diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 1be2b4472a83..3ab2539b7b2e 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1947,7 +1947,7 @@ extern void ext4_htree_free_dir_info(struct dir_private_info *p);
 
 /* fsync.c */
 extern int ext4_sync_file(struct file *, loff_t, loff_t, int);
-extern int ext4_flush_completed_IO(struct inode *);
+extern int ext4_flush_unwritten_io(struct inode *);
 
 /* hash.c */
 extern int ext4fs_dirhash(const char *name, int len, struct
@@ -2371,6 +2371,7 @@ extern const struct file_operations ext4_dir_operations;
 extern const struct inode_operations ext4_file_inode_operations;
 extern const struct file_operations ext4_file_operations;
 extern loff_t ext4_llseek(struct file *file, loff_t offset, int origin);
+extern void ext4_unwritten_wait(struct inode *inode);
 
 /* namei.c */
 extern const struct inode_operations ext4_dir_inode_operations;
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index c1fcf489e056..1c94cca35ed1 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -4268,7 +4268,7 @@ void ext4_ext_truncate(struct inode *inode)
 	 * finish any pending end_io work so we won't run the risk of
 	 * converting any truncated blocks to initialized later
 	 */
-	ext4_flush_completed_IO(inode);
+	ext4_flush_unwritten_io(inode);
 
 	/*
 	 * probably first extent we're gonna free will be last in block
@@ -4847,10 +4847,10 @@ int ext4_ext_punch_hole(struct file *file, loff_t offset, loff_t length)
 
 	/* Wait all existing dio workers, newcomers will block on i_mutex */
 	ext4_inode_block_unlocked_dio(inode);
-	inode_dio_wait(inode);
-	err = ext4_flush_completed_IO(inode);
+	err = ext4_flush_unwritten_io(inode);
 	if (err)
 		goto out_dio;
+	inode_dio_wait(inode);
 
 	credits = ext4_writepage_trans_blocks(inode);
 	handle = ext4_journal_start(inode, credits);
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 39335bda404b..ca6f07afe601 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -55,7 +55,7 @@ static int ext4_release_file(struct inode *inode, struct file *filp)
 	return 0;
 }
 
-static void ext4_unwritten_wait(struct inode *inode)
+void ext4_unwritten_wait(struct inode *inode)
 {
 	wait_queue_head_t *wq = ext4_ioend_wq(inode);
 
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index 460000868b8e..be1d89f385b4 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -138,7 +138,7 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	if (inode->i_sb->s_flags & MS_RDONLY)
 		goto out;
 
-	ret = ext4_flush_completed_IO(inode);
+	ret = ext4_flush_unwritten_io(inode);
 	if (ret < 0)
 		goto out;
 
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index 8d849dae8428..792e388e7b44 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -807,9 +807,11 @@ ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb,
 
 retry:
 	if (rw == READ && ext4_should_dioread_nolock(inode)) {
-		if (unlikely(!list_empty(&ei->i_completed_io_list)))
-			ext4_flush_completed_IO(inode);
-
+		if (unlikely(atomic_read(&EXT4_I(inode)->i_unwritten))) {
+			mutex_lock(&inode->i_mutex);
+			ext4_flush_unwritten_io(inode);
+			mutex_unlock(&inode->i_mutex);
+		}
 		/*
 		 * Nolock dioread optimization may be dynamically disabled
 		 * via ext4_inode_block_unlocked_dio(). Check inode's state
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 5b24c407701b..68e896e12a67 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -189,8 +189,6 @@ static int ext4_do_flush_completed_IO(struct inode *inode,
 
 		list_add_tail(&io->list, &complete);
 	}
-	/* It is important to update all flags for all end_io in one shot w/o
-	 * dropping the lock.*/
 	spin_lock_irqsave(&ei->i_completed_io_lock, flags);
 	while (!list_empty(&complete)) {
 		io = list_entry(complete.next, ext4_io_end_t, list);
@@ -228,9 +226,14 @@ static void ext4_end_io_work(struct work_struct *work)
 	ext4_do_flush_completed_IO(io->inode, io);
 }
 
-int ext4_flush_completed_IO(struct inode *inode)
+int ext4_flush_unwritten_io(struct inode *inode)
 {
-	return ext4_do_flush_completed_IO(inode, NULL);
+	int ret;
+	WARN_ON_ONCE(!mutex_is_locked(&inode->i_mutex) &&
+		     !(inode->i_state & I_FREEING));
+	ret = ext4_do_flush_completed_IO(inode, NULL);
+	ext4_unwritten_wait(inode);
+	return ret;
 }
 
 ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags)