_T select ARCH_HAS_BINFMT_FLAT + select ARCH_HAS_CPU_FINALIZE_INIT if MMU select ARCH_HAS_CURRENT_STACK_POINTER select ARCH_HAS_DMA_PREP_COHERENT if HAS_DMA && MMU && !COLDFIRE select ARCH_HAS_SYNC_DMA_FOR_DEVICE if HAS_DMA diff --git a/arch/m68k/include/asm/bugs.h b/arch/m68k/include/asm/bugs.h deleted file mode 100644 index 745530651e0b..000000000000 --- a/arch/m68k/include/asm/bugs.h +++ /dev/null @@ -1,21 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * include/asm-m68k/bugs.h - * - * Copyright (C) 1994 Linus Torvalds - */ - -/* - * This is included by init/main.c to check for architecture-dependent bugs. - * - * Needs: - * void check_bugs(void); - */ - -#ifdef CONFIG_MMU -extern void check_bugs(void); /* in arch/m68k/kernel/setup.c */ -#else -static void check_bugs(void) -{ -} -#endif diff --git a/arch/m68k/kernel/setup_mm.c b/arch/m68k/kernel/setup_mm.c index fbff1cea62ca..6f1ae01f322c 100644 --- a/arch/m68k/kernel/setup_mm.c +++ b/arch/m68k/kernel/setup_mm.c @@ -10,6 +10,7 @@ */ #include <linux/kernel.h> +#include <linux/cpu.h> #include <linux/mm.h> #include <linux/sched.h> #include <linux/delay.h> @@ -504,7 +505,7 @@ static int __init proc_hardware_init(void) module_init(proc_hardware_init); #endif -void check_bugs(void) +void __init arch_cpu_finalize_init(void) { #if defined(CONFIG_FPU) && !defined(CONFIG_M68KFPU_EMU) if (m68k_fputype == 0) { diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 7b0856c76c9a..cf1fbf4eaa8a 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -4,6 +4,7 @@ config MIPS default y select ARCH_32BIT_OFF_T if !64BIT select ARCH_BINFMT_ELF_STATE if MIPS_FP_SUPPORT + select ARCH_HAS_CPU_FINALIZE_INIT select ARCH_HAS_CURRENT_STACK_POINTER if !CC_IS_CLANG || CLANG_VERSION >= 140000 select ARCH_HAS_DEBUG_VIRTUAL if !64BIT select ARCH_HAS_FORTIFY_SOURCE diff --git a/arch/mips/alchemy/devboards/db1000.c b/arch/mips/alchemy/devboards/db1000.c index 2c52ee27b4f2..50de86eb8784 100644 --- a/arch/mips/alchemy/devboards/db1000.c +++ b/arch/mips/alchemy/devboards/db1000.c @@ -14,7 +14,6 @@ #include <linux/interrupt.h> #include <linux/leds.h> #include <linux/mmc/host.h> -#include <linux/module.h> #include <linux/platform_device.h> #include <linux/pm.h> #include <linux/spi/spi.h> @@ -167,12 +166,7 @@ static struct platform_device db1x00_audio_dev = { static irqreturn_t db1100_mmc_cd(int irq, void *ptr) { - void (*mmc_cd)(struct mmc_host *, unsigned long); - /* link against CONFIG_MMC=m */ - mmc_cd = symbol_get(mmc_detect_change); - mmc_cd(ptr, msecs_to_jiffies(500)); - symbol_put(mmc_detect_change); - + mmc_detect_change(ptr, msecs_to_jiffies(500)); return IRQ_HANDLED; } diff --git a/arch/mips/alchemy/devboards/db1200.c b/arch/mips/alchemy/devboards/db1200.c index 1864eb935ca5..76080c71a2a7 100644 --- a/arch/mips/alchemy/devboards/db1200.c +++ b/arch/mips/alchemy/devboards/db1200.c @@ -10,7 +10,6 @@ #include <linux/gpio.h> #include <linux/i2c.h> #include <linux/init.h> -#include <linux/module.h> #include <linux/interrupt.h> #include <linux/io.h> #include <linux/leds.h> @@ -340,14 +339,7 @@ static irqreturn_t db1200_mmc_cd(int irq, void *ptr) static irqreturn_t db1200_mmc_cdfn(int irq, void *ptr) { - void (*mmc_cd)(struct mmc_host *, unsigned long); - - /* link against CONFIG_MMC=m */ - mmc_cd = symbol_get(mmc_detect_change); - if (mmc_cd) { - mmc_cd(ptr, msecs_to_jiffies(200)); - symbol_put(mmc_detect_change); - } + mmc_detect_change(ptr, msecs_to_jiffies(200)); msleep(100); /* debounce */ if (irq == DB1200_SD0_INSERT_INT) @@ -431,14 +423,7 @@ static irqreturn_t pb1200_mmc1_cd(int irq, void *ptr) static irqreturn_t pb1200_mmc1_cdfn(int irq, void *ptr) { - void (*mmc_cd)(struct mmc_host *, unsigned long); - - /* link against CONFIG_MMC=m */ - mmc_cd = symbol_get(mmc_detect_change); - if (mmc_cd) { - mmc_cd(ptr, msecs_to_jiffies(200)); - symbol_put(mmc_detect_change); - } + mmc_detect_change(ptr, msecs_to_jiffies(200)); msleep(100); /* debounce */ if (irq == PB1200_SD1_INSERT_INT) diff --git a/arch/mips/alchemy/devboards/db1300.c b/arch/mips/alchemy/devboards/db1300.c index e70e529ddd91..ff61901329c6 100644 --- a/arch/mips/alchemy/devboards/db1300.c +++ b/arch/mips/alchemy/devboards/db1300.c @@ -17,7 +17,6 @@ #include <linux/interrupt.h> #include <linux/ata_platform.h> #include <linux/mmc/host.h> -#include <linux/module.h> #include <linux/mtd/mtd.h> #include <linux/mtd/platnand.h> #include <linux/platform_device.h> @@ -459,14 +458,7 @@ static irqreturn_t db1300_mmc_cd(int irq, void *ptr) static irqreturn_t db1300_mmc_cdfn(int irq, void *ptr) { - void (*mmc_cd)(struct mmc_host *, unsigned long); - - /* link against CONFIG_MMC=m. We can only be called once MMC core has - * initialized the controller, so symbol_get() should always succeed. - */ - mmc_cd = symbol_get(mmc_detect_change); - mmc_cd(ptr, msecs_to_jiffies(200)); - symbol_put(mmc_detect_change); + mmc_detect_change(ptr, msecs_to_jiffies(200)); msleep(100); /* debounce */ if (irq == DB1300_SD1_INSERT_INT) diff --git a/arch/mips/include/asm/bugs.h b/arch/mips/include/asm/bugs.h index d72dc6e1cf3c..8d4cf29861b8 100644 --- a/arch/mips/include/asm/bugs.h +++ b/arch/mips/include/asm/bugs.h @@ -1,17 +1,11 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* - * This is included by init/main.c to check for architecture-dependent bugs. - * * Copyright (C) 2007 Maciej W. Rozycki - * - * Needs: - * void check_bugs(void); */ #ifndef _ASM_BUGS_H #define _ASM_BUGS_H #include <linux/bug.h> -#include <linux/delay.h> #include <linux/smp.h> #include <asm/cpu.h> @@ -30,17 +24,6 @@ static inline void check_bugs_early(void) check_bugs64_early(); } -static inline void check_bugs(void) -{ - unsigned int cpu = smp_processor_id(); - - cpu_data[cpu].udelay_val = loops_per_jiffy; - check_bugs32(); - - if (IS_ENABLED(CONFIG_CPU_R4X00_BUGS64)) - check_bugs64(); -} - static inline int r4k_daddiu_bug(void) { if (!IS_ENABLED(CONFIG_CPU_R4X00_BUGS64)) diff --git a/arch/mips/include/asm/cpu-features.h b/arch/mips/include/asm/cpu-features.h index c0983130a44c..e0a4da4cfd8b 100644 --- a/arch/mips/include/asm/cpu-features.h +++ b/arch/mips/include/asm/cpu-features.h @@ -121,7 +121,24 @@ #define cpu_has_4k_cache __isa_ge_or_opt(1, MIPS_CPU_4K_CACHE) #endif #ifndef cpu_has_octeon_cache -#define cpu_has_octeon_cache 0 +#define cpu_has_octeon_cache \ +({ \ + int __res; \ + \ + switch (boot_cpu_type()) { \ + case CPU_CAVIUM_OCTEON: \ + case CPU_CAVIUM_OCTEON_PLUS: \ + case CPU_CAVIUM_OCTEON2: \ + case CPU_CAVIUM_OCTEON3: \ + __res = 1; \ + break; \ + \ + default: \ + __res = 0; \ + } \ + \ + __res; \ +}) #endif /* Don't override `cpu_has_fpu' to 1 or the "nofpu" option won't work. */ #ifndef cpu_has_fpu @@ -351,7 +368,7 @@ ({ \ int __res; \ \ - switch (current_cpu_type()) { \ + switch (boot_cpu_type()) { \ case CPU_M14KC: \ case CPU_74K: \ case CPU_1074K: \ diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index 81dbb4ef5231..7c540572f1f7 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -11,6 +11,8 @@ * Copyright (C) 2000, 2001, 2002, 2007 Maciej W. Rozycki */ #include <linux/init.h> +#include <linux/cpu.h> +#include <linux/delay.h> #include <linux/ioport.h> #include <linux/export.h> #include <linux/screen_info.h> @@ -840,3 +842,14 @@ static int __init setnocoherentio(char *str) } early_param("nocoherentio", setnocoherentio); #endif + +void __init arch_cpu_finalize_init(void) +{ + unsigned int cpu = smp_processor_id(); + + cpu_data[cpu].udelay_val = loops_per_jiffy; + check_bugs32(); + + if (IS_ENABLED(CONFIG_CPU_R4X00_BUGS64)) + check_bugs64(); +} diff --git a/arch/parisc/include/asm/bugs.h b/arch/parisc/include/asm/bugs.h deleted file mode 100644 index 0a7f9db6bd1c..000000000000 --- a/arch/parisc/include/asm/bugs.h +++ /dev/null @@ -1,20 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * include/asm-parisc/bugs.h - * - * Copyright (C) 1999 Mike Shaver - */ - -/* - * This is included by init/main.c to check for architecture-dependent bugs. - * - * Needs: - * void check_bugs(void); - */ - -#include <asm/processor.h> - -static inline void check_bugs(void) -{ -// identify_cpu(&boot_cpu_data); -} diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c index 09a34b07f02e..9915062d5243 100644 --- a/arch/parisc/kernel/sys_parisc.c +++ b/arch/parisc/kernel/sys_parisc.c @@ -24,32 +24,28 @@ #include <linux/personality.h> #include <linux/random.h> #include <linux/compat.h> +#include <linux/elf-randomize.h> -/* we construct an artificial offset for the mapping based on the physical - * address of the kernel mapping variable */ -#define GET_LAST_MMAP(filp) \ - (filp ? ((unsigned long) filp->f_mapping) >> 8 : 0UL) -#define SET_LAST_MMAP(filp, val) \ - { /* nothing */ } - -static int get_offset(unsigned int last_mmap) -{ - return (last_mmap & (SHM_COLOUR-1)) >> PAGE_SHIFT; -} +/* + * Construct an artificial page offset for the mapping based on the physical + * address of the kernel file mapping variable. + */ +#define GET_FILP_PGOFF(filp) \ + (filp ? (((unsigned long) filp->f_mapping) >> 8) \ + & ((SHM_COLOUR-1) >> PAGE_SHIFT) : 0UL) -static unsigned long shared_align_offset(unsigned int last_mmap, +static unsigned long shared_align_offset(unsigned long filp_pgoff, unsigned long pgoff) { - return (get_offset(last_mmap) + pgoff) << PAGE_SHIFT; + return (filp_pgoff + pgoff) << PAGE_SHIFT; } static inline unsigned long COLOR_ALIGN(unsigned long addr, - unsigned int last_mmap, unsigned long pgoff) + unsigned long filp_pgoff, unsigned long pgoff) { unsigned long base = (addr+SHM_COLOUR-1) & ~(SHM_COLOUR-1); unsigned long off = (SHM_COLOUR-1) & - (shared_align_offset(last_mmap, pgoff) << PAGE_SHIFT); - + shared_align_offset(filp_pgoff, pgoff); return base + off; } @@ -98,126 +94,91 @@ static unsigned long mmap_upper_limit(struct rlimit *rlim_stack) return PAGE_ALIGN(STACK_TOP - stack_base); } +enum mmap_allocation_direction {UP, DOWN}; -unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, - unsigned long len, unsigned long pgoff, unsigned long flags) +static unsigned long arch_get_unmapped_area_common(struct file *filp, + unsigned long addr, unsigned long len, unsigned long pgoff, + unsigned long flags, enum mmap_allocation_direction dir) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev; - unsigned long task_size = TASK_SIZE; - int do_color_align, last_mmap; + unsigned long filp_pgoff; + int do_color_align; struct vm_unmapped_area_info info; - if (len > task_size) + if (unlikely(len > TASK_SIZE)) return -ENOMEM; do_color_align = 0; if (filp || (flags & MAP_SHARED)) do_color_align = 1; - last_mmap = GET_LAST_MMAP(filp); + filp_pgoff = GET_FILP_PGOFF(filp); if (flags & MAP_FIXED) { - if ((flags & MAP_SHARED) && last_mmap && - (addr - shared_align_offset(last_mmap, pgoff)) + /* Even MAP_FIXED mappings must reside within TASK_SIZE */ + if (TASK_SIZE - len < addr) + return -EINVAL; + + if ((flags & MAP_SHARED) && filp && + (addr - shared_align_offset(filp_pgoff, pgoff)) & (SHM_COLOUR - 1)) return -EINVAL; - goto found_addr; + return addr; } if (addr) { - if (do_color_align && last_mmap) - addr = COLOR_ALIGN(addr, last_mmap, pgoff); + if (do_color_align) + addr = COLOR_ALIGN(addr, filp_pgoff, pgoff); else addr = PAGE_ALIGN(addr); vma = find_vma_prev(mm, addr, &prev); - if (task_size - len >= addr && + if (TASK_SIZE - len >= addr && (!vma || addr + len <= vm_start_gap(vma)) && (!prev || addr >= vm_end_gap(prev))) - goto found_addr; + return addr; } - info.flags = 0; info.length = len; + info.align_mask = do_color_align ? (PAGE_MASK & (SHM_COLOUR - 1)) : 0; + info.align_offset = shared_align_offset(filp_pgoff, pgoff); + + if (dir == DOWN) { + info.flags = VM_UNMAPPED_AREA_TOPDOWN; + info.low_limit = PAGE_SIZE; + info.high_limit = mm->mmap_base; + addr = vm_unmapped_area(&info); + if (!(addr & ~PAGE_MASK)) + return addr; + VM_BUG_ON(addr != -ENOMEM); + + /* + * A failed mmap() very likely causes application failure, + * so fall back to the bottom-up function here. This scenario + * can happen with large stack limits and large mmap() + * allocations. + */ + } + + info.flags = 0; info.low_limit = mm->mmap_legacy_base; info.high_limit = mmap_upper_limit(NULL); - info.align_mask = last_mmap ? (PAGE_MASK & (SHM_COLOUR - 1)) : 0; - info.align_offset = shared_align_offset(last_mmap, pgoff); - addr = vm_unmapped_area(&info); - -found_addr: - if (do_color_align && !last_mmap && !(addr & ~PAGE_MASK)) - SET_LAST_MMAP(filp, addr - (pgoff << PAGE_SHIFT)); - - return addr; + return vm_unmapped_area(&info); } -unsigned long -arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, - const unsigned long len, const unsigned long pgoff, - const unsigned long flags) +unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, unsigned long flags) { - struct vm_area_struct *vma, *prev; - struct mm_struct *mm = current->mm; - unsigned long addr = addr0; - int do_color_align, last_mmap; - struct vm_unmapped_area_info info; - - /* requested length too big for entire address space */ - if (len > TASK_SIZE) - return -ENOMEM; - - do_color_align = 0; - if (filp || (flags & MAP_SHARED)) - do_color_align = 1; - last_mmap = GET_LAST_MMAP(filp); - - if (flags & MAP_FIXED) { - if ((flags & MAP_SHARED) && last_mmap && - (addr - shared_align_offset(last_mmap, pgoff)) - & (SHM_COLOUR - 1)) - return -EINVAL; - goto found_addr; - } - - /* requesting a specific address */ - if (addr) { - if (do_color_align && last_mmap) - addr = COLOR_ALIGN(addr, last_mmap, pgoff); - else - addr = PAGE_ALIGN(addr); - - vma = find_vma_prev(mm, addr, &prev); - if (TASK_SIZE - len >= addr && - (!vma || addr + len <= vm_start_gap(vma)) && - (!prev || addr >= vm_end_gap(prev))) - goto found_addr; - } - - info.flags = VM_UNMAPPED_AREA_TOPDOWN; - info.length = len; - info.low_limit = PAGE_SIZE; - info.high_limit = mm->mmap_base; - info.align_mask = last_mmap ? (PAGE_MASK & (SHM_COLOUR - 1)) : 0; - info.align_offset = shared_align_offset(last_mmap, pgoff); - addr = vm_unmapped_area(&info); - if (!(addr & ~PAGE_MASK)) - goto found_addr; - VM_BUG_ON(addr != -ENOMEM); - - /* - * A failed mmap() very likely causes application failure, - * so fall back to the bottom-up function here. This scenario - * can happen with large stack limits and large mmap() - * allocations. - */ - return arch_get_unmapped_area(filp, addr0, len, pgoff, flags); - -found_addr: - if (do_color_align && !last_mmap && !(addr & ~PAGE_MASK)) - SET_LAST_MMAP(filp, addr - (pgoff << PAGE_SHIFT)); + return arch_get_unmapped_area_common(filp, + addr, len, pgoff, flags, UP); +} - return addr; +unsigned long arch_get_unmapped_area_topdown(struct file *filp, + unsigned long addr, unsigned long len, unsigned long pgoff, + unsigned long flags) +{ + return arch_get_unmapped_area_common(filp, + addr, len, pgoff, flags, DOWN); } static int mmap_is_legacy(void) @@ -379,7 +340,7 @@ asmlinkage long parisc_fallocate(int fd, int mode, u32 offhi, u32 offlo, ((u64)lenhi << 32) | lenlo); } -long parisc_personality(unsigned long personality) +asmlinkage long parisc_personality(unsigned long personality) { long err; diff --git a/arch/powerpc/include/asm/bugs.h b/arch/powerpc/include/asm/bugs.h deleted file mode 100644 index 01b8f6ca4dbb..000000000000 --- a/arch/powerpc/include/asm/bugs.h +++ /dev/null @@ -1,15 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -#ifndef _ASM_POWERPC_BUGS_H -#define _ASM_POWERPC_BUGS_H - -/* - */ - -/* - * This file is included by 'init/main.c' to check for - * architecture-dependent bugs. - */ - -static inline void check_bugs(void) { } - -#endif /* _ASM_POWERPC_BUGS_H */ diff --git a/arch/powerpc/include/asm/word-at-a-time.h b/arch/powerpc/include/asm/word-at-a-time.h index 46c31fb8748d..30a12d208687 100644 --- a/arch/powerpc/include/asm/word-at-a-time.h +++ b/arch/powerpc/include/asm/word-at-a-time.h @@ -34,7 +34,7 @@ static inline long find_zero(unsigned long mask) return leading_zero_bits >> 3; } -static inline bool has_zero(unsigned long val, unsigned long *data, const struct word_at_a_time *c) +static inline unsigned long has_zero(unsigned long val, unsigned long *data, const struct word_at_a_time *c) { unsigned long rhs = val | c->low_bits; *data = rhs; diff --git a/arch/powerpc/kernel/rtas_flash.c b/arch/powerpc/kernel/rtas_flash.c index bc817a5619d6..43c635ddba70 100644 --- a/arch/powerpc/kernel/rtas_flash.c +++ b/arch/powerpc/kernel/rtas_flash.c @@ -710,9 +710,9 @@ static int __init rtas_flash_init(void) if (!rtas_validate_flash_data.buf) return -ENOMEM; - flash_block_cache = kmem_cache_create("rtas_flash_cache", - RTAS_BLK_SIZE, RTAS_BLK_SIZE, 0, - NULL); + flash_block_cache = kmem_cache_create_usercopy("rtas_flash_cache", + RTAS_BLK_SIZE, RTAS_BLK_SIZE, + 0, 0, RTAS_BLK_SIZE, NULL); if (!flash_block_cache) { printk(KERN_ERR "%s: failed to create block cache\n", __func__); diff --git a/arch/powerpc/kernel/trace/ftrace_mprofile.S b/arch/powerpc/kernel/trace/ftrace_mprofile.S index d031093bc436..6f9c2dea905b 100644 --- a/arch/powerpc/kernel/trace/ftrace_mprofile.S +++ b/arch/powerpc/kernel/trace/ftrace_mprofile.S @@ -33,6 +33,9 @@ * and then arrange for the ftrace function to be called. */ .macro ftrace_regs_entry allregs + /* Create a minimal stack frame for representing B */ + PPC_STLU r1, -STACK_FRAME_MIN_SIZE(r1) + /* Create our stack frame + pt_regs */ PPC_STLU r1,-SWITCH_FRAME_SIZE(r1) @@ -42,7 +45,7 @@ #ifdef CONFIG_PPC64 /* Save the original return address in A's stack frame */ - std r0, LRSAVE+SWITCH_FRAME_SIZE(r1) + std r0, LRSAVE+SWITCH_FRAME_SIZE+STACK_FRAME_MIN_SIZE(r1) /* Ok to continue? */ lbz r3, PACA_FTRACE_ENABLED(r13) cmpdi r3, 0 @@ -77,6 +80,8 @@ mflr r7 /* Save it as pt_regs->nip */ PPC_STL r7, _NIP(r1) + /* Also save it in B's stackframe header for proper unwind */ + PPC_STL r7, LRSAVE+SWITCH_FRAME_SIZE(r1) /* Save the read LR in pt_regs->link */ PPC_STL r0, _LINK(r1) @@ -142,7 +147,7 @@ #endif /* Pop our stack frame */ - addi r1, r1, SWITCH_FRAME_SIZE + addi r1, r1, SWITCH_FRAME_SIZE+STACK_FRAME_MIN_SIZE #ifdef CONFIG_LIVEPATCH_64 /* Based on the cmpd above, if the NIP was altered handle livepatch */ diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index fe1b83020e0d..0ec5b45b1e86 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -314,8 +314,7 @@ void __ref vmemmap_free(unsigned long start, unsigned long end, start = ALIGN_DOWN(start, page_size); if (altmap) { alt_start = altmap->base_pfn; - alt_end = altmap->base_pfn + altmap->reserve + - altmap->free + altmap->alloc + altmap->align; + alt_end = altmap->base_pfn + altmap->reserve + altmap->free; } pr_debug("vmemmap_free %lx...%lx\n", start, end); diff --git a/arch/powerpc/mm/kasan/Makefile b/arch/powerpc/mm/kasan/Makefile index 699eeffd9f55..f9522fd70b2f 100644 --- a/arch/powerpc/mm/kasan/Makefile +++ b/arch/powerpc/mm/kasan/Makefile @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 KASAN_SANITIZE := n +KCOV_INSTRUMENT := n obj-$(CONFIG_PPC32) += init_32.o obj-$(CONFIG_PPC_8xx) += 8xx.o diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 6bf8dc0b8f93..d702359f8ab5 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -447,24 +447,30 @@ config TOOLCHAIN_HAS_ZIHINTPAUSE config TOOLCHAIN_NEEDS_EXPLICIT_ZICSR_ZIFENCEI def_bool y # https://sourceware.org/git/?p=binutils-gdb.git;a=commit;h=aed44286efa8ae8717a77d94b51ac3614e2ca6dc - depends on AS_IS_GNU && AS_VERSION >= 23800 + # https://gcc.gnu.org/git/?p=gcc.git;a=commit;h=98416dbb0a62579d4a7a4a76bab51b5b52fec2cd + depends on AS_IS_GNU && AS_VERSION >= 23600 help - Newer binutils versions default to ISA spec version 20191213 which - moves some instructions from the I extension to the Zicsr and Zifencei - extensions. + Binutils-2.38 and GCC-12.1.0 bumped the default ISA spec to the newer + 20191213 version, which moves some instructions from the I extension to + the Zicsr and Zifencei extensions. This requires explicitly specifying + Zicsr and Zifencei when binutils >= 2.38 or GCC >= 12.1.0. Zicsr + and Zifencei are supported in binutils from version 2.36 onwards. + To make life easier, and avoid forcing toolchains that default to a + newer ISA spec to version 2.2, relax the check to binutils >= 2.36. + For clang < 17 or GCC < 11.3.0, for which this is not possible or need + special treatment, this is dealt with in TOOLCHAIN_NEEDS_OLD_ISA_SPEC. config TOOLCHAIN_NEEDS_OLD_ISA_SPEC def_bool y depends on TOOLCHAIN_NEEDS_EXPLICIT_ZICSR_ZIFENCEI # https://github.com/llvm/llvm-project/commit/22e199e6afb1263c943c0c0d4498694e15bf8a16 - depends on CC_IS_CLANG && CLANG_VERSION < 170000 + # https://gcc.gnu.org/git/?p=gcc.git;a=commit;h=d29f5d6ab513c52fd872f532c492e35ae9fd6671 + depends on (CC_IS_CLANG && CLANG_VERSION < 170000) || (CC_IS_GCC && GCC_VERSION < 110300) help - Certain versions of clang do not support zicsr and zifencei via -march - but newer versions of binutils require it for the reasons noted in the - help text of CONFIG_TOOLCHAIN_NEEDS_EXPLICIT_ZICSR_ZIFENCEI. This - option causes an older ISA spec compatible with these older versions - of clang to be passed to GAS, which has the same result as passing zicsr - and zifencei to -march. + Certain versions of clang and GCC do not support zicsr and zifencei via + -march. This option causes an older ISA spec compatible with these older + versions of clang and GCC to be passed to GAS, which has the same result + as passing zicsr and zifencei to -march. config FPU bool "FPU support" diff --git a/arch/riscv/include/asm/mmio.h b/arch/riscv/include/asm/mmio.h index aff6c33ab0c0..4c58ee7f95ec 100644 --- a/arch/riscv/include/asm/mmio.h +++ b/arch/riscv/include/asm/mmio.h @@ -101,9 +101,9 @@ static inline u64 __raw_readq(const volatile void __iomem *addr) * Relaxed I/O memory access primitives. These follow the Device memory * ordering rules but do not guarantee any ordering relative to Normal memory * accesses. These are defined to order the indicated access (either a read or - * write) with all other I/O memory accesses. Since the platform specification - * defines that all I/O regions are strongly ordered on channel 2, no explicit - * fences are required to enforce this ordering. + * write) with all other I/O memory accesses to the same peripheral. Since the + * platform specification defines that all I/O regions are strongly ordered on + * channel 0, no explicit fences are required to enforce this ordering. */ /* FIXME: These are now the same as asm-generic */ #define __io_rbr() do {} while (0) @@ -125,14 +125,14 @@ static inline u64 __raw_readq(const volatile void __iomem *addr) #endif /* - * I/O memory access primitives. Reads are ordered relative to any - * following Normal memory access. Writes are ordered relative to any prior - * Normal memory access. The memory barriers here are necessary as RISC-V + * I/O memory access primitives. Reads are ordered relative to any following + * Normal memory read and delay() loop. Writes are ordered relative to any + * prior Normal memory write. The memory barriers here are necessary as RISC-V * doesn't define any ordering between the memory space and the I/O space. */ #define __io_br() do {} while (0) -#define __io_ar(v) __asm__ __volatile__ ("fence i,r" : : : "memory") -#define __io_bw() __asm__ __volatile__ ("fence w,o" : : : "memory") +#define __io_ar(v) ({ __asm__ __volatile__ ("fence i,ir" : : : "memory"); }) +#define __io_bw() ({ __asm__ __volatile__ ("fence w,o" : : : "memory"); }) #define __io_aw() mmiowb_set_pending() #define readb(c) ({ u8 __v; __io_br(); __v = readb_cpu(c); __io_ar(__v); __v; }) diff --git a/arch/riscv/kernel/compat_vdso/Makefile b/arch/riscv/kernel/compat_vdso/Makefile index 7f34f3c7c882..737c0857b14c 100644 --- a/arch/riscv/kernel/compat_vdso/Makefile +++ b/arch/riscv/kernel/compat_vdso/Makefile @@ -11,7 +11,13 @@ compat_vdso-syms += flush_icache COMPAT_CC := $(CC) COMPAT_LD := $(LD) -COMPAT_CC_FLAGS := -march=rv32g -mabi=ilp32 +# binutils 2.35 does not support the zifencei extension, but in the ISA +# spec 20191213, G stands for IMAFD_ZICSR_ZIFENCEI. +ifdef CONFIG_TOOLCHAIN_NEEDS_EXPLICIT_ZICSR_ZIFENCEI + COMPAT_CC_FLAGS := -march=rv32g -mabi=ilp32 +else + COMPAT_CC_FLAGS := -march=rv32imafd -mabi=ilp32 +endif COMPAT_LD_FLAGS := -melf32lriscv # Disable attributes, as they're useless and break the build. diff --git a/arch/riscv/kernel/elf_kexec.c b/arch/riscv/kernel/elf_kexec.c index 5372b708fae2..c08bb5c3b385 100644 --- a/arch/riscv/kernel/elf_kexec.c +++ b/arch/riscv/kernel/elf_kexec.c @@ -281,7 +281,7 @@ static void *elf_kexec_load(struct kimage *image, char *kernel_buf, kbuf.buffer = initrd; kbuf.bufsz = kbuf.memsz = initrd_len; kbuf.buf_align = PAGE_SIZE; - kbuf.top_down = false; + kbuf.top_down = true; kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; ret = kexec_add_buffer(&kbuf); if (ret) @@ -425,6 +425,7 @@ int arch_kexec_apply_relocations_add(struct purgatory_info *pi, * sym, instead of searching the whole relsec. */ case R_RISCV_PCREL_HI20: + case R_RISCV_CALL_PLT: case R_RISCV_CALL: *(u64 *)loc = CLEAN_IMM(UITYPE, *(u64 *)loc) | ENCODE_UJTYPE_IMM(val - addr); diff --git a/arch/riscv/lib/uaccess.S b/arch/riscv/lib/uaccess.S index ec486e5369d9..09b47ebacf2e 100644 --- a/arch/riscv/lib/uaccess.S +++ b/arch/riscv/lib/uaccess.S @@ -17,8 +17,11 @@ ENTRY(__asm_copy_from_user) li t6, SR_SUM csrs CSR_STATUS, t6 - /* Save for return value */ - mv t5, a2 + /* + * Save the terminal address which will be used to compute the number + * of bytes copied in case of a fixup exception. + */ + add t5, a0, a2 /* * Register allocation for code below: @@ -176,7 +179,7 @@ ENTRY(__asm_copy_from_user) 10: /* Disable access to user memory */ csrc CSR_STATUS, t6 - mv a0, t5 + sub a0, t5, a0 ret ENDPROC(__asm_copy_to_user) ENDPROC(__asm_copy_from_user) @@ -228,7 +231,7 @@ ENTRY(__clear_user) 11: /* Disable access to user memory */ csrc CSR_STATUS, t6 - mv a0, a1 + sub a0, a3, a0 ret ENDPROC(__clear_user) EXPORT_SYMBOL(__clear_user) diff --git a/arch/s390/kernel/sthyi.c b/arch/s390/kernel/sthyi.c index 4d141e2c132e..2ea7f208f0e7 100644 --- a/arch/s390/kernel/sthyi.c +++ b/arch/s390/kernel/sthyi.c @@ -459,9 +459,9 @@ static int sthyi_update_cache(u64 *rc) * * Fills the destination with system information returned by the STHYI * instruction. The data is generated by emulation or execution of STHYI, - * if available. The return value is the condition code that would be - * returned, the rc parameter is the return code which is passed in - * register R2 + 1. + * if available. The return value is either a negative error value or + * the condition code that would be returned, the rc parameter is the + * return code which is passed in register R2 + 1. */ int sthyi_fill(void *dst, u64 *rc) { diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c index ee7478a60144..b37bb960bfaf 100644 --- a/arch/s390/kvm/intercept.c +++ b/arch/s390/kvm/intercept.c @@ -389,8 +389,8 @@ static int handle_partial_execution(struct kvm_vcpu *vcpu) */ int handle_sthyi(struct kvm_vcpu *vcpu) { - int reg1, reg2, r = 0; - u64 code, addr, cc = 0, rc = 0; + int reg1, reg2, cc = 0, r = 0; + u64 code, addr, rc = 0; struct sthyi_sctns *sctns = NULL; if (!test_kvm_facility(vcpu->kvm, 74)) @@ -421,7 +421,10 @@ int handle_sthyi(struct kvm_vcpu *vcpu) return -ENOMEM; cc = sthyi_fill(sctns, &rc); - + if (cc < 0) { + free_page((unsigned long)sctns); + return cc; + } out: if (!cc) { if (kvm_s390_pv_cpu_is_protected(vcpu)) { diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 8e4d1f757bcc..a0593f6ce0e0 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -7,6 +7,7 @@ config SUPERH select ARCH_HAVE_CUSTOM_GPIO_H select ARCH_HAVE_NMI_SAFE_CMPXCHG if (GUSA_RB || CPU_SH4A) select ARCH_HAS_BINFMT_FLAT if !MMU + select ARCH_HAS_CPU_FINALIZE_INIT select ARCH_HAS_CURRENT_STACK_POINTER select ARCH_HAS_GIGANTIC_PAGE select ARCH_HAS_GCOV_PROFILE_ALL diff --git a/arch/sh/include/asm/bugs.h b/arch/sh/include/asm/bugs.h deleted file mode 100644 index fe52abb69cea..000000000000 --- a/arch/sh/include/asm/bugs.h +++ /dev/null @@ -1,74 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __ASM_SH_BUGS_H -#define __ASM_SH_BUGS_H - -/* - * This is included by init/main.c to check for architecture-dependent bugs. - * - * Needs: - * void check_bugs(void); - */ - -/* - * I don't know of any Super-H bugs yet. - */ - -#include <asm/processor.h> - -extern void select_idle_routine(void); - -static void __init check_bugs(void) -{ - extern unsigned long loops_per_jiffy; - char *p = &init_utsname()->machine[2]; /* "sh" */ - - select_idle_routine(); - - current_cpu_data.loops_per_jiffy = loops_per_jiffy; - - switch (current_cpu_data.family) { - case CPU_FAMILY_SH2: - *p++ = '2'; - break; - case CPU_FAMILY_SH2A: - *p++ = '2'; - *p++ = 'a'; - break; - case CPU_FAMILY_SH3: - *p++ = '3'; - break; - case CPU_FAMILY_SH4: - *p++ = '4'; - break; - case CPU_FAMILY_SH4A: - *p++ = '4'; - *p++ = 'a'; - break; - case CPU_FAMILY_SH4AL_DSP: - *p++ = '4'; - *p++ = 'a'; - *p++ = 'l'; - *p++ = '-'; - *p++ = 'd'; - *p++ = 's'; - *p++ = 'p'; - break; - case CPU_FAMILY_UNKNOWN: - /* - * Specifically use CPU_FAMILY_UNKNOWN rather than - * default:, so we're able to have the compiler whine - * about unhandled enumerations. - */ - break; - } - - printk("CPU: %s\n", get_cpu_subtype(¤t_cpu_data)); - -#ifndef __LITTLE_ENDIAN__ - /* 'eb' means 'Endian Big' */ - *p++ = 'e'; - *p++ = 'b'; -#endif - *p = '\0'; -} -#endif /* __ASM_SH_BUGS_H */ diff --git a/arch/sh/include/asm/processor.h b/arch/sh/include/asm/processor.h index 85a6c1c3c16e..73fba7c922f9 100644 --- a/arch/sh/include/asm/processor.h +++ b/arch/sh/include/asm/processor.h @@ -166,6 +166,8 @@ extern unsigned int instruction_size(unsigned int insn); #define instruction_size(insn) (2) #endif +void select_idle_routine(void); + #endif /* __ASSEMBLY__ */ #include <asm/processor_32.h> diff --git a/arch/sh/kernel/idle.c b/arch/sh/kernel/idle.c index f59814983bd5..a80b2a5b25c7 100644 --- a/arch/sh/kernel/idle.c +++ b/arch/sh/kernel/idle.c @@ -14,6 +14,7 @@ #include <linux/irqflags.h> #include <linux/smp.h> #include <linux/atomic.h> +#include <asm/processor.h> #include <asm/smp.h> #include <asm/bl_bit.h> diff --git a/arch/sh/kernel/setup.c b/arch/sh/kernel/setup.c index af977ec4ca5e..cf7c0f72f293 100644 --- a/arch/sh/kernel/setup.c +++ b/arch/sh/kernel/setup.c @@ -43,6 +43,7 @@ #include <asm/smp.h> #include <asm/mmu_context.h> #include <asm/mmzone.h> +#include <asm/processor.h> #include <asm/sparsemem.h> #include <asm/platform_early.h> @@ -354,3 +355,57 @@ int test_mode_pin(int pin) { return sh_mv.mv_mode_pins() & pin; } + +void __init arch_cpu_finalize_init(void) +{ + char *p = &init_utsname()->machine[2]; /* "sh" */ + + select_idle_routine(); + + current_cpu_data.loops_per_jiffy = loops_per_jiffy; + + switch (current_cpu_data.family) { + case CPU_FAMILY_SH2: + *p++ = '2'; + break; + case CPU_FAMILY_SH2A: + *p++ = '2'; + *p++ = 'a'; + break; + case CPU_FAMILY_SH3: + *p++ = '3'; + break; + case CPU_FAMILY_SH4: + *p++ = '4'; + break; + case CPU_FAMILY_SH4A: + *p++ = '4'; + *p++ = 'a'; + break; + case CPU_FAMILY_SH4AL_DSP: + *p++ = '4'; + *p++ = 'a'; + *p++ = 'l'; + *p++ = '-'; + *p++ = 'd'; + *p++ = 's'; + *p++ = 'p'; + break; + case CPU_FAMILY_UNKNOWN: + /* + * Specifically use CPU_FAMILY_UNKNOWN rather than + * default:, so we're able to have the compiler whine + * about unhandled enumerations. + */ + break; + } + + pr_info("CPU: %s\n", get_cpu_subtype(¤t_cpu_data)); + +#ifndef __LITTLE_ENDIAN__ + /* 'eb' means 'Endian Big' */ + *p++ = 'e'; + *p++ = 'b'; +#endif + *p = '\0'; +} diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index dbb1760cbe8c..b67d96e3392e 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -51,6 +51,7 @@ config SPARC config SPARC32 def_bool !64BIT select ARCH_32BIT_OFF_T + select ARCH_HAS_CPU_FINALIZE_INIT if !SMP select ARCH_HAS_SYNC_DMA_FOR_CPU select CLZ_TAB select DMA_DIRECT_REMAP diff --git a/arch/sparc/include/asm/bugs.h b/arch/sparc/include/asm/bugs.h deleted file mode 100644 index 02fa369b9c21..000000000000 --- a/arch/sparc/include/asm/bugs.h +++ /dev/null @@ -1,18 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* include/asm/bugs.h: Sparc probes for various bugs. - * - * Copyright (C) 1996, 2007 David S. Miller (davem@davemloft.net) - */ - -#ifdef CONFIG_SPARC32 -#include <asm/cpudata.h> -#endif - -extern unsigned long loops_per_jiffy; - -static void __init check_bugs(void) -{ -#if defined(CONFIG_SPARC32) && !defined(CONFIG_SMP) - cpu_data(0).udelay_val = loops_per_jiffy; -#endif -} diff --git a/arch/sparc/kernel/setup_32.c b/arch/sparc/kernel/setup_32.c index c8e0dd99f370..c9d1ba4f311b 100644 --- a/arch/sparc/kernel/setup_32.c +++ b/arch/sparc/kernel/setup_32.c @@ -412,3 +412,10 @@ static int __init topology_init(void) } subsys_initcall(topology_init); + +#if defined(CONFIG_SPARC32) && !defined(CONFIG_SMP) +void __init arch_cpu_finalize_init(void) +{ + cpu_data(0).udelay_val = loops_per_jiffy; +} +#endif diff --git a/arch/um/Kconfig b/arch/um/Kconfig index ad4ff3b0e91e..82709bc36df7 100644 --- a/arch/um/Kconfig +++ b/arch/um/Kconfig @@ -6,6 +6,7 @@ config UML bool default y select ARCH_EPHEMERAL_INODES + select ARCH_HAS_CPU_FINALIZE_INIT select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAS_KCOV diff --git a/arch/um/include/asm/bugs.h b/arch/um/include/asm/bugs.h deleted file mode 100644 index 4473942a0839..000000000000 --- a/arch/um/include/asm/bugs.h +++ /dev/null @@ -1,7 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __UM_BUGS_H -#define __UM_BUGS_H - -void check_bugs(void); - -#endif diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c index 8adf8e89b255..334c91191b31 100644 --- a/arch/um/kernel/um_arch.c +++ b/arch/um/kernel/um_arch.c @@ -3,6 +3,7 @@ * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com) */ +#include <linux/cpu.h> #include <linux/delay.h> #include <linux/init.h> #include <linux/mm.h> @@ -426,7 +427,7 @@ void __init setup_arch(char **cmdline_p) } } -void __init check_bugs(void) +void __init arch_cpu_finalize_init(void) { arch_check_bugs(); os_check_bugs(); diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index b3d5706579d4..4c9bfc4be58d 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -69,6 +69,7 @@ config X86 select ARCH_ENABLE_THP_MIGRATION if X86_64 && TRANSPARENT_HUGEPAGE select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI select ARCH_HAS_CACHE_LINE_SIZE + select ARCH_HAS_CPU_FINALIZE_INIT select ARCH_HAS_CURRENT_STACK_POINTER select ARCH_HAS_DEBUG_VIRTUAL select ARCH_HAS_DEBUG_VM_PGTABLE if !X86_PAE @@ -2511,6 +2512,13 @@ config CPU_IBRS_ENTRY This mitigates both spectre_v2 and retbleed at great cost to performance. +config CPU_SRSO + bool "Mitigate speculative RAS overflow on AMD" + depends on CPU_SUP_AMD && X86_64 && RETHUNK + default y + help + Enable the SRSO mitigation needed on AMD Zen1-4 machines. + config SLS bool "Mitigate Straight-Line-Speculation" depends on CC_HAS_SLS && X86_64 @@ -2521,6 +2529,25 @@ config SLS against straight line speculation. The kernel image might be slightly larger. +config GDS_FORCE_MITIGATION + bool "Force GDS Mitigation" + depends on CPU_SUP_INTEL + default n + help + Gather Data Sampling (GDS) is a hardware vulnerability which allows + unprivileged speculative access to data which was previously stored in + vector registers. + + This option is equivalent to setting gather_data_sampling=force on the + command line. The microcode mitigation is used if present, otherwise + AVX is disabled as a mitigation. On affected systems that are missing + the microcode any userspace code that unconditionally uses AVX will + break with this option set. + + Setting this option on systems not vulnerable to GDS has no effect. + + If in doubt, say N. + endif config ARCH_HAS_ADD_PAGES diff --git a/arch/x86/boot/compressed/idt_64.c b/arch/x86/boot/compressed/idt_64.c index 6debb816e83d..3cdf94b41456 100644 --- a/arch/x86/boot/compressed/idt_64.c +++ b/arch/x86/boot/compressed/idt_64.c @@ -63,7 +63,14 @@ void load_stage2_idt(void) set_idt_entry(X86_TRAP_PF, boot_page_fault); #ifdef CONFIG_AMD_MEM_ENCRYPT - set_idt_entry(X86_TRAP_VC, boot_stage2_vc); + /* + * Clear the second stage #VC handler in case guest types + * needing #VC have not been detected. + */ + if (sev_status & BIT(1)) + set_idt_entry(X86_TRAP_VC, boot_stage2_vc); + else + set_idt_entry(X86_TRAP_VC, NULL); #endif load_boot_idt(&boot_idt_desc); diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c index d63ad8f99f83..e65f0968e0d9 100644 --- a/arch/x86/boot/compressed/sev.c +++ b/arch/x86/boot/compressed/sev.c @@ -355,12 +355,45 @@ void sev_enable(struct boot_params *bp) bp->cc_blob_address = 0; /* + * Do an initial SEV capability check before snp_init() which + * loads the CPUID page and the same checks afterwards are done + * without the hypervisor and are trustworthy. + * + * If the HV fakes SEV support, the guest will crash'n'burn + * which is good enough. + */ + + /* Check for the SME/SEV support leaf */ + eax = 0x80000000; + ecx = 0; + native_cpuid(&eax, &ebx, &ecx, &edx); + if (eax < 0x8000001f) + return; + + /* + * Check for the SME/SEV feature: + * CPUID Fn8000_001F[EAX] + * - Bit 0 - Secure Memory Encryption support + * - Bit 1 - Secure Encrypted Virtualization support + * CPUID Fn8000_001F[EBX] + * - Bits 5:0 - Pagetable bit position used to indicate encryption + */ + eax = 0x8000001f; + ecx = 0; + native_cpuid(&eax, &ebx, &ecx, &edx); + /* Check whether SEV is supported */ + if (!(eax & BIT(1))) + return; + + /* * Setup/preliminary detection of SNP. This will be sanity-checked * against CPUID/MSR values later. */ snp = snp_init(bp); - /* Check for the SME/SEV support leaf */ + /* Now repeat the checks with the SNP CPUID table. */ + + /* Recheck the SME/SEV support leaf */ eax = 0x80000000; ecx = 0; native_cpuid(&eax, &ebx, &ecx, &edx); @@ -368,7 +401,7 @@ void sev_enable(struct boot_params *bp) return; /* - * Check for the SME/SEV feature: + * Recheck for the SME/SEV feature: * CPUID Fn8000_001F[EAX] * - Bit 0 - Secure Memory Encryption support * - Bit 1 - Secure Encrypted Virtualization support diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c index 311eae30e089..1288661397f0 100644 --- a/arch/x86/entry/vdso/vma.c +++ b/arch/x86/entry/vdso/vma.c @@ -322,8 +322,8 @@ static unsigned long vdso_addr(unsigned long start, unsigned len) /* Round the lowest possible end address up to a PMD boundary. */ end = (start + len + PMD_SIZE - 1) & PMD_MASK; - if (end >= TASK_SIZE_MAX) - end = TASK_SIZE_MAX; + if (end >= DEFAULT_MAP_WINDOW) + end = DEFAULT_MAP_WINDOW; end -= len; if (end > start) { diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 85863b9c9e68..189ae92de4d0 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -14,6 +14,7 @@ #include <asm/apic.h> #include <asm/desc.h> #include <asm/sev.h> +#include <asm/ibt.h> #include <asm/hypervisor.h> #include <asm/hyperv-tlfs.h> #include <asm/mshyperv.h> @@ -468,6 +469,26 @@ void __init hyperv_init(void) } /* + * Some versions of Hyper-V that provide IBT in guest VMs have a bug + * in that there's no ENDBR64 instruction at the entry to the + * hypercall page. Because hypercalls are invoked via an indirect call + * to the hypercall page, all hypercall attempts fail when IBT is + * enabled, and Linux panics. For such buggy versions, disable IBT. + * + * Fixed versions of Hyper-V always provide ENDBR64 on the hypercall + * page, so if future Linux kernel versions enable IBT for 32-bit + * builds, additional hypercall page hackery will be required here + * to provide an ENDBR32. + */ +#ifdef CONFIG_X86_KERNEL_IBT + if (cpu_feature_enabled(X86_FEATURE_IBT) && + *(u32 *)hv_hypercall_pg != gen_endbr()) { + setup_clear_cpu_cap(X86_FEATURE_IBT); + pr_warn("Hyper-V: Disabling IBT because of Hyper-V bug\n"); + } +#endif + + /* * hyperv_init() is called before LAPIC is initialized: see * apic_intr_mode_init() -> x86_platform.apic_post_init() and * apic_bsp_setup() -> setup_local_APIC(). The direct-mode STIMER diff --git a/arch/x86/include/asm/bugs.h b/arch/x86/include/asm/bugs.h index 92ae28389940..f25ca2d709d4 100644 --- a/arch/x86/include/asm/bugs.h +++ b/arch/x86/include/asm/bugs.h @@ -4,8 +4,6 @@ #include <asm/processor.h> -extern void check_bugs(void); - #if defined(CONFIG_CPU_SUP_INTEL) && defined(CONFIG_X86_32) int ppro_with_ram_bug(void); #else diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 1a85e1fb0922..ce0c8f7d3218 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -32,6 +32,7 @@ enum cpuid_leafs CPUID_8000_0007_EBX, CPUID_7_EDX, CPUID_8000_001F_EAX, + CPUID_8000_0021_EAX, }; #define X86_CAP_FMT_NUM "%d:%d" @@ -94,8 +95,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 17, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 18, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 19, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 20, feature_bit) || \ REQUIRED_MASK_CHECK || \ - BUILD_BUG_ON_ZERO(NCAPINTS != 20)) + BUILD_BUG_ON_ZERO(NCAPINTS != 21)) #define DISABLED_MASK_BIT_SET(feature_bit) \ ( CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 0, feature_bit) || \ @@ -118,8 +120,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 17, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 18, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 19, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 20, feature_bit) || \ DISABLED_MASK_CHECK || \ - BUILD_BUG_ON_ZERO(NCAPINTS != 20)) + BUILD_BUG_ON_ZERO(NCAPINTS != 21)) #define cpu_has(c, bit) \ (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \ diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 92729c38853d..b122708792c4 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -13,8 +13,8 @@ /* * Defines x86 CPU feature bits */ -#define NCAPINTS 20 /* N 32-bit words worth of info */ -#define NBUGINTS 1 /* N 32-bit bug flags */ +#define NCAPINTS 21 /* N 32-bit words worth of info */ +#define NBUGINTS 2 /* N 32-bit bug flags */ /* * Note: If the comment begins with a quoted string, that string is used @@ -308,6 +308,10 @@ #define X86_FEATURE_MSR_TSX_CTRL (11*32+20) /* "" MSR IA32_TSX_CTRL (Intel) implemented */ +#define X86_FEATURE_SRSO (11*32+24) /* "" AMD BTB untrain RETs */ +#define X86_FEATURE_SRSO_ALIAS (11*32+25) /* "" AMD BTB untrain RETs through aliasing */ +#define X86_FEATURE_IBPB_ON_VMEXIT (11*32+26) /* "" Issue an IBPB only on VMEXIT */ + /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */ #define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */ @@ -423,6 +427,10 @@ #define X86_FEATURE_V_TSC_AUX (19*32+ 9) /* "" Virtual TSC_AUX */ #define X86_FEATURE_SME_COHERENT (19*32+10) /* "" AMD hardware-enforced cache coherency */ +#define X86_FEATURE_SBPB (20*32+27) /* "" Selective Branch Prediction Barrier */ +#define X86_FEATURE_IBPB_BRTYPE (20*32+28) /* "" MSR_PRED_CMD[IBPB] flushes all branch type predictions */ +#define X86_FEATURE_SRSO_NO (20*32+29) /* "" CPU is not affected by SRSO */ + /* * BUG word(s) */ @@ -464,5 +472,9 @@ #define X86_BUG_RETBLEED X86_BUG(27) /* CPU is affected by RETBleed */ #define X86_BUG_EIBRS_PBRSB X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */ #define X86_BUG_SMT_RSB X86_BUG(29) /* CPU is vulnerable to Cross-Thread Return Address Predictions */ +#define X86_BUG_GDS X86_BUG(30) /* CPU is affected by Gather Data Sampling */ +/* BUG word 2 */ +#define X86_BUG_SRSO X86_BUG(1*32 + 0) /* AMD SRSO bug */ +#define X86_BUG_DIV0 X86_BUG(1*32 + 1) /* AMD DIV0 speculation bug */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h index 33d2cd04d254..000037078db4 100644 --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -111,6 +111,7 @@ #define DISABLED_MASK17 0 #define DISABLED_MASK18 0 #define DISABLED_MASK19 0 -#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 20) +#define DISABLED_MASK20 0 +#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21) #endif /* _ASM_X86_DISABLED_FEATURES_H */ diff --git a/arch/x86/include/asm/entry-common.h b/arch/x86/include/asm/entry-common.h index 674ed46d3ced..11203a9fe0a8 100644 --- a/arch/x86/include/asm/entry-common.h +++ b/arch/x86/include/asm/entry-common.h @@ -92,6 +92,7 @@ static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs, static __always_inline void arch_exit_to_user_mode(void) { mds_user_clear_cpu_buffers(); + amd_clear_divider(); } #define arch_exit_to_user_mode arch_exit_to_user_mode diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h index 503a577814b2..b475d9a582b8 100644 --- a/arch/x86/include/asm/fpu/api.h +++ b/arch/x86/include/asm/fpu/api.h @@ -109,7 +109,7 @@ extern void fpu_reset_from_exception_fixup(void); /* Boot, hotplug and resume */ extern void fpu__init_cpu(void); -extern void fpu__init_system(struct cpuinfo_x86 *c); +extern void fpu__init_system(void); extern void fpu__init_check_bugs(void); extern void fpu__resume_cpu(void); diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h index 72ca90552b6a..8f513372cd8d 100644 --- a/arch/x86/include/asm/mem_encrypt.h +++ b/arch/x86/include/asm/mem_encrypt.h @@ -17,6 +17,12 @@ #include <asm/bootparam.h> +#ifdef CONFIG_X86_MEM_ENCRYPT +void __init mem_encrypt_init(void); +#else +static inline void mem_encrypt_init(void) { } +#endif + #ifdef CONFIG_AMD_MEM_ENCRYPT extern u64 sme_me_mask; @@ -86,9 +92,6 @@ static inline void mem_encrypt_free_decrypted_mem(void) { } #endif /* CONFIG_AMD_MEM_ENCRYPT */ -/* Architecture __weak replacement functions */ -void __init mem_encrypt_init(void); - void add_encrypt_protection_map(void); /* diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 846067e1ee8b..52d8c67d9308 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -60,6 +60,7 @@ #define MSR_IA32_PRED_CMD 0x00000049 /* Prediction Command */ #define PRED_CMD_IBPB BIT(0) /* Indirect Branch Prediction Barrier */ +#define PRED_CMD_SBPB BIT(7) /* Selective Branch Prediction Barrier */ #define MSR_PPIN_CTL 0x0000004e #define MSR_PPIN 0x0000004f @@ -158,6 +159,15 @@ * Not susceptible to Post-Barrier * Return Stack Buffer Predictions. */ +#define ARCH_CAP_GDS_CTRL BIT(25) /* + * CPU is vulnerable to Gather + * Data Sampling (GDS) and + * has controls for mitigation. + */ +#define ARCH_CAP_GDS_NO BIT(26) /* + * CPU is not vulnerable to Gather + * Data Sampling (GDS). + */ #define ARCH_CAP_XAPIC_DISABLE BIT(21) /* * IA32_XAPIC_DISABLE_STATUS MSR @@ -181,6 +191,8 @@ #define RNGDS_MITG_DIS BIT(0) /* SRBDS support */ #define RTM_ALLOW BIT(1) /* TSX development mode */ #define FB_CLEAR_DIS BIT(3) /* CPU Fill buffer clear disable */ +#define GDS_MITG_DIS BIT(4) /* Disable GDS mitigation */ +#define GDS_MITG_LOCKED BIT(5) /* GDS mitigation locked */ #define MSR_IA32_SYSENTER_CS 0x00000174 #define MSR_IA32_SYSENTER_ESP 0x00000175 diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index dfdb103ae4f6..2f123d4fb85b 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -112,7 +112,7 @@ * eventually turn into it's own annotation. */ .macro ANNOTATE_UNRET_END -#ifdef CONFIG_DEBUG_ENTRY +#if (defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_SRSO)) ANNOTATE_RETPOLINE_SAFE nop #endif @@ -168,9 +168,9 @@ .endm #ifdef CONFIG_CPU_UNRET_ENTRY -#define CALL_ZEN_UNTRAIN_RET "call zen_untrain_ret" +#define CALL_UNTRAIN_RET "call entry_untrain_ret" #else -#define CALL_ZEN_UNTRAIN_RET "" +#define CALL_UNTRAIN_RET "" #endif /* @@ -178,17 +178,18 @@ * return thunk isn't mapped into the userspace tables (then again, AMD * typically has NO_MELTDOWN). * - * While zen_untrain_ret() doesn't clobber anything but requires stack, + * While retbleed_untrain_ret() doesn't clobber anything but requires stack, * entry_ibpb() will clobber AX, CX, DX. * * As such, this must be placed after every *SWITCH_TO_KERNEL_CR3 at a point * where we have a stack but before any RET instruction. */ .macro UNTRAIN_RET -#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY) +#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY) || \ + defined(CONFIG_CPU_SRSO) ANNOTATE_UNRET_END ALTERNATIVE_2 "", \ - CALL_ZEN_UNTRAIN_RET, X86_FEATURE_UNRET, \ + CALL_UNTRAIN_RET, X86_FEATURE_UNRET, \ "call entry_ibpb", X86_FEATURE_ENTRY_IBPB #endif .endm @@ -204,8 +205,21 @@ typedef u8 retpoline_thunk_t[RETPOLINE_THUNK_SIZE]; extern retpoline_thunk_t __x86_indirect_thunk_array[]; +#ifdef CONFIG_RETHUNK extern void __x86_return_thunk(void); -extern void zen_untrain_ret(void); +#else +static inline void __x86_return_thunk(void) {} +#endif + +extern void retbleed_return_thunk(void); +extern void srso_return_thunk(void); +extern void srso_alias_return_thunk(void); + +extern void retbleed_untrain_ret(void); +extern void srso_untrain_ret(void); +extern void srso_alias_untrain_ret(void); + +extern void entry_untrain_ret(void); extern void entry_ibpb(void); #ifdef CONFIG_RETPOLINE @@ -311,11 +325,11 @@ void alternative_msr_write(unsigned int msr, u64 val, unsigned int feature) : "memory"); } +extern u64 x86_pred_cmd; + static inline void indirect_branch_prediction_barrier(void) { - u64 val = PRED_CMD_IBPB; - - alternative_msr_write(MSR_IA32_PRED_CMD, val, X86_FEATURE_USE_IBPB); + alternative_msr_write(MSR_IA32_PRED_CMD, x86_pred_cmd, X86_FEATURE_USE_IBPB); } /* The Intel SPEC CTRL MSR base value cache */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index d8277eec1bcd..94ea13adb724 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -800,9 +800,13 @@ extern u16 get_llc_id(unsigned int cpu); #ifdef CONFIG_CPU_SUP_AMD extern u32 amd_get_nodes_per_socket(void); extern u32 amd_get_highest_perf(void); +extern bool cpu_has_ibpb_brtype_microcode(void); +extern void amd_clear_divider(void); #else static inline u32 amd_get_nodes_per_socket(void) { return 0; } static inline u32 amd_get_highest_perf(void) { return 0; } +static inline bool cpu_has_ibpb_brtype_microcode(void) { return false; } +static inline void amd_clear_divider(void) { } #endif #define for_each_possible_hypervisor_cpuid_base(function) \ @@ -863,4 +867,6 @@ bool arch_is_platform_page(u64 paddr); #define arch_is_platform_page arch_is_platform_page #endif +extern bool gds_ucode_mitigated(void); + #endif /* _ASM_X86_PROCESSOR_H */ diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h index aff774775c67..7ba1726b71c7 100644 --- a/arch/x86/include/asm/required-features.h +++ b/arch/x86/include/asm/required-features.h @@ -98,6 +98,7 @@ #define REQUIRED_MASK17 0 #define REQUIRED_MASK18 0 #define REQUIRED_MASK19 0 -#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 20) +#define REQUIRED_MASK20 0 +#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21) #endif /* _ASM_X86_REQUIRED_FEATURES_H */ diff --git a/arch/x86/include/asm/sections.h b/arch/x86/include/asm/sections.h index a6e8373a5170..3fa87e5e11ab 100644 --- a/arch/x86/include/asm/sections.h +++ b/arch/x86/include/asm/sections.h @@ -2,8 +2,6 @@ #ifndef _ASM_X86_SECTIONS_H #define _ASM_X86_SECTIONS_H -#define arch_is_kernel_initmem_freed arch_is_kernel_initmem_freed - #include <asm-generic/sections.h> #include <asm/extable.h> @@ -18,20 +16,4 @@ extern char __end_of_kernel_reserve[]; extern unsigned long _brk_start, _brk_end; -static inline bool arch_is_kernel_initmem_freed(unsigned long addr) -{ - /* - * If _brk_start has not been cleared, brk allocation is incomplete, - * and we can not make assumptions about its use. - */ - if (_brk_start) - return 0; - - /* - * After brk allocation is complete, space between _brk_end and _end - * is available for allocation. - */ - return addr >= _brk_end && addr < (unsigned long)&_end; -} - #endif /* _ASM_X86_SECTIONS_H */ diff --git a/arch/x86/include/asm/sigframe.h b/arch/x86/include/asm/sigframe.h index 5b1ed650b124..84eab2724875 100644 --- a/arch/x86/include/asm/sigframe.h +++ b/arch/x86/include/asm/sigframe.h @@ -85,6 +85,4 @@ struct rt_sigframe_x32 { #endif /* CONFIG_X86_64 */ -void __init init_sigframe_size(void); - #endif /* _ASM_X86_SIGFRAME_H */ diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 7f4eb8b027cc..f240c978d85e 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -73,8 +73,13 @@ static const int amd_erratum_1054[] = static const int amd_zenbleed[] = AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0x30, 0x0, 0x4f, 0xf), AMD_MODEL_RANGE(0x17, 0x60, 0x0, 0x7f, 0xf), + AMD_MODEL_RANGE(0x17, 0x90, 0x0, 0x91, 0xf), AMD_MODEL_RANGE(0x17, 0xa0, 0x0, 0xaf, 0xf)); +static const int amd_div0[] = + AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0x00, 0x0, 0x2f, 0xf), + AMD_MODEL_RANGE(0x17, 0x50, 0x0, 0x5f, 0xf)); + static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum) { int osvw_id = *erratum++; @@ -1115,6 +1120,11 @@ static void init_amd(struct cpuinfo_x86 *c) check_null_seg_clears_base(c); zenbleed_check(c); + + if (cpu_has_amd_erratum(c, amd_div0)) { + pr_notice_once("AMD Zen1 DIV0 bug detected. Disable SMT for full protection.\n"); + setup_force_cpu_bug(X86_BUG_DIV0); + } } #ifdef CONFIG_X86_32 @@ -1245,6 +1255,25 @@ u32 amd_get_highest_perf(void) } EXPORT_SYMBOL_GPL(amd_get_highest_perf); +bool cpu_has_ibpb_brtype_microcode(void) +{ + switch (boot_cpu_data.x86) { + /* Zen1/2 IBPB flushes branch type predictions too. */ + case 0x17: + return boot_cpu_has(X86_FEATURE_AMD_IBPB); + case 0x19: + /* Poke the MSR bit on Zen3/4 to check its presence. */ + if (!wrmsrl_safe(MSR_IA32_PRED_CMD, PRED_CMD_SBPB)) { + setup_force_cpu_cap(X86_FEATURE_SBPB); + return true; + } else { + return false; + } + default: + return false; + } +} + static void zenbleed_check_cpu(void *unused) { struct cpuinfo_x86 *c = &cpu_data(smp_processor_id()); @@ -1256,3 +1285,14 @@ void amd_check_microcode(void) { on_each_cpu(zenbleed_check_cpu, NULL, 1); } + +/* + * Issue a DIV 0/1 insn to clear any division data from previous DIV + * operations. + */ +void noinstr amd_clear_divider(void) +{ + asm volatile(ALTERNATIVE("", "div %2\n\t", X86_BUG_DIV0) + :: "a" (0), "d" (0), "r" (1)); +} +EXPORT_SYMBOL_GPL(amd_clear_divider); diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index f54992887491..3a893ab398a0 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -9,7 +9,6 @@ * - Andrew D. Balsa (code cleanup). */ #include <linux/init.h> -#include <linux/utsname.h> #include <linux/cpu.h> #include <linux/module.h> #include <linux/nospec.h> @@ -27,8 +26,6 @@ #include <asm/msr.h> #include <asm/vmx.h> #include <asm/paravirt.h> -#include <asm/alternative.h> -#include <asm/set_memory.h> #include <asm/intel-family.h> #include <asm/e820/api.h> #include <asm/hypervisor.h> @@ -49,6 +46,8 @@ static void __init taa_select_mitigation(void); static void __init mmio_select_mitigation(void); static void __init srbds_select_mitigation(void); static void __init l1d_flush_select_mitigation(void); +static void __init gds_select_mitigation(void); +static void __init srso_select_mitigation(void); /* The base value of the SPEC_CTRL MSR without task-specific bits set */ u64 x86_spec_ctrl_base; @@ -58,8 +57,13 @@ EXPORT_SYMBOL_GPL(x86_spec_ctrl_base); DEFINE_PER_CPU(u64, x86_spec_ctrl_current); EXPORT_SYMBOL_GPL(x86_spec_ctrl_current); +u64 x86_pred_cmd __ro_after_init = PRED_CMD_IBPB; +EXPORT_SYMBOL_GPL(x86_pred_cmd); + static DEFINE_MUTEX(spec_ctrl_mutex); +void (*x86_return_thunk)(void) __ro_after_init = &__x86_return_thunk; + /* Update SPEC_CTRL MSR and its cached copy unconditionally */ static void update_spec_ctrl(u64 val) { @@ -124,21 +128,8 @@ DEFINE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush); DEFINE_STATIC_KEY_FALSE(mmio_stale_data_clear); EXPORT_SYMBOL_GPL(mmio_stale_data_clear); -void __init check_bugs(void) +void __init cpu_select_mitigations(void) { - identify_boot_cpu(); - - /* - * identify_boot_cpu() initialized SMT support information, let the - * core code know. - */ - cpu_smt_check_topology(); - - if (!IS_ENABLED(CONFIG_SMP)) { - pr_info("CPU: "); - print_cpu_info(&boot_cpu_data); - } - /* * Read the SPEC_CTRL MSR to account for reserved bits which may * have unknown values. AMD64_LS_CFG MSR is cached in the early AMD @@ -176,38 +167,12 @@ void __init check_bugs(void) srbds_select_mitigation(); l1d_flush_select_mitigation(); - arch_smt_update(); - -#ifdef CONFIG_X86_32 - /* - * Check whether we are able to run this kernel safely on SMP. - * - * - i386 is no longer supported. - * - In order to run on anything without a TSC, we need to be - * compiled for a i486. - */ - if (boot_cpu_data.x86 < 4) - panic("Kernel requires i486+ for 'invlpg' and other features"); - - init_utsname()->machine[1] = - '0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86); - alternative_instructions(); - - fpu__init_check_bugs(); -#else /* CONFIG_X86_64 */ - alternative_instructions(); - /* - * Make sure the first 2MB area is not mapped by huge pages - * There are typically fixed size MTRRs in there and overlapping - * MTRRs into large pages causes slow downs. - * - * Right now we don't do that with gbpages because there seems - * very little benefit for that case. + * srso_select_mitigation() depends and must run after + * retbleed_select_mitigation(). */ - if (!direct_gbpages) - set_memory_4k((unsigned long)__va(0), 1); -#endif + srso_select_mitigation(); + gds_select_mitigation(); } /* @@ -694,6 +659,149 @@ static int __init l1d_flush_parse_cmdline(char *str) early_param("l1d_flush", l1d_flush_parse_cmdline); #undef pr_fmt +#define pr_fmt(fmt) "GDS: " fmt + +enum gds_mitigations { + GDS_MITIGATION_OFF, + GDS_MITIGATION_UCODE_NEEDED, + GDS_MITIGATION_FORCE, + GDS_MITIGATION_FULL, + GDS_MITIGATION_FULL_LOCKED, + GDS_MITIGATION_HYPERVISOR, +}; + +#if IS_ENABLED(CONFIG_GDS_FORCE_MITIGATION) +static enum gds_mitigations gds_mitigation __ro_after_init = GDS_MITIGATION_FORCE; +#else +static enum gds_mitigations gds_mitigation __ro_after_init = GDS_MITIGATION_FULL; +#endif + +static const char * const gds_strings[] = { + [GDS_MITIGATION_OFF] = "Vulnerable", + [GDS_MITIGATION_UCODE_NEEDED] = "Vulnerable: No microcode", + [GDS_MITIGATION_FORCE] = "Mitigation: AVX disabled, no microcode", + [GDS_MITIGATION_FULL] = "Mitigation: Microcode", + [GDS_MITIGATION_FULL_LOCKED] = "Mitigation: Microcode (locked)", + [GDS_MITIGATION_HYPERVISOR] = "Unknown: Dependent on hypervisor status", +}; + +bool gds_ucode_mitigated(void) +{ + return (gds_mitigation == GDS_MITIGATION_FULL || + gds_mitigation == GDS_MITIGATION_FULL_LOCKED); +} +EXPORT_SYMBOL_GPL(gds_ucode_mitigated); + +void update_gds_msr(void) +{ + u64 mcu_ctrl_after; + u64 mcu_ctrl; + + switch (gds_mitigation) { + case GDS_MITIGATION_OFF: + rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl); + mcu_ctrl |= GDS_MITG_DIS; + break; + case GDS_MITIGATION_FULL_LOCKED: + /* + * The LOCKED state comes from the boot CPU. APs might not have + * the same state. Make sure the mitigation is enabled on all + * CPUs. + */ + case GDS_MITIGATION_FULL: + rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl); + mcu_ctrl &= ~GDS_MITG_DIS; + break; + case GDS_MITIGATION_FORCE: + case GDS_MITIGATION_UCODE_NEEDED: + case GDS_MITIGATION_HYPERVISOR: + return; + }; + + wrmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl); + + /* + * Check to make sure that the WRMSR value was not ignored. Writes to + * GDS_MITG_DIS will be ignored if this processor is locked but the boot + * processor was not. + */ + rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl_after); + WARN_ON_ONCE(mcu_ctrl != mcu_ctrl_after); +} + +static void __init gds_select_mitigation(void) +{ + u64 mcu_ctrl; + + if (!boot_cpu_has_bug(X86_BUG_GDS)) + return; + + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) { + gds_mitigation = GDS_MITIGATION_HYPERVISOR; + goto out; + } + + if (cpu_mitigations_off()) + gds_mitigation = GDS_MITIGATION_OFF; + /* Will verify below that mitigation _can_ be disabled */ + + /* No microcode */ + if (!(x86_read_arch_cap_msr() & ARCH_CAP_GDS_CTRL)) { + if (gds_mitigation == GDS_MITIGATION_FORCE) { + /* + * This only needs to be done on the boot CPU so do it + * here rather than in update_gds_msr() + */ + setup_clear_cpu_cap(X86_FEATURE_AVX); + pr_warn("Microcode update needed! Disabling AVX as mitigation.\n"); + } else { + gds_mitigation = GDS_MITIGATION_UCODE_NEEDED; + } + goto out; + } + + /* Microcode has mitigation, use it */ + if (gds_mitigation == GDS_MITIGATION_FORCE) + gds_mitigation = GDS_MITIGATION_FULL; + + rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl); + if (mcu_ctrl & GDS_MITG_LOCKED) { + if (gds_mitigation == GDS_MITIGATION_OFF) + pr_warn("Mitigation locked. Disable failed.\n"); + + /* + * The mitigation is selected from the boot CPU. All other CPUs + * _should_ have the same state. If the boot CPU isn't locked + * but others are then update_gds_msr() will WARN() of the state + * mismatch. If the boot CPU is locked update_gds_msr() will + * ensure the other CPUs have the mitigation enabled. + */ + gds_mitigation = GDS_MITIGATION_FULL_LOCKED; + } + + update_gds_msr(); +out: + pr_info("%s\n", gds_strings[gds_mitigation]); +} + +static int __init gds_parse_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + if (!boot_cpu_has_bug(X86_BUG_GDS)) + return 0; + + if (!strcmp(str, "off")) + gds_mitigation = GDS_MITIGATION_OFF; + else if (!strcmp(str, "force")) + gds_mitigation = GDS_MITIGATION_FORCE; + + return 0; +} +early_param("gather_data_sampling", gds_parse_cmdline); + +#undef pr_fmt #define pr_fmt(fmt) "Spectre V1 : " fmt enum spectre_v1_mitigation { @@ -912,6 +1020,9 @@ do_cmd_auto: setup_force_cpu_cap(X86_FEATURE_RETHUNK); setup_force_cpu_cap(X86_FEATURE_UNRET); + if (IS_ENABLED(CONFIG_RETHUNK)) + x86_return_thunk = retbleed_return_thunk; + if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD && boot_cpu_data.x86_vendor != X86_VENDOR_HYGON) pr_err(RETBLEED_UNTRAIN_MSG); @@ -2208,6 +2319,170 @@ static int __init l1tf_cmdline(char *str) early_param("l1tf", l1tf_cmdline); #undef pr_fmt +#define pr_fmt(fmt) "Speculative Return Stack Overflow: " fmt + +enum srso_mitigation { + SRSO_MITIGATION_NONE, + SRSO_MITIGATION_MICROCODE, + SRSO_MITIGATION_SAFE_RET, + SRSO_MITIGATION_IBPB, + SRSO_MITIGATION_IBPB_ON_VMEXIT, +}; + +enum srso_mitigation_cmd { + SRSO_CMD_OFF, + SRSO_CMD_MICROCODE, + SRSO_CMD_SAFE_RET, + SRSO_CMD_IBPB, + SRSO_CMD_IBPB_ON_VMEXIT, +}; + +static const char * const srso_strings[] = { + [SRSO_MITIGATION_NONE] = "Vulnerable", + [SRSO_MITIGATION_MICROCODE] = "Mitigation: microcode", + [SRSO_MITIGATION_SAFE_RET] = "Mitigation: safe RET", + [SRSO_MITIGATION_IBPB] = "Mitigation: IBPB", + [SRSO_MITIGATION_IBPB_ON_VMEXIT] = "Mitigation: IBPB on VMEXIT only" +}; + +static enum srso_mitigation srso_mitigation __ro_after_init = SRSO_MITIGATION_NONE; +static enum srso_mitigation_cmd srso_cmd __ro_after_init = SRSO_CMD_SAFE_RET; + +static int __init srso_parse_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + if (!strcmp(str, "off")) + srso_cmd = SRSO_CMD_OFF; + else if (!strcmp(str, "microcode")) + srso_cmd = SRSO_CMD_MICROCODE; + else if (!strcmp(str, "safe-ret")) + srso_cmd = SRSO_CMD_SAFE_RET; + else if (!strcmp(str, "ibpb")) + srso_cmd = SRSO_CMD_IBPB; + else if (!strcmp(str, "ibpb-vmexit")) + srso_cmd = SRSO_CMD_IBPB_ON_VMEXIT; + else + pr_err("Ignoring unknown SRSO option (%s).", str); + + return 0; +} +early_param("spec_rstack_overflow", srso_parse_cmdline); + +#define SRSO_NOTICE "WARNING: See https://kernel.org/doc/html/latest/admin-guide/hw-vuln/srso.html for mitigation options." + +static void __init srso_select_mitigation(void) +{ + bool has_microcode; + + if (!boot_cpu_has_bug(X86_BUG_SRSO) || cpu_mitigations_off()) + goto pred_cmd; + + /* + * The first check is for the kernel running as a guest in order + * for guests to verify whether IBPB is a viable mitigation. + */ + has_microcode = boot_cpu_has(X86_FEATURE_IBPB_BRTYPE) || cpu_has_ibpb_brtype_microcode(); + if (!has_microcode) { + pr_warn("IBPB-extending microcode not applied!\n"); + pr_warn(SRSO_NOTICE); + } else { + /* + * Enable the synthetic (even if in a real CPUID leaf) + * flags for guests. + */ + setup_force_cpu_cap(X86_FEATURE_IBPB_BRTYPE); + + /* + * Zen1/2 with SMT off aren't vulnerable after the right + * IBPB microcode has been applied. + */ + if (boot_cpu_data.x86 < 0x19 && !cpu_smt_possible()) { + setup_force_cpu_cap(X86_FEATURE_SRSO_NO); + return; + } + } + + if (retbleed_mitigation == RETBLEED_MITIGATION_IBPB) { + if (has_microcode) { + pr_err("Retbleed IBPB mitigation enabled, using same for SRSO\n"); + srso_mitigation = SRSO_MITIGATION_IBPB; + goto pred_cmd; + } + } + + switch (srso_cmd) { + case SRSO_CMD_OFF: + return; + + case SRSO_CMD_MICROCODE: + if (has_microcode) { + srso_mitigation = SRSO_MITIGATION_MICROCODE; + pr_warn(SRSO_NOTICE); + } + break; + + case SRSO_CMD_SAFE_RET: + if (IS_ENABLED(CONFIG_CPU_SRSO)) { + /* + * Enable the return thunk for generated code + * like ftrace, static_call, etc. + */ + setup_force_cpu_cap(X86_FEATURE_RETHUNK); + setup_force_cpu_cap(X86_FEATURE_UNRET); + + if (boot_cpu_data.x86 == 0x19) { + setup_force_cpu_cap(X86_FEATURE_SRSO_ALIAS); + x86_return_thunk = srso_alias_return_thunk; + } else { + setup_force_cpu_cap(X86_FEATURE_SRSO); + x86_return_thunk = srso_return_thunk; + } + srso_mitigation = SRSO_MITIGATION_SAFE_RET; + } else { + pr_err("WARNING: kernel not compiled with CPU_SRSO.\n"); + goto pred_cmd; + } + break; + + case SRSO_CMD_IBPB: + if (IS_ENABLED(CONFIG_CPU_IBPB_ENTRY)) { + if (has_microcode) { + setup_force_cpu_cap(X86_FEATURE_ENTRY_IBPB); + srso_mitigation = SRSO_MITIGATION_IBPB; + } + } else { + pr_err("WARNING: kernel not compiled with CPU_IBPB_ENTRY.\n"); + goto pred_cmd; + } + break; + + case SRSO_CMD_IBPB_ON_VMEXIT: + if (IS_ENABLED(CONFIG_CPU_SRSO)) { + if (!boot_cpu_has(X86_FEATURE_ENTRY_IBPB) && has_microcode) { + setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT); + srso_mitigation = SRSO_MITIGATION_IBPB_ON_VMEXIT; + } + } else { + pr_err("WARNING: kernel not compiled with CPU_SRSO.\n"); + goto pred_cmd; + } + break; + + default: + break; + } + + pr_info("%s%s\n", srso_strings[srso_mitigation], (has_microcode ? "" : ", no microcode")); + +pred_cmd: + if ((boot_cpu_has(X86_FEATURE_SRSO_NO) || srso_cmd == SRSO_CMD_OFF) && + boot_cpu_has(X86_FEATURE_SBPB)) + x86_pred_cmd = PRED_CMD_SBPB; +} + +#undef pr_fmt #define pr_fmt(fmt) fmt #ifdef CONFIG_SYSFS @@ -2405,6 +2680,21 @@ static ssize_t retbleed_show_state(char *buf) return sprintf(buf, "%s\n", retbleed_strings[retbleed_mitigation]); } +static ssize_t gds_show_state(char *buf) +{ + return sysfs_emit(buf, "%s\n", gds_strings[gds_mitigation]); +} + +static ssize_t srso_show_state(char *buf) +{ + if (boot_cpu_has(X86_FEATURE_SRSO_NO)) + return sysfs_emit(buf, "Mitigation: SMT disabled\n"); + + return sysfs_emit(buf, "%s%s\n", + srso_strings[srso_mitigation], + (cpu_has_ibpb_brtype_microcode() ? "" : ", no microcode")); +} + static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr, char *buf, unsigned int bug) { @@ -2454,6 +2744,12 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr case X86_BUG_RETBLEED: return retbleed_show_state(buf); + case X86_BUG_GDS: + return gds_show_state(buf); + + case X86_BUG_SRSO: + return srso_show_state(buf); + default: break; } @@ -2518,4 +2814,14 @@ ssize_t cpu_show_retbleed(struct device *dev, struct device_attribute *attr, cha { return cpu_show_common(dev, attr, buf, X86_BUG_RETBLEED); } + +ssize_t cpu_show_gds(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_GDS); +} + +ssize_t cpu_show_spec_rstack_overflow(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_SRSO); +} #endif diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index d298d70f74ce..d38ae25e7c01 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -18,11 +18,15 @@ #include <linux/init.h> #include <linux/kprobes.h> #include <linux/kgdb.h> +#include <linux/mem_encrypt.h> #include <linux/smp.h> +#include <linux/cpu.h> #include <linux/io.h> #include <linux/syscore_ops.h> #include <linux/pgtable.h> +#include <linux/utsname.h> +#include <asm/alternative.h> #include <asm/cmdline.h> #include <asm/stackprotector.h> #include <asm/perf_event.h> @@ -58,7 +62,7 @@ #include <asm/intel-family.h> #include <asm/cpu_device_id.h> #include <asm/uv/uv.h> -#include <asm/sigframe.h> +#include <asm/set_memory.h> #include <asm/traps.h> #include <asm/sev.h> @@ -1072,6 +1076,9 @@ void get_cpu_cap(struct cpuinfo_x86 *c) if (c->extended_cpuid_level >= 0x8000001f) c->x86_capability[CPUID_8000_001F_EAX] = cpuid_eax(0x8000001f); + if (c->extended_cpuid_level >= 0x80000021) + c->x86_capability[CPUID_8000_0021_EAX] = cpuid_eax(0x80000021); + init_scattered_cpuid_features(c); init_speculation_control(c); @@ -1237,6 +1244,10 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { #define RETBLEED BIT(3) /* CPU is affected by SMT (cross-thread) return predictions */ #define SMT_RSB BIT(4) +/* CPU is affected by SRSO */ +#define SRSO BIT(5) +/* CPU is affected by GDS */ +#define GDS BIT(6) static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(IVYBRIDGE, X86_STEPPING_ANY, SRBDS), @@ -1249,27 +1260,30 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(BROADWELL_X, X86_STEPPING_ANY, MMIO), VULNBL_INTEL_STEPPINGS(BROADWELL, X86_STEPPING_ANY, SRBDS), VULNBL_INTEL_STEPPINGS(SKYLAKE_L, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED), - VULNBL_INTEL_STEPPINGS(SKYLAKE_X, X86_STEPPING_ANY, MMIO | RETBLEED), + VULNBL_INTEL_STEPPINGS(SKYLAKE_X, X86_STEPPING_ANY, MMIO | RETBLEED | GDS), VULNBL_INTEL_STEPPINGS(SKYLAKE, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED), - VULNBL_INTEL_STEPPINGS(KABYLAKE_L, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED), - VULNBL_INTEL_STEPPINGS(KABYLAKE, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED), + VULNBL_INTEL_STEPPINGS(KABYLAKE_L, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED | GDS), + VULNBL_INTEL_STEPPINGS(KABYLAKE, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED | GDS), VULNBL_INTEL_STEPPINGS(CANNONLAKE_L, X86_STEPPING_ANY, RETBLEED), - VULNBL_INTEL_STEPPINGS(ICELAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED), - VULNBL_INTEL_STEPPINGS(ICELAKE_D, X86_STEPPING_ANY, MMIO), - VULNBL_INTEL_STEPPINGS(ICELAKE_X, X86_STEPPING_ANY, MMIO), - VULNBL_INTEL_STEPPINGS(COMETLAKE, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED), + VULNBL_INTEL_STEPPINGS(ICELAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS), + VULNBL_INTEL_STEPPINGS(ICELAKE_D, X86_STEPPING_ANY, MMIO | GDS), + VULNBL_INTEL_STEPPINGS(ICELAKE_X, X86_STEPPING_ANY, MMIO | GDS), + VULNBL_INTEL_STEPPINGS(COMETLAKE, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS), VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPINGS(0x0, 0x0), MMIO | RETBLEED), - VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED), + VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS), + VULNBL_INTEL_STEPPINGS(TIGERLAKE_L, X86_STEPPING_ANY, GDS), + VULNBL_INTEL_STEPPINGS(TIGERLAKE, X86_STEPPING_ANY, GDS), VULNBL_INTEL_STEPPINGS(LAKEFIELD, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED), - VULNBL_INTEL_STEPPINGS(ROCKETLAKE, X86_STEPPING_ANY, MMIO | RETBLEED), + VULNBL_INTEL_STEPPINGS(ROCKETLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS), VULNBL_INTEL_STEPPINGS(ATOM_TREMONT, X86_STEPPING_ANY, MMIO | MMIO_SBDS), VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_D, X86_STEPPING_ANY, MMIO), VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS), VULNBL_AMD(0x15, RETBLEED), VULNBL_AMD(0x16, RETBLEED), - VULNBL_AMD(0x17, RETBLEED | SMT_RSB), + VULNBL_AMD(0x17, RETBLEED | SMT_RSB | SRSO), VULNBL_HYGON(0x18, RETBLEED | SMT_RSB), + VULNBL_AMD(0x19, SRSO), {} }; @@ -1390,6 +1404,21 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) if (cpu_matches(cpu_vuln_blacklist, SMT_RSB)) setup_force_cpu_bug(X86_BUG_SMT_RSB); + /* + * Check if CPU is vulnerable to GDS. If running in a virtual machine on + * an affected processor, the VMM may have disabled the use of GATHER by + * disabling AVX2. The only way to do this in HW is to clear XCR0[2], + * which means that AVX will be disabled. + */ + if (cpu_matches(cpu_vuln_blacklist, GDS) && !(ia32_cap & ARCH_CAP_GDS_NO) && + boot_cpu_has(X86_FEATURE_AVX)) + setup_force_cpu_bug(X86_BUG_GDS); + + if (!cpu_has(c, X86_FEATURE_SRSO_NO)) { + if (cpu_matches(cpu_vuln_blacklist, SRSO)) + setup_force_cpu_bug(X86_BUG_SRSO); + } + if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return; @@ -1571,10 +1600,6 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) sld_setup(c); - fpu__init_system(c); - - init_sigframe_size(); - #ifdef CONFIG_X86_32 /* * Regardless of whether PCID is enumerated, the SDM says @@ -1957,6 +1982,8 @@ void identify_secondary_cpu(struct cpuinfo_x86 *c) validate_apic_and_package_id(c); x86_spec_ctrl_setup_ap(); update_srbds_msr(); + if (boot_cpu_has_bug(X86_BUG_GDS)) + update_gds_msr(); tsx_ap_init(); } @@ -2290,8 +2317,6 @@ void cpu_init(void) doublefault_init_cpu_tss(); - fpu__init_cpu(); - if (is_uv_system()) uv_cpu_init(); @@ -2307,6 +2332,7 @@ void cpu_init_secondary(void) */ cpu_init_exception_handling(); cpu_init(); + fpu__init_cpu(); } #endif @@ -2369,3 +2395,69 @@ void arch_smt_update(void) /* Check whether IPI broadcasting can be enabled */ apic_smt_update(); } + +void __init arch_cpu_finalize_init(void) +{ + identify_boot_cpu(); + + /* + * identify_boot_cpu() initialized SMT support information, let the + * core code know. + */ + cpu_smt_check_topology(); + + if (!IS_ENABLED(CONFIG_SMP)) { + pr_info("CPU: "); + print_cpu_info(&boot_cpu_data); + } + + cpu_select_mitigations(); + + arch_smt_update(); + + if (IS_ENABLED(CONFIG_X86_32)) { + /* + * Check whether this is a real i386 which is not longer + * supported and fixup the utsname. + */ + if (boot_cpu_data.x86 < 4) + panic("Kernel requires i486+ for 'invlpg' and other features"); + + init_utsname()->machine[1] = + '0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86); + } + + /* + * Must be before alternatives because it might set or clear + * feature bits. + */ + fpu__init_system(); + fpu__init_cpu(); + + alternative_instructions(); + + if (IS_ENABLED(CONFIG_X86_64)) { + /* + * Make sure the first 2MB area is not mapped by huge pages + * There are typically fixed size MTRRs in there and overlapping + * MTRRs into large pages causes slow downs. + * + * Right now we don't do that with gbpages because there seems + * very little benefit for that case. + */ + if (!direct_gbpages) + set_memory_4k((unsigned long)__va(0), 1); + } else { + fpu__init_check_bugs(); + } + + /* + * This needs to be called before any devices perform DMA + * operations that might use the SWIOTLB bounce buffers. It will + * mark the bounce buffers as decrypted so that their usage will + * not cause "plain-text" data to be decrypted when accessed. It + * must be called after late_time_init() so that Hyper-V x86/x64 + * hypercalls work when the SWIOTLB bounce buffers are decrypted. + */ + mem_encrypt_init(); +} diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index 7c9b5893c30a..d9aeb335002d 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -79,9 +79,11 @@ extern void detect_ht(struct cpuinfo_x86 *c); extern void check_null_seg_clears_base(struct cpuinfo_x86 *c); unsigned int aperfmperf_get_khz(int cpu); +void cpu_select_mitigations(void); extern void x86_spec_ctrl_setup_ap(void); extern void update_srbds_msr(void); +extern void update_gds_msr(void); extern u64 x86_read_arch_cap_msr(void); diff --git a/arch/x86/kernel/fpu/context.h b/arch/x86/kernel/fpu/context.h index 9fcfa5c4dad7..71b5059e092a 100644 --- a/arch/x86/kernel/fpu/context.h +++ b/arch/x86/kernel/fpu/context.h @@ -19,8 +19,7 @@ * FPU state for a task MUST let the rest of the kernel know that the * FPU registers are no longer valid for this task. * - * Either one of these invalidation functions is enough. Invalidate - * a resource you control: CPU if using the CPU for something else + * Invalidate a resource you control: CPU if using the CPU for something else * (with preemption disabled), FPU for the current task, or a task that * is prevented from running by the current task. */ diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index caf33486dc5e..a083f9ac9e4f 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -679,7 +679,7 @@ static void fpu_reset_fpregs(void) struct fpu *fpu = ¤t->thread.fpu; fpregs_lock(); - fpu__drop(fpu); + __fpu_invalidate_fpregs_state(fpu); /* * This does not change the actual hardware registers. It just * resets the memory image and sets TIF_NEED_FPU_LOAD so a diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index 851eb13edc01..998a08f17e33 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -53,7 +53,7 @@ void fpu__init_cpu(void) fpu__init_cpu_xstate(); } -static bool fpu__probe_without_cpuid(void) +static bool __init fpu__probe_without_cpuid(void) { unsigned long cr0; u16 fsw, fcw; @@ -71,7 +71,7 @@ static bool fpu__probe_without_cpuid(void) return fsw == 0 && (fcw & 0x103f) == 0x003f; } -static void fpu__init_system_early_generic(struct cpuinfo_x86 *c) +static void __init fpu__init_system_early_generic(void) { if (!boot_cpu_has(X86_FEATURE_CPUID) && !test_bit(X86_FEATURE_FPU, (unsigned long *)cpu_caps_cleared)) { @@ -211,10 +211,10 @@ static void __init fpu__init_system_xstate_size_legacy(void) * Called on the boot CPU once per system bootup, to set up the initial * FPU state that is later cloned into all processes: */ -void __init fpu__init_system(struct cpuinfo_x86 *c) +void __init fpu__init_system(void) { fpstate_reset(¤t->thread.fpu); - fpu__init_system_early_generic(c); + fpu__init_system_early_generic(); /* * The FPU has to be operational for some of the diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 0bab497c9436..1afbc4866b10 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -882,6 +882,13 @@ void __init fpu__init_system_xstate(unsigned int legacy_size) goto out_disable; } + /* + * CPU capabilities initialization runs before FPU init. So + * X86_FEATURE_OSXSAVE is not set. Now that XSAVE is completely + * functional, set the feature bit so depending code works. + */ + setup_force_cpu_cap(X86_FEATURE_OSXSAVE); + print_xstate_offset_size(); pr_info("x86/fpu: Enabled xstate features 0x%llx, context size is %d bytes, using '%s' format.\n", fpu_kernel_cfg.max_features, diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 82c562e2cc98..55ed638cb3fd 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -724,7 +724,7 @@ badframe: static unsigned long __ro_after_init max_frame_size; static unsigned int __ro_after_init fpu_default_state_size; -void __init init_sigframe_size(void) +static int __init init_sigframe_size(void) { fpu_default_state_size = fpu__get_fpstate_size(); @@ -736,7 +736,9 @@ void __init init_sigframe_size(void) max_frame_size = round_up(max_frame_size, FRAME_ALIGNMENT); pr_info("max sigframe size: %lu\n", max_frame_size); + return 0; } +early_initcall(init_sigframe_size); unsigned long get_sigframe_size(void) { diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c index a9b54b795ebf..3fbb49168827 100644 --- a/arch/x86/kernel/static_call.c +++ b/arch/x86/kernel/static_call.c @@ -184,6 +184,19 @@ EXPORT_SYMBOL_GPL(arch_static_call_transform); */ bool __static_call_fixup(void *tramp, u8 op, void *dest) { + unsigned long addr = (unsigned long)tramp; + /* + * Not all .return_sites are a static_call trampoline (most are not). + * Check if the 3 bytes after the return are still kernel text, if not, + * then this definitely is not a trampoline and we need not worry + * further. + * + * This avoids the memcmp() below tripping over pagefaults etc.. + */ + if (((addr >> PAGE_SHIFT) != ((addr + 7) >> PAGE_SHIFT)) && + !kernel_text_address(addr + 7)) + return false; + if (memcmp(tramp+5, tramp_ud, 3)) { /* Not a trampoline site, not our problem. */ return false; diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 15f29053cec4..78ccb5ec3c0e 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -133,7 +133,20 @@ SECTIONS LOCK_TEXT KPROBES_TEXT ALIGN_ENTRY_TEXT_BEGIN +#ifdef CONFIG_CPU_SRSO + *(.text..__x86.rethunk_untrain) +#endif + ENTRY_TEXT + +#ifdef CONFIG_CPU_SRSO + /* + * See the comment above srso_alias_untrain_ret()'s + * definition. + */ + . = srso_alias_untrain_ret | (1 << 2) | (1 << 8) | (1 << 14) | (1 << 20); + *(.text..__x86.rethunk_safe) +#endif ALIGN_ENTRY_TEXT_END SOFTIRQENTRY_TEXT STATIC_CALL_TEXT @@ -141,13 +154,15 @@ SECTIONS #ifdef CONFIG_RETPOLINE __indirect_thunk_start = .; - *(.text.__x86.*) + *(.text..__x86.indirect_thunk) + *(.text..__x86.return_thunk) __indirect_thunk_end = .; #endif } :text =0xcccc /* End of text section, which should occupy whole number of pages */ _etext = .; + . = ALIGN(PAGE_SIZE); X86_ALIGN_RODATA_BEGIN @@ -492,6 +507,27 @@ INIT_PER_CPU(irq_stack_backing_store); "fixed_percpu_data is not at start of per-cpu area"); #endif +#ifdef CONFIG_RETHUNK +. = ASSERT((retbleed_return_thunk & 0x3f) == 0, "retbleed_return_thunk not cacheline-aligned"); +. = ASSERT((srso_safe_ret & 0x3f) == 0, "srso_safe_ret not cacheline-aligned"); +#endif + +#ifdef CONFIG_CPU_SRSO +/* + * GNU ld cannot do XOR until 2.41. + * https://sourceware.org/git/?p=binutils-gdb.git;a=commit;h=f6f78318fca803c4907fb8d7f6ded8295f1947b1 + * + * LLVM lld cannot do XOR until lld-17. + * https://github.com/llvm/llvm-project/commit/fae96104d4378166cbe5c875ef8ed808a356f3fb + * + * Instead do: (A | B) - (A & B) in order to compute the XOR + * of the two function addresses: + */ +. = ASSERT(((ABSOLUTE(srso_alias_untrain_ret) | srso_alias_safe_ret) - + (ABSOLUTE(srso_alias_untrain_ret) & srso_alias_safe_ret)) == ((1 << 2) | (1 << 8) | (1 << 14) | (1 << 20)), + "SRSO function pair won't alias"); +#endif + #endif /* CONFIG_X86_64 */ #ifdef CONFIG_KEXEC_CORE diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 6047dbe04880..7b4224f5ee2d 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -736,6 +736,9 @@ void kvm_set_cpu_caps(void) F(PMM) | F(PMM_EN) ); + if (cpu_feature_enabled(X86_FEATURE_SRSO_NO)) + kvm_cpu_cap_set(X86_FEATURE_SRSO_NO); + /* * Hide RDTSCP and RDPID if either feature is reported as supported but * probing MSR_TSC_AUX failed. This is purely a sanity check and diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 230108a90cf3..beca03556379 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -4212,7 +4212,8 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) * root was invalidated by a memslot update or a relevant mmu_notifier fired. */ static bool is_page_fault_stale(struct kvm_vcpu *vcpu, - struct kvm_page_fault *fault, int mmu_seq) + struct kvm_page_fault *fault, + unsigned long mmu_seq) { struct kvm_mmu_page *sp = to_shadow_page(vcpu->arch.mmu->root.hpa); diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 672f0432d777..70945f00ec41 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -51,7 +51,17 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm) if (!kvm->arch.tdp_mmu_enabled) return; - /* Also waits for any queued work items. */ + /* + * Invalidate all roots, which besides the obvious, schedules all roots + * for zapping and thus puts the TDP MMU's reference to each root, i.e. + * ultimately frees all roots. + */ + kvm_tdp_mmu_invalidate_all_roots(kvm); + + /* + * Destroying a workqueue also first flushes the workqueue, i.e. no + * need to invoke kvm_tdp_mmu_zap_invalidated_roots(). + */ destroy_workqueue(kvm->arch.tdp_mmu_zap_wq); WARN_ON(!list_empty(&kvm->arch.tdp_mmu_pages)); @@ -127,16 +137,6 @@ static void tdp_mmu_schedule_zap_root(struct kvm *kvm, struct kvm_mmu_page *root queue_work(kvm->arch.tdp_mmu_zap_wq, &root->tdp_mmu_async_work); } -static inline bool kvm_tdp_root_mark_invalid(struct kvm_mmu_page *page) -{ - union kvm_mmu_page_role role = page->role; - role.invalid = true; - - /* No need to use cmpxchg, only the invalid bit can change. */ - role.word = xchg(&page->role.word, role.word); - return role.invalid; -} - void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root, bool shared) { @@ -145,45 +145,12 @@ void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root, if (!refcount_dec_and_test(&root->tdp_mmu_root_count)) return; - WARN_ON(!root->tdp_mmu_page); - /* - * The root now has refcount=0. It is valid, but readers already - * cannot acquire a reference to it because kvm_tdp_mmu_get_root() - * rejects it. This remains true for the rest of the execution - * of this function, because readers visit valid roots only - * (except for tdp_mmu_zap_root_work(), which however - * does not acquire any reference itself). - * - * Even though there are flows that need to visit all roots for - * correctness, they all take mmu_lock for write, so they cannot yet - * run concurrently. The same is true after kvm_tdp_root_mark_invalid, - * since the root still has refcount=0. - * - * However, tdp_mmu_zap_root can yield, and writers do not expect to - * see refcount=0 (see for example kvm_tdp_mmu_invalidate_all_roots()). - * So the root temporarily gets an extra reference, going to refcount=1 - * while staying invalid. Readers still cannot acquire any reference; - * but writers are now allowed to run if tdp_mmu_zap_root yields and - * they might take an extra reference if they themselves yield. - * Therefore, when the reference is given back by the worker, - * there is no guarantee that the refcount is still 1. If not, whoever - * puts the last reference will free the page, but they will not have to - * zap the root because a root cannot go from invalid to valid. + * The TDP MMU itself holds a reference to each root until the root is + * explicitly invalidated, i.e. the final reference should be never be + * put for a valid root. */ - if (!kvm_tdp_root_mark_invalid(root)) { - refcount_set(&root->tdp_mmu_root_count, 1); - - /* - * Zapping the root in a worker is not just "nice to have"; - * it is required because kvm_tdp_mmu_invalidate_all_roots() - * skips already-invalid roots. If kvm_tdp_mmu_put_root() did - * not add the root to the workqueue, kvm_tdp_mmu_zap_all_fast() - * might return with some roots not zapped yet. - */ - tdp_mmu_schedule_zap_root(kvm, root); - return; - } + KVM_BUG_ON(!is_tdp_mmu_page(root) || !root->role.invalid, kvm); spin_lock(&kvm->arch.tdp_mmu_pages_lock); list_del_rcu(&root->link); @@ -329,7 +296,14 @@ hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu) root = tdp_mmu_alloc_sp(vcpu); tdp_mmu_init_sp(root, NULL, 0, role); - refcount_set(&root->tdp_mmu_root_count, 1); + /* + * TDP MMU roots are kept until they are explicitly invalidated, either + * by a memslot update or by the destruction of the VM. Initialize the + * refcount to two; one reference for the vCPU, and one reference for + * the TDP MMU itself, which is held until the root is invalidated and + * is ultimately put by tdp_mmu_zap_root_work(). + */ + refcount_set(&root->tdp_mmu_root_count, 2); spin_lock(&kvm->arch.tdp_mmu_pages_lock); list_add_rcu(&root->link, &kvm->arch.tdp_mmu_roots); @@ -1027,32 +1001,49 @@ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm) /* * Mark each TDP MMU root as invalid to prevent vCPUs from reusing a root that * is about to be zapped, e.g. in response to a memslots update. The actual - * zapping is performed asynchronously, so a reference is taken on all roots. - * Using a separate workqueue makes it easy to ensure that the destruction is - * performed before the "fast zap" completes, without keeping a separate list - * of invalidated roots; the list is effectively the list of work items in - * the workqueue. - * - * Get a reference even if the root is already invalid, the asynchronous worker - * assumes it was gifted a reference to the root it processes. Because mmu_lock - * is held for write, it should be impossible to observe a root with zero refcount, - * i.e. the list of roots cannot be stale. + * zapping is performed asynchronously. Using a separate workqueue makes it + * easy to ensure that the destruction is performed before the "fast zap" + * completes, without keeping a separate list of invalidated roots; the list is + * effectively the list of work items in the workqueue. * - * This has essentially the same effect for the TDP MMU - * as updating mmu_valid_gen does for the shadow MMU. + * Note, the asynchronous worker is gifted the TDP MMU's reference. + * See kvm_tdp_mmu_get_vcpu_root_hpa(). */ void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm) { struct kvm_mmu_page *root; - lockdep_assert_held_write(&kvm->mmu_lock); - list_for_each_entry(root, &kvm->arch.tdp_mmu_roots, link) { - if (!root->role.invalid && - !WARN_ON_ONCE(!kvm_tdp_mmu_get_root(root))) { + /* + * mmu_lock must be held for write to ensure that a root doesn't become + * invalid while there are active readers (invalidating a root while + * there are active readers may or may not be problematic in practice, + * but it's uncharted territory and not supported). + * + * Waive the assertion if there are no users of @kvm, i.e. the VM is + * being destroyed after all references have been put, or if no vCPUs + * have been created (which means there are no roots), i.e. the VM is + * being destroyed in an error path of KVM_CREATE_VM. + */ + if (IS_ENABLED(CONFIG_PROVE_LOCKING) && + refcount_read(&kvm->users_count) && kvm->created_vcpus) + lockdep_assert_held_write(&kvm->mmu_lock); + + /* + * As above, mmu_lock isn't held when destroying the VM! There can't + * be other references to @kvm, i.e. nothing else can invalidate roots + * or be consuming roots, but walking the list of roots does need to be + * guarded against roots being deleted by the asynchronous zap worker. + */ + rcu_read_lock(); + + list_for_each_entry_rcu(root, &kvm->arch.tdp_mmu_roots, link) { + if (!root->role.invalid) { root->role.invalid = true; tdp_mmu_schedule_zap_root(kvm, root); } } + + rcu_read_unlock(); } /* diff --git a/arch/x86/kvm/reverse_cpuid.h b/arch/x86/kvm/reverse_cpuid.h index a19d473d0184..7eeade35a425 100644 --- a/arch/x86/kvm/reverse_cpuid.h +++ b/arch/x86/kvm/reverse_cpuid.h @@ -48,6 +48,7 @@ static const struct cpuid_reg reverse_cpuid[] = { [CPUID_7_1_EAX] = { 7, 1, CPUID_EAX}, [CPUID_12_EAX] = {0x00000012, 0, CPUID_EAX}, [CPUID_8000_001F_EAX] = {0x8000001f, 0, CPUID_EAX}, + [CPUID_8000_0021_EAX] = {0x80000021, 0, CPUID_EAX}, }; /* diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 4cb2e483db53..e0437acb5cf7 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -2410,15 +2410,18 @@ static void sev_es_sync_from_ghcb(struct vcpu_svm *svm) */ memset(vcpu->arch.regs, 0, sizeof(vcpu->arch.regs)); - vcpu->arch.regs[VCPU_REGS_RAX] = ghcb_get_rax_if_valid(ghcb); - vcpu->arch.regs[VCPU_REGS_RBX] = ghcb_get_rbx_if_valid(ghcb); - vcpu->arch.regs[VCPU_REGS_RCX] = ghcb_get_rcx_if_valid(ghcb); - vcpu->arch.regs[VCPU_REGS_RDX] = ghcb_get_rdx_if_valid(ghcb); - vcpu->arch.regs[VCPU_REGS_RSI] = ghcb_get_rsi_if_valid(ghcb); + BUILD_BUG_ON(sizeof(svm->sev_es.valid_bitmap) != sizeof(ghcb->save.valid_bitmap)); + memcpy(&svm->sev_es.valid_bitmap, &ghcb->save.valid_bitmap, sizeof(ghcb->save.valid_bitmap)); - svm->vmcb->save.cpl = ghcb_get_cpl_if_valid(ghcb); + vcpu->arch.regs[VCPU_REGS_RAX] = kvm_ghcb_get_rax_if_valid(svm, ghcb); + vcpu->arch.regs[VCPU_REGS_RBX] = kvm_ghcb_get_rbx_if_valid(svm, ghcb); + vcpu->arch.regs[VCPU_REGS_RCX] = kvm_ghcb_get_rcx_if_valid(svm, ghcb); + vcpu->arch.regs[VCPU_REGS_RDX] = kvm_ghcb_get_rdx_if_valid(svm, ghcb); + vcpu->arch.regs[VCPU_REGS_RSI] = kvm_ghcb_get_rsi_if_valid(svm, ghcb); - if (ghcb_xcr0_is_valid(ghcb)) { + svm->vmcb->save.cpl = kvm_ghcb_get_cpl_if_valid(svm, ghcb); + + if (kvm_ghcb_xcr0_is_valid(svm)) { vcpu->arch.xcr0 = ghcb_get_xcr0(ghcb); kvm_update_cpuid_runtime(vcpu); } @@ -2429,14 +2432,21 @@ static void sev_es_sync_from_ghcb(struct vcpu_svm *svm) control->exit_code_hi = upper_32_bits(exit_code); control->exit_info_1 = ghcb_get_sw_exit_info_1(ghcb); control->exit_info_2 = ghcb_get_sw_exit_info_2(ghcb); + svm->sev_es.sw_scratch = kvm_ghcb_get_sw_scratch_if_valid(svm, ghcb); /* Clear the valid entries fields */ memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap)); } +static u64 kvm_ghcb_get_sw_exit_code(struct vmcb_control_area *control) +{ + return (((u64)control->exit_code_hi) << 32) | control->exit_code; +} + static int sev_es_validate_vmgexit(struct vcpu_svm *svm) { - struct kvm_vcpu *vcpu; + struct vmcb_control_area *control = &svm->vmcb->control; + struct kvm_vcpu *vcpu = &svm->vcpu; struct ghcb *ghcb; u64 exit_code; u64 reason; @@ -2447,7 +2457,7 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm) * Retrieve the exit code now even though it may not be marked valid * as it could help with debugging. */ - exit_code = ghcb_get_sw_exit_code(ghcb); + exit_code = kvm_ghcb_get_sw_exit_code(control); /* Only GHCB Usage code 0 is supported */ if (ghcb->ghcb_usage) { @@ -2457,56 +2467,56 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm) reason = GHCB_ERR_MISSING_INPUT; - if (!ghcb_sw_exit_code_is_valid(ghcb) || - !ghcb_sw_exit_info_1_is_valid(ghcb) || - !ghcb_sw_exit_info_2_is_valid(ghcb)) + if (!kvm_ghcb_sw_exit_code_is_valid(svm) || + !kvm_ghcb_sw_exit_info_1_is_valid(svm) || + !kvm_ghcb_sw_exit_info_2_is_valid(svm)) goto vmgexit_err; - switch (ghcb_get_sw_exit_code(ghcb)) { + switch (exit_code) { case SVM_EXIT_READ_DR7: break; case SVM_EXIT_WRITE_DR7: - if (!ghcb_rax_is_valid(ghcb)) + if (!kvm_ghcb_rax_is_valid(svm)) goto vmgexit_err; break; case SVM_EXIT_RDTSC: break; case SVM_EXIT_RDPMC: - if (!ghcb_rcx_is_valid(ghcb)) + if (!kvm_ghcb_rcx_is_valid(svm)) goto vmgexit_err; break; case SVM_EXIT_CPUID: - if (!ghcb_rax_is_valid(ghcb) || - !ghcb_rcx_is_valid(ghcb)) + if (!kvm_ghcb_rax_is_valid(svm) || + !kvm_ghcb_rcx_is_valid(svm)) goto vmgexit_err; - if (ghcb_get_rax(ghcb) == 0xd) - if (!ghcb_xcr0_is_valid(ghcb)) + if (vcpu->arch.regs[VCPU_REGS_RAX] == 0xd) + if (!kvm_ghcb_xcr0_is_valid(svm)) goto vmgexit_err; break; case SVM_EXIT_INVD: break; case SVM_EXIT_IOIO: - if (ghcb_get_sw_exit_info_1(ghcb) & SVM_IOIO_STR_MASK) { - if (!ghcb_sw_scratch_is_valid(ghcb)) + if (control->exit_info_1 & SVM_IOIO_STR_MASK) { + if (!kvm_ghcb_sw_scratch_is_valid(svm)) goto vmgexit_err; } else { - if (!(ghcb_get_sw_exit_info_1(ghcb) & SVM_IOIO_TYPE_MASK)) - if (!ghcb_rax_is_valid(ghcb)) + if (!(control->exit_info_1 & SVM_IOIO_TYPE_MASK)) + if (!kvm_ghcb_rax_is_valid(svm)) goto vmgexit_err; } break; case SVM_EXIT_MSR: - if (!ghcb_rcx_is_valid(ghcb)) + if (!kvm_ghcb_rcx_is_valid(svm)) goto vmgexit_err; - if (ghcb_get_sw_exit_info_1(ghcb)) { - if (!ghcb_rax_is_valid(ghcb) || - !ghcb_rdx_is_valid(ghcb)) + if (control->exit_info_1) { + if (!kvm_ghcb_rax_is_valid(svm) || + !kvm_ghcb_rdx_is_valid(svm)) goto vmgexit_err; } break; case SVM_EXIT_VMMCALL: - if (!ghcb_rax_is_valid(ghcb) || - !ghcb_cpl_is_valid(ghcb)) + if (!kvm_ghcb_rax_is_valid(svm) || + !kvm_ghcb_cpl_is_valid(svm)) goto vmgexit_err; break; case SVM_EXIT_RDTSCP: @@ -2514,19 +2524,19 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm) case SVM_EXIT_WBINVD: break; case SVM_EXIT_MONITOR: - if (!ghcb_rax_is_valid(ghcb) || - !ghcb_rcx_is_valid(ghcb) || - !ghcb_rdx_is_valid(ghcb)) + if (!kvm_ghcb_rax_is_valid(svm) || + !kvm_ghcb_rcx_is_valid(svm) || + !kvm_ghcb_rdx_is_valid(svm)) goto vmgexit_err; break; case SVM_EXIT_MWAIT: - if (!ghcb_rax_is_valid(ghcb) || - !ghcb_rcx_is_valid(ghcb)) + if (!kvm_ghcb_rax_is_valid(svm) || + !kvm_ghcb_rcx_is_valid(svm)) goto vmgexit_err; break; case SVM_VMGEXIT_MMIO_READ: case SVM_VMGEXIT_MMIO_WRITE: - if (!ghcb_sw_scratch_is_valid(ghcb)) + if (!kvm_ghcb_sw_scratch_is_valid(svm)) goto vmgexit_err; break; case SVM_VMGEXIT_NMI_COMPLETE: @@ -2542,8 +2552,6 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm) return 0; vmgexit_err: - vcpu = &svm->vcpu; - if (reason == GHCB_ERR_INVALID_USAGE) { vcpu_unimpl(vcpu, "vmgexit: ghcb usage %#x is not valid\n", ghcb->ghcb_usage); @@ -2556,9 +2564,6 @@ vmgexit_err: dump_ghcb(svm); } - /* Clear the valid entries fields */ - memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap)); - ghcb_set_sw_exit_info_1(ghcb, 2); ghcb_set_sw_exit_info_2(ghcb, reason); @@ -2579,7 +2584,7 @@ void sev_es_unmap_ghcb(struct vcpu_svm *svm) */ if (svm->sev_es.ghcb_sa_sync) { kvm_write_guest(svm->vcpu.kvm, - ghcb_get_sw_scratch(svm->sev_es.ghcb), + svm->sev_es.sw_scratch, svm->sev_es.ghcb_sa, svm->sev_es.ghcb_sa_len); svm->sev_es.ghcb_sa_sync = false; @@ -2630,7 +2635,7 @@ static int setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len) u64 scratch_gpa_beg, scratch_gpa_end; void *scratch_va; - scratch_gpa_beg = ghcb_get_sw_scratch(ghcb); + scratch_gpa_beg = svm->sev_es.sw_scratch; if (!scratch_gpa_beg) { pr_err("vmgexit: scratch gpa not provided\n"); goto e_scratch; @@ -2844,16 +2849,15 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu) trace_kvm_vmgexit_enter(vcpu->vcpu_id, ghcb); - exit_code = ghcb_get_sw_exit_code(ghcb); - + sev_es_sync_from_ghcb(svm); ret = sev_es_validate_vmgexit(svm); if (ret) return ret; - sev_es_sync_from_ghcb(svm); ghcb_set_sw_exit_info_1(ghcb, 0); ghcb_set_sw_exit_info_2(ghcb, 0); + exit_code = kvm_ghcb_get_sw_exit_code(control); switch (exit_code) { case SVM_VMGEXIT_MMIO_READ: ret = setup_vmgexit_scratch(svm, true, control->exit_info_2); diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 0a212fe2cd39..a96f9a17e8b5 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1485,7 +1485,9 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) if (sd->current_vmcb != svm->vmcb) { sd->current_vmcb = svm->vmcb; - indirect_branch_prediction_barrier(); + + if (!cpu_feature_enabled(X86_FEATURE_IBPB_ON_VMEXIT)) + indirect_branch_prediction_barrier(); } if (kvm_vcpu_apicv_active(vcpu)) avic_vcpu_load(vcpu, cpu); @@ -3945,6 +3947,8 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu, bool spec_ctrl_in guest_state_enter_irqoff(); + amd_clear_divider(); + if (sev_es_guest(vcpu->kvm)) __svm_sev_es_vcpu_run(svm, spec_ctrl_intercepted); else diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index d0ed3f595229..62f87492763e 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -196,10 +196,12 @@ struct vcpu_sev_es_state { /* SEV-ES support */ struct sev_es_save_area *vmsa; struct ghcb *ghcb; + u8 valid_bitmap[16]; struct kvm_host_map ghcb_map; bool received_first_sipi; /* SEV-ES scratch area support */ + u64 sw_scratch; void *ghcb_sa; u32 ghcb_sa_len; bool ghcb_sa_sync; @@ -688,4 +690,28 @@ void sev_es_unmap_ghcb(struct vcpu_svm *svm); void __svm_sev_es_vcpu_run(struct vcpu_svm *svm, bool spec_ctrl_intercepted); void __svm_vcpu_run(struct vcpu_svm *svm, bool spec_ctrl_intercepted); +#define DEFINE_KVM_GHCB_ACCESSORS(field) \ + static __always_inline bool kvm_ghcb_##field##_is_valid(const struct vcpu_svm *svm) \ + { \ + return test_bit(GHCB_BITMAP_IDX(field), \ + (unsigned long *)&svm->sev_es.valid_bitmap); \ + } \ + \ + static __always_inline u64 kvm_ghcb_get_##field##_if_valid(struct vcpu_svm *svm, struct ghcb *ghcb) \ + { \ + return kvm_ghcb_##field##_is_valid(svm) ? ghcb->save.field : 0; \ + } \ + +DEFINE_KVM_GHCB_ACCESSORS(cpl) +DEFINE_KVM_GHCB_ACCESSORS(rax) +DEFINE_KVM_GHCB_ACCESSORS(rcx) +DEFINE_KVM_GHCB_ACCESSORS(rdx) +DEFINE_KVM_GHCB_ACCESSORS(rbx) +DEFINE_KVM_GHCB_ACCESSORS(rsi) +DEFINE_KVM_GHCB_ACCESSORS(sw_exit_code) +DEFINE_KVM_GHCB_ACCESSORS(sw_exit_info_1) +DEFINE_KVM_GHCB_ACCESSORS(sw_exit_info_2) +DEFINE_KVM_GHCB_ACCESSORS(sw_scratch) +DEFINE_KVM_GHCB_ACCESSORS(xcr0) + #endif diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S index 34367dc203f2..5be9a63f09ff 100644 --- a/arch/x86/kvm/svm/vmenter.S +++ b/arch/x86/kvm/svm/vmenter.S @@ -223,6 +223,9 @@ SYM_FUNC_START(__svm_vcpu_run) */ UNTRAIN_RET + /* SRSO */ + ALTERNATIVE "", "call entry_ibpb", X86_FEATURE_IBPB_ON_VMEXIT + /* * Clear all general purpose registers except RSP and RAX to prevent * speculative use of the guest's values, even those that are reloaded diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 32f589b96d99..1931d3fcbbe0 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1613,7 +1613,7 @@ static unsigned int num_msr_based_features; ARCH_CAP_SKIP_VMENTRY_L1DFLUSH | ARCH_CAP_SSB_NO | ARCH_CAP_MDS_NO | \ ARCH_CAP_PSCHANGE_MC_NO | ARCH_CAP_TSX_CTRL_MSR | ARCH_CAP_TAA_NO | \ ARCH_CAP_SBDR_SSDP_NO | ARCH_CAP_FBSDP_NO | ARCH_CAP_PSDP_NO | \ - ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO) + ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO | ARCH_CAP_GDS_NO) static u64 kvm_get_arch_capabilities(void) { @@ -1670,6 +1670,9 @@ static u64 kvm_get_arch_capabilities(void) */ } + if (!boot_cpu_has_bug(X86_BUG_GDS) || gds_ucode_mitigated()) + data |= ARCH_CAP_GDS_NO; + return data; } diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index 841955dc2573..65c5c44f006b 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -9,8 +9,9 @@ #include <asm/nospec-branch.h> #include <asm/unwind_hints.h> #include <asm/frame.h> +#include <asm/nops.h> - .section .text.__x86.indirect_thunk + .section .text..__x86.indirect_thunk .macro RETPOLINE reg ANNOTATE_INTRA_FUNCTION_CALL @@ -74,36 +75,107 @@ SYM_CODE_END(__x86_indirect_thunk_array) */ #ifdef CONFIG_RETHUNK - .section .text.__x86.return_thunk +/* + * srso_alias_untrain_ret() and srso_alias_safe_ret() are placed at + * special addresses: + * + * - srso_alias_untrain_ret() is 2M aligned + * - srso_alias_safe_ret() is also in the same 2M page but bits 2, 8, 14 + * and 20 in its virtual address are set (while those bits in the + * srso_alias_untrain_ret() function are cleared). + * + * This guarantees that those two addresses will alias in the branch + * target buffer of Zen3/4 generations, leading to any potential + * poisoned entries at that BTB slot to get evicted. + * + * As a result, srso_alias_safe_ret() becomes a safe return. + */ +#ifdef CONFIG_CPU_SRSO + .section .text..__x86.rethunk_untrain + +SYM_START(srso_alias_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE) + UNWIND_HINT_FUNC + ANNOTATE_NOENDBR + ASM_NOP2 + lfence + jmp srso_alias_return_thunk +SYM_FUNC_END(srso_alias_untrain_ret) +__EXPORT_THUNK(srso_alias_untrain_ret) + + .section .text..__x86.rethunk_safe +#else +/* dummy definition for alternatives */ +SYM_START(srso_alias_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE) + ANNOTATE_UNRET_SAFE + ret + int3 +SYM_FUNC_END(srso_alias_untrain_ret) +#endif + +SYM_START(srso_alias_safe_ret, SYM_L_GLOBAL, SYM_A_NONE) + lea 8(%_ASM_SP), %_ASM_SP + UNWIND_HINT_FUNC + ANNOTATE_UNRET_SAFE + ret + int3 +SYM_FUNC_END(srso_alias_safe_ret) + + .section .text..