diff options
Diffstat (limited to 'arch')
184 files changed, 1640 insertions, 1600 deletions
diff --git a/arch/alpha/include/asm/Kbuild b/arch/alpha/include/asm/Kbuild index bf8475ce85ee..baa152b9348e 100644 --- a/arch/alpha/include/asm/Kbuild +++ b/arch/alpha/include/asm/Kbuild @@ -1,7 +1,6 @@ generic-y += clkdev.h -generic-y += cputime.h generic-y += exec.h generic-y += export.h generic-y += irq_work.h diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c index 54d8616644e2..9d27a7d333dc 100644 --- a/arch/alpha/kernel/osf_sys.c +++ b/arch/alpha/kernel/osf_sys.c @@ -1145,7 +1145,7 @@ struct rusage32 { SYSCALL_DEFINE2(osf_getrusage, int, who, struct rusage32 __user *, ru) { struct rusage32 r; - cputime_t utime, stime; + u64 utime, stime; unsigned long utime_jiffies, stime_jiffies; if (who != RUSAGE_SELF && who != RUSAGE_CHILDREN) @@ -1155,16 +1155,16 @@ SYSCALL_DEFINE2(osf_getrusage, int, who, struct rusage32 __user *, ru) switch (who) { case RUSAGE_SELF: task_cputime(current, &utime, &stime); - utime_jiffies = cputime_to_jiffies(utime); - stime_jiffies = cputime_to_jiffies(stime); + utime_jiffies = nsecs_to_jiffies(utime); + stime_jiffies = nsecs_to_jiffies(stime); jiffies_to_timeval32(utime_jiffies, &r.ru_utime); jiffies_to_timeval32(stime_jiffies, &r.ru_stime); r.ru_minflt = current->min_flt; r.ru_majflt = current->maj_flt; break; case RUSAGE_CHILDREN: - utime_jiffies = cputime_to_jiffies(current->signal->cutime); - stime_jiffies = cputime_to_jiffies(current->signal->cstime); + utime_jiffies = nsecs_to_jiffies(current->signal->cutime); + stime_jiffies = nsecs_to_jiffies(current->signal->cstime); jiffies_to_timeval32(utime_jiffies, &r.ru_utime); jiffies_to_timeval32(stime_jiffies, &r.ru_stime); r.ru_minflt = current->signal->cmin_flt; diff --git a/arch/arc/include/asm/Kbuild b/arch/arc/include/asm/Kbuild index c332604606dd..63a04013d05a 100644 --- a/arch/arc/include/asm/Kbuild +++ b/arch/arc/include/asm/Kbuild @@ -2,7 +2,6 @@ generic-y += auxvec.h generic-y += bitsperlong.h generic-y += bugs.h generic-y += clkdev.h -generic-y += cputime.h generic-y += device.h generic-y += div64.h generic-y += emergency-restart.h diff --git a/arch/arc/kernel/unaligned.c b/arch/arc/kernel/unaligned.c index 91ebe382147f..5f69c3bd59bb 100644 --- a/arch/arc/kernel/unaligned.c +++ b/arch/arc/kernel/unaligned.c @@ -243,7 +243,7 @@ int misaligned_fixup(unsigned long address, struct pt_regs *regs, /* clear any remanants of delay slot */ if (delay_mode(regs)) { - regs->ret = regs->bta ~1U; + regs->ret = regs->bta & ~1U; regs->status32 &= ~STATUS_DE_MASK; } else { regs->ret += state.instr_len; diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile index f10fe8526239..01d178a2009f 100644 --- a/arch/arm/boot/dts/Makefile +++ b/arch/arm/boot/dts/Makefile @@ -617,7 +617,7 @@ dtb-$(CONFIG_ARCH_ORION5X) += \ orion5x-lacie-ethernet-disk-mini-v2.dtb \ orion5x-linkstation-lsgl.dtb \ orion5x-linkstation-lswtgl.dtb \ - orion5x-lschl.dtb \ + orion5x-linkstation-lschl.dtb \ orion5x-lswsgl.dtb \ orion5x-maxtor-shared-storage-2.dtb \ orion5x-netgear-wnr854t.dtb \ diff --git a/arch/arm/boot/dts/imx1.dtsi b/arch/arm/boot/dts/imx1.dtsi index b792eee3899b..2ee40bc9ec21 100644 --- a/arch/arm/boot/dts/imx1.dtsi +++ b/arch/arm/boot/dts/imx1.dtsi @@ -18,6 +18,14 @@ / { #address-cells = <1>; #size-cells = <1>; + /* + * The decompressor and also some bootloaders rely on a + * pre-existing /chosen node to be available to insert the + * command line and merge other ATAGS info. + * Also for U-Boot there must be a pre-existing /memory node. + */ + chosen {}; + memory { device_type = "memory"; reg = <0 0>; }; aliases { gpio0 = &gpio1; diff --git a/arch/arm/boot/dts/imx23.dtsi b/arch/arm/boot/dts/imx23.dtsi index ac2a9da62b6c..43ccbbf754a3 100644 --- a/arch/arm/boot/dts/imx23.dtsi +++ b/arch/arm/boot/dts/imx23.dtsi @@ -16,6 +16,14 @@ #size-cells = <1>; interrupt-parent = <&icoll>; + /* + * The decompressor and also some bootloaders rely on a + * pre-existing /chosen node to be available to insert the + * command line and merge other ATAGS info. + * Also for U-Boot there must be a pre-existing /memory node. + */ + chosen {}; + memory { device_type = "memory"; reg = <0 0>; }; aliases { gpio0 = &gpio0; diff --git a/arch/arm/boot/dts/imx25.dtsi b/arch/arm/boot/dts/imx25.dtsi index 831d09a28155..acd475659156 100644 --- a/arch/arm/boot/dts/imx25.dtsi +++ b/arch/arm/boot/dts/imx25.dtsi @@ -14,6 +14,14 @@ / { #address-cells = <1>; #size-cells = <1>; + /* + * The decompressor and also some bootloaders rely on a + * pre-existing /chosen node to be available to insert the + * command line and merge other ATAGS info. + * Also for U-Boot there must be a pre-existing /memory node. + */ + chosen {}; + memory { device_type = "memory"; reg = <0 0>; }; aliases { ethernet0 = &fec; diff --git a/arch/arm/boot/dts/imx27.dtsi b/arch/arm/boot/dts/imx27.dtsi index 9d8b5969ee3b..b397384248f4 100644 --- a/arch/arm/boot/dts/imx27.dtsi +++ b/arch/arm/boot/dts/imx27.dtsi @@ -19,6 +19,14 @@ / { #address-cells = <1>; #size-cells = <1>; + /* + * The decompressor and also some bootloaders rely on a + * pre-existing /chosen node to be available to insert the + * command line and merge other ATAGS info. + * Also for U-Boot there must be a pre-existing /memory node. + */ + chosen {}; + memory { device_type = "memory"; reg = <0 0>; }; aliases { ethernet0 = &fec; diff --git a/arch/arm/boot/dts/imx28.dtsi b/arch/arm/boot/dts/imx28.dtsi index 3aabf65a6a52..d6a2190b60ef 100644 --- a/arch/arm/boot/dts/imx28.dtsi +++ b/arch/arm/boot/dts/imx28.dtsi @@ -17,6 +17,14 @@ #size-cells = <1>; interrupt-parent = <&icoll>; + /* + * The decompressor and also some bootloaders rely on a + * pre-existing /chosen node to be available to insert the + * command line and merge other ATAGS info. + * Also for U-Boot there must be a pre-existing /memory node. + */ + chosen {}; + memory { device_type = "memory"; reg = <0 0>; }; aliases { ethernet0 = &mac0; diff --git a/arch/arm/boot/dts/imx31.dtsi b/arch/arm/boot/dts/imx31.dtsi index 85cd8be22f71..23b0d2cf9acd 100644 --- a/arch/arm/boot/dts/imx31.dtsi +++ b/arch/arm/boot/dts/imx31.dtsi @@ -12,6 +12,14 @@ / { #address-cells = <1>; #size-cells = <1>; + /* + * The decompressor and also some bootloaders rely on a + * pre-existing /chosen node to be available to insert the + * command line and merge other ATAGS info. + * Also for U-Boot there must be a pre-existing /memory node. + */ + chosen {}; + memory { device_type = "memory"; reg = <0 0>; }; aliases { serial0 = &uart1; diff --git a/arch/arm/boot/dts/imx35.dtsi b/arch/arm/boot/dts/imx35.dtsi index 9f40e6229189..d0496c65cea2 100644 --- a/arch/arm/boot/dts/imx35.dtsi +++ b/arch/arm/boot/dts/imx35.dtsi @@ -13,6 +13,14 @@ / { #address-cells = <1>; #size-cells = <1>; + /* + * The decompressor and also some bootloaders rely on a + * pre-existing /chosen node to be available to insert the + * command line and merge other ATAGS info. + * Also for U-Boot there must be a pre-existing /memory node. + */ + chosen {}; + memory { device_type = "memory"; reg = <0 0>; }; aliases { ethernet0 = &fec; diff --git a/arch/arm/boot/dts/imx50.dtsi b/arch/arm/boot/dts/imx50.dtsi index fe0221e4cbf7..ceae909e2201 100644 --- a/arch/arm/boot/dts/imx50.dtsi +++ b/arch/arm/boot/dts/imx50.dtsi @@ -17,6 +17,14 @@ / { #address-cells = <1>; #size-cells = <1>; + /* + * The decompressor and also some bootloaders rely on a + * pre-existing /chosen node to be available to insert the + * command line and merge other ATAGS info. + * Also for U-Boot there must be a pre-existing /memory node. + */ + chosen {}; + memory { device_type = "memory"; reg = <0 0>; }; aliases { ethernet0 = &fec; diff --git a/arch/arm/boot/dts/imx51.dtsi b/arch/arm/boot/dts/imx51.dtsi index 33526cade735..1ee1d542d9ad 100644 --- a/arch/arm/boot/dts/imx51.dtsi +++ b/arch/arm/boot/dts/imx51.dtsi @@ -19,6 +19,14 @@ / { #address-cells = <1>; #size-cells = <1>; + /* + * The decompressor and also some bootloaders rely on a + * pre-existing /chosen node to be available to insert the + * command line and merge other ATAGS info. + * Also for U-Boot there must be a pre-existing /memory node. + */ + chosen {}; + memory { device_type = "memory"; reg = <0 0>; }; aliases { ethernet0 = &fec; diff --git a/arch/arm/boot/dts/imx53.dtsi b/arch/arm/boot/dts/imx53.dtsi index ca51dc03e327..2e516f4985e4 100644 --- a/arch/arm/boot/dts/imx53.dtsi +++ b/arch/arm/boot/dts/imx53.dtsi @@ -19,6 +19,14 @@ / { #address-cells = <1>; #size-cells = <1>; + /* + * The decompressor and also some bootloaders rely on a + * pre-existing /chosen node to be available to insert the + * command line and merge other ATAGS info. + * Also for U-Boot there must be a pre-existing /memory node. + */ + chosen {}; + memory { device_type = "memory"; reg = <0 0>; }; aliases { ethernet0 = &fec; diff --git a/arch/arm/boot/dts/imx6dl.dtsi b/arch/arm/boot/dts/imx6dl.dtsi index 1ade1951e620..7aa120fbdc71 100644 --- a/arch/arm/boot/dts/imx6dl.dtsi +++ b/arch/arm/boot/dts/imx6dl.dtsi @@ -137,7 +137,7 @@ &gpio4 { gpio-ranges = <&iomuxc 5 136 1>, <&iomuxc 6 145 1>, <&iomuxc 7 150 1>, <&iomuxc 8 146 1>, <&iomuxc 9 151 1>, <&iomuxc 10 147 1>, - <&iomuxc 11 151 1>, <&iomuxc 12 148 1>, <&iomuxc 13 153 1>, + <&iomuxc 11 152 1>, <&iomuxc 12 148 1>, <&iomuxc 13 153 1>, <&iomuxc 14 149 1>, <&iomuxc 15 154 1>, <&iomuxc 16 39 7>, <&iomuxc 23 56 1>, <&iomuxc 24 61 7>, <&iomuxc 31 46 1>; }; diff --git a/arch/arm/boot/dts/imx6qdl.dtsi b/arch/arm/boot/dts/imx6qdl.dtsi index 89b834f3fa17..e7d30f45b161 100644 --- a/arch/arm/boot/dts/imx6qdl.dtsi +++ b/arch/arm/boot/dts/imx6qdl.dtsi @@ -16,6 +16,14 @@ / { #address-cells = <1>; #size-cells = <1>; + /* + * The decompressor and also some bootloaders rely on a + * pre-existing /chosen node to be available to insert the + * command line and merge other ATAGS info. + * Also for U-Boot there must be a pre-existing /memory node. + */ + chosen {}; + memory { device_type = "memory"; reg = <0 0>; }; aliases { ethernet0 = &fec; diff --git a/arch/arm/boot/dts/imx6sl.dtsi b/arch/arm/boot/dts/imx6sl.dtsi index 19cbd879c448..cc9572ea2860 100644 --- a/arch/arm/boot/dts/imx6sl.dtsi +++ b/arch/arm/boot/dts/imx6sl.dtsi @@ -14,6 +14,14 @@ / { #address-cells = <1>; #size-cells = <1>; + /* + * The decompressor and also some bootloaders rely on a + * pre-existing /chosen node to be available to insert the + * command line and merge other ATAGS info. + * Also for U-Boot there must be a pre-existing /memory node. + */ + chosen {}; + memory { device_type = "memory"; reg = <0 0>; }; aliases { ethernet0 = &fec; diff --git a/arch/arm/boot/dts/imx6sx.dtsi b/arch/arm/boot/dts/imx6sx.dtsi index 10f333016197..dd4ec85ecbaa 100644 --- a/arch/arm/boot/dts/imx6sx.dtsi +++ b/arch/arm/boot/dts/imx6sx.dtsi @@ -15,6 +15,14 @@ / { #address-cells = <1>; #size-cells = <1>; + /* + * The decompressor and also some bootloaders rely on a + * pre-existing /chosen node to be available to insert the + * command line and merge other ATAGS info. + * Also for U-Boot there must be a pre-existing /memory node. + */ + chosen {}; + memory { device_type = "memory"; reg = <0 0>; }; aliases { can0 = &flexcan1; diff --git a/arch/arm/boot/dts/imx6ul.dtsi b/arch/arm/boot/dts/imx6ul.dtsi index 39845a7e0463..53d3f8e41e9b 100644 --- a/arch/arm/boot/dts/imx6ul.dtsi +++ b/arch/arm/boot/dts/imx6ul.dtsi @@ -15,6 +15,14 @@ / { #address-cells = <1>; #size-cells = <1>; + /* + * The decompressor and also some bootloaders rely on a + * pre-existing /chosen node to be available to insert the + * command line and merge other ATAGS info. + * Also for U-Boot there must be a pre-existing /memory node. + */ + chosen {}; + memory { device_type = "memory"; reg = <0 0>; }; aliases { ethernet0 = &fec1; diff --git a/arch/arm/boot/dts/imx7s.dtsi b/arch/arm/boot/dts/imx7s.dtsi index 8ff2cbdd8f0d..be33dfc86838 100644 --- a/arch/arm/boot/dts/imx7s.dtsi +++ b/arch/arm/boot/dts/imx7s.dtsi @@ -50,6 +50,14 @@ / { #address-cells = <1>; #size-cells = <1>; + /* + * The decompressor and also some bootloaders rely on a + * pre-existing /chosen node to be available to insert the + * command line and merge other ATAGS info. + * Also for U-Boot there must be a pre-existing /memory node. + */ + chosen {}; + memory { device_type = "memory"; reg = <0 0>; }; aliases { gpio0 = &gpio1; diff --git a/arch/arm/boot/dts/orion5x-lschl.dts b/arch/arm/boot/dts/orion5x-linkstation-lschl.dts index 947409252845..ea6c881634b9 100644 --- a/arch/arm/boot/dts/orion5x-lschl.dts +++ b/arch/arm/boot/dts/orion5x-linkstation-lschl.dts @@ -2,7 +2,7 @@ * Device Tree file for Buffalo Linkstation LS-CHLv3 * * Copyright (C) 2016 Ash Hughes <ashley.hughes@blueyonder.co.uk> - * Copyright (C) 2015, 2016 + * Copyright (C) 2015-2017 * Roger Shimizu <rogershimizu@gmail.com> * * This file is dual-licensed: you can use it either under the terms @@ -52,7 +52,7 @@ #include <dt-bindings/gpio/gpio.h> / { - model = "Buffalo Linkstation Live v3 (LS-CHL)"; + model = "Buffalo Linkstation LiveV3 (LS-CHL)"; compatible = "buffalo,lschl", "marvell,orion5x-88f5182", "marvell,orion5x"; memory { /* 128 MB */ diff --git a/arch/arm/boot/dts/stih407-family.dtsi b/arch/arm/boot/dts/stih407-family.dtsi index c8b2944e304a..ace97e8576db 100644 --- a/arch/arm/boot/dts/stih407-family.dtsi +++ b/arch/arm/boot/dts/stih407-family.dtsi @@ -680,6 +680,7 @@ phy-names = "usb2-phy", "usb3-phy"; phys = <&usb2_picophy0>, <&phy_port2 PHY_TYPE_USB3>; + snps,dis_u3_susphy_quirk; }; }; diff --git a/arch/arm/configs/ezx_defconfig b/arch/arm/configs/ezx_defconfig index ea316c4b890e..d3f1768840e2 100644 --- a/arch/arm/configs/ezx_defconfig +++ b/arch/arm/configs/ezx_defconfig @@ -64,8 +64,8 @@ CONFIG_NETFILTER=y CONFIG_NETFILTER_NETLINK_QUEUE=m CONFIG_NF_CONNTRACK=m CONFIG_NF_CONNTRACK_EVENTS=y -CONFIG_NF_CT_PROTO_SCTP=m -CONFIG_NF_CT_PROTO_UDPLITE=m +CONFIG_NF_CT_PROTO_SCTP=y +CONFIG_NF_CT_PROTO_UDPLITE=y CONFIG_NF_CONNTRACK_AMANDA=m CONFIG_NF_CONNTRACK_FTP=m CONFIG_NF_CONNTRACK_H323=m diff --git a/arch/arm/configs/imote2_defconfig b/arch/arm/configs/imote2_defconfig index 18e59feaa307..7f479cdb3479 100644 --- a/arch/arm/configs/imote2_defconfig +++ b/arch/arm/configs/imote2_defconfig @@ -56,8 +56,8 @@ CONFIG_NETFILTER=y CONFIG_NETFILTER_NETLINK_QUEUE=m CONFIG_NF_CONNTRACK=m CONFIG_NF_CONNTRACK_EVENTS=y -CONFIG_NF_CT_PROTO_SCTP=m -CONFIG_NF_CT_PROTO_UDPLITE=m +CONFIG_NF_CT_PROTO_SCTP=y +CONFIG_NF_CT_PROTO_UDPLITE=y CONFIG_NF_CONNTRACK_AMANDA=m CONFIG_NF_CONNTRACK_FTP=m CONFIG_NF_CONNTRACK_H323=m diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig index 028d2b70e3b5..f57ec511e7ae 100644 --- a/arch/arm/configs/multi_v7_defconfig +++ b/arch/arm/configs/multi_v7_defconfig @@ -824,6 +824,7 @@ CONFIG_QCOM_SMSM=y CONFIG_QCOM_WCNSS_CTRL=m CONFIG_ROCKCHIP_PM_DOMAINS=y CONFIG_COMMON_CLK_QCOM=y +CONFIG_QCOM_CLK_RPM=y CONFIG_CHROME_PLATFORMS=y CONFIG_STAGING_BOARD=y CONFIG_CROS_EC_CHARDEV=m diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild index efb21757d41f..b14e8c7d71bd 100644 --- a/arch/arm/include/asm/Kbuild +++ b/arch/arm/include/asm/Kbuild @@ -2,7 +2,6 @@ generic-y += bitsperlong.h generic-y += clkdev.h -generic-y += cputime.h generic-y += current.h generic-y += early_ioremap.h generic-y += emergency-restart.h diff --git a/arch/arm/include/asm/efi.h b/arch/arm/include/asm/efi.h index 0b06f5341b45..e4e6a9d6a825 100644 --- a/arch/arm/include/asm/efi.h +++ b/arch/arm/include/asm/efi.h @@ -55,6 +55,7 @@ void efi_virtmap_unload(void); #define efi_call_early(f, ...) sys_table_arg->boottime->f(__VA_ARGS__) #define __efi_call_early(f, ...) f(__VA_ARGS__) +#define efi_call_runtime(f, ...) sys_table_arg->runtime->f(__VA_ARGS__) #define efi_is_64bit() (false) #define efi_call_proto(protocol, f, instance, ...) \ diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h index 1f59ea051bab..b7e0125c0bbf 100644 --- a/arch/arm/include/asm/uaccess.h +++ b/arch/arm/include/asm/uaccess.h @@ -478,11 +478,10 @@ extern unsigned long __must_check arm_copy_from_user(void *to, const void __user *from, unsigned long n); static inline unsigned long __must_check -__copy_from_user(void *to, const void __user *from, unsigned long n) +__arch_copy_from_user(void *to, const void __user *from, unsigned long n) { unsigned int __ua_flags; - check_object_size(to, n, false); __ua_flags = uaccess_save_and_enable(); n = arm_copy_from_user(to, from, n); uaccess_restore(__ua_flags); @@ -495,18 +494,15 @@ extern unsigned long __must_check __copy_to_user_std(void __user *to, const void *from, unsigned long n); static inline unsigned long __must_check -__copy_to_user(void __user *to, const void *from, unsigned long n) +__arch_copy_to_user(void __user *to, const void *from, unsigned long n) { #ifndef CONFIG_UACCESS_WITH_MEMCPY unsigned int __ua_flags; - - check_object_size(from, n, true); __ua_flags = uaccess_save_and_enable(); n = arm_copy_to_user(to, from, n); uaccess_restore(__ua_flags); return n; #else - check_object_size(from, n, true); return arm_copy_to_user(to, from, n); #endif } @@ -526,25 +522,49 @@ __clear_user(void __user *addr, unsigned long n) } #else -#define __copy_from_user(to, from, n) (memcpy(to, (void __force *)from, n), 0) -#define __copy_to_user(to, from, n) (memcpy((void __force *)to, from, n), 0) +#define __arch_copy_from_user(to, from, n) \ + (memcpy(to, (void __force *)from, n), 0) +#define __arch_copy_to_user(to, from, n) \ + (memcpy((void __force *)to, from, n), 0) #define __clear_user(addr, n) (memset((void __force *)addr, 0, n), 0) #endif -static inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n) +static inline unsigned long __must_check +__copy_from_user(void *to, const void __user *from, unsigned long n) +{ + check_object_size(to, n, false); + return __arch_copy_from_user(to, from, n); +} + +static inline unsigned long __must_check +copy_from_user(void *to, const void __user *from, unsigned long n) { unsigned long res = n; + + check_object_size(to, n, false); + if (likely(access_ok(VERIFY_READ, from, n))) - res = __copy_from_user(to, from, n); + res = __arch_copy_from_user(to, from, n); if (unlikely(res)) memset(to + (n - res), 0, res); return res; } -static inline unsigned long __must_check copy_to_user(void __user *to, const void *from, unsigned long n) +static inline unsigned long __must_check +__copy_to_user(void __user *to, const void *from, unsigned long n) { + check_object_size(from, n, true); + + return __arch_copy_to_user(to, from, n); +} + +static inline unsigned long __must_check +copy_to_user(void __user *to, const void *from, unsigned long n) +{ + check_object_size(from, n, true); + if (access_ok(VERIFY_WRITE, to, n)) - n = __copy_to_user(to, from, n); + n = __arch_copy_to_user(to, from, n); return n; } diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c index ce131ed5939d..ae738a6319f6 100644 --- a/arch/arm/kernel/ptrace.c +++ b/arch/arm/kernel/ptrace.c @@ -600,7 +600,7 @@ static int gpr_set(struct task_struct *target, const void *kbuf, const void __user *ubuf) { int ret; - struct pt_regs newregs; + struct pt_regs newregs = *task_pt_regs(target); ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &newregs, diff --git a/arch/arm/lib/getuser.S b/arch/arm/lib/getuser.S index 8ecfd15c3a02..df73914e81c8 100644 --- a/arch/arm/lib/getuser.S +++ b/arch/arm/lib/getuser.S @@ -67,7 +67,7 @@ ENTRY(__get_user_4) ENDPROC(__get_user_4) ENTRY(__get_user_8) - check_uaccess r0, 8, r1, r2, __get_user_bad + check_uaccess r0, 8, r1, r2, __get_user_bad8 #ifdef CONFIG_THUMB2_KERNEL 5: TUSER(ldr) r2, [r0] 6: TUSER(ldr) r3, [r0, #4] diff --git a/arch/arm/mach-imx/mmdc.c b/arch/arm/mach-imx/mmdc.c index 699157759120..c03bf28d8bbc 100644 --- a/arch/arm/mach-imx/mmdc.c +++ b/arch/arm/mach-imx/mmdc.c @@ -60,7 +60,6 @@ #define to_mmdc_pmu(p) container_of(p, struct mmdc_pmu, pmu) -static enum cpuhp_state cpuhp_mmdc_state; static int ddr_type; struct fsl_mmdc_devtype_data { @@ -82,6 +81,7 @@ static const struct of_device_id imx_mmdc_dt_ids[] = { #ifdef CONFIG_PERF_EVENTS +static enum cpuhp_state cpuhp_mmdc_state; static DEFINE_IDA(mmdc_ida); PMU_EVENT_ATTR_STRING(total-cycles, mmdc_pmu_total_cycles, "event=0x00") diff --git a/arch/arm/mach-shmobile/Kconfig b/arch/arm/mach-shmobile/Kconfig index 2bb4b09f079e..ad7d604ff001 100644 --- a/arch/arm/mach-shmobile/Kconfig +++ b/arch/arm/mach-shmobile/Kconfig @@ -57,6 +57,7 @@ config ARCH_R7S72100 select PM select PM_GENERIC_DOMAINS select SYS_SUPPORTS_SH_MTU2 + select RENESAS_OSTM config ARCH_R8A73A4 bool "R-Mobile APE6 (R8A73A40)" diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index 3a2e678b8d30..0122ad1a6027 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -610,9 +610,9 @@ static int __init early_abort_handler(unsigned long addr, unsigned int fsr, void __init early_abt_enable(void) { - fsr_info[22].fn = early_abort_handler; + fsr_info[FSR_FS_AEA].fn = early_abort_handler; local_abt_enable(); - fsr_info[22].fn = do_bad; + fsr_info[FSR_FS_AEA].fn = do_bad; } #ifndef CONFIG_ARM_LPAE diff --git a/arch/arm/mm/fault.h b/arch/arm/mm/fault.h index 67532f242271..afc1f84e763b 100644 --- a/arch/arm/mm/fault.h +++ b/arch/arm/mm/fault.h @@ -11,11 +11,15 @@ #define FSR_FS5_0 (0x3f) #ifdef CONFIG_ARM_LPAE +#define FSR_FS_AEA 17 + static inline int fsr_fs(unsigned int fsr) { return fsr & FSR_FS5_0; } #else +#define FSR_FS_AEA 22 + static inline int fsr_fs(unsigned int fsr) { return (fsr & FSR_FS3_0) | (fsr & FSR_FS4) >> 6; diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 111742126897..f7dfd6d58659 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -96,7 +96,7 @@ config ARM64 select HAVE_RCU_TABLE_FREE select HAVE_SYSCALL_TRACEPOINTS select HAVE_KPROBES - select HAVE_KRETPROBES if HAVE_KPROBES + select HAVE_KRETPROBES select IOMMU_DMA if IOMMU_SUPPORT select IRQ_DOMAIN select IRQ_FORCED_THREADING diff --git a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi index eada0b58ba1c..0cbe24b49710 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi @@ -55,6 +55,24 @@ #address-cells = <2>; #size-cells = <2>; + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + /* 16 MiB reserved for Hardware ROM Firmware */ + hwrom_reserved: hwrom@0 { + reg = <0x0 0x0 0x0 0x1000000>; + no-map; + }; + + /* 2 MiB reserved for ARM Trusted Firmware (BL31) */ + secmon_reserved: secmon@10000000 { + reg = <0x0 0x10000000 0x0 0x200000>; + no-map; + }; + }; + cpus { #address-cells = <0x2>; #size-cells = <0x0>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts index 5d28e1cdc998..c59403adb387 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts @@ -151,6 +151,18 @@ status = "okay"; pinctrl-0 = <ð_rgmii_pins>; pinctrl-names = "default"; + phy-handle = <ð_phy0>; + + mdio { + compatible = "snps,dwmac-mdio"; + #address-cells = <1>; + #size-cells = <0>; + + eth_phy0: ethernet-phy@0 { + reg = <0>; + eee-broken-1000t; + }; + }; }; &ir { diff --git a/arch/arm64/crypto/aes-modes.S b/arch/arm64/crypto/aes-modes.S index c53dbeae79f2..838dad5c209f 100644 --- a/arch/arm64/crypto/aes-modes.S +++ b/arch/arm64/crypto/aes-modes.S @@ -193,15 +193,16 @@ AES_ENTRY(aes_cbc_encrypt) cbz w6, .Lcbcencloop ld1 {v0.16b}, [x5] /* get iv */ - enc_prepare w3, x2, x5 + enc_prepare w3, x2, x6 .Lcbcencloop: ld1 {v1.16b}, [x1], #16 /* get next pt block */ eor v0.16b, v0.16b, v1.16b /* ..and xor with iv */ - encrypt_block v0, w3, x2, x5, w6 + encrypt_block v0, w3, x2, x6, w7 st1 {v0.16b}, [x0], #16 subs w4, w4, #1 bne .Lcbcencloop + st1 {v0.16b}, [x5] /* return iv */ ret AES_ENDPROC(aes_cbc_encrypt) @@ -211,7 +212,7 @@ AES_ENTRY(aes_cbc_decrypt) cbz w6, .LcbcdecloopNx ld1 {v7.16b}, [x5] /* get iv */ - dec_prepare w3, x2, x5 + dec_prepare w3, x2, x6 .LcbcdecloopNx: #if INTERLEAVE >= 2 @@ -248,7 +249,7 @@ AES_ENTRY(aes_cbc_decrypt) .Lcbcdecloop: ld1 {v1.16b}, [x1], #16 /* get next ct block */ mov v0.16b, v1.16b /* ...and copy to v0 */ - decrypt_block v0, w3, x2, x5, w6 + decrypt_block v0, w3, x2, x6, w7 eor v0.16b, v0.16b, v7.16b /* xor with iv => pt */ mov v7.16b, v1.16b /* ct is next iv */ st1 {v0.16b}, [x0], #16 @@ -256,6 +257,7 @@ AES_ENTRY(aes_cbc_decrypt) bne .Lcbcdecloop .Lcbcdecout: FRAME_POP + st1 {v7.16b}, [x5] /* return iv */ ret AES_ENDPROC(aes_cbc_decrypt) @@ -267,24 +269,15 @@ AES_ENDPROC(aes_cbc_decrypt) AES_ENTRY(aes_ctr_encrypt) FRAME_PUSH - cbnz w6, .Lctrfirst /* 1st time around? */ - umov x5, v4.d[1] /* keep swabbed ctr in reg */ - rev x5, x5 -#if INTERLEAVE >= 2 - cmn w5, w4 /* 32 bit overflow? */ - bcs .Lctrinc - add x5, x5, #1 /* increment BE ctr */ - b .LctrincNx -#else - b .Lctrinc -#endif -.Lctrfirst: + cbz w6, .Lctrnotfirst /* 1st time around? */ enc_prepare w3, x2, x6 ld1 {v4.16b}, [x5] - umov x5, v4.d[1] /* keep swabbed ctr in reg */ - rev x5, x5 + +.Lctrnotfirst: + umov x8, v4.d[1] /* keep swabbed ctr in reg */ + rev x8, x8 #if INTERLEAVE >= 2 - cmn w5, w4 /* 32 bit overflow? */ + cmn w8, w4 /* 32 bit overflow? */ bcs .Lctrloop .LctrloopNx: subs w4, w4, #INTERLEAVE @@ -292,11 +285,11 @@ AES_ENTRY(aes_ctr_encrypt) #if INTERLEAVE == 2 mov v0.8b, v4.8b mov v1.8b, v4.8b - rev x7, x5 - add x5, x5, #1 + rev x7, x8 + add x8, x8, #1 ins v0.d[1], x7 - rev x7, x5 - add x5, x5, #1 + rev x7, x8 + add x8, x8, #1 ins v1.d[1], x7 ld1 {v2.16b-v3.16b}, [x1], #32 /* get 2 input blocks */ do_encrypt_block2x @@ -305,7 +298,7 @@ AES_ENTRY(aes_ctr_encrypt) st1 {v0.16b-v1.16b}, [x0], #32 #else ldr q8, =0x30000000200000001 /* addends 1,2,3[,0] */ - dup v7.4s, w5 + dup v7.4s, w8 mov v0.16b, v4.16b add v7.4s, v7.4s, v8.4s mov v1.16b, v4.16b @@ -323,18 +316,12 @@ AES_ENTRY(aes_ctr_encrypt) eor v2.16b, v7.16b, v2.16b eor v3.16b, v5.16b, v3.16b st1 {v0.16b-v3.16b}, [x0], #64 - add x5, x5, #INTERLEAVE + add x8, x8, #INTERLEAVE #endif - cbz w4, .LctroutNx -.LctrincNx: - rev x7, x5 + rev x7, x8 ins v4.d[1], x7 + cbz w4, .Lctrout b .LctrloopNx -.LctroutNx: - sub x5, x5, #1 - rev x7, x5 - ins v4.d[1], x7 - b .Lctrout .Lctr1x: adds w4, w4, #INTERLEAVE beq .Lctrout @@ -342,30 +329,39 @@ AES_ENTRY(aes_ctr_encrypt) .Lctrloop: mov v0.16b, v4.16b encrypt_block v0, w3, x2, x6, w7 + + adds x8, x8, #1 /* increment BE ctr */ + rev x7, x8 + ins v4.d[1], x7 + bcs .Lctrcarry /* overflow? */ + +.Lctrcarrydone: subs w4, w4, #1 bmi .Lctrhalfblock /* blocks < 0 means 1/2 block */ ld1 {v3.16b}, [x1], #16 eor v3.16b, v0.16b, v3.16b st1 {v3.16b}, [x0], #16 - beq .Lctrout -.Lctrinc: - adds x5, x5, #1 /* increment BE ctr */ - rev x7, x5 - ins v4.d[1], x7 - bcc .Lctrloop /* no overflow? */ - umov x7, v4.d[0] /* load upper word of ctr */ - rev x7, x7 /* ... to handle the carry */ - add x7, x7, #1 - rev x7, x7 - ins v4.d[0], x7 - b .Lctrloop + bne .Lctrloop + +.Lctrout: + st1 {v4.16b}, [x5] /* return next CTR value */ + FRAME_POP + ret + .Lctrhalfblock: ld1 {v3.8b}, [x1] eor v3.8b, v0.8b, v3.8b st1 {v3.8b}, [x0] -.Lctrout: FRAME_POP ret + +.Lctrcarry: + umov x7, v4.d[0] /* load upper word of ctr */ + rev x7, x7 /* ... to handle the carry */ + add x7, x7, #1 + rev x7, x7 + ins v4.d[0], x7 + b .Lctrcarrydone AES_ENDPROC(aes_ctr_encrypt) .ltorg diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild index 8365a84c2640..a12f1afc95a3 100644 --- a/arch/arm64/include/asm/Kbuild +++ b/arch/arm64/include/asm/Kbuild @@ -1,6 +1,5 @@ generic-y += bugs.h generic-y += clkdev.h -generic-y += cputime.h generic-y += delay.h generic-y += div64.h generic-y += dma.h diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h index eaa5bbe3fa87..b4b34004a21e 100644 --- a/arch/arm64/include/asm/arch_timer.h +++ b/arch/arm64/include/asm/arch_timer.h @@ -29,41 +29,29 @@ #include <clocksource/arm_arch_timer.h> -#if IS_ENABLED(CONFIG_FSL_ERRATUM_A008585) +#if IS_ENABLED(CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND) extern struct static_key_false arch_timer_read_ool_enabled; -#define needs_fsl_a008585_workaround() \ +#define needs_unstable_timer_counter_workaround() \ static_branch_unlikely(&arch_timer_read_ool_enabled) #else -#define needs_fsl_a008585_workaround() false +#define needs_unstable_timer_counter_workaround() false #endif -u32 __fsl_a008585_read_cntp_tval_el0(void); -u32 __fsl_a008585_read_cntv_tval_el0(void); -u64 __fsl_a008585_read_cntvct_el0(void); -/* - * The number of retries is an arbitrary value well beyond the highest number - * of iterations the loop has been observed to take. - */ -#define __fsl_a008585_read_reg(reg) ({ \ - u64 _old, _new; \ - int _retries = 200; \ - \ - do { \ - _old = read_sysreg(reg); \ - _new = read_sysreg(reg); \ - _retries--; \ - } while (unlikely(_old != _new) && _retries); \ - \ - WARN_ON_ONCE(!