0: sampled instruction
*
* See asm/perf_regs.h for details.
*/
#ifndef __GENKSYMS__
__u64 sample_regs_intr;
/*
* Wakeup watermark for AUX area
*/
__u32 aux_watermark;
__u32 __reserved_3; /* align to __u64 */
#endif
};
/*
* Structure used by below PERF_EVENT_IOC_QUERY_BPF command
* to query bpf programs attached to the same perf tracepoint
* as the given perf event.
*/
struct perf_event_query_bpf {
/*
* The below ids array length
*/
__u32 ids_len;
/*
* Set by the kernel to indicate the number of
* available programs
*/
__u32 prog_cnt;
/*
* User provided buffer to store program ids
*/
__u32 ids[0];
};
#define perf_flags(attr) (*(&(attr)->read_format + 1))
/*
* 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('$', 6, char *)
#define PERF_EVENT_IOC_ID _IOR('$', 7, __u64 *)
#define PERF_EVENT_IOC_SET_BPF _IOW('$', 8, __u32)
#define PERF_EVENT_IOC_PAUSE_OUTPUT _IOW('$', 9, __u32)
#define PERF_EVENT_IOC_QUERY_BPF _IOWR('$', 10, struct perf_event_query_bpf *)
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, time_mult, time_shift, index, width;
* u64 count, enabled, running;
* u64 cyc, time_offset;
* s64 pmc = 0;
*
* do {
* seq = pc->lock;
* barrier()
*
* enabled = pc->time_enabled;
* running = pc->time_running;
*
* if (pc->cap_usr_time && enabled != running) {
* cyc = rdtsc();
* time_offset = pc->time_offset;
* time_mult = pc->time_mult;
* time_shift = pc->time_shift;
* }
*
* index = pc->index;
* count = pc->offset;
* if (pc->cap_user_rdpmc && index) {
* width = pc->pmc_width;
* pmc = rdpmc(index - 1);
* }
*
* 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 */
union {
__u64 capabilities;
struct {
__u64 cap_bit0 : 1, /* Always 0, deprecated, see commit 860f085b74e9 */
cap_bit0_is_deprecated : 1, /* Always 1, signals that bit 0 is zero */
cap_user_rdpmc : 1, /* The RDPMC instruction can be used to read counts */
cap_user_time : 1, /* The time_* fields are used */
cap_user_time_zero : 1, /* The time_zero field is used */
cap_____res : 59;
};
};
/*
* If cap_user_rdpmc this field provides the bit-width of the value
* read using the rdpmc() or equivalent instruction. This can be used
* to sign extend the result like:
*
* pmc <<= 64 - width;
* pmc >>= 64 - width; // signed shift right
* count += pmc;
*/
__u16 pmc_width;
/*
* If cap_usr_time the below fields can be used to compute the time
* delta since time_enabled (in ns) using rdtsc or similar.
*
* u64 quot, rem;
* u64 delta;
*
* quot = (cyc >> time_shift);
* rem = cyc & (((u64)1 << time_shift) - 1);
* delta = time_offset + quot * time_mult +
* ((rem * time_mult) >> time_shift);
*
* Where time_offset,time_mult,time_shift and cyc are read in the
* seqcount loop described above. This delta can then be added to
* enabled and possible running (if index), improving the scaling:
*
* enabled += delta;
* if (index)
* running += delta;
*
* quot = count / running;
* rem = count % running;
* count = quot * enabled + (rem * enabled) / running;
*/
__u16 time_shift;
__u32 time_mult;
__u64 time_offset;
/*
* If cap_usr_time_zero, the hardware clock (e.g. TSC) can be calculated
* from sample timestamps.
*
* time = timestamp - time_zero;
* quot = time / time_mult;
* rem = time % time_mult;
* cyc = (quot << time_shift) + (rem << time_shift) / time_mult;
*
* And vice versa:
*
* quot = cyc >> time_shift;
* rem = cyc & (((u64)1 << time_shift) - 1);
* timestamp = time_zero + quot * time_mult +
* ((rem * time_mult) >> time_shift);
*/
__u64 time_zero;
__u32 size; /* Header size up to __reserved[] fields. */
/*
* Hole for extension of the self monitor capabilities
*/
__u8 __reserved[118*8+4]; /* align to 1k. */
/*
* Control data for the mmap() data buffer.