__x86.return_thunk + +SYM_CODE_START(srso_alias_return_thunk) + UNWIND_HINT_FUNC + ANNOTATE_NOENDBR + call srso_alias_safe_ret + ud2 +SYM_CODE_END(srso_alias_return_thunk) + +/* + * Some generic notes on the untraining sequences: + * + * They are interchangeable when it comes to flushing potentially wrong + * RET predictions from the BTB. + * + * The SRSO Zen1/2 (MOVABS) untraining sequence is longer than the + * Retbleed sequence because the return sequence done there + * (srso_safe_ret()) is longer and the return sequence must fully nest + * (end before) the untraining sequence. Therefore, the untraining + * sequence must fully overlap the return sequence. + * + * Regarding alignment - the instructions which need to be untrained, + * must all start at a cacheline boundary for Zen1/2 generations. That + * is, instruction sequences starting at srso_safe_ret() and + * the respective instruction sequences at retbleed_return_thunk() + * must start at a cacheline boundary. + */ /* * Safety details here pertain to the AMD Zen{1,2} microarchitecture: - * 1) The RET at __x86_return_thunk must be on a 64 byte boundary, for + * 1) The RET at retbleed_return_thunk must be on a 64 byte boundary, for * alignment within the BTB. - * 2) The instruction at zen_untrain_ret must contain, and not + * 2) The instruction at retbleed_untrain_ret must contain, and not * end with, the 0xc3 byte of the RET. * 3) STIBP must be enabled, or SMT disabled, to prevent the sibling thread * from re-poisioning the BTB prediction. */ .align 64 - .skip 63, 0xcc -SYM_START(zen_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE) + .skip 64 - (retbleed_return_thunk - retbleed_untrain_ret), 0xcc +SYM_START(retbleed_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE) ANNOTATE_NOENDBR /* - * As executed from zen_untrain_ret, this is: + * As executed from retbleed_untrain_ret, this is: * * TEST $0xcc, %bl * LFENCE - * JMP __x86_return_thunk + * JMP retbleed_return_thunk * * Executing the TEST instruction has a side effect of evicting any BTB * prediction (potentially attacker controlled) attached to the RET, as - * __x86_return_thunk + 1 isn't an instruction boundary at the moment. + * retbleed_return_thunk + 1 isn't an instruction boundary at the moment. */ .byte 0xf6 /* - * As executed from __x86_return_thunk, this is a plain RET. + * As executed from retbleed_return_thunk, this is a plain RET. * * As part of the TEST above, RET is the ModRM byte, and INT3 the imm8. * @@ -115,13 +187,13 @@ SYM_START(zen_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE) * With SMT enabled and STIBP active, a sibling thread cannot poison * RET's prediction to a type of its choice, but can evict the * prediction due to competitive sharing. If the prediction is - * evicted, __x86_return_thunk will suffer Straight Line Speculation + * evicted, retbleed_return_thunk will suffer Straight Line Speculation * which will be contained safely by the INT3. */ -SYM_INNER_LABEL(__x86_return_thunk, SYM_L_GLOBAL) +SYM_INNER_LABEL(retbleed_return_thunk, SYM_L_GLOBAL) ret int3 -SYM_CODE_END(__x86_return_thunk) +SYM_CODE_END(retbleed_return_thunk) /* * Ensure the TEST decoding / BTB invalidation is complete. @@ -132,11 +204,67 @@ SYM_CODE_END(__x86_return_thunk) * Jump back and execute the RET in the middle of the TEST instruction. * INT3 is for SLS protection. */ - jmp __x86_return_thunk + jmp retbleed_return_thunk int3 -SYM_FUNC_END(zen_untrain_ret) -__EXPORT_THUNK(zen_untrain_ret) +SYM_FUNC_END(retbleed_untrain_ret) +__EXPORT_THUNK(retbleed_untrain_ret) +/* + * SRSO untraining sequence for Zen1/2, similar to retbleed_untrain_ret() + * above. On kernel entry, srso_untrain_ret() is executed which is a + * + * movabs $0xccccc30824648d48,%rax + * + * and when the return thunk executes the inner label srso_safe_ret() + * later, it is a stack manipulation and a RET which is mispredicted and + * thus a "safe" one to use. + */ + .align 64 + .skip 64 - (srso_safe_ret - srso_untrain_ret), 0xcc +SYM_START(srso_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE) + ANNOTATE_NOENDBR + .byte 0x48, 0xb8 + +/* + * This forces the function return instruction to speculate into a trap + * (UD2 in srso_return_thunk() below). This RET will then mispredict + * and execution will continue at the return site read from the top of + * the stack. + */ +SYM_INNER_LABEL(srso_safe_ret, SYM_L_GLOBAL) + lea 8(%_ASM_SP), %_ASM_SP + ret + int3 + int3 + /* end of movabs */ + lfence + call srso_safe_ret + ud2 +SYM_CODE_END(srso_safe_ret) +SYM_FUNC_END(srso_untrain_ret) +__EXPORT_THUNK(srso_untrain_ret) + +SYM_CODE_START(srso_return_thunk) + UNWIND_HINT_FUNC + ANNOTATE_NOENDBR + call srso_safe_ret + ud2 +SYM_CODE_END(srso_return_thunk) + +SYM_FUNC_START(entry_untrain_ret) + ALTERNATIVE_2 "jmp retbleed_untrain_ret", \ + "jmp srso_untrain_ret", X86_FEATURE_SRSO, \ + "jmp srso_alias_untrain_ret", X86_FEATURE_SRSO_ALIAS +SYM_FUNC_END(entry_untrain_ret) +__EXPORT_THUNK(entry_untrain_ret) + +SYM_CODE_START(__x86_return_thunk) + UNWIND_HINT_FUNC + ANNOTATE_NOENDBR + ANNOTATE_UNRET_SAFE + ret + int3 +SYM_CODE_END(__x86_return_thunk) EXPORT_SYMBOL(__x86_return_thunk) #endif /* CONFIG_RETHUNK */ diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 0d5ccea2538f..913287b9340c 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -27,6 +27,7 @@ #include <asm/pti.h> #include <asm/text-patching.h> #include <asm/memtype.h> +#include <asm/paravirt.h> /* * We need to define the tracepoints somewhere, and tlb.c @@ -826,9 +827,12 @@ void __init poking_init(void) spinlock_t *ptl; pte_t *ptep; - poking_mm = copy_init_mm(); + poking_mm = mm_alloc(); BUG_ON(!poking_mm); + /* Xen PV guests need the PGD to be pinned. */ + paravirt_arch_dup_mmap(NULL, poking_mm); + /* * Randomize the poking address, but make sure that the following page * will be mapped at the same PMD. We need 2 pages, so find space for 3, diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c index 6175f2c5c822..e97bab7b0010 100644 --- a/arch/x86/xen/smp_pv.c +++ b/arch/x86/xen/smp_pv.c @@ -63,6 +63,7 @@ static void cpu_bringup(void) cr4_init(); cpu_init(); + fpu__init_cpu(); touch_softlockup_watchdog(); /* PVH runs in ring 0 and allows us to do native syscalls. Yay! */ diff --git a/arch/xtensa/include/asm/bugs.h b/arch/xtensa/include/asm/bugs.h deleted file mode 100644 index 69b29d198249..000000000000 --- a/arch/xtensa/include/asm/bugs.h +++ /dev/null @@ -1,18 +0,0 @@ -/* - * include/asm-xtensa/bugs.h - * - * This is included by init/main.c to check for architecture-dependent bugs. - * - * Xtensa processors don't have any bugs. :) - * - * This file is subject to the terms and conditions of the GNU General - * Public License. See the file "COPYING" in the main directory of - * this archive for more details. - */ - -#ifndef _XTENSA_BUGS_H -#define _XTENSA_BUGS_H - -static void check_bugs(void) { } - -#endif /* _XTENSA_BUGS_H */ diff --git a/block/blk-crypto-fallback.c b/block/blk-crypto-fallback.c index ad9844c5b40c..e6468eab2681 100644 --- a/block/blk-crypto-fallback.c +++ b/block/blk-crypto-fallback.c @@ -78,7 +78,7 @@ static struct blk_crypto_fallback_keyslot { struct crypto_skcipher *tfms[BLK_ENCRYPTION_MODE_MAX]; } *blk_crypto_keyslots; -static struct blk_crypto_profile blk_crypto_fallback_profile; +static struct blk_crypto_profile *blk_crypto_fallback_profile; static struct workqueue_struct *blk_crypto_wq; static mempool_t *blk_crypto_bounce_page_pool; static struct bio_set crypto_bio_split; @@ -292,7 +292,7 @@ static bool blk_crypto_fallback_encrypt_bio(struct bio **bio_ptr) * Get a blk-crypto-fallback keyslot that contains a crypto_skcipher for * this bio's algorithm and key. */ - blk_st = blk_crypto_get_keyslot(&blk_crypto_fallback_profile, + blk_st = blk_crypto_get_keyslot(blk_crypto_fallback_profile, bc->bc_key, &slot); if (blk_st != BLK_STS_OK) { src_bio->bi_status = blk_st; @@ -395,7 +395,7 @@ static void blk_crypto_fallback_decrypt_bio(struct work_struct *work) * Get a blk-crypto-fallback keyslot that contains a crypto_skcipher for * this bio's algorithm and key. */ - blk_st = blk_crypto_get_keyslot(&blk_crypto_fallback_profile, + blk_st = blk_crypto_get_keyslot(blk_crypto_fallback_profile, bc->bc_key, &slot); if (blk_st != BLK_STS_OK) { bio->bi_status = blk_st; @@ -499,7 +499,7 @@ bool blk_crypto_fallback_bio_prep(struct bio **bio_ptr) return false; } - if (!__blk_crypto_cfg_supported(&blk_crypto_fallback_profile, + if (!__blk_crypto_cfg_supported(blk_crypto_fallback_profile, &bc->bc_key->crypto_cfg)) { bio->bi_status = BLK_STS_NOTSUPP; return false; @@ -526,7 +526,7 @@ bool blk_crypto_fallback_bio_prep(struct bio **bio_ptr) int blk_crypto_fallback_evict_key(const struct blk_crypto_key *key) { - return __blk_crypto_evict_key(&blk_crypto_fallback_profile, key); + return __blk_crypto_evict_key(blk_crypto_fallback_profile, key); } static bool blk_crypto_fallback_inited; @@ -534,7 +534,6 @@ static int blk_crypto_fallback_init(void) { int i; int err; - struct blk_crypto_profile *profile = &blk_crypto_fallback_profile; if (blk_crypto_fallback_inited) return 0; @@ -545,18 +544,27 @@ static int blk_crypto_fallback_init(void) if (err) goto out; - err = blk_crypto_profile_init(profile, blk_crypto_num_keyslots); - if (err) + /* Dynamic allocation is needed because of lockdep_register_key(). */ + blk_crypto_fallback_profile = + kzalloc(sizeof(*blk_crypto_fallback_profile), GFP_KERNEL); + if (!blk_crypto_fallback_profile) { + err = -ENOMEM; goto fail_free_bioset; + } + + err = blk_crypto_profile_init(blk_crypto_fallback_profile, + blk_crypto_num_keyslots); + if (err) + goto fail_free_profile; err = -ENOMEM; - profile->ll_ops = blk_crypto_fallback_ll_ops; - profile->max_dun_bytes_supported = BLK_CRYPTO_MAX_IV_SIZE; + blk_crypto_fallback_profile->ll_ops = blk_crypto_fallback_ll_ops; + blk_crypto_fallback_profile->max_dun_bytes_supported = BLK_CRYPTO_MAX_IV_SIZE; /* All blk-crypto modes have a crypto API fallback. */ for (i = 0; i < BLK_ENCRYPTION_MODE_MAX; i++) - profile->modes_supported[i] = 0xFFFFFFFF; - profile->modes_supported[BLK_ENCRYPTION_MODE_INVALID] = 0; + blk_crypto_fallback_profile->modes_supported[i] = 0xFFFFFFFF; + blk_crypto_fallback_profile->modes_supported[BLK_ENCRYPTION_MODE_INVALID] = 0; blk_crypto_wq = alloc_workqueue("blk_crypto_wq", WQ_UNBOUND | WQ_HIGHPRI | @@ -597,7 +605,9 @@ fail_free_keyslots: fail_free_wq: destroy_workqueue(blk_crypto_wq); fail_destroy_profile: - blk_crypto_profile_destroy(profile); + blk_crypto_profile_destroy(blk_crypto_fallback_profile); +fail_free_profile: + kfree(blk_crypto_fallback_profile); fail_free_bioset: bioset_exit(&crypto_bio_split); out: diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index dbfa58e799e2..a0e347f6f97e 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -1712,6 +1712,7 @@ static bool acpi_device_enumeration_by_parent(struct acpi_device *device) {"BSG1160", }, {"BSG2150", }, {"CSC3551", }, + {"CSC3556", }, {"INT33FE", }, {"INT3515", }, /* Non-conforming _HID for Cirrus Logic already released */ diff --git a/drivers/acpi/thermal.c b/drivers/acpi/thermal.c index 40b07057983e..40ecb55b52f8 100644 --- a/drivers/acpi/thermal.c +++ b/drivers/acpi/thermal.c @@ -59,10 +59,6 @@ static int tzp; module_param(tzp, int, 0444); MODULE_PARM_DESC(tzp, "Thermal zone polling frequency, in 1/10 seconds."); -static int nocrt; -module_param(nocrt, int, 0); -MODULE_PARM_DESC(nocrt, "Set to take no action upon ACPI thermal zone critical trips points."); - static int off; module_param(off, int, 0); MODULE_PARM_DESC(off, "Set to disable ACPI thermal support."); @@ -1128,7 +1124,7 @@ static int thermal_act(const struct dmi_system_id *d) { static int thermal_nocrt(const struct dmi_system_id *d) { pr_notice("%s detected: disabling all critical thermal trip point actions.\n", d->ident); - nocrt = 1; + crt = -1; return 0; } static int thermal_tzp(const struct dmi_system_id *d) { diff --git a/drivers/android/binder.c b/drivers/android/binder.c index e374a8a2da46..e4a6da81cd4b 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -6602,6 +6602,7 @@ err_init_binder_device_failed: err_alloc_device_names_failed: debugfs_remove_recursive(binder_debugfs_dir_entry_root); + binder_alloc_shrinker_exit(); return ret; } diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c index 4fb89ef067d5..cd87f12733f2 100644 --- a/drivers/android/binder_alloc.c +++ b/drivers/android/binder_alloc.c @@ -1087,6 +1087,12 @@ int binder_alloc_shrinker_init(void) return ret; } +void binder_alloc_shrinker_exit(void) +{ + unregister_shrinker(&binder_shrinker); + list_lru_destroy(&binder_alloc_lru); +} + /** * check_buffer() - verify that buffer/offset is safe to access * @alloc: binder_alloc for this proc diff --git a/drivers/android/binder_alloc.h b/drivers/android/binder_alloc.h index 138d1d5af9ce..dc1e2b01dd64 100644 --- a/drivers/android/binder_alloc.h +++ b/drivers/android/binder_alloc.h @@ -129,6 +129,7 @@ extern struct binder_buffer *binder_alloc_new_buf(struct binder_alloc *alloc, int pid); extern void binder_alloc_init(struct binder_alloc *alloc); extern int binder_alloc_shrinker_init(void); +extern void binder_alloc_shrinker_exit(void); extern void binder_alloc_vma_close(struct binder_alloc *alloc); extern struct binder_buffer * binder_alloc_prepare_to_free(struct binder_alloc *alloc, diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index 7af8e33735a3..dab70a65377c 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -577,6 +577,18 @@ ssize_t __weak cpu_show_retbleed(struct device *dev, return sysfs_emit(buf, "Not affected\n"); } +ssize_t __weak cpu_show_gds(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "Not affected\n"); +} + +ssize_t __weak cpu_show_spec_rstack_overflow(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "Not affected\n"); +} + static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL); static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL); static DEVICE_ATTR(spectre_v2, 0444, cpu_show_spectre_v2, NULL); @@ -588,6 +600,8 @@ static DEVICE_ATTR(itlb_multihit, 0444, cpu_show_itlb_multihit, NULL); static DEVICE_ATTR(srbds, 0444, cpu_show_srbds, NULL); static DEVICE_ATTR(mmio_stale_data, 0444, cpu_show_mmio_stale_data, NULL); static DEVICE_ATTR(retbleed, 0444, cpu_show_retbleed, NULL); +static DEVICE_ATTR(gather_data_sampling, 0444, cpu_show_gds, NULL); +static DEVICE_ATTR(spec_rstack_overflow, 0444, cpu_show_spec_rstack_overflow, NULL); static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_meltdown.attr, @@ -601,6 +615,8 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_srbds.attr, &dev_attr_mmio_stale_data.attr, &dev_attr_retbleed.attr, + &dev_attr_gather_data_sampling.attr, + &dev_attr_spec_rstack_overflow.attr, NULL }; diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index daec0321cd76..74ef3da54536 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -3676,7 +3676,7 @@ static int rbd_lock(struct rbd_device *rbd_dev) ret = ceph_cls_lock(osdc, &rbd_dev->header_oid, &rbd_dev->header_oloc, RBD_LOCK_NAME, CEPH_CLS_LOCK_EXCLUSIVE, cookie, RBD_LOCK_TAG, "", 0); - if (ret) + if (ret && ret != -EEXIST) return ret; __rbd_lock(rbd_dev, cookie); @@ -3879,7 +3879,7 @@ static struct ceph_locker *get_lock_owner_info(struct rbd_device *rbd_dev) &rbd_dev->header_oloc, RBD_LOCK_NAME, &lock_type, &lock_tag, &lockers, &num_lockers); if (ret) { - rbd_warn(rbd_dev, "failed to retrieve lockers: %d", ret); + rbd_warn(rbd_dev, "failed to get header lockers: %d", ret); return ERR_PTR(ret); } @@ -3941,8 +3941,10 @@ static int find_watcher(struct rbd_device *rbd_dev, ret = ceph_osdc_list_watchers(osdc, &rbd_dev->header_oid, &rbd_dev->header_oloc, &watchers, &num_watchers); - if (ret) + if (ret) { + rbd_warn(rbd_dev, "failed to get watchers: %d", ret); return ret; + } sscanf(locker->id.cookie, RBD_LOCK_COOKIE_PREFIX " %llu", &cookie); for (i = 0; i < num_watchers; i++) { @@ -3986,8 +3988,12 @@ static int rbd_try_lock(struct rbd_device *rbd_dev) locker = refreshed_locker = NULL; ret = rbd_lock(rbd_dev); - if (ret != -EBUSY) + if (!ret) + goto out; + if (ret != -EBUSY) { + rbd_warn(rbd_dev, "failed to lock header: %d", ret); goto out; + } /* determine if the current lock holder is still alive */ locker = get_lock_owner_info(rbd_dev); @@ -4090,11 +4096,8 @@ static int rbd_try_acquire_lock(struct rbd_device *rbd_dev) ret = rbd_try_lock(rbd_dev); if (ret < 0) { - rbd_warn(rbd_dev, "failed to lock header: %d", ret); - if (ret == -EBLOCKLISTED) - goto out; - - ret = 1; /* request lock anyway */ + rbd_warn(rbd_dev, "failed to acquire lock: %d", ret); + goto out; } if (ret > 0) { up_write(&rbd_dev->lock_rwsem); @@ -6628,12 +6631,11 @@ static int rbd_add_acquire_lock(struct rbd_device *rbd_dev) cancel_delayed_work_sync(&rbd_dev->lock_dwork); if (!ret) ret = -ETIMEDOUT; - } - if (ret) { - rbd_warn(rbd_dev, "failed to acquire exclusive lock: %ld", ret); - return ret; + rbd_warn(rbd_dev, "failed to acquire lock: %ld", ret); } + if (ret) + return ret; /* * The lock may have been released by now, unless automatic lock diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 4459cfbdbcb1..c2f0f74193f0 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -1223,9 +1223,6 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd, __func__, cmd->cmd_op, ub_cmd->q_id, tag, ub_cmd->result); - if (!(issue_flags & IO_URING_F_SQE128)) - goto out; - if (ub_cmd->q_id >= ub->dev_info.nr_hw_queues) goto out; diff --git a/drivers/bluetooth/btsdio.c b/drivers/bluetooth/btsdio.c index 795be33f2892..f19d31ee37ea 100644 --- a/drivers/bluetooth/btsdio.c +++ b/drivers/bluetooth/btsdio.c @@ -357,6 +357,7 @@ static void btsdio_remove(struct sdio_func *func) if (!data) return; + cancel_work_sync(&data->work); hdev = data->hdev; sdio_set_drvdata(func, NULL); diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index faad19b396d5..d6f405763c56 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -600,6 +600,9 @@ static const struct usb_device_id blacklist_table[] = { { USB_DEVICE(0x0489, 0xe0d9), .driver_info = BTUSB_MEDIATEK | BTUSB_WIDEBAND_SPEECH | BTUSB_VALID_LE_STATES }, + { USB_DEVICE(0x0489, 0xe0f5), .driver_info = BTUSB_MEDIATEK | + BTUSB_WIDEBAND_SPEECH | + BTUSB_VALID_LE_STATES }, { USB_DEVICE(0x13d3, 0x3568), .driver_info = BTUSB_MEDIATEK | BTUSB_WIDEBAND_SPEECH | BTUSB_VALID_LE_STATES }, diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index cae078bffc71..9b7268bae66a 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -2159,6 +2159,8 @@ static int sysc_reset(struct sysc *ddata) sysc_val = sysc_read_sysconfig(ddata); sysc_val |= sysc_mask; sysc_write(ddata, sysc_offset, sysc_val); + /* Flush posted write */ + sysc_val = sysc_read_sysconfig(ddata); } if (ddata->cfg.srst_udelay) diff --git a/drivers/char/tpm/tpm-chip.c b/drivers/char/tpm/tpm-chip.c index d7ef4d0a7409..c0759d49fd14 100644 --- a/drivers/char/tpm/tpm-chip.c +++ b/drivers/char/tpm/tpm-chip.c @@ -507,70 +507,6 @@ static int tpm_add_legacy_sysfs(struct tpm_chip *chip) return 0; } -/* - * Some AMD fTPM versions may cause stutter - * https://www.amd.com/en/support/kb/faq/pa-410 - * - * Fixes are available in two series of fTPM firmware: - * 6.x.y.z series: 6.0.18.6 + - * 3.x.y.z series: 3.57.y.5 + - */ -#ifdef CONFIG_X86 -static bool tpm_amd_is_rng_defective(struct tpm_chip *chip) -{ - u32 val1, val2; - u64 version; - int ret; - - if (!(chip->flags & TPM_CHIP_FLAG_TPM2)) - return false; - - ret = tpm_request_locality(chip); - if (ret) - return false; - - ret = tpm2_get_tpm_pt(chip, TPM2_PT_MANUFACTURER, &val1, NULL); - if (ret) - goto release; - if (val1 != 0x414D4400U /* AMD */) { - ret = -ENODEV; - goto release; - } - ret = tpm2_get_tpm_pt(chip, TPM2_PT_FIRMWARE_VERSION_1, &val1, NULL); - if (ret) - goto release; - ret = tpm2_get_tpm_pt(chip, TPM2_PT_FIRMWARE_VERSION_2, &val2, NULL); - -release: - tpm_relinquish_locality(chip); - - if (ret) - return false; - - version = ((u64)val1 << 32) | val2; - if ((version >> 48) == 6) { - if (version >= 0x0006000000180006ULL) - return false; - } else if ((version >> 48) == 3) { - if (version >= 0x0003005700000005ULL) - return false; - } else { - return false; - } - - dev_warn(&chip->dev, - "AMD fTPM version 0x%llx causes system stutter; hwrng disabled\n", - version); - - return true; -} -#else -static inline bool tpm_amd_is_rng_defective(struct tpm_chip *chip) -{ - return false; -} -#endif /* CONFIG_X86 */ - static int tpm_hwrng_read(struct hwrng *rng, void *data, size_t max, bool wait) { struct tpm_chip *chip = container_of(rng, struct tpm_chip, hwrng); @@ -582,10 +518,20 @@ static int tpm_hwrng_read(struct hwrng *rng, void *data, size_t max, bool wait) return tpm_get_random(chip, data, max); } +static bool tpm_is_hwrng_enabled(struct tpm_chip *chip) +{ + if (!IS_ENABLED(CONFIG_HW_RANDOM_TPM)) + return false; + if (tpm_is_firmware_upgrade(chip)) + return false; + if (chip->flags & TPM_CHIP_FLAG_HWRNG_DISABLED) + return false; + return true; +} + static int tpm_add_hwrng(struct tpm_chip *chip) { - if (!IS_ENABLED(CONFIG_HW_RANDOM_TPM) || tpm_is_firmware_upgrade(chip) || - tpm_amd_is_rng_defective(chip)) + if (!tpm_is_hwrng_enabled(chip)) return 0; snprintf(chip->hwrng_name, sizeof(chip->hwrng_name), @@ -690,7 +636,7 @@ int tpm_chip_register(struct tpm_chip *chip) return 0; out_hwrng: - if (IS_ENABLED(CONFIG_HW_RANDOM_TPM) && !tpm_is_firmware_upgrade(chip)) + if (tpm_is_hwrng_enabled(chip)) hwrng_unregister(&chip->hwrng); out_ppi: tpm_bios_log_teardown(chip); @@ -715,8 +661,7 @@ EXPORT_SYMBOL_GPL(tpm_chip_register); void tpm_chip_unregister(struct tpm_chip *chip) { tpm_del_legacy_sysfs(chip); - if (IS_ENABLED(CONFIG_HW_RANDOM_TPM) && !tpm_is_firmware_upgrade(chip) && - !tpm_amd_is_rng_defective(chip)) + if (tpm_is_hwrng_enabled(chip)) hwrng_unregister(&chip->hwrng); tpm_bios_log_teardown(chip); if (chip->flags & TPM_CHIP_FLAG_TPM2 && !tpm_is_firmware_upgrade(chip)) diff --git a/drivers/char/tpm/tpm_crb.c b/drivers/char/tpm/tpm_crb.c index cbbedf52607c..7f7f3bded453 100644 --- a/drivers/char/tpm/tpm_crb.c +++ b/drivers/char/tpm/tpm_crb.c @@ -463,6 +463,28 @@ static bool crb_req_canceled(struct tpm_chip *chip, u8 status) return (cancel & CRB_CANCEL_INVOKE) == CRB_CANCEL_INVOKE; } +static int crb_check_flags(struct tpm_chip *chip) +{ + u32 val; + int ret; + + ret = crb_request_locality(chip, 0); + if (ret) + return ret; + + ret = tpm2_get_tpm_pt(chip, TPM2_PT_MANUFACTURER, &val, NULL); + if (ret) + goto release; + + if (val == 0x414D4400U /* AMD */) + chip->flags |= TPM_CHIP_FLAG_HWRNG_DISABLED; + +release: + crb_relinquish_locality(chip, 0); + + return ret; +} + static const struct tpm_class_ops tpm_crb = { .flags = TPM_OPS_AUTO_STARTUP, .status = crb_status, @@ -800,6 +822,14 @@ static int crb_acpi_add(struct acpi_device *device) chip->acpi_dev_handle = device->handle; chip->flags = TPM_CHIP_FLAG_TPM2; + rc = tpm_chip_bootstrap(chip); + if (rc) + goto out; + + rc = crb_check_flags(chip); + if (rc) + goto out; + rc = tpm_chip_register(chip); out: diff --git a/drivers/clk/clk-devres.c b/drivers/clk/clk-devres.c index 4fb4fd4b06bd..737aa70e2cb3 100644 --- a/drivers/clk/clk-devres.c +++ b/drivers/clk/clk-devres.c @@ -205,18 +205,19 @@ EXPORT_SYMBOL(devm_clk_put); struct clk *devm_get_clk_from_child(struct device *dev, struct device_node *np, const char *con_id) { - struct clk **ptr, *clk; + struct devm_clk_state *state; + struct clk *clk; - ptr = devres_alloc(devm_clk_release, sizeof(*ptr), GFP_KERNEL); - if (!ptr) + state = devres_alloc(devm_clk_release, sizeof(*state), GFP_KERNEL); + if (!state) return ERR_PTR(-ENOMEM); clk = of_clk_get_by_name(np, con_id); if (!IS_ERR(clk)) { - *ptr = clk; - devres_add(dev, ptr); + state->clk = clk; + devres_add(dev, state); } else { - devres_free(ptr); + devres_free(state); } return clk; diff --git a/drivers/clk/imx/clk-imx93.c b/drivers/clk/imx/clk-imx93.c index 5e3d299190c8..61d9f9bf86e6 100644 --- a/drivers/clk/imx/clk-imx93.c +++ b/drivers/clk/imx/clk-imx93.c @@ -288,7 +288,7 @@ static int imx93_clocks_probe(struct platform_device *pdev) anatop_base = devm_of_iomap(dev, np, 0, NULL); of_node_put(np); if (WARN_ON(IS_ERR(anatop_base))) { - ret = PTR_ERR(base); + ret = PTR_ERR(anatop_base); goto unregister_hws; } diff --git a/drivers/cpuidle/cpuidle-psci-domain.c b/drivers/cpuidle/cpuidle-psci-domain.c index fe0664472520..f5d4359555d7 100644 --- a/drivers/cpuidle/cpuidle-psci-domain.c +++ b/drivers/cpuidle/cpuidle-psci-domain.c @@ -117,20 +117,6 @@ static void psci_pd_remove(void) } } -static bool psci_pd_try_set_osi_mode(void) -{ - int ret; - - if (!psci_has_osi_support()) - return false; - - ret = psci_set_osi_mode(true); - if (ret) - return false; - - return true; -} - static void psci_cpuidle_domain_sync_state(struct device *dev) { /* @@ -149,15 +135,12 @@ static int psci_cpuidle_domain_probe(struct platform_device *pdev) { struct device_node *np = pdev->dev.of_node; struct device_node *node; - bool use_osi; + bool use_osi = psci_has_osi_support(); int ret = 0, pd_count = 0; if (!np) return -ENODEV; - /* If OSI mode is supported, let's try to enable it. */ - use_osi = psci_pd_try_set_osi_mode(); - /* * Parse child nodes for the "#power-domain-cells" property and * initialize a genpd/genpd-of-provider pair when it's found. @@ -167,32 +150,37 @@ static int psci_cpuidle_domain_probe(struct platform_device *pdev) continue; ret = psci_pd_init(node, use_osi); - if (ret) - goto put_node; + if (ret) { + of_node_put(node); + goto exit; + } pd_count++; } /* Bail out if not using the hierarchical CPU topology. */ if (!pd_count) - goto no_pd; + return 0; /* Link genpd masters/subdomains to model the CPU topology. */ ret = dt_idle_pd_init_topology(np); if (ret) goto remove_pd; - pr_info("Initialized CPU PM domain topology\n"); + /* let's try to enable OSI. */ + ret = psci_set_osi_mode(use_osi); + if (ret) + goto remove_pd; + + pr_info("Initialized CPU PM domain topology using %s mode\n", + use_osi ? "OSI" : "PC"); return 0; -put_node: - of_node_put(node); remove_pd: + dt_idle_pd_remove_topology(np); psci_pd_remove(); +exit: pr_err("failed to create CPU PM domains ret=%d\n", ret); -no_pd: - if (use_osi) - psci_set_osi_mode(false); return ret; } diff --git a/drivers/cpuidle/dt_idle_genpd.c b/drivers/cpuidle/dt_idle_genpd.c index b37165514d4e..1af63c189039 100644 --- a/drivers/cpuidle/dt_idle_genpd.c +++ b/drivers/cpuidle/dt_idle_genpd.c @@ -152,6 +152,30 @@ int dt_idle_pd_init_topology(struct device_node *np) return 0; } +int dt_idle_pd_remove_topology(struct device_node *np) +{ + struct device_node *node; + struct of_phandle_args child, parent; + int ret; + + for_each_child_of_node(np, node) { + if (of_parse_phandle_with_args(node, "power-domains", + "#power-domain-cells", 0, &parent)) + continue; + + child.np = node; + child.args_count = 0; + ret = of_genpd_remove_subdomain(&parent, &child); + of_node_put(parent.np); + if (ret) { + of_node_put(node); + return ret; + } + } + + return 0; +} + struct device *dt_idle_attach_cpu(int cpu, const char *name) { struct device *dev; diff --git a/drivers/cpuidle/dt_idle_genpd.h b/drivers/cpuidle/dt_idle_genpd.h index a95483d08a02..3be1f70f55b5 100644 --- a/drivers/cpuidle/dt_idle_genpd.h +++ b/drivers/cpuidle/dt_idle_genpd.h @@ -14,6 +14,8 @@ struct generic_pm_domain *dt_idle_pd_alloc(struct device_node *np, int dt_idle_pd_init_topology(struct device_node *np); +int dt_idle_pd_remove_topology(struct device_node *np); + struct device *dt_idle_attach_cpu(int cpu, const char *name); void dt_idle_detach_cpu(struct device *dev); @@ -36,6 +38,11 @@ static inline int dt_idle_pd_init_topology(struct device_node *np) return 0; } +static inline int dt_idle_pd_remove_topology(struct device_node *np) +{ + return 0; +} + static inline struct device *dt_idle_attach_cpu(int cpu, const char *name) { return NULL; diff --git a/drivers/dma-buf/sw_sync.c b/drivers/dma-buf/sw_sync.c index 348b3a9170fa..7f5ed1aa7a9f 100644 --- a/drivers/dma-buf/sw_sync.c +++ b/drivers/dma-buf/sw_sync.c @@ -191,6 +191,7 @@ static const struct dma_fence_ops timeline_fence_ops = { */ static void sync_timeline_signal(struct sync_timeline *obj, unsigned int inc) { + LIST_HEAD(signalled); struct sync_pt *pt, *next; trace_sync_timeline(obj); @@ -203,21 +204,20 @@ static void sync_timeline_signal(struct sync_timeline *obj, unsigned int inc) if (!timeline_fence_signaled(&pt->base)) break; - list_del_init(&pt->link); + dma_fence_get(&pt->base); + + list_move_tail(&pt->link, &signalled); rb_erase(&pt->node, &obj->pt_tree); - /* - * A signal callback may release the last reference to this - * fence, causing it to be freed. That operation has to be - * last to avoid a use after free inside this loop, and must - * be after we remove the fence from the timeline in order to - * prevent deadlocking on timeline->lock inside - * timeline_fence_release(). - */ dma_fence_signal_locked(&pt->base); } spin_unlock_irq(&obj->lock); + + list_for_each_entry_safe(pt, next, &signalled, link) { + list_del_init(&pt->link); + dma_fence_put(&pt->base); + } } /** diff --git a/drivers/dma/mcf-edma.c b/drivers/dma/mcf-edma.c index e12b754e6398..60d3c5f09ad6 100644 --- a/drivers/dma/mcf-edma.c +++ b/drivers/dma/mcf-edma.c @@ -191,7 +191,13 @@ static int mcf_edma_probe(struct platform_device *pdev) return -EINVAL; } - chans = pdata->dma_channels; + if (!pdata->dma_channels) { + dev_info(&pdev->dev, "setting default channel number to 64"); + chans = 64; + } else { + chans = pdata->dma_channels; + } + len = sizeof(*mcf_edma) + sizeof(*mcf_chan) * chans; mcf_edma = devm_kzalloc(&pdev->dev, len, GFP_KERNEL); if (!mcf_edma) @@ -203,11 +209,6 @@ static int mcf_edma_probe(struct platform_device *pdev) mcf_edma->drvdata = &mcf_data; mcf_edma->big_endian = 1; - if (!mcf_edma->n_chans) { - dev_info(&pdev->dev, "setting default channel number to 64"); - mcf_edma->n_chans = 64; - } - mutex_init(&mcf_edma->fsl_edma_mutex); res = platform_get_resource(pdev, IORESOURCE_MEM, 0); diff --git a/drivers/dma/owl-dma.c b/drivers/dma/owl-dma.c index 95a462a1f511..b6e0ac8314e5 100644 --- a/drivers/dma/owl-dma.c +++ b/drivers/dma/owl-dma.c @@ -192,7 +192,7 @@ struct owl_dma_pchan { }; /** - * struct owl_dma_pchan - Wrapper for DMA ENGINE channel + * struct owl_dma_vchan - Wrapper for DMA ENGINE channel * @vc: wrapped virtual channel * @pchan: the physical channel utilized by this channel * @txd: active transaction on this channel diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c index b4731fe6bbc1..3cf0b38387ae 100644 --- a/drivers/dma/pl330.c +++ b/drivers/dma/pl330.c @@ -404,6 +404,12 @@ enum desc_status { */ BUSY, /* + * Pause was called while descriptor was BUSY. Due to hardware + * limitations, only termination is possible for descriptors + * that have been paused. + */ + PAUSED, + /* * Sitting on the channel work_list but xfer done * by PL330 core */ @@ -2041,7 +2047,7 @@ static inline void fill_queue(struct dma_pl330_chan *pch) list_for_each_entry(desc, &pch->work_list, node) { /* If already submitted */ - if (desc->status == BUSY) + if (desc->status == BUSY || desc->status == PAUSED) continue; ret = pl330_submit_req(pch->thread, desc); @@ -2326,6 +2332,7 @@ static int pl330_pause(struct dma_chan *chan) { struct dma_pl330_chan *pch = to_pchan(chan); struct pl330_dmac *pl330 = pch->dmac; + struct dma_pl330_desc *desc; unsigned long flags; pm_runtime_get_sync(pl330->ddma.dev); @@ -2335,6 +2342,10 @@ static int pl330_pause(struct dma_chan *chan) _stop(pch->thread); spin_unlock(&pl330->lock); + list_for_each_entry(desc, &pch->work_list, node) { + if (desc->status == BUSY) + desc->status = PAUSED; + } spin_unlock_irqrestore(&pch->lock, flags); pm_runtime_mark_last_busy(pl330->ddma.dev); pm_runtime_put_autosuspend(pl330->ddma.dev); @@ -2425,7 +2436,7 @@ pl330_tx_status(struct dma_chan *chan, dma_cookie_t cookie, else if (running && desc == running) transferred = pl330_get_current_xferred_count(pch, desc); - else if (desc->status == BUSY) + else if (desc->status == BUSY || desc->status == PAUSED) /* * Busy but not running means either just enqueued, * or finished and not yet marked done @@ -2442,6 +2453,9 @@ pl330_tx_status(struct dma_chan *chan, dma_cookie_t cookie, case DONE: ret = DMA_COMPLETE; break; + case PAUSED: + ret = DMA_PAUSED; + break; case PREP: case BUSY: ret = DMA_IN_PROGRESS; diff --git a/drivers/firewire/net.c b/drivers/firewire/net.c index af22be84034b..a53eacebca33 100644 --- a/drivers/firewire/net.c +++ b/drivers/firewire/net.c @@ -479,7 +479,7 @@ static int fwnet_finish_incoming_packet(struct net_device *net, struct sk_buff *skb, u16 source_node_id, bool is_broadcast, u16 ether_type) { - int status; + int status, len; switch (ether_type) { case ETH_P_ARP: @@ -533,13 +533,15 @@ static int fwnet_finish_incoming_packet(struct net_device *net, } skb->protocol = protocol; } + + len = skb->len; status = netif_rx(skb); if (status == NET_RX_DROP) { net->stats.rx_errors++; net->stats.rx_dropped++; } else { net->stats.rx_packets++; - net->stats.rx_bytes += skb->len; + net->stats.rx_bytes += len; } return 0; diff --git a/drivers/firmware/arm_scmi/mailbox.c b/drivers/firmware/arm_scmi/mailbox.c index a455f3c0e98b..25d31dfdad15 100644 --- a/drivers/firmware/arm_scmi/mailbox.c +++ b/drivers/firmware/arm_scmi/mailbox.c @@ -106,8 +106,10 @@ static int mailbox_chan_setup(struct scmi_chan_info *cinfo, struct device *dev, return -ENOMEM; shmem = of_parse_phandle(cdev->of_node, "shmem", idx); - if (!of_device_is_compatible(shmem, "arm,scmi-shmem")) + if (!of_device_is_compatible(shmem, "arm,scmi-shmem")) { + of_node_put(shmem); return -ENXIO; + } ret = of_address_to_resource(shmem, 0, &res); of_node_put(shmem); diff --git a/drivers/firmware/arm_scmi/smc.c b/drivers/firmware/arm_scmi/smc.c index 87a7b13cf868..ac0bd51ef16a 100644 --- a/drivers/firmware/arm_scmi/smc.c +++ b/drivers/firmware/arm_scmi/smc.c @@ -23,6 +23,7 @@ /** * struct scmi_smc - Structure representing a SCMI smc transport * + * @irq: An optional IRQ for completion * @cinfo: SCMI channel info * @shmem: Transmit/Receive shared memory area * @shmem_lock: Lock to protect access to Tx/Rx shared memory area. @@ -33,6 +34,7 @@ */ struct scmi_smc { + int irq; struct scmi_chan_info *cinfo; struct scmi_shared_mem __iomem *shmem; /* Protect access to shmem area */ @@ -106,7 +108,7 @@ static int smc_chan_setup(struct scmi_chan_info *cinfo, struct device *dev, struct resource res; struct device_node *np; u32 func_id; - int ret, irq; + int ret; if (!tx) return -ENODEV; @@ -116,8 +118,10 @@ static int smc_chan_setup(struct scmi_chan_info *cinfo, struct device *dev, return -ENOMEM; np = of_parse_phandle(cdev->of_node, "shmem", 0); - if (!of_device_is_compatible(np, "arm,scmi-shmem")) + if (!of_device_is_compatible(np, "arm,scmi-shmem")) { + of_node_put(np); return -ENXIO; + } ret = of_address_to_resource(np, 0, &res); of_node_put(np); @@ -142,11 +146,10 @@ static int smc_chan_setup(struct scmi_chan_info *cinfo, struct device *dev, * completion of a message is signaled by an interrupt rather than by * the return of the SMC call. */ - irq = of_irq_get_byname(cdev->of_node, "a2p"); - if (irq > 0) { - ret = devm_request_irq(dev, irq, smc_msg_done_isr, - IRQF_NO_SUSPEND, - dev_name(dev), scmi_info); + scmi_info->irq = of_irq_get_byname(cdev->of_node, "a2p"); + if (scmi_info->irq > 0) { + ret = request_irq(scmi_info->irq, smc_msg_done_isr, + IRQF_NO_SUSPEND, dev_name(dev), scmi_info); if (ret) { dev_err(dev, "failed to setup SCMI smc irq\n"); return ret; @@ -168,6 +171,10 @@ static int smc_chan_free(int id, void *p, void *data) struct scmi_chan_info *cinfo = p; struct scmi_smc *scmi_info = cinfo->transport_info; + /* Ignore any possible further reception on the IRQ path */ + if (scmi_info->irq > 0) + free_irq(scmi_info->irq, scmi_info); + cinfo->transport_info = NULL; scmi_info->cinfo = NULL; diff --git a/drivers/firmware/smccc/soc_id.c b/drivers/firmware/smccc/soc_id.c index 890eb454599a..1990263fbba0 100644 --- a/drivers/firmware/smccc/soc_id.c +++ b/drivers/firmware/smccc/soc_id.c @@ -34,7 +34,6 @@ static struct soc_device_attribute *soc_dev_attr; static int __init smccc_soc_init(void) { - struct arm_smccc_res res; int soc_id_rev, soc_id_version; static char soc_id_str[20], soc_id_rev_str[12]; static char soc_id_jep106_id_str[12]; @@ -49,13 +48,13 @@ static int __init smccc_soc_init(void) } if (soc_id_version < 0) { - pr_err("ARCH_SOC_ID(0) returned error: %lx\n", res.a0); + pr_err("Invalid SoC Version: %x\n", soc_id_version); return -EINVAL; } soc_id_rev = arm_smccc_get_soc_id_revision(); if (soc_id_rev < 0) { - pr_err("ARCH_SOC_ID(1) returned error: %lx\n", res.a0); + pr_err("Invalid SoC Revision: %x\n", soc_id_rev); return -EINVAL; } diff --git a/drivers/firmware/stratix10-svc.c b/drivers/firmware/stratix10-svc.c index 2d674126160f..cab11af28c23 100644 --- a/drivers/firmware/stratix10-svc.c +++ b/drivers/firmware/stratix10-svc.c @@ -756,7 +756,7 @@ svc_create_memory_pool(struct platform_device *pdev, paddr = begin; size = end - begin; va = devm_memremap(dev, paddr, size, MEMREMAP_WC); - if (!va) { + if (IS_ERR(va)) { dev_err(dev, "fail to remap shared memory\n"); return ERR_PTR(-EINVAL); } diff --git a/drivers/fsi/fsi-master-ast-cf.c b/drivers/fsi/fsi-master-ast-cf.c index 5f608ef8b53c..cde281ec89d7 100644 --- a/drivers/fsi/fsi-master-ast-cf.c +++ b/drivers/fsi/fsi-master-ast-cf.c @@ -1441,3 +1441,4 @@ static struct platform_driver fsi_master_acf = { module_platform_driver(fsi_master_acf); MODULE_LICENSE("GPL"); +MODULE_FIRMWARE(FW_FILE_NAME); diff --git a/drivers/gpio/gpio-sim.c b/drivers/gpio/gpio-sim.c index 803676e307d7..b352775e5e0b 100644 --- a/drivers/gpio/gpio-sim.c +++ b/drivers/gpio/gpio-sim.c @@ -290,6 +290,15 @@ static void gpio_sim_mutex_destroy(void *data) mutex_destroy(lock); } +static void gpio_sim_dispose_mappings(void *data) +{ + struct gpio_sim_chip *chip = data; + unsigned int i; + + for (i = 0; i < chip->gc.ngpio; i++) + irq_dispose_mapping(irq_find_mapping(chip->irq_sim, i)); +} + static void gpio_sim_sysfs_remove(void *data) { struct gpio_sim_chip *chip = data; @@ -398,10 +407,14 @@ static int gpio_sim_add_bank(struct fwnode_handle *swnode, struct device *dev) if (!chip->pull_map) return -ENOMEM; - chip->irq_sim = devm_irq_domain_create_sim(dev, NULL, num_lines); + chip->irq_sim = devm_irq_domain_create_sim(dev, swnode, num_lines); if (IS_ERR(chip->irq_sim)) return PTR_ERR(chip->irq_sim); + ret = devm_add_action_or_reset(dev, gpio_sim_dispose_mappings, chip); + if (ret) + return ret; + mutex_init(&chip->lock); ret = devm_add_action_or_reset(dev, gpio_sim_mutex_destroy, &chip->lock); @@ -425,6 +438,7 @@ static int gpio_sim_add_bank(struct fwnode_handle *swnode, struct device *dev) gc->set_config = gpio_sim_set_config; gc->to_irq = gpio_sim_to_irq; gc->free = gpio_sim_free; + gc->can_sleep = true; ret = devm_gpiochip_add_data(dev, gc, chip); if (ret) diff --git a/drivers/gpio/gpio-ws16c48.c b/drivers/gpio/gpio-ws16c48.c index e73885a4dc32..afb42a8e916f 100644 --- a/drivers/gpio/gpio-ws16c48.c +++ b/drivers/gpio/gpio-ws16c48.c @@ -18,7 +18,7 @@ #include <linux/spinlock.h> #include <linux/types.h> -#define WS16C48_EXTENT 10 +#define WS16C48_EXTENT 11 #define MAX_NUM_WS16C48 max_num_isa_dev(WS16C48_EXTENT) static unsigned int base[MAX_NUM_WS16C48]; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 925def03d2d6..09b8052735b9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -286,6 +286,9 @@ extern int amdgpu_user_partt_mode; #define AMDGPU_SMARTSHIFT_MAX_BIAS (100) #define AMDGPU_SMARTSHIFT_MIN_BIAS (-100) +/* Extra time delay(in ms) to eliminate the influence of temperature momentary fluctuation */ +#define AMDGPU_SWCTF_EXTRA_DELAY 50 + struct amdgpu_xcp_mgr; struct amdgpu_device; struct amdgpu_irq_src; @@ -1307,6 +1310,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, void amdgpu_device_pci_config_reset(struct amdgpu_device *adev); int amdgpu_device_pci_reset(struct amdgpu_device *adev); bool amdgpu_device_need_post(struct amdgpu_device *adev); +bool amdgpu_sg_display_supported(struct amdgpu_device *adev); bool amdgpu_device_pcie_dynamic_switching_supported(void); bool amdgpu_device_should_use_aspm(struct amdgpu_device *adev); bool amdgpu_device_aspm_support_quirk(void); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c index ef4b9a41f20a..13495957615d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c @@ -104,7 +104,7 @@ void amdgpu_atomfirmware_scratch_regs_init(struct amdgpu_device *adev) static int amdgpu_atomfirmware_allocate_fb_v2_1(struct amdgpu_device *adev, struct vram_usagebyfirmware_v2_1 *fw_usage, int *usage_bytes) { - u32 start_addr, fw_size, drv_size; + uint32_t start_addr, fw_size, drv_size; start_addr = le32_to_cpu(fw_usage->start_address_in_kb); fw_size = le16_to_cpu(fw_usage->used_by_firmware_in_kb); @@ -116,7 +116,7 @@ static int amdgpu_atomfirmware_allocate_fb_v2_1(struct amdgpu_device *adev, drv_size); if ((start_addr & ATOM_VRAM_OPERATION_FLAGS_MASK) == - (u32)(ATOM_VRAM_BLOCK_SRIOV_MSG_SHARE_RESERVATION << + (uint32_t)(ATOM_VRAM_BLOCK_SRIOV_MSG_SHARE_RESERVATION << ATOM_VRAM_OPERATION_FLAGS_SHIFT)) { /* Firmware request VRAM reservation for SR-IOV */ adev->mman.fw_vram_usage_start_offset = (start_addr & @@ -133,7 +133,7 @@ static int amdgpu_atomfirmware_allocate_fb_v2_1(struct amdgpu_device *adev, static int amdgpu_atomfirmware_allocate_fb_v2_2(struct amdgpu_device *adev, struct vram_usagebyfirmware_v2_2 *fw_usage, int *usage_bytes) { - u32 fw_start_addr, fw_size, drv_start_addr, drv_size; + uint32_t fw_start_addr, fw_size, drv_start_addr, drv_size; fw_start_addr = le32_to_cpu(fw_usage->fw_region_start_address_in_kb); fw_size = le16_to_cpu(fw_usage->used_by_firmware_in_kb); @@ -176,8 +176,8 @@ int amdgpu_atomfirmware_allocate_fb_scratch(struct amdgpu_device *adev) vram_usagebyfirmware); struct vram_usagebyfirmware_v2_1 *fw_usage_v2_1; struct vram_usagebyfirmware_v2_2 *fw_usage_v2_2; - u16 data_offset; - u8 frev, crev; + uint16_t data_offset; + uint8_t frev, crev; int usage_bytes = 0; if (amdgpu_atom_parse_data_header(ctx, index, NULL, &frev, &crev, &data_offset)) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index e753aba4b4f4..19a42f841692 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -293,7 +293,7 @@ static int amdgpu_cs_pass1(struct amdgpu_cs_parser *p, if (!p->gang_size) { ret = -EINVAL; - goto free_partial_kdata; + goto free_all_kdata; } for (i = 0; i < p->gang_size; ++i) { @@ -1652,15 +1652,15 @@ static int amdgpu_cs_wait_all_fences(struct amdgpu_device *adev, continue; r = dma_fence_wait_timeout(fence, true, timeout); + if (r > 0 && fence->error) + r = fence->error; + dma_fence_put(fence); if (r < 0) return r; if (r == 0) break; - - if (fence->error) - return fence->error; } memset(wait, 0, sizeof(*wait)); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 40615773b8d1..eb1fe518e78c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -1462,6 +1462,32 @@ bool amdgpu_device_need_post(struct amdgpu_device *adev) } /* + * On APUs with >= 64GB white flickering has been observed w/ SG enabled. + * Disable S/G on such systems until we have a proper fix. + * https://gitlab.freedesktop.org/drm/amd/-/issues/2354 + * https://gitlab.freedesktop.org/drm/amd/-/issues/2735 + */ +bool amdgpu_sg_display_supported(struct amdgpu_device *adev) +{ + switch (amdgpu_sg_display) { + case -1: + break; + case 0: + return false; + case 1: + return true; + default: + return false; + } + if ((totalram_pages() << (PAGE_SHIFT - 10)) + + (adev->gmc.real_vram_size / 1024) >= 64000000) { + DRM_WARN("Disabling S/G due to >=64GB RAM\n"); + return false; + } + return true; +} + +/* * Intel hosts such as Raptor Lake and Sapphire Rapids don't support dynamic * speed switching. Until we have confirmation from Intel that a specific host * supports it, it's safer that we keep it disabled for all. @@ -4351,6 +4377,7 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon) drm_fb_helper_set_suspend_unlocked(adev_to_drm(adev)->fb_helper, true); cancel_delayed_work_sync(&adev->delayed_init_work); + flush_delayed_work(&adev->gfx.gfx_off_delay_work); amdgpu_ras_suspend(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c index c694b41f6461..7537f5aa76f0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c @@ -552,6 +552,41 @@ int amdgpu_fence_driver_sw_init(struct amdgpu_device *adev) } /** + * amdgpu_fence_need_ring_interrupt_restore - helper function to check whether + * fence driver interrupts need to be restored. + * + * @ring: ring that to be checked + * + * Interrupts for rings that belong to GFX IP don't need to be restored + * when the target power state is s0ix. + * + * Return true if need to restore interrupts, false otherwise. + */ +static bool amdgpu_fence_need_ring_interrupt_restore(struct amdgpu_ring *ring) +{ + struct amdgpu_device *adev = ring->adev; + bool is_gfx_power_domain = false; + + switch (ring->funcs->type) { + case AMDGPU_RING_TYPE_SDMA: + /* SDMA 5.x+ is part of GFX power domain so it's covered by GFXOFF */ + if (adev->ip_versions[SDMA0_HWIP][0] >= IP_VERSION(5, 0, 0)) + is_gfx_power_domain = true; + break; + case AMDGPU_RING_TYPE_GFX: + case AMDGPU_RING_TYPE_COMPUTE: + case AMDGPU_RING_TYPE_KIQ: + case AMDGPU_RING_TYPE_MES: + is_gfx_power_domain = true; + break; + default: + break; + } + + return !(adev->in_s0ix && is_gfx_power_domain); +} + +/** * amdgpu_fence_driver_hw_fini - tear down the fence driver * for all possible rings. * @@ -579,7 +614,8 @@ void amdgpu_fence_driver_hw_fini(struct amdgpu_device *adev) amdgpu_fence_driver_force_completion(ring); if (!drm_dev_is_unplugged(adev_to_drm(adev)) && - ring->fence_drv.irq_src) + ring->fence_drv.irq_src && + amdgpu_fence_need_ring_interrupt_restore(ring)) amdgpu_irq_put(adev, ring->fence_drv.irq_src, ring->fence_drv.irq_type); @@ -655,7 +691,8 @@ void amdgpu_fence_driver_hw_init(struct amdgpu_device *adev) continue; /* enable the interrupt */ - if (ring->fence_drv.irq_src) + if (ring->fence_drv.irq_src && + amdgpu_fence_need_ring_interrupt_restore(ring)) amdgpu_irq_get(adev, ring->fence_drv.irq_src, ring->fence_drv.irq_type); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c index a33d4bc34cee..fd81b04559d4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c @@ -692,15 +692,8 @@ void amdgpu_gfx_off_ctrl(struct amdgpu_device *adev, bool enable) if (adev->gfx.gfx_off_req_count == 0 && !adev->gfx.gfx_off_state) { - /* If going to s2idle, no need to wait */ - if (adev->in_s0ix) { - if (!amdgpu_dpm_set_powergating_by_smu(adev, - AMD_IP_BLOCK_TYPE_GFX, true)) - adev->gfx.gfx_off_state = true; - } else { - schedule_delayed_work(&adev->gfx.gfx_off_delay_work, + schedule_delayed_work(&adev->gfx.gfx_off_delay_work, delay); - } } } else { if (adev->gfx.gfx_off_req_count == 0) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c index 00f2106c17b9..f90920fbd340 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c @@ -140,7 +140,6 @@ void amdgpu_irq_disable_all(struct amdgpu_device *adev) continue; for (k = 0; k < src->num_types; ++k) { - atomic_set(&src->enabled_types[k], 0); r = src->funcs->set(adev, src, k, AMDGPU_IRQ_STATE_DISABLE); if (r) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 6c8487945a16..27edf4fa2aab 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -8088,7 +8088,15 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, * Only allow immediate flips for fast updates that don't * change memory domain, FB pitch, DCC state, rotation or * mirroring. + * + * dm_crtc_helper_atomic_check() only accepts async flips with + * fast updates. */ + if (crtc->state->async_flip && + acrtc_state->update_type != UPDATE_TYPE_FAST) + drm_warn_once(state->dev, + "[PLANE:%d:%s] async flip with non-fast update\n", + plane->base.id, plane->name); bundle->flip_addrs[planes_count].flip_immediate = crtc->state->async_flip && acrtc_state->update_type == UPDATE_TYPE_FAST && diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index 46d0a8f57e55..d1f82fcd4e9a 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -33,6 +33,10 @@ #include "amdgpu_dm_mst_types.h" #include "amdgpu_dm_hdcp.h" +#ifdef CONFIG_DRM_AMD_DC_HDCP +#include "amdgpu_dm_hdcp.h" +#endif + #include "dc.h" #include "dm_helpers.h" diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c index e5b7ef7422b8..50dc83404644 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c @@ -357,8 +357,11 @@ void dpp3_set_cursor_attributes( int cur_rom_en = 0; if (color_format == CURSOR_MODE_COLOR_PRE_MULTIPLIED_ALPHA || - color_format == CURSOR_MODE_COLOR_UN_PRE_MULTIPLIED_ALPHA) - cur_rom_en = 1; + color_format == CURSOR_MODE_COLOR_UN_PRE_MULTIPLIED_ALPHA) { + if (cursor_attributes->attribute_flags.bits.ENABLE_CURSOR_DEGAMMA) { + cur_rom_en = 1; + } + } REG_UPDATE_3(CURSOR0_CONTROL, CUR0_MODE, color_format, diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dccg.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dccg.c index 4c2fdfea162f..65c1d754e2d6 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dccg.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dccg.c @@ -47,6 +47,14 @@ void dccg31_update_dpp_dto(struct dccg *dccg, int dpp_inst, int req_dppclk) { struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg); + if (dccg->dpp_clock_gated[dpp_inst]) { + /* + * Do not update the DPPCLK DTO if the clock is stopped. + * It is treated the same as if the pipe itself were in PG. + */ + return; + } + if (dccg->ref_dppclk && req_dppclk) { int ref_dppclk = dccg->ref_dppclk; int modulo, phase; diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c index e0e7d32bb1a0..0746ed31d1d1 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c @@ -332,6 +332,9 @@ static void dccg314_dpp_root_clock_control( { struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg); + if (dccg->dpp_clock_gated[dpp_inst] != clock_on) + return; + if (clock_on) { /* turn off the DTO and leave phase/modulo at max */ REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_ENABLE[dpp_inst], 0); @@ -345,6 +348,8 @@ static void dccg314_dpp_root_clock_control( DPPCLK0_DTO_PHASE, 0, DPPCLK0_DTO_MODULO, 1); } + + dccg->dpp_clock_gated[dpp_inst] = !clock_on; } static const struct dccg_funcs dccg314_funcs = { diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c index 3592efcc7fae..ed0f0a5d354e 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c @@ -921,6 +921,22 @@ static const struct dc_debug_options debug_defaults_drv = { .afmt = true, } }, + + .root_clock_optimization = { + .bits = { + .dpp = true, + .dsc = false, + .hdmistream = false, + .hdmichar = false, + .dpstream = false, + .symclk32_se = false, + .symclk32_le = false, + .symclk_fe = false, + .physymclk = false, + .dpiasymclk = false, + } + }, + .seamless_boot_odm_combine = true }; @@ -1904,6 +1920,10 @@ static bool dcn314_resource_construct( dc->debug = debug_defaults_drv; else dc->debug = debug_defaults_diags; + + /* Disable root clock optimization */ + dc->debug.root_clock_optimization.u32All = 0; + // Init the vm_helper if (dc->vm_helper) vm_helper_init(dc->vm_helper, 16); diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dccg.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dccg.h index 0b700b3d7d97..8dc804bbe98b 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/dccg.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dccg.h @@ -68,6 +68,7 @@ struct dccg { const struct dccg_funcs *funcs; int pipe_dppclk_khz[MAX_PIPES]; int ref_dppclk; + bool dpp_clock_gated[MAX_PIPES]; //int dtbclk_khz[MAX_PIPES];/* TODO needs to be removed */ //int audio_dtbclk_khz;/* TODO needs to be removed */ //int ref_dtbclk_khz;/* TODO needs to be removed */ diff --git a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h index d178f3f44081..42172b00be66 100644 --- a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h +++ b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h @@ -89,6 +89,8 @@ struct amdgpu_dpm_thermal { int max_mem_crit_temp; /* memory max emergency(shutdown) temp */ int max_mem_emergency_temp; + /* SWCTF threshold */ + int sw_ctf_threshold; /* was last interrupt low to high or high to low */ bool high_to_low; /* interrupt source */ diff --git a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c index 11b7b4cffaae..ff360c699171 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c +++ b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c @@ -26,6 +26,7 @@ #include <linux/gfp.h> #include <linux/slab.h> #include <linux/firmware.h> +#include <linux/reboot.h> #include "amd_shared.h" #include "amd_powerplay.h" #include "power_state.h" @@ -91,6 +92,45 @@ static int pp_early_init(void *handle) return 0; } +static void pp_swctf_delayed_work_handler(struct work_struct *work) +{ + struct pp_hwmgr *hwmgr = + container_of(work, struct pp_hwmgr, swctf_delayed_work.work); + struct amdgpu_device *adev = hwmgr->adev; + struct amdgpu_dpm_thermal *range = + &adev->pm.dpm.thermal; + uint32_t gpu_temperature, size; + int ret; + + /* + * If the hotspot/edge temperature is confirmed as below SW CTF setting point + * after the delay enforced, nothing will be done. + * Otherwise, a graceful shutdown will be performed to prevent further damage. + */ + if (range->sw_ctf_threshold && + hwmgr->hwmgr_func->read_sensor) { + ret = hwmgr->hwmgr_func->read_sensor(hwmgr, + AMDGPU_PP_SENSOR_HOTSPOT_TEMP, + &gpu_temperature, + &size); + /* + * For some legacy ASICs, hotspot temperature retrieving might be not + * supported. Check the edge temperature instead then. + */ + if (ret == -EOPNOTSUPP) + ret = hwmgr->hwmgr_func->read_sensor(hwmgr, + AMDGPU_PP_SENSOR_EDGE_TEMP, + &gpu_temperature, + &size); + if (!ret && gpu_temperature / 1000 < range->sw_ctf_threshold) + return; + } + + dev_emerg(adev->dev, "ERROR: GPU over temperature range(SW CTF) detected!\n"); + dev_emerg(adev->dev, "ERROR: System is going to shutdown due to GPU SW CTF!\n"); + orderly_poweroff(true); +} + static int pp_sw_init(void *handle) { struct amdgpu_device *adev = handle; @@ -101,6 +141,10 @@ static int pp_sw_init(void *handle) pr_debug("powerplay sw init %s\n", ret ? "failed" : "successfully"); + if (!ret) + INIT_DELAYED_WORK(&hwmgr->swctf_delayed_work, + pp_swctf_delayed_work_handler); + return ret; } @@ -135,6 +179,8 @@ static int pp_hw_fini(void *handle) struct amdgpu_device *adev = handle; struct pp_hwmgr *hwmgr = adev->powerplay.pp_handle; + cancel_delayed_work_sync(&hwmgr->swctf_delayed_work); + hwmgr_hw_fini(hwmgr); return 0; @@ -221,6 +267,8 @@ static int pp_suspend(void *handle) struct amdgpu_device *adev = handle; struct pp_hwmgr *hwmgr = adev->powerplay.pp_handle; + cancel_delayed_work_sync(&hwmgr->swctf_delayed_work); + return hwmgr_suspend(hwmgr); } diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/hardwaremanager.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/hardwaremanager.c index 981dc8c7112d..90452b66e107 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/hardwaremanager.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/hardwaremanager.c @@ -241,7 +241,8 @@ int phm_start_thermal_controller(struct pp_hwmgr *hwmgr) TEMP_RANGE_MAX, TEMP_RANGE_MIN, TEMP_RANGE_MAX, - TEMP_RANGE_MAX}; + TEMP_RANGE_MAX, + 0}; struct amdgpu_device *adev = hwmgr->adev; if (!hwmgr->not_vf) @@ -265,6 +266,7 @@ int phm_start_thermal_controller(struct pp_hwmgr *hwmgr) adev->pm.dpm.thermal.min_mem_temp = range.mem_min; adev->pm.dpm.thermal.max_mem_crit_temp = range.mem_crit_max; adev->pm.dpm.thermal.max_mem_emergency_temp = range.mem_emergency_max; + adev->pm.dpm.thermal.sw_ctf_threshold = range.sw_ctf_threshold; return ret; } diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c index d82767866ac1..6d887ead2967 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c @@ -5433,6 +5433,8 @@ static int smu7_get_thermal_temperature_range(struct pp_hwmgr *hwmgr, thermal_data->max = data->thermal_temp_setting.temperature_shutdown * PP_TEMPERATURE_UNITS_PER_CENTIGRADES; + thermal_data->sw_ctf_threshold = thermal_data->max; + return 0; } diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.c index bfe80ac0ad8c..d0b1ab6c4523 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.c @@ -603,21 +603,17 @@ int phm_irq_process(struct amdgpu_device *adev, struct amdgpu_irq_src *source, struct amdgpu_iv_entry *entry) { + struct pp_hwmgr *hwmgr = adev->powerplay.pp_handle; uint32_t client_id = entry->client_id; uint32_t src_id = entry->src_id; if (client_id == AMDGPU_IRQ_CLIENTID_LEGACY) { if (src_id == VISLANDS30_IV_SRCID_CG_TSS_THERMAL_LOW_TO_HIGH) { - dev_emerg(adev->dev, "ERROR: GPU over temperature range(SW CTF) detected!\n"); - /* - * SW CTF just occurred. - * Try to do a graceful shutdown to prevent further damage. - */ - dev_emerg(adev->dev, "ERROR: System is going to shutdown due to GPU SW CTF!\n"); - orderly_poweroff(true); - } else if (src_id == VISLANDS30_IV_SRCID_CG_TSS_THERMAL_HIGH_TO_LOW) + schedule_delayed_work(&hwmgr->swctf_delayed_work, + msecs_to_jiffies(AMDGPU_SWCTF_EXTRA_DELAY)); + } else if (src_id == VISLANDS30_IV_SRCID_CG_TSS_THERMAL_HIGH_TO_LOW) { dev_emerg(adev->dev, "ERROR: GPU under temperature range detected!\n"); - else if (src_id == VISLANDS30_IV_SRCID_GPIO_19) { + } else if (src_id == VISLANDS30_IV_SRCID_GPIO_19) { dev_emerg(adev->dev, "ERROR: GPU HW Critical Temperature Fault(aka CTF) detected!\n"); /* * HW CTF just occurred. Shutdown to prevent further damage. @@ -626,15 +622,10 @@ int phm_irq_process(struct amdgpu_device *adev, orderly_poweroff(true); } } else if (client_id == SOC15_IH_CLIENTID_THM) { - if (src_id == 0) { - dev_emerg(adev->dev, "ERROR: GPU over temperature range(SW CTF) detected!\n"); - /* - * SW CTF just occurred. - * Try to do a graceful shutdown to prevent further damage. - */ - dev_emerg(adev->dev, "ERROR: System is going to shutdown due to GPU SW CTF!\n"); - orderly_poweroff(true); - } else + if (src_id == 0) + schedule_delayed_work(&hwmgr->swctf_delayed_work, + msecs_to_jiffies(AMDGPU_SWCTF_EXTRA_DELAY)); + else dev_emerg(adev->dev, "ERROR: GPU under temperature range detected!\n"); } else if (client_id == SOC15_IH_CLIENTID_ROM_SMUIO) { dev_emerg(adev->dev, "ERROR: GPU HW Critical Temperature Fault(aka CTF) detected!\n"); diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c index 6f5161738bf8..d8cd23438b76 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c @@ -5242,6 +5242,9 @@ static int vega10_get_thermal_temperature_range(struct pp_hwmgr *hwmgr, { struct vega10_hwmgr *data = hwmgr->backend; PPTable_t *pp_table = &(data->smc_state_table.pp_table); + struct phm_ppt_v2_information *pp_table_info = + (struct phm_ppt_v2_information *)(hwmgr->pptable); + struct phm_tdp_table *tdp_table = pp_table_info->tdp_table; memcpy(thermal_data, &SMU7ThermalWithDelayPolicy[0], sizeof(struct PP_TemperatureRange)); @@ -5258,6 +5261,13 @@ static int vega10_get_thermal_temperature_range(struct pp_hwmgr *hwmgr, thermal_data->mem_emergency_max = (pp_table->ThbmLimit + CTF_OFFSET_HBM)* PP_TEMPERATURE_UNITS_PER_CENTIGRADES; + if (tdp_table->usSoftwareShutdownTemp > pp_table->ThotspotLimit && + tdp_table->usSoftwareShutdownTemp < VEGA10_THERMAL_MAXIMUM_ALERT_TEMP) + thermal_data->sw_ctf_threshold = tdp_table->usSoftwareShutdownTemp; + else + thermal_data->sw_ctf_threshold = VEGA10_THERMAL_MAXIMUM_ALERT_TEMP; + thermal_data->sw_ctf_threshold *= PP_TEMPERATURE_UNITS_PER_CENTIGRADES; + return 0; } diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c index 33f31461ea6c..1069eaaae2f8 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c @@ -2764,6 +2764,8 @@ static int vega12_notify_cac_buffer_info(struct pp_hwmgr *hwmgr, static int vega12_get_thermal_temperature_range(struct pp_hwmgr *hwmgr, struct PP_TemperatureRange *thermal_data) { + struct phm_ppt_v3_information *pptable_information = + (struct phm_ppt_v3_information *)hwmgr->pptable; struct vega12_hwmgr *data = (struct vega12_hwmgr *)(hwmgr->backend); PPTable_t *pp_table = &(data->smc_state_table.pp_table); @@ -2782,6 +2784,8 @@ static int vega12_get_thermal_temperature_range(struct pp_hwmgr *hwmgr, PP_TEMPERATURE_UNITS_PER_CENTIGRADES; thermal_data->mem_emergency_max = (pp_table->ThbmLimit + CTF_OFFSET_HBM)* PP_TEMPERATURE_UNITS_PER_CENTIGRADES; + thermal_data->sw_ctf_threshold = pptable_information->us_software_shutdown_temp * + PP_TEMPERATURE_UNITS_PER_CENTIGRADES; return 0; } diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c index 2a5abac81b4a..ff77a3683efd 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c @@ -4207,6 +4207,8 @@ static int vega20_notify_cac_buffer_info(struct pp_hwmgr *hwmgr, static int vega20_get_thermal_temperature_range(struct pp_hwmgr *hwmgr, struct PP_TemperatureRange *thermal_data) { + struct phm_ppt_v3_information *pptable_information = + (struct phm_ppt_v3_information *)hwmgr->pptable; struct vega20_hwmgr *data = (struct vega20_hwmgr *)(hwmgr->backend); PPTable_t *pp_table = &(data->smc_state_table.pp_table); @@ -4225,6 +4227,8 @@ static int vega20_get_thermal_temperature_range(struct pp_hwmgr *hwmgr, PP_TEMPERATURE_UNITS_PER_CENTIGRADES; thermal_data->mem_emergency_max = (pp_table->ThbmLimit + CTF_OFFSET_HBM)* PP_TEMPERATURE_UNITS_PER_CENTIGRADES; + thermal_data->sw_ctf_threshold = pptable_information->us_software_shutdown_temp * + PP_TEMPERATURE_UNITS_PER_CENTIGRADES; return 0; } diff --git a/drivers/gpu/drm/amd/pm/powerplay/inc/hwmgr.h b/drivers/gpu/drm/amd/pm/powerplay/inc/hwmgr.h index f1580a26a850..ec10643edea3 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/inc/hwmgr.h +++ b/drivers/gpu/drm/amd/pm/powerplay/inc/hwmgr.h @@ -359,7 +359,7 @@ struct pp_hwmgr_func { int (*set_ppfeature_status)(struct pp_hwmgr *hwmgr, uint64_t ppfeature_masks); int (*set_mp1_state)(struct pp_hwmgr *hwmgr, enum pp_mp1_state mp1_state); int (*asic_reset)(struct pp_hwmgr *hwmgr, enum SMU_ASIC_RESET_MODE mode); - int (*smu_i2c_bus_access)(struct pp_hwmgr *hwmgr, bool acquire); + int (*smu_i2c_bus_access)(struct pp_hwmgr *hwmgr, bool aquire); int (*set_df_cstate)(struct pp_hwmgr *hwmgr, enum pp_df_cstate state); int (*set_xgmi_pstate)(struct pp_hwmgr *hwmgr, uint32_t pstate); int (*disable_power_features_for_compute_performance)(struct pp_hwmgr *hwmgr, @@ -811,6 +811,8 @@ struct pp_hwmgr { bool gfxoff_state_changed_by_workload; uint32_t pstate_sclk_peak; uint32_t pstate_mclk_peak; + + struct delayed_work swctf_delayed_work; }; int hwmgr_early_init(struct pp_hwmgr *hwmgr); diff --git a/drivers/gpu/drm/amd/pm/powerplay/inc/power_state.h b/drivers/gpu/drm/amd/pm/powerplay/inc/power_state.h index a5f2227a3971..0ffc2347829d 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/inc/power_state.h +++ b/drivers/gpu/drm/amd/pm/powerplay/inc/power_state.h @@ -131,6 +131,7 @@ struct PP_TemperatureRange { int mem_min; int mem_crit_max; int mem_emergency_max; + int sw_ctf_threshold; }; struct PP_StateValidationBlock { diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index 4dea79a0c5b5..222af2fae745 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -24,6 +24,7 @@ #include <linux/firmware.h> #include <linux/pci.h> +#include <linux/reboot.h> #include "amdgpu.h" #include "amdgpu_smu.h" @@ -1078,6 +1079,34 @@ static void smu_interrupt_work_fn(struct work_struct *work) smu->ppt_funcs->interrupt_work(smu); } +static void smu_swctf_delayed_work_handler(struct work_struct *work) +{ + struct smu_context *smu = + container_of(work, struct smu_context, swctf_delayed_work.work); + struct smu_temperature_range *range = + &smu->thermal_range; + struct amdgpu_device *adev = smu->adev; + uint32_t hotspot_tmp, size; + + /* + * If the hotspot temperature is confirmed as below SW CTF setting point + * after the delay enforced, nothing will be done. + * Otherwise, a graceful shutdown will be performed to prevent further damage. + */ + if (range->software_shutdown_temp && + smu->ppt_funcs->read_sensor && + !smu->ppt_funcs->read_sensor(smu, + AMDGPU_PP_SENSOR_HOTSPOT_TEMP, + &hotspot_tmp, + &size) && + hotspot_tmp / 1000 < range->software_shutdown_temp) + return; + + dev_emerg(adev->dev, "ERROR: GPU over temperature range(SW CTF) detected!\n"); + dev_emerg(adev->dev, "ERROR: System is going to shutdown due to GPU SW CTF!\n"); + orderly_poweroff(true); +} + static int smu_sw_init(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; @@ -1120,6 +1149,9 @@ static int smu_sw_init(void *handle) smu->smu_dpm.dpm_level = AMD_DPM_FORCED_LEVEL_AUTO; smu->smu_dpm.requested_dpm_level = AMD_DPM_FORCED_LEVEL_AUTO; + INIT_DELAYED_WORK(&smu->swctf_delayed_work, + smu_swctf_delayed_work_handler); + ret = smu_smc_table_sw_init(smu); if (ret) { dev_err(adev->dev, "Failed to sw init smc table!\n"); @@ -1549,9 +1581,9 @@ static int smu_disable_dpms(struct smu_context *smu) /* * For SMU 13.0.4/11, PMFW will handle the features disablement properly - * for gpu reset case. Driver involvement is unnecessary. + * for gpu reset and S0i3 cases. Driver involvement is unnecessary. */ - if (amdgpu_in_reset(adev)) { + if (amdgpu_in_reset(adev) || adev->in_s0ix) { switch (adev->ip_versions[MP1_HWIP][0]) { case IP_VERSION(13, 0, 4): case IP_VERSION(13, 0, 11): @@ -1600,6 +1632,8 @@ static int smu_smc_hw_cleanup(struct smu_context *smu) return ret; } + cancel_delayed_work_sync(&smu->swctf_delayed_work); + ret = smu_disable_dpms(smu); if (ret) { dev_err(adev->dev, "Fail to disable dpm features!\n"); diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h index 09469c750a96..6e2069dcb6b9 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h @@ -573,6 +573,8 @@ struct smu_context u32 debug_param_reg; u32 debug_msg_reg; u32 debug_resp_reg; + + struct delayed_work swctf_delayed_work; }; struct i2c_adapter; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c index 31835d96deef..839a812e0da3 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c @@ -588,7 +588,9 @@ err0_out: return -ENOMEM; } -static uint32_t sienna_cichlid_get_throttler_status_locked(struct smu_context *smu) +static uint32_t sienna_cichlid_get_throttler_status_locked(struct smu_context *smu, + bool use_metrics_v3, + bool use_metrics_v2) { struct smu_table_context *smu_table= &smu->smu_table; SmuMetricsExternal_t *metrics_ext = @@ -596,13 +598,11 @@ static uint32_t sienna_cichlid_get_throttler_status_locked(struct smu_context *s uint32_t throttler_status = 0; int i; - if ((smu->adev->ip_versions[MP1_HWIP][0] == IP_VERSION(11, 0, 7)) && - (smu->smc_fw_version >= 0x3A4900)) { + if (use_metrics_v3) { for (i = 0; i < THROTTLER_COUNT; i++) throttler_status |= (metrics_ext->SmuMetrics_V3.ThrottlingPercentage[i] ? 1U << i : 0); - } else if ((smu->adev->ip_versions[MP1_HWIP][0] == IP_VERSION(11, 0, 7)) && - (smu->smc_fw_version >= 0x3A4300)) { + } else if (use_metrics_v2) { for (i = 0; i < THROTTLER_COUNT; i++) throttler_status |= (metrics_ext->SmuMetrics_V2.ThrottlingPercentage[i] ? 1U << i : 0); @@ -864,7 +864,7 @@ static int sienna_cichlid_get_smu_metrics_data(struct smu_context *smu, metrics->TemperatureVrSoc) * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; break; case METRICS_THROTTLER_STATUS: - *value = sienna_cichlid_get_throttler_status_locked(smu); + *value = sienna_cichlid_get_throttler_status_locked(smu, use_metrics_v3, use_metrics_v2); break; case METRICS_CURR_FANSPEED: *value = use_metrics_v3 ? metrics_v3->CurrFanSpeed : @@ -4017,7 +4017,7 @@ static ssize_t sienna_cichlid_get_gpu_metrics(struct smu_context *smu, gpu_metrics->current_dclk1 = use_metrics_v3 ? metrics_v3->CurrClock[PPCLK_DCLK_1] : use_metrics_v2 ? metrics_v2->CurrClock[PPCLK_DCLK_1] : metrics->CurrClock[PPCLK_DCLK_1]; - gpu_metrics->throttle_status = sienna_cichlid_get_throttler_status_locked(smu); + gpu_metrics->throttle_status = sienna_cichlid_get_throttler_status_locked(smu, use_metrics_v3, use_metrics_v2); gpu_metrics->indep_throttle_status = smu_cmn_get_indep_throttler_status(gpu_metrics->throttle_status, sienna_cichlid_throttler_map); diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c index e1ef88ee1ed3..aa4a5498a12f 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c @@ -1412,13 +1412,8 @@ static int smu_v11_0_irq_process(struct amdgpu_device *adev, if (client_id == SOC15_IH_CLIENTID_THM) { switch (src_id) { case THM_11_0__SRCID__THM_DIG_THERM_L2H: - dev_emerg(adev->dev, "ERROR: GPU over temperature range(SW CTF) detected!\n"); - /* - * SW CTF just occurred. - * Try to do a graceful shutdown to prevent further damage. - */ - dev_emerg(adev->dev, "ERROR: System is going to shutdown due to GPU SW CTF!\n"); - orderly_poweroff(true); + schedule_delayed_work(&smu->swctf_delayed_work, + msecs_to_jiffies(AMDGPU_SWCTF_EXTRA_DELAY)); break; case THM_11_0__SRCID__THM_DIG_THERM_H2L: dev_emerg(adev->dev, "ERROR: GPU under temperature range detected\n"); diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c index 63b5c52a67cb..7bf800364c14 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c @@ -1342,13 +1342,8 @@ static int smu_v13_0_irq_process(struct amdgpu_device *adev, if (client_id == SOC15_IH_CLIENTID_THM) { switch (src_id) { case THM_11_0__SRCID__THM_DIG_THERM_L2H: - dev_emerg(adev->dev, "ERROR: GPU over temperature range(SW CTF) detected!\n"); - /* - * SW CTF just occurred. - * Try to do a graceful shutdown to prevent further damage. - */ - dev_emerg(adev->dev, "ERROR: System is going to shutdown due to GPU SW CTF!\n"); - orderly_poweroff(true); + schedule_delayed_work(&smu->swctf_delayed_work, + msecs_to_jiffies(AMDGPU_SWCTF_EXTRA_DELAY)); break; case THM_11_0__SRCID__THM_DIG_THERM_H2L: dev_emerg(adev->dev, "ERROR: GPU under temperature range detected\n"); diff --git a/drivers/gpu/drm/arm/hdlcd_drv.c b/drivers/gpu/drm/arm/hdlcd_drv.c index 7043d1c9ed8f..98267e355918 100644 --- a/drivers/gpu/drm/arm/hdlcd_drv.c +++ b/drivers/gpu/drm/arm/hdlcd_drv.c @@ -297,7 +297,7 @@ static int hdlcd_drm_bind(struct device *dev) */ if (hdlcd_read(hdlcd, HDLCD_REG_COMMAND)) { hdlcd_write(hdlcd, HDLCD_REG_COMMAND, 0); - drm_aperture_remove_framebuffers(false, &hdlcd_driver); + drm_aperture_remove_framebuffers(&hdlcd_driver); } drm_mode_config_reset(drm); diff --git a/drivers/gpu/drm/armada/armada_drv.c b/drivers/gpu/drm/armada/armada_drv.c index 142668cd6d7c..688ba358f531 100644 --- a/drivers/gpu/drm/armada/armada_drv.c +++ b/drivers/gpu/drm/armada/armada_drv.c @@ -95,7 +95,7 @@ static int armada_drm_bind(struct device *dev) } /* Remove early framebuffers */ - ret = drm_aperture_remove_framebuffers(false, &armada_drm_driver); + ret = drm_aperture_remove_framebuffers(&armada_drm_driver); if (ret) { dev_err(dev, "[" DRM_NAME ":%s] can't kick out simple-fb: %d\n", __func__, ret); diff --git a/drivers/gpu/drm/ast/ast_drv.c b/drivers/gpu/drm/ast/ast_drv.c index 420fc75c240e..3ac24a780f50 100644 --- a/drivers/gpu/drm/ast/ast_drv.c +++ b/drivers/gpu/drm/ast/ast_drv.c @@ -90,27 +90,13 @@ static const struct pci_device_id ast_pciidlist[] = { MODULE_DEVICE_TABLE(pci, ast_pciidlist); -static int ast_remove_conflicting_framebuffers(struct pci_dev *pdev) -{ - bool primary = false; - resource_size_t base, size; - - base = pci_resource_start(pdev, 0); - size = pci_resource_len(pdev, 0); -#ifdef CONFIG_X86 - primary = pdev->resource[PCI_ROM_RESOURCE].flags & IORESOURCE_ROM_SHADOW; -#endif - - return drm_aperture_remove_conflicting_framebuffers(base, size, primary, &ast_driver); -} - static int ast_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { struct ast_private *ast; struct drm_device *dev; int ret; - ret = ast_remove_conflicting_framebuffers(pdev); + ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, &ast_driver); if (ret) return ret; diff --git a/drivers/gpu/drm/drm_aperture.c b/drivers/gpu/drm/drm_aperture.c index 3b8fdeeafd53..697cffbfd603 100644 --- a/drivers/gpu/drm/drm_aperture.c +++ b/drivers/gpu/drm/drm_aperture.c @@ -32,17 +32,13 @@ * * static int remove_conflicting_framebuffers(struct pci_dev *pdev) * { - * bool primary = false; * resource_size_t base, size; * int ret; * * base = pci_resource_start(pdev, 0); * size = pci_resource_len(pdev, 0); - * #ifdef CONFIG_X86 - * primary = pdev->resource[PCI_ROM_RESOURCE].flags & IORESOURCE_ROM_SHADOW; - * #endif * - * return drm_aperture_remove_conflicting_framebuffers(base, size, primary, + * return drm_aperture_remove_conflicting_framebuffers(base, size, * &example_driver); * } * @@ -161,7 +157,6 @@ EXPORT_SYMBOL(devm_aperture_acquire_from_firmware); * drm_aperture_remove_conflicting_framebuffers - remove existing framebuffers in the given range * @base: the aperture's base address in physical memory * @size: aperture size in bytes - * @primary: also kick vga16fb if present * @req_driver: requesting DRM driver * * This function removes graphics device drivers which use the memory range described by @@ -171,9 +166,9 @@ EXPORT_SYMBOL(devm_aperture_acquire_from_firmware); * 0 on success, or a negative errno code otherwise */ int drm_aperture_remove_conflicting_framebuffers(resource_size_t base, resource_size_t size, - bool primary, const struct drm_driver *req_driver) + const struct drm_driver *req_driver) { - return aperture_remove_conflicting_devices(base, size, primary, req_driver->name); + return aperture_remove_conflicting_devices(base, size, false, req_driver->name); } EXPORT_SYMBOL(drm_aperture_remove_conflicting_framebuffers); diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c index 5fdc608043e7..e33f06bb66eb 100644 --- a/drivers/gpu/drm/drm_gem_shmem_helper.c +++ b/drivers/gpu/drm/drm_gem_shmem_helper.c @@ -622,7 +622,13 @@ int drm_gem_shmem_mmap(struct drm_gem_shmem_object *shmem, struct vm_area_struct int ret; if (obj->import_attach) { + /* Reset both vm_ops and vm_private_data, so we don't end up with + * vm_ops pointing to our implementation if the dma-buf backend + * doesn't set those fields. + */ vma->vm_private_data = NULL; + vma->vm_ops = NULL; + ret = dma_buf_mmap(obj->dma_buf, vma, 0); /* Drop the reference drm_gem_mmap_obj() acquired.*/ diff --git a/drivers/gpu/drm/gma500/psb_drv.c b/drivers/gpu/drm/gma500/psb_drv.c index cd9c73f5a64a..738eb558a97e 100644 --- a/drivers/gpu/drm/gma500/psb_drv.c +++ b/drivers/gpu/drm/gma500/psb_drv.c @@ -424,12 +424,17 @@ static int psb_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* * We cannot yet easily find the framebuffer's location in memory. So - * remove all framebuffers here. + * remove all framebuffers here. Note that we still want the pci special + * handling to kick out vgacon. * * TODO: Refactor psb_driver_load() to map vdc_reg earlier. Then we * might be able to read the framebuffer range from the device. */ - ret = drm_aperture_remove_framebuffers(true, &driver); + ret = drm_aperture_remove_framebuffers(&driver); + if (ret) + return ret; + + ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, &driver); if (ret) return ret; diff --git a/drivers/gpu/drm/hyperv/hyperv_drm_drv.c b/drivers/gpu/drm/hyperv/hyperv_drm_drv.c index 427c20ba3404..7e81d58c083f 100644 --- a/drivers/gpu/drm/hyperv/hyperv_drm_drv.c +++ b/drivers/gpu/drm/hyperv/hyperv_drm_drv.c @@ -74,7 +74,6 @@ static int hyperv_setup_vram(struct hyperv_drm_device *hv, drm_aperture_remove_conflicting_framebuffers(screen_info.lfb_base, screen_info.lfb_size, - false, &hyperv_driver); hv->fb_size = (unsigned long)hv->mmio_megabytes * 1024 * 1024; diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index cfc17cd27541..520ed321435a 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -7106,8 +7106,6 @@ static void intel_update_crtc(struct intel_atomic_state *state, intel_fbc_update(state, crtc); - drm_WARN_ON(&i915->drm, !intel_display_power_is_enabled(i915, POWER_DOMAIN_DC_OFF)); - if (!modeset && intel_crtc_needs_color_update(new_crtc_state)) intel_color_commit_noarm(new_crtc_state); @@ -7481,28 +7479,8 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state) drm_atomic_helper_wait_for_dependencies(&state->base); drm_dp_mst_atomic_wait_for_dependencies(&state->base); - /* - * During full modesets we write a lot of registers, wait - * for PLLs, etc. Doing that while DC states are enabled - * is not a good idea. - * - * During fastsets and other updates we also need to - * disable DC states due to the following scenario: - * 1. DC5 exit and PSR exit happen - * 2. Some or all _noarm() registers are written - * 3. Due to some long delay PSR is re-entered - * 4. DC5 entry -> DMC saves the already written new - * _noarm() registers and the old not yet written - * _arm() registers - * 5. DC5 exit -> DMC restores a mixture of old and - * new register values and arms the update - * 6. PSR exit -> hardware latches a mixture of old and - * new register values -> corrupted frame, or worse - * 7. New _arm() registers are finally written - * 8. Hardware finally latches a complete set of new - * register values, and subsequent frames will be OK again - */ - wakeref = intel_display_power_get(dev_priv, POWER_DOMAIN_DC_OFF); + if (state->modeset) + wakeref = intel_display_power_get(dev_priv, POWER_DOMAIN_MODESET); intel_atomic_prepare_plane_clear_colors(state); @@ -7646,8 +7624,8 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state) * the culprit. */ intel_uncore_arm_unclaimed_mmio_detection(&dev_priv->uncore); + intel_display_power_put(dev_priv, POWER_DOMAIN_MODESET, wakeref); } - intel_display_power_put(dev_priv, POWER_DOMAIN_DC_OFF, wakeref); intel_runtime_pm_put(&dev_priv->runtime_pm, state->wakeref); /* diff --git a/drivers/gpu/drm/i915/display/intel_sdvo.c b/drivers/gpu/drm/i915/display/intel_sdvo.c index 21805c15d5eb..a37b77cfb391 100644 --- a/drivers/gpu/drm/i915/display/intel_sdvo.c +++ b/drivers/gpu/drm/i915/display/intel_sdvo.c @@ -2731,7 +2731,7 @@ static struct intel_sdvo_connector *intel_sdvo_connector_alloc(void) __drm_atomic_helper_connector_reset(&sdvo_connector->base.base, &conn_state->base.base); - INIT_LIST_HEAD(&sdvo_connector->base.panel.fixed_modes); + intel_panel_init_alloc(&sdvo_connector->base); return sdvo_connector; } diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c index e1c76e5bfa82..aee39b96a73e 100644 --- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c @@ -165,14 +165,60 @@ static u32 preparser_disable(bool state) return MI_ARB_CHECK | 1 << 8 | state; } -u32 *gen12_emit_aux_table_inv(struct intel_gt *gt, u32 *cs, const i915_reg_t inv_reg) +static i915_reg_t gen12_get_aux_inv_reg(struct intel_engine_cs *engine) { - u32 gsi_offset = gt->uncore->gsi_offset; + switch (engine->id) { + case RCS0: + return GEN12_CCS_AUX_INV; + case BCS0: + return GEN12_BCS0_AUX_INV; + case VCS0: + return GEN12_VD0_AUX_INV; + case VCS2: + return GEN12_VD2_AUX_INV; + case VECS0: + return GEN12_VE0_AUX_INV; + case CCS0: + return GEN12_CCS0_AUX_INV; + default: + return INVALID_MMIO_REG; + } +} + +static bool gen12_needs_ccs_aux_inv(struct intel_engine_cs *engine) +{ + i915_reg_t reg = gen12_get_aux_inv_reg(engine); + + if (IS_PONTEVECCHIO(engine->i915)) + return false; + + /* + * So far platforms supported by i915 having flat ccs do not require + * AUX invalidation. Check also whether the engine requires it. + */ + return i915_mmio_reg_valid(reg) && !HAS_FLAT_CCS(engine->i915); +} + +u32 *gen12_emit_aux_table_inv(struct intel_engine_cs *engine, u32 *cs) +{ + i915_reg_t inv_reg = gen12_get_aux_inv_reg(engine); + u32 gsi_offset = engine->gt->uncore->gsi_offset; + + if (!gen12_needs_ccs_aux_inv(engine)) + return cs; *cs++ = MI_LOAD_REGISTER_IMM(1) | MI_LRI_MMIO_REMAP_EN; *cs++ = i915_mmio_reg_offset(inv_reg) + gsi_offset; *cs++ = AUX_INV; - *cs++ = MI_NOOP; + + *cs++ = MI_SEMAPHORE_WAIT_TOKEN | + MI_SEMAPHORE_REGISTER_POLL | + MI_SEMAPHORE_POLL | + MI_SEMAPHORE_SAD_EQ_SDD; + *cs++ = 0; + *cs++ = i915_mmio_reg_offset(inv_reg) + gsi_offset; + *cs++ = 0; + *cs++ = 0; return cs; } @@ -181,7 +227,11 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode) { struct intel_engine_cs *engine = rq->engine; - if (mode & EMIT_FLUSH) { + /* + * On Aux CCS platforms the invalidation of the Aux + * table requires quiescing memory traffic beforehand + */ + if (mode & EMIT_FLUSH || gen12_needs_ccs_aux_inv(engine)) { u32 flags = 0; u32 *cs; @@ -236,10 +286,9 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode) else if (engine->class == COMPUTE_CLASS) flags &= ~PIPE_CONTROL_3D_ENGINE_FLAGS; - if (!HAS_FLAT_CCS(rq->engine->i915)) - count = 8 + 4; - else - count = 8; + count = 8; + if (gen12_needs_ccs_aux_inv(rq->engine)) + count += 8; cs = intel_ring_begin(rq, count); if (IS_ERR(cs)) @@ -254,11 +303,7 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode) cs = gen8_emit_pipe_control(cs, flags, LRC_PPHWSP_SCRATCH_ADDR); - if (!HAS_FLAT_CCS(rq->engine->i915)) { - /* hsdes: 1809175790 */ - cs = gen12_emit_aux_table_inv(rq->engine->gt, - cs, GEN12_GFX_CCS_AUX_NV); - } + cs = gen12_emit_aux_table_inv(engine, cs); *cs++ = preparser_disable(false); intel_ring_advance(rq, cs); @@ -269,21 +314,14 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode) int gen12_emit_flush_xcs(struct i915_request *rq, u32 mode) { - intel_engine_mask_t aux_inv = 0; - u32 cmd, *cs; + u32 cmd = 4; + u32 *cs; - cmd = 4; if (mode & EMIT_INVALIDATE) { cmd += 2; - if (!HAS_FLAT_CCS(rq->engine->i915) && - (rq->engine->class == VIDEO_DECODE_CLASS || - rq->engine->class == VIDEO_ENHANCEMENT_CLASS)) { - aux_inv = rq->engine->mask & - ~GENMASK(_BCS(I915_MAX_BCS - 1), BCS0); - if (aux_inv) - cmd += 4; - } + if (gen12_needs_ccs_aux_inv(rq->engine)) + cmd += 8; } cs = intel_ring_begin(rq, cmd); @@ -314,14 +352,7 @@ int gen12_emit_flush_xcs(struct i915_request *rq, u32 mode) *cs++ = 0; /* upper addr */ *cs++ = 0; /* value */ - if (aux_inv) { /* hsdes: 1809175790 */ - if (rq->engine->class == VIDEO_DECODE_CLASS) - cs = gen12_emit_aux_table_inv(rq->engine->gt, - cs, GEN12_VD0_AUX_NV); - else - cs = gen12_emit_aux_table_inv(rq->engine->gt, - cs, GEN12_VE0_AUX_NV); - } + cs = gen12_emit_aux_table_inv(rq->engine, cs); if (mode & EMIT_INVALIDATE) *cs++ = preparser_disable(false); diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.h b/drivers/gpu/drm/i915/gt/gen8_engine_cs.h index 655e5c00ddc2..42cca26013a0 100644 --- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.h +++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.h @@ -13,6 +13,7 @@ #include "intel_gt_regs.h" #include "intel_gpu_commands.h" +struct intel_engine_cs; struct intel_gt; struct i915_request; @@ -46,7 +47,7 @@ u32 *gen8_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs); u32 *gen11_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs); u32 *gen12_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs); -u32 *gen12_emit_aux_table_inv(struct intel_gt *gt, u32 *cs, const i915_reg_t inv_reg); +u32 *gen12_emit_aux_table_inv(struct intel_engine_cs *engine, u32 *cs); static inline u32 * __gen8_emit_pipe_control(u32 *batch, u32 flags0, u32 flags1, u32 offset) diff --git a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h index f50ea92910d9..4105e66202ae 100644 --- a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h +++ b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h @@ -120,6 +120,7 @@ #define MI_SEMAPHORE_TARGET(engine) ((engine)<<15) #define MI_SEMAPHORE_WAIT MI_INSTR(0x1c, 2) /* GEN8+ */ #define MI_SEMAPHORE_WAIT_TOKEN MI_INSTR(0x1c, 3) /* GEN12+ */ +#define MI_SEMAPHORE_REGISTER_POLL (1 << 16) #define MI_SEMAPHORE_POLL (1 << 15) #define MI_SEMAPHORE_SAD_GT_SDD (0 << 12) #define MI_SEMAPHORE_SAD_GTE_SDD (1 << 12) diff --git a/drivers/gpu/drm/i915/gt/intel_gt_regs.h b/drivers/gpu/drm/i915/gt/intel_gt_regs.h index c3cd92691795..404673f96325 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_regs.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_regs.h @@ -332,9 +332,11 @@ #define GEN8_PRIVATE_PAT_HI _MMIO(0x40e0 + 4) #define GEN10_PAT_INDEX(index) _MMIO(0x40e0 + (index) * 4) #define BSD_HWS_PGA_GEN7 _MMIO(0x4180) -#define GEN12_GFX_CCS_AUX_NV _MMIO(0x4208) -#define GEN12_VD0_AUX_NV _MMIO(0x4218) -#define GEN12_VD1_AUX_NV _MMIO(0x4228) + +#define GEN12_CCS_AUX_INV _MMIO(0x4208) +#define GEN12_VD0_AUX_INV _MMIO(0x4218) +#define GEN12_VE0_AUX_INV _MMIO(0x4238) +#define GEN12_BCS0_AUX_INV _MMIO(0x4248) #define GEN8_RTCR _MMIO(0x4260) #define GEN8_M1TCR _MMIO(0x4264) @@ -342,14 +344,12 @@ #define GEN8_BTCR _MMIO(0x426c) #define GEN8_VTCR _MMIO(0x4270) -#define GEN12_VD2_AUX_NV _MMIO(0x4298) -#define GEN12_VD3_AUX_NV _MMIO(0x42a8) -#define GEN12_VE0_AUX_NV _MMIO(0x4238) - #define BLT_HWS_PGA_GEN7 _MMIO(0x4280) -#define GEN12_VE1_AUX_NV _MMIO(0x42b8) +#define GEN12_VD2_AUX_INV _MMIO(0x4298) +#define GEN12_CCS0_AUX_INV _MMIO(0x42c8) #define AUX_INV REG_BIT(0) + #define VEBOX_HWS_PGA_GEN7 _MMIO(0x4380) #define GEN12_AUX_ERR_DBG _MMIO(0x43f4) diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index 7771a19008c6..884dda4c77f8 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -1399,10 +1399,7 @@ gen12_emit_indirect_ctx_rcs(const struct intel_context *ce, u32 *cs) IS_DG2_G11(ce->engine->i915)) cs = gen8_emit_pipe_control(cs, PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE, 0); - /* hsdes: 1809175790 */ - if (!HAS_FLAT_CCS(ce->engine->i915)) - cs = gen12_emit_aux_table_inv(ce->engine->gt, - cs, GEN12_GFX_CCS_AUX_NV); + cs = gen12_emit_aux_table_inv(ce->engine, cs); /* Wa_16014892111 */ if (IS_DG2(ce->engine->i915)) @@ -1425,17 +1422,7 @@ gen12_emit_indirect_ctx_xcs(const struct intel_context *ce, u32 *cs) PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE, 0); - /* hsdes: 1809175790 */ - if (!HAS_FLAT_CCS(ce->engine->i915)) { - if (ce->engine->class == VIDEO_DECODE_CLASS) - cs = gen12_emit_aux_table_inv(ce->engine->gt, - cs, GEN12_VD0_AUX_NV); - else if (ce->engine->class == VIDEO_ENHANCEMENT_CLASS) - cs = gen12_emit_aux_table_inv(ce->engine->gt, - cs, GEN12_VE0_AUX_NV); - } - - return cs; + return gen12_emit_aux_table_inv(ce->engine, cs); } static void diff --git a/drivers/gpu/drm/i915/i915_active.c b/drivers/gpu/drm/i915/i915_active.c index 8ef93889061a..5ec293011d99 100644 --- a/drivers/gpu/drm/i915/i915_active.c +++ b/drivers/gpu/drm/i915/i915_active.c @@ -449,8 +449,11 @@ int i915_active_add_request(struct i915_active *ref, struct i915_request *rq) } } while (unlikely(is_barrier(active))); - if (!__i915_active_fence_set(active, fence)) + fence = __i915_active_fence_set(active, fence); + if (!fence) __i915_active_acquire(ref); + else + dma_fence_put(fence); out: i915_active_release(ref); @@ -469,13 +472,9 @@ __i915_active_set_fence(struct i915_active *ref, return NULL; } - rcu_read_lock(); prev = __i915_active_fence_set(active, fence); - if (prev) - prev = dma_fence_get_rcu(prev); - else + if (!prev) __i915_active_acquire(ref); - rcu_read_unlock(); return prev; } @@ -1019,10 +1018,11 @@ void i915_request_add_active_barriers(struct i915_request *rq) * * Records the new @fence as the last active fence along its timeline in * this active tracker, moving the tracking callbacks from the previous - * fence onto this one. Returns the previous fence (if not already completed), - * which the caller must ensure is executed before the new fence. To ensure - * that the order of fences within the timeline of the i915_active_fence is - * understood, it should be locked by the caller. + * fence onto this one. Gets and returns a reference to the previous fence + * (if not already completed), which the caller must put after making sure + * that it is executed before the new fence. To ensure that the order of + * fences within the timeline of the i915_active_fence is understood, it + * should be locked by the caller. */ struct dma_fence * __i915_active_fence_set(struct i915_active_fence *active, @@ -1031,7 +1031,23 @@ __i915_active_fence_set(struct i915_active_fence *active, struct dma_fence *prev; unsigned long flags; - if (fence == rcu_access_pointer(active->fence)) + /* + * In case of fences embedded in i915_requests, their memory is + * SLAB_FAILSAFE_BY_RCU, then it can be reused right after release + * by new requests. Then, there is a risk of passing back a pointer + * to a new, completely unrelated fence that reuses the same memory + * while tracked under a different active tracker. Combined with i915 + * perf open/close operations that build await dependencies between + * engine kernel context requests and user requests from different + * timelines, this can lead to dependency loops and infinite waits. + * + * As a countermeasure, we try to get a reference to the active->fence + * first, so if we succeed and pass it back to our user then it is not + * released and potentially reused by an unrelated request before the + * user has a chance to set up an await dependency on it. + */ + prev = i915_active_fence_get(active); + if (fence == prev) return fence; GEM_BUG_ON(test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)); @@ -1040,27 +1056,56 @@ __i915_active_fence_set(struct i915_active_fence *active, * Consider that we have two threads arriving (A and B), with * C already resident as the active->fence. * - * A does the xchg first, and so it sees C or NULL depending - * on the timing of the interrupt handler. If it is NULL, the - * previous fence must have been signaled and we know that - * we are first on the timeline. If it is still present, - * we acquire the lock on that fence and serialise with the interrupt - * handler, in the process removing it from any future interrupt - * callback. A will then wait on C before executing (if present). - * - * As B is second, it sees A as the previous fence and so waits for - * it to complete its transition and takes over the occupancy for - * itself -- remembering that it needs to wait on A before executing. + * Both A and B have got a reference to C or NULL, depending on the + * timing of the interrupt handler. Let's assume that if A has got C + * then it has locked C first (before B). * * Note the strong ordering of the timeline also provides consistent * nesting rules for the fence->lock; the inner lock is always the * older lock. */ spin_lock_irqsave(fence->lock, flags); - prev = xchg(__active_fence_slot(active), fence); - if (prev) { - GEM_BUG_ON(prev == fence); + if (prev) spin_lock_nested(prev->lock, SINGLE_DEPTH_NESTING); + + /* + * A does the cmpxchg first, and so it sees C or NULL, as before, or + * something else, depending on the timing of other threads and/or + * interrupt handler. If not the same as before then A unlocks C if + * applicable and retries, starting from an attempt to get a new + * active->fence. Meanwhile, B follows the same path as A. + * Once A succeeds with cmpxch, B fails again, retires, gets A from + * active->fence, locks it as soon as A completes, and possibly + * succeeds with cmpxchg. + */ + while (cmpxchg(__active_fence_slot(active), prev, fence) != prev) { + if (prev) { + spin_unlock(prev->lock); + dma_fence_put(prev); + } + spin_unlock_irqrestore(fence->lock, flags); + + prev = i915_active_fence_get(active); + GEM_BUG_ON(prev == fence); + + spin_lock_irqsave(fence->lock, flags); + if (prev) + spin_lock_nested(prev->lock, SINGLE_DEPTH_NESTING); + } + + /* + * If prev is NULL then the previous fence must have been signaled + * and we know that we are first on the timeline. If it is still + * present then, having the lock on that fence already acquired, we + * serialise with the interrupt handler, in the process of removing it + * from any future interrupt callback. A will then wait on C before + * executing (if present). + * + * As B is second, it sees A as the previous fence and so waits for + * it to complete its transition and takes over the occupancy for + * itself -- remembering that it needs to wait on A before executing. + */ + if (prev) { __list_del_entry(&active->cb.node); spin_unlock(prev->lock); /* serialise with prev->cb_list */ } @@ -1077,11 +1122,7 @@ int i915_active_fence_set(struct i915_active_fence *active, int err = 0; /* Must maintain timeline ordering wrt previous active requests */ - rcu_read_lock(); fence = __i915_active_fence_set(active, &rq->fence); - if (fence) /* but the previous fence may not belong to that timeline! */ - fence = dma_fence_get_rcu(fence); - rcu_read_unlock(); if (fence) { err = i915_request_await_dma_fence(rq, fence); dma_fence_put(fence); diff --git a/drivers/gpu/drm/i915/i915_driver.c b/drivers/gpu/drm/i915/i915_driver.c index 61c38fc734cf..b67e085324fc 100644 --- a/drivers/gpu/drm/i915/i915_driver.c +++ b/drivers/gpu/drm/i915/i915_driver.c @@ -574,7 +574,6 @@ static int i915_pcode_init(struct drm_i915_private *i915) static int i915_driver_hw_probe(struct drm_i915_private *dev_priv) { struct pci_dev *pdev = to_pci_dev(dev_priv->drm.dev); - struct pci_dev *root_pdev; int ret; if (i915_inject_probe_failure(dev_priv)) @@ -686,15 +685,6 @@ static int i915_driver_hw_probe(struct drm_i915_private *dev_priv) intel_bw_init_hw(dev_priv); - /* - * FIXME: Temporary hammer to avoid freezing the machine on our DGFX - * This should be totally removed when we handle the pci states properly - * on runtime PM and on s2idle cases. - */ - root_pdev = pcie_find_root_port(pdev); - if (root_pdev) - pci_d3cold_disable(root_pdev); - return 0; err_msi: @@ -718,16 +708,11 @@ err_perf: static void i915_driver_hw_remove(struct drm_i915_private *dev_priv) { struct pci_dev *pdev = to_pci_dev(dev_priv->drm.dev); - struct pci_dev *root_pdev; i915_perf_fini(dev_priv); if (pdev->msi_enabled) pci_disable_msi(pdev); - - root_pdev = pcie_find_root_port(pdev); - if (root_pdev) - pci_d3cold_enable(root_pdev); } /** @@ -1622,6 +1607,8 @@ static int intel_runtime_suspend(struct device *kdev) { struct drm_i915_private *dev_priv = kdev_to_i915(kdev); struct intel_runtime_pm *rpm = &dev_priv->runtime_pm; + struct pci_dev *pdev = to_pci_dev(dev_priv->drm.dev); + struct pci_dev *root_pdev; struct intel_gt *gt; int ret, i; @@ -1671,6 +1658,15 @@ static int intel_runtime_suspend(struct device *kdev) drm_err(&dev_priv->drm, "Unclaimed access detected prior to suspending\n"); + /* + * FIXME: Temporary hammer to avoid freezing the machine on our DGFX + * This should be totally removed when we handle the pci states properly + * on runtime PM. + */ + root_pdev = pcie_find_root_port(pdev); + if (root_pdev) + pci_d3cold_disable(root_pdev); + rpm->suspended = true; /* @@ -1709,6 +1705,8 @@ static int intel_runtime_resume(struct device *kdev) { struct drm_i915_private *dev_priv = kdev_to_i915(kdev); struct intel_runtime_pm *rpm = &dev_priv->runtime_pm; + struct pci_dev *pdev = to_pci_dev(dev_priv->drm.dev); + struct pci_dev *root_pdev; struct intel_gt *gt; int ret, i; @@ -1722,6 +1720,11 @@ static int intel_runtime_resume(struct device *kdev) intel_opregion_notify_adapter(dev_priv, PCI_D0); rpm->suspended = false; + + root_pdev = pcie_find_root_port(pdev); + if (root_pdev) + pci_d3cold_enable(root_pdev); + if (intel_uncore_unclaimed_mmio(&dev_priv->uncore)) drm_dbg(&dev_priv->drm, "Unclaimed access during suspend, bios?\n"); diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index f949a9495758..e69e1cbb5d01 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -1661,6 +1661,11 @@ __i915_request_ensure_parallel_ordering(struct i915_request *rq, request_to_parent(rq)->parallel.last_rq = i915_request_get(rq); + /* + * Users have to put a reference potentially got by + * __i915_active_fence_set() to the returned request + * when no longer needed + */ return to_request(__i915_active_fence_set(&timeline->last_request, &rq->fence)); } @@ -1707,6 +1712,10 @@ __i915_request_ensure_ordering(struct i915_request *rq, 0); } + /* + * Users have to put the reference to prev potentially got + * by __i915_active_fence_set() when no longer needed + */ return prev; } @@ -1760,6 +1769,8 @@ __i915_request_add_to_timeline(struct i915_request *rq) prev = __i915_request_ensure_ordering(rq, timeline); else prev = __i915_request_ensure_parallel_ordering(rq, timeline); + if (prev) + i915_request_put(prev); /* * Make sure that no request gazumped us - if it was allocated after diff --git a/drivers/gpu/drm/imx/ipuv3-crtc.c b/drivers/gpu/drm/imx/ipuv3-crtc.c index 5f26090b0c98..89585b31b985 100644 --- a/drivers/gpu/drm/imx/ipuv3-crtc.c +++ b/drivers/gpu/drm/imx/ipuv3-crtc.c @@ -310,7 +310,7 @@ static void ipu_crtc_mode_set_nofb(struct drm_crtc *crtc) dev_warn(ipu_crtc->dev, "8-pixel align hactive %d -> %d\n", sig_cfg.mode.hactive, new_hactive); - sig_cfg.mode.hfront_porch = new_hactive - sig_cfg.mode.hactive; + sig_cfg.mode.hfront_porch -= new_hactive - sig_cfg.mode.hactive; sig_cfg.mode.hactive = new_hactive; } diff --git a/drivers/gpu/drm/meson/meson_drv.c b/drivers/gpu/drm/meson/meson_drv.c index 7caf937c3c90..3c0699307678 100644 --- a/drivers/gpu/drm/meson/meson_drv.c +++ b/drivers/gpu/drm/meson/meson_drv.c @@ -285,7 +285,7 @@ static int meson_drv_bind_master(struct device *dev, bool has_components) * Remove early framebuffers (ie. simplefb). The framebuffer can be * located anywhere in RAM */ - ret = drm_aperture_remove_framebuffers(false, &meson_driver); + ret = drm_aperture_remove_framebuffers(&meson_driver); if (ret) goto free_drm; diff --git a/drivers/gpu/drm/msm/msm_fbdev.c b/drivers/gpu/drm/msm/msm_fbdev.c index 31e1e30cb52a..84dfbccb6912 100644 --- a/drivers/gpu/drm/msm/msm_fbdev.c +++ b/drivers/gpu/drm/msm/msm_fbdev.c @@ -155,7 +155,7 @@ struct drm_fb_helper *msm_fbdev_init(struct drm_device *dev) } /* the fw fb could be anywhere in memory */ - ret = drm_aperture_remove_framebuffers(false, dev->driver); + ret = drm_aperture_remove_framebuffers(dev->driver); if (ret) goto fini; diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c index f75c6f09dd2a..ba1baf1d640a 100644 --- a/drivers/gpu/drm/nouveau/nouveau_connector.c +++ b/drivers/gpu/drm/nouveau/nouveau_connector.c @@ -967,7 +967,7 @@ nouveau_connector_get_modes(struct drm_connector *connector) /* Determine display colour depth for everything except LVDS now, * DP requires this before mode_valid() is called. */ - if (connector->connector_type != DRM_MODE_CONNECTOR_LVDS && nv_connector->native_mode) + if (connector->connector_type != DRM_MODE_CONNECTOR_LVDS) nouveau_connector_detect_depth(connector); /* Find the native mode if this is a digital panel, if we didn't @@ -1408,8 +1408,7 @@ nouveau_connector_create(struct drm_device *dev, ret = nvif_conn_ctor(&disp->disp, nv_connector->base.name, nv_connector->index, &nv_connector->conn); if (ret) { - kfree(nv_connector); - return ERR_PTR(ret); + goto drm_conn_err; } ret = nvif_conn_event_ctor(&nv_connector->conn, "kmsHotplug", @@ -1475,4 +1474,9 @@ nouveau_connector_create(struct drm_device *dev, drm_connector_register(connector); return connector; + +drm_conn_err: + drm_connector_cleanup(connector); + kfree(nv_connector); + return ERR_PTR(ret); } diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c index 40c8ea43c42f..9aa1aee103e8 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c @@ -26,6 +26,8 @@ #include "head.h" #include "ior.h" +#include <drm/display/drm_dp.h> + #include <subdev/bios.h> #include <subdev/bios/init.h> #include <subdev/gpio.h> @@ -513,6 +515,50 @@ nvkm_dp_train(struct nvkm_outp *outp, u32 dataKBps) return ret; } +/* XXX: This is a big fat hack, and this is just drm_dp_read_dpcd_caps() + * converted to work inside nvkm. This is a temporary holdover until we start + * passing the drm_dp_aux device through NVKM + */ +static int +nvkm_dp_read_dpcd_caps(struct nvkm_outp *outp) +{ + struct nvkm_i2c_aux *aux = outp->dp.aux; + u8 dpcd_ext[DP_RECEIVER_CAP_SIZE]; + int ret; + + ret = nvkm_rdaux(aux, DPCD_RC00_DPCD_REV, outp->dp.dpcd, DP_RECEIVER_CAP_SIZE); + if (ret < 0) + return ret; + + /* + * Prior to DP1.3 the bit represented by + * DP_EXTENDED_RECEIVER_CAP_FIELD_PRESENT was reserved. + * If it is set DP_DPCD_REV at 0000h could be at a value less than + * the true capability of the panel. The only way to check is to + * then compare 0000h and 2200h. + */ + if (!(outp->dp.dpcd[DP_TRAINING_AUX_RD_INTERVAL] & + DP_EXTENDED_RECEIVER_CAP_FIELD_PRESENT)) + return 0; + + ret = nvkm_rdaux(aux, DP_DP13_DPCD_REV, dpcd_ext, sizeof(dpcd_ext)); + if (ret < 0) + return ret; + + if (outp->dp.dpcd[DP_DPCD_REV] > dpcd_ext[DP_DPCD_REV]) { + OUTP_DBG(outp, "Extended DPCD rev less than base DPCD rev (%d > %d)\n", + outp->dp.dpcd[DP_DPCD_REV], dpcd_ext[DP_DPCD_REV]); + return 0; + } + + if (!memcmp(outp->dp.dpcd, dpcd_ext, sizeof(dpcd_ext))) + return 0; + + memcpy(outp->dp.dpcd, dpcd_ext, sizeof(dpcd_ext)); + + return 0; +} + void nvkm_dp_disable(struct nvkm_outp *outp, struct nvkm_ior *ior) { @@ -689,7 +735,7 @@ nvkm_dp_enable(struct nvkm_outp *outp, bool auxpwr) memset(outp->dp.lttpr, 0x00, sizeof(outp->dp.lttpr)); } - if (!nvkm_rdaux(aux, DPCD_RC00_DPCD_REV, outp->dp.dpcd, sizeof(outp->dp.dpcd))) { + if (!nvkm_dp_read_dpcd_caps(outp)) { const u8 rates[] = { 0x1e, 0x14, 0x0a, 0x06, 0 }; const u8 *rate; int rate_max; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.h b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.h index 00dbeda7e346..de161e7a04aa 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.h +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.h @@ -117,6 +117,7 @@ void gk104_grctx_generate_r418800(struct gf100_gr *); extern const struct gf100_grctx_func gk110_grctx; void gk110_grctx_generate_r419eb0(struct gf100_gr *); +void gk110_grctx_generate_r419f78(struct gf100_gr *); extern const struct gf100_grctx_func gk110b_grctx; extern const struct gf100_grctx_func gk208_grctx; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk104.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk104.c index 94233d0119df..52a234b1ef01 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk104.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk104.c @@ -906,7 +906,9 @@ static void gk104_grctx_generate_r419f78(struct gf100_gr *gr) { struct nvkm_device *device = gr->base.engine.subdev.device; - nvkm_mask(device, 0x419f78, 0x00000001, 0x00000000); + + /* bit 3 set disables loads in fp helper invocations, we need it enabled */ + nvkm_mask(device, 0x419f78, 0x00000009, 0x00000000); } void diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk110.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk110.c index 4391458e1fb2..3acdd9eeb74a 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk110.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk110.c @@ -820,6 +820,15 @@ gk110_grctx_generate_r419eb0(struct gf100_gr *gr) nvkm_mask(device, 0x419eb0, 0x00001000, 0x00001000); } +void +gk110_grctx_generate_r419f78(struct gf100_gr *gr) +{ + struct nvkm_device *device = gr->base.engine.subdev.device; + + /* bit 3 set disables loads in fp helper invocations, we need it enabled */ + nvkm_mask(device, 0x419f78, 0x00000008, 0x00000000); +} + const struct gf100_grctx_func gk110_grctx = { .main = gf100_grctx_generate_main, @@ -854,4 +863,5 @@ gk110_grctx = { .gpc_tpc_nr = gk104_grctx_generate_gpc_tpc_nr, .r418800 = gk104_grctx_generate_r418800, .r419eb0 = gk110_grctx_generate_r419eb0, + .r419f78 = gk110_grctx_generate_r419f78, }; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk110b.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk110b.c index 7b9a34f9ec3c..5597e87624ac 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk110b.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk110b.c @@ -103,4 +103,5 @@ gk110b_grctx = { .gpc_tpc_nr = gk104_grctx_generate_gpc_tpc_nr, .r418800 = gk104_grctx_generate_r418800, .r419eb0 = gk110_grctx_generate_r419eb0, + .r419f78 = gk110_grctx_generate_r419f78, }; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk208.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk208.c index c78d07a8bb7d..612656496541 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk208.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk208.c @@ -568,4 +568,5 @@ gk208_grctx = { .dist_skip_table = gf117_grctx_generate_dist_skip_table, .gpc_tpc_nr = gk104_grctx_generate_gpc_tpc_nr, .r418800 = gk104_grctx_generate_r418800, + .r419f78 = gk110_grctx_generate_r419f78, }; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm107.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm107.c index beac66eb2a80..9906974ac3f0 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm107.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm107.c @@ -988,4 +988,5 @@ gm107_grctx = { .r406500 = gm107_grctx_generate_r406500, .gpc_tpc_nr = gk104_grctx_generate_gpc_tpc_nr, .r419e00 = gm107_grctx_generate_r419e00, + .r419f78 = gk110_grctx_generate_r419f78, }; diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c index f851aaf2c591..5e067ba7e5fb 100644 --- a/drivers/gpu/drm/panel/panel-simple.c +++ b/drivers/gpu/drm/panel/panel-simple.c @@ -969,21 +969,21 @@ static const struct panel_desc auo_g104sn02 = { .connector_type = DRM_MODE_CONNECTOR_LVDS, }; -static const struct drm_display_mode auo_g121ean01_mode = { - .clock = 66700, - .hdisplay = 1280, - .hsync_start = 1280 + 58, - .hsync_end = 1280 + 58 + 8, - .htotal = 1280 + 58 + 8 + 70, - .vdisplay = 800, - .vsync_start = 800 + 6, - .vsync_end = 800 + 6 + 4, - .vtotal = 800 + 6 + 4 + 10, +static const struct display_timing auo_g121ean01_timing = { + .pixelclock = { 60000000, 74400000, 90000000 }, + .hactive = { 1280, 1280, 1280 }, + .hfront_porch = { 20, 50, 100 }, + .hback_porch = { 20, 50, 100 }, + .hsync_len = { 30, 100, 200 }, + .vactive = { 800, 800, 800 }, + .vfront_porch = { 2, 10, 25 }, + .vback_porch = { 2, 10, 25 }, + .vsync_len = { 4, 18, 50 }, }; static const struct panel_desc auo_g121ean01 = { - .modes = &auo_g121ean01_mode, - .num_modes = 1, + .timings = &auo_g121ean01_timing, + .num_timings = 1, .bpc = 8, .size = { .width = 261, diff --git a/drivers/gpu/drm/qxl/qxl_drv.h b/drivers/gpu/drm/qxl/qxl_drv.h index 76f060810f63..da3e19bd14d3 100644 --- a/drivers/gpu/drm/qxl/qxl_drv.h +++ b/drivers/gpu/drm/qxl/qxl_drv.h @@ -311,7 +311,7 @@ int qxl_gem_object_create_with_handle(struct qxl_device *qdev, u32 domain, size_t size, struct qxl_surface *surf, - struct qxl_bo **qobj, + struct drm_gem_object **gobj, uint32_t *handle); void qxl_gem_object_free(struct drm_gem_object *gobj); int qxl_gem_object_open(struct drm_gem_object *obj, struct drm_file *file_priv); diff --git a/drivers/gpu/drm/qxl/qxl_dumb.c b/drivers/gpu/drm/qxl/qxl_dumb.c index d636ba685451..17df5c7ccf69 100644 --- a/drivers/gpu/drm/qxl/qxl_dumb.c +++ b/drivers/gpu/drm/qxl/qxl_dumb.c @@ -34,6 +34,7 @@ int qxl_mode_dumb_create(struct drm_file *file_priv, { struct qxl_device *qdev = to_qxl(dev); struct qxl_bo *qobj; + struct drm_gem_object *gobj; uint32_t handle; int r; struct qxl_surface surf; @@ -62,11 +63,13 @@ int qxl_mode_dumb_create(struct drm_file *file_priv, r = qxl_gem_object_create_with_handle(qdev, file_priv, QXL_GEM_DOMAIN_CPU, - args->size, &surf, &qobj, + args->size, &surf, &gobj, &handle); if (r) return r; + qobj = gem_to_qxl_bo(gobj); qobj->is_dumb = true; + drm_gem_object_put(gobj); args->pitch = pitch; args->handle = handle; return 0; diff --git a/drivers/gpu/drm/qxl/qxl_gem.c b/drivers/gpu/drm/qxl/qxl_gem.c index a08da0bd9098..fc5e3763c359 100644 --- a/drivers/gpu/drm/qxl/qxl_gem.c +++ b/drivers/gpu/drm/qxl/qxl_gem.c @@ -72,32 +72,41 @@ int qxl_gem_object_create(struct qxl_device *qdev, int size, return 0; } +/* + * If the caller passed a valid gobj pointer, it is responsible to call + * drm_gem_object_put() when it no longer needs to acess the object. + * + * If gobj is NULL, it is handled internally. + */ int qxl_gem_object_create_with_handle(struct qxl_device *qdev, struct drm_file *file_priv, u32 domain, size_t size, struct qxl_surface *surf, - struct qxl_bo **qobj, + struct drm_gem_object **gobj, uint32_t *handle) { - struct drm_gem_object *gobj; int r; + struct drm_gem_object *local_gobj; - BUG_ON(!qobj); BUG_ON(!handle); r = qxl_gem_object_create(qdev, size, 0, domain, false, false, surf, - &gobj); + &local_gobj); if (r) return -ENOMEM; - r = drm_gem_handle_create(file_priv, gobj, handle); + r = drm_gem_handle_create(file_priv, local_gobj, handle); if (r) return r; - /* drop reference from allocate - handle holds it now */ - *qobj = gem_to_qxl_bo(gobj); - drm_gem_object_put(gobj); + + if (gobj) + *gobj = local_gobj; + else + /* drop reference from allocate - handle holds it now */ + drm_gem_object_put(local_gobj); + return 0; } diff --git a/drivers/gpu/drm/qxl/qxl_ioctl.c b/drivers/gpu/drm/qxl/qxl_ioctl.c index 30f58b21372a..dd0f834d881c 100644 --- a/drivers/gpu/drm/qxl/qxl_ioctl.c +++ b/drivers/gpu/drm/qxl/qxl_ioctl.c @@ -38,7 +38,6 @@ int qxl_alloc_ioctl(struct drm_device *dev, void *data, struct drm_file *file_pr struct qxl_device *qdev = to_qxl(dev); struct drm_qxl_alloc *qxl_alloc = data; int ret; - struct qxl_bo *qobj; uint32_t handle; u32 domain = QXL_GEM_DOMAIN_VRAM; @@ -50,7 +49,7 @@ int qxl_alloc_ioctl(struct drm_device *dev, void *data, struct drm_file *file_pr domain, qxl_alloc->size, NULL, - &qobj, &handle); + NULL, &handle); if (ret) { DRM_ERROR("%s: failed to create gem ret=%d\n", __func__, ret); @@ -386,7 +385,6 @@ int qxl_alloc_surf_ioctl(struct drm_device *dev, void *data, struct drm_file *fi { struct qxl_device *qdev = to_qxl(dev); struct drm_qxl_alloc_surf *param = data; - struct qxl_bo *qobj; int handle; int ret; int size, actual_stride; @@ -406,7 +404,7 @@ int qxl_alloc_surf_ioctl(struct drm_device *dev, void *data, struct drm_file *fi QXL_GEM_DOMAIN_SURFACE, size, &surf, - &qobj, &handle); + NULL, &handle); if (ret) { DRM_ERROR("%s: failed to create gem ret=%d\n", __func__, ret); diff --git a/drivers/gpu/drm/rcar-du/rcar_du_crtc.c b/drivers/gpu/drm/rcar-du/rcar_du_crtc.c index b7dd59fe119e..9edb5edb2bad 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_crtc.c +++ b/drivers/gpu/drm/rcar-du/rcar_du_crtc.c @@ -223,20 +223,6 @@ static void rcar_du_crtc_set_display_timing(struct rcar_du_crtc *rcrtc) * DU channels that have a display PLL can't use the internal * system clock, and have no internal clock divider. */ - - /* - * The H3 ES1.x exhibits dot clock duty cycle stability issues. - * We can work around them by configuring the DPLL to twice the - * desired frequency, coupled with a /2 post-divider. Restrict - * the workaround to H3 ES1.x as ES2.0 and all other SoCs have - * no post-divider when a display PLL is present (as shown by - * the workaround breaking HDMI output on M3-W during testing). - */ - if (rcdu->info->quirks & RCAR_DU_QUIRK_H3_ES1_PCLK_STABILITY) { - target *= 2; - div = 1; - } - extclk = clk_get_rate(rcrtc->extclock); rcar_du_dpll_divider(rcrtc, &dpll, extclk, target); @@ -245,30 +231,13 @@ static void rcar_du_crtc_set_display_timing(struct rcar_du_crtc *rcrtc) | DPLLCR_N(dpll.n) | DPLLCR_M(dpll.m) | DPLLCR_STBY; - if (rcrtc->index == 1) { + if (rcrtc->index == 1) dpllcr |= DPLLCR_PLCS1 | DPLLCR_INCS_DOTCLKIN1; - } else { - dpllcr |= DPLLCR_PLCS0_PLL + else + dpllcr |= DPLLCR_PLCS0 | DPLLCR_INCS_DOTCLKIN0; - /* - * On ES2.x we have a single mux controlled via bit 21, - * which selects between DCLKIN source (bit 21 = 0) and - * a PLL source (bit 21 = 1), where the PLL is always - * PLL1. - * - * On ES1.x we have an additional mux, controlled - * via bit 20, for choosing between PLL0 (bit 20 = 0) - * and PLL1 (bit 20 = 1). We always want to use PLL1, - * so on ES1.x, in addition to setting bit 21, we need - * to set the bit 20. - */ - - if (rcdu->info->quirks & RCAR_DU_QUIRK_H3_ES1_PLL) - dpllcr |= DPLLCR_PLCS0_H3ES1X_PLL1; - } - rcar_du_group_write(rcrtc->group, DPLLCR, dpllcr); escr = ESCR_DCLKSEL_DCLKIN | div; diff --git a/drivers/gpu/drm/rcar-du/rcar_du_drv.c b/drivers/gpu/drm/rcar-du/rcar_du_drv.c index 53c9669a3851..4b07a72206d6 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_drv.c +++ b/drivers/gpu/drm/rcar-du/rcar_du_drv.c @@ -16,7 +16,6 @@ #include <linux/platform_device.h> #include <linux/pm.h> #include <linux/slab.h> -#include <linux/sys_soc.h> #include <linux/wait.h> #include <drm/drm_atomic_helper.h> @@ -387,43 +386,6 @@ static const struct rcar_du_device_info rcar_du_r8a7795_info = { .dpll_mask = BIT(2) | BIT(1), }; -static const struct rcar_du_device_info rcar_du_r8a7795_es1_info = { - .gen = 3, - .features = RCAR_DU_FEATURE_CRTC_IRQ - | RCAR_DU_FEATURE_CRTC_CLOCK - | RCAR_DU_FEATURE_VSP1_SOURCE - | RCAR_DU_FEATURE_INTERLACED - | RCAR_DU_FEATURE_TVM_SYNC, - .quirks = RCAR_DU_QUIRK_H3_ES1_PCLK_STABILITY - | RCAR_DU_QUIRK_H3_ES1_PLL, - .channels_mask = BIT(3) | BIT(2) | BIT(1) | BIT(0), - .routes = { - /* - * R8A7795 has one RGB output, two HDMI outputs and one - * LVDS output. - */ - [RCAR_DU_OUTPUT_DPAD0] = { - .possible_crtcs = BIT(3), - .port = 0, - }, - [RCAR_DU_OUTPUT_HDMI0] = { - .possible_crtcs = BIT(1), - .port = 1, - }, - [RCAR_DU_OUTPUT_HDMI1] = { - .possible_crtcs = BIT(2), - .port = 2, - }, - [RCAR_DU_OUTPUT_LVDS0] = { - .possible_crtcs = BIT(0), - .port = 3, - }, - }, - .num_lvds = 1, - .num_rpf = 5, - .dpll_mask = BIT(2) | BIT(1), -}; - static const struct rcar_du_device_info rcar_du_r8a7796_info = { .gen = 3, .features = RCAR_DU_FEATURE_CRTC_IRQ @@ -592,11 +554,6 @@ static const struct of_device_id rcar_du_of_table[] = { MODULE_DEVICE_TABLE(of, rcar_du_of_table); -static const struct soc_device_attribute rcar_du_soc_table[] = { - { .soc_id = "r8a7795", .revision = "ES1.