inode.c

linux 内核源代码

	ret = walk_page_buffers(handle, page_buffers(page), from,
				to, &partial, write_end_fn);
	if (!partial)
		SetPageUptodate(page);
	if (pos+copied > inode->i_size)
		i_size_write(inode, pos+copied);
	EXT4_I(inode)->i_state |= EXT4_STATE_JDATA;
	if (inode->i_size > EXT4_I(inode)->i_disksize) {
		EXT4_I(inode)->i_disksize = inode->i_size;
		ret2 = ext4_mark_inode_dirty(handle, inode);
		if (!ret)
			ret = ret2;
	}

	ret2 = ext4_journal_stop(handle);
	if (!ret)
		ret = ret2;
	unlock_page(page);
	page_cache_release(page);

	return ret ? ret : copied;
}

/*
 * bmap() is special.  It gets used by applications such as lilo and by
 * the swapper to find the on-disk block of a specific piece of data.
 *
 * Naturally, this is dangerous if the block concerned is still in the
 * journal.  If somebody makes a swapfile on an ext4 data-journaling
 * filesystem and enables swap, then they may get a nasty shock when the
 * data getting swapped to that swapfile suddenly gets overwritten by
 * the original zero's written out previously to the journal and
 * awaiting writeback in the kernel's buffer cache.
 *
 * So, if we see any bmap calls here on a modified, data-journaled file,
 * take extra steps to flush any blocks which might be in the cache.
 */
static sector_t ext4_bmap(struct address_space *mapping, sector_t block)
{
	struct inode *inode = mapping->host;
	journal_t *journal;
	int err;

	if (EXT4_I(inode)->i_state & EXT4_STATE_JDATA) {
		/*
		 * This is a REALLY heavyweight approach, but the use of
		 * bmap on dirty files is expected to be extremely rare:
		 * only if we run lilo or swapon on a freshly made file
		 * do we expect this to happen.
		 *
		 * (bmap requires CAP_SYS_RAWIO so this does not
		 * represent an unprivileged user DOS attack --- we'd be
		 * in trouble if mortal users could trigger this path at
		 * will.)
		 *
		 * NB. EXT4_STATE_JDATA is not set on files other than
		 * regular files.  If somebody wants to bmap a directory
		 * or symlink and gets confused because the buffer
		 * hasn't yet been flushed to disk, they deserve
		 * everything they get.
		 */

		EXT4_I(inode)->i_state &= ~EXT4_STATE_JDATA;
		journal = EXT4_JOURNAL(inode);
		jbd2_journal_lock_updates(journal);
		err = jbd2_journal_flush(journal);
		jbd2_journal_unlock_updates(journal);

		if (err)
			return 0;
	}

	return generic_block_bmap(mapping,block,ext4_get_block);
}

static int bget_one(handle_t *handle, struct buffer_head *bh)
{
	get_bh(bh);
	return 0;
}

static int bput_one(handle_t *handle, struct buffer_head *bh)
{
	put_bh(bh);
	return 0;
}

static int jbd2_journal_dirty_data_fn(handle_t *handle, struct buffer_head *bh)
{
	if (buffer_mapped(bh))
		return ext4_journal_dirty_data(handle, bh);
	return 0;
}

/*
 * Note that we always start a transaction even if we're not journalling
 * data.  This is to preserve ordering: any hole instantiation within
 * __block_write_full_page -> ext4_get_block() should be journalled
 * along with the data so we don't crash and then get metadata which
 * refers to old data.
 *
 * In all journalling modes block_write_full_page() will start the I/O.
 *
 * Problem:
 *
 *	ext4_writepage() -> kmalloc() -> __alloc_pages() -> page_launder() ->
 *		ext4_writepage()
 *
 * Similar for:
 *
 *	ext4_file_write() -> generic_file_write() -> __alloc_pages() -> ...
 *
 * Same applies to ext4_get_block().  We will deadlock on various things like
 * lock_journal and i_truncate_mutex.
 *
 * Setting PF_MEMALLOC here doesn't work - too many internal memory
 * allocations fail.
 *
 * 16May01: If we're reentered then journal_current_handle() will be
 *	    non-zero. We simply *return*.
 *
 * 1 July 2001: @@@ FIXME:
 *   In journalled data mode, a data buffer may be metadata against the
 *   current transaction.  But the same file is part of a shared mapping
 *   and someone does a writepage() on it.
 *
 *   We will move the buffer onto the async_data list, but *after* it has
 *   been dirtied. So there's a small window where we have dirty data on
 *   BJ_Metadata.
 *
 *   Note that this only applies to the last partial page in the file.  The
 *   bit which block_write_full_page() uses prepare/commit for.  (That's
 *   broken code anyway: it's wrong for msync()).
 *
 *   It's a rare case: affects the final partial page, for journalled data
 *   where the file is subject to bith write() and writepage() in the same
 *   transction.  To fix it we'll need a custom block_write_full_page().
 *   We'll probably need that anyway for journalling writepage() output.
 *
 * We don't honour synchronous mounts for writepage().  That would be
 * disastrous.  Any write() or metadata operation will sync the fs for
 * us.
 *
 * AKPM2: if all the page's buffers are mapped to disk and !data=journal,
 * we don't need to open a transaction here.
 */
static int ext4_ordered_writepage(struct page *page,
				struct writeback_control *wbc)
{
	struct inode *inode = page->mapping->host;
	struct buffer_head *page_bufs;
	handle_t *handle = NULL;
	int ret = 0;
	int err;

