linux/fs/erofs/data.c
Gao Xiang 55252ab72b erofs: fix erofs_get_meta_page locking due to a cleanup
After doing more drop_caches stress test on
our products, I found the mistake introduced by
a very recent cleanup [1].

The current rule is that "erofs_get_meta_page"
should be returned with page locked (although
it's mostly unnecessary for read-only fs after
pages are PG_uptodate), but a fix should be
done for this.

[1] https://lore.kernel.org/r/20190904020912.63925-26-gaoxiang25@huawei.com
Fixes: 618f40ea02 ("erofs: use read_cache_page_gfp for erofs_get_meta_page")
Reviewed-by: Chao Yu <yuchao0@huawei.com>
Link: https://lore.kernel.org/r/20190921184355.149928-1-gaoxiang25@huawei.com
Signed-off-by: Gao Xiang <gaoxiang25@huawei.com>
2019-10-01 04:54:33 +08:00

365 lines
8.6 KiB
C

// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2017-2018 HUAWEI, Inc.
* http://www.huawei.com/
* Created by Gao Xiang <gaoxiang25@huawei.com>
*/
#include "internal.h"
#include <linux/prefetch.h>
#include <trace/events/erofs.h>
static void erofs_readendio(struct bio *bio)
{
struct bio_vec *bvec;
blk_status_t err = bio->bi_status;
struct bvec_iter_all iter_all;
bio_for_each_segment_all(bvec, bio, iter_all) {
struct page *page = bvec->bv_page;
/* page is already locked */
DBG_BUGON(PageUptodate(page));
if (err)
SetPageError(page);
else
SetPageUptodate(page);
unlock_page(page);
/* page could be reclaimed now */
}
bio_put(bio);
}
struct page *erofs_get_meta_page(struct super_block *sb, erofs_blk_t blkaddr)
{
struct address_space *const mapping = sb->s_bdev->bd_inode->i_mapping;
struct page *page;
page = read_cache_page_gfp(mapping, blkaddr,
mapping_gfp_constraint(mapping, ~__GFP_FS));
/* should already be PageUptodate */
if (!IS_ERR(page))
lock_page(page);
return page;
}
static int erofs_map_blocks_flatmode(struct inode *inode,
struct erofs_map_blocks *map,
int flags)
{
int err = 0;
erofs_blk_t nblocks, lastblk;
u64 offset = map->m_la;
struct erofs_inode *vi = EROFS_I(inode);
bool tailendpacking = (vi->datalayout == EROFS_INODE_FLAT_INLINE);
trace_erofs_map_blocks_flatmode_enter(inode, map, flags);
nblocks = DIV_ROUND_UP(inode->i_size, PAGE_SIZE);
lastblk = nblocks - tailendpacking;
if (offset >= inode->i_size) {
/* leave out-of-bound access unmapped */
map->m_flags = 0;
map->m_plen = 0;
goto out;
}
/* there is no hole in flatmode */
map->m_flags = EROFS_MAP_MAPPED;
if (offset < blknr_to_addr(lastblk)) {
map->m_pa = blknr_to_addr(vi->raw_blkaddr) + map->m_la;
map->m_plen = blknr_to_addr(lastblk) - offset;
} else if (tailendpacking) {
/* 2 - inode inline B: inode, [xattrs], inline last blk... */
struct erofs_sb_info *sbi = EROFS_SB(inode->i_sb);
map->m_pa = iloc(sbi, vi->nid) + vi->inode_isize +
vi->xattr_isize + erofs_blkoff(map->m_la);
map->m_plen = inode->i_size - offset;
/* inline data should be located in one meta block */
if (erofs_blkoff(map->m_pa) + map->m_plen > PAGE_SIZE) {
erofs_err(inode->i_sb,
"inline data cross block boundary @ nid %llu",
vi->nid);
DBG_BUGON(1);
err = -EFSCORRUPTED;
goto err_out;
}
map->m_flags |= EROFS_MAP_META;
} else {
erofs_err(inode->i_sb,
"internal error @ nid: %llu (size %llu), m_la 0x%llx",
vi->nid, inode->i_size, map->m_la);
DBG_BUGON(1);
err = -EIO;
goto err_out;
}
out:
map->m_llen = map->m_plen;
err_out:
trace_erofs_map_blocks_flatmode_exit(inode, map, flags, 0);
return err;
}
int erofs_map_blocks(struct inode *inode,
struct erofs_map_blocks *map, int flags)
{
if (erofs_inode_is_data_compressed(EROFS_I(inode)->datalayout)) {
int err = z_erofs_map_blocks_iter(inode, map, flags);
if (map->mpage) {
put_page(map->mpage);
map->mpage = NULL;
}
return err;
}
return erofs_map_blocks_flatmode(inode, map, flags);
}
static inline struct bio *erofs_read_raw_page(struct bio *bio,
struct address_space *mapping,
struct page *page,
erofs_off_t *last_block,
unsigned int nblocks,
bool ra)
{
struct inode *const inode = mapping->host;
struct super_block *const sb = inode->i_sb;
erofs_off_t current_block = (erofs_off_t)page->index;
int err;
DBG_BUGON(!nblocks);
if (PageUptodate(page)) {
err = 0;
goto has_updated;
}
/* note that for readpage case, bio also equals to NULL */
if (bio &&
/* not continuous */
*last_block + 1 != current_block) {
submit_bio_retry:
submit_bio(bio);
bio = NULL;
