static int do_test(struct bpf_object *obj, int (*func)(void),
int expect)
{
struct record_opts opts = {
.target = {
.uid = UINT_MAX,
.uses_mmap = true,
},
.freq = 0,
.mmap_pages = 256,
.default_interval = 1,
};
char pid[16];
char sbuf[STRERR_BUFSIZE];
struct perf_evlist *evlist;
int i, ret = TEST_FAIL, err = 0, count = 0;
struct parse_events_evlist parse_evlist;
struct parse_events_error parse_error;
bzero(&parse_error, sizeof(parse_error));
bzero(&parse_evlist, sizeof(parse_evlist));
parse_evlist.error = &parse_error;
INIT_LIST_HEAD(&parse_evlist.list);
err = parse_events_load_bpf_obj(&parse_evlist, &parse_evlist.list, obj, NULL);
if (err || list_empty(&parse_evlist.list)) {
pr_debug("Failed to add events selected by BPF\n");
return TEST_FAIL;
}
snprintf(pid, sizeof(pid), "%d", getpid());
pid[sizeof(pid) - 1] = '\0';
opts.target.tid = opts.target.pid = pid;
/* Instead of perf_evlist__new_default, don't add default events */
evlist = perf_evlist__new();
if (!evlist) {
pr_debug("Not enough memory to create evlist\n");
return TEST_FAIL;
}
err = perf_evlist__create_maps(evlist, &opts.target);
if (err < 0) {
pr_debug("Not enough memory to create thread/cpu maps\n");
goto out_delete_evlist;
}
perf_evlist__splice_list_tail(evlist, &parse_evlist.list);
evlist->nr_groups = parse_evlist.nr_groups;
perf_evlist__config(evlist, &opts, NULL);
err = perf_evlist__open(evlist);
if (err < 0) {
pr_debug("perf_evlist__open: %s\n",
str_error_r(errno, sbuf, sizeof(sbuf)));
goto out_delete_evlist;
}
err = perf_evlist__mmap(evlist, opts.mmap_pages, false);
if (err < 0) {
pr_debug("perf_evlist__mmap: %s\n",
str_error_r(errno, sbuf, sizeof(sbuf)));
goto out_delete_evlist;
}
perf_evlist__enable(evlist);
(*func)();
perf_evlist__disable(evlist);
for (i = 0; i < evlist->nr_mmaps; i++) {
union perf_event *event;
while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
const u32 type = event->header.type;
if (type == PERF_RECORD_SAMPLE)
count ++;
}
}
if (count != expect) {
pr_debug("BPF filter result incorrect\n");
goto out_delete_evlist;
}
ret = TEST_OK;
out_delete_evlist:
perf_evlist__delete(evlist);
return ret;
}
int test__syscall_open_tp_fields(void)
{
struct perf_record_opts opts = {
.target = {
.uid = UINT_MAX,
.uses_mmap = true,
},
.no_delay = true,
.freq = 1,
.mmap_pages = 256,
.raw_samples = true,
};
const char *filename = "/etc/passwd";
int flags = O_RDONLY | O_DIRECTORY;
struct perf_evlist *evlist = perf_evlist__new();
struct perf_evsel *evsel;
int err = -1, i, nr_events = 0, nr_polls = 0;
if (evlist == NULL) {
pr_debug("%s: perf_evlist__new\n", __func__);
goto out;
}
evsel = perf_evsel__newtp("syscalls", "sys_enter_open");
if (evsel == NULL) {
pr_debug("%s: perf_evsel__newtp\n", __func__);
goto out_delete_evlist;
}
perf_evlist__add(evlist, evsel);
err = perf_evlist__create_maps(evlist, &opts.target);
if (err < 0) {
pr_debug("%s: perf_evlist__create_maps\n", __func__);
goto out_delete_evlist;
}
perf_evsel__config(evsel, &opts);
evlist->threads->map[0] = getpid();
err = perf_evlist__open(evlist);
if (err < 0) {
pr_debug("perf_evlist__open: %s\n", strerror(errno));
goto out_delete_maps;
}
err = perf_evlist__mmap(evlist, UINT_MAX, false);
if (err < 0) {
pr_debug("perf_evlist__mmap: %s\n", strerror(errno));
