commit 8882135bcd332f294df5455747ea43ba9e6f77ad
author Peter Zijlstra <a.p.zijlstra@chello.nl> Tue Nov 09 19:01:43 2010 +0100
committer Ingo Molnar <mingo@elte.hu> Thu Nov 18 13:18:46 2010 +0100
tree 758f26d26750fd5007e885cc28125f7c1fa24ca6
parent fcf48a725a176ba12aa7be64c50190deaa2f86df

perf: Fix owner-list vs exit

Oleg noticed that a perf-fd keeping a reference on the creating task
leads to a few funny side effects.

There's two different aspects to this:

  - kernel based perf-events, these should not take out
    a reference on the creating task and appear on the task's
    event list since they're not bound to fds nor visible
    to userspace.

  - fork() and pthread_create(), these can lead to the creating
    task dying (and thus the task's event-list becomming useless)
    but keeping the list and ref alive until the event is closed.

Combined they lead to malfunction of the ptrace hw_tracepoints.

Cure this by not considering kernel based perf_events for the
owner-list and destroying the owner-list when the owner dies.

Reported-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Oleg Nesterov <oleg@redhat.com>
LKML-Reference: <1289576883.2084.286.camel@laptop>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

kernel/perf_event.c

diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index f818d9d..671f6c8 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -2235,11 +2235,6 @@
 	raw_spin_unlock_irq(&ctx->lock);
 	mutex_unlock(&ctx->mutex);
 
-	mutex_lock(&event->owner->perf_event_mutex);
-	list_del_init(&event->owner_entry);
-	mutex_unlock(&event->owner->perf_event_mutex);
-	put_task_struct(event->owner);
-
 	free_event(event);
 
 	return 0;
@@ -2252,9 +2247,43 @@
 static int perf_release(struct inode *inode, struct file *file)
 {
 	struct perf_event *event = file->private_data;
+	struct task_struct *owner;
 
 	file->private_data = NULL;
 
+	rcu_read_lock();
+	owner = ACCESS_ONCE(event->owner);
+	/*
+	 * Matches the smp_wmb() in perf_event_exit_task(). If we observe
+	 * !owner it means the list deletion is complete and we can indeed
+	 * free this event, otherwise we need to serialize on
+	 * owner->perf_event_mutex.
+	 */
+	smp_read_barrier_depends();
+	if (owner) {
+		/*
+		 * Since delayed_put_task_struct() also drops the last
+		 * task reference we can safely take a new reference
+		 * while holding the rcu_read_lock().
+		 */
+		get_task_struct(owner);
+	}
+	rcu_read_unlock();
+
+	if (owner) {
+		mutex_lock(&owner->perf_event_mutex);
+		/*
+		 * We have to re-check the event->owner field, if it is cleared
+		 * we raced with perf_event_exit_task(), acquiring the mutex
+		 * ensured they're done, and we can proceed with freeing the
+		 * event.
+		 */
+		if (event->owner)
+			list_del_init(&event->owner_entry);
+		mutex_unlock(&owner->perf_event_mutex);
+		put_task_struct(owner);
+	}
+
 	return perf_event_release_kernel(event);
 }
 
@@ -5678,7 +5707,7 @@
 	mutex_unlock(&ctx->mutex);
 
 	event->owner = current;
-	get_task_struct(current);
+
 	mutex_lock(&current->perf_event_mutex);
 	list_add_tail(&event->owner_entry, &current->perf_event_list);
 	mutex_unlock(&current->perf_event_mutex);
@@ -5746,12 +5775,6 @@
 	++ctx->generation;
 	mutex_unlock(&ctx->mutex);
 
-	event->owner = current;
-	get_task_struct(current);
-	mutex_lock(&current->perf_event_mutex);
-	list_add_tail(&event->owner_entry, &current->perf_event_list);
-	mutex_unlock(&current->perf_event_mutex);
-
 	return event;
 
 err_free:
@@ -5902,8 +5925,24 @@
  */
 void perf_event_exit_task(struct task_struct *child)
 {
+	struct perf_event *event, *tmp;
 	int ctxn;
 
+	mutex_lock(&child->perf_event_mutex);
+	list_for_each_entry_safe(event, tmp, &child->perf_event_list,
+				 owner_entry) {
+		list_del_init(&event->owner_entry);
+
+		/*
+		 * Ensure the list deletion is visible before we clear
+		 * the owner, closes a race against perf_release() where
+		 * we need to serialize on the owner->perf_event_mutex.
+		 */
+		smp_wmb();
+		event->owner = NULL;
+	}
+	mutex_unlock(&child->perf_event_mutex);
+
 	for_each_task_context_nr(ctxn)
 		perf_event_exit_task_context(child, ctxn);
 }