The following commit has been merged into the perf/core branch of tip:
Commit-ID: 47a3aeb39e8dc099ae431cd8b46bdf218f5511b2
Gitweb: https://git.kernel.org/tip/47a3aeb39e8dc099ae431cd8b46bdf218f5511b2
Author: Kan Liang <kan.liang@xxxxxxxxxxxxxxx>
AuthorDate: Thu, 01 Sep 2022 06:09:55 -07:00
Committer: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
CommitterDate: Tue, 06 Sep 2022 11:33:01 +02:00
perf/x86/intel/pebs: Fix PEBS timestamps overwritten
The PEBS TSC-based timestamps do not appear correctly in the final
perf.data output file from perf record.
The data->time field setup by PEBS in the setup_pebs_fixed_sample_data()
is later overwritten by perf_events generic code in
perf_prepare_sample(). There is an ordering problem.
Set the sample flags when the data->time is updated by PEBS.
The data->time field will not be overwritten anymore.
Reported-by: Andreas Kogler <andreas.kogler.0x@xxxxxxxxx>
Reported-by: Stephane Eranian <eranian@xxxxxxxxxx>
Signed-off-by: Kan Liang <kan.liang@xxxxxxxxxxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Link: https://lore.kernel.org/r/20220901130959.1285717-3-kan.liang@xxxxxxxxxxxxxxx
---
arch/x86/events/intel/ds.c | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index ba60427..cdd857b 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1635,8 +1635,10 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event,
* We can only do this for the default trace clock.
*/
if (x86_pmu.intel_cap.pebs_format >= 3 &&
- event->attr.use_clockid == 0)
+ event->attr.use_clockid == 0) {
data->time = native_sched_clock_from_tsc(pebs->tsc);
+ data->sample_flags |= PERF_SAMPLE_TIME;
+ }
if (has_branch_stack(event))
data->br_stack = &cpuc->lbr_stack;
@@ -1697,8 +1699,10 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
perf_sample_data_init(data, 0, event->hw.last_period);
data->period = event->hw.last_period;
- if (event->attr.use_clockid == 0)
+ if (event->attr.use_clockid == 0) {
data->time = native_sched_clock_from_tsc(basic->tsc);
+ data->sample_flags |= PERF_SAMPLE_TIME;
+ }
/*
* We must however always use iregs for the unwinder to stay sane; the
|