diff options
Diffstat (limited to 'arch')
219 files changed, 5408 insertions, 4299 deletions
diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c index 9d0ac091a52a..4a905bd667e2 100644 --- a/arch/alpha/mm/fault.c +++ b/arch/alpha/mm/fault.c @@ -23,8 +23,7 @@ #include <linux/smp.h> #include <linux/interrupt.h> #include <linux/module.h> - -#include <asm/uaccess.h> +#include <linux/uaccess.h> extern void die_if_kernel(char *,struct pt_regs *,long, unsigned long *); @@ -107,7 +106,7 @@ do_page_fault(unsigned long address, unsigned long mmcsr, /* If we're in an interrupt context, or have no user context, we must not take the fault. */ - if (!mm || in_atomic()) + if (!mm || faulthandler_disabled()) goto no_context; #ifdef CONFIG_ALPHA_LARGE_VMALLOC diff --git a/arch/arc/include/asm/futex.h b/arch/arc/include/asm/futex.h index 4dc64ddebece..05b5aaf5b0f9 100644 --- a/arch/arc/include/asm/futex.h +++ b/arch/arc/include/asm/futex.h @@ -53,7 +53,7 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr) if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int))) return -EFAULT; - pagefault_disable(); /* implies preempt_disable() */ + pagefault_disable(); switch (op) { case FUTEX_OP_SET: @@ -75,7 +75,7 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr) ret = -ENOSYS; } - pagefault_enable(); /* subsumes preempt_enable() */ + pagefault_enable(); if (!ret) { switch (cmp) { @@ -104,7 +104,7 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr) return ret; } -/* Compare-xchg with preemption disabled. +/* Compare-xchg with pagefaults disabled. * Notes: * -Best-Effort: Exchg happens only if compare succeeds. * If compare fails, returns; leaving retry/looping to upper layers @@ -121,7 +121,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval, if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int))) return -EFAULT; - pagefault_disable(); /* implies preempt_disable() */ + pagefault_disable(); /* TBD : can use llock/scond */ __asm__ __volatile__( @@ -142,7 +142,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval, : "r"(oldval), "r"(newval), "r"(uaddr), "ir"(-EFAULT) : "cc", "memory"); - pagefault_enable(); /* subsumes preempt_enable() */ + pagefault_enable(); *uval = val; return val; diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c index 6a2e006cbcce..d948e4e9d89c 100644 --- a/arch/arc/mm/fault.c +++ b/arch/arc/mm/fault.c @@ -86,7 +86,7 @@ void do_page_fault(unsigned long address, struct pt_regs *regs) * If we're in an interrupt or have no user * context, we must not take the fault.. */ - if (in_atomic() || !mm) + if (faulthandler_disabled() || !mm) goto no_context; if (user_mode(regs)) diff --git a/arch/arm/boot/dts/am335x-bone-common.dtsi b/arch/arm/boot/dts/am335x-bone-common.dtsi index c3255e0c90aa..dbb3f4d2bf84 100644 --- a/arch/arm/boot/dts/am335x-bone-common.dtsi +++ b/arch/arm/boot/dts/am335x-bone-common.dtsi @@ -223,6 +223,25 @@ /include/ "tps65217.dtsi" &tps { + /* + * Configure pmic to enter OFF-state instead of SLEEP-state ("RTC-only + * mode") at poweroff. Most BeagleBone versions do not support RTC-only + * mode and risk hardware damage if this mode is entered. + * + * For details, see linux-omap mailing list May 2015 thread + * [PATCH] ARM: dts: am335x-bone* enable pmic-shutdown-controller + * In particular, messages: + * http://www.spinics.net/lists/linux-omap/msg118585.html + * http://www.spinics.net/lists/linux-omap/msg118615.html + * + * You can override this later with + * &tps { /delete-property/ ti,pmic-shutdown-controller; } + * if you want to use RTC-only mode and made sure you are not affected + * by the hardware problems. (Tip: double-check by performing a current + * measurement after shutdown: it should be less than 1 mA.) + */ + ti,pmic-shutdown-controller; + regulators { dcdc1_reg: regulator@0 { regulator-name = "vdds_dpr"; diff --git a/arch/arm/boot/dts/am35xx-clocks.dtsi b/arch/arm/boot/dts/am35xx-clocks.dtsi index 518b8fde88b0..18cc826e9db5 100644 --- a/arch/arm/boot/dts/am35xx-clocks.dtsi +++ b/arch/arm/boot/dts/am35xx-clocks.dtsi @@ -12,7 +12,7 @@ #clock-cells = <0>; compatible = "ti,am35xx-gate-clock"; clocks = <&ipss_ick>; - reg = <0x059c>; + reg = <0x032c>; ti,bit-shift = <1>; }; @@ -20,7 +20,7 @@ #clock-cells = <0>; compatible = "ti,gate-clock"; clocks = <&rmii_ck>; - reg = <0x059c>; + reg = <0x032c>; ti,bit-shift = <9>; }; @@ -28,7 +28,7 @@ #clock-cells = <0>; compatible = "ti,am35xx-gate-clock"; clocks = <&ipss_ick>; - reg = <0x059c>; + reg = <0x032c>; ti,bit-shift = <2>; }; @@ -36,7 +36,7 @@ #clock-cells = <0>; compatible = "ti,gate-clock"; clocks = <&pclk_ck>; - reg = <0x059c>; + reg = <0x032c>; ti,bit-shift = <10>; }; @@ -44,7 +44,7 @@ #clock-cells = <0>; compatible = "ti,am35xx-gate-clock"; clocks = <&ipss_ick>; - reg = <0x059c>; + reg = <0x032c>; ti,bit-shift = <0>; }; @@ -52,7 +52,7 @@ #clock-cells = <0>; compatible = "ti,gate-clock"; clocks = <&sys_ck>; - reg = <0x059c>; + reg = <0x032c>; ti,bit-shift = <8>; }; @@ -60,7 +60,7 @@ #clock-cells = <0>; compatible = "ti,am35xx-gate-clock"; clocks = <&sys_ck>; - reg = <0x059c>; + reg = <0x032c>; ti,bit-shift = <3>; }; }; diff --git a/arch/arm/boot/dts/armada-xp-linksys-mamba.dts b/arch/arm/boot/dts/armada-xp-linksys-mamba.dts index a2cf2154dcdb..fdd187c55aa5 100644 --- a/arch/arm/boot/dts/armada-xp-linksys-mamba.dts +++ b/arch/arm/boot/dts/armada-xp-linksys-mamba.dts @@ -95,6 +95,11 @@ internal-regs { + rtc@10300 { + /* No crystal connected to the internal RTC */ + status = "disabled"; + }; + /* J10: VCC, NC, RX, NC, TX, GND */ serial@12000 { status = "okay"; diff --git a/arch/arm/boot/dts/dm816x.dtsi b/arch/arm/boot/dts/dm816x.dtsi index de8427be830a..289806adb343 100644 --- a/arch/arm/boot/dts/dm816x.dtsi +++ b/arch/arm/boot/dts/dm816x.dtsi @@ -382,7 +382,7 @@ ti,hwmods = "usb_otg_hs"; usb0: usb@47401000 { - compatible = "ti,musb-am33xx"; + compatible = "ti,musb-dm816"; reg = <0x47401400 0x400 0x47401000 0x200>; reg-names = "mc", "control"; @@ -422,7 +422,7 @@ }; usb1: usb@47401800 { - compatible = "ti,musb-am33xx"; + compatible = "ti,musb-dm816"; reg = <0x47401c00 0x400 0x47401800 0x200>; reg-names = "mc", "control"; diff --git a/arch/arm/boot/dts/omap3-n900.dts b/arch/arm/boot/dts/omap3-n900.dts index 5c16145920ea..5f5e0f3d5b64 100644 --- a/arch/arm/boot/dts/omap3-n900.dts +++ b/arch/arm/boot/dts/omap3-n900.dts @@ -832,8 +832,8 @@ touchscreen-fuzz-x = <4>; touchscreen-fuzz-y = <7>; touchscreen-fuzz-pressure = <2>; - touchscreen-max-x = <4096>; - touchscreen-max-y = <4096>; + touchscreen-size-x = <4096>; + touchscreen-size-y = <4096>; touchscreen-max-pressure = <2048>; ti,x-plate-ohms = <280>; diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h index 4e78065a16aa..5eed82809d82 100644 --- a/arch/arm/include/asm/futex.h +++ b/arch/arm/include/asm/futex.h @@ -93,6 +93,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) return -EFAULT; + preempt_disable(); __asm__ __volatile__("@futex_atomic_cmpxchg_inatomic\n" "1: " TUSER(ldr) " %1, [%4]\n" " teq %1, %2\n" @@ -104,6 +105,8 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, : "cc", "memory"); *uval = val; + preempt_enable(); + return ret; } @@ -124,7 +127,10 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr) if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) return -EFAULT; - pagefault_disable(); /* implies preempt_disable() */ +#ifndef CONFIG_SMP + preempt_disable(); +#endif + pagefault_disable(); switch (op) { case FUTEX_OP_SET: @@ -146,7 +152,10 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr) ret = -ENOSYS; } - pagefault_enable(); /* subsumes preempt_enable() */ + pagefault_enable(); +#ifndef CONFIG_SMP + preempt_enable(); +#endif if (!ret) { switch (cmp) { diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h index 2fe85fff5cca..370f7a732900 100644 --- a/arch/arm/include/asm/topology.h +++ b/arch/arm/include/asm/topology.h @@ -18,7 +18,7 @@ extern struct cputopo_arm cpu_topology[NR_CPUS]; #define topology_physical_package_id(cpu) (cpu_topology[cpu].socket_id) #define topology_core_id(cpu) (cpu_topology[cpu].core_id) #define topology_core_cpumask(cpu) (&cpu_topology[cpu].core_sibling) -#define topology_thread_cpumask(cpu) (&cpu_topology[cpu].thread_sibling) +#define topology_sibling_cpumask(cpu) (&cpu_topology[cpu].thread_sibling) void init_cpu_topology(void); void store_cpu_topology(unsigned int cpuid); diff --git a/arch/arm/mach-exynos/suspend.c b/arch/arm/mach-exynos/suspend.c index c0b6dccbf7bd..7d23ce04cad5 100644 --- a/arch/arm/mach-exynos/suspend.c +++ b/arch/arm/mach-exynos/suspend.c @@ -87,8 +87,8 @@ static unsigned int exynos_pmu_spare3; static u32 exynos_irqwake_intmask = 0xffffffff; static const struct exynos_wkup_irq exynos3250_wkup_irq[] = { - { 105, BIT(1) }, /* RTC alarm */ - { 106, BIT(2) }, /* RTC tick */ + { 73, BIT(1) }, /* RTC alarm */ + { 74, BIT(2) }, /* RTC tick */ { /* sentinel */ }, }; diff --git a/arch/arm/mach-omap2/sleep34xx.S b/arch/arm/mach-omap2/sleep34xx.S index d1dedc8195ed..eafd120b53f1 100644 --- a/arch/arm/mach-omap2/sleep34xx.S +++ b/arch/arm/mach-omap2/sleep34xx.S @@ -203,23 +203,8 @@ save_context_wfi: */ ldr r1, kernel_flush blx r1 - /* - * The kernel doesn't interwork: v7_flush_dcache_all in particluar will - * always return in Thumb state when CONFIG_THUMB2_KERNEL is enabled. - * This sequence switches back to ARM. Note that .align may insert a - * nop: bx pc needs to be word-aligned in order to work. - */ - THUMB( .thumb ) - THUMB( .align ) - THUMB( bx pc ) - THUMB( nop ) - .arm - b omap3_do_wfi - -/* - * Local variables - */ +ENDPROC(omap34xx_cpu_suspend) omap3_do_wfi_sram_addr: .word omap3_do_wfi_sram kernel_flush: @@ -364,10 +349,7 @@ exit_nonoff_modes: * =================================== */ ldmfd sp!, {r4 - r11, pc} @ restore regs and return - -/* - * Local variables - */ +ENDPROC(omap3_do_wfi) sdrc_power: .word SDRC_POWER_V cm_idlest1_core: diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index 6333d9c17875..0d629b8f973f 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -276,7 +276,7 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) * If we're in an interrupt or have no user * context, we must not take the fault.. */ - if (in_atomic() || !mm) + if (faulthandler_disabled() || !mm) goto no_context; if (user_mode(regs)) diff --git a/arch/arm/mm/highmem.c b/arch/arm/mm/highmem.c index b98895d9fe57..ee8dfa793989 100644 --- a/arch/arm/mm/highmem.c +++ b/arch/arm/mm/highmem.c @@ -59,6 +59,7 @@ void *kmap_atomic(struct page *page) void *kmap; int type; + preempt_disable(); pagefault_disable(); if (!PageHighMem(page)) return page_address(page); @@ -121,6 +122,7 @@ void __kunmap_atomic(void *kvaddr) kunmap_high(pte_page(pkmap_page_table[PKMAP_NR(vaddr)])); } pagefault_enable(); + preempt_enable(); } EXPORT_SYMBOL(__kunmap_atomic); @@ -130,6 +132,7 @@ void *kmap_atomic_pfn(unsigned long pfn) int idx, type; struct page *page = pfn_to_page(pfn); + preempt_disable(); pagefault_disable(); if (!PageHighMem(page)) return page_address(page); diff --git a/arch/arm64/boot/dts/mediatek/mt8173-evb.dts b/arch/arm64/boot/dts/mediatek/mt8173-evb.dts index 43d54017b779..d0ab012fa379 100644 --- a/arch/arm64/boot/dts/mediatek/mt8173-evb.dts +++ b/arch/arm64/boot/dts/mediatek/mt8173-evb.dts @@ -16,7 +16,8 @@ #include "mt8173.dtsi" / { - model = "mediatek,mt8173-evb"; + model = "MediaTek MT8173 evaluation board"; + compatible = "mediatek,mt8173-evb", "mediatek,mt8173"; aliases { serial0 = &uart0; diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h index 5f750dc96e0f..74069b3bd919 100644 --- a/arch/arm64/include/asm/futex.h +++ b/arch/arm64/include/asm/futex.h @@ -58,7 +58,7 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr) if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) return -EFAULT; - pagefault_disable(); /* implies preempt_disable() */ + pagefault_disable(); switch (op) { case FUTEX_OP_SET: @@ -85,7 +85,7 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr) ret = -ENOSYS; } - pagefault_enable(); /* subsumes preempt_enable() */ + pagefault_enable(); if (!ret) { switch (cmp) { diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h index 7ebcd31ce51c..225ec3524fbf 100644 --- a/arch/arm64/include/asm/topology.h +++ b/arch/arm64/include/asm/topology.h @@ -18,7 +18,7 @@ extern struct cpu_topology cpu_topology[NR_CPUS]; #define topology_physical_package_id(cpu) (cpu_topology[cpu].cluster_id) #define topology_core_id(cpu) (cpu_topology[cpu].core_id) #define topology_core_cpumask(cpu) (&cpu_topology[cpu].core_sibling) -#define topology_thread_cpumask(cpu) (&cpu_topology[cpu].thread_sibling) +#define topology_sibling_cpumask(cpu) (&cpu_topology[cpu].thread_sibling) void init_cpu_topology(void); void store_cpu_topology(unsigned int cpuid); diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 96da13167d4a..0948d327d013 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -211,7 +211,7 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr, * If we're in an interrupt or have no user context, we must not take * the fault. */ - if (in_atomic() || !mm) + if (faulthandler_disabled() || !mm) goto no_context; if (user_mode(regs)) diff --git a/arch/avr32/include/asm/uaccess.h b/arch/avr32/include/asm/uaccess.h index a46f7cf3e1ea..68cf638faf48 100644 --- a/arch/avr32/include/asm/uaccess.h +++ b/arch/avr32/include/asm/uaccess.h @@ -97,7 +97,8 @@ static inline __kernel_size_t __copy_from_user(void *to, * @x: Value to copy to user space. * @ptr: Destination address, in user space. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * This macro copies a single simple value from kernel space to user * space. It supports simple types like char and int, but not larger @@ -116,7 +117,8 @@ static inline __kernel_size_t __copy_from_user(void *to, * @x: Variable to store result. * @ptr: Source address, in user space. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * This macro copies a single simple variable from user space to kernel * space. It supports simple types like char and int, but not larger @@ -136,7 +138,8 @@ static inline __kernel_size_t __copy_from_user(void *to, * @x: Value to copy to user space. * @ptr: Destination address, in user space. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * This macro copies a single simple value from kernel space to user * space. It supports simple types like char and int, but not larger @@ -158,7 +161,8 @@ static inline __kernel_size_t __copy_from_user(void *to, * @x: Variable to store result. * @ptr: Source address, in user space. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * This macro copies a single simple variable from user space to kernel * space. It supports simple types like char and int, but not larger diff --git a/arch/avr32/mm/fault.c b/arch/avr32/mm/fault.c index d223a8b57c1e..c03533937a9f 100644 --- a/arch/avr32/mm/fault.c +++ b/arch/avr32/mm/fault.c @@ -14,11 +14,11 @@ #include <linux/pagemap.h> #include <linux/kdebug.h> #include <linux/kprobes.h> +#include <linux/uaccess.h> #include <asm/mmu_context.h> #include <asm/sysreg.h> #include <asm/tlb.h> -#include <asm/uaccess.h> #ifdef CONFIG_KPROBES static inline int notify_page_fault(struct pt_regs *regs, int trap) @@ -81,7 +81,7 @@ asmlinkage void do_page_fault(unsigned long ecr, struct pt_regs *regs) * If we're in an interrupt or have no user context, we must * not take the fault... */ - if (in_atomic() || !mm || regs->sr & SYSREG_BIT(GM)) + if (faulthandler_disabled() || !mm || regs->sr & SYSREG_BIT(GM)) goto no_context; local_irq_enable(); diff --git a/arch/blackfin/include/asm/io.h b/arch/blackfin/include/asm/io.h index 4e8ad0523118..6abebe82d4e9 100644 --- a/arch/blackfin/include/asm/io.h +++ b/arch/blackfin/include/asm/io.h @@ -10,6 +10,7 @@ #include <linux/compiler.h> #include <linux/types.h> #include <asm/byteorder.h> +#include <asm/def_LPBlackfin.h> #define __raw_readb bfin_read8 #define __raw_readw bfin_read16 diff --git a/arch/cris/mm/fault.c b/arch/cris/mm/fault.c index 83f12f2ed9e3..3066d40a6db1 100644 --- a/arch/cris/mm/fault.c +++ b/arch/cris/mm/fault.c @@ -8,7 +8,7 @@ #include <linux/interrupt.h> #include <linux/module.h> #include <linux/wait.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include <arch/system.h> extern int find_fixup_code(struct pt_regs *); @@ -109,11 +109,11 @@ do_page_fault(unsigned long address, struct pt_regs *regs, info.si_code = SEGV_MAPERR; /* - * If we're in an interrupt or "atomic" operation or have no + * If we're in an interrupt, have pagefaults disabled or have no * user context, we must not take the fault. */ - if (in_atomic() || !mm) + if (faulthandler_disabled() || !mm) goto no_context; if (user_mode(regs)) diff --git a/arch/frv/mm/fault.c b/arch/frv/mm/fault.c index ec4917ddf678..61d99767fe16 100644 --- a/arch/frv/mm/fault.c +++ b/arch/frv/mm/fault.c @@ -19,9 +19,9 @@ #include <linux/kernel.h> #include <linux/ptrace.h> #include <linux/hardirq.h> +#include <linux/uaccess.h> #include <asm/pgtable.h> -#include <asm/uaccess.h> #include <asm/gdb-stub.h> /*****************************************************************************/ @@ -78,7 +78,7 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear * If we're in an interrupt or have no user * context, we must not take the fault.. */ - if (in_atomic() || !mm) + if (faulthandler_disabled() || !mm) goto no_context; if (user_mode(__frame)) diff --git a/arch/frv/mm/highmem.c b/arch/frv/mm/highmem.c index bed9a9bd3c10..785344bbdc07 100644 --- a/arch/frv/mm/highmem.c +++ b/arch/frv/mm/highmem.c @@ -42,6 +42,7 @@ void *kmap_atomic(struct page *page) unsigned long paddr; int type; + preempt_disable(); pagefault_disable(); type = kmap_atomic_idx_push(); paddr = page_to_phys(page); @@ -85,5 +86,6 @@ void __kunmap_atomic(void *kvaddr) } kmap_atomic_idx_pop(); pagefault_enable(); + preempt_enable(); } EXPORT_SYMBOL(__kunmap_atomic); diff --git a/arch/hexagon/include/asm/uaccess.h b/arch/hexagon/include/asm/uaccess.h index e4127e4d6a5b..f000a382bc7f 100644 --- a/arch/hexagon/include/asm/uaccess.h +++ b/arch/hexagon/include/asm/uaccess.h @@ -36,7 +36,8 @@ * @addr: User space pointer to start of block to check * @size: Size of block to check * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * Checks if a pointer to a block of memory in user space is valid. * diff --git a/arch/ia64/include/asm/topology.h b/arch/ia64/include/asm/topology.h index 6437ca21f61b..3ad8f6988363 100644 --- a/arch/ia64/include/asm/topology.h +++ b/arch/ia64/include/asm/topology.h @@ -53,7 +53,7 @@ void build_cpu_to_node_map(void); #define topology_physical_package_id(cpu) (cpu_data(cpu)->socket_id) #define topology_core_id(cpu) (cpu_data(cpu)->core_id) #define topology_core_cpumask(cpu) (&cpu_core_map[cpu]) -#define topology_thread_cpumask(cpu) (&per_cpu(cpu_sibling_map, cpu)) +#define topology_sibling_cpumask(cpu) (&per_cpu(cpu_sibling_map, cpu)) #endif extern void arch_fix_phys_package_id(int num, u32 slot); diff --git a/arch/ia64/kernel/smpboot.c b/arch/ia64/kernel/smpboot.c index 15051e9c2c6f..b054c5c6e713 100644 --- a/arch/ia64/kernel/smpboot.c +++ b/arch/ia64/kernel/smpboot.c @@ -127,7 +127,7 @@ int smp_num_siblings = 1; volatile int ia64_cpu_to_sapicid[NR_CPUS]; EXPORT_SYMBOL(ia64_cpu_to_sapicid); -static volatile cpumask_t cpu_callin_map; +static cpumask_t cpu_callin_map; struct smp_boot_data smp_boot_data __initdata; @@ -477,6 +477,7 @@ do_boot_cpu (int sapicid, int cpu, struct task_struct *idle) for (timeout = 0; timeout < 100000; timeout++) { if (cpumask_test_cpu(cpu, &cpu_callin_map)) break; /* It has booted */ + barrier(); /* Make sure we re-read cpu_callin_map */ udelay(100); } Dprintk("\n"); diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c index ba5ba7accd0d..70b40d1205a6 100644 --- a/arch/ia64/mm/fault.c +++ b/arch/ia64/mm/fault.c @@ -11,10 +11,10 @@ #include <linux/kprobes.h> #include <linux/kdebug.h> #include <linux/prefetch.h> +#include <linux/uaccess.h> #include <asm/pgtable.h> #include <asm/processor.h> -#include <asm/uaccess.h> extern int die(char *, struct pt_regs *, long); @@ -96,7 +96,7 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re /* * If we're in an interrupt or have no user context, we must not take the fault.. */ - if (in_atomic() || !mm) + if (faulthandler_disabled() || !mm) goto no_context; #ifdef CONFIG_VIRTUAL_MEM_MAP diff --git a/arch/m32r/include/asm/uaccess.h b/arch/m32r/include/asm/uaccess.h index 71adff209405..cac7014daef3 100644 --- a/arch/m32r/include/asm/uaccess.h +++ b/arch/m32r/include/asm/uaccess.h @@ -91,7 +91,8 @@ static inline void set_fs(mm_segment_t s) * @addr: User space pointer to start of block to check * @size: Size of block to check * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * Checks if a pointer to a block of memory in user space is valid. * @@ -155,7 +156,8 @@ extern int fixup_exception(struct pt_regs *regs); * @x: Variable to store result. * @ptr: Source address, in user space. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * This macro copies a single simple variable from user space to kernel * space. It supports simple types like char and int, but not larger @@ -175,7 +177,8 @@ extern int fixup_exception(struct pt_regs *regs); * @x: Value to copy to user space. * @ptr: Destination address, in user space. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * This macro copies a single simple value from kernel space to user * space. It supports simple types like char and int, but not larger @@ -194,7 +197,8 @@ extern int fixup_exception(struct pt_regs *regs); * @x: Variable to store result. * @ptr: Source address, in user space. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * This macro copies a single simple variable from user space to kernel * space. It supports simple types like char and int, but not larger @@ -274,7 +278,8 @@ do { \ * @x: Value to copy to user space. * @ptr: Destination address, in user space. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * This macro copies a single simple value from kernel space to user * space. It supports simple types like char and int, but not larger @@ -568,7 +573,8 @@ unsigned long __generic_copy_from_user(void *, const void __user *, unsigned lon * @from: Source address, in kernel space. * @n: Number of bytes to copy. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * Copy data from kernel space to user space. Caller must check * the specified block with access_ok() before calling this function. @@ -588,7 +594,8 @@ unsigned long __generic_copy_from_user(void *, const void __user *, unsigned lon * @from: Source address, in kernel space. * @n: Number of bytes to copy. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * Copy data from kernel space to user space. * @@ -606,7 +613,8 @@ unsigned long __generic_copy_from_user(void *, const void __user *, unsigned lon * @from: Source address, in user space. * @n: Number of bytes to copy. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * Copy data from user space to kernel space. Caller must check * the specified block with access_ok() before calling this function. @@ -626,7 +634,8 @@ unsigned long __generic_copy_from_user(void *, const void __user *, unsigned lon * @from: Source address, in user space. * @n: Number of bytes to copy. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * Copy data from user space to kernel space. * @@ -677,7 +686,8 @@ unsigned long clear_user(void __user *mem, unsigned long len); * strlen_user: - Get the size of a string in user space. * @str: The string to measure. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * Get the size of a NUL-terminated string in user space. * diff --git a/arch/m32r/mm/fault.c b/arch/m32r/mm/fault.c index e3d4d4890104..8f9875b7933d 100644 --- a/arch/m32r/mm/fault.c +++ b/arch/m32r/mm/fault.c @@ -24,9 +24,9 @@ #include <linux/vt_kern.h> /* For unblank_screen() */ #include <linux/highmem.h> #include <linux/module.h> +#include <linux/uaccess.h> #include <asm/m32r.h> -#include <asm/uaccess.h> #include <asm/hardirq.h> #include <asm/mmu_context.h> #include <asm/tlbflush.h> @@ -111,10 +111,10 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code, mm = tsk->mm; /* - * If we're in an interrupt or have no user context or are running in an - * atomic region then we must not take the fault.. + * If we're in an interrupt or have no user context or have pagefaults + * disabled then we must not take the fault. */ - if (in_atomic() || !mm) + if (faulthandler_disabled() || !mm) goto bad_area_nosemaphore; if (error_code & ACE_USERMODE) diff --git a/arch/m68k/include/asm/irqflags.h b/arch/m68k/include/asm/irqflags.h index a823cd73dc09..b5941818346f 100644 --- a/arch/m68k/include/asm/irqflags.h +++ b/arch/m68k/include/asm/irqflags.h @@ -2,9 +2,6 @@ #define _M68K_IRQFLAGS_H #include <linux/types.h> -#ifdef CONFIG_MMU -#include <linux/preempt_mask.h> -#endif #include <linux/preempt.h> #include <asm/thread_info.h> #include <asm/entry.h> diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c index b2f04aee46ec..6a94cdd0c830 100644 --- a/arch/m68k/mm/fault.c +++ b/arch/m68k/mm/fault.c @@ -10,10 +10,10 @@ #include <linux/ptrace.h> #include <linux/interrupt.h> #include <linux/module.h> +#include <linux/uaccess.h> #include <asm/setup.h> #include <asm/traps.h> -#include <asm/uaccess.h> #include <asm/pgalloc.h> extern void die_if_kernel(char *, struct pt_regs *, long); @@ -81,7 +81,7 @@ int do_page_fault(struct pt_regs *regs, unsigned long address, * If we're in an interrupt or have no user * context, we must not take the fault.. */ - if (in_atomic() || !mm) + if (faulthandler_disabled() || !mm) goto no_context; if (user_mode(regs)) diff --git a/arch/metag/mm/fault.c b/arch/metag/mm/fault.c index 2de5dc695a87..f57edca63609 100644 --- a/arch/metag/mm/fault.c +++ b/arch/metag/mm/fault.c @@ -105,7 +105,7 @@ int do_page_fault(struct pt_regs *regs, unsigned long address, mm = tsk->mm; - if (in_atomic() || !mm) + if (faulthandler_disabled() || !mm) goto no_context; if (user_mode(regs)) diff --git a/arch/metag/mm/highmem.c b/arch/metag/mm/highmem.c index d71f621a2c0b..807f1b1c4e65 100644 --- a/arch/metag/mm/highmem.c +++ b/arch/metag/mm/highmem.c @@ -43,7 +43,7 @@ void *kmap_atomic(struct page *page) unsigned long vaddr; int type; - /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */ + preempt_disable(); pagefault_disable(); if (!PageHighMem(page)) return page_address(page); @@ -82,6 +82,7 @@ void __kunmap_atomic(void *kvaddr) } pagefault_enable(); + preempt_enable(); } EXPORT_SYMBOL(__kunmap_atomic); @@ -95,6 +96,7 @@ void *kmap_atomic_pfn(unsigned long pfn) unsigned long vaddr; int type; + preempt_disable(); pagefault_disable(); type = kmap_atomic_idx_push(); diff --git a/arch/microblaze/include/asm/uaccess.h b/arch/microblaze/include/asm/uaccess.h index 62942fd12672..331b0d35f89c 100644 --- a/arch/microblaze/include/asm/uaccess.h +++ b/arch/microblaze/include/asm/uaccess.h @@ -178,7 +178,8 @@ extern long __user_bad(void); * @x: Variable to store result. * @ptr: Source address, in user space. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * This macro copies a single simple variable from user space to kernel * space. It supports simple types like char and int, but not larger @@ -290,7 +291,8 @@ extern long __user_bad(void); * @x: Value to copy to user space. * @ptr: Destination address, in user space. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * This macro copies a single simple value from kernel space to user * space. It supports simple types like char and int, but not larger diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c index d46a5ebb7570..177dfc003643 100644 --- a/arch/microblaze/mm/fault.c +++ b/arch/microblaze/mm/fault.c @@ -107,14 +107,14 @@ void do_page_fault(struct pt_regs *regs, unsigned long address, if ((error_code & 0x13) == 0x13 || (error_code & 0x11) == 0x11) is_write = 0; - if (unlikely(in_atomic() || !mm)) { + if (unlikely(faulthandler_disabled() || !mm)) { if (kernel_mode(regs)) goto bad_area_nosemaphore; - /* in_atomic() in user mode is really bad, + /* faulthandler_disabled() in user mode is really bad, as is current->mm == NULL. */ - pr_emerg("Page fault in user mode with in_atomic(), mm = %p\n", - mm); + pr_emerg("Page fault in user mode with faulthandler_disabled(), mm = %p\n", + mm); pr_emerg("r15 = %lx MSR = %lx\n", regs->r15, regs->msr); die("Weird page fault", regs, SIGSEGV); diff --git a/arch/microblaze/mm/highmem.c b/arch/microblaze/mm/highmem.c index 5a92576fad92..2fcc5a52d84d 100644 --- a/arch/microblaze/mm/highmem.c +++ b/arch/microblaze/mm/highmem.c @@ -37,7 +37,7 @@ void *kmap_atomic_prot(struct page *page, pgprot_t prot) unsigned long vaddr; int idx, type; - /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */ + preempt_disable(); pagefault_disable(); if (!PageHighMem(page)) return page_address(page); @@ -63,6 +63,7 @@ void __kunmap_atomic(void *kvaddr) if (vaddr < __fix_to_virt(FIX_KMAP_END)) { pagefault_enable(); + preempt_enable(); return; } @@ -84,5 +85,6 @@ void __kunmap_atomic(void *kvaddr) #endif kmap_atomic_idx_pop(); pagefault_enable(); + preempt_enable(); } EXPORT_SYMBOL(__kunmap_atomic); diff --git a/arch/mips/ath79/setup.c b/arch/mips/ath79/setup.c index a73c93c3d44a..7fc8397d16f2 100644 --- a/arch/mips/ath79/setup.c +++ b/arch/mips/ath79/setup.c @@ -225,7 +225,7 @@ void __init plat_time_init(void) ddr_clk_rate = ath79_get_sys_clk_rate("ddr"); ref_clk_rate = ath79_get_sys_clk_rate("ref"); - pr_info("Clocks: CPU:%lu.%03luMHz, DDR:%lu.%03luMHz, AHB:%lu.%03luMHz, Ref:%lu.%03luMHz", + pr_info("Clocks: CPU:%lu.%03luMHz, DDR:%lu.%03luMHz, AHB:%lu.%03luMHz, Ref:%lu.%03luMHz\n", cpu_clk_rate / 1000000, (cpu_clk_rate / 1000) % 1000, ddr_clk_rate / 1000000, (ddr_clk_rate / 1000) % 1000, ahb_clk_rate / 1000000, (ahb_clk_rate / 1000) % 1000, diff --git a/arch/mips/cobalt/Makefile b/arch/mips/cobalt/Makefile index 558e94977942..68f0c5871adc 100644 --- a/arch/mips/cobalt/Makefile +++ b/arch/mips/cobalt/Makefile @@ -2,7 +2,6 @@ # Makefile for the Cobalt micro systems family specific parts of the kernel # -obj-y := buttons.o irq.o lcd.o led.o reset.o rtc.o serial.o setup.o time.o +obj-y := buttons.o irq.o lcd.o led.o mtd.o reset.o rtc.o serial.o setup.o time.o obj-$(CONFIG_PCI) += pci.o -obj-$(CONFIG_MTD_PHYSMAP) += mtd.o diff --git a/arch/mips/include/asm/pgtable-bits.h b/arch/mips/include/asm/pgtable-bits.h index 18ae5ddef118..c28a8499aec7 100644 --- a/arch/mips/include/asm/pgtable-bits.h +++ b/arch/mips/include/asm/pgtable-bits.h @@ -113,7 +113,7 @@ #define _PAGE_PRESENT_SHIFT 0 #define _PAGE_PRESENT (1 << _PAGE_PRESENT_SHIFT) /* R2 or later cores check for RI/XI support to determine _PAGE_READ */ -#ifdef CONFIG_CPU_MIPSR2 +#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6) #define _PAGE_WRITE_SHIFT (_PAGE_PRESENT_SHIFT + 1) #define _PAGE_WRITE (1 << _PAGE_WRITE_SHIFT) #else @@ -135,16 +135,16 @@ #define _PAGE_SPLITTING (1 << _PAGE_SPLITTING_SHIFT) /* Only R2 or newer cores have the XI bit */ -#ifdef CONFIG_CPU_MIPSR2 +#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6) #define _PAGE_NO_EXEC_SHIFT (_PAGE_SPLITTING_SHIFT + 1) #else #define _PAGE_GLOBAL_SHIFT (_PAGE_SPLITTING_SHIFT + 1) #define _PAGE_GLOBAL (1 << _PAGE_GLOBAL_SHIFT) -#endif /* CONFIG_CPU_MIPSR2 */ +#endif /* CONFIG_CPU_MIPSR2 || CONFIG_CPU_MIPSR6 */ #endif /* CONFIG_64BIT && CONFIG_MIPS_HUGE_TLB_SUPPORT */ -#ifdef CONFIG_CPU_MIPSR2 +#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6) /* XI - page cannot be executed */ #ifndef _PAGE_NO_EXEC_SHIFT #define _PAGE_NO_EXEC_SHIFT (_PAGE_MODIFIED_SHIFT + 1) @@ -160,10 +160,10 @@ #define _PAGE_GLOBAL_SHIFT (_PAGE_NO_READ_SHIFT + 1) #define _PAGE_GLOBAL (1 << _PAGE_GLOBAL_SHIFT) -#else /* !CONFIG_CPU_MIPSR2 */ +#else /* !CONFIG_CPU_MIPSR2 && !CONFIG_CPU_MIPSR6 */ #define _PAGE_GLOBAL_SHIFT (_PAGE_MODIFIED_SHIFT + 1) #define _PAGE_GLOBAL (1 << _PAGE_GLOBAL_SHIFT) -#endif /* CONFIG_CPU_MIPSR2 */ +#endif /* CONFIG_CPU_MIPSR2 || CONFIG_CPU_MIPSR6 */ #define _PAGE_VALID_SHIFT (_PAGE_GLOBAL_SHIFT + 1) #define _PAGE_VALID (1 << _PAGE_VALID_SHIFT) @@ -205,7 +205,7 @@ */ static inline uint64_t pte_to_entrylo(unsigned long pte_val) { -#ifdef CONFIG_CPU_MIPSR2 +#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6) if (cpu_has_rixi) { int sa; #ifdef CONFIG_32BIT diff --git a/arch/mips/include/asm/switch_to.h b/arch/mips/include/asm/switch_to.h index e92d6c4b5ed1..7163cd7fdd69 100644 --- a/arch/mips/include/asm/switch_to.h +++ b/arch/mips/include/asm/switch_to.h @@ -104,7 +104,6 @@ do { \ if (test_and_clear_tsk_thread_flag(prev, TIF_USEDMSA)) \ __fpsave = FP_SAVE_VECTOR; \ (last) = resume(prev, next, task_thread_info(next), __fpsave); \ - disable_msa(); \ } while (0) #define finish_arch_switch(prev) \ @@ -122,6 +121,7 @@ do { \ if (cpu_has_userlocal) \ write_c0_userlocal(current_thread_info()->tp_value); \ __restore_watch(); \ + disable_msa(); \ } while (0) #endif /* _ASM_SWITCH_TO_H */ diff --git a/arch/mips/include/asm/topology.h b/arch/mips/include/asm/topology.h index 3e307ec2afba..7afda4150a59 100644 --- a/arch/mips/include/asm/topology.h +++ b/arch/mips/include/asm/topology.h @@ -15,7 +15,7 @@ #define topology_physical_package_id(cpu) (cpu_data[cpu].package) #define topology_core_id(cpu) (cpu_data[cpu].core) #define topology_core_cpumask(cpu) (&cpu_core_map[cpu]) -#define topology_thread_cpumask(cpu) (&cpu_sibling_map[cpu]) +#define topology_sibling_cpumask(cpu) (&cpu_sibling_map[cpu]) #endif #endif /* __ASM_TOPOLOGY_H */ diff --git a/arch/mips/include/asm/uaccess.h b/arch/mips/include/asm/uaccess.h index bf8b32450ef6..9722357d2854 100644 --- a/arch/mips/include/asm/uaccess.h +++ b/arch/mips/include/asm/uaccess.h @@ -103,7 +103,8 @@ extern u64 __ua_limit; * @addr: User space pointer to start of block to check * @size: Size of block to check * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * Checks if a pointer to a block of memory in user space is valid. * @@ -138,7 +139,8 @@ extern u64 __ua_limit; * @x: Value to copy to user space. * @ptr: Destination address, in user space. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * This macro copies a single simple value from kernel space to user * space. It supports simple types like char and int, but not larger @@ -157,7 +159,8 @@ extern u64 __ua_limit; * @x: Variable to store result. * @ptr: Source address, in user space. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * This macro copies a single simple variable from user space to kernel * space. It supports simple types like char and int, but not larger @@ -177,7 +180,8 @@ extern u64 __ua_limit; * @x: Value to copy to user space. * @ptr: Destination address, in user space. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * This macro copies a single simple value from kernel space to user * space. It supports simple types like char and int, but not larger @@ -199,7 +203,8 @@ extern u64 __ua_limit; * @x: Variable to store result. * @ptr: Source address, in user space. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * This macro copies a single simple variable from user space to kernel * space. It supports simple types like char and int, but not larger @@ -498,7 +503,8 @@ extern void __put_user_unknown(void); * @x: Value to copy to user space. * @ptr: Destination address, in user space. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * This macro copies a single simple value from kernel space to user * space. It supports simple types like char and int, but not larger @@ -517,7 +523,8 @@ extern void __put_user_unknown(void); * @x: Variable to store result. * @ptr: Source address, in user space. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * This macro copies a single simple variable from user space to kernel * space. It supports simple types like char and int, but not larger @@ -537,7 +544,8 @@ extern void __put_user_unknown(void); * @x: Value to copy to user space. * @ptr: Destination address, in user space. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * This macro copies a single simple value from kernel space to user * space. It supports simple types like char and int, but not larger @@ -559,7 +567,8 @@ extern void __put_user_unknown(void); * @x: Variable to store result. * @ptr: Source address, in user space. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * This macro copies a single simple variable from user space to kernel * space. It supports simple types like char and int, but not larger @@ -815,7 +824,8 @@ extern size_t __copy_user(void *__to, const void *__from, size_t __n); * @from: Source address, in kernel space. * @n: Number of bytes to copy. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * Copy data from kernel space to user space. Caller must check * the specified block with access_ok() before calling this function. @@ -888,7 +898,8 @@ extern size_t __copy_user_inatomic(void *__to, const void *__from, size_t __n); * @from: Source address, in kernel space. * @n: Number of bytes to copy. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * Copy data from kernel space to user space. * @@ -1075,7 +1086,8 @@ extern size_t __copy_in_user_eva(void *__to, const void *__from, size_t __n); * @from: Source address, in user space. * @n: Number of bytes to copy. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * Copy data from user space to kernel space. Caller must check * the specified block with access_ok() before calling this function. @@ -1107,7 +1119,8 @@ extern size_t __copy_in_user_eva(void *__to, const void *__from, size_t __n); * @from: Source address, in user space. * @n: Number of bytes to copy. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * Copy data from user space to kernel space. * @@ -1329,7 +1342,8 @@ strncpy_from_user(char *__to, const char __user *__from, long __len) * strlen_user: - Get the size of a string in user space. * @str: The string to measure. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * Get the size of a NUL-terminated string in user space. * @@ -1398,7 +1412,8 @@ static inline long __strnlen_user(const char __user *s, long n) * strnlen_user: - Get the size of a string in user space. * @str: The string to measure. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * Get the size of a NUL-terminated string in user space. * diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c index e36515dcd3b2..209e5b76c1bc 100644 --- a/arch/mips/kernel/cpu-probe.c +++ b/arch/mips/kernel/cpu-probe.c @@ -74,13 +74,12 @@ static inline void cpu_set_fpu_fcsr_mask(struct cpuinfo_mips *c) { unsigned long sr, mask, fcsr, fcsr0, fcsr1; + fcsr = c->fpu_csr31; mask = FPU_CSR_ALL_X | FPU_CSR_ALL_E | FPU_CSR_ALL_S | FPU_CSR_RM; sr = read_c0_status(); __enable_fpu(FPU_AS_IS); - fcsr = read_32bit_cp1_register(CP1_STATUS); - fcsr0 = fcsr & mask; write_32bit_cp1_register(CP1_STATUS, fcsr0); fcsr0 = read_32bit_cp1_register(CP1_STATUS); diff --git a/arch/mips/kernel/irq.c b/arch/mips/kernel/irq.c index 51f57d841662..3c8a18a00a65 100644 --- a/arch/mips/kernel/irq.c +++ b/arch/mips/kernel/irq.c @@ -109,7 +109,7 @@ void __init init_IRQ(void) #endif } -#ifdef DEBUG_STACKOVERFLOW +#ifdef CONFIG_DEBUG_STACKOVERFLOW static inline void check_stack_overflow(void) { unsigned long sp; diff --git a/arch/mips/kernel/signal-common.h b/arch/mips/kernel/signal-common.h index 06805e09bcd3..0b85f827cd18 100644 --- a/arch/mips/kernel/signal-common.h +++ b/arch/mips/kernel/signal-common.h @@ -28,12 +28,7 @@ extern void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, extern int fpcsr_pending(unsigned int __user *fpcsr); /* Make sure we will not lose FPU ownership */ -#ifdef CONFIG_PREEMPT -#define lock_fpu_owner() preempt_disable() -#define unlock_fpu_owner() preempt_enable() -#else -#define lock_fpu_owner() pagefault_disable() -#define unlock_fpu_owner() pagefault_enable() -#endif +#define lock_fpu_owner() ({ preempt_disable(); pagefault_disable(); }) +#define unlock_fpu_owner() ({ pagefault_enable(); preempt_enable(); }) #endif /* __SIGNAL_COMMON_H */ diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c index 4b50c5787e25..d5fa3eaf39a1 100644 --- a/arch/mips/kvm/emulate.c +++ b/arch/mips/kvm/emulate.c @@ -2409,7 +2409,7 @@ enum emulation_result kvm_mips_complete_mmio_load(struct kvm_vcpu *vcpu, if (vcpu->mmio_needed == 2) *gpr = *(int16_t *) run->mmio.data; else - *gpr = *(int16_t *) run->mmio.data; + *gpr = *(uint16_t *)run->mmio.data; break; case 1: diff --git a/arch/mips/loongson/common/Makefile b/arch/mips/loongson/common/Makefile index e70c33fdb881..f2e8153e44f5 100644 --- a/arch/mips/loongson/common/Makefile +++ b/arch/mips/loongson/common/Makefile @@ -3,15 +3,13 @@ # obj-y += setup.o init.o cmdline.o env.o time.o reset.o irq.o \ - bonito-irq.o mem.o machtype.o platform.o + bonito-irq.o mem.o machtype.o platform.o serial.o obj-$(CONFIG_PCI) += pci.o # # Serial port support # obj-$(CONFIG_EARLY_PRINTK) += early_printk.o -loongson-serial-$(CONFIG_SERIAL_8250) := serial.o -obj-y += $(loongson-serial-m) $(loongson-serial-y) obj-$(CONFIG_LOONGSON_UART_BASE) += uart_base.o obj-$(CONFIG_LOONGSON_MC146818) += rtc.o diff --git a/arch/mips/loongson/loongson-3/smp.c b/arch/mips/loongson/loongson-3/smp.c index e3c68b5da18d..509877c6e9d9 100644 --- a/arch/mips/loongson/loongson-3/smp.c +++ b/arch/mips/loongson/loongson-3/smp.c @@ -272,7 +272,7 @@ void loongson3_ipi_interrupt(struct pt_regs *regs) if (action & SMP_ASK_C0COUNT) { BUG_ON(cpu != 0); c0count = read_c0_count(); - for (i = 1; i < loongson_sysconf.nr_cpus; i++) + for (i = 1; i < num_possible_cpus(); i++) per_cpu(core0_c0count, i) = c0count; } } diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c index 0dbb65a51ce5..2e03ab173591 100644 --- a/arch/mips/mm/c-r4k.c +++ b/arch/mips/mm/c-r4k.c @@ -1372,7 +1372,7 @@ static int probe_scache(void) scache_size = addr; c->scache.linesz = 16 << ((config & R4K_CONF_SB) >> 22); c->scache.ways = 1; - c->dcache.waybit = 0; /* does not matter */ + c->scache.waybit = 0; /* does not matter */ return 1; } diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c index 7ff8637e530d..36c0f26fac6b 100644 --- a/arch/mips/mm/fault.c +++ b/arch/mips/mm/fault.c @@ -21,10 +21,10 @@ #include <linux/module.h> #include <linux/kprobes.h> #include <linux/perf_event.h> +#include <linux/uaccess.h> #include <asm/branch.h> #include <asm/mmu_context.h> -#include <asm/uaccess.h> #include <asm/ptrace.h> #include <asm/highmem.h> /* For VMALLOC_END */ #include <linux/kdebug.h> @@ -94,7 +94,7 @@ static void __kprobes __do_page_fault(struct pt_regs *regs, unsigned long write, * If we're in an interrupt or have no user * context, we must not take the fault.. */ - if (in_atomic() || !mm) + if (faulthandler_disabled() || !mm) goto bad_area_nosemaphore; if (user_mode(regs)) diff --git a/arch/mips/mm/highmem.c b/arch/mips/mm/highmem.c index da815d295239..11661cbc11a8 100644 --- a/arch/mips/mm/highmem.c +++ b/arch/mips/mm/highmem.c @@ -47,7 +47,7 @@ void *kmap_atomic(struct page *page) unsigned long vaddr; int idx, type; - /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */ + preempt_disable(); pagefault_disable(); if (!PageHighMem(page)) return page_address(page); @@ -72,6 +72,7 @@ void __kunmap_atomic(void *kvaddr) if (vaddr < FIXADDR_START) { // FIXME pagefault_enable(); + preempt_enable(); return; } @@ -92,6 +93,7 @@ void __kunmap_atomic(void *kvaddr) #endif kmap_atomic_idx_pop(); pagefault_enable(); + preempt_enable(); } EXPORT_SYMBOL(__kunmap_atomic); @@ -104,6 +106,7 @@ void *kmap_atomic_pfn(unsigned long pfn) unsigned long vaddr; int idx, type; + preempt_disable(); pagefault_disable(); type = kmap_atomic_idx_push(); diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c index faa5c9822ecc..198a3147dd7d 100644 --- a/arch/mips/mm/init.c +++ b/arch/mips/mm/init.c @@ -90,6 +90,7 @@ static void *__kmap_pgprot(struct page *page, unsigned long addr, pgprot_t prot) BUG_ON(Page_dcache_dirty(page)); + preempt_disable(); pagefault_disable(); idx = (addr >> PAGE_SHIFT) & (FIX_N_COLOURS - 1); idx += in_interrupt() ? FIX_N_COLOURS : 0; @@ -152,6 +153,7 @@ void kunmap_coherent(void) write_c0_entryhi(old_ctx); local_irq_restore(flags); pagefault_enable(); + preempt_enable(); } void copy_user_highpage(struct page *to, struct page *from, diff --git a/arch/mips/net/bpf_jit.c b/arch/mips/net/bpf_jit.c index 5d6139390bf8..e23fdf2a9c80 100644 --- a/arch/mips/net/bpf_jit.c +++ b/arch/mips/net/bpf_jit.c @@ -681,11 +681,7 @@ static unsigned int get_stack_depth(struct jit_ctx *ctx) sp_off += config_enabled(CONFIG_64BIT) ? (ARGS_USED_BY_JIT + 1) * RSIZE : RSIZE; - /* - * Subtract the bytes for the last registers since we only care about - * the location on the stack pointer. - */ - return sp_off - RSIZE; + return sp_off; } static void build_prologue(struct jit_ctx *ctx) diff --git a/arch/mips/ralink/ill_acc.c b/arch/mips/ralink/ill_acc.c index e20b02e3ae28..e10d10b9e82a 100644 --- a/arch/mips/ralink/ill_acc.c +++ b/arch/mips/ralink/ill_acc.c @@ -41,7 +41,7 @@ static irqreturn_t ill_acc_irq_handler(int irq, void *_priv) addr, (type >> ILL_ACC_OFF_S) & ILL_ACC_OFF_M, type & ILL_ACC_LEN_M); - rt_memc_w32(REG_ILL_ACC_TYPE, REG_ILL_ACC_TYPE); + rt_memc_w32(ILL_INT_STATUS, REG_ILL_ACC_TYPE); return IRQ_HANDLED; } diff --git a/arch/mn10300/include/asm/highmem.h b/arch/mn10300/include/asm/highmem.h index 2fbbe4d920aa..1ddea5afba09 100644 --- a/arch/mn10300/include/asm/highmem.h +++ b/arch/mn10300/include/asm/highmem.h @@ -75,6 +75,7 @@ static inline void *kmap_atomic(struct page *page) unsigned long vaddr; int idx, type; + preempt_disable(); pagefault_disable(); if (page < highmem_start_page) return page_address(page); @@ -98,6 +99,7 @@ static inline void __kunmap_atomic(unsigned long vaddr) if (vaddr < FIXADDR_START) { /* FIXME */ pagefault_enable(); + preempt_enable(); return; } @@ -122,6 +124,7 @@ static inline void __kunmap_atomic(unsigned long vaddr) kmap_atomic_idx_pop(); pagefault_enable(); + preempt_enable(); } #endif /* __KERNEL__ */ diff --git a/arch/mn10300/mm/fault.c b/arch/mn10300/mm/fault.c index 0c2cc5d39c8e..4a1d181ed32f 100644 --- a/arch/mn10300/mm/fault.c +++ b/arch/mn10300/mm/fault.c @@ -23,8 +23,8 @@ #include <linux/interrupt.h> #include <linux/init.h> #include <linux/vt_kern.h> /* For unblank_screen() */ +#include <linux/uaccess.h> -#include <asm/uaccess.h> #include <asm/pgalloc.h> #include <asm/hardirq.h> #include <asm/cpu-regs.h> @@ -168,7 +168,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long fault_code, * If we're in an interrupt or have no user * context, we must not take the fault.. */ - if (in_atomic() || !mm) + if (faulthandler_disabled() || !mm) goto no_context; if ((fault_code & MMUFCR_xFC_ACCESS) == MMUFCR_xFC_ACCESS_USR) diff --git a/arch/nios2/mm/fault.c b/arch/nios2/mm/fault.c index 0c9b6afe69e9..b51878b0c6b8 100644 --- a/arch/nios2/mm/fault.c +++ b/arch/nios2/mm/fault.c @@ -77,7 +77,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long cause, * If we're in an interrupt or have no user * context, we must not take the fault.. */ - if (in_atomic() || !mm) + if (faulthandler_disabled() || !mm) goto bad_area_nosemaphore; if (user_mode(regs)) diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h index de65f66ea64e..ec2df4bab302 100644 --- a/arch/parisc/include/asm/cacheflush.h +++ b/arch/parisc/include/asm/cacheflush.h @@ -142,6 +142,7 @@ static inline void kunmap(struct page *page) static inline void *kmap_atomic(struct page *page) { + preempt_disable(); pagefault_disable(); return page_address(page); } @@ -150,6 +151,7 @@ static inline void __kunmap_atomic(void *addr) { flush_kernel_dcache_page_addr(addr); pagefault_enable(); + preempt_enable(); } #define kmap_atomic_prot(page, prot) kmap_atomic(page) diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c index 47ee620d15d2..6548fd1d2e62 100644 --- a/arch/parisc/kernel/traps.c +++ b/arch/parisc/kernel/traps.c @@ -26,9 +26,9 @@ #include <linux/console.h> #include <linux/bug.h> #include <linux/ratelimit.h> +#include <linux/uaccess.h> #include <asm/assembly.h> -#include <asm/uaccess.h> #include <asm/io.h> #include <asm/irq.h> #include <asm/traps.h> @@ -800,7 +800,7 @@ void notrace handle_interruption(int code, struct pt_regs *regs) * unless pagefault_disable() was called before. */ - if (fault_space == 0 && !in_atomic()) + if (fault_space == 0 && !faulthandler_disabled()) { pdc_chassis_send_status(PDC_CHASSIS_DIRECT_PANIC); parisc_terminate("Kernel Fault", regs, code, fault_address); diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index e5120e653240..15503adddf4f 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -15,8 +15,8 @@ #include <linux/sched.h> #include <linux/interrupt.h> #include <linux/module.h> +#include <linux/uaccess.h> -#include <asm/uaccess.h> #include <asm/traps.h> /* Various important other fields */ @@ -207,7 +207,7 @@ void do_page_fault(struct pt_regs *regs, unsigned long code, int fault; unsigned int flags; - if (in_atomic()) + if (pagefault_disabled()) goto no_context; tsk = current; diff --git a/arch/powerpc/include/asm/barrier.h b/arch/powerpc/include/asm/barrier.h index 39505d660a70..51ccc7232042 100644 --- a/arch/powerpc/include/asm/barrier.h +++ b/arch/powerpc/include/asm/barrier.h @@ -89,5 +89,6 @@ do { \ #define smp_mb__before_atomic() smp_mb() #define smp_mb__after_atomic() smp_mb() +#define smp_mb__before_spinlock() smp_mb() #endif /* _ASM_POWERPC_BARRIER_H */ diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index 5f1048eaa5b6..8b3b46b7b0f2 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -87,7 +87,7 @@ static inline int prrn_is_enabled(void) #include <asm/smp.h> #define topology_physical_package_id(cpu) (cpu_to_chip_id(cpu)) -#define topology_thread_cpumask(cpu) (per_cpu(cpu_sibling_map, cpu)) +#define topology_sibling_cpumask(cpu) (per_cpu(cpu_sibling_map, cpu)) #define topology_core_cpumask(cpu) (per_cpu(cpu_core_map, cpu)) #define topology_core_id(cpu) (cpu_to_core_id(cpu)) #endif diff --git a/arch/powerpc/lib/vmx-helper.c b/arch/powerpc/lib/vmx-helper.c index 3cf529ceec5b..ac93a3bd2730 100644 --- a/arch/powerpc/lib/vmx-helper.c +++ b/arch/powerpc/lib/vmx-helper.c @@ -27,11 +27,11 @@ int enter_vmx_usercopy(void) if (in_interrupt()) return 0; - /* This acts as preempt_disable() as well and will make - * enable_kernel_altivec(). We need to disable page faults - * as they can call schedule and thus make us lose the VMX - * context. So on page faults, we just fail which will cause - * a fallback to the normal non-vmx copy. + preempt_disable(); + /* + * We need to disable page faults as they can call schedule and + * thus make us lose the VMX context. So on page faults, we just + * fail which will cause a fallback to the normal non-vmx copy. */ pagefault_disable(); @@ -47,6 +47,7 @@ int enter_vmx_usercopy(void) int exit_vmx_usercopy(void) { pagefault_enable(); + preempt_enable(); return 0; } diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index b396868d2aa7..6d535973b200 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -33,13 +33,13 @@ #include <linux/ratelimit.h> #include <linux/context_tracking.h> #include <linux/hugetlb.h> +#include <linux/uaccess.h> #include <asm/firmware.h> #include <asm/page.h> #include <asm/pgtable.h> #include <asm/mmu.h> #include <asm/mmu_context.h> -#include <asm/uaccess.h> #include <asm/tlbflush.h> #include <asm/siginfo.h> #include <asm/debug.h> @@ -272,15 +272,16 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address, if (!arch_irq_disabled_regs(regs)) local_irq_enable(); - if (in_atomic() || mm == NULL) { + if (faulthandler_disabled() || mm == NULL) { if (!user_mode(regs)) { rc = SIGSEGV; goto bail; } - /* in_atomic() in user mode is really bad, + /* faulthandler_disabled() in user mode is really bad, as is current->mm == NULL. */ printk(KERN_EMERG "Page fault in user mode with " - "in_atomic() = %d mm = %p\n", in_atomic(), mm); + "faulthandler_disabled() = %d mm = %p\n", + faulthandler_disabled(), mm); printk(KERN_EMERG "NIP = %lx MSR = %lx\n", regs->nip, regs->msr); die("Weird page fault", regs, SIGSEGV); diff --git a/arch/powerpc/mm/highmem.c b/arch/powerpc/mm/highmem.c index e7450bdbe83a..e292c8a60952 100644 --- a/arch/powerpc/mm/highmem.c +++ b/arch/powerpc/mm/highmem.c @@ -34,7 +34,7 @@ void *kmap_atomic_prot(struct page *page, pgprot_t prot) unsigned long vaddr; int idx, type; - /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */ + preempt_disable(); pagefault_disable(); if (!PageHighMem(page)) return page_address(page); @@ -59,6 +59,7 @@ void __kunmap_atomic(void *kvaddr) if (vaddr < __fix_to_virt(FIX_KMAP_END)) { pagefault_enable(); + preempt_enable(); return; } @@ -82,5 +83,6 @@ void __kunmap_atomic(void *kvaddr) kmap_atomic_idx_pop(); pagefault_enable(); + preempt_enable(); } EXPORT_SYMBOL(__kunmap_atomic); diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c index cbd3d069897f..723a099f6be3 100644 --- a/arch/powerpc/mm/tlb_nohash.c +++ b/arch/powerpc/mm/tlb_nohash.c @@ -217,7 +217,7 @@ static DEFINE_RAW_SPINLOCK(tlbivax_lock); static int mm_is_core_local(struct mm_struct *mm) { return cpumask_subset(mm_cpumask(mm), - topology_thread_cpumask(smp_processor_id())); + topology_sibling_cpumask(smp_processor_id())); } struct tlb_flush_param { diff --git a/arch/s390/include/asm/topology.h b/arch/s390/include/asm/topology.h index b1453a2ae1ca..4990f6c66288 100644 --- a/arch/s390/include/asm/topology.h +++ b/arch/s390/include/asm/topology.h @@ -22,7 +22,8 @@ DECLARE_PER_CPU(struct cpu_topology_s390, cpu_topology); #define topology_physical_package_id(cpu) (per_cpu(cpu_topology, cpu).socket_id) #define topology_thread_id(cpu) (per_cpu(cpu_topology, cpu).thread_id) -#define topology_thread_cpumask(cpu) (&per_cpu(cpu_topology, cpu).thread_mask) +#define topology_sibling_cpumask(cpu) \ + (&per_cpu(cpu_topology, cpu).thread_mask) #define topology_core_id(cpu) (per_cpu(cpu_topology, cpu).core_id) #define topology_core_cpumask(cpu) (&per_cpu(cpu_topology, cpu).core_mask) #define topology_book_id(cpu) (per_cpu(cpu_topology, cpu).book_id) diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h index d64a7a62164f..9dd4cc47ddc7 100644 --- a/arch/s390/include/asm/uaccess.h +++ b/arch/s390/include/asm/uaccess.h @@ -98,7 +98,8 @@ static inline unsigned long extable_fixup(const struct exception_table_entry *x) * @from: Source address, in user space. * @n: Number of bytes to copy. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * Copy data from user space to kernel space. Caller must check * the specified block with access_ok() before calling this function. @@ -118,7 +119,8 @@ unsigned long __must_check __copy_from_user(void *to, const void __user *from, * @from: Source address, in kernel space. * @n: Number of bytes to copy. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * Copy data from kernel space to user space. Caller must check * the specified block with access_ok() before calling this function. @@ -264,7 +266,8 @@ int __get_user_bad(void) __attribute__((noreturn)); * @from: Source address, in kernel space. * @n: Number of bytes to copy. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * Copy data from kernel space to user space. * @@ -290,7 +293,8 @@ __compiletime_warning("copy_from_user() buffer size is not provably correct") * @from: Source address, in user space. * @n: Number of bytes to copy. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * Copy data from user space to kernel space. * @@ -348,7 +352,8 @@ static inline unsigned long strnlen_user(const char __user *src, unsigned long n * strlen_user: - Get the size of a string in user space. * @str: The string to measure. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * Get the size of a NUL-terminated string in user space. * diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index 76515bcea2f1..4c8f5d7f9c23 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -399,7 +399,7 @@ static inline int do_exception(struct pt_regs *regs, int access) * user context. */ fault = VM_FAULT_BADCONTEXT; - if (unlikely(!user_space_fault(regs) || in_atomic() || !mm)) + if (unlikely(!user_space_fault(regs) || faulthandler_disabled() || !mm)) goto out; address = trans_exc_code & __FAIL_ADDR_MASK; diff --git a/arch/s390/net/bpf_jit.h b/arch/s390/net/bpf_jit.h index ba8593a515ba..de156ba3bd71 100644 --- a/arch/s390/net/bpf_jit.h +++ b/arch/s390/net/bpf_jit.h @@ -48,7 +48,9 @@ extern u8 sk_load_word[], sk_load_half[], sk_load_byte[]; * We get 160 bytes stack space from calling function, but only use * 11 * 8 byte (old backchain + r15 - r6) for storing registers. */ -#define STK_OFF (MAX_BPF_STACK + 8 + 4 + 4 + (160 - 11 * 8)) +#define STK_SPACE (MAX_BPF_STACK + 8 + 4 + 4 + 160) +#define STK_160_UNUSED (160 - 11 * 8) +#define STK_OFF (STK_SPACE - STK_160_UNUSED) #define STK_OFF_TMP 160 /* Offset of tmp buffer on stack */ #define STK_OFF_HLEN 168 /* Offset of SKB header length on stack */ diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index 20c146d1251a..55423d8be580 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -384,13 +384,16 @@ static void bpf_jit_prologue(struct bpf_jit *jit) } /* Setup stack and backchain */ if (jit->seen & SEEN_STACK) { - /* lgr %bfp,%r15 (BPF frame pointer) */ - EMIT4(0xb9040000, BPF_REG_FP, REG_15); + if (jit->seen & SEEN_FUNC) + /* lgr %w1,%r15 (backchain) */ + EMIT4(0xb9040000, REG_W1, REG_15); + /* la %bfp,STK_160_UNUSED(%r15) (BPF frame pointer) */ + EMIT4_DISP(0x41000000, BPF_REG_FP, REG_15, STK_160_UNUSED); /* aghi %r15,-STK_OFF */ EMIT4_IMM(0xa70b0000, REG_15, -STK_OFF); if (jit->seen & SEEN_FUNC) - /* stg %bfp,152(%r15) (backchain) */ - EMIT6_DISP_LH(0xe3000000, 0x0024, BPF_REG_FP, REG_0, + /* stg %w1,152(%r15) (backchain) */ + EMIT6_DISP_LH(0xe3000000, 0x0024, REG_W1, REG_0, REG_15, 152); } /* diff --git a/arch/score/include/asm/uaccess.h b/arch/score/include/asm/uaccess.h index ab66ddde777b..20a3591225cc 100644 --- a/arch/score/include/asm/uaccess.h +++ b/arch/score/include/asm/uaccess.h @@ -36,7 +36,8 @@ * @addr: User space pointer to start of block to check * @size: Size of block to check * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * Checks if a pointer to a block of memory in user space is valid. * @@ -61,7 +62,8 @@ * @x: Value to copy to user space. * @ptr: Destination address, in user space. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * This macro copies a single simple value from kernel space to user * space. It supports simple types like char and int, but not larger @@ -79,7 +81,8 @@ * @x: Variable to store result. * @ptr: Source address, in user space. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * This macro copies a single simple variable from user space to kernel * space. It supports simple types like char and int, but not larger @@ -98,7 +101,8 @@ * @x: Value to copy to user space. * @ptr: Destination address, in user space. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * This macro copies a single simple value from kernel space to user * space. It supports simple types like char and int, but not larger @@ -119,7 +123,8 @@ * @x: Variable to store result. * @ptr: Source address, in user space. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * This macro copies a single simple variable from user space to kernel * space. It supports simple types like char and int, but not larger diff --git a/arch/score/lib/string.S b/arch/score/lib/string.S index 00b7d3a2fc60..16efa3ad037f 100644 --- a/arch/score/lib/string.S +++ b/arch/score/lib/string.S @@ -175,10 +175,10 @@ ENTRY(__clear_user) br r3 .section .fixup, "ax" +99: br r3 .previous .section __ex_table, "a" .align 2 -99: .word 0b, 99b .previous diff --git a/arch/score/mm/fault.c b/arch/score/mm/fault.c index 6860beb2a280..37a6c2e0e969 100644 --- a/arch/score/mm/fault.c +++ b/arch/score/mm/fault.c @@ -34,6 +34,7 @@ #include <linux/string.h> #include <linux/types.h> #include <linux/ptrace.h> +#include <linux/uaccess.h> /* * This routine handles page faults. It determines the address, @@ -73,7 +74,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long write, * If we're in an interrupt or have no user * context, we must not take the fault.. */ - if (in_atomic() || !mm) + if (pagefault_disabled() || !mm) goto bad_area_nosemaphore; if (user_mode(regs)) diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c index a58fec9b55e0..79d8276377d1 100644 --- a/arch/sh/mm/fault.c +++ b/arch/sh/mm/fault.c @@ -17,6 +17,7 @@ #include <linux/kprobes.h> #include <linux/perf_event.h> #include <linux/kdebug.h> +#include <linux/uaccess.h> #include <asm/io_trapped.h> #include <asm/mmu_context.h> #include <asm/tlbflush.h> @@ -438,9 +439,9 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs, /* * If we're in an interrupt, have no user context or are running - * in an atomic region then we must not take the fault: + * with pagefaults disabled then we must not take the fault: */ - if (unlikely(in_atomic() || !mm)) { + if (unlikely(faulthandler_disabled() || !mm)) { bad_area_nosemaphore(regs, error_code, address); return; } diff --git a/arch/sparc/include/asm/topology_64.h b/arch/sparc/include/asm/topology_64.h index d1761df5cca6..01d17046225a 100644 --- a/arch/sparc/include/asm/topology_64.h +++ b/arch/sparc/include/asm/topology_64.h @@ -41,7 +41,7 @@ static inline int pcibus_to_node(struct pci_bus *pbus) #define topology_physical_package_id(cpu) (cpu_data(cpu).proc_id) #define topology_core_id(cpu) (cpu_data(cpu).core_id) #define topology_core_cpumask(cpu) (&cpu_core_sib_map[cpu]) -#define topology_thread_cpumask(cpu) (&per_cpu(cpu_sibling_map, cpu)) +#define topology_sibling_cpumask(cpu) (&per_cpu(cpu_sibling_map, cpu)) #endif /* CONFIG_SMP */ extern cpumask_t cpu_core_map[NR_CPUS]; diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c index 70d817154fe8..c399e7b3b035 100644 --- a/arch/sparc/mm/fault_32.c +++ b/arch/sparc/mm/fault_32.c @@ -21,6 +21,7 @@ #include <linux/perf_event.h> #include <linux/interrupt.h> #include <linux/kdebug.h> +#include <linux/uaccess.h> #include <asm/page.h> #include <asm/pgtable.h> @@ -29,7 +30,6 @@ #include <asm/setup.h> #include <asm/smp.h> #include <asm/traps.h> -#include <asm/uaccess.h> #include "mm_32.h" @@ -196,7 +196,7 @@ asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write, * If we're in an interrupt or have no user * context, we must not take the fault.. */ - if (in_atomic() || !mm) + if (pagefault_disabled() || !mm) goto no_context; perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c index 479823249429..e9268ea1a68d 100644 --- a/arch/sparc/mm/fault_64.c +++ b/arch/sparc/mm/fault_64.c @@ -22,12 +22,12 @@ #include <linux/kdebug.h> #include <linux/percpu.h> #include <linux/context_tracking.h> +#include <linux/uaccess.h> #include <asm/page.h> #include <asm/pgtable.h> #include <asm/openprom.h> #include <asm/oplib.h> -#include <asm/uaccess.h> #include <asm/asi.h> #include <asm/lsu.h> #include <asm/sections.h> @@ -330,7 +330,7 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs) * If we're in an interrupt or have no user * context, we must not take the fault.. */ - if (in_atomic() || !mm) + if (faulthandler_disabled() || !mm) goto intr_or_no_mm; perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); diff --git a/arch/sparc/mm/highmem.c b/arch/sparc/mm/highmem.c index 449f864f0cef..a454ec5ff07a 100644 --- a/arch/sparc/mm/highmem.c +++ b/arch/sparc/mm/highmem.c @@ -53,7 +53,7 @@ void *kmap_atomic(struct page *page) unsigned long vaddr; long idx, type; - /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */ + preempt_disable(); pagefault_disable(); if (!PageHighMem(page)) return page_address(page); @@ -91,6 +91,7 @@ void __kunmap_atomic(void *kvaddr) if (vaddr < FIXADDR_START) { // FIXME pagefault_enable(); + preempt_enable(); return; } @@ -126,5 +127,6 @@ void __kunmap_atomic(void *kvaddr) kmap_atomic_idx_pop(); pagefault_enable(); + preempt_enable(); } EXPORT_SYMBOL(__kunmap_atomic); diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 559cb744112c..c5d08b89a96c 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -2738,7 +2738,7 @@ void hugetlb_setup(struct pt_regs *regs) struct mm_struct *mm = current->mm; struct tsb_config *tp; - if (in_atomic() || !mm) { + if (faulthandler_disabled() || !mm) { const struct exception_table_entry *entry; entry = search_exception_tables(regs->tpc); diff --git a/arch/tile/include/asm/topology.h b/arch/tile/include/asm/topology.h index 938311844233..76b0d0ebb244 100644 --- a/arch/tile/include/asm/topology.h +++ b/arch/tile/include/asm/topology.h @@ -55,7 +55,7 @@ static inline const struct cpumask *cpumask_of_node(int node) #define topology_physical_package_id(cpu) ((void)(cpu), 0) #define topology_core_id(cpu) (cpu) #define topology_core_cpumask(cpu) ((void)(cpu), cpu_online_mask) -#define topology_thread_cpumask(cpu) cpumask_of(cpu) +#define topology_sibling_cpumask(cpu) cpumask_of(cpu) #endif #endif /* _ASM_TILE_TOPOLOGY_H */ diff --git a/arch/tile/include/asm/uaccess.h b/arch/tile/include/asm/uaccess.h index f41cb53cf645..a33276bf5ca1 100644 --- a/arch/tile/include/asm/uaccess.h +++ b/arch/tile/include/asm/uaccess.h @@ -78,7 +78,8 @@ int __range_ok(unsigned long addr, unsigned long size); * @addr: User space pointer to start of block to check * @size: Size of block to check * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * Checks if a pointer to a block of memory in user space is valid. * @@ -192,7 +193,8 @@ extern int __get_user_bad(void) * @x: Variable to store result. * @ptr: Source address, in user space. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * This macro copies a single simple variable from user space to kernel * space. It supports simple types like char and int, but not larger @@ -274,7 +276,8 @@ extern int __put_user_bad(void) * @x: Value to copy to user space. * @ptr: Destination address, in user space. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * This macro copies a single simple value from kernel space to user * space. It supports simple types like char and int, but not larger @@ -330,7 +333,8 @@ extern int __put_user_bad(void) * @from: Source address, in kernel space. * @n: Number of bytes to copy. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * Copy data from kernel space to user space. Caller must check * the specified block with access_ok() before calling this function. @@ -366,7 +370,8 @@ copy_to_user(void __user *to, const void *from, unsigned long n) * @from: Source address, in user space. * @n: Number of bytes to copy. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * Copy data from user space to kernel space. Caller must check * the specified block with access_ok() before calling this function. @@ -437,7 +442,8 @@ static inline unsigned long __must_check copy_from_user(void *to, * @from: Source address, in user space. * @n: Number of bytes to copy. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * Copy data from user space to user space. Caller must check * the specified blocks with access_ok() before calling this function. diff --git a/arch/tile/mm/fault.c b/arch/tile/mm/fault.c index e83cc999da02..3f4f58d34a92 100644 --- a/arch/tile/mm/fault.c +++ b/arch/tile/mm/fault.c @@ -354,9 +354,9 @@ static int handle_page_fault(struct pt_regs *regs, /* * If we're in an interrupt, have no user context or are running in an - * atomic region then we must not take the fault. + * region with pagefaults disabled then we must not take the fault. */ - if (in_atomic() || !mm) { + if (pagefault_disabled() || !mm) { vma = NULL; /* happy compiler */ goto bad_area_nosemaphore; } diff --git a/arch/tile/mm/highmem.c b/arch/tile/mm/highmem.c index 6aa2f2625447..fcd545014e79 100644 --- a/arch/tile/mm/highmem.c +++ b/arch/tile/mm/highmem.c @@ -201,7 +201,7 @@ void *kmap_atomic_prot(struct page *page, pgprot_t prot) int idx, type; pte_t *pte; - /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */ + preempt_disable(); pagefault_disable(); /* Avoid icache flushes by disallowing atomic executable mappings. */ @@ -259,6 +259,7 @@ void __kunmap_atomic(void *kvaddr) } pagefault_enable(); + preempt_enable(); } EXPORT_SYMBOL(__kunmap_atomic); diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c index 8e4daf44e980..47ff9b7f3e5d 100644 --- a/arch/um/kernel/trap.c +++ b/arch/um/kernel/trap.c @@ -7,6 +7,7 @@ #include <linux/sched.h> #include <linux/hardirq.h> #include <linux/module.h> +#include <linux/uaccess.h> #include <asm/current.h> #include <asm/pgtable.h> #include <asm/tlbflush.h> @@ -35,10 +36,10 @@ int handle_page_fault(unsigned long address, unsigned long ip, *code_out = SEGV_MAPERR; /* - * If the fault was during atomic operation, don't take the fault, just + * If the fault was with pagefaults disabled, don't take the fault, just * fail. */ - if (in_atomic()) + if (faulthandler_disabled()) goto out_nosemaphore; if (is_user) diff --git a/arch/unicore32/mm/fault.c b/arch/unicore32/mm/fault.c index 0dc922dba915..afccef5529cc 100644 --- a/arch/unicore32/mm/fault.c +++ b/arch/unicore32/mm/fault.c @@ -218,7 +218,7 @@ static int do_pf(unsigned long addr, unsigned int fsr, struct pt_regs *regs) * If we're in an interrupt or have no user * context, we must not take the fault.. */ - if (in_atomic() || !mm) + if (faulthandler_disabled() || !mm) goto no_context; if (user_mode(regs)) diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index a5973f851750..a15893d17c55 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -332,6 +332,18 @@ config X86_DEBUG_STATIC_CPU_HAS If unsure, say N. +config X86_DEBUG_FPU + bool "Debug the x86 FPU code" + depends on DEBUG_KERNEL + default y + ---help--- + If this option is enabled then there will be extra sanity + checks and (boot time) debug printouts added to the kernel. + This debugging adds some small amount of runtime overhead + to the kernel. + + If unsure, say N. + config PUNIT_ATOM_DEBUG tristate "ATOM Punit debug driver" select DEBUG_FS diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index 89dd0d78013a..805d25ca5f1d 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -2,15 +2,14 @@ #define BOOT_COMPRESSED_MISC_H /* - * we have to be careful, because no indirections are allowed here, and - * paravirt_ops is a kind of one. As it will only run in baremetal anyway, - * we just keep it from happening + * Special hack: we have to be careful, because no indirections are allowed here, + * and paravirt_ops is a kind of one. As it will only run in baremetal anyway, + * we just keep it from happening. (This list needs to be extended when new + * paravirt and debugging variants are added.) */ #undef CONFIG_PARAVIRT +#undef CONFIG_PARAVIRT_SPINLOCKS #undef CONFIG_KASAN -#ifdef CONFIG_X86_32 -#define _ASM_X86_DESC_H 1 -#endif #include <linux/linkage.h> #include <linux/screen_info.h> diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c index 112cefacf2af..b419f43ce0c5 100644 --- a/arch/x86/crypto/aesni-intel_glue.c +++ b/arch/x86/crypto/aesni-intel_glue.c @@ -32,7 +32,7 @@ #include <crypto/lrw.h> #include <crypto/xts.h> #include <asm/cpu_device_id.h> -#include <asm/i387.h> +#include <asm/fpu/api.h> #include <asm/crypto/aes.h> #include <crypto/ablk_helper.h> #include <crypto/scatterwalk.h> diff --git a/arch/x86/crypto/camellia_aesni_avx2_glue.c b/arch/x86/crypto/camellia_aesni_avx2_glue.c index baf0ac21ace5..4c65c70e628b 100644 --- a/arch/x86/crypto/camellia_aesni_avx2_glue.c +++ b/arch/x86/crypto/camellia_aesni_avx2_glue.c @@ -19,8 +19,7 @@ #include <crypto/ctr.h> #include <crypto/lrw.h> #include <crypto/xts.h> -#include <asm/xcr.h> -#include <asm/xsave.h> +#include <asm/fpu/api.h> #include <asm/crypto/camellia.h> #include <asm/crypto/glue_helper.h> @@ -561,16 +560,15 @@ static struct crypto_alg cmll_algs[10] = { { static int __init camellia_aesni_init(void) { - u64 xcr0; + const char *feature_name; if (!cpu_has_avx2 || !cpu_has_avx || !cpu_has_aes || !cpu_has_osxsave) { pr_info("AVX2 or AES-NI instructions are not detected.\n"); return -ENODEV; } - xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); - if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) { - pr_info("AVX2 detected but unusable.\n"); + if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) { + pr_info("CPU feature '%s' is not supported.\n", feature_name); return -ENODEV; } diff --git a/arch/x86/crypto/camellia_aesni_avx_glue.c b/arch/x86/crypto/camellia_aesni_avx_glue.c index 78818a1e73e3..80a0e4389c9a 100644 --- a/arch/x86/crypto/camellia_aesni_avx_glue.c +++ b/arch/x86/crypto/camellia_aesni_avx_glue.c @@ -19,8 +19,7 @@ #include <crypto/ctr.h> #include <crypto/lrw.h> #include <crypto/xts.h> -#include <asm/xcr.h> -#include <asm/xsave.h> +#include <asm/fpu/api.h> #include <asm/crypto/camellia.h> #include <asm/crypto/glue_helper.h> @@ -553,16 +552,10 @@ static struct crypto_alg cmll_algs[10] = { { static int __init camellia_aesni_init(void) { - u64 xcr0; + const char *feature_name; - if (!cpu_has_avx || !cpu_has_aes || !cpu_has_osxsave) { - pr_info("AVX or AES-NI instructions are not detected.\n"); - return -ENODEV; - } - - xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); - if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) { - pr_info("AVX detected but unusable.\n"); + if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) { + pr_info("CPU feature '%s' is not supported.\n", feature_name); return -ENODEV; } diff --git a/arch/x86/crypto/cast5_avx_glue.c b/arch/x86/crypto/cast5_avx_glue.c index 236c80974457..be00aa48b2b5 100644 --- a/arch/x86/crypto/cast5_avx_glue.c +++ b/arch/x86/crypto/cast5_avx_glue.c @@ -31,8 +31,7 @@ #include <crypto/cast5.h> #include <crypto/cryptd.h> #include <crypto/ctr.h> -#include <asm/xcr.h> -#include <asm/xsave.h> +#include <asm/fpu/api.h> #include <asm/crypto/glue_helper.h> #define CAST5_PARALLEL_BLOCKS 16 @@ -468,16 +467,10 @@ static struct crypto_alg cast5_algs[6] = { { static int __init cast5_init(void) { - u64 xcr0; + const char *feature_name; - if (!cpu_has_avx || !cpu_has_osxsave) { - pr_info("AVX instructions are not detected.\n"); - return -ENODEV; - } - - xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); - if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) { - pr_info("AVX detected but unusable.\n"); + if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) { + pr_info("CPU feature '%s' is not supported.\n", feature_name); return -ENODEV; } diff --git a/arch/x86/crypto/cast6_avx_glue.c b/arch/x86/crypto/cast6_avx_glue.c index f448810ca4ac..5dbba7224221 100644 --- a/arch/x86/crypto/cast6_avx_glue.c +++ b/arch/x86/crypto/cast6_avx_glue.c @@ -36,8 +36,7 @@ #include <crypto/ctr.h> #include <crypto/lrw.h> #include <crypto/xts.h> -#include <asm/xcr.h> -#include <asm/xsave.h> +#include <asm/fpu/api.h> #include <asm/crypto/glue_helper.h> #define CAST6_PARALLEL_BLOCKS 8 @@ -590,16 +589,10 @@ static struct crypto_alg cast6_algs[10] = { { static int __init cast6_init(void) { - u64 xcr0; + const char *feature_name; - if (!cpu_has_avx || !cpu_has_osxsave) { - pr_info("AVX instructions are not detected.\n"); - return -ENODEV; - } - - xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); - if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) { - pr_info("AVX detected but unusable.\n"); + if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) { + pr_info("CPU feature '%s' is not supported.\n", feature_name); return -ENODEV; } diff --git a/arch/x86/crypto/crc32-pclmul_glue.c b/arch/x86/crypto/crc32-pclmul_glue.c index 1937fc1d8763..07d2c6c86a54 100644 --- a/arch/x86/crypto/crc32-pclmul_glue.c +++ b/arch/x86/crypto/crc32-pclmul_glue.c @@ -35,7 +35,7 @@ #include <asm/cpufeature.h> #include <asm/cpu_device_id.h> -#include <asm/i387.h> +#include <asm/fpu/api.h> #define CHKSUM_BLOCK_SIZE 1 #define CHKSUM_DIGEST_SIZE 4 diff --git a/arch/x86/crypto/crc32c-intel_glue.c b/arch/x86/crypto/crc32c-intel_glue.c index 28640c3d6af7..81a595d75cf5 100644 --- a/arch/x86/crypto/crc32c-intel_glue.c +++ b/arch/x86/crypto/crc32c-intel_glue.c @@ -32,8 +32,7 @@ #include <asm/cpufeature.h> #include <asm/cpu_device_id.h> -#include <asm/i387.h> -#include <asm/fpu-internal.h> +#include <asm/fpu/internal.h> #define CHKSUM_BLOCK_SIZE 1 #define CHKSUM_DIGEST_SIZE 4 diff --git a/arch/x86/crypto/crct10dif-pclmul_glue.c b/arch/x86/crypto/crct10dif-pclmul_glue.c index b6c67bf30fdf..a3fcfc97a311 100644 --- a/arch/x86/crypto/crct10dif-pclmul_glue.c +++ b/arch/x86/crypto/crct10dif-pclmul_glue.c @@ -29,7 +29,7 @@ #include <linux/init.h> #include <linux/string.h> #include <linux/kernel.h> -#include <asm/i387.h> +#include <asm/fpu/api.h> #include <asm/cpufeature.h> #include <asm/cpu_device_id.h> diff --git a/arch/x86/crypto/fpu.c b/arch/x86/crypto/fpu.c index f368ba261739..5a2f30f9f52d 100644 --- a/arch/x86/crypto/fpu.c +++ b/arch/x86/crypto/fpu.c @@ -18,7 +18,7 @@ #include <linux/module.h> #include <linux/slab.h> #include <linux/crypto.h> -#include <asm/i387.h> +#include <asm/fpu/api.h> struct crypto_fpu_ctx { struct crypto_blkcipher *child; diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c index 2079baf06bdd..64d7cf1b50e1 100644 --- a/arch/x86/crypto/ghash-clmulni-intel_glue.c +++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c @@ -19,7 +19,7 @@ #include <crypto/cryptd.h> #include <crypto/gf128mul.h> #include <crypto/internal/hash.h> -#include <asm/i387.h> +#include <asm/fpu/api.h> #include <asm/cpu_device_id.h> #define GHASH_BLOCK_SIZE 16 diff --git a/arch/x86/crypto/serpent_avx2_glue.c b/arch/x86/crypto/serpent_avx2_glue.c index 2f63dc89e7a9..7d838dc4d888 100644 --- a/arch/x86/crypto/serpent_avx2_glue.c +++ b/arch/x86/crypto/serpent_avx2_glue.c @@ -20,8 +20,7 @@ #include <crypto/lrw.h> #include <crypto/xts.h> #include <crypto/serpent.h> -#include <asm/xcr.h> -#include <asm/xsave.h> +#include <asm/fpu/api.h> #include <asm/crypto/serpent-avx.h> #include <asm/crypto/glue_helper.h> @@ -537,16 +536,14 @@ static struct crypto_alg srp_algs[10] = { { static int __init init(void) { - u64 xcr0; + const char *feature_name; if (!cpu_has_avx2 || !cpu_has_osxsave) { pr_info("AVX2 instructions are not detected.\n"); return -ENODEV; } - - xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); - if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) { - pr_info("AVX detected but unusable.\n"); + if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) { + pr_info("CPU feature '%s' is not supported.\n", feature_name); return -ENODEV; } diff --git a/arch/x86/crypto/serpent_avx_glue.c b/arch/x86/crypto/serpent_avx_glue.c index c8d478af8456..da7dafc9b16d 100644 --- a/arch/x86/crypto/serpent_avx_glue.c +++ b/arch/x86/crypto/serpent_avx_glue.c @@ -36,8 +36,7 @@ #include <crypto/ctr.h> #include <crypto/lrw.h> #include <crypto/xts.h> -#include <asm/xcr.h> -#include <asm/xsave.h> +#include <asm/fpu/api.h> #include <asm/crypto/serpent-avx.h> #include <asm/crypto/glue_helper.h> @@ -596,16 +595,10 @@ static struct crypto_alg serpent_algs[10] = { { static int __init serpent_init(void) { - u64 xcr0; + const char *feature_name; - if (!cpu_has_avx || !cpu_has_osxsave) { - printk(KERN_INFO "AVX instructions are not detected.\n"); - return -ENODEV; - } - - xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); - if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) { - printk(KERN_INFO "AVX detected but unusable.\n"); + if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) { + pr_info("CPU feature '%s' is not supported.\n", feature_name); return -ENODEV; } diff --git a/arch/x86/crypto/sha-mb/sha1_mb.c b/arch/x86/crypto/sha-mb/sha1_mb.c index e510b1c5d690..f53ed1dc88ea 100644 --- a/arch/x86/crypto/sha-mb/sha1_mb.c +++ b/arch/x86/crypto/sha-mb/sha1_mb.c @@ -65,11 +65,8 @@ #include <crypto/mcryptd.h> #include <crypto/crypto_wq.h> #include <asm/byteorder.h> -#include <asm/i387.h> -#include <asm/xcr.h> -#include <asm/xsave.h> #include <linux/hardirq.h> -#include <asm/fpu-internal.h> +#include <asm/fpu/api.h> #include "sha_mb_ctx.h" #define FLUSH_INTERVAL 1000 /* in usec */ diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c index 33d1b9dc14cc..7c48e8b20848 100644 --- a/arch/x86/crypto/sha1_ssse3_glue.c +++ b/arch/x86/crypto/sha1_ssse3_glue.c @@ -29,9 +29,7 @@ #include <linux/types.h> #include <crypto/sha.h> #include <crypto/sha1_base.h> -#include <asm/i387.h> -#include <asm/xcr.h> -#include <asm/xsave.h> +#include <asm/fpu/api.h> asmlinkage void sha1_transform_ssse3(u32 *digest, const char *data, @@ -123,15 +121,9 @@ static struct shash_alg alg = { #ifdef CONFIG_AS_AVX static bool __init avx_usable(void) { - u64 xcr0; - - if (!cpu_has_avx || !cpu_has_osxsave) - return false; - - xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); - if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) { - pr_info("AVX detected but unusable.\n"); - + if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, NULL)) { + if (cpu_has_avx) + pr_info("AVX detected but unusable.\n"); return false; } diff --git a/arch/x86/crypto/sha256_ssse3_glue.c b/arch/x86/crypto/sha256_ssse3_glue.c index ccc338881ee8..f8097fc0d1d1 100644 --- a/arch/x86/crypto/sha256_ssse3_glue.c +++ b/arch/x86/crypto/sha256_ssse3_glue.c @@ -37,9 +37,7 @@ #include <linux/types.h> #include <crypto/sha.h> #include <crypto/sha256_base.h> -#include <asm/i387.h> -#include <asm/xcr.h> -#include <asm/xsave.h> +#include <asm/fpu/api.h> #include <linux/string.h> asmlinkage void sha256_transform_ssse3(u32 *digest, const char *data, @@ -132,15 +130,9 @@ static struct shash_alg algs[] = { { #ifdef CONFIG_AS_AVX static bool __init avx_usable(void) { - u64 xcr0; - - if (!cpu_has_avx || !cpu_has_osxsave) - return false; - - xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); - if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) { - pr_info("AVX detected but unusable.\n"); - + if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, NULL)) { + if (cpu_has_avx) + pr_info("AVX detected but unusable.\n"); return false; } diff --git a/arch/x86/crypto/sha512_ssse3_glue.c b/arch/x86/crypto/sha512_ssse3_glue.c index d9fa4c1e063f..2edad7b81870 100644 --- a/arch/x86/crypto/sha512_ssse3_glue.c +++ b/arch/x86/crypto/sha512_ssse3_glue.c @@ -35,9 +35,7 @@ #include <linux/types.h> #include <crypto/sha.h> #include <crypto/sha512_base.h> -#include <asm/i387.h> -#include <asm/xcr.h> -#include <asm/xsave.h> +#include <asm/fpu/api.h> #include <linux/string.h> @@ -131,15 +129,9 @@ static struct shash_alg algs[] = { { #ifdef CONFIG_AS_AVX static bool __init avx_usable(void) { - u64 xcr0; - - if (!cpu_has_avx || !cpu_has_osxsave) - return false; - - xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); - if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) { - pr_info("AVX detected but unusable.\n"); - + if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, NULL)) { + if (cpu_has_avx) + pr_info("AVX detected but unusable.\n"); return false; } diff --git a/arch/x86/crypto/twofish_avx_glue.c b/arch/x86/crypto/twofish_avx_glue.c index b5e2d5651851..c2bd0ce718ee 100644 --- a/arch/x86/crypto/twofish_avx_glue.c +++ b/arch/x86/crypto/twofish_avx_glue.c @@ -36,9 +36,7 @@ #include <crypto/ctr.h> #include <crypto/lrw.h> #include <crypto/xts.h> -#include <asm/i387.h> -#include <asm/xcr.h> -#include <asm/xsave.h> +#include <asm/fpu/api.h> #include <asm/crypto/twofish.h> #include <asm/crypto/glue_helper.h> #include <crypto/scatterwalk.h> @@ -558,16 +556,10 @@ static struct crypto_alg twofish_algs[10] = { { static int __init twofish_init(void) { - u64 xcr0; + const char *feature_name; - if (!cpu_has_avx || !cpu_has_osxsave) { - printk(KERN_INFO "AVX instructions are not detected.\n"); - return -ENODEV; - } - - xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); - if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) { - printk(KERN_INFO "AVX detected but unusable.\n"); + if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) { + pr_info("CPU feature '%s' is not supported.\n", feature_name); return -ENODEV; } diff --git a/arch/x86/entry/thunk_32.S b/arch/x86/entry/thunk_32.S index e9acf5f4fc92..e5a17114a8c4 100644 --- a/arch/x86/entry/thunk_32.S +++ b/arch/x86/entry/thunk_32.S @@ -35,8 +35,6 @@ #ifdef CONFIG_PREEMPT THUNK ___preempt_schedule, preempt_schedule -#ifdef CONFIG_CONTEXT_TRACKING - THUNK ___preempt_schedule_context, preempt_schedule_context -#endif + THUNK ___preempt_schedule_notrace, preempt_schedule_notrace #endif diff --git a/arch/x86/entry/thunk_64.S b/arch/x86/entry/thunk_64.S index 3e95681b4e2d..efb2b932b748 100644 --- a/arch/x86/entry/thunk_64.S +++ b/arch/x86/entry/thunk_64.S @@ -46,9 +46,7 @@ #ifdef CONFIG_PREEMPT THUNK ___preempt_schedule, preempt_schedule -#ifdef CONFIG_CONTEXT_TRACKING - THUNK ___preempt_schedule_context, preempt_schedule_context -#endif + THUNK ___preempt_schedule_notrace, preempt_schedule_notrace #endif #if defined(CONFIG_TRACE_IRQFLAGS) \ diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c index c81d35e6c7f1..ae3a29ae875b 100644 --- a/arch/x86/ia32/ia32_signal.c +++ b/arch/x86/ia32/ia32_signal.c @@ -21,8 +21,8 @@ #include <linux/binfmts.h> #include <asm/ucontext.h> #include <asm/uaccess.h> -#include <asm/i387.h> -#include <asm/fpu-internal.h> +#include <asm/fpu/internal.h> +#include <asm/fpu/signal.h> #include <asm/ptrace.h> #include <asm/ia32_unistd.h> #include <asm/user32.h> @@ -198,7 +198,7 @@ static int ia32_restore_sigcontext(struct pt_regs *regs, buf = compat_ptr(tmp); } get_user_catch(err); - err |= restore_xstate_sig(buf, 1); + err |= fpu__restore_sig(buf, 1); force_iret(); @@ -308,6 +308,7 @@ static void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, size_t frame_size, void __user **fpstate) { + struct fpu *fpu = ¤t->thread.fpu; unsigned long sp; /* Default to using normal stack */ @@ -322,12 +323,12 @@ static void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, ksig->ka.sa.sa_restorer) sp = (unsigned long) ksig->ka.sa.sa_restorer; - if (used_math()) { + if (fpu->fpstate_active) { unsigned long fx_aligned, math_size; - sp = alloc_mathframe(sp, 1, &fx_aligned, &math_size); + sp = fpu__alloc_mathframe(sp, 1, &fx_aligned, &math_size); *fpstate = (struct _fpstate_ia32 __user *) sp; - if (save_xstate_sig(*fpstate, (void __user *)fx_aligned, + if (copy_fpstate_to_sigframe(*fpstate, (void __user *)fx_aligned, math_size) < 0) return (void __user *) -1L; } diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index ba32af062f61..7bfc85bbb8ff 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -52,6 +52,12 @@ struct alt_instr { u8 padlen; /* length of build-time padding */ } __packed; +/* + * Debug flag that can be tested to see whether alternative + * instructions were patched in already: + */ +extern int alternatives_patched; + extern void alternative_instructions(void); extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end); diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h index aaac3b2fb746..1a5da2e63aee 100644 --- a/arch/x86/include/asm/amd_nb.h +++ b/arch/x86/include/asm/amd_nb.h @@ -98,11 +98,22 @@ static inline u16 amd_get_node_id(struct pci_dev *pdev) return 0; } +static inline bool amd_gart_present(void) +{ + /* GART present only on Fam15h, upto model 0fh */ + if (boot_cpu_data.x86 == 0xf || boot_cpu_data.x86 == 0x10 || + (boot_cpu_data.x86 == 0x15 && boot_cpu_data.x86_model < 0x10)) + return true; + + return false; +} + #else #define amd_nb_num(x) 0 #define amd_nb_has_feature(x) false #define node_to_amd_nb(x) NULL +#define amd_gart_present(x) false #endif diff --git a/arch/x86/include/asm/crypto/glue_helper.h b/arch/x86/include/asm/crypto/glue_helper.h index 1eef55596e82..03bb1065c335 100644 --- a/arch/x86/include/asm/crypto/glue_helper.h +++ b/arch/x86/include/asm/crypto/glue_helper.h @@ -7,7 +7,7 @@ #include <linux/kernel.h> #include <linux/crypto.h> -#include <asm/i387.h> +#include <asm/fpu/api.h> #include <crypto/b128ops.h> typedef void (*common_glue_func_t)(void *ctx, u8 *dst, const u8 *src); diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h index 808dae63eeea..1f5b7287d1ad 100644 --- a/arch/x86/include/asm/dma-mapping.h +++ b/arch/x86/include/asm/dma-mapping.h @@ -127,50 +127,14 @@ static inline gfp_t dma_alloc_coherent_gfp_flags(struct device *dev, gfp_t gfp) #define dma_alloc_coherent(d,s,h,f) dma_alloc_attrs(d,s,h,f,NULL) -static inline void * +void * dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle, - gfp_t gfp, struct dma_attrs *attrs) -{ - struct dma_map_ops *ops = get_dma_ops(dev); - void *memory; - - gfp &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32); - - if (dma_alloc_from_coherent(dev, size, dma_handle, &memory)) - return memory; - - if (!dev) - dev = &x86_dma_fallback_dev; - - if (!is_device_dma_capable(dev)) - return NULL; - - if (!ops->alloc) - return NULL; - - memory = ops->alloc(dev, size, dma_handle, - dma_alloc_coherent_gfp_flags(dev, gfp), attrs); - debug_dma_alloc_coherent(dev, size, *dma_handle, memory); - - return memory; -} + gfp_t gfp, struct dma_attrs *attrs); #define dma_free_coherent(d,s,c,h) dma_free_attrs(d,s,c,h,NULL) -static inline void dma_free_attrs(struct device *dev, size_t size, - void *vaddr, dma_addr_t bus, - struct dma_attrs *attrs) -{ - struct dma_map_ops *ops = get_dma_ops(dev); - - WARN_ON(irqs_disabled()); /* for portability */ - - if (dma_release_from_coherent(dev, get_order(size), vaddr)) - return; - - debug_dma_free_coherent(dev, size, vaddr, bus); - if (ops->free) - ops->free(dev, size, vaddr, bus, attrs); -} +void dma_free_attrs(struct device *dev, size_t size, + void *vaddr, dma_addr_t bus, + struct dma_attrs *attrs); #endif diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 3738b138b843..155162ea0e00 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -1,7 +1,7 @@ #ifndef _ASM_X86_EFI_H #define _ASM_X86_EFI_H -#include <asm/i387.h> +#include <asm/fpu/api.h> #include <asm/pgtable.h> /* diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h deleted file mode 100644 index da5e96756570..000000000000 --- a/arch/x86/include/asm/fpu-internal.h +++ /dev/null @@ -1,626 +0,0 @@ -/* - * Copyright (C) 1994 Linus Torvalds - * - * Pentium III FXSR, SSE support - * General FPU state handling cleanups - * Gareth Hughes <gareth@valinux.com>, May 2000 - * x86-64 work by Andi Kleen 2002 - */ - -#ifndef _FPU_INTERNAL_H -#define _FPU_INTERNAL_H - -#include <linux/kernel_stat.h> -#include <linux/regset.h> -#include <linux/compat.h> -#include <linux/slab.h> -#include <asm/asm.h> -#include <asm/cpufeature.h> -#include <asm/processor.h> -#include <asm/sigcontext.h> -#include <asm/user.h> -#include <asm/uaccess.h> -#include <asm/xsave.h> -#include <asm/smap.h> - -#ifdef CONFIG_X86_64 -# include <asm/sigcontext32.h> -# include <asm/user32.h> -struct ksignal; -int ia32_setup_rt_frame(int sig, struct ksignal *ksig, - compat_sigset_t *set, struct pt_regs *regs); -int ia32_setup_frame(int sig, struct ksignal *ksig, - compat_sigset_t *set, struct pt_regs *regs); -#else -# define user_i387_ia32_struct user_i387_struct -# define user32_fxsr_struct user_fxsr_struct -# define ia32_setup_frame __setup_frame -# define ia32_setup_rt_frame __setup_rt_frame -#endif - -extern unsigned int mxcsr_feature_mask; -extern void fpu_init(void); -extern void eager_fpu_init(void); - -DECLARE_PER_CPU(struct task_struct *, fpu_owner_task); - -extern void convert_from_fxsr(struct user_i387_ia32_struct *env, - struct task_struct *tsk); -extern void convert_to_fxsr(struct task_struct *tsk, - const struct user_i387_ia32_struct *env); - -extern user_regset_active_fn fpregs_active, xfpregs_active; -extern user_regset_get_fn fpregs_get, xfpregs_get, fpregs_soft_get, - xstateregs_get; -extern user_regset_set_fn fpregs_set, xfpregs_set, fpregs_soft_set, - xstateregs_set; - -/* - * xstateregs_active == fpregs_active. Please refer to the comment - * at the definition of fpregs_active. - */ -#define xstateregs_active fpregs_active - -#ifdef CONFIG_MATH_EMULATION -extern void finit_soft_fpu(struct i387_soft_struct *soft); -#else -static inline void finit_soft_fpu(struct i387_soft_struct *soft) {} -#endif - -/* - * Must be run with preemption disabled: this clears the fpu_owner_task, - * on this CPU. - * - * This will disable any lazy FPU state restore of the current FPU state, - * but if the current thread owns the FPU, it will still be saved by. - */ -static inline void __cpu_disable_lazy_restore(unsigned int cpu) -{ - per_cpu(fpu_owner_task, cpu) = NULL; -} - -/* - * Used to indicate that the FPU state in memory is newer than the FPU - * state in registers, and the FPU state should be reloaded next time the - * task is run. Only safe on the current task, or non-running tasks. - */ -static inline void task_disable_lazy_fpu_restore(struct task_struct *tsk) -{ - tsk->thread.fpu.last_cpu = ~0; -} - -static inline int fpu_lazy_restore(struct task_struct *new, unsigned int cpu) -{ - return new == this_cpu_read_stable(fpu_owner_task) && - cpu == new->thread.fpu.last_cpu; -} - -static inline int is_ia32_compat_frame(void) -{ - return config_enabled(CONFIG_IA32_EMULATION) && - test_thread_flag(TIF_IA32); -} - -static inline int is_ia32_frame(void) -{ - return config_enabled(CONFIG_X86_32) || is_ia32_compat_frame(); -} - -static inline int is_x32_frame(void) -{ - return config_enabled(CONFIG_X86_X32_ABI) && test_thread_flag(TIF_X32); -} - -#define X87_FSW_ES (1 << 7) /* Exception Summary */ - -static __always_inline __pure bool use_eager_fpu(void) -{ - return static_cpu_has_safe(X86_FEATURE_EAGER_FPU); -} - -static __always_inline __pure bool use_xsaveopt(void) -{ - return static_cpu_has_safe(X86_FEATURE_XSAVEOPT); -} - -static __always_inline __pure bool use_xsave(void) -{ - return static_cpu_has_safe(X86_FEATURE_XSAVE); -} - -static __always_inline __pure bool use_fxsr(void) -{ - return static_cpu_has_safe(X86_FEATURE_FXSR); -} - -static inline void fx_finit(struct i387_fxsave_struct *fx) -{ - fx->cwd = 0x37f; - fx->mxcsr = MXCSR_DEFAULT; -} - -extern void __sanitize_i387_state(struct task_struct *); - -static inline void sanitize_i387_state(struct task_struct *tsk) -{ - if (!use_xsaveopt()) - return; - __sanitize_i387_state(tsk); -} - -#define user_insn(insn, output, input...) \ -({ \ - int err; \ - asm volatile(ASM_STAC "\n" \ - "1:" #insn "\n\t" \ - "2: " ASM_CLAC "\n" \ - ".section .fixup,\"ax\"\n" \ - "3: movl $-1,%[err]\n" \ - " jmp 2b\n" \ - ".previous\n" \ - _ASM_EXTABLE(1b, 3b) \ - : [err] "=r" (err), output \ - : "0"(0), input); \ - err; \ -}) - -#define check_insn(insn, output, input...) \ -({ \ - int err; \ - asm volatile("1:" #insn "\n\t" \ - "2:\n" \ - ".section .fixup,\"ax\"\n" \ - "3: movl $-1,%[err]\n" \ - " jmp 2b\n" \ - ".previous\n" \ - _ASM_EXTABLE(1b, 3b) \ - : [err] "=r" (err), output \ - : "0"(0), input); \ - err; \ -}) - -static inline int fsave_user(struct i387_fsave_struct __user *fx) -{ - return user_insn(fnsave %[fx]; fwait, [fx] "=m" (*fx), "m" (*fx)); -} - -static inline int fxsave_user(struct i387_fxsave_struct __user *fx) -{ - if (config_enabled(CONFIG_X86_32)) - return user_insn(fxsave %[fx], [fx] "=m" (*fx), "m" (*fx)); - else if (config_enabled(CONFIG_AS_FXSAVEQ)) - return user_insn(fxsaveq %[fx], [fx] "=m" (*fx), "m" (*fx)); - - /* See comment in fpu_fxsave() below. */ - return user_insn(rex64/fxsave (%[fx]), "=m" (*fx), [fx] "R" (fx)); -} - -static inline int fxrstor_checking(struct i387_fxsave_struct *fx) -{ - if (config_enabled(CONFIG_X86_32)) - return check_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); - else if (config_enabled(CONFIG_AS_FXSAVEQ)) - return check_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); - - /* See comment in fpu_fxsave() below. */ - return check_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx), - "m" (*fx)); -} - -static inline int fxrstor_user(struct i387_fxsave_struct __user *fx) -{ - if (config_enabled(CONFIG_X86_32)) - return user_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); - else if (config_enabled(CONFIG_AS_FXSAVEQ)) - return user_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); - - /* See comment in fpu_fxsave() below. */ - return user_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx), - "m" (*fx)); -} - -static inline int frstor_checking(struct i387_fsave_struct *fx) -{ - return check_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); -} - -static inline int frstor_user(struct i387_fsave_struct __user *fx) -{ - return user_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); -} - -static inline void fpu_fxsave(struct fpu *fpu) -{ - if (config_enabled(CONFIG_X86_32)) - asm volatile( "fxsave %[fx]" : [fx] "=m" (fpu->state->fxsave)); - else if (config_enabled(CONFIG_AS_FXSAVEQ)) - asm volatile("fxsaveq %[fx]" : [fx] "=m" (fpu->state->fxsave)); - else { - /* Using "rex64; fxsave %0" is broken because, if the memory - * operand uses any extended registers for addressing, a second - * REX prefix will be generated (to the assembler, rex64 - * followed by semicolon is a separate instruction), and hence - * the 64-bitness is lost. - * - * Using "fxsaveq %0" would be the ideal choice, but is only - * supported starting with gas 2.16. - * - * Using, as a workaround, the properly prefixed form below - * isn't accepted by any binutils version so far released, - * complaining that the same type of prefix is used twice if - * an extended register is needed for addressing (fix submitted - * to mainline 2005-11-21). - * - * asm volatile("rex64/fxsave %0" : "=m" (fpu->state->fxsave)); - * - * This, however, we can work around by forcing the compiler to - * select an addressing mode that doesn't require extended - * registers. - */ - asm volatile( "rex64/fxsave (%[fx])" - : "=m" (fpu->state->fxsave) - : [fx] "R" (&fpu->state->fxsave)); - } -} - -/* - * These must be called with preempt disabled. Returns - * 'true' if the FPU state is still intact. - */ -static inline int fpu_save_init(struct fpu *fpu) -{ - if (use_xsave()) { - fpu_xsave(fpu); - - /* - * xsave header may indicate the init state of the FP. - */ - if (!(fpu->state->xsave.xsave_hdr.xstate_bv & XSTATE_FP)) - return 1; - } else if (use_fxsr()) { - fpu_fxsave(fpu); - } else { - asm volatile("fnsave %[fx]; fwait" - : [fx] "=m" (fpu->state->fsave)); - return 0; - } - - /* - * If exceptions are pending, we need to clear them so - * that we don't randomly get exceptions later. - * - * FIXME! Is this perhaps only true for the old-style - * irq13 case? Maybe we could leave the x87 state - * intact otherwise? - */ - if (unlikely(fpu->state->fxsave.swd & X87_FSW_ES)) { - asm volatile("fnclex"); - return 0; - } - return 1; -} - -static inline int __save_init_fpu(struct task_struct *tsk) -{ - return fpu_save_init(&tsk->thread.fpu); -} - -static inline int fpu_restore_checking(struct fpu *fpu) -{ - if (use_xsave()) - return fpu_xrstor_checking(&fpu->state->xsave); - else if (use_fxsr()) - return fxrstor_checking(&fpu->state->fxsave); - else - return frstor_checking(&fpu->state->fsave); -} - -static inline int restore_fpu_checking(struct task_struct *tsk) -{ - /* - * AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception is - * pending. Clear the x87 state here by setting it to fixed values. - * "m" is a random variable that should be in L1. - */ - if (unlikely(static_cpu_has_bug_safe(X86_BUG_FXSAVE_LEAK))) { - asm volatile( - "fnclex\n\t" - "emms\n\t" - "fildl %P[addr]" /* set F?P to defined value */ - : : [addr] "m" (tsk->thread.fpu.has_fpu)); - } - - return fpu_restore_checking(&tsk->thread.fpu); -} - -/* - * Software FPU state helpers. Careful: these need to - * be preemption protection *and* they need to be - * properly paired with the CR0.TS changes! - */ -static inline int __thread_has_fpu(struct task_struct *tsk) -{ - return tsk->thread.fpu.has_fpu; -} - -/* Must be paired with an 'stts' after! */ -static inline void __thread_clear_has_fpu(struct task_struct *tsk) -{ - tsk->thread.fpu.has_fpu = 0; - this_cpu_write(fpu_owner_task, NULL); -} - -/* Must be paired with a 'clts' before! */ -static inline void __thread_set_has_fpu(struct task_struct *tsk) -{ - tsk->thread.fpu.has_fpu = 1; - this_cpu_write(fpu_owner_task, tsk); -} - -/* - * Encapsulate the CR0.TS handling together with the - * software flag. - * - * These generally need preemption protection to work, - * do try to avoid using these on their own. - */ -static inline void __thread_fpu_end(struct task_struct *tsk) -{ - __thread_clear_has_fpu(tsk); - if (!use_eager_fpu()) - stts(); -} - -static inline void __thread_fpu_begin(struct task_struct *tsk) -{ - if (!use_eager_fpu()) - clts(); - __thread_set_has_fpu(tsk); -} - -static inline void drop_fpu(struct task_struct *tsk) -{ - /* - * Forget coprocessor state.. - */ - preempt_disable(); - tsk->thread.fpu_counter = 0; - - if (__thread_has_fpu(tsk)) { - /* Ignore delayed exceptions from user space */ - asm volatile("1: fwait\n" - "2:\n" - _ASM_EXTABLE(1b, 2b)); - __thread_fpu_end(tsk); - } - - clear_stopped_child_used_math(tsk); - preempt_enable(); -} - -static inline void restore_init_xstate(void) -{ - if (use_xsave()) - xrstor_state(init_xstate_buf, -1); - else - fxrstor_checking(&init_xstate_buf->i387); -} - -/* - * Reset the FPU state in the eager case and drop it in the lazy case (later use - * will reinit it). - */ -static inline void fpu_reset_state(struct task_struct *tsk) -{ - if (!use_eager_fpu()) - drop_fpu(tsk); - else - restore_init_xstate(); -} - -/* - * FPU state switching for scheduling. - * - * This is a two-stage process: - * - * - switch_fpu_prepare() saves the old state and - * sets the new state of the CR0.TS bit. This is - * done within the context of the old process. - * - * - switch_fpu_finish() restores the new state as - * necessary. - */ -typedef struct { int preload; } fpu_switch_t; - -static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct task_struct *new, int cpu) -{ - fpu_switch_t fpu; - - /* - * If the task has used the math, pre-load the FPU on xsave processors - * or if the past 5 consecutive context-switches used math. - */ - fpu.preload = tsk_used_math(new) && - (use_eager_fpu() || new->thread.fpu_counter > 5); - - if (__thread_has_fpu(old)) { - if (!