[PATCH 2/6] fanotify: Fix list corruption in fanotify_get_response()

[Jan Kara <jack@suse.cz>]

fanotify_get_response() calls fsnotify_remove_event() when it finds that
group is being released from fanotify_release() (bypass_perm is set).
However the event it removes need not be only in the group's notification
queue but it can have already moved to access_list (userspace read the
event before closing the fanotify instance fd) which is protected by a
different lock. Thus when fsnotify_remove_event() races with
fanotify_release() operating on access_list, the list can get corrupted.

Fix the problem by moving all the logic removing permission events from
the lists to one place - fanotify_release().

Fixes: 5838d4442bd5971687b72221736222637e03140d
CC: stable@vger.kernel.org
Reported-and-tested-by: Miklos Szeredi <mszeredi@redhat.com>
Reviewed-by: Miklos Szeredi <mszeredi@redhat.com>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/notify/fanotify/fanotify.c      | 13 +------------
 fs/notify/fanotify/fanotify_user.c | 36 ++++++++++++++++++++++++------------
 fs/notify/notification.c           | 15 ---------------
 include/linux/fsnotify_backend.h   |  3 ---
 4 files changed, 25 insertions(+), 42 deletions(-)

diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index d2f97ecca6a5..e0e5f7c3c99f 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -67,18 +67,7 @@ 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, event->response ||
-				atomic_read(&group->fanotify_data.bypass_perm));
-
-	if (!event->response) {	/* bypass_perm set */
-		/*
-		 * Event was canceled because group is being destroyed. Remove
-		 * it from group's event list because we are responsible for
-		 * freeing the permission event.
-		 */
-		fsnotify_remove_event(group, &event->fae.fse);
-		return 0;
-	}
+	wait_event(group->fanotify_data.access_waitq, event->response);
 
 	/* userspace responded, convert to something usable */
 	switch (event->response) {
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 8e8e6bcd1d43..a64313868d3a 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -358,16 +358,20 @@ static int fanotify_release(struct inode *ignored, struct file *file)
 
 #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
 	struct fanotify_perm_event_info *event, *next;
+	struct fsnotify_event *fsn_event;
 
 	/*
-	 * There may be still new events arriving in the notification queue
-	 * but since userspace cannot use fanotify fd anymore, no event can
-	 * enter or leave access_list by now.
+	 * Stop new events from arriving in the notification queue. since
+	 * userspace cannot use fanotify fd anymore, no event can enter or
+	 * leave access_list by now either.
 	 */
-	spin_lock(&group->fanotify_data.access_lock);
-
-	atomic_inc(&group->fanotify_data.bypass_perm);
+	fsnotify_group_stop_queueing(group);
 
+	/*
+	 * Process all permission events on access_list and notification queue
+	 * and simulate reply from userspace.
+	 */
+	spin_lock(&group->fanotify_data.access_lock);
 	list_for_each_entry_safe(event, next, &group->fanotify_data.access_list,
 				 fae.fse.list) {
 		pr_debug("%s: found group=%p event=%p\n", __func__, group,
@@ -379,12 +383,21 @@ static int fanotify_release(struct inode *ignored, struct file *file)
 	spin_unlock(&group->fanotify_data.access_lock);
 
 	/*
-	 * Since bypass_perm is set, newly queued events will not wait for
-	 * access response. Wake up the already sleeping ones now.
-	 * synchronize_srcu() in fsnotify_destroy_group() will wait for all
-	 * processes sleeping in fanotify_handle_event() waiting for access
-	 * response and thus also for all permission events to be freed.
+	 * Destroy all non-permission events. For permission events just
+	 * dequeue them and set the response. They will be freed once the
+	 * response is consumed and fanotify_get_response() returns.
 	 */
+	mutex_lock(&group->notification_mutex);
+	while (!fsnotify_notify_queue_is_empty(group)) {
+		fsn_event = fsnotify_remove_first_event(group);
+		if (!(fsn_event->mask & FAN_ALL_PERM_EVENTS))
+			fsnotify_destroy_event(group, fsn_event);
+		else
+			FANOTIFY_PE(fsn_event)->response = FAN_ALLOW;
+	}
+	mutex_unlock(&group->notification_mutex);
+
+	/* Response for all permission events it set, wakeup waiters */
 	wake_up(&group->fanotify_data.access_waitq);
 #endif
 
@@ -755,7 +768,6 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
 	spin_lock_init(&group->fanotify_data.access_lock);
 	init_waitqueue_head(&group->fanotify_data.access_waitq);
 	INIT_LIST_HEAD(&group->fanotify_data.access_list);
-	atomic_set(&group->fanotify_data.bypass_perm, 0);
 #endif
 	switch (flags & FAN_ALL_CLASS_BITS) {
 	case FAN_CLASS_NOTIF:
diff --git a/fs/notify/notification.c b/fs/notify/notification.c
index 3d76e65ff84f..e455e83ceeeb 100644
--- a/fs/notify/notification.c
+++ b/fs/notify/notification.c
@@ -132,21 +132,6 @@ queue:
 }
 
 /*
- * Remove @event from group's notification queue. It is the responsibility of
- * the caller to destroy the event.
- */
-void fsnotify_remove_event(struct fsnotify_group *group,
-			   struct fsnotify_event *event)
-{
-	mutex_lock(&group->notification_mutex);
-	if (!list_empty(&event->list)) {
-		list_del_init(&event->list);
-		group->q_len--;
-	}
-	mutex_unlock(&group->notification_mutex);
-}
-
-/*
  * Remove and return the first event from the notification list.  It is the
  * responsibility of the caller to destroy the obtained event
  */
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 40a9e99de703..7268ed076be8 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -180,7 +180,6 @@ struct fsnotify_group {
 			spinlock_t access_lock;
 			struct list_head access_list;
 			wait_queue_head_t access_waitq;
-			atomic_t bypass_perm;
 #endif /* CONFIG_FANOTIFY_ACCESS_PERMISSIONS */
 			int f_flags;
 			unsigned int max_marks;
@@ -307,8 +306,6 @@ extern int fsnotify_add_event(struct fsnotify_group *group,
 			      struct fsnotify_event *event,
 			      int (*merge)(struct list_head *,
 					   struct fsnotify_event *));
-/* Remove passed event from groups notification queue */
-extern void fsnotify_remove_event(struct fsnotify_group *group, struct fsnotify_event *event);
 /* true if the group notification queue is empty */
 extern bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group);
 /* return, but do not dequeue the first event on the notification queue */
-- 
2.6.6