diff options
Diffstat (limited to 'arch/x86')
65 files changed, 1232 insertions, 662 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 226d5696e1d1..4e986e809861 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -127,7 +127,8 @@ config X86 select MODULES_USE_ELF_RELA if X86_64 select CLONE_BACKWARDS if X86_32 select ARCH_USE_BUILTIN_BSWAP - select ARCH_USE_QUEUE_RWLOCK + select ARCH_USE_QUEUED_SPINLOCKS + select ARCH_USE_QUEUED_RWLOCKS select OLD_SIGSUSPEND3 if X86_32 || IA32_EMULATION select OLD_SIGACTION if X86_32 select COMPAT_OLD_SIGACTION if IA32_EMULATION @@ -666,7 +667,7 @@ config PARAVIRT_DEBUG config PARAVIRT_SPINLOCKS bool "Paravirtualization layer for spinlocks" depends on PARAVIRT && SMP - select UNINLINE_SPIN_UNLOCK + select UNINLINE_SPIN_UNLOCK if !QUEUED_SPINLOCKS ---help--- Paravirtualized spinlocks allow a pvops backend to replace the spinlock implementation with something virtualization-friendly diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index 89dd0d78013a..805d25ca5f1d 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -2,15 +2,14 @@ #define BOOT_COMPRESSED_MISC_H /* - * we have to be careful, because no indirections are allowed here, and - * paravirt_ops is a kind of one. As it will only run in baremetal anyway, - * we just keep it from happening + * Special hack: we have to be careful, because no indirections are allowed here, + * and paravirt_ops is a kind of one. As it will only run in baremetal anyway, + * we just keep it from happening. (This list needs to be extended when new + * paravirt and debugging variants are added.) */ #undef CONFIG_PARAVIRT +#undef CONFIG_PARAVIRT_SPINLOCKS #undef CONFIG_KASAN -#ifdef CONFIG_X86_32 -#define _ASM_X86_DESC_H 1 -#endif #include <linux/linkage.h> #include <linux/screen_info.h> diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h index aaac3b2fb746..1a5da2e63aee 100644 --- a/arch/x86/include/asm/amd_nb.h +++ b/arch/x86/include/asm/amd_nb.h @@ -98,11 +98,22 @@ static inline u16 amd_get_node_id(struct pci_dev *pdev) return 0; } +static inline bool amd_gart_present(void) +{ + /* GART present only on Fam15h, upto model 0fh */ + if (boot_cpu_data.x86 == 0xf || boot_cpu_data.x86 == 0x10 || + (boot_cpu_data.x86 == 0x15 && boot_cpu_data.x86_model < 0x10)) + return true; + + return false; +} + #else #define amd_nb_num(x) 0 #define amd_nb_has_feature(x) false #define node_to_amd_nb(x) NULL +#define amd_gart_present(x) false #endif diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h index 959e45b81fe2..e51a8f803f55 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -35,12 +35,12 @@ #define smp_mb() mb() #define smp_rmb() dma_rmb() #define smp_wmb() barrier() -#define set_mb(var, value) do { (void)xchg(&var, value); } while (0) +#define smp_store_mb(var, value) do { (void)xchg(&var, value); } while (0) #else /* !SMP */ #define smp_mb() barrier() #define smp_rmb() barrier() #define smp_wmb() barrier() -#define set_mb(var, value) do { var = value; barrier(); } while (0) +#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); barrier(); } while (0) #endif /* SMP */ #define read_barrier_depends() do { } while (0) diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h index 99c105d78b7e..ad19841eddfe 100644 --- a/arch/x86/include/asm/cmpxchg.h +++ b/arch/x86/include/asm/cmpxchg.h @@ -4,8 +4,6 @@ #include <linux/compiler.h> #include <asm/alternative.h> /* Provides LOCK_PREFIX */ -#define __HAVE_ARCH_CMPXCHG 1 - /* * Non-existant functions to indicate usage errors at link time * (or compile-time if the compiler implements __compiletime_error(). diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h index 808dae63eeea..1f5b7287d1ad 100644 --- a/arch/x86/include/asm/dma-mapping.h +++ b/arch/x86/include/asm/dma-mapping.h @@ -127,50 +127,14 @@ static inline gfp_t dma_alloc_coherent_gfp_flags(struct device *dev, gfp_t gfp) #define dma_alloc_coherent(d,s,h,f) dma_alloc_attrs(d,s,h,f,NULL) -static inline void * +void * dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle, - gfp_t gfp, struct dma_attrs *attrs) -{ - struct dma_map_ops *ops = get_dma_ops(dev); - void *memory; - - gfp &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32); - - if (dma_alloc_from_coherent(dev, size, dma_handle, &memory)) - return memory; - - if (!dev) - dev = &x86_dma_fallback_dev; - - if (!is_device_dma_capable(dev)) - return NULL; - - if (!ops->alloc) - return NULL; - - memory = ops->alloc(dev, size, dma_handle, - dma_alloc_coherent_gfp_flags(dev, gfp), attrs); - debug_dma_alloc_coherent(dev, size, *dma_handle, memory); - - return memory; -} + gfp_t gfp, struct dma_attrs *attrs); #define dma_free_coherent(d,s,c,h) dma_free_attrs(d,s,c,h,NULL) -static inline void dma_free_attrs(struct device *dev, size_t size, - void *vaddr, dma_addr_t bus, - struct dma_attrs *attrs) -{ - struct dma_map_ops *ops = get_dma_ops(dev); - - WARN_ON(irqs_disabled()); /* for portability */ - - if (dma_release_from_coherent(dev, get_order(size), vaddr)) - return; - - debug_dma_free_coherent(dev, size, vaddr, bus); - if (ops->free) - ops->free(dev, size, vaddr, bus, attrs); -} +void dma_free_attrs(struct device *dev, size_t size, + void *vaddr, dma_addr_t bus, + struct dma_attrs *attrs); #endif diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 8957810ad7d1..d143bfad45d7 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -712,6 +712,31 @@ static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx, #if defined(CONFIG_SMP) && defined(CONFIG_PARAVIRT_SPINLOCKS) +#ifdef CONFIG_QUEUED_SPINLOCKS + +static __always_inline void pv_queued_spin_lock_slowpath(struct qspinlock *lock, + u32 val) +{ + PVOP_VCALL2(pv_lock_ops.queued_spin_lock_slowpath, lock, val); +} + +static __always_inline void pv_queued_spin_unlock(struct qspinlock *lock) +{ + PVOP_VCALLEE1(pv_lock_ops.queued_spin_unlock, lock); +} + +static __always_inline void pv_wait(u8 *ptr, u8 val) +{ + PVOP_VCALL2(pv_lock_ops.wait, ptr, val); +} + +static __always_inline void pv_kick(int cpu) +{ + PVOP_VCALL1(pv_lock_ops.kick, cpu); +} + +#else /* !CONFIG_QUEUED_SPINLOCKS */ + static __always_inline void __ticket_lock_spinning(struct arch_spinlock *lock, __ticket_t ticket) { @@ -724,7 +749,9 @@ static __always_inline void __ticket_unlock_kick(struct arch_spinlock *lock, PVOP_VCALL2(pv_lock_ops.unlock_kick, lock, ticket); } -#endif +#endif /* CONFIG_QUEUED_SPINLOCKS */ + +#endif /* SMP && PARAVIRT_SPINLOCKS */ #ifdef CONFIG_X86_32 #define PV_SAVE_REGS "pushl %ecx; pushl %edx;" diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index f7b0b5c112f2..8766c7c395c2 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -333,9 +333,19 @@ struct arch_spinlock; typedef u16 __ticket_t; #endif +struct qspinlock; + struct pv_lock_ops { +#ifdef CONFIG_QUEUED_SPINLOCKS + void (*queued_spin_lock_slowpath)(struct qspinlock *lock, u32 val); + struct paravirt_callee_save queued_spin_unlock; + + void (*wait)(u8 *ptr, u8 val); + void (*kick)(int cpu); +#else /* !CONFIG_QUEUED_SPINLOCKS */ struct paravirt_callee_save lock_spinning; void (*unlock_kick)(struct arch_spinlock *lock, __ticket_t ticket); +#endif /* !CONFIG_QUEUED_SPINLOCKS */ }; /* This contains all the paravirt structures: we get a convenient diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h index 8f3271842533..dca71714f860 100644 --- a/arch/x86/include/asm/preempt.h +++ b/arch/x86/include/asm/preempt.h @@ -99,11 +99,9 @@ static __always_inline bool should_resched(void) extern asmlinkage void ___preempt_schedule(void); # define __preempt_schedule() asm ("call ___preempt_schedule") extern asmlinkage void preempt_schedule(void); -# ifdef CONFIG_CONTEXT_TRACKING - extern asmlinkage void ___preempt_schedule_context(void); -# define __preempt_schedule_context() asm ("call ___preempt_schedule_context") - extern asmlinkage void preempt_schedule_context(void); -# endif + extern asmlinkage void ___preempt_schedule_notrace(void); +# define __preempt_schedule_notrace() asm ("call ___preempt_schedule_notrace") + extern asmlinkage void preempt_schedule_notrace(void); #endif #endif /* __ASM_PREEMPT_H */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 23ba6765b718..9aa52fd13a78 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -946,6 +946,7 @@ static inline int mpx_disable_management(struct task_struct *tsk) #endif /* CONFIG_X86_INTEL_MPX */ extern u16 amd_get_nb_id(int cpu); +extern u32 amd_get_nodes_per_socket(void); static inline uint32_t hypervisor_cpuid_base(const char *sig, uint32_t leaves) { diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index 19507ffa5d28..5fabf1362942 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -107,7 +107,7 @@ static inline unsigned long regs_return_value(struct pt_regs *regs) static inline int user_mode(struct pt_regs *regs) { #ifdef CONFIG_X86_32 - return (regs->cs & SEGMENT_RPL_MASK) == USER_RPL; + return ((regs->cs & SEGMENT_RPL_MASK) | (regs->flags & X86_VM_MASK)) >= USER_RPL; #else return !!(regs->cs & 3); #endif diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h new file mode 100644 index 000000000000..9d51fae1cba3 --- /dev/null +++ b/arch/x86/include/asm/qspinlock.h @@ -0,0 +1,57 @@ +#ifndef _ASM_X86_QSPINLOCK_H +#define _ASM_X86_QSPINLOCK_H + +#include <asm/cpufeature.h> +#include <asm-generic/qspinlock_types.h> +#include <asm/paravirt.h> + +#define queued_spin_unlock queued_spin_unlock +/** + * queued_spin_unlock - release a queued spinlock + * @lock : Pointer to queued spinlock structure + * + * A smp_store_release() on the least-significant byte. + */ +static inline void native_queued_spin_unlock(struct qspinlock *lock) +{ + smp_store_release((u8 *)lock, 0); +} + +#ifdef CONFIG_PARAVIRT_SPINLOCKS +extern void native_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val); +extern void __pv_init_lock_hash(void); +extern void __pv_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val); +extern void __raw_callee_save___pv_queued_spin_unlock(struct qspinlock *lock); + +static inline void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val) +{ + pv_queued_spin_lock_slowpath(lock, val); +} + +static inline void queued_spin_unlock(struct qspinlock *lock) +{ + pv_queued_spin_unlock(lock); +} +#else +static inline void queued_spin_unlock(struct qspinlock *lock) +{ + native_queued_spin_unlock(lock); +} +#endif + +#define virt_queued_spin_lock virt_queued_spin_lock + +static inline bool virt_queued_spin_lock(struct qspinlock *lock) +{ + if (!static_cpu_has(X86_FEATURE_HYPERVISOR)) + return false; + + while (atomic_cmpxchg(&lock->val, 0, _Q_LOCKED_VAL) != 0) + cpu_relax(); + + return true; +} + +#include <asm-generic/qspinlock.h> + +#endif /* _ASM_X86_QSPINLOCK_H */ diff --git a/arch/x86/include/asm/qspinlock_paravirt.h b/arch/x86/include/asm/qspinlock_paravirt.h new file mode 100644 index 000000000000..b002e711ba88 --- /dev/null +++ b/arch/x86/include/asm/qspinlock_paravirt.h @@ -0,0 +1,6 @@ +#ifndef __ASM_QSPINLOCK_PARAVIRT_H +#define __ASM_QSPINLOCK_PARAVIRT_H + +PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock); + +#endif diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h index 5a9856eb12ba..7d5a1929d76b 100644 --- a/arch/x86/include/asm/segment.h +++ b/arch/x86/include/asm/segment.h @@ -231,11 +231,21 @@ #define TLS_SIZE (GDT_ENTRY_TLS_ENTRIES* 8) #ifdef __KERNEL__ + +/* + * early_idt_handler_array is an array of entry points referenced in the + * early IDT. For simplicity, it's a real array with one entry point + * every nine bytes. That leaves room for an optional 'push $0' if the + * vector has no error code (two bytes), a 'push $vector_number' (two + * bytes), and a jump to the common entry code (up to five bytes). + */ +#define EARLY_IDT_HANDLER_SIZE 9 + #ifndef __ASSEMBLY__ -extern const char early_idt_handlers[NUM_EXCEPTION_VECTORS][2+2+5]; +extern const char early_idt_handler_array[NUM_EXCEPTION_VECTORS][EARLY_IDT_HANDLER_SIZE]; #ifdef CONFIG_TRACING -# define trace_early_idt_handlers early_idt_handlers +# define trace_early_idt_handler_array early_idt_handler_array #endif /* diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index 17a8dced12da..222a6a3ca2b5 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -37,16 +37,6 @@ DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map); DECLARE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id); DECLARE_PER_CPU_READ_MOSTLY(int, cpu_number); -static inline struct cpumask *cpu_sibling_mask(int cpu) -{ - return per_cpu(cpu_sibling_map, cpu); -} - -static inline struct cpumask *cpu_core_mask(int cpu) -{ - return per_cpu(cpu_core_map, cpu); -} - static inline struct cpumask *cpu_llc_shared_mask(int cpu) { return per_cpu(cpu_llc_shared_map, cpu); diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h index 64b611782ef0..be0a05913b91 100644 --- a/arch/x86/include/asm/spinlock.h +++ b/arch/x86/include/asm/spinlock.h @@ -42,6 +42,10 @@ extern struct static_key paravirt_ticketlocks_enabled; static __always_inline bool static_key_false(struct static_key *key); +#ifdef CONFIG_QUEUED_SPINLOCKS +#include <asm/qspinlock.h> +#else + #ifdef CONFIG_PARAVIRT_SPINLOCKS static inline void __ticket_enter_slowpath(arch_spinlock_t *lock) @@ -196,6 +200,7 @@ static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) cpu_relax(); } } +#endif /* CONFIG_QUEUED_SPINLOCKS */ /* * Read-write spinlocks, allowing multiple readers diff --git a/arch/x86/include/asm/spinlock_types.h b/arch/x86/include/asm/spinlock_types.h index 5f9d7572d82b..65c3e37f879a 100644 --- a/arch/x86/include/asm/spinlock_types.h +++ b/arch/x86/include/asm/spinlock_types.h @@ -23,6 +23,9 @@ typedef u32 __ticketpair_t; #define TICKET_SHIFT (sizeof(__ticket_t) * 8) +#ifdef CONFIG_QUEUED_SPINLOCKS +#include <asm-generic/qspinlock_types.h> +#else typedef struct arch_spinlock { union { __ticketpair_t head_tail; @@ -33,6 +36,7 @@ typedef struct arch_spinlock { } arch_spinlock_t; #define __ARCH_SPIN_LOCK_UNLOCKED { { 0 } } +#endif /* CONFIG_QUEUED_SPINLOCKS */ #include <asm-generic/qrwlock_types.h> diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index 0e8f04f2c26f..5a77593fdace 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -124,7 +124,7 @@ extern const struct cpumask *cpu_coregroup_mask(int cpu); #ifdef ENABLE_TOPO_DEFINES #define topology_core_cpumask(cpu) (per_cpu(cpu_core_map, cpu)) -#define topology_thread_cpumask(cpu) (per_cpu(cpu_sibling_map, cpu)) +#define topology_sibling_cpumask(cpu) (per_cpu(cpu_sibling_map, cpu)) #endif static inline void arch_fix_phys_package_id(int num, u32 slot) diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index ace9dec050b1..a8df874f3e88 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -74,7 +74,8 @@ static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, un * @addr: User space pointer to start of block to check * @size: Size of block to check * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * Checks if a pointer to a block of memory in user space is valid. * @@ -145,7 +146,8 @@ __typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL)) * @x: Variable to store result. * @ptr: Source address, in user space. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * This macro copies a single simple variable from user space to kernel * space. It supports simple types like char and int, but not larger @@ -240,7 +242,8 @@ extern void __put_user_8(void); * @x: Value to copy to user space. * @ptr: Destination address, in user space. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * This macro copies a single simple value from kernel space to user * space. It supports simple types like char and int, but not larger @@ -455,7 +458,8 @@ struct __large_struct { unsigned long buf[100]; }; * @x: Variable to store result. * @ptr: Source address, in user space. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * This macro copies a single simple variable from user space to kernel * space. It supports simple types like char and int, but not larger @@ -479,7 +483,8 @@ struct __large_struct { unsigned long buf[100]; }; * @x: Value to copy to user space. * @ptr: Destination address, in user space. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * This macro copies a single simple value from kernel space to user * space. It supports simple types like char and int, but not larger diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h index 3c03a5de64d3..7c8ad3451988 100644 --- a/arch/x86/include/asm/uaccess_32.h +++ b/arch/x86/include/asm/uaccess_32.h @@ -70,7 +70,8 @@ __copy_to_user_inatomic(void __user *to, const void *from, unsigned long n) * @from: Source address, in kernel space. * @n: Number of bytes to copy. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * Copy data from kernel space to user space. Caller must check * the specified block with access_ok() before calling this function. @@ -117,7 +118,8 @@ __copy_from_user_inatomic(void *to, const void __user *from, unsigned long n) * @from: Source address, in user space. * @n: Number of bytes to copy. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * Copy data from user space to kernel space. Caller must check * the specified block with access_ok() before calling this function. diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 5caed1dd7ccf..29fa475ec518 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -89,9 +89,7 @@ int amd_cache_northbridges(void) next_northbridge(link, amd_nb_link_ids); } - /* GART present only on Fam15h upto model 0fh */ - if (boot_cpu_data.x86 == 0xf || boot_cpu_data.x86 == 0x10 || - (boot_cpu_data.x86 == 0x15 && boot_cpu_data.x86_model < 0x10)) + if (amd_gart_present()) amd_northbridges.flags |= AMD_NB_GART; /* diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index 76164e173a24..6e85f713641d 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -262,6 +262,9 @@ void __init early_gart_iommu_check(void) u64 aper_base = 0, last_aper_base = 0; int aper_enabled = 0, last_aper_enabled = 0, last_valid = 0; + if (!amd_gart_present()) + return; + if (!early_pci_allowed()) return; @@ -355,6 +358,9 @@ int __init gart_iommu_hole_init(void) int fix, slot, valid_agp = 0; int i, node; + if (!amd_gart_present()) + return -ENODEV; + if (gart_iommu_aperture_disabled || !fix_aperture || !early_pci_allowed()) return -ENODEV; @@ -452,7 +458,7 @@ out: force_iommu || valid_agp || fallback_aper_force) { - pr_info("Your BIOS doesn't leave a aperture memory hole\n"); + pr_info("Your BIOS doesn't leave an aperture memory hole\n"); pr_info("Please enable the IOMMU option in the BIOS setup\n"); pr_info("This costs you %dMB of RAM\n", 32 << fallback_aper_order); diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index 9f6b9341950f..b27f6ec90caa 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -41,6 +41,25 @@ void common(void) { OFFSET(pbe_orig_address, pbe, orig_address); OFFSET(pbe_next, pbe, next); +#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION) + BLANK(); + OFFSET(IA32_SIGCONTEXT_ax, sigcontext_ia32, ax); + OFFSET(IA32_SIGCONTEXT_bx, sigcontext_ia32, bx); + OFFSET(IA32_SIGCONTEXT_cx, sigcontext_ia32, cx); + OFFSET(IA32_SIGCONTEXT_dx, sigcontext_ia32, dx); + OFFSET(IA32_SIGCONTEXT_si, sigcontext_ia32, si); + OFFSET(IA32_SIGCONTEXT_di, sigcontext_ia32, di); + OFFSET(IA32_SIGCONTEXT_bp, sigcontext_ia32, bp); + OFFSET(IA32_SIGCONTEXT_sp, sigcontext_ia32, sp); + OFFSET(IA32_SIGCONTEXT_ip, sigcontext_ia32, ip); + + BLANK(); + OFFSET(TI_sysenter_return, thread_info, sysenter_return); + + BLANK(); + OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe_ia32, uc.uc_mcontext); +#endif + #ifdef CONFIG_PARAVIRT BLANK(); OFFSET(PARAVIRT_enabled, pv_info, paravirt_enabled); diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c index 47703aed74cf..6ce39025f467 100644 --- a/arch/x86/kernel/asm-offsets_32.c +++ b/arch/x86/kernel/asm-offsets_32.c @@ -17,17 +17,6 @@ void foo(void); void foo(void) { - OFFSET(IA32_SIGCONTEXT_ax, sigcontext, ax); - OFFSET(IA32_SIGCONTEXT_bx, sigcontext, bx); - OFFSET(IA32_SIGCONTEXT_cx, sigcontext, cx); - OFFSET(IA32_SIGCONTEXT_dx, sigcontext, dx); - OFFSET(IA32_SIGCONTEXT_si, sigcontext, si); - OFFSET(IA32_SIGCONTEXT_di, sigcontext, di); - OFFSET(IA32_SIGCONTEXT_bp, sigcontext, bp); - OFFSET(IA32_SIGCONTEXT_sp, sigcontext, sp); - OFFSET(IA32_SIGCONTEXT_ip, sigcontext, ip); - BLANK(); - OFFSET(CPUINFO_x86, cpuinfo_x86, x86); OFFSET(CPUINFO_x86_vendor, cpuinfo_x86, x86_vendor); OFFSET(CPUINFO_x86_model, cpuinfo_x86, x86_model); @@ -37,10 +26,6 @@ void foo(void) OFFSET(CPUINFO_x86_vendor_id, cpuinfo_x86, x86_vendor_id); BLANK(); - OFFSET(TI_sysenter_return, thread_info, sysenter_return); - OFFSET(TI_cpu, thread_info, cpu); - BLANK(); - OFFSET(PT_EBX, pt_regs, bx); OFFSET(PT_ECX, pt_regs, cx); OFFSET(PT_EDX, pt_regs, dx); @@ -60,9 +45,6 @@ void foo(void) OFFSET(PT_OLDSS, pt_regs, ss); BLANK(); - OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe, uc.uc_mcontext); - BLANK(); - OFFSET(saved_context_gdt_desc, saved_context, gdt_desc); BLANK(); diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index 5ce6f2da8763..dcaab87da629 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -29,27 +29,6 @@ int main(void) BLANK(); #endif -#ifdef CONFIG_IA32_EMULATION - OFFSET(TI_sysenter_return, thread_info, sysenter_return); - BLANK(); - -#define ENTRY(entry) OFFSET(IA32_SIGCONTEXT_ ## entry, sigcontext_ia32, entry) - ENTRY(ax); - ENTRY(bx); - ENTRY(cx); - ENTRY(dx); - ENTRY(si); - ENTRY(di); - ENTRY(bp); - ENTRY(sp); - ENTRY(ip); - BLANK(); -#undef ENTRY - - OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe_ia32, uc.uc_mcontext); - BLANK(); -#endif - #define ENTRY(entry) OFFSET(pt_regs_ ## entry, pt_regs, entry) ENTRY(bx); ENTRY(cx); diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index e4cf63301ff4..56cae1964a81 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -19,6 +19,13 @@ #include "cpu.h" +/* + * nodes_per_socket: Stores the number of nodes per socket. + * Refer to Fam15h Models 00-0fh BKDG - CPUID Fn8000_001E_ECX + * Node Identifiers[10:8] + */ +static u32 nodes_per_socket = 1; + static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p) { u32 gprs[8] = { 0 }; @@ -291,7 +298,7 @@ static int nearby_node(int apicid) #ifdef CONFIG_X86_HT static void amd_get_topology(struct cpuinfo_x86 *c) { - u32 nodes, cores_per_cu = 1; + u32 cores_per_cu = 1; u8 node_id; int cpu = smp_processor_id(); @@ -300,7 +307,7 @@ static void amd_get_topology(struct cpuinfo_x86 *c) u32 eax, ebx, ecx, edx; cpuid(0x8000001e, &eax, &ebx, &ecx, &edx); - nodes = ((ecx >> 8) & 7) + 1; + nodes_per_socket = ((ecx >> 8) & 7) + 1; node_id = ecx & 7; /* get compute unit information */ @@ -311,18 +318,18 @@ static void amd_get_topology(struct cpuinfo_x86 *c) u64 value; rdmsrl(MSR_FAM10H_NODE_ID, value); - nodes = ((value >> 3) & 7) + 1; + nodes_per_socket = ((value >> 3) & 7) + 1; node_id = value & 7; } else return; /* fixup multi-node processor information */ - if (nodes > 1) { + if (nodes_per_socket > 1) { u32 cores_per_node; u32 cus_per_node; set_cpu_cap(c, X86_FEATURE_AMD_DCM); - cores_per_node = c->x86_max_cores / nodes; + cores_per_node = c->x86_max_cores / nodes_per_socket; cus_per_node = cores_per_node / cores_per_cu; /* store NodeID, use llc_shared_map to store sibling info */ @@ -366,6 +373,12 @@ u16 amd_get_nb_id(int cpu) } EXPORT_SYMBOL_GPL(amd_get_nb_id); +u32 amd_get_nodes_per_socket(void) +{ + return nodes_per_socket; +} +EXPORT_SYMBOL_GPL(amd_get_nodes_per_socket); + static void srat_detect_node(struct cpuinfo_x86 *c) { #ifdef CONFIG_NUMA @@ -520,8 +533,16 @@ static void early_init_amd(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_K6_MTRR); #endif #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_PCI) - /* check CPU config space for extended APIC ID */ - if (cpu_has_apic && c->x86 >= 0xf) { + /* + * ApicID can always be treated as an 8-bit value for AMD APIC versions + * >= 0x10, but even old K8s came out of reset with version 0x10. So, we + * can safely set X86_FEATURE_EXTD_APICID unconditionally for families + * after 16h. + */ + if (cpu_has_apic && c->x86 > 0x16) { + set_cpu_cap(c, X86_FEATURE_EXTD_APICID); + } else if (cpu_has_apic && c->x86 >= 0xf) { + /* check CPU config space for extended APIC ID */ unsigned int val; val = read_pci_config(0, 24, 0, 0x68); if ((val & ((1 << 17) | (1 << 18))) == ((1 << 17) | (1 << 18))) diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index a62cf04dac8a..351197cbbc8e 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -5,6 +5,7 @@ #include <linux/module.h> #include <linux/percpu.h> #include <linux/string.h> +#include <linux/ctype.h> #include <linux/delay.h> #include <linux/sched.h> #include <linux/init.h> @@ -419,7 +420,7 @@ static const struct cpu_dev *cpu_devs[X86_VENDOR_NUM] = {}; static void get_model_name(struct cpuinfo_x86 *c) { unsigned int *v; - char *p, *q; + char *p, *q, *s; if (c->extended_cpuid_level < 0x80000004) return; @@ -430,19 +431,21 @@ static void get_model_name(struct cpuinfo_x86 *c) cpuid(0x80000004, &v[8], &v[9], &v[10], &v[11]); c->x86_model_id[48] = 0; - /* - * Intel chips right-justify this string for some dumb reason; - * undo that brain damage: - */ - p = q = &c->x86_model_id[0]; + /* Trim whitespace */ + p = q = s = &c->x86_model_id[0]; + while (*p == ' ') p++; - if (p != q) { - while (*p) - *q++ = *p++; - while (q <= &c->x86_model_id[48]) - *q++ = '\0'; /* Zero-pad the rest */ + + while (*p) { + /* Note the last non-whitespace index */ + if (!isspace(*p)) + s = q; + + *q++ = *p++; } + + *(s + 1) = '\0'; } void cpu_detect_cache_sizes(struct cpuinfo_x86 *c) @@ -1122,7 +1125,7 @@ void print_cpu_info(struct cpuinfo_x86 *c) printk(KERN_CONT "%s ", vendor); if (c->x86_model_id[0]) - printk(KERN_CONT "%s", strim(c->x86_model_id)); + printk(KERN_CONT "%s", c->x86_model_id); else printk(KERN_CONT "%d86", c->x86); diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 20190bdac9d5..95cf78d44ab4 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -53,9 +53,12 @@ static DEFINE_MUTEX(mce_chrdev_read_mutex); #define rcu_dereference_check_mce(p) \ - rcu_dereference_index_check((p), \ - rcu_read_lock_sched_held() || \ - lockdep_is_held(&mce_chrdev_read_mutex)) +({ \ + rcu_lockdep_assert(rcu_read_lock_sched_held() || \ + lockdep_is_held(&mce_chrdev_read_mutex), \ + "suspicious rcu_dereference_check_mce() usage"); \ + smp_load_acquire(&(p)); \ +}) #define CREATE_TRACE_POINTS #include <trace/events/mce.h> @@ -1887,7 +1890,7 @@ out: static unsigned int mce_chrdev_poll(struct file *file, poll_table *wait) { poll_wait(file, &mce_chrdev_wait, wait); - if (rcu_access_index(mcelog.next)) + if (READ_ONCE(mcelog.next)) return POLLIN | POLLRDNORM; if (!mce_apei_read_done && apei_check_mce()) return POLLIN | POLLRDNORM; @@ -1932,8 +1935,8 @@ void register_mce_write_callback(ssize_t (*fn)(struct file *filp, } EXPORT_SYMBOL_GPL(register_mce_write_callback); -ssize_t mce_chrdev_write(struct file *filp, const char __user *ubuf, - size_t usize, loff_t *off) +static ssize_t mce_chrdev_write(struct file *filp, const char __user *ubuf, + size_t usize, loff_t *off) { if (mce_write) return mce_write(filp, ubuf, usize, off); diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 87848ebe2bb7..5801a14f7524 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -135,6 +135,7 @@ static int x86_pmu_extra_regs(u64 config, struct perf_event *event) } static atomic_t active_events; +static atomic_t pmc_refcount; static DEFINE_MUTEX(pmc_reserve_mutex); #ifdef CONFIG_X86_LOCAL_APIC @@ -190,6 +191,7 @@ static bool check_hw_exists(void) u64 val, val_fail, val_new= ~0; int i, reg, reg_fail, ret = 0; int bios_fail = 0; + int reg_safe = -1; /* * Check to see if the BIOS enabled any of the counters, if so @@ -204,6 +206,8 @@ static bool check_hw_exists(void) bios_fail = 1; val_fail = val; reg_fail = reg; + } else { + reg_safe = i; } } @@ -222,11 +226,22 @@ static bool check_hw_exists(void) } /* + * If all the counters are enabled, the below test will always + * fail. The tools will also become useless in this scenario. + * Just fail and disable the hardware counters. + */ + + if (reg_safe == -1) { + reg = reg_safe; + goto msr_fail; + } + + /* * Read the current value, change it and read it back to see if it * matches, this is needed to detect certain hardware emulators * (qemu/kvm) that don't trap on the MSR access and always return 0s. */ - reg = x86_pmu_event_addr(0); + reg = x86_pmu_event_addr(reg_safe); if (rdmsrl_safe(reg, &val)) goto msr_fail; val ^= 0xffffUL; @@ -256,11 +271,8 @@ msr_fail: static void hw_perf_event_destroy(struct perf_event *event) { - if (atomic_dec_and_mutex_lock(&active_events, &pmc_reserve_mutex)) { - release_pmc_hardware(); - release_ds_buffers(); - mutex_unlock(&pmc_reserve_mutex); - } + x86_release_hardware(); + atomic_dec(&active_events); } void hw_perf_lbr_event_destroy(struct perf_event *event) @@ -310,6 +322,35 @@ set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event *event) return x86_pmu_extra_regs(val, event); } +int x86_reserve_hardware(void) +{ + int err = 0; + + if (!atomic_inc_not_zero(&pmc_refcount)) { + mutex_lock(&pmc_reserve_mutex); + if (atomic_read(&pmc_refcount) == 0) { + if (!reserve_pmc_hardware()) + err = -EBUSY; + else + reserve_ds_buffers(); + } + if (!err) + atomic_inc(&pmc_refcount); + mutex_unlock(&pmc_reserve_mutex); + } + + return err; +} + +void x86_release_hardware(void) +{ + if (atomic_dec_and_mutex_lock(&pmc_refcount, &pmc_reserve_mutex)) { + release_pmc_hardware(); + release_ds_buffers(); + mutex_unlock(&pmc_reserve_mutex); + } +} + /* * Check if we can create event of a certain type (that no conflicting events * are present). @@ -322,21 +363,34 @@ int x86_add_exclusive(unsigned int what) return 0; mutex_lock(&pmc_reserve_mutex); - for (i = 0; i < ARRAY_SIZE(x86_pmu.lbr_exclusive); i++) + for (i = 0; i < ARRAY_SIZE(x86_pmu.lbr_exclusive); i++) { if (i != what && atomic_read(&x86_pmu.lbr_exclusive[i])) goto out; + } atomic_inc(&x86_pmu.lbr_exclusive[what]); ret = 0; out: