diff --git a/fs/direct-io.c b/fs/direct-io.c
index 0a073c7125a6..01d2d9ef609c 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -293,11 +293,12 @@ static ssize_t dio_complete(struct dio *dio, loff_t offset, ssize_t ret, bool is
 	if (dio->end_io && dio->result) {
 		dio->end_io(dio->iocb, offset, transferred,
 			    dio->map_bh.b_private, ret, is_async);
-	} else if (is_async) {
-		aio_complete(dio->iocb, ret, 0);
+	} else {
+		if (is_async)
+			aio_complete(dio->iocb, ret, 0);
+		inode_dio_done(dio->inode);
 	}
 
-	inode_dio_done(dio->inode);
 	return ret;
 }
 
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 1f35573a34e1..678cde834f19 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3573,6 +3573,7 @@ static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
 			    ssize_t size, void *private, int ret,
 			    bool is_async)
 {
+	struct inode *inode = iocb->ki_filp->f_path.dentry->d_inode;
         ext4_io_end_t *io_end = iocb->private;
 	struct workqueue_struct *wq;
 	unsigned long flags;
@@ -3594,6 +3595,7 @@ static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
 out:
 		if (is_async)
 			aio_complete(iocb, ret, 0);
+		inode_dio_done(inode);
 		return;
 	}
 
@@ -3614,6 +3616,9 @@ out:
 	/* queue the work to convert unwritten extents to written */
 	queue_work(wq, &io_end->work);
 	iocb->private = NULL;
+
+	/* XXX: probably should move into the real I/O completion handler */
+	inode_dio_done(inode);
 }
 
 static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate)
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 524d6167fb63..c1efe939c774 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -577,6 +577,7 @@ static void ocfs2_dio_end_io(struct kiocb *iocb,
 
 	if (is_async)
 		aio_complete(iocb, ret, 0);
+	inode_dio_done(inode);
 }
 
 /*
diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c
index 79ce38be15a1..b3b418f519f3 100644
--- a/fs/xfs/linux-2.6/xfs_aops.c
+++ b/fs/xfs/linux-2.6/xfs_aops.c
@@ -1339,6 +1339,9 @@ xfs_end_io_direct_write(
 	} else {
 		xfs_finish_ioend_sync(ioend);
 	}
+
+	/* XXX: probably should move into the real I/O completion handler */
+	inode_dio_done(ioend->io_inode);
 }
 
 STATIC ssize_t