inode.c

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

	if (handle->h_transaction->t_state == T_LOCKED) {
		/*
		 * Huge direct-io writes can hold off commits for long
		 * periods of time.  Let this commit run.
		 */
		ext3_journal_stop(handle);
		handle = ext3_journal_start(inode, DIO_CREDITS);
		if (IS_ERR(handle))
			ret = PTR_ERR(handle);
		goto get_block;
	}

	if (handle->h_buffer_credits <= EXT3_RESERVE_TRANS_BLOCKS) {
		/*
		 * Getting low on buffer credits...
		 */
		ret = ext3_journal_extend(handle, DIO_CREDITS);
		if (ret > 0) {
			/*
			 * Couldn't extend the transaction.  Start a new one.
			 */
			ret = ext3_journal_restart(handle, DIO_CREDITS);
		}
	}

get_block:
	if (ret == 0)
		ret = ext3_get_block_handle(handle, inode, iblock,
					bh_result, create, 0);
	bh_result->b_size = (1 << inode->i_blkbits);
	return ret;
}

/*
 * `handle' can be NULL if create is zero
 */
struct buffer_head *ext3_getblk(handle_t *handle, struct inode * inode,
				long block, int create, int * errp)
{
	struct buffer_head dummy;
	int fatal = 0, err;

	J_ASSERT(handle != NULL || create == 0);

	dummy.b_state = 0;
	dummy.b_blocknr = -1000;
	buffer_trace_init(&dummy.b_history);
	*errp = ext3_get_block_handle(handle, inode, block, &dummy, create, 1);
	if (!*errp && buffer_mapped(&dummy)) {
		struct buffer_head *bh;
		bh = sb_getblk(inode->i_sb, dummy.b_blocknr);
		if (buffer_new(&dummy)) {
			J_ASSERT(create != 0);
			J_ASSERT(handle != 0);

			/* Now that we do not always journal data, we
			   should keep in mind whether this should
			   always journal the new buffer as metadata.
			   For now, regular file writes use
			   ext3_get_block instead, so it's not a
			   problem. */
			lock_buffer(bh);
			BUFFER_TRACE(bh, "call get_create_access");
			fatal = ext3_journal_get_create_access(handle, bh);
			if (!fatal && !buffer_uptodate(bh)) {
				memset(bh->b_data, 0, inode->i_sb->s_blocksize);
				set_buffer_uptodate(bh);
			}
			unlock_buffer(bh);
			BUFFER_TRACE(bh, "call ext3_journal_dirty_metadata");
			err = ext3_journal_dirty_metadata(handle, bh);
			if (!fatal)
				fatal = err;
		} else {
			BUFFER_TRACE(bh, "not a new buffer");
		}
		if (fatal) {
			*errp = fatal;
			brelse(bh);
			bh = NULL;
		}
		return bh;
	}
	return NULL;
}

struct buffer_head *ext3_bread(handle_t *handle, struct inode * inode,
			       int block, int create, int *err)
{
	struct buffer_head * bh;
	int prev_blocks;

	prev_blocks = inode->i_blocks;

	bh = ext3_getblk (handle, inode, block, create, err);
	if (!bh)
		return bh;
#ifdef EXT3_PREALLOCATE
	/*
	 * If the inode has grown, and this is a directory, then use a few
	 * more of the preallocated blocks to keep directory fragmentation
	 * down.  The preallocated blocks are guaranteed to be contiguous.
	 */
	if (create &&
	    S_ISDIR(inode->i_mode) &&
	    inode->i_blocks > prev_blocks &&
	    EXT3_HAS_COMPAT_FEATURE(inode->i_sb,
				    EXT3_FEATURE_COMPAT_DIR_PREALLOC)) {
		int i;
		struct buffer_head *tmp_bh;