_retries); \ - _new; \ -}) +struct arch_timer_erratum_workaround { + const char *id; /* Indicate the Erratum ID */ + u32 (*read_cntp_tval_el0)(void); + u32 (*read_cntv_tval_el0)(void); + u64 (*read_cntvct_el0)(void); +}; + +extern const struct arch_timer_erratum_workaround *timer_unstable_counter_workaround; #define arch_timer_reg_read_stable(reg) \ ({ \ u64 _val; \ - if (needs_fsl_a008585_workaround()) \ - _val = __fsl_a008585_read_##reg(); \ + if (needs_unstable_timer_counter_workaround()) \ + _val = timer_unstable_counter_workaround->read_##reg();\ else \ _val = read_sysreg(reg); \ _val; \ diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h index 0b6b1633017f..e7445281e534 100644 --- a/arch/arm64/include/asm/efi.h +++ b/arch/arm64/include/asm/efi.h @@ -50,6 +50,7 @@ int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md); #define efi_call_early(f, ...) sys_table_arg->boottime->f(__VA_ARGS__) #define __efi_call_early(f, ...) f(__VA_ARGS__) +#define efi_call_runtime(f, ...) sys_table_arg->runtime->f(__VA_ARGS__) #define efi_is_64bit() (true) #define efi_call_proto(protocol, f, instance, ...) \ diff --git a/arch/avr32/include/asm/Kbuild b/arch/avr32/include/asm/Kbuild index 241b9b9729d8..3d7ef2c17a7c 100644 --- a/arch/avr32/include/asm/Kbuild +++ b/arch/avr32/include/asm/Kbuild @@ -1,6 +1,5 @@ generic-y += clkdev.h -generic-y += cputime.h generic-y += delay.h generic-y += device.h generic-y += div64.h diff --git a/arch/blackfin/include/asm/Kbuild b/arch/blackfin/include/asm/Kbuild index 2fb67b59d188..d6fa60b158be 100644 --- a/arch/blackfin/include/asm/Kbuild +++ b/arch/blackfin/include/asm/Kbuild @@ -2,7 +2,6 @@ generic-y += auxvec.h generic-y += bitsperlong.h generic-y += bugs.h -generic-y += cputime.h generic-y += current.h generic-y += device.h generic-y += div64.h diff --git a/arch/c6x/include/asm/Kbuild b/arch/c6x/include/asm/Kbuild index 64465e7e2245..4e9f57433f3a 100644 --- a/arch/c6x/include/asm/Kbuild +++ b/arch/c6x/include/asm/Kbuild @@ -5,7 +5,6 @@ generic-y += barrier.h generic-y += bitsperlong.h generic-y += bugs.h generic-y += clkdev.h -generic-y += cputime.h generic-y += current.h generic-y += device.h generic-y += div64.h diff --git a/arch/cris/include/asm/Kbuild b/arch/cris/include/asm/Kbuild index 1778805f6380..9f19e19bff9d 100644 --- a/arch/cris/include/asm/Kbuild +++ b/arch/cris/include/asm/Kbuild @@ -4,7 +4,6 @@ generic-y += barrier.h generic-y += bitsperlong.h generic-y += clkdev.h generic-y += cmpxchg.h -generic-y += cputime.h generic-y += device.h generic-y += div64.h generic-y += errno.h diff --git a/arch/frv/include/asm/Kbuild b/arch/frv/include/asm/Kbuild index 1fa084cf1a43..0f5b0d5d313c 100644 --- a/arch/frv/include/asm/Kbuild +++ b/arch/frv/include/asm/Kbuild @@ -1,6 +1,5 @@ generic-y += clkdev.h -generic-y += cputime.h generic-y += exec.h generic-y += irq_work.h generic-y += mcs_spinlock.h diff --git a/arch/h8300/include/asm/Kbuild b/arch/h8300/include/asm/Kbuild index 373cb23301e3..5efd0c87f3c0 100644 --- a/arch/h8300/include/asm/Kbuild +++ b/arch/h8300/include/asm/Kbuild @@ -5,7 +5,6 @@ generic-y += bugs.h generic-y += cacheflush.h generic-y += checksum.h generic-y += clkdev.h -generic-y += cputime.h generic-y += current.h generic-y += delay.h generic-y += device.h diff --git a/arch/hexagon/include/asm/Kbuild b/arch/hexagon/include/asm/Kbuild index db8ddabc6bd2..a43a7c90e4af 100644 --- a/arch/hexagon/include/asm/Kbuild +++ b/arch/hexagon/include/asm/Kbuild @@ -6,7 +6,6 @@ generic-y += barrier.h generic-y += bug.h generic-y += bugs.h generic-y += clkdev.h -generic-y += cputime.h generic-y += current.h generic-y += device.h generic-y += div64.h diff --git a/arch/ia64/include/asm/cputime.h b/arch/ia64/include/asm/cputime.h index e2d3f5baf265..3d665c0627a8 100644 --- a/arch/ia64/include/asm/cputime.h +++ b/arch/ia64/include/asm/cputime.h @@ -18,11 +18,7 @@ #ifndef __IA64_CPUTIME_H #define __IA64_CPUTIME_H -#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE -# include <asm-generic/cputime.h> -#else -# include <asm/processor.h> -# include <asm-generic/cputime_nsecs.h> +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE extern void arch_vtime_task_switch(struct task_struct *tsk); #endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ diff --git a/arch/ia64/include/asm/thread_info.h b/arch/ia64/include/asm/thread_info.h index c7026429816b..8742d741d19a 100644 --- a/arch/ia64/include/asm/thread_info.h +++ b/arch/ia64/include/asm/thread_info.h @@ -27,6 +27,12 @@ struct thread_info { mm_segment_t addr_limit; /* user-level address space limit */ int preempt_count; /* 0=premptable, <0=BUG; will also serve as bh-counter */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE + __u64 utime; + __u64 stime; + __u64 gtime; + __u64 hardirq_time; + __u64 softirq_time; + __u64 idle_time; __u64 ac_stamp; __u64 ac_leave; __u64 ac_stime; diff --git a/arch/ia64/kernel/head.S b/arch/ia64/kernel/head.S index c9b5e942f671..3204fddc439c 100644 --- a/arch/ia64/kernel/head.S +++ b/arch/ia64/kernel/head.S @@ -1031,7 +1031,7 @@ GLOBAL_ENTRY(ia64_native_sched_clock) END(ia64_native_sched_clock) #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE -GLOBAL_ENTRY(cycle_to_cputime) +GLOBAL_ENTRY(cycle_to_nsec) alloc r16=ar.pfs,1,0,0,0 addl r8=THIS_CPU(ia64_cpu_info) + IA64_CPUINFO_NSEC_PER_CYC_OFFSET,r0 ;; @@ -1047,7 +1047,7 @@ GLOBAL_ENTRY(cycle_to_cputime) ;; shrp r8=r9,r8,IA64_NSEC_PER_CYC_SHIFT br.ret.sptk.many rp -END(cycle_to_cputime) +END(cycle_to_nsec) #endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ #ifdef CONFIG_IA64_BRL_EMU diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c index 7ec7acc844c2..c483ece3eb84 100644 --- a/arch/ia64/kernel/setup.c +++ b/arch/ia64/kernel/setup.c @@ -619,6 +619,8 @@ setup_arch (char **cmdline_p) check_sal_cache_flush(); #endif paging_init(); + + clear_sched_clock_stable(); } /* diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c index 71775b95d6cc..faa116822c4c 100644 --- a/arch/ia64/kernel/time.c +++ b/arch/ia64/kernel/time.c @@ -21,6 +21,7 @@ #include <linux/timex.h> #include <linux/timekeeper_internal.h> #include <linux/platform_device.h> +#include <linux/cputime.h> #include <asm/machvec.h> #include <asm/delay.h> @@ -59,18 +60,43 @@ static struct clocksource *itc_clocksource; #include <linux/kernel_stat.h> -extern cputime_t cycle_to_cputime(u64 cyc); +extern u64 cycle_to_nsec(u64 cyc); -void vtime_account_user(struct task_struct *tsk) +void vtime_flush(struct task_struct *tsk) { - cputime_t delta_utime; struct thread_info *ti = task_thread_info(tsk); + u64 delta; - if (ti->ac_utime) { - delta_utime = cycle_to_cputime(ti->ac_utime); - account_user_time(tsk, delta_utime); - ti->ac_utime = 0; + if (ti->utime) + account_user_time(tsk, cycle_to_nsec(ti->utime)); + + if (ti->gtime) + account_guest_time(tsk, cycle_to_nsec(ti->gtime)); + + if (ti->idle_time) + account_idle_time(cycle_to_nsec(ti->idle_time)); + + if (ti->stime) { + delta = cycle_to_nsec(ti->stime); + account_system_index_time(tsk, delta, CPUTIME_SYSTEM); + } + + if (ti->hardirq_time) { + delta = cycle_to_nsec(ti->hardirq_time); + account_system_index_time(tsk, delta, CPUTIME_IRQ); + } + + if (ti->softirq_time) { + delta = cycle_to_nsec(ti->softirq_time)); + account_system_index_time(tsk, delta, CPUTIME_SOFTIRQ); } + + ti->utime = 0; + ti->gtime = 0; + ti->idle_time = 0; + ti->stime = 0; + ti->hardirq_time = 0; + ti->softirq_time = 0; } /* @@ -83,7 +109,7 @@ void arch_vtime_task_switch(struct task_struct *prev) struct thread_info *pi = task_thread_info(prev); struct thread_info *ni = task_thread_info(current); - pi->ac_stamp = ni->ac_stamp; + ni->ac_stamp = pi->ac_stamp; ni->ac_stime = ni->ac_utime = 0; } @@ -91,18 +117,15 @@ void arch_vtime_task_switch(struct task_struct *prev) * Account time for a transition between system, hard irq or soft irq state. * Note that this function is called with interrupts enabled. */ -static cputime_t vtime_delta(struct task_struct *tsk) +static __u64 vtime_delta(struct task_struct *tsk) { struct thread_info *ti = task_thread_info(tsk); - cputime_t delta_stime; - __u64 now; + __u64 now, delta_stime; WARN_ON_ONCE(!irqs_disabled()); now = ia64_get_itc(); - - delta_stime = cycle_to_cputime(ti->ac_stime + (now - ti->ac_stamp)); - ti->ac_stime = 0; + delta_stime = now - ti->ac_stamp; ti->ac_stamp = now; return delta_stime; @@ -110,15 +133,25 @@ static cputime_t vtime_delta(struct task_struct *tsk) void vtime_account_system(struct task_struct *tsk) { - cputime_t delta = vtime_delta(tsk); - - account_system_time(tsk, 0, delta); + struct thread_info *ti = task_thread_info(tsk); + __u64 stime = vtime_delta(tsk); + + if ((tsk->flags & PF_VCPU) && !irq_count()) + ti->gtime += stime; + else if (hardirq_count()) + ti->hardirq_time += stime; + else if (in_serving_softirq()) + ti->softirq_time += stime; + else + ti->stime += stime; } EXPORT_SYMBOL_GPL(vtime_account_system); void vtime_account_idle(struct task_struct *tsk) { - account_idle_time(vtime_delta(tsk)); + struct thread_info *ti = task_thread_info(tsk); + + ti->idle_time += vtime_delta(tsk); } #endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ diff --git a/arch/m32r/include/asm/Kbuild b/arch/m32r/include/asm/Kbuild index 860e440611c9..652100b64a71 100644 --- a/arch/m32r/include/asm/Kbuild +++ b/arch/m32r/include/asm/Kbuild @@ -1,6 +1,5 @@ generic-y += clkdev.h -generic-y += cputime.h generic-y += exec.h generic-y += irq_work.h generic-y += kvm_para.h diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild index 1f2e5d31cb24..6c76d6c24b3d 100644 --- a/arch/m68k/include/asm/Kbuild +++ b/arch/m68k/include/asm/Kbuild @@ -1,7 +1,6 @@ generic-y += barrier.h generic-y += bitsperlong.h generic-y += clkdev.h -generic-y += cputime.h generic-y += device.h generic-y += emergency-restart.h generic-y += errno.h diff --git a/arch/metag/include/asm/Kbuild b/arch/metag/include/asm/Kbuild index 167150c701d1..d3731f0db73b 100644 --- a/arch/metag/include/asm/Kbuild +++ b/arch/metag/include/asm/Kbuild @@ -2,7 +2,6 @@ generic-y += auxvec.h generic-y += bitsperlong.h generic-y += bugs.h generic-y += clkdev.h -generic-y += cputime.h generic-y += current.h generic-y += device.h generic-y += dma.h diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild index b0ae88c9fed9..6275eb051801 100644 --- a/arch/microblaze/include/asm/Kbuild +++ b/arch/microblaze/include/asm/Kbuild @@ -1,7 +1,6 @@ generic-y += barrier.h generic-y += clkdev.h -generic-y += cputime.h generic-y += device.h generic-y += exec.h generic-y += irq_work.h diff --git a/arch/mips/include/asm/Kbuild b/arch/mips/include/asm/Kbuild index 3269b742a75e..994b1c4392be 100644 --- a/arch/mips/include/asm/Kbuild +++ b/arch/mips/include/asm/Kbuild @@ -1,7 +1,6 @@ # MIPS headers generic-(CONFIG_GENERIC_CSUM) += checksum.h generic-y += clkdev.h -generic-y += cputime.h generic-y += current.h generic-y += dma-contiguous.h generic-y += emergency-restart.h diff --git a/arch/mips/kernel/binfmt_elfn32.c b/arch/mips/kernel/binfmt_elfn32.c index 9c7f3e136d50..4a2ff3953b99 100644 --- a/arch/mips/kernel/binfmt_elfn32.c +++ b/arch/mips/kernel/binfmt_elfn32.c @@ -99,15 +99,7 @@ jiffies_to_compat_timeval(unsigned long jiffies, struct compat_timeval *value) #undef TASK_SIZE #define TASK_SIZE TASK_SIZE32 -#undef cputime_to_timeval -#define cputime_to_timeval cputime_to_compat_timeval -static __inline__ void -cputime_to_compat_timeval(const cputime_t cputime, struct compat_timeval *value) -{ - unsigned long jiffies = cputime_to_jiffies(cputime); - - value->tv_usec = (jiffies % HZ) * (1000000L / HZ); - value->tv_sec = jiffies / HZ; -} +#undef ns_to_timeval +#define ns_to_timeval ns_to_compat_timeval #include "../../../fs/binfmt_elf.c" diff --git a/arch/mips/kernel/binfmt_elfo32.c b/arch/mips/kernel/binfmt_elfo32.c index 1ab34322dd97..3916404e7fd1 100644 --- a/arch/mips/kernel/binfmt_elfo32.c +++ b/arch/mips/kernel/binfmt_elfo32.c @@ -102,15 +102,7 @@ jiffies_to_compat_timeval(unsigned long jiffies, struct compat_timeval *value) #undef TASK_SIZE #define TASK_SIZE TASK_SIZE32 -#undef cputime_to_timeval -#define cputime_to_timeval cputime_to_compat_timeval -static __inline__ void -cputime_to_compat_timeval(const cputime_t cputime, struct compat_timeval *value) -{ - unsigned long jiffies = cputime_to_jiffies(cputime); - - value->tv_usec = (jiffies % HZ) * (1000000L / HZ); - value->tv_sec = jiffies / HZ; -} +#undef ns_to_timeval +#define ns_to_timeval ns_to_compat_timeval #include "../../../fs/binfmt_elf.c" diff --git a/arch/mn10300/include/asm/Kbuild b/arch/mn10300/include/asm/Kbuild index 1c8dd0f5cd5d..97f64c723a0c 100644 --- a/arch/mn10300/include/asm/Kbuild +++ b/arch/mn10300/include/asm/Kbuild @@ -1,7 +1,6 @@ generic-y += barrier.h generic-y += clkdev.h -generic-y += cputime.h generic-y += exec.h generic-y += irq_work.h generic-y += mcs_spinlock.h diff --git a/arch/nios2/include/asm/Kbuild b/arch/nios2/include/asm/Kbuild index d63330e88379..35b0e883761a 100644 --- a/arch/nios2/include/asm/Kbuild +++ b/arch/nios2/include/asm/Kbuild @@ -6,7 +6,6 @@ generic-y += bitsperlong.h generic-y += bug.h generic-y += bugs.h generic-y += clkdev.h -generic-y += cputime.h generic-y += current.h generic-y += device.h generic-y += div64.h diff --git a/arch/openrisc/include/asm/Kbuild b/arch/openrisc/include/asm/Kbuild index 2832f031fb11..ef8d1ccc3e45 100644 --- a/arch/openrisc/include/asm/Kbuild +++ b/arch/openrisc/include/asm/Kbuild @@ -12,7 +12,6 @@ generic-y += checksum.h generic-y += clkdev.h generic-y += cmpxchg-local.h generic-y += cmpxchg.h -generic-y += cputime.h generic-y += current.h generic-y += device.h generic-y += div64.h diff --git a/arch/parisc/include/asm/Kbuild b/arch/parisc/include/asm/Kbuild index 91f53c07f410..4e179d770d69 100644 --- a/arch/parisc/include/asm/Kbuild +++ b/arch/parisc/include/asm/Kbuild @@ -2,7 +2,6 @@ generic-y += auxvec.h generic-y += barrier.h generic-y += clkdev.h -generic-y += cputime.h generic-y += device.h generic-y += div64.h generic-y += emergency-restart.h diff --git a/arch/parisc/kernel/binfmt_elf32.c b/arch/parisc/kernel/binfmt_elf32.c index 00dc66f9c2ba..f2adcf33f8f2 100644 --- a/arch/parisc/kernel/binfmt_elf32.c +++ b/arch/parisc/kernel/binfmt_elf32.c @@ -91,14 +91,7 @@ struct elf_prpsinfo32 current->thread.map_base = DEFAULT_MAP_BASE32; \ current->thread.task_size = DEFAULT_TASK_SIZE32 \ -#undef cputime_to_timeval -#define cputime_to_timeval cputime_to_compat_timeval -static __inline__ void -cputime_to_compat_timeval(const cputime_t cputime, struct compat_timeval *value) -{ - unsigned long jiffies = cputime_to_jiffies(cputime); - value->tv_usec = (jiffies % HZ) * (1000000L / HZ); - value->tv_sec = jiffies / HZ; -} +#undef ns_to_timeval +#define ns_to_timeval ns_to_compat_timeval #include "../../../fs/binfmt_elf.c" diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c index 2e66a887788e..068ed3607bac 100644 --- a/arch/parisc/kernel/setup.c +++ b/arch/parisc/kernel/setup.c @@ -36,6 +36,7 @@ #undef PCI_DEBUG #include <linux/proc_fs.h> #include <linux/export.h> +#include <linux/sched.h> #include <asm/processor.h> #include <asm/sections.h> @@ -176,6 +177,7 @@ void __init setup_arch(char **cmdline_p) conswitchp = &dummy_con; /* we use do_take_over_console() later ! */ #endif + clear_sched_clock_stable(); } /* diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index a8ee573fe610..281f4f1fcd1f 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -164,7 +164,6 @@ config PPC select ARCH_HAS_SCALED_CPUTIME if VIRT_CPU_ACCOUNTING_NATIVE select HAVE_ARCH_HARDENED_USERCOPY select HAVE_KERNEL_GZIP - select HAVE_CC_STACKPROTECTOR config GENERIC_CSUM def_bool CPU_LITTLE_ENDIAN @@ -484,6 +483,7 @@ config RELOCATABLE bool "Build a relocatable kernel" depends on (PPC64 && !COMPILE_TEST) || (FLATMEM && (44x || FSL_BOOKE)) select NONSTATIC_KERNEL + select MODULE_REL_CRCS if MODVERSIONS help This builds a kernel image that is capable of running at the location the kernel is loaded at. For ppc32, there is no any diff --git a/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi b/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi index c744569a20e1..a97296c64eb2 100644 --- a/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi @@ -678,5 +678,6 @@ compatible = "fsl,t2080-l2-cache-controller"; reg = <0xc20000 0x40000>; next-level-cache = <&cpc>; + interrupts = <16 2 1 9>; }; }; diff --git a/arch/powerpc/include/asm/accounting.h b/arch/powerpc/include/asm/accounting.h index c133246df467..3abcf98ed2e0 100644 --- a/arch/powerpc/include/asm/accounting.h +++ b/arch/powerpc/include/asm/accounting.h @@ -12,9 +12,17 @@ /* Stuff for accurate time accounting */ struct cpu_accounting_data { - unsigned long user_time; /* accumulated usermode TB ticks */ - unsigned long system_time; /* accumulated system TB ticks */ - unsigned long user_time_scaled; /* accumulated usermode SPURR ticks */ + /* Accumulated cputime values to flush on ticks*/ + unsigned long utime; + unsigned long stime; + unsigned long utime_scaled; + unsigned long stime_scaled; + unsigned long gtime; + unsigned long hardirq_time; + unsigned long softirq_time; + unsigned long steal_time; + unsigned long idle_time; + /* Internal counters */ unsigned long starttime; /* TB value snapshot */ unsigned long starttime_user; /* TB value on exit to usermode */ unsigned long startspurr; /* SPURR value snapshot */ diff --git a/arch/powerpc/include/asm/cpu_has_feature.h b/arch/powerpc/include/asm/cpu_has_feature.h index b312b152461b..6e834caa3720 100644 --- a/arch/powerpc/include/asm/cpu_has_feature.h +++ b/arch/powerpc/include/asm/cpu_has_feature.h @@ -23,7 +23,9 @@ static __always_inline bool cpu_has_feature(unsigned long feature) { int i; +#ifndef __clang__ /* clang can't cope with this */ BUILD_BUG_ON(!__builtin_constant_p(feature)); +#endif #ifdef CONFIG_JUMP_LABEL_FEATURE_CHECK_DEBUG if (!static_key_initialized) { diff --git a/arch/powerpc/include/asm/cputime.h b/arch/powerpc/include/asm/cputime.h index aa2e6a34b872..99b541865d8d 100644 --- a/arch/powerpc/include/asm/cputime.h +++ b/arch/powerpc/include/asm/cputime.h @@ -16,12 +16,7 @@ #ifndef __POWERPC_CPUTIME_H #define __POWERPC_CPUTIME_H -#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE -#include <asm-generic/cputime.h> -#ifdef __KERNEL__ -static inline void setup_cputime_one_jiffy(void) { } -#endif -#else +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE #include <linux/types.h> #include <linux/time.h> @@ -36,65 +31,6 @@ typedef u64 __nocast cputime64_t; #define cmpxchg_cputime(ptr, old, new) cmpxchg(ptr, old, new) #ifdef __KERNEL__ - -/* - * One jiffy in timebase units computed during initialization - */ -extern cputime_t cputime_one_jiffy; - -/* - * Convert cputime <-> jiffies - */ -extern u64 __cputime_jiffies_factor; - -static inline unsigned long cputime_to_jiffies(const cputime_t ct) -{ - return mulhdu((__force u64) ct, __cputime_jiffies_factor); -} - -static inline cputime_t jiffies_to_cputime(const unsigned long jif) -{ - u64 ct; - unsigned long sec; - - /* have to be a little careful about overflow */ - ct = jif % HZ; - sec = jif / HZ; - if (ct) { - ct *= tb_ticks_per_sec; - do_div(ct, HZ); - } - if (sec) - ct += (cputime_t) sec * tb_ticks_per_sec; - return (__force cputime_t) ct; -} - -static inline void setup_cputime_one_jiffy(void) -{ - cputime_one_jiffy = jiffies_to_cputime(1); -} - -static inline cputime64_t jiffies64_to_cputime64(const u64 jif) -{ - u64 ct; - u64 sec = jif; - - /* have to be a little careful about overflow */ - ct = do_div(sec, HZ); - if (ct) { - ct *= tb_ticks_per_sec; - do_div(ct, HZ); - } - if (sec) - ct += (u64) sec * tb_ticks_per_sec; - return (__force cputime64_t) ct; -} - -static inline u64 cputime64_to_jiffies64(const cputime_t ct) -{ - return mulhdu((__force u64) ct, __cputime_jiffies_factor); -} - /* * Convert cputime <-> microseconds */ @@ -105,117 +41,6 @@ static inline unsigned long cputime_to_usecs(const cputime_t ct) return mulhdu((__force u64) ct, __cputime_usec_factor); } -static inline cputime_t usecs_to_cputime(const unsigned long us) -{ - u64 ct; - unsigned long sec; - - /* have to be a little careful about overflow */ - ct = us % 1000000; - sec = us / 1000000; - if (ct) { - ct *= tb_ticks_per_sec; - do_div(ct, 1000000); - } - if (sec) - ct += (cputime_t) sec * tb_ticks_per_sec; - return (__force cputime_t) ct; -} - -#define usecs_to_cputime64(us) usecs_to_cputime(us) - -/* - * Convert cputime <-> seconds - */ -extern u64 __cputime_sec_factor; - -static inline unsigned long cputime_to_secs(const cputime_t ct) -{ - return mulhdu((__force u64) ct, __cputime_sec_factor); -} - -static inline cputime_t secs_to_cputime(const unsigned long sec) -{ - return (__force cputime_t)((u64) sec * tb_ticks_per_sec); -} - -/* - * Convert cputime <-> timespec - */ -static inline void cputime_to_timespec(const cputime_t ct, struct timespec *p) -{ - u64 x = (__force u64) ct; - unsigned int frac; - - frac = do_div(x, tb_ticks_per_sec); - p->tv_sec = x; - x = (u64) frac * 1000000000; - do_div(x, tb_ticks_per_sec); - p->tv_nsec = x; -} - -static inline cputime_t timespec_to_cputime(const struct timespec *p) -{ - u64 ct; - - ct = (u64) p->tv_nsec * tb_ticks_per_sec; - do_div(ct, 1000000000); - return (__force cputime_t)(ct + (u64) p->tv_sec * tb_ticks_per_sec); -} - -/* - * Convert cputime <-> timeval - */ -static inline void cputime_to_timeval(const cputime_t ct, struct timeval *p) -{ - u64 x = (__force u64) ct; - unsigned int frac; - - frac = do_div(x, tb_ticks_per_sec); - p->tv_sec = x; - x = (u64) frac * 1000000; - do_div(x, tb_ticks_per_sec); - p->tv_usec = x; -} - -static inline cputime_t timeval_to_cputime(const struct timeval *p) -{ - u64 ct; - - ct = (u64) p->tv_usec * tb_ticks_per_sec; - do_div(ct, 1000000); - return (__force cputime_t)(ct + (u64) p->tv_sec * tb_ticks_per_sec); -} - -/* - * Convert cputime <-> clock_t (units of 1/USER_HZ seconds) - */ -extern u64 __cputime_clockt_factor; - -static inline unsigned long cputime_to_clock_t(const cputime_t ct) -{ - return mulhdu((__force u64) ct, __cputime_clockt_factor); -} - -static inline cputime_t clock_t_to_cputime(const unsigned long clk) -{ - u64 ct; - unsigned long sec; - - /* have to be a little careful about overflow */ - ct = clk % USER_HZ; - sec = clk / USER_HZ; - if (ct) { - ct *= tb_ticks_per_sec; - do_div(ct, USER_HZ); - } - if (sec) - ct += (u64) sec * tb_ticks_per_sec; - return (__force cputime_t) ct; -} - -#define cputime64_to_clock_t(ct) cputime_to_clock_t((cputime_t)(ct)) - /* * PPC64 uses PACA which is task independent for storing accounting data while * PPC32 uses struct thread_info, therefore at task switch the accounting data diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h index a34c764ca8dd..233a7e8cc8e3 100644 --- a/arch/powerpc/include/asm/mmu.h +++ b/arch/powerpc/include/asm/mmu.h @@ -160,7 +160,9 @@ static __always_inline bool mmu_has_feature(unsigned long feature) { int i; +#ifndef __clang__ /* clang can't cope with this */ BUILD_BUG_ON(!