diff --git a/fs/block_dev.c b/fs/block_dev.c
index 79b4fa3..c7e4163 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -152,7 +152,8 @@
 	struct inode *inode = file->f_mapping->host;
 
 	return __blockdev_direct_IO(iocb, inode, I_BDEV(inode), iter, offset,
-				    blkdev_get_block, NULL, NULL, 0);
+				    blkdev_get_block, NULL, NULL,
+				    DIO_SKIP_DIO_COUNT);
 }
 
 int __sync_blockdev(struct block_device *bdev, int wait)
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 8115763..9b774a0 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -8129,7 +8129,7 @@
 	if (check_direct_IO(BTRFS_I(inode)->root, iocb, iter, offset))
 		return 0;
 
-	atomic_inc(&inode->i_dio_count);
+	inode_dio_begin(inode);
 	smp_mb__after_atomic();
 
 	/*
@@ -8169,7 +8169,7 @@
 		current->journal_info = &outstanding_extents;
 	} else if (test_bit(BTRFS_INODE_READDIO_NEED_LOCK,
 				     &BTRFS_I(inode)->runtime_flags)) {
-		inode_dio_done(inode);
+		inode_dio_end(inode);
 		flags = DIO_LOCKING | DIO_SKIP_HOLES;
 		wakeup = false;
 	}
@@ -8188,7 +8188,7 @@
 	}
 out:
 	if (wakeup)
-		inode_dio_done(inode);
+		inode_dio_end(inode);
 	if (relock)
 		mutex_lock(&inode->i_mutex);
 
diff --git a/fs/dax.c b/fs/dax.c
index a278469..cdde2b35 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -209,7 +209,7 @@
 	}
 
 	/* Protects against truncate */
-	atomic_inc(&inode->i_dio_count);
+	inode_dio_begin(inode);
 
 	retval = dax_io(inode, iter, pos, end, get_block, &bh);
 
@@ -219,7 +219,7 @@
 	if ((retval > 0) && end_io)
 		end_io(iocb, pos, retval, bh.b_private);
 
-	inode_dio_done(inode);
+	inode_dio_end(inode);
  out:
 	return retval;
 }
diff --git a/fs/direct-io.c b/fs/direct-io.c
index c3b560b..745d234 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -253,7 +253,9 @@
 	if (dio->end_io && dio->result)
 		dio->end_io(dio->iocb, offset, transferred, dio->private);
 
-	inode_dio_done(dio->inode);
+	if (!(dio->flags & DIO_SKIP_DIO_COUNT))
+		inode_dio_end(dio->inode);
+
 	if (is_async) {
 		if (dio->rw & WRITE) {
 			int err;
@@ -1195,7 +1197,8 @@
 	/*
 	 * Will be decremented at I/O completion time.
 	 */
-	atomic_inc(&inode->i_dio_count);
+	if (!(dio->flags & DIO_SKIP_DIO_COUNT))
+		inode_dio_begin(inode);
 
 	retval = 0;
 	sdio.blkbits = blkbits;
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index 3580629e..9588240 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -682,11 +682,11 @@
 		 * via ext4_inode_block_unlocked_dio(). Check inode's state
 		 * while holding extra i_dio_count ref.
 		 */
-		atomic_inc(&inode->i_dio_count);
+		inode_dio_begin(inode);
 		smp_mb();
 		if (unlikely(ext4_test_inode_state(inode,
 						    EXT4_STATE_DIOREAD_LOCK))) {
-			inode_dio_done(inode);
+			inode_dio_end(inode);
 			goto locked;
 		}
 		if (IS_DAX(inode))
@@ -697,7 +697,7 @@
 						   inode->i_sb->s_bdev, iter,
 						   offset, ext4_get_block, NULL,
 						   NULL, 0);
-		inode_dio_done(inode);
+		inode_dio_end(inode);
 	} else {
 locked:
 		if (IS_DAX(inode))
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 063052e..bccec41 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2977,7 +2977,7 @@
 	 * overwrite DIO as i_dio_count needs to be incremented under i_mutex.
 	 */
 	if (iov_iter_rw(iter) == WRITE)
-		atomic_inc(&inode->i_dio_count);
+		inode_dio_begin(inode);
 
 	/* If we do a overwrite dio, i_mutex locking can be released */
 	overwrite = *((int *)iocb->private);
@@ -3079,7 +3079,7 @@
 
 retake_lock:
 	if (iov_iter_rw(iter) == WRITE)
-		inode_dio_done(inode);
+		inode_dio_end(inode);
 	/* take i_mutex locking again if we do a ovewrite dio */
 	if (overwrite) {
 		up_read(&EXT4_I(inode)->i_data_sem);
diff --git a/fs/inode.c b/fs/inode.c
index 94886f9..ea37cd1 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -1946,20 +1946,6 @@
 EXPORT_SYMBOL(inode_dio_wait);
 
 /*
- * inode_dio_done - signal finish of a direct I/O requests
- * @inode: inode the direct I/O happens on
- *
- * This is called once we've finished processing a direct I/O request,
- * and is used to wake up callers waiting for direct I/O to be quiesced.
- */
-void inode_dio_done(struct inode *inode)
-{
-	if (atomic_dec_and_test(&inode->i_dio_count))
-		wake_up_bit(&inode->i_state, __I_DIO_WAKEUP);
-}
-EXPORT_SYMBOL(inode_dio_done);
-
-/*
  * inode_set_flags - atomically set some inode flags
  *
  * Note: the caller should be holding i_mutex, or else be sure that
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index ed0e603..b2cbc3a 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -386,7 +386,7 @@
 	if (write)
 		nfs_zap_mapping(inode, inode->i_mapping);
 
-	inode_dio_done(inode);
+	inode_dio_end(inode);
 
 	if (dreq->iocb) {
 		long res = (long) dreq->error;
@@ -486,7 +486,7 @@
 			     &nfs_direct_read_completion_ops);
 	get_dreq(dreq);
 	desc.pg_dreq = dreq;
-	atomic_inc(&inode->i_dio_count);
+	inode_dio_begin(inode);
 
 	while (iov_iter_count(iter)) {
 		struct page **pagevec;
@@ -538,7 +538,7 @@
 	 * generic layer handle the completion.
 	 */
 	if (requested_bytes == 0) {
-		inode_dio_done(inode);
+		inode_dio_end(inode);
 		nfs_direct_req_release(dreq);
 		return result < 0 ? result : -EIO;
 	}
@@ -872,7 +872,7 @@
 			      &nfs_direct_write_completion_ops);
 	desc.pg_dreq = dreq;
 	get_dreq(dreq);
-	atomic_inc(&inode->i_dio_count);
+	inode_dio_begin(inode);
 
 	NFS_I(inode)->write_io += iov_iter_count(iter);
 	while (iov_iter_count(iter)) {
@@ -928,7 +928,7 @@
 	 * generic layer handle the completion.
 	 */
 	if (requested_bytes == 0) {
-		inode_dio_done(inode);
+		inode_dio_end(inode);
 		nfs_direct_req_release(dreq);
 		return result < 0 ? result : -EIO;
 	}