*", .data = &rcar_du_r8a7795_es1_info }, - { /* sentinel */ } -}; - const char *rcar_du_output_name(enum rcar_du_output output) { static const char * const names[] = { @@ -688,7 +645,6 @@ static void rcar_du_shutdown(struct platform_device *pdev) static int rcar_du_probe(struct platform_device *pdev) { - const struct soc_device_attribute *soc_attr; struct rcar_du_device *rcdu; unsigned int mask; int ret; @@ -706,10 +662,6 @@ static int rcar_du_probe(struct platform_device *pdev) rcdu->info = of_device_get_match_data(rcdu->dev); - soc_attr = soc_device_match(rcar_du_soc_table); - if (soc_attr) - rcdu->info = soc_attr->data; - platform_set_drvdata(pdev, rcdu); /* I/O resources */ diff --git a/drivers/gpu/drm/rcar-du/rcar_du_drv.h b/drivers/gpu/drm/rcar-du/rcar_du_drv.h index acc3673fefe1..5cfa2bb7ad93 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_drv.h +++ b/drivers/gpu/drm/rcar-du/rcar_du_drv.h @@ -34,8 +34,6 @@ struct rcar_du_device; #define RCAR_DU_FEATURE_NO_BLENDING BIT(5) /* PnMR.SPIM does not have ALP nor EOR bits */ #define RCAR_DU_QUIRK_ALIGN_128B BIT(0) /* Align pitches to 128 bytes */ -#define RCAR_DU_QUIRK_H3_ES1_PCLK_STABILITY BIT(1) /* H3 ES1 has pclk stability issue */ -#define RCAR_DU_QUIRK_H3_ES1_PLL BIT(2) /* H3 ES1 PLL setup differs from non-ES1 */ enum rcar_du_output { RCAR_DU_OUTPUT_DPAD0, diff --git a/drivers/gpu/drm/rcar-du/rcar_du_regs.h b/drivers/gpu/drm/rcar-du/rcar_du_regs.h index 789ae9285108..288eff12b2b1 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_regs.h +++ b/drivers/gpu/drm/rcar-du/rcar_du_regs.h @@ -283,8 +283,7 @@ #define DPLLCR 0x20044 #define DPLLCR_CODE (0x95 << 24) #define DPLLCR_PLCS1 (1 << 23) -#define DPLLCR_PLCS0_PLL (1 << 21) -#define DPLLCR_PLCS0_H3ES1X_PLL1 (1 << 20) +#define DPLLCR_PLCS0 (1 << 21) #define DPLLCR_CLKE (1 << 18) #define DPLLCR_FDPLL(n) ((n) << 12) #define DPLLCR_N(n) ((n) << 5) diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c index 6e0788d14c10..d97f2edc646b 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c @@ -140,7 +140,7 @@ static int rockchip_drm_bind(struct device *dev) int ret; /* Remove existing drivers that may own the framebuffer memory. */ - ret = drm_aperture_remove_framebuffers(false, &rockchip_drm_driver); + ret = drm_aperture_remove_framebuffers(&rockchip_drm_driver); if (ret) { DRM_DEV_ERROR(dev, "Failed to remove existing framebuffers - %d.\n", diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c index 9fea03121247..2e2e08f4359a 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c @@ -836,12 +836,12 @@ static int vop_plane_atomic_check(struct drm_plane *plane, * need align with 2 pixel. */ if (fb->format->is_yuv && ((new_plane_state->src.x1 >> 16) % 2)) { - DRM_ERROR("Invalid Source: Yuv format not support odd xpos\n"); + DRM_DEBUG_KMS("Invalid Source: Yuv format not support odd xpos\n"); return -EINVAL; } if (fb->format->is_yuv && new_plane_state->rotation & DRM_MODE_REFLECT_Y) { - DRM_ERROR("Invalid Source: Yuv format does not support this rotation\n"); + DRM_DEBUG_KMS("Invalid Source: Yuv format does not support this rotation\n"); return -EINVAL; } @@ -849,7 +849,7 @@ static int vop_plane_atomic_check(struct drm_plane *plane, struct vop *vop = to_vop(crtc); if (!vop->data->afbc) { - DRM_ERROR("vop does not support AFBC\n"); + DRM_DEBUG_KMS("vop does not support AFBC\n"); return -EINVAL; } @@ -858,15 +858,16 @@ static int vop_plane_atomic_check(struct drm_plane *plane, return ret; if (new_plane_state->src.x1 || new_plane_state->src.y1) { - DRM_ERROR("AFBC does not support offset display, xpos=%d, ypos=%d, offset=%d\n", - new_plane_state->src.x1, - new_plane_state->src.y1, fb->offsets[0]); + DRM_DEBUG_KMS("AFBC does not support offset display, " \ + "xpos=%d, ypos=%d, offset=%d\n", + new_plane_state->src.x1, new_plane_state->src.y1, + fb->offsets[0]); return -EINVAL; } if (new_plane_state->rotation && new_plane_state->rotation != DRM_MODE_ROTATE_0) { - DRM_ERROR("No rotation support in AFBC, rotation=%d\n", - new_plane_state->rotation); + DRM_DEBUG_KMS("No rotation support in AFBC, rotation=%d\n", + new_plane_state->rotation); return -EINVAL; } } diff --git a/drivers/gpu/drm/stm/drv.c b/drivers/gpu/drm/stm/drv.c index 50410bd99dfe..354349c6e085 100644 --- a/drivers/gpu/drm/stm/drv.c +++ b/drivers/gpu/drm/stm/drv.c @@ -185,7 +185,7 @@ static int stm_drm_platform_probe(struct platform_device *pdev) DRM_DEBUG("%s\n", __func__); - ret = drm_aperture_remove_framebuffers(false, &drv_driver); + ret = drm_aperture_remove_framebuffers(&drv_driver); if (ret) return ret; diff --git a/drivers/gpu/drm/stm/ltdc.c b/drivers/gpu/drm/stm/ltdc.c index 03c6becda795..b8be4c1db423 100644 --- a/drivers/gpu/drm/stm/ltdc.c +++ b/drivers/gpu/drm/stm/ltdc.c @@ -1145,7 +1145,7 @@ static void ltdc_crtc_disable_vblank(struct drm_crtc *crtc) static int ltdc_crtc_set_crc_source(struct drm_crtc *crtc, const char *source) { - struct ltdc_device *ldev = crtc_to_ltdc(crtc); + struct ltdc_device *ldev; int ret; DRM_DEBUG_DRIVER("\n"); @@ -1153,6 +1153,8 @@ static int ltdc_crtc_set_crc_source(struct drm_crtc *crtc, const char *source) if (!crtc) return -ENODEV; + ldev = crtc_to_ltdc(crtc); + if (source && strcmp(source, "auto") == 0) { ldev->crc_active = true; ret = regmap_set_bits(ldev->regmap, LTDC_GCR, GCR_CRCEN); diff --git a/drivers/gpu/drm/sun4i/sun4i_drv.c b/drivers/gpu/drm/sun4i/sun4i_drv.c index d6c741716167..4dd82d75eff5 100644 --- a/drivers/gpu/drm/sun4i/sun4i_drv.c +++ b/drivers/gpu/drm/sun4i/sun4i_drv.c @@ -98,7 +98,7 @@ static int sun4i_drv_bind(struct device *dev) goto unbind_all; /* Remove early framebuffers (ie. simplefb) */ - ret = drm_aperture_remove_framebuffers(false, &sun4i_drv_driver); + ret = drm_aperture_remove_framebuffers(&sun4i_drv_driver); if (ret) goto unbind_all; diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c index 7bd2e65c2a16..d2ff527cf6d7 100644 --- a/drivers/gpu/drm/tegra/drm.c +++ b/drivers/gpu/drm/tegra/drm.c @@ -1252,7 +1252,7 @@ static int host1x_drm_probe(struct host1x_device *dev) drm_mode_config_reset(drm); - err = drm_aperture_remove_framebuffers(false, &tegra_drm_driver); + err = drm_aperture_remove_framebuffers(&tegra_drm_driver); if (err < 0) goto hub; diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 2092d11a8785..3e9fa63a1966 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -549,7 +549,8 @@ static bool ttm_bo_evict_swapout_allowable(struct ttm_buffer_object *bo, if (bo->pin_count) { *locked = false; - *busy = false; + if (busy) + *busy = false; return false; } diff --git a/drivers/gpu/drm/vc4/vc4_drv.c b/drivers/gpu/drm/vc4/vc4_drv.c index 5990d8f8c363..8e569d8419b0 100644 --- a/drivers/gpu/drm/vc4/vc4_drv.c +++ b/drivers/gpu/drm/vc4/vc4_drv.c @@ -351,7 +351,7 @@ static int vc4_drm_bind(struct device *dev) return -EPROBE_DEFER; } - ret = drm_aperture_remove_framebuffers(false, driver); + ret = drm_aperture_remove_framebuffers(driver); if (ret) return ret; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index 5acbf5849b27..0a117da946e9 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -1658,4 +1658,16 @@ static inline bool vmw_has_fences(struct vmw_private *vmw) return (vmw_fifo_caps(vmw) & SVGA_FIFO_CAP_FENCE) != 0; } +static inline bool vmw_shadertype_is_valid(enum vmw_sm_type shader_model, + u32 shader_type) +{ + SVGA3dShaderType max_allowed = SVGA3D_SHADERTYPE_PREDX_MAX; + + if (shader_model >= VMW_SM_5) + max_allowed = SVGA3D_SHADERTYPE_MAX; + else if (shader_model >= VMW_SM_4) + max_allowed = SVGA3D_SHADERTYPE_DX10_MAX; + return shader_type >= SVGA3D_SHADERTYPE_MIN && shader_type < max_allowed; +} + #endif diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index c0686283ffd1..3611ea32efc3 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -1985,7 +1985,7 @@ static int vmw_cmd_set_shader(struct vmw_private *dev_priv, cmd = container_of(header, typeof(*cmd), header); - if (cmd->body.type >= SVGA3D_SHADERTYPE_PREDX_MAX) { + if (!vmw_shadertype_is_valid(VMW_SM_LEGACY, cmd->body.type)) { VMW_DEBUG_USER("Illegal shader type %u.\n", (unsigned int) cmd->body.type); return -EINVAL; @@ -2108,8 +2108,6 @@ vmw_cmd_dx_set_single_constant_buffer(struct vmw_private *dev_priv, SVGA3dCmdHeader *header) { VMW_DECLARE_CMD_VAR(*cmd, SVGA3dCmdDXSetSingleConstantBuffer); - SVGA3dShaderType max_shader_num = has_sm5_context(dev_priv) ? - SVGA3D_NUM_SHADERTYPE : SVGA3D_NUM_SHADERTYPE_DX10; struct vmw_resource *res = NULL; struct vmw_ctx_validation_info *ctx_node = VMW_GET_CTX_NODE(sw_context); @@ -2126,6 +2124,14 @@ vmw_cmd_dx_set_single_constant_buffer(struct vmw_private *dev_priv, if (unlikely(ret != 0)) return ret; + if (!vmw_shadertype_is_valid(dev_priv->sm_type, cmd->body.type) || + cmd->body.slot >= SVGA3D_DX_MAX_CONSTBUFFERS) { + VMW_DEBUG_USER("Illegal const buffer shader %u slot %u.\n", + (unsigned int) cmd->body.type, + (unsigned int) cmd->body.slot); + return -EINVAL; + } + binding.bi.ctx = ctx_node->ctx; binding.bi.res = res; binding.bi.bt = vmw_ctx_binding_cb; @@ -2134,14 +2140,6 @@ vmw_cmd_dx_set_single_constant_buffer(struct vmw_private *dev_priv, binding.size = cmd->body.sizeInBytes; binding.slot = cmd->body.slot; - if (binding.shader_slot >= max_shader_num || - binding.slot >= SVGA3D_DX_MAX_CONSTBUFFERS) { - VMW_DEBUG_USER("Illegal const buffer shader %u slot %u.\n", - (unsigned int) cmd->body.type, - (unsigned int) binding.slot); - return -EINVAL; - } - vmw_binding_add(ctx_node->staged, &binding.bi, binding.shader_slot, binding.slot); @@ -2200,15 +2198,13 @@ static int vmw_cmd_dx_set_shader_res(struct vmw_private *dev_priv, { VMW_DECLARE_CMD_VAR(*cmd, SVGA3dCmdDXSetShaderResources) = container_of(header, typeof(*cmd), header); - SVGA3dShaderType max_allowed = has_sm5_context(dev_priv) ? - SVGA3D_SHADERTYPE_MAX : SVGA3D_SHADERTYPE_DX10_MAX; u32 num_sr_view = (cmd->header.size - sizeof(cmd->body)) / sizeof(SVGA3dShaderResourceViewId); if ((u64) cmd->body.startView + (u64) num_sr_view > (u64) SVGA3D_DX_MAX_SRVIEWS || - cmd->body.type >= max_allowed) { + !vmw_shadertype_is_valid(dev_priv->sm_type, cmd->body.type)) { VMW_DEBUG_USER("Invalid shader binding.\n"); return -EINVAL; } @@ -2232,8 +2228,6 @@ static int vmw_cmd_dx_set_shader(struct vmw_private *dev_priv, SVGA3dCmdHeader *header) { VMW_DECLARE_CMD_VAR(*cmd, SVGA3dCmdDXSetShader); - SVGA3dShaderType max_allowed = has_sm5_context(dev_priv) ? - SVGA3D_SHADERTYPE_MAX : SVGA3D_SHADERTYPE_DX10_MAX; struct vmw_resource *res = NULL; struct vmw_ctx_validation_info *ctx_node = VMW_GET_CTX_NODE(sw_context); struct vmw_ctx_bindinfo_shader binding; @@ -2244,8 +2238,7 @@ static int vmw_cmd_dx_set_shader(struct vmw_private *dev_priv, cmd = container_of(header, typeof(*cmd), header); - if (cmd->body.type >= max_allowed || - cmd->body.type < SVGA3D_SHADERTYPE_MIN) { + if (!vmw_shadertype_is_valid(dev_priv->sm_type, cmd->body.type)) { VMW_DEBUG_USER("Illegal shader type %u.\n", (unsigned int) cmd->body.type); return -EINVAL; diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c index 0b4204b9a253..97eefb77f601 100644 --- a/drivers/hid/hid-logitech-hidpp.c +++ b/drivers/hid/hid-logitech-hidpp.c @@ -4403,6 +4403,8 @@ static const struct hid_device_id hidpp_devices[] = { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC086) }, { /* Logitech G903 Hero Gaming Mouse over USB */ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC091) }, + { /* Logitech G915 TKL Keyboard over USB */ + HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC343) }, { /* Logitech G920 Wheel over USB */ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_G920_WHEEL), .driver_data = HIDPP_QUIRK_CLASS_G920 | HIDPP_QUIRK_FORCE_OUTPUT_REPORTS}, @@ -4418,6 +4420,8 @@ static const struct hid_device_id hidpp_devices[] = { { /* MX5500 keyboard over Bluetooth */ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb30b), .driver_data = HIDPP_QUIRK_HIDPP_CONSUMER_VENDOR_KEYS }, + { /* Logitech G915 TKL keyboard over Bluetooth */ + HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb35f) }, { /* M-RCQ142 V470 Cordless Laser Mouse over Bluetooth */ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb008) }, { /* MX Master mouse over Bluetooth */ diff --git a/drivers/hid/intel-ish-hid/ipc/hw-ish.h b/drivers/hid/intel-ish-hid/ipc/hw-ish.h index fc108f19a64c..e99f3a3c65e1 100644 --- a/drivers/hid/intel-ish-hid/ipc/hw-ish.h +++ b/drivers/hid/intel-ish-hid/ipc/hw-ish.h @@ -33,6 +33,7 @@ #define ADL_N_DEVICE_ID 0x54FC #define RPL_S_DEVICE_ID 0x7A78 #define MTL_P_DEVICE_ID 0x7E45 +#define ARL_H_DEVICE_ID 0x7745 #define REVISION_ID_CHT_A0 0x6 #define REVISION_ID_CHT_Ax_SI 0x0 diff --git a/drivers/hid/intel-ish-hid/ipc/pci-ish.c b/drivers/hid/intel-ish-hid/ipc/pci-ish.c index 7120b30ac51d..55cb25038e63 100644 --- a/drivers/hid/intel-ish-hid/ipc/pci-ish.c +++ b/drivers/hid/intel-ish-hid/ipc/pci-ish.c @@ -44,6 +44,7 @@ static const struct pci_device_id ish_pci_tbl[] = { {PCI_DEVICE(PCI_VENDOR_ID_INTEL, ADL_N_DEVICE_ID)}, {PCI_DEVICE(PCI_VENDOR_ID_INTEL, RPL_S_DEVICE_ID)}, {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MTL_P_DEVICE_ID)}, + {PCI_DEVICE(PCI_VENDOR_ID_INTEL, ARL_H_DEVICE_ID)}, {0, } }; MODULE_DEVICE_TABLE(pci, ish_pci_tbl); diff --git a/drivers/hid/wacom.h b/drivers/hid/wacom.h index 4da50e19808e..166a76c9bcad 100644 --- a/drivers/hid/wacom.h +++ b/drivers/hid/wacom.h @@ -150,6 +150,7 @@ struct wacom_remote { struct input_dev *input; bool registered; struct wacom_battery battery; + ktime_t active_time; } remotes[WACOM_MAX_REMOTES]; }; diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c index aff4a21a46b6..af163e8dfec0 100644 --- a/drivers/hid/wacom_sys.c +++ b/drivers/hid/wacom_sys.c @@ -2527,6 +2527,18 @@ fail: return; } +static void wacom_remote_destroy_battery(struct wacom *wacom, int index) +{ + struct wacom_remote *remote = wacom->remote; + + if (remote->remotes[index].battery.battery) { + devres_release_group(&wacom->hdev->dev, + &remote->remotes[index].battery.bat_desc); + remote->remotes[index].battery.battery = NULL; + remote->remotes[index].active_time = 0; + } +} + static void wacom_remote_destroy_one(struct wacom *wacom, unsigned int index) { struct wacom_remote *remote = wacom->remote; @@ -2541,9 +2553,7 @@ static void wacom_remote_destroy_one(struct wacom *wacom, unsigned int index) remote->remotes[i].registered = false; spin_unlock_irqrestore(&remote->remote_lock, flags); - if (remote->remotes[i].battery.battery) - devres_release_group(&wacom->hdev->dev, - &remote->remotes[i].battery.bat_desc); + wacom_remote_destroy_battery(wacom, i); if (remote->remotes[i].group.name) devres_release_group(&wacom->hdev->dev, @@ -2551,7 +2561,6 @@ static void wacom_remote_destroy_one(struct wacom *wacom, unsigned int index) remote->remotes[i].serial = 0; remote->remotes[i].group.name = NULL; - remote->remotes[i].battery.battery = NULL; wacom->led.groups[i].select = WACOM_STATUS_UNKNOWN; } } @@ -2636,6 +2645,9 @@ static int wacom_remote_attach_battery(struct wacom *wacom, int index) if (remote->remotes[index].battery.battery) return 0; + if (!remote->remotes[index].active_time) + return 0; + if (wacom->led.groups[index].select == WACOM_STATUS_UNKNOWN) return 0; @@ -2651,6 +2663,7 @@ static void wacom_remote_work(struct work_struct *work) { struct wacom *wacom = container_of(work, struct wacom, remote_work); struct wacom_remote *remote = wacom->remote; + ktime_t kt = ktime_get(); struct wacom_remote_data data; unsigned long flags; unsigned int count; @@ -2677,6 +2690,10 @@ static void wacom_remote_work(struct work_struct *work) serial = data.remote[i].serial; if (data.remote[i].connected) { + if (kt - remote->remotes[i].active_time > WACOM_REMOTE_BATTERY_TIMEOUT + && remote->remotes[i].active_time != 0) + wacom_remote_destroy_battery(wacom, i); + if (remote->remotes[i].serial == serial) { wacom_remote_attach_battery(wacom, i); continue; diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index 15cd0cabee2a..c1270db12178 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -1129,6 +1129,7 @@ static int wacom_remote_irq(struct wacom_wac *wacom_wac, size_t len) if (index < 0 || !remote->remotes[index].registered) goto out; + remote->remotes[i].active_time = ktime_get(); input = remote->remotes[index].input; input_report_key(input, BTN_0, (data[9] & 0x01)); diff --git a/drivers/hid/wacom_wac.h b/drivers/hid/wacom_wac.h index ee21bb260f22..2e7cc5e7a0cb 100644 --- a/drivers/hid/wacom_wac.h +++ b/drivers/hid/wacom_wac.h @@ -13,6 +13,7 @@ #define WACOM_NAME_MAX 64 #define WACOM_MAX_REMOTES 5 #define WACOM_STATUS_UNKNOWN 255 +#define WACOM_REMOTE_BATTERY_TIMEOUT 21000000000ll /* packet length for individual models */ #define WACOM_PKGLEN_BBFUN 9 diff --git a/drivers/hwmon/aquacomputer_d5next.c b/drivers/hwmon/aquacomputer_d5next.c index c51a2678f0eb..8c7796d3fdd2 100644 --- a/drivers/hwmon/aquacomputer_d5next.c +++ b/drivers/hwmon/aquacomputer_d5next.c @@ -12,9 +12,11 @@ #include <linux/crc16.h> #include <linux/debugfs.h> +#include <linux/delay.h> #include <linux/hid.h> #include <linux/hwmon.h> #include <linux/jiffies.h> +#include <linux/ktime.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/seq_file.h> @@ -49,6 +51,8 @@ static const char *const aqc_device_names[] = { #define CTRL_REPORT_ID 0x03 +#define CTRL_REPORT_DELAY 200 /* ms */ + /* The HID report that the official software always sends * after writing values, currently same for all devices */ @@ -269,6 +273,9 @@ struct aqc_data { enum kinds kind; const char *name; + ktime_t last_ctrl_report_op; + int ctrl_report_delay; /* Delay between two ctrl report operations, in ms */ + int buffer_size; u8 *buffer; int checksum_start; @@ -325,17 +332,35 @@ static int aqc_pwm_to_percent(long val) return DIV_ROUND_CLOSEST(val * 100 * 100, 255); } +static void aqc_delay_ctrl_report(struct aqc_data *priv) +{ + /* + * If previous read or write is too close to this one, delay the current operation + * to give the device enough time to process the previous one. + */ + if (priv->ctrl_report_delay) { + s64 delta = ktime_ms_delta(ktime_get(), priv->last_ctrl_report_op); + + if (delta < priv->ctrl_report_delay) + msleep(priv->ctrl_report_delay - delta); + } +} + /* Expects the mutex to be locked */ static int aqc_get_ctrl_data(struct aqc_data *priv) { int ret; + aqc_delay_ctrl_report(priv); + memset(priv->buffer, 0x00, priv->buffer_size); ret = hid_hw_raw_request(priv->hdev, CTRL_REPORT_ID, priv->buffer, priv->buffer_size, HID_FEATURE_REPORT, HID_REQ_GET_REPORT); if (ret < 0) ret = -ENODATA; + priv->last_ctrl_report_op = ktime_get(); + return ret; } @@ -345,6 +370,8 @@ static int aqc_send_ctrl_data(struct aqc_data *priv) int ret; u16 checksum; + aqc_delay_ctrl_report(priv); + /* Init and xorout value for CRC-16/USB is 0xffff */ checksum = crc16(0xffff, priv->buffer + priv->checksum_start, priv->checksum_length); checksum ^= 0xffff; @@ -356,12 +383,16 @@ static int aqc_send_ctrl_data(struct aqc_data *priv) ret = hid_hw_raw_request(priv->hdev, CTRL_REPORT_ID, priv->buffer, priv->buffer_size, HID_FEATURE_REPORT, HID_REQ_SET_REPORT); if (ret < 0) - return ret; + goto record_access_and_ret; /* The official software sends this report after every change, so do it here as well */ ret = hid_hw_raw_request(priv->hdev, SECONDARY_CTRL_REPORT_ID, secondary_ctrl_report, SECONDARY_CTRL_REPORT_SIZE, HID_FEATURE_REPORT, HID_REQ_SET_REPORT); + +record_access_and_ret: + priv->last_ctrl_report_op = ktime_get(); + return ret; } @@ -853,6 +884,7 @@ static int aqc_probe(struct hid_device *hdev, const struct hid_device_id *id) priv->virtual_temp_sensor_start_offset = D5NEXT_VIRTUAL_SENSORS_START; priv->power_cycle_count_offset = D5NEXT_POWER_CYCLES; priv->buffer_size = D5NEXT_CTRL_REPORT_SIZE; + priv->ctrl_report_delay = CTRL_REPORT_DELAY; priv->temp_label = label_d5next_temp; priv->virtual_temp_label = label_virtual_temp_sensors; @@ -893,6 +925,7 @@ static int aqc_probe(struct hid_device *hdev, const struct hid_device_id *id) priv->virtual_temp_sensor_start_offset = OCTO_VIRTUAL_SENSORS_START; priv->power_cycle_count_offset = OCTO_POWER_CYCLES; priv->buffer_size = OCTO_CTRL_REPORT_SIZE; + priv->ctrl_report_delay = CTRL_REPORT_DELAY; priv->temp_label = label_temp_sensors; priv->virtual_temp_label = label_virtual_temp_sensors; @@ -913,6 +946,7 @@ static int aqc_probe(struct hid_device *hdev, const struct hid_device_id *id) priv->virtual_temp_sensor_start_offset = QUADRO_VIRTUAL_SENSORS_START; priv->power_cycle_count_offset = QUADRO_POWER_CYCLES; priv->buffer_size = QUADRO_CTRL_REPORT_SIZE; + priv->ctrl_report_delay = CTRL_REPORT_DELAY; priv->flow_sensor_offset = QUADRO_FLOW_SENSOR_OFFSET; priv->temp_label = label_temp_sensors; diff --git a/drivers/hwmon/pmbus/bel-pfe.c b/drivers/hwmon/pmbus/bel-pfe.c index 4100eefb7ac3..61c195f8fd3b 100644 --- a/drivers/hwmon/pmbus/bel-pfe.c +++ b/drivers/hwmon/pmbus/bel-pfe.c @@ -17,12 +17,13 @@ enum chips {pfe1100, pfe3000}; /* - * Disable status check for pfe3000 devices, because some devices report - * communication error (invalid command) for VOUT_MODE command (0x20) - * although correct VOUT_MODE (0x16) is returned: it leads to incorrect - * exponent in linear mode. + * Disable status check because some devices report communication error + * (invalid command) for VOUT_MODE command (0x20) although the correct + * VOUT_MODE (0x16) is returned: it leads to incorrect exponent in linear + * mode. + * This affects both pfe3000 and pfe1100. */ -static struct pmbus_platform_data pfe3000_plat_data = { +static struct pmbus_platform_data pfe_plat_data = { .flags = PMBUS_SKIP_STATUS_CHECK, }; @@ -94,16 +95,15 @@ static int pfe_pmbus_probe(struct i2c_client *client) int model; model = (int)i2c_match_id(pfe_device_id, client)->driver_data; + client->dev.platform_data = &pfe_plat_data; /* * PFE3000-12-069RA devices may not stay in page 0 during device * probe which leads to probe failure (read status word failed). * So let's set the device to page 0 at the beginning. */ - if (model == pfe3000) { - client->dev.platform_data = &pfe3000_plat_data; + if (model == pfe3000) i2c_smbus_write_byte_data(client, PMBUS_PAGE, 0); - } return pmbus_do_probe(client, &pfe_driver_info[model]); } diff --git a/drivers/i2c/busses/i2c-bcm-iproc.c b/drivers/i2c/busses/i2c-bcm-iproc.c index 85d8a6b04885..30a2a3200bed 100644 --- a/drivers/i2c/busses/i2c-bcm-iproc.c +++ b/drivers/i2c/busses/i2c-bcm-iproc.c @@ -233,13 +233,14 @@ static inline u32 iproc_i2c_rd_reg(struct bcm_iproc_i2c_dev *iproc_i2c, u32 offset) { u32 val; + unsigned long flags; if (iproc_i2c->idm_base) { - spin_lock(&iproc_i2c->idm_lock); + spin_lock_irqsave(&iproc_i2c->idm_lock, flags); writel(iproc_i2c->ape_addr_mask, iproc_i2c->idm_base + IDM_CTRL_DIRECT_OFFSET); val = readl(iproc_i2c->base + offset); - spin_unlock(&iproc_i2c->idm_lock); + spin_unlock_irqrestore(&iproc_i2c->idm_lock, flags); } else { val = readl(iproc_i2c->base + offset); } @@ -250,12 +251,14 @@ static inline u32 iproc_i2c_rd_reg(struct bcm_iproc_i2c_dev *iproc_i2c, static inline void iproc_i2c_wr_reg(struct bcm_iproc_i2c_dev *iproc_i2c, u32 offset, u32 val) { + unsigned long flags; + if (iproc_i2c->idm_base) { - spin_lock(&iproc_i2c->idm_lock); + spin_lock_irqsave(&iproc_i2c->idm_lock, flags); writel(iproc_i2c->ape_addr_mask, iproc_i2c->idm_base + IDM_CTRL_DIRECT_OFFSET); writel(val, iproc_i2c->base + offset); - spin_unlock(&iproc_i2c->idm_lock); + spin_unlock_irqrestore(&iproc_i2c->idm_lock, flags); } else { writel(val, iproc_i2c->base + offset); } diff --git a/drivers/i2c/busses/i2c-designware-master.c b/drivers/i2c/busses/i2c-designware-master.c index dc3c5a15a95b..004ccb2d9f36 100644 --- a/drivers/i2c/busses/i2c-designware-master.c +++ b/drivers/i2c/busses/i2c-designware-master.c @@ -525,9 +525,21 @@ i2c_dw_read(struct dw_i2c_dev *dev) u32 flags = msgs[dev->msg_read_idx].flags; regmap_read(dev->map, DW_IC_DATA_CMD, &tmp); + tmp &= DW_IC_DATA_CMD_DAT; /* Ensure length byte is a valid value */ - if (flags & I2C_M_RECV_LEN && - (tmp & DW_IC_DATA_CMD_DAT) <= I2C_SMBUS_BLOCK_MAX && tmp > 0) { + if (flags & I2C_M_RECV_LEN) { + /* + * if IC_EMPTYFIFO_HOLD_MASTER_EN is set, which cannot be + * detected from the registers, the controller can be + * disabled if the STOP bit is set. But it is only set + * after receiving block data response length in + * I2C_FUNC_SMBUS_BLOCK_DATA case. That needs to read + * another byte with STOP bit set when the block data + * response length is invalid to complete the transaction. + */ + if (!tmp || tmp > I2C_SMBUS_BLOCK_MAX) + tmp = 1; + len = i2c_dw_recv_len(dev, tmp); } *buf++ = tmp; diff --git a/drivers/i2c/busses/i2c-hisi.c b/drivers/i2c/busses/i2c-hisi.c index 8a61bee745a1..14ec9ee8f6f3 100644 --- a/drivers/i2c/busses/i2c-hisi.c +++ b/drivers/i2c/busses/i2c-hisi.c @@ -328,6 +328,14 @@ static irqreturn_t hisi_i2c_irq(int irq, void *context) struct hisi_i2c_controller *ctlr = context; u32 int_stat; + /* + * Don't handle the interrupt if cltr->completion is NULL. We may + * reach here because the interrupt is spurious or the transfer is + * started by another port (e.g. firmware) rather than us. + */ + if (!ctlr->completion) + return IRQ_NONE; + int_stat = readl(ctlr->iobase + HISI_I2C_INT_MSTAT); hisi_i2c_clear_int(ctlr, int_stat); if (!(int_stat & HISI_I2C_INT_ALL)) diff --git a/drivers/i2c/busses/i2c-tegra.c b/drivers/i2c/busses/i2c-tegra.c index 2bc40f957e50..aa469b33ee2e 100644 --- a/drivers/i2c/busses/i2c-tegra.c +++ b/drivers/i2c/busses/i2c-tegra.c @@ -449,7 +449,7 @@ static int tegra_i2c_init_dma(struct tegra_i2c_dev *i2c_dev) if (i2c_dev->is_vi) return 0; - if (!i2c_dev->hw->has_apb_dma) { + if (i2c_dev->hw->has_apb_dma) { if (!IS_ENABLED(CONFIG_TEGRA20_APB_DMA)) { dev_dbg(i2c_dev->dev, "APB DMA support not enabled\n"); return 0; diff --git a/drivers/iio/adc/ad7192.c b/drivers/iio/adc/ad7192.c index 8720ac43a4a4..80eff7090f14 100644 --- a/drivers/iio/adc/ad7192.c +++ b/drivers/iio/adc/ad7192.c @@ -62,7 +62,6 @@ #define AD7192_MODE_STA_MASK BIT(20) /* Status Register transmission Mask */ #define AD7192_MODE_CLKSRC(x) (((x) & 0x3) << 18) /* Clock Source Select */ #define AD7192_MODE_SINC3 BIT(15) /* SINC3 Filter Select */ -#define AD7192_MODE_ACX BIT(14) /* AC excitation enable(AD7195 only)*/ #define AD7192_MODE_ENPAR BIT(13) /* Parity Enable */ #define AD7192_MODE_CLKDIV BIT(12) /* Clock divide by 2 (AD7190/2 only)*/ #define AD7192_MODE_SCYCLE BIT(11) /* Single cycle conversion */ @@ -91,6 +90,7 @@ /* Configuration Register Bit Designations (AD7192_REG_CONF) */ #define AD7192_CONF_CHOP BIT(23) /* CHOP enable */ +#define AD7192_CONF_ACX BIT(22) /* AC excitation enable(AD7195 only) */ #define AD7192_CONF_REFSEL BIT(20) /* REFIN1/REFIN2 Reference Select */ #define AD7192_CONF_CHAN(x) ((x) << 8) /* Channel select */ #define AD7192_CONF_CHAN_MASK (0x7FF << 8) /* Channel select mask */ @@ -473,7 +473,7 @@ static ssize_t ad7192_show_ac_excitation(struct device *dev, struct iio_dev *indio_dev = dev_to_iio_dev(dev); struct ad7192_state *st = iio_priv(indio_dev); - return sysfs_emit(buf, "%d\n", !!(st->mode & AD7192_MODE_ACX)); + return sysfs_emit(buf, "%d\n", !!(st->conf & AD7192_CONF_ACX)); } static ssize_t ad7192_show_bridge_switch(struct device *dev, @@ -514,13 +514,13 @@ static ssize_t ad7192_set(struct device *dev, ad_sd_write_reg(&st->sd, AD7192_REG_GPOCON, 1, st->gpocon); break; - case AD7192_REG_MODE: + case AD7192_REG_CONF: if (val) - st->mode |= AD7192_MODE_ACX; + st->conf |= AD7192_CONF_ACX; else - st->mode &= ~AD7192_MODE_ACX; + st->conf &= ~AD7192_CONF_ACX; - ad_sd_write_reg(&st->sd, AD7192_REG_MODE, 3, st->mode); + ad_sd_write_reg(&st->sd, AD7192_REG_CONF, 3, st->conf); break; default: ret = -EINVAL; @@ -580,12 +580,11 @@ static IIO_DEVICE_ATTR(bridge_switch_en, 0644, static IIO_DEVICE_ATTR(ac_excitation_en, 0644, ad7192_show_ac_excitation, ad7192_set, - AD7192_REG_MODE); + AD7192_REG_CONF); static struct attribute *ad7192_attributes[] = { &iio_dev_attr_filter_low_pass_3db_frequency_available.dev_attr.attr, &iio_dev_attr_bridge_switch_en.dev_attr.attr, - &iio_dev_attr_ac_excitation_en.dev_attr.attr, NULL }; @@ -596,6 +595,7 @@ static const struct attribute_group ad7192_attribute_group = { static struct attribute *ad7195_attributes[] = { &iio_dev_attr_filter_low_pass_3db_frequency_available.dev_attr.attr, &iio_dev_attr_bridge_switch_en.dev_attr.attr, + &iio_dev_attr_ac_excitation_en.dev_attr.attr, NULL }; diff --git a/drivers/iio/adc/ina2xx-adc.c b/drivers/iio/adc/ina2xx-adc.c index 910e7e965fc4..74092f3836b8 100644 --- a/drivers/iio/adc/ina2xx-adc.c +++ b/drivers/iio/adc/ina2xx-adc.c @@ -124,6 +124,7 @@ static const struct regmap_config ina2xx_regmap_config = { enum ina2xx_ids { ina219, ina226 }; struct ina2xx_config { + const char *name; u16 config_default; int calibration_value; int shunt_voltage_lsb; /* nV */ @@ -155,6 +156,7 @@ struct ina2xx_chip_info { static const struct ina2xx_config ina2xx_config[] = { [ina219] = { + .name = "ina219", .config_default = INA219_CONFIG_DEFAULT, .calibration_value = 4096, .shunt_voltage_lsb = 10000, @@ -164,6 +166,7 @@ static const struct ina2xx_config ina2xx_config[] = { .chip_id = ina219, }, [ina226] = { + .name = "ina226", .config_default = INA226_CONFIG_DEFAULT, .calibration_value = 2048, .shunt_voltage_lsb = 2500, @@ -996,7 +999,7 @@ static int ina2xx_probe(struct i2c_client *client, /* Patch the current config register with default. */ val = chip->config->config_default; - if (id->driver_data == ina226) { + if (type == ina226) { ina226_set_average(chip, INA226_DEFAULT_AVG, &val); ina226_set_int_time_vbus(chip, INA226_DEFAULT_IT, &val); ina226_set_int_time_vshunt(chip, INA226_DEFAULT_IT, &val); @@ -1015,7 +1018,7 @@ static int ina2xx_probe(struct i2c_client *client, } indio_dev->modes = INDIO_DIRECT_MODE; - if (id->driver_data == ina226) { + if (type == ina226) { indio_dev->channels = ina226_channels; indio_dev->num_channels = ARRAY_SIZE(ina226_channels); indio_dev->info = &ina226_info; @@ -1024,7 +1027,7 @@ static int ina2xx_probe(struct i2c_client *client, indio_dev->num_channels = ARRAY_SIZE(ina219_channels); indio_dev->info = &ina219_info; } - indio_dev->name = id->name; + indio_dev->name = id ? id->name : chip->config->name; ret = devm_iio_kfifo_buffer_setup(&client->dev, indio_dev, &ina2xx_setup_ops); diff --git a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c index 05a28d353e34..d98f7e4d202c 100644 --- a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c +++ b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c @@ -253,7 +253,7 @@ int cros_ec_sensors_core_init(struct platform_device *pdev, platform_set_drvdata(pdev, indio_dev); state->ec = ec->ec_dev; - state->msg = devm_kzalloc(&pdev->dev, + state->msg = devm_kzalloc(&pdev->dev, sizeof(*state->msg) + max((u16)sizeof(struct ec_params_motion_sense), state->ec->max_response), GFP_KERNEL); if (!state->msg) diff --git a/drivers/iio/frequency/admv1013.c b/drivers/iio/frequency/admv1013.c index ed8167271358..e6311213f3e8 100644 --- a/drivers/iio/frequency/admv1013.c +++ b/drivers/iio/frequency/admv1013.c @@ -344,9 +344,12 @@ static int admv1013_update_quad_filters(struct admv1013_state *st) static int admv1013_update_mixer_vgate(struct admv1013_state *st) { - unsigned int vcm, mixer_vgate; + unsigned int mixer_vgate; + int vcm; vcm = regulator_get_voltage(st->reg); + if (vcm < 0) + return vcm; if (vcm < 1800000) mixer_vgate = (2389 * vcm / 1000000 + 8100) / 100; diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c index 151ff3993354..f3f8392623a4 100644 --- a/drivers/iio/industrialio-core.c +++ b/drivers/iio/industrialio-core.c @@ -1916,7 +1916,7 @@ static const struct iio_buffer_setup_ops noop_ring_setup_ops; int __iio_device_register(struct iio_dev *indio_dev, struct module *this_mod) { struct iio_dev_opaque *iio_dev_opaque = to_iio_dev_opaque(indio_dev); - struct fwnode_handle *fwnode; + struct fwnode_handle *fwnode = NULL; int ret; if (!indio_dev->info) @@ -1927,7 +1927,8 @@ int __iio_device_register(struct iio_dev *indio_dev, struct module *this_mod) /* If the calling driver did not initialize firmware node, do it here */ if (dev_fwnode(&indio_dev->dev)) fwnode = dev_fwnode(&indio_dev->dev); - else + /* The default dummy IIO device has no parent */ + else if (indio_dev->dev.parent) fwnode = dev_fwnode(indio_dev->dev.parent); device_set_node(&indio_dev->dev, fwnode); diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c index 86d479772fbc..957634eceba8 100644 --- a/drivers/infiniband/core/umem.c +++ b/drivers/infiniband/core/umem.c @@ -85,6 +85,8 @@ unsigned long ib_umem_find_best_pgsz(struct ib_umem *umem, dma_addr_t mask; int i; + umem->iova = va = virt; + if (umem->is_odp) { unsigned int page_size = BIT(to_ib_umem_odp(umem)->page_shift); @@ -100,7 +102,6 @@ unsigned long ib_umem_find_best_pgsz(struct ib_umem *umem, */ pgsz_bitmap &= GENMASK(BITS_PER_LONG - 1, PAGE_SHIFT); - umem->iova = va = virt; /* The best result is the smallest page size that results in the minimum * number of required pages. Compute the largest page size that could * work based on VA address bits that don't change. diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c index 90b672feed83..194cac40da65 100644 --- a/drivers/infiniband/hw/hfi1/chip.c +++ b/drivers/infiniband/hw/hfi1/chip.c @@ -12307,6 +12307,7 @@ static void free_cntrs(struct hfi1_devdata *dd) if (dd->synth_stats_timer.function) del_timer_sync(&dd->synth_stats_timer); + cancel_work_sync(&dd->update_cntr_work); ppd = (struct hfi1_pportdata *)(dd + 1); for (i = 0; i < dd->num_pports; i++, ppd++) { kfree(ppd->cntrs); diff --git a/drivers/infiniband/hw/mlx5/qpc.c b/drivers/infiniband/hw/mlx5/qpc.c index 542e4c63a8de..d4e7864c56f1 100644 --- a/drivers/infiniband/hw/mlx5/qpc.c +++ b/drivers/infiniband/hw/mlx5/qpc.c @@ -297,8 +297,7 @@ int mlx5_core_destroy_qp(struct mlx5_ib_dev *dev, struct mlx5_core_qp *qp) MLX5_SET(destroy_qp_in, in, opcode, MLX5_CMD_OP_DESTROY_QP); MLX5_SET(destroy_qp_in, in, qpn, qp->qpn); MLX5_SET(destroy_qp_in, in, uid, qp->uid); - mlx5_cmd_exec_in(dev->mdev, destroy_qp, in); - return 0; + return mlx5_cmd_exec_in(dev->mdev, destroy_qp, in); } int mlx5_core_set_delay_drop(struct mlx5_ib_dev *dev, @@ -548,14 +547,14 @@ int mlx5_core_xrcd_dealloc(struct mlx5_ib_dev *dev, u32 xrcdn) return mlx5_cmd_exec_in(dev->mdev, dealloc_xrcd, in); } -static void destroy_rq_tracked(struct mlx5_ib_dev *dev, u32 rqn, u16 uid) +static int destroy_rq_tracked(struct mlx5_ib_dev *dev, u32 rqn, u16 uid) { u32 in[MLX5_ST_SZ_DW(destroy_rq_in)] = {}; MLX5_SET(destroy_rq_in, in, opcode, MLX5_CMD_OP_DESTROY_RQ); MLX5_SET(destroy_rq_in, in, rqn, rqn); MLX5_SET(destroy_rq_in, in, uid, uid); - mlx5_cmd_exec_in(dev->mdev, destroy_rq, in); + return mlx5_cmd_exec_in(dev->mdev, destroy_rq, in); } int mlx5_core_create_rq_tracked(struct mlx5_ib_dev *dev, u32 *in, int inlen, @@ -586,8 +585,7 @@ int mlx5_core_destroy_rq_tracked(struct mlx5_ib_dev *dev, struct mlx5_core_qp *rq) { destroy_resource_common(dev, rq); - destroy_rq_tracked(dev, rq->qpn, rq->uid); - return 0; + return destroy_rq_tracked(dev, rq->qpn, rq->uid); } static void destroy_sq_tracked(struct mlx5_ib_dev *dev, u32 sqn, u16 uid) diff --git a/drivers/interconnect/qcom/bcm-voter.c b/drivers/interconnect/qcom/bcm-voter.c index 8f385f9c2dd3..d5f2a6b5376b 100644 --- a/drivers/interconnect/qcom/bcm-voter.c +++ b/drivers/interconnect/qcom/bcm-voter.c @@ -83,6 +83,11 @@ static void bcm_aggregate(struct qcom_icc_bcm *bcm) temp = agg_peak[bucket] * bcm->vote_scale; bcm->vote_y[bucket] = bcm_div(temp, bcm->aux_data.unit); + + if (bcm->enable_mask && (bcm->vote_x[bucket] || bcm->vote_y[bucket])) { + bcm->vote_x[bucket] = 0; + bcm->vote_y[bucket] = bcm->enable_mask; + } } if (bcm->keepalive && bcm->vote_x[QCOM_ICC_BUCKET_AMC] == 0 && diff --git a/drivers/interconnect/qcom/icc-rpmh.h b/drivers/interconnect/qcom/icc-rpmh.h index 04391c1ba465..7843d8864d6b 100644 --- a/drivers/interconnect/qcom/icc-rpmh.h +++ b/drivers/interconnect/qcom/icc-rpmh.h @@ -81,6 +81,7 @@ struct qcom_icc_node { * @vote_x: aggregated threshold values, represents sum_bw when @type is bw bcm * @vote_y: aggregated threshold values, represents peak_bw when @type is bw bcm * @vote_scale: scaling factor for vote_x and vote_y + * @enable_mask: optional mask to send as vote instead of vote_x/vote_y * @dirty: flag used to indicate whether the bcm needs to be committed * @keepalive: flag used to indicate whether a keepalive is required * @aux_data: auxiliary data used when calculating threshold values and @@ -97,6 +98,7 @@ struct qcom_icc_bcm { u64 vote_x[QCOM_ICC_NUM_BUCKETS]; u64 vote_y[QCOM_ICC_NUM_BUCKETS]; u64 vote_scale; + u32 enable_mask; bool dirty; bool keepalive; struct bcm_db aux_data; diff --git a/drivers/interconnect/qcom/sm8450.c b/drivers/interconnect/qcom/sm8450.c index 2d7a8e7b85ec..e64c214b4020 100644 --- a/drivers/interconnect/qcom/sm8450.c +++ b/drivers/interconnect/qcom/sm8450.c @@ -1337,6 +1337,7 @@ static struct qcom_icc_node qns_mem_noc_sf_disp = { static struct qcom_icc_bcm bcm_acv = { .name = "ACV", + .enable_mask = 0x8, .num_nodes = 1, .nodes = { &ebi }, }; @@ -1349,6 +1350,7 @@ static struct qcom_icc_bcm bcm_ce0 = { static struct qcom_icc_bcm bcm_cn0 = { .name = "CN0", + .enable_mask = 0x1, .keepalive = true, .num_nodes = 55, .nodes = { &qnm_gemnoc_cnoc, &qnm_gemnoc_pcie, @@ -1383,6 +1385,7 @@ static struct qcom_icc_bcm bcm_cn0 = { static struct qcom_icc_bcm bcm_co0 = { .name = "CO0", + .enable_mask = 0x1, .num_nodes = 2, .nodes = { &qxm_nsp, &qns_nsp_gemnoc }, }; @@ -1403,6 +1406,7 @@ static struct qcom_icc_bcm bcm_mm0 = { static struct qcom_icc_bcm bcm_mm1 = { .name = "MM1", + .enable_mask = 0x1, .num_nodes = 12, .nodes = { &qnm_camnoc_hf, &qnm_camnoc_icp, &qnm_camnoc_sf, &qnm_mdp, @@ -1445,6 +1449,7 @@ static struct qcom_icc_bcm bcm_sh0 = { static struct qcom_icc_bcm bcm_sh1 = { .name = "SH1", + .enable_mask = 0x1, .num_nodes = 7, .nodes = { &alm_gpu_tcu, &alm_sys_tcu, &qnm_nsp_gemnoc, &qnm_pcie, @@ -1461,6 +1466,7 @@ static struct qcom_icc_bcm bcm_sn0 = { static struct qcom_icc_bcm bcm_sn1 = { .name = "SN1", + .enable_mask = 0x1, .num_nodes = 4, .nodes = { &qhm_gic, &qxm_pimem, &xm_gic, &qns_gemnoc_gc }, @@ -1492,6 +1498,7 @@ static struct qcom_icc_bcm bcm_sn7 = { static struct qcom_icc_bcm bcm_acv_disp = { .name = "ACV", + .enable_mask = 0x1, .num_nodes = 1, .nodes = { &ebi_disp }, }; @@ -1510,6 +1517,7 @@ static struct qcom_icc_bcm bcm_mm0_disp = { static struct qcom_icc_bcm bcm_mm1_disp = { .name = "MM1", + .enable_mask = 0x1, .num_nodes = 3, .nodes = { &qnm_mdp_disp, &qnm_rot_disp, &qns_mem_noc_sf_disp }, @@ -1523,6 +1531,7 @@ static struct qcom_icc_bcm bcm_sh0_disp = { static struct qcom_icc_bcm bcm_sh1_disp = { .name = "SH1", + .enable_mask = 0x1, .num_nodes = 1, .nodes = { &qnm_pcie_disp }, }; diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h index 5ecc17240eff..f5e9377b5521 100644 --- a/drivers/iommu/amd/amd_iommu_types.h +++ b/drivers/iommu/amd/amd_iommu_types.h @@ -172,6 +172,7 @@ #define CONTROL_GAINT_EN 29 #define CONTROL_XT_EN 50 #define CONTROL_INTCAPXT_EN 51 +#define CONTROL_IRTCACHEDIS 59 #define CONTROL_SNPAVIC_EN 61 #define CTRL_INV_TO_MASK (7 << CONTROL_INV_TIMEOUT) @@ -708,6 +709,9 @@ struct amd_iommu { /* if one, we need to send a completion wait command */ bool need_sync; + /* true if disable irte caching */ + bool irtcachedis_enabled; + /* Handle for IOMMU core code */ struct iommu_device iommu; diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index b0af8b5967e0..f6e64c985802 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -160,6 +160,7 @@ static int amd_iommu_xt_mode = IRQ_REMAP_XAPIC_MODE; static bool amd_iommu_detected; static bool amd_iommu_disabled __initdata; static bool amd_iommu_force_enable __initdata; +static bool amd_iommu_irtcachedis; static int amd_iommu_target_ivhd_type; /* Global EFR and EFR2 registers */ @@ -477,6 +478,9 @@ static void iommu_disable(struct amd_iommu *iommu) /* Disable IOMMU hardware itself */ iommu_feature_disable(iommu, CONTROL_IOMMU_EN); + + /* Clear IRTE cache disabling bit */ + iommu_feature_disable(iommu, CONTROL_IRTCACHEDIS); } /* @@ -2700,6 +2704,33 @@ static void iommu_enable_ga(struct amd_iommu *iommu) #endif } +static void iommu_disable_irtcachedis(struct amd_iommu *iommu) +{ + iommu_feature_disable(iommu, CONTROL_IRTCACHEDIS); +} + +static void iommu_enable_irtcachedis(struct amd_iommu *iommu) +{ + u64 ctrl; + + if (!amd_iommu_irtcachedis) + return; + + /* + * Note: + * The support for IRTCacheDis feature is dertermined by + * checking if the bit is writable. + */ + iommu_feature_enable(iommu, CONTROL_IRTCACHEDIS); + ctrl = readq(iommu->mmio_base + MMIO_CONTROL_OFFSET); + ctrl &= (1ULL << CONTROL_IRTCACHEDIS); + if (ctrl) + iommu->irtcachedis_enabled = true; + pr_info("iommu%d (%#06x) : IRT cache is %s\n", + iommu->index, iommu->devid, + iommu->irtcachedis_enabled ? "disabled" : "enabled"); +} + static void early_enable_iommu(struct amd_iommu *iommu) { iommu_disable(iommu); @@ -2710,6 +2741,7 @@ static void early_enable_iommu(struct amd_iommu *iommu) iommu_set_exclusion_range(iommu); iommu_enable_ga(iommu); iommu_enable_xt(iommu); + iommu_enable_irtcachedis(iommu); iommu_enable(iommu); iommu_flush_all_caches(iommu); } @@ -2760,10 +2792,12 @@ static void early_enable_iommus(void) for_each_iommu(iommu) { iommu_disable_command_buffer(iommu); iommu_disable_event_buffer(iommu); + iommu_disable_irtcachedis(iommu); iommu_enable_command_buffer(iommu); iommu_enable_event_buffer(iommu); iommu_enable_ga(iommu); iommu_enable_xt(iommu); + iommu_enable_irtcachedis(iommu); iommu_set_device_table(iommu); iommu_flush_all_caches(iommu); } @@ -3411,6 +3445,8 @@ static int __init parse_amd_iommu_options(char *str) amd_iommu_pgtable = AMD_IOMMU_V1; } else if (strncmp(str, "pgtbl_v2", 8) == 0) { amd_iommu_pgtable = AMD_IOMMU_V2; + } else if (strncmp(str, "irtcachedis", 11) == 0) { + amd_iommu_irtcachedis = true; } else { pr_notice("Unknown option - '%s'\n", str); } diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index d4d8bfee9feb..db33dc87f69e 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -882,6 +882,12 @@ static void arm_smmu_cmdq_batch_add(struct arm_smmu_device *smmu, { int index; + if (cmds->num == CMDQ_BATCH_ENTRIES - 1 && + (smmu->options & ARM_SMMU_OPT_CMDQ_FORCE_SYNC)) { + arm_smmu_cmdq_issue_cmdlist(smmu, cmds->cmds, cmds->num, true); + cmds->num = 0; + } + if (cmds->num == CMDQ_BATCH_ENTRIES) { arm_smmu_cmdq_issue_cmdlist(smmu, cmds->cmds, cmds->num, false); cmds->num = 0; @@ -3410,6 +3416,44 @@ static int arm_smmu_device_reset(struct arm_smmu_device *smmu, bool bypass) return 0; } +#define IIDR_IMPLEMENTER_ARM 0x43b +#define IIDR_PRODUCTID_ARM_MMU_600 0x483 +#define IIDR_PRODUCTID_ARM_MMU_700 0x487 + +static void arm_smmu_device_iidr_probe(struct arm_smmu_device *smmu) +{ + u32 reg; + unsigned int implementer, productid, variant, revision; + + reg = readl_relaxed(smmu->base + ARM_SMMU_IIDR); + implementer = FIELD_GET(IIDR_IMPLEMENTER, reg); + productid = FIELD_GET(IIDR_PRODUCTID, reg); + variant = FIELD_GET(IIDR_VARIANT, reg); + revision = FIELD_GET(IIDR_REVISION, reg); + + switch (implementer) { + case IIDR_IMPLEMENTER_ARM: + switch (productid) { + case IIDR_PRODUCTID_ARM_MMU_600: + /* Arm erratum 1076982 */ + if (variant == 0 && revision <= 2) + smmu->features &= ~ARM_SMMU_FEAT_SEV; + /* Arm erratum 1209401 */ + if (variant < 2) + smmu->features &= ~ARM_SMMU_FEAT_NESTING; + break; + case IIDR_PRODUCTID_ARM_MMU_700: + /* Arm erratum 2812531 */ + smmu->features &= ~ARM_SMMU_FEAT_BTM; + smmu->options |= ARM_SMMU_OPT_CMDQ_FORCE_SYNC; + /* Arm errata 2268618, 2812531 */ + smmu->features &= ~ARM_SMMU_FEAT_NESTING; + break; + } + break; + } +} + static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu) { u32 reg; @@ -3615,6 +3659,12 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu) smmu->ias = max(smmu->ias, smmu->oas); + if ((smmu->features & ARM_SMMU_FEAT_TRANS_S1) && + (smmu->features & ARM_SMMU_FEAT_TRANS_S2)) + smmu->features |= ARM_SMMU_FEAT_NESTING; + + arm_smmu_device_iidr_probe(smmu); + if (arm_smmu_sva_supported(smmu)) smmu->features |= ARM_SMMU_FEAT_SVA; diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h index cd48590ada30..d0b207cae107 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h @@ -69,6 +69,12 @@ #define IDR5_VAX GENMASK(11, 10) #define IDR5_VAX_52_BIT 1 +#define ARM_SMMU_IIDR 0x18 +#define IIDR_PRODUCTID GENMASK(31, 20) +#define IIDR_VARIANT GENMASK(19, 16) +#define IIDR_REVISION GENMASK(15, 12) +#define IIDR_IMPLEMENTER GENMASK(11, 0) + #define ARM_SMMU_CR0 0x20 #define CR0_ATSCHK (1 << 4) #define CR0_CMDQEN (1 << 3) @@ -639,11 +645,13 @@ struct arm_smmu_device { #define ARM_SMMU_FEAT_BTM (1 << 16) #define ARM_SMMU_FEAT_SVA (1 << 17) #define ARM_SMMU_FEAT_E2H (1 << 18) +#define ARM_SMMU_FEAT_NESTING (1 << 19) u32 features; #define ARM_SMMU_OPT_SKIP_PREFETCH (1 << 0) #define ARM_SMMU_OPT_PAGE0_REGS_ONLY (1 << 1) #define ARM_SMMU_OPT_MSIPOLL (1 << 2) +#define ARM_SMMU_OPT_CMDQ_FORCE_SYNC (1 << 3) u32 options; struct arm_smmu_cmdq cmdq; diff --git a/drivers/isdn/hardware/mISDN/hfcpci.c b/drivers/isdn/hardware/mISDN/hfcpci.c index c0331b268010..fe391de1aba3 100644 --- a/drivers/isdn/hardware/mISDN/hfcpci.c +++ b/drivers/isdn/hardware/mISDN/hfcpci.c @@ -839,7 +839,7 @@ hfcpci_fill_fifo(struct bchannel *bch) *z1t = cpu_to_le16(new_z1); /* now send data */ if (bch->tx_idx < bch->tx_skb->len) return; - dev_kfree_skb(bch->tx_skb); + dev_kfree_skb_any(bch->tx_skb); if (get_next_bframe(bch)) goto next_t_frame; return; @@ -895,7 +895,7 @@ hfcpci_fill_fifo(struct bchannel *bch) } bz->za[new_f1].z1 = cpu_to_le16(new_z1); /* for next buffer */ bz->f1 = new_f1; /* next frame */ - dev_kfree_skb(bch->tx_skb); + dev_kfree_skb_any(bch->tx_skb); get_next_bframe(bch); } @@ -1119,7 +1119,7 @@ tx_birq(struct bchannel *bch) if (bch->tx_skb && bch->tx_idx < bch->tx_skb->len) hfcpci_fill_fifo(bch); else { - dev_kfree_skb(bch->tx_skb); + dev_kfree_skb_any(bch->tx_skb); if (get_next_bframe(bch)) hfcpci_fill_fifo(bch); } @@ -2277,7 +2277,7 @@ _hfcpci_softirq(struct device *dev, void *unused) return 0; if (hc->hw.int_m2 & HFCPCI_IRQ_ENABLE) { - spin_lock(&hc->lock); + spin_lock_irq(&hc->lock); bch = Sel_BCS(hc, hc->hw.bswapped ? 2 : 1); if (bch && bch->state == ISDN_P_B_RAW) { /* B1 rx&tx */ main_rec_hfcpci(bch); @@ -2288,7 +2288,7 @@ _hfcpci_softirq(struct device *dev, void *unused) main_rec_hfcpci(bch); tx_birq(bch); } - spin_unlock(&hc->lock); + spin_unlock_irq(&hc->lock); } return 0; } diff --git a/drivers/isdn/mISDN/dsp.h b/drivers/isdn/mISDN/dsp.h index fa09d511a8ed..baf31258f5c9 100644 --- a/drivers/isdn/mISDN/dsp.h +++ b/drivers/isdn/mISDN/dsp.h @@ -247,7 +247,7 @@ extern void dsp_cmx_hardware(struct dsp_conf *conf, struct dsp *dsp); extern int dsp_cmx_conf(struct dsp *dsp, u32 conf_id); extern void dsp_cmx_receive(struct dsp *dsp, struct sk_buff *skb); extern void dsp_cmx_hdlc(struct dsp *dsp, struct sk_buff *skb); -extern void dsp_cmx_send(void *arg); +extern void dsp_cmx_send(struct timer_list *arg); extern void dsp_cmx_transmit(struct dsp *dsp, struct sk_buff *skb); extern int dsp_cmx_del_conf_member(struct dsp *dsp); extern int dsp_cmx_del_conf(struct dsp_conf *conf); diff --git a/drivers/isdn/mISDN/dsp_cmx.c b/drivers/isdn/mISDN/dsp_cmx.c index 6d2088fbaf69..1b73af501397 100644 --- a/drivers/isdn/mISDN/dsp_cmx.c +++ b/drivers/isdn/mISDN/dsp_cmx.c @@ -1625,7 +1625,7 @@ static u16 dsp_count; /* last sample count */ static int dsp_count_valid; /* if we have last sample count */ void -dsp_cmx_send(void *arg) +dsp_cmx_send(struct timer_list *arg) { struct dsp_conf *conf; struct dsp_conf_member *member; diff --git a/drivers/isdn/mISDN/dsp_core.c b/drivers/isdn/mISDN/dsp_core.c index 386084530c2f..fae95f166688 100644 --- a/drivers/isdn/mISDN/dsp_core.c +++ b/drivers/isdn/mISDN/dsp_core.c @@ -1195,7 +1195,7 @@ static int __init dsp_init(void) } /* set sample timer */ - timer_setup(&dsp_spl_tl, (void *)dsp_cmx_send, 0); + timer_setup(&dsp_spl_tl, dsp_cmx_send, 0); dsp_spl_tl.expires = jiffies + dsp_tics; dsp_spl_jiffies = dsp_spl_tl.expires; add_timer(&dsp_spl_tl); diff --git a/drivers/leds/rgb/leds-qcom-lpg.c b/drivers/leds/rgb/leds-qcom-lpg.c index f1c2419334e6..f85a5d65d131 100644 --- a/drivers/leds/rgb/leds-qcom-lpg.c +++ b/drivers/leds/rgb/leds-qcom-lpg.c @@ -1112,8 +1112,10 @@ static int lpg_add_led(struct lpg *lpg, struct device_node *np) i = 0; for_each_available_child_of_node(np, child) { ret = lpg_parse_channel(lpg, child, &led->channels[i]); - if (ret < 0) + if (ret < 0) { + of_node_put(child); return ret; + } info[i].color_index = led->channels[i]->color; info[i].intensity = 0; @@ -1291,8 +1293,10 @@ static int lpg_probe(struct platform_device *pdev) for_each_available_child_of_node(pdev->dev.of_node, np) { ret = lpg_add_led(lpg, np); - if (ret) + if (ret) { + of_node_put(np); return ret; + } } for (i = 0; i < lpg->num_channels; i++) diff --git a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_enc.c b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_enc.c index d810a78dde51..31e3c3766218 100644 --- a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_enc.c +++ b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_enc.c @@ -821,6 +821,8 @@ static int vb2ops_venc_queue_setup(struct vb2_queue *vq, return -EINVAL; if (*nplanes) { + if (*nplanes != q_data->fmt->num_planes) + return -EINVAL; for (i = 0; i < *nplanes; i++) if (sizes[i] < q_data->sizeimage[i]) return -EINVAL; diff --git a/drivers/media/platform/mediatek/vpu/mtk_vpu.c b/drivers/media/platform/mediatek/vpu/mtk_vpu.c index 47b684b92f81..6beab9e86a22 100644 --- a/drivers/media/platform/mediatek/vpu/mtk_vpu.c +++ b/drivers/media/platform/mediatek/vpu/mtk_vpu.c @@ -562,15 +562,17 @@ static int load_requested_vpu(struct mtk_vpu *vpu, int vpu_load_firmware(struct platform_device *pdev) { struct mtk_vpu *vpu; - struct device *dev = &pdev->dev; + struct device *dev; struct vpu_run *run; int ret; if (!pdev) { - dev_err(dev, "VPU platform device is invalid\n"); + pr_err("VPU platform device is invalid\n"); return -EINVAL; } + dev = &pdev->dev; + vpu = platform_get_drvdata(pdev); run = &vpu->run; diff --git a/drivers/media/platform/qcom/camss/camss-vfe.c b/drivers/media/platform/qcom/camss/camss-vfe.c index a26e4a5d87b6..d8cd9b09c20d 100644 --- a/drivers/media/platform/qcom/camss/camss-vfe.c +++ b/drivers/media/platform/qcom/camss/camss-vfe.c @@ -1540,7 +1540,11 @@ int msm_vfe_register_entities(struct vfe_device *vfe, } video_out->ops = &vfe->video_ops; - video_out->bpl_alignment = 8; + if (vfe->camss->version == CAMSS_845 || + vfe->camss->version == CAMSS_8250) + video_out->bpl_alignment = 16; + else + video_out->bpl_alignment = 8; video_out->line_based = 0; if (i == VFE_LINE_PIX) { video_out->bpl_alignment = 16; diff --git a/drivers/misc/cardreader/rts5227.c b/drivers/misc/cardreader/rts5227.c index d676cf63a966..3dae5e3a1697 100644 --- a/drivers/misc/cardreader/rts5227.c +++ b/drivers/misc/cardreader/rts5227.c @@ -195,7 +195,7 @@ static int rts5227_extra_init_hw(struct rtsx_pcr *pcr) } } - if (option->force_clkreq_0) + if (option->force_clkreq_0 && pcr->aspm_mode == ASPM_MODE_CFG) rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, PETXCFG, FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_LOW); else diff --git a/drivers/misc/cardreader/rts5228.c b/drivers/misc/cardreader/rts5228.c index cfebad51d1d8..f4ab09439da7 100644 --- a/drivers/misc/cardreader/rts5228.c +++ b/drivers/misc/cardreader/rts5228.c @@ -435,17 +435,10 @@ static void rts5228_init_from_cfg(struct rtsx_pcr *pcr) option->ltr_enabled = false; } } - - if (rtsx_check_dev_flag(pcr, ASPM_L1_1_EN | ASPM_L1_2_EN - | PM_L1_1_EN | PM_L1_2_EN)) - option->force_clkreq_0 = false; - else - option->force_clkreq_0 = true; } static int rts5228_extra_init_hw(struct rtsx_pcr *pcr) { - struct rtsx_cr_option *option = &pcr->option; rtsx_pci_write_register(pcr, RTS5228_AUTOLOAD_CFG1, CD_RESUME_EN_MASK, CD_RESUME_EN_MASK); @@ -476,17 +469,6 @@ static int rts5228_extra_init_hw(struct rtsx_pcr *pcr) else rtsx_pci_write_register(pcr, PETXCFG, 0x30, 0x00); - /* - * If u_force_clkreq_0 is enabled, CLKREQ# PIN will be forced - * to drive low, and we forcibly request clock. - */ - if (option->force_clkreq_0) - rtsx_pci_write_register(pcr, PETXCFG, - FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_LOW); - else - rtsx_pci_write_register(pcr, PETXCFG, - FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_HIGH); - rtsx_pci_write_register(pcr, PWD_SUSPEND_EN, 0xFF, 0xFB); if (pcr->rtd3_en) { diff --git a/drivers/misc/cardreader/rts5249.c b/drivers/misc/cardreader/rts5249.c index 91d240dd68fa..47ab72a43256 100644 --- a/drivers/misc/cardreader/rts5249.c +++ b/drivers/misc/cardreader/rts5249.c @@ -327,12 +327,11 @@ static int rts5249_extra_init_hw(struct rtsx_pcr *pcr) } } - /* * If u_force_clkreq_0 is enabled, CLKREQ# PIN will be forced * to drive low, and we forcibly request clock. */ - if (option->force_clkreq_0) + if (option->force_clkreq_0 && pcr->aspm_mode == ASPM_MODE_CFG) rtsx_pci_write_register(pcr, PETXCFG, FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_LOW); else diff --git a/drivers/misc/cardreader/rts5260.c b/drivers/misc/cardreader/rts5260.c index 9b42b20a3e5a..79b18f6f73a8 100644 --- a/drivers/misc/cardreader/rts5260.c +++ b/drivers/misc/cardreader/rts5260.c @@ -517,17 +517,10 @@ static void rts5260_init_from_cfg(struct rtsx_pcr *pcr) option->ltr_enabled = false; } } - - if (rtsx_check_dev_flag(pcr, ASPM_L1_1_EN | ASPM_L1_2_EN - | PM_L1_1_EN | PM_L1_2_EN)) - option->force_clkreq_0 = false; - else - option->force_clkreq_0 = true; } static int rts5260_extra_init_hw(struct rtsx_pcr *pcr) { - struct rtsx_cr_option *option = &pcr->option; /* Set mcu_cnt to 7 to ensure data can be sampled properly */ rtsx_pci_write_register(pcr, 0xFC03, 0x7F, 0x07); @@ -546,17 +539,6 @@ static int rts5260_extra_init_hw(struct rtsx_pcr *pcr) rts5260_init_hw(pcr); - /* - * If u_force_clkreq_0 is enabled, CLKREQ# PIN will be forced - * to drive low, and we forcibly request clock. - */ - if (option->force_clkreq_0) - rtsx_pci_write_register(pcr, PETXCFG, - FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_LOW); - else - rtsx_pci_write_register(pcr, PETXCFG, - FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_HIGH); - rtsx_pci_write_register(pcr, pcr->reg_pm_ctrl3, 0x10, 0x00); return 0; diff --git a/drivers/misc/cardreader/rts5261.c b/drivers/misc/cardreader/rts5261.c index b1e76030cafd..94af6bf8a25a 100644 --- a/drivers/misc/cardreader/rts5261.c +++ b/drivers/misc/cardreader/rts5261.c @@ -498,17 +498,10 @@ static void rts5261_init_from_cfg(struct rtsx_pcr *pcr) option->ltr_enabled = false; } } - - if (rtsx_check_dev_flag(pcr, ASPM_L1_1_EN | ASPM_L1_2_EN - | PM_L1_1_EN | PM_L1_2_EN)) - option->force_clkreq_0 = false; - else - option->force_clkreq_0 = true; } static int rts5261_extra_init_hw(struct rtsx_pcr *pcr) { - struct rtsx_cr_option *option = &pcr->option; u32 val; rtsx_pci_write_register(pcr, RTS5261_AUTOLOAD_CFG1, @@ -554,17 +547,6 @@ static int rts5261_extra_init_hw(struct rtsx_pcr *pcr) else rtsx_pci_write_register(pcr, PETXCFG, 0x30, 0x00); - /* - * If u_force_clkreq_0 is enabled, CLKREQ# PIN will be forced - * to drive low, and we forcibly request clock. - */ - if (option->force_clkreq_0) - rtsx_pci_write_register(pcr, PETXCFG, - FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_LOW); - else - rtsx_pci_write_register(pcr, PETXCFG, - FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_HIGH); - rtsx_pci_write_register(pcr, PWD_SUSPEND_EN, 0xFF, 0xFB); if (pcr->rtd3_en) { diff --git a/drivers/misc/cardreader/rtsx_pcr.c b/drivers/misc/cardreader/rtsx_pcr.c index 32b7783e9d4f..a3f4b52bb159 100644 --- a/drivers/misc/cardreader/rtsx_pcr.c +++ b/drivers/misc/cardreader/rtsx_pcr.c @@ -1326,8 +1326,11 @@ static int rtsx_pci_init_hw(struct rtsx_pcr *pcr) return err; } - if (pcr->aspm_mode == ASPM_MODE_REG) + if (pcr->aspm_mode == ASPM_MODE_REG) { rtsx_pci_write_register(pcr, ASPM_FORCE_CTL, 0x30, 0x30); + rtsx_pci_write_register(pcr, PETXCFG, + FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_HIGH); + } /* No CD interrupt if probing driver with card inserted. * So we need to initialize pcr->card_exist here. diff --git a/drivers/misc/habanalabs/common/device.c b/drivers/misc/habanalabs/common/device.c index e0dca445abf1..9ee1b6abd8a0 100644 --- a/drivers/misc/habanalabs/common/device.c +++ b/drivers/misc/habanalabs/common/device.c @@ -870,6 +870,18 @@ static void device_early_fini(struct hl_device *hdev) hdev->asic_funcs->early_fini(hdev); } +static bool is_pci_link_healthy(struct hl_device *hdev) +{ + u16 vendor_id; + + if (!hdev->pdev) + return false; + + pci_read_config_word(hdev->pdev, PCI_VENDOR_ID, &vendor_id); + + return (vendor_id == PCI_VENDOR_ID_HABANALABS); +} + static void hl_device_heartbeat(struct work_struct *work) { struct hl_device *hdev = container_of(work, struct hl_device, @@ -882,7 +894,8 @@ static void hl_device_heartbeat(struct work_struct *work) goto reschedule; if (hl_device_operational(hdev, NULL)) - dev_err(hdev->dev, "Device heartbeat failed!\n"); + dev_err(hdev->dev, "Device heartbeat failed! PCI link is %s\n", + is_pci_link_healthy(hdev) ? "healthy" : "broken"); hl_device_reset(hdev, HL_DRV_RESET_HARD | HL_DRV_RESET_HEARTBEAT); diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h index 58c95b13be69..257b94cec624 100644 --- a/drivers/misc/habanalabs/common/habanalabs.h +++ b/drivers/misc/habanalabs/common/habanalabs.h @@ -34,6 +34,8 @@ struct hl_device; struct hl_fpriv; +#define PCI_VENDOR_ID_HABANALABS 0x1da3 + /* Use upper bits of mmap offset to store habana driver specific information. * bits[63:59] - Encode mmap type * bits[45:0] - mmap offset value diff --git a/drivers/misc/habanalabs/common/habanalabs_drv.c b/drivers/misc/habanalabs/common/habanalabs_drv.c index 112632afe7d5..ae3cab3f4aa5 100644 --- a/drivers/misc/habanalabs/common/habanalabs_drv.c +++ b/drivers/misc/habanalabs/common/habanalabs_drv.c @@ -54,8 +54,6 @@ module_param(boot_error_status_mask, ulong, 0444); MODULE_PARM_DESC(boot_error_status_mask, "Mask of the error status during device CPU boot (If bitX is cleared then error X is masked. Default all 1's)"); -#define PCI_VENDOR_ID_HABANALABS 0x1da3 - #define PCI_IDS_GOYA 0x0001 #define PCI_IDS_GAUDI 0x1000 #define PCI_IDS_GAUDI_SEC 0x1010 diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index 498333b769fd..cdd7f126d4ae 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -2097,14 +2097,14 @@ static void mmc_blk_mq_poll_completion(struct mmc_queue *mq, mmc_blk_urgent_bkops(mq, mqrq); } -static void mmc_blk_mq_dec_in_flight(struct mmc_queue *mq, struct request *req) +static void mmc_blk_mq_dec_in_flight(struct mmc_queue *mq, enum mmc_issue_type issue_type) { unsigned long flags; bool put_card; spin_lock_irqsave(&mq->lock, flags); - mq->in_flight[mmc_issue_type(mq, req)] -= 1; + mq->in_flight[issue_type] -= 1; put_card = (mmc_tot_in_flight(mq) == 0); @@ -2117,6 +2117,7 @@ static void mmc_blk_mq_dec_in_flight(struct mmc_queue *mq, struct request *req) static void mmc_blk_mq_post_req(struct mmc_queue *mq, struct request *req, bool can_sleep) { + enum mmc_issue_type issue_type = mmc_issue_type(mq, req); struct mmc_queue_req *mqrq = req_to_mmc_queue_req(req); struct mmc_request *mrq = &mqrq->brq.mrq; struct mmc_host *host = mq->card->host; @@ -2136,7 +2137,7 @@ static void mmc_blk_mq_post_req(struct mmc_queue *mq, struct request *req, blk_mq_complete_request(req); } - mmc_blk_mq_dec_in_flight(mq, req); + mmc_blk_mq_dec_in_flight(mq, issue_type); } void mmc_blk_mq_recovery(struct mmc_queue *mq) diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig index fb1062a6394c..9b5a2cb110b3 100644 --- a/drivers/mmc/host/Kconfig +++ b/drivers/mmc/host/Kconfig @@ -528,11 +528,12 @@ config MMC_ALCOR of Alcor Micro PCI-E card reader config MMC_AU1X - tristate "Alchemy AU1XX0 MMC Card Interface support" + bool "Alchemy AU1XX0 MMC Card Interface support" depends on MIPS_ALCHEMY + depends on MMC=y help This selects the AMD Alchemy(R) Multimedia card interface. - If you have a Alchemy platform with a MMC slot, say Y or M here. + If you have a Alchemy platform with a MMC slot, say Y here. If unsure, say N. diff --git a/drivers/mmc/host/moxart-mmc.c b/drivers/mmc/host/moxart-mmc.c index 52ed30f2d9f4..94e9a08bc90e 100644 --- a/drivers/mmc/host/moxart-mmc.c +++ b/drivers/mmc/host/moxart-mmc.c @@ -338,13 +338,7 @@ static void moxart_transfer_pio(struct moxart_host *host) return; } for (len = 0; len < remain && len < host->fifo_width;) { - /* SCR data must be read in big endian. */ - if (data->mrq->cmd->opcode == SD_APP_SEND_SCR) - *sgp = ioread32be(host->base + - REG_DATA_WINDOW); - else - *sgp = ioread32(host->base + - REG_DATA_WINDOW); + *sgp = ioread32(host->base + REG_DATA_WINDOW); sgp++; len += 4; } diff --git a/drivers/mmc/host/sdhci_f_sdh30.c b/drivers/mmc/host/sdhci_f_sdh30.c index 6c4f43e11282..7ede74bf3723 100644 --- a/drivers/mmc/host/sdhci_f_sdh30.c +++ b/drivers/mmc/host/sdhci_f_sdh30.c @@ -26,9 +26,16 @@ struct f_sdhost_priv { bool enable_cmd_dat_delay; }; +static void *sdhci_f_sdhost_priv(struct sdhci_host *host) +{ + struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); + + return sdhci_pltfm_priv(pltfm_host); +} + static void sdhci_f_sdh30_soft_voltage_switch(struct sdhci_host *host) { - struct f_sdhost_priv *priv = sdhci_priv(host); + struct f_sdhost_priv *priv = sdhci_f_sdhost_priv(host); u32 ctrl = 0; usleep_range(2500, 3000); @@ -61,7 +68,7 @@ static unsigned int sdhci_f_sdh30_get_min_clock(struct sdhci_host *host) static void sdhci_f_sdh30_reset(struct sdhci_host *host, u8 mask) { - struct f_sdhost_priv *priv = sdhci_priv(host); + struct f_sdhost_priv *priv = sdhci_f_sdhost_priv(host); u32 ctl; if (sdhci_readw(host, SDHCI_CLOCK_CONTROL) == 0) @@ -85,30 +92,32 @@ static const struct sdhci_ops sdhci_f_sdh30_ops = { .set_uhs_signaling = sdhci_set_uhs_signaling, }; +static const struct sdhci_pltfm_data sdhci_f_sdh30_pltfm_data = { + .ops = &sdhci_f_sdh30_ops, + .quirks = SDHCI_QUIRK_NO_ENDATTR_IN_NOPDESC + | SDHCI_QUIRK_INVERTED_WRITE_PROTECT, + .quirks2 = SDHCI_QUIRK2_SUPPORT_SINGLE + | SDHCI_QUIRK2_TUNING_WORK_AROUND, +}; + static int sdhci_f_sdh30_probe(struct platform_device *pdev) { struct sdhci_host *host; struct device *dev = &pdev->dev; - int irq, ctrl = 0, ret = 0; + int ctrl = 0, ret = 0; struct f_sdhost_priv *priv; + struct sdhci_pltfm_host *pltfm_host; u32 reg = 0; - irq = platform_get_irq(pdev, 0); - if (irq < 0) - return irq; - - host = sdhci_alloc_host(dev, sizeof(struct f_sdhost_priv)); + host = sdhci_pltfm_init(pdev, &sdhci_f_sdh30_pltfm_data, + sizeof(struct f_sdhost_priv)); if (IS_ERR(host)) return PTR_ERR(host); - priv = sdhci_priv(host); + pltfm_host = sdhci_priv(host); + priv = sdhci_pltfm_priv(pltfm_host); priv->dev = dev; - host->quirks = SDHCI_QUIRK_NO_ENDATTR_IN_NOPDESC | - SDHCI_QUIRK_INVERTED_WRITE_PROTECT; - host->quirks2 = SDHCI_QUIRK2_SUPPORT_SINGLE | - SDHCI_QUIRK2_TUNING_WORK_AROUND; - priv->enable_cmd_dat_delay = device_property_read_bool(dev, "fujitsu,cmd-dat-delay-select"); @@ -116,18 +125,6 @@ static int sdhci_f_sdh30_probe(struct platform_device *pdev) if (ret) goto err; - platform_set_drvdata(pdev, host); - - host->hw_name = "f_sdh30"; - host->ops = &sdhci_f_sdh30_ops; - host->irq = irq; - - host->ioaddr = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(host->ioaddr)) { - ret = PTR_ERR(host->ioaddr); - goto err; - } - if (dev_of_node(dev)) { sdhci_get_of_property(pdev); @@ -182,23 +179,22 @@ err_add_host: err_clk: clk_disable_unprepare(priv->clk_iface); err: - sdhci_free_host(host); + sdhci_pltfm_free(pdev); + return ret; } static int sdhci_f_sdh30_remove(struct platform_device *pdev) { struct sdhci_host *host = platform_get_drvdata(pdev); - struct f_sdhost_priv *priv = sdhci_priv(host); - - sdhci_remove_host(host, readl(host->ioaddr + SDHCI_INT_STATUS) == - 0xffffffff); + struct f_sdhost_priv *priv = sdhci_f_sdhost_priv(host); + struct clk *clk_iface = priv->clk_iface; + struct clk *clk = priv->clk; - clk_disable_unprepare(priv->clk_iface); - clk_disable_unprepare(priv->clk); + sdhci_pltfm_unregister(pdev); - sdhci_free_host(host); - platform_set_drvdata(pdev, NULL); + clk_disable_unprepare(clk_iface); + clk_disable_unprepare(clk); return 0; } diff --git a/drivers/mmc/host/wbsd.c b/drivers/mmc/host/wbsd.c index 7c7ec8d10232..b5b1a42ca25e 100644 --- a/drivers/mmc/host/wbsd.c +++ b/drivers/mmc/host/wbsd.c @@ -1705,8 +1705,6 @@ static int wbsd_init(struct device *dev, int base, int irq, int dma, wbsd_release_resources(host); wbsd_free_mmc(dev); - - mmc_free_host(mmc); return ret; } diff --git a/drivers/mtd/nand/raw/fsl_upm.c b/drivers/mtd/nand/raw/fsl_upm.c index b3cc427100a2..636e65328bb3 100644 --- a/drivers/mtd/nand/raw/fsl_upm.c +++ b/drivers/mtd/nand/raw/fsl_upm.c @@ -135,7 +135,7 @@ static int fun_exec_op(struct nand_chip *chip, const struct nand_operation *op, unsigned int i; int ret; - if (op->cs > NAND_MAX_CHIPS) + if (op->cs >= NAND_MAX_CHIPS) return -EINVAL; if (check_only) diff --git a/drivers/mtd/nand/raw/meson_nand.c b/drivers/mtd/nand/raw/meson_nand.c index 029a2a302aa6..ac4947f72047 100644 --- a/drivers/mtd/nand/raw/meson_nand.c +++ b/drivers/mtd/nand/raw/meson_nand.c @@ -1184,7 +1184,6 @@ static int meson_nand_attach_chip(struct nand_chip *nand) struct meson_nfc *nfc = nand_get_controller_data(nand); struct meson_nfc_nand_chip *meson_chip = to_meson_nand(nand); struct mtd_info *mtd = nand_to_mtd(nand); - int nsectors = mtd->writesize / 1024; int ret; if (!mtd->name) { @@ -1202,7 +1201,7 @@ static int meson_nand_attach_chip(struct nand_chip *nand) nand->options |= NAND_NO_SUBPAGE_WRITE; ret = nand_ecc_choose_conf(nand, nfc->data->ecc_caps, - mtd->oobsize - 2 * nsectors); + mtd->oobsize - 2); if (ret) { dev_err(nfc->dev, "failed to ECC init\n"); return -EINVAL; diff --git a/drivers/mtd/nand/raw/omap_elm.c b/drivers/mtd/nand/raw/omap_elm.c index 4796a48e1012..22d37fc37e98 100644 --- a/drivers/mtd/nand/raw/omap_elm.c +++ b/drivers/mtd/nand/raw/omap_elm.c @@ -177,17 +177,17 @@ static void elm_load_syndrome(struct elm_info *info, switch (info->bch_type) { case BCH8_ECC: /* syndrome fragment 0 = ecc[9-12B] */ - val = cpu_to_be32(*(u32 *) &ecc[9]); + val = (__force u32)cpu_to_be32(*(u32 *)&ecc[9]); elm_write_reg(info, offset, val); /* syndrome fragment 1 = ecc[5-8B] */ offset += 4; - val = cpu_to_be32(*(u32 *) &ecc[5]); + val = (__force u32)cpu_to_be32(*(u32 *)&ecc[5]); elm_write_reg(info, offset, val); /* syndrome fragment 2 = ecc[1-4B] */ offset += 4; - val = cpu_to_be32(*(u32 *) &ecc[1]); + val = (__force u32)cpu_to_be32(*(u32 *)&ecc[1]); elm_write_reg(info, offset, val); /* syndrome fragment 3 = ecc[0B] */ @@ -197,35 +197,35 @@ static void elm_load_syndrome(struct elm_info *info, break; case BCH4_ECC: /* syndrome fragment 0 = ecc[20-52b] bits */ - val = (cpu_to_be32(*(u32 *) &ecc[3]) >> 4) | + val = ((__force u32)cpu_to_be32(*(u32 *)&ecc[3]) >> 4) | ((ecc[2] & 0xf) << 28); elm_write_reg(info, offset, val); /* syndrome fragment 1 = ecc[0-20b] bits */ offset += 4; - val = cpu_to_be32(*(u32 *) &ecc[0]) >> 12; + val = (__force u32)cpu_to_be32(*(u32 *)&ecc[0]) >> 12; elm_write_reg(info, offset, val); break; case BCH16_ECC: - val = cpu_to_be32(*(u32 *) &ecc[22]); + val = (__force u32)cpu_to_be32(*(u32 *)&ecc[22]); elm_write_reg(info, offset, val); offset += 4; - val = cpu_to_be32(*(u32 *) &ecc[18]); + val = (__force u32)cpu_to_be32(*(u32 *)&ecc[18]); elm_write_reg(info, offset, val); offset += 4; - val = cpu_to_be32(*(u32 *) &ecc[14]); + val = (__force u32)cpu_to_be32(*(u32 *)&ecc[14]); elm_write_reg(info, offset, val); offset += 4; - val = cpu_to_be32(*(u32 *) &ecc[10]); + val = (__force u32)cpu_to_be32(*(u32 *)&ecc[10]); elm_write_reg(info, offset, val); offset += 4; - val = cpu_to_be32(*(u32 *) &ecc[6]); + val = (__force u32)cpu_to_be32(*(u32 *)&ecc[6]); elm_write_reg(info, offset, val); offset += 4; - val = cpu_to_be32(*(u32 *) &ecc[2]); + val = (__force u32)cpu_to_be32(*(u32 *)&ecc[2]); elm_write_reg(info, offset, val); offset += 4; - val = cpu_to_be32(*(u32 *) &ecc[0]) >> 16; + val = (__force u32)cpu_to_be32(*(u32 *)&ecc[0]) >> 16; elm_write_reg(info, offset, val); break; default: diff --git a/drivers/mtd/nand/raw/rockchip-nand-controller.c b/drivers/mtd/nand/raw/rockchip-nand-controller.c index f133985cc053..c9c4e9ffcae1 100644 --- a/drivers/mtd/nand/raw/rockchip-nand-controller.c +++ b/drivers/mtd/nand/raw/rockchip-nand-controller.c @@ -562,9 +562,10 @@ static int rk_nfc_write_page_raw(struct nand_chip *chip, const u8 *buf, * BBM OOB1 OOB2 OOB3 |......| PA0 PA1 PA2 PA3 * * The rk_nfc_ooblayout_free() function already has reserved - * these 4 bytes with: + * these 4 bytes together with 2 bytes for BBM + * by reducing it's length: * - * oob_region->offset = NFC_SYS_DATA_SIZE + 2; + * oob_region->length = rknand->metadata_size - NFC_SYS_DATA_SIZE - 2; */ if (!i) memcpy(rk_nfc_oob_ptr(chip, i), @@ -597,7 +598,7 @@ static int rk_nfc_write_page_hwecc(struct nand_chip *chip, const u8 *buf, int pages_per_blk = mtd->erasesize / mtd->writesize; int ret = 0, i, boot_rom_mode = 0; dma_addr_t dma_data, dma_oob; - u32 reg; + u32 tmp; u8 *oob; nand_prog_page_begin_op(chip, page, 0, NULL, 0); @@ -624,6 +625,13 @@ static int rk_nfc_write_page_hwecc(struct nand_chip *chip, const u8 *buf, * * 0xFF 0xFF 0xFF 0xFF | BBM OOB1 OOB2 OOB3 | ... * + * The code here just swaps the first 4 bytes with the last + * 4 bytes without losing any data. + * + * The chip->oob_poi data layout: + * + * BBM OOB1 OOB2 OOB3 |......| PA0 PA1 PA2 PA3 + * * Configure the ECC algorithm supported by the boot ROM. */ if ((page < (pages_per_blk * rknand->boot_blks)) && @@ -634,21 +642,17 @@ static int rk_nfc_write_page_hwecc(struct nand_chip *chip, const u8 *buf, } for (i = 0; i < ecc->steps; i++) { - if (!i) { - reg = 0xFFFFFFFF; - } else { + if (!i) + oob = chip->oob_poi + (ecc->steps - 1) * NFC_SYS_DATA_SIZE; + else oob = chip->oob_poi + (i - 1) * NFC_SYS_DATA_SIZE; - reg = oob[0] | oob[1] << 8 | oob[2] << 16 | - oob[3] << 24; - } - if (!i && boot_rom_mode) - reg = (page & (pages_per_blk - 1)) * 4; + tmp = oob[0] | oob[1] << 8 | oob[2] << 16 | oob[3] << 24; if (nfc->cfg->type == NFC_V9) - nfc->oob_buf[i] = reg; + nfc->oob_buf[i] = tmp; else - nfc->oob_buf[i * (oob_step / 4)] = reg; + nfc->oob_buf[i * (oob_step / 4)] = tmp; } dma_data = dma_map_single(nfc->dev, (void *)nfc->page_buf, @@ -811,12 +815,17 @@ static int rk_nfc_read_page_hwecc(struct nand_chip *chip, u8 *buf, int oob_on, goto timeout_err; } - for (i = 1; i < ecc->steps; i++) { - oob = chip->oob_poi + (i - 1) * NFC_SYS_DATA_SIZE; + for (i = 0; i < ecc->steps; i++) { + if (!i) + oob = chip->oob_poi + (ecc->steps - 1) * NFC_SYS_DATA_SIZE; + else + oob = chip->oob_poi + (i - 1) * NFC_SYS_DATA_SIZE; + if (nfc->cfg->type == NFC_V9) tmp = nfc->oob_buf[i]; else tmp = nfc->oob_buf[i * (oob_step / 4)]; + *oob++ = (u8)tmp; *oob++ = (u8)(tmp >> 8); *oob++ = (u8)(tmp >> 16); @@ -933,12 +942,8 @@ static int rk_nfc_ooblayout_free(struct mtd_info *mtd, int section, if (section) return -ERANGE; - /* - * The beginning of the OOB area stores the reserved data for the NFC, - * the size of the reserved data is NFC_SYS_DATA_SIZE bytes. - */ oob_region->length = rknand->metadata_size - NFC_SYS_DATA_SIZE - 2; - oob_region->offset = NFC_SYS_DATA_SIZE + 2; + oob_region->offset = 2; return 0; } diff --git a/drivers/mtd/nand/spi/toshiba.c b/drivers/mtd/nand/spi/toshiba.c index 7380b1ebaccd..a80427c13121 100644 --- a/drivers/mtd/nand/spi/toshiba.c +++ b/drivers/mtd/nand/spi/toshiba.c @@ -73,7 +73,7 @@ static int tx58cxgxsxraix_ecc_get_status(struct spinand_device *spinand, { struct nand_device *nand = spinand_to_nand(spinand); u8 mbf = 0; - struct spi_mem_op op = SPINAND_GET_FEATURE_OP(0x30, &mbf); + struct spi_mem_op op = SPINAND_GET_FEATURE_OP(0x30, spinand->scratchbuf); switch (status & STATUS_ECC_MASK) { case STATUS_ECC_NO_BITFLIPS: @@ -92,7 +92,7 @@ static int tx58cxgxsxraix_ecc_get_status(struct spinand_device *spinand, if (spi_mem_exec_op(spinand->spimem, &op)) return nanddev_get_ecc_conf(nand)->strength; - mbf >>= 4; + mbf = *(spinand->scratchbuf) >> 4; if (WARN_ON(mbf > nanddev_get_ecc_conf(nand)->strength || !mbf)) return nanddev_get_ecc_conf(nand)->strength; diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index b9dbad3a8af8..fc5da5d7744d 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -660,10 +660,10 @@ static struct slave *rlb_arp_xmit(struct sk_buff *skb, struct bonding *bond) return NULL; arp = (struct arp_pkt *)skb_network_header(skb); - /* Don't modify or load balance ARPs that do not originate locally - * (e.g.,arrive via a bridge). + /* Don't modify or load balance ARPs that do not originate + * from the bond itself or a VLAN directly above the bond. */ - if (!bond_slave_has_mac_rx(bond, arp->mac_src)) + if (!bond_slave_has_mac_rcu(bond, arp->mac_src)) return NULL; dev = ip_dev_find(dev_net(bond->dev), arp->ip_src); diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 576370f89c75..7a3c7a74af04 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -5839,7 +5839,9 @@ void bond_setup(struct net_device *bond_dev) bond_dev->hw_features = BOND_VLAN_FEATURES | NETIF_F_HW_VLAN_CTAG_RX | - NETIF_F_HW_VLAN_CTAG_FILTER; + NETIF_F_HW_VLAN_CTAG_FILTER | + NETIF_F_HW_VLAN_STAG_RX | + NETIF_F_HW_VLAN_STAG_FILTER; bond_dev->hw_features |= NETIF_F_GSO_ENCAP_ALL; bond_dev->features |= bond_dev->hw_features; diff --git a/drivers/net/can/vxcan.c b/drivers/net/can/vxcan.c index 26a472d2ea58..6d549dbdb467 100644 --- a/drivers/net/can/vxcan.c +++ b/drivers/net/can/vxcan.c @@ -192,12 +192,7 @@ static int vxcan_newlink(struct net *net, struct net_device *dev, nla_peer = data[VXCAN_INFO_PEER]; ifmp = nla_data(nla_peer); - err = rtnl_nla_parse_ifla(peer_tb, - nla_data(nla_peer) + - sizeof(struct ifinfomsg), - nla_len(nla_peer) - - sizeof(struct ifinfomsg), - NULL); + err = rtnl_nla_parse_ifinfomsg(peer_tb, nla_peer, extack); if (err < 0) return err; diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index cde253d27bd0..72374b066f64 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -1436,7 +1436,9 @@ static int bcm_sf2_sw_probe(struct platform_device *pdev) if (IS_ERR(priv->clk)) return PTR_ERR(priv->clk); - clk_prepare_enable(priv->clk); + ret = clk_prepare_enable(priv->clk); + if (ret) + return ret; priv->clk_mdiv = devm_clk_get_optional(&pdev->dev, "sw_switch_mdiv"); if (IS_ERR(priv->clk_mdiv)) { @@ -1444,7 +1446,9 @@ static int bcm_sf2_sw_probe(struct platform_device *pdev) goto out_clk; } - clk_prepare_enable(priv->clk_mdiv); + ret = clk_prepare_enable(priv->clk_mdiv); + if (ret) + goto out_clk; ret = bcm_sf2_sw_rst(priv); if (ret) { diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 51d2ef0dc835..b988c8a40d53 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -1005,6 +1005,10 @@ mt753x_trap_frames(struct mt7530_priv *priv) mt7530_rmw(priv, MT753X_BPC, MT753X_BPDU_PORT_FW_MASK, MT753X_BPDU_CPU_ONLY); + /* Trap 802.1X PAE frames to the CPU port(s) */ + mt7530_rmw(priv, MT753X_BPC, MT753X_PAE_PORT_FW_MASK, + MT753X_PAE_PORT_FW(MT753X_BPDU_CPU_ONLY)); + /* Trap LLDP frames with :0E MAC DA to the CPU port(s) */ mt7530_rmw(priv, MT753X_RGAC2, MT753X_R0E_PORT_FW_MASK, MT753X_R0E_PORT_FW(MT753X_BPDU_CPU_ONLY)); diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h index 9a45663d8b4e..6202b0f8c3f3 100644 --- a/drivers/net/dsa/mt7530.h +++ b/drivers/net/dsa/mt7530.h @@ -64,6 +64,8 @@ enum mt753x_id { /* Registers for BPDU and PAE frame control*/ #define MT753X_BPC 0x24 #define MT753X_BPDU_PORT_FW_MASK GENMASK(2, 0) +#define MT753X_PAE_PORT_FW_MASK GENMASK(18, 16) +#define MT753X_PAE_PORT_FW(x) FIELD_PREP(MT753X_PAE_PORT_FW_MASK, x) /* Register for :03 and :0E MAC DA frame control */ #define MT753X_RGAC2 0x2c diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index b69bd44ada1f..a73008b9e0b3 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -3006,6 +3006,14 @@ static void mv88e6xxx_hardware_reset(struct mv88e6xxx_chip *chip) /* If there is a GPIO connected to the reset pin, toggle it */ if (gpiod) { + /* If the switch has just been reset and not yet completed + * loading EEPROM, the reset may interrupt the I2C transaction + * mid-byte, causing the first EEPROM read after the reset + * from the wrong location resulting in the switch booting + * to wrong mode and inoperable. + */ + mv88e6xxx_g1_wait_eeprom_done(chip); + gpiod_set_value_cansleep(gpiod, 1); usleep_range(10000, 20000); gpiod_set_value_cansleep(gpiod, 0); diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index 4faabc4364aa..2d2c6f941272 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -1606,8 +1606,10 @@ static void felix_teardown(struct dsa_switch *ds) struct felix *felix = ocelot_to_felix(ocelot); struct dsa_port *dp; + rtnl_lock(); if (felix->tag_proto_ops) felix->tag_proto_ops->teardown(ds); + rtnl_unlock(); dsa_switch_for_each_available_port(dp, ds) ocelot_deinit_port(ocelot, dp->index); diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c index 5f6af0870dfd..0186482194d2 100644 --- a/drivers/net/dsa/ocelot/felix_vsc9959.c +++ b/drivers/net/dsa/ocelot/felix_vsc9959.c @@ -1071,6 +1071,9 @@ static u64 vsc9959_tas_remaining_gate_len_ps(u64 gate_len_ns) if (gate_len_ns == U64_MAX) return U64_MAX; + if (gate_len_ns < VSC9959_TAS_MIN_GATE_LEN_NS) + return 0; + return (gate_len_ns - VSC9959_TAS_MIN_GATE_LEN_NS) * PSEC_PER_NSEC; } diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c index 10c7c232cc4e..52ee3751187a 100644 --- a/drivers/net/ethernet/broadcom/bgmac.c +++ b/drivers/net/ethernet/broadcom/bgmac.c @@ -1448,7 +1448,7 @@ int bgmac_phy_connect_direct(struct bgmac *bgmac) int err; phy_dev = fixed_phy_register(PHY_POLL, &fphy_status, NULL); - if (!phy_dev || IS_ERR(phy_dev)) { + if (IS_ERR(phy_dev)) { dev_err(bgmac->dev, "Failed to register fixed PHY device\n"); return -ENODEV; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 6469fb8a42a8..969db3c45d17 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -721,17 +721,24 @@ next_tx_int: static struct page *__bnxt_alloc_rx_page(struct bnxt *bp, dma_addr_t *mapping, struct bnxt_rx_ring_info *rxr, + unsigned int *offset, gfp_t gfp) { struct device *dev = &bp->pdev->dev; struct page *page; - page = page_pool_dev_alloc_pages(rxr->page_pool); + if (PAGE_SIZE > BNXT_RX_PAGE_SIZE) { + page = page_pool_dev_alloc_frag(rxr->page_pool, offset, + BNXT_RX_PAGE_SIZE); + } else { + page = page_pool_dev_alloc_pages(rxr->page_pool); + *offset = 0; + } if (!page) return NULL; - *mapping = dma_map_page_attrs(dev, page, 0, PAGE_SIZE, bp->rx_dir, - DMA_ATTR_WEAK_ORDERING); + *mapping = dma_map_page_attrs(dev, page, *offset, BNXT_RX_PAGE_SIZE, + bp->rx_dir, DMA_ATTR_WEAK_ORDERING); if (dma_mapping_error(dev, *mapping)) { page_pool_recycle_direct(rxr->page_pool, page); return NULL; @@ -771,15 +778,16 @@ int bnxt_alloc_rx_data(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, dma_addr_t mapping; if (BNXT_RX_PAGE_MODE(bp)) { + unsigned int offset; struct page *page = - __bnxt_alloc_rx_page(bp, &mapping, rxr, gfp); + __bnxt_alloc_rx_page(bp, &mapping, rxr, &offset, gfp); if (!page) return -ENOMEM; mapping += bp->rx_dma_offset; rx_buf->data = page; - rx_buf->data_ptr = page_address(page) + bp->rx_offset; + rx_buf->data_ptr = page_address(page) + offset + bp->rx_offset; } else { u8 *data = __bnxt_alloc_rx_frag(bp, &mapping, gfp); @@ -839,7 +847,7 @@ static inline int bnxt_alloc_rx_page(struct bnxt *bp, unsigned int offset = 0; if (BNXT_RX_PAGE_MODE(bp)) { - page = __bnxt_alloc_rx_page(bp, &mapping, rxr, gfp); + page = __bnxt_alloc_rx_page(bp, &mapping, rxr, &offset, gfp); if (!page) return -ENOMEM; @@ -986,15 +994,15 @@ static struct sk_buff *bnxt_rx_multi_page_skb(struct bnxt *bp, return NULL; } dma_addr -= bp->rx_dma_offset; - dma_unmap_page_attrs(&bp->pdev->dev, dma_addr, PAGE_SIZE, bp->rx_dir, - DMA_ATTR_WEAK_ORDERING); - skb = build_skb(page_address(page), PAGE_SIZE); + dma_unmap_page_attrs(&bp->pdev->dev, dma_addr, BNXT_RX_PAGE_SIZE, + bp->rx_dir, DMA_ATTR_WEAK_ORDERING); + skb = build_skb(data_ptr - bp->rx_offset, BNXT_RX_PAGE_SIZE); if (!skb) { page_pool_recycle_direct(rxr->page_pool, page); return NULL; } skb_mark_for_recycle(skb); - skb_reserve(skb, bp->rx_dma_offset); + skb_reserve(skb, bp->rx_offset); __skb_put(skb, len); return skb; @@ -1020,8 +1028,8 @@ static struct sk_buff *bnxt_rx_page_skb(struct bnxt *bp, return NULL; } dma_addr -= bp->rx_dma_offset; - dma_unmap_page_attrs(&bp->pdev->dev, dma_addr, PAGE_SIZE, bp->rx_dir, - DMA_ATTR_WEAK_ORDERING); + dma_unmap_page_attrs(&bp->pdev->dev, dma_addr, BNXT_RX_PAGE_SIZE, + bp->rx_dir, DMA_ATTR_WEAK_ORDERING); if (unlikely(!payload)) payload = eth_get_headlen(bp->dev, data_ptr, len); @@ -1034,7 +1042,7 @@ static struct sk_buff *bnxt_rx_page_skb(struct bnxt *bp, skb_mark_for_recycle(skb); off = (void *)data_ptr - page_address(page); - skb_add_rx_frag(skb, 0, page, off, len, PAGE_SIZE); + skb_add_rx_frag(skb, 0, page, off, len, BNXT_RX_PAGE_SIZE); memcpy(skb->data - NET_IP_ALIGN, data_ptr - NET_IP_ALIGN, payload + NET_IP_ALIGN); @@ -1169,7 +1177,7 @@ static struct sk_buff *bnxt_rx_agg_pages_skb(struct bnxt *bp, skb->data_len += total_frag_len; skb->len += total_frag_len; - skb->truesize += PAGE_SIZE * agg_bufs; + skb->truesize += BNXT_RX_PAGE_SIZE * agg_bufs; return skb; } @@ -2972,8 +2980,8 @@ skip_rx_tpa_free: rx_buf->data = NULL; if (BNXT_RX_PAGE_MODE(bp)) { mapping -= bp->rx_dma_offset; - dma_unmap_page_attrs(&pdev->dev, mapping, PAGE_SIZE, - bp->rx_dir, + dma_unmap_page_attrs(&pdev->dev, mapping, + BNXT_RX_PAGE_SIZE, bp->rx_dir, DMA_ATTR_WEAK_ORDERING); page_pool_recycle_direct(rxr->page_pool, data); } else { @@ -3241,6 +3249,8 @@ static int bnxt_alloc_rx_page_pool(struct bnxt *bp, pp.nid = dev_to_node(&bp->pdev->dev); pp.dev = &bp->pdev->dev; pp.dma_dir = DMA_BIDIRECTIONAL; + if (PAGE_SIZE > BNXT_RX_PAGE_SIZE) + pp.flags |= PP_FLAG_PAGE_FRAG; rxr->page_pool = page_pool_create(&pp); if (IS_ERR(rxr->page_pool)) { @@ -4017,26 +4027,29 @@ void bnxt_set_ring_params(struct bnxt *bp) */ int bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode) { + struct net_device *dev = bp->dev; + if (page_mode) { bp->flags &= ~BNXT_FLAG_AGG_RINGS; bp->flags |= BNXT_FLAG_RX_PAGE_MODE; - if (bp->dev->mtu > BNXT_MAX_PAGE_MODE_MTU) { + if (bp->xdp_prog->aux->xdp_has_frags) + dev->max_mtu = min_t(u16, bp->max_mtu, BNXT_MAX_MTU); + else + dev->max_mtu = + min_t(u16, bp->max_mtu, BNXT_MAX_PAGE_MODE_MTU); + if (dev->mtu > BNXT_MAX_PAGE_MODE_MTU) { bp->flags |= BNXT_FLAG_JUMBO; bp->rx_skb_func = bnxt_rx_multi_page_skb; - bp->dev->max_mtu = - min_t(u16, bp->max_mtu, BNXT_MAX_MTU); } else { bp->flags |= BNXT_FLAG_NO_AGG_RINGS; bp->rx_skb_func = bnxt_rx_page_skb; - bp->dev->max_mtu = - min_t(u16, bp->max_mtu, BNXT_MAX_PAGE_MODE_MTU); } bp->rx_dir = DMA_BIDIRECTIONAL; /* Disable LRO or GRO_HW */ - netdev_update_features(bp->dev); + netdev_update_features(dev); } else { - bp->dev->max_mtu = bp->max_mtu; + dev->max_mtu = bp->max_mtu; bp->flags &= ~BNXT_FLAG_RX_PAGE_MODE; bp->rx_dir = DMA_FROM_DEVICE; bp->rx_skb_func = bnxt_rx_skb; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c index 36d5202c0aee..aa56db138d6b 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c @@ -180,8 +180,8 @@ void bnxt_xdp_buff_init(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons, u8 *data_ptr, unsigned int len, struct xdp_buff *xdp) { + u32 buflen = BNXT_RX_PAGE_SIZE; struct bnxt_sw_rx_bd *rx_buf; - u32 buflen = PAGE_SIZE; struct pci_dev *pdev; dma_addr_t mapping; u32 offset; @@ -297,7 +297,7 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons, rx_buf = &rxr->rx_buf_ring[cons]; mapping = rx_buf->mapping - bp->rx_dma_offset; dma_unmap_page_attrs(&pdev->dev, mapping, - PAGE_SIZE, bp->rx_dir, + BNXT_RX_PAGE_SIZE, bp->rx_dir, DMA_ATTR_WEAK_ORDERING); /* if we are unable to allocate a new buffer, abort and reuse */ @@ -478,7 +478,7 @@ bnxt_xdp_build_skb(struct bnxt *bp, struct sk_buff *skb, u8 num_frags, } xdp_update_skb_shared_info(skb, num_frags, sinfo->xdp_frags_size, - PAGE_SIZE * sinfo->nr_frags, + BNXT_RX_PAGE_SIZE * sinfo->nr_frags, xdp_buff_is_frag_pfmemalloc(xdp)); return skb; } diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c index 1fe8038587ac..1779ee524dac 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmmii.c +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -608,7 +608,7 @@ static int bcmgenet_mii_pd_init(struct bcmgenet_priv *priv) }; phydev = fixed_phy_register(PHY_POLL, &fphy_status, NULL); - if (!phydev || IS_ERR(phydev)) { + if (IS_ERR(phydev)) { dev_err(kdev, "failed to register fixed PHY device\n"); return -ENODEV; } diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index abd6cc0cd641..5fb991835078 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -5070,6 +5070,9 @@ static int __maybe_unused macb_suspend(struct device *dev) unsigned int q; int err; + if (!device_may_wakeup(&bp->dev->dev)) + phy_exit(bp->sgmii_phy); + if (!netif_running(netdev)) return 0; @@ -5130,7 +5133,6 @@ static int __maybe_unused macb_suspend(struct device *dev) if (!(bp->wol & MACB_WOL_ENABLED)) { rtnl_lock(); phylink_stop(bp->phylink); - phy_exit(bp->sgmii_phy); rtnl_unlock(); spin_lock_irqsave(&bp->lock, flags); macb_reset_hw(bp); @@ -5160,6 +5162,9 @@ static int __maybe_unused macb_resume(struct device *dev) unsigned int q; int err; + if (!device_may_wakeup(&bp->dev->dev)) + phy_init(bp->sgmii_phy); + if (!netif_running(netdev)) return 0; @@ -5220,8 +5225,6 @@ static int __maybe_unused macb_resume(struct device *dev) macb_set_rx_mode(netdev); macb_restore_features(bp); rtnl_lock(); - if (!device_may_wakeup(&bp->dev->dev)) - phy_init(bp->sgmii_phy); phylink_start(bp->phylink); rtnl_unlock(); diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c index c2e7037c7ba1..7750702900fa 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c @@ -1466,7 +1466,7 @@ static void make_established(struct sock *sk, u32 snd_isn, unsigned int opt) tp->write_seq = snd_isn; tp->snd_nxt = snd_isn; tp->snd_una = snd_isn; - inet_sk(sk)->inet_id = get_random_u16(); + atomic_set(&inet_sk(sk)->inet_id, get_random_u16()); assign_rxopt(sk, opt); if (tp->rcv_wnd > (RCV_BUFSIZ_M << 10)) diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ptp.c b/drivers/net/ethernet/freescale/enetc/enetc_ptp.c index 17c097cef7d4..5243fc031058 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_ptp.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_ptp.c @@ -8,7 +8,7 @@ #include "enetc.h" int enetc_phc_index = -1; -EXPORT_SYMBOL(enetc_phc_index); +EXPORT_SYMBOL_GPL(enetc_phc_index); static struct ptp_clock_info enetc_ptp_caps = { .owner = THIS_MODULE, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c index f6ededec5a4f..69d1549e63a9 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c @@ -458,9 +458,9 @@ static void hns3_dbg_fill_content(char *content, u16 len, if (result) { if (item_len < strlen(result[i])) break; - strscpy(pos, result[i], strlen(result[i])); + memcpy(pos, result[i], strlen(result[i])); } else { - strscpy(pos, items[i].name, strlen(items[i].name)); + memcpy(pos, items[i].name, strlen(items[i].name)); } pos += item_len; len -= item_len; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 248f15dac86b..61f833d61f58 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -5854,6 +5854,9 @@ void hns3_external_lb_prepare(struct net_device *ndev, bool if_running) if (!if_running) return; + if (test_and_set_bit(HNS3_NIC_STATE_DOWN, &priv->state)) + return; + netif_carrier_off(ndev); netif_tx_disable(ndev); @@ -5882,7 +5885,16 @@ void hns3_external_lb_restore(struct net_device *ndev, bool if_running) if (!if_running) return; - hns3_nic_reset_all_ring(priv->ae_handle); + if (hns3_nic_resetting(ndev)) + return; + + if (!test_bit(HNS3_NIC_STATE_DOWN, &priv->state)) + return; + + if (hns3_nic_reset_all_ring(priv->ae_handle)) + return; + + clear_bit(HNS3_NIC_STATE_DOWN, &priv->state); for (i = 0; i < priv->vector_num; i++) hns3_vector_enable(&priv->tqp_vector[i]); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c index 726062e51293..5cb8f1818e51 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c @@ -110,9 +110,9 @@ static void hclge_dbg_fill_content(char *content, u16 len, if (result) { if (item_len < strlen(result[i])) break; - strscpy(pos, result[i], strlen(result[i])); + memcpy(pos, result[i], strlen(result[i])); } else { - strscpy(pos, items[i].name, strlen(items[i].name)); + memcpy(pos, items[i].name, strlen(items[i].name)); } pos += item_len; len -= item_len; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 50e956d6c3b2..6af2273f227c 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -72,6 +72,8 @@ static void hclge_restore_hw_table(struct hclge_dev *hdev); static void hclge_sync_promisc_mode(struct hclge_dev *hdev); static void hclge_sync_fd_table(struct hclge_dev *hdev); static void hclge_update_fec_stats(struct hclge_dev *hdev); +static int hclge_mac_link_status_wait(struct hclge_dev *hdev, int link_ret, + int wait_cnt); static struct hnae3_ae_algo ae_algo; @@ -7567,6 +7569,8 @@ static void hclge_enable_fd(struct hnae3_handle *handle, bool enable) static void hclge_cfg_mac_mode(struct hclge_dev *hdev, bool enable) { +#define HCLGE_LINK_STATUS_WAIT_CNT 3 + struct hclge_desc desc; struct hclge_config_mac_mode_cmd *req = (struct hclge_config_mac_mode_cmd *)desc.data; @@ -7591,9 +7595,15 @@ static void hclge_cfg_mac_mode(struct hclge_dev *hdev, bool enable) req->txrx_pad_fcs_loop_en = cpu_to_le32(loop_en); ret = hclge_cmd_send(&hdev->hw, &desc, 1); - if (ret) + if (ret) { dev_err(&hdev->pdev->dev, "mac enable fail, ret =%d.\n", ret); + return; + } + + if (!enable) + hclge_mac_link_status_wait(hdev, HCLGE_LINK_STATUS_DOWN, + HCLGE_LINK_STATUS_WAIT_CNT); } static int hclge_config_switch_param(struct hclge_dev *hdev, int vfid, @@ -7656,10 +7666,9 @@ static void hclge_phy_link_status_wait(struct hclge_dev *hdev, } while (++i < HCLGE_PHY_LINK_STATUS_NUM); } -static int hclge_mac_link_status_wait(struct hclge_dev *hdev, int link_ret) +static int hclge_mac_link_status_wait(struct hclge_dev *hdev, int link_ret, + int wait_cnt) { -#define HCLGE_MAC_LINK_STATUS_NUM 100 - int link_status; int i = 0; int ret; @@ -7672,13 +7681,15 @@ static int hclge_mac_link_status_wait(struct hclge_dev *hdev, int link_ret) return 0; msleep(HCLGE_LINK_STATUS_MS); - } while (++i < HCLGE_MAC_LINK_STATUS_NUM); + } while (++i < wait_cnt); return -EBUSY; } static int hclge_mac_phy_link_status_wait(struct hclge_dev *hdev, bool en, bool is_phy) { +#define HCLGE_MAC_LINK_STATUS_NUM 100 + int link_ret; link_ret = en ? HCLGE_LINK_STATUS_UP : HCLGE_LINK_STATUS_DOWN; @@ -7686,7 +7697,8 @@ static int hclge_mac_phy_link_status_wait(struct hclge_dev *hdev, bool en, if (is_phy) hclge_phy_link_status_wait(hdev, link_ret); - return hclge_mac_link_status_wait(hdev, link_ret); + return hclge_mac_link_status_wait(hdev, link_ret, + HCLGE_MAC_LINK_STATUS_NUM); } static int hclge_set_app_loopback(struct hclge_dev *hdev, bool en) diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c index 5b96cd94dcd2..0b4ec6e41eb4 100644 --- a/drivers/net/ethernet/ibm/ibmveth.c +++ b/drivers/net/ethernet/ibm/ibmveth.c @@ -203,7 +203,7 @@ static inline void ibmveth_flush_buffer(void *addr, unsigned long length) unsigned long offset; for (offset = 0; offset < length; offset += SMP_CACHE_BYTES) - asm("dcbfl %0,%1" :: "b" (addr), "r" (offset)); + asm("dcbf %0,%1,1" :: "b" (addr), "r" (offset)); } /* replenish the buffers for a pool. note that we don't need to diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index bc97f24b0827..157be4e9be4b 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -96,6 +96,8 @@ static int pending_scrq(struct ibmvnic_adapter *, static union sub_crq *ibmvnic_next_scrq(struct ibmvnic_adapter *, struct ibmvnic_sub_crq_queue *); static int ibmvnic_poll(struct napi_struct *napi, int data); +static int reset_sub_crq_queues(struct ibmvnic_adapter *adapter); +static inline void reinit_init_done(struct ibmvnic_adapter *adapter); static void send_query_map(struct ibmvnic_adapter *adapter); static int send_request_map(struct ibmvnic_adapter *, dma_addr_t, u32, u8); static int send_request_unmap(struct ibmvnic_adapter *, u8); @@ -113,6 +115,7 @@ static void ibmvnic_tx_scrq_clean_buffer(struct ibmvnic_adapter *adapter, static void free_long_term_buff(struct ibmvnic_adapter *adapter, struct ibmvnic_long_term_buff *ltb); static void ibmvnic_disable_irqs(struct ibmvnic_adapter *adapter); +static void flush_reset_queue(struct ibmvnic_adapter *adapter); struct ibmvnic_stat { char name[ETH_GSTRING_LEN]; @@ -1314,8 +1317,8 @@ static const char *adapter_state_to_string(enum vnic_state state) static int ibmvnic_login(struct net_device *netdev) { + unsigned long flags, timeout = msecs_to_jiffies(20000); struct ibmvnic_adapter *adapter = netdev_priv(netdev); - unsigned long timeout = msecs_to_jiffies(20000); int retry_count = 0; int retries = 10; bool retry; @@ -1336,11 +1339,9 @@ static int ibmvnic_login(struct net_device *netdev) if (!wait_for_completion_timeout(&adapter->init_done, timeout)) { - netdev_warn(netdev, "Login timed out, retrying...\n"); - retry = true; - adapter->init_done_rc = 0; - retry_count++; - continue; + netdev_warn(netdev, "Login timed out\n"); + adapter->login_pending = false; + goto partial_reset; } if (adapter->init_done_rc == ABORTED) { @@ -1382,10 +1383,69 @@ static int ibmvnic_login(struct net_device *netdev) "SCRQ irq initialization failed\n"); return rc; } + /* Default/timeout error handling, reset and start fresh */ } else if (adapter->init_done_rc) { netdev_warn(netdev, "Adapter login failed, init_done_rc = %d\n", adapter->init_done_rc); - return -EIO; + +partial_reset: + /* adapter login failed, so free any CRQs or sub-CRQs + * and register again before attempting to login again. + * If we don't do this then the VIOS may think that + * we are already logged in and reject any subsequent + * attempts + */ + netdev_warn(netdev, + "Freeing and re-registering CRQs before attempting to login again\n"); + retry = true; + adapter->init_done_rc = 0; + release_sub_crqs(adapter, true); + /* Much of this is similar logic as ibmvnic_probe(), + * we are essentially re-initializing communication + * with the server. We really should not run any + * resets/failovers here because this is already a form + * of reset and we do not want parallel resets occurring + */ + do { + reinit_init_done(adapter); + /* Clear any failovers we got in the previous + * pass since we are re-initializing the CRQ + */ + adapter->failover_pending = false; + release_crq_queue(adapter); + /* If we don't sleep here then we risk an + * unnecessary failover event from the VIOS. + * This is a known VIOS issue caused by a vnic + * device freeing and registering a CRQ too + * quickly. + */ + msleep(1500); + /* Avoid any resets, since we are currently + * resetting. + */ + spin_lock_irqsave(&adapter->rwi_lock, flags); + flush_reset_queue(adapter); + spin_unlock_irqrestore(&adapter->rwi_lock, + flags); + + rc = init_crq_queue(adapter); + if (rc) { + netdev_err(netdev, "login recovery: init CRQ failed %d\n", + rc); + return -EIO; + } + + rc = ibmvnic_reset_init(adapter, false); + if (rc) + netdev_err(netdev, "login recovery: Reset init failed %d\n", + rc); + /* IBMVNIC_CRQ_INIT will return EAGAIN if it + * fails, since ibmvnic_reset_init will free + * irq's in failure, we won't be able to receive + * new CRQs so we need to keep trying. probe() + * handles this similarly. + */ + } while (rc == -EAGAIN && retry_count++ < retries); } } while (retry); @@ -1397,12 +1457,22 @@ static int ibmvnic_login(struct net_device *netdev) static void release_login_buffer(struct ibmvnic_adapter *adapter) { + if (!adapter->login_buf) + return; + + dma_unmap_single(&adapter->vdev->dev, adapter->login_buf_token, + adapter->login_buf_sz, DMA_TO_DEVICE); kfree(adapter->login_buf); adapter->login_buf = NULL; } static void release_login_rsp_buffer(struct ibmvnic_adapter *adapter) { + if (!adapter->login_rsp_buf) + return; + + dma_unmap_single(&adapter->vdev->dev, adapter->login_rsp_buf_token, + adapter->login_rsp_buf_sz, DMA_FROM_DEVICE); kfree(adapter->login_rsp_buf); adapter->login_rsp_buf = NULL; } @@ -4626,11 +4696,14 @@ static int send_login(struct ibmvnic_adapter *adapter) if (rc) { adapter->login_pending = false; netdev_err(adapter->netdev, "Failed to send login, rc=%d\n", rc); - goto buf_rsp_map_failed; + goto buf_send_failed; } return 0; +buf_send_failed: + dma_unmap_single(dev, rsp_buffer_token, rsp_buffer_size, + DMA_FROM_DEVICE); buf_rsp_map_failed: kfree(login_rsp_buffer); adapter->login_rsp_buf = NULL; @@ -5192,6 +5265,7 @@ static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq, int num_tx_pools; int num_rx_pools; u64 *size_array; + u32 rsp_len; int i; /* CHECK: Test/set of login_pending does not need to be atomic @@ -5203,11 +5277,6 @@ static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq, } adapter->login_pending = false; - dma_unmap_single(dev, adapter->login_buf_token, adapter->login_buf_sz, - DMA_TO_DEVICE); - dma_unmap_single(dev, adapter->login_rsp_buf_token, - adapter->login_rsp_buf_sz, DMA_FROM_DEVICE); - /* If the number of queues requested can't be allocated by the * server, the login response will return with code 1. We will need * to resend the login buffer with fewer queues requested. @@ -5243,6 +5312,23 @@ static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq, ibmvnic_reset(adapter, VNIC_RESET_FATAL); return -EIO; } + + rsp_len = be32_to_cpu(login_rsp->len); + if (be32_to_cpu(login->login_rsp_len) < rsp_len || + rsp_len <= be32_to_cpu(login_rsp->off_txsubm_subcrqs) || + rsp_len <= be32_to_cpu(login_rsp->off_rxadd_subcrqs) || + rsp_len <= be32_to_cpu(login_rsp->off_rxadd_buff_size) || + rsp_len <= be32_to_cpu(login_rsp->off_supp_tx_desc)) { + /* This can happen if a login request times out and there are + * 2 outstanding login requests sent, the LOGIN_RSP crq + * could have been for the older login request. So we are + * parsing the newer response buffer which may be incomplete + */ + dev_err(dev, "FATAL: Login rsp offsets/lengths invalid\n"); + ibmvnic_reset(adapter, VNIC_RESET_FATAL); + return -EIO; + } + size_array = (u64 *)((u8 *)(adapter->login_rsp_buf) + be32_to_cpu(adapter->login_rsp_buf->off_rxadd_buff_size)); /* variable buffer sizes are not supported, so just read the diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 0e01b1927c1c..08ccf0024ce1 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -2615,7 +2615,7 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) retval = i40e_correct_mac_vlan_filters (vsi, &tmp_add_list, &tmp_del_list, vlan_filters); - else + else if (pf->vf) retval = i40e_correct_vf_mac_vlan_filters (vsi, &tmp_add_list, &tmp_del_list, vlan_filters, pf->vf[vsi->vf_id].trusted); @@ -2788,7 +2788,8 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) } /* if the VF is not trusted do not do promisc */ - if ((vsi->type == I40E_VSI_SRIOV) && !pf->vf[vsi->vf_id].trusted) { + if (vsi->type == I40E_VSI_SRIOV && pf->vf && + !pf->vf[vsi->vf_id].trusted) { clear_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state); goto out; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_nvm.c b/drivers/net/ethernet/intel/i40e/i40e_nvm.c index 17e3f26eee4a..779ba907009a 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_nvm.c +++ b/drivers/net/ethernet/intel/i40e/i40e_nvm.c @@ -210,11 +210,11 @@ read_nvm_exit: * @hw: pointer to the HW structure. * @module_pointer: module pointer location in words from the NVM beginning * @offset: offset in words from module start - * @words: number of words to write - * @data: buffer with words to write to the Shadow RAM + * @words: number of words to read + * @data: buffer with words to read to the Shadow RAM * @last_command: tells the AdminQ that this is the last command * - * Writes a 16 bit words buffer to the Shadow RAM using the admin command. + * Reads a 16 bit words buffer to the Shadow RAM using the admin command. **/ static int i40e_read_nvm_aq(struct i40e_hw *hw, u8 module_pointer, u32 offset, @@ -234,18 +234,18 @@ static int i40e_read_nvm_aq(struct i40e_hw *hw, */ if ((offset + words) > hw->nvm.sr_size) i40e_debug(hw, I40E_DEBUG_NVM, - "NVM write error: offset %d beyond Shadow RAM limit %d\n", + "NVM read error: offset %d beyond Shadow RAM limit %d\n", (offset + words), hw->nvm.sr_size); else if (words > I40E_SR_SECTOR_SIZE_IN_WORDS) - /* We can write only up to 4KB (one sector), in one AQ write */ + /* We can read only up to 4KB (one sector), in one AQ write */ i40e_debug(hw, I40E_DEBUG_NVM, - "NVM write fail error: tried to write %d words, limit is %d.\n", + "NVM read fail error: tried to read %d words, limit is %d.