int ext4_bio_write_page(struct ext4_io_submit *io,
			struct page *page,
			int len,
			struct writeback_control *wbc)
{
	struct inode *inode = page->mapping->host;
	unsigned block_start, block_end, blocksize;
	struct ext4_io_page *io_page;
	struct buffer_head *bh, *head;
	int ret = 0;

	blocksize = 1 << inode->i_blkbits;

	BUG_ON(!PageLocked(page));
	BUG_ON(PageWriteback(page));

	io_page = kmem_cache_alloc(io_page_cachep, GFP_NOFS);
	if (!io_page) {
		set_page_dirty(page);
		unlock_page(page);
		return -ENOMEM;
	}
	io_page->p_page = page;
	atomic_set(&io_page->p_count, 1);
	get_page(page);
	set_page_writeback(page);
	ClearPageError(page);

	for (bh = head = page_buffers(page), block_start = 0;
	     bh != head || !block_start;
	     block_start = block_end, bh = bh->b_this_page) {

		block_end = block_start + blocksize;
		if (block_start >= len) {
			zero_user_segment(page, block_start, block_end);
			clear_buffer_dirty(bh);
			set_buffer_uptodate(bh);
			continue;
		}
		clear_buffer_dirty(bh);
		ret = io_submit_add_bh(io, io_page, inode, wbc, bh);
		if (ret) {
			set_page_dirty(page);
			break;
		}
	}
	unlock_page(page);
	put_io_page(io_page);
	return ret;
}

void nilfs_clear_dirty_pages(struct address_space *mapping)
{
	struct pagevec pvec;
	unsigned int i;
	pgoff_t index = 0;

	pagevec_init(&pvec, 0);

	while (pagevec_lookup_tag(&pvec, mapping, &index, PAGECACHE_TAG_DIRTY,
				  PAGEVEC_SIZE)) {
		for (i = 0; i < pagevec_count(&pvec); i++) {
			struct page *page = pvec.pages[i];
			struct buffer_head *bh, *head;

			lock_page(page);
			ClearPageUptodate(page);
			ClearPageMappedToDisk(page);
			bh = head = page_buffers(page);
			do {
				lock_buffer(bh);
				clear_buffer_dirty(bh);
				clear_buffer_nilfs_volatile(bh);
				clear_buffer_uptodate(bh);
				clear_buffer_mapped(bh);
				unlock_buffer(bh);
				bh = bh->b_this_page;
			} while (bh != head);

			__nilfs_clear_page_dirty(page);
			unlock_page(page);
		}
		pagevec_release(&pvec);
		cond_resched();
	}
}

void gfs2_remove_from_journal(struct buffer_head *bh, struct gfs2_trans *tr, int meta)
{
	struct gfs2_sbd *sdp = GFS2_SB(bh->b_page->mapping->host);
	struct gfs2_bufdata *bd = bh->b_private;
	if (test_clear_buffer_pinned(bh)) {
		list_del_init(&bd->bd_le.le_list);
		if (meta) {
			gfs2_assert_warn(sdp, sdp->sd_log_num_buf);
			sdp->sd_log_num_buf--;
			tr->tr_num_buf_rm++;
		} else {
			gfs2_assert_warn(sdp, sdp->sd_log_num_databuf);
			sdp->sd_log_num_databuf--;
			tr->tr_num_databuf_rm++;
		}
		tr->tr_touched = 1;
		brelse(bh);
	}
	if (bd) {
		if (bd->bd_ail) {
			gfs2_remove_from_ail(bd);
			bh->b_private = NULL;
			bd->bd_bh = NULL;
			bd->bd_blkno = bh->b_blocknr;
			gfs2_trans_add_revoke(sdp, bd);
		}
	}
	clear_buffer_dirty(bh);
	clear_buffer_uptodate(bh);
}

