int test__openat_syscall_event_on_all_cpus(int subtest __maybe_unused)
{
int err = -1, fd, cpu;
struct cpu_map *cpus;
struct perf_evsel *evsel;
unsigned int nr_openat_calls = 111, i;
cpu_set_t cpu_set;
struct thread_map *threads = thread_map__new(-1, getpid(), UINT_MAX);
char sbuf[STRERR_BUFSIZE];
char errbuf[BUFSIZ];
if (threads == NULL) {
pr_debug("thread_map__new\n");
return -1;
}
cpus = cpu_map__new(NULL);
if (cpus == NULL) {
pr_debug("cpu_map__new\n");
goto out_thread_map_delete;
}
CPU_ZERO(&cpu_set);
evsel = perf_evsel__newtp("syscalls", "sys_enter_openat");
if (IS_ERR(evsel)) {
tracing_path__strerror_open_tp(errno, errbuf, sizeof(errbuf), "syscalls", "sys_enter_openat");
pr_debug("%s\n", errbuf);
goto out_thread_map_delete;
}
if (perf_evsel__open(evsel, cpus, threads) < 0) {
pr_debug("failed to open counter: %s, "
"tweak /proc/sys/kernel/perf_event_paranoid?\n",
str_error_r(errno, sbuf, sizeof(sbuf)));
goto out_evsel_delete;
}
for (cpu = 0; cpu < cpus->nr; ++cpu) {
unsigned int ncalls = nr_openat_calls + cpu;
/*
* XXX eventually lift this restriction in a way that
* keeps perf building on older glibc installations
* without CPU_ALLOC. 1024 cpus in 2010 still seems
* a reasonable upper limit tho :-)
*/
if (cpus->map[cpu] >= CPU_SETSIZE) {
pr_debug("Ignoring CPU %d\n", cpus->map[cpu]);
continue;
}
CPU_SET(cpus->map[cpu], &cpu_set);
if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0) {
pr_debug("sched_setaffinity() failed on CPU %d: %s ",
cpus->map[cpu],
str_error_r(errno, sbuf, sizeof(sbuf)));
goto out_close_fd;
}
for (i = 0; i < ncalls; ++i) {
fd = openat(0, "/etc/passwd", O_RDONLY);
close(fd);
}
CPU_CLR(cpus->map[cpu], &cpu_set);
}
/*
* Here we need to explicitly preallocate the counts, as if
* we use the auto allocation it will allocate just for 1 cpu,
* as we start by cpu 0.
*/
if (perf_evsel__alloc_counts(evsel, cpus->nr, 1) < 0) {
pr_debug("perf_evsel__alloc_counts(ncpus=%d)\n", cpus->nr);
goto out_close_fd;
}
err = 0;
for (cpu = 0; cpu < cpus->nr; ++cpu) {
unsigned int expected;
if (cpus->map[cpu] >= CPU_SETSIZE)
continue;
if (perf_evsel__read_on_cpu(evsel, cpu, 0) < 0) {
pr_debug("perf_evsel__read_on_cpu\n");
err = -1;
break;
}
expected = nr_openat_calls + cpu;
if (perf_counts(evsel->counts, cpu, 0)->val != expected) {
pr_debug("perf_evsel__read_on_cpu: expected to intercept %d calls on cpu %d, got %" PRIu64 "\n",
expected, cpus->map[cpu], perf_counts(evsel->counts, cpu, 0)->val);
err = -1;
}
}
perf_evsel__free_counts(evsel);
out_close_fd:
perf_evsel__close_fd(evsel, 1, threads->nr);
out_evsel_delete:
perf_evsel__delete(evsel);
out_thread_map_delete:
thread_map__put(threads);
return err;
}
/**
* test__keep_tracking - test using a dummy software event to keep tracking.
*
* This function implements a test that checks that tracking events continue
* when an event is disabled but a dummy software event is not disabled. If the
* test passes %0 is returned, otherwise %-1 is returned.
