[PATCH v3 RESEND] perf/core: Fix missing read event generation on task exit

[PATCH v3 RESEND] perf/core: Fix missing read event generation on task exit

[Thaumy Cheng]

For events with inherit_stat enabled, a "read" event will be generated
to collect per task event counts on task exit.

The call chain is as follows:

do_exit
  -> perf_event_exit_task
    -> perf_event_exit_task_context
      -> perf_event_exit_event
        -> perf_remove_from_context
          -> perf_child_detach
            -> sync_child_event
              -> perf_event_read_event

However, the child event context detaches the task too early in
perf_event_exit_task_context, which causes sync_child_event to never
generate the read event in this case, since child_event->ctx->task is
always set to TASK_TOMBSTONE. Fix that by moving context lock section
backward to ensure ctx->task is not set to TASK_TOMBSTONE before
generating the read event.

Because perf_event_free_task calls perf_event_exit_task_context with
exit = false to tear down all child events from the context, and the
task never lived, accessing the task PID can lead to a use-after-free.

To fix that, let sync_child_event read task from argument and move the
call to the only place it should be triggered to avoid the effect of
setting ctx->task to TASK_TOMESTONE, and add a task parameter to
perf_event_exit_event to trigger the sync_child_event properly when
needed.

This bug can be reproduced by running "perf record -s" and attaching to
any program that generates perf events in its child tasks. If we check
the result with "perf report -T", the last line of the report will leave
an empty table like "# PID  TID", which is expected to contain the
per-task event counts by design.

Fixes: ef54c1a476ae ("perf: Rework perf_event_exit_event()")
Signed-off-by: Thaumy Cheng <thaumy.love@gmail.com>
---
Changes in v3:
- Fix the bug in a more direct way by moving the call to
  sync_child_event and bring back the task param to
  perf_event_exit_event.
  This approach avoids the event unscheduling issue in v2.

Changes in v2:
- Only trigger read event on task exit.
- Rename perf_event_exit_event to perf_event_detach_event.
- Link to v2: https://lore.kernel.org/all/20250817132742.85154-1-thaumy.love@gmail.com/

Changes in v1:
- Set TASK_TOMBSTONE after the read event is tirggered.
- Link to v1: https://lore.kernel.org/all/20250720000424.12572-1-thaumy.love@gmail.com/

 kernel/events/core.c | 23 ++++++++++++++---------
 1 file changed, 14 insertions(+), 9 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 177e57c1a362..618e7947c358 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2316,7 +2316,8 @@ static void perf_group_detach(struct perf_event *event)
 	perf_event__header_size(leader);
 }

-static void sync_child_event(struct perf_event *child_event);
+static void sync_child_event(struct perf_event *child_event,
+			     struct task_struct *task);

 static void perf_child_detach(struct perf_event *event)
 {
@@ -2336,7 +2337,6 @@ static void perf_child_detach(struct perf_event *event)
 	lockdep_assert_held(&parent_event->child_mutex);
 	 */

-	sync_child_event(event);
 	list_del_init(&event->child_list);
 }

@@ -4587,6 +4587,7 @@ static void perf_event_enable_on_exec(struct perf_event_context *ctx)
 static void perf_remove_from_owner(struct perf_event *event);
 static void perf_event_exit_event(struct perf_event *event,
 				  struct perf_event_context *ctx,
+				  struct task_struct *task,
 				  bool revoke);

 /*
@@ -4614,7 +4615,7 @@ static void perf_event_remove_on_exec(struct perf_event_context *ctx)

 		modified = true;

-		perf_event_exit_event(event, ctx, false);
+		perf_event_exit_event(event, ctx, ctx->task, false);
 	}

 	raw_spin_lock_irqsave(&ctx->lock, flags);
@@ -12437,7 +12438,7 @@ static void __pmu_detach_event(struct pmu *pmu, struct perf_event *event,
 	/*
 	 * De-schedule the event and mark it REVOKED.
 	 */
-	perf_event_exit_event(event, ctx, true);
+	perf_event_exit_event(event, ctx, ctx->task, true);

 	/*
 	 * All _free_event() bits that rely on event->pmu:
@@ -13994,14 +13995,13 @@ void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu)
 }
 EXPORT_SYMBOL_GPL(perf_pmu_migrate_context);