	J_ASSERT(PageLocked(page));

	/*
	 * We give up here if we're reentered, because it might be for a
	 * different filesystem.
	 */
	if (ext4_journal_current_handle())
		goto out_fail;

	handle = ext4_journal_start(inode, ext4_writepage_trans_blocks(inode));

	if (IS_ERR(handle)) {
		ret = PTR_ERR(handle);
		goto out_fail;
	}

	if (!page_has_buffers(page)) {
		create_empty_buffers(page, inode->i_sb->s_blocksize,
				(1 << BH_Dirty)|(1 << BH_Uptodate));
	}
	page_bufs = page_buffers(page);
	walk_page_buffers(handle, page_bufs, 0,
			PAGE_CACHE_SIZE, NULL, bget_one);

	ret = block_write_full_page(page, ext4_get_block, wbc);

	/*
	 * The page can become unlocked at any point now, and
	 * truncate can then come in and change things.  So we
	 * can't touch *page from now on.  But *page_bufs is
	 * safe due to elevated refcount.
	 */

	/*
	 * And attach them to the current transaction.  But only if
	 * block_write_full_page() succeeded.  Otherwise they are unmapped,
	 * and generally junk.
	 */
	if (ret == 0) {
		err = walk_page_buffers(handle, page_bufs, 0, PAGE_CACHE_SIZE,
					NULL, jbd2_journal_dirty_data_fn);
		if (!ret)
			ret = err;
	}
	walk_page_buffers(handle, page_bufs, 0,
			PAGE_CACHE_SIZE, NULL, bput_one);
	err = ext4_journal_stop(handle);
	if (!ret)
		ret = err;
	return ret;

out_fail:
	redirty_page_for_writepage(wbc, page);
	unlock_page(page);
	return ret;
}

static int ext4_writeback_writepage(struct page *page,
				struct writeback_control *wbc)
{
	struct inode *inode = page->mapping->host;
	handle_t *handle = NULL;
	int ret = 0;
	int err;

	if (ext4_journal_current_handle())
		goto out_fail;

	handle = ext4_journal_start(inode, ext4_writepage_trans_blocks(inode));
	if (IS_ERR(handle)) {
		ret = PTR_ERR(handle);
		goto out_fail;
	}

	if (test_opt(inode->i_sb, NOBH) && ext4_should_writeback_data(inode))
		ret = nobh_writepage(page, ext4_get_block, wbc);
	else
		ret = block_write_full_page(page, ext4_get_block, wbc);

	err = ext4_journal_stop(handle);
	if (!ret)
		ret = err;
	return ret;

out_fail:
	redirty_page_for_writepage(wbc, page);
	unlock_page(page);
	return ret;
}

static int ext4_journalled_writepage(struct page *page,
				struct writeback_control *wbc)
{
	struct inode *inode = page->mapping->host;
	handle_t *handle = NULL;
	int ret = 0;
	int err;

	if (ext4_journal_current_handle())
		goto no_write;

	handle = ext4_journal_start(inode, ext4_writepage_trans_blocks(inode));
	if (IS_ERR(handle)) {
		ret = PTR_ERR(handle);
		goto no_write;
	}

	if (!page_has_buffers(page) || PageChecked(page)) {
		/*
		 * It's mmapped pagecache.  Add buffers and journal it.  There
		 * doesn't seem much point in redirtying the page here.
		 */
		ClearPageChecked(page);
		ret = block_prepare_write(page, 0, PAGE_CACHE_SIZE,
					ext4_get_block);
		if (ret != 0) {
			ext4_journal_stop(handle);
			goto out_unlock;
		}
		ret = walk_page_buffers(handle, page_buffers(page), 0,
			PAGE_CACHE_SIZE, NULL, do_journal_get_write_access);

		err = walk_page_buffers(handle, page_buffers(page), 0,
				PAGE_CACHE_SIZE, NULL, write_end_fn);
		if (ret == 0)
			ret = err;
		EXT4_I(inode)->i_state |= EXT4_STATE_JDATA;
		unlock_page(page);
	} else {
		/*
		 * It may be a page full of checkpoint-mode buffers.  We don't
		 * really know unless we go poke around in the buffer_heads.
		 * But block_write_full_page will do the right thing.
		 */
		ret = block_write_full_page(page, ext4_get_block, wbc);
	}
	err = ext4_journal_stop(handle);
	if (!ret)
		ret = err;
out:
	return ret;