*/
int test__keep_tracking(void)
{
struct record_opts opts = {
.mmap_pages = UINT_MAX,
.user_freq = UINT_MAX,
.user_interval = ULLONG_MAX,
.freq = 4000,
.target = {
.uses_mmap = true,
},
};
struct thread_map *threads = NULL;
struct cpu_map *cpus = NULL;
struct perf_evlist *evlist = NULL;
struct perf_evsel *evsel = NULL;
int found, err = -1;
const char *comm;
threads = thread_map__new(-1, getpid(), UINT_MAX);
CHECK_NOT_NULL__(threads);
cpus = cpu_map__new(NULL);
CHECK_NOT_NULL__(cpus);
evlist = perf_evlist__new();
CHECK_NOT_NULL__(evlist);
perf_evlist__set_maps(evlist, cpus, threads);
CHECK__(parse_events(evlist, "dummy:u", NULL));
CHECK__(parse_events(evlist, "cycles:u", NULL));
perf_evlist__config(evlist, &opts);
evsel = perf_evlist__first(evlist);
evsel->attr.comm = 1;
evsel->attr.disabled = 1;
evsel->attr.enable_on_exec = 0;
if (perf_evlist__open(evlist) < 0) {
fprintf(stderr, " (not supported)");
err = 0;
goto out_err;
}
CHECK__(perf_evlist__mmap(evlist, UINT_MAX, false));
/*
* First, test that a 'comm' event can be found when the event is
* enabled.
*/
perf_evlist__enable(evlist);
comm = "Test COMM 1";
CHECK__(prctl(PR_SET_NAME, (unsigned long)comm, 0, 0, 0));
perf_evlist__disable(evlist);
found = find_comm(evlist, comm);
if (found != 1) {
pr_debug("First time, failed to find tracking event.\n");
goto out_err;
}
/*
* Secondly, test that a 'comm' event can be found when the event is
* disabled with the dummy event still enabled.
*/
perf_evlist__enable(evlist);
evsel = perf_evlist__last(evlist);
CHECK__(perf_evlist__disable_event(evlist, evsel));
comm = "Test COMM 2";
CHECK__(prctl(PR_SET_NAME, (unsigned long)comm, 0, 0, 0));
perf_evlist__disable(evlist);
found = find_comm(evlist, comm);
if (found != 1) {
pr_debug("Seconf time, failed to find tracking event.\n");
goto out_err;
}
err = 0;
out_err:
if (evlist) {
perf_evlist__disable(evlist);
perf_evlist__delete(evlist);
} else {
cpu_map__put(cpus);
thread_map__put(threads);
}
return err;
}
int test__open_syscall_event(void)
{
int err = -1, fd;
struct thread_map *threads;
struct perf_evsel *evsel;
struct perf_event_attr attr;
unsigned int nr_open_calls = 111, i;
int id = trace_event__id("sys_enter_open");
if (id < 0) {
pr_debug("is debugfs mounted on /sys/kernel/debug?\n");
return -1;
}
threads = thread_map__new(-1, getpid(), UINT_MAX);
if (threads == NULL) {
pr_debug("thread_map__new\n");
return -1;
}
memset(&attr, 0, sizeof(attr));
attr.type = PERF_TYPE_TRACEPOINT;
attr.config = id;
evsel = perf_evsel__new(&attr, 0);
if (evsel == NULL) {
pr_debug("perf_evsel__new\n");
goto out_thread_map_delete;
}
if (perf_evsel__open_per_thread(evsel, threads) < 0) {
pr_debug("failed to open counter: %s, "
"tweak /proc/sys/kernel/perf_event_paranoid?\n",
strerror(errno));
goto out_evsel_delete;
}
for (i = 0; i < nr_open_calls; ++i) {
fd = open("/etc/passwd", O_RDONLY);
close(fd);
}
if (perf_evsel__read_on_cpu(evsel, 0, 0) < 0) {
pr_debug("perf_evsel__read_on_cpu\n");
goto out_close_fd;
}
if (evsel->counts->cpu[0].val != nr_open_calls) {
pr_debug("perf_evsel__read_on_cpu: expected to intercept %d calls, got %" PRIu64 "\n",
nr_open_calls, evsel->counts->cpu[0].val);
goto out_close_fd;
}
err = 0;
out_close_fd:
perf_evsel__close_fd(evsel, 1, threads->nr);
out_evsel_delete:
perf_evsel__delete(evsel);
out_thread_map_delete:
thread_map__delete(threads);
return err;
}
#include <api/fs/tracing_path.h>
#include <linux/err.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <fcntl.h>
#include "thread_map.h"
#include "evsel.h"
#include "debug.h"
#include "tests.h"
int test__openat_syscall_event(struct test *test __maybe_unused, int subtest __maybe_unused)
{
int err = -1, fd;
struct perf_evsel *evsel;
unsigned int nr_openat_calls = 111, i;
struct thread_map *threads = thread_map__new(-1, getpid(), UINT_MAX);
char sbuf[STRERR_BUFSIZE];
char errbuf[BUFSIZ];
if (threads == NULL) {
pr_debug("thread_map__new\n");
return -1;
}
evsel = perf_evsel__newtp("syscalls", "sys_enter_openat");
if (IS_ERR(evsel)) {
tracing_path__strerror_open_tp(errno, errbuf, sizeof(errbuf), "syscalls", "sys_enter_openat");
pr_debug("%s\n", errbuf);
goto out_thread_map_delete;
}
/*
* This test will generate random numbers of calls to some getpid syscalls,
* then establish an mmap for a group of events that are created to monitor
* the syscalls.