__builtin_constant_p(feature)); +#endif #ifdef CONFIG_JUMP_LABEL_FEATURE_CHECK_DEBUG if (!static_key_initialized) { diff --git a/arch/powerpc/include/asm/module.h b/arch/powerpc/include/asm/module.h index cc12c61ef315..53885512b8d3 100644 --- a/arch/powerpc/include/asm/module.h +++ b/arch/powerpc/include/asm/module.h @@ -90,9 +90,5 @@ static inline int module_finalize_ftrace(struct module *mod, const Elf_Shdr *sec } #endif -#if defined(CONFIG_MODVERSIONS) && defined(CONFIG_PPC64) -#define ARCH_RELOCATES_KCRCTAB -#define reloc_start PHYSICAL_START -#endif #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_MODULE_H */ diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index 6a6792bb39fb..708c3e592eeb 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -187,7 +187,6 @@ struct paca_struct { /* Stuff for accurate time accounting */ struct cpu_accounting_data accounting; - u64 stolen_time; /* TB ticks taken by hypervisor */ u64 dtl_ridx; /* read index in dispatch log */ struct dtl_entry *dtl_curr; /* pointer corresponding to dtl_ridx */ diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 0d4531aa2052..dff79798903d 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -649,9 +649,10 @@ #define SRR1_ISI_N_OR_G 0x10000000 /* ISI: Access is no-exec or G */ #define SRR1_ISI_PROT 0x08000000 /* ISI: Other protection fault */ #define SRR1_WAKEMASK 0x00380000 /* reason for wakeup */ -#define SRR1_WAKEMASK_P8 0x003c0000 /* reason for wakeup on POWER8 */ +#define SRR1_WAKEMASK_P8 0x003c0000 /* reason for wakeup on POWER8 and 9 */ #define SRR1_WAKESYSERR 0x00300000 /* System error */ #define SRR1_WAKEEE 0x00200000 /* External interrupt */ +#define SRR1_WAKEHVI 0x00240000 /* Hypervisor Virtualization Interrupt (P9) */ #define SRR1_WAKEMT 0x00280000 /* mtctrl */ #define SRR1_WAKEHMI 0x00280000 /* Hypervisor maintenance */ #define SRR1_WAKEDEC 0x00180000 /* Decrementer interrupt */ diff --git a/arch/powerpc/include/asm/stackprotector.h b/arch/powerpc/include/asm/stackprotector.h deleted file mode 100644 index 6720190eabec..000000000000 --- a/arch/powerpc/include/asm/stackprotector.h +++ /dev/null @@ -1,40 +0,0 @@ -/* - * GCC stack protector support. - * - * Stack protector works by putting predefined pattern at the start of - * the stack frame and verifying that it hasn't been overwritten when - * returning from the function. The pattern is called stack canary - * and gcc expects it to be defined by a global variable called - * "__stack_chk_guard" on PPC. This unfortunately means that on SMP - * we cannot have a different canary value per task. - */ - -#ifndef _ASM_STACKPROTECTOR_H -#define _ASM_STACKPROTECTOR_H - -#include <linux/random.h> -#include <linux/version.h> -#include <asm/reg.h> - -extern unsigned long __stack_chk_guard; - -/* - * Initialize the stackprotector canary value. - * - * NOTE: this must only be called from functions that never return, - * and it must always be inlined. - */ -static __always_inline void boot_init_stack_canary(void) -{ - unsigned long canary; - - /* Try to get a semi random initial value. */ - get_random_bytes(&canary, sizeof(canary)); - canary ^= mftb(); - canary ^= LINUX_VERSION_CODE; - - current->stack_canary = canary; - __stack_chk_guard = current->stack_canary; -} - -#endif /* _ASM_STACKPROTECTOR_H */ diff --git a/arch/powerpc/include/asm/xics.h b/arch/powerpc/include/asm/xics.h index f0b238516e9b..e0b9e576905a 100644 --- a/arch/powerpc/include/asm/xics.h +++ b/arch/powerpc/include/asm/xics.h @@ -44,6 +44,7 @@ static inline int icp_hv_init(void) { return -ENODEV; } #ifdef CONFIG_PPC_POWERNV extern int icp_opal_init(void); +extern void icp_opal_flush_interrupt(void); #else static inline int icp_opal_init(void) { return -ENODEV; } #endif diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 23f8082d7bfa..f4c2b52e58b3 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -19,10 +19,6 @@ CFLAGS_init.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) CFLAGS_btext.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) CFLAGS_prom.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) -# -fstack-protector triggers protection checks in this code, -# but it is being used too early to link to meaningful stack_chk logic. -CFLAGS_prom_init.o += $(call cc-option, -fno-stack-protector) - ifdef CONFIG_FUNCTION_TRACER # Do not trace early boot code CFLAGS_REMOVE_cputable.o = -mno-sched-epilog $(CC_FLAGS_FTRACE) diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 0601e6a7297c..9e8e771f8acb 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -91,9 +91,6 @@ int main(void) DEFINE(TI_livepatch_sp, offsetof(struct thread_info, livepatch_sp)); #endif -#ifdef CONFIG_CC_STACKPROTECTOR - DEFINE(TSK_STACK_CANARY, offsetof(struct task_struct, stack_canary)); -#endif DEFINE(KSP, offsetof(struct thread_struct, ksp)); DEFINE(PT_REGS, offsetof(struct thread_struct, regs)); #ifdef CONFIG_BOOKE @@ -252,9 +249,9 @@ int main(void) DEFINE(ACCOUNT_STARTTIME_USER, offsetof(struct paca_struct, accounting.starttime_user)); DEFINE(ACCOUNT_USER_TIME, - offsetof(struct paca_struct, accounting.user_time)); + offsetof(struct paca_struct, accounting.utime)); DEFINE(ACCOUNT_SYSTEM_TIME, - offsetof(struct paca_struct, accounting.system_time)); + offsetof(struct paca_struct, accounting.stime)); DEFINE(PACA_TRAP_SAVE, offsetof(struct paca_struct, trap_save)); DEFINE(PACA_NAPSTATELOST, offsetof(struct paca_struct, nap_state_lost)); DEFINE(PACA_SPRG_VDSO, offsetof(struct paca_struct, sprg_vdso)); @@ -265,9 +262,9 @@ int main(void) DEFINE(ACCOUNT_STARTTIME_USER, offsetof(struct thread_info, accounting.starttime_user)); DEFINE(ACCOUNT_USER_TIME, - offsetof(struct thread_info, accounting.user_time)); + offsetof(struct thread_info, accounting.utime)); DEFINE(ACCOUNT_SYSTEM_TIME, - offsetof(struct thread_info, accounting.system_time)); + offsetof(struct thread_info, accounting.stime)); #endif #endif /* CONFIG_PPC64 */ diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index d88573bdd090..b94887165a10 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -545,7 +545,7 @@ static void *eeh_pe_detach_dev(void *data, void *userdata) static void *__eeh_clear_pe_frozen_state(void *data, void *flag) { struct eeh_pe *pe = (struct eeh_pe *)data; - bool *clear_sw_state = flag; + bool clear_sw_state = *(bool *)flag; int i, rc = 1; for (i = 0; rc && i < 3; i++) diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 5742dbdbee46..3841d749a430 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -674,11 +674,7 @@ BEGIN_FTR_SECTION mtspr SPRN_SPEFSCR,r0 /* restore SPEFSCR reg */ END_FTR_SECTION_IFSET(CPU_FTR_SPE) #endif /* CONFIG_SPE */ -#if defined(CONFIG_CC_STACKPROTECTOR) && !defined(CONFIG_SMP) - lwz r0,TSK_STACK_CANARY(r2) - lis r4,__stack_chk_guard@ha - stw r0,__stack_chk_guard@l(r4) -#endif + lwz r0,_CCR(r1) mtcrf 0xFF,r0 /* r3-r12 are destroyed -- Cort */ diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index bb1807184bad..0b0f89685b67 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -286,14 +286,6 @@ static void dedotify_versions(struct modversion_info *vers, for (end = (void *)vers + size; vers < end; vers++) if (vers->name[0] == '.') { memmove(vers->name, vers->name+1, strlen(vers->name)); -#ifdef ARCH_RELOCATES_KCRCTAB - /* The TOC symbol has no CRC computed. To avoid CRC - * check failing, we must force it to the expected - * value (see CRC check in module.c). - */ - if (!strcmp(vers->name, "TOC.")) - vers->crc = -(unsigned long)reloc_start; -#endif } } diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 04885cec24df..5dd056df0baa 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -64,12 +64,6 @@ #include <linux/kprobes.h> #include <linux/kdebug.h> -#ifdef CONFIG_CC_STACKPROTECTOR -#include <linux/stackprotector.h> -unsigned long __stack_chk_guard __read_mostly; -EXPORT_SYMBOL(__stack_chk_guard); -#endif - /* Transactional Memory debug */ #ifdef TM_DEBUG_SW #define TM_DEBUG(x...) printk(KERN_INFO x) diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index ec47a939cbdd..ac83eb04a8b8 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -2834,6 +2834,9 @@ static void __init prom_find_boot_cpu(void) cpu_pkg = call_prom("instance-to-package", 1, 1, prom_cpu); + if (!PHANDLE_VALID(cpu_pkg)) + return; + prom_getprop(cpu_pkg, "reg", &rval, sizeof(rval)); prom.cpu = be32_to_cpu(rval); diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index bc2e08d415fa..14e485525e31 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -57,6 +57,7 @@ #include <linux/clk-provider.h> #include <linux/suspend.h> #include <linux/rtc.h> +#include <linux/cputime.h> #include <asm/trace.h> #include <asm/io.h> @@ -72,7 +73,6 @@ #include <asm/smp.h> #include <asm/vdso_datapage.h> #include <asm/firmware.h> -#include <asm/cputime.h> #include <asm/asm-prototypes.h> /* powerpc clocksource/clockevent code */ @@ -152,20 +152,11 @@ EXPORT_SYMBOL_GPL(ppc_tb_freq); #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE /* - * Factors for converting from cputime_t (timebase ticks) to - * jiffies, microseconds, seconds, and clock_t (1/USER_HZ seconds). - * These are all stored as 0.64 fixed-point binary fractions. + * Factor for converting from cputime_t (timebase ticks) to + * microseconds. This is stored as 0.64 fixed-point binary fraction. */ -u64 __cputime_jiffies_factor; -EXPORT_SYMBOL(__cputime_jiffies_factor); u64 __cputime_usec_factor; EXPORT_SYMBOL(__cputime_usec_factor); -u64 __cputime_sec_factor; -EXPORT_SYMBOL(__cputime_sec_factor); -u64 __cputime_clockt_factor; -EXPORT_SYMBOL(__cputime_clockt_factor); - -cputime_t cputime_one_jiffy; #ifdef CONFIG_PPC_SPLPAR void (*dtl_consumer)(struct dtl_entry *, u64); @@ -181,14 +172,8 @@ static void calc_cputime_factors(void) { struct div_result res; - div128_by_32(HZ, 0, tb_ticks_per_sec, &res); - __cputime_jiffies_factor = res.result_low; div128_by_32(1000000, 0, tb_ticks_per_sec, &res); __cputime_usec_factor = res.result_low; - div128_by_32(1, 0, tb_ticks_per_sec, &res); - __cputime_sec_factor = res.result_low; - div128_by_32(USER_HZ, 0, tb_ticks_per_sec, &res); - __cputime_clockt_factor = res.result_low; } /* @@ -271,25 +256,19 @@ void accumulate_stolen_time(void) sst = scan_dispatch_log(acct->starttime_user); ust = scan_dispatch_log(acct->starttime); - acct->system_time -= sst; - acct->user_time -= ust; - local_paca->stolen_time += ust + sst; + acct->stime -= sst; + acct->utime -= ust; + acct->steal_time += ust + sst; local_paca->soft_enabled = save_soft_enabled; } static inline u64 calculate_stolen_time(u64 stop_tb) { - u64 stolen = 0; + if (get_paca()->dtl_ridx != be64_to_cpu(get_lppaca()->dtl_idx)) + return scan_dispatch_log(stop_tb); - if (get_paca()->dtl_ridx != be64_to_cpu(get_lppaca()->dtl_idx)) { - stolen = scan_dispatch_log(stop_tb); - get_paca()->accounting.system_time -= stolen; - } - - stolen += get_paca()->stolen_time; - get_paca()->stolen_time = 0; - return stolen; + return 0; } #else /* CONFIG_PPC_SPLPAR */ @@ -305,28 +284,27 @@ static inline u64 calculate_stolen_time(u64 stop_tb) * or soft irq state. */ static unsigned long vtime_delta(struct task_struct *tsk, - unsigned long *sys_scaled, - unsigned long *stolen) + unsigned long *stime_scaled, + unsigned long *steal_time) { unsigned long now, nowscaled, deltascaled; - unsigned long udelta, delta, user_scaled; + unsigned long stime; + unsigned long utime, utime_scaled; struct cpu_accounting_data *acct = get_accounting(tsk); WARN_ON_ONCE(!irqs_disabled()); now = mftb(); nowscaled = read_spurr(now); - acct->system_time += now - acct->starttime; + stime = now - acct->starttime; acct->starttime = now; deltascaled = nowscaled - acct->startspurr; acct->startspurr = nowscaled; - *stolen = calculate_stolen_time(now); + *steal_time = calculate_stolen_time(now); - delta = acct->system_time; - acct->system_time = 0; - udelta = acct->user_time - acct->utime_sspurr; - acct->utime_sspurr = acct->user_time; + utime = acct->utime - acct->utime_sspurr; + acct->utime_sspurr = acct->utime; /* * Because we don't read the SPURR on every kernel entry/exit, @@ -338,62 +316,105 @@ static unsigned long vtime_delta(struct task_struct *tsk, * the user ticks get saved up in paca->user_time_scaled to be * used by account_process_tick. */ - *sys_scaled = delta; - user_scaled = udelta; - if (deltascaled != delta + udelta) { - if (udelta) { - *sys_scaled = deltascaled * delta / (delta + udelta); - user_scaled = deltascaled - *sys_scaled; + *stime_scaled = stime; + utime_scaled = utime; + if (deltascaled != stime + utime) { + if (utime) { + *stime_scaled = deltascaled * stime / (stime + utime); + utime_scaled = deltascaled - *stime_scaled; } else { - *sys_scaled = deltascaled; + *stime_scaled = deltascaled; } } - acct->user_time_scaled += user_scaled; + acct->utime_scaled += utime_scaled; - return delta; + return stime; } void vtime_account_system(struct task_struct *tsk) { - unsigned long delta, sys_scaled, stolen; + unsigned long stime, stime_scaled, steal_time; + struct cpu_accounting_data *acct = get_accounting(tsk); + + stime = vtime_delta(tsk, &stime_scaled, &steal_time); - delta = vtime_delta(tsk, &sys_scaled, &stolen); - account_system_time(tsk, 0, delta); - tsk->stimescaled += sys_scaled; - if (stolen) - account_steal_time(stolen); + stime -= min(stime, steal_time); + acct->steal_time += steal_time; + + if ((tsk->flags & PF_VCPU) && !irq_count()) { + acct->gtime += stime; + acct->utime_scaled += stime_scaled; + } else { + if (hardirq_count()) + acct->hardirq_time += stime; + else if (in_serving_softirq()) + acct->softirq_time += stime; + else + acct->stime += stime; + + acct->stime_scaled += stime_scaled; + } } EXPORT_SYMBOL_GPL(vtime_account_system); void vtime_account_idle(struct task_struct *tsk) { - unsigned long delta, sys_scaled, stolen; + unsigned long stime, stime_scaled, steal_time; + struct cpu_accounting_data *acct = get_accounting(tsk); - delta = vtime_delta(tsk, &sys_scaled, &stolen); - account_idle_time(delta + stolen); + stime = vtime_delta(tsk, &stime_scaled, &steal_time); + acct->idle_time += stime + steal_time; } /* - * Transfer the user time accumulated in the paca - * by the exception entry and exit code to the generic - * process user time records. + * Account the whole cputime accumulated in the paca * Must be called with interrupts disabled. * Assumes that vtime_account_system/idle() has been called * recently (i.e. since the last entry from usermode) so that * get_paca()->user_time_scaled is up to date. */ -void vtime_account_user(struct task_struct *tsk) +void vtime_flush(struct task_struct *tsk) { - cputime_t utime, utimescaled; struct cpu_accounting_data *acct = get_accounting(tsk); - utime = acct->user_time; - utimescaled = acct->user_time_scaled; - acct->user_time = 0; - acct->user_time_scaled = 0; + if (acct->utime) + account_user_time(tsk, cputime_to_nsecs(acct->utime)); + + if (acct->utime_scaled) + tsk->utimescaled += cputime_to_nsecs(acct->utime_scaled); + + if (acct->gtime) + account_guest_time(tsk, cputime_to_nsecs(acct->gtime)); + + if (acct->steal_time) + account_steal_time(cputime_to_nsecs(acct->steal_time)); + + if (acct->idle_time) + account_idle_time(cputime_to_nsecs(acct->idle_time)); + + if (acct->stime) + account_system_index_time(tsk, cputime_to_nsecs(acct->stime), + CPUTIME_SYSTEM); + if (acct->stime_scaled) + tsk->stimescaled += cputime_to_nsecs(acct->stime_scaled); + + if (acct->hardirq_time) + account_system_index_time(tsk, cputime_to_nsecs(acct->hardirq_time), + CPUTIME_IRQ); + if (acct->softirq_time) + account_system_index_time(tsk, cputime_to_nsecs(acct->softirq_time), + CPUTIME_SOFTIRQ); + + acct->utime = 0; + acct->utime_scaled = 0; acct->utime_sspurr = 0; - account_user_time(tsk, utime); - tsk->utimescaled += utimescaled; + acct->gtime = 0; + acct->steal_time = 0; + acct->idle_time = 0; + acct->stime = 0; + acct->stime_scaled = 0; + acct->hardirq_time = 0; + acct->softirq_time = 0; } #ifdef CONFIG_PPC32 @@ -407,8 +428,7 @@ void arch_vtime_task_switch(struct task_struct *prev) struct cpu_accounting_data *acct = get_accounting(current); acct->starttime = get_accounting(prev)->starttime; - acct->system_time = 0; - acct->user_time = 0; + acct->startspurr = get_accounting(prev)->startspurr; } #endif /* CONFIG_PPC32 */ @@ -1018,7 +1038,6 @@ void __init time_init(void) tb_ticks_per_sec = ppc_tb_freq; tb_ticks_per_usec = ppc_tb_freq / 1000000; calc_cputime_factors(); - setup_cputime_one_jiffy(); /* * Compute scale factor for sched_clock. diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index 6fd30ac7d14a..62a50d6d1053 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -253,8 +253,11 @@ int do_page_fault(struct pt_regs *regs, unsigned long address, if (unlikely(debugger_fault_handler(regs))) goto bail; - /* On a kernel SLB miss we can only check for a valid exception entry */ - if (!user_mode(regs) && (address >= TASK_SIZE)) { + /* + * The kernel should never take an execute fault nor should it + * take a page fault to a kernel address. + */ + if (!user_mode(regs) && (is_exec || (address >= TASK_SIZE))) { rc = SIGSEGV; goto bail; } @@ -391,20 +394,6 @@ good_area: if (is_exec) { /* - * An execution fault + no execute ? - * - * On CPUs that don't have CPU_FTR_COHERENT_ICACHE we - * deliberately create NX mappings, and use the fault to do the - * cache flush. This is usually handled in hash_page_do_lazy_icache() - * but we could end up here if that races with a concurrent PTE - * update. In that case we need to fall through here to the VMA - * check below. - */ - if (cpu_has_feature(CPU_FTR_COHERENT_ICACHE) && - (regs->msr & SRR1_ISI_N_OR_G)) - goto bad_area; - - /* * Allow execution from readable areas if the MMU does not * provide separate controls over reading and executing. * diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index 93abf8a9813d..8e1588021d1c 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -347,7 +347,8 @@ early_param("disable_radix", parse_disable_radix); void __init mmu_early_init_devtree(void) { /* Disable radix mode based on kernel command line. */ - if (disable_radix) + /* We don't yet have the machinery to do radix as a guest. */ + if (disable_radix || !(mfmsr() & MSR_HV)) cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX; if (early_radix_enabled()) diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c index cfa53ccc8baf..34f1a0dbc898 100644 --- a/arch/powerpc/mm/pgtable-radix.c +++ b/arch/powerpc/mm/pgtable-radix.c @@ -65,7 +65,7 @@ int radix__map_kernel_page(unsigned long ea, unsigned long pa, if (!pmdp) return -ENOMEM; if (map_page_size == PMD_SIZE) { - ptep = (pte_t *)pudp; + ptep = pmdp_ptep(pmdp); goto set_the_pte; } ptep = pte_alloc_kernel(pmdp, ea); @@ -90,7 +90,7 @@ int radix__map_kernel_page(unsigned long ea, unsigned long pa, } pmdp = pmd_offset(pudp, ea); if (map_page_size == PMD_SIZE) { - ptep = (pte_t *)pudp; + ptep = pmdp_ptep(pmdp); goto set_the_pte; } if (!pmd_present(*pmdp)) { diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c index 61b79119065f..952713d6cf04 100644 --- a/arch/powerpc/mm/tlb-radix.c +++ b/arch/powerpc/mm/tlb-radix.c @@ -50,9 +50,7 @@ static inline void _tlbiel_pid(unsigned long pid, unsigned long ric) for (set = 0; set < POWER9_TLB_SETS_RADIX ; set++) { __tlbiel_pid(pid, set, ric); } - if (cpu_has_feature(CPU_FTR_POWER9_DD1)) - asm volatile(PPC_INVALIDATE_ERAT : : :"memory"); - return; + asm volatile(PPC_INVALIDATE_ERAT "; isync" : : :"memory"); } static inline void _tlbie_pid(unsigned long pid, unsigned long ric) @@ -85,8 +83,6 @@ static inline void _tlbiel_va(unsigned long va, unsigned long pid, asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1) : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory"); asm volatile("ptesync": : :"memory"); - if (cpu_has_feature(CPU_FTR_POWER9_DD1)) - asm volatile(PPC_INVALIDATE_ERAT : : :"memory"); } static inline void _tlbie_va(unsigned long va, unsigned long pid, diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c index c789258ae1e1..eec0e8d0454d 100644 --- a/arch/powerpc/platforms/powernv/smp.c +++ b/arch/powerpc/platforms/powernv/smp.c @@ -155,8 +155,10 @@ static void pnv_smp_cpu_kill_self(void) wmask = SRR1_WAKEMASK_P8; idle_states = pnv_get_supported_cpuidle_states(); + /* We don't want to take decrementer interrupts while we are offline, - * so clear LPCR:PECE1. We keep PECE2 enabled. + * so clear LPCR:PECE1. We keep PECE2 (and LPCR_PECE_HVEE on P9) + * enabled as to let IPIs in. */ mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1); @@ -206,8 +208,12 @@ static void pnv_smp_cpu_kill_self(void) * contains 0. */ if (((srr1 & wmask) == SRR1_WAKEEE) || + ((srr1 & wmask) == SRR1_WAKEHVI) || (local_paca->irq_happened & PACA_IRQ_EE)) { - icp_native_flush_interrupt(); + if (cpu_has_feature(CPU_FTR_ARCH_300)) + icp_opal_flush_interrupt(); + else + icp_native_flush_interrupt(); } else if ((srr1 & wmask) == SRR1_WAKEHDBELL) { unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER); asm volatile(PPC_MSGCLR(%0) : : "r" (msg)); @@ -221,6 +227,8 @@ static void pnv_smp_cpu_kill_self(void) if (srr1 && !generic_check_cpu_restart(cpu)) DBG("CPU%d Unexpected exit while offline !\n", cpu); } + + /* Re-enable decrementer interrupts */ mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) | LPCR_PECE1); DBG("CPU%d coming online...