94f9eb95d9
perf_pmus__has_hybrid was used to detect when there was >1 core PMU, this can be achieved with perf_pmus__num_core_pmus that doesn't depend upon is_pmu_hybrid and PMU name comparisons. When modifying the function calls take the opportunity to improve comments, enable/simplify tests that were previously failing for hybrid but now pass and to simplify generic code. Reviewed-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ali Saidi <alisaidi@amazon.com> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Dmitrii Dolgov <9erthalion6@gmail.com> Cc: Huacai Chen <chenhuacai@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kang Minchul <tegongkang@gmail.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Madhavan Srinivasan <maddy@linux.ibm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mike Leach <mike.leach@linaro.org> Cc: Ming Wang <wangming01@loongson.cn> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Rob Herring <robh@kernel.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Will Deacon <will@kernel.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230527072210.2900565-34-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
587 lines
13 KiB
C
587 lines
13 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
#include <sys/time.h>
|
|
#include <sys/prctl.h>
|
|
#include <errno.h>
|
|
#include <limits.h>
|
|
#include <time.h>
|
|
#include <stdlib.h>
|
|
#include <linux/zalloc.h>
|
|
#include <linux/err.h>
|
|
#include <perf/cpumap.h>
|
|
#include <perf/evlist.h>
|
|
#include <perf/mmap.h>
|
|
|
|
#include "debug.h"
|
|
#include "parse-events.h"
|
|
#include "evlist.h"
|
|
#include "evsel.h"
|
|
#include "thread_map.h"
|
|
#include "record.h"
|
|
#include "tests.h"
|
|
#include "util/mmap.h"
|
|
#include "util/sample.h"
|
|
#include "pmus.h"
|
|
|
|
static int spin_sleep(void)
|
|
{
|
|
struct timeval start, now, diff, maxtime;
|
|
struct timespec ts;
|
|
int err, i;
|
|
|
|
maxtime.tv_sec = 0;
|
|
maxtime.tv_usec = 50000;
|
|
|
|
err = gettimeofday(&start, NULL);
|
|
if (err)
|
|
return err;
|
|
|
|
/* Spin for 50ms */
|
|
while (1) {
|
|
for (i = 0; i < 1000; i++)
|
|
barrier();
|
|
|
|
err = gettimeofday(&now, NULL);
|
|
if (err)
|
|
return err;
|
|
|
|
timersub(&now, &start, &diff);
|
|
if (timercmp(&diff, &maxtime, > /* For checkpatch */))
|
|
break;
|
|
}
|
|
|
|
ts.tv_nsec = 50 * 1000 * 1000;
|
|
ts.tv_sec = 0;
|
|
|
|
/* Sleep for 50ms */
|
|
err = nanosleep(&ts, NULL);
|
|
if (err == EINTR)
|
|
err = 0;
|
|
|
|
return err;
|
|
}
|
|
|
|
struct switch_tracking {
|
|
struct evsel *switch_evsel;
|
|
struct evsel *cycles_evsel;
|
|
pid_t *tids;
|
|
int nr_tids;
|
|
int comm_seen[4];
|
|
int cycles_before_comm_1;
|
|
int cycles_between_comm_2_and_comm_3;
|
|
int cycles_after_comm_4;
|
|
};
|
|
|
|
static int check_comm(struct switch_tracking *switch_tracking,
|
|
union perf_event *event, const char *comm, int nr)
|
|
{
|
|
if (event->header.type == PERF_RECORD_COMM &&
|
|
(pid_t)event->comm.pid == getpid() &&
|
|
(pid_t)event->comm.tid == getpid() &&
|
|
strcmp(event->comm.comm, comm) == 0) {
|
|
if (switch_tracking->comm_seen[nr]) {
|
|
pr_debug("Duplicate comm event\n");
|