*
* User-space reading the @data_head value should issue an smp_rmb(),
* after reading this value.
*
* When the mapping is PROT_WRITE the @data_tail value should be
* written by userspace to reflect the last read data, after issueing
* an smp_mb() to separate the data read from the ->data_tail store.
* In this case the kernel will not over-write unread data.
*
* See perf_output_put_handle() for the data ordering.
*
* data_{offset,size} indicate the location and size of the perf record
* buffer within the mmapped area.
*/
__u64 data_head; /* head in the data section */
__u64 data_tail; /* user-space written tail */
__u64 data_offset; /* where the buffer starts */
__u64 data_size; /* data buffer size */
/*
* AUX area is defined by aux_{offset,size} fields that should be set
* by the userspace, so that
*
* aux_offset >= data_offset + data_size
*
* prior to mmap()ing it. Size of the mmap()ed area should be aux_size.
*
* Ring buffer pointers aux_{head,tail} have the same semantics as
* data_{head,tail} and same ordering rules apply.
*/
__u64 aux_head;
__u64 aux_tail;
__u64 aux_offset;
__u64 aux_size;
};
#define PERF_RECORD_MISC_CPUMODE_MASK (7 << 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)
#define PERF_RECORD_MISC_GUEST_KERNEL (4 << 0)
#define PERF_RECORD_MISC_GUEST_USER (5 << 0)
/*
* Indicates that /proc/PID/maps parsing are truncated by time out.
*/
#define PERF_RECORD_MISC_PROC_MAP_PARSE_TIMEOUT (1 << 12)
/*
* Following PERF_RECORD_MISC_* are used on different
* events, so can reuse the same bit position:
*
* PERF_RECORD_MISC_MMAP_DATA - PERF_RECORD_MMAP* events
* PERF_RECORD_MISC_COMM_EXEC - PERF_RECORD_COMM event
* PERF_RECORD_MISC_FORK_EXEC - PERF_RECORD_FORK event (perf internal)
* PERF_RECORD_MISC_SWITCH_OUT - PERF_RECORD_SWITCH* events
*/
#define PERF_RECORD_MISC_MMAP_DATA (1 << 13)
#define PERF_RECORD_MISC_COMM_EXEC (1 << 13)
#define PERF_RECORD_MISC_FORK_EXEC (1 << 13)
#define PERF_RECORD_MISC_SWITCH_OUT (1 << 13)
/*
* These PERF_RECORD_MISC_* flags below are safely reused
* for the following events:
*
* PERF_RECORD_MISC_EXACT_IP - PERF_RECORD_SAMPLE of precise events
* PERF_RECORD_MISC_SWITCH_OUT_PREEMPT - PERF_RECORD_SWITCH* events
*
*
* PERF_RECORD_MISC_EXACT_IP:
* Indicates that the content of PERF_SAMPLE_IP points to
* the actual instruction that triggered the event. See also
* perf_event_attr::precise_ip.
*
* PERF_RECORD_MISC_SWITCH_OUT_PREEMPT:
* Indicates that thread was preempted in TASK_RUNNING state.
*/
#define PERF_RECORD_MISC_EXACT_IP (1 << 14)
#define PERF_RECORD_MISC_SWITCH_OUT_PREEMPT (1 << 14)
/*
* Reserve the last bit to indicate some extended misc field
*/
#define PERF_RECORD_MISC_EXT_RESERVED (1 << 15)
struct perf_event_header {
__u32 type;
__u16 misc;
__u16 size;
};
enum perf_event_type {
/*
* If perf_event_attr.sample_id_all is set then all event types will
* have the sample_type selected fields related to where/when
* (identity) an event took place (TID, TIME, ID, STREAM_ID, CPU,
* IDENTIFIER) described in PERF_RECORD_SAMPLE below, it will be stashed
* just after the perf_event_header and the fields already present for
* the existing fields, i.e. at the end of the payload. That way a newer
* perf.data file will be supported by older perf tools, with these new
* optional fields being ignored.