mutex_unlock(&pmc_reserve_mutex); + + /* + * Assuming that all exclusive events will share the PMI handler + * (which checks active_events for whether there is work to do), + * we can bump active_events counter right here, except for + * x86_lbr_exclusive_lbr events that go through x86_pmu_event_init() + * path, which already bumps active_events for them. + */ + if (!ret && what != x86_lbr_exclusive_lbr) + atomic_inc(&active_events); + return ret; } void x86_del_exclusive(unsigned int what) { atomic_dec(&x86_pmu.lbr_exclusive[what]); + atomic_dec(&active_events); } int x86_setup_perfctr(struct perf_event *event) @@ -513,22 +567,11 @@ static int __x86_pmu_event_init(struct perf_event *event) if (!x86_pmu_initialized()) return -ENODEV; - err = 0; - if (!atomic_inc_not_zero(&active_events)) { - mutex_lock(&pmc_reserve_mutex); - if (atomic_read(&active_events) == 0) { - if (!reserve_pmc_hardware()) - err = -EBUSY; - else - reserve_ds_buffers(); - } - if (!err) - atomic_inc(&active_events); - mutex_unlock(&pmc_reserve_mutex); - } + err = x86_reserve_hardware(); if (err) return err; + atomic_inc(&active_events); event->destroy = hw_perf_event_destroy; event->hw.idx = -1; @@ -611,6 +654,7 @@ struct sched_state { int event; /* event index */ int counter; /* counter index */ int unassigned; /* number of events to be assigned left */ + int nr_gp; /* number of GP counters used */ unsigned long used[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; }; @@ -620,27 +664,29 @@ struct sched_state { struct perf_sched { int max_weight; int max_events; - struct perf_event **events; - struct sched_state state; + int max_gp; int saved_states; + struct event_constraint **constraints; + struct sched_state state; struct sched_state saved[SCHED_STATES_MAX]; }; /* * Initialize interator that runs through all events and counters. */ -static void perf_sched_init(struct perf_sched *sched, struct perf_event **events, - int num, int wmin, int wmax) +static void perf_sched_init(struct perf_sched *sched, struct event_constraint **constraints, + int num, int wmin, int wmax, int gpmax) { int idx; memset(sched, 0, sizeof(*sched)); sched->max_events = num; sched->max_weight = wmax; - sched->events = events; + sched->max_gp = gpmax; + sched->constraints = constraints; for (idx = 0; idx < num; idx++) { - if (events[idx]->hw.constraint->weight == wmin) + if (constraints[idx]->weight == wmin) break; } @@ -687,7 +733,7 @@ static bool __perf_sched_find_counter(struct perf_sched *sched) if (sched->state.event >= sched->max_events) return false; - c = sched->events[sched->state.event]->hw.constraint; + c = sched->constraints[sched->state.event]; /* Prefer fixed purpose counters */ if (c->idxmsk64 & (~0ULL << INTEL_PMC_IDX_FIXED)) { idx = INTEL_PMC_IDX_FIXED; @@ -696,11 +742,16 @@ static bool __perf_sched_find_counter(struct perf_sched *sched) goto done; } } + /* Grab the first unused counter starting with idx */ idx = sched->state.counter; for_each_set_bit_from(idx, c->idxmsk, INTEL_PMC_IDX_FIXED) { - if (!__test_and_set_bit(idx, sched->state.used)) + if (!__test_and_set_bit(idx, sched->state.used)) { + if (sched->state.nr_gp++ >= sched->max_gp) + return false; + goto done; + } } return false; @@ -745,7 +796,7 @@ static bool perf_sched_next_event(struct perf_sched *sched) if (sched->state.weight > sched->max_weight) return false; } - c = sched->events[sched->state.event]->hw.constraint; + c = sched->constraints[sched->state.event]; } while (c->weight != sched->state.weight); sched->state.counter = 0; /* start with first counter */ @@ -756,12 +807,12 @@ static bool perf_sched_next_event(struct perf_sched *sched) /* * Assign a counter for each event. */ -int perf_assign_events(struct perf_event **events, int n, - int wmin, int wmax, int *assign) +int perf_assign_events(struct event_constraint **constraints, int n, + int wmin, int wmax, int gpmax, int *assign) { struct perf_sched sched; - perf_sched_init(&sched, events, n, wmin, wmax); + perf_sched_init(&sched, constraints, n, wmin, wmax, gpmax); do { if (!perf_sched_find_counter(&sched)) @@ -788,9 +839,9 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) x86_pmu.start_scheduling(cpuc); for (i = 0, wmin = X86_PMC_IDX_MAX, wmax = 0; i < n; i++) { - hwc = &cpuc->event_list[i]->hw; + cpuc->event_constraint[i] = NULL; c = x86_pmu.get_event_constraints(cpuc, i, cpuc->event_list[i]); - hwc->constraint = c; + cpuc->event_constraint[i] = c; wmin = min(wmin, c->weight); wmax = max(wmax, c->weight); @@ -801,7 +852,7 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) */ for (i = 0; i < n; i++) { hwc = &cpuc->event_list[i]->hw; - c = hwc->constraint; + c = cpuc->event_constraint[i]; /* never assigned */ if (hwc->idx == -1) @@ -821,9 +872,26 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) } /* slow path */ - if (i != n) - unsched = perf_assign_events(cpuc->event_list, n, wmin, - wmax, assign); + if (i != n) { + int gpmax = x86_pmu.num_counters; + + /* + * Do not allow scheduling of more than half the available + * generic counters. + * + * This helps avoid counter starvation of sibling thread by + * ensuring at most half the counters cannot be in exclusive + * mode. There is no designated counters for the limits. Any + * N/2 counters can be used. This helps with events with + * specific counter constraints. + */ + if (is_ht_workaround_enabled() && !cpuc->is_fake && + READ_ONCE(cpuc->excl_cntrs->exclusive_present)) + gpmax /= 2; + + unsched = perf_assign_events(cpuc->event_constraint, n, wmin, + wmax, gpmax, assign); + } /* * In case of success (unsched = 0), mark events as committed, @@ -840,12 +908,9 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) e = cpuc->event_list[i]; e->hw.flags |= PERF_X86_EVENT_COMMITTED; if (x86_pmu.commit_scheduling) - x86_pmu.commit_scheduling(cpuc, e, assign[i]); + x86_pmu.commit_scheduling(cpuc, i, assign[i]); } - } - - if (!assign || unsched) { - + } else { for (i = 0; i < n; i++) { e = cpuc->event_list[i]; /* @@ -1058,13 +1123,16 @@ int x86_perf_event_set_period(struct perf_event *event) per_cpu(pmc_prev_left[idx], smp_processor_id()) = left; - /* - * The hw event starts counting from this event offset, - * mark it to be able to extra future deltas: - */ - local64_set(&hwc->prev_count, (u64)-left); + if (!(hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) || + local64_read(&hwc->prev_count) != (u64)-left) { + /* + * The hw event starts counting from this event offset, + * mark it to be able to extra future deltas: + */ + local64_set(&hwc->prev_count, (u64)-left); - wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask); + wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask); + } /* * Due to erratum on certan cpu we need @@ -1292,8 +1360,10 @@ static void x86_pmu_del(struct perf_event *event, int flags) x86_pmu.put_event_constraints(cpuc, event); /* Delete the array entry. */ - while (++i < cpuc->n_events) + while (++i < cpuc->n_events) { cpuc->event_list[i-1] = cpuc->event_list[i]; + cpuc->event_constraint[i-1] = cpuc->event_constraint[i]; + } --cpuc->n_events; perf_event_update_userpage(event); @@ -1374,6 +1444,10 @@ perf_event_nmi_handler(unsigned int cmd, struct pt_regs *regs) u64 finish_clock; int ret; + /* + * All PMUs/events that share this PMI handler should make sure to + * increment active_events for their events. + */ if (!atomic_read(&active_events)) return NMI_DONE; diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index 6ac5cb7a9e14..3e7fd27dfe20 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -74,6 +74,9 @@ struct event_constraint { #define PERF_X86_EVENT_EXCL 0x0040 /* HT exclusivity on counter */ #define PERF_X86_EVENT_DYNAMIC 0x0080 /* dynamic alloc'd constraint */ #define PERF_X86_EVENT_RDPMC_ALLOWED 0x0100 /* grant rdpmc permission */ +#define PERF_X86_EVENT_EXCL_ACCT 0x0200 /* accounted EXCL event */ +#define PERF_X86_EVENT_AUTO_RELOAD 0x0400 /* use PEBS auto-reload */ +#define PERF_X86_EVENT_FREERUNNING 0x0800 /* use freerunning PEBS */ struct amd_nb { @@ -87,6 +90,18 @@ struct amd_nb { #define MAX_PEBS_EVENTS 8 /* + * Flags PEBS can handle without an PMI. + * + * TID can only be handled by flushing at context switch. + * + */ +#define PEBS_FREERUNNING_FLAGS \ + (PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_ADDR | \ + PERF_SAMPLE_ID | PERF_SAMPLE_CPU | PERF_SAMPLE_STREAM_ID | \ + PERF_SAMPLE_DATA_SRC | PERF_SAMPLE_IDENTIFIER | \ + PERF_SAMPLE_TRANSACTION) + +/* * A debug store configuration. * * We only support architectures that use 64bit fields. @@ -132,10 +147,7 @@ enum intel_excl_state_type { }; struct intel_excl_states { - enum intel_excl_state_type init_state[X86_PMC_IDX_MAX]; enum intel_excl_state_type state[X86_PMC_IDX_MAX]; - int num_alloc_cntrs;/* #counters allocated */ - int max_alloc_cntrs;/* max #counters allowed */ bool sched_started; /* true if scheduling has started */ }; @@ -144,6 +156,11 @@ struct intel_excl_cntrs { struct intel_excl_states states[2]; + union { + u16 has_exclusive[2]; + u32 exclusive_present; + }; + int refcnt; /* per-core: #HT threads */ unsigned core_id; /* per-core: core id */ }; @@ -172,7 +189,11 @@ struct cpu_hw_events { added in the current transaction */ int assign[X86_PMC_IDX_MAX]; /* event to counter assignment */ u64 tags[X86_PMC_IDX_MAX]; + struct perf_event *event_list[X86_PMC_IDX_MAX]; /* in enabled order */ + struct event_constraint *event_constraint[X86_PMC_IDX_MAX]; + + int n_excl; /* the number of exclusive events */ unsigned int group_flag; int is_fake; @@ -519,12 +540,10 @@ struct x86_pmu { void (*put_event_constraints)(struct cpu_hw_events *cpuc, struct perf_event *event); - void (*commit_scheduling)(struct cpu_hw_events *cpuc, - struct perf_event *event, - int cntr); - void (*start_scheduling)(struct cpu_hw_events *cpuc); + void (*commit_scheduling)(struct cpu_hw_events *cpuc, int idx, int cntr); + void (*stop_scheduling)(struct cpu_hw_events *cpuc); struct event_constraint *event_constraints; @@ -697,6 +716,10 @@ int x86_add_exclusive(unsigned int what); void x86_del_exclusive(unsigned int what); +int x86_reserve_hardware(void); + +void x86_release_hardware(void); + void hw_perf_lbr_event_destroy(struct perf_event *event); int x86_setup_perfctr(struct perf_event *event); @@ -717,8 +740,8 @@ static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc, void x86_pmu_enable_all(int added); -int perf_assign_events(struct perf_event **events, int n, - int wmin, int wmax, int *assign); +int perf_assign_events(struct event_constraint **constraints, int n, + int wmin, int wmax, int gpmax, int *assign); int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign); void x86_pmu_stop(struct perf_event *event, int flags); @@ -860,6 +883,8 @@ void intel_pmu_pebs_enable_all(void); void intel_pmu_pebs_disable_all(void); +void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in); + void intel_ds_init(void); void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in); @@ -929,4 +954,8 @@ static inline struct intel_shared_regs *allocate_shared_regs(int cpu) return NULL; } +static inline int is_ht_workaround_enabled(void) +{ + return 0; +} #endif /* CONFIG_CPU_SUP_INTEL */ diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 3998131d1a68..b9826a981fb2 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -1903,9 +1903,8 @@ static void intel_start_scheduling(struct cpu_hw_events *cpuc) { struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs; - struct intel_excl_states *xl, *xlo; + struct intel_excl_states *xl; int tid = cpuc->excl_thread_id; - int o_tid = 1 - tid; /* sibling thread */ /* * nothing needed if in group validation mode @@ -1916,35 +1915,52 @@ intel_start_scheduling(struct cpu_hw_events *cpuc) /* * no exclusion needed */ - if (!excl_cntrs) + if (WARN_ON_ONCE(!excl_cntrs)) return; - xlo = &excl_cntrs->states[o_tid]; xl = &excl_cntrs->states[tid]; xl->sched_started = true; - xl->num_alloc_cntrs = 0; /* * lock shared state until we are done scheduling * in stop_event_scheduling() * makes scheduling appear as a transaction */ - WARN_ON_ONCE(!irqs_disabled()); raw_spin_lock(&excl_cntrs->lock); +} - /* - * save initial state of sibling thread - */ - memcpy(xlo->init_state, xlo->state, sizeof(xlo->init_state)); +static void intel_commit_scheduling(struct cpu_hw_events *cpuc, int idx, int cntr) +{ + struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs; + struct event_constraint *c = cpuc->event_constraint[idx]; + struct intel_excl_states *xl; + int tid = cpuc->excl_thread_id; + + if (cpuc->is_fake || !is_ht_workaround_enabled()) + return; + + if (WARN_ON_ONCE(!excl_cntrs)) + return; + + if (!(c->flags & PERF_X86_EVENT_DYNAMIC)) + return; + + xl = &excl_cntrs->states[tid]; + + lockdep_assert_held(&excl_cntrs->lock); + + if (c->flags & PERF_X86_EVENT_EXCL) + xl->state[cntr] = INTEL_EXCL_EXCLUSIVE; + else + xl->state[cntr] = INTEL_EXCL_SHARED; } static void intel_stop_scheduling(struct cpu_hw_events *cpuc) { struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs; - struct intel_excl_states *xl, *xlo; + struct intel_excl_states *xl; int tid = cpuc->excl_thread_id; - int o_tid = 1 - tid; /* sibling thread */ /* * nothing needed if in group validation mode @@ -1954,17 +1970,11 @@ intel_stop_scheduling(struct cpu_hw_events *cpuc) /* * no exclusion needed */ - if (!excl_cntrs) + if (WARN_ON_ONCE(!excl_cntrs)) return; - xlo = &excl_cntrs->states[o_tid]; xl = &excl_cntrs->states[tid]; - /* - * make new sibling thread state visible - */ - memcpy(xlo->state, xlo->init_state, sizeof(xlo->state)); - xl->sched_started = false; /* * release shared state lock (acquired in intel_start_scheduling()) @@ -1976,12 +1986,10 @@ static struct event_constraint * intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event, int idx, struct event_constraint *c) { - struct event_constraint *cx; struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs; - struct intel_excl_states *xl, *xlo; - int is_excl, i; + struct intel_excl_states *xlo; int tid = cpuc->excl_thread_id; - int o_tid = 1 - tid; /* alternate */ + int is_excl, i; /* * validating a group does not require @@ -1993,34 +2001,8 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event, /* * no exclusion needed */ - if (!excl_cntrs) + if (WARN_ON_ONCE(!excl_cntrs)) return c; - /* - * event requires exclusive counter access - * across HT threads - */ - is_excl = c->flags & PERF_X86_EVENT_EXCL; - - /* - * xl = state of current HT - * xlo = state of sibling HT - */ - xl = &excl_cntrs->states[tid]; - xlo = &excl_cntrs->states[o_tid]; - - /* - * do not allow scheduling of more than max_alloc_cntrs - * which is set to half the available generic counters. - * this helps avoid counter starvation of sibling thread - * by ensuring at most half the counters cannot be in - * exclusive mode. There is not designated counters for the - * limits. Any N/2 counters can be used. This helps with - * events with specifix counter constraints - */ - if (xl->num_alloc_cntrs++ == xl->max_alloc_cntrs) - return &emptyconstraint; - - cx = c; /* * because we modify the constraint, we need @@ -2031,10 +2013,7 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event, * been cloned (marked dynamic) */ if (!