diff options
Diffstat (limited to 'include/linux/perf_event.h')
| -rw-r--r-- | include/linux/perf_event.h | 521 |
1 files changed, 333 insertions, 188 deletions
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index d2a15c0c6f8a..52dc7cfab0e0 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -26,18 +26,9 @@ # include <asm/local64.h> #endif -#define PERF_GUEST_ACTIVE 0x01 -#define PERF_GUEST_USER 0x02 - -struct perf_guest_info_callbacks { - unsigned int (*state)(void); - unsigned long (*get_ip)(void); - unsigned int (*handle_intel_pt_intr)(void); -}; - #ifdef CONFIG_HAVE_HW_BREAKPOINT -#include <linux/rhashtable-types.h> -#include <asm/hw_breakpoint.h> +# include <linux/rhashtable-types.h> +# include <asm/hw_breakpoint.h> #endif #include <linux/list.h> @@ -62,19 +53,20 @@ struct perf_guest_info_callbacks { #include <linux/security.h> #include <linux/static_call.h> #include <linux/lockdep.h> + #include <asm/local.h> struct perf_callchain_entry { - __u64 nr; - __u64 ip[]; /* /proc/sys/kernel/perf_event_max_stack */ + u64 nr; + u64 ip[]; /* /proc/sys/kernel/perf_event_max_stack */ }; struct perf_callchain_entry_ctx { - struct perf_callchain_entry *entry; - u32 max_stack; - u32 nr; - short contexts; - bool contexts_maxed; + struct perf_callchain_entry *entry; + u32 max_stack; + u32 nr; + short contexts; + bool contexts_maxed; }; typedef unsigned long (*perf_copy_f)(void *dst, const void *src, @@ -121,8 +113,8 @@ static __always_inline bool perf_raw_frag_last(const struct perf_raw_frag *frag) * already stored in age order, the hw_idx should be 0. */ struct perf_branch_stack { - __u64 nr; - __u64 hw_idx; + u64 nr; + u64 hw_idx; struct perf_branch_entry entries[]; }; @@ -132,10 +124,10 @@ struct task_struct; * extra PMU register associated with an event */ struct hw_perf_event_extra { - u64 config; /* register value */ - unsigned int reg; /* register address or index */ - int alloc; /* extra register already allocated */ - int idx; /* index in shared_regs->regs[] */ + u64 config; /* register value */ + unsigned int reg; /* register address or index */ + int alloc; /* extra register already allocated */ + int idx; /* index in shared_regs->regs[] */ }; /** @@ -144,8 +136,8 @@ struct hw_perf_event_extra { * PERF_EVENT_FLAG_ARCH bits are reserved for architecture-specific * usage. */ -#define PERF_EVENT_FLAG_ARCH 0x000fffff -#define PERF_EVENT_FLAG_USER_READ_CNT 0x80000000 +#define PERF_EVENT_FLAG_ARCH 0x0fffffff +#define PERF_EVENT_FLAG_USER_READ_CNT 0x80000000 static_assert((PERF_EVENT_FLAG_USER_READ_CNT & PERF_EVENT_FLAG_ARCH) == 0); @@ -157,7 +149,9 @@ struct hw_perf_event { union { struct { /* hardware */ u64 config; + u64 config1; u64 last_tag; + u64 dyn_constraint; unsigned long config_base; unsigned long event_base; int event_base_rdpmc; @@ -168,6 +162,15 @@ 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; }; @@ -216,9 +219,14 @@ struct hw_perf_event { /* * hw_perf_event::state flags; used to track the PERF_EF_* state. */ -#define PERF_HES_STOPPED 0x01 /* the counter is stopped */ -#define PERF_HES_UPTODATE 0x02 /* event->count up-to-date */ -#define PERF_HES_ARCH 0x04 + +/* the counter is stopped */ +#define PERF_HES_STOPPED 0x01 + +/* event->count up-to-date */ +#define PERF_HES_UPTODATE 0x02 + +#define PERF_HES_ARCH 0x04 int state; @@ -267,7 +275,7 @@ struct hw_perf_event { */ u64 freq_time_stamp; u64 freq_count_stamp; -#endif +#endif /* CONFIG_PERF_EVENTS */ }; struct perf_event; @@ -276,21 +284,40 @@ struct perf_event_pmu_context; /* * Common implementation detail of pmu::{start,commit,cancel}_txn */ -#define PERF_PMU_TXN_ADD 0x1 /* txn to add/schedule event on PMU */ -#define PERF_PMU_TXN_READ 0x2 /* txn to read event group from PMU */ + +/* txn to add/schedule event on PMU */ +#define PERF_PMU_TXN_ADD 0x1 + +/* txn to read event group from PMU */ +#define PERF_PMU_TXN_READ 0x2 /** * pmu::capabilities flags */ -#define PERF_PMU_CAP_NO_INTERRUPT 0x0001 -#define PERF_PMU_CAP_NO_NMI 0x0002 -#define PERF_PMU_CAP_AUX_NO_SG 0x0004 -#define PERF_PMU_CAP_EXTENDED_REGS 0x0008 -#define PERF_PMU_CAP_EXCLUSIVE 0x0010 -#define PERF_PMU_CAP_ITRACE 0x0020 -#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_NO_INTERRUPT 0x0001 +#define PERF_PMU_CAP_NO_NMI 0x0002 +#define PERF_PMU_CAP_AUX_NO_SG 0x0004 +#define PERF_PMU_CAP_EXTENDED_REGS 0x0008 +#define PERF_PMU_CAP_EXCLUSIVE 