*
* struct sample_id {
* { u32 pid, tid; } && PERF_SAMPLE_TID
* { u64 time; } && PERF_SAMPLE_TIME
* { u64 id; } && PERF_SAMPLE_ID
* { u64 stream_id;} && PERF_SAMPLE_STREAM_ID
* { u32 cpu, res; } && PERF_SAMPLE_CPU
* { u64 id; } && PERF_SAMPLE_IDENTIFIER
* } && perf_event_attr::sample_id_all
*
* Note that PERF_SAMPLE_IDENTIFIER duplicates PERF_SAMPLE_ID. The
* advantage of PERF_SAMPLE_IDENTIFIER is that its position is fixed
* relative to header.size.
*/
/*
* 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[];
* struct sample_id sample_id;
* };
*/
PERF_RECORD_MMAP = 1,
/*
* struct {
* struct perf_event_header header;
* u64 id;
* u64 lost;
* struct sample_id sample_id;
* };
*/
PERF_RECORD_LOST = 2,
/*
* struct {
* struct perf_event_header header;
*
* u32 pid, tid;
* char comm[];
* struct sample_id sample_id;
* };
*/
PERF_RECORD_COMM = 3,
/*
* struct {
* struct perf_event_header header;
* u32 pid, ppid;
* u32 tid, ptid;
* u64 time;
* struct sample_id sample_id;
* };
*/
PERF_RECORD_EXIT = 4,
/*
* struct {
* struct perf_event_header header;
* u64 time;
* u64 id;
* u64 stream_id;
* struct sample_id sample_id;
* };
*/
PERF_RECORD_THROTTLE = 5,
PERF_RECORD_UNTHROTTLE = 6,
/*
* struct {
* struct perf_event_header header;
* u32 pid, ppid;
* u32 tid, ptid;
* u64 time;
* struct sample_id sample_id;
* };
*/
PERF_RECORD_FORK = 7,
/*
* struct {
* struct perf_event_header header;
* u32 pid, tid;
*
* struct read_format values;
* struct sample_id sample_id;
* };
*/
PERF_RECORD_READ = 8,
/*
* struct {
* struct perf_event_header header;
*
* #
* # Note that PERF_SAMPLE_IDENTIFIER duplicates PERF_SAMPLE_ID.
* # The advantage of PERF_SAMPLE_IDENTIFIER is that its position
* # is fixed relative to header.
* #
*
* { u64 id; } && PERF_SAMPLE_IDENTIFIER
* { 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
*
* { u64 nr;
* { u64 from, to, flags } lbr[nr];} && PERF_SAMPLE_BRANCH_STACK
*
* { u64 abi; # enum perf_sample_regs_abi
* u64 regs[weight(mask)]; } && PERF_SAMPLE_REGS_USER
*
* { u64 size;
* char data[size];
* u64 dyn_size; } && PERF_SAMPLE_STACK_USER
*
* { u64 weight; } && PERF_SAMPLE_WEIGHT
* { u64 data_src; } && PERF_SAMPLE_DATA_SRC
* { u64 transaction; } && PERF_SAMPLE_TRANSACTION
* { u64 abi; # enum perf_sample_regs_abi
* u64 regs[weight(mask)]; } && PERF_SAMPLE_REGS_INTR
* { u64 phys_addr;} && PERF_SAMPLE_PHYS_ADDR
* };
*/
PERF_RECORD_SAMPLE = 9,
/*
* The MMAP2 records are an augmented version of MMAP, they add
* maj, min, ino numbers to be used to uniquely identify each mapping
*
* struct {
* struct perf_event_header header;
*
* u32 pid, tid;
* u64 addr;
* u64 len;
* u64 pgoff;
* u32 maj;
* u32 min;
* u64 ino;
* u64 ino_generation;
* u32 prot, flags;
* char filename[];
* struct sample_id sample_id;
* };
*/
PERF_RECORD_MMAP2 = 10,
/*
* Records that new data landed in the AUX buffer part.
*
* struct {
* struct perf_event_header header;
*
* u64 aux_offset;
* u64 aux_size;
* u64 flags;
* struct sample_id sample_id;
* };
*/
PERF_RECORD_AUX = 11,
/*
* Indicates that instruction trace has started
*
* struct {
* struct perf_event_header header;
* u32 pid;
* u32 tid;
* struct sample_id sample_id;
* };
*/
PERF_RECORD_ITRACE_START = 12,
/*
* Records the dropped/lost sample number.
