/* * Performance events: * * Copyright (C) 2008-2009, Thomas Gleixner * Copyright (C) 2008-2009, Red Hat, Inc., Ingo Molnar * Copyright (C) 2008-2009, Red Hat, Inc., Peter Zijlstra * * Data type definitions, declarations, prototypes. * * Started by: Thomas Gleixner and Ingo Molnar * * For licencing details see kernel-base/COPYING */ #ifndef _LINUX_PERF_EVENT_H #define _LINUX_PERF_EVENT_H #include #include #include #ifdef CONFIG_HAVE_HW_BREAKPOINT #include #endif /* * User-space ABI bits: */ /* * attr.type */ enum perf_type_id { PERF_TYPE_HARDWARE = 0, PERF_TYPE_SOFTWARE = 1, PERF_TYPE_TRACEPOINT = 2, PERF_TYPE_HW_CACHE = 3, PERF_TYPE_RAW = 4, PERF_TYPE_BREAKPOINT = 5, PERF_TYPE_MAX, /* non-ABI */ }; /* * Generalized performance event event_id types, used by the * attr.event_id parameter of the sys_perf_event_open() * syscall: */ enum perf_hw_id { /* * Common hardware events, generalized by the kernel: */ PERF_COUNT_HW_CPU_CYCLES = 0, PERF_COUNT_HW_INSTRUCTIONS = 1, PERF_COUNT_HW_CACHE_REFERENCES = 2, PERF_COUNT_HW_CACHE_MISSES = 3, PERF_COUNT_HW_BRANCH_INSTRUCTIONS = 4, PERF_COUNT_HW_BRANCH_MISSES = 5, PERF_COUNT_HW_BUS_CYCLES = 6, PERF_COUNT_HW_MAX, /* non-ABI */ }; /* * Generalized hardware cache events: * * { L1-D, L1-I, LLC, ITLB, DTLB, BPU } x * { read, write, prefetch } x * { accesses, misses } */ enum perf_hw_cache_id { PERF_COUNT_HW_CACHE_L1D = 0, PERF_COUNT_HW_CACHE_L1I = 1, PERF_COUNT_HW_CACHE_LL = 2, PERF_COUNT_HW_CACHE_DTLB = 3, PERF_COUNT_HW_CACHE_ITLB = 4, PERF_COUNT_HW_CACHE_BPU = 5, PERF_COUNT_HW_CACHE_MAX, /* non-ABI */ }; enum perf_hw_cache_op_id { PERF_COUNT_HW_CACHE_OP_READ = 0, PERF_COUNT_HW_CACHE_OP_WRITE = 1, PERF_COUNT_HW_CACHE_OP_PREFETCH = 2, PERF_COUNT_HW_CACHE_OP_MAX, /* non-ABI */ }; enum perf_hw_cache_op_result_id { PERF_COUNT_HW_CACHE_RESULT_ACCESS = 0, PERF_COUNT_HW_CACHE_RESULT_MISS = 1, PERF_COUNT_HW_CACHE_RESULT_MAX, /* non-ABI */ }; /* * Special "software" events provided by the kernel, even if the hardware * does not support performance events. These events measure various * physical and sw events of the kernel (and allow the profiling of them as * well): */ enum perf_sw_ids { PERF_COUNT_SW_CPU_CLOCK = 0, PERF_COUNT_SW_TASK_CLOCK = 1, PERF_COUNT_SW_PAGE_FAULTS = 2, PERF_COUNT_SW_CONTEXT_SWITCHES = 3, PERF_COUNT_SW_CPU_MIGRATIONS = 4, PERF_COUNT_SW_PAGE_FAULTS_MIN = 5, PERF_COUNT_SW_PAGE_FAULTS_MAJ = 6, PERF_COUNT_SW_ALIGNMENT_FAULTS = 7, PERF_COUNT_SW_EMULATION_FAULTS = 8, PERF_COUNT_SW_MAX, /* non-ABI */ }; /* * Bits that can be set in attr.sample_type to request information * in the overflow packets. */ enum perf_event_sample_format { PERF_SAMPLE_IP = 1U << 0, PERF_SAMPLE_TID = 1U << 1, PERF_SAMPLE_TIME = 1U << 2, PERF_SAMPLE_ADDR = 1U << 3, PERF_SAMPLE_READ = 1U << 4, PERF_SAMPLE_CALLCHAIN = 1U << 5, PERF_SAMPLE_ID = 1U << 6, PERF_SAMPLE_CPU = 1U << 7, PERF_SAMPLE_PERIOD = 1U << 8, PERF_SAMPLE_STREAM_ID = 1U << 9, PERF_SAMPLE_RAW = 1U << 10, PERF_SAMPLE_MAX = 1U << 11, /* non-ABI */ }; /* * The format of the data returned by read() on a perf event fd, * as specified by attr.read_format: * * struct read_format { * { u64 value; * { u64 time_enabled; } && PERF_FORMAT_ENABLED * { u64 time_running; } && PERF_FORMAT_RUNNING * { u64 id; } && PERF_FORMAT_ID * } && !PERF_FORMAT_GROUP * * { u64 nr; * { u64 time_enabled; } && PERF_FORMAT_ENABLED * { u64 time_running; } && PERF_FORMAT_RUNNING * { u64 value; * { u64 