		for (i = 1;
		     EXT3_I(inode)->i_prealloc_count &&
		     i < EXT3_SB(inode->i_sb)->s_es->s_prealloc_dir_blocks;
		     i++) {
			/*
			 * ext3_getblk will zero out the contents of the
			 * directory for us
			 */
			tmp_bh = ext3_getblk(handle, inode,
						block+i, create, err);
			if (!tmp_bh) {
				brelse (bh);
				return 0;
			}
			brelse (tmp_bh);
		}
	}
#endif
	if (buffer_uptodate(bh))
		return bh;
	ll_rw_block (READ, 1, &bh);
	wait_on_buffer (bh);
	if (buffer_uptodate(bh))
		return bh;
	brelse (bh);
	*err = -EIO;
	return NULL;
}

static int walk_page_buffers(	handle_t *handle,
				struct buffer_head *head,
				unsigned from,
				unsigned to,
				int *partial,
				int (*fn)(	handle_t *handle,
						struct buffer_head *bh))
{
	struct buffer_head *bh;
	unsigned block_start, block_end;
	unsigned blocksize = head->b_size;
	int err, ret = 0;
	struct buffer_head *next;

	for (	bh = head, block_start = 0;
		ret == 0 && (bh != head || !block_start);
	    	block_start = block_end, bh = next)
	{
		next = bh->b_this_page;
		block_end = block_start + blocksize;
		if (block_end <= from || block_start >= to) {
			if (partial && !buffer_uptodate(bh))
				*partial = 1;
			continue;
		}
		err = (*fn)(handle, bh);
		if (!ret)
			ret = err;
	}
	return ret;
}

/*
 * To preserve ordering, it is essential that the hole instantiation and
 * the data write be encapsulated in a single transaction.  We cannot
 * close off a transaction and start a new one between the ext3_get_block()
 * and the commit_write().  So doing the journal_start at the start of
 * prepare_write() is the right place.
 *
 * Also, this function can nest inside ext3_writepage() ->
 * block_write_full_page(). In that case, we *know* that ext3_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, ext3 can be reentered when a transaction is open via
 * quota file writes.  If we were to commit the transaction while thus
 * reentered, there can be a deadlock - we would be holding a quota
 * lock, and the commit would never complete if another thread had a
 * transaction open and was blocking on the quota lock - a ranking
 * violation.
 *
 * So what we do is to rely on the fact that journal_stop/journal_start
 * will _not_ run commit under these circumstances because handle->h_ref
 * is elevated.  We'll still have enough credits for the tiny quotafile
 * write.  
 */

static int do_journal_get_write_access(handle_t *handle, 
				       struct buffer_head *bh)
{
	if (!buffer_mapped(bh) || buffer_freed(bh))
		return 0;
	return ext3_journal_get_write_access(handle, bh);
}

static int ext3_prepare_write(struct file *file, struct page *page,
			      unsigned from, unsigned to)
{
	struct inode *inode = page->mapping->host;
	int ret, needed_blocks = ext3_writepage_trans_blocks(inode);
	handle_t *handle;
	int retries = 0;

retry:
	handle = ext3_journal_start(inode, needed_blocks);
	if (IS_ERR(handle)) {
		ret = PTR_ERR(handle);
		goto out;
	}
	ret = block_prepare_write(page, from, to, ext3_get_block);
	if (ret)
		goto prepare_write_failed;

	if (ext3_should_journal_data(inode)) {
		ret = walk_page_buffers(handle, page_buffers(page),
				from, to, NULL, do_journal_get_write_access);
	}
prepare_write_failed:
	if (ret)
		ext3_journal_stop(handle);
	if (ret == -ENOSPC && ext3_should_retry_alloc(inode->i_sb, &retries))
		goto retry;
out:
	return ret;
}

static int
ext3_journal_dirty_data(handle_t *handle, struct buffer_head *bh)
{
	int err = journal_dirty_data(handle, bh);
	if (err)
		ext3_journal_abort_handle(__FUNCTION__, __FUNCTION__,
						bh, handle,err);
	return err;
}

/* For commit_write() in data=journal mode */
static int commit_write_fn(handle_t *handle, struct buffer_head *bh)
{
	if (!buffer_mapped(bh) || buffer_freed(bh))
		return 0;
	set_buffer_uptodate(bh);
	return ext3_journal_dirty_metadata(handle, bh);
}

