diff options
Diffstat (limited to 'arch/x86')
86 files changed, 2698 insertions, 503 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index edcf80eda566..9b8ecfc00fa1 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -125,6 +125,7 @@ config X86 select RTC_LIB select HAVE_DEBUG_STACKOVERFLOW select HAVE_IRQ_EXIT_ON_IRQ_STACK if X86_64 + select HAVE_CC_STACKPROTECTOR config INSTRUCTION_DECODER def_bool y @@ -1601,22 +1602,6 @@ config SECCOMP If unsure, say Y. Only embedded should say N here. -config CC_STACKPROTECTOR - bool "Enable -fstack-protector buffer overflow detection" - ---help--- - This option turns on the -fstack-protector GCC feature. This - feature puts, at the beginning of functions, a canary value on - the stack just before the return address, and validates - the value just before actually returning. Stack based buffer - overflows (that need to overwrite this return address) now also - overwrite the canary, which gets detected and the attack is then - neutralized via a kernel panic. - - This feature requires gcc version 4.2 or above, or a distribution - gcc with the feature backported. Older versions are automatically - detected and for those versions, this configuration option is - ignored. (and a warning is printed during bootup) - source kernel/Kconfig.hz config KEXEC diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 57d021507120..13b22e0f681d 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -89,13 +89,11 @@ else KBUILD_CFLAGS += -maccumulate-outgoing-args endif +# Make sure compiler does not have buggy stack-protector support. ifdef CONFIG_CC_STACKPROTECTOR cc_has_sp := $(srctree)/scripts/gcc-x86_$(BITS)-has-stack-protector.sh - ifeq ($(shell $(CONFIG_SHELL) $(cc_has_sp) $(CC) $(KBUILD_CPPFLAGS) $(biarch)),y) - stackp-y := -fstack-protector - KBUILD_CFLAGS += $(stackp-y) - else - $(warning stack protector enabled but no compiler support) + ifneq ($(shell $(CONFIG_SHELL) $(cc_has_sp) $(CC) $(KBUILD_CPPFLAGS) $(biarch)),y) + $(warning stack-protector enabled but compiler support broken) endif endif diff --git a/arch/x86/boot/bioscall.S b/arch/x86/boot/bioscall.S index 1dfbf64e52a2..d401b4a262b0 100644 --- a/arch/x86/boot/bioscall.S +++ b/arch/x86/boot/bioscall.S @@ -1,6 +1,6 @@ /* ----------------------------------------------------------------------- * - * Copyright 2009 Intel Corporation; author H. Peter Anvin + * Copyright 2009-2014 Intel Corporation; author H. Peter Anvin * * 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 @@ -13,8 +13,8 @@ * touching registers they shouldn't be. */ - .code16gcc - .text + .code16 + .section ".inittext","ax" .globl intcall .type intcall, @function intcall: diff --git a/arch/x86/boot/copy.S b/arch/x86/boot/copy.S index 11f272c6f5e9..1eb7d298b47d 100644 --- a/arch/x86/boot/copy.S +++ b/arch/x86/boot/copy.S @@ -14,7 +14,7 @@ * Memory copy routines */ - .code16gcc + .code16 .text GLOBAL(memcpy) @@ -30,7 +30,7 @@ GLOBAL(memcpy) rep; movsb popw %di popw %si - ret + retl ENDPROC(memcpy) GLOBAL(memset) @@ -45,25 +45,25 @@ GLOBAL(memset) andw $3, %cx rep; stosb popw %di - ret + retl ENDPROC(memset) GLOBAL(copy_from_fs) pushw %ds pushw %fs popw %ds - call memcpy + calll memcpy popw %ds - ret + retl ENDPROC(copy_from_fs) GLOBAL(copy_to_fs) pushw %es pushw %fs popw %es - call memcpy + calll memcpy popw %es - ret + retl ENDPROC(copy_to_fs) #if 0 /* Not currently used, but can be enabled as needed */ @@ -71,17 +71,17 @@ GLOBAL(copy_from_gs) pushw %ds pushw %gs popw %ds - call memcpy + calll memcpy popw %ds - ret + retl ENDPROC(copy_from_gs) GLOBAL(copy_to_gs) pushw %es pushw %gs popw %es - call memcpy + calll memcpy popw %es - ret + retl ENDPROC(copy_to_gs) #endif diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index 9ec06a1f6d61..ec3b8ba68096 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -391,7 +391,14 @@ xloadflags: #else # define XLF23 0 #endif - .word XLF0 | XLF1 | XLF23 + +#if defined(CONFIG_X86_64) && defined(CONFIG_EFI) && defined(CONFIG_KEXEC) +# define XLF4 XLF_EFI_KEXEC +#else +# define XLF4 0 +#endif + + .word XLF0 | XLF1 | XLF23 | XLF4 cmdline_size: .long COMMAND_LINE_SIZE-1 #length of the command line, #added with boot protocol diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h index c6cd358a1eec..04a48903b2eb 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -92,12 +92,53 @@ #endif #define smp_read_barrier_depends() read_barrier_depends() #define set_mb(var, value) do { (void)xchg(&var, value); } while (0) -#else +#else /* !SMP */ #define smp_mb() barrier() #define smp_rmb() barrier() #define smp_wmb() barrier() #define smp_read_barrier_depends() do { } while (0) #define set_mb(var, value) do { var = value; barrier(); } while (0) +#endif /* SMP */ + +#if defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE) + +/* + * For either of these options x86 doesn't have a strong TSO memory + * model and we should fall back to full barriers. + */ + +#define smp_store_release(p, v) \ +do { \ + compiletime_assert_atomic_type(*p); \ + smp_mb(); \ + ACCESS_ONCE(*p) = (v); \ +} while (0) + +#define smp_load_acquire(p) \ +({ \ + typeof(*p) ___p1 = ACCESS_ONCE(*p); \ + compiletime_assert_atomic_type(*p); \ + smp_mb(); \ + ___p1; \ +}) + +#else /* regular x86 TSO memory ordering */ + +#define smp_store_release(p, v) \ +do { \ + compiletime_assert_atomic_type(*p); \ + barrier(); \ + ACCESS_ONCE(*p) = (v); \ +} while (0) + +#define smp_load_acquire(p) \ +({ \ + typeof(*p) ___p1 = ACCESS_ONCE(*p); \ + compiletime_assert_atomic_type(*p); \ + barrier(); \ + ___p1; \ +}) + #endif /* diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 65c6e6e3a552..3b978c472d08 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -1,6 +1,24 @@ #ifndef _ASM_X86_EFI_H #define _ASM_X86_EFI_H +/* + * We map the EFI regions needed for runtime services non-contiguously, + * with preserved alignment on virtual addresses starting from -4G down + * for a total max space of 64G. This way, we provide for stable runtime + * services addresses across kernels so that a kexec'd kernel can still + * use them. + * + * This is the main reason why we're doing stable VA mappings for RT + * services. + * + * This flag is used in conjuction with a chicken bit called + * "efi=old_map" which can be used as a fallback to the old runtime + * services mapping method in case there's some b0rkage with a + * particular EFI implementation (haha, it is hard to hold up the + * sarcasm here...). + */ +#define EFI_OLD_MEMMAP EFI_ARCH_1 + #ifdef CONFIG_X86_32 #define EFI_LOADER_SIGNATURE "EL32" @@ -69,24 +87,31 @@ extern u64 efi_call6(void *fp, u64 arg1, u64 arg2, u64 arg3, efi_call6((f), (u64)(a1), (u64)(a2), (u64)(a3), \ (u64)(a4), (u64)(a5), (u64)(a6)) +#define _efi_call_virtX(x, f, ...) \ +({ \ + efi_status_t __s; \ + \ + efi_sync_low_kernel_mappings(); \ + preempt_disable(); \ + __s = efi_call##x((void *)efi.systab->runtime->f, __VA_ARGS__); \ + preempt_enable(); \ + __s; \ +}) + #define efi_call_virt0(f) \ - efi_call0((efi.systab->runtime->f)) -#define efi_call_virt1(f, a1) \ - efi_call1((efi.systab->runtime->f), (u64)(a1)) -#define efi_call_virt2(f, a1, a2) \ - efi_call2((efi.systab->runtime->f), (u64)(a1), (u64)(a2)) -#define efi_call_virt3(f, a1, a2, a3) \ - efi_call3((efi.systab->runtime->f), (u64)(a1), (u64)(a2), \ - (u64)(a3)) -#define efi_call_virt4(f, a1, a2, a3, a4) \ - efi_call4((efi.systab->runtime->f), (u64)(a1), (u64)(a2), \ - (u64)(a3), (u64)(a4)) -#define efi_call_virt5(f, a1, a2, a3, a4, a5) \ - efi_call5((efi.systab->runtime->f), (u64)(a1), (u64)(a2), \ - (u64)(a3), (u64)(a4), (u64)(a5)) -#define efi_call_virt6(f, a1, a2, a3, a4, a5, a6) \ - efi_call6((efi.systab->runtime->f), (u64)(a1), (u64)(a2), \ - (u64)(a3), (u64)(a4), (u64)(a5), (u64)(a6)) + _efi_call_virtX(0, f) +#define efi_call_virt1(f, a1) \ + _efi_call_virtX(1, f, (u64)(a1)) +#define efi_call_virt2(f, a1, a2) \ + _efi_call_virtX(2, f, (u64)(a1), (u64)(a2)) +#define efi_call_virt3(f, a1, a2, a3) \ + _efi_call_virtX(3, f, (u64)(a1), (u64)(a2), (u64)(a3)) +#define efi_call_virt4(f, a1, a2, a3, a4) \ + _efi_call_virtX(4, f, (u64)(a1), (u64)(a2), (u64)(a3), (u64)(a4)) +#define efi_call_virt5(f, a1, a2, a3, a4, a5) \ + _efi_call_virtX(5, f, (u64)(a1), (u64)(a2), (u64)(a3), (u64)(a4), (u64)(a5)) +#define efi_call_virt6(f, a1, a2, a3, a4, a5, a6) \ + _efi_call_virtX(6, f, (u64)(a1), (u64)(a2), (u64)(a3), (u64)(a4), (u64)(a5), (u64)(a6)) extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size, u32 type, u64 attribute); @@ -95,12 +120,28 @@ extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size, extern int add_efi_memmap; extern unsigned long x86_efi_facility; +extern struct efi_scratch efi_scratch; extern void efi_set_executable(efi_memory_desc_t *md, bool executable); extern int efi_memblock_x86_reserve_range(void); extern void efi_call_phys_prelog(void); extern void efi_call_phys_epilog(void); extern void efi_unmap_memmap(void); extern void efi_memory_uc(u64 addr, unsigned long size); +extern void __init efi_map_region(efi_memory_desc_t *md); +extern void __init efi_map_region_fixed(efi_memory_desc_t *md); +extern void efi_sync_low_kernel_mappings(void); +extern void efi_setup_page_tables(void); +extern void __init old_map_region(efi_memory_desc_t *md); + +struct efi_setup_data { + u64 fw_vendor; + u64 runtime; + u64 tables; + u64 smbios; + u64 reserved[8]; +}; + +extern u64 efi_setup; #ifdef CONFIG_EFI @@ -110,7 +151,7 @@ static inline bool efi_is_native(void) } extern struct console early_efi_console; - +extern void parse_efi_setup(u64 phys_addr, u32 data_len); #else /* * IF EFI is not configured, have the EFI calls return -ENOSYS. @@ -122,6 +163,7 @@ extern struct console early_efi_console; #define efi_call4(_f, _a1, _a2, _a3, _a4) (-ENOSYS) #define efi_call5(_f, _a1, _a2, _a3, _a4, _a5) (-ENOSYS) #define efi_call6(_f, _a1, _a2, _a3, _a4, _a5, _a6) (-ENOSYS) +static inline void parse_efi_setup(u64 phys_addr, u32 data_len) {} #endif /* CONFIG_EFI */ #endif /* _ASM_X86_EFI_H */ diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h index c49a613c6452..cea1c76d49bf 100644 --- a/arch/x86/include/asm/fpu-internal.h +++ b/arch/x86/include/asm/fpu-internal.h @@ -293,12 +293,13 @@ 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 */ - alternative_input( - ASM_NOP8 ASM_NOP2, - "emms\n\t" /* clear stack tags */ - "fildl %P[addr]", /* set F?P to defined value */ - X86_FEATURE_FXSAVE_LEAK, - [addr] "m" (tsk->thread.fpu.has_fpu)); + if (unlikely(static_cpu_has(X86_FEATURE_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); } diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h index cba45d99ac1a..67d69b8e2d20 100644 --- a/arch/x86/include/asm/hw_irq.h +++ b/arch/x86/include/asm/hw_irq.h @@ -191,6 +191,9 @@ extern void (*__initconst interrupt[NR_VECTORS-FIRST_EXTERNAL_VECTOR])(void); #define trace_interrupt interrupt #endif +#define VECTOR_UNDEFINED -1 +#define VECTOR_RETRIGGERED -2 + typedef int vector_irq_t[NR_VECTORS]; DECLARE_PER_CPU(vector_irq_t, vector_irq); extern void setup_vector_irq(int cpu); diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index c696a8687567..6e4ce2df87cf 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -118,7 +118,6 @@ extern void mce_register_decode_chain(struct notifier_block *nb); extern void mce_unregister_decode_chain(struct notifier_block *nb); #include <linux/percpu.h> -#include <linux/init.h> #include <linux/atomic.h> extern int mce_p5_enabled; diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h index 3142a94c7b4b..3e6b4920ef5d 100644 --- a/arch/x86/include/asm/mpspec.h +++ b/arch/x86/include/asm/mpspec.h @@ -1,7 +1,6 @@ #ifndef _ASM_X86_MPSPEC_H #define _ASM_X86_MPSPEC_H -#include <linux/init.h> #include <asm/mpspec_def.h> #include <asm/x86_init.h> diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h index 2f366d0ac6b4..1da25a5f96f9 100644 --- a/arch/x86/include/asm/mwait.h +++ b/arch/x86/include/asm/mwait.h @@ -1,6 +1,8 @@ #ifndef _ASM_X86_MWAIT_H #define _ASM_X86_MWAIT_H +#include <linux/sched.h> + #define MWAIT_SUBSTATE_MASK 0xf #define MWAIT_CSTATE_MASK 0xf #define MWAIT_SUBSTATE_SIZE 4 @@ -13,4 +15,45 @@ #define MWAIT_ECX_INTERRUPT_BREAK 0x1 +static inline void __monitor(const void *eax, unsigned long ecx, + unsigned long edx) +{ + /* "monitor %eax, %ecx, %edx;" */ + asm volatile(".byte 0x0f, 0x01, 0xc8;" + :: "a" (eax), "c" (ecx), "d"(edx)); +} + +static inline void __mwait(unsigned long eax, unsigned long ecx) +{ + /* "mwait %eax, %ecx;" */ + asm volatile(".byte 0x0f, 0x01, 0xc9;" + :: "a" (eax), "c" (ecx)); +} + +/* + * This uses new MONITOR/MWAIT instructions on P4 processors with PNI, + * which can obviate IPI to trigger checking of need_resched. + * We execute MONITOR against need_resched and enter optimized wait state + * through MWAIT. Whenever someone changes need_resched, we would be woken + * up from MWAIT (without an IPI). + * + * New with Core Duo processors, MWAIT can take some hints based on CPU + * capability. + */ +static inline void mwait_idle_with_hints(unsigned long eax, unsigned long ecx) +{ + if (!current_set_polling_and_test()) { + if (static_cpu_has(X86_FEATURE_CLFLUSH_MONITOR)) { + mb(); + clflush((void *)¤t_thread_info()->flags); + mb(); + } + + __monitor((void *)¤t_thread_info()->flags, 0, 0); + if (!need_resched()) + __mwait(eax, ecx); + } + current_clr_polling(); +} + #endif /* _ASM_X86_MWAIT_H */ diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 0ecac257fb26..a83aa44bb1fb 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -382,7 +382,8 @@ static inline void update_page_count(int level, unsigned long pages) { } */ extern pte_t *lookup_address(unsigned long address, unsigned int *level); extern phys_addr_t slow_virt_to_phys(void *__address); - +extern int kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address, + unsigned numpages, unsigned long page_flags); #endif /* !__ASSEMBLY__ */ #endif /* _ASM_X86_PGTABLE_DEFS_H */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 7b034a4057f9..a61b0717da32 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -27,7 +27,6 @@ struct mm_struct; #include <linux/cache.h> #include <linux/threads.h> #include <linux/math64.h> -#include <linux/init.h> #include <linux/err.h> #include <linux/irqflags.h> @@ -72,6 +71,7 @@ extern u16 __read_mostly tlb_lli_4m[NR_INFO]; extern u16 __read_mostly tlb_lld_4k[NR_INFO]; extern u16 __read_mostly tlb_lld_2m[NR_INFO]; extern u16 __read_mostly tlb_lld_4m[NR_INFO]; +extern u16 __read_mostly tlb_lld_1g[NR_INFO]; extern s8 __read_mostly tlb_flushall_shift; /* @@ -700,29 +700,6 @@ static inline void sync_core(void) #endif } -static inline void __monitor(const void *eax, unsigned long ecx, - unsigned long edx) -{ - /* "monitor %eax, %ecx, %edx;" */ - asm volatile(".byte 0x0f, 0x01, 0xc8;" - :: "a" (eax), "c" (ecx), "d"(edx)); -} - -static inline void __mwait(unsigned long eax, unsigned long ecx) -{ - /* "mwait %eax, %ecx;" */ - asm volatile(".byte 0x0f, 0x01, 0xc9;" - :: "a" (eax), "c" (ecx)); -} - -static inline void __sti_mwait(unsigned long eax, unsigned long ecx) -{ - trace_hardirqs_on(); - /* "mwait %eax, %ecx;" */ - asm volatile("sti; .byte 0x0f, 0x01, 0xc9;" - :: "a" (eax), "c" (ecx)); -} - extern void select_idle_routine(const struct cpuinfo_x86 *c); extern void init_amd_e400_c1e_mask(void); diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index 942a08623a1a..14fd6fd75a19 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -60,7 +60,6 @@ struct pt_regs { #endif /* !