__save_init_fpu(old)) - task_disable_lazy_fpu_restore(old); - else - old->thread.fpu.last_cpu = cpu; - - /* But leave fpu_owner_task! */ - old->thread.fpu.has_fpu = 0; - - /* Don't change CR0.TS if we just switch! */ - if (fpu.preload) { - new->thread.fpu_counter++; - __thread_set_has_fpu(new); - prefetch(new->thread.fpu.state); - } else if (!use_eager_fpu()) - stts(); - } else { - old->thread.fpu_counter = 0; - task_disable_lazy_fpu_restore(old); - if (fpu.preload) { - new->thread.fpu_counter++; - if (fpu_lazy_restore(new, cpu)) - fpu.preload = 0; - else - prefetch(new->thread.fpu.state); - __thread_fpu_begin(new); - } - } - return fpu; -} - -/* - * By the time this gets called, we've already cleared CR0.TS and - * given the process the FPU if we are going to preload the FPU - * state - all we need to do is to conditionally restore the register - * state itself. - */ -static inline void switch_fpu_finish(struct task_struct *new, fpu_switch_t fpu) -{ - if (fpu.preload) { - if (unlikely(restore_fpu_checking(new))) - fpu_reset_state(new); - } -} - -/* - * Signal frame handlers... - */ -extern int save_xstate_sig(void __user *buf, void __user *fx, int size); -extern int __restore_xstate_sig(void __user *buf, void __user *fx, int size); - -static inline int xstate_sigframe_size(void) -{ - return use_xsave() ? xstate_size + FP_XSTATE_MAGIC2_SIZE : xstate_size; -} - -static inline int restore_xstate_sig(void __user *buf, int ia32_frame) -{ - void __user *buf_fx = buf; - int size = xstate_sigframe_size(); - - if (ia32_frame && use_fxsr()) { - buf_fx = buf + sizeof(struct i387_fsave_struct); - size += sizeof(struct i387_fsave_struct); - } - - return __restore_xstate_sig(buf, buf_fx, size); -} - -/* - * Needs to be preemption-safe. - * - * NOTE! user_fpu_begin() must be used only immediately before restoring - * the save state. It does not do any saving/restoring on its own. In - * lazy FPU mode, it is just an optimization to avoid a #NM exception, - * the task can lose the FPU right after preempt_enable(). - */ -static inline void user_fpu_begin(void) -{ - preempt_disable(); - if (!user_has_fpu()) - __thread_fpu_begin(current); - preempt_enable(); -} - -static inline void __save_fpu(struct task_struct *tsk) -{ - if (use_xsave()) { - if (unlikely(system_state == SYSTEM_BOOTING)) - xsave_state_booting(&tsk->thread.fpu.state->xsave, -1); - else - xsave_state(&tsk->thread.fpu.state->xsave, -1); - } else - fpu_fxsave(&tsk->thread.fpu); -} - -/* - * i387 state interaction - */ -static inline unsigned short get_fpu_cwd(struct task_struct *tsk) -{ - if (cpu_has_fxsr) { - return tsk->thread.fpu.state->fxsave.cwd; - } else { - return (unsigned short)tsk->thread.fpu.state->fsave.cwd; - } -} - -static inline unsigned short get_fpu_swd(struct task_struct *tsk) -{ - if (cpu_has_fxsr) { - return tsk->thread.fpu.state->fxsave.swd; - } else { - return (unsigned short)tsk->thread.fpu.state->fsave.swd; - } -} - -static inline unsigned short get_fpu_mxcsr(struct task_struct *tsk) -{ - if (cpu_has_xmm) { - return tsk->thread.fpu.state->fxsave.mxcsr; - } else { - return MXCSR_DEFAULT; - } -} - -static bool fpu_allocated(struct fpu *fpu) -{ - return fpu->state != NULL; -} - -static inline int fpu_alloc(struct fpu *fpu) -{ - if (fpu_allocated(fpu)) - return 0; - fpu->state = kmem_cache_alloc(task_xstate_cachep, GFP_KERNEL); - if (!fpu->state) - return -ENOMEM; - WARN_ON((unsigned long)fpu->state & 15); - return 0; -} - -static inline void fpu_free(struct fpu *fpu) -{ - if (fpu->state) { - kmem_cache_free(task_xstate_cachep, fpu->state); - fpu->state = NULL; - } -} - -static inline void fpu_copy(struct task_struct *dst, struct task_struct *src) -{ - if (use_eager_fpu()) { - memset(&dst->thread.fpu.state->xsave, 0, xstate_size); - __save_fpu(dst); - } else { - struct fpu *dfpu = &dst->thread.fpu; - struct fpu *sfpu = &src->thread.fpu; - - unlazy_fpu(src); - memcpy(dfpu->state, sfpu->state, xstate_size); - } -} - -static inline unsigned long -alloc_mathframe(unsigned long sp, int ia32_frame, unsigned long *buf_fx, - unsigned long *size) -{ - unsigned long frame_size = xstate_sigframe_size(); - - *buf_fx = sp = round_down(sp - frame_size, 64); - if (ia32_frame && use_fxsr()) { - frame_size += sizeof(struct i387_fsave_struct); - sp -= sizeof(struct i387_fsave_struct); - } - - *size = frame_size; - return sp; -} - -#endif diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h new file mode 100644 index 000000000000..1429a7c736db --- /dev/null +++ b/arch/x86/include/asm/fpu/api.h @@ -0,0 +1,48 @@ +/* + * Copyright (C) 1994 Linus Torvalds + * + * Pentium III FXSR, SSE support + * General FPU state handling cleanups + * Gareth Hughes <gareth@valinux.com>, May 2000 + * x86-64 work by Andi Kleen 2002 + */ + +#ifndef _ASM_X86_FPU_API_H +#define _ASM_X86_FPU_API_H + +/* + * Careful: __kernel_fpu_begin/end() must be called with preempt disabled + * and they don't touch the preempt state on their own. + * If you enable preemption after __kernel_fpu_begin(), preempt notifier + * should call the __kernel_fpu_end() to prevent the kernel/user FPU + * state from getting corrupted. KVM for example uses this model. + * + * All other cases use kernel_fpu_begin/end() which disable preemption + * during kernel FPU usage. + */ +extern void __kernel_fpu_begin(void); +extern void __kernel_fpu_end(void); +extern void kernel_fpu_begin(void); +extern void kernel_fpu_end(void); +extern bool irq_fpu_usable(void); + +/* + * Some instructions like VIA's padlock instructions generate a spurious + * DNA fault but don't modify SSE registers. And these instructions + * get used from interrupt context as well. To prevent these kernel instructions + * in interrupt context interacting wrongly with other user/kernel fpu usage, we + * should use them only in the context of irq_ts_save/restore() + */ +extern int irq_ts_save(void); +extern void irq_ts_restore(int TS_state); + +/* + * Query the presence of one or more xfeatures. Works on any legacy CPU as well. + * + * If 'feature_name' is set then put a human-readable description of + * the feature there as well - this can be used to print error (or success) + * messages. + */ +extern int cpu_has_xfeatures(u64 xfeatures_mask, const char **feature_name); + +#endif /* _ASM_X86_FPU_API_H */ diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h new file mode 100644 index 000000000000..3c3550c3a4a3 --- /dev/null +++ b/arch/x86/include/asm/fpu/internal.h @@ -0,0 +1,694 @@ +/* + * Copyright (C) 1994 Linus Torvalds + * + * Pentium III FXSR, SSE support + * General FPU state handling cleanups + * Gareth Hughes <gareth@valinux.com>, May 2000 + * x86-64 work by Andi Kleen 2002 + */ + +#ifndef _ASM_X86_FPU_INTERNAL_H +#define _ASM_X86_FPU_INTERNAL_H + +#include <linux/compat.h> +#include <linux/sched.h> +#include <linux/slab.h> + +#include <asm/user.h> +#include <asm/fpu/api.h> +#include <asm/fpu/xstate.h> + +/* + * High level FPU state handling functions: + */ +extern void fpu__activate_curr(struct fpu *fpu); +extern void fpu__activate_fpstate_read(struct fpu *fpu); +extern void fpu__activate_fpstate_write(struct fpu *fpu); +extern void fpu__save(struct fpu *fpu); +extern void fpu__restore(struct fpu *fpu); +extern int fpu__restore_sig(void __user *buf, int ia32_frame); +extern void fpu__drop(struct fpu *fpu); +extern int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu); +extern void fpu__clear(struct fpu *fpu); +extern int fpu__exception_code(struct fpu *fpu, int trap_nr); +extern int dump_fpu(struct pt_regs *ptregs, struct user_i387_struct *fpstate); + +/* + * Boot time FPU initialization functions: + */ +extern void fpu__init_cpu(void); +extern void fpu__init_system_xstate(void); +extern void fpu__init_cpu_xstate(void); +extern void fpu__init_system(struct cpuinfo_x86 *c); +extern void fpu__init_check_bugs(void); +extern void fpu__resume_cpu(void); + +/* + * Debugging facility: + */ +#ifdef CONFIG_X86_DEBUG_FPU +# define WARN_ON_FPU(x) WARN_ON_ONCE(x) +#else +# define WARN_ON_FPU(x) ({ (void)(x); 0; }) +#endif + +/* + * FPU related CPU feature flag helper routines: + */ +static __always_inline __pure bool use_eager_fpu(void) +{ + return static_cpu_has_safe(X86_FEATURE_EAGER_FPU); +} + +static __always_inline __pure bool use_xsaveopt(void) +{ + return static_cpu_has_safe(X86_FEATURE_XSAVEOPT); +} + +static __always_inline __pure bool use_xsave(void) +{ + return static_cpu_has_safe(X86_FEATURE_XSAVE); +} + +static __always_inline __pure bool use_fxsr(void) +{ + return static_cpu_has_safe(X86_FEATURE_FXSR); +} + +/* + * fpstate handling functions: + */ + +extern union fpregs_state init_fpstate; + +extern void fpstate_init(union fpregs_state *state); +#ifdef CONFIG_MATH_EMULATION +extern void fpstate_init_soft(struct swregs_state *soft); +#else +static inline void fpstate_init_soft(struct swregs_state *soft) {} +#endif +static inline void fpstate_init_fxstate(struct fxregs_state *fx) +{ + fx->cwd = 0x37f; + fx->mxcsr = MXCSR_DEFAULT; +} +extern void fpstate_sanitize_xstate(struct fpu *fpu); + +#define user_insn(insn, output, input...) \ +({ \ + int err; \ + asm volatile(ASM_STAC "\n" \ + "1:" #insn "\n\t" \ + "2: " ASM_CLAC "\n" \ + ".section .fixup,\"ax\"\n" \ + "3: movl $-1,%[err]\n" \ + " jmp 2b\n" \ + ".previous\n" \ + _ASM_EXTABLE(1b, 3b) \ + : [err] "=r" (err), output \ + : "0"(0), input); \ + err; \ +}) + +#define check_insn(insn, output, input...) \ +({ \ + int err; \ + asm volatile("1:" #insn "\n\t" \ + "2:\n" \ + ".section .fixup,\"ax\"\n" \ + "3: movl $-1,%[err]\n" \ + " jmp 2b\n" \ + ".previous\n" \ + _ASM_EXTABLE(1b, 3b) \ + : [err] "=r" (err), output \ + : "0"(0), input); \ + err; \ +}) + +static inline int copy_fregs_to_user(struct fregs_state __user *fx) +{ + return user_insn(fnsave %[fx]; fwait, [fx] "=m" (*fx), "m" (*fx)); +} + +static inline int copy_fxregs_to_user(struct fxregs_state __user *fx) +{ + if (config_enabled(CONFIG_X86_32)) + return user_insn(fxsave %[fx], [fx] "=m" (*fx), "m" (*fx)); + else if (config_enabled(CONFIG_AS_FXSAVEQ)) + return user_insn(fxsaveq %[fx], [fx] "=m" (*fx), "m" (*fx)); + + /* See comment in copy_fxregs_to_kernel() below. */ + return user_insn(rex64/fxsave (%[fx]), "=m" (*fx), [fx] "R" (fx)); +} + +static inline void copy_kernel_to_fxregs(struct fxregs_state *fx) +{ + int err; + + if (config_enabled(CONFIG_X86_32)) { + err = check_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); + } else { + if (config_enabled(CONFIG_AS_FXSAVEQ)) { + err = check_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); + } else { + /* See comment in copy_fxregs_to_kernel() below. */ + err = check_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx), "m" (*fx)); + } + } + /* Copying from a kernel buffer to FPU registers should never fail: */ + WARN_ON_FPU(err); +} + +static inline int copy_user_to_fxregs(struct fxregs_state __user *fx) +{ + if (config_enabled(CONFIG_X86_32)) + return user_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); + else if (config_enabled(CONFIG_AS_FXSAVEQ)) + return user_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); + + /* See comment in copy_fxregs_to_kernel() below. */ + return user_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx), + "m" (*fx)); +} + +static inline void copy_kernel_to_fregs(struct fregs_state *fx) +{ + int err = check_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); + + WARN_ON_FPU(err); +} + +static inline int copy_user_to_fregs(struct fregs_state __user *fx) +{ + return user_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); +} + +static inline void copy_fxregs_to_kernel(struct fpu *fpu) +{ + if (config_enabled(CONFIG_X86_32)) + asm volatile( "fxsave %[fx]" : [fx] "=m" (fpu->state.fxsave)); + else if (config_enabled(CONFIG_AS_FXSAVEQ)) + asm volatile("fxsaveq %[fx]" : [fx] "=m" (fpu->state.fxsave)); + else { + /* Using "rex64; fxsave %0" is broken because, if the memory + * operand uses any extended registers for addressing, a second + * REX prefix will be generated (to the assembler, rex64 + * followed by semicolon is a separate instruction), and hence + * the 64-bitness is lost. + * + * Using "fxsaveq %0" would be the ideal choice, but is only + * supported starting with gas 2.16. + * + * Using, as a workaround, the properly prefixed form below + * isn't accepted by any binutils version so far released, + * complaining that the same type of prefix is used twice if + * an extended register is needed for addressing (fix submitted + * to mainline 2005-11-21). + * + * asm volatile("rex64/fxsave %0" : "=m" (fpu->state.fxsave)); + * + * This, however, we can work around by forcing the compiler to + * select an addressing mode that doesn't require extended + * registers. + */ + asm volatile( "rex64/fxsave (%[fx])" + : "=m" (fpu->state.fxsave) + : [fx] "R" (&fpu->state.fxsave)); + } +} + +/* These macros all use (%edi)/(%rdi) as the single memory argument. */ +#define XSAVE ".byte " REX_PREFIX "0x0f,0xae,0x27" +#define XSAVEOPT ".byte " REX_PREFIX "0x0f,0xae,0x37" +#define XSAVES ".byte " REX_PREFIX "0x0f,0xc7,0x2f" +#define XRSTOR ".byte " REX_PREFIX "0x0f,0xae,0x2f" +#define XRSTORS ".byte " REX_PREFIX "0x0f,0xc7,0x1f" + +/* xstate instruction fault handler: */ +#define xstate_fault(__err) \ + \ + ".section .fixup,\"ax\"\n" \ + \ + "3: movl $-2,%[_err]\n" \ + " jmp 2b\n" \ + \ + ".previous\n" \ + \ + _ASM_EXTABLE(1b, 3b) \ + : [_err] "=r" (__err) + +/* + * This function is called only during boot time when x86 caps are not set + * up and alternative can not be used yet. + */ +static inline void copy_xregs_to_kernel_booting(struct xregs_state *xstate) +{ + u64 mask = -1; + u32 lmask = mask; + u32 hmask = mask >> 32; + int err = 0; + + WARN_ON(system_state != SYSTEM_BOOTING); + + if (boot_cpu_has(X86_FEATURE_XSAVES)) + asm volatile("1:"XSAVES"\n\t" + "2:\n\t" + xstate_fault(err) + : "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err) + : "memory"); + else + asm volatile("1:"XSAVE"\n\t" + "2:\n\t" + xstate_fault(err) + : "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err) + : "memory"); + + /* We should never fault when copying to a kernel buffer: */ + WARN_ON_FPU(err); +} + +/* + * This function is called only during boot time when x86 caps are not set + * up and alternative can not be used yet. + */ +static inline void copy_kernel_to_xregs_booting(struct xregs_state *xstate) +{ + u64 mask = -1; + u32 lmask = mask; + u32 hmask = mask >> 32; + int err = 0; + + WARN_ON(system_state != SYSTEM_BOOTING); + + if (boot_cpu_has(X86_FEATURE_XSAVES)) + asm volatile("1:"XRSTORS"\n\t" + "2:\n\t" + xstate_fault(err) + : "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err) + : "memory"); + else + asm volatile("1:"XRSTOR"\n\t" + "2:\n\t" + xstate_fault(err) + : "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err) + : "memory"); + + /* We should never fault when copying from a kernel buffer: */ + WARN_ON_FPU(err); +} + +/* + * Save processor xstate to xsave area. + */ +static inline void copy_xregs_to_kernel(struct xregs_state *xstate) +{ + u64 mask = -1; + u32 lmask = mask; + u32 hmask = mask >> 32; + int err = 0; + + WARN_ON(!alternatives_patched); + + /* + * If xsaves is enabled, xsaves replaces xsaveopt because + * it supports compact format and supervisor states in addition to + * modified optimization in xsaveopt. + * + * Otherwise, if xsaveopt is enabled, xsaveopt replaces xsave + * because xsaveopt supports modified optimization which is not + * supported by xsave. + * + * If none of xsaves and xsaveopt is enabled, use xsave. + */ + alternative_input_2( + "1:"XSAVE, + XSAVEOPT, + X86_FEATURE_XSAVEOPT, + XSAVES, + X86_FEATURE_XSAVES, + [xstate] "D" (xstate), "a" (lmask), "d" (hmask) : + "memory"); + asm volatile("2:\n\t" + xstate_fault(err) + : "0" (err) + : "memory"); + + /* We should never fault when copying to a kernel buffer: */ + WARN_ON_FPU(err); +} + +/* + * Restore processor xstate from xsave area. + */ +static inline void copy_kernel_to_xregs(struct xregs_state *xstate, u64 mask) +{ + u32 lmask = mask; + u32 hmask = mask >> 32; + int err = 0; + + /* + * Use xrstors to restore context if it is enabled. xrstors supports + * compacted format of xsave area which is not supported by xrstor. + */ + alternative_input( + "1: " XRSTOR, + XRSTORS, + X86_FEATURE_XSAVES, + "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask) + : "memory"); + + asm volatile("2:\n" + xstate_fault(err) + : "0" (err) + : "memory"); + + /* We should never fault when copying from a kernel buffer: */ + WARN_ON_FPU(err); +} + +/* + * Save xstate to user space xsave area. + * + * We don't use modified optimization because xrstor/xrstors might track + * a different application. + * + * We don't use compacted format xsave area for + * backward compatibility for old applications which don't understand + * compacted format of xsave area. + */ +static inline int copy_xregs_to_user(struct xregs_state __user *buf) +{ + int err; + + /* + * Clear the xsave header first, so that reserved fields are + * initialized to zero. + */ + err = __clear_user(&buf->header, sizeof(buf->header)); + if (unlikely(err)) + return -EFAULT; + + __asm__ __volatile__(ASM_STAC "\n" + "1:"XSAVE"\n" + "2: " ASM_CLAC "\n" + xstate_fault(err) + : "D" (buf), "a" (-1), "d" (-1), "0" (err) + : "memory"); + return err; +} + +/* + * Restore xstate from user space xsave area. + */ +static inline int copy_user_to_xregs(struct xregs_state __user *buf, u64 mask) +{ + struct xregs_state *xstate = ((__force struct xregs_state *)buf); + u32 lmask = mask; + u32 hmask = mask >> 32; + int err = 0; + + __asm__ __volatile__(ASM_STAC "\n" + "1:"XRSTOR"\n" + "2: " ASM_CLAC "\n" + xstate_fault(err) + : "D" (xstate), "a" (lmask), "d" (hmask), "0" (err) + : "memory"); /* memory required? */ + return err; +} + +/* + * These must be called with preempt disabled. Returns + * 'true' if the FPU state is still intact and we can + * keep registers active. + * + * The legacy FNSAVE instruction cleared all FPU state + * unconditionally, so registers are essentially destroyed. + * Modern FPU state can be kept in registers, if there are + * no pending FP exceptions. + */ +static inline int copy_fpregs_to_fpstate(struct fpu *fpu) +{ + if (likely(use_xsave())) { + copy_xregs_to_kernel(&fpu->state.xsave); + return 1; + } + + if (likely(use_fxsr())) { + copy_fxregs_to_kernel(fpu); + return 1; + } + + /* + * Legacy FPU register saving, FNSAVE always clears FPU registers, + * so we have to mark them inactive: + */ + asm volatile("fnsave %[fp]; fwait" : [fp] "=m" (fpu->state.fsave)); + + return 0; +} + +static inline void __copy_kernel_to_fpregs(union fpregs_state *fpstate) +{ + if (use_xsave()) { + copy_kernel_to_xregs(&fpstate->xsave, -1); + } else { + if (use_fxsr()) + copy_kernel_to_fxregs(&fpstate->fxsave); + else + copy_kernel_to_fregs(&fpstate->fsave); + } +} + +static inline void copy_kernel_to_fpregs(union fpregs_state *fpstate) +{ + /* + * AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception is + * pending. Clear the x87 state here by setting it to fixed values. + * "m" is a random variable that should be in L1. + */ + if (unlikely(static_cpu_has_bug_safe(X86_BUG_FXSAVE_LEAK))) { + asm volatile( + "fnclex\n\t" + "emms\n\t" + "fildl %P[addr]" /* set F?P to defined value */ + : : [addr] "m" (fpstate)); + } + + __copy_kernel_to_fpregs(fpstate); +} + +extern int copy_fpstate_to_sigframe(void __user *buf, void __user *fp, int size); + +/* + * FPU context switch related helper methods: + */ + +DECLARE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx); + +/* + * Must be run with preemption disabled: this clears the fpu_fpregs_owner_ctx, + * on this CPU. + * + * This will disable any lazy FPU state restore of the current FPU state, + * but if the current thread owns the FPU, it will still be saved by. + */ +static inline void __cpu_disable_lazy_restore(unsigned int cpu) +{ + per_cpu(fpu_fpregs_owner_ctx, cpu) = NULL; +} + +static inline int fpu_want_lazy_restore(struct fpu *fpu, unsigned int cpu) +{ + return fpu == this_cpu_read_stable(fpu_fpregs_owner_ctx) && cpu == fpu->last_cpu; +} + + +/* + * Wrap lazy FPU TS handling in a 'hw fpregs activation/deactivation' + * idiom, which is then paired with the sw-flag (fpregs_active) later on: + */ + +static inline void __fpregs_activate_hw(void) +{ + if (!use_eager_fpu()) + clts(); +} + +static inline void __fpregs_deactivate_hw(void) +{ + if (!use_eager_fpu()) + stts(); +} + +/* Must be paired with an 'stts' (fpregs_deactivate_hw()) after! */ +static inline void __fpregs_deactivate(struct fpu *fpu) +{ + WARN_ON_FPU(!fpu->fpregs_active); + + fpu->fpregs_active = 0; + this_cpu_write(fpu_fpregs_owner_ctx, NULL); +} + +/* Must be paired with a 'clts' (fpregs_activate_hw()) before! */ +static inline void __fpregs_activate(struct fpu *fpu) +{ + WARN_ON_FPU(fpu->fpregs_active); + + fpu->fpregs_active = 1; + this_cpu_write(fpu_fpregs_owner_ctx, fpu); +} + +/* + * The question "does this thread have fpu access?" + * is slightly racy, since preemption could come in + * and revoke it immediately after the test. + * + * However, even in that very unlikely scenario, + * we can just assume we have FPU access - typically + * to save the FP state - we'll just take a #NM + * fault and get the FPU access back. + */ +static inline int fpregs_active(void) +{ + return current->thread.fpu.fpregs_active; +} + +/* + * Encapsulate the CR0.TS handling together with the + * software flag. + * + * These generally need preemption protection to work, + * do try to avoid using these on their own. + */ +static inline void fpregs_activate(struct fpu *fpu) +{ + __fpregs_activate_hw(); + __fpregs_activate(fpu); +} + +static inline void fpregs_deactivate(struct fpu *fpu) +{ + __fpregs_deactivate(fpu); + __fpregs_deactivate_hw(); +} + +/* + * FPU state switching for scheduling. + * + * This is a two-stage process: + * + * - switch_fpu_prepare() saves the old state and + * sets the new state of the CR0.TS bit. This is + * done within the context of the old process. + * + * - switch_fpu_finish() restores the new state as + * necessary. + */ +typedef struct { int preload; } fpu_switch_t; + +static inline fpu_switch_t +switch_fpu_prepare(struct fpu *old_fpu, struct fpu *new_fpu, int cpu) +{ + fpu_switch_t fpu; + + /* + * If the task has used the math, pre-load the FPU on xsave processors + * or if the past 5 consecutive context-switches used math. + */ + fpu.preload = new_fpu->fpstate_active && + (use_eager_fpu() || new_fpu->counter > 5); + + if (old_fpu->fpregs_active) { + if (!copy_fpregs_to_fpstate(old_fpu)) + old_fpu->last_cpu = -1; + else + old_fpu->last_cpu = cpu; + + /* But leave fpu_fpregs_owner_ctx! */ + old_fpu->fpregs_active = 0; + + /* Don't change CR0.TS if we just switch! */ + if (fpu.preload) { + new_fpu->counter++; + __fpregs_activate(new_fpu); + prefetch(&new_fpu->state); + } else { + __fpregs_deactivate_hw(); + } + } else { + old_fpu->counter = 0; + old_fpu->last_cpu = -1; + if (fpu.preload) { + new_fpu->counter++; + if (fpu_want_lazy_restore(new_fpu, cpu)) + fpu.preload = 0; + else + prefetch(&new_fpu->state); + fpregs_activate(new_fpu); + } + } + return fpu; +} + +/* + * Misc helper functions: + */ + +/* + * By the time this gets called, we've already cleared CR0.TS and + * given the process the FPU if we are going to preload the FPU + * state - all we need to do is to conditionally restore the register + * state itself. + */ +static inline void switch_fpu_finish(struct fpu *new_fpu, fpu_switch_t fpu_switch) +{ + if (fpu_switch.preload) + copy_kernel_to_fpregs(&new_fpu->state); +} + +/* + * Needs to be preemption-safe. + * + * NOTE! user_fpu_begin() must be used only immediately before restoring + * the save state. It does not do any saving/restoring on its own. In + * lazy FPU mode, it is just an optimization to avoid a #NM exception, + * the task can lose the FPU right after preempt_enable(). + */ +static inline void user_fpu_begin(void) +{ + struct fpu *fpu = ¤t->thread.fpu; + + preempt_disable(); + if (!fpregs_active()) + fpregs_activate(fpu); + preempt_enable(); +} + +/* + * MXCSR and XCR definitions: + */ + +extern unsigned int mxcsr_feature_mask; + +#define XCR_XFEATURE_ENABLED_MASK 0x00000000 + +static inline u64 xgetbv(u32 index) +{ + u32 eax, edx; + + asm volatile(".byte 0x0f,0x01,0xd0" /* xgetbv */ + : "=a" (eax), "=d" (edx) + : "c" (index)); + return eax + ((u64)edx << 32); +} + +static inline void xsetbv(u32 index, u64 value) +{ + u32 eax = value; + u32 edx = value >> 32; + + asm volatile(".byte 0x0f,0x01,0xd1" /* xsetbv */ + : : "a" (eax), "d" (edx), "c" (index)); +} + +#endif /* _ASM_X86_FPU_INTERNAL_H */ diff --git a/arch/x86/include/asm/fpu/regset.h b/arch/x86/include/asm/fpu/regset.h new file mode 100644 index 000000000000..39d3107ac6c7 --- /dev/null +++ b/arch/x86/include/asm/fpu/regset.h @@ -0,0 +1,21 @@ +/* + * FPU regset handling methods: + */ +#ifndef _ASM_X86_FPU_REGSET_H +#define _ASM_X86_FPU_REGSET_H + +#include <linux/regset.h> + +extern user_regset_active_fn regset_fpregs_active, regset_xregset_fpregs_active; +extern user_regset_get_fn fpregs_get, xfpregs_get, fpregs_soft_get, + xstateregs_get; +extern user_regset_set_fn fpregs_set, xfpregs_set, fpregs_soft_set, + xstateregs_set; + +/* + * xstateregs_active == regset_fpregs_active. Please refer to the comment + * at the definition of regset_fpregs_active. + */ +#define xstateregs_active regset_fpregs_active + +#endif /* _ASM_X86_FPU_REGSET_H */ diff --git a/arch/x86/include/asm/fpu/signal.h b/arch/x86/include/asm/fpu/signal.h new file mode 100644 index 000000000000..7358e9d61f1e --- /dev/null +++ b/arch/x86/include/asm/fpu/signal.h @@ -0,0 +1,33 @@ +/* + * x86 FPU signal frame handling methods: + */ +#ifndef _ASM_X86_FPU_SIGNAL_H +#define _ASM_X86_FPU_SIGNAL_H + +#ifdef CONFIG_X86_64 +# include <asm/sigcontext32.h> +# include <asm/user32.h> +struct ksignal; +int ia32_setup_rt_frame(int sig, struct ksignal *ksig, + compat_sigset_t *set, struct pt_regs *regs); +int ia32_setup_frame(int sig, struct ksignal *ksig, + compat_sigset_t *set, struct pt_regs *regs); +#else +# define user_i387_ia32_struct user_i387_struct +# define user32_fxsr_struct user_fxsr_struct +# define ia32_setup_frame __setup_frame +# define ia32_setup_rt_frame __setup_rt_frame +#endif + +extern void convert_from_fxsr(struct user_i387_ia32_struct *env, + struct task_struct *tsk); +extern void convert_to_fxsr(struct task_struct *tsk, + const struct user_i387_ia32_struct *env); + +unsigned long +fpu__alloc_mathframe(unsigned long sp, int ia32_frame, + unsigned long *buf_fx, unsigned long *size); + +extern void fpu__init_prepare_fx_sw_frame(void); + +#endif /* _ASM_X86_FPU_SIGNAL_H */ diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h new file mode 100644 index 000000000000..0637826292de --- /dev/null +++ b/arch/x86/include/asm/fpu/types.h @@ -0,0 +1,293 @@ +/* + * FPU data structures: + */ +#ifndef _ASM_X86_FPU_H +#define _ASM_X86_FPU_H + +/* + * The legacy x87 FPU state format, as saved by FSAVE and + * restored by the FRSTOR instructions: + */ +struct fregs_state { + u32 cwd; /* FPU Control Word */ + u32 swd; /* FPU Status Word */ + u32 twd; /* FPU Tag Word */ + u32 fip; /* FPU IP Offset */ + u32 fcs; /* FPU IP Selector */ + u32 foo; /* FPU Operand Pointer Offset */ + u32 fos; /* FPU Operand Pointer Selector */ + + /* 8*10 bytes for each FP-reg = 80 bytes: */ + u32 st_space[20]; + + /* Software status information [not touched by FSAVE]: */ + u32 status; +}; + +/* + * The legacy fx SSE/MMX FPU state format, as saved by FXSAVE and + * restored by the FXRSTOR instructions. It's similar to the FSAVE + * format, but differs in some areas, plus has extensions at + * the end for the XMM registers. + */ +struct fxregs_state { + u16 cwd; /* Control Word */ + u16 swd; /* Status Word */ + u16 twd; /* Tag Word */ + u16 fop; /* Last Instruction Opcode */ + union { + struct { + u64 rip; /* Instruction Pointer */ + u64 rdp; /* Data Pointer */ + }; + struct { + u32 fip; /* FPU IP Offset */ + u32 fcs; /* FPU IP Selector */ + u32 foo; /* FPU Operand Offset */ + u32 fos; /* FPU Operand Selector */ + }; + }; + u32 mxcsr; /* MXCSR Register State */ + u32 mxcsr_mask; /* MXCSR Mask */ + + /* 8*16 bytes for each FP-reg = 128 bytes: */ + u32 st_space[32]; + + /* 16*16 bytes for each XMM-reg = 256 bytes: */ + u32 xmm_space[64]; + + u32 padding[12]; + + union { + u32 padding1[12]; + u32 sw_reserved[12]; + }; + +} __attribute__((aligned(16))); + +/* Default value for fxregs_state.mxcsr: */ +#define MXCSR_DEFAULT 0x1f80 + +/* + * Software based FPU emulation state. This is arbitrary really, + * it matches the x87 format to make it easier to understand: + */ +struct swregs_state { + u32 cwd; + u32 swd; + u32 twd; + u32 fip; + u32 fcs; + u32 foo; + u32 fos; + /* 8*10 bytes for each FP-reg = 80 bytes: */ + u32 st_space[20]; + u8 ftop; + u8 changed; + u8 lookahead; + u8 no_update; + u8 rm; + u8 alimit; + struct math_emu_info *info; + u32 entry_eip; +}; + +/* + * List of XSAVE features Linux knows about: + */ +enum xfeature_bit { + XSTATE_BIT_FP, + XSTATE_BIT_SSE, + XSTATE_BIT_YMM, + XSTATE_BIT_BNDREGS, + XSTATE_BIT_BNDCSR, + XSTATE_BIT_OPMASK, + XSTATE_BIT_ZMM_Hi256, + XSTATE_BIT_Hi16_ZMM, + + XFEATURES_NR_MAX, +}; + +#define XSTATE_FP (1 << XSTATE_BIT_FP) +#define XSTATE_SSE (1 << XSTATE_BIT_SSE) +#define XSTATE_YMM (1 << XSTATE_BIT_YMM) +#define XSTATE_BNDREGS (1 << XSTATE_BIT_BNDREGS) +#define XSTATE_BNDCSR (1 << XSTATE_BIT_BNDCSR) +#define XSTATE_OPMASK (1 << XSTATE_BIT_OPMASK) +#define XSTATE_ZMM_Hi256 (1 << XSTATE_BIT_ZMM_Hi256) +#define XSTATE_Hi16_ZMM (1 << XSTATE_BIT_Hi16_ZMM) + +#define XSTATE_FPSSE (XSTATE_FP | XSTATE_SSE) +#define XSTATE_AVX512 (XSTATE_OPMASK | XSTATE_ZMM_Hi256 | XSTATE_Hi16_ZMM) + +/* + * There are 16x 256-bit AVX registers named YMM0-YMM15. + * The low 128 bits are aliased to the 16 SSE registers (XMM0-XMM15) + * and are stored in 'struct fxregs_state::xmm_space[]'. + * + * The high 128 bits are stored here: + * 16x 128 bits == 256 bytes. + */ +struct ymmh_struct { + u8 ymmh_space[256]; +}; + +/* We don't support LWP yet: */ +struct lwp_struct { + u8 reserved[128]; +}; + +/* Intel MPX support: */ +struct bndreg { + u64 lower_bound; + u64 upper_bound; +} __packed; + +struct bndcsr { + u64 bndcfgu; + u64 bndstatus; +} __packed; + +struct mpx_struct { + struct bndreg bndreg[4]; + struct bndcsr bndcsr; +}; + +struct xstate_header { + u64 xfeatures; + u64 xcomp_bv; + u64 reserved[6]; +} __attribute__((packed)); + +/* New processor state extensions should be added here: */ +#define XSTATE_RESERVE (sizeof(struct ymmh_struct) + \ + sizeof(struct lwp_struct) + \ + sizeof(struct mpx_struct) ) +/* + * This is our most modern FPU state format, as saved by the XSAVE + * and restored by the XRSTOR instructions. + * + * It consists of a legacy fxregs portion, an xstate header and + * subsequent fixed size areas as defined by the xstate header. + * Not all CPUs support all the extensions. + */ +struct xregs_state { + struct fxregs_state i387; + struct xstate_header header; + u8 __reserved[XSTATE_RESERVE]; +} __attribute__ ((packed, aligned (64))); + +/* + * This is a union of all the possible FPU state formats + * put together, so that we can pick the right one runtime. + * + * The size of the structure is determined by the largest + * member - which is the xsave area: + */ +union fpregs_state { + struct fregs_state fsave; + struct fxregs_state fxsave; + struct swregs_state soft; + struct xregs_state xsave; +}; + +/* + * Highest level per task FPU state data structure that + * contains the FPU register state plus various FPU + * state fields: + */ +struct fpu { + /* + * @state: + * + * In-memory copy of all FPU registers that we save/restore + * over context switches. If the task is using the FPU then + * the registers in the FPU are more recent than this state + * copy. If the task context-switches away then they get + * saved here and represent the FPU state. + * + * After context switches there may be a (short) time period + * during which the in-FPU hardware registers are unchanged + * and still perfectly match this state, if the tasks + * scheduled afterwards are not using the FPU. + * + * This is the 'lazy restore' window of optimization, which + * we track though 'fpu_fpregs_owner_ctx' and 'fpu->last_cpu'. + * + * We detect whether a subsequent task uses the FPU via setting + * CR0::TS to 1, which causes any FPU use to raise a #NM fault. + * + * During this window, if the task gets scheduled again, we + * might be able to skip having to do a restore from this + * memory buffer to the hardware registers - at the cost of + * incurring the overhead of #NM fault traps. + * + * Note that on modern CPUs that support the XSAVEOPT (or other + * optimized XSAVE instructions), we don't use #NM traps anymore, + * as the hardware can track whether FPU registers need saving + * or not. On such CPUs we activate the non-lazy ('eagerfpu') + * logic, which unconditionally saves/restores all FPU state + * across context switches. (if FPU state exists.) + */ + union fpregs_state state; + + /* + * @last_cpu: + * + * Records the last CPU on which this context was loaded into + * FPU registers. (In the lazy-restore case we might be + * able to reuse FPU registers across multiple context switches + * this way, if no intermediate task used the FPU.) + * + * A value of -1 is used to indicate that the FPU state in context + * memory is newer than the FPU state in registers, and that the + * FPU state should be reloaded next time the task is run. + */ + unsigned int last_cpu; + + /* + * @fpstate_active: + * + * This flag indicates whether this context is active: if the task + * is not running then we can restore from this context, if the task + * is running then we should save into this context. + */ + unsigned char fpstate_active; + + /* + * @fpregs_active: + * + * This flag determines whether a given context is actively + * loaded into the FPU's registers and that those registers + * represent the task's current FPU state. + * + * Note the interaction with fpstate_active: + * + * # task does not use the FPU: + * fpstate_active == 0 + * + * # task uses the FPU and regs are active: + * fpstate_active == 1 && fpregs_active == 1 + * + * # the regs are inactive but still match fpstate: + * fpstate_active == 1 && fpregs_active == 0 && fpregs_owner == fpu + * + * The third state is what we use for the lazy restore optimization + * on lazy-switching CPUs. + */ + unsigned char fpregs_active; + + /* + * @counter: + * + * This counter contains the number of consecutive context switches + * during which the FPU stays used. If this is over a threshold, the + * lazy FPU restore logic becomes eager, to save the trap overhead. + * This is an unsigned char so that after 256 iterations the counter + * wraps and the context switch behavior turns lazy again; this is to + * deal with bursty apps that only use the FPU for a short time: + */ + unsigned char counter; +}; + +#endif /* _ASM_X86_FPU_H */ diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h new file mode 100644 index 000000000000..4656b25bb9a7 --- /dev/null +++ b/arch/x86/include/asm/fpu/xstate.h @@ -0,0 +1,46 @@ +#ifndef __ASM_X86_XSAVE_H +#define __ASM_X86_XSAVE_H + +#include <linux/types.h> +#include <asm/processor.h> +#include <linux/uaccess.h> + +/* Bit 63 of XCR0 is reserved for future expansion */ +#define XSTATE_EXTEND_MASK (~(XSTATE_FPSSE | (1ULL << 63))) + +#define XSTATE_CPUID 0x0000000d + +#define FXSAVE_SIZE 512 + +#define XSAVE_HDR_SIZE 64 +#define XSAVE_HDR_OFFSET FXSAVE_SIZE + +#define XSAVE_YMM_SIZE 256 +#define XSAVE_YMM_OFFSET (XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET) + +/* Supported features which support lazy state saving */ +#define XSTATE_LAZY (XSTATE_FP | XSTATE_SSE | XSTATE_YMM \ + | XSTATE_OPMASK | XSTATE_ZMM_Hi256 | XSTATE_Hi16_ZMM) + +/* Supported features which require eager state saving */ +#define XSTATE_EAGER (XSTATE_BNDREGS | XSTATE_BNDCSR) + +/* All currently supported features */ +#define XCNTXT_MASK (XSTATE_LAZY | XSTATE_EAGER) + +#ifdef CONFIG_X86_64 +#define REX_PREFIX "0x48, " +#else +#define REX_PREFIX +#endif + +extern unsigned int xstate_size; +extern u64 xfeatures_mask; +extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS]; + +extern void update_regset_xstate_info(unsigned int size, u64 xstate_mask); + +void *get_xsave_addr(struct xregs_state *xsave, int xstate); +const void *get_xsave_field_ptr(int xstate_field); + +#endif diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h deleted file mode 100644 index 6eb6fcb83f63..000000000000 --- a/arch/x86/include/asm/i387.h +++ /dev/null @@ -1,108 +0,0 @@ -/* - * Copyright (C) 1994 Linus Torvalds - * - * Pentium III FXSR, SSE support - * General FPU state handling cleanups - * Gareth Hughes <gareth@valinux.com>, May 2000 - * x86-64 work by Andi Kleen 2002 - */ - -#ifndef _ASM_X86_I387_H -#define _ASM_X86_I387_H - -#ifndef __ASSEMBLY__ - -#include <linux/sched.h> -#include <linux/hardirq.h> - -struct pt_regs; -struct user_i387_struct; - -extern int init_fpu(struct task_struct *child); -extern void fpu_finit(struct fpu *fpu); -extern int dump_fpu(struct pt_regs *, struct user_i387_struct *); -extern void math_state_restore(void); - -extern bool irq_fpu_usable(void); - -/* - * Careful: __kernel_fpu_begin/end() must be called with preempt disabled - * and they don't touch the preempt state on their own. - * If you enable preemption after __kernel_fpu_begin(), preempt notifier - * should call the __kernel_fpu_end() to prevent the kernel/user FPU - * state from getting corrupted. KVM for example uses this model. - * - * All other cases use kernel_fpu_begin/end() which disable preemption - * during kernel FPU usage. - */ -extern void __kernel_fpu_begin(void); -extern void __kernel_fpu_end(void); - -static inline void kernel_fpu_begin(void) -{ - preempt_disable(); - WARN_ON_ONCE(!irq_fpu_usable()); - __kernel_fpu_begin(); -} - -static inline void kernel_fpu_end(void) -{ - __kernel_fpu_end(); - preempt_enable(); -} - -/* Must be called with preempt disabled */ -extern void kernel_fpu_disable(void); -extern void kernel_fpu_enable(void); - -/* - * Some instructions like VIA's padlock instructions generate a spurious - * DNA fault but don't modify SSE registers. And these instructions - * get used from interrupt context as well. To prevent these kernel instructions - * in interrupt context interacting wrongly with other user/kernel fpu usage, we - * should use them only in the context of irq_ts_save/restore() - */ -static inline int irq_ts_save(void) -{ - /* - * If in process context and not atomic, we can take a spurious DNA fault. - * Otherwise, doing clts() in process context requires disabling preemption - * or some heavy lifting like kernel_fpu_begin() - */ - if (!in_atomic()) - return 0; - - if (read_cr0() & X86_CR0_TS) { - clts(); - return 1; - } - - return 0; -} - -static inline void irq_ts_restore(int TS_state) -{ - if (TS_state) - stts(); -} - -/* - * The question "does this thread have fpu access?" - * is slightly racy, since preemption could come in - * and revoke it immediately after the test. - * - * However, even in that very unlikely scenario, - * we can just assume we have FPU access - typically - * to save the FP state - we'll just take a #NM - * fault and get the FPU access back. - */ -static inline int user_has_fpu(void) -{ - return current->thread.fpu.has_fpu; -} - -extern void unlazy_fpu(struct task_struct *tsk); - -#endif /* __ASSEMBLY__ */ - -#endif /* _ASM_X86_I387_H */ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index f4a555beef19..f8c0ec3a4a97 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1002,8 +1002,6 @@ void kvm_pic_clear_all(struct kvm_pic *pic, int irq_source_id); void kvm_inject_nmi(struct kvm_vcpu *vcpu); -int fx_init(struct kvm_vcpu *vcpu); - void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new, int bytes); int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn); diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index 2fb20d6f7e23..9e6278c7140e 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -1,6 +1,8 @@ #ifndef _ASM_X86_MICROCODE_H #define _ASM_X86_MICROCODE_H +#include <linux/earlycpio.h> + #define native_rdmsr(msr, val1, val2) \ do { \ u64 __val = native_read_msr((msr)); \ @@ -152,6 +154,7 @@ extern void __init load_ucode_bsp(void); extern void load_ucode_ap(void); extern int __init save_microcode_in_initrd(void); void reload_early_microcode(void); +extern bool get_builtin_firmware(struct cpio_data *cd, const char *name); #else static inline void __init load_ucode_bsp(void) {} static inline void load_ucode_ap(void) {} @@ -160,6 +163,9 @@ static inline int __init save_microcode_in_initrd(void) return 0; } static inline void reload_early_microcode(void) {} +static inline bool get_builtin_firmware(struct cpio_data *cd, const char *name) +{ + return false; +} #endif - #endif /* _ASM_X86_MICROCODE_H */ diff --git a/arch/x86/include/asm/microcode_amd.h b/arch/x86/include/asm/microcode_amd.h index af935397e053..ac6d328977a6 100644 --- a/arch/x86/include/asm/microcode_amd.h +++ b/arch/x86/include/asm/microcode_amd.h @@ -65,12 +65,12 @@ extern enum ucode_state load_microcode_amd(int cpu, u8 family, const u8 *data, s extern u8 amd_ucode_patch[PATCH_MAX_SIZE]; #ifdef CONFIG_MICROCODE_AMD_EARLY -extern void __init load_ucode_amd_bsp(void); +extern void __init load_ucode_amd_bsp(unsigned int family); extern void load_ucode_amd_ap(void); extern int __init save_microcode_in_initrd_amd(void); void reload_ucode_amd(void); #else -static inline void __init load_ucode_amd_bsp(void) {} +static inline void __init load_ucode_amd_bsp(unsigned int family) {} static inline void load_ucode_amd_ap(void) {} static inline int __init save_microcode_in_initrd_amd(void) { return -EINVAL; } void reload_ucode_amd(void) {} diff --git a/arch/x86/include/asm/microcode_intel.h b/arch/x86/include/asm/microcode_intel.h index 2b9209c46ca9..7991c606125d 100644 --- a/arch/x86/include/asm/microcode_intel.h +++ b/arch/x86/include/asm/microcode_intel.h @@ -51,20 +51,11 @@ struct extended_sigtable { (((struct microcode_intel *)mc)->hdr.datasize ? \ ((struct microcode_intel *)mc)->hdr.datasize : DEFAULT_UCODE_DATASIZE) -#define sigmatch(s1, s2, p1, p2) \ - (((s1) == (s2)) && (((p1) & (p2)) || (((p1) == 0) && ((p2) == 0)))) - #define exttable_size(et) ((et)->count * EXT_SIGNATURE_SIZE + EXT_HEADER_SIZE) -extern int get_matching_microcode(unsigned int csig, int cpf, int rev, void *mc); +extern int has_newer_microcode(void *mc, unsigned int csig, int cpf, int rev); extern int microcode_sanity_check(void *mc, int print_err); -extern int get_matching_sig(unsigned int csig, int cpf, int rev, void *mc); - -static inline int -revision_is_newer(struct microcode_header_intel *mc_header, int rev) -{ - return (mc_header->rev <= rev) ? 0 : 1; -} +extern int find_matching_signature(void *mc, unsigned int csig, int cpf); #ifdef CONFIG_MICROCODE_INTEL_EARLY extern void __init load_ucode_intel_bsp(void); diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 883f6b933fa4..5e8daee7c5c9 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -142,6 +142,19 @@ static inline void arch_exit_mmap(struct mm_struct *mm) paravirt_arch_exit_mmap(mm); } +#ifdef CONFIG_X86_64 +static inline bool is_64bit_mm(struct mm_struct *mm) +{ + return !config_enabled(CONFIG_IA32_EMULATION) || + !(mm->context.ia32_compat == TIF_IA32); +} +#else +static inline bool is_64bit_mm(struct mm_struct *mm) +{ + return false; +} +#endif + static inline void arch_bprm_mm_init(struct mm_struct *mm, struct vm_area_struct *vma) { diff --git a/arch/x86/include/asm/mpx.h b/arch/x86/include/asm/mpx.h index a952a13d59a7..7a35495275a9 100644 --- a/arch/x86/include/asm/mpx.h +++ b/arch/x86/include/asm/mpx.h @@ -13,55 +13,50 @@ #define MPX_BNDCFG_ENABLE_FLAG 0x1 #define MPX_BD_ENTRY_VALID_FLAG 0x1 -#ifdef CONFIG_X86_64 - -/* upper 28 bits [47:20] of the virtual address in 64-bit used to - * index into bounds directory (BD). - */ -#define MPX_BD_ENTRY_OFFSET 28 -#define MPX_BD_ENTRY_SHIFT 3 -/* bits [19:3] of the virtual address in 64-bit used to index into - * bounds table (BT). +/* + * The upper 28 bits [47:20] of the virtual address in 64-bit + * are used to index into bounds directory (BD). + * + * The directory is 2G (2^31) in size, and with 8-byte entries + * it has 2^28 entries. */ -#define MPX_BT_ENTRY_OFFSET 17 -#define MPX_BT_ENTRY_SHIFT 5 -#define MPX_IGN_BITS 3 -#define MPX_BD_ENTRY_TAIL 3 +#define MPX_BD_SIZE_BYTES_64 (1UL<<31) +#define MPX_BD_ENTRY_BYTES_64 8 +#define MPX_BD_NR_ENTRIES_64 (MPX_BD_SIZE_BYTES_64/MPX_BD_ENTRY_BYTES_64) -#else - -#define MPX_BD_ENTRY_OFFSET 20 -#define MPX_BD_ENTRY_SHIFT 2 -#define MPX_BT_ENTRY_OFFSET 10 -#define MPX_BT_ENTRY_SHIFT 4 -#define MPX_IGN_BITS 2 -#define MPX_BD_ENTRY_TAIL 2 +/* + * The 32-bit directory is 4MB (2^22) in size, and with 4-byte + * entries it has 2^20 entries. + */ +#define MPX_BD_SIZE_BYTES_32 (1UL<<22) +#define MPX_BD_ENTRY_BYTES_32 4 +#define MPX_BD_NR_ENTRIES_32 (MPX_BD_SIZE_BYTES_32/MPX_BD_ENTRY_BYTES_32) -#endif +/* + * A 64-bit table is 4MB total in size, and an entry is + * 4 64-bit pointers in size. + */ +#define MPX_BT_SIZE_BYTES_64 (1UL<<22) +#define MPX_BT_ENTRY_BYTES_64 32 +#define MPX_BT_NR_ENTRIES_64 (MPX_BT_SIZE_BYTES_64/MPX_BT_ENTRY_BYTES_64) -#define MPX_BD_SIZE_BYTES (1UL<<(MPX_BD_ENTRY_OFFSET+MPX_BD_ENTRY_SHIFT)) -#define MPX_BT_SIZE_BYTES (1UL<<(MPX_BT_ENTRY_OFFSET+MPX_BT_ENTRY_SHIFT)) +/* + * A 32-bit table is 16kB total in size, and an entry is + * 4 32-bit pointers in size. + */ +#define MPX_BT_SIZE_BYTES_32 (1UL<<14) +#define MPX_BT_ENTRY_BYTES_32 16 +#define MPX_BT_NR_ENTRIES_32 (MPX_BT_SIZE_BYTES_32/MPX_BT_ENTRY_BYTES_32) #define MPX_BNDSTA_TAIL 2 #define MPX_BNDCFG_TAIL 12 #define MPX_BNDSTA_ADDR_MASK (~((1UL<<MPX_BNDSTA_TAIL)-1)) #define MPX_BNDCFG_ADDR_MASK (~((1UL<<MPX_BNDCFG_TAIL)-1)) -#define MPX_BT_ADDR_MASK (~((1UL<<MPX_BD_ENTRY_TAIL)-1)) - -#define MPX_BNDCFG_ADDR_MASK (~((1UL<<MPX_BNDCFG_TAIL)-1)) #define MPX_BNDSTA_ERROR_CODE 0x3 -#define MPX_BD_ENTRY_MASK ((1<<MPX_BD_ENTRY_OFFSET)-1) -#define MPX_BT_ENTRY_MASK ((1<<MPX_BT_ENTRY_OFFSET)-1) -#define MPX_GET_BD_ENTRY_OFFSET(addr) ((((addr)>>(MPX_BT_ENTRY_OFFSET+ \ - MPX_IGN_BITS)) & MPX_BD_ENTRY_MASK) << MPX_BD_ENTRY_SHIFT) -#define MPX_GET_BT_ENTRY_OFFSET(addr) ((((addr)>>MPX_IGN_BITS) & \ - MPX_BT_ENTRY_MASK) << MPX_BT_ENTRY_SHIFT) - #ifdef CONFIG_X86_INTEL_MPX -siginfo_t *mpx_generate_siginfo(struct pt_regs *regs, - struct xsave_struct *xsave_buf); -int mpx_handle_bd_fault(struct xsave_struct *xsave_buf); +siginfo_t *mpx_generate_siginfo(struct pt_regs *regs); +int mpx_handle_bd_fault(void); static inline int kernel_managing_mpx_tables(struct mm_struct *mm) { return (mm->bd_addr != MPX_INVALID_BOUNDS_DIR); @@ -77,12 +72,11 @@ static inline void mpx_mm_init(struct mm_struct *mm) void mpx_notify_unmap(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long start, unsigned long end); #else -static inline siginfo_t *mpx_generate_siginfo(struct pt_regs *regs, - struct xsave_struct *xsave_buf) +static inline siginfo_t *mpx_generate_siginfo(struct pt_regs *regs) { return NULL; } -static inline int mpx_handle_bd_fault(struct xsave_struct *xsave_buf) +static inline int mpx_handle_bd_fault(void) { return -EINVAL; } diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h index 8f3271842533..dca71714f860 100644 --- a/arch/x86/include/asm/preempt.h +++ b/arch/x86/include/asm/preempt.h @@ -99,11 +99,9 @@ static __always_inline bool should_resched(void) extern asmlinkage void ___preempt_schedule(void); # define __preempt_schedule() asm ("call ___preempt_schedule") extern asmlinkage void preempt_schedule(void); -# ifdef CONFIG_CONTEXT_TRACKING - extern asmlinkage void ___preempt_schedule_context(void); -# define __preempt_schedule_context() asm ("call ___preempt_schedule_context") - extern asmlinkage void preempt_schedule_context(void); -# endif + extern asmlinkage void ___preempt_schedule_notrace(void); +# define __preempt_schedule_notrace() asm ("call ___preempt_schedule_notrace") + extern asmlinkage void preempt_schedule_notrace(void); #endif #endif /* __ASM_PREEMPT_H */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 23ba6765b718..43e6519df0d5 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -21,6 +21,7 @@ struct mm_struct; #include <asm/desc_defs.h> #include <asm/nops.h> #include <asm/special_insns.h> +#include <asm/fpu/types.h> #include <linux/personality.h> #include <linux/cpumask.h> @@ -52,11 +53,16 @@ static inline void *current_text_addr(void) return pc; } +/* + * These alignment constraints are for performance in the vSMP case, + * but in the task_struct case we must also meet hardware imposed + * alignment requirements of the FPU state: + */ #ifdef CONFIG_X86_VSMP # define ARCH_MIN_TASKALIGN (1 << INTERNODE_CACHE_SHIFT) # define ARCH_MIN_MMSTRUCT_ALIGN (1 << INTERNODE_CACHE_SHIFT) #else -# define ARCH_MIN_TASKALIGN 16 +# define ARCH_MIN_TASKALIGN __alignof__(union fpregs_state) # define ARCH_MIN_MMSTRUCT_ALIGN 0 #endif @@ -166,7 +172,6 @@ extern const struct seq_operations cpuinfo_op; #define cache_line_size() (boot_cpu_data.x86_cache_alignment) extern void cpu_detect(struct cpuinfo_x86 *c); -extern void fpu_detect(struct cpuinfo_x86 *c); extern void early_cpu_init(void); extern void identify_boot_cpu(void); @@ -313,128 +318,6 @@ struct orig_ist { unsigned long ist[7]; }; -#define MXCSR_DEFAULT 0x1f80 - -struct i387_fsave_struct { - u32 cwd; /* FPU Control Word */ - u32 swd; /* FPU Status Word */ - u32 twd; /* FPU Tag Word */ - u32 fip; /* FPU IP Offset */ - u32 fcs; /* FPU IP Selector */ - u32 foo; /* FPU Operand Pointer Offset */ - u32 fos; /* FPU Operand Pointer Selector */ - - /* 8*10 bytes for each FP-reg = 80 bytes: */ - u32 st_space[20]; - - /* Software status information [not touched by FSAVE ]: */ - u32 status; -}; - -struct i387_fxsave_struct { - u16 cwd; /* Control Word */ - u16 swd; /* Status Word */ - u16 twd; /* Tag Word */ - u16 fop; /* Last Instruction Opcode */ - union { - struct { - u64 rip; /* Instruction Pointer */ - u64 rdp; /* Data Pointer */ - }; - struct { - u32 fip; /* FPU IP Offset */ - u32 fcs; /* FPU IP Selector */ - u32 foo; /* FPU Operand Offset */ - u32 fos; /* FPU Operand Selector */ - }; - }; - u32 mxcsr; /* MXCSR Register State */ - u32 mxcsr_mask; /* MXCSR Mask */ - - /* 8*16 bytes for each FP-reg = 128 bytes: */ - u32 st_space[32]; - - /* 16*16 bytes for each XMM-reg = 256 bytes: */ - u32 xmm_space[64]; - - u32 padding[12]; - - union { - u32 padding1[12]; - u32 sw_reserved[12]; - }; - -} __attribute__((aligned(16))); - -struct i387_soft_struct { - u32 cwd; - u32 swd; - u32 twd; - u32 fip; - u32 fcs; - u32 foo; - u32 fos; - /* 8*10 bytes for each FP-reg = 80 bytes: */ - u32 st_space[20]; - u8 ftop; - u8 changed; - u8 lookahead; - u8 no_update; - u8 rm; - u8 alimit; - struct math_emu_info *info; - u32 entry_eip; -}; - -struct ymmh_struct { - /* 16 * 16 bytes for each YMMH-reg = 256 bytes */ - u32 ymmh_space[64]; -}; - -/* We don't support LWP yet: */ -struct lwp_struct { - u8 reserved[128]; -}; - -struct bndreg { - u64 lower_bound; - u64 upper_bound; -} __packed; - -struct bndcsr { - u64 bndcfgu; - u64 bndstatus; -} __packed; - -struct xsave_hdr_struct { - u64 xstate_bv; - u64 xcomp_bv; - u64 reserved[6]; -} __attribute__((packed)); - -struct xsave_struct { - struct i387_fxsave_struct i387; - struct xsave_hdr_struct xsave_hdr; - struct ymmh_struct ymmh; - struct lwp_struct lwp; - struct bndreg bndreg[4]; - struct bndcsr bndcsr; - /* new processor state extensions will go here */ -} __attribute__ ((packed, aligned (64))); - -union thread_xstate { - struct i387_fsave_struct fsave; - struct i387_fxsave_struct fxsave; - struct i387_soft_struct soft; - struct xsave_struct xsave; -}; - -struct fpu { - unsigned int last_cpu; - unsigned int has_fpu; - union thread_xstate *state; -}; - #ifdef CONFIG_X86_64 DECLARE_PER_CPU(struct orig_ist, orig_ist); @@ -483,8 +366,6 @@ DECLARE_PER_CPU(struct irq_stack *, softirq_stack); #endif /* X86_64 */ extern unsigned int xstate_size; -extern void free_thread_xstate(struct task_struct *); -extern struct kmem_cache *task_xstate_cachep; struct perf_event; @@ -508,6 +389,10 @@ struct thread_struct { unsigned long fs; #endif unsigned long gs; + + /* Floating point and extended processor state */ + struct fpu fpu; + /* Save middle states of ptrace breakpoints */ struct perf_event *ptrace_bps[HBP_NUM]; /* Debug status used for traps, single steps, etc... */ @@ -518,8 +403,6 @@ struct thread_struct { unsigned long cr2; unsigned long trap_nr; unsigned long error_code; - /* floating point and extended processor state */ - struct fpu fpu; #ifdef CONFIG_X86_32 /* Virtual 86 mode info */ struct vm86_struct __user *vm86_info; @@ -535,15 +418,6 @@ struct thread_struct { unsigned long iopl; /* Max allowed port in the bitmap, in bytes: */ unsigned io_bitmap_max; - /* - * fpu_counter contains the number of consecutive context switches - * that the FPU is used. If this is over a threshold, the lazy fpu - * saving becomes unlazy to save the trap. This is an unsigned char - * so that after 256 times the counter wraps and the behavior turns - * lazy again; this to deal with bursty apps that only use FPU for - * a short time - */ - unsigned char fpu_counter; }; /* @@ -928,24 +802,25 @@ extern int get_tsc_mode(unsigned long adr); extern int set_tsc_mode(unsigned int val); /* Register/unregister a process' MPX related resource */ -#define MPX_ENABLE_MANAGEMENT(tsk) mpx_enable_management((tsk)) -#define MPX_DISABLE_MANAGEMENT(tsk) mpx_disable_management((tsk)) +#define MPX_ENABLE_MANAGEMENT() mpx_enable_management() +#define MPX_DISABLE_MANAGEMENT() mpx_disable_management() #ifdef CONFIG_X86_INTEL_MPX -extern int mpx_enable_management(struct task_struct *tsk); -extern int mpx_disable_management(struct task_struct *tsk); +extern int mpx_enable_management(void); +extern int mpx_disable_management(void); #else -static inline int mpx_enable_management(struct task_struct *tsk) +static inline int mpx_enable_management(void) { return -EINVAL; } -static inline int mpx_disable_management(struct task_struct *tsk) +static inline int mpx_disable_management(void) { return -EINVAL; } #endif /* CONFIG_X86_INTEL_MPX */ extern u16 amd_get_nb_id(int cpu); +extern u32 amd_get_nodes_per_socket(void); static inline uint32_t hypervisor_cpuid_base(const char *sig, uint32_t leaves) { diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index 19507ffa5d28..5fabf1362942 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -107,7 +107,7 @@ static inline unsigned long regs_return_value(struct pt_regs *regs) static inline int user_mode(struct pt_regs *regs) { #ifdef CONFIG_X86_32 - return (regs->cs & SEGMENT_RPL_MASK) == USER_RPL; + return ((regs->cs & SEGMENT_RPL_MASK) | (regs->flags & X86_VM_MASK)) >= USER_RPL; #else return !!(regs->cs & 3); #endif diff --git a/arch/x86/include/asm/simd.h b/arch/x86/include/asm/simd.h index ee80b92f0096..6c8a7ed13365 100644 --- a/arch/x86/include/asm/simd.h +++ b/arch/x86/include/asm/simd.h @@ -1,5 +1,5 @@ -#include <asm/i387.h> +#include <asm/fpu/api.h> /* * may_use_simd - whether it is allowable at this time to issue SIMD diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index 17a8dced12da..222a6a3ca2b5 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -37,16 +37,6 @@ DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map); DECLARE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id); DECLARE_PER_CPU_READ_MOSTLY(int, cpu_number); -static inline struct cpumask *cpu_sibling_mask(int cpu) -{ - return per_cpu(cpu_sibling_map, cpu); -} - -static inline struct cpumask *cpu_core_mask(int cpu) -{ - return per_cpu(cpu_core_map, cpu); -} - static inline struct cpumask *cpu_llc_shared_mask(int cpu) { return per_cpu(cpu_llc_shared_map, cpu); diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h index 6a998598f172..c2e00bb2a136 100644 --- a/arch/x86/include/asm/stackprotector.h +++ b/arch/x86/include/asm/stackprotector.h @@ -39,7 +39,9 @@ #include <asm/processor.h> #include <asm/percpu.h> #include <asm/desc.h> + #include <linux/random.h> +#include <linux/sched.h> /* * 24 byte read-only segment initializer for stack canary. Linker diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h index 552d6c90a6d4..d1793f06854d 100644 --- a/arch/x86/include/asm/suspend_32.h +++ b/arch/x86/include/asm/suspend_32.h @@ -7,7 +7,7 @@ #define _ASM_X86_SUSPEND_32_H #include <asm/desc.h> -#include <asm/i387.h> +#include <asm/fpu/api.h> /* image of the saved processor state */ struct saved_context { diff --git a/arch/x86/include/asm/suspend_64.h b/arch/x86/include/asm/suspend_64.h index bc6232834bab..7ebf0ebe4e68 100644 --- a/arch/x86/include/asm/suspend_64.h +++ b/arch/x86/include/asm/suspend_64.h @@ -7,7 +7,7 @@ #define _ASM_X86_SUSPEND_64_H #include <asm/desc.h> -#include <asm/i387.h> +#include <asm/fpu/api.h> /* * Image of the saved processor state, used by the low level ACPI suspend to diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index 8d717faeed22..0fb46482dfde 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -124,7 +124,7 @@ extern const struct cpumask *cpu_coregroup_mask(int cpu); #ifdef ENABLE_TOPO_DEFINES #define topology_core_cpumask(cpu) (per_cpu(cpu_core_map, cpu)) -#define topology_thread_cpumask(cpu) (per_cpu(cpu_sibling_map, cpu)) +#define topology_sibling_cpumask(cpu) (per_cpu(cpu_sibling_map, cpu)) #endif static inline void arch_fix_phys_package_id(int num, u32 slot) diff --git a/arch/x86/include/asm/trace/mpx.h b/arch/x86/include/asm/trace/mpx.h new file mode 100644 index 000000000000..173dd3ba108c --- /dev/null +++ b/arch/x86/include/asm/trace/mpx.h @@ -0,0 +1,132 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM mpx + +#if !defined(_TRACE_MPX_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_MPX_H + +#include <linux/tracepoint.h> + +#ifdef CONFIG_X86_INTEL_MPX + +TRACE_EVENT(mpx_bounds_register_exception, + + TP_PROTO(void *addr_referenced, + const struct bndreg *bndreg), + TP_ARGS(addr_referenced, bndreg), + + TP_STRUCT__entry( + __field(void *, addr_referenced) + __field(u64, lower_bound) + __field(u64, upper_bound) + ), + + TP_fast_assign( + __entry->addr_referenced = addr_referenced; + __entry->lower_bound = bndreg->lower_bound; + __entry->upper_bound = bndreg->upper_bound; + ), + /* + * Note that we are printing out the '~' of the upper + * bounds register here. It is actually stored in its + * one's complement form so that its 'init' state + * corresponds to all 0's. But, that looks like + * gibberish when printed out, so print out the 1's + * complement instead of the actual value here. Note + * though that you still need to specify filters for the + * actual value, not the displayed one. + */ + TP_printk("address referenced: 0x%p bounds: lower: 0x%llx ~upper: 0x%llx", + __entry->addr_referenced, + __entry->lower_bound, + ~__entry->upper_bound + ) +); + +TRACE_EVENT(bounds_exception_mpx, + + TP_PROTO(const struct bndcsr *bndcsr), + TP_ARGS(bndcsr), + + TP_STRUCT__entry( + __field(u64, bndcfgu) + __field(u64, bndstatus) + ), + + TP_fast_assign( + /* need to get rid of the 'const' on bndcsr */ + __entry->bndcfgu = (u64)bndcsr->bndcfgu; + __entry->bndstatus = (u64)bndcsr->bndstatus; + ), + + TP_printk("bndcfgu:0x%llx bndstatus:0x%llx", + __entry->bndcfgu, + __entry->bndstatus) +); + +DECLARE_EVENT_CLASS(mpx_range_trace, + + TP_PROTO(unsigned long start, + unsigned long end), + TP_ARGS(start, end), + + TP_STRUCT__entry( + __field(unsigned long, start) + __field(unsigned long, end) + ), + + TP_fast_assign( + __entry->start = start; + __entry->end = end; + ), + + TP_printk("[0x%p:0x%p]", + (void *)__entry->start, + (void *)__entry->end + ) +); + +DEFINE_EVENT(mpx_range_trace, mpx_unmap_zap, + TP_PROTO(unsigned long start, unsigned long end), + TP_ARGS(start, end) +); + +DEFINE_EVENT(mpx_range_trace, mpx_unmap_search, + TP_PROTO(unsigned long start, unsigned long end), + TP_ARGS(start, end) +); + +TRACE_EVENT(mpx_new_bounds_table, + + TP_PROTO(unsigned long table_vaddr), + TP_ARGS(table_vaddr), + + TP_STRUCT__entry( + __field(unsigned long, table_vaddr) + ), + + TP_fast_assign( + __entry->table_vaddr = table_vaddr; + ), + + TP_printk("table vaddr:%p", (void *)__entry->table_vaddr) +); + +#else + +/* + * This gets used outside of MPX-specific code, so we need a stub. + */ +static inline void trace_bounds_exception_mpx(const struct bndcsr *bndcsr) +{ +} + +#endif /* CONFIG_X86_INTEL_MPX */ + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH asm/trace/ +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE mpx +#endif /* _TRACE_MPX_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index ace9dec050b1..a8df874f3e88 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -74,7 +74,8 @@ static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, un * @addr: User space pointer to start of block to check * @size: Size of block to check * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * Checks if a pointer to a block of memory in user space is valid. * @@ -145,7 +146,8 @@ __typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL)) * @x: Variable to store result. * @ptr: Source address, in user space. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * This macro copies a single simple variable from user space to kernel * space. It supports simple types like char and int, but not larger @@ -240,7 +242,8 @@ extern void __put_user_8(void); * @x: Value to copy to user space. * @ptr: Destination address, in user space. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * This macro copies a single simple value from kernel space to user * space. It supports simple types like char and int, but not larger @@ -455,7 +458,8 @@ struct __large_struct { unsigned long buf[100]; }; * @x: Variable to store result. * @ptr: Source address, in user space. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * This macro copies a single simple variable from user space to kernel * space. It supports simple types like char and int, but not larger @@ -479,7 +483,8 @@ struct __large_struct { unsigned long buf[100]; }; * @x: Value to copy to user space. * @ptr: Destination address, in user space. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * This macro copies a single simple value from kernel space to user * space. It supports simple types like char and int, but not larger diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h index 0ed5504c6060..f5dcb5204dcd 100644 --- a/arch/x86/include/asm/uaccess_32.h +++ b/arch/x86/include/asm/uaccess_32.h @@ -74,7 +74,8 @@ __copy_to_user_inatomic(void __user *to, const void *from, unsigned long n) * @from: Source address, in kernel space. * @n: Number of bytes to copy. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * Copy data from kernel space to user space. Caller must check * the specified block with access_ok() before calling this function. @@ -121,7 +122,8 @@ __copy_from_user_inatomic(void *to, const void __user *from, unsigned long n) * @from: Source address, in user space. * @n: Number of bytes to copy. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * Copy data from user space to kernel space. Caller must check * the specified block with access_ok() before calling this function. diff --git a/arch/x86/include/asm/user.h b/arch/x86/include/asm/user.h index ccab4af1646d..59a54e869f15 100644 --- a/arch/x86/include/asm/user.h +++ b/arch/x86/include/asm/user.h @@ -14,8 +14,8 @@ struct user_ymmh_regs { __u32 ymmh_space[64]; }; -struct user_xsave_hdr { - __u64 xstate_bv; +struct user_xstate_header { + __u64 xfeatures; __u64 reserved1[2]; __u64 reserved2[5]; }; @@ -41,11 +41,11 @@ struct user_xsave_hdr { * particular process/thread. * * Also when the user modifies certain state FP/SSE/etc through the - * ptrace interface, they must ensure that the xsave_hdr.xstate_bv + * ptrace interface, they must ensure that the header.xfeatures * bytes[512..519] of the memory layout are updated correspondingly. * i.e., for example when FP state is modified to a non-init state, - * xsave_hdr.xstate_bv's bit 0 must be set to '1', when SSE is modified to - * non-init state, xsave_hdr.xstate_bv's bit 1 must to be set to '1', etc. + * header.xfeatures's bit 0 must be set to '1', when SSE is modified to + * non-init state, header.xfeatures's bit 1 must to be set to '1', etc. */ #define USER_XSTATE_FX_SW_WORDS 6 #define USER_XSTATE_XCR0_WORD 0 @@ -55,7 +55,7 @@ struct user_xstateregs { __u64 fpx_space[58]; __u64 xstate_fx_sw[USER_XSTATE_FX_SW_WORDS]; } i387; - struct user_xsave_hdr xsave_hdr; + struct user_xstate_header header; struct user_ymmh_regs ymmh; /* further processor state extensions go here */ }; diff --git a/arch/x86/include/asm/xcr.h b/arch/x86/include/asm/xcr.h deleted file mode 100644 index f2cba4e79a23..000000000000 --- a/arch/x86/include/asm/xcr.h +++ /dev/null @@ -1,49 +0,0 @@ -/* -*- linux-c -*- ------------------------------------------------------- * - * - * Copyright 2008 rPath, Inc. - All Rights Reserved - * - * This file is part of the Linux kernel, and is made available under - * the terms of the GNU General Public License version 2 or (at your - * option) any later version; incorporated herein by reference. - * - * ----------------------------------------------------------------------- */ - -/* - * asm-x86/xcr.h - * - * Definitions for the eXtended Control Register instructions - */ - -#ifndef _ASM_X86_XCR_H -#define _ASM_X86_XCR_H - -#define XCR_XFEATURE_ENABLED_MASK 0x00000000 - -#ifdef __KERNEL__ -# ifndef __ASSEMBLY__ - -#include <linux/types.h> - -static inline u64 xgetbv(u32 index) -{ - u32 eax, edx; - - asm volatile(".byte 0x0f,0x01,0xd0" /* xgetbv */ - : "=a" (eax), "=d" (edx) - : "c" (index)); - return eax + ((u64)edx << 32); -} - -static inline void xsetbv(u32 index, u64 value) -{ - u32 eax = value; - u32 edx = value >> 32; - - asm volatile(".byte 0x0f,0x01,0xd1" /* xsetbv */ - : : "a" (eax), "d" (edx), "c" (index)); -} - -# endif /* __ASSEMBLY__ */ -#endif /* __KERNEL__ */ - -#endif /* _ASM_X86_XCR_H */ diff --git a/arch/x86/include/asm/xor.h b/arch/x86/include/asm/xor.h index d8829751b3f8..1f5c5161ead6 100644 --- a/arch/x86/include/asm/xor.h +++ b/arch/x86/include/asm/xor.h @@ -36,7 +36,7 @@ * no advantages to be gotten from x86-64 here anyways. */ -#include <asm/i387.h> +#include <asm/fpu/api.h> #ifdef CONFIG_X86_32 /* reduce register pressure */ diff --git a/arch/x86/include/asm/xor_32.h b/arch/x86/include/asm/xor_32.h index ce05722e3c68..5a08bc8bff33 100644 --- a/arch/x86/include/asm/xor_32.h +++ b/arch/x86/include/asm/xor_32.h @@ -26,7 +26,7 @@ #define XO3(x, y) " pxor 8*("#x")(%4), %%mm"#y" ;\n" #define XO4(x, y) " pxor 8*("#x")(%5), %%mm"#y" ;\n" -#include <asm/i387.h> +#include <asm/fpu/api.h> static void xor_pII_mmx_2(unsigned long bytes, unsigned long *p1, unsigned long *p2) diff --git a/arch/x86/include/asm/xor_avx.h b/arch/x86/include/asm/xor_avx.h index 492b29802f57..7c0a517ec751 100644 --- a/arch/x86/include/asm/xor_avx.h +++ b/arch/x86/include/asm/xor_avx.h @@ -18,7 +18,7 @@ #ifdef CONFIG_AS_AVX #include <linux/compiler.h> -#include <asm/i387.h> +#include <asm/fpu/api.h> #define BLOCK4(i) \ BLOCK(32 * i, 0) \ diff --git a/arch/x86/include/asm/xsave.h b/arch/x86/include/asm/xsave.h deleted file mode 100644 index c9a6d68b8d62..000000000000 --- a/arch/x86/include/asm/xsave.h +++ /dev/null @@ -1,257 +0,0 @@ -#ifndef __ASM_X86_XSAVE_H -#define __ASM_X86_XSAVE_H - -#include <linux/types.h> -#include <asm/processor.h> - -#define XSTATE_CPUID 0x0000000d - -#define XSTATE_FP 0x1 -#define XSTATE_SSE 0x2 -#define XSTATE_YMM 0x4 -#define XSTATE_BNDREGS 0x8 -#define XSTATE_BNDCSR 0x10 -#define XSTATE_OPMASK 0x20 -#define XSTATE_ZMM_Hi256 0x40 -#define XSTATE_Hi16_ZMM 0x80 - -#define XSTATE_FPSSE (XSTATE_FP | XSTATE_SSE) -#define XSTATE_AVX512 (XSTATE_OPMASK | XSTATE_ZMM_Hi256 | XSTATE_Hi16_ZMM) -/* Bit 63 of XCR0 is reserved for future expansion */ -#define XSTATE_EXTEND_MASK (~(XSTATE_FPSSE | (1ULL << 63))) - -#define FXSAVE_SIZE 512 - -#define XSAVE_HDR_SIZE 64 -#define XSAVE_HDR_OFFSET FXSAVE_SIZE - -#define XSAVE_YMM_SIZE 256 -#define XSAVE_YMM_OFFSET (XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET) - -/* Supported features which support lazy state saving */ -#define XSTATE_LAZY (XSTATE_FP | XSTATE_SSE | XSTATE_YMM \ - | XSTATE_OPMASK | XSTATE_ZMM_Hi256 | XSTATE_Hi16_ZMM) - -/* Supported features which require eager state saving */ -#define XSTATE_EAGER (XSTATE_BNDREGS | XSTATE_BNDCSR) - -/* All currently supported features */ -#define XCNTXT_MASK (XSTATE_LAZY | XSTATE_EAGER) - -#ifdef CONFIG_X86_64 -#define REX_PREFIX "0x48, " -#else -#define REX_PREFIX -#endif - -extern unsigned int xstate_size; -extern u64 pcntxt_mask; -extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS]; -extern struct xsave_struct *init_xstate_buf; - -extern void xsave_init(void); -extern void update_regset_xstate_info(unsigned int size, u64 xstate_mask); -extern int init_fpu(struct task_struct *child); - -/* These macros all use (%edi)/(%rdi) as the single memory argument. */ -#define XSAVE ".byte " REX_PREFIX "0x0f,0xae,0x27" -#define XSAVEOPT ".byte " REX_PREFIX "0x0f,0xae,0x37" -#define XSAVES ".byte " REX_PREFIX "0x0f,0xc7,0x2f" -#define XRSTOR ".byte " REX_PREFIX "0x0f,0xae,0x2f" -#define XRSTORS ".byte " REX_PREFIX "0x0f,0xc7,0x1f" - -#define xstate_fault ".section .fixup,\"ax\"\n" \ - "3: movl $-1,%[err]\n" \ - " jmp 2b\n" \ - ".previous\n" \ - _ASM_EXTABLE(1b, 3b) \ - : [err] "=r" (err) - -/* - * This function is called only during boot time when x86 caps are not set - * up and alternative can not be used yet. - */ -static inline int xsave_state_booting(struct xsave_struct *fx, u64 mask) -{ - u32 lmask = mask; - u32 hmask = mask >> 32; - int err = 0; - - WARN_ON(system_state != SYSTEM_BOOTING); - - if (boot_cpu_has(X86_FEATURE_XSAVES)) - asm volatile("1:"XSAVES"\n\t" - "2:\n\t" - xstate_fault - : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask) - : "memory"); - else - asm volatile("1:"XSAVE"\n\t" - "2:\n\t" - xstate_fault - : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask) - : "memory"); - return err; -} - -/* - * This function is called only during boot time when x86 caps are not set - * up and alternative can not be used yet. - */ -static inline int xrstor_state_booting(struct xsave_struct *fx, u64 mask) -{ - u32 lmask = mask; - u32 hmask = mask >> 32; - int err = 0; - - WARN_ON(system_state != SYSTEM_BOOTING); - - if (boot_cpu_has(X86_FEATURE_XSAVES)) - asm volatile("1:"XRSTORS"\n\t" - "2:\n\t" - xstate_fault - : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask) - : "memory"); - else - asm volatile("1:"XRSTOR"\n\t" - "2:\n\t" - xstate_fault - : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask) - : "memory"); - return err; -} - -/* - * Save processor xstate to xsave area. - */ -static inline int xsave_state(struct xsave_struct *fx, u64 mask) -{ - u32 lmask = mask; - u32 hmask = mask >> 32; - int err = 0; - - /* - * If xsaves is enabled, xsaves replaces xsaveopt because - * it supports compact format and supervisor states in addition to - * modified optimization in xsaveopt. - * - * Otherwise, if xsaveopt is enabled, xsaveopt replaces xsave - * because xsaveopt supports modified optimization which is not - * supported by xsave. - * - * If none of xsaves and xsaveopt is enabled, use xsave. - */ - alternative_input_2( - "1:"XSAVE, - XSAVEOPT, - X86_FEATURE_XSAVEOPT, - XSAVES, - X86_FEATURE_XSAVES, - [fx] "D" (fx), "a" (lmask), "d" (hmask) : - "memory"); - asm volatile("2:\n\t" - xstate_fault - : "0" (0) - : "memory"); - - return err; -} - -/* - * Restore processor xstate from xsave area. - */ -static inline int xrstor_state(struct xsave_struct *fx, u64 mask) -{ - int err = 0; - u32 lmask = mask; - u32 hmask = mask >> 32; - - /* - * Use xrstors to restore context if it is enabled. xrstors supports - * compacted format of xsave area which is not supported by xrstor. - */ - alternative_input( - "1: " XRSTOR, - XRSTORS, - X86_FEATURE_XSAVES, - "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask) - : "memory"); - - asm volatile("2:\n" - xstate_fault - : "0" (0) - : "memory"); - - return err; -} - -/* - * Save xstate context for old process during context switch. - */ -static inline void fpu_xsave(struct fpu *fpu) -{ - xsave_state(&fpu->state->xsave, -1); -} - -/* - * Restore xstate context for new process during context switch. - */ -static inline int fpu_xrstor_checking(struct xsave_struct *fx) -{ - return xrstor_state(fx, -1); -} - -/* - * Save xstate to user space xsave area. - * - * We don't use modified optimization because xrstor/xrstors might track - * a different application. - * - * We don't use compacted format xsave area for - * backward compatibility for old applications which don't understand - * compacted format of xsave area. - */ -static inline int xsave_user(struct xsave_struct __user *buf) -{ - int err; - - /* - * Clear the xsave header first, so that reserved fields are - * initialized to zero. - */ - err = __clear_user(&buf->xsave_hdr, sizeof(buf->xsave_hdr)); - if (unlikely(err)) - return -EFAULT; - - __asm__ __volatile__(ASM_STAC "\n" - "1:"XSAVE"\n" - "2: " ASM_CLAC "\n" - xstate_fault - : "D" (buf), "a" (-1), "d" (-1), "0" (0) - : "memory"); - return err; -} - -/* - * Restore xstate from user space xsave area. - */ -static inline int xrestore_user(struct xsave_struct __user *buf, u64 mask) -{ - int err = 0; - struct xsave_struct *xstate = ((__force struct xsave_struct *)buf); - u32 lmask = mask; - u32 hmask = mask >> 32; - - __asm__ __volatile__(ASM_STAC "\n" - "1:"XRSTOR"\n" - "2: " ASM_CLAC "\n" - xstate_fault - : "D" (xstate), "a" (lmask), "d" (hmask), "0" (0) - : "memory"); /* memory required? */ - return err; -} - -void *get_xsave_addr(struct xsave_struct *xsave, int xstate); -void setup_xstate_comp(void); - -#endif diff --git a/arch/x86/include/uapi/asm/sigcontext.h b/arch/x86/include/uapi/asm/sigcontext.h index 16dc4e8a2cd3..0e8a973de9ee 100644 --- a/arch/x86/include/uapi/asm/sigcontext.h +++ b/arch/x86/include/uapi/asm/sigcontext.h @@ -25,7 +25,7 @@ struct _fpx_sw_bytes { __u32 extended_size; /* total size of the layout referred by * fpstate pointer in the sigcontext. */ - __u64 xstate_bv; + __u64 xfeatures; /* feature bit mask (including fp/sse/extended * state) that is present in the memory * layout. @@ -209,8 +209,8 @@ struct sigcontext { #endif /* !__i386__ */ -struct _xsave_hdr { - __u64 xstate_bv; +struct _header { + __u64 xfeatures; __u64 reserved1[2]; __u64 reserved2[5]; }; @@ -228,7 +228,7 @@ struct _ymmh_state { */ struct _xstate { struct _fpstate fpstate; - struct _xsave_hdr xstate_hdr; + struct _header xstate_hdr; struct _ymmh_state ymmh; /* new processor state extensions go here */ }; diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 01663ee5f1b7..0f15af41bd80 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -41,7 +41,7 @@ obj-y += pci-iommu_table.o obj-y += resource.o obj-y += process.o -obj-y += i387.o xsave.o +obj-y += fpu/ obj-y += ptrace.o obj-$(CONFIG_X86_32) += tls.o obj-$(CONFIG_IA32_EMULATION) += tls.o diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index b0932c4341b3..c42827eb86cf 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -21,6 +21,10 @@ #include <asm/io.h> #include <asm/fixmap.h> +int __read_mostly alternatives_patched; + +EXPORT_SYMBOL_GPL(alternatives_patched); + #define MAX_PATCH_LEN (255-1) static int __initdata_or_module debug_alternative; @@ -636,6 +640,7 @@ void __init alternative_instructions(void) apply_paravirt(__parainstructions, __parainstructions_end); restart_nmi(); + alternatives_patched = 1; } /** diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 5caed1dd7ccf..29fa475ec518 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -89,9 +89,7 @@ int amd_cache_northbridges(void) next_northbridge(link, amd_nb_link_ids); } - /* GART present only on Fam15h upto model 0fh */ - if (boot_cpu_data.x86 == 0xf || boot_cpu_data.x86 == 0x10 || - (boot_cpu_data.x86 == 0x15 && boot_cpu_data.x86_model < 0x10)) + if (amd_gart_present()) amd_northbridges.flags |= AMD_NB_GART; /* diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index 76164e173a24..6e85f713641d 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -262,6 +262,9 @@ void __init early_gart_iommu_check(void) u64 aper_base = 0, last_aper_base = 0; int aper_enabled = 0, last_aper_enabled = 0, last_valid = 0; + if (!amd_gart_present()) + return; + if (!early_pci_allowed()) return; @@ -355,6 +358,9 @@ int __init gart_iommu_hole_init(void) int fix, slot, valid_agp = 0; int i, node; + if (!amd_gart_present()) + return -ENODEV; + if (gart_iommu_aperture_disabled || !fix_aperture || !early_pci_allowed()) return -ENODEV; @@ -452,7 +458,7 @@ out: force_iommu || valid_agp || fallback_aper_force) { - pr_info("Your BIOS doesn't leave a aperture memory hole\n"); + pr_info("Your BIOS doesn't leave an aperture memory hole\n"); pr_info("Please enable the IOMMU option in the BIOS setup\n"); pr_info("This costs you %dMB of RAM\n", 32 << fallback_aper_order); diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index eb4f01269b5d..dd3a4baffe50 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -19,6 +19,13 @@ #include "cpu.h" +/* + * nodes_per_socket: Stores the number of nodes per socket. + * Refer to Fam15h Models 00-0fh BKDG - CPUID Fn8000_001E_ECX + * Node Identifiers[10:8] + */ +static u32 nodes_per_socket = 1; + static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p) { u32 gprs[8] = { 0 }; @@ -291,7 +298,7 @@ static int nearby_node(int apicid) #ifdef CONFIG_SMP static void amd_get_topology(struct cpuinfo_x86 *c) { - u32 nodes, cores_per_cu = 1; + u32 cores_per_cu = 1; u8 node_id; int cpu = smp_processor_id(); @@ -300,7 +307,7 @@ static void amd_get_topology(struct cpuinfo_x86 *c) u32 eax, ebx, ecx, edx; cpuid(0x8000001e, &eax, &ebx, &ecx, &edx); - nodes = ((ecx >> 8) & 7) + 1; + nodes_per_socket = ((ecx >> 8) & 7) + 1; node_id = ecx & 7; /* get compute unit information */ @@ -311,18 +318,18 @@ static void amd_get_topology(struct cpuinfo_x86 *c) u64 value; rdmsrl(MSR_FAM10H_NODE_ID, value); - nodes = ((value >> 3) & 7) + 1; + nodes_per_socket = ((value >> 3) & 7) + 1; node_id = value & 7; } else return; /* fixup multi-node processor information */ - if (nodes > 1) { + if (nodes_per_socket > 1) { u32 cores_per_node; u32 cus_per_node; set_cpu_cap(c, X86_FEATURE_AMD_DCM); - cores_per_node = c->x86_max_cores / nodes; + cores_per_node = c->x86_max_cores / nodes_per_socket; cus_per_node = cores_per_node / cores_per_cu; /* store NodeID, use llc_shared_map to store sibling info */ @@ -366,6 +373,12 @@ u16 amd_get_nb_id(int cpu) } EXPORT_SYMBOL_GPL(amd_get_nb_id); +u32 amd_get_nodes_per_socket(void) +{ + return nodes_per_socket; +} +EXPORT_SYMBOL_GPL(amd_get_nodes_per_socket); + static void srat_detect_node(struct cpuinfo_x86 *c) { #ifdef CONFIG_NUMA @@ -520,8 +533,16 @@ static void early_init_amd(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_K6_MTRR); #endif #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_PCI) - /* check CPU config space for extended APIC ID */ - if (cpu_has_apic && c->x86 >= 0xf) { + /* + * ApicID can always be treated as an 8-bit value for AMD APIC versions + * >= 0x10, but even old K8s came out of reset with version 0x10. So, we + * can safely set X86_FEATURE_EXTD_APICID unconditionally for families + * after 16h. + */ + if (cpu_has_apic && c->x86 > 0x16) { + set_cpu_cap(c, X86_FEATURE_EXTD_APICID); + } else if (cpu_has_apic && c->x86 >= 0xf) { + /* check CPU config space for extended APIC ID */ unsigned int val; val = read_pci_config(0, 24, 0, 0x68); if ((val & ((1 << 17) | (1 << 18))) == ((1 << 17) | (1 << 18))) diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 03445346ee0a..bd17db15a2c1 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -12,57 +12,11 @@ #include <asm/bugs.h> #include <asm/processor.h> #include <asm/processor-flags.h> -#include <asm/i387.h> +#include <asm/fpu/internal.h> #include <asm/msr.h> #include <asm/paravirt.h> #include <asm/alternative.h> -static double __initdata x = 4195835.0; -static double __initdata y = 3145727.0; - -/* - * This used to check for exceptions.. - * However, it turns out that to support that, - * the XMM trap handlers basically had to - * be buggy. So let's have a correct XMM trap - * handler, and forget about printing out - * some status at boot. - * - * We should really only care about bugs here - * anyway. Not features. - */ -static void __init check_fpu(void) -{ - s32 fdiv_bug; - - kernel_fpu_begin(); - - /* - * trap_init() enabled FXSR and company _before_ testing for FP - * problems here. - * - * Test for the divl bug: http://en.wikipedia.org/wiki/Fdiv_bug - */ - __asm__("fninit\n\t" - "fldl %1\n\t" - "fdivl %2\n\t" - "fmull %2\n\t" - "fldl %1\n\t" - "fsubp %%st,%%st(1)\n\t" - "fistpl %0\n\t" - "fwait\n\t" - "fninit" - : "=m" (*&fdiv_bug) - : "m" (*&x), "m" (*&y)); - - kernel_fpu_end(); - - if (fdiv_bug) { - set_cpu_bug(&boot_cpu_data, X86_BUG_FDIV); - pr_warn("Hmm, FPU with FDIV bug\n"); - } -} - void __init check_bugs(void) { identify_boot_cpu(); @@ -85,10 +39,5 @@ void __init check_bugs(void) '0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86); alternative_instructions(); - /* - * kernel_fpu_begin/end() in check_fpu() relies on the patched - * alternative instructions. - */ - if (cpu_has_fpu) - check_fpu(); + fpu__init_check_bugs(); } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index cc7f753e571d..9fc5e3d9d9c8 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -5,6 +5,7 @@ #include <linux/module.h> #include <linux/percpu.h> #include <linux/string.h> +#include <linux/ctype.h> #include <linux/delay.h> #include <linux/sched.h> #include <linux/init.h> @@ -31,8 +32,7 @@ #include <asm/setup.h> #include <asm/apic.h> #include <asm/desc.h> -#include <asm/i387.h> -#include <asm/fpu-internal.h> +#include <asm/fpu/internal.h> #include <asm/mtrr.h> #include <linux/numa.h> #include <asm/asm.h> @@ -145,32 +145,21 @@ DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = { } }; EXPORT_PER_CPU_SYMBOL_GPL(gdt_page); -static int __init x86_xsave_setup(char *s) +static int __init x86_mpx_setup(char *s) { + /* require an exact match without trailing characters */ if (strlen(s)) return 0; - setup_clear_cpu_cap(X86_FEATURE_XSAVE); - setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); - setup_clear_cpu_cap(X86_FEATURE_XSAVES); - setup_clear_cpu_cap(X86_FEATURE_AVX); - setup_clear_cpu_cap(X86_FEATURE_AVX2); - return 1; -} -__setup("noxsave", x86_xsave_setup); -static int __init x86_xsaveopt_setup(char *s) -{ - setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); - return 1; -} -__setup("noxsaveopt", x86_xsaveopt_setup); + /* do not emit a message if the feature is not present */ + if (!boot_cpu_has(X86_FEATURE_MPX)) + return 1; -static int __init x86_xsaves_setup(char *s) -{ - setup_clear_cpu_cap(X86_FEATURE_XSAVES); + setup_clear_cpu_cap(X86_FEATURE_MPX); + pr_info("nompx: Intel Memory Protection Extensions (MPX) disabled\n"); return 1; } -__setup("noxsaves", x86_xsaves_setup); +__setup("nompx", x86_mpx_setup); #ifdef CONFIG_X86_32 static int cachesize_override = -1; @@ -183,14 +172,6 @@ static int __init cachesize_setup(char *str) } __setup("cachesize=", cachesize_setup); -static int __init x86_fxsr_setup(char *s) -{ - setup_clear_cpu_cap(X86_FEATURE_FXSR); - setup_clear_cpu_cap(X86_FEATURE_XMM); - return 1; -} -__setup("nofxsr", x86_fxsr_setup); - static int __init x86_sep_setup(char *s) { setup_clear_cpu_cap(X86_FEATURE_SEP); @@ -419,7 +400,7 @@ static const struct cpu_dev *cpu_devs[X86_VENDOR_NUM] = {}; static void get_model_name(struct cpuinfo_x86 *c) { unsigned int *v; - char *p, *q; + char *p, *q, *s; if (c->extended_cpuid_level < 0x80000004) return; @@ -430,19 +411,21 @@ static void get_model_name(struct cpuinfo_x86 *c) cpuid(0x80000004, &v[8], &v[9], &v[10], &v[11]); c->x86_model_id[48] = 0; - /* - * Intel chips right-justify this string for some dumb reason; - * undo that brain damage: - */ - p = q = &c->x86_model_id[0]; + /* Trim whitespace */ + p = q = s = &c->x86_model_id[0]; + while (*p == ' ') p++; - if (p != q) { - while (*p) - *q++ = *p++; - while (q <= &c->x86_model_id[48]) - *q++ = '\0'; /* Zero-pad the rest */ + + while (*p) { + /* Note the last non-whitespace index */ + if (!isspace(*p)) + s = q; + + *q++ = *p++; } + + *(s + 1) = '\0'; } void cpu_detect_cache_sizes(struct cpuinfo_x86 *c) @@ -759,7 +742,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) cpu_detect(c); get_cpu_vendor(c); get_cpu_cap(c); - fpu_detect(c); + fpu__init_system(c); if (this_cpu->c_early_init) this_cpu->c_early_init(c); @@ -1122,7 +1105,7 @@ void print_cpu_info(struct cpuinfo_x86 *c) printk(KERN_CONT "%s ", vendor); if (c->x86_model_id[0]) - printk(KERN_CONT "%s", strim(c->x86_model_id)); + printk(KERN_CONT "%s", c->x86_model_id); else printk(KERN_CONT "%d86", c->x86); @@ -1179,8 +1162,6 @@ DEFINE_PER_CPU(unsigned int, irq_count) __visible = -1; DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT; EXPORT_PER_CPU_SYMBOL(__preempt_count); -DEFINE_PER_CPU(struct task_struct *, fpu_owner_task); - /* * Special IST stacks which the CPU switches to when it calls * an IST-marked descriptor entry. Up to 7 stacks (hardware @@ -1271,7 +1252,6 @@ DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task; EXPORT_PER_CPU_SYMBOL(current_task); DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT; EXPORT_PER_CPU_SYMBOL(__preempt_count); -DEFINE_PER_CPU(struct task_struct *, fpu_owner_task); /* * On x86_32, vm86 modifies tss.sp0, so sp0 isn't a reliable way to find @@ -1435,7 +1415,7 @@ void cpu_init(void) clear_all_debug_regs(); dbg_restore_debug_regs(); - fpu_init(); + fpu__init_cpu(); if (is_uv_system()) uv_cpu_init(); @@ -1491,7 +1471,7 @@ void cpu_init(void) clear_all_debug_regs(); dbg_restore_debug_regs(); - fpu_init(); + fpu__init_cpu(); } #endif diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 5b974c97e31e..df919ff103c3 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -53,9 +53,12 @@ static DEFINE_MUTEX(mce_chrdev_read_mutex); #define rcu_dereference_check_mce(p) \ - rcu_dereference_index_check((p), \ - rcu_read_lock_sched_held() || \ - lockdep_is_held(&mce_chrdev_read_mutex)) +({ \ + rcu_lockdep_assert(rcu_read_lock_sched_held() || \ + lockdep_is_held(&mce_chrdev_read_mutex), \ + "suspicious rcu_dereference_check_mce() usage"); \ + smp_load_acquire(&(p)); \ +}) #define CREATE_TRACE_POINTS #include <trace/events/mce.h> @@ -1913,7 +1916,7 @@ out: static unsigned int mce_chrdev_poll(struct file *file, poll_table *wait) { poll_wait(file, &mce_chrdev_wait, wait); - if (rcu_access_index(mcelog.next)) + if (READ_ONCE(mcelog.next)) return POLLIN | POLLRDNORM; if (!mce_apei_read_done && apei_check_mce()) return POLLIN | POLLRDNORM; @@ -1958,8 +1961,8 @@ void register_mce_write_callback(ssize_t (*fn)(struct file *filp, } EXPORT_SYMBOL_GPL(register_mce_write_callback); -ssize_t mce_chrdev_write(struct file *filp, const char __user *ubuf, - size_t usize, loff_t *off) +static ssize_t mce_chrdev_write(struct file *filp, const char __user *ubuf, + size_t usize, loff_t *off) { if (mce_write) return mce_write(filp, ubuf, usize, off); diff --git a/arch/x86/kernel/cpu/microcode/amd_early.c b/arch/x86/kernel/cpu/microcode/amd_early.c index 737737edbd1e..e8a215a9a345 100644 --- a/arch/x86/kernel/cpu/microcode/amd_early.c +++ b/arch/x86/kernel/cpu/microcode/amd_early.c @@ -228,7 +228,23 @@ static void apply_ucode_in_initrd(void *ucode, size_t size, bool save_patch) } } -void __init load_ucode_amd_bsp(void) +static bool __init load_builtin_amd_microcode(struct cpio_data *cp, + unsigned int family) +{ +#ifdef CONFIG_X86_64 + char fw_name[36] = "amd-ucode/microcode_amd.bin"; + + if (family >= 0x15) + snprintf(fw_name, sizeof(fw_name), + "amd-ucode/microcode_amd_fam%.2xh.bin", family); + + return get_builtin_firmware(cp, fw_name); +#else + return false; +#endif +} + +void __init load_ucode_amd_bsp(unsigned int family) { struct cpio_data cp; void **data; @@ -243,8 +259,10 @@ void __init load_ucode_amd_bsp(void) #endif cp = find_ucode_in_initrd(); - if (!cp.data) - return; + if (!cp.data) { + if (!load_builtin_amd_microcode(&cp, family)) + return; + } *data = cp.data; *size = cp.size; diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 36a83617eb21..6236a54a63f4 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -1,74 +1,16 @@ /* - * Intel CPU Microcode Update Driver for Linux + * CPU Microcode Update Driver for Linux * - * Copyright (C) 2000-2006 Tigran Aivazian <tigran@aivazian.fsnet.co.uk> - * 2006 Shaohua Li <shaohua.li@intel.com> + * Copyright (C) 2000-2006 Tigran Aivazian <tigran@aivazian.fsnet.co.uk> + * 2006 Shaohua Li <shaohua.li@intel.com> + * 2013-2015 Borislav Petkov <bp@alien8.de> * - * This driver allows to upgrade microcode on Intel processors - * belonging to IA-32 family - PentiumPro, Pentium II, - * Pentium III, Xeon, Pentium 4, etc. + * This driver allows to upgrade microcode on x86 processors. * - * Reference: Section 8.11 of Volume 3a, IA-32 Intel? Architecture - * Software Developer's Manual - * Order Number 253668 or free download from: - * - * http://developer.intel.com/Assets/PDF/manual/253668.pdf - * - * For more information, go to http://www.urbanmyth.org/microcode - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * - * 1.0 16 Feb 2000, Tigran Aivazian <tigran@sco.com> - * Initial release. - * 1.01 18 Feb 2000, Tigran Aivazian <tigran@sco.com> - * Added read() support + cleanups. - * 1.02 21 Feb 2000, Tigran Aivazian <tigran@sco.com> - * Added 'device trimming' support. open(O_WRONLY) zeroes - * and frees the saved copy of applied microcode. - * 1.03 29 Feb 2000, Tigran Aivazian <tigran@sco.com> - * Made to use devfs (/dev/cpu/microcode) + cleanups. - * 1.04 06 Jun 2000, Simon Trimmer <simon@veritas.com> - * Added misc device support (now uses both devfs and misc). - * Added MICROCODE_IOCFREE ioctl to clear memory. - * 1.05 09 Jun 2000, Simon Trimmer <simon@veritas.com> - * Messages for error cases (non Intel & no suitable microcode). - * 1.06 03 Aug 2000, Tigran Aivazian <tigran@veritas.com> - * Removed ->release(). Removed exclusive open and status bitmap. - * Added microcode_rwsem to serialize read()/write()/ioctl(). - * Removed global kernel lock usage. - * 1.07 07 Sep 2000, Tigran Aivazian <tigran@veritas.com> - * Write 0 to 0x8B msr and then cpuid before reading revision, - * so that it works even if there were no update done by the - * BIOS. Otherwise, reading from 0x8B gives junk (which happened - * to be 0 on my machine which is why it worked even when I - * disabled update by the BIOS) - * Thanks to Eric W. Biederman <ebiederman@lnxi.com> for the fix. - * 1.08 11 Dec 2000, Richard Schaal <richard.schaal@intel.com> and - * Tigran Aivazian <tigran@veritas.com> - * Intel Pentium 4 processor support and bugfixes. - * 1.09 30 Oct 2001, Tigran Aivazian <tigran@veritas.com> - * Bugfix for HT (Hyper-Threading) enabled processors - * whereby processor resources are shared by all logical processors - * in a single CPU package. - * 1.10 28 Feb 2002 Asit K Mallick <asit.k.mallick@intel.com> and - * Tigran Aivazian <tigran@veritas.com>, - * Serialize updates as required on HT processors due to - * speculative nature of implementation. - * 1.11 22 Mar 2002 Tigran Aivazian <tigran@veritas.com> - * Fix the panic when writing zero-length microcode chunk. - * 1.12 29 Sep 2003 Nitin Kamble <nitin.a.kamble@intel.com>, - * Jun Nakajima <jun.nakajima@intel.com> - * Support for the microcode updates in the new format. - * 1.13 10 Oct 2003 Tigran Aivazian <tigran@veritas.com> - * Removed ->read() method and obsoleted MICROCODE_IOCFREE ioctl - * because we no longer hold a copy of applied microcode - * in kernel memory. - * 1.14 25 Jun 2004 Tigran Aivazian <tigran@veritas.com> - * Fix sigmatch() macro to handle old CPUs with pf == 0. - * Thanks to Stuart Swales for pointing out this bug. + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt diff --git a/arch/x86/kernel/cpu/microcode/core_early.c b/arch/x86/kernel/cpu/microcode/core_early.c index a413a69cbd74..8ebc421d6299 100644 --- a/arch/x86/kernel/cpu/microcode/core_early.c +++ b/arch/x86/kernel/cpu/microcode/core_early.c @@ -3,6 +3,7 @@ * * Copyright (C) 2012 Fenghua Yu <fenghua.yu@intel.com> * H Peter Anvin" <hpa@zytor.com> + * (C) 2015 Borislav Petkov <bp@alien8.de> * * This driver allows to early upgrade microcode on Intel processors * belonging to IA-32 family - PentiumPro, Pentium II, @@ -17,6 +18,7 @@ * 2 of the License, or (at your option) any later version. */ #include <linux/module.h> +#include <linux/firmware.h> #include <asm/microcode.h> #include <asm/microcode_intel.h> #include <asm/microcode_amd.h> @@ -43,9 +45,29 @@ static bool __init check_loader_disabled_bsp(void) return *res; } +extern struct builtin_fw __start_builtin_fw[]; +extern struct builtin_fw __end_builtin_fw[]; + +bool get_builtin_firmware(struct cpio_data *cd, const char *name) +{ +#ifdef CONFIG_FW_LOADER + struct builtin_fw *b_fw; + + for (b_fw = __start_builtin_fw; b_fw != __end_builtin_fw; b_fw++) { + if (!strcmp(name, b_fw->name)) { + cd->size = b_fw->size; + cd->data = b_fw->data; + return true; + } + } +#endif + return false; +} + void __init load_ucode_bsp(void) { - int vendor, family; + int vendor; + unsigned int family; if (check_loader_disabled_bsp()) return; @@ -63,7 +85,7 @@ void __init load_ucode_bsp(void) break; case X86_VENDOR_AMD: if (family >= 0x10) - load_ucode_amd_bsp(); + load_ucode_amd_bsp(family); break; default: break; diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index a41beadb3db9..969dc17eb1b4 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -1,74 +1,13 @@ /* - * Intel CPU Microcode Update Driver for Linux + * Intel CPU Microcode Update Driver for Linux * - * Copyright (C) 2000-2006 Tigran Aivazian <tigran@aivazian.fsnet.co.uk> - * 2006 Shaohua Li <shaohua.li@intel.com> + * Copyright (C) 2000-2006 Tigran Aivazian <tigran@aivazian.fsnet.co.uk> + * 2006 Shaohua Li <shaohua.li@intel.com> * - * This driver allows to upgrade microcode on Intel processors - * belonging to IA-32 family - PentiumPro, Pentium II, - * Pentium III, Xeon, Pentium 4, etc. - * - * Reference: Section 8.11 of Volume 3a, IA-32 Intel? Architecture - * Software Developer's Manual - * Order Number 253668 or free download from: - * - * http://developer.intel.com/Assets/PDF/manual/253668.pdf - * - * For more information, go to http://www.urbanmyth.org/microcode - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * - * 1.0 16 Feb 2000, Tigran Aivazian <tigran@sco.com> - * Initial release. - * 1.01 18 Feb 2000, Tigran Aivazian <tigran@sco.com> - * Added read() support + cleanups. - * 1.02 21 Feb 2000, Tigran Aivazian <tigran@sco.com> - * Added 'device trimming' support. open(O_WRONLY) zeroes - * and frees the saved copy of applied microcode. - * 1.03 29 Feb 2000, Tigran Aivazian <tigran@sco.com> - * Made to use devfs (/dev/cpu/microcode) + cleanups. - * 1.04 06 Jun 2000, Simon Trimmer <simon@veritas.com> - * Added misc device support (now uses both devfs and misc). - * Added MICROCODE_IOCFREE ioctl to clear memory. - * 1.05 09 Jun 2000, Simon Trimmer <simon@veritas.com> - * Messages for error cases (non Intel & no suitable microcode). - * 1.06 03 Aug 2000, Tigran Aivazian <tigran@veritas.com> - * Removed ->release(). Removed exclusive open and status bitmap. - * Added microcode_rwsem to serialize read()/write()/ioctl(). - * Removed global kernel lock usage. - * 1.07 07 Sep 2000, Tigran Aivazian <tigran@veritas.com> - * Write 0 to 0x8B msr and then cpuid before reading revision, - * so that it works even if there were no update done by the - * BIOS. Otherwise, reading from 0x8B gives junk (which happened - * to be 0 on my machine which is why it worked even when I - * disabled update by the BIOS) - * Thanks to Eric W. Biederman <ebiederman@lnxi.com> for the fix. - * 1.08 11 Dec 2000, Richard Schaal <richard.schaal@intel.com> and - * Tigran Aivazian <tigran@veritas.com> - * Intel Pentium 4 processor support and bugfixes. - * 1.09 30 Oct 2001, Tigran Aivazian <tigran@veritas.com> - * Bugfix for HT (Hyper-Threading) enabled processors - * whereby processor resources are shared by all logical processors - * in a single CPU package. - * 1.10 28 Feb 2002 Asit K Mallick <asit.k.mallick@intel.com> and - * Tigran Aivazian <tigran@veritas.com>, - * Serialize updates as required on HT processors due to - * speculative nature of implementation. - * 1.11 22 Mar 2002 Tigran Aivazian <tigran@veritas.com> - * Fix the panic when writing zero-length microcode chunk. - * 1.12 29 Sep 2003 Nitin Kamble <nitin.a.kamble@intel.com>, - * Jun Nakajima <jun.nakajima@intel.com> - * Support for the microcode updates in the new format. - * 1.13 10 Oct 2003 Tigran Aivazian <tigran@veritas.com> - * Removed ->read() method and obsoleted MICROCODE_IOCFREE ioctl - * because we no longer hold a copy of applied microcode - * in kernel memory. - * 1.14 25 Jun 2004 Tigran Aivazian <tigran@veritas.com> - * Fix sigmatch() macro to handle old CPUs with pf == 0. - * Thanks to Stuart Swales for pointing out this bug. + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -124,7 +63,7 @@ static int get_matching_mc(struct microcode_intel *mc_intel, int cpu) cpf = cpu_sig.pf; crev = cpu_sig.rev; - return get_matching_microcode(csig, cpf, crev, mc_intel); + return has_newer_microcode(mc_intel, csig, cpf, crev); } static int apply_microcode_intel(int cpu) @@ -226,7 +165,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size, csig = uci->cpu_sig.sig; cpf = uci->cpu_sig.pf; - if (get_matching_microcode(csig, cpf, new_rev, mc)) { + if (has_newer_microcode(mc, csig, cpf, new_rev)) { vfree(new_mc); new_rev = mc_header.rev; new_mc = mc; diff --git a/arch/x86/kernel/cpu/microcode/intel_early.c b/arch/x86/kernel/cpu/microcode/intel_early.c index 2f49ab4ac0ae..8187b7247d1c 100644 --- a/arch/x86/kernel/cpu/microcode/intel_early.c +++ b/arch/x86/kernel/cpu/microcode/intel_early.c @@ -59,10 +59,10 @@ load_microcode_early(struct microcode_intel **saved, ucode_ptr = saved[i]; mc_hdr = (struct microcode_header_intel *)ucode_ptr; - ret = get_matching_microcode(uci->cpu_sig.sig, - uci->cpu_sig.pf, - new_rev, - ucode_ptr); + ret = has_newer_microcode(ucode_ptr, + uci->cpu_sig.sig, + uci->cpu_sig.pf, + new_rev); if (!ret) continue; @@ -246,7 +246,7 @@ static unsigned int _save_mc(struct microcode_intel **mc_saved, u8 *ucode_ptr, unsigned int num_saved) { struct microcode_header_intel *mc_hdr, *mc_saved_hdr; - unsigned int sig, pf, new_rev; + unsigned int sig, pf; int found = 0, i; mc_hdr = (struct microcode_header_intel *)ucode_ptr; @@ -255,14 +255,13 @@ static unsigned int _save_mc(struct microcode_intel **mc_saved, mc_saved_hdr = (struct microcode_header_intel *)mc_saved[i]; sig = mc_saved_hdr->sig; pf = mc_saved_hdr->pf; - new_rev = mc_hdr->rev; - if (!get_matching_sig(sig, pf, new_rev, ucode_ptr)) + if (!find_matching_signature(ucode_ptr, sig, pf)) continue; found = 1; - if (!revision_is_newer(mc_hdr, new_rev)) + if (mc_hdr->rev <= mc_saved_hdr->rev) continue; /* @@ -522,6 +521,27 @@ out: EXPORT_SYMBOL_GPL(save_mc_for_early); #endif +static bool __init load_builtin_intel_microcode(struct cpio_data *cp) +{ +#ifdef CONFIG_X86_64 + unsigned int eax = 0x00000001, ebx, ecx = 0, edx; + unsigned int family, model, stepping; + char name[30]; + + native_cpuid(&eax, &ebx, &ecx, &edx); + + family = __x86_family(eax); + model = x86_model(eax); + stepping = eax & 0xf; + + sprintf(name, "intel-ucode/%02x-%02x-%02x", family, model, stepping); + + return get_builtin_firmware(cp, name); +#else + return false; +#endif +} + static __initdata char ucode_name[] = "kernel/x86/microcode/GenuineIntel.bin"; static __init enum ucode_state scan_microcode(struct mc_saved_data *mc_saved_data, unsigned long *initrd, @@ -540,8 +560,10 @@ scan_microcode(struct mc_saved_data *mc_saved_data, unsigned long *initrd, cd.size = 0; cd = find_cpio_data(p, (void *)start, size, &offset); - if (!cd.data) - return UCODE_ERROR; + if (!cd.data) { + if (!load_builtin_intel_microcode(&cd)) + return UCODE_ERROR; + } return get_matching_model_microcode(0, start, cd.data, cd.size, mc_saved_data, initrd, uci); diff --git a/arch/x86/kernel/cpu/microcode/intel_lib.c b/arch/x86/kernel/cpu/microcode/intel_lib.c index cd47a510a3f1..1883d252ff7d 100644 --- a/arch/x86/kernel/cpu/microcode/intel_lib.c +++ b/arch/x86/kernel/cpu/microcode/intel_lib.c @@ -31,11 +31,18 @@ #include <asm/processor.h> #include <asm/msr.h> -static inline int -update_match_cpu(unsigned int csig, unsigned int cpf, - unsigned int sig, unsigned int pf) +static inline bool cpu_signatures_match(unsigned int s1, unsigned int p1, + unsigned int s2, unsigned int p2) { - return (!sigmatch(sig, csig, pf, cpf)) ? 0 : 1; + if (s1 != s2) + return false; + + /* Processor flags are either both 0 ... */ + if (!p1 && !p2) + return true; + + /* ... or they intersect. */ + return p1 & p2; } int microcode_sanity_check(void *mc, int print_err) @@ -124,27 +131,25 @@ EXPORT_SYMBOL_GPL(microcode_sanity_check); /* * Returns 1 if update has been found, 0 otherwise. */ -int get_matching_sig(unsigned int csig, int cpf, int rev, void *mc) +int find_matching_signature(void *mc, unsigned int csig, int cpf) { - struct microcode_header_intel *mc_header = mc; - struct extended_sigtable *ext_header; - unsigned long total_size = get_totalsize(mc_header); - int ext_sigcount, i; + struct microcode_header_intel *mc_hdr = mc; + struct extended_sigtable *ext_hdr; struct extended_signature *ext_sig; + int i; - if (update_match_cpu(csig, cpf, mc_header->sig, mc_header->pf)) + if (cpu_signatures_match(csig, cpf, mc_hdr->sig, mc_hdr->pf)) return 1; /* Look for ext. headers: */ - if (total_size <= get_datasize(mc_header) + MC_HEADER_SIZE) + if (get_totalsize(mc_hdr) <= get_datasize(mc_hdr) + MC_HEADER_SIZE) return 0; - ext_header = mc + get_datasize(mc_header) + MC_HEADER_SIZE; - ext_sigcount = ext_header->count; - ext_sig = (void *)ext_header + EXT_HEADER_SIZE; + ext_hdr = mc + get_datasize(mc_hdr) + MC_HEADER_SIZE; + ext_sig = (void *)ext_hdr + EXT_HEADER_SIZE; - for (i = 0; i < ext_sigcount; i++) { - if (update_match_cpu(csig, cpf, ext_sig->sig, ext_sig->pf)) + for (i = 0; i < ext_hdr->count; i++) { + if (cpu_signatures_match(csig, cpf, ext_sig->sig, ext_sig->pf)) return 1; ext_sig++; } @@ -154,13 +159,13 @@ int get_matching_sig(unsigned int csig, int cpf, int rev, void *mc) /* * Returns 1 if update has been found, 0 otherwise. */ -int get_matching_microcode(unsigned int csig, int cpf, int rev, void *mc) +int has_newer_microcode(void *mc, unsigned int csig, int cpf, int new_rev) { struct microcode_header_intel *mc_hdr = mc; - if (!revision_is_newer(mc_hdr, rev)) + if (mc_hdr->rev <= new_rev) return 0; - return get_matching_sig(csig, cpf, rev, mc); + return find_matching_signature(mc, csig, cpf); } -EXPORT_SYMBOL_GPL(get_matching_microcode); +EXPORT_SYMBOL_GPL(has_newer_microcode); diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 87848ebe2bb7..5801a14f7524 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -135,6 +135,7 @@ static int x86_pmu_extra_regs(u64 config, struct perf_event *event) } static atomic_t active_events; +static atomic_t pmc_refcount; static DEFINE_MUTEX(pmc_reserve_mutex); #ifdef CONFIG_X86_LOCAL_APIC @@ -190,6 +191,7 @@ static bool check_hw_exists(void) u64 val, val_fail, val_new= ~0; int i, reg, reg_fail, ret = 0; int bios_fail = 0; + int reg_safe = -1; /* * Check to see if the BIOS enabled any of the counters, if so @@ -204,6 +206,8 @@ static bool check_hw_exists(void) bios_fail = 1; val_fail = val; reg_fail = reg; + } else { + reg_safe = i; } } @@ -222,11 +226,22 @@ static bool check_hw_exists(void) } /* + * If all the counters are enabled, the below test will always + * fail. The tools will also become useless in this scenario. + * Just fail and disable the hardware counters. + */ + + if (reg_safe == -1) { + reg = reg_safe; + goto msr_fail; + } + + /* * Read the current value, change it and read it back to see if it * matches, this is needed to detect certain hardware emulators * (qemu/kvm) that don't trap on the MSR access and always return 0s. */ - reg = x86_pmu_event_addr(0); + reg = x86_pmu_event_addr(reg_safe); if (rdmsrl_safe(reg, &val)) goto msr_fail; val ^= 0xffffUL; @@ -256,11 +271,8 @@ msr_fail: static void hw_perf_event_destroy(struct perf_event *event) { - if (atomic_dec_and_mutex_lock(&active_events, &pmc_reserve_mutex)) { - release_pmc_hardware(); - release_ds_buffers(); - mutex_unlock(&pmc_reserve_mutex); - } + x86_release_hardware(); + atomic_dec(&active_events); } void hw_perf_lbr_event_destroy(struct perf_event *event) @@ -310,6 +322,35 @@ set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event *event) return x86_pmu_extra_regs(val, event); } +int x86_reserve_hardware(void) +{ + int err = 0; + + if (!atomic_inc_not_zero(&pmc_refcount)) { + mutex_lock(&pmc_reserve_mutex); + if (atomic_read(&pmc_refcount) == 0) { + if (!reserve_pmc_hardware()) + err = -EBUSY; + else + reserve_ds_buffers(); + } + if (!err) + atomic_inc(&pmc_refcount); + mutex_unlock(&pmc_reserve_mutex); + } + + return err; +} + +void x86_release_hardware(void) +{ + if (atomic_dec_and_mutex_lock(&pmc_refcount, &pmc_reserve_mutex)) { + release_pmc_hardware(); + release_ds_buffers(); + mutex_unlock(&pmc_reserve_mutex); + } +} + /* * Check if we can create event of a certain type (that no conflicting events * are present). @@ -322,21 +363,34 @@ int x86_add_exclusive(unsigned int what) return 0; mutex_lock(&pmc_reserve_mutex); - for (i = 0; i < ARRAY_SIZE(x86_pmu.lbr_exclusive); i++) + for (i = 0; i < ARRAY_SIZE(x86_pmu.lbr_exclusive); i++) { if (i != what && atomic_read(&x86_pmu.lbr_exclusive[i])) goto out; + } atomic_inc(&x86_pmu.lbr_exclusive[what]); ret = 0; out: mutex_unlock(&pmc_reserve_mutex); + + /* + * Assuming that all exclusive events will share the PMI handler + * (which checks active_events for whether there is work to do), + * we can bump active_events counter right here, except for + * x86_lbr_exclusive_lbr events that go through x86_pmu_event_init() + * path, which already bumps active_events for them. + */ + if (!ret && what != x86_lbr_exclusive_lbr) + atomic_inc(&active_events); + return ret; } void x86_del_exclusive(unsigned int what) { atomic_dec(&x86_pmu.lbr_exclusive[what]); + atomic_dec(&active_events); } int x86_setup_perfctr(struct perf_event *event) @@ -513,22 +567,11 @@ static int __x86_pmu_event_init(struct perf_event *event) if (!x86_pmu_initialized()) return -ENODEV; - err = 0; - if (!atomic_inc_not_zero(&active_events)) { - mutex_lock(&pmc_reserve_mutex); - if (atomic_read(&active_events) == 0) { - if (!reserve_pmc_hardware()) - err = -EBUSY; - else - reserve_ds_buffers(); - } - if (!err) - atomic_inc(&active_events); - mutex_unlock(&pmc_reserve_mutex); - } + err = x86_reserve_hardware(); if (err) return err; + atomic_inc(&active_events); event->destroy = hw_perf_event_destroy; event->hw.idx = -1; @@ -611,6 +654,7 @@ struct sched_state { int event; /* event index */ int counter; /* counter index */ int unassigned; /* number of events to be assigned left */ + int nr_gp; /* number of GP counters used */ unsigned long used[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; }; @@ -620,27 +664,29 @@ struct sched_state { struct perf_sched { int max_weight; int max_events; - struct perf_event **events; - struct sched_state state; + int max_gp; int saved_states; + struct event_constraint **constraints; + struct sched_state state; struct sched_state saved[SCHED_STATES_MAX]; }; /* * Initialize interator that runs through all events and counters. */ -static void perf_sched_init(struct perf_sched *sched, struct perf_event **events, - int num, int wmin, int wmax) +static void perf_sched_init(struct perf_sched *sched, struct event_constraint **constraints, + int num, int wmin, int wmax, int gpmax) { int idx; memset(sched, 0, sizeof(*sched)); sched->max_events = num; sched->max_weight = wmax; - sched->events = events; + sched->max_gp = gpmax; + sched->constraints = constraints; for (idx = 0; idx < num; idx++) { - if (events[idx]->hw.constraint->weight == wmin) + if (constraints[idx]->weight == wmin) break; } @@ -687,7 +733,7 @@ static bool __perf_sched_find_counter(struct perf_sched *sched) if (sched->state.event >= sched->max_events) return false; - c = sched->events[sched->state.event]->hw.constraint; + c = sched->constraints[sched->state.event]; /* Prefer fixed purpose counters */ if (c->idxmsk64 & (~0ULL << INTEL_PMC_IDX_FIXED)) { idx = INTEL_PMC_IDX_FIXED; @@ -696,11 +742,16 @@ static bool __perf_sched_find_counter(struct perf_sched *sched) goto done; } } + /* Grab the first unused counter starting with idx */ idx = sched->state.counter; for_each_set_bit_from(idx, c->idxmsk, INTEL_PMC_IDX_FIXED) { - if (!__test_and_set_bit(idx, sched->state.used)) + if (!__test_and_set_bit(idx, sched->state.used)) { + if (sched->state.nr_gp++ >= sched->max_gp) + return false; + goto done; + } } return false; @@ -745,7 +796,7 @@ static bool perf_sched_next_event(struct perf_sched *sched) if (sched->state.weight > sched->max_weight) return false; } - c = sched->events[sched->state.event]->hw.constraint; + c = sched->constraints[sched->state.event]; } while (c->weight != sched->state.weight); sched->state.counter = 0; /* start with first counter */ @@ -756,12 +807,12 @@ static bool perf_sched_next_event(struct perf_sched *sched) /* * Assign a counter for each event. */ -int perf_assign_events(struct perf_event **events, int n, - int wmin, int wmax, int *assign) +int perf_assign_events(struct event_constraint **constraints, int n, + int wmin, int wmax, int gpmax, int *assign) { struct perf_sched sched; - perf_sched_init(&sched, events, n, wmin, wmax); + perf_sched_init(&sched, constraints, n, wmin, wmax, gpmax); do { if (!perf_sched_find_counter(&sched)) @@ -788,9 +839,9 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) x86_pmu.start_scheduling(cpuc); for (i = 0, wmin = X86_PMC_IDX_MAX, wmax = 0; i < n; i++) { - hwc = &cpuc->event_list[i]->hw; + cpuc->event_constraint[i] = NULL; c = x86_pmu.get_event_constraints(cpuc, i, cpuc->event_list[i]); - hwc->constraint = c; + cpuc->event_constraint[i] = c; wmin = min(wmin, c->weight); wmax = max(wmax, c->weight); @@ -801,7 +852,7 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) */ for (i = 0; i < n; i++) { hwc = &cpuc->event_list[i]->hw; - c = hwc->constraint; + c = cpuc->event_constraint[i]; /* never assigned */ if (hwc->idx == -1) @@ -821,9 +872,26 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) } /* slow path */ - if (i != n) - unsched = perf_assign_events(cpuc->event_list, n, wmin, - wmax, assign); + if (i != n) { + int gpmax = x86_pmu.num_counters; + + /* + * Do not allow scheduling of more than half the available + * generic counters. + * + * This helps avoid counter starvation of sibling thread by + * ensuring at most half the counters cannot be in exclusive + * mode. There is no designated counters for the limits. Any + * N/2 counters can be used. This helps with events with + * specific counter constraints. + */ + if (is_ht_workaround_enabled() && !cpuc->is_fake && + READ_ONCE(cpuc->excl_cntrs->exclusive_present)) + gpmax /= 2; + + unsched = perf_assign_events(cpuc->event_constraint, n, wmin, + wmax, gpmax, assign); + } /* * In case of success (unsched = 0), mark events as committed, @@ -840,12 +908,9 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) e = cpuc->event_list[i]; e->hw.flags |= PERF_X86_EVENT_COMMITTED; if (x86_pmu.commit_scheduling) - x86_pmu.commit_scheduling(cpuc, e, assign[i]); + x86_pmu.commit_scheduling(cpuc, i, assign[i]); } - } - - if (!assign || unsched) { - + } else { for (i = 0; i < n; i++) { e = cpuc->event_list[i]; /* @@ -1058,13 +1123,16 @@ int x86_perf_event_set_period(struct perf_event *event) per_cpu(pmc_prev_left[idx], smp_processor_id()) = left; - /* - * The hw event starts counting from this event offset, - * mark it to be able to extra future deltas: - */ - local64_set(&hwc->prev_count, (u64)-left); + if (!(hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) || + local64_read(&hwc->prev_count) != (u64)-left) { + /* + * The hw event starts counting from this event offset, + * mark it to be able to extra future deltas: + */ + local64_set(&hwc->prev_count, (u64)-left); - wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask); + wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask); + } /* * Due to erratum on certan cpu we need @@ -1292,8 +1360,10 @@ static void x86_pmu_del(struct perf_event *event, int flags) x86_pmu.put_event_constraints(cpuc, event); /* Delete the array entry. */ - while (++i < cpuc->n_events) + while (++i < cpuc->n_events) { cpuc->event_list[i-1] = cpuc->event_list[i]; + cpuc->event_constraint[i-1] = cpuc->event_constraint[i]; + } --cpuc->n_events; perf_event_update_userpage(event); @@ -1374,6 +1444,10 @@ perf_event_nmi_handler(unsigned int cmd, struct pt_regs *regs) u64 finish_clock; int ret; + /* + * All PMUs/events that share this PMI handler should make sure to + * increment active_events for their events. + */ if (!atomic_read(&active_events)) return NMI_DONE; diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index 6ac5cb7a9e14..3e7fd27dfe20 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -74,6 +74,9 @@ struct event_constraint { #define PERF_X86_EVENT_EXCL 0x0040 /* HT exclusivity on counter */ #define PERF_X86_EVENT_DYNAMIC 0x0080 /* dynamic alloc'd constraint */ #define PERF_X86_EVENT_RDPMC_ALLOWED 0x0100 /* grant rdpmc permission */ +#define PERF_X86_EVENT_EXCL_ACCT 0x0200 /* accounted EXCL event */ +#define PERF_X86_EVENT_AUTO_RELOAD 0x0400 /* use PEBS auto-reload */ +#define PERF_X86_EVENT_FREERUNNING 0x0800 /* use freerunning PEBS */ struct amd_nb { @@ -87,6 +90,18 @@ struct amd_nb { #define MAX_PEBS_EVENTS 8 /* + * Flags PEBS can handle without an PMI. + * + * TID can only be handled by flushing at context switch. + * + */ +#define PEBS_FREERUNNING_FLAGS \ + (PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_ADDR | \ + PERF_SAMPLE_ID | PERF_SAMPLE_CPU | PERF_SAMPLE_STREAM_ID | \ + PERF_SAMPLE_DATA_SRC | PERF_SAMPLE_IDENTIFIER | \ + PERF_SAMPLE_TRANSACTION) + +/* * A debug store configuration. * * We only support architectures that use 64bit fields. @@ -132,10 +147,7 @@ enum intel_excl_state_type { }; struct intel_excl_states { - enum intel_excl_state_type init_state[X86_PMC_IDX_MAX]; enum intel_excl_state_type state[X86_PMC_IDX_MAX]; - int num_alloc_cntrs;/* #counters allocated */ - int max_alloc_cntrs;/* max #counters allowed */ bool sched_started; /* true if scheduling has started */ }; @@ -144,6 +156,11 @@ struct intel_excl_cntrs { struct intel_excl_states states[2]; + union { + u16 has_exclusive[2]; + u32 exclusive_present; + }; + int refcnt; /* per-core: #HT threads */ unsigned core_id; /* per-core: core id */ }; @@ -172,7 +189,11 @@ struct cpu_hw_events { added in the current transaction */ int assign[X86_PMC_IDX_MAX]; /* event to counter assignment */ u64 tags[X86_PMC_IDX_MAX]; + struct perf_event *event_list[X86_PMC_IDX_MAX]; /* in enabled order */ + struct event_constraint *event_constraint[X86_PMC_IDX_MAX]; + + int n_excl; /* the number of exclusive events */ unsigned int group_flag; int is_fake; @@ -519,12 +540,10 @@ struct x86_pmu { void (*put_event_constraints)(struct cpu_hw_events *cpuc, struct perf_event *event); - void (*commit_scheduling)(struct cpu_hw_events *cpuc, - struct perf_event *event, - int cntr); - void (*start_scheduling)(struct cpu_hw_events *cpuc); + void (*commit_scheduling)(struct cpu_hw_events *cpuc, int idx, int cntr); + void (*stop_scheduling)(struct cpu_hw_events *cpuc); struct event_constraint *event_constraints; @@ -697,6 +716,10 @@ int x86_add_exclusive(unsigned int what); void x86_del_exclusive(unsigned int what); +int x86_reserve_hardware(void); + +void x86_release_hardware(void); + void hw_perf_lbr_event_destroy(struct perf_event *event); int x86_setup_perfctr(struct perf_event *event); @@ -717,8 +740,8 @@ static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc, void x86_pmu_enable_all(int added); -int perf_assign_events(struct perf_event **events, int n, - int wmin, int wmax, int *assign); +int perf_assign_events(struct event_constraint **constraints, int n, + int wmin, int wmax, int gpmax, int *assign); int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign); void x86_pmu_stop(struct perf_event *event, int flags); @@ -860,6 +883,8 @@ void intel_pmu_pebs_enable_all(void); void intel_pmu_pebs_disable_all(void); +void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in); + void intel_ds_init(void); void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in); @@ -929,4 +954,8 @@ static inline struct intel_shared_regs *allocate_shared_regs(int cpu) return NULL; } +static inline int is_ht_workaround_enabled(void) +{ + return 0; +} #endif /* CONFIG_CPU_SUP_INTEL */ diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 3998131d1a68..b9826a981fb2 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -1903,9 +1903,8 @@ static void intel_start_scheduling(struct cpu_hw_events *cpuc) { struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs; - struct intel_excl_states *xl, *xlo; + struct intel_excl_states *xl; int tid = cpuc->excl_thread_id; - int o_tid = 1 - tid; /* sibling thread */ /* * nothing needed if in group validation mode @@ -1916,35 +1915,52 @@ intel_start_scheduling(struct cpu_hw_events *cpuc) /* * no exclusion needed */ - if (!excl_cntrs) + if (WARN_ON_ONCE(!excl_cntrs)) return; - xlo = &excl_cntrs->states[o_tid]; xl = &excl_cntrs->states[tid]; xl->sched_started = true; - xl->num_alloc_cntrs = 0; /* * lock shared state until we are done scheduling * in stop_event_scheduling() * makes scheduling appear as a transaction */ - WARN_ON_ONCE(!irqs_disabled()); raw_spin_lock(&excl_cntrs->lock); +} - /* - * save initial state of sibling thread - */ - memcpy(xlo->init_state, xlo->state, sizeof(xlo->init_state)); +static void intel_commit_scheduling(struct cpu_hw_events *cpuc, int idx, int cntr) +{ + struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs; + struct event_constraint *c = cpuc->event_constraint[idx]; + struct intel_excl_states *xl; + int tid = cpuc->excl_thread_id; + + if (cpuc->is_fake || !is_ht_workaround_enabled()) + return; + + if (WARN_ON_ONCE(!excl_cntrs)) + return; + + if (!(c->flags & PERF_X86_EVENT_DYNAMIC)) + return; + + xl = &excl_cntrs->states[tid]; + + lockdep_assert_held(&excl_cntrs->lock); + + if (c->flags & PERF_X86_EVENT_EXCL) + xl->state[cntr] = INTEL_EXCL_EXCLUSIVE; + else + xl->state[cntr] = INTEL_EXCL_SHARED; } static void intel_stop_scheduling(struct cpu_hw_events *cpuc) { struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs; - struct intel_excl_states *xl, *xlo; + struct intel_excl_states *xl; int tid = cpuc->excl_thread_id; - int o_tid = 1 - tid; /* sibling thread */ /* * nothing needed if in group validation mode @@ -1954,17 +1970,11 @@ intel_stop_scheduling(struct cpu_hw_events *cpuc) /* * no exclusion needed */ - if (!excl_cntrs) + if (WARN_ON_ONCE(!excl_cntrs)) return; - xlo = &excl_cntrs->states[o_tid]; xl = &excl_cntrs->states[tid]; - /* - * make new sibling thread state visible - */ - memcpy(xlo->state, xlo->init_state, sizeof(xlo->state)); - xl->sched_started = false; /* * release shared state lock (acquired in intel_start_scheduling()) @@ -1976,12 +1986,10 @@ static struct event_constraint * intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event, int idx, struct event_constraint *c) { - struct event_constraint *cx; struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs; - struct intel_excl_states *xl, *xlo; - int is_excl, i; + struct intel_excl_states *xlo; int tid = cpuc->excl_thread_id; - int o_tid = 1 - tid; /* alternate */ + int is_excl, i; /* * validating a group does not require @@ -1993,34 +2001,8 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event, /* * no exclusion needed */ - if (!excl_cntrs) + if (WARN_ON_ONCE(!excl_cntrs)) return c; - /* - * event requires exclusive counter access - * across HT threads - */ - is_excl = c->flags & PERF_X86_EVENT_EXCL; - - /* - * xl = state of current HT - * xlo = state of sibling HT - */ - xl = &excl_cntrs->states[tid]; - xlo = &excl_cntrs->states[o_tid]; - - /* - * do not allow scheduling of more than max_alloc_cntrs - * which is set to half the available generic counters. - * this helps avoid counter starvation of sibling thread - * by ensuring at most half the counters cannot be in - * exclusive mode. There is not designated counters for the - * limits. Any N/2 counters can be used. This helps with - * events with specifix counter constraints - */ - if (xl->num_alloc_cntrs++ == xl->max_alloc_cntrs) - return &emptyconstraint; - - cx = c; /* * because we modify the constraint, we need @@ -2031,10 +2013,7 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event, * been cloned (marked dynamic) */ if (!(c->flags & PERF_X86_EVENT_DYNAMIC)) { - - /* sanity check */ - if (idx < 0) - return &emptyconstraint; + struct event_constraint *cx; /* * grab pre-allocated constraint entry @@ -2045,13 +2024,14 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event, * initialize dynamic constraint * with static constraint */ - memcpy(cx, c, sizeof(*cx)); + *cx = *c; /* * mark constraint as dynamic, so we * can free it later on */ cx->flags |= PERF_X86_EVENT_DYNAMIC; + c = cx; } /* @@ -2062,6 +2042,22 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event, */ /* + * state of sibling HT + */ + xlo = &excl_cntrs->states[tid ^ 1]; + + /* + * event requires exclusive counter access + * across HT threads + */ + is_excl = c->flags & PERF_X86_EVENT_EXCL; + if (is_excl && !(event->hw.flags & PERF_X86_EVENT_EXCL_ACCT)) { + event->hw.flags |= PERF_X86_EVENT_EXCL_ACCT; + if (!cpuc->n_excl++) + WRITE_ONCE(excl_cntrs->has_exclusive[tid], 1); + } + + /* * Modify static constraint with current dynamic * state of thread * @@ -2069,44 +2065,44 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event, * SHARED : sibling counter measuring non-exclusive event * UNUSED : sibling counter unused */ - for_each_set_bit(i, cx->idxmsk, X86_PMC_IDX_MAX) { + for_each_set_bit(i, c->idxmsk, X86_PMC_IDX_MAX) { /* * exclusive event in sibling counter * our corresponding counter cannot be used * regardless of our event */ - if (xl->state[i] == INTEL_EXCL_EXCLUSIVE) - __clear_bit(i, cx->idxmsk); + if (xlo->state[i] == INTEL_EXCL_EXCLUSIVE) + __clear_bit(i, c->idxmsk); /* * if measuring an exclusive event, sibling * measuring non-exclusive, then counter cannot * be used */ - if (is_excl && xl->state[i] == INTEL_EXCL_SHARED) - __clear_bit(i, cx->idxmsk); + if (is_excl && xlo->state[i] == INTEL_EXCL_SHARED) + __clear_bit(i, c->idxmsk); } /* * recompute actual bit weight for scheduling algorithm */ - cx->weight = hweight64(cx->idxmsk64); + c->weight = hweight64(c->idxmsk64); /* * if we return an empty mask, then switch * back to static empty constraint to avoid * the cost of freeing later on */ - if (cx->weight == 0) - cx = &emptyconstraint; + if (c->weight == 0) + c = &emptyconstraint; - return cx; + return c; } static struct event_constraint * intel_get_event_constraints(struct cpu_hw_events *cpuc, int idx, struct perf_event *event) { - struct event_constraint *c1 = event->hw.constraint; + struct event_constraint *c1 = cpuc->event_constraint[idx]; struct event_constraint *c2; /* @@ -2132,10 +2128,8 @@ static void intel_put_excl_constraints(struct cpu_hw_events *cpuc, { struct hw_perf_event *hwc = &event->hw; struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs; - struct intel_excl_states *xlo, *xl; - unsigned long flags = 0; /* keep compiler happy */ int tid = cpuc->excl_thread_id; - int o_tid = 1 - tid; + struct intel_excl_states *xl; /* * nothing needed if in group validation mode @@ -2143,31 +2137,35 @@ static void intel_put_excl_constraints(struct cpu_hw_events *cpuc, if (cpuc->is_fake) return; - WARN_ON_ONCE(!excl_cntrs); - - if (!excl_cntrs) + if (WARN_ON_ONCE(!excl_cntrs)) return; - xl = &excl_cntrs->states[tid]; - xlo = &excl_cntrs->states[o_tid]; + if (hwc->flags & PERF_X86_EVENT_EXCL_ACCT) { + hwc->flags &= ~PERF_X86_EVENT_EXCL_ACCT; + if (!--cpuc->n_excl) + WRITE_ONCE(excl_cntrs->has_exclusive[tid], 0); + } /* - * put_constraint may be called from x86_schedule_events() - * which already has the lock held so here make locking - * conditional + * If event was actually assigned, then mark the counter state as + * unused now. */ - if (!xl->sched_started) - raw_spin_lock_irqsave(&excl_cntrs->lock, flags); + if (hwc->idx >= 0) { + xl = &excl_cntrs->states[tid]; - /* - * if event was actually assigned, then mark the - * counter state as unused now - */ - if (hwc->idx >= 0) - xlo->state[hwc->idx] = INTEL_EXCL_UNUSED; + /* + * put_constraint may be called from x86_schedule_events() + * which already has the lock held so here make locking + * conditional. + */ + if (!xl->sched_started) + raw_spin_lock(&excl_cntrs->lock); - if (!xl->sched_started) - raw_spin_unlock_irqrestore(&excl_cntrs->lock, flags); + xl->state[hwc->idx] = INTEL_EXCL_UNUSED; + + if (!xl->sched_started) + raw_spin_unlock(&excl_cntrs->lock); + } } static void @@ -2188,8 +2186,6 @@ intel_put_shared_regs_event_constraints(struct cpu_hw_events *cpuc, static void intel_put_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) { - struct event_constraint *c = event->hw.constraint; - intel_put_shared_regs_event_constraints(cpuc, event); /* @@ -2197,48 +2193,8 @@ static void intel_put_event_constraints(struct cpu_hw_events *cpuc, * all events are subject to and must call the * put_excl_constraints() routine */ - if (c && cpuc->excl_cntrs) + if (cpuc->excl_cntrs) intel_put_excl_constraints(cpuc, event); - - /* cleanup dynamic constraint */ - if (c && (c->flags & PERF_X86_EVENT_DYNAMIC)) - event->hw.constraint = NULL; -} - -static void intel_commit_scheduling(struct cpu_hw_events *cpuc, - struct perf_event *event, int cntr) -{ - struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs; - struct event_constraint *c = event->hw.constraint; - struct intel_excl_states *xlo, *xl; - int tid = cpuc->excl_thread_id; - int o_tid = 1 - tid; - int is_excl; - - if (cpuc->is_fake || !c) - return; - - is_excl = c->flags & PERF_X86_EVENT_EXCL; - - if (!(c->flags & PERF_X86_EVENT_DYNAMIC)) - return; - - WARN_ON_ONCE(!excl_cntrs); - - if (!excl_cntrs) - return; - - xl = &excl_cntrs->states[tid]; - xlo = &excl_cntrs->states[o_tid]; - - WARN_ON_ONCE(!raw_spin_is_locked(&excl_cntrs->lock)); - - if (cntr >= 0) { - if (is_excl) - xlo->init_state[cntr] = INTEL_EXCL_EXCLUSIVE; - else - xlo->init_state[cntr] = INTEL_EXCL_SHARED; - } } static void intel_pebs_aliases_core2(struct perf_event *event) @@ -2304,8 +2260,15 @@ static int intel_pmu_hw_config(struct perf_event *event) if (ret) return ret; - if (event->attr.precise_ip && x86_pmu.pebs_aliases) - x86_pmu.pebs_aliases(event); + if (event->attr.precise_ip) { + if (!event->attr.freq) { + event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD; + if (!(event->attr.sample_type & ~PEBS_FREERUNNING_FLAGS)) + event->hw.flags |= PERF_X86_EVENT_FREERUNNING; + } + if (x86_pmu.pebs_aliases) + x86_pmu.pebs_aliases(event); + } if (needs_branch_stack(event)) { ret = intel_pmu_setup_lbr_filter(event); @@ -2554,19 +2517,11 @@ struct intel_shared_regs *allocate_shared_regs(int cpu) static struct intel_excl_cntrs *allocate_excl_cntrs(int cpu) { struct intel_excl_cntrs *c; - int i; c = kzalloc_node(sizeof(struct intel_excl_cntrs), GFP_KERNEL, cpu_to_node(cpu)); if (c) { raw_spin_lock_init(&c->lock); - for (i = 0; i < X86_PMC_IDX_MAX; i++) { - c->states[0].state[i] = INTEL_EXCL_UNUSED; - c->states[0].init_state[i] = INTEL_EXCL_UNUSED; - - c->states[1].state[i] = INTEL_EXCL_UNUSED; - c->states[1].init_state[i] = INTEL_EXCL_UNUSED; - } c->core_id = -1; } return c; @@ -2621,7 +2576,7 @@ static void intel_pmu_cpu_starting(int cpu) if (!(x86_pmu.flags & PMU_FL_NO_HT_SHARING)) { void **onln = &cpuc->kfree_on_online[X86_PERF_KFREE_SHARED]; - for_each_cpu(i, topology_thread_cpumask(cpu)) { + for_each_cpu(i, topology_sibling_cpumask(cpu)) { struct intel_shared_regs *pc; pc = per_cpu(cpu_hw_events, i).shared_regs; @@ -2639,9 +2594,7 @@ static void intel_pmu_cpu_starting(int cpu) cpuc->lbr_sel = &cpuc->shared_regs->regs[EXTRA_REG_LBR]; if (x86_pmu.flags & PMU_FL_EXCL_CNTRS) { - int h = x86_pmu.num_counters >> 1; - - for_each_cpu(i, topology_thread_cpumask(cpu)) { + for_each_cpu(i, topology_sibling_cpumask(cpu)) { struct intel_excl_cntrs *c; c = per_cpu(cpu_hw_events, i).excl_cntrs; @@ -2654,11 +2607,6 @@ static void intel_pmu_cpu_starting(int cpu) } cpuc->excl_cntrs->core_id = core_id; cpuc->excl_cntrs->refcnt++; - /* - * set hard limit to half the number of generic counters - */ - cpuc->excl_cntrs->states[0].max_alloc_cntrs = h; - cpuc->excl_cntrs->states[1].max_alloc_cntrs = h; } } @@ -2694,6 +2642,15 @@ static void intel_pmu_cpu_dying(int cpu) fini_debug_store_on_cpu(cpu); } +static void intel_pmu_sched_task(struct perf_event_context *ctx, + bool sched_in) +{ + if (x86_pmu.pebs_active) + intel_pmu_pebs_sched_task(ctx, sched_in); + if (x86_pmu.lbr_nr) + intel_pmu_lbr_sched_task(ctx, sched_in); +} + PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63"); PMU_FORMAT_ATTR(ldlat, "config1:0-15"); @@ -2783,7 +2740,7 @@ static __initconst const struct x86_pmu intel_pmu = { .cpu_starting = intel_pmu_cpu_starting, .cpu_dying = intel_pmu_cpu_dying, .guest_get_msrs = intel_guest_get_msrs, - .sched_task = intel_pmu_lbr_sched_task, + .sched_task = intel_pmu_sched_task, }; static __init void intel_clovertown_quirk(void) @@ -2956,8 +2913,8 @@ static __init void intel_ht_bug(void) { x86_pmu.flags |= PMU_FL_EXCL_CNTRS | PMU_FL_EXCL_ENABLED; - x86_pmu.commit_scheduling = intel_commit_scheduling; x86_pmu.start_scheduling = intel_start_scheduling; + x86_pmu.commit_scheduling = intel_commit_scheduling; x86_pmu.stop_scheduling = intel_stop_scheduling; } @@ -3270,6 +3227,8 @@ __init int intel_pmu_init(void) case 61: /* 14nm Broadwell Core-M */ case 86: /* 14nm Broadwell Xeon D */ + case 71: /* 14nm Broadwell + GT3e (Intel Iris Pro graphics) */ + case 79: /* 14nm Broadwell Server */ x86_pmu.late_ack = true; memcpy(hw_cache_event_ids, hsw_hw_cache_event_ids, sizeof(hw_cache_event_ids)); memcpy(hw_cache_extra_regs, hsw_hw_cache_extra_regs, sizeof(hw_cache_extra_regs)); @@ -3339,13 +3298,13 @@ __init int intel_pmu_init(void) * counter, so do not extend mask to generic counters */ for_each_event_constraint(c, x86_pmu.event_constraints) { - if (c->cmask != FIXED_EVENT_FLAGS - || c->idxmsk64 == INTEL_PMC_MSK_FIXED_REF_CYCLES) { - continue; + if (c->cmask == FIXED_EVENT_FLAGS + && c->idxmsk64 != INTEL_PMC_MSK_FIXED_REF_CYCLES) { + c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1; } - - c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1; - c->weight += x86_pmu.num_counters; + c->idxmsk64 &= + ~(~0UL << (INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed)); + c->weight = hweight64(c->idxmsk64); } } @@ -3403,7 +3362,7 @@ static __init int fixup_ht_bug(void) if (!(x86_pmu.flags & PMU_FL_EXCL_ENABLED)) return 0; - w = cpumask_weight(topology_thread_cpumask(cpu)); + w = cpumask_weight(topology_sibling_cpumask(cpu)); if (w > 1) { pr_info("PMU erratum BJ122, BV98, HSD29 worked around, HT is on\n"); return 0; @@ -3413,8 +3372,8 @@ static __init int fixup_ht_bug(void) x86_pmu.flags &= ~(PMU_FL_EXCL_CNTRS | PMU_FL_EXCL_ENABLED); - x86_pmu.commit_scheduling = NULL; x86_pmu.start_scheduling = NULL; + x86_pmu.commit_scheduling = NULL; x86_pmu.stop_scheduling = NULL; watchdog_nmi_enable_all(); diff --git a/arch/x86/kernel/cpu/perf_event_intel_bts.c b/arch/x86/kernel/cpu/perf_event_intel_bts.c index ac1f0c55f379..7795f3f8b1d5 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_bts.c +++ b/arch/x86/kernel/cpu/perf_event_intel_bts.c @@ -483,17 +483,26 @@ static int bts_event_add(struct perf_event *event, int mode) static void bts_event_destroy(struct perf_event *event) { + x86_release_hardware(); x86_del_exclusive(x86_lbr_exclusive_bts); } static int bts_event_init(struct perf_event *event) { + int ret; + if (event->attr.type != bts_pmu.type) return -ENOENT; if (x86_add_exclusive(x86_lbr_exclusive_bts)) return -EBUSY; + ret = x86_reserve_hardware(); + if (ret) { + x86_del_exclusive(x86_lbr_exclusive_bts); + return ret; + } + event->destroy = bts_event_destroy; return 0; diff --git a/arch/x86/kernel/cpu/perf_event_intel_cqm.c b/arch/x86/kernel/cpu/perf_event_intel_cqm.c index e4d1b8b738fa..188076161c1b 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_cqm.c +++ b/arch/x86/kernel/cpu/perf_event_intel_cqm.c @@ -13,16 +13,35 @@ #define MSR_IA32_QM_CTR 0x0c8e #define MSR_IA32_QM_EVTSEL 0x0c8d -static unsigned int cqm_max_rmid = -1; +static u32 cqm_max_rmid = -1; static unsigned int cqm_l3_scale; /* supposedly cacheline size */ -struct intel_cqm_state { - raw_spinlock_t lock; - int rmid; - int cnt; +/** + * struct intel_pqr_state - State cache for the PQR MSR + * @rmid: The cached Resource Monitoring ID + * @closid: The cached Class Of Service ID + * @rmid_usecnt: The usage counter for rmid + * + * The upper 32 bits of MSR_IA32_PQR_ASSOC contain closid and the + * lower 10 bits rmid. The update to MSR_IA32_PQR_ASSOC always + * contains both parts, so we need to cache them. + * + * The cache also helps to avoid pointless updates if the value does + * not change. + */ +struct intel_pqr_state { + u32 rmid; + u32 closid; + int rmid_usecnt; }; -static DEFINE_PER_CPU(struct intel_cqm_state, cqm_state); +/* + * The cached intel_pqr_state is strictly per CPU and can never be + * updated from a remote CPU. Both functions which modify the state + * (intel_cqm_event_start and intel_cqm_event_stop) are called with + * interrupts disabled, which is sufficient for the protection. + */ +static DEFINE_PER_CPU(struct intel_pqr_state, pqr_state); /* * Protects cache_cgroups and cqm_rmid_free_lru and cqm_rmid_limbo_lru. @@ -57,7 +76,7 @@ static cpumask_t cqm_cpumask; * near-zero occupancy value, i.e. no cachelines are tagged with this * RMID, once __intel_cqm_rmid_rotate() returns. */ -static unsigned int intel_cqm_rotation_rmid; +static u32 intel_cqm_rotation_rmid; #define INVALID_RMID (-1) @@ -69,7 +88,7 @@ static unsigned int intel_cqm_rotation_rmid; * Likewise, an rmid value of -1 is used to indicate "no rmid currently * assigned" and is used as part of the rotation code. */ -static inline bool __rmid_valid(unsigned int rmid) +static inline bool __rmid_valid(u32 rmid) { if (!rmid || rmid == INVALID_RMID) return false; @@ -77,7 +96,7 @@ static inline bool __rmid_valid(unsigned int rmid) return true; } -static u64 __rmid_read(unsigned int rmid) +static u64 __rmid_read(u32 rmid) { u64 val; @@ -102,7 +121,7 @@ enum rmid_recycle_state { }; struct cqm_rmid_entry { - unsigned int rmid; + u32 rmid; enum rmid_recycle_state state; struct list_head list; unsigned long queue_time; @@ -147,7 +166,7 @@ static LIST_HEAD(cqm_rmid_limbo_lru); */ static struct cqm_rmid_entry **cqm_rmid_ptrs; -static inline struct cqm_rmid_entry *__rmid_entry(int rmid) +static inline struct cqm_rmid_entry *__rmid_entry(u32 rmid) { struct cqm_rmid_entry *entry; @@ -162,7 +181,7 @@ static inline struct cqm_rmid_entry *__rmid_entry(int rmid) * * We expect to be called with cache_mutex held. */ -static int __get_rmid(void) +static u32 __get_rmid(void) { struct cqm_rmid_entry *entry; @@ -177,7 +196,7 @@ static int __get_rmid(void) return entry->rmid; } -static void __put_rmid(unsigned int rmid) +static void __put_rmid(u32 rmid) { struct cqm_rmid_entry *entry; @@ -372,7 +391,7 @@ static bool __conflict_event(struct perf_event *a, struct perf_event *b) } struct rmid_read { - unsigned int rmid; + u32 rmid; atomic64_t value; }; @@ -381,12 +400,11 @@ static void __intel_cqm_event_count(void *info); /* * Exchange the RMID of a group of events. */ -static unsigned int -intel_cqm_xchg_rmid(struct perf_event *group, unsigned int rmid) +static u32 intel_cqm_xchg_rmid(struct perf_event *group, u32 rmid) { struct perf_event *event; - unsigned int old_rmid = group->hw.cqm_rmid; struct list_head *head = &group->hw.cqm_group_entry; + u32 old_rmid = group->hw.cqm_rmid; lockdep_assert_held(&cache_mutex); @@ -451,7 +469,7 @@ static void intel_cqm_stable(void *arg) * If we have group events waiting for an RMID that don't conflict with * events already running, assign @rmid. */ -static bool intel_cqm_sched_in_event(unsigned int rmid) +static bool intel_cqm_sched_in_event(u32 rmid) { struct perf_event *leader, *event; @@ -598,7 +616,7 @@ static bool intel_cqm_rmid_stabilize(unsigned int *available) static void __intel_cqm_pick_and_rotate(struct perf_event *next) { struct perf_event *rotor; - unsigned int rmid; + u32 rmid; lockdep_assert_held(&cache_mutex); @@ -626,7 +644,7 @@ static void __intel_cqm_pick_and_rotate(struct perf_event *next) static void intel_cqm_sched_out_conflicting_events(struct perf_event *event) { struct perf_event *group, *g; - unsigned int rmid; + u32 rmid; lockdep_assert_held(&cache_mutex); @@ -828,8 +846,8 @@ static void intel_cqm_setup_event(struct perf_event *event, struct perf_event **group) { struct perf_event *iter; - unsigned int rmid; bool conflict = false; + u32 rmid; list_for_each_entry(iter, &cache_groups, hw.cqm_groups_entry) { rmid = iter->hw.cqm_rmid; @@ -860,7 +878,7 @@ static void intel_cqm_setup_event(struct perf_event *event, static void intel_cqm_event_read(struct perf_event *event) { unsigned long flags; - unsigned int rmid; + u32 rmid; u64 val; /* @@ -961,55 +979,48 @@ out: static void intel_cqm_event_start(struct perf_event *event, int mode) { - struct intel_cqm_state *state = this_cpu_ptr(&cqm_state); - unsigned int rmid = event->hw.cqm_rmid; - unsigned long flags; + struct intel_pqr_state *state = this_cpu_ptr(&pqr_state); + u32 rmid = event->hw.cqm_rmid; if (!(event->hw.cqm_state & PERF_HES_STOPPED)) return; event->hw.cqm_state &= ~PERF_HES_STOPPED; - raw_spin_lock_irqsave(&state->lock, flags); - - if (state->cnt++) - WARN_ON_ONCE(state->rmid != rmid); - else + if (state->rmid_usecnt++) { + if (!WARN_ON_ONCE(state->rmid != rmid)) + return; + } else { WARN_ON_ONCE(state->rmid); + } state->rmid = rmid; - wrmsrl(MSR_IA32_PQR_ASSOC, state->rmid); - - raw_spin_unlock_irqrestore(&state->lock, flags); + wrmsr(MSR_IA32_PQR_ASSOC, rmid, state->closid); } static void intel_cqm_event_stop(struct perf_event *event, int mode) { - struct intel_cqm_state *state = this_cpu_ptr(&cqm_state); - unsigned long flags; + struct intel_pqr_state *state = this_cpu_ptr(&pqr_state); if (event->hw.cqm_state & PERF_HES_STOPPED) return; event->hw.cqm_state |= PERF_HES_STOPPED; - raw_spin_lock_irqsave(&state->lock, flags); intel_cqm_event_read(event); - if (!--state->cnt) { + if (!--state->rmid_usecnt) { state->rmid = 0; - wrmsrl(MSR_IA32_PQR_ASSOC, 0); + wrmsr(MSR_IA32_PQR_ASSOC, 0, state->closid); } else { WARN_ON_ONCE(!state->rmid); } - - raw_spin_unlock_irqrestore(&state->lock, flags); } static int intel_cqm_event_add(struct perf_event *event, int mode) { unsigned long flags; - unsigned int rmid; + u32 rmid; raw_spin_lock_irqsave(&cache_lock, flags); @@ -1024,11 +1035,6 @@ static int intel_cqm_event_add(struct perf_event *event, int mode) return 0; } -static void intel_cqm_event_del(struct perf_event *event, int mode) -{ - intel_cqm_event_stop(event, mode); -} - static void intel_cqm_event_destroy(struct perf_event *event) { struct perf_event *group_other = NULL; @@ -1057,7 +1063,7 @@ static void intel_cqm_event_destroy(struct perf_event *event) list_replace(&event->hw.cqm_groups_entry, &group_other->hw.cqm_groups_entry); } else { - unsigned int rmid = event->hw.cqm_rmid; + u32 rmid = event->hw.cqm_rmid; if (__rmid_valid(rmid)) __put_rmid(rmid); @@ -1221,7 +1227,7 @@ static struct pmu intel_cqm_pmu = { .task_ctx_nr = perf_sw_context, .event_init = intel_cqm_event_init, .add = intel_cqm_event_add, - .del = intel_cqm_event_del, + .del = intel_cqm_event_stop, .start = intel_cqm_event_start, .stop = intel_cqm_event_stop, .read = intel_cqm_event_read, @@ -1243,12 +1249,12 @@ static inline void cqm_pick_event_reader(int cpu) static void intel_cqm_cpu_prepare(unsigned int cpu) { - struct intel_cqm_state *state = &per_cpu(cqm_state, cpu); + struct intel_pqr_state *state = &per_cpu(pqr_state, cpu); struct cpuinfo_x86 *c = &cpu_data(cpu); - raw_spin_lock_init(&state->lock); state->rmid = 0; - state->cnt = 0; + state->closid = 0; + state->rmid_usecnt = 0; WARN_ON(c->x86_cache_max_rmid != cqm_max_rmid); WARN_ON(c->x86_cache_occ_scale != cqm_l3_scale); diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index 813f75d71175..71fc40238843 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -11,7 +11,7 @@ #define BTS_RECORD_SIZE 24 #define BTS_BUFFER_SIZE (PAGE_SIZE << 4) -#define PEBS_BUFFER_SIZE PAGE_SIZE +#define PEBS_BUFFER_SIZE (PAGE_SIZE << 4) #define PEBS_FIXUP_SIZE PAGE_SIZE /* @@ -250,7 +250,7 @@ static int alloc_pebs_buffer(int cpu) { struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds; int node = cpu_to_node(cpu); - int max, thresh = 1; /* always use a single PEBS record */ + int max; void *buffer, *ibuffer; if (!x86_pmu.pebs) @@ -280,9 +280,6 @@ static int alloc_pebs_buffer(int cpu) ds->pebs_absolute_maximum = ds->pebs_buffer_base + max * x86_pmu.pebs_record_size; - ds->pebs_interrupt_threshold = ds->pebs_buffer_base + - thresh * x86_pmu.pebs_record_size; - return 0; } @@ -549,6 +546,19 @@ int intel_pmu_drain_bts_buffer(void) return 1; } +static inline void intel_pmu_drain_pebs_buffer(void) +{ + struct pt_regs regs; + + x86_pmu.drain_pebs(®s); +} + +void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in) +{ + if (!sched_in) + intel_pmu_drain_pebs_buffer(); +} + /* * PEBS */ @@ -684,33 +694,81 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event) return &emptyconstraint; } +static inline bool pebs_is_enabled(struct cpu_hw_events *cpuc) +{ + return (cpuc->pebs_enabled & ((1ULL << MAX_PEBS_EVENTS) - 1)); +} + void intel_pmu_pebs_enable(struct perf_event *event) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc = &event->hw; + struct debug_store *ds = cpuc->ds; + bool first_pebs; + u64 threshold; hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT; + first_pebs = !pebs_is_enabled(cpuc); cpuc->pebs_enabled |= 1ULL << hwc->idx; if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT) cpuc->pebs_enabled |= 1ULL << (hwc->idx + 32); else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST) cpuc->pebs_enabled |= 1ULL << 63; + + /* + * When the event is constrained enough we can use a larger + * threshold and run the event with less frequent PMI. + */ + if (hwc->flags & PERF_X86_EVENT_FREERUNNING) { + threshold = ds->pebs_absolute_maximum - + x86_pmu.max_pebs_events * x86_pmu.pebs_record_size; + + if (first_pebs) + perf_sched_cb_inc(event->ctx->pmu); + } else { + threshold = ds->pebs_buffer_base + x86_pmu.pebs_record_size; + + /* + * If not all events can use larger buffer, + * roll back to threshold = 1 + */ + if (!first_pebs && + (ds->pebs_interrupt_threshold > threshold)) + perf_sched_cb_dec(event->ctx->pmu); + } + + /* Use auto-reload if possible to save a MSR write in the PMI */ + if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) { + ds->pebs_event_reset[hwc->idx] = + (u64)(-hwc->sample_period) & x86_pmu.cntval_mask; + } + + if (first_pebs || ds->pebs_interrupt_threshold > threshold) + ds->pebs_interrupt_threshold = threshold; } void intel_pmu_pebs_disable(struct perf_event *event) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc = &event->hw; + struct debug_store *ds = cpuc->ds; cpuc->pebs_enabled &= ~(1ULL << hwc->idx); - if (event->hw.constraint->flags & PERF_X86_EVENT_PEBS_LDLAT) + if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT) cpuc->pebs_enabled &= ~(1ULL << (hwc->idx + 32)); - else if (event->hw.constraint->flags & PERF_X86_EVENT_PEBS_ST) + else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST) cpuc->pebs_enabled &= ~(1ULL << 63); + if (ds->pebs_interrupt_threshold > + ds->pebs_buffer_base + x86_pmu.pebs_record_size) { + intel_pmu_drain_pebs_buffer(); + if (!pebs_is_enabled(cpuc)) + perf_sched_cb_dec(event->ctx->pmu); + } + if (cpuc->enabled) wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled); @@ -846,8 +904,10 @@ static inline u64 intel_hsw_transaction(struct pebs_record_hsw *pebs) return txn; } -static void __intel_pmu_pebs_event(struct perf_event *event, - struct pt_regs *iregs, void *__pebs) +static void setup_pebs_sample_data(struct perf_event *event, + struct pt_regs *iregs, void *__pebs, + struct perf_sample_data *data, + struct pt_regs *regs) { #define PERF_X86_EVENT_PEBS_HSW_PREC \ (PERF_X86_EVENT_PEBS_ST_HSW | \ @@ -859,13 +919,11 @@ static void __intel_pmu_pebs_event(struct perf_event *event, */ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct pebs_record_hsw *pebs = __pebs; - struct perf_sample_data data; - struct pt_regs regs; u64 sample_type; int fll, fst, dsrc; int fl = event->hw.flags; - if (!intel_pmu_save_and_restart(event)) + if (pebs == NULL) return; sample_type = event->attr.sample_type; @@ -874,15 +932,15 @@ static void __intel_pmu_pebs_event(struct perf_event *event, fll = fl & PERF_X86_EVENT_PEBS_LDLAT; fst = fl & (PERF_X86_EVENT_PEBS_ST | PERF_X86_EVENT_PEBS_HSW_PREC); - perf_sample_data_init(&data, 0, event->hw.last_period); + perf_sample_data_init(data, 0, event->hw.last_period); - data.period = event->hw.last_period; + data->period = event->hw.last_period; /* * Use latency for weight (only avail with PEBS-LL) */ if (fll && (sample_type & PERF_SAMPLE_WEIGHT)) - data.weight = pebs->lat; + data->weight = pebs->lat; /* * data.data_src encodes the data source @@ -895,7 +953,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event, val = precise_datala_hsw(event, pebs->dse); else if (fst) val = precise_store_data(pebs->dse); - data.data_src.val = val; + data->data_src.val = val; } /* @@ -908,61 +966,123 @@ static void __intel_pmu_pebs_event(struct perf_event *event, * PERF_SAMPLE_IP and PERF_SAMPLE_CALLCHAIN to function properly. * A possible PERF_SAMPLE_REGS will have to transfer all regs. */ - regs = *iregs; - regs.flags = pebs->flags; - set_linear_ip(®s, pebs->ip); - regs.bp = pebs->bp; - regs.sp = pebs->sp; + *regs = *iregs; + regs->flags = pebs->flags; + set_linear_ip(regs, pebs->ip); + regs->bp = pebs->bp; + regs->sp = pebs->sp; if (sample_type & PERF_SAMPLE_REGS_INTR) { - regs.ax = pebs->ax; - regs.bx = pebs->bx; - regs.cx = pebs->cx; - regs.dx = pebs->dx; - regs.si = pebs->si; - regs.di = pebs->di; - regs.bp = pebs->bp; - regs.sp = pebs->sp; - - regs.flags = pebs->flags; + regs->ax = pebs->ax; + regs->bx = pebs->bx; + regs->cx = pebs->cx; + regs->dx = pebs->dx; + regs->si = pebs->si; + regs->di = pebs->di; + regs->bp = pebs->bp; + regs->sp = pebs->sp; + + regs->flags = pebs->flags; #ifndef CONFIG_X86_32 - regs.r8 = pebs->r8; - regs.r9 = pebs->r9; - regs.r10 = pebs->r10; - regs.r11 = pebs->r11; - regs.r12 = pebs->r12; - regs.r13 = pebs->r13; - regs.r14 = pebs->r14; - regs.r15 = pebs->r15; + regs->r8 = pebs->r8; + regs->r9 = pebs->r9; + regs->r10 = pebs->r10; + regs->r11 = pebs->r11; + regs->r12 = pebs->r12; + regs->r13 = pebs->r13; + regs->r14 = pebs->r14; + regs->r15 = pebs->r15; #endif } if (event->attr.precise_ip > 1 && x86_pmu.intel_cap.pebs_format >= 2) { - regs.ip = pebs->real_ip; - regs.flags |= PERF_EFLAGS_EXACT; - } else if (event->attr.precise_ip > 1 && intel_pmu_pebs_fixup_ip(®s)) - regs.flags |= PERF_EFLAGS_EXACT; + regs->ip = pebs->real_ip; + regs->flags |= PERF_EFLAGS_EXACT; + } else if (event->attr.precise_ip > 1 && intel_pmu_pebs_fixup_ip(regs)) + regs->flags |= PERF_EFLAGS_EXACT; else - regs.flags &= ~PERF_EFLAGS_EXACT; + regs->flags &= ~PERF_EFLAGS_EXACT; if ((sample_type & PERF_SAMPLE_ADDR) && x86_pmu.intel_cap.pebs_format >= 1) - data.addr = pebs->dla; + data->addr = pebs->dla; if (x86_pmu.intel_cap.pebs_format >= 2) { /* Only set the TSX weight when no memory weight. */ if ((sample_type & PERF_SAMPLE_WEIGHT) && !fll) - data.weight = intel_hsw_weight(pebs); + data->weight = intel_hsw_weight(pebs); if (sample_type & PERF_SAMPLE_TRANSACTION) - data.txn = intel_hsw_transaction(pebs); + data->txn = intel_hsw_transaction(pebs); } if (has_branch_stack(event)) - data.br_stack = &cpuc->lbr_stack; + data->br_stack = &cpuc->lbr_stack; +} + +static inline void * +get_next_pebs_record_by_bit(void *base, void *top, int bit) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + void *at; + u64 pebs_status; + + if (base == NULL) + return NULL; + + for (at = base; at < top; at += x86_pmu.pebs_record_size) { + struct pebs_record_nhm *p = at; - if (perf_event_overflow(event, &data, ®s)) + if (test_bit(bit, (unsigned long *)&p->status)) { + /* PEBS v3 has accurate status bits */ + if (x86_pmu.intel_cap.pebs_format >= 3) + return at; + + if (p->status == (1 << bit)) + return at; + + /* clear non-PEBS bit and re-check */ + pebs_status = p->status & cpuc->pebs_enabled; + pebs_status &= (1ULL << MAX_PEBS_EVENTS) - 1; + if (pebs_status == (1 << bit)) + return at; + } + } + return NULL; +} + +static void __intel_pmu_pebs_event(struct perf_event *event, + struct pt_regs *iregs, + void *base, void *top, + int bit, int count) +{ + struct perf_sample_data data; + struct pt_regs regs; + void *at = get_next_pebs_record_by_bit(base, top, bit); + + if (!intel_pmu_save_and_restart(event) && + !(event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD)) + return; + + while (count > 1) { + setup_pebs_sample_data(event, iregs, at, &data, ®s); + perf_event_output(event, &data, ®s); + at += x86_pmu.pebs_record_size; + at = get_next_pebs_record_by_bit(at, top, bit); + count--; + } + + setup_pebs_sample_data(event, iregs, at, &data, ®s); + + /* + * All but the last records are processed. + * The last one is left to be able to call the overflow handler. + */ + if (perf_event_overflow(event, &data, ®s)) { x86_pmu_stop(event, 0); + return; + } + } static void intel_pmu_drain_pebs_core(struct pt_regs *iregs) @@ -992,72 +1112,99 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs) if (!event->attr.precise_ip) return; - n = top - at; + n = (top - at) / x86_pmu.pebs_record_size; if (n <= 0) return; - /* - * Should not happen, we program the threshold at 1 and do not - * set a reset value. - */ - WARN_ONCE(n > 1, "bad leftover pebs %d\n", n); - at += n - 1; - - __intel_pmu_pebs_event(event, iregs, at); + __intel_pmu_pebs_event(event, iregs, at, top, 0, n); } static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct debug_store *ds = cpuc->ds; - struct perf_event *event = NULL; - void *at, *top; - u64 status = 0; - int bit; + struct perf_event *event; + void *base, *at, *top; + short counts[MAX_PEBS_EVENTS] = {}; + short error[MAX_PEBS_EVENTS] = {}; + int bit, i; if (!x86_pmu.pebs_active) return; - at = (struct pebs_record_nhm *)(unsigned long)ds->pebs_buffer_base; + base = (struct pebs_record_nhm *)(unsigned long)ds->pebs_buffer_base; top = (struct pebs_record_nhm *)(unsigned long)ds->pebs_index; ds->pebs_index = ds->pebs_buffer_base; - if (unlikely(at > top)) + if (unlikely(base >= top)) return; - /* - * Should not happen, we program the threshold at 1 and do not - * set a reset value. - */ - WARN_ONCE(top - at > x86_pmu.max_pebs_events * x86_pmu.pebs_record_size, - "Unexpected number of pebs records %ld\n", - (long)(top - at) / x86_pmu.pebs_record_size); - - for (; at < top; at += x86_pmu.pebs_record_size) { + for (at = base; at < top; at += x86_pmu.pebs_record_size) { struct pebs_record_nhm *p = at; - for_each_set_bit(bit, (unsigned long *)&p->status, - x86_pmu.max_pebs_events) { - event = cpuc->events[bit]; - if (!test_bit(bit, cpuc->active_mask)) - continue; - - WARN_ON_ONCE(!event); + /* PEBS v3 has accurate status bits */ + if (x86_pmu.intel_cap.pebs_format >= 3) { + for_each_set_bit(bit, (unsigned long *)&p->status, + MAX_PEBS_EVENTS) + counts[bit]++; - if (!event->attr.precise_ip) - continue; + continue; + } - if (__test_and_set_bit(bit, (unsigned long *)&status)) + bit = find_first_bit((unsigned long *)&p->status, + x86_pmu.max_pebs_events); + if (bit >= x86_pmu.max_pebs_events) + continue; + if (!test_bit(bit, cpuc->active_mask)) + continue; + /* + * The PEBS hardware does not deal well with the situation + * when events happen near to each other and multiple bits + * are set. But it should happen rarely. + * + * If these events include one PEBS and multiple non-PEBS + * events, it doesn't impact PEBS record. The record will + * be handled normally. (slow path) + * + * If these events include two or more PEBS events, the + * records for the events can be collapsed into a single + * one, and it's not possible to reconstruct all events + * that caused the PEBS record. It's called collision. + * If collision happened, the record will be dropped. + * + */ + if (p->status != (1 << bit)) { + u64 pebs_status; + + /* slow path */ + pebs_status = p->status & cpuc->pebs_enabled; + pebs_status &= (1ULL << MAX_PEBS_EVENTS) - 1; + if (pebs_status != (1 << bit)) { + for_each_set_bit(i, (unsigned long *)&pebs_status, + MAX_PEBS_EVENTS) + error[i]++; continue; - - break; + } } + counts[bit]++; + } - if (!event || bit >= x86_pmu.max_pebs_events) + for (bit = 0; bit < x86_pmu.max_pebs_events; bit++) { + if ((counts[bit] == 0) && (error[bit] == 0)) continue; + event = cpuc->events[bit]; + WARN_ON_ONCE(!event); + WARN_ON_ONCE(!event->attr.precise_ip); - __intel_pmu_pebs_event(event, iregs, at); + /* log dropped samples number */ + if (error[bit]) + perf_log_lost_samples(event, error[bit]); + + if (counts[bit]) { + __intel_pmu_pebs_event(event, iregs, base, + top, bit, counts[bit]); + } } } diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c index 94e5b506caa6..452a7bd2dedb 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c +++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c @@ -96,6 +96,7 @@ enum { X86_BR_NO_TX = 1 << 14,/* not in transaction */ X86_BR_ZERO_CALL = 1 << 15,/* zero length call */ X86_BR_CALL_STACK = 1 << 16,/* call stack */ + X86_BR_IND_JMP = 1 << 17,/* indirect jump */ }; #define X86_BR_PLM (X86_BR_USER | X86_BR_KERNEL) @@ -113,6 +114,7 @@ enum { X86_BR_IRQ |\ X86_BR_ABORT |\ X86_BR_IND_CALL |\ + X86_BR_IND_JMP |\ X86_BR_ZERO_CALL) #define X86_BR_ALL (X86_BR_PLM | X86_BR_ANY) @@ -262,9 +264,6 @@ void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in) struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct x86_perf_task_context *task_ctx; - if (!x86_pmu.lbr_nr) - return; - /* * If LBR callstack feature is enabled and the stack was saved when * the task was scheduled out, restore the stack. Otherwise flush @@ -523,6 +522,9 @@ static int intel_pmu_setup_sw_lbr_filter(struct perf_event *event) X86_BR_CALL_STACK; } + if (br_type & PERF_SAMPLE_BRANCH_IND_JUMP) + mask |= X86_BR_IND_JMP; + /* * stash actual user request into reg, it may * be used by fixup code for some CPU @@ -736,7 +738,7 @@ static int branch_type(unsigned long from, unsigned long to, int abort) break; case 4: case 5: - ret = X86_BR_JMP; + ret = X86_BR_IND_JMP; break; } break; @@ -844,6 +846,7 @@ static const int nhm_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = { */ [PERF_SAMPLE_BRANCH_IND_CALL_SHIFT] = LBR_IND_CALL | LBR_IND_JMP, [PERF_SAMPLE_BRANCH_COND_SHIFT] = LBR_JCC, + [PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT] = LBR_IND_JMP, }; static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = { @@ -856,6 +859,7 @@ static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = { | LBR_FAR, [PERF_SAMPLE_BRANCH_IND_CALL_SHIFT] = LBR_IND_CALL, [PERF_SAMPLE_BRANCH_COND_SHIFT] = LBR_JCC, + [PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT] = LBR_IND_JMP, }; static const int hsw_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = { @@ -870,6 +874,7 @@ static const int hsw_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = { [PERF_SAMPLE_BRANCH_COND_SHIFT] = LBR_JCC, [PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT] = LBR_REL_CALL | LBR_IND_CALL | LBR_RETURN | LBR_CALL_STACK, + [PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT] = LBR_IND_JMP, }; /* core */ diff --git a/arch/x86/kernel/cpu/perf_event_intel_pt.c b/arch/x86/kernel/cpu/perf_event_intel_pt.c index ffe666c2c6b5..159887c3a89d 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_pt.c +++ b/arch/x86/kernel/cpu/perf_event_intel_pt.c @@ -151,7 +151,7 @@ static int __init pt_pmu_hw_init(void) de_attr->attr.attr.name = pt_caps[i].name; - sysfs_attr_init(&de_attrs->attr.attr); + sysfs_attr_init(&de_attr->attr.attr); de_attr->attr.attr.mode = S_IRUGO; de_attr->attr.show = pt_cap_show; @@ -187,15 +187,6 @@ static bool pt_event_valid(struct perf_event *event) * These all are cpu affine and operate on a local PT */ -static bool pt_is_running(void) -{ - u64 ctl; - - rdmsrl(MSR_IA32_RTIT_CTL, ctl); - - return !!(ctl & RTIT_CTL_TRACEEN); -} - static void pt_config(struct perf_event *event) { u64 reg; @@ -609,16 +600,19 @@ static unsigned int pt_topa_next_entry(struct pt_buffer *buf, unsigned int pg) * @handle: Current output handle. * * Place INT and STOP marks to prevent overwriting old data that the consumer - * hasn't yet collected. + * hasn't yet collected and waking up the consumer after a certain fraction of + * the buffer has filled up. Only needed and sensible for non-snapshot counters. + * + * This obviously relies on buf::head to figure out buffer markers, so it has + * to be called after pt_buffer_reset_offsets() and before the hardware tracing + * is enabled. */ static int pt_buffer_reset_markers(struct pt_buffer *buf, struct perf_output_handle *handle) { - unsigned long idx, npages, end; - - if (buf->snapshot) - return 0; + unsigned long head = local64_read(&buf->head); + unsigned long idx, npages, wakeup; /* can't stop in the middle of an output region */ if (buf->output_off + handle->size + 1 < @@ -634,17 +628,26 @@ static int pt_buffer_reset_markers(struct pt_buffer *buf, buf->topa_index[buf->stop_pos]->stop = 0; buf->topa_index[buf->intr_pos]->intr = 0; - if (pt_cap_get(PT_CAP_topa_multiple_entries)) { - npages = (handle->size + 1) >> PAGE_SHIFT; - end = (local64_read(&buf->head) >> PAGE_SHIFT) + npages; - /*if (end > handle->wakeup >> PAGE_SHIFT) - end = handle->wakeup >> PAGE_SHIFT;*/ - idx = end & (buf->nr_pages - 1); - buf->stop_pos = idx; - idx = (local64_read(&buf->head) >> PAGE_SHIFT) + npages - 1; - idx &= buf->nr_pages - 1; - buf->intr_pos = idx; - } + /* how many pages till the STOP marker */ + npages = handle->size >> PAGE_SHIFT; + + /* if it's on a page boundary, fill up one more page */ + if (!offset_in_page(head + handle->size + 1)) + npages++; + + idx = (head >> PAGE_SHIFT) + npages; + idx &= buf->nr_pages - 1; + buf->stop_pos = idx; + + wakeup = handle->wakeup >> PAGE_SHIFT; + + /* in the worst case, wake up the consumer one page before hard stop */ + idx = (head >> PAGE_SHIFT) + npages - 1; + if (idx > wakeup) + idx = wakeup; + + idx &= buf->nr_pages - 1; + buf->intr_pos = idx; buf->topa_index[buf->stop_pos]->stop = 1; buf->topa_index[buf->intr_pos]->intr = 1; @@ -664,7 +667,7 @@ static void pt_buffer_setup_topa_index(struct pt_buffer *buf) struct topa *cur = buf->first, *prev = buf->last; struct topa_entry *te_cur = TOPA_ENTRY(cur, 0), *te_prev = TOPA_ENTRY(prev, prev->last - 1); - int pg = 0, idx = 0, ntopa = 0; + int pg = 0, idx = 0; while (pg < buf->nr_pages) { int tidx; @@ -679,9 +682,9 @@ static void pt_buffer_setup_topa_index(struct pt_buffer *buf) /* advance to next topa table */ idx = 0; cur = list_entry(cur->list.next, struct topa, list); - ntopa++; - } else + } else { idx++; + } te_cur = TOPA_ENTRY(cur, idx); } @@ -693,7 +696,14 @@ static void pt_buffer_setup_topa_index(struct pt_buffer *buf) * @head: Write pointer (aux_head) from AUX buffer. * * Find the ToPA table and entry corresponding to given @head and set buffer's - * "current" pointers accordingly. + * "current" pointers accordingly. This is done after we have obtained the + * current aux_head position from a successful call to perf_aux_output_begin() + * to make sure the hardware is writing to the right place. + * + * This function modifies buf::{cur,cur_idx,output_off} that will be programmed + * into PT msrs when the tracing is enabled and buf::head and buf::data_size, + * which are used to determine INT and STOP markers' locations by a subsequent + * call to pt_buffer_reset_markers(). */ static void pt_buffer_reset_offsets(struct pt_buffer *buf, unsigned long head) { @@ -891,6 +901,7 @@ void intel_pt_interrupt(void) } pt_buffer_reset_offsets(buf, pt->handle.head); + /* snapshot counters don't use PMI, so it's safe */ ret = pt_buffer_reset_markers(buf, &pt->handle); if (ret) { perf_aux_output_end(&pt->handle, 0, true); @@ -913,7 +924,7 @@ static void pt_event_start(struct perf_event *event, int mode) struct pt *pt = this_cpu_ptr(&pt_ctx); struct pt_buffer *buf = perf_get_aux(&pt->handle); - if (pt_is_running() || !buf || pt_buffer_is_full(buf, pt)) { + if (!buf || pt_buffer_is_full(buf, pt)) { event->hw.state = PERF_HES_STOPPED; return; } @@ -944,7 +955,6 @@ static void pt_event_stop(struct perf_event *event, int mode) event->hw.state = PERF_HES_STOPPED; if (mode & PERF_EF_UPDATE) { - struct pt *pt = this_cpu_ptr(&pt_ctx); struct pt_buffer *buf = perf_get_aux(&pt->handle); if (!buf) diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index c635b8b49e93..7c1de1610178 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -365,9 +365,8 @@ static int uncore_assign_events(struct intel_uncore_box *box, int assign[], int bitmap_zero(used_mask, UNCORE_PMC_IDX_MAX); for (i = 0, wmin = UNCORE_PMC_IDX_MAX, wmax = 0; i < n; i++) { - hwc = &box->event_list[i]->hw; c = uncore_get_event_constraint(box, box->event_list[i]); - hwc->constraint = c; + box->event_constraint[i] = c; wmin = min(wmin, c->weight); wmax = max(wmax, c->weight); } @@ -375,7 +374,7 @@ static int uncore_assign_events(struct intel_uncore_box *box, int assign[], int /* fastpath, try to reuse previous register */ for (i = 0; i < n; i++) { hwc = &box->event_list[i]->hw; - c = hwc->constraint; + c = box->event_constraint[i]; /* never assigned */ if (hwc->idx == -1) @@ -395,8 +394,8 @@ static int uncore_assign_events(struct intel_uncore_box *box, int assign[], int } /* slow path */ if (i != n) - ret = perf_assign_events(box->event_list, n, - wmin, wmax, assign); + ret = perf_assign_events(box->event_constraint, n, + wmin, wmax, n, assign); if (!assign || ret) { for (i = 0; i < n; i++) @@ -840,6 +839,7 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id box->phys_id = phys_id; box->pci_dev = pdev; box->pmu = pmu; + uncore_box_init(box); pci_set_drvdata(pdev, box); raw_spin_lock(&uncore_box_lock); @@ -922,6 +922,9 @@ static int __init uncore_pci_init(void) case 69: /* Haswell Celeron */ ret = hsw_uncore_pci_init(); break; + case 61: /* Broadwell */ + ret = bdw_uncore_pci_init(); + break; default: return 0; } @@ -1003,8 +1006,10 @@ static int uncore_cpu_starting(int cpu) pmu = &type->pmus[j]; box = *per_cpu_ptr(pmu->box, cpu); /* called by uncore_cpu_init? */ - if (box && box->phys_id >= 0) + if (box && box->phys_id >= 0) { + uncore_box_init(box); continue; + } for_each_online_cpu(k) { exist = *per_cpu_ptr(pmu->box, k); @@ -1020,8 +1025,10 @@ static int uncore_cpu_starting(int cpu) } } - if (box) + if (box) { box->phys_id = phys_id; + uncore_box_init(box); + } } } return 0; diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h index 6c8c1e7e69d8..0f77f0a196e4 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h @@ -97,6 +97,7 @@ struct intel_uncore_box { atomic_t refcnt; struct perf_event *events[UNCORE_PMC_IDX_MAX]; struct perf_event *event_list[UNCORE_PMC_IDX_MAX]; + struct event_constraint *event_constraint[UNCORE_PMC_IDX_MAX]; unsigned long active_mask[BITS_TO_LONGS(UNCORE_PMC_IDX_MAX)]; u64 tags[UNCORE_PMC_IDX_MAX]; struct pci_dev *pci_dev; @@ -257,14 +258,6 @@ static inline int uncore_num_counters(struct intel_uncore_box *box) return box->pmu->type->num_counters; } -static inline void uncore_box_init(struct intel_uncore_box *box) -{ - if (!test_and_set_bit(UNCORE_BOX_FLAG_INITIATED, &box->flags)) { - if (box->pmu->type->ops->init_box) - box->pmu->type->ops->init_box(box); - } -} - static inline void uncore_disable_box(struct intel_uncore_box *box) { if (box->pmu->type->ops->disable_box) @@ -273,8 +266,6 @@ static inline void uncore_disable_box(struct intel_uncore_box *box) static inline void uncore_enable_box(struct intel_uncore_box *box) { - uncore_box_init(box); - if (box->pmu->type->ops->enable_box) box->pmu->type->ops->enable_box(box); } @@ -297,6 +288,14 @@ static inline u64 uncore_read_counter(struct intel_uncore_box *box, return box->pmu->type->ops->read_counter(box, event); } +static inline void uncore_box_init(struct intel_uncore_box *box) +{ + if (!test_and_set_bit(UNCORE_BOX_FLAG_INITIATED, &box->flags)) { + if (box->pmu->type->ops->init_box) + box->pmu->type->ops->init_box(box); + } +} + static inline bool uncore_box_is_fake(struct intel_uncore_box *box) { return (box->phys_id < 0); @@ -326,6 +325,7 @@ extern struct event_constraint uncore_constraint_empty; int snb_uncore_pci_init(void); int ivb_uncore_pci_init(void); int hsw_uncore_pci_init(void); +int bdw_uncore_pci_init(void); void snb_uncore_cpu_init(void); void nhm_uncore_cpu_init(void); diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c index 4562e9e22c60..b005a78c7012 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c @@ -7,6 +7,7 @@ #define PCI_DEVICE_ID_INTEL_IVB_E3_IMC 0x0150 #define PCI_DEVICE_ID_INTEL_HSW_IMC 0x0c00 #define PCI_DEVICE_ID_INTEL_HSW_U_IMC 0x0a04 +#define PCI_DEVICE_ID_INTEL_BDW_IMC 0x1604 /* SNB event control */ #define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff @@ -486,6 +487,14 @@ static const struct pci_device_id hsw_uncore_pci_ids[] = { { /* end: all zeroes */ }, }; +static const struct pci_device_id bdw_uncore_pci_ids[] = { + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BDW_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* end: all zeroes */ }, +}; + static struct pci_driver snb_uncore_pci_driver = { .name = "snb_uncore", .id_table = snb_uncore_pci_ids, @@ -501,6 +510,11 @@ static struct pci_driver hsw_uncore_pci_driver = { .id_table = hsw_uncore_pci_ids, }; +static struct pci_driver bdw_uncore_pci_driver = { + .name = "bdw_uncore", + .id_table = bdw_uncore_pci_ids, +}; + struct imc_uncore_pci_dev { __u32 pci_id; struct pci_driver *driver; @@ -514,6 +528,7 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = { IMC_DEV(IVB_E3_IMC, &ivb_uncore_pci_driver), /* Xeon E3-1200 v2/3rd Gen Core processor */ IMC_DEV(HSW_IMC, &hsw_uncore_pci_driver), /* 4th Gen Core Processor */ IMC_DEV(HSW_U_IMC, &hsw_uncore_pci_driver), /* 4th Gen Core ULT Mobile Processor */ + IMC_DEV(BDW_IMC, &bdw_uncore_pci_driver), /* 5th Gen Core U */ { /* end marker */ } }; @@ -561,6 +576,11 @@ int hsw_uncore_pci_init(void) return imc_uncore_pci_init(); } +int bdw_uncore_pci_init(void) +{ + return imc_uncore_pci_init(); +} + /* end of Sandy Bridge uncore support */ /* Nehalem uncore support */ diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c index 12d9548457e7..6d6e85dd5849 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c @@ -164,8 +164,8 @@ ((1ULL << (n)) - 1))) /* Haswell-EP Ubox */ -#define HSWEP_U_MSR_PMON_CTR0 0x705 -#define HSWEP_U_MSR_PMON_CTL0 0x709 +#define HSWEP_U_MSR_PMON_CTR0 0x709 +#define HSWEP_U_MSR_PMON_CTL0 0x705 #define HSWEP_U_MSR_PMON_FILTER 0x707 #define HSWEP_U_MSR_PMON_UCLK_FIXED_CTL 0x703 @@ -1914,7 +1914,7 @@ static struct intel_uncore_type hswep_uncore_cbox = { .name = "cbox", .num_counters = 4, .num_boxes = 18, - .perf_ctr_bits = 44, + .perf_ctr_bits = 48, .event_ctl = HSWEP_C0_MSR_PMON_CTL0, .perf_ctr = HSWEP_C0_MSR_PMON_CTR0, .event_mask = SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK, diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index e7d8c7608471..18ca99f2798b 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -12,7 +12,8 @@ static void show_cpuinfo_core(struct seq_file *m, struct cpuinfo_x86 *c, { #ifdef CONFIG_SMP seq_printf(m, "physical id\t: %d\n", c->phys_proc_id); - seq_printf(m, "siblings\t: %d\n", cpumask_weight(cpu_core_mask(cpu))); + seq_printf(m, "siblings\t: %d\n", + cpumask_weight(topology_core_cpumask(cpu))); seq_printf(m, "core id\t\t: %d\n", c->cpu_core_id); seq_printf(m, "cpu cores\t: %d\n", c->booted_cores); seq_printf(m, "apicid\t\t: %d\n", c->apicid); diff --git a/arch/x86/kernel/fpu/Makefile b/arch/x86/kernel/fpu/Makefile new file mode 100644 index 000000000000..68279efb811a --- /dev/null +++ b/arch/x86/kernel/fpu/Makefile @@ -0,0 +1,5 @@ +# +# Build rules for the FPU support code: +# + +obj-y += init.o bugs.o core.o regset.o signal.o xstate.o diff --git a/arch/x86/kernel/fpu/bugs.c b/arch/x86/kernel/fpu/bugs.c new file mode 100644 index 000000000000..dd9ca9b60ff3 --- /dev/null +++ b/arch/x86/kernel/fpu/bugs.c @@ -0,0 +1,71 @@ +/* + * x86 FPU bug checks: + */ +#include <asm/fpu/internal.h> + +/* + * Boot time CPU/FPU FDIV bug detection code: + */ + +static