ext4: Always use ext4_bio_write_page() for writeout

Currently we sometimes used block_write_full_page() and sometimes
ext4_bio_write_page() for writeback (depending on mount options and call
path). Let's always use ext4_bio_write_page() to simplify things a bit.

Reviewed-by: Zheng Liu <wenqing.lz@taobao.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index ca9294f..0ccda0c 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -215,7 +215,6 @@
 	struct list_head	list;		/* per-file finished IO list */
 	struct inode		*inode;		/* file being written to */
 	unsigned int		flag;		/* unwritten or not */
-	struct page		*page;		/* for writepage() path */
 	loff_t			offset;		/* offset in the file */
 	ssize_t			size;		/* size of the extent */
 	struct work_struct	work;		/* data work queue */
@@ -985,7 +984,6 @@
 #define EXT4_MOUNT_DIOREAD_NOLOCK	0x400000 /* Enable support for dio read nolocking */
 #define EXT4_MOUNT_JOURNAL_CHECKSUM	0x800000 /* Journal checksums */
 #define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT	0x1000000 /* Journal Async Commit */
-#define EXT4_MOUNT_MBLK_IO_SUBMIT	0x4000000 /* multi-block io submits */
 #define EXT4_MOUNT_DELALLOC		0x8000000 /* Delalloc support */
 #define EXT4_MOUNT_DATA_ERR_ABORT	0x10000000 /* Abort on file data write */
 #define EXT4_MOUNT_BLOCK_VALIDITY	0x20000000 /* Block validity checking */
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 80683bf..82f9342 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -134,8 +134,6 @@
 static void ext4_invalidatepage(struct page *page, unsigned long offset);
 static int noalloc_get_block_write(struct inode *inode, sector_t iblock,
 				   struct buffer_head *bh_result, int create);
-static int ext4_set_bh_endio(struct buffer_head *bh, struct inode *inode);
-static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate);
 static int __ext4_journalled_writepage(struct page *page, unsigned int len);
 static int ext4_bh_delay_or_unwritten(handle_t *handle, struct buffer_head *bh);
 static int ext4_discard_partial_page_buffers_no_lock(handle_t *handle,
@@ -808,11 +806,10 @@
  * and the commit_write().  So doing the jbd2_journal_start at the start of
  * prepare_write() is the right place.
  *
- * Also, this function can nest inside ext4_writepage() ->
- * block_write_full_page(). In that case, we *know* that ext4_writepage()
- * has generated enough buffer credits to do the whole page.  So we won't
- * block on the journal in that case, which is good, because the caller may
- * be PF_MEMALLOC.
+ * Also, this function can nest inside ext4_writepage().  In that case, we
+ * *know* that ext4_writepage() has generated enough buffer credits to do the
+ * whole page.  So we won't block on the journal in that case, which is good,
+ * because the caller may be PF_MEMALLOC.
  *
  * By accident, ext4 can be reentered when a transaction is open via
  * quota file writes.  If we were to commit the transaction while thus
@@ -1463,18 +1460,9 @@
 			 */
 			if (unlikely(journal_data && PageChecked(page)))
 				err = __ext4_journalled_writepage(page, len);
-			else if (test_opt(inode->i_sb, MBLK_IO_SUBMIT))
+			else
 				err = ext4_bio_write_page(&io_submit, page,
 							  len, mpd->wbc);
-			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);
-
 			if (!err)
 				mpd->pages_written++;
 			/*
@@ -1891,16 +1879,16 @@
 }
 
 /*
- * This function is used as a standard get_block_t calback function
- * when there is no desire to allocate any blocks.  It is used as a
- * callback function for block_write_begin() and block_write_full_page().
- * These functions should only try to map a single block at a time.
+ * This function is used as a standard get_block_t calback function when there
+ * is no desire to allocate any blocks.  It is used as a callback function for
+ * block_write_begin().  These functions should only try to map a single block
+ * at a time.
  *
  * Since this function doesn't do block allocations even if the caller
  * requests it by passing in create=1, it is critically important that
  * any caller checks to make sure that any buffer heads are returned
  * by this function are either all already mapped or marked for
- * delayed allocation before calling  block_write_full_page().  Otherwise,
+ * delayed allocation before calling ext4_bio_write_page().  Otherwise,
  * b_blocknr could be left unitialized, and the page write functions will
  * be taken by surprise.
  */
@@ -2040,6 +2028,7 @@
 	unsigned int len;
 	struct buffer_head *page_bufs = NULL;
 	struct inode *inode = page->mapping->host;
+	struct ext4_io_submit io_submit;
 
 	trace_ext4_writepage(page);
 	size = i_size_read(inode);
@@ -2089,14 +2078,9 @@
 		 */
 		return __ext4_journalled_writepage(page, len);
 
-	if (buffer_uninit(page_bufs)) {
-		ext4_set_bh_endio(page_bufs, inode);
-		ret = block_write_full_page_endio(page, noalloc_get_block_write,
-					    wbc, ext4_end_io_buffer_write);
-	} else
-		ret = block_write_full_page(page, noalloc_get_block_write,
-					    wbc);
-
+	memset(&io_submit, 0, sizeof(io_submit));
+	ret = ext4_bio_write_page(&io_submit, page, len, wbc);
+	ext4_io_submit(&io_submit);
 	return ret;
 }
 
@@ -2858,36 +2842,10 @@
 	return mpage_readpages(mapping, pages, nr_pages, ext4_get_block);
 }
 