__i386__ */ -#include <linux/init.h> #ifdef CONFIG_PARAVIRT #include <asm/paravirt_types.h> #endif diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index 4137890e88e3..8cd27e08e23c 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -2,7 +2,6 @@ #define _ASM_X86_SMP_H #ifndef __ASSEMBLY__ #include <linux/cpumask.h> -#include <linux/init.h> #include <asm/percpu.h> /* diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h index 34baa0eb5d0c..a04eabd43d06 100644 --- a/arch/x86/include/asm/timer.h +++ b/arch/x86/include/asm/timer.h @@ -1,9 +1,9 @@ #ifndef _ASM_X86_TIMER_H #define _ASM_X86_TIMER_H -#include <linux/init.h> #include <linux/pm.h> #include <linux/percpu.h> #include <linux/interrupt.h> +#include <linux/math64.h> #define TICK_SIZE (tick_nsec / 1000) @@ -12,68 +12,26 @@ extern int recalibrate_cpu_khz(void); extern int no_timer_check; -/* Accelerators for sched_clock() - * convert from cycles(64bits) => nanoseconds (64bits) - * basic equation: - * ns = cycles / (freq / ns_per_sec) - * ns = cycles * (ns_per_sec / freq) - * ns = cycles * (10^9 / (cpu_khz * 10^3)) - * ns = cycles * (10^6 / cpu_khz) +/* + * We use the full linear equation: f(x) = a + b*x, in order to allow + * a continuous function in the face of dynamic freq changes. * - * Then we use scaling math (suggested by george@mvista.com) to get: - * ns = cycles * (10^6 * SC / cpu_khz) / SC - * ns = cycles * cyc2ns_scale / SC + * Continuity means that when our frequency changes our slope (b); we want to + * ensure that: f(t) == f'(t), which gives: a + b*t == a' + b'*t. * - * And since SC is a constant power of two, we can convert the div - * into a shift. + * Without an offset (a) the above would not be possible. * - * We can use khz divisor instead of mhz to keep a better precision, since - * cyc2ns_scale is limited to 10^6 * 2^10, which fits in 32 bits. - * (mathieu.desnoyers@polymtl.ca) - * - * -johnstul@us.ibm.com "math is hard, lets go shopping!" - * - * In: - * - * ns = cycles * cyc2ns_scale / SC - * - * Although we may still have enough bits to store the value of ns, - * in some cases, we may not have enough bits to store cycles * cyc2ns_scale, - * leading to an incorrect result. - * - * To avoid this, we can decompose 'cycles' into quotient and remainder - * of division by SC. Then, - * - * ns = (quot * SC + rem) * cyc2ns_scale / SC - * = quot * cyc2ns_scale + (rem * cyc2ns_scale) / SC - * - * - sqazi@google.com + * See the comment near cycles_2_ns() for details on how we compute (b). */ - -DECLARE_PER_CPU(unsigned long, cyc2ns); -DECLARE_PER_CPU(unsigned long long, cyc2ns_offset); - -#define CYC2NS_SCALE_FACTOR 10 /* 2^10, carefully chosen */ - -static inline unsigned long long __cycles_2_ns(unsigned long long cyc) -{ - int cpu = smp_processor_id(); - unsigned long long ns = per_cpu(cyc2ns_offset, cpu); - ns += mult_frac(cyc, per_cpu(cyc2ns, cpu), - (1UL << CYC2NS_SCALE_FACTOR)); - return ns; -} - -static inline unsigned long long cycles_2_ns(unsigned long long cyc) -{ - unsigned long long ns; - unsigned long flags; - - local_irq_save(flags); - ns = __cycles_2_ns(cyc); - local_irq_restore(flags); - - return ns; -} +struct cyc2ns_data { + u32 cyc2ns_mul; + u32 cyc2ns_shift; + u64 cyc2ns_offset; + u32 __count; + /* u32 hole */ +}; /* 24 bytes -- do not grow */ + +extern struct cyc2ns_data *cyc2ns_read_begin(void); +extern void cyc2ns_read_end(struct cyc2ns_data *); #endif /* _ASM_X86_TIMER_H */ diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 8ec57c07b125..6f1bb74d547b 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -40,22 +40,30 @@ /* * Test whether a block of memory is a valid user space address. * Returns 0 if the range is valid, nonzero otherwise. - * - * This is equivalent to the following test: - * (u33)addr + (u33)size > (u33)current->addr_limit.seg (u65 for x86_64) - * - * This needs 33-bit (65-bit for x86_64) arithmetic. We have a carry... */ +static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, unsigned long limit) +{ + /* + * If we have used "sizeof()" for the size, + * we know it won't overflow the limit (but + * it might overflow the 'addr', so it's + * important to subtract the size from the + * limit, not add it to the address). + */ + if (__builtin_constant_p(size)) + return addr > limit - size; + + /* Arbitrary sizes? Be careful about overflow */ + addr += size; + if (addr < size) + return true; + return addr > limit; +} #define __range_not_ok(addr, size, limit) \ ({ \ - unsigned long flag, roksum; \ __chk_user_ptr(addr); \ - asm("add %3,%1 ; sbb %0,%0 ; cmp %1,%4 ; sbb $0,%0" \ - : "=&r" (flag), "=r" (roksum) \ - : "1" (addr), "g" ((long)(size)), \ - "rm" (limit)); \ - flag; \ + __chk_range_not_ok((unsigned long __force)(addr), size, limit); \ }) /** @@ -78,7 +86,7 @@ * this function, memory access functions may still return -EFAULT. */ #define access_ok(type, addr, size) \ - (likely(__range_not_ok(addr, size, user_addr_max()) == 0)) + likely(!__range_not_ok(addr, size, user_addr_max())) /* * The exception table consists of pairs of addresses relative to the diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index 190413d0de57..12a26b979bf1 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -204,13 +204,13 @@ int __copy_in_user(void __user *dst, const void __user *src, unsigned size) static __must_check __always_inline int __copy_from_user_inatomic(void *dst, const void __user *src, unsigned size) { - return __copy_from_user_nocheck(dst, (__force const void *)src, size); + return __copy_from_user_nocheck(dst, src, size); } static __must_check __always_inline int __copy_to_user_inatomic(void __user *dst, const void *src, unsigned size) { - return __copy_to_user_nocheck((__force void *)dst, src, size); + return __copy_to_user_nocheck(dst, src, size); } extern long __copy_user_nocache(void *dst, const void __user *src, diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h index 9c3733c5f8f7..225b0988043a 100644 --- a/arch/x86/include/uapi/asm/bootparam.h +++ b/arch/x86/include/uapi/asm/bootparam.h @@ -6,6 +6,7 @@ #define SETUP_E820_EXT 1 #define SETUP_DTB 2 #define SETUP_PCI 3 +#define SETUP_EFI 4 /* ram_size flags */ #define RAMDISK_IMAGE_START_MASK 0x07FF @@ -23,6 +24,7 @@ #define XLF_CAN_BE_LOADED_ABOVE_4G (1<<1) #define XLF_EFI_HANDOVER_32 (1<<2) #define XLF_EFI_HANDOVER_64 (1<<3) +#define XLF_EFI_KEXEC (1<<4) #ifndef __ASSEMBLY__ diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 9b0a34e2cd79..510cca5c5390 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -29,6 +29,7 @@ obj-$(CONFIG_X86_64) += sys_x86_64.o x8664_ksyms_64.o obj-y += syscall_$(BITS).o obj-$(CONFIG_X86_64) += vsyscall_64.o obj-$(CONFIG_X86_64) += vsyscall_emu_64.o +obj-$(CONFIG_SYSFS) += ksysfs.o obj-y += bootflag.o e820.o obj-y += pci-dma.o quirks.o topology.o kdebugfs.o obj-y += alternative.o i8253.o pci-nommu.o hw_breakpoint.o diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c index d2b7f27781bc..e69182fd01cf 100644 --- a/arch/x86/kernel/acpi/cstate.c +++ b/arch/x86/kernel/acpi/cstate.c @@ -150,29 +150,6 @@ int acpi_processor_ffh_cstate_probe(unsigned int cpu, } EXPORT_SYMBOL_GPL(acpi_processor_ffh_cstate_probe); -/* - * This uses new MONITOR/MWAIT instructions on P4 processors with PNI, - * which can obviate IPI to trigger checking of need_resched. - * We execute MONITOR against need_resched and enter optimized wait state - * through MWAIT. Whenever someone changes need_resched, we would be woken - * up from MWAIT (without an IPI). - * - * New with Core Duo processors, MWAIT can take some hints based on CPU - * capability. - */ -void mwait_idle_with_hints(unsigned long ax, unsigned long cx) -{ - if (!need_resched()) { - if (this_cpu_has(X86_FEATURE_CLFLUSH_MONITOR)) - clflush((void *)¤t_thread_info()->flags); - - __monitor((void *)¤t_thread_info()->flags, 0, 0); - smp_mb(); - if (!need_resched()) - __mwait(ax, cx); - } -} - void acpi_processor_ffh_cstate_enter(struct acpi_processor_cx *cx) { unsigned int cpu = smp_processor_id(); diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index d278736bf774..7f26c9a70a9e 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -75,6 +75,13 @@ unsigned int max_physical_apicid; physid_mask_t phys_cpu_present_map; /* + * Processor to be disabled specified by kernel parameter + * disable_cpu_apicid=<int>, mostly used for the kdump 2nd kernel to + * avoid undefined behaviour caused by sending INIT from AP to BSP. + */ +static unsigned int disabled_cpu_apicid __read_mostly = BAD_APICID; + +/* * Map cpu index to physical APIC ID */ DEFINE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_cpu_to_apicid, BAD_APICID); @@ -1968,7 +1975,7 @@ __visible void smp_trace_spurious_interrupt(struct pt_regs *regs) */ static inline void __smp_error_interrupt(struct pt_regs *regs) { - u32 v0, v1; + u32 v; u32 i = 0; static const char * const error_interrupt_reason[] = { "Send CS error", /* APIC Error Bit 0 */ @@ -1982,21 +1989,20 @@ static inline void __smp_error_interrupt(struct pt_regs *regs) }; /* First tickle the hardware, only then report what went on. -- REW */ - v0 = apic_read(APIC_ESR); apic_write(APIC_ESR, 0); - v1 = apic_read(APIC_ESR); + v = apic_read(APIC_ESR); ack_APIC_irq(); atomic_inc(&irq_err_count); - apic_printk(APIC_DEBUG, KERN_DEBUG "APIC error on CPU%d: %02x(%02x)", - smp_processor_id(), v0 , v1); + apic_printk(APIC_DEBUG, KERN_DEBUG "APIC error on CPU%d: %02x", + smp_processor_id(), v); - v1 = v1 & 0xff; - while (v1) { - if (v1 & 0x1) + v &= 0xff; + while (v) { + if (v & 0x1) apic_printk(APIC_DEBUG, KERN_CONT " : %s", error_interrupt_reason[i]); i++; - v1 >>= 1; + v >>= 1; } apic_printk(APIC_DEBUG, KERN_CONT "\n"); @@ -2115,6 +2121,39 @@ int generic_processor_info(int apicid, int version) phys_cpu_present_map); /* + * boot_cpu_physical_apicid is designed to have the apicid + * returned by read_apic_id(), i.e, the apicid of the + * currently booting-up processor. However, on some platforms, + * it is temporarily modified by the apicid reported as BSP + * through MP table. Concretely: + * + * - arch/x86/kernel/mpparse.c: MP_processor_info() + * - arch/x86/mm/amdtopology.c: amd_numa_init() + * - arch/x86/platform/visws/visws_quirks.c: MP_processor_info() + * + * This function is executed with the modified + * boot_cpu_physical_apicid. So, disabled_cpu_apicid kernel + * parameter doesn't work to disable APs on kdump 2nd kernel. + * + * Since fixing handling of boot_cpu_physical_apicid requires + * another discussion and tests on each platform, we leave it + * for now and here we use read_apic_id() directly in this + * function, generic_processor_info(). + */ + if (disabled_cpu_apicid != BAD_APICID && + disabled_cpu_apicid != read_apic_id() && + disabled_cpu_apicid == apicid) { + int thiscpu = num_processors + disabled_cpus; + + pr_warning("APIC: Disabling requested cpu." + " Processor %d/0x%x ignored.\n", + thiscpu, apicid); + + disabled_cpus++; + return -ENODEV; + } + + /* * If boot cpu has not been detected yet, then only allow upto * nr_cpu_ids - 1 processors and keep one slot free for boot cpu */ @@ -2592,3 +2631,12 @@ static int __init lapic_insert_resource(void) * that is using request_resource */ late_initcall(lapic_insert_resource); + +static int __init apic_set_disabled_cpu_apicid(char *arg) +{ + if (!arg || !get_option(&arg, &disabled_cpu_apicid)) + return -EINVAL; + + return 0; +} +early_param("disable_cpu_apicid", apic_set_disabled_cpu_apicid); diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c index 00c77cf78e9e..5d5b9eb2b7a4 100644 --- a/arch/x86/kernel/apic/apic_flat_64.c +++ b/arch/x86/kernel/apic/apic_flat_64.c @@ -14,7 +14,6 @@ #include <linux/string.h> #include <linux/kernel.h> #include <linux/ctype.h> -#include <linux/init.h> #include <linux/hardirq.h> #include <linux/module.h> #include <asm/smp.h> diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c index e145f28b4099..191ce75c0e54 100644 --- a/arch/x86/kernel/apic/apic_noop.c +++ b/arch/x86/kernel/apic/apic_noop.c @@ -15,7 +15,6 @@ #include <linux/string.h> #include <linux/kernel.h> #include <linux/ctype.h> -#include <linux/init.h> #include <linux/errno.h> #include <asm/fixmap.h> #include <asm/mpspec.h> diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index e63a5bd2a78f..a43f068ebec1 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1142,9 +1142,10 @@ next: if (test_bit(vector, used_vectors)) goto next; - for_each_cpu_and(new_cpu, tmp_mask, cpu_online_mask) - if (per_cpu(vector_irq, new_cpu)[vector] != -1) + for_each_cpu_and(new_cpu, tmp_mask, cpu_online_mask) { + if (per_cpu(vector_irq, new_cpu)[vector] > VECTOR_UNDEFINED) goto next; + } /* Found one! */ current_vector = vector; current_offset = offset; @@ -1183,7 +1184,7 @@ static void __clear_irq_vector(int irq, struct irq_cfg *cfg) vector = cfg->vector; for_each_cpu_and(cpu, cfg->domain, cpu_online_mask) - per_cpu(vector_irq, cpu)[vector] = -1; + per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED; cfg->vector = 0; cpumask_clear(cfg->domain); @@ -1191,11 +1192,10 @@ static void __clear_irq_vector(int irq, struct irq_cfg *cfg) if (likely(!cfg->move_in_progress)) return; for_each_cpu_and(cpu, cfg->old_domain, cpu_online_mask) { - for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; - vector++) { + for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) { if (per_cpu(vector_irq, cpu)[vector] != irq) continue; - per_cpu(vector_irq, cpu)[vector] = -1; + per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED; break; } } @@ -1228,12 +1228,12 @@ void __setup_vector_irq(int cpu) /* Mark the free vectors */ for (vector = 0; vector < NR_VECTORS; ++vector) { irq = per_cpu(vector_irq, cpu)[vector]; - if (irq < 0) + if (irq <= VECTOR_UNDEFINED) continue; cfg = irq_cfg(irq); if (!cpumask_test_cpu(cpu, cfg->domain)) - per_cpu(vector_irq, cpu)[vector] = -1; + per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED; } raw_spin_unlock(&vector_lock); } @@ -2202,13 +2202,13 @@ asmlinkage void smp_irq_move_cleanup_interrupt(void) me = smp_processor_id(); for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) { - unsigned int irq; + int irq; unsigned int irr; struct irq_desc *desc; struct irq_cfg *cfg; irq = __this_cpu_read(vector_irq[vector]); - if (irq == -1) + if (irq <= VECTOR_UNDEFINED) continue; desc = irq_to_desc(irq); diff --git a/arch/x86/kernel/apic/ipi.c b/arch/x86/kernel/apic/ipi.c index 7434d8556d09..62071569bd50 100644 --- a/arch/x86/kernel/apic/ipi.c +++ b/arch/x86/kernel/apic/ipi.c @@ -1,6 +1,5 @@ #include <linux/cpumask.h> #include <linux/interrupt.h> -#include <linux/init.h> #include <linux/mm.h> #include <linux/delay.h> diff --git a/arch/x86/kernel/apic/summit_32.c b/arch/x86/kernel/apic/summit_32.c index 77c95c0e1bf7..00146f9b0254 100644 --- a/arch/x86/kernel/apic/summit_32.c +++ b/arch/x86/kernel/apic/summit_32.c @@ -29,7 +29,6 @@ #define pr_fmt(fmt) "summit: %s: " fmt, __func__ #include <linux/mm.h> -#include <linux/init.h> #include <asm/io.h> #include <asm/bios_ebda.h> diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index 140e29db478d..cac85ee6913f 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -3,7 +3,6 @@ #include <linux/string.h> #include <linux/kernel.h> #include <linux/ctype.h> -#include <linux/init.h> #include <linux/dmar.h> #include <linux/cpu.h> diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c index 562a76d433c8..de231e328cae 100644 --- a/arch/x86/kernel/apic/x2apic_phys.c +++ b/arch/x86/kernel/apic/x2apic_phys.c @@ -3,7 +3,6 @@ #include <linux/string.h> #include <linux/kernel.h> #include <linux/ctype.h> -#include <linux/init.h> #include <linux/dmar.h> #include <asm/smp.h> diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 47b56a7e99cb..6359506a19ee 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -36,7 +36,7 @@ obj-$(CONFIG_CPU_SUP_AMD) += perf_event_amd_iommu.o endif obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_p6.o perf_event_knc.o perf_event_p4.o obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_lbr.o perf_event_intel_ds.o perf_event_intel.o -obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_uncore.o +obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_uncore.o perf_event_intel_rapl.o endif diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index bca023bdd6b2..525712c7ffa2 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -1,5 +1,4 @@ #include <linux/export.h> -#include <linux/init.h> #include <linux/bitops.h> #include <linux/elf.h> #include <linux/mm.h> @@ -487,7 +486,7 @@ static void early_init_amd(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC); if (!check_tsc_unstable()) - sched_clock_stable = 1; + set_sched_clock_stable(); } #ifdef CONFIG_X86_64 @@ -790,14 +789,10 @@ static void cpu_detect_tlb_amd(struct cpuinfo_x86 *c) } /* Handle DTLB 2M and 4M sizes, fall back to L1 if L2 is disabled */ - if (!((eax >> 16) & mask)) { - u32 a, b, c, d; - - cpuid(0x80000005, &a, &b, &c, &d); - tlb_lld_2m[ENTRIES] = (a >> 16) & 0xff; - } else { + if (!