\n", cpu); } diff --git a/arch/powerpc/sysdev/xics/icp-opal.c b/arch/powerpc/sysdev/xics/icp-opal.c index 60c57657c772..f9670eabfcfa 100644 --- a/arch/powerpc/sysdev/xics/icp-opal.c +++ b/arch/powerpc/sysdev/xics/icp-opal.c @@ -120,18 +120,49 @@ static void icp_opal_cause_ipi(int cpu, unsigned long data) { int hw_cpu = get_hard_smp_processor_id(cpu); + kvmppc_set_host_ipi(cpu, 1); opal_int_set_mfrr(hw_cpu, IPI_PRIORITY); } static irqreturn_t icp_opal_ipi_action(int irq, void *dev_id) { - int hw_cpu = hard_smp_processor_id(); + int cpu = smp_processor_id(); - opal_int_set_mfrr(hw_cpu, 0xff); + kvmppc_set_host_ipi(cpu, 0); + opal_int_set_mfrr(get_hard_smp_processor_id(cpu), 0xff); return smp_ipi_demux(); } +/* + * Called when an interrupt is received on an off-line CPU to + * clear the interrupt, so that the CPU can go back to nap mode. + */ +void icp_opal_flush_interrupt(void) +{ + unsigned int xirr; + unsigned int vec; + + do { + xirr = icp_opal_get_xirr(); + vec = xirr & 0x00ffffff; + if (vec == XICS_IRQ_SPURIOUS) + break; + if (vec == XICS_IPI) { + /* Clear pending IPI */ + int cpu = smp_processor_id(); + kvmppc_set_host_ipi(cpu, 0); + opal_int_set_mfrr(get_hard_smp_processor_id(cpu), 0xff); + } else { + pr_err("XICS: hw interrupt 0x%x to offline cpu, " + "disabling\n", vec); + xics_mask_unknown_vec(vec); + } + + /* EOI the interrupt */ + } while (opal_int_eoi(xirr) > 0); +} + #endif /* CONFIG_SMP */ static const struct icp_ops icp_opal_ops = { diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 9c0e17cf6886..3f864c36d847 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -2287,14 +2287,14 @@ static void dump_one_paca(int cpu) DUMP(p, subcore_sibling_mask, "x"); #endif - DUMP(p, accounting.user_time, "llx"); - DUMP(p, accounting.system_time, "llx"); - DUMP(p, accounting.user_time_scaled, "llx"); + DUMP(p, accounting.utime, "llx"); + DUMP(p, accounting.stime, "llx"); + DUMP(p, accounting.utime_scaled, "llx"); DUMP(p, accounting.starttime, "llx"); DUMP(p, accounting.starttime_user, "llx"); DUMP(p, accounting.startspurr, "llx"); DUMP(p, accounting.utime_sspurr, "llx"); - DUMP(p, stolen_time, "llx"); + DUMP(p, accounting.steal_time, "llx"); #undef DUMP catch_memory_errors = 0; diff --git a/arch/s390/appldata/appldata_os.c b/arch/s390/appldata/appldata_os.c index 69b23b25ac34..08b9e942a262 100644 --- a/arch/s390/appldata/appldata_os.c +++ b/arch/s390/appldata/appldata_os.c @@ -113,21 +113,21 @@ static void appldata_get_os_data(void *data) j = 0; for_each_online_cpu(i) { os_data->os_cpu[j].per_cpu_user = - cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_USER]); + nsecs_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_USER]); os_data->os_cpu[j].per_cpu_nice = - cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_NICE]); + nsecs_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_NICE]); os_data->os_cpu[j].per_cpu_system = - cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_SYSTEM]); + nsecs_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_SYSTEM]); os_data->os_cpu[j].per_cpu_idle = - cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IDLE]); + nsecs_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IDLE]); os_data->os_cpu[j].per_cpu_irq = - cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IRQ]); + nsecs_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IRQ]); os_data->os_cpu[j].per_cpu_softirq = - cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_SOFTIRQ]); + nsecs_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_SOFTIRQ]); os_data->os_cpu[j].per_cpu_iowait = - cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IOWAIT]); + nsecs_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IOWAIT]); os_data->os_cpu[j].per_cpu_steal = - cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_STEAL]); + nsecs_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_STEAL]); os_data->os_cpu[j].cpu_id = i; j++; } diff --git a/arch/s390/include/asm/cputime.h b/arch/s390/include/asm/cputime.h index 221b454c734a..d1c407ddf703 100644 --- a/arch/s390/include/asm/cputime.h +++ b/arch/s390/include/asm/cputime.h @@ -25,33 +25,6 @@ static inline unsigned long __div(unsigned long long n, unsigned long base) return n / base; } -#define cputime_one_jiffy jiffies_to_cputime(1) - -/* - * Convert cputime to jiffies and back. - */ -static inline unsigned long cputime_to_jiffies(const cputime_t cputime) -{ - return __div((__force unsigned long long) cputime, CPUTIME_PER_SEC / HZ); -} - -static inline cputime_t jiffies_to_cputime(const unsigned int jif) -{ - return (__force cputime_t)(jif * (CPUTIME_PER_SEC / HZ)); -} - -static inline u64 cputime64_to_jiffies64(cputime64_t cputime) -{ - unsigned long long jif = (__force unsigned long long) cputime; - do_div(jif, CPUTIME_PER_SEC / HZ); - return jif; -} - -static inline cputime64_t jiffies64_to_cputime64(const u64 jif) -{ - return (__force cputime64_t)(jif * (CPUTIME_PER_SEC / HZ)); -} - /* * Convert cputime to microseconds and back. */ @@ -60,88 +33,8 @@ static inline unsigned int cputime_to_usecs(const cputime_t cputime) return (__force unsigned long long) cputime >> 12; } -static inline cputime_t usecs_to_cputime(const unsigned int m) -{ - return (__force cputime_t)(m * CPUTIME_PER_USEC); -} - -#define usecs_to_cputime64(m) usecs_to_cputime(m) - -/* - * Convert cputime to milliseconds and back. - */ -static inline unsigned int cputime_to_secs(const cputime_t cputime) -{ - return __div((__force unsigned long long) cputime, CPUTIME_PER_SEC / 2) >> 1; -} - -static inline cputime_t secs_to_cputime(const unsigned int s) -{ - return (__force cputime_t)(s * CPUTIME_PER_SEC); -} - -/* - * Convert cputime to timespec and back. - */ -static inline cputime_t timespec_to_cputime(const struct timespec *value) -{ - unsigned long long ret = value->tv_sec * CPUTIME_PER_SEC; - return (__force cputime_t)(ret + __div(value->tv_nsec * CPUTIME_PER_USEC, NSEC_PER_USEC)); -} - -static inline void cputime_to_timespec(const cputime_t cputime, - struct timespec *value) -{ - unsigned long long __cputime = (__force unsigned long long) cputime; - value->tv_nsec = (__cputime % CPUTIME_PER_SEC) * NSEC_PER_USEC / CPUTIME_PER_USEC; - value->tv_sec = __cputime / CPUTIME_PER_SEC; -} - -/* - * Convert cputime to timeval and back. - * Since cputime and timeval have the same resolution (microseconds) - * this is easy. - */ -static inline cputime_t timeval_to_cputime(const struct timeval *value) -{ - unsigned long long ret = value->tv_sec * CPUTIME_PER_SEC; - return (__force cputime_t)(ret + value->tv_usec * CPUTIME_PER_USEC); -} - -static inline void cputime_to_timeval(const cputime_t cputime, - struct timeval *value) -{ - unsigned long long __cputime = (__force unsigned long long) cputime; - value->tv_usec = (__cputime % CPUTIME_PER_SEC) / CPUTIME_PER_USEC; - value->tv_sec = __cputime / CPUTIME_PER_SEC; -} - -/* - * Convert cputime to clock and back. - */ -static inline clock_t cputime_to_clock_t(cputime_t cputime) -{ - unsigned long long clock = (__force unsigned long long) cputime; - do_div(clock, CPUTIME_PER_SEC / USER_HZ); - return clock; -} - -static inline cputime_t clock_t_to_cputime(unsigned long x) -{ - return (__force cputime_t)(x * (CPUTIME_PER_SEC / USER_HZ)); -} - -/* - * Convert cputime64 to clock. - */ -static inline clock_t cputime64_to_clock_t(cputime64_t cputime) -{ - unsigned long long clock = (__force unsigned long long) cputime; - do_div(clock, CPUTIME_PER_SEC / USER_HZ); - return clock; -} -cputime64_t arch_cpu_idle_time(int cpu); +u64 arch_cpu_idle_time(int cpu); #define arch_idle_time(cpu) arch_cpu_idle_time(cpu) diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h index 9bfad2ad6312..61261e0e95c0 100644 --- a/arch/s390/include/asm/lowcore.h +++ b/arch/s390/include/asm/lowcore.h @@ -85,53 +85,56 @@ struct lowcore { __u64 mcck_enter_timer; /* 0x02c0 */ __u64 exit_timer; /* 0x02c8 */ __u64 user_timer; /* 0x02d0 */ - __u64 system_timer; /* 0x02d8 */ - __u64 steal_timer; /* 0x02e0 */ - __u64 last_update_timer; /* 0x02e8 */ - __u64 last_update_clock; /* 0x02f0 */ - __u64 int_clock; /* 0x02f8 */ - __u64 mcck_clock; /* 0x0300 */ - __u64 clock_comparator; /* 0x0308 */ + __u64 guest_timer; /* 0x02d8 */ + __u64 system_timer; /* 0x02e0 */ + __u64 hardirq_timer; /* 0x02e8 */ + __u64 softirq_timer; /* 0x02f0 */ + __u64 steal_timer; /* 0x02f8 */ + __u64 last_update_timer; /* 0x0300 */ + __u64 last_update_clock; /* 0x0308 */ + __u64 int_clock; /* 0x0310 */ + __u64 mcck_clock; /* 0x0318 */ + __u64 clock_comparator; /* 0x0320 */ /* Current process. */ - __u64 current_task; /* 0x0310 */ - __u8 pad_0x318[0x320-0x318]; /* 0x0318 */ - __u64 kernel_stack; /* 0x0320 */ + __u64 current_task; /* 0x0328 */ + __u8 pad_0x318[0x320-0x318]; /* 0x0330 */ + __u64 kernel_stack; /* 0x0338 */ /* Interrupt, panic and restart stack. */ - __u64 async_stack; /* 0x0328 */ - __u64 panic_stack; /* 0x0330 */ - __u64 restart_stack; /* 0x0338 */ + __u64 async_stack; /* 0x0340 */ + __u64 panic_stack; /* 0x0348 */ + __u64 restart_stack; /* 0x0350 */ /* Restart function and parameter. */ - __u64 restart_fn; /* 0x0340 */ - __u64 restart_data; /* 0x0348 */ - __u64 restart_source; /* 0x0350 */ + __u64 restart_fn; /* 0x0358 */ + __u64 restart_data; /* 0x0360 */ + __u64 restart_source; /* 0x0368 */ /* Address space pointer. */ - __u64 kernel_asce; /* 0x0358 */ - __u64 user_asce; /* 0x0360 */ + __u64 kernel_asce; /* 0x0370 */ + __u64 user_asce; /* 0x0378 */ /* * The lpp and current_pid fields form a * 64-bit value that is set as program * parameter with the LPP instruction. */ - __u32 lpp; /* 0x0368 */ - __u32 current_pid; /* 0x036c */ + __u32 lpp; /* 0x0380 */ + __u32 current_pid; /* 0x0384 */ /* SMP info area */ - __u32 cpu_nr; /* 0x0370 */ - __u32 softirq_pending; /* 0x0374 */ - __u64 percpu_offset; /* 0x0378 */ - __u64 vdso_per_cpu_data; /* 0x0380 */ - __u64 machine_flags; /* 0x0388 */ - __u32 preempt_count; /* 0x0390 */ - __u8 pad_0x0394[0x0398-0x0394]; /* 0x0394 */ - __u64 gmap; /* 0x0398 */ - __u32 spinlock_lockval; /* 0x03a0 */ - __u32 fpu_flags; /* 0x03a4 */ - __u8 pad_0x03a8[0x0400-0x03a8]; /* 0x03a8 */ + __u32 cpu_nr; /* 0x0388 */ + __u32 softirq_pending; /* 0x038c */ + __u64 percpu_offset; /* 0x0390 */ + __u64 vdso_per_cpu_data; /* 0x0398 */ + __u64 machine_flags; /* 0x03a0 */ + __u32 preempt_count; /* 0x03a8 */ + __u8 pad_0x03ac[0x03b0-0x03ac]; /* 0x03ac */ + __u64 gmap; /* 0x03b0 */ + __u32 spinlock_lockval; /* 0x03b8 */ + __u32 fpu_flags; /* 0x03bc */ + __u8 pad_0x03c0[0x0400-0x03c0]; /* 0x03c0 */ /* Per cpu primary space access list */ __u32 paste[16]; /* 0x0400 */ diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index 6bca916a5ba0..977a5b6501b8 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -111,7 +111,10 @@ struct thread_struct { unsigned int acrs[NUM_ACRS]; unsigned long ksp; /* kernel stack pointer */ unsigned long user_timer; /* task cputime in user space */ + unsigned long guest_timer; /* task cputime in kvm guest */ unsigned long system_timer; /* task cputime in kernel space */ + unsigned long hardirq_timer; /* task cputime in hardirq context */ + unsigned long softirq_timer; /* task cputime in softirq context */ unsigned long sys_call_table; /* system call table address */ mm_segment_t mm_segment; unsigned long gmap_addr; /* address of last gmap fault. */ diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c index 7a55c29b0b33..d3bf69ef42cf 100644 --- a/arch/s390/kernel/idle.c +++ b/arch/s390/kernel/idle.c @@ -12,7 +12,7 @@ #include <linux/notifier.h> #include <linux/init.h> #include <linux/cpu.h> -#include <asm/cputime.h> +#include <linux/cputime.h> #include <asm/nmi.h> #include <asm/smp.h> #include "entry.h" @@ -43,7 +43,7 @@ void enabled_wait(void) idle->clock_idle_enter = idle->clock_idle_exit = 0ULL; idle->idle_time += idle_time; idle->idle_count++; - account_idle_time(idle_time); + account_idle_time(cputime_to_nsecs(idle_time)); write_seqcount_end(&idle->seqcount); } NOKPROBE_SYMBOL(enabled_wait); @@ -84,7 +84,7 @@ static ssize_t show_idle_time(struct device *dev, } DEVICE_ATTR(idle_time_us, 0444, show_idle_time, NULL); -cputime64_t arch_cpu_idle_time(int cpu) +u64 arch_cpu_idle_time(int cpu) { struct s390_idle_data *idle = &per_cpu(s390_idle, cpu); unsigned long long now, idle_enter, idle_exit; @@ -96,7 +96,8 @@ cputime64_t arch_cpu_idle_time(int cpu) idle_enter = ACCESS_ONCE(idle->clock_idle_enter); idle_exit = ACCESS_ONCE(idle->clock_idle_exit); } while (read_seqcount_retry(&idle->seqcount, seq)); - return idle_enter ? ((idle_exit ?: now) - idle_enter) : 0; + + return cputime_to_nsecs(idle_enter ? ((idle_exit ?: now) - idle_enter) : 0); } void arch_cpu_idle_enter(void) diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c index 1b5c5ee9fc1b..b4a3e9e06ef2 100644 --- a/arch/s390/kernel/vtime.c +++ b/arch/s390/kernel/vtime.c @@ -6,13 +6,13 @@ */ #include <linux/kernel_stat.h> +#include <linux/cputime.h> #include <linux/export.h> #include <linux/kernel.h> #include <linux/timex.h> #include <linux/types.h> #include <linux/time.h> -#include <asm/cputime.h> #include <asm/vtimer.h> #include <asm/vtime.h> #include <asm/cpu_mf.h> @@ -90,14 +90,41 @@ static void update_mt_scaling(void) __this_cpu_write(mt_scaling_jiffies, jiffies_64); } +static inline u64 update_tsk_timer(unsigned long *tsk_vtime, u64 new) +{ + u64 delta; + + delta = new - *tsk_vtime; + *tsk_vtime = new; + return delta; +} + + +static inline u64 scale_vtime(u64 vtime) +{ + u64 mult = __this_cpu_read(mt_scaling_mult); + u64 div = __this_cpu_read(mt_scaling_div); + + if (smp_cpu_mtid) + return vtime * mult / div; + return vtime; +} + +static void account_system_index_scaled(struct task_struct *p, + cputime_t cputime, cputime_t scaled, + enum cpu_usage_stat index) +{ + p->stimescaled += cputime_to_nsecs(scaled); + account_system_index_time(p, cputime_to_nsecs(cputime), index); +} + /* * Update process times based on virtual cpu times stored by entry.S * to the lowcore fields user_timer, system_timer & steal_clock. */ static int do_account_vtime(struct task_struct *tsk) { - u64 timer, clock, user, system, steal; - u64 user_scaled, system_scaled; + u64 timer, clock, user, guest, system, hardirq, softirq, steal; timer = S390_lowcore.last_update_timer; clock = S390_lowcore.last_update_clock; @@ -110,53 +137,76 @@ static int do_account_vtime(struct task_struct *tsk) #endif : "=m" (S390_lowcore.last_update_timer), "=m" (S390_lowcore.last_update_clock)); - S390_lowcore.system_timer += timer - S390_lowcore.last_update_timer; - S390_lowcore.steal_timer += S390_lowcore.last_update_clock - clock; + clock = S390_lowcore.last_update_clock - clock; + timer -= S390_lowcore.last_update_timer; + + if (hardirq_count()) + S390_lowcore.hardirq_timer += timer; + else + S390_lowcore.system_timer += timer; /* Update MT utilization calculation */ if (smp_cpu_mtid && time_after64(jiffies_64, this_cpu_read(mt_scaling_jiffies))) update_mt_scaling(); - user = S390_lowcore.user_timer - tsk->thread.user_timer; - S390_lowcore.steal_timer -= user; - tsk->thread.user_timer = S390_lowcore.user_timer; - - system = S390_lowcore.system_timer - tsk->thread.system_timer; - S390_lowcore.steal_timer -= system; - tsk->thread.system_timer = S390_lowcore.system_timer; - - user_scaled = user; - system_scaled = system; - /* Do MT utilization scaling */ - if (smp_cpu_mtid) { - u64 mult = __this_cpu_read(mt_scaling_mult); - u64 div = __this_cpu_read(mt_scaling_div); + /* Calculate cputime delta */ + user = update_tsk_timer(&tsk->thread.user_timer, + READ_ONCE(S390_lowcore.user_timer)); + guest = update_tsk_timer(&tsk->thread.guest_timer, + READ_ONCE(S390_lowcore.guest_timer)); + system = update_tsk_timer(&tsk->thread.system_timer, + READ_ONCE(S390_lowcore.system_timer)); + hardirq = update_tsk_timer(&tsk->thread.hardirq_timer, + READ_ONCE(S390_lowcore.hardirq_timer)); + softirq = update_tsk_timer(&tsk->thread.softirq_timer, + READ_ONCE(S390_lowcore.softirq_timer)); + S390_lowcore.steal_timer += + clock - user - guest - system - hardirq - softirq; + + /* Push account value */ + if (user) { + account_user_time(tsk, cputime_to_nsecs(user)); + tsk->utimescaled += cputime_to_nsecs(scale_vtime(user)); + } - user_scaled = (user_scaled * mult) / div; - system_scaled = (system_scaled * mult) / div; + if (guest) { + account_guest_time(tsk, cputime_to_nsecs(guest)); + tsk->utimescaled += cputime_to_nsecs(scale_vtime(guest)); } - account_user_time(tsk, user); - tsk->utimescaled += user_scaled; - account_system_time(tsk, 0, system); - tsk->stimescaled += system_scaled; + + if (system) + account_system_index_scaled(tsk, system, scale_vtime(system), + CPUTIME_SYSTEM); + if (hardirq) + account_system_index_scaled(tsk, hardirq, scale_vtime(hardirq), + CPUTIME_IRQ); + if (softirq) + account_system_index_scaled(tsk, softirq, scale_vtime(softirq), + CPUTIME_SOFTIRQ); steal = S390_lowcore.steal_timer; if ((s64) steal > 0) { S390_lowcore.steal_timer = 0; - account_steal_time(steal); + account_steal_time(cputime_to_nsecs(steal)); } - return virt_timer_forward(user + system); + return virt_timer_forward(user + guest + system + hardirq + softirq); } void vtime_task_switch(struct task_struct *prev) { do_account_vtime(prev); prev->thread.user_timer = S390_lowcore.user_timer; + prev->thread.guest_timer = S390_lowcore.guest_timer; prev->thread.system_timer = S390_lowcore.system_timer; + prev->thread.hardirq_timer = S390_lowcore.hardirq_timer; + prev->thread.softirq_timer = S390_lowcore.softirq_timer; S390_lowcore.user_timer = current->thread.user_timer; + S390_lowcore.guest_timer = current->thread.guest_timer; S390_lowcore.system_timer = current->thread.system_timer; + S390_lowcore.hardirq_timer = current->thread.hardirq_timer; + S390_lowcore.softirq_timer = current->thread.softirq_timer; } /* @@ -164,7 +214,7 @@ void vtime_task_switch(struct task_struct *prev) * accounting system time in order to correctly compute * the stolen time accounting. */ -void vtime_account_user(struct task_struct *tsk) +void vtime_flush(struct task_struct *tsk) { if (do_account_vtime(tsk)) virt_timer_expire(); @@ -176,32 +226,22 @@ void vtime_account_user(struct task_struct *tsk) */ void vtime_account_irq_enter(struct task_struct *tsk) { - u64 timer, system, system_scaled; + u64 timer; timer = S390_lowcore.last_update_timer; S390_lowcore.last_update_timer = get_vtimer(); - S390_lowcore.system_timer += timer - S390_lowcore.last_update_timer; - - /* Update MT utilization calculation */ - if (smp_cpu_mtid && - time_after64(jiffies_64, this_cpu_read(mt_scaling_jiffies))) - update_mt_scaling(); - - system = S390_lowcore.system_timer - tsk->thread.system_timer; - S390_lowcore.steal_timer -= system; - tsk->thread.system_timer = S390_lowcore.system_timer; - system_scaled = system; - /* Do MT utilization scaling */ - if (smp_cpu_mtid) { - u64 mult = __this_cpu_read(mt_scaling_mult); - u64 div = __this_cpu_read(mt_scaling_div); - - system_scaled = (system_scaled * mult) / div; - } - account_system_time(tsk, 0, system); - tsk->stimescaled += system_scaled; - - virt_timer_forward(system); + timer -= S390_lowcore.last_update_timer; + + if ((tsk->flags & PF_VCPU) && (irq_count() == 0)) + S390_lowcore.guest_timer += timer; + else if (hardirq_count()) + S390_lowcore.hardirq_timer += timer; + else if (in_serving_softirq()) + S390_lowcore.softirq_timer += timer; + else + S390_lowcore.system_timer += timer; + + virt_timer_forward(timer); } EXPORT_SYMBOL_GPL(vtime_account_irq_enter); diff --git a/arch/score/include/asm/Kbuild b/arch/score/include/asm/Kbuild index a05218ff3fe4..51970bb6c4fe 100644 --- a/arch/score/include/asm/Kbuild +++ b/arch/score/include/asm/Kbuild @@ -4,7 +4,6 @@ header-y += generic-y += barrier.h generic-y += clkdev.h -generic-y += cputime.h generic-y += irq_work.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h diff --git a/arch/sh/include/asm/Kbuild b/arch/sh/include/asm/Kbuild index 751c3373a92c..cf2a75063b53 100644 --- a/arch/sh/include/asm/Kbuild +++ b/arch/sh/include/asm/Kbuild @@ -1,7 +1,6 @@ generic-y += bitsperlong.h generic-y += clkdev.h -generic-y += cputime.h generic-y += current.h generic-y += delay.h generic-y += div64.h diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild index 0569bfac4afb..e9e837bc3158 100644 --- a/arch/sparc/include/asm/Kbuild +++ b/arch/sparc/include/asm/Kbuild @@ -2,7 +2,6 @@ generic-y += clkdev.h -generic-y += cputime.h generic-y += div64.h generic-y += emergency-restart.h generic-y += exec.h diff --git a/arch/sparc/include/asm/mmu_context_64.h b/arch/sparc/include/asm/mmu_context_64.h index b84be675e507..d0317993e947 100644 --- a/arch/sparc/include/asm/mmu_context_64.h +++ b/arch/sparc/include/asm/mmu_context_64.h @@ -35,15 +35,15 @@ void __tsb_context_switch(unsigned long pgd_pa, static inline void tsb_context_switch(struct mm_struct *mm) { __tsb_context_switch(__pa(mm->pgd), - &mm->context.tsb_block[0], + &mm->context.tsb_block[MM_TSB_BASE], #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE) - (mm->context.tsb_block[1].tsb ? - &mm->context.tsb_block[1] : + (mm->context.tsb_block[MM_TSB_HUGE].tsb ? + &mm->context.tsb_block[MM_TSB_HUGE] : NULL) #else NULL #endif - , __pa(&mm->context.tsb_descr[0])); + , __pa(&mm->context.tsb_descr[MM_TSB_BASE])); } void tsb_grow(struct mm_struct *mm, diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c index 3bebf395252c..4d0248aa0928 100644 --- a/arch/sparc/kernel/irq_64.c +++ b/arch/sparc/kernel/irq_64.c @@ -1021,7 +1021,7 @@ static void __init alloc_one_queue(unsigned long *pa_ptr, unsigned long qmask) unsigned long order = get_order(size); unsigned long p; - p = __get_free_pages(GFP_KERNEL, order); + p = __get_free_pages(GFP_KERNEL | __GFP_ZERO, order); if (!p) { prom_printf("SUN4V: Error, cannot allocate queue.\n"); prom_halt(); diff --git a/arch/sparc/kernel/sstate.c b/arch/sparc/kernel/sstate.c index c59af546f522..3caed4023589 100644 --- a/arch/sparc/kernel/sstate.c +++ b/arch/sparc/kernel/sstate.c @@ -43,8 +43,8 @@ static const char poweroff_msg[32] __attribute__((aligned(32))) = "Linux powering off"; static const char rebooting_msg[32] __attribute__((aligned(32))) = "Linux rebooting"; -static const char panicing_msg[32] __attribute__((aligned(32))) = - "Linux panicing"; +static const char panicking_msg[32] __attribute__((aligned(32))) = + "Linux panicking"; static int sstate_reboot_call(struct notifier_block *np, unsigned long type, void *_unused) { @@ -76,7 +76,7 @@ static struct notifier_block sstate_reboot_notifier = { static int sstate_panic_event(struct notifier_block *n, unsigned long event, void *ptr) { - do_set_sstate(HV_SOFT_STATE_TRANSITION, panicing_msg); + do_set_sstate(HV_SOFT_STATE_TRANSITION, panicking_msg); return NOTIFY_DONE; } diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c index 4bc10e44d1ca..dfc97a47c9a0 100644 --- a/arch/sparc/kernel/traps_64.c +++ b/arch/sparc/kernel/traps_64.c @@ -2051,6 +2051,73 @@ void sun4v_resum_overflow(struct pt_regs *regs) atomic_inc(&sun4v_resum_oflow_cnt); } +/* Given a set of registers, get the virtual addressi that was being accessed + * by the faulting instructions at tpc. + */ +static unsigned long sun4v_get_vaddr(struct pt_regs *regs) +{ + unsigned int insn; + + if (!copy_from_user(&insn, (void __user *)regs->tpc, 4)) { + return compute_effective_address(regs, insn, + (insn >> 25) & 0x1f); + } + return 0; +} + +/* Attempt to handle non-resumable errors generated from userspace. + * Returns true if the signal was handled, false otherwise. + */ +bool sun4v_nonresum_error_user_handled(struct pt_regs *regs, + struct sun4v_error_entry *ent) { + + unsigned int attrs = ent->err_attrs; + + if (attrs & SUN4V_ERR_ATTRS_MEMORY) { + unsigned long addr = ent->err_raddr; + siginfo_t info; + + if (addr == ~(u64)0) { + /* This seems highly unlikely to ever occur */ + pr_emerg("SUN4V NON-RECOVERABLE ERROR: Memory error detected in unknown location!\n"); + } else { + unsigned long page_cnt = DIV_ROUND_UP(ent->err_size, + PAGE_SIZE); + + /* Break the unfortunate news. */ + pr_emerg("SUN4V NON-RECOVERABLE ERROR: Memory failed at %016lX\n", + addr); + pr_emerg("SUN4V NON-RECOVERABLE ERROR: Claiming %lu ages.\n", + page_cnt); + + while (page_cnt-- > 0) { + if (pfn_valid(addr >> PAGE_SHIFT)) + get_page(pfn_to_page(addr >> PAGE_SHIFT)); + addr += PAGE_SIZE; + } + } + info.si_signo = SIGKILL; + info.si_errno = 0; + info.si_trapno = 0; + force_sig_info(info.si_signo, &info, current); + + return true; + } + if (attrs & SUN4V_ERR_ATTRS_PIO) { + siginfo_t info; + + info.si_signo = SIGBUS; + info.si_code = BUS_ADRERR; + info.si_addr = (void __user *)sun4v_get_vaddr(regs); + force_sig_info(info.si_signo, &info, current); + + return true; + } + + /* Default to doing nothing */ + return false; +} + /* We run with %pil set to PIL_NORMAL_MAX and PSTATE_IE enabled in %pstate. * Log the event, clear the first word of the entry, and die. */ @@ -2075,6 +2142,12 @@ void sun4v_nonresum_error(struct pt_regs *regs, unsigned long offset) put_cpu(); + if (!