id; } && PERF_FORMAT_ID * } cntr[nr]; * } && PERF_FORMAT_GROUP * }; */ enum perf_event_read_format { PERF_FORMAT_TOTAL_TIME_ENABLED = 1U << 0, PERF_FORMAT_TOTAL_TIME_RUNNING = 1U << 1, PERF_FORMAT_ID = 1U << 2, PERF_FORMAT_GROUP = 1U << 3, PERF_FORMAT_MAX = 1U << 4, /* non-ABI */ }; #define PERF_ATTR_SIZE_VER0 64 /* sizeof first published struct */ /* * Hardware event_id to monitor via a performance monitoring event: */ struct perf_event_attr { /* * Major type: hardware/software/tracepoint/etc. */ __u32 type; /* * Size of the attr structure, for fwd/bwd compat. */ __u32 size; /* * Type specific configuration information. */ __u64 config; union { __u64 sample_period; __u64 sample_freq; }; __u64 sample_type; __u64 read_format; __u64 disabled : 1, /* off by default */ inherit : 1, /* children inherit it */ pinned : 1, /* must always be on PMU */ exclusive : 1, /* only group on PMU */ exclude_user : 1, /* don't count user */ exclude_kernel : 1, /* ditto kernel */ exclude_hv : 1, /* ditto hypervisor */ exclude_idle : 1, /* don't count when idle */ mmap : 1, /* include mmap data */ comm : 1, /* include comm data */ freq : 1, /* use freq, not period */ inherit_stat : 1, /* per task counts */ enable_on_exec : 1, /* next exec enables */ task : 1, /* trace fork/exit */ watermark : 1, /* wakeup_watermark */ __reserved_1 : 49; union { __u32 wakeup_events; /* wakeup every n events */ __u32 wakeup_watermark; /* bytes before wakeup */ }; union { struct { /* Hardware breakpoint info */ __u64 bp_addr; __u32 bp_type; __u32 bp_len; }; }; __u32 __reserved_2; __u64 __reserved_3; }; /* * Ioctls that can be done on a perf event fd: */ #define PERF_EVENT_IOC_ENABLE _IO ('$', 0) #define PERF_EVENT_IOC_DISABLE _IO ('$', 1) #define PERF_EVENT_IOC_REFRESH _IO ('$', 2) #define PERF_EVENT_IOC_RESET _IO ('$', 3) #define PERF_EVENT_IOC_PERIOD _IOW('$', 4, __u64) #define PERF_EVENT_IOC_SET_OUTPUT _IO ('$', 5) #define PERF_EVENT_IOC_SET_FILTER _IOW('$', 6, char *) enum perf_event_ioc_flags { PERF_IOC_FLAG_GROUP = 1U << 0, }; /* * Structure of the page that can be mapped via mmap */ struct perf_event_mmap_page { __u32 version; /* version number of this structure */ __u32 compat_version; /* lowest version this is compat with */ /* * Bits needed to read the hw events in user-space. * * u32 seq; * s64 count; * * do { * seq = pc->lock; * * barrier() * if (pc->index) { * count = pmc_read(pc->index - 1); * count += pc->offset; * } else * goto regular_read; * * barrier(); * } while (pc->lock != seq); * * NOTE: for obvious reason this only works on self-monitoring * processes. */ __u32 lock; /* seqlock for synchronization */ __u32 index; /* hardware event identifier */ __s64 offset; /* add to hardware event value */ __u64 time_enabled; /* time event active */ __u64 time_running; /* time event on cpu */ /* * Hole for extension of the self monitor capabilities */ __u64 __reserved[123]; /* align to 1k */ /* * Control data for the mmap() data buffer. * * User-space reading the @data_head value should issue an rmb(), on * SMP capable platforms, after reading this value -- see * perf_event_wakeup(). * * When the mapping is PROT_WRITE the @data_tail value should be * written by userspace to reflect the last read data. In this case * the kernel will not over-write unread data. */ __u64 data_head; /* head in the data section */ __u64 data_tail; /* user-space written tail */ }; #define PERF_RECORD_MISC_CPUMODE_MASK (3 << 0) #define PERF_RECORD_MISC_CPUMODE_UNKNOWN (0 << 0) #define PERF_RECORD_MISC_KERNEL (1 << 0) #define PERF_RECORD_MISC_USER (2 << 0) #define PERF_RECORD_MISC_HYPERVISOR (3 << 0) struct perf_event_header { __u32 type; __u16 misc; __u16 size; }; enum perf_event_type { /* * The MMAP events record the PROT_EXEC mappings so that we can * correlate userspace IPs to code. They have the following structure: * * struct { * struct perf_event_header header; * * u32 pid, tid; * u64 addr; * u64 len; * u64 pgoff; * char filename[]; * }; */ PERF_RECORD_MMAP = 1, /* * struct { * struct perf_event_header header; * u64 id; * u64 lost; * }; */ PERF_RECORD_LOST = 2, /* * struct { * struct perf_event_header header; * * u32 pid, tid; * char comm[]; * }; */ PERF_RECORD_COMM = 3, /* * struct { * struct perf_event_header header; * u32 pid, ppid; * u32 tid, ptid; * u64 time; * }; */ PERF_RECORD_EXIT = 4, /* * struct { * struct perf_event_header header; * u64 time; * u64 id; * u64 stream_id; * }; */ PERF_RECORD_THROTTLE = 5, PERF_RECORD_UNTHROTTLE = 6, /* * struct { * struct perf_event_header header; * u32 pid, ppid; * u32 tid, ptid; * u64 time; * }; */ PERF_RECORD_FORK = 7, /* * struct { * struct perf_event_header header; * u32 pid, tid; * * struct read_format values; * }; */ PERF_RECORD_READ = 8, /* * struct { * struct perf_event_header header; * * { u64 ip; } && PERF_SAMPLE_IP * { u32 pid, tid; } && PERF_SAMPLE_TID * { u64 time; } && PERF_SAMPLE_TIME * { u64 addr; } && PERF_SAMPLE_ADDR * { u64 id; } && PERF_SAMPLE_ID * { u64 stream_id;} && PERF_SAMPLE_STREAM_ID * { u32 cpu, res; } && PERF_SAMPLE_CPU * { u64 period; } && PERF_SAMPLE_PERIOD * * { struct read_format values; } && PERF_SAMPLE_READ * * { u64 nr, * u64 ips[nr]; } && PERF_SAMPLE_CALLCHAIN * * # * # The RAW record below is opaque data wrt the ABI * # * # That is, the ABI doesn't make any promises wrt to * # the stability of its content, it may vary depending * # on event, hardware, kernel version and phase of * # the moon. * # * # In other words, PERF_SAMPLE_RAW contents are not an ABI. * # * * { u32 size; * char data[size];}&& PERF_SAMPLE_RAW * }; */ PERF_RECORD_SAMPLE = 9, PERF_RECORD_MAX, /* non-ABI */ }; enum perf_callchain_context { PERF_CONTEXT_HV = (__u64)-32, PERF_CONTEXT_KERNEL = (__u64)-128, PERF_CONTEXT_USER = (__u64)-512, PERF_CONTEXT_GUEST = (__u64)-2048, PERF_CONTEXT_GUEST_KERNEL = (__u64)-2176, PERF_CONTEXT_GUEST_USER = (__u64)-2560, PERF_CONTEXT_MAX = (__u64)-4095, }; #define PERF_FLAG_FD_NO_GROUP (1U << 0) #define PERF_FLAG_FD_OUTPUT (1U << 1) #ifdef __KERNEL__ /* * Kernel-internal data types and definitions: */ #ifdef CONFIG_PERF_EVENTS # include #endif #include #include #include #include #include #include #include #include #include #include #define PERF_MAX_STACK_DEPTH 255 struct perf_callchain_entry { __u64 nr; __u64 ip[PERF_MAX_STACK_DEPTH]; }; struct perf_raw_record { u32 size; void *data; }; struct task_struct; /** * struct hw_perf_event - performance event hardware details: */ struct hw_perf_event { #ifdef CONFIG_PERF_EVENTS union { struct { /* hardware */ u64 config; unsigned long config_base; unsigned long event_base; int idx; }; struct { /* software */ s64 remaining; struct hrtimer hrtimer; }; #ifdef CONFIG_HAVE_HW_BREAKPOINT union { /* breakpoint */ struct arch_hw_breakpoint info; }; #endif }; atomic64_t prev_count; u64 sample_period; u64 last_period; atomic64_t