[PATCH] selftests/timers/posix_timers: reimplement check_timer_distribution()

[Oleg Nesterov <oleg@xxxxxxxxxx>]

Thomas says:

	The signal distribution test has a tendency to hang for a long
	time as the signal delivery is not really evenly distributed. In
	fact it might never be distributed across all threads ever in
	the way it is written.

To me even the

	This primarily tests that the kernel does not favour any one.

comment doesn't look right. The kernel does favour a thread which hits
the timer interrupt when CLOCK_PROCESS_CPUTIME_ID expires.

The new version simply checks that the group leader sleeping in join()
never receives SIGALRM, cpu_timer_fire() should always send the signal
to the thread which burns cpu.

Without the commit bcb7ee79029d ("posix-timers: Prefer delivery of signals
to the current thread") the test-case fails immediately, the very 1st tick
wakes the leader up. Otherwise it quickly succeeds after 100 ticks.

Signed-off-by: Oleg Nesterov <oleg@xxxxxxxxxx>
---
 tools/testing/selftests/timers/posix_timers.c | 102 ++++++++----------
 1 file changed, 46 insertions(+), 56 deletions(-)

diff --git a/tools/testing/selftests/timers/posix_timers.c b/tools/testing/selftests/timers/posix_timers.c
index d49dd3ffd0d9..2586a6552737 100644
--- a/tools/testing/selftests/timers/posix_timers.c
+++ b/tools/testing/selftests/timers/posix_timers.c
@@ -184,80 +184,70 @@ static int check_timer_create(int which)
 	return 0;
 }
 
-int remain;
-__thread int got_signal;
+static pthread_t ctd_thread;
+static volatile int ctd_count, ctd_failed;
 
-static void *distribution_thread(void *arg)
+static void ctd_sighandler(int sig)
 {
-	while (__atomic_load_n(&remain, __ATOMIC_RELAXED));
-	return NULL;
+	if (pthread_self() != ctd_thread)
+		ctd_failed = 1;
+	ctd_count--;
 }
 
-static void distribution_handler(int nr)
+static void *ctd_thread_func(void *arg)
 {
-	if (!__atomic_exchange_n(&got_signal, 1, __ATOMIC_RELAXED))
-		__atomic_fetch_sub(&remain, 1, __ATOMIC_RELAXED);
-}
-
-/*
- * Test that all running threads _eventually_ receive CLOCK_PROCESS_CPUTIME_ID
- * timer signals. This primarily tests that the kernel does not favour any one.
- */
-static int check_timer_distribution(void)
-{
-	int err, i;
-	timer_t id;
-	const int nthreads = 10;
-	pthread_t threads[nthreads];
 	struct itimerspec val = {
 		.it_value.tv_sec = 0,
 		.it_value.tv_nsec = 1000 * 1000,
 		.it_interval.tv_sec = 0,
 		.it_interval.tv_nsec = 1000 * 1000,
 	};
+	timer_t id;
 
-	remain = nthreads + 1;  /* worker threads + this thread */
-	signal(SIGALRM, distribution_handler);
-	err = timer_create(CLOCK_PROCESS_CPUTIME_ID, NULL, &id);
-	if (err < 0) {
-		ksft_perror("Can't create timer");
-		return -1;
-	}
-	err = timer_settime(id, 0, &val, NULL);
-	if (err < 0) {
-		ksft_perror("Can't set timer");
-		return -1;
-	}
+	/* 1/10 seconds to ensure the leader sleeps */
+	usleep(10000);
 
-	for (i = 0; i < nthreads; i++) {
-		err = pthread_create(&threads[i], NULL, distribution_thread,
-				     NULL);
-		if (err) {
-			ksft_print_msg("Can't create thread: %s (%d)\n",
-				       strerror(errno), errno);
-			return -1;
-		}
-	}
+	ctd_count = 100;
+	if (timer_create(CLOCK_PROCESS_CPUTIME_ID, NULL, &id))
+		return "Can't create timer";
+	if (timer_settime(id, 0, &val, NULL))
+		return "Can't set timer";
 
-	/* Wait for all threads to receive the signal. */
-	while (__atomic_load_n(&remain, __ATOMIC_RELAXED));
+	while (ctd_count > 0 && !ctd_failed)
+		;
 
-	for (i = 0; i < nthreads; i++) {
-		err = pthread_join(threads[i], NULL);
-		if (err) {
-			ksft_print_msg("Can't join thread: %s (%d)\n",
-				       strerror(errno), errno);
-			return -1;
-		}
-	}
+	if (timer_delete(id))
+		return "Can't delete timer";
 
-	if (timer_delete(id)) {
-		ksft_perror("Can't delete timer");
-		return -1;
-	}
+	return NULL;
+}
+
+/*
+ * Test that only the running thread receives the timer signal.
+ */
+static int check_timer_distribution(void)
+{
+	const char *errmsg;
+
+	signal(SIGALRM, ctd_sighandler);
+
+	errmsg = "Can't create thread";
+	if (pthread_create(&ctd_thread, NULL, ctd_thread_func, NULL))
+		goto err;
+
+	errmsg = "Can't join thread";
+	if (pthread_join(ctd_thread, (void **)&errmsg) || errmsg)
+		goto err;
+
+	if (ctd_failed)
+		ksft_test_result_skip("No signal distribution. Assuming old kernel\n");
+	else
+		ksft_test_result_pass("check signal distribution\n");
 
-	ksft_test_result_pass("check_timer_distribution\n");
 	return 0;
+err:
+	ksft_print_msg(errmsg);
+	return -1;
 }
 
 int main(int argc, char **argv)
-- 
2.25.1.362.g51ebf55