((eax >> 16) & mask)) + tlb_lld_2m[ENTRIES] = (cpuid_eax(0x80000005) >> 16) & 0xff; + else tlb_lld_2m[ENTRIES] = (eax >> 16) & mask; - } /* a 4M entry uses two 2M entries */ tlb_lld_4m[ENTRIES] = tlb_lld_2m[ENTRIES] >> 1; diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c index 8d5652dc99dd..8779edab684e 100644 --- a/arch/x86/kernel/cpu/centaur.c +++ b/arch/x86/kernel/cpu/centaur.c @@ -1,6 +1,5 @@ #include <linux/bitops.h> #include <linux/kernel.h> -#include <linux/init.h> #include <asm/processor.h> #include <asm/e820.h> diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 6abc172b8258..24b6fd10625a 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -472,6 +472,7 @@ u16 __read_mostly tlb_lli_4m[NR_INFO]; u16 __read_mostly tlb_lld_4k[NR_INFO]; u16 __read_mostly tlb_lld_2m[NR_INFO]; u16 __read_mostly tlb_lld_4m[NR_INFO]; +u16 __read_mostly tlb_lld_1g[NR_INFO]; /* * tlb_flushall_shift shows the balance point in replacing cr3 write @@ -486,13 +487,13 @@ void cpu_detect_tlb(struct cpuinfo_x86 *c) if (this_cpu->c_detect_tlb) this_cpu->c_detect_tlb(c); - printk(KERN_INFO "Last level iTLB entries: 4KB %d, 2MB %d, 4MB %d\n" \ - "Last level dTLB entries: 4KB %d, 2MB %d, 4MB %d\n" \ + printk(KERN_INFO "Last level iTLB entries: 4KB %d, 2MB %d, 4MB %d\n" + "Last level dTLB entries: 4KB %d, 2MB %d, 4MB %d, 1GB %d\n" "tlb_flushall_shift: %d\n", tlb_lli_4k[ENTRIES], tlb_lli_2m[ENTRIES], tlb_lli_4m[ENTRIES], tlb_lld_4k[ENTRIES], tlb_lld_2m[ENTRIES], tlb_lld_4m[ENTRIES], - tlb_flushall_shift); + tlb_lld_1g[ENTRIES], tlb_flushall_shift); } void detect_ht(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c index d0969c75ab54..aaf152e79637 100644 --- a/arch/x86/kernel/cpu/cyrix.c +++ b/arch/x86/kernel/cpu/cyrix.c @@ -1,4 +1,3 @@ -#include <linux/init.h> #include <linux/bitops.h> #include <linux/delay.h> #include <linux/pci.h> diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index ea04b342c026..3db61c644e44 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -1,4 +1,3 @@ -#include <linux/init.h> #include <linux/kernel.h> #include <linux/string.h> @@ -93,7 +92,7 @@ static void early_init_intel(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC); if (!check_tsc_unstable()) - sched_clock_stable = 1; + set_sched_clock_stable(); } /* Penwell and Cloverview have the TSC which doesn't sleep on S3 */ @@ -506,6 +505,7 @@ static unsigned int intel_size_cache(struct cpuinfo_x86 *c, unsigned int size) #define TLB_DATA0_2M_4M 0x23 #define STLB_4K 0x41 +#define STLB_4K_2M 0x42 static const struct _tlb_table intel_tlb_table[] = { { 0x01, TLB_INST_4K, 32, " TLB_INST 4 KByte pages, 4-way set associative" }, @@ -526,13 +526,20 @@ static const struct _tlb_table intel_tlb_table[] = { { 0x5b, TLB_DATA_4K_4M, 64, " TLB_DATA 4 KByte and 4 MByte pages" }, { 0x5c, TLB_DATA_4K_4M, 128, " TLB_DATA 4 KByte and 4 MByte pages" }, { 0x5d, TLB_DATA_4K_4M, 256, " TLB_DATA 4 KByte and 4 MByte pages" }, + { 0x61, TLB_INST_4K, 48, " TLB_INST 4 KByte pages, full associative" }, + { 0x63, TLB_DATA_1G, 4, " TLB_DATA 1 GByte pages, 4-way set associative" }, + { 0x76, TLB_INST_2M_4M, 8, " TLB_INST 2-MByte or 4-MByte pages, fully associative" }, { 0xb0, TLB_INST_4K, 128, " TLB_INST 4 KByte pages, 4-way set associative" }, { 0xb1, TLB_INST_2M_4M, 4, " TLB_INST 2M pages, 4-way, 8 entries or 4M pages, 4-way entries" }, { 0xb2, TLB_INST_4K, 64, " TLB_INST 4KByte pages, 4-way set associative" }, { 0xb3, TLB_DATA_4K, 128, " TLB_DATA 4 KByte pages, 4-way set associative" }, { 0xb4, TLB_DATA_4K, 256, " TLB_DATA 4 KByte pages, 4-way associative" }, + { 0xb5, TLB_INST_4K, 64, " TLB_INST 4 KByte pages, 8-way set ssociative" }, + { 0xb6, TLB_INST_4K, 128, " TLB_INST 4 KByte pages, 8-way set ssociative" }, { 0xba, TLB_DATA_4K, 64, " TLB_DATA 4 KByte pages, 4-way associative" }, { 0xc0, TLB_DATA_4K_4M, 8, " TLB_DATA 4 KByte and 4 MByte pages, 4-way associative" }, + { 0xc1, STLB_4K_2M, 1024, " STLB 4 KByte and 2 MByte pages, 8-way associative" }, + { 0xc2, TLB_DATA_2M_4M, 16, " DTLB 2 MByte/4MByte pages, 4-way associative" }, { 0xca, STLB_4K, 512, " STLB 4 KByte pages, 4-way associative" }, { 0x00, 0, 0 } }; @@ -558,6 +565,20 @@ static void intel_tlb_lookup(const unsigned char desc) if (tlb_lld_4k[ENTRIES] < intel_tlb_table[k].entries) tlb_lld_4k[ENTRIES] = intel_tlb_table[k].entries; break; + case STLB_4K_2M: + if (tlb_lli_4k[ENTRIES] < intel_tlb_table[k].entries) + tlb_lli_4k[ENTRIES] = intel_tlb_table[k].entries; + if (tlb_lld_4k[ENTRIES] < intel_tlb_table[k].entries) + tlb_lld_4k[ENTRIES] = intel_tlb_table[k].entries; + if (tlb_lli_2m[ENTRIES] < intel_tlb_table[k].entries) + tlb_lli_2m[ENTRIES] = intel_tlb_table[k].entries; + if (tlb_lld_2m[ENTRIES] < intel_tlb_table[k].entries) + tlb_lld_2m[ENTRIES] = intel_tlb_table[k].entries; + if (tlb_lli_4m[ENTRIES] < intel_tlb_table[k].entries) + tlb_lli_4m[ENTRIES] = intel_tlb_table[k].entries; + if (tlb_lld_4m[ENTRIES] < intel_tlb_table[k].entries) + tlb_lld_4m[ENTRIES] = intel_tlb_table[k].entries; + break; case TLB_INST_ALL: if (tlb_lli_4k[ENTRIES] < intel_tlb_table[k].entries) tlb_lli_4k[ENTRIES] = intel_tlb_table[k].entries; @@ -603,6 +624,10 @@ static void intel_tlb_lookup(const unsigned char desc) if (tlb_lld_4m[ENTRIES] < intel_tlb_table[k].entries) tlb_lld_4m[ENTRIES] = intel_tlb_table[k].entries; break; + case TLB_DATA_1G: + if (tlb_lld_1g[ENTRIES] < intel_tlb_table[k].entries) + tlb_lld_1g[ENTRIES] = intel_tlb_table[k].entries; + break; } } diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c index 4cfe0458ca66..fb6156fee6f7 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_intel.c +++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c @@ -6,7 +6,6 @@ */ #include <linux/gfp.h> -#include <linux/init.h> #include <linux/interrupt.h> #include <linux/percpu.h> #include <linux/sched.h> diff --git a/arch/x86/kernel/cpu/mcheck/p5.c b/arch/x86/kernel/cpu/mcheck/p5.c index 1c044b1ccc59..a3042989398c 100644 --- a/arch/x86/kernel/cpu/mcheck/p5.c +++ b/arch/x86/kernel/cpu/mcheck/p5.c @@ -5,7 +5,6 @@ #include <linux/interrupt.h> #include <linux/kernel.h> #include <linux/types.h> -#include <linux/init.h> #include <linux/smp.h> #include <asm/processor.h> diff --git a/arch/x86/kernel/cpu/mcheck/winchip.c b/arch/x86/kernel/cpu/mcheck/winchip.c index e9a701aecaa1..7dc5564d0cdf 100644 --- a/arch/x86/kernel/cpu/mcheck/winchip.c +++ b/arch/x86/kernel/cpu/mcheck/winchip.c @@ -5,7 +5,6 @@ #include <linux/interrupt.h> #include <linux/kernel.h> #include <linux/types.h> -#include <linux/init.h> #include <asm/processor.h> #include <asm/mce.h> diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 8e132931614d..b88645191fe5 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -1883,21 +1883,27 @@ static struct pmu pmu = { void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now) { + struct cyc2ns_data *data; + userpg->cap_user_time = 0; userpg->cap_user_time_zero = 0; userpg->cap_user_rdpmc = x86_pmu.attr_rdpmc; userpg->pmc_width = x86_pmu.cntval_bits; - if (!sched_clock_stable) + if (!sched_clock_stable()) return; + data = cyc2ns_read_begin(); + userpg->cap_user_time = 1; - userpg->time_mult = this_cpu_read(cyc2ns); - userpg->time_shift = CYC2NS_SCALE_FACTOR; - userpg->time_offset = this_cpu_read(cyc2ns_offset) - now; + userpg->time_mult = data->cyc2ns_mul; + userpg->time_shift = data->cyc2ns_shift; + userpg->time_offset = data->cyc2ns_offset - now; userpg->cap_user_time_zero = 1; - userpg->time_zero = this_cpu_read(cyc2ns_offset); + userpg->time_zero = data->cyc2ns_offset; + + cyc2ns_read_end(data); } /* diff --git a/arch/x86/kernel/cpu/perf_event_amd_ibs.c b/arch/x86/kernel/cpu/perf_event_amd_ibs.c index e09f0bfb7b8f..4b8e4d3cd6ea 100644 --- a/arch/x86/kernel/cpu/perf_event_amd_ibs.c +++ b/arch/x86/kernel/cpu/perf_event_amd_ibs.c @@ -10,6 +10,7 @@ #include <linux/module.h> #include <linux/pci.h> #include <linux/ptrace.h> +#include <linux/syscore_ops.h> #include <asm/apic.h> @@ -816,6 +817,18 @@ out: return ret; } +static void ibs_eilvt_setup(void) +{ + /* + * Force LVT offset assignment for family 10h: The offsets are + * not assigned by the BIOS for this family, so the OS is + * responsible for doing it. If the OS assignment fails, fall + * back to BIOS settings and try to setup this. + */ + if (boot_cpu_data.x86 == 0x10) + force_ibs_eilvt_setup(); +} + static inline int get_ibs_lvt_offset(void) { u64 val; @@ -851,6 +864,36 @@ static void clear_APIC_ibs(void *dummy) setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_FIX, 1); } +#ifdef CONFIG_PM + +static int perf_ibs_suspend(void) +{ + clear_APIC_ibs(NULL); + return 0; +} + +static void perf_ibs_resume(void) +{ + ibs_eilvt_setup(); + setup_APIC_ibs(NULL); +} + +static struct syscore_ops perf_ibs_syscore_ops = { + .resume = perf_ibs_resume, + .suspend = perf_ibs_suspend, +}; + +static void perf_ibs_pm_init(void) +{ + register_syscore_ops(&perf_ibs_syscore_ops); +} + +#else + +static inline void perf_ibs_pm_init(void) { } + +#endif + static int perf_ibs_cpu_notifier(struct notifier_block *self, unsigned long action, void *hcpu) { @@ -877,18 +920,12 @@ static __init int amd_ibs_init(void) if (!caps) return -ENODEV; /* ibs not supported by the cpu */ - /* - * Force LVT offset assignment for family 10h: The offsets are - * not assigned by the BIOS for this family, so the OS is - * responsible for doing it. If the OS assignment fails, fall - * back to BIOS settings and try to setup this. - */ - if (boot_cpu_data.x86 == 0x10) - force_ibs_eilvt_setup(); + ibs_eilvt_setup(); if (!ibs_eilvt_valid()) goto out; + perf_ibs_pm_init(); get_online_cpus(); ibs_caps = caps; /* make ibs_caps visible to other cpus: */ diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c new file mode 100644 index 000000000000..5ad35ad94d0f --- /dev/null +++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c @@ -0,0 +1,679 @@ +/* + * perf_event_intel_rapl.c: support Intel RAPL energy consumption counters + * Copyright (C) 2013 Google, Inc., Stephane Eranian + * + * Intel RAPL interface is specified in the IA-32 Manual Vol3b + * section 14.7.1 (September 2013) + * + * RAPL provides more controls than just reporting energy consumption + * however here we only expose the 3 energy consumption free running + * counters (pp0, pkg, dram). + * + * Each of those counters increments in a power unit defined by the + * RAPL_POWER_UNIT MSR. On SandyBridge, this unit is 1/(2^16) Joules + * but it can vary. + * + * Counter to rapl events mappings: + * + * pp0 counter: consumption of all physical cores (power plane 0) + * event: rapl_energy_cores + * perf code: 0x1 + * + * pkg counter: consumption of the whole processor package + * event: rapl_energy_pkg + * perf code: 0x2 + * + * dram counter: consumption of the dram domain (servers only) + * event: rapl_energy_dram + * perf code: 0x3 + * + * dram counter: consumption of the builtin-gpu domain (client only) + * event: rapl_energy_gpu + * perf code: 0x4 + * + * We manage those counters as free running (read-only). They may be + * use simultaneously by other tools, such as turbostat. + * + * The events only support system-wide mode counting. There is no + * sampling support because it does not make sense and is not + * supported by the RAPL hardware. + * + * Because we want to avoid floating-point operations in the kernel, + * the events are all reported in fixed point arithmetic (32.32). + * Tools must adjust the counts to convert them to Watts using + * the duration of the measurement. Tools may use a function such as + * ldexp(raw_count, -32); + */ +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/perf_event.h> +#include <asm/cpu_device_id.h> +#include "perf_event.h" + +/* + * RAPL energy status counters + */ +#define RAPL_IDX_PP0_NRG_STAT 0 /* all cores */ +#define INTEL_RAPL_PP0 0x1 /* pseudo-encoding */ +#define RAPL_IDX_PKG_NRG_STAT 1 /* entire package */ +#define INTEL_RAPL_PKG 0x2 /* pseudo-encoding */ +#define RAPL_IDX_RAM_NRG_STAT 2 /* DRAM */ +#define INTEL_RAPL_RAM 0x3 /* pseudo-encoding */ +#define RAPL_IDX_PP1_NRG_STAT 3 /* DRAM */ +#define INTEL_RAPL_PP1 0x4 /* pseudo-encoding */ + +/* Clients have PP0, PKG */ +#define RAPL_IDX_CLN (1<<RAPL_IDX_PP0_NRG_STAT|\ + 1<<RAPL_IDX_PKG_NRG_STAT|\ + 1<<RAPL_IDX_PP1_NRG_STAT) + +/* Servers have PP0, PKG, RAM */ +#define RAPL_IDX_SRV (1<<RAPL_IDX_PP0_NRG_STAT|\ + 1<<RAPL_IDX_PKG_NRG_STAT|\ + 1<<RAPL_IDX_RAM_NRG_STAT) + +/* + * event code: LSB 8 bits, passed in attr->config + * any other bit is reserved + */ +#define RAPL_EVENT_MASK 0xFFULL + +#define DEFINE_RAPL_FORMAT_ATTR(_var, _name, _format) \ +static ssize_t __rapl_##_var##_show(struct kobject *kobj, \ + struct kobj_attribute *attr, \ + char *page) \ +{ \ + BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \ + return sprintf(page, _format "\n"); \ +} \ +static struct kobj_attribute format_attr_##_var = \ + __ATTR(_name, 0444, __rapl_##_var##_show, NULL) + +#define RAPL_EVENT_DESC(_name, _config) \ +{ \ + .attr = __ATTR(_name, 0444, rapl_event_show, NULL), \ + .config = _config, \ +} + +#define RAPL_CNTR_WIDTH 32 /* 32-bit rapl counters */ + +struct rapl_pmu { + spinlock_t lock; + int hw_unit; /* 1/2^hw_unit Joule */ + int n_active; /* number of active events */ + struct list_head active_list; + struct pmu *pmu; /* pointer to rapl_pmu_class */ + ktime_t timer_interval; /* in ktime_t unit */ + struct hrtimer hrtimer; +}; + +static struct pmu rapl_pmu_class; +static cpumask_t rapl_cpu_mask; +static int rapl_cntr_mask; + +static DEFINE_PER_CPU(struct rapl_pmu *, rapl_pmu); +static DEFINE_PER_CPU(struct rapl_pmu *, rapl_pmu_to_free); + +static inline u64 rapl_read_counter(struct perf_event *event) +{ + u64 raw; + rdmsrl(event->hw.event_base, raw); + return raw; +} + +static inline u64 rapl_scale(u64 v) +{ + /* + * scale delta to smallest unit (1/2^32) + * users must then scale back: count * 1/(1e9*2^32) to get Joules + * or use ldexp(count, -32). + * Watts = Joules/Time delta + */ + return v << (32 - __get_cpu_var(rapl_pmu)->hw_unit); +} + +static u64 rapl_event_update(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + u64 prev_raw_count, new_raw_count; + s64 delta, sdelta; + int shift = RAPL_CNTR_WIDTH; + +again: + prev_raw_count = local64_read(&hwc->prev_count); + rdmsrl(event->hw.event_base, new_raw_count); + + if (local64_cmpxchg(&hwc->prev_count, prev_raw_count, + new_raw_count) != prev_raw_count) { + cpu_relax(); + goto again; + } + + /* + * Now we have the new raw value and have updated the prev + * timestamp already. We can now calculate the elapsed delta + * (event-)time and add that to the generic event. + * + * Careful, not all hw sign-extends above the physical width + * of the count. + */ + delta = (new_raw_count << shift) - (prev_raw_count << shift); + delta >>= shift; + + sdelta = rapl_scale(delta); + + local64_add(sdelta, &event->count); + + return new_raw_count; +} + +static void rapl_start_hrtimer(struct rapl_pmu *pmu) +{ + __hrtimer_start_range_ns(&pmu->hrtimer, + pmu->timer_interval, 0, + HRTIMER_MODE_REL_PINNED, 0); +} + +static void rapl_stop_hrtimer(struct rapl_pmu *pmu) +{ + hrtimer_cancel(&pmu->hrtimer); +} + +static enum hrtimer_restart rapl_hrtimer_handle(struct hrtimer *hrtimer) +{ + struct rapl_pmu *pmu = __get_cpu_var(rapl_pmu); + struct perf_event *event; + unsigned long flags; + + if (!pmu->n_active) + return HRTIMER_NORESTART; + + spin_lock_irqsave(&pmu->lock, flags); + + list_for_each_entry(event, &pmu->active_list, active_entry) { + rapl_event_update(event); + } + + spin_unlock_irqrestore(&pmu->lock, flags); + + hrtimer_forward_now(hrtimer, pmu->timer_interval); + + return HRTIMER_RESTART; +} + +static void rapl_hrtimer_init(struct rapl_pmu *pmu) +{ + struct hrtimer *hr = &pmu->hrtimer; + + hrtimer_init(hr, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hr->function = rapl_hrtimer_handle; +} + +static void __rapl_pmu_event_start(struct rapl_pmu *pmu, + struct perf_event *event) +{ + if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED))) + return; + + event->hw.state = 0; + + list_add_tail(&event->active_entry, &pmu->active_list); + + local64_set(&event->hw.prev_count, rapl_read_counter(event)); + + pmu->n_active++; + if (pmu->n_active == 1) + rapl_start_hrtimer(pmu); +} + +static void rapl_pmu_event_start(struct perf_event *event, int mode) +{ + struct rapl_pmu *pmu = __get_cpu_var(rapl_pmu); + unsigned long flags; + + spin_lock_irqsave(&pmu->lock, flags); + __rapl_pmu_event_start(pmu, event); + spin_unlock_irqrestore(&pmu->lock, flags); +} + +static void rapl_pmu_event_stop(struct perf_event *event, int mode) +{ + struct rapl_pmu *pmu = __get_cpu_var(rapl_pmu); + struct hw_perf_event *hwc = &event->hw; + unsigned long flags; + + spin_lock_irqsave(&pmu->lock, flags); + + /* mark event as deactivated and stopped */ + if (!(hwc->state & PERF_HES_STOPPED)) { + WARN_ON_ONCE(pmu->n_active <= 0); + pmu->n_active--; + if (pmu->n_active == 0) + rapl_stop_hrtimer(pmu); + + list_del(&event->active_entry); + + WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED); + hwc->state |= PERF_HES_STOPPED; + } + + /* check if update of sw counter is necessary */ + if ((mode & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) { + /* + * Drain the remaining delta count out of a event + * that we are disabling: + */ + rapl_event_update(event); + hwc->state |= PERF_HES_UPTODATE; + } + + spin_unlock_irqrestore(&pmu->lock, flags); +} + +static int rapl_pmu_event_add(struct perf_event *event, int mode) +{ + struct rapl_pmu *pmu = __get_cpu_var(rapl_pmu); + struct hw_perf_event *hwc = &event->hw; + unsigned long flags; + + spin_lock_irqsave(&pmu->lock, flags); + + hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED; + + if (mode & PERF_EF_START) + __rapl_pmu_event_start(pmu, event); + + spin_unlock_irqrestore(&pmu->lock, flags); + + return 0; +} + +static void rapl_pmu_event_del(struct perf_event *event, int flags) +{ + rapl_pmu_event_stop(event, PERF_EF_UPDATE); +} + +static int rapl_pmu_event_init(struct perf_event *event) +{ + u64 cfg = event->attr.config & RAPL_EVENT_MASK; + int bit, msr, ret = 0; + + /* only look at RAPL events */ + if (event->attr.type != rapl_pmu_class.type) + return -ENOENT; + + /* check only supported bits are set */ + if (event->attr.config & ~RAPL_EVENT_MASK) + return -EINVAL; + + /* + * check event is known (determines counter) + */ + switch (cfg) { + case INTEL_RAPL_PP0: + bit = RAPL_IDX_PP0_NRG_STAT; + msr = MSR_PP0_ENERGY_STATUS; + break; + case INTEL_RAPL_PKG: + bit = RAPL_IDX_PKG_NRG_STAT; + msr = MSR_PKG_ENERGY_STATUS; + break; + case INTEL_RAPL_RAM: + bit = RAPL_IDX_RAM_NRG_STAT; + msr = MSR_DRAM_ENERGY_STATUS; + break; + case INTEL_RAPL_PP1: + bit = RAPL_IDX_PP1_NRG_STAT; + msr = MSR_PP1_ENERGY_STATUS; + break; + default: + return -EINVAL; + } + /* check event supported */ + if (!