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@xxxxxxxxxx>
---
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
