[PATCH] locks: reinstate locks_delete_block optimization

[Linus Torvalds]

There is measurable performance impact in some synthetic tests due to
commit 6d390e4b5d48 (locks: fix a potential use-after-free problem when
wakeup a waiter). Fix the race condition instead by clearing the
fl_blocker pointer after the wake_up, using explicit acquire/release
semantics.

With this change, we can just check for fl_blocker to clear as an
indicator that the block is already deleted, and eliminate the
list_empty check that was in the old optimization.

This does mean that we can no longer use the clearing of fl_blocker as
the wait condition, so switch the waiters over to checking whether the
fl_blocked_member list_head is empty.

Cc: yangerkun <yangerkun@xxxxxxxxxx>
Cc: NeilBrown <neilb@xxxxxxx>
Fixes: 6d390e4b5d48 (locks: fix a potential use-after-free problem when wakeup a waiter)
Signed-off-by: Jeff Layton <jlayton@xxxxxxxxxx>
---
 fs/cifs/file.c |  3 ++-
 fs/locks.c     | 38 ++++++++++++++++++++++++++++++++------
 2 files changed, 34 insertions(+), 7 deletions(-)

diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 3b942ecdd4be..8f9d849a0012 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -1169,7 +1169,8 @@ cifs_posix_lock_set(struct file *file, struct file_lock *flock)
 	rc = posix_lock_file(file, flock, NULL);
 	up_write(&cinode->lock_sem);
 	if (rc == FILE_LOCK_DEFERRED) {
-		rc = wait_event_interruptible(flock->fl_wait, !flock->fl_blocker);
+		rc = wait_event_interruptible(flock->fl_wait,
+					list_empty(&flock->fl_blocked_member));
 		if (!rc)
 			goto try_again;
 		locks_delete_block(flock);
diff --git a/fs/locks.c b/fs/locks.c
index 426b55d333d5..652a09ab02d7 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -725,7 +725,6 @@ static void __locks_delete_block(struct file_lock *waiter)
 {
 	locks_delete_global_blocked(waiter);
 	list_del_init(&waiter->fl_blocked_member);
-	waiter->fl_blocker = NULL;
 }
 
 static void __locks_wake_up_blocks(struct file_lock *blocker)
@@ -740,6 +739,12 @@ static void __locks_wake_up_blocks(struct file_lock *blocker)
 			waiter->fl_lmops->lm_notify(waiter);
 		else
 			wake_up(&waiter->fl_wait);
+
+		/*
+		 * Tell the world we're done with it - see comment at
+		 * top of locks_delete_block().
+		 */
+		smp_store_release(&waiter->fl_blocker, NULL);
 	}
 }
 
@@ -753,11 +758,27 @@ int locks_delete_block(struct file_lock *waiter)
 {
 	int status = -ENOENT;
 
+	/*
+	 * If fl_blocker is NULL, it won't be set again as this thread "owns"
+	 * the lock and is the only one that might try to claim the lock.
+	 * Because fl_blocker is explicitly set last during a delete, it's
+	 * safe to locklessly test to see if it's NULL and avoid doing
+	 * anything further if it is.
+	 */
+	if (!smp_load_acquire(&waiter->fl_blocker))
+		return status;
+
 	spin_lock(&blocked_lock_lock);
 	if (waiter->fl_blocker)
 		status = 0;
 	__locks_wake_up_blocks(waiter);
 	__locks_delete_block(waiter);
+
+	/*
+	 * Tell the world we're done with it - see comment at top
+	 * of this function
+	 */
+	smp_store_release(&waiter->fl_blocker, NULL);
 	spin_unlock(&blocked_lock_lock);
 	return status;
 }
@@ -1350,7 +1371,8 @@ static int posix_lock_inode_wait(struct inode *inode, struct file_lock *fl)
 		error = posix_lock_inode(inode, fl, NULL);
 		if (error != FILE_LOCK_DEFERRED)
 			break;
-		error = wait_event_interruptible(fl->fl_wait, !fl->fl_blocker);
+		error = wait_event_interruptible(fl->fl_wait,
+					list_empty(&fl->fl_blocked_member));
 		if (error)
 			break;
 	}
@@ -1435,7 +1457,8 @@ int locks_mandatory_area(struct inode *inode, struct file *filp, loff_t start,
 		error = posix_lock_inode(inode, &fl, NULL);
 		if (error != FILE_LOCK_DEFERRED)
 			break;
-		error = wait_event_interruptible(fl.fl_wait, !fl.fl_blocker);
+		error = wait_event_interruptible(fl.fl_wait,
+					list_empty(&fl.fl_blocked_member));
 		if (!error) {
 			/*
 			 * If we've been sleeping someone might have
@@ -1638,7 +1661,8 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 
 	locks_dispose_list(&dispose);
 	error = wait_event_interruptible_timeout(new_fl->fl_wait,
-						!new_fl->fl_blocker, break_time);
+					list_empty(&new_fl->fl_blocked_member),
+					break_time);
 
 	percpu_down_read(&file_rwsem);
 	spin_lock(&ctx->flc_lock);
@@ -2122,7 +2146,8 @@ static int flock_lock_inode_wait(struct inode *inode, struct file_lock *fl)
 		error = flock_lock_inode(inode, fl);
 		if (error != FILE_LOCK_DEFERRED)
 			break;
-		error = wait_event_interruptible(fl->fl_wait, !fl->fl_blocker);
+		error = wait_event_interruptible(fl->fl_wait,
+				list_empty(&fl->fl_blocked_member));
 		if (error)
 			break;
 	}
@@ -2399,7 +2424,8 @@ static int do_lock_file_wait(struct file *filp, unsigned int cmd,
 		error = vfs_lock_file(filp, cmd, fl, NULL);
 		if (error != FILE_LOCK_DEFERRED)
 			break;
-		error = wait_event_interruptible(fl->fl_wait, !fl->fl_blocker);
+		error = wait_event_interruptible(fl->fl_wait,
+					list_empty(&fl->fl_blocked_member));
 		if (error)
 			break;
 	}
-- 
2.24.1