|
return -1;
|
|
}
|
|
switch_tracking->comm_seen[nr] = 1;
|
|
pr_debug3("comm event: %s nr: %d\n", event->comm.comm, nr);
|
|
return 1;
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
static int check_cpu(struct switch_tracking *switch_tracking, int cpu)
|
|
{
|
|
int i, nr = cpu + 1;
|
|
|
|
if (cpu < 0)
|
|
return -1;
|
|
|
|
if (!switch_tracking->tids) {
|
|
switch_tracking->tids = calloc(nr, sizeof(pid_t));
|
|
if (!switch_tracking->tids)
|
|
return -1;
|
|
for (i = 0; i < nr; i++)
|
|
switch_tracking->tids[i] = -1;
|
|
switch_tracking->nr_tids = nr;
|
|
return 0;
|
|
}
|
|
|
|
if (cpu >= switch_tracking->nr_tids) {
|
|
void *addr;
|
|
|
|
addr = realloc(switch_tracking->tids, nr * sizeof(pid_t));
|
|
if (!addr)
|
|
return -1;
|
|
switch_tracking->tids = addr;
|
|
for (i = switch_tracking->nr_tids; i < nr; i++)
|
|
switch_tracking->tids[i] = -1;
|
|
switch_tracking->nr_tids = nr;
|
|
return 0;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int process_sample_event(struct evlist *evlist,
|
|
union perf_event *event,
|
|
struct switch_tracking *switch_tracking)
|
|
{
|
|
struct perf_sample sample;
|
|
struct evsel *evsel;
|
|
pid_t next_tid, prev_tid;
|
|
int cpu, err;
|
|
|
|
if (evlist__parse_sample(evlist, event, &sample)) {
|
|
pr_debug("evlist__parse_sample failed\n");
|
|
return -1;
|
|
}
|
|
|
|
evsel = evlist__id2evsel(evlist, sample.id);
|
|
if (evsel == switch_tracking->switch_evsel) {
|
|
next_tid = evsel__intval(evsel, &sample, "next_pid");
|
|
prev_tid = evsel__intval(evsel, &sample, "prev_pid");
|
|
cpu = sample.cpu;
|
|
pr_debug3("sched_switch: cpu: %d prev_tid %d next_tid %d\n",
|
|
cpu, prev_tid, next_tid);
|
|
err = check_cpu(switch_tracking, cpu);
|
|
if (err)
|
|
return err;
|
|
/*
|
|
* Check for no missing sched_switch events i.e. that the
|
|
* evsel->core.system_wide flag has worked.
|
|
*/
|
|
if (switch_tracking->tids[cpu] != -1 &&
|
|
switch_tracking->tids[cpu] != prev_tid) {
|
|
pr_debug("Missing sched_switch events\n");
|
|
return -1;
|
|
}
|
|
switch_tracking->tids[cpu] = next_tid;
|
|
}
|
|
|
|
if (evsel == switch_tracking->cycles_evsel) {
|
|
pr_debug3("cycles event\n");
|
|
if (!switch_tracking->comm_seen[0])
|
|
switch_tracking->cycles_before_comm_1 = 1;
|
|
if (switch_tracking->comm_seen[1] &&
|
|
!switch_tracking->comm_seen[2])
|
|
switch_tracking->cycles_between_comm_2_and_comm_3 = 1;
|
|
if (switch_tracking->comm_seen[3])
|
|
switch_tracking->cycles_after_comm_4 = 1;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int process_event(struct evlist *evlist, union perf_event *event,
|
|
struct switch_tracking *switch_tracking)
|
|
{
|
|
if (event->header.type == PERF_RECORD_SAMPLE)
|
|
return process_sample_event(evlist, event, switch_tracking);
|
|
|
|
if (event->header.type == PERF_RECORD_COMM) {
|
|
int err, done = 0;
|
|
|
|
err = check_comm(switch_tracking, event, "Test COMM 1", 0);
|
|
if (err < 0)
|
|
return -1;
|
|
done += err;
|
|
err = check_comm(switch_tracking, event, "Test COMM 2", 1);
|
|
if (err < 0)
|
|
return -1;
|
|
done += err;
|
|
err = check_comm(switch_tracking, event, "Test COMM 3", 2);
|
|
if (err < 0)
|
|
return -1;
|
|
done += err;
|
