diff options
Diffstat (limited to 'arch/x86')
47 files changed, 765 insertions, 381 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index ee2fb9d37745..5cd6eea9b7b3 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -123,6 +123,7 @@ config X86 select COMPAT_OLD_SIGACTION if IA32_EMULATION select RTC_LIB select HAVE_DEBUG_STACKOVERFLOW + select HAVE_IRQ_EXIT_ON_IRQ_STACK if X86_64 config INSTRUCTION_DECODER def_bool y @@ -860,7 +861,7 @@ source "kernel/Kconfig.preempt" config X86_UP_APIC bool "Local APIC support on uniprocessors" - depends on X86_32 && !SMP && !X86_32_NON_STANDARD + depends on X86_32 && !SMP && !X86_32_NON_STANDARD && !PCI_MSI ---help--- A local APIC (Advanced Programmable Interrupt Controller) is an integrated interrupt controller in the CPU. If you have a single-CPU @@ -885,11 +886,11 @@ config X86_UP_IOAPIC config X86_LOCAL_APIC def_bool y - depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_APIC + depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_APIC || PCI_MSI config X86_IO_APIC def_bool y - depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_IOAPIC + depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_IOAPIC || PCI_MSI config X86_VISWS_APIC def_bool y @@ -1033,6 +1034,7 @@ config X86_REBOOTFIXUPS config MICROCODE tristate "CPU microcode loading support" + depends on CPU_SUP_AMD || CPU_SUP_INTEL select FW_LOADER ---help--- diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h index 722aa3b04624..da31c8b8a92d 100644 --- a/arch/x86/include/asm/atomic.h +++ b/arch/x86/include/asm/atomic.h @@ -6,6 +6,7 @@ #include <asm/processor.h> #include <asm/alternative.h> #include <asm/cmpxchg.h> +#include <asm/rmwcc.h> /* * Atomic operations that C can't guarantee us. Useful for @@ -76,12 +77,7 @@ static inline void atomic_sub(int i, atomic_t *v) */ static inline int atomic_sub_and_test(int i, atomic_t *v) { - unsigned char c; - - asm volatile(LOCK_PREFIX "subl %2,%0; sete %1" - : "+m" (v->counter), "=qm" (c) - : "ir" (i) : "memory"); - return c; + GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, i, "%0", "e"); } /** @@ -118,12 +114,7 @@ static inline void atomic_dec(atomic_t *v) */ static inline int atomic_dec_and_test(atomic_t *v) { - unsigned char c; - - asm volatile(LOCK_PREFIX "decl %0; sete %1" - : "+m" (v->counter), "=qm" (c) - : : "memory"); - return c != 0; + GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", "e"); } /** @@ -136,12 +127,7 @@ static inline int atomic_dec_and_test(atomic_t *v) */ static inline int atomic_inc_and_test(atomic_t *v) { - unsigned char c; - - asm volatile(LOCK_PREFIX "incl %0; sete %1" - : "+m" (v->counter), "=qm" (c) - : : "memory"); - return c != 0; + GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, "%0", "e"); } /** @@ -155,12 +141,7 @@ static inline int atomic_inc_and_test(atomic_t *v) */ static inline int atomic_add_negative(int i, atomic_t *v) { - unsigned char c; - - asm volatile(LOCK_PREFIX "addl %2,%0; sets %1" - : "+m" (v->counter), "=qm" (c) - : "ir" (i) : "memory"); - return c; + GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, i, "%0", "s"); } /** diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h index 0e1cbfc8ee06..3f065c985aee 100644 --- a/arch/x86/include/asm/atomic64_64.h +++ b/arch/x86/include/asm/atomic64_64.h @@ -72,12 +72,7 @@ static inline void atomic64_sub(long i, atomic64_t *v) */ static inline int atomic64_sub_and_test(long i, atomic64_t *v) { - unsigned char c; - - asm volatile(LOCK_PREFIX "subq %2,%0; sete %1" - : "=m" (v->counter), "=qm" (c) - : "er" (i), "m" (v->counter) : "memory"); - return c; + GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, i, "%0", "e"); } /** @@ -116,12 +111,7 @@ static inline void atomic64_dec(atomic64_t *v) */ static inline int atomic64_dec_and_test(atomic64_t *v) { - unsigned char c; - - asm volatile(LOCK_PREFIX "decq %0; sete %1" - : "=m" (v->counter), "=qm" (c) - : "m" (v->counter) : "memory"); - return c != 0; + GEN_UNARY_RMWcc(LOCK_PREFIX "decq", v->counter, "%0", "e"); } /** @@ -134,12 +124,7 @@ static inline int atomic64_dec_and_test(atomic64_t *v) */ static inline int atomic64_inc_and_test(atomic64_t *v) { - unsigned char c; - - asm volatile(LOCK_PREFIX "incq %0; sete %1" - : "=m" (v->counter), "=qm" (c) - : "m" (v->counter) : "memory"); - return c != 0; + GEN_UNARY_RMWcc(LOCK_PREFIX "incq", v->counter, "%0", "e"); } /** @@ -153,12 +138,7 @@ static inline int atomic64_inc_and_test(atomic64_t *v) */ static inline int atomic64_add_negative(long i, atomic64_t *v) { - unsigned char c; - - asm volatile(LOCK_PREFIX "addq %2,%0; sets %1" - : "=m" (v->counter), "=qm" (c) - : "er" (i), "m" (v->counter) : "memory"); - return c; + GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, i, "%0", "s"); } /** diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index 41639ce8fd63..6d76d0935989 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -14,6 +14,7 @@ #include <linux/compiler.h> #include <asm/alternative.h> +#include <asm/rmwcc.h> #if BITS_PER_LONG == 32 # define _BITOPS_LONG_SHIFT 5 @@ -204,12 +205,7 @@ static inline void change_bit(long nr, volatile unsigned long *addr) */ static inline int test_and_set_bit(long nr, volatile unsigned long *addr) { - int oldbit; - - asm volatile(LOCK_PREFIX "bts %2,%1\n\t" - "sbb %0,%0" : "=r" (oldbit), ADDR : "Ir" (nr) : "memory"); - - return oldbit; + GEN_BINARY_RMWcc(LOCK_PREFIX "bts", *addr, nr, "%0", "c"); } /** @@ -255,13 +251,7 @@ static inline int __test_and_set_bit(long nr, volatile unsigned long *addr) */ static inline int test_and_clear_bit(long nr, volatile unsigned long *addr) { - int oldbit; - - asm volatile(LOCK_PREFIX "btr %2,%1\n\t" - "sbb %0,%0" - : "=r" (oldbit), ADDR : "Ir" (nr) : "memory"); - - return oldbit; + GEN_BINARY_RMWcc(LOCK_PREFIX "btr", *addr, nr, "%0", "c"); } /** @@ -314,13 +304,7 @@ static inline int __test_and_change_bit(long nr, volatile unsigned long *addr) */ static inline int test_and_change_bit(long nr, volatile unsigned long *addr) { - int oldbit; - - asm volatile(LOCK_PREFIX "btc %2,%1\n\t" - "sbb %0,%0" - : "=r" (oldbit), ADDR : "Ir" (nr) : "memory"); - - return oldbit; + GEN_BINARY_RMWcc(LOCK_PREFIX "btc", *addr, nr, "%0", "c"); } static __always_inline int constant_test_bit(long nr, const volatile unsigned long *addr) diff --git a/arch/x86/include/asm/calling.h b/arch/x86/include/asm/calling.h index 0fa675033912..cb4c73bfeb48 100644 --- a/arch/x86/include/asm/calling.h +++ b/arch/x86/include/asm/calling.h @@ -48,6 +48,8 @@ For 32-bit we have the following conventions - kernel is built with #include <asm/dwarf2.h> +#ifdef CONFIG_X86_64 + /* * 64-bit system call stack frame layout defines and helpers, * for assembly code: @@ -192,3 +194,51 @@ For 32-bit we have the following conventions - kernel is built with .macro icebp .byte 0xf1 .endm + +#else /* CONFIG_X86_64 */ + +/* + * For 32bit only simplified versions of SAVE_ALL/RESTORE_ALL. These + * are different from the entry_32.S versions in not changing the segment + * registers. So only suitable for in kernel use, not when transitioning + * from or to user space. The resulting stack frame is not a standard + * pt_regs frame. The main use case is calling C code from assembler + * when all the registers need to be preserved. + */ + + .macro SAVE_ALL + pushl_cfi %eax + CFI_REL_OFFSET eax, 0 + pushl_cfi %ebp + CFI_REL_OFFSET ebp, 0 + pushl_cfi %edi + CFI_REL_OFFSET edi, 0 + pushl_cfi %esi + CFI_REL_OFFSET esi, 0 + pushl_cfi %edx + CFI_REL_OFFSET edx, 0 + pushl_cfi %ecx + CFI_REL_OFFSET ecx, 0 + pushl_cfi %ebx + CFI_REL_OFFSET ebx, 0 + .endm + + .macro RESTORE_ALL + popl_cfi %ebx + CFI_RESTORE ebx + popl_cfi %ecx + CFI_RESTORE ecx + popl_cfi %edx + CFI_RESTORE edx + popl_cfi %esi + CFI_RESTORE esi + popl_cfi %edi + CFI_RESTORE edi + popl_cfi %ebp + CFI_RESTORE ebp + popl_cfi %eax + CFI_RESTORE eax + .endm + +#endif /* CONFIG_X86_64 */ + diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index d3f5c63078d8..89270b4318db 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -374,7 +374,7 @@ static __always_inline __pure bool __static_cpu_has(u16 bit) * Catch too early usage of this before alternatives * have run. */ - asm goto("1: jmp %l[t_warn]\n" + asm_volatile_goto("1: jmp %l[t_warn]\n" "2:\n" ".section .altinstructions,\"a\"\n" " .long 1b - .