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 for 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 optimization purposes - dirty pages are
 * not budgeted so the flag shows that 'ubifs_write_end()' should not release
 * the budget for this page. 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
 * 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
 * information about how the page was budgeted, to make it possible to release
 * the budget properly.
 *
 * A thing to keep in mind: inode @i_mutex is locked in most VFS operations we
 * implement. However, this is not true for 'ubifs_writepage()', which may be
 * called with @i_mutex unlocked. For example, when pdflush is doing background
 * write-back, it calls 'ubifs_writepage()' with unlocked @i_mutex. At "normal"
 * work-paths the @i_mutex is locked in 'ubifs_writepage()', e.g. in the
 * "sys_write -> alloc_pages -> direct reclaim path". So, in 'ubifs_writepage()'
 * we are only guaranteed that the page is locked.
 *
 * Similarly, @i_mutex is not always locked in 'ubifs_readpage()', e.g., the
 * read-ahead path does not lock it ("sys_read -> generic_file_aio_read ->
 * ondemand_readahead -> readpage"). In case of readahead, @I_SYNC flag is not
 * set as well. However, UBIFS disables readahead.
 */

#include "ubifs.h"
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/slab.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(le64_to_cpu(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, inode->i_ino);
	dbg_dump_node(c, dn);
	return -EINVAL;
}

static int do_readpage(struct page *page)
{
	void *addr;
	int err = 0, i;
	unsigned int block, beyond;
	struct ubifs_data_node *dn;
	struct inode *inode = page->mapping->host;
	loff_t i_size = i_size_read(inode);

	dbg_gen("ino %lu, pg %lu, i_size %lld, flags %#lx",
		inode->i_ino, page->index, i_size, page->flags);
	ubifs_assert(!PageChecked(page));
	ubifs_assert(!PagePrivate(page));

	addr = kmap(page);

	block = page->index << UBIFS_BLOCKS_PER_PAGE_SHIFT;
	beyond = (i_size + UBIFS_BLOCK_SIZE - 1) >> UBIFS_BLOCK_SHIFT;
	if (block >= beyond) {
		/* Reading beyond inode */
		SetPageChecked(page);
		memset(addr, 0, PAGE_CACHE_SIZE);
		goto out;
	}

	dn = kmalloc(UBIFS_MAX_DATA_NODE_SZ, GFP_NOFS);
	if (!dn) {
		err = -ENOMEM;
		goto error;
	}

	i = 0;
	while (1) {
		int ret;

		if (block >= beyond) {
			/* Reading beyond inode */
			err = -ENOENT;
			memset(addr, 0, UBIFS_BLOCK_SIZE);
		} else {
			ret = read_block(inode, addr, block, dn);
			if (ret) {
				err = ret;
				if (err != -ENOENT)
					break;
			} else if (block + 1 == beyond) {
				int dlen = le32_to_cpu(dn->size);
				int ilen = i_size & (UBIFS_BLOCK_SIZE - 1);

				if (ilen && ilen < dlen)
					memset(addr + ilen, 0, dlen - ilen);
			}
		}
		if (++i >= UBIFS_BLOCKS_PER_PAGE)
			break;
		block += 1;
		addr += UBIFS_BLOCK_SIZE;
	}
	if (err) {
		if (err == -ENOENT) {
			/* Not