Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Message-ID: <20230606142031.071059989@linutronix.de>
From:   Thomas Gleixner <tglx@linutronix.de>
To:     LKML <linux-kernel@vger.kernel.org>
Cc:     Frederic Weisbecker <frederic@kernel.org>,
        Anna-Maria Behnsen <anna-maria@linutronix.de>,
        John Stultz <jstultz@google.com>,
        Peter Zijlstra <peterz@infradead.org>,
        Ingo Molnar <mingo@kernel.org>,
        Stephen Boyd <sboyd@kernel.org>,
        Eric Biederman <ebiederm@xmission.com>,
        Oleg Nesterov <oleg@redhat.com>
Subject: [patch 01/45] selftests/timers/posix_timers: Make signal distribution
 test less fragile
References: <20230606132949.068951363@linutronix.de>
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Date:   Tue,  6 Jun 2023 16:37:19 +0200 (CEST)
Precedence: bulk

The signal distribution test has a tendency to hang for a long time as the
signal delivery is not really evenly distributed.

Increasing the timer interval to 10ms makes this less likely. Add a timeout
to catch the case where it hangs and terminate the test gracefully.

While at it get rid of the pointless atomic operation on a the thread local
variable in the signal handler.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 tools/testing/selftests/timers/posix_timers.c |   42 ++++++++++++++++----------
 1 file changed, 27 insertions(+), 15 deletions(-)

--- a/tools/testing/selftests/timers/posix_timers.c
+++ b/tools/testing/selftests/timers/posix_timers.c
@@ -188,18 +188,19 @@ static int check_timer_create(int which)
 	return 0;
 }
 
-int remain;
-__thread int got_signal;
+static int remain;
+static __thread int got_signal;
 
 static void *distribution_thread(void *arg)
 {
-	while (__atomic_load_n(&remain, __ATOMIC_RELAXED));
+	while (__atomic_load_n(&remain, __ATOMIC_RELAXED) && !done);
+
 	return NULL;
 }
 
 static void distribution_handler(int nr)
 {
-	if (!__atomic_exchange_n(&got_signal, 1, __ATOMIC_RELAXED))
+	if (++got_signal == 1)
 		__atomic_fetch_sub(&remain, 1, __ATOMIC_RELAXED);
 }
 
@@ -209,20 +210,22 @@ static void distribution_handler(int nr)
  */
 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_value.tv_nsec = 20 * 1000 * 1000,
 		.it_interval.tv_sec = 0,
-		.it_interval.tv_nsec = 1000 * 1000,
+		.it_interval.tv_nsec = 20 * 1000 * 1000,
 	};
+	time_t start, now;
+	int err, i;
+	timer_t id;
 
 	printf("Check timer_create() per process signal distribution... ");
 	fflush(stdout);
 
+	done = 0;
 	remain = nthreads + 1;  /* worker threads + this thread */
 	signal(SIGALRM, distribution_handler);
 	err = timer_create(CLOCK_PROCESS_CPUTIME_ID, NULL, &id);
@@ -244,7 +247,18 @@ static int check_timer_distribution(void
 	}
 
 	/* Wait for all threads to receive the signal. */
-	while (__atomic_load_n(&remain, __ATOMIC_RELAXED));
+	now = start = time(NULL);
+	while (__atomic_load_n(&remain, __ATOMIC_RELAXED)) {
+		now = time(NULL);
+		if (now - start > 5)
+			break;
+	}
+	done = 1;
+
+	if (timer_delete(id)) {
+		perror("Can't delete timer\n");
+		return -1;
+	}
 
 	for (i = 0; i < nthreads; i++) {
 		if (pthread_join(threads[i], NULL)) {
@@ -253,12 +267,10 @@ static int check_timer_distribution(void
 		}
 	}
 
-	if (timer_delete(id)) {
-		perror("Can't delete timer\n");
-		return -1;
-	}
-
-	printf("[OK]\n");
+	if (now - start <= 5)
+		printf("[OK]\n");
+	else
+		printf("%d [FAIL]\n", got_signal);
 	return 0;
 }