Time readers rely on perf_event_context->[time|timestamp|timeoffset] to get
accurate time_enabled and time_running for an event. The difference between
ctx->timestamp and ctx->time is the among of time when the context is not
enabled. __update_context_time(ctx, false) is used to increase timestamp,
but not time. Therefore, it should only be called in ctx_sched_in() when
EVENT_TIME was not enabled.

Fixes: 09f5e7dc7ad7 ("perf: Fix perf_event_read_local() time")
Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Song Liu <song@kernel.org>
---
 kernel/events/core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 380476a934e8..67478f43e26e 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3872,7 +3872,7 @@ ctx_sched_in(struct perf_event_context *ctx, enum event_type_t event_type)
 	if (likely(!ctx->nr_events))
 		return;
 
-	if (is_active ^ EVENT_TIME) {
+	if (!(is_active & EVENT_TIME)) {
 		/* start ctx time */
 		__update_context_time(ctx, false);
 		perf_cgroup_set_timestamp(cpuctx);
-- 
2.34.1

On Mon, Mar 13, 2023 at 10:16:08AM -0700, Song Liu wrote:
> Time readers rely on perf_event_context->[time|timestamp|timeoffset] to get
> accurate time_enabled and time_running for an event. The difference between
> ctx->timestamp and ctx->time is the among of time when the context is not
> enabled. __update_context_time(ctx, false) is used to increase timestamp,
> but not time. Therefore, it should only be called in ctx_sched_in() when
> EVENT_TIME was not enabled.
> 
> Fixes: 09f5e7dc7ad7 ("perf: Fix perf_event_read_local() time")
> Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
> Cc: Namhyung Kim <namhyung@kernel.org>
> Acked-by: Namhyung Kim <namhyung@kernel.org>
> Signed-off-by: Song Liu <song@kernel.org>

Looks like I'm wearing another brown paper bag tonight..

Thanks!

The following commit has been merged into the perf/urgent branch of tip:

Commit-ID:     baf1b12a67f5b24f395baca03e442ce27cab0c18
Gitweb:        https://git.kernel.org/tip/baf1b12a67f5b24f395baca03e442ce27cab0c18
Author:        Song Liu <song@kernel.org>
AuthorDate:    Mon, 13 Mar 2023 10:16:08 -07:00
Committer:     Peter Zijlstra <peterz@infradead.org>
CommitterDate: Wed, 15 Mar 2023 21:49:46 +01:00

perf: fix perf_event_context->time

Time readers rely on perf_event_context->[time|timestamp|timeoffset] to get
accurate time_enabled and time_running for an event. The difference between
ctx->timestamp and ctx->time is the among of time when the context is not
enabled. __update_context_time(ctx, false) is used to increase timestamp,
but not time. Therefore, it should only be called in ctx_sched_in() when
EVENT_TIME was not enabled.

Fixes: 09f5e7dc7ad7 ("perf: Fix perf_event_read_local() time")
Signed-off-by: Song Liu <song@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/r/20230313171608.298734-1-song@kernel.org
---
 kernel/events/core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 296617e..52b4aa0 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3872,7 +3872,7 @@ ctx_sched_in(struct perf_event_context *ctx, enum event_type_t event_type)
 	if (likely(!ctx->nr_events))
 		return;
 
-	if (is_active ^ EVENT_TIME) {
+	if (!(is_active & EVENT_TIME)) {
 		/* start ctx time */
 		__update_context_time(ctx, false);
 		perf_cgroup_set_timestamp(cpuctx);