mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-11-15 16:24:13 +08:00
3c1763115b
Adding 'S' event/group modifier to specify that the event value/s are read by PERF_SAMPLE_READ sample type processing, instead of the period value offered by lower layers. There's additional behaviour change for 'S' modifier being specified on event group: Currently all the events within a group makes samples. If user now specifies 'S' within group modifier, only the leader will trigger samples. The rest of events in the group will have sampling disabled. And same as for single events, values of all events within the group (including leader) are read by PERF_SAMPLE_READ sample type processing. Following example will create event group with cycles and cache-misses events, setting the cycles as group leader and the only event to actually sample. Both cycles and cache-misses event period values are read by PERF_SAMPLE_READ sample type processing with PERF_FORMAT_GROUP read format. Example: $ perf record -e '{cycles,cache-misses}:S' ls ... $ perf report --group --show-total-period --stdio ... # Samples: 36 of event 'anon group { cycles, cache-misses }' # Event count (approx.): 12585593 # # Overhead Period Command Shared Object Symbol # .............. .............. ....... ................. .......................... # 19.92% 1.20% 2505936 31 ls [kernel.kallsyms] [k] mark_held_locks 13.74% 0.47% 1729327 12 ls [kernel.kallsyms] [k] sched_clock_local 13.64% 23.72% 1716147 612 ls ld-2.14.90.so [.] check_match.10805 13.12% 23.22% 1650778 599 ls libc-2.14.90.so [.] _nl_intern_locale_data 11.24% 29.19% 1414554 753 ls [kernel.kallsyms] [k] sched_clock_cpu 8.50% 0.35% 1070150 9 ls [kernel.kallsyms] [k] check_chain_key ... Signed-off-by: Jiri Olsa <jolsa@redhat.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/n/tip-iyoinu3axi11mymwnh2b7fxj@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
309 lines
8.8 KiB
C
309 lines
8.8 KiB
C
#ifndef __PERF_EVSEL_H
|
|
#define __PERF_EVSEL_H 1
|
|
|
|
#include <linux/list.h>
|
|
#include <stdbool.h>
|
|
#include <stddef.h>
|
|
#include <linux/perf_event.h>
|
|
#include "types.h"
|
|
#include "xyarray.h"
|
|
#include "cgroup.h"
|
|
#include "hist.h"
|
|
#include "symbol.h"
|
|
|
|
struct perf_counts_values {
|
|
union {
|
|
struct {
|
|
u64 val;
|
|
u64 ena;
|
|
u64 run;
|
|
};
|
|
u64 values[3];
|
|
};
|
|
};
|
|
|
|
struct perf_counts {
|
|
s8 scaled;
|
|
struct perf_counts_values aggr;
|
|
struct perf_counts_values cpu[];
|
|
};
|
|
|
|
struct perf_evsel;
|
|
|
|
/*
|
|
* Per fd, to map back from PERF_SAMPLE_ID to evsel, only used when there are
|
|
* more than one entry in the evlist.
|
|
*/
|
|
struct perf_sample_id {
|
|
struct hlist_node node;
|
|
u64 id;
|
|
struct perf_evsel *evsel;
|
|
|
|
/* Holds total ID period value for PERF_SAMPLE_READ processing. */
|
|
u64 period;
|
|
};
|
|
|
|
/** struct perf_evsel - event selector
|
|
*
|
|
* @name - Can be set to retain the original event name passed by the user,
|
|
* so that when showing results in tools such as 'perf stat', we
|
|
* show the name used, not some alias.
