diff options
Diffstat (limited to 'include/linux/perf_event.h')
| -rw-r--r-- | include/linux/perf_event.h | 262 |
1 files changed, 186 insertions, 76 deletions
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index d2a15c0c6f8a..5a9bf15d4461 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -168,6 +168,15 @@ struct hw_perf_event { struct hw_perf_event_extra extra_reg; struct hw_perf_event_extra branch_reg; }; + struct { /* aux / Intel-PT */ + u64 aux_config; + /* + * For AUX area events, aux_paused cannot be a state + * flag because it can be updated asynchronously to + * state. + */ + unsigned int aux_paused; + }; struct { /* software */ struct hrtimer hrtimer; }; @@ -291,6 +300,20 @@ struct perf_event_pmu_context; #define PERF_PMU_CAP_NO_EXCLUDE 0x0040 #define PERF_PMU_CAP_AUX_OUTPUT 0x0080 #define PERF_PMU_CAP_EXTENDED_HW_TYPE 0x0100 +#define PERF_PMU_CAP_AUX_PAUSE 0x0200 + +/** + * pmu::scope + */ +enum perf_pmu_scope { + PERF_PMU_SCOPE_NONE = 0, + PERF_PMU_SCOPE_CORE, + PERF_PMU_SCOPE_DIE, + PERF_PMU_SCOPE_CLUSTER, + PERF_PMU_SCOPE_PKG, + PERF_PMU_SCOPE_SYS_WIDE, + PERF_PMU_MAX_SCOPE, +}; struct perf_output_handle; @@ -315,8 +338,12 @@ struct pmu { */ int capabilities; - int __percpu *pmu_disable_count; - struct perf_cpu_pmu_context __percpu *cpu_pmu_context; + /* + * PMU scope + */ + unsigned int scope; + + struct perf_cpu_pmu_context * __percpu *cpu_pmu_context; atomic_t exclusive_cnt; /* < 0: cpu; > 0: tsk */ int task_ctx_nr; int hrtimer_interval_ms; @@ -363,6 +390,8 @@ struct pmu { #define PERF_EF_START 0x01 /* start the counter when adding */ #define PERF_EF_RELOAD 0x02 /* reload the counter when starting */ #define PERF_EF_UPDATE 0x04 /* update the counter when stopping */ +#define PERF_EF_PAUSE 0x08 /* AUX area event, pause tracing */ +#define PERF_EF_RESUME 0x10 /* AUX area event, resume tracing */ /* * Adds/Removes a counter to/from the PMU, can be done inside a @@ -402,6 +431,18 @@ struct pmu { * * ->start() with PERF_EF_RELOAD will reprogram the counter * value, must be preceded by a ->stop() with PERF_EF_UPDATE. + * + * ->stop() with PERF_EF_PAUSE will stop as simply as possible. Will not + * overlap another ->stop() with PERF_EF_PAUSE nor ->start() with + * PERF_EF_RESUME. + * + * ->start() with PERF_EF_RESUME will start as simply as possible but + * only if the counter is not otherwise stopped. Will not overlap + * another ->start() with PERF_EF_RESUME nor ->stop() with + * PERF_EF_PAUSE. + * + * Notably, PERF_EF_PAUSE/PERF_EF_RESUME *can* be concurrent with other + * ->stop()/->start() invocations, just not itself. */ void (*start) (struct perf_event *event, int flags); void (*stop) (struct perf_event *event, int flags); @@ -453,7 +494,7 @@ struct pmu { * context-switches callback */ void (*sched_task) (struct perf_event_pmu_context *pmu_ctx, - bool sched_in); + struct task_struct *task, bool sched_in); /* * Kmem cache of PMU specific data @@ -461,16 +502,6 @@ struct pmu { struct kmem_cache *task_ctx_cache; /* - * PMU specific parts of task perf event context (i.e. ctx->task_ctx_data) - * can be synchronized using this function. See Intel LBR callstack support - * implementation and Perf core context switch handling callbacks for usage - * examples. - */ - void (*swap_task_ctx) (struct perf_event_pmu_context *prev_epc, - struct perf_event_pmu_context *next_epc); - /* optional */ - - /* * Set up pmu-private data structures for an AUX area */ void *(*setup_aux) (struct perf_event *event, void **pages, @@ -615,10 +646,13 @@ typedef void (*perf_overflow_handler_t)(struct perf_event *, * PERF_EV_CAP_SIBLING: An event with this flag must be a group sibling and * cannot be a group leader. If an event with this flag is detached from the * group it is scheduled out and moved into an unrecoverable ERROR state. + * PERF_EV_CAP_READ_SCOPE: A CPU event that can be read from any CPU of the + * PMU scope where it is active. */ #define PERF_EV_CAP_SOFTWARE BIT(0) #define PERF_EV_CAP_READ_ACTIVE_PKG BIT(1) #define PERF_EV_CAP_SIBLING BIT(2) +#define PERF_EV_CAP_READ_SCOPE