/* stolen from fs/buffer.c */
void reiserfs_unmap_buffer(struct buffer_head *bh)
{
	lock_buffer(bh);
	if (buffer_journaled(bh) || buffer_journal_dirty(bh)) {
		BUG();
	}
	clear_buffer_dirty(bh);
	/*
	 * Remove the buffer from whatever list it belongs to. We are mostly
	 * interested in removing it from per-sb j_dirty_buffers list, to avoid
	 * BUG() on attempt to write not mapped buffer
	 */
	if ((!list_empty(&bh->b_assoc_buffers) || bh->b_private) && bh->b_page) {
		struct inode *inode = bh->b_page->mapping->host;
		struct reiserfs_journal *j = SB_JOURNAL(inode->i_sb);
		spin_lock(&j->j_dirty_buffers_lock);
		list_del_init(&bh->b_assoc_buffers);
		reiserfs_free_jh(bh);
		spin_unlock(&j->j_dirty_buffers_lock);
	}
	clear_buffer_mapped(bh);
	clear_buffer_req(bh);
	clear_buffer_new(bh);
	bh->b_bdev = NULL;
	unlock_buffer(bh);
}

int ext4_bio_write_page(struct ext4_io_submit *io,
			struct page *page,
			int len,
			struct writeback_control *wbc)
{
	struct inode *inode = page->mapping->host;
	unsigned block_start, block_end, blocksize;
	struct ext4_io_page *io_page;
	struct buffer_head *bh, *head;
	int ret = 0;

	blocksize = 1 << inode->i_blkbits;

	BUG_ON(PageWriteback(page));
	set_page_writeback(page);
	ClearPageError(page);

	io_page = kmem_cache_alloc(io_page_cachep, GFP_NOFS);
	if (!io_page) {
		set_page_dirty(page);
		unlock_page(page);
		return -ENOMEM;
	}
	io_page->p_page = page;
	atomic_set(&io_page->p_count, 1);
	get_page(page);

	for (bh = head = page_buffers(page), block_start = 0;
	     bh != head || !block_start;
	     block_start = block_end, bh = bh->b_this_page) {
		block_end = block_start + blocksize;
		if (block_start >= len) {
			clear_buffer_dirty(bh);
			set_buffer_uptodate(bh);
			continue;
		}
		ret = io_submit_add_bh(io, io_page, inode, wbc, bh);
		if (ret) {
			/*
			 * We only get here on ENOMEM.  Not much else
			 * we can do but mark the page as dirty, and
			 * better luck next time.
			 */
			set_page_dirty(page);
			break;
		}
	}
	unlock_page(page);
	/*
	 * If the page was truncated before we could do the writeback,
	 * or we had a memory allocation error while trying to write
	 * the first buffer head, we won't have submitted any pages for
	 * I/O.  In that case we need to make sure we've cleared the
	 * PageWriteback bit from the page to prevent the system from
	 * wedging later on.
	 */
	put_io_page(io_page);
	return ret;
}

static void meta_prep_new(struct buffer_head *bh)
{
	struct gfs2_meta_header *mh = (struct gfs2_meta_header *)bh->b_data;

	lock_buffer(bh);
	clear_buffer_dirty(bh);
	set_buffer_uptodate(bh);
	unlock_buffer(bh);

	mh->mh_magic = cpu_to_be32(GFS2_MAGIC);
}

static int io_submit_add_bh(struct ext4_io_submit *io,
			    struct ext4_io_page *io_page,
			    struct inode *inode,
			    struct writeback_control *wbc,
			    struct buffer_head *bh)
{
	ext4_io_end_t *io_end;
	int ret;

	if (buffer_new(bh)) {
		clear_buffer_new(bh);
		unmap_underlying_metadata(bh->b_bdev, bh->b_blocknr);
	}

	if (!buffer_mapped(bh) || buffer_delay(bh)) {
		if (!buffer_mapped(bh))
			clear_buffer_dirty(bh);
		if (io->io_bio)
			ext4_io_submit(io);
		return 0;
	}

	if (io->io_bio && bh->b_blocknr != io->io_next_block) {
submit_and_retry:
		ext4_io_submit(io);
	}
	if (io->io_bio == NULL) {
		ret = io_submit_init(io, inode, wbc, bh);
		if (ret)
			return ret;
	}
	io_end = io->io_end;
	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_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));
	if (ret != bh->b_size)
		goto submit_and_retry;
	if ((io_end->num_io_pages == 0) ||
	    (io_end->pages[io_end->num_io_pages-1] != io_page)) {
		io_end->pages[io_end->num_io_pages++] = io_page;
		atomic_inc(&io_page->p_count);
	}
	return 0;
}

int ocfs2_write_block(struct ocfs2_super *osb, struct buffer_head *bh,
		      struct inode *inode)
{
	int ret = 0;

	mlog_entry("(bh->b_blocknr = %llu, inode=%p)\n",
		   (unsigned long long)bh->b_blocknr, inode);

	BUG_ON(bh->b_blocknr < OCFS2_SUPER_BLOCK_BLKNO);
	BUG_ON(buffer_jbd(bh));

