diff --git a/fs/direct-io.c b/fs/direct-io.c
index 354cbdb..0a073c7 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -297,8 +297,7 @@
 		aio_complete(dio->iocb, ret, 0);
 	}
 
-	if (dio->flags & DIO_LOCKING)
-		inode_dio_done(dio->inode);
+	inode_dio_done(dio->inode);
 	return ret;
 }
 
@@ -1185,14 +1184,16 @@
  *    For writes this function is called under i_mutex and returns with
  *    i_mutex held, for reads, i_mutex is not held on entry, but it is
  *    taken and dropped again before returning.
- *    The i_dio_count counter keeps track of the number of outstanding
- *    direct I/O requests, and truncate waits for it to reach zero.
- *    New references to i_dio_count must only be grabbed with i_mutex
- *    held.
- *
  *  - if the flags value does NOT contain DIO_LOCKING we don't use any
  *    internal locking but rather rely on the filesystem to synchronize
  *    direct I/O reads/writes versus each other and truncate.
+ *
+ * To help with locking against truncate we incremented the i_dio_count
+ * counter before starting direct I/O, and decrement it once we are done.
+ * Truncate can wait for it to reach zero to provide exclusion.  It is
+ * expected that filesystem provide exclusion between new direct I/O
+ * and truncates.  For DIO_LOCKING filesystems this is done by i_mutex,
+ * but other filesystems need to take care of this on their own.
  */
 ssize_t
 __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
@@ -1270,14 +1271,14 @@
 				goto out;
 			}
 		}
-
-		/*
-		 * Will be decremented at I/O completion time.
-		 */
-		atomic_inc(&inode->i_dio_count);
 	}
 
 	/*
+	 * Will be decremented at I/O completion time.
+	 */
+	atomic_inc(&inode->i_dio_count);
+
+	/*
 	 * For file extending writes updating i_size before data
 	 * writeouts complete can expose uninitialized blocks. So
 	 * even for AIO, we need to wait for i/o to complete before