|
err = check_comm(switch_tracking, event, "Test COMM 4", 3);
|
|
if (err < 0)
|
|
return -1;
|
|
done += err;
|
|
if (done != 1) {
|
|
pr_debug("Unexpected comm event\n");
|
|
return -1;
|
|
}
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
struct event_node {
|
|
struct list_head list;
|
|
union perf_event *event;
|
|
u64 event_time;
|
|
};
|
|
|
|
static int add_event(struct evlist *evlist, struct list_head *events,
|
|
union perf_event *event)
|
|
{
|
|
struct perf_sample sample;
|
|
struct event_node *node;
|
|
|
|
node = malloc(sizeof(struct event_node));
|
|
if (!node) {
|
|
pr_debug("malloc failed\n");
|
|
return -1;
|
|
}
|
|
node->event = event;
|
|
list_add(&node->list, events);
|
|
|
|
if (evlist__parse_sample(evlist, event, &sample)) {
|
|
pr_debug("evlist__parse_sample failed\n");
|
|
return -1;
|
|
}
|
|
|
|
if (!sample.time) {
|
|
pr_debug("event with no time\n");
|
|
return -1;
|
|
}
|
|
|
|
node->event_time = sample.time;
|
|
|
|
return 0;
|
|
}
|
|
|
|
static void free_event_nodes(struct list_head *events)
|
|
{
|
|
struct event_node *node;
|
|
|
|
while (!list_empty(events)) {
|
|
node = list_entry(events->next, struct event_node, list);
|
|
list_del_init(&node->list);
|
|
free(node);
|
|
}
|
|
}
|
|
|
|
static int compar(const void *a, const void *b)
|
|
{
|
|
const struct event_node *nodea = a;
|
|
const struct event_node *nodeb = b;
|
|
s64 cmp = nodea->event_time - nodeb->event_time;
|
|
|
|
return cmp;
|
|
}
|
|
|
|
static int process_events(struct evlist *evlist,
|
|
struct switch_tracking *switch_tracking)
|
|
{
|
|
union perf_event *event;
|
|
unsigned pos, cnt = 0;
|
|
LIST_HEAD(events);
|
|
struct event_node *events_array, *node;
|
|
struct mmap *md;
|
|
int i, ret;
|
|
|
|
for (i = 0; i < evlist->core.nr_mmaps; i++) {
|
|
md = &evlist->mmap[i];
|
|
if (perf_mmap__read_init(&md->core) < 0)
|
|
continue;
|
|
|
|
while ((event = perf_mmap__read_event(&md->core)) != NULL) {
|
|
cnt += 1;
|
|
ret = add_event(evlist, &events, event);
|
|
perf_mmap__consume(&md->core);
|
|
if (ret < 0)
|
|
goto out_free_nodes;
|
|
}
|
|
perf_mmap__read_done(&md->core);
|
|
}
|
|
|
|
events_array = calloc(cnt, sizeof(struct event_node));
|
|
if (!events_array) {
|
|
pr_debug("calloc failed\n");
|
|
ret = -1;
|
|
goto out_free_nodes;
|
|
}
|
|
|
|
pos = 0;
|
|
list_for_each_entry(node, &events, list)
|
|
events_array[pos++] = *node;
|
|
|
|
qsort(events_array, cnt, sizeof(struct event_node), compar);
|
|
|
|
for (pos = 0; pos < cnt; pos++) {
|
|
ret = process_event(evlist, events_array[pos].event,
|
|
switch_tracking);
|
|
if (ret < 0)
|
|
goto out_free;
|
|
}
|
|
|
|
ret = 0;
|
|
out_free:
|
|
pr_debug("%u events recorded\n", cnt);
|
|
free(events_array);
|
|
out_free_nodes:
|
|
free_event_nodes(&events);
|
|
return ret;
|
|
}
|
|
|
|
/**
|
|
* test__switch_tracking - test using sched_switch and tracking events.
|
|
*
|
|
* This function implements a test that checks that sched_switch events and
|
|
* tracking events can be recorded for a workload (current process) using the
|
|
* evsel->core.system_wide and evsel->tracking flags (respectively) with other events
|
|
* sometimes enabled or disabled.