\n" @@ -388,7 +388,7 @@ static __always_inline __pure bool __static_cpu_has(u16 bit) #endif - asm goto("1: jmp %l[t_no]\n" + asm_volatile_goto("1: jmp %l[t_no]\n" "2:\n" ".section .altinstructions,\"a\"\n" " .long 1b - .\n" @@ -453,7 +453,7 @@ static __always_inline __pure bool _static_cpu_has_safe(u16 bit) * have. Thus, we force the jump to the widest, 4-byte, signed relative * offset even though the last would often fit in less bytes. */ - asm goto("1: .byte 0xe9\n .long %l[t_dynamic] - 2f\n" + asm_volatile_goto("1: .byte 0xe9\n .long %l[t_dynamic] - 2f\n" "2:\n" ".section .altinstructions,\"a\"\n" " .long 1b - .\n" /* src offset */ diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h index 64507f35800c..6a2cefb4395a 100644 --- a/arch/x86/include/asm/jump_label.h +++ b/arch/x86/include/asm/jump_label.h @@ -18,7 +18,7 @@ static __always_inline bool arch_static_branch(struct static_key *key) { - asm goto("1:" + asm_volatile_goto("1:" ".byte " __stringify(STATIC_KEY_INIT_NOP) "\n\t" ".pushsection __jump_table, \"aw\" \n\t" _ASM_ALIGN "\n\t" diff --git a/arch/x86/include/asm/local.h b/arch/x86/include/asm/local.h index 2d89e3980cbd..5b23e605e707 100644 --- a/arch/x86/include/asm/local.h +++ b/arch/x86/include/asm/local.h @@ -52,12 +52,7 @@ static inline void local_sub(long i, local_t *l) */ static inline int local_sub_and_test(long i, local_t *l) { - unsigned char c; - - asm volatile(_ASM_SUB "%2,%0; sete %1" - : "+m" (l->a.counter), "=qm" (c) - : "ir" (i) : "memory"); - return c; + GEN_BINARY_RMWcc(_ASM_SUB, l->a.counter, i, "%0", "e"); } /** @@ -70,12 +65,7 @@ static inline int local_sub_and_test(long i, local_t *l) */ static inline int local_dec_and_test(local_t *l) { - unsigned char c; - - asm volatile(_ASM_DEC "%0; sete %1" - : "+m" (l->a.counter), "=qm" (c) - : : "memory"); - return c != 0; + GEN_UNARY_RMWcc(_ASM_DEC, l->a.counter, "%0", "e"); } /** @@ -88,12 +78,7 @@ static inline int local_dec_and_test(local_t *l) */ static inline int local_inc_and_test(local_t *l) { - unsigned char c; - - asm volatile(_ASM_INC "%0; sete %1" - : "+m" (l->a.counter), "=qm" (c) - : : "memory"); - return c != 0; + GEN_UNARY_RMWcc(_ASM_INC, l->a.counter, "%0", "e"); } /** @@ -107,12 +92,7 @@ static inline int local_inc_and_test(local_t *l) */ static inline int local_add_negative(long i, local_t *l) { - unsigned char c; - - asm volatile(_ASM_ADD "%2,%0; sets %1" - : "+m" (l->a.counter), "=qm" (c) - : "ir" (i) : "memory"); - return c; + GEN_BINARY_RMWcc(_ASM_ADD, l->a.counter, i, "%0", "s"); } /** diff --git a/arch/x86/include/asm/mutex_64.h b/arch/x86/include/asm/mutex_64.h index e7e6751648ed..07537a44216e 100644 --- a/arch/x86/include/asm/mutex_64.h +++ b/arch/x86/include/asm/mutex_64.h @@ -20,7 +20,7 @@ static inline void __mutex_fastpath_lock(atomic_t *v, void (*fail_fn)(atomic_t *)) { - asm volatile goto(LOCK_PREFIX " decl %0\n" + asm_volatile_goto(LOCK_PREFIX " decl %0\n" " jns %l[exit]\n" : : "m" (v->counter) : "memory", "cc" @@ -75,7 +75,7 @@ static inline int __mutex_fastpath_lock_retval(atomic_t *count) static inline void __mutex_fastpath_unlock(atomic_t *v, void (*fail_fn)(atomic_t *)) { - asm volatile goto(LOCK_PREFIX " incl %0\n" + asm_volatile_goto(LOCK_PREFIX " incl %0\n" " jg %l[exit]\n" : : "m" (v->counter) : "memory", "cc" diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index 0da5200ee79d..b3e18f800302 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -128,7 +128,8 @@ do { \ do { \ typedef typeof(var) pao_T__; \ const int pao_ID__ = (__builtin_constant_p(val) && \ - ((val) == 1 || (val) == -1)) ? (val) : 0; \ + ((val) == 1 || (val) == -1)) ? \ + (int)(val) : 0; \ if (0) { \ pao_T__ pao_tmp__; \ pao_tmp__ = (val); \ diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h new file mode 100644 index 000000000000..8729723636fd --- /dev/null +++ b/arch/x86/include/asm/preempt.h @@ -0,0 +1,100 @@ +#ifndef __ASM_PREEMPT_H +#define __ASM_PREEMPT_H + +#include <asm/rmwcc.h> +#include <asm/percpu.h> +#include <linux/thread_info.h> + +DECLARE_PER_CPU(int, __preempt_count); + +/* + * We mask the PREEMPT_NEED_RESCHED bit so as not to confuse all current users + * that think a non-zero value indicates we cannot preempt. + */ +static __always_inline int preempt_count(void) +{ + return __this_cpu_read_4(__preempt_count) & ~PREEMPT_NEED_RESCHED; +} + +static __always_inline void preempt_count_set(int pc) +{ + __this_cpu_write_4(__preempt_count, pc); +} + +/* + * must be macros to avoid header recursion hell + */ +#define task_preempt_count(p) \ + (task_thread_info(p)->saved_preempt_count & ~PREEMPT_NEED_RESCHED) + +#define init_task_preempt_count(p) do { \ + task_thread_info(p)->saved_preempt_count = PREEMPT_DISABLED; \ +} while (0) + +#define init_idle_preempt_count(p, cpu) do { \ + task_thread_info(p)->saved_preempt_count = PREEMPT_ENABLED; \ + per_cpu(__preempt_count, (cpu)) = PREEMPT_ENABLED; \ +} while (0) + +/* + * We fold the NEED_RESCHED bit into the preempt count such that + * preempt_enable() can decrement and test for needing to reschedule with a + * single instruction. + * + * We invert the actual bit, so that when the decrement hits 0 we know we both + * need to resched (the bit is cleared) and can resched (no preempt count). + */ + +static __always_inline void set_preempt_need_resched(void) +{ + __this_cpu_and_4(__preempt_count, ~PREEMPT_NEED_RESCHED); +} + +static __always_inline void clear_preempt_need_resched(void) +{ + __this_cpu_or_4(__preempt_count, PREEMPT_NEED_RESCHED); +} + +static __always_inline bool test_preempt_need_resched(void) +{ + return !(__this_cpu_read_4(__preempt_count) & PREEMPT_NEED_RESCHED); +} + +/* + * The various preempt_count add/sub methods + */ + +static __always_inline void __preempt_count_add(int val) +{ + __this_cpu_add_4(__preempt_count, val); +} + +static __always_inline void __preempt_count_sub(int val) +{ + __this_cpu_add_4(__preempt_count, -val); +} + +static __always_inline bool __preempt_count_dec_and_test(void) +{ + GEN_UNARY_RMWcc("decl", __preempt_count, __percpu_arg(0), "e"); +} + +/* + * Returns true when we need to resched and can (barring IRQ state). + */ +static __always_inline bool should_resched(void) +{ + return unlikely(!__this_cpu_read_4(__preempt_count)); +} + +#ifdef CONFIG_PREEMPT + extern asmlinkage void ___preempt_schedule(void); +# define __preempt_schedule() asm ("call ___preempt_schedule") + extern asmlinkage void preempt_schedule(void); +# ifdef CONFIG_CONTEXT_TRACKING + extern asmlinkage void ___preempt_schedule_context(void); +# define __preempt_schedule_context() asm ("call ___preempt_schedule_context") +# endif +#endif + +#endif /* __ASM_PREEMPT_H */ diff --git a/arch/x86/include/asm/rmwcc.h b/arch/x86/include/asm/rmwcc.h new file mode 100644 index 000000000000..1ff990f1de8e --- /dev/null +++ b/arch/x86/include/asm/rmwcc.h @@ -0,0 +1,41 @@ +#ifndef _ASM_X86_RMWcc +#define _ASM_X86_RMWcc + +#ifdef CC_HAVE_ASM_GOTO + +#define __GEN_RMWcc(fullop, var, cc, ...) \ +do { \ + asm_volatile_goto (fullop "; j" cc " %l[cc_label]" \ + : : "m" (var), ## __VA_ARGS__ \ + : "memory" : cc_label); \ + return 0; \ +cc_label: \ + return 1; \ +} while (0) + +#define GEN_UNARY_RMWcc(op, var, arg0, cc) \ + __GEN_RMWcc(op " " arg0, var, cc) + +#define GEN_BINARY_RMWcc(op, var, val, arg0, cc) \ + __GEN_RMWcc(op " %1, " arg0, var, cc, "er" (val)) + +#else /* !CC_HAVE_ASM_GOTO */ + +#define __GEN_RMWcc(fullop, var, cc, ...) \ +do { \ + char c; \ + asm volatile (fullop "; set" cc " %1" \ + : "+m" (var), "=qm" (c) \ + : __VA_ARGS__ : "memory"); \ + return c != 0; \ +} while (0) + +#define GEN_UNARY_RMWcc(op, var, arg0, cc) \ + __GEN_RMWcc(op " " arg0, var, cc) + +#define GEN_BINARY_RMWcc(op, var, val, arg0, cc) \ + __GEN_RMWcc(op " %2, " arg0, var, cc, "er" (val)) + +#endif /* CC_HAVE_ASM_GOTO */ + +#endif /* _ASM_X86_RMWcc */ diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 27811190cbd7..c46a46be1ec6 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -28,8 +28,7 @@ struct thread_info { __u32 flags; /* low level flags */ __u32 status; /* thread synchronous flags */ __u32 cpu; /* current CPU */ - int preempt_count; /* 0 => preemptable, - <0 => BUG */ + int saved_preempt_count; mm_segment_t addr_limit; struct restart_block restart_block; void __user *sysenter_return; @@ -49,7 +48,7 @@ struct thread_info { .exec_domain = &default_exec_domain, \ .flags = 0, \ .cpu = 0, \ - .preempt_count = INIT_PREEMPT_COUNT, \ + .saved_preempt_count = INIT_PREEMPT_COUNT, \ .addr_limit = KERNEL_DS, \ .restart_block = { \ .fn = do_no_restart_syscall, \ diff --git a/arch/x86/include/asm/uprobes.h b/arch/x86/include/asm/uprobes.h index 6e5197910fd8..3087ea9c5f2e 100644 --- a/arch/x86/include/asm/uprobes.h +++ b/arch/x86/include/asm/uprobes.h @@ -35,7 +35,10 @@ typedef u8 uprobe_opcode_t; struct arch_uprobe { u16 fixups; - u8 insn[MAX_UINSN_BYTES]; + union { + u8 insn[MAX_UINSN_BYTES]; + u8 ixol[MAX_UINSN_BYTES]; + }; #ifdef CONFIG_X86_64 unsigned long rip_rela_target_address; #endif @@ -49,11 +52,4 @@ struct arch_uprobe_task { unsigned int saved_tf; }; -extern int arch_uprobe_analyze_insn(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long addr); -extern int arch_uprobe_pre_xol(struct arch_uprobe *aup, struct pt_regs *regs); -extern int arch_uprobe_post_xol(struct arch_uprobe *aup, struct pt_regs *regs); -extern bool arch_uprobe_xol_was_trapped(struct task_struct *tsk); -extern int arch_uprobe_exception_notify(struct notifier_block *self, unsigned long val, void *data); -extern void arch_uprobe_abort_xol(struct arch_uprobe *aup, struct pt_regs *regs); -extern unsigned long arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs *regs); #endif /* _ASM_UPROBES_H */ diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index a5408b965c9d..9b0a34e2cd79 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -36,6 +36,8 @@ obj-y += tsc.o io_delay.o rtc.o obj-y += pci-iommu_table.o obj-y += resource.o +obj-$(CONFIG_PREEMPT) += preempt.o + obj-y += process.o obj-y += i387.o xsave.o obj-y += ptrace.o diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 1191ac1c9d25..a419814cea57 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -113,7 +113,7 @@ static int __init early_get_pnodeid(void) break; case UV3_HUB_PART_NUMBER: case UV3_HUB_PART_NUMBER_X: - uv_min_hub_revision_id += UV3_HUB_REVISION_BASE - 1; + uv_min_hub_revision_id += UV3_HUB_REVISION_BASE; break; } diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index 28610822fb3c..9f6b9341950f 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -32,7 +32,6 @@ void common(void) { OFFSET(TI_flags, thread_info, flags); OFFSET(TI_status, thread_info, status); OFFSET(TI_addr_limit, thread_info, addr_limit); - OFFSET(TI_preempt_count, thread_info, preempt_count); BLANK(); OFFSET(crypto_tfm_ctx_offset, crypto_tfm, __crt_ctx); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 2793d1f095a2..5223fe6dec7b 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1095,6 +1095,9 @@ DEFINE_PER_CPU(char *, irq_stack_ptr) = DEFINE_PER_CPU(unsigned int, irq_count) __visible = -1; +DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT; +EXPORT_PER_CPU_SYMBOL(__preempt_count); + DEFINE_PER_CPU(struct task_struct *, fpu_owner_task); /* @@ -1169,6 +1172,8 @@ void debug_stack_reset(void) DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task; EXPORT_PER_CPU_SYMBOL(current_task); +DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT; +EXPORT_PER_CPU_SYMBOL(__preempt_count); DEFINE_PER_CPU(struct task_struct *, fpu_owner_task); #ifdef CONFIG_CC_STACKPROTECTOR diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 897783b3302a..8e132931614d 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -1276,16 +1276,16 @@ void perf_events_lapic_init(void) static int __kprobes perf_event_nmi_handler(unsigned int cmd, struct pt_regs *regs) { - int ret; u64 start_clock; u64 finish_clock; + int ret; if (!atomic_read(&active_events)) return NMI_DONE; - start_clock = local_clock(); + start_clock = sched_clock(); ret = x86_pmu.handle_irq(regs); - finish_clock = local_clock(); + finish_clock = sched_clock(); perf_sample_event_took(finish_clock - start_clock); @@ -1888,10 +1888,7 @@ void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now) userpg->cap_user_rdpmc = x86_pmu.attr_rdpmc; userpg->pmc_width = x86_pmu.cntval_bits; - if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) - return; - - if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC)) + if (!sched_clock_stable) return; userpg->cap_user_time = 1; @@ -1899,10 +1896,8 @@ void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now) userpg->time_shift = CYC2NS_SCALE_FACTOR; userpg->time_offset = this_cpu_read(cyc2ns_offset) - now; - if (sched_clock_stable && !check_tsc_disabled()) { - userpg->cap_user_time_zero = 1; - userpg->time_zero = this_cpu_read(cyc2ns_offset); - } + userpg->cap_user_time_zero = 1; + userpg->time_zero = this_cpu_read(cyc2ns_offset); } /* @@ -1994,7 +1989,7 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry) frame.return_address = 0; bytes = copy_from_user_nmi(&frame, fp, sizeof(frame)); - if (bytes != sizeof(frame)) + if (bytes != 0) break; if (!valid_user_frame(fp, sizeof(frame))) @@ -2046,7 +2041,7 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs) frame.return_address = 0; bytes = copy_from_user_nmi(&frame, fp, sizeof(frame)); - if (bytes != sizeof(frame)) + if (bytes != 0) break; if (!valid_user_frame(fp, sizeof(frame))) diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index cc16faae0538..fd00bb29425d 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -164,6 +164,11 @@ struct cpu_hw_events { struct perf_guest_switch_msr guest_switch_msrs[X86_PMC_IDX_MAX]; /* + * Intel checkpoint mask + */ + u64 intel_cp_status; + + /* * manage shared (per-core, per-cpu) registers * used on Intel NHM/WSM/SNB */ @@ -440,6 +445,7 @@ struct x86_pmu { int lbr_nr; /* hardware stack size */ u64 lbr_sel_mask; /* LBR_SELECT valid bits */ const int *lbr_sel_map; /* lbr_select mappings */ + bool lbr_double_abort; /* duplicated lbr aborts */ /* * Extra registers for events diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index f31a1655d1ff..0fa4f242f050 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -190,9 +190,9 @@ static struct extra_reg intel_snbep_extra_regs[] __read_mostly = { EVENT_EXTRA_END }; -EVENT_ATTR_STR(mem-loads, mem_ld_nhm, "event=0x0b,umask=0x10,ldlat=3"); -EVENT_ATTR_STR(mem-loads, mem_ld_snb, "event=0xcd,umask=0x1,ldlat=3"); -EVENT_ATTR_STR(mem-stores, mem_st_snb, "event=0xcd,umask=0x2"); +EVENT_ATTR_STR(mem-loads, mem_ld_nhm, "event=0x0b,umask=0x10,ldlat=3"); +EVENT_ATTR_STR(mem-loads, mem_ld_snb, "event=0xcd,umask=0x1,ldlat=3"); +EVENT_ATTR_STR(mem-stores, mem_st_snb, "event=0xcd,umask=0x2"); struct attribute *nhm_events_attrs[] = { EVENT_PTR(mem_ld_nhm), @@ -1184,6 +1184,11 @@ static void intel_pmu_disable_fixed(struct hw_perf_event *hwc) wrmsrl(hwc->config_base, ctrl_val); } +static inline bool event_is_checkpointed(struct perf_event *event) +{ + return (event->hw.config & HSW_IN_TX_CHECKPOINTED) != 0; +} + static void intel_pmu_disable_event(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; @@ -1197,6 +1202,7 @@ static void intel_pmu_disable_event(struct perf_event *event) cpuc->intel_ctrl_guest_mask &= ~(1ull << hwc->idx); cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx); + cpuc->intel_cp_status &= ~(1ull << hwc->idx); /* * must disable before any actual event @@ -1271,6 +1277,9 @@ static void intel_pmu_enable_event(struct perf_event *event) if (event->attr.exclude_guest) cpuc->intel_ctrl_host_mask |= (1ull << hwc->idx); + if (unlikely(event_is_checkpointed(event))) + cpuc->intel_cp_status |= (1ull << hwc->idx); + if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) { intel_pmu_enable_fixed(hwc); return; @@ -1289,6 +1298,17 @@ static void intel_pmu_enable_event(struct perf_event *event) int intel_pmu_save_and_restart(struct