\n", words, I40E_SR_SECTOR_SIZE_IN_WORDS); else if (((offset + (words - 1)) / I40E_SR_SECTOR_SIZE_IN_WORDS) != (offset / I40E_SR_SECTOR_SIZE_IN_WORDS)) - /* A single write cannot spread over two sectors */ + /* A single read cannot spread over two sectors */ i40e_debug(hw, I40E_DEBUG_NVM, - "NVM write error: cannot spread over two sectors in a single write offset=%d words=%d\n", + "NVM read error: cannot spread over two sectors in a single read offset=%d words=%d\n", offset, words); else ret_code = i40e_aq_read_nvm(hw, module_pointer, diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index fd6d6f6263f6..fe912b1c468e 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -1289,6 +1289,7 @@ iavf_add_fdir_fltr_info(struct iavf_adapter *adapter, struct ethtool_rx_flow_spe fltr->ip_mask.src_port = fsp->m_u.tcp_ip4_spec.psrc; fltr->ip_mask.dst_port = fsp->m_u.tcp_ip4_spec.pdst; fltr->ip_mask.tos = fsp->m_u.tcp_ip4_spec.tos; + fltr->ip_ver = 4; break; case AH_V4_FLOW: case ESP_V4_FLOW: @@ -1300,6 +1301,7 @@ iavf_add_fdir_fltr_info(struct iavf_adapter *adapter, struct ethtool_rx_flow_spe fltr->ip_mask.v4_addrs.dst_ip = fsp->m_u.ah_ip4_spec.ip4dst; fltr->ip_mask.spi = fsp->m_u.ah_ip4_spec.spi; fltr->ip_mask.tos = fsp->m_u.ah_ip4_spec.tos; + fltr->ip_ver = 4; break; case IPV4_USER_FLOW: fltr->ip_data.v4_addrs.src_ip = fsp->h_u.usr_ip4_spec.ip4src; @@ -1312,6 +1314,7 @@ iavf_add_fdir_fltr_info(struct iavf_adapter *adapter, struct ethtool_rx_flow_spe fltr->ip_mask.l4_header = fsp->m_u.usr_ip4_spec.l4_4_bytes; fltr->ip_mask.tos = fsp->m_u.usr_ip4_spec.tos; fltr->ip_mask.proto = fsp->m_u.usr_ip4_spec.proto; + fltr->ip_ver = 4; break; case TCP_V6_FLOW: case UDP_V6_FLOW: @@ -1330,6 +1333,7 @@ iavf_add_fdir_fltr_info(struct iavf_adapter *adapter, struct ethtool_rx_flow_spe fltr->ip_mask.src_port = fsp->m_u.tcp_ip6_spec.psrc; fltr->ip_mask.dst_port = fsp->m_u.tcp_ip6_spec.pdst; fltr->ip_mask.tclass = fsp->m_u.tcp_ip6_spec.tclass; + fltr->ip_ver = 6; break; case AH_V6_FLOW: case ESP_V6_FLOW: @@ -1345,6 +1349,7 @@ iavf_add_fdir_fltr_info(struct iavf_adapter *adapter, struct ethtool_rx_flow_spe sizeof(struct in6_addr)); fltr->ip_mask.spi = fsp->m_u.ah_ip6_spec.spi; fltr->ip_mask.tclass = fsp->m_u.ah_ip6_spec.tclass; + fltr->ip_ver = 6; break; case IPV6_USER_FLOW: memcpy(&fltr->ip_data.v6_addrs.src_ip, fsp->h_u.usr_ip6_spec.ip6src, @@ -1361,6 +1366,7 @@ iavf_add_fdir_fltr_info(struct iavf_adapter *adapter, struct ethtool_rx_flow_spe fltr->ip_mask.l4_header = fsp->m_u.usr_ip6_spec.l4_4_bytes; fltr->ip_mask.tclass = fsp->m_u.usr_ip6_spec.tclass; fltr->ip_mask.proto = fsp->m_u.usr_ip6_spec.l4_proto; + fltr->ip_ver = 6; break; case ETHER_FLOW: fltr->eth_data.etype = fsp->h_u.ether_spec.h_proto; @@ -1371,6 +1377,10 @@ iavf_add_fdir_fltr_info(struct iavf_adapter *adapter, struct ethtool_rx_flow_spe return -EINVAL; } + err = iavf_validate_fdir_fltr_masks(adapter, fltr); + if (err) + return err; + if (iavf_fdir_is_dup_fltr(adapter, fltr)) return -EEXIST; @@ -1401,14 +1411,15 @@ static int iavf_add_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx if (fsp->flow_type & FLOW_MAC_EXT) return -EINVAL; + spin_lock_bh(&adapter->fdir_fltr_lock); if (adapter->fdir_active_fltr >= IAVF_MAX_FDIR_FILTERS) { + spin_unlock_bh(&adapter->fdir_fltr_lock); dev_err(&adapter->pdev->dev, "Unable to add Flow Director filter because VF reached the limit of max allowed filters (%u)\n", IAVF_MAX_FDIR_FILTERS); return -ENOSPC; } - spin_lock_bh(&adapter->fdir_fltr_lock); if (iavf_find_fdir_fltr_by_loc(adapter, fsp->location)) { dev_err(&adapter->pdev->dev, "Failed to add Flow Director filter, it already exists\n"); spin_unlock_bh(&adapter->fdir_fltr_lock); @@ -1781,7 +1792,9 @@ static int iavf_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd, case ETHTOOL_GRXCLSRLCNT: if (!FDIR_FLTR_SUPPORT(adapter)) break; + spin_lock_bh(&adapter->fdir_fltr_lock); cmd->rule_cnt = adapter->fdir_active_fltr; + spin_unlock_bh(&adapter->fdir_fltr_lock); cmd->data = IAVF_MAX_FDIR_FILTERS; ret = 0; break; diff --git a/drivers/net/ethernet/intel/iavf/iavf_fdir.c b/drivers/net/ethernet/intel/iavf/iavf_fdir.c index 6146203efd84..03e774bd2a5b 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_fdir.c +++ b/drivers/net/ethernet/intel/iavf/iavf_fdir.c @@ -18,6 +18,79 @@ static const struct in6_addr ipv6_addr_full_mask = { } }; +static const struct in6_addr ipv6_addr_zero_mask = { + .in6_u = { + .u6_addr8 = { + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + } + } +}; + +/** + * iavf_validate_fdir_fltr_masks - validate Flow Director filter fields masks + * @adapter: pointer to the VF adapter structure + * @fltr: Flow Director filter data structure + * + * Returns 0 if all masks of packet fields are either full or empty. Returns + * error on at least one partial mask. + */ +int iavf_validate_fdir_fltr_masks(struct iavf_adapter *adapter, + struct iavf_fdir_fltr *fltr) +{ + if (fltr->eth_mask.etype && fltr->eth_mask.etype != htons(U16_MAX)) + goto partial_mask; + + if (fltr->ip_ver == 4) { + if (fltr->ip_mask.v4_addrs.src_ip && + fltr->ip_mask.v4_addrs.src_ip != htonl(U32_MAX)) + goto partial_mask; + + if (fltr->ip_mask.v4_addrs.dst_ip && + fltr->ip_mask.v4_addrs.dst_ip != htonl(U32_MAX)) + goto partial_mask; + + if (fltr->ip_mask.tos && fltr->ip_mask.tos != U8_MAX) + goto partial_mask; + } else if (fltr->ip_ver == 6) { + if (memcmp(&fltr->ip_mask.v6_addrs.src_ip, &ipv6_addr_zero_mask, + sizeof(struct in6_addr)) && + memcmp(&fltr->ip_mask.v6_addrs.src_ip, &ipv6_addr_full_mask, + sizeof(struct in6_addr))) + goto partial_mask; + + if (memcmp(&fltr->ip_mask.v6_addrs.dst_ip, &ipv6_addr_zero_mask, + sizeof(struct in6_addr)) && + memcmp(&fltr->ip_mask.v6_addrs.dst_ip, &ipv6_addr_full_mask, + sizeof(struct in6_addr))) + goto partial_mask; + + if (fltr->ip_mask.tclass && fltr->ip_mask.tclass != U8_MAX) + goto partial_mask; + } + + if (fltr->ip_mask.proto && fltr->ip_mask.proto != U8_MAX) + goto partial_mask; + + if (fltr->ip_mask.src_port && fltr->ip_mask.src_port != htons(U16_MAX)) + goto partial_mask; + + if (fltr->ip_mask.dst_port && fltr->ip_mask.dst_port != htons(U16_MAX)) + goto partial_mask; + + if (fltr->ip_mask.spi && fltr->ip_mask.spi != htonl(U32_MAX)) + goto partial_mask; + + if (fltr->ip_mask.l4_header && + fltr->ip_mask.l4_header != htonl(U32_MAX)) + goto partial_mask; + + return 0; + +partial_mask: + dev_err(&adapter->pdev->dev, "Failed to add Flow Director filter, partial masks are not supported\n"); + return -EOPNOTSUPP; +} + /** * iavf_pkt_udp_no_pay_len - the length of UDP packet without payload * @fltr: Flow Director filter data structure @@ -263,8 +336,6 @@ iavf_fill_fdir_ip4_hdr(struct iavf_fdir_fltr *fltr, VIRTCHNL_ADD_PROTO_HDR_FIELD_BIT(hdr, IPV4, DST); } - fltr->ip_ver = 4; - return 0; } @@ -309,8 +380,6 @@ iavf_fill_fdir_ip6_hdr(struct iavf_fdir_fltr *fltr, VIRTCHNL_ADD_PROTO_HDR_FIELD_BIT(hdr, IPV6, DST); } - fltr->ip_ver = 6; - return 0; } @@ -722,7 +791,9 @@ void iavf_print_fdir_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *f bool iavf_fdir_is_dup_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr) { struct iavf_fdir_fltr *tmp; + bool ret = false; + spin_lock_bh(&adapter->fdir_fltr_lock); list_for_each_entry(tmp, &adapter->fdir_list_head, list) { if (tmp->flow_type != fltr->flow_type) continue; @@ -732,11 +803,14 @@ bool iavf_fdir_is_dup_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr * !memcmp(&tmp->ip_data, &fltr->ip_data, sizeof(fltr->ip_data)) && !memcmp(&tmp->ext_data, &fltr->ext_data, - sizeof(fltr->ext_data))) - return true; + sizeof(fltr->ext_data))) { + ret = true; + break; + } } + spin_unlock_bh(&adapter->fdir_fltr_lock); - return false; + return ret; } /** diff --git a/drivers/net/ethernet/intel/iavf/iavf_fdir.h b/drivers/net/ethernet/intel/iavf/iavf_fdir.h index 33c55c366315..9eb9f73f6adf 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_fdir.h +++ b/drivers/net/ethernet/intel/iavf/iavf_fdir.h @@ -110,6 +110,8 @@ struct iavf_fdir_fltr { struct virtchnl_fdir_add vc_add_msg; }; +int iavf_validate_fdir_fltr_masks(struct iavf_adapter *adapter, + struct iavf_fdir_fltr *fltr); int iavf_fill_fdir_add_msg(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr); void iavf_print_fdir_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr); bool iavf_fdir_is_dup_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr); diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index e864634d66bc..818eca6aa4a4 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -396,7 +396,8 @@ static int ice_setup_rx_ctx(struct ice_rx_ring *ring) /* Receive Packet Data Buffer Size. * The Packet Data Buffer Size is defined in 128 byte units. */ - rlan_ctx.dbuf = ring->rx_buf_len >> ICE_RLAN_CTX_DBUF_S; + rlan_ctx.dbuf = DIV_ROUND_UP(ring->rx_buf_len, + BIT_ULL(ICE_RLAN_CTX_DBUF_S)); /* use 32 byte descriptors */ rlan_ctx.dsize = 1; diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c index f9f15acae90a..2ffe5708a045 100644 --- a/drivers/net/ethernet/intel/ice/ice_eswitch.c +++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c @@ -562,6 +562,12 @@ ice_eswitch_mode_set(struct devlink *devlink, u16 mode, break; case DEVLINK_ESWITCH_MODE_SWITCHDEV: { + if (ice_is_adq_active(pf)) { + dev_err(ice_pf_to_dev(pf), "Couldn't change eswitch mode to switchdev - ADQ is active. Delete ADQ configs and try again, e.g. tc qdisc del dev $PF root"); + NL_SET_ERR_MSG_MOD(extack, "Couldn't change eswitch mode to switchdev - ADQ is active. Delete ADQ configs and try again, e.g. tc qdisc del dev $PF root"); + return -EOPNOTSUPP; + } + dev_info(ice_pf_to_dev(pf), "PF %d changed eswitch mode to switchdev", pf->hw.pf_id); NL_SET_ERR_MSG_MOD(extack, "Changed eswitch mode to switchdev"); diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 8f77088900e9..7a00d297be3a 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -8777,6 +8777,7 @@ ice_setup_tc(struct net_device *netdev, enum tc_setup_type type, { struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_pf *pf = np->vsi->back; + bool locked = false; int err; switch (type) { @@ -8786,10 +8787,32 @@ ice_setup_tc(struct net_device *netdev, enum tc_setup_type type, ice_setup_tc_block_cb, np, np, true); case TC_SETUP_QDISC_MQPRIO: + if (ice_is_eswitch_mode_switchdev(pf)) { + netdev_err(netdev, "TC MQPRIO offload not supported, switchdev is enabled\n"); + return -EOPNOTSUPP; + } + + if (pf->adev) { + mutex_lock(&pf->adev_mutex); + device_lock(&pf->adev->dev); + locked = true; + if (pf->adev->dev.driver) { + netdev_err(netdev, "Cannot change qdisc when RDMA is active\n"); + err = -EBUSY; + goto adev_unlock; + } + } + /* setup traffic classifier for receive side */ mutex_lock(&pf->tc_mutex); err = ice_setup_tc_mqprio_qdisc(netdev, type_data); mutex_unlock(&pf->tc_mutex); + +adev_unlock: + if (locked) { + device_unlock(&pf->adev->dev); + mutex_unlock(&pf->adev_mutex); + } return err; default: return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c index b8c31bf721ad..b719e9a771e3 100644 --- a/drivers/net/ethernet/intel/ice/ice_sriov.c +++ b/drivers/net/ethernet/intel/ice/ice_sriov.c @@ -1240,7 +1240,7 @@ int ice_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool ena) if (!vf) return -EINVAL; - ret = ice_check_vf_ready_for_reset(vf); + ret = ice_check_vf_ready_for_cfg(vf); if (ret) goto out_put_vf; @@ -1355,7 +1355,7 @@ int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) goto out_put_vf; } - ret = ice_check_vf_ready_for_reset(vf); + ret = ice_check_vf_ready_for_cfg(vf); if (ret) goto out_put_vf; @@ -1409,7 +1409,7 @@ int ice_set_vf_trust(struct net_device *netdev, int vf_id, bool trusted) return -EOPNOTSUPP; } - ret = ice_check_vf_ready_for_reset(vf); + ret = ice_check_vf_ready_for_cfg(vf); if (ret) goto out_put_vf; @@ -1722,7 +1722,7 @@ ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos, if (!vf) return -EINVAL; - ret = ice_check_vf_ready_for_reset(vf); + ret = ice_check_vf_ready_for_cfg(vf); if (ret) goto out_put_vf; diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c index 71047fc34139..9dbe6e9bb1f7 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c @@ -186,25 +186,6 @@ int ice_check_vf_ready_for_cfg(struct ice_vf *vf) } /** - * ice_check_vf_ready_for_reset - check if VF is ready to be reset - * @vf: VF to check if it's ready to be reset - * - * The purpose of this function is to ensure that the VF is not in reset, - * disabled, and is both initialized and active, thus enabling us to safely - * initialize another reset. - */ -int ice_check_vf_ready_for_reset(struct ice_vf *vf) -{ - int ret; - - ret = ice_check_vf_ready_for_cfg(vf); - if (!ret && !test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) - ret = -EAGAIN; - - return ret; -} - -/** * ice_trigger_vf_reset - Reset a VF on HW * @vf: pointer to the VF structure * @is_vflr: true if VFLR was issued, false if not @@ -588,11 +569,17 @@ int ice_reset_vf(struct ice_vf *vf, u32 flags) return 0; } + if (flags & ICE_VF_RESET_LOCK) + mutex_lock(&vf->cfg_lock); + else + lockdep_assert_held(&vf->cfg_lock); + if (ice_is_vf_disabled(vf)) { vsi = ice_get_vf_vsi(vf); if (!vsi) { dev_dbg(dev, "VF is already removed\n"); - return -EINVAL; + err = -EINVAL; + goto out_unlock; } ice_vsi_stop_lan_tx_rings(vsi, ICE_NO_RESET, vf->vf_id); @@ -601,14 +588,9 @@ int ice_reset_vf(struct ice_vf *vf, u32 flags) dev_dbg(dev, "VF is already disabled, there is no need for resetting it, telling VM, all is fine %d\n", vf->vf_id); - return 0; + goto out_unlock; } - if (flags & ICE_VF_RESET_LOCK) - mutex_lock(&vf->cfg_lock); - else - lockdep_assert_held(&vf->cfg_lock); - /* Set VF disable bit state here, before triggering reset */ set_bit(ICE_VF_STATE_DIS, vf->vf_states); ice_trigger_vf_reset(vf, flags & ICE_VF_RESET_VFLR, false); diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.h b/drivers/net/ethernet/intel/ice/ice_vf_lib.h index e5bed8572462..9f7fcd8e5714 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.h @@ -214,7 +214,6 @@ u16 ice_get_num_vfs(struct ice_pf *pf); struct ice_vsi *ice_get_vf_vsi(struct ice_vf *vf); bool ice_is_vf_disabled(struct ice_vf *vf); int ice_check_vf_ready_for_cfg(struct ice_vf *vf); -int ice_check_vf_ready_for_reset(struct ice_vf *vf); void ice_set_vf_state_dis(struct ice_vf *vf); bool ice_is_any_vf_in_unicast_promisc(struct ice_pf *pf); void diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c index ef3c709d6a75..2b4c791b6cba 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c @@ -3722,7 +3722,6 @@ error_handler: ice_vc_notify_vf_link_state(vf); break; case VIRTCHNL_OP_RESET_VF: - clear_bit(ICE_VF_STATE_ACTIVE, vf->vf_states); ops->reset_vf(vf); break; case VIRTCHNL_OP_ADD_ETH_ADDR: diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index 15e57460e19e..07171e574e7d 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -1404,18 +1404,6 @@ void igb_ptp_init(struct igb_adapter *adapter) return; } - spin_lock_init(&adapter->tmreg_lock); - INIT_WORK(&adapter->ptp_tx_work, igb_ptp_tx_work); - - if (adapter->ptp_flags & IGB_PTP_OVERFLOW_CHECK) - INIT_DELAYED_WORK(&adapter->ptp_overflow_work, - igb_ptp_overflow_check); - - adapter->tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE; - adapter->tstamp_config.tx_type = HWTSTAMP_TX_OFF; - - igb_ptp_reset(adapter); - adapter->ptp_clock = ptp_clock_register(&adapter->ptp_caps, &adapter->pdev->dev); if (IS_ERR(adapter->ptp_clock)) { @@ -1425,6 +1413,18 @@ void igb_ptp_init(struct igb_adapter *adapter) dev_info(&adapter->pdev->dev, "added PHC on %s\n", adapter->netdev->name); adapter->ptp_flags |= IGB_PTP_ENABLED; + + spin_lock_init(&adapter->tmreg_lock); + INIT_WORK(&adapter->ptp_tx_work, igb_ptp_tx_work); + + if (adapter->ptp_flags & IGB_PTP_OVERFLOW_CHECK) + INIT_DELAYED_WORK(&adapter->ptp_overflow_work, + igb_ptp_overflow_check); + + adapter->tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE; + adapter->tstamp_config.tx_type = HWTSTAMP_TX_OFF; + + igb_ptp_reset(adapter); } } diff --git a/drivers/net/ethernet/intel/igc/igc_base.h b/drivers/net/ethernet/intel/igc/igc_base.h index ce530f5fd7bd..52849f5e8048 100644 --- a/drivers/net/ethernet/intel/igc/igc_base.h +++ b/drivers/net/ethernet/intel/igc/igc_base.h @@ -85,8 +85,13 @@ union igc_adv_rx_desc { #define IGC_RXDCTL_SWFLUSH 0x04000000 /* Receive Software Flush */ /* SRRCTL bit definitions */ -#define IGC_SRRCTL_BSIZEPKT_SHIFT 10 /* Shift _right_ */ -#define IGC_SRRCTL_BSIZEHDRSIZE_SHIFT 2 /* Shift _left_ */ -#define IGC_SRRCTL_DESCTYPE_ADV_ONEBUF 0x02000000 +#define IGC_SRRCTL_BSIZEPKT_MASK GENMASK(6, 0) +#define IGC_SRRCTL_BSIZEPKT(x) FIELD_PREP(IGC_SRRCTL_BSIZEPKT_MASK, \ + (x) / 1024) /* in 1 KB resolution */ +#define IGC_SRRCTL_BSIZEHDR_MASK GENMASK(13, 8) +#define IGC_SRRCTL_BSIZEHDR(x) FIELD_PREP(IGC_SRRCTL_BSIZEHDR_MASK, \ + (x) / 64) /* in 64 bytes resolution */ +#define IGC_SRRCTL_DESCTYPE_MASK GENMASK(27, 25) +#define IGC_SRRCTL_DESCTYPE_ADV_ONEBUF FIELD_PREP(IGC_SRRCTL_DESCTYPE_MASK, 1) #endif /* _IGC_BASE_H */ diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h index dbfa4b9dee06..90ca01889cd8 100644 --- a/drivers/net/ethernet/intel/igc/igc_defines.h +++ b/drivers/net/ethernet/intel/igc/igc_defines.h @@ -536,7 +536,7 @@ #define IGC_PTM_CTRL_START_NOW BIT(29) /* Start PTM Now */ #define IGC_PTM_CTRL_EN BIT(30) /* Enable PTM */ #define IGC_PTM_CTRL_TRIG BIT(31) /* PTM Cycle trigger */ -#define IGC_PTM_CTRL_SHRT_CYC(usec) (((usec) & 0x2f) << 2) +#define IGC_PTM_CTRL_SHRT_CYC(usec) (((usec) & 0x3f) << 2) #define IGC_PTM_CTRL_PTM_TO(usec) (((usec) & 0xff) << 8) #define IGC_PTM_SHORT_CYC_DEFAULT 10 /* Default Short/interrupted cycle interval */ diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index d877dc0f87f7..2f3947cf513b 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -675,8 +675,11 @@ static void igc_configure_rx_ring(struct igc_adapter *adapter, else buf_size = IGC_RXBUFFER_2048; - srrctl = IGC_RX_HDR_LEN << IGC_SRRCTL_BSIZEHDRSIZE_SHIFT; - srrctl |= buf_size >> IGC_SRRCTL_BSIZEPKT_SHIFT; + srrctl = rd32(IGC_SRRCTL(reg_idx)); + srrctl &= ~(IGC_SRRCTL_BSIZEPKT_MASK | IGC_SRRCTL_BSIZEHDR_MASK | + IGC_SRRCTL_DESCTYPE_MASK); + srrctl |= IGC_SRRCTL_BSIZEHDR(IGC_RX_HDR_LEN); + srrctl |= IGC_SRRCTL_BSIZEPKT(buf_size); srrctl |= IGC_SRRCTL_DESCTYPE_ADV_ONEBUF; wr32(IGC_SRRCTL(reg_idx), srrctl); diff --git a/drivers/net/ethernet/korina.c b/drivers/net/ethernet/korina.c index 2b9335cb4bb3..8537578e1cf1 100644 --- a/drivers/net/ethernet/korina.c +++ b/drivers/net/ethernet/korina.c @@ -1302,11 +1302,10 @@ static int korina_probe(struct platform_device *pdev) else if (of_get_ethdev_address(pdev->dev.of_node, dev) < 0) eth_hw_addr_random(dev); - clk = devm_clk_get_optional(&pdev->dev, "mdioclk"); + clk = devm_clk_get_optional_enabled(&pdev->dev, "mdioclk"); if (IS_ERR(clk)) return PTR_ERR(clk); if (clk) { - clk_prepare_enable(clk); lp->mii_clock_freq = clk_get_rate(clk); } else { lp->mii_clock_freq = 200000000; /* max possible input clk */ diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c index 8979dd05e873..d4ec46d1c8cf 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c @@ -1121,12 +1121,12 @@ static void octep_remove(struct pci_dev *pdev) if (!oct) return; - cancel_work_sync(&oct->tx_timeout_task); cancel_work_sync(&oct->ctrl_mbox_task); netdev = oct->netdev; if (netdev->reg_state == NETREG_REGISTERED) unregister_netdev(netdev); + cancel_work_sync(&oct->tx_timeout_task); octep_device_cleanup(oct); pci_release_mem_regions(pdev); free_netdev(netdev); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index 705325431dec..5541e284cd3f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -4005,9 +4005,10 @@ rx_frscfg: if (link < 0) return NIX_AF_ERR_RX_LINK_INVALID; - nix_find_link_frs(rvu, req, pcifunc); linkcfg: + nix_find_link_frs(rvu, req, pcifunc); + cfg = rvu_read64(rvu, blkaddr, NIX_AF_RX_LINKX_CFG(link)); cfg = (cfg & ~(0xFFFFULL << 16)) | ((u64)req->maxlen << 16); if (req->update_minlen) diff --git a/drivers/net/ethernet/marvell/prestera/prestera_pci.c b/drivers/net/ethernet/marvell/prestera/prestera_pci.c index 59470d99f522..a37dbbda8de3 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_pci.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_pci.c @@ -702,7 +702,8 @@ pick_fw_ver: err = request_firmware_direct(&fw->bin, fw_path, fw->dev.dev); if (err) { - if (ver_maj == PRESTERA_SUPP_FW_MAJ_VER) { + if (ver_maj != PRESTERA_PREV_FW_MAJ_VER || + ver_min != PRESTERA_PREV_FW_MIN_VER) { ver_maj = PRESTERA_PREV_FW_MAJ_VER; ver_min = PRESTERA_PREV_FW_MIN_VER; diff --git a/drivers/net/ethernet/marvell/prestera/prestera_router.c b/drivers/net/ethernet/marvell/prestera/prestera_router.c index a9a1028cb17b..de317179a7dc 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_router.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_router.c @@ -166,11 +166,11 @@ prestera_util_neigh2nc_key(struct prestera_switch *sw, struct neighbour *n, static bool __prestera_fi_is_direct(struct fib_info *fi) { - struct fib_nh *fib_nh; + struct fib_nh_common *fib_nhc; if (fib_info_num_path(fi) == 1) { - fib_nh = fib_info_nh(fi, 0); - if (fib_nh->fib_nh_gw_family == AF_UNSPEC) + fib_nhc = fib_info_nhc(fi, 0); + if (fib_nhc->nhc_gw_family == AF_UNSPEC) return true; } @@ -261,7 +261,7 @@ static bool __prestera_util_kern_n_is_reachable_v4(u32 tb_id, __be32 *addr, struct net_device *dev) { - struct fib_nh *fib_nh; + struct fib_nh_common *fib_nhc; struct fib_result res; bool reachable; @@ -269,8 +269,8 @@ __prestera_util_kern_n_is_reachable_v4(u32 tb_id, __be32 *addr, if (!prestera_util_kern_get_route(&res, tb_id, addr)) if (prestera_fi_is_direct(res.fi)) { - fib_nh = fib_info_nh(res.fi, 0); - if (dev == fib_nh->fib_nh_dev) + fib_nhc = fib_info_nhc(res.fi, 0); + if (dev == fib_nhc->nhc_dev) reachable = true; } @@ -324,7 +324,7 @@ prestera_kern_fib_info_nhc(struct fib_notifier_info *info, int n) if (info->family == AF_INET) { fen4_info = container_of(info, struct fib_entry_notifier_info, info); - return &fib_info_nh(fen4_info->fi, n)->nh_common; + return fib_info_nhc(fen4_info->fi, n); } else if (info->family == AF_INET6) { fen6_info = container_of(info, struct fib6_entry_notifier_info, info); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c index 6859f1c1a831..c4a84f0a3b73 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c @@ -58,7 +58,9 @@ static int mlx5e_ipsec_remove_trailer(struct sk_buff *skb, struct xfrm_state *x) trailer_len = alen + plen + 2; - pskb_trim(skb, skb->len - trailer_len); + ret = pskb_trim(skb, skb->len - trailer_len); + if (unlikely(ret)) + return ret; if (skb->protocol == htons(ETH_P_IP)) { ipv4hdr->tot_len = htons(ntohs(ipv4hdr->tot_len) - trailer_len); ip_send_check(ipv4hdr); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_fs.c index 5b658a5588c6..6ecf0bf2366a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_fs.c @@ -160,6 +160,7 @@ static int macsec_fs_tx_create_crypto_table_groups(struct mlx5e_flow_table *ft) if (!in) { kfree(ft->g); + ft->g = NULL; return -ENOMEM; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c index 0ae1865086ff..dc0a0a27ac84 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c @@ -136,6 +136,16 @@ static void arfs_del_rules(struct mlx5e_flow_steering *fs); int mlx5e_arfs_disable(struct mlx5e_flow_steering *fs) { + /* Moving to switchdev mode, fs->arfs is freed by mlx5e_nic_profile + * cleanup_rx callback and it is not recreated when + * mlx5e_uplink_rep_profile is loaded as mlx5e_create_flow_steering() + * is not called by the uplink_rep profile init_rx callback. Thus, if + * ntuple is set, moving to switchdev flow will enter this function + * with fs->arfs nullified. + */ + if (!mlx5e_fs_get_arfs(fs)) + return 0; + arfs_del_rules(fs); return arfs_disable(fs); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 9bd1a93a512d..bd895ef341a0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -912,7 +912,7 @@ static int mlx5e_init_rep_rx(struct mlx5e_priv *priv) err = mlx5e_open_drop_rq(priv, &priv->drop_rq); if (err) { mlx5_core_err(mdev, "open drop rq failed, %d\n", err); - return err; + goto err_rx_res_free; } err = mlx5e_rx_res_init(priv->rx_res, priv->mdev, 0, @@ -946,6 +946,7 @@ err_destroy_rx_res: mlx5e_rx_res_destroy(priv->rx_res); err_close_drop_rq: mlx5e_close_drop_rq(&priv->drop_rq); +err_rx_res_free: mlx5e_rx_res_free(priv->rx_res); priv->rx_res = NULL; err_free_fs: @@ -1039,6 +1040,10 @@ static int mlx5e_init_rep_tx(struct mlx5e_priv *priv) return err; } + err = mlx5e_rep_neigh_init(rpriv); + if (err) + goto err_neigh_init; + if (rpriv->rep->vport == MLX5_VPORT_UPLINK) { err = mlx5e_init_uplink_rep_tx(rpriv); if (err) @@ -1055,6 +1060,8 @@ err_ht_init: if (rpriv->rep->vport == MLX5_VPORT_UPLINK) mlx5e_cleanup_uplink_rep_tx(rpriv); err_init_tx: + mlx5e_rep_neigh_cleanup(rpriv); +err_neigh_init: mlx5e_destroy_tises(priv); return err; } @@ -1068,22 +1075,17 @@ static void mlx5e_cleanup_rep_tx(struct mlx5e_priv *priv) if (rpriv->rep->vport == MLX5_VPORT_UPLINK) mlx5e_cleanup_uplink_rep_tx(rpriv); + mlx5e_rep_neigh_cleanup(rpriv); mlx5e_destroy_tises(priv); } static void mlx5e_rep_enable(struct mlx5e_priv *priv) { - struct mlx5e_rep_priv *rpriv = priv->ppriv; - mlx5e_set_netdev_mtu_boundaries(priv); - mlx5e_rep_neigh_init(rpriv); } static void mlx5e_rep_disable(struct mlx5e_priv *priv) { - struct mlx5e_rep_priv *rpriv = priv->ppriv; - - mlx5e_rep_neigh_cleanup(rpriv); } static int mlx5e_update_rep_rx(struct mlx5e_priv *priv) @@ -1118,7 +1120,6 @@ static int uplink_rep_async_event(struct notifier_block *nb, unsigned long event static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv) { - struct mlx5e_rep_priv *rpriv = priv->ppriv; struct net_device *netdev = priv->netdev; struct mlx5_core_dev *mdev = priv->mdev; u16 max_mtu; @@ -1138,7 +1139,6 @@ static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv) mlx5_notifier_register(mdev, &priv->events_nb); mlx5e_dcbnl_initialize(priv); mlx5e_dcbnl_init_app(priv); - mlx5e_rep_neigh_init(rpriv); mlx5e_rep_bridge_init(priv); netdev->wanted_features |= NETIF_F_HW_TC; @@ -1153,7 +1153,6 @@ static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv) static void mlx5e_uplink_rep_disable(struct mlx5e_priv *priv) { - struct mlx5e_rep_priv *rpriv = priv->ppriv; struct mlx5_core_dev *mdev = priv->mdev; rtnl_lock(); @@ -1163,7 +1162,6 @@ static void mlx5e_uplink_rep_disable(struct mlx5e_priv *priv) rtnl_unlock(); mlx5e_rep_bridge_cleanup(priv); - mlx5e_rep_neigh_cleanup(rpriv); mlx5e_dcbnl_delete_app(priv); mlx5_notifier_unregister(mdev, &priv->events_nb); mlx5e_rep_tc_disable(priv); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index a0242dc15741..e112b5685b02 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -1061,7 +1061,7 @@ void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev) mutex_lock(&table->lock); /* sync with create/destroy_async_eq */ if (!mlx5_core_is_sf(dev)) clear_rmap(dev); - mlx5_irq_table_destroy(dev); + mlx5_irq_table_free_irqs(dev); mutex_unlock(&table->lock); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index d53749248fa0..e6674118bc42 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -860,7 +860,7 @@ static struct mlx5_flow_table *find_closest_ft_recursive(struct fs_node *root, struct fs_node *iter = list_entry(start, struct fs_node, list); struct mlx5_flow_table *ft = NULL; - if (!root || root->type == FS_TYPE_PRIO_CHAINS) + if (!root) return NULL; list_for_each_advance_continue(iter, &root->children, reverse) { @@ -876,20 +876,42 @@ static struct mlx5_flow_table *find_closest_ft_recursive(struct fs_node *root, return ft; } -/* If reverse is false then return the first flow table in next priority of - * prio in the tree, else return the last flow table in the previous priority - * of prio in the tree. +static struct fs_node *find_prio_chains_parent(struct fs_node *parent, + struct fs_node **child) +{ + struct fs_node *node = NULL; + + while (parent && parent->type != FS_TYPE_PRIO_CHAINS) { + node = parent; + parent = parent->parent; + } + + if (child) + *child = node; + + return parent; +} + +/* If reverse is false then return the first flow table next to the passed node + * in the tree, else return the last flow table before the node in the tree. + * If skip is true, skip the flow tables in the same prio_chains prio. */ -static struct mlx5_flow_table *find_closest_ft(struct fs_prio *prio, bool reverse) +static struct mlx5_flow_table *find_closest_ft(struct fs_node *node, bool reverse, + bool skip) { + struct fs_node *prio_chains_parent = NULL; struct mlx5_flow_table *ft = NULL; struct fs_node *curr_node; struct fs_node *parent; - parent = prio->node.parent; - curr_node = &prio->node; + if (skip) + prio_chains_parent = find_prio_chains_parent(node, NULL); + parent = node->parent; + curr_node = node; while (!ft && parent) { - ft = find_closest_ft_recursive(parent, &curr_node->list, reverse); + if (parent != prio_chains_parent) + ft = find_closest_ft_recursive(parent, &curr_node->list, + reverse); curr_node = parent; parent = curr_node->parent; } @@ -897,15 +919,15 @@ static struct mlx5_flow_table *find_closest_ft(struct fs_prio *prio, bool revers } /* Assuming all the tree is locked by mutex chain lock */ -static struct mlx5_flow_table *find_next_chained_ft(struct fs_prio *prio) +static struct mlx5_flow_table *find_next_chained_ft(struct fs_node *node) { - return find_closest_ft(prio, false); + return find_closest_ft(node, false, true); } /* Assuming all the tree is locked by mutex chain lock */ -static struct mlx5_flow_table *find_prev_chained_ft(struct fs_prio *prio) +static struct mlx5_flow_table *find_prev_chained_ft(struct fs_node *node) { - return find_closest_ft(prio, true); + return find_closest_ft(node, true, true); } static struct mlx5_flow_table *find_next_fwd_ft(struct mlx5_flow_table *ft, @@ -917,7 +939,7 @@ static struct mlx5_flow_table *find_next_fwd_ft(struct mlx5_flow_table *ft, next_ns = flow_act->action & MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_NS; fs_get_obj(prio, next_ns ? ft->ns->node.parent : ft->node.parent); - return find_next_chained_ft(prio); + return find_next_chained_ft(&prio->node); } static int connect_fts_in_prio(struct mlx5_core_dev *dev, @@ -941,21 +963,55 @@ static int connect_fts_in_prio(struct mlx5_core_dev *dev, return 0; } +static struct mlx5_flow_table *find_closet_ft_prio_chains(struct fs_node *node, + struct fs_node *parent, + struct fs_node **child, + bool reverse) +{ + struct mlx5_flow_table *ft; + + ft = find_closest_ft(node, reverse, false); + + if (ft && parent == find_prio_chains_parent(&ft->node, child)) + return ft; + + return NULL; +} + /* Connect flow tables from previous priority of prio to ft */ static int connect_prev_fts(struct mlx5_core_dev *dev, struct mlx5_flow_table *ft, struct fs_prio *prio) { + struct fs_node *prio_parent, *parent = NULL, *child, *node; struct mlx5_flow_table *prev_ft; + int err = 0; + + prio_parent = find_prio_chains_parent(&prio->node, &child); + + /* return directly if not under the first sub ns of prio_chains prio */ + if (prio_parent && !list_is_first(&child->list, &prio_parent->children)) + return 0; - prev_ft = find_prev_chained_ft(prio); - if (prev_ft) { + prev_ft = find_prev_chained_ft(&prio->node); + while (prev_ft) { struct fs_prio *prev_prio; fs_get_obj(prev_prio, prev_ft->node.parent); - return connect_fts_in_prio(dev, prev_prio, ft); + err = connect_fts_in_prio(dev, prev_prio, ft); + if (err) + break; + + if (!parent) { + parent = find_prio_chains_parent(&prev_prio->node, &child); + if (!parent) + break; + } + + node = child; + prev_ft = find_closet_ft_prio_chains(node, parent, &child, true); } - return 0; + return err; } static int update_root_ft_create(struct mlx5_flow_table *ft, struct fs_prio @@ -1094,7 +1150,7 @@ static int connect_flow_table(struct mlx5_core_dev *dev, struct mlx5_flow_table if (err) return err; - next_ft = first_ft ? first_ft : find_next_chained_ft(prio); + next_ft = first_ft ? first_ft : find_next_chained_ft(&prio->node); err = connect_fwd_rules(dev, ft, next_ft); if (err) return err; @@ -1169,7 +1225,7 @@ static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespa tree_init_node(&ft->node, del_hw_flow_table, del_sw_flow_table); next_ft = unmanaged ? ft_attr->next_ft : - find_next_chained_ft(fs_prio); + find_next_chained_ft(&fs_prio->node); ft->def_miss_action = ns->def_miss_action; ft->ns = ns; err = root->cmds->create_flow_table(root, ft, ft_attr, next_ft); @@ -2157,13 +2213,20 @@ EXPORT_SYMBOL(mlx5_del_flow_rules); /* Assuming prio->node.children(flow tables) is sorted by level */ static struct mlx5_flow_table *find_next_ft(struct mlx5_flow_table *ft) { + struct fs_node *prio_parent, *child; struct fs_prio *prio; fs_get_obj(prio, ft->node.parent); if (!list_is_last(&ft->node.list, &prio->node.children)) return list_next_entry(ft, node.list); - return find_next_chained_ft(prio); + + prio_parent = find_prio_chains_parent(&prio->node, &child); + + if (prio_parent && list_is_first(&child->list, &prio_parent->children)) + return find_closest_ft(&prio->node, false, false); + + return find_next_chained_ft(&prio->node); } static int update_root_ft_destroy(struct mlx5_flow_table *ft) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c index d3a3fe4ce670..7d9bbb494d95 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c @@ -574,7 +574,7 @@ static int __mlx5_lag_modify_definers_destinations(struct mlx5_lag *ldev, for (i = 0; i < ldev->ports; i++) { for (j = 0; j < ldev->buckets; j++) { idx = i * ldev->buckets + j; - if (ldev->v2p_map[i] == ports[i]) + if (ldev->v2p_map[idx] == ports[idx]) continue; dest.vport.vhca_id = MLX5_CAP_GEN(ldev->pf[ports[idx] - 1].dev, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c index d7ddfc489536..2ac255bb918b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c @@ -198,10 +198,15 @@ static void mlx5_timestamp_overflow(struct work_struct *work) clock = container_of(timer, struct mlx5_clock, timer); mdev = container_of(clock, struct mlx5_core_dev, clock); + if (mdev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) + goto out; + write_seqlock_irqsave(&clock->lock, flags); timecounter_read(&timer->tc); mlx5_update_clock_info_page(mdev); write_sequnlock_irqrestore(&clock->lock, flags); + +out: schedule_delayed_work(&timer->overflow_work, timer->overflow_period); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 077204929fe4..6ab0642e9de7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1794,7 +1794,7 @@ static pci_ers_result_t mlx5_pci_err_detected(struct pci_dev *pdev, mlx5_enter_error_state(dev, false); mlx5_error_sw_reset(dev); - mlx5_unload_one(dev, true); + mlx5_unload_one(dev, false); mlx5_drain_health_wq(dev); mlx5_pci_disable_device(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h index 23cb63fa4588..2e728e4e81fa 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h @@ -14,6 +14,7 @@ int mlx5_irq_table_init(struct mlx5_core_dev *dev); void mlx5_irq_table_cleanup(struct mlx5_core_dev *dev); int mlx5_irq_table_create(struct mlx5_core_dev *dev); void mlx5_irq_table_destroy(struct mlx5_core_dev *dev); +void mlx5_irq_table_free_irqs(struct mlx5_core_dev *dev); int mlx5_irq_table_get_num_comp(struct mlx5_irq_table *table); int mlx5_irq_table_get_sfs_vec(struct mlx5_irq_table *table); struct mlx5_irq_table *mlx5_irq_table_get(struct mlx5_core_dev *dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c index 662f1d55e30e..5e0f7d96aac5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c @@ -591,6 +591,24 @@ static void irq_pools_destroy(struct mlx5_irq_table *table) irq_pool_free(table->pf_pool); } +static void mlx5_irq_pool_free_irqs(struct mlx5_irq_pool *pool) +{ + struct mlx5_irq *irq; + unsigned long index; + + xa_for_each(&pool->irqs, index, irq) + free_irq(irq->irqn, &irq->nh); +} + +static void mlx5_irq_pools_free_irqs(struct mlx5_irq_table *table) +{ + if (table->sf_ctrl_pool) { + mlx5_irq_pool_free_irqs(table->sf_comp_pool); + mlx5_irq_pool_free_irqs(table->sf_ctrl_pool); + } + mlx5_irq_pool_free_irqs(table->pf_pool); +} + /* irq_table API */ int mlx5_irq_table_init(struct mlx5_core_dev *dev) @@ -670,6 +688,17 @@ void mlx5_irq_table_destroy(struct mlx5_core_dev *dev) pci_free_irq_vectors(dev->pdev); } +void mlx5_irq_table_free_irqs(struct mlx5_core_dev *dev) +{ + struct mlx5_irq_table *table = dev->priv.irq_table; + + if (mlx5_core_is_sf(dev)) + return; + + mlx5_irq_pools_free_irqs(table); + pci_free_irq_vectors(dev->pdev); +} + int mlx5_irq_table_get_sfs_vec(struct mlx5_irq_table *table) { if (table->sf_comp_pool) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c index 20d7662c10fb..5f2195e65dd6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c @@ -264,8 +264,7 @@ static u16 mlx5_get_max_vfs(struct mlx5_core_dev *dev) host_total_vfs = MLX5_GET(query_esw_functions_out, out, host_params_context.host_total_vfs); kvfree(out); - if (host_total_vfs) - return host_total_vfs; + return host_total_vfs; } done: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c index 84364691a379..d7b1a230b59e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c @@ -538,11 +538,12 @@ int mlx5dr_cmd_create_reformat_ctx(struct mlx5_core_dev *mdev, err = mlx5_cmd_exec(mdev, in, inlen, out, sizeof(out)); if (err) - return err; + goto err_free_in; *reformat_id = MLX5_GET(alloc_packet_reformat_context_out, out, packet_reformat_id); - kvfree(in); +err_free_in: + kvfree(in); return err; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c index bd1a51a0a540..f208a237d0b5 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c @@ -32,8 +32,8 @@ static const struct mlxsw_afk_element_info mlxsw_afk_element_infos[] = { MLXSW_AFK_ELEMENT_INFO_U32(IP_TTL_, 0x18, 0, 8), MLXSW_AFK_ELEMENT_INFO_U32(IP_ECN, 0x18, 9, 2), MLXSW_AFK_ELEMENT_INFO_U32(IP_DSCP, 0x18, 11, 6), - MLXSW_AFK_ELEMENT_INFO_U32(VIRT_ROUTER_MSB, 0x18, 17, 3), - MLXSW_AFK_ELEMENT_INFO_U32(VIRT_ROUTER_LSB, 0x18, 20, 8), + MLXSW_AFK_ELEMENT_INFO_U32(VIRT_ROUTER_MSB, 0x18, 17, 4), + MLXSW_AFK_ELEMENT_INFO_U32(VIRT_ROUTER_LSB, 0x18, 21, 8), MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP_96_127, 0x20, 4), MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP_64_95, 0x24, 4), MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP_32_63, 0x28, 4), diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c index c968309657dd..51eea1f0529c 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.c +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c @@ -517,11 +517,15 @@ static void mlxsw_pci_skb_cb_ts_set(struct mlxsw_pci *mlxsw_pci, struct sk_buff *skb, enum mlxsw_pci_cqe_v cqe_v, char *cqe) { + u8 ts_type; + if (cqe_v != MLXSW_PCI_CQE_V2) return; - if (mlxsw_pci_cqe2_time_stamp_type_get(cqe) != - MLXSW_PCI_CQE_TIME_STAMP_TYPE_UTC) + ts_type = mlxsw_pci_cqe2_time_stamp_type_get(cqe); + + if (ts_type != MLXSW_PCI_CQE_TIME_STAMP_TYPE_UTC && + ts_type != MLXSW_PCI_CQE_TIME_STAMP_TYPE_MIRROR_UTC) return; mlxsw_skb_cb(skb)->cqe_ts.sec = mlxsw_pci_cqe2_time_stamp_sec_get(cqe); diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 0777bed5bb1a..a34ff19c58bd 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -97,14 +97,6 @@ MLXSW_ITEM32(reg, sspr, m, 0x00, 31, 1); */ MLXSW_ITEM32_LP(reg, sspr, 0x00, 16, 0x00, 12); -/* reg_sspr_sub_port - * Virtual port within the physical port. - * Should be set to 0 when virtual ports are not enabled on the port. - * - * Access: RW - */ -MLXSW_ITEM32(reg, sspr, sub_port, 0x00, 8, 8); - /* reg_sspr_system_port * Unique identifier within the stacking domain that represents all the ports * that are available in the system (external ports). @@ -120,7 +112,6 @@ static inline void mlxsw_reg_sspr_pack(char *payload, u16 local_port) MLXSW_REG_ZERO(sspr, payload); mlxsw_reg_sspr_m_set(payload, 1); mlxsw_reg_sspr_local_port_set(payload, local_port); - mlxsw_reg_sspr_sub_port_set(payload, 0); mlxsw_reg_sspr_system_port_set(payload, local_port); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_mr_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_mr_tcam.c index e4f4cded2b6f..b1178b7a7f51 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_mr_tcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_mr_tcam.c @@ -193,7 +193,7 @@ mlxsw_sp2_mr_tcam_rule_parse(struct mlxsw_sp_acl_rule *rule, key->vrid, GENMASK(7, 0)); mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_VIRT_ROUTER_MSB, - key->vrid >> 8, GENMASK(2, 0)); + key->vrid >> 8, GENMASK(3, 0)); switch (key->proto) { case MLXSW_SP_L3_PROTO_IPV4: return mlxsw_sp2_mr_tcam_rule_parse4(rulei, key); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c index 00c32320f891..173808c096ba 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c @@ -169,7 +169,7 @@ static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_2[] = { static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_4[] = { MLXSW_AFK_ELEMENT_INST_U32(VIRT_ROUTER_LSB, 0x04, 24, 8), - MLXSW_AFK_ELEMENT_INST_U32(VIRT_ROUTER_MSB, 0x00, 0, 3), + MLXSW_AFK_ELEMENT_INST_EXT_U32(VIRT_ROUTER_MSB, 0x00, 0, 3, 0, true), }; static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv6_0[] = { @@ -319,7 +319,7 @@ static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_mac_5b[] = { static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_4b[] = { MLXSW_AFK_ELEMENT_INST_U32(VIRT_ROUTER_LSB, 0x04, 13, 8), - MLXSW_AFK_ELEMENT_INST_EXT_U32(VIRT_ROUTER_MSB, 0x04, 21, 4, 0, true), + MLXSW_AFK_ELEMENT_INST_U32(VIRT_ROUTER_MSB, 0x04, 21, 4), }; static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv6_2b[] = { diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 27a0f3af8aab..4f4204432aaa 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -8,6 +8,7 @@ #include <linux/ethtool.h> #include <linux/filter.h> #include <linux/mm.h> +#include <linux/pci.h> #include <net/checksum.h> #include <net/ip6_checksum.h> @@ -1972,9 +1973,12 @@ int mana_attach(struct net_device *ndev) static int mana_dealloc_queues(struct net_device *ndev) { struct mana_port_context *apc = netdev_priv(ndev); + unsigned long timeout = jiffies + 120 * HZ; struct gdma_dev *gd = apc->ac->gdma_dev; struct mana_txq *txq; + struct sk_buff *skb; int i, err; + u32 tsleep; if (apc->port_is_up) return -EINVAL; @@ -1990,15 +1994,40 @@ static int mana_dealloc_queues(struct net_device *ndev) * to false, but it doesn't matter since mana_start_xmit() drops any * new packets due to apc->port_is_up being false. * - * Drain all the in-flight TX packets + * Drain all the in-flight TX packets. + * A timeout of 120 seconds for all the queues is used. + * This will break the while loop when h/w is not responding. + * This value of 120 has been decided here considering max + * number of queues. */ + for (i = 0; i < apc->num_queues; i++) { txq = &apc->tx_qp[i].txq; - - while (atomic_read(&txq->pending_sends) > 0) - usleep_range(1000, 2000); + tsleep = 1000; + while (atomic_read(&txq->pending_sends) > 0 && + time_before(jiffies, timeout)) { + usleep_range(tsleep, tsleep + 1000); + tsleep <<= 1; + } + if (atomic_read(&txq->pending_sends)) { + err = pcie_flr(to_pci_dev(gd->gdma_context->dev)); + if (err) { + netdev_err(ndev, "flr failed %d with %d pkts pending in txq %u\n", + err, atomic_read(&txq->pending_sends), + txq->gdma_txq_id); + } + break; + } } + for (i = 0; i < apc->num_queues; i++) { + txq = &apc->tx_qp[i].txq; + while ((skb = skb_dequeue(&txq->pending_skbs))) { + mana_unmap_skb(skb, apc); + dev_kfree_skb_any(skb); + } + atomic_set(&txq->pending_sends, 0); + } /* We're 100% sure the queues can no longer be woken up, because * we're sure now mana_poll_tx_cq() can't be running. */ diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev_api.h b/drivers/net/ethernet/qlogic/qed/qed_dev_api.h index f8682356d0cf..94d4f9413ab7 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev_api.h +++ b/drivers/net/ethernet/qlogic/qed/qed_dev_api.h @@ -194,6 +194,22 @@ void qed_hw_remove(struct qed_dev *cdev); struct qed_ptt *qed_ptt_acquire(struct qed_hwfn *p_hwfn); /** + * qed_ptt_acquire_context(): Allocate a PTT window honoring the context + * atomicy. + * + * @p_hwfn: HW device data. + * @is_atomic: Hint from the caller - if the func can sleep or not. + * + * Context: The function should not sleep in case is_atomic == true. + * Return: struct qed_ptt. + * + * Should be called at the entry point to the driver + * (at the beginning of an exported function). + */ +struct qed_ptt *qed_ptt_acquire_context(struct qed_hwfn *p_hwfn, + bool is_atomic); + +/** * qed_ptt_release(): Release PTT Window. * * @p_hwfn: HW device data. diff --git a/drivers/net/ethernet/qlogic/qed/qed_fcoe.c b/drivers/net/ethernet/qlogic/qed/qed_fcoe.c index 3764190b948e..04602ac94708 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_fcoe.c +++ b/drivers/net/ethernet/qlogic/qed/qed_fcoe.c @@ -693,13 +693,14 @@ static void _qed_fcoe_get_pstats(struct qed_hwfn *p_hwfn, } static int qed_fcoe_get_stats(struct qed_hwfn *p_hwfn, - struct qed_fcoe_stats *p_stats) + struct qed_fcoe_stats *p_stats, + bool is_atomic) { struct qed_ptt *p_ptt; memset(p_stats, 0, sizeof(*p_stats)); - p_ptt = qed_ptt_acquire(p_hwfn); + p_ptt = qed_ptt_acquire_context(p_hwfn, is_atomic); if (!p_ptt) { DP_ERR(p_hwfn, "Failed to acquire ptt\n"); @@ -973,19 +974,27 @@ static int qed_fcoe_destroy_conn(struct qed_dev *cdev, QED_SPQ_MODE_EBLOCK, NULL); } +static int qed_fcoe_stats_context(struct qed_dev *cdev, + struct qed_fcoe_stats *stats, + bool is_atomic) +{ + return qed_fcoe_get_stats(QED_AFFIN_HWFN(cdev), stats, is_atomic); +} + static int qed_fcoe_stats(struct qed_dev *cdev, struct qed_fcoe_stats *stats) { - return qed_fcoe_get_stats(QED_AFFIN_HWFN(cdev), stats); + return qed_fcoe_stats_context(cdev, stats, false); } void qed_get_protocol_stats_fcoe(struct qed_dev *cdev, - struct qed_mcp_fcoe_stats *stats) + struct qed_mcp_fcoe_stats *stats, + bool is_atomic) { struct qed_fcoe_stats proto_stats; /* Retrieve FW statistics */ memset(&proto_stats, 0, sizeof(proto_stats)); - if (qed_fcoe_stats(cdev, &proto_stats)) { + if (qed_fcoe_stats_context(cdev, &proto_stats, is_atomic)) { DP_VERBOSE(cdev, QED_MSG_STORAGE, "Failed to collect FCoE statistics\n"); return; diff --git a/drivers/net/ethernet/qlogic/qed/qed_fcoe.h b/drivers/net/ethernet/qlogic/qed/qed_fcoe.h index 19c85adf4ceb..214e8299ecb4 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_fcoe.h +++ b/drivers/net/ethernet/qlogic/qed/qed_fcoe.h @@ -28,8 +28,20 @@ int qed_fcoe_alloc(struct qed_hwfn *p_hwfn); void qed_fcoe_setup(struct qed_hwfn *p_hwfn); void qed_fcoe_free(struct qed_hwfn *p_hwfn); +/** + * qed_get_protocol_stats_fcoe(): Fills provided statistics + * struct with statistics. + * + * @cdev: Qed dev pointer. + * @stats: Points to struct that will be filled with statistics. + * @is_atomic: Hint from the caller - if the func can sleep or not. + * + * Context: The function should not sleep in case is_atomic == true. + * Return: Void. + */ void qed_get_protocol_stats_fcoe(struct qed_dev *cdev, - struct qed_mcp_fcoe_stats *stats); + struct qed_mcp_fcoe_stats *stats, + bool is_atomic); #else /* CONFIG_QED_FCOE */ static inline int qed_fcoe_alloc(struct qed_hwfn *p_hwfn) { @@ -40,7 +52,8 @@ static inline void qed_fcoe_setup(struct qed_hwfn *p_hwfn) {} static inline void qed_fcoe_free(struct qed_hwfn *p_hwfn) {} static inline void qed_get_protocol_stats_fcoe(struct qed_dev *cdev, - struct qed_mcp_fcoe_stats *stats) + struct qed_mcp_fcoe_stats *stats, + bool is_atomic) { } #endif /* CONFIG_QED_FCOE */ diff --git a/drivers/net/ethernet/qlogic/qed/qed_hw.c b/drivers/net/ethernet/qlogic/qed/qed_hw.c index 554f30b0cfd5..6263f847b6b9 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_hw.c +++ b/drivers/net/ethernet/qlogic/qed/qed_hw.c @@ -23,7 +23,10 @@ #include "qed_reg_addr.h" #include "qed_sriov.h" -#define QED_BAR_ACQUIRE_TIMEOUT 1000 +#define QED_BAR_ACQUIRE_TIMEOUT_USLEEP_CNT 1000 +#define QED_BAR_ACQUIRE_TIMEOUT_USLEEP 1000 +#define QED_BAR_ACQUIRE_TIMEOUT_UDELAY_CNT 100000 +#define QED_BAR_ACQUIRE_TIMEOUT_UDELAY 10 /* Invalid values */ #define QED_BAR_INVALID_OFFSET (cpu_to_le32(-1)) @@ -85,11 +88,21 @@ void qed_ptt_pool_free(struct qed_hwfn *p_hwfn) struct qed_ptt *qed_ptt_acquire(struct qed_hwfn *p_hwfn) { + return qed_ptt_acquire_context(p_hwfn, false); +} + +struct qed_ptt *qed_ptt_acquire_context(struct qed_hwfn *p_hwfn, bool is_atomic) +{ struct qed_ptt *p_ptt; - unsigned int i; + unsigned int i, count; + + if (is_atomic) + count = QED_BAR_ACQUIRE_TIMEOUT_UDELAY_CNT; + else + count = QED_BAR_ACQUIRE_TIMEOUT_USLEEP_CNT; /* Take the free PTT from the list */ - for (i = 0; i < QED_BAR_ACQUIRE_TIMEOUT; i++) { + for (i = 0; i < count; i++) { spin_lock_bh(&p_hwfn->p_ptt_pool->lock); if (!list_empty(&p_hwfn->p_ptt_pool->free_list)) { @@ -105,7 +118,12 @@ struct qed_ptt *qed_ptt_acquire(struct qed_hwfn *p_hwfn) } spin_unlock_bh(&p_hwfn->p_ptt_pool->lock); - usleep_range(1000, 2000); + + if (is_atomic) + udelay(QED_BAR_ACQUIRE_TIMEOUT_UDELAY); + else + usleep_range(QED_BAR_ACQUIRE_TIMEOUT_USLEEP, + QED_BAR_ACQUIRE_TIMEOUT_USLEEP * 2); } DP_NOTICE(p_hwfn, "PTT acquire timeout - failed to allocate PTT\n"); diff --git a/drivers/net/ethernet/qlogic/qed/qed_iscsi.c b/drivers/net/ethernet/qlogic/qed/qed_iscsi.c index 511ab214eb9c..980e7289b481 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iscsi.c +++ b/drivers/net/ethernet/qlogic/qed/qed_iscsi.c @@ -999,13 +999,14 @@ static void _qed_iscsi_get_pstats(struct qed_hwfn *p_hwfn, } static int qed_iscsi_get_stats(struct qed_hwfn *p_hwfn, - struct qed_iscsi_stats *stats) + struct qed_iscsi_stats *stats, + bool is_atomic) { struct qed_ptt *p_ptt; memset(stats, 0, sizeof(*stats)); - p_ptt = qed_ptt_acquire(p_hwfn); + p_ptt = qed_ptt_acquire_context(p_hwfn, is_atomic); if (!p_ptt) { DP_ERR(p_hwfn, "Failed to acquire ptt\n"); return -EAGAIN; @@ -1336,9 +1337,16 @@ static int qed_iscsi_destroy_conn(struct qed_dev *cdev, QED_SPQ_MODE_EBLOCK, NULL); } +static int qed_iscsi_stats_context(struct qed_dev *cdev, + struct qed_iscsi_stats *stats, + bool is_atomic) +{ + return qed_iscsi_get_stats(QED_AFFIN_HWFN(cdev), stats, is_atomic); +} + static int qed_iscsi_stats(struct qed_dev *cdev, struct qed_iscsi_stats *stats) { - return qed_iscsi_get_stats(QED_AFFIN_HWFN(cdev), stats); + return qed_iscsi_stats_context(cdev, stats, false); } static int qed_iscsi_change_mac(struct qed_dev *cdev, @@ -1358,13 +1366,14 @@ static int qed_iscsi_change_mac(struct qed_dev *cdev, } void qed_get_protocol_stats_iscsi(struct qed_dev *cdev, - struct qed_mcp_iscsi_stats *stats) + struct qed_mcp_iscsi_stats *stats, + bool is_atomic) { struct qed_iscsi_stats proto_stats; /* Retrieve FW statistics */ memset(&proto_stats, 0, sizeof(proto_stats)); - if (qed_iscsi_stats(cdev, &proto_stats)) { + if (qed_iscsi_stats_context(cdev, &proto_stats, is_atomic)) { DP_VERBOSE(cdev, QED_MSG_STORAGE, "Failed to collect ISCSI statistics\n"); return; diff --git a/drivers/net/ethernet/qlogic/qed/qed_iscsi.h b/drivers/net/ethernet/qlogic/qed/qed_iscsi.h index dec2b00259d4..974cb8d26608 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iscsi.h +++ b/drivers/net/ethernet/qlogic/qed/qed_iscsi.h @@ -39,11 +39,14 @@ void qed_iscsi_free(struct qed_hwfn *p_hwfn); * * @cdev: Qed dev pointer. * @stats: Points to struct that will be filled with statistics. + * @is_atomic: Hint from the caller - if the func can sleep or not. * + * Context: The function should not sleep in case is_atomic == true. * Return: Void. */ void qed_get_protocol_stats_iscsi(struct qed_dev *cdev, - struct qed_mcp_iscsi_stats *stats); + struct qed_mcp_iscsi_stats *stats, + bool is_atomic); #else /* IS_ENABLED(CONFIG_QED_ISCSI) */ static inline int qed_iscsi_alloc(struct qed_hwfn *p_hwfn) { @@ -56,7 +59,8 @@ static inline void qed_iscsi_free(struct qed_hwfn *p_hwfn) {} static inline void qed_get_protocol_stats_iscsi(struct qed_dev *cdev, - struct qed_mcp_iscsi_stats *stats) {} + struct qed_mcp_iscsi_stats *stats, + bool is_atomic) {} #endif /* IS_ENABLED(CONFIG_QED_ISCSI) */ #endif diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index 7776d3bdd459..970b9aabbc3d 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -1863,7 +1863,8 @@ static void __qed_get_vport_stats(struct qed_hwfn *p_hwfn, } static void _qed_get_vport_stats(struct qed_dev *cdev, - struct qed_eth_stats *stats) + struct qed_eth_stats *stats, + bool is_atomic) { u8 fw_vport = 0; int i; @@ -1872,10 +1873,11 @@ static void _qed_get_vport_stats(struct qed_dev *cdev, for_each_hwfn(cdev, i) { struct qed_hwfn *p_hwfn = &cdev->hwfns[i]; - struct qed_ptt *p_ptt = IS_PF(cdev) ? qed_ptt_acquire(p_hwfn) - : NULL; + struct qed_ptt *p_ptt; bool b_get_port_stats; + p_ptt = IS_PF(cdev) ? qed_ptt_acquire_context(p_hwfn, is_atomic) + : NULL; if (IS_PF(cdev)) { /* The main vport index is relative first */ if (qed_fw_vport(p_hwfn, 0, &fw_vport)) { @@ -1901,6 +1903,13 @@ out: void qed_get_vport_stats(struct qed_dev *cdev, struct qed_eth_stats *stats) { + qed_get_vport_stats_context(cdev, stats, false); +} + +void qed_get_vport_stats_context(struct qed_dev *cdev, + struct qed_eth_stats *stats, + bool is_atomic) +{ u32 i; if (!cdev || cdev->recov_in_prog) { @@ -1908,7 +1917,7 @@ void qed_get_vport_stats(struct qed_dev *cdev, struct qed_eth_stats *stats) return; } - _qed_get_vport_stats(cdev, stats); + _qed_get_vport_stats(cdev, stats, is_atomic); if (!cdev->reset_stats) return; @@ -1960,7 +1969,7 @@ void qed_reset_vport_stats(struct qed_dev *cdev) if (!cdev->reset_stats) { DP_INFO(cdev, "Reset stats not allocated\n"); } else { - _qed_get_vport_stats(cdev, cdev->reset_stats); + _qed_get_vport_stats(cdev, cdev->reset_stats, false); cdev->reset_stats->common.link_change_count = 0; } } diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.h b/drivers/net/ethernet/qlogic/qed/qed_l2.h index a538cf478c14..2d2f82c785ad 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.h +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.h @@ -249,8 +249,32 @@ qed_sp_eth_rx_queues_update(struct qed_hwfn *p_hwfn, enum spq_mode comp_mode, struct qed_spq_comp_cb *p_comp_data); +/** + * qed_get_vport_stats(): Fills provided statistics + * struct with statistics. + * + * @cdev: Qed dev pointer. + * @stats: Points to struct that will be filled with statistics. + * + * Return: Void. + */ void qed_get_vport_stats(struct qed_dev *cdev, struct qed_eth_stats *stats); +/** + * qed_get_vport_stats_context(): Fills provided statistics + * struct with statistics. + * + * @cdev: Qed dev pointer. + * @stats: Points to struct that will be filled with statistics. + * @is_atomic: Hint from the caller - if the func can sleep or not. + * + * Context: The function should not sleep in case is_atomic == true. + * Return: Void. + */ +void qed_get_vport_stats_context(struct qed_dev *cdev, + struct qed_eth_stats *stats, + bool is_atomic); + void qed_reset_vport_stats(struct qed_dev *cdev); /** diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index c91898be7c03..25d9c254288b 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -3101,7 +3101,7 @@ void qed_get_protocol_stats(struct qed_dev *cdev, switch (type) { case QED_MCP_LAN_STATS: - qed_get_vport_stats(cdev, ð_stats); + qed_get_vport_stats_context(cdev, ð_stats, true); stats->lan_stats.ucast_rx_pkts = eth_stats.common.rx_ucast_pkts; stats->lan_stats.ucast_tx_pkts = @@ -3109,10 +3109,10 @@ void qed_get_protocol_stats(struct qed_dev *cdev, stats->lan_stats.fcs_err = -1; break; case QED_MCP_FCOE_STATS: - qed_get_protocol_stats_fcoe(cdev, &stats->fcoe_stats); + qed_get_protocol_stats_fcoe(cdev, &stats->fcoe_stats, true); break; case QED_MCP_ISCSI_STATS: - qed_get_protocol_stats_iscsi(cdev, &stats->iscsi_stats); + qed_get_protocol_stats_iscsi(cdev, &stats->iscsi_stats, true); break; default: DP_VERBOSE(cdev, QED_MSG_SP, diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index e8d427c7d1cf..dc43e74147fb 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -177,6 +177,15 @@ static int qede_sriov_configure(struct pci_dev *pdev, int num_vfs_param) } #endif +static int __maybe_unused qede_suspend(struct device *dev) +{ + dev_info(dev, "Device does not support suspend operation\n"); + + return -EOPNOTSUPP; +} + +static DEFINE_SIMPLE_DEV_PM_OPS(qede_pm_ops, qede_suspend, NULL); + static const struct pci_error_handlers qede_err_handler = { .error_detected = qede_io_error_detected, }; @@ -191,6 +200,7 @@ static struct pci_driver qede_pci_driver = { .sriov_configure = qede_sriov_configure, #endif .err_handler = &qede_err_handler, + .driver.pm = &qede_pm_ops, }; static struct qed_eth_cb_ops qede_ll_ops = { diff --git a/drivers/net/ethernet/sfc/tc.c b/drivers/net/ethernet/sfc/tc.c index 3478860d4023..d312147cd2dd 100644 --- a/drivers/net/ethernet/sfc/tc.c +++ b/drivers/net/ethernet/sfc/tc.c @@ -603,10 +603,10 @@ int efx_init_tc(struct efx_nic *efx) rc = efx_tc_configure_rep_mport(efx); if (rc) return rc; - efx->tc->up = true; rc = flow_indr_dev_register(efx_tc_indr_setup_cb, efx); if (rc) return rc; + efx->tc->up = true; return 0; } diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c index 9b46579b5a10..b130e978366c 100644 --- a/drivers/net/ethernet/socionext/netsec.c +++ b/drivers/net/ethernet/socionext/netsec.c @@ -1851,6 +1851,17 @@ static int netsec_of_probe(struct platform_device *pdev, return err; } + /* + * SynQuacer is physically configured with TX and RX delays + * but the standard firmware claimed otherwise for a long + * time, ignore it. + */ + if (of_machine_is_compatible("socionext,developer-box") && + priv->phy_interface != PHY_INTERFACE_MODE_RGMII_ID) { + dev_warn(&pdev->dev, "Outdated firmware reports incorrect PHY mode, overriding\n"); + priv->phy_interface = PHY_INTERFACE_MODE_RGMII_ID; + } + priv->phy_np = of_parse_phandle(pdev->dev.of_node, "phy-handle", 0); if (!priv->phy_np) { dev_err(&pdev->dev, "missing required property 'phy-handle'\n"); diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c index 1066420d6a83..6bf5e341c3c1 100644 --- a/drivers/net/ethernet/xilinx/ll_temac_main.c +++ b/drivers/net/ethernet/xilinx/ll_temac_main.c @@ -1568,12 +1568,16 @@ static int temac_probe(struct platform_device *pdev) } /* Error handle returned DMA RX and TX interrupts */ - if (lp->rx_irq < 0) - return dev_err_probe(&pdev->dev, lp->rx_irq, + if (lp->rx_irq <= 0) { + rc = lp->rx_irq ?: -EINVAL; + return dev_err_probe(&pdev->dev, rc, "could not get DMA RX irq\n"); - if (lp->tx_irq < 0) - return dev_err_probe(&pdev->dev, lp->tx_irq, + } + if (lp->tx_irq <= 0) { + rc = lp->tx_irq ?: -EINVAL; + return dev_err_probe(&pdev->dev, rc, "could not get DMA TX irq\n"); + } if (temac_np) { /* Retrieve the MAC address */ diff --git a/drivers/net/ipa/ipa_table.c b/drivers/net/ipa/ipa_table.c index 510ff2dc8999..cd81dd916c29 100644 --- a/drivers/net/ipa/ipa_table.c +++ b/drivers/net/ipa/ipa_table.c @@ -311,16 +311,15 @@ static int ipa_filter_reset(struct ipa *ipa, bool modem) if (ret) return ret; - ret = ipa_filter_reset_table(ipa, IPA_MEM_V4_FILTER_HASHED, modem); - if (ret) + ret = ipa_filter_reset_table(ipa, IPA_MEM_V6_FILTER, modem); + if (ret || !ipa_table_hash_support(ipa)) return ret; - ret = ipa_filter_reset_table(ipa, IPA_MEM_V6_FILTER, modem); + ret = ipa_filter_reset_table(ipa, IPA_MEM_V4_FILTER_HASHED, modem); if (ret) return ret; - ret = ipa_filter_reset_table(ipa, IPA_MEM_V6_FILTER_HASHED, modem); - return ret; + return ipa_filter_reset_table(ipa, IPA_MEM_V6_FILTER_HASHED, modem); } /* The AP routes and modem routes are each contiguous within the @@ -329,11 +328,12 @@ static int ipa_filter_reset(struct ipa *ipa, bool modem) * */ static int ipa_route_reset(struct ipa *ipa, bool modem) { + bool hash_support = ipa_table_hash_support(ipa); struct gsi_trans *trans; u16 first; u16 count; - trans = ipa_cmd_trans_alloc(ipa, 4); + trans = ipa_cmd_trans_alloc(ipa, hash_support ? 4 : 2); if (!trans) { dev_err(&ipa->pdev->dev, "no transaction for %s route reset\n", @@ -350,12 +350,14 @@ static int ipa_route_reset(struct ipa *ipa, bool modem) } ipa_table_reset_add(trans, false, first, count, IPA_MEM_V4_ROUTE); - ipa_table_reset_add(trans, false, first, count, - IPA_MEM_V4_ROUTE_HASHED); - ipa_table_reset_add(trans, false, first, count, IPA_MEM_V6_ROUTE); - ipa_table_reset_add(trans, false, first, count, - IPA_MEM_V6_ROUTE_HASHED); + + if (hash_support) { + ipa_table_reset_add(trans, false, first, count, + IPA_MEM_V4_ROUTE_HASHED); + ipa_table_reset_add(trans, false, first, count, + IPA_MEM_V6_ROUTE_HASHED); + } gsi_trans_commit_wait(trans); diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 796a38f9d7b2..cd16bc8bf154 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -748,7 +748,8 @@ static int ipvlan_device_event(struct notifier_block *unused, write_pnet(&port->pnet, newnet); - ipvlan_migrate_l3s_hook(oldnet, newnet); + if (port->mode == IPVLAN_MODE_L3S) + ipvlan_migrate_l3s_hook(oldnet, newnet); break; } case NETDEV_UNREGISTER: diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 983cabf9a0f6..6a7965ed6300 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -743,7 +743,7 @@ static bool macsec_post_decrypt(struct sk_buff *skb, struct macsec_secy *secy, u u64_stats_update_begin(&rxsc_stats->syncp); rxsc_stats->stats.InPktsLate++; u64_stats_update_end(&rxsc_stats->syncp); - secy->netdev->stats.rx_dropped++; + DEV_STATS_INC(secy->netdev, rx_dropped); return false; } @@ -767,7 +767,7 @@ static bool macsec_post_decrypt(struct sk_buff *skb, struct macsec_secy *secy, u rxsc_stats->stats.InPktsNotValid++; u64_stats_update_end(&rxsc_stats->syncp); this_cpu_inc(rx_sa->stats->InPktsNotValid); - secy->netdev->stats.rx_errors++; + DEV_STATS_INC(secy->netdev, rx_errors); return false; } @@ -1059,7 +1059,7 @@ static enum rx_handler_result handle_not_macsec(struct sk_buff *skb) u64_stats_update_begin(&secy_stats->syncp); secy_stats->stats.InPktsNoTag++; u64_stats_update_end(&secy_stats->syncp); - macsec->secy.netdev->stats.rx_dropped++; + DEV_STATS_INC(macsec->secy.netdev, rx_dropped); continue; } @@ -1169,7 +1169,7 @@ static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb) u64_stats_update_begin(&secy_stats->syncp); secy_stats->stats.InPktsBadTag++; u64_stats_update_end(&secy_stats->syncp); - secy->netdev->stats.rx_errors++; + DEV_STATS_INC(secy->netdev, rx_errors); goto drop_nosa; } @@ -1186,7 +1186,7 @@ static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb) u64_stats_update_begin(&rxsc_stats->syncp); rxsc_stats->stats.InPktsNotUsingSA++; u64_stats_update_end(&rxsc_stats->syncp); - secy->netdev->stats.rx_errors++; + DEV_STATS_INC(secy->netdev, rx_errors); if (active_rx_sa) this_cpu_inc(active_rx_sa->stats->InPktsNotUsingSA); goto drop_nosa; @@ -1220,7 +1220,7 @@ static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb) u64_stats_update_begin(&rxsc_stats->syncp); rxsc_stats->stats.InPktsLate++; u64_stats_update_end(&rxsc_stats->syncp); - macsec->secy.netdev->stats.rx_dropped++; + DEV_STATS_INC(macsec->secy.netdev, rx_dropped); goto drop; } } @@ -1261,7 +1261,7 @@ deliver: if (ret == NET_RX_SUCCESS) count_rx(dev, len); else - macsec->secy.netdev->stats.rx_dropped++; + DEV_STATS_INC(macsec->secy.netdev, rx_dropped); rcu_read_unlock(); @@ -1298,7 +1298,7 @@ nosci: u64_stats_update_begin(&secy_stats->syncp); secy_stats->stats.InPktsNoSCI++; u64_stats_update_end(&secy_stats->syncp); - macsec->secy.netdev->stats.rx_errors++; + DEV_STATS_INC(macsec->secy.netdev, rx_errors); continue; } @@ -1317,7 +1317,7 @@ nosci: secy_stats->stats.InPktsUnknownSCI++; u64_stats_update_end(&secy_stats->syncp); } else { - macsec->secy.netdev->stats.rx_dropped++; + DEV_STATS_INC(macsec->secy.netdev, rx_dropped); } } @@ -3418,7 +3418,7 @@ static netdev_tx_t macsec_start_xmit(struct sk_buff *skb, if (!secy->operational) { kfree_skb(skb); - dev->stats.tx_dropped++; + DEV_STATS_INC(dev, tx_dropped); return NETDEV_TX_OK; } @@ -3426,7 +3426,7 @@ static netdev_tx_t macsec_start_xmit(struct sk_buff *skb, skb = macsec_encrypt(skb, dev); if (IS_ERR(skb)) { if (PTR_ERR(skb) != -EINPROGRESS) - dev->stats.tx_dropped++; + DEV_STATS_INC(dev, tx_dropped); return NETDEV_TX_OK; } @@ -3663,9 +3663,9 @@ static void macsec_get_stats64(struct net_device *dev, dev_fetch_sw_netstats(s, dev->tstats); - s->rx_dropped = dev->stats.rx_dropped; - s->tx_dropped = dev->stats.tx_dropped; - s->rx_errors = dev->stats.rx_errors; + s->rx_dropped = atomic_long_read(&dev->stats.__rx_dropped); + s->tx_dropped = atomic_long_read(&dev->stats.__tx_dropped); + s->rx_errors = atomic_long_read(&dev->stats.__rx_errors); } static int macsec_get_iflink(const struct net_device *dev) diff --git a/drivers/net/pcs/pcs-rzn1-miic.c b/drivers/net/pcs/pcs-rzn1-miic.c index c1424119e821..847ab37f1367 100644 --- a/drivers/net/pcs/pcs-rzn1-miic.c +++ b/drivers/net/pcs/pcs-rzn1-miic.c @@ -317,15 +317,21 @@ struct phylink_pcs *miic_create(struct device *dev, struct device_node *np) pdev = of_find_device_by_node(pcs_np); of_node_put(pcs_np); - if (!pdev || !platform_get_drvdata(pdev)) + if (!pdev || !platform_get_drvdata(pdev)) { + if (pdev) + put_device(&pdev->dev); return ERR_PTR(-EPROBE_DEFER); + } miic_port = kzalloc(sizeof(*miic_port), GFP_KERNEL); - if (!miic_port) + if (!miic_port) { + put_device(&pdev->dev); return ERR_PTR(-ENOMEM); + } miic = platform_get_drvdata(pdev); device_link_add(dev, miic->dev, DL_FLAG_AUTOREMOVE_CONSUMER); + put_device(&pdev->dev); miic_port->miic = miic; miic_port->port = port - 1; diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c index d49965907561..edd4b1e58d96 100644 --- a/drivers/net/phy/at803x.c +++ b/drivers/net/phy/at803x.c @@ -305,7 +305,6 @@ struct at803x_priv { bool is_1000basex; struct regulator_dev *vddio_rdev; struct regulator_dev *vddh_rdev; - struct regulator *vddio; u64 stats[ARRAY_SIZE(at803x_hw_stats)]; }; @@ -461,21 +460,27 @@ static int at803x_set_wol(struct phy_device *phydev, phy_write_mmd(phydev, MDIO_MMD_PCS, offsets[i], mac[(i * 2) + 1] | (mac[(i * 2)] << 8)); - /* Enable WOL function */ - ret = phy_modify_mmd(phydev, MDIO_MMD_PCS, AT803X_PHY_MMD3_WOL_CTRL, - 0, AT803X_WOL_EN); - if (ret) - return ret; + /* Enable WOL function for 1588 */ + if (phydev->drv->phy_id == ATH8031_PHY_ID) { + ret = phy_modify_mmd(phydev, MDIO_MMD_PCS, + AT803X_PHY_MMD3_WOL_CTRL, + 0, AT803X_WOL_EN); + if (ret) + return ret; + } /* Enable WOL interrupt */ ret = phy_modify(phydev, AT803X_INTR_ENABLE, 0, AT803X_INTR_ENABLE_WOL); if (ret) return ret; } else { - /* Disable WoL function */ - ret = phy_modify_mmd(phydev, MDIO_MMD_PCS, AT803X_PHY_MMD3_WOL_CTRL, - AT803X_WOL_EN, 0); - if (ret) - return ret; + /* Disable WoL function for 1588 */ + if (phydev->drv->phy_id == ATH8031_PHY_ID) { + ret = phy_modify_mmd(phydev, MDIO_MMD_PCS, + AT803X_PHY_MMD3_WOL_CTRL, + AT803X_WOL_EN, 0); + if (ret) + return ret; + } /* Disable WOL interrupt */ ret = phy_modify(phydev, AT803X_INTR_ENABLE, AT803X_INTR_ENABLE_WOL, 0); if (ret) @@ -510,11 +515,11 @@ static void at803x_get_wol(struct phy_device *phydev, wol->supported = WAKE_MAGIC; wol->wolopts = 0; - value = phy_read_mmd(phydev, MDIO_MMD_PCS, AT803X_PHY_MMD3_WOL_CTRL); + value = phy_read(phydev, AT803X_INTR_ENABLE); if (value < 0) return; - if (value & AT803X_WOL_EN) + if (value & AT803X_INTR_ENABLE_WOL) wol->wolopts |= WAKE_MAGIC; } @@ -825,11 +830,11 @@ static int at803x_parse_dt(struct phy_device *phydev) if (ret < 0) return ret; - priv->vddio = devm_regulator_get_optional(&phydev->mdio.dev, - "vddio"); - if (IS_ERR(priv->vddio)) { + ret = devm_regulator_get_enable_optional(&phydev->mdio.dev, + "vddio"); + if (ret) { phydev_err(phydev, "failed to get VDDIO regulator\n"); - return PTR_ERR(priv->vddio); + return ret; } /* Only AR8031/8033 support 1000Base-X for SFP modules */ @@ -857,23 +862,12 @@ static int at803x_probe(struct phy_device *phydev) if (ret) return ret; - if (priv->vddio) { - ret = regulator_enable(priv->vddio); - if (ret < 0) - return ret; - } - if (phydev->drv->phy_id == ATH8031_PHY_ID) { int ccr = phy_read(phydev, AT803X_REG_CHIP_CONFIG); int mode_cfg; - struct ethtool_wolinfo wol = { - .wolopts = 0, - }; - if (ccr < 0) { - ret = ccr; - goto err; - } + if (ccr < 0) + return ccr; mode_cfg = ccr & AT803X_MODE_CFG_MASK; switch (mode_cfg) { @@ -887,29 +881,17 @@ static int at803x_probe(struct phy_device *phydev) break; } - /* Disable WOL by default */ - ret = at803x_set_wol(phydev, &wol); - if (ret < 0) { - phydev_err(phydev, "failed to disable WOL on probe: %d\n", ret); - goto err; - } + /* Disable WoL in 1588 register which is enabled + * by default + */ + ret = phy_modify_mmd(phydev, MDIO_MMD_PCS, + AT803X_PHY_MMD3_WOL_CTRL, + AT803X_WOL_EN, 0); + if (ret) + return ret; } return 0; - -err: - if (priv->vddio) - regulator_disable(priv->vddio); - - return ret; -} - -static void at803x_remove(struct phy_device *phydev) -{ - struct at803x_priv *priv = phydev->priv; - - if (priv->vddio) - regulator_disable(priv->vddio); } static int at803x_get_features(struct phy_device *phydev) @@ -2022,7 +2004,6 @@ static struct phy_driver at803x_driver[] = { .name = "Qualcomm Atheros AR8035", .flags = PHY_POLL_CABLE_TEST, .probe = at803x_probe, - .remove = at803x_remove, .config_aneg = at803x_config_aneg, .config_init = at803x_config_init, .soft_reset = genphy_soft_reset, @@ -2044,7 +2025,6 @@ static struct phy_driver at803x_driver[] = { .name = "Qualcomm Atheros AR8030", .phy_id_mask = AT8030_PHY_ID_MASK, .probe = at803x_probe, - .remove = at803x_remove, .config_init = at803x_config_init, .link_change_notify = at803x_link_change_notify, .set_wol = at803x_set_wol, @@ -2060,7 +2040,6 @@ static struct phy_driver at803x_driver[] = { .name = "Qualcomm Atheros AR8031/AR8033", .flags = PHY_POLL_CABLE_TEST, .probe = at803x_probe, - .remove = at803x_remove, .config_init = at803x_config_init, .config_aneg = at803x_config_aneg, .soft_reset = genphy_soft_reset, @@ -2083,12 +2062,9 @@ static struct phy_driver at803x_driver[] = { PHY_ID_MATCH_EXACT(ATH8032_PHY_ID), .name = "Qualcomm Atheros AR8032", .probe = at803x_probe, - .remove = at803x_remove, .flags = PHY_POLL_CABLE_TEST, .config_init = at803x_config_init, .link_change_notify = at803x_link_change_notify, - .set_wol = at803x_set_wol, - .get_wol = at803x_get_wol, .suspend = at803x_suspend, .resume = at803x_resume, /* PHY_BASIC_FEATURES */ @@ -2101,7 +2077,6 @@ static struct phy_driver at803x_driver[] = { PHY_ID_MATCH_EXACT(ATH9331_PHY_ID), .name = "Qualcomm Atheros AR9331 built-in PHY", .probe = at803x_probe, - .remove = at803x_remove, .suspend = at803x_suspend, .resume = at803x_resume, .flags = PHY_POLL_CABLE_TEST, @@ -2118,7 +2093,6 @@ static struct phy_driver at803x_driver[] = { PHY_ID_MATCH_EXACT(QCA9561_PHY_ID), .name = "Qualcomm Atheros QCA9561 built-in PHY", .probe = at803x_probe, - .remove = at803x_remove, .suspend = at803x_suspend, .resume = at803x_resume, .flags = PHY_POLL_CABLE_TEST, @@ -2184,7 +2158,6 @@ static struct phy_driver at803x_driver[] = { .name = "Qualcomm QCA8081", .flags = PHY_POLL_CABLE_TEST, .probe = at803x_probe, - .remove = at803x_remove, .config_intr = at803x_config_intr, .handle_interrupt = at803x_handle_interrupt, .get_tunable = at803x_get_tunable, diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c index ad71c88c87e7..f9ad8902100f 100644 --- a/drivers/net/phy/broadcom.c +++ b/drivers/net/phy/broadcom.c @@ -486,6 +486,17 @@ static int bcm54xx_resume(struct phy_device *phydev) return bcm54xx_config_init(phydev); } +static int bcm54810_read_mmd(struct phy_device *phydev, int devnum, u16 regnum) +{ + return -EOPNOTSUPP; +} + +static int bcm54810_write_mmd(struct phy_device *phydev, int devnum, u16 regnum, + u16 val) +{ + return -EOPNOTSUPP; +} + static int bcm54811_config_init(struct phy_device *phydev) { int err, reg; @@ -981,6 +992,8 @@ static struct phy_driver broadcom_drivers[] = { .get_strings = bcm_phy_get_strings, .get_stats = bcm54xx_get_stats, .probe = bcm54xx_phy_probe, + .read_mmd = bcm54810_read_mmd, + .write_mmd = bcm54810_write_mmd, .config_init = bcm54xx_config_init, .config_aneg = bcm5481_config_aneg, .config_intr = bcm_phy_config_intr, diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 82f74f96eba2..944f76e6fc8e 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -3050,6 +3050,8 @@ static int phy_probe(struct device *dev) goto out; } + phy_disable_interrupts(phydev); + /* Start out supporting everything. Eventually, * a controller will attach, and may modify one * or both of these values @@ -3137,16 +3139,6 @@ static int phy_remove(struct device *dev) return 0; } -static void phy_shutdown(struct device *dev) -{ - struct phy_device *phydev = to_phy_device(dev); - - if (phydev->state == PHY_READY || !phydev->attached_dev) - return; - - phy_disable_interrupts(phydev); -} - /** * phy_driver_register - register a phy_driver with the PHY layer * @new_driver: new phy_driver to register @@ -3180,7 +3172,6 @@ int phy_driver_register(struct phy_driver *new_driver, struct module *owner) new_driver->mdiodrv.driver.bus = &mdio_bus_type; new_driver->mdiodrv.driver.probe = phy_probe; new_driver->mdiodrv.driver.remove = phy_remove; - new_driver->mdiodrv.driver.shutdown = phy_shutdown; new_driver->mdiodrv.driver.owner = owner; new_driver->mdiodrv.driver.probe_type = PROBE_FORCE_SYNCHRONOUS; diff --git a/drivers/net/tap.c b/drivers/net/tap.c index 3c468ef8f245..8c010857e6d7 100644 --- a/drivers/net/tap.c +++ b/drivers/net/tap.c @@ -533,7 +533,7 @@ static int tap_open(struct inode *inode, struct file *file) q->sock.state = SS_CONNECTED; q->sock.file = file; q->sock.ops = &tap_socket_ops; - sock_init_data_uid(&q->sock, &q->sk, inode->i_uid); + sock_init_data_uid(&q->sock, &q->sk, current_fsuid()); q->sk.sk_write_space = tap_sock_write_space; q->sk.sk_destruct = tap_sock_destruct; q->flags = IFF_VNET_HDR | IFF_NO_PI | IFF_TAP; diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 509ba706781e..921ca59822b0 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -2200,7 +2200,9 @@ static void team_setup(struct net_device *dev) dev->hw_features = TEAM_VLAN_FEATURES | NETIF_F_HW_VLAN_CTAG_RX | - NETIF_F_HW_VLAN_CTAG_FILTER; + NETIF_F_HW_VLAN_CTAG_FILTER | + NETIF_F_HW_VLAN_STAG_RX | + NETIF_F_HW_VLAN_STAG_FILTER; dev->hw_features |= NETIF_F_GSO_ENCAP_ALL; dev->features |= dev->hw_features; diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 7c8db8f6f661..7544df1ff50e 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1588,7 +1588,7 @@ static bool tun_can_build_skb(struct tun_struct *tun, struct tun_file *tfile, if (zerocopy) return false; - if (SKB_DATA_ALIGN(len + TUN_RX_PAD) + + if (SKB_DATA_ALIGN(len + TUN_RX_PAD + XDP_PACKET_HEADROOM) + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) > PAGE_SIZE) return false; @@ -3457,7 +3457,7 @@ static int tun_chr_open(struct inode *inode, struct file * file) tfile->socket.file = file; tfile->socket.ops = &tun_socket_ops; - sock_init_data_uid(&tfile->socket, &tfile->sk, inode->i_uid); + sock_init_data_uid(&tfile->socket, &tfile->sk, current_fsuid()); tfile->sk.sk_write_space = tun_sock_write_space; tfile->sk.sk_sndbuf = INT_MAX; diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c index fb5f59d0d55d..f07bfe56ec87 100644 --- a/drivers/net/usb/cdc_ether.c +++ b/drivers/net/usb/cdc_ether.c @@ -618,6 +618,13 @@ static const struct usb_device_id products[] = { .match_flags = USB_DEVICE_ID_MATCH_INT_INFO | USB_DEVICE_ID_MATCH_DEVICE, .idVendor = 0x04DD, + .idProduct = 0x8005, /* A-300 */ + ZAURUS_FAKE_INTERFACE, + .driver_info = 0, +}, { + .match_flags = USB_DEVICE_ID_MATCH_INT_INFO + | USB_DEVICE_ID_MATCH_DEVICE, + .idVendor = 0x04DD, .idProduct = 0x8006, /* B-500/SL-5600 */ ZAURUS_MASTER_INTERFACE, .driver_info = 0, @@ -625,11 +632,25 @@ static const struct usb_device_id products[] = { .match_flags = USB_DEVICE_ID_MATCH_INT_INFO | USB_DEVICE_ID_MATCH_DEVICE, .idVendor = 0x04DD, + .idProduct = 0x8006, /* B-500/SL-5600 */ + ZAURUS_FAKE_INTERFACE, + .driver_info = 0, +}, { + .match_flags = USB_DEVICE_ID_MATCH_INT_INFO + | USB_DEVICE_ID_MATCH_DEVICE, + .idVendor = 0x04DD, .idProduct = 0x8007, /* C-700 */ ZAURUS_MASTER_INTERFACE, .driver_info = 0, }, { .match_flags = USB_DEVICE_ID_MATCH_INT_INFO + | USB_DEVICE_ID_MATCH_DEVICE, + .idVendor = 0x04DD, + .idProduct = 0x8007, /* C-700 */ + ZAURUS_FAKE_INTERFACE, + .driver_info = 0, +}, { + .match_flags = USB_DEVICE_ID_MATCH_INT_INFO | USB_DEVICE_ID_MATCH_DEVICE, .idVendor = 0x04DD, .idProduct = 0x9031, /* C-750 C-760 */ diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 64a9a80b2309..405e588f8a3a 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -1770,6 +1770,10 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod) } else if (!info->in || !info->out) status = usbnet_get_endpoints (dev, udev); else { + u8 ep_addrs[3] = { + info->in + USB_DIR_IN, info->out + USB_DIR_OUT, 0 + }; + dev->in = usb_rcvbulkpipe (xdev, info->in); dev->out = usb_sndbulkpipe (xdev, info->out); if (!(info->flags & FLAG_NO_SETINT)) @@ -1779,6 +1783,8 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod) else status = 0; + if (status == 0 && !usb_check_bulk_endpoints(udev, ep_addrs)) + status = -EINVAL; } if (status >= 0 && dev->status) status = init_status (dev, udev); diff --git a/drivers/net/usb/zaurus.c b/drivers/net/usb/zaurus.c index 7984f2157d22..df3617c4c44e 100644 --- a/drivers/net/usb/zaurus.c +++ b/drivers/net/usb/zaurus.c @@ -289,11 +289,25 @@ static const struct usb_device_id products [] = { .match_flags = USB_DEVICE_ID_MATCH_INT_INFO | USB_DEVICE_ID_MATCH_DEVICE, .idVendor = 0x04DD, + .idProduct = 0x8005, /* A-300 */ + ZAURUS_FAKE_INTERFACE, + .driver_info = (unsigned long)&bogus_mdlm_info, +}, { + .match_flags = USB_DEVICE_ID_MATCH_INT_INFO + | USB_DEVICE_ID_MATCH_DEVICE, + .idVendor = 0x04DD, .idProduct = 0x8006, /* B-500/SL-5600 */ ZAURUS_MASTER_INTERFACE, .driver_info = ZAURUS_PXA_INFO, }, { .match_flags = USB_DEVICE_ID_MATCH_INT_INFO + | USB_DEVICE_ID_MATCH_DEVICE, + .idVendor = 0x04DD, + .idProduct = 0x8006, /* B-500/SL-5600 */ + ZAURUS_FAKE_INTERFACE, + .driver_info = (unsigned long)&bogus_mdlm_info, +}, { + .match_flags = USB_DEVICE_ID_MATCH_INT_INFO | USB_DEVICE_ID_MATCH_DEVICE, .idVendor = 0x04DD, .idProduct = 0x8007, /* C-700 */ @@ -301,6 +315,13 @@ static const struct usb_device_id products [] = { .driver_info = ZAURUS_PXA_INFO, }, { .match_flags = USB_DEVICE_ID_MATCH_INT_INFO + | USB_DEVICE_ID_MATCH_DEVICE, + .idVendor = 0x04DD, + .idProduct = 0x8007, /* C-700 */ + ZAURUS_FAKE_INTERFACE, + .driver_info = (unsigned long)&bogus_mdlm_info, +}, { + .match_flags = USB_DEVICE_ID_MATCH_INT_INFO | USB_DEVICE_ID_MATCH_DEVICE, .idVendor = 0x04DD, .idProduct = 0x9031, /* C-750 C-760 */ diff --git a/drivers/net/veth.c b/drivers/net/veth.c index a71786b3e7ba..727b9278b9fe 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -1716,10 +1716,7 @@ static int veth_newlink(struct net *src_net, struct net_device *dev, nla_peer = data[VETH_INFO_PEER]; ifmp = nla_data(nla_peer); - err = rtnl_nla_parse_ifla(peer_tb, - nla_data(nla_peer) + sizeof(struct ifinfomsg), - nla_len(nla_peer) - sizeof(struct ifinfomsg), - NULL); + err = rtnl_nla_parse_ifinfomsg(peer_tb, nla_peer, extack); if (err < 0) return err; diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 075d5d42f5eb..21d3461fb5d1 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -2504,7 +2504,7 @@ static void virtnet_init_default_rss(struct virtnet_info *vi) vi->ctrl->rss.indirection_table[i] = indir_val; } - vi->ctrl->rss.max_tx_vq = vi->curr_queue_pairs; + vi->ctrl->rss.max_tx_vq = vi->has_rss ? vi->curr_queue_pairs : 0; vi->ctrl->rss.hash_key_length = vi->rss_key_size; netdev_rss_key_fill(vi->ctrl->rss.key, vi->rss_key_size); @@ -3825,6 +3825,8 @@ static int virtnet_probe(struct virtio_device *vdev) eth_hw_addr_set(dev, addr); } else { eth_hw_addr_random(dev); + dev_info(&vdev->dev, "Assigned random MAC address %pM\n", + dev->dev_addr); } /* Set up our device-specific information */ @@ -3940,8 +3942,6 @@ static int virtnet_probe(struct virtio_device *vdev) if (vi->has_rss || vi->has_rss_hash_report) virtnet_init_default_rss(vi); - _virtnet_set_queues(vi, vi->curr_queue_pairs); - /* serialize netdev register + virtio_device_ready() with ndo_open() */ rtnl_lock(); @@ -3954,6 +3954,26 @@ static int virtnet_probe(struct virtio_device *vdev) virtio_device_ready(vdev); + _virtnet_set_queues(vi, vi->curr_queue_pairs); + + /* a random MAC address has been assigned, notify the device. + * We don't fail probe if VIRTIO_NET_F_CTRL_MAC_ADDR is not there + * because many devices work fine without getting MAC explicitly + */ + if (!virtio_has_feature(vdev, VIRTIO_NET_F_MAC) && + virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_MAC_ADDR)) { + struct scatterlist sg; + + sg_init_one(&sg, dev->dev_addr, dev->addr_len); + if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MAC, + VIRTIO_NET_CTRL_MAC_ADDR_SET, &sg)) { + pr_debug("virtio_net: setting MAC address failed\n"); + rtnl_unlock(); + err = -EINVAL; + goto free_unregister_netdev; + } + } + rtnl_unlock(); err = virtnet_cpu_notif_add(vi); diff --git a/drivers/net/vxlan/vxlan_vnifilter.c b/drivers/net/vxlan/vxlan_vnifilter.c index 3e04af4c5daa..c5cf55030158 100644 --- a/drivers/net/vxlan/vxlan_vnifilter.c +++ b/drivers/net/vxlan/vxlan_vnifilter.c @@ -713,6 +713,12 @@ static struct vxlan_vni_node *vxlan_vni_alloc(struct vxlan_dev *vxlan, return vninode; } +static void vxlan_vni_free(struct vxlan_vni_node *vninode) +{ + free_percpu(vninode->stats); + kfree(vninode); +} + static int vxlan_vni_add(struct vxlan_dev *vxlan, struct vxlan_vni_group *vg, u32 vni, union vxlan_addr *group, @@ -740,7 +746,7 @@ static int vxlan_vni_add(struct vxlan_dev *vxlan, &vninode->vnode, vxlan_vni_rht_params); if (err) { - kfree(vninode); + vxlan_vni_free(vninode); return err; } @@ -763,8 +769,7 @@ static void vxlan_vni_node_rcu_free(struct rcu_head *rcu) struct vxlan_vni_node *v; v = container_of(rcu, struct vxlan_vni_node, rcu); - free_percpu(v->stats); - kfree(v); + vxlan_vni_free(v); } static int vxlan_vni_del(struct vxlan_dev *vxlan, diff --git a/drivers/net/wireguard/allowedips.c b/drivers/net/wireguard/allowedips.c index 5bf7822c53f1..0ba714ca5185 100644 --- a/drivers/net/wireguard/allowedips.c +++ b/drivers/net/wireguard/allowedips.c @@ -6,7 +6,7 @@ #include "allowedips.h" #include "peer.h" -enum { MAX_ALLOWEDIPS_BITS = 128 }; +enum { MAX_ALLOWEDIPS_DEPTH = 129 }; static struct kmem_cache *node_cache; @@ -42,7 +42,7 @@ static void push_rcu(struct allowedips_node **stack, struct allowedips_node __rcu *p, unsigned int *len) { if (rcu_access_pointer(p)) { - if (WARN_ON(IS_ENABLED(DEBUG) && *len >= MAX_ALLOWEDIPS_BITS)) + if (WARN_ON(IS_ENABLED(DEBUG) && *len >= MAX_ALLOWEDIPS_DEPTH)) return; stack[(*len)++] = rcu_dereference_raw(p); } @@ -55,7 +55,7 @@ static void node_free_rcu(struct rcu_head *rcu) static void root_free_rcu(struct rcu_head *rcu) { - struct allowedips_node *node, *stack[MAX_ALLOWEDIPS_BITS] = { + struct allowedips_node *node, *stack[MAX_ALLOWEDIPS_DEPTH] = { container_of(rcu, struct allowedips_node, rcu) }; unsigned int len = 1; @@ -68,7 +68,7 @@ static void root_free_rcu(struct rcu_head *rcu) static void root_remove_peer_lists(struct allowedips_node *root) { - struct allowedips_node *node, *stack[MAX_ALLOWEDIPS_BITS] = { root }; + struct allowedips_node *node, *stack[MAX_ALLOWEDIPS_DEPTH] = { root }; unsigned int len = 1; while (len > 0 && (node = stack[--len])) { diff --git a/drivers/net/wireguard/selftest/allowedips.c b/drivers/net/wireguard/selftest/allowedips.c index 19eac00b2381..c51c794e70a0 100644 --- a/drivers/net/wireguard/selftest/allowedips.c +++ b/drivers/net/wireguard/selftest/allowedips.c @@ -593,16 +593,20 @@ bool __init wg_allowedips_selftest(void) wg_allowedips_remove_by_peer(&t, a, &mutex); test_negative(4, a, 192, 168, 0, 1); - /* These will hit the WARN_ON(len >= MAX_ALLOWEDIPS_BITS) in free_node + /* These will hit the WARN_ON(len >= MAX_ALLOWEDIPS_DEPTH) in free_node * if something goes wrong. */ - for (i = 0; i < MAX_ALLOWEDIPS_BITS; ++i) { - part = cpu_to_be64(~(1LLU << (i % 64))); - memset(&ip, 0xff, 16); - memcpy((u8 *)&ip + (i < 64) * 8, &part, 8); + for (i = 0; i < 64; ++i) { + part = cpu_to_be64(~0LLU << i); + memset(&ip, 0xff, 8); + memcpy((u8 *)&ip + 8, &part, 8); + wg_allowedips_insert_v6(&t, &ip, 128, a, &mutex); + memcpy(&ip, &part, 8); + memset((u8 *)&ip + 8, 0, 8); wg_allowedips_insert_v6(&t, &ip, 128, a, &mutex); } - + memset(&ip, 0, 16); + wg_allowedips_insert_v6(&t, &ip, 128, a, &mutex); wg_allowedips_free(&t, &mutex); wg_allowedips_init(&t); diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/eeprom.c b/drivers/net/wireless/mediatek/mt76/mt7615/eeprom.c index 6dbaaf95ee38..2092aa373ab3 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/eeprom.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/eeprom.c @@ -123,12 +123,12 @@ mt7615_eeprom_parse_hw_band_cap(struct mt7615_dev *dev) case MT_EE_5GHZ: dev->mphy.cap.has_5ghz = true; break; - case MT_EE_2GHZ: - dev->mphy.cap.has_2ghz = true; - break; case MT_EE_DBDC: dev->dbdc_support = true; fallthrough; + case MT_EE_2GHZ: + dev->mphy.cap.has_2ghz = true; + break; default: dev->mphy.cap.has_2ghz = true; dev->mphy.cap.has_5ghz = true; diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c b/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c index 68511597599e..f7d392fce8c2 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c @@ -465,6 +465,7 @@ void mt76_connac2_mac_write_txwi(struct mt76_dev *dev, __le32 *txwi, BSS_CHANGED_BEACON_ENABLED)); bool inband_disc = !!(changed & (BSS_CHANGED_UNSOL_BCAST_PROBE_RESP | BSS_CHANGED_FILS_DISCOVERY)); + bool amsdu_en = wcid->amsdu; if (vif) { struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv; @@ -524,12 +525,14 @@ void mt76_connac2_mac_write_txwi(struct mt76_dev *dev, __le32 *txwi, txwi[4] = 0; val = FIELD_PREP(MT_TXD5_PID, pid); - if (pid >= MT_PACKET_ID_FIRST) + if (pid >= MT_PACKET_ID_FIRST) { val |= MT_TXD5_TX_STATUS_HOST; + amsdu_en = amsdu_en && !is_mt7921(dev); + } txwi[5] = cpu_to_le32(val); txwi[6] = 0; - txwi[7] = wcid->amsdu ? cpu_to_le32(MT_TXD7_HW_AMSDU) : 0; + txwi[7] = amsdu_en ? cpu_to_le32(MT_TXD7_HW_AMSDU) : 0; if (is_8023) mt76_connac2_mac_write_txwi_8023(txwi, skb, wcid); diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c index 60fbbd1ac2f7..172ba7199485 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c @@ -1280,7 +1280,7 @@ mt7921_set_antenna(struct ieee80211_hw *hw, u32 tx_ant, u32 rx_ant) return -EINVAL; if ((BIT(hweight8(tx_ant)) - 1) != tx_ant) - tx_ant = BIT(ffs(tx_ant) - 1) - 1; + return -EINVAL; mt7921_mutex_acquire(dev); diff --git a/drivers/net/wireless/realtek/rtw89/mac.c b/drivers/net/wireless/realtek/rtw89/mac.c index 077fddc5fa1e..4a1c9e18c530 100644 --- a/drivers/net/wireless/realtek/rtw89/mac.c +++ b/drivers/net/wireless/realtek/rtw89/mac.c @@ -2209,7 +2209,7 @@ static int cmac_dma_init(struct rtw89_dev *rtwdev, u8 mac_idx) u32 reg; int ret; - if (chip_id != RTL8852A && chip_id != RTL8852B) + if (chip_id != RTL8852B) return 0; ret = rtw89_mac_check_mac_en(rtwdev, mac_idx, RTW89_CMAC_SEL); diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index c35c085dbc87..c3a8d78a41a7 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -396,7 +396,7 @@ static void xenvif_get_requests(struct xenvif_queue *queue, struct gnttab_map_grant_ref *gop = queue->tx_map_ops + *map_ops; struct xen_netif_tx_request *txp = first; - nr_slots = shinfo->nr_frags + 1; + nr_slots = shinfo->nr_frags + frag_overflow + 1; copy_count(skb) = 0; XENVIF_TX_CB(skb)->split_mask = 0; @@ -462,8 +462,8 @@ static void xenvif_get_requests(struct xenvif_queue *queue, } } - for (shinfo->nr_frags = 0; shinfo->nr_frags < nr_slots; - shinfo->nr_frags++, gop++) { + for (shinfo->nr_frags = 0; nr_slots > 0 && shinfo->nr_frags < MAX_SKB_FRAGS; + shinfo->nr_frags++, gop++, nr_slots--) { index = pending_index(queue->pending_cons++); pending_idx = queue->pending_ring[index]; xenvif_tx_create_map_op(queue, pending_idx, txp, @@ -476,12 +476,12 @@ static void xenvif_get_requests(struct xenvif_queue *queue, txp++; } - if (frag_overflow) { + if (nr_slots > 0) { shinfo = skb_shinfo(nskb); frags = shinfo->frags; - for (shinfo->nr_frags = 0; shinfo->nr_frags < frag_overflow; + for (shinfo->nr_frags = 0; shinfo->nr_frags < nr_slots; shinfo->nr_frags++, txp++, gop++) { index = pending_index(queue->pending_cons++); pending_idx = queue->pending_ring[index]; @@ -492,6 +492,11 @@ static void xenvif_get_requests(struct xenvif_queue *queue, } skb_shinfo(skb)->frag_list = nskb; + } else if (nskb) { + /* A frag_list skb was allocated but it is no longer needed + * because enough slots were converted to copy ops above. + */ + kfree_skb(nskb); } (*copy_ops) = cop - queue->tx_copy_ops; diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index ce2e628f94a0..b30269f5e68f 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -3504,7 +3504,8 @@ static const struct pci_device_id nvme_id_table[] = { { PCI_DEVICE(0x1d97, 0x2263), /* SPCC */ .driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, }, { PCI_DEVICE(0x144d, 0xa80b), /* Samsung PM9B1 256G and 512G */ - .driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, }, + .driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES | + NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(0x144d, 0xa809), /* Samsung MZALQ256HBJD 256G */ .driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, }, { PCI_DEVICE(0x1cc4, 0x6303), /* UMIS RPJTJ512MGE1QDY 512G */ diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 80383213b882..c478480f54aa 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -923,6 +923,7 @@ static int nvme_rdma_configure_io_queues(struct nvme_rdma_ctrl *ctrl, bool new) goto out_cleanup_tagset; if (!new) { + nvme_start_freeze(&ctrl->ctrl); nvme_start_queues(&ctrl->ctrl); if (!nvme_wait_freeze_timeout(&ctrl->ctrl, NVME_IO_TIMEOUT)) { /* @@ -931,6 +932,7 @@ static int nvme_rdma_configure_io_queues(struct nvme_rdma_ctrl *ctrl, bool new) * to be safe. */ ret = -ENODEV; + nvme_unfreeze(&ctrl->ctrl); goto out_wait_freeze_timed_out; } blk_mq_update_nr_hw_queues(ctrl->ctrl.tagset, @@ -980,7 +982,6 @@ static void nvme_rdma_teardown_io_queues(struct nvme_rdma_ctrl *ctrl, bool remove) { if (ctrl->ctrl.queue_count > 1) { - nvme_start_freeze(&ctrl->ctrl); nvme_stop_queues(&ctrl->ctrl); nvme_sync_io_queues(&ctrl->ctrl); nvme_rdma_stop_io_queues(ctrl); diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 8f17cbec5a0e..f2fedd25915f 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -1890,6 +1890,7 @@ static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new) goto out_cleanup_connect_q; if (!new) { + nvme_start_freeze(ctrl); nvme_start_queues(ctrl); if (!nvme_wait_freeze_timeout(ctrl, NVME_IO_TIMEOUT)) { /* @@ -1898,6 +1899,7 @@ static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new) * to be safe. */ ret = -ENODEV; + nvme_unfreeze(ctrl); goto out_wait_freeze_timed_out; } blk_mq_update_nr_hw_queues(ctrl->tagset, @@ -2002,7 +2004,6 @@ static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl, if (ctrl->queue_count <= 1) return; nvme_stop_admin_queue(ctrl); - nvme_start_freeze(ctrl); nvme_stop_queues(ctrl); nvme_sync_io_queues(ctrl); nvme_tcp_stop_io_queues(ctrl); diff --git a/drivers/of/dynamic.c b/drivers/of/dynamic.c index cd3821a6444f..4e436f2d13ae 100644 --- a/drivers/of/dynamic.c +++ b/drivers/of/dynamic.c @@ -63,15 +63,14 @@ int of_reconfig_notifier_unregister(struct notifier_block *nb) } EXPORT_SYMBOL_GPL(of_reconfig_notifier_unregister); -#ifdef DEBUG -const char *action_names[] = { +static const char *action_names[] = { + [0] = "INVALID", [OF_RECONFIG_ATTACH_NODE] = "ATTACH_NODE", [OF_RECONFIG_DETACH_NODE] = "DETACH_NODE", [OF_RECONFIG_ADD_PROPERTY] = "ADD_PROPERTY", [OF_RECONFIG_REMOVE_PROPERTY] = "REMOVE_PROPERTY", [OF_RECONFIG_UPDATE_PROPERTY] = "UPDATE_PROPERTY", }; -#endif int of_reconfig_notify(unsigned long action, struct of_reconfig_data *p) { @@ -594,21 +593,9 @@ static int __of_changeset_entry_apply(struct of_changeset_entry *ce) } ret = __of_add_property(ce->np, ce->prop); - if (ret) { - pr_err("changeset: add_property failed @%pOF/%s\n", - ce->np, - ce->prop->name); - break; - } break; case OF_RECONFIG_REMOVE_PROPERTY: ret = __of_remove_property(ce->np, ce->prop); - if (ret) { - pr_err("changeset: remove_property failed @%pOF/%s\n", - ce->np, - ce->prop->name); - break; - } break; case OF_RECONFIG_UPDATE_PROPERTY: @@ -622,20 +609,17 @@ static int __of_changeset_entry_apply(struct of_changeset_entry *ce) } ret = __of_update_property(ce->np, ce->prop, &old_prop); - if (ret) { - pr_err("changeset: update_property failed @%pOF/%s\n", - ce->np, - ce->prop->name); - break; - } break; default: ret = -EINVAL; } raw_spin_unlock_irqrestore(&devtree_lock, flags); - if (ret) + if (ret) { + pr_err("changeset: apply failed: %-15s %pOF:%s\n", + action_names[ce->action], ce->np, ce->prop->name); return ret; + } switch (ce->action) { case OF_RECONFIG_ATTACH_NODE: @@ -921,6 +905,9 @@ int of_changeset_action(struct of_changeset *ocs, unsigned long action, if (!ce) return -ENOMEM; + if (WARN_ON(action >= ARRAY_SIZE(action_names))) + return -EINVAL; + /* get a reference to the node */ ce->action = action; ce->np = of_node_get(np); diff --git a/drivers/of/kexec.c b/drivers/of/kexec.c index f26d2ba8a371..68278340cecf 100644 --- a/drivers/of/kexec.c +++ b/drivers/of/kexec.c @@ -184,7 +184,8 @@ int __init ima_free_kexec_buffer(void) if (ret) return ret; - return memblock_phys_free(addr, size); + memblock_free_late(addr, size); + return 0; } #endif diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c index b89ab5d9fea5..9be6ed47a1ce 100644 --- a/drivers/of/unittest.c +++ b/drivers/of/unittest.c @@ -657,12 +657,12 @@ static void __init of_unittest_parse_phandle_with_args_map(void) memset(&args, 0, sizeof(args)); EXPECT_BEGIN(KERN_INFO, - "OF: /testcase-data/phandle-tests/consumer-b: could not find phandle"); + "OF: /testcase-data/phandle-tests/consumer-b: could not find phandle 12345678"); rc = of_parse_phandle_with_args_map(np, "phandle-list-bad-phandle", "phandle", 0, &args); EXPECT_END(KERN_INFO, - "OF: /testcase-data/phandle-tests/consumer-b: could not find phandle"); + "OF: /testcase-data/phandle-tests/consumer-b: could not find phandle 12345678"); unittest(rc == -EINVAL, "expected:%i got:%i\n", -EINVAL, rc); diff --git a/drivers/pci/controller/dwc/pcie-tegra194.c b/drivers/pci/controller/dwc/pcie-tegra194.c index 1b6b437823d2..528e73ccfa43 100644 --- a/drivers/pci/controller/dwc/pcie-tegra194.c +++ b/drivers/pci/controller/dwc/pcie-tegra194.c @@ -224,6 +224,7 @@ #define EP_STATE_ENABLED 1 static const unsigned int pcie_gen_freq[] = { + GEN1_CORE_CLK_FREQ, /* PCI_EXP_LNKSTA_CLS == 0; undefined */ GEN1_CORE_CLK_FREQ, GEN2_CORE_CLK_FREQ, GEN3_CORE_CLK_FREQ, @@ -455,7 +456,11 @@ static irqreturn_t tegra_pcie_ep_irq_thread(int irq, void *arg) speed = dw_pcie_readw_dbi(pci, pcie->pcie_cap_base + PCI_EXP_LNKSTA) & PCI_EXP_LNKSTA_CLS; - clk_set_rate(pcie->core_clk, pcie_gen_freq[speed - 1]); + + if (speed >= ARRAY_SIZE(pcie_gen_freq)) + speed = 0; + + clk_set_rate(pcie->core_clk, pcie_gen_freq[speed]); if (pcie->of_data->has_ltr_req_fix) return IRQ_HANDLED; @@ -1016,7 +1021,11 @@ retry_link: speed = dw_pcie_readw_dbi(pci, pcie->pcie_cap_base + PCI_EXP_LNKSTA) & PCI_EXP_LNKSTA_CLS; - clk_set_rate(pcie->core_clk, pcie_gen_freq[speed - 1]); + + if (speed >= ARRAY_SIZE(pcie_gen_freq)) + speed = 0; + + clk_set_rate(pcie->core_clk, pcie_gen_freq[speed]); tegra_pcie_enable_interrupts(pp); diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c index 6efa3d8db9a5..ea0195337bab 100644 --- a/drivers/pci/hotplug/acpiphp_glue.c +++ b/drivers/pci/hotplug/acpiphp_glue.c @@ -504,12 +504,15 @@ static void enable_slot(struct acpiphp_slot *slot, bool bridge) if (pass && dev->subordinate) { check_hotplug_bridge(slot, dev); pcibios_resource_survey_bus(dev->subordinate); - __pci_bus_size_bridges(dev->subordinate, - &add_list); + if (pci_is_root_bus(bus)) + __pci_bus_size_bridges(dev->subordinate, &add_list); } } } - __pci_bus_assign_resources(bus, &add_list, NULL); + if (pci_is_root_bus(bus)) + __pci_bus_assign_resources(bus, &add_list, NULL); + else + pci_assign_unassigned_bridge_resources(bus->self); } acpiphp_sanitize_bus(bus); diff --git a/drivers/pcmcia/rsrc_nonstatic.c b/drivers/pcmcia/rsrc_nonstatic.c index ad1141fddb4c..8bda75990bce 100644 --- a/drivers/pcmcia/rsrc_nonstatic.c +++ b/drivers/pcmcia/rsrc_nonstatic.c @@ -1053,6 +1053,8 @@ static void nonstatic_release_resource_db(struct pcmcia_socket *s) q = p->next; kfree(p); } + + kfree(data); } diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c index a8df77e80549..2b6d996e393e 100644 --- a/drivers/pinctrl/pinctrl-amd.c +++ b/drivers/pinctrl/pinctrl-amd.c @@ -748,7 +748,7 @@ static int amd_pinconf_get(struct pinctrl_dev *pctldev, break; default: - dev_err(&gpio_dev->pdev->dev, "Invalid config param %04x\n", + dev_dbg(&gpio_dev->pdev->dev, "Invalid config param %04x\n", param); return -ENOTSUPP; } @@ -798,7 +798,7 @@ static int amd_pinconf_set(struct pinctrl_dev *pctldev, unsigned int pin, break; default: - dev_err(&gpio_dev->pdev->dev, + dev_dbg(&gpio_dev->pdev->dev, "Invalid config param %04x\n", param); ret = -ENOTSUPP; } @@ -862,6 +862,33 @@ static const struct pinconf_ops amd_pinconf_ops = { .pin_config_group_set = amd_pinconf_group_set, }; +static void amd_gpio_irq_init(struct amd_gpio *gpio_dev) +{ + struct pinctrl_desc *desc = gpio_dev->pctrl->desc; + unsigned long flags; + u32 pin_reg, mask; + int i; + + mask = BIT(WAKE_CNTRL_OFF_S0I3) | BIT(WAKE_CNTRL_OFF_S3) | + BIT(WAKE_CNTRL_OFF_S4); + + for (i = 0; i < desc->npins; i++) { + int pin = desc->pins[i].number; + const struct pin_desc *pd = pin_desc_get(gpio_dev->pctrl, pin); + + if (!pd) + continue; + + raw_spin_lock_irqsave(&gpio_dev->lock, flags); + + pin_reg = readl(gpio_dev->base + pin * 4); + pin_reg &= ~mask; + writel(pin_reg, gpio_dev->base + pin * 4); + + raw_spin_unlock_irqrestore(&gpio_dev->lock, flags); + } +} + #ifdef CONFIG_PM_SLEEP static bool amd_gpio_should_save(struct amd_gpio *gpio_dev, unsigned int pin) { @@ -1099,6 +1126,9 @@ static int amd_gpio_probe(struct platform_device *pdev) return PTR_ERR(gpio_dev->pctrl); } + /* Disable and mask interrupts */ + amd_gpio_irq_init(gpio_dev); + girq = &gpio_dev->gc.irq; gpio_irq_chip_set_chip(girq, &amd_gpio_irqchip); /* This will let us handle the parent IRQ in the driver */ diff --git a/drivers/pinctrl/renesas/pinctrl-rza2.c b/drivers/pinctrl/renesas/pinctrl-rza2.c index c0a04f1ee994..12126e30dc20 100644 --- a/drivers/pinctrl/renesas/pinctrl-rza2.c +++ b/drivers/pinctrl/renesas/pinctrl-rza2.c @@ -14,6 +14,7 @@ #include <linux/gpio/driver.h> #include <linux/io.h> #include <linux/module.h> +#include <linux/mutex.h> #include <linux/of_device.h> #include <linux/pinctrl/pinmux.h> @@ -46,6 +47,7 @@ struct rza2_pinctrl_priv { struct pinctrl_dev *pctl; struct pinctrl_gpio_range gpio_range; int npins; + struct mutex mutex; /* serialize adding groups and functions */ }; #define RZA2_PDR(port) (0x0000 + (port) * 2) /* Direction 16-bit */ @@ -358,10 +360,14 @@ static int rza2_dt_node_to_map(struct pinctrl_dev *pctldev, psel_val[i] = MUX_FUNC(value); } + mutex_lock(&priv->mutex); + /* Register a single pin group listing all the pins we read from DT */ gsel = pinctrl_generic_add_group(pctldev, np->name, pins, npins, NULL); - if (gsel < 0) - return gsel; + if (gsel < 0) { + ret = gsel; + goto unlock; + } /* * Register a single group function where the 'data' is an array PSEL @@ -390,6 +396,8 @@ static int rza2_dt_node_to_map(struct pinctrl_dev *pctldev, (*map)->data.mux.function = np->name; *num_maps = 1; + mutex_unlock(&priv->mutex); + return 0; remove_function: @@ -398,6 +406,9 @@ remove_function: remove_group: pinctrl_generic_remove_group(pctldev, gsel); +unlock: + mutex_unlock(&priv->mutex); + dev_err(priv->dev, "Unable to parse DT node %s\n", np->name); return ret; @@ -473,6 +484,8 @@ static int rza2_pinctrl_probe(struct platform_device *pdev) if (IS_ERR(priv->base)) return PTR_ERR(priv->base); + mutex_init(&priv->mutex); + platform_set_drvdata(pdev, priv); priv->npins = (int)(uintptr_t)of_device_get_match_data(&pdev->dev) * diff --git a/drivers/pinctrl/renesas/pinctrl-rzg2l.c b/drivers/pinctrl/renesas/pinctrl-rzg2l.c index fd11d28e5a1e..2a617832a7e6 100644 --- a/drivers/pinctrl/renesas/pinctrl-rzg2l.c +++ b/drivers/pinctrl/renesas/pinctrl-rzg2l.c @@ -11,6 +11,7 @@ #include <linux/io.h> #include <linux/interrupt.h> #include <linux/module.h> +#include <linux/mutex.h> #include <linux/of_device.h> #include <linux/of_irq.h> #include <linux/pinctrl/pinconf-generic.h> @@ -146,10 +147,11 @@ struct rzg2l_pinctrl { struct gpio_chip gpio_chip; struct pinctrl_gpio_range gpio_range; DECLARE_BITMAP(tint_slot, RZG2L_TINT_MAX_INTERRUPT); - spinlock_t bitmap_lock; + spinlock_t bitmap_lock; /* protect tint_slot bitmap */ unsigned int hwirq[RZG2L_TINT_MAX_INTERRUPT]; - spinlock_t lock; + spinlock_t lock; /* lock read/write registers */ + struct mutex mutex; /* serialize adding groups and functions */ }; static const unsigned int iolh_groupa_mA[] = { 2, 4, 8, 12 }; @@ -359,11 +361,13 @@ static int rzg2l_dt_subnode_to_map(struct pinctrl_dev *pctldev, name = np->name; } + mutex_lock(&pctrl->mutex); + /* Register a single pin group listing all the pins we read from DT */ gsel = pinctrl_generic_add_group(pctldev, name, pins, num_pinmux, NULL); if (gsel < 0) { ret = gsel; - goto done; + goto unlock; } /* @@ -377,6 +381,8 @@ static int rzg2l_dt_subnode_to_map(struct pinctrl_dev *pctldev, goto remove_group; } + mutex_unlock(&pctrl->mutex); + maps[idx].type = PIN_MAP_TYPE_MUX_GROUP; maps[idx].data.mux.group = name; maps[idx].data.mux.function = name; @@ -388,6 +394,8 @@ static int rzg2l_dt_subnode_to_map(struct pinctrl_dev *pctldev, remove_group: pinctrl_generic_remove_group(pctldev, gsel); +unlock: + mutex_unlock(&pctrl->mutex); done: *index = idx; kfree(configs); @@ -1501,6 +1509,7 @@ static int rzg2l_pinctrl_probe(struct platform_device *pdev) spin_lock_init(&pctrl->lock); spin_lock_init(&pctrl->bitmap_lock); + mutex_init(&pctrl->mutex); platform_set_drvdata(pdev, pctrl); diff --git a/drivers/pinctrl/renesas/pinctrl-rzv2m.c b/drivers/pinctrl/renesas/pinctrl-rzv2m.c index 35f382b055e8..2858800288bb 100644 --- a/drivers/pinctrl/renesas/pinctrl-rzv2m.c +++ b/drivers/pinctrl/renesas/pinctrl-rzv2m.c @@ -14,6 +14,7 @@ #include <linux/gpio/driver.h> #include <linux/io.h> #include <linux/module.h> +#include <linux/mutex.h> #include <linux/of_device.h> #include <linux/pinctrl/pinconf-generic.h> #include <linux/pinctrl/pinconf.h> @@ -121,7 +122,8 @@ struct rzv2m_pinctrl { struct gpio_chip gpio_chip; struct pinctrl_gpio_range gpio_range; - spinlock_t lock; + spinlock_t lock; /* lock read/write registers */ + struct mutex mutex; /* serialize adding groups and functions */ }; static const unsigned int drv_1_8V_group2_uA[] = { 1800, 3800, 7800, 11000 }; @@ -320,11 +322,13 @@ static int rzv2m_dt_subnode_to_map(struct pinctrl_dev *pctldev, name = np->name; } + mutex_lock(&pctrl->mutex); + /* Register a single pin group listing all the pins we read from DT */ gsel = pinctrl_generic_add_group(pctldev, name, pins, num_pinmux, NULL); if (gsel < 0) { ret = gsel; - goto done; + goto unlock; } /* @@ -338,6 +342,8 @@ static int rzv2m_dt_subnode_to_map(struct pinctrl_dev *pctldev, goto remove_group; } + mutex_unlock(&pctrl->mutex); + maps[idx].type = PIN_MAP_TYPE_MUX_GROUP; maps[idx].data.mux.group = name; maps[idx].data.mux.function = name; @@ -349,6 +355,8 @@ static int rzv2m_dt_subnode_to_map(struct pinctrl_dev *pctldev, remove_group: pinctrl_generic_remove_group(pctldev, gsel); +unlock: + mutex_unlock(&pctrl->mutex); done: *index = idx; kfree(configs); @@ -1070,6 +1078,7 @@ static int rzv2m_pinctrl_probe(struct platform_device *pdev) } spin_lock_init(&pctrl->lock); + mutex_init(&pctrl->mutex); platform_set_drvdata(pdev, pctrl); diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c index bd38c7dcae34..de03b8889e9d 100644 --- a/drivers/platform/x86/ideapad-laptop.c +++ b/drivers/platform/x86/ideapad-laptop.c @@ -1176,6 +1176,11 @@ static const struct key_entry ideapad_keymap[] = { { KE_IGNORE, 0x03 | IDEAPAD_WMI_KEY }, /* Customizable Lenovo Hotkey ("star" with 'S' inside) */ { KE_KEY, 0x01 | IDEAPAD_WMI_KEY, { KEY_FAVORITES } }, + { KE_KEY, 0x04 | IDEAPAD_WMI_KEY, { KEY_SELECTIVE_SCREENSHOT } }, + /* Lenovo Support */ + { KE_KEY, 0x07 | IDEAPAD_WMI_KEY, { KEY_HELP } }, + { KE_KEY, 0x0e | IDEAPAD_WMI_KEY, { KEY_PICKUP_PHONE } }, + { KE_KEY, 0x0f | IDEAPAD_WMI_KEY, { KEY_HANGUP_PHONE } }, /* Dark mode toggle */ { KE_KEY, 0x13 | IDEAPAD_WMI_KEY, { KEY_PROG1 } }, /* Sound profile switch */ diff --git a/drivers/platform/x86/serial-multi-instantiate.c b/drivers/platform/x86/serial-multi-instantiate.c index 5362f1a7b77c..7a9c758e9547 100644 --- a/drivers/platform/x86/serial-multi-instantiate.c +++ b/drivers/platform/x86/serial-multi-instantiate.c @@ -21,6 +21,7 @@ #define IRQ_RESOURCE_NONE 0 #define IRQ_RESOURCE_GPIO 1 #define IRQ_RESOURCE_APIC 2 +#define IRQ_RESOURCE_AUTO 3 enum smi_bus_type { SMI_I2C, @@ -52,6 +53,18 @@ static int smi_get_irq(struct platform_device *pdev, struct acpi_device *adev, int ret; switch (inst->flags & IRQ_RESOURCE_TYPE) { + case IRQ_RESOURCE_AUTO: + ret = acpi_dev_gpio_irq_get(adev, inst->irq_idx); + if (ret > 0) { + dev_dbg(&pdev->dev, "Using gpio irq\n"); + break; + } + ret = platform_get_irq(pdev, inst->irq_idx); + if (ret > 0) { + dev_dbg(&pdev->dev, "Using platform irq\n"); + break; + } + break; case IRQ_RESOURCE_GPIO: ret = acpi_dev_gpio_irq_get(adev, inst->irq_idx); break; @@ -308,10 +321,23 @@ static const struct smi_node int3515_data = { static const struct smi_node cs35l41_hda = { .instances = { - { "cs35l41-hda", IRQ_RESOURCE_GPIO, 0 }, - { "cs35l41-hda", IRQ_RESOURCE_GPIO, 0 }, - { "cs35l41-hda", IRQ_RESOURCE_GPIO, 0 }, - { "cs35l41-hda", IRQ_RESOURCE_GPIO, 0 }, + { "cs35l41-hda", IRQ_RESOURCE_AUTO, 0 }, + { "cs35l41-hda", IRQ_RESOURCE_AUTO, 0 }, + { "cs35l41-hda", IRQ_RESOURCE_AUTO, 0 }, + { "cs35l41-hda", IRQ_RESOURCE_AUTO, 0 }, + {} + }, + .bus_type = SMI_AUTO_DETECT, +}; + +static const struct smi_node cs35l56_hda = { + .instances = { + { "cs35l56-hda", IRQ_RESOURCE_AUTO, 0 }, + { "cs35l56-hda", IRQ_RESOURCE_AUTO, 0 }, + { "cs35l56-hda", IRQ_RESOURCE_AUTO, 0 }, + { "cs35l56-hda", IRQ_RESOURCE_AUTO, 0 }, + /* a 5th entry is an alias address, not a real device */ + { "cs35l56-hda_dummy_dev" }, {} }, .bus_type = SMI_AUTO_DETECT, @@ -325,6 +351,7 @@ static const struct acpi_device_id smi_acpi_ids[] = { { "BSG1160", (unsigned long)&bsg1160_data }, { "BSG2150", (unsigned long)&bsg2150_data }, { "CSC3551", (unsigned long)&cs35l41_hda }, + { "CSC3556", (unsigned long)&cs35l56_hda }, { "INT3515", (unsigned long)&int3515_data }, /* Non-conforming _HID for Cirrus Logic already released */ { "CLSA0100", (unsigned long)&cs35l41_hda }, diff --git a/drivers/rtc/rtc-ds1685.c b/drivers/rtc/rtc-ds1685.c index 5db9c737c022..db7216f14164 100644 --- a/drivers/rtc/rtc-ds1685.c +++ b/drivers/rtc/rtc-ds1685.c @@ -1434,7 +1434,7 @@ ds1685_rtc_poweroff(struct platform_device *pdev) unreachable(); } } -EXPORT_SYMBOL(ds1685_rtc_poweroff); +EXPORT_SYMBOL_GPL(ds1685_rtc_poweroff); /* ----------------------------------------------------------------------- */ diff --git a/drivers/s390/crypto/zcrypt_msgtype6.c b/drivers/s390/crypto/zcrypt_msgtype6.c index f99a9ef42116..84e3ad290f6b 100644 --- a/drivers/s390/crypto/zcrypt_msgtype6.c +++ b/drivers/s390/crypto/zcrypt_msgtype6.c @@ -926,8 +926,7 @@ static void zcrypt_msgtype6_receive(struct ap_queue *aq, .type = TYPE82_RSP_CODE, .reply_code = REP82_ERROR_MACHINE_FAILURE, }; - struct response_type *resp_type = - (struct response_type *)msg->private; + struct response_type *resp_type = msg->private; struct type86x_reply *t86r; int len; @@ -982,8 +981,7 @@ static void zcrypt_msgtype6_receive_ep11(struct ap_queue *aq, .type = TYPE82_RSP_CODE, .reply_code = REP82_ERROR_MACHINE_FAILURE, }; - struct response_type *resp_type = - (struct response_type *)msg->private; + struct response_type *resp_type = msg->private; struct type86_ep11_reply *t86r; int len; @@ -1156,23 +1154,36 @@ static long zcrypt_msgtype6_send_cprb(bool userspace, struct zcrypt_queue *zq, struct ica_xcRB *xcrb, struct ap_message *ap_msg) { - int rc; - struct response_type *rtype = (struct response_type *)(ap_msg->private); + struct response_type *rtype = ap_msg->private; struct { struct type6_hdr hdr; struct CPRBX cprbx; /* ... more data blocks ... */ } __packed * msg = ap_msg->msg; - - /* - * Set the queue's reply buffer length minus 128 byte padding - * as reply limit for the card firmware. - */ - msg->hdr.fromcardlen1 = min_t(unsigned int, msg->hdr.fromcardlen1, - zq->reply.bufsize - 128); - if (msg->hdr.fromcardlen2) - msg->hdr.fromcardlen2 = - zq->reply.bufsize - msg->hdr.fromcardlen1 - 128; + unsigned int max_payload_size; + int rc, delta; + + /* calculate maximum payload for this card and msg type */ + max_payload_size = zq->reply.bufsize - sizeof(struct type86_fmt2_msg); + + /* limit each of the two from fields to the maximum payload size */ + msg->hdr.fromcardlen1 = min(msg->hdr.fromcardlen1, max_payload_size); + msg->hdr.fromcardlen2 = min(msg->hdr.fromcardlen2, max_payload_size); + + /* calculate delta if the sum of both exceeds max payload size */ + delta = msg->hdr.fromcardlen1 + msg->hdr.fromcardlen2 + - max_payload_size; + if (delta > 0) { + /* + * Sum exceeds maximum payload size, prune fromcardlen1 + * (always trust fromcardlen2) + */ + if (delta > msg->hdr.fromcardlen1) { + rc = -EINVAL; + goto out; + } + msg->hdr.fromcardlen1 -= delta; + } init_completion(&rtype->work); rc = ap_queue_message(zq->queue, ap_msg); @@ -1243,7 +1254,7 @@ static long zcrypt_msgtype6_send_ep11_cprb(bool userspace, struct zcrypt_queue * { int rc; unsigned int lfmt; - struct response_type *rtype = (struct response_type *)(ap_msg->private); + struct response_type *rtype = ap_msg->private; struct { struct type6_hdr hdr; struct ep11_cprb cprbx; @@ -1365,7 +1376,7 @@ static long zcrypt_msgtype6_rng(struct zcrypt_queue *zq, short int verb_length; short int key_length; } __packed * msg = ap_msg->msg; - struct response_type *rtype = (struct response_type *)(ap_msg->private); + struct response_type *rtype = ap_msg->private; int rc; msg->cprbx.domain = AP_QID_QUEUE(zq->queue->qid); diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index 1d195429753d..613eab729704 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -716,7 +716,6 @@ struct qeth_card_info { u16 chid; u8 ids_valid:1; /* cssid,iid,chid */ u8 dev_addr_is_registered:1; - u8 open_when_online:1; u8 promisc_mode:1; u8 use_v1_blkt:1; u8 is_vm_nic:1; diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 8bd9fd51208c..ae4b6d24bc90 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -5371,8 +5371,6 @@ int qeth_set_offline(struct qeth_card *card, const struct qeth_discipline *disc, qeth_clear_ipacmd_list(card); rtnl_lock(); - card->info.open_when_online = card->dev->flags & IFF_UP; - dev_close(card->dev); netif_device_detach(card->dev); netif_carrier_off(card->dev); rtnl_unlock(); diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index c6ded3fdd715..9ef2118fc7a2 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -2387,9 +2387,12 @@ static int qeth_l2_set_online(struct qeth_card *card, bool carrier_ok) qeth_enable_hw_features(dev); qeth_l2_enable_brport_features(card); - if (card->info.open_when_online) { - card->info.open_when_online = 0; - dev_open(dev, NULL); + if (netif_running(dev)) { + local_bh_disable(); + napi_schedule(&card->napi); + /* kick-start the NAPI softirq: */ + local_bh_enable(); + qeth_l2_set_rx_mode(dev); } rtnl_unlock(); } diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index d8487a10cd55..c0f30cefec10 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -2017,9 +2017,11 @@ static int qeth_l3_set_online(struct qeth_card *card, bool carrier_ok) netif_device_attach(dev); qeth_enable_hw_features(dev); - if (card->info.open_when_online) { - card->info.open_when_online = 0; - dev_open(dev, NULL); + if (netif_running(dev)) { + local_bh_disable(); + napi_schedule(&card->napi); + /* kick-start the NAPI softirq: */ + local_bh_enable(); } rtnl_unlock(); } diff --git a/drivers/s390/scsi/zfcp_fc.c b/drivers/s390/scsi/zfcp_fc.c index 77917b339870..a64def01d824 100644 --- a/drivers/s390/scsi/zfcp_fc.c +++ b/drivers/s390/scsi/zfcp_fc.c @@ -534,8 +534,7 @@ static void zfcp_fc_adisc_handler(void *data) /* re-init to undo drop from zfcp_fc_adisc() */ port->d_id = ntoh24(adisc_resp->adisc_port_id); - /* port is good, unblock rport without going through erp */ - zfcp_scsi_schedule_rport_register(port); + /* port is still good, nothing to do */ out: atomic_andnot(ZFCP_STATUS_PORT_LINK_TEST, &port->status); put_device(&port->dev); @@ -595,9 +594,6 @@ void zfcp_fc_link_test_work(struct work_struct *work) int retval; set_worker_desc("zadisc%16llx", port->wwpn); /* < WORKER_DESC_LEN=24 */ - get_device(&port->dev); - port->rport_task = RPORT_DEL; - zfcp_scsi_rport_work(&port->rport_work); /* only issue one test command at one time per port */ if (atomic_read(&port->status) & ZFCP_STATUS_PORT_LINK_TEST) diff --git a/drivers/scsi/53c700.c b/drivers/scsi/53c700.c index e1e4f9d10887..857be0f3ae5b 100644 --- a/drivers/scsi/53c700.c +++ b/drivers/scsi/53c700.c @@ -1598,7 +1598,7 @@ NCR_700_intr(int irq, void *dev_id) printk("scsi%d (%d:%d) PHASE MISMATCH IN SEND MESSAGE %d remain, return %p[%04x], phase %s\n", host->host_no, pun, lun, count, (void *)temp, temp - hostdata->pScript, sbcl_to_string(NCR_700_readb(host, SBCL_REG))); #endif resume_offset = hostdata->pScript + Ent_SendMessagePhaseMismatch; - } else if(dsp >= to32bit(&slot->pSG[0].ins) && + } else if (slot && dsp >= to32bit(&slot->pSG[0].ins) && dsp <= to32bit(&slot->pSG[NCR_700_SG_SEGMENTS].ins)) { int data_transfer = NCR_700_readl(host, DBC_REG) & 0xffffff; int SGcount = (dsp - to32bit(&slot->pSG[0].ins))/sizeof(struct NCR_700_SG_List); diff --git a/drivers/scsi/fnic/fnic.h b/drivers/scsi/fnic/fnic.h index d82de34f6fd7..e51e92f932fa 100644 --- a/drivers/scsi/fnic/fnic.h +++ b/drivers/scsi/fnic/fnic.h @@ -27,7 +27,7 @@ #define DRV_NAME "fnic" #define DRV_DESCRIPTION "Cisco FCoE HBA Driver" -#define DRV_VERSION "1.6.0.54" +#define DRV_VERSION "1.6.0.55" #define PFX DRV_NAME ": " #define DFX DRV_NAME "%d: " diff --git a/drivers/scsi/fnic/fnic_scsi.c b/drivers/scsi/fnic/fnic_scsi.c index 26dbd347156e..be89ce96df46 100644 --- a/drivers/scsi/fnic/fnic_scsi.c +++ b/drivers/scsi/fnic/fnic_scsi.c @@ -2139,7 +2139,7 @@ static int fnic_clean_pending_aborts(struct fnic *fnic, bool new_sc) { - int ret = SUCCESS; + int ret = 0; struct fnic_pending_aborts_iter_data iter_data = { .fnic = fnic, .lun_dev = lr_sc->device, @@ -2159,9 +2159,11 @@ static int fnic_clean_pending_aborts(struct fnic *fnic, /* walk again to check, if IOs are still pending in fw */ if (fnic_is_abts_pending(fnic, lr_sc)) - ret = FAILED; + ret = 1; clean_pending_aborts_end: + FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, + "%s: exit status: %d\n", __func__, ret); return ret; } diff --git a/drivers/scsi/qedf/qedf_main.c b/drivers/scsi/qedf/qedf_main.c index ecff2ec83a00..c4f293d39f22 100644 --- a/drivers/scsi/qedf/qedf_main.c +++ b/drivers/scsi/qedf/qedf_main.c @@ -31,6 +31,7 @@ static void qedf_remove(struct pci_dev *pdev); static void qedf_shutdown(struct pci_dev *pdev); static void qedf_schedule_recovery_handler(void *dev); static void qedf_recovery_handler(struct work_struct *work); +static int qedf_suspend(struct pci_dev *pdev, pm_message_t state); /* * Driver module parameters. @@ -3276,6 +3277,7 @@ static struct pci_driver qedf_pci_driver = { .probe = qedf_probe, .remove = qedf_remove, .shutdown = qedf_shutdown, + .suspend = qedf_suspend, }; static int __qedf_probe(struct pci_dev *pdev, int mode) @@ -4005,6 +4007,22 @@ static void qedf_shutdown(struct pci_dev *pdev) __qedf_remove(pdev, QEDF_MODE_NORMAL); } +static int qedf_suspend(struct pci_dev *pdev, pm_message_t state) +{ + struct qedf_ctx *qedf; + + if (!pdev) { + QEDF_ERR(NULL, "pdev is NULL.