buffer.c

			page_cache_release(page);
			*pagep = NULL;

			/*
			 * prepare_write() may have instantiated a few blocks
			 * outside i_size.  Trim these off again. Don't need
			 * i_size_read because we hold i_mutex.
			 */
			if (pos + len > inode->i_size)
				vmtruncate(inode, inode->i_size);
		}
	}

out:
	return status;
}
EXPORT_SYMBOL(block_write_begin);

int block_write_end(struct file *file, struct address_space *mapping,
			loff_t pos, unsigned len, unsigned copied,
			struct page *page, void *fsdata)
{
	struct inode *inode = mapping->host;
	unsigned start;

	start = pos & (PAGE_CACHE_SIZE - 1);

	if (unlikely(copied < len)) {
		/*
		 * The buffers that were written will now be uptodate, so we
		 * don't have to worry about a readpage reading them and
		 * overwriting a partial write. However if we have encountered
		 * a short write and only partially written into a buffer, it
		 * will not be marked uptodate, so a readpage might come in and
		 * destroy our partial write.
		 *
		 * Do the simplest thing, and just treat any short write to a
		 * non uptodate page as a zero-length write, and force the
		 * caller to redo the whole thing.
		 */
		if (!PageUptodate(page))
			copied = 0;

		page_zero_new_buffers(page, start+copied, start+len);
	}
	flush_dcache_page(page);

	/* This could be a short (even 0-length) commit */
	__block_commit_write(inode, page, start, start+copied);

	return copied;
}
EXPORT_SYMBOL(block_write_end);

int generic_write_end(struct file *file, struct address_space *mapping,
			loff_t pos, unsigned len, unsigned copied,
			struct page *page, void *fsdata)
{
	struct inode *inode = mapping->host;
	int i_size_changed = 0;

	copied = block_write_end(file, mapping, pos, len, copied, page, fsdata);

	/*
	 * No need to use i_size_read() here, the i_size
	 * cannot change under us because we hold i_mutex.
	 *
	 * But it's important to update i_size while still holding page lock:
	 * page writeout could otherwise come in and zero beyond i_size.
	 */
	if (pos+copied > inode->i_size) {
		i_size_write(inode, pos+copied);
		i_size_changed = 1;
	}

	unlock_page(page);
	page_cache_release(page);

	/*
	 * Don't mark the inode dirty under page lock. First, it unnecessarily
	 * makes the holding time of page lock longer. Second, it forces lock
	 * ordering of page lock and transaction start for journaling
	 * filesystems.
	 */
	if (i_size_changed)
		mark_inode_dirty(inode);

	return copied;
}
EXPORT_SYMBOL(generic_write_end);

/*
 * block_is_partially_uptodate checks whether buffers within a page are
 * uptodate or not.
 *
 * Returns true if all buffers which correspond to a file portion
 * we want to read are uptodate.
 */
int block_is_partially_uptodate(struct page *page, read_descriptor_t *desc,
					unsigned long from)
{
	struct inode *inode = page->mapping->host;
	unsigned block_start, block_end, blocksize;
	unsigned to;
	struct buffer_head *bh, *head;
	int ret = 1;

	if (!page_has_buffers(page))
		return 0;

	blocksize = 1 << inode->i_blkbits;
	to = min_t(unsigned, PAGE_CACHE_SIZE - from, desc->count);
	to = from + to;
	if (from < blocksize && to > PAGE_CACHE_SIZE - blocksize)
		return 0;

	head = page_buffers(page);
	bh = head;
	block_start = 0;
	do {
		block_end = block_start + blocksize;
		if (block_end > from && block_start < to) {
			if (!buffer_uptodate(bh)) {
				ret = 0;
				break;
			}
			if (block_end >= to)
				break;
		}
		block_start = block_end;
		bh = bh->b_this_page;
	} while (bh != head);

	return ret;
}
EXPORT_SYMBOL(block_is_partially_uptodate);

/*
 * Generic "read page" function for block devices that have the normal
 * get_block functionality. This is most of the block device filesystems.
 * Reads the page asynchronously --- the unlock_buffer() and
 * set/clear_buffer_uptodate() functions propagate buffer state into the
 * page struct once IO has completed.
 */
int block_read_full_page(struct page *page, get_block_t *get_block)
{
	struct inode *inode = page->mapping->host;
	sector_t iblock, lblock;
	struct buffer_head *bh, *head, *arr[MAX_BUF_PER_PAGE];
	unsigned int blocksize;
	int nr, i;
	int fully_mapped = 1;