perf_event *event) { x86_perf_event_update(event); + /* + * For a checkpointed counter always reset back to 0. This + * avoids a situation where the counter overflows, aborts the + * transaction and is then set back to shortly before the + * overflow, and overflows and aborts again. + */ + if (unlikely(event_is_checkpointed(event))) { + /* No race with NMIs because the counter should not be armed */ + wrmsrl(event->hw.event_base, 0); + local64_set(&event->hw.prev_count, 0); + } return x86_perf_event_set_period(event); } @@ -1372,6 +1392,13 @@ again: x86_pmu.drain_pebs(regs); } + /* + * Checkpointed counters can lead to 'spurious' PMIs because the + * rollback caused by the PMI will have cleared the overflow status + * bit. Therefore always force probe these counters. + */ + status |= cpuc->intel_cp_status; + for_each_set_bit(bit, (unsigned long *)&status, X86_PMC_IDX_MAX) { struct perf_event *event = cpuc->events[bit]; @@ -1837,6 +1864,20 @@ static int hsw_hw_config(struct perf_event *event) event->attr.precise_ip > 0)) return -EOPNOTSUPP; + if (event_is_checkpointed(event)) { + /* + * Sampling of checkpointed events can cause situations where + * the CPU constantly aborts because of a overflow, which is + * then checkpointed back and ignored. Forbid checkpointing + * for sampling. + * + * But still allow a long sampling period, so that perf stat + * from KVM works. + */ + if (event->attr.sample_period > 0 && + event->attr.sample_period < 0x7fffffff) + return -EOPNOTSUPP; + } return 0; } @@ -2182,10 +2223,36 @@ static __init void intel_nehalem_quirk(void) } } -EVENT_ATTR_STR(mem-loads, mem_ld_hsw, "event=0xcd,umask=0x1,ldlat=3"); -EVENT_ATTR_STR(mem-stores, mem_st_hsw, "event=0xd0,umask=0x82") +EVENT_ATTR_STR(mem-loads, mem_ld_hsw, "event=0xcd,umask=0x1,ldlat=3"); +EVENT_ATTR_STR(mem-stores, mem_st_hsw, "event=0xd0,umask=0x82") + +/* Haswell special events */ +EVENT_ATTR_STR(tx-start, tx_start, "event=0xc9,umask=0x1"); +EVENT_ATTR_STR(tx-commit, tx_commit, "event=0xc9,umask=0x2"); +EVENT_ATTR_STR(tx-abort, tx_abort, "event=0xc9,umask=0x4"); +EVENT_ATTR_STR(tx-capacity, tx_capacity, "event=0x54,umask=0x2"); +EVENT_ATTR_STR(tx-conflict, tx_conflict, "event=0x54,umask=0x1"); +EVENT_ATTR_STR(el-start, el_start, "event=0xc8,umask=0x1"); +EVENT_ATTR_STR(el-commit, el_commit, "event=0xc8,umask=0x2"); +EVENT_ATTR_STR(el-abort, el_abort, "event=0xc8,umask=0x4"); +EVENT_ATTR_STR(el-capacity, el_capacity, "event=0x54,umask=0x2"); +EVENT_ATTR_STR(el-conflict, el_conflict, "event=0x54,umask=0x1"); +EVENT_ATTR_STR(cycles-t, cycles_t, "event=0x3c,in_tx=1"); +EVENT_ATTR_STR(cycles-ct, cycles_ct, "event=0x3c,in_tx=1,in_tx_cp=1"); static struct attribute *hsw_events_attrs[] = { + EVENT_PTR(tx_start), + EVENT_PTR(tx_commit), + EVENT_PTR(tx_abort), + EVENT_PTR(tx_capacity), + EVENT_PTR(tx_conflict), + EVENT_PTR(el_start), + EVENT_PTR(el_commit), + EVENT_PTR(el_abort), + EVENT_PTR(el_capacity), + EVENT_PTR(el_conflict), + EVENT_PTR(cycles_t), + EVENT_PTR(cycles_ct), EVENT_PTR(mem_ld_hsw), EVENT_PTR(mem_st_hsw), NULL @@ -2452,6 +2519,7 @@ __init int intel_pmu_init(void) x86_pmu.hw_config = hsw_hw_config; x86_pmu.get_event_constraints = hsw_get_event_constraints; x86_pmu.cpu_events = hsw_events_attrs; + x86_pmu.lbr_double_abort = true; pr_cont("Haswell events, "); break; diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index ab3ba1c1b7dd..ae96cfa5eddd 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -12,6 +12,7 @@ #define BTS_BUFFER_SIZE (PAGE_SIZE << 4) #define PEBS_BUFFER_SIZE PAGE_SIZE +#define PEBS_FIXUP_SIZE PAGE_SIZE /* * pebs_record_32 for p4 and core not supported @@ -182,18 +183,32 @@ struct pebs_record_nhm { * Same as pebs_record_nhm, with two additional fields. */ struct pebs_record_hsw { - struct pebs_record_nhm nhm; - /* - * Real IP of the event. In the Intel documentation this - * is called eventingrip. - */ - u64 real_ip; - /* - * TSX tuning information field: abort cycles and abort flags. - */ - u64 tsx_tuning; + u64 flags, ip; + u64 ax, bx, cx, dx; + u64 si, di, bp, sp; + u64 r8, r9, r10, r11; + u64 r12, r13, r14, r15; + u64 status, dla, dse, lat; + u64 real_ip, tsx_tuning; +}; + +union hsw_tsx_tuning { + struct { + u32 cycles_last_block : 32, + hle_abort : 1, + rtm_abort : 1, + instruction_abort : 1, + non_instruction_abort : 1, + retry : 1, + data_conflict : 1, + capacity_writes : 1, + capacity_reads : 1; + }; + u64 value; }; +#define PEBS_HSW_TSX_FLAGS 0xff00000000ULL + void init_debug_store_on_cpu(int cpu) { struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds; @@ -214,12 +229,14 @@ void fini_debug_store_on_cpu(int cpu) wrmsr_on_cpu(cpu, MSR_IA32_DS_AREA, 0, 0); } +static DEFINE_PER_CPU(void *, insn_buffer); + static int alloc_pebs_buffer(int cpu) { struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds; int node = cpu_to_node(cpu); int max, thresh = 1; /* always use a single PEBS record */ - void *buffer; + void *buffer, *ibuffer; if (!x86_pmu.pebs) return 0; @@ -228,6 +245,19 @@ static int alloc_pebs_buffer(int cpu) if (unlikely(!buffer)) return -ENOMEM; + /* + * HSW+ already provides us the eventing ip; no need to allocate this + * buffer then. + */ + if (x86_pmu.intel_cap.pebs_format < 2) { + ibuffer = kzalloc_node(PEBS_FIXUP_SIZE, GFP_KERNEL, node); + if (!ibuffer) { + kfree(buffer); + return -ENOMEM; + } + per_cpu(insn_buffer, cpu) = ibuffer; + } + max = PEBS_BUFFER_SIZE / x86_pmu.pebs_record_size; ds->pebs_buffer_base = (u64)(unsigned long)buffer; @@ -248,6 +278,9 @@ static void release_pebs_buffer(int cpu) if (!ds || !x86_pmu.pebs) return; + kfree(per_cpu(insn_buffer, cpu)); + per_cpu(insn_buffer, cpu) = NULL; + kfree((void *)(unsigned long)ds->pebs_buffer_base); ds->pebs_buffer_base = 0; } @@ -715,6 +748,7 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs) unsigned long old_to, to = cpuc->lbr_entries[0].to; unsigned long ip = regs->ip; int is_64bit = 0; + void *kaddr; /* * We don't need to fixup if the PEBS assist is fault like @@ -738,7 +772,7 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs) * unsigned math, either ip is before the start (impossible) or * the basic block is larger than 1 page (sanity) */ - if ((ip - to) > PAGE_SIZE) + if ((ip - to) > PEBS_FIXUP_SIZE) return 0; /* @@ -749,29 +783,33 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs) return 1; } + if (!kernel_ip(ip)) { + int size, bytes; + u8 *buf = this_cpu_read(insn_buffer); + + size = ip - to; /* Must fit our buffer, see above */ + bytes = copy_from_user_nmi(buf, (void __user *)to, size); + if (bytes != 0) + return 0; + + kaddr = buf; + } else { + kaddr = (void *)to; + } + do { struct insn insn; - u8 buf[MAX_INSN_SIZE]; - void *kaddr; old_to = to; - if (!kernel_ip(ip)) { - int bytes, size = MAX_INSN_SIZE; - - bytes = copy_from_user_nmi(buf, (void __user *)to, size); - if (bytes != size) - return 0; - - kaddr = buf; - } else - kaddr = (void *)to; #ifdef CONFIG_X86_64 is_64bit = kernel_ip(to) || !test_thread_flag(TIF_IA32); #endif insn_init(&insn, kaddr, is_64bit); insn_get_length(&insn); + to += insn.length; + kaddr += insn.length; } while (to < ip); if (to == ip) { @@ -786,16 +824,34 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs) return 0; } +static inline u64 intel_hsw_weight(struct pebs_record_hsw *pebs) +{ + if (pebs->tsx_tuning) { + union hsw_tsx_tuning tsx = { .value = pebs->tsx_tuning }; + return tsx.cycles_last_block; + } + return 0; +} + +static inline u64 intel_hsw_transaction(struct pebs_record_hsw *pebs) +{ + u64 txn = (pebs->tsx_tuning & PEBS_HSW_TSX_FLAGS) >> 32; + + /* For RTM XABORTs also log the abort code from AX */ + if ((txn & PERF_TXN_TRANSACTION) && (pebs->ax & 1)) + txn |= ((pebs->ax >> 24) & 0xff) << PERF_TXN_ABORT_SHIFT; + return txn; +} + static void __intel_pmu_pebs_event(struct perf_event *event, struct pt_regs *iregs, void *__pebs) { /* - * We cast to pebs_record_nhm to get the load latency data - * if extra_reg MSR_PEBS_LD_LAT_THRESHOLD used + * We cast to the biggest pebs_record but are careful not to + * unconditionally access the 'extra' entries. */ struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); - struct pebs_record_nhm *pebs = __pebs; - struct pebs_record_hsw *pebs_hsw = __pebs; + struct pebs_record_hsw *pebs = __pebs; struct perf_sample_data data; struct pt_regs regs; u64 sample_type; @@ -854,7 +910,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event, regs.sp = pebs->sp; if (event->attr.precise_ip > 1 && x86_pmu.intel_cap.pebs_format >= 2) { - regs.ip = pebs_hsw->real_ip; + regs.ip = pebs->real_ip; regs.flags |= PERF_EFLAGS_EXACT; } else if (event->attr.precise_ip > 1 && intel_pmu_pebs_fixup_ip(®s)) regs.flags |= PERF_EFLAGS_EXACT; @@ -862,9 +918,18 @@ static void __intel_pmu_pebs_event(struct perf_event *event, regs.flags &= ~PERF_EFLAGS_EXACT; if ((event->attr.sample_type & PERF_SAMPLE_ADDR) && - x86_pmu.intel_cap.pebs_format >= 1) + x86_pmu.intel_cap.pebs_format >= 1) data.addr = pebs->dla; + if (x86_pmu.intel_cap.pebs_format >= 2) { + /* Only set the TSX weight when no memory weight. */ + if ((event->attr.sample_type & PERF_SAMPLE_WEIGHT) && !fll) + data.weight = intel_hsw_weight(pebs); + + if (event->attr.sample_type & PERF_SAMPLE_TRANSACTION) + data.txn = intel_hsw_transaction(pebs); + } + if (has_branch_stack(event)) data.br_stack = &cpuc->lbr_stack; @@ -913,17 +978,34 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs) __intel_pmu_pebs_event(event, iregs, at); } -static void __intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, void *at, - void *top) +static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); struct debug_store *ds = cpuc->ds; struct perf_event *event = NULL; + void *at, *top; u64 status = 0; int bit; + if (!x86_pmu.pebs_active) + return; + + at = (struct pebs_record_nhm *)(unsigned long)ds->pebs_buffer_base; + top = (struct pebs_record_nhm *)(unsigned long)ds->pebs_index; + ds->pebs_index = ds->pebs_buffer_base; + if (unlikely(at > top)) + return; + + /* + * Should not happen, we program the threshold at 1 and do not + * set a reset value. + */ + WARN_ONCE(top - at > x86_pmu.max_pebs_events * x86_pmu.pebs_record_size, + "Unexpected number of pebs records %ld\n", + (long)(top - at) / x86_pmu.pebs_record_size); + for (; at < top; at += x86_pmu.pebs_record_size) { struct pebs_record_nhm *p = at; @@ -951,61 +1033,6 @@ static void __intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, void *at, } } -static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) -{ - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); - struct debug_store *ds = cpuc->ds; - struct pebs_record_nhm *at, *top; - int n; - - if (!x86_pmu.pebs_active) - return; - - at = (struct pebs_record_nhm *)(unsigned long)ds->pebs_buffer_base; - top = (struct pebs_record_nhm *)(unsigned long)ds->pebs_index; - - ds->pebs_index = ds->pebs_buffer_base; - - n = top - at; - if (n <= 0) - return; - - /* - * Should not happen, we program the threshold at 1 and do not - * set a reset value. - */ - WARN_ONCE(n > x86_pmu.max_pebs_events, - "Unexpected number of pebs records %d\n", n); - - return __intel_pmu_drain_pebs_nhm(iregs, at, top); -} - -static void intel_pmu_drain_pebs_hsw(struct pt_regs *iregs) -{ - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); - struct debug_store *ds = cpuc->ds; - struct pebs_record_hsw *at, *top; - int n; - - if (!x86_pmu.pebs_active) - return; - - at = (struct pebs_record_hsw *)(unsigned long)ds->pebs_buffer_base; - top = (struct pebs_record_hsw *)(unsigned long)ds->pebs_index; - - n = top - at; - if (n <= 0) - return; - /* - * Should not happen, we program the threshold at 1 and do not - * set a reset value. - */ - WARN_ONCE(n > x86_pmu.max_pebs_events, - "Unexpected number of pebs records %d\n", n); - - return __intel_pmu_drain_pebs_nhm(iregs, at, top); -} - /* * BTS, PEBS probe and setup */ @@ -1040,7 +1067,7 @@ void intel_ds_init(void) case 2: pr_cont("PEBS fmt2%c, ", pebs_type); x86_pmu.pebs_record_size = sizeof(struct pebs_record_hsw); - x86_pmu.drain_pebs = intel_pmu_drain_pebs_hsw; + x86_pmu.drain_pebs = intel_pmu_drain_pebs_nhm; break; default: diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c index d5be06a5005e..d82d155aca8c 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c +++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c @@ -284,6 +284,7 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) int lbr_format = x86_pmu.intel_cap.lbr_format; u64 tos = intel_pmu_lbr_tos(); int i; + int out = 0; for (i = 0; i < x86_pmu.lbr_nr; i++) { unsigned long lbr_idx = (tos - i) & mask; @@ -306,15 +307,27 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) } from = (u64)((((s64)from) << skip) >> skip); - cpuc->lbr_entries[i].from = from; - cpuc->lbr_entries[i].to = to; - cpuc->lbr_entries[i].mispred = mis; - cpuc->lbr_entries[i].predicted = pred; - cpuc->lbr_entries[i].in_tx = in_tx; - cpuc->lbr_entries[i].abort = abort; - cpuc->lbr_entries[i].reserved = 0; + /* + * Some CPUs report duplicated abort records, + * with the second entry not having an abort bit set. + * Skip them here. This loop runs backwards, + * so we need to undo the previous record. + * If the abort just happened outside the window + * the extra entry cannot be removed. + */ + if (abort && x86_pmu.lbr_double_abort && out > 0) + out--; + + cpuc->lbr_entries[out].from = from; + cpuc->lbr_entries[out].to = to; + cpuc->lbr_entries[out].mispred = mis; + cpuc->lbr_entries[out].predicted = pred; + cpuc->lbr_entries[out].in_tx = in_tx; + cpuc->lbr_entries[out].abort = abort; + cpuc->lbr_entries[out].reserved = 0; + out++; } - cpuc->lbr_stack.nr = i; + cpuc->lbr_stack.nr = out; } void intel_pmu_lbr_read(void) @@ -478,7 +491,7 @@ static int branch_type(unsigned long from, unsigned long to, int abort) /* may fail if text not present */ bytes = copy_from_user_nmi(buf, (void __user *)from, size); - if (bytes != size) + if (bytes != 0) return X86_BR_NONE; addr = buf; diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index 4118f9f68315..29c248799ced 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -997,6 +997,20 @@ static int snbep_pci2phy_map_init(int devid) } } + if (!err) { + /* + * For PCI bus with no UBOX device, find the next bus + * that has UBOX device and use its mapping. + */ + i = -1; + for (bus = 255; bus >= 0; bus--) { + if (pcibus_to_physid[bus] >= 0) + i = pcibus_to_physid[bus]; + else + pcibus_to_physid[bus] = i; + } + } + if (ubox_dev) pci_dev_put(ubox_dev); @@ -1099,6 +1113,24 @@ static struct attribute *ivt_uncore_qpi_formats_attr[] = { &format_attr_umask.attr, &format_attr_edge.attr, &format_attr_thresh8.attr, + &format_attr_match_rds.attr, + &format_attr_match_rnid30.attr, + &format_attr_match_rnid4.attr, + &format_attr_match_dnid.attr, + &format_attr_match_mc.attr, + &format_attr_match_opc.attr, + &format_attr_match_vnw.attr, + &format_attr_match0.attr, + &format_attr_match1.attr, + &format_attr_mask_rds.attr, + &format_attr_mask_rnid30.attr, + &format_attr_mask_rnid4.attr, + &format_attr_mask_dnid.attr, + &format_attr_mask_mc.attr, + &format_attr_mask_opc.attr, + &format_attr_mask_vnw.attr, + &format_attr_mask0.attr, + &format_attr_mask1.attr, NULL, }; @@ -1312,17 +1344,83 @@ static struct intel_uncore_type ivt_uncore_imc = { IVT_UNCORE_PCI_COMMON_INIT(), }; +/* registers in IRP boxes are not properly aligned */ +static unsigned ivt_uncore_irp_ctls[] = {0xd8, 0xdc, 0xe0, 0xe4}; +static unsigned ivt_uncore_irp_ctrs[] = {0xa0, 0xb0, 0xb8, 0xc0}; + +static void ivt_uncore_irp_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct pci_dev *pdev = box->pci_dev; + struct hw_perf_event *hwc = &event->hw; + + pci_write_config_dword(pdev, ivt_uncore_irp_ctls[hwc->idx], + hwc->config | SNBEP_PMON_CTL_EN); +} + +static void ivt_uncore_irp_disable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct pci_dev *pdev = box->pci_dev; + struct hw_perf_event *hwc = &event->hw; + + pci_write_config_dword(pdev, ivt_uncore_irp_ctls[hwc->idx], hwc->config); +} + +static u64 ivt_uncore_irp_read_counter(struct intel_uncore_box *box, struct perf_event *event) +{ + struct pci_dev *pdev = box->pci_dev; + struct hw_perf_event *hwc = &event->hw; + u64 