\n"); + return -ENODEV; + } + + qedf = pci_get_drvdata(pdev); + + QEDF_ERR(&qedf->dbg_ctx, "%s: Device does not support suspend operation\n", __func__); + + return -EPERM; +} + /* * Recovery handler code */ diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c index f530bb036493..9fd68d362698 100644 --- a/drivers/scsi/qedi/qedi_main.c +++ b/drivers/scsi/qedi/qedi_main.c @@ -69,6 +69,7 @@ static struct nvm_iscsi_block *qedi_get_nvram_block(struct qedi_ctx *qedi); static void qedi_recovery_handler(struct work_struct *work); static void qedi_schedule_hw_err_handler(void *dev, enum qed_hw_err_type err_type); +static int qedi_suspend(struct pci_dev *pdev, pm_message_t state); static int qedi_iscsi_event_cb(void *context, u8 fw_event_code, void *fw_handle) { @@ -2510,6 +2511,22 @@ static void qedi_shutdown(struct pci_dev *pdev) __qedi_remove(pdev, QEDI_MODE_SHUTDOWN); } +static int qedi_suspend(struct pci_dev *pdev, pm_message_t state) +{ + struct qedi_ctx *qedi; + + if (!pdev) { + QEDI_ERR(NULL, "pdev is NULL.\n"); + return -ENODEV; + } + + qedi = pci_get_drvdata(pdev); + + QEDI_ERR(&qedi->dbg_ctx, "%s: Device does not support suspend operation\n", __func__); + + return -EPERM; +} + static int __qedi_probe(struct pci_dev *pdev, int mode) { struct qedi_ctx *qedi; @@ -2868,6 +2885,7 @@ static struct pci_driver qedi_pci_driver = { .remove = qedi_remove, .shutdown = qedi_shutdown, .err_handler = &qedi_err_handler, + .suspend = qedi_suspend, }; static int __init qedi_init(void) diff --git a/drivers/scsi/raid_class.c b/drivers/scsi/raid_class.c index 898a0bdf8df6..95a86e0dfd77 100644 --- a/drivers/scsi/raid_class.c +++ b/drivers/scsi/raid_class.c @@ -209,53 +209,6 @@ raid_attr_ro_state(level); raid_attr_ro_fn(resync); raid_attr_ro_state_fn(state); -static void raid_component_release(struct device *dev) -{ - struct raid_component *rc = - container_of(dev, struct raid_component, dev); - dev_printk(KERN_ERR, rc->dev.parent, "COMPONENT RELEASE\n"); - put_device(rc->dev.parent); - kfree(rc); -} - -int raid_component_add(struct raid_template *r,struct device *raid_dev, - struct device *component_dev) -{ - struct device *cdev = - attribute_container_find_class_device(&r->raid_attrs.ac, - raid_dev); - struct raid_component *rc; - struct raid_data *rd = dev_get_drvdata(cdev); - int err; - - rc = kzalloc(sizeof(*rc), GFP_KERNEL); - if (!rc) - return -ENOMEM; - - INIT_LIST_HEAD(&rc->node); - device_initialize(&rc->dev); - rc->dev.release = raid_component_release; - rc->dev.parent = get_device(component_dev); - rc->num = rd->component_count++; - - dev_set_name(&rc->dev, "component-%d", rc->num); - list_add_tail(&rc->node, &rd->component_list); - rc->dev.class = &raid_class.class; - err = device_add(&rc->dev); - if (err) - goto err_out; - - return 0; - -err_out: - list_del(&rc->node); - rd->component_count--; - put_device(component_dev); - kfree(rc); - return err; -} -EXPORT_SYMBOL(raid_component_add); - struct raid_template * raid_class_attach(struct raid_function_template *ft) { diff --git a/drivers/scsi/scsi_proc.c b/drivers/scsi/scsi_proc.c index 95aee1ad1383..7184e169a4a5 100644 --- a/drivers/scsi/scsi_proc.c +++ b/drivers/scsi/scsi_proc.c @@ -311,7 +311,7 @@ static ssize_t proc_scsi_write(struct file *file, const char __user *buf, size_t length, loff_t *ppos) { int host, channel, id, lun; - char *buffer, *p; + char *buffer, *end, *p; int err; if (!buf || length > PAGE_SIZE) @@ -326,10 +326,14 @@ static ssize_t proc_scsi_write(struct file *file, const char __user *buf, goto out; err = -EINVAL; - if (length < PAGE_SIZE) - buffer[length] = '\0'; - else if (buffer[PAGE_SIZE-1]) - goto out; + if (length < PAGE_SIZE) { + end = buffer + length; + *end = '\0'; + } else { + end = buffer + PAGE_SIZE - 1; + if (*end) + goto out; + } /* * Usage: echo "scsi add-single-device 0 1 2 3" >/proc/scsi/scsi @@ -338,10 +342,10 @@ static ssize_t proc_scsi_write(struct file *file, const char __user *buf, if (!strncmp("scsi add-single-device", buffer, 22)) { p = buffer + 23; - host = simple_strtoul(p, &p, 0); - channel = simple_strtoul(p + 1, &p, 0); - id = simple_strtoul(p + 1, &p, 0); - lun = simple_strtoul(p + 1, &p, 0); + host = (p < end) ? simple_strtoul(p, &p, 0) : 0; + channel = (p + 1 < end) ? simple_strtoul(p + 1, &p, 0) : 0; + id = (p + 1 < end) ? simple_strtoul(p + 1, &p, 0) : 0; + lun = (p + 1 < end) ? simple_strtoul(p + 1, &p, 0) : 0; err = scsi_add_single_device(host, channel, id, lun); @@ -352,10 +356,10 @@ static ssize_t proc_scsi_write(struct file *file, const char __user *buf, } else if (!strncmp("scsi remove-single-device", buffer, 25)) { p = buffer + 26; - host = simple_strtoul(p, &p, 0); - channel = simple_strtoul(p + 1, &p, 0); - id = simple_strtoul(p + 1, &p, 0); - lun = simple_strtoul(p + 1, &p, 0); + host = (p < end) ? simple_strtoul(p, &p, 0) : 0; + channel = (p + 1 < end) ? simple_strtoul(p + 1, &p, 0) : 0; + id = (p + 1 < end) ? simple_strtoul(p + 1, &p, 0) : 0; + lun = (p + 1 < end) ? simple_strtoul(p + 1, &p, 0) : 0; err = scsi_remove_single_device(host, channel, id, lun); } diff --git a/drivers/scsi/snic/snic_disc.c b/drivers/scsi/snic/snic_disc.c index 8fbf3c1b1311..6c529b37f3b4 100644 --- a/drivers/scsi/snic/snic_disc.c +++ b/drivers/scsi/snic/snic_disc.c @@ -307,7 +307,7 @@ snic_tgt_create(struct snic *snic, struct snic_tgt_id *tgtid) spin_lock_irqsave(snic->shost->host_lock, flags); list_del(&tgt->list); spin_unlock_irqrestore(snic->shost->host_lock, flags); - kfree(tgt); + put_device(&tgt->dev); tgt = NULL; return tgt; diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index 5284f9a0b826..83d09c200928 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -365,6 +365,7 @@ static void storvsc_on_channel_callback(void *context); #define STORVSC_FC_MAX_LUNS_PER_TARGET 255 #define STORVSC_FC_MAX_TARGETS 128 #define STORVSC_FC_MAX_CHANNELS 8 +#define STORVSC_FC_MAX_XFER_SIZE ((u32)(512 * 1024)) #define STORVSC_IDE_MAX_LUNS_PER_TARGET 64 #define STORVSC_IDE_MAX_TARGETS 1 @@ -1669,10 +1670,6 @@ static int storvsc_host_reset_handler(struct scsi_cmnd *scmnd) */ static enum blk_eh_timer_return storvsc_eh_timed_out(struct scsi_cmnd *scmnd) { -#if IS_ENABLED(CONFIG_SCSI_FC_ATTRS) - if (scmnd->device->host->transportt == fc_transport_template) - return fc_eh_timed_out(scmnd); -#endif return BLK_EH_RESET_TIMER; } @@ -2002,6 +1999,9 @@ static int storvsc_probe(struct hv_device *device, * protecting it from any weird value. */ max_xfer_bytes = round_down(stor_device->max_transfer_bytes, HV_HYP_PAGE_SIZE); + if (is_fc) + max_xfer_bytes = min(max_xfer_bytes, STORVSC_FC_MAX_XFER_SIZE); + /* max_hw_sectors_kb */ host->max_sectors = max_xfer_bytes >> 9; /* diff --git a/drivers/soc/aspeed/aspeed-socinfo.c b/drivers/soc/aspeed/aspeed-socinfo.c index 1ca140356a08..3f759121dc00 100644 --- a/drivers/soc/aspeed/aspeed-socinfo.c +++ b/drivers/soc/aspeed/aspeed-socinfo.c @@ -137,6 +137,7 @@ static int __init aspeed_socinfo_init(void) soc_dev = soc_device_register(attrs); if (IS_ERR(soc_dev)) { + kfree(attrs->machine); kfree(attrs->soc_id); kfree(attrs->serial_number); kfree(attrs); diff --git a/drivers/soc/aspeed/aspeed-uart-routing.c b/drivers/soc/aspeed/aspeed-uart-routing.c index ef8b24fd1851..59123e1f27ac 100644 --- a/drivers/soc/aspeed/aspeed-uart-routing.c +++ b/drivers/soc/aspeed/aspeed-uart-routing.c @@ -524,7 +524,7 @@ static ssize_t aspeed_uart_routing_store(struct device *dev, struct aspeed_uart_routing_selector *sel = to_routing_selector(attr); int val; - val = match_string(sel->options, -1, buf); + val = __sysfs_match_string(sel->options, -1, buf); if (val < 0) { dev_err(dev, "invalid value \"%s\"\n", buf); return -EINVAL; diff --git a/drivers/staging/rtl8712/os_intfs.c b/drivers/staging/rtl8712/os_intfs.c index 003e97205124..3ea70d042f9a 100644 --- a/drivers/staging/rtl8712/os_intfs.c +++ b/drivers/staging/rtl8712/os_intfs.c @@ -323,6 +323,7 @@ int r8712_init_drv_sw(struct _adapter *padapter) mp871xinit(padapter); init_default_value(padapter); r8712_InitSwLeds(padapter); + mutex_init(&padapter->mutex_start); return ret; } diff --git a/drivers/staging/rtl8712/usb_intf.c b/drivers/staging/rtl8712/usb_intf.c index 37364d3101e2..df05213f922f 100644 --- a/drivers/staging/rtl8712/usb_intf.c +++ b/drivers/staging/rtl8712/usb_intf.c @@ -567,7 +567,6 @@ static int r871xu_drv_init(struct usb_interface *pusb_intf, if (rtl871x_load_fw(padapter)) goto deinit_drv_sw; init_completion(&padapter->rx_filter_ready); - mutex_init(&padapter->mutex_start); return 0; deinit_drv_sw: diff --git a/drivers/thunderbolt/nhi.c b/drivers/thunderbolt/nhi.c index 4a6a3802d7e5..288aaa05d007 100644 --- a/drivers/thunderbolt/nhi.c +++ b/drivers/thunderbolt/nhi.c @@ -1479,6 +1479,8 @@ static struct pci_device_id nhi_ids[] = { .driver_data = (kernel_ulong_t)&icl_nhi_ops }, { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_MTL_P_NHI1), .driver_data = (kernel_ulong_t)&icl_nhi_ops }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_BARLOW_RIDGE_HOST_80G_NHI) }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_BARLOW_RIDGE_HOST_40G_NHI) }, /* Any USB4 compliant host */ { PCI_DEVICE_CLASS(PCI_CLASS_SERIAL_USB_USB4, ~0) }, diff --git a/drivers/thunderbolt/nhi.h b/drivers/thunderbolt/nhi.h index b0718020c6f5..0f029ce75882 100644 --- a/drivers/thunderbolt/nhi.h +++ b/drivers/thunderbolt/nhi.h @@ -75,6 +75,10 @@ extern const struct tb_nhi_ops icl_nhi_ops; #define PCI_DEVICE_ID_INTEL_TITAN_RIDGE_DD_BRIDGE 0x15ef #define PCI_DEVICE_ID_INTEL_ADL_NHI0 0x463e #define PCI_DEVICE_ID_INTEL_ADL_NHI1 0x466d +#define PCI_DEVICE_ID_INTEL_BARLOW_RIDGE_HOST_80G_NHI 0x5781 +#define PCI_DEVICE_ID_INTEL_BARLOW_RIDGE_HOST_40G_NHI 0x5784 +#define PCI_DEVICE_ID_INTEL_BARLOW_RIDGE_HUB_80G_BRIDGE 0x5786 +#define PCI_DEVICE_ID_INTEL_BARLOW_RIDGE_HUB_40G_BRIDGE 0x57a4 #define PCI_DEVICE_ID_INTEL_MTL_M_NHI0 0x7eb2 #define PCI_DEVICE_ID_INTEL_MTL_P_NHI0 0x7ec2 #define PCI_DEVICE_ID_INTEL_MTL_P_NHI1 0x7ec3 diff --git a/drivers/thunderbolt/quirks.c b/drivers/thunderbolt/quirks.c index ae28a03fa890..8c2ee431fcde 100644 --- a/drivers/thunderbolt/quirks.c +++ b/drivers/thunderbolt/quirks.c @@ -26,6 +26,19 @@ static void quirk_clx_disable(struct tb_switch *sw) tb_sw_dbg(sw, "disabling CL states\n"); } +static void quirk_usb3_maximum_bandwidth(struct tb_switch *sw) +{ + struct tb_port *port; + + tb_switch_for_each_port(sw, port) { + if (!tb_port_is_usb3_down(port)) + continue; + port->max_bw = 16376; + tb_port_dbg(port, "USB3 maximum bandwidth limited to %u Mb/s\n", + port->max_bw); + } +} + struct tb_quirk { u16 hw_vendor_id; u16 hw_device_id; @@ -44,6 +57,32 @@ static const struct tb_quirk tb_quirks[] = { */ { 0x8087, 0x0b26, 0x0000, 0x0000, quirk_dp_credit_allocation }, /* + * Limit the maximum USB3 bandwidth for the following Intel USB4 + * host routers due to a hardware issue. + */ + { 0x8087, PCI_DEVICE_ID_INTEL_ADL_NHI0, 0x0000, 0x0000, + quirk_usb3_maximum_bandwidth }, + { 0x8087, PCI_DEVICE_ID_INTEL_ADL_NHI1, 0x0000, 0x0000, + quirk_usb3_maximum_bandwidth }, + { 0x8087, PCI_DEVICE_ID_INTEL_RPL_NHI0, 0x0000, 0x0000, + quirk_usb3_maximum_bandwidth }, + { 0x8087, PCI_DEVICE_ID_INTEL_RPL_NHI1, 0x0000, 0x0000, + quirk_usb3_maximum_bandwidth }, + { 0x8087, PCI_DEVICE_ID_INTEL_MTL_M_NHI0, 0x0000, 0x0000, + quirk_usb3_maximum_bandwidth }, + { 0x8087, PCI_DEVICE_ID_INTEL_MTL_P_NHI0, 0x0000, 0x0000, + quirk_usb3_maximum_bandwidth }, + { 0x8087, PCI_DEVICE_ID_INTEL_MTL_P_NHI1, 0x0000, 0x0000, + quirk_usb3_maximum_bandwidth }, + { 0x8087, PCI_DEVICE_ID_INTEL_BARLOW_RIDGE_HOST_80G_NHI, 0x0000, 0x0000, + quirk_usb3_maximum_bandwidth }, + { 0x8087, PCI_DEVICE_ID_INTEL_BARLOW_RIDGE_HOST_40G_NHI, 0x0000, 0x0000, + quirk_usb3_maximum_bandwidth }, + { 0x8087, PCI_DEVICE_ID_INTEL_BARLOW_RIDGE_HUB_80G_BRIDGE, 0x0000, 0x0000, + quirk_usb3_maximum_bandwidth }, + { 0x8087, PCI_DEVICE_ID_INTEL_BARLOW_RIDGE_HUB_40G_BRIDGE, 0x0000, 0x0000, + quirk_usb3_maximum_bandwidth }, + /* * CLx is not supported on AMD USB4 Yellow Carp and Pink Sardine platforms. */ { 0x0438, 0x0208, 0x0000, 0x0000, quirk_clx_disable }, diff --git a/drivers/thunderbolt/retimer.c b/drivers/thunderbolt/retimer.c index 9cc28197dbc4..edbd92435b41 100644 --- a/drivers/thunderbolt/retimer.c +++ b/drivers/thunderbolt/retimer.c @@ -187,6 +187,21 @@ static ssize_t nvm_authenticate_show(struct device *dev, return ret; } +static void tb_retimer_nvm_authenticate_status(struct tb_port *port, u32 *status) +{ + int i; + + tb_port_dbg(port, "reading NVM authentication status of retimers\n"); + + /* + * Before doing anything else, read the authentication status. + * If the retimer has it set, store it for the new retimer + * device instance. + */ + for (i = 1; i <= TB_MAX_RETIMER_INDEX; i++) + usb4_port_retimer_nvm_authenticate_status(port, i, &status[i]); +} + static void tb_retimer_set_inbound_sbtx(struct tb_port *port) { int i; @@ -455,18 +470,16 @@ int tb_retimer_scan(struct tb_port *port, bool add) return ret; /* - * Enable sideband channel for each retimer. We can do this - * regardless whether there is device connected or not. + * Immediately after sending enumerate retimers read the + * authentication status of each retimer. */ - tb_retimer_set_inbound_sbtx(port); + tb_retimer_nvm_authenticate_status(port, status); /* - * Before doing anything else, read the authentication status. - * If the retimer has it set, store it for the new retimer - * device instance. + * Enable sideband channel for each retimer. We can do this + * regardless whether there is device connected or not. */ - for (i = 1; i <= TB_MAX_RETIMER_INDEX; i++) - usb4_port_retimer_nvm_authenticate_status(port, i, &status[i]); + tb_retimer_set_inbound_sbtx(port); for (i = 1; i <= TB_MAX_RETIMER_INDEX; i++) { /* diff --git a/drivers/thunderbolt/tmu.c b/drivers/thunderbolt/tmu.c index 626aca3124b1..49146f97bb16 100644 --- a/drivers/thunderbolt/tmu.c +++ b/drivers/thunderbolt/tmu.c @@ -415,7 +415,9 @@ int tb_switch_tmu_disable(struct tb_switch *sw) * uni-directional mode and we don't want to change it's TMU * mode. */ - tb_switch_tmu_rate_write(sw, TB_SWITCH_TMU_RATE_OFF); + ret = tb_switch_tmu_rate_write(sw, TB_SWITCH_TMU_RATE_OFF); + if (ret) + return ret; tb_port_tmu_time_sync_disable(up); ret = tb_port_tmu_time_sync_disable(down); diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c index 59a559366b61..c1fa20a4e342 100644 --- a/drivers/tty/n_gsm.c +++ b/drivers/tty/n_gsm.c @@ -2481,12 +2481,13 @@ static void gsm_error(struct gsm_mux *gsm) static void gsm_cleanup_mux(struct gsm_mux *gsm, bool disc) { int i; - struct gsm_dlci *dlci = gsm->dlci[0]; + struct gsm_dlci *dlci; struct gsm_msg *txq, *ntxq; gsm->dead = true; mutex_lock(&gsm->mutex); + dlci = gsm->dlci[0]; if (dlci) { if (disc && dlci->state != DLCI_CLOSED) { gsm_dlci_begin_close(dlci); diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index acf578aa9930..38760bd6e0c2 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -3281,6 +3281,7 @@ void serial8250_init_port(struct uart_8250_port *up) struct uart_port *port = &up->port; spin_lock_init(&port->lock); + port->pm = NULL; port->ops = &serial8250_pops; port->has_sysrq = IS_ENABLED(CONFIG_SERIAL_8250_CONSOLE); diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c index f6d0ea2c6be4..c5a9b89c4d31 100644 --- a/drivers/tty/serial/fsl_lpuart.c +++ b/drivers/tty/serial/fsl_lpuart.c @@ -1125,8 +1125,8 @@ static void lpuart_copy_rx_to_tty(struct lpuart_port *sport) unsigned long sr = lpuart32_read(&sport->port, UARTSTAT); if (sr & (UARTSTAT_PE | UARTSTAT_FE)) { - /* Read DR to clear the error flags */ - lpuart32_read(&sport->port, UARTDATA); + /* Clear the error flags */ + lpuart32_write(&sport->port, sr, UARTSTAT); if (sr & UARTSTAT_PE) sport->port.icount.parity++; diff --git a/drivers/tty/serial/qcom_geni_serial.c b/drivers/tty/serial/qcom_geni_serial.c index 6f6c4e9b7743..d6f682ed1581 100644 --- a/drivers/tty/serial/qcom_geni_serial.c +++ b/drivers/tty/serial/qcom_geni_serial.c @@ -129,6 +129,7 @@ struct qcom_geni_serial_port { u32 tx_fifo_width; u32 rx_fifo_depth; bool setup; + unsigned long clk_rate; int (*handle_rx)(struct uart_port *uport, u32 bytes, bool drop); unsigned int baud; void *rx_fifo; @@ -1061,6 +1062,7 @@ static void qcom_geni_serial_set_termios(struct uart_port *uport, baud * sampling_rate, clk_rate, clk_div); uport->uartclk = clk_rate; + port->clk_rate = clk_rate; dev_pm_opp_set_rate(uport->dev, clk_rate); ser_clk_cfg = SER_CLK_EN; ser_clk_cfg |= clk_div << CLK_DIV_SHFT; @@ -1330,10 +1332,13 @@ static void qcom_geni_serial_pm(struct uart_port *uport, if (new_state == UART_PM_STATE_ON && old_state == UART_PM_STATE_OFF) { geni_icc_enable(&port->se); + if (port->clk_rate) + dev_pm_opp_set_rate(uport->dev, port->clk_rate); geni_se_resources_on(&port->se); } else if (new_state == UART_PM_STATE_OFF && old_state == UART_PM_STATE_ON) { geni_se_resources_off(&port->se); + dev_pm_opp_set_rate(uport->dev, 0); geni_icc_disable(&port->se); } } diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c index 93cf5f788817..8411a0f312db 100644 --- a/drivers/tty/serial/sc16is7xx.c +++ b/drivers/tty/serial/sc16is7xx.c @@ -1345,9 +1345,18 @@ static int sc16is7xx_gpio_direction_output(struct gpio_chip *chip, state |= BIT(offset); else state &= ~BIT(offset); - sc16is7xx_port_write(port, SC16IS7XX_IOSTATE_REG, state); + + /* + * If we write IOSTATE first, and then IODIR, the output value is not + * transferred to the corresponding I/O pin. + * The datasheet states that each register bit will be transferred to + * the corresponding I/O pin programmed as output when writing to + * IOSTATE. Therefore, configure direction first with IODIR, and then + * set value after with IOSTATE. + */ sc16is7xx_port_update(port, SC16IS7XX_IODIR_REG, BIT(offset), BIT(offset)); + sc16is7xx_port_write(port, SC16IS7XX_IOSTATE_REG, state); return 0; } @@ -1439,6 +1448,12 @@ static int sc16is7xx_probe(struct device *dev, s->p[i].port.fifosize = SC16IS7XX_FIFO_SIZE; s->p[i].port.flags = UPF_FIXED_TYPE | UPF_LOW_LATENCY; s->p[i].port.iobase = i; + /* + * Use all ones as membase to make sure uart_configure_port() in + * serial_core.c does not abort for SPI/I2C devices where the + * membase address is not applicable. + */ + s->p[i].port.membase = (void __iomem *)~0; s->p[i].port.iotype = UPIO_PORT; s->p[i].port.uartclk = freq; s->p[i].port.rs485_config = sc16is7xx_config_rs485; diff --git a/drivers/tty/serial/stm32-usart.c b/drivers/tty/serial/stm32-usart.c index 28edbaf7bb32..2a9c4058824a 100644 --- a/drivers/tty/serial/stm32-usart.c +++ b/drivers/tty/serial/stm32-usart.c @@ -1753,13 +1753,10 @@ static int stm32_usart_serial_remove(struct platform_device *pdev) struct uart_port *port = platform_get_drvdata(pdev); struct stm32_port *stm32_port = to_stm32_port(port); const struct stm32_usart_offsets *ofs = &stm32_port->info->ofs; - int err; u32 cr3; pm_runtime_get_sync(&pdev->dev); - err = uart_remove_one_port(&stm32_usart_driver, port); - if (err) - return(err); + uart_remove_one_port(&stm32_usart_driver, port); pm_runtime_disable(&pdev->dev); pm_runtime_set_suspended(&pdev->dev); diff --git a/drivers/ufs/host/ufs-renesas.c b/drivers/ufs/host/ufs-renesas.c index f8a5e79ed3b4..ab0652d8705a 100644 --- a/drivers/ufs/host/ufs-renesas.c +++ b/drivers/ufs/host/ufs-renesas.c @@ -359,7 +359,7 @@ static int ufs_renesas_init(struct ufs_hba *hba) { struct ufs_renesas_priv *priv; - priv = devm_kmalloc(hba->dev, sizeof(*priv), GFP_KERNEL); + priv = devm_kzalloc(hba->dev, sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; ufshcd_set_variant(hba, priv); diff --git a/drivers/usb/chipidea/ci_hdrc_imx.c b/drivers/usb/chipidea/ci_hdrc_imx.c index 9ffcecd3058c..caa91117ba42 100644 --- a/drivers/usb/chipidea/ci_hdrc_imx.c +++ b/drivers/usb/chipidea/ci_hdrc_imx.c @@ -70,6 +70,10 @@ static const struct ci_hdrc_imx_platform_flag imx7ulp_usb_data = { CI_HDRC_PMQOS, }; +static const struct ci_hdrc_imx_platform_flag imx8ulp_usb_data = { + .flags = CI_HDRC_SUPPORTS_RUNTIME_PM, +}; + static const struct of_device_id ci_hdrc_imx_dt_ids[] = { { .compatible = "fsl,imx23-usb", .data = &imx23_usb_data}, { .compatible = "fsl,imx28-usb", .data = &imx28_usb_data}, @@ -80,6 +84,7 @@ static const struct of_device_id ci_hdrc_imx_dt_ids[] = { { .compatible = "fsl,imx6ul-usb", .data = &imx6ul_usb_data}, { .compatible = "fsl,imx7d-usb", .data = &imx7d_usb_data}, { .compatible = "fsl,imx7ulp-usb", .data = &imx7ulp_usb_data}, + { .compatible = "fsl,imx8ulp-usb", .data = &imx8ulp_usb_data}, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, ci_hdrc_imx_dt_ids); @@ -170,10 +175,12 @@ static struct imx_usbmisc_data *usbmisc_get_init_data(struct device *dev) if (of_usb_get_phy_mode(np) == USBPHY_INTERFACE_MODE_ULPI) data->ulpi = 1; - of_property_read_u32(np, "samsung,picophy-pre-emp-curr-control", - &data->emp_curr_control); - of_property_read_u32(np, "samsung,picophy-dc-vol-level-adjust", - &data->dc_vol_level_adjust); + if (of_property_read_u32(np, "samsung,picophy-pre-emp-curr-control", + &data->emp_curr_control)) + data->emp_curr_control = -1; + if (of_property_read_u32(np, "samsung,picophy-dc-vol-level-adjust", + &data->dc_vol_level_adjust)) + data->dc_vol_level_adjust = -1; return data; } diff --git a/drivers/usb/chipidea/usbmisc_imx.c b/drivers/usb/chipidea/usbmisc_imx.c index bac0f5458cab..a2cb4f48c84c 100644 --- a/drivers/usb/chipidea/usbmisc_imx.c +++ b/drivers/usb/chipidea/usbmisc_imx.c @@ -135,7 +135,7 @@ #define TXVREFTUNE0_MASK (0xf << 20) #define MX6_USB_OTG_WAKEUP_BITS (MX6_BM_WAKEUP_ENABLE | MX6_BM_VBUS_WAKEUP | \ - MX6_BM_ID_WAKEUP) + MX6_BM_ID_WAKEUP | MX6SX_BM_DPDM_WAKEUP_EN) struct usbmisc_ops { /* It's called once when probe a usb device */ @@ -657,13 +657,15 @@ static int usbmisc_imx7d_init(struct imx_usbmisc_data *data) usbmisc->base + MX7D_USBNC_USB_CTRL2); /* PHY tuning for signal quality */ reg = readl(usbmisc->base + MX7D_USB_OTG_PHY_CFG1); - if (data->emp_curr_control && data->emp_curr_control <= + if (data->emp_curr_control >= 0 && + data->emp_curr_control <= (TXPREEMPAMPTUNE0_MASK >> TXPREEMPAMPTUNE0_BIT)) { reg &= ~TXPREEMPAMPTUNE0_MASK; reg |= (data->emp_curr_control << TXPREEMPAMPTUNE0_BIT); } - if (data->dc_vol_level_adjust && data->dc_vol_level_adjust <= + if (data->dc_vol_level_adjust >= 0 && + data->dc_vol_level_adjust <= (TXVREFTUNE0_MASK >> TXVREFTUNE0_BIT)) { reg &= ~TXVREFTUNE0_MASK; reg |= (data->dc_vol_level_adjust << TXVREFTUNE0_BIT); diff --git a/drivers/usb/common/usb-conn-gpio.c b/drivers/usb/common/usb-conn-gpio.c index e20874caba36..3f5180d64931 100644 --- a/drivers/usb/common/usb-conn-gpio.c +++ b/drivers/usb/common/usb-conn-gpio.c @@ -42,6 +42,7 @@ struct usb_conn_info { struct power_supply_desc desc; struct power_supply *charger; + bool initial_detection; }; /* @@ -86,11 +87,13 @@ static void usb_conn_detect_cable(struct work_struct *work) dev_dbg(info->dev, "role %s -> %s, gpios: id %d, vbus %d\n", usb_role_string(info->last_role), usb_role_string(role), id, vbus); - if (info->last_role == role) { + if (!info->initial_detection && info->last_role == role) { dev_warn(info->dev, "repeated role: %s\n", usb_role_string(role)); return; } + info->initial_detection = false; + if (info->last_role == USB_ROLE_HOST && info->vbus) regulator_disable(info->vbus); @@ -258,6 +261,7 @@ static int usb_conn_probe(struct platform_device *pdev) device_set_wakeup_capable(&pdev->dev, true); /* Perform initial detection */ + info->initial_detection = true; usb_conn_queue_dwork(info, 0); return 0; diff --git a/drivers/usb/dwc3/dwc3-meson-g12a.c b/drivers/usb/dwc3/dwc3-meson-g12a.c index eaea944ebd2c..10298b91731e 100644 --- a/drivers/usb/dwc3/dwc3-meson-g12a.c +++ b/drivers/usb/dwc3/dwc3-meson-g12a.c @@ -938,6 +938,12 @@ static int __maybe_unused dwc3_meson_g12a_resume(struct device *dev) return ret; } + if (priv->drvdata->usb_post_init) { + ret = priv->drvdata->usb_post_init(priv); + if (ret) + return ret; + } + return 0; } diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index c3590a0c4203..137602d9076f 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -4342,9 +4342,14 @@ static irqreturn_t dwc3_check_event_buf(struct dwc3_event_buffer *evt) u32 count; if (pm_runtime_suspended(dwc->dev)) { + dwc->pending_events = true; + /* + * Trigger runtime resume. The get() function will be balanced + * after processing the pending events in dwc3_process_pending + * events(). + */ pm_runtime_get(dwc->dev); disable_irq_nosync(dwc->irq_gadget); - dwc->pending_events = true; return IRQ_HANDLED; } @@ -4609,6 +4614,8 @@ void dwc3_gadget_process_pending_events(struct dwc3 *dwc) { if (dwc->pending_events) { dwc3_interrupt(dwc->irq_gadget, dwc->ev_buf); + dwc3_thread_interrupt(dwc->irq_gadget, dwc->ev_buf); + pm_runtime_put(dwc->dev); dwc->pending_events = false; enable_irq(dwc->irq_gadget); } diff --git a/drivers/usb/gadget/function/u_serial.c b/drivers/usb/gadget/function/u_serial.c index ea2c5b6cde8c..3c51355ccc94 100644 --- a/drivers/usb/gadget/function/u_serial.c +++ b/drivers/usb/gadget/function/u_serial.c @@ -915,8 +915,11 @@ static void __gs_console_push(struct gs_console *cons) } req->length = size; + + spin_unlock_irq(&cons->lock); if (usb_ep_queue(ep, req, GFP_ATOMIC)) req->length = 0; + spin_lock_irq(&cons->lock); } static void gs_console_work(struct work_struct *work) diff --git a/drivers/usb/gadget/function/uvc_video.c b/drivers/usb/gadget/function/uvc_video.c index dd1c6b2ca7c6..e81865978299 100644 --- a/drivers/usb/gadget/function/uvc_video.c +++ b/drivers/usb/gadget/function/uvc_video.c @@ -386,6 +386,9 @@ static void uvcg_video_pump(struct work_struct *work) struct uvc_buffer *buf; unsigned long flags; int ret; + bool buf_int; + /* video->max_payload_size is only set when using bulk transfer */ + bool is_bulk = video->max_payload_size; while (video->ep->enabled) { /* @@ -408,20 +411,35 @@ static void uvcg_video_pump(struct work_struct *work) */ spin_lock_irqsave(&queue->irqlock, flags); buf = uvcg_queue_head(queue); - if (buf == NULL) { + + if (buf != NULL) { + video->encode(req, video, buf); + /* Always interrupt for the last request of a video buffer */ + buf_int = buf->state == UVC_BUF_STATE_DONE; + } else if (!(queue->flags & UVC_QUEUE_DISCONNECTED) && !is_bulk) { + /* + * No video buffer available; the queue is still connected and + * we're traferring over ISOC. Queue a 0 length request to + * prevent missed ISOC transfers. + */ + req->length = 0; + buf_int = false; + } else { + /* + * Either queue has been disconnected or no video buffer + * available to bulk transfer. Either way, stop processing + * further. + */ spin_unlock_irqrestore(&queue->irqlock, flags); break; } - video->encode(req, video, buf); - /* * With usb3 we have more requests. This will decrease the * interrupt load to a quarter but also catches the corner * cases, which needs to be handled. */ - if (list_empty(&video->req_free) || - buf->state == UVC_BUF_STATE_DONE || + if (list_empty(&video->req_free) || buf_int || !(video->req_int_count % DIV_ROUND_UP(video->uvc_num_requests, 4))) { video->req_int_count = 0; @@ -441,8 +459,7 @@ static void uvcg_video_pump(struct work_struct *work) /* Endpoint now owns the request */ req = NULL; - if (buf->state != UVC_BUF_STATE_DONE) - video->req_int_count++; + video->req_int_count++; } if (!req) @@ -527,4 +544,3 @@ int uvcg_video_init(struct uvc_video *video, struct uvc_device *uvc) V4L2_BUF_TYPE_VIDEO_OUTPUT, &video->mutex); return 0; } - diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c index 139f471894fb..316e9cc3987b 100644 --- a/drivers/usb/gadget/udc/core.c +++ b/drivers/usb/gadget/udc/core.c @@ -795,6 +795,9 @@ EXPORT_SYMBOL_GPL(usb_gadget_disconnect); * usb_gadget_activate() is called. For example, user mode components may * need to be activated before the system can talk to hosts. * + * This routine may sleep; it must not be called in interrupt context + * (such as from within a gadget driver's disconnect() callback). + * * Returns zero on success, else negative errno. */ int usb_gadget_deactivate(struct usb_gadget *gadget) @@ -833,6 +836,8 @@ EXPORT_SYMBOL_GPL(usb_gadget_deactivate); * This routine activates gadget which was previously deactivated with * usb_gadget_deactivate() call. It calls usb_gadget_connect() if needed. * + * This routine may sleep; it must not be called in interrupt context. + * * Returns zero on success, else negative errno. */ int usb_gadget_activate(struct usb_gadget *gadget) @@ -1611,7 +1616,11 @@ static void gadget_unbind_driver(struct device *dev) usb_gadget_disable_async_callbacks(udc); if (gadget->irq) synchronize_irq(gadget->irq); + mutex_unlock(&udc->connect_lock); + udc->driver->unbind(gadget); + + mutex_lock(&udc->connect_lock); usb_gadget_udc_stop_locked(udc); mutex_unlock(&udc->connect_lock); diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 119641761c3b..f13930b4534c 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -259,6 +259,7 @@ static void option_instat_callback(struct urb *urb); #define QUECTEL_PRODUCT_EM05G 0x030a #define QUECTEL_PRODUCT_EM060K 0x030b #define QUECTEL_PRODUCT_EM05G_CS 0x030c +#define QUECTEL_PRODUCT_EM05GV2 0x030e #define QUECTEL_PRODUCT_EM05CN_SG 0x0310 #define QUECTEL_PRODUCT_EM05G_SG 0x0311 #define QUECTEL_PRODUCT_EM05CN 0x0312 @@ -1190,6 +1191,8 @@ static const struct usb_device_id option_ids[] = { .driver_info = RSVD(6) | ZLP }, { USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05G_GR, 0xff), .driver_info = RSVD(6) | ZLP }, + { USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05GV2, 0xff), + .driver_info = RSVD(4) | ZLP }, { USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05G_CS, 0xff), .driver_info = RSVD(6) | ZLP }, { USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05G_RS, 0xff), @@ -2232,6 +2235,10 @@ static const struct usb_device_id option_ids[] = { .driver_info = RSVD(0) | RSVD(1) | RSVD(6) }, { USB_DEVICE_INTERFACE_CLASS(0x0489, 0xe0db, 0xff), /* Foxconn T99W265 MBIM */ .driver_info = RSVD(3) }, + { USB_DEVICE_INTERFACE_CLASS(0x0489, 0xe0ee, 0xff), /* Foxconn T99W368 MBIM */ + .driver_info = RSVD(3) }, + { USB_DEVICE_INTERFACE_CLASS(0x0489, 0xe0f0, 0xff), /* Foxconn T99W373 MBIM */ + .driver_info = RSVD(3) }, { USB_DEVICE(0x1508, 0x1001), /* Fibocom NL668 (IOT version) */ .driver_info = RSVD(4) | RSVD(5) | RSVD(6) }, { USB_DEVICE(0x1782, 0x4d10) }, /* Fibocom L610 (AT mode) */ diff --git a/drivers/usb/storage/alauda.c b/drivers/usb/storage/alauda.c index 5e912dd29b4c..115f05a6201a 100644 --- a/drivers/usb/storage/alauda.c +++ b/drivers/usb/storage/alauda.c @@ -318,7 +318,8 @@ static int alauda_get_media_status(struct us_data *us, unsigned char *data) rc = usb_stor_ctrl_transfer(us, us->recv_ctrl_pipe, command, 0xc0, 0, 1, data, 2); - usb_stor_dbg(us, "Media status %02X %02X\n", data[0], data[1]); + if (rc == USB_STOR_XFER_GOOD) + usb_stor_dbg(us, "Media status %02X %02X\n", data[0], data[1]); return rc; } @@ -454,9 +455,14 @@ static int alauda_init_media(struct us_data *us) static int alauda_check_media(struct us_data *us) { struct alauda_info *info = (struct alauda_info *) us->extra; - unsigned char status[2]; + unsigned char *status = us->iobuf; + int rc; - alauda_get_media_status(us, status); + rc = alauda_get_media_status(us, status); + if (rc != USB_STOR_XFER_GOOD) { + status[0] = 0xF0; /* Pretend there's no media */ + status[1] = 0; + } /* Check for no media or door open */ if ((status[0] & 0x80) || ((status[0] & 0x1F) == 0x10) diff --git a/drivers/usb/typec/altmodes/displayport.c b/drivers/usb/typec/altmodes/displayport.c index 7cdf83f4c811..7a3caf556dae 100644 --- a/drivers/usb/typec/altmodes/displayport.c +++ b/drivers/usb/typec/altmodes/displayport.c @@ -60,6 +60,7 @@ struct dp_altmode { enum dp_state state; bool hpd; + bool pending_hpd; struct mutex lock; /* device lock */ struct work_struct work; @@ -144,8 +145,13 @@ static int dp_altmode_status_update(struct dp_altmode *dp) dp->state = DP_STATE_EXIT; } else if (!(con & DP_CONF_CURRENTLY(dp->data.conf))) { ret = dp_altmode_configure(dp, con); - if (!ret) + if (!ret) { dp->state = DP_STATE_CONFIGURE; + if (dp->hpd != hpd) { + dp->hpd = hpd; + dp->pending_hpd = true; + } + } } else { if (dp->hpd != hpd) { drm_connector_oob_hotplug_event(dp->connector_fwnode); @@ -160,6 +166,16 @@ static int dp_altmode_configured(struct dp_altmode *dp) { sysfs_notify(&dp->alt->dev.kobj, "displayport", "configuration"); sysfs_notify(&dp->alt->dev.kobj, "displayport", "pin_assignment"); + /* + * If the DFP_D/UFP_D sends a change in HPD when first notifying the + * DisplayPort driver that it is connected, then we wait until + * configuration is complete to signal HPD. + */ + if (dp->pending_hpd) { + drm_connector_oob_hotplug_event(dp->connector_fwnode); + sysfs_notify(&dp->alt->dev.kobj, "displayport", "hpd"); + dp->pending_hpd = false; + } return dp_altmode_notify(dp); } diff --git a/drivers/usb/typec/tcpm/tcpci.c b/drivers/usb/typec/tcpm/tcpci.c index 72f8d1e87600..816945913ed0 100644 --- a/drivers/usb/typec/tcpm/tcpci.c +++ b/drivers/usb/typec/tcpm/tcpci.c @@ -593,6 +593,10 @@ static int tcpci_init(struct tcpc_dev *tcpc) if (time_after(jiffies, timeout)) return -ETIMEDOUT; + ret = tcpci_write16(tcpci, TCPC_FAULT_STATUS, TCPC_FAULT_STATUS_ALL_REG_RST_TO_DEFAULT); + if (ret < 0) + return ret; + /* Handle vendor init */ if (tcpci->data->init) { ret = tcpci->data->init(tcpci, tcpci->data); diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index 524099634a1d..5f45b82dd191 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -2747,6 +2747,13 @@ static void tcpm_pd_ctrl_request(struct tcpm_port *port, port->sink_cap_done = true; tcpm_set_state(port, ready_state(port), 0); break; + /* + * Some port partners do not support GET_STATUS, avoid soft reset the link to + * prevent redundant power re-negotiation + */ + case GET_STATUS_SEND: + tcpm_set_state(port, ready_state(port), 0); + break; case SRC_READY: case SNK_READY: if (port->vdm_state > VDM_STATE_READY) { @@ -5322,6 +5329,10 @@ static void _tcpm_pd_vbus_off(struct tcpm_port *port) /* Do nothing, vbus drop expected */ break; + case SNK_HARD_RESET_WAIT_VBUS: + /* Do nothing, its OK to receive vbus off events */ + break; + default: if (port->pwr_role == TYPEC_SINK && port->attached) tcpm_set_state(port, SNK_UNATTACHED, tcpm_wait_for_discharge(port)); @@ -5368,6 +5379,9 @@ static void _tcpm_pd_vbus_vsafe0v(struct tcpm_port *port) case SNK_DEBOUNCED: /*Do nothing, still waiting for VSAFE5V for connect */ break; + case SNK_HARD_RESET_WAIT_VBUS: + /* Do nothing, its OK to receive vbus off events */ + break; default: if (port->pwr_role == TYPEC_SINK && port->auto_vbus_discharge_enabled) tcpm_set_state(port, SNK_UNATTACHED, 0); diff --git a/drivers/vdpa/mlx5/core/mlx5_vdpa.h b/drivers/vdpa/mlx5/core/mlx5_vdpa.h index 25fc4120b618..b53420e874ac 100644 --- a/drivers/vdpa/mlx5/core/mlx5_vdpa.h +++ b/drivers/vdpa/mlx5/core/mlx5_vdpa.h @@ -31,6 +31,7 @@ struct mlx5_vdpa_mr { struct list_head head; unsigned long num_directs; unsigned long num_klms; + /* state of dvq mr */ bool initialized; /* serialize mkey creation and destruction */ @@ -121,6 +122,7 @@ int mlx5_vdpa_handle_set_map(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *io int mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb, unsigned int asid); void mlx5_vdpa_destroy_mr(struct mlx5_vdpa_dev *mvdev); +void mlx5_vdpa_destroy_mr_asid(struct mlx5_vdpa_dev *mvdev, unsigned int asid); #define mlx5_vdpa_warn(__dev, format, ...) \ dev_warn((__dev)->mdev->device, "%s:%d:(pid %d) warning: " format, __func__, __LINE__, \ diff --git a/drivers/vdpa/mlx5/core/mr.c b/drivers/vdpa/mlx5/core/mr.c index a4d7ee2339fa..113aac0446de 100644 --- a/drivers/vdpa/mlx5/core/mr.c +++ b/drivers/vdpa/mlx5/core/mr.c @@ -491,15 +491,24 @@ static void destroy_user_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_mr *mr } } -void mlx5_vdpa_destroy_mr(struct mlx5_vdpa_dev *mvdev) +static void _mlx5_vdpa_destroy_cvq_mr(struct mlx5_vdpa_dev *mvdev, unsigned int asid) +{ + if (mvdev->group2asid[MLX5_VDPA_CVQ_GROUP] != asid) + return; + + prune_iotlb(mvdev); +} + +static void _mlx5_vdpa_destroy_dvq_mr(struct mlx5_vdpa_dev *mvdev, unsigned int asid) { struct mlx5_vdpa_mr *mr = &mvdev->mr; - mutex_lock(&mr->mkey_mtx); + if (mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP] != asid) + return; + if (!mr->initialized) - goto out; + return; - prune_iotlb(mvdev); if (mr->user_mr) destroy_user_mr(mvdev, mr); else @@ -507,45 +516,79 @@ void mlx5_vdpa_destroy_mr(struct mlx5_vdpa_dev *mvdev) memset(mr, 0, sizeof(*mr)); mr->initialized = false; -out: +} + +void mlx5_vdpa_destroy_mr_asid(struct mlx5_vdpa_dev *mvdev, unsigned int asid) +{ + struct mlx5_vdpa_mr *mr = &mvdev->mr; + + mutex_lock(&mr->mkey_mtx); + + _mlx5_vdpa_destroy_dvq_mr(mvdev, asid); + _mlx5_vdpa_destroy_cvq_mr(mvdev, asid); + mutex_unlock(&mr->mkey_mtx); } -static int _mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, - struct vhost_iotlb *iotlb, unsigned int asid) +void mlx5_vdpa_destroy_mr(struct mlx5_vdpa_dev *mvdev) +{ + mlx5_vdpa_destroy_mr_asid(mvdev, mvdev->group2asid[MLX5_VDPA_CVQ_GROUP]); + mlx5_vdpa_destroy_mr_asid(mvdev, mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP]); +} + +static int _mlx5_vdpa_create_cvq_mr(struct mlx5_vdpa_dev *mvdev, + struct vhost_iotlb *iotlb, + unsigned int asid) +{ + if (mvdev->group2asid[MLX5_VDPA_CVQ_GROUP] != asid) + return 0; + + return dup_iotlb(mvdev, iotlb); +} + +static int _mlx5_vdpa_create_dvq_mr(struct mlx5_vdpa_dev *mvdev, + struct vhost_iotlb *iotlb, + unsigned int asid) { struct mlx5_vdpa_mr *mr = &mvdev->mr; int err; - if (mr->initialized) + if (mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP] != asid) return 0; - if (mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP] == asid) { - if (iotlb) - err = create_user_mr(mvdev, iotlb); - else - err = create_dma_mr(mvdev, mr); + if (mr->initialized) + return 0; - if (err) - return err; - } + if (iotlb) + err = create_user_mr(mvdev, iotlb); + else + err = create_dma_mr(mvdev, mr); - if (mvdev->group2asid[MLX5_VDPA_CVQ_GROUP] == asid) { - err = dup_iotlb(mvdev, iotlb); - if (err) - goto out_err; - } + if (err) + return err; mr->initialized = true; + + return 0; +} + +static int _mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, + struct vhost_iotlb *iotlb, unsigned int asid) +{ + int err; + + err = _mlx5_vdpa_create_dvq_mr(mvdev, iotlb, asid); + if (err) + return err; + + err = _mlx5_vdpa_create_cvq_mr(mvdev, iotlb, asid); + if (err) + goto out_err; + return 0; out_err: - if (mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP] == asid) { - if (iotlb) - destroy_user_mr(mvdev, mr); - else - destroy_dma_mr(mvdev, mr); - } + _mlx5_vdpa_destroy_dvq_mr(mvdev, asid); return err; } diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index daac3ab31478..bf99654371b3 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -2406,7 +2406,7 @@ static int mlx5_vdpa_change_map(struct mlx5_vdpa_dev *mvdev, goto err_mr; teardown_driver(ndev); - mlx5_vdpa_destroy_mr(mvdev); + mlx5_vdpa_destroy_mr_asid(mvdev, asid); err = mlx5_vdpa_create_mr(mvdev, iotlb, asid); if (err) goto err_mr; @@ -2422,7 +2422,7 @@ static int mlx5_vdpa_change_map(struct mlx5_vdpa_dev *mvdev, return 0; err_setup: - mlx5_vdpa_destroy_mr(mvdev); + mlx5_vdpa_destroy_mr_asid(mvdev, asid); err_mr: return err; } diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index febdc99b51a7..908b3f98ecbe 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -1172,44 +1172,41 @@ static const struct nla_policy vdpa_nl_policy[VDPA_ATTR_MAX + 1] = { [VDPA_ATTR_MGMTDEV_DEV_NAME] = { .type = NLA_STRING }, [VDPA_ATTR_DEV_NAME] = { .type = NLA_STRING }, [VDPA_ATTR_DEV_NET_CFG_MACADDR] = NLA_POLICY_ETH_ADDR, + [VDPA_ATTR_DEV_NET_CFG_MAX_VQP] = { .type = NLA_U16 }, /* virtio spec 1.1 section 5.1.4.1 for valid MTU range */ [VDPA_ATTR_DEV_NET_CFG_MTU] = NLA_POLICY_MIN(NLA_U16, 68), + [VDPA_ATTR_DEV_QUEUE_INDEX] = { .type = NLA_U32 }, + [VDPA_ATTR_DEV_FEATURES] = { .type = NLA_U64 }, }; static const struct genl_ops vdpa_nl_ops[] = { { .cmd = VDPA_CMD_MGMTDEV_GET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = vdpa_nl_cmd_mgmtdev_get_doit, .dumpit = vdpa_nl_cmd_mgmtdev_get_dumpit, }, { .cmd = VDPA_CMD_DEV_NEW, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = vdpa_nl_cmd_dev_add_set_doit, .flags = GENL_ADMIN_PERM, }, { .cmd = VDPA_CMD_DEV_DEL, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = vdpa_nl_cmd_dev_del_set_doit, .flags = GENL_ADMIN_PERM, }, { .cmd = VDPA_CMD_DEV_GET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = vdpa_nl_cmd_dev_get_doit, .dumpit = vdpa_nl_cmd_dev_get_dumpit, }, { .cmd = VDPA_CMD_DEV_CONFIG_GET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = vdpa_nl_cmd_dev_config_get_doit, .dumpit = vdpa_nl_cmd_dev_config_get_dumpit, }, { .cmd = VDPA_CMD_DEV_VSTATS_GET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = vdpa_nl_cmd_dev_stats_get_doit, .flags = GENL_ADMIN_PERM, }, diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c index 72f924ec4658..edcd74cc4c0f 100644 --- a/drivers/vdpa/vdpa_user/vduse_dev.c +++ b/drivers/vdpa/vdpa_user/vduse_dev.c @@ -899,10 +899,10 @@ static void vduse_dev_irq_inject(struct work_struct *work) { struct vduse_dev *dev = container_of(work, struct vduse_dev, inject); - spin_lock_irq(&dev->irq_lock); + spin_lock_bh(&dev->irq_lock); if (dev->config_cb.callback) dev->config_cb.callback(dev->config_cb.private); - spin_unlock_irq(&dev->irq_lock); + spin_unlock_bh(&dev->irq_lock); } static void vduse_vq_irq_inject(struct work_struct *work) @@ -910,10 +910,10 @@ static void vduse_vq_irq_inject(struct work_struct *work) struct vduse_virtqueue *vq = container_of(work, struct vduse_virtqueue, inject); - spin_lock_irq(&vq->irq_lock); + spin_lock_bh(&vq->irq_lock); if (vq->ready && vq->cb.callback) vq->cb.callback(vq->cb.private); - spin_unlock_irq(&vq->irq_lock); + spin_unlock_bh(&vq->irq_lock); } static int vduse_dev_queue_irq_work(struct vduse_dev *dev, diff --git a/drivers/video/aperture.c b/drivers/video/aperture.c index 41e77de1ea82..3e4a1f55f51b 100644 --- a/drivers/video/aperture.c +++ b/drivers/video/aperture.c @@ -298,14 +298,6 @@ int aperture_remove_conflicting_devices(resource_size_t base, resource_size_t si aperture_detach_devices(base, size); - /* - * If this is the primary adapter, there could be a VGA device - * that consumes the VGA framebuffer I/O range. Remove this device - * as well. - */ - if (primary) - aperture_detach_devices(VGA_FB_PHYS_BASE, VGA_FB_PHYS_SIZE); - return 0; } EXPORT_SYMBOL(aperture_remove_conflicting_devices); @@ -332,25 +324,35 @@ int aperture_remove_conflicting_pci_devices(struct pci_dev *pdev, const char *na primary = pdev->resource[PCI_ROM_RESOURCE].flags & IORESOURCE_ROM_SHADOW; #endif + if (primary) + sysfb_disable(); + for (bar = 0; bar < PCI_STD_NUM_BARS; ++bar) { if (!(pci_resource_flags(pdev, bar) & IORESOURCE_MEM)) continue; base = pci_resource_start(pdev, bar); size = pci_resource_len(pdev, bar); - ret = aperture_remove_conflicting_devices(base, size, primary, name); + aperture_detach_devices(base, size); + } + + if (primary) { + /* + * If this is the primary adapter, there could be a VGA device + * that consumes the VGA framebuffer I/O range. Remove this + * device as well. + */ + aperture_detach_devices(VGA_FB_PHYS_BASE, VGA_FB_PHYS_SIZE); + + /* + * WARNING: Apparently we must kick fbdev drivers before vgacon, + * otherwise the vga fbdev driver falls over. + */ + ret = vga_remove_vgacon(pdev); if (ret) return ret; } - /* - * WARNING: Apparently we must kick fbdev drivers before vgacon, - * otherwise the vga fbdev driver falls over. - */ - ret = vga_remove_vgacon(pdev); - if (ret) - return ret; - return 0; } diff --git a/drivers/video/fbdev/aty/radeon_base.c b/drivers/video/fbdev/aty/radeon_base.c index 657064227de8..972c4bbedfa3 100644 --- a/drivers/video/fbdev/aty/radeon_base.c +++ b/drivers/video/fbdev/aty/radeon_base.c @@ -2238,14 +2238,6 @@ static const struct bin_attribute edid2_attr = { .read = radeon_show_edid2, }; -static int radeon_kick_out_firmware_fb(struct pci_dev *pdev) -{ - resource_size_t base = pci_resource_start(pdev, 0); - resource_size_t size = pci_resource_len(pdev, 0); - - return aperture_remove_conflicting_devices(base, size, false, KBUILD_MODNAME); -} - static int radeonfb_pci_register(struct pci_dev *pdev, const struct pci_device_id *ent) { @@ -2296,7 +2288,7 @@ static int radeonfb_pci_register(struct pci_dev *pdev, rinfo->fb_base_phys = pci_resource_start (pdev, 0); rinfo->mmio_base_phys = pci_resource_start (pdev, 2); - ret = radeon_kick_out_firmware_fb(pdev); + ret = aperture_remove_conflicting_pci_devices(pdev, KBUILD_MODNAME); if (ret) goto err_release_fb; diff --git a/drivers/video/fbdev/hyperv_fb.c b/drivers/video/fbdev/hyperv_fb.c index 4d5ef8023afb..5d937bb1df6f 100644 --- a/drivers/video/fbdev/hyperv_fb.c +++ b/drivers/video/fbdev/hyperv_fb.c @@ -994,13 +994,10 @@ static int hvfb_getmem(struct hv_device *hdev, struct fb_info *info) struct pci_dev *pdev = NULL; void __iomem *fb_virt; int gen2vm = efi_enabled(EFI_BOOT); + resource_size_t base, size; phys_addr_t paddr; int ret; - info->apertures = alloc_apertures(1); - if (!info->apertures) - return -ENOMEM; - if (!gen2vm) { pdev = pci_get_device(PCI_VENDOR_ID_MICROSOFT, PCI_DEVICE_ID_HYPERV_VIDEO, NULL); @@ -1009,8 +1006,8 @@ static int hvfb_getmem(struct hv_device *hdev, struct fb_info *info) return -ENODEV; } - info->apertures->ranges[0].base = pci_resource_start(pdev, 0); - info->apertures->ranges[0].size = pci_resource_len(pdev, 0); + base = pci_resource_start(pdev, 0); + size = pci_resource_len(pdev, 0); /* * For Gen 1 VM, we can directly use the contiguous memory @@ -1033,8 +1030,8 @@ static int hvfb_getmem(struct hv_device *hdev, struct fb_info *info) } pr_info("Unable to allocate enough contiguous physical memory on Gen 1 VM. Using MMIO instead.\n"); } else { - info->apertures->ranges[0].base = screen_info.lfb_base; - info->apertures->ranges[0].size = screen_info.lfb_size; + base = screen_info.lfb_base; + size = screen_info.lfb_size; } /* @@ -1076,9 +1073,7 @@ static int hvfb_getmem(struct hv_device *hdev, struct fb_info *info) info->screen_size = dio_fb_size; getmem_done: - aperture_remove_conflicting_devices(info->apertures->ranges[0].base, - info->apertures->ranges[0].size, - false, KBUILD_MODNAME); + aperture_remove_conflicting_devices(base, size, false, KBUILD_MODNAME); if (gen2vm) { /* framebuffer is reallocated, clear screen_info to avoid misuse from kexec */ diff --git a/drivers/video/fbdev/mmp/hw/mmp_ctrl.c b/drivers/video/fbdev/mmp/hw/mmp_ctrl.c index 51fbf02a0343..76b50b6c98ad 100644 --- a/drivers/video/fbdev/mmp/hw/mmp_ctrl.c +++ b/drivers/video/fbdev/mmp/hw/mmp_ctrl.c @@ -519,7 +519,9 @@ static int mmphw_probe(struct platform_device *pdev) "unable to get clk %s\n", mi->clk_name); goto failed; } - clk_prepare_enable(ctrl->clk); + ret = clk_prepare_enable(ctrl->clk); + if (ret) + goto failed; /* init global regs */ ctrl_set_default(ctrl); diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c index 3ff746e3f24a..dec3cba88458 100644 --- a/drivers/virtio/virtio_mmio.c +++ b/drivers/virtio/virtio_mmio.c @@ -590,9 +590,8 @@ static void virtio_mmio_release_dev(struct device *_d) struct virtio_device *vdev = container_of(_d, struct virtio_device, dev); struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev); - struct platform_device *pdev = vm_dev->pdev; - devm_kfree(&pdev->dev, vm_dev); + kfree(vm_dev); } /* Platform device */ @@ -603,7 +602,7 @@ static int virtio_mmio_probe(struct platform_device *pdev) unsigned long magic; int rc; - vm_dev = devm_kzalloc(&pdev->dev, sizeof(*vm_dev), GFP_KERNEL); + vm_dev = kzalloc(sizeof(*vm_dev), GFP_KERNEL); if (!vm_dev) return -ENOMEM; diff --git a/drivers/watchdog/sp5100_tco.c b/drivers/watchdog/sp5100_tco.c index 14f8d8d90920..2bd3dc25cb03 100644 --- a/drivers/watchdog/sp5100_tco.c +++ b/drivers/watchdog/sp5100_tco.c @@ -96,7 +96,7 @@ static enum tco_reg_layout tco_reg_layout(struct pci_dev *dev) sp5100_tco_pci->device == PCI_DEVICE_ID_AMD_KERNCZ_SMBUS && sp5100_tco_pci->revision >= AMD_ZEN_SMBUS_PCI_REV) { return efch_mmio; - } else if (dev->vendor == PCI_VENDOR_ID_AMD && + } else if ((dev->vendor == PCI_VENDOR_ID_AMD || dev->vendor == PCI_VENDOR_ID_HYGON) && ((dev->device == PCI_DEVICE_ID_AMD_HUDSON2_SMBUS && dev->revision >= 0x41) || (dev->device == PCI_DEVICE_ID_AMD_KERNCZ_SMBUS && @@ -579,6 +579,8 @@ static const struct pci_device_id sp5100_tco_pci_tbl[] = { PCI_ANY_ID, }, { PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_KERNCZ_SMBUS, PCI_ANY_ID, PCI_ANY_ID, }, + { PCI_VENDOR_ID_HYGON, PCI_DEVICE_ID_AMD_KERNCZ_SMBUS, PCI_ANY_ID, + PCI_ANY_ID, }, { 0, }, /* End of list */ }; MODULE_DEVICE_TABLE(pci, sp5100_tco_pci_tbl); diff --git a/fs/attr.c b/fs/attr.c index b45f30e516fa..9b9a70e0cc54 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -47,6 +47,7 @@ int setattr_should_drop_sgid(struct user_namespace *mnt_userns, return ATTR_KILL_SGID; return 0; } +EXPORT_SYMBOL(setattr_should_drop_sgid); /** * setattr_should_drop_suidgid - determine whether the set{g,u}id bit needs to diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index d93e8735ab1f..08017b180a10 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -436,13 +436,23 @@ void btrfs_wait_block_group_cache_progress(struct btrfs_block_group *cache, u64 num_bytes) { struct btrfs_caching_control *caching_ctl; + int progress; caching_ctl = btrfs_get_caching_control(cache); if (!caching_ctl) return; + /* + * We've already failed to allocate from this block group, so even if + * there's enough space in the block group it isn't contiguous enough to + * allow for an allocation, so wait for at least the next wakeup tick, + * or for the thing to be done. + */ + progress = atomic_read(&caching_ctl->progress); + wait_event(caching_ctl->wait, btrfs_block_group_done(cache) || - (cache->free_space_ctl->free_space >= num_bytes)); + (progress != atomic_read(&caching_ctl->progress) && + (cache->free_space_ctl->free_space >= num_bytes))); btrfs_put_caching_control(caching_ctl); } @@ -494,12 +504,16 @@ static void fragment_free_space(struct btrfs_block_group *block_group) * used yet since their free space will be released as soon as the transaction * commits. */ -u64 add_new_free_space(struct btrfs_block_group *block_group, u64 start, u64 end) +int add_new_free_space(struct btrfs_block_group *block_group, u64 start, u64 end, + u64 *total_added_ret) { struct btrfs_fs_info *info = block_group->fs_info; - u64 extent_start, extent_end, size, total_added = 0; + u64 extent_start, extent_end, size; int ret; + if (total_added_ret) + *total_added_ret = 0; + while (start < end) { ret = find_first_extent_bit(&info->excluded_extents, start, &extent_start, &extent_end, @@ -512,10 +526,12 @@ u64 add_new_free_space(struct btrfs_block_group *block_group, u64 start, u64 end start = extent_end + 1; } else if (extent_start > start && extent_start < end) { size = extent_start - start; - total_added += size; ret = btrfs_add_free_space_async_trimmed(block_group, start, size); - BUG_ON(ret); /* -ENOMEM or logic error */ + if (ret) + return ret; + if (total_added_ret) + *total_added_ret += size; start = extent_end + 1; } else { break; @@ -524,13 +540,15 @@ u64 add_new_free_space(struct btrfs_block_group *block_group, u64 start, u64 end if (start < end) { size = end - start; - total_added += size; ret = btrfs_add_free_space_async_trimmed(block_group, start, size); - BUG_ON(ret); /* -ENOMEM or logic error */ + if (ret) + return ret; + if (total_added_ret) + *total_added_ret += size; } - return total_added; + return 0; } static int load_extent_tree_free(struct btrfs_caching_control *caching_ctl) @@ -637,8 +655,13 @@ next: if (key.type == BTRFS_EXTENT_ITEM_KEY || key.type == BTRFS_METADATA_ITEM_KEY) { - total_found += add_new_free_space(block_group, last, - key.objectid); + u64 space_added; + + ret = add_new_free_space(block_group, last, key.objectid, + &space_added); + if (ret) + goto out; + total_found += space_added; if (key.type == BTRFS_METADATA_ITEM_KEY) last = key.objectid + fs_info->nodesize; @@ -647,17 +670,18 @@ next: if (total_found > CACHING_CTL_WAKE_UP) { total_found = 0; - if (wakeup) + if (wakeup) { + atomic_inc(&caching_ctl->progress); wake_up(&caching_ctl->wait); + } } } path->slots[0]++; } - ret = 0; - - total_found += add_new_free_space(block_group, last, - block_group->start + block_group->length); + ret = add_new_free_space(block_group, last, + block_group->start + block_group->length, + NULL); out: btrfs_free_path(path); return ret; @@ -755,6 +779,7 @@ int btrfs_cache_block_group(struct btrfs_block_group *cache, bool wait) init_waitqueue_head(&caching_ctl->wait); caching_ctl->block_group = cache; refcount_set(&caching_ctl->count, 2); + atomic_set(&caching_ctl->progress, 0); btrfs_init_work(&caching_ctl->work, caching_thread, NULL, NULL); spin_lock(&cache->lock); @@ -1508,6 +1533,10 @@ void btrfs_mark_bg_unused(struct btrfs_block_group *bg) btrfs_get_block_group(bg); trace_btrfs_add_unused_block_group(bg); list_add_tail(&bg->bg_list, &fs_info->unused_bgs); + } else if (!test_bit(BLOCK_GROUP_FLAG_NEW, &bg->runtime_flags)) { + /* Pull out the block group from the reclaim_bgs list. */ + trace_btrfs_add_unused_block_group(bg); + list_move_tail(&bg->bg_list, &fs_info->unused_bgs); } spin_unlock(&fs_info->unused_bgs_lock); } @@ -2101,9 +2130,11 @@ static int read_one_block_group(struct btrfs_fs_info *info, btrfs_free_excluded_extents(cache); } else if (cache->used == 0) { cache->cached = BTRFS_CACHE_FINISHED; - add_new_free_space(cache, cache->start, - cache->start + cache->length); + ret = add_new_free_space(cache, cache->start, + cache->start + cache->length, NULL); btrfs_free_excluded_extents(cache); + if (ret) + goto error; } ret = btrfs_add_block_group_cache(info, cache); @@ -2466,6 +2497,7 @@ void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans) next: btrfs_delayed_refs_rsv_release(fs_info, 1); list_del_init(&block_group->bg_list); + clear_bit(BLOCK_GROUP_FLAG_NEW, &block_group->runtime_flags); } btrfs_trans_release_chunk_metadata(trans); } @@ -2505,6 +2537,13 @@ struct btrfs_block_group *btrfs_make_block_group(struct btrfs_trans_handle *tran if (!cache) return ERR_PTR(-ENOMEM); + /* + * Mark it as new before adding it to the rbtree of block groups or any + * list, so that no other task finds it and calls btrfs_mark_bg_unused() + * before the new flag is set. + */ + set_bit(BLOCK_GROUP_FLAG_NEW, &cache->runtime_flags); + cache->length = size; set_free_space_tree_thresholds(cache); cache->used = bytes_used; @@ -2513,7 +2552,7 @@ struct btrfs_block_group *btrfs_make_block_group(struct btrfs_trans_handle *tran cache->global_root_id = calculate_global_root_id(fs_info, cache->start); if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) - cache->needs_free_space = 1; + set_bit(BLOCK_GROUP_FLAG_NEEDS_FREE_SPACE, &cache->runtime_flags); ret = btrfs_load_block_group_zone_info(cache, true); if (ret) { @@ -2529,9 +2568,12 @@ struct btrfs_block_group *btrfs_make_block_group(struct btrfs_trans_handle *tran return ERR_PTR(ret); } - add_new_free_space(cache, chunk_offset, chunk_offset + size); - + ret = add_new_free_space(cache, chunk_offset, chunk_offset + size, NULL); btrfs_free_excluded_extents(cache); + if (ret) { + btrfs_put_block_group(cache); + return ERR_PTR(ret); + } /* * Ensure the corresponding space_info object is created and diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h index 8fb14b99a1d1..47a2dcbfee25 100644 --- a/fs/btrfs/block-group.h +++ b/fs/btrfs/block-group.h @@ -55,6 +55,15 @@ enum btrfs_block_group_flags { BLOCK_GROUP_FLAG_CHUNK_ITEM_INSERTED, BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, BLOCK_GROUP_FLAG_ZONED_DATA_RELOC, + /* Does the block group need to be added to the free space tree? */ + BLOCK_GROUP_FLAG_NEEDS_FREE_SPACE, + /* Indicate that the block group is placed on a sequential zone */ + BLOCK_GROUP_FLAG_SEQUENTIAL_ZONE, + /* + * Indicate that block group is in the list of new block groups of a + * transaction. + */ + BLOCK_GROUP_FLAG_NEW, }; enum btrfs_caching_type { @@ -70,6 +79,8 @@ struct btrfs_caching_control { wait_queue_head_t wait; struct btrfs_work work; struct btrfs_block_group *block_group; + /* Track progress of caching during allocation. */ + atomic_t progress; refcount_t count; }; @@ -203,15 +214,6 @@ struct btrfs_block_group { struct mutex free_space_lock; /* - * Does the block group need to be added to the free space tree? - * Protected by free_space_lock. - */ - int needs_free_space; - - /* Flag indicating this block group is placed on a sequential zone */ - bool seq_zone; - - /* * Number of extents in this block group used for swap files. * All accesses protected by the spinlock 'lock'. */ @@ -284,8 +286,8 @@ int btrfs_cache_block_group(struct btrfs_block_group *cache, bool wait); void btrfs_put_caching_control(struct btrfs_caching_control *ctl); struct btrfs_caching_control *btrfs_get_caching_control( struct btrfs_block_group *cache); -u64 add_new_free_space(struct btrfs_block_group *block_group, - u64 start, u64 end); +int add_new_free_space(struct btrfs_block_group *block_group, + u64 start, u64 end, u64 *total_added_ret); struct btrfs_trans_handle *btrfs_start_trans_remove_block_group( struct btrfs_fs_info *fs_info, const u64 chunk_offset); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index f22e00dfec6c..96369c44863a 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1455,7 +1455,8 @@ static int btrfs_init_fs_root(struct btrfs_root *root, dev_t anon_dev) goto fail; if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID && - !btrfs_is_data_reloc_root(root)) { + !btrfs_is_data_reloc_root(root) && + is_fstree(root->root_key.objectid)) { set_bit(BTRFS_ROOT_SHAREABLE, &root->state); btrfs_check_and_init_root_item(&root->root_item); } diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 571fcc5ae4dc..f2ee70c03f0d 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -4411,8 +4411,11 @@ have_block_group: ret = 0; } - if (unlikely(block_group->cached == BTRFS_CACHE_ERROR)) + if (unlikely(block_group->cached == BTRFS_CACHE_ERROR)) { + if (!cache_block_group_error) + cache_block_group_error = -EIO; goto loop; + } bg_ret = NULL; ret = do_allocation(block_group, ffe_ctl, &bg_ret); diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 58785dc7080a..0ad69041954f 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -3015,11 +3015,12 @@ retry: } /* - * the filesystem may choose to bump up nr_to_write. + * The filesystem may choose to bump up nr_to_write. * We have to make sure to honor the new nr_to_write - * at any time + * at any time. */ - nr_to_write_done = wbc->nr_to_write <= 0; + nr_to_write_done = (wbc->sync_mode == WB_SYNC_NONE && + wbc->nr_to_write <= 0); } pagevec_release(&pvec); cond_resched(); diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c index 4abbe4b35253..56d7580fdc3c 100644 --- a/fs/btrfs/extent_map.c +++ b/fs/btrfs/extent_map.c @@ -784,8 +784,6 @@ void btrfs_drop_extent_map_range(struct btrfs_inode *inode, u64 start, u64 end, if (skip_pinned && test_bit(EXTENT_FLAG_PINNED, &em->flags)) { start = em_end; - if (end != (u64)-1) - len = start + len - em_end; goto next; } @@ -853,8 +851,8 @@ void btrfs_drop_extent_map_range(struct btrfs_inode *inode, u64 start, u64 end, if (!split) goto remove_em; } - split->start = start + len; - split->len = em_end - (start + len); + split->start = end; + split->len = em_end - end; split->block_start = em->block_start; split->flags = flags; split->compress_type = em->compress_type; diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c index a07450f64abb..6a44733a95e1 100644 --- a/fs/btrfs/free-space-tree.c +++ b/fs/btrfs/free-space-tree.c @@ -803,7 +803,7 @@ int __remove_from_free_space_tree(struct btrfs_trans_handle *trans, u32 flags; int ret; - if (block_group->needs_free_space) { + if (test_bit(BLOCK_GROUP_FLAG_NEEDS_FREE_SPACE, &block_group->runtime_flags)) { ret = __add_block_group_free_space(trans, block_group, path); if (ret) return ret; @@ -996,7 +996,7 @@ int __add_to_free_space_tree(struct btrfs_trans_handle *trans, u32 flags; int ret; - if (block_group->needs_free_space) { + if (test_bit(BLOCK_GROUP_FLAG_NEEDS_FREE_SPACE, &block_group->runtime_flags)) { ret = __add_block_group_free_space(trans, block_group, path); if (ret) return ret; @@ -1350,7 +1350,7 @@ static int __add_block_group_free_space(struct btrfs_trans_handle *trans, { int ret; - block_group->needs_free_space = 0; + clear_bit(BLOCK_GROUP_FLAG_NEEDS_FREE_SPACE, &block_group->runtime_flags); ret = add_new_free_space_info(trans, block_group, path); if (ret) @@ -1372,7 +1372,7 @@ int add_block_group_free_space(struct btrfs_trans_handle *trans, return 0; mutex_lock(&block_group->free_space_lock); - if (!block_group->needs_free_space) + if (!test_bit(BLOCK_GROUP_FLAG_NEEDS_FREE_SPACE, &block_group->runtime_flags)) goto out; path = btrfs_alloc_path(); @@ -1405,7 +1405,7 @@ int remove_block_group_free_space(struct btrfs_trans_handle *trans, if (!btrfs_fs_compat_ro(trans->fs_info, FREE_SPACE_TREE)) return 0; - if (block_group->needs_free_space) { + if (test_bit(BLOCK_GROUP_FLAG_NEEDS_FREE_SPACE, &block_group->runtime_flags)) { /* We never added this block group to the free space tree. */ return 0; } @@ -1510,9 +1510,13 @@ static int load_free_space_bitmaps(struct btrfs_caching_control *caching_ctl, if (prev_bit == 0 && bit == 1) { extent_start = offset; } else if (prev_bit == 1 && bit == 0) { - total_found += add_new_free_space(block_group, - extent_start, - offset); + u64 space_added; + + ret = add_new_free_space(block_group, extent_start, + offset, &space_added); + if (ret) + goto out; + total_found += space_added; if (total_found > CACHING_CTL_WAKE_UP) { total_found = 0; wake_up(&caching_ctl->wait); @@ -1524,8 +1528,9 @@ static int load_free_space_bitmaps(struct btrfs_caching_control *caching_ctl, } } if (prev_bit == 1) { - total_found += add_new_free_space(block_group, extent_start, - end); + ret = add_new_free_space(block_group, extent_start, end, NULL); + if (ret) + goto out; extent_count++; } @@ -1564,6 +1569,8 @@ static int load_free_space_extents(struct btrfs_caching_control *caching_ctl, end = block_group->start + block_group->length; while (1) { + u64 space_added; + ret = btrfs_next_item(root, path); if (ret < 0) goto out; @@ -1578,8 +1585,11 @@ static int load_free_space_extents(struct btrfs_caching_control *caching_ctl, ASSERT(key.type == BTRFS_FREE_SPACE_EXTENT_KEY); ASSERT(key.objectid < end && key.objectid + key.offset <= end); - total_found += add_new_free_space(block_group, key.objectid, - key.objectid + key.offset); + ret = add_new_free_space(block_group, key.objectid, + key.objectid + key.offset, &space_added); + if (ret) + goto out; + total_found += space_added; if (total_found > CACHING_CTL_WAKE_UP) { total_found = 0; wake_up(&caching_ctl->wait); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 3c48273cd7a5..28bcba2e0590 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1429,8 +1429,6 @@ out_unlock: clear_bits, page_ops); start += cur_alloc_size; - if (start >= end) - return ret; } /* @@ -1439,9 +1437,11 @@ out_unlock: * space_info's bytes_may_use counter, reserved in * btrfs_check_data_free_space(). */ - extent_clear_unlock_delalloc(inode, start, end, locked_page, - clear_bits | EXTENT_CLEAR_DATA_RESV, - page_ops); + if (start < end) { + clear_bits |= EXTENT_CLEAR_DATA_RESV; + extent_clear_unlock_delalloc(inode, start, end, locked_page, + clear_bits, page_ops); + } return ret; } diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 666a37a0ee89..d3591c7f166a 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -1902,7 +1902,39 @@ again: err = PTR_ERR(root); break; } - ASSERT(root->reloc_root == reloc_root); + + if (unlikely(root->reloc_root != reloc_root)) { + if (root->reloc_root) { + btrfs_err(fs_info, +"reloc tree mismatch, root %lld has reloc root key (%lld %u %llu) gen %llu, expect reloc root key (%lld %u %llu) gen %llu", + root->root_key.objectid, + root->reloc_root->root_key.objectid, + root->reloc_root->root_key.type, + root->reloc_root->root_key.offset, + btrfs_root_generation( + &root->reloc_root->root_item), + reloc_root->root_key.objectid, + reloc_root->root_key.type, + reloc_root->root_key.offset, + btrfs_root_generation( + &reloc_root->root_item)); + } else { + btrfs_err(fs_info, +"reloc tree mismatch, root %lld has no reloc root, expect reloc root key (%lld %u %llu) gen %llu", + root->root_key.objectid, + reloc_root->root_key.objectid, + reloc_root->root_key.type, + reloc_root->root_key.offset, + btrfs_root_generation( + &reloc_root->root_item)); + } + list_add(&reloc_root->root_list, &reloc_roots); + btrfs_put_root(root); + btrfs_abort_transaction(trans, -EUCLEAN); + if (!err) + err = -EUCLEAN; + break; + } /* * set reference count to 1, so btrfs_recover_relocation @@ -1975,7 +2007,7 @@ again: root = btrfs_get_fs_root(fs_info, reloc_root->root_key.offset, false); if (btrfs_root_refs(&reloc_root->root_item) > 0) { - if (IS_ERR(root)) { + if (WARN_ON(IS_ERR(root))) { /* * For recovery we read the fs roots on mount, * and if we didn't find the root then we marked @@ -1984,17 +2016,14 @@ again: * memory. However there's no reason we can't * handle the error properly here just in case. */ - ASSERT(0); ret = PTR_ERR(root); goto out; } - if (root->reloc_root != reloc_root) { + if (WARN_ON(root->reloc_root != reloc_root)) { /* - * This is actually impossible without something - * going really wrong (like weird race condition - * or cosmic rays). + * This can happen if on-disk metadata has some + * corruption, e.g. bad reloc tree key offset. */ - ASSERT(0); ret = -EINVAL; goto out; } diff --git a/fs/btrfs/tests/free-space-tree-tests.c b/fs/btrfs/tests/free-space-tree-tests.c index 13734ed43bfc..766117a76d74 100644 --- a/fs/btrfs/tests/free-space-tree-tests.c +++ b/fs/btrfs/tests/free-space-tree-tests.c @@ -470,7 +470,7 @@ static int run_test(test_func_t test_func, int bitmaps, u32 sectorsize, } cache->bitmap_low_thresh = 0; cache->bitmap_high_thresh = (u32)-1; - cache->needs_free_space = 1; + set_bit(BLOCK_GROUP_FLAG_NEEDS_FREE_SPACE, &cache->runtime_flags); cache->fs_info = root->fs_info; btrfs_init_dummy_trans(&trans, root->fs_info); diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 43f905ab0a18..2b39c7f9226f 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -442,6 +442,20 @@ static int check_root_key(struct extent_buffer *leaf, struct btrfs_key *key, btrfs_item_key_to_cpu(leaf, &item_key, slot); is_root_item = (item_key.type == BTRFS_ROOT_ITEM_KEY); + /* + * Bad rootid for reloc trees. + * + * Reloc trees are only for subvolume trees, other trees only need + * to be COWed to be relocated. + */ + if (unlikely(is_root_item && key->objectid == BTRFS_TREE_RELOC_OBJECTID && + !is_fstree(key->offset))) { + generic_err(leaf, slot, + "invalid reloc tree for root %lld, root id is not a subvolume tree", + key->offset); + return -EUCLEAN; + } + /* No such tree id */ if (unlikely(key->objectid == 0)) { if (is_root_item) diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 2e0832d70406..567c5c010f93 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -4652,8 +4652,7 @@ int btrfs_cancel_balance(struct btrfs_fs_info *fs_info) } } - BUG_ON(fs_info->balance_ctl || - test_bit(BTRFS_FS_BALANCE_RUNNING, &fs_info->flags)); + ASSERT(!test_bit(BTRFS_FS_BALANCE_RUNNING, &fs_info->flags)); atomic_dec(&fs_info->balance_cancel_req); mutex_unlock(&fs_info->balance_mutex); return 0; diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 836babd23db5..9bc7ac06c517 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -1436,7 +1436,7 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new) } if (num_sequential > 0) - cache->seq_zone = true; + set_bit(BLOCK_GROUP_FLAG_SEQUENTIAL_ZONE, &cache->runtime_flags); if (num_conventional > 0) { /* Zone capacity is always zone size in emulation */ @@ -1658,7 +1658,7 @@ bool btrfs_use_zone_append(struct btrfs_inode *inode, u64 start) if (!cache) return false; - ret = cache->seq_zone; + ret = !!test_bit(BLOCK_GROUP_FLAG_SEQUENTIAL_ZONE, &cache->runtime_flags); btrfs_put_block_group(cache); return ret; @@ -2177,7 +2177,8 @@ static void btrfs_zone_finish_endio_workfn(struct work_struct *work) void btrfs_schedule_zone_finish_bg(struct btrfs_block_group *bg, struct extent_buffer *eb) { - if (!bg->seq_zone || eb->start + eb->len * 2 <= bg->start + bg->zone_capacity) + if (!test_bit(BLOCK_GROUP_FLAG_SEQUENTIAL_ZONE, &bg->runtime_flags) || + eb->start + eb->len * 2 <= bg->start + bg->zone_capacity) return; if (WARN_ON(bg->zone_finish_work.func == btrfs_zone_finish_endio_workfn)) { diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 1989c8deea55..5399a9ea5b4f 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -645,6 +645,7 @@ bad: err = -EIO; out_bad: pr_err("mds parse_reply err %d\n", err); + ceph_msg_dump(msg); return err; } @@ -3534,6 +3535,7 @@ static void handle_forward(struct ceph_mds_client *mdsc, bad: pr_err("mdsc_handle_forward decode error err=%d\n", err); + ceph_msg_dump(msg); } static int __decode_session_metadata(void **p, void *end, @@ -4758,7 +4760,7 @@ static void delayed_work(struct work_struct *work) dout("mdsc delayed_work\n"); - if (mdsc->stopping) + if (mdsc->stopping >= CEPH_MDSC_STOPPING_FLUSHED) return; mutex_lock(&mdsc->mutex); @@ -4937,7 +4939,7 @@ void send_flush_mdlog(struct ceph_mds_session *s) void ceph_mdsc_pre_umount(struct ceph_mds_client *mdsc) { dout("pre_umount\n"); - mdsc->stopping = 1; + mdsc->stopping = CEPH_MDSC_STOPPING_BEGIN; ceph_mdsc_iterate_sessions(mdsc, send_flush_mdlog, true); ceph_mdsc_iterate_sessions(mdsc, lock_unlock_session, false); @@ -5254,6 +5256,7 @@ void ceph_mdsc_handle_fsmap(struct ceph_mds_client *mdsc, struct ceph_msg *msg) bad: pr_err("error decoding fsmap %d. Shutting down mount.\n", err); ceph_umount_begin(mdsc->fsc->sb); + ceph_msg_dump(msg); err_out: mutex_lock(&mdsc->mutex); mdsc->mdsmap_err = err; @@ -5322,6 +5325,7 @@ bad_unlock: bad: pr_err("error decoding mdsmap %d. Shutting down mount.\n", err); ceph_umount_begin(mdsc->fsc->sb); + ceph_msg_dump(msg); return; } diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index 18b026b1ac63..9a80658f4167 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -380,6 +380,11 @@ struct cap_wait { int want; }; +enum { + CEPH_MDSC_STOPPING_BEGIN = 1, + CEPH_MDSC_STOPPING_FLUSHED = 2, +}; + /* * mds client state */ diff --git a/fs/ceph/super.c b/fs/ceph/super.c index 3fc48b43cab0..a5f52013314d 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -1374,6 +1374,16 @@ static void ceph_kill_sb(struct super_block *s) ceph_mdsc_pre_umount(fsc->mdsc); flush_fs_workqueues(fsc); + /* + * Though the kill_anon_super() will finally trigger the + * sync_filesystem() anyway, we still need to do it here + * and then bump the stage of shutdown to stop the work + * queue as earlier as possible. + */ + sync_filesystem(s); + + fsc->mdsc->stopping = CEPH_MDSC_STOPPING_FLUSHED; + kill_anon_super(s); fsc->client->extra_mon_dispatch = NULL; diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 533e612b6a48..1b91ac5be961 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -869,6 +869,8 @@ hitted: cur = end - min_t(erofs_off_t, offset + end - map->m_la, end); if (!(map->m_flags & EROFS_MAP_MAPPED)) { zero_user_segment(page, cur, end); + ++spiltted; + tight = false; goto next_part; } if (map->m_flags & EROFS_MAP_FRAGMENT) { @@ -989,10 +991,11 @@ static void z_erofs_do_decompressed_bvec(struct z_erofs_decompress_backend *be, struct z_erofs_bvec *bvec) { struct z_erofs_bvec_item *item; + unsigned int pgnr; - if (!((bvec->offset + be->pcl->pageofs_out) & ~PAGE_MASK)) { - unsigned int pgnr; - + if (!((bvec->offset + be->pcl->pageofs_out) & ~PAGE_MASK) && + (bvec->end == PAGE_SIZE || + bvec->offset + bvec->end == be->pcl->length)) { pgnr = (bvec->offset + be->pcl->pageofs_out) >> PAGE_SHIFT; DBG_BUGON(pgnr >= be->nr_pages); if (!be->decompressed_pages[pgnr]) { diff --git a/fs/exfat/balloc.c b/fs/exfat/balloc.c index 9f42f25fab92..e918decb3735 100644 --- a/fs/exfat/balloc.c +++ b/fs/exfat/balloc.c @@ -69,7 +69,7 @@ static int exfat_allocate_bitmap(struct super_block *sb, } sbi->map_sectors = ((need_map_size - 1) >> (sb->s_blocksize_bits)) + 1; - sbi->vol_amap = kmalloc_array(sbi->map_sectors, + sbi->vol_amap = kvmalloc_array(sbi->map_sectors, sizeof(struct buffer_head *), GFP_KERNEL); if (!sbi->vol_amap) return -ENOMEM; @@ -84,7 +84,7 @@ static int exfat_allocate_bitmap(struct super_block *sb, while (j < i) brelse(sbi->vol_amap[j++]); - kfree(sbi->vol_amap); + kvfree(sbi->vol_amap); sbi->vol_amap = NULL; return -EIO; } @@ -138,7 +138,7 @@ void exfat_free_bitmap(struct exfat_sb_info *sbi) for (i = 0; i < sbi->map_sectors; i++) __brelse(sbi->vol_amap[i]); - kfree(sbi->vol_amap); + kvfree(sbi->vol_amap); } int exfat_set_bitmap(struct inode *inode, unsigned int clu, bool sync) diff --git a/fs/exfat/dir.c b/fs/exfat/dir.c index 15c4f901be36..51b03b0dd5f7 100644 --- a/fs/exfat/dir.c +++ b/fs/exfat/dir.c @@ -34,6 +34,7 @@ static void exfat_get_uniname_from_ext_entry(struct super_block *sb, { int i; struct exfat_entry_set_cache *es; + unsigned int uni_len = 0, len; es = exfat_get_dentry_set(sb, p_dir, entry, ES_ALL_ENTRIES); if (!es) @@ -52,7 +53,10 @@ static void exfat_get_uniname_from_ext_entry(struct super_block *sb, if (exfat_get_entry_type(ep) != TYPE_EXTEND) break; - exfat_extract_uni_name(ep, uniname); + len = exfat_extract_uni_name(ep, uniname); + uni_len += len; + if (len != EXFAT_FILE_NAME_LEN || uni_len >= MAX_NAME_LENGTH) + break; uniname += EXFAT_FILE_NAME_LEN; } @@ -210,7 +214,10 @@ static void exfat_free_namebuf(struct exfat_dentry_namebuf *nb) exfat_init_namebuf(nb); } -/* skip iterating emit_dots when dir is empty */ +/* + * Before calling dir_emit*(), sbi->s_lock should be released + * because page fault can occur in dir_emit*(). + */ #define ITER_POS_FILLED_DOTS (2) static int exfat_iterate(struct file *file, struct dir_context *ctx) { @@ -225,11 +232,10 @@ static int exfat_iterate(struct file *file, struct dir_context *ctx) int err = 0, fake_offset = 0; exfat_init_namebuf(nb); - mutex_lock(&EXFAT_SB(sb)->s_lock); cpos = ctx->pos; if (!dir_emit_dots(file, ctx)) - goto unlock; + goto out; if (ctx->pos == ITER_POS_FILLED_DOTS) { cpos = 0; @@ -241,16 +247,18 @@ static int exfat_iterate(struct file *file, struct dir_context *ctx) /* name buffer should be allocated before use */ err = exfat_alloc_namebuf(nb); if (err) - goto unlock; + goto out; get_new: + mutex_lock(&EXFAT_SB(sb)->s_lock); + if (ei->flags == ALLOC_NO_FAT_CHAIN && cpos >= i_size_read(inode)) goto end_of_dir; err = exfat_readdir(inode, &cpos, &de); if (err) { /* - * At least we tried to read a sector. Move cpos to next sector - * position (should be aligned). + * At least we tried to read a sector. + * Move cpos to next sector position (should be aligned). */ if (err == -EIO) { cpos += 1 << (sb->s_blocksize_bits); @@ -273,16 +281,10 @@ get_new: inum = iunique(sb, EXFAT_ROOT_INO); } - /* - * Before calling dir_emit(), sb_lock should be released. - * Because page fault can occur in dir_emit() when the size - * of buffer given from user is larger than one page size. - */ mutex_unlock(&EXFAT_SB(sb)->s_lock); if (!dir_emit(ctx, nb->lfn, strlen(nb->lfn), inum, (de.attr & ATTR_SUBDIR) ? DT_DIR : DT_REG)) - goto out_unlocked; - mutex_lock(&EXFAT_SB(sb)->s_lock); + goto out; ctx->pos = cpos; goto get_new; @@ -290,9 +292,8 @@ end_of_dir: if (!cpos && fake_offset) cpos = ITER_POS_FILLED_DOTS; ctx->pos = cpos; -unlock: mutex_unlock(&EXFAT_SB(sb)->s_lock); -out_unlocked: +out: /* * To improve performance, free namebuf after unlock sb_lock. * If namebuf is not allocated, this function do nothing @@ -1027,7 +1028,8 @@ rewind: if (entry_type == TYPE_EXTEND) { unsigned short entry_uniname[16], unichar; - if (step != DIRENT_STEP_NAME) { + if (step != DIRENT_STEP_NAME || + name_len >= MAX_NAME_LENGTH) { step = DIRENT_STEP_FILE; continue; } diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h index dc5dcb78bc27..2c95916aead8 100644 --- a/fs/ext2/ext2.h +++ b/fs/ext2/ext2.h @@ -70,10 +70,7 @@ struct mb_cache; * second extended-fs super-block data in memory */ struct ext2_sb_info { - unsigned long s_frag_size; /* Size of a fragment in bytes */ - unsigned long s_frags_per_block;/* Number of fragments per block */ unsigned long s_inodes_per_block;/* Number of inodes per block */ - unsigned long s_frags_per_group;/* Number of fragments in a group */ unsigned long s_blocks_per_group;/* Number of blocks in a group */ unsigned long s_inodes_per_group;/* Number of inodes in a group */ unsigned long s_itb_per_group; /* Number of inode table blocks per group */ @@ -189,15 +186,6 @@ static inline struct ext2_sb_info *EXT2_SB(struct super_block *sb) #define EXT2_FIRST_INO(s) (EXT2_SB(s)->s_first_ino) /* - * Macro-instructions used to manage fragments - */ -#define EXT2_MIN_FRAG_SIZE 1024 -#define EXT2_MAX_FRAG_SIZE 4096 -#define EXT2_MIN_FRAG_LOG_SIZE 10 -#define EXT2_FRAG_SIZE(s) (EXT2_SB(s)->s_frag_size) -#define EXT2_FRAGS_PER_BLOCK(s) (EXT2_SB(s)->s_frags_per_block) - -/* * Structure of a blocks group descriptor */ struct ext2_group_desc diff --git a/fs/ext2/super.c b/fs/ext2/super.c index 3feea4b31fa7..99b26fe20d17 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -668,10 +668,9 @@ static int ext2_setup_super (struct super_block * sb, es->s_max_mnt_count = cpu_to_le16(EXT2_DFL_MAX_MNT_COUNT); le16_add_cpu(&es->s_mnt_count, 1); if (test_opt (sb, DEBUG)) - ext2_msg(sb, KERN_INFO, "%s, %s, bs=%lu, fs=%lu, gc=%lu, " + ext2_msg(sb, KERN_INFO, "%s, %s, bs=%lu, gc=%lu, " "bpg=%lu, ipg=%lu, mo=%04lx]", EXT2FS_VERSION, EXT2FS_DATE, sb->s_blocksize, - sbi->s_frag_size, sbi->s_groups_count, EXT2_BLOCKS_PER_GROUP(sb), EXT2_INODES_PER_GROUP(sb), @@ -1012,14 +1011,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) } } - sbi->s_frag_size = EXT2_MIN_FRAG_SIZE << - le32_to_cpu(es->s_log_frag_size); - if (sbi->s_frag_size == 0) - goto cantfind_ext2; - sbi->s_frags_per_block = sb->s_blocksize / sbi->s_frag_size; - sbi->s_blocks_per_group = le32_to_cpu(es->s_blocks_per_group); - sbi->s_frags_per_group = le32_to_cpu(es->s_frags_per_group); sbi->s_inodes_per_group = le32_to_cpu(es->s_inodes_per_group); sbi->s_inodes_per_block = sb->s_blocksize / EXT2_INODE_SIZE(sb); @@ -1045,11 +1037,10 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount; } - if (sb->s_blocksize != sbi->s_frag_size) { + if (es->s_log_frag_size != es->s_log_block_size) { ext2_msg(sb, KERN_ERR, - "error: fragsize %lu != blocksize %lu" - "(not supported yet)", - sbi->s_frag_size, sb->s_blocksize); + "error: fragsize log %u != blocksize log %u", + le32_to_cpu(es->s_log_frag_size), sb->s_blocksize_bits); goto failed_mount; } @@ -1066,12 +1057,6 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) sbi->s_blocks_per_group, sbi->s_inodes_per_group + 3); goto failed_mount; } - if (sbi->s_frags_per_group > sb->s_blocksize * 8) { - ext2_msg(sb, KERN_ERR, - "error: #fragments per group too big: %lu", - sbi->s_frags_per_group); - goto failed_mount; - } if (sbi->s_inodes_per_group < sbi->s_inodes_per_block || sbi->s_inodes_per_group > sb->s_blocksize * 8) { ext2_msg(sb, KERN_ERR, diff --git a/fs/file.c b/fs/file.c index 35c62b54c9d6..dbca26ef7a01 100644 --- a/fs/file.c +++ b/fs/file.c @@ -1036,12 +1036,28 @@ unsigned long __fdget_raw(unsigned int fd) return __fget_light(fd, 0); } +/* + * Try to avoid f_pos locking. We only need it if the + * file is marked for FMODE_ATOMIC_POS, and it can be + * accessed multiple ways. + * + * Always do it for directories, because pidfd_getfd() + * can make a file accessible even if it otherwise would + * not be, and for directories this is a correctness + * issue, not a "POSIX requirement". + */ +static inline bool file_needs_f_pos_lock(struct file *file) +{ + return (file->f_mode & FMODE_ATOMIC_POS) && + (file_count(file) > 1 || S_ISDIR(file_inode(file)->i_mode)); +} + unsigned long __fdget_pos(unsigned int fd) { unsigned long v = __fdget(fd); struct file *file = (struct file *)(v & ~3); - if (file && (file->f_mode & FMODE_ATOMIC_POS)) { + if (file && file_needs_f_pos_lock(file)) { v |= FDPUT_POS_UNLOCK; mutex_lock(&file->f_pos_lock); } diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index 9d27aa8bd2bc..44c564f0bc62 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -981,7 +981,14 @@ static int gfs2_show_options(struct seq_file *s, struct dentry *root) { struct gfs2_sbd *sdp = root->d_sb->s_fs_info; struct gfs2_args *args = &sdp->sd_args; - int val; + unsigned int logd_secs, statfs_slow, statfs_quantum, quota_quantum; + + spin_lock(&sdp->sd_tune.gt_spin); + logd_secs = sdp->sd_tune.gt_logd_secs; + quota_quantum = sdp->sd_tune.gt_quota_quantum; + statfs_quantum = sdp->sd_tune.gt_statfs_quantum; + statfs_slow = sdp->sd_tune.gt_statfs_slow; + spin_unlock(&sdp->sd_tune.gt_spin); if (is_ancestor(root, sdp->sd_master_dir)) seq_puts(s, ",meta"); @@ -1036,17 +1043,14 @@ static int gfs2_show_options(struct seq_file *s, struct dentry *root) } if (args->ar_discard) seq_puts(s, ",discard"); - val = sdp->sd_tune.gt_logd_secs; - if (val != 30) - seq_printf(s, ",commit=%d", val); - val = sdp->sd_tune.gt_statfs_quantum; - if (val != 30) - seq_printf(s, ",statfs_quantum=%d", val); - else if (sdp->sd_tune.gt_statfs_slow) + if (logd_secs != 30) + seq_printf(s, ",commit=%d", logd_secs); + if (statfs_quantum != 30) + seq_printf(s, ",statfs_quantum=%d", statfs_quantum); + else if (statfs_slow) seq_puts(s, ",statfs_quantum=0"); - val = sdp->sd_tune.gt_quota_quantum; - if (val != 60) - seq_printf(s, ",quota_quantum=%d", val); + if (quota_quantum != 60) + seq_printf(s, ",quota_quantum=%d", quota_quantum); if (args->ar_statfs_percent) seq_printf(s, ",statfs_percent=%d", args->ar_statfs_percent); if (args->ar_errors != GFS2_ERRORS_DEFAULT) { diff --git a/fs/internal.h b/fs/internal.h index 46caa33373a4..42df013f7fe7 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -242,5 +242,3 @@ ssize_t __kernel_write_iter(struct file *file, struct iov_iter *from, loff_t *po /* * fs/attr.c */ -int setattr_should_drop_sgid(struct user_namespace *mnt_userns, - const struct inode *inode); diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index c4e0da6db719..9ec91017a7f3 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -27,7 +27,7 @@ * * Called with j_list_lock held. */ -static inline void __buffer_unlink_first(struct journal_head *jh) +static inline void __buffer_unlink(struct journal_head *jh) { transaction_t *transaction = jh->b_cp_transaction; @@ -41,23 +41,6 @@ static inline void __buffer_unlink_first(struct journal_head *jh) } /* - * Unlink a buffer from a transaction checkpoint(io) list. - * - * Called with j_list_lock held. - */ -static inline void __buffer_unlink(struct journal_head *jh) -{ - transaction_t *transaction = jh->b_cp_transaction; - - __buffer_unlink_first(jh); - if (transaction->t_checkpoint_io_list == jh) { - transaction->t_checkpoint_io_list = jh->b_cpnext; - if (transaction->t_checkpoint_io_list == jh) - transaction->t_checkpoint_io_list = NULL; - } -} - -/* * Check a checkpoint buffer could be release or not. * * Requires j_list_lock @@ -367,49 +350,9 @@ int jbd2_cleanup_journal_tail(journal_t *journal) /* Checkpoint list management */ /* - * journal_clean_one_cp_list - * - * Find all the written-back checkpoint buffers in the given list and - * release them. If 'destroy' is set, clean all buffers unconditionally. - * - * Called with j_list_lock held. - * Returns 1 if we freed the transaction, 0 otherwise. - */ -static int journal_clean_one_cp_list(struct journal_head *jh, bool destroy) -{ - struct journal_head *last_jh; - struct journal_head *next_jh = jh; - - if (!jh) - return 0; - - last_jh = jh->b_cpprev; - do { - jh = next_jh; - next_jh = jh->b_cpnext; - - if (!destroy && __cp_buffer_busy(jh)) - return 0; - - if (__jbd2_journal_remove_checkpoint(jh)) - return 1; - /* - * This function only frees up some memory - * if possible so we dont have an obligation - * to finish processing. Bail out if preemption - * requested: - */ - if (need_resched()) - return 0; - } while (jh != last_jh); - - return 0; -} - -/* * journal_shrink_one_cp_list * - * Find 'nr_to_scan' written-back checkpoint buffers in the given list + * Find all the written-back checkpoint buffers in the given list * and try to release them. If the whole transaction is released, set * the 'released' parameter. Return the number of released checkpointed * buffers. @@ -417,15 +360,15 @@ static int journal_clean_one_cp_list(struct journal_head *jh, bool destroy) * Called with j_list_lock held. */ static unsigned long journal_shrink_one_cp_list(struct journal_head *jh, - unsigned long *nr_to_scan, - bool *released) + bool destroy, bool *released) { struct journal_head *last_jh; struct journal_head *next_jh = jh; unsigned long nr_freed = 0; int ret; - if (!jh || *nr_to_scan == 0) + *released = false; + if (!jh) return 0; last_jh = jh->b_cpprev; @@ -433,12 +376,15 @@ static unsigned long journal_shrink_one_cp_list(struct journal_head *jh, jh = next_jh; next_jh = jh->b_cpnext; - (*nr_to_scan)--; - if (__cp_buffer_busy(jh)) - continue; + if (destroy) { + ret = __jbd2_journal_remove_checkpoint(jh); + } else { + ret = jbd2_journal_try_remove_checkpoint(jh); + if (ret < 0) + continue; + } nr_freed++; - ret = __jbd2_journal_remove_checkpoint(jh); if (ret) { *released = true; break; @@ -446,7 +392,7 @@ static unsigned long journal_shrink_one_cp_list(struct journal_head *jh, if (need_resched()) break; - } while (jh != last_jh && *nr_to_scan); + } while (jh != last_jh); return nr_freed; } @@ -464,11 +410,11 @@ unsigned long jbd2_journal_shrink_checkpoint_list(journal_t *journal, unsigned long *nr_to_scan) { transaction_t *transaction, *last_transaction, *next_transaction; - bool released; + bool __maybe_unused released; tid_t first_tid = 0, last_tid = 0, next_tid = 0; tid_t tid = 0; unsigned long nr_freed = 0; - unsigned long nr_scanned = *nr_to_scan; + unsigned long freed; again: spin_lock(&journal->j_list_lock); @@ -497,19 +443,11 @@ again: transaction = next_transaction; next_transaction = transaction->t_cpnext; tid = transaction->t_tid; - released = false; - nr_freed += journal_shrink_one_cp_list(transaction->t_checkpoint_list, - nr_to_scan, &released); - if (*nr_to_scan == 0) - break; - if (need_resched() || spin_needbreak(&journal->j_list_lock)) - break; - if (released) - continue; - - nr_freed += journal_shrink_one_cp_list(transaction->t_checkpoint_io_list, - nr_to_scan, &released); + freed = journal_shrink_one_cp_list(transaction->t_checkpoint_list, + false, &released); + nr_freed += freed; + (*nr_to_scan) -= min(*nr_to_scan, freed); if (*nr_to_scan == 0) break; if (need_resched() || spin_needbreak(&journal->j_list_lock)) @@ -530,9 +468,8 @@ again: if (*nr_to_scan && next_tid) goto again; out: - nr_scanned -= *nr_to_scan; trace_jbd2_shrink_checkpoint_list(journal, first_tid, tid, last_tid, - nr_freed, nr_scanned, next_tid); + nr_freed, next_tid); return nr_freed; } @@ -548,7 +485,7 @@ out: void __jbd2_journal_clean_checkpoint_list(journal_t *journal, bool destroy) { transaction_t *transaction, *last_transaction, *next_transaction; - int ret; + bool released; transaction = journal->j_checkpoint_transactions; if (!transaction) @@ -559,8 +496,8 @@ void __jbd2_journal_clean_checkpoint_list(journal_t *journal, bool destroy) do { transaction = next_transaction; next_transaction = transaction->t_cpnext; - ret = journal_clean_one_cp_list(transaction->t_checkpoint_list, - destroy); + journal_shrink_one_cp_list(transaction->t_checkpoint_list, + destroy, &released); /* * This function only frees up some memory if possible so we * dont have an obligation to finish processing. Bail out if @@ -568,23 +505,12 @@ void __jbd2_journal_clean_checkpoint_list(journal_t *journal, bool destroy) */ if (need_resched()) return; - if (ret) - continue; - /* - * It is essential that we are as careful as in the case of - * t_checkpoint_list with removing the buffer from the list as - * we can possibly see not yet submitted buffers on io_list - */ - ret = journal_clean_one_cp_list(transaction-> - t_checkpoint_io_list, destroy); - if (need_resched()) - return; /* * Stop scanning if we couldn't free the transaction. This * avoids pointless scanning of transactions which still * weren't checkpointed. */ - if (!ret) + if (!released) return; } while (transaction != last_transaction); } @@ -663,7 +589,7 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh) jbd2_journal_put_journal_head(jh); /* Is this transaction empty? */ - if (transaction->t_checkpoint_list || transaction->t_checkpoint_io_list) + if (transaction->t_checkpoint_list) return 0; /* @@ -695,6 +621,34 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh) } /* + * Check the checkpoint buffer and try to remove it from the checkpoint + * list if it's clean. Returns -EBUSY if it is not clean, returns 1 if + * it frees the transaction, 0 otherwise. + * + * This function is called with j_list_lock held. + */ +int jbd2_journal_try_remove_checkpoint(struct journal_head *jh) +{ + struct buffer_head *bh = jh2bh(jh); + + if (!trylock_buffer(bh)) + return -EBUSY; + if (buffer_dirty(bh)) { + unlock_buffer(bh); + return -EBUSY; + } + unlock_buffer(bh); + + /* + * Buffer is clean and the IO has finished (we held the buffer + * lock) so the checkpoint is done. We can safely remove the + * buffer from this transaction. + */ + JBUFFER_TRACE(jh, "remove from checkpoint list"); + return __jbd2_journal_remove_checkpoint(jh); +} + +/* * journal_insert_checkpoint: put a committed buffer onto a checkpoint * list so that we know when it is safe to clean the transaction out of * the log. @@ -755,7 +709,6 @@ void __jbd2_journal_drop_transaction(journal_t *journal, transaction_t *transact J_ASSERT(transaction->t_forget == NULL); J_ASSERT(transaction->t_shadow_list == NULL); J_ASSERT(transaction->t_checkpoint_list == NULL); - J_ASSERT(transaction->t_checkpoint_io_list == NULL); J_ASSERT(atomic_read(&transaction->t_updates) == 0); J_ASSERT(journal->j_committing_transaction != transaction); J_ASSERT(journal->j_running_transaction != transaction); diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 885a7a6cc53e..f1d9db6686e3 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -1171,8 +1171,7 @@ restart_loop: spin_lock(&journal->j_list_lock); commit_transaction->t_state = T_FINISHED; /* Check if the transaction can be dropped now that we are finished */ - if (commit_transaction->t_checkpoint_list == NULL && - commit_transaction->t_checkpoint_io_list == NULL) { + if (commit_transaction->t_checkpoint_list == NULL) { __jbd2_journal_drop_transaction(journal, commit_transaction); jbd2_journal_free_transaction(commit_transaction); } diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 18611241f451..6ef5022949c4 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -1784,8 +1784,7 @@ int jbd2_journal_forget(handle_t *handle, struct buffer_head *bh) * Otherwise, if the buffer has been written to disk, * it is safe to remove the checkpoint and drop it. */ - if (!buffer_dirty(bh)) { - __jbd2_journal_remove_checkpoint(jh); + if (jbd2_journal_try_remove_checkpoint(jh) >= 0) { spin_unlock(&journal->j_list_lock); goto drop; } @@ -2112,20 +2111,14 @@ __journal_try_to_free_buffer(journal_t *journal, struct buffer_head *bh) jh = bh2jh(bh); - if (buffer_locked(bh) || buffer_dirty(bh)) - goto out; - if (jh->b_next_transaction != NULL || jh->b_transaction != NULL) - goto out; + return; spin_lock(&journal->j_list_lock); - if (jh->b_cp_transaction != NULL) { - /* written-back checkpointed metadata buffer */ - JBUFFER_TRACE(jh, "remove from checkpoint list"); - __jbd2_journal_remove_checkpoint(jh); - } + /* Remove written-back checkpointed metadata buffer */ + if (jh->b_cp_transaction != NULL) + jbd2_journal_try_remove_checkpoint(jh); spin_unlock(&journal->j_list_lock); -out: return; } diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 1707f46b1335..cf34d0c30945 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -474,20 +474,26 @@ out: return result; } -static void -nfs_direct_join_group(struct list_head *list, struct inode *inode) +static void nfs_direct_join_group(struct list_head *list, struct inode *inode) { - struct nfs_page *req, *next; + struct nfs_page *req, *subreq; list_for_each_entry(req, list, wb_list) { - if (req->wb_head != req || req->wb_this_page == req) + if (req->wb_head != req) continue; - for (next = req->wb_this_page; - next != req->wb_head; - next = next->wb_this_page) { - nfs_list_remove_request(next); - nfs_release_request(next); - } + subreq = req->wb_this_page; + if (subreq == req) + continue; + do { + /* + * Remove subrequests from this list before freeing + * them in the call to nfs_join_page_group(). + */ + if (!list_empty(&subreq->wb_list)) { + nfs_list_remove_request(subreq); + nfs_release_request(subreq); + } + } while ((subreq = subreq->wb_this_page) != req); nfs_join_page_group(req, inode); } } diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 6b2cfa59a1a2..e0c1fb98f907 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -717,9 +717,7 @@ void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr, if ((attr->ia_valid & ATTR_KILL_SUID) != 0 && inode->i_mode & S_ISUID) inode->i_mode &= ~S_ISUID; - if ((attr->ia_valid & ATTR_KILL_SGID) != 0 && - (inode->i_mode & (S_ISGID | S_IXGRP)) == - (S_ISGID | S_IXGRP)) + if (setattr_should_drop_sgid(&init_user_ns, inode)) inode->i_mode &= ~S_ISGID; if ((attr->ia_valid & ATTR_MODE) != 0) { int mode = attr->ia_mode & S_IALLUGO; diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index ecb428512fe1..7c33bba179d2 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -1359,7 +1359,6 @@ ssize_t nfs42_proc_getxattr(struct inode *inode, const char *name, for (i = 0; i < np; i++) { pages[i] = alloc_page(GFP_KERNEL); if (!pages[i]) { - np = i + 1; err = -ENOMEM; goto out; } @@ -1383,8 +1382,8 @@ ssize_t nfs42_proc_getxattr(struct inode *inode, const char *name, } while (exception.retry); out: - while (--np >= 0) - __free_page(pages[np]); + while (--i >= 0) + __free_page(pages[i]); kfree(pages); return err; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 177cb7b089b9..1044305e7799 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -5995,9 +5995,8 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, out_ok: ret = res.acl_len; out_free: - for (i = 0; i < npages; i++) - if (pages[i]) - __free_page(pages[i]); + while (--i >= 0) + __free_page(pages[i]); if (res.acl_scratch) __free_page(res.acl_scratch); kfree(pages); @@ -7171,8 +7170,15 @@ static void nfs4_lock_done(struct rpc_task *task, void *calldata) } else if (!nfs4_update_lock_stateid(lsp, &data->res.stateid)) goto out_restart; break; - case -NFS4ERR_BAD_STATEID: case -NFS4ERR_OLD_STATEID: + if (data->arg.new_lock_owner != 0 && + nfs4_refresh_open_old_stateid(&data->arg.open_stateid, + lsp->ls_state)) + goto out_restart; + if (nfs4_refresh_lock_old_stateid(&data->arg.lock_stateid, lsp)) + goto out_restart; + fallthrough; + case -NFS4ERR_BAD_STATEID: case -NFS4ERR_STALE_STATEID: case -NFS4ERR_EXPIRED: if (data->arg.new_lock_owner != 0) { diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index c5dc0cd6f703..96714e105d7b 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -1368,9 +1368,9 @@ static void revoke_delegation(struct nfs4_delegation *dp) WARN_ON(!list_empty(&dp->dl_recall_lru)); if (clp->cl_minorversion) { + spin_lock(&clp->cl_lock); dp->dl_stid.sc_type = NFS4_REVOKED_DELEG_STID; refcount_inc(&dp->dl_stid.sc_count); - spin_lock(&clp->cl_lock); list_add(&dp->dl_recall_lru, &clp->cl_revoked); spin_unlock(&clp->cl_lock); } diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 155b34c4683c..4c11046800ab 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -321,7 +321,9 @@ nfsd_sanitize_attrs(struct inode *inode, struct iattr *iap) iap->ia_mode &= ~S_ISGID; } else { /* set ATTR_KILL_* bits and let VFS handle it */ - iap->ia_valid |= (ATTR_KILL_SUID | ATTR_KILL_SGID); + iap->ia_valid |= ATTR_KILL_SUID; + iap->ia_valid |= + setattr_should_drop_sgid(&init_user_ns, inode); } } } diff --git a/fs/nilfs2/alloc.c b/fs/nilfs2/alloc.c index 6ce8617b562d..7342de296ec3 100644 --- a/fs/nilfs2/alloc.c +++ b/fs/nilfs2/alloc.c @@ -205,7 +205,8 @@ static int nilfs_palloc_get_block(struct inode *inode, unsigned long blkoff, int ret; spin_lock(lock); - if (prev->bh && blkoff == prev->blkoff) { + if (prev->bh && blkoff == prev->blkoff && + likely(buffer_uptodate(prev->bh))) { get_bh(prev->bh); *bhp = prev->bh; spin_unlock(lock); diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index f6e44efb58e1..f625872321cc 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -1025,7 +1025,7 @@ int nilfs_load_inode_block(struct inode *inode, struct buffer_head **pbh) int err; spin_lock(&nilfs->ns_inode_lock); - if (ii->i_bh == NULL) { + if (ii->i_bh == NULL || unlikely(!buffer_uptodate(ii->i_bh))) { spin_unlock(&nilfs->ns_inode_lock); err = nilfs_ifile_get_inode_block(ii->i_root->ifile, inode->i_ino, pbh); @@ -1034,7 +1034,10 @@ int nilfs_load_inode_block(struct inode *inode, struct buffer_head **pbh) spin_lock(&nilfs->ns_inode_lock); if (ii->i_bh == NULL) ii->i_bh = *pbh; - else { + else if (unlikely(!buffer_uptodate(ii->i_bh))) { + __brelse(ii->i_bh); + ii->i_bh = *pbh; + } else { brelse(*pbh); *pbh = ii->i_bh; } @@ -1101,9 +1104,17 @@ int nilfs_set_file_dirty(struct inode *inode, unsigned int nr_dirty) int __nilfs_mark_inode_dirty(struct inode *inode, int flags) { + struct the_nilfs *nilfs = inode->i_sb->s_fs_info; struct buffer_head *ibh; int err; + /* + * Do not dirty inodes after the log writer has been detached + * and its nilfs_root struct has been freed. + */ + if (unlikely(nilfs_purging(nilfs))) + return 0; + err = nilfs_load_inode_block(inode, &ibh); if (unlikely(err)) { nilfs_warn(inode->i_sb, diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 6cf64023be31..a4a147a983e0 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -725,6 +725,11 @@ static size_t nilfs_lookup_dirty_data_buffers(struct inode *inode, struct page *page = pvec.pages[i]; lock_page(page); + if (unlikely(page->mapping != mapping)) { + /* Exclude pages removed from the address space */ + unlock_page(page); + continue; + } if (!page_has_buffers(page)) create_empty_buffers(page, i_blocksize(inode), 0); unlock_page(page); @@ -2843,6 +2848,7 @@ void nilfs_detach_log_writer(struct super_block *sb) nilfs_segctor_destroy(nilfs->ns_writer); nilfs->ns_writer = NULL; } + set_nilfs_purging(nilfs); /* Force to free the list of dirty files */ spin_lock(&nilfs->ns_inode_lock); @@ -2855,4 +2861,5 @@ void nilfs_detach_log_writer(struct super_block *sb) up_write(&nilfs->ns_segctor_sem); nilfs_dispose_list(nilfs, &garbage_list, 1); + clear_nilfs_purging(nilfs); } diff --git a/fs/nilfs2/the_nilfs.h b/fs/nilfs2/the_nilfs.h index 47c7dfbb7ea5..cd4ae1b8ae16 100644 --- a/fs/nilfs2/the_nilfs.h +++ b/fs/nilfs2/the_nilfs.h @@ -29,6 +29,7 @@ enum { THE_NILFS_DISCONTINUED, /* 'next' pointer chain has broken */ THE_NILFS_GC_RUNNING, /* gc process is running */ THE_NILFS_SB_DIRTY, /* super block is dirty */ + THE_NILFS_PURGING, /* disposing dirty files for cleanup */ }; /** @@ -208,6 +209,7 @@ THE_NILFS_FNS(INIT, init) THE_NILFS_FNS(DISCONTINUED, discontinued) THE_NILFS_FNS(GC_RUNNING, gc_running) THE_NILFS_FNS(SB_DIRTY, sb_dirty) +THE_NILFS_FNS(PURGING, purging) /* * Mount option operations diff --git a/fs/ntfs3/attrlist.c b/fs/ntfs3/attrlist.c index c0c6bcbc8c05..81c22df27c72 100644 --- a/fs/ntfs3/attrlist.c +++ b/fs/ntfs3/attrlist.c @@ -52,7 +52,7 @@ int ntfs_load_attr_list(struct ntfs_inode *ni, struct ATTRIB *attr) if (!attr->non_res) { lsize = le32_to_cpu(attr->res.data_size); - le = kmalloc(al_aligned(lsize), GFP_NOFS); + le = kmalloc(al_aligned(lsize), GFP_NOFS | __GFP_NOWARN); if (!le) { err = -ENOMEM; goto out; @@ -80,7 +80,7 @@ int ntfs_load_attr_list(struct ntfs_inode *ni, struct ATTRIB *attr) if (err < 0) goto out; - le = kmalloc(al_aligned(lsize), GFP_NOFS); + le = kmalloc(al_aligned(lsize), GFP_NOFS | __GFP_NOWARN); if (!le) { err = -ENOMEM; goto out; diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c index b1b476fb7229..dda13e1f1b33 100644 --- a/fs/ntfs3/frecord.c +++ b/fs/ntfs3/frecord.c @@ -874,6 +874,7 @@ int ni_create_attr_list(struct ntfs_inode *ni) if (err) goto out1; + err = -EINVAL; /* Call mi_remove_attr() in reverse order to keep pointers 'arr_move' valid. */ while (to_free > 0) { struct ATTRIB *b = arr_move[--nb]; @@ -882,7 +883,8 @@ int ni_create_attr_list(struct ntfs_inode *ni) attr = mi_insert_attr(mi, b->type, Add2Ptr(b, name_off), b->name_len, asize, name_off); - WARN_ON(!attr); + if (!attr) + goto out1; mi_get_ref(mi, &le_b[nb]->ref); le_b[nb]->id = attr->id; @@ -892,17 +894,20 @@ int ni_create_attr_list(struct ntfs_inode *ni) attr->id = le_b[nb]->id; /* Remove from primary record. */ - WARN_ON(!mi_remove_attr(NULL, &ni->mi, b)); + if (!mi_remove_attr(NULL, &ni->mi, b)) + goto out1; if (to_free <= asize) break; to_free -= asize; - WARN_ON(!nb); + if (!nb) + goto out1; } attr = mi_insert_attr(&ni->mi, ATTR_LIST, NULL, 0, lsize + SIZEOF_RESIDENT, SIZEOF_RESIDENT); - WARN_ON(!attr); + if (!attr) + goto out1; attr->non_res = 0; attr->flags = 0; @@ -922,9 +927,10 @@ out1: kfree(ni->attr_list.le); ni->attr_list.le = NULL; ni->attr_list.size = 0; + return err; out: - return err; + return 0; } /* diff --git a/fs/ntfs3/fsntfs.c b/fs/ntfs3/fsntfs.c index b6e22bcb929b..829b62d3bb88 100644 --- a/fs/ntfs3/fsntfs.c +++ b/fs/ntfs3/fsntfs.c @@ -154,7 +154,7 @@ int ntfs_fix_post_read(struct NTFS_RECORD_HEADER *rhdr, size_t bytes, /* Check errors. */ if ((fo & 1) || fo + fn * sizeof(short) > SECTOR_SIZE || !fn-- || fn * SECTOR_SIZE > bytes) { - return -EINVAL; /* Native chkntfs returns ok! */ + return -E_NTFS_CORRUPT; } /* Get fixup pointer. */ diff --git a/fs/ntfs3/index.c b/fs/ntfs3/index.c index 9e9a9ffd9295..495cfb37962f 100644 --- a/fs/ntfs3/index.c +++ b/fs/ntfs3/index.c @@ -1103,6 +1103,12 @@ ok: *node = in; out: + if (err == -E_NTFS_CORRUPT) { + ntfs_inode_err(&ni->vfs_inode, "directory corrupted"); + ntfs_set_state(ni->mi.sbi, NTFS_DIRTY_ERROR); + err = -EINVAL; + } + if (ib != in->index) kfree(ib); diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h index 24227b2e1b2b..8c9abaf139e6 100644 --- a/fs/ntfs3/ntfs_fs.h +++ b/fs/ntfs3/ntfs_fs.h @@ -53,6 +53,8 @@ enum utf16_endian; #define E_NTFS_NONRESIDENT 556 /* NTFS specific error code about punch hole. */ #define E_NTFS_NOTALIGNED 557 +/* NTFS specific error code when on-disk struct is corrupted. */ +#define E_NTFS_CORRUPT 558 /* sbi->flags */ diff --git a/fs/ntfs3/record.c b/fs/ntfs3/record.c index af1e4b364ea8..ba336c7280b8 100644 --- a/fs/ntfs3/record.c +++ b/fs/ntfs3/record.c @@ -124,7 +124,7 @@ int mi_read(struct mft_inode *mi, bool is_mft) struct rw_semaphore *rw_lock = NULL; if (is_mounted(sbi)) { - if (!is_mft) { + if (!is_mft && mft_ni) { rw_lock = &mft_ni->file.run_lock; down_read(rw_lock); } @@ -148,7 +148,7 @@ int mi_read(struct mft_inode *mi, bool is_mft) ni_lock(mft_ni); down_write(rw_lock); } - err = attr_load_runs_vcn(mft_ni, ATTR_DATA, NULL, 0, &mft_ni->file.run, + err = attr_load_runs_vcn(mft_ni, ATTR_DATA, NULL, 0, run, vbo >> sbi->cluster_bits); if (rw_lock) { up_write(rw_lock); @@ -180,6 +180,12 @@ ok: return 0; out: + if (err == -E_NTFS_CORRUPT) { + ntfs_err(sbi->sb, "mft corrupted"); + ntfs_set_state(sbi, NTFS_DIRTY_ERROR); + err = -EINVAL; + } + return err; } diff --git a/fs/open.c b/fs/open.c index 9541430ec5b3..51dc46620d03 100644 --- a/fs/open.c +++ b/fs/open.c @@ -1233,7 +1233,7 @@ inline int build_open_flags(const struct open_how *how, struct open_flags *op) lookup_flags |= LOOKUP_IN_ROOT; if (how->resolve & RESOLVE_CACHED) { /* Don't bother even trying for create/truncate/tmpfile open */ - if (flags & (O_TRUNC | O_CREAT | O_TMPFILE)) + if (flags & (O_TRUNC | O_CREAT | __O_TMPFILE)) return -EAGAIN; lookup_flags |= LOOKUP_CACHED; } diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c index 078df1e2dd18..18d66497c42d 100644 --- a/fs/smb/client/cifsfs.c +++ b/fs/smb/client/cifsfs.c @@ -883,11 +883,11 @@ struct dentry * cifs_smb3_do_mount(struct file_system_type *fs_type, int flags, struct smb3_fs_context *old_ctx) { - int rc; - struct super_block *sb = NULL; - struct cifs_sb_info *cifs_sb = NULL; struct cifs_mnt_data mnt_data; + struct cifs_sb_info *cifs_sb; + struct super_block *sb; struct dentry *root; + int rc; /* * Prints in Kernel / CIFS log the attempted mount operation @@ -898,11 +898,9 @@ cifs_smb3_do_mount(struct file_system_type *fs_type, else cifs_info("Attempting to mount %s\n", old_ctx->UNC); - cifs_sb = kzalloc(sizeof(struct cifs_sb_info), GFP_KERNEL); - if (cifs_sb == NULL) { - root = ERR_PTR(-ENOMEM); - goto out; - } + cifs_sb = kzalloc(sizeof(*cifs_sb), GFP_KERNEL); + if (!cifs_sb) + return ERR_PTR(-ENOMEM); cifs_sb->ctx = kzalloc(sizeof(struct smb3_fs_context), GFP_KERNEL); if (!cifs_sb->ctx) { @@ -945,10 +943,8 @@ cifs_smb3_do_mount(struct file_system_type *fs_type, sb = sget(fs_type, cifs_match_super, cifs_set_super, flags, &mnt_data); if (IS_ERR(sb)) { - root = ERR_CAST(sb); cifs_umount(cifs_sb); - cifs_sb = NULL; - goto out; + return ERR_CAST(sb); } if (sb->s_root) { @@ -979,13 +975,9 @@ out_super: deactivate_locked_super(sb); return root; out: - if (cifs_sb) { - if (!sb || IS_ERR(sb)) { /* otherwise kill_sb will handle */ - kfree(cifs_sb->prepath); - smb3_cleanup_fs_context(cifs_sb->ctx); - kfree(cifs_sb); - } - } + kfree(cifs_sb->prepath); + smb3_cleanup_fs_context(cifs_sb->ctx); + kfree(cifs_sb); return root; } diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index 27c6d14e369f..0f3405e0f2e4 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -4885,9 +4885,9 @@ static int cifs_readpage_worker(struct file *file, struct page *page, io_error: kunmap(page); - unlock_page(page); read_complete: + unlock_page(page); return rc; } @@ -5082,9 +5082,11 @@ void cifs_oplock_break(struct work_struct *work) struct cifsFileInfo *cfile = container_of(work, struct cifsFileInfo, oplock_break); struct inode *inode = d_inode(cfile->dentry); + struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); struct cifsInodeInfo *cinode = CIFS_I(inode); - struct cifs_tcon *tcon = tlink_tcon(cfile->tlink); - struct TCP_Server_Info *server = tcon->ses->server; + struct cifs_tcon *tcon; + struct TCP_Server_Info *server; + struct tcon_link *tlink; int rc = 0; bool purge_cache = false, oplock_break_cancelled; __u64 persistent_fid, volatile_fid; @@ -5093,6 +5095,12 @@ void cifs_oplock_break(struct work_struct *work) wait_on_bit(&cinode->flags, CIFS_INODE_PENDING_WRITERS, TASK_UNINTERRUPTIBLE); + tlink = cifs_sb_tlink(cifs_sb); + if (IS_ERR(tlink)) + goto out; + tcon = tlink_tcon(tlink); + server = tcon->ses->server; + server->ops->downgrade_oplock(server, cinode, cfile->oplock_level, cfile->oplock_epoch, &purge_cache); @@ -5142,18 +5150,19 @@ oplock_break_ack: /* * MS-SMB2 3.2.5.19.1 and 3.2.5.19.2 (and MS-CIFS 3.2.5.42) do not require * an acknowledgment to be sent when the file has already been closed. - * check for server null, since can race with kill_sb calling tree disconnect. */ spin_lock(&cinode->open_file_lock); - if (tcon->ses && tcon->ses->server && !oplock_break_cancelled && - !list_empty(&cinode->openFileList)) { + /* check list empty since can race with kill_sb calling tree disconnect */ + if (!oplock_break_cancelled && !list_empty(&cinode->openFileList)) { spin_unlock(&cinode->open_file_lock); - rc = tcon->ses->server->ops->oplock_response(tcon, persistent_fid, - volatile_fid, net_fid, cinode); + rc = server->ops->oplock_response(tcon, persistent_fid, + volatile_fid, net_fid, cinode); cifs_dbg(FYI, "Oplock release rc = %d\n", rc); } else spin_unlock(&cinode->open_file_lock); + cifs_put_tlink(tlink); +out: cifs_done_oplock_break(cinode); } diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 3ca593cdda76..ba46156e3268 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -3841,6 +3841,12 @@ void smb2_reconnect_server(struct work_struct *work) spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { + spin_lock(&ses->ses_lock); + if (ses->ses_status == SES_EXITING) { + spin_unlock(&ses->ses_lock); + continue; + } + spin_unlock(&ses->ses_lock); tcon_selected = false; diff --git a/fs/smb/server/auth.c b/fs/smb/server/auth.c index 5e5e120edcc2..15e5684e328c 100644 --- a/fs/smb/server/auth.c +++ b/fs/smb/server/auth.c @@ -355,6 +355,9 @@ int ksmbd_decode_ntlmssp_auth_blob(struct authenticate_message *authblob, if (blob_len < (u64)sess_key_off + sess_key_len) return -EINVAL; + if (sess_key_len > CIFS_KEY_SIZE) + return -EINVAL; + ctx_arc4 = kmalloc(sizeof(*ctx_arc4), GFP_KERNEL); if (!ctx_arc4) return -ENOMEM; diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index 4b210cdd7556..c81aee9ce7ec 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -1492,7 +1492,7 @@ struct create_context *smb2_find_context_vals(void *open_req, const char *tag, i name_len < 4 || name_off + name_len > cc_len || (value_off & 0x7) != 0 || - (value_off && (value_off < name_off + name_len)) || + (value_len && value_off < name_off + (name_len < 8 ? 