path: root/fs/ubifs/file.c

/*
 * This file is part of UBIFS.
 *
 * Copyright (C) 2006-2008 Nokia Corporation.
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms of the GNU General Public License version 2 as published by
 * the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful, but WITHOUT
 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
 * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
 * more details.
 *
 * You should have received a copy of the GNU General Public License along with
 * this program; if not, write to the Free Software Foundation, Inc., 51
 * Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
 *
 * Authors: Artem Bityutskiy (Битюцкий Артём)
 *          Adrian Hunter
 */

/*
 * This file implements VFS file and inode operations of regular files, device
 * nodes and symlinks as well as address space operations.
 *
 * UBIFS uses 2 page flags: PG_private and PG_checked. PG_private is set if the
 * page is dirty and is used for budgeting purposes - dirty pages should not be
 * budgeted. The PG_checked flag is set if full budgeting is required for the
 * page e.g., when it corresponds to a file hole or it is just beyond the file
 * size. The budgeting is done in 'ubifs_write_begin()', because it is OK to
 * fail in this function, and the budget is released in 'ubifs_write_end()'. So
 * the PG_private and PG_checked flags carry the information about how the page
 * was budgeted, to make it possible to release the budget properly.
 *
 * A thing to keep in mind: inode's 'i_mutex' is locked in most VFS operations
 * we implement. However, this is not true for '->writepage()', which might be
 * called with 'i_mutex' unlocked. For example, when pdflush is performing
 * write-back, it calls 'writepage()' with unlocked 'i_mutex', although the
 * inode has 'I_LOCK' flag in this case. At "normal" work-paths 'i_mutex' is
 * locked in '->writepage', e.g. in "sys_write -> alloc_pages -> direct reclaim
 * path'. So, in '->writepage()' we are only guaranteed that the page is
 * locked.
 *
 * Similarly, 'i_mutex' does not have to be locked in readpage(), e.g.,
 * readahead path does not have it locked ("sys_read -> generic_file_aio_read
 * -> ondemand_readahead -> readpage"). In case of readahead, 'I_LOCK' flag is
 * not set as well. However, UBIFS disables readahead.
 *
 * This, for example means that there might be 2 concurrent '->writepage()'
 * calls for the same inode, but different inode dirty pages.
 */

#include "ubifs.h"
#include <linux/mount.h>
#include <linux/namei.h>

static int read_block(struct inode *inode, void *addr, unsigned int block,
		      struct ubifs_data_node *dn)
{
	struct ubifs_info *c = inode->i_sb->s_fs_info;
	int err, len, out_len;
	union ubifs_key key;
	unsigned int dlen;

	data_key_init(c, &key, inode->i_ino, block);
	err = ubifs_tnc_lookup(c, &key, dn);
	if (err) {
		if (err == -ENOENT)
			/* Not found, so it must be a hole */
			memset(addr, 0, UBIFS_BLOCK_SIZE);
		return err;
	}

	ubifs_assert(dn->ch.sqnum > ubifs_inode(inode)->creat_sqnum);

	len = le32_to_cpu(dn->size);
	if (len <= 0 || len > UBIFS_BLOCK_SIZE)
		goto dump;

	dlen = le32_to_cpu(dn->ch.len) - UBIFS_DATA_NODE_SZ;
	out_len = UBIFS_BLOCK_SIZE;
	err = ubifs_decompress(&dn->data, dlen, addr, &out_len,
			       le16_to_cpu(dn->compr_type));
	if (err || len != out_len)
		goto dump;

	/*
	 * Data length can be less than a full block, even for blocks that are
	 * not the last in the file (e.g., as a result of making a hole and
	 * appending data). Ensure that the remainder is zeroed out.
	 */
	if (len < UBIFS_BLOCK_SIZE)
		memset(addr + len, 0, UBIFS_BLOCK_SIZE - len);

	return 0;

dump:
	ubifs_err("bad data node (block %u, inode %lu)",
		  block,