(rapl_cntr_mask & (1 << bit))) + return -EINVAL; + + /* unsupported modes and filters */ + if (event->attr.exclude_user || + event->attr.exclude_kernel || + event->attr.exclude_hv || + event->attr.exclude_idle || + event->attr.exclude_host || + event->attr.exclude_guest || + event->attr.sample_period) /* no sampling */ + return -EINVAL; + + /* must be done before validate_group */ + event->hw.event_base = msr; + event->hw.config = cfg; + event->hw.idx = bit; + + return ret; +} + +static void rapl_pmu_event_read(struct perf_event *event) +{ + rapl_event_update(event); +} + +static ssize_t rapl_get_attr_cpumask(struct device *dev, + struct device_attribute *attr, char *buf) +{ + int n = cpulist_scnprintf(buf, PAGE_SIZE - 2, &rapl_cpu_mask); + + buf[n++] = '\n'; + buf[n] = '\0'; + return n; +} + +static DEVICE_ATTR(cpumask, S_IRUGO, rapl_get_attr_cpumask, NULL); + +static struct attribute *rapl_pmu_attrs[] = { + &dev_attr_cpumask.attr, + NULL, +}; + +static struct attribute_group rapl_pmu_attr_group = { + .attrs = rapl_pmu_attrs, +}; + +EVENT_ATTR_STR(energy-cores, rapl_cores, "event=0x01"); +EVENT_ATTR_STR(energy-pkg , rapl_pkg, "event=0x02"); +EVENT_ATTR_STR(energy-ram , rapl_ram, "event=0x03"); +EVENT_ATTR_STR(energy-gpu , rapl_gpu, "event=0x04"); + +EVENT_ATTR_STR(energy-cores.unit, rapl_cores_unit, "Joules"); +EVENT_ATTR_STR(energy-pkg.unit , rapl_pkg_unit, "Joules"); +EVENT_ATTR_STR(energy-ram.unit , rapl_ram_unit, "Joules"); +EVENT_ATTR_STR(energy-gpu.unit , rapl_gpu_unit, "Joules"); + +/* + * we compute in 0.23 nJ increments regardless of MSR + */ +EVENT_ATTR_STR(energy-cores.scale, rapl_cores_scale, "2.3283064365386962890625e-10"); +EVENT_ATTR_STR(energy-pkg.scale, rapl_pkg_scale, "2.3283064365386962890625e-10"); +EVENT_ATTR_STR(energy-ram.scale, rapl_ram_scale, "2.3283064365386962890625e-10"); +EVENT_ATTR_STR(energy-gpu.scale, rapl_gpu_scale, "2.3283064365386962890625e-10"); + +static struct attribute *rapl_events_srv_attr[] = { + EVENT_PTR(rapl_cores), + EVENT_PTR(rapl_pkg), + EVENT_PTR(rapl_ram), + + EVENT_PTR(rapl_cores_unit), + EVENT_PTR(rapl_pkg_unit), + EVENT_PTR(rapl_ram_unit), + + EVENT_PTR(rapl_cores_scale), + EVENT_PTR(rapl_pkg_scale), + EVENT_PTR(rapl_ram_scale), + NULL, +}; + +static struct attribute *rapl_events_cln_attr[] = { + EVENT_PTR(rapl_cores), + EVENT_PTR(rapl_pkg), + EVENT_PTR(rapl_gpu), + + EVENT_PTR(rapl_cores_unit), + EVENT_PTR(rapl_pkg_unit), + EVENT_PTR(rapl_gpu_unit), + + EVENT_PTR(rapl_cores_scale), + EVENT_PTR(rapl_pkg_scale), + EVENT_PTR(rapl_gpu_scale), + NULL, +}; + +static struct attribute_group rapl_pmu_events_group = { + .name = "events", + .attrs = NULL, /* patched at runtime */ +}; + +DEFINE_RAPL_FORMAT_ATTR(event, event, "config:0-7"); +static struct attribute *rapl_formats_attr[] = { + &format_attr_event.attr, + NULL, +}; + +static struct attribute_group rapl_pmu_format_group = { + .name = "format", + .attrs = rapl_formats_attr, +}; + +const struct attribute_group *rapl_attr_groups[] = { + &rapl_pmu_attr_group, + &rapl_pmu_format_group, + &rapl_pmu_events_group, + NULL, +}; + +static struct pmu rapl_pmu_class = { + .attr_groups = rapl_attr_groups, + .task_ctx_nr = perf_invalid_context, /* system-wide only */ + .event_init = rapl_pmu_event_init, + .add = rapl_pmu_event_add, /* must have */ + .del = rapl_pmu_event_del, /* must have */ + .start = rapl_pmu_event_start, + .stop = rapl_pmu_event_stop, + .read = rapl_pmu_event_read, +}; + +static void rapl_cpu_exit(int cpu) +{ + struct rapl_pmu *pmu = per_cpu(rapl_pmu, cpu); + int i, phys_id = topology_physical_package_id(cpu); + int target = -1; + + /* find a new cpu on same package */ + for_each_online_cpu(i) { + if (i == cpu) + continue; + if (phys_id == topology_physical_package_id(i)) { + target = i; + break; + } + } + /* + * clear cpu from cpumask + * if was set in cpumask and still some cpu on package, + * then move to new cpu + */ + if (cpumask_test_and_clear_cpu(cpu, &rapl_cpu_mask) && target >= 0) + cpumask_set_cpu(target, &rapl_cpu_mask); + + WARN_ON(cpumask_empty(&rapl_cpu_mask)); + /* + * migrate events and context to new cpu + */ + if (target >= 0) + perf_pmu_migrate_context(pmu->pmu, cpu, target); + + /* cancel overflow polling timer for CPU */ + rapl_stop_hrtimer(pmu); +} + +static void rapl_cpu_init(int cpu) +{ + int i, phys_id = topology_physical_package_id(cpu); + + /* check if phys_is is already covered */ + for_each_cpu(i, &rapl_cpu_mask) { + if (phys_id == topology_physical_package_id(i)) + return; + } + /* was not found, so add it */ + cpumask_set_cpu(cpu, &rapl_cpu_mask); +} + +static int rapl_cpu_prepare(int cpu) +{ + struct rapl_pmu *pmu = per_cpu(rapl_pmu, cpu); + int phys_id = topology_physical_package_id(cpu); + u64 ms; + + if (pmu) + return 0; + + if (phys_id < 0) + return -1; + + pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu)); + if (!pmu) + return -1; + + spin_lock_init(&pmu->lock); + + INIT_LIST_HEAD(&pmu->active_list); + + /* + * grab power unit as: 1/2^unit Joules + * + * we cache in local PMU instance + */ + rdmsrl(MSR_RAPL_POWER_UNIT, pmu->hw_unit); + pmu->hw_unit = (pmu->hw_unit >> 8) & 0x1FULL; + pmu->pmu = &rapl_pmu_class; + + /* + * use reference of 200W for scaling the timeout + * to avoid missing counter overflows. + * 200W = 200 Joules/sec + * divide interval by 2 to avoid lockstep (2 * 100) + * if hw unit is 32, then we use 2 ms 1/200/2 + */ + if (pmu->hw_unit < 32) + ms = (1000 / (2 * 100)) * (1ULL << (32 - pmu->hw_unit - 1)); + else + ms = 2; + + pmu->timer_interval = ms_to_ktime(ms); + + rapl_hrtimer_init(pmu); + + /* set RAPL pmu for this cpu for now */ + per_cpu(rapl_pmu, cpu) = pmu; + per_cpu(rapl_pmu_to_free, cpu) = NULL; + + return 0; +} + +static void rapl_cpu_kfree(int cpu) +{ + struct rapl_pmu *pmu = per_cpu(rapl_pmu_to_free, cpu); + + kfree(pmu); + + per_cpu(rapl_pmu_to_free, cpu) = NULL; +} + +static int rapl_cpu_dying(int cpu) +{ + struct rapl_pmu *pmu = per_cpu(rapl_pmu, cpu); + + if (!pmu) + return 0; + + per_cpu(rapl_pmu, cpu) = NULL; + + per_cpu(rapl_pmu_to_free, cpu) = pmu; + + return 0; +} + +static int rapl_cpu_notifier(struct notifier_block *self, + unsigned long action, void *hcpu) +{ + unsigned int cpu = (long)hcpu; + + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_UP_PREPARE: + rapl_cpu_prepare(cpu); + break; + case CPU_STARTING: + rapl_cpu_init(cpu); + break; + case CPU_UP_CANCELED: + case CPU_DYING: + rapl_cpu_dying(cpu); + break; + case CPU_ONLINE: + case CPU_DEAD: + rapl_cpu_kfree(cpu); + break; + case CPU_DOWN_PREPARE: + rapl_cpu_exit(cpu); + break; + default: + break; + } + + return NOTIFY_OK; +} + +static const struct x86_cpu_id rapl_cpu_match[] = { + [0] = { .vendor = X86_VENDOR_INTEL, .family = 6 }, + [1] = {}, +}; + +static int __init rapl_pmu_init(void) +{ + struct rapl_pmu *pmu; + int cpu, ret; + + /* + * check for Intel processor family 6 + */ + if (!x86_match_cpu(rapl_cpu_match)) + return 0; + + /* check supported CPU */ + switch (boot_cpu_data.x86_model) { + case 42: /* Sandy Bridge */ + case 58: /* Ivy Bridge */ + case 60: /* Haswell */ + case 69: /* Haswell-Celeron */ + rapl_cntr_mask = RAPL_IDX_CLN; + rapl_pmu_events_group.attrs = rapl_events_cln_attr; + break; + case 45: /* Sandy Bridge-EP */ + case 62: /* IvyTown */ + rapl_cntr_mask = RAPL_IDX_SRV; + rapl_pmu_events_group.attrs = rapl_events_srv_attr; + break; + + default: + /* unsupported */ + return 0; + } + get_online_cpus(); + + for_each_online_cpu(cpu) { + rapl_cpu_prepare(cpu); + rapl_cpu_init(cpu); + } + + perf_cpu_notifier(rapl_cpu_notifier); + + ret = perf_pmu_register(&rapl_pmu_class, "power", -1); + if (WARN_ON(ret)) { + pr_info("RAPL PMU detected, registration failed (%d), RAPL PMU disabled\n", ret); + put_online_cpus(); + return -1; + } + + pmu = __get_cpu_var(rapl_pmu); + + pr_info("RAPL PMU detected, hw unit 2^-%d Joules," + " API unit is 2^-32 Joules," + " %d fixed counters" + " %llu ms ovfl timer\n", + pmu->hw_unit, + hweight32(rapl_cntr_mask), + ktime_to_ms(pmu->timer_interval)); + + put_online_cpus(); + + return 0; +} +device_initcall(rapl_pmu_init); diff --git a/arch/x86/kernel/cpu/transmeta.c b/arch/x86/kernel/cpu/transmeta.c index aa0430d69b90..3fa0e5ad86b4 100644 --- a/arch/x86/kernel/cpu/transmeta.c +++ b/arch/x86/kernel/cpu/transmeta.c @@ -1,6 +1,5 @@ #include <linux/kernel.h> #include <linux/mm.h> -#include <linux/init.h> #include <asm/processor.h> #include <asm/msr.h> #include "cpu.h" diff --git a/arch/x86/kernel/cpu/umc.c b/arch/x86/kernel/cpu/umc.c index 75c5ad5d35cc..ef9c2a0078bd 100644 --- a/arch/x86/kernel/cpu/umc.c +++ b/arch/x86/kernel/cpu/umc.c @@ -1,5 +1,4 @@ #include <linux/kernel.h> -#include <linux/init.h> #include <asm/processor.h> #include "cpu.h" diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 18677a90d6a3..a57902efe2d5 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -7,7 +7,6 @@ * */ -#include <linux/init.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/smp.h> diff --git a/arch/x86/kernel/doublefault.c b/arch/x86/kernel/doublefault.c index 5d3fe8d36e4a..f6dfd9334b67 100644 --- a/arch/x86/kernel/doublefault.c +++ b/arch/x86/kernel/doublefault.c @@ -1,6 +1,5 @@ #include <linux/mm.h> #include <linux/sched.h> -#include <linux/init.h> #include <linux/init_task.h> #include <linux/fs.h> diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 51e2988c5728..a2a4f4697889 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -1082,7 +1082,7 @@ ENTRY(ftrace_caller) pushl $0 /* Pass NULL as regs pointer */ movl 4*4(%esp), %eax movl 0x4(%ebp), %edx - leal function_trace_op, %ecx + movl function_trace_op, %ecx subl $MCOUNT_INSN_SIZE, %eax .globl ftrace_call @@ -1140,7 +1140,7 @@ ENTRY(ftrace_regs_caller) movl 12*4(%esp), %eax /* Load ip (1st parameter) */ subl $MCOUNT_INSN_SIZE, %eax /* Adjust ip */ movl 0x4(%ebp), %edx /* Load parent ip (2nd parameter) */ - leal function_trace_op, %ecx /* Save ftrace_pos in 3rd parameter */ + movl function_trace_op, %ecx /* Save ftrace_pos in 3rd parameter */ pushl %esp /* Save pt_regs as 4th parameter */ GLOBAL(ftrace_regs_call) diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index e21b0785a85b..1e96c3628bf2 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -88,7 +88,7 @@ END(function_hook) MCOUNT_SAVE_FRAME \skip /* Load the ftrace_ops into the 3rd parameter */ - leaq function_trace_op, %rdx + movq function_trace_op(%rip), %rdx /* Load ip into the first parameter */ movq RIP(%rsp), %rdi diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c index f66ff162dce8..a67b47c31314 100644 --- a/arch/x86/kernel/hw_breakpoint.c +++ b/arch/x86/kernel/hw_breakpoint.c @@ -38,7 +38,6 @@ #include <linux/kernel.h> #include <linux/module.h> #include <linux/sched.h> -#include <linux/init.h> #include <linux/smp.h> #include <asm/hw_breakpoint.h> diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 22d0687e7fda..884d875c1434 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -193,9 +193,13 @@ __visible unsigned int __irq_entry do_IRQ(struct pt_regs *regs) if (!handle_irq(irq, regs)) { ack_APIC_irq(); - if (printk_ratelimit()) - pr_emerg("%s: %d.%d No irq handler for vector (irq %d)\n", - __func__, smp_processor_id(), vector, irq); + if (irq != VECTOR_RETRIGGERED) { + pr_emerg_ratelimited("%s: %d.%d No irq handler for vector (irq %d)\n", + __func__, smp_processor_id(), + vector, irq); + } else { + __this_cpu_write(vector_irq[vector], VECTOR_UNDEFINED); + } } irq_exit(); @@ -344,7 +348,7 @@ void fixup_irqs(void) for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) { unsigned int irr; - if (__this_cpu_read(vector_irq[vector]) < 0) + if (__this_cpu_read(vector_irq[vector]) <= VECTOR_UNDEFINED) continue; irr = apic_read(APIC_IRR + (vector / 32 * 0x10)); @@ -355,11 +359,14 @@ void fixup_irqs(void) data = irq_desc_get_irq_data(desc); chip = irq_data_get_irq_chip(data); raw_spin_lock(&desc->lock); - if (chip->irq_retrigger) + if (chip->irq_retrigger) { chip->irq_retrigger(data); + __this_cpu_write(vector_irq[vector], VECTOR_RETRIGGERED); + } raw_spin_unlock(&desc->lock); } - __this_cpu_write(vector_irq[vector], -1); + if (__this_cpu_read(vector_irq[vector]) != VECTOR_RETRIGGERED) + __this_cpu_write(vector_irq[vector], VECTOR_UNDEFINED); } } #endif diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c index a2a1fbc594ff..7f50156542fb 100644 --- a/arch/x86/kernel/irqinit.c +++ b/arch/x86/kernel/irqinit.c @@ -52,7 +52,7 @@ static struct irqaction irq2 = { }; DEFINE_PER_CPU(vector_irq_t, vector_irq) = { - [0 ... NR_VECTORS - 1] = -1, + [0 ... NR_VECTORS - 1] = VECTOR_UNDEFINED, }; int vector_used_by_percpu_irq(unsigned int vector) @@ -60,7 +60,7 @@ int vector_used_by_percpu_irq(unsigned int vector) int cpu; for_each_online_cpu(cpu) { - if (per_cpu(vector_irq, cpu)[vector] != -1) + if (per_cpu(vector_irq, cpu)[vector] > VECTOR_UNDEFINED) return 1; } diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index 836f8322960e..7ec1d5f8d283 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -39,7 +39,6 @@ #include <linux/sched.h> #include <linux/delay.h> #include <linux/kgdb.h> -#include <linux/init.h> #include <linux/smp.h> #include <linux/nmi.h> #include <linux/hw_breakpoint.h> diff --git a/arch/x86/kernel/ksysfs.c b/arch/x86/kernel/ksysfs.c new file mode 100644 index 000000000000..c2bedaea11f7 --- /dev/null +++ b/arch/x86/kernel/ksysfs.c @@ -0,0 +1,340 @@ +/* + * Architecture specific sysfs attributes in /sys/kernel + * + * Copyright (C) 2007, Intel Corp. + * Huang Ying <ying.huang@intel.com> + * Copyright (C) 2013, 2013 Red Hat, Inc. + * Dave Young <dyoung@redhat.com> + * + * This file is released under the GPLv2 + */ + +#include <linux/kobject.h> +#include <linux/string.h> +#include <linux/sysfs.h> +#include <linux/init.h> +#include <linux/stat.h> +#include <linux/slab.h> +#include <linux/mm.h> + +#include <asm/io.h> +#include <asm/setup.h> + +static ssize_t version_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "0x%04x\n", boot_params.hdr.version); +} + +static struct kobj_attribute boot_params_version_attr = __ATTR_RO(version); + +static ssize_t boot_params_data_read(struct file *fp, struct kobject *kobj, + struct bin_attribute *bin_attr, + char *buf, loff_t off, size_t count) +{ + memcpy(buf, (void *)&boot_params + off, count); + return count; +} + +static struct bin_attribute boot_params_data_attr = { + .attr = { + .name = "data", + .mode = S_IRUGO, + }, + .read = boot_params_data_read, + .size = sizeof(boot_params), +}; + +static struct attribute *boot_params_version_attrs[] = { + &boot_params_version_attr.attr, + NULL, +}; + +static struct bin_attribute *boot_params_data_attrs[] = { + &boot_params_data_attr, + NULL, +}; + +static struct attribute_group boot_params_attr_group = { + .attrs = boot_params_version_attrs, + .bin_attrs = boot_params_data_attrs, +}; + +static int kobj_to_setup_data_nr(struct kobject *kobj, int *nr) +{ + const char *name; + + name = kobject_name(kobj); + return kstrtoint(name, 10, nr); +} + +static int get_setup_data_paddr(int nr, u64 *paddr) +{ + int i = 0; + struct setup_data *data; + u64 pa_data = boot_params.hdr.setup_data; + + while (pa_data) { + if (nr == i) { + *paddr = pa_data; + return 0; + } + data = ioremap_cache(pa_data, sizeof(*data)); + if (!data) + return -ENOMEM; + + pa_data = data->next; + iounmap(data); + i++; + } + return -EINVAL; +} + +static int __init get_setup_data_size(int nr, size_t *size) +{ + int i = 0; + struct setup_data *data; + u64 pa_data = boot_params.hdr.setup_data; + + while (pa_data) { + data = ioremap_cache(pa_data, sizeof(*data)); + if (!data) + return -ENOMEM; + if (nr == i) { + *size = data->len; + iounmap(data); + return 0; + } + + pa_data = data->next; + iounmap(data); + i++; + } + return -EINVAL; +} + +static ssize_t type_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + int nr, ret; + u64 paddr; + struct setup_data *data; + + ret = kobj_to_setup_data_nr(kobj, &nr); + if (ret) + return ret; + + ret = get_setup_data_paddr(nr, &paddr); + if (ret) + return ret; + data = ioremap_cache(paddr, sizeof(*data)); + if (!data) + return -ENOMEM; + + ret = sprintf(buf, "0x%x\n", data->type); + iounmap(data); + return ret; +} + +static ssize_t setup_data_data_read(struct file *fp, + struct kobject *kobj, + struct bin_attribute *bin_attr, + char *buf, + loff_t off, size_t count) +{ + int nr, ret = 0; + u64 paddr; + struct setup_data *data; + void *p; + + ret = kobj_to_setup_data_nr(kobj, &nr); + if (ret) + return ret; + + ret = get_setup_data_paddr(nr, &paddr); + if (ret) + return ret; + data = ioremap_cache(paddr, sizeof(*data)); + if (!data) + return -ENOMEM; + + if (off > data->len) { + ret = -EINVAL; + goto out; + } + + if (count > data->len - off) + count = data->len - off; + + if (!count) + goto out; + + ret = count; + p = ioremap_cache(paddr + sizeof(*data), data->len); + if (!p) { + ret = -ENOMEM; + goto out; + } + memcpy(buf, p + off, count); + iounmap(p); +out: + iounmap(data); + return ret; +} + +static struct kobj_attribute type_attr = __ATTR_RO(type); + +static struct bin_attribute data_attr = { + .attr = { + .name = "data", + .mode = S_IRUGO, + }, + .read = setup_data_data_read, +}; + +static struct attribute *setup_data_type_attrs[] = { + &type_attr.attr, + NULL, +}; + +static struct bin_attribute *setup_data_data_attrs[] = { + &data_attr, + NULL, +}; + +static struct attribute_group setup_data_attr_group = { + .attrs = setup_data_type_attrs, + .bin_attrs = setup_data_data_attrs, +}; + +static int __init create_setup_data_node(struct kobject *parent, + struct kobject **kobjp, int nr) +{ + int ret = 0; + size_t size; + struct kobject *kobj; + char name[16]; /* should be enough for setup_data nodes numbers */ + snprintf(name, 16, "%d", nr); + + kobj = kobject_create_and_add(name, parent); + if (!kobj) + return -ENOMEM; + + ret = get_setup_data_size(nr, &size); + if (ret) + goto out_kobj; + + data_attr.size = size; + ret = sysfs_create_group(kobj, &setup_data_attr_group); + if (ret) + goto out_kobj; + *kobjp = kobj; + + return 0; +out_kobj: + kobject_put(kobj); + return ret; +} + +static void __init cleanup_setup_data_node(struct kobject *kobj) +{ + sysfs_remove_group(kobj, &setup_data_attr_group); + kobject_put(kobj); +} + +static int __init get_setup_data_total_num(u64 pa_data, int *nr) +{ + int ret = 0; + struct setup_data *data; + + *nr = 0; + while (pa_data) { + *nr += 1; + data = ioremap_cache(pa_data, sizeof(*data)); + if (!data) { + ret = -ENOMEM; + goto out; + } + pa_data = data->next; + iounmap(data); + } + +out: + return ret; +} + +static int __init create_setup_data_nodes(struct kobject *parent) +{ + struct kobject *setup_data_kobj, **kobjp; + u64 pa_data; + int i, j, nr, ret = 0; + + pa_data = boot_params.hdr.setup_data; + if (!pa_data) + return 0; + + setup_data_kobj = kobject_create_and_add("setup_data", parent); + if (!setup_data_kobj) { + ret = -ENOMEM; + goto out; + } + + ret = get_setup_data_total_num(pa_data, &nr); + if (ret) + goto out_setup_data_kobj; + + kobjp = kmalloc(sizeof(*kobjp) * nr, GFP_KERNEL); + if (!kobjp) { + ret = -ENOMEM; + goto out_setup_data_kobj; + } + + for (i = 0; i < nr; i++) { + ret = create_setup_data_node(setup_data_kobj, kobjp + i, i); + if (ret) + goto out_clean_nodes; + } + + kfree(kobjp); + return 0; + +out_clean_nodes: + for (j = i - 1; j > 0; j--) + cleanup_setup_data_node(*(kobjp + j)); + kfree(kobjp); +out_setup_data_kobj: + kobject_put(setup_data_kobj); +out: + return ret; +} + +static int __init boot_params_ksysfs_init(void) +{ + int ret; + struct kobject *boot_params_kobj; + + boot_params_kobj = kobject_create_and_add("boot_params", + kernel_kobj); + if (!boot_params_kobj) { + ret = -ENOMEM; + goto out; + } + + ret = sysfs_create_group(boot_params_kobj, &boot_params_attr_group); + if (ret) + goto out_boot_params_kobj; + + ret = create_setup_data_nodes(boot_params_kobj); + if (ret) + goto out_create_group; + + return 0; +out_create_group: + sysfs_remove_group(boot_params_kobj, &boot_params_attr_group); +out_boot_params_kobj: + kobject_put(boot_params_kobj); +out: + return ret; +} + +arch_initcall(boot_params_ksysfs_init); diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c index 5b19e4d78b00..1667b1de8d5d 100644 --- a/arch/x86/kernel/machine_kexec_32.c +++ b/arch/x86/kernel/machine_kexec_32.c @@ -9,7 +9,6 @@ #include <linux/mm.h> #include <linux/kexec.h> #include <linux/delay.h> -#include <linux/init.h> #include <linux/numa.h> #include <linux/ftrace.h> #include <linux/suspend.h> diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c index 871be4a84c7d..da15918d1c81 100644 --- a/arch/x86/kernel/pci-nommu.c +++ b/arch/x86/kernel/pci-nommu.c @@ -3,7 +3,6 @@ #include <linux/dma-mapping.h> #include <linux/scatterlist.h> #include <linux/string.h> -#include <linux/init.h> #include <linux/gfp.h> #include <linux/pci.h> #include <linux/mm.h> diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 6f1236c29c4b..0de43e98ce08 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -24,7 +24,6 @@ #include <linux/interrupt.h> #include <linux/delay.h> #include <linux/reboot.h> -#include <linux/init.h> #include <linux/mc146818rtc.h> #include <linux/module.h> #include <linux/kallsyms.h> diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index cb233bc9dee3..be4b456e444b 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -447,6 +447,9 @@ static void __init parse_setup_data(void) case SETUP_DTB: add_dtb(pa_data); break; + case SETUP_EFI: + parse_efi_setup(pa_data, data_len); + break; default: break; } @@ -924,8 +927,6 @@ void __init setup_arch(char **cmdline_p) iomem_resource.end = (1ULL << boot_cpu_data.x86_phys_bits) - 1; setup_memory_map(); parse_setup_data(); - /* update the e820_saved too */ - e820_reserve_setup_data(); copy_edd(); @@ -987,6 +988,8 @@ void __init setup_arch(char **cmdline_p) early_dump_pci_devices(); #endif + /* update the e820_saved too */ + e820_reserve_setup_data(); finish_e820_parsing(); if (efi_enabled(EFI_BOOT)) diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 85dc05a3aa02..f5252c4eec8c 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1417,7 +1417,9 @@ static inline void mwait_play_dead(void) * The WBINVD is insufficient due to the spurious-wakeup * case where we return around the loop. */ + mb(); clflush(mwait_ptr); + mb(); __monitor(mwait_ptr, 0, 0); mb(); __mwait(eax, 0); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index b857ed890b4c..57409f6b8c62 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -211,21 +211,17 @@ dotraplinkage void do_##name(struct pt_regs *regs, long error_code) \ exception_exit(prev_state); \ } -DO_ERROR_INFO(X86_TRAP_DE, SIGFPE, "divide error", divide_error, FPE_INTDIV, - regs->ip) -DO_ERROR(X86_TRAP_OF, SIGSEGV, "overflow", overflow) -DO_ERROR(X86_TRAP_BR, SIGSEGV, "bounds", bounds) -DO_ERROR_INFO(X86_TRAP_UD, SIGILL, "invalid opcode", invalid_op, ILL_ILLOPN, - regs->ip) -DO_ERROR(X86_TRAP_OLD_MF, SIGFPE, "coprocessor segment overrun", - coprocessor_segment_overrun) -DO_ERROR(X86_TRAP_TS, SIGSEGV, "invalid TSS", invalid_TSS) -DO_ERROR(X86_TRAP_NP, SIGBUS, "segment not present", segment_not_present) +DO_ERROR_INFO(X86_TRAP_DE, SIGFPE, "divide error", divide_error, FPE_INTDIV, regs->ip ) +DO_ERROR (X86_TRAP_OF, SIGSEGV, "overflow", overflow ) +DO_ERROR (X86_TRAP_BR, SIGSEGV, "bounds", bounds ) +DO_ERROR_INFO(X86_TRAP_UD, SIGILL, "invalid opcode", invalid_op, ILL_ILLOPN, regs->ip ) +DO_ERROR (X86_TRAP_OLD_MF, SIGFPE, "coprocessor segment overrun", coprocessor_segment_overrun ) +DO_ERROR (X86_TRAP_TS, SIGSEGV, "invalid TSS", invalid_TSS ) +DO_ERROR (X86_TRAP_NP, SIGBUS, "segment not present", segment_not_present ) #ifdef CONFIG_X86_32 -DO_ERROR(X86_TRAP_SS, SIGBUS, "stack segment", stack_segment) +DO_ERROR (X86_TRAP_SS, SIGBUS, "stack segment", stack_segment ) #endif -DO_ERROR_INFO(X86_TRAP_AC, SIGBUS, "alignment check", alignment_check, - BUS_ADRALN, 0) +DO_ERROR_INFO(X86_TRAP_AC, SIGBUS, "alignment check", alignment_check, BUS_ADRALN, 0 ) #ifdef CONFIG_X86_64 /* Runs on IST stack */ diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 930e5d48f560..6377fb28b958 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -11,6 +11,7 @@ #include <linux/clocksource.h> #include <linux/percpu.h> #include <linux/timex.h> +#include <linux/static_key.h> #include <asm/hpet.h> #include <asm/timer.h> @@ -37,13 +38,244 @@ static int __read_mostly tsc_unstable; erroneous rdtsc usage on !cpu_has_tsc processors */ static int __read_mostly tsc_disabled = -1; +static struct static_key __use_tsc = STATIC_KEY_INIT; + int tsc_clocksource_reliable; + +/* + * Use a ring-buffer like data structure, where a writer advances the head by + * writing a new data entry and a reader advances the tail when it observes a + * new entry. + * + * Writers are made to wait on readers until there's space to write a new + * entry. + * + * This means that we can always use an {offset, mul} pair to compute a ns + * value that is 'roughly' in the right direction, even if we're writing a new + * {offset, mul} pair during the clock read. + * + * The down-side is that we can no longer guarantee strict monotonicity anymore + * (assuming the TSC was that to begin with), because while we compute the + * intersection point of the two clock slopes and make sure the time is + * continuous at the point of switching; we can no longer guarantee a reader is + * strictly before or after the switch point. + * + * It does mean a reader no longer needs to disable IRQs in order to avoid + * CPU-Freq updates messing with his times, and similarly an NMI reader will + * no longer run the risk of hitting half-written state. + */ + +struct cyc2ns { + struct cyc2ns_data data[2]; /* 0 + 2*24 = 48 */ + struct cyc2ns_data *head; /* 48 + 8 = 56 */ + struct cyc2ns_data *tail; /* 56 + 8 = 64 */ +}; /* exactly fits one cacheline */ + +static DEFINE_PER_CPU_ALIGNED(struct cyc2ns, cyc2ns); + +struct cyc2ns_data *cyc2ns_read_begin(void) +{ + struct cyc2ns_data *head; + + preempt_disable(); + + head = this_cpu_read(cyc2ns.head); + /* + * Ensure we observe the entry when we observe the pointer to it. + * matches the wmb from cyc2ns_write_end(). + */ + smp_read_barrier_depends(); + head->__count++; + barrier(); + + return head; +} + +void cyc2ns_read_end(struct cyc2ns_data *head) +{ + barrier(); + /* + * If we're the outer most nested read; update the tail pointer + * when we're done. This notifies possible pending writers + * that we've observed the head pointer and that the other + * entry is now free. + */ + if (!--head->__count) { + /* + * x86-TSO does not reorder writes with older reads; + * therefore once this write becomes visible to another + * cpu, we must be finished reading the cyc2ns_data. + * + * matches with cyc2ns_write_begin(). + */ + this_cpu_write(cyc2ns.tail, head); + } + preempt_enable(); +} + +/* + * Begin writing a new @data entry for @cpu. + * + * Assumes some sort of write side lock; currently 'provided' by the assumption + * that cpufreq will call its notifiers sequentially. + */ +static struct cyc2ns_data *cyc2ns_write_begin(int cpu) +{ + struct cyc2ns *c2n = &per_cpu(cyc2ns, cpu); + struct cyc2ns_data *data = c2n->data; + + if (data == c2n->head) + data++; + + /* XXX send an IPI to @cpu in order to guarantee a read? */ + + /* + * When we observe the tail write from cyc2ns_read_end(), + * the cpu must be done with that entry and its safe + * to start writing to it. + */ + while (c2n->tail == data) + cpu_relax(); + + return data; +} + +static void cyc2ns_write_end(int cpu, struct cyc2ns_data *data) +{ + struct cyc2ns *c2n = &per_cpu(cyc2ns, cpu); + + /* + * Ensure the @data writes are visible before we publish the + * entry. Matches the data-depencency in cyc2ns_read_begin(). + */ + smp_wmb(); + + ACCESS_ONCE(c2n->head) = data; +} + +/* + * Accelerators for sched_clock() + * convert from cycles(64bits) => nanoseconds (64bits) + * basic equation: + * ns = cycles / (freq / ns_per_sec) + * ns = cycles * (ns_per_sec / freq) + * ns = cycles * (10^9 / (cpu_khz * 10^3)) + * ns = cycles * (10^6 / cpu_khz) + * + * Then we use scaling math (suggested by george@mvista.com) to get: + * ns = cycles * (10^6 * SC / cpu_khz) / SC + * ns = cycles * cyc2ns_scale / SC + * + * And since SC is a constant power of two, we can convert the div + * into a shift. + * + * We can use khz divisor instead of mhz to keep a better precision, since + * cyc2ns_scale is limited to 10^6 * 2^10, which fits in 32 bits. + * (mathieu.desnoyers@polymtl.ca) + * + * -johnstul@us.ibm.com "math is hard, lets go shopping!" + */ + +#define CYC2NS_SCALE_FACTOR 10 /* 2^10, carefully chosen */ + +static void cyc2ns_data_init(struct cyc2ns_data *data) +{ + data->cyc2ns_mul = 1U << CYC2NS_SCALE_FACTOR; + data->cyc2ns_shift = CYC2NS_SCALE_FACTOR; + data->cyc2ns_offset = 0; + data->__count = 0; +} + +static void cyc2ns_init(int cpu) +{ + struct cyc2ns *c2n = &per_cpu(cyc2ns, cpu); + + cyc2ns_data_init(&c2n->data[0]); + cyc2ns_data_init(&c2n->data[1]); + + c2n->head = c2n->data; + c2n->tail = c2n->data; +} + +static inline unsigned long long cycles_2_ns(unsigned long long cyc) +{ + struct cyc2ns_data *data, *tail; + unsigned long long ns; + + /* + * See cyc2ns_read_*() for details; replicated in order to avoid + * an extra few instructions that came with the abstraction. + * Notable, it allows us to only do the __count and tail update + * dance when its actually needed. + */ + + preempt_disable(); + data = this_cpu_read(cyc2ns.head); + tail = this_cpu_read(cyc2ns.tail); + + if (likely(data == tail)) { + ns = data->cyc2ns_offset; + ns += mul_u64_u32_shr(cyc, data->cyc2ns_mul, CYC2NS_SCALE_FACTOR); + } else { + data->__count++; + + barrier(); + + ns = data->cyc2ns_offset; + ns += mul_u64_u32_shr(cyc, data->cyc2ns_mul, CYC2NS_SCALE_FACTOR); + + barrier(); + + if (!--data->__count) + this_cpu_write(cyc2ns.tail, data); + } + preempt_enable(); + + return ns; +} + +/* XXX surely we already have this someplace in the kernel?! */ +#define DIV_ROUND(n, d) (((n) + ((d) / 2)) / (d)) + +static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu) +{ + unsigned long long tsc_now, ns_now; + struct cyc2ns_data *data; + unsigned long flags; + + local_irq_save(flags); + sched_clock_idle_sleep_event(); + + if (!cpu_khz) + goto done; + + data = cyc2ns_write_begin(cpu); + + rdtscll(tsc_now); + ns_now = cycles_2_ns(tsc_now); + + /* + * Compute a new multiplier as per the above comment and ensure our + * time function is continuous; see the comment near struct + * cyc2ns_data. + */ + data->cyc2ns_mul = DIV_ROUND(NSEC_PER_MSEC << CYC2NS_SCALE_FACTOR, cpu_khz); + data->cyc2ns_shift = CYC2NS_SCALE_FACTOR; + data->cyc2ns_offset = ns_now - + mul_u64_u32_shr(tsc_now, data->cyc2ns_mul, CYC2NS_SCALE_FACTOR); + + cyc2ns_write_end(cpu, data); + +done: + sched_clock_idle_wakeup_event(0); + local_irq_restore(flags); +} /* * Scheduler clock - returns current time in nanosec units. */ u64 native_sched_clock(void) { - u64 this_offset; + u64 tsc_now; /* * Fall back to jiffies if there's no TSC available: @@ -53,16 +285,16 @@ u64 native_sched_clock(void) * very important for it to be as fast as the platform * can achieve it. ) */ - if (unlikely(tsc_disabled)) { + if (!static_key_false(&__use_tsc)) { /* No locking but a rare wrong value is not a big deal: */ return (jiffies_64 - INITIAL_JIFFIES) * (1000000000 / HZ); } /* read the Time Stamp Counter: */ - rdtscll(this_offset); + rdtscll(tsc_now); /* return the value in ns */ - return __cycles_2_ns(this_offset); + return cycles_2_ns(tsc_now); } /* We need to define a real function for sched_clock, to override the @@ -589,61 +821,11 @@ int recalibrate_cpu_khz(void) EXPORT_SYMBOL(recalibrate_cpu_khz); -/* Accelerators for sched_clock() - * convert from cycles(64bits) => nanoseconds (64bits) - * basic equation: - * ns = cycles / (freq / ns_per_sec) - * ns = cycles * (ns_per_sec / freq) - * ns = cycles * (10^9 / (cpu_khz * 10^3)) - * ns = cycles * (10^6 / cpu_khz) - * - * Then we use scaling math (suggested by george@mvista.com) to get: - * ns = cycles * (10^6 * SC / cpu_khz) / SC - * ns = cycles * cyc2ns_scale / SC - * - * And since SC is a constant power of two, we can convert the div - * into a shift. - * - * We can use khz divisor instead of mhz to keep a better precision, since - * cyc2ns_scale is limited to 10^6 * 2^10, which fits in 32 bits. - * (mathieu.desnoyers@polymtl.ca) - * - * -johnstul@us.ibm.com "math is hard, lets go shopping!" - */ - -DEFINE_PER_CPU(unsigned long, cyc2ns); -DEFINE_PER_CPU(unsigned long long, cyc2ns_offset); - -static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu) -{ - unsigned long long tsc_now, ns_now, *offset; - unsigned long flags, *scale; - - local_irq_save(flags); - sched_clock_idle_sleep_event(); - - scale = &per_cpu(cyc2ns, cpu); - offset = &per_cpu(cyc2ns_offset, cpu); - - rdtscll(tsc_now); - ns_now = __cycles_2_ns(tsc_now); - - if (cpu_khz) { - *scale = ((NSEC_PER_MSEC << CYC2NS_SCALE_FACTOR) + - cpu_khz / 2) / cpu_khz; - *offset = ns_now - mult_frac(tsc_now, *scale, - (1UL << CYC2NS_SCALE_FACTOR)); - } - - sched_clock_idle_wakeup_event(0); - local_irq_restore(flags); -} - static unsigned long long cyc2ns_suspend; void tsc_save_sched_clock_state(void) { - if (!sched_clock_stable) + if (!sched_clock_stable()) return; cyc2ns_suspend = sched_clock(); @@ -663,16 +845,26 @@ void tsc_restore_sched_clock_state(void) unsigned long flags; int cpu; - if (!sched_clock_stable) + if (!sched_clock_stable()) return; local_irq_save(flags); - __this_cpu_write(cyc2ns_offset, 0); + /* + * We're comming out of suspend, there's no concurrency yet; don't + * bother being nice about the RCU stuff, just write to both + * data fields. + */ + + this_cpu_write(cyc2ns.data[0].cyc2ns_offset, 0); + this_cpu_write(cyc2ns.data[1].cyc2ns_offset, 0); + offset = cyc2ns_suspend - sched_clock(); - for_each_possible_cpu(cpu) - per_cpu(cyc2ns_offset, cpu) = offset; + for_each_possible_cpu(cpu) { + per_cpu(cyc2ns.data[0].cyc2ns_offset, cpu) = offset; + per_cpu(cyc2ns.data[1].cyc2ns_offset, cpu) = offset; + } local_irq_restore(flags); } @@ -795,7 +987,7 @@ void mark_tsc_unstable(char *reason) { if (!tsc_unstable) { tsc_unstable = 1; - sched_clock_stable = 0; + clear_sched_clock_stable(); disable_sched_clock_irqtime(); pr_info("Marking TSC unstable due to %s\n", reason); /* Change only the rating, when not registered */ @@ -995,14 +1187,18 @@ void __init tsc_init(void) * speed as the bootup CPU. (cpufreq notifiers will fix this * up if their speed diverges) */ - for_each_possible_cpu(cpu) + for_each_possible_cpu(cpu) { + cyc2ns_init(cpu); set_cyc2ns_scale(cpu_khz, cpu); + } if (tsc_disabled > 0) return; /* now allow native_sched_clock() to use rdtsc */ + tsc_disabled = 0; + static_key_slow_inc(&__use_tsc); if (!no_sched_irq_time) enable_sched_clock_irqtime(); diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c index adfdf56a3714..26488487bc61 100644 --- a/arch/x86/kernel/tsc_sync.c +++ b/arch/x86/kernel/tsc_sync.c @@ -16,7 +16,6 @@ */ #include <linux/spinlock.h> #include <linux/kernel.h> -#include <linux/init.h> #include <linux/smp.h> #include <linux/nmi.h> #include <asm/tsc.h> diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 1673940cf9c3..775702f649ca 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1355,7 +1355,7 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value) vcpu->arch.apic_base = value; /* update jump label if enable bit changes */ - if ((vcpu->arch.apic_base ^ value) & MSR_IA32_APICBASE_ENABLE) { + if ((old_value ^ value) & MSR_IA32_APICBASE_ENABLE) { if (value & MSR_IA32_APICBASE_ENABLE) static_key_slow_dec_deferred(&apic_hw_disabled); else diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S index a30ca15be21c..dee945d55594 100644 --- a/arch/x86/lib/copy_user_64.S +++ b/arch/x86/lib/copy_user_64.S @@ -186,7 +186,7 @@ ENTRY(copy_user_generic_unrolled) 30: shll $6,%ecx addl %ecx,%edx jmp 60f -40: lea (%rdx,%rcx,8),%rdx +40: leal (%rdx,%rcx,8),%edx jmp 60f 50: movl %ecx,%edx 60: jmp copy_user_handle_tail /* ecx is zerorest also */ @@ -236,8 +236,6 @@ ENDPROC(copy_user_generic_unrolled) ENTRY(copy_user_generic_string) CFI_STARTPROC ASM_STAC - andl %edx,%edx - jz 4f cmpl $8,%edx jb 2f /* less than 8 bytes, go to byte copy loop */ ALIGN_DESTINATION @@ -249,12 +247,12 @@ ENTRY(copy_user_generic_string) 2: movl %edx,%ecx 3: rep movsb -4: xorl %eax,%eax + xorl %eax,%eax ASM_CLAC ret .section .fixup,"ax" -11: lea (%rdx,%rcx,8),%rcx +11: leal (%rdx,%rcx,8),%ecx 12: movl %ecx,%edx /* ecx is zerorest also */ jmp copy_user_handle_tail .previous @@ -279,12 +277,10 @@ ENDPROC(copy_user_generic_string) ENTRY(copy_user_enhanced_fast_string) CFI_STARTPROC ASM_STAC - andl %edx,%edx - jz 2f movl %edx,%ecx 1: rep movsb -2: xorl %eax,%eax + xorl %eax,%eax ASM_CLAC ret diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c index 7c3bee636e2f..39d6a3db0b96 100644 --- a/arch/x86/lib/delay.c +++ b/arch/x86/lib/delay.c @@ -16,7 +16,6 @@ #include <linux/timex.h> #include <linux/preempt.h> #include <linux/delay.h> -#include <linux/init.h> #include <asm/processor.h> #include <asm/delay.h> diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 9ff85bb8dd69..9d591c895803 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -641,6 +641,20 @@ no_context(struct pt_regs *regs, unsigned long error_code, /* Are we prepared to handle this kernel fault? */ if (fixup_exception(regs)) { + /* + * Any interrupt that takes a fault gets the fixup. This makes + * the below recursive fault logic only apply to a faults from + * task context. + */ + if (in_interrupt()) + return; + + /* + * Per the above we're !in_interrupt(), aka. task context. + * + * In this case we need to make sure we're not recursively + * faulting through the emulate_vsyscall() logic. + */ if (current_thread_info()->sig_on_uaccess_error && signal) { tsk->thread.trap_nr = X86_TRAP_PF; tsk->thread.error_code = error_code | PF_USER; @@ -649,6 +663,10 @@ no_context(struct pt_regs *regs, unsigned long error_code, /* XXX: hwpoison faults will set the wrong code. */ force_sig_info_fault(signal, si_code, address, tsk, 0); } + + /* + * Barring that, we can do the fixup and be happy. + */ return; } diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c index e5d5e2ce9f77..637ab34ed632 100644 --- a/arch/x86/mm/kmmio.c +++ b/arch/x86/mm/kmmio.c @@ -11,7 +11,6 @@ #include <linux/rculist.h> #include <linux/spinlock.h> #include <linux/hash.h> -#include <linux/init.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/uaccess.h> diff --git a/arch/x86/mm/pageattr-test.c b/arch/x86/mm/pageattr-test.c index d0b1773d9d2e..461bc8289024 100644 --- a/arch/x86/mm/pageattr-test.c +++ b/arch/x86/mm/pageattr-test.c @@ -8,7 +8,6 @@ #include <linux/kthread.h> #include <linux/random.h> #include <linux/kernel.h> -#include <linux/init.h> #include <linux/mm.h> #include <asm/cacheflush.h> diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index bb32480c2d71..b3b19f46c016 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -30,6 +30,7 @@ */ struct cpa_data { unsigned long *vaddr; + pgd_t *pgd; pgprot_t mask_set; pgprot_t mask_clr; int numpages; @@ -322,17 +323,9 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address, return prot; } -/* - * Lookup the page table entry for a virtual address. Return a pointer - * to the entry and the level of the mapping. - * - * Note: We return pud and pmd either when the entry is marked large - * or when the present bit is not set. Otherwise we would return a - * pointer to a nonexisting mapping. - */ -pte_t *lookup_address(unsigned long address, unsigned int *level) +static pte_t *__lookup_address_in_pgd(pgd_t *pgd, unsigned long address, + unsigned int *level) { - pgd_t *pgd = pgd_offset_k(address); pud_t *pud; pmd_t *pmd; @@ -361,8 +354,31 @@ pte_t *lookup_address(unsigned long address, unsigned int *level) return pte_offset_kernel(pmd, address); } + +/* + * Lookup the page table entry for a virtual address. Return a pointer + * to the entry and the level of the mapping. + * + * Note: We return pud and pmd either when the entry is marked large + * or when the present bit is not set. Otherwise we would return a + * pointer to a nonexisting mapping. + */ +pte_t *lookup_address(unsigned long address, unsigned int *level) +{ + return __lookup_address_in_pgd(pgd_offset_k(address), address, level); +} EXPORT_SYMBOL_GPL(lookup_address); +static pte_t *_lookup_address_cpa(struct cpa_data *cpa, unsigned long address, + unsigned int *level) +{ + if (cpa->pgd) + return __lookup_address_in_pgd(cpa->pgd + pgd_index(address), + address, level); + + return lookup_address(address, level); +} + /* * This is necessary because __pa() does not work on some * kinds of memory, like vmalloc() or the alloc_remap() @@ -437,7 +453,7 @@ try_preserve_large_page(pte_t *kpte, unsigned long address, * Check for races, another CPU might have split this page * up already: */ - tmp = lookup_address(address, &level); + tmp = _lookup_address_cpa(cpa, address, &level); if (tmp != kpte) goto out_unlock; @@ -543,7 +559,8 @@ out_unlock: } static int -__split_large_page(pte_t *kpte, unsigned long address, struct page *base) +__split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address, + struct page *base) { pte_t *pbase = (pte_t *)page_address(base); unsigned long pfn, pfninc = 1; @@ -556,7 +573,7 @@ __split_large_page(pte_t *kpte, unsigned long address, struct page *base) * Check for races, another CPU might have split this page * up for us already: */ - tmp = lookup_address(address, &level); + tmp = _lookup_address_cpa(cpa, address, &level); if (tmp != kpte) { spin_unlock(&pgd_lock); return 1; @@ -632,7 +649,8 @@ __split_large_page(pte_t *kpte, unsigned long address, struct page *base) return 0; } -static int split_large_page(pte_t *kpte, unsigned long address) +static int split_large_page(struct cpa_data *cpa, pte_t *kpte, + unsigned long address) { struct page *base; @@ -644,15 +662,390 @@ static int split_large_page(pte_t *kpte, unsigned long address) if (!base) return -ENOMEM; - if (__split_large_page(kpte, address, base)) + if (__split_large_page(cpa, kpte, address, base)) __free_page(base); return 0; } +static bool try_to_free_pte_page(pte_t *pte) +{ + int i; + + for (i = 0; i < PTRS_PER_PTE; i++) + if (!pte_none(pte[i])) + return false; + + free_page((unsigned long)pte); + return true; +} + +static bool try_to_free_pmd_page(pmd_t *pmd) +{ + int i; + + for (i = 0; i < PTRS_PER_PMD; i++) + if (!pmd_none(pmd[i])) + return false; + + free_page((unsigned long)pmd); + return true; +} + +static bool unmap_pte_range(pmd_t *pmd, unsigned long start, unsigned long end) +{ + pte_t *pte = pte_offset_kernel(pmd, start); + + while (start < end) { + set_pte(pte, __pte(0)); + + start += PAGE_SIZE; + pte++; + } + + if (try_to_free_pte_page((pte_t *)pmd_page_vaddr(*pmd))) { + pmd_clear(pmd); + return true; + } + return false; +} + +static void __unmap_pmd_range(pud_t *pud, pmd_t *pmd, + unsigned long start, unsigned long end) +{ + if (unmap_pte_range(pmd, start, end)) + if (try_to_free_pmd_page((pmd_t *)pud_page_vaddr(*pud))) + pud_clear(pud); +} + +static void unmap_pmd_range(pud_t *pud, unsigned long start, unsigned long end) +{ + pmd_t *pmd = pmd_offset(pud, start); + + /* + * Not on a 2MB page boundary? + */ + if (start & (PMD_SIZE - 1)) { + unsigned long next_page = (start + PMD_SIZE) & PMD_MASK; + unsigned long pre_end = min_t(unsigned long, end, next_page); + + __unmap_pmd_range(pud, pmd, start, pre_end); + + start = pre_end; + pmd++; + } + + /* + * Try to unmap in 2M chunks. + */ + while (end - start >= PMD_SIZE) { + if (pmd_large(*pmd)) + pmd_clear(pmd); + else + __unmap_pmd_range(pud, pmd, start, start + PMD_SIZE); + + start += PMD_SIZE; + pmd++; + } + + /* + * 4K leftovers? + */ + if (start < end) + return __unmap_pmd_range(pud, pmd, start, end); + + /* + * Try again to free the PMD page if haven't succeeded above. + */ + if (!pud_none(*pud)) + if (try_to_free_pmd_page((pmd_t *)pud_page_vaddr(*pud))) + pud_clear(pud); +} + +static void unmap_pud_range(pgd_t *pgd, unsigned long start, unsigned long end) +{ + pud_t *pud = pud_offset(pgd, start); + + /* + * Not on a GB page boundary? + */ + if (start & (PUD_SIZE - 1)) { + unsigned long next_page = (start + PUD_SIZE) & PUD_MASK; + unsigned long pre_end = min_t(unsigned long, end, next_page); + + unmap_pmd_range(pud, start, pre_end); + + start = pre_end; + pud++; + } + + /* + * Try to unmap in 1G chunks? + */ + while (end - start >= PUD_SIZE) { + + if (pud_large(*pud)) + pud_clear(pud); + else + unmap_pmd_range(pud, start, start + PUD_SIZE); + + start += PUD_SIZE; + pud++; + } + + /* + * 2M leftovers? + */ + if (start < end) + unmap_pmd_range(pud, start, end); + + /* + * No need to try to free the PUD page because we'll free it in + * populate_pgd's error path + */ +} + +static int alloc_pte_page(pmd_t *pmd) +{ + pte_t *pte = (pte_t *)get_zeroed_page(GFP_KERNEL | __GFP_NOTRACK); + if (!pte) + return -1; + + set_pmd(pmd, __pmd(__pa(pte) | _KERNPG_TABLE)); + return 0; +} + +static int alloc_pmd_page(pud_t *pud) +{ + pmd_t *pmd = (pmd_t *)get_zeroed_page(GFP_KERNEL | __GFP_NOTRACK); + if (!pmd) + return -1; + + set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE)); + return 0; +} + +static void populate_pte(struct cpa_data *cpa, + unsigned long start, unsigned long end, + unsigned num_pages, pmd_t *pmd, pgprot_t pgprot) +{ + pte_t *pte; + + pte = pte_offset_kernel(pmd, start); + + while (num_pages-- && start < end) { + + /* deal with the NX bit */ + if (!(pgprot_val(pgprot) & _PAGE_NX)) + cpa->pfn &= ~_PAGE_NX; + + set_pte(pte, pfn_pte(cpa->pfn >> PAGE_SHIFT, pgprot)); + + start += PAGE_SIZE; + cpa->pfn += PAGE_SIZE; + pte++; + } +} + +static int populate_pmd(struct cpa_data *cpa, + unsigned long start, unsigned long end, + unsigned num_pages, pud_t *pud, pgprot_t pgprot) +{ + unsigned int cur_pages = 0; + pmd_t *pmd; + + /* + * Not on a 2M boundary? + */ + if (start & (PMD_SIZE - 1)) { + unsigned long pre_end = start + (num_pages << PAGE_SHIFT); + unsigned long next_page = (start + PMD_SIZE) & PMD_MASK; + + pre_end = min_t(unsigned long, pre_end, next_page); + cur_pages = (pre_end - start) >> PAGE_SHIFT; + cur_pages = min_t(unsigned int, num_pages, cur_pages); + + /* + * Need a PTE page? + */ + pmd = pmd_offset(pud, start); + if (pmd_none(*pmd)) + if (alloc_pte_page(pmd)) + return -1; + + populate_pte(cpa, start, pre_end, cur_pages, pmd, pgprot); + + start = pre_end; + } + + /* + * We mapped them all? + */ + if (num_pages == cur_pages) + return cur_pages; + + while (end - start >= PMD_SIZE) { + + /* + * We cannot use a 1G page so allocate a PMD page if needed. + */ + if (pud_none(*pud)) + if (alloc_pmd_page(pud)) + return -1; + + pmd = pmd_offset(pud, start); + + set_pmd(pmd, __pmd(cpa->pfn | _PAGE_PSE | massage_pgprot(pgprot))); + + start += PMD_SIZE; + cpa->pfn += PMD_SIZE; + cur_pages += PMD_SIZE >> PAGE_SHIFT; + } + + /* + * Map trailing 4K pages. + */ + if (start < end) { + pmd = pmd_offset(pud, start); + if (pmd_none(*pmd)) + if (alloc_pte_page(pmd)) + return -1; + + populate_pte(cpa, start, end, num_pages - cur_pages, + pmd, pgprot); + } + return num_pages; +} + +static int populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd, + pgprot_t pgprot) +{ + pud_t *pud; + unsigned long end; + int cur_pages = 0; + + end = start + (cpa->numpages << PAGE_SHIFT); + + /* + * Not on a Gb page boundary? => map everything up to it with + * smaller pages. + */ + if (start & (PUD_SIZE - 1)) { + unsigned long pre_end; + unsigned long next_page = (start + PUD_SIZE) & PUD_MASK; + + pre_end = min_t(unsigned long, end, next_page); + cur_pages = (pre_end - start) >> PAGE_SHIFT; + cur_pages = min_t(int, (int)cpa->numpages, cur_pages); + + pud = pud_offset(pgd, start); + + /* + * Need a PMD page? + */ + if (pud_none(*pud)) + if (alloc_pmd_page(pud)) + return -1; + + cur_pages = populate_pmd(cpa, start, pre_end, cur_pages, + pud, pgprot); + if (cur_pages < 0) + return cur_pages; + + start = pre_end; + } + + /* We mapped them all? */ + if (cpa->numpages == cur_pages) + return cur_pages; + + pud = pud_offset(pgd, start); + + /* + * Map everything starting from the Gb boundary, possibly with 1G pages + */ + while (end - start >= PUD_SIZE) { + set_pud(pud, __pud(cpa->pfn | _PAGE_PSE | massage_pgprot(pgprot))); + + start += PUD_SIZE; + cpa->pfn += PUD_SIZE; + cur_pages += PUD_SIZE >> PAGE_SHIFT; + pud++; + } + + /* Map trailing leftover */ + if (start < end) { + int tmp; + + pud = pud_offset(pgd, start); + if (pud_none(*pud)) + if (alloc_pmd_page(pud)) + return -1; + + tmp = populate_pmd(cpa, start, end, cpa->numpages - cur_pages, + pud, pgprot); + if (tmp < 0) + return cur_pages; + + cur_pages += tmp; + } + return cur_pages; +} + +/* + * Restrictions for kernel page table do not necessarily apply when mapping in + * an alternate PGD. + */ +static int populate_pgd(struct cpa_data *cpa, unsigned long addr) +{ + pgprot_t pgprot = __pgprot(_KERNPG_TABLE); + bool allocd_pgd = false; + pgd_t *pgd_entry; + pud_t *pud = NULL; /* shut up gcc */ + int ret; + + pgd_entry = cpa->pgd + pgd_index(addr); + + /* + * Allocate a PUD page and hand it down for mapping. + */ + if (pgd_none(*pgd_entry)) { + pud = (pud_t *)get_zeroed_page(GFP_KERNEL | __GFP_NOTRACK); + if (!pud) + return -1; + + set_pgd(pgd_entry, __pgd(__pa(pud) | _KERNPG_TABLE)); + allocd_pgd = true; + } + + pgprot_val(pgprot) &= ~pgprot_val(cpa->mask_clr); + pgprot_val(pgprot) |= pgprot_val(cpa->mask_set); + + ret = populate_pud(cpa, addr, pgd_entry, pgprot); + if (ret < 0) { + unmap_pud_range(pgd_entry, addr, + addr + (cpa->numpages << PAGE_SHIFT)); + + if (allocd_pgd) { + /* + * If I allocated this PUD page, I can just as well + * free it in this error path. + */ + pgd_clear(pgd_entry); + free_page((unsigned long)pud); + } + return ret; + } + cpa->numpages = ret; + return 0; +} + static int __cpa_process_fault(struct cpa_data *cpa, unsigned long vaddr, int primary) { + if (cpa->pgd) + return populate_pgd(cpa, vaddr); + /* * Ignore all non primary paths. */ @@ -697,7 +1090,7 @@ static int __change_page_attr(struct cpa_data *cpa, int primary) else address = *cpa->vaddr; repeat: - kpte = lookup_address(address, &level); + kpte = _lookup_address_cpa(cpa, address, &level); if (!kpte) return __cpa_process_fault(cpa, address, primary); @@ -761,7 +1154,7 @@ repeat: /* * We have to split the large page: */ - err = split_large_page(kpte, address); + err = split_large_page(cpa, kpte, address); if (!err) { /* * Do a global flush tlb after splitting the large page @@ -910,6 +1303,8 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages, int ret, cache, checkalias; unsigned long baddr = 0; + memset(&cpa, 0, sizeof(cpa)); + /* * Check, if we are requested to change a not supported * feature: @@ -1356,6 +1751,7 @@ static int __set_pages_p(struct page *page, int numpages) { unsigned long tempaddr = (unsigned long) page_address(page); struct cpa_data cpa = { .vaddr = &tempaddr, + .pgd = NULL, .numpages = numpages, .mask_set = __pgprot(_PAGE_PRESENT | _PAGE_RW), .mask_clr = __pgprot(0), @@ -1374,6 +1770,7 @@ static int __set_pages_np(struct page *page, int numpages) { unsigned long tempaddr = (unsigned long) page_address(page); struct cpa_data cpa = { .vaddr = &tempaddr, + .pgd = NULL, .numpages = numpages, .mask_set = __pgprot(0), .mask_clr = __pgprot(_PAGE_PRESENT | _PAGE_RW), @@ -1434,6 +1831,36 @@ bool kernel_page_present(struct page *page) #endif /* CONFIG_DEBUG_PAGEALLOC */ +int kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address, + unsigned numpages, unsigned long page_flags) +{ + int retval = -EINVAL; + + struct cpa_data cpa = { + .vaddr = &address, + .pfn = pfn, + .pgd = pgd, + .numpages = numpages, + .mask_set = __pgprot(0), + .mask_clr = __pgprot(0), + .flags = 0, + }; + + if (!