	/* No need to check for a soft readonly file system here. non
	 * journalled writes are only ever done on system files which
	 * can get modified during recovery even if read-only. */
	if (ocfs2_is_hard_readonly(osb)) {
		ret = -EROFS;
		goto out;
	}

	mutex_lock(&OCFS2_I(inode)->ip_io_mutex);

	lock_buffer(bh);
	set_buffer_uptodate(bh);

	/* remove from dirty list before I/O. */
	clear_buffer_dirty(bh);

	get_bh(bh); /* for end_buffer_write_sync() */
	bh->b_end_io = end_buffer_write_sync;
	submit_bh(WRITE, bh);

	wait_on_buffer(bh);

	if (buffer_uptodate(bh)) {
		ocfs2_set_buffer_uptodate(inode, bh);
	} else {
		/* We don't need to remove the clustered uptodate
		 * information for this bh as it's not marked locally
		 * uptodate. */
		ret = -EIO;
		put_bh(bh);
	}

	mutex_unlock(&OCFS2_I(inode)->ip_io_mutex);
out:
	mlog_exit(ret);
	return ret;
}

int jbd2_journal_get_create_access(handle_t *handle, struct buffer_head *bh)
{
	transaction_t *transaction = handle->h_transaction;
	journal_t *journal = transaction->t_journal;
	struct journal_head *jh = jbd2_journal_add_journal_head(bh);
	int err;

	jbd_debug(5, "journal_head %p\n", jh);
	err = -EROFS;
	if (is_handle_aborted(handle))
		goto out;
	err = 0;

	JBUFFER_TRACE(jh, "entry");
	jbd_lock_bh_state(bh);
	spin_lock(&journal->j_list_lock);
	J_ASSERT_JH(jh, (jh->b_transaction == transaction ||
		jh->b_transaction == NULL ||
		(jh->b_transaction == journal->j_committing_transaction &&
			  jh->b_jlist == BJ_Forget)));

	J_ASSERT_JH(jh, jh->b_next_transaction == NULL);
	J_ASSERT_JH(jh, buffer_locked(jh2bh(jh)));

	if (jh->b_transaction == NULL) {
		clear_buffer_dirty(jh2bh(jh));
		
		jh->b_modified = 0;

		JBUFFER_TRACE(jh, "file as BJ_Reserved");
		__jbd2_journal_file_buffer(jh, transaction, BJ_Reserved);
	} else if (jh->b_transaction == journal->j_committing_transaction) {
		
		jh->b_modified = 0;

		JBUFFER_TRACE(jh, "set next transaction");
		jh->b_next_transaction = transaction;
	}
	spin_unlock(&journal->j_list_lock);
	jbd_unlock_bh_state(bh);

	JBUFFER_TRACE(jh, "cancelling revoke");
	jbd2_journal_cancel_revoke(handle, jh);
out:
	jbd2_journal_put_journal_head(jh);
	return err;
}

int ocfs2_write_block(struct ocfs2_super *osb, struct buffer_head *bh,
		      struct ocfs2_caching_info *ci)
{
	int ret = 0;

	trace_ocfs2_write_block((unsigned long long)bh->b_blocknr, ci);

	BUG_ON(bh->b_blocknr < OCFS2_SUPER_BLOCK_BLKNO);
	BUG_ON(buffer_jbd(bh));

	/* No need to check for a soft readonly file system here. non
	 * journalled writes are only ever done on system files which
	 * can get modified during recovery even if read-only. */
	if (ocfs2_is_hard_readonly(osb)) {
		ret = -EROFS;
		mlog_errno(ret);
		goto out;
	}

	ocfs2_metadata_cache_io_lock(ci);

	lock_buffer(bh);
	set_buffer_uptodate(bh);