0x0010 +#define PERF_PMU_CAP_ITRACE 0x0020 +#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 +#define PERF_PMU_CAP_AUX_PREFER_LARGE 0x0400 + +/** + * 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; @@ -302,6 +329,9 @@ struct perf_output_handle; struct pmu { struct list_head entry; + spinlock_t events_lock; + struct list_head events; + struct module *module; struct device *dev; struct device *parent; @@ -315,8 +345,12 @@ 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; @@ -360,9 +394,21 @@ struct pmu { * Flags for ->add()/->del()/ ->start()/->stop(). There are * matching hw_perf_event::state flags. */ -#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 */ + +/* start the counter when adding */ +#define PERF_EF_START 0x01 + +/* reload the counter when starting */ +#define PERF_EF_RELOAD 0x02 + +/* update the counter when stopping */ +#define PERF_EF_UPDATE 0x04 + +/* AUX area event, pause tracing */ +#define PERF_EF_PAUSE 0x08 + +/* AUX area event, resume tracing */ +#define PERF_EF_RESUME 0x10 /* * Adds/Removes a counter to/from the PMU, can be done inside a @@ -402,6 +448,18 @@ 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 +511,7 @@ 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 +519,6 @@ 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, @@ -559,10 +607,10 @@ enum perf_addr_filter_action_t { * This is a hardware-agnostic filter configuration as specified by the user. */ struct perf_addr_filter { - struct list_head entry; - struct path path; - unsigned long offset; - unsigned long size; + struct list_head entry; + struct path path; + unsigned long offset; + unsigned long size; enum perf_addr_filter_action_t action; }; @@ -577,23 +625,24 @@ struct perf_addr_filter { * bundled together; see perf_event_addr_filters(). */ struct perf_addr_filters_head { - struct list_head list; - raw_spinlock_t lock; - unsigned int nr_file_filters; + struct list_head list; + raw_spinlock_t lock; + unsigned int nr_file_filters; }; struct perf_addr_filter_range { - unsigned long start; - unsigned long size; + unsigned long start; + unsigned long size; }; /** * enum perf_event_state - the states of an event: */ enum perf_event_state { - PERF_EVENT_STATE_DEAD = -4, - PERF_EVENT_STATE_EXIT = -3, - PERF_EVENT_STATE_ERROR = -2, + PERF_EVENT_STATE_DEAD = -5, + PERF_EVENT_STATE_REVOKED = -4, /* pmu gone, must not touch */ + PERF_EVENT_STATE_EXIT = -3, /* task died, still inherit */ + PERF_EVENT_STATE_ERROR = -2, /* scheduling error, can enable */ PERF_EVENT_STATE_OFF = -1, PERF_EVENT_STATE_INACTIVE = 0, PERF_EVENT_STATE_ACTIVE = 1, @@ -615,10 +664,13 @@ 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) @@ -628,21 +680,24 @@ 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; struct perf_buffer; struct pmu_event_list { - raw_spinlock_t lock; - struct list_head list; + raw_spinlock_t lock; + struct list_head list; }; /* @@ -652,12 +707,12 @@ struct pmu_event_list { * disabled is sufficient since it will hold-off the IPIs. */ #ifdef CONFIG_PROVE_LOCKING -#define lockdep_assert_event_ctx(event) \ +# define lockdep_assert_event_ctx(event) \ WARN_ON_ONCE(__lockdep_enabled && \ (this_cpu_read(hardirqs_enabled) && \ lockdep_is_held(&(event)->ctx->mutex) != LOCK_STATE_HELD)) #else -#define lockdep_assert_event_ctx(event) +# define lockdep_assert_event_ctx(event) #endif #define for_each_sibling_event(sibling, event) \ @@ -781,9 +836,9 @@ 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; @@ -809,18 +864,15 @@ 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; struct event_filter *filter; -#ifdef CONFIG_FUNCTION_TRACER +# ifdef CONFIG_FUNCTION_TRACER struct ftrace_ops ftrace_ops; -#endif +# endif #endif #ifdef CONFIG_CGROUP_PERF @@ -831,6 +883,7 @@ struct perf_event { void *security; #endif struct list_head sb_list; + struct list_head pmu_list; /* * Certain events gets forwarded to another pmu internally by over- @@ -838,7 +891,7 @@ struct perf_event { * of it. event->orig_type contains original 'type' requested by * user. */ - __u32 orig_type; + u32 orig_type; #endif /* CONFIG_PERF_EVENTS */ }; @@ -878,16 +931,16 @@ 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 @@ -897,9 +950,14 @@ 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; + struct rb_root tree; + u64 index; }; @@ -930,7 +988,6 @@ 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 +1016,52 @@ 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 +1072,7 @@ struct perf_cpu_pmu_context { int active_oncpu; int exclusive; + int pmu_disable_count; raw_spinlock_t hrtimer_lock; struct hrtimer hrtimer; @@ -1015,7 +1106,13 @@ 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; @@ -1077,7 +1174,7 @@ extern void perf_aux_output_flag(struct perf_output_handle *handle, u64 flags); extern void perf_event_itrace_started(struct perf_event *event); extern int perf_pmu_register(struct pmu *pmu, const char *name, int type); -extern void perf_pmu_unregister(struct pmu *pmu); +extern int perf_pmu_unregister(struct pmu *pmu); extern void __perf_event_task_sched_in(struct task_struct *prev, struct task_struct *task); @@ -1103,16 +1200,18 @@ extern void perf_pmu_resched(struct pmu *pmu); extern int perf_event_refresh(struct perf_event *event, int refresh); extern void perf_event_update_userpage(struct perf_event *event); extern int perf_event_release_kernel(struct perf_event *event); + extern struct perf_event * perf_event_create_kernel_counter(struct perf_event_attr *attr, - int cpu, - struct task_struct *task, - perf_overflow_handler_t callback, - void *context); + int cpu, + struct task_struct *task, + perf_overflow_handler_t callback, + void *context); + extern void perf_pmu_migrate_context(struct pmu *pmu, - int src_cpu, int dst_cpu); -int perf_event_read_local(struct perf_event *event, u64 *value, - u64 *enabled, u64 *running); + int src_cpu, int dst_cpu); +extern int perf_event_read_local(struct perf_event *event, u64 *value, + u64 *enabled, u64 *running); extern u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running); @@ -1232,6 +1331,11 @@ 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 +1344,18 @@ 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 +1372,11 @@ 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 +1384,16 @@ 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); /* @@ -1305,14 +1428,14 @@ static inline u32 perf_sample_data_size(struct perf_sample_data *data, */ static inline void perf_clear_branch_entry_bitfields(struct perf_branch_entry *br) { - br->mispred = 0; - br->predicted = 0; - br->in_tx = 0; - br->abort = 0; - br->cycles = 0; - br->type = 0; - br->spec = PERF_BR_SPEC_NA; - br->reserved = 0; + br->mispred = 0; + br->predicted = 0; + br->in_tx = 0; + br->abort = 0; + br->cycles = 0; + br->type = 0; + br->spec = PERF_BR_SPEC_NA; + br->reserved = 0; } extern void perf_output_sample(struct perf_output_handle *handle, @@ -1342,8 +1465,10 @@ 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 +1476,6 @@ __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, @@ -1515,7 +1624,17 @@ extern void perf_event_bpf_event(struct bpf_prog *prog, enum perf_bpf_event_type type, u16 flags); +#define PERF_GUEST_ACTIVE 0x01 +#define PERF_GUEST_USER 0x02 + +struct perf_guest_info_callbacks { + unsigned int (*state)(void); + unsigned long (*get_ip)(void); + unsigned int (*handle_intel_pt_intr)(void); +}; + #ifdef CONFIG_GUEST_PERF_EVENTS + extern struct perf_guest_info_callbacks __rcu *perf_guest_cbs; DECLARE_STATIC_CALL(__perf_guest_state, *perf_guest_cbs->state); @@ -1526,21 +1645,27 @@ static inline unsigned int perf_guest_state(void) { return static_call(__perf_guest_state)(); } + static inline unsigned long perf_guest_get_ip(void) { return static_call(__perf_guest_get_ip)(); } + static inline unsigned int perf_guest_handle_intel_pt_intr(void) { return static_call(__perf_guest_handle_intel_pt_intr)(); } + extern void perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *cbs); extern void perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *cbs); -#else + +#else /* !CONFIG_GUEST_PERF_EVENTS: */ + static inline unsigned int perf_guest_state(void) { return 0; } static inline unsigned long perf_guest_get_ip(void) { return 0; } static inline unsigned int perf_guest_handle_intel_pt_intr(void) { return 0; } -#endif /* CONFIG_GUEST_PERF_EVENTS */ + +#endif /* !CONFIG_GUEST_PERF_EVENTS */ extern void perf_event_exec(void); extern void perf_event_comm(struct task_struct *tsk, bool exec); @@ -1570,6 +1695,7 @@ static inline int perf_callchain_store_context(struct perf_callchain_entry_ctx * { if (ctx->contexts < sysctl_perf_event_max_contexts_per_stack) { struct perf_callchain_entry *entry = ctx->entry; + entry->ip[entry->nr++] = ip; ++ctx->contexts; return 0; @@ -1583,6 +1709,7 @@ static inline int perf_callchain_store(struct perf_callchain_entry_ctx *ctx, u64 { if (ctx->nr < ctx->max_stack && !ctx->contexts_maxed) { struct perf_callchain_entry *entry = ctx->entry; + entry->ip[entry->nr++] = ip; ++ctx->nr; return 0; @@ -1592,19 +1719,10 @@ 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 +1736,26 @@ 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; +extern int perf_allow_kernel(void); - return security_perf_event_open(attr, PERF_SECURITY_KERNEL); -} - -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 +1763,34 @@ 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) { @@ -1670,7 +1799,14 @@ static inline bool needs_branch_stack(struct perf_event *event) static inline bool has_aux(struct perf_event *event) { - return event->pmu->setup_aux; + return event->pmu && 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) @@ -1697,6 +1833,14 @@ 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); @@ -1714,7 +1858,7 @@ extern int perf_output_begin_backward(struct perf_output_handle *handle, extern void perf_output_end(struct perf_output_handle *handle); extern unsigned int perf_output_copy(struct perf_output_handle *handle, - const void *buf, unsigned int len); + const void *buf, unsigned int len); extern unsigned int perf_output_skip(struct perf_output_handle *handle, unsigned int len); extern long perf_output_copy_aux(struct perf_output_handle *aux_handle, @@ -1731,7 +1875,9 @@ extern void perf_event_task_tick(void); extern int perf_event_account_interrupt(struct perf_event *event); extern int perf_event_period(struct perf_event *event, u64 value); extern u64 perf_event_pause(struct perf_event *event, bool reset); + #else /* !CONFIG_PERF_EVENTS: */ + static inline void * perf_aux_output_begin(struct perf_output_handle *handle, struct perf_event *event) { return NULL; } @@ -1809,15 +1955,14 @@ static inline void perf_event_disable(struct perf_event *event) { } static inline int __perf_event_disable(void *info) { return -1; } static inline void perf_event_task_tick(void) { } static inline int perf_event_release_kernel(struct perf_event *event) { return 0; } -static inline int perf_event_period(struct perf_event *event, u64 value) -{ - return -EINVAL; -} -static inline u64 perf_event_pause(struct perf_event *event, bool reset) -{ - return 0; -} -#endif +static inline int +perf_event_period(struct perf_event *event, u64 value) { return -EINVAL; } +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 /* !CONFIG_PERF_EVENTS */ #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL) extern void perf_restore_debug_store(void); @@ -1825,31 +1970,31 @@ extern void perf_restore_debug_store(void); static inline void perf_restore_debug_store(void) { } #endif -#define perf_output_put(handle, x) perf_output_copy((handle), &(x), sizeof(x)) +#define perf_output_put(handle, x) perf_output_copy((handle), &(x), sizeof(x)) struct perf_pmu_events_attr { - struct device_attribute attr; - u64 id; - const char *event_str; + struct device_attribute attr; + u64 id; + const char *event_str; }; struct perf_pmu_events_ht_attr { - struct device_attribute attr; - u64 id; - const char *event_str_ht; - const char *event_str_noht; + struct device_attribute attr; + u64 id; + const char *event_str_ht; + const char *event_str_noht; }; struct perf_pmu_events_hybrid_attr { - struct device_attribute attr; - u64 id; - const char *event_str; - u64 pmu_type; + struct device_attribute attr; + u64 id; + const char *event_str; + u64 pmu_type; }; struct perf_pmu_format_hybrid_attr { - struct device_attribute attr; - u64 pmu_type; + struct device_attribute attr; + u64 pmu_type; }; ssize_t perf_event_sysfs_show(struct device *dev, struct device_attribute *attr, @@ -1891,11 +2036,11 @@ static struct device_attribute format_attr_##_name = __ATTR_RO(_name) /* Performance counter hotplug functions */ #ifdef CONFIG_PERF_EVENTS -int perf_event_init_cpu(unsigned int cpu); -int perf_event_exit_cpu(unsigned int cpu); +extern int perf_event_init_cpu(unsigned int cpu); +extern int perf_event_exit_cpu(unsigned int cpu); #else -#define perf_event_init_cpu NULL -#define perf_event_exit_cpu NULL +# define perf_event_init_cpu NULL +# define perf_event_exit_cpu NULL #endif extern void arch_perf_update_userpage(struct perf_event *event, |