	BUG_ON(!PageLocked(page));
	blocksize = 1 << inode->i_blkbits;
	if (!page_has_buffers(page))
		create_empty_buffers(page, blocksize, 0);
	head = page_buffers(page);

	iblock = (sector_t)page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
	lblock = (i_size_read(inode)+blocksize-1) >> inode->i_blkbits;
	bh = head;
	nr = 0;
	i = 0;

	do {
		if (buffer_uptodate(bh))
			continue;

		if (!buffer_mapped(bh)) {
			int err = 0;

			fully_mapped = 0;
			if (iblock < lblock) {
				WARN_ON(bh->b_size != blocksize);
				err = get_block(inode, iblock, bh, 0);
				if (err)
					SetPageError(page);
			}
			if (!buffer_mapped(bh)) {
				zero_user(page, i * blocksize, blocksize);
				if (!err)
					set_buffer_uptodate(bh);
				continue;
			}
			/*
			 * get_block() might have updated the buffer
			 * synchronously
			 */
			if (buffer_uptodate(bh))
				continue;
		}
		arr[nr++] = bh;
	} while (i++, iblock++, (bh = bh->b_this_page) != head);

	if (fully_mapped)
		SetPageMappedToDisk(page);

	if (!nr) {
		/*
		 * All buffers are uptodate - we can set the page uptodate
		 * as well. But not if get_block() returned an error.
		 */
		if (!PageError(page))
			SetPageUptodate(page);
		unlock_page(page);
		return 0;
	}

	/* Stage two: lock the buffers */
	for (i = 0; i < nr; i++) {
		bh = arr[i];
		lock_buffer(bh);
		mark_buffer_async_read(bh);
	}

	/*
	 * Stage 3: start the IO.  Check for uptodateness
	 * inside the buffer lock in case another process reading
	 * the underlying blockdev brought it uptodate (the sct fix).
	 */
	for (i = 0; i < nr; i++) {
		bh = arr[i];
		if (buffer_uptodate(bh))
			end_buffer_async_read(bh, 1);
		else
			submit_bh(READ, bh);
	}
	return 0;
}
EXPORT_SYMBOL(block_read_full_page);

/* utility function for filesystems that need to do work on expanding
 * truncates.  Uses filesystem pagecache writes to allow the filesystem to
 * deal with the hole.  
 */
int generic_cont_expand_simple(struct inode *inode, loff_t size)
{
	struct address_space *mapping = inode->i_mapping;
	struct page *page;
	void *fsdata;
	int err;

	err = inode_newsize_ok(inode, size);
	if (err)
		goto out;

	err = pagecache_write_begin(NULL, mapping, size, 0,
				AOP_FLAG_UNINTERRUPTIBLE|AOP_FLAG_CONT_EXPAND,
				&page, &fsdata);
	if (err)
		goto out;

	err = pagecache_write_end(NULL, mapping, size, 0, 0, page, fsdata);
	BUG_ON(err > 0);

out:
	return err;
}
EXPORT_SYMBOL(generic_cont_expand_simple);

static int cont_expand_zero(struct file *file, struct address_space *mapping,
			    loff_t pos, loff_t *bytes)
{
	struct inode *inode = mapping->host;
	unsigned blocksize = 1 << inode->i_blkbits;
	struct page *page;
	void *fsdata;
	pgoff_t index, curidx;
	loff_t curpos;
	unsigned zerofrom, offset, len;
	int err = 0;

	index = pos >> PAGE_CACHE_SHIFT;
	offset = pos & ~PAGE_CACHE_MASK;

	while (index > (curidx = (curpos = *bytes)>>PAGE_CACHE_SHIFT)) {
		zerofrom = curpos & ~PAGE_CACHE_MASK;
		if (zerofrom & (blocksize-1)) {
			*bytes |= (blocksize-1);
			(*bytes)++;
		}
		len = PAGE_CACHE_SIZE - zerofrom;

		err = pagecache_write_begin(file, mapping, curpos, len,
						AOP_FLAG_UNINTERRUPTIBLE,
						&page, &fsdata);
		if (err)
			goto out;
		zero_user(page, zerofrom, len);
		err = pagecache_write_end(file, mapping, curpos, len, len,
						page, fsdata);
		if (err < 0)
			goto out;
		BUG_ON(err != len);
		err = 0;

