[PATCH v3 2/3] perf lock contention: Check race in tstamp elem creation

[Namhyung Kim <namhyung@kernel.org>]

When pelem is NULL, it'd create a new entry with zero data.  But it
might be preempted by IRQ/NMI just before calling bpf_map_update_elem()
then there's a chance to call it twice for the same pid.  So it'd be
better to use BPF_NOEXIST flag and check the return value to prevent
the race.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/bpf_skel/lock_contention.bpf.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/bpf_skel/lock_contention.bpf.c b/tools/perf/util/bpf_skel/lock_contention.bpf.c
index b11179452e19..69d31fd77cd0 100644
--- a/tools/perf/util/bpf_skel/lock_contention.bpf.c
+++ b/tools/perf/util/bpf_skel/lock_contention.bpf.c
@@ -328,7 +328,11 @@ int contention_begin(u64 *ctx)
 	if (pelem == NULL) {
 		struct tstamp_data zero = {};
 
-		bpf_map_update_elem(&tstamp, &pid, &zero, BPF_ANY);
+		if (bpf_map_update_elem(&tstamp, &pid, &zero, BPF_NOEXIST) < 0) {
+			__sync_fetch_and_add(&task_fail, 1);
+			return 0;
+		}
+
 		pelem = bpf_map_lookup_elem(&tstamp, &pid);
 		if (pelem == NULL) {
 			__sync_fetch_and_add(&task_fail, 1);
-- 
2.42.0.655.g421f12c284-goog