Received-SPF: pass (google.com: domain of linux-kernel+bounces-136989-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.199.223 as permitted sender) client-ip=147.75.199.223;
Date: Tue, 9 Apr 2024 15:38:03 +0200
From: Oleg Nesterov <oleg@redhat.com>
To: Thomas Gleixner <tglx@linutronix.de>
Cc: Dmitry Vyukov <dvyukov@google.com>, John Stultz <jstultz@google.com>,
	Marco Elver <elver@google.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@kernel.org>,
	"Eric W. Biederman" <ebiederm@xmission.com>,
	linux-kernel@vger.kernel.org, linux-kselftest@vger.kernel.org,
	kasan-dev@googlegroups.com, Edward Liaw <edliaw@google.com>,
	Carlos Llamas <cmllamas@google.com>,
	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Subject: [PATCH v2] selftests/timers/posix_timers: reimplement
 check_timer_distribution()
Message-ID: <20240409133802.GD29396@redhat.com>
References: <20240404145408.GD7153@redhat.com>
 <87le5t9f14.ffs@tglx>
 <20240406150950.GA3060@redhat.com>
 <20240406151057.GB3060@redhat.com>
 <CACT4Y+Ych4+pdpcTk=yWYUOJcceL5RYoE_B9djX_pwrgOcGmFA@mail.gmail.com>
 <20240408102639.GA25058@redhat.com>
 <20240408184957.GD25058@redhat.com>
 <87il0r7b4k.ffs@tglx>
 <20240409111051.GB29396@redhat.com>
 <877ch67nhb.ffs@tglx>
Precedence: bulk
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <877ch67nhb.ffs@tglx>
User-Agent: Mutt/1.5.24 (2015-08-30)

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.

As Thomas suggested, the new version doesn't report the failure on the
pre v6.3 kernels that do not have the commit bcb7ee79029d; this is a
feature that obviously fails on the older kernels. So the patch adds the
new simple ksft_ck_kernel_version() helper and uses ksft_test_result_skip()
if check_timer_distribution() fails on the older kernel.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
---
 tools/testing/selftests/kselftest.h           |  14 +++
 tools/testing/selftests/timers/posix_timers.c | 103 ++++++++----------
 2 files changed, 61 insertions(+), 56 deletions(-)

diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h
index 541bf192e30e..6aab3309c6a3 100644
--- a/tools/testing/selftests/kselftest.h
+++ b/tools/testing/selftests/kselftest.h
@@ -51,6 +51,7 @@
 #include <stdarg.h>
 #include <string.h>
 #include <stdio.h>
+#include <sys/utsname.h>
 #endif
 
 #ifndef ARRAY_SIZE
@@ -388,4 +389,17 @@ static inline __printf(1, 2) int ksft_exit_skip(const char *msg, ...)
 	exit(KSFT_SKIP);
 }
 
+static inline int ksft_ck_kernel_version(unsigned int min_major,
+					 unsigned int min_minor)
+{
+	struct utsname info;
+	unsigned int major, minor;
+
+	uname(&info);
+	if (sscanf(info.release, "%u.%u.", &major, &minor) != 2)
+		ksft_exit_fail();
+
+	return major > min_major || (major == min_major && minor >= min_minor);
+}
+
 #endif /* __KSELFTEST_H */
diff --git a/tools/testing/selftests/timers/posix_timers.c b/tools/testing/selftests/timers/posix_timers.c
index d49dd3ffd0d9..64c41463b704 100644
--- a/tools/testing/selftests/timers/posix_timers.c
+++ b/tools/testing/selftests/timers/posix_timers.c
@@ -184,80 +184,71 @@ 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;
 
-	ksft_test_result_pass("check_timer_distribution\n");
+	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_pass("check signal distribution\n");
+	else if (ksft_ck_kernel_version(6, 3))
+		ksft_test_result_fail("check signal distribution\n");
+	else
+		ksft_test_result_skip("check signal distribution (old kernel)\n");
 	return 0;
+err:
+	ksft_print_msg(errmsg);
+	return -1;
 }
 
 int main(int argc, char **argv)
-- 
2.25.1.362.g51ebf55