	/* remove from dirty list before I/O. */
	clear_buffer_dirty(bh);

	get_bh(bh); /* for end_buffer_write_sync() */
	bh->b_end_io = end_buffer_write_sync;
	submit_bh(REQ_OP_WRITE, 0, bh);

	wait_on_buffer(bh);

	if (buffer_uptodate(bh)) {
		ocfs2_set_buffer_uptodate(ci, bh);
	} else {
		/* We don't need to remove the clustered uptodate
		 * information for this bh as it's not marked locally
		 * uptodate. */
		ret = -EIO;
		mlog_errno(ret);
	}

	ocfs2_metadata_cache_io_unlock(ci);
out:
	return ret;
}

static int __dispose_buffer(struct journal_head *jh, transaction_t *transaction)
{
	int may_free = 1;
	struct buffer_head *bh = jh2bh(jh);

	if (jh->b_cp_transaction) {
		JBUFFER_TRACE(jh, "on running+cp transaction");
		__jbd2_journal_temp_unlink_buffer(jh);
		clear_buffer_dirty(bh);
		__jbd2_journal_file_buffer(jh, transaction, BJ_Forget);
		may_free = 0;
	} else {
		JBUFFER_TRACE(jh, "on running transaction");
		__jbd2_journal_unfile_buffer(jh);
	}
	return may_free;
}

/* Clear buffer dirty for I/O (Caller must remove buffer from list) */
static void tux3_clear_buffer_dirty_for_io(struct buffer_head *buffer,
					   struct sb *sb, block_t block)
{
	assert(list_empty(&buffer->b_assoc_buffers));
	assert(buffer_dirty(buffer));	/* Who cleared the dirty? */
	/* If buffer was hole and dirtied, it can be !buffer_mapped() */
	/*assert(buffer_mapped(buffer));*/
	assert(buffer_uptodate(buffer));

	/* Set up buffer for I/O. FIXME: need? */
	map_bh(buffer, vfs_sb(sb), block);
	clear_buffer_delay(buffer);

	/*buffer->b_assoc_map = NULL;*/	/* FIXME: hack for *_for_io_hack */
	tux3_clear_bufdelta(buffer);	/* FIXME: hack for save delta */
	clear_buffer_dirty(buffer);
}

/**
 * nilfs_forget_buffer - discard dirty state
 * @inode: owner inode of the buffer
 * @bh: buffer head of the buffer to be discarded
 */
void nilfs_forget_buffer(struct buffer_head *bh)
{
	struct page *page = bh->b_page;

	lock_buffer(bh);
	clear_buffer_nilfs_volatile(bh);
	clear_buffer_dirty(bh);
	if (nilfs_page_buffers_clean(page))
		__nilfs_clear_page_dirty(page);

	clear_buffer_uptodate(bh);
	clear_buffer_mapped(bh);
	bh->b_blocknr = -1;
	ClearPageUptodate(page);
	ClearPageMappedToDisk(page);
	unlock_buffer(bh);
	brelse(bh);
}

/*
 * Caller must hold lock_page() or backend (otherwise, you may race
 * with buffer fork or set dirty)
 */
void tux3_clear_buffer_dirty(struct buffer_head *buffer, unsigned delta)
{
	struct address_space *buffer_mapping = buffer->b_assoc_map;

	/* The buffer must not need to fork */
	assert(buffer_can_modify(buffer, delta));

	if (buffer_mapping) {
		spin_lock(&buffer_mapping->private_lock);
		list_del_init(&buffer->b_assoc_buffers);
		buffer->b_assoc_map = NULL;
		tux3_clear_bufdelta(buffer);
		spin_unlock(&buffer_mapping->private_lock);

		clear_buffer_dirty(buffer);
	} else
		BUG_ON(!list_empty(&buffer->b_assoc_buffers));
}

void reiserfs_unmap_buffer(struct buffer_head *bh)
{
	lock_buffer(bh);
	if (buffer_journaled(bh) || buffer_journal_dirty(bh)) {
		BUG();
	}
	clear_buffer_dirty(bh);
	if ((!list_empty(&bh->b_assoc_buffers) || bh->b_private) && bh->b_page) {
		struct inode *inode = bh->b_page->mapping->host;
		struct reiserfs_journal *j = SB_JOURNAL(inode->i_sb);
		spin_lock(&j->j_dirty_buffers_lock);
		list_del_init(&bh->b_assoc_buffers);
		reiserfs_free_jh(bh);
		spin_unlock(&j->j_dirty_buffers_lock);
	}
	clear_buffer_mapped(bh);
	clear_buffer_req(bh);
	clear_buffer_new(bh);
	bh->b_bdev = NULL;
	unlock_buffer(bh);
}

static void gfs2_discard(struct gfs2_sbd *sdp, struct buffer_head *bh)
{
	struct gfs2_bufdata *bd;

	lock_buffer(bh);
	gfs2_log_lock(sdp);
	clear_buffer_dirty(bh);
	bd = bh->b_private;
	if (bd) {
		if (!list_empty(&bd->bd_le.le_list) && !buffer_pinned(bh))
			list_del_init(&bd->bd_le.le_list);
		else
			gfs2_remove_from_journal(bh, current->journal_info, 0);
	}
	bh->b_bdev = NULL;
	clear_buffer_mapped(bh);
	clear_buffer_req(bh);
	clear_buffer_new(bh);
	gfs2_log_unlock(sdp);
	unlock_buffer(bh);
}

static void discard_buffer(struct gfs2_sbd *sdp, struct buffer_head *bh)
{
	struct gfs2_bufdata *bd;

	gfs2_log_lock(sdp);
	bd = bh->b_private;
	if (bd) {
		bd->bd_bh = NULL;
		bh->b_private = NULL;
	}
	gfs2_log_unlock(sdp);

	lock_buffer(bh);
	clear_buffer_dirty(bh);
	bh->b_bdev = NULL;
	clear_buffer_mapped(bh);
	clear_buffer_req(bh);
	clear_buffer_new(bh);
	clear_buffer_delay(bh);
	unlock_buffer(bh);
}

/**
 * nilfs_clear_dirty_page - discard dirty page
 * @page: dirty page that will be discarded
 * @silent: suppress [true] or print [false] warning messages
 */
void nilfs_clear_dirty_page(struct page *page, bool silent)
{
	struct inode *inode = page->mapping->host;
	struct super_block *sb = inode->i_sb;

	BUG_ON(!PageLocked(page));

	if (!silent) {
		nilfs_warning(sb, __func__,
				"discard page: offset %lld, ino %lu",
				page_offset(page), inode->i_ino);
	}

	ClearPageUptodate(page);
	ClearPageMappedToDisk(page);

	if (page_has_buffers(page)) {
		struct buffer_head *bh, *head;

		bh = head = page_buffers(page);
		do {
			lock_buffer(bh);
			if (!silent) {
				nilfs_warning(sb, __func__,
					"discard block %llu, size %zu",
					(u64)bh->b_blocknr, bh->b_size);
			}
			clear_buffer_async_write(bh);
			clear_buffer_dirty(bh);
			clear_buffer_nilfs_volatile(bh);
			clear_buffer_nilfs_checked(bh);
			clear_buffer_nilfs_redirected(bh);
			clear_buffer_uptodate(bh);
			clear_buffer_mapped(bh);
			unlock_buffer(bh);
		} while (bh = bh->b_this_page, bh != head);
	}

	__nilfs_clear_page_dirty(page);
}

/*
 * Write super block and backups doesn't need to collaborate with journal,
 * so we don't need to lock ip_io_mutex and inode doesn't need to bea passed
 * into this function.
 */
int ocfs2_write_super_or_backup(struct ocfs2_super *osb,
				struct buffer_head *bh)
{
	int ret = 0;

	mlog_entry_void();

	BUG_ON(buffer_jbd(bh));
	ocfs2_check_super_or_backup(osb->sb, bh->b_blocknr);

	if (ocfs2_is_hard_readonly(osb) || ocfs2_is_soft_readonly(osb)) {
		ret = -EROFS;
		goto out;
	}

	lock_buffer(bh);
	set_buffer_uptodate(bh);

	/* remove from dirty list before I/O. */
	clear_buffer_dirty(bh);

	get_bh(bh); /* for end_buffer_write_sync() */
	bh->b_end_io = end_buffer_write_sync;
	submit_bh(WRITE, bh);

	wait_on_buffer(bh);

	if (!buffer_uptodate(bh)) {
		ret = -EIO;
		put_bh(bh);
	}

out:
	mlog_exit(ret);
	return ret;
}

/*
 * We have our BIO, so we can now mark the buffers clean.  Make
 * sure to only clean buffers which we know we'll be writing.
 */
static void clean_buffers(struct page *page, unsigned first_unmapped)
{
	unsigned buffer_counter = 0;
	struct buffer_head *bh, *head;
	if (!page_has_buffers(page))
		return;
	head = page_buffers(page);
	bh = head;

	do {
		if (buffer_counter++ == first_unmapped)
			break;
		clear_buffer_dirty(bh);
		bh = bh->b_this_page;
	} while (bh != head);

	/*
	 * we cannot drop the bh if the page is not uptodate or a concurrent
	 * readpage would fail to serialize with the bh and it would read from
	 * disk before we reach the platter.
	 */
	if (buffer_heads_over_limit && PageUptodate(page))
		try_to_free_buffers(page);
}