no_write:
	redirty_page_for_writepage(wbc, page);
out_unlock:
	unlock_page(page);
	goto out;
}

static int ext4_readpage(struct file *file, struct page *page)
{
	return mpage_readpage(page, ext4_get_block);
}

static int
ext4_readpages(struct file *file, struct address_space *mapping,
		struct list_head *pages, unsigned nr_pages)
{
	return mpage_readpages(mapping, pages, nr_pages, ext4_get_block);
}

static void ext4_invalidatepage(struct page *page, unsigned long offset)
{
	journal_t *journal = EXT4_JOURNAL(page->mapping->host);

	/*
	 * If it's a full truncate we just forget about the pending dirtying
	 */
	if (offset == 0)
		ClearPageChecked(page);

	jbd2_journal_invalidatepage(journal, page, offset);
}

static int ext4_releasepage(struct page *page, gfp_t wait)
{
	journal_t *journal = EXT4_JOURNAL(page->mapping->host);

	WARN_ON(PageChecked(page));
	if (!page_has_buffers(page))
		return 0;
	return jbd2_journal_try_to_free_buffers(journal, page, wait);
}

/*
 * If the O_DIRECT write will extend the file then add this inode to the
 * orphan list.  So recovery will truncate it back to the original size
 * if the machine crashes during the write.
 *
 * If the O_DIRECT write is intantiating holes inside i_size and the machine
 * crashes then stale disk data _may_ be exposed inside the file.
 */
static ssize_t ext4_direct_IO(int rw, struct kiocb *iocb,
			const struct iovec *iov, loff_t offset,
			unsigned long nr_segs)
{
	struct file *file = iocb->ki_filp;
	struct inode *inode = file->f_mapping->host;
	struct ext4_inode_info *ei = EXT4_I(inode);
	handle_t *handle = NULL;
	ssize_t ret;
	int orphan = 0;
	size_t count = iov_length(iov, nr_segs);

	if (rw == WRITE) {
		loff_t final_size = offset + count;

		handle = ext4_journal_start(inode, DIO_CREDITS);
		if (IS_ERR(handle)) {
			ret = PTR_ERR(handle);
			goto out;
		}
		if (final_size > inode->i_size) {
			ret = ext4_orphan_add(handle, inode);
			if (ret)
				goto out_stop;
			orphan = 1;
			ei->i_disksize = inode->i_size;
		}
	}

	ret = blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov,
				 offset, nr_segs,
				 ext4_get_block, NULL);

	/*
	 * Reacquire the handle: ext4_get_block() can restart the transaction
	 */
	handle = ext4_journal_current_handle();

out_stop:
	if (handle) {
		int err;

		if (orphan && inode->i_nlink)
			ext4_orphan_del(handle, inode);
		if (orphan && ret > 0) {
			loff_t end = offset + ret;
			if (end > inode->i_size) {
				ei->i_disksize = end;
				i_size_write(inode, end);
				/*
				 * We're going to return a positive `ret'
				 * here due to non-zero-length I/O, so there's
				 * no way of reporting error returns from
				 * ext4_mark_inode_dirty() to userspace.  So
				 * ignore it.
				 */
				ext4_mark_inode_dirty(handle, inode);
			}
		}
		err = ext4_journal_stop(handle);
		if (ret == 0)
			ret = err;
	}
out:
	return ret;
}

/*
 * Pages can be marked dirty completely asynchronously from ext4's journalling
 * activity.  By filemap_sync_pte(), try_to_unmap_one(), etc.  We cannot do
 * much here because ->set_page_dirty is called under VFS locks.  The page is
 * not necessarily locked.
 *
 * We cannot just dirty the page and leave attached buffers clean, because the
 * buffers' dirty state is "definitive".  We cannot just set the buffers dirty
 * or jbddirty because all the journalling code will explode.
 *
 * So what we do is to mark the page "pending dirty" and next time writepage
 * is called, propagate that into the buffers appropriately.
 */
static int ext4_journalled_set_page_dirty(struct page *page)
{
	SetPageChecked(page);
	return __set_page_dirty_nobuffers(page);
}

static const struct address_space_operations ext4_ordered_aops = {
	.readpage	= ext4_readpage,
	.readpages	= ext4_readpages,
	.writepage	= ext4_ordered_writepage,
	.sync_page	= block_sync_page,
	.write_begin	= ext4_write_begin,
	.write_end	= ext4_ordered_write_end,
	.bmap		= ext4_bmap,
	.invalidatepage	= ext4_invalidatepage,
	.releasepage	= ext4_releasepage,
	.direct_IO	= ext4_direct_IO,
	.migratepage	= buffer_migrate_page,