-static void sync_child_event(struct perf_event *child_event)
+static void sync_child_event(struct perf_event *child_event,
+			     struct task_struct *task)
 {
 	struct perf_event *parent_event = child_event->parent;
 	u64 child_val;

 	if (child_event->attr.inherit_stat) {
-		struct task_struct *task = child_event->ctx->task;
-
 		if (task && task != TASK_TOMBSTONE)
 			perf_event_read_event(child_event, task);
 	}
@@ -14020,7 +14020,9 @@ static void sync_child_event(struct perf_event *child_event)

 static void
 perf_event_exit_event(struct perf_event *event,
-		      struct perf_event_context *ctx, bool revoke)
+		      struct perf_event_context *ctx,
+		      struct task_struct *task,
+		      bool revoke)
 {
 	struct perf_event *parent_event = event->parent;
 	unsigned long detach_flags = DETACH_EXIT;
@@ -14043,6 +14045,9 @@ perf_event_exit_event(struct perf_event *event,
 		mutex_lock(&parent_event->child_mutex);
 		/* PERF_ATTACH_ITRACE might be set concurrently */
 		attach_state = READ_ONCE(event->attach_state);
+
+		if (attach_state & PERF_ATTACH_CHILD)
+			sync_child_event(event, task);
 	}

 	if (revoke)
@@ -14134,7 +14139,7 @@ static void perf_event_exit_task_context(struct task_struct *task, bool exit)
 		perf_event_task(task, ctx, 0);

 	list_for_each_entry_safe(child_event, next, &ctx->event_list, event_entry)
-		perf_event_exit_event(child_event, ctx, false);
+		perf_event_exit_event(child_event, ctx, exit ? task : NULL, false);

 	mutex_unlock(&ctx->mutex);

--
2.51.0

[tip: perf/urgent] perf/core: Fix missing read event generation on task exit

[tip-bot2 for Thaumy Cheng]

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

Commit-ID:     02a4984a359633d45b0926eb2a9c6d7bfb71b2e2
Gitweb:        https://git.kernel.org/tip/02a4984a359633d45b0926eb2a9c6d7bfb71b2e2
Author:        Thaumy Cheng <thaumy.love@gmail.com>
AuthorDate:    Tue, 09 Dec 2025 12:16:00 +08:00
Committer:     Ingo Molnar <mingo@kernel.org>
CommitterDate: Tue, 09 Dec 2025 09:57:45 +01:00

perf/core: Fix missing read event generation on task exit

For events with inherit_stat enabled, a "read" event will be generated
to collect per task event counts on task exit.

The call chain is as follows:

do_exit
  -> perf_event_exit_task
    -> perf_event_exit_task_context
      -> perf_event_exit_event
        -> perf_remove_from_context
          -> perf_child_detach
            -> sync_child_event
              -> perf_event_read_event

However, the child event context detaches the task too early in
perf_event_exit_task_context, which causes sync_child_event to never
generate the read event in this case, since child_event->ctx->task is
always set to TASK_TOMBSTONE. Fix that by moving context lock section
backward to ensure ctx->task is not set to TASK_TOMBSTONE before
generating the read event.

Because perf_event_free_task calls perf_event_exit_task_context with
exit = false to tear down all child events from the context, and the
task never lived, accessing the task PID can lead to a use-after-free.

To fix that, let sync_child_event read task from argument and move the
call to the only place it should be triggered to avoid the effect of
setting ctx->task to TASK_TOMESTONE, and add a task parameter to
perf_event_exit_event to trigger the sync_child_event properly when
needed.

This bug can be reproduced by running "perf record -s" and attaching to
any program that generates perf events in its child tasks. If we check
the result with "perf report -T", the last line of the report will leave
an empty table like "# PID  TID", which is expected to contain the
per-task event counts by design.

