[PATCH v2 3/3] fsnotify: allow sleepable child flag update

[Stephen Brennan]

With very large d_subdirs lists, iteration can take a long time. Since
iteration needs to hold parent->d_lock, this can trigger soft lockups.
It would be best to make this iteration sleepable. Since we have the
inode locked exclusive, we can drop the parent->d_lock and sleep,
holding a reference to a child dentry, and continue iteration once we
wake.

Signed-off-by: Stephen Brennan <stephen.s.brennan@xxxxxxxxxx>
---
 fs/notify/fsnotify.c | 39 +++++++++++++++++++++++++++++++++++----
 1 file changed, 35 insertions(+), 4 deletions(-)

diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index f83eca4fb841..061e626127ca 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -102,10 +102,12 @@ void fsnotify_sb_delete(struct super_block *sb)
  * on a child we run all of our children and set a dentry flag saying that the
  * 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.
+ *
+ * Context: inode locked exclusive
  */
 bool __fsnotify_update_children_dentry_flags(struct inode *inode)
 {
-	struct dentry *alias, *child;
+	struct dentry *child, *alias, *last_ref = NULL;
 	int watched;
 
 	if (!S_ISDIR(inode->i_mode))
@@ -119,11 +121,38 @@ bool __fsnotify_update_children_dentry_flags(struct inode *inode)
 	/* Since this is a directory, there damn well better only be one child */
 	alias = d_find_any_alias(inode);
 
-	/* run all of the children of the original inode and fix their
-	 * d_flags to indicate parental interest (their parent is the
-	 * original inode) */
+	/*
+	 * These lists can get very long, so we may need to sleep during
+	 * iteration. Normally this would be impossible without a cursor,
+	 * but since we have the inode locked exclusive, we're guaranteed
+	 * that the directory won't be modified, so whichever dentry we
+	 * pick to sleep on won't get moved. So, start a manual iteration
+	 * over d_subdirs which will allow us to sleep.
+	 */
 	spin_lock(&alias->d_lock);
+retry:
 	list_for_each_entry(child, &alias->d_subdirs, d_child) {
+		if (need_resched()) {
+			/*
+			 * We need to hold a reference while we sleep. But when
+			 * we wake, dput() could free the dentry, invalidating
+			 * the list pointers. We can't look at the list pointers
+			 * until we re-lock the parent, and we can't dput() once
+			 * we have the parent locked. So the solution is to hold
+			 * onto our reference and free it the *next* time we drop
+			 * alias->d_lock: either at the end of the function, or
+			 * at the time of the next sleep.
+			 */
+			dget(child);
+			spin_unlock(&alias->d_lock);
+			dput(last_ref);
+			last_ref = child;
+			cond_resched();
+			spin_lock(&alias->d_lock);
+			if (child->d_parent != alias)
+				goto retry;
+		}
+
 		if (!child->d_inode)
 			continue;
 
@@ -135,6 +164,8 @@ bool __fsnotify_update_children_dentry_flags(struct inode *inode)
 		spin_unlock(&child->d_lock);
 	}
 	spin_unlock(&alias->d_lock);
+	if (last_ref)
+		dput(last_ref);
 	return watched;
 }
 
-- 
2.34.1