inode.c

linux 内核源代码

	/*
	 * Next look up the indirect map to count the totoal number of
	 * direct blocks to allocate for this branch.
	 */
	count = ext4_blks_to_allocate(partial, indirect_blks,
					maxblocks, blocks_to_boundary);
	/*
	 * Block out ext4_truncate while we alter the tree
	 */
	err = ext4_alloc_branch(handle, inode, indirect_blks, &count, goal,
				offsets + (partial - chain), partial);

	/*
	 * The ext4_splice_branch call will free and forget any buffers
	 * on the new chain if there is a failure, but that risks using
	 * up transaction credits, especially for bitmaps where the
	 * credits cannot be returned.  Can we handle this somehow?  We
	 * may need to return -EAGAIN upwards in the worst case.  --sct
	 */
	if (!err)
		err = ext4_splice_branch(handle, inode, iblock,
					partial, indirect_blks, count);
	/*
	 * i_disksize growing is protected by truncate_mutex.  Don't forget to
	 * protect it if you're about to implement concurrent
	 * ext4_get_block() -bzzz
	*/
	if (!err && extend_disksize && inode->i_size > ei->i_disksize)
		ei->i_disksize = inode->i_size;
	mutex_unlock(&ei->truncate_mutex);
	if (err)
		goto cleanup;

	set_buffer_new(bh_result);
got_it:
	map_bh(bh_result, inode->i_sb, le32_to_cpu(chain[depth-1].key));
	if (count > blocks_to_boundary)
		set_buffer_boundary(bh_result);
	err = count;
	/* Clean up and exit */
	partial = chain + depth - 1;	/* the whole chain */
cleanup:
	while (partial > chain) {
		BUFFER_TRACE(partial->bh, "call brelse");
		brelse(partial->bh);
		partial--;
	}
	BUFFER_TRACE(bh_result, "returned");
out:
	return err;
}

#define DIO_CREDITS (EXT4_RESERVE_TRANS_BLOCKS + 32)

static int ext4_get_block(struct inode *inode, sector_t iblock,
			struct buffer_head *bh_result, int create)
{
	handle_t *handle = ext4_journal_current_handle();
	int ret = 0;
	unsigned max_blocks = bh_result->b_size >> inode->i_blkbits;

	if (!create)
		goto get_block;		/* A read */

	if (max_blocks == 1)
		goto get_block;		/* A single block get */

	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.
		 */
		ext4_journal_stop(handle);
		handle = ext4_journal_start(inode, DIO_CREDITS);
		if (IS_ERR(handle))
			ret = PTR_ERR(handle);
		goto get_block;
	}

	if (handle->h_buffer_credits <= EXT4_RESERVE_TRANS_BLOCKS) {
		/*
		 * Getting low on buffer credits...
		 */
		ret = ext4_journal_extend(handle, DIO_CREDITS);
		if (ret > 0) {
			/*
			 * Couldn't extend the transaction.  Start a new one.
			 */
			ret = ext4_journal_restart(handle, DIO_CREDITS);
		}
	}

get_block:
	if (ret == 0) {
		ret = ext4_get_blocks_wrap(handle, inode, iblock,
					max_blocks, bh_result, create, 0);
		if (ret > 0) {
			bh_result->b_size = (ret << inode->i_blkbits);
			ret = 0;
		}
	}
	return ret;
}

/*
 * `handle' can be NULL if create is zero
 */
struct buffer_head *ext4_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);
	err = ext4_get_blocks_wrap(handle, inode, block, 1,
					&dummy, create, 1);
	/*
	 * ext4_get_blocks_handle() returns number of blocks
	 * mapped. 0 in case of a HOLE.
	 */
	if (err > 0) {
		if (err > 1)
			WARN_ON(1);
		err = 0;
	}
	*errp = err;
	if (!err && buffer_mapped(&dummy)) {
		struct buffer_head *bh;
		bh = sb_getblk(inode->i_sb, dummy.b_blocknr);
		if (!bh) {
			*errp = -EIO;
			goto err;
		}
		if (buffer_new(&dummy)) {
			J_ASSERT(create != 0);
			J_ASSERT(handle != NULL);

			/*
			 * 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 ext4_get_block instead, so it's not a
			 * problem.
			 */
			lock_buffer(bh);
			BUFFER_TRACE(bh, "call get_create_access");
			fatal = ext4_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 ext4_journal_dirty_metadata");
			err = ext4_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;
	}
err:
	return NULL;
}

struct buffer_head *ext4_bread(handle_t *handle, struct inode *inode,
			       int block, int create, int *err)
{
	struct buffer_head * bh;