double __initdata x = 4195835.0; +static double __initdata y = 3145727.0; + +/* + * This used to check for exceptions.. + * However, it turns out that to support that, + * the XMM trap handlers basically had to + * be buggy. So let's have a correct XMM trap + * handler, and forget about printing out + * some status at boot. + * + * We should really only care about bugs here + * anyway. Not features. + */ +static void __init check_fpu(void) +{ + u32 cr0_saved; + s32 fdiv_bug; + + /* We might have CR0::TS set already, clear it: */ + cr0_saved = read_cr0(); + write_cr0(cr0_saved & ~X86_CR0_TS); + + kernel_fpu_begin(); + + /* + * trap_init() enabled FXSR and company _before_ testing for FP + * problems here. + * + * Test for the divl bug: http://en.wikipedia.org/wiki/Fdiv_bug + */ + __asm__("fninit\n\t" + "fldl %1\n\t" + "fdivl %2\n\t" + "fmull %2\n\t" + "fldl %1\n\t" + "fsubp %%st,%%st(1)\n\t" + "fistpl %0\n\t" + "fwait\n\t" + "fninit" + : "=m" (*&fdiv_bug) + : "m" (*&x), "m" (*&y)); + + kernel_fpu_end(); + + write_cr0(cr0_saved); + + if (fdiv_bug) { + set_cpu_bug(&boot_cpu_data, X86_BUG_FDIV); + pr_warn("Hmm, FPU with FDIV bug\n"); + } +} + +void __init fpu__init_check_bugs(void) +{ + /* + * kernel_fpu_begin/end() in check_fpu() relies on the patched + * alternative instructions. + */ + if (cpu_has_fpu) + check_fpu(); +} diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c new file mode 100644 index 000000000000..79de954626fd --- /dev/null +++ b/arch/x86/kernel/fpu/core.c @@ -0,0 +1,523 @@ +/* + * Copyright (C) 1994 Linus Torvalds + * + * Pentium III FXSR, SSE support + * General FPU state handling cleanups + * Gareth Hughes <gareth@valinux.com>, May 2000 + */ +#include <asm/fpu/internal.h> +#include <asm/fpu/regset.h> +#include <asm/fpu/signal.h> +#include <asm/traps.h> + +#include <linux/hardirq.h> + +/* + * Represents the initial FPU state. It's mostly (but not completely) zeroes, + * depending on the FPU hardware format: + */ +union fpregs_state init_fpstate __read_mostly; + +/* + * Track whether the kernel is using the FPU state + * currently. + * + * This flag is used: + * + * - by IRQ context code to potentially use the FPU + * if it's unused. + * + * - to debug kernel_fpu_begin()/end() correctness + */ +static DEFINE_PER_CPU(bool, in_kernel_fpu); + +/* + * Track which context is using the FPU on the CPU: + */ +DEFINE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx); + +static void kernel_fpu_disable(void) +{ + WARN_ON_FPU(this_cpu_read(in_kernel_fpu)); + this_cpu_write(in_kernel_fpu, true); +} + +static void kernel_fpu_enable(void) +{ + WARN_ON_FPU(!this_cpu_read(in_kernel_fpu)); + this_cpu_write(in_kernel_fpu, false); +} + +static bool kernel_fpu_disabled(void) +{ + return this_cpu_read(in_kernel_fpu); +} + +/* + * Were we in an interrupt that interrupted kernel mode? + * + * On others, we can do a kernel_fpu_begin/end() pair *ONLY* if that + * pair does nothing at all: the thread must not have fpu (so + * that we don't try to save the FPU state), and TS must + * be set (so that the clts/stts pair does nothing that is + * visible in the interrupted kernel thread). + * + * Except for the eagerfpu case when we return true; in the likely case + * the thread has FPU but we are not going to set/clear TS. + */ +static bool interrupted_kernel_fpu_idle(void) +{ + if (kernel_fpu_disabled()) + return false; + + if (use_eager_fpu()) + return true; + + return !current->thread.fpu.fpregs_active && (read_cr0() & X86_CR0_TS); +} + +/* + * Were we in user mode (or vm86 mode) when we were + * interrupted? + * + * Doing kernel_fpu_begin/end() is ok if we are running + * in an interrupt context from user mode - we'll just + * save the FPU state as required. + */ +static bool interrupted_user_mode(void) +{ + struct pt_regs *regs = get_irq_regs(); + return regs && user_mode(regs); +} + +/* + * Can we use the FPU in kernel mode with the + * whole "kernel_fpu_begin/end()" sequence? + * + * It's always ok in process context (ie "not interrupt") + * but it is sometimes ok even from an irq. + */ +bool irq_fpu_usable(void) +{ + return !in_interrupt() || + interrupted_user_mode() || + interrupted_kernel_fpu_idle(); +} +EXPORT_SYMBOL(irq_fpu_usable); + +void __kernel_fpu_begin(void) +{ + struct fpu *fpu = ¤t->thread.fpu; + + WARN_ON_FPU(!irq_fpu_usable()); + + kernel_fpu_disable(); + + if (fpu->fpregs_active) { + copy_fpregs_to_fpstate(fpu); + } else { + this_cpu_write(fpu_fpregs_owner_ctx, NULL); + __fpregs_activate_hw(); + } +} +EXPORT_SYMBOL(__kernel_fpu_begin); + +void __kernel_fpu_end(void) +{ + struct fpu *fpu = ¤t->thread.fpu; + + if (fpu->fpregs_active) + copy_kernel_to_fpregs(&fpu->state); + else + __fpregs_deactivate_hw(); + + kernel_fpu_enable(); +} +EXPORT_SYMBOL(__kernel_fpu_end); + +void kernel_fpu_begin(void) +{ + preempt_disable(); + __kernel_fpu_begin(); +} +EXPORT_SYMBOL_GPL(kernel_fpu_begin); + +void kernel_fpu_end(void) +{ + __kernel_fpu_end(); + preempt_enable(); +} +EXPORT_SYMBOL_GPL(kernel_fpu_end); + +/* + * CR0::TS save/restore functions: + */ +int irq_ts_save(void) +{ + /* + * If in process context and not atomic, we can take a spurious DNA fault. + * Otherwise, doing clts() in process context requires disabling preemption + * or some heavy lifting like kernel_fpu_begin() + */ + if (!in_atomic()) + return 0; + + if (read_cr0() & X86_CR0_TS) { + clts(); + return 1; + } + + return 0; +} +EXPORT_SYMBOL_GPL(irq_ts_save); + +void irq_ts_restore(int TS_state) +{ + if (TS_state) + stts(); +} +EXPORT_SYMBOL_GPL(irq_ts_restore); + +/* + * Save the FPU state (mark it for reload if necessary): + * + * This only ever gets called for the current task. + */ +void fpu__save(struct fpu *fpu) +{ + WARN_ON_FPU(fpu != ¤t->thread.fpu); + + preempt_disable(); + if (fpu->fpregs_active) { + if (!copy_fpregs_to_fpstate(fpu)) + fpregs_deactivate(fpu); + } + preempt_enable(); +} +EXPORT_SYMBOL_GPL(fpu__save); + +/* + * Legacy x87 fpstate state init: + */ +static inline void fpstate_init_fstate(struct fregs_state *fp) +{ + fp->cwd = 0xffff037fu; + fp->swd = 0xffff0000u; + fp->twd = 0xffffffffu; + fp->fos = 0xffff0000u; +} + +void fpstate_init(union fpregs_state *state) +{ + if (!cpu_has_fpu) { + fpstate_init_soft(&state->soft); + return; + } + + memset(state, 0, xstate_size); + + if (cpu_has_fxsr) + fpstate_init_fxstate(&state->fxsave); + else + fpstate_init_fstate(&state->fsave); +} +EXPORT_SYMBOL_GPL(fpstate_init); + +/* + * Copy the current task's FPU state to a new task's FPU context. + * + * In both the 'eager' and the 'lazy' case we save hardware registers + * directly to the destination buffer. + */ +static void fpu_copy(struct fpu *dst_fpu, struct fpu *src_fpu) +{ + WARN_ON_FPU(src_fpu != ¤t->thread.fpu); + + /* + * Don't let 'init optimized' areas of the XSAVE area + * leak into the child task: + */ + if (use_eager_fpu()) + memset(&dst_fpu->state.xsave, 0, xstate_size); + + /* + * Save current FPU registers directly into the child + * FPU context, without any memory-to-memory copying. + * + * If the FPU context got destroyed in the process (FNSAVE + * done on old CPUs) then copy it back into the source + * context and mark the current task for lazy restore. + * + * We have to do all this with preemption disabled, + * mostly because of the FNSAVE case, because in that + * case we must not allow preemption in the window + * between the FNSAVE and us marking the context lazy. + * + * It shouldn't be an issue as even FNSAVE is plenty + * fast in terms of critical section length. + */ + preempt_disable(); + if (!copy_fpregs_to_fpstate(dst_fpu)) { + memcpy(&src_fpu->state, &dst_fpu->state, xstate_size); + fpregs_deactivate(src_fpu); + } + preempt_enable(); +} + +int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu) +{ + dst_fpu->counter = 0; + dst_fpu->fpregs_active = 0; + dst_fpu->last_cpu = -1; + + if (src_fpu->fpstate_active) + fpu_copy(dst_fpu, src_fpu); + + return 0; +} + +/* + * Activate the current task's in-memory FPU context, + * if it has not been used before: + */ +void fpu__activate_curr(struct fpu *fpu) +{ + WARN_ON_FPU(fpu != ¤t->thread.fpu); + + if (!fpu->fpstate_active) { + fpstate_init(&fpu->state); + + /* Safe to do for the current task: */ + fpu->fpstate_active = 1; + } +} +EXPORT_SYMBOL_GPL(fpu__activate_curr); + +/* + * This function must be called before we read a task's fpstate. + * + * If the task has not used the FPU before then initialize its + * fpstate. + * + * If the task has used the FPU before then save it. + */ +void fpu__activate_fpstate_read(struct fpu *fpu) +{ + /* + * If fpregs are active (in the current CPU), then + * copy them to the fpstate: + */ + if (fpu->fpregs_active) { + fpu__save(fpu); + } else { + if (!fpu->fpstate_active) { + fpstate_init(&fpu->state); + + /* Safe to do for current and for stopped child tasks: */ + fpu->fpstate_active = 1; + } + } +} + +/* + * This function must be called before we write a task's fpstate. + * + * If the task has used the FPU before then unlazy it. + * If the task has not used the FPU before then initialize its fpstate. + * + * After this function call, after registers in the fpstate are + * modified and the child task has woken up, the child task will + * restore the modified FPU state from the modified context. If we + * didn't clear its lazy status here then the lazy in-registers + * state pending on its former CPU could be restored, corrupting + * the modifications. + */ +void fpu__activate_fpstate_write(struct fpu *fpu) +{ + /* + * Only stopped child tasks can be used to modify the FPU + * state in the fpstate buffer: + */ + WARN_ON_FPU(fpu == ¤t->thread.fpu); + + if (fpu->fpstate_active) { + /* Invalidate any lazy state: */ + fpu->last_cpu = -1; + } else { + fpstate_init(&fpu->state); + + /* Safe to do for stopped child tasks: */ + fpu->fpstate_active = 1; + } +} + +/* + * 'fpu__restore()' is called to copy FPU registers from + * the FPU fpstate to the live hw registers and to activate + * access to the hardware registers, so that FPU instructions + * can be used afterwards. + * + * Must be called with kernel preemption disabled (for example + * with local interrupts disabled, as it is in the case of + * do_device_not_available()). + */ +void fpu__restore(struct fpu *fpu) +{ + fpu__activate_curr(fpu); + + /* Avoid __kernel_fpu_begin() right after fpregs_activate() */ + kernel_fpu_disable(); + fpregs_activate(fpu); + copy_kernel_to_fpregs(&fpu->state); + fpu->counter++; + kernel_fpu_enable(); +} +EXPORT_SYMBOL_GPL(fpu__restore); + +/* + * Drops current FPU state: deactivates the fpregs and + * the fpstate. NOTE: it still leaves previous contents + * in the fpregs in the eager-FPU case. + * + * This function can be used in cases where we know that + * a state-restore is coming: either an explicit one, + * or a reschedule. + */ +void fpu__drop(struct fpu *fpu) +{ + preempt_disable(); + fpu->counter = 0; + + if (fpu->fpregs_active) { + /* Ignore delayed exceptions from user space */ + asm volatile("1: fwait\n" + "2:\n" + _ASM_EXTABLE(1b, 2b)); + fpregs_deactivate(fpu); + } + + fpu->fpstate_active = 0; + + preempt_enable(); +} + +/* + * Clear FPU registers by setting them up from + * the init fpstate: + */ +static inline void copy_init_fpstate_to_fpregs(void) +{ + if (use_xsave()) + copy_kernel_to_xregs(&init_fpstate.xsave, -1); + else + copy_kernel_to_fxregs(&init_fpstate.fxsave); +} + +/* + * Clear the FPU state back to init state. + * + * Called by sys_execve(), by the signal handler code and by various + * error paths. + */ +void fpu__clear(struct fpu *fpu) +{ + WARN_ON_FPU(fpu != ¤t->thread.fpu); /* Almost certainly an anomaly */ + + if (!use_eager_fpu()) { + /* FPU state will be reallocated lazily at the first use. */ + fpu__drop(fpu); + } else { + if (!fpu->fpstate_active) { + fpu__activate_curr(fpu); + user_fpu_begin(); + } + copy_init_fpstate_to_fpregs(); + } +} + +/* + * x87 math exception handling: + */ + +static inline unsigned short get_fpu_cwd(struct fpu *fpu) +{ + if (cpu_has_fxsr) { + return fpu->state.fxsave.cwd; + } else { + return (unsigned short)fpu->state.fsave.cwd; + } +} + +static inline unsigned short get_fpu_swd(struct fpu *fpu) +{ + if (cpu_has_fxsr) { + return fpu->state.fxsave.swd; + } else { + return (unsigned short)fpu->state.fsave.swd; + } +} + +static inline unsigned short get_fpu_mxcsr(struct fpu *fpu) +{ + if (cpu_has_xmm) { + return fpu->state.fxsave.mxcsr; + } else { + return MXCSR_DEFAULT; + } +} + +int fpu__exception_code(struct fpu *fpu, int trap_nr) +{ + int err; + + if (trap_nr == X86_TRAP_MF) { + unsigned short cwd, swd; + /* + * (~cwd & swd) will mask out exceptions that are not set to unmasked + * status. 0x3f is the exception bits in these regs, 0x200 is the + * C1 reg you need in case of a stack fault, 0x040 is the stack + * fault bit. We should only be taking one exception at a time, + * so if this combination doesn't produce any single exception, + * then we have a bad program that isn't synchronizing its FPU usage + * and it will suffer the consequences since we won't be able to + * fully reproduce the context of the exception + */ + cwd = get_fpu_cwd(fpu); + swd = get_fpu_swd(fpu); + + err = swd & ~cwd; + } else { + /* + * The SIMD FPU exceptions are handled a little differently, as there + * is only a single status/control register. Thus, to determine which + * unmasked exception was caught we must mask the exception mask bits + * at 0x1f80, and then use these to mask the exception bits at 0x3f. + */ + unsigned short mxcsr = get_fpu_mxcsr(fpu); + err = ~(mxcsr >> 7) & mxcsr; + } + + if (err & 0x001) { /* Invalid op */ + /* + * swd & 0x240 == 0x040: Stack Underflow + * swd & 0x240 == 0x240: Stack Overflow + * User must clear the SF bit (0x40) if set + */ + return FPE_FLTINV; + } else if (err & 0x004) { /* Divide by Zero */ + return FPE_FLTDIV; + } else if (err & 0x008) { /* Overflow */ + return FPE_FLTOVF; + } else if (err & 0x012) { /* Denormal, Underflow */ + return FPE_FLTUND; + } else if (err & 0x020) { /* Precision */ + return FPE_FLTRES; + } + + /* + * If we're using IRQ 13, or supposedly even some trap + * X86_TRAP_MF implementations, it's possible + * we get a spurious trap, which is not an error. + */ + return 0; +} diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c new file mode 100644 index 000000000000..fc878fee6a51 --- /dev/null +++ b/arch/x86/kernel/fpu/init.c @@ -0,0 +1,354 @@ +/* + * x86 FPU boot time init code: + */ +#include <asm/fpu/internal.h> +#include <asm/tlbflush.h> + +/* + * Initialize the TS bit in CR0 according to the style of context-switches + * we are using: + */ +static void fpu__init_cpu_ctx_switch(void) +{ + if (!cpu_has_eager_fpu) + stts(); + else + clts(); +} + +/* + * Initialize the registers found in all CPUs, CR0 and CR4: + */ +static void fpu__init_cpu_generic(void) +{ + unsigned long cr0; + unsigned long cr4_mask = 0; + + if (cpu_has_fxsr) + cr4_mask |= X86_CR4_OSFXSR; + if (cpu_has_xmm) + cr4_mask |= X86_CR4_OSXMMEXCPT; + if (cr4_mask) + cr4_set_bits(cr4_mask); + + cr0 = read_cr0(); + cr0 &= ~(X86_CR0_TS|X86_CR0_EM); /* clear TS and EM */ + if (!cpu_has_fpu) + cr0 |= X86_CR0_EM; + write_cr0(cr0); + + /* Flush out any pending x87 state: */ + asm volatile ("fninit"); +} + +/* + * Enable all supported FPU features. Called when a CPU is brought online: + */ +void fpu__init_cpu(void) +{ + fpu__init_cpu_generic(); + fpu__init_cpu_xstate(); + fpu__init_cpu_ctx_switch(); +} + +/* + * The earliest FPU detection code. + * + * Set the X86_FEATURE_FPU CPU-capability bit based on + * trying to execute an actual sequence of FPU instructions: + */ +static void fpu__init_system_early_generic(struct cpuinfo_x86 *c) +{ + unsigned long cr0; + u16 fsw, fcw; + + fsw = fcw = 0xffff; + + cr0 = read_cr0(); + cr0 &= ~(X86_CR0_TS | X86_CR0_EM); + write_cr0(cr0); + + asm volatile("fninit ; fnstsw %0 ; fnstcw %1" + : "+m" (fsw), "+m" (fcw)); + + if (fsw == 0 && (fcw & 0x103f) == 0x003f) + set_cpu_cap(c, X86_FEATURE_FPU); + else + clear_cpu_cap(c, X86_FEATURE_FPU); + +#ifndef CONFIG_MATH_EMULATION + if (!cpu_has_fpu) { + pr_emerg("x86/fpu: Giving up, no FPU found and no math emulation present\n"); + for (;;) + asm volatile("hlt"); + } +#endif +} + +/* + * Boot time FPU feature detection code: + */ +unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu; + +static void __init fpu__init_system_mxcsr(void) +{ + unsigned int mask = 0; + + if (cpu_has_fxsr) { + struct fxregs_state fx_tmp __aligned(32) = { }; + + asm volatile("fxsave %0" : "+m" (fx_tmp)); + + mask = fx_tmp.mxcsr_mask; + + /* + * If zero then use the default features mask, + * which has all features set, except the + * denormals-are-zero feature bit: + */ + if (mask == 0) + mask = 0x0000ffbf; + } + mxcsr_feature_mask &= mask; +} + +/* + * Once per bootup FPU initialization sequences that will run on most x86 CPUs: + */ +static void __init fpu__init_system_generic(void) +{ + /* + * Set up the legacy init FPU context. (xstate init might overwrite this + * with a more modern format, if the CPU supports it.) + */ + fpstate_init_fxstate(&init_fpstate.fxsave); + + fpu__init_system_mxcsr(); +} + +/* + * Size of the FPU context state. All tasks in the system use the + * same context size, regardless of what portion they use. + * This is inherent to the XSAVE architecture which puts all state + * components into a single, continuous memory block: + */ +unsigned int xstate_size; +EXPORT_SYMBOL_GPL(xstate_size); + +/* + * Set up the xstate_size based on the legacy FPU context size. + * + * We set this up first, and later it will be overwritten by + * fpu__init_system_xstate() if the CPU knows about xstates. + */ +static void __init fpu__init_system_xstate_size_legacy(void) +{ + static int on_boot_cpu = 1; + + WARN_ON_FPU(!on_boot_cpu); + on_boot_cpu = 0; + + /* + * Note that xstate_size might be overwriten later during + * fpu__init_system_xstate(). + */ + + if (!cpu_has_fpu) { + /* + * Disable xsave as we do not support it if i387 + * emulation is enabled. + */ + setup_clear_cpu_cap(X86_FEATURE_XSAVE); + setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); + xstate_size = sizeof(struct swregs_state); + } else { + if (cpu_has_fxsr) + xstate_size = sizeof(struct fxregs_state); + else + xstate_size = sizeof(struct fregs_state); + } + /* + * Quirk: we don't yet handle the XSAVES* instructions + * correctly, as we don't correctly convert between + * standard and compacted format when interfacing + * with user-space - so disable it for now. + * + * The difference is small: with recent CPUs the + * compacted format is only marginally smaller than + * the standard FPU state format. + * + * ( This is easy to backport while we are fixing + * XSAVES* support. ) + */ + setup_clear_cpu_cap(X86_FEATURE_XSAVES); +} + +/* + * FPU context switching strategies: + * + * Against popular belief, we don't do lazy FPU saves, due to the + * task migration complications it brings on SMP - we only do + * lazy FPU restores. + * + * 'lazy' is the traditional strategy, which is based on setting + * CR0::TS to 1 during context-switch (instead of doing a full + * restore of the FPU state), which causes the first FPU instruction + * after the context switch (whenever it is executed) to fault - at + * which point we lazily restore the FPU state into FPU registers. + * + * Tasks are of course under no obligation to execute FPU instructions, + * so it can easily happen that another context-switch occurs without + * a single FPU instruction being executed. If we eventually switch + * back to the original task (that still owns the FPU) then we have + * not only saved the restores along the way, but we also have the + * FPU ready to be used for the original task. + * + * 'eager' switching is used on modern CPUs, there we switch the FPU + * state during every context switch, regardless of whether the task + * has used FPU instructions in that time slice or not. This is done + * because modern FPU context saving instructions are able to optimize + * state saving and restoration in hardware: they can detect both + * unused and untouched FPU state and optimize accordingly. + * + * [ Note that even in 'lazy' mode we might optimize context switches + * to use 'eager' restores, if we detect that a task is using the FPU + * frequently. See the fpu->counter logic in fpu/internal.h for that. ] + */ +static enum { AUTO, ENABLE, DISABLE } eagerfpu = AUTO; + +static int __init eager_fpu_setup(char *s) +{ + if (!strcmp(s, "on")) + eagerfpu = ENABLE; + else if (!strcmp(s, "off")) + eagerfpu = DISABLE; + else if (!strcmp(s, "auto")) + eagerfpu = AUTO; + return 1; +} +__setup("eagerfpu=", eager_fpu_setup); + +/* + * Pick the FPU context switching strategy: + */ +static void __init fpu__init_system_ctx_switch(void) +{ + static bool on_boot_cpu = 1; + + WARN_ON_FPU(!on_boot_cpu); + on_boot_cpu = 0; + + WARN_ON_FPU(current->thread.fpu.fpstate_active); + current_thread_info()->status = 0; + + /* Auto enable eagerfpu for xsaveopt */ + if (cpu_has_xsaveopt && eagerfpu != DISABLE) + eagerfpu = ENABLE; + + if (xfeatures_mask & XSTATE_EAGER) { + if (eagerfpu == DISABLE) { + pr_err("x86/fpu: eagerfpu switching disabled, disabling the following xstate features: 0x%llx.\n", + xfeatures_mask & XSTATE_EAGER); + xfeatures_mask &= ~XSTATE_EAGER; + } else { + eagerfpu = ENABLE; + } + } + + if (eagerfpu == ENABLE) + setup_force_cpu_cap(X86_FEATURE_EAGER_FPU); + + printk(KERN_INFO "x86/fpu: Using '%s' FPU context switches.\n", eagerfpu == ENABLE ? "eager" : "lazy"); +} + +/* + * Called on the boot CPU once per system bootup, to set up the initial + * FPU state that is later cloned into all processes: + */ +void __init fpu__init_system(struct cpuinfo_x86 *c) +{ + fpu__init_system_early_generic(c); + + /* + * The FPU has to be operational for some of the + * later FPU init activities: + */ + fpu__init_cpu(); + + /* + * But don't leave CR0::TS set yet, as some of the FPU setup + * methods depend on being able to execute FPU instructions + * that will fault on a set TS, such as the FXSAVE in + * fpu__init_system_mxcsr(). + */ + clts(); + + fpu__init_system_generic(); + fpu__init_system_xstate_size_legacy(); + fpu__init_system_xstate(); + + fpu__init_system_ctx_switch(); +} + +/* + * Boot parameter to turn off FPU support and fall back to math-emu: + */ +static int __init no_387(char *s) +{ + setup_clear_cpu_cap(X86_FEATURE_FPU); + return 1; +} +__setup("no387", no_387); + +/* + * Disable all xstate CPU features: + */ +static int __init x86_noxsave_setup(char *s) +{ + if (strlen(s)) + return 0; + + setup_clear_cpu_cap(X86_FEATURE_XSAVE); + setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); + setup_clear_cpu_cap(X86_FEATURE_XSAVES); + setup_clear_cpu_cap(X86_FEATURE_AVX); + setup_clear_cpu_cap(X86_FEATURE_AVX2); + + return 1; +} +__setup("noxsave", x86_noxsave_setup); + +/* + * Disable the XSAVEOPT instruction specifically: + */ +static int __init x86_noxsaveopt_setup(char *s) +{ + setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); + + return 1; +} +__setup("noxsaveopt", x86_noxsaveopt_setup); + +/* + * Disable the XSAVES instruction: + */ +static int __init x86_noxsaves_setup(char *s) +{ + setup_clear_cpu_cap(X86_FEATURE_XSAVES); + + return 1; +} +__setup("noxsaves", x86_noxsaves_setup); + +/* + * Disable FX save/restore and SSE support: + */ +static int __init x86_nofxsr_setup(char *s) +{ + setup_clear_cpu_cap(X86_FEATURE_FXSR); + setup_clear_cpu_cap(X86_FEATURE_FXSR_OPT); + setup_clear_cpu_cap(X86_FEATURE_XMM); + + return 1; +} +__setup("nofxsr", x86_nofxsr_setup); diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c new file mode 100644 index 000000000000..dc60810c1c74 --- /dev/null +++ b/arch/x86/kernel/fpu/regset.c @@ -0,0 +1,356 @@ +/* + * FPU register's regset abstraction, for ptrace, core dumps, etc. + */ +#include <asm/fpu/internal.h> +#include <asm/fpu/signal.h> +#include <asm/fpu/regset.h> + +/* + * The xstateregs_active() routine is the same as the regset_fpregs_active() routine, + * as the "regset->n" for the xstate regset will be updated based on the feature + * capabilites supported by the xsave. + */ +int regset_fpregs_active(struct task_struct *target, const struct user_regset *regset) +{ + struct fpu *target_fpu = &target->thread.fpu; + + return target_fpu->fpstate_active ? regset->n : 0; +} + +int regset_xregset_fpregs_active(struct task_struct *target, const struct user_regset *regset) +{ + struct fpu *target_fpu = &target->thread.fpu; + + return (cpu_has_fxsr && target_fpu->fpstate_active) ? regset->n : 0; +} + +int xfpregs_get(struct task_struct *target, const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + struct fpu *fpu = &target->thread.fpu; + + if (!cpu_has_fxsr) + return -ENODEV; + + fpu__activate_fpstate_read(fpu); + fpstate_sanitize_xstate(fpu); + + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &fpu->state.fxsave, 0, -1); +} + +int xfpregs_set(struct task_struct *target, const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + struct fpu *fpu = &target->thread.fpu; + int ret; + + if (!cpu_has_fxsr) + return -ENODEV; + + fpu__activate_fpstate_write(fpu); + fpstate_sanitize_xstate(fpu); + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &fpu->state.fxsave, 0, -1); + + /* + * mxcsr reserved bits must be masked to zero for security reasons. + */ + fpu->state.fxsave.mxcsr &= mxcsr_feature_mask; + + /* + * update the header bits in the xsave header, indicating the + * presence of FP and SSE state. + */ + if (cpu_has_xsave) + fpu->state.xsave.header.xfeatures |= XSTATE_FPSSE; + + return ret; +} + +int xstateregs_get(struct task_struct *target, const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + struct fpu *fpu = &target->thread.fpu; + struct xregs_state *xsave; + int ret; + + if (!cpu_has_xsave) + return -ENODEV; + + fpu__activate_fpstate_read(fpu); + + xsave = &fpu->state.xsave; + + /* + * Copy the 48bytes defined by the software first into the xstate + * memory layout in the thread struct, so that we can copy the entire + * xstateregs to the user using one user_regset_copyout(). + */ + memcpy(&xsave->i387.sw_reserved, + xstate_fx_sw_bytes, sizeof(xstate_fx_sw_bytes)); + /* + * Copy the xstate memory layout. + */ + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, xsave, 0, -1); + return ret; +} + +int xstateregs_set(struct task_struct *target, const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + struct fpu *fpu = &target->thread.fpu; + struct xregs_state *xsave; + int ret; + + if (!cpu_has_xsave) + return -ENODEV; + + fpu__activate_fpstate_write(fpu); + + xsave = &fpu->state.xsave; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, xsave, 0, -1); + /* + * mxcsr reserved bits must be masked to zero for security reasons. + */ + xsave->i387.mxcsr &= mxcsr_feature_mask; + xsave->header.xfeatures &= xfeatures_mask; + /* + * These bits must be zero. + */ + memset(&xsave->header.reserved, 0, 48); + + return ret; +} + +#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION + +/* + * FPU tag word conversions. + */ + +static inline unsigned short twd_i387_to_fxsr(unsigned short twd) +{ + unsigned int tmp; /* to avoid 16 bit prefixes in the code */ + + /* Transform each pair of bits into 01 (valid) or 00 (empty) */ + tmp = ~twd; + tmp = (tmp | (tmp>>1)) & 0x5555; /* 0V0V0V0V0V0V0V0V */ + /* and move the valid bits to the lower byte. */ + tmp = (tmp | (tmp >> 1)) & 0x3333; /* 00VV00VV00VV00VV */ + tmp = (tmp | (tmp >> 2)) & 0x0f0f; /* 0000VVVV0000VVVV */ + tmp = (tmp | (tmp >> 4)) & 0x00ff; /* 00000000VVVVVVVV */ + + return tmp; +} + +#define FPREG_ADDR(f, n) ((void *)&(f)->st_space + (n) * 16) +#define FP_EXP_TAG_VALID 0 +#define FP_EXP_TAG_ZERO 1 +#define FP_EXP_TAG_SPECIAL 2 +#define FP_EXP_TAG_EMPTY 3 + +static inline u32 twd_fxsr_to_i387(struct fxregs_state *fxsave) +{ + struct _fpxreg *st; + u32 tos = (fxsave->swd >> 11) & 7; + u32 twd = (unsigned long) fxsave->twd; + u32 tag; + u32 ret = 0xffff0000u; + int i; + + for (i = 0; i < 8; i++, twd >>= 1) { + if (twd & 0x1) { + st = FPREG_ADDR(fxsave, (i - tos) & 7); + + switch (st->exponent & 0x7fff) { + case 0x7fff: + tag = FP_EXP_TAG_SPECIAL; + break; + case 0x0000: + if (!st->significand[0] && + !st->significand[1] && + !st->significand[2] && + !st->significand[3]) + tag = FP_EXP_TAG_ZERO; + else + tag = FP_EXP_TAG_SPECIAL; + break; + default: + if (st->significand[3] & 0x8000) + tag = FP_EXP_TAG_VALID; + else + tag = FP_EXP_TAG_SPECIAL; + break; + } + } else { + tag = FP_EXP_TAG_EMPTY; + } + ret |= tag << (2 * i); + } + return ret; +} + +/* + * FXSR floating point environment conversions. + */ + +void +convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk) +{ + struct fxregs_state *fxsave = &tsk->thread.fpu.state.fxsave; + struct _fpreg *to = (struct _fpreg *) &env->st_space[0]; + struct _fpxreg *from = (struct _fpxreg *) &fxsave->st_space[0]; + int i; + + env->cwd = fxsave->cwd | 0xffff0000u; + env->swd = fxsave->swd | 0xffff0000u; + env->twd = twd_fxsr_to_i387(fxsave); + +#ifdef CONFIG_X86_64 + env->fip = fxsave->rip; + env->foo = fxsave->rdp; + /* + * should be actually ds/cs at fpu exception time, but + * that information is not available in 64bit mode. + */ + env->fcs = task_pt_regs(tsk)->cs; + if (tsk == current) { + savesegment(ds, env->fos); + } else { + env->fos = tsk->thread.ds; + } + env->fos |= 0xffff0000; +#else + env->fip = fxsave->fip; + env->fcs = (u16) fxsave->fcs | ((u32) fxsave->fop << 16); + env->foo = fxsave->foo; + env->fos = fxsave->fos; +#endif + + for (i = 0; i < 8; ++i) + memcpy(&to[i], &from[i], sizeof(to[0])); +} + +void convert_to_fxsr(struct task_struct *tsk, + const struct user_i387_ia32_struct *env) + +{ + struct fxregs_state *fxsave = &tsk->thread.fpu.state.fxsave; + struct _fpreg *from = (struct _fpreg *) &env->st_space[0]; + struct _fpxreg *to = (struct _fpxreg *) &fxsave->st_space[0]; + int i; + + fxsave->cwd = env->cwd; + fxsave->swd = env->swd; + fxsave->twd = twd_i387_to_fxsr(env->twd); + fxsave->fop = (u16) ((u32) env->fcs >> 16); +#ifdef CONFIG_X86_64 + fxsave->rip = env->fip; + fxsave->rdp = env->foo; + /* cs and ds ignored */ +#else + fxsave->fip = env->fip; + fxsave->fcs = (env->fcs & 0xffff); + fxsave->foo = env->foo; + fxsave->fos = env->fos; +#endif + + for (i = 0; i < 8; ++i) + memcpy(&to[i], &from[i], sizeof(from[0])); +} + +int fpregs_get(struct task_struct *target, const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + struct fpu *fpu = &target->thread.fpu; + struct user_i387_ia32_struct env; + + fpu__activate_fpstate_read(fpu); + + if (!static_cpu_has(X86_FEATURE_FPU)) + return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf); + + if (!cpu_has_fxsr) + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &fpu->state.fsave, 0, + -1); + + fpstate_sanitize_xstate(fpu); + + if (kbuf && pos == 0 && count == sizeof(env)) { + convert_from_fxsr(kbuf, target); + return 0; + } + + convert_from_fxsr(&env, target); + + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &env, 0, -1); +} + +int fpregs_set(struct task_struct *target, const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + struct fpu *fpu = &target->thread.fpu; + struct user_i387_ia32_struct env; + int ret; + + fpu__activate_fpstate_write(fpu); + fpstate_sanitize_xstate(fpu); + + if (!static_cpu_has(X86_FEATURE_FPU)) + return fpregs_soft_set(target, regset, pos, count, kbuf, ubuf); + + if (!cpu_has_fxsr) + return user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &fpu->state.fsave, 0, + -1); + + if (pos > 0 || count < sizeof(env)) + convert_from_fxsr(&env, target); + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &env, 0, -1); + if (!ret) + convert_to_fxsr(target, &env); + + /* + * update the header bit in the xsave header, indicating the + * presence of FP. + */ + if (cpu_has_xsave) + fpu->state.xsave.header.xfeatures |= XSTATE_FP; + return ret; +} + +/* + * FPU state for core dumps. + * This is only used for a.out dumps now. + * It is declared generically using elf_fpregset_t (which is + * struct user_i387_struct) but is in fact only used for 32-bit + * dumps, so on 64-bit it is really struct user_i387_ia32_struct. + */ +int dump_fpu(struct pt_regs *regs, struct user_i387_struct *ufpu) +{ + struct task_struct *tsk = current; + struct fpu *fpu = &tsk->thread.fpu; + int fpvalid; + + fpvalid = fpu->fpstate_active; + if (fpvalid) + fpvalid = !fpregs_get(tsk, NULL, + 0, sizeof(struct user_i387_ia32_struct), + ufpu, NULL); + + return fpvalid; +} +EXPORT_SYMBOL(dump_fpu); + +#endif /* CONFIG_X86_32 || CONFIG_IA32_EMULATION */ diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c new file mode 100644 index 000000000000..50ec9af1bd51 --- /dev/null +++ b/arch/x86/kernel/fpu/signal.c @@ -0,0 +1,404 @@ +/* + * FPU signal frame handling routines. + */ + +#include <linux/compat.h> +#include <linux/cpu.h> + +#include <asm/fpu/internal.h> +#include <asm/fpu/signal.h> +#include <asm/fpu/regset.h> + +#include <asm/sigframe.h> + +static struct _fpx_sw_bytes fx_sw_reserved, fx_sw_reserved_ia32; + +/* + * Check for the presence of extended state information in the + * user fpstate pointer in the sigcontext. + */ +static inline int check_for_xstate(struct fxregs_state __user *buf, + void __user *fpstate, + struct _fpx_sw_bytes *fx_sw) +{ + int min_xstate_size = sizeof(struct fxregs_state) + + sizeof(struct xstate_header); + unsigned int magic2; + + if (__copy_from_user(fx_sw, &buf->sw_reserved[0], sizeof(*fx_sw))) + return -1; + + /* Check for the first magic field and other error scenarios. */ + if (fx_sw->magic1 != FP_XSTATE_MAGIC1 || + fx_sw->xstate_size < min_xstate_size || + fx_sw->xstate_size > xstate_size || + fx_sw->xstate_size > fx_sw->extended_size) + return -1; + + /* + * Check for the presence of second magic word at the end of memory + * layout. This detects the case where the user just copied the legacy + * fpstate layout with out copying the extended state information + * in the memory layout. + */ + if (__get_user(magic2, (__u32 __user *)(fpstate + fx_sw->xstate_size)) + || magic2 != FP_XSTATE_MAGIC2) + return -1; + + return 0; +} + +/* + * Signal frame handlers. + */ +static inline int save_fsave_header(struct task_struct *tsk, void __user *buf) +{ + if (use_fxsr()) { + struct xregs_state *xsave = &tsk->thread.fpu.state.xsave; + struct user_i387_ia32_struct env; + struct _fpstate_ia32 __user *fp = buf; + + convert_from_fxsr(&env, tsk); + + if (__copy_to_user(buf, &env, sizeof(env)) || + __put_user(xsave->i387.swd, &fp->status) || + __put_user(X86_FXSR_MAGIC, &fp->magic)) + return -1; + } else { + struct fregs_state __user *fp = buf; + u32 swd; + if (__get_user(swd, &fp->swd) || __put_user(swd, &fp->status)) + return -1; + } + + return 0; +} + +static inline int save_xstate_epilog(void __user *buf, int ia32_frame) +{ + struct xregs_state __user *x = buf; + struct _fpx_sw_bytes *sw_bytes; + u32 xfeatures; + int err; + + /* Setup the bytes not touched by the [f]xsave and reserved for SW. */ + sw_bytes = ia32_frame ? &fx_sw_reserved_ia32 : &fx_sw_reserved; + err = __copy_to_user(&x->i387.sw_reserved, sw_bytes, sizeof(*sw_bytes)); + + if (!use_xsave()) + return err; + + err |= __put_user(FP_XSTATE_MAGIC2, (__u32 *)(buf + xstate_size)); + + /* + * Read the xfeatures which we copied (directly from the cpu or + * from the state in task struct) to the user buffers. + */ + err |= __get_user(xfeatures, (__u32 *)&x->header.xfeatures); + + /* + * For legacy compatible, we always set FP/SSE bits in the bit + * vector while saving the state to the user context. This will + * enable us capturing any changes(during sigreturn) to + * the FP/SSE bits by the legacy applications which don't touch + * xfeatures in the xsave header. + * + * xsave aware apps can change the xfeatures in the xsave + * header as well as change any contents in the memory layout. + * xrestore as part of sigreturn will capture all the changes. + */ + xfeatures |= XSTATE_FPSSE; + + err |= __put_user(xfeatures, (__u32 *)&x->header.xfeatures); + + return err; +} + +static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf) +{ + int err; + + if (use_xsave()) + err = copy_xregs_to_user(buf); + else if (use_fxsr()) + err = copy_fxregs_to_user((struct fxregs_state __user *) buf); + else + err = copy_fregs_to_user((struct fregs_state __user *) buf); + + if (unlikely(err) && __clear_user(buf, xstate_size)) + err = -EFAULT; + return err; +} + +/* + * Save the fpu, extended register state to the user signal frame. + * + * 'buf_fx' is the 64-byte aligned pointer at which the [f|fx|x]save + * state is copied. + * 'buf' points to the 'buf_fx' or to the fsave header followed by 'buf_fx'. + * + * buf == buf_fx for 64-bit frames and 32-bit fsave frame. + * buf != buf_fx for 32-bit frames with fxstate. + * + * If the fpu, extended register state is live, save the state directly + * to the user frame pointed by the aligned pointer 'buf_fx'. Otherwise, + * copy the thread's fpu state to the user frame starting at 'buf_fx'. + * + * If this is a 32-bit frame with fxstate, put a fsave header before + * the aligned state at 'buf_fx'. + * + * For [f]xsave state, update the SW reserved fields in the [f]xsave frame + * indicating the absence/presence of the extended state to the user. + */ +int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size) +{ + struct xregs_state *xsave = ¤t->thread.fpu.state.xsave; + struct task_struct *tsk = current; + int ia32_fxstate = (buf != buf_fx); + + ia32_fxstate &= (config_enabled(CONFIG_X86_32) || + config_enabled(CONFIG_IA32_EMULATION)); + + if (!access_ok(VERIFY_WRITE, buf, size)) + return -EACCES; + + if (!static_cpu_has(X86_FEATURE_FPU)) + return fpregs_soft_get(current, NULL, 0, + sizeof(struct user_i387_ia32_struct), NULL, + (struct _fpstate_ia32 __user *) buf) ? -1 : 1; + + if (fpregs_active()) { + /* Save the live register state to the user directly. */ + if (copy_fpregs_to_sigframe(buf_fx)) + return -1; + /* Update the thread's fxstate to save the fsave header. */ + if (ia32_fxstate) + copy_fxregs_to_kernel(&tsk->thread.fpu); + } else { + fpstate_sanitize_xstate(&tsk->thread.fpu); + if (__copy_to_user(buf_fx, xsave, xstate_size)) + return -1; + } + + /* Save the fsave header for the 32-bit frames. */ + if ((ia32_fxstate || !use_fxsr()) && save_fsave_header(tsk, buf)) + return -1; + + if (use_fxsr() && save_xstate_epilog(buf_fx, ia32_fxstate)) + return -1; + + return 0; +} + +static inline void +sanitize_restored_xstate(struct task_struct *tsk, + struct user_i387_ia32_struct *ia32_env, + u64 xfeatures, int fx_only) +{ + struct xregs_state *xsave = &tsk->thread.fpu.state.xsave; + struct xstate_header *header = &xsave->header; + + if (use_xsave()) { + /* These bits must be zero. */ + memset(header->reserved, 0, 48); + + /* + * Init the state that is not present in the memory + * layout and not enabled by the OS. + */ + if (fx_only) + header->xfeatures = XSTATE_FPSSE; + else + header->xfeatures &= (xfeatures_mask & xfeatures); + } + + if (use_fxsr()) { + /* + * mscsr reserved bits must be masked to zero for security + * reasons. + */ + xsave->i387.mxcsr &= mxcsr_feature_mask; + + convert_to_fxsr(tsk, ia32_env); + } +} + +/* + * Restore the extended state if present. Otherwise, restore the FP/SSE state. + */ +static inline int copy_user_to_fpregs_zeroing(void __user *buf, u64 xbv, int fx_only) +{ + if (use_xsave()) { + if ((unsigned long)buf % 64 || fx_only) { + u64 init_bv = xfeatures_mask & ~XSTATE_FPSSE; + copy_kernel_to_xregs(&init_fpstate.xsave, init_bv); + return copy_user_to_fxregs(buf); + } else { + u64 init_bv = xfeatures_mask & ~xbv; + if (unlikely(init_bv)) + copy_kernel_to_xregs(&init_fpstate.xsave, init_bv); + return copy_user_to_xregs(buf, xbv); + } + } else if (use_fxsr()) { + return copy_user_to_fxregs(buf); + } else + return copy_user_to_fregs(buf); +} + +static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) +{ + int ia32_fxstate = (buf != buf_fx); + struct task_struct *tsk = current; + struct fpu *fpu = &tsk->thread.fpu; + int state_size = xstate_size; + u64 xfeatures = 0; + int fx_only = 0; + + ia32_fxstate &= (config_enabled(CONFIG_X86_32) || + config_enabled(CONFIG_IA32_EMULATION)); + + if (!buf) { + fpu__clear(fpu); + return 0; + } + + if (!access_ok(VERIFY_READ, buf, size)) + return -EACCES; + + fpu__activate_curr(fpu); + + if (!static_cpu_has(X86_FEATURE_FPU)) + return fpregs_soft_set(current, NULL, + 0, sizeof(struct user_i387_ia32_struct), + NULL, buf) != 0; + + if (use_xsave()) { + struct _fpx_sw_bytes fx_sw_user; + if (unlikely(check_for_xstate(buf_fx, buf_fx, &fx_sw_user))) { + /* + * Couldn't find the extended state information in the + * memory layout. Restore just the FP/SSE and init all + * the other extended state. + */ + state_size = sizeof(struct fxregs_state); + fx_only = 1; + } else { + state_size = fx_sw_user.xstate_size; + xfeatures = fx_sw_user.xfeatures; + } + } + + if (ia32_fxstate) { + /* + * For 32-bit frames with fxstate, copy the user state to the + * thread's fpu state, reconstruct fxstate from the fsave + * header. Sanitize the copied state etc. + */ + struct fpu *fpu = &tsk->thread.fpu; + struct user_i387_ia32_struct env; + int err = 0; + + /* + * Drop the current fpu which clears fpu->fpstate_active. This ensures + * that any context-switch during the copy of the new state, + * avoids the intermediate state from getting restored/saved. + * Thus avoiding the new restored state from getting corrupted. + * We will be ready to restore/save the state only after + * fpu->fpstate_active is again set. + */ + fpu__drop(fpu); + + if (__copy_from_user(&fpu->state.xsave, buf_fx, state_size) || + __copy_from_user(&env, buf, sizeof(env))) { + fpstate_init(&fpu->state); + err = -1; + } else { + sanitize_restored_xstate(tsk, &env, xfeatures, fx_only); + } + + fpu->fpstate_active = 1; + if (use_eager_fpu()) { + preempt_disable(); + fpu__restore(fpu); + preempt_enable(); + } + + return err; + } else { + /* + * For 64-bit frames and 32-bit fsave frames, restore the user + * state to the registers directly (with exceptions handled). + */ + user_fpu_begin(); + if (copy_user_to_fpregs_zeroing(buf_fx, xfeatures, fx_only)) { + fpu__clear(fpu); + return -1; + } + } + + return 0; +} + +static inline int xstate_sigframe_size(void) +{ + return use_xsave() ? xstate_size + FP_XSTATE_MAGIC2_SIZE : xstate_size; +} + +/* + * Restore FPU state from a sigframe: + */ +int fpu__restore_sig(void __user *buf, int ia32_frame) +{ + void __user *buf_fx = buf; + int size = xstate_sigframe_size(); + + if (ia32_frame && use_fxsr()) { + buf_fx = buf + sizeof(struct fregs_state); + size += sizeof(struct fregs_state); + } + + return __fpu__restore_sig(buf, buf_fx, size); +} + +unsigned long +fpu__alloc_mathframe(unsigned long sp, int ia32_frame, + unsigned long *buf_fx, unsigned long *size) +{ + unsigned long frame_size = xstate_sigframe_size(); + + *buf_fx = sp = round_down(sp - frame_size, 64); + if (ia32_frame && use_fxsr()) { + frame_size += sizeof(struct fregs_state); + sp -= sizeof(struct fregs_state); + } + + *size = frame_size; + + return sp; +} +/* + * Prepare the SW reserved portion of the fxsave memory layout, indicating + * the presence of the extended state information in the memory layout + * pointed by the fpstate pointer in the sigcontext. + * This will be saved when ever the FP and extended state context is + * saved on the user stack during the signal handler delivery to the user. + */ +void fpu__init_prepare_fx_sw_frame(void) +{ + int fsave_header_size = sizeof(struct fregs_state); + int size = xstate_size + FP_XSTATE_MAGIC2_SIZE; + + if (config_enabled(CONFIG_X86_32)) + size += fsave_header_size; + + fx_sw_reserved.magic1 = FP_XSTATE_MAGIC1; + fx_sw_reserved.extended_size = size; + fx_sw_reserved.xfeatures = xfeatures_mask; + fx_sw_reserved.xstate_size = xstate_size; + + if (config_enabled(CONFIG_IA32_EMULATION)) { + fx_sw_reserved_ia32 = fx_sw_reserved; + fx_sw_reserved_ia32.extended_size += fsave_header_size; + } +} + diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c new file mode 100644 index 000000000000..62fc001c7846 --- /dev/null +++ b/arch/x86/kernel/fpu/xstate.c @@ -0,0 +1,461 @@ +/* + * xsave/xrstor support. + * + * Author: Suresh Siddha <suresh.b.siddha@intel.com> + */ +#include <linux/compat.h> +#include <linux/cpu.h> + +#include <asm/fpu/api.h> +#include <asm/fpu/internal.h> +#include <asm/fpu/signal.h> +#include <asm/fpu/regset.h> + +#include <asm/tlbflush.h> + +static const char *xfeature_names[] = +{ + "x87 floating point registers" , + "SSE registers" , + "AVX registers" , + "MPX bounds registers" , + "MPX CSR" , + "AVX-512 opmask" , + "AVX-512 Hi256" , + "AVX-512 ZMM_Hi256" , + "unknown xstate feature" , +}; + +/* + * Mask of xstate features supported by the CPU and the kernel: + */ +u64 xfeatures_mask __read_mostly; + +static unsigned int xstate_offsets[XFEATURES_NR_MAX] = { [ 0 ... XFEATURES_NR_MAX - 1] = -1}; +static unsigned int xstate_sizes[XFEATURES_NR_MAX] = { [ 0 ... XFEATURES_NR_MAX - 1] = -1}; +static unsigned int xstate_comp_offsets[sizeof(xfeatures_mask)*8]; + +/* The number of supported xfeatures in xfeatures_mask: */ +static unsigned int xfeatures_nr; + +/* + * Return whether the system supports a given xfeature. + * + * Also return the name of the (most advanced) feature that the caller requested: + */ +int cpu_has_xfeatures(u64 xfeatures_needed, const char **feature_name) +{ + u64 xfeatures_missing = xfeatures_needed & ~xfeatures_mask; + + if (unlikely(feature_name)) { + long xfeature_idx, max_idx; + u64 xfeatures_print; + /* + * So we use FLS here to be able to print the most advanced + * feature that was requested but is missing. So if a driver + * asks about "XSTATE_SSE | XSTATE_YMM" we'll print the + * missing AVX feature - this is the most informative message + * to users: + */ + if (xfeatures_missing) + xfeatures_print = xfeatures_missing; + else + xfeatures_print = xfeatures_needed; + + xfeature_idx = fls64(xfeatures_print)-1; + max_idx = ARRAY_SIZE(xfeature_names)-1; + xfeature_idx = min(xfeature_idx, max_idx); + + *feature_name = xfeature_names[xfeature_idx]; + } + + if (xfeatures_missing) + return 0; + + return 1; +} +EXPORT_SYMBOL_GPL(cpu_has_xfeatures); + +/* + * When executing XSAVEOPT (or other optimized XSAVE instructions), if + * a processor implementation detects that an FPU state component is still + * (or is again) in its initialized state, it may clear the corresponding + * bit in the header.xfeatures field, and can skip the writeout of registers + * to the corresponding memory layout. + * + * This means that when the bit is zero, the state component might still contain + * some previous - non-initialized register state. + * + * Before writing xstate information to user-space we sanitize those components, + * to always ensure that the memory layout of a feature will be in the init state + * if the corresponding header bit is zero. This is to ensure that user-space doesn't + * see some stale state in the memory layout during signal handling, debugging etc. + */ +void fpstate_sanitize_xstate(struct fpu *fpu) +{ + struct fxregs_state *fx = &fpu->state.fxsave; + int feature_bit; + u64 xfeatures; + + if (!use_xsaveopt()) + return; + + xfeatures = fpu->state.xsave.header.xfeatures; + + /* + * None of the feature bits are in init state. So nothing else + * to do for us, as the memory layout is up to date. + */ + if ((xfeatures & xfeatures_mask) == xfeatures_mask) + return; + + /* + * FP is in init state + */ + if (!(xfeatures & XSTATE_FP)) { + fx->cwd = 0x37f; + fx->swd = 0; + fx->twd = 0; + fx->fop = 0; + fx->rip = 0; + fx->rdp = 0; + memset(&fx->st_space[0], 0, 128); + } + + /* + * SSE is in init state + */ + if (!(xfeatures & XSTATE_SSE)) + memset(&fx->xmm_space[0], 0, 256); + + /* + * First two features are FPU and SSE, which above we handled + * in a special way already: + */ + feature_bit = 0x2; + xfeatures = (xfeatures_mask & ~xfeatures) >> 2; + + /* + * Update all the remaining memory layouts according to their + * standard xstate layout, if their header bit is in the init + * state: + */ + while (xfeatures) { + if (xfeatures & 0x1) { + int offset = xstate_offsets[feature_bit]; + int size = xstate_sizes[feature_bit]; + + memcpy((void *)fx + offset, + (void *)&init_fpstate.xsave + offset, + size); + } + + xfeatures >>= 1; + feature_bit++; + } +} + +/* + * Enable the extended processor state save/restore feature. + * Called once per CPU onlining. + */ +void fpu__init_cpu_xstate(void) +{ + if (!cpu_has_xsave || !xfeatures_mask) + return; + + cr4_set_bits(X86_CR4_OSXSAVE); + xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask); +} + +/* + * Record the offsets and sizes of various xstates contained + * in the XSAVE state memory layout. + * + * ( Note that certain features might be non-present, for them + * we'll have 0 offset and 0 size. ) + */ +static void __init setup_xstate_features(void) +{ + u32 eax, ebx, ecx, edx, leaf; + + xfeatures_nr = fls64(xfeatures_mask); + + for (leaf = 2; leaf < xfeatures_nr; leaf++) { + cpuid_count(XSTATE_CPUID, leaf, &eax, &ebx, &ecx, &edx); + + xstate_offsets[leaf] = ebx; + xstate_sizes[leaf] = eax; + + printk(KERN_INFO "x86/fpu: xstate_offset[%d]: %04x, xstate_sizes[%d]: %04x\n", leaf, ebx, leaf, eax); + } +} + +static void __init print_xstate_feature(u64 xstate_mask) +{ + const char *feature_name; + + if (cpu_has_xfeatures(xstate_mask, &feature_name)) + pr_info("x86/fpu: Supporting XSAVE feature 0x%02Lx: '%s'\n", xstate_mask, feature_name); +} + +/* + * Print out all the supported xstate features: + */ +static void __init print_xstate_features(void) +{ + print_xstate_feature(XSTATE_FP); + print_xstate_feature(XSTATE_SSE); + print_xstate_feature(XSTATE_YMM); + print_xstate_feature(XSTATE_BNDREGS); + print_xstate_feature(XSTATE_BNDCSR); + print_xstate_feature(XSTATE_OPMASK); + print_xstate_feature(XSTATE_ZMM_Hi256); + print_xstate_feature(XSTATE_Hi16_ZMM); +} + +/* + * This function sets up offsets and sizes of all extended states in + * xsave area. This supports both standard format and compacted format + * of the xsave aread. + */ +static void __init setup_xstate_comp(void) +{ + unsigned int xstate_comp_sizes[sizeof(xfeatures_mask)*8]; + int i; + + /* + * The FP xstates and SSE xstates are legacy states. They are always + * in the fixed offsets in the xsave area in either compacted form + * or standard form. + */ + xstate_comp_offsets[0] = 0; + xstate_comp_offsets[1] = offsetof(struct fxregs_state, xmm_space); + + if (!cpu_has_xsaves) { + for (i = 2; i < xfeatures_nr; i++) { + if (test_bit(i, (unsigned long *)&xfeatures_mask)) { + xstate_comp_offsets[i] = xstate_offsets[i]; + xstate_comp_sizes[i] = xstate_sizes[i]; + } + } + return; + } + + xstate_comp_offsets[2] = FXSAVE_SIZE + XSAVE_HDR_SIZE; + + for (i = 2; i < xfeatures_nr; i++) { + if (test_bit(i, (unsigned long *)&xfeatures_mask)) + xstate_comp_sizes[i] = xstate_sizes[i]; + else + xstate_comp_sizes[i] = 0; + + if (i > 2) + xstate_comp_offsets[i] = xstate_comp_offsets[i-1] + + xstate_comp_sizes[i-1]; + + } +} + +/* + * setup the xstate image representing the init state + */ +static void __init setup_init_fpu_buf(void) +{ + static int on_boot_cpu = 1; + + WARN_ON_FPU(!on_boot_cpu); + on_boot_cpu = 0; + + if (!cpu_has_xsave) + return; + + setup_xstate_features(); + print_xstate_features(); + + if (cpu_has_xsaves) { + init_fpstate.xsave.header.xcomp_bv = (u64)1 << 63 | xfeatures_mask; + init_fpstate.xsave.header.xfeatures = xfeatures_mask; + } + + /* + * Init all the features state with header_bv being 0x0 + */ + copy_kernel_to_xregs_booting(&init_fpstate.xsave); + + /* + * Dump the init state again. This is to identify the init state + * of any feature which is not represented by all zero's. + */ + copy_xregs_to_kernel_booting(&init_fpstate.xsave); +} + +/* + * Calculate total size of enabled xstates in XCR0/xfeatures_mask. + */ +static void __init init_xstate_size(void) +{ + unsigned int eax, ebx, ecx, edx; + int i; + + if (!cpu_has_xsaves) { + cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx); + xstate_size = ebx; + return; + } + + xstate_size = FXSAVE_SIZE + XSAVE_HDR_SIZE; + for (i = 2; i < 64; i++) { + if (test_bit(i, (unsigned long *)&xfeatures_mask)) { + cpuid_count(XSTATE_CPUID, i, &eax, &ebx, &ecx, &edx); + xstate_size += eax; + } + } +} + +/* + * Enable and initialize the xsave feature. + * Called once per system bootup. + */ +void __init fpu__init_system_xstate(void) +{ + unsigned int eax, ebx, ecx, edx; + static int on_boot_cpu = 1; + + WARN_ON_FPU(!on_boot_cpu); + on_boot_cpu = 0; + + if (!cpu_has_xsave) { + pr_info("x86/fpu: Legacy x87 FPU detected.\n"); + return; + } + + if (boot_cpu_data.cpuid_level < XSTATE_CPUID) { + WARN_ON_FPU(1); + return; + } + + cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx); + xfeatures_mask = eax + ((u64)edx << 32); + + if ((xfeatures_mask & XSTATE_FPSSE) != XSTATE_FPSSE) { + pr_err("x86/fpu: FP/SSE not present amongst the CPU's xstate features: 0x%llx.\n", xfeatures_mask); + BUG(); + } + + /* Support only the state known to the OS: */ + xfeatures_mask = xfeatures_mask & XCNTXT_MASK; + + /* Enable xstate instructions to be able to continue with initialization: */ + fpu__init_cpu_xstate(); + + /* Recompute the context size for enabled features: */ + init_xstate_size(); + + update_regset_xstate_info(xstate_size, xfeatures_mask); + fpu__init_prepare_fx_sw_frame(); + setup_init_fpu_buf(); + setup_xstate_comp(); + + pr_info("x86/fpu: Enabled xstate features 0x%llx, context size is 0x%x bytes, using '%s' format.\n", + xfeatures_mask, + xstate_size, + cpu_has_xsaves ? "compacted" : "standard"); +} + +/* + * Restore minimal FPU state after suspend: + */ +void fpu__resume_cpu(void) +{ + /* + * Restore XCR0 on xsave capable CPUs: + */ + if (cpu_has_xsave) + xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask); +} + +/* + * Given the xsave area and a state inside, this function returns the + * address of the state. + * + * This is the API that is called to get xstate address in either + * standard format or compacted format of xsave area. + * + * Note that if there is no data for the field in the xsave buffer + * this will return NULL. + * + * Inputs: + * xstate: the thread's storage area for all FPU data + * xstate_feature: state which is defined in xsave.h (e.g. + * XSTATE_FP, XSTATE_SSE, etc...) + * Output: + * address of the state in the xsave area, or NULL if the + * field is not present in the xsave buffer. + */ +void *get_xsave_addr(struct xregs_state *xsave, int xstate_feature) +{ + int feature_nr = fls64(xstate_feature) - 1; + /* + * Do we even *have* xsave state? + */ + if (!boot_cpu_has(X86_FEATURE_XSAVE)) + return NULL; + + xsave = ¤t->thread.fpu.state.xsave; + /* + * We should not ever be requesting features that we + * have not enabled. Remember that pcntxt_mask is + * what we write to the XCR0 register. + */ + WARN_ONCE(!