diff --git a/fs/direct-io.c b/fs/direct-io.c
index 354cbdbc14bd..0a073c7125a6 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -297,8 +297,7 @@ static ssize_t dio_complete(struct dio *dio, loff_t offset, ssize_t ret, bool is
 		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 @@ direct_io_worker(int rw, struct kiocb *iocb, struct inode *inode,
  *    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,
@@ -1270,13 +1271,13 @@ __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
 				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
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index de1d3953599d..524d6167fb63 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -567,10 +567,8 @@ static void ocfs2_dio_end_io(struct kiocb *iocb,
 	/* this io's submitter should not have unlocked this before we could */
 	BUG_ON(!ocfs2_iocb_is_rw_locked(iocb));
 
-	if (ocfs2_iocb_is_sem_locked(iocb)) {
-		inode_dio_done(inode);
+	if (ocfs2_iocb_is_sem_locked(iocb))
 		ocfs2_iocb_clear_sem_locked(iocb);
-	}
 
 	ocfs2_iocb_clear_rw_locked(iocb);
 
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 736283ca4a4c..22d604601957 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -2240,7 +2240,6 @@ static ssize_t ocfs2_file_aio_write(struct kiocb *iocb,
 relock:
 	/* to match setattr's i_mutex -> rw_lock ordering */
 	if (direct_io) {
-		atomic_inc(&inode->i_dio_count);
 		have_alloc_sem = 1;
 		/* communicate with ocfs2_dio_end_io */
 		ocfs2_iocb_set_sem_locked(iocb);
@@ -2292,7 +2291,6 @@ relock:
 	 */
 	if (direct_io && !can_do_direct) {
 		ocfs2_rw_unlock(inode, rw_level);
-		inode_dio_done(inode);
 
 		have_alloc_sem = 0;
 		rw_level = -1;
@@ -2379,10 +2377,8 @@ out:
 		ocfs2_rw_unlock(inode, rw_level);
 
 out_sems:
-	if (have_alloc_sem) {
-		inode_dio_done(inode);
+	if (have_alloc_sem)
 		ocfs2_iocb_clear_sem_locked(iocb);
-	}
 
 	mutex_unlock(&inode->i_mutex);
 
@@ -2533,7 +2529,6 @@ static ssize_t ocfs2_file_aio_read(struct kiocb *iocb,
 	 */
 	if (filp->f_flags & O_DIRECT) {
 		have_alloc_sem = 1;
-		atomic_inc(&inode->i_dio_count);
 		ocfs2_iocb_set_sem_locked(iocb);
 
 		ret = ocfs2_rw_lock(inode, 0);
@@ -2575,10 +2570,9 @@ static ssize_t ocfs2_file_aio_read(struct kiocb *iocb,
 	}
 
 bail:
-	if (have_alloc_sem) {
-		inode_dio_done(inode);
+	if (have_alloc_sem)
 		ocfs2_iocb_clear_sem_locked(iocb);
-	}
+
 	if (rw_level != -1)
 		ocfs2_rw_unlock(inode, rw_level);