|
|
*/
|
|
static int test__switch_tracking(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
|
|
{
|
|
const char *sched_switch = "sched:sched_switch";
|
|
const char *cycles = "cycles:u";
|
|
struct switch_tracking switch_tracking = { .tids = NULL, };
|
|
struct record_opts opts = {
|
|
.mmap_pages = UINT_MAX,
|
|
.user_freq = UINT_MAX,
|
|
.user_interval = ULLONG_MAX,
|
|
.freq = 4000,
|
|
.target = {
|
|
.uses_mmap = true,
|
|
},
|
|
};
|
|
struct perf_thread_map *threads = NULL;
|
|
struct perf_cpu_map *cpus = NULL;
|
|
struct evlist *evlist = NULL;
|
|
struct evsel *evsel, *cpu_clocks_evsel, *cycles_evsel;
|
|
struct evsel *switch_evsel, *tracking_evsel;
|
|
const char *comm;
|
|
int err = -1;
|
|
|
|
threads = thread_map__new(-1, getpid(), UINT_MAX);
|
|
if (!threads) {
|
|
pr_debug("thread_map__new failed!\n");
|
|
goto out_err;
|
|
}
|
|
|
|
cpus = perf_cpu_map__new(NULL);
|
|
if (!cpus) {
|
|
pr_debug("perf_cpu_map__new failed!\n");
|
|
goto out_err;
|
|
}
|
|
|
|
evlist = evlist__new();
|
|
if (!evlist) {
|
|
pr_debug("evlist__new failed!\n");
|
|
goto out_err;
|
|
}
|
|
|
|
perf_evlist__set_maps(&evlist->core, cpus, threads);
|
|
|
|
/* First event */
|
|
err = parse_event(evlist, "cpu-clock:u");
|
|
if (err) {
|
|
pr_debug("Failed to parse event dummy:u\n");
|
|
goto out_err;
|
|
}
|
|
|
|
cpu_clocks_evsel = evlist__last(evlist);
|
|
|
|
/* Second event */
|
|
err = parse_event(evlist, cycles);
|
|
if (err) {
|
|
pr_debug("Failed to parse event %s\n", cycles);
|
|
goto out_err;
|
|
}
|
|
|
|
cycles_evsel = evlist__last(evlist);
|
|
|
|
/* Third event */
|
|
if (!evlist__can_select_event(evlist, sched_switch)) {
|
|
pr_debug("No sched_switch\n");
|
|
err = 0;
|
|
goto out;
|
|
}
|
|
|
|
switch_evsel = evlist__add_sched_switch(evlist, true);
|
|
if (IS_ERR(switch_evsel)) {
|
|
err = PTR_ERR(switch_evsel);
|
|
pr_debug("Failed to create event %s\n", sched_switch);
|
|
goto out_err;
|
|
}
|
|
|
|
switch_evsel->immediate = true;
|
|
|
|
/* Test moving an event to the front */
|
|
if (cycles_evsel == evlist__first(evlist)) {
|
|
pr_debug("cycles event already at front");
|
|
goto out_err;
|
|
}
|
|
evlist__to_front(evlist, cycles_evsel);
|
|
if (cycles_evsel != evlist__first(evlist)) {
|
|
pr_debug("Failed to move cycles event to front");
|
|
goto out_err;
|
|
}
|
|
|
|
evsel__set_sample_bit(cycles_evsel, CPU);
|
|
evsel__set_sample_bit(cycles_evsel, TIME);
|
|
|
|
/* Fourth event */
|
|
err = parse_event(evlist, "dummy:u");
|
|
if (err) {
|
|
pr_debug("Failed to parse event dummy:u\n");
|
|
goto out_err;
|
|
}
|
|
|
|
tracking_evsel = evlist__last(evlist);
|
|
|
|
evlist__set_tracking_event(evlist, tracking_evsel);
|
|
|
|
tracking_evsel->core.attr.freq = 0;
|
|
tracking_evsel->core.attr.sample_period = 1;
|
|
|
|
evsel__set_sample_bit(tracking_evsel, TIME);
|
|
|
|
/* Config events */
|
|
evlist__config(evlist, &opts, NULL);
|
|
|
|
/* Check moved event is still at the front */
|
|
if (cycles_evsel != evlist__first(evlist)) {
|
|
pr_debug("Front event no longer at front");
|
|
goto out_err;
|
|
}
|
|
|
|
/* Check tracking event is tracking */
|
|
if (!tracking_evsel->core.attr.mmap || !tracking_evsel->core.attr.comm) {
|
|
pr_debug("Tracking event not tracking\n");
|
|
goto out_err;
|
|
}
|
|
|
|