(c->flags & PERF_X86_EVENT_DYNAMIC)) { - - /* sanity check */ - if (idx < 0) - return &emptyconstraint; + struct event_constraint *cx; /* * grab pre-allocated constraint entry @@ -2045,13 +2024,14 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event, * initialize dynamic constraint * with static constraint */ - memcpy(cx, c, sizeof(*cx)); + *cx = *c; /* * mark constraint as dynamic, so we * can free it later on */ cx->flags |= PERF_X86_EVENT_DYNAMIC; + c = cx; } /* @@ -2062,6 +2042,22 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event, */ /* + * state of sibling HT + */ + xlo = &excl_cntrs->states[tid ^ 1]; + + /* + * event requires exclusive counter access + * across HT threads + */ + is_excl = c->flags & PERF_X86_EVENT_EXCL; + if (is_excl && !(event->hw.flags & PERF_X86_EVENT_EXCL_ACCT)) { + event->hw.flags |= PERF_X86_EVENT_EXCL_ACCT; + if (!cpuc->n_excl++) + WRITE_ONCE(excl_cntrs->has_exclusive[tid], 1); + } + + /* * Modify static constraint with current dynamic * state of thread * @@ -2069,44 +2065,44 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event, * SHARED : sibling counter measuring non-exclusive event * UNUSED : sibling counter unused */ - for_each_set_bit(i, cx->idxmsk, X86_PMC_IDX_MAX) { + for_each_set_bit(i, c->idxmsk, X86_PMC_IDX_MAX) { /* * exclusive event in sibling counter * our corresponding counter cannot be used * regardless of our event */ - if (xl->state[i] == INTEL_EXCL_EXCLUSIVE) - __clear_bit(i, cx->idxmsk); + if (xlo->state[i] == INTEL_EXCL_EXCLUSIVE) + __clear_bit(i, c->idxmsk); /* * if measuring an exclusive event, sibling * measuring non-exclusive, then counter cannot * be used */ - if (is_excl && xl->state[i] == INTEL_EXCL_SHARED) - __clear_bit(i, cx->idxmsk); + if (is_excl && xlo->state[i] == INTEL_EXCL_SHARED) + __clear_bit(i, c->idxmsk); } /* * recompute actual bit weight for scheduling algorithm */ - cx->weight = hweight64(cx->idxmsk64); + c->weight = hweight64(c->idxmsk64); /* * if we return an empty mask, then switch * back to static empty constraint to avoid * the cost of freeing later on */ - if (cx->weight == 0) - cx = &emptyconstraint; + if (c->weight == 0) + c = &emptyconstraint; - return cx; + return c; } static struct event_constraint * intel_get_event_constraints(struct cpu_hw_events *cpuc, int idx, struct perf_event *event) { - struct event_constraint *c1 = event->hw.constraint; + struct event_constraint *c1 = cpuc->event_constraint[idx]; struct event_constraint *c2; /* @@ -2132,10 +2128,8 @@ static void intel_put_excl_constraints(struct cpu_hw_events *cpuc, { struct hw_perf_event *hwc = &event->hw; struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs; - struct intel_excl_states *xlo, *xl; - unsigned long flags = 0; /* keep compiler happy */ int tid = cpuc->excl_thread_id; - int o_tid = 1 - tid; + struct intel_excl_states *xl; /* * nothing needed if in group validation mode @@ -2143,31 +2137,35 @@ static void intel_put_excl_constraints(struct cpu_hw_events *cpuc, if (cpuc->is_fake) return; - WARN_ON_ONCE(!excl_cntrs); - - if (!excl_cntrs) + if (WARN_ON_ONCE(!excl_cntrs)) return; - xl = &excl_cntrs->states[tid]; - xlo = &excl_cntrs->states[o_tid]; + if (hwc->flags & PERF_X86_EVENT_EXCL_ACCT) { + hwc->flags &= ~PERF_X86_EVENT_EXCL_ACCT; + if (!--cpuc->n_excl) + WRITE_ONCE(excl_cntrs->has_exclusive[tid], 0); + } /* - * put_constraint may be called from x86_schedule_events() - * which already has the lock held so here make locking - * conditional + * If event was actually assigned, then mark the counter state as + * unused now. */ - if (!xl->sched_started) - raw_spin_lock_irqsave(&excl_cntrs->lock, flags); + if (hwc->idx >= 0) { + xl = &excl_cntrs->states[tid]; - /* - * if event was actually assigned, then mark the - * counter state as unused now - */ - if (hwc->idx >= 0) - xlo->state[hwc->idx] = INTEL_EXCL_UNUSED; + /* + * put_constraint may be called from x86_schedule_events() + * which already has the lock held so here make locking + * conditional. + */ + if (!xl->sched_started) + raw_spin_lock(&excl_cntrs->lock); - if (!xl->sched_started) - raw_spin_unlock_irqrestore(&excl_cntrs->lock, flags); + xl->state[hwc->idx] = INTEL_EXCL_UNUSED; + + if (!xl->sched_started) + raw_spin_unlock(&excl_cntrs->lock); + } } static void @@ -2188,8 +2186,6 @@ intel_put_shared_regs_event_constraints(struct cpu_hw_events *cpuc, static void intel_put_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) { - struct event_constraint *c = event->hw.constraint; - intel_put_shared_regs_event_constraints(cpuc, event); /* @@ -2197,48 +2193,8 @@ static void intel_put_event_constraints(struct cpu_hw_events *cpuc, * all events are subject to and must call the * put_excl_constraints() routine */ - if (c && cpuc->excl_cntrs) + if (cpuc->excl_cntrs) intel_put_excl_constraints(cpuc, event); - - /* cleanup dynamic constraint */ - if (c && (c->flags & PERF_X86_EVENT_DYNAMIC)) - event->hw.constraint = NULL; -} - -static void intel_commit_scheduling(struct cpu_hw_events *cpuc, - struct perf_event *event, int cntr) -{ - struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs; - struct event_constraint *c = event->hw.constraint; - struct intel_excl_states *xlo, *xl; - int tid = cpuc->excl_thread_id; - int o_tid = 1 - tid; - int is_excl; - - if (cpuc->is_fake || !c) - return; - - is_excl = c->flags & PERF_X86_EVENT_EXCL; - - if (!(c->flags & PERF_X86_EVENT_DYNAMIC)) - return; - - WARN_ON_ONCE(!excl_cntrs); - - if (!excl_cntrs) - return; - - xl = &excl_cntrs->states[tid]; - xlo = &excl_cntrs->states[o_tid]; - - WARN_ON_ONCE(!raw_spin_is_locked(&excl_cntrs->lock)); - - if (cntr >= 0) { - if (is_excl) - xlo->init_state[cntr] = INTEL_EXCL_EXCLUSIVE; - else - xlo->init_state[cntr] = INTEL_EXCL_SHARED; - } } static void intel_pebs_aliases_core2(struct perf_event *event) @@ -2304,8 +2260,15 @@ static int intel_pmu_hw_config(struct perf_event *event) if (ret) return ret; - if (event->attr.precise_ip && x86_pmu.pebs_aliases) - x86_pmu.pebs_aliases(event); + if (event->attr.precise_ip) { + if (!event->attr.freq) { + event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD; + if (!(event->attr.sample_type & ~PEBS_FREERUNNING_FLAGS)) + event->hw.flags |= PERF_X86_EVENT_FREERUNNING; + } + if (x86_pmu.pebs_aliases) + x86_pmu.pebs_aliases(event); + } if (needs_branch_stack(event)) { ret = intel_pmu_setup_lbr_filter(event); @@ -2554,19 +2517,11 @@ struct intel_shared_regs *allocate_shared_regs(int cpu) static struct intel_excl_cntrs *allocate_excl_cntrs(int cpu) { struct intel_excl_cntrs *c; - int i; c = kzalloc_node(sizeof(struct intel_excl_cntrs), GFP_KERNEL, cpu_to_node(cpu)); if (c) { raw_spin_lock_init(&c->lock); - for (i = 0; i < X86_PMC_IDX_MAX; i++) { - c->states[0].state[i] = INTEL_EXCL_UNUSED; - c->states[0].init_state[i] = INTEL_EXCL_UNUSED; - - c->states[1].state[i] = INTEL_EXCL_UNUSED; - c->states[1].init_state[i] = INTEL_EXCL_UNUSED; - } c->core_id = -1; } return c; @@ -2621,7 +2576,7 @@ static void intel_pmu_cpu_starting(int cpu) if (!(x86_pmu.flags & PMU_FL_NO_HT_SHARING)) { void **onln = &cpuc->kfree_on_online[X86_PERF_KFREE_SHARED]; - for_each_cpu(i, topology_thread_cpumask(cpu)) { + for_each_cpu(i, topology_sibling_cpumask(cpu)) { struct intel_shared_regs *pc; pc = per_cpu(cpu_hw_events, i).shared_regs; @@ -2639,9 +2594,7 @@ static void intel_pmu_cpu_starting(int cpu) cpuc->lbr_sel = &cpuc->shared_regs->regs[EXTRA_REG_LBR]; if (x86_pmu.flags & PMU_FL_EXCL_CNTRS) { - int h = x86_pmu.num_counters >> 1; - - for_each_cpu(i, topology_thread_cpumask(cpu)) { + for_each_cpu(i, topology_sibling_cpumask(cpu)) { struct intel_excl_cntrs *c; c = per_cpu(cpu_hw_events, i).excl_cntrs; @@ -2654,11 +2607,6 @@ static void intel_pmu_cpu_starting(int cpu) } cpuc->excl_cntrs->core_id = core_id; cpuc->excl_cntrs->refcnt++; - /* - * set hard limit to half the number of generic counters - */ - cpuc->excl_cntrs->states[0].max_alloc_cntrs = h; - cpuc->excl_cntrs->states[1].max_alloc_cntrs = h; } } @@ -2694,6 +2642,15 @@ static void intel_pmu_cpu_dying(int cpu) fini_debug_store_on_cpu(cpu); } +static void intel_pmu_sched_task(struct perf_event_context *ctx, + bool sched_in) +{ + if (x86_pmu.pebs_active) + intel_pmu_pebs_sched_task(ctx, sched_in); + if (x86_pmu.lbr_nr) + intel_pmu_lbr_sched_task(ctx, sched_in); +} + PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63"); PMU_FORMAT_ATTR(ldlat, "config1:0-15"); @@ -2783,7 +2740,7 @@ static __initconst const struct x86_pmu intel_pmu = { .cpu_starting = intel_pmu_cpu_starting, .cpu_dying = intel_pmu_cpu_dying, .guest_get_msrs = intel_guest_get_msrs, - .sched_task = intel_pmu_lbr_sched_task, + .sched_task = intel_pmu_sched_task, }; static __init void intel_clovertown_quirk(void) @@ -2956,8 +2913,8 @@ static __init void intel_ht_bug(void) { x86_pmu.flags |= PMU_FL_EXCL_CNTRS | PMU_FL_EXCL_ENABLED; - x86_pmu.commit_scheduling = intel_commit_scheduling; x86_pmu.start_scheduling = intel_start_scheduling; + x86_pmu.commit_scheduling = intel_commit_scheduling; x86_pmu.stop_scheduling = intel_stop_scheduling; } @@ -3270,6 +3227,8 @@ __init int intel_pmu_init(void) case 61: /* 14nm Broadwell Core-M */ case 86: /* 14nm Broadwell Xeon D */ + case 71: /* 14nm Broadwell + GT3e (Intel Iris Pro graphics) */ + case 79: /* 14nm Broadwell Server */ x86_pmu.late_ack = true; memcpy(hw_cache_event_ids, hsw_hw_cache_event_ids, sizeof(hw_cache_event_ids)); memcpy(hw_cache_extra_regs, hsw_hw_cache_extra_regs, sizeof(hw_cache_extra_regs)); @@ -3339,13 +3298,13 @@ __init int intel_pmu_init(void) * counter, so do not extend mask to generic counters */ for_each_event_constraint(c, x86_pmu.event_constraints) { - if (c->cmask != FIXED_EVENT_FLAGS - || c->idxmsk64 == INTEL_PMC_MSK_FIXED_REF_CYCLES) { - continue; + if (c->cmask == FIXED_EVENT_FLAGS + && c->idxmsk64 != INTEL_PMC_MSK_FIXED_REF_CYCLES) { + c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1; } - - c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1; - c->weight += x86_pmu.num_counters; + c->idxmsk64 &= + ~(~0UL << (INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed)); + c->weight = hweight64(c->idxmsk64); } } @@ -3403,7 +3362,7 @@ static __init int fixup_ht_bug(void) if (!(x86_pmu.flags & PMU_FL_EXCL_ENABLED)) return 0; - w = cpumask_weight(topology_thread_cpumask(cpu)); + w = cpumask_weight(topology_sibling_cpumask(cpu)); if (w > 1) { pr_info("PMU erratum BJ122, BV98, HSD29 worked around, HT is on\n"); return 0; @@ -3413,8 +3372,8 @@ static __init int fixup_ht_bug(void) x86_pmu.flags &= ~(PMU_FL_EXCL_CNTRS | PMU_FL_EXCL_ENABLED); - x86_pmu.commit_scheduling = NULL; x86_pmu.start_scheduling = NULL; + x86_pmu.commit_scheduling = NULL; x86_pmu.stop_scheduling = NULL; watchdog_nmi_enable_all(); diff --git a/arch/x86/kernel/cpu/perf_event_intel_bts.c b/arch/x86/kernel/cpu/perf_event_intel_bts.c index ac1f0c55f379..7795f3f8b1d5 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_bts.c +++ b/arch/x86/kernel/cpu/perf_event_intel_bts.c @@ -483,17 +483,26 @@ static int bts_event_add(struct perf_event *event, int mode) static void bts_event_destroy(struct perf_event *event) { + x86_release_hardware(); x86_del_exclusive(x86_lbr_exclusive_bts); } static int bts_event_init(struct perf_event *event) { + int ret; + if (event->attr.type != bts_pmu.type) return -ENOENT; if (x86_add_exclusive(x86_lbr_exclusive_bts)) return -EBUSY; + ret = x86_reserve_hardware(); + if (ret) { + x86_del_exclusive(x86_lbr_exclusive_bts); + return ret; + } + event->destroy = bts_event_destroy; return 0; diff --git a/arch/x86/kernel/cpu/perf_event_intel_cqm.c b/arch/x86/kernel/cpu/perf_event_intel_cqm.c index e4d1b8b738fa..188076161c1b 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_cqm.c +++ b/arch/x86/kernel/cpu/perf_event_intel_cqm.c @@ -13,16 +13,35 @@ #define MSR_IA32_QM_CTR 0x0c8e #define MSR_IA32_QM_EVTSEL 0x0c8d -static unsigned int cqm_max_rmid = -1; +static u32 cqm_max_rmid = -1; static unsigned int cqm_l3_scale; /* supposedly cacheline size */ -struct intel_cqm_state { - raw_spinlock_t lock; - int rmid; - int cnt; +/** + * struct intel_pqr_state - State cache for the PQR MSR + * @rmid: The cached Resource Monitoring ID + * @closid: The cached Class Of Service ID + * @rmid_usecnt: The usage counter for rmid + * + * The upper 32 bits of MSR_IA32_PQR_ASSOC contain closid and the + * lower 10 bits rmid. The update to MSR_IA32_PQR_ASSOC always + * contains both parts, so we need to cache them. + * + * The cache also helps to avoid pointless updates if the value does + * not change. + */ +struct intel_pqr_state { + u32 rmid; + u32 closid; + int rmid_usecnt; }; -static DEFINE_PER_CPU(struct intel_cqm_state, cqm_state); +/* + * The cached intel_pqr_state is strictly per CPU and can never be + * updated from a remote CPU. Both functions which modify the state + * (intel_cqm_event_start and intel_cqm_event_stop) are called with + * interrupts disabled, which is sufficient for the protection. + */ +static DEFINE_PER_CPU(struct intel_pqr_state, pqr_state); /* * Protects cache_cgroups and cqm_rmid_free_lru and cqm_rmid_limbo_lru. @@ -57,7 +76,7 @@ static cpumask_t cqm_cpumask; * near-zero occupancy value, i.e. no cachelines are tagged with this * RMID, once __intel_cqm_rmid_rotate() returns. */ -static unsigned int intel_cqm_rotation_rmid; +static u32 intel_cqm_rotation_rmid; #define INVALID_RMID (-1) @@ -69,7 +88,7 @@ static unsigned int intel_cqm_rotation_rmid; * Likewise, an rmid value of -1 is used to indicate "no rmid currently * assigned" and is used as part of the rotation code. */ -static inline bool __rmid_valid(unsigned int rmid) +static inline bool __rmid_valid(u32 rmid) { if (!rmid || rmid == INVALID_RMID) return false; @@ -77,7 +96,7 @@ static inline bool __rmid_valid(unsigned int rmid) return true; } -static u64 __rmid_read(unsigned int rmid) +static u64 __rmid_read(u32 rmid) { u64 val; @@ -102,7 +121,7 @@ enum rmid_recycle_state { }; struct cqm_rmid_entry { - unsigned int rmid; + u32 rmid; enum rmid_recycle_state state; struct list_head list; unsigned long queue_time; @@ -147,7 +166,7 @@ static LIST_HEAD(cqm_rmid_limbo_lru); */ static struct cqm_rmid_entry **cqm_rmid_ptrs; -static inline struct cqm_rmid_entry *__rmid_entry(int rmid) +static inline struct cqm_rmid_entry *__rmid_entry(u32 rmid) { struct cqm_rmid_entry *entry; @@ -162,7 +181,7 @@ static inline struct cqm_rmid_entry *__rmid_entry(int rmid) * * We expect to be called with cache_mutex held. */ -static int __get_rmid(void) +static u32 __get_rmid(void) { struct cqm_rmid_entry *entry; @@ -177,7 +196,7 @@ static int __get_rmid(void) return entry->rmid; } -static void __put_rmid(unsigned int rmid) +static void __put_rmid(u32 rmid) { struct cqm_rmid_entry *entry; @@ -372,7 +391,7 @@ static bool __conflict_event(struct perf_event *a, struct perf_event *b) } struct rmid_read { - unsigned int rmid; + u32 rmid; atomic64_t value; }; @@ -381,12 +400,11 @@ static void __intel_cqm_event_count(void *info); /* * Exchange the RMID of a group of events. */ -static unsigned int -intel_cqm_xchg_rmid(struct perf_event *group, unsigned int rmid) +static u32 intel_cqm_xchg_rmid(struct perf_event *group, u32 rmid) { struct perf_event *event; - unsigned int old_rmid = group->hw.cqm_rmid; struct list_head *head = &group->hw.cqm_group_entry; + u32 old_rmid = group->hw.cqm_rmid; lockdep_assert_held(&cache_mutex); @@ -451,7 +469,7 @@ static void intel_cqm_stable(void *arg) * If we have group events waiting for an RMID that don't conflict with * events already running, assign @rmid. */ -static bool intel_cqm_sched_in_event(unsigned int rmid) +static bool intel_cqm_sched_in_event(u32 rmid) { struct perf_event *leader, *event; @@ -598,7 +616,7 @@ static bool intel_cqm_rmid_stabilize(unsigned int *available) static void __intel_cqm_pick_and_rotate(struct perf_event *next) { struct perf_event *rotor; - unsigned int rmid; + u32 rmid; lockdep_assert_held(&cache_mutex); @@ -626,7 +644,7 @@ static void __intel_cqm_pick_and_rotate(struct perf_event *next) static void intel_cqm_sched_out_conflicting_events(struct perf_event *event) { struct perf_event *group, *g; - unsigned int rmid; + u32 rmid; lockdep_assert_held(&cache_mutex); @@ -828,8 +846,8 @@ static void intel_cqm_setup_event(struct perf_event *event, struct perf_event **group) { struct perf_event *iter; - unsigned int rmid; bool conflict = false; + u32 rmid; list_for_each_entry(iter, &cache_groups, hw.cqm_groups_entry) { rmid = iter->hw.cqm_rmid; @@ -860,7 +878,7 @@ static void intel_cqm_setup_event(struct perf_event *event, static void intel_cqm_event_read(struct perf_event *event) { unsigned long flags; - unsigned int rmid; + u32 rmid; u64 val; /* @@ -961,55 +979,48 @@ out: static void intel_cqm_event_start(struct perf_event *event, int mode) { - struct intel_cqm_state *state = this_cpu_ptr(&cqm_state); - unsigned int rmid = event->hw.cqm_rmid; - unsigned long flags; + struct intel_pqr_state *state = this_cpu_ptr(&pqr_state); + u32 rmid = event->hw.cqm_rmid; if (!