period_left; u64 interrupts; u64 freq_count; u64 freq_interrupts; u64 freq_stamp; #endif }; struct perf_event; /** * struct pmu - generic performance monitoring unit */ struct pmu { int (*enable) (struct perf_event *event); void (*disable) (struct perf_event *event); void (*read) (struct perf_event *event); void (*unthrottle) (struct perf_event *event); }; /** * enum perf_event_active_state - the states of a event */ enum perf_event_active_state { PERF_EVENT_STATE_ERROR = -2, PERF_EVENT_STATE_OFF = -1, PERF_EVENT_STATE_INACTIVE = 0, PERF_EVENT_STATE_ACTIVE = 1, }; struct file; struct perf_mmap_data { struct rcu_head rcu_head; #ifdef CONFIG_PERF_USE_VMALLOC struct work_struct work; #endif int data_order; int nr_pages; /* nr of data pages */ int writable; /* are we writable */ int nr_locked; /* nr pages mlocked */ atomic_t poll; /* POLL_ for wakeups */ atomic_t events; /* event_id limit */ atomic_long_t head; /* write position */ atomic_long_t done_head; /* completed head */ atomic_t lock; /* concurrent writes */ atomic_t wakeup; /* needs a wakeup */ atomic_t lost; /* nr records lost */ long watermark; /* wakeup watermark */ struct perf_event_mmap_page *user_page; void *data_pages[0]; }; struct perf_pending_entry { struct perf_pending_entry *next; void (*func)(struct perf_pending_entry *); }; typedef void (*perf_callback_t)(struct perf_event *, void *); struct perf_sample_data; /** * struct perf_event - performance event kernel representation: */ struct perf_event { #ifdef CONFIG_PERF_EVENTS struct list_head group_entry; struct list_head event_entry; struct list_head sibling_list; int nr_siblings; struct perf_event *group_leader; struct perf_event *output; const struct pmu *pmu; enum perf_event_active_state state; atomic64_t count; /* * These are the total time in nanoseconds that the event * has been enabled (i.e. eligible to run, and the task has * been scheduled in, if this is a per-task event) * and running (scheduled onto the CPU), respectively. * * They are computed from tstamp_enabled, tstamp_running and * tstamp_stopped when the event is in INACTIVE or ACTIVE state. */ u64 total_time_enabled; u64 total_time_running; /* * These are timestamps used for computing total_time_enabled * and total_time_running when the event is in INACTIVE or * ACTIVE state, measured in nanoseconds from an arbitrary point * in time. * tstamp_enabled: the notional time when the event was enabled * tstamp_running: the notional time when the event was scheduled on * tstamp_stopped: in INACTIVE state, the notional time when the * event was scheduled off. */ u64 tstamp_enabled; u64 tstamp_running; u64 tstamp_stopped; struct perf_event_attr attr; struct hw_perf_event hw; struct perf_event_context *ctx; struct file *filp; /* * These accumulate total time (in nanoseconds) that children * events have been enabled and running, respectively. */ atomic64_t child_total_time_enabled; atomic64_t child_total_time_running; /* * Protect attach/detach and child_list: */ struct mutex child_mutex; struct list_head child_list; struct perf_event *parent; int oncpu; int cpu; struct list_head owner_entry; struct task_struct *owner; /* mmap bits */ struct mutex mmap_mutex; atomic_t mmap_count; struct perf_mmap_data *data; /* poll related */ wait_queue_head_t waitq; struct fasync_struct *fasync; /* delayed work for NMIs and such */ int pending_wakeup; int pending_kill; int pending_disable; struct