count = 0; + + pci_read_config_dword(pdev, ivt_uncore_irp_ctrs[hwc->idx], (u32 *)&count); + pci_read_config_dword(pdev, ivt_uncore_irp_ctrs[hwc->idx] + 4, (u32 *)&count + 1); + + return count; +} + +static struct intel_uncore_ops ivt_uncore_irp_ops = { + .init_box = ivt_uncore_pci_init_box, + .disable_box = snbep_uncore_pci_disable_box, + .enable_box = snbep_uncore_pci_enable_box, + .disable_event = ivt_uncore_irp_disable_event, + .enable_event = ivt_uncore_irp_enable_event, + .read_counter = ivt_uncore_irp_read_counter, +}; + +static struct intel_uncore_type ivt_uncore_irp = { + .name = "irp", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + .event_mask = IVT_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_PCI_PMON_BOX_CTL, + .ops = &ivt_uncore_irp_ops, + .format_group = &ivt_uncore_format_group, +}; + +static struct intel_uncore_ops ivt_uncore_qpi_ops = { + .init_box = ivt_uncore_pci_init_box, + .disable_box = snbep_uncore_pci_disable_box, + .enable_box = snbep_uncore_pci_enable_box, + .disable_event = snbep_uncore_pci_disable_event, + .enable_event = snbep_qpi_enable_event, + .read_counter = snbep_uncore_pci_read_counter, + .hw_config = snbep_qpi_hw_config, + .get_constraint = uncore_get_constraint, + .put_constraint = uncore_put_constraint, +}; + static struct intel_uncore_type ivt_uncore_qpi = { - .name = "qpi", - .num_counters = 4, - .num_boxes = 3, - .perf_ctr_bits = 48, - .perf_ctr = SNBEP_PCI_PMON_CTR0, - .event_ctl = SNBEP_PCI_PMON_CTL0, - .event_mask = IVT_QPI_PCI_PMON_RAW_EVENT_MASK, - .box_ctl = SNBEP_PCI_PMON_BOX_CTL, - .ops = &ivt_uncore_pci_ops, - .format_group = &ivt_uncore_qpi_format_group, + .name = "qpi", + .num_counters = 4, + .num_boxes = 3, + .perf_ctr_bits = 48, + .perf_ctr = SNBEP_PCI_PMON_CTR0, + .event_ctl = SNBEP_PCI_PMON_CTL0, + .event_mask = IVT_QPI_PCI_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_PCI_PMON_BOX_CTL, + .num_shared_regs = 1, + .ops = &ivt_uncore_qpi_ops, + .format_group = &ivt_uncore_qpi_format_group, }; static struct intel_uncore_type ivt_uncore_r2pcie = { @@ -1346,6 +1444,7 @@ static struct intel_uncore_type ivt_uncore_r3qpi = { enum { IVT_PCI_UNCORE_HA, IVT_PCI_UNCORE_IMC, + IVT_PCI_UNCORE_IRP, IVT_PCI_UNCORE_QPI, IVT_PCI_UNCORE_R2PCIE, IVT_PCI_UNCORE_R3QPI, @@ -1354,6 +1453,7 @@ enum { static struct intel_uncore_type *ivt_pci_uncores[] = { [IVT_PCI_UNCORE_HA] = &ivt_uncore_ha, [IVT_PCI_UNCORE_IMC] = &ivt_uncore_imc, + [IVT_PCI_UNCORE_IRP] = &ivt_uncore_irp, [IVT_PCI_UNCORE_QPI] = &ivt_uncore_qpi, [IVT_PCI_UNCORE_R2PCIE] = &ivt_uncore_r2pcie, [IVT_PCI_UNCORE_R3QPI] = &ivt_uncore_r3qpi, @@ -1401,6 +1501,10 @@ static DEFINE_PCI_DEVICE_TABLE(ivt_uncore_pci_ids) = { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef1), .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 7), }, + { /* IRP */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe39), + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IRP, 0), + }, { /* QPI0 Port 0 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe32), .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_QPI, 0), @@ -1429,6 +1533,16 @@ static DEFINE_PCI_DEVICE_TABLE(ivt_uncore_pci_ids) = { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe3e), .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R3QPI, 2), }, + { /* QPI Port 0 filter */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe86), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, + SNBEP_PCI_QPI_PORT0_FILTER), + }, + { /* QPI Port 0 filter */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe96), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, + SNBEP_PCI_QPI_PORT1_FILTER), + }, { /* end: all zeroes */ } }; diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index f0dcb0ceb6a2..fd1bc1b15e6d 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -362,12 +362,9 @@ END(ret_from_exception) #ifdef CONFIG_PREEMPT ENTRY(resume_kernel) DISABLE_INTERRUPTS(CLBR_ANY) - cmpl $0,TI_preempt_count(%ebp) # non-zero preempt_count ? - jnz restore_all need_resched: - movl TI_flags(%ebp), %ecx # need_resched set ? - testb $_TIF_NEED_RESCHED, %cl - jz restore_all + cmpl $0,PER_CPU_VAR(__preempt_count) + jnz restore_all testl $X86_EFLAGS_IF,PT_EFLAGS(%esp) # interrupts off (exception path) ? jz restore_all call preempt_schedule_irq diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index b077f4cc225a..603be7c70675 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -1103,10 +1103,8 @@ retint_signal: /* Returning to kernel space. Check if we need preemption */ /* rcx: threadinfo. interrupts off. */ ENTRY(retint_kernel) - cmpl $0,TI_preempt_count(%rcx) + cmpl $0,PER_CPU_VAR(__preempt_count) jnz retint_restore_args - bt $TIF_NEED_RESCHED,TI_flags(%rcx) - jnc retint_restore_args bt $9,EFLAGS-ARGOFFSET(%rsp) /* interrupts off? */ jnc retint_restore_args call preempt_schedule_irq @@ -1342,7 +1340,7 @@ bad_gs: .previous /* Call softirq on interrupt stack. Interrupts are off. */ -ENTRY(call_softirq) +ENTRY(do_softirq_own_stack) CFI_STARTPROC pushq_cfi %rbp CFI_REL_OFFSET rbp,0 @@ -1359,7 +1357,7 @@ ENTRY(call_softirq) decl PER_CPU_VAR(irq_count) ret CFI_ENDPROC -END(call_softirq) +END(do_softirq_own_stack) #ifdef CONFIG_XEN zeroentry xen_hypervisor_callback xen_do_hypervisor_callback diff --git a/arch/x86/kernel/i386_ksyms_32.c b/arch/x86/kernel/i386_ksyms_32.c index 0fa69127209a..05fd74f537d6 100644 --- a/arch/x86/kernel/i386_ksyms_32.c +++ b/arch/x86/kernel/i386_ksyms_32.c @@ -37,3 +37,10 @@ EXPORT_SYMBOL(strstr); EXPORT_SYMBOL(csum_partial); EXPORT_SYMBOL(empty_zero_page); + +#ifdef CONFIG_PREEMPT +EXPORT_SYMBOL(___preempt_schedule); +#ifdef CONFIG_CONTEXT_TRACKING +EXPORT_SYMBOL(___preempt_schedule_context); +#endif +#endif diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c index 9a5c460404dc..2e977b5d61dd 100644 --- a/arch/x86/kernel/i8259.c +++ b/arch/x86/kernel/i8259.c @@ -312,8 +312,7 @@ static void init_8259A(int auto_eoi) */ outb_pic(0x11, PIC_MASTER_CMD); /* ICW1: select 8259A-1 init */ - /* ICW2: 8259A-1 IR0-7 mapped to 0x30-0x37 on x86-64, - to 0x20-0x27 on i386 */ + /* ICW2: 8259A-1 IR0-7 mapped to 0x30-0x37 */ outb_pic(IRQ0_VECTOR, PIC_MASTER_IMR); /* 8259A-1 (the master) has a slave on IR2 */ diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index 4186755f1d7c..d7fcbedc9c43 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -100,9 +100,6 @@ execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq) irqctx->tinfo.task = curctx->tinfo.task; irqctx->tinfo.previous_esp = current_stack_pointer; - /* Copy the preempt_count so that the [soft]irq checks work. */ - irqctx->tinfo.preempt_count = curctx->tinfo.preempt_count; - if (unlikely(overflow)) call_on_stack(print_stack_overflow, isp); @@ -131,7 +128,6 @@ void irq_ctx_init(int cpu) THREAD_SIZE_ORDER)); memset(&irqctx->tinfo, 0, sizeof(struct thread_info)); irqctx->tinfo.cpu = cpu; - irqctx->tinfo.preempt_count = HARDIRQ_OFFSET; irqctx->tinfo.addr_limit = MAKE_MM_SEG(0); per_cpu(hardirq_ctx, cpu) = irqctx; @@ -149,35 +145,21 @@ void irq_ctx_init(int cpu) cpu, per_cpu(hardirq_ctx, cpu), per_cpu(softirq_ctx, cpu)); } -asmlinkage void do_softirq(void) +void do_softirq_own_stack(void) { - unsigned long flags; struct thread_info *curctx; union irq_ctx *irqctx; u32 *isp; - if (in_interrupt()) - return; - - local_irq_save(flags); - - if (local_softirq_pending()) { - curctx = current_thread_info(); - irqctx = __this_cpu_read(softirq_ctx); - irqctx->tinfo.task = curctx->task; - irqctx->tinfo.previous_esp = current_stack_pointer; - - /* build the stack frame on the softirq stack */ - isp = (u32 *) ((char *)irqctx + sizeof(*irqctx)); + curctx = current_thread_info(); + irqctx = __this_cpu_read(softirq_ctx); + irqctx->tinfo.task = curctx->task; + irqctx->tinfo.previous_esp = current_stack_pointer; - call_on_stack(__do_softirq, isp); - /* - * Shouldn't happen, we returned above if in_interrupt(): - */ - WARN_ON_ONCE(softirq_count()); - } + /* build the stack frame on the softirq stack */ + isp = (u32 *) ((char *)irqctx + sizeof(*irqctx)); - local_irq_restore(flags); + call_on_stack(__do_softirq, isp); } bool