*
* struct {
* struct perf_event_header header;
*
* u64 lost;
* struct sample_id sample_id;
* };
*/
PERF_RECORD_LOST_SAMPLES = 13,
/*
* Records a context switch in or out (flagged by
* PERF_RECORD_MISC_SWITCH_OUT). See also
* PERF_RECORD_SWITCH_CPU_WIDE.
*
* struct {
* struct perf_event_header header;
* struct sample_id sample_id;
* };
*/
PERF_RECORD_SWITCH = 14,
/*
* CPU-wide version of PERF_RECORD_SWITCH with next_prev_pid and
* next_prev_tid that are the next (switching out) or previous
* (switching in) pid/tid.
*
* struct {
* struct perf_event_header header;
* u32 next_prev_pid;
* u32 next_prev_tid;
* struct sample_id sample_id;
* };
*/
PERF_RECORD_SWITCH_CPU_WIDE = 15,
PERF_RECORD_MAX, /* non-ABI */
};
#define PERF_MAX_STACK_DEPTH 127
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,
};
/**
* PERF_RECORD_AUX::flags bits
*/
#define PERF_AUX_FLAG_TRUNCATED 0x01 /* record was truncated to fit */
#define PERF_AUX_FLAG_OVERWRITE 0x02 /* snapshot from overwrite mode */
#define PERF_AUX_FLAG_PARTIAL 0x04 /* record contains gaps */
#define PERF_AUX_FLAG_COLLISION 0x08 /* sample collided with another */
#define PERF_FLAG_FD_NO_GROUP (1UL << 0)
#define PERF_FLAG_FD_OUTPUT (1UL << 1)
#define PERF_FLAG_PID_CGROUP (1UL << 2) /* pid=cgroup id, per-cpu mode only */
#define PERF_FLAG_FD_CLOEXEC (1UL << 3) /* O_CLOEXEC */
#ifdef __GENKSYMS__
union perf_mem_data_src {
__u64 val;
struct {
__u64 mem_op:5, /* type of opcode */
mem_lvl:14, /* memory hierarchy level */
mem_snoop:5, /* snoop mode */
mem_lock:2, /* lock instr */
mem_dtlb:7, /* tlb access */
mem_rsvd:31;
};
};
#else
#if defined(__LITTLE_ENDIAN_BITFIELD)
union perf_mem_data_src {
__u64 val;
struct {
__u64 mem_op:5, /* type of opcode */
mem_lvl:14, /* memory hierarchy level */
mem_snoop:5, /* snoop mode */
mem_lock:2, /* lock instr */
mem_dtlb:7, /* tlb access */
mem_lvl_num:4, /* memory hierarchy level number */
mem_remote:1, /* remote */
mem_snoopx:2, /* snoop mode, ext */
mem_rsvd:24;
};
};
#elif defined(__BIG_ENDIAN_BITFIELD)
union perf_mem_data_src {
__u64 val;
struct {
__u64 mem_rsvd:24,
mem_snoopx:2, /* snoop mode, ext */
mem_remote:1, /* remote */
mem_lvl_num:4, /* memory hierarchy level number */
mem_dtlb:7, /* tlb access */
mem_lock:2, /* lock instr */
mem_snoop:5, /* snoop mode */
mem_lvl:14, /* memory hierarchy level */
mem_op:5; /* type of opcode */
};
};
#else
#error "Unknown endianness"
#endif
#endif /* __GENKSYMS__ */
/* type of opcode (load/store/prefetch,code) */
#define PERF_MEM_OP_NA 0x01 /* not available */
#define PERF_MEM_OP_LOAD 0x02 /* load instruction */
#define PERF_MEM_OP_STORE 0x04 /* store instruction */
#define PERF_MEM_OP_PFETCH 0x08 /* prefetch */
#define PERF_MEM_OP_EXEC 0x10 /* code (execution) */
#define PERF_MEM_OP_SHIFT 0
/* memory hierarchy (memory level, hit or miss) */
#define PERF_MEM_LVL_NA 0x01 /* not available */
#define PERF_MEM_LVL_HIT 0x02 /* hit level */
#define PERF_MEM_LVL_MISS 0x04 /* miss level */