BIT(3) #define SWEVENT_HLIST_BITS 8 #define SWEVENT_HLIST_SIZE (1 << SWEVENT_HLIST_BITS) @@ -628,13 +662,16 @@ struct swevent_hlist { struct rcu_head rcu_head; }; -#define PERF_ATTACH_CONTEXT 0x01 -#define PERF_ATTACH_GROUP 0x02 -#define PERF_ATTACH_TASK 0x04 -#define PERF_ATTACH_TASK_DATA 0x08 -#define PERF_ATTACH_ITRACE 0x10 -#define PERF_ATTACH_SCHED_CB 0x20 -#define PERF_ATTACH_CHILD 0x40 +#define PERF_ATTACH_CONTEXT 0x0001 +#define PERF_ATTACH_GROUP 0x0002 +#define PERF_ATTACH_TASK 0x0004 +#define PERF_ATTACH_TASK_DATA 0x0008 +#define PERF_ATTACH_GLOBAL_DATA 0x0010 +#define PERF_ATTACH_SCHED_CB 0x0020 +#define PERF_ATTACH_CHILD 0x0040 +#define PERF_ATTACH_EXCLUSIVE 0x0080 +#define PERF_ATTACH_CALLCHAIN 0x0100 +#define PERF_ATTACH_ITRACE 0x0200 struct bpf_prog; struct perf_cgroup; @@ -781,11 +818,12 @@ struct perf_event { unsigned int pending_wakeup; unsigned int pending_kill; unsigned int pending_disable; - unsigned int pending_sigtrap; unsigned long pending_addr; /* SIGTRAP */ struct irq_work pending_irq; + struct irq_work pending_disable_irq; struct callback_head pending_task; unsigned int pending_work; + struct rcuwait pending_work_wait; atomic_t event_limit; @@ -809,11 +847,8 @@ struct perf_event { u64 (*clock)(void); perf_overflow_handler_t overflow_handler; void *overflow_handler_context; -#ifdef CONFIG_BPF_SYSCALL - perf_overflow_handler_t orig_overflow_handler; struct bpf_prog *prog; u64 bpf_cookie; -#endif #ifdef CONFIG_EVENT_TRACING struct trace_event_call *tp_event; @@ -878,16 +913,16 @@ struct perf_event_pmu_context { struct list_head pinned_active; struct list_head flexible_active; - /* Used to avoid freeing per-cpu perf_event_pmu_context */ + /* Used to identify the per-cpu perf_event_pmu_context */ unsigned int embedded : 1; unsigned int nr_events; unsigned int nr_cgroups; + unsigned int nr_freq; atomic_t refcount; /* event <-> epc */ struct rcu_head rcu_head; - void *task_ctx_data; /* pmu specific data */ /* * Set when one or more (plausibly active) event can't be scheduled * due to pmu overcommit or pmu constraints, except tolerant to @@ -897,6 +932,11 @@ struct perf_event_pmu_context { int rotate_necessary; }; +static inline bool perf_pmu_ctx_is_active(struct perf_event_pmu_context *epc) +{ + return !list_empty(&epc->flexible_active) || !list_empty(&epc->pinned_active); +} + struct perf_event_groups { struct rb_root tree; u64 index; @@ -930,7 +970,6 @@ struct perf_event_context { int nr_user; int is_active; - int nr_task_data; int nr_stat; int nr_freq; int rotate_disable; @@ -959,19 +998,52 @@ struct perf_event_context { struct rcu_head rcu_head; /* - * Sum (event->pending_sigtrap + event->pending_work) + * The count of events for which using the switch-out fast path + * should be avoided. + * + * Sum (event->pending_work + events with + * (attr->inherit && (attr->sample_type & PERF_SAMPLE_READ))) * * The SIGTRAP is targeted at ctx->task, as such it won't do changing * that until the signal is delivered. */ - local_t nr_pending; + local_t nr_no_switch_fast; }; -/* - * Number of contexts where an event can trigger: - * task, softirq, hardirq, nmi. +/** + * struct perf_ctx_data - PMU specific data for a task + * @rcu_head: To avoid the race on free PMU specific data + * @refcount: To track users + * @global: To track system-wide users + * @ctx_cache: Kmem cache of PMU specific data + * @data: PMU specific data + * + * Currently, the struct is only used in Intel LBR call stack mode to + * save/restore the call stack of a task on context switches. + * + * The rcu_head is used to prevent the race on free the data. + * The data only be allocated when Intel LBR call stack mode is enabled. + * The data will be freed when the mode is disabled. + * The content of the data will only be accessed in context switch, which + * should be protected by rcu_read_lock(). + * + * Because of the alignment requirement of Intel Arch LBR, the Kmem cache + * is used to allocate the PMU specific data. The ctx_cache is to track + * the Kmem cache. + * + * Careful: Struct perf_ctx_data