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

diff --git a/kernel/events/core.c b/kernel/events/core.c
index ece716879cbc24922891d4f43d0494ee82394340..dad0d3d2e85f7d1446b2988c34e31771f6faded0 100644 (file)
--- 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);