mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-24 13:59:22 +07:00
79695e1bb6
When no event is specified the tools use perf_evlist__add_default(), that will
call event_attr_init to initialize the KVM exclusion bits.
When the change was made to the tools so that by default guest samples would be
excluded, the changes were made just to the parsing routines and to
perf_evlist__add_default(), not to perf_evlist__add_attrs, that is used so far
just by perf stat to add multiple events, according to the level of detail
specified.
Recently the tools were changed to reconstruct the event name from all the
details in perf_event_attr, not just from .type and .config, but taking into
account all the feature bits (.exclude_{guest,host,user,kernel,etc},
.precise_ip, etc).
That is when we noticed that the default for perf stat wasn't the one for the
rest of the tools, i.e. the .exclude_guest bit wasn't being set.
I.e. the default, that doesn't call event_attr_init was showing the :HG
modifier:
$ perf stat usleep 1
Performance counter stats for 'usleep 1':
0.942119 task-clock # 0.454 CPUs utilized
1 context-switches # 0.001 M/sec
0 CPU-migrations # 0.000 K/sec
126 page-faults # 0.134 M/sec
693,193 cycles:HG # 0.736 GHz [40.11%]
407,461 stalled-cycles-frontend:HG # 58.78% frontend cycles idle [72.29%]
365,403 stalled-cycles-backend:HG # 52.71% backend cycles idle
465,982 instructions:HG # 0.67 insns per cycle
# 0.87 stalled cycles per insn
89,760 branches:HG # 95.275 M/sec
6,178 branch-misses:HG # 6.88% of all branches
0.002077228 seconds time elapsed
While if one explicitely specifies the same events, which will make the parsing code
to be called and thus event_attr_init is called:
$ perf stat -e task-clock,context-switches,migrations,page-faults,cycles,stalled-cycles-frontend,stalled-cycles-backend,instructions,branches,branch-misses usleep 1
Performance counter stats for 'usleep 1':
1.040349 task-clock # 0.500 CPUs utilized
2 context-switches # 0.002 M/sec
0 CPU-migrations # 0.000 K/sec
127 page-faults # 0.122 M/sec
587,966 cycles # 0.565 GHz [13.18%]
459,167 stalled-cycles-frontend # 78.09% frontend cycles idle
390,249 stalled-cycles-backend # 66.37% backend cycles idle
504,006 instructions # 0.86 insns per cycle
# 0.91 stalled cycles per insn
96,455 branches # 92.714 M/sec
6,522 branch-misses # 6.76% of all branches [96.12%]
0.002078681 seconds time elapsed
Fix it by introducing a perf_evlist__add_default_attrs method that will call
evlist_attr_init in all the perf_event_attr entries before adding the events.
Reported-by: Ingo Molnar <mingo@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-4eysr236r0pgiyum9epwxw7s@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
130 lines
4.1 KiB
C
130 lines
4.1 KiB
C
#ifndef __PERF_EVLIST_H
|
|
#define __PERF_EVLIST_H 1
|
|
|
|
#include <linux/list.h>
|
|
#include <stdio.h>
|
|
#include "../perf.h"
|
|
#include "event.h"
|
|
#include "util.h"
|
|
#include <unistd.h>
|
|
|
|
struct pollfd;
|
|
struct thread_map;
|
|
struct cpu_map;
|
|
struct perf_record_opts;
|
|
|
|
#define PERF_EVLIST__HLIST_BITS 8
|
|
#define PERF_EVLIST__HLIST_SIZE (1 << PERF_EVLIST__HLIST_BITS)
|
|
|
|
struct perf_evlist {
|
|
struct list_head entries;
|
|
struct hlist_head heads[PERF_EVLIST__HLIST_SIZE];
|
|
int nr_entries;
|
|
int nr_fds;
|
|
int nr_mmaps;
|
|
int mmap_len;
|
|
struct {
|
|
int cork_fd;
|
|
pid_t pid;
|
|
} workload;
|
|
bool overwrite;
|
|
union perf_event event_copy;
|
|
struct perf_mmap *mmap;
|
|
struct pollfd *pollfd;
|
|
struct thread_map *threads;
|
|
struct cpu_map *cpus;
|
|
struct perf_evsel *selected;
|
|
};
|
|