(xfeatures_mask & xstate_feature), + "get of unsupported state"); + /* + * This assumes the last 'xsave*' instruction to + * have requested that 'xstate_feature' be saved. + * If it did not, we might be seeing and old value + * of the field in the buffer. + * + * This can happen because the last 'xsave' did not + * request that this feature be saved (unlikely) + * or because the "init optimization" caused it + * to not be saved. + */ + if (!(xsave->header.xfeatures & xstate_feature)) + return NULL; + + return (void *)xsave + xstate_comp_offsets[feature_nr]; +} +EXPORT_SYMBOL_GPL(get_xsave_addr); + +/* + * This wraps up the common operations that need to occur when retrieving + * data from xsave state. It first ensures that the current task was + * using the FPU and retrieves the data in to a buffer. It then calculates + * the offset of the requested field in the buffer. + * + * This function is safe to call whether the FPU is in use or not. + * + * Note that this only works on the current task. + * + * Inputs: + * @xsave_state: state which is defined in xsave.h (e.g. XSTATE_FP, + * XSTATE_SSE, etc...) + * Output: + * address of the state in the xsave area or NULL if the state + * is not present or is in its 'init state'. + */ +const void *get_xsave_field_ptr(int xsave_state) +{ + struct fpu *fpu = ¤t->thread.fpu; + + if (!fpu->fpstate_active) + return NULL; + /* + * fpu__save() takes the CPU's xstate registers + * and saves them off to the 'fpu memory buffer. + */ + fpu__save(fpu); + + return get_xsave_addr(&fpu->state.xsave, xsave_state); +} diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 544dec4cc605..0e2d96ffd158 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -62,9 +62,16 @@ #define PAGE_TABLE_SIZE(pages) ((pages) / PTRS_PER_PGD) #endif -/* Number of possible pages in the lowmem region */ -LOWMEM_PAGES = (((1<<32) - __PAGE_OFFSET) >> PAGE_SHIFT) - +/* + * 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 diff --git a/arch/x86/kernel/i386_ksyms_32.c b/arch/x86/kernel/i386_ksyms_32.c index 05fd74f537d6..64341aa485ae 100644 --- a/arch/x86/kernel/i386_ksyms_32.c +++ b/arch/x86/kernel/i386_ksyms_32.c @@ -40,7 +40,5 @@ EXPORT_SYMBOL(empty_zero_page); #ifdef CONFIG_PREEMPT EXPORT_SYMBOL(___preempt_schedule); -#ifdef CONFIG_CONTEXT_TRACKING -EXPORT_SYMBOL(___preempt_schedule_context); -#endif +EXPORT_SYMBOL(___preempt_schedule_notrace); #endif diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c deleted file mode 100644 index 6185d3141219..000000000000 --- a/arch/x86/kernel/i387.c +++ /dev/null @@ -1,671 +0,0 @@ -/* - * Copyright (C) 1994 Linus Torvalds - * - * Pentium III FXSR, SSE support - * General FPU state handling cleanups - * Gareth Hughes <gareth@valinux.com>, May 2000 - */ -#include <linux/module.h> -#include <linux/regset.h> -#include <linux/sched.h> -#include <linux/slab.h> - -#include <asm/sigcontext.h> -#include <asm/processor.h> -#include <asm/math_emu.h> -#include <asm/tlbflush.h> -#include <asm/uaccess.h> -#include <asm/ptrace.h> -#include <asm/i387.h> -#include <asm/fpu-internal.h> -#include <asm/user.h> - -static DEFINE_PER_CPU(bool, in_kernel_fpu); - -void kernel_fpu_disable(void) -{ - WARN_ON(this_cpu_read(in_kernel_fpu)); - this_cpu_write(in_kernel_fpu, true); -} - -void kernel_fpu_enable(void) -{ - this_cpu_write(in_kernel_fpu, false); -} - -/* - * Were we in an interrupt that interrupted kernel mode? - * - * On others, we can do a kernel_fpu_begin/end() pair *ONLY* if that - * pair does nothing at all: the thread must not have fpu (so - * that we don't try to save the FPU state), and TS must - * be set (so that the clts/stts pair does nothing that is - * visible in the interrupted kernel thread). - * - * Except for the eagerfpu case when we return true; in the likely case - * the thread has FPU but we are not going to set/clear TS. - */ -static inline bool interrupted_kernel_fpu_idle(void) -{ - if (this_cpu_read(in_kernel_fpu)) - return false; - - if (use_eager_fpu()) - return true; - - return !__thread_has_fpu(current) && - (read_cr0() & X86_CR0_TS); -} - -/* - * Were we in user mode (or vm86 mode) when we were - * interrupted? - * - * Doing kernel_fpu_begin/end() is ok if we are running - * in an interrupt context from user mode - we'll just - * save the FPU state as required. - */ -static inline bool interrupted_user_mode(void) -{ - struct pt_regs *regs = get_irq_regs(); - return regs && user_mode(regs); -} - -/* - * Can we use the FPU in kernel mode with the - * whole "kernel_fpu_begin/end()" sequence? - * - * It's always ok in process context (ie "not interrupt") - * but it is sometimes ok even from an irq. - */ -bool irq_fpu_usable(void) -{ - return !in_interrupt() || - interrupted_user_mode() || - interrupted_kernel_fpu_idle(); -} -EXPORT_SYMBOL(irq_fpu_usable); - -void __kernel_fpu_begin(void) -{ - struct task_struct *me = current; - - this_cpu_write(in_kernel_fpu, true); - - if (__thread_has_fpu(me)) { - __save_init_fpu(me); - } else { - this_cpu_write(fpu_owner_task, NULL); - if (!use_eager_fpu()) - clts(); - } -} -EXPORT_SYMBOL(__kernel_fpu_begin); - -void __kernel_fpu_end(void) -{ - struct task_struct *me = current; - - if (__thread_has_fpu(me)) { - if (WARN_ON(restore_fpu_checking(me))) - fpu_reset_state(me); - } else if (!use_eager_fpu()) { - stts(); - } - - this_cpu_write(in_kernel_fpu, false); -} -EXPORT_SYMBOL(__kernel_fpu_end); - -void unlazy_fpu(struct task_struct *tsk) -{ - preempt_disable(); - if (__thread_has_fpu(tsk)) { - if (use_eager_fpu()) { - __save_fpu(tsk); - } else { - __save_init_fpu(tsk); - __thread_fpu_end(tsk); - } - } - preempt_enable(); -} -EXPORT_SYMBOL(unlazy_fpu); - -unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu; -unsigned int xstate_size; -EXPORT_SYMBOL_GPL(xstate_size); -static struct i387_fxsave_struct fx_scratch; - -static void mxcsr_feature_mask_init(void) -{ - unsigned long mask = 0; - - if (cpu_has_fxsr) { - memset(&fx_scratch, 0, sizeof(struct i387_fxsave_struct)); - asm volatile("fxsave %0" : "+m" (fx_scratch)); - mask = fx_scratch.mxcsr_mask; - if (mask == 0) - mask = 0x0000ffbf; - } - mxcsr_feature_mask &= mask; -} - -static void init_thread_xstate(void) -{ - /* - * Note that xstate_size might be overwriten later during - * xsave_init(). - */ - - if (!cpu_has_fpu) { - /* - * Disable xsave as we do not support it if i387 - * emulation is enabled. - */ - setup_clear_cpu_cap(X86_FEATURE_XSAVE); - setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); - xstate_size = sizeof(struct i387_soft_struct); - return; - } - - if (cpu_has_fxsr) - xstate_size = sizeof(struct i387_fxsave_struct); - else - xstate_size = sizeof(struct i387_fsave_struct); - - /* - * Quirk: we don't yet handle the XSAVES* instructions - * correctly, as we don't correctly convert between - * standard and compacted format when interfacing - * with user-space - so disable it for now. - * - * The difference is small: with recent CPUs the - * compacted format is only marginally smaller than - * the standard FPU state format. - * - * ( This is easy to backport while we are fixing - * XSAVES* support. ) - */ - setup_clear_cpu_cap(X86_FEATURE_XSAVES); -} - -/* - * Called at bootup to set up the initial FPU state that is later cloned - * into all processes. - */ - -void fpu_init(void) -{ - unsigned long cr0; - unsigned long cr4_mask = 0; - -#ifndef CONFIG_MATH_EMULATION - if (!cpu_has_fpu) { - pr_emerg("No FPU found and no math emulation present\n"); - pr_emerg("Giving up\n"); - for (;;) - asm volatile("hlt"); - } -#endif - if (cpu_has_fxsr) - cr4_mask |= X86_CR4_OSFXSR; - if (cpu_has_xmm) - cr4_mask |= X86_CR4_OSXMMEXCPT; - if (cr4_mask) - cr4_set_bits(cr4_mask); - - cr0 = read_cr0(); - cr0 &= ~(X86_CR0_TS|X86_CR0_EM); /* clear TS and EM */ - if (!cpu_has_fpu) - cr0 |= X86_CR0_EM; - write_cr0(cr0); - - /* - * init_thread_xstate is only called once to avoid overriding - * xstate_size during boot time or during CPU hotplug. - */ - if (xstate_size == 0) - init_thread_xstate(); - - mxcsr_feature_mask_init(); - xsave_init(); - eager_fpu_init(); -} - -void fpu_finit(struct fpu *fpu) -{ - if (!cpu_has_fpu) { - finit_soft_fpu(&fpu->state->soft); - return; - } - - memset(fpu->state, 0, xstate_size); - - if (cpu_has_fxsr) { - fx_finit(&fpu->state->fxsave); - } else { - struct i387_fsave_struct *fp = &fpu->state->fsave; - fp->cwd = 0xffff037fu; - fp->swd = 0xffff0000u; - fp->twd = 0xffffffffu; - fp->fos = 0xffff0000u; - } -} -EXPORT_SYMBOL_GPL(fpu_finit); - -/* - * The _current_ task is using the FPU for the first time - * so initialize it and set the mxcsr to its default - * value at reset if we support XMM instructions and then - * remember the current task has used the FPU. - */ -int init_fpu(struct task_struct *tsk) -{ - int ret; - - if (tsk_used_math(tsk)) { - if (cpu_has_fpu && tsk == current) - unlazy_fpu(tsk); - task_disable_lazy_fpu_restore(tsk); - return 0; - } - - /* - * Memory allocation at the first usage of the FPU and other state. - */ - ret = fpu_alloc(&tsk->thread.fpu); - if (ret) - return ret; - - fpu_finit(&tsk->thread.fpu); - - set_stopped_child_used_math(tsk); - return 0; -} -EXPORT_SYMBOL_GPL(init_fpu); - -/* - * The xstateregs_active() routine is the same as the fpregs_active() routine, - * as the "regset->n" for the xstate regset will be updated based on the feature - * capabilites supported by the xsave. - */ -int fpregs_active(struct task_struct *target, const struct user_regset *regset) -{ - return tsk_used_math(target) ? regset->n : 0; -} - -int xfpregs_active(struct task_struct *target, const struct user_regset *regset) -{ - return (cpu_has_fxsr && tsk_used_math(target)) ? regset->n : 0; -} - -int xfpregs_get(struct task_struct *target, const struct user_regset *regset, - unsigned int pos, unsigned int count, - void *kbuf, void __user *ubuf) -{ - int ret; - - if (!cpu_has_fxsr) - return -ENODEV; - - ret = init_fpu(target); - if (ret) - return ret; - - sanitize_i387_state(target); - - return user_regset_copyout(&pos, &count, &kbuf, &ubuf, - &target->thread.fpu.state->fxsave, 0, -1); -} - -int xfpregs_set(struct task_struct *target, const struct user_regset *regset, - unsigned int pos, unsigned int count, - const void *kbuf, const void __user *ubuf) -{ - int ret; - - if (!cpu_has_fxsr) - return -ENODEV; - - ret = init_fpu(target); - if (ret) - return ret; - - sanitize_i387_state(target); - - ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, - &target->thread.fpu.state->fxsave, 0, -1); - - /* - * mxcsr reserved bits must be masked to zero for security reasons. - */ - target->thread.fpu.state->fxsave.mxcsr &= mxcsr_feature_mask; - - /* - * update the header bits in the xsave header, indicating the - * presence of FP and SSE state. - */ - if (cpu_has_xsave) - target->thread.fpu.state->xsave.xsave_hdr.xstate_bv |= XSTATE_FPSSE; - - return ret; -} - -int xstateregs_get(struct task_struct *target, const struct user_regset *regset, - unsigned int pos, unsigned int count, - void *kbuf, void __user *ubuf) -{ - struct xsave_struct *xsave; - int ret; - - if (!cpu_has_xsave) - return -ENODEV; - - ret = init_fpu(target); - if (ret) - return ret; - - xsave = &target->thread.fpu.state->xsave; - - /* - * Copy the 48bytes defined by the software first into the xstate - * memory layout in the thread struct, so that we can copy the entire - * xstateregs to the user using one user_regset_copyout(). - */ - memcpy(&xsave->i387.sw_reserved, - xstate_fx_sw_bytes, sizeof(xstate_fx_sw_bytes)); - /* - * Copy the xstate memory layout. - */ - ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, xsave, 0, -1); - return ret; -} - -int xstateregs_set(struct task_struct *target, const struct user_regset *regset, - unsigned int pos, unsigned int count, - const void *kbuf, const void __user *ubuf) -{ - struct xsave_struct *xsave; - int ret; - - if (!cpu_has_xsave) - return -ENODEV; - - ret = init_fpu(target); - if (ret) - return ret; - - xsave = &target->thread.fpu.state->xsave; - - ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, xsave, 0, -1); - /* - * mxcsr reserved bits must be masked to zero for security reasons. - */ - xsave->i387.mxcsr &= mxcsr_feature_mask; - xsave->xsave_hdr.xstate_bv &= pcntxt_mask; - /* - * These bits must be zero. - */ - memset(&xsave->xsave_hdr.reserved, 0, 48); - return ret; -} - -#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION - -/* - * FPU tag word conversions. - */ - -static inline unsigned short twd_i387_to_fxsr(unsigned short twd) -{ - unsigned int tmp; /* to avoid 16 bit prefixes in the code */ - - /* Transform each pair of bits into 01 (valid) or 00 (empty) */ - tmp = ~twd; - tmp = (tmp | (tmp>>1)) & 0x5555; /* 0V0V0V0V0V0V0V0V */ - /* and move the valid bits to the lower byte. */ - tmp = (tmp | (tmp >> 1)) & 0x3333; /* 00VV00VV00VV00VV */ - tmp = (tmp | (tmp >> 2)) & 0x0f0f; /* 0000VVVV0000VVVV */ - tmp = (tmp | (tmp >> 4)) & 0x00ff; /* 00000000VVVVVVVV */ - - return tmp; -} - -#define FPREG_ADDR(f, n) ((void *)&(f)->st_space + (n) * 16) -#define FP_EXP_TAG_VALID 0 -#define FP_EXP_TAG_ZERO 1 -#define FP_EXP_TAG_SPECIAL 2 -#define FP_EXP_TAG_EMPTY 3 - -static inline u32 twd_fxsr_to_i387(struct i387_fxsave_struct *fxsave) -{ - struct _fpxreg *st; - u32 tos = (fxsave->swd >> 11) & 7; - u32 twd = (unsigned long) fxsave->twd; - u32 tag; - u32 ret = 0xffff0000u; - int i; - - for (i = 0; i < 8; i++, twd >>= 1) { - if (twd & 0x1) { - st = FPREG_ADDR(fxsave, (i - tos) & 7); - - switch (st->exponent & 0x7fff) { - case 0x7fff: - tag = FP_EXP_TAG_SPECIAL; - break; - case 0x0000: - if (!st->significand[0] && - !st->significand[1] && - !st->significand[2] && - !st->significand[3]) - tag = FP_EXP_TAG_ZERO; - else - tag = FP_EXP_TAG_SPECIAL; - break; - default: - if (st->significand[3] & 0x8000) - tag = FP_EXP_TAG_VALID; - else - tag = FP_EXP_TAG_SPECIAL; - break; - } - } else { - tag = FP_EXP_TAG_EMPTY; - } - ret |= tag << (2 * i); - } - return ret; -} - -/* - * FXSR floating point environment conversions. - */ - -void -convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk) -{ - struct i387_fxsave_struct *fxsave = &tsk->thread.fpu.state->fxsave; - struct _fpreg *to = (struct _fpreg *) &env->st_space[0]; - struct _fpxreg *from = (struct _fpxreg *) &fxsave->st_space[0]; - int i; - - env->cwd = fxsave->cwd | 0xffff0000u; - env->swd = fxsave->swd | 0xffff0000u; - env->twd = twd_fxsr_to_i387(fxsave); - -#ifdef CONFIG_X86_64 - env->fip = fxsave->rip; - env->foo = fxsave->rdp; - /* - * should be actually ds/cs at fpu exception time, but - * that information is not available in 64bit mode. - */ - env->fcs = task_pt_regs(tsk)->cs; - if (tsk == current) { - savesegment(ds, env->fos); - } else { - env->fos = tsk->thread.ds; - } - env->fos |= 0xffff0000; -#else - env->fip = fxsave->fip; - env->fcs = (u16) fxsave->fcs | ((u32) fxsave->fop << 16); - env->foo = fxsave->foo; - env->fos = fxsave->fos; -#endif - - for (i = 0; i < 8; ++i) - memcpy(&to[i], &from[i], sizeof(to[0])); -} - -void convert_to_fxsr(struct task_struct *tsk, - const struct user_i387_ia32_struct *env) - -{ - struct i387_fxsave_struct *fxsave = &tsk->thread.fpu.state->fxsave; - struct _fpreg *from = (struct _fpreg *) &env->st_space[0]; - struct _fpxreg *to = (struct _fpxreg *) &fxsave->st_space[0]; - int i; - - fxsave->cwd = env->cwd; - fxsave->swd = env->swd; - fxsave->twd = twd_i387_to_fxsr(env->twd); - fxsave->fop = (u16) ((u32) env->fcs >> 16); -#ifdef CONFIG_X86_64 - fxsave->rip = env->fip; - fxsave->rdp = env->foo; - /* cs and ds ignored */ -#else - fxsave->fip = env->fip; - fxsave->fcs = (env->fcs & 0xffff); - fxsave->foo = env->foo; - fxsave->fos = env->fos; -#endif - - for (i = 0; i < 8; ++i) - memcpy(&to[i], &from[i], sizeof(from[0])); -} - -int fpregs_get(struct task_struct *target, const struct user_regset *regset, - unsigned int pos, unsigned int count, - void *kbuf, void __user *ubuf) -{ - struct user_i387_ia32_struct env; - int ret; - - ret = init_fpu(target); - if (ret) - return ret; - - if (!static_cpu_has(X86_FEATURE_FPU)) - return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf); - - if (!cpu_has_fxsr) - return user_regset_copyout(&pos, &count, &kbuf, &ubuf, - &target->thread.fpu.state->fsave, 0, - -1); - - sanitize_i387_state(target); - - if (kbuf && pos == 0 && count == sizeof(env)) { - convert_from_fxsr(kbuf, target); - return 0; - } - - convert_from_fxsr(&env, target); - - return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &env, 0, -1); -} - -int fpregs_set(struct task_struct *target, const struct user_regset *regset, - unsigned int pos, unsigned int count, - const void *kbuf, const void __user *ubuf) -{ - struct user_i387_ia32_struct env; - int ret; - - ret = init_fpu(target); - if (ret) - return ret; - - sanitize_i387_state(target); - - if (!static_cpu_has(X86_FEATURE_FPU)) - return fpregs_soft_set(target, regset, pos, count, kbuf, ubuf); - - if (!cpu_has_fxsr) - return user_regset_copyin(&pos, &count, &kbuf, &ubuf, - &target->thread.fpu.state->fsave, 0, - -1); - - if (pos > 0 || count < sizeof(env)) - convert_from_fxsr(&env, target); - - ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &env, 0, -1); - if (!ret) - convert_to_fxsr(target, &env); - - /* - * update the header bit in the xsave header, indicating the - * presence of FP. - */ - if (cpu_has_xsave) - target->thread.fpu.state->xsave.xsave_hdr.xstate_bv |= XSTATE_FP; - return ret; -} - -/* - * FPU state for core dumps. - * This is only used for a.out dumps now. - * It is declared generically using elf_fpregset_t (which is - * struct user_i387_struct) but is in fact only used for 32-bit - * dumps, so on 64-bit it is really struct user_i387_ia32_struct. - */ -int dump_fpu(struct pt_regs *regs, struct user_i387_struct *fpu) -{ - struct task_struct *tsk = current; - int fpvalid; - - fpvalid = !!used_math(); - if (fpvalid) - fpvalid = !fpregs_get(tsk, NULL, - 0, sizeof(struct user_i387_ia32_struct), - fpu, NULL); - - return fpvalid; -} -EXPORT_SYMBOL(dump_fpu); - -#endif /* CONFIG_X86_32 || CONFIG_IA32_EMULATION */ - -static int __init no_387(char *s) -{ - setup_clear_cpu_cap(X86_FEATURE_FPU); - return 1; -} - -__setup("no387", no_387); - -void fpu_detect(struct cpuinfo_x86 *c) -{ - unsigned long cr0; - u16 fsw, fcw; - - fsw = fcw = 0xffff; - - cr0 = read_cr0(); - cr0 &= ~(X86_CR0_TS | X86_CR0_EM); - write_cr0(cr0); - - asm volatile("fninit ; fnstsw %0 ; fnstcw %1" - : "+m" (fsw), "+m" (fcw)); - - if (fsw == 0 && (fcw & 0x103f) == 0x003f) - set_cpu_cap(c, X86_FEATURE_FPU); - else - clear_cpu_cap(c, X86_FEATURE_FPU); - - /* The final cr0 value is set in fpu_init() */ -} diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index a25e202bb319..353972c1946c 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -140,6 +140,51 @@ void dma_generic_free_coherent(struct device *dev, size_t size, void *vaddr, free_pages((unsigned long)vaddr, get_order(size)); } +void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle, + gfp_t gfp, struct dma_attrs *attrs) +{ + struct dma_map_ops *ops = get_dma_ops(dev); + void *memory; + + gfp &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32); + + if (dma_alloc_from_coherent(dev, size, dma_handle, &memory)) + return memory; + + if (!dev) + dev = &x86_dma_fallback_dev; + + if (!is_device_dma_capable(dev)) + return NULL; + + if (!ops->alloc) + return NULL; + + memory = ops->alloc(dev, size, dma_handle, + dma_alloc_coherent_gfp_flags(dev, gfp), attrs); + debug_dma_alloc_coherent(dev, size, *dma_handle, memory); + + return memory; +} +EXPORT_SYMBOL(dma_alloc_attrs); + +void dma_free_attrs(struct device *dev, size_t size, + void *vaddr, dma_addr_t bus, + struct dma_attrs *attrs) +{ + struct dma_map_ops *ops = get_dma_ops(dev); + + WARN_ON(irqs_disabled()); /* for portability */ + + if (dma_release_from_coherent(dev, get_order(size), vaddr)) + return; + + debug_dma_free_coherent(dev, size, vaddr, bus); + if (ops->free) + ops->free(dev, size, vaddr, bus, attrs); +} +EXPORT_SYMBOL(dma_free_attrs); + /* * See <Documentation/x86/x86_64/boot-options.txt> for the iommu kernel * parameter documentation. diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c index 77dd0ad58be4..adf0392d549a 100644 --- a/arch/x86/kernel/pci-swiotlb.c +++ b/arch/x86/kernel/pci-swiotlb.c @@ -20,6 +20,13 @@ void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size, { void *vaddr; + /* + * Don't print a warning when the first allocation attempt fails. + * swiotlb_alloc_coherent() will print a warning when the DMA + * memory allocation ultimately failed. + */ + flags |= __GFP_NOWARN; + vaddr = dma_generic_alloc_coherent(hwdev, size, dma_handle, flags, attrs); if (vaddr) diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 6e338e3b1dc0..9cad694ed7c4 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -25,8 +25,7 @@ #include <asm/idle.h> #include <asm/uaccess.h> #include <asm/mwait.h> -#include <asm/i387.h> -#include <asm/fpu-internal.h> +#include <asm/fpu/internal.h> #include <asm/debugreg.h> #include <asm/nmi.h> #include <asm/tlbflush.h> @@ -76,9 +75,6 @@ void idle_notifier_unregister(struct notifier_block *n) EXPORT_SYMBOL_GPL(idle_notifier_unregister); #endif -struct kmem_cache *task_xstate_cachep; -EXPORT_SYMBOL_GPL(task_xstate_cachep); - /* * this gets called so that we can store lazy state into memory and copy the * current task into the new thread. @@ -87,36 +83,7 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { *dst = *src; - dst->thread.fpu_counter = 0; - dst->thread.fpu.has_fpu = 0; - dst->thread.fpu.state = NULL; - task_disable_lazy_fpu_restore(dst); - if (tsk_used_math(src)) { - int err = fpu_alloc(&dst->thread.fpu); - if (err) - return err; - fpu_copy(dst, src); - } - return 0; -} - -void free_thread_xstate(struct task_struct *tsk) -{ - fpu_free(&tsk->thread.fpu); -} - -void arch_release_task_struct(struct task_struct *tsk) -{ - free_thread_xstate(tsk); -} - -void arch_task_cache_init(void) -{ - task_xstate_cachep = - kmem_cache_create("task_xstate", xstate_size, - __alignof__(union thread_xstate), - SLAB_PANIC | SLAB_NOTRACK, NULL); - setup_xstate_comp(); + return fpu__copy(&dst->thread.fpu, &src->thread.fpu); } /* @@ -127,6 +94,7 @@ void exit_thread(void) struct task_struct *me = current; struct thread_struct *t = &me->thread; unsigned long *bp = t->io_bitmap_ptr; + struct fpu *fpu = &t->fpu; if (bp) { struct tss_struct *tss = &per_cpu(cpu_tss, get_cpu()); @@ -142,7 +110,7 @@ void exit_thread(void) kfree(bp); } - drop_fpu(me); + fpu__drop(fpu); } void flush_thread(void) @@ -152,19 +120,7 @@ void flush_thread(void) flush_ptrace_hw_breakpoint(tsk); memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array)); - if (!use_eager_fpu()) { - /* FPU state will be reallocated lazily at the first use. */ - drop_fpu(tsk); - free_thread_xstate(tsk); - } else { - if (!tsk_used_math(tsk)) { - /* kthread execs. TODO: cleanup this horror. */ - if (WARN_ON(init_fpu(tsk))) - force_sig(SIGKILL, tsk); - user_fpu_begin(); - } - restore_init_xstate(); - } + fpu__clear(&tsk->thread.fpu); } static void hard_disable_TSC(void) @@ -445,11 +401,10 @@ static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c) } /* - * MONITOR/MWAIT with no hints, used for default default C1 state. - * This invokes MWAIT with interrutps enabled and no flags, - * which is backwards compatible with the original MWAIT implementation. + * MONITOR/MWAIT with no hints, used for default C1 state. This invokes MWAIT + * with interrupts enabled and no flags, which is backwards compatible with the + * original MWAIT implementation. */ - static void mwait_idle(void) { if (!current_set_polling_and_test()) { diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index a99900cedc22..c09c99ccf3e3 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -39,8 +39,7 @@ #include <asm/pgtable.h> #include <asm/ldt.h> #include <asm/processor.h> -#include <asm/i387.h> -#include <asm/fpu-internal.h> +#include <asm/fpu/internal.h> #include <asm/desc.h> #ifdef CONFIG_MATH_EMULATION #include <asm/math_emu.h> @@ -242,14 +241,16 @@ __visible __notrace_funcgraph struct task_struct * __switch_to(struct task_struct *prev_p, struct task_struct *next_p) { struct thread_struct *prev = &prev_p->thread, - *next = &next_p->thread; + *next = &next_p->thread; + struct fpu *prev_fpu = &prev->fpu; + struct fpu *next_fpu = &next->fpu; int cpu = smp_processor_id(); struct tss_struct *tss = &per_cpu(cpu_tss, cpu); - fpu_switch_t fpu; + fpu_switch_t fpu_switch; /* never put a printk in __switch_to... printk() calls wake_up*() indirectly */ - fpu = switch_fpu_prepare(prev_p, next_p, cpu); + fpu_switch = switch_fpu_prepare(prev_fpu, next_fpu, cpu); /* * Save away %gs. No need to save %fs, as it was saved on the @@ -296,7 +297,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) * Leave lazy mode, flushing any hypercalls made here. * This must be done before restoring TLS segments so * the GDT and LDT are properly updated, and must be - * done before math_state_restore, so the TS bit is up + * done before fpu__restore(), so the TS bit is up * to date. */ arch_end_context_switch(next_p); @@ -316,7 +317,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) if (prev->gs | next->gs) lazy_load_gs(next->gs); - switch_fpu_finish(next_p, fpu); + switch_fpu_finish(next_fpu, fpu_switch); this_cpu_write(current_task, next_p); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 82134506faa8..843f92e4c711 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -38,8 +38,7 @@ #include <asm/pgtable.h> #include <asm/processor.h> -#include <asm/i387.h> -#include <asm/fpu-internal.h> +#include <asm/fpu/internal.h> #include <asm/mmu_context.h> #include <asm/prctl.h> #include <asm/desc.h> @@ -274,12 +273,14 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) { struct thread_struct *prev = &prev_p->thread; struct thread_struct *next = &next_p->thread; + struct fpu *prev_fpu = &prev->fpu; + struct fpu *next_fpu = &next->fpu; int cpu = smp_processor_id(); struct tss_struct *tss = &per_cpu(cpu_tss, cpu); unsigned fsindex, gsindex; - fpu_switch_t fpu; + fpu_switch_t fpu_switch; - fpu = switch_fpu_prepare(prev_p, next_p, cpu); + fpu_switch = switch_fpu_prepare(prev_fpu, next_fpu, cpu); /* We must save %fs and %gs before load_TLS() because * %fs and %gs may be cleared by load_TLS(). @@ -299,7 +300,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) * Leave lazy mode, flushing any hypercalls made here. This * must be done after loading TLS entries in the GDT but before * loading segments that might reference them, and and it must - * be done before math_state_restore, so the TS bit is up to + * be done before fpu__restore(), so the TS bit is up to * date. */ arch_end_context_switch(next_p); @@ -391,7 +392,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) wrmsrl(MSR_KERNEL_GS_BASE, next->gs); prev->gsindex = gsindex; - switch_fpu_finish(next_p, fpu); + switch_fpu_finish(next_fpu, fpu_switch); /* * Switch the PDA and FPU contexts. diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index a7bc79480719..9be72bc3613f 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -11,7 +11,6 @@ #include <linux/errno.h> #include <linux/slab.h> #include <linux/ptrace.h> -#include <linux/regset.h> #include <linux/tracehook.h> #include <linux/user.h> #include <linux/elf.h> @@ -28,8 +27,9 @@ #include <asm/uaccess.h> #include <asm/pgtable.h> #include <asm/processor.h> -#include <asm/i387.h> -#include <asm/fpu-internal.h> +#include <asm/fpu/internal.h> +#include <asm/fpu/signal.h> +#include <asm/fpu/regset.h> #include <asm/debugreg.h> #include <asm/ldt.h> #include <asm/desc.h> @@ -1297,7 +1297,7 @@ static struct user_regset x86_64_regsets[] __read_mostly = { .core_note_type = NT_PRFPREG, .n = sizeof(struct user_i387_struct) / sizeof(long), .size = sizeof(long), .align = sizeof(long), - .active = xfpregs_active, .get = xfpregs_get, .set = xfpregs_set + .active = regset_xregset_fpregs_active, .get = xfpregs_get, .set = xfpregs_set }, [REGSET_XSTATE] = { .core_note_type = NT_X86_XSTATE, @@ -1338,13 +1338,13 @@ static struct user_regset x86_32_regsets[] __read_mostly = { .core_note_type = NT_PRFPREG, .n = sizeof(struct user_i387_ia32_struct) / sizeof(u32), .size = sizeof(u32), .align = sizeof(u32), - .active = fpregs_active, .get = fpregs_get, .set = fpregs_set + .active = regset_fpregs_active, .get = fpregs_get, .set = fpregs_set }, [REGSET_XFP] = { .core_note_type = NT_PRXFPREG, .n = sizeof(struct user32_fxsr_struct) / sizeof(u32), .size = sizeof(u32), .align = sizeof(u32), - .active = xfpregs_active, .get = xfpregs_get, .set = xfpregs_set + .active = regset_xregset_fpregs_active, .get = xfpregs_get, .set = xfpregs_set }, [REGSET_XSTATE] = { .core_note_type = NT_X86_XSTATE, diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 8d04a7594a03..265a6fdea8b7 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -531,12 +531,14 @@ static void __init reserve_crashkernel_low(void) if (ret != 0) { /* * two parts from lib/swiotlb.c: - * swiotlb size: user specified with swiotlb= or default. - * swiotlb overflow buffer: now is hardcoded to 32k. - * We round it to 8M for other buffers that - * may need to stay low too. + * -swiotlb size: user-specified with swiotlb= or default. + * + * -swiotlb overflow buffer: now hardcoded to 32k. We round it + * to 8M for other buffers that may need to stay low too. Also + * make sure we allocate enough extra low memory so that we + * don't run out of DMA buffers for 32-bit devices. */ - low_size = swiotlb_size_or_default() + (8UL<<20); + low_size = max(swiotlb_size_or_default() + (8UL<<20), 256UL<<20); auto_set = true; } else { /* passed with crashkernel=0,low ? */ diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 1ea14fd53933..206996c1669d 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -26,8 +26,8 @@ #include <asm/processor.h> #include <asm/ucontext.h> -#include <asm/i387.h> -#include <asm/fpu-internal.h> +#include <asm/fpu/internal.h> +#include <asm/fpu/signal.h> #include <asm/vdso.h> #include <asm/mce.h> #include <asm/sighandling.h> @@ -103,7 +103,7 @@ int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc) get_user_ex(buf, &sc->fpstate); } get_user_catch(err); - err |= restore_xstate_sig(buf, config_enabled(CONFIG_X86_32)); + err |= fpu__restore_sig(buf, config_enabled(CONFIG_X86_32)); force_iret(); @@ -199,6 +199,7 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, unsigned long sp = regs->sp; unsigned long buf_fx = 0; int onsigstack = on_sig_stack(sp); + struct fpu *fpu = ¤t->thread.fpu; /* redzone */ if (config_enabled(CONFIG_X86_64)) @@ -218,9 +219,9 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, } } - if (used_math()) { - sp = alloc_mathframe(sp, config_enabled(CONFIG_X86_32), - &buf_fx, &math_size); + if (fpu->fpstate_active) { + sp = fpu__alloc_mathframe(sp, config_enabled(CONFIG_X86_32), + &buf_fx, &math_size); *fpstate = (void __user *)sp; } @@ -234,8 +235,8 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, return (void __user *)-1L; /* save i387 and extended state */ - if (used_math() && - save_xstate_sig(*fpstate, (void __user *)buf_fx, math_size) < 0) + if (fpu->fpstate_active && + copy_fpstate_to_sigframe(*fpstate, (void __user *)buf_fx, math_size) < 0) return (void __user *)-1L; return (void __user *)sp; @@ -593,6 +594,22 @@ badframe: return 0; } +static inline int is_ia32_compat_frame(void) +{ + return config_enabled(CONFIG_IA32_EMULATION) && + test_thread_flag(TIF_IA32); +} + +static inline int is_ia32_frame(void) +{ + return config_enabled(CONFIG_X86_32) || is_ia32_compat_frame(); +} + +static inline int is_x32_frame(void) +{ + return config_enabled(CONFIG_X86_X32_ABI) && test_thread_flag(TIF_X32); +} + static int setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs) { @@ -617,6 +634,7 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) { bool stepping, failed; + struct fpu *fpu = ¤t->thread.fpu; /* Are we from a system call? */ if (syscall_get_nr(current, regs) >= 0) { @@ -665,8 +683,8 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) /* * Ensure the signal handler starts with the new fpu state. */ - if (used_math()) - fpu_reset_state(current); + if (fpu->fpstate_active) + fpu__clear(fpu); } signal_setup_done(failed, ksig, stepping); } diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index fd6291c921b6..8add66b22f33 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -68,8 +68,7 @@ #include <asm/mwait.h> #include <asm/apic.h> #include <asm/io_apic.h> -#include <asm/i387.h> -#include <asm/fpu-internal.h> +#include <asm/fpu/internal.h> #include <asm/setup.h> #include <asm/uv/uv.h> #include <linux/mc146818rtc.h> @@ -314,10 +313,10 @@ topology_sane(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o, const char *name) cpu1, name, cpu2, cpu_to_node(cpu1), cpu_to_node(cpu2)); } -#define link_mask(_m, c1, c2) \ +#define link_mask(mfunc, c1, c2) \ do { \ - cpumask_set_cpu((c1), cpu_##_m##_mask(c2)); \ - cpumask_set_cpu((c2), cpu_##_m##_mask(c1)); \ + cpumask_set_cpu((c1), mfunc(c2)); \ + cpumask_set_cpu((c2), mfunc(c1)); \ } while (0) static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) @@ -398,9 +397,9 @@ void set_cpu_sibling_map(int cpu) cpumask_set_cpu(cpu, cpu_sibling_setup_mask); if (!has_mp) { - cpumask_set_cpu(cpu, cpu_sibling_mask(cpu)); + cpumask_set_cpu(cpu, topology_sibling_cpumask(cpu)); cpumask_set_cpu(cpu, cpu_llc_shared_mask(cpu)); - cpumask_set_cpu(cpu, cpu_core_mask(cpu)); + cpumask_set_cpu(cpu, topology_core_cpumask(cpu)); c->booted_cores = 1; return; } @@ -409,32 +408,34 @@ void set_cpu_sibling_map(int cpu) o = &cpu_data(i); if ((i == cpu) || (has_smt && match_smt(c, o))) - link_mask(sibling, cpu, i); + link_mask(topology_sibling_cpumask, cpu, i); if ((i == cpu) || (has_mp && match_llc(c, o))) - link_mask(llc_shared, cpu, i); + link_mask(cpu_llc_shared_mask, cpu, i); } /* * This needs a separate iteration over the cpus because we rely on all - * cpu_sibling_mask links to be set-up. + * topology_sibling_cpumask links to be set-up. */ for_each_cpu(i, cpu_sibling_setup_mask) { o = &cpu_data(i); if ((i == cpu) || (has_mp && match_die(c, o))) { - link_mask(core, cpu, i); + link_mask(topology_core_cpumask, cpu, i); /* * Does this new cpu bringup a new core? */ - if (cpumask_weight(cpu_sibling_mask(cpu)) == 1) { + if (cpumask_weight( + topology_sibling_cpumask(cpu)) == 1) { /* * for each core in package, increment * the booted_cores for this new cpu */ - if (cpumask_first(cpu_sibling_mask(i)) == i) + if (cpumask_first( + topology_sibling_cpumask(i)) == i) c->booted_cores++; /* * increment the core count for all @@ -1042,8 +1043,8 @@ static __init void disable_smp(void) physid_set_mask_of_physid(boot_cpu_physical_apicid, &phys_cpu_present_map); else physid_set_mask_of_physid(0, &phys_cpu_present_map); - cpumask_set_cpu(0, cpu_sibling_mask(0)); - cpumask_set_cpu(0, cpu_core_mask(0)); + cpumask_set_cpu(0, topology_sibling_cpumask(0)); + cpumask_set_cpu(0, topology_core_cpumask(0)); } enum { @@ -1328,22 +1329,22 @@ static void remove_siblinginfo(int cpu) int sibling; struct cpuinfo_x86 *c = &cpu_data(cpu); - for_each_cpu(sibling, cpu_core_mask(cpu)) { - cpumask_clear_cpu(cpu, cpu_core_mask(sibling)); + for_each_cpu(sibling, topology_core_cpumask(cpu)) { + cpumask_clear_cpu(cpu, topology_core_cpumask(sibling)); /*/ * last thread sibling in this cpu core going down */ - if (cpumask_weight(cpu_sibling_mask(cpu)) == 1) + if (cpumask_weight(topology_sibling_cpumask(cpu)) == 1) cpu_data(sibling).booted_cores--; } - for_each_cpu(sibling, cpu_sibling_mask(cpu)) - cpumask_clear_cpu(cpu, cpu_sibling_mask(sibling)); + for_each_cpu(sibling, topology_sibling_cpumask(cpu)) + cpumask_clear_cpu(cpu, topology_sibling_cpumask(sibling)); for_each_cpu(sibling, cpu_llc_shared_mask(cpu)) cpumask_clear_cpu(cpu, cpu_llc_shared_mask(sibling)); cpumask_clear(cpu_llc_shared_mask(cpu)); - cpumask_clear(cpu_sibling_mask(cpu)); - cpumask_clear(cpu_core_mask(cpu)); + cpumask_clear(topology_sibling_cpumask(cpu)); + cpumask_clear(topology_core_cpumask(cpu)); c->phys_proc_id = 0; c->cpu_core_id = 0; cpumask_clear_cpu(cpu, cpu_sibling_setup_mask); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index de379366f6d1..f5791927aa64 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -54,12 +54,13 @@ #include <asm/ftrace.h> #include <asm/traps.h> #include <asm/desc.h> -#include <asm/i387.h> -#include <asm/fpu-internal.h> +#include <asm/fpu/internal.h> #include <asm/mce.h> #include <asm/fixmap.h> #include <asm/mach_traps.h> #include <asm/alternative.h> +#include <asm/fpu/xstate.h> +#include <asm/trace/mpx.h> #include <asm/mpx.h> #ifdef CONFIG_X86_64 @@ -370,10 +371,8 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) dotraplinkage void do_bounds(struct pt_regs *regs, long error_code) { - struct task_struct *tsk = current; - struct xsave_struct *xsave_buf; enum ctx_state prev_state; - struct bndcsr *bndcsr; + const struct bndcsr *bndcsr; siginfo_t *info; prev_state = exception_enter(); @@ -392,15 +391,15 @@ dotraplinkage void do_bounds(struct pt_regs *regs, long error_code) /* * We need to look at BNDSTATUS to resolve this exception. - * It is not directly accessible, though, so we need to - * do an xsave and then pull it out of the xsave buffer. + * A NULL here might mean that it is in its 'init state', + * which is all zeros which indicates MPX was not + * responsible for the exception. */ - fpu_save_init(&tsk->thread.fpu); - xsave_buf = &(tsk->thread.fpu.state->xsave); - bndcsr = get_xsave_addr(xsave_buf, XSTATE_BNDCSR); + bndcsr = get_xsave_field_ptr(XSTATE_BNDCSR); if (!bndcsr) goto exit_trap; + trace_bounds_exception_mpx(bndcsr); /* * The error code field of the BNDSTATUS register communicates status * information of a bound range exception #BR or operation involving @@ -408,11 +407,11 @@ dotraplinkage void do_bounds(struct pt_regs *regs, long error_code) */ switch (bndcsr->bndstatus & MPX_BNDSTA_ERROR_CODE) { case 2: /* Bound directory has invalid entry. */ - if (mpx_handle_bd_fault(xsave_buf)) + if (mpx_handle_bd_fault()) goto exit_trap; break; /* Success, it was handled */ case 1: /* Bound violation. */ - info = mpx_generate_siginfo(regs, xsave_buf); + info = mpx_generate_siginfo(regs); if (IS_ERR(info)) { /* * We failed to decode the MPX instruction. Act as if @@ -708,8 +707,8 @@ NOKPROBE_SYMBOL(do_debug); static void math_error(struct pt_regs *regs, int error_code, int trapnr) { struct task_struct *task = current; + struct fpu *fpu = &task->thread.fpu; siginfo_t info; - unsigned short err; char *str = (trapnr == X86_TRAP_MF) ? "fpu exception" : "simd exception"; @@ -717,8 +716,7 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr) return; conditional_sti(regs); - if (!user_mode(regs)) - { + if (!user_mode(regs)) { if (!fixup_exception(regs)) { task->thread.error_code = error_code; task->thread.trap_nr = trapnr; @@ -730,62 +728,20 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr) /* * Save the info for the exception handler and clear the error. */ - unlazy_fpu(task); - task->thread.trap_nr = trapnr; + fpu__save(fpu); + + task->thread.trap_nr = trapnr; task->thread.error_code = error_code; - info.si_signo = SIGFPE; - info.si_errno = 0; - info.si_addr = (void __user *)uprobe_get_trap_addr(regs); - if (trapnr == X86_TRAP_MF) { - unsigned short cwd, swd; - /* - * (~cwd & swd) will mask out exceptions that are not set to unmasked - * status. 0x3f is the exception bits in these regs, 0x200 is the - * C1 reg you need in case of a stack fault, 0x040 is the stack - * fault bit. We should only be taking one exception at a time, - * so if this combination doesn't produce any single exception, - * then we have a bad program that isn't synchronizing its FPU usage - * and it will suffer the consequences since we won't be able to - * fully reproduce the context of the exception - */ - cwd = get_fpu_cwd(task); - swd = get_fpu_swd(task); + info.si_signo = SIGFPE; + info.si_errno = 0; + info.si_addr = (void __user *)uprobe_get_trap_addr(regs); - err = swd & ~cwd; - } else { - /* - * The SIMD FPU exceptions are handled a little differently, as there - * is only a single status/control register. Thus, to determine which - * unmasked exception was caught we must mask the exception mask bits - * at 0x1f80, and then use these to mask the exception bits at 0x3f. - */ - unsigned short mxcsr = get_fpu_mxcsr(task); - err = ~(mxcsr >> 7) & mxcsr; - } + info.si_code = fpu__exception_code(fpu, trapnr); - if (err & 0x001) { /* Invalid op */ - /* - * swd & 0x240 == 0x040: Stack Underflow - * swd & 0x240 == 0x240: Stack Overflow - * User must clear the SF bit (0x40) if set - */ - info.si_code = FPE_FLTINV; - } else if (err & 0x004) { /* Divide by Zero */ - info.si_code = FPE_FLTDIV; - } else if (err & 0x008) { /* Overflow */ - info.si_code = FPE_FLTOVF; - } else if (err & 0x012) { /* Denormal, Underflow */ - info.si_code = FPE_FLTUND; - } else if (err & 0x020) { /* Precision */ - info.si_code = FPE_FLTRES; - } else { - /* - * If we're using IRQ 13, or supposedly even some trap - * X86_TRAP_MF implementations, it's possible - * we get a spurious trap, which is not an error. - */ + /* Retry when we get spurious exceptions: */ + if (!info.si_code) return; - } + force_sig_info(SIGFPE, &info, task); } @@ -814,48 +770,6 @@ do_spurious_interrupt_bug(struct pt_regs *regs, long error_code) conditional_sti(regs); } -/* - * 'math_state_restore()' saves the current math information in the - * old math state array, and gets the new ones from the current task - * - * Careful.. There are problems with IBM-designed IRQ13 behaviour. - * Don't touch unless you *really* know how it works. - * - * Must be called with kernel preemption disabled (eg with local - * local interrupts as in the case of do_device_not_available). - */ -void math_state_restore(void) -{ - struct task_struct *tsk = current; - - if (!tsk_used_math(tsk)) { - local_irq_enable(); - /* - * does a slab alloc which can sleep - */ - if (init_fpu(tsk)) { - /* - * ran out of memory! - */ - do_group_exit(SIGKILL); - return; - } - local_irq_disable(); - } - - /* Avoid __kernel_fpu_begin() right after __thread_fpu_begin() */ - kernel_fpu_disable(); - __thread_fpu_begin(tsk); - if (unlikely(restore_fpu_checking(tsk))) { - fpu_reset_state(tsk); - force_sig_info(SIGSEGV, SEND_SIG_PRIV, tsk); - } else { - tsk->thread.fpu_counter++; - } - kernel_fpu_enable(); -} -EXPORT_SYMBOL_GPL(math_state_restore); - dotraplinkage void do_device_not_available(struct pt_regs *regs, long error_code) { @@ -876,7 +790,7 @@ do_device_not_available(struct pt_regs *regs, long error_code) return; } #endif - math_state_restore(); /* interrupts still off */ + fpu__restore(¤t->thread.fpu); /* interrupts still off */ #ifdef CONFIG_X86_32 conditional_sti(regs); #endif diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c index 26488487bc61..dd8d0791dfb5 100644 --- a/arch/x86/kernel/tsc_sync.c +++ b/arch/x86/kernel/tsc_sync.c @@ -113,7 +113,7 @@ static void check_tsc_warp(unsigned int timeout) */ static inline unsigned int loop_timeout(int cpu) { - return (cpumask_weight(cpu_core_mask(cpu)) > 1) ? 2 : 20; + return (cpumask_weight(topology_core_cpumask(cpu)) > 1) ? 2 : 20; } /* diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index 0b81ad67da07..66476244731e 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -29,6 +29,7 @@ #include <linux/kdebug.h> #include <asm/processor.h> #include <asm/insn.h> +#include <asm/mmu_context.h> /* Post-execution fixups. */ @@ -312,11 +313,6 @@ static int uprobe_init_insn(struct arch_uprobe *auprobe, struct insn *insn, bool } #ifdef CONFIG_X86_64 -static inline bool is_64bit_mm(struct mm_struct *mm) -{ - return !config_enabled(CONFIG_IA32_EMULATION) || - !(mm->context.ia32_compat == TIF_IA32); -} /* * If arch_uprobe->insn doesn't use rip-relative addressing, return * immediately. Otherwise, rewrite the instruction so that it accesses @@ -497,10 +493,6 @@ static void riprel_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) } } #else /* 32-bit: */ -static inline bool is_64bit_mm(struct mm_struct *mm) -{ - return false; -} /* * No RIP-relative addressing on 32-bit */ diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c index 37d8fa4438f0..a0695be19864 100644 --- a/arch/x86/kernel/x8664_ksyms_64.c +++ b/arch/x86/kernel/x8664_ksyms_64.c @@ -75,7 +75,5 @@ EXPORT_SYMBOL(native_load_gs_index); #ifdef CONFIG_PREEMPT EXPORT_SYMBOL(___preempt_schedule); -#ifdef CONFIG_CONTEXT_TRACKING -EXPORT_SYMBOL(___preempt_schedule_context); -#endif +EXPORT_SYMBOL(___preempt_schedule_notrace); #endif diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c deleted file mode 100644 index 87a815b85f3e..000000000000 --- a/arch/x86/kernel/xsave.c +++ /dev/null @@ -1,724 +0,0 @@ -/* - * xsave/xrstor support. - * - * Author: Suresh Siddha <suresh.b.siddha@intel.com> - */ - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include <linux/bootmem.h> -#include <linux/compat.h> -#include <linux/cpu.h> -#include <asm/i387.h> -#include <asm/fpu-internal.h> -#include <asm/sigframe.h> -#include <asm/tlbflush.h> -#include <asm/xcr.h> - -/* - * Supported feature mask by the CPU and the kernel. - */ -u64 pcntxt_mask; - -/* - * Represents init state for the supported extended state. - */ -struct xsave_struct *init_xstate_buf; - -static struct _fpx_sw_bytes fx_sw_reserved, fx_sw_reserved_ia32; -static unsigned int *xstate_offsets, *xstate_sizes; -static unsigned int xstate_comp_offsets[sizeof(pcntxt_mask)*8]; -static unsigned int xstate_features; - -/* - * If a processor implementation discern that a processor state component is - * in its initialized state it may modify the corresponding bit in the - * xsave_hdr.xstate_bv as '0', with out modifying the corresponding memory - * layout in the case of xsaveopt. While presenting the xstate information to - * the user, we always ensure that the memory layout of a feature will be in - * the init state if the corresponding header bit is zero. This is to ensure - * that the user doesn't see some stale state in the memory layout during - * signal handling, debugging etc. - */ -void __sanitize_i387_state(struct task_struct *tsk) -{ - struct i387_fxsave_struct *fx = &tsk->thread.fpu.state->fxsave; - int feature_bit = 0x2; - u64 xstate_bv; - - if (!fx) - return; - - xstate_bv = tsk->thread.fpu.state->xsave.xsave_hdr.xstate_bv; - - /* - * None of the feature bits are in init state. So nothing else - * to do for us, as the memory layout is up to date. - */ - if ((xstate_bv & pcntxt_mask) == pcntxt_mask) - return; - - /* - * FP is in init state - */ - if (!(xstate_bv & XSTATE_FP)) { - fx->cwd = 0x37f; - fx->swd = 0; - fx->twd = 0; - fx->fop = 0; - fx->rip = 0; - fx->rdp = 0; - memset(&fx->st_space[0], 0, 128); - } - - /* - * SSE is in init state - */ - if (!