|
|
*/
|
|
struct perf_evsel {
|
|
struct list_head node;
|
|
struct perf_event_attr attr;
|
|
char *filter;
|
|
struct xyarray *fd;
|
|
struct xyarray *sample_id;
|
|
u64 *id;
|
|
struct perf_counts *counts;
|
|
struct perf_counts *prev_raw_counts;
|
|
int idx;
|
|
u32 ids;
|
|
struct hists hists;
|
|
char *name;
|
|
struct event_format *tp_format;
|
|
union {
|
|
void *priv;
|
|
off_t id_offset;
|
|
};
|
|
struct cgroup_sel *cgrp;
|
|
struct {
|
|
void *func;
|
|
void *data;
|
|
} handler;
|
|
struct cpu_map *cpus;
|
|
unsigned int sample_size;
|
|
bool supported;
|
|
bool needs_swap;
|
|
/* parse modifier helper */
|
|
int exclude_GH;
|
|
int nr_members;
|
|
int sample_read;
|
|
struct perf_evsel *leader;
|
|
char *group_name;
|
|
};
|
|
|
|
#define hists_to_evsel(h) container_of(h, struct perf_evsel, hists)
|
|
|
|
struct cpu_map;
|
|
struct thread_map;
|
|
struct perf_evlist;
|
|
struct perf_record_opts;
|
|
|
|
struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx);
|
|
struct perf_evsel *perf_evsel__newtp(const char *sys, const char *name, int idx);
|
|
|
|
struct event_format *event_format__new(const char *sys, const char *name);
|
|
|
|
void perf_evsel__init(struct perf_evsel *evsel,
|
|
struct perf_event_attr *attr, int idx);
|
|
void perf_evsel__exit(struct perf_evsel *evsel);
|
|
void perf_evsel__delete(struct perf_evsel *evsel);
|
|
|
|
void perf_evsel__config(struct perf_evsel *evsel,
|
|
struct perf_record_opts *opts);
|
|
|
|
bool perf_evsel__is_cache_op_valid(u8 type, u8 op);
|
|
|
|
#define PERF_EVSEL__MAX_ALIASES 8
|
|
|
|
extern const char *perf_evsel__hw_cache[PERF_COUNT_HW_CACHE_MAX]
|
|
[PERF_EVSEL__MAX_ALIASES];
|
|
extern const char *perf_evsel__hw_cache_op[PERF_COUNT_HW_CACHE_OP_MAX]
|
|
[PERF_EVSEL__MAX_ALIASES];
|
|
extern const char *perf_evsel__hw_cache_result[PERF_COUNT_HW_CACHE_RESULT_MAX]
|
|
[PERF_EVSEL__MAX_ALIASES];
|
|
extern const char *perf_evsel__hw_names[PERF_COUNT_HW_MAX];
|
|
extern const char *perf_evsel__sw_names[PERF_COUNT_SW_MAX];
|
|
int __perf_evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result,
|
|
char *bf, size_t size);
|
|
const char *perf_evsel__name(struct perf_evsel *evsel);
|
|
const char *perf_evsel__group_name(struct perf_evsel *evsel);
|
|
int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size);
|
|
|
|
int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
|
|
int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads);
|
|
int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus);
|
|
void perf_evsel__reset_counts(struct perf_evsel *evsel, int ncpus);
|
|
void perf_evsel__free_fd(struct perf_evsel *evsel);
|
|
void perf_evsel__free_id(struct perf_evsel *evsel);
|
|
void perf_evsel__free_counts(struct perf_evsel *evsel);
|
|
void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
|
|
|
|
void __perf_evsel__set_sample_bit(struct perf_evsel *evsel,
|
|
enum perf_event_sample_format bit);
|
|
void __perf_evsel__reset_sample_bit(struct perf_evsel *evsel,
|
|
enum perf_event_sample_format bit);
|
|
|
|
#define perf_evsel__set_sample_bit(evsel, bit) \
|
|
__perf_evsel__set_sample_bit(evsel, PERF_SAMPLE_##bit)
|
|
|
|
#define perf_evsel__reset_sample_bit(evsel, bit) \
|
|
__perf_evsel__reset_sample_bit(evsel, PERF_SAMPLE_##bit)
|
|
|
|
void perf_evsel__set_sample_id(struct perf_evsel *evsel);
|
|
|
|
int perf_evsel__set_filter(struct perf_evsel *evsel, int ncpus, int nthreads,
|
|
const char *filter);
|
|
|
|
int perf_evsel__open_per_cpu(struct perf_evsel *evsel,
|
|
struct cpu_map *cpus);
|
|
int perf_evsel__open_per_thread(struct perf_evsel *evsel,
|
|
struct thread_map *threads);
|
|
int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
|
|
struct thread_map *threads);
|
|
void perf_evsel__close(struct perf_evsel *evsel, int ncpus, int nthreads);
|
|
|
|
struct perf_sample;
|
|
|
|
void *perf_evsel__rawptr(struct perf_evsel *evsel, struct perf_sample *sample,
|
|
const char *name);
|
|
u64 perf_evsel__intval(struct perf_evsel *evsel, struct perf_sample *sample,
|
|
const char *name);
|
|
|
|
static inline char *perf_evsel__strval(struct perf_evsel *evsel,
|
|
struct perf_sample *sample,
|
|
const char *name)
|
|
{
|
|
return perf_evsel__rawptr(evsel, sample, name);
|
|
}
|
|
|
|
struct format_field;