(regs->tstate & TSTATE_PRIV) && + sun4v_nonresum_error_user_handled(regs, &local_copy)) { + /* DON'T PANIC: This userspace error was handled. */ + return; + } + #ifdef CONFIG_PCI /* Check for the special PCI poke sequence. */ if (pci_poke_in_progress && pci_poke_cpu == cpu) { diff --git a/arch/tile/include/asm/Kbuild b/arch/tile/include/asm/Kbuild index 2d1f5638974c..aa48b6eaff2d 100644 --- a/arch/tile/include/asm/Kbuild +++ b/arch/tile/include/asm/Kbuild @@ -4,8 +4,6 @@ header-y += ../arch/ generic-y += bug.h generic-y += bugs.h generic-y += clkdev.h -generic-y += cputime.h -generic-y += div64.h generic-y += emergency-restart.h generic-y += errno.h generic-y += exec.h diff --git a/arch/tile/include/asm/div64.h b/arch/tile/include/asm/div64.h new file mode 100644 index 000000000000..9f765cdf09a5 --- /dev/null +++ b/arch/tile/include/asm/div64.h @@ -0,0 +1,16 @@ +#ifndef _ASM_TILE_DIV64_H +#define _ASM_TILE_DIV64_H + +#include <linux/types.h> + +#ifdef __tilegx__ +static inline u64 mul_u32_u32(u32 a, u32 b) +{ + return __insn_mul_lu_lu(a, b); +} +#define mul_u32_u32 mul_u32_u32 +#endif + +#include <asm-generic/div64.h> + +#endif /* _ASM_TILE_DIV64_H */ diff --git a/arch/um/drivers/random.c b/arch/um/drivers/random.c index 05523f14d7b2..57f03050c850 100644 --- a/arch/um/drivers/random.c +++ b/arch/um/drivers/random.c @@ -76,7 +76,7 @@ static ssize_t rng_dev_read (struct file *filp, char __user *buf, size_t size, add_sigio_fd(random_fd); add_wait_queue(&host_read_wait, &wait); - set_task_state(current, TASK_INTERRUPTIBLE); + set_current_state(TASK_INTERRUPTIBLE); schedule(); remove_wait_queue(&host_read_wait, &wait); diff --git a/arch/um/include/asm/Kbuild b/arch/um/include/asm/Kbuild index 052f7f6d0551..90c281cd7e1d 100644 --- a/arch/um/include/asm/Kbuild +++ b/arch/um/include/asm/Kbuild @@ -1,7 +1,6 @@ generic-y += barrier.h generic-y += bug.h generic-y += clkdev.h -generic-y += cputime.h generic-y += current.h generic-y += delay.h generic-y += device.h diff --git a/arch/unicore32/include/asm/Kbuild b/arch/unicore32/include/asm/Kbuild index 256c45b3ae34..5d51ade89f4c 100644 --- a/arch/unicore32/include/asm/Kbuild +++ b/arch/unicore32/include/asm/Kbuild @@ -4,7 +4,6 @@ generic-y += auxvec.h generic-y += bitsperlong.h generic-y += bugs.h generic-y += clkdev.h -generic-y += cputime.h generic-y += current.h generic-y += device.h generic-y += div64.h diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index e487493bbd47..f8fbfc5a98ba 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1070,7 +1070,7 @@ config X86_MCE_THRESHOLD def_bool y config X86_MCE_INJECT - depends on X86_MCE + depends on X86_MCE && X86_LOCAL_APIC tristate "Machine check injector support" ---help--- Provide support for injecting machine checks for testing purposes. @@ -1994,10 +1994,6 @@ config RANDOMIZE_BASE theoretically possible, but the implementations are further limited due to memory layouts. - If CONFIG_HIBERNATE is also enabled, KASLR is disabled at boot - time. To enable it, boot with "kaslr" on the kernel command - line (which will also disable hibernation). - If unsure, say N. # Relocation on x86 needs some additional build support diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h index e5612f3e3b57..9b42b6d1e902 100644 --- a/arch/x86/boot/boot.h +++ b/arch/x86/boot/boot.h @@ -333,6 +333,7 @@ size_t strnlen(const char *s, size_t maxlen); unsigned int atou(const char *s); unsigned long long simple_strtoull(const char *cp, char **endp, unsigned int base); size_t strlen(const char *s); +char *strchr(const char *s, int c); /* tty.c */ void puts(const char *); diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index ff01c8fc76f7..801c7a158e55 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -32,160 +32,13 @@ static void setup_boot_services##bits(struct efi_config *c) \ \ table = (typeof(table))sys_table; \ \ + c->runtime_services = table->runtime; \ c->boot_services = table->boottime; \ c->text_output = table->con_out; \ } BOOT_SERVICES(32); BOOT_SERVICES(64); -void efi_char16_printk(efi_system_table_t *, efi_char16_t *); - -static efi_status_t -__file_size32(void *__fh, efi_char16_t *filename_16, - void **handle, u64 *file_sz) -{ - efi_file_handle_32_t *h, *fh = __fh; - efi_file_info_t *info; - efi_status_t status; - efi_guid_t info_guid = EFI_FILE_INFO_ID; - u32 info_sz; - - status = efi_early->call((unsigned long)fh->open, fh, &h, filename_16, - EFI_FILE_MODE_READ, (u64)0); - if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to open file: "); - efi_char16_printk(sys_table, filename_16); - efi_printk(sys_table, "\n"); - return status; - } - - *handle = h; - - info_sz = 0; - status = efi_early->call((unsigned long)h->get_info, h, &info_guid, - &info_sz, NULL); - if (status != EFI_BUFFER_TOO_SMALL) { - efi_printk(sys_table, "Failed to get file info size\n"); - return status; - } - -grow: - status = efi_call_early(allocate_pool, EFI_LOADER_DATA, - info_sz, (void **)&info); - if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to alloc mem for file info\n"); - return status; - } - - status = efi_early->call((unsigned long)h->get_info, h, &info_guid, - &info_sz, info); - if (status == EFI_BUFFER_TOO_SMALL) { - efi_call_early(free_pool, info); - goto grow; - } - - *file_sz = info->file_size; - efi_call_early(free_pool, info); - - if (status != EFI_SUCCESS) - efi_printk(sys_table, "Failed to get initrd info\n"); - - return status; -} - -static efi_status_t -__file_size64(void *__fh, efi_char16_t *filename_16, - void **handle, u64 *file_sz) -{ - efi_file_handle_64_t *h, *fh = __fh; - efi_file_info_t *info; - efi_status_t status; - efi_guid_t info_guid = EFI_FILE_INFO_ID; - u64 info_sz; - - status = efi_early->call((unsigned long)fh->open, fh, &h, filename_16, - EFI_FILE_MODE_READ, (u64)0); - if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to open file: "); - efi_char16_printk(sys_table, filename_16); - efi_printk(sys_table, "\n"); - return status; - } - - *handle = h; - - info_sz = 0; - status = efi_early->call((unsigned long)h->get_info, h, &info_guid, - &info_sz, NULL); - if (status != EFI_BUFFER_TOO_SMALL) { - efi_printk(sys_table, "Failed to get file info size\n"); - return status; - } - -grow: - status = efi_call_early(allocate_pool, EFI_LOADER_DATA, - info_sz, (void **)&info); - if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to alloc mem for file info\n"); - return status; - } - - status = efi_early->call((unsigned long)h->get_info, h, &info_guid, - &info_sz, info); - if (status == EFI_BUFFER_TOO_SMALL) { - efi_call_early(free_pool, info); - goto grow; - } - - *file_sz = info->file_size; - efi_call_early(free_pool, info); - - if (status != EFI_SUCCESS) - efi_printk(sys_table, "Failed to get initrd info\n"); - - return status; -} -efi_status_t -efi_file_size(efi_system_table_t *sys_table, void *__fh, - efi_char16_t *filename_16, void **handle, u64 *file_sz) -{ - if (efi_early->is64) - return __file_size64(__fh, filename_16, handle, file_sz); - - return __file_size32(__fh, filename_16, handle, file_sz); -} - -efi_status_t -efi_file_read(void *handle, unsigned long *size, void *addr) -{ - unsigned long func; - - if (efi_early->is64) { - efi_file_handle_64_t *fh = handle; - - func = (unsigned long)fh->read; - return efi_early->call(func, handle, size, addr); - } else { - efi_file_handle_32_t *fh = handle; - - func = (unsigned long)fh->read; - return efi_early->call(func, handle, size, addr); - } -} - -efi_status_t efi_file_close(void *handle) -{ - if (efi_early->is64) { - efi_file_handle_64_t *fh = handle; - - return efi_early->call((unsigned long)fh->close, handle); - } else { - efi_file_handle_32_t *fh = handle; - - return efi_early->call((unsigned long)fh->close, handle); - } -} - static inline efi_status_t __open_volume32(void *__image, void **__fh) { efi_file_io_interface_t *io; @@ -249,30 +102,8 @@ efi_open_volume(efi_system_table_t *sys_table, void *__image, void **__fh) void efi_char16_printk(efi_system_table_t *table, efi_char16_t *str) { - unsigned long output_string; - size_t offset; - - if (efi_early->is64) { - struct efi_simple_text_output_protocol_64 *out; - u64 *func; - - offset = offsetof(typeof(*out), output_string); - output_string = efi_early->text_output + offset; - out = (typeof(out))(unsigned long)efi_early->text_output; - func = (u64 *)output_string; - - efi_early->call(*func, out, str); - } else { - struct efi_simple_text_output_protocol_32 *out; - u32 *func; - - offset = offsetof(typeof(*out), output_string); - output_string = efi_early->text_output + offset; - out = (typeof(out))(unsigned long)efi_early->text_output; - func = (u32 *)output_string; - - efi_early->call(*func, out, str); - } + efi_call_proto(efi_simple_text_output_protocol, output_string, + efi_early->text_output, str); } static efi_status_t @@ -1157,6 +988,13 @@ struct boot_params *efi_main(struct efi_config *c, else setup_boot_services32(efi_early); + /* + * If the boot loader gave us a value for secure_boot then we use that, + * otherwise we ask the BIOS. + */ + if (boot_params->secure_boot == efi_secureboot_mode_unset) + boot_params->secure_boot = efi_get_secureboot(sys_table); + setup_graphics(boot_params); setup_efi_pci(boot_params); diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S index fd0b6a272dd5..d85b9625e836 100644 --- a/arch/x86/boot/compressed/head_32.S +++ b/arch/x86/boot/compressed/head_32.S @@ -82,7 +82,7 @@ ENTRY(efi_pe_entry) /* Relocate efi_config->call() */ leal efi32_config(%esi), %eax - add %esi, 32(%eax) + add %esi, 40(%eax) pushl %eax call make_boot_params @@ -108,7 +108,7 @@ ENTRY(efi32_stub_entry) /* Relocate efi_config->call() */ leal efi32_config(%esi), %eax - add %esi, 32(%eax) + add %esi, 40(%eax) pushl %eax 2: call efi_main @@ -264,7 +264,7 @@ relocated: #ifdef CONFIG_EFI_STUB .data efi32_config: - .fill 4,8,0 + .fill 5,8,0 .long efi_call_phys .long 0 .byte 0 diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index 4d85e600db78..d2ae1f821e0c 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -264,7 +264,7 @@ ENTRY(efi_pe_entry) /* * Relocate efi_config->call(). */ - addq %rbp, efi64_config+32(%rip) + addq %rbp, efi64_config+40(%rip) movq %rax, %rdi call make_boot_params @@ -284,7 +284,7 @@ handover_entry: * Relocate efi_config->call(). */ movq efi_config(%rip), %rax - addq %rbp, 32(%rax) + addq %rbp, 40(%rax) 2: movq efi_config(%rip), %rdi call efi_main @@ -456,14 +456,14 @@ efi_config: #ifdef CONFIG_EFI_MIXED .global efi32_config efi32_config: - .fill 4,8,0 + .fill 5,8,0 .quad efi64_thunk .byte 0 #endif .global efi64_config efi64_config: - .fill 4,8,0 + .fill 5,8,0 .quad efi_call .byte 1 #endif /* CONFIG_EFI_STUB */ diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c index a66854d99ee1..8b7c9e75edcb 100644 --- a/arch/x86/boot/compressed/kaslr.c +++ b/arch/x86/boot/compressed/kaslr.c @@ -11,6 +11,7 @@ */ #include "misc.h" #include "error.h" +#include "../boot.h" #include <generated/compile.h> #include <linux/module.h> @@ -52,15 +53,22 @@ static unsigned long get_boot_seed(void) #include "../../lib/kaslr.c" struct mem_vector { - unsigned long start; - unsigned long size; + unsigned long long start; + unsigned long long size; }; +/* Only supporting at most 4 unusable memmap regions with kaslr */ +#define MAX_MEMMAP_REGIONS 4 + +static bool memmap_too_large; + enum mem_avoid_index { MEM_AVOID_ZO_RANGE = 0, MEM_AVOID_INITRD, MEM_AVOID_CMDLINE, MEM_AVOID_BOOTPARAMS, + MEM_AVOID_MEMMAP_BEGIN, + MEM_AVOID_MEMMAP_END = MEM_AVOID_MEMMAP_BEGIN + MAX_MEMMAP_REGIONS - 1, MEM_AVOID_MAX, }; @@ -77,6 +85,123 @@ static bool mem_overlaps(struct mem_vector *one, struct mem_vector *two) return true; } +/** + * _memparse - Parse a string with mem suffixes into a number + * @ptr: Where parse begins + * @retptr: (output) Optional pointer to next char after parse completes + * + * Parses a string into a number. The number stored at @ptr is + * potentially suffixed with K, M, G, T, P, E. + */ +static unsigned long long _memparse(const char *ptr, char **retptr) +{ + char *endptr; /* Local pointer to end of parsed string */ + + unsigned long long ret = simple_strtoull(ptr, &endptr, 0); + + switch (*endptr) { + case 'E': + case 'e': + ret <<= 10; + case 'P': + case 'p': + ret <<= 10; + case 'T': + case 't': + ret <<= 10; + case 'G': + case 'g': + ret <<= 10; + case 'M': + case 'm': + ret <<= 10; + case 'K': + case 'k': + ret <<= 10; + endptr++; + default: + break; + } + + if (retptr) + *retptr = endptr; + + return ret; +} + +static int +parse_memmap(char *p, unsigned long long *start, unsigned long long *size) +{ + char *oldp; + + if (!p) + return -EINVAL; + + /* We don't care about this option here */ + if (!strncmp(p, "exactmap", 8)) + return -EINVAL; + + oldp = p; + *size = _memparse(p, &p); + if (p == oldp) + return -EINVAL; + + switch (*p) { + case '@': + /* Skip this region, usable */ + *start = 0; + *size = 0; + return 0; + case '#': + case '$': + case '!': + *start = _memparse(p + 1, &p); + return 0; + } + + return -EINVAL; +} + +static void mem_avoid_memmap(void) +{ + char arg[128]; + int rc; + int i; + char *str; + + /* See if we have any memmap areas */ + rc = cmdline_find_option("memmap", arg, sizeof(arg)); + if (rc <= 0) + return; + + i = 0; + str = arg; + while (str && (i < MAX_MEMMAP_REGIONS)) { + int rc; + unsigned long long start, size; + char *k = strchr(str, ','); + + if (k) + *k++ = 0; + + rc = parse_memmap(str, &start, &size); + if (rc < 0) + break; + str = k; + /* A usable region that should not be skipped */ + if (size == 0) + continue; + + mem_avoid[MEM_AVOID_MEMMAP_BEGIN + i].start = start; + mem_avoid[MEM_AVOID_MEMMAP_BEGIN + i].size = size; + i++; + } + + /* More than 4 memmaps, fail kaslr */ + if ((i >= MAX_MEMMAP_REGIONS) && str) + memmap_too_large = true; +} + /* * In theory, KASLR can put the kernel anywhere in the range of [16M, 64T). * The mem_avoid array is used to store the ranges that need to be avoided @@ -197,6 +322,9 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size, /* We don't need to set a mapping for setup_data. */ + /* Mark the memmap regions we need to avoid */ + mem_avoid_memmap(); + #ifdef CONFIG_X86_VERBOSE_BOOTUP /* Make sure video RAM can be used. */ add_identity_map(0, PMD_SIZE); @@ -379,6 +507,12 @@ static unsigned long find_random_phys_addr(unsigned long minimum, int i; unsigned long addr; + /* Check if we had too many memmaps. */ + if (memmap_too_large) { + debug_putstr("Aborted e820 scan (more than 4 memmap= args)!\n"); + return 0; + } + /* Make sure minimum is aligned. */ minimum = ALIGN(minimum, CONFIG_PHYSICAL_ALIGN); @@ -456,7 +590,7 @@ void choose_random_location(unsigned long input, /* Walk e820 and find a random address. */ random_addr = find_random_phys_addr(min_addr, output_size); if (!random_addr) { - warn("KASLR disabled: could not find suitable E820 region!"); + warn("Physical KASLR disabled: no suitable memory region!"); } else { /* Update the new physical address location. */ if (*output != random_addr) { diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c index 9e240fcba784..5457b02fc050 100644 --- a/arch/x86/boot/string.c +++ b/arch/x86/boot/string.c @@ -156,3 +156,16 @@ char *strstr(const char *s1, const char *s2) } return NULL; } + +/** + * strchr - Find the first occurrence of the character c in the string s. + * @s: the string to be searched + * @c: the character to search for + */ +char *strchr(const char *s, int c) +{ + while (*s != (char)c) + if (*s++ == '\0') + return NULL; + return (char *)s; +} diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c index 6ef688a1ef3e..7ff1b0c86a8e 100644 --- a/arch/x86/crypto/aesni-intel_glue.c +++ b/arch/x86/crypto/aesni-intel_glue.c @@ -1085,9 +1085,9 @@ static void aesni_free_simds(void) aesni_simd_skciphers[i]; i++) simd_skcipher_free(aesni_simd_skciphers[i]); - for (i = 0; i < ARRAY_SIZE(aesni_simd_skciphers2) && - aesni_simd_skciphers2[i].simd; i++) - simd_skcipher_free(aesni_simd_skciphers2[i].simd); + for (i = 0; i < ARRAY_SIZE(aesni_simd_skciphers2); i++) + if (aesni_simd_skciphers2[i].simd) + simd_skcipher_free(aesni_simd_skciphers2[i].simd); } static int __init aesni_init(void) @@ -1168,7 +1168,7 @@ static int __init aesni_init(void) simd = simd_skcipher_create_compat(algname, drvname, basename); err = PTR_ERR(simd); if (IS_ERR(simd)) - goto unregister_simds; + continue; aesni_simd_skciphers2[i].simd = simd; } diff --git a/arch/x86/events/Makefile b/arch/x86/events/Makefile index 1d392c39fe56..b8ccdb5c9244 100644 --- a/arch/x86/events/Makefile +++ b/arch/x86/events/Makefile @@ -1,11 +1,4 @@ -obj-y += core.o - -obj-$(CONFIG_CPU_SUP_AMD) += amd/core.o amd/uncore.o -obj-$(CONFIG_PERF_EVENTS_AMD_POWER) += amd/power.o -obj-$(CONFIG_X86_LOCAL_APIC) += amd/ibs.o msr.o -ifdef CONFIG_AMD_IOMMU -obj-$(CONFIG_CPU_SUP_AMD) += amd/iommu.o -endif - -obj-$(CONFIG_CPU_SUP_INTEL) += msr.o +obj-y += core.o +obj-y += amd/ +obj-$(CONFIG_X86_LOCAL_APIC) += msr.o obj-$(CONFIG_CPU_SUP_INTEL) += intel/ diff --git a/arch/x86/events/amd/Makefile b/arch/x86/events/amd/Makefile new file mode 100644 index 000000000000..b1da46f396e0 --- /dev/null +++ b/arch/x86/events/amd/Makefile @@ -0,0 +1,7 @@ +obj-$(CONFIG_CPU_SUP_AMD) += core.o uncore.o +obj-$(CONFIG_PERF_EVENTS_AMD_POWER) += power.o +obj-$(CONFIG_X86_LOCAL_APIC) += ibs.o +ifdef CONFIG_AMD_IOMMU +obj-$(CONFIG_CPU_SUP_AMD) += iommu.o +endif + diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c index a0b1bdb3ad42..4d1f7f2d9aff 100644 --- a/arch/x86/events/amd/uncore.c +++ b/arch/x86/events/amd/uncore.c @@ -22,13 +22,17 @@ #define NUM_COUNTERS_NB 4 #define NUM_COUNTERS_L2 4 -#define MAX_COUNTERS NUM_COUNTERS_NB +#define NUM_COUNTERS_L3 6 +#define MAX_COUNTERS 6 #define RDPMC_BASE_NB 6 -#define RDPMC_BASE_L2 10 +#define RDPMC_BASE_LLC 10 #define COUNTER_SHIFT 16 +static int num_counters_llc; +static int num_counters_nb; + static HLIST_HEAD(uncore_unused_list); struct amd_uncore { @@ -45,30 +49,30 @@ struct amd_uncore { }; static struct amd_uncore * __percpu *amd_uncore_nb; -static struct amd_uncore * __percpu *amd_uncore_l2; +static struct amd_uncore * __percpu *amd_uncore_llc; static struct pmu amd_nb_pmu; -static struct pmu amd_l2_pmu; +static struct pmu amd_llc_pmu; static cpumask_t amd_nb_active_mask; -static cpumask_t amd_l2_active_mask; +static cpumask_t amd_llc_active_mask; static bool is_nb_event(struct perf_event *event) { return event->pmu->type == amd_nb_pmu.type; } -static bool is_l2_event(struct perf_event *event) +static bool is_llc_event(struct perf_event *event) { - return event->pmu->type == amd_l2_pmu.type; + return event->pmu->type == amd_llc_pmu.type; } static struct amd_uncore *event_to_amd_uncore(struct perf_event *event) { if (is_nb_event(event) && amd_uncore_nb) return *per_cpu_ptr(amd_uncore_nb, event->cpu); - else if (is_l2_event(event) && amd_uncore_l2) - return *per_cpu_ptr(amd_uncore_l2, event->cpu); + else if (is_llc_event(event) && amd_uncore_llc) + return *per_cpu_ptr(amd_uncore_llc, event->cpu); return NULL; } @@ -183,16 +187,16 @@ static int amd_uncore_event_init(struct perf_event *event) return -ENOENT; /* - * NB and L2 counters (MSRs) are shared across all cores that share the - * same NB / L2 cache. Interrupts can be directed to a single target - * core, however, event counts generated by processes running on other - * cores cannot be masked out. So we do not support sampling and - * per-thread events. + * NB and Last level cache counters (MSRs) are shared across all cores + * that share the same NB / Last level cache. Interrupts can be directed + * to a single target core, however, event counts generated by processes + * running on other cores cannot be masked out. So we do not support + * sampling and per-thread events. */ if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK) return -EINVAL; - /* NB and L2 counters do not have usr/os/guest/host bits */ + /* NB and Last level cache counters do not have usr/os/guest/host bits */ if (event->attr.exclude_user || event->attr.exclude_kernel || event->attr.exclude_host || event->attr.exclude_guest) return -EINVAL; @@ -226,8 +230,8 @@ static ssize_t amd_uncore_attr_show_cpumask(struct device *dev, if (pmu->type == amd_nb_pmu.type) active_mask = &amd_nb_active_mask; - else if (pmu->type == amd_l2_pmu.type) - active_mask = &amd_l2_active_mask; + else if (pmu->type == amd_llc_pmu.type) + active_mask = &amd_llc_active_mask; else return 0; @@ -244,30 +248,47 @@ static struct attribute_group amd_uncore_attr_group = { .attrs = amd_uncore_attrs, }; -PMU_FORMAT_ATTR(event, "config:0-7,32-35"); -PMU_FORMAT_ATTR(umask, "config:8-15"); - -static struct attribute *amd_uncore_format_attr[] = { - &format_attr_event.attr, - &format_attr_umask.attr, - NULL, -}; - -static struct attribute_group amd_uncore_format_group = { - .name = "format", - .attrs = amd_uncore_format_attr, +/* + * Similar to PMU_FORMAT_ATTR but allowing for format_attr to be assigned based + * on family + */ +#define AMD_FORMAT_ATTR(_dev, _name, _format) \ +static ssize_t \ +_dev##_show##_name(struct device *dev, \ + struct device_attribute *attr, \ + char *page) \ +{ \ + BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \ + return sprintf(page, _format "\n"); \ +} \ +static struct device_attribute format_attr_##_dev##_name = __ATTR_RO(_dev); + +/* Used for each uncore counter type */ +#define AMD_ATTRIBUTE(_name) \ +static struct attribute *amd_uncore_format_attr_##_name[] = { \ + &format_attr_event_##_name.attr, \ + &format_attr_umask.attr, \ + NULL, \ +}; \ +static struct attribute_group amd_uncore_format_group_##_name = { \ + .name = "format", \ + .attrs = amd_uncore_format_attr_##_name, \ +}; \ +static const struct attribute_group *amd_uncore_attr_groups_##_name[] = { \ + &amd_uncore_attr_group, \ + &amd_uncore_format_group_##_name, \ + NULL, \ }; -static const struct attribute_group *amd_uncore_attr_groups[] = { - &amd_uncore_attr_group, - &amd_uncore_format_group, - NULL, -}; +AMD_FORMAT_ATTR(event, , "config:0-7,32-35"); +AMD_FORMAT_ATTR(umask, , "config:8-15"); +AMD_FORMAT_ATTR(event, _df, "config:0-7,32-35,59-60"); +AMD_FORMAT_ATTR(event, _l3, "config:0-7"); +AMD_ATTRIBUTE(df); +AMD_ATTRIBUTE(l3); static struct pmu amd_nb_pmu = { .task_ctx_nr = perf_invalid_context, - .attr_groups = amd_uncore_attr_groups, - .name = "amd_nb", .event_init = amd_uncore_event_init, .add = amd_uncore_add, .del = amd_uncore_del, @@ -276,10 +297,8 @@ static struct pmu amd_nb_pmu = { .read = amd_uncore_read, }; -static struct pmu amd_l2_pmu = { +static struct pmu amd_llc_pmu = { .task_ctx_nr = perf_invalid_context, - .attr_groups = amd_uncore_attr_groups, - .name = "amd_l2", .event_init = amd_uncore_event_init, .add = amd_uncore_add, .del = amd_uncore_del, @@ -296,14 +315,14 @@ static struct amd_uncore *amd_uncore_alloc(unsigned int cpu) static int amd_uncore_cpu_up_prepare(unsigned int cpu) { - struct amd_uncore *uncore_nb = NULL, *uncore_l2; + struct amd_uncore *uncore_nb = NULL, *uncore_llc; if (amd_uncore_nb) { uncore_nb = amd_uncore_alloc(cpu); if (!uncore_nb) goto fail; uncore_nb->cpu = cpu; - uncore_nb->num_counters = NUM_COUNTERS_NB; + uncore_nb->num_counters = num_counters_nb; uncore_nb->rdpmc_base = RDPMC_BASE_NB; uncore_nb->msr_base = MSR_F15H_NB_PERF_CTL; uncore_nb->active_mask = &amd_nb_active_mask; @@ -312,18 +331,18 @@ static int amd_uncore_cpu_up_prepare(unsigned int cpu) *per_cpu_ptr(amd_uncore_nb, cpu) = uncore_nb; } - if (amd_uncore_l2) { - uncore_l2 = amd_uncore_alloc(cpu); - if (!uncore_l2) + if (amd_uncore_llc) { + uncore_llc = amd_uncore_alloc(cpu); + if (!uncore_llc) goto fail; - uncore_l2->cpu = cpu; - uncore_l2->num_counters = NUM_COUNTERS_L2; - uncore_l2->rdpmc_base = RDPMC_BASE_L2; - uncore_l2->msr_base = MSR_F16H_L2I_PERF_CTL; - uncore_l2->active_mask = &amd_l2_active_mask; - uncore_l2->pmu = &amd_l2_pmu; - uncore_l2->id = -1; - *per_cpu_ptr(amd_uncore_l2, cpu) = uncore_l2; + uncore_llc->cpu = cpu; + uncore_llc->num_counters = num_counters_llc; + uncore_llc->rdpmc_base = RDPMC_BASE_LLC; + uncore_llc->msr_base = MSR_F16H_L2I_PERF_CTL; + uncore_llc->active_mask = &amd_llc_active_mask; + uncore_llc->pmu = &amd_llc_pmu; + uncore_llc->id = -1; + *per_cpu_ptr(amd_uncore_llc, cpu) = uncore_llc; } return 0; @@ -376,17 +395,17 @@ static int amd_uncore_cpu_starting(unsigned int cpu) *per_cpu_ptr(amd_uncore_nb, cpu) = uncore; } - if (amd_uncore_l2) { + if (amd_uncore_llc) { unsigned int apicid = cpu_data(cpu).apicid; unsigned int nshared; - uncore = *per_cpu_ptr(amd_uncore_l2, cpu); + uncore = *per_cpu_ptr(amd_uncore_llc, cpu); cpuid_count(0x8000001d, 2, &eax, &ebx, &ecx, &edx); nshared = ((eax >> 14) & 0xfff) + 1; uncore->id = apicid - (apicid % nshared); - uncore = amd_uncore_find_online_sibling(uncore, amd_uncore_l2); - *per_cpu_ptr(amd_uncore_l2, cpu) = uncore; + uncore = amd_uncore_find_online_sibling(uncore, amd_uncore_llc); + *per_cpu_ptr(amd_uncore_llc, cpu) = uncore; } return 0; @@ -419,8 +438,8 @@ static int amd_uncore_cpu_online(unsigned int cpu) if (amd_uncore_nb) uncore_online(cpu, amd_uncore_nb); - if (amd_uncore_l2) - uncore_online(cpu, amd_uncore_l2); + if (amd_uncore_llc) + uncore_online(cpu, amd_uncore_llc); return 0; } @@ -456,8 +475,8 @@ static int amd_uncore_cpu_down_prepare(unsigned int cpu) if (amd_uncore_nb) uncore_down_prepare(cpu, amd_uncore_nb); - if (amd_uncore_l2) - uncore_down_prepare(cpu, amd_uncore_l2); + if (amd_uncore_llc) + uncore_down_prepare(cpu, amd_uncore_llc); return 0; } @@ -479,8 +498,8 @@ static int amd_uncore_cpu_dead(unsigned int cpu) if (amd_uncore_nb) uncore_dead(cpu, amd_uncore_nb); - if (amd_uncore_l2) - uncore_dead(cpu, amd_uncore_l2); + if (amd_uncore_llc) + uncore_dead(cpu, amd_uncore_llc); return 0; } @@ -492,6 +511,47 @@ static int __init amd_uncore_init(void) if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) goto fail_nodev; + switch(boot_cpu_data.x86) { + case 23: + /* Family 17h: */ + num_counters_nb = NUM_COUNTERS_NB; + num_counters_llc = NUM_COUNTERS_L3; + /* + * For Family17h, the NorthBridge counters are + * re-purposed as Data Fabric counters. Also, support is + * added for L3 counters. The pmus are exported based on + * family as either L2 or L3 and NB or DF. + */ + amd_nb_pmu.name = "amd_df"; + amd_llc_pmu.name = "amd_l3"; + format_attr_event_df.show = &event_show_df; + format_attr_event_l3.show = &event_show_l3; + break; + case 22: + /* Family 16h - may change: */ + num_counters_nb = NUM_COUNTERS_NB; + num_counters_llc = NUM_COUNTERS_L2; + amd_nb_pmu.name = "amd_nb"; + amd_llc_pmu.name = "amd_l2"; + format_attr_event_df = format_attr_event; + format_attr_event_l3 = format_attr_event; + break; + default: + /* + * All prior families have the same number of + * NorthBridge and Last Level Cache counters + */ + num_counters_nb = NUM_COUNTERS_NB; + num_counters_llc = NUM_COUNTERS_L2; + amd_nb_pmu.name = "amd_nb"; + amd_llc_pmu.name = "amd_l2"; + format_attr_event_df = format_attr_event; + format_attr_event_l3 = format_attr_event; + break; + } + amd_nb_pmu.attr_groups = amd_uncore_attr_groups_df; + amd_llc_pmu.attr_groups = amd_uncore_attr_groups_l3; + if (!boot_cpu_has(X86_FEATURE_TOPOEXT)) goto fail_nodev; @@ -510,16 +570,16 @@ static int __init amd_uncore_init(void) } if (boot_cpu_has(X86_FEATURE_PERFCTR_L2)) { - amd_uncore_l2 = alloc_percpu(struct amd_uncore *); - if (!amd_uncore_l2) { + amd_uncore_llc = alloc_percpu(struct amd_uncore *); + if (!amd_uncore_llc) { ret = -ENOMEM; - goto fail_l2; + goto fail_llc; } - ret = perf_pmu_register(&amd_l2_pmu, amd_l2_pmu.name, -1); + ret = perf_pmu_register(&amd_llc_pmu, amd_llc_pmu.name, -1); if (ret) - goto fail_l2; + goto fail_llc; - pr_info("perf: AMD L2I counters detected\n"); + pr_info("perf: AMD LLC counters detected\n"); ret = 0; } @@ -529,7 +589,7 @@ static int __init amd_uncore_init(void) if (cpuhp_setup_state(CPUHP_PERF_X86_AMD_UNCORE_PREP, "perf/x86/amd/uncore:prepare", amd_uncore_cpu_up_prepare, amd_uncore_cpu_dead)) - goto fail_l2; + goto fail_llc; if (cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING, "perf/x86/amd/uncore:starting", @@ -546,11 +606,11 @@ fail_start: cpuhp_remove_state(CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING); fail_prep: cpuhp_remove_state(CPUHP_PERF_X86_AMD_UNCORE_PREP); -fail_l2: +fail_llc: if (boot_cpu_has(X86_FEATURE_PERFCTR_NB)) perf_pmu_unregister(&amd_nb_pmu); - if (amd_uncore_l2) - free_percpu(amd_uncore_l2); + if (amd_uncore_llc) + free_percpu(amd_uncore_llc); fail_nb: if (amd_uncore_nb) free_percpu(amd_uncore_nb); diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index 1076c9a77292..aff4b5b69d40 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -541,6 +541,9 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_MOBILE, snb_cstates), X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_DESKTOP, snb_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_MOBILE, snb_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_DESKTOP, snb_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNL, knl_cstates), X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNM, knl_cstates), { }, diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c index 1c1b9fe705c8..5900471ee508 100644 --- a/arch/x86/events/intel/pt.c +++ b/arch/x86/events/intel/pt.c @@ -99,18 +99,24 @@ static struct attribute_group pt_cap_group = { }; PMU_FORMAT_ATTR(cyc, "config:1" ); +PMU_FORMAT_ATTR(pwr_evt, "config:4" ); +PMU_FORMAT_ATTR(fup_on_ptw, "config:5" ); PMU_FORMAT_ATTR(mtc, "config:9" ); PMU_FORMAT_ATTR(tsc, "config:10" ); PMU_FORMAT_ATTR(noretcomp, "config:11" ); +PMU_FORMAT_ATTR(ptw, "config:12" ); PMU_FORMAT_ATTR(mtc_period, "config:14-17" ); PMU_FORMAT_ATTR(cyc_thresh, "config:19-22" ); PMU_FORMAT_ATTR(psb_period, "config:24-27" ); static struct attribute *pt_formats_attr[] = { &format_attr_cyc.attr, + &format_attr_pwr_evt.attr, + &format_attr_fup_on_ptw.attr, &format_attr_mtc.attr, &format_attr_tsc.attr, &format_attr_noretcomp.attr, + &format_attr_ptw.attr, &format_attr_mtc_period.attr, &format_attr_cyc_thresh.attr, &format_attr_psb_period.attr, diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c index 17c3564d087a..22054ca49026 100644 --- a/arch/x86/events/intel/rapl.c +++ b/arch/x86/events/intel/rapl.c @@ -161,7 +161,13 @@ static u64 rapl_timer_ms; static inline struct rapl_pmu *cpu_to_rapl_pmu(unsigned int cpu) { - return rapl_pmus->pmus[topology_logical_package_id(cpu)]; + unsigned int pkgid = topology_logical_package_id(cpu); + + /* + * The unsigned check also catches the '-1' return value for non + * existent mappings in the topology map. + */ + return pkgid < rapl_pmus->maxpkg ? rapl_pmus->pmus[pkgid] : NULL; } static inline u64 rapl_read_counter(struct perf_event *event) @@ -402,6 +408,8 @@ static int rapl_pmu_event_init(struct perf_event *event) /* must be done before validate_group */ pmu = cpu_to_rapl_pmu(event->cpu); + if (!pmu) + return -EINVAL; event->cpu = pmu->cpu; event->pmu_private = pmu; event->hw.event_base = msr; @@ -585,6 +593,20 @@ static int rapl_cpu_online(unsigned int cpu) struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu); int target; + if (!pmu) { + pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu)); + if (!pmu) + return -ENOMEM; + + raw_spin_lock_init(&pmu->lock); + INIT_LIST_HEAD(&pmu->active_list); + pmu->pmu = &rapl_pmus->pmu; + pmu->timer_interval = ms_to_ktime(rapl_timer_ms); + rapl_hrtimer_init(pmu); + + rapl_pmus->pmus[topology_logical_package_id(cpu)] = pmu; + } + /* * Check if there is an online cpu in the package which collects rapl * events already. @@ -598,27 +620,6 @@ static int rapl_cpu_online(unsigned int cpu) return 0; } -static int rapl_cpu_prepare(unsigned int cpu) -{ - struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu); - - if (pmu) - return 0; - - pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu)); - if (!pmu) - return -ENOMEM; - - raw_spin_lock_init(&pmu->lock); - INIT_LIST_HEAD(&pmu->active_list); - pmu->pmu = &rapl_pmus->pmu; - pmu->timer_interval = ms_to_ktime(rapl_timer_ms); - pmu->cpu = -1; - rapl_hrtimer_init(pmu); - rapl_pmus->pmus[topology_logical_package_id(cpu)] = pmu; - return 0; -} - static int rapl_check_hw_unit(bool apply_quirk) { u64 msr_rapl_power_unit_bits; @@ -770,6 +771,9 @@ static const struct x86_cpu_id rapl_cpu_match[] __initconst = { X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_DESKTOP, skl_rapl_init), X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_X, hsx_rapl_init), + X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE_MOBILE, skl_rapl_init), + X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE_DESKTOP, skl_rapl_init), + X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT, hsw_rapl_init), {}, }; @@ -803,29 +807,21 @@ static int __init rapl_pmu_init(void) /* * Install callbacks. Core will call them for each online cpu. */ - - ret = cpuhp_setup_state(CPUHP_PERF_X86_RAPL_PREP, "perf/x86/rapl:prepare", - rapl_cpu_prepare, NULL); - if (ret) - goto out; - ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_RAPL_ONLINE, "perf/x86/rapl:online", rapl_cpu_online, rapl_cpu_offline); if (ret) - goto out1; + goto out; ret = perf_pmu_register(&rapl_pmus->pmu, "power", -1); if (ret) - goto out2; + goto out1; rapl_advertise(); return 0; -out2: - cpuhp_remove_state(CPUHP_AP_PERF_X86_RAPL_ONLINE); out1: - cpuhp_remove_state(CPUHP_PERF_X86_RAPL_PREP); + cpuhp_remove_state(CPUHP_AP_PERF_X86_RAPL_ONLINE); out: pr_warn("Initialization failed (%d), disabled\n", ret); cleanup_rapl_pmus(); @@ -836,7 +832,6 @@ module_init(rapl_pmu_init); static void __exit intel_rapl_exit(void) { cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_RAPL_ONLINE); - cpuhp_remove_state_nocalls(CPUHP_PERF_X86_RAPL_PREP); perf_pmu_unregister(&rapl_pmus->pmu); cleanup_rapl_pmus(); } diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 8c4ccdc3a3f3..758c1aa5009d 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -100,7 +100,13 @@ ssize_t uncore_event_show(struct kobject *kobj, struct intel_uncore_box *uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu) { - return pmu->boxes[topology_logical_package_id(cpu)]; + unsigned int pkgid = topology_logical_package_id(cpu); + + /* + * The unsigned check also catches the '-1' return value for non + * existent mappings in the topology map. + */ + return pkgid < max_packages ? pmu->boxes[pkgid] : NULL; } u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event) @@ -764,30 +770,6 @@ static void uncore_pmu_unregister(struct intel_uncore_pmu *pmu) pmu->registered = false; } -static void __uncore_exit_boxes(struct intel_uncore_type *type, int cpu) -{ - struct intel_uncore_pmu *pmu = type->pmus; - struct intel_uncore_box *box; - int i, pkg; - - if (pmu) { - pkg = topology_physical_package_id(cpu); - for (i = 0; i < type->num_boxes; i++, pmu++) { - box = pmu->boxes[pkg]; - if (box) - uncore_box_exit(box); - } - } -} - -static void uncore_exit_boxes(void *dummy) -{ - struct intel_uncore_type **types; - - for (types = uncore_msr_uncores; *types; types++) - __uncore_exit_boxes(*types++, smp_processor_id()); -} - static void uncore_free_boxes(struct intel_uncore_pmu *pmu) { int pkg; @@ -1058,86 +1040,6 @@ static void uncore_pci_exit(void) } } -static int uncore_cpu_dying(unsigned int cpu) -{ - struct intel_uncore_type *type, **types = uncore_msr_uncores; - struct intel_uncore_pmu *pmu; - struct intel_uncore_box *box; - int i, pkg; - - pkg = topology_logical_package_id(cpu); - for (; *types; types++) { - type = *types; - pmu = type->pmus; - for (i = 0; i < type->num_boxes; i++, pmu++) { - box = pmu->boxes[pkg]; - if (box && atomic_dec_return(&box->refcnt) == 0) - uncore_box_exit(box); - } - } - return 0; -} - -static int first_init; - -static int uncore_cpu_starting(unsigned int cpu) -{ - struct intel_uncore_type *type, **types = uncore_msr_uncores; - struct intel_uncore_pmu *pmu; - struct intel_uncore_box *box; - int i, pkg, ncpus = 1; - - if (first_init) { - /* - * On init we get the number of online cpus in the package - * and set refcount for all of them. - */ - ncpus = cpumask_weight(topology_core_cpumask(cpu)); - } - - pkg = topology_logical_package_id(cpu); - for (; *types; types++) { - type = *types; - pmu = type->pmus; - for (i = 0; i < type->num_boxes; i++, pmu++) { - box = pmu->boxes[pkg]; - if (!box) - continue; - /* The first cpu on a package activates the box */ - if (atomic_add_return(ncpus, &box->refcnt) == ncpus) - uncore_box_init(box); - } - } - - return 0; -} - -static int uncore_cpu_prepare(unsigned int cpu) -{ - struct intel_uncore_type *type, **types = uncore_msr_uncores; - struct intel_uncore_pmu *pmu; - struct intel_uncore_box *box; - int i, pkg; - - pkg = topology_logical_package_id(cpu); - for (; *types; types++) { - type = *types; - pmu = type->pmus; - for (i = 0; i < type->num_boxes; i++, pmu++) { - if (pmu->boxes[pkg]) - continue; - /* First cpu of a package allocates the box */ - box = uncore_alloc_box(type, cpu_to_node(cpu)); - if (!box) - return -ENOMEM; - box->pmu = pmu; - box->pkgid = pkg; - pmu->boxes[pkg] = box; - } - } - return 0; -} - static void uncore_change_type_ctx(struct intel_uncore_type *type, int old_cpu, int new_cpu) { @@ -1177,12 +1079,14 @@ static void uncore_change_context(struct intel_uncore_type **uncores, static int uncore_event_cpu_offline(unsigned int cpu) { - int target; + struct intel_uncore_type *type, **types = uncore_msr_uncores; + struct intel_uncore_pmu *pmu; + struct intel_uncore_box *box; + int i, pkg, target; /* Check if exiting cpu is used for collecting uncore events */ if (!cpumask_test_and_clear_cpu(cpu, &uncore_cpu_mask)) - return 0; - + goto unref; /* Find a new cpu to collect uncore events */ target = cpumask_any_but(topology_core_cpumask(cpu), cpu); @@ -1194,12 +1098,82 @@ static int uncore_event_cpu_offline(unsigned int cpu) uncore_change_context(uncore_msr_uncores, cpu, target); uncore_change_context(uncore_pci_uncores, cpu, target); + +unref: + /* Clear the references */ + pkg = topology_logical_package_id(cpu); + for (; *types; types++) { + type = *types; + pmu = type->pmus; + for (i = 0; i < type->num_boxes; i++, pmu++) { + box = pmu->boxes[pkg]; + if (box && atomic_dec_return(&box->refcnt) == 0) + uncore_box_exit(box); + } + } return 0; } +static int allocate_boxes(struct intel_uncore_type **types, + unsigned int pkg, unsigned int cpu) +{ + struct intel_uncore_box *box, *tmp; + struct intel_uncore_type *type; + struct intel_uncore_pmu *pmu; + LIST_HEAD(allocated); + int i; + + /* Try to allocate all required boxes */ + for (; *types; types++) { + type = *types; + pmu = type->pmus; + for (i = 0; i < type->num_boxes; i++, pmu++) { + if (pmu->boxes[pkg]) + continue; + box = uncore_alloc_box(type, cpu_to_node(cpu)); + if (!box) + goto cleanup; + box->pmu = pmu; + box->pkgid = pkg; + list_add(&box->active_list, &allocated); + } + } + /* Install them in the pmus */ + list_for_each_entry_safe(box, tmp, &allocated, active_list) { + list_del_init(&box->active_list); + box->pmu->boxes[pkg] = box; + } + return 0; + +cleanup: + list_for_each_entry_safe(box, tmp, &allocated, active_list) { + list_del_init(&box->active_list); + kfree(box); + } + return -ENOMEM; +} + static int uncore_event_cpu_online(unsigned int cpu) { - int target; + struct intel_uncore_type *type, **types = uncore_msr_uncores; + struct intel_uncore_pmu *pmu; + struct intel_uncore_box *box; + int i, ret, pkg, target; + + pkg = topology_logical_package_id(cpu); + ret = allocate_boxes(types, pkg, cpu); + if (ret) + return ret; + + for (; *types; types++) { + type = *types; + pmu = type->pmus; + for (i = 0; i < type->num_boxes; i++, pmu++) { + box = pmu->boxes[pkg]; + if (!box && atomic_inc_return(&box->refcnt) == 1) + uncore_box_init(box); + } + } /* * Check if there is an online cpu in the package @@ -1354,6 +1328,8 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = { X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_DESKTOP,skl_uncore_init), X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_MOBILE, skl_uncore_init), X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_X, skx_uncore_init), + X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE_MOBILE, skl_uncore_init), + X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE_DESKTOP, skl_uncore_init), {}, }; @@ -1389,38 +1365,16 @@ static int __init intel_uncore_init(void) if (cret && pret) return -ENODEV; - /* - * Install callbacks. Core will call them for each online cpu. - * - * The first online cpu of each package allocates and takes - * the refcounts for all other online cpus in that package. - * If msrs are not enabled no allocation is required and - * uncore_cpu_prepare() is not called for each online cpu. - */ - if (!cret) { - ret = cpuhp_setup_state(CPUHP_PERF_X86_UNCORE_PREP, - "perf/x86/intel/uncore:prepare", - uncore_cpu_prepare, NULL); - if (ret) - goto err; - } else { - cpuhp_setup_state_nocalls(CPUHP_PERF_X86_UNCORE_PREP, - "perf/x86/intel/uncore:prepare", - uncore_cpu_prepare, NULL); - } - first_init = 1; - cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_STARTING, - "perf/x86/uncore:starting", - uncore_cpu_starting, uncore_cpu_dying); - first_init = 0; - cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_ONLINE, - "perf/x86/uncore:online", - uncore_event_cpu_online, uncore_event_cpu_offline); + /* Install hotplug callbacks to setup the targets for each package */ + ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_ONLINE, + "perf/x86/intel/uncore:online", + uncore_event_cpu_online, + uncore_event_cpu_offline); + if (ret) + goto err; return 0; err: - /* Undo box->init_box() */ - on_each_cpu_mask(&uncore_cpu_mask, uncore_exit_boxes, NULL, 1); uncore_types_exit(uncore_msr_uncores); uncore_pci_exit(); return ret; @@ -1429,9 +1383,7 @@ module_init(intel_uncore_init); static void __exit intel_uncore_exit(void) { - cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_UNCORE_ONLINE); - cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_UNCORE_STARTING); - cpuhp_remove_state_nocalls(CPUHP_PERF_X86_UNCORE_PREP); + cpuhp_remove_state(CPUHP_AP_PERF_X86_UNCORE_ONLINE); uncore_types_exit(uncore_msr_uncores); uncore_pci_exit(); } diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild index 2b892e2313a9..5d6a53fd7521 100644 --- a/arch/x86/include/asm/Kbuild +++ b/arch/x86/include/asm/Kbuild @@ -7,7 +7,6 @@ generated-y += unistd_64_x32.h generated-y += xen-hypercalls.h generic-y += clkdev.h -generic-y += cputime.h generic-y += dma-contiguous.h generic-y += early_ioremap.h generic-y += mcs_spinlock.h diff --git a/arch/x86/include/asm/div64.h b/arch/x86/include/asm/div64.h index ced283ac79df..af95c47d5c9e 100644 --- a/arch/x86/include/asm/div64.h +++ b/arch/x86/include/asm/div64.h @@ -59,6 +59,17 @@ static inline u64 div_u64_rem(u64 dividend, u32 divisor, u32 *remainder) } #define div_u64_rem div_u64_rem +static inline u64 mul_u32_u32(u32 a, u32 b) +{ + u32 high, low; + + asm ("mull %[b]" : "=a" (low), "=d" (high) + : [a] "a" (a), [b] "rm" (b) ); + + return low | ((u64)high) << 32; +} +#define mul_u32_u32 mul_u32_u32 + #else # include <asm-generic/div64.h> #endif /* CONFIG_X86_32 */ diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h index ec23d8e1297c..67313f3a9874 100644 --- a/arch/x86/include/asm/e820.h +++ b/arch/x86/include/asm/e820.h @@ -30,8 +30,6 @@ extern u64 e820_remove_range(u64 start, u64 size, unsigned old_type, int checktype); extern void update_e820(void); extern void e820_setup_gap(void); -extern int e820_search_gap(unsigned long *gapstart, unsigned long *gapsize, - unsigned long start_addr, unsigned long long end_addr); struct setup_data; extern void parse_e820_ext(u64 phys_addr, u32 data_len); diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index e99675b9c861..2f77bcefe6b4 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -191,6 +191,7 @@ static inline efi_status_t efi_thunk_set_virtual_address_map( struct efi_config { u64 image_handle; u64 table; + u64 runtime_services; u64 boot_services; u64 text_output; efi_status_t (*call)(unsigned long, ...); @@ -226,6 +227,10 @@ static inline bool efi_is_64bit(void) #define __efi_call_early(f, ...) \ __efi_early()->call((unsigned long)f, __VA_ARGS__); +#define efi_call_runtime(f, ...) \ + __efi_early()->call(efi_table_attr(efi_runtime_services, f, \ + __efi_early()->runtime_services), __VA_ARGS__) + extern bool efi_reboot_required(void); #else diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 5132f2a6c0a2..e63873683d4a 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -97,10 +97,6 @@ #define MCE_OVERFLOW 0 /* bit 0 in flags means overflow */ -/* Software defined banks */ -#define MCE_EXTENDED_BANK 128 -#define MCE_THERMAL_BANK (MCE_EXTENDED_BANK + 0) - #define MCE_LOG_LEN 32 #define MCE_LOG_SIGNATURE "MACHINECHECK" @@ -193,6 +189,15 @@ extern struct mce_vendor_flags mce_flags; extern struct mca_config mca_cfg; extern struct mca_msr_regs msr_ops; + +enum mce_notifier_prios { + MCE_PRIO_SRAO = INT_MAX, + MCE_PRIO_EXTLOG = INT_MAX - 1, + MCE_PRIO_NFIT = INT_MAX - 2, + MCE_PRIO_EDAC = INT_MAX - 3, + MCE_PRIO_LOWEST = 0, +}; + extern void mce_register_decode_chain(struct notifier_block *nb); extern void mce_unregister_decode_chain(struct notifier_block *nb); @@ -306,8 +311,6 @@ extern void (*deferred_error_int_vector)(void); void intel_init_thermal(struct cpuinfo_x86 *c); -void mce_log_therm_throt_event(__u64 status); - /* Interrupt Handler for core thermal thresholds */ extern int (*platform_thermal_notify)(__u64 msr_val); @@ -362,12 +365,13 @@ struct smca_hwid { unsigned int bank_type; /* Use with smca_bank_types for easy indexing. */ u32 hwid_mcatype; /* (hwid,mcatype) tuple */ u32 xec_bitmap; /* Bitmap of valid ExtErrorCodes; current max is 21. */ + u8 count; /* Number of instances. */ }; struct smca_bank { struct smca_hwid *hwid; - /* Instance ID */ - u32 id; + u32 id; /* Value of MCA_IPID[InstanceId]. */ + u8 sysfs_id; /* Value used for sysfs name. */ }; extern struct smca_bank smca_banks[MAX_NR_BANKS]; diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index 38711df3bcb5..2266f864b747 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -140,6 +140,7 @@ extern void __init load_ucode_bsp(void); extern void load_ucode_ap(void); void reload_early_microcode(void); extern bool get_builtin_firmware(struct cpio_data *cd, const char *name); +extern bool initrd_gone; #else static inline int __init microcode_init(void) { return 0; }; static inline void __init load_ucode_bsp(void) { } diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h index b6c0b404898a..fbc73360aea0 100644 --- a/arch/x86/include/asm/pgtable_32.h +++ b/arch/x86/include/asm/pgtable_32.h @@ -27,6 +27,7 @@ struct vm_area_struct; extern pgd_t swapper_pg_dir[1024]; extern pgd_t initial_page_table[1024]; +extern pmd_t initial_pg_pmd[]; static inline void pgtable_cache_init(void) { } static inline void check_pgt_cache(void) { } @@ -75,4 +76,35 @@ do { \ #define kern_addr_valid(kaddr) (0) #endif +/* + * This is how much memory in addition to the memory covered up to + * and including _end we need mapped initially. + * We need: + * (KERNEL_IMAGE_SIZE/4096) / 1024 pages (worst case, non PAE) + * (KERNEL_IMAGE_SIZE/4096) / 512 + 4 pages (worst case for PAE) + * + * Modulo rounding, each megabyte assigned here requires a kilobyte of + * memory, which is currently unreclaimed. + * + * This should be a multiple of a page. + * + * KERNEL_IMAGE_SIZE should be greater than pa(_end) + * and small than max_low_pfn, otherwise will waste some page table entries + */ +#if PTRS_PER_PMD > 1 +#define PAGE_TABLE_SIZE(pages) (((pages) / PTRS_PER_PMD) + PTRS_PER_PGD) +#else +#define PAGE_TABLE_SIZE(pages) ((pages) / PTRS_PER_PGD) +#endif + +/* + * Number of possible pages in the lowmem region. + * + * We shift 2 by 31 instead of 1 by 32 to the left in order to avoid a + * gas warning about overflowing shift count when gas has been compiled + * with only a host target support using a 32-bit type for internal + * representation. + */ +#define LOWMEM_PAGES ((((2<<31) - __PAGE_OFFSET) >> PAGE_SHIFT)) + #endif /* _ASM_X86_PGTABLE_32_H */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 1be64da0384e..e6cfe7ba2d65 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -104,6 +104,7 @@ struct cpuinfo_x86 { __u8 x86_phys_bits; /* CPUID returned core id bits: */ __u8 x86_coreid_bits; + __u8 cu_id; /* Max extended CPUID function supported: */ __u32 extended_cpuid_level; /* Maximum supported CPUID level, -1=no CPUID: */ diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h index 921bea7a2708..6d391909e864 100644 --- a/arch/x86/include/asm/spinlock.h +++ b/arch/x86/include/asm/spinlock.h @@ -23,9 +23,6 @@ /* How long a lock should spin before we consider blocking */ #define SPIN_THRESHOLD (1 << 15) -extern struct static_key paravirt_ticketlocks_enabled; -static __always_inline bool static_key_false(struct static_key *key); - #include <asm/qspinlock.h> /* diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h index b10bf319ed20..5138dacf8bb8 100644 --- a/arch/x86/include/uapi/asm/bootparam.h +++ b/arch/x86/include/uapi/asm/bootparam.h @@ -135,7 +135,8 @@ struct boot_params { __u8 eddbuf_entries; /* 0x1e9 */ __u8 edd_mbr_sig_buf_entries; /* 0x1ea */ __u8 kbd_status; /* 0x1eb */ - __u8 _pad5[3]; /* 0x1ec */ + __u8 secure_boot; /* 0x1ec */ + __u8 _pad5[2]; /* 0x1ed */ /* * The sentinel is set to a nonzero value (0xff) in header.S. * diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 64422f850e95..7ff007ed899d 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -35,6 +35,7 @@ #include <linux/bootmem.h> #include <linux/ioport.h> #include <linux/pci.h> +#include <linux/efi-bgrt.h> #include <asm/irqdomain.h> #include <asm/pci_x86.h> @@ -1557,6 +1558,12 @@ int __init early_acpi_boot_init(void) return 0; } +static int __init acpi_parse_bgrt(struct acpi_table_header *table) +{ + efi_bgrt_init(table); + return 0; +} + int __init acpi_boot_init(void) { /* those are executed after early-quirks are executed */ @@ -1581,6 +1588,8 @@ int __init acpi_boot_init(void) acpi_process_madt(); acpi_table_parse(ACPI_SIG_HPET, acpi_parse_hpet); + if (IS_ENABLED(CONFIG_ACPI_BGRT)) + acpi_table_parse(ACPI_SIG_BGRT, acpi_parse_bgrt); if (!acpi_noirq) x86_init.pci.init = pci_acpi_init; diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 5b7e43eff139..8567c851172c 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -529,18 +529,19 @@ static void lapic_timer_broadcast(const struct cpumask *mask) * The local apic timer can be used for any function which is CPU local. */ static struct clock_event_device lapic_clockevent = { - .name = "lapic", - .features = CLOCK_EVT_FEAT_PERIODIC | - CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_C3STOP - | CLOCK_EVT_FEAT_DUMMY, - .shift = 32, - .set_state_shutdown = lapic_timer_shutdown, - .set_state_periodic = lapic_timer_set_periodic, - .set_state_oneshot = lapic_timer_set_oneshot, - .set_next_event = lapic_next_event, - .broadcast = lapic_timer_broadcast, - .rating = 100, - .irq = -1, + .name = "lapic", + .features = CLOCK_EVT_FEAT_PERIODIC | + CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_C3STOP + | CLOCK_EVT_FEAT_DUMMY, + .shift = 32, + .set_state_shutdown = lapic_timer_shutdown, + .set_state_periodic = lapic_timer_set_periodic, + .set_state_oneshot = lapic_timer_set_oneshot, + .set_state_oneshot_stopped = lapic_timer_shutdown, + .set_next_event = lapic_next_event, + .broadcast = lapic_timer_broadcast, + .rating = 100, + .irq = -1, }; static DEFINE_PER_CPU(struct clock_event_device, lapic_events); @@ -1245,7 +1246,7 @@ static void lapic_setup_esr(void) /** * setup_local_APIC - setup the local APIC * - * Used to setup local APIC while initializing BSP or bringin up APs. + * Used to setup local APIC while initializing BSP or bringing up APs. * Always called with preemption disabled. */ void setup_local_APIC(void) @@ -2028,8 +2029,8 @@ void disconnect_bsp_APIC(int virt_wire_setup) /* * The number of allocated logical CPU