		balance_dirty_pages_ratelimited(mapping);
	}

	/* page covers the boundary, find the boundary offset */
	if (index == curidx) {
		zerofrom = curpos & ~PAGE_CACHE_MASK;
		/* if we will expand the thing last block will be filled */
		if (offset <= zerofrom) {
			goto out;
		}
		if (zerofrom & (blocksize-1)) {
			*bytes |= (blocksize-1);
			(*bytes)++;
		}
		len = offset - zerofrom;

		err = pagecache_write_begin(file, mapping, curpos, len,
						AOP_FLAG_UNINTERRUPTIBLE,
						&page, &fsdata);
		if (err)
			goto out;
		zero_user(page, zerofrom, len);
		err = pagecache_write_end(file, mapping, curpos, len, len,
						page, fsdata);
		if (err < 0)
			goto out;
		BUG_ON(err != len);
		err = 0;
	}
out:
	return err;
}

/*
 * For moronic filesystems that do not allow holes in file.
 * We may have to extend the file.
 */
int cont_write_begin(struct file *file, struct address_space *mapping,
			loff_t pos, unsigned len, unsigned flags,
			struct page **pagep, void **fsdata,
			get_block_t *get_block, loff_t *bytes)
{
	struct inode *inode = mapping->host;
	unsigned blocksize = 1 << inode->i_blkbits;
	unsigned zerofrom;
	int err;

	err = cont_expand_zero(file, mapping, pos, bytes);
	if (err)
		goto out;

	zerofrom = *bytes & ~PAGE_CACHE_MASK;
	if (pos+len > *bytes && zerofrom & (blocksize-1)) {
		*bytes |= (blocksize-1);
		(*bytes)++;
	}

	*pagep = NULL;
	err = block_write_begin(file, mapping, pos, len,
				flags, pagep, fsdata, get_block);
out:
	return err;
}
EXPORT_SYMBOL(cont_write_begin);

int block_prepare_write(struct page *page, unsigned from, unsigned to,
			get_block_t *get_block)
{
	struct inode *inode = page->mapping->host;
	int err = __block_prepare_write(inode, page, from, to, get_block);
	if (err)
		ClearPageUptodate(page);
	return err;
}
EXPORT_SYMBOL(block_prepare_write);

int block_commit_write(struct page *page, unsigned from, unsigned to)
{
	struct inode *inode = page->mapping->host;
	__block_commit_write(inode,page,from,to);
	return 0;
}
EXPORT_SYMBOL(block_commit_write);

/*
 * block_page_mkwrite() is not allowed to change the file size as it gets
 * called from a page fault handler when a page is first dirtied. Hence we must
 * be careful to check for EOF conditions here. We set the page up correctly
 * for a written page which means we get ENOSPC checking when writing into
 * holes and correct delalloc and unwritten extent mapping on filesystems that
 * support these features.
 *
 * We are not allowed to take the i_mutex here so we have to play games to
 * protect against truncate races as the page could now be beyond EOF.  Because
 * vmtruncate() writes the inode size before removing pages, once we have the
 * page lock we can determine safely if the page is beyond EOF. If it is not
 * beyond EOF, then the page is guaranteed safe against truncation until we
 * unlock the page.
 */
int
block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
		   get_block_t get_block)
{
	struct page *page = vmf->page;
	struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
	unsigned long end;
	loff_t size;
	int ret = VM_FAULT_NOPAGE; /* make the VM retry the fault */

	lock_page(page);
	size = i_size_read(inode);
	if ((page->mapping != inode->i_mapping) ||
	    (page_offset(page) > size)) {
		/* page got truncated out from underneath us */
		unlock_page(page);
		goto out;
	}

	/* page is wholly or partially inside EOF */
	if (((page->index + 1) << PAGE_CACHE_SHIFT) > size)
		end = size & ~PAGE_CACHE_MASK;
	else
		end = PAGE_CACHE_SIZE;

	ret = block_prepare_write(page, 0, end, get_block);
	if (!ret)
		ret = block_commit_write(page, 0, end);

	if (unlikely(ret)) {
		unlock_page(page);
		if (ret == -ENOMEM)
			ret = VM_FAULT_OOM;
		else /* -ENOSPC, -EIO, etc */
			ret = VM_FAULT_SIGBUS;
	} else
		ret = VM_FAULT_LOCKED;

out:
	return ret;
}
EXPORT_SYMBOL(block_page_mkwrite);

