diff options
Diffstat (limited to 'include/uapi/linux/perf_event.h')
| -rw-r--r-- | include/uapi/linux/perf_event.h | 163 |
1 files changed, 145 insertions, 18 deletions
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 0b1df41691e8..e1802d6153ae 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -109,6 +109,7 @@ enum perf_sw_ids { PERF_COUNT_SW_PAGE_FAULTS_MAJ = 6, PERF_COUNT_SW_ALIGNMENT_FAULTS = 7, PERF_COUNT_SW_EMULATION_FAULTS = 8, + PERF_COUNT_SW_DUMMY = 9, PERF_COUNT_SW_MAX, /* non-ABI */ }; @@ -134,8 +135,10 @@ enum perf_event_sample_format { PERF_SAMPLE_STACK_USER = 1U << 13, PERF_SAMPLE_WEIGHT = 1U << 14, PERF_SAMPLE_DATA_SRC = 1U << 15, + PERF_SAMPLE_IDENTIFIER = 1U << 16, + PERF_SAMPLE_TRANSACTION = 1U << 17, - PERF_SAMPLE_MAX = 1U << 16, /* non-ABI */ + PERF_SAMPLE_MAX = 1U << 18, /* non-ABI */ }; /* @@ -179,6 +182,28 @@ enum perf_sample_regs_abi { }; /* + * Values for the memory transaction event qualifier, mostly for + * abort events. Multiple bits can be set. + */ +enum { + PERF_TXN_ELISION = (1 << 0), /* From elision */ + PERF_TXN_TRANSACTION = (1 << 1), /* From transaction */ + PERF_TXN_SYNC = (1 << 2), /* Instruction is related */ + PERF_TXN_ASYNC = (1 << 3), /* Instruction not related */ + PERF_TXN_RETRY = (1 << 4), /* Retry possible */ + PERF_TXN_CONFLICT = (1 << 5), /* Conflict abort */ + PERF_TXN_CAPACITY_WRITE = (1 << 6), /* Capacity write abort */ + PERF_TXN_CAPACITY_READ = (1 << 7), /* Capacity read abort */ + + PERF_TXN_MAX = (1 << 8), /* non-ABI */ + + /* bits 32..63 are reserved for the abort code */ + + PERF_TXN_ABORT_MASK = (0xffffffffULL << 32), + PERF_TXN_ABORT_SHIFT = 32, +}; + +/* * The format of the data returned by read() on a perf event fd, * as specified by attr.read_format: * @@ -275,8 +300,9 @@ struct perf_event_attr { exclude_callchain_kernel : 1, /* exclude kernel callchains */ exclude_callchain_user : 1, /* exclude user callchains */ + mmap2 : 1, /* include mmap with inode data */ - __reserved_1 : 41; + __reserved_1 : 40; union { __u32 wakeup_events; /* wakeup every n events */ @@ -321,6 +347,7 @@ struct perf_event_attr { #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 *) enum perf_event_ioc_flags { PERF_IOC_FLAG_GROUP = 1U << 0, @@ -375,9 +402,15 @@ struct perf_event_mmap_page { __u64 time_running; /* time event on cpu */ union { __u64 capabilities; - __u64 cap_usr_time : 1, - cap_usr_rdpmc : 1, - cap_____res : 62; + 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; + }; }; /* @@ -418,23 +451,43 @@ struct perf_event_mmap_page { __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 & ((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 */ - __u64 __reserved[120]; /* align to 1k */ + __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 rmb(), on - * SMP capable platforms, after reading this value -- see - * perf_event_wakeup(). + * 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. In this case - * the kernel will not over-write unread data. + * 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. */ __u64 data_head; /* head in the data section */ __u64 data_tail; /* user-space written tail */ @@ -471,13 +524,28 @@ 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, CPU, STREAM_ID) - * 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. + * (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: * @@ -489,6 +557,7 @@ enum perf_event_type { * u64 len; * u64 pgoff; * char filename[]; + * struct sample_id sample_id; * }; */ PERF_RECORD_MMAP = 1, @@ -498,6 +567,7 @@ enum perf_event_type { * struct perf_event_header header; * u64 id; * u64 lost; + * struct sample_id sample_id; * }; */ PERF_RECORD_LOST = 2, @@ -508,6 +578,7 @@ enum perf_event_type { * * u32 pid, tid; * char comm[]; + * struct sample_id sample_id; * }; */ PERF_RECORD_COMM = 3, @@ -518,6 +589,7 @@ enum perf_event_type { * u32 pid, ppid; * u32 tid, ptid; * u64 time; + * struct sample_id sample_id; * }; */ PERF_RECORD_EXIT = 4, @@ -528,6 +600,7 @@ enum perf_event_type { * u64 time; * u64 id; * u64 stream_id; + * struct sample_id sample_id; * }; */ PERF_RECORD_THROTTLE = 5, @@ -539,6 +612,7 @@ enum perf_event_type { * u32 pid, ppid; * u32 tid, ptid; * u64 time; + * struct sample_id sample_id; * }; */ PERF_RECORD_FORK = 7, @@ -549,6 +623,7 @@ enum perf_event_type { * u32 pid, tid; * * struct read_format values; + * struct sample_id sample_id; * }; */ PERF_RECORD_READ = 8, @@ -557,6 +632,13 @@ enum perf_event_type { * 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 @@ -596,11 +678,32 @@ enum perf_event_type { * u64 dyn_size; } && PERF_SAMPLE_STACK_USER * * { u64 weight; } && PERF_SAMPLE_WEIGHT - * { u64 data_src; } && PERF_SAMPLE_DATA_SRC + * { u64 data_src; } && PERF_SAMPLE_DATA_SRC * }; */ 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; + * char filename[]; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_MMAP2 = 10, + PERF_RECORD_MAX, /* non-ABI */ }; @@ -685,4 +788,28 @@ union perf_mem_data_src { #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 + */ +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 */ + reserved:60; +}; + #endif /* _UAPI_LINUX_PERF_EVENT_H */ |