Skip to contentSkip to conversation

selftests/bpf: Skip res_spin_lock_stress if no perf support

PATCH Applied Maxim Khmelevskii 2 participants 2 messages Jul 8

Subsystems (3)
lore
Share & tools
lore
#0 lore raw

PATCH 1/1 selftests/bpf: Skip res_spin_lock_stress if no perf support

Probe PMU support before loading bpf_test_rqspinlock.ko, otherwise the test fails with not obvious error without proper perf event support:

Failed to load bpf_test_rqspinlock.ko into the kernel: -2 serial_test_res_spin_lock_stress:FAIL:load module AA
unexpected error: -22 (errno 2)

---
 .../selftests/bpf/prog_tests/res_spin_lock.c  | 20 +++++++++++++++++++
 1 file changed, 20 insertions(+)
tools/testing/selftests/bpf/prog_tests/res_spin_lock.c +20 -0
index f0a8c828f8f1..7541f4966abc 100644
@@ -3,6 +3,8 @@
 #include <test_progs.h>
 #include <network_helpers.h>
 #include <sys/sysinfo.h>
+#include <sys/syscall.h>
+#include <linux/perf_event.h>
 
 #include "res_spin_lock.skel.h"
 #include "res_spin_lock_fail.skel.h"
@@ -102,11 +104,29 @@ void test_res_spin_lock_success(void)
 
 void serial_test_res_spin_lock_stress(void)
 {
+	struct perf_event_attr attr = {
+		.size = sizeof(attr),
+		.type = PERF_TYPE_HARDWARE,
+		.config = PERF_COUNT_HW_CPU_CYCLES,
+	};
+	int pmu_fd;
+
 	if (libbpf_num_possible_cpus() < 3) {
 		test__skip();
 		return;
 	}
 
+	pmu_fd = syscall(__NR_perf_event_open, &attr, 0, -1, -1, 0);
+	if (pmu_fd < 0) {
+		if (errno == ENOENT || errno == EOPNOTSUPP) {
+			test__skip();
+			return;
+		}
+		ASSERT_OK(-errno, "perf_event_open pmu probe");
+		return;
+	}
+	close(pmu_fd);
+
 	ASSERT_OK(load_module("bpf_test_rqspinlock.ko", false), "load module AA");
 	sleep(5);
 	unload_module("bpf_test_rqspinlock", false);
Signature · 1 line
2.54.0
#1 lore raw
This patch was applied to bpf/bpf-next.git (master) by Kumar Kartikeya Dwivedi <[email protected]>:

Hello:

This patch was applied to bpf/bpf-next.git (master) by Kumar Kartikeya Dwivedi <[email protected]>:

Quoted 9 lines · On Wed, 8 Jul 2026 12:47:17 +0200 you wrote:

Probe PMU support before loading bpf_test_rqspinlock.ko, otherwise the test fails with not obvious error without proper perf event support:

Failed to load bpf_test_rqspinlock.ko into the kernel: -2 serial_test_res_spin_lock_stress:FAIL:load module AA
unexpected error: -22 (errno 2)

[...]

Here is the summary with links:
- [bpf-next] selftests/bpf: Skip res_spin_lock_stress if no perf support

    https://git.kernel.org/bpf/bpf-next/c/41ec7e4a1779

You are awesome, thank you!

Signature · 2 lines
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html