IDs. Since logical CPU IDs are allocated * contiguously, it equals to current allocated max logical CPU ID plus 1. - * All allocated CPU ID should be in [0, nr_logical_cpuidi), so the maximum of - * nr_logical_cpuids is nr_cpu_ids. + * All allocated CPU IDs should be in the [0, nr_logical_cpuids) range, + * so the maximum of nr_logical_cpuids is nr_cpu_ids. * * NOTE: Reserve 0 for BSP. */ @@ -2094,7 +2095,7 @@ int __generic_processor_info(int apicid, int version, bool enabled) * Since fixing handling of boot_cpu_physical_apicid requires * another discussion and tests on each platform, we leave it * for now and here we use read_apic_id() directly in this - * function, generic_processor_info(). + * function, __generic_processor_info(). */ if (disabled_cpu_apicid != BAD_APICID && disabled_cpu_apicid != read_apic_id() && diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 1e35dd06b090..52f352b063fd 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2117,6 +2117,7 @@ static inline void __init check_timer(void) if (idx != -1 && irq_trigger(idx)) unmask_ioapic_irq(irq_get_chip_data(0)); } + irq_domain_deactivate_irq(irq_data); irq_domain_activate_irq(irq_data); if (timer_irq_works()) { if (disable_timer_pin_1 > 0) @@ -2138,6 +2139,7 @@ static inline void __init check_timer(void) * legacy devices should be connected to IO APIC #0 */ replace_pin_at_irq_node(data, node, apic1, pin1, apic2, pin2); + irq_domain_deactivate_irq(irq_data); irq_domain_activate_irq(irq_data); legacy_pic->unmask(0); if (timer_irq_works()) { diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index 45d44c173cf9..4a7080c84a5a 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -905,8 +905,8 @@ static int apm_cpu_idle(struct cpuidle_device *dev, { static int use_apm_idle; /* = 0 */ static unsigned int last_jiffies; /* = 0 */ - static unsigned int last_stime; /* = 0 */ - cputime_t stime, utime; + static u64 last_stime; /* = 0 */ + u64 stime, utime; int apm_idle_done = 0; unsigned int jiffies_since_last_check = jiffies - last_jiffies; @@ -919,7 +919,7 @@ recalc: } else if (jiffies_since_last_check > idle_period) { unsigned int idle_percentage; - idle_percentage = cputime_to_jiffies(stime - last_stime); + idle_percentage = nsecs_to_jiffies(stime - last_stime); idle_percentage *= 100; idle_percentage /= jiffies_since_last_check; use_apm_idle = (idle_percentage > idle_threshold); diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index c62e015b126c..de827d6ac8c2 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -81,6 +81,7 @@ void common(void) { BLANK(); OFFSET(BP_scratch, boot_params, scratch); + OFFSET(BP_secure_boot, boot_params, secure_boot); OFFSET(BP_loadflags, boot_params, hdr.loadflags); OFFSET(BP_hardware_subarch, boot_params, hdr.hardware_subarch); OFFSET(BP_version, boot_params, hdr.version); diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 1d3167269a67..4e95b2e0d95f 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -309,8 +309,22 @@ static void amd_get_topology(struct cpuinfo_x86 *c) /* get information required for multi-node processors */ if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { + u32 eax, ebx, ecx, edx; - node_id = cpuid_ecx(0x8000001e) & 7; + cpuid(0x8000001e, &eax, &ebx, &ecx, &edx); + + node_id = ecx & 0xff; + smp_num_siblings = ((ebx >> 8) & 0xff) + 1; + + if (c->x86 == 0x15) + c->cu_id = ebx & 0xff; + + if (c->x86 >= 0x17) { + c->cpu_core_id = ebx & 0xff; + + if (smp_num_siblings > 1) + c->x86_max_cores /= smp_num_siblings; + } /* * We may have multiple LLCs if L3 caches exist, so check if we @@ -541,8 +555,10 @@ static void early_init_amd(struct cpuinfo_x86 *c) if (c->x86_power & (1 << 8)) { set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC); - if (!check_tsc_unstable()) - set_sched_clock_stable(); + if (check_tsc_unstable()) + clear_sched_clock_stable(); + } else { + clear_sched_clock_stable(); } /* Bit 12 of 8000_0007 edx is accumulated power mechanism. */ diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c index 1661d8ec9280..2c234a6d94c4 100644 --- a/arch/x86/kernel/cpu/centaur.c +++ b/arch/x86/kernel/cpu/centaur.c @@ -1,5 +1,5 @@ -#include <linux/bitops.h> -#include <linux/kernel.h> + +#include <linux/sched.h> #include <asm/cpufeature.h> #include <asm/e820.h> @@ -104,6 +104,8 @@ static void early_init_centaur(struct cpuinfo_x86 *c) #ifdef CONFIG_X86_64 set_cpu_cap(c, X86_FEATURE_SYSENTER32); #endif + + clear_sched_clock_stable(); } static void init_centaur(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 9bab7a8a4293..3bcf6d880611 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -83,6 +83,7 @@ static void default_init(struct cpuinfo_x86 *c) strcpy(c->x86_model_id, "386"); } #endif + clear_sched_clock_stable(); } static const struct cpu_dev default_cpu = { @@ -1015,6 +1016,7 @@ static void identify_cpu(struct cpuinfo_x86 *c) c->x86_model_id[0] = '\0'; /* Unset */ c->x86_max_cores = 1; c->x86_coreid_bits = 0; + c->cu_id = 0xff; #ifdef CONFIG_X86_64 c->x86_clflush_size = 64; c->x86_phys_bits = 36; @@ -1055,6 +1057,8 @@ static void identify_cpu(struct cpuinfo_x86 *c) */ if (this_cpu->c_init) this_cpu->c_init(c); + else + clear_sched_clock_stable(); /* Disable the PN if appropriate */ squash_the_stupid_serial_number(c); diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c index bd9dcd6b712d..47416f959a48 100644 --- a/arch/x86/kernel/cpu/cyrix.c +++ b/arch/x86/kernel/cpu/cyrix.c @@ -9,6 +9,7 @@ #include <asm/pci-direct.h> #include <asm/tsc.h> #include <asm/cpufeature.h> +#include <linux/sched.h> #include "cpu.h" @@ -183,6 +184,7 @@ static void early_init_cyrix(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_CYRIX_ARR); break; } + clear_sched_clock_stable(); } static void init_cyrix(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 203f860d2ab3..026c728d6ba7 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -119,8 +119,10 @@ static void early_init_intel(struct cpuinfo_x86 *c) if (c->x86_power & (1 << 8)) { set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC); - if (!check_tsc_unstable()) - set_sched_clock_stable(); + if (check_tsc_unstable()) + clear_sched_clock_stable(); + } else { + clear_sched_clock_stable(); } /* Penwell and Cloverview have the TSC which doesn't sleep on S3 */ diff --git a/arch/x86/kernel/cpu/mcheck/mce-apei.c b/arch/x86/kernel/cpu/mcheck/mce-apei.c index 83f1a98d37db..2eee85379689 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-apei.c +++ b/arch/x86/kernel/cpu/mcheck/mce-apei.c @@ -52,8 +52,11 @@ void apei_mce_report_mem_error(int severity, struct cper_sec_mem_err *mem_err) if (severity >= GHES_SEV_RECOVERABLE) m.status |= MCI_STATUS_UC; - if (severity >= GHES_SEV_PANIC) + + if (severity >= GHES_SEV_PANIC) { m.status |= MCI_STATUS_PCC; + m.tsc = rdtsc(); + } m.addr = mem_err->physical_addr; mce_log(&m); diff --git a/arch/x86/kernel/cpu/mcheck/mce-genpool.c b/arch/x86/kernel/cpu/mcheck/mce-genpool.c index 93d824ec3120..1e5a50c11d3c 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-genpool.c +++ b/arch/x86/kernel/cpu/mcheck/mce-genpool.c @@ -72,7 +72,7 @@ struct llist_node *mce_gen_pool_prepare_records(void) return new_head.first; } -void mce_gen_pool_process(void) +void mce_gen_pool_process(struct work_struct *__unused) { struct llist_node *head; struct mce_evt_llist *node, *tmp; diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c index 517619ea6498..99165b206df3 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-inject.c +++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c @@ -152,7 +152,6 @@ static void raise_mce(struct mce *m) if (context == MCJ_CTX_RANDOM) return; -#ifdef CONFIG_X86_LOCAL_APIC if (m->inject_flags & (MCJ_IRQ_BROADCAST | MCJ_NMI_BROADCAST)) { unsigned long start; int cpu; @@ -192,9 +191,7 @@ static void raise_mce(struct mce *m) raise_local(); put_cpu(); put_online_cpus(); - } else -#endif - { + } else { preempt_disable(); raise_local(); preempt_enable(); diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h index cd74a3f00aea..903043e6a62b 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-internal.h +++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h @@ -31,7 +31,7 @@ struct mce_evt_llist { struct mce mce; }; -void mce_gen_pool_process(void); +void mce_gen_pool_process(struct work_struct *__unused); bool mce_gen_pool_empty(void); int mce_gen_pool_add(struct mce *mce); int mce_gen_pool_init(void); diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 00ef43233e03..8e9725c607ea 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -128,7 +128,6 @@ void mce_setup(struct mce *m) { memset(m, 0, sizeof(struct mce)); m->cpu = m->extcpu = smp_processor_id(); - m->tsc = rdtsc(); /* We hope get_seconds stays lockless */ m->time = get_seconds(); m->cpuvendor = boot_cpu_data.x86_vendor; @@ -217,9 +216,7 @@ void mce_register_decode_chain(struct notifier_block *nb) { atomic_inc(&num_notifiers); - /* Ensure SRAO notifier has the highest priority in the decode chain. */ - if (nb != &mce_srao_nb && nb->priority == INT_MAX) - nb->priority -= 1; + WARN_ON(nb->priority > MCE_PRIO_LOWEST && nb->priority < MCE_PRIO_EDAC); atomic_notifier_chain_register(&x86_mce_decoder_chain, nb); } @@ -583,7 +580,7 @@ static int srao_decode_notifier(struct notifier_block *nb, unsigned long val, } static struct notifier_block mce_srao_nb = { .notifier_call = srao_decode_notifier, - .priority = INT_MAX, + .priority = MCE_PRIO_SRAO, }; static int mce_default_notifier(struct notifier_block *nb, unsigned long val, @@ -609,7 +606,7 @@ static int mce_default_notifier(struct notifier_block *nb, unsigned long val, static struct notifier_block mce_default_nb = { .notifier_call = mce_default_notifier, /* lowest prio, we want it to run last. */ - .priority = 0, + .priority = MCE_PRIO_LOWEST, }; /* @@ -710,14 +707,8 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) mce_gather_info(&m, NULL); - /* - * m.tsc was set in mce_setup(). Clear it if not requested. - * - * FIXME: Propagate @flags to mce_gather_info/mce_setup() to avoid - * that dance. - */ - if (!(flags & MCP_TIMESTAMP)) - m.tsc = 0; + if (flags & MCP_TIMESTAMP) + m.tsc = rdtsc(); for (i = 0; i < mca_cfg.banks; i++) { if (!mce_banks[i].ctl || !test_bit(i, *b)) @@ -1156,6 +1147,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) goto out; mce_gather_info(&m, regs); + m.tsc = rdtsc(); final = this_cpu_ptr(&mces_seen); *final = m; @@ -1322,41 +1314,6 @@ int memory_failure(unsigned long pfn, int vector, int flags) #endif /* - * Action optional processing happens here (picking up - * from the list of faulting pages that do_machine_check() - * placed into the genpool). - */ -static void mce_process_work(struct work_struct *dummy) -{ - mce_gen_pool_process(); -} - -#ifdef CONFIG_X86_MCE_INTEL -/*** - * mce_log_therm_throt_event - Logs the thermal throttling event to mcelog - * @cpu: The CPU on which the event occurred. - * @status: Event status information - * - * This function should be called by the thermal interrupt after the - * event has been processed and the decision was made to log the event - * further. - * - * The status parameter will be saved to the 'status' field of 'struct mce' - * and historically has been the register value of the - * MSR_IA32_THERMAL_STATUS (Intel) msr. - */ -void mce_log_therm_throt_event(__u64 status) -{ - struct mce m; - - mce_setup(&m); - m.bank = MCE_THERMAL_BANK; - m.status = status; - mce_log(&m); -} -#endif /* CONFIG_X86_MCE_INTEL */ - -/* * Periodic polling timer for "silent" machine check errors. If the * poller finds an MCE, poll 2x faster. When the poller finds no more * errors, poll 2x slower (up to check_interval seconds). @@ -1373,20 +1330,15 @@ static unsigned long mce_adjust_timer_default(unsigned long interval) static unsigned long (*mce_adjust_timer)(unsigned long interval) = mce_adjust_timer_default; -static void __restart_timer(struct timer_list *t, unsigned long interval) +static void __start_timer(struct timer_list *t, unsigned long interval) { unsigned long when = jiffies + interval; unsigned long flags; local_irq_save(flags); - if (timer_pending(t)) { - if (time_before(when, t->expires)) - mod_timer(t, when); - } else { - t->expires = round_jiffies(when); - add_timer_on(t, smp_processor_id()); - } + if (!timer_pending(t) || time_before(when, t->expires)) + mod_timer(t, round_jiffies(when)); local_irq_restore(flags); } @@ -1421,7 +1373,7 @@ static void mce_timer_fn(unsigned long data) done: __this_cpu_write(mce_next_interval, iv); - __restart_timer(t, iv); + __start_timer(t, iv); } /* @@ -1432,7 +1384,7 @@ void mce_timer_kick(unsigned long interval) struct timer_list *t = this_cpu_ptr(&mce_timer); unsigned long iv = __this_cpu_read(mce_next_interval); - __restart_timer(t, interval); + __start_timer(t, interval); if (interval < iv) __this_cpu_write(mce_next_interval, interval); @@ -1779,17 +1731,15 @@ static void __mcheck_cpu_clear_vendor(struct cpuinfo_x86 *c) } } -static void mce_start_timer(unsigned int cpu, struct timer_list *t) +static void mce_start_timer(struct timer_list *t) { unsigned long iv = check_interval * HZ; if (mca_cfg.ignore_ce || !iv) return; - per_cpu(mce_next_interval, cpu) = iv; - - t->expires = round_jiffies(jiffies + iv); - add_timer_on(t, cpu); + this_cpu_write(mce_next_interval, iv); + __start_timer(t, iv); } static void __mcheck_cpu_setup_timer(void) @@ -1806,7 +1756,7 @@ static void __mcheck_cpu_init_timer(void) unsigned int cpu = smp_processor_id(); setup_pinned_timer(t, mce_timer_fn, cpu); - mce_start_timer(cpu, t); + mce_start_timer(t); } /* Handle unconfigured int18 (should never happen) */ @@ -2196,7 +2146,7 @@ int __init mcheck_init(void) mce_register_decode_chain(&mce_default_nb); mcheck_vendor_init_severity(); - INIT_WORK(&mce_work, mce_process_work); + INIT_WORK(&mce_work, mce_gen_pool_process); init_irq_work(&mce_irq_work, mce_irq_work_cb); return 0; @@ -2566,7 +2516,7 @@ static int mce_cpu_dead(unsigned int cpu) static int mce_cpu_online(unsigned int cpu) { - struct timer_list *t = &per_cpu(mce_timer, cpu); + struct timer_list *t = this_cpu_ptr(&mce_timer); int ret; mce_device_create(cpu); @@ -2577,13 +2527,13 @@ static int mce_cpu_online(unsigned int cpu) return ret; } mce_reenable_cpu(); - mce_start_timer(cpu, t); + mce_start_timer(t); return 0; } static int mce_cpu_pre_down(unsigned int cpu) { - struct timer_list *t = &per_cpu(mce_timer, cpu); + struct timer_list *t = this_cpu_ptr(&mce_timer); mce_disable_cpu(); del_timer_sync(t); diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index a5fd137417a2..9e5427df3243 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -192,6 +192,7 @@ static void get_smca_bank_info(unsigned int bank) smca_banks[bank].hwid = s_hwid; smca_banks[bank].id = instance_id; + smca_banks[bank].sysfs_id = s_hwid->count++; break; } } @@ -777,7 +778,8 @@ __log_error(unsigned int bank, bool deferred_err, bool threshold_err, u64 misc) mce_setup(&m); m.status = status; - m.bank = bank; + m.bank = bank; + m.tsc = rdtsc(); if (threshold_err) m.misc = misc; @@ -1064,9 +1066,12 @@ static const char *get_name(unsigned int bank, struct threshold_block *b) return NULL; } + if (smca_banks[bank].hwid->count == 1) + return smca_get_name(bank_type); + snprintf(buf_mcatype, MAX_MCATYPE_NAME_LEN, "%s_%x", smca_get_name(bank_type), - smca_banks[bank].id); + smca_banks[bank].sysfs_id); return buf_mcatype; } diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index 465aca8be009..85469f84c921 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -6,7 +6,7 @@ * * Maintains a counter in /sys that keeps track of the number of thermal * events, such that the user knows how bad the thermal problem might be - * (since the logging to syslog and mcelog is rate limited). + * (since the logging to syslog is rate limited). * * Author: Dmitriy Zavin (dmitriyz@google.com) * @@ -141,13 +141,8 @@ static struct attribute_group thermal_attr_group = { * IRQ has been acknowledged. * * It will take care of rate limiting and printing messages to the syslog. - * - * Returns: 0 : Event should NOT be further logged, i.e. still in - * "timeout" from previous log message. - * 1 : Event should be logged further, and a message has been - * printed to the syslog. */ -static int therm_throt_process(bool new_event, int event, int level) +static void therm_throt_process(bool new_event, int event, int level) { struct _thermal_state *state; unsigned int this_cpu = smp_processor_id(); @@ -162,16 +157,16 @@ static int therm_throt_process(bool new_event, int event, int level) else if (event == POWER_LIMIT_EVENT) state = &pstate->core_power_limit; else - return 0; + return; } else if (level == PACKAGE_LEVEL) { if (event == THERMAL_THROTTLING_EVENT) state = &pstate->package_throttle; else if (event == POWER_LIMIT_EVENT) state = &pstate->package_power_limit; else - return 0; + return; } else - return 0; + return; old_event = state->new_event; state->new_event = new_event; @@ -181,7 +176,7 @@ static int therm_throt_process(bool new_event, int event, int level) if (time_before64(now, state->next_check) && state->count != state->last_count) - return 0; + return; state->next_check = now + CHECK_INTERVAL; state->last_count = state->count; @@ -193,16 +188,14 @@ static int therm_throt_process(bool new_event, int event, int level) this_cpu, level == CORE_LEVEL ? "Core" : "Package", state->count); - return 1; + return; } if (old_event) { if (event == THERMAL_THROTTLING_EVENT) pr_info("CPU%d: %s temperature/speed normal\n", this_cpu, level == CORE_LEVEL ? "Core" : "Package"); - return 1; + return; } - - return 0; } static int thresh_event_valid(int level, int event) @@ -365,10 +358,9 @@ static void intel_thermal_interrupt(void) /* Check for violation of core thermal thresholds*/ notify_thresholds(msr_val); - if (therm_throt_process(msr_val & THERM_STATUS_PROCHOT, - THERMAL_THROTTLING_EVENT, - CORE_LEVEL) != 0) - mce_log_therm_throt_event(msr_val); + therm_throt_process(msr_val & THERM_STATUS_PROCHOT, + THERMAL_THROTTLING_EVENT, + CORE_LEVEL); if (this_cpu_has(X86_FEATURE_PLN) && int_pln_enable) therm_throt_process(msr_val & THERM_STATUS_POWER_LIMIT, diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 6a31e2691f3a..079e81733a58 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -384,8 +384,9 @@ void load_ucode_amd_ap(unsigned int family) reget: if (!get_builtin_microcode(&cp, family)) { #ifdef CONFIG_BLK_DEV_INITRD - cp = find_cpio_data(ucode_path, (void *)initrd_start, - initrd_end - initrd_start, NULL); + if (!initrd_gone) + cp = find_cpio_data(ucode_path, (void *)initrd_start, + initrd_end - initrd_start, NULL); #endif if (!(cp.data && cp.size)) { /* diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 2af69d27da62..73102d932760 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -46,6 +46,8 @@ static struct microcode_ops *microcode_ops; static bool dis_ucode_ldr = true; +bool initrd_gone; + LIST_HEAD(microcode_cache); /* @@ -190,21 +192,24 @@ void load_ucode_ap(void) static int __init save_microcode_in_initrd(void) { struct cpuinfo_x86 *c = &boot_cpu_data; + int ret = -EINVAL; switch (c->x86_vendor) { case X86_VENDOR_INTEL: if (c->x86 >= 6) - return save_microcode_in_initrd_intel(); + ret = save_microcode_in_initrd_intel(); break; case X86_VENDOR_AMD: if (c->x86 >= 0x10) - return save_microcode_in_initrd_amd(c->x86); + ret = save_microcode_in_initrd_amd(c->x86); break; default: break; } - return -EINVAL; + initrd_gone = true; + + return ret; } struct cpio_data find_microcode_in_initrd(const char *path, bool use_pa) @@ -247,9 +252,16 @@ struct cpio_data find_microcode_in_initrd(const char *path, bool use_pa) * has the virtual address of the beginning of the initrd. It also * possibly relocates the ramdisk. In either case, initrd_start contains * the updated address so use that instead. + * + * initrd_gone is for the hotplug case where we've thrown out initrd + * already. */ - if (!use_pa && initrd_start) - start = initrd_start; + if (!use_pa) { + if (initrd_gone) + return (struct cpio_data){ NULL, 0, "" }; + if (initrd_start) + start = initrd_start; + } return find_cpio_data(path, (void *)start, size, NULL); #else /* !CONFIG_BLK_DEV_INITRD */ diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 3f329b74e040..8325d8a09ab0 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -41,7 +41,7 @@ static const char ucode_path[] = "kernel/x86/microcode/GenuineIntel.bin"; -/* Current microcode patch used in early patching */ +/* Current microcode patch used in early patching on the APs. */ struct microcode_intel *intel_ucode_patch; static inline bool cpu_signatures_match(unsigned int s1, unsigned int p1, @@ -607,12 +607,6 @@ int __init save_microcode_in_initrd_intel(void) struct ucode_cpu_info uci; struct cpio_data cp; - /* - * AP loading didn't find any microcode patch, no need to save anything. - */ - if (!intel_ucode_patch || IS_ERR(intel_ucode_patch)) - return 0; - if (!load_builtin_intel_microcode(&cp)) cp = find_microcode_in_initrd(ucode_path, false); @@ -628,7 +622,6 @@ int __init save_microcode_in_initrd_intel(void) return 0; } - /* * @res_patch, output: a pointer to the patch we found. */ diff --git a/arch/x86/kernel/cpu/transmeta.c b/arch/x86/kernel/cpu/transmeta.c index 34178564be2a..c1ea5b999839 100644 --- a/arch/x86/kernel/cpu/transmeta.c +++ b/arch/x86/kernel/cpu/transmeta.c @@ -1,4 +1,5 @@ #include <linux/kernel.h> +#include <linux/sched.h> #include <linux/mm.h> #include <asm/cpufeature.h> #include <asm/msr.h> @@ -14,6 +15,8 @@ static void early_init_transmeta(struct cpuinfo_x86 *c) if (xlvl >= 0x80860001) c->x86_capability[CPUID_8086_0001_EDX] = cpuid_edx(0x80860001); } + + clear_sched_clock_stable(); } static void init_transmeta(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 90e8dde3ec26..b2bbad6ebe4d 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -580,24 +580,19 @@ static void __init update_e820_saved(void) } #define MAX_GAP_END 0x100000000ull /* - * Search for a gap in the e820 memory space from start_addr to end_addr. + * Search for a gap in the e820 memory space from 0 to MAX_GAP_END. */ -__init int e820_search_gap(unsigned long *gapstart, unsigned long *gapsize, - unsigned long start_addr, unsigned long long end_addr) +static int __init e820_search_gap(unsigned long *gapstart, + unsigned long *gapsize) { - unsigned long long last; + unsigned long long last = MAX_GAP_END; int i = e820->nr_map; int found = 0; - last = (end_addr && end_addr < MAX_GAP_END) ? end_addr : MAX_GAP_END; - while (--i >= 0) { unsigned long long start = e820->map[i].addr; unsigned long long end = start + e820->map[i].size; - if (end < start_addr) - continue; - /* * Since "last" is at most 4GB, we know we'll * fit in 32 bits if this condition is true @@ -628,18 +623,19 @@ __init void e820_setup_gap(void) unsigned long gapstart, gapsize; int found; - gapstart = 0x10000000; gapsize = 0x400000; - found = e820_search_gap(&gapstart, &gapsize, 0, MAX_GAP_END); + found = e820_search_gap(&gapstart, &gapsize); -#ifdef CONFIG_X86_64 if (!found) { +#ifdef CONFIG_X86_64 gapstart = (max_pfn << PAGE_SHIFT) + 1024*1024; printk(KERN_ERR "e820: cannot find a gap in the 32bit address range\n" "e820: PCI devices with unassigned 32bit BARs may break!