*
* It will receive the events, using mmap, use its PERF_SAMPLE_ID generated
* sample.id field to map back to its respective perf_evsel instance.
*
* Then it checks if the number of syscalls reported as perf events by
* the kernel corresponds to the number of syscalls made.
*/
int test__basic_mmap(void)
{
int err = -1;
union perf_event *event;
struct thread_map *threads;
struct cpu_map *cpus;
struct perf_evlist *evlist;
cpu_set_t cpu_set;
const char *syscall_names[] = { "getsid", "getppid", "getpgrp",
"getpgid", };
pid_t (*syscalls[])(void) = { (void *)getsid, getppid, getpgrp,
(void*)getpgid };
#define nsyscalls ARRAY_SIZE(syscall_names)
unsigned int nr_events[nsyscalls],
expected_nr_events[nsyscalls], i, j;
struct perf_evsel *evsels[nsyscalls], *evsel;
threads = thread_map__new(-1, getpid(), UINT_MAX);
if (threads == NULL) {
pr_debug("thread_map__new\n");
return -1;
}
cpus = cpu_map__new(NULL);
if (cpus == NULL) {
pr_debug("cpu_map__new\n");
goto out_free_threads;
}
CPU_ZERO(&cpu_set);
CPU_SET(cpus->map[0], &cpu_set);
sched_setaffinity(0, sizeof(cpu_set), &cpu_set);
if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0) {
pr_debug("sched_setaffinity() failed on CPU %d: %s ",
cpus->map[0], strerror(errno));
goto out_free_cpus;
}
evlist = perf_evlist__new();
if (evlist == NULL) {
pr_debug("perf_evlist__new\n");
goto out_free_cpus;
}
perf_evlist__set_maps(evlist, cpus, threads);
for (i = 0; i < nsyscalls; ++i) {
char name[64];
snprintf(name, sizeof(name), "sys_enter_%s", syscall_names[i]);
evsels[i] = perf_evsel__newtp("syscalls", name);
if (evsels[i] == NULL) {
pr_debug("perf_evsel__new\n");
goto out_delete_evlist;
}
evsels[i]->attr.wakeup_events = 1;
perf_evsel__set_sample_id(evsels[i], false);
perf_evlist__add(evlist, evsels[i]);
if (perf_evsel__open(evsels[i], cpus, threads) < 0) {
pr_debug("failed to open counter: %s, "
"tweak /proc/sys/kernel/perf_event_paranoid?\n",
strerror(errno));
goto out_delete_evlist;
}
nr_events[i] = 0;
expected_nr_events[i] = 1 + rand() % 127;
}
if (perf_evlist__mmap(evlist, 128, true) < 0) {
pr_debug("failed to mmap events: %d (%s)\n", errno,
strerror(errno));
goto out_delete_evlist;
}
for (i = 0; i < nsyscalls; ++i)
for (j = 0; j < expected_nr_events[i]; ++j) {
int foo = syscalls[i]();
++foo;
}
while ((event = perf_evlist__mmap_read(evlist, 0)) != NULL) {
struct perf_sample sample;
if (event->header.type != PERF_RECORD_SAMPLE) {
pr_debug("unexpected %s event\n",
perf_event__name(event->header.type));
goto out_delete_evlist;
}
err = perf_evlist__parse_sample(evlist, event, &sample);
if (err) {
pr_err("Can't parse sample, err = %d\n", err);
goto out_delete_evlist;
}
err = -1;
evsel = perf_evlist__id2evsel(evlist, sample.id);
if (evsel == NULL) {
pr_debug("event with id %" PRIu64
" doesn't map to an evsel\n", sample.id);
goto out_delete_evlist;
}
nr_events[evsel->idx]++;
perf_evlist__mmap_consume(evlist, 0);
}
err = 0;
evlist__for_each(evlist, evsel) {
if (nr_events[evsel->idx] != expected_nr_events[evsel->idx]) {
pr_debug("expected %d %s events, got %d\n",
expected_nr_events[evsel->idx],
perf_evsel__name(evsel), nr_events[evsel->idx]);
err = -1;
goto out_delete_evlist;
}
}
out_delete_evlist:
perf_evlist__delete(evlist);
cpus = NULL;
threads = NULL;
out_free_cpus:
cpu_map__delete(cpus);
out_free_threads:
thread_map__delete(threads);
return err;
}
/**
* test__perf_time_to_tsc - test converting perf time to TSC.