	bh = ext4_getblk(handle, inode, block, create, err);
	if (!bh)
		return bh;
	if (buffer_uptodate(bh))
		return bh;
	ll_rw_block(READ_META, 1, &bh);
	wait_on_buffer(bh);
	if (buffer_uptodate(bh))
		return bh;
	put_bh(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 ext4_get_block()
 * and the commit_write().  So doing the jbd2_journal_start at the start of
 * prepare_write() is the right place.
 *
 * Also, this function can nest inside ext4_writepage() ->
 * block_write_full_page(). In that case, we *know* that ext4_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, ext4 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 jbd2_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 ext4_journal_get_write_access(handle, bh);
}

static int ext4_write_begin(struct file *file, struct address_space *mapping,
				loff_t pos, unsigned len, unsigned flags,
				struct page **pagep, void **fsdata)
{
 	struct inode *inode = mapping->host;
	int ret, needed_blocks = ext4_writepage_trans_blocks(inode);
	handle_t *handle;
	int retries = 0;
 	struct page *page;
 	pgoff_t index;
 	unsigned from, to;

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

retry:
 	page = __grab_cache_page(mapping, index);
 	if (!page)
 		return -ENOMEM;
 	*pagep = page;

  	handle = ext4_journal_start(inode, needed_blocks);
  	if (IS_ERR(handle)) {
 		unlock_page(page);
 		page_cache_release(page);
  		ret = PTR_ERR(handle);
  		goto out;
	}

	ret = block_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
							ext4_get_block);

	if (!ret && ext4_should_journal_data(inode)) {
		ret = walk_page_buffers(handle, page_buffers(page),
				from, to, NULL, do_journal_get_write_access);
	}

	if (ret) {
		ext4_journal_stop(handle);
 		unlock_page(page);
 		page_cache_release(page);
	}

	if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
		goto retry;
out:
	return ret;
}

int ext4_journal_dirty_data(handle_t *handle, struct buffer_head *bh)
{
	int err = jbd2_journal_dirty_data(handle, bh);
	if (err)
		ext4_journal_abort_handle(__FUNCTION__, __FUNCTION__,
						bh, handle, err);
	return err;
}

/* For write_end() in data=journal mode */
static int write_end_fn(handle_t *handle, struct buffer_head *bh)
{
	if (!buffer_mapped(bh) || buffer_freed(bh))
		return 0;
	set_buffer_uptodate(bh);
	return ext4_journal_dirty_metadata(handle, bh);
}

/*
 * Generic write_end handler for ordered and writeback ext4 journal modes.
 * We can't use generic_write_end, because that unlocks the page and we need to
 * unlock the page after ext4_journal_stop, but ext4_journal_stop must run
 * after block_write_end.
 */
static int ext4_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 = file->f_mapping->host;

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

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

	return copied;
}

/*
 * 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().
 *
 * ext4 never places buffers on inode->i_mapping->private_list.  metadata
 * buffers are managed internally.
 */
static int ext4_ordered_write_end(struct file *file,
				struct address_space *mapping,
				loff_t pos, unsigned len, unsigned copied,
				struct page *page, void *fsdata)
{
	handle_t *handle = ext4_journal_current_handle();
	struct inode *inode = file->f_mapping->host;
	unsigned from, to;
	int ret = 0, ret2;

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

	ret = walk_page_buffers(handle, page_buffers(page),
		from, to, NULL, ext4_journal_dirty_data);

	if (ret == 0) {
		/*
		 * generic_write_end() 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 = pos + copied;
		if (new_i_size > EXT4_I(inode)->i_disksize)
			EXT4_I(inode)->i_disksize = new_i_size;
		copied = ext4_generic_write_end(file, mapping, pos, len, copied,
							page, fsdata);
		if (copied < 0)
			ret = copied;
	}
	ret2 = ext4_journal_stop(handle);
	if (!ret)
		ret = ret2;
	unlock_page(page);
	page_cache_release(page);

	return ret ? ret : copied;
}

static int ext4_writeback_write_end(struct file *file,
				struct address_space *mapping,
				loff_t pos, unsigned len, unsigned copied,
				struct page *page, void *fsdata)
{
	handle_t *handle = ext4_journal_current_handle();
	struct inode *inode = file->f_mapping->host;
	int ret = 0, ret2;
	loff_t new_i_size;

	new_i_size = pos + copied;
	if (new_i_size > EXT4_I(inode)->i_disksize)
		EXT4_I(inode)->i_disksize = new_i_size;

	copied = ext4_generic_write_end(file, mapping, pos, len, copied,
							page, fsdata);
	if (copied < 0)
		ret = copied;

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

	return ret ? ret : copied;
}

static int ext4_journalled_write_end(struct file *file,
				struct address_space *mapping,
				loff_t pos, unsigned len, unsigned copied,
				struct page *page, void *fsdata)
{
	handle_t *handle = ext4_journal_current_handle();
	struct inode *inode = mapping->host;
	int ret = 0, ret2;
	int partial = 0;
	unsigned from, to;

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

	if (copied < len) {
		if (!PageUptodate(page))
			copied = 0;
		page_zero_new_buffers(page, from+copied, to);
	}