goto out_close_evlist;
}
perf_evlist__enable(evlist);
/*
* Generate the event:
*/
open(filename, flags);
while (1) {
int before = nr_events;
for (i = 0; i < evlist->nr_mmaps; i++) {
union perf_event *event;
while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
const u32 type = event->header.type;
int tp_flags;
struct perf_sample sample;
++nr_events;
if (type != PERF_RECORD_SAMPLE) {
perf_evlist__mmap_consume(evlist, i);
continue;
}
err = perf_evsel__parse_sample(evsel, event, &sample);
if (err) {
pr_err("Can't parse sample, err = %d\n", err);
goto out_munmap;
}
tp_flags = perf_evsel__intval(evsel, &sample, "flags");
if (flags != tp_flags) {
pr_debug("%s: Expected flags=%#x, got %#x\n",
__func__, flags, tp_flags);
goto out_munmap;
}
goto out_ok;
}
}
if (nr_events == before)
poll(evlist->pollfd, evlist->nr_fds, 10);
if (++nr_polls > 5) {
pr_debug("%s: no events!\n", __func__);
goto out_munmap;
}
}
out_ok:
err = 0;
out_munmap:
perf_evlist__munmap(evlist);
out_close_evlist:
perf_evlist__close(evlist);
out_delete_maps:
perf_evlist__delete_maps(evlist);
out_delete_evlist:
perf_evlist__delete(evlist);
out:
return err;
}
int test__PERF_RECORD(int subtest __maybe_unused)
{
struct record_opts opts = {
.target = {
.uid = UINT_MAX,
.uses_mmap = true,
},
.no_buffering = true,
.mmap_pages = 256,
};
cpu_set_t cpu_mask;
size_t cpu_mask_size = sizeof(cpu_mask);
struct perf_evlist *evlist = perf_evlist__new_dummy();
struct perf_evsel *evsel;
struct perf_sample sample;
const char *cmd = "sleep";
const char *argv[] = { cmd, "1", NULL, };
char *bname, *mmap_filename;
u64 prev_time = 0;
bool found_cmd_mmap = false,
found_libc_mmap = false,
found_vdso_mmap = false,
found_ld_mmap = false;
int err = -1, errs = 0, i, wakeups = 0;
u32 cpu;
int total_events = 0, nr_events[PERF_RECORD_MAX] = { 0, };
char sbuf[STRERR_BUFSIZE];
if (evlist == NULL) /* Fallback for kernels lacking PERF_COUNT_SW_DUMMY */
evlist = perf_evlist__new_default();
if (evlist == NULL || argv == NULL) {
pr_debug("Not enough memory to create evlist\n");
goto out;
}
/*
* 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.
*/
err = perf_evlist__create_maps(evlist, &opts.target);
if (err < 0) {
pr_debug("Not enough memory to create thread/cpu maps\n");
goto out_delete_evlist;
}
/*
* Prepare the workload in argv[] to run, it'll fork it, and then wait
* for perf_evlist__start_workload() to exec it. This is done this way
* so that we have time to open the evlist (calling sys_perf_event_open
* on all the fds) and then mmap them.
*/
err = perf_evlist__prepare_workload(evlist, &opts.target, argv, false, NULL);
if (err < 0) {
pr_debug("Couldn't run the workload!\n");
goto out_delete_evlist;
}
/*
* Config the evsels, setting attr->comm on the first one, etc.
*/
evsel = perf_evlist__first(evlist);
perf_evsel__set_sample_bit(evsel, CPU);
perf_evsel__set_sample_bit(evsel, TID);
perf_evsel__set_sample_bit(evsel, TIME);
perf_evlist__config(evlist, &opts);
err = sched__get_first_possible_cpu(evlist->workload.pid, &cpu_mask);
if (err < 0) {
pr_debug("sched__get_first_possible_cpu: %s\n",
strerror_r(errno, sbuf, sizeof(sbuf)));
goto out_delete_evlist;
}
cpu = err;
/*
* So that we can check perf_sample.cpu on all the samples.
