mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-11-29 23:24:11 +08:00
6d18804b96
A common problem is confusing CPU map indices with the CPU, by wrapping the CPU with a struct then this is avoided. This approach is similar to atomic_t. Committer notes: To make it build with BUILD_BPF_SKEL=1 these files needed the conversions to 'struct perf_cpu' usage: tools/perf/util/bpf_counter.c tools/perf/util/bpf_counter_cgroup.c tools/perf/util/bpf_ftrace.c Also perf_env__get_cpu() was removed back in "perf cpumap: Switch cpu_map__build_map to cpu function". Additionally these needed to be fixed for the ARM builds to complete: tools/perf/arch/arm/util/cs-etm.c tools/perf/arch/arm64/util/pmu.c Suggested-by: John Garry <john.garry@huawei.com> Signed-off-by: Ian Rogers <irogers@google.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mathieu Poirier <mathieu.poirier@linaro.org> Cc: Mike Leach <mike.leach@linaro.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Clarke <pc@us.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Riccardo Mancini <rickyman7@gmail.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Vineet Singh <vineet.singh@intel.com> Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Cc: zhengjun.xing@intel.com Link: https://lore.kernel.org/r/20220105061351.120843-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
198 lines
3.8 KiB
C
198 lines
3.8 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
|
|
#include "perf-sys.h"
|
|
#include "util/cloexec.h"
|
|
#include "util/evlist.h"
|
|
#include "util/evsel.h"
|
|
#include "util/parse-events.h"
|
|
#include "util/perf_api_probe.h"
|
|
#include <perf/cpumap.h>
|
|
#include <errno.h>
|
|
|
|
typedef void (*setup_probe_fn_t)(struct evsel *evsel);
|
|
|
|
static int perf_do_probe_api(setup_probe_fn_t fn, struct perf_cpu cpu, const char *str)
|
|
{
|
|
struct evlist *evlist;
|
|
struct evsel *evsel;
|
|
unsigned long flags = perf_event_open_cloexec_flag();
|
|
int err = -EAGAIN, fd;
|
|
static pid_t pid = -1;
|
|
|
|
evlist = evlist__new();
|
|
if (!evlist)
|
|
return -ENOMEM;
|
|
|
|
if (parse_events(evlist, str, NULL))
|
|
goto out_delete;
|
|
|
|
evsel = evlist__first(evlist);
|
|
|
|
while (1) {
|
|
fd = sys_perf_event_open(&evsel->core.attr, pid, cpu.cpu, -1, flags);
|
|
if (fd < 0) {
|
|
if (pid == -1 && errno == EACCES) {
|
|
pid = 0;
|
|
continue;
|
|
}
|
|
goto out_delete;
|
|
}
|
|
break;
|
|
}
|
|
close(fd);
|
|
|
|
fn(evsel);
|
|
|
|
fd = sys_perf_event_open(&evsel->core.attr, pid, cpu.cpu, -1, flags);
|
|
if (fd < 0) {
|
|
if (errno == EINVAL)
|
|
err = -EINVAL;
|
|
goto out_delete;
|
|
}
|
|
close(fd);
|
|
err = 0;
|
|
|
|
out_delete:
|
|
evlist__delete(evlist);
|
|
return err;
|
|
}
|
|
|
|
static bool perf_probe_api(setup_probe_fn_t fn)
|
|
{
|
|
const char *try[] = {"cycles:u", "instructions:u", "cpu-clock:u", NULL};
|
|
struct perf_cpu_map *cpus;
|
|
struct perf_cpu cpu;
|
|
int ret, i = 0;
|
|
|
|
cpus = perf_cpu_map__new(NULL);
|
|