8 : name_len)) || ((u64)value_off + value_len > cc_len)) return ERR_PTR(-EINVAL); diff --git a/fs/smb/server/smb2misc.c b/fs/smb/server/smb2misc.c index 33b7e6c4ceff..e881df1d10cb 100644 --- a/fs/smb/server/smb2misc.c +++ b/fs/smb/server/smb2misc.c @@ -380,13 +380,13 @@ int ksmbd_smb2_check_message(struct ksmbd_work *work) } if (smb2_req_struct_sizes[command] != pdu->StructureSize2) { - if (command == SMB2_OPLOCK_BREAK_HE && - le16_to_cpu(pdu->StructureSize2) != OP_BREAK_STRUCT_SIZE_20 && - le16_to_cpu(pdu->StructureSize2) != OP_BREAK_STRUCT_SIZE_21) { + if (!(command == SMB2_OPLOCK_BREAK_HE && + (le16_to_cpu(pdu->StructureSize2) == OP_BREAK_STRUCT_SIZE_20 || + le16_to_cpu(pdu->StructureSize2) == OP_BREAK_STRUCT_SIZE_21))) { /* special case for SMB2.1 lease break message */ ksmbd_debug(SMB, - "Illegal request size %d for oplock break\n", - le16_to_cpu(pdu->StructureSize2)); + "Illegal request size %u for command %d\n", + le16_to_cpu(pdu->StructureSize2), command); return 1; } } diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 26cf73d664f9..9b621fd993bb 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -2340,9 +2340,16 @@ next: break; buf_len -= next; eabuf = (struct smb2_ea_info *)((char *)eabuf + next); - if (next < (u32)eabuf->EaNameLength + le16_to_cpu(eabuf->EaValueLength)) + if (buf_len < sizeof(struct smb2_ea_info)) { + rc = -EINVAL; break; + } + if (buf_len < sizeof(struct smb2_ea_info) + eabuf->EaNameLength + + le16_to_cpu(eabuf->EaValueLength)) { + rc = -EINVAL; + break; + } } while (next != 0); kfree(attr_name); @@ -4315,7 +4322,7 @@ static int smb2_get_ea(struct ksmbd_work *work, struct ksmbd_file *fp, if (!strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN)) name_len -= XATTR_USER_PREFIX_LEN; - ptr = (char *)(&eainfo->name + name_len + 1); + ptr = eainfo->name + name_len + 1; buf_free_len -= (offsetof(struct smb2_ea_info, name) + name_len + 1); /* bailout if xattr can't fit in buf_free_len */ diff --git a/fs/smb/server/smb2pdu.h b/fs/smb/server/smb2pdu.h index dd10f8031606..665a83737854 100644 --- a/fs/smb/server/smb2pdu.h +++ b/fs/smb/server/smb2pdu.h @@ -410,7 +410,7 @@ struct smb2_ea_info { __u8 Flags; __u8 EaNameLength; __le16 EaValueLength; - char name[1]; + char name[]; /* optionally followed by value */ } __packed; /* level 15 Query */ diff --git a/fs/smb/server/transport_rdma.c b/fs/smb/server/transport_rdma.c index c06efc020bd9..7578200f63b1 100644 --- a/fs/smb/server/transport_rdma.c +++ b/fs/smb/server/transport_rdma.c @@ -1366,24 +1366,35 @@ static int smb_direct_rdma_xmit(struct smb_direct_transport *t, LIST_HEAD(msg_list); char *desc_buf; int credits_needed; - unsigned int desc_buf_len; - size_t total_length = 0; + unsigned int desc_buf_len, desc_num = 0; if (t->status != SMB_DIRECT_CS_CONNECTED) return -ENOTCONN; + if (buf_len > t->max_rdma_rw_size) + return -EINVAL; + /* calculate needed credits */ credits_needed = 0; desc_buf = buf; for (i = 0; i < desc_len / sizeof(*desc); i++) { + if (!buf_len) + break; + desc_buf_len = le32_to_cpu(desc[i].length); + if (!desc_buf_len) + return -EINVAL; + + if (desc_buf_len > buf_len) { + desc_buf_len = buf_len; + desc[i].length = cpu_to_le32(desc_buf_len); + buf_len = 0; + } credits_needed += calc_rw_credits(t, desc_buf, desc_buf_len); desc_buf += desc_buf_len; - total_length += desc_buf_len; - if (desc_buf_len == 0 || total_length > buf_len || - total_length > t->max_rdma_rw_size) - return -EINVAL; + buf_len -= desc_buf_len; + desc_num++; } ksmbd_debug(RDMA, "RDMA %s, len %#x, needed credits %#x\n", @@ -1395,7 +1406,7 @@ static int smb_direct_rdma_xmit(struct smb_direct_transport *t, /* build rdma_rw_ctx for each descriptor */ desc_buf = buf; - for (i = 0; i < desc_len / sizeof(*desc); i++) { + for (i = 0; i < desc_num; i++) { msg = kzalloc(offsetof(struct smb_direct_rdma_rw_msg, sg_list) + sizeof(struct scatterlist) * SG_CHUNK_SIZE, GFP_KERNEL); if (!msg) { diff --git a/fs/super.c b/fs/super.c index 7c140ee60c54..d138332e57a9 100644 --- a/fs/super.c +++ b/fs/super.c @@ -904,6 +904,7 @@ int reconfigure_super(struct fs_context *fc) struct super_block *sb = fc->root->d_sb; int retval; bool remount_ro = false; + bool remount_rw = false; bool force = fc->sb_flags & SB_FORCE; if (fc->sb_flags_mask & ~MS_RMT_MASK) @@ -921,7 +922,7 @@ int reconfigure_super(struct fs_context *fc) bdev_read_only(sb->s_bdev)) return -EACCES; #endif - + remount_rw = !(fc->sb_flags & SB_RDONLY) && sb_rdonly(sb); remount_ro = (fc->sb_flags & SB_RDONLY) && !sb_rdonly(sb); } @@ -951,6 +952,14 @@ int reconfigure_super(struct fs_context *fc) if (retval) return retval; } + } else if (remount_rw) { + /* + * We set s_readonly_remount here to protect filesystem's + * reconfigure code from writes from userspace until + * reconfigure finishes. + */ + sb->s_readonly_remount = 1; + smp_wmb(); } if (fc->ops->reconfigure) { diff --git a/fs/sysv/itree.c b/fs/sysv/itree.c index 3b8567564e7e..9925cfe57159 100644 --- a/fs/sysv/itree.c +++ b/fs/sysv/itree.c @@ -145,6 +145,10 @@ static int alloc_branch(struct inode *inode, */ parent = block_to_cpu(SYSV_SB(inode->i_sb), branch[n-1].key); bh = sb_getblk(inode->i_sb, parent); + if (!bh) { + sysv_free_block(inode->i_sb, branch[n].key); + break; + } lock_buffer(bh); memset(bh->b_data, 0, blocksize); branch[n].bh = bh; diff --git a/include/asm-generic/bugs.h b/include/asm-generic/bugs.h deleted file mode 100644 index 69021830f078..000000000000 --- a/include/asm-generic/bugs.h +++ /dev/null @@ -1,11 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __ASM_GENERIC_BUGS_H -#define __ASM_GENERIC_BUGS_H -/* - * This file is included by 'init/main.c' to check for - * architecture-dependent bugs. - */ - -static inline void check_bugs(void) { } - -#endif /* __ASM_GENERIC_BUGS_H */ diff --git a/include/asm-generic/word-at-a-time.h b/include/asm-generic/word-at-a-time.h index 20c93f08c993..95a1d214108a 100644 --- a/include/asm-generic/word-at-a-time.h +++ b/include/asm-generic/word-at-a-time.h @@ -38,7 +38,7 @@ static inline long find_zero(unsigned long mask) return (mask >> 8) ? byte : byte + 1; } -static inline bool has_zero(unsigned long val, unsigned long *data, const struct word_at_a_time *c) +static inline unsigned long has_zero(unsigned long val, unsigned long *data, const struct word_at_a_time *c) { unsigned long rhs = val | c->low_bits; *data = rhs; diff --git a/include/drm/display/drm_dp.h b/include/drm/display/drm_dp.h index e5ba3e8f1bc0..1f3eae8f5b63 100644 --- a/include/drm/display/drm_dp.h +++ b/include/drm/display/drm_dp.h @@ -1534,7 +1534,7 @@ enum drm_dp_phy { #define DP_BRANCH_OUI_HEADER_SIZE 0xc #define DP_RECEIVER_CAP_SIZE 0xf -#define DP_DSC_RECEIVER_CAP_SIZE 0xf +#define DP_DSC_RECEIVER_CAP_SIZE 0x10 /* DSC Capabilities 0x60 through 0x6F */ #define EDP_PSR_RECEIVER_CAP_SIZE 2 #define EDP_DISPLAY_CTL_CAP_SIZE 3 #define DP_LTTPR_COMMON_CAP_SIZE 8 diff --git a/include/drm/drm_aperture.h b/include/drm/drm_aperture.h index 7096703c3949..cbe33b49fd5d 100644 --- a/include/drm/drm_aperture.h +++ b/include/drm/drm_aperture.h @@ -13,14 +13,13 @@ int devm_aperture_acquire_from_firmware(struct drm_device *dev, resource_size_t resource_size_t size); int drm_aperture_remove_conflicting_framebuffers(resource_size_t base, resource_size_t size, - bool primary, const struct drm_driver *req_driver); + const struct drm_driver *req_driver); int drm_aperture_remove_conflicting_pci_framebuffers(struct pci_dev *pdev, const struct drm_driver *req_driver); /** * drm_aperture_remove_framebuffers - remove all existing framebuffers - * @primary: also kick vga16fb if present * @req_driver: requesting DRM driver * * This function removes all graphics device drivers. Use this function on systems @@ -30,9 +29,9 @@ int drm_aperture_remove_conflicting_pci_framebuffers(struct pci_dev *pdev, * 0 on success, or a negative errno code otherwise */ static inline int -drm_aperture_remove_framebuffers(bool primary, const struct drm_driver *req_driver) +drm_aperture_remove_framebuffers(const struct drm_driver *req_driver) { - return drm_aperture_remove_conflicting_framebuffers(0, (resource_size_t)-1, primary, + return drm_aperture_remove_conflicting_framebuffers(0, (resource_size_t)-1, req_driver); } diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index 4df9e73a8bb5..1d7d4cffaefc 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -429,6 +429,6 @@ int kvm_vgic_v4_unset_forwarding(struct kvm *kvm, int irq, int vgic_v4_load(struct kvm_vcpu *vcpu); void vgic_v4_commit(struct kvm_vcpu *vcpu); -int vgic_v4_put(struct kvm_vcpu *vcpu, bool need_db); +int vgic_v4_put(struct kvm_vcpu *vcpu); #endif /* __KVM_ARM_VGIC_H */ diff --git a/include/linux/clk.h b/include/linux/clk.h index 1ef013324237..06f1b292f8a0 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -183,6 +183,39 @@ int clk_get_scaled_duty_cycle(struct clk *clk, unsigned int scale); */ bool clk_is_match(const struct clk *p, const struct clk *q); +/** + * clk_rate_exclusive_get - get exclusivity over the rate control of a + * producer + * @clk: clock source + * + * This function allows drivers to get exclusive control over the rate of a + * provider. It prevents any other consumer to execute, even indirectly, + * opereation which could alter the rate of the provider or cause glitches + * + * If exlusivity is claimed more than once on clock, even by the same driver, + * the rate effectively gets locked as exclusivity can't be preempted. + * + * Must not be called from within atomic context. + * + * Returns success (0) or negative errno. + */ +int clk_rate_exclusive_get(struct clk *clk); + +/** + * clk_rate_exclusive_put - release exclusivity over the rate control of a + * producer + * @clk: clock source + * + * This function allows drivers to release the exclusivity it previously got + * from clk_rate_exclusive_get() + * + * The caller must balance the number of clk_rate_exclusive_get() and + * clk_rate_exclusive_put() calls. + * + * Must not be called from within atomic context. + */ +void clk_rate_exclusive_put(struct clk *clk); + #else static inline int clk_notifier_register(struct clk *clk, @@ -236,6 +269,13 @@ static inline bool clk_is_match(const struct clk *p, const struct clk *q) return p == q; } +static inline int clk_rate_exclusive_get(struct clk *clk) +{ + return 0; +} + +static inline void clk_rate_exclusive_put(struct clk *clk) {} + #endif #ifdef CONFIG_HAVE_CLK_PREPARE @@ -583,38 +623,6 @@ struct clk *devm_clk_get_optional_enabled(struct device *dev, const char *id); */ struct clk *devm_get_clk_from_child(struct device *dev, struct device_node *np, const char *con_id); -/** - * clk_rate_exclusive_get - get exclusivity over the rate control of a - * producer - * @clk: clock source - * - * This function allows drivers to get exclusive control over the rate of a - * provider. It prevents any other consumer to execute, even indirectly, - * opereation which could alter the rate of the provider or cause glitches - * - * If exlusivity is claimed more than once on clock, even by the same driver, - * the rate effectively gets locked as exclusivity can't be preempted. - * - * Must not be called from within atomic context. - * - * Returns success (0) or negative errno. - */ -int clk_rate_exclusive_get(struct clk *clk); - -/** - * clk_rate_exclusive_put - release exclusivity over the rate control of a - * producer - * @clk: clock source - * - * This function allows drivers to release the exclusivity it previously got - * from clk_rate_exclusive_get() - * - * The caller must balance the number of clk_rate_exclusive_get() and - * clk_rate_exclusive_put() calls. - * - * Must not be called from within atomic context. - */ -void clk_rate_exclusive_put(struct clk *clk); /** * clk_enable - inform the system when the clock source should be running. @@ -974,14 +982,6 @@ static inline void clk_bulk_put_all(int num_clks, struct clk_bulk_data *clks) {} static inline void devm_clk_put(struct device *dev, struct clk *clk) {} - -static inline int clk_rate_exclusive_get(struct clk *clk) -{ - return 0; -} - -static inline void clk_rate_exclusive_put(struct clk *clk) {} - static inline int clk_enable(struct clk *clk) { return 0; diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 314802f98b9d..008bfa68cfab 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -70,6 +70,10 @@ extern ssize_t cpu_show_mmio_stale_data(struct device *dev, char *buf); extern ssize_t cpu_show_retbleed(struct device *dev, struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_spec_rstack_overflow(struct device *dev, + struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_gds(struct device *dev, + struct device_attribute *attr, char *buf); extern __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata, @@ -187,6 +191,12 @@ void arch_cpu_idle_enter(void); void arch_cpu_idle_exit(void); void arch_cpu_idle_dead(void); +#ifdef CONFIG_ARCH_HAS_CPU_FINALIZE_INIT +void arch_cpu_finalize_init(void); +#else +static inline void arch_cpu_finalize_init(void) { } +#endif + int cpu_report_state(int cpu); int cpu_check_up_prepare(int cpu); void cpu_set_state_online(int cpu); diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index d58e0476ee8e..0348dba5680e 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -71,8 +71,10 @@ extern void cpuset_init_smp(void); extern void cpuset_force_rebuild(void); extern void cpuset_update_active_cpus(void); extern void cpuset_wait_for_hotplug(void); -extern void cpuset_read_lock(void); -extern void cpuset_read_unlock(void); +extern void inc_dl_tasks_cs(struct task_struct *task); +extern void dec_dl_tasks_cs(struct task_struct *task); +extern void cpuset_lock(void); +extern void cpuset_unlock(void); extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask); extern bool cpuset_cpus_allowed_fallback(struct task_struct *p); extern nodemask_t cpuset_mems_allowed(struct task_struct *p); @@ -196,8 +198,10 @@ static inline void cpuset_update_active_cpus(void) static inline void cpuset_wait_for_hotplug(void) { } -static inline void cpuset_read_lock(void) { } -static inline void cpuset_read_unlock(void) { } +static inline void inc_dl_tasks_cs(struct task_struct *task) { } +static inline void dec_dl_tasks_cs(struct task_struct *task) { } +static inline void cpuset_lock(void) { } +static inline void cpuset_unlock(void) { } static inline void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask) diff --git a/include/linux/fs.h b/include/linux/fs.h index a2b5592c6828..26ea1a0a59a1 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3120,6 +3120,8 @@ extern struct inode *new_inode(struct super_block *sb); extern void free_inode_nonrcu(struct inode *inode); extern int setattr_should_drop_suidgid(struct user_namespace *, struct inode *); extern int file_remove_privs(struct file *); +int setattr_should_drop_sgid(struct user_namespace *mnt_userns, + const struct inode *inode); /* * This must be used for allocating filesystems specific inodes to set diff --git a/include/linux/iopoll.h b/include/linux/iopoll.h index 2c8860e406bd..0417360a6db9 100644 --- a/include/linux/iopoll.h +++ b/include/linux/iopoll.h @@ -53,6 +53,7 @@ } \ if (__sleep_us) \ usleep_range((__sleep_us >> 2) + 1, __sleep_us); \ + cpu_relax(); \ } \ (cond) ? 0 : -ETIMEDOUT; \ }) @@ -95,6 +96,7 @@ } \ if (__delay_us) \ udelay(__delay_us); \ + cpu_relax(); \ } \ (cond) ? 0 : -ETIMEDOUT; \ }) diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 0b7242370b56..ebb1608d9dcd 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -623,12 +623,6 @@ struct transaction_s struct journal_head *t_checkpoint_list; /* - * Doubly-linked circular list of all buffers submitted for IO while - * checkpointing. [j_list_lock] - */ - struct journal_head *t_checkpoint_io_list; - - /* * Doubly-linked circular list of metadata buffers being * shadowed by log IO. The IO buffers on the iobuf list and * the shadow buffers on this list match each other one for @@ -1441,6 +1435,7 @@ extern void jbd2_journal_commit_transaction(journal_t *); void __jbd2_journal_clean_checkpoint_list(journal_t *journal, bool destroy); unsigned long jbd2_journal_shrink_checkpoint_list(journal_t *journal, unsigned long *nr_to_scan); int __jbd2_journal_remove_checkpoint(struct journal_head *); +int jbd2_journal_try_remove_checkpoint(struct journal_head *jh); void jbd2_journal_destroy_checkpoint(journal_t *journal); void __jbd2_journal_insert_checkpoint(struct journal_head *, transaction_t *); diff --git a/include/linux/mm.h b/include/linux/mm.h index b8ed44f401b5..104ec00823da 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1727,6 +1727,25 @@ static inline size_t folio_size(struct folio *folio) return PAGE_SIZE << folio_order(folio); } +/** + * folio_estimated_sharers - Estimate the number of sharers of a folio. + * @folio: The folio. + * + * folio_estimated_sharers() aims to serve as a function to efficiently + * estimate the number of processes sharing a folio. This is done by + * looking at the precise mapcount of the first subpage in the folio, and + * assuming the other subpages are the same. This may not be true for large + * folios. If you want exact mapcounts for exact calculations, look at + * page_mapcount() or folio_total_mapcount(). + * + * Return: The estimated number of processes sharing a folio. + */ +static inline int folio_estimated_sharers(struct folio *folio) +{ + return page_mapcount(folio_page(folio, 0)); +} + + #ifndef HAVE_ARCH_MAKE_PAGE_ACCESSIBLE static inline int arch_make_page_accessible(struct page *page) { @@ -3092,6 +3111,16 @@ static inline bool gup_must_unshare(unsigned int flags, struct page *page) smp_rmb(); /* + * During GUP-fast we might not get called on the head page for a + * hugetlb page that is mapped using cont-PTE, because GUP-fast does + * not work with the abstracted hugetlb PTEs that always point at the + * head page. For hugetlb, PageAnonExclusive only applies on the head + * page (as it cannot be partially COW-shared), so lookup the head page. + */ + if (unlikely(!PageHead(page) && PageHuge(page))) + page = compound_head(page); + + /* * Note that PageKsm() pages cannot be exclusive, and consequently, * cannot get pinned. */ diff --git a/include/linux/moduleloader.h b/include/linux/moduleloader.h index 9e09d11ffe5b..1322652a9d0d 100644 --- a/include/linux/moduleloader.h +++ b/include/linux/moduleloader.h @@ -39,6 +39,11 @@ bool module_init_section(const char *name); */ bool module_exit_section(const char *name); +/* Describes whether within_module_init() will consider this an init section + * or not. This behaviour changes with CONFIG_MODULE_UNLOAD. + */ +bool module_init_layout_section(const char *sname); + /* * Apply the given relocation to the (simplified) ELF. Return -error * or 0. diff --git a/include/linux/raid_class.h b/include/linux/raid_class.h index 5cdfcb873a8f..772d45b2a60a 100644 --- a/include/linux/raid_class.h +++ b/include/linux/raid_class.h @@ -77,7 +77,3 @@ DEFINE_RAID_ATTRIBUTE(enum raid_state, state) struct raid_template *raid_class_attach(struct raid_function_template *); void raid_class_release(struct raid_template *); - -int __must_check raid_component_add(struct raid_template *, struct device *, - struct device *); - diff --git a/include/linux/sched.h b/include/linux/sched.h index ffb6eb55cd13..0cac69902ec5 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1846,7 +1846,9 @@ current_restore_flags(unsigned long orig_flags, unsigned long flags) } extern int cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial); -extern int task_can_attach(struct task_struct *p, const struct cpumask *cs_effective_cpus); +extern int task_can_attach(struct task_struct *p); +extern int dl_bw_alloc(int cpu, u64 dl_bw); +extern void dl_bw_free(int cpu, u64 dl_bw); #ifdef CONFIG_SMP extern void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask); extern int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask); diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index d6c48163c6de..357e0068497c 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -65,6 +65,7 @@ extern void sched_dead(struct task_struct *p); void __noreturn do_task_dead(void); void __noreturn make_task_dead(int signr); +extern void mm_cache_init(void); extern void proc_caches_init(void); extern void fork_init(void); @@ -90,7 +91,6 @@ extern void exit_itimers(struct task_struct *); extern pid_t kernel_clone(struct kernel_clone_args *kargs); struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node); struct task_struct *fork_idle(int); -struct mm_struct *copy_init_mm(void); extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags); extern pid_t user_mode_thread(int (*fn)(void *), void *arg, unsigned long flags); extern long kernel_wait4(pid_t, int __user *, int, struct rusage *); diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 054d7911bfc9..c1637515a8a4 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -62,6 +62,7 @@ struct sk_psock_progs { enum sk_psock_state_bits { SK_PSOCK_TX_ENABLED, + SK_PSOCK_RX_STRP_ENABLED, }; struct sk_psock_link { diff --git a/include/linux/tpm.h b/include/linux/tpm.h index 4e22e4f4cec8..df5cd4245f29 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -282,6 +282,7 @@ enum tpm_chip_flags { TPM_CHIP_FLAG_FIRMWARE_POWER_MANAGED = BIT(6), TPM_CHIP_FLAG_FIRMWARE_UPGRADE = BIT(7), TPM_CHIP_FLAG_SUSPENDED = BIT(8), + TPM_CHIP_FLAG_HWRNG_DISABLED = BIT(9), }; #define to_tpm_chip(d) container_of(d, struct tpm_chip, dev) diff --git a/include/linux/usb/tcpci.h b/include/linux/usb/tcpci.h index 17657451c762..77eb40b918d7 100644 --- a/include/linux/usb/tcpci.h +++ b/include/linux/usb/tcpci.h @@ -103,6 +103,7 @@ #define TCPC_POWER_STATUS_SINKING_VBUS BIT(0) #define TCPC_FAULT_STATUS 0x1f +#define TCPC_FAULT_STATUS_ALL_REG_RST_TO_DEFAULT BIT(7) #define TCPC_ALERT_EXTENDED 0x21 diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index a960de68ac69..6047058d6703 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -148,6 +148,10 @@ retry: if (gso_type & SKB_GSO_UDP) nh_off -= thlen; + /* Kernel has a special handling for GSO_BY_FRAGS. */ + if (gso_size == GSO_BY_FRAGS) + return -EINVAL; + /* Too small packets are not really GSO ones. */ if (skb->len - nh_off > gso_size) { shinfo->gso_size = gso_size; diff --git a/include/media/v4l2-mem2mem.h b/include/media/v4l2-mem2mem.h index bb9de6a899e0..d6c8eb2b5201 100644 --- a/include/media/v4l2-mem2mem.h +++ b/include/media/v4l2-mem2mem.h @@ -593,7 +593,14 @@ void v4l2_m2m_buf_queue(struct v4l2_m2m_ctx *m2m_ctx, static inline unsigned int v4l2_m2m_num_src_bufs_ready(struct v4l2_m2m_ctx *m2m_ctx) { - return m2m_ctx->out_q_ctx.num_rdy; + unsigned int num_buf_rdy; + unsigned long flags; + + spin_lock_irqsave(&m2m_ctx->out_q_ctx.rdy_spinlock, flags); + num_buf_rdy = m2m_ctx->out_q_ctx.num_rdy; + spin_unlock_irqrestore(&m2m_ctx->out_q_ctx.rdy_spinlock, flags); + + return num_buf_rdy; } /** @@ -605,7 +612,14 @@ unsigned int v4l2_m2m_num_src_bufs_ready(struct v4l2_m2m_ctx *m2m_ctx) static inline unsigned int v4l2_m2m_num_dst_bufs_ready(struct v4l2_m2m_ctx *m2m_ctx) { - return m2m_ctx->cap_q_ctx.num_rdy; + unsigned int num_buf_rdy; + unsigned long flags; + + spin_lock_irqsave(&m2m_ctx->cap_q_ctx.rdy_spinlock, flags); + num_buf_rdy = m2m_ctx->cap_q_ctx.num_rdy; + spin_unlock_irqrestore(&m2m_ctx->cap_q_ctx.rdy_spinlock, flags); + + return num_buf_rdy; } /** diff --git a/include/net/bonding.h b/include/net/bonding.h index 17329a19f0c6..9a3ac960dfe1 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -727,23 +727,14 @@ static inline struct slave *bond_slave_has_mac(struct bonding *bond, } /* Caller must hold rcu_read_lock() for read */ -static inline bool bond_slave_has_mac_rx(struct bonding *bond, const u8 *mac) +static inline bool bond_slave_has_mac_rcu(struct bonding *bond, const u8 *mac) { struct list_head *iter; struct slave *tmp; - struct netdev_hw_addr *ha; bond_for_each_slave_rcu(bond, tmp, iter) if (ether_addr_equal_64bits(mac, tmp->dev->dev_addr)) return true; - - if (netdev_uc_empty(bond->dev)) - return false; - - netdev_for_each_uc_addr(ha, bond->dev) - if (ether_addr_equal_64bits(mac, ha->addr)) - return true; - return false; } diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index e09ff87146c1..5976545aa26b 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -562,6 +562,9 @@ ieee80211_get_sband_iftype_data(const struct ieee80211_supported_band *sband, if (WARN_ON(iftype >= NL80211_IFTYPE_MAX)) return NULL; + if (iftype == NL80211_IFTYPE_AP_VLAN) + iftype = NL80211_IFTYPE_AP; + for (i = 0; i < sband->n_iftype_data; i++) { const struct ieee80211_sband_iftype_data *data = &sband->iftype_data[i]; diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 51857117ac09..c2432c2addc8 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -107,11 +107,12 @@ static inline struct inet_request_sock *inet_rsk(const struct request_sock *sk) static inline u32 inet_request_mark(const struct sock *sk, struct sk_buff *skb) { - if (!sk->sk_mark && - READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fwmark_accept)) + u32 mark = READ_ONCE(sk->sk_mark); + + if (!mark && READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fwmark_accept)) return skb->mark; - return sk->sk_mark; + return mark; } static inline int inet_request_bound_dev_if(const struct sock *sk, @@ -221,8 +222,8 @@ struct inet_sock { __s16 uc_ttl; __u16 cmsg_flags; struct ip_options_rcu __rcu *inet_opt; + atomic_t inet_id; __be16 inet_sport; - __u16 inet_id; __u8 tos; __u8 min_ttl; diff --git a/include/net/ip.h b/include/net/ip.h index 83a1a9bc3ceb..1872f570abed 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -93,7 +93,7 @@ static inline void ipcm_init_sk(struct ipcm_cookie *ipcm, { ipcm_init(ipcm); - ipcm->sockc.mark = inet->sk.sk_mark; + ipcm->sockc.mark = READ_ONCE(inet->sk.sk_mark); ipcm->sockc.tsflags = inet->sk.sk_tsflags; ipcm->oif = READ_ONCE(inet->sk.sk_bound_dev_if); ipcm->addr = inet->inet_saddr; @@ -532,8 +532,19 @@ static inline void ip_select_ident_segs(struct net *net, struct sk_buff *skb, * generator as much as we can. */ if (sk && inet_sk(sk)->inet_daddr) { - iph->id = htons(inet_sk(sk)->inet_id); - inet_sk(sk)->inet_id += segs; + int val; + + /* avoid atomic operations for TCP, + * as we hold socket lock at this point. + */ + if (sk_is_tcp(sk)) { + sock_owned_by_me(sk); + val = atomic_read(&inet_sk(sk)->inet_id); + atomic_set(&inet_sk(sk)->inet_id, val + segs); + } else { + val = atomic_add_return(segs, &inet_sk(sk)->inet_id); + } + iph->id = htons(val); return; } if ((iph->frag_off & htons(IP_DF)) && !skb->ignore_df) { diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 72b739dc6d53..8a338c33118f 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -6444,6 +6444,7 @@ void ieee80211_stop_rx_ba_session(struct ieee80211_vif *vif, u16 ba_rx_bitmap, * marks frames marked in the bitmap as having been filtered. Afterwards, it * checks if any frames in the window starting from @ssn can now be released * (in case they were only waiting for frames that were filtered.) + * (Only work correctly if @max_rx_aggregation_subframes <= 64 frames) */ void ieee80211_mark_rx_ba_filtered_frames(struct ieee80211_sta *pubsta, u8 tid, u16 ssn, u64 filtered, diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index f3a37cacb32c..c752b6f50979 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1192,6 +1192,29 @@ int __nft_release_basechain(struct nft_ctx *ctx); unsigned int nft_do_chain(struct nft_pktinfo *pkt, void *priv); +static inline bool nft_use_inc(u32 *use) +{ + if (*use == UINT_MAX) + return false; + + (*use)++; + + return true; +} + +static inline void nft_use_dec(u32 *use) +{ + WARN_ON_ONCE((*use)-- == 0); +} + +/* For error and abort path: restore use counter to previous state. */ +static inline void nft_use_inc_restore(u32 *use) +{ + WARN_ON_ONCE(!nft_use_inc(use)); +} + +#define nft_use_dec_restore nft_use_dec + /** * struct nft_table - nf_tables table * @@ -1275,8 +1298,8 @@ struct nft_object { struct list_head list; struct rhlist_head rhlhead; struct nft_object_hash_key key; - u32 genmask:2, - use:30; + u32 genmask:2; + u32 use; u64 handle; u16 udlen; u8 *udata; @@ -1378,8 +1401,8 @@ struct nft_flowtable { char *name; int hooknum; int ops_len; - u32 genmask:2, - use:30; + u32 genmask:2; + u32 use; u64 handle; /* runtime data below here */ struct list_head hook_list ____cacheline_aligned; diff --git a/include/net/route.h b/include/net/route.h index fe00b0a2e475..af8431b25f80 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -171,7 +171,7 @@ static inline struct rtable *ip_route_output_ports(struct net *net, struct flowi __be16 dport, __be16 sport, __u8 proto, __u8 tos, int oif) { - flowi4_init_output(fl4, oif, sk ? sk->sk_mark : 0, tos, + flowi4_init_output(fl4, oif, sk ? READ_ONCE(sk->sk_mark) : 0, tos, RT_SCOPE_UNIVERSE, proto, sk ? inet_sk_flowi_flags(sk) : 0, daddr, saddr, dport, sport, sock_net_uid(net, sk)); @@ -304,7 +304,7 @@ static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst, if (inet_sk(sk)->transparent) flow_flags |= FLOWI_FLAG_ANYSRC; - flowi4_init_output(fl4, oif, sk->sk_mark, ip_sock_rt_tos(sk), + flowi4_init_output(fl4, oif, READ_ONCE(sk->sk_mark), ip_sock_rt_tos(sk), ip_sock_rt_scope(sk), protocol, flow_flags, dst, src, dport, sport, sk->sk_uid); } diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index bf8bb3357825..9f881b74f32e 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -189,8 +189,8 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname, int rtnl_delete_link(struct net_device *dev); int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm); -int rtnl_nla_parse_ifla(struct nlattr **tb, const struct nlattr *head, int len, - struct netlink_ext_ack *exterr); +int rtnl_nla_parse_ifinfomsg(struct nlattr **tb, const struct nlattr *nla_peer, + struct netlink_ext_ack *exterr); struct net *rtnl_get_net_ns_capable(struct sock *sk, int netnsid); #define MODULE_ALIAS_RTNL_LINK(kind) MODULE_ALIAS("rtnl-link-" kind) diff --git a/include/net/sock.h b/include/net/sock.h index 1bbdddcf6154..d1f936ed9755 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1320,6 +1320,7 @@ struct proto { /* * Pressure flag: try to collapse. * Technical note: it is used by multiple contexts non atomically. + * Make sure to use READ_ONCE()/WRITE_ONCE() for all reads/writes. * All the __sk_mem_schedule() is of this nature: accounting * is strict, actions are advisory and have some latency. */ @@ -1445,6 +1446,12 @@ static inline bool sk_has_memory_pressure(const struct sock *sk) return sk->sk_prot->memory_pressure != NULL; } +static inline bool sk_under_global_memory_pressure(const struct sock *sk) +{ + return sk->sk_prot->memory_pressure && + !!READ_ONCE(*sk->sk_prot->memory_pressure); +} + static inline bool sk_under_memory_pressure(const struct sock *sk) { if (!sk->sk_prot->memory_pressure) @@ -1454,7 +1461,7 @@ static inline bool sk_under_memory_pressure(const struct sock *sk) mem_cgroup_under_socket_pressure(sk->sk_memcg)) return true; - return !!*sk->sk_prot->memory_pressure; + return !!READ_ONCE(*sk->sk_prot->memory_pressure); } static inline long @@ -1531,7 +1538,7 @@ proto_memory_pressure(struct proto *prot) { if (!prot->memory_pressure) return false; - return !!*prot->memory_pressure; + return !!READ_ONCE(*prot->memory_pressure); } diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 03bcc1ef0d61..a46ec889acb7 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -548,12 +548,12 @@ static inline void vxlan_flag_attr_error(int attrtype, } static inline bool vxlan_fdb_nh_path_select(struct nexthop *nh, - int hash, + u32 hash, struct vxlan_rdst *rdst) { struct fib_nh_common *nhc; - nhc = nexthop_path_fdb_result(nh, hash); + nhc = nexthop_path_fdb_result(nh, hash >> 1); if (unlikely(!nhc)) return false; diff --git a/include/trace/events/jbd2.h b/include/trace/events/jbd2.h index 8f5ee380d309..5646ae15a957 100644 --- a/include/trace/events/jbd2.h +++ b/include/trace/events/jbd2.h @@ -462,11 +462,9 @@ TRACE_EVENT(jbd2_shrink_scan_exit, TRACE_EVENT(jbd2_shrink_checkpoint_list, TP_PROTO(journal_t *journal, tid_t first_tid, tid_t tid, tid_t last_tid, - unsigned long nr_freed, unsigned long nr_scanned, - tid_t next_tid), + unsigned long nr_freed, tid_t next_tid), - TP_ARGS(journal, first_tid, tid, last_tid, nr_freed, - nr_scanned, next_tid), + TP_ARGS(journal, first_tid, tid, last_tid, nr_freed, next_tid), TP_STRUCT__entry( __field(dev_t, dev) @@ -474,7 +472,6 @@ TRACE_EVENT(jbd2_shrink_checkpoint_list, __field(tid_t, tid) __field(tid_t, last_tid) __field(unsigned long, nr_freed) - __field(unsigned long, nr_scanned) __field(tid_t, next_tid) ), @@ -484,15 +481,14 @@ TRACE_EVENT(jbd2_shrink_checkpoint_list, __entry->tid = tid; __entry->last_tid = last_tid; __entry->nr_freed = nr_freed; - __entry->nr_scanned = nr_scanned; __entry->next_tid = next_tid; ), TP_printk("dev %d,%d shrink transaction %u-%u(%u) freed %lu " - "scanned %lu next transaction %u", + "next transaction %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->first_tid, __entry->tid, __entry->last_tid, - __entry->nr_freed, __entry->nr_scanned, __entry->next_tid) + __entry->nr_freed, __entry->next_tid) ); #endif /* _TRACE_JBD2_H */ diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h index 901b440238d5..0a14c474c6f9 100644 --- a/include/trace/events/tcp.h +++ b/include/trace/events/tcp.h @@ -381,6 +381,7 @@ TRACE_EVENT(tcp_cong_state_set, __field(const void *, skaddr) __field(__u16, sport) __field(__u16, dport) + __field(__u16, family) __array(__u8, saddr, 4) __array(__u8, daddr, 4) __array(__u8, saddr_v6, 16) @@ -396,6 +397,7 @@ TRACE_EVENT(tcp_cong_state_set, __entry->sport = ntohs(inet->inet_sport); __entry->dport = ntohs(inet->inet_dport); + __entry->family = sk->sk_family; p32 = (__be32 *) __entry->saddr; *p32 = inet->inet_saddr; @@ -409,7 +411,8 @@ TRACE_EVENT(tcp_cong_state_set, __entry->cong_state = ca_state; ), - TP_printk("sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c cong_state=%u", + TP_printk("family=%s sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c cong_state=%u", + show_family_name(__entry->family), __entry->sport, __entry->dport, __entry->saddr, __entry->daddr, __entry->saddr_v6, __entry->daddr_v6, diff --git a/init/main.c b/init/main.c index aa21add5f7c5..fe378351e8a9 100644 --- a/init/main.c +++ b/init/main.c @@ -96,7 +96,6 @@ #include <linux/cache.h> #include <linux/rodata_test.h> #include <linux/jump_label.h> -#include <linux/mem_encrypt.h> #include <linux/kcsan.h> #include <linux/init_syscalls.h> #include <linux/stackdepot.h> @@ -104,7 +103,6 @@ #include <net/net_namespace.h> #include <asm/io.h> -#include <asm/bugs.h> #include <asm/setup.h> #include <asm/sections.h> #include <asm/cacheflush.h> @@ -781,8 +779,6 @@ void __init __weak thread_stack_cache_init(void) } #endif -void __init __weak mem_encrypt_init(void) { } - void __init __weak poking_init(void) { } void __init __weak pgtable_cache_init(void) { } @@ -860,6 +856,7 @@ static void __init mm_init(void) /* Should be run after espfix64 is set up. */ pti_init(); kmsan_init_runtime(); + mm_cache_init(); } #ifdef CONFIG_RANDOMIZE_KSTACK_OFFSET @@ -995,7 +992,7 @@ asmlinkage __visible void __init __no_sanitize_address start_kernel(void) sort_main_extable(); trap_init(); mm_init(); - + poking_init(); ftrace_init(); /* trace_printk can be enabled here */ @@ -1084,14 +1081,6 @@ asmlinkage __visible void __init __no_sanitize_address start_kernel(void) */ locking_selftest(); - /* - * This needs to be called before any devices perform DMA - * operations that might use the SWIOTLB bounce buffers. It will - * mark the bounce buffers as decrypted so that their usage will - * not cause "plain-text" data to be decrypted when accessed. - */ - mem_encrypt_init(); - #ifdef CONFIG_BLK_DEV_INITRD if (initrd_start && !initrd_below_start_ok && page_to_pfn(virt_to_page((void *)initrd_start)) < min_low_pfn) { @@ -1108,6 +1097,9 @@ asmlinkage __visible void __init __no_sanitize_address start_kernel(void) late_time_init(); sched_clock_init(); calibrate_delay(); + + arch_cpu_finalize_init(); + pid_idr_init(); anon_vma_init(); #ifdef CONFIG_X86 @@ -1134,9 +1126,6 @@ asmlinkage __visible void __init __no_sanitize_address start_kernel(void) taskstats_init_early(); delayacct_init(); - poking_init(); - check_bugs(); - acpi_subsystem_init(); arch_post_acpi_subsys_init(); kcsan_init(); diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index f091153bc854..b0e47fe1eb4b 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -72,6 +72,7 @@ #include <linux/io_uring.h> #include <linux/audit.h> #include <linux/security.h> +#include <asm/shmparam.h> #define CREATE_TRACE_POINTS #include <trace/events/io_uring.h> @@ -2349,12 +2350,21 @@ int io_run_task_work_sig(struct io_ring_ctx *ctx) return 0; } +static bool current_pending_io(void) +{ + struct io_uring_task *tctx = current->io_uring; + + if (!tctx) + return false; + return percpu_counter_read_positive(&tctx->inflight); +} + /* when returns >0, the caller should retry */ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx, struct io_wait_queue *iowq, ktime_t *timeout) { - int token, ret; + int io_wait, ret; unsigned long check_cq; /* make sure we run task_work before checking for signals */ @@ -2372,15 +2382,17 @@ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx, } /* - * Use io_schedule_prepare/finish, so cpufreq can take into account - * that the task is waiting for IO - turns out to be important for low - * QD IO. + * Mark us as being in io_wait if we have pending requests, so cpufreq + * can take into account that the task is waiting for IO - turns out + * to be important for low QD IO. */ - token = io_schedule_prepare(); + io_wait = current->in_iowait; + if (current_pending_io()) + current->in_iowait = 1; ret = 1; if (!schedule_hrtimeout(timeout, HRTIMER_MODE_ABS)) ret = -ETIME; - io_schedule_finish(token); + current->in_iowait = io_wait; return ret; } @@ -3099,6 +3111,49 @@ static __cold int io_uring_mmap(struct file *file, struct vm_area_struct *vma) return remap_pfn_range(vma, vma->vm_start, pfn, sz, vma->vm_page_prot); } +static unsigned long io_uring_mmu_get_unmapped_area(struct file *filp, + unsigned long addr, unsigned long len, + unsigned long pgoff, unsigned long flags) +{ + void *ptr; + + /* + * Do not allow to map to user-provided address to avoid breaking the + * aliasing rules. Userspace is not able to guess the offset address of + * kernel kmalloc()ed memory area. + */ + if (addr) + return -EINVAL; + + ptr = io_uring_validate_mmap_request(filp, pgoff, len); + if (IS_ERR(ptr)) + return -ENOMEM; + + /* + * Some architectures have strong cache aliasing requirements. + * For such architectures we need a coherent mapping which aliases + * kernel memory *and* userspace memory. To achieve that: + * - use a NULL file pointer to reference physical memory, and + * - use the kernel virtual address of the shared io_uring context + * (instead of the userspace-provided address, which has to be 0UL + * anyway). + * - use the same pgoff which the get_unmapped_area() uses to + * calculate the page colouring. + * For architectures without such aliasing requirements, the + * architecture will return any suitable mapping because addr is 0. + */ + filp = NULL; + flags |= MAP_SHARED; + pgoff = 0; /* has been translated to ptr above */ +#ifdef SHM_COLOUR + addr = (uintptr_t) ptr; + pgoff = addr >> PAGE_SHIFT; +#else + addr = 0UL; +#endif + return current->mm->get_unmapped_area(filp, addr, len, pgoff, flags); +} + #else /* !CONFIG_MMU */ static int io_uring_mmap(struct file *file, struct vm_area_struct *vma) @@ -3313,6 +3368,8 @@ static const struct file_operations io_uring_fops = { #ifndef CONFIG_MMU .get_unmapped_area = io_uring_nommu_get_unmapped_area, .mmap_capabilities = io_uring_nommu_mmap_capabilities, +#else + .get_unmapped_area = io_uring_mmu_get_unmapped_area, #endif .poll = io_uring_poll, #ifdef CONFIG_PROC_FS diff --git a/io_uring/msg_ring.c b/io_uring/msg_ring.c index 3526389ac218..cd922d2bef5f 100644 --- a/io_uring/msg_ring.c +++ b/io_uring/msg_ring.c @@ -15,6 +15,7 @@ struct io_msg { struct file *file; + struct file *src_file; u64 user_data; u32 len; u32 cmd; @@ -23,33 +24,12 @@ struct io_msg { u32 flags; }; -static int io_msg_ring_data(struct io_kiocb *req) +static void io_double_unlock_ctx(struct io_ring_ctx *octx) { - struct io_ring_ctx *target_ctx = req->file->private_data; - struct io_msg *msg = io_kiocb_to_cmd(req, struct io_msg); - - if (msg->src_fd || msg->dst_fd || msg->flags) - return -EINVAL; - if (target_ctx->flags & IORING_SETUP_R_DISABLED) - return -EBADFD; - - if (io_post_aux_cqe(target_ctx, msg->user_data, msg->len, 0, true)) - return 0; - - return -EOVERFLOW; -} - -static void io_double_unlock_ctx(struct io_ring_ctx *ctx, - struct io_ring_ctx *octx, - unsigned int issue_flags) -{ - if (issue_flags & IO_URING_F_UNLOCKED) - mutex_unlock(&ctx->uring_lock); mutex_unlock(&octx->uring_lock); } -static int io_double_lock_ctx(struct io_ring_ctx *ctx, - struct io_ring_ctx *octx, +static int io_double_lock_ctx(struct io_ring_ctx *octx, unsigned int issue_flags) { /* @@ -62,60 +42,86 @@ static int io_double_lock_ctx(struct io_ring_ctx *ctx, return -EAGAIN; return 0; } + mutex_lock(&octx->uring_lock); + return 0; +} - /* Always grab smallest value ctx first. We know ctx != octx. */ - if (ctx < octx) { - mutex_lock(&ctx->uring_lock); - mutex_lock(&octx->uring_lock); - } else { - mutex_lock(&octx->uring_lock); - mutex_lock(&ctx->uring_lock); - } +void io_msg_ring_cleanup(struct io_kiocb *req) +{ + struct io_msg *msg = io_kiocb_to_cmd(req, struct io_msg); - return 0; + if (WARN_ON_ONCE(!msg->src_file)) + return; + + fput(msg->src_file); + msg->src_file = NULL; } -static int io_msg_send_fd(struct io_kiocb *req, unsigned int issue_flags) +static int io_msg_ring_data(struct io_kiocb *req, unsigned int issue_flags) { struct io_ring_ctx *target_ctx = req->file->private_data; struct io_msg *msg = io_kiocb_to_cmd(req, struct io_msg); - struct io_ring_ctx *ctx = req->ctx; - unsigned long file_ptr; - struct file *src_file; int ret; - if (msg->len) - return -EINVAL; - if (target_ctx == ctx) + if (msg->src_fd || msg->dst_fd || msg->flags) return -EINVAL; if (target_ctx->flags & IORING_SETUP_R_DISABLED) return -EBADFD; - ret = io_double_lock_ctx(ctx, target_ctx, issue_flags); - if (unlikely(ret)) - return ret; + ret = -EOVERFLOW; + if (target_ctx->flags & IORING_SETUP_IOPOLL) { + if (unlikely(io_double_lock_ctx(target_ctx, issue_flags))) + return -EAGAIN; + if (io_post_aux_cqe(target_ctx, msg->user_data, msg->len, 0, true)) + ret = 0; + io_double_unlock_ctx(target_ctx); + } else { + if (io_post_aux_cqe(target_ctx, msg->user_data, msg->len, 0, true)) + ret = 0; + } - ret = -EBADF; - if (unlikely(msg->src_fd >= ctx->nr_user_files)) - goto out_unlock; + return ret; +} - msg->src_fd = array_index_nospec(msg->src_fd, ctx->nr_user_files); - file_ptr = io_fixed_file_slot(&ctx->file_table, msg->src_fd)->file_ptr; - if (!file_ptr) - goto out_unlock; +static struct file *io_msg_grab_file(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_msg *msg = io_kiocb_to_cmd(req, struct io_msg); + struct io_ring_ctx *ctx = req->ctx; + struct file *file = NULL; + unsigned long file_ptr; + int idx = msg->src_fd; + + io_ring_submit_lock(ctx, issue_flags); + if (likely(idx < ctx->nr_user_files)) { + idx = array_index_nospec(idx, ctx->nr_user_files); + file_ptr = io_fixed_file_slot(&ctx->file_table, idx)->file_ptr; + file = (struct file *) (file_ptr & FFS_MASK); + if (file) + get_file(file); + } + io_ring_submit_unlock(ctx, issue_flags); + return file; +} - src_file = (struct file *) (file_ptr & FFS_MASK); - get_file(src_file); +static int io_msg_install_complete(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_ring_ctx *target_ctx = req->file->private_data; + struct io_msg *msg = io_kiocb_to_cmd(req, struct io_msg); + struct file *src_file = msg->src_file; + int ret; + + if (unlikely(io_double_lock_ctx(target_ctx, issue_flags))) + return -EAGAIN; ret = __io_fixed_fd_install(target_ctx, src_file, msg->dst_fd); - if (ret < 0) { - fput(src_file); + if (ret < 0) goto out_unlock; - } + + msg->src_file = NULL; + req->flags &= ~REQ_F_NEED_CLEANUP; if (msg->flags & IORING_MSG_RING_CQE_SKIP) goto out_unlock; - /* * If this fails, the target still received the file descriptor but * wasn't notified of the fact. This means that if this request @@ -125,10 +131,29 @@ static int io_msg_send_fd(struct io_kiocb *req, unsigned int issue_flags) if (!io_post_aux_cqe(target_ctx, msg->user_data, ret, 0, true)) ret = -EOVERFLOW; out_unlock: - io_double_unlock_ctx(ctx, target_ctx, issue_flags); + io_double_unlock_ctx(target_ctx); return ret; } +static int io_msg_send_fd(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_ring_ctx *target_ctx = req->file->private_data; + struct io_msg *msg = io_kiocb_to_cmd(req, struct io_msg); + struct io_ring_ctx *ctx = req->ctx; + struct file *src_file = msg->src_file; + + if (target_ctx == ctx) + return -EINVAL; + if (!src_file) { + src_file = io_msg_grab_file(req, issue_flags); + if (!src_file) + return -EBADF; + msg->src_file = src_file; + req->flags |= REQ_F_NEED_CLEANUP; + } + return io_msg_install_complete(req, issue_flags); +} + int io_msg_ring_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_msg *msg = io_kiocb_to_cmd(req, struct io_msg); @@ -136,6 +161,7 @@ int io_msg_ring_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (unlikely(sqe->buf_index || sqe->personality)) return -EINVAL; + msg->src_file = NULL; msg->user_data = READ_ONCE(sqe->off); msg->len = READ_ONCE(sqe->len); msg->cmd = READ_ONCE(sqe->addr); @@ -159,7 +185,7 @@ int io_msg_ring(struct io_kiocb *req, unsigned int issue_flags) switch (msg->cmd) { case IORING_MSG_DATA: - ret = io_msg_ring_data(req); + ret = io_msg_ring_data(req, issue_flags); break; case IORING_MSG_SEND_FD: ret = io_msg_send_fd(req, issue_flags); diff --git a/io_uring/msg_ring.h b/io_uring/msg_ring.h index fb9601f202d0..3987ee6c0e5f 100644 --- a/io_uring/msg_ring.h +++ b/io_uring/msg_ring.h @@ -2,3 +2,4 @@ int io_msg_ring_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); int io_msg_ring(struct io_kiocb *req, unsigned int issue_flags); +void io_msg_ring_cleanup(struct io_kiocb *req); diff --git a/io_uring/opdef.c b/io_uring/opdef.c index 04dd2c983fce..3aa0d65c50e3 100644 --- a/io_uring/opdef.c +++ b/io_uring/opdef.c @@ -445,6 +445,7 @@ const struct io_op_def io_op_defs[] = { .name = "MSG_RING", .prep = io_msg_ring_prep, .issue = io_msg_ring, + .cleanup = io_msg_ring_cleanup, }, [IORING_OP_FSETXATTR] = { .needs_file = 1, diff --git a/io_uring/openclose.c b/io_uring/openclose.c index 67178e4bb282..008990e58180 100644 --- a/io_uring/openclose.c +++ b/io_uring/openclose.c @@ -110,9 +110,11 @@ int io_openat2(struct io_kiocb *req, unsigned int issue_flags) if (issue_flags & IO_URING_F_NONBLOCK) { /* * Don't bother trying for O_TRUNC, O_CREAT, or O_TMPFILE open, - * it'll always -EAGAIN + * it'll always -EAGAIN. Note that we test for __O_TMPFILE + * because O_TMPFILE includes O_DIRECTORY, which isn't a flag + * we need to force async for. */ - if (open->how.flags & (O_TRUNC | O_CREAT | O_TMPFILE)) + if (open->how.flags & (O_TRUNC | O_CREAT | __O_TMPFILE)) return -EAGAIN; op.lookup_flags |= LOOKUP_CACHED; op.open_flag |= O_NONBLOCK; diff --git a/io_uring/timeout.c b/io_uring/timeout.c index 4c6a5666541c..b0cf05ebcbcc 100644 --- a/io_uring/timeout.c +++ b/io_uring/timeout.c @@ -545,7 +545,7 @@ int io_timeout(struct io_kiocb *req, unsigned int issue_flags) goto add; } - tail = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts); + tail = data_race(ctx->cached_cq_tail) - atomic_read(&ctx->cq_timeouts); timeout->target_seq = tail + off; /* Update the last seq here in case io_flush_timeouts() hasn't. diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index 09141351d545..08a8e8102728 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -26,6 +26,7 @@ #include <linux/workqueue.h> #include <linux/kthread.h> #include <linux/capability.h> +#include <linux/completion.h> #include <trace/events/xdp.h> #include <linux/btf_ids.h> @@ -71,6 +72,7 @@ struct bpf_cpu_map_entry { struct rcu_head rcu; struct work_struct kthread_stop_wq; + struct completion kthread_running; }; struct bpf_cpu_map { @@ -134,11 +136,17 @@ static void __cpu_map_ring_cleanup(struct ptr_ring *ring) * invoked cpu_map_kthread_stop(). Catch any broken behaviour * gracefully and warn once. */ - struct xdp_frame *xdpf; + void *ptr; - while ((xdpf = ptr_ring_consume(ring))) - if (WARN_ON_ONCE(xdpf)) - xdp_return_frame(xdpf); + while ((ptr = ptr_ring_consume(ring))) { + WARN_ON_ONCE(1); + if (unlikely(__ptr_test_bit(0, &ptr))) { + __ptr_clear_bit(0, &ptr); + kfree_skb(ptr); + continue; + } + xdp_return_frame(ptr); + } } static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu) @@ -158,7 +166,6 @@ static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu) static void cpu_map_kthread_stop(struct work_struct *work) { struct bpf_cpu_map_entry *rcpu; - int err; rcpu = container_of(work, struct bpf_cpu_map_entry, kthread_stop_wq); @@ -168,14 +175,7 @@ static void cpu_map_kthread_stop(struct work_struct *work) rcu_barrier(); /* kthread_stop will wake_up_process and wait for it to complete */ - err = kthread_stop(rcpu->kthread); - if (err) { - /* kthread_stop may be called before cpu_map_kthread_run - * is executed, so we need to release the memory related - * to rcpu. - */ - put_cpu_map_entry(rcpu); - } + kthread_stop(rcpu->kthread); } static void cpu_map_bpf_prog_run_skb(struct bpf_cpu_map_entry *rcpu, @@ -303,11 +303,11 @@ static int cpu_map_bpf_prog_run(struct bpf_cpu_map_entry *rcpu, void **frames, return nframes; } - static int cpu_map_kthread_run(void *data) { struct bpf_cpu_map_entry *rcpu = data; + complete(&rcpu->kthread_running); set_current_state(TASK_INTERRUPTIBLE); /* When kthread gives stop order, then rcpu have been disconnected @@ -472,6 +472,7 @@ __cpu_map_entry_alloc(struct bpf_map *map, struct bpf_cpumap_val *value, goto free_ptr_ring; /* Setup kthread */ + init_completion(&rcpu->kthread_running); rcpu->kthread = kthread_create_on_node(cpu_map_kthread_run, rcpu, numa, "cpumap/%d/map:%d", cpu, map->id); @@ -485,6 +486,12 @@ __cpu_map_entry_alloc(struct bpf_map *map, struct bpf_cpumap_val *value, kthread_bind(rcpu->kthread, cpu); wake_up_process(rcpu->kthread); + /* Make sure kthread has been running, so kthread_stop() will not + * stop the kthread prematurely and all pending frames or skbs + * will be handled by the kthread before kthread_stop() returns. + */ + wait_for_completion(&rcpu->kthread_running); + return rcpu; free_prog: diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 73f11e4db3a4..97ecca43386d 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -57,6 +57,7 @@ #include <linux/file.h> #include <linux/fs_parser.h> #include <linux/sched/cputime.h> +#include <linux/sched/deadline.h> #include <linux/psi.h> #include <net/sock.h> @@ -6681,6 +6682,9 @@ void cgroup_exit(struct task_struct *tsk) list_add_tail(&tsk->cg_list, &cset->dying_tasks); cset->nr_tasks--; + if (dl_task(tsk)) + dec_dl_tasks_cs(tsk); + WARN_ON_ONCE(cgroup_task_frozen(tsk)); if (unlikely(!(tsk->flags & PF_KTHREAD) && test_bit(CGRP_FREEZE, &task_dfl_cgroup(tsk)->flags))) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index e276db722845..db3e05b6b4dd 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -193,6 +193,14 @@ struct cpuset { int use_parent_ecpus; int child_ecpus_count; + /* + * number of SCHED_DEADLINE tasks attached to this cpuset, so that we + * know when to rebuild associated root domain bandwidth information. + */ + int nr_deadline_tasks; + int nr_migrate_dl_tasks; + u64 sum_migrate_dl_bw; + /* Invalid partition error code, not lock protected */ enum prs_errcode prs_err; @@ -245,6 +253,20 @@ static inline struct cpuset *parent_cs(struct cpuset *cs) return css_cs(cs->css.parent); } +void inc_dl_tasks_cs(struct task_struct *p) +{ + struct cpuset *cs = task_cs(p); + + cs->nr_deadline_tasks++; +} + +void dec_dl_tasks_cs(struct task_struct *p) +{ + struct cpuset *cs = task_cs(p); + + cs->nr_deadline_tasks--; +} + /* bits in struct cpuset flags field */ typedef enum { CS_ONLINE, @@ -366,22 +388,23 @@ static struct cpuset top_cpuset = { if (is_cpuset_online(((des_cs) = css_cs((pos_css))))) /* - * There are two global locks guarding cpuset structures - cpuset_rwsem and + * There are two global locks guarding cpuset structures - cpuset_mutex and * callback_lock. We also require taking task_lock() when dereferencing a * task's cpuset pointer. See "The task_lock() exception", at the end of this - * comment. The cpuset code uses only cpuset_rwsem write lock. Other - * kernel subsystems can use cpuset_read_lock()/cpuset_read_unlock() to - * prevent change to cpuset structures. + * comment. The cpuset code uses only cpuset_mutex. Other kernel subsystems + * can use cpuset_lock()/cpuset_unlock() to prevent change to cpuset + * structures. Note that cpuset_mutex needs to be a mutex as it is used in + * paths that rely on priority inheritance (e.g. scheduler - on RT) for + * correctness. * * A task must hold both locks to modify cpusets. If a task holds - * cpuset_rwsem, it blocks others wanting that rwsem, ensuring that it - * is the only task able to also acquire callback_lock and be able to - * modify cpusets. It can perform various checks on the cpuset structure - * first, knowing nothing will change. It can also allocate memory while - * just holding cpuset_rwsem. While it is performing these checks, various - * callback routines can briefly acquire callback_lock to query cpusets. - * Once it is ready to make the changes, it takes callback_lock, blocking - * everyone else. + * cpuset_mutex, it blocks others, ensuring that it is the only task able to + * also acquire callback_lock and be able to modify cpusets. It can perform + * various checks on the cpuset structure first, knowing nothing will change. + * It can also allocate memory while just holding cpuset_mutex. While it is + * performing these checks, various callback routines can briefly acquire + * callback_lock to query cpusets. Once it is ready to make the changes, it + * takes callback_lock, blocking everyone else. * * Calls to the kernel memory allocator can not be made while holding * callback_lock, as that would risk double tripping on callback_lock @@ -403,16 +426,16 @@ static struct cpuset top_cpuset = { * guidelines for accessing subsystem state in kernel/cgroup.c */ -DEFINE_STATIC_PERCPU_RWSEM(cpuset_rwsem); +static DEFINE_MUTEX(cpuset_mutex); -void cpuset_read_lock(void) +void cpuset_lock(void) { - percpu_down_read(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); } -void cpuset_read_unlock(void) +void cpuset_unlock(void) { - percpu_up_read(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); } static DEFINE_SPINLOCK(callback_lock); @@ -496,7 +519,7 @@ static inline bool partition_is_populated(struct cpuset *cs, * One way or another, we guarantee to return some non-empty subset * of cpu_online_mask. * - * Call with callback_lock or cpuset_rwsem held. + * Call with callback_lock or cpuset_mutex held. */ static void guarantee_online_cpus(struct task_struct *tsk, struct cpumask *pmask) @@ -538,7 +561,7 @@ out_unlock: * One way or another, we guarantee to return some non-empty subset * of node_states[N_MEMORY]. * - * Call with callback_lock or cpuset_rwsem held. + * Call with callback_lock or cpuset_mutex held. */ static void guarantee_online_mems(struct cpuset *cs, nodemask_t *pmask) { @@ -550,7 +573,7 @@ static void guarantee_online_mems(struct cpuset *cs, nodemask_t *pmask) /* * update task's spread flag if cpuset's page/slab spread flag is set * - * Call with callback_lock or cpuset_rwsem held. The check can be skipped + * Call with callback_lock or cpuset_mutex held. The check can be skipped * if on default hierarchy. */ static void cpuset_update_task_spread_flags(struct cpuset *cs, @@ -575,7 +598,7 @@ static void cpuset_update_task_spread_flags(struct cpuset *cs, * * One cpuset is a subset of another if all its allowed CPUs and * Memory Nodes are a subset of the other, and its exclusive flags - * are only set if the other's are set. Call holding cpuset_rwsem. + * are only set if the other's are set. Call holding cpuset_mutex. */ static int is_cpuset_subset(const struct cpuset *p, const struct cpuset *q) @@ -713,7 +736,7 @@ out: * If we replaced the flag and mask values of the current cpuset * (cur) with those values in the trial cpuset (trial), would * our various subset and exclusive rules still be valid? Presumes - * cpuset_rwsem held. + * cpuset_mutex held. * * 'cur' is the address of an actual, in-use cpuset. Operations * such as list traversal that depend on the actual address of the @@ -829,7 +852,7 @@ static void update_domain_attr_tree(struct sched_domain_attr *dattr, rcu_read_unlock(); } -/* Must be called with cpuset_rwsem held. */ +/* Must be called with cpuset_mutex held. */ static inline int nr_cpusets(void) { /* jump label reference count + the top-level cpuset */ @@ -855,7 +878,7 @@ static inline int nr_cpusets(void) * domains when operating in the severe memory shortage situations * that could cause allocation failures below. * - * Must be called with cpuset_rwsem held. + * Must be called with cpuset_mutex held. * * The three key local variables below are: * cp - cpuset pointer, used (together with pos_css) to perform a @@ -1066,11 +1089,14 @@ done: return ndoms; } -static void update_tasks_root_domain(struct cpuset *cs) +static void dl_update_tasks_root_domain(struct cpuset *cs) { struct css_task_iter it; struct task_struct *task; + if (cs->nr_deadline_tasks == 0) + return; + css_task_iter_start(&cs->css, 0, &it); while ((task = css_task_iter_next(&it))) @@ -1079,12 +1105,12 @@ static void update_tasks_root_domain(struct cpuset *cs) css_task_iter_end(&it); } -static void rebuild_root_domains(void) +static void dl_rebuild_rd_accounting(void) { struct cpuset *cs = NULL; struct cgroup_subsys_state *pos_css; - percpu_rwsem_assert_held(&cpuset_rwsem); + lockdep_assert_held(&cpuset_mutex); lockdep_assert_cpus_held(); lockdep_assert_held(&sched_domains_mutex); @@ -1107,7 +1133,7 @@ static void rebuild_root_domains(void) rcu_read_unlock(); - update_tasks_root_domain(cs); + dl_update_tasks_root_domain(cs); rcu_read_lock(); css_put(&cs->css); @@ -1121,7 +1147,7 @@ partition_and_rebuild_sched_domains(int ndoms_new, cpumask_var_t doms_new[], { mutex_lock(&sched_domains_mutex); partition_sched_domains_locked(ndoms_new, doms_new, dattr_new); - rebuild_root_domains(); + dl_rebuild_rd_accounting(); mutex_unlock(&sched_domains_mutex); } @@ -1134,7 +1160,7 @@ partition_and_rebuild_sched_domains(int ndoms_new, cpumask_var_t doms_new[], * 'cpus' is removed, then call this routine to rebuild the * scheduler's dynamic sched domains. * - * Call with cpuset_rwsem held. Takes cpus_read_lock(). + * Call with cpuset_mutex held. Takes cpus_read_lock(). */ static void rebuild_sched_domains_locked(void) { @@ -1145,7 +1171,7 @@ static void rebuild_sched_domains_locked(void) int ndoms; lockdep_assert_cpus_held(); - percpu_rwsem_assert_held(&cpuset_rwsem); + lockdep_assert_held(&cpuset_mutex); /* * If we have raced with CPU hotplug, return early to avoid @@ -1196,9 +1222,9 @@ static void rebuild_sched_domains_locked(void) void rebuild_sched_domains(void) { cpus_read_lock(); - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); rebuild_sched_domains_locked(); - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); cpus_read_unlock(); } @@ -1208,7 +1234,7 @@ void rebuild_sched_domains(void) * @new_cpus: the temp variable for the new effective_cpus mask * * Iterate through each task of @cs updating its cpus_allowed to the - * effective cpuset's. As this function is called with cpuset_rwsem held, + * effective cpuset's. As this function is called with cpuset_mutex held, * cpuset membership stays stable. */ static void update_tasks_cpumask(struct cpuset *cs, struct cpumask *new_cpus) @@ -1317,7 +1343,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd, int old_prs, new_prs; int part_error = PERR_NONE; /* Partition error? */ - percpu_rwsem_assert_held(&cpuset_rwsem); + lockdep_assert_held(&cpuset_mutex); /* * The parent must be a partition root. @@ -1540,7 +1566,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd, * * On legacy hierarchy, effective_cpus will be the same with cpu_allowed. * - * Called with cpuset_rwsem held + * Called with cpuset_mutex held */ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp, bool force) @@ -1700,7 +1726,7 @@ static void update_sibling_cpumasks(struct cpuset *parent, struct cpuset *cs, struct cpuset *sibling; struct cgroup_subsys_state *pos_css; - percpu_rwsem_assert_held(&cpuset_rwsem); + lockdep_assert_held(&cpuset_mutex); /* * Check all its siblings and call update_cpumasks_hier() @@ -1950,12 +1976,12 @@ static void *cpuset_being_rebound; * @cs: the cpuset in which each task's mems_allowed mask needs to be changed * * Iterate through each task of @cs updating its mems_allowed to the - * effective cpuset's. As this function is called with cpuset_rwsem held, + * effective cpuset's. As this function is called with cpuset_mutex held, * cpuset membership stays stable. */ static void update_tasks_nodemask(struct cpuset *cs) { - static nodemask_t newmems; /* protected by cpuset_rwsem */ + static nodemask_t newmems; /* protected by cpuset_mutex */ struct css_task_iter it; struct task_struct *task; @@ -1968,7 +1994,7 @@ static void update_tasks_nodemask(struct cpuset *cs) * take while holding tasklist_lock. Forks can happen - the * mpol_dup() cpuset_being_rebound check will catch such forks, * and rebind their vma mempolicies too. Because we still hold - * the global cpuset_rwsem, we know that no other rebind effort + * the global cpuset_mutex, we know that no other rebind effort * will be contending for the global variable cpuset_being_rebound. * It's ok if we rebind the same mm twice; mpol_rebind_mm() * is idempotent. Also migrate pages in each mm to new nodes. @@ -2014,7 +2040,7 @@ static void update_tasks_nodemask(struct cpuset *cs) * * On legacy hierarchy, effective_mems will be the same with mems_allowed. * - * Called with cpuset_rwsem held + * Called with cpuset_mutex held */ static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems) { @@ -2067,7 +2093,7 @@ static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems) * mempolicies and if the cpuset is marked 'memory_migrate', * migrate the tasks pages to the new memory. * - * Call with cpuset_rwsem held. May take callback_lock during call. + * Call with cpuset_mutex held. May take callback_lock during call. * Will take tasklist_lock, scan tasklist for tasks in cpuset cs, * lock each such tasks mm->mmap_lock, scan its vma's and rebind * their mempolicies to the cpusets new mems_allowed. @@ -2159,7 +2185,7 @@ static int update_relax_domain_level(struct cpuset *cs, s64 val) * @cs: the cpuset in which each task's spread flags needs to be changed * * Iterate through each task of @cs updating its spread flags. As this - * function is called with cpuset_rwsem held, cpuset membership stays + * function is called with cpuset_mutex held, cpuset membership stays * stable. */ static void update_tasks_flags(struct cpuset *cs) @@ -2179,7 +2205,7 @@ static void update_tasks_flags(struct cpuset *cs) * cs: the cpuset to update * turning_on: whether the flag is being set or cleared * - * Call with cpuset_rwsem held. + * Call with cpuset_mutex held. */ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, @@ -2229,7 +2255,7 @@ out: * @new_prs: new partition root state * Return: 0 if successful, != 0 if error * - * Call with cpuset_rwsem held. + * Call with cpuset_mutex held. */ static int update_prstate(struct cpuset *cs, int new_prs) { @@ -2467,19 +2493,26 @@ static int cpuset_can_attach_check(struct cpuset *cs) return 0; } -/* Called by cgroups to determine if a cpuset is usable; cpuset_rwsem held */ +static void reset_migrate_dl_data(struct cpuset *cs) +{ + cs->nr_migrate_dl_tasks = 0; + cs->sum_migrate_dl_bw = 0; +} + +/* Called by cgroups to determine if a cpuset is usable; cpuset_mutex held */ static int cpuset_can_attach(struct cgroup_taskset *tset) { struct cgroup_subsys_state *css; - struct cpuset *cs; + struct cpuset *cs, *oldcs; struct task_struct *task; int ret; /* used later by cpuset_attach() */ cpuset_attach_old_cs = task_cs(cgroup_taskset_first(tset, &css)); + oldcs = cpuset_attach_old_cs; cs = css_cs(css); - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); /* Check to see if task is allowed in the cpuset */ ret = cpuset_can_attach_check(cs); @@ -2487,21 +2520,46 @@ static int cpuset_can_attach(struct cgroup_taskset *tset) goto out_unlock; cgroup_taskset_for_each(task, css, tset) { - ret = task_can_attach(task, cs->effective_cpus); + ret = task_can_attach(task); if (ret) goto out_unlock; ret = security_task_setscheduler(task); if (ret) goto out_unlock; + + if (dl_task(task)) { + cs->nr_migrate_dl_tasks++; + cs->sum_migrate_dl_bw += task->dl.dl_bw; + } } + if (!cs->nr_migrate_dl_tasks) + goto out_success; + + if (!cpumask_intersects(oldcs->effective_cpus, cs->effective_cpus)) { + int cpu = cpumask_any_and(cpu_active_mask, cs->effective_cpus); + + if (unlikely(cpu >= nr_cpu_ids)) { + reset_migrate_dl_data(cs); + ret = -EINVAL; + goto out_unlock; + } + + ret = dl_bw_alloc(cpu, cs->sum_migrate_dl_bw); + if (ret) { + reset_migrate_dl_data(cs); + goto out_unlock; + } + } + +out_success: /* * Mark attach is in progress. This makes validate_change() fail * changes which zero cpus/mems_allowed. */ cs->attach_in_progress++; out_unlock: - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); return ret; } @@ -2513,15 +2571,23 @@ static void cpuset_cancel_attach(struct cgroup_taskset *tset) cgroup_taskset_first(tset, &css); cs = css_cs(css); - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); cs->attach_in_progress--; if (!cs->attach_in_progress) wake_up(&cpuset_attach_wq); - percpu_up_write(&cpuset_rwsem); + + if (cs->nr_migrate_dl_tasks) { + int cpu = cpumask_any(cs->effective_cpus); + + dl_bw_free(cpu, cs->sum_migrate_dl_bw); + reset_migrate_dl_data(cs); + } + + mutex_unlock(&cpuset_mutex); } /* - * Protected by cpuset_rwsem. cpus_attach is used only by cpuset_attach_task() + * Protected by cpuset_mutex. cpus_attach is used only by cpuset_attach_task() * but we can't allocate it dynamically there. Define it global and * allocate from cpuset_init(). */ @@ -2530,7 +2596,7 @@ static nodemask_t cpuset_attach_nodemask_to; static void cpuset_attach_task(struct cpuset *cs, struct task_struct *task) { - percpu_rwsem_assert_held(&cpuset_rwsem); + lockdep_assert_held(&cpuset_mutex); if (cs != &top_cpuset) guarantee_online_cpus(task, cpus_attach); @@ -2558,7 +2624,7 @@ static void cpuset_attach(struct cgroup_taskset *tset) cs = css_cs(css); lockdep_assert_cpus_held(); /* see cgroup_attach_lock() */ - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); guarantee_online_mems(cs, &cpuset_attach_nodemask_to); @@ -2594,11 +2660,17 @@ static void cpuset_attach(struct cgroup_taskset *tset) cs->old_mems_allowed = cpuset_attach_nodemask_to; + if (cs->nr_migrate_dl_tasks) { + cs->nr_deadline_tasks += cs->nr_migrate_dl_tasks; + oldcs->nr_deadline_tasks -= cs->nr_migrate_dl_tasks; + reset_migrate_dl_data(cs); + } + cs->attach_in_progress--; if (!cs->attach_in_progress) wake_up(&cpuset_attach_wq); - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); } /* The various types of files and directories in a cpuset file system */ @@ -2630,7 +2702,7 @@ static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft, int retval = 0; cpus_read_lock(); - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); if (!is_cpuset_online(cs)) { retval = -ENODEV; goto out_unlock; @@ -2666,7 +2738,7 @@ static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft, break; } out_unlock: - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); cpus_read_unlock(); return retval; } @@ -2679,7 +2751,7 @@ static int cpuset_write_s64(struct cgroup_subsys_state *css, struct cftype *cft, int retval = -ENODEV; cpus_read_lock(); - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); if (!is_cpuset_online(cs)) goto out_unlock; @@ -2692,7 +2764,7 @@ static int cpuset_write_s64(struct cgroup_subsys_state *css, struct cftype *cft, break; } out_unlock: - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); cpus_read_unlock(); return retval; } @@ -2725,7 +2797,7 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of, * operation like this one can lead to a deadlock through kernfs * active_ref protection. Let's break the protection. Losing the * protection is okay as we check whether @cs is online after - * grabbing cpuset_rwsem anyway. This only happens on the legacy + * grabbing cpuset_mutex anyway. This only happens on the legacy * hierarchies. */ css_get(&cs->css); @@ -2733,7 +2805,7 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of, flush_work(&cpuset_hotplug_work); cpus_read_lock(); - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); if (!is_cpuset_online(cs)) goto out_unlock; @@ -2757,7 +2829,7 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of, free_cpuset(trialcs); out_unlock: - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); cpus_read_unlock(); kernfs_unbreak_active_protection(of->kn); css_put(&cs->css); @@ -2905,13 +2977,13 @@ static ssize_t sched_partition_write(struct kernfs_open_file *of, char *buf, css_get(&cs->css); cpus_read_lock(); - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); if (!is_cpuset_online(cs)) goto out_unlock; retval = update_prstate(cs, val); out_unlock: - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); cpus_read_unlock(); css_put(&cs->css); return retval ?: nbytes; @@ -3124,7 +3196,7 @@ static int cpuset_css_online(struct cgroup_subsys_state *css) return 0; cpus_read_lock(); - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); set_bit(CS_ONLINE, &cs->flags); if (is_spread_page(parent)) @@ -3175,7 +3247,7 @@ static int cpuset_css_online(struct cgroup_subsys_state *css) cpumask_copy(cs->effective_cpus, parent->cpus_allowed); spin_unlock_irq(&callback_lock); out_unlock: - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); cpus_read_unlock(); return 0; } @@ -3196,7 +3268,7 @@ static void cpuset_css_offline(struct cgroup_subsys_state *css) struct cpuset *cs = css_cs(css); cpus_read_lock(); - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); if (is_partition_valid(cs)) update_prstate(cs, 0); @@ -3215,7 +3287,7 @@ static void cpuset_css_offline(struct cgroup_subsys_state *css) cpuset_dec(); clear_bit(CS_ONLINE, &cs->flags); - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); cpus_read_unlock(); } @@ -3228,7 +3300,7 @@ static void cpuset_css_free(struct cgroup_subsys_state *css) static void cpuset_bind(struct cgroup_subsys_state *root_css) { - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); spin_lock_irq(&callback_lock); if (is_in_v2_mode()) { @@ -3241,7 +3313,7 @@ static void cpuset_bind(struct cgroup_subsys_state *root_css) } spin_unlock_irq(&callback_lock); - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); } /* @@ -3262,14 +3334,14 @@ static int cpuset_can_fork(struct task_struct *task, struct css_set *cset) return 0; lockdep_assert_held(&cgroup_mutex); - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); /* Check to see if task is allowed in the cpuset */ ret = cpuset_can_attach_check(cs); if (ret) goto out_unlock; - ret = task_can_attach(task, cs->effective_cpus); + ret = task_can_attach(task); if (ret) goto out_unlock; @@ -3283,7 +3355,7 @@ static int cpuset_can_fork(struct task_struct *task, struct css_set *cset) */ cs->attach_in_progress++; out_unlock: - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); return ret; } @@ -3299,11 +3371,11 @@ static void cpuset_cancel_fork(struct task_struct *task, struct css_set *cset) if (same_cs) return; - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); cs->attach_in_progress--; if (!cs->attach_in_progress) wake_up(&cpuset_attach_wq); - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); } /* @@ -3331,7 +3403,7 @@ static void cpuset_fork(struct task_struct *task) } /* CLONE_INTO_CGROUP */ - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); guarantee_online_mems(cs, &cpuset_attach_nodemask_to); cpuset_attach_task(cs, task); @@ -3339,7 +3411,7 @@ static void cpuset_fork(struct task_struct *task) if (!cs->attach_in_progress) wake_up(&cpuset_attach_wq); - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); } struct cgroup_subsys cpuset_cgrp_subsys = { @@ -3369,8 +3441,6 @@ struct cgroup_subsys cpuset_cgrp_subsys = { int __init cpuset_init(void) { - BUG_ON(percpu_init_rwsem(&cpuset_rwsem)); - BUG_ON(!alloc_cpumask_var(&top_cpuset.cpus_allowed, GFP_KERNEL)); BUG_ON(!alloc_cpumask_var(&top_cpuset.effective_cpus, GFP_KERNEL)); BUG_ON(!zalloc_cpumask_var(&top_cpuset.subparts_cpus, GFP_KERNEL)); @@ -3442,7 +3512,7 @@ hotplug_update_tasks_legacy(struct cpuset *cs, is_empty = cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed); - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); /* * Move tasks to the nearest ancestor with execution resources, @@ -3452,7 +3522,7 @@ hotplug_update_tasks_legacy(struct cpuset *cs, if (is_empty) remove_tasks_in_empty_cpuset(cs); - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); } static void @@ -3503,14 +3573,14 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp) retry: wait_event(cpuset_attach_wq, cs->attach_in_progress == 0); - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); /* * We have raced with task attaching. We wait until attaching * is finished, so we won't attach a task to an empty cpuset. */ if (cs->attach_in_progress) { - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); goto retry; } @@ -3604,7 +3674,7 @@ update_tasks: hotplug_update_tasks_legacy(cs, &new_cpus, &new_mems, cpus_updated, mems_updated); - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); } /** @@ -3634,7 +3704,7 @@ static void cpuset_hotplug_workfn(struct work_struct *work) if (on_dfl && !alloc_cpumasks(NULL, &tmp)) ptmp = &tmp; - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); /* fetch the available cpus/mems and find out which changed how */ cpumask_copy(&new_cpus, cpu_active_mask); @@ -3691,7 +3761,7 @@ static void cpuset_hotplug_workfn(struct work_struct *work) update_tasks_nodemask(&top_cpuset); } - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); /* if cpus or mems changed, we need to propagate to descendants */ if (cpus_updated || mems_updated) { @@ -4101,7 +4171,7 @@ void __cpuset_memory_pressure_bump(void) * - Used for /proc/<pid>/cpuset. * - No need to task_lock(tsk) on this tsk->cpuset reference, as it * doesn't really matter if tsk->cpuset changes after we read it, - * and we take cpuset_rwsem, keeping cpuset_attach() from changing it + * and we take cpuset_mutex, keeping cpuset_attach() from changing it * anyway. */ int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns, diff --git a/kernel/dma/remap.c b/kernel/dma/remap.c index b4526668072e..27596f3b4aef 100644 --- a/kernel/dma/remap.c +++ b/kernel/dma/remap.c @@ -43,13 +43,13 @@ void *dma_common_contiguous_remap(struct page *page, size_t size, void *vaddr; int i; - pages = kmalloc_array(count, sizeof(struct page *), GFP_KERNEL); + pages = kvmalloc_array(count, sizeof(struct page *), GFP_KERNEL); if (!pages) return NULL; for (i = 0; i < count; i++) pages[i] = nth_page(page, i); vaddr = vmap(pages, count, VM_DMA_COHERENT, prot); - kfree(pages); + kvfree(pages); return vaddr; } diff --git a/kernel/events/core.c b/kernel/events/core.c index 934332b3eb54..db1065daabb6 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1133,6 +1133,11 @@ static int perf_mux_hrtimer_restart(struct perf_cpu_context *cpuctx) return 0; } +static int perf_mux_hrtimer_restart_ipi(void *arg) +{ + return perf_mux_hrtimer_restart(arg); +} + void perf_pmu_disable(struct pmu *pmu) { int *count = this_cpu_ptr(pmu->pmu_disable_count); @@ -11155,8 +11160,7 @@ perf_event_mux_interval_ms_store(struct device *dev, cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu); cpuctx->hrtimer_interval = ns_to_ktime(NSEC_PER_MSEC * timer); - cpu_function_call(cpu, - (remote_function_f)perf_mux_hrtimer_restart, cpuctx); + cpu_function_call(cpu, perf_mux_hrtimer_restart_ipi, cpuctx); } cpus_read_unlock(); mutex_unlock(&mux_interval_mutex); diff --git a/kernel/fork.c b/kernel/fork.c index 6bb91fbbf73c..41950ff90aa3 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2600,11 +2600,6 @@ struct task_struct * __init fork_idle(int cpu) return task; } -struct mm_struct *copy_init_mm(void) -{ - return dup_mm(NULL, &init_mm); -} - /* * This is like kernel_clone(), but shaved down and tailored to just * creating io_uring workers. It returns a created task, or an error pointer. @@ -3023,10 +3018,27 @@ static void sighand_ctor(void *data) init_waitqueue_head(&sighand->signalfd_wqh); } -void __init proc_caches_init(void) +void __init mm_cache_init(void) { unsigned int mm_size; + /* + * The mm_cpumask is located at the end of mm_struct, and is + * dynamically sized based on the maximum CPU number this system + * can have, taking hotplug into account (nr_cpu_ids). + */ + mm_size = sizeof(struct mm_struct) + cpumask_size(); + + mm_cachep = kmem_cache_create_usercopy("mm_struct", + mm_size, ARCH_MIN_MMSTRUCT_ALIGN, + SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, + offsetof(struct mm_struct, saved_auxv), + sizeof_field(struct mm_struct, saved_auxv), + NULL); +} + +void __init proc_caches_init(void) +{ sighand_cachep = kmem_cache_create("sighand_cache", sizeof(struct sighand_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_TYPESAFE_BY_RCU| @@ -3044,19 +3056,6 @@ void __init proc_caches_init(void) SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); - /* - * The mm_cpumask is located at the end of mm_struct, and is - * dynamically sized based on the maximum CPU number this system - * can have, taking hotplug into account (nr_cpu_ids). - */ - mm_size = sizeof(struct mm_struct) + cpumask_size(); - - mm_cachep = kmem_cache_create_usercopy("mm_struct", - mm_size, ARCH_MIN_MMSTRUCT_ALIGN, - SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, - offsetof(struct mm_struct, saved_auxv), - sizeof_field(struct mm_struct, saved_auxv), - NULL); vm_area_cachep = KMEM_CACHE(vm_area_struct, SLAB_PANIC|SLAB_ACCOUNT); mmap_init(); nsproxy_cache_init(); diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c index 676328a7c8c7..ad3cccb0970f 100644 --- a/kernel/kallsyms.c +++ b/kernel/kallsyms.c @@ -188,16 +188,13 @@ static bool cleanup_symbol_name(char *s) static int compare_symbol_name(const char *name, char *namebuf) { - int ret; - - ret = strcmp(name, namebuf); - if (!ret) - return ret; - - if (cleanup_symbol_name(namebuf) && !strcmp(name, namebuf)) - return 0; - - return ret; + /* The kallsyms_seqs_of_names is sorted based on names after + * cleanup_symbol_name() (see scripts/kallsyms.c) if clang lto is enabled. + * To ensure correct bisection in kallsyms_lookup_names(), do + * cleanup_symbol_name(namebuf) before comparing name and namebuf. + */ + cleanup_symbol_name(namebuf); + return strcmp(name, namebuf); } static int kallsyms_lookup_names(const char *name, diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 50d4863974e7..0224b0329d01 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -817,34 +817,26 @@ static int very_verbose(struct lock_class *class) * Is this the address of a static object: */ #ifdef __KERNEL__ -/* - * Check if an address is part of freed initmem. After initmem is freed, - * memory can be allocated from it, and such allocations would then have - * addresses within the range [_stext, _end]. - */ -#ifndef arch_is_kernel_initmem_freed -static int arch_is_kernel_initmem_freed(unsigned long addr) -{ - if (system_state < SYSTEM_FREEING_INITMEM) - return 0; - - return init_section_contains((void *)addr, 1); -} -#endif - static int static_obj(const void *obj) { - unsigned long start = (unsigned long) &_stext, - end = (unsigned long) &_end, - addr = (unsigned long) obj; + unsigned long addr = (unsigned long) obj; - if (arch_is_kernel_initmem_freed(addr)) - return 0; + if (is_kernel_core_data(addr)) + return 1; + + /* + * keys are allowed in the __ro_after_init section. + */ + if (is_kernel_rodata(addr)) + return 1; /* - * static variable? + * in initdata section and used during bootup only? + * NOTE: On some platforms the initdata section is + * outside of the _stext ... _end range. */ - if ((addr >= start) && (addr < end)) + if (system_state < SYSTEM_FREEING_INITMEM && + init_section_contains((void *)addr, 1)) return 1; /* diff --git a/kernel/module/main.c b/kernel/module/main.c index 7a627345d4fd..7a376e26de85 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -1214,12 +1214,20 @@ void *__symbol_get(const char *symbol) }; preempt_disable(); - if (!find_symbol(&fsa) || strong_try_module_get(fsa.owner)) { - preempt_enable(); - return NULL; + if (!find_symbol(&fsa)) + goto fail; + if (fsa.license != GPL_ONLY) { + pr_warn("failing symbol_get of non-GPLONLY symbol %s.