4 files changed, 116 insertions, 6 deletions

diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
index b8e1224cfd19..6f1bfacd7375 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
@@ -265,10 +265,10 @@ static void *run_test_task_tid(void *arg)
 
 	linfo.task.tid = 0;
 	linfo.task.pid = getpid();
-	/* This includes the parent thread, this thread,
+	/* This includes the parent thread, this thread, watchdog timer thread
 	 * and the do_nothing_wait thread
 	 */
-	test_task_common(&opts, 2, 1);
+	test_task_common(&opts, 3, 1);
 
 	test_task_common_nocheck(NULL, &num_unknown_tid, &num_known_tid);
 	ASSERT_GT(num_unknown_tid, 2, "check_num_unknown_tid");
@@ -297,7 +297,7 @@ static void test_task_pid(void)
 	opts.link_info = &linfo;
 	opts.link_info_len = sizeof(linfo);
 
-	test_task_common(&opts, 1, 1);
+	test_task_common(&opts, 2, 1);
 }
 
 static void test_task_pidfd(void)
@@ -315,7 +315,7 @@ static void test_task_pidfd(void)
 	opts.link_info = &linfo;
 	opts.link_info_len = sizeof(linfo);
 
-	test_task_common(&opts, 1, 1);
+	test_task_common(&opts, 2, 1);
 
 	close(pidfd);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/iters.c b/tools/testing/selftests/bpf/prog_tests/iters.c
index 89ff23c4a8bc..3cea71f9c500 100644
--- a/tools/testing/selftests/bpf/prog_tests/iters.c
+++ b/tools/testing/selftests/bpf/prog_tests/iters.c
@@ -192,8 +192,8 @@ static void subtest_task_iters(void)
 	syscall(SYS_getpgid);
 	iters_task__detach(skel);
 	ASSERT_EQ(skel->bss->procs_cnt, 1, "procs_cnt");
-	ASSERT_EQ(skel->bss->threads_cnt, thread_num + 1, "threads_cnt");
-	ASSERT_EQ(skel->bss->proc_threads_cnt, thread_num + 1, "proc_threads_cnt");
+	ASSERT_EQ(skel->bss->threads_cnt, thread_num + 2, "threads_cnt");
+	ASSERT_EQ(skel->bss->proc_threads_cnt, thread_num + 2, "proc_threads_cnt");
 	ASSERT_EQ(skel->bss->invalid_cnt, 0, "invalid_cnt");
 	pthread_mutex_unlock(&do_nothing_mutex);
 	for (int i = 0; i < thread_num; i++)
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index 7421874380c2..6088d8222d59 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -16,6 +16,7 @@
 #include <sys/socket.h>
 #include <sys/un.h>
 #include <bpf/btf.h>
+#include <time.h>
 #include "json_writer.h"
 
 #include "network_helpers.h"
@@ -179,6 +180,88 @@ int usleep(useconds_t usec)
 	return syscall(__NR_nanosleep, &ts, NULL);
 }
 
+/* Watchdog timer is started by watchdog_start() and stopped by watchdog_stop().
+ * If timer is active for longer than env.secs_till_notify,
+ * it prints the name of the current test to the stderr.
+ * If timer is active for longer than env.secs_till_kill,
+ * it kills the thread executing the test by sending a SIGSEGV signal to it.
+ */
+static void watchdog_timer_func(union sigval sigval)
+{
+	struct itimerspec timeout = {};
+	char test_name[256];
+	int err;
+
+	if (env.subtest_state)
+		snprintf(test_name, sizeof(test_name), "%s/%s",
+			 env.test->test_name, env.subtest_state->name);
+	else
+		snprintf(test_name, sizeof(test_name), "%s",
+			 env.test->test_name);
+
+	switch (env.watchdog_state) {
+	case WD_NOTIFY:
+		fprintf(env.stderr_saved, "WATCHDOG: test case %s executes for %d seconds...\n",
+			test_name, env.secs_till_notify);
+		timeout.it_value.tv_sec = env.secs_till_kill - env.secs_till_notify;
+		env.watchdog_state = WD_KILL;
+		err = timer_settime(env.watchdog, 0, &timeout, NULL);
+		if (err)
+			fprintf(env.stderr_saved, "Failed to arm watchdog timer\n");
+		break;
+	case WD_KILL:
+		fprintf(env.stderr_saved,
+			"WATCHDOG: test case %s executes for %d seconds, terminating with SIGSEGV\n",
+			test_name, env.secs_till_kill);
+		pthread_kill(env.main_thread, SIGSEGV);
+		break;
+	}
+}
+
+static void watchdog_start(void)
+{
+	struct itimerspec timeout = {};
+	int err;
+
+	if (env.secs_till_kill == 0)
+		return;
+	if (env.secs_till_notify > 0) {
+		env.watchdog_state = WD_NOTIFY;
+		timeout.it_value.tv_sec = env.secs_till_notify;
+	} else {
+		env.watchdog_state = WD_KILL;
+		timeout.it_value.tv_sec = env.secs_till_kill;
+	}
+	err = timer_settime(env.watchdog, 0, &timeout, NULL);
+	if (err)
+		fprintf(env.stderr_saved, "Failed to start watchdog timer\n");
+}
+
+static void watchdog_stop(void)
+{
+	struct itimerspec timeout = {};
+	int err;
+
+	env.watchdog_state = WD_NOTIFY;
+	err = timer_settime(env.watchdog, 0, &timeout, NULL);
+	if (err)
+		fprintf(env.stderr_saved, "Failed to stop watchdog timer\n");
+}
+
+static void watchdog_init(void)
+{
+	struct sigevent watchdog_sev = {
+		.sigev_notify = SIGEV_THREAD,
+		.sigev_notify_function = watchdog_timer_func,
+	};
+	int err;
+
+	env.main_thread = pthread_self();
+	err = timer_create(CLOCK_MONOTONIC, &watchdog_sev, &env.watchdog);
+	if (err)
+		fprintf(stderr, "Failed to initialize watchdog timer\n");
+}
+
 static bool should_run(struct test_selector *sel, int num, const char *name)
 {
 	int i;
@@ -515,6 +598,7 @@ bool test__start_subtest(const char *subtest_name)
 