#define PERF_MEM_LVL_L1 0x08 /* L1 */
#define PERF_MEM_LVL_LFB 0x10 /* Line Fill Buffer */
#define PERF_MEM_LVL_L2 0x20 /* L2 */
#define PERF_MEM_LVL_L3 0x40 /* L3 */
#define PERF_MEM_LVL_LOC_RAM 0x80 /* Local DRAM */
#define PERF_MEM_LVL_REM_RAM1 0x100 /* Remote DRAM (1 hop) */
#define PERF_MEM_LVL_REM_RAM2 0x200 /* Remote DRAM (2 hops) */
#define PERF_MEM_LVL_REM_CCE1 0x400 /* Remote Cache (1 hop) */
#define PERF_MEM_LVL_REM_CCE2 0x800 /* Remote Cache (2 hops) */
#define PERF_MEM_LVL_IO 0x1000 /* I/O memory */
#define PERF_MEM_LVL_UNC 0x2000 /* Uncached memory */
#define PERF_MEM_LVL_SHIFT 5
#define PERF_MEM_REMOTE_REMOTE 0x01 /* Remote */
#define PERF_MEM_REMOTE_SHIFT 37
#define PERF_MEM_LVLNUM_L1 0x01 /* L1 */
#define PERF_MEM_LVLNUM_L2 0x02 /* L2 */
#define PERF_MEM_LVLNUM_L3 0x03 /* L3 */
#define PERF_MEM_LVLNUM_L4 0x04 /* L4 */
/* 5-0xa available */
#define PERF_MEM_LVLNUM_ANY_CACHE 0x0b /* Any cache */
#define PERF_MEM_LVLNUM_LFB 0x0c /* LFB */
#define PERF_MEM_LVLNUM_RAM 0x0d /* RAM */
#define PERF_MEM_LVLNUM_PMEM 0x0e /* PMEM */
#define PERF_MEM_LVLNUM_NA 0x0f /* N/A */
#define PERF_MEM_LVLNUM_SHIFT 33
/* snoop mode */
#define PERF_MEM_SNOOP_NA 0x01 /* not available */
#define PERF_MEM_SNOOP_NONE 0x02 /* no snoop */
#define PERF_MEM_SNOOP_HIT 0x04 /* snoop hit */
#define PERF_MEM_SNOOP_MISS 0x08 /* snoop miss */
#define PERF_MEM_SNOOP_HITM 0x10 /* snoop hit modified */
#define PERF_MEM_SNOOP_SHIFT 19
#define PERF_MEM_SNOOPX_FWD 0x01 /* forward */
/* 1 free */
#define PERF_MEM_SNOOPX_SHIFT 37
/* locked instruction */
#define PERF_MEM_LOCK_NA 0x01 /* not available */
#define PERF_MEM_LOCK_LOCKED 0x02 /* locked transaction */
#define PERF_MEM_LOCK_SHIFT 24
/* TLB access */
#define PERF_MEM_TLB_NA 0x01 /* not available */
#define PERF_MEM_TLB_HIT 0x02 /* hit level */
#define PERF_MEM_TLB_MISS 0x04 /* miss level */
#define PERF_MEM_TLB_L1 0x08 /* L1 */
#define PERF_MEM_TLB_L2 0x10 /* L2 */
#define PERF_MEM_TLB_WK 0x20 /* Hardware Walker*/
#define PERF_MEM_TLB_OS 0x40 /* OS fault handler */
#define PERF_MEM_TLB_SHIFT 26
#define PERF_MEM_S(a, s) \
(((__u64)PERF_MEM_##a##_##s) << PERF_MEM_##a##_SHIFT)
/*
* single taken branch record layout:
*
* from: source instruction (may not always be a branch insn)
* to: branch target
* mispred: branch target was mispredicted
* predicted: branch target was predicted
*
* support for mispred, predicted is optional. In case it
* is not supported mispred = predicted = 0.
*
* in_tx: running in a hardware transaction
* abort: aborting a hardware transaction
* cycles: cycles from last branch (or 0 if not supported)
* type: branch type
*/
struct perf_branch_entry {
__u64 from;
__u64 to;
__u64 mispred:1, /* target mispredicted */
predicted:1,/* target predicted */
in_tx:1, /* in transaction */
abort:1, /* transaction abort */
#ifndef __GENKSYMS__
cycles:16, /* cycle count to last branch */
type:4, /* branch type */
reserved:40;
#else
reserved:60;
#endif
};
#endif /* _LINUX_PERF_EVENT_H */