fanotify: Use interruptible wait when waiting for permission events

When waiting for response to fanotify permission events, we currently
use uninterruptible waits. That makes code simple however it can cause
lots of processes to end up in uninterruptible sleep with hard reboot
being the only alternative in case fanotify listener process stops
responding (e.g. due to a bug in its implementation). Uninterruptible
sleep also makes system hibernation fail if the listener gets frozen
before the process generating fanotify permission event.

Fix these problems by using interruptible sleep for waiting for response
to fanotify event. This is slightly tricky though - we have to
detect when the event got already reported to userspace as in that
case we must not free the event. Instead we push the responsibility for
freeing the event to the process that will write response to the
event.

Reported-by: Orion Poplawski <orion@nwra.com>
Reported-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>

fs/notify/fanotify/fanotify.c

@@ -77,6 +77,13 @@ static int fanotify_merge(struct list_head *list, struct fsnotify_event *event)
 	return 0;
 }
 
+/*
+ * Wait for response to permission event. The function also takes care of
+ * freeing the permission event (or offloads that in case the wait is canceled
+ * by a signal). The function returns 0 in case access got allowed by userspace,
+ * -EPERM in case userspace disallowed the access, and -ERESTARTSYS in case
+ * the wait got interrupted by a signal.
+ */
 static int fanotify_get_response(struct fsnotify_group *group,
 				 struct fanotify_perm_event *event,
 				 struct fsnotify_iter_info *iter_info)
@@ -85,8 +92,29 @@ static int fanotify_get_response(struct fsnotify_group *group,
 
 	pr_debug("%s: group=%p event=%p\n", __func__, group, event);
 
-	wait_event(group->fanotify_data.access_waitq,
+	ret = wait_event_interruptible(group->fanotify_data.access_waitq,
 				       event->state == FAN_EVENT_ANSWERED);
+	/* Signal pending? */
+	if (ret < 0) {
+		spin_lock(&group->notification_lock);
+		/* Event reported to userspace and no answer yet? */
+		if (event->state == FAN_EVENT_REPORTED) {
+			/* Event will get freed once userspace answers to it */
+			event->state = FAN_EVENT_CANCELED;
+			spin_unlock(&group->notification_lock);
+			return ret;
+		}
+		/* Event not yet reported? Just remove it. */
+		if (event->state == FAN_EVENT_INIT)
+			fsnotify_remove_queued_event(group, &event->fae.fse);
+		/*
+		 * Event may be also answered in case signal delivery raced
+		 * with wakeup. In that case we have nothing to do besides
+		 * freeing the event and reporting error.
+		 */
+		spin_unlock(&group->notification_lock);
+		goto out;
+	}
 
 	/* userspace responded, convert to something usable */
 	switch (event->response & ~FAN_AUDIT) {
@@ -104,6 +132,8 @@ static int fanotify_get_response(struct fsnotify_group *group,
 
 	pr_debug("%s: group=%p event=%p about to return ret=%d\n", __func__,
 		 group, event, ret);
+out:
+	fsnotify_destroy_event(group, &event->fae.fse);
 
 	return ret;
 }
@@ -406,7 +436,6 @@ static int fanotify_handle_event(struct fsnotify_group *group,
 	} else if (fanotify_is_perm_event(mask)) {
 		ret = fanotify_get_response(group, FANOTIFY_PE(fsn_event),
 					    iter_info);
-		fsnotify_destroy_event(group, fsn_event);
 	}
 finish:
 	if (fanotify_is_perm_event(mask))

fs/notify/fanotify/fanotify.h

@@ -12,7 +12,8 @@ extern struct kmem_cache *fanotify_perm_event_cachep;
 enum {
 	FAN_EVENT_INIT,
 	FAN_EVENT_REPORTED,
-	FAN_EVENT_ANSWERED
+	FAN_EVENT_ANSWERED,
+	FAN_EVENT_CANCELED,
 };
 
 /*

fs/notify/fanotify/fanotify_user.c

@@ -147,10 +147,17 @@ static void finish_permission_event(struct fsnotify_group *group,
 				    unsigned int response)
 				    __releases(&group->notification_lock)
 {
+	bool destroy = false;
+
 	assert_spin_locked(&group->notification_lock);
 	event->response = response;
+	if (event->state == FAN_EVENT_CANCELED)
+		destroy = true;
+	else
 		event->state = FAN_EVENT_ANSWERED;
 	spin_unlock(&group->notification_lock);
+	if (destroy)
+		fsnotify_destroy_event(group, &event->fae.fse);
 }
 
 static int process_access_response(struct fsnotify_group *group,