(event->hw.cqm_state & PERF_HES_STOPPED)) return; event->hw.cqm_state &= ~PERF_HES_STOPPED; - raw_spin_lock_irqsave(&state->lock, flags); - - if (state->cnt++) - WARN_ON_ONCE(state->rmid != rmid); - else + if (state->rmid_usecnt++) { + if (!WARN_ON_ONCE(state->rmid != rmid)) + return; + } else { WARN_ON_ONCE(state->rmid); + } state->rmid = rmid; - wrmsrl(MSR_IA32_PQR_ASSOC, state->rmid); - - raw_spin_unlock_irqrestore(&state->lock, flags); + wrmsr(MSR_IA32_PQR_ASSOC, rmid, state->closid); } static void intel_cqm_event_stop(struct perf_event *event, int mode) { - struct intel_cqm_state *state = this_cpu_ptr(&cqm_state); - unsigned long flags; + struct intel_pqr_state *state = this_cpu_ptr(&pqr_state); if (event->hw.cqm_state & PERF_HES_STOPPED) return; event->hw.cqm_state |= PERF_HES_STOPPED; - raw_spin_lock_irqsave(&state->lock, flags); intel_cqm_event_read(event); - if (!--state->cnt) { + if (!--state->rmid_usecnt) { state->rmid = 0; - wrmsrl(MSR_IA32_PQR_ASSOC, 0); + wrmsr(MSR_IA32_PQR_ASSOC, 0, state->closid); } else { WARN_ON_ONCE(!state->rmid); } - - raw_spin_unlock_irqrestore(&state->lock, flags); } static int intel_cqm_event_add(struct perf_event *event, int mode) { unsigned long flags; - unsigned int rmid; + u32 rmid; raw_spin_lock_irqsave(&cache_lock, flags); @@ -1024,11 +1035,6 @@ static int intel_cqm_event_add(struct perf_event *event, int mode) return 0; } -static void intel_cqm_event_del(struct perf_event *event, int mode) -{ - intel_cqm_event_stop(event, mode); -} - static void intel_cqm_event_destroy(struct perf_event *event) { struct perf_event *group_other = NULL; @@ -1057,7 +1063,7 @@ static void intel_cqm_event_destroy(struct perf_event *event) list_replace(&event->hw.cqm_groups_entry, &group_other->hw.cqm_groups_entry); } else { - unsigned int rmid = event->hw.cqm_rmid; + u32 rmid = event->hw.cqm_rmid; if (__rmid_valid(rmid)) __put_rmid(rmid); @@ -1221,7 +1227,7 @@ static struct pmu intel_cqm_pmu = { .task_ctx_nr = perf_sw_context, .event_init = intel_cqm_event_init, .add = intel_cqm_event_add, - .del = intel_cqm_event_del, + .del = intel_cqm_event_stop, .start = intel_cqm_event_start, .stop = intel_cqm_event_stop, .read = intel_cqm_event_read, @@ -1243,12 +1249,12 @@ static inline void cqm_pick_event_reader(int cpu) static void intel_cqm_cpu_prepare(unsigned int cpu) { - struct intel_cqm_state *state = &per_cpu(cqm_state, cpu); + struct intel_pqr_state *state = &per_cpu(pqr_state, cpu); struct cpuinfo_x86 *c = &cpu_data(cpu); - raw_spin_lock_init(&state->lock); state->rmid = 0; - state->cnt = 0; + state->closid = 0; + state->rmid_usecnt = 0; WARN_ON(c->x86_cache_max_rmid != cqm_max_rmid); WARN_ON(c->x86_cache_occ_scale != cqm_l3_scale); diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index 813f75d71175..71fc40238843 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -11,7 +11,7 @@ #define BTS_RECORD_SIZE 24 #define BTS_BUFFER_SIZE (PAGE_SIZE << 4) -#define PEBS_BUFFER_SIZE PAGE_SIZE +#define PEBS_BUFFER_SIZE (PAGE_SIZE << 4) #define PEBS_FIXUP_SIZE PAGE_SIZE /* @@ -250,7 +250,7 @@ static int alloc_pebs_buffer(int cpu) { struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds; int node = cpu_to_node(cpu); - int max, thresh = 1; /* always use a single PEBS record */ + int max; void *buffer, *ibuffer; if (!x86_pmu.pebs) @@ -280,9 +280,6 @@ static int alloc_pebs_buffer(int cpu) ds->pebs_absolute_maximum = ds->pebs_buffer_base + max * x86_pmu.pebs_record_size; - ds->pebs_interrupt_threshold = ds->pebs_buffer_base + - thresh * x86_pmu.pebs_record_size; - return 0; } @@ -549,6 +546,19 @@ int intel_pmu_drain_bts_buffer(void) return 1; } +static inline void intel_pmu_drain_pebs_buffer(void) +{ + struct pt_regs regs; + + x86_pmu.drain_pebs(®s); +} + +void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in) +{ + if (!sched_in) + intel_pmu_drain_pebs_buffer(); +} + /* * PEBS */ @@ -684,33 +694,81 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event) return &emptyconstraint; } +static inline bool pebs_is_enabled(struct cpu_hw_events *cpuc) +{ + return (cpuc->pebs_enabled & ((1ULL << MAX_PEBS_EVENTS) - 1)); +} + void intel_pmu_pebs_enable(struct perf_event *event) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc = &event->hw; + struct debug_store *ds = cpuc->ds; + bool first_pebs; + u64 threshold; hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT; + first_pebs = !pebs_is_enabled(cpuc); cpuc->pebs_enabled |= 1ULL << hwc->idx; if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT) cpuc->pebs_enabled |= 1ULL << (hwc->idx + 32); else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST) cpuc->pebs_enabled |= 1ULL << 63; + + /* + * When the event is constrained enough we can use a larger + * threshold and run the event with less frequent PMI. + */ + if (hwc->flags & PERF_X86_EVENT_FREERUNNING) { + threshold = ds->pebs_absolute_maximum - + x86_pmu.max_pebs_events * x86_pmu.pebs_record_size; + + if (first_pebs) + perf_sched_cb_inc(event->ctx->pmu); + } else { + threshold = ds->pebs_buffer_base + x86_pmu.pebs_record_size; + + /* + * If not all events can use larger buffer, + * roll back to threshold = 1 + */ + if (!first_pebs && + (ds->pebs_interrupt_threshold > threshold)) + perf_sched_cb_dec(event->ctx->pmu); + } + + /* Use auto-reload if possible to save a MSR write in the PMI */ + if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) { + ds->pebs_event_reset[hwc->idx] = + (u64)(-hwc->sample_period) & x86_pmu.cntval_mask; + } + + if (first_pebs || ds->pebs_interrupt_threshold > threshold) + ds->pebs_interrupt_threshold = threshold; } void intel_pmu_pebs_disable(struct perf_event *event) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc = &event->hw; + struct debug_store *ds = cpuc->ds; cpuc->pebs_enabled &= ~(1ULL << hwc->idx); - if (event->hw.constraint->flags & PERF_X86_EVENT_PEBS_LDLAT) + if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT) cpuc->pebs_enabled &= ~(1ULL << (hwc->idx + 32)); - else if (event->hw.constraint->flags & PERF_X86_EVENT_PEBS_ST) + else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST) cpuc->pebs_enabled &= ~(1ULL << 63); + if (ds->pebs_interrupt_threshold > + ds->pebs_buffer_base + x86_pmu.pebs_record_size) { + intel_pmu_drain_pebs_buffer(); + if (!pebs_is_enabled(cpuc)) + perf_sched_cb_dec(event->ctx->pmu); + } + if (cpuc->enabled) wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled); @@ -846,8 +904,10 @@ static inline u64 intel_hsw_transaction(struct pebs_record_hsw *pebs) return txn; } -static void __intel_pmu_pebs_event(struct perf_event *event, - struct pt_regs *iregs, void *__pebs) +static void setup_pebs_sample_data(struct perf_event *event, + struct pt_regs *iregs, void *__pebs, + struct perf_sample_data *data, + struct pt_regs *regs) { #define PERF_X86_EVENT_PEBS_HSW_PREC \ (PERF_X86_EVENT_PEBS_ST_HSW | \ @@ -859,13 +919,11 @@ static void __intel_pmu_pebs_event(struct perf_event *event, */ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct pebs_record_hsw *pebs = __pebs; - struct perf_sample_data data; - struct pt_regs regs; u64 sample_type; int fll, fst, dsrc; int fl = event->hw.flags; - if (!intel_pmu_save_and_restart(event)) + if (pebs == NULL) return; sample_type = event->attr.sample_type; @@ -874,15 +932,15 @@ static void __intel_pmu_pebs_event(struct perf_event *event, fll = fl & PERF_X86_EVENT_PEBS_LDLAT; fst = fl & (PERF_X86_EVENT_PEBS_ST | PERF_X86_EVENT_PEBS_HSW_PREC); - perf_sample_data_init(&data, 0, event->hw.last_period); + perf_sample_data_init(data, 0, event->hw.last_period); - data.period = event->hw.last_period; + data->period = event->hw.last_period; /* * Use latency for weight (only avail with PEBS-LL) */ if (fll && (sample_type & PERF_SAMPLE_WEIGHT)) - data.weight = pebs->lat; + data->weight = pebs->lat; /* * data.data_src encodes the data source @@ -895,7 +953,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event, val = precise_datala_hsw(event, pebs->dse); else if (fst) val = precise_store_data(pebs->dse); - data.data_src.val = val; + data->data_src.val = val; } /* @@ -908,61 +966,123 @@ static void __intel_pmu_pebs_event(struct perf_event *event, * PERF_SAMPLE_IP and PERF_SAMPLE_CALLCHAIN to function properly. * A possible PERF_SAMPLE_REGS will have to transfer all regs. */ - regs = *iregs; - regs.flags = pebs->flags; - set_linear_ip(®s, pebs->ip); - regs.bp = pebs->bp; - regs.sp = pebs->sp; + *regs = *iregs; + regs->flags = pebs->flags; + set_linear_ip(regs, pebs->ip); + regs->bp = pebs->bp; + regs->sp = pebs->sp; if (sample_type & PERF_SAMPLE_REGS_INTR) { - regs.ax = pebs->ax; - regs.bx = pebs->bx; - regs.cx = pebs->cx; - regs.dx = pebs->dx; - regs.si = pebs->si; - regs.di = pebs->di; - regs.bp = pebs->bp; - regs.sp = pebs->sp; - - regs.flags = pebs->flags; + regs->ax = pebs->ax; + regs->bx = pebs->bx; + regs->cx = pebs->cx; + regs->dx = pebs->dx; + regs->si = pebs->si; + regs->di = pebs->di; + regs->bp = pebs->bp; + regs->sp = pebs->sp; + + regs->flags = pebs->flags; #ifndef CONFIG_X86_32 - regs.r8 = pebs->r8; - regs.r9 = pebs->r9; - regs.r10 = pebs->r10; - regs.r11 = pebs->r11; - regs.r12 = pebs->r12; - regs.r13 = pebs->r13; - regs.r14 = pebs->r14; - regs.r15 = pebs->r15; + regs->r8 = pebs->r8; + regs->r9 = pebs->r9; + regs->r10 = pebs->r10; + regs->r11 = pebs->r11; + regs->r12 = pebs->r12; + regs->r13 = pebs->r13; + regs->r14 = pebs->r14; + regs->r15 = pebs->r15; #endif } if (event->attr.precise_ip > 1 && x86_pmu.intel_cap.pebs_format >= 2) { - regs.ip = pebs->real_ip; - regs.flags |= PERF_EFLAGS_EXACT; - } else if (event->attr.precise_ip > 1 && intel_pmu_pebs_fixup_ip(®s)) - regs.flags |= PERF_EFLAGS_EXACT; + regs->ip = pebs->real_ip; + regs->flags |= PERF_EFLAGS_EXACT; + } else if (event->attr.precise_ip > 1 && intel_pmu_pebs_fixup_ip(regs)) + regs->flags |= PERF_EFLAGS_EXACT; else - regs.flags &= ~PERF_EFLAGS_EXACT; + regs->flags &= ~PERF_EFLAGS_EXACT; if ((sample_type & PERF_SAMPLE_ADDR) && x86_pmu.intel_cap.pebs_format >= 1) - data.addr = pebs->dla; + data->addr = pebs->dla; if (x86_pmu.intel_cap.pebs_format >= 2) { /* Only set the TSX weight when no memory weight. */ if ((sample_type & PERF_SAMPLE_WEIGHT) && !fll) - data.weight = intel_hsw_weight(pebs); + data->weight = intel_hsw_weight(pebs); if (sample_type & PERF_SAMPLE_TRANSACTION) - data.txn = intel_hsw_transaction(pebs); + data->txn = intel_hsw_transaction(pebs); } if (has_branch_stack(event)) - data.br_stack = &cpuc->lbr_stack; + data->br_stack = &cpuc->lbr_stack; +} + +static inline void * +get_next_pebs_record_by_bit(void *base, void *top, int bit) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + void *at; + u64 pebs_status; + + if (base == NULL) + return NULL; + + for (at = base; at < top; at += x86_pmu.pebs_record_size) { + struct pebs_record_nhm *p = at; - if (perf_event_overflow(event, &data, ®s)) + if (test_bit(bit, (unsigned long *)&p->status)) { + /* PEBS v3 has accurate status bits */ + if (x86_pmu.intel_cap.pebs_format >= 3) + return at; + + if (p->status == (1 << bit)) + return at; + + /* clear non-PEBS bit and re-check */ + pebs_status = p->status & cpuc->pebs_enabled; + pebs_status &= (1ULL << MAX_PEBS_EVENTS) - 1; + if (pebs_status == (1 << bit)) + return at; + } + } + return NULL; +} + +static void __intel_pmu_pebs_event(struct perf_event *event, + struct pt_regs *iregs, + void *base, void *top, + int bit, int count) +{ + struct perf_sample_data data; + struct pt_regs regs; + void *at = get_next_pebs_record_by_bit(base, top, bit); + + if (!intel_pmu_save_and_restart(event) && + !