if (!cpus)
|
|
return false;
|
|
cpu = cpus->map[0];
|
|
perf_cpu_map__put(cpus);
|
|
|
|
do {
|
|
ret = perf_do_probe_api(fn, cpu, try[i++]);
|
|
if (!ret)
|
|
return true;
|
|
} while (ret == -EAGAIN && try[i]);
|
|
|
|
return false;
|
|
}
|
|
|
|
static void perf_probe_sample_identifier(struct evsel *evsel)
|
|
{
|
|
evsel->core.attr.sample_type |= PERF_SAMPLE_IDENTIFIER;
|
|
}
|
|
|
|
static void perf_probe_comm_exec(struct evsel *evsel)
|
|
{
|
|
evsel->core.attr.comm_exec = 1;
|
|
}
|
|
|
|
static void perf_probe_context_switch(struct evsel *evsel)
|
|
{
|
|
evsel->core.attr.context_switch = 1;
|
|
}
|
|
|
|
static void perf_probe_text_poke(struct evsel *evsel)
|
|
{
|
|
evsel->core.attr.text_poke = 1;
|
|
}
|
|
|
|
static void perf_probe_build_id(struct evsel *evsel)
|
|
{
|
|
evsel->core.attr.build_id = 1;
|
|
}
|
|
|
|
static void perf_probe_cgroup(struct evsel *evsel)
|
|
{
|
|
evsel->core.attr.cgroup = 1;
|
|
}
|
|
|
|
bool perf_can_sample_identifier(void)
|
|
{
|
|
return perf_probe_api(perf_probe_sample_identifier);
|
|
}
|
|
|
|
bool perf_can_comm_exec(void)
|
|
{
|
|
return perf_probe_api(perf_probe_comm_exec);
|
|
}
|
|
|
|
bool perf_can_record_switch_events(void)
|
|
{
|
|
return perf_probe_api(perf_probe_context_switch);
|
|
}
|
|
|
|
bool perf_can_record_text_poke_events(void)
|
|
{
|
|
return perf_probe_api(perf_probe_text_poke);
|
|
}
|
|
|
|
bool perf_can_record_cpu_wide(void)
|
|
{
|
|
struct perf_event_attr attr = {
|
|
.type = PERF_TYPE_SOFTWARE,
|
|
.config = PERF_COUNT_SW_CPU_CLOCK,
|
|
.exclude_kernel = 1,
|
|
};
|
|
struct perf_cpu_map *cpus;
|
|
struct perf_cpu cpu;
|
|
int fd;
|
|
|
|
cpus = perf_cpu_map__new(NULL);
|
|
if (!cpus)
|
|
return false;
|
|
|
|
cpu = cpus->map[0];
|
|
perf_cpu_map__put(cpus);
|
|
|
|
fd = sys_perf_event_open(&attr, -1, cpu.cpu, -1, 0);
|
|
if (fd < 0)
|
|
return false;
|
|
close(fd);
|
|
|
|
return true;
|
|
}
|
|
|
|
/*
|
|
* Architectures are expected to know if AUX area sampling is supported by the
|
|
* hardware. Here we check for kernel support.
|
|
*/
|
|
bool perf_can_aux_sample(void)
|
|
{
|
|
struct perf_event_attr attr = {
|
|
.size = sizeof(struct perf_event_attr),
|
|
.exclude_kernel = 1,
|
|
/*
|
|
* Non-zero value causes the kernel to calculate the effective
|
|
* attribute size up to that byte.
|
|
*/
|
|
.aux_sample_size = 1,
|
|
};
|
|
int fd;
|
|
|
|
fd = sys_perf_event_open(&attr, -1, 0, -1, 0);
|
|
/*
|
|
* If the kernel attribute is big enough to contain aux_sample_size
|
|
* then we assume that it is supported. We are relying on the kernel to
|
|
* validate the attribute size before anything else that could be wrong.
|
|
*/
|
|
if (fd < 0 && errno == E2BIG)
|
|
return false;
|
|
if (fd >= 0)
|
|
close(fd);
|
|
|
|
return true;
|
|
}
|
|
|
|
bool perf_can_record_build_id(void)
|
|
{
|
|
return perf_probe_api(perf_probe_build_id);
|
|
}
|
|
|
|
bool perf_can_record_cgroup(void)
|
|
{
|
|
return perf_probe_api(perf_probe_cgroup);
|
|
}
|