is added as a pointer in struct task_struct. + * When system-wide Intel LBR call stack mode is enabled, a buffer with + * constant size will be allocated for each task. + * Also, system memory consumption can further grow when the size of + * struct perf_ctx_data enlarges. */ -#define PERF_NR_CONTEXTS 4 +struct perf_ctx_data { + struct rcu_head rcu_head; + refcount_t refcount; + int global; + struct kmem_cache *ctx_cache; + void *data; +}; struct perf_cpu_pmu_context { struct perf_event_pmu_context epc; @@ -982,6 +1054,7 @@ struct perf_cpu_pmu_context { int active_oncpu; int exclusive; + int pmu_disable_count; raw_spinlock_t hrtimer_lock; struct hrtimer hrtimer; @@ -1015,7 +1088,13 @@ struct perf_output_handle { struct perf_buffer *rb; unsigned long wakeup; unsigned long size; - u64 aux_flags; + union { + u64 flags; /* perf_output*() */ + u64 aux_flags; /* perf_aux_output*() */ + struct { + u64 skip_read : 1; + }; + }; union { void *addr; unsigned long head; @@ -1232,6 +1311,11 @@ static inline void perf_sample_save_callchain(struct perf_sample_data *data, { int size = 1; + if (!(event->attr.sample_type & PERF_SAMPLE_CALLCHAIN)) + return; + if (WARN_ON_ONCE(data->sample_flags & PERF_SAMPLE_CALLCHAIN)) + return; + data->callchain = perf_callchain(event, regs); size += data->callchain->nr; @@ -1240,12 +1324,18 @@ static inline void perf_sample_save_callchain(struct perf_sample_data *data, } static inline void perf_sample_save_raw_data(struct perf_sample_data *data, + struct perf_event *event, struct perf_raw_record *raw) { struct perf_raw_frag *frag = &raw->frag; u32 sum = 0; int size; + if (!(event->attr.sample_type & PERF_SAMPLE_RAW)) + return; + if (WARN_ON_ONCE(data->sample_flags & PERF_SAMPLE_RAW)) + return; + do { sum += frag->size; if (perf_raw_frag_last(frag)) @@ -1262,6 +1352,11 @@ static inline void perf_sample_save_raw_data(struct perf_sample_data *data, data->sample_flags |= PERF_SAMPLE_RAW; } +static inline bool has_branch_stack(struct perf_event *event) +{ + return event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK; +} + static inline void perf_sample_save_brstack(struct perf_sample_data *data, struct perf_event *event, struct perf_branch_stack *brs, @@ -1269,8 +1364,16 @@ static inline void perf_sample_save_brstack(struct perf_sample_data *data, { int size = sizeof(u64); /* nr */ + if (!has_branch_stack(event)) + return; + if (WARN_ON_ONCE(data->sample_flags & PERF_SAMPLE_BRANCH_STACK)) + return; + if (branch_sample_hw_index(event)) size += sizeof(u64); + + brs->nr = min_t(u16, event->attr.sample_max_stack, brs->nr); + size += brs->nr * sizeof(struct perf_branch_entry); /* @@ -1342,8 +1445,10 @@ extern int perf_event_output(struct perf_event *event, struct pt_regs *regs); static inline bool -__is_default_overflow_handler(perf_overflow_handler_t overflow_handler) +is_default_overflow_handler(struct perf_event *event) { + perf_overflow_handler_t overflow_handler = event->overflow_handler; + if (likely(overflow_handler == perf_event_output_forward)) return true; if (unlikely(overflow_handler == perf_event_output_backward)) @@ -1351,22 +1456,6 @@ __is_default_overflow_handler(perf_overflow_handler_t overflow_handler) return false; } -#define is_default_overflow_handler(event) \ - __is_default_overflow_handler((event)->overflow_handler) - -#ifdef CONFIG_BPF_SYSCALL -static inline bool uses_default_overflow_handler(struct perf_event *event) -{ - if (likely(is_default_overflow_handler(event))) - return true; - - return __is_default_overflow_handler(event->orig_overflow_handler); -} -#else -#define uses_default_overflow_handler(event) \ - is_default_overflow_handler(event) -#endif - extern void perf_event_header__init_id(struct perf_event_header *header, struct perf_sample_data *data, @@ -1592,19 +1681,10 @@ static inline int perf_callchain_store(struct perf_callchain_entry_ctx *ctx, u64 } extern int sysctl_perf_event_paranoid; -extern int sysctl_perf_event_mlock; extern int sysctl_perf_event_sample_rate; -extern int sysctl_perf_cpu_time_max_percent; extern void