(__supported_pte_mask & _PAGE_NX)) + goto out; + + if (!(page_flags & _PAGE_NX)) + cpa.mask_clr = __pgprot(_PAGE_NX); + + cpa.mask_set = __pgprot(_PAGE_PRESENT | page_flags); + + retval = __change_page_attr_set_clr(&cpa, 0); + __flush_tlb_all(); + +out: + return retval; +} + /* * The testcases use internal knowledge of the implementation that shouldn't * be exposed to the rest of the kernel. Include these directly here. diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 26328e800869..4ed75dd81d05 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -359,15 +359,21 @@ void bpf_jit_compile(struct sk_filter *fp) EMIT2(0x89, 0xd0); /* mov %edx,%eax */ break; case BPF_S_ALU_MOD_K: /* A %= K; */ + if (K == 1) { + CLEAR_A(); + break; + } EMIT2(0x31, 0xd2); /* xor %edx,%edx */ EMIT1(0xb9);EMIT(K, 4); /* mov imm32,%ecx */ EMIT2(0xf7, 0xf1); /* div %ecx */ EMIT2(0x89, 0xd0); /* mov %edx,%eax */ break; - case BPF_S_ALU_DIV_K: /* A = reciprocal_divide(A, K); */ - EMIT3(0x48, 0x69, 0xc0); /* imul imm32,%rax,%rax */ - EMIT(K, 4); - EMIT4(0x48, 0xc1, 0xe8, 0x20); /* shr $0x20,%rax */ + case BPF_S_ALU_DIV_K: /* A /= K */ + if (K == 1) + break; + EMIT2(0x31, 0xd2); /* xor %edx,%edx */ + EMIT1(0xb9);EMIT(K, 4); /* mov imm32,%ecx */ + EMIT2(0xf7, 0xf1); /* div %ecx */ break; case BPF_S_ALU_AND_X: seen |= SEEN_XREG; diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index b046e070e088..bca9e85daaa5 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -5,7 +5,6 @@ #include <linux/delay.h> #include <linux/dmi.h> #include <linux/pci.h> -#include <linux/init.h> #include <linux/vgaarb.h> #include <asm/pci_x86.h> diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index cceb813044ef..d62ec87a2b26 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -12,6 +12,8 @@ * Bibo Mao <bibo.mao@intel.com> * Chandramouli Narayanan <mouli@linux.intel.com> * Huang Ying <ying.huang@intel.com> + * Copyright (C) 2013 SuSE Labs + * Borislav Petkov <bp@suse.de> - runtime services VA mapping * * Copied from efi_32.c to eliminate the duplicated code between EFI * 32/64 support code. --ying 2007-10-26 @@ -51,7 +53,7 @@ #include <asm/x86_init.h> #include <asm/rtc.h> -#define EFI_DEBUG 1 +#define EFI_DEBUG #define EFI_MIN_RESERVE 5120 @@ -74,6 +76,8 @@ static __initdata efi_config_table_type_t arch_tables[] = { {NULL_GUID, NULL, NULL}, }; +u64 efi_setup; /* efi setup_data physical address */ + /* * Returns 1 if 'facility' is enabled, 0 otherwise. */ @@ -110,7 +114,6 @@ static int __init setup_storage_paranoia(char *arg) } early_param("efi_no_storage_paranoia", setup_storage_paranoia); - static efi_status_t virt_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc) { unsigned long flags; @@ -398,9 +401,9 @@ int __init efi_memblock_x86_reserve_range(void) return 0; } -#if EFI_DEBUG static void __init print_efi_memmap(void) { +#ifdef EFI_DEBUG efi_memory_desc_t *md; void *p; int i; @@ -415,8 +418,8 @@ static void __init print_efi_memmap(void) md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT), (md->num_pages >> (20 - EFI_PAGE_SHIFT))); } -} #endif /* EFI_DEBUG */ +} void __init efi_reserve_boot_services(void) { @@ -436,7 +439,7 @@ void __init efi_reserve_boot_services(void) * - Not within any part of the kernel * - Not the bios reserved area */ - if ((start+size >= __pa_symbol(_text) + if ((start + size > __pa_symbol(_text) && start <= __pa_symbol(_end)) || !e820_all_mapped(start, start+size, E820_RAM) || memblock_is_region_reserved(start, size)) { @@ -489,18 +492,27 @@ static int __init efi_systab_init(void *phys) { if (efi_enabled(EFI_64BIT)) { efi_system_table_64_t *systab64; + struct efi_setup_data *data = NULL; u64 tmp = 0; + if (efi_setup) { + data = early_memremap(efi_setup, sizeof(*data)); + if (!data) + return -ENOMEM; + } systab64 = early_ioremap((unsigned long)phys, sizeof(*systab64)); if (systab64 == NULL) { pr_err("Couldn't map the system table!\n"); + if (data) + early_iounmap(data, sizeof(*data)); return -ENOMEM; } efi_systab.hdr = systab64->hdr; - efi_systab.fw_vendor = systab64->fw_vendor; - tmp |= systab64->fw_vendor; + efi_systab.fw_vendor = data ? (unsigned long)data->fw_vendor : + systab64->fw_vendor; + tmp |= data ? data->fw_vendor : systab64->fw_vendor; efi_systab.fw_revision = systab64->fw_revision; efi_systab.con_in_handle = systab64->con_in_handle; tmp |= systab64->con_in_handle; @@ -514,15 +526,20 @@ static int __init efi_systab_init(void *phys) tmp |= systab64->stderr_handle; efi_systab.stderr = systab64->stderr; tmp |= systab64->stderr; - efi_systab.runtime = (void *)(unsigned long)systab64->runtime; - tmp |= systab64->runtime; + efi_systab.runtime = data ? + (void *)(unsigned long)data->runtime : + (void *)(unsigned long)systab64->runtime; + tmp |= data ? data->runtime : systab64->runtime; efi_systab.boottime = (void *)(unsigned long)systab64->boottime; tmp |= systab64->boottime; efi_systab.nr_tables = systab64->nr_tables; - efi_systab.tables = systab64->tables; - tmp |= systab64->tables; + efi_systab.tables = data ? (unsigned long)data->tables : + systab64->tables; + tmp |= data ? data->tables : systab64->tables; early_iounmap(systab64, sizeof(*systab64)); + if (data) + early_iounmap(data, sizeof(*data)); #ifdef CONFIG_X86_32 if (tmp >> 32) { pr_err("EFI data located above 4GB, disabling EFI.\n"); @@ -626,6 +643,62 @@ static int __init efi_memmap_init(void) return 0; } +/* + * A number of config table entries get remapped to virtual addresses + * after entering EFI virtual mode. However, the kexec kernel requires + * their physical addresses therefore we pass them via setup_data and + * correct those entries to their respective physical addresses here. + * + * Currently only handles smbios which is necessary for some firmware + * implementation. + */ +static int __init efi_reuse_config(u64 tables, int nr_tables) +{ + int i, sz, ret = 0; + void *p, *tablep; + struct efi_setup_data *data; + + if (!efi_setup) + return 0; + + if (!efi_enabled(EFI_64BIT)) + return 0; + + data = early_memremap(efi_setup, sizeof(*data)); + if (!data) { + ret = -ENOMEM; + goto out; + } + + if (!data->smbios) + goto out_memremap; + + sz = sizeof(efi_config_table_64_t); + + p = tablep = early_memremap(tables, nr_tables * sz); + if (!p) { + pr_err("Could not map Configuration table!\n"); + ret = -ENOMEM; + goto out_memremap; + } + + for (i = 0; i < efi.systab->nr_tables; i++) { + efi_guid_t guid; + + guid = ((efi_config_table_64_t *)p)->guid; + + if (!efi_guidcmp(guid, SMBIOS_TABLE_GUID)) + ((efi_config_table_64_t *)p)->table = data->smbios; + p += sz; + } + early_iounmap(tablep, nr_tables * sz); + +out_memremap: + early_iounmap(data, sizeof(*data)); +out: + return ret; +} + void __init efi_init(void) { efi_char16_t *c16; @@ -651,6 +724,10 @@ void __init efi_init(void) set_bit(EFI_SYSTEM_TABLES, &x86_efi_facility); + efi.config_table = (unsigned long)efi.systab->tables; + efi.fw_vendor = (unsigned long)efi.systab->fw_vendor; + efi.runtime = (unsigned long)efi.systab->runtime; + /* * Show what we know for posterity */ @@ -667,6 +744,9 @@ void __init efi_init(void) efi.systab->hdr.revision >> 16, efi.systab->hdr.revision & 0xffff, vendor); + if (efi_reuse_config(efi.systab->tables, efi.systab->nr_tables)) + return; + if (efi_config_init(arch_tables)) return; @@ -684,15 +764,12 @@ void __init efi_init(void) return; set_bit(EFI_RUNTIME_SERVICES, &x86_efi_facility); } - if (efi_memmap_init()) return; set_bit(EFI_MEMMAP, &x86_efi_facility); -#if EFI_DEBUG print_efi_memmap(); -#endif } void __init efi_late_init(void) @@ -741,36 +818,38 @@ void efi_memory_uc(u64 addr, unsigned long size) set_memory_uc(addr, npages); } -/* - * This function will switch the EFI runtime services to virtual mode. - * Essentially, look through the EFI memmap and map every region that - * has the runtime attribute bit set in its memory descriptor and update - * that memory descriptor with the virtual address obtained from ioremap(). - * This enables the runtime services to be called without having to - * thunk back into physical mode for every invocation. - */ -void __init efi_enter_virtual_mode(void) +void __init old_map_region(efi_memory_desc_t *md) { - efi_memory_desc_t *md, *prev_md = NULL; - efi_status_t status; + u64 start_pfn, end_pfn, end; unsigned long size; - u64 end, systab, start_pfn, end_pfn; - void *p, *va, *new_memmap = NULL; - int count = 0; + void *va; - efi.systab = NULL; + start_pfn = PFN_DOWN(md->phys_addr); + size = md->num_pages << PAGE_SHIFT; + end = md->phys_addr + size; + end_pfn = PFN_UP(end); - /* - * We don't do virtual mode, since we don't do runtime services, on - * non-native EFI - */ + if (pfn_range_is_mapped(start_pfn, end_pfn)) { + va = __va(md->phys_addr); - if (!efi_is_native()) { - efi_unmap_memmap(); - return; - } + if (!(md->attribute & EFI_MEMORY_WB)) + efi_memory_uc((u64)(unsigned long)va, size); + } else + va = efi_ioremap(md->phys_addr, size, + md->type, md->attribute); + + md->virt_addr = (u64) (unsigned long) va; + if (!va) + pr_err("ioremap of 0x%llX failed!\n", + (unsigned long long)md->phys_addr); +} + +/* Merge contiguous regions of the same type and attribute */ +static void __init efi_merge_regions(void) +{ + void *p; + efi_memory_desc_t *md, *prev_md = NULL; - /* Merge contiguous regions of the same type and attribute */ for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { u64 prev_size; md = p; @@ -796,6 +875,77 @@ void __init efi_enter_virtual_mode(void) } prev_md = md; } +} + +static void __init get_systab_virt_addr(efi_memory_desc_t *md) +{ + unsigned long size; + u64 end, systab; + + size = md->num_pages << EFI_PAGE_SHIFT; + end = md->phys_addr + size; + systab = (u64)(unsigned long)efi_phys.systab; + if (md->phys_addr <= systab && systab < end) { + systab += md->virt_addr - md->phys_addr; + efi.systab = (efi_system_table_t *)(unsigned long)systab; + } +} + +static int __init save_runtime_map(void) +{ + efi_memory_desc_t *md; + void *tmp, *p, *q = NULL; + int count = 0; + + for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { + md = p; + + if (!(md->attribute & EFI_MEMORY_RUNTIME) || + (md->type == EFI_BOOT_SERVICES_CODE) || + (md->type == EFI_BOOT_SERVICES_DATA)) + continue; + tmp = krealloc(q, (count + 1) * memmap.desc_size, GFP_KERNEL); + if (!tmp) + goto out; + q = tmp; + + memcpy(q + count * memmap.desc_size, md, memmap.desc_size); + count++; + } + + efi_runtime_map_setup(q, count, memmap.desc_size); + + return 0; +out: + kfree(q); + return -ENOMEM; +} + +/* + * Map efi regions which were passed via setup_data. The virt_addr is a fixed + * addr which was used in first kernel of a kexec boot. + */ +static void __init efi_map_regions_fixed(void) +{ + void *p; + efi_memory_desc_t *md; + + for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { + md = p; + efi_map_region_fixed(md); /* FIXME: add error handling */ + get_systab_virt_addr(md); + } + +} + +/* + * Map efi memory ranges for runtime serivce and update new_memmap with virtual + * addresses. + */ +static void * __init efi_map_regions(int *count) +{ + efi_memory_desc_t *md; + void *p, *tmp, *new_memmap = NULL; for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { md = p; @@ -807,53 +957,95 @@ void __init efi_enter_virtual_mode(void) continue; } - size = md->num_pages << EFI_PAGE_SHIFT; - end = md->phys_addr + size; + efi_map_region(md); + get_systab_virt_addr(md); - start_pfn = PFN_DOWN(md->phys_addr); - end_pfn = PFN_UP(end); - if (pfn_range_is_mapped(start_pfn, end_pfn)) { - va = __va(md->phys_addr); + tmp = krealloc(new_memmap, (*count + 1) * memmap.desc_size, + GFP_KERNEL); + if (!tmp) + goto out; + new_memmap = tmp; + memcpy(new_memmap + (*count * memmap.desc_size), md, + memmap.desc_size); + (*count)++; + } - if (!(md->attribute & EFI_MEMORY_WB)) - efi_memory_uc((u64)(unsigned long)va, size); - } else - va = efi_ioremap(md->phys_addr, size, - md->type, md->attribute); + return new_memmap; +out: + kfree(new_memmap); + return NULL; +} + +/* + * This function will switch the EFI runtime services to virtual mode. + * Essentially, we look through the EFI memmap and map every region that + * has the runtime attribute bit set in its memory descriptor into the + * ->trampoline_pgd page table using a top-down VA allocation scheme. + * + * The old method which used to update that memory descriptor with the + * virtual address obtained from ioremap() is still supported when the + * kernel is booted with efi=old_map on its command line. Same old + * method enabled the runtime services to be called without having to + * thunk back into physical mode for every invocation. + * + * The new method does a pagetable switch in a preemption-safe manner + * so that we're in a different address space when calling a runtime + * function. For function arguments passing we do copy the PGDs of the + * kernel page table into ->trampoline_pgd prior to each call. + * + * Specially for kexec boot, efi runtime maps in previous kernel should + * be passed in via setup_data. In that case runtime ranges will be mapped + * to the same virtual addresses as the first kernel. + */ +void __init efi_enter_virtual_mode(void) +{ + efi_status_t status; + void *new_memmap = NULL; + int err, count = 0; - md->virt_addr = (u64) (unsigned long) va; + efi.systab = NULL; - if (!va) { - pr_err("ioremap of 0x%llX failed!\n", - (unsigned long long)md->phys_addr); - continue; - } + /* + * We don't do virtual mode, since we don't do runtime services, on + * non-native EFI + */ + if (!efi_is_native()) { + efi_unmap_memmap(); + return; + } - systab = (u64) (unsigned long) efi_phys.systab; - if (md->phys_addr <= systab && systab < end) { - systab += md->virt_addr - md->phys_addr; - efi.systab = (efi_system_table_t *) (unsigned long) systab; + if (efi_setup) { + efi_map_regions_fixed(); + } else { + efi_merge_regions(); + new_memmap = efi_map_regions(&count); + if (!new_memmap) { + pr_err("Error reallocating memory, EFI runtime non-functional!\n"); + return; } - new_memmap = krealloc(new_memmap, - (count + 1) * memmap.desc_size, - GFP_KERNEL); - memcpy(new_memmap + (count * memmap.desc_size), md, - memmap.desc_size); - count++; } + err = save_runtime_map(); + if (err) + pr_err("Error saving runtime map, efi runtime on kexec non-functional!!