*
* This function implements a test that checks that the conversion of perf time
* to and from TSC is consistent with the order of events. If the test passes
* %0 is returned, otherwise %-1 is returned. If TSC conversion is not
* supported then then the test passes but " (not supported)" is printed.
*/
int test__perf_time_to_tsc(void)
{
struct record_opts opts = {
.mmap_pages = UINT_MAX,
.user_freq = UINT_MAX,
.user_interval = ULLONG_MAX,
.freq = 4000,
.target = {
.uses_mmap = true,
},
.sample_time = true,
};
struct thread_map *threads = NULL;
struct cpu_map *cpus = NULL;
struct perf_evlist *evlist = NULL;
struct perf_evsel *evsel = NULL;
int err = -1, ret, i;
const char *comm1, *comm2;
struct perf_tsc_conversion tc;
struct perf_event_mmap_page *pc;
union perf_event *event;
u64 test_tsc, comm1_tsc, comm2_tsc;
u64 test_time, comm1_time = 0, comm2_time = 0;
threads = thread_map__new(-1, getpid(), UINT_MAX);
CHECK_NOT_NULL__(threads);
cpus = cpu_map__new(NULL);
CHECK_NOT_NULL__(cpus);
evlist = perf_evlist__new();
CHECK_NOT_NULL__(evlist);
perf_evlist__set_maps(evlist, cpus, threads);
CHECK__(parse_events(evlist, "cycles:u", NULL));
perf_evlist__config(evlist, &opts);
evsel = perf_evlist__first(evlist);
evsel->attr.comm = 1;
evsel->attr.disabled = 1;
evsel->attr.enable_on_exec = 0;
CHECK__(perf_evlist__open(evlist));
CHECK__(perf_evlist__mmap(evlist, UINT_MAX, false));
pc = evlist->mmap[0].base;
ret = perf_read_tsc_conversion(pc, &tc);
if (ret) {
if (ret == -EOPNOTSUPP) {
fprintf(stderr, " (not supported)");
return 0;
}
goto out_err;
}
perf_evlist__enable(evlist);
comm1 = "Test COMM 1";
CHECK__(prctl(PR_SET_NAME, (unsigned long)comm1, 0, 0, 0));
test_tsc = rdtsc();
comm2 = "Test COMM 2";
CHECK__(prctl(PR_SET_NAME, (unsigned long)comm2, 0, 0, 0));
perf_evlist__disable(evlist);
for (i = 0; i < evlist->nr_mmaps; i++) {
while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
struct perf_sample sample;
if (event->header.type != PERF_RECORD_COMM ||
(pid_t)event->comm.pid != getpid() ||
(pid_t)event->comm.tid != getpid())
goto next_event;
if (strcmp(event->comm.comm, comm1) == 0) {
CHECK__(perf_evsel__parse_sample(evsel, event,
&sample));
comm1_time = sample.time;
}
if (strcmp(event->comm.comm, comm2) == 0) {
CHECK__(perf_evsel__parse_sample(evsel, event,
&sample));
comm2_time = sample.time;
}
next_event:
perf_evlist__mmap_consume(evlist, i);
}
}
if (!comm1_time || !comm2_time)
goto out_err;
test_time = tsc_to_perf_time(test_tsc, &tc);
comm1_tsc = perf_time_to_tsc(comm1_time, &tc);
comm2_tsc = perf_time_to_tsc(comm2_time, &tc);
pr_debug("1st event perf time %"PRIu64" tsc %"PRIu64"\n",
comm1_time, comm1_tsc);
pr_debug("rdtsc time %"PRIu64" tsc %"PRIu64"\n",
test_time, test_tsc);
pr_debug("2nd event perf time %"PRIu64" tsc %"PRIu64"\n",
comm2_time, comm2_tsc);
if (test_time <= comm1_time ||
test_time >= comm2_time)
goto out_err;
if (test_tsc <= comm1_tsc ||
test_tsc >= comm2_tsc)
goto out_err;
err = 0;
out_err:
if (evlist) {
perf_evlist__disable(evlist);
perf_evlist__delete(evlist);
}
return err;
}