fsnotify: clear PARENT_WATCHED flags lazily

In some setups directories can have many (usually negative) dentries.
Hence __fsnotify_update_child_dentry_flags() function can take a
significant amount of time. Since the bulk of this function happens
under inode->i_lock this causes a significant contention on the lock
when we remove the watch from the directory as the
__fsnotify_update_child_dentry_flags() call from fsnotify_recalc_mask()
races with __fsnotify_update_child_dentry_flags() calls from
__fsnotify_parent() happening on children. This can lead upto softlockup
reports reported by users.

Fix the problem by calling fsnotify_update_children_dentry_flags() to
set PARENT_WATCHED flags only when parent starts watching children.

When parent stops watching children, clear false positive PARENT_WATCHED
flags lazily in __fsnotify_parent() for each accessed child.

Suggested-by: Jan Kara <jack@suse.cz>
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Stephen Brennan <stephen.s.brennan@oracle.com>
Signed-off-by: Jan Kara <jack@suse.cz>

3 files changed, 51 insertions, 14 deletions

diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index ff69ae24c4e8..272c8a1dab3c 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -117,17 +117,13 @@ void fsnotify_sb_free(struct super_block *sb)
  * parent cares.  Thus when an event happens on a child it can quickly tell
  * if there is a need to find a parent and send the event to the parent.
  */
-void __fsnotify_update_child_dentry_flags(struct inode *inode)
+void fsnotify_set_children_dentry_flags(struct inode *inode)
 {
 	struct dentry *alias;
-	int watched;
 
 	if (!S_ISDIR(inode->i_mode))
 		return;
 
-	/* determine if the children should tell inode about their events */
-	watched = fsnotify_inode_watches_children(inode);
-
 	spin_lock(&inode->i_lock);
 	/* run all of the dentries associated with this inode.  Since this is a
 	 * directory, there damn well better only be one item on this list */
@@ -143,10 +139,7 @@ void __fsnotify_update_child_dentry_flags(struct inode *inode)
 				continue;
 
 			spin_lock_nested(&child->d_lock, DENTRY_D_LOCK_NESTED);
-			if (watched)
-				child->d_flags |= DCACHE_FSNOTIFY_PARENT_WATCHED;
-			else
-				child->d_flags &= ~DCACHE_FSNOTIFY_PARENT_WATCHED;
+			child->d_flags |= DCACHE_FSNOTIFY_PARENT_WATCHED;
 			spin_unlock(&child->d_lock);
 		}
 		spin_unlock(&alias->d_lock);
@@ -154,6 +147,24 @@ void __fsnotify_update_child_dentry_flags(struct inode *inode)
 	spin_unlock(&inode->i_lock);
 }
 
+/*
+ * Lazily clear false positive PARENT_WATCHED flag for child whose parent had
+ * stopped watching children.
+ */
+static void fsnotify_clear_child_dentry_flag(struct inode *pinode,
+					     struct dentry *dentry)
+{
+	spin_lock(&dentry->d_lock);
+	/*
+	 * d_lock is a sufficient barrier to prevent observing a non-watched
+	 * parent state from before the fsnotify_set_children_dentry_flags()
+	 * or fsnotify_update_flags() call that had set PARENT_WATCHED.
+	 */
+	if (!fsnotify_inode_watches_children(pinode))
+		dentry->d_flags &= ~DCACHE_FSNOTIFY_PARENT_WATCHED;
+	spin_unlock(&dentry->d_lock);
+}
+
 /* Are inode/sb/mount interested in parent and name info with this event? */
 static bool fsnotify_event_needs_parent(struct inode *inode, __u32 mnt_mask,
 					__u32 mask)
@@ -228,7 +239,7 @@ int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data,
 	p_inode = parent->d_inode;
 	p_mask = fsnotify_inode_watches_children(p_inode);
 	if (unlikely(parent_watched && !p_mask))
-		__fsnotify_update_child_dentry_flags(p_inode);
+		fsnotify_clear_child_dentry_flag(p_inode, dentry);
 
 	/*
 	 * Include parent/name in notification either if some notification
diff --git a/fs/notify/fsnotify.h b/fs/notify/fsnotify.h
index 2d059f789ee3..663759ed6fbc 100644
--- a/fs/notify/fsnotify.h
+++ b/fs/notify/fsnotify.h
@@ -93,7 +93,7 @@ static inline void fsnotify_clear_marks_by_sb(struct super_block *sb)
  * update the dentry->d_flags of all of inode's children to indicate if inode cares
  * about events that happen to its children.
  */
-extern void __fsnotify_update_child_dentry_flags(struct inode *inode);
+extern void fsnotify_set_children_dentry_flags(struct inode *inode);
 
 extern struct kmem_cache *fsnotify_mark_connector_cachep;
 
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index c3eefa70633c..5e170e713088 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -250,6 +250,24 @@ static void *__fsnotify_recalc_mask(struct fsnotify_mark_connector *conn)
 	return fsnotify_update_iref(conn, want_iref);
 }
 
+static bool fsnotify_conn_watches_children(
+					struct fsnotify_mark_connector *conn)
+{
+	if (conn->type != FSNOTIFY_OBJ_TYPE_INODE)
+		return false;
+
+	return fsnotify_inode_watches_children(fsnotify_conn_inode(conn));
+}
+
+static void fsnotify_conn_set_children_dentry_flags(
+					struct fsnotify_mark_connector *conn)
+{
+	if (conn->type != FSNOTIFY_OBJ_TYPE_INODE)
+		return;
+
+	fsnotify_set_children_dentry_flags(fsnotify_conn_inode(conn));
+}
+
 /*
  * Calculate mask of events for a list of marks. The caller must make sure
  * connector and connector->obj cannot disappear under us.  Callers achieve
@@ -258,15 +276,23 @@ static void *__fsnotify_recalc_mask(struct fsnotify_mark_connector *conn)
  */
 void fsnotify_recalc_mask(struct fsnotify_mark_connector *conn)
 {
+	bool update_children;
+
 	if (!conn)
 		return;
 
 	spin_lock(&conn->lock);
+	update_children = !fsnotify_conn_watches_children(conn);
 	__fsnotify_recalc_mask(conn);
+	update_children &= fsnotify_conn_watches_children(conn);
 	spin_unlock(&conn->lock);
-	if (conn->type == FSNOTIFY_OBJ_TYPE_INODE)
-		__fsnotify_update_child_dentry_flags(
-					fsnotify_conn_inode(conn));
+	/*
+	 * Set children's PARENT_WATCHED flags only if parent started watching.
+	 * When parent stops watching, we clear false positive PARENT_WATCHED
+	 * flags lazily in __fsnotify_parent().
+	 */
+	if (update_children)
+		fsnotify_conn_set_children_dentry_flags(conn);
 }
 
 /* Free all connectors queued for freeing once SRCU period ends */