/*
 * nobh_write_begin()'s prereads are special: the buffer_heads are freed
 * immediately, while under the page lock.  So it needs a special end_io
 * handler which does not touch the bh after unlocking it.
 */
static void end_buffer_read_nobh(struct buffer_head *bh, int uptodate)
{
	__end_buffer_read_notouch(bh, uptodate);
}

/*
 * Attach the singly-linked list of buffers created by nobh_write_begin, to
 * the page (converting it to circular linked list and taking care of page
 * dirty races).
 */
static void attach_nobh_buffers(struct page *page, struct buffer_head *head)
{
	struct buffer_head *bh;

	BUG_ON(!PageLocked(page));

	spin_lock(&page->mapping->private_lock);
	bh = head;
	do {
		if (PageDirty(page))
			set_buffer_dirty(bh);
		if (!bh->b_this_page)
			bh->b_this_page = head;
		bh = bh->b_this_page;
	} while (bh != head);
	attach_page_buffers(page, head);
	spin_unlock(&page->mapping->private_lock);
}

/*
 * On entry, the page is fully not uptodate.
 * On exit the page is fully uptodate in the areas outside (from,to)
 */
int nobh_write_begin(struct file *file, struct address_space *mapping,
			loff_t pos, unsigned len, unsigned flags,
			struct page **pagep, void **fsdata,
			get_block_t *get_block)
{
	struct inode *inode = mapping->host;
	const unsigned blkbits = inode->i_blkbits;
	const unsigned blocksize = 1 << blkbits;
	struct buffer_head *head, *bh;
	struct page *page;
	pgoff_t index;
	unsigned from, to;
	unsigned block_in_page;
	unsigned block_start, block_end;
	sector_t block_in_file;
	int nr_reads = 0;
	int ret = 0;
	int is_mapped_to_disk = 1;

	index = pos >> PAGE_CACHE_SHIFT;
	from = pos & (PAGE_CACHE_SIZE - 1);
	to = from + len;

	page = grab_cache_page_write_begin(mapping, index, flags);
	if (!page)
		return -ENOMEM;
	*pagep = page;
	*fsdata = NULL;

	if (page_has_buffers(page)) {
		unlock_page(page);
		page_cache_release(page);
		*pagep = NULL;
		return block_write_begin(file, mapping, pos, len, flags, pagep,
					fsdata, get_block);
	}

	if (PageMappedToDisk(page))
		return 0;

	/*
	 * Allocate buffers so that we can keep track of state, and potentially
	 * attach them to the page if an error occurs. In the common case of
	 * no error, they will just be freed again without ever being attached
	 * to the page (which is all OK, because we're under the page lock).
	 *
	 * Be careful: the buffer linked list is a NULL terminated one, rather
	 * than the circular one we're used to.
	 */
	head = alloc_page_buffers(page, blocksize, 0);
	if (!head) {
		ret = -ENOMEM;
		goto out_release;
	}

	block_in_file = (sector_t)page->index << (PAGE_CACHE_SHIFT - blkbits);

	/*
	 * We loop across all blocks in the page, whether or not they are
	 * part of the affected region.  This is so we can discover if the
	 * page is fully mapped-to-disk.
	 */
	for (block_start = 0, block_in_page = 0, bh = head;
		  block_start < PAGE_CACHE_SIZE;
		  block_in_page++, block_start += blocksize, bh = bh->b_this_page) {
		int create;

		block_end = block_start + blocksize;
		bh->b_state = 0;
		create = 1;
		if (block_start >= to)
			create = 0;
		ret = get_block(inode, block_in_file + block_in_page,
					bh, create);
		if (ret)
			goto failed;
		if (!buffer_mapped(bh))
			is_mapped_to_disk = 0;
		if (buffer_new(bh))
			unmap_underlying_metadata(bh->b_bdev, bh->b_blocknr);
		if (PageUptodate(page)) {
			set_buffer_uptodate(bh);
			continue;
		}
		if (buffer_new(bh) || !buffer_mapped(bh)) {
			zero_user_segments(page, block_start, from,
							to, block_end);
			continue;
		}
		if (buffer_uptodate(bh))
			continue;	/* reiserfs does this */
		if (block_start < from || block_end > to) {
			lock_buffer(bh);
			bh->b_end_io = end_buffer_read_nobh;
			submit_bh(READ, bh);
			nr_reads++;
		}
	}

	if (nr_reads) {
		/*
		 * The page is locked, so these buffers are protected from
		 * any VM or truncate activity.  Hence we don't need to care
		 * for the buffer_head refcounts.
		 */
		for (bh = head; bh; bh = bh->b_this_page) {
			wait_on_buffer(bh);
			if (!buffer_uptodate(bh))
				ret = -EIO;
		}
		if (ret)
			goto failed;
	}

	if (is_mapped_to_disk)
		SetPageMappedToDisk(page);