\n"); + BUG_ON(!efi.systab); - status = phys_efi_set_virtual_address_map( - memmap.desc_size * count, - memmap.desc_size, - memmap.desc_version, - (efi_memory_desc_t *)__pa(new_memmap)); + efi_setup_page_tables(); + efi_sync_low_kernel_mappings(); - if (status != EFI_SUCCESS) { - pr_alert("Unable to switch EFI into virtual mode " - "(status=%lx)!\n", status); - panic("EFI call to SetVirtualAddressMap() failed!"); + if (!efi_setup) { + status = phys_efi_set_virtual_address_map( + memmap.desc_size * count, + memmap.desc_size, + memmap.desc_version, + (efi_memory_desc_t *)__pa(new_memmap)); + + if (status != EFI_SUCCESS) { + pr_alert("Unable to switch EFI into virtual mode (status=%lx)!\n", + status); + panic("EFI call to SetVirtualAddressMap() failed!"); + } } /* @@ -876,7 +1068,8 @@ void __init efi_enter_virtual_mode(void) efi.query_variable_info = virt_efi_query_variable_info; efi.update_capsule = virt_efi_update_capsule; efi.query_capsule_caps = virt_efi_query_capsule_caps; - if (__supported_pte_mask & _PAGE_NX) + + if (efi_enabled(EFI_OLD_MEMMAP) && (__supported_pte_mask & _PAGE_NX)) runtime_code_page_mkexec(); kfree(new_memmap); @@ -1006,3 +1199,15 @@ efi_status_t efi_query_variable_store(u32 attributes, unsigned long size) return EFI_SUCCESS; } EXPORT_SYMBOL_GPL(efi_query_variable_store); + +static int __init parse_efi_cmdline(char *str) +{ + if (*str == '=') + str++; + + if (!strncmp(str, "old_map", 7)) + set_bit(EFI_OLD_MEMMAP, &x86_efi_facility); + + return 0; +} +early_param("efi", parse_efi_cmdline); diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c index 40e446941dd7..249b183cf417 100644 --- a/arch/x86/platform/efi/efi_32.c +++ b/arch/x86/platform/efi/efi_32.c @@ -37,9 +37,19 @@ * claim EFI runtime service handler exclusively and to duplicate a memory in * low memory space say 0 - 3G. */ - static unsigned long efi_rt_eflags; +void efi_sync_low_kernel_mappings(void) {} +void efi_setup_page_tables(void) {} + +void __init efi_map_region(efi_memory_desc_t *md) +{ + old_map_region(md); +} + +void __init efi_map_region_fixed(efi_memory_desc_t *md) {} +void __init parse_efi_setup(u64 phys_addr, u32 data_len) {} + void efi_call_phys_prelog(void) { struct desc_ptr gdt_descr; diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 39a0e7f1f0a3..6284f158a47d 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -38,10 +38,28 @@ #include <asm/efi.h> #include <asm/cacheflush.h> #include <asm/fixmap.h> +#include <asm/realmode.h> static pgd_t *save_pgd __initdata; static unsigned long efi_flags __initdata; +/* + * We allocate runtime services regions bottom-up, starting from -4G, i.e. + * 0xffff_ffff_0000_0000 and limit EFI VA mapping space to 64G. + */ +static u64 efi_va = -4 * (1UL << 30); +#define EFI_VA_END (-68 * (1UL << 30)) + +/* + * Scratch space used for switching the pagetable in the EFI stub + */ +struct efi_scratch { + u64 r15; + u64 prev_cr3; + pgd_t *efi_pgt; + bool use_pgd; +}; + static void __init early_code_mapping_set_exec(int executable) { efi_memory_desc_t *md; @@ -65,6 +83,9 @@ void __init efi_call_phys_prelog(void) int pgd; int n_pgds; + if (!efi_enabled(EFI_OLD_MEMMAP)) + return; + early_code_mapping_set_exec(1); local_irq_save(efi_flags); @@ -86,6 +107,10 @@ void __init efi_call_phys_epilog(void) */ int pgd; int n_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT) , PGDIR_SIZE); + + if (!efi_enabled(EFI_OLD_MEMMAP)) + return; + for (pgd = 0; pgd < n_pgds; pgd++) set_pgd(pgd_offset_k(pgd * PGDIR_SIZE), save_pgd[pgd]); kfree(save_pgd); @@ -94,6 +119,96 @@ void __init efi_call_phys_epilog(void) early_code_mapping_set_exec(0); } +/* + * Add low kernel mappings for passing arguments to EFI functions. + */ +void efi_sync_low_kernel_mappings(void) +{ + unsigned num_pgds; + pgd_t *pgd = (pgd_t *)__va(real_mode_header->trampoline_pgd); + + if (efi_enabled(EFI_OLD_MEMMAP)) + return; + + num_pgds = pgd_index(MODULES_END - 1) - pgd_index(PAGE_OFFSET); + + memcpy(pgd + pgd_index(PAGE_OFFSET), + init_mm.pgd + pgd_index(PAGE_OFFSET), + sizeof(pgd_t) * num_pgds); +} + +void efi_setup_page_tables(void) +{ + efi_scratch.efi_pgt = (pgd_t *)(unsigned long)real_mode_header->trampoline_pgd; + + if (!efi_enabled(EFI_OLD_MEMMAP)) + efi_scratch.use_pgd = true; +} + +static void __init __map_region(efi_memory_desc_t *md, u64 va) +{ + pgd_t *pgd = (pgd_t *)__va(real_mode_header->trampoline_pgd); + unsigned long pf = 0; + + if (!(md->attribute & EFI_MEMORY_WB)) + pf |= _PAGE_PCD; + + if (kernel_map_pages_in_pgd(pgd, md->phys_addr, va, md->num_pages, pf)) + pr_warn("Error mapping PA 0x%llx -> VA 0x%llx!\n", + md->phys_addr, va); +} + +void __init efi_map_region(efi_memory_desc_t *md) +{ + unsigned long size = md->num_pages << PAGE_SHIFT; + u64 pa = md->phys_addr; + + if (efi_enabled(EFI_OLD_MEMMAP)) + return old_map_region(md); + + /* + * Make sure the 1:1 mappings are present as a catch-all for b0rked + * firmware which doesn't update all internal pointers after switching + * to virtual mode and would otherwise crap on us. + */ + __map_region(md, md->phys_addr); + + efi_va -= size; + + /* Is PA 2M-aligned? */ + if (!(pa & (PMD_SIZE - 1))) { + efi_va &= PMD_MASK; + } else { + u64 pa_offset = pa & (PMD_SIZE - 1); + u64 prev_va = efi_va; + + /* get us the same offset within this 2M page */ + efi_va = (efi_va & PMD_MASK) + pa_offset; + + if (efi_va > prev_va) + efi_va -= PMD_SIZE; + } + + if (efi_va < EFI_VA_END) { + pr_warn(FW_WARN "VA address range overflow!\n"); + return; + } + + /* Do the VA map */ + __map_region(md, efi_va); + md->virt_addr = efi_va; +} + +/* + * kexec kernel will use efi_map_region_fixed to map efi runtime memory ranges. + * md->virt_addr is the original virtual address which had been mapped in kexec + * 1st kernel. + */ +void __init efi_map_region_fixed(efi_memory_desc_t *md) +{ + __map_region(md, md->virt_addr); +} + void __iomem *__init efi_ioremap(unsigned long phys_addr, unsigned long size, u32 type, u64 attribute) { @@ -113,3 +228,8 @@ void __iomem *__init efi_ioremap(unsigned long phys_addr, unsigned long size, return (void __iomem *)__va(phys_addr); } + +void __init parse_efi_setup(u64 phys_addr, u32 data_len) +{ + efi_setup = phys_addr + sizeof(struct setup_data); +} diff --git a/arch/x86/platform/efi/efi_stub_64.S b/arch/x86/platform/efi/efi_stub_64.S index 4c07ccab8146..88073b140298 100644 --- a/arch/x86/platform/efi/efi_stub_64.S +++ b/arch/x86/platform/efi/efi_stub_64.S @@ -34,10 +34,47 @@ mov %rsi, %cr0; \ mov (%rsp), %rsp + /* stolen from gcc */ + .macro FLUSH_TLB_ALL + movq %r15, efi_scratch(%rip) + movq %r14, efi_scratch+8(%rip) + movq %cr4, %r15 + movq %r15, %r14 + andb $0x7f, %r14b + movq %r14, %cr4 + movq %r15, %cr4 + movq efi_scratch+8(%rip), %r14 + movq efi_scratch(%rip), %r15 + .endm + + .macro SWITCH_PGT + cmpb $0, efi_scratch+24(%rip) + je 1f + movq %r15, efi_scratch(%rip) # r15 + # save previous CR3 + movq %cr3, %r15 + movq %r15, efi_scratch+8(%rip) # prev_cr3 + movq efi_scratch+16(%rip), %r15 # EFI pgt + movq %r15, %cr3 + 1: + .endm + + .macro RESTORE_PGT + cmpb $0, efi_scratch+24(%rip) + je 2f + movq efi_scratch+8(%rip), %r15 + movq %r15, %cr3 + movq efi_scratch(%rip), %r15 + FLUSH_TLB_ALL + 2: + .endm + ENTRY(efi_call0) SAVE_XMM subq $32, %rsp + SWITCH_PGT call *%rdi + RESTORE_PGT addq $32, %rsp RESTORE_XMM ret @@ -47,7 +84,9 @@ ENTRY(efi_call1) SAVE_XMM subq $32, %rsp mov %rsi, %rcx + SWITCH_PGT call *%rdi + RESTORE_PGT addq $32, %rsp RESTORE_XMM ret @@ -57,7 +96,9 @@ ENTRY(efi_call2) SAVE_XMM subq $32, %rsp mov %rsi, %rcx + SWITCH_PGT call *%rdi + RESTORE_PGT addq $32, %rsp RESTORE_XMM ret @@ -68,7 +109,9 @@ ENTRY(efi_call3) subq $32, %rsp mov %rcx, %r8 mov %rsi, %rcx + SWITCH_PGT call *%rdi + RESTORE_PGT addq $32, %rsp RESTORE_XMM ret @@ -80,7 +123,9 @@ ENTRY(efi_call4) mov %r8, %r9 mov %rcx, %r8 mov %rsi, %rcx + SWITCH_PGT call *%rdi + RESTORE_PGT addq $32, %rsp RESTORE_XMM ret @@ -93,7 +138,9 @@ ENTRY(efi_call5) mov %r8, %r9 mov %rcx, %r8 mov %rsi, %rcx + SWITCH_PGT call *%rdi + RESTORE_PGT addq $48, %rsp RESTORE_XMM ret @@ -109,8 +156,15 @@ ENTRY(efi_call6) mov %r8, %r9 mov %rcx, %r8 mov %rsi, %rcx + SWITCH_PGT call *%rdi + RESTORE_PGT addq $48, %rsp RESTORE_XMM ret ENDPROC(efi_call6) + + .data +ENTRY(efi_scratch) + .fill 3,8,0 + .byte 0 diff --git a/arch/x86/platform/intel-mid/early_printk_intel_mid.c b/arch/x86/platform/intel-mid/early_printk_intel_mid.c index 4f702f554f6e..e0bd082a80e0 100644 --- a/arch/x86/platform/intel-mid/early_printk_intel_mid.c +++ b/arch/x86/platform/intel-mid/early_printk_intel_mid.c @@ -22,7 +22,6 @@ #include <linux/console.h> #include <linux/kernel.h> #include <linux/delay.h> -#include <linux/init.h> #include <linux/io.h> #include <asm/fixmap.h> diff --git a/arch/x86/platform/iris/iris.c b/arch/x86/platform/iris/iris.c index e6cb80f620af..4d171e8640ef 100644 --- a/arch/x86/platform/iris/iris.c +++ b/arch/x86/platform/iris/iris.c @@ -27,7 +27,6 @@ #include <linux/kernel.h> #include <linux/errno.h> #include <linux/delay.h> -#include <linux/init.h> #include <linux/pm.h> #include <asm/io.h> diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c index efe4d7220397..dfe605ac1bcd 100644 --- a/arch/x86/platform/uv/tlb_uv.c +++ b/arch/x86/platform/uv/tlb_uv.c @@ -433,15 +433,49 @@ static void reset_with_ipi(struct pnmask *distribution, struct bau_control *bcp) return; } -static inline unsigned long cycles_2_us(unsigned long long cyc) +/* + * Not to be confused with cycles_2_ns() from tsc.c; this gives a relative + * number, not an absolute. It converts a duration in cycles to a duration in + * ns. + */ +static inline unsigned long long cycles_2_ns(unsigned long long cyc) { + struct cyc2ns_data *data = cyc2ns_read_begin(); unsigned long long ns; - unsigned long us; - int cpu = smp_processor_id(); - ns = (cyc * per_cpu(cyc2ns, cpu)) >> CYC2NS_SCALE_FACTOR; - us = ns / 1000; - return us; + ns = mul_u64_u32_shr(cyc, data->cyc2ns_mul, data->cyc2ns_shift); + + cyc2ns_read_end(data); + return ns; +} + +/* + * The reverse of the above; converts a duration in ns to a duration in cycles. + */ +static inline unsigned long long ns_2_cycles(unsigned long long ns) +{ + struct cyc2ns_data *data = cyc2ns_read_begin(); + unsigned long long cyc; + + cyc = (ns << data->cyc2ns_shift) / data->cyc2ns_mul; + + cyc2ns_read_end(data); + return cyc; +} + +static inline unsigned long cycles_2_us(unsigned long long cyc) +{ + return cycles_2_ns(cyc) / NSEC_PER_USEC; +} + +static inline cycles_t sec_2_cycles(unsigned long sec) +{ + return ns_2_cycles(sec * NSEC_PER_SEC); +} + +static inline unsigned long long usec_2_cycles(unsigned long usec) +{ + return ns_2_cycles(usec * NSEC_PER_USEC); } /* @@ -668,16 +702,6 @@ static int wait_completion(struct bau_desc *bau_desc, bcp, try); } -static inline cycles_t sec_2_cycles(unsigned long sec) -{ - unsigned long ns; - cycles_t cyc; - - ns = sec * 1000000000; - cyc = (ns << CYC2NS_SCALE_FACTOR)/(per_cpu(cyc2ns, smp_processor_id())); - return cyc; -} - /* * Our retries are blocked by all destination sw ack resources being * in use, and a timeout is pending. In that case hardware immediately @@ -1327,16 +1351,6 @@ static void ptc_seq_stop(struct seq_file *file, void *data) { } -static inline unsigned long long usec_2_cycles(unsigned long microsec) -{ - unsigned long ns; - unsigned long long cyc; - - ns = microsec * 1000; - cyc = (ns << CYC2NS_SCALE_FACTOR)/(per_cpu(cyc2ns, smp_processor_id())); - return cyc; -} - /* * Display the statistics thru /proc/sgi_uv/ptc_statistics * 'data' points to the cpu number diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c index a44f457e70a1..bad628a620c4 100644 --- a/arch/x86/realmode/init.c +++ b/arch/x86/realmode/init.c @@ -29,12 +29,10 @@ void __init reserve_real_mode(void) void __init setup_real_mode(void) { u16 real_mode_seg; - u32 *rel; + const u32 *rel; u32 count; - u32 *ptr; - u16 *seg; - int i; unsigned char *base; + unsigned long phys_base; struct trampoline_header *trampoline_header; size_t size = PAGE_ALIGN(real_mode_blob_end - real_mode_blob); #ifdef CONFIG_X86_64 @@ -46,23 +44,23 @@ void __init setup_real_mode(void) memcpy(base, real_mode_blob, size); - real_mode_seg = __pa(base) >> 4; + phys_base = __pa(base); + real_mode_seg = phys_base >> 4; + rel = (u32 *) real_mode_relocs; /* 16-bit segment relocations. */ - count = rel[0]; - rel = &rel[1]; - for (i = 0; i < count; i++) { - seg = (u16 *) (base + rel[i]); + count = *rel++; + while (count--) { + u16 *seg = (u16 *) (base + *rel++); *seg = real_mode_seg; } /* 32-bit linear relocations. */ - count = rel[i]; - rel = &rel[i + 1]; - for (i = 0; i < count; i++) { - ptr = (u32 *) (base + rel[i]); - *ptr += __pa(base); + count = *rel++; + while (count--) { + u32 *ptr = (u32 *) (base + *rel++); + *ptr += phys_base; } /* Must be perfomed *after* relocation. */ diff --git a/arch/x86/realmode/rm/reboot.S b/arch/x86/realmode/rm/reboot.S index f932ea61d1c8..d66c607bdc58 100644 --- a/arch/x86/realmode/rm/reboot.S +++ b/arch/x86/realmode/rm/reboot.S @@ -1,5 +1,4 @@ #include <linux/linkage.h> -#include <linux/init.h> #include <asm/segment.h> #include <asm/page_types.h> #include <asm/processor-flags.h> diff --git a/arch/x86/realmode/rm/trampoline_32.S b/arch/x86/realmode/rm/trampoline_32.S index c1b2791183e7..48ddd76bc4c3 100644 --- a/arch/x86/realmode/rm/trampoline_32.S +++ b/arch/x86/realmode/rm/trampoline_32.S @@ -20,7 +20,6 @@ */ #include <linux/linkage.h> -#include <linux/init.h> #include <asm/segment.h> #include <asm/page_types.h> #include "realmode.h" diff --git a/arch/x86/realmode/rm/trampoline_64.S b/arch/x86/realmode/rm/trampoline_64.S index bb360dc39d21..dac7b20d2f9d 100644 --- a/arch/x86/realmode/rm/trampoline_64.S +++ b/arch/x86/realmode/rm/trampoline_64.S @@ -25,7 +25,6 @@ */ #include <linux/linkage.h> -#include <linux/init.h> #include <asm/pgtable_types.h> #include <asm/page_types.h> #include <asm/msr.h> diff --git a/arch/x86/syscalls/syscall_32.tbl b/arch/x86/syscalls/syscall_32.tbl index aabfb8380a1c..96bc506ac6de 100644 --- a/arch/x86/syscalls/syscall_32.tbl +++ b/arch/x86/syscalls/syscall_32.tbl @@ -357,3 +357,5 @@ 348 i386 process_vm_writev sys_process_vm_writev compat_sys_process_vm_writev 349 i386 kcmp sys_kcmp 350 i386 finit_module sys_finit_module +351 i386 sched_setattr sys_sched_setattr +352 i386 sched_getattr sys_sched_getattr diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl index 38ae65dfd14f..a12bddc7ccea 100644 --- a/arch/x86/syscalls/syscall_64.tbl +++ b/arch/x86/syscalls/syscall_64.tbl @@ -320,6 +320,8 @@ 311 64 process_vm_writev sys_process_vm_writev 312 common kcmp sys_kcmp 313 common finit_module sys_finit_module +314 common sched_setattr sys_sched_setattr +315 common sched_getattr sys_sched_getattr # # x32-specific system call numbers start at 512 to avoid cache impact diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c index 2ada505067cc..eb5d7a56f8d4 100644 --- a/arch/x86/vdso/vclock_gettime.c +++ b/arch/x86/vdso/vclock_gettime.c @@ -178,7 +178,7 @@ notrace static int __always_inline do_realtime(struct timespec *ts) ts->tv_nsec = 0; do { - seq = read_seqcount_begin_no_lockdep(>od->seq); + seq = raw_read_seqcount_begin(>od->seq); mode = gtod->clock.vclock_mode; ts->tv_sec = gtod->wall_time_sec; ns = gtod->wall_time_snsec; @@ -198,7 +198,7 @@ notrace static int do_monotonic(struct timespec *ts) ts->tv_nsec = 0; do { - seq = read_seqcount_begin_no_lockdep(>od->seq); + seq = raw_read_seqcount_begin(>od->seq); mode = gtod->clock.vclock_mode; ts->tv_sec = gtod->monotonic_time_sec; ns = gtod->monotonic_time_snsec; @@ -214,7 +214,7 @@ notrace static int do_realtime_coarse(struct timespec *ts) { unsigned long seq; do { - seq = read_seqcount_begin_no_lockdep(>od->seq); + seq = raw_read_seqcount_begin(>od->seq); ts->tv_sec = gtod->wall_time_coarse.tv_sec; ts->tv_nsec = gtod->wall_time_coarse.tv_nsec; } while (unlikely(read_seqcount_retry(>od->seq, seq))); @@ -225,7 +225,7 @@ notrace static int do_monotonic_coarse(struct timespec *ts) { unsigned long seq; do { - seq = read_seqcount_begin_no_lockdep(>od->seq); + seq = raw_read_seqcount_begin(>od->seq); ts->tv_sec = gtod->monotonic_time_coarse.tv_sec; ts->tv_nsec = gtod->monotonic_time_coarse.tv_nsec; } while (unlikely(read_seqcount_retry(>od->seq, seq))); diff --git a/arch/x86/vdso/vdso.S b/arch/x86/vdso/vdso.S index 01f5e3b4613c..1e13eb8c9656 100644 --- a/arch/x86/vdso/vdso.S +++ b/arch/x86/vdso/vdso.S @@ -1,6 +1,5 @@ #include <asm/page_types.h> #include <linux/linkage.h> -#include <linux/init.h> __PAGE_ALIGNED_DATA diff --git a/arch/x86/vdso/vdsox32.S b/arch/x86/vdso/vdsox32.S index d6b9a7f42a8a..295f1c7543d8 100644 --- a/arch/x86/vdso/vdsox32.S +++ b/arch/x86/vdso/vdsox32.S @@ -1,6 +1,5 @@ #include <asm/page_types.h> #include <linux/linkage.h> -#include <linux/init.h> __PAGE_ALIGNED_DATA |