perf_pending_entry pending; atomic_t event_limit; void (*destroy)(struct perf_event *); struct rcu_head rcu_head; struct pid_namespace *ns; u64 id; void (*overflow_handler)(struct perf_event *event, int nmi, struct perf_sample_data *data, struct pt_regs *regs); #ifdef CONFIG_EVENT_PROFILE struct event_filter *filter; #endif perf_callback_t callback; perf_callback_t event_callback; #endif /* CONFIG_PERF_EVENTS */ }; /** * struct perf_event_context - event context structure * * Used as a container for task events and CPU events as well: */ struct perf_event_context { /* * Protect the states of the events in the list, * nr_active, and the list: */ spinlock_t lock; /* * Protect the list of events. Locking either mutex or lock * is sufficient to ensure the list doesn't change; to change * the list you need to lock both the mutex and the spinlock. */ struct mutex mutex; struct list_head group_list; struct list_head event_list; int nr_events; int nr_active; int is_active; int nr_stat; atomic_t refcount; struct task_struct *task; /* * Context clock, runs when context enabled. */ u64 time; u64 timestamp; /* * These fields let us detect when two contexts have both * been cloned (inherited) from a common ancestor. */ struct perf_event_context *parent_ctx; u64 parent_gen; u64 generation; int pin_count; struct rcu_head rcu_head; }; /** * struct perf_event_cpu_context - per cpu event context structure */ struct perf_cpu_context { struct perf_event_context ctx; struct perf_event_context *task_ctx; int active_oncpu; int max_pertask; int exclusive; /* * Recursion avoidance: * * task, softirq, irq, nmi context */ int recursion[4]; }; struct perf_output_handle { struct perf_event *event; struct perf_mmap_data *data; unsigned long head; unsigned long offset; int nmi; int sample; int locked; }; #ifdef CONFIG_PERF_EVENTS /* * Set by architecture code: */ extern int perf_max_events; extern const struct pmu *hw_perf_event_init(struct perf_event *event); extern void perf_event_task_sched_in(struct task_struct *task, int cpu); extern void perf_event_task_sched_out(struct task_struct *task, struct task_struct *next, int cpu); extern void perf_event_task_tick(struct task_struct *task, int cpu); extern int perf_event_init_task(struct task_struct *child); extern void perf_event_exit_task(struct task_struct *child); extern void perf_event_free_task(struct task_struct *task); extern void set_perf_event_pending(void); extern void perf_event_do_pending(void); extern void perf_event_print_debug(void); extern void __perf_disable(void); extern bool __perf_enable(void); extern void perf_disable(void); extern void perf_enable(void); extern int perf_event_task_disable(void); extern int perf_event_task_enable(void); extern int hw_perf_group_sched_in(struct perf_event *group_leader, struct perf_cpu_context *cpuctx, struct perf_event_context *ctx, int cpu); 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, pid_t pid, perf_callback_t callback); extern u64 perf_event_read_value(struct perf_event *event); struct perf_sample_data { u64 type; u64 ip; struct { u32 pid; u32 tid; } tid_entry; u64 time; u64 addr; u64 id; u64 stream_id; struct { u32 cpu; u32 reserved; } cpu_entry; u64 period; struct perf_callchain_entry *callchain; struct perf_raw_record *raw; }; extern void perf_output_sample(struct perf_output_handle *handle, struct perf_event_header *header, struct perf_sample_data *data, struct