\n", + symbol); + goto fail; } + if (strong_try_module_get(fsa.owner)) + goto fail; preempt_enable(); return (void *)kernel_symbol_value(fsa.sym); +fail: + preempt_enable(); + return NULL; } EXPORT_SYMBOL_GPL(__symbol_get); @@ -1401,7 +1409,7 @@ long module_get_offset(struct module *mod, unsigned int *size, return ret; } -static bool module_init_layout_section(const char *sname) +bool module_init_layout_section(const char *sname) { #ifndef CONFIG_MODULE_UNLOAD if (module_exit_section(sname)) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index b23dcbeacdf3..0f6a92737c91 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -7475,6 +7475,7 @@ static int __sched_setscheduler(struct task_struct *p, int reset_on_fork; int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK; struct rq *rq; + bool cpuset_locked = false; /* The pi code expects interrupts enabled */ BUG_ON(pi && in_interrupt()); @@ -7524,8 +7525,14 @@ recheck: return retval; } - if (pi) - cpuset_read_lock(); + /* + * SCHED_DEADLINE bandwidth accounting relies on stable cpusets + * information. + */ + if (dl_policy(policy) || dl_policy(p->policy)) { + cpuset_locked = true; + cpuset_lock(); + } /* * Make sure no PI-waiters arrive (or leave) while we are @@ -7601,8 +7608,8 @@ change: if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) { policy = oldpolicy = -1; task_rq_unlock(rq, p, &rf); - if (pi) - cpuset_read_unlock(); + if (cpuset_locked) + cpuset_unlock(); goto recheck; } @@ -7669,7 +7676,8 @@ change: task_rq_unlock(rq, p, &rf); if (pi) { - cpuset_read_unlock(); + if (cpuset_locked) + cpuset_unlock(); rt_mutex_adjust_pi(p); } @@ -7681,8 +7689,8 @@ change: unlock: task_rq_unlock(rq, p, &rf); - if (pi) - cpuset_read_unlock(); + if (cpuset_locked) + cpuset_unlock(); return retval; } @@ -9075,8 +9083,7 @@ int cpuset_cpumask_can_shrink(const struct cpumask *cur, return ret; } -int task_can_attach(struct task_struct *p, - const struct cpumask *cs_effective_cpus) +int task_can_attach(struct task_struct *p) { int ret = 0; @@ -9089,21 +9096,9 @@ int task_can_attach(struct task_struct *p, * success of set_cpus_allowed_ptr() on all attached tasks * before cpus_mask may be changed. */ - if (p->flags & PF_NO_SETAFFINITY) { + if (p->flags & PF_NO_SETAFFINITY) ret = -EINVAL; - goto out; - } - if (dl_task(p) && !cpumask_intersects(task_rq(p)->rd->span, - cs_effective_cpus)) { - int cpu = cpumask_any_and(cpu_active_mask, cs_effective_cpus); - - if (unlikely(cpu >= nr_cpu_ids)) - return -EINVAL; - ret = dl_cpu_busy(cpu, p); - } - -out: return ret; } @@ -9385,7 +9380,7 @@ static void cpuset_cpu_active(void) static int cpuset_cpu_inactive(unsigned int cpu) { if (!cpuhp_tasks_frozen) { - int ret = dl_cpu_busy(cpu, NULL); + int ret = dl_bw_check_overflow(cpu); if (ret) return ret; diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index f7d381b6c313..9ce9810861ba 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -16,6 +16,8 @@ * Fabio Checconi <fchecconi@gmail.com> */ +#include <linux/cpuset.h> + /* * Default limits for DL period; on the top end we guard against small util * tasks still getting ridiculously long effective runtimes, on the bottom end we @@ -2597,6 +2599,12 @@ static void switched_from_dl(struct rq *rq, struct task_struct *p) if (task_on_rq_queued(p) && p->dl.dl_runtime) task_non_contending(p); + /* + * In case a task is setscheduled out from SCHED_DEADLINE we need to + * keep track of that on its cpuset (for correct bandwidth tracking). + */ + dec_dl_tasks_cs(p); + if (!task_on_rq_queued(p)) { /* * Inactive timer is armed. However, p is leaving DEADLINE and @@ -2637,6 +2645,12 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p) if (hrtimer_try_to_cancel(&p->dl.inactive_timer) == 1) put_task_struct(p); + /* + * In case a task is setscheduled to SCHED_DEADLINE we need to keep + * track of that on its cpuset (for correct bandwidth tracking). + */ + inc_dl_tasks_cs(p); + /* If p is not queued we will update its parameters at next wakeup. */ if (!task_on_rq_queued(p)) { add_rq_bw(&p->dl, &rq->dl); @@ -3023,26 +3037,38 @@ int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur, return ret; } -int dl_cpu_busy(int cpu, struct task_struct *p) +enum dl_bw_request { + dl_bw_req_check_overflow = 0, + dl_bw_req_alloc, + dl_bw_req_free +}; + +static int dl_bw_manage(enum dl_bw_request req, int cpu, u64 dl_bw) { - unsigned long flags, cap; + unsigned long flags; struct dl_bw *dl_b; - bool overflow; + bool overflow = 0; rcu_read_lock_sched(); dl_b = dl_bw_of(cpu); raw_spin_lock_irqsave(&dl_b->lock, flags); - cap = dl_bw_capacity(cpu); - overflow = __dl_overflow(dl_b, cap, 0, p ? p->dl.dl_bw : 0); - if (!overflow && p) { - /* - * We reserve space for this task in the destination - * root_domain, as we can't fail after this point. - * We will free resources in the source root_domain - * later on (see set_cpus_allowed_dl()). - */ - __dl_add(dl_b, p->dl.dl_bw, dl_bw_cpus(cpu)); + if (req == dl_bw_req_free) { + __dl_sub(dl_b, dl_bw, dl_bw_cpus(cpu)); + } else { + unsigned long cap = dl_bw_capacity(cpu); + + overflow = __dl_overflow(dl_b, cap, 0, dl_bw); + + if (req == dl_bw_req_alloc && !overflow) { + /* + * We reserve space in the destination + * root_domain, as we can't fail after this point. + * We will free resources in the source root_domain + * later on (see set_cpus_allowed_dl()). + */ + __dl_add(dl_b, dl_bw, dl_bw_cpus(cpu)); + } } raw_spin_unlock_irqrestore(&dl_b->lock, flags); @@ -3050,6 +3076,21 @@ int dl_cpu_busy(int cpu, struct task_struct *p) return overflow ? -EBUSY : 0; } + +int dl_bw_check_overflow(int cpu) +{ + return dl_bw_manage(dl_bw_req_check_overflow, cpu, 0); +} + +int dl_bw_alloc(int cpu, u64 dl_bw) +{ + return dl_bw_manage(dl_bw_req_alloc, cpu, dl_bw); +} + +void dl_bw_free(int cpu, u64 dl_bw) +{ + dl_bw_manage(dl_bw_req_free, cpu, dl_bw); +} #endif #ifdef CONFIG_SCHED_DEBUG diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 5e5aea2360a8..612873ec2197 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -4464,17 +4464,9 @@ static inline int util_fits_cpu(unsigned long util, * * For uclamp_max, we can tolerate a drop in performance level as the * goal is to cap the task. So it's okay if it's getting less. - * - * In case of capacity inversion we should honour the inverted capacity - * for both uclamp_min and uclamp_max all the time. */ - capacity_orig = cpu_in_capacity_inversion(cpu); - if (capacity_orig) { - capacity_orig_thermal = capacity_orig; - } else { - capacity_orig = capacity_orig_of(cpu); - capacity_orig_thermal = capacity_orig - arch_scale_thermal_pressure(cpu); - } + capacity_orig = capacity_orig_of(cpu); + capacity_orig_thermal = capacity_orig - arch_scale_thermal_pressure(cpu); /* * We want to force a task to fit a cpu as implied by uclamp_max. @@ -4549,8 +4541,8 @@ static inline int util_fits_cpu(unsigned long util, * handle the case uclamp_min > uclamp_max. */ uclamp_min = min(uclamp_min, uclamp_max); - if (util < uclamp_min && capacity_orig != SCHED_CAPACITY_SCALE) - fits = fits && (uclamp_min <= capacity_orig_thermal); + if (fits && (util < uclamp_min) && (uclamp_min > capacity_orig_thermal)) + return -1; return fits; } @@ -4560,7 +4552,11 @@ static inline int task_fits_cpu(struct task_struct *p, int cpu) unsigned long uclamp_min = uclamp_eff_value(p, UCLAMP_MIN); unsigned long uclamp_max = uclamp_eff_value(p, UCLAMP_MAX); unsigned long util = task_util_est(p); - return util_fits_cpu(util, uclamp_min, uclamp_max, cpu); + /* + * Return true only if the cpu fully fits the task requirements, which + * include the utilization but also the performance hints. + */ + return (util_fits_cpu(util, uclamp_min, uclamp_max, cpu) > 0); } static inline void update_misfit_status(struct task_struct *p, struct rq *rq) @@ -6043,6 +6039,7 @@ static inline bool cpu_overutilized(int cpu) unsigned long rq_util_min = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MIN); unsigned long rq_util_max = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MAX); + /* Return true only if the utilization doesn't fit CPU's capacity */ return !util_fits_cpu(cpu_util_cfs(cpu), rq_util_min, rq_util_max, cpu); } @@ -6836,6 +6833,7 @@ static int select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target) { unsigned long task_util, util_min, util_max, best_cap = 0; + int fits, best_fits = 0; int cpu, best_cpu = -1; struct cpumask *cpus; @@ -6851,12 +6849,28 @@ select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target) if (!available_idle_cpu(cpu) && !sched_idle_cpu(cpu)) continue; - if (util_fits_cpu(task_util, util_min, util_max, cpu)) + + fits = util_fits_cpu(task_util, util_min, util_max, cpu); + + /* This CPU fits with all requirements */ + if (fits > 0) return cpu; + /* + * Only the min performance hint (i.e. uclamp_min) doesn't fit. + * Look for the CPU with best capacity. + */ + else if (fits < 0) + cpu_cap = capacity_orig_of(cpu) - thermal_load_avg(cpu_rq(cpu)); - if (cpu_cap > best_cap) { + /* + * First, select CPU which fits better (-1 being better than 0). + * Then, select the one with best capacity at same level. + */ + if ((fits < best_fits) || + ((fits == best_fits) && (cpu_cap > best_cap))) { best_cap = cpu_cap; best_cpu = cpu; + best_fits = fits; } } @@ -6869,7 +6883,11 @@ static inline bool asym_fits_cpu(unsigned long util, int cpu) { if (sched_asym_cpucap_active()) - return util_fits_cpu(util, util_min, util_max, cpu); + /* + * Return true only if the cpu fully fits the task requirements + * which include the utilization and the performance hints. + */ + return (util_fits_cpu(util, util_min, util_max, cpu) > 0); return true; } @@ -7236,6 +7254,9 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) unsigned long p_util_max = uclamp_is_used() ? uclamp_eff_value(p, UCLAMP_MAX) : 1024; struct root_domain *rd = this_rq()->rd; int cpu, best_energy_cpu, target = -1; + int prev_fits = -1, best_fits = -1; + unsigned long best_thermal_cap = 0; + unsigned long prev_thermal_cap = 0; struct sched_domain *sd; struct perf_domain *pd; struct energy_env eenv; @@ -7271,6 +7292,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) unsigned long prev_spare_cap = 0; int max_spare_cap_cpu = -1; unsigned long base_energy; + int fits, max_fits = -1; cpumask_and(cpus, perf_domain_span(pd), cpu_online_mask); @@ -7320,7 +7342,9 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) util_min = max(rq_util_min, p_util_min); util_max = max(rq_util_max, p_util_max); } - if (!util_fits_cpu(util, util_min, util_max, cpu)) + + fits = util_fits_cpu(util, util_min, util_max, cpu); + if (!fits) continue; lsub_positive(&cpu_cap, util); @@ -7328,7 +7352,9 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) if (cpu == prev_cpu) { /* Always use prev_cpu as a candidate. */ prev_spare_cap = cpu_cap; - } else if (cpu_cap > max_spare_cap) { + prev_fits = fits; + } else if ((fits > max_fits) || + ((fits == max_fits) && (cpu_cap > max_spare_cap))) { /* * Find the CPU with the maximum spare capacity * among the remaining CPUs in the performance @@ -7336,6 +7362,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) */ max_spare_cap = cpu_cap; max_spare_cap_cpu = cpu; + max_fits = fits; } } @@ -7354,26 +7381,50 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) if (prev_delta < base_energy) goto unlock; prev_delta -= base_energy; + prev_thermal_cap = cpu_thermal_cap; best_delta = min(best_delta, prev_delta); } /* Evaluate the energy impact of using max_spare_cap_cpu. */ if (max_spare_cap_cpu >= 0 && max_spare_cap > prev_spare_cap) { + /* Current best energy cpu fits better */ + if (max_fits < best_fits) + continue; + + /* + * Both don't fit performance hint (i.e. uclamp_min) + * but best energy cpu has better capacity. + */ + if ((max_fits < 0) && + (cpu_thermal_cap <= best_thermal_cap)) + continue; + cur_delta = compute_energy(&eenv, pd, cpus, p, max_spare_cap_cpu); /* CPU utilization has changed */ if (cur_delta < base_energy) goto unlock; cur_delta -= base_energy; - if (cur_delta < best_delta) { - best_delta = cur_delta; - best_energy_cpu = max_spare_cap_cpu; - } + + /* + * Both fit for the task but best energy cpu has lower + * energy impact. + */ + if ((max_fits > 0) && (best_fits > 0) && + (cur_delta >= best_delta)) + continue; + + best_delta = cur_delta; + best_energy_cpu = max_spare_cap_cpu; + best_fits = max_fits; + best_thermal_cap = cpu_thermal_cap; } } rcu_read_unlock(); - if (best_delta < prev_delta) + if ((best_fits > prev_fits) || + ((best_fits > 0) && (best_delta < prev_delta)) || + ((best_fits < 0) && (best_thermal_cap > prev_thermal_cap))) target = best_energy_cpu; return target; @@ -8870,82 +8921,16 @@ static unsigned long scale_rt_capacity(int cpu) static void update_cpu_capacity(struct sched_domain *sd, int cpu) { - unsigned long capacity_orig = arch_scale_cpu_capacity(cpu); unsigned long capacity = scale_rt_capacity(cpu); struct sched_group *sdg = sd->groups; - struct rq *rq = cpu_rq(cpu); - rq->cpu_capacity_orig = capacity_orig; + cpu_rq(cpu)->cpu_capacity_orig = arch_scale_cpu_capacity(cpu); if (!capacity) capacity = 1; - rq->cpu_capacity = capacity; - - /* - * Detect if the performance domain is in capacity inversion state. - * - * Capacity inversion happens when another perf domain with equal or - * lower capacity_orig_of() ends up having higher capacity than this - * domain after subtracting thermal pressure. - * - * We only take into account thermal pressure in this detection as it's - * the only metric that actually results in *real* reduction of - * capacity due to performance points (OPPs) being dropped/become - * unreachable due to thermal throttling. - * - * We assume: - * * That all cpus in a perf domain have the same capacity_orig - * (same uArch). - * * Thermal pressure will impact all cpus in this perf domain - * equally. - */ - if (sched_energy_enabled()) { - unsigned long inv_cap = capacity_orig - thermal_load_avg(rq); - struct perf_domain *pd; - - rcu_read_lock(); - - pd = rcu_dereference(rq->rd->pd); - rq->cpu_capacity_inverted = 0; - - for (; pd; pd = pd->next) { - struct cpumask *pd_span = perf_domain_span(pd); - unsigned long pd_cap_orig, pd_cap; - - /* We can't be inverted against our own pd */ - if (cpumask_test_cpu(cpu_of(rq), pd_span)) - continue; - - cpu = cpumask_any(pd_span); - pd_cap_orig = arch_scale_cpu_capacity(cpu); - - if (capacity_orig < pd_cap_orig) - continue; - - /* - * handle the case of multiple perf domains have the - * same capacity_orig but one of them is under higher - * thermal pressure. We record it as capacity - * inversion. - */ - if (capacity_orig == pd_cap_orig) { - pd_cap = pd_cap_orig - thermal_load_avg(cpu_rq(cpu)); - - if (pd_cap > inv_cap) { - rq->cpu_capacity_inverted = inv_cap; - break; - } - } else if (pd_cap_orig > inv_cap) { - rq->cpu_capacity_inverted = inv_cap; - break; - } - } - - rcu_read_unlock(); - } - - trace_sched_cpu_capacity_tp(rq); + cpu_rq(cpu)->cpu_capacity = capacity; + trace_sched_cpu_capacity_tp(cpu_rq(cpu)); sdg->sgc->capacity = capacity; sdg->sgc->min_capacity = capacity; @@ -10183,24 +10168,23 @@ static struct sched_group *find_busiest_group(struct lb_env *env) */ update_sd_lb_stats(env, &sds); - if (sched_energy_enabled()) { - struct root_domain *rd = env->dst_rq->rd; - - if (rcu_dereference(rd->pd) && !READ_ONCE(rd->overutilized)) - goto out_balanced; - } - - local = &sds.local_stat; - busiest = &sds.busiest_stat; - /* There is no busy sibling group to pull tasks from */ if (!sds.busiest) goto out_balanced; + busiest = &sds.busiest_stat; + /* Misfit tasks should be dealt with regardless of the avg load */ if (busiest->group_type == group_misfit_task) goto force_balance; + if (sched_energy_enabled()) { + struct root_domain *rd = env->dst_rq->rd; + + if (rcu_dereference(rd->pd) && !READ_ONCE(rd->overutilized)) + goto out_balanced; + } + /* ASYM feature bypasses nice load balance check */ if (busiest->group_type == group_asym_packing) goto force_balance; @@ -10213,6 +10197,7 @@ static struct sched_group *find_busiest_group(struct lb_env *env) if (busiest->group_type == group_imbalanced) goto force_balance; + local = &sds.local_stat; /* * If the local group is busier than the selected busiest group * don't try and pull any tasks. diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 5f18460f62f0..b62d53d7c264 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -330,7 +330,7 @@ extern void __getparam_dl(struct task_struct *p, struct sched_attr *attr); extern bool __checkparam_dl(const struct sched_attr *attr); extern bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr); extern int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial); -extern int dl_cpu_busy(int cpu, struct task_struct *p); +extern int dl_bw_check_overflow(int cpu); #ifdef CONFIG_CGROUP_SCHED @@ -1041,7 +1041,6 @@ struct rq { unsigned long cpu_capacity; unsigned long cpu_capacity_orig; - unsigned long cpu_capacity_inverted; struct balance_callback *balance_callback; @@ -2879,24 +2878,6 @@ static inline unsigned long capacity_orig_of(int cpu) return cpu_rq(cpu)->cpu_capacity_orig; } -/* - * Returns inverted capacity if the CPU is in capacity inversion state. - * 0 otherwise. - * - * Capacity inversion detection only considers thermal impact where actual - * performance points (OPPs) gets dropped. - * - * Capacity inversion state happens when another performance domain that has - * equal or lower capacity_orig_of() becomes effectively larger than the perf - * domain this CPU belongs to due to thermal pressure throttling it hard. - * - * See comment in update_cpu_capacity(). - */ -static inline unsigned long cpu_in_capacity_inversion(int cpu) -{ - return cpu_rq(cpu)->cpu_capacity_inverted; -} - /** * enum cpu_util_type - CPU utilization type * @FREQUENCY_UTIL: Utilization used to select frequency diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 1642548892a8..ad04390883ad 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -662,8 +662,7 @@ static DEFINE_PER_CPU(int, bpf_trace_nest_level); BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map, u64, flags, void *, data, u64, size) { - struct bpf_trace_sample_data *sds = this_cpu_ptr(&bpf_trace_sds); - int nest_level = this_cpu_inc_return(bpf_trace_nest_level); + struct bpf_trace_sample_data *sds; struct perf_raw_record raw = { .frag = { .size = size, @@ -671,7 +670,11 @@ BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map, }, }; struct perf_sample_data *sd; - int err; + int nest_level, err; + + preempt_disable(); + sds = this_cpu_ptr(&bpf_trace_sds); + nest_level = this_cpu_inc_return(bpf_trace_nest_level); if (WARN_ON_ONCE(nest_level > ARRAY_SIZE(sds->sds))) { err = -EBUSY; @@ -690,9 +693,9 @@ BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map, sd->sample_flags |= PERF_SAMPLE_RAW; err = __bpf_perf_event_output(regs, map, flags, sd); - out: this_cpu_dec(bpf_trace_nest_level); + preempt_enable(); return err; } @@ -717,7 +720,6 @@ static DEFINE_PER_CPU(struct bpf_trace_sample_data, bpf_misc_sds); u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy) { - int nest_level = this_cpu_inc_return(bpf_event_output_nest_level); struct perf_raw_frag frag = { .copy = ctx_copy, .size = ctx_size, @@ -734,8 +736,12 @@ u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, }; struct perf_sample_data *sd; struct pt_regs *regs; + int nest_level; u64 ret; + preempt_disable(); + nest_level = this_cpu_inc_return(bpf_event_output_nest_level); + if (WARN_ON_ONCE(nest_level > ARRAY_SIZE(bpf_misc_sds.sds))) { ret = -EBUSY; goto out; @@ -751,6 +757,7 @@ u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, ret = __bpf_perf_event_output(regs, map, flags, sd); out: this_cpu_dec(bpf_event_output_nest_level); + preempt_enable(); return ret; } diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index c49ed619a64d..de55107aef5d 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -544,6 +544,7 @@ struct trace_buffer { unsigned flags; int cpus; atomic_t record_disabled; + atomic_t resizing; cpumask_var_t cpumask; struct lock_class_key *reader_lock_key; @@ -2173,7 +2174,7 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size, /* prevent another thread from changing buffer sizes */ mutex_lock(&buffer->mutex); - + atomic_inc(&buffer->resizing); if (cpu_id == RING_BUFFER_ALL_CPUS) { /* @@ -2312,6 +2313,7 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size, atomic_dec(&buffer->record_disabled); } + atomic_dec(&buffer->resizing); mutex_unlock(&buffer->mutex); return 0; @@ -2332,6 +2334,7 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size, } } out_err_unlock: + atomic_dec(&buffer->resizing); mutex_unlock(&buffer->mutex); return err; } @@ -5539,6 +5542,15 @@ int ring_buffer_swap_cpu(struct trace_buffer *buffer_a, if (local_read(&cpu_buffer_b->committing)) goto out_dec; + /* + * When resize is in progress, we cannot swap it because + * it will mess the state of the cpu buffer. + */ + if (atomic_read(&buffer_a->resizing)) + goto out_dec; + if (atomic_read(&buffer_b->resizing)) + goto out_dec; + buffer_a->buffers[cpu] = cpu_buffer_b; buffer_b->buffers[cpu] = cpu_buffer_a; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 709af9631be4..1a87cb70f1eb 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1885,9 +1885,10 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) * place on this CPU. We fail to record, but we reset * the max trace buffer (no one writes directly to it) * and flag that it failed. + * Another reason is resize is in progress. */ trace_array_printk_buf(tr->max_buffer.buffer, _THIS_IP_, - "Failed to swap buffers due to commit in progress\n"); + "Failed to swap buffers due to commit or resize in progress\n"); } WARN_ON_ONCE(ret && ret != -EAGAIN && ret != -EBUSY); @@ -4127,8 +4128,15 @@ static void *s_start(struct seq_file *m, loff_t *pos) * will point to the same string as current_trace->name. */ mutex_lock(&trace_types_lock); - if (unlikely(tr->current_trace && iter->trace->name != tr->current_trace->name)) + if (unlikely(tr->current_trace && iter->trace->name != tr->current_trace->name)) { + /* Close iter->trace before switching to the new current tracer */ + if (iter->trace->close) + iter->trace->close(iter); *iter->trace = *tr->current_trace; + /* Reopen the new current tracer */ + if (iter->trace->open) + iter->trace->open(iter); + } mutex_unlock(&trace_types_lock); #ifdef CONFIG_TRACER_MAX_TRACE @@ -5188,11 +5196,17 @@ int tracing_set_cpumask(struct trace_array *tr, !cpumask_test_cpu(cpu, tracing_cpumask_new)) { atomic_inc(&per_cpu_ptr(tr->array_buffer.data, cpu)->disabled); ring_buffer_record_disable_cpu(tr->array_buffer.buffer, cpu); +#ifdef CONFIG_TRACER_MAX_TRACE + ring_buffer_record_disable_cpu(tr->max_buffer.buffer, cpu); +#endif } if (!cpumask_test_cpu(cpu, tr->tracing_cpumask) && cpumask_test_cpu(cpu, tracing_cpumask_new)) { atomic_dec(&per_cpu_ptr(tr->array_buffer.data, cpu)->disabled); ring_buffer_record_enable_cpu(tr->array_buffer.buffer, cpu); +#ifdef CONFIG_TRACER_MAX_TRACE + ring_buffer_record_enable_cpu(tr->max_buffer.buffer, cpu); +#endif } } arch_spin_unlock(&tr->max_lock); diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index 590b3d51afae..ba37f768e2f2 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -231,7 +231,8 @@ static void irqsoff_trace_open(struct trace_iterator *iter) { if (is_graph(iter->tr)) graph_trace_open(iter); - + else + iter->private = NULL; } static void irqsoff_trace_close(struct trace_iterator *iter) diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index 330aee1c1a49..0469a04a355f 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -168,6 +168,8 @@ static void wakeup_trace_open(struct trace_iterator *iter) { if (is_graph(iter->tr)) graph_trace_open(iter); + else + iter->private = NULL; } static void wakeup_trace_close(struct trace_iterator *iter) diff --git a/lib/Makefile b/lib/Makefile index 59bd7c2f793a..5ffe72ec9979 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -81,8 +81,14 @@ obj-$(CONFIG_TEST_STATIC_KEYS) += test_static_key_base.o obj-$(CONFIG_TEST_DYNAMIC_DEBUG) += test_dynamic_debug.o obj-$(CONFIG_TEST_PRINTF) += test_printf.o obj-$(CONFIG_TEST_SCANF) += test_scanf.o + obj-$(CONFIG_TEST_BITMAP) += test_bitmap.o obj-$(CONFIG_TEST_STRSCPY) += test_strscpy.o +ifeq ($(CONFIG_CC_IS_CLANG)$(CONFIG_KASAN),yy) +# FIXME: Clang breaks test_bitmap_const_eval when KASAN and GCOV are enabled +GCOV_PROFILE_test_bitmap.o := n +endif + obj-$(CONFIG_TEST_UUID) += test_uuid.o obj-$(CONFIG_TEST_XARRAY) += test_xarray.o obj-$(CONFIG_TEST_MAPLE_TREE) += test_maple_tree.o diff --git a/lib/clz_ctz.c b/lib/clz_ctz.c index 0d3a686b5ba2..fb8c0c5c2bd2 100644 --- a/lib/clz_ctz.c +++ b/lib/clz_ctz.c @@ -28,36 +28,16 @@ int __weak __clzsi2(int val) } EXPORT_SYMBOL(__clzsi2); -int __weak __clzdi2(long val); -int __weak __ctzdi2(long val); -#if BITS_PER_LONG == 32 - -int __weak __clzdi2(long val) +int __weak __clzdi2(u64 val); +int __weak __clzdi2(u64 val) { - return 32 - fls((int)val); + return 64 - fls64(val); } EXPORT_SYMBOL(__clzdi2); -int __weak __ctzdi2(long val) +int __weak __ctzdi2(u64 val); +int __weak __ctzdi2(u64 val) { - return __ffs((u32)val); + return __ffs64(val); } EXPORT_SYMBOL(__ctzdi2); - -#elif BITS_PER_LONG == 64 - -int __weak __clzdi2(long val) -{ - return 64 - fls64((u64)val); -} -EXPORT_SYMBOL(__clzdi2); - -int __weak __ctzdi2(long val) -{ - return __ffs64((u64)val); -} -EXPORT_SYMBOL(__ctzdi2); - -#else -#error BITS_PER_LONG not 32 or 64 -#endif diff --git a/lib/debugobjects.c b/lib/debugobjects.c index c46736210363..dacb80c22c4f 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -498,6 +498,15 @@ static void debug_print_object(struct debug_obj *obj, char *msg) const struct debug_obj_descr *descr = obj->descr; static int limit; + /* + * Don't report if lookup_object_or_alloc() by the current thread + * failed because lookup_object_or_alloc()/debug_objects_oom() by a + * concurrent thread turned off debug_objects_enabled and cleared + * the hash buckets. + */ + if (!debug_objects_enabled) + return; + if (limit < 5 && descr != descr_test) { void *hint = descr->debug_hint ? descr->debug_hint(obj->object) : NULL; diff --git a/lib/maple_tree.c b/lib/maple_tree.c index 47d0c95b9a01..250b4c67fac8 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -4333,6 +4333,9 @@ static inline bool mas_wr_append(struct ma_wr_state *wr_mas) struct ma_state *mas = wr_mas->mas; unsigned char node_pivots = mt_pivots[wr_mas->type]; + if (mt_in_rcu(mas->tree)) + return false; + if ((mas->index != wr_mas->r_min) && (mas->last == wr_mas->r_max)) { if (new_end < node_pivots) wr_mas->pivots[new_end] = wr_mas->pivots[end]; diff --git a/lib/radix-tree.c b/lib/radix-tree.c index 3c78e1e8b2ad..2ec38f08e4f0 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -1134,7 +1134,6 @@ static void set_iter_tags(struct radix_tree_iter *iter, void __rcu **radix_tree_iter_resume(void __rcu **slot, struct radix_tree_iter *iter) { - slot++; iter->index = __radix_tree_iter_add(iter, 1); iter->next_index = iter->index; iter->tags = 0; diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c index a8005ad3bd58..37a9108c4f58 100644 --- a/lib/test_bitmap.c +++ b/lib/test_bitmap.c @@ -1149,6 +1149,10 @@ static void __init test_bitmap_print_buf(void) } } +/* + * FIXME: Clang breaks compile-time evaluations when KASAN and GCOV are enabled. + * To workaround it, GCOV is force-disabled in Makefile for this configuration. + */ static void __init test_bitmap_const_eval(void) { DECLARE_BITMAP(bitmap, BITS_PER_LONG); @@ -1174,11 +1178,7 @@ static void __init test_bitmap_const_eval(void) * the compiler is fixed. */ bitmap_clear(bitmap, 0, BITS_PER_LONG); -#if defined(__s390__) && defined(__clang__) - if (!const_test_bit(7, bitmap)) -#else if (!test_bit(7, bitmap)) -#endif bitmap_set(bitmap, 5, 2); /* Equals to `unsigned long bitopvar = BIT(20)` */ diff --git a/mm/hugetlb.c b/mm/hugetlb.c index d3ffa0fd49e5..c38ec6efec0f 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1581,9 +1581,37 @@ static inline void destroy_compound_gigantic_page(struct page *page, unsigned int order) { } #endif +static inline void __clear_hugetlb_destructor(struct hstate *h, + struct page *page) +{ + lockdep_assert_held(&hugetlb_lock); + + /* + * Very subtle + * + * For non-gigantic pages set the destructor to the normal compound + * page dtor. This is needed in case someone takes an additional + * temporary ref to the page, and freeing is delayed until they drop + * their reference. + * + * For gigantic pages set the destructor to the null dtor. This + * destructor will never be called. Before freeing the gigantic + * page destroy_compound_gigantic_folio will turn the folio into a + * simple group of pages. After this the destructor does not + * apply. + * + */ + if (hstate_is_gigantic(h)) + set_compound_page_dtor(page, NULL_COMPOUND_DTOR); + else + set_compound_page_dtor(page, COMPOUND_PAGE_DTOR); +} + /* - * Remove hugetlb page from lists, and update dtor so that page appears - * as just a compound page. + * Remove hugetlb page from lists. + * If vmemmap exists for the page, update dtor so that the page appears + * as just a compound page. Otherwise, wait until after allocating vmemmap + * to update dtor. * * A reference is held on the page, except in the case of demote. * @@ -1614,31 +1642,19 @@ static void __remove_hugetlb_page(struct hstate *h, struct page *page, } /* - * Very subtle - * - * For non-gigantic pages set the destructor to the normal compound - * page dtor. This is needed in case someone takes an additional - * temporary ref to the page, and freeing is delayed until they drop - * their reference. - * - * For gigantic pages set the destructor to the null dtor. This - * destructor will never be called. Before freeing the gigantic - * page destroy_compound_gigantic_page will turn the compound page - * into a simple group of pages. After this the destructor does not - * apply. - * - * This handles the case where more than one ref is held when and - * after update_and_free_page is called. - * - * In the case of demote we do not ref count the page as it will soon - * be turned into a page of smaller size. + * We can only clear the hugetlb destructor after allocating vmemmap + * pages. Otherwise, someone (memory error handling) may try to write + * to tail struct pages. + */ + if (!HPageVmemmapOptimized(page)) + __clear_hugetlb_destructor(h, page); + + /* + * In the case of demote we do not ref count the page as it will soon + * be turned into a page of smaller size. */ if (!demote) set_page_refcounted(page); - if (hstate_is_gigantic(h)) - set_compound_page_dtor(page, NULL_COMPOUND_DTOR); - else - set_compound_page_dtor(page, COMPOUND_PAGE_DTOR); h->nr_huge_pages--; h->nr_huge_pages_node[nid]--; @@ -1706,6 +1722,7 @@ static void __update_and_free_page(struct hstate *h, struct page *page) { int i; struct page *subpage; + bool clear_dtor = HPageVmemmapOptimized(page); if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) return; @@ -1736,6 +1753,16 @@ static void __update_and_free_page(struct hstate *h, struct page *page) if (unlikely(PageHWPoison(page))) hugetlb_clear_page_hwpoison(page); + /* + * If vmemmap pages were allocated above, then we need to clear the + * hugetlb destructor under the hugetlb lock. + */ + if (clear_dtor) { + spin_lock_irq(&hugetlb_lock); + __clear_hugetlb_destructor(h, page); + spin_unlock_irq(&hugetlb_lock); + } + for (i = 0; i < pages_per_huge_page(h); i++) { subpage = nth_page(page, i); subpage->flags &= ~(1 << PG_locked | 1 << PG_error | diff --git a/mm/madvise.c b/mm/madvise.c index d03e149ffe6e..5973399b2f9b 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -654,8 +654,8 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, * deactivate all pages. */ if (folio_test_large(folio)) { - if (folio_mapcount(folio) != 1) - goto out; + if (folio_estimated_sharers(folio) != 1) + break; folio_get(folio); if (!folio_trylock(folio)) { folio_put(folio); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 3e8f1ad0fe9d..67b6d8238b3e 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3165,12 +3165,12 @@ void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat, * accumulating over a page of vmstat data or when pgdat or idx * changes. */ - if (stock->cached_objcg != objcg) { + if (READ_ONCE(stock->cached_objcg) != objcg) { old = drain_obj_stock(stock); obj_cgroup_get(objcg); stock->nr_bytes = atomic_read(&objcg->nr_charged_bytes) ? atomic_xchg(&objcg->nr_charged_bytes, 0) : 0; - stock->cached_objcg = objcg; + WRITE_ONCE(stock->cached_objcg, objcg); stock->cached_pgdat = pgdat; } else if (stock->cached_pgdat != pgdat) { /* Flush the existing cached vmstat data */ @@ -3224,7 +3224,7 @@ static bool consume_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes) local_lock_irqsave(&memcg_stock.stock_lock, flags); stock = this_cpu_ptr(&memcg_stock); - if (objcg == stock->cached_objcg && stock->nr_bytes >= nr_bytes) { + if (objcg == READ_ONCE(stock->cached_objcg) && stock->nr_bytes >= nr_bytes) { stock->nr_bytes -= nr_bytes; ret = true; } @@ -3236,7 +3236,7 @@ static bool consume_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes) static struct obj_cgroup *drain_obj_stock(struct memcg_stock_pcp *stock) { - struct obj_cgroup *old = stock->cached_objcg; + struct obj_cgroup *old = READ_ONCE(stock->cached_objcg); if (!old) return NULL; @@ -3289,7 +3289,7 @@ static struct obj_cgroup *drain_obj_stock(struct memcg_stock_pcp *stock) stock->cached_pgdat = NULL; } - stock->cached_objcg = NULL; + WRITE_ONCE(stock->cached_objcg, NULL); /* * The `old' objects needs to be released by the caller via * obj_cgroup_put() outside of memcg_stock_pcp::stock_lock. @@ -3300,10 +3300,11 @@ static struct obj_cgroup *drain_obj_stock(struct memcg_stock_pcp *stock) static bool obj_stock_flush_required(struct memcg_stock_pcp *stock, struct mem_cgroup *root_memcg) { + struct obj_cgroup *objcg = READ_ONCE(stock->cached_objcg); struct mem_cgroup *memcg; - if (stock->cached_objcg) { - memcg = obj_cgroup_memcg(stock->cached_objcg); + if (objcg) { + memcg = obj_cgroup_memcg(objcg); if (memcg && mem_cgroup_is_descendant(memcg, root_memcg)) return true; } @@ -3322,10 +3323,10 @@ static void refill_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes, local_lock_irqsave(&memcg_stock.stock_lock, flags); stock = this_cpu_ptr(&memcg_stock); - if (stock->cached_objcg != objcg) { /* reset if necessary */ + if (READ_ONCE(stock->cached_objcg) != objcg) { /* reset if necessary */ old = drain_obj_stock(stock); obj_cgroup_get(objcg); - stock->cached_objcg = objcg; + WRITE_ONCE(stock->cached_objcg, objcg); stock->nr_bytes = atomic_read(&objcg->nr_charged_bytes) ? atomic_xchg(&objcg->nr_charged_bytes, 0) : 0; allow_uncharge = true; /* Allow uncharge when objcg changes */ diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 4457f9423e2c..99de0328d1be 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -2591,10 +2591,13 @@ retry: if (ret > 0) { ret = soft_offline_in_use_page(page); } else if (ret == 0) { - if (!page_handle_poison(page, true, false) && try_again) { - try_again = false; - flags &= ~MF_COUNT_INCREASED; - goto retry; + if (!page_handle_poison(page, true, false)) { + if (try_again) { + try_again = false; + flags &= ~MF_COUNT_INCREASED; + goto retry; + } + ret = -EBUSY; } } diff --git a/mm/shmem.c b/mm/shmem.c index aba041a3df73..10365ced5b1f 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -800,14 +800,16 @@ unsigned long shmem_partial_swap_usage(struct address_space *mapping, XA_STATE(xas, &mapping->i_pages, start); struct page *page; unsigned long swapped = 0; + unsigned long max = end - 1; rcu_read_lock(); - xas_for_each(&xas, page, end - 1) { + xas_for_each(&xas, page, max) { if (xas_retry(&xas, page)) continue; if (xa_is_value(page)) swapped++; - + if (xas.xa_index == max) + break; if (need_resched()) { xas_pause(&xas); cond_resched_rcu(); diff --git a/mm/vmalloc.c b/mm/vmalloc.c index d5dc361dc104..80bd104a4d42 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -2909,6 +2909,10 @@ void *vmap_pfn(unsigned long *pfns, unsigned int count, pgprot_t prot) free_vm_area(area); return NULL; } + + flush_cache_vmap((unsigned long)area->addr, + (unsigned long)area->addr + count * PAGE_SIZE); + return area->addr; } EXPORT_SYMBOL_GPL(vmap_pfn); diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index d03941cace2c..37f755c9a1b7 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -33,8 +33,7 @@ /* * lock ordering: * page_lock - * pool->migrate_lock - * class->lock + * pool->lock * zspage->lock */ @@ -192,7 +191,6 @@ static const int fullness_threshold_frac = 4; static size_t huge_class_size; struct size_class { - spinlock_t lock; struct list_head fullness_list[NR_ZS_FULLNESS]; /* * Size of objects stored in this class. Must be multiple @@ -247,8 +245,8 @@ struct zs_pool { #ifdef CONFIG_COMPACTION struct work_struct free_work; #endif - /* protect page/zspage migration */ - rwlock_t migrate_lock; + spinlock_t lock; + atomic_t compaction_in_progress; }; struct zspage { @@ -355,7 +353,7 @@ static void cache_free_zspage(struct zs_pool *pool, struct zspage *zspage) kmem_cache_free(pool->zspage_cachep, zspage); } -/* class->lock(which owns the handle) synchronizes races */ +/* pool->lock(which owns the handle) synchronizes races */ static void record_obj(unsigned long handle, unsigned long obj) { *(unsigned long *)handle = obj; @@ -452,7 +450,7 @@ static __maybe_unused int is_first_page(struct page *page) return PagePrivate(page); } -/* Protected by class->lock */ +/* Protected by pool->lock */ static inline int get_zspage_inuse(struct zspage *zspage) { return zspage->inuse; @@ -597,13 +595,13 @@ static int zs_stats_size_show(struct seq_file *s, void *v) if (class->index != i) continue; - spin_lock(&class->lock); + spin_lock(&pool->lock); class_almost_full = zs_stat_get(class, CLASS_ALMOST_FULL); class_almost_empty = zs_stat_get(class, CLASS_ALMOST_EMPTY); obj_allocated = zs_stat_get(class, OBJ_ALLOCATED); obj_used = zs_stat_get(class, OBJ_USED); freeable = zs_can_compact(class); - spin_unlock(&class->lock); + spin_unlock(&pool->lock); objs_per_zspage = class->objs_per_zspage; pages_used = obj_allocated / objs_per_zspage * @@ -916,7 +914,7 @@ static void __free_zspage(struct zs_pool *pool, struct size_class *class, get_zspage_mapping(zspage, &class_idx, &fg); - assert_spin_locked(&class->lock); + assert_spin_locked(&pool->lock); VM_BUG_ON(get_zspage_inuse(zspage)); VM_BUG_ON(fg != ZS_EMPTY); @@ -1247,19 +1245,19 @@ void *zs_map_object(struct zs_pool *pool, unsigned long handle, BUG_ON(in_interrupt()); /* It guarantees it can get zspage from handle safely */ - read_lock(&pool->migrate_lock); + spin_lock(&pool->lock); obj = handle_to_obj(handle); obj_to_location(obj, &page, &obj_idx); zspage = get_zspage(page); /* - * migration cannot move any zpages in this zspage. Here, class->lock + * migration cannot move any zpages in this zspage. Here, pool->lock * is too heavy since callers would take some time until they calls * zs_unmap_object API so delegate the locking from class to zspage * which is smaller granularity. */ migrate_read_lock(zspage); - read_unlock(&pool->migrate_lock); + spin_unlock(&pool->lock); class = zspage_class(pool, zspage); off = (class->size * obj_idx) & ~PAGE_MASK; @@ -1412,8 +1410,8 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp) size += ZS_HANDLE_SIZE; class = pool->size_class[get_size_class_index(size)]; - /* class->lock effectively protects the zpage migration */ - spin_lock(&class->lock); + /* pool->lock effectively protects the zpage migration */ + spin_lock(&pool->lock); zspage = find_get_zspage(class); if (likely(zspage)) { obj = obj_malloc(pool, zspage, handle); @@ -1421,12 +1419,12 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp) fix_fullness_group(class, zspage); record_obj(handle, obj); class_stat_inc(class, OBJ_USED, 1); - spin_unlock(&class->lock); + spin_unlock(&pool->lock); return handle; } - spin_unlock(&class->lock); + spin_unlock(&pool->lock); zspage = alloc_zspage(pool, class, gfp); if (!zspage) { @@ -1434,7 +1432,7 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp) return (unsigned long)ERR_PTR(-ENOMEM); } - spin_lock(&class->lock); + spin_lock(&pool->lock); obj = obj_malloc(pool, zspage, handle); newfg = get_fullness_group(class, zspage); insert_zspage(class, zspage, newfg); @@ -1447,7 +1445,7 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp) /* We completely set up zspage so mark them as movable */ SetZsPageMovable(pool, zspage); - spin_unlock(&class->lock); + spin_unlock(&pool->lock); return handle; } @@ -1491,16 +1489,14 @@ void zs_free(struct zs_pool *pool, unsigned long handle) return; /* - * The pool->migrate_lock protects the race with zpage's migration + * The pool->lock protects the race with zpage's migration * so it's safe to get the page from handle. */ - read_lock(&pool->migrate_lock); + spin_lock(&pool->lock); obj = handle_to_obj(handle); obj_to_page(obj, &f_page); zspage = get_zspage(f_page); class = zspage_class(pool, zspage); - spin_lock(&class->lock); - read_unlock(&pool->migrate_lock); obj_free(class->size, obj); class_stat_dec(class, OBJ_USED, 1); @@ -1510,7 +1506,7 @@ void zs_free(struct zs_pool *pool, unsigned long handle) free_zspage(pool, class, zspage); out: - spin_unlock(&class->lock); + spin_unlock(&pool->lock); cache_free_handle(pool, handle); } EXPORT_SYMBOL_GPL(zs_free); @@ -1821,6 +1817,7 @@ static void replace_sub_page(struct size_class *class, struct zspage *zspage, static bool zs_page_isolate(struct page *page, isolate_mode_t mode) { + struct zs_pool *pool; struct zspage *zspage; /* @@ -1831,9 +1828,10 @@ static bool zs_page_isolate(struct page *page, isolate_mode_t mode) VM_BUG_ON_PAGE(PageIsolated(page), page); zspage = get_zspage(page); - migrate_write_lock(zspage); + pool = zspage->pool; + spin_lock(&pool->lock); inc_zspage_isolation(zspage); - migrate_write_unlock(zspage); + spin_unlock(&pool->lock); return true; } @@ -1867,16 +1865,12 @@ static int zs_page_migrate(struct page *newpage, struct page *page, pool = zspage->pool; /* - * The pool migrate_lock protects the race between zpage migration + * The pool's lock protects the race between zpage migration * and zs_free. */ - write_lock(&pool->migrate_lock); + spin_lock(&pool->lock); class = zspage_class(pool, zspage); - /* - * the class lock protects zpage alloc/free in the zspage. - */ - spin_lock(&class->lock); /* the migrate_write_lock protects zpage access via zs_map_object */ migrate_write_lock(zspage); @@ -1904,13 +1898,12 @@ static int zs_page_migrate(struct page *newpage, struct page *page, kunmap_atomic(s_addr); replace_sub_page(class, zspage, newpage, page); + dec_zspage_isolation(zspage); /* * Since we complete the data copy and set up new zspage structure, - * it's okay to release migration_lock. + * it's okay to release the pool's lock. */ - write_unlock(&pool->migrate_lock); - spin_unlock(&class->lock); - dec_zspage_isolation(zspage); + spin_unlock(&pool->lock); migrate_write_unlock(zspage); get_page(newpage); @@ -1927,15 +1920,17 @@ static int zs_page_migrate(struct page *newpage, struct page *page, static void zs_page_putback(struct page *page) { + struct zs_pool *pool; struct zspage *zspage; VM_BUG_ON_PAGE(!PageMovable(page), page); VM_BUG_ON_PAGE(!PageIsolated(page), page); zspage = get_zspage(page); - migrate_write_lock(zspage); + pool = zspage->pool; + spin_lock(&pool->lock); dec_zspage_isolation(zspage); - migrate_write_unlock(zspage); + spin_unlock(&pool->lock); } static const struct movable_operations zsmalloc_mops = { @@ -1964,9 +1959,9 @@ static void async_free_zspage(struct work_struct *work) if (class->index != i) continue; - spin_lock(&class->lock); + spin_lock(&pool->lock); list_splice_init(&class->fullness_list[ZS_EMPTY], &free_pages); - spin_unlock(&class->lock); + spin_unlock(&pool->lock); } list_for_each_entry_safe(zspage, tmp, &free_pages, list) { @@ -1976,9 +1971,9 @@ static void async_free_zspage(struct work_struct *work) get_zspage_mapping(zspage, &class_idx, &fullness); VM_BUG_ON(fullness != ZS_EMPTY); class = pool->size_class[class_idx]; - spin_lock(&class->lock); + spin_lock(&pool->lock); __free_zspage(pool, class, zspage); - spin_unlock(&class->lock); + spin_unlock(&pool->lock); } }; @@ -2039,10 +2034,11 @@ static unsigned long __zs_compact(struct zs_pool *pool, struct zspage *dst_zspage = NULL; unsigned long pages_freed = 0; - /* protect the race between zpage migration and zs_free */ - write_lock(&pool->migrate_lock); - /* protect zpage allocation/free */ - spin_lock(&class->lock); + /* + * protect the race between zpage migration and zs_free + * as well as zpage allocation/free + */ + spin_lock(&pool->lock); while ((src_zspage = isolate_zspage(class, true))) { /* protect someone accessing the zspage(i.e., zs_map_object) */ migrate_write_lock(src_zspage); @@ -2067,7 +2063,7 @@ static unsigned long __zs_compact(struct zs_pool *pool, putback_zspage(class, dst_zspage); migrate_write_unlock(dst_zspage); dst_zspage = NULL; - if (rwlock_is_contended(&pool->migrate_lock)) + if (spin_is_contended(&pool->lock)) break; } @@ -2084,11 +2080,9 @@ static unsigned long __zs_compact(struct zs_pool *pool, pages_freed += class->pages_per_zspage; } else migrate_write_unlock(src_zspage); - spin_unlock(&class->lock); - write_unlock(&pool->migrate_lock); + spin_unlock(&pool->lock); cond_resched(); - write_lock(&pool->migrate_lock); - spin_lock(&class->lock); + spin_lock(&pool->lock); } if (src_zspage) { @@ -2096,8 +2090,7 @@ static unsigned long __zs_compact(struct zs_pool *pool, migrate_write_unlock(src_zspage); } - spin_unlock(&class->lock); - write_unlock(&pool->migrate_lock); + spin_unlock(&pool->lock); return pages_freed; } @@ -2108,6 +2101,15 @@ unsigned long zs_compact(struct zs_pool *pool) struct size_class *class; unsigned long pages_freed = 0; + /* + * Pool compaction is performed under pool->lock so it is basically + * single-threaded. Having more than one thread in __zs_compact() + * will increase pool->lock contention, which will impact other + * zsmalloc operations that need pool->lock. + */ + if (atomic_xchg(&pool->compaction_in_progress, 1)) + return 0; + for (i = ZS_SIZE_CLASSES - 1; i >= 0; i--) { class = pool->size_class[i]; if (class->index != i) @@ -2115,6 +2117,7 @@ unsigned long zs_compact(struct zs_pool *pool) pages_freed += __zs_compact(pool, class); } atomic_long_add(pages_freed, &pool->stats.pages_compacted); + atomic_set(&pool->compaction_in_progress, 0); return pages_freed; } @@ -2200,7 +2203,8 @@ struct zs_pool *zs_create_pool(const char *name) return NULL; init_deferred_free(pool); - rwlock_init(&pool->migrate_lock); + spin_lock_init(&pool->lock); + atomic_set(&pool->compaction_in_progress, 0); pool->name = kstrdup(name, GFP_KERNEL); if (!pool->name) @@ -2271,7 +2275,6 @@ struct zs_pool *zs_create_pool(const char *name) class->index = i; class->pages_per_zspage = pages_per_zspage; class->objs_per_zspage = objs_per_zspage; - spin_lock_init(&class->lock); pool->size_class[i] = class; for (fullness = ZS_EMPTY; fullness < NR_ZS_FULLNESS; fullness++) diff --git a/net/Makefile b/net/Makefile index 6a62e5b27378..0914bea9c335 100644 --- a/net/Makefile +++ b/net/Makefile @@ -23,6 +23,7 @@ obj-$(CONFIG_BPFILTER) += bpfilter/ obj-$(CONFIG_PACKET) += packet/ obj-$(CONFIG_NET_KEY) += key/ obj-$(CONFIG_BRIDGE) += bridge/ +obj-$(CONFIG_NET_DEVLINK) += devlink/ obj-$(CONFIG_NET_DSA) += dsa/ obj-$(CONFIG_ATALK) += appletalk/ obj-$(CONFIG_X25) += x25/ diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c index f1741fbfb617..98a624f32b94 100644 --- a/net/batman-adv/bat_v_elp.c +++ b/net/batman-adv/bat_v_elp.c @@ -506,7 +506,7 @@ int batadv_v_elp_packet_recv(struct sk_buff *skb, struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface); struct batadv_elp_packet *elp_packet; struct batadv_hard_iface *primary_if; - struct ethhdr *ethhdr = (struct ethhdr *)skb_mac_header(skb); + struct ethhdr *ethhdr; bool res; int ret = NET_RX_DROP; @@ -514,6 +514,7 @@ int batadv_v_elp_packet_recv(struct sk_buff *skb, if (!res) goto free_skb; + ethhdr = eth_hdr(skb); if (batadv_is_my_mac(bat_priv, ethhdr->h_source)) goto free_skb; diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c index 033639df96d8..9f4815f4c8e8 100644 --- a/net/batman-adv/bat_v_ogm.c +++ b/net/batman-adv/bat_v_ogm.c @@ -124,8 +124,10 @@ static void batadv_v_ogm_send_to_if(struct sk_buff *skb, { struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); - if (hard_iface->if_status != BATADV_IF_ACTIVE) + if (hard_iface->if_status != BATADV_IF_ACTIVE) { + kfree_skb(skb); return; + } batadv_inc_counter(bat_priv, BATADV_CNT_MGMT_TX); batadv_add_counter(bat_priv, BATADV_CNT_MGMT_TX_BYTES, @@ -986,7 +988,7 @@ int batadv_v_ogm_packet_recv(struct sk_buff *skb, { struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface); struct batadv_ogm2_packet *ogm_packet; - struct ethhdr *ethhdr = eth_hdr(skb); + struct ethhdr *ethhdr; int ogm_offset; u8 *packet_pos; int ret = NET_RX_DROP; @@ -1000,6 +1002,7 @@ int batadv_v_ogm_packet_recv(struct sk_buff *skb, if (!batadv_check_management_packet(skb, if_incoming, BATADV_OGM2_HLEN)) goto free_skb; + ethhdr = eth_hdr(skb); if (batadv_is_my_mac(bat_priv, ethhdr->h_source)) goto free_skb; diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index 41c1ad33d009..24c9c0c3f316 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -630,7 +630,19 @@ out: */ void batadv_update_min_mtu(struct net_device *soft_iface) { - soft_iface->mtu = batadv_hardif_min_mtu(soft_iface); + struct batadv_priv *bat_priv = netdev_priv(soft_iface); + int limit_mtu; + int mtu; + + mtu = batadv_hardif_min_mtu(soft_iface); + + if (bat_priv->mtu_set_by_user) + limit_mtu = bat_priv->mtu_set_by_user; + else + limit_mtu = ETH_DATA_LEN; + + mtu = min(mtu, limit_mtu); + dev_set_mtu(soft_iface, mtu); /* Check if the local translate table should be cleaned up to match a * new (and smaller) MTU. diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c index a5e4a4e976cf..86e0664e0511 100644 --- a/net/batman-adv/netlink.c +++ b/net/batman-adv/netlink.c @@ -495,7 +495,10 @@ static int batadv_netlink_set_mesh(struct sk_buff *skb, struct genl_info *info) attr = info->attrs[BATADV_ATTR_FRAGMENTATION_ENABLED]; atomic_set(&bat_priv->fragmentation, !!nla_get_u8(attr)); + + rtnl_lock(); batadv_update_min_mtu(bat_priv->soft_iface); + rtnl_unlock(); } if (info->attrs[BATADV_ATTR_GW_BANDWIDTH_DOWN]) { diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 0f5c0679b55a..38d411a52f33 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -154,11 +154,14 @@ static int batadv_interface_set_mac_addr(struct net_device *dev, void *p) static int batadv_interface_change_mtu(struct net_device *dev, int new_mtu) { + struct batadv_priv *bat_priv = netdev_priv(dev); + /* check ranges */ if (new_mtu < 68 || new_mtu > batadv_hardif_min_mtu(dev)) return -EINVAL; dev->mtu = new_mtu; + bat_priv->mtu_set_by_user = new_mtu; return 0; } diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 01d30c1e412c..5d8cee74772f 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -774,7 +774,6 @@ check_roaming: if (roamed_back) { batadv_tt_global_free(bat_priv, tt_global, "Roaming canceled"); - tt_global = NULL; } else { /* The global entry has to be marked as ROAMING and * has to be kept for consistency purpose diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 758cd797a063..76791815b26b 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -1547,6 +1547,12 @@ struct batadv_priv { struct net_device *soft_iface; /** + * @mtu_set_by_user: MTU was set once by user + * protected by rtnl_lock + */ + int mtu_set_by_user; + + /** * @bat_counters: mesh internal traffic statistic counters (see * batadv_counters) */ diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 02fc9961464c..a7899857aee5 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -6375,9 +6375,14 @@ static inline int l2cap_le_command_rej(struct l2cap_conn *conn, if (!chan) goto done; + chan = l2cap_chan_hold_unless_zero(chan); + if (!chan) + goto done; + l2cap_chan_lock(chan); l2cap_chan_del(chan, ECONNREFUSED); l2cap_chan_unlock(chan); + l2cap_chan_put(chan); done: mutex_unlock(&conn->chan_lock); diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index eebe256104bc..947ca580bb9a 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -46,6 +46,7 @@ static const struct proto_ops l2cap_sock_ops; static void l2cap_sock_init(struct sock *sk, struct sock *parent); static struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock, int proto, gfp_t prio, int kern); +static void l2cap_sock_cleanup_listen(struct sock *parent); bool l2cap_is_socket(struct socket *sock) { @@ -1415,6 +1416,7 @@ static int l2cap_sock_release(struct socket *sock) if (!sk) return 0; + l2cap_sock_cleanup_listen(sk); bt_sock_unlink(&l2cap_sk_list, sk); err = l2cap_sock_shutdown(sock, SHUT_RDWR); diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 89c94f3e96bc..d2e8565d0b33 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -7277,7 +7277,7 @@ static void get_conn_info_complete(struct hci_dev *hdev, void *data, int err) bt_dev_dbg(hdev, "err %d", err); - memcpy(&rp.addr, &cp->addr.bdaddr, sizeof(rp.addr)); + memcpy(&rp.addr, &cp->addr, sizeof(rp.addr)); status = mgmt_status(err); if (status == MGMT_STATUS_SUCCESS) { diff --git a/net/can/isotp.c b/net/can/isotp.c index b3c2a49b189c..8c97f4061ffd 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -175,12 +175,6 @@ static bool isotp_register_rxid(struct isotp_sock *so) return (isotp_bc_flags(so) == 0); } -static bool isotp_register_txecho(struct isotp_sock *so) -{ - /* all modes but SF_BROADCAST register for tx echo skbs */ - return (isotp_bc_flags(so) != CAN_ISOTP_SF_BROADCAST); -} - static enum hrtimer_restart isotp_rx_timer_handler(struct hrtimer *hrtimer) { struct isotp_sock *so = container_of(hrtimer, struct isotp_sock, @@ -1176,7 +1170,7 @@ static int isotp_release(struct socket *sock) lock_sock(sk); /* remove current filters & unregister */ - if (so->bound && isotp_register_txecho(so)) { + if (so->bound) { if (so->ifindex) { struct net_device *dev; @@ -1293,14 +1287,12 @@ static int isotp_bind(struct socket *sock, struct sockaddr *uaddr, int len) can_rx_register(net, dev, rx_id, SINGLE_MASK(rx_id), isotp_rcv, sk, "isotp", sk); - if (isotp_register_txecho(so)) { - /* no consecutive frame echo skb in flight */ - so->cfecho = 0; + /* no consecutive frame echo skb in flight */ + so->cfecho = 0; - /* register for echo skb's */ - can_rx_register(net, dev, tx_id, SINGLE_MASK(tx_id), - isotp_rcv_echo, sk, "isotpe", sk); - } + /* register for echo skb's */ + can_rx_register(net, dev, tx_id, SINGLE_MASK(tx_id), + isotp_rcv_echo, sk, "isotpe", sk); dev_put(dev); @@ -1521,7 +1513,7 @@ static void isotp_notify(struct isotp_sock *so, unsigned long msg, case NETDEV_UNREGISTER: lock_sock(sk); /* remove current filters & unregister */ - if (so->bound && isotp_register_txecho(so)) { + if (so->bound) { if (isotp_register_rxid(so)) can_rx_unregister(dev_net(dev), dev, so->rxid, SINGLE_MASK(so->rxid), diff --git a/net/can/raw.c b/net/can/raw.c index 4abab2c3011a..8c104339d538 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -84,6 +84,8 @@ struct raw_sock { struct sock sk; int bound; int ifindex; + struct net_device *dev; + netdevice_tracker dev_tracker; struct list_head notifier; int loopback; int recv_own_msgs; @@ -277,21 +279,24 @@ static void raw_notify(struct raw_sock *ro, unsigned long msg, if (!net_eq(dev_net(dev), sock_net(sk))) return; - if (ro->ifindex != dev->ifindex) + if (ro->dev != dev) return; switch (msg) { case NETDEV_UNREGISTER: lock_sock(sk); /* remove current filters & unregister */ - if (ro->bound) + if (ro->bound) { raw_disable_allfilters(dev_net(dev), dev, sk); + netdev_put(dev, &ro->dev_tracker); + } if (ro->count > 1) kfree(ro->filter); ro->ifindex = 0; ro->bound = 0; + ro->dev = NULL; ro->count = 0; release_sock(sk); @@ -337,6 +342,7 @@ static int raw_init(struct sock *sk) ro->bound = 0; ro->ifindex = 0; + ro->dev = NULL; /* set default filter to single entry dfilter */ ro->dfilter.can_id = 0; @@ -383,18 +389,14 @@ static int raw_release(struct socket *sock) list_del(&ro->notifier); spin_unlock(&raw_notifier_lock); + rtnl_lock(); lock_sock(sk); /* remove current filters & unregister */ if (ro->bound) { - if (ro->ifindex) { - struct net_device *dev; - - dev = dev_get_by_index(sock_net(sk), ro->ifindex); - if (dev) { - raw_disable_allfilters(dev_net(dev), dev, sk); - dev_put(dev); - } + if (ro->dev) { + raw_disable_allfilters(dev_net(ro->dev), ro->dev, sk); + netdev_put(ro->dev, &ro->dev_tracker); } else { raw_disable_allfilters(sock_net(sk), NULL, sk); } @@ -405,6 +407,7 @@ static int raw_release(struct socket *sock) ro->ifindex = 0; ro->bound = 0; + ro->dev = NULL; ro->count = 0; free_percpu(ro->uniq); @@ -412,6 +415,8 @@ static int raw_release(struct socket *sock) sock->sk = NULL; release_sock(sk); + rtnl_unlock(); + sock_put(sk); return 0; @@ -422,6 +427,7 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len) struct sockaddr_can *addr = (struct sockaddr_can *)uaddr; struct sock *sk = sock->sk; struct raw_sock *ro = raw_sk(sk); + struct net_device *dev = NULL; int ifindex; int err = 0; int notify_enetdown = 0; @@ -431,24 +437,23 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len) if (addr->can_family != AF_CAN) return -EINVAL; + rtnl_lock(); lock_sock(sk); if (ro->bound && addr->can_ifindex == ro->ifindex) goto out; if (addr->can_ifindex) { - struct net_device *dev; - dev = dev_get_by_index(sock_net(sk), addr->can_ifindex); if (!dev) { err = -ENODEV; goto out; } if (dev->type != ARPHRD_CAN) { - dev_put(dev); err = -ENODEV; - goto out; + goto out_put_dev; } + if (!(dev->flags & IFF_UP)) notify_enetdown = 1; @@ -456,7 +461,9 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len) /* filters set by default/setsockopt */ err = raw_enable_allfilters(sock_net(sk), dev, sk); - dev_put(dev); + if (err) + goto out_put_dev; + } else { ifindex = 0; @@ -467,26 +474,30 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len) if (!err) { if (ro->bound) { /* unregister old filters */ - if (ro->ifindex) { - struct net_device *dev; - - dev = dev_get_by_index(sock_net(sk), - ro->ifindex); - if (dev) { - raw_disable_allfilters(dev_net(dev), - dev, sk); - dev_put(dev); - } + if (ro->dev) { + raw_disable_allfilters(dev_net(ro->dev), + ro->dev, sk); + /* drop reference to old ro->dev */ + netdev_put(ro->dev, &ro->dev_tracker); } else { raw_disable_allfilters(sock_net(sk), NULL, sk); } } ro->ifindex = ifindex; ro->bound = 1; + /* bind() ok -> hold a reference for new ro->dev */ + ro->dev = dev; + if (ro->dev) + netdev_hold(ro->dev, &ro->dev_tracker, GFP_KERNEL); } - out: +out_put_dev: + /* remove potential reference from dev_get_by_index() */ + if (dev) + dev_put(dev); +out: release_sock(sk); + rtnl_unlock(); if (notify_enetdown) { sk->sk_err = ENETDOWN; @@ -552,9 +563,9 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, rtnl_lock(); lock_sock(sk); - if (ro->bound && ro->ifindex) { - dev = dev_get_by_index(sock_net(sk), ro->ifindex); - if (!dev) { + dev = ro->dev; + if (ro->bound && dev) { + if (dev->reg_state != NETREG_REGISTERED) { if (count > 1) kfree(filter); err = -ENODEV; @@ -595,7 +606,6 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, ro->count = count; out_fil: - dev_put(dev); release_sock(sk); rtnl_unlock(); @@ -613,9 +623,9 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, rtnl_lock(); lock_sock(sk); - if (ro->bound && ro->ifindex) { - dev = dev_get_by_index(sock_net(sk), ro->ifindex); - if (!dev) { + dev = ro->dev; + if (ro->bound && dev) { + if (dev->reg_state != NETREG_REGISTERED) { err = -ENODEV; goto out_err; } @@ -639,7 +649,6 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, ro->err_mask = err_mask; out_err: - dev_put(dev); release_sock(sk); rtnl_unlock(); diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 4e4f1e4bc265..c22bb06b450e 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -3334,17 +3334,24 @@ static int linger_reg_commit_wait(struct ceph_osd_linger_request *lreq) int ret; dout("%s lreq %p linger_id %llu\n", __func__, lreq, lreq->linger_id); - ret = wait_for_completion_interruptible(&lreq->reg_commit_wait); + ret = wait_for_completion_killable(&lreq->reg_commit_wait); return ret ?: lreq->reg_commit_error; } -static int linger_notify_finish_wait(struct ceph_osd_linger_request *lreq) +static int linger_notify_finish_wait(struct ceph_osd_linger_request *lreq, + unsigned long timeout) { - int ret; + long left; dout("%s lreq %p linger_id %llu\n", __func__, lreq, lreq->linger_id); - ret = wait_for_completion_interruptible(&lreq->notify_finish_wait); - return ret ?: lreq->notify_finish_error; + left = wait_for_completion_killable_timeout(&lreq->notify_finish_wait, + ceph_timeout_jiffies(timeout)); + if (left <= 0) + left = left ?: -ETIMEDOUT; + else + left = lreq->notify_finish_error; /* completed */ + + return left; } /* @@ -4896,7 +4903,8 @@ int ceph_osdc_notify(struct ceph_osd_client *osdc, linger_submit(lreq); ret = linger_reg_commit_wait(lreq); if (!ret) - ret = linger_notify_finish_wait(lreq); + ret = linger_notify_finish_wait(lreq, + msecs_to_jiffies(2 * timeout * MSEC_PER_SEC)); else dout("lreq %p failed to initiate notify %d\n", lreq, ret); diff --git a/net/core/Makefile b/net/core/Makefile index 5857cec87b83..10edd66a8a37 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -33,7 +33,6 @@ obj-$(CONFIG_LWTUNNEL) += lwtunnel.o obj-$(CONFIG_LWTUNNEL_BPF) += lwt_bpf.o obj-$(CONFIG_DST_CACHE) += dst_cache.o obj-$(CONFIG_HWBM) += hwbm.o -obj-$(CONFIG_NET_DEVLINK) += devlink.o obj-$(CONFIG_GRO_CELLS) += gro_cells.o obj-$(CONFIG_FAILOVER) += failover.o obj-$(CONFIG_NET_SOCK_MSG) += skmsg.o diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index 94374d529ea4..ad01b1bea52e 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -531,8 +531,11 @@ bpf_sk_storage_diag_alloc(const struct nlattr *nla_stgs) return ERR_PTR(-EPERM); nla_for_each_nested(nla, nla_stgs, rem) { - if (nla_type(nla) == SK_DIAG_BPF_STORAGE_REQ_MAP_FD) + if (nla_type(nla) == SK_DIAG_BPF_STORAGE_REQ_MAP_FD) { + if (nla_len(nla) != sizeof(u32)) + return ERR_PTR(-EINVAL); nr_maps++; + } } diag = kzalloc(struct_size(diag, maps, nr_maps), GFP_KERNEL); diff --git a/net/core/filter.c b/net/core/filter.c index da71e6812ab5..419ce7c61bd6 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4064,12 +4064,6 @@ BPF_CALL_2(bpf_xdp_adjust_tail, struct xdp_buff *, xdp, int, offset) if (unlikely(data_end > data_hard_end)) return -EINVAL; - /* ALL drivers MUST init xdp->frame_sz, chicken check below */ - if (unlikely(xdp->frame_sz > PAGE_SIZE)) { - WARN_ONCE(1, "Too BIG xdp->frame_sz = %d\n", xdp->frame_sz); - return -EINVAL; - } - if (unlikely(data_end < xdp->data + ETH_HLEN)) return -EINVAL; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 5625ed30a06f..9d4507aa736b 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2220,13 +2220,27 @@ out_err: return err; } -int rtnl_nla_parse_ifla(struct nlattr **tb, const struct nlattr *head, int len, - struct netlink_ext_ack *exterr) +int rtnl_nla_parse_ifinfomsg(struct nlattr **tb, const struct nlattr *nla_peer, + struct netlink_ext_ack *exterr) { - return nla_parse_deprecated(tb, IFLA_MAX, head, len, ifla_policy, + const struct ifinfomsg *ifmp; + const struct nlattr *attrs; + size_t len; + + ifmp = nla_data(nla_peer); + attrs = nla_data(nla_peer) + sizeof(struct ifinfomsg); + len = nla_len(nla_peer) - sizeof(struct ifinfomsg); + + if (ifmp->ifi_index < 0) { + NL_SET_ERR_MSG_ATTR(exterr, nla_peer, + "ifindex can't be negative"); + return -EINVAL; + } + + return nla_parse_deprecated(tb, IFLA_MAX, attrs, len, ifla_policy, exterr); } -EXPORT_SYMBOL(rtnl_nla_parse_ifla); +EXPORT_SYMBOL(rtnl_nla_parse_ifinfomsg); struct net *rtnl_link_get_net(struct net *src_net, struct nlattr *tb[]) { @@ -3451,6 +3465,9 @@ replay: if (ifm->ifi_index > 0) { link_specified = true; dev = __dev_get_by_index(net, ifm->ifi_index); + } else if (ifm->ifi_index < 0) { + NL_SET_ERR_MSG(extack, "ifindex can't be negative"); + return -EINVAL; } else if (tb[IFLA_IFNAME] || tb[IFLA_ALT_IFNAME]) { link_specified = true; dev = rtnl_dev_get(net, tb); @@ -5030,13 +5047,17 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); if (br_spec) { nla_for_each_nested(attr, br_spec, rem) { - if (nla_type(attr) == IFLA_BRIDGE_FLAGS) { + if (nla_type(attr) == IFLA_BRIDGE_FLAGS && !have_flags) { if (nla_len(attr) < sizeof(flags)) return -EINVAL; have_flags = true; flags = nla_get_u16(attr); - break; + } + + if (nla_type(attr) == IFLA_BRIDGE_MODE) { + if (nla_len(attr) < sizeof(u16)) + return -EINVAL; } } } diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 65fb6f5b21b2..296e45b6c3c0 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -1117,13 +1117,19 @@ static void sk_psock_strp_data_ready(struct sock *sk) int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock) { + int ret; + static const struct strp_callbacks cb = { .rcv_msg = sk_psock_strp_read, .read_sock_done = sk_psock_strp_read_done, .parse_msg = sk_psock_strp_parse, }; - return strp_init(&psock->strp, sk, &cb); + ret = strp_init(&psock->strp, sk, &cb); + if (!ret) + sk_psock_set_state(psock, SK_PSOCK_RX_STRP_ENABLED); + + return ret; } void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock) @@ -1151,7 +1157,7 @@ void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock) static void sk_psock_done_strp(struct sk_psock *psock) { /* Parser has been stopped */ - if (psock->progs.stream_parser) + if (sk_psock_test_state(psock, SK_PSOCK_RX_STRP_ENABLED)) strp_done(&psock->strp); } #else diff --git a/net/core/sock.c b/net/core/sock.c index 0c1baa5517f1..509773919d30 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -800,7 +800,7 @@ EXPORT_SYMBOL(sock_no_linger); void sock_set_priority(struct sock *sk, u32 priority) { lock_sock(sk); - sk->sk_priority = priority; + WRITE_ONCE(sk->sk_priority, priority); release_sock(sk); } EXPORT_SYMBOL(sock_set_priority); @@ -977,7 +977,7 @@ EXPORT_SYMBOL(sock_set_rcvbuf); static void __sock_set_mark(struct sock *sk, u32 val) { if (val != sk->sk_mark) { - sk->sk_mark = val; + WRITE_ONCE(sk->sk_mark, val); sk_dst_reset(sk); } } @@ -996,7 +996,7 @@ static void sock_release_reserved_memory(struct sock *sk, int bytes) bytes = round_down(bytes, PAGE_SIZE); WARN_ON(bytes > sk->sk_reserved_mem); - sk->sk_reserved_mem -= bytes; + WRITE_ONCE(sk->sk_reserved_mem, sk->sk_reserved_mem - bytes); sk_mem_reclaim(sk); } @@ -1033,7 +1033,8 @@ static int sock_reserve_memory(struct sock *sk, int bytes) } sk->sk_forward_alloc += pages << PAGE_SHIFT; - sk->sk_reserved_mem += pages << PAGE_SHIFT; + WRITE_ONCE(sk->sk_reserved_mem, + sk->sk_reserved_mem + (pages << PAGE_SHIFT)); return 0; } @@ -1202,7 +1203,7 @@ set_sndbuf: if ((val >= 0 && val <= 6) || sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) || sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) - sk->sk_priority = val; + WRITE_ONCE(sk->sk_priority, val); else ret = -EPERM; break; @@ -1425,7 +1426,8 @@ set_sndbuf: cmpxchg(&sk->sk_pacing_status, SK_PACING_NONE, SK_PACING_NEEDED); - sk->sk_max_pacing_rate = ulval; + /* Pairs with READ_ONCE() from sk_getsockopt() */ + WRITE_ONCE(sk->sk_max_pacing_rate, ulval); sk->sk_pacing_rate = min(sk->sk_pacing_rate, ulval); break; } @@ -1520,7 +1522,9 @@ set_sndbuf: } if ((u8)val == SOCK_TXREHASH_DEFAULT) val = READ_ONCE(sock_net(sk)->core.sysctl_txrehash); - /* Paired with READ_ONCE() in tcp_rtx_synack() */ + /* Paired with READ_ONCE() in tcp_rtx_synack() + * and sk_getsockopt(). + */ WRITE_ONCE(sk->sk_txrehash, (u8)val); break; @@ -1620,11 +1624,11 @@ int sk_getsockopt(struct sock *sk, int level, int optname, break; case SO_SNDBUF: - v.val = sk->sk_sndbuf; + v.val = READ_ONCE(sk->sk_sndbuf); break; case SO_RCVBUF: - v.val = sk->sk_rcvbuf; + v.val = READ_ONCE(sk->sk_rcvbuf); break; case SO_REUSEADDR: @@ -1666,7 +1670,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname, break; case SO_PRIORITY: - v.val = sk->sk_priority; + v.val = READ_ONCE(sk->sk_priority); break; case SO_LINGER: @@ -1713,7 +1717,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname, break; case SO_RCVLOWAT: - v.val = sk->sk_rcvlowat; + v.val = READ_ONCE(sk->sk_rcvlowat); break; case SO_SNDLOWAT: @@ -1792,7 +1796,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname, return security_socket_getpeersec_stream(sock, optval.user, optlen.user, len); case SO_MARK: - v.val = sk->sk_mark; + v.val = READ_ONCE(sk->sk_mark); break; case SO_RCVMARK: @@ -1811,7 +1815,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname, if (!sock->ops->set_peek_off) return -EOPNOTSUPP; - v.val = sk->sk_peek_off; + v.val = READ_ONCE(sk->sk_peek_off); break; case SO_NOFCS: v.val = sock_flag(sk, SOCK_NOFCS); @@ -1841,7 +1845,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname, #ifdef CONFIG_NET_RX_BUSY_POLL case SO_BUSY_POLL: - v.val = sk->sk_ll_usec; + v.val = READ_ONCE(sk->sk_ll_usec); break; case SO_PREFER_BUSY_POLL: v.val = READ_ONCE(sk->sk_prefer_busy_poll); @@ -1849,12 +1853,14 @@ int sk_getsockopt(struct sock *sk, int level, int optname, #endif case SO_MAX_PACING_RATE: + /* The READ_ONCE() pair with the WRITE_ONCE() in sk_setsockopt() */ if (sizeof(v.ulval) != sizeof(v.val) && len >= sizeof(v.ulval)) { lv = sizeof(v.ulval); - v.ulval = sk->sk_max_pacing_rate; + v.ulval = READ_ONCE(sk->sk_max_pacing_rate); } else { /* 32bit version */ - v.val = min_t(unsigned long, sk->sk_max_pacing_rate, ~0U); + v.val = min_t(unsigned long, ~0U, + READ_ONCE(sk->sk_max_pacing_rate)); } break; @@ -1922,11 +1928,12 @@ int sk_getsockopt(struct sock *sk, int level, int optname, break; case SO_RESERVE_MEM: - v.val = sk->sk_reserved_mem; + v.val = READ_ONCE(sk->sk_reserved_mem); break; case SO_TXREHASH: - v.val = sk->sk_txrehash; + /* Paired with WRITE_ONCE() in sk_setsockopt() */ + v.val = READ_ONCE(sk->sk_txrehash); break; default: @@ -3092,7 +3099,7 @@ void __sk_mem_reduce_allocated(struct sock *sk, int amount) if (mem_cgroup_sockets_enabled && sk->sk_memcg) mem_cgroup_uncharge_skmem(sk->sk_memcg, amount); - if (sk_under_memory_pressure(sk) && + if (sk_under_global_memory_pressure(sk) && (sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0))) sk_leave_memory_pressure(sk); } @@ -3112,7 +3119,7 @@ EXPORT_SYMBOL(__sk_mem_reclaim); int sk_set_peek_off(struct sock *sk, int val) { - sk->sk_peek_off = val; + WRITE_ONCE(sk->sk_peek_off, val); return 0; } EXPORT_SYMBOL_GPL(sk_set_peek_off); diff --git a/net/core/sock_map.c b/net/core/sock_map.c index d38267201892..96db7409baa1 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -117,7 +117,6 @@ static void sock_map_sk_acquire(struct sock *sk) __acquires(&sk->sk_lock.slock) { lock_sock(sk); - preempt_disable(); rcu_read_lock(); } @@ -125,7 +124,6 @@ static void sock_map_sk_release(struct sock *sk) __releases(&sk->sk_lock.slock) { rcu_read_unlock(); - preempt_enable(); release_sock(sk); } @@ -150,13 +148,13 @@ static void sock_map_del_link(struct sock *sk, list_for_each_entry_safe(link, tmp, &psock->link, list) { if (link->link_raw == link_raw) { struct bpf_map *map = link->map; - struct bpf_stab *stab = container_of(map, struct bpf_stab, - map); - if (psock->saved_data_ready && stab->progs.stream_parser) + struct sk_psock_progs *progs = sock_map_progs(map); + + if (psock->saved_data_ready && progs->stream_parser) strp_stop = true; - if (psock->saved_data_ready && stab->progs.stream_verdict) + if (psock->saved_data_ready && progs->stream_verdict) verdict_stop = true; - if (psock->saved_data_ready && stab->progs.skb_verdict) + if (psock->saved_data_ready && progs->skb_verdict) verdict_stop = true; list_del(&link->list); sk_psock_free_link(link); diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index dc4fb699b56c..d2981e89d363 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -946,7 +946,7 @@ static int dcbnl_bcn_setcfg(struct net_device *netdev, struct nlmsghdr *nlh, return -EOPNOTSUPP; ret = nla_parse_nested_deprecated(data, DCB_BCN_ATTR_MAX, - tb[DCB_ATTR_BCN], dcbnl_pfc_up_nest, + tb[DCB_ATTR_BCN], dcbnl_bcn_nest, NULL); if (ret) return ret; diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index b780827f5e0a..bfececa9e244 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -130,7 +130,7 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) inet->inet_daddr, inet->inet_sport, inet->inet_dport); - inet->inet_id = get_random_u16(); + atomic_set(&inet->inet_id, get_random_u16()); err = dccp_connect(sk); rt = NULL; @@ -430,7 +430,7 @@ struct sock *dccp_v4_request_recv_sock(const struct sock *sk, RCU_INIT_POINTER(newinet->inet_opt, rcu_dereference(ireq->ireq_opt)); newinet->mc_index = inet_iif(skb); newinet->mc_ttl = ip_hdr(skb)->ttl; - newinet->inet_id = get_random_u16(); + atomic_set(&newinet->inet_id, get_random_u16()); if (dst == NULL && (dst = inet_csk_route_child_sock(sk, newsk, req)) == NULL) goto put_and_exit; diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index c0fd8f5f3b94..b51ce6f8ceba 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -237,8 +237,8 @@ static int dccp_v6_send_response(const struct sock *sk, struct request_sock *req opt = ireq->ipv6_opt; if (!opt) opt = rcu_dereference(np->opt); - err = ip6_xmit(sk, skb, &fl6, sk->sk_mark, opt, np->tclass, - sk->sk_priority); + err = ip6_xmit(sk, skb, &fl6, READ_ONCE(sk->sk_mark), opt, + np->tclass, sk->sk_priority); rcu_read_unlock(); err = net_xmit_eval(err); } diff --git a/net/dccp/output.c b/net/dccp/output.c index b8a24734385e..fd2eb148d24d 100644 --- a/net/dccp/output.c +++ b/net/dccp/output.c @@ -187,7 +187,7 @@ unsigned int dccp_sync_mss(struct sock *sk, u32 pmtu) /* And store cached results */ icsk->icsk_pmtu_cookie = pmtu; - dp->dccps_mss_cache = cur_mps; + WRITE_ONCE(dp->dccps_mss_cache, cur_mps); return cur_mps; } diff --git a/net/dccp/proto.c b/net/dccp/proto.c index a06b5641287a..c522c76a9f89 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -312,11 +312,15 @@ EXPORT_SYMBOL_GPL(dccp_disconnect); __poll_t dccp_poll(struct file *file, struct socket *sock, poll_table *wait) { - __poll_t mask; struct sock *sk = sock->sk; + __poll_t mask; + u8 shutdown; + int state; sock_poll_wait(file, sock, wait); - if (sk->sk_state == DCCP_LISTEN) + + state = inet_sk_state_load(sk); + if (state == DCCP_LISTEN) return inet_csk_listen_poll(sk); /* Socket is not locked. We are protected from async events @@ -325,20 +329,21 @@ __poll_t dccp_poll(struct file *file, struct socket *sock, */ mask = 0; - if (sk->sk_err) + if (READ_ONCE(sk->sk_err)) mask = EPOLLERR; + shutdown = READ_ONCE(sk->sk_shutdown); - if (sk->sk_shutdown == SHUTDOWN_MASK || sk->sk_state == DCCP_CLOSED) + if (shutdown == SHUTDOWN_MASK || state == DCCP_CLOSED) mask |= EPOLLHUP; - if (sk->sk_shutdown & RCV_SHUTDOWN) + if (shutdown & RCV_SHUTDOWN) mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP; /* Connected? */ - if ((1 << sk->sk_state) & ~(DCCPF_REQUESTING | DCCPF_RESPOND)) { + if ((1 << state) & ~(DCCPF_REQUESTING | DCCPF_RESPOND)) { if (atomic_read(&sk->sk_rmem_alloc) > 0) mask |= EPOLLIN | EPOLLRDNORM; - if (!(sk->sk_shutdown & SEND_SHUTDOWN)) { + if (!(shutdown & SEND_SHUTDOWN)) { if (sk_stream_is_writeable(sk)) { mask |= EPOLLOUT | EPOLLWRNORM; } else { /* send SIGIO later */ @@ -356,7 +361,6 @@ __poll_t dccp_poll(struct file *file, struct socket *sock, } return mask; } - EXPORT_SYMBOL_GPL(dccp_poll); int dccp_ioctl(struct sock *sk, int cmd, unsigned long arg) @@ -627,7 +631,7 @@ static int do_dccp_getsockopt(struct sock *sk, int level, int optname, return dccp_getsockopt_service(sk, len, (__be32 __user *)optval, optlen); case DCCP_SOCKOPT_GET_CUR_MPS: - val = dp->dccps_mss_cache; + val = READ_ONCE(dp->dccps_mss_cache); break; case DCCP_SOCKOPT_AVAILABLE_CCIDS: return ccid_getsockopt_builtin_ccids(sk, len, optval, optlen); @@ -736,7 +740,7 @@ int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) trace_dccp_probe(sk, len); - if (len > dp->dccps_mss_cache) + if (len > READ_ONCE(dp->dccps_mss_cache)) return -EMSGSIZE; lock_sock(sk); @@ -769,6 +773,12 @@ int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) goto out_discard; } + /* We need to check dccps_mss_cache after socket is locked. */ + if (len > dp->dccps_mss_cache) { + rc = -EMSGSIZE; + goto out_discard; + } + skb_reserve(skb, sk->sk_prot->max_header); rc = memcpy_from_msg(skb_put(skb, len), msg, len); if (rc != 0) diff --git a/net/devlink/Makefile b/net/devlink/Makefile new file mode 100644 index 000000000000..3a60959f71ee --- /dev/null +++ b/net/devlink/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 + +obj-y := leftover.o diff --git a/net/core/devlink.c b/net/devlink/leftover.c index 5a4a4b34ac15..63188d6a50fe 100644 --- a/net/core/devlink.c +++ b/net/devlink/leftover.c @@ -9727,6 +9727,7 @@ static void devlink_notify_unregister(struct devlink *devlink) struct devlink_param_item *param_item; struct devlink_trap_item *trap_item; struct devlink_port *devlink_port; + struct devlink_linecard *linecard; struct devlink_rate *rate_node; struct devlink_region *region; @@ -9753,6 +9754,8 @@ static void devlink_notify_unregister(struct devlink *devlink) list_for_each_entry_reverse(devlink_port, &devlink->port_list, list) devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_DEL); + list_for_each_entry_reverse(linecard, &devlink->linecard_list, list) + devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_DEL); devlink_notify(devlink, DEVLINK_CMD_DEL); } diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index ebb737ac9e89..04853c83c85c 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -340,7 +340,7 @@ lookup_protocol: else inet->pmtudisc = IP_PMTUDISC_WANT; - inet->inet_id = 0; + atomic_set(&inet->inet_id, 0); sock_init_data(sock, sk); diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index 4d1af0cd7d99..cb5dbee9e018 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -73,7 +73,7 @@ int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len reuseport_has_conns_set(sk); sk->sk_state = TCP_ESTABLISHED; sk_set_txhash(sk); - inet->inet_id = get_random_u16(); + atomic_set(&inet->inet_id, get_random_u16()); sk_dst_set(sk, &rt->dst); err = 0; diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index b812eb36f0e3..f7426926a104 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -150,7 +150,7 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, } #endif - if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, sk->sk_mark)) + if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, READ_ONCE(sk->sk_mark))) goto errout; if (ext & (1 << (INET_DIAG_CLASS_ID - 1)) || @@ -799,7 +799,7 @@ int inet_diag_bc_sk(const struct nlattr *bc, struct sock *sk) entry.ifindex = sk->sk_bound_dev_if; entry.userlocks = sk_fullsock(sk) ? sk->sk_userlocks : 0; if (sk_fullsock(sk)) - entry.mark = sk->sk_mark; + entry.mark = READ_ONCE(sk->sk_mark); else if (sk->sk_state == TCP_NEW_SYN_RECV) entry.mark = inet_rsk(inet_reqsk(sk))->ir_mark; else if (sk->sk_state == TCP_TIME_WAIT) diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 7b4ab545c06e..acfe58d2f1dd 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -182,9 +182,9 @@ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk, ip_options_build(skb, &opt->opt, daddr, rt); } - skb->priority = sk->sk_priority; + skb->priority = READ_ONCE(sk->sk_priority); if (!skb->mark) - skb->mark = sk->sk_mark; + skb->mark = READ_ONCE(sk->sk_mark); /* Send it out. */ return ip_local_out(net, skb->sk, skb); @@ -526,8 +526,8 @@ packet_routed: skb_shinfo(skb)->gso_segs ?: 1); /* TODO : should we use skb->sk here instead of sk ? */ - skb->priority = sk->sk_priority; - skb->mark = sk->sk_mark; + skb->priority = READ_ONCE(sk->sk_priority); + skb->mark = READ_ONCE(sk->sk_mark); res = ip_local_out(net, sk, skb); rcu_read_unlock(); diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index a7fd035b5b4f..63aa52becd88 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -591,7 +591,7 @@ void __ip_sock_set_tos(struct sock *sk, int val) } if (inet_sk(sk)->tos != val) { inet_sk(sk)->tos = val; - sk->sk_priority = rt_tos2priority(val); + WRITE_ONCE(sk->sk_priority, rt_tos2priority(val)); sk_dst_reset(sk); } } diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 92c02c886fe7..586b1b3e35b8 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -224,7 +224,7 @@ static int iptunnel_pmtud_build_icmp(struct sk_buff *skb, int mtu) .un.frag.__unused = 0, .un.frag.mtu = htons(mtu), }; - icmph->checksum = ip_compute_csum(icmph, len); + icmph->checksum = csum_fold(skb_checksum(skb, 0, len, 0)); skb_reset_transport_header(skb); niph = skb_push(skb, sizeof(*niph)); diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 8c2bd1d9ddce..615c1dcf3a28 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -287,12 +287,12 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) switch (skb->protocol) { case htons(ETH_P_IP): - xfrm_decode_session(skb, &fl, AF_INET); memset(IPCB(skb), 0, sizeof(*IPCB(skb))); + xfrm_decode_session(skb, &fl, AF_INET); break; case htons(ETH_P_IPV6): - xfrm_decode_session(skb, &fl, AF_INET6); memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); + xfrm_decode_session(skb, &fl, AF_INET6); break; default: goto tx_err; diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index d8ef05347fd9..9cc287902454 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -3221,13 +3221,9 @@ static int rtm_dump_nexthop(struct sk_buff *skb, struct netlink_callback *cb) &rtm_dump_nexthop_cb, &filter); if (err < 0) { if (likely(skb->len)) - goto out; - goto out_err; + err = skb->len; } -out: - err = skb->len; -out_err: cb->seq = net->nexthop.seq; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); return err; @@ -3367,25 +3363,19 @@ static int rtm_dump_nexthop_bucket_nh(struct sk_buff *skb, dd->filter.res_bucket_nh_id != nhge->nh->id) continue; + dd->ctx->bucket_index = bucket_index; err = nh_fill_res_bucket(skb, nh, bucket, bucket_index, RTM_NEWNEXTHOPBUCKET, portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->extack); - if (err < 0) { - if (likely(skb->len)) - goto out; - goto out_err; - } + if (err) + return err; } dd->ctx->done_nh_idx = dd->ctx->nh.idx + 1; - bucket_index = 0; + dd->ctx->bucket_index = 0; -out: - err = skb->len; -out_err: - dd->ctx->bucket_index = bucket_index; - return err; + return 0; } static int rtm_dump_nexthop_bucket_cb(struct sk_buff *skb, @@ -3434,13 +3424,9 @@ static int rtm_dump_nexthop_bucket(struct sk_buff *skb, if (err < 0) { if (likely(skb->len)) - goto out; - goto out_err; + err = skb->len; } -out: - err = skb->len; -out_err: cb->seq = net->nexthop.seq; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); return err; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 86197634dcf5..639aa5abda9d 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -346,7 +346,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, goto error; skb_reserve(skb, hlen); - skb->priority = sk->sk_priority; + skb->priority = READ_ONCE(sk->sk_priority); skb->mark = sockc->mark; skb->tstamp = sockc->transmit_time; skb_dst_set(skb, &rt->dst); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index cd1fa9f70f1a..51bd9a50a1d1 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -518,7 +518,7 @@ static void __build_flow_key(const struct net *net, struct flowi4 *fl4, const struct inet_sock *inet = inet_sk(sk); oif = sk->sk_bound_dev_if; - mark = sk->sk_mark; + mark = READ_ONCE(sk->sk_mark); tos = ip_sock_rt_tos(sk); scope = ip_sock_rt_scope(sk); prot = inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol; @@ -552,7 +552,7 @@ static void build_sk_flow_key(struct flowi4 *fl4, const struct sock *sk) inet_opt = rcu_dereference(inet->inet_opt); if (inet_opt && inet_opt->opt.srr) daddr = inet_opt->opt.faddr; - flowi4_init_output(fl4, sk->sk_bound_dev_if, sk->sk_mark, + flowi4_init_output(fl4, sk->sk_bound_dev_if, READ_ONCE(sk->sk_mark), ip_sock_rt_tos(sk) & IPTOS_RT_MASK, ip_sock_rt_scope(sk), inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol, diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 9a8d59e9303a..f9b8a4a1d2ed 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -312,7 +312,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) inet->inet_daddr)); } - inet->inet_id = get_random_u16(); + atomic_set(&inet->inet_id, get_random_u16()); if (tcp_fastopen_defer_connect(sk, &err)) return err; @@ -931,9 +931,9 @@ static void tcp_v4_send_ack(const struct sock *sk, ctl_sk = this_cpu_read(ipv4_tcp_sk); sock_net_set(ctl_sk, net); ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ? - inet_twsk(sk)->tw_mark : sk->sk_mark; + inet_twsk(sk)->tw_mark : READ_ONCE(sk->sk_mark); ctl_sk->sk_priority = (sk->sk_state == TCP_TIME_WAIT) ? - inet_twsk(sk)->tw_priority : sk->sk_priority; + inet_twsk(sk)->tw_priority : READ_ONCE(sk->sk_priority); transmit_time = tcp_transmit_time(sk); ip_send_unicast_reply(ctl_sk, skb, &TCP_SKB_CB(skb)->header.h4.opt, @@ -1539,7 +1539,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, inet_csk(newsk)->icsk_ext_hdr_len = 0; if (inet_opt) inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen; - newinet->inet_id = get_random_u16(); + atomic_set(&newinet->inet_id, get_random_u16()); /* Set ToS of the new socket based upon the value of incoming SYN. * ECT bits are set later in tcp_init_transfer(). diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 82f4575f9cd9..99ac5efe244d 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -40,7 +40,7 @@ struct tcp_fastopen_metrics { struct tcp_metrics_block { struct tcp_metrics_block __rcu *tcpm_next; - possible_net_t tcpm_net; + struct net *tcpm_net; struct inetpeer_addr tcpm_saddr; struct inetpeer_addr tcpm_daddr; unsigned long tcpm_stamp; @@ -51,34 +51,38 @@ struct tcp_metrics_block { struct rcu_head rcu_head; }; -static inline struct net *tm_net(struct tcp_metrics_block *tm) +static inline struct net *tm_net(const struct tcp_metrics_block *tm) { - return read_pnet(&tm->tcpm_net); + /* Paired with the WRITE_ONCE() in tcpm_new() */ + return READ_ONCE(tm->tcpm_net); } static bool tcp_metric_locked(struct tcp_metrics_block *tm, enum tcp_metric_index idx) { - return tm->tcpm_lock & (1 << idx); + /* Paired with WRITE_ONCE() in tcpm_suck_dst() */ + return READ_ONCE(tm->tcpm_lock) & (1 << idx); } -static u32 tcp_metric_get(struct tcp_metrics_block *tm, +static u32 tcp_metric_get(const struct tcp_metrics_block *tm, enum tcp_metric_index idx) { - return tm->tcpm_vals[idx]; + /* Paired with WRITE_ONCE() in tcp_metric_set() */ + return READ_ONCE(tm->tcpm_vals[idx]); } static void tcp_metric_set(struct tcp_metrics_block *tm, enum tcp_metric_index idx, u32 val) { - tm->tcpm_vals[idx] = val; + /* Paired with READ_ONCE() in tcp_metric_get() */ + WRITE_ONCE(tm->tcpm_vals[idx], val); } static bool addr_same(const struct inetpeer_addr *a, const struct inetpeer_addr *b) { - return inetpeer_addr_cmp(a, b) == 0; + return (a->family == b->family) && !inetpeer_addr_cmp(a, b); } struct tcpm_hash_bucket { @@ -89,6 +93,7 @@ static struct tcpm_hash_bucket *tcp_metrics_hash __read_mostly; static unsigned int tcp_metrics_hash_log __read_mostly; static DEFINE_SPINLOCK(tcp_metrics_lock); +static DEFINE_SEQLOCK(fastopen_seqlock); static void tcpm_suck_dst(struct tcp_metrics_block *tm, const struct dst_entry *dst, @@ -97,7 +102,7 @@ static void tcpm_suck_dst(struct tcp_metrics_block *tm, u32 msval; u32 val; - tm->tcpm_stamp = jiffies; + WRITE_ONCE(tm->tcpm_stamp, jiffies); val = 0; if (dst_metric_locked(dst, RTAX_RTT)) @@ -110,30 +115,42 @@ static void tcpm_suck_dst(struct tcp_metrics_block *tm, val |= 1 << TCP_METRIC_CWND; if (dst_metric_locked(dst, RTAX_REORDERING)) val |= 1 << TCP_METRIC_REORDERING; - tm->tcpm_lock = val; + /* Paired with READ_ONCE() in tcp_metric_locked() */ + WRITE_ONCE(tm->tcpm_lock, val); msval = dst_metric_raw(dst, RTAX_RTT); - tm->tcpm_vals[TCP_METRIC_RTT] = msval * USEC_PER_MSEC; + tcp_metric_set(tm, TCP_METRIC_RTT, msval * USEC_PER_MSEC); msval = dst_metric_raw(dst, RTAX_RTTVAR); - tm->tcpm_vals[TCP_METRIC_RTTVAR] = msval * USEC_PER_MSEC; - tm->tcpm_vals[TCP_METRIC_SSTHRESH] = dst_metric_raw(dst, RTAX_SSTHRESH); - tm->tcpm_vals[TCP_METRIC_CWND] = dst_metric_raw(dst, RTAX_CWND); - tm->tcpm_vals[TCP_METRIC_REORDERING] = dst_metric_raw(dst, RTAX_REORDERING); + tcp_metric_set(tm, TCP_METRIC_RTTVAR, msval * USEC_PER_MSEC); + tcp_metric_set(tm, TCP_METRIC_SSTHRESH, + dst_metric_raw(dst, RTAX_SSTHRESH)); + tcp_metric_set(tm, TCP_METRIC_CWND, + dst_metric_raw(dst, RTAX_CWND)); + tcp_metric_set(tm, TCP_METRIC_REORDERING, + dst_metric_raw(dst, RTAX_REORDERING)); if (fastopen_clear) { + write_seqlock(&fastopen_seqlock); tm->tcpm_fastopen.mss = 0; tm->tcpm_fastopen.syn_loss = 0; tm->tcpm_fastopen.try_exp = 0; tm->tcpm_fastopen.cookie.exp = false; tm->tcpm_fastopen.cookie.len = 0; + write_sequnlock(&fastopen_seqlock); } } #define TCP_METRICS_TIMEOUT (60 * 60 * HZ) -static void tcpm_check_stamp(struct tcp_metrics_block *tm, struct dst_entry *dst) +static void tcpm_check_stamp(struct tcp_metrics_block *tm, + const struct dst_entry *dst) { - if (tm && unlikely(time_after(jiffies, tm->tcpm_stamp + TCP_METRICS_TIMEOUT))) + unsigned long limit; + + if (!tm) + return; + limit = READ_ONCE(tm->tcpm_stamp) + TCP_METRICS_TIMEOUT; + if (unlikely(time_after(jiffies, limit))) tcpm_suck_dst(tm, dst, false); } @@ -174,20 +191,23 @@ static struct tcp_metrics_block *tcpm_new(struct dst_entry *dst, oldest = deref_locked(tcp_metrics_hash[hash].chain); for (tm = deref_locked(oldest->tcpm_next); tm; tm = deref_locked(tm->tcpm_next)) { - if (time_before(tm->tcpm_stamp, oldest->tcpm_stamp)) + if (time_before(READ_ONCE(tm->tcpm_stamp), + READ_ONCE(oldest->tcpm_stamp))) oldest = tm; } tm = oldest; } else { - tm = kmalloc(sizeof(*tm), GFP_ATOMIC); + tm = kzalloc(sizeof(*tm), GFP_ATOMIC); if (!tm) goto out_unlock; } - write_pnet(&tm->tcpm_net, net); + /* Paired with the READ_ONCE() in tm_net() */ + WRITE_ONCE(tm->tcpm_net, net); + tm->tcpm_saddr = *saddr; tm->tcpm_daddr = *daddr; - tcpm_suck_dst(tm, dst, true); + tcpm_suck_dst(tm, dst, reclaim); if (likely(!reclaim)) { tm->tcpm_next = tcp_metrics_hash[hash].chain; @@ -434,7 +454,7 @@ void tcp_update_metrics(struct sock *sk) tp->reordering); } } - tm->tcpm_stamp = jiffies; + WRITE_ONCE(tm->tcpm_stamp, jiffies); out_unlock: rcu_read_unlock(); } @@ -539,8 +559,6 @@ bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst) return ret; } -static DEFINE_SEQLOCK(fastopen_seqlock); - void tcp_fastopen_cache_get(struct sock *sk, u16 *mss, struct tcp_fastopen_cookie *cookie) { @@ -647,7 +665,7 @@ static int tcp_metrics_fill_info(struct sk_buff *msg, } if (nla_put_msecs(msg, TCP_METRICS_ATTR_AGE, - jiffies - tm->tcpm_stamp, + jiffies - READ_ONCE(tm->tcpm_stamp), TCP_METRICS_ATTR_PAD) < 0) goto nla_put_failure; @@ -658,7 +676,7 @@ static int tcp_metrics_fill_info(struct sk_buff *msg, if (!nest) goto nla_put_failure; for (i = 0; i < TCP_METRIC_MAX_KERNEL + 1; i++) { - u32 val = tm->tcpm_vals[i]; + u32 val = tcp_metric_get(tm, i); if (!val) continue; diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 0b5d0a2867a8..cf354c29ec12 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -586,7 +586,9 @@ out_reset_timer: tcp_stream_is_thin(tp) && icsk->icsk_retransmits <= TCP_THIN_LINEAR_RETRIES) { icsk->icsk_backoff = 0; - icsk->icsk_rto = min(__tcp_set_rto(tp), TCP_RTO_MAX); + icsk->icsk_rto = clamp(__tcp_set_rto(tp), + tcp_rto_min(sk), + TCP_RTO_MAX); } else { /* Use normal (exponential) backoff */ icsk->icsk_rto = min(icsk->icsk_rto << 1, TCP_RTO_MAX); diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 151337d7f67b..cb71463bbbab 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -570,12 +570,12 @@ vti6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) vti6_addr_conflict(t, ipv6_hdr(skb))) goto tx_err; - xfrm_decode_session(skb, &fl, AF_INET6); memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); + xfrm_decode_session(skb, &fl, AF_INET6); break; case htons(ETH_P_IP): - xfrm_decode_session(skb, &fl, AF_INET); memset(IPCB(skb), 0, sizeof(*IPCB(skb))); + xfrm_decode_session(skb, &fl, AF_INET); break; default: goto tx_err; diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index facdc78a43e5..27fb5479988a 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1073,7 +1073,7 @@ static int ip6mr_cache_report(const struct mr_table *mrt, struct sk_buff *pkt, And all this only to mangle msg->im6_msgtype and to set msg->im6_mbz to "mbz" :-) */ - skb_push(skb, -skb_network_offset(pkt)); + __skb_pull(skb, skb_network_offset(pkt)); skb_push(skb, sizeof(*msg)); skb_reset_transport_header(skb); diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 3a553494ff16..a4d43eb45a9d 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -197,7 +197,8 @@ static struct nd_opt_hdr *ndisc_next_option(struct nd_opt_hdr *cur, static inline int ndisc_is_useropt(const struct net_device *dev, struct nd_opt_hdr *opt) { - return opt->nd_opt_type == ND_OPT_RDNSS || + return opt->nd_opt_type == ND_OPT_PREFIX_INFO || + opt->nd_opt_type == ND_OPT_RDNSS || opt->nd_opt_type == ND_OPT_DNSSL || opt->nd_opt_type == ND_OPT_CAPTIVE_PORTAL || opt->nd_opt_type == ND_OPT_PREF64 || diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index 4651aaf70db4..4d5a27dd9a4b 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -120,7 +120,7 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) ipcm6_init_sk(&ipc6, np); ipc6.sockc.tsflags = sk->sk_tsflags; - ipc6.sockc.mark = sk->sk_mark; + ipc6.sockc.mark = READ_ONCE(sk->sk_mark); fl6.flowi6_oif = oif; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 33852fc38ad9..df3abd9e5237 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -612,7 +612,7 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length, skb_reserve(skb, hlen); skb->protocol = htons(ETH_P_IPV6); - skb->priority = sk->sk_priority; + skb->priority = READ_ONCE(sk->sk_priority); skb->mark = sockc->mark; skb->tstamp = sockc->transmit_time; @@ -772,12 +772,12 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) */ memset(&fl6, 0, sizeof(fl6)); - fl6.flowi6_mark = sk->sk_mark; + fl6.flowi6_mark = READ_ONCE(sk->sk_mark); fl6.flowi6_uid = sk->sk_uid; ipcm6_init(&ipc6); ipc6.sockc.tsflags = sk->sk_tsflags; - ipc6.sockc.mark = sk->sk_mark; + ipc6.sockc.mark = fl6.flowi6_mark; if (sin6) { if (addr_len < SIN6_LEN_RFC2133) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 0b060cb8681f..960ab43a49c4 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2952,7 +2952,8 @@ void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu) if (!oif && skb->dev) oif = l3mdev_master_ifindex(skb->dev); - ip6_update_pmtu(skb, sock_net(sk), mtu, oif, sk->sk_mark, sk->sk_uid); + ip6_update_pmtu(skb, sock_net(sk), mtu, oif, READ_ONCE(sk->sk_mark), + sk->sk_uid); dst = __sk_dst_get(sk); if (!dst || !dst->obsolete || @@ -3173,8 +3174,8 @@ void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif) void ip6_sk_redirect(struct sk_buff *skb, struct sock *sk) { - ip6_redirect(skb, sock_net(sk), sk->sk_bound_dev_if, sk->sk_mark, - sk->sk_uid); + ip6_redirect(skb, sock_net(sk), sk->sk_bound_dev_if, + READ_ONCE(sk->sk_mark), sk->sk_uid); } EXPORT_SYMBOL_GPL(ip6_sk_redirect); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index d9253aa764fa..4bdd356bb5c4 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -567,8 +567,8 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, opt = ireq->ipv6_opt; if (!opt) opt = rcu_dereference(np->opt); - err = ip6_xmit(sk, skb, fl6, skb->mark ? : sk->sk_mark, opt, - tclass, sk->sk_priority); + err = ip6_xmit(sk, skb, fl6, skb->mark ? : READ_ONCE(sk->sk_mark), + opt, tclass, sk->sk_priority); rcu_read_unlock(); err = net_xmit_eval(err); } @@ -943,7 +943,7 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 if (sk->sk_state == TCP_TIME_WAIT) mark = inet_twsk(sk)->tw_mark; else - mark = sk->sk_mark; + mark = READ_ONCE(sk->sk_mark); skb_set_delivery_time(buff, tcp_transmit_time(sk), true); } if (txhash) { @@ -1132,7 +1132,8 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, tcp_time_stamp_raw() + tcp_rsk(req)->ts_off, READ_ONCE(req->ts_recent), sk->sk_bound_dev_if, tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->saddr, l3index), - ipv6_get_dsfield(ipv6_hdr(skb)), 0, sk->sk_priority, + ipv6_get_dsfield(ipv6_hdr(skb)), 0, + READ_ONCE(sk->sk_priority), READ_ONCE(tcp_rsk(req)->txhash)); } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 04f1d696503c..27348172b25b 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -622,7 +622,7 @@ int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (type == NDISC_REDIRECT) { if (tunnel) { ip6_redirect(skb, sock_net(sk), inet6_iif(skb), - sk->sk_mark, sk->sk_uid); + READ_ONCE(sk->sk_mark), sk->sk_uid); } else { ip6_sk_redirect(skb, sk); } @@ -1350,7 +1350,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) ipcm6_init(&ipc6); ipc6.gso_size = READ_ONCE(up->gso_size); ipc6.sockc.tsflags = sk->sk_tsflags; - ipc6.sockc.mark = sk->sk_mark; + ipc6.sockc.mark = READ_ONCE(sk->sk_mark); /* destination address check */ if (sin6) { diff --git a/net/key/af_key.c b/net/key/af_key.c index 8c21de50eadf..8a8f2429d5d9 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -1848,9 +1848,9 @@ static int pfkey_dump(struct sock *sk, struct sk_buff *skb, const struct sadb_ms if (ext_hdrs[SADB_X_EXT_FILTER - 1]) { struct sadb_x_filter *xfilter = ext_hdrs[SADB_X_EXT_FILTER - 1]; - if ((xfilter->sadb_x_filter_splen >= + if ((xfilter->sadb_x_filter_splen > (sizeof(xfrm_address_t) << 3)) || - (xfilter->sadb_x_filter_dplen >= + (xfilter->sadb_x_filter_dplen > (sizeof(xfrm_address_t) << 3))) { mutex_unlock(&pfk->dump_lock); return -EINVAL; diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 5137ea1861ce..bce4132b0a5c 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -519,7 +519,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) /* Get and verify the address */ memset(&fl6, 0, sizeof(fl6)); - fl6.flowi6_mark = sk->sk_mark; + fl6.flowi6_mark = READ_ONCE(sk->sk_mark); fl6.flowi6_uid = sk->sk_uid; ipcm6_init(&ipc6); diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 0f81492da0b4..55dc0610e863 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -1102,7 +1102,8 @@ static inline bool ieee80211_rx_reorder_ready(struct tid_ampdu_rx *tid_agg_rx, struct sk_buff *tail = skb_peek_tail(frames); struct ieee80211_rx_status *status; - if (tid_agg_rx->reorder_buf_filtered & BIT_ULL(index)) + if (tid_agg_rx->reorder_buf_filtered && + tid_agg_rx->reorder_buf_filtered & BIT_ULL(index)) return true; if (!tail) @@ -1143,7 +1144,8 @@ static void ieee80211_release_reorder_frame(struct ieee80211_sub_if_data *sdata, } no_frame: - tid_agg_rx->reorder_buf_filtered &= ~BIT_ULL(index); + if (tid_agg_rx->reorder_buf_filtered) + tid_agg_rx->reorder_buf_filtered &= ~BIT_ULL(index); tid_agg_rx->head_seq_num = ieee80211_sn_inc(tid_agg_rx->head_seq_num); } @@ -4162,6 +4164,7 @@ void ieee80211_mark_rx_ba_filtered_frames(struct ieee80211_sta *pubsta, u8 tid, u16 ssn, u64 filtered, u16 received_mpdus) { + struct ieee80211_local *local; struct sta_info *sta; struct tid_ampdu_rx *tid_agg_rx; struct sk_buff_head frames; @@ -4179,6 +4182,11 @@ void ieee80211_mark_rx_ba_filtered_frames(struct ieee80211_sta *pubsta, u8 tid, sta = container_of(pubsta, struct sta_info, sta); + local = sta->sdata->local; + WARN_ONCE(local->hw.max_rx_aggregation_subframes > 64, + "RX BA marker can't support max_rx_aggregation_subframes %u > 64\n", + local->hw.max_rx_aggregation_subframes); + if (!ieee80211_rx_data_set_sta(&rx, sta, -1)) return; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index f6f2e6417dcb..61fefa1a82db 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2367,7 +2367,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, lock_sock_nested(ssk, SINGLE_DEPTH_NESTING); - if (flags & MPTCP_CF_FASTCLOSE) { + if ((flags & MPTCP_CF_FASTCLOSE) && !__mptcp_check_fallback(msk)) { /* be sure to force the tcp_disconnect() path, * to generate the egress reset */ @@ -3370,7 +3370,7 @@ static void mptcp_release_cb(struct sock *sk) if (__test_and_clear_bit(MPTCP_CLEAN_UNA, &msk->cb_flags)) __mptcp_clean_una_wakeup(sk); - if (unlikely(&msk->cb_flags)) { + if (unlikely(msk->cb_flags)) { /* be sure to set the current sk state before tacking actions * depending on sk_state, that is processing MPTCP_ERROR_REPORT */ diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index fc00dd587a29..d77b25636125 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -312,7 +312,6 @@ struct mptcp_sock { u32 setsockopt_seq; char ca_name[TCP_CA_NAME_MAX]; - struct mptcp_sock *dl_next; }; #define mptcp_data_lock(sk) spin_lock_bh(&(sk)->sk_lock.slock) diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index 696ba398d699..937bd4c55615 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -102,7 +102,7 @@ static void mptcp_sol_socket_sync_intval(struct mptcp_sock *msk, int optname, in break; case SO_MARK: if (READ_ONCE(ssk->sk_mark) != sk->sk_mark) { - ssk->sk_mark = sk->sk_mark; + WRITE_ONCE(ssk->sk_mark, sk->sk_mark); sk_dst_reset(ssk); } break; diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 047e46dd028d..52a747a80e88 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1724,16 +1724,31 @@ static void subflow_state_change(struct sock *sk) void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_ssk) { struct request_sock_queue *queue = &inet_csk(listener_ssk)->icsk_accept_queue; - struct mptcp_sock *msk, *next, *head = NULL; - struct request_sock *req; - struct sock *sk; + struct request_sock *req, *head, *tail; + struct mptcp_subflow_context *subflow; + struct sock *sk, *ssk; - /* build a list of all unaccepted mptcp sockets */ + /* Due to lock dependencies no relevant lock can be acquired under rskq_lock. + * Splice the req list, so that accept() can not reach the pending ssk after + * the listener socket is released below. + */ spin_lock_bh(&queue->rskq_lock); - for (req = queue->rskq_accept_head; req; req = req->dl_next) { - struct mptcp_subflow_context *subflow; - struct sock *ssk = req->sk; + head = queue->rskq_accept_head; + tail = queue->rskq_accept_tail; + queue->rskq_accept_head = NULL; + queue->rskq_accept_tail = NULL; + spin_unlock_bh(&queue->rskq_lock); + + if (!head) + return; + /* can't acquire the msk socket lock under the subflow one, + * or will cause ABBA deadlock + */ + release_sock(listener_ssk); + + for (req = head; req; req = req->dl_next) { + ssk = req->sk; if (!sk_is_mptcp(ssk)) continue; @@ -1741,32 +1756,10 @@ void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_s if (!subflow || !subflow->conn) continue; - /* skip if already in list */ sk = subflow->conn; - msk = mptcp_sk(sk); - if (msk->dl_next || msk == head) - continue; - sock_hold(sk); - msk->dl_next = head; - head = msk; - } - spin_unlock_bh(&queue->rskq_lock); - if (!head) - return; - - /* can't acquire the msk socket lock under the subflow one, - * or will cause ABBA deadlock - */ - release_sock(listener_ssk); - - for (msk = head; msk; msk = next) { - sk = (struct sock *)msk; lock_sock_nested(sk, SINGLE_DEPTH_NESTING); - next = msk->dl_next; - msk->dl_next = NULL; - __mptcp_unaccepted_force_close(sk); release_sock(sk); @@ -1790,6 +1783,13 @@ void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_s /* we are still under the listener msk socket lock */ lock_sock_nested(listener_ssk, SINGLE_DEPTH_NESTING); + + /* restore the listener queue, to let the TCP code clean it up */ + spin_lock_bh(&queue->rskq_lock); + WARN_ON_ONCE(queue->rskq_accept_head); + queue->rskq_accept_head = head; + queue->rskq_accept_tail = tail; + spin_unlock_bh(&queue->rskq_lock); } static int subflow_ulp_init(struct sock *sk) diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 03af6a2ffd56..17a1b731a76b 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -1798,6 +1798,7 @@ static int proc_do_sync_threshold(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { + struct netns_ipvs *ipvs = table->extra2; int *valp = table->data; int val[2]; int rc; @@ -1807,6 +1808,7 @@ proc_do_sync_threshold(struct ctl_table *table, int write, .mode = table->mode, }; + mutex_lock(&ipvs->sync_mutex); memcpy(val, valp, sizeof(val)); rc = proc_dointvec(&tmp, write, buffer, lenp, ppos); if (write) { @@ -1816,6 +1818,7 @@ proc_do_sync_threshold(struct ctl_table *table, int write, else memcpy(valp, val, sizeof(val)); } + mutex_unlock(&ipvs->sync_mutex); return rc; } @@ -4080,6 +4083,7 @@ static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs) ipvs->sysctl_sync_threshold[0] = DEFAULT_SYNC_THRESHOLD; ipvs->sysctl_sync_threshold[1] = DEFAULT_SYNC_PERIOD; tbl[idx].data = &ipvs->sysctl_sync_threshold; + tbl[idx].extra2 = ipvs; tbl[idx++].maxlen = sizeof(ipvs->sysctl_sync_threshold); ipvs->sysctl_sync_refresh_period = DEFAULT_SYNC_REFRESH_PERIOD; tbl[idx++].data = &ipvs->sysctl_sync_refresh_period; diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 895e0ca54299..7247af51bdfc 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -49,8 +49,8 @@ static const unsigned int sctp_timeouts[SCTP_CONNTRACK_MAX] = { [SCTP_CONNTRACK_COOKIE_WAIT] = 3 SECS, [SCTP_CONNTRACK_COOKIE_ECHOED] = 3 SECS, [SCTP_CONNTRACK_ESTABLISHED] = 210 SECS, - [SCTP_CONNTRACK_SHUTDOWN_SENT] = 300 SECS / 1000, - [SCTP_CONNTRACK_SHUTDOWN_RECD] = 300 SECS / 1000, + [SCTP_CONNTRACK_SHUTDOWN_SENT] = 3 SECS, + [SCTP_CONNTRACK_SHUTDOWN_RECD] = 3 SECS, [SCTP_CONNTRACK_SHUTDOWN_ACK_SENT] = 3 SECS, [SCTP_CONNTRACK_HEARTBEAT_SENT] = 30 SECS, }; @@ -105,7 +105,7 @@ static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = { { /* ORIGINAL */ /* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS */ -/* init */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCW}, +/* init */ {sCL, sCL, sCW, sCE, sES, sCL, sCL, sSA, sCW}, /* init_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL}, /* abort */ {sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL}, /* shutdown */ {sCL, sCL, sCW, sCE, sSS, sSS, sSR, sSA, sCL}, diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index dd57a9ebe113..3c5cac9bd9b7 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -255,8 +255,10 @@ int nf_tables_bind_chain(const struct nft_ctx *ctx, struct nft_chain *chain) if (chain->bound) return -EBUSY; + if (!nft_use_inc(&chain->use)) + return -EMFILE; + chain->bound = true; - chain->use++; nft_chain_trans_bind(ctx, chain); return 0; @@ -439,7 +441,7 @@ static int nft_delchain(struct nft_ctx *ctx) if (IS_ERR(trans)) return PTR_ERR(trans); - ctx->table->use--; + nft_use_dec(&ctx->table->use); nft_deactivate_next(ctx->net, ctx->chain); return 0; @@ -478,7 +480,7 @@ nf_tables_delrule_deactivate(struct nft_ctx *ctx, struct nft_rule *rule) /* You cannot delete the same rule twice */ if (nft_is_active_next(ctx->net, rule)) { nft_deactivate_next(ctx->net, rule); - ctx->chain->use--; + nft_use_dec(&ctx->chain->use); return 0; } return -ENOENT; @@ -645,7 +647,7 @@ static int nft_delset(const struct nft_ctx *ctx, struct nft_set *set) nft_map_deactivate(ctx, set); nft_deactivate_next(ctx->net, set); - ctx->table->use--; + nft_use_dec(&ctx->table->use); return err; } @@ -677,7 +679,7 @@ static int nft_delobj(struct nft_ctx *ctx, struct nft_object *obj) return err; nft_deactivate_next(ctx->net, obj); - ctx->table->use--; + nft_use_dec(&ctx->table->use); return err; } @@ -712,7 +714,7 @@ static int nft_delflowtable(struct nft_ctx *ctx, return err; nft_deactivate_next(ctx->net, flowtable); - ctx->table->use--; + nft_use_dec(&ctx->table->use); return err; } @@ -2358,9 +2360,6 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, unsigned int data_size; int err; - if (table->use == UINT_MAX) - return -EOVERFLOW; - if (nla[NFTA_CHAIN_HOOK]) { struct nft_stats __percpu *stats = NULL; struct nft_chain_hook hook; @@ -2457,6 +2456,11 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, if (err < 0) goto err_destroy_chain; + if (!nft_use_inc(&table->use)) { + err = -EMFILE; + goto err_use; + } + trans = nft_trans_chain_add(ctx, NFT_MSG_NEWCHAIN); if (IS_ERR(trans)) { err = PTR_ERR(trans); @@ -2473,10 +2477,11 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, goto err_unregister_hook; } - table->use++; - return 0; + err_unregister_hook: + nft_use_dec_restore(&table->use); +err_use: nf_tables_unregister_hook(net, table, chain); err_destroy_chain: nf_tables_chain_destroy(ctx); @@ -3663,9 +3668,6 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, return -EINVAL; handle = nf_tables_alloc_handle(table); - if (chain->use == UINT_MAX) - return -EOVERFLOW; - if (nla[NFTA_RULE_POSITION]) { pos_handle = be64_to_cpu(nla_get_be64(nla[NFTA_RULE_POSITION])); old_rule = __nft_rule_lookup(chain, pos_handle); @@ -3759,6 +3761,11 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, } } + if (!nft_use_inc(&chain->use)) { + err = -EMFILE; + goto err_release_rule; + } + if (info->nlh->nlmsg_flags & NLM_F_REPLACE) { err = nft_delrule(&ctx, old_rule); if (err < 0) @@ -3790,7 +3797,6 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, } } kvfree(expr_info); - chain->use++; if (flow) nft_trans_flow_rule(trans) = flow; @@ -3801,6 +3807,7 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, return 0; err_destroy_flow_rule: + nft_use_dec_restore(&chain->use); if (flow) nft_flow_rule_destroy(flow); err_release_rule: @@ -4818,9 +4825,15 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, alloc_size = sizeof(*set) + size + udlen; if (alloc_size < size || alloc_size > INT_MAX) return -ENOMEM; + + if (!nft_use_inc(&table->use)) + return -EMFILE; + set = kvzalloc(alloc_size, GFP_KERNEL_ACCOUNT); - if (!set) - return -ENOMEM; + if (!set) { + err = -ENOMEM; + goto err_alloc; + } name = nla_strdup(nla[NFTA_SET_NAME], GFP_KERNEL_ACCOUNT); if (!name) { @@ -4878,7 +4891,7 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, goto err_set_expr_alloc; list_add_tail_rcu(&set->list, &table->sets); - table->use++; + return 0; err_set_expr_alloc: @@ -4890,6 +4903,9 @@ err_set_init: kfree(set->name); err_set_name: kvfree(set); +err_alloc: + nft_use_dec_restore(&table->use); + return err; } @@ -5024,9 +5040,6 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_binding *i; struct nft_set_iter iter; - if (set->use == UINT_MAX) - return -EOVERFLOW; - if (!list_empty(&set->bindings) && nft_set_is_anonymous(set)) return -EBUSY; @@ -5054,10 +5067,12 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, return iter.err; } bind: + if (!nft_use_inc(&set->use)) + return -EMFILE; + binding->chain = ctx->chain; list_add_tail_rcu(&binding->list, &set->bindings); nft_set_trans_bind(ctx, set); - set->use++; return 0; } @@ -5131,7 +5146,7 @@ void nf_tables_activate_set(const struct nft_ctx *ctx, struct nft_set *set) nft_clear(ctx->net, set); } - set->use++; + nft_use_inc_restore(&set->use); } EXPORT_SYMBOL_GPL(nf_tables_activate_set); @@ -5147,7 +5162,7 @@ void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set, else list_del_rcu(&binding->list); - set->use--; + nft_use_dec(&set->use); break; case NFT_TRANS_PREPARE: if (nft_set_is_anonymous(set)) { @@ -5156,7 +5171,7 @@ void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set, nft_deactivate_next(ctx->net, set); } - set->use--; + nft_use_dec(&set->use); return; case NFT_TRANS_ABORT: case NFT_TRANS_RELEASE: @@ -5164,7 +5179,7 @@ void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set, set->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) nft_map_deactivate(ctx, set); - set->use--; + nft_use_dec(&set->use); fallthrough; default: nf_tables_unbind_set(ctx, set, binding, @@ -5933,7 +5948,7 @@ void nft_set_elem_destroy(const struct nft_set *set, void *elem, nft_set_elem_expr_destroy(&ctx, nft_set_ext_expr(ext)); if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF)) - (*nft_set_ext_obj(ext))->use--; + nft_use_dec(&(*nft_set_ext_obj(ext))->use); kfree(elem); } EXPORT_SYMBOL_GPL(nft_set_elem_destroy); @@ -6435,8 +6450,16 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, set->objtype, genmask); if (IS_ERR(obj)) { err = PTR_ERR(obj); + obj = NULL; goto err_parse_key_end; } + + if (!nft_use_inc(&obj->use)) { + err = -EMFILE; + obj = NULL; + goto err_parse_key_end; + } + err = nft_set_ext_add(&tmpl, NFT_SET_EXT_OBJREF); if (err < 0) goto err_parse_key_end; @@ -6505,10 +6528,9 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (flags) *nft_set_ext_flags(ext) = flags; - if (obj) { + if (obj) *nft_set_ext_obj(ext) = obj; - obj->use++; - } + if (ulen > 0) { if (nft_set_ext_check(&tmpl, NFT_SET_EXT_USERDATA, ulen) < 0) { err = -EINVAL; @@ -6573,12 +6595,13 @@ err_element_clash: kfree(trans); err_elem_free: nf_tables_set_elem_destroy(ctx, set, elem.priv); - if (obj) - obj->use--; err_parse_data: if (nla[NFTA_SET_ELEM_DATA] != NULL) nft_data_release(&elem.data.val, desc.type); err_parse_key_end: + if (obj) + nft_use_dec_restore(&obj->use); + nft_data_release(&elem.key_end.val, NFT_DATA_VALUE); err_parse_key: nft_data_release(&elem.key.val, NFT_DATA_VALUE); @@ -6659,7 +6682,7 @@ void nft_data_hold(const struct nft_data *data, enum nft_data_types type) case NFT_JUMP: case NFT_GOTO: chain = data->verdict.chain; - chain->use++; + nft_use_inc_restore(&chain->use); break; } } @@ -6674,7 +6697,7 @@ static void nft_setelem_data_activate(const struct net *net, if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA)) nft_data_hold(nft_set_ext_data(ext), set->dtype); if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF)) - (*nft_set_ext_obj(ext))->use++; + nft_use_inc_restore(&(*nft_set_ext_obj(ext))->use); } static void nft_setelem_data_deactivate(const struct net *net, @@ -6686,7 +6709,7 @@ static void nft_setelem_data_deactivate(const struct net *net, if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA)) nft_data_release(nft_set_ext_data(ext), set->dtype); if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF)) - (*nft_set_ext_obj(ext))->use--; + nft_use_dec(&(*nft_set_ext_obj(ext))->use); } static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, @@ -6851,6 +6874,7 @@ static int nft_set_catchall_flush(const struct nft_ctx *ctx, ret = __nft_set_catchall_flush(ctx, set, &elem); if (ret < 0) break; + nft_set_elem_change_active(ctx->net, set, ext); } return ret; @@ -7225,9 +7249,14 @@ static int nf_tables_newobj(struct sk_buff *skb, const struct nfnl_info *info, nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); + if (!nft_use_inc(&table->use)) + return -EMFILE; + type = nft_obj_type_get(net, objtype); - if (IS_ERR(type)) - return PTR_ERR(type); + if (IS_ERR(type)) { + err = PTR_ERR(type); + goto err_type; + } obj = nft_obj_init(&ctx, type, nla[NFTA_OBJ_DATA]); if (IS_ERR(obj)) { @@ -7261,7 +7290,7 @@ static int nf_tables_newobj(struct sk_buff *skb, const struct nfnl_info *info, goto err_obj_ht; list_add_tail_rcu(&obj->list, &table->objects); - table->use++; + return 0; err_obj_ht: /* queued in transaction log */ @@ -7277,6 +7306,9 @@ err_strdup: kfree(obj); err_init: module_put(type->owner); +err_type: + nft_use_dec_restore(&table->use); + return err; } @@ -7667,7 +7699,7 @@ void nf_tables_deactivate_flowtable(const struct nft_ctx *ctx, case NFT_TRANS_PREPARE: case NFT_TRANS_ABORT: case NFT_TRANS_RELEASE: - flowtable->use--; + nft_use_dec(&flowtable->use); fallthrough; default: return; @@ -8015,9 +8047,14 @@ static int nf_tables_newflowtable(struct sk_buff *skb, nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); + if (!nft_use_inc(&table->use)) + return -EMFILE; + flowtable = kzalloc(sizeof(*flowtable), GFP_KERNEL_ACCOUNT); - if (!flowtable) - return -ENOMEM; + if (!flowtable) { + err = -ENOMEM; + goto flowtable_alloc; + } flowtable->table = table; flowtable->handle = nf_tables_alloc_handle(table); @@ -8072,7 +8109,6 @@ static int nf_tables_newflowtable(struct sk_buff *skb, goto err5; list_add_tail_rcu(&flowtable->list, &table->flowtables); - table->use++; return 0; err5: @@ -8089,6 +8125,9 @@ err2: kfree(flowtable->name); err1: kfree(flowtable); +flowtable_alloc: + nft_use_dec_restore(&table->use); + return err; } @@ -9374,7 +9413,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) */ if (nft_set_is_anonymous(nft_trans_set(trans)) && !list_empty(&nft_trans_set(trans)->bindings)) - trans->ctx.table->use--; + nft_use_dec(&trans->ctx.table->use); } nf_tables_set_notify(&trans->ctx, nft_trans_set(trans), NFT_MSG_NEWSET, GFP_KERNEL); @@ -9593,7 +9632,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nft_trans_destroy(trans); break; } - trans->ctx.table->use--; + nft_use_dec_restore(&trans->ctx.table->use); nft_chain_del(trans->ctx.chain); nf_tables_unregister_hook(trans->ctx.net, trans->ctx.table, @@ -9601,7 +9640,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) } break; case NFT_MSG_DELCHAIN: - trans->ctx.table->use++; + nft_use_inc_restore(&trans->ctx.table->use); nft_clear(trans->ctx.net, trans->ctx.chain); nft_trans_destroy(trans); break; @@ -9610,7 +9649,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nft_trans_destroy(trans); break; } - trans->ctx.chain->use--; + nft_use_dec_restore(&trans->ctx.chain->use); list_del_rcu(&nft_trans_rule(trans)->list); nft_rule_expr_deactivate(&trans->ctx, nft_trans_rule(trans), @@ -9619,7 +9658,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nft_flow_rule_destroy(nft_trans_flow_rule(trans)); break; case NFT_MSG_DELRULE: - trans->ctx.chain->use++; + nft_use_inc_restore(&trans->ctx.chain->use); nft_clear(trans->ctx.net, nft_trans_rule(trans)); nft_rule_expr_activate(&trans->ctx, nft_trans_rule(trans)); if (trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD) @@ -9632,7 +9671,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nft_trans_destroy(trans); break; } - trans->ctx.table->use--; + nft_use_dec_restore(&trans->ctx.table->use); if (nft_trans_set_bound(trans)) { nft_trans_destroy(trans); break; @@ -9640,7 +9679,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) list_del_rcu(&nft_trans_set(trans)->list); break; case NFT_MSG_DELSET: - trans->ctx.table->use++; + nft_use_inc_restore(&trans->ctx.table->use); nft_clear(trans->ctx.net, nft_trans_set(trans)); if (nft_trans_set(trans)->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) nft_map_activate(&trans->ctx, nft_trans_set(trans)); @@ -9683,12 +9722,12 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nft_obj_destroy(&trans->ctx, nft_trans_obj_newobj(trans)); nft_trans_destroy(trans); } else { - trans->ctx.table->use--; + nft_use_dec_restore(&trans->ctx.table->use); nft_obj_del(nft_trans_obj(trans)); } break; case NFT_MSG_DELOBJ: - trans->ctx.table->use++; + nft_use_inc_restore(&trans->ctx.table->use); nft_clear(trans->ctx.net, nft_trans_obj(trans)); nft_trans_destroy(trans); break; @@ -9697,7 +9736,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nft_unregister_flowtable_net_hooks(net, &nft_trans_flowtable_hooks(trans)); } else { - trans->ctx.table->use--; + nft_use_dec_restore(&trans->ctx.table->use); list_del_rcu(&nft_trans_flowtable(trans)->list); nft_unregister_flowtable_net_hooks(net, &nft_trans_flowtable(trans)->hook_list); @@ -9708,7 +9747,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) list_splice(&nft_trans_flowtable_hooks(trans), &nft_trans_flowtable(trans)->hook_list); } else { - trans->ctx.table->use++; + nft_use_inc_restore(&trans->ctx.table->use); nft_clear(trans->ctx.net, nft_trans_flowtable(trans)); } nft_trans_destroy(trans); @@ -10161,8 +10200,9 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, if (desc->flags & NFT_DATA_DESC_SETELEM && chain->flags & NFT_CHAIN_BINDING) return -EINVAL; + if (!nft_use_inc(&chain->use)) + return -EMFILE; - chain->use++; data->verdict.chain = chain; break; } @@ -10180,7 +10220,7 @@ static void nft_verdict_uninit(const struct nft_data *data) case NFT_JUMP: case NFT_GOTO: chain = data->verdict.chain; - chain->use--; + nft_use_dec(&chain->use); break; } } @@ -10349,11 +10389,11 @@ int __nft_release_basechain(struct nft_ctx *ctx) nf_tables_unregister_hook(ctx->net, ctx->chain->table, ctx->chain); list_for_each_entry_safe(rule, nr, &ctx->chain->rules, list) { list_del(&rule->list); - ctx->chain->use--; + nft_use_dec(&ctx->chain->use); nf_tables_rule_release(ctx, rule); } nft_chain_del(ctx->chain); - ctx->table->use--; + nft_use_dec(&ctx->table->use); nf_tables_chain_destroy(ctx); return 0; @@ -10406,18 +10446,18 @@ static void __nft_release_table(struct net *net, struct nft_table *table) ctx.chain = chain; list_for_each_entry_safe(rule, nr, &chain->rules, list) { list_del(&rule->list); - chain->use--; + nft_use_dec(&chain->use); nf_tables_rule_release(&ctx, rule); } } list_for_each_entry_safe(flowtable, nf, &table->flowtables, list) { list_del(&flowtable->list); - table->use--; + nft_use_dec(&table->use); nf_tables_flowtable_destroy(flowtable); } list_for_each_entry_safe(set, ns, &table->sets, list) { list_del(&set->list); - table->use--; + nft_use_dec(&table->use); if (set->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) nft_map_deactivate(&ctx, set); @@ -10425,13 +10465,13 @@ static void __nft_release_table(struct net *net, struct nft_table *table) } list_for_each_entry_safe(obj, ne, &table->objects, list) { nft_obj_del(obj); - table->use--; + nft_use_dec(&table->use); nft_obj_destroy(&ctx, obj); } list_for_each_entry_safe(chain, nc, &table->chains, list) { ctx.chain = chain; nft_chain_del(chain); - table->use--; + nft_use_dec(&table->use); nf_tables_chain_destroy(&ctx); } nf_tables_table_destroy(&ctx); @@ -10469,7 +10509,7 @@ static int nft_rcv_nl_event(struct notifier_block *this, unsigned long event, deleted = 0; mutex_lock(&nft_net->commit_mutex); if (!list_empty(&nf_tables_destroy_list)) - rcu_barrier(); + nf_tables_trans_destroy_flush_work(); again: list_for_each_entry(table, &nft_net->tables, list) { if (nft_table_has_owner(table) && diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index e65a83328b55..cf9a1ae87d9b 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -191,6 +191,9 @@ static int nft_dynset_init(const struct nft_ctx *ctx, if (IS_ERR(set)) return PTR_ERR(set); + if (set->flags & NFT_SET_OBJECT) + return -EOPNOTSUPP; + if (set->ops->update == NULL) return -EOPNOTSUPP; diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index a25c88bc8b75..8a43f6f9c90b 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -404,8 +404,10 @@ static int nft_flow_offload_init(const struct nft_ctx *ctx, if (IS_ERR(flowtable)) return PTR_ERR(flowtable); + if (!nft_use_inc(&flowtable->use)) + return -EMFILE; + priv->flowtable = flowtable; - flowtable->use++; return nf_ct_netns_get(ctx->net, ctx->family); } @@ -424,7 +426,7 @@ static void nft_flow_offload_activate(const struct nft_ctx *ctx, { struct nft_flow_offload *priv = nft_expr_priv(expr); - priv->flowtable->use++; + nft_use_inc_restore(&priv->flowtable->use); } static void nft_flow_offload_destroy(const struct nft_ctx *ctx, diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c index 391c18e4b3eb..5f59dbab3e93 100644 --- a/net/netfilter/nft_immediate.c +++ b/net/netfilter/nft_immediate.c @@ -168,7 +168,7 @@ static void nft_immediate_deactivate(const struct nft_ctx *ctx, nft_immediate_chain_deactivate(ctx, chain, phase); nft_chain_del(chain); chain->bound = false; - chain->table->use--; + nft_use_dec(&chain->table->use); break; } break; @@ -207,7 +207,7 @@ static void nft_immediate_destroy(const struct nft_ctx *ctx, * let the transaction records release this chain and its rules. */ if (chain->bound) { - chain->use--; + nft_use_dec(&chain->use); break; } @@ -215,9 +215,9 @@ static void nft_immediate_destroy(const struct nft_ctx *ctx, chain_ctx = *ctx; chain_ctx.chain = chain; - chain->use--; + nft_use_dec(&chain->use); list_for_each_entry_safe(rule, n, &chain->rules, list) { - chain->use--; + nft_use_dec(&chain->use); list_del(&rule->list); nf_tables_rule_destroy(&chain_ctx, rule); } diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c index 7f8e480b6be5..0017bd341872 100644 --- a/net/netfilter/nft_objref.c +++ b/net/netfilter/nft_objref.c @@ -41,8 +41,10 @@ static int nft_objref_init(const struct nft_ctx *ctx, if (IS_ERR(obj)) return -ENOENT; + if (!nft_use_inc(&obj->use)) + return -EMFILE; + nft_objref_priv(expr) = obj; - obj->use++; return 0; } @@ -71,7 +73,7 @@ static void nft_objref_deactivate(const struct nft_ctx *ctx, if (phase == NFT_TRANS_COMMIT) return; - obj->use--; + nft_use_dec(&obj->use); } static void nft_objref_activate(const struct nft_ctx *ctx, @@ -79,7 +81,7 @@ static void nft_objref_activate(const struct nft_ctx *ctx, { struct nft_object *obj = nft_objref_priv(expr); - obj->use++; + nft_use_inc_restore(&obj->use); } static struct nft_expr_type nft_objref_type; diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index a81829c10fea..8c16681884b7 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -901,12 +901,14 @@ static void pipapo_lt_bits_adjust(struct nft_pipapo_field *f) static int pipapo_insert(struct nft_pipapo_field *f, const uint8_t *k, int mask_bits) { - int rule = f->rules++, group, ret, bit_offset = 0; + int rule = f->rules, group, ret, bit_offset = 0; - ret = pipapo_resize(f, f->rules - 1, f->rules); + ret = pipapo_resize(f, f->rules, f->rules + 1); if (ret) return ret; + f->rules++; + for (group = 0; group < f->groups; group++) { int i, v; u8 mask; @@ -1051,7 +1053,9 @@ static int pipapo_expand(struct nft_pipapo_field *f, step++; if (step >= len) { if (!masks) { - pipapo_insert(f, base, 0); + err = pipapo_insert(f, base, 0); + if (err < 0) + return err; masks = 1; } goto out; @@ -1234,6 +1238,9 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, else ret = pipapo_expand(f, start, end, f->groups * f->bb); + if (ret < 0) + return ret; + if (f->bsize > bsize_max) bsize_max = f->bsize; @@ -1665,6 +1672,17 @@ static void nft_pipapo_commit(const struct nft_set *set) priv->clone = new_clone; } +static bool nft_pipapo_transaction_mutex_held(const struct nft_set *set) +{ +#ifdef CONFIG_PROVE_LOCKING + const struct net *net = read_pnet(&set->net); + + return lockdep_is_held(&nft_pernet(net)->commit_mutex); +#else + return true; +#endif +} + static void nft_pipapo_abort(const struct nft_set *set) { struct nft_pipapo *priv = nft_set_priv(set); @@ -1673,7 +1691,7 @@ static void nft_pipapo_abort(const struct nft_set *set) if (!priv->dirty) return; - m = rcu_dereference(priv->match); + m = rcu_dereference_protected(priv->match, nft_pipapo_transaction_mutex_held(set)); new_clone = pipapo_clone(m); if (IS_ERR(new_clone)) diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c index 49a5348a6a14..777561b71fcb 100644 --- a/net/netfilter/nft_socket.c +++ b/net/netfilter/nft_socket.c @@ -107,7 +107,7 @@ static void nft_socket_eval(const struct nft_expr *expr, break; case NFT_SOCKET_MARK: if (sk_fullsock(sk)) { - *dest = sk->sk_mark; + *dest = READ_ONCE(sk->sk_mark); } else { regs->verdict.code = NFT_BREAK; return; diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c index 7013f55f05d1..76e01f292aaf 100644 --- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -77,7 +77,7 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par, if (info->flags & XT_SOCKET_RESTORESKMARK && !wildcard && transparent && sk_fullsock(sk)) - pskb->mark = sk->sk_mark; + pskb->mark = READ_ONCE(sk->sk_mark); if (sk != skb->sk) sock_gen_put(sk); @@ -138,7 +138,7 @@ socket_mt6_v1_v2_v3(const struct sk_buff *skb, struct xt_action_param *par) if (info->flags & XT_SOCKET_RESTORESKMARK && !wildcard && transparent && sk_fullsock(sk)) - pskb->mark = sk->sk_mark; + pskb->mark = READ_ONCE(sk->sk_mark); if (sk != skb->sk) sock_gen_put(sk); diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 5920fdca1287..3c7b24535409 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -1806,7 +1806,7 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info) parms.port_no = OVSP_LOCAL; parms.upcall_portids = a[OVS_DP_ATTR_UPCALL_PID]; parms.desired_ifindex = a[OVS_DP_ATTR_IFINDEX] - ? nla_get_u32(a[OVS_DP_ATTR_IFINDEX]) : 0; + ? nla_get_s32(a[OVS_DP_ATTR_IFINDEX]) : 0; /* So far only local changes have been made, now need the lock. */ ovs_lock(); @@ -2026,7 +2026,7 @@ static const struct nla_policy datapath_policy[OVS_DP_ATTR_MAX + 1] = { [OVS_DP_ATTR_USER_FEATURES] = { .type = NLA_U32 }, [OVS_DP_ATTR_MASKS_CACHE_SIZE] = NLA_POLICY_RANGE(NLA_U32, 0, PCPU_MIN_UNIT_SIZE / sizeof(struct mask_cache_entry)), - [OVS_DP_ATTR_IFINDEX] = {.type = NLA_U32 }, + [OVS_DP_ATTR_IFINDEX] = NLA_POLICY_MIN(NLA_S32, 0), }; static const struct genl_small_ops dp_datapath_genl_ops[] = { @@ -2276,7 +2276,7 @@ restart: parms.port_no = port_no; parms.upcall_portids = a[OVS_VPORT_ATTR_UPCALL_PID]; parms.desired_ifindex = a[OVS_VPORT_ATTR_IFINDEX] - ? nla_get_u32(a[OVS_VPORT_ATTR_IFINDEX]) : 0; + ? nla_get_s32(a[OVS_VPORT_ATTR_IFINDEX]) : 0; vport = new_vport(&parms); err = PTR_ERR(vport); @@ -2513,7 +2513,7 @@ static const struct nla_policy vport_policy[OVS_VPORT_ATTR_MAX + 1] = { [OVS_VPORT_ATTR_TYPE] = { .type = NLA_U32 }, [OVS_VPORT_ATTR_UPCALL_PID] = { .type = NLA_UNSPEC }, [OVS_VPORT_ATTR_OPTIONS] = { .type = NLA_NESTED }, - [OVS_VPORT_ATTR_IFINDEX] = { .type = NLA_U32 }, + [OVS_VPORT_ATTR_IFINDEX] = NLA_POLICY_MIN(NLA_S32, 0), [OVS_VPORT_ATTR_NETNSID] = { .type = NLA_S32 }, }; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 6ab9d5b54338..451bd8bfafd2 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -404,18 +404,20 @@ static void __packet_set_status(struct packet_sock *po, void *frame, int status) { union tpacket_uhdr h; + /* WRITE_ONCE() are paired with READ_ONCE() in __packet_get_status */ + h.raw = frame; switch (po->tp_version) { case TPACKET_V1: - h.h1->tp_status = status; + WRITE_ONCE(h.h1->tp_status, status); flush_dcache_page(pgv_to_page(&h.h1->tp_status)); break; case TPACKET_V2: - h.h2->tp_status = status; + WRITE_ONCE(h.h2->tp_status, status); flush_dcache_page(pgv_to_page(&h.h2->tp_status)); break; case TPACKET_V3: - h.h3->tp_status = status; + WRITE_ONCE(h.h3->tp_status, status); flush_dcache_page(pgv_to_page(&h.h3->tp_status)); break; default: @@ -432,17 +434,19 @@ static int __packet_get_status(const struct packet_sock *po, void *frame) smp_rmb(); + /* READ_ONCE() are paired with WRITE_ONCE() in __packet_set_status */ + h.raw = frame; switch (po->tp_version) { case TPACKET_V1: flush_dcache_page(pgv_to_page(&h.h1->tp_status)); - return h.h1->tp_status; + return READ_ONCE(h.h1->tp_status); case TPACKET_V2: flush_dcache_page(pgv_to_page(&h.h2->tp_status)); - return h.h2->tp_status; + return READ_ONCE(h.h2->tp_status); case TPACKET_V3: flush_dcache_page(pgv_to_page(&h.h3->tp_status)); - return h.h3->tp_status; + return READ_ONCE(h.h3->tp_status); default: WARN(1, "TPACKET version not supported.