*/
if (sched_setaffinity(evlist->workload.pid, cpu_mask_size, &cpu_mask) < 0) {
pr_debug("sched_setaffinity: %s\n",
strerror_r(errno, sbuf, sizeof(sbuf)));
goto out_delete_evlist;
}
/*
* Call sys_perf_event_open on all the fds on all the evsels,
* grouping them if asked to.
*/
err = perf_evlist__open(evlist);
if (err < 0) {
pr_debug("perf_evlist__open: %s\n",
strerror_r(errno, sbuf, sizeof(sbuf)));
goto out_delete_evlist;
}
/*
* mmap the first fd on a given CPU and ask for events for the other
* fds in the same CPU to be injected in the same mmap ring buffer
* (using ioctl(PERF_EVENT_IOC_SET_OUTPUT)).
*/
err = perf_evlist__mmap(evlist, opts.mmap_pages, false);
if (err < 0) {
pr_debug("perf_evlist__mmap: %s\n",
strerror_r(errno, sbuf, sizeof(sbuf)));
goto out_delete_evlist;
}
/*
* Now that all is properly set up, enable the events, they will
* count just on workload.pid, which will start...
*/
perf_evlist__enable(evlist);
/*
* Now!
*/
perf_evlist__start_workload(evlist);
while (1) {
int before = total_events;
for (i = 0; i < evlist->nr_mmaps; i++) {
union perf_event *event;
while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
const u32 type = event->header.type;
const char *name = perf_event__name(type);
++total_events;
if (type < PERF_RECORD_MAX)
nr_events[type]++;
err = perf_evlist__parse_sample(evlist, event, &sample);
if (err < 0) {
if (verbose)
perf_event__fprintf(event, stderr);
pr_debug("Couldn't parse sample\n");
goto out_delete_evlist;
}
if (verbose) {
pr_info("%" PRIu64" %d ", sample.time, sample.cpu);
perf_event__fprintf(event, stderr);
}
if (prev_time > sample.time) {
pr_debug("%s going backwards in time, prev=%" PRIu64 ", curr=%" PRIu64 "\n",
name, prev_time, sample.time);
++errs;
}
prev_time = sample.time;
if (sample.cpu != cpu) {
pr_debug("%s with unexpected cpu, expected %d, got %d\n",
name, cpu, sample.cpu);
++errs;
}
if ((pid_t)sample.pid != evlist->workload.pid) {
pr_debug("%s with unexpected pid, expected %d, got %d\n",
name, evlist->workload.pid, sample.pid);
++errs;
}
if ((pid_t)sample.tid != evlist->workload.pid) {
pr_debug("%s with unexpected tid, expected %d, got %d\n",
name, evlist->workload.pid, sample.tid);
++errs;
}
if ((type == PERF_RECORD_COMM ||
type == PERF_RECORD_MMAP ||
type == PERF_RECORD_MMAP2 ||
type == PERF_RECORD_FORK ||
type == PERF_RECORD_EXIT) &&
(pid_t)event->comm.pid != evlist->workload.pid) {
pr_debug("%s with unexpected pid/tid\n", name);
++errs;
}
if ((type == PERF_RECORD_COMM ||
type == PERF_RECORD_MMAP ||
type == PERF_RECORD_MMAP2) &&
event->comm.pid != event->comm.tid) {
pr_debug("%s with different pid/tid!\n", name);
++errs;
}
switch (type) {
case PERF_RECORD_COMM:
if (strcmp(event->comm.comm, cmd)) {
pr_debug("%s with unexpected comm!\n", name);
++errs;
}
break;
case PERF_RECORD_EXIT:
goto found_exit;
case PERF_RECORD_MMAP:
mmap_filename = event->mmap.filename;
goto check_bname;
case PERF_RECORD_MMAP2:
mmap_filename = event->mmap2.filename;
check_bname:
bname = strrchr(mmap_filename, '/');
if (bname != NULL) {
if (!found_cmd_mmap)
found_cmd_mmap = !strcmp(bname + 1, cmd);
if (!found_libc_mmap)
found_libc_mmap = !strncmp(bname + 1, "libc", 4);
if (!found_ld_mmap)
found_ld_mmap = !strncmp(bname + 1, "ld", 2);
} else if (!found_vdso_mmap)
found_vdso_mmap = !strcmp(mmap_filename, "[vdso]");
break;
case PERF_RECORD_SAMPLE:
/* Just ignore samples for now */
break;
default:
pr_debug("Unexpected perf_event->header.type %d!\n",
type);
++errs;
}
perf_evlist__mmap_consume(evlist, i);
}
}
/*
* We don't use poll here because at least at 3.1 times the
* PERF_RECORD_{!SAMPLE} events don't honour
* perf_event_attr.wakeup_events, just PERF_EVENT_SAMPLE does.
