From 27746aaf1b20172f0859546c4a3e82eca459f680 Mon Sep 17 00:00:00 2001 From: Matt Bobrowski Date: Thu, 20 Nov 2025 14:20:59 +0000 Subject: selftests/bpf: skip test_perf_branches_hw() on unsupported platforms Gracefully skip the test_perf_branches_hw subtest on platforms that do not support LBR or require specialized perf event attributes to enable branch sampling. For example, AMD's Milan (Zen 3) supports BRS rather than traditional LBR. This requires specific configurations (attr.type = PERF_TYPE_RAW, attr.config = RETIRED_TAKEN_BRANCH_INSTRUCTIONS) that differ from the generic setup used within this test. Notably, it also probably doesn't hold much value to special case perf event configurations for selected micro architectures. Fixes: 67306f84ca78c ("selftests/bpf: Add bpf_read_branch_records() selftest") Signed-off-by: Matt Bobrowski Acked-by: Song Liu Link: https://lore.kernel.org/r/20251120142059.2836181-1-mattbobrowski@google.com Signed-off-by: Alexei Starovoitov --- tools/testing/selftests/bpf/prog_tests/perf_branches.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'tools/testing/selftests/bpf/prog_tests/perf_branches.c') diff --git a/tools/testing/selftests/bpf/prog_tests/perf_branches.c b/tools/testing/selftests/bpf/prog_tests/perf_branches.c index bc24f83339d6..06c7986131d9 100644 --- a/tools/testing/selftests/bpf/prog_tests/perf_branches.c +++ b/tools/testing/selftests/bpf/prog_tests/perf_branches.c @@ -116,11 +116,11 @@ static void test_perf_branches_hw(void) pfd = syscall(__NR_perf_event_open, &attr, -1, 0, -1, PERF_FLAG_FD_CLOEXEC); /* - * Some setups don't support branch records (virtual machines, !x86), - * so skip test in this case. + * Some setups don't support LBR (virtual machines, !x86, AMD Milan Zen + * 3 which only supports BRS), so skip test in this case. */ if (pfd < 0) { - if (errno == ENOENT || errno == EOPNOTSUPP) { + if (errno == ENOENT || errno == EOPNOTSUPP || errno == EINVAL) { printf("%s:SKIP:no PERF_SAMPLE_BRANCH_STACK\n", __func__); test__skip(); -- cgit v1.2.3 From ae24fc8a16b0481ea8c5acbc66453c49ec0431c4 Mon Sep 17 00:00:00 2001 From: Matt Bobrowski Date: Wed, 19 Nov 2025 14:35:40 +0000 Subject: selftests/bpf: Improve reliability of test_perf_branches_no_hw() Currently, test_perf_branches_no_hw() relies on the busy loop within test_perf_branches_common() being slow enough to allow at least one perf event sample tick to occur before starting to tear down the backing perf event BPF program. With a relatively small fixed iteration count of 1,000,000, this is not guaranteed on modern fast CPUs, resulting in the test run to subsequently fail with the following: bpf_testmod.ko is already unloaded. Loading bpf_testmod.ko... Successfully loaded bpf_testmod.ko. test_perf_branches_common:PASS:test_perf_branches_load 0 nsec test_perf_branches_common:PASS:attach_perf_event 0 nsec test_perf_branches_common:PASS:set_affinity 0 nsec check_good_sample:PASS:output not valid 0 nsec check_good_sample:PASS:read_branches_size 0 nsec check_good_sample:PASS:read_branches_stack 0 nsec check_good_sample:PASS:read_branches_stack 0 nsec check_good_sample:PASS:read_branches_global 0 nsec check_good_sample:PASS:read_branches_global 0 nsec check_good_sample:PASS:read_branches_size 0 nsec test_perf_branches_no_hw:PASS:perf_event_open 0 nsec test_perf_branches_common:PASS:test_perf_branches_load 0 nsec test_perf_branches_common:PASS:attach_perf_event 0 nsec test_perf_branches_common:PASS:set_affinity 0 nsec check_bad_sample:FAIL:output not valid no valid sample from prog Summary: 0/1 PASSED, 0 SKIPPED, 1 FAILED Successfully unloaded bpf_testmod.ko. On a modern CPU (i.e. one with a 3.5 GHz clock rate), executing 1 million increments of a volatile integer can take significantly less than 1 millisecond. If the spin loop and detachment of the perf event BPF program elapses before the first 1 ms sampling interval elapses, the perf event will never end up firing. Fix this by bumping the loop iteration counter a little within test_perf_branches_common(), along with ensuring adding another loop termination condition which is directly influenced by the backing perf event BPF program executing. Notably, a concious decision was made to not adjust the sample_freq value as that is just not a reliable way to go about fixing the problem. It effectively still leaves the race window open. Fixes: 67306f84ca78c ("selftests/bpf: Add bpf_read_branch_records() selftest") Signed-off-by: Matt Bobrowski Reviewed-by: Jiri Olsa Link: https://lore.kernel.org/r/20251119143540.2911424-1-mattbobrowski@google.com Signed-off-by: Alexei Starovoitov --- tools/testing/selftests/bpf/prog_tests/perf_branches.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) (limited to 'tools/testing/selftests/bpf/prog_tests/perf_branches.c') diff --git a/tools/testing/selftests/bpf/prog_tests/perf_branches.c b/tools/testing/selftests/bpf/prog_tests/perf_branches.c index 06c7986131d9..0a7ef770c487 100644 --- a/tools/testing/selftests/bpf/prog_tests/perf_branches.c +++ b/tools/testing/selftests/bpf/prog_tests/perf_branches.c @@ -15,6 +15,10 @@ static void check_good_sample(struct test_perf_branches *skel) int pbe_size = sizeof(struct perf_branch_entry); int duration = 0; + if (CHECK(!skel->bss->run_cnt, "invalid run_cnt", + "checked sample validity before prog run")) + return; + if (CHECK(!skel->bss->valid, "output not valid", "no valid sample from prog")) return; @@ -45,6 +49,10 @@ static void check_bad_sample(struct test_perf_branches *skel) int written_stack = skel->bss->written_stack_out; int duration = 0; + if (CHECK(!skel->bss->run_cnt, "invalid run_cnt", + "checked sample validity before prog run")) + return; + if (CHECK(!skel->bss->valid, "output not valid", "no valid sample from prog")) return; @@ -83,8 +91,12 @@ static void test_perf_branches_common(int perf_fd, err = pthread_setaffinity_np(pthread_self(), sizeof(cpu_set), &cpu_set); if (CHECK(err, "set_affinity", "cpu #0, err %d\n", err)) goto out_destroy; - /* spin the loop for a while (random high number) */ - for (i = 0; i < 1000000; ++i) + + /* Spin the loop for a while by using a high iteration count, and by + * checking whether the specific run count marker has been explicitly + * incremented at least once by the backing perf_event BPF program. + */ + for (i = 0; i < 100000000 && !*(volatile int *)&skel->bss->run_cnt; ++i) ++j; test_perf_branches__detach(skel); -- cgit v1.2.3