fsnotify: fix oops in fsnotify_clear_marks_by_group_flags()

fsnotify_clear_marks_by_group_flags() can race with
fsnotify_destroy_marks() so when fsnotify_destroy_mark_locked() drops
mark_mutex, a mark from the list iterated by
fsnotify_clear_marks_by_group_flags() can be freed and we dereference free
memory in the loop there.

Fix the problem by keeping mark_mutex held in
fsnotify_destroy_mark_locked().  The reason why we drop that mutex is that
we need to call a ->freeing_mark() callback which may acquire mark_mutex
again.  To avoid this and similar lock inversion issues, we move the call
to ->freeing_mark() callback to the kthread destroying the mark.

Signed-off-by: Jan Kara <jack@suse.cz>
Reported-by: Ashish Sangwan <a.sangwan@samsung.com>
Suggested-by: Lino Sanfilippo <LinoSanfilippo@gmx.de>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 14 insertions, 20 deletions

diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index 92e48c7..3e594ce4 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -152,31 +152,15 @@ void fsnotify_destroy_mark_locked(struct fsnotify_mark *mark,
 		BUG();
 
 	list_del_init(&mark->g_list);
-
 	spin_unlock(&mark->lock);
 
 	if (inode && (mark->flags & FSNOTIFY_MARK_FLAG_OBJECT_PINNED))
 		iput(inode);
-	/* release lock temporarily */
-	mutex_unlock(&group->mark_mutex);
 
 	spin_lock(&destroy_lock);
 	list_add(&mark->g_list, &destroy_list);
 	spin_unlock(&destroy_lock);
 	wake_up(&destroy_waitq);
-	/*
-	 * We don't necessarily have a ref on mark from caller so the above destroy
-	 * may have actually freed it, unless this group provides a 'freeing_mark'
-	 * function which must be holding a reference.
-	 */
-
-	/*
-	 * Some groups like to know that marks are being freed.  This is a
-	 * callback to the group function to let it know that this mark
-	 * is being freed.
-	 */
-	if (group->ops->freeing_mark)
-		group->ops->freeing_mark(mark, group);
 
 	/*
 	 * __fsnotify_update_child_dentry_flags(inode);
@@ -191,8 +175,6 @@ void fsnotify_destroy_mark_locked(struct fsnotify_mark *mark,
 	 */
 
 	atomic_dec(&group->num_marks);
-
-	mutex_lock_nested(&group->mark_mutex, SINGLE_DEPTH_NESTING);
 }
 
 void fsnotify_destroy_mark(struct fsnotify_mark *mark,
@@ -205,7 +187,10 @@ void fsnotify_destroy_mark(struct fsnotify_mark *mark,
 
 /*
  * Destroy all marks in the given list. The marks must be already detached from
- * the original inode / vfsmount.
+ * the original inode / vfsmount. Note that we can race with
+ * fsnotify_clear_marks_by_group_flags(). However we hold a reference to each
+ * mark so they won't get freed from under us and nobody else touches our
+ * free_list list_head.
  */
 void fsnotify_destroy_marks(struct list_head *to_free)
 {
@@ -406,7 +391,7 @@ struct fsnotify_mark *fsnotify_find_mark(struct hlist_head *head,
 }
 
 /*
- * clear any marks in a group in which mark->flags & flags is true
+ * Clear any marks in a group in which mark->flags & flags is true.
  */
 void fsnotify_clear_marks_by_group_flags(struct fsnotify_group *group,
 					 unsigned int flags)
@@ -460,6 +445,7 @@ static int fsnotify_mark_destroy(void *ignored)
 {
 	struct fsnotify_mark *mark, *next;
 	struct list_head private_destroy_list;
+	struct fsnotify_group *group;
 
 	for (;;) {
 		spin_lock(&destroy_lock);
@@ -471,6 +457,14 @@ static int fsnotify_mark_destroy(void *ignored)
 
 		list_for_each_entry_safe(mark, next, &private_destroy_list, g_list) {
 			list_del_init(&mark->g_list);
+			group = mark->group;
+			/*
+			 * Some groups like to know that marks are being freed.
+			 * This is a callback to the group function to let it
+			 * know that this mark is being freed.
+			 */
+			if (group && group->ops->freeing_mark)
+				group->ops->freeing_mark(mark, group);
 			fsnotify_put_mark(mark);
 		}