*/
if (total_events == before && false)
perf_evlist__poll(evlist, -1);
sleep(1);
if (++wakeups > 5) {
pr_debug("No PERF_RECORD_EXIT event!\n");
break;
}
}
found_exit:
if (nr_events[PERF_RECORD_COMM] > 1) {
pr_debug("Excessive number of PERF_RECORD_COMM events!\n");
++errs;
}
if (nr_events[PERF_RECORD_COMM] == 0) {
pr_debug("Missing PERF_RECORD_COMM for %s!\n", cmd);
++errs;
}
if (!found_cmd_mmap) {
pr_debug("PERF_RECORD_MMAP for %s missing!\n", cmd);
++errs;
}
if (!found_libc_mmap) {
pr_debug("PERF_RECORD_MMAP for %s missing!\n", "libc");
++errs;
}
if (!found_ld_mmap) {
pr_debug("PERF_RECORD_MMAP for %s missing!\n", "ld");
++errs;
}
if (!found_vdso_mmap) {
pr_debug("PERF_RECORD_MMAP for %s missing!\n", "[vdso]");
++errs;
}
out_delete_evlist:
perf_evlist__delete(evlist);
out:
return (err < 0 || errs > 0) ? -1 : 0;
}
int test__backward_ring_buffer(int subtest __maybe_unused)
{
int ret = TEST_SKIP, err, sample_count = 0, comm_count = 0;
char pid[16], sbuf[STRERR_BUFSIZE];
struct perf_evlist *evlist;
struct perf_evsel *evsel __maybe_unused;
struct parse_events_error parse_error;
struct record_opts opts = {
.target = {
.uid = UINT_MAX,
.uses_mmap = true,
},
.freq = 0,
.mmap_pages = 256,
.default_interval = 1,
};
snprintf(pid, sizeof(pid), "%d", getpid());
pid[sizeof(pid) - 1] = '\0';
opts.target.tid = opts.target.pid = pid;
evlist = perf_evlist__new();
if (!evlist) {
pr_debug("No ehough memory to create evlist\n");
return TEST_FAIL;
}
err = perf_evlist__create_maps(evlist, &opts.target);
if (err < 0) {
pr_debug("Not enough memory to create thread/cpu maps\n");
goto out_delete_evlist;
}
bzero(&parse_error, sizeof(parse_error));
err = parse_events(evlist, "syscalls:sys_enter_prctl", &parse_error);
if (err) {
pr_debug("Failed to parse tracepoint event, try use root\n");
ret = TEST_SKIP;
goto out_delete_evlist;
}
perf_evlist__config(evlist, &opts, NULL);
/* Set backward bit, ring buffer should be writing from end */
evlist__for_each(evlist, evsel)
evsel->attr.write_backward = 1;
err = perf_evlist__open(evlist);
if (err < 0) {
pr_debug("perf_evlist__open: %s\n",
strerror_r(errno, sbuf, sizeof(sbuf)));
goto out_delete_evlist;
}
ret = TEST_FAIL;
err = do_test(evlist, opts.mmap_pages, &sample_count,
&comm_count);
if (err != TEST_OK)
goto out_delete_evlist;
if ((sample_count != NR_ITERS) || (comm_count != NR_ITERS)) {
pr_err("Unexpected counter: sample_count=%d, comm_count=%d\n",
sample_count, comm_count);
goto out_delete_evlist;
}
err = do_test(evlist, 1, &sample_count, &comm_count);
if (err != TEST_OK)
goto out_delete_evlist;
ret = TEST_OK;
out_delete_evlist:
perf_evlist__delete(evlist);
return ret;
}