handle_irq(unsigned irq, struct pt_regs *regs) diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c index d04d3ecded62..4d1c746892eb 100644 --- a/arch/x86/kernel/irq_64.c +++ b/arch/x86/kernel/irq_64.c @@ -87,24 +87,3 @@ bool handle_irq(unsigned irq, struct pt_regs *regs) generic_handle_irq_desc(irq, desc); return true; } - - -extern void call_softirq(void); - -asmlinkage void do_softirq(void) -{ - __u32 pending; - unsigned long flags; - - if (in_interrupt()) - return; - - local_irq_save(flags); - pending = local_softirq_pending(); - /* Switch to interrupt stack */ - if (pending) { - call_softirq(); - WARN_ON_ONCE(softirq_count()); - } - local_irq_restore(flags); -} diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 697b93af02dd..b2046e4d0b59 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -609,7 +609,7 @@ static struct dentry *d_kvm_debug; struct dentry *kvm_init_debugfs(void) { - d_kvm_debug = debugfs_create_dir("kvm", NULL); + d_kvm_debug = debugfs_create_dir("kvm-guest", NULL); if (!d_kvm_debug) printk(KERN_WARNING "Could not create 'kvm' debugfs directory\n"); @@ -775,11 +775,22 @@ void __init kvm_spinlock_init(void) if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT)) return; - printk(KERN_INFO "KVM setup paravirtual spinlock\n"); + pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(kvm_lock_spinning); + pv_lock_ops.unlock_kick = kvm_unlock_kick; +} + +static __init int kvm_spinlock_init_jump(void) +{ + if (!kvm_para_available()) + return 0; + if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT)) + return 0; static_key_slow_inc(¶virt_ticketlocks_enabled); + printk(KERN_INFO "KVM setup paravirtual spinlock\n"); - pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(kvm_lock_spinning); - pv_lock_ops.unlock_kick = kvm_unlock_kick; + return 0; } +early_initcall(kvm_spinlock_init_jump); + #endif /* CONFIG_PARAVIRT_SPINLOCKS */ diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index ba77ebc2c353..6fcb49ce50a1 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -113,10 +113,10 @@ static int __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2 u64 before, delta, whole_msecs; int remainder_ns, decimal_msecs, thishandled; - before = local_clock(); + before = sched_clock(); thishandled = a->handler(type, regs); handled += thishandled; - delta = local_clock() - before; + delta = sched_clock() - before; trace_nmi_handler(a->handler, (int)delta, thishandled); if (delta < nmi_longest_ns) diff --git a/arch/x86/kernel/preempt.S b/arch/x86/kernel/preempt.S new file mode 100644 index 000000000000..ca7f0d58a87d --- /dev/null +++ b/arch/x86/kernel/preempt.S @@ -0,0 +1,25 @@ + +#include <linux/linkage.h> +#include <asm/dwarf2.h> +#include <asm/asm.h> +#include <asm/calling.h> + +ENTRY(___preempt_schedule) + CFI_STARTPROC + SAVE_ALL + call preempt_schedule + RESTORE_ALL + ret + CFI_ENDPROC + +#ifdef CONFIG_CONTEXT_TRACKING + +ENTRY(___preempt_schedule_context) + CFI_STARTPROC + SAVE_ALL + call preempt_schedule_context + RESTORE_ALL + ret + CFI_ENDPROC + +#endif diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index c83516be1052..3fb8d95ab8b5 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -391,9 +391,9 @@ static void amd_e400_idle(void) * The switch back from broadcast mode needs to be * called with interrupts disabled. */ - local_irq_disable(); - clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu); - local_irq_enable(); + local_irq_disable(); + clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu); + local_irq_enable(); } else default_idle(); } diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 884f98f69354..c2ec1aa6d454 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -292,6 +292,14 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) set_iopl_mask(next->iopl); /* + * If it were not for PREEMPT_ACTIVE we could guarantee that the + * preempt_count of all tasks was equal here and this would not be + * needed. + */ + task_thread_info(prev_p)->saved_preempt_count = this_cpu_read(__preempt_count); + this_cpu_write(__preempt_count, task_thread_info(next_p)->saved_preempt_count); + + /* * Now maybe handle debug registers and/or IO bitmaps */ if (unlikely(task_thread_info(prev_p)->flags & _TIF_WORK_CTXSW_PREV || diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index bb1dc51bab05..45ab4d6fc8a7 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -363,6 +363,14 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) this_cpu_write(old_rsp, next->usersp); this_cpu_write(current_task, next_p); + /* + * If it were not for PREEMPT_ACTIVE we could guarantee that the + * preempt_count of all tasks was equal here and this would not be + * needed. + */ + task_thread_info(prev_p)->saved_preempt_count = this_cpu_read(__preempt_count); + this_cpu_write(__preempt_count, task_thread_info(next_p)->saved_preempt_count); + this_cpu_write(kernel_stack, (unsigned long)task_stack_page(next_p) + THREAD_SIZE - KERNEL_STACK_OFFSET); diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index e643e744e4d8..7e920bff99a3 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -326,6 +326,14 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E6320"), }, }, + { /* Handle problems with rebooting on the Latitude E5410. */ + .callback = set_pci_reboot, + .ident = "Dell Latitude E5410", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E5410"), + }, + }, { /* Handle problems with rebooting on the Latitude E5420. */ .callback = set_pci_reboot, .ident = "Dell Latitude E5420", diff --git a/arch/x86/kernel/sysfb_simplefb.c b/arch/x86/kernel/sysfb_simplefb.c index 22513e96b012..86179d409893 100644 --- a/arch/x86/kernel/sysfb_simplefb.c +++ b/arch/x86/kernel/sysfb_simplefb.c @@ -72,14 +72,14 @@ __init int create_simplefb(const struct screen_info *si, * the part that is occupied by the framebuffer */ len = mode->height * mode->stride; len = PAGE_ALIGN(len); - if (len > si->lfb_size << 16) { + if (len > (u64)si->lfb_size << 16) { printk(KERN_WARNING "sysfb: VRAM smaller than advertised\n"); return -EINVAL; } /* setup IORESOURCE_MEM as framebuffer memory */ memset(&res, 0, sizeof(res)); - res.flags = IORESOURCE_MEM; + res.flags = IORESOURCE_MEM | IORESOURCE_BUSY; res.name = simplefb_resname; res.start = si->lfb_base; res.end = si->lfb_base + len - 1; diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 8c8093b146ca..729aa779ff75 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -88,7 +88,7 @@ static inline void conditional_sti(struct pt_regs *regs) static inline void preempt_conditional_sti(struct pt_regs *regs) { - inc_preempt_count(); + preempt_count_inc(); if (regs->flags & X86_EFLAGS_IF) local_irq_enable(); } @@ -103,7 +103,7 @@ static inline void preempt_conditional_cli(struct pt_regs *regs) { if (regs->flags & X86_EFLAGS_IF) local_irq_disable(); - dec_preempt_count(); + preempt_count_dec(); } static int __kprobes diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c index b014d9414d08..040681928e9d 100644 --- a/arch/x86/kernel/x8664_ksyms_64.c +++ b/arch/x86/kernel/x8664_ksyms_64.c @@ -66,3 +66,10 @@ EXPORT_SYMBOL(empty_zero_page); #ifndef CONFIG_PARAVIRT EXPORT_SYMBOL(native_load_gs_index); #endif + +#ifdef CONFIG_PREEMPT +EXPORT_SYMBOL(___preempt_schedule); +#ifdef CONFIG_CONTEXT_TRACKING +EXPORT_SYMBOL(___preempt_schedule_context); +#endif +#endif diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index a1216de9ffda..2b2fce1b2009 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -3255,25 +3255,29 @@ static void vmx_decache_cr4_guest_bits(struct kvm_vcpu *vcpu) static void ept_load_pdptrs(struct kvm_vcpu *vcpu) { + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; + if (!test_bit(VCPU_EXREG_PDPTR, (unsigned long *)&vcpu->arch.regs_dirty)) return; if (is_paging(vcpu) && is_pae(vcpu) && !is_long_mode(vcpu)) { - vmcs_write64(GUEST_PDPTR0, vcpu->arch.mmu.pdptrs[0]); - vmcs_write64(GUEST_PDPTR1, vcpu->arch.mmu.pdptrs[1]); - vmcs_write64(GUEST_PDPTR2, vcpu->arch.mmu.pdptrs[2]); - vmcs_write64(GUEST_PDPTR3, vcpu->arch.mmu.pdptrs[3]); + vmcs_write64(GUEST_PDPTR0, mmu->pdptrs[0]); + vmcs_write64(GUEST_PDPTR1, mmu->pdptrs[1]); + vmcs_write64(GUEST_PDPTR2, mmu->pdptrs[2]); + vmcs_write64(GUEST_PDPTR3, mmu->pdptrs[3]); } } static void ept_save_pdptrs(struct kvm_vcpu *vcpu) { + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; + if (is_paging(vcpu) && is_pae(vcpu) && !is_long_mode(vcpu)) { - vcpu->arch.mmu.pdptrs[0] = vmcs_read64(GUEST_PDPTR0); - vcpu->arch.mmu.pdptrs[1] = vmcs_read64(GUEST_PDPTR1); - vcpu->arch.mmu.pdptrs[2] = vmcs_read64(GUEST_PDPTR2); - vcpu->arch.mmu.pdptrs[3] = vmcs_read64(GUEST_PDPTR3); + mmu->pdptrs[0] = vmcs_read64(GUEST_PDPTR0); + mmu->pdptrs[1] = vmcs_read64(GUEST_PDPTR1); + mmu->pdptrs[2] = vmcs_read64(GUEST_PDPTR2); + mmu->pdptrs[3] = vmcs_read64(GUEST_PDPTR3); } __set_bit(VCPU_EXREG_PDPTR, @@ -5345,7 +5349,9 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu) * There are errata that may cause this bit to not be set: * AAK134, BY25. */ - if (exit_qualification & INTR_INFO_UNBLOCK_NMI) + if (!