The following commit has been merged into the perf/core branch of tip:
Commit-ID: 0eed28220598cd990d094b7b9f8c832c425080c0
Gitweb: https://git.kernel.org/tip/0eed28220598cd990d094b7b9f8c832c425080c0
Author: Namhyung Kim <namhyung@xxxxxxxxxx>
AuthorDate: Tue, 17 Jan 2023 22:05:59 -08:00
Committer: Ingo Molnar <mingo@xxxxxxxxxx>
CommitterDate: Wed, 18 Jan 2023 11:57:21 +01:00
perf/core: Call perf_prepare_sample() before running BPF
As BPF can access sample data, it needs to populate the data. Also
remove the logic to get the callchain specifically as it's covered by
the perf_prepare_sample() now.
Signed-off-by: Namhyung Kim <namhyung@xxxxxxxxxx>
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
Tested-by: Jiri Olsa <jolsa@xxxxxxxxxx>
Acked-by: Jiri Olsa <jolsa@xxxxxxxxxx>
Acked-by: Song Liu <song@xxxxxxxxxx>
Acked-by: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Link: https://lore.kernel.org/r/20230118060559.615653-9-namhyung@xxxxxxxxxx
---
kernel/events/core.c | 8 +-------
1 file changed, 1 insertion(+), 7 deletions(-)
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 4aa73ed..380476a 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -10356,13 +10356,7 @@ static void bpf_overflow_handler(struct perf_event *event,
rcu_read_lock();
prog = READ_ONCE(event->prog);
if (prog) {
- if (prog->call_get_stack &&
- (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) &&
- !(data->sample_flags & PERF_SAMPLE_CALLCHAIN)) {
- data->callchain = perf_callchain(event, regs);
- data->sample_flags |= PERF_SAMPLE_CALLCHAIN;
- }
-
+ perf_prepare_sample(data, event, regs);
ret = bpf_prog_run(prog, &ctx);
}
rcu_read_unlock();
|