442 lines
10 KiB
C
442 lines
10 KiB
C
/*
|
|
* NOTE: this file will be removed in a future kernel release, it is
|
|
* provided as a courtesy copy of user-space code that relies on the
|
|
* old (pre-rename) symbols and constants.
|
|
*
|
|
* Performance events:
|
|
*
|
|
* Copyright (C) 2008-2009, Thomas Gleixner <tglx@linutronix.de>
|
|
* 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_COUNTER_H
|
|
#define _LINUX_PERF_COUNTER_H
|
|
|
|
#include <linux/types.h>
|
|
#include <linux/ioctl.h>
|
|
#include <asm/byteorder.h>
|
|
|
|
/*
|
|
* 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_MAX, /* non-ABI */
|
|
};
|
|
|
|
/*
|
|
* Generalized performance counter event types, used by the
|
|
* attr.event_id parameter of the sys_perf_counter_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 counters:
|
|
*
|
|
* { 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" counters provided by the kernel, even if the hardware
|
|
* does not support performance counters. These counters 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_MAX, /* non-ABI */
|
|
};
|
|
|
|
/*
|
|
* Bits that can be set in attr.sample_type to request information
|
|
* in the overflow packets.
|
|
*/
|
|
enum perf_counter_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 counter 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_counter_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 to monitor via a performance monitoring counter:
|
|
*/
|
|
struct perf_counter_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 */
|
|
};
|
|
__u32 __reserved_2;
|
|
|
|
__u64 __reserved_3;
|
|
};
|
|
|
|
/*
|
|
* Ioctls that can be done on a perf counter fd:
|
|
*/
|
|
#define PERF_COUNTER_IOC_ENABLE _IO ('$', 0)
|
|
#define PERF_COUNTER_IOC_DISABLE _IO ('$', 1)
|
|
#define PERF_COUNTER_IOC_REFRESH _IO ('$', 2)
|
|
#define PERF_COUNTER_IOC_RESET _IO ('$', 3)
|
|
#define PERF_COUNTER_IOC_PERIOD _IOW('$', 4, u64)
|
|
#define PERF_COUNTER_IOC_SET_OUTPUT _IO ('$', 5)
|
|
|
|
enum perf_counter_ioc_flags {
|
|
PERF_IOC_FLAG_GROUP = 1U << 0,
|
|
};
|
|
|
|
/*
|
|
* Structure of the page that can be mapped via mmap
|
|
*/
|
|
struct perf_counter_mmap_page {
|
|
__u32 version; /* version number of this structure */
|
|
__u32 compat_version; /* lowest version this is compat with */
|
|
|
|
/*
|
|
* Bits needed to read the hw counters 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 counter identifier */
|
|
__s64 offset; /* add to hardware counter value */
|
|
__u64 time_enabled; /* time counter active */
|
|
__u64 time_running; /* time counter 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_counter_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_EVENT_MISC_CPUMODE_MASK (3 << 0)
|
|
#define PERF_EVENT_MISC_CPUMODE_UNKNOWN (0 << 0)
|
|
#define PERF_EVENT_MISC_KERNEL (1 << 0)
|
|
#define PERF_EVENT_MISC_USER (2 << 0)
|
|
#define PERF_EVENT_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_EVENT_MMAP = 1,
|
|
|
|
/*
|
|
* struct {
|
|
* struct perf_event_header header;
|
|
* u64 id;
|
|
* u64 lost;
|
|
* };
|
|
*/
|
|
PERF_EVENT_LOST = 2,
|
|
|
|
/*
|
|
* struct {
|
|
* struct perf_event_header header;
|
|
*
|
|
* u32 pid, tid;
|
|
* char comm[];
|
|
* };
|
|
*/
|
|
PERF_EVENT_COMM = 3,
|
|
|
|
/*
|
|
* struct {
|
|
* struct perf_event_header header;
|
|
* u32 pid, ppid;
|
|
* u32 tid, ptid;
|
|
* u64 time;
|
|
* };
|
|
*/
|
|
PERF_EVENT_EXIT = 4,
|
|
|
|
/*
|
|
* struct {
|
|
* struct perf_event_header header;
|
|
* u64 time;
|
|
* u64 id;
|
|
* u64 stream_id;
|
|
* };
|
|
*/
|
|
PERF_EVENT_THROTTLE = 5,
|
|
PERF_EVENT_UNTHROTTLE = 6,
|
|
|
|
/*
|
|
* struct {
|
|
* struct perf_event_header header;
|
|
* u32 pid, ppid;
|
|
* u32 tid, ptid;
|
|
* { u64 time; } && PERF_SAMPLE_TIME
|
|
* };
|
|
*/
|
|
PERF_EVENT_FORK = 7,
|
|
|
|
/*
|
|
* struct {
|
|
* struct perf_event_header header;
|
|
* u32 pid, tid;
|
|
*
|
|
* struct read_format values;
|
|
* };
|
|
*/
|
|
PERF_EVENT_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_EVENT_SAMPLE = 9,
|
|
|
|
PERF_EVENT_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)
|
|
|
|
/*
|
|
* In case some app still references the old symbols:
|
|
*/
|
|
|
|
#define __NR_perf_counter_open __NR_perf_event_open
|
|
|
|
#define PR_TASK_PERF_COUNTERS_DISABLE PR_TASK_PERF_EVENTS_DISABLE
|
|
#define PR_TASK_PERF_COUNTERS_ENABLE PR_TASK_PERF_EVENTS_ENABLE
|
|
|
|
#endif /* _LINUX_PERF_COUNTER_H */
|