perf_sample_event_took(u64 sample_len_ns); -int perf_event_max_sample_rate_handler(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); -int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); -int perf_event_max_stack_handler(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); - /* Access to perf_event_open(2) syscall. */ #define PERF_SECURITY_OPEN 0 @@ -1618,30 +1698,26 @@ static inline int perf_is_paranoid(void) return sysctl_perf_event_paranoid > -1; } -static inline int perf_allow_kernel(struct perf_event_attr *attr) -{ - if (sysctl_perf_event_paranoid > 1 && !perfmon_capable()) - return -EACCES; - - return security_perf_event_open(attr, PERF_SECURITY_KERNEL); -} +int perf_allow_kernel(void); -static inline int perf_allow_cpu(struct perf_event_attr *attr) +static inline int perf_allow_cpu(void) { if (sysctl_perf_event_paranoid > 0 && !perfmon_capable()) return -EACCES; - return security_perf_event_open(attr, PERF_SECURITY_CPU); + return security_perf_event_open(PERF_SECURITY_CPU); } -static inline int perf_allow_tracepoint(struct perf_event_attr *attr) +static inline int perf_allow_tracepoint(void) { if (sysctl_perf_event_paranoid > -1 && !perfmon_capable()) return -EPERM; - return security_perf_event_open(attr, PERF_SECURITY_TRACEPOINT); + return security_perf_event_open(PERF_SECURITY_TRACEPOINT); } +extern int perf_exclude_event(struct perf_event *event, struct pt_regs *regs); + extern void perf_event_init(void); extern void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size, struct pt_regs *regs, @@ -1649,19 +1725,34 @@ extern void perf_tp_event(u16 event_type, u64 count, void *record, struct task_struct *task); extern void perf_bp_event(struct perf_event *event, void *data); -#ifndef perf_misc_flags -# define perf_misc_flags(regs) \ +extern unsigned long perf_misc_flags(struct perf_event *event, struct pt_regs *regs); +extern unsigned long perf_instruction_pointer(struct perf_event *event, + struct pt_regs *regs); + +#ifndef perf_arch_misc_flags +# define perf_arch_misc_flags(regs) \ (user_mode(regs) ? PERF_RECORD_MISC_USER : PERF_RECORD_MISC_KERNEL) -# define perf_instruction_pointer(regs) instruction_pointer(regs) +# define perf_arch_instruction_pointer(regs) instruction_pointer(regs) #endif #ifndef perf_arch_bpf_user_pt_regs # define perf_arch_bpf_user_pt_regs(regs) regs #endif -static inline bool has_branch_stack(struct perf_event *event) +#ifndef perf_arch_guest_misc_flags +static inline unsigned long perf_arch_guest_misc_flags(struct pt_regs *regs) { - return event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK; + unsigned long guest_state = perf_guest_state(); + + if (!(guest_state & PERF_GUEST_ACTIVE)) + return 0; + + if (guest_state & PERF_GUEST_USER) + return PERF_RECORD_MISC_GUEST_USER; + else + return PERF_RECORD_MISC_GUEST_KERNEL; } +# define perf_arch_guest_misc_flags(regs) perf_arch_guest_misc_flags(regs) +#endif static inline bool needs_branch_stack(struct perf_event *event) { @@ -1673,6 +1764,13 @@ static inline bool has_aux(struct perf_event *event) return event->pmu->setup_aux; } +static inline bool has_aux_action(struct perf_event *event) +{ + return event->attr.aux_sample_size || + event->attr.aux_pause || + event->attr.aux_resume; +} + static inline bool is_write_backward(struct perf_event *event) { return !!event->attr.write_backward; @@ -1697,6 +1795,14 @@ perf_event_addr_filters(struct perf_event *event) return ifh; } +static inline struct fasync_struct **perf_event_fasync(struct perf_event *event) +{ + /* Only the parent has fasync state */ + if (event->parent) + event = event->parent; + return &event->fasync; +} + extern void perf_event_addr_filters_sync(struct perf_event *event); extern void perf_report_aux_output_id(struct perf_event *event, u64 hw_id); @@ -1817,6 +1923,10 @@ static inline u64 perf_event_pause(struct perf_event *event, bool reset) { return 0; } +static inline int perf_exclude_event(struct perf_event *event, struct pt_regs *regs) +{ + return 0; +} #endif #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL) |