(event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD)) + return; + + while (count > 1) { + setup_pebs_sample_data(event, iregs, at, &data, ®s); + perf_event_output(event, &data, ®s); + at += x86_pmu.pebs_record_size; + at = get_next_pebs_record_by_bit(at, top, bit); + count--; + } + + setup_pebs_sample_data(event, iregs, at, &data, ®s); + + /* + * All but the last records are processed. + * The last one is left to be able to call the overflow handler. + */ + if (perf_event_overflow(event, &data, ®s)) { x86_pmu_stop(event, 0); + return; + } + } static void intel_pmu_drain_pebs_core(struct pt_regs *iregs) @@ -992,72 +1112,99 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs) if (!event->attr.precise_ip) return; - n = top - at; + n = (top - at) / x86_pmu.pebs_record_size; if (n <= 0) return; - /* - * Should not happen, we program the threshold at 1 and do not - * set a reset value. - */ - WARN_ONCE(n > 1, "bad leftover pebs %d\n", n); - at += n - 1; - - __intel_pmu_pebs_event(event, iregs, at); + __intel_pmu_pebs_event(event, iregs, at, top, 0, n); } static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct debug_store *ds = cpuc->ds; - struct perf_event *event = NULL; - void *at, *top; - u64 status = 0; - int bit; + struct perf_event *event; + void *base, *at, *top; + short counts[MAX_PEBS_EVENTS] = {}; + short error[MAX_PEBS_EVENTS] = {}; + int bit, i; if (!x86_pmu.pebs_active) return; - at = (struct pebs_record_nhm *)(unsigned long)ds->pebs_buffer_base; + base = (struct pebs_record_nhm *)(unsigned long)ds->pebs_buffer_base; top = (struct pebs_record_nhm *)(unsigned long)ds->pebs_index; ds->pebs_index = ds->pebs_buffer_base; - if (unlikely(at > top)) + if (unlikely(base >= top)) return; - /* - * Should not happen, we program the threshold at 1 and do not - * set a reset value. - */ - WARN_ONCE(top - at > x86_pmu.max_pebs_events * x86_pmu.pebs_record_size, - "Unexpected number of pebs records %ld\n", - (long)(top - at) / x86_pmu.pebs_record_size); - - for (; at < top; at += x86_pmu.pebs_record_size) { + for (at = base; at < top; at += x86_pmu.pebs_record_size) { struct pebs_record_nhm *p = at; - for_each_set_bit(bit, (unsigned long *)&p->status, - x86_pmu.max_pebs_events) { - event = cpuc->events[bit]; - if (!test_bit(bit, cpuc->active_mask)) - continue; - - WARN_ON_ONCE(!event); + /* PEBS v3 has accurate status bits */ + if (x86_pmu.intel_cap.pebs_format >= 3) { + for_each_set_bit(bit, (unsigned long *)&p->status, + MAX_PEBS_EVENTS) + counts[bit]++; - if (!event->attr.precise_ip) - continue; + continue; + } - if (__test_and_set_bit(bit, (unsigned long *)&status)) + bit = find_first_bit((unsigned long *)&p->status, + x86_pmu.max_pebs_events); + if (bit >= x86_pmu.max_pebs_events) + continue; + if (!test_bit(bit, cpuc->active_mask)) + continue; + /* + * The PEBS hardware does not deal well with the situation + * when events happen near to each other and multiple bits + * are set. But it should happen rarely. + * + * If these events include one PEBS and multiple non-PEBS + * events, it doesn't impact PEBS record. The record will + * be handled normally. (slow path) + * + * If these events include two or more PEBS events, the + * records for the events can be collapsed into a single + * one, and it's not possible to reconstruct all events + * that caused the PEBS record. It's called collision. + * If collision happened, the record will be dropped. + * + */ + if (p->status != (1 << bit)) { + u64 pebs_status; + + /* slow path */ + pebs_status = p->status & cpuc->pebs_enabled; + pebs_status &= (1ULL << MAX_PEBS_EVENTS) - 1; + if (pebs_status != (1 << bit)) { + for_each_set_bit(i, (unsigned long *)&pebs_status, + MAX_PEBS_EVENTS) + error[i]++; continue; - - break; + } } + counts[bit]++; + } - if (!event || bit >= x86_pmu.max_pebs_events) + for (bit = 0; bit < x86_pmu.max_pebs_events; bit++) { + if ((counts[bit] == 0) && (error[bit] == 0)) continue; + event = cpuc->events[bit]; + WARN_ON_ONCE(!event); + WARN_ON_ONCE(!event->attr.precise_ip); - __intel_pmu_pebs_event(event, iregs, at); + /* log dropped samples number */ + if (error[bit]) + perf_log_lost_samples(event, error[bit]); + + if (counts[bit]) { + __intel_pmu_pebs_event(event, iregs, base, + top, bit, counts[bit]); + } } } diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c index 94e5b506caa6..452a7bd2dedb 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c +++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c @@ -96,6 +96,7 @@ enum { X86_BR_NO_TX = 1 << 14,/* not in transaction */ X86_BR_ZERO_CALL = 1 << 15,/* zero length call */ X86_BR_CALL_STACK = 1 << 16,/* call stack */ + X86_BR_IND_JMP = 1 << 17,/* indirect jump */ }; #define X86_BR_PLM (X86_BR_USER | X86_BR_KERNEL) @@ -113,6 +114,7 @@ enum { X86_BR_IRQ |\ X86_BR_ABORT |\ X86_BR_IND_CALL |\ + X86_BR_IND_JMP |\ X86_BR_ZERO_CALL) #define X86_BR_ALL (X86_BR_PLM | X86_BR_ANY) @@ -262,9 +264,6 @@ void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in) struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct x86_perf_task_context *task_ctx; - if (!x86_pmu.lbr_nr) - return; - /* * If LBR callstack feature is enabled and the stack was saved when * the task was scheduled out, restore the stack. Otherwise flush @@ -523,6 +522,9 @@ static int intel_pmu_setup_sw_lbr_filter(struct perf_event *event) X86_BR_CALL_STACK; } + if (br_type & PERF_SAMPLE_BRANCH_IND_JUMP) + mask |= X86_BR_IND_JMP; + /* * stash actual user request into reg, it may * be used by fixup code for some CPU @@ -736,7 +738,7 @@ static int branch_type(unsigned long from, unsigned long to, int abort) break; case 4: case 5: - ret = X86_BR_JMP; + ret = X86_BR_IND_JMP; break; } break; @@ -844,6 +846,7 @@ static const int nhm_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = { */ [PERF_SAMPLE_BRANCH_IND_CALL_SHIFT] = LBR_IND_CALL | LBR_IND_JMP, [PERF_SAMPLE_BRANCH_COND_SHIFT] = LBR_JCC, + [PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT] = LBR_IND_JMP, }; static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = { @@ -856,6 +859,7 @@ static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = { | LBR_FAR, [PERF_SAMPLE_BRANCH_IND_CALL_SHIFT] = LBR_IND_CALL, [PERF_SAMPLE_BRANCH_COND_SHIFT] = LBR_JCC, + [PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT] = LBR_IND_JMP, }; static const int hsw_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = { @@ -870,6 +874,7 @@ static const int hsw_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = { [PERF_SAMPLE_BRANCH_COND_SHIFT] = LBR_JCC, [PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT] = LBR_REL_CALL | LBR_IND_CALL | LBR_RETURN | LBR_CALL_STACK, + [PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT] = LBR_IND_JMP, }; /* core */ diff --git a/arch/x86/kernel/cpu/perf_event_intel_pt.c b/arch/x86/kernel/cpu/perf_event_intel_pt.c index ffe666c2c6b5..159887c3a89d 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_pt.c +++ b/arch/x86/kernel/cpu/perf_event_intel_pt.c @@ -151,7 +151,7 @@ static int __init pt_pmu_hw_init(void) de_attr->attr.attr.name = pt_caps[i].name; - sysfs_attr_init(&de_attrs->attr.attr); + sysfs_attr_init(&de_attr->attr.attr); de_attr->attr.attr.mode = S_IRUGO; de_attr->attr.show = pt_cap_show; @@ -187,15 +187,6 @@ static bool pt_event_valid(struct perf_event *event) * These all are cpu affine and operate on a local PT */ -static bool pt_is_running(void) -{ - u64 ctl; - - rdmsrl(MSR_IA32_RTIT_CTL, ctl); - - return !!(ctl & RTIT_CTL_TRACEEN); -} - static void pt_config(struct perf_event *event) { u64 reg; @@ -609,16 +600,19 @@ static unsigned int pt_topa_next_entry(struct pt_buffer *buf, unsigned int pg) * @handle: Current output handle. * * Place INT and STOP marks to prevent overwriting old data that the consumer - * hasn't yet collected. + * hasn't yet collected and waking up the consumer after a certain fraction of + * the buffer has filled up. Only needed and sensible for non-snapshot counters. + * + * This obviously relies on buf::head to figure out buffer markers, so it has + * to be called after pt_buffer_reset_offsets() and before the hardware tracing + * is enabled. */ static int pt_buffer_reset_markers(struct pt_buffer *buf, struct perf_output_handle *handle) { - unsigned long idx, npages, end; - - if (buf->snapshot) - return 0; + unsigned long head = local64_read(&buf->head); + unsigned long idx, npages, wakeup; /* can't stop in the middle of an output region */ if (buf->output_off + handle->size + 1 < @@ -634,17 +628,26 @@ static int pt_buffer_reset_markers(struct pt_buffer *buf, buf->topa_index[buf->stop_pos]->stop = 0; buf->topa_index[buf->intr_pos]->intr = 0; - if (pt_cap_get(PT_CAP_topa_multiple_entries)) { - npages = (handle->size + 1) >> PAGE_SHIFT; - end = (local64_read(&buf->head) >> PAGE_SHIFT) + npages; - /*if (end > handle->wakeup >> PAGE_SHIFT) - end = handle->wakeup >> PAGE_SHIFT;*/ - idx = end & (buf->nr_pages - 1); - buf->stop_pos = idx; - idx = (local64_read(&buf->head) >> PAGE_SHIFT) + npages - 1; - idx &= buf->nr_pages - 1; - buf->intr_pos = idx; - } + /* how many pages till the STOP marker */ + npages = handle->size >> PAGE_SHIFT; + + /* if it's on a page boundary, fill up one more page */ + if (!offset_in_page(head + handle->size + 1)) + npages++; + + idx = (head >> PAGE_SHIFT) + npages; + idx &= buf->nr_pages - 1; + buf->stop_pos = idx; + + wakeup = handle->wakeup >> PAGE_SHIFT; + + /* in the worst case, wake up the consumer one page before hard stop */ + idx = (head >> PAGE_SHIFT) + npages - 1; + if (idx > wakeup) + idx = wakeup; + + idx &= buf->nr_pages - 1; + buf->intr_pos = idx; buf->topa_index[buf->stop_pos]->stop = 1; buf->topa_index[buf->intr_pos]->intr = 1; @@ -664,7 +667,7 @@ static void pt_buffer_setup_topa_index(struct pt_buffer *buf) struct topa *cur = buf->first, *prev = buf->last; struct topa_entry *te_cur = TOPA_ENTRY(cur, 0), *te_prev = TOPA_ENTRY(prev, prev->last - 1); - int pg = 0, idx = 0, ntopa = 0; + int pg = 0, idx = 0; while (pg < buf->nr_pages) { int tidx; @@ -679,9 +682,9 @@ static void pt_buffer_setup_topa_index(struct pt_buffer *buf) /* advance to next topa table */ idx = 0; cur = list_entry(cur->list.next, struct topa, list); - ntopa++; - } else + } else { idx++; + } te_cur = TOPA_ENTRY(cur, idx); } @@ -693,7 +696,14 @@ static void pt_buffer_setup_topa_index(struct pt_buffer *buf) * @head: Write pointer (aux_head) from AUX buffer. * * Find the ToPA table and entry corresponding to given @head and set buffer's - * "current" pointers accordingly. + * "current" pointers accordingly. This is done after we have obtained the + * current aux_head position from a successful call to perf_aux_output_begin() + * to make sure the hardware is writing to the right place. + * + * This function modifies buf::{cur,cur_idx,output_off} that will be programmed + * into PT msrs when the tracing is enabled and buf::head and buf::data_size, + * which are used to determine INT and STOP markers' locations by a subsequent + * call to pt_buffer_reset_markers(). */ static void pt_buffer_reset_offsets(struct pt_buffer *buf, unsigned long head) { @@ -891,6 +901,7 @@ void intel_pt_interrupt(void) } pt_buffer_reset_offsets(buf, pt->handle.head); + /* snapshot counters don't use PMI, so it's safe */ ret = pt_buffer_reset_markers(buf, &pt->handle); if (ret) { perf_aux_output_end(&pt->handle, 0, true); @@ -913,7 +924,7 @@ static void pt_event_start(struct perf_event *event, int mode) struct pt *pt = this_cpu_ptr(&pt_ctx); struct pt_buffer *buf = perf_get_aux(&pt->handle); - if (pt_is_running() || !buf || pt_buffer_is_full(buf, pt)) { + if (!buf || pt_buffer_is_full(buf, pt)) { event->hw.state = PERF_HES_STOPPED; return; } @@ -944,7 +955,6 @@ static void pt_event_stop(struct perf_event *event, int mode) event->hw.state = PERF_HES_STOPPED; if (mode & PERF_EF_UPDATE) { - struct pt *pt = this_cpu_ptr(&pt_ctx); struct pt_buffer *buf = perf_get_aux(&pt->handle); if (!buf) diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index c635b8b49e93..7c1de1610178 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -365,9 +365,8 @@ static int uncore_assign_events(struct intel_uncore_box *box, int assign[], int bitmap_zero(used_mask, UNCORE_PMC_IDX_MAX); for (i = 0, wmin = UNCORE_PMC_IDX_MAX, wmax = 0; i < n; i++) { - hwc = &box->event_list[i]->hw; c = uncore_get_event_constraint(box, box->event_list[i]); - hwc->constraint = c; + box->event_constraint[i] = c; wmin = min(wmin, c->weight); wmax = max(wmax, c->weight); } @@ -375,7 +374,7 @@ static int uncore_assign_events(struct intel_uncore_box *box, int assign[], int /* fastpath, try to reuse previous register */ for (i = 0; i < n; i++) { hwc = &box->event_list[i]->hw; - c = hwc->constraint; + c = box->event_constraint[i]; /* never assigned */ if (hwc->idx == -1) @@ -395,8 +394,8 @@ static int uncore_assign_events(struct intel_uncore_box *box, int assign[], int } /* slow path */ if (i != n) - ret = perf_assign_events(box->event_list, n, - wmin, wmax, assign); + ret = perf_assign_events(box->event_constraint, n, + wmin, wmax, n, assign); if (!assign || ret) { for (i = 0; i < n; i++) @@ -840,6 +839,7 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id box->phys_id = phys_id; box->pci_dev = pdev; box->pmu = pmu; + uncore_box_init(box); pci_set_drvdata(pdev, box); raw_spin_lock(&uncore_box_lock); @@ -922,6 +922,9 @@ static int __init uncore_pci_init(void) case 69: /* Haswell Celeron */ ret = hsw_uncore_pci_init(); break; + case 61: /* Broadwell */ + ret = bdw_uncore_pci_init(); + break; default: return 0; } @@ -1003,8 +1006,10 @@ static int uncore_cpu_starting(int cpu) pmu = &type->pmus[j]; box = *per_cpu_ptr(pmu->box, cpu); /* called by uncore_cpu_init? */ - if (box && box->phys_id >= 0) + if (box && box->phys_id >= 0) { + uncore_box_init(box); continue; + } for_each_online_cpu(k) { exist = *per_cpu_ptr(pmu->box, k); @@ -1020,8 +1025,10 @@ static int uncore_cpu_starting(int cpu) } } - if (box) + if (box) { box->phys_id = phys_id; + uncore_box_init(box); + } } } return 0; diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h index 6c8c1e7e69d8..0f77f0a196e4 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h @@ -97,6 +97,7 @@ struct intel_uncore_box { atomic_t refcnt; struct perf_event *events[UNCORE_PMC_IDX_MAX]; struct perf_event *event_list[UNCORE_PMC_IDX_MAX]; + struct event_constraint *event_constraint[UNCORE_PMC_IDX_MAX]; unsigned long active_mask[BITS_TO_LONGS(UNCORE_PMC_IDX_MAX)]; u64 tags[UNCORE_PMC_IDX_MAX]; struct pci_dev *pci_dev; @@ -257,14 +258,6 @@ static inline int uncore_num_counters(struct intel_uncore_box *box) return box->pmu->type->num_counters; } -static inline void uncore_box_init(struct intel_uncore_box *box) -{ - if (!test_and_set_bit(UNCORE_BOX_FLAG_INITIATED, &box->flags)) { - if (box->pmu->type->ops->init_box) - box->pmu->type->ops->init_box(box); - } -} - static inline void uncore_disable_box(struct intel_uncore_box *box) { if (box->pmu->type->ops->disable_box) @@ -273,8 +266,6 @@ static inline void uncore_disable_box(struct intel_uncore_box *box) static inline void uncore_enable_box(struct intel_uncore_box *box) { - uncore_box_init(box); - if (box->pmu->type->ops->enable_box) box->pmu->type->ops->enable_box(box); } @@ -297,6 +288,14 @@ static inline u64 uncore_read_counter(struct intel_uncore_box *box, return box->pmu->type->ops->read_counter(box, event); } +static inline void uncore_box_init(struct intel_uncore_box *box) +{ + if (!test_and_set_bit(UNCORE_BOX_FLAG_INITIATED, &box->flags)) { + if (box->pmu->type->ops->init_box) + box->pmu->type->ops->init_box(box); + } +} + static inline bool uncore_box_is_fake(struct intel_uncore_box *box) { return (box->phys_id < 0); @@ -326,6 +325,7 @@ extern struct event_constraint uncore_constraint_empty; int snb_uncore_pci_init(void); int ivb_uncore_pci_init(void); int hsw_uncore_pci_init(void); +int bdw_uncore_pci_init(void); void snb_uncore_cpu_init(void); void nhm_uncore_cpu_init(void); diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c index 4562e9e22c60..b005a78c7012 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c @@ -7,6 +7,7 @@ #define PCI_DEVICE_ID_INTEL_IVB_E3_IMC 0x0150 #define PCI_DEVICE_ID_INTEL_HSW_IMC 0x0c00 #define PCI_DEVICE_ID_INTEL_HSW_U_IMC 0x0a04 +#define