\n"); - } +#else + gapstart = 0x10000000; #endif + } /* * e820_reserve_resources_late protect stolen RAM already diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index e4e97a5355ce..de7234401275 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -9,6 +9,7 @@ #include <asm/fpu/regset.h> #include <asm/fpu/signal.h> #include <asm/fpu/types.h> +#include <asm/fpu/xstate.h> #include <asm/traps.h> #include <linux/hardirq.h> @@ -183,7 +184,8 @@ void fpstate_init(union fpregs_state *state) * it will #GP. Make sure it is replaced after the memset(). */ if (static_cpu_has(X86_FEATURE_XSAVES)) - state->xsave.header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT; + state->xsave.header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT | + xfeatures_mask; if (static_cpu_has(X86_FEATURE_FXSR)) fpstate_init_fxstate(&state->fxsave); diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index f16c55bfc090..e5fb436a6548 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -49,3 +49,65 @@ asmlinkage __visible void __init i386_start_kernel(void) start_kernel(); } + +/* + * Initialize page tables. This creates a PDE and a set of page + * tables, which are located immediately beyond __brk_base. The variable + * _brk_end is set up to point to the first "safe" location. + * Mappings are created both at virtual address 0 (identity mapping) + * and PAGE_OFFSET for up to _end. + * + * In PAE mode initial_page_table is statically defined to contain + * enough entries to cover the VMSPLIT option (that is the top 1, 2 or 3 + * entries). The identity mapping is handled by pointing two PGD entries + * to the first kernel PMD. Note the upper half of each PMD or PTE are + * always zero at this stage. + */ +void __init mk_early_pgtbl_32(void) +{ +#ifdef __pa +#undef __pa +#endif +#define __pa(x) ((unsigned long)(x) - PAGE_OFFSET) + pte_t pte, *ptep; + int i; + unsigned long *ptr; + /* Enough space to fit pagetables for the low memory linear map */ + const unsigned long limit = __pa(_end) + + (PAGE_TABLE_SIZE(LOWMEM_PAGES) << PAGE_SHIFT); +#ifdef CONFIG_X86_PAE + pmd_t pl2, *pl2p = (pmd_t *)__pa(initial_pg_pmd); +#define SET_PL2(pl2, val) { (pl2).pmd = (val); } +#else + pgd_t pl2, *pl2p = (pgd_t *)__pa(initial_page_table); +#define SET_PL2(pl2, val) { (pl2).pgd = (val); } +#endif + + ptep = (pte_t *)__pa(__brk_base); + pte.pte = PTE_IDENT_ATTR; + + while ((pte.pte & PTE_PFN_MASK) < limit) { + + SET_PL2(pl2, (unsigned long)ptep | PDE_IDENT_ATTR); + *pl2p = pl2; +#ifndef CONFIG_X86_PAE + /* Kernel PDE entry */ + *(pl2p + ((PAGE_OFFSET >> PGDIR_SHIFT))) = pl2; +#endif + for (i = 0; i < PTRS_PER_PTE; i++) { + *ptep = pte; + pte.pte += PAGE_SIZE; + ptep++; + } + + pl2p++; + } + + ptr = (unsigned long *)__pa(&max_pfn_mapped); + /* Can't use pte_pfn() since it's a call with CONFIG_PARAVIRT */ + *ptr = (pte.pte & PTE_PFN_MASK) >> PAGE_SHIFT; + + ptr = (unsigned long *)__pa(&_brk_end); + *ptr = (unsigned long)ptep + PAGE_OFFSET; +} + diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 4e8577d03372..1f85ee8f9439 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -24,6 +24,7 @@ #include <asm/nops.h> #include <asm/bootparam.h> #include <asm/export.h> +#include <asm/pgtable_32.h> /* Physical address */ #define pa(X) ((X) - __PAGE_OFFSET) @@ -41,44 +42,10 @@ #define X86_CAPABILITY new_cpu_data+CPUINFO_x86_capability #define X86_VENDOR_ID new_cpu_data+CPUINFO_x86_vendor_id -/* - * This is how much memory in addition to the memory covered up to - * and including _end we need mapped initially. - * We need: - * (KERNEL_IMAGE_SIZE/4096) / 1024 pages (worst case, non PAE) - * (KERNEL_IMAGE_SIZE/4096) / 512 + 4 pages (worst case for PAE) - * - * Modulo rounding, each megabyte assigned here requires a kilobyte of - * memory, which is currently unreclaimed. - * - * This should be a multiple of a page. - * - * KERNEL_IMAGE_SIZE should be greater than pa(_end) - * and small than max_low_pfn, otherwise will waste some page table entries - */ - -#if PTRS_PER_PMD > 1 -#define PAGE_TABLE_SIZE(pages) (((pages) / PTRS_PER_PMD) + PTRS_PER_PGD) -#else -#define PAGE_TABLE_SIZE(pages) ((pages) / PTRS_PER_PGD) -#endif #define SIZEOF_PTREGS 17*4 /* - * Number of possible pages in the lowmem region. - * - * We shift 2 by 31 instead of 1 by 32 to the left in order to avoid a - * gas warning about overflowing shift count when gas has been compiled - * with only a host target support using a 32-bit type for internal - * representation. - */ -LOWMEM_PAGES = (((2<<31) - __PAGE_OFFSET) >> PAGE_SHIFT) - -/* Enough space to fit pagetables for the low memory linear map */ -MAPPING_BEYOND_END = PAGE_TABLE_SIZE(LOWMEM_PAGES) << PAGE_SHIFT - -/* * Worst-case size of the kernel mapping we need to make: * a relocatable kernel can live anywhere in lowmem, so we need to be able * to map all of lowmem. @@ -160,90 +127,15 @@ ENTRY(startup_32) call load_ucode_bsp #endif -/* - * Initialize page tables. This creates a PDE and a set of page - * tables, which are located immediately beyond __brk_base. The variable - * _brk_end is set up to point to the first "safe" location. - * Mappings are created both at virtual address 0 (identity mapping) - * and PAGE_OFFSET for up to _end. - */ -#ifdef CONFIG_X86_PAE - - /* - * In PAE mode initial_page_table is statically defined to contain - * enough entries to cover the VMSPLIT option (that is the top 1, 2 or 3 - * entries). The identity mapping is handled by pointing two PGD entries - * to the first kernel PMD. - * - * Note the upper half of each PMD or PTE are always zero at this stage. - */ - -#define KPMDS (((-__PAGE_OFFSET) >> 30) & 3) /* Number of kernel PMDs */ - - xorl %ebx,%ebx /* %ebx is kept at zero */ - - movl $pa(__brk_base), %edi - movl $pa(initial_pg_pmd), %edx - movl $PTE_IDENT_ATTR, %eax -10: - leal PDE_IDENT_ATTR(%edi),%ecx /* Create PMD entry */ - movl %ecx,(%edx) /* Store PMD entry */ - /* Upper half already zero */ - addl $8,%edx - movl $512,%ecx -11: - stosl - xchgl %eax,%ebx - stosl - xchgl %eax,%ebx - addl $0x1000,%eax - loop 11b - - /* - * End condition: we must map up to the end + MAPPING_BEYOND_END. - */ - movl $pa(_end) + MAPPING_BEYOND_END + PTE_IDENT_ATTR, %ebp - cmpl %ebp,%eax - jb 10b -1: - addl $__PAGE_OFFSET, %edi - movl %edi, pa(_brk_end) - shrl $12, %eax - movl %eax, pa(max_pfn_mapped) + /* Create early pagetables. */ + call mk_early_pgtbl_32 /* Do early initialization of the fixmap area */ movl $pa(initial_pg_fixmap)+PDE_IDENT_ATTR,%eax +#ifdef CONFIG_X86_PAE +#define KPMDS (((-__PAGE_OFFSET) >> 30) & 3) /* Number of kernel PMDs */ movl %eax,pa(initial_pg_pmd+0x1000*KPMDS-8) -#else /* Not PAE */ - -page_pde_offset = (__PAGE_OFFSET >> 20); - - movl $pa(__brk_base), %edi - movl $pa(initial_page_table), %edx - movl $PTE_IDENT_ATTR, %eax -10: - leal PDE_IDENT_ATTR(%edi),%ecx /* Create PDE entry */ - movl %ecx,(%edx) /* Store identity PDE entry */ - movl %ecx,page_pde_offset(%edx) /* Store kernel PDE entry */ - addl $4,%edx - movl $1024, %ecx -11: - stosl - addl $0x1000,%eax - loop 11b - /* - * End condition: we must map up to the end + MAPPING_BEYOND_END. - */ - movl $pa(_end) + MAPPING_BEYOND_END + PTE_IDENT_ATTR, %ebp - cmpl %ebp,%eax - jb 10b - addl $__PAGE_OFFSET, %edi - movl %edi, pa(_brk_end) - shrl $12, %eax - movl %eax, pa(max_pfn_mapped) - - /* Do early initialization of the fixmap area */ - movl $pa(initial_pg_fixmap)+PDE_IDENT_ATTR,%eax +#else movl %eax,pa(initial_page_table+0xffc) #endif @@ -666,6 +558,7 @@ ENTRY(setup_once_ref) __PAGE_ALIGNED_BSS .align PAGE_SIZE #ifdef CONFIG_X86_PAE +.globl initial_pg_pmd initial_pg_pmd: .fill 1024*KPMDS,4,0 #else diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 85e87b46c318..dc6ba5bda9fc 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -352,6 +352,7 @@ static int hpet_resume(struct clock_event_device *evt, int timer) } else { struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt); + irq_domain_deactivate_irq(irq_get_irq_data(hdev->irq)); irq_domain_activate_irq(irq_get_irq_data(hdev->irq)); disable_irq(hdev->irq); irq_set_affinity(hdev->irq, cpumask_of(hdev->cpu)); diff --git a/arch/x86/kernel/itmt.c b/arch/x86/kernel/itmt.c index cb9c1ed1d391..f73f475d0573 100644 --- a/arch/x86/kernel/itmt.c +++ b/arch/x86/kernel/itmt.c @@ -132,10 +132,8 @@ int sched_set_itmt_support(void) sysctl_sched_itmt_enabled = 1; - if (sysctl_sched_itmt_enabled) { - x86_topology_update = true; - rebuild_sched_domains(); - } + x86_topology_update = true; + rebuild_sched_domains(); mutex_unlock(&itmt_update_mutex); diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c index fc25f698d792..c37bd0f39c70 100644 --- a/arch/x86/kernel/jump_label.c +++ b/arch/x86/kernel/jump_label.c @@ -32,8 +32,7 @@ static void bug_at(unsigned char *ip, int line) * Something went wrong. Crash the box, as something could be * corrupting the kernel. */ - pr_warning("Unexpected op at %pS [%p] (%02x %02x %02x %02x %02x) %s:%d\n", - ip, ip, ip[0], ip[1], ip[2], ip[3], ip[4], __FILE__, line); + pr_crit("jump_label: Fatal kernel bug, unexpected op at %pS [%p] (%5ph) %d\n", ip, ip, ip, line); BUG(); } diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index eb3509338ae0..520b8dfe1640 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -745,7 +745,7 @@ __visible __used void *trampoline_handler(struct pt_regs *regs) * will be the real return address, and all the rest will * point to kretprobe_trampoline. */ - hlist_for_each_entry_safe(ri, tmp, head, hlist) { + hlist_for_each_entry(ri, head, hlist) { if (ri->task != current) /* another task is sharing our hash bucket */ continue; diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 36bc66416021..099fcba4981d 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -620,18 +620,4 @@ void __init kvm_spinlock_init(void) } } -static __init int kvm_spinlock_init_jump(void) -{ - if (!kvm_para_available()) - return 0; - if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT)) - return 0; - - static_key_slow_inc(¶virt_ticketlocks_enabled); - printk(KERN_INFO "KVM setup paravirtual spinlock\n"); - - return 0; -} -early_initcall(kvm_spinlock_init_jump); - #endif /* CONFIG_PARAVIRT_SPINLOCKS */ diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 2a5cafdf8808..542710b99f52 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -107,12 +107,12 @@ static inline void kvm_sched_clock_init(bool stable) { if (!stable) { pv_time_ops.sched_clock = kvm_clock_read; + clear_sched_clock_stable(); return; } kvm_sched_clock_offset = kvm_clock_read(); pv_time_ops.sched_clock = kvm_sched_clock_read; - set_sched_clock_stable(); printk(KERN_INFO "kvm-clock: using sched offset of %llu cycles\n", kvm_sched_clock_offset); diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c index 6d4bf812af45..6259327f3454 100644 --- a/arch/x86/kernel/paravirt-spinlocks.c +++ b/arch/x86/kernel/paravirt-spinlocks.c @@ -42,6 +42,3 @@ struct pv_lock_ops pv_lock_ops = { #endif /* SMP */ }; EXPORT_SYMBOL(pv_lock_ops); - -struct static_key paravirt_ticketlocks_enabled = STATIC_KEY_INIT_FALSE; -EXPORT_SYMBOL(paravirt_ticketlocks_enabled); diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 4cfba947d774..69780edf0dde 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1176,6 +1176,20 @@ void __init setup_arch(char **cmdline_p) /* Allocate bigger log buffer */ setup_log_buf(1); + if (efi_enabled(EFI_BOOT)) { + switch (boot_params.secure_boot) { + case efi_secureboot_mode_disabled: + pr_info("Secure boot disabled\n"); + break; + case efi_secureboot_mode_enabled: + pr_info("Secure boot enabled\n"); + break; + default: + pr_info("Secure boot could not be determined\n"); + break; + } + } + reserve_initrd(); acpi_table_upgrade(); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 46732dc3b73c..99b920d0e516 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -433,9 +433,15 @@ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) int cpu1 = c->cpu_index, cpu2 = o->cpu_index; if (c->phys_proc_id == o->phys_proc_id && - per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2) && - c->cpu_core_id == o->cpu_core_id) - return topology_sane(c, o, "smt"); + per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2)) { + if (c->cpu_core_id == o->cpu_core_id) + return topology_sane(c, o, "smt"); + + if ((c->cu_id != 0xff) && + (o->cu_id != 0xff) && + (c->cu_id == o->cu_id)) + return topology_sane(c, o, "smt"); + } } else if (c->phys_proc_id == o->phys_proc_id && c->cpu_core_id == o->cpu_core_id) { diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index e41af597aed8..2724dc82f992 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -1107,6 +1107,16 @@ static u64 read_tsc(struct clocksource *cs) return (u64)rdtsc_ordered(); } +static void tsc_cs_mark_unstable(struct clocksource *cs) +{ + if (tsc_unstable) + return; + tsc_unstable = 1; + clear_sched_clock_stable(); + disable_sched_clock_irqtime(); + pr_info("Marking TSC unstable due to clocksource watchdog\n"); +} + /* * .mask MUST be CLOCKSOURCE_MASK(64). See comment above read_tsc() */ @@ -1119,6 +1129,7 @@ static struct clocksource clocksource_tsc = { CLOCK_SOURCE_MUST_VERIFY, .archdata = { .vclock_mode = VCLOCK_TSC }, .resume = tsc_resume, + .mark_unstable = tsc_cs_mark_unstable, }; void mark_tsc_unstable(char *reason) @@ -1356,6 +1367,9 @@ void __init tsc_init(void) (unsigned long)cpu_khz / 1000, (unsigned long)cpu_khz % 1000); + /* Sanitize TSC ADJUST before cyc2ns gets initialized */ + tsc_store_and_check_tsc_adjust(true); + /* * Secondary CPUs do not run through tsc_init(), so set up * all the scale factors for all CPUs, assuming the same @@ -1386,8 +1400,6 @@ void __init tsc_init(void) if (unsynchronized_tsc()) mark_tsc_unstable("TSCs unsynchronized"); - else - tsc_store_and_check_tsc_adjust(true); check_system_tsc_reliable(); diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c index d0db011051a5..728f75378475 100644 --- a/arch/x86/kernel/tsc_sync.c +++ b/arch/x86/kernel/tsc_sync.c @@ -286,13 +286,6 @@ void check_tsc_sync_source(int cpu) if (unsynchronized_tsc()) return; - if (tsc_clocksource_reliable) { - if (cpu == (nr_cpu_ids-1) || system_state != SYSTEM_BOOTING) - pr_info( - "Skipped synchronization checks as TSC is reliable.\n"); - return; - } - /* * Set the maximum number of test runs to * 1 if the CPU does not provide the TSC_ADJUST MSR @@ -380,14 +373,19 @@ void check_tsc_sync_target(void) int cpus = 2; /* Also aborts if there is no TSC. */ - if (unsynchronized_tsc() || tsc_clocksource_reliable) + if (unsynchronized_tsc()) return; /* * Store, verify and sanitize the TSC adjust register. If * successful skip the test. + * + * The test is also skipped when the TSC is marked reliable. This + * is true for SoCs which have no fallback clocksource. On these + * SoCs the TSC is frequency synchronized, but still the TSC ADJUST + * register might have been wreckaged by the BIOS.. */ - if (tsc_store_and_check_tsc_adjust(false)) { + if (tsc_store_and_check_tsc_adjust(false) || tsc_clocksource_reliable) { atomic_inc(&skip_test); return; } diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index ec5d7545e6dc..0442d98367ae 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -160,11 +160,12 @@ void save_v86_state(struct kernel_vm86_regs *regs, int retval) static void mark_screen_rdonly(struct mm_struct *mm) { + struct vm_area_struct *vma; + spinlock_t *ptl; pgd_t *pgd; pud_t *pud; pmd_t *pmd; pte_t *pte; - spinlock_t *ptl; int i; down_write(&mm->mmap_sem); @@ -177,7 +178,7 @@ static void mark_screen_rdonly(struct mm_struct *mm) pmd = pmd_offset(pud, 0xA0000); if (pmd_trans_huge(*pmd)) { - struct vm_area_struct *vma = find_vma(mm, 0xA0000); + vma = find_vma(mm, 0xA0000); split_huge_pmd(vma, pmd, 0xA0000); } if (pmd_none_or_clear_bad(pmd)) diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 1572c35b4f1a..2ecd7dab4631 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -964,10 +964,11 @@ static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data, /* Calculate cpu time spent by current task in 100ns units */ static u64 current_task_runtime_100ns(void) { - cputime_t utime, stime; + u64 utime, stime; task_cputime_adjusted(current, &utime, &stime); - return div_u64(cputime_to_nsecs(utime + stime), 100); + + return div_u64(utime + stime, 100); } static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index d153be8929a6..e52c9088660f 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3182,6 +3182,7 @@ static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu) memcpy(dest, xsave, XSAVE_HDR_OFFSET); /* Set XSTATE_BV */ + xstate_bv &= vcpu->arch.guest_supported_xcr0 | XFEATURE_MASK_FPSSE; *(u64 *)(dest + XSAVE_HDR_OFFSET) = xstate_bv; /* diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c index 073d1f1a620b..a8e91ae89fb3 100644 --- a/arch/x86/lib/delay.c +++ b/arch/x86/lib/delay.c @@ -156,13 +156,13 @@ EXPORT_SYMBOL(__delay); inline void __const_udelay(unsigned long xloops) { + unsigned long lpj = this_cpu_read(cpu_info.loops_per_jiffy) ? : loops_per_jiffy; int d0; xloops *= 4; asm("mull %%edx" :"=d" (xloops), "=&a" (d0) - :"1" (xloops), "0" - (this_cpu_read(cpu_info.loops_per_jiffy) * (HZ/4))); + :"1" (xloops), "0" (lpj * (HZ / 4))); __delay(++xloops); } diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index ea9c49adaa1f..8aa6bea1cd6c 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -15,6 +15,7 @@ #include <linux/debugfs.h> #include <linux/mm.h> #include <linux/init.h> +#include <linux/sched.h> #include <linux/seq_file.h> #include <asm/pgtable.h> @@ -406,6 +407,7 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd, } else note_page(m, &st, __pgprot(0), 1); + cond_resched(); start++; } diff --git a/arch/x86/platform/efi/efi-bgrt.c b/arch/x86/platform/efi/efi-bgrt.c index 6aad870e8962..04ca8764f0c0 100644 --- a/arch/x86/platform/efi/efi-bgrt.c +++ b/arch/x86/platform/efi/efi-bgrt.c @@ -19,8 +19,7 @@ #include <linux/efi.h> #include <linux/efi-bgrt.h> -struct acpi_table_bgrt *bgrt_tab; -void *__initdata bgrt_image; +struct acpi_table_bgrt bgrt_tab; size_t __initdata bgrt_image_size; struct bmp_header { @@ -28,66 +27,58 @@ struct bmp_header { u32 size; } __packed; -void __init efi_bgrt_init(void) +void __init efi_bgrt_init(struct acpi_table_header *table) { - acpi_status status; void *image; struct bmp_header bmp_header; + struct acpi_table_bgrt *bgrt = &bgrt_tab; if (acpi_disabled) return; - status = acpi_get_table("BGRT", 0, - (struct acpi_table_header **)&bgrt_tab); - if (ACPI_FAILURE(status)) - return; - - if (bgrt_tab->header.length < sizeof(*bgrt_tab)) { + if (table->length < sizeof(bgrt_tab)) { pr_notice("Ignoring BGRT: invalid length %u (expected %zu)\n", - bgrt_tab->header.length, sizeof(*bgrt_tab)); + table->length, sizeof(bgrt_tab)); return; } - if (bgrt_tab->version != 1) { + *bgrt = *(struct acpi_table_bgrt *)table; + if (bgrt->version != 1) { pr_notice("Ignoring BGRT: invalid version %u (expected 1)\n", - bgrt_tab->version); - return; + bgrt->version); + goto out; } - if (bgrt_tab->status & 0xfe) { + if (bgrt->status & 0xfe) { pr_notice("Ignoring BGRT: reserved status bits are non-zero %u\n", - bgrt_tab->status); - return; + bgrt->status); + goto out; } - if (bgrt_tab->image_type != 0) { + if (bgrt->image_type != 0) { pr_notice("Ignoring BGRT: invalid image type %u (expected 0)\n", - bgrt_tab->image_type); - return; + bgrt->image_type); + goto out; } - if (!bgrt_tab->image_address) { + if (!bgrt->image_address) { pr_notice("Ignoring BGRT: null image address\n"); - return; + goto out; } - image = memremap(bgrt_tab->image_address, sizeof(bmp_header), MEMREMAP_WB); + image = early_memremap(bgrt->image_address, sizeof(bmp_header)); if (!image) { pr_notice("Ignoring BGRT: failed to map image header memory\n"); - return; + goto out; } memcpy(&bmp_header, image, sizeof(bmp_header)); - memunmap(image); + early_memunmap(image, sizeof(bmp_header)); if (bmp_header.id != 0x4d42) { pr_notice("Ignoring BGRT: Incorrect BMP magic number 0x%x (expected 0x4d42)\n", bmp_header.id); - return; + goto out; } bgrt_image_size = bmp_header.size; + efi_mem_reserve(bgrt->image_address, bgrt_image_size); - bgrt_image = memremap(bgrt_tab->image_address, bmp_header.size, MEMREMAP_WB); - if (!bgrt_image) { - pr_notice("Ignoring BGRT: failed to map image memory\n"); - bgrt_image = NULL; - return; - } - - efi_mem_reserve(bgrt_tab->image_address, bgrt_image_size); + return; +out: + memset(bgrt, 0, sizeof(bgrt_tab)); } diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 274dfc481849..565dff3c9a12 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -542,11 +542,6 @@ void __init efi_init(void) efi_print_memmap(); } -void __init efi_late_init(void) -{ - efi_bgrt_init(); -} - void __init efi_set_executable(efi_memory_desc_t *md, bool executable) { u64 addr, npages; @@ -960,6 +955,11 @@ static void __init __efi_enter_virtual_mode(void) return; } + if (efi_enabled(EFI_DBG)) { + pr_info("EFI runtime memory map:\n"); + efi_print_memmap(); + } + BUG_ON(!efi.systab); if (efi_setup_page_tables(pa, 1 << pg_shift)) { diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 319148bd4b05..a4695da42d77 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -269,6 +269,22 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) efi_scratch.use_pgd = true; /* + * Certain firmware versions are way too sentimential and still believe + * they are exclusive and unquestionable owners of the first physical page, + * even though they explicitly mark it as EFI_CONVENTIONAL_MEMORY + * (but then write-access it later during SetVirtualAddressMap()). + * + * Create a 1:1 mapping for this page, to avoid triple faults during early + * boot with such firmware. We are free to hand this page to the BIOS, + * as trim_bios_range() will reserve the first page and isolate it away + * from memory allocators anyway. + */ + if (kernel_map_pages_in_pgd(pgd, 0x0, 0x0, 1, _PAGE_RW)) { + pr_err("Failed to create 1:1 mapping for the first page!\n"); + return 1; + } + + /* * When making calls to the firmware everything needs to be 1:1 * mapped and addressable with 32-bit pointers. Map the kernel * text and allocate a new stack because we can't rely on the @@ -398,10 +414,44 @@ void __init parse_efi_setup(u64 phys_addr, u32 data_len) efi_setup = phys_addr + sizeof(struct setup_data); } -void __init efi_runtime_update_mappings(void) +static int __init efi_update_mappings(efi_memory_desc_t *md, unsigned long pf) { unsigned long pfn; pgd_t *pgd = efi_pgd; + int err1, err2; + + /* Update the 1:1 mapping */ + pfn = md->phys_addr >> PAGE_SHIFT; + err1 = kernel_map_pages_in_pgd(pgd, pfn, md->phys_addr, md->num_pages, pf); + if (err1) { + pr_err("Error while updating 1:1 mapping PA 0x%llx -> VA 0x%llx!\n", + md->phys_addr, md->virt_addr); + } + + err2 = kernel_map_pages_in_pgd(pgd, pfn, md->virt_addr, md->num_pages, pf); + if (err2) { + pr_err("Error while updating VA mapping PA 0x%llx -> VA 0x%llx!\n", + md->phys_addr, md->virt_addr); + } + + return err1 || err2; +} + +static int __init efi_update_mem_attr(struct mm_struct *mm, efi_memory_desc_t *md) +{ + unsigned long pf = 0; + + if (md->attribute & EFI_MEMORY_XP) + pf |= _PAGE_NX; + + if (!(md->attribute & EFI_MEMORY_RO)) + pf |= _PAGE_RW; + + return efi_update_mappings(md, pf); +} + +void __init efi_runtime_update_mappings(void) +{ efi_memory_desc_t *md; if (efi_enabled(EFI_OLD_MEMMAP)) { @@ -410,6 +460,24 @@ void __init efi_runtime_update_mappings(void) return; } + /* + * Use the EFI Memory Attribute Table for mapping permissions if it + * exists, since it is intended to supersede EFI_PROPERTIES_TABLE. + */ + if (efi_enabled(EFI_MEM_ATTR)) { + efi_memattr_apply_permissions(NULL, efi_update_mem_attr); + return; + } + + /* + * EFI_MEMORY_ATTRIBUTES_TABLE is intended to replace + * EFI_PROPERTIES_TABLE. So, use EFI_PROPERTIES_TABLE to update + * permissions only if EFI_MEMORY_ATTRIBUTES_TABLE is not + * published by the firmware. Even if we find a buggy implementation of + * EFI_MEMORY_ATTRIBUTES_TABLE, don't fall back to + * EFI_PROPERTIES_TABLE, because of the same reason. + */ + if (!efi_enabled(EFI_NX_PE_DATA)) return; @@ -430,15 +498,7 @@ void __init efi_runtime_update_mappings(void) (md->type != EFI_RUNTIME_SERVICES_CODE)) pf |= _PAGE_RW; - /* Update the 1:1 mapping */ - pfn = md->phys_addr >> PAGE_SHIFT; - if (kernel_map_pages_in_pgd(pgd, pfn, md->phys_addr, md->num_pages, pf)) - pr_warn("Error mapping PA 0x%llx -> VA 0x%llx!\n", - md->phys_addr, md->virt_addr); - - if (kernel_map_pages_in_pgd(pgd, pfn, md->virt_addr, md->num_pages, pf)) - pr_warn("Error mapping PA 0x%llx -> VA 0x%llx!\n", - md->phys_addr, md->virt_addr); + efi_update_mappings(md, pf); } } diff --git a/arch/x86/ras/Kconfig b/arch/x86/ras/Kconfig index d957d5f21a86..0bc60a308730 100644 --- a/arch/x86/ras/Kconfig +++ b/arch/x86/ras/Kconfig @@ -1,6 +1,6 @@ config MCE_AMD_INJ tristate "Simple MCE injection interface for AMD processors" - depends on RAS && EDAC_DECODE_MCE && DEBUG_FS && AMD_NB + depends on RAS && X86_MCE && DEBUG_FS && AMD_NB default n help This is a simple debugfs interface to inject MCEs and test different diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c index e8a9ea7d7a21..25a7c4302ce7 100644 --- a/arch/x86/xen/spinlock.c +++ b/arch/x86/xen/spinlock.c @@ -141,25 +141,6 @@ void __init xen_init_spinlocks(void) pv_lock_ops.vcpu_is_preempted = PV_CALLEE_SAVE(xen_vcpu_stolen); } -/* - * While the jump_label init code needs to happend _after_ the jump labels are - * enabled and before SMP is started. Hence we use pre-SMP initcall level - * init. We cannot do it in xen_init_spinlocks as that is done before - * jump labels are activated. - */ -static __init int xen_init_spinlocks_jump(void) -{ - if (!xen_pvspin) - return 0; - - if (!xen_domain()) - return 0; - - static_key_slow_inc(¶virt_ticketlocks_enabled); - return 0; -} -early_initcall(xen_init_spinlocks_jump); - static __init int xen_parse_nopvspin(char *arg) { xen_pvspin = false; diff --git a/arch/xtensa/include/asm/Kbuild b/arch/xtensa/include/asm/Kbuild index b7fbaa56b51a..9e9760b20be5 100644 --- a/arch/xtensa/include/asm/Kbuild +++ b/arch/xtensa/include/asm/Kbuild @@ -1,7 +1,6 @@ generic-y += bitsperlong.h generic-y += bug.h generic-y += clkdev.h -generic-y += cputime.h generic-y += div64.h generic-y += dma-contiguous.h generic-y += emergency-restart.h diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c index 848e8568fb3c..8fd4be610607 100644 --- a/arch/xtensa/kernel/setup.c +++ b/arch/xtensa/kernel/setup.c @@ -419,7 +419,7 @@ subsys_initcall(topology_init); void cpu_reset(void) { -#if XCHAL_HAVE_PTP_MMU +#if XCHAL_HAVE_PTP_MMU && IS_ENABLED(CONFIG_MMU) local_irq_disable(); /* * We have full MMU: all autoload ways, ways 7, 8 and 9 of DTLB must |