/*
 * We need to pick up the new inode size which generic_commit_write gave us
 * `file' can be NULL - eg, when called from page_symlink().
 *
 * ext3 never places buffers on inode->i_mapping->private_list.  metadata
 * buffers are managed internally.
 */

static int ext3_ordered_commit_write(struct file *file, struct page *page,
			     unsigned from, unsigned to)
{
	handle_t *handle = ext3_journal_current_handle();
	struct inode *inode = page->mapping->host;
	int ret = 0, ret2;

	ret = walk_page_buffers(handle, page_buffers(page),
		from, to, NULL, ext3_journal_dirty_data);

	if (ret == 0) {
		/*
		 * generic_commit_write() will run mark_inode_dirty() if i_size
		 * changes.  So let's piggyback the i_disksize mark_inode_dirty
		 * into that.
		 */
		loff_t new_i_size;

		new_i_size = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to;
		if (new_i_size > EXT3_I(inode)->i_disksize)
			EXT3_I(inode)->i_disksize = new_i_size;
		ret = generic_commit_write(file, page, from, to);
	}
	ret2 = ext3_journal_stop(handle);
	if (!ret)
		ret = ret2;
	return ret;
}

static int ext3_writeback_commit_write(struct file *file, struct page *page,
			     unsigned from, unsigned to)
{
	handle_t *handle = ext3_journal_current_handle();
	struct inode *inode = page->mapping->host;
	int ret = 0, ret2;
	loff_t new_i_size;

	new_i_size = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to;
	if (new_i_size > EXT3_I(inode)->i_disksize)
		EXT3_I(inode)->i_disksize = new_i_size;
	ret = generic_commit_write(file, page, from, to);
	ret2 = ext3_journal_stop(handle);
	if (!ret)
		ret = ret2;
	return ret;
}

static int ext3_journalled_commit_write(struct file *file,
			struct page *page, unsigned from, unsigned to)
{
	handle_t *handle = ext3_journal_current_handle();
	struct inode *inode = page->mapping->host;
	int ret = 0, ret2;
	int partial = 0;
	loff_t pos;

	/*
	 * Here we duplicate the generic_commit_write() functionality
	 */
	pos = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to;

	ret = walk_page_buffers(handle, page_buffers(page), from,
				to, &partial, commit_write_fn);
	if (!partial)
		SetPageUptodate(page);
	if (pos > inode->i_size)
		i_size_write(inode, pos);
	EXT3_I(inode)->i_state |= EXT3_STATE_JDATA;
	if (inode->i_size > EXT3_I(inode)->i_disksize) {
		EXT3_I(inode)->i_disksize = inode->i_size;
		ret2 = ext3_mark_inode_dirty(handle, inode);
		if (!ret) 
			ret = ret2;
	}
	ret2 = ext3_journal_stop(handle);
	if (!ret)
		ret = ret2;
	return ret;
}

/* 
 * 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 ext3 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 ext3_bmap(struct address_space *mapping, sector_t block)
{
	struct inode *inode = mapping->host;
	journal_t *journal;
	int err;

	if (EXT3_I(inode)->i_state & EXT3_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. EXT3_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.
		 */

		EXT3_I(inode)->i_state &= ~EXT3_STATE_JDATA;
		journal = EXT3_JOURNAL(inode);
		journal_lock_updates(journal);
		err = journal_flush(journal);
		journal_unlock_updates(journal);

		if (err)
			return 0;
	}

	return generic_block_bmap(mapping,block,ext3_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 journal_dirty_data_fn(handle_t *handle, struct buffer_head *bh)
{
	if (buffer_mapped(bh))
		return ext3_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 -> ext3_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:
 *
 *	ext3_writepage() -> kmalloc() -> __alloc_pages() -> page_launder() ->
 *		ext3_writepage()
 *
 * Similar for:
 *
 *	ext3_file_write() -> generic_file_write() -> __alloc_pages() -> ...
 *
 * Same applies to ext3_get_block().  We will deadlock on various things like
 * lock_journal and i_truncate_sem.
 *
 * 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