Fixes: ef54c1a476ae ("perf: Rework perf_event_exit_event()")
Signed-off-by: Thaumy Cheng <thaumy.love@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Ian Rogers <irogers@google.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: linux-perf-users@vger.kernel.org
Link: https://patch.msgid.link/20251209041600.963586-1-thaumy.love@gmail.com
---
 kernel/events/core.c | 23 ++++++++++++++---------
 1 file changed, 14 insertions(+), 9 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index ece7168..47d5dc4 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2317,7 +2317,8 @@ out:
 	perf_event__header_size(leader);
 }
 
-static void sync_child_event(struct perf_event *child_event);
+static void sync_child_event(struct perf_event *child_event,
+			     struct task_struct *task);
 
 static void perf_child_detach(struct perf_event *event)
 {
@@ -2337,7 +2338,6 @@ static void perf_child_detach(struct perf_event *event)
 	lockdep_assert_held(&parent_event->child_mutex);
 	 */
 
-	sync_child_event(event);
 	list_del_init(&event->child_list);
 }
 
@@ -4588,6 +4588,7 @@ out:
 static void perf_remove_from_owner(struct perf_event *event);
 static void perf_event_exit_event(struct perf_event *event,
 				  struct perf_event_context *ctx,
+				  struct task_struct *task,
 				  bool revoke);
 
 /*
@@ -4615,7 +4616,7 @@ static void perf_event_remove_on_exec(struct perf_event_context *ctx)
 
 		modified = true;
 
-		perf_event_exit_event(event, ctx, false);
+		perf_event_exit_event(event, ctx, ctx->task, false);
 	}
 
 	raw_spin_lock_irqsave(&ctx->lock, flags);
@@ -12518,7 +12519,7 @@ static void __pmu_detach_event(struct pmu *pmu, struct perf_event *event,
 	/*
 	 * De-schedule the event and mark it REVOKED.
 	 */
-	perf_event_exit_event(event, ctx, true);
+	perf_event_exit_event(event, ctx, ctx->task, true);
 
 	/*
 	 * All _free_event() bits that rely on event->pmu:
@@ -14075,14 +14076,13 @@ void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu)
 }
 EXPORT_SYMBOL_GPL(perf_pmu_migrate_context);
 
-static void sync_child_event(struct perf_event *child_event)
+static void sync_child_event(struct perf_event *child_event,
+			     struct task_struct *task)
 {
 	struct perf_event *parent_event = child_event->parent;
 	u64 child_val;
 
 	if (child_event->attr.inherit_stat) {
-		struct task_struct *task = child_event->ctx->task;
-
 		if (task && task != TASK_TOMBSTONE)
 			perf_event_read_event(child_event, task);
 	}
@@ -14101,7 +14101,9 @@ static void sync_child_event(struct perf_event *child_event)
 
 static void
 perf_event_exit_event(struct perf_event *event,
-		      struct perf_event_context *ctx, bool revoke)
+		      struct perf_event_context *ctx,
+		      struct task_struct *task,
+		      bool revoke)
 {
 	struct perf_event *parent_event = event->parent;
 	unsigned long detach_flags = DETACH_EXIT;
@@ -14124,6 +14126,9 @@ perf_event_exit_event(struct perf_event *event,
 		mutex_lock(&parent_event->child_mutex);
 		/* PERF_ATTACH_ITRACE might be set concurrently */
 		attach_state = READ_ONCE(event->attach_state);
+
+		if (attach_state & PERF_ATTACH_CHILD)
+			sync_child_event(event, task);
 	}
 
 	if (revoke)
@@ -14215,7 +14220,7 @@ static void perf_event_exit_task_context(struct task_struct *task, bool exit)
 		perf_event_task(task, ctx, 0);
 
 	list_for_each_entry_safe(child_event, next, &ctx->event_list, event_entry)
-		perf_event_exit_event(child_event, ctx, false);
+		perf_event_exit_event(child_event, ctx, exit ? task : NULL, false);
 
 	mutex_unlock(&ctx->mutex);
 

Re: [PATCH v3 RESEND] perf/core: Fix missing read event generation on task exit

[Peter Zijlstra]