/* Check non-tracking events are not tracking */
|
|
evlist__for_each_entry(evlist, evsel) {
|
|
if (evsel != tracking_evsel) {
|
|
if (evsel->core.attr.mmap || evsel->core.attr.comm) {
|
|
pr_debug("Non-tracking event is tracking\n");
|
|
goto out_err;
|
|
}
|
|
}
|
|
}
|
|
|
|
if (evlist__open(evlist) < 0) {
|
|
pr_debug("Not supported\n");
|
|
err = 0;
|
|
goto out;
|
|
}
|
|
|
|
err = evlist__mmap(evlist, UINT_MAX);
|
|
if (err) {
|
|
pr_debug("evlist__mmap failed!\n");
|
|
goto out_err;
|
|
}
|
|
|
|
evlist__enable(evlist);
|
|
|
|
err = evsel__disable(cpu_clocks_evsel);
|
|
if (err) {
|
|
pr_debug("perf_evlist__disable_event failed!\n");
|
|
goto out_err;
|
|
}
|
|
|
|
err = spin_sleep();
|
|
if (err) {
|
|
pr_debug("spin_sleep failed!\n");
|
|
goto out_err;
|
|
}
|
|
|
|
comm = "Test COMM 1";
|
|
err = prctl(PR_SET_NAME, (unsigned long)comm, 0, 0, 0);
|
|
if (err) {
|
|
pr_debug("PR_SET_NAME failed!\n");
|
|
goto out_err;
|
|
}
|
|
|
|
err = evsel__disable(cycles_evsel);
|
|
if (err) {
|
|
pr_debug("perf_evlist__disable_event failed!\n");
|
|
goto out_err;
|
|
}
|
|
|
|
comm = "Test COMM 2";
|
|
err = prctl(PR_SET_NAME, (unsigned long)comm, 0, 0, 0);
|
|
if (err) {
|
|
pr_debug("PR_SET_NAME failed!\n");
|
|
goto out_err;
|
|
}
|
|
|
|
err = spin_sleep();
|
|
if (err) {
|
|
pr_debug("spin_sleep failed!\n");
|
|
goto out_err;
|
|
}
|
|
|
|
comm = "Test COMM 3";
|
|
err = prctl(PR_SET_NAME, (unsigned long)comm, 0, 0, 0);
|
|
if (err) {
|
|
pr_debug("PR_SET_NAME failed!\n");
|
|
goto out_err;
|
|
}
|
|
|
|
err = evsel__enable(cycles_evsel);
|
|
if (err) {
|
|
pr_debug("perf_evlist__disable_event failed!\n");
|
|
goto out_err;
|
|
}
|
|
|
|
comm = "Test COMM 4";
|
|
err = prctl(PR_SET_NAME, (unsigned long)comm, 0, 0, 0);
|
|
if (err) {
|
|
pr_debug("PR_SET_NAME failed!\n");
|
|
goto out_err;
|
|
}
|
|
|
|
err = spin_sleep();
|
|
if (err) {
|
|
pr_debug("spin_sleep failed!\n");
|
|
goto out_err;
|
|
}
|
|
|
|
evlist__disable(evlist);
|
|
|
|
switch_tracking.switch_evsel = switch_evsel;
|
|
switch_tracking.cycles_evsel = cycles_evsel;
|
|
|
|
err = process_events(evlist, &switch_tracking);
|
|
|
|
zfree(&switch_tracking.tids);
|
|
|
|
if (err)
|
|
goto out_err;
|
|
|
|
/* Check all 4 comm events were seen i.e. that evsel->tracking works */
|
|
if (!switch_tracking.comm_seen[0] || !switch_tracking.comm_seen[1] ||
|
|
!switch_tracking.comm_seen[2] || !switch_tracking.comm_seen[3]) {
|
|
pr_debug("Missing comm events\n");
|
|
goto out_err;
|
|
}
|
|
|
|
/* Check cycles event got enabled */
|
|
if (!switch_tracking.cycles_before_comm_1) {
|
|
pr_debug("Missing cycles events\n");
|
|
goto out_err;
|
|
}
|
|
|
|
/* Check cycles event got disabled */
|
|
if (switch_tracking.cycles_between_comm_2_and_comm_3) {
|
|
pr_debug("cycles events even though event was disabled\n");
|
|
goto out_err;
|
|
}
|
|
|
|
/* Check cycles event got enabled again */
|
|
if (!switch_tracking.cycles_after_comm_4) {
|
|
pr_debug("Missing cycles events\n");
|
|
goto out_err;
|
|
}
|
|
out:
|
|
if (evlist) {
|
|
evlist__disable(evlist);
|
|
evlist__delete(evlist);
|
|
}
|
|
perf_cpu_map__put(cpus);
|
|
perf_thread_map__put(threads);
|
|
|
|
return err;
|
|
|
|
out_err:
|
|
err = -1;
|
|
goto out;
|
|
}
|
|
|
|
DEFINE_SUITE("Track with sched_switch", switch_tracking);
|