kernfs: replace kernfs_node->u.completion with kernfs_root->deactivate_waitq

kernfs_node->u.completion is used to notify deactivation completion
from kernfs_put_active() to kernfs_deactivate().  We now allow
multiple racing removals of the same node and the current removal
scheme is no longer correct - kernfs_remove() invocation may return
before the node is properly deactivated if it races against another
removal.  The removal path will be restructured to address the issue.

To help such restructure which requires supporting multiple waiters,
this patch replaces kernfs_node->u.completion with
kernfs_root->deactivate_waitq.  This makes deactivation event
notifications share a per-root waitqueue_head; however, the wait path
is quite cold and this will also allow shaving one pointer off
kernfs_node.

v2: Refreshed on top of ("kernfs: make kernfs_deactivate() honor
    KERNFS_LOCKDEP flag").

Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

1 files changed, 13 insertions, 18 deletions

diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index bd6e18be6e1..2193d30156e 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -8,6 +8,7 @@
  * This file is released under the GPLv2.
  */
 
+#include <linux/sched.h>
 #include <linux/fs.h>
 #include <linux/namei.h>
 #include <linux/idr.h>
@@ -151,6 +152,7 @@ struct kernfs_node *kernfs_get_active(struct kernfs_node *kn)
  */
 void kernfs_put_active(struct kernfs_node *kn)
 {
+	struct kernfs_root *root = kernfs_root(kn);
 	int v;
 
 	if (unlikely(!kn))
@@ -162,11 +164,7 @@ void kernfs_put_active(struct kernfs_node *kn)
 	if (likely(v != KN_DEACTIVATED_BIAS))
 		return;
 
-	/*
-	 * atomic_dec_return() is a mb(), we'll always see the updated
-	 * kn->u.completion.
-	 */
-	complete(kn->u.completion);
+	wake_up_all(&root->deactivate_waitq);
 }
 
 /**
@@ -177,28 +175,24 @@ void kernfs_put_active(struct kernfs_node *kn)
  */
 static void kernfs_deactivate(struct kernfs_node *kn)
 {
-	DECLARE_COMPLETION_ONSTACK(wait);
-	int v;
+	struct kernfs_root *root = kernfs_root(kn);
 
 	BUG_ON(!(kn->flags & KERNFS_REMOVED));
 
 	if (!(kernfs_type(kn) & KERNFS_ACTIVE_REF))
 		return;
 
-	kn->u.completion = (void *)&wait;
-
 	if (kn->flags & KERNFS_LOCKDEP)
 		rwsem_acquire(&kn->dep_map, 0, 0, _RET_IP_);
-	/* atomic_add_return() is a mb(), put_active() will always see
-	 * the updated kn->u.completion.
-	 */
-	v = atomic_add_return(KN_DEACTIVATED_BIAS, &kn->active);
 
-	if (v != KN_DEACTIVATED_BIAS) {
-		if (kn->flags & KERNFS_LOCKDEP)
-			lock_contended(&kn->dep_map, _RET_IP_);
-		wait_for_completion(&wait);
-	}
+	atomic_add(KN_DEACTIVATED_BIAS, &kn->active);
+
+	if ((kn->flags & KERNFS_LOCKDEP) &&
+	    atomic_read(&kn->active) != KN_DEACTIVATED_BIAS)
+		lock_contended(&kn->dep_map, _RET_IP_);
+
+	wait_event(root->deactivate_waitq,
+		   atomic_read(&kn->active) == KN_DEACTIVATED_BIAS);
 
 	if (kn->flags & KERNFS_LOCKDEP) {
 		lock_acquired(&kn->dep_map, _RET_IP_);
@@ -630,6 +624,7 @@ struct kernfs_root *kernfs_create_root(struct kernfs_dir_ops *kdops, void *priv)
 
 	root->dir_ops = kdops;
 	root->kn = kn;
+	init_waitqueue_head(&root->deactivate_waitq);
 
 	return root;
 }