|
|
struct perf_evsel_str_handler {
|
|
const char *name;
|
|
void *handler;
|
|
};
|
|
|
|
struct perf_evsel;
|
|
|
|
struct perf_evlist *perf_evlist__new(struct cpu_map *cpus,
|
|
struct thread_map *threads);
|
|
void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus,
|
|
struct thread_map *threads);
|
|
void perf_evlist__exit(struct perf_evlist *evlist);
|
|
void perf_evlist__delete(struct perf_evlist *evlist);
|
|
|
|
void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry);
|
|
int perf_evlist__add_default(struct perf_evlist *evlist);
|
|
int perf_evlist__add_attrs(struct perf_evlist *evlist,
|
|
struct perf_event_attr *attrs, size_t nr_attrs);
|
|
int __perf_evlist__add_default_attrs(struct perf_evlist *evlist,
|
|
struct perf_event_attr *attrs, size_t nr_attrs);
|
|
int perf_evlist__add_tracepoints(struct perf_evlist *evlist,
|
|
const char *tracepoints[], size_t nr_tracepoints);
|
|
int perf_evlist__set_tracepoints_handlers(struct perf_evlist *evlist,
|
|
const struct perf_evsel_str_handler *assocs,
|
|
size_t nr_assocs);
|
|
|
|
#define perf_evlist__add_attrs_array(evlist, array) \
|
|
perf_evlist__add_attrs(evlist, array, ARRAY_SIZE(array))
|
|
#define perf_evlist__add_default_attrs(evlist, array) \
|
|
__perf_evlist__add_default_attrs(evlist, array, ARRAY_SIZE(array))
|
|
|
|
#define perf_evlist__add_tracepoints_array(evlist, array) \
|
|
perf_evlist__add_tracepoints(evlist, array, ARRAY_SIZE(array))
|
|
|
|
#define perf_evlist__set_tracepoints_handlers_array(evlist, array) \
|
|
perf_evlist__set_tracepoints_handlers(evlist, array, ARRAY_SIZE(array))
|
|
|
|
void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel,
|
|
int cpu, int thread, u64 id);
|
|
|
|
void perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd);
|
|
|
|
struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id);
|
|
|
|
union perf_event *perf_evlist__mmap_read(struct perf_evlist *self, int idx);
|
|
|
|
int perf_evlist__open(struct perf_evlist *evlist, bool group);
|
|
|
|
void perf_evlist__config_attrs(struct perf_evlist *evlist,
|
|
struct perf_record_opts *opts);
|
|
|
|
int perf_evlist__prepare_workload(struct perf_evlist *evlist,
|
|
struct perf_record_opts *opts,
|
|
const char *argv[]);
|
|
int perf_evlist__start_workload(struct perf_evlist *evlist);
|
|
|
|
int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
|
|
bool overwrite);
|
|
void perf_evlist__munmap(struct perf_evlist *evlist);
|
|
|
|
void perf_evlist__disable(struct perf_evlist *evlist);
|
|
void perf_evlist__enable(struct perf_evlist *evlist);
|
|
|
|
void perf_evlist__set_selected(struct perf_evlist *evlist,
|
|
struct perf_evsel *evsel);
|
|
|
|
static inline void perf_evlist__set_maps(struct perf_evlist *evlist,
|
|
struct cpu_map *cpus,
|
|
struct thread_map *threads)
|
|
{
|
|
evlist->cpus = cpus;
|
|
evlist->threads = threads;
|
|
}
|
|
|
|
int perf_evlist__create_maps(struct perf_evlist *evlist,
|
|
struct perf_target *target);
|
|
void perf_evlist__delete_maps(struct perf_evlist *evlist);
|
|
int perf_evlist__set_filters(struct perf_evlist *evlist);
|
|
|
|
u64 perf_evlist__sample_type(const struct perf_evlist *evlist);
|
|
bool perf_evlist__sample_id_all(const const struct perf_evlist *evlist);
|
|
u16 perf_evlist__id_hdr_size(const struct perf_evlist *evlist);
|
|
|
|
bool perf_evlist__valid_sample_type(const struct perf_evlist *evlist);
|
|
bool perf_evlist__valid_sample_id_all(const struct perf_evlist *evlist);
|
|
|
|
void perf_evlist__splice_list_tail(struct perf_evlist *evlist,
|
|
struct list_head *list,
|
|
int nr_entries);
|
|
|
|
#endif /* __PERF_EVLIST_H */
|