inode.c

来自「Linux Kernel 2.6.9 for OMAP1710」· C语言 代码 · 共 2,219 行 · 第 1/5 页

 *   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 ext3_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 (ext3_journal_current_handle())
		goto out_fail;

	handle = ext3_journal_start(inode, ext3_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, ext3_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, journal_dirty_data_fn);
		if (!ret)
			ret = err;
	}
	walk_page_buffers(handle, page_bufs, 0,
			PAGE_CACHE_SIZE, NULL, bput_one);
	err = ext3_journal_stop(handle);
	if (!ret)
		ret = err;
	return ret;

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

static int ext3_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 (ext3_journal_current_handle())
		goto out_fail;

	handle = ext3_journal_start(inode, ext3_writepage_trans_blocks(inode));
	if (IS_ERR(handle)) {
		ret = PTR_ERR(handle);
		goto out_fail;
	}

	ret = block_write_full_page(page, ext3_get_block, wbc);
	err = ext3_journal_stop(handle);
	if (!ret)
		ret = err;
	return ret;

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

static int ext3_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 (ext3_journal_current_handle())
		goto no_write;

	handle = ext3_journal_start(inode, ext3_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,
					ext3_get_block);
		if (ret != 0)
			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, commit_write_fn);
		if (ret == 0)
			ret = err;
		EXT3_I(inode)->i_state |= EXT3_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, ext3_get_block, wbc);
	}
	err = ext3_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 ext3_readpage(struct file *file, struct page *page)
{
	return mpage_readpage(page, ext3_get_block);
}

static int
ext3_readpages(struct file *file, struct address_space *mapping,
		struct list_head *pages, unsigned nr_pages)
{
	return mpage_readpages(mapping, pages, nr_pages, ext3_get_block);
}

static int ext3_invalidatepage(struct page *page, unsigned long offset)
{
	journal_t *journal = EXT3_JOURNAL(page->mapping->host);

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

	return journal_invalidatepage(journal, page, offset);
}

static int ext3_releasepage(struct page *page, int wait)
{
	journal_t *journal = EXT3_JOURNAL(page->mapping->host);

	WARN_ON(PageChecked(page));
	return 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 ext3_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 ext3_inode_info *ei = EXT3_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 = ext3_journal_start(inode, DIO_CREDITS);
		if (IS_ERR(handle)) {
			ret = PTR_ERR(handle);
			goto out;
		}
		if (final_size > inode->i_size) {
			ret = ext3_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,
				 ext3_direct_io_get_blocks, NULL);

	/*
	 * Reacquire the handle: ext3_direct_io_get_block() can restart the
	 * transaction
	 */
	handle = journal_current_handle();

out_stop:
	if (handle) {
		int err;

		if (orphan) 
			ext3_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);
				err = ext3_mark_inode_dirty(handle, inode);
				if (!ret) 
					ret = err;
			}
		}
		err = ext3_journal_stop(handle);
		if (ret == 0)
			ret = err;
	}
out:
	return ret;
}

/*
 * Pages can be marked dirty completely asynchronously from ext3'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 ext3_journalled_set_page_dirty(struct page *page)
{
	SetPageChecked(page);
	return __set_page_dirty_nobuffers(page);
}

static struct address_space_operations ext3_ordered_aops = {
	.readpage	= ext3_readpage,
	.readpages	= ext3_readpages,
	.writepage	= ext3_ordered_writepage,
	.sync_page	= block_sync_page,
	.prepare_write	= ext3_prepare_write,
	.commit_write	= ext3_ordered_commit_write,
	.bmap		= ext3_bmap,
	.invalidatepage	= ext3_invalidatepage,
	.releasepage	= ext3_releasepage,
	.direct_IO	= ext3_direct_IO,
};

static struct address_space_operations ext3_writeback_aops = {
	.readpage	= ext3_readpage,
	.readpages	= ext3_readpages,
	.writepage	= ext3_writeback_writepage,
	.sync_page	= block_sync_page,
	.prepare_write	= ext3_prepare_write,
	.commit_write	= ext3_writeback_commit_write,
	.bmap		= ext3_bmap,
	.invalidatepage	= ext3_invalidatepage,
	.releasepage	= ext3_releasepage,
	.direct_IO	= ext3_direct_IO,
};

static struct address_space_operations ext3_journalled_aops = {
	.readpage	= ext3_readpage,
	.readpages	= ext3_readpages,
	.writepage	= ext3_journalled_writepage,
	.sync_page	= block_sync_page,
	.prepare_write	= ext3_prepare_write,
	.commit_write	= ext3_journalled_commit_write,
	.set_page_dirty	= ext3_journalled_set_page_dirty,
	.bmap		= ext3_bmap,
	.invalidatepage	= ext3_invalidatepage,
	.releasepage	= ext3_releasepage,
};

void ext3_set_aops(struct inode *inode)
{
	if (ext3_should_order_data(inode))
		inode->i_mapping->a_ops = &ext3_ordered_aops;
	else if (ext3_should_writeback_data(inode))
		inode->i_mapping->a_ops = &ext3_writeback_aops;
	else
		inode->i_mapping->a_ops = &ext3_journalled_aops;
}

/*
 * ext3_block_truncate_page() zeroes out a mapping from file offset `from'
 * up to the end of the block which corresponds to `from'.
 * This required during truncate. We need to physically zero the tail end
 * of that block so it doesn't yield old data if the file is later grown.
 */
static int ext3_block_truncate_page(handle_t *handle, struct page *page,
		struct address_space *mapping, loff_t from)
{
	unsigned long index = from >> PAGE_CACHE_SHIFT;
	unsigned offset = from & (PAGE_CACHE_SIZE-1);
	unsigned blocksize, iblock, length, pos;
	struct inode *inode = mapping->host;
	struct buffer_head *bh;
	int err;
	void *kaddr;

	blocksize = inode->i_sb->s_blocksize;
	length = blocksize - (offset & (blocksize - 1));
	iblock = index << (PAGE_CACHE_SHIFT - inode->i_sb->s_blocksize_bits);

	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_freed(bh)) {
		BUFFER_TRACE(bh, "freed: skip");
		goto unlock;
	}

	if (!buffer_mapped(bh)) {
		BUFFER_TRACE(bh, "unmapped");
		ext3_get_block(inode, iblock, bh, 0);
		/* unmapped? It's a hole - nothing to do */
		if (!buffer_mapped(bh)) {
			BUFFER_TRACE(bh, "still unmapped");
			goto unlock;
		}
	}

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

	if (!buffer_uptodate(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;
	}

	if (ext3_should_journal_data(inode)) {
		BUFFER_TRACE(bh, "get write access");
		err = ext3_journal_get_write_access(handle, bh);
		if (err)
			goto unlock;
	}

	kaddr = kmap_atomic(page, KM_USER0);
	memset(kaddr + offset, 0, length);
	flush_dcache_page(page);
	kunmap_atomic(kaddr, KM_USER0);

	BUFFER_TRACE(bh, "zeroed end of block");

	err = 0;
	if (ext3_should_journal_data(inode)) {
		err = ext3_journal_dirty_metadata(handle, bh);
	} else {
		if (ext3_should_order_data(inode))
			err = ext3_journal_dirty_data(handle, bh);
		mark_buffer_dirty(bh);
	}

unlock:
	unlock_page(page);
	page_cache_release(page);
	return err;
}

/*
 * Probably it should be a library function... search for first non-zero word
 * or memcmp with zero_page, whatever is better for particular architecture.
 * Linus?
 */
static inline int all_zeroes(__le32 *p, __le32 *q)