	*fsdata = head; /* to be released by nobh_write_end */

	return 0;

failed:
	BUG_ON(!ret);
	/*
	 * Error recovery is a bit difficult. We need to zero out blocks that
	 * were newly allocated, and dirty them to ensure they get written out.
	 * Buffers need to be attached to the page at this point, otherwise
	 * the handling of potential IO errors during writeout would be hard
	 * (could try doing synchronous writeout, but what if that fails too?)
	 */
	attach_nobh_buffers(page, head);
	page_zero_new_buffers(page, from, to);

out_release:
	unlock_page(page);
	page_cache_release(page);
	*pagep = NULL;

	if (pos + len > inode->i_size)
		vmtruncate(inode, inode->i_size);

	return ret;
}
EXPORT_SYMBOL(nobh_write_begin);

int nobh_write_end(struct file *file, struct address_space *mapping,
			loff_t pos, unsigned len, unsigned copied,
			struct page *page, void *fsdata)
{
	struct inode *inode = page->mapping->host;
	struct buffer_head *head = fsdata;
	struct buffer_head *bh;
	BUG_ON(fsdata != NULL && page_has_buffers(page));

	if (unlikely(copied < len) && head)
		attach_nobh_buffers(page, head);
	if (page_has_buffers(page))
		return generic_write_end(file, mapping, pos, len,
					copied, page, fsdata);

	SetPageUptodate(page);
	set_page_dirty(page);
	if (pos+copied > inode->i_size) {
		i_size_write(inode, pos+copied);
		mark_inode_dirty(inode);
	}

	unlock_page(page);
	page_cache_release(page);

	while (head) {
		bh = head;
		head = head->b_this_page;
		free_buffer_head(bh);
	}

	return copied;
}
EXPORT_SYMBOL(nobh_write_end);

/*
 * nobh_writepage() - based on block_full_write_page() except
 * that it tries to operate without attaching bufferheads to
 * the page.
 */
int nobh_writepage(struct page *page, get_block_t *get_block,
			struct writeback_control *wbc)
{
	struct inode * const inode = page->mapping->host;
	loff_t i_size = i_size_read(inode);
	const pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT;
	unsigned offset;
	int ret;

	/* Is the page fully inside i_size? */
	if (page->index < end_index)
		goto out;

	/* Is the page fully outside i_size? (truncate in progress) */
	offset = i_size & (PAGE_CACHE_SIZE-1);
	if (page->index >= end_index+1 || !offset) {
		/*
		 * The page may have dirty, unmapped buffers.  For example,
		 * they may have been added in ext3_writepage().  Make them
		 * freeable here, so the page does not leak.
		 */
#if 0
		/* Not really sure about this  - do we need this ? */
		if (page->mapping->a_ops->invalidatepage)
			page->mapping->a_ops->invalidatepage(page, offset);
#endif
		unlock_page(page);
		return 0; /* don't care */
	}

	/*
	 * The page straddles i_size.  It must be zeroed out on each and every
	 * writepage invocation because it may be mmapped.  "A file is mapped
	 * in multiples of the page size.  For a file that is not a multiple of
	 * the  page size, the remaining memory is zeroed when mapped, and
	 * writes to that region are not written out to the file."
	 */
	zero_user_segment(page, offset, PAGE_CACHE_SIZE);
out:
	ret = mpage_writepage(page, get_block, wbc);
	if (ret == -EAGAIN)
		ret = __block_write_full_page(inode, page, get_block, wbc,
					      end_buffer_async_write);
	return ret;
}
EXPORT_SYMBOL(nobh_writepage);

int nobh_truncate_page(struct address_space *mapping,
			loff_t from, get_block_t *get_block)
{
	pgoff_t index = from >> PAGE_CACHE_SHIFT;
	unsigned offset = from & (PAGE_CACHE_SIZE-1);
	unsigned blocksize;
	sector_t iblock;
	unsigned length, pos;
	struct inode *inode = mapping->host;
	struct page *page;
	struct buffer_head map_bh;
	int err;

	blocksize = 1 << inode->i_blkbits;
	length = offset & (blocksize - 1);