\n"); BUG(); @@ -2052,8 +2056,8 @@ retry: skb->protocol = proto; skb->dev = dev; - skb->priority = sk->sk_priority; - skb->mark = sk->sk_mark; + skb->priority = READ_ONCE(sk->sk_priority); + skb->mark = READ_ONCE(sk->sk_mark); skb->tstamp = sockc.transmit_time; skb_setup_tx_timestamp(skb, sockc.tsflags); @@ -2575,8 +2579,8 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, skb->protocol = proto; skb->dev = dev; - skb->priority = po->sk.sk_priority; - skb->mark = po->sk.sk_mark; + skb->priority = READ_ONCE(po->sk.sk_priority); + skb->mark = READ_ONCE(po->sk.sk_mark); skb->tstamp = sockc->transmit_time; skb_setup_tx_timestamp(skb, sockc->tsflags); skb_zcopy_set_nouarg(skb, ph.raw); @@ -2978,7 +2982,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) goto out_unlock; sockcm_init(&sockc, sk); - sockc.mark = sk->sk_mark; + sockc.mark = READ_ONCE(sk->sk_mark); if (msg->msg_controllen) { err = sock_cmsg_send(sk, msg, &sockc); if (unlikely(err)) @@ -3052,7 +3056,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) skb->protocol = proto; skb->dev = dev; - skb->priority = sk->sk_priority; + skb->priority = READ_ONCE(sk->sk_priority); skb->mark = sockc.mark; skb->tstamp = sockc.transmit_time; diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index 1212b057b129..6160ef7d646a 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -265,7 +265,6 @@ static int fw_change(struct net *net, struct sk_buff *in_skb, return -ENOBUFS; fnew->id = f->id; - fnew->res = f->res; fnew->ifindex = f->ifindex; fnew->tp = f->tp; diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c index 9e43b929d4ca..306188bf2d1f 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -511,7 +511,6 @@ static int route4_change(struct net *net, struct sk_buff *in_skb, if (fold) { f->id = fold->id; f->iif = fold->iif; - f->res = fold->res; f->handle = fold->handle; f->tp = fold->tp; diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 1280736a7b92..ba93e2a6bdbb 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -824,7 +824,6 @@ static struct tc_u_knode *u32_init_knode(struct net *net, struct tcf_proto *tp, new->ifindex = n->ifindex; new->fshift = n->fshift; - new->res = n->res; new->flags = n->flags; RCU_INIT_POINTER(new->ht_down, ht); @@ -1022,18 +1021,62 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, return -EINVAL; } + /* At this point, we need to derive the new handle that will be used to + * uniquely map the identity of this table match entry. The + * identity of the entry that we need to construct is 32 bits made of: + * htid(12b):bucketid(8b):node/entryid(12b) + * + * At this point _we have the table(ht)_ in which we will insert this + * entry. We carry the table's id in variable "htid". + * Note that earlier code picked the ht selection either by a) the user + * providing the htid specified via TCA_U32_HASH attribute or b) when + * no such attribute is passed then the root ht, is default to at ID + * 0x[800][00][000]. Rule: the root table has a single bucket with ID 0. + * If OTOH the user passed us the htid, they may also pass a bucketid of + * choice. 0 is fine. For example a user htid is 0x[600][01][000] it is + * indicating hash bucketid of 1. Rule: the entry/node ID _cannot_ be + * passed via the htid, so even if it was non-zero it will be ignored. + * + * We may also have a handle, if the user passed one. The handle also + * carries the same addressing of htid(12b):bucketid(8b):node/entryid(12b). + * Rule: the bucketid on the handle is ignored even if one was passed; + * rather the value on "htid" is always assumed to be the bucketid. + */ if (handle) { + /* Rule: The htid from handle and tableid from htid must match */ if (TC_U32_HTID(handle) && TC_U32_HTID(handle ^ htid)) { NL_SET_ERR_MSG_MOD(extack, "Handle specified hash table address mismatch"); return -EINVAL; } - handle = htid | TC_U32_NODE(handle); - err = idr_alloc_u32(&ht->handle_idr, NULL, &handle, handle, - GFP_KERNEL); - if (err) - return err; - } else + /* Ok, so far we have a valid htid(12b):bucketid(8b) but we + * need to finalize the table entry identification with the last + * part - the node/entryid(12b)). Rule: Nodeid _cannot be 0_ for + * entries. Rule: nodeid of 0 is reserved only for tables(see + * earlier code which processes TC_U32_DIVISOR attribute). + * Rule: The nodeid can only be derived from the handle (and not + * htid). + * Rule: if the handle specified zero for the node id example + * 0x60000000, then pick a new nodeid from the pool of IDs + * this hash table has been allocating from. + * If OTOH it is specified (i.e for example the user passed a + * handle such as 0x60000123), then we use it generate our final + * handle which is used to uniquely identify the match entry. + */ + if (!TC_U32_NODE(handle)) { + handle = gen_new_kid(ht, htid); + } else { + handle = htid | TC_U32_NODE(handle); + err = idr_alloc_u32(&ht->handle_idr, NULL, &handle, + handle, GFP_KERNEL); + if (err) + return err; + } + } else { + /* The user did not give us a handle; lets just generate one + * from the table's pool of nodeids. + */ handle = gen_new_kid(ht, htid); + } if (tb[TCA_U32_SEL] == NULL) { NL_SET_ERR_MSG_MOD(extack, "Selector not specified"); diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 01d07e6a6811..e8f988e1c7e6 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1550,10 +1550,28 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, return 0; } +static bool req_create_or_replace(struct nlmsghdr *n) +{ + return (n->nlmsg_flags & NLM_F_CREATE && + n->nlmsg_flags & NLM_F_REPLACE); +} + +static bool req_create_exclusive(struct nlmsghdr *n) +{ + return (n->nlmsg_flags & NLM_F_CREATE && + n->nlmsg_flags & NLM_F_EXCL); +} + +static bool req_change(struct nlmsghdr *n) +{ + return (!(n->nlmsg_flags & NLM_F_CREATE) && + !(n->nlmsg_flags & NLM_F_REPLACE) && + !(n->nlmsg_flags & NLM_F_EXCL)); +} + /* * Create/change qdisc. */ - static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n, struct netlink_ext_ack *extack) { @@ -1647,27 +1665,35 @@ replay: * * We know, that some child q is already * attached to this parent and have choice: - * either to change it or to create/graft new one. + * 1) change it or 2) create/graft new one. + * If the requested qdisc kind is different + * than the existing one, then we choose graft. + * If they are the same then this is "change" + * operation - just let it fallthrough.. * * 1. We are allowed to create/graft only - * if CREATE and REPLACE flags are set. + * if the request is explicitly stating + * "please create if it doesn't exist". * - * 2. If EXCL is set, requestor wanted to say, - * that qdisc tcm_handle is not expected + * 2. If the request is to exclusive create + * then the qdisc tcm_handle is not expected * to exist, so that we choose create/graft too. * * 3. The last case is when no flags are set. + * This will happen when for example tc + * utility issues a "change" command. * Alas, it is sort of hole in API, we * cannot decide what to do unambiguously. - * For now we select create/graft, if - * user gave KIND, which does not match existing. + * For now we select create/graft. */ - if ((n->nlmsg_flags & NLM_F_CREATE) && - (n->nlmsg_flags & NLM_F_REPLACE) && - ((n->nlmsg_flags & NLM_F_EXCL) || - (tca[TCA_KIND] && - nla_strcmp(tca[TCA_KIND], q->ops->id)))) - goto create_n_graft; + if (tca[TCA_KIND] && + nla_strcmp(tca[TCA_KIND], q->ops->id)) { + if (req_create_or_replace(n) || + req_create_exclusive(n)) + goto create_n_graft; + else if (req_change(n)) + goto create_n_graft2; + } } } } else { @@ -1701,6 +1727,7 @@ create_n_graft: NL_SET_ERR_MSG(extack, "Qdisc not found. To create specify NLM_F_CREATE flag"); return -ENOENT; } +create_n_graft2: if (clid == TC_H_INGRESS) { if (dev_ingress_queue(dev)) { q = qdisc_create(dev, dev_ingress_queue(dev), diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index aa9842158df0..d0e045116d4e 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -773,12 +773,10 @@ static void dist_free(struct disttable *d) * signed 16 bit values. */ -static int get_dist_table(struct Qdisc *sch, struct disttable **tbl, - const struct nlattr *attr) +static int get_dist_table(struct disttable **tbl, const struct nlattr *attr) { size_t n = nla_len(attr)/sizeof(__s16); const __s16 *data = nla_data(attr); - spinlock_t *root_lock; struct disttable *d; int i; @@ -793,13 +791,7 @@ static int get_dist_table(struct Qdisc *sch, struct disttable **tbl, for (i = 0; i < n; i++) d->table[i] = data[i]; - root_lock = qdisc_root_sleeping_lock(sch); - - spin_lock_bh(root_lock); - swap(*tbl, d); - spin_unlock_bh(root_lock); - - dist_free(d); + *tbl = d; return 0; } @@ -956,6 +948,8 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt, { struct netem_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_NETEM_MAX + 1]; + struct disttable *delay_dist = NULL; + struct disttable *slot_dist = NULL; struct tc_netem_qopt *qopt; struct clgstate old_clg; int old_loss_model = CLG_RANDOM; @@ -966,6 +960,18 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt, if (ret < 0) return ret; + if (tb[TCA_NETEM_DELAY_DIST]) { + ret = get_dist_table(&delay_dist, tb[TCA_NETEM_DELAY_DIST]); + if (ret) + goto table_free; + } + + if (tb[TCA_NETEM_SLOT_DIST]) { + ret = get_dist_table(&slot_dist, tb[TCA_NETEM_SLOT_DIST]); + if (ret) + goto table_free; + } + sch_tree_lock(sch); /* backup q->clg and q->loss_model */ old_clg = q->clg; @@ -975,26 +981,17 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt, ret = get_loss_clg(q, tb[TCA_NETEM_LOSS]); if (ret) { q->loss_model = old_loss_model; + q->clg = old_clg; goto unlock; } } else { q->loss_model = CLG_RANDOM; } - if (tb[TCA_NETEM_DELAY_DIST]) { - ret = get_dist_table(sch, &q->delay_dist, - tb[TCA_NETEM_DELAY_DIST]); - if (ret) - goto get_table_failure; - } - - if (tb[TCA_NETEM_SLOT_DIST]) { - ret = get_dist_table(sch, &q->slot_dist, - tb[TCA_NETEM_SLOT_DIST]); - if (ret) - goto get_table_failure; - } - + if (delay_dist) + swap(q->delay_dist, delay_dist); + if (slot_dist) + swap(q->slot_dist, slot_dist); sch->limit = qopt->limit; q->latency = PSCHED_TICKS2NS(qopt->latency); @@ -1044,17 +1041,11 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt, unlock: sch_tree_unlock(sch); - return ret; -get_table_failure: - /* recover clg and loss_model, in case of - * q->clg and q->loss_model were modified - * in get_loss_clg() - */ - q->clg = old_clg; - q->loss_model = old_loss_model; - - goto unlock; +table_free: + dist_free(delay_dist); + dist_free(slot_dist); + return ret; } static int netem_init(struct Qdisc *sch, struct nlattr *opt, diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index a274a9332f33..8d5eebb2dd1b 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -769,6 +769,11 @@ static const struct nla_policy taprio_tc_policy[TCA_TAPRIO_TC_ENTRY_MAX + 1] = { [TCA_TAPRIO_TC_ENTRY_MAX_SDU] = { .type = NLA_U32 }, }; +static struct netlink_range_validation_signed taprio_cycle_time_range = { + .min = 0, + .max = INT_MAX, +}; + static const struct nla_policy taprio_policy[TCA_TAPRIO_ATTR_MAX + 1] = { [TCA_TAPRIO_ATTR_PRIOMAP] = { .len = sizeof(struct tc_mqprio_qopt) @@ -777,7 +782,8 @@ static const struct nla_policy taprio_policy[TCA_TAPRIO_ATTR_MAX + 1] = { [TCA_TAPRIO_ATTR_SCHED_BASE_TIME] = { .type = NLA_S64 }, [TCA_TAPRIO_ATTR_SCHED_SINGLE_ENTRY] = { .type = NLA_NESTED }, [TCA_TAPRIO_ATTR_SCHED_CLOCKID] = { .type = NLA_S32 }, - [TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME] = { .type = NLA_S64 }, + [TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME] = + NLA_POLICY_FULL_RANGE_SIGNED(NLA_S64, &taprio_cycle_time_range), [TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME_EXTENSION] = { .type = NLA_S64 }, [TCA_TAPRIO_ATTR_FLAGS] = { .type = NLA_U32 }, [TCA_TAPRIO_ATTR_TXTIME_DELAY] = { .type = NLA_U32 }, @@ -913,6 +919,11 @@ static int parse_taprio_schedule(struct taprio_sched *q, struct nlattr **tb, return -EINVAL; } + if (cycle < 0 || cycle > INT_MAX) { + NL_SET_ERR_MSG(extack, "'cycle_time' is too big"); + return -EINVAL; + } + new->cycle_time = cycle; } @@ -1110,7 +1121,7 @@ static void setup_txtime(struct taprio_sched *q, struct sched_gate_list *sched, ktime_t base) { struct sched_entry *entry; - u32 interval = 0; + u64 interval = 0; list_for_each_entry(entry, &sched->entries, list) { entry->next_txtime = ktime_add_ns(base, interval); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index c806d272107a..a11b0d903514 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -98,7 +98,7 @@ struct percpu_counter sctp_sockets_allocated; static void sctp_enter_memory_pressure(struct sock *sk) { - sctp_memory_pressure = 1; + WRITE_ONCE(sctp_memory_pressure, 1); } @@ -9472,7 +9472,7 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk, newinet->inet_rcv_saddr = inet->inet_rcv_saddr; newinet->inet_dport = htons(asoc->peer.port); newinet->pmtudisc = inet->pmtudisc; - newinet->inet_id = get_random_u16(); + atomic_set(&newinet->inet_id, get_random_u16()); newinet->uc_ttl = inet->uc_ttl; newinet->mc_loop = 1; diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 02d1daae7739..84219c5121bc 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -379,8 +379,8 @@ static struct sock *smc_sock_alloc(struct net *net, struct socket *sock, sk->sk_state = SMC_INIT; sk->sk_destruct = smc_destruct; sk->sk_protocol = protocol; - WRITE_ONCE(sk->sk_sndbuf, READ_ONCE(net->smc.sysctl_wmem)); - WRITE_ONCE(sk->sk_rcvbuf, READ_ONCE(net->smc.sysctl_rmem)); + WRITE_ONCE(sk->sk_sndbuf, 2 * READ_ONCE(net->smc.sysctl_wmem)); + WRITE_ONCE(sk->sk_rcvbuf, 2 * READ_ONCE(net->smc.sysctl_rmem)); smc = smc_sk(sk); INIT_WORK(&smc->tcp_listen_work, smc_tcp_listen_work); INIT_WORK(&smc->connect_work, smc_connect_work); @@ -438,24 +438,9 @@ out: return rc; } -static void smc_copy_sock_settings(struct sock *nsk, struct sock *osk, - unsigned long mask) -{ - /* options we don't get control via setsockopt for */ - nsk->sk_type = osk->sk_type; - nsk->sk_sndbuf = osk->sk_sndbuf; - nsk->sk_rcvbuf = osk->sk_rcvbuf; - nsk->sk_sndtimeo = osk->sk_sndtimeo; - nsk->sk_rcvtimeo = osk->sk_rcvtimeo; - nsk->sk_mark = osk->sk_mark; - nsk->sk_priority = osk->sk_priority; - nsk->sk_rcvlowat = osk->sk_rcvlowat; - nsk->sk_bound_dev_if = osk->sk_bound_dev_if; - nsk->sk_err = osk->sk_err; - - nsk->sk_flags &= ~mask; - nsk->sk_flags |= osk->sk_flags & mask; -} +/* copy only relevant settings and flags of SOL_SOCKET level from smc to + * clc socket (since smc is not called for these options from net/core) + */ #define SK_FLAGS_SMC_TO_CLC ((1UL << SOCK_URGINLINE) | \ (1UL << SOCK_KEEPOPEN) | \ @@ -472,9 +457,55 @@ static void smc_copy_sock_settings(struct sock *nsk, struct sock *osk, (1UL << SOCK_NOFCS) | \ (1UL << SOCK_FILTER_LOCKED) | \ (1UL << SOCK_TSTAMP_NEW)) -/* copy only relevant settings and flags of SOL_SOCKET level from smc to - * clc socket (since smc is not called for these options from net/core) - */ + +/* if set, use value set by setsockopt() - else use IPv4 or SMC sysctl value */ +static void smc_adjust_sock_bufsizes(struct sock *nsk, struct sock *osk, + unsigned long mask) +{ + struct net *nnet = sock_net(nsk); + + nsk->sk_userlocks = osk->sk_userlocks; + if (osk->sk_userlocks & SOCK_SNDBUF_LOCK) { + nsk->sk_sndbuf = osk->sk_sndbuf; + } else { + if (mask == SK_FLAGS_SMC_TO_CLC) + WRITE_ONCE(nsk->sk_sndbuf, + READ_ONCE(nnet->ipv4.sysctl_tcp_wmem[1])); + else + WRITE_ONCE(nsk->sk_sndbuf, + 2 * READ_ONCE(nnet->smc.sysctl_wmem)); + } + if (osk->sk_userlocks & SOCK_RCVBUF_LOCK) { + nsk->sk_rcvbuf = osk->sk_rcvbuf; + } else { + if (mask == SK_FLAGS_SMC_TO_CLC) + WRITE_ONCE(nsk->sk_rcvbuf, + READ_ONCE(nnet->ipv4.sysctl_tcp_rmem[1])); + else + WRITE_ONCE(nsk->sk_rcvbuf, + 2 * READ_ONCE(nnet->smc.sysctl_rmem)); + } +} + +static void smc_copy_sock_settings(struct sock *nsk, struct sock *osk, + unsigned long mask) +{ + /* options we don't get control via setsockopt for */ + nsk->sk_type = osk->sk_type; + nsk->sk_sndtimeo = osk->sk_sndtimeo; + nsk->sk_rcvtimeo = osk->sk_rcvtimeo; + nsk->sk_mark = READ_ONCE(osk->sk_mark); + nsk->sk_priority = osk->sk_priority; + nsk->sk_rcvlowat = osk->sk_rcvlowat; + nsk->sk_bound_dev_if = osk->sk_bound_dev_if; + nsk->sk_err = osk->sk_err; + + nsk->sk_flags &= ~mask; + nsk->sk_flags |= osk->sk_flags & mask; + + smc_adjust_sock_bufsizes(nsk, osk, mask); +} + static void smc_copy_sock_settings_to_clc(struct smc_sock *smc) { smc_copy_sock_settings(smc->clcsock->sk, &smc->sk, SK_FLAGS_SMC_TO_CLC); @@ -2466,8 +2497,6 @@ static void smc_tcp_listen_work(struct work_struct *work) sock_hold(lsk); /* sock_put in smc_listen_work */ INIT_WORK(&new_smc->smc_listen_work, smc_listen_work); smc_copy_sock_settings_to_smc(new_smc); - new_smc->sk.sk_sndbuf = lsmc->sk.sk_sndbuf; - new_smc->sk.sk_rcvbuf = lsmc->sk.sk_rcvbuf; sock_hold(&new_smc->sk); /* sock_put in passive closing */ if (!queue_work(smc_hs_wq, &new_smc->smc_listen_work)) sock_put(&new_smc->sk); diff --git a/net/smc/smc.h b/net/smc/smc.h index 5ed765ea0c73..1d36720fc019 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -161,7 +161,7 @@ struct smc_connection { struct smc_buf_desc *sndbuf_desc; /* send buffer descriptor */ struct smc_buf_desc *rmb_desc; /* RMBE descriptor */ - int rmbe_size_short;/* compressed notation */ + int rmbe_size_comp; /* compressed notation */ int rmbe_update_limit; /* lower limit for consumer * cursor update diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index dfb9797f7bc6..9b8999e2afca 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -1002,7 +1002,7 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc, clc->hdr.typev1 = SMC_TYPE_D; clc->d0.gid = conn->lgr->smcd->local_gid; clc->d0.token = conn->rmb_desc->token; - clc->d0.dmbe_size = conn->rmbe_size_short; + clc->d0.dmbe_size = conn->rmbe_size_comp; clc->d0.dmbe_idx = 0; memcpy(&clc->d0.linkid, conn->lgr->id, SMC_LGR_ID_SIZE); if (version == SMC_V1) { @@ -1045,7 +1045,7 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc, clc->r0.qp_mtu = min(link->path_mtu, link->peer_mtu); break; } - clc->r0.rmbe_size = conn->rmbe_size_short; + clc->r0.rmbe_size = conn->rmbe_size_comp; clc->r0.rmb_dma_addr = conn->rmb_desc->is_vm ? cpu_to_be64((uintptr_t)conn->rmb_desc->cpu_addr) : cpu_to_be64((u64)sg_dma_address diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index f82f43573a15..c676d92af7b7 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -852,8 +852,8 @@ static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini) lgr->freeing = 0; lgr->vlan_id = ini->vlan_id; refcount_set(&lgr->refcnt, 1); /* set lgr refcnt to 1 */ - mutex_init(&lgr->sndbufs_lock); - mutex_init(&lgr->rmbs_lock); + init_rwsem(&lgr->sndbufs_lock); + init_rwsem(&lgr->rmbs_lock); rwlock_init(&lgr->conns_lock); for (i = 0; i < SMC_RMBE_SIZES; i++) { INIT_LIST_HEAD(&lgr->sndbufs[i]); @@ -1095,7 +1095,7 @@ err_out: static void smcr_buf_unuse(struct smc_buf_desc *buf_desc, bool is_rmb, struct smc_link_group *lgr) { - struct mutex *lock; /* lock buffer list */ + struct rw_semaphore *lock; /* lock buffer list */ int rc; if (is_rmb && buf_desc->is_conf_rkey && !list_empty(&lgr->list)) { @@ -1115,9 +1115,9 @@ static void smcr_buf_unuse(struct smc_buf_desc *buf_desc, bool is_rmb, /* buf registration failed, reuse not possible */ lock = is_rmb ? &lgr->rmbs_lock : &lgr->sndbufs_lock; - mutex_lock(lock); + down_write(lock); list_del(&buf_desc->list); - mutex_unlock(lock); + up_write(lock); smc_buf_free(lgr, is_rmb, buf_desc); } else { @@ -1220,15 +1220,16 @@ static void smcr_buf_unmap_lgr(struct smc_link *lnk) int i; for (i = 0; i < SMC_RMBE_SIZES; i++) { - mutex_lock(&lgr->rmbs_lock); + down_write(&lgr->rmbs_lock); list_for_each_entry_safe(buf_desc, bf, &lgr->rmbs[i], list) smcr_buf_unmap_link(buf_desc, true, lnk); - mutex_unlock(&lgr->rmbs_lock); - mutex_lock(&lgr->sndbufs_lock); + up_write(&lgr->rmbs_lock); + + down_write(&lgr->sndbufs_lock); list_for_each_entry_safe(buf_desc, bf, &lgr->sndbufs[i], list) smcr_buf_unmap_link(buf_desc, false, lnk); - mutex_unlock(&lgr->sndbufs_lock); + up_write(&lgr->sndbufs_lock); } } @@ -1986,19 +1987,19 @@ int smc_uncompress_bufsize(u8 compressed) * buffer size; if not available, return NULL */ static struct smc_buf_desc *smc_buf_get_slot(int compressed_bufsize, - struct mutex *lock, + struct rw_semaphore *lock, struct list_head *buf_list) { struct smc_buf_desc *buf_slot; - mutex_lock(lock); + down_read(lock); list_for_each_entry(buf_slot, buf_list, list) { if (cmpxchg(&buf_slot->used, 0, 1) == 0) { - mutex_unlock(lock); + up_read(lock); return buf_slot; } } - mutex_unlock(lock); + up_read(lock); return NULL; } @@ -2107,13 +2108,13 @@ int smcr_link_reg_buf(struct smc_link *link, struct smc_buf_desc *buf_desc) return 0; } -static int _smcr_buf_map_lgr(struct smc_link *lnk, struct mutex *lock, +static int _smcr_buf_map_lgr(struct smc_link *lnk, struct rw_semaphore *lock, struct list_head *lst, bool is_rmb) { struct smc_buf_desc *buf_desc, *bf; int rc = 0; - mutex_lock(lock); + down_write(lock); list_for_each_entry_safe(buf_desc, bf, lst, list) { if (!buf_desc->used) continue; @@ -2122,7 +2123,7 @@ static int _smcr_buf_map_lgr(struct smc_link *lnk, struct mutex *lock, goto out; } out: - mutex_unlock(lock); + up_write(lock); return rc; } @@ -2155,37 +2156,37 @@ int smcr_buf_reg_lgr(struct smc_link *lnk) int i, rc = 0; /* reg all RMBs for a new link */ - mutex_lock(&lgr->rmbs_lock); + down_write(&lgr->rmbs_lock); for (i = 0; i < SMC_RMBE_SIZES; i++) { list_for_each_entry_safe(buf_desc, bf, &lgr->rmbs[i], list) { if (!buf_desc->used) continue; rc = smcr_link_reg_buf(lnk, buf_desc); if (rc) { - mutex_unlock(&lgr->rmbs_lock); + up_write(&lgr->rmbs_lock); return rc; } } } - mutex_unlock(&lgr->rmbs_lock); + up_write(&lgr->rmbs_lock); if (lgr->buf_type == SMCR_PHYS_CONT_BUFS) return rc; /* reg all vzalloced sndbufs for a new link */ - mutex_lock(&lgr->sndbufs_lock); + down_write(&lgr->sndbufs_lock); for (i = 0; i < SMC_RMBE_SIZES; i++) { list_for_each_entry_safe(buf_desc, bf, &lgr->sndbufs[i], list) { if (!buf_desc->used || !buf_desc->is_vm) continue; rc = smcr_link_reg_buf(lnk, buf_desc); if (rc) { - mutex_unlock(&lgr->sndbufs_lock); + up_write(&lgr->sndbufs_lock); return rc; } } } - mutex_unlock(&lgr->sndbufs_lock); + up_write(&lgr->sndbufs_lock); return rc; } @@ -2304,31 +2305,30 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) struct smc_connection *conn = &smc->conn; struct smc_link_group *lgr = conn->lgr; struct list_head *buf_list; - int bufsize, bufsize_short; + int bufsize, bufsize_comp; + struct rw_semaphore *lock; /* lock buffer list */ bool is_dgraded = false; - struct mutex *lock; /* lock buffer list */ - int sk_buf_size; if (is_rmb) /* use socket recv buffer size (w/o overhead) as start value */ - sk_buf_size = smc->sk.sk_rcvbuf; + bufsize = smc->sk.sk_rcvbuf / 2; else /* use socket send buffer size (w/o overhead) as start value */ - sk_buf_size = smc->sk.sk_sndbuf; + bufsize = smc->sk.sk_sndbuf / 2; - for (bufsize_short = smc_compress_bufsize(sk_buf_size, is_smcd, is_rmb); - bufsize_short >= 0; bufsize_short--) { + for (bufsize_comp = smc_compress_bufsize(bufsize, is_smcd, is_rmb); + bufsize_comp >= 0; bufsize_comp--) { if (is_rmb) { lock = &lgr->rmbs_lock; - buf_list = &lgr->rmbs[bufsize_short]; + buf_list = &lgr->rmbs[bufsize_comp]; } else { lock = &lgr->sndbufs_lock; - buf_list = &lgr->sndbufs[bufsize_short]; + buf_list = &lgr->sndbufs[bufsize_comp]; } - bufsize = smc_uncompress_bufsize(bufsize_short); + bufsize = smc_uncompress_bufsize(bufsize_comp); /* check for reusable slot in the link group */ - buf_desc = smc_buf_get_slot(bufsize_short, lock, buf_list); + buf_desc = smc_buf_get_slot(bufsize_comp, lock, buf_list); if (buf_desc) { buf_desc->is_dma_need_sync = 0; SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, bufsize); @@ -2354,9 +2354,9 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) SMC_STAT_RMB_ALLOC(smc, is_smcd, is_rmb); SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, bufsize); buf_desc->used = 1; - mutex_lock(lock); + down_write(lock); list_add(&buf_desc->list, buf_list); - mutex_unlock(lock); + up_write(lock); break; /* found */ } @@ -2372,8 +2372,8 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) if (is_rmb) { conn->rmb_desc = buf_desc; - conn->rmbe_size_short = bufsize_short; - smc->sk.sk_rcvbuf = bufsize; + conn->rmbe_size_comp = bufsize_comp; + smc->sk.sk_rcvbuf = bufsize * 2; atomic_set(&conn->bytes_to_rcv, 0); conn->rmbe_update_limit = smc_rmb_wnd_update_limit(buf_desc->len); @@ -2381,7 +2381,7 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) smc_ism_set_conn(conn); /* map RMB/smcd_dev to conn */ } else { conn->sndbuf_desc = buf_desc; - smc->sk.sk_sndbuf = bufsize; + smc->sk.sk_sndbuf = bufsize * 2; atomic_set(&conn->sndbuf_space, bufsize); } return 0; @@ -2430,9 +2430,9 @@ int smc_buf_create(struct smc_sock *smc, bool is_smcd) /* create rmb */ rc = __smc_buf_create(smc, is_smcd, true); if (rc) { - mutex_lock(&smc->conn.lgr->sndbufs_lock); + down_write(&smc->conn.lgr->sndbufs_lock); list_del(&smc->conn.sndbuf_desc->list); - mutex_unlock(&smc->conn.lgr->sndbufs_lock); + up_write(&smc->conn.lgr->sndbufs_lock); smc_buf_free(smc->conn.lgr, false, smc->conn.sndbuf_desc); smc->conn.sndbuf_desc = NULL; } diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index 285f9bd8e232..6051d9227013 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -252,9 +252,9 @@ struct smc_link_group { unsigned short vlan_id; /* vlan id of link group */ struct list_head sndbufs[SMC_RMBE_SIZES];/* tx buffers */ - struct mutex sndbufs_lock; /* protects tx buffers */ + struct rw_semaphore sndbufs_lock; /* protects tx buffers */ struct list_head rmbs[SMC_RMBE_SIZES]; /* rx buffers */ - struct mutex rmbs_lock; /* protects rx buffers */ + struct rw_semaphore rmbs_lock; /* protects rx buffers */ u8 id[SMC_LGR_ID_SIZE]; /* unique lgr id */ struct delayed_work free_work; /* delayed freeing of an lgr */ diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index 760f8bbff822..fcb24a0ccf76 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -611,7 +611,7 @@ static int smc_llc_fill_ext_v2(struct smc_llc_msg_add_link_v2_ext *ext, prim_lnk_idx = link->link_idx; lnk_idx = link_new->link_idx; - mutex_lock(&lgr->rmbs_lock); + down_write(&lgr->rmbs_lock); ext->num_rkeys = lgr->conns_num; if (!ext->num_rkeys) goto out; @@ -631,7 +631,7 @@ static int smc_llc_fill_ext_v2(struct smc_llc_msg_add_link_v2_ext *ext, } len += i * sizeof(ext->rt[0]); out: - mutex_unlock(&lgr->rmbs_lock); + up_write(&lgr->rmbs_lock); return len; } @@ -892,7 +892,7 @@ static int smc_llc_cli_rkey_exchange(struct smc_link *link, int rc = 0; int i; - mutex_lock(&lgr->rmbs_lock); + down_write(&lgr->rmbs_lock); num_rkeys_send = lgr->conns_num; buf_pos = smc_llc_get_first_rmb(lgr, &buf_lst); do { @@ -919,7 +919,7 @@ static int smc_llc_cli_rkey_exchange(struct smc_link *link, break; } while (num_rkeys_send || num_rkeys_recv); - mutex_unlock(&lgr->rmbs_lock); + up_write(&lgr->rmbs_lock); return rc; } @@ -1002,14 +1002,14 @@ static void smc_llc_save_add_link_rkeys(struct smc_link *link, ext = (struct smc_llc_msg_add_link_v2_ext *)((u8 *)lgr->wr_rx_buf_v2 + SMC_WR_TX_SIZE); max = min_t(u8, ext->num_rkeys, SMC_LLC_RKEYS_PER_MSG_V2); - mutex_lock(&lgr->rmbs_lock); + down_write(&lgr->rmbs_lock); for (i = 0; i < max; i++) { smc_rtoken_set(lgr, link->link_idx, link_new->link_idx, ext->rt[i].rmb_key, ext->rt[i].rmb_vaddr_new, ext->rt[i].rmb_key_new); } - mutex_unlock(&lgr->rmbs_lock); + up_write(&lgr->rmbs_lock); } static void smc_llc_save_add_link_info(struct smc_link *link, @@ -1316,7 +1316,7 @@ static int smc_llc_srv_rkey_exchange(struct smc_link *link, int rc = 0; int i; - mutex_lock(&lgr->rmbs_lock); + down_write(&lgr->rmbs_lock); num_rkeys_send = lgr->conns_num; buf_pos = smc_llc_get_first_rmb(lgr, &buf_lst); do { @@ -1341,7 +1341,7 @@ static int smc_llc_srv_rkey_exchange(struct smc_link *link, smc_llc_flow_qentry_del(&lgr->llc_flow_lcl); } while (num_rkeys_send || num_rkeys_recv); out: - mutex_unlock(&lgr->rmbs_lock); + up_write(&lgr->rmbs_lock); return rc; } diff --git a/net/smc/smc_sysctl.c b/net/smc/smc_sysctl.c index b6f79fabb9d3..0b2a957ca5f5 100644 --- a/net/smc/smc_sysctl.c +++ b/net/smc/smc_sysctl.c @@ -21,6 +21,10 @@ static int min_sndbuf = SMC_BUF_MIN_SIZE; static int min_rcvbuf = SMC_BUF_MIN_SIZE; +static int max_sndbuf = INT_MAX / 2; +static int max_rcvbuf = INT_MAX / 2; +static const int net_smc_wmem_init = (64 * 1024); +static const int net_smc_rmem_init = (64 * 1024); static struct ctl_table smc_table[] = { { @@ -53,6 +57,7 @@ static struct ctl_table smc_table[] = { .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &min_sndbuf, + .extra2 = &max_sndbuf, }, { .procname = "rmem", @@ -61,6 +66,7 @@ static struct ctl_table smc_table[] = { .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &min_rcvbuf, + .extra2 = &max_rcvbuf, }, { } }; @@ -88,8 +94,8 @@ int __net_init smc_sysctl_net_init(struct net *net) net->smc.sysctl_autocorking_size = SMC_AUTOCORKING_DEFAULT_SIZE; net->smc.sysctl_smcr_buf_type = SMCR_PHYS_CONT_BUFS; net->smc.sysctl_smcr_testlink_time = SMC_LLC_TESTLINK_DEFAULT_TIME; - WRITE_ONCE(net->smc.sysctl_wmem, READ_ONCE(net->ipv4.sysctl_tcp_wmem[1])); - WRITE_ONCE(net->smc.sysctl_rmem, READ_ONCE(net->ipv4.sysctl_tcp_rmem[1])); + WRITE_ONCE(net->smc.sysctl_wmem, net_smc_wmem_init); + WRITE_ONCE(net->smc.sysctl_rmem, net_smc_rmem_init); return 0; diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index b098fde373ab..28c0771c4e8c 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -935,9 +935,6 @@ struct rpcrdma_rep *rpcrdma_rep_create(struct rpcrdma_xprt *r_xprt, if (!rep->rr_rdmabuf) goto out_free; - if (!rpcrdma_regbuf_dma_map(r_xprt, rep->rr_rdmabuf)) - goto out_free_regbuf; - rep->rr_cid.ci_completion_id = atomic_inc_return(&r_xprt->rx_ep->re_completion_ids); @@ -956,8 +953,6 @@ struct rpcrdma_rep *rpcrdma_rep_create(struct rpcrdma_xprt *r_xprt, spin_unlock(&buf->rb_lock); return rep; -out_free_regbuf: - rpcrdma_regbuf_free(rep->rr_rdmabuf); out_free: kfree(rep); out: @@ -1363,6 +1358,10 @@ void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, int needed, bool temp) rep = rpcrdma_rep_create(r_xprt, temp); if (!rep) break; + if (!rpcrdma_regbuf_dma_map(r_xprt, rep->rr_rdmabuf)) { + rpcrdma_rep_put(buf, rep); + break; + } rep->rr_cid.ci_queue_id = ep->re_attr.recv_cq->res.id; trace_xprtrdma_post_recv(rep); diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index bf69c9d6d06c..184982788473 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -52,6 +52,8 @@ static LIST_HEAD(tls_device_list); static LIST_HEAD(tls_device_down_list); static DEFINE_SPINLOCK(tls_device_lock); +static struct page *dummy_page; + static void tls_device_free_ctx(struct tls_context *ctx) { if (ctx->tx_conf == TLS_HW) { @@ -313,36 +315,33 @@ static int tls_push_record(struct sock *sk, return tls_push_sg(sk, ctx, offload_ctx->sg_tx_data, 0, flags); } -static int tls_device_record_close(struct sock *sk, - struct tls_context *ctx, - struct tls_record_info *record, - struct page_frag *pfrag, - unsigned char record_type) +static void tls_device_record_close(struct sock *sk, + struct tls_context *ctx, + struct tls_record_info *record, + struct page_frag *pfrag, + unsigned char record_type) { struct tls_prot_info *prot = &ctx->prot_info; - int ret; + struct page_frag dummy_tag_frag; /* append tag * device will fill in the tag, we just need to append a placeholder * use socket memory to improve coalescing (re-using a single buffer * increases frag count) - * if we can't allocate memory now, steal some back from data + * if we can't allocate memory now use the dummy page */ - if (likely(skb_page_frag_refill(prot->tag_size, pfrag, - sk->sk_allocation))) { - ret = 0; - tls_append_frag(record, pfrag, prot->tag_size); - } else { - ret = prot->tag_size; - if (record->len <= prot->overhead_size) - return -ENOMEM; + if (unlikely(pfrag->size - pfrag->offset < prot->tag_size) && + !skb_page_frag_refill(prot->tag_size, pfrag, sk->sk_allocation)) { + dummy_tag_frag.page = dummy_page; + dummy_tag_frag.offset = 0; + pfrag = &dummy_tag_frag; } + tls_append_frag(record, pfrag, prot->tag_size); /* fill prepend */ tls_fill_prepend(ctx, skb_frag_address(&record->frags[0]), record->len - prot->overhead_size, record_type); - return ret; } static int tls_create_new_record(struct tls_offload_context_tx *offload_ctx, @@ -535,18 +534,8 @@ last_record: if (done || record->len >= max_open_record_len || (record->num_frags >= MAX_SKB_FRAGS - 1)) { - rc = tls_device_record_close(sk, tls_ctx, record, - pfrag, record_type); - if (rc) { - if (rc > 0) { - size += rc; - } else { - size = orig_size; - destroy_record(record); - ctx->open_record = NULL; - break; - } - } + tls_device_record_close(sk, tls_ctx, record, + pfrag, record_type); rc = tls_push_record(sk, tls_ctx, @@ -1466,14 +1455,26 @@ int __init tls_device_init(void) { int err; - destruct_wq = alloc_workqueue("ktls_device_destruct", 0, 0); - if (!destruct_wq) + dummy_page = alloc_page(GFP_KERNEL); + if (!dummy_page) return -ENOMEM; + destruct_wq = alloc_workqueue("ktls_device_destruct", 0, 0); + if (!destruct_wq) { + err = -ENOMEM; + goto err_free_dummy; + } + err = register_netdevice_notifier(&tls_dev_notifier); if (err) - destroy_workqueue(destruct_wq); + goto err_destroy_wq; + return 0; + +err_destroy_wq: + destroy_workqueue(destruct_wq); +err_free_dummy: + put_page(dummy_page); return err; } @@ -1482,4 +1483,5 @@ void __exit tls_device_cleanup(void) unregister_netdevice_notifier(&tls_dev_notifier); destroy_workqueue(destruct_wq); clean_acked_data_flush(); + put_page(dummy_page); } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 5b19b6c53a2c..ca31847a6c70 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -779,7 +779,7 @@ static int unix_set_peek_off(struct sock *sk, int val) if (mutex_lock_interruptible(&u->iolock)) return -EINTR; - sk->sk_peek_off = val; + WRITE_ONCE(sk->sk_peek_off, val); mutex_unlock(&u->iolock); return 0; @@ -2290,6 +2290,7 @@ static ssize_t unix_stream_sendpage(struct socket *socket, struct page *page, if (false) { alloc_skb: + spin_unlock(&other->sk_receive_queue.lock); unix_state_unlock(other); mutex_unlock(&unix_sk(other)->iolock); newskb = sock_alloc_send_pskb(sk, 0, 0, flags & MSG_DONTWAIT, @@ -2329,6 +2330,7 @@ alloc_skb: init_scm = false; } + spin_lock(&other->sk_receive_queue.lock); skb = skb_peek_tail(&other->sk_receive_queue); if (tail && tail == skb) { skb = newskb; @@ -2359,14 +2361,11 @@ alloc_skb: refcount_add(size, &sk->sk_wmem_alloc); if (newskb) { - err = unix_scm_to_skb(&scm, skb, false); - if (err) - goto err_state_unlock; - spin_lock(&other->sk_receive_queue.lock); + unix_scm_to_skb(&scm, skb, false); __skb_queue_tail(&other->sk_receive_queue, newskb); - spin_unlock(&other->sk_receive_queue.lock); } + spin_unlock(&other->sk_receive_queue.lock); unix_state_unlock(other); mutex_unlock(&unix_sk(other)->iolock); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 087c0c442e23..c2363d44a1ff 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -5378,8 +5378,11 @@ nl80211_parse_mbssid_elems(struct wiphy *wiphy, struct nlattr *attrs) if (!wiphy->mbssid_max_interfaces) return ERR_PTR(-EINVAL); - nla_for_each_nested(nl_elems, attrs, rem_elems) + nla_for_each_nested(nl_elems, attrs, rem_elems) { + if (num_elems >= 255) + return ERR_PTR(-EINVAL); num_elems++; + } elems = kzalloc(struct_size(elems, elem, num_elems), GFP_KERNEL); if (!elems) diff --git a/net/wireless/scan.c b/net/wireless/scan.c index efe9283e9893..e5c1510c098f 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -643,7 +643,7 @@ static int cfg80211_parse_colocated_ap(const struct cfg80211_bss_ies *ies, ret = cfg80211_calc_short_ssid(ies, &ssid_elem, &s_ssid_tmp); if (ret) - return ret; + return 0; /* RNR IE may contain more than one NEIGHBOR_AP_INFO */ while (pos + sizeof(*ap_info) <= end) { diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 371d269d22fa..f7592638e61d 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -504,7 +504,7 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs, skb->dev = dev; skb->priority = xs->sk.sk_priority; - skb->mark = xs->sk.sk_mark; + skb->mark = READ_ONCE(xs->sk.sk_mark); skb_shinfo(skb)->destructor_arg = (void *)(long)desc->addr; skb->destructor = xsk_destruct_skb; @@ -994,6 +994,7 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) err = xp_alloc_tx_descs(xs->pool, xs); if (err) { xp_put_pool(xs->pool); + xs->pool = NULL; sockfd_put(sock); goto out_unlock; } diff --git a/net/xfrm/xfrm_compat.c b/net/xfrm/xfrm_compat.c index 8cbf45a8bcdc..655fe4ff8621 100644 --- a/net/xfrm/xfrm_compat.c +++ b/net/xfrm/xfrm_compat.c @@ -108,7 +108,7 @@ static const struct nla_policy compat_policy[XFRMA_MAX+1] = { [XFRMA_ALG_COMP] = { .len = sizeof(struct xfrm_algo) }, [XFRMA_ENCAP] = { .len = sizeof(struct xfrm_encap_tmpl) }, [XFRMA_TMPL] = { .len = sizeof(struct xfrm_user_tmpl) }, - [XFRMA_SEC_CTX] = { .len = sizeof(struct xfrm_sec_ctx) }, + [XFRMA_SEC_CTX] = { .len = sizeof(struct xfrm_user_sec_ctx) }, [XFRMA_LTIME_VAL] = { .len = sizeof(struct xfrm_lifetime_cur) }, [XFRMA_REPLAY_VAL] = { .len = sizeof(struct xfrm_replay_state) }, [XFRMA_REPLAY_THRESH] = { .type = NLA_U32 }, diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c index 94a3609548b1..d71dbe822096 100644 --- a/net/xfrm/xfrm_interface_core.c +++ b/net/xfrm/xfrm_interface_core.c @@ -528,8 +528,8 @@ static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev) switch (skb->protocol) { case htons(ETH_P_IPV6): - xfrm_decode_session(skb, &fl, AF_INET6); memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); + xfrm_decode_session(skb, &fl, AF_INET6); if (!dst) { fl.u.ip6.flowi6_oif = dev->ifindex; fl.u.ip6.flowi6_flags |= FLOWI_FLAG_ANYSRC; @@ -543,8 +543,8 @@ static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev) } break; case htons(ETH_P_IP): - xfrm_decode_session(skb, &fl, AF_INET); memset(IPCB(skb), 0, sizeof(*IPCB(skb))); + xfrm_decode_session(skb, &fl, AF_INET); if (!dst) { struct rtable *rt; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 7b1b93584bdb..e65de78cb61b 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2174,7 +2174,7 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir, match = xfrm_selector_match(&pol->selector, fl, family); if (match) { - if ((sk->sk_mark & pol->mark.m) != pol->mark.v || + if ((READ_ONCE(sk->sk_mark) & pol->mark.m) != pol->mark.v || pol->if_id != if_id) { pol = NULL; goto out; diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 2d68a173b227..d042ca01211f 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -615,7 +615,7 @@ static void xfrm_update_ae_params(struct xfrm_state *x, struct nlattr **attrs, struct nlattr *rt = attrs[XFRMA_REPLAY_THRESH]; struct nlattr *mt = attrs[XFRMA_MTIMER_THRESH]; - if (re) { + if (re && x->replay_esn && x->preplay_esn) { struct xfrm_replay_state_esn *replay_esn; replay_esn = nla_data(re); memcpy(x->replay_esn, replay_esn, @@ -1250,6 +1250,15 @@ static int xfrm_dump_sa(struct sk_buff *skb, struct netlink_callback *cb) sizeof(*filter), GFP_KERNEL); if (filter == NULL) return -ENOMEM; + + /* see addr_match(), (prefix length >> 5) << 2 + * will be used to compare xfrm_address_t + */ + if (filter->splen > (sizeof(xfrm_address_t) << 3) || + filter->dplen > (sizeof(xfrm_address_t) << 3)) { + kfree(filter); + return -EINVAL; + } } if (attrs[XFRMA_PROTO]) @@ -2960,7 +2969,7 @@ const struct nla_policy xfrma_policy[XFRMA_MAX+1] = { [XFRMA_ALG_COMP] = { .len = sizeof(struct xfrm_algo) }, [XFRMA_ENCAP] = { .len = sizeof(struct xfrm_encap_tmpl) }, [XFRMA_TMPL] = { .len = sizeof(struct xfrm_user_tmpl) }, - [XFRMA_SEC_CTX] = { .len = sizeof(struct xfrm_sec_ctx) }, + [XFRMA_SEC_CTX] = { .len = sizeof(struct xfrm_user_sec_ctx) }, [XFRMA_LTIME_VAL] = { .len = sizeof(struct xfrm_lifetime_cur) }, [XFRMA_REPLAY_VAL] = { .len = sizeof(struct xfrm_replay_state) }, [XFRMA_REPLAY_THRESH] = { .type = NLA_U32 }, @@ -2980,6 +2989,7 @@ const struct nla_policy xfrma_policy[XFRMA_MAX+1] = { [XFRMA_SET_MARK] = { .type = NLA_U32 }, [XFRMA_SET_MARK_MASK] = { .type = NLA_U32 }, [XFRMA_IF_ID] = { .type = NLA_U32 }, + [XFRMA_MTIMER_THRESH] = { .type = NLA_U32 }, }; EXPORT_SYMBOL_GPL(xfrma_policy); diff --git a/rust/bindings/bindings_helper.h b/rust/bindings/bindings_helper.h index c48bc284214a..fdb4e11df3bd 100644 --- a/rust/bindings/bindings_helper.h +++ b/rust/bindings/bindings_helper.h @@ -9,5 +9,6 @@ #include <linux/slab.h> /* `bindgen` gets confused at certain things. */ +const size_t BINDINGS_ARCH_SLAB_MINALIGN = ARCH_SLAB_MINALIGN; const gfp_t BINDINGS_GFP_KERNEL = GFP_KERNEL; const gfp_t BINDINGS___GFP_ZERO = __GFP_ZERO; diff --git a/rust/kernel/allocator.rs b/rust/kernel/allocator.rs index 397a3dd57a9b..9363b527be66 100644 --- a/rust/kernel/allocator.rs +++ b/rust/kernel/allocator.rs @@ -9,6 +9,36 @@ use crate::bindings; struct KernelAllocator; +/// Calls `krealloc` with a proper size to alloc a new object aligned to `new_layout`'s alignment. +/// +/// # Safety +/// +/// - `ptr` can be either null or a pointer which has been allocated by this allocator. +/// - `new_layout` must have a non-zero size. +unsafe fn krealloc_aligned(ptr: *mut u8, new_layout: Layout, flags: bindings::gfp_t) -> *mut u8 { + // Customized layouts from `Layout::from_size_align()` can have size < align, so pad first. + let layout = new_layout.pad_to_align(); + + let mut size = layout.size(); + + if layout.align() > bindings::BINDINGS_ARCH_SLAB_MINALIGN { + // The alignment requirement exceeds the slab guarantee, thus try to enlarge the size + // to use the "power-of-two" size/alignment guarantee (see comments in `kmalloc()` for + // more information). + // + // Note that `layout.size()` (after padding) is guaranteed to be a multiple of + // `layout.align()`, so `next_power_of_two` gives enough alignment guarantee. + size = size.next_power_of_two(); + } + + // SAFETY: + // - `ptr` is either null or a pointer returned from a previous `k{re}alloc()` by the + // function safety requirement. + // - `size` is greater than 0 since it's either a `layout.size()` (which cannot be zero + // according to the function safety requirement) or a result from `next_power_of_two()`. + unsafe { bindings::krealloc(ptr as *const core::ffi::c_void, size, flags) as *mut u8 } +} + unsafe impl GlobalAlloc for KernelAllocator { unsafe fn alloc(&self, layout: Layout) -> *mut u8 { // `krealloc()` is used instead of `kmalloc()` because the latter is @@ -30,10 +60,20 @@ static ALLOCATOR: KernelAllocator = KernelAllocator; // to extract the object file that has them from the archive. For the moment, // let's generate them ourselves instead. // +// Note: Although these are *safe* functions, they are called by the compiler +// with parameters that obey the same `GlobalAlloc` function safety +// requirements: size and align should form a valid layout, and size is +// greater than 0. +// // Note that `#[no_mangle]` implies exported too, nowadays. #[no_mangle] -fn __rust_alloc(size: usize, _align: usize) -> *mut u8 { - unsafe { bindings::krealloc(core::ptr::null(), size, bindings::GFP_KERNEL) as *mut u8 } +fn __rust_alloc(size: usize, align: usize) -> *mut u8 { + // SAFETY: See assumption above. + let layout = unsafe { Layout::from_size_align_unchecked(size, align) }; + + // SAFETY: `ptr::null_mut()` is null, per assumption above the size of `layout` is greater + // than 0. + unsafe { krealloc_aligned(ptr::null_mut(), layout, bindings::GFP_KERNEL) } } #[no_mangle] @@ -42,23 +82,27 @@ fn __rust_dealloc(ptr: *mut u8, _size: usize, _align: usize) { } #[no_mangle] -fn __rust_realloc(ptr: *mut u8, _old_size: usize, _align: usize, new_size: usize) -> *mut u8 { - unsafe { - bindings::krealloc( - ptr as *const core::ffi::c_void, - new_size, - bindings::GFP_KERNEL, - ) as *mut u8 - } +fn __rust_realloc(ptr: *mut u8, _old_size: usize, align: usize, new_size: usize) -> *mut u8 { + // SAFETY: See assumption above. + let new_layout = unsafe { Layout::from_size_align_unchecked(new_size, align) }; + + // SAFETY: Per assumption above, `ptr` is allocated by `__rust_*` before, and the size of + // `new_layout` is greater than 0. + unsafe { krealloc_aligned(ptr, new_layout, bindings::GFP_KERNEL) } } #[no_mangle] -fn __rust_alloc_zeroed(size: usize, _align: usize) -> *mut u8 { +fn __rust_alloc_zeroed(size: usize, align: usize) -> *mut u8 { + // SAFETY: See assumption above. + let layout = unsafe { Layout::from_size_align_unchecked(size, align) }; + + // SAFETY: `ptr::null_mut()` is null, per assumption above the size of `layout` is greater + // than 0. unsafe { - bindings::krealloc( - core::ptr::null(), - size, + krealloc_aligned( + ptr::null_mut(), + layout, bindings::GFP_KERNEL | bindings::__GFP_ZERO, - ) as *mut u8 + ) } } diff --git a/scripts/gcc-plugins/gcc-common.h b/scripts/gcc-plugins/gcc-common.h index 9a1895747b15..84c730da36dd 100644 --- a/scripts/gcc-plugins/gcc-common.h +++ b/scripts/gcc-plugins/gcc-common.h @@ -71,7 +71,9 @@ #include "varasm.h" #include "stor-layout.h" #include "internal-fn.h" +#include "gimple.h" #include "gimple-expr.h" +#include "gimple-iterator.h" #include "gimple-fold.h" #include "context.h" #include "tree-ssa-alias.h" @@ -85,10 +87,8 @@ #include "tree-eh.h" #include "stmt.h" #include "gimplify.h" -#include "gimple.h" #include "tree-phinodes.h" #include "tree-cfg.h" -#include "gimple-iterator.h" #include "gimple-ssa.h" #include "ssa-iterators.h" diff --git a/security/selinux/ss/policydb.c b/security/selinux/ss/policydb.c index adcfb63b3550..6f9ff4643dcb 100644 --- a/security/selinux/ss/policydb.c +++ b/security/selinux/ss/policydb.c @@ -2005,6 +2005,7 @@ static int filename_trans_read_helper(struct policydb *p, void *fp) if (!datum) goto out; + datum->next = NULL; *dst = datum; /* ebitmap_read() will at least init the bitmap */ @@ -2017,7 +2018,6 @@ static int filename_trans_read_helper(struct policydb *p, void *fp) goto out; datum->otype = le32_to_cpu(buf[0]); - datum->next = NULL; dst = &datum->next; } diff --git a/sound/hda/hdac_regmap.c b/sound/hda/hdac_regmap.c index fe3587547cfe..39610a15bcc9 100644 --- a/sound/hda/hdac_regmap.c +++ b/sound/hda/hdac_regmap.c @@ -597,10 +597,9 @@ EXPORT_SYMBOL_GPL(snd_hdac_regmap_update_raw_once); */ void snd_hdac_regmap_sync(struct hdac_device *codec) { - if (codec->regmap) { - mutex_lock(&codec->regmap_lock); + mutex_lock(&codec->regmap_lock); + if (codec->regmap) regcache_sync(codec->regmap); - mutex_unlock(&codec->regmap_lock); - } + mutex_unlock(&codec->regmap_lock); } EXPORT_SYMBOL_GPL(snd_hdac_regmap_sync); diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index f93b68a2a839..aa475154c582 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -7081,6 +7081,8 @@ enum { ALC285_FIXUP_SPEAKER2_TO_DAC1, ALC285_FIXUP_ASUS_SPEAKER2_TO_DAC1, ALC285_FIXUP_ASUS_HEADSET_MIC, + ALC285_FIXUP_ASUS_I2C_SPEAKER2_TO_DAC1, + ALC285_FIXUP_ASUS_I2C_HEADSET_MIC, ALC280_FIXUP_HP_HEADSET_MIC, ALC221_FIXUP_HP_FRONT_MIC, ALC292_FIXUP_TPT460, @@ -7136,6 +7138,10 @@ enum { ALC294_FIXUP_ASUS_DUAL_SPK, ALC285_FIXUP_THINKPAD_X1_GEN7, ALC285_FIXUP_THINKPAD_HEADSET_JACK, + ALC294_FIXUP_ASUS_ALLY, + ALC294_FIXUP_ASUS_ALLY_PINS, + ALC294_FIXUP_ASUS_ALLY_VERBS, + ALC294_FIXUP_ASUS_ALLY_SPEAKER, ALC294_FIXUP_ASUS_HPE, ALC294_FIXUP_ASUS_COEF_1B, ALC294_FIXUP_ASUS_GX502_HP, @@ -8069,6 +8075,22 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC285_FIXUP_ASUS_SPEAKER2_TO_DAC1 }, + [ALC285_FIXUP_ASUS_I2C_SPEAKER2_TO_DAC1] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc285_fixup_speaker2_to_dac1, + .chained = true, + .chain_id = ALC287_FIXUP_CS35L41_I2C_2 + }, + [ALC285_FIXUP_ASUS_I2C_HEADSET_MIC] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x19, 0x03a11050 }, + { 0x1b, 0x03a11c30 }, + { } + }, + .chained = true, + .chain_id = ALC285_FIXUP_ASUS_I2C_SPEAKER2_TO_DAC1 + }, [ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { @@ -8450,6 +8472,47 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC294_FIXUP_SPK2_TO_DAC1 }, + [ALC294_FIXUP_ASUS_ALLY] = { + .type = HDA_FIXUP_FUNC, + .v.func = cs35l41_fixup_i2c_two, + .chained = true, + .chain_id = ALC294_FIXUP_ASUS_ALLY_PINS + }, + [ALC294_FIXUP_ASUS_ALLY_PINS] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x19, 0x03a11050 }, + { 0x1a, 0x03a11c30 }, + { 0x21, 0x03211420 }, + { } + }, + .chained = true, + .chain_id = ALC294_FIXUP_ASUS_ALLY_VERBS + }, + [ALC294_FIXUP_ASUS_ALLY_VERBS] = { + .type = HDA_FIXUP_VERBS, + .v.verbs = (const struct hda_verb[]) { + { 0x20, AC_VERB_SET_COEF_INDEX, 0x45 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x5089 }, + { 0x20, AC_VERB_SET_COEF_INDEX, 0x46 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x0004 }, + { 0x20, AC_VERB_SET_COEF_INDEX, 0x47 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0xa47a }, + { 0x20, AC_VERB_SET_COEF_INDEX, 0x49 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x0049}, + { 0x20, AC_VERB_SET_COEF_INDEX, 0x4a }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x201b }, + { 0x20, AC_VERB_SET_COEF_INDEX, 0x6b }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x4278}, + { } + }, + .chained = true, + .chain_id = ALC294_FIXUP_ASUS_ALLY_SPEAKER + }, + [ALC294_FIXUP_ASUS_ALLY_SPEAKER] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc285_fixup_speaker2_to_dac1, + }, [ALC285_FIXUP_THINKPAD_X1_GEN7] = { .type = HDA_FIXUP_FUNC, .v.func = alc285_fixup_thinkpad_x1_gen7, @@ -9533,7 +9596,13 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8b96, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8b97, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8bf0, "HP", ALC236_FIXUP_HP_GPIO_LED), - SND_PCI_QUIRK(0x103c, 0x8c26, "HP HP EliteBook 800G11", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8c46, "HP EliteBook 830 G11", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8c47, "HP EliteBook 840 G11", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8c48, "HP EliteBook 860 G11", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8c49, "HP Elite x360 830 2-in-1 G11", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8c70, "HP EliteBook 835 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8c71, "HP EliteBook 845 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8c72, "HP EliteBook 865 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC), SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300), SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), @@ -9553,15 +9622,19 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1313, "Asus K42JZ", ALC269VB_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x13b0, "ASUS Z550SA", ALC256_FIXUP_ASUS_MIC), SND_PCI_QUIRK(0x1043, 0x1427, "Asus Zenbook UX31E", ALC269VB_FIXUP_ASUS_ZENBOOK), + SND_PCI_QUIRK(0x1043, 0x1433, "ASUS GX650P", ALC285_FIXUP_ASUS_I2C_HEADSET_MIC), + SND_PCI_QUIRK(0x1043, 0x1463, "Asus GA402X", ALC285_FIXUP_ASUS_I2C_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x1473, "ASUS GU604V", ALC285_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x1483, "ASUS GU603V", ALC285_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x1517, "Asus Zenbook UX31A", ALC269VB_FIXUP_ASUS_ZENBOOK_UX31A), + SND_PCI_QUIRK(0x1043, 0x1573, "ASUS GZ301V", ALC285_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x1662, "ASUS GV301QH", ALC294_FIXUP_ASUS_DUAL_SPK), SND_PCI_QUIRK(0x1043, 0x1683, "ASUS UM3402YAR", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x1043, 0x16b2, "ASUS GU603", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x16e3, "ASUS UX50", ALC269_FIXUP_STEREO_DMIC), SND_PCI_QUIRK(0x1043, 0x1740, "ASUS UX430UA", ALC295_FIXUP_ASUS_DACS), SND_PCI_QUIRK(0x1043, 0x17d1, "ASUS UX431FL", ALC294_FIXUP_ASUS_DUAL_SPK), + SND_PCI_QUIRK(0x1043, 0x17f3, "ROG Ally RC71L_RC71L", ALC294_FIXUP_ASUS_ALLY), SND_PCI_QUIRK(0x1043, 0x1881, "ASUS Zephyrus S/M", ALC294_FIXUP_ASUS_GX502_PINS), SND_PCI_QUIRK(0x1043, 0x18b1, "Asus MJ401TA", ALC256_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x18f1, "Asus FX505DT", ALC256_FIXUP_ASUS_HEADSET_MIC), @@ -10547,6 +10620,7 @@ static int patch_alc269(struct hda_codec *codec) spec = codec->spec; spec->gen.shared_mic_vref_pin = 0x18; codec->power_save_node = 0; + spec->en_3kpull_low = true; #ifdef CONFIG_PM codec->patch_ops.suspend = alc269_suspend; @@ -10629,14 +10703,16 @@ static int patch_alc269(struct hda_codec *codec) spec->shutup = alc256_shutup; spec->init_hook = alc256_init; spec->gen.mixer_nid = 0; /* ALC256 does not have any loopback mixer path */ - if (codec->bus->pci->vendor == PCI_VENDOR_ID_AMD) - spec->en_3kpull_low = true; + if (codec->core.vendor_id == 0x10ec0236 && + codec->bus->pci->vendor != PCI_VENDOR_ID_AMD) + spec->en_3kpull_low = false; break; case 0x10ec0257: spec->codec_variant = ALC269_TYPE_ALC257; spec->shutup = alc256_shutup; spec->init_hook = alc256_init; spec->gen.mixer_nid = 0; + spec->en_3kpull_low = false; break; case 0x10ec0215: case 0x10ec0245: @@ -11268,6 +11344,7 @@ enum { ALC897_FIXUP_HP_HSMIC_VERB, ALC897_FIXUP_LENOVO_HEADSET_MODE, ALC897_FIXUP_HEADSET_MIC_PIN2, + ALC897_FIXUP_UNIS_H3C_X500S, }; static const struct hda_fixup alc662_fixups[] = { @@ -11707,6 +11784,13 @@ static const struct hda_fixup alc662_fixups[] = { .chained = true, .chain_id = ALC897_FIXUP_LENOVO_HEADSET_MODE }, + [ALC897_FIXUP_UNIS_H3C_X500S] = { + .type = HDA_FIXUP_VERBS, + .v.verbs = (const struct hda_verb[]) { + { 0x14, AC_VERB_SET_EAPD_BTLENABLE, 0 }, + {} + }, + }, }; static const struct snd_pci_quirk alc662_fixup_tbl[] = { @@ -11868,6 +11952,7 @@ static const struct hda_model_fixup alc662_fixup_models[] = { {.id = ALC662_FIXUP_USI_HEADSET_MODE, .name = "usi-headset"}, {.id = ALC662_FIXUP_LENOVO_MULTI_CODECS, .name = "dual-codecs"}, {.id = ALC669_FIXUP_ACER_ASPIRE_ETHOS, .name = "aspire-ethos"}, + {.id = ALC897_FIXUP_UNIS_H3C_X500S, .name = "unis-h3c-x500s"}, {} }; diff --git a/sound/pci/ymfpci/ymfpci.c b/sound/pci/ymfpci/ymfpci.c index 82d4e0fda91b..d62a0e2ddf60 100644 --- a/sound/pci/ymfpci/ymfpci.c +++ b/sound/pci/ymfpci/ymfpci.c @@ -150,8 +150,8 @@ static inline int snd_ymfpci_create_gameport(struct snd_ymfpci *chip, int dev, i void snd_ymfpci_free_gameport(struct snd_ymfpci *chip) { } #endif /* SUPPORT_JOYSTICK */ -static int snd_card_ymfpci_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_card_ymfpci_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -333,6 +333,12 @@ static int snd_card_ymfpci_probe(struct pci_dev *pci, return 0; } +static int snd_card_ymfpci_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_card_ymfpci_probe(pci, pci_id)); +} + static struct pci_driver ymfpci_driver = { .name = KBUILD_MODNAME, .id_table = snd_ymfpci_ids, diff --git a/sound/soc/amd/Kconfig b/sound/soc/amd/Kconfig index c88ebd84bdd5..44d4e6e51a35 100644 --- a/sound/soc/amd/Kconfig +++ b/sound/soc/amd/Kconfig @@ -71,6 +71,7 @@ config SND_SOC_AMD_RENOIR_MACH config SND_SOC_AMD_ACP5x tristate "AMD Audio Coprocessor-v5.x I2S support" depends on X86 && PCI + select SND_AMD_ACP_CONFIG help This option enables ACP v5.x support on AMD platform @@ -81,6 +82,7 @@ config SND_SOC_AMD_VANGOGH_MACH tristate "AMD Vangogh support for NAU8821 CS35L41" select SND_SOC_NAU8821 select SND_SOC_CS35L41_SPI + select SND_AMD_ACP_CONFIG depends on SND_SOC_AMD_ACP5x && I2C && SPI_MASTER help This option enables machine driver for Vangogh platform diff --git a/sound/soc/amd/vangogh/acp5x.h b/sound/soc/amd/vangogh/acp5x.h index bd9f1c5684d1..ac1936a8c43f 100644 --- a/sound/soc/amd/vangogh/acp5x.h +++ b/sound/soc/amd/vangogh/acp5x.h @@ -147,6 +147,8 @@ static inline void acp_writel(u32 val, void __iomem *base_addr) writel(val, base_addr - ACP5x_PHY_BASE_ADDRESS); } +int snd_amd_acp_find_config(struct pci_dev *pci); + static inline u64 acp_get_byte_count(struct i2s_stream_instance *rtd, int direction) { diff --git a/sound/soc/amd/vangogh/pci-acp5x.c b/sound/soc/amd/vangogh/pci-acp5x.c index e0df17c88e8e..c4634a8a17cd 100644 --- a/sound/soc/amd/vangogh/pci-acp5x.c +++ b/sound/soc/amd/vangogh/pci-acp5x.c @@ -125,10 +125,15 @@ static int snd_acp5x_probe(struct pci_dev *pci, { struct acp5x_dev_data *adata; struct platform_device_info pdevinfo[ACP5x_DEVS]; - unsigned int irqflags; + unsigned int irqflags, flag; int ret, i; u32 addr, val; + /* Return if acp config flag is defined */ + flag = snd_amd_acp_find_config(pci); + if (flag) + return -ENODEV; + irqflags = IRQF_SHARED; if (pci->revision != 0x50) return -ENODEV; diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c index c1ca3ceac5f2..9a9571c3f08c 100644 --- a/sound/soc/amd/yc/acp6x-mach.c +++ b/sound/soc/amd/yc/acp6x-mach.c @@ -217,7 +217,7 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { .driver_data = &acp6x_card, .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), - DMI_MATCH(DMI_PRODUCT_NAME, "82"), + DMI_MATCH(DMI_PRODUCT_NAME, "82V2"), } }, { @@ -251,6 +251,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { { .driver_data = &acp6x_card, .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "M6500RC"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "TIMI"), DMI_MATCH(DMI_PRODUCT_NAME, "Redmi Book Pro 15 2022"), } diff --git a/sound/soc/codecs/cs35l41.c b/sound/soc/codecs/cs35l41.c index f2b5032daa6a..2f4b0ee93ace 100644 --- a/sound/soc/codecs/cs35l41.c +++ b/sound/soc/codecs/cs35l41.c @@ -167,7 +167,7 @@ static int cs35l41_get_fs_mon_config_index(int freq) static const DECLARE_TLV_DB_RANGE(dig_vol_tlv, 0, 0, TLV_DB_SCALE_ITEM(TLV_DB_GAIN_MUTE, 0, 1), 1, 913, TLV_DB_MINMAX_ITEM(-10200, 1200)); -static DECLARE_TLV_DB_SCALE(amp_gain_tlv, 0, 1, 1); +static DECLARE_TLV_DB_SCALE(amp_gain_tlv, 50, 100, 0); static const struct snd_kcontrol_new dre_ctrl = SOC_DAPM_SINGLE("Switch", CS35L41_PWR_CTRL3, 20, 1, 0); diff --git a/sound/soc/codecs/rt5665.c b/sound/soc/codecs/rt5665.c index 6e66cc218fa8..76ff097518c8 100644 --- a/sound/soc/codecs/rt5665.c +++ b/sound/soc/codecs/rt5665.c @@ -4472,6 +4472,8 @@ static void rt5665_remove(struct snd_soc_component *component) struct rt5665_priv *rt5665 = snd_soc_component_get_drvdata(component); regmap_write(rt5665->regmap, RT5665_RESET, 0); + + regulator_bulk_disable(ARRAY_SIZE(rt5665->supplies), rt5665->supplies); } #ifdef CONFIG_PM diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c index a37c85d30147..064b6feb7616 100644 --- a/sound/soc/intel/boards/sof_sdw.c +++ b/sound/soc/intel/boards/sof_sdw.c @@ -374,6 +374,31 @@ static const struct dmi_system_id sof_sdw_quirk_table[] = { }, .driver_data = (void *)(RT711_JD1), }, + { + .callback = sof_sdw_quirk_cb, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Intel Corporation"), + DMI_MATCH(DMI_PRODUCT_NAME, "Meteor Lake Client Platform"), + }, + .driver_data = (void *)(RT711_JD2_100K), + }, + { + .callback = sof_sdw_quirk_cb, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Google"), + DMI_MATCH(DMI_PRODUCT_NAME, "Rex"), + }, + .driver_data = (void *)(SOF_SDW_PCH_DMIC), + }, + /* LunarLake devices */ + { + .callback = sof_sdw_quirk_cb, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Intel Corporation"), + DMI_MATCH(DMI_PRODUCT_NAME, "Lunar Lake Client Platform"), + }, + .driver_data = (void *)(RT711_JD2_100K), + }, {} }; diff --git a/sound/soc/intel/boards/sof_sdw_rt711_sdca.c b/sound/soc/intel/boards/sof_sdw_rt711_sdca.c index 7f16304d025b..cf8b9793fe0e 100644 --- a/sound/soc/intel/boards/sof_sdw_rt711_sdca.c +++ b/sound/soc/intel/boards/sof_sdw_rt711_sdca.c @@ -143,6 +143,9 @@ int sof_sdw_rt711_sdca_exit(struct snd_soc_card *card, struct snd_soc_dai_link * if (!ctx->headset_codec_dev) return 0; + if (!SOF_RT711_JDSRC(sof_sdw_quirk)) + return 0; + device_remove_software_node(ctx->headset_codec_dev); put_device(ctx->headset_codec_dev); diff --git a/sound/soc/meson/axg-tdm-formatter.c b/sound/soc/meson/axg-tdm-formatter.c index 9883dc777f63..63333a2b0a9c 100644 --- a/sound/soc/meson/axg-tdm-formatter.c +++ b/sound/soc/meson/axg-tdm-formatter.c @@ -30,27 +30,32 @@ int axg_tdm_formatter_set_channel_masks(struct regmap *map, struct axg_tdm_stream *ts, unsigned int offset) { - unsigned int val, ch = ts->channels; - unsigned long mask; - int i, j; + unsigned int ch = ts->channels; + u32 val[AXG_TDM_NUM_LANES]; + int i, j, k; + + /* + * We need to mimick the slot distribution used by the HW to keep the + * channel placement consistent regardless of the number of channel + * in the stream. This is why the odd algorithm below is used. + */ + memset(val, 0, sizeof(*val) * AXG_TDM_NUM_LANES); /* * Distribute the channels of the stream over the available slots - * of each TDM lane + * of each TDM lane. We need to go over the 32 slots ... */ - for (i = 0; i < AXG_TDM_NUM_LANES; i++) { - val = 0; - mask = ts->mask[i]; - - for (j = find_first_bit(&mask, 32); - (j < 32) && ch; - j = find_next_bit(&mask, 32, j + 1)) { - val |= 1 << j; - ch -= 1; + for (i = 0; (i < 32) && ch; i += 2) { + /* ... of all the lanes ... */ + for (j = 0; j < AXG_TDM_NUM_LANES; j++) { + /* ... then distribute the channels in pairs */ + for (k = 0; k < 2; k++) { + if ((BIT(i + k) & ts->mask[j]) && ch) { + val[j] |= BIT(i + k); + ch -= 1; + } + } } - - regmap_write(map, offset, val); - offset += regmap_get_reg_stride(map); } /* @@ -63,6 +68,11 @@ int axg_tdm_formatter_set_channel_masks(struct regmap *map, return -EINVAL; } + for (i = 0; i < AXG_TDM_NUM_LANES; i++) { + regmap_write(map, offset, val[i]); + offset += regmap_get_reg_stride(map); + } + return 0; } EXPORT_SYMBOL_GPL(axg_tdm_formatter_set_channel_masks); diff --git a/sound/soc/sof/amd/acp.h b/sound/soc/sof/amd/acp.h index bcfd0bccf75a..20d8d576a81b 100644 --- a/sound/soc/sof/amd/acp.h +++ b/sound/soc/sof/amd/acp.h @@ -57,6 +57,9 @@ #define ACP_DSP_TO_HOST_IRQ 0x04 +#define ACP_RN_PCI_ID 0x01 +#define ACP_RMB_PCI_ID 0x6F + #define HOST_BRIDGE_CZN 0x1630 #define HOST_BRIDGE_VGH 0x1645 #define HOST_BRIDGE_RMB 0x14B5 diff --git a/sound/soc/sof/amd/pci-rmb.c b/sound/soc/sof/amd/pci-rmb.c index eaf70ea6e556..58b3092425f1 100644 --- a/sound/soc/sof/amd/pci-rmb.c +++ b/sound/soc/sof/amd/pci-rmb.c @@ -65,6 +65,9 @@ static int acp_pci_rmb_probe(struct pci_dev *pci, const struct pci_device_id *pc { unsigned int flag; + if (pci->revision != ACP_RMB_PCI_ID) + return -ENODEV; + flag = snd_amd_acp_find_config(pci); if (flag != FLAG_AMD_SOF && flag != FLAG_AMD_SOF_ONLY_DMIC) return -ENODEV; diff --git a/sound/soc/sof/amd/pci-rn.c b/sound/soc/sof/amd/pci-rn.c index 4809cb644152..7409e21ce5aa 100644 --- a/sound/soc/sof/amd/pci-rn.c +++ b/sound/soc/sof/amd/pci-rn.c @@ -65,6 +65,9 @@ static int acp_pci_rn_probe(struct pci_dev *pci, const struct pci_device_id *pci { unsigned int flag; + if (pci->revision != ACP_RN_PCI_ID) + return -ENODEV; + flag = snd_amd_acp_find_config(pci); if (flag != FLAG_AMD_SOF && flag != FLAG_AMD_SOF_ONLY_DMIC) return -ENODEV; diff --git a/sound/soc/sof/core.c b/sound/soc/sof/core.c index 625977a29d8a..75a1e2c6539f 100644 --- a/sound/soc/sof/core.c +++ b/sound/soc/sof/core.c @@ -479,8 +479,10 @@ int snd_sof_device_shutdown(struct device *dev) if (IS_ENABLED(CONFIG_SND_SOC_SOF_PROBE_WORK_QUEUE)) cancel_work_sync(&sdev->probe_work); - if (sdev->fw_state == SOF_FW_BOOT_COMPLETE) + if (sdev->fw_state == SOF_FW_BOOT_COMPLETE) { + sof_fw_trace_free(sdev); return snd_sof_shutdown(sdev); + } return 0; } diff --git a/sound/soc/sof/intel/hda.c b/sound/soc/sof/intel/hda.c index 02c67d662b07..8e07dccbd6b8 100644 --- a/sound/soc/sof/intel/hda.c +++ b/sound/soc/sof/intel/hda.c @@ -1308,12 +1308,22 @@ static void hda_generic_machine_select(struct snd_sof_dev *sdev, hda_mach->mach_params.dmic_num = dmic_num; pdata->tplg_filename = tplg_filename; - if (codec_num == 2) { + if (codec_num == 2 || + (codec_num == 1 && !HDA_IDISP_CODEC(bus->codec_mask))) { /* * Prevent SoundWire links from starting when an external * HDaudio codec is used */ hda_mach->mach_params.link_mask = 0; + } else { + /* + * Allow SoundWire links to start when no external HDaudio codec + * was detected. This will not create a SoundWire card but + * will help detect if any SoundWire codec reports as ATTACHED. + */ + struct sof_intel_hda_dev *hdev = sdev->pdata->hw_pdata; + + hda_mach->mach_params.link_mask = hdev->info.link_mask; } *mach = hda_mach; diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h index efb4a3311cc5..5d72dc8441cb 100644 --- a/sound/usb/quirks-table.h +++ b/sound/usb/quirks-table.h @@ -4507,6 +4507,35 @@ YAMAHA_DEVICE(0x7010, "UB99"), } } }, +{ + /* Advanced modes of the Mythware XA001AU. + * For the standard mode, Mythware XA001AU has ID ffad:a001 + */ + USB_DEVICE_VENDOR_SPEC(0xffad, 0xa001), + .driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) { + .vendor_name = "Mythware", + .product_name = "XA001AU", + .ifnum = QUIRK_ANY_INTERFACE, + .type = QUIRK_COMPOSITE, + .data = (const struct snd_usb_audio_quirk[]) { + { + .ifnum = 0, + .type = QUIRK_IGNORE_INTERFACE, + }, + { + .ifnum = 1, + .type = QUIRK_AUDIO_STANDARD_INTERFACE, + }, + { + .ifnum = 2, + .type = QUIRK_AUDIO_STANDARD_INTERFACE, + }, + { + .ifnum = -1 + } + } + } +}, #undef USB_DEVICE_VENDOR_SPEC #undef USB_AUDIO_DEVICE diff --git a/sound/usb/stream.c b/sound/usb/stream.c index f10f4e6d3fb8..3d4add94e367 100644 --- a/sound/usb/stream.c +++ b/sound/usb/stream.c @@ -1093,6 +1093,7 @@ static int __snd_usb_parse_audio_interface(struct snd_usb_audio *chip, int i, altno, err, stream; struct audioformat *fp = NULL; struct snd_usb_power_domain *pd = NULL; + bool set_iface_first; int num, protocol; dev = chip->dev; @@ -1223,11 +1224,19 @@ static int __snd_usb_parse_audio_interface(struct snd_usb_audio *chip, return err; } + set_iface_first = false; + if (protocol == UAC_VERSION_1 || + (chip->quirk_flags & QUIRK_FLAG_SET_IFACE_FIRST)) + set_iface_first = true; + /* try to set the interface... */ usb_set_interface(chip->dev, iface_no, 0); + if (set_iface_first) + usb_set_interface(chip->dev, iface_no, altno); snd_usb_init_pitch(chip, fp); snd_usb_init_sample_rate(chip, fp, fp->rate_max); - usb_set_interface(chip->dev, iface_no, altno); + if (!set_iface_first) + usb_set_interface(chip->dev, iface_no, altno); } return 0; } diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index b71f4f2ecdd5..9ecc62861194 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -14,7 +14,7 @@ * Defines x86 CPU feature bits */ #define NCAPINTS 20 /* N 32-bit words worth of info */ -#define NBUGINTS 1 /* N 32-bit bug flags */ +#define NBUGINTS 2 /* N 32-bit bug flags */ /* * Note: If the comment begins with a quoted string, that string is used diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index 1c253b4b7ce0..1ed49ab4e871 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -798,3 +798,9 @@ bool arch_is_rethunk(struct symbol *sym) { return !strcmp(sym->name, "__x86_return_thunk"); } + +bool arch_is_embedded_insn(struct symbol *sym) +{ + return !strcmp(sym->name, "retbleed_return_thunk") || + !strcmp(sym->name, "srso_safe_ret"); +} diff --git a/tools/objtool/check.c b/tools/objtool/check.c index c2c350933a23..f8008ab31eef 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -379,7 +379,7 @@ static int decode_instructions(struct objtool_file *file) if (!strcmp(sec->name, ".noinstr.text") || !strcmp(sec->name, ".entry.text") || - !strncmp(sec->name, ".text.__x86.", 12)) + !strncmp(sec->name, ".text..__x86.", 13)) sec->noinstr = true; for (offset = 0; offset < sec->sh.sh_size; offset += insn->len) { @@ -1164,16 +1164,33 @@ static int add_ignore_alternatives(struct objtool_file *file) return 0; } +/* + * Symbols that replace INSN_CALL_DYNAMIC, every (tail) call to such a symbol + * will be added to the .retpoline_sites section. + */ __weak bool arch_is_retpoline(struct symbol *sym) { return false; } +/* + * Symbols that replace INSN_RETURN, every (tail) call to such a symbol + * will be added to the .return_sites section. + */ __weak bool arch_is_rethunk(struct symbol *sym) { return false; } +/* + * Symbols that are embedded inside other instructions, because sometimes crazy + * code exists. These are mostly ignored for validation purposes. + */ +__weak bool arch_is_embedded_insn(struct symbol *sym) +{ + return false; +} + #define NEGATIVE_RELOC ((void *)-1L) static struct reloc *insn_reloc(struct objtool_file *file, struct instruction *insn) @@ -1430,14 +1447,14 @@ static int add_jump_destinations(struct objtool_file *file) struct symbol *sym = find_symbol_by_offset(dest_sec, dest_off); /* - * This is a special case for zen_untrain_ret(). + * This is a special case for retbleed_untrain_ret(). * It jumps to __x86_return_thunk(), but objtool * can't find the thunk's starting RET * instruction, because the RET is also in the * middle of another instruction. Objtool only * knows about the outer instruction. */ - if (sym && sym->return_thunk) { + if (sym && sym->embedded_insn) { add_return_call(file, insn, false); continue; } @@ -2327,6 +2344,9 @@ static int classify_symbols(struct objtool_file *file) if (arch_is_rethunk(func)) func->return_thunk = true; + if (arch_is_embedded_insn(func)) + func->embedded_insn = true; + if (!strcmp(func->name, "__fentry__")) func->fentry = true; @@ -2450,12 +2470,17 @@ static int decode_sections(struct objtool_file *file) return 0; } -static bool is_fentry_call(struct instruction *insn) +static bool is_special_call(struct instruction *insn) { - if (insn->type == INSN_CALL && - insn->call_dest && - insn->call_dest->fentry) - return true; + if (insn->type == INSN_CALL) { + struct symbol *dest = insn->call_dest; + + if (!dest) + return false; + + if (dest->fentry) + return true; + } return false; } @@ -3448,7 +3473,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, if (ret) return ret; - if (opts.stackval && func && !is_fentry_call(insn) && + if (opts.stackval && func && !is_special_call(insn) && !has_valid_stack_frame(&state)) { WARN_FUNC("call without frame pointer save/setup", sec, insn->offset); diff --git a/tools/objtool/include/objtool/arch.h b/tools/objtool/include/objtool/arch.h index beb2f3aa94ff..861c0c60ac81 100644 --- a/tools/objtool/include/objtool/arch.h +++ b/tools/objtool/include/objtool/arch.h @@ -90,6 +90,7 @@ int arch_decode_hint_reg(u8 sp_reg, int *base); bool arch_is_retpoline(struct symbol *sym); bool arch_is_rethunk(struct symbol *sym); +bool arch_is_embedded_insn(struct symbol *sym); int arch_rewrite_retpolines(struct objtool_file *file); diff --git a/tools/objtool/include/objtool/elf.h b/tools/objtool/include/objtool/elf.h index 16f4067b82ae..5d4a841fbd31 100644 --- a/tools/objtool/include/objtool/elf.h +++ b/tools/objtool/include/objtool/elf.h @@ -60,6 +60,7 @@ struct symbol { u8 return_thunk : 1; u8 fentry : 1; u8 profiling_func : 1; + u8 embedded_insn : 1; struct list_head pv_target; }; diff --git a/tools/perf/tests/shell/test_uprobe_from_different_cu.sh b/tools/perf/tests/shell/test_uprobe_from_different_cu.sh index 00d2e0e2e0c2..319f36ebb9a4 100644 --- a/tools/perf/tests/shell/test_uprobe_from_different_cu.sh +++ b/tools/perf/tests/shell/test_uprobe_from_different_cu.sh @@ -4,6 +4,12 @@ set -e +# skip if there's no gcc +if ! [ -x "$(command -v gcc)" ]; then + echo "failed: no gcc compiler" + exit 2 +fi + temp_dir=$(mktemp -d /tmp/perf-uprobe-different-cu-sh.XXXXXXXXXX) cleanup() @@ -11,7 +17,7 @@ cleanup() trap - EXIT TERM INT if [[ "${temp_dir}" =~ ^/tmp/perf-uprobe-different-cu-sh.*$ ]]; then echo "--- Cleaning up ---" - perf probe -x ${temp_dir}/testfile -d foo + perf probe -x ${temp_dir}/testfile -d foo || true rm -f "${temp_dir}/"* rmdir "${temp_dir}" fi diff --git a/tools/testing/radix-tree/regression1.c b/tools/testing/radix-tree/regression1.c index a61c7bcbc72d..63f468bf8245 100644 --- a/tools/testing/radix-tree/regression1.c +++ b/tools/testing/radix-tree/regression1.c @@ -177,7 +177,7 @@ void regression1_test(void) nr_threads = 2; pthread_barrier_init(&worker_barrier, NULL, nr_threads); - threads = malloc(nr_threads * sizeof(pthread_t *)); + threads = malloc(nr_threads * sizeof(*threads)); for (i = 0; i < nr_threads; i++) { arg = i; diff --git a/tools/testing/selftests/drivers/net/bonding/bond-break-lacpdu-tx.sh b/tools/testing/selftests/drivers/net/bonding/bond-break-lacpdu-tx.sh index 47ab90596acb..6358df5752f9 100755 --- a/tools/testing/selftests/drivers/net/bonding/bond-break-lacpdu-tx.sh +++ b/tools/testing/selftests/drivers/net/bonding/bond-break-lacpdu-tx.sh @@ -57,8 +57,8 @@ ip link add name veth2-bond type veth peer name veth2-end # add ports ip link set fbond master fab-br0 -ip link set veth1-bond down master fbond -ip link set veth2-bond down master fbond +ip link set veth1-bond master fbond +ip link set veth2-bond master fbond # bring up ip link set veth1-end up diff --git a/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh b/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh index 7d9e73a43a49..0c47faff9274 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh @@ -98,12 +98,12 @@ sb_occ_etc_check() port_pool_test() { - local exp_max_occ=288 + local exp_max_occ=$(devlink_cell_size_get) local max_occ devlink sb occupancy clearmax $DEVLINK_DEV - $MZ $h1 -c 1 -p 160 -a $h1mac -b $h2mac -A 192.0.1.1 -B 192.0.1.2 \ + $MZ $h1 -c 1 -p 10 -a $h1mac -b $h2mac -A 192.0.1.1 -B 192.0.1.2 \ -t ip -q devlink sb occupancy snapshot $DEVLINK_DEV @@ -126,12 +126,12 @@ port_pool_test() port_tc_ip_test() { - local exp_max_occ=288 + local exp_max_occ=$(devlink_cell_size_get) local max_occ devlink sb occupancy clearmax $DEVLINK_DEV - $MZ $h1 -c 1 -p 160 -a $h1mac -b $h2mac -A 192.0.1.1 -B 192.0.1.2 \ + $MZ $h1 -c 1 -p 10 -a $h1mac -b $h2mac -A 192.0.1.1 -B 192.0.1.2 \ -t ip -q devlink sb occupancy snapshot $DEVLINK_DEV @@ -154,16 +154,12 @@ port_tc_ip_test() port_tc_arp_test() { - local exp_max_occ=96 + local exp_max_occ=$(devlink_cell_size_get) local max_occ - if [[ $MLXSW_CHIP != "mlxsw_spectrum" ]]; then - exp_max_occ=144 - fi - devlink sb occupancy clearmax $DEVLINK_DEV - $MZ $h1 -c 1 -p 160 -a $h1mac -A 192.0.1.1 -t arp -q + $MZ $h1 -c 1 -p 10 -a $h1mac -A 192.0.1.1 -t arp -q devlink sb occupancy snapshot $DEVLINK_DEV diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 69c58362c0ed..48d1a68be1d5 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -71,14 +71,60 @@ TEST_GEN_FILES += bind_bhash TEST_GEN_PROGS += sk_bind_sendto_listen TEST_GEN_PROGS += sk_connect_zero_addr TEST_PROGS += test_ingress_egress_chaining.sh +TEST_GEN_FILES += nat6to4.o TEST_FILES := settings include ../lib.mk -include bpf/Makefile - $(OUTPUT)/reuseport_bpf_numa: LDLIBS += -lnuma $(OUTPUT)/tcp_mmap: LDLIBS += -lpthread $(OUTPUT)/tcp_inq: LDLIBS += -lpthread $(OUTPUT)/bind_bhash: LDLIBS += -lpthread + +# Rules to generate bpf obj nat6to4.o +CLANG ?= clang +SCRATCH_DIR := $(OUTPUT)/tools +BUILD_DIR := $(SCRATCH_DIR)/build +BPFDIR := $(abspath ../../../lib/bpf) +APIDIR := $(abspath ../../../include/uapi) + +CCINCLUDE += -I../bpf +CCINCLUDE += -I../../../../usr/include/ +CCINCLUDE += -I$(SCRATCH_DIR)/include + +BPFOBJ := $(BUILD_DIR)/libbpf/libbpf.a + +MAKE_DIRS := $(BUILD_DIR)/libbpf +$(MAKE_DIRS): + mkdir -p $@ + +# Get Clang's default includes on this system, as opposed to those seen by +# '-target bpf'. This fixes "missing" files on some architectures/distros, +# such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc. +# +# Use '-idirafter': Don't interfere with include mechanics except where the +# build would have failed anyways. +define get_sys_includes +$(shell $(1) $(2) -v -E - </dev/null 2>&1 \ + | sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }') \ +$(shell $(1) $(2) -dM -E - </dev/null | grep '__riscv_xlen ' | awk '{printf("-D__riscv_xlen=%d -D__BITS_PER_LONG=%d", $$3, $$3)}') +endef + +ifneq ($(CROSS_COMPILE),) +CLANG_TARGET_ARCH = --target=$(notdir $(CROSS_COMPILE:%-=%)) +endif + +CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG),$(CLANG_TARGET_ARCH)) + +$(OUTPUT)/nat6to4.o: nat6to4.c $(BPFOBJ) | $(MAKE_DIRS) + $(CLANG) -O2 -target bpf -c $< $(CCINCLUDE) $(CLANG_SYS_INCLUDES) -o $@ + +$(BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile) \ + $(APIDIR)/linux/bpf.h \ + | $(BUILD_DIR)/libbpf + $(MAKE) $(submake_extras) -C $(BPFDIR) OUTPUT=$(BUILD_DIR)/libbpf/ \ + EXTRA_CFLAGS='-g -O0' \ + DESTDIR=$(SCRATCH_DIR) prefix= all install_headers + +EXTRA_CLEAN := $(SCRATCH_DIR) diff --git a/tools/testing/selftests/net/bpf/Makefile b/tools/testing/selftests/net/bpf/Makefile deleted file mode 100644 index 8ccaf8732eb2..000000000000 --- a/tools/testing/selftests/net/bpf/Makefile +++ /dev/null @@ -1,14 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 - -CLANG ?= clang -CCINCLUDE += -I../../bpf -CCINCLUDE += -I../../../../lib -CCINCLUDE += -I../../../../../usr/include/ - -TEST_CUSTOM_PROGS = $(OUTPUT)/bpf/nat6to4.o -all: $(TEST_CUSTOM_PROGS) - -$(OUTPUT)/%.o: %.c - $(CLANG) -O2 -target bpf -c $< $(CCINCLUDE) -o $@ - -EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index 0f5e88c8f4ff..df8d90b51867 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -1981,6 +1981,11 @@ basic() run_cmd "$IP link set dev lo up" + # Dump should not loop endlessly when maximum nexthop ID is configured. + run_cmd "$IP nexthop add id $((2**32-1)) blackhole" + run_cmd "timeout 5 $IP nexthop" + log_test $? 0 "Maximum nexthop ID dump" + # # groups # @@ -2201,6 +2206,11 @@ basic_res() run_cmd "$IP nexthop bucket list fdb" log_test $? 255 "Dump all nexthop buckets with invalid 'fdb' keyword" + # Dump should not loop endlessly when maximum nexthop ID is configured. + run_cmd "$IP nexthop add id $((2**32-1)) group 1/2 type resilient buckets 4" + run_cmd "timeout 5 $IP nexthop bucket" + log_test $? 0 "Maximum nexthop ID dump" + # # resilient nexthop buckets get requests # diff --git a/tools/testing/selftests/net/forwarding/ethtool.sh b/tools/testing/selftests/net/forwarding/ethtool.sh index dbb9fcf759e0..aa2eafb7b243 100755 --- a/tools/testing/selftests/net/forwarding/ethtool.sh +++ b/tools/testing/selftests/net/forwarding/ethtool.sh @@ -286,6 +286,8 @@ different_speeds_autoneg_on() ethtool -s $h1 autoneg on } +skip_on_veth + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/net/forwarding/ethtool_extended_state.sh b/tools/testing/selftests/net/forwarding/ethtool_extended_state.sh index 072faa77f53b..17f89c3b7c02 100755 --- a/tools/testing/selftests/net/forwarding/ethtool_extended_state.sh +++ b/tools/testing/selftests/net/forwarding/ethtool_extended_state.sh @@ -108,6 +108,8 @@ no_cable() ip link set dev $swp3 down } +skip_on_veth + setup_prepare tests_run diff --git a/tools/testing/selftests/net/forwarding/hw_stats_l3_gre.sh b/tools/testing/selftests/net/forwarding/hw_stats_l3_gre.sh index eb9ec4a68f84..7594bbb49029 100755 --- a/tools/testing/selftests/net/forwarding/hw_stats_l3_gre.sh +++ b/tools/testing/selftests/net/forwarding/hw_stats_l3_gre.sh @@ -99,6 +99,8 @@ test_stats_rx() test_stats g2a rx } +skip_on_veth + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh b/tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh index 9f5b3e2e5e95..49fa94b53a1c 100755 --- a/tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh +++ b/tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh @@ -14,6 +14,8 @@ ALL_TESTS=" NUM_NETIFS=4 source lib.sh +require_command $TROUTE6 + h1_create() { simple_if_init $h1 2001:1:1::2/64 diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index f4721f1b2886..06027772cf79 100755 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -30,6 +30,7 @@ REQUIRE_MZ=${REQUIRE_MZ:=yes} REQUIRE_MTOOLS=${REQUIRE_MTOOLS:=no} STABLE_MAC_ADDRS=${STABLE_MAC_ADDRS:=no} TCPDUMP_EXTRA_FLAGS=${TCPDUMP_EXTRA_FLAGS:=} +TROUTE6=${TROUTE6:=traceroute6} relative_path="${BASH_SOURCE%/*}" if [[ "$relative_path" == "${BASH_SOURCE}" ]]; then @@ -137,6 +138,17 @@ check_locked_port_support() fi } +skip_on_veth() +{ + local kind=$(ip -j -d link show dev ${NETIFS[p1]} | + jq -r '.[].linkinfo.info_kind') + + if [[ $kind == veth ]]; then + echo "SKIP: Test cannot be run with veth pairs" + exit $ksft_skip + fi +} + if [[ "$(id -u)" -ne 0 ]]; then echo "SKIP: need root privileges" exit $ksft_skip @@ -199,6 +211,11 @@ create_netif_veth() for ((i = 1; i <= NUM_NETIFS; ++i)); do local j=$((i+1)) + if [ -z ${NETIFS[p$i]} ]; then + echo "SKIP: Cannot create interface. Name not specified" + exit $ksft_skip + fi + ip link show dev ${NETIFS[p$i]} &> /dev/null if [[ $? -ne 0 ]]; then ip link add ${NETIFS[p$i]} type veth \ diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh b/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh index aff88f78e339..5ea9d63915f7 100755 --- a/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh @@ -72,7 +72,8 @@ test_span_gre_ttl() RET=0 - mirror_install $swp1 ingress $tundev "matchall $tcflags" + mirror_install $swp1 ingress $tundev \ + "prot ip flower $tcflags ip_prot icmp" tc filter add dev $h3 ingress pref 77 prot $prot \ flower skip_hw ip_ttl 50 action pass diff --git a/tools/testing/selftests/net/forwarding/settings b/tools/testing/selftests/net/forwarding/settings new file mode 100644 index 000000000000..e7b9417537fb --- /dev/null +++ b/tools/testing/selftests/net/forwarding/settings @@ -0,0 +1 @@ +timeout=0 diff --git a/tools/testing/selftests/net/forwarding/tc_actions.sh b/tools/testing/selftests/net/forwarding/tc_actions.sh index 919c0dd9fe4b..b0f5e55d2d0b 100755 --- a/tools/testing/selftests/net/forwarding/tc_actions.sh +++ b/tools/testing/selftests/net/forwarding/tc_actions.sh @@ -9,6 +9,8 @@ NUM_NETIFS=4 source tc_common.sh source lib.sh +require_command ncat + tcflags="skip_hw" h1_create() @@ -201,10 +203,10 @@ mirred_egress_to_ingress_test() mirred_egress_to_ingress_tcp_test() { - local tmpfile=$(mktemp) tmpfile1=$(mktemp) + mirred_e2i_tf1=$(mktemp) mirred_e2i_tf2=$(mktemp) RET=0 - dd conv=sparse status=none if=/dev/zero bs=1M count=2 of=$tmpfile + dd conv=sparse status=none if=/dev/zero bs=1M count=2 of=$mirred_e2i_tf1 tc filter add dev $h1 protocol ip pref 100 handle 100 egress flower \ $tcflags ip_proto tcp src_ip 192.0.2.1 dst_ip 192.0.2.2 \ action ct commit nat src addr 192.0.2.2 pipe \ @@ -220,11 +222,11 @@ mirred_egress_to_ingress_tcp_test() ip_proto icmp \ action drop - ip vrf exec v$h1 nc --recv-only -w10 -l -p 12345 -o $tmpfile1 & + ip vrf exec v$h1 ncat --recv-only -w10 -l -p 12345 -o $mirred_e2i_tf2 & local rpid=$! - ip vrf exec v$h1 nc -w1 --send-only 192.0.2.2 12345 <$tmpfile + ip vrf exec v$h1 ncat -w1 --send-only 192.0.2.2 12345 <$mirred_e2i_tf1 wait -n $rpid - cmp -s $tmpfile $tmpfile1 + cmp -s $mirred_e2i_tf1 $mirred_e2i_tf2 check_err $? "server output check failed" $MZ $h1 -c 10 -p 64 -a $h1mac -b $h1mac -A 192.0.2.1 -B 192.0.2.1 \ @@ -241,7 +243,7 @@ mirred_egress_to_ingress_tcp_test() tc filter del dev $h1 egress protocol ip pref 101 handle 101 flower tc filter del dev $h1 ingress protocol ip pref 102 handle 102 flower - rm -f $tmpfile $tmpfile1 + rm -f $mirred_e2i_tf1 $mirred_e2i_tf2 log_test "mirred_egress_to_ingress_tcp ($tcflags)" } @@ -270,6 +272,8 @@ setup_prepare() cleanup() { + local tf + pre_cleanup switch_destroy @@ -280,6 +284,8 @@ cleanup() ip link set $swp2 address $swp2origmac ip link set $swp1 address $swp1origmac + + for tf in $mirred_e2i_tf1 $mirred_e2i_tf2; do rm -f $tf; done } mirred_egress_redirect_test() diff --git a/tools/testing/selftests/net/forwarding/tc_flower.sh b/tools/testing/selftests/net/forwarding/tc_flower.sh index 683711f41aa9..b1daad19b01e 100755 --- a/tools/testing/selftests/net/forwarding/tc_flower.sh +++ b/tools/testing/selftests/net/forwarding/tc_flower.sh @@ -52,8 +52,8 @@ match_dst_mac_test() tc_check_packets "dev $h2 ingress" 101 1 check_fail $? "Matched on a wrong filter" - tc_check_packets "dev $h2 ingress" 102 1 - check_err $? "Did not match on correct filter" + tc_check_packets "dev $h2 ingress" 102 0 + check_fail $? "Did not match on correct filter" tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower tc filter del dev $h2 ingress protocol ip pref 2 handle 102 flower @@ -78,8 +78,8 @@ match_src_mac_test() tc_check_packets "dev $h2 ingress" 101 1 check_fail $? "Matched on a wrong filter" - tc_check_packets "dev $h2 ingress" 102 1 - check_err $? "Did not match on correct filter" + tc_check_packets "dev $h2 ingress" 102 0 + check_fail $? "Did not match on correct filter" tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower tc filter del dev $h2 ingress protocol ip pref 2 handle 102 flower diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index a3108c3cff47..7b20878a1af5 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -650,6 +650,7 @@ pm_nl_del_endpoint() local addr=$3 if [ $ip_mptcp -eq 1 ]; then + [ $id -ne 0 ] && addr='' ip -n $ns mptcp endpoint delete id $id $addr else ip netns exec $ns ./pm_nl_ctl del $id $addr @@ -740,10 +741,11 @@ pm_nl_check_endpoint() fi if [ $ip_mptcp -eq 1 ]; then + # get line and trim trailing whitespace line=$(ip -n $ns mptcp endpoint show $id) + line="${line% }" # the dump order is: address id flags port dev - expected_line="$addr" - [ -n "$addr" ] && expected_line="$expected_line $addr" + [ -n "$addr" ] && expected_line="$addr" expected_line="$expected_line $id" [ -n "$_flags" ] && expected_line="$expected_line ${_flags//","/" "}" [ -n "$dev" ] && expected_line="$expected_line $dev" diff --git a/tools/testing/selftests/net/bpf/nat6to4.c b/tools/testing/selftests/net/nat6to4.c index ac54c36b25fc..ac54c36b25fc 100644 --- a/tools/testing/selftests/net/bpf/nat6to4.c +++ b/tools/testing/selftests/net/nat6to4.c diff --git a/tools/testing/selftests/net/udpgro_frglist.sh b/tools/testing/selftests/net/udpgro_frglist.sh index c9c4b9d65839..0a6359bed0b9 100755 --- a/tools/testing/selftests/net/udpgro_frglist.sh +++ b/tools/testing/selftests/net/udpgro_frglist.sh @@ -40,8 +40,8 @@ run_one() { ip -n "${PEER_NS}" link set veth1 xdp object ${BPF_FILE} section xdp tc -n "${PEER_NS}" qdisc add dev veth1 clsact - tc -n "${PEER_NS}" filter add dev veth1 ingress prio 4 protocol ipv6 bpf object-file ../bpf/nat6to4.o section schedcls/ingress6/nat_6 direct-action - tc -n "${PEER_NS}" filter add dev veth1 egress prio 4 protocol ip bpf object-file ../bpf/nat6to4.o section schedcls/egress4/snat4 direct-action + tc -n "${PEER_NS}" filter add dev veth1 ingress prio 4 protocol ipv6 bpf object-file nat6to4.o section schedcls/ingress6/nat_6 direct-action + tc -n "${PEER_NS}" filter add dev veth1 egress prio 4 protocol ip bpf object-file nat6to4.o section schedcls/egress4/snat4 direct-action echo ${rx_args} ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${rx_args} -r & @@ -88,8 +88,8 @@ if [ ! -f ${BPF_FILE} ]; then exit -1 fi -if [ ! -f bpf/nat6to4.o ]; then - echo "Missing nat6to4 helper. Build bpfnat6to4.o selftest first" +if [ ! -f nat6to4.o ]; then + echo "Missing nat6to4 helper. Build bpf nat6to4.o selftest first" exit -1 fi diff --git a/tools/testing/selftests/rseq/Makefile b/tools/testing/selftests/rseq/Makefile index 3a173e184566..cb5a9fc629fe 100644 --- a/tools/testing/selftests/rseq/Makefile +++ b/tools/testing/selftests/rseq/Makefile @@ -4,8 +4,10 @@ ifneq ($(shell $(CC) --version 2>&1 | head -n 1 | grep clang),) CLANG_FLAGS += -no-integrated-as endif +top_srcdir = ../../../.. + CFLAGS += -O2 -Wall -g -I./ $(KHDR_INCLUDES) -L$(OUTPUT) -Wl,-rpath=./ \ - $(CLANG_FLAGS) + $(CLANG_FLAGS) -I$(top_srcdir)/tools/include LDLIBS += -lpthread -ldl # Own dependencies because we only want to build against 1st prerequisite, but diff --git a/tools/testing/selftests/rseq/rseq.c b/tools/testing/selftests/rseq/rseq.c index 4177f9507bbe..e20191fb40d4 100644 --- a/tools/testing/selftests/rseq/rseq.c +++ b/tools/testing/selftests/rseq/rseq.c @@ -29,12 +29,22 @@ #include <dlfcn.h> #include <stddef.h> +#include <linux/compiler.h> + #include "../kselftest.h" #include "rseq.h" -static const ptrdiff_t *libc_rseq_offset_p; -static const unsigned int *libc_rseq_size_p; -static const unsigned int *libc_rseq_flags_p; +/* + * Define weak versions to play nice with binaries that are statically linked + * against a libc that doesn't support registering its own rseq. + */ +__weak ptrdiff_t __rseq_offset; +__weak unsigned int __rseq_size; +__weak unsigned int __rseq_flags; + +static const ptrdiff_t *libc_rseq_offset_p = &__rseq_offset; +static const unsigned int *libc_rseq_size_p = &__rseq_size; +static const unsigned int *libc_rseq_flags_p = &__rseq_flags; /* Offset from the thread pointer to the rseq area. */ ptrdiff_t rseq_offset; @@ -108,9 +118,17 @@ int rseq_unregister_current_thread(void) static __attribute__((constructor)) void rseq_init(void) { - libc_rseq_offset_p = dlsym(RTLD_NEXT, "__rseq_offset"); - libc_rseq_size_p = dlsym(RTLD_NEXT, "__rseq_size"); - libc_rseq_flags_p = dlsym(RTLD_NEXT, "__rseq_flags"); + /* + * If the libc's registered rseq size isn't already valid, it may be + * because the binary is dynamically linked and not necessarily due to + * libc not having registered a restartable sequence. Try to find the + * symbols if that's the case. + */ + if (!*libc_rseq_size_p) { + libc_rseq_offset_p = dlsym(RTLD_NEXT, "__rseq_offset"); + libc_rseq_size_p = dlsym(RTLD_NEXT, "__rseq_size"); + libc_rseq_flags_p = dlsym(RTLD_NEXT, "__rseq_flags"); + } if (libc_rseq_size_p && libc_rseq_offset_p && libc_rseq_flags_p && *libc_rseq_size_p != 0) { /* rseq registration owned by glibc */ diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json index a44455372646..08d4861c2e78 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json @@ -131,5 +131,30 @@ "teardown": [ "echo \"1\" > /sys/bus/netdevsim/del_device" ] + }, + { + "id": "3e1e", + "name": "Add taprio Qdisc with an invalid cycle-time", + "category": [ + "qdisc", + "taprio" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "echo \"1 1 8\" > /sys/bus/netdevsim/new_device", + "$TC qdisc add dev $ETH root handle 1: taprio num_tc 3 map 2 2 1 0 2 2 2 2 2 2 2 2 2 2 2 2 queues 1@0 1@0 1@0 base-time 1000000000 sched-entry S 01 300000 flags 0x1 clockid CLOCK_TAI cycle-time 4294967296 || /bin/true", + "$IP link set dev $ETH up", + "$IP addr add 10.10.10.10/24 dev $ETH" + ], + "cmdUnderTest": "/bin/true", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $ETH", + "matchPattern": "qdisc taprio 1: root refcnt", + "matchCount": "0", + "teardown": [ + "echo \"1\" > /sys/bus/netdevsim/del_device" + ] } ] |