On Tue, Dec 09, 2025 at 12:16:00PM +0800, Thaumy Cheng wrote:
> For events with inherit_stat enabled, a "read" event will be generated
> to collect per task event counts on task exit.
> 
> The call chain is as follows:
> 
> do_exit
>   -> perf_event_exit_task
>     -> perf_event_exit_task_context
>       -> perf_event_exit_event
>         -> perf_remove_from_context
>           -> perf_child_detach
>             -> sync_child_event
>               -> perf_event_read_event
> 
> However, the child event context detaches the task too early in
> perf_event_exit_task_context, which causes sync_child_event to never
> generate the read event in this case, since child_event->ctx->task is
> always set to TASK_TOMBSTONE. Fix that by moving context lock section
> backward to ensure ctx->task is not set to TASK_TOMBSTONE before
> generating the read event.
> 
> Because perf_event_free_task calls perf_event_exit_task_context with
> exit = false to tear down all child events from the context, and the
> task never lived, accessing the task PID can lead to a use-after-free.
> 
> To fix that, let sync_child_event read task from argument and move the
> call to the only place it should be triggered to avoid the effect of
> setting ctx->task to TASK_TOMESTONE, and add a task parameter to
> perf_event_exit_event to trigger the sync_child_event properly when
> needed.
> 
> This bug can be reproduced by running "perf record -s" and attaching to
> any program that generates perf events in its child tasks. If we check
> the result with "perf report -T", the last line of the report will leave
> an empty table like "# PID  TID", which is expected to contain the
> per-task event counts by design.
> 
> Fixes: ef54c1a476ae ("perf: Rework perf_event_exit_event()")
> Signed-off-by: Thaumy Cheng <thaumy.love@gmail.com>
> ---

>  kernel/events/core.c | 23 ++++++++++++++---------
>  1 file changed, 14 insertions(+), 9 deletions(-)
> 
> diff --git a/kernel/events/core.c b/kernel/events/core.c
> index 177e57c1a362..618e7947c358 100644
> --- a/kernel/events/core.c
> +++ b/kernel/events/core.c
> @@ -2316,7 +2316,8 @@ static void perf_group_detach(struct perf_event *event)
>  	perf_event__header_size(leader);
>  }
> 
> -static void sync_child_event(struct perf_event *child_event);
> +static void sync_child_event(struct perf_event *child_event,
> +			     struct task_struct *task);

This forward declaration can be entirely removed now.

Other than that, yes this seems fine. I see Ingo already picked up the
patch, thanks!

Re: [PATCH v3 RESEND] perf/core: Fix missing read event generation on task exit

[Ingo Molnar]

* Peter Zijlstra <peterz@infradead.org> wrote:

> >
> > -static void sync_child_event(struct perf_event *child_event);
> > +static void sync_child_event(struct perf_event *child_event,
> > +			     struct task_struct *task);
>
> This forward declaration can be entirely removed now.

Indeed - I've applied the delta patch below.

>
> Other than that, yes this seems fine. I see Ingo already picked up the
> patch, thanks!

and I've added your Acked-by as well.

Thanks,

	Ingo

================>
 kernel/events/core.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 47d5dc4bf700..dad0d3d2e85f 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2317,9 +2317,6 @@ static void perf_group_detach(struct perf_event *event)
 	perf_event__header_size(leader);
 }
 
-static void sync_child_event(struct perf_event *child_event,
-			     struct task_struct *task);
-
 static void perf_child_detach(struct perf_event *event)
 {
 	struct perf_event *parent_event = event->parent;

[tip: perf/urgent] perf/core: Fix missing read event generation on task exit

[tip-bot2 for Thaumy Cheng]

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

Commit-ID:     c418d8b4d7a43a86b82ee39cb52ece3034383530
Gitweb:        https://git.kernel.org/tip/c418d8b4d7a43a86b82ee39cb52ece3034383530
Author:        Thaumy Cheng <thaumy.love@gmail.com>
AuthorDate:    Tue, 09 Dec 2025 12:16:00 +08:00
Committer:     Ingo Molnar <mingo@kernel.org>
CommitterDate: Tue, 09 Dec 2025 12:22:25 +01:00

perf/core: Fix missing read event generation on task exit

For events with inherit_stat enabled, a "read" event will be generated
to collect per task event counts on task exit.

The call chain is as follows:

do_exit
  -> perf_event_exit_task
    -> perf_event_exit_task_context
      -> perf_event_exit_event
        -> perf_remove_from_context
          -> perf_child_detach
            -> sync_child_event
              -> perf_event_read_event

However, the child event context detaches the task too early in
perf_event_exit_task_context, which causes sync_child_event to never
generate the read event in this case, since child_event->ctx->task is
always set to TASK_TOMBSTONE. Fix that by moving context lock section
backward to ensure ctx->task is not set to TASK_TOMBSTONE before
generating the read event.

Because perf_event_free_task calls perf_event_exit_task_context with
exit = false to tear down all child events from the context, and the
task never lived, accessing the task PID can lead to a use-after-free.