(xstate_bv & XSTATE_SSE)) - memset(&fx->xmm_space[0], 0, 256); - - xstate_bv = (pcntxt_mask & ~xstate_bv) >> 2; - - /* - * Update all the other memory layouts for which the corresponding - * header bit is in the init state. - */ - while (xstate_bv) { - if (xstate_bv & 0x1) { - int offset = xstate_offsets[feature_bit]; - int size = xstate_sizes[feature_bit]; - - memcpy(((void *) fx) + offset, - ((void *) init_xstate_buf) + offset, - size); - } - - xstate_bv >>= 1; - feature_bit++; - } -} - -/* - * Check for the presence of extended state information in the - * user fpstate pointer in the sigcontext. - */ -static inline int check_for_xstate(struct i387_fxsave_struct __user *buf, - void __user *fpstate, - struct _fpx_sw_bytes *fx_sw) -{ - int min_xstate_size = sizeof(struct i387_fxsave_struct) + - sizeof(struct xsave_hdr_struct); - unsigned int magic2; - - if (__copy_from_user(fx_sw, &buf->sw_reserved[0], sizeof(*fx_sw))) - return -1; - - /* Check for the first magic field and other error scenarios. */ - if (fx_sw->magic1 != FP_XSTATE_MAGIC1 || - fx_sw->xstate_size < min_xstate_size || - fx_sw->xstate_size > xstate_size || - fx_sw->xstate_size > fx_sw->extended_size) - return -1; - - /* - * Check for the presence of second magic word at the end of memory - * layout. This detects the case where the user just copied the legacy - * fpstate layout with out copying the extended state information - * in the memory layout. - */ - if (__get_user(magic2, (__u32 __user *)(fpstate + fx_sw->xstate_size)) - || magic2 != FP_XSTATE_MAGIC2) - return -1; - - return 0; -} - -/* - * Signal frame handlers. - */ -static inline int save_fsave_header(struct task_struct *tsk, void __user *buf) -{ - if (use_fxsr()) { - struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave; - struct user_i387_ia32_struct env; - struct _fpstate_ia32 __user *fp = buf; - - convert_from_fxsr(&env, tsk); - - if (__copy_to_user(buf, &env, sizeof(env)) || - __put_user(xsave->i387.swd, &fp->status) || - __put_user(X86_FXSR_MAGIC, &fp->magic)) - return -1; - } else { - struct i387_fsave_struct __user *fp = buf; - u32 swd; - if (__get_user(swd, &fp->swd) || __put_user(swd, &fp->status)) - return -1; - } - - return 0; -} - -static inline int save_xstate_epilog(void __user *buf, int ia32_frame) -{ - struct xsave_struct __user *x = buf; - struct _fpx_sw_bytes *sw_bytes; - u32 xstate_bv; - int err; - - /* Setup the bytes not touched by the [f]xsave and reserved for SW. */ - sw_bytes = ia32_frame ? &fx_sw_reserved_ia32 : &fx_sw_reserved; - err = __copy_to_user(&x->i387.sw_reserved, sw_bytes, sizeof(*sw_bytes)); - - if (!use_xsave()) - return err; - - err |= __put_user(FP_XSTATE_MAGIC2, (__u32 *)(buf + xstate_size)); - - /* - * Read the xstate_bv which we copied (directly from the cpu or - * from the state in task struct) to the user buffers. - */ - err |= __get_user(xstate_bv, (__u32 *)&x->xsave_hdr.xstate_bv); - - /* - * For legacy compatible, we always set FP/SSE bits in the bit - * vector while saving the state to the user context. This will - * enable us capturing any changes(during sigreturn) to - * the FP/SSE bits by the legacy applications which don't touch - * xstate_bv in the xsave header. - * - * xsave aware apps can change the xstate_bv in the xsave - * header as well as change any contents in the memory layout. - * xrestore as part of sigreturn will capture all the changes. - */ - xstate_bv |= XSTATE_FPSSE; - - err |= __put_user(xstate_bv, (__u32 *)&x->xsave_hdr.xstate_bv); - - return err; -} - -static inline int save_user_xstate(struct xsave_struct __user *buf) -{ - int err; - - if (use_xsave()) - err = xsave_user(buf); - else if (use_fxsr()) - err = fxsave_user((struct i387_fxsave_struct __user *) buf); - else - err = fsave_user((struct i387_fsave_struct __user *) buf); - - if (unlikely(err) && __clear_user(buf, xstate_size)) - err = -EFAULT; - return err; -} - -/* - * Save the fpu, extended register state to the user signal frame. - * - * 'buf_fx' is the 64-byte aligned pointer at which the [f|fx|x]save - * state is copied. - * 'buf' points to the 'buf_fx' or to the fsave header followed by 'buf_fx'. - * - * buf == buf_fx for 64-bit frames and 32-bit fsave frame. - * buf != buf_fx for 32-bit frames with fxstate. - * - * If the fpu, extended register state is live, save the state directly - * to the user frame pointed by the aligned pointer 'buf_fx'. Otherwise, - * copy the thread's fpu state to the user frame starting at 'buf_fx'. - * - * If this is a 32-bit frame with fxstate, put a fsave header before - * the aligned state at 'buf_fx'. - * - * For [f]xsave state, update the SW reserved fields in the [f]xsave frame - * indicating the absence/presence of the extended state to the user. - */ -int save_xstate_sig(void __user *buf, void __user *buf_fx, int size) -{ - struct xsave_struct *xsave = ¤t->thread.fpu.state->xsave; - struct task_struct *tsk = current; - int ia32_fxstate = (buf != buf_fx); - - ia32_fxstate &= (config_enabled(CONFIG_X86_32) || - config_enabled(CONFIG_IA32_EMULATION)); - - if (!access_ok(VERIFY_WRITE, buf, size)) - return -EACCES; - - if (!static_cpu_has(X86_FEATURE_FPU)) - return fpregs_soft_get(current, NULL, 0, - sizeof(struct user_i387_ia32_struct), NULL, - (struct _fpstate_ia32 __user *) buf) ? -1 : 1; - - if (user_has_fpu()) { - /* Save the live register state to the user directly. */ - if (save_user_xstate(buf_fx)) - return -1; - /* Update the thread's fxstate to save the fsave header. */ - if (ia32_fxstate) - fpu_fxsave(&tsk->thread.fpu); - } else { - sanitize_i387_state(tsk); - if (__copy_to_user(buf_fx, xsave, xstate_size)) - return -1; - } - - /* Save the fsave header for the 32-bit frames. */ - if ((ia32_fxstate || !use_fxsr()) && save_fsave_header(tsk, buf)) - return -1; - - if (use_fxsr() && save_xstate_epilog(buf_fx, ia32_fxstate)) - return -1; - - return 0; -} - -static inline void -sanitize_restored_xstate(struct task_struct *tsk, - struct user_i387_ia32_struct *ia32_env, - u64 xstate_bv, int fx_only) -{ - struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave; - struct xsave_hdr_struct *xsave_hdr = &xsave->xsave_hdr; - - if (use_xsave()) { - /* These bits must be zero. */ - memset(xsave_hdr->reserved, 0, 48); - - /* - * Init the state that is not present in the memory - * layout and not enabled by the OS. - */ - if (fx_only) - xsave_hdr->xstate_bv = XSTATE_FPSSE; - else - xsave_hdr->xstate_bv &= (pcntxt_mask & xstate_bv); - } - - if (use_fxsr()) { - /* - * mscsr reserved bits must be masked to zero for security - * reasons. - */ - xsave->i387.mxcsr &= mxcsr_feature_mask; - - convert_to_fxsr(tsk, ia32_env); - } -} - -/* - * Restore the extended state if present. Otherwise, restore the FP/SSE state. - */ -static inline int restore_user_xstate(void __user *buf, u64 xbv, int fx_only) -{ - if (use_xsave()) { - if ((unsigned long)buf % 64 || fx_only) { - u64 init_bv = pcntxt_mask & ~XSTATE_FPSSE; - xrstor_state(init_xstate_buf, init_bv); - return fxrstor_user(buf); - } else { - u64 init_bv = pcntxt_mask & ~xbv; - if (unlikely(init_bv)) - xrstor_state(init_xstate_buf, init_bv); - return xrestore_user(buf, xbv); - } - } else if (use_fxsr()) { - return fxrstor_user(buf); - } else - return frstor_user(buf); -} - -int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size) -{ - int ia32_fxstate = (buf != buf_fx); - struct task_struct *tsk = current; - int state_size = xstate_size; - u64 xstate_bv = 0; - int fx_only = 0; - - ia32_fxstate &= (config_enabled(CONFIG_X86_32) || - config_enabled(CONFIG_IA32_EMULATION)); - - if (!buf) { - fpu_reset_state(tsk); - return 0; - } - - if (!access_ok(VERIFY_READ, buf, size)) - return -EACCES; - - if (!used_math() && init_fpu(tsk)) - return -1; - - if (!static_cpu_has(X86_FEATURE_FPU)) - return fpregs_soft_set(current, NULL, - 0, sizeof(struct user_i387_ia32_struct), - NULL, buf) != 0; - - if (use_xsave()) { - struct _fpx_sw_bytes fx_sw_user; - if (unlikely(check_for_xstate(buf_fx, buf_fx, &fx_sw_user))) { - /* - * Couldn't find the extended state information in the - * memory layout. Restore just the FP/SSE and init all - * the other extended state. - */ - state_size = sizeof(struct i387_fxsave_struct); - fx_only = 1; - } else { - state_size = fx_sw_user.xstate_size; - xstate_bv = fx_sw_user.xstate_bv; - } - } - - if (ia32_fxstate) { - /* - * For 32-bit frames with fxstate, copy the user state to the - * thread's fpu state, reconstruct fxstate from the fsave - * header. Sanitize the copied state etc. - */ - struct fpu *fpu = &tsk->thread.fpu; - struct user_i387_ia32_struct env; - int err = 0; - - /* - * Drop the current fpu which clears used_math(). This ensures - * that any context-switch during the copy of the new state, - * avoids the intermediate state from getting restored/saved. - * Thus avoiding the new restored state from getting corrupted. - * We will be ready to restore/save the state only after - * set_used_math() is again set. - */ - drop_fpu(tsk); - - if (__copy_from_user(&fpu->state->xsave, buf_fx, state_size) || - __copy_from_user(&env, buf, sizeof(env))) { - fpu_finit(fpu); - err = -1; - } else { - sanitize_restored_xstate(tsk, &env, xstate_bv, fx_only); - } - - set_used_math(); - if (use_eager_fpu()) { - preempt_disable(); - math_state_restore(); - preempt_enable(); - } - - return err; - } else { - /* - * For 64-bit frames and 32-bit fsave frames, restore the user - * state to the registers directly (with exceptions handled). - */ - user_fpu_begin(); - if (restore_user_xstate(buf_fx, xstate_bv, fx_only)) { - fpu_reset_state(tsk); - return -1; - } - } - - return 0; -} - -/* - * Prepare the SW reserved portion of the fxsave memory layout, indicating - * the presence of the extended state information in the memory layout - * pointed by the fpstate pointer in the sigcontext. - * This will be saved when ever the FP and extended state context is - * saved on the user stack during the signal handler delivery to the user. - */ -static void prepare_fx_sw_frame(void) -{ - int fsave_header_size = sizeof(struct i387_fsave_struct); - int size = xstate_size + FP_XSTATE_MAGIC2_SIZE; - - if (config_enabled(CONFIG_X86_32)) - size += fsave_header_size; - - fx_sw_reserved.magic1 = FP_XSTATE_MAGIC1; - fx_sw_reserved.extended_size = size; - fx_sw_reserved.xstate_bv = pcntxt_mask; - fx_sw_reserved.xstate_size = xstate_size; - - if (config_enabled(CONFIG_IA32_EMULATION)) { - fx_sw_reserved_ia32 = fx_sw_reserved; - fx_sw_reserved_ia32.extended_size += fsave_header_size; - } -} - -/* - * Enable the extended processor state save/restore feature - */ -static inline void xstate_enable(void) -{ - cr4_set_bits(X86_CR4_OSXSAVE); - xsetbv(XCR_XFEATURE_ENABLED_MASK, pcntxt_mask); -} - -/* - * Record the offsets and sizes of different state managed by the xsave - * memory layout. - */ -static void __init setup_xstate_features(void) -{ - int eax, ebx, ecx, edx, leaf = 0x2; - - xstate_features = fls64(pcntxt_mask); - xstate_offsets = alloc_bootmem(xstate_features * sizeof(int)); - xstate_sizes = alloc_bootmem(xstate_features * sizeof(int)); - - do { - cpuid_count(XSTATE_CPUID, leaf, &eax, &ebx, &ecx, &edx); - - if (eax == 0) - break; - - xstate_offsets[leaf] = ebx; - xstate_sizes[leaf] = eax; - - leaf++; - } while (1); -} - -/* - * This function sets up offsets and sizes of all extended states in - * xsave area. This supports both standard format and compacted format - * of the xsave aread. - * - * Input: void - * Output: void - */ -void setup_xstate_comp(void) -{ - unsigned int xstate_comp_sizes[sizeof(pcntxt_mask)*8]; - int i; - - /* - * The FP xstates and SSE xstates are legacy states. They are always - * in the fixed offsets in the xsave area in either compacted form - * or standard form. - */ - xstate_comp_offsets[0] = 0; - xstate_comp_offsets[1] = offsetof(struct i387_fxsave_struct, xmm_space); - - if (!cpu_has_xsaves) { - for (i = 2; i < xstate_features; i++) { - if (test_bit(i, (unsigned long *)&pcntxt_mask)) { - xstate_comp_offsets[i] = xstate_offsets[i]; - xstate_comp_sizes[i] = xstate_sizes[i]; - } - } - return; - } - - xstate_comp_offsets[2] = FXSAVE_SIZE + XSAVE_HDR_SIZE; - - for (i = 2; i < xstate_features; i++) { - if (test_bit(i, (unsigned long *)&pcntxt_mask)) - xstate_comp_sizes[i] = xstate_sizes[i]; - else - xstate_comp_sizes[i] = 0; - - if (i > 2) - xstate_comp_offsets[i] = xstate_comp_offsets[i-1] - + xstate_comp_sizes[i-1]; - - } -} - -/* - * setup the xstate image representing the init state - */ -static void __init setup_init_fpu_buf(void) -{ - /* - * Setup init_xstate_buf to represent the init state of - * all the features managed by the xsave - */ - init_xstate_buf = alloc_bootmem_align(xstate_size, - __alignof__(struct xsave_struct)); - fx_finit(&init_xstate_buf->i387); - - if (!cpu_has_xsave) - return; - - setup_xstate_features(); - - if (cpu_has_xsaves) { - init_xstate_buf->xsave_hdr.xcomp_bv = - (u64)1 << 63 | pcntxt_mask; - init_xstate_buf->xsave_hdr.xstate_bv = pcntxt_mask; - } - - /* - * Init all the features state with header_bv being 0x0 - */ - xrstor_state_booting(init_xstate_buf, -1); - /* - * Dump the init state again. This is to identify the init state - * of any feature which is not represented by all zero's. - */ - xsave_state_booting(init_xstate_buf, -1); -} - -static enum { AUTO, ENABLE, DISABLE } eagerfpu = AUTO; -static int __init eager_fpu_setup(char *s) -{ - if (!strcmp(s, "on")) - eagerfpu = ENABLE; - else if (!strcmp(s, "off")) - eagerfpu = DISABLE; - else if (!strcmp(s, "auto")) - eagerfpu = AUTO; - return 1; -} -__setup("eagerfpu=", eager_fpu_setup); - - -/* - * Calculate total size of enabled xstates in XCR0/pcntxt_mask. - */ -static void __init init_xstate_size(void) -{ - unsigned int eax, ebx, ecx, edx; - int i; - - if (!cpu_has_xsaves) { - cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx); - xstate_size = ebx; - return; - } - - xstate_size = FXSAVE_SIZE + XSAVE_HDR_SIZE; - for (i = 2; i < 64; i++) { - if (test_bit(i, (unsigned long *)&pcntxt_mask)) { - cpuid_count(XSTATE_CPUID, i, &eax, &ebx, &ecx, &edx); - xstate_size += eax; - } - } -} - -/* - * Enable and initialize the xsave feature. - */ -static void __init xstate_enable_boot_cpu(void) -{ - unsigned int eax, ebx, ecx, edx; - - if (boot_cpu_data.cpuid_level < XSTATE_CPUID) { - WARN(1, KERN_ERR "XSTATE_CPUID missing\n"); - return; - } - - cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx); - pcntxt_mask = eax + ((u64)edx << 32); - - if ((pcntxt_mask & XSTATE_FPSSE) != XSTATE_FPSSE) { - pr_err("FP/SSE not shown under xsave features 0x%llx\n", - pcntxt_mask); - BUG(); - } - - /* - * Support only the state known to OS. - */ - pcntxt_mask = pcntxt_mask & XCNTXT_MASK; - - xstate_enable(); - - /* - * Recompute the context size for enabled features - */ - init_xstate_size(); - - update_regset_xstate_info(xstate_size, pcntxt_mask); - prepare_fx_sw_frame(); - setup_init_fpu_buf(); - - /* Auto enable eagerfpu for xsaveopt */ - if (cpu_has_xsaveopt && eagerfpu != DISABLE) - eagerfpu = ENABLE; - - if (pcntxt_mask & XSTATE_EAGER) { - if (eagerfpu == DISABLE) { - pr_err("eagerfpu not present, disabling some xstate features: 0x%llx\n", - pcntxt_mask & XSTATE_EAGER); - pcntxt_mask &= ~XSTATE_EAGER; - } else { - eagerfpu = ENABLE; - } - } - - pr_info("enabled xstate_bv 0x%llx, cntxt size 0x%x using %s\n", - pcntxt_mask, xstate_size, - cpu_has_xsaves ? "compacted form" : "standard form"); -} - -/* - * For the very first instance, this calls xstate_enable_boot_cpu(); - * for all subsequent instances, this calls xstate_enable(). - * - * This is somewhat obfuscated due to the lack of powerful enough - * overrides for the section checks. - */ -void xsave_init(void) -{ - static __refdata void (*next_func)(void) = xstate_enable_boot_cpu; - void (*this_func)(void); - - if (!cpu_has_xsave) - return; - - this_func = next_func; - next_func = xstate_enable; - this_func(); -} - -/* - * setup_init_fpu_buf() is __init and it is OK to call it here because - * init_xstate_buf will be unset only once during boot. - */ -void __init_refok eager_fpu_init(void) -{ - WARN_ON(used_math()); - current_thread_info()->status = 0; - - if (eagerfpu == ENABLE) - setup_force_cpu_cap(X86_FEATURE_EAGER_FPU); - - if (!cpu_has_eager_fpu) { - stts(); - return; - } - - if (!init_xstate_buf) - setup_init_fpu_buf(); -} - -/* - * Given the xsave area and a state inside, this function returns the - * address of the state. - * - * This is the API that is called to get xstate address in either - * standard format or compacted format of xsave area. - * - * Inputs: - * xsave: base address of the xsave area; - * xstate: state which is defined in xsave.h (e.g. XSTATE_FP, XSTATE_SSE, - * etc.) - * Output: - * address of the state in the xsave area. - */ -void *get_xsave_addr(struct xsave_struct *xsave, int xstate) -{ - int feature = fls64(xstate) - 1; - if (!test_bit(feature, (unsigned long *)&pcntxt_mask)) - return NULL; - - return (void *)xsave + xstate_comp_offsets[feature]; -} -EXPORT_SYMBOL_GPL(get_xsave_addr); diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 1d08ad3582d0..9f705e618af5 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -16,10 +16,8 @@ #include <linux/module.h> #include <linux/vmalloc.h> #include <linux/uaccess.h> -#include <asm/i387.h> /* For use_eager_fpu. Ugh! */ -#include <asm/fpu-internal.h> /* For use_eager_fpu. Ugh! */ #include <asm/user.h> -#include <asm/xsave.h> +#include <asm/fpu/xstate.h> #include "cpuid.h" #include "lapic.h" #include "mmu.h" diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 629af0f1c5c4..4c7deb4f78a1 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1090,6 +1090,17 @@ static void update_divide_count(struct kvm_lapic *apic) apic->divide_count); } +static void apic_update_lvtt(struct kvm_lapic *apic) +{ + u32 timer_mode = kvm_apic_get_reg(apic, APIC_LVTT) & + apic->lapic_timer.timer_mode_mask; + + if (apic->lapic_timer.timer_mode != timer_mode) { + apic->lapic_timer.timer_mode = timer_mode; + hrtimer_cancel(&apic->lapic_timer.timer); + } +} + static void apic_timer_expired(struct kvm_lapic *apic) { struct kvm_vcpu *vcpu = apic->vcpu; @@ -1298,6 +1309,7 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) apic_set_reg(apic, APIC_LVTT + 0x10 * i, lvt_val | APIC_LVT_MASKED); } + apic_update_lvtt(apic); atomic_set(&apic->lapic_timer.pending, 0); } @@ -1330,20 +1342,13 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) break; - case APIC_LVTT: { - u32 timer_mode = val & apic->lapic_timer.timer_mode_mask; - - if (apic->lapic_timer.timer_mode != timer_mode) { - apic->lapic_timer.timer_mode = timer_mode; - hrtimer_cancel(&apic->lapic_timer.timer); - } - + case APIC_LVTT: if (!kvm_apic_sw_enabled(apic)) val |= APIC_LVT_MASKED; val &= (apic_lvt_mask[0] | apic->lapic_timer.timer_mode_mask); apic_set_reg(apic, APIC_LVTT, val); + apic_update_lvtt(apic); break; - } case APIC_TMICT: if (apic_lvtt_tscdeadline(apic)) @@ -1576,7 +1581,7 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu) for (i = 0; i < APIC_LVT_NUM; i++) apic_set_reg(apic, APIC_LVTT + 0x10 * i, APIC_LVT_MASKED); - apic->lapic_timer.timer_mode = 0; + apic_update_lvtt(apic); apic_set_reg(apic, APIC_LVT0, SET_APIC_DELIVERY_MODE(0, APIC_MODE_EXTINT)); @@ -1802,6 +1807,7 @@ void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu, apic_update_ppr(apic); hrtimer_cancel(&apic->lapic_timer.timer); + apic_update_lvtt(apic); update_divide_count(apic); start_apic_timer(apic); apic->irr_pending = true; diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 44a7d2515497..b73337634214 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -4215,13 +4215,13 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, u64 entry, gentry, *spte; int npte; bool remote_flush, local_flush, zap_page; - union kvm_mmu_page_role mask = (union kvm_mmu_page_role) { - .cr0_wp = 1, - .cr4_pae = 1, - .nxe = 1, - .smep_andnot_wp = 1, - .smap_andnot_wp = 1, - }; + union kvm_mmu_page_role mask = { }; + + mask.cr0_wp = 1; + mask.cr4_pae = 1; + mask.nxe = 1; + mask.smep_andnot_wp = 1; + mask.smap_andnot_wp = 1; /* * If we don't have indirect shadow pages, it means no page is diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 2d73807f0d31..e11dd59398f1 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -40,8 +40,7 @@ #include <asm/vmx.h> #include <asm/virtext.h> #include <asm/mce.h> -#include <asm/i387.h> -#include <asm/xcr.h> +#include <asm/fpu/internal.h> #include <asm/perf_event.h> #include <asm/debugreg.h> #include <asm/kexec.h> @@ -1883,7 +1882,7 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx) * If the FPU is not active (through the host task or * the guest vcpu), then restore the cr0.TS bit. */ - if (!user_has_fpu() && !vmx->vcpu.guest_fpu_loaded) + if (!fpregs_active() && !vmx->vcpu.guest_fpu_loaded) stts(); load_gdt(this_cpu_ptr(&host_gdt)); } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index ea306adbbc13..26eaeb522cab 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -59,9 +59,8 @@ #include <asm/desc.h> #include <asm/mtrr.h> #include <asm/mce.h> -#include <asm/i387.h> -#include <asm/fpu-internal.h> /* Ugh! */ -#include <asm/xcr.h> +#include <linux/kernel_stat.h> +#include <asm/fpu/internal.h> /* Ugh! */ #include <asm/pvclock.h> #include <asm/div64.h> @@ -3194,8 +3193,8 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu, static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu) { - struct xsave_struct *xsave = &vcpu->arch.guest_fpu.state->xsave; - u64 xstate_bv = xsave->xsave_hdr.xstate_bv; + struct xregs_state *xsave = &vcpu->arch.guest_fpu.state.xsave; + u64 xstate_bv = xsave->header.xfeatures; u64 valid; /* @@ -3230,7 +3229,7 @@ static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu) static void load_xsave(struct kvm_vcpu *vcpu, u8 *src) { - struct xsave_struct *xsave = &vcpu->arch.guest_fpu.state->xsave; + struct xregs_state *xsave = &vcpu->arch.guest_fpu.state.xsave; u64 xstate_bv = *(u64 *)(src + XSAVE_HDR_OFFSET); u64 valid; @@ -3241,9 +3240,9 @@ static void load_xsave(struct kvm_vcpu *vcpu, u8 *src) memcpy(xsave, src, XSAVE_HDR_OFFSET); /* Set XSTATE_BV and possibly XCOMP_BV. */ - xsave->xsave_hdr.xstate_bv = xstate_bv; + xsave->header.xfeatures = xstate_bv; if (cpu_has_xsaves) - xsave->xsave_hdr.xcomp_bv = host_xcr0 | XSTATE_COMPACTION_ENABLED; + xsave->header.xcomp_bv = host_xcr0 | XSTATE_COMPACTION_ENABLED; /* * Copy each region from the non-compacted offset to the @@ -3275,8 +3274,8 @@ static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu, fill_xsave((u8 *) guest_xsave->region, vcpu); } else { memcpy(guest_xsave->region, - &vcpu->arch.guest_fpu.state->fxsave, - sizeof(struct i387_fxsave_struct)); + &vcpu->arch.guest_fpu.state.fxsave, + sizeof(struct fxregs_state)); *(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)] = XSTATE_FPSSE; } @@ -3300,8 +3299,8 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu, } else { if (xstate_bv & ~XSTATE_FPSSE) return -EINVAL; - memcpy(&vcpu->arch.guest_fpu.state->fxsave, - guest_xsave->region, sizeof(struct i387_fxsave_struct)); + memcpy(&vcpu->arch.guest_fpu.state.fxsave, + guest_xsave->region, sizeof(struct fxregs_state)); } return 0; } @@ -6597,11 +6596,11 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu) int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { + struct fpu *fpu = ¤t->thread.fpu; int r; sigset_t sigsaved; - if (!tsk_used_math(current) && init_fpu(current)) - return -ENOMEM; + fpu__activate_curr(fpu); if (vcpu->sigset_active) sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved); @@ -6971,8 +6970,8 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) { - struct i387_fxsave_struct *fxsave = - &vcpu->arch.guest_fpu.state->fxsave; + struct fxregs_state *fxsave = + &vcpu->arch.guest_fpu.state.fxsave; memcpy(fpu->fpr, fxsave->st_space, 128); fpu->fcw = fxsave->cwd; @@ -6988,8 +6987,8 @@ int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) { - struct i387_fxsave_struct *fxsave = - &vcpu->arch.guest_fpu.state->fxsave; + struct fxregs_state *fxsave = + &vcpu->arch.guest_fpu.state.fxsave; memcpy(fxsave->st_space, fpu->fpr, 128); fxsave->cwd = fpu->fcw; @@ -7003,17 +7002,11 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) return 0; } -int fx_init(struct kvm_vcpu *vcpu) +static void fx_init(struct kvm_vcpu *vcpu) { - int err; - - err = fpu_alloc(&vcpu->arch.guest_fpu); - if (err) - return err; - - fpu_finit(&vcpu->arch.guest_fpu); + fpstate_init(&vcpu->arch.guest_fpu.state); if (cpu_has_xsaves) - vcpu->arch.guest_fpu.state->xsave.xsave_hdr.xcomp_bv = + vcpu->arch.guest_fpu.state.xsave.header.xcomp_bv = host_xcr0 | XSTATE_COMPACTION_ENABLED; /* @@ -7022,14 +7015,6 @@ int fx_init(struct kvm_vcpu *vcpu) vcpu->arch.xcr0 = XSTATE_FP; vcpu->arch.cr0 |= X86_CR0_ET; - - return 0; -} -EXPORT_SYMBOL_GPL(fx_init); - -static void fx_free(struct kvm_vcpu *vcpu) -{ - fpu_free(&vcpu->arch.guest_fpu); } void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) @@ -7045,7 +7030,7 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) kvm_put_guest_xcr0(vcpu); vcpu->guest_fpu_loaded = 1; __kernel_fpu_begin(); - fpu_restore_checking(&vcpu->arch.guest_fpu); + __copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state); trace_kvm_fpu(1); } @@ -7057,7 +7042,7 @@ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) return; vcpu->guest_fpu_loaded = 0; - fpu_save_init(&vcpu->arch.guest_fpu); + copy_fpregs_to_fpstate(&vcpu->arch.guest_fpu); __kernel_fpu_end(); ++vcpu->stat.fpu_reload; if (!vcpu->arch.eager_fpu) @@ -7071,7 +7056,6 @@ void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) kvmclock_reset(vcpu); free_cpumask_var(vcpu->arch.wbinvd_dirty_mask); - fx_free(vcpu); kvm_x86_ops->vcpu_free(vcpu); } @@ -7137,7 +7121,6 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) kvm_mmu_unload(vcpu); vcpu_put(vcpu); - fx_free(vcpu); kvm_x86_ops->vcpu_free(vcpu); } @@ -7363,9 +7346,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) goto fail_free_mce_banks; } - r = fx_init(vcpu); - if (r) - goto fail_free_wbinvd_dirty_mask; + fx_init(vcpu); vcpu->arch.ia32_tsc_adjust_msr = 0x0; vcpu->arch.pv_time_enabled = false; @@ -7379,8 +7360,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) kvm_pmu_init(vcpu); return 0; -fail_free_wbinvd_dirty_mask: - free_cpumask_var(vcpu->arch.wbinvd_dirty_mask); + fail_free_mce_banks: kfree(vcpu->arch.mce_banks); fail_free_lapic: diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index cab9aaa7802c..f2dc08c003eb 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -70,7 +70,7 @@ #include <asm/e820.h> #include <asm/mce.h> #include <asm/io.h> -#include <asm/i387.h> +#include <asm/fpu/api.h> #include <asm/stackprotector.h> #include <asm/reboot.h> /* for struct machine_ops */ #include <asm/kvm_para.h> diff --git a/arch/x86/lib/mmx_32.c b/arch/x86/lib/mmx_32.c index c9f2d9ba8dd8..e5e3ed8dc079 100644 --- a/arch/x86/lib/mmx_32.c +++ b/arch/x86/lib/mmx_32.c @@ -22,7 +22,7 @@ #include <linux/sched.h> #include <linux/types.h> -#include <asm/i387.h> +#include <asm/fpu/api.h> #include <asm/asm.h> void *_mmx_memcpy(void *to, const void *from, size_t len) diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c index e2f5e21c03b3..91d93b95bd86 100644 --- a/arch/x86/lib/usercopy_32.c +++ b/arch/x86/lib/usercopy_32.c @@ -647,7 +647,8 @@ EXPORT_SYMBOL(__copy_from_user_ll_nocache_nozero); * @from: Source address, in kernel space. * @n: Number of bytes to copy. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * Copy data from kernel space to user space. * @@ -668,7 +669,8 @@ EXPORT_SYMBOL(_copy_to_user); * @from: Source address, in user space. * @n: Number of bytes to copy. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * Copy data from user space to kernel space. * diff --git a/arch/x86/math-emu/fpu_aux.c b/arch/x86/math-emu/fpu_aux.c index dc8adad10a2f..dd76a05729b0 100644 --- a/arch/x86/math-emu/fpu_aux.c +++ b/arch/x86/math-emu/fpu_aux.c @@ -30,7 +30,7 @@ static void fclex(void) } /* Needs to be externally visible */ -void finit_soft_fpu(struct i387_soft_struct *soft) +void fpstate_init_soft(struct swregs_state *soft) { struct address *oaddr, *iaddr; memset(soft, 0, sizeof(*soft)); @@ -52,7 +52,7 @@ void finit_soft_fpu(struct i387_soft_struct *soft) void finit(void) { - finit_soft_fpu(¤t->thread.fpu.state->soft); + fpstate_init_soft(¤t->thread.fpu.state.soft); } /* diff --git a/arch/x86/math-emu/fpu_entry.c b/arch/x86/math-emu/fpu_entry.c index 9b868124128d..f37e84ab49f3 100644 --- a/arch/x86/math-emu/fpu_entry.c +++ b/arch/x86/math-emu/fpu_entry.c @@ -31,7 +31,7 @@ #include <asm/traps.h> #include <asm/desc.h> #include <asm/user.h> -#include <asm/i387.h> +#include <asm/fpu/internal.h> #include "fpu_system.h" #include "fpu_emu.h" @@ -147,13 +147,9 @@ void math_emulate(struct math_emu_info *info) unsigned long code_base = 0; unsigned long code_limit = 0; /* Initialized to stop compiler warnings */ struct desc_struct code_descriptor; + struct fpu *fpu = ¤t->thread.fpu; - if (!used_math()) { - if (init_fpu(current)) { - do_group_exit(SIGKILL); - return; - } - } + fpu__activate_curr(fpu); #ifdef RE_ENTRANT_CHECKING if (emulating) { @@ -673,7 +669,7 @@ void math_abort(struct math_emu_info *info, unsigned int signal) #endif /* PARANOID */ } -#define S387 ((struct i387_soft_struct *)s387) +#define S387 ((struct swregs_state *)s387) #define sstatus_word() \ ((S387->swd & ~SW_Top & 0xffff) | ((S387->ftop << SW_Top_Shift) & SW_Top)) @@ -682,14 +678,14 @@ int fpregs_soft_set(struct task_struct *target, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { - struct i387_soft_struct *s387 = &target->thread.fpu.state->soft; + struct swregs_state *s387 = &target->thread.fpu.state.soft; void *space = s387->st_space; int ret; int offset, other, i, tags, regnr, tag, newtop; RE_ENTRANT_CHECK_OFF; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, s387, 0, - offsetof(struct i387_soft_struct, st_space)); + offsetof(struct swregs_state, st_space)); RE_ENTRANT_CHECK_ON; if (ret) @@ -734,7 +730,7 @@ int fpregs_soft_get(struct task_struct *target, unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf) { - struct i387_soft_struct *s387 = &target->thread.fpu.state->soft; + struct swregs_state *s387 = &target->thread.fpu.state.soft; const void *space = s387->st_space; int ret; int offset = (S387->ftop & 7) * 10, other = 80 - offset; @@ -752,7 +748,7 @@ int fpregs_soft_get(struct task_struct *target, #endif /* PECULIAR_486 */ ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, s387, 0, - offsetof(struct i387_soft_struct, st_space)); + offsetof(struct swregs_state, st_space)); /* Copy all registers in stack order. */ if (!ret) diff --git a/arch/x86/math-emu/fpu_system.h b/arch/x86/math-emu/fpu_system.h index 2c614410a5f3..9ccecb61a4fa 100644 --- a/arch/x86/math-emu/fpu_system.h +++ b/arch/x86/math-emu/fpu_system.h @@ -31,7 +31,7 @@ #define SEG_EXPAND_DOWN(s) (((s).b & ((1 << 11) | (1 << 10))) \ == (1 << 10)) -#define I387 (current->thread.fpu.state) +#define I387 (¤t->thread.fpu.state) #define FPU_info (I387->soft.info) #define FPU_CS (*(unsigned short *) &(FPU_info->regs->cs)) diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 181c53bac3a7..9dc909841739 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -13,6 +13,7 @@ #include <linux/hugetlb.h> /* hstate_index_to_shift */ #include <linux/prefetch.h> /* prefetchw */ #include <linux/context_tracking.h> /* exception_enter(), ... */ +#include <linux/uaccess.h> /* faulthandler_disabled() */ #include <asm/traps.h> /* dotraplinkage, ... */ #include <asm/pgalloc.h> /* pgd_*(), ... */ @@ -1126,9 +1127,9 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code, /* * If we're in an interrupt, have no user context or are running - * in an atomic region then we must not take the fault: + * in a region with pagefaults disabled then we must not take the fault */ - if (unlikely(in_atomic() || !mm)) { + if (unlikely(faulthandler_disabled() || !mm)) { bad_area_nosemaphore(regs, error_code, address); return; } diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c index 4500142bc4aa..eecb207a2037 100644 --- a/arch/x86/mm/highmem_32.c +++ b/arch/x86/mm/highmem_32.c @@ -35,7 +35,7 @@ void *kmap_atomic_prot(struct page *page, pgprot_t prot) unsigned long vaddr; int idx, type; - /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */ + preempt_disable(); pagefault_disable(); if (!PageHighMem(page)) @@ -100,6 +100,7 @@ void __kunmap_atomic(void *kvaddr) #endif pagefault_enable(); + preempt_enable(); } EXPORT_SYMBOL(__kunmap_atomic); diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c index a9dc7a37e6a2..9c0ff045fdd4 100644 --- a/arch/x86/mm/iomap_32.c +++ b/arch/x86/mm/iomap_32.c @@ -59,6 +59,7 @@ void *kmap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot) unsigned long vaddr; int idx, type; + preempt_disable(); pagefault_disable(); type = kmap_atomic_idx_push(); @@ -117,5 +118,6 @@ iounmap_atomic(void __iomem *kvaddr) } pagefault_enable(); + preempt_enable(); } EXPORT_SYMBOL_GPL(iounmap_atomic); diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 8405c0c6a535..cc5ccc415cc0 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -408,18 +408,18 @@ void *xlate_dev_mem_ptr(phys_addr_t phys) { unsigned long start = phys & PAGE_MASK; unsigned long offset = phys & ~PAGE_MASK; - unsigned long vaddr; + void *vaddr; /* If page is RAM, we can use __va. Otherwise ioremap and unmap. */ if (page_is_ram(start >> PAGE_SHIFT)) return __va(phys); - vaddr = (unsigned long)ioremap_cache(start, PAGE_SIZE); + vaddr = ioremap_cache(start, PAGE_SIZE); /* Only add the offset on success and return NULL if the ioremap() failed: */ if (vaddr) vaddr += offset; - return (void *)vaddr; + return vaddr; } void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr) @@ -428,7 +428,6 @@ void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr) return; iounmap((void __iomem *)((unsigned long)addr & PAGE_MASK)); - return; } static pte_t bm_pte[PAGE_SIZE/sizeof(pte_t)] __page_aligned_bss; diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c index c439ec478216..7a657f58bbea 100644 --- a/arch/x86/mm/mpx.c +++ b/arch/x86/mm/mpx.c @@ -10,13 +10,15 @@ #include <linux/syscalls.h> #include <linux/sched/sysctl.h> -#include <asm/i387.h> #include <asm/insn.h> #include <asm/mman.h> #include <asm/mmu_context.h> #include <asm/mpx.h> #include <asm/processor.h> -#include <asm/fpu-internal.h> +#include <asm/fpu/internal.h> + +#define CREATE_TRACE_POINTS +#include <asm/trace/mpx.h> static const char *mpx_mapping_name(struct vm_area_struct *vma) { @@ -32,6 +34,22 @@ static int is_mpx_vma(struct vm_area_struct *vma) return (vma->vm_ops == &mpx_vma_ops); } +static inline unsigned long mpx_bd_size_bytes(struct mm_struct *mm) +{ + if (is_64bit_mm(mm)) + return MPX_BD_SIZE_BYTES_64; + else + return MPX_BD_SIZE_BYTES_32; +} + +static inline unsigned long mpx_bt_size_bytes(struct mm_struct *mm) +{ + if (is_64bit_mm(mm)) + return MPX_BT_SIZE_BYTES_64; + else + return MPX_BT_SIZE_BYTES_32; +} + /* * This is really a simplified "vm_mmap". it only handles MPX * bounds tables (the bounds directory is user-allocated). @@ -47,8 +65,8 @@ static unsigned long mpx_mmap(unsigned long len) vm_flags_t vm_flags; struct vm_area_struct *vma; - /* Only bounds table and bounds directory can be allocated here */ - if (len != MPX_BD_SIZE_BYTES && len != MPX_BT_SIZE_BYTES) + /* Only bounds table can be allocated here */ + if (len != mpx_bt_size_bytes(mm)) return -EINVAL; down_write(&mm->mmap_sem); @@ -272,10 +290,9 @@ bad_opcode: * * The caller is expected to kfree() the returned siginfo_t. */ -siginfo_t *mpx_generate_siginfo(struct pt_regs *regs, - struct xsave_struct *xsave_buf) +siginfo_t *mpx_generate_siginfo(struct pt_regs *regs) { - struct bndreg *bndregs, *bndreg; + const struct bndreg *bndregs, *bndreg; siginfo_t *info = NULL; struct insn insn; uint8_t bndregno; @@ -295,8 +312,8 @@ siginfo_t *mpx_generate_siginfo(struct pt_regs *regs, err = -EINVAL; goto err_out; } - /* get the bndregs _area_ of the xsave structure */ - bndregs = get_xsave_addr(xsave_buf, XSTATE_BNDREGS); + /* get bndregs field from current task's xsave area */ + bndregs = get_xsave_field_ptr(XSTATE_BNDREGS); if (!bndregs) { err = -EINVAL; goto err_out; @@ -334,6 +351,7 @@ siginfo_t *mpx_generate_siginfo(struct pt_regs *regs, err = -EINVAL; goto err_out; } + trace_mpx_bounds_register_exception(info->si_addr, bndreg); return info; err_out: /* info might be NULL, but kfree() handles that */ @@ -341,25 +359,18 @@ err_out: return ERR_PTR(err); } -static __user void *task_get_bounds_dir(struct task_struct *tsk) +static __user void *mpx_get_bounds_dir(void) { - struct bndcsr *bndcsr; + const struct bndcsr *bndcsr; if (!cpu_feature_enabled(X86_FEATURE_MPX)) return MPX_INVALID_BOUNDS_DIR; /* - * 32-bit binaries on 64-bit kernels are currently - * unsupported. - */ - if (IS_ENABLED(CONFIG_X86_64) && test_thread_flag(TIF_IA32)) - return MPX_INVALID_BOUNDS_DIR; - /* * The bounds directory pointer is stored in a register * only accessible if we first do an xsave. */ - fpu_save_init(&tsk->thread.fpu); - bndcsr = get_xsave_addr(&tsk->thread.fpu.state->xsave, XSTATE_BNDCSR); + bndcsr = get_xsave_field_ptr(XSTATE_BNDCSR); if (!bndcsr) return MPX_INVALID_BOUNDS_DIR; @@ -378,10 +389,10 @@ static __user void *task_get_bounds_dir(struct task_struct *tsk) (bndcsr->bndcfgu & MPX_BNDCFG_ADDR_MASK); } -int mpx_enable_management(struct task_struct *tsk) +int mpx_enable_management(void) { void __user *bd_base = MPX_INVALID_BOUNDS_DIR; - struct mm_struct *mm = tsk->mm; + struct mm_struct *mm = current->mm; int ret = 0; /* @@ -390,11 +401,12 @@ int mpx_enable_management(struct task_struct *tsk) * directory into XSAVE/XRSTOR Save Area and enable MPX through * XRSTOR instruction. * - * fpu_xsave() is expected to be very expensive. Storing the bounds - * directory here means that we do not have to do xsave in the unmap - * path; we can just use mm->bd_addr instead. + * The copy_xregs_to_kernel() beneath get_xsave_field_ptr() is + * expected to be relatively expensive. Storing the bounds + * directory here means that we do not have to do xsave in the + * unmap path; we can just use mm->bd_addr instead. */ - bd_base = task_get_bounds_dir(tsk); + bd_base = mpx_get_bounds_dir(); down_write(&mm->mmap_sem); mm->bd_addr = bd_base; if (mm->bd_addr == MPX_INVALID_BOUNDS_DIR) @@ -404,7 +416,7 @@ int mpx_enable_management(struct task_struct *tsk) return ret; } -int mpx_disable_management(struct task_struct *tsk) +int mpx_disable_management(void) { struct mm_struct *mm = current->mm; @@ -417,29 +429,59 @@ int mpx_disable_management(struct task_struct *tsk) return 0; } +static int mpx_cmpxchg_bd_entry(struct mm_struct *mm, + unsigned long *curval, + unsigned long __user *addr, + unsigned long old_val, unsigned long new_val) +{ + int ret; + /* + * user_atomic_cmpxchg_inatomic() actually uses sizeof() + * the pointer that we pass to it to figure out how much + * data to cmpxchg. We have to be careful here not to + * pass a pointer to a 64-bit data type when we only want + * a 32-bit copy. + */ + if (is_64bit_mm(mm)) { + ret = user_atomic_cmpxchg_inatomic(curval, + addr, old_val, new_val); + } else { + u32 uninitialized_var(curval_32); + u32 old_val_32 = old_val; + u32 new_val_32 = new_val; + u32 __user *addr_32 = (u32 __user *)addr; + + ret = user_atomic_cmpxchg_inatomic(&curval_32, + addr_32, old_val_32, new_val_32); + *curval = curval_32; + } + return ret; +} + /* - * With 32-bit mode, MPX_BT_SIZE_BYTES is 4MB, and the size of each - * bounds table is 16KB. With 64-bit mode, MPX_BT_SIZE_BYTES is 2GB, + * With 32-bit mode, a bounds directory is 4MB, and the size of each + * bounds table is 16KB. With 64-bit mode, a bounds directory is 2GB, * and the size of each bounds table is 4MB. */ -static int allocate_bt(long __user *bd_entry) +static int allocate_bt(struct mm_struct *mm, long __user *bd_entry) { unsigned long expected_old_val = 0; unsigned long actual_old_val = 0; unsigned long bt_addr; + unsigned long bd_new_entry; int ret = 0; /* * Carve the virtual space out of userspace for the new * bounds table: */ - bt_addr = mpx_mmap(MPX_BT_SIZE_BYTES); + bt_addr = mpx_mmap(mpx_bt_size_bytes(mm)); if (IS_ERR((void *)bt_addr)) return PTR_ERR((void *)bt_addr); /* * Set the valid flag (kinda like _PAGE_PRESENT in a pte) */ - bt_addr = bt_addr | MPX_BD_ENTRY_VALID_FLAG; + bd_new_entry = bt_addr | MPX_BD_ENTRY_VALID_FLAG; /* * Go poke the address of the new bounds table in to the @@ -452,8 +494,8 @@ static int allocate_bt(long __user *bd_entry) * mmap_sem at this point, unlike some of the other part * of the MPX code that have to pagefault_disable(). */ - ret = user_atomic_cmpxchg_inatomic(&actual_old_val, bd_entry, - expected_old_val, bt_addr); + ret = mpx_cmpxchg_bd_entry(mm, &actual_old_val, bd_entry, + expected_old_val, bd_new_entry); if (ret) goto out_unmap; @@ -481,9 +523,10 @@ static int allocate_bt(long __user *bd_entry) ret = -EINVAL; goto out_unmap; } + trace_mpx_new_bounds_table(bt_addr); return 0; out_unmap: - vm_munmap(bt_addr & MPX_BT_ADDR_MASK, MPX_BT_SIZE_BYTES); + vm_munmap(bt_addr, mpx_bt_size_bytes(mm)); return ret; } @@ -498,12 +541,13 @@ out_unmap: * bound table is 16KB. With 64-bit mode, the size of BD is 2GB, * and the size of each bound table is 4MB. */ -static int do_mpx_bt_fault(struct xsave_struct *xsave_buf) +static int do_mpx_bt_fault(void) { unsigned long bd_entry, bd_base; - struct bndcsr *bndcsr; + const struct bndcsr *bndcsr; + struct mm_struct *mm = current->mm; - bndcsr = get_xsave_addr(xsave_buf, XSTATE_BNDCSR); + bndcsr = get_xsave_field_ptr(XSTATE_BNDCSR); if (!bndcsr) return -EINVAL; /* @@ -520,13 +564,13 @@ static int do_mpx_bt_fault(struct xsave_struct *xsave_buf) * the directory is. */ if ((bd_entry < bd_base) || - (bd_entry >= bd_base + MPX_BD_SIZE_BYTES)) + (bd_entry >= bd_base + mpx_bd_size_bytes(mm))) return -EINVAL; - return allocate_bt((long __user *)bd_entry); + return allocate_bt(mm, (long __user *)bd_entry); } -int mpx_handle_bd_fault(struct xsave_struct *xsave_buf) +int mpx_handle_bd_fault(void) { /* * Userspace never asked us to manage the bounds tables, @@ -535,7 +579,7 @@ int mpx_handle_bd_fault(struct xsave_struct *xsave_buf) if (!kernel_managing_mpx_tables(current->mm)) return -EINVAL; - if (do_mpx_bt_fault(xsave_buf)) { + if (do_mpx_bt_fault()) { force_sig(SIGSEGV, current); /* * The force_sig() is essentially "handling" this @@ -572,29 +616,55 @@ static int mpx_resolve_fault(long __user *addr, int write) return 0; } +static unsigned long mpx_bd_entry_to_bt_addr(struct mm_struct *mm, + unsigned long bd_entry) +{ + unsigned long bt_addr = bd_entry; + int align_to_bytes; + /* + * Bit 0 in a bt_entry is always the valid bit. + */ + bt_addr &= ~MPX_BD_ENTRY_VALID_FLAG; + /* + * Tables are naturally aligned at 8-byte boundaries + * on 64-bit and 4-byte boundaries on 32-bit. The + * documentation makes it appear that the low bits + * are ignored by the hardware, so we do the same. + */ + if (is_64bit_mm(mm)) + align_to_bytes = 8; + else + align_to_bytes = 4; + bt_addr &= ~(align_to_bytes-1); + return bt_addr; +} + /* * Get the base of bounds tables pointed by specific bounds * directory entry. */ static int get_bt_addr(struct mm_struct *mm, - long __user *bd_entry, unsigned long *bt_addr) + long __user *bd_entry_ptr, + unsigned long *bt_addr_result) { int ret; int valid_bit; + unsigned long bd_entry; + unsigned long bt_addr; - if (!access_ok(VERIFY_READ, (bd_entry), sizeof(*bd_entry))) + if (!access_ok(VERIFY_READ, (bd_entry_ptr), sizeof(*bd_entry_ptr))) return -EFAULT; while (1) { int need_write = 0; pagefault_disable(); - ret = get_user(*bt_addr, bd_entry); + ret = get_user(bd_entry, bd_entry_ptr); pagefault_enable(); if (!ret) break; if (ret == -EFAULT) - ret = mpx_resolve_fault(bd_entry, need_write); + ret = mpx_resolve_fault(bd_entry_ptr, need_write); /* * If we could not resolve the fault, consider it * userspace's fault and error out. @@ -603,8 +673,8 @@ static int get_bt_addr(struct mm_struct *mm, return ret; } - valid_bit = *bt_addr & MPX_BD_ENTRY_VALID_FLAG; - *bt_addr &= MPX_BT_ADDR_MASK; + valid_bit = bd_entry & MPX_BD_ENTRY_VALID_FLAG; + bt_addr = mpx_bd_entry_to_bt_addr(mm, bd_entry); /* * When the kernel is managing bounds tables, a bounds directory @@ -613,7 +683,7 @@ static int get_bt_addr(struct mm_struct *mm, * data in the address field, we know something is wrong. This * -EINVAL return will cause a SIGSEGV. */ - if (!valid_bit && *bt_addr) + if (!valid_bit && bt_addr) return -EINVAL; /* * Do we have an completely zeroed bt entry? That is OK. It @@ -624,19 +694,100 @@ static int get_bt_addr(struct mm_struct *mm, if (!valid_bit) return -ENOENT; + *bt_addr_result = bt_addr; return 0; } +static inline int bt_entry_size_bytes(struct mm_struct *mm) +{ + if (is_64bit_mm(mm)) + return MPX_BT_ENTRY_BYTES_64; + else + return MPX_BT_ENTRY_BYTES_32; +} + +/* + * Take a virtual address and turns it in to the offset in bytes + * inside of the bounds table where the bounds table entry + * controlling 'addr' can be found. + */ +static unsigned long mpx_get_bt_entry_offset_bytes(struct mm_struct *mm, + unsigned long addr) +{ + unsigned long bt_table_nr_entries; + unsigned long offset = addr; + + if (is_64bit_mm(mm)) { + /* Bottom 3 bits are ignored on 64-bit */ + offset >>= 3; + bt_table_nr_entries = MPX_BT_NR_ENTRIES_64; + } else { + /* Bottom 2 bits are ignored on 32-bit */ + offset >>= 2; + bt_table_nr_entries = MPX_BT_NR_ENTRIES_32; + } + /* + * We know the size of the table in to which we are + * indexing, and we have eliminated all the low bits + * which are ignored for indexing. + * + * Mask out all the high bits which we do not need + * to index in to the table. Note that the tables + * are always powers of two so this gives us a proper + * mask. + */ + offset &= (bt_table_nr_entries-1); + /* + * We now have an entry offset in terms of *entries* in + * the table. We need to scale it back up to bytes. + */ + offset *= bt_entry_size_bytes(mm); + return offset; +} + +/* + * How much virtual address space does a single bounds + * directory entry cover? + * + * Note, we need a long long because 4GB doesn't fit in + * to a long on 32-bit. + */ +static inline unsigned long bd_entry_virt_space(struct mm_struct *mm) +{ + unsigned long long virt_space = (1ULL << boot_cpu_data.x86_virt_bits); + if (is_64bit_mm(mm)) + return virt_space / MPX_BD_NR_ENTRIES_64; + else + return virt_space / MPX_BD_NR_ENTRIES_32; +} + /* * Free the backing physical pages of bounds table 'bt_addr'. * Assume start...end is within that bounds table. */ -static int zap_bt_entries(struct mm_struct *mm, +static noinline int zap_bt_entries_mapping(struct mm_struct *mm, unsigned long bt_addr, - unsigned long start, unsigned long end) + unsigned long start_mapping, unsigned long end_mapping) { struct vm_area_struct *vma; unsigned long addr, len; + unsigned long start; + unsigned long end; + + /* + * if we 'end' on a boundary, the offset will be 0 which + * is not what we want. Back it up a byte to get the + * last bt entry. Then once we have the entry itself, + * move 'end' back up by the table entry size. + */ + start = bt_addr + mpx_get_bt_entry_offset_bytes(mm, start_mapping); + end = bt_addr + mpx_get_bt_entry_offset_bytes(mm, end_mapping - 1); + /* + * Move end back up by one entry. Among other things + * this ensures that it remains page-aligned and does + * not screw up zap_page_range() + */ + end += bt_entry_size_bytes(mm); /* * Find the first overlapping vma. If vma->vm_start > start, there @@ -648,7 +799,7 @@ static int zap_bt_entries(struct mm_struct *mm, return -EINVAL; /* - * A NUMA policy on a VM_MPX VMA could cause this bouds table to + * A NUMA policy on a VM_MPX VMA could cause this bounds table to * be split. So we need to look across the entire 'start -> end' * range of this bounds table, find all of the VM_MPX VMAs, and * zap only those. @@ -666,27 +817,65 @@ static int zap_bt_entries(struct mm_struct *mm, len = min(vma->vm_end, end) - addr; zap_page_range(vma, addr, len, NULL); + trace_mpx_unmap_zap(addr, addr+len); vma = vma->vm_next; addr = vma->vm_start; } - return 0; } -static int unmap_single_bt(struct mm_struct *mm, +static unsigned long mpx_get_bd_entry_offset(struct mm_struct *mm, + unsigned long addr) +{ + /* + * There are several ways to derive the bd offsets. We + * use the following approach here: + * 1. We know the size of the virtual address space + * 2. We know the number of entries in a bounds table + * 3. We know that each entry covers a fixed amount of + * virtual address space. + * So, we can just divide the virtual address by the + * virtual space used by one entry to determine which + * entry "controls" the given virtual address. + */ + if (is_64bit_mm(mm)) { + int bd_entry_size = 8; /* 64-bit pointer */ + /* + * Take the 64-bit addressing hole in to account. + */ + addr &= ((1UL << boot_cpu_data.x86_virt_bits) - 1); + return (addr / bd_entry_virt_space(mm)) * bd_entry_size; + } else { + int bd_entry_size = 4; /* 32-bit pointer */ + /* + * 32-bit has no hole so this case needs no mask + */ + return (addr / bd_entry_virt_space(mm)) * bd_entry_size; + } + /* + * The two return calls above are exact copies. If we + * pull out a single copy and put it in here, gcc won't + * realize that we're doing a power-of-2 divide and use + * shifts. It uses a real divide. If we put them up + * there, it manages to figure it out (gcc 4.8.3). + */ +} + +static int unmap_entire_bt(struct mm_struct *mm, long __user *bd_entry, unsigned long bt_addr) { unsigned long expected_old_val = bt_addr | MPX_BD_ENTRY_VALID_FLAG; - unsigned long actual_old_val = 0; + unsigned long uninitialized_var(actual_old_val); int ret; while (1) { int need_write = 1; + unsigned long cleared_bd_entry = 0; pagefault_disable(); - ret = user_atomic_cmpxchg_inatomic(&actual_old_val, bd_entry, - expected_old_val, 0); + ret = mpx_cmpxchg_bd_entry(mm, &actual_old_val, + bd_entry, expected_old_val, cleared_bd_entry); pagefault_enable(); if (!ret) break; @@ -705,9 +894,8 @@ static int unmap_single_bt(struct mm_struct *mm, if (actual_old_val != expected_old_val) { /* * Someone else raced with us to unmap the table. - * There was no bounds table pointed to by the - * directory, so declare success. Somebody freed - * it. + * That is OK, since we were both trying to do + * the same thing. Declare success. */ if (!actual_old_val) return 0; @@ -720,176 +908,113 @@ static int unmap_single_bt(struct mm_struct *mm, */ return -EINVAL; } - /* * Note, we are likely being called under do_munmap() already. To * avoid recursion, do_munmap() will check whether it comes * from one bounds table through VM_MPX flag. */ - return do_munmap(mm, bt_addr, MPX_BT_SIZE_BYTES); + return do_munmap(mm, bt_addr, mpx_bt_size_bytes(mm)); } -/* - * If the bounds table pointed by bounds directory 'bd_entry' is - * not shared, unmap this whole bounds table. Otherwise, only free - * those backing physical pages of bounds table entries covered - * in this virtual address region start...end. - */ -static int unmap_shared_bt(struct mm_struct *mm, - long __user *bd_entry, unsigned long start, - unsigned long end, bool prev_shared, bool next_shared) +static int try_unmap_single_bt(struct mm_struct *mm, + unsigned long start, unsigned long end) { - unsigned long bt_addr; - int ret; - - ret = get_bt_addr(mm, bd_entry, &bt_addr); + struct vm_area_struct *next; + struct vm_area_struct *prev; /* - * We could see an "error" ret for not-present bounds - * tables (not really an error), or actual errors, but - * stop unmapping either way. + * "bta" == Bounds Table Area: the area controlled by the + * bounds table that we are unmapping. */ - if (ret) - return ret; - - if (prev_shared && next_shared) - ret = zap_bt_entries(mm, bt_addr, - bt_addr+MPX_GET_BT_ENTRY_OFFSET(start), - bt_addr+MPX_GET_BT_ENTRY_OFFSET(end)); - else if (prev_shared) - ret = zap_bt_entries(mm, bt_addr, - bt_addr+MPX_GET_BT_ENTRY_OFFSET(start), - bt_addr+MPX_BT_SIZE_BYTES); - else if (next_shared) - ret = zap_bt_entries(mm, bt_addr, bt_addr, - bt_addr+MPX_GET_BT_ENTRY_OFFSET(end)); - else - ret = unmap_single_bt(mm, bd_entry, bt_addr); - - return ret; -} - -/* - * A virtual address region being munmap()ed might share bounds table - * with adjacent VMAs. We only need to free the backing physical - * memory of these shared bounds tables entries covered in this virtual - * address region. - */ -static int unmap_edge_bts(struct mm_struct *mm, - unsigned long start, unsigned long end) -{ + unsigned long bta_start_vaddr = start & ~(bd_entry_virt_space(mm)-1); + unsigned long bta_end_vaddr = bta_start_vaddr + bd_entry_virt_space(mm); + unsigned long uninitialized_var(bt_addr); + void __user *bde_vaddr; int ret; - long __user *bde_start, *bde_end; - struct vm_area_struct *prev, *next; - bool prev_shared = false, next_shared = false; - - bde_start = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(start); - bde_end = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(end-1); - /* - * Check whether bde_start and bde_end are shared with adjacent - * VMAs. - * - * We already unliked the VMAs from the mm's rbtree so 'start' + * We already unlinked the VMAs from the mm's rbtree so 'start' * is guaranteed to be in a hole. This gets us the first VMA * before the hole in to 'prev' and the next VMA after the hole * in to 'next'. */ next = find_vma_prev(mm, start, &prev); - if (prev && (mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(prev->vm_end-1)) - == bde_start) - prev_shared = true; - if (next && (mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(next->vm_start)) - == bde_end) - next_shared = true; - /* - * This virtual address region being munmap()ed is only - * covered by one bounds table. - * - * In this case, if this table is also shared with adjacent - * VMAs, only part of the backing physical memory of the bounds - * table need be freeed. Otherwise the whole bounds table need - * be unmapped. - */ - if (bde_start == bde_end) { - return unmap_shared_bt(mm, bde_start, start, end, - prev_shared, next_shared); + * Do not count other MPX bounds table VMAs as neighbors. + * Although theoretically possible, we do not allow bounds + * tables for bounds tables so our heads do not explode. + * If we count them as neighbors here, we may end up with + * lots of tables even though we have no actual table + * entries in use. + */ + while (next && is_mpx_vma(next)) + next = next->vm_next; + while (prev && is_mpx_vma(prev)) + prev = prev->vm_prev; + /* + * We know 'start' and 'end' lie within an area controlled + * by a single bounds table. See if there are any other + * VMAs controlled by that bounds table. If there are not + * then we can "expand" the are we are unmapping to possibly + * cover the entire table. + */ + next = find_vma_prev(mm, start, &prev); + if ((!prev || prev->vm_end <= bta_start_vaddr) && + (!next || next->vm_start >= bta_end_vaddr)) { + /* + * No neighbor VMAs controlled by same bounds + * table. Try to unmap the whole thing + */ + start = bta_start_vaddr; + end = bta_end_vaddr; } + bde_vaddr = mm->bd_addr + mpx_get_bd_entry_offset(mm, start); + ret = get_bt_addr(mm, bde_vaddr, &bt_addr); /* - * If more than one bounds tables are covered in this virtual - * address region being munmap()ed, we need to separately check - * whether bde_start and bde_end are shared with adjacent VMAs. + * No bounds table there, so nothing to unmap. */ - ret = unmap_shared_bt(mm, bde_start, start, end, prev_shared, false); - if (ret) - return ret; - ret = unmap_shared_bt(mm, bde_end, start, end, false, next_shared); + if (ret == -ENOENT) { + ret = 0; + return 0; + } if (ret) return ret; - - return 0; + /* + * We are unmapping an entire table. Either because the + * unmap that started this whole process was large enough + * to cover an entire table, or that the unmap was small + * but was the area covered by a bounds table. + */ + if ((start == bta_start_vaddr) && + (end == bta_end_vaddr)) + return unmap_entire_bt(mm, bde_vaddr, bt_addr); + return zap_bt_entries_mapping(mm, bt_addr, start, end); } static int mpx_unmap_tables(struct mm_struct *mm, unsigned long start, unsigned long end) { - int ret; - long __user *bd_entry, *bde_start, *bde_end; - unsigned long bt_addr; - - /* - * "Edge" bounds tables are those which are being used by the region - * (start -> end), but that may be shared with adjacent areas. If they - * turn out to be completely unshared, they will be freed. If they are - * shared, we will free the backing store (like an MADV_DONTNEED) for - * areas used by this region. - */ - ret = unmap_edge_bts(mm, start, end); - switch (ret) { - /* non-present tables are OK */ - case 0: - case -ENOENT: - /* Success, or no tables to unmap */ - break; - case -EINVAL: - case -EFAULT: - default: - return ret; - } - - /* - * Only unmap the bounds table that are - * 1. fully covered - * 2. not at the edges of the mapping, even if full aligned - */ - bde_start = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(start); - bde_end = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(end-1); - for (bd_entry = bde_start + 1; bd_entry < bde_end; bd_entry++) { - ret = get_bt_addr(mm, bd_entry, &bt_addr); - switch (ret) { - case 0: - break; - case -ENOENT: - /* No table here, try the next one */ - continue; - case -EINVAL: - case -EFAULT: - default: - /* - * Note: we are being strict here. - * Any time we run in to an issue - * unmapping tables, we stop and - * SIGSEGV. - */ - return ret; - } - - ret = unmap_single_bt(mm, bd_entry, bt_addr); + unsigned long one_unmap_start; + trace_mpx_unmap_search(start, end); + + one_unmap_start = start; + while (one_unmap_start < end) { + int ret; + unsigned long next_unmap_start = ALIGN(one_unmap_start+1, + bd_entry_virt_space(mm)); + unsigned long one_unmap_end = end; + /* + * if the end is beyond the current bounds table, + * move it back so we only deal with a single one + * at a time + */ + if (one_unmap_end > next_unmap_start) + one_unmap_end = next_unmap_start; + ret = try_unmap_single_bt(mm, one_unmap_start, one_unmap_end); if (ret) return ret; - } + one_unmap_start = next_unmap_start; + } return 0; } diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 02744df576d5..3b984c3aa1b0 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -501,6 +501,8 @@ void __init efi_init(void) if (efi_enabled(EFI_DBG)) print_efi_memmap(); + + efi_esrt_init(); } void __init efi_late_init(void) diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 757678fb26e1..0d7dd1f5ac36 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -18,10 +18,9 @@ #include <asm/mtrr.h> #include <asm/page.h> #include <asm/mce.h> -#include <asm/xcr.h> #include <asm/suspend.h> +#include <asm/fpu/internal.h> #include <asm/debugreg.h> -#include <asm/fpu-internal.h> /* pcntxt_mask */ #include <asm/cpu.h> #ifdef CONFIG_X86_32 @@ -155,6 +154,8 @@ static void fix_processor_context(void) #endif load_TR_desc(); /* This does ltr */ load_LDT(¤t->active_mm->context); /* This does lldt */ + + fpu__resume_cpu(); } /** @@ -221,12 +222,6 @@ static void notrace __restore_processor_state(struct saved_context *ctxt) wrmsrl(MSR_KERNEL_GS_BASE, ctxt->gs_kernel_base); #endif - /* - * restore XCR0 for xsave capable cpu's. - */ - if (cpu_has_xsave) - xsetbv(XCR_XFEATURE_ENABLED_MASK, pcntxt_mask); - fix_processor_context(); do_fpu_end(); diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index a8f57a94785a..0b95c9b8283f 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1424,7 +1424,7 @@ static void xen_pvh_set_cr_flags(int cpu) return; /* * For BSP, PSE PGE are set in probe_page_size_mask(), for APs - * set them here. For all, OSFXSR OSXMMEXCPT are set in fpu_init. + * set them here. For all, OSFXSR OSXMMEXCPT are set in fpu__init_cpu(). */ if (cpu_has_pse) cr4_set_bits_and_update_boot(X86_CR4_PSE); diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c index 9e3571a6535c..83a44a33cfa1 100644 --- a/arch/xtensa/mm/fault.c +++ b/arch/xtensa/mm/fault.c @@ -15,10 +15,10 @@ #include <linux/mm.h> #include <linux/module.h> #include <linux/hardirq.h> +#include <linux/uaccess.h> #include <asm/mmu_context.h> #include <asm/cacheflush.h> #include <asm/hardirq.h> -#include <asm/uaccess.h> #include <asm/pgalloc.h> DEFINE_PER_CPU(unsigned long, asid_cache) = ASID_USER_FIRST; @@ -57,7 +57,7 @@ void do_page_fault(struct pt_regs *regs) /* If we're in an interrupt or have no user * context, we must not take the fault.. */ - if (in_atomic() || !mm) { + if (faulthandler_disabled() || !mm) { bad_page_fault(regs, address, SIGSEGV); return; } diff --git a/arch/xtensa/mm/highmem.c b/arch/xtensa/mm/highmem.c index 8cfb71ec0937..184ceadccc1a 100644 --- a/arch/xtensa/mm/highmem.c +++ b/arch/xtensa/mm/highmem.c @@ -42,6 +42,7 @@ void *kmap_atomic(struct page *page) enum fixed_addresses idx; unsigned long vaddr; + preempt_disable(); pagefault_disable(); if (!PageHighMem(page)) return page_address(page); @@ -79,6 +80,7 @@ void __kunmap_atomic(void *kvaddr) } pagefault_enable(); + preempt_enable(); } EXPORT_SYMBOL(__kunmap_atomic); |
