mirror of
https://github.com/FEX-Emu/linux.git
synced 2024-12-24 02:18:54 +00:00
0252208eb5
And a test for it: [acme@felicio linux]$ perf test 1: vmlinux symtab matches kallsyms: Ok 2: detect open syscall event: Ok 3: detect open syscall event on all cpus: Ok [acme@felicio linux]$ Translating C the test does: 1. generates different number of open syscalls on each CPU by using sched_setaffinity 2. Verifies that the expected number of events is generated on each CPU It works as expected. LKML-Reference: <new-submission> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Tom Zanussi <tzanussi@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
202 lines
4.3 KiB
C
202 lines
4.3 KiB
C
#include "evsel.h"
|
|
#include "../perf.h"
|
|
#include "util.h"
|
|
#include "cpumap.h"
|
|
#include "thread.h"
|
|
|
|
#define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
|
|
|
|
struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx)
|
|
{
|
|
struct perf_evsel *evsel = zalloc(sizeof(*evsel));
|
|
|
|
if (evsel != NULL) {
|
|
evsel->idx = idx;
|
|
evsel->attr = *attr;
|
|
INIT_LIST_HEAD(&evsel->node);
|
|
}
|
|
|
|
return evsel;
|
|
}
|
|
|
|
int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
|
|
{
|
|
evsel->fd = xyarray__new(ncpus, nthreads, sizeof(int));
|
|
return evsel->fd != NULL ? 0 : -ENOMEM;
|
|
}
|
|
|
|
int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus)
|
|
{
|
|
evsel->counts = zalloc((sizeof(*evsel->counts) +
|
|
(ncpus * sizeof(struct perf_counts_values))));
|
|
return evsel->counts != NULL ? 0 : -ENOMEM;
|
|
}
|
|
|
|
void perf_evsel__free_fd(struct perf_evsel *evsel)
|
|
{
|
|
xyarray__delete(evsel->fd);
|
|
evsel->fd = NULL;
|
|
}
|
|
|
|
void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
|
|
{
|
|
int cpu, thread;
|
|
|
|
for (cpu = 0; cpu < ncpus; cpu++)
|
|
for (thread = 0; thread < nthreads; ++thread) {
|
|
close(FD(evsel, cpu, thread));
|
|
FD(evsel, cpu, thread) = -1;
|
|
}
|
|
}
|
|
|
|
void perf_evsel__delete(struct perf_evsel *evsel)
|
|
{
|
|
assert(list_empty(&evsel->node));
|
|
xyarray__delete(evsel->fd);
|
|
free(evsel);
|
|
}
|
|
|
|
int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
|
|
int cpu, int thread, bool scale)
|
|
{
|
|
struct perf_counts_values count;
|
|
size_t nv = scale ? 3 : 1;
|
|
|
|
if (FD(evsel, cpu, thread) < 0)
|
|
return -EINVAL;
|
|
|
|
if (evsel->counts == NULL && perf_evsel__alloc_counts(evsel, cpu + 1) < 0)
|
|
return -ENOMEM;
|
|
|
|
if (readn(FD(evsel, cpu, thread), &count, nv * sizeof(u64)) < 0)
|
|
return -errno;
|
|
|
|
if (scale) {
|
|
if (count.run == 0)
|
|
count.val = 0;
|
|
else if (count.run < count.ena)
|
|
count.val = (u64)((double)count.val * count.ena / count.run + 0.5);
|
|
} else
|
|
count.ena = count.run = 0;
|
|
|
|
evsel->counts->cpu[cpu] = count;
|
|
return 0;
|
|
}
|
|
|
|
int __perf_evsel__read(struct perf_evsel *evsel,
|
|
int ncpus, int nthreads, bool scale)
|
|
{
|
|
size_t nv = scale ? 3 : 1;
|
|
int cpu, thread;
|
|
struct perf_counts_values *aggr = &evsel->counts->aggr, count;
|
|
|
|
aggr->val = 0;
|
|
|
|
for (cpu = 0; cpu < ncpus; cpu++) {
|
|
for (thread = 0; thread < nthreads; thread++) {
|
|
if (FD(evsel, cpu, thread) < 0)
|
|
continue;
|
|
|
|
if (readn(FD(evsel, cpu, thread),
|
|
&count, nv * sizeof(u64)) < 0)
|
|
return -errno;
|
|
|
|
aggr->val += count.val;
|
|
if (scale) {
|
|
aggr->ena += count.ena;
|
|
aggr->run += count.run;
|
|
}
|
|
}
|
|
}
|
|
|
|
evsel->counts->scaled = 0;
|
|
if (scale) {
|
|
if (aggr->run == 0) {
|
|
evsel->counts->scaled = -1;
|
|
aggr->val = 0;
|
|
return 0;
|
|
}
|
|
|
|
if (aggr->run < aggr->ena) {
|
|
evsel->counts->scaled = 1;
|
|
aggr->val = (u64)((double)aggr->val * aggr->ena / aggr->run + 0.5);
|
|
}
|
|
} else
|
|
aggr->ena = aggr->run = 0;
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
|
|
struct thread_map *threads)
|
|
{
|
|
int cpu, thread;
|
|
|
|
if (evsel->fd == NULL &&
|
|
perf_evsel__alloc_fd(evsel, cpus->nr, threads->nr) < 0)
|
|
return -1;
|
|
|
|
for (cpu = 0; cpu < cpus->nr; cpu++) {
|
|
for (thread = 0; thread < threads->nr; thread++) {
|
|
FD(evsel, cpu, thread) = sys_perf_event_open(&evsel->attr,
|
|
threads->map[thread],
|
|
cpus->map[cpu], -1, 0);
|
|
if (FD(evsel, cpu, thread) < 0)
|
|
goto out_close;
|
|
}
|
|
}
|
|
|
|
return 0;
|
|
|
|
out_close:
|
|
do {
|
|
while (--thread >= 0) {
|
|
close(FD(evsel, cpu, thread));
|
|
FD(evsel, cpu, thread) = -1;
|
|
}
|
|
thread = threads->nr;
|
|
} while (--cpu >= 0);
|
|
return -1;
|
|
}
|
|
|
|
static struct {
|
|
struct cpu_map map;
|
|
int cpus[1];
|
|
} empty_cpu_map = {
|
|
.map.nr = 1,
|
|
.cpus = { -1, },
|
|
};
|
|
|
|
static struct {
|
|
struct thread_map map;
|
|
int threads[1];
|
|
} empty_thread_map = {
|
|
.map.nr = 1,
|
|
.threads = { -1, },
|
|
};
|
|
|
|
int perf_evsel__open(struct perf_evsel *evsel,
|
|
struct cpu_map *cpus, struct thread_map *threads)
|
|
{
|
|
|
|
if (cpus == NULL) {
|
|
/* Work around old compiler warnings about strict aliasing */
|
|
cpus = &empty_cpu_map.map;
|
|
}
|
|
|
|
if (threads == NULL)
|
|
threads = &empty_thread_map.map;
|
|
|
|
return __perf_evsel__open(evsel, cpus, threads);
|
|
}
|
|
|
|
int perf_evsel__open_per_cpu(struct perf_evsel *evsel, struct cpu_map *cpus)
|
|
{
|
|
return __perf_evsel__open(evsel, cpus, &empty_thread_map.map);
|
|
}
|
|
|
|
int perf_evsel__open_per_thread(struct perf_evsel *evsel, struct thread_map *threads)
|
|
{
|
|
return __perf_evsel__open(evsel, &empty_cpu_map.map, threads);
|
|
}
|