diff --git a/fs/block_dev.c b/fs/block_dev.c
index dd76930..55dcb78 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -406,17 +406,23 @@
  
 int blkdev_fsync(struct file *filp, struct dentry *dentry, int datasync)
 {
-	struct block_device *bdev = I_BDEV(filp->f_mapping->host);
+	struct inode *bd_inode = filp->f_mapping->host;
+	struct block_device *bdev = I_BDEV(bd_inode);
 	int error;
 
-	error = sync_blockdev(bdev);
-	if (error)
-		return error;
-	
-	error = blkdev_issue_flush(bdev, GFP_KERNEL, NULL,
-				(BLKDEV_IFL_WAIT));
+	/*
+	 * There is no need to serialise calls to blkdev_issue_flush with
+	 * i_mutex and doing so causes performance issues with concurrent
+	 * O_SYNC writers to a block device.
+	 */
+	mutex_unlock(&bd_inode->i_mutex);
+
+	error = blkdev_issue_flush(bdev, GFP_KERNEL, NULL, BLKDEV_IFL_WAIT);
 	if (error == -EOPNOTSUPP)
 		error = 0;
+
+	mutex_lock(&bd_inode->i_mutex);
+
 	return error;
 }
 EXPORT_SYMBOL(blkdev_fsync);