(to_vmx(vcpu)->idt_vectoring_info & VECTORING_INFO_VALID_MASK) && + cpu_has_virtual_nmis() && + (exit_qualification & INTR_INFO_UNBLOCK_NMI)) vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, GUEST_INTR_STATE_NMI); gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS); @@ -7775,10 +7781,6 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) vmcs_write64(GUEST_PDPTR1, vmcs12->guest_pdptr1); vmcs_write64(GUEST_PDPTR2, vmcs12->guest_pdptr2); vmcs_write64(GUEST_PDPTR3, vmcs12->guest_pdptr3); - __clear_bit(VCPU_EXREG_PDPTR, - (unsigned long *)&vcpu->arch.regs_avail); - __clear_bit(VCPU_EXREG_PDPTR, - (unsigned long *)&vcpu->arch.regs_dirty); } kvm_register_write(vcpu, VCPU_REGS_RSP, vmcs12->guest_rsp); diff --git a/arch/x86/lib/usercopy.c b/arch/x86/lib/usercopy.c index 4f74d94c8d97..ddf9ecb53cc3 100644 --- a/arch/x86/lib/usercopy.c +++ b/arch/x86/lib/usercopy.c @@ -11,39 +11,26 @@ #include <linux/sched.h> /* - * best effort, GUP based copy_from_user() that is NMI-safe + * We rely on the nested NMI work to allow atomic faults from the NMI path; the + * nested NMI paths are careful to preserve CR2. */ unsigned long copy_from_user_nmi(void *to, const void __user *from, unsigned long n) { - unsigned long offset, addr = (unsigned long)from; - unsigned long size, len = 0; - struct page *page; - void *map; - int ret; + unsigned long ret; if (__range_not_ok(from, n, TASK_SIZE)) - return len; - - do { - ret = __get_user_pages_fast(addr, 1, 0, &page); - if (!ret) - break; - - offset = addr & (PAGE_SIZE - 1); - size = min(PAGE_SIZE - offset, n - len); - - map = kmap_atomic(page); - memcpy(to, map+offset, size); - kunmap_atomic(map); - put_page(page); - - len += size; - to += size; - addr += size; - - } while (len < n); - - return len; + return 0; + + /* + * Even though this function is typically called from NMI/IRQ context + * disable pagefaults so that its behaviour is consistent even when + * called form other contexts. + */ + pagefault_disable(); + ret = __copy_from_user_inatomic(to, from, n); + pagefault_enable(); + + return ret; } EXPORT_SYMBOL_GPL(copy_from_user_nmi); diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 3aaeffcfd67a..7a517bb41060 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -51,7 +51,7 @@ kmmio_fault(struct pt_regs *regs, unsigned long addr) return 0; } -static inline int __kprobes notify_page_fault(struct pt_regs *regs) +static inline int __kprobes kprobes_fault(struct pt_regs *regs) { int ret = 0; @@ -1048,7 +1048,7 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code) return; /* kprobes don't want to hook the spurious faults: */ - if (notify_page_fault(regs)) + if (kprobes_fault(regs)) return; /* * Don't take the mm semaphore here. If we fixup a prefetch @@ -1060,23 +1060,8 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code) } /* kprobes don't want to hook the spurious faults: */ - if (unlikely(notify_page_fault(regs))) + if (unlikely(kprobes_fault(regs))) return; - /* - * It's safe to allow irq's after cr2 has been saved and the - * vmalloc fault has been handled. - * - * User-mode registers count as a user access even for any - * potential system fault or CPU buglet: - */ - if (user_mode_vm(regs)) { - local_irq_enable(); - error_code |= PF_USER; - flags |= FAULT_FLAG_USER; - } else { - if (regs->flags & X86_EFLAGS_IF) - local_irq_enable(); - } if (unlikely(error_code & PF_RSVD)) pgtable_bad(regs, error_code, address); @@ -1088,8 +1073,6 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code) } } - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); - /* * If we're in an interrupt, have no user context or are running * in an atomic region then we must not take the fault: @@ -1099,6 +1082,24 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code) return; } + /* + * It's safe to allow irq's after cr2 has been saved and the + * vmalloc fault has been handled. + * + * User-mode registers count as a user access even for any + * potential system fault or CPU buglet: + */ + if (user_mode_vm(regs)) { + local_irq_enable(); + error_code |= PF_USER; + flags |= FAULT_FLAG_USER; + } else { + if (regs->flags & X86_EFLAGS_IF) + local_irq_enable(); + } + + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); + if (error_code & PF_WRITE) flags |= FAULT_FLAG_WRITE; diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 79c216aa0e2b..516593e1ce33 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -772,13 +772,21 @@ out: return; } +static void bpf_jit_free_deferred(struct work_struct *work) +{ + struct sk_filter *fp = container_of(work, struct sk_filter, work); + unsigned long addr = (unsigned long)fp->bpf_func & PAGE_MASK; + struct bpf_binary_header *header = (void *)addr; + + set_memory_rw(addr, header->pages); + module_free(NULL, header); + kfree(fp); +} + void bpf_jit_free(struct sk_filter *fp) { if (fp->bpf_func != sk_run_filter) { - unsigned long addr = (unsigned long)fp->bpf_func & PAGE_MASK; - struct bpf_binary_header *header = (void *)addr; - - set_memory_rw(addr, header->pages); - module_free(NULL, header); + INIT_WORK(&fp->work, bpf_jit_free_deferred); + schedule_work(&fp->work); } } diff --git a/arch/x86/oprofile/backtrace.c b/arch/x86/oprofile/backtrace.c index d6aa6e8315d1..5d04be5efb64 100644 --- a/arch/x86/oprofile/backtrace.c +++ b/arch/x86/oprofile/backtrace.c @@ -47,7 +47,7 @@ dump_user_backtrace_32(struct stack_frame_ia32 *head) unsigned long bytes; bytes = copy_from_user_nmi(bufhead, head, sizeof(bufhead)); - if (bytes != sizeof(bufhead)) + if (bytes != 0) return NULL; fp = (struct stack_frame_ia32 *) compat_ptr(bufhead[0].next_frame); @@ -93,7 +93,7 @@ static struct stack_frame *dump_user_backtrace(struct stack_frame *head) unsigned long bytes; bytes = copy_from_user_nmi(bufhead, head, sizeof(bufhead)); - if (bytes != sizeof(bufhead)) + if (bytes != 0) return NULL; oprofile_add_trace(bufhead[0].return_address); diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c index 5596c7bdd327..082e88129712 100644 --- a/arch/x86/pci/mmconfig-shared.c +++ b/arch/x86/pci/mmconfig-shared.c @@ -700,7 +700,7 @@ int pci_mmconfig_insert(struct device *dev, u16 seg, u8 start, u8 end, if (!(pci_probe & PCI_PROBE_MMCONF) || pci_mmcfg_arch_init_failed) return -ENODEV; - if (start > end || !addr) + if (start > end) return -EINVAL; mutex_lock(&pci_mmcfg_lock); @@ -716,6 +716,11 @@ int pci_mmconfig_insert(struct device *dev, u16 seg, u8 start, u8 end, return -EEXIST; } + if (!addr) { + mutex_unlock(&pci_mmcfg_lock); + return -EINVAL; + } + rc = -EBUSY; cfg = pci_mmconfig_alloc(seg, start, end, addr); if (cfg == NULL) { diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index d1e4777b4e75..31d04758b76f 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -278,6 +278,15 @@ static void __init xen_smp_prepare_boot_cpu(void) old memory can be recycled */ make_lowmem_page_readwrite(xen_initial_gdt); +#ifdef CONFIG_X86_32 + /* + * Xen starts us with XEN_FLAT_RING1_DS, but linux code + * expects __USER_DS + */ + loadsegment(ds, __USER_DS); + loadsegment(es, __USER_DS); +#endif + xen_filter_cpu_maps(); xen_setup_vcpu_info_placement(); } |