PCI_DEVICE_ID_INTEL_BDW_IMC 0x1604 /* SNB event control */ #define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff @@ -486,6 +487,14 @@ static const struct pci_device_id hsw_uncore_pci_ids[] = { { /* end: all zeroes */ }, }; +static const struct pci_device_id bdw_uncore_pci_ids[] = { + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BDW_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* end: all zeroes */ }, +}; + static struct pci_driver snb_uncore_pci_driver = { .name = "snb_uncore", .id_table = snb_uncore_pci_ids, @@ -501,6 +510,11 @@ static struct pci_driver hsw_uncore_pci_driver = { .id_table = hsw_uncore_pci_ids, }; +static struct pci_driver bdw_uncore_pci_driver = { + .name = "bdw_uncore", + .id_table = bdw_uncore_pci_ids, +}; + struct imc_uncore_pci_dev { __u32 pci_id; struct pci_driver *driver; @@ -514,6 +528,7 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = { IMC_DEV(IVB_E3_IMC, &ivb_uncore_pci_driver), /* Xeon E3-1200 v2/3rd Gen Core processor */ IMC_DEV(HSW_IMC, &hsw_uncore_pci_driver), /* 4th Gen Core Processor */ IMC_DEV(HSW_U_IMC, &hsw_uncore_pci_driver), /* 4th Gen Core ULT Mobile Processor */ + IMC_DEV(BDW_IMC, &bdw_uncore_pci_driver), /* 5th Gen Core U */ { /* end marker */ } }; @@ -561,6 +576,11 @@ int hsw_uncore_pci_init(void) return imc_uncore_pci_init(); } +int bdw_uncore_pci_init(void) +{ + return imc_uncore_pci_init(); +} + /* end of Sandy Bridge uncore support */ /* Nehalem uncore support */ diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c index 12d9548457e7..6d6e85dd5849 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c @@ -164,8 +164,8 @@ ((1ULL << (n)) - 1))) /* Haswell-EP Ubox */ -#define HSWEP_U_MSR_PMON_CTR0 0x705 -#define HSWEP_U_MSR_PMON_CTL0 0x709 +#define HSWEP_U_MSR_PMON_CTR0 0x709 +#define HSWEP_U_MSR_PMON_CTL0 0x705 #define HSWEP_U_MSR_PMON_FILTER 0x707 #define HSWEP_U_MSR_PMON_UCLK_FIXED_CTL 0x703 @@ -1914,7 +1914,7 @@ static struct intel_uncore_type hswep_uncore_cbox = { .name = "cbox", .num_counters = 4, .num_boxes = 18, - .perf_ctr_bits = 44, + .perf_ctr_bits = 48, .event_ctl = HSWEP_C0_MSR_PMON_CTL0, .perf_ctr = HSWEP_C0_MSR_PMON_CTR0, .event_mask = SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK, diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index e7d8c7608471..18ca99f2798b 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -12,7 +12,8 @@ static void show_cpuinfo_core(struct seq_file *m, struct cpuinfo_x86 *c, { #ifdef CONFIG_SMP seq_printf(m, "physical id\t: %d\n", c->phys_proc_id); - seq_printf(m, "siblings\t: %d\n", cpumask_weight(cpu_core_mask(cpu))); + seq_printf(m, "siblings\t: %d\n", + cpumask_weight(topology_core_cpumask(cpu))); seq_printf(m, "core id\t\t: %d\n", c->cpu_core_id); seq_printf(m, "cpu cores\t: %d\n", c->booted_cores); seq_printf(m, "apicid\t\t: %d\n", c->apicid); diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 2b55ee6db053..5a4668136e98 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -167,7 +167,7 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data) clear_bss(); for (i = 0; i < NUM_EXCEPTION_VECTORS; i++) - set_intr_gate(i, early_idt_handlers[i]); + set_intr_gate(i, early_idt_handler_array[i]); load_idt((const struct desc_ptr *)&idt_descr); copy_bootdata(__va(real_mode_data)); diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index d031bad9e07e..53eeb226657c 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -478,21 +478,22 @@ is486: __INIT setup_once: /* - * Set up a idt with 256 entries pointing to ignore_int, - * interrupt gates. It doesn't actually load idt - that needs - * to be done on each CPU. Interrupts are enabled elsewhere, - * when we can be relatively sure everything is ok. + * Set up a idt with 256 interrupt gates that push zero if there + * is no error code and then jump to early_idt_handler_common. + * It doesn't actually load the idt - that needs to be done on + * each CPU. Interrupts are enabled elsewhere, when we can be + * relatively sure everything is ok. */ movl $idt_table,%edi - movl $early_idt_handlers,%eax + movl $early_idt_handler_array,%eax movl $NUM_EXCEPTION_VECTORS,%ecx 1: movl %eax,(%edi) movl %eax,4(%edi) /* interrupt gate, dpl=0, present */ movl $(0x8E000000 + __KERNEL_CS),2(%edi) - addl $9,%eax + addl $EARLY_IDT_HANDLER_SIZE,%eax addl $8,%edi loop 1b @@ -524,26 +525,28 @@ setup_once: andl $0,setup_once_ref /* Once is enough, thanks */ ret -ENTRY(early_idt_handlers) +ENTRY(early_idt_handler_array) # 36(%esp) %eflags # 32(%esp) %cs # 28(%esp) %eip # 24(%rsp) error code i = 0 .rept NUM_EXCEPTION_VECTORS - .if (EXCEPTION_ERRCODE_MASK >> i) & 1 - ASM_NOP2 - .else + .ifeq (EXCEPTION_ERRCODE_MASK >> i) & 1 pushl $0 # Dummy error code, to make stack frame uniform .endif pushl $i # 20(%esp) Vector number - jmp early_idt_handler + jmp early_idt_handler_common i = i + 1 + .fill early_idt_handler_array + i*EARLY_IDT_HANDLER_SIZE - ., 1, 0xcc .endr -ENDPROC(early_idt_handlers) +ENDPROC(early_idt_handler_array) - /* This is global to keep gas from relaxing the jumps */ -ENTRY(early_idt_handler) +early_idt_handler_common: + /* + * The stack is the hardware frame, an error code or zero, and the + * vector number. + */ cld cmpl $2,(%esp) # X86_TRAP_NMI @@ -603,7 +606,7 @@ ex_entry: is_nmi: addl $8,%esp /* drop vector number and error code */ iret -ENDPROC(early_idt_handler) +ENDPROC(early_idt_handler_common) /* This is the default interrupt "handler" :-) */ ALIGN diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index ae6588b301c2..df7e78057ae0 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -321,26 +321,28 @@ bad_address: jmp bad_address __INIT - .globl early_idt_handlers -early_idt_handlers: +ENTRY(early_idt_handler_array) # 104(%rsp) %rflags # 96(%rsp) %cs # 88(%rsp) %rip # 80(%rsp) error code i = 0 .rept NUM_EXCEPTION_VECTORS - .if (EXCEPTION_ERRCODE_MASK >> i) & 1 - ASM_NOP2 - .else + .ifeq (EXCEPTION_ERRCODE_MASK >> i) & 1 pushq $0 # Dummy error code, to make stack frame uniform .endif pushq $i # 72(%rsp) Vector number - jmp early_idt_handler + jmp early_idt_handler_common i = i + 1 + .fill early_idt_handler_array + i*EARLY_IDT_HANDLER_SIZE - ., 1, 0xcc .endr +ENDPROC(early_idt_handler_array) -/* This is global to keep gas from relaxing the jumps */ -ENTRY(early_idt_handler) +early_idt_handler_common: + /* + * The stack is the hardware frame, an error code or zero, and the + * vector number. + */ cld cmpl $2,(%rsp) # X86_TRAP_NMI @@ -412,7 +414,7 @@ ENTRY(early_idt_handler) is_nmi: addq $16,%rsp # drop vector number and error code INTERRUPT_RETURN -ENDPROC(early_idt_handler) +ENDPROC(early_idt_handler_common) __INITDATA diff --git a/arch/x86/kernel/i386_ksyms_32.c b/arch/x86/kernel/i386_ksyms_32.c index 05fd74f537d6..64341aa485ae 100644 --- a/arch/x86/kernel/i386_ksyms_32.c +++ b/arch/x86/kernel/i386_ksyms_32.c @@ -40,7 +40,5 @@ EXPORT_SYMBOL(empty_zero_page); #ifdef CONFIG_PREEMPT EXPORT_SYMBOL(___preempt_schedule); -#ifdef CONFIG_CONTEXT_TRACKING -EXPORT_SYMBOL(___preempt_schedule_context); -#endif +EXPORT_SYMBOL(___preempt_schedule_notrace); #endif diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 9435620062df..1681504e44a4 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -584,6 +584,39 @@ static void kvm_kick_cpu(int cpu) kvm_hypercall2(KVM_HC_KICK_CPU, flags, apicid); } + +#ifdef CONFIG_QUEUED_SPINLOCKS + +#include <asm/qspinlock.h> + +static void kvm_wait(u8 *ptr, u8 val) +{ + unsigned long flags; + + if (in_nmi()) + return; + + local_irq_save(flags); + + if (READ_ONCE(*ptr) != val) + goto out; + + /* + * halt until it's our turn and kicked. Note that we do safe halt + * for irq enabled case to avoid hang when lock info is overwritten + * in irq spinlock slowpath and no spurious interrupt occur to save us. + */ + if (arch_irqs_disabled_flags(flags)) + halt(); + else + safe_halt(); + +out: + local_irq_restore(flags); +} + +#else /* !CONFIG_QUEUED_SPINLOCKS */ + enum kvm_contention_stat { TAKEN_SLOW, TAKEN_SLOW_PICKUP, @@ -817,6 +850,8 @@ static void kvm_unlock_kick(struct arch_spinlock *lock, __ticket_t ticket) } } +#endif /* !CONFIG_QUEUED_SPINLOCKS */ + /* * Setup pv_lock_ops to exploit KVM_FEATURE_PV_UNHALT if present. */ @@ -828,8 +863,16 @@ void __init kvm_spinlock_init(void) if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT)) return; +#ifdef CONFIG_QUEUED_SPINLOCKS + __pv_init_lock_hash(); + pv_lock_ops.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath; + pv_lock_ops.queued_spin_unlock = PV_CALLEE_SAVE(__pv_queued_spin_unlock); + pv_lock_ops.wait = kvm_wait; + pv_lock_ops.kick = kvm_kick_cpu; +#else /* !CONFIG_QUEUED_SPINLOCKS */ pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(kvm_lock_spinning); pv_lock_ops.unlock_kick = kvm_unlock_kick; +#endif } static __init int kvm_spinlock_init_jump(void) diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c index bbb6c7316341..33ee3e0efd65 100644 --- a/arch/x86/kernel/paravirt-spinlocks.c +++ b/arch/x86/kernel/paravirt-spinlocks.c @@ -8,11 +8,33 @@ #include <asm/paravirt.h> +#ifdef CONFIG_QUEUED_SPINLOCKS +__visible void __native_queued_spin_unlock(struct qspinlock *lock) +{ + native_queued_spin_unlock(lock); +} + +PV_CALLEE_SAVE_REGS_THUNK(__native_queued_spin_unlock); + +bool pv_is_native_spin_unlock(void) +{ + return pv_lock_ops.queued_spin_unlock.func == + __raw_callee_save___native_queued_spin_unlock; +} +#endif + struct pv_lock_ops pv_lock_ops = { #ifdef CONFIG_SMP +#ifdef CONFIG_QUEUED_SPINLOCKS + .queued_spin_lock_slowpath = native_queued_spin_lock_slowpath, + .queued_spin_unlock = PV_CALLEE_SAVE(__native_queued_spin_unlock), + .wait = paravirt_nop, + .kick = paravirt_nop, +#else /* !CONFIG_QUEUED_SPINLOCKS */ .lock_spinning = __PV_IS_CALLEE_SAVE(paravirt_nop), .unlock_kick = paravirt_nop, -#endif +#endif /* !CONFIG_QUEUED_SPINLOCKS */ +#endif /* SMP */ }; EXPORT_SYMBOL(pv_lock_ops); diff --git a/arch/x86/kernel/paravirt_patch_32.c b/arch/x86/kernel/paravirt_patch_32.c index d9f32e6d6ab6..e1b013696dde 100644 --- a/arch/x86/kernel/paravirt_patch_32.c +++ b/arch/x86/kernel/paravirt_patch_32.c @@ -12,6 +12,10 @@ DEF_NATIVE(pv_mmu_ops, read_cr3, "mov %cr3, %eax"); DEF_NATIVE(pv_cpu_ops, clts, "clts"); DEF_NATIVE(pv_cpu_ops, read_tsc, "rdtsc"); +#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS) +DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%eax)"); +#endif + unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len) { /* arg in %eax, return in %eax */ @@ -24,6 +28,8 @@ unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len) return 0; } +extern bool pv_is_native_spin_unlock(void); + unsigned native_patch(u8 type, u16 clobbers, void *ibuf, unsigned long addr, unsigned len) { @@ -47,14 +53,22 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf, PATCH_SITE(pv_mmu_ops, write_cr3); PATCH_SITE(pv_cpu_ops, clts); PATCH_SITE(pv_cpu_ops, read_tsc); - - patch_site: - ret = paravirt_patch_insns(ibuf, len, start, end); - break; +#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS) + case PARAVIRT_PATCH(pv_lock_ops.queued_spin_unlock): + if (pv_is_native_spin_unlock()) { + start = start_pv_lock_ops_queued_spin_unlock; + end = end_pv_lock_ops_queued_spin_unlock; + goto patch_site; + } +#endif default: ret = paravirt_patch_default(type, clobbers, ibuf, addr, len); break; + +patch_site: + ret = paravirt_patch_insns(ibuf, len, start, end); + break; } #undef PATCH_SITE return ret; diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c index a1da6737ba5b..a1fa86782186 100644 --- a/arch/x86/kernel/paravirt_patch_64.c +++ b/arch/x86/kernel/paravirt_patch_64.c @@ -21,6 +21,10 @@ DEF_NATIVE(pv_cpu_ops, swapgs, "swapgs"); DEF_NATIVE(, mov32, "mov %edi, %eax"); DEF_NATIVE(, mov64, "mov %rdi, %rax"); +#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS) +DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%rdi)"); +#endif + unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len) { return paravirt_patch_insns(insnbuf, len, @@ -33,6 +37,8 @@ unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len) start__mov64, end__mov64); } +extern bool pv_is_native_spin_unlock(void); + unsigned native_patch(u8 type, u16 clobbers, void *ibuf, unsigned long addr, unsigned len) { @@ -59,14 +65,22 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf, PATCH_SITE(pv_cpu_ops, clts); PATCH_SITE(pv_mmu_ops, flush_tlb_single); PATCH_SITE(pv_cpu_ops, wbinvd); - - patch_site: - ret = paravirt_patch_insns(ibuf, len, start, end); - break; +#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS) + case PARAVIRT_PATCH(pv_lock_ops.queued_spin_unlock): + if (pv_is_native_spin_unlock()) { + start = start_pv_lock_ops_queued_spin_unlock; + end = end_pv_lock_ops_queued_spin_unlock; + goto patch_site; + } +#endif default: ret = paravirt_patch_default(type, clobbers, ibuf, addr, len); break; + +patch_site: + ret = paravirt_patch_insns(ibuf, len, start, end); + break; } #undef PATCH_SITE return ret; diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index a25e202bb319..353972c1946c 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -140,6 +140,51 @@ void dma_generic_free_coherent(struct device *dev, size_t size, void *vaddr, free_pages((unsigned long)vaddr, get_order(size)); } +void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle, + gfp_t gfp, struct dma_attrs *attrs) +{ + struct dma_map_ops *ops = get_dma_ops(dev); + void *memory; + + gfp &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32); + + if (dma_alloc_from_coherent(dev, size, dma_handle, &memory)) + return memory; + + if (!dev) + dev = &x86_dma_fallback_dev; + + if (!is_device_dma_capable(dev)) + return NULL; + + if (!ops->alloc) + return NULL; + + memory = ops->alloc(dev, size, dma_handle, + dma_alloc_coherent_gfp_flags(dev, gfp), attrs); + debug_dma_alloc_coherent(dev, size, *dma_handle, memory); + + return memory; +} +EXPORT_SYMBOL(dma_alloc_attrs); + +void dma_free_attrs(struct device *dev, size_t size, + void *vaddr, dma_addr_t bus, + struct dma_attrs *attrs) +{ + struct dma_map_ops *ops = get_dma_ops(dev); + + WARN_ON(irqs_disabled()); /* for portability */ + + if (dma_release_from_coherent(dev, get_order(size), vaddr)) + return; + + debug_dma_free_coherent(dev, size, vaddr, bus); + if (ops->free) + ops->free(dev, size, vaddr, bus, attrs); +} +EXPORT_SYMBOL(dma_free_attrs); + /* * See <Documentation/x86/x86_64/boot-options.txt> for the iommu kernel * parameter documentation. diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 6e338e3b1dc0..c648139d68d7 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -445,11 +445,10 @@ static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c) } /* - * MONITOR/MWAIT with no hints, used for default default C1 state. - * This invokes MWAIT with interrutps enabled and no flags, - * which is backwards compatible with the original MWAIT implementation. + * MONITOR/MWAIT with no hints, used for default C1 state. This invokes MWAIT + * with interrupts enabled and no flags, which is backwards compatible with the + * original MWAIT implementation. */ - static void mwait_idle(void) { if (!current_set_polling_and_test()) { diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 50e547eac8cd..0e8209619455 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -314,10 +314,10 @@ topology_sane(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o, const char *name) cpu1, name, cpu2, cpu_to_node(cpu1), cpu_to_node(cpu2)); } -#define link_mask(_m, c1, c2) \ +#define link_mask(mfunc, c1, c2) \ do { \ - cpumask_set_cpu((c1), cpu_##_m##_mask(c2)); \ - cpumask_set_cpu((c2), cpu_##_m##_mask(c1)); \ + cpumask_set_cpu((c1), mfunc(c2)); \ + cpumask_set_cpu((c2), mfunc(c1)); \ } while (0) static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) @@ -398,9 +398,9 @@ void set_cpu_sibling_map(int cpu) cpumask_set_cpu(cpu, cpu_sibling_setup_mask); if (!has_mp) { - cpumask_set_cpu(cpu, cpu_sibling_mask(cpu)); + cpumask_set_cpu(cpu, topology_sibling_cpumask(cpu)); cpumask_set_cpu(cpu, cpu_llc_shared_mask(cpu)); - cpumask_set_cpu(cpu, cpu_core_mask(cpu)); + cpumask_set_cpu(cpu, topology_core_cpumask(cpu)); c->booted_cores = 1; return; } @@ -409,32 +409,34 @@ void set_cpu_sibling_map(int cpu) o = &cpu_data(i); if ((i == cpu) || (has_smt && match_smt(c, o))) - link_mask(sibling, cpu, i); + link_mask(topology_sibling_cpumask, cpu, i); if ((i == cpu) || (has_mp && match_llc(c, o))) - link_mask(llc_shared, cpu, i); + link_mask(cpu_llc_shared_mask, cpu, i); } /* * This needs a separate iteration over the cpus because we rely on all - * cpu_sibling_mask links to be set-up. + * topology_sibling_cpumask links to be set-up. */ for_each_cpu(i, cpu_sibling_setup_mask) { o = &cpu_data(i); if ((i == cpu) || (has_mp && match_die(c, o))) { - link_mask(core, cpu, i); + link_mask(topology_core_cpumask, cpu, i); /* * Does this new cpu bringup a new core? */ - if (cpumask_weight(cpu_sibling_mask(cpu)) == 1) { + if (cpumask_weight( + topology_sibling_cpumask(cpu)) == 1) { /* * for each core in package, increment * the booted_cores for this new cpu */ - if (cpumask_first(cpu_sibling_mask(i)) == i) + if (cpumask_first( + topology_sibling_cpumask(i)) == i) c->booted_cores++; /* * increment the core count for all @@ -1009,8 +1011,8 @@ static __init void disable_smp(void) physid_set_mask_of_physid(boot_cpu_physical_apicid, &phys_cpu_present_map); else physid_set_mask_of_physid(0, &phys_cpu_present_map); - cpumask_set_cpu(0, cpu_sibling_mask(0)); - cpumask_set_cpu(0, cpu_core_mask(0)); + cpumask_set_cpu(0, topology_sibling_cpumask(0)); + cpumask_set_cpu(0, topology_core_cpumask(0)); } enum { @@ -1293,22 +1295,22 @@ static void remove_siblinginfo(int cpu) int sibling; struct cpuinfo_x86 *c = &cpu_data(cpu); - for_each_cpu(sibling, cpu_core_mask(cpu)) { - cpumask_clear_cpu(cpu, cpu_core_mask(sibling)); + for_each_cpu(sibling, topology_core_cpumask(cpu)) { + cpumask_clear_cpu(cpu, topology_core_cpumask(sibling)); /*/ * last thread sibling in this cpu core going down */ - if (cpumask_weight(cpu_sibling_mask(cpu)) == 1) + if (cpumask_weight(topology_sibling_cpumask(cpu)) == 1) cpu_data(sibling).booted_cores--; } - for_each_cpu(sibling, cpu_sibling_mask(cpu)) - cpumask_clear_cpu(cpu, cpu_sibling_mask(sibling)); + for_each_cpu(sibling, topology_sibling_cpumask(cpu)) + cpumask_clear_cpu(cpu, topology_sibling_cpumask(sibling)); for_each_cpu(sibling, cpu_llc_shared_mask(cpu)) cpumask_clear_cpu(cpu, cpu_llc_shared_mask(sibling)); cpumask_clear(cpu_llc_shared_mask(cpu)); - cpumask_clear(cpu_sibling_mask(cpu)); - cpumask_clear(cpu_core_mask(cpu)); + cpumask_clear(topology_sibling_cpumask(cpu)); + cpumask_clear(topology_core_cpumask(cpu)); c->phys_proc_id = 0; c->cpu_core_id = 0; cpumask_clear_cpu(cpu, cpu_sibling_setup_mask); diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c index 26488487bc61..dd8d0791dfb5 100644 --- a/arch/x86/kernel/tsc_sync.c +++ b/arch/x86/kernel/tsc_sync.c @@ -113,7 +113,7 @@ static void check_tsc_warp(unsigned int timeout) */ static inline unsigned int loop_timeout(int cpu) { - return (cpumask_weight(cpu_core_mask(cpu)) > 1) ? 2 : 20; + return (cpumask_weight(topology_core_cpumask(cpu)) > 1) ? 2 : 20; } /* diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c index 37d8fa4438f0..a0695be19864 100644 --- a/arch/x86/kernel/x8664_ksyms_64.c +++ b/arch/x86/kernel/x8664_ksyms_64.c @@ -75,7 +75,5 @@ EXPORT_SYMBOL(native_load_gs_index); #ifdef CONFIG_PREEMPT EXPORT_SYMBOL(___preempt_schedule); -#ifdef CONFIG_CONTEXT_TRACKING -EXPORT_SYMBOL(___preempt_schedule_context); -#endif +EXPORT_SYMBOL(___preempt_schedule_notrace); #endif diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 629af0f1c5c4..4c7deb4f78a1 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1090,6 +1090,17 @@ static void update_divide_count(struct kvm_lapic *apic) apic->divide_count); } +static void apic_update_lvtt(struct kvm_lapic *apic) +{ + u32 timer_mode = kvm_apic_get_reg(apic, APIC_LVTT) & + apic->lapic_timer.timer_mode_mask; + + if (apic->lapic_timer.timer_mode != timer_mode) { + apic->lapic_timer.timer_mode = timer_mode; + hrtimer_cancel(&apic->lapic_timer.timer); + } +} + static void apic_timer_expired(struct kvm_lapic *apic) { struct kvm_vcpu *vcpu = apic->vcpu; @@ -1298,6 +1309,7 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) apic_set_reg(apic, APIC_LVTT + 0x10 * i, lvt_val | APIC_LVT_MASKED); } + apic_update_lvtt(apic); atomic_set(&apic->lapic_timer.pending, 0); } @@ -1330,20 +1342,13 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) break; - case APIC_LVTT: { - u32 timer_mode = val & apic->lapic_timer.timer_mode_mask; - - if (apic->lapic_timer.timer_mode != timer_mode) { - apic->lapic_timer.timer_mode = timer_mode; - hrtimer_cancel(&apic->lapic_timer.timer); - } - + case APIC_LVTT: if (!kvm_apic_sw_enabled(apic)) val |= APIC_LVT_MASKED; val &= (apic_lvt_mask[0] | apic->lapic_timer.timer_mode_mask); apic_set_reg(apic, APIC_LVTT, val); + apic_update_lvtt(apic); break; - } case APIC_TMICT: if (apic_lvtt_tscdeadline(apic)) @@ -1576,7 +1581,7 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu) for (i = 0; i < APIC_LVT_NUM; i++) apic_set_reg(apic, APIC_LVTT + 0x10 * i, APIC_LVT_MASKED); - apic->lapic_timer.timer_mode = 0; + apic_update_lvtt(apic); apic_set_reg(apic, APIC_LVT0, SET_APIC_DELIVERY_MODE(0, APIC_MODE_EXTINT)); @@ -1802,6 +1807,7 @@ void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu, apic_update_ppr(apic); hrtimer_cancel(&apic->lapic_timer.timer); + apic_update_lvtt(apic); update_divide_count(apic); start_apic_timer(apic); apic->irr_pending = true; diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 44a7d2515497..b73337634214 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -4215,13 +4215,13 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, u64 entry, gentry, *spte; int npte; bool remote_flush, local_flush, zap_page; - union kvm_mmu_page_role mask = (union kvm_mmu_page_role) { - .cr0_wp = 1, - .cr4_pae = 1, - .nxe = 1, - .smep_andnot_wp = 1, - .smap_andnot_wp = 1, - }; + union kvm_mmu_page_role mask = { }; + + mask.cr0_wp = 1; + mask.cr4_pae = 1; + mask.nxe = 1; + mask.smep_andnot_wp = 1; + mask.smap_andnot_wp = 1; /* * If we don't have indirect shadow pages, it means no page is diff --git a/arch/x86/lib/thunk_32.S b/arch/x86/lib/thunk_32.S index 5eb715087b80..e407941d0488 100644 --- a/arch/x86/lib/thunk_32.S +++ b/arch/x86/lib/thunk_32.S @@ -38,8 +38,6 @@ #ifdef CONFIG_PREEMPT THUNK ___preempt_schedule, preempt_schedule -#ifdef CONFIG_CONTEXT_TRACKING - THUNK ___preempt_schedule_context, preempt_schedule_context -#endif + THUNK ___preempt_schedule_notrace, preempt_schedule_notrace #endif diff --git a/arch/x86/lib/thunk_64.S b/arch/x86/lib/thunk_64.S index f89ba4e93025..2198902329b5 100644 --- a/arch/x86/lib/thunk_64.S +++ b/arch/x86/lib/thunk_64.S @@ -49,9 +49,7 @@ #ifdef CONFIG_PREEMPT THUNK ___preempt_schedule, preempt_schedule -#ifdef CONFIG_CONTEXT_TRACKING - THUNK ___preempt_schedule_context, preempt_schedule_context -#endif + THUNK ___preempt_schedule_notrace, preempt_schedule_notrace #endif #if defined(CONFIG_TRACE_IRQFLAGS) \ diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c index e2f5e21c03b3..91d93b95bd86 100644 --- a/arch/x86/lib/usercopy_32.c +++ b/arch/x86/lib/usercopy_32.c @@ -647,7 +647,8 @@ EXPORT_SYMBOL(__copy_from_user_ll_nocache_nozero); * @from: Source address, in kernel space. * @n: Number of bytes to copy. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * Copy data from kernel space to user space. * @@ -668,7 +669,8 @@ EXPORT_SYMBOL(_copy_to_user); * @from: Source address, in user space. * @n: Number of bytes to copy. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * Copy data from user space to kernel space. * diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 181c53bac3a7..9dc909841739 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -13,6 +13,7 @@ #include <linux/hugetlb.h> /* hstate_index_to_shift */ #include <linux/prefetch.h> /* prefetchw */ #include <linux/context_tracking.h> /* exception_enter(), ... */ +#include <linux/uaccess.h> /* faulthandler_disabled() */ #include <asm/traps.h> /* dotraplinkage, ... */ #include <asm/pgalloc.h> /* pgd_*(), ... */ @@ -1126,9 +1127,9 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code, /* * If we're in an interrupt, have no user context or are running - * in an atomic region then we must not take the fault: + * in a region with pagefaults disabled then we must not take the fault */ - if (unlikely(in_atomic() || !mm)) { + if (unlikely(faulthandler_disabled() || !mm)) { bad_area_nosemaphore(regs, error_code, address); return; } diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c index 4500142bc4aa..eecb207a2037 100644 --- a/arch/x86/mm/highmem_32.c +++ b/arch/x86/mm/highmem_32.c @@ -35,7 +35,7 @@ void *kmap_atomic_prot(struct page *page, pgprot_t prot) unsigned long vaddr; int idx, type; - /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */ + preempt_disable(); pagefault_disable(); if (!PageHighMem(page)) @@ -100,6 +100,7 @@ void __kunmap_atomic(void *kvaddr) #endif pagefault_enable(); + preempt_enable(); } EXPORT_SYMBOL(__kunmap_atomic); diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c index 9ca35fc60cfe..2b7ece0e103a 100644 --- a/arch/x86/mm/iomap_32.c +++ b/arch/x86/mm/iomap_32.c @@ -59,6 +59,7 @@ void *kmap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot) unsigned long vaddr; int idx, type; + preempt_disable(); pagefault_disable(); type = kmap_atomic_idx_push(); @@ -117,5 +118,6 @@ iounmap_atomic(void __iomem *kvaddr) } pagefault_enable(); + preempt_enable(); } EXPORT_SYMBOL_GPL(iounmap_atomic); diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 70e7444c6835..27ff21216dfa 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -353,18 +353,18 @@ void *xlate_dev_mem_ptr(phys_addr_t phys) { unsigned long start = phys & PAGE_MASK; unsigned long offset = phys & ~PAGE_MASK; - unsigned long vaddr; + void *vaddr; /* If page is RAM, we can use __va. Otherwise ioremap and unmap. */ if (page_is_ram(start >> PAGE_SHIFT)) return __va(phys); - vaddr = (unsigned long)ioremap_cache(start, PAGE_SIZE); + vaddr = ioremap_cache(start, PAGE_SIZE); /* Only add the offset on success and return NULL if the ioremap() failed: */ if (vaddr) vaddr += offset; - return (void *)vaddr; + return vaddr; } void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr) @@ -373,7 +373,6 @@ void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr) return; iounmap((void __iomem *)((unsigned long)addr & PAGE_MASK)); - return; } static pte_t bm_pte[PAGE_SIZE/sizeof(pte_t)] __page_aligned_bss; diff --git a/arch/x86/um/asm/barrier.h b/arch/x86/um/asm/barrier.h index 7e8a1a650435..b9531d343134 100644 --- a/arch/x86/um/asm/barrier.h +++ b/arch/x86/um/asm/barrier.h @@ -39,7 +39,8 @@ #define smp_mb() barrier() #define smp_rmb() barrier() #define smp_wmb() barrier() -#define set_mb(var, value) do { var = value; barrier(); } while (0) + +#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); barrier(); } while (0) #define read_barrier_depends() do { } while (0) #define smp_read_barrier_depends() do { } while (0) diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c index 956374c1edbc..9e2ba5c6e1dd 100644 --- a/arch/x86/xen/spinlock.c +++ b/arch/x86/xen/spinlock.c @@ -17,6 +17,56 @@ #include "xen-ops.h" #include "debugfs.h" +static DEFINE_PER_CPU(int, lock_kicker_irq) = -1; +static DEFINE_PER_CPU(char *, irq_name); +static bool xen_pvspin = true; + +#ifdef CONFIG_QUEUED_SPINLOCKS + +#include <asm/qspinlock.h> + +static void xen_qlock_kick(int cpu) +{ + xen_send_IPI_one(cpu, XEN_SPIN_UNLOCK_VECTOR); +} + +/* + * Halt the current CPU & release it back to the host + */ +static void xen_qlock_wait(u8 *byte, u8 val) +{ + int irq = __this_cpu_read(lock_kicker_irq); + + /* If kicker interrupts not initialized yet, just spin */ + if (irq == -1) + return; + + /* clear pending */ + xen_clear_irq_pending(irq); + barrier(); + + /* + * We check the byte value after clearing pending IRQ to make sure + * that we won't miss a wakeup event because of the clearing. + * + * The sync_clear_bit() call in xen_clear_irq_pending() is atomic. + * So it is effectively a memory barrier for x86. + */ + if (READ_ONCE(*byte) != val) + return; + + /* + * If an interrupt happens here, it will leave the wakeup irq + * pending, which will cause xen_poll_irq() to return + * immediately. + */ + + /* Block until irq becomes pending (or perhaps a spurious wakeup) */ + xen_poll_irq(irq); +} + +#else /* CONFIG_QUEUED_SPINLOCKS */ + enum xen_contention_stat { TAKEN_SLOW, TAKEN_SLOW_PICKUP, @@ -100,12 +150,9 @@ struct xen_lock_waiting { __ticket_t want; }; -static DEFINE_PER_CPU(int, lock_kicker_irq) = -1; -static DEFINE_PER_CPU(char *, irq_name); static DEFINE_PER_CPU(struct xen_lock_waiting, lock_waiting); static cpumask_t waiting_cpus; -static bool xen_pvspin = true; __visible void xen_lock_spinning(struct arch_spinlock *lock, __ticket_t want) { int irq = __this_cpu_read(lock_kicker_irq); @@ -217,6 +264,7 @@ static void xen_unlock_kick(struct arch_spinlock *lock, __ticket_t next) } } } +#endif /* CONFIG_QUEUED_SPINLOCKS */ static irqreturn_t dummy_handler(int irq, void *dev_id) { @@ -280,8 +328,16 @@ void __init xen_init_spinlocks(void) return; } printk(KERN_DEBUG "xen: PV spinlocks enabled\n"); +#ifdef CONFIG_QUEUED_SPINLOCKS + __pv_init_lock_hash(); + pv_lock_ops.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath; + pv_lock_ops.queued_spin_unlock = PV_CALLEE_SAVE(__pv_queued_spin_unlock); + pv_lock_ops.wait = xen_qlock_wait; + pv_lock_ops.kick = xen_qlock_kick; +#else pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(xen_lock_spinning); pv_lock_ops.unlock_kick = xen_unlock_kick; +#endif } /* @@ -310,7 +366,7 @@ static __init int xen_parse_nopvspin(char *arg) } early_param("xen_nopvspin", xen_parse_nopvspin); -#ifdef CONFIG_XEN_DEBUG_FS +#if defined(CONFIG_XEN_DEBUG_FS) && !defined(CONFIG_QUEUED_SPINLOCKS) static struct dentry *d_spin_debug; |