linux-stable/tools/perf/tests/task-exit.c
Leo Yan 5bd1406c51 perf test: Avoid infinite loop for task exit case
[ Upstream commit 791ce9c48c ]

When executing the task exit testing case, perf gets stuck in an endless
loop this case and doesn't return back on Arm64 Juno board.

After digging into this issue, since Juno board has Arm's big.LITTLE
CPUs, thus the PMUs are not compatible between the big CPUs and little
CPUs.  This leads to a PMU event that cannot be enabled properly when
the traced task is migrated from one variant's CPU to another variant.
Finally, the test case runs into infinite loop for cannot read out any
event data after return from polling.

Eventually, we need to work out formal solution to allow PMU events can
be freely migrated from one CPU variant to another, but this is a
difficult task and a different topic.  This patch tries to fix the Perf
test case to avoid infinite loop, when the testing detects 1000 times
retrying for reading empty events, it will directly bail out and return
failure.  This allows the Perf tool can continue its other test cases.

Signed-off-by: Leo Yan <leo.yan@linaro.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lore.kernel.org/lkml/20191011091942.29841-2-leo.yan@linaro.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
2019-12-31 16:44:06 +01:00

157 lines
3.5 KiB
C

// SPDX-License-Identifier: GPL-2.0
#include "debug.h"
#include "evlist.h"
#include "evsel.h"
#include "target.h"
#include "thread_map.h"
#include "tests.h"
#include "util/mmap.h"
#include <errno.h>
#include <signal.h>
#include <linux/string.h>
#include <perf/cpumap.h>
#include <perf/evlist.h>
static int exited;
static int nr_exit;
static void sig_handler(int sig __maybe_unused)
{
exited = 1;
}
/*
* perf_evlist__prepare_workload will send a SIGUSR1 if the fork fails, since
* we asked by setting its exec_error to this handler.
*/
static void workload_exec_failed_signal(int signo __maybe_unused,
siginfo_t *info __maybe_unused,
void *ucontext __maybe_unused)
{
exited = 1;
nr_exit = -1;
}
/*
* This test will start a workload that does nothing then it checks
* if the number of exit event reported by the kernel is 1 or not
* in order to check the kernel returns correct number of event.
*/
int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused)
{
int err = -1;
union perf_event *event;
struct evsel *evsel;
struct evlist *evlist;
struct target target = {
.uid = UINT_MAX,
.uses_mmap = true,
};
const char *argv[] = { "true", NULL };
char sbuf[STRERR_BUFSIZE];
struct perf_cpu_map *cpus;
struct perf_thread_map *threads;
struct mmap *md;
int retry_count = 0;
signal(SIGCHLD, sig_handler);
evlist = perf_evlist__new_default();
if (evlist == NULL) {
pr_debug("perf_evlist__new_default\n");
return -1;
}
/*
* Create maps of threads and cpus to monitor. In this case
* we start with all threads and cpus (-1, -1) but then in
* perf_evlist__prepare_workload we'll fill in the only thread
* we're monitoring, the one forked there.
*/
cpus = perf_cpu_map__dummy_new();
threads = thread_map__new_by_tid(-1);
if (!cpus || !threads) {
err = -ENOMEM;
pr_debug("Not enough memory to create thread/cpu maps\n");
goto out_free_maps;
}
perf_evlist__set_maps(&evlist->core, cpus, threads);
cpus = NULL;
threads = NULL;
err = perf_evlist__prepare_workload(evlist, &target, argv, false,
workload_exec_failed_signal);
if (err < 0) {
pr_debug("Couldn't run the workload!\n");
goto out_delete_evlist;
}
evsel = evlist__first(evlist);
evsel->core.attr.task = 1;
#ifdef __s390x__
evsel->core.attr.sample_freq = 1000000;
#else
evsel->core.attr.sample_freq = 1;
#endif
evsel->core.attr.inherit = 0;
evsel->core.attr.watermark = 0;
evsel->core.attr.wakeup_events = 1;
evsel->core.attr.exclude_kernel = 1;
err = evlist__open(evlist);
if (err < 0) {
pr_debug("Couldn't open the evlist: %s\n",
str_error_r(-err, sbuf, sizeof(sbuf)));
goto out_delete_evlist;
}
if (evlist__mmap(evlist, 128) < 0) {
pr_debug("failed to mmap events: %d (%s)\n", errno,
str_error_r(errno, sbuf, sizeof(sbuf)));
err = -1;
goto out_delete_evlist;
}
perf_evlist__start_workload(evlist);
retry:
md = &evlist->mmap[0];
if (perf_mmap__read_init(md) < 0)
goto out_init;
while ((event = perf_mmap__read_event(md)) != NULL) {
if (event->header.type == PERF_RECORD_EXIT)
nr_exit++;
perf_mmap__consume(md);
}
perf_mmap__read_done(md);
out_init:
if (!exited || !nr_exit) {
evlist__poll(evlist, -1);
if (retry_count++ > 1000) {
pr_debug("Failed after retrying 1000 times\n");
err = -1;
goto out_free_maps;
}
goto retry;
}
if (nr_exit != 1) {
pr_debug("received %d EXIT records\n", nr_exit);
err = -1;
}
out_free_maps:
perf_cpu_map__put(cpus);
perf_thread_map__put(threads);
out_delete_evlist:
evlist__delete(evlist);
return err;
}