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 <[e-mail]>
Signed-off-by: Ingo Molnar <[e-mail]>
Acked-by: Peter Zijlstra <[e-mail]>
Cc: Adrian Hunter <[e-mail]>
Cc: Alexander Shishkin <[e-mail]>
Cc: Arnaldo Carvalho de Melo <[e-mail]>
Cc: Ian Rogers <[e-mail]>
Cc: James Clark <[e-mail]>
Cc: Jiri Olsa <[e-mail]>
Cc: Mark Rutland <[e-mail]>
Cc: Namhyung Kim <[e-mail]>
Cc: [e-mail]
Link: https://patch.msgid.link/[e-mail]

kernel/events/core.c

···
 	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;
···
 	lockdep_assert_held(&parent_event->child_mutex);
 	 */
 
-	sync_child_event(event);
 	list_del_init(&event->child_list);
 }
 
···
 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);
 
 /*
···
 
 		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);
···
 	/*
 	 * 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:
···
 }
 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);
 	}
···
 
 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;
···
 		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)
···
 		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);