	/* Block boundary? Nothing to do */
	if (!length)
		return 0;

	length = blocksize - length;
	iblock = (sector_t)index << (PAGE_CACHE_SHIFT - inode->i_blkbits);

	page = grab_cache_page(mapping, index);
	err = -ENOMEM;
	if (!page)
		goto out;

	if (page_has_buffers(page)) {
has_buffers:
		unlock_page(page);
		page_cache_release(page);
		return block_truncate_page(mapping, from, get_block);
	}

	/* Find the buffer that contains "offset" */
	pos = blocksize;
	while (offset >= pos) {
		iblock++;
		pos += blocksize;
	}

	map_bh.b_size = blocksize;
	map_bh.b_state = 0;
	err = get_block(inode, iblock, &map_bh, 0);
	if (err)
		goto unlock;
	/* unmapped? It's a hole - nothing to do */
	if (!buffer_mapped(&map_bh))
		goto unlock;

	/* Ok, it's mapped. Make sure it's up-to-date */
	if (!PageUptodate(page)) {
		err = mapping->a_ops->readpage(NULL, page);
		if (err) {
			page_cache_release(page);
			goto out;
		}
		lock_page(page);
		if (!PageUptodate(page)) {
			err = -EIO;
			goto unlock;
		}
		if (page_has_buffers(page))
			goto has_buffers;
	}
	zero_user(page, offset, length);
	set_page_dirty(page);
	err = 0;

unlock:
	unlock_page(page);
	page_cache_release(page);
out:
	return err;
}
EXPORT_SYMBOL(nobh_truncate_page);

int block_truncate_page(struct address_space *mapping,
			loff_t from, get_block_t *get_block)
{
	pgoff_t index = from >> PAGE_CACHE_SHIFT;
	unsigned offset = from & (PAGE_CACHE_SIZE-1);
	unsigned blocksize;
	sector_t iblock;
	unsigned length, pos;
	struct inode *inode = mapping->host;
	struct page *page;
	struct buffer_head *bh;
	int err;

	blocksize = 1 << inode->i_blkbits;
	length = offset & (blocksize - 1);

	/* Block boundary? Nothing to do */
	if (!length)
		return 0;

	length = blocksize - length;
	iblock = (sector_t)index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
	
	page = grab_cache_page(mapping, index);
	err = -ENOMEM;
	if (!page)
		goto out;

	if (!page_has_buffers(page))
		create_empty_buffers(page, blocksize, 0);

	/* Find the buffer that contains "offset" */
	bh = page_buffers(page);
	pos = blocksize;
	while (offset >= pos) {
		bh = bh->b_this_page;
		iblock++;
		pos += blocksize;
	}

	err = 0;
	if (!buffer_mapped(bh)) {
		WARN_ON(bh->b_size != blocksize);
		err = get_block(inode, iblock, bh, 0);
		if (err)
			goto unlock;
		/* unmapped? It's a hole - nothing to do */
		if (!buffer_mapped(bh))
			goto unlock;
	}

	/* Ok, it's mapped. Make sure it's up-to-date */
	if (PageUptodate(page))
		set_buffer_uptodate(bh);

	if (!buffer_uptodate(bh) && !buffer_delay(bh) && !buffer_unwritten(bh)) {
		err = -EIO;
		ll_rw_block(READ, 1, &bh);
		wait_on_buffer(bh);
		/* Uhhuh. Read error. Complain and punt. */
		if (!buffer_uptodate(bh))
			goto unlock;
	}

	zero_user(page, offset, length);
	mark_buffer_dirty(bh);
	err = 0;

unlock:
	unlock_page(page);
	page_cache_release(page);
out:
	return err;
}
EXPORT_SYMBOL(block_truncate_page);

/*
 * The generic ->writepage function for buffer-backed address_spaces
 * this form passes in the end_io handler used to finish the IO.
 */
int block_write_full_page_endio(struct page *page, get_block_t *get_block,
			struct writeback_control *wbc, bh_end_io_t *handler)
{
	struct inode * const inode = page->mapping->host;
	loff_t i_size = i_size_read(inode);
	const pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT;
	unsigned offset;