-static void ext4_invalidatepage_free_endio(struct page *page, unsigned long offset)
-{
-	struct buffer_head *head, *bh;
-	unsigned int curr_off = 0;
-
-	if (!page_has_buffers(page))
-		return;
-	head = bh = page_buffers(page);
-	do {
-		if (offset <= curr_off && test_clear_buffer_uninit(bh)
-					&& bh->b_private) {
-			ext4_free_io_end(bh->b_private);
-			bh->b_private = NULL;
-			bh->b_end_io = NULL;
-		}
-		curr_off = curr_off + bh->b_size;
-		bh = bh->b_this_page;
-	} while (bh != head);
-}
-
 static void ext4_invalidatepage(struct page *page, unsigned long offset)
 {
 	trace_ext4_invalidatepage(page, offset);
 
-	/*
-	 * free any io_end structure allocated for buffers to be discarded
-	 */
-	if (ext4_should_dioread_nolock(page->mapping->host))
-		ext4_invalidatepage_free_endio(page, offset);
-
 	/* No journalling happens on data buffers when this function is used */
 	WARN_ON(page_has_buffers(page) && buffer_jbd(page_buffers(page)));
 
@@ -2993,65 +2951,6 @@
 	ext4_add_complete_io(io_end);
 }
 
-static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate)
-{
-	ext4_io_end_t *io_end = bh->b_private;
-	struct inode *inode;
-
-	if (!test_clear_buffer_uninit(bh) || !io_end)
-		goto out;
-
-	if (!(io_end->inode->i_sb->s_flags & MS_ACTIVE)) {
-		ext4_msg(io_end->inode->i_sb, KERN_INFO,
-			 "sb umounted, discard end_io request for inode %lu",
-			 io_end->inode->i_ino);
-		ext4_free_io_end(io_end);
-		goto out;
-	}
-
-	/*
-	 * 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;
-	ext4_set_io_unwritten_flag(inode, io_end);
-	ext4_add_complete_io(io_end);
-out:
-	bh->b_private = NULL;
-	bh->b_end_io = NULL;
-	clear_buffer_uninit(bh);
-	end_buffer_async_write(bh, uptodate);
-}
-
-static int ext4_set_bh_endio(struct buffer_head *bh, struct inode *inode)
-{
-	ext4_io_end_t *io_end;
-	struct page *page = bh->b_page;
-	loff_t offset = (sector_t)page->index << PAGE_CACHE_SHIFT;
-	size_t size = bh->b_size;
-
-retry:
-	io_end = ext4_init_io_end(inode, GFP_ATOMIC);
-	if (!io_end) {
-		pr_warn_ratelimited("%s: allocation fail\n", __func__);
-		schedule();
-		goto retry;
-	}
-	io_end->offset = offset;
-	io_end->size = size;
-	/*
-	 * We need to hold a reference to the page to make sure it
-	 * doesn't get evicted before ext4_end_io_work() has a chance
-	 * to convert the extent from written to unwritten.
-	 */
-	io_end->page = page;
-	get_page(io_end->page);
-
-	bh->b_private = io_end;
-	bh->b_end_io = ext4_end_io_buffer_write;
-	return 0;
-}
-
 /*
  * For ext4 extent files, ext4 will do direct-io write to holes,
  * preallocated extents, and those write extend the file, no need to
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 0016fbc..ddb3d40 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -73,8 +73,6 @@
 	BUG_ON(!list_empty(&io->list));
 	BUG_ON(io->flag & EXT4_IO_END_UNWRITTEN);
 
-	if (io->page)
-		put_page(io->page);
 	for (i = 0; i < io->num_io_pages; i++)
 		put_io_page(io->pages[i]);
 	io->num_io_pages = 0;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 3b04d15..d5d336b 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1280,8 +1280,8 @@
 	{Opt_stripe, "stripe=%u"},
 	{Opt_delalloc, "delalloc"},
 	{Opt_nodelalloc, "nodelalloc"},
-	{Opt_mblk_io_submit, "mblk_io_submit"},
-	{Opt_nomblk_io_submit, "nomblk_io_submit"},
+	{Opt_removed, "mblk_io_submit"},
+	{Opt_removed, "nomblk_io_submit"},
 	{Opt_block_validity, "block_validity"},
 	{Opt_noblock_validity, "noblock_validity"},
 	{Opt_inode_readahead_blks, "inode_readahead_blks=%u"},
@@ -1415,8 +1415,6 @@
 	{Opt_bsd_df, EXT4_MOUNT_MINIX_DF, MOPT_CLEAR},
 	{Opt_grpid, EXT4_MOUNT_GRPID, MOPT_SET},
 	{Opt_nogrpid, EXT4_MOUNT_GRPID, MOPT_CLEAR},
-	{Opt_mblk_io_submit, EXT4_MOUNT_MBLK_IO_SUBMIT, MOPT_SET},
-	{Opt_nomblk_io_submit, EXT4_MOUNT_MBLK_IO_SUBMIT, MOPT_CLEAR},
 	{Opt_block_validity, EXT4_MOUNT_BLOCK_VALIDITY, MOPT_SET},
 	{Opt_noblock_validity, EXT4_MOUNT_BLOCK_VALIDITY, MOPT_CLEAR},
 	{Opt_dioread_nolock, EXT4_MOUNT_DIOREAD_NOLOCK, MOPT_SET},
@@ -3381,7 +3379,6 @@
 #ifdef CONFIG_EXT4_FS_POSIX_ACL
 	set_opt(sb, POSIX_ACL);
 #endif
-	set_opt(sb, MBLK_IO_SUBMIT);
 	if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_DATA)
 		set_opt(sb, JOURNAL_DATA);
 	else if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_ORDERED)