|
|
|
|
struct format_field *perf_evsel__field(struct perf_evsel *evsel, const char *name);
|
|
|
|
#define perf_evsel__match(evsel, t, c) \
|
|
(evsel->attr.type == PERF_TYPE_##t && \
|
|
evsel->attr.config == PERF_COUNT_##c)
|
|
|
|
static inline bool perf_evsel__match2(struct perf_evsel *e1,
|
|
struct perf_evsel *e2)
|
|
{
|
|
return (e1->attr.type == e2->attr.type) &&
|
|
(e1->attr.config == e2->attr.config);
|
|
}
|
|
|
|
int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
|
|
int cpu, int thread, bool scale);
|
|
|
|
/**
|
|
* perf_evsel__read_on_cpu - Read out the results on a CPU and thread
|
|
*
|
|
* @evsel - event selector to read value
|
|
* @cpu - CPU of interest
|
|
* @thread - thread of interest
|
|
*/
|
|
static inline int perf_evsel__read_on_cpu(struct perf_evsel *evsel,
|
|
int cpu, int thread)
|
|
{
|
|
return __perf_evsel__read_on_cpu(evsel, cpu, thread, false);
|
|
}
|
|
|
|
/**
|
|
* perf_evsel__read_on_cpu_scaled - Read out the results on a CPU and thread, scaled
|
|
*
|
|
* @evsel - event selector to read value
|
|
* @cpu - CPU of interest
|
|
* @thread - thread of interest
|
|
*/
|
|
static inline int perf_evsel__read_on_cpu_scaled(struct perf_evsel *evsel,
|
|
int cpu, int thread)
|
|
{
|
|
return __perf_evsel__read_on_cpu(evsel, cpu, thread, true);
|
|
}
|
|
|
|
int __perf_evsel__read(struct perf_evsel *evsel, int ncpus, int nthreads,
|
|
bool scale);
|
|
|
|
/**
|
|
* perf_evsel__read - Read the aggregate results on all CPUs
|
|
*
|
|
* @evsel - event selector to read value
|
|
* @ncpus - Number of cpus affected, from zero
|
|
* @nthreads - Number of threads affected, from zero
|
|
*/
|
|
static inline int perf_evsel__read(struct perf_evsel *evsel,
|
|
int ncpus, int nthreads)
|
|
{
|
|
return __perf_evsel__read(evsel, ncpus, nthreads, false);
|
|
}
|
|
|
|
/**
|
|
* perf_evsel__read_scaled - Read the aggregate results on all CPUs, scaled
|
|
*
|
|
* @evsel - event selector to read value
|
|
* @ncpus - Number of cpus affected, from zero
|
|
* @nthreads - Number of threads affected, from zero
|
|
*/
|
|
static inline int perf_evsel__read_scaled(struct perf_evsel *evsel,
|
|
int ncpus, int nthreads)
|
|
{
|
|
return __perf_evsel__read(evsel, ncpus, nthreads, true);
|
|
}
|
|
|
|
void hists__init(struct hists *hists);
|
|
|
|
int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
|
|
struct perf_sample *sample);
|
|
|
|
static inline struct perf_evsel *perf_evsel__next(struct perf_evsel *evsel)
|
|
{
|
|
return list_entry(evsel->node.next, struct perf_evsel, node);
|
|
}
|
|
|
|
/**
|
|
* perf_evsel__is_group_leader - Return whether given evsel is a leader event
|
|
*
|
|
* @evsel - evsel selector to be tested
|
|
*
|
|
* Return %true if @evsel is a group leader or a stand-alone event
|
|
*/
|
|
static inline bool perf_evsel__is_group_leader(const struct perf_evsel *evsel)
|
|
{
|
|
return evsel->leader == evsel;
|
|
}
|
|
|
|
/**
|
|
* perf_evsel__is_group_event - Return whether given evsel is a group event
|
|
*
|
|
* @evsel - evsel selector to be tested
|
|
*
|
|
* Return %true iff event group view is enabled and @evsel is a actual group
|
|
* leader which has other members in the group
|
|
*/
|
|
static inline bool perf_evsel__is_group_event(struct perf_evsel *evsel)
|
|
{
|
|
if (!symbol_conf.event_group)
|
|
return false;
|
|
|
|
return perf_evsel__is_group_leader(evsel) && evsel->nr_members > 1;
|
|
}
|
|
|
|
struct perf_attr_details {
|
|
bool freq;
|
|
bool verbose;
|
|
bool event_group;
|
|
};
|
|
|
|
int perf_evsel__fprintf(struct perf_evsel *evsel,
|
|
struct perf_attr_details *details, FILE *fp);
|
|
|
|
bool perf_evsel__fallback(struct perf_evsel *evsel, int err,
|
|
char *msg, size_t msgsize);
|
|
int perf_evsel__open_strerror(struct perf_evsel *evsel,
|
|
struct perf_target *target,
|
|
int err, char *msg, size_t size);
|
|
|
|
static inline int perf_evsel__group_idx(struct perf_evsel *evsel)
|
|
{
|
|
return evsel->idx - evsel->leader->idx;
|
|
}
|
|
|
|
#define for_each_group_member(_evsel, _leader) \
|
|
for ((_evsel) = list_entry((_leader)->node.next, struct perf_evsel, node); \
|
|
(_evsel) && (_evsel)->leader == (_leader); \
|
|
(_evsel) = list_entry((_evsel)->node.next, struct perf_evsel, node))
|
|
|
|
#endif /* __PERF_EVSEL_H */
|