diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index bb85757689b6af513dd556559a407049a1fc9782..5802fa1dab18f4a8aac358bd79f3ae92109daf02 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -289,10 +289,10 @@ static inline int ext4_should_order_data(struct inode *inode)
 
 static inline int ext4_should_writeback_data(struct inode *inode)
 {
-	if (!S_ISREG(inode->i_mode))
-		return 0;
 	if (EXT4_JOURNAL(inode) == NULL)
 		return 1;
+	if (!S_ISREG(inode->i_mode))
+		return 0;
 	if (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA))
 		return 0;
 	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index b8602cde5b5af7d11f2fe3e62cc88661b8fc52b9..0962642119c0475953fc70da38a5ed9bbea417a2 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -800,12 +800,17 @@ ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb,
 	}
 
 retry:
-	if (rw == READ && ext4_should_dioread_nolock(inode))
+	if (rw == READ && ext4_should_dioread_nolock(inode)) {
+		if (unlikely(!list_empty(&ei->i_completed_io_list))) {
+			mutex_lock(&inode->i_mutex);
+			ext4_flush_completed_IO(inode);
+			mutex_unlock(&inode->i_mutex);
+		}
 		ret = __blockdev_direct_IO(rw, iocb, inode,
 				 inode->i_sb->s_bdev, iov,
 				 offset, nr_segs,
 				 ext4_get_block, NULL, NULL, 0);
-	else {
+	} else {
 		ret = blockdev_direct_IO(rw, iocb, inode, iov,
 				 offset, nr_segs, ext4_get_block);
 
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index d47264cafee00e2f95e90460d67c42c2bc1d7656..c4da98a959ae06deb04e25663ce8b697b0b31458 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -120,6 +120,12 @@ void ext4_evict_inode(struct inode *inode)
 	int err;
 
 	trace_ext4_evict_inode(inode);
+
+	mutex_lock(&inode->i_mutex);
+	ext4_flush_completed_IO(inode);
+	mutex_unlock(&inode->i_mutex);
+	ext4_ioend_wait(inode);
+
 	if (inode->i_nlink) {
 		/*
 		 * When journalling data dirty buffers are tracked only in the
@@ -983,6 +989,8 @@ static int ext4_journalled_write_end(struct file *file,
 	from = pos & (PAGE_CACHE_SIZE - 1);
 	to = from + len;
 
+	BUG_ON(!ext4_handle_valid(handle));
+
 	if (copied < len) {
 		if (!PageUptodate(page))
 			copied = 0;
@@ -1283,7 +1291,12 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd,
 			else if (test_opt(inode->i_sb, MBLK_IO_SUBMIT))
 				err = ext4_bio_write_page(&io_submit, page,
 							  len, mpd->wbc);
-			else
+			else if (buffer_uninit(page_bufs)) {
+				ext4_set_bh_endio(page_bufs, inode);
+				err = block_write_full_page_endio(page,
+					noalloc_get_block_write,
+					mpd->wbc, ext4_end_io_buffer_write);
+			} else
 				err = block_write_full_page(page,
 					noalloc_get_block_write, mpd->wbc);
 
@@ -1699,6 +1712,8 @@ static int __ext4_journalled_writepage(struct page *page,
 		goto out;
 	}
 
+	BUG_ON(!ext4_handle_valid(handle));
+
 	ret = walk_page_buffers(handle, page_bufs, 0, len, NULL,
 				do_journal_get_write_access);
 
@@ -2668,8 +2683,15 @@ static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate)
 		goto out;
 	}
 
-	io_end->flag = EXT4_IO_END_UNWRITTEN;
+	/*
+	 * It may be over-defensive here to check EXT4_IO_END_UNWRITTEN now,
+	 * but being more careful is always safe for the future change.
+	 */
 	inode = io_end->inode;
+	if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
+		io_end->flag |= EXT4_IO_END_UNWRITTEN;
+		atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten);
+	}
 
 	/* Add the io_end to per-inode completed io list*/
 	spin_lock_irqsave(&EXT4_I(inode)->i_completed_io_lock, flags);
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 430c401d089514b6297d5ad88ea2d3c00b9dbb7b..78839af7ce29303118a590381dc7eda9a350f15c 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -334,8 +334,10 @@ static int io_submit_add_bh(struct ext4_io_submit *io,
 	if ((io_end->num_io_pages >= MAX_IO_PAGES) &&
 	    (io_end->pages[io_end->num_io_pages-1] != io_page))
 		goto submit_and_retry;
-	if (buffer_uninit(bh))
-		io->io_end->flag |= EXT4_IO_END_UNWRITTEN;
+	if (buffer_uninit(bh) && !(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
+		io_end->flag |= EXT4_IO_END_UNWRITTEN;
+		atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten);
+	}
 	io->io_end->size += bh->b_size;
 	io->io_next_block++;
 	ret = bio_add_page(io->io_bio, bh->b_page, bh->b_size, bh_offset(bh));
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 4687fea0c00f24498ff58c80e7d39d9c086bd62a..44d0c8db2239f958d08d4de4462cdc6ca936d1e1 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -919,7 +919,6 @@ static void ext4_i_callback(struct rcu_head *head)
 
 static void ext4_destroy_inode(struct inode *inode)
 {
-	ext4_ioend_wait(inode);
 	if (!list_empty(&(EXT4_I(inode)->i_orphan))) {
 		ext4_msg(inode->i_sb, KERN_ERR,
 			 "Inode %lu (%p): orphan list check failed!",