	/* Is the page fully inside i_size? */
	if (page->index < end_index)
		return __block_write_full_page(inode, page, get_block, wbc,
					       handler);

	/* Is the page fully outside i_size? (truncate in progress) */
	offset = i_size & (PAGE_CACHE_SIZE-1);
	if (page->index >= end_index+1 || !offset) {
		/*
		 * The page may have dirty, unmapped buffers.  For example,
		 * they may have been added in ext3_writepage().  Make them
		 * freeable here, so the page does not leak.
		 */
		do_invalidatepage(page, 0);
		unlock_page(page);
		return 0; /* don't care */
	}

	/*
	 * The page straddles i_size.  It must be zeroed out on each and every
	 * writepage invocation because it may be mmapped.  "A file is mapped
	 * in multiples of the page size.  For a file that is not a multiple of
	 * the  page size, the remaining memory is zeroed when mapped, and
	 * writes to that region are not written out to the file."
	 */
	zero_user_segment(page, offset, PAGE_CACHE_SIZE);
	return __block_write_full_page(inode, page, get_block, wbc, handler);
}
EXPORT_SYMBOL(block_write_full_page_endio);

/*
 * The generic ->writepage function for buffer-backed address_spaces
 */
int block_write_full_page(struct page *page, get_block_t *get_block,
			struct writeback_control *wbc)
{
	return block_write_full_page_endio(page, get_block, wbc,
					   end_buffer_async_write);
}
EXPORT_SYMBOL(block_write_full_page);

sector_t generic_block_bmap(struct address_space *mapping, sector_t block,
			    get_block_t *get_block)
{
	struct buffer_head tmp;
	struct inode *inode = mapping->host;
	tmp.b_state = 0;
	tmp.b_blocknr = 0;
	tmp.b_size = 1 << inode->i_blkbits;
	get_block(inode, block, &tmp, 0);
	return tmp.b_blocknr;
}
EXPORT_SYMBOL(generic_block_bmap);

static void end_bio_bh_io_sync(struct bio *bio, int err)
{
	struct buffer_head *bh = bio->bi_private;

	if (err == -EOPNOTSUPP) {
		set_bit(BIO_EOPNOTSUPP, &bio->bi_flags);
		set_bit(BH_Eopnotsupp, &bh->b_state);
	}

	if (unlikely (test_bit(BIO_QUIET,&bio->bi_flags)))
		set_bit(BH_Quiet, &bh->b_state);

	bh->b_end_io(bh, test_bit(BIO_UPTODATE, &bio->bi_flags));
	bio_put(bio);
}

int submit_bh(int rw, struct buffer_head * bh)
{
	struct bio *bio;
	int ret = 0;

	BUG_ON(!buffer_locked(bh));
	BUG_ON(!buffer_mapped(bh));
	BUG_ON(!bh->b_end_io);
	BUG_ON(buffer_delay(bh));
	BUG_ON(buffer_unwritten(bh));

	/*
	 * Mask in barrier bit for a write (could be either a WRITE or a
	 * WRITE_SYNC
	 */
	if (buffer_ordered(bh) && (rw & WRITE))
		rw |= WRITE_BARRIER;

	/*
	 * Only clear out a write error when rewriting
	 */
	if (test_set_buffer_req(bh) && (rw & WRITE))
		clear_buffer_write_io_error(bh);

	/*
	 * from here on down, it's all bio -- do the initial mapping,
	 * submit_bio -> generic_make_request may further map this bio around
	 */
	bio = bio_alloc(GFP_NOIO, 1);

	bio->bi_sector = bh->b_blocknr * (bh->b_size >> 9);
	bio->bi_bdev = bh->b_bdev;
	bio->bi_io_vec[0].bv_page = bh->b_page;
	bio->bi_io_vec[0].bv_len = bh->b_size;
	bio->bi_io_vec[0].bv_offset = bh_offset(bh);

	bio->bi_vcnt = 1;
	bio->bi_idx = 0;
	bio->bi_size = bh->b_size;

	bio->bi_end_io = end_bio_bh_io_sync;
	bio->bi_private = bh;

	bio_get(bio);
	submit_bio(rw, bio);

	if (bio_flagged(bio, BIO_EOPNOTSUPP))
		ret = -EOPNOTSUPP;

	bio_put(bio);
	return ret;
}
EXPORT_SYMBOL(submit_bh);

/**