perf_event *event); extern void perf_prepare_sample(struct perf_event_header *header, struct perf_sample_data *data, struct perf_event *event, struct pt_regs *regs); extern int perf_event_overflow(struct perf_event *event, int nmi, struct perf_sample_data *data, struct pt_regs *regs); /* * Return 1 for a software event, 0 for a hardware event */ static inline int is_software_event(struct perf_event *event) { return (event->attr.type != PERF_TYPE_RAW) && (event->attr.type != PERF_TYPE_HARDWARE) && (event->attr.type != PERF_TYPE_HW_CACHE); } extern atomic_t perf_swevent_enabled[PERF_COUNT_SW_MAX]; extern void __perf_sw_event(u32, u64, int, struct pt_regs *, u64); static inline void perf_sw_event(u32 event_id, u64 nr, int nmi, struct pt_regs *regs, u64 addr) { if (atomic_read(&perf_swevent_enabled[event_id])) __perf_sw_event(event_id, nr, nmi, regs, addr); } extern void __perf_event_mmap(struct vm_area_struct *vma); static inline void perf_event_mmap(struct vm_area_struct *vma) { if (vma->vm_flags & VM_EXEC) __perf_event_mmap(vma); } extern void perf_event_comm(struct task_struct *tsk); extern void perf_event_fork(struct task_struct *tsk); extern struct perf_callchain_entry *perf_callchain(struct pt_regs *regs); extern int sysctl_perf_event_paranoid; extern int sysctl_perf_event_mlock; extern int sysctl_perf_event_sample_rate; extern void perf_event_init(void); extern void perf_tp_event(int event_id, u64 addr, u64 count, void *record, int entry_size); extern void perf_bp_event(struct perf_event *event, void *data); #ifndef perf_misc_flags #define perf_misc_flags(regs) (user_mode(regs) ? PERF_RECORD_MISC_USER : \ PERF_RECORD_MISC_KERNEL) #define perf_instruction_pointer(regs) instruction_pointer(regs) #endif extern int perf_output_begin(struct perf_output_handle *handle, struct perf_event *event, unsigned int size, int nmi, int sample); extern void perf_output_end(struct perf_output_handle *handle); extern void perf_output_copy(struct perf_output_handle *handle, const void *buf, unsigned int len); #else static inline void perf_event_task_sched_in(struct task_struct *task, int cpu) { } static inline void perf_event_task_sched_out(struct task_struct *task, struct task_struct *next, int cpu) { } static inline void perf_event_task_tick(struct task_struct *task, int cpu) { } static inline int perf_event_init_task(struct task_struct *child) { return 0; } static inline void perf_event_exit_task(struct task_struct *child) { } static inline void perf_event_free_task(struct task_struct *task) { } static inline void perf_event_do_pending(void) { } static inline void perf_event_print_debug(void) { } static inline void perf_disable(void) { } static inline void perf_enable(void) { } static inline int perf_event_task_disable(void) { return -EINVAL; } static inline int perf_event_task_enable(void) { return -EINVAL; } static inline void perf_sw_event(u32 event_id, u64 nr, int nmi, struct pt_regs *regs, u64 addr) { } static inline void perf_bp_event(struct perf_event *event, void *data) { } static inline void perf_event_mmap(struct vm_area_struct *vma) { } static inline void perf_event_comm(struct task_struct *tsk) { } static inline void perf_event_fork(struct task_struct *tsk) { } static inline void perf_event_init(void) { } #endif #define perf_output_put(handle, x) \ perf_output_copy((handle), &(x), sizeof(x)) #endif /* __KERNEL__ */ #endif /* _LINUX_PERF_EVENT_H */