 	env.subtest_state = subtest_state;
 	stdio_hijack_init(&subtest_state->log_buf, &subtest_state->log_cnt);
+	watchdog_start();
 
 	return true;
 }
@@ -780,6 +864,7 @@ enum ARG_KEYS {
 	ARG_DEBUG = -1,
 	ARG_JSON_SUMMARY = 'J',
 	ARG_TRAFFIC_MONITOR = 'm',
+	ARG_WATCHDOG_TIMEOUT = 'w',
 };
 
 static const struct argp_option opts[] = {
@@ -810,6 +895,8 @@ static const struct argp_option opts[] = {
 	{ "traffic-monitor", ARG_TRAFFIC_MONITOR, "NAMES", 0,
 	  "Monitor network traffic of tests with name matching the pattern (supports '*' wildcard)." },
 #endif
+	{ "watchdog-timeout", ARG_WATCHDOG_TIMEOUT, "SECONDS", 0,
+	  "Kill the process if tests are not making progress for specified number of seconds." },
 	{},
 };
 
@@ -1035,6 +1122,16 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state)
 					      true);
 		break;
 #endif
+	case ARG_WATCHDOG_TIMEOUT:
+		env->secs_till_kill = atoi(arg);
+		if (env->secs_till_kill < 0) {
+			fprintf(stderr, "Invalid watchdog timeout: %s.\n", arg);
+			return -EINVAL;
+		}
+		if (env->secs_till_kill < env->secs_till_notify) {
+			env->secs_till_notify = 0;
+		}
+		break;
 	default:
 		return ARGP_ERR_UNKNOWN;
 	}
@@ -1263,10 +1360,12 @@ static void run_one_test(int test_num)
 
 	stdio_hijack(&state->log_buf, &state->log_cnt);
 
+	watchdog_start();
 	if (test->run_test)
 		test->run_test();
 	else if (test->run_serial_test)
 		test->run_serial_test();
+	watchdog_stop();
 
 	/* ensure last sub-test is finalized properly */
 	if (env.subtest_state)
@@ -1707,6 +1806,7 @@ out:
 static int worker_main(int sock)
 {
 	save_netns();
+	watchdog_init();
 
 	while (true) {
 		/* receive command */
@@ -1816,6 +1916,8 @@ int main(int argc, char **argv)
 
 	sigaction(SIGSEGV, &sigact, NULL);
 
+	env.secs_till_notify = 10;
+	env.secs_till_kill = 120;
 	err = argp_parse(&argp, argc, argv, 0, NULL, &env);
 	if (err)
 		return err;
@@ -1824,6 +1926,8 @@ int main(int argc, char **argv)
 	if (err)
 		return err;
 
+	watchdog_init();
+
 	/* Use libbpf 1.0 API mode */
 	libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
 	libbpf_set_print(libbpf_print_fn);
diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h
index 7a58895867c3..74de33ae37e5 100644
--- a/tools/testing/selftests/bpf/test_progs.h
+++ b/tools/testing/selftests/bpf/test_progs.h
@@ -131,6 +131,12 @@ struct test_env {
 	pid_t *worker_pids; /* array of worker pids */
 	int *worker_socks; /* array of worker socks */
 	int *worker_current_test; /* array of current running test for each worker */
+
+	pthread_t main_thread;
+	int secs_till_notify;
+	int secs_till_kill;
+	timer_t watchdog; /* watch for stalled tests/subtests */
+	enum { WD_NOTIFY, WD_KILL } watchdog_state;
 };
 
 #define MAX_LOG_TRUNK_SIZE 8192