To fix that, let sync_child_event read task from argument and move the
call to the only place it should be triggered to avoid the effect of
setting ctx->task to TASK_TOMESTONE, and add a task parameter to
perf_event_exit_event to trigger the sync_child_event properly when
needed.

This bug can be reproduced by running "perf record -s" and attaching to
any program that generates perf events in its child tasks. If we check
the result with "perf report -T", the last line of the report will leave
an empty table like "# PID  TID", which is expected to contain the
per-task event counts by design.

Fixes: ef54c1a476ae ("perf: Rework perf_event_exit_event()")
Signed-off-by: Thaumy Cheng <thaumy.love@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Ian Rogers <irogers@google.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: linux-perf-users@vger.kernel.org
Link: https://patch.msgid.link/20251209041600.963586-1-thaumy.love@gmail.com
---
 kernel/events/core.c | 22 ++++++++++++----------
 1 file changed, 12 insertions(+), 10 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index ece7168..dad0d3d 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2317,8 +2317,6 @@ out:
 	perf_event__header_size(leader);
 }
 
-static void sync_child_event(struct perf_event *child_event);
-
 static void perf_child_detach(struct perf_event *event)
 {
 	struct perf_event *parent_event = event->parent;
@@ -2337,7 +2335,6 @@ static void perf_child_detach(struct perf_event *event)
 	lockdep_assert_held(&parent_event->child_mutex);
 	 */
 
-	sync_child_event(event);
 	list_del_init(&event->child_list);
 }
 
@@ -4588,6 +4585,7 @@ out:
 static void perf_remove_from_owner(struct perf_event *event);
 static void perf_event_exit_event(struct perf_event *event,
 				  struct perf_event_context *ctx,
+				  struct task_struct *task,
 				  bool revoke);
 
 /*
@@ -4615,7 +4613,7 @@ static void perf_event_remove_on_exec(struct perf_event_context *ctx)
 
 		modified = true;
 
-		perf_event_exit_event(event, ctx, false);
+		perf_event_exit_event(event, ctx, ctx->task, false);
 	}
 
 	raw_spin_lock_irqsave(&ctx->lock, flags);
@@ -12518,7 +12516,7 @@ static void __pmu_detach_event(struct pmu *pmu, struct perf_event *event,
 	/*
 	 * De-schedule the event and mark it REVOKED.
 	 */
-	perf_event_exit_event(event, ctx, true);
+	perf_event_exit_event(event, ctx, ctx->task, true);
 
 	/*
 	 * All _free_event() bits that rely on event->pmu:
@@ -14075,14 +14073,13 @@ void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu)
 }
 EXPORT_SYMBOL_GPL(perf_pmu_migrate_context);
 
-static void sync_child_event(struct perf_event *child_event)
+static void sync_child_event(struct perf_event *child_event,
+			     struct task_struct *task)
 {
 	struct perf_event *parent_event = child_event->parent;
 	u64 child_val;
 
 	if (child_event->attr.inherit_stat) {
-		struct task_struct *task = child_event->ctx->task;
-
 		if (task && task != TASK_TOMBSTONE)
 			perf_event_read_event(child_event, task);
 	}
@@ -14101,7 +14098,9 @@ static void sync_child_event(struct perf_event *child_event)
 
 static void
 perf_event_exit_event(struct perf_event *event,
-		      struct perf_event_context *ctx, bool revoke)
+		      struct perf_event_context *ctx,
+		      struct task_struct *task,
+		      bool revoke)
 {
 	struct perf_event *parent_event = event->parent;
 	unsigned long detach_flags = DETACH_EXIT;
@@ -14124,6 +14123,9 @@ perf_event_exit_event(struct perf_event *event,
 		mutex_lock(&parent_event->child_mutex);
 		/* PERF_ATTACH_ITRACE might be set concurrently */
 		attach_state = READ_ONCE(event->attach_state);
+
+		if (attach_state & PERF_ATTACH_CHILD)
+			sync_child_event(event, task);
 	}
 
 	if (revoke)
@@ -14215,7 +14217,7 @@ static void perf_event_exit_task_context(struct task_struct *task, bool exit)
 		perf_event_task(task, ctx, 0);
 
 	list_for_each_entry_safe(child_event, next, &ctx->event_list, event_entry)
-		perf_event_exit_event(child_event, ctx, false);
+		perf_event_exit_event(child_event, ctx, exit ? task : NULL, false);
 
 	mutex_unlock(&ctx->mutex);