selftests/bpf: watchdog timer for test_progs

This commit provides a watchdog timer that sets a limit of how long a
single sub-test could run:
- if sub-test runs for 10 seconds, the name of the test is printed
  (currently the name of the test is printed only after it finishes);
- if sub-test runs for 120 seconds, the running thread is terminated
  with SIGSEGV (to trigger crash_handler() and get a stack trace).

Specifically:
- the timer is armed on each call to run_one_test();
- re-armed at each call to test__start_subtest();
- is stopped when exiting run_one_test().

Default timeout could be overridden using '-w' or '--watchdog-timeout'
options. Value 0 can be used to turn the timer off.
Here is an example execution:

    $ ./ssh-exec.sh ./test_progs -w 5 -t \
      send_signal/send_signal_perf_thread_remote,send_signal/send_signal_nmi_thread_remote
    WATCHDOG: test case send_signal/send_signal_nmi_thread_remote executes for 5 seconds, terminating with SIGSEGV
    Caught signal #11!
    Stack trace:
    ./test_progs(crash_handler+0x1f)[0x9049ef]
    /lib64/libc.so.6(+0x40d00)[0x7f1f1184fd00]
    /lib64/libc.so.6(read+0x4a)[0x7f1f1191cc4a]
    ./test_progs[0x720dd3]
    ./test_progs[0x71ef7a]
    ./test_progs(test_send_signal+0x1db)[0x71edeb]
    ./test_progs[0x9066c5]
    ./test_progs(main+0x5ed)[0x9054ad]
    /lib64/libc.so.6(+0x2a088)[0x7f1f11839088]
    /lib64/libc.so.6(__libc_start_main+0x8b)[0x7f1f1183914b]
    ./test_progs(_start+0x25)[0x527385]
    #292     send_signal:FAIL
    test_send_signal_common:PASS:reading pipe 0 nsec
    test_send_signal_common:PASS:reading pipe error: size 0 0 nsec
    test_send_signal_common:PASS:incorrect result 0 nsec
    test_send_signal_common:PASS:pipe_write 0 nsec
    test_send_signal_common:PASS:setpriority 0 nsec

Timer is implemented using timer_{create,start} librt API.
Internally librt uses pthreads for SIGEV_THREAD timers,
so this change adds a background timer thread to the test process.
Because of this a few checks in tests 'bpf_iter' and 'iters'
need an update to account for an extra thread.

For parallelized scenario the watchdog is also created for each worker
fork. If one of the workers gets stuck, it would be terminated by a
watchdog. In theory, this might lead to a scenario when all worker
threads are exhausted, however this should not be a problem for
server_main(), as it would exit with some of the tests not run.

Signed-off-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20241112110906.3045278-2-eddyz87@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

1 files changed, 4 insertions, 4 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);
 }