}
if (!bio) {
struct erofs_map_blocks map = {
.m_la = blknr_to_addr(current_block),
};
erofs_blk_t blknr;
unsigned int blkoff;
err = erofs_map_blocks(inode, &map, EROFS_GET_BLOCKS_RAW);
if (err)
goto err_out;
/* zero out the holed page */
if (!(map.m_flags & EROFS_MAP_MAPPED)) {
zero_user_segment(page, 0, PAGE_SIZE);
SetPageUptodate(page);
/* imply err = 0, see erofs_map_blocks */
goto has_updated;
}
/* for RAW access mode, m_plen must be equal to m_llen */
DBG_BUGON(map.m_plen != map.m_llen);
blknr = erofs_blknr(map.m_pa);
blkoff = erofs_blkoff(map.m_pa);
/* deal with inline page */
if (map.m_flags & EROFS_MAP_META) {
void *vsrc, *vto;
struct page *ipage;
DBG_BUGON(map.m_plen > PAGE_SIZE);
ipage = erofs_get_meta_page(inode->i_sb, blknr);
if (IS_ERR(ipage)) {
err = PTR_ERR(ipage);
goto err_out;
}
vsrc = kmap_atomic(ipage);
vto = kmap_atomic(page);
memcpy(vto, vsrc + blkoff, map.m_plen);
memset(vto + map.m_plen, 0, PAGE_SIZE - map.m_plen);
kunmap_atomic(vto);
kunmap_atomic(vsrc);
flush_dcache_page(page);
SetPageUptodate(page);
/* TODO: could we unlock the page earlier? */
unlock_page(ipage);
put_page(ipage);
/* imply err = 0, see erofs_map_blocks */
goto has_updated;
}
/* pa must be block-aligned for raw reading */
DBG_BUGON(erofs_blkoff(map.m_pa));
/* max # of continuous pages */
if (nblocks > DIV_ROUND_UP(map.m_plen, PAGE_SIZE))
nblocks = DIV_ROUND_UP(map.m_plen, PAGE_SIZE);
if (nblocks > BIO_MAX_PAGES)
nblocks = BIO_MAX_PAGES;
bio = bio_alloc(GFP_NOIO, nblocks);
bio->bi_end_io = erofs_readendio;
bio_set_dev(bio, sb->s_bdev);
bio->bi_iter.bi_sector = (sector_t)blknr <<
LOG_SECTORS_PER_BLOCK;
bio->bi_opf = REQ_OP_READ;
}
err = bio_add_page(bio, page, PAGE_SIZE, 0);
/* out of the extent or bio is full */
if (err < PAGE_SIZE)
goto submit_bio_retry;
*last_block = current_block;
/* shift in advance in case of it followed by too many gaps */
if (bio->bi_iter.bi_size >= bio->bi_max_vecs * PAGE_SIZE) {
/* err should reassign to 0 after submitting */
err = 0;
goto submit_bio_out;
}
return bio;
err_out:
/* for sync reading, set page error immediately */
if (!ra) {
SetPageError(page);
ClearPageUptodate(page);
}
has_updated:
unlock_page(page);
/* if updated manually, continuous pages has a gap */
if (bio)
submit_bio_out:
submit_bio(bio);
return err ? ERR_PTR(err) : NULL;
}
/*
* since we dont have write or truncate flows, so no inode
* locking needs to be held at the moment.
*/
static int erofs_raw_access_readpage(struct file *file, struct page *page)
{
erofs_off_t last_block;
struct bio *bio;
trace_erofs_readpage(page, true);
bio = erofs_read_raw_page(NULL, page->mapping,
page, &last_block, 1, false);
if (IS_ERR(bio))
return PTR_ERR(bio);
DBG_BUGON(bio); /* since we have only one bio -- must be NULL */
return 0;
}
static int erofs_raw_access_readpages(struct file *filp,
struct address_space *mapping,
struct list_head *pages,
unsigned int nr_pages)
{
erofs_off_t last_block;
struct bio *bio = NULL;
gfp_t gfp = readahead_gfp_mask(mapping);
struct page *page = list_last_entry(pages, struct page, lru);
trace_erofs_readpages(mapping->host, page, nr_pages, true);
for (; nr_pages; --nr_pages) {
page = list_entry(pages->prev, struct page, lru);
prefetchw(&page->flags);
list_del(&page->lru);
if (!add_to_page_cache_lru(page, mapping, page->index, gfp)) {
bio = erofs_read_raw_page(bio, mapping, page,
&last_block, nr_pages, true);
/* all the page errors are ignored when readahead */
if (IS_ERR(bio)) {
pr_err("%s, readahead error at page %lu of nid %llu\n",
__func__, page->index,
EROFS_I(mapping->host)->nid);
bio = NULL;
}
}
/* pages could still be locked */
put_page(page);
}
DBG_BUGON(!list_empty(pages));
/* the rare case (end in gaps) */
if (bio)
submit_bio(bio);
return 0;
}
static int erofs_get_block(struct inode *inode, sector_t iblock,
struct buffer_head *bh, int create)
{
struct erofs_map_blocks map = {
.m_la = iblock << 9,
};
int err;
err = erofs_map_blocks(inode, &map, EROFS_GET_BLOCKS_RAW);
if (err)
return err;
if (map.m_flags & EROFS_MAP_MAPPED)
bh->b_blocknr = erofs_blknr(map.m_pa);
return err;
}
static sector_t erofs_bmap(struct address_space *mapping, sector_t block)
{
struct inode *inode = mapping->host;
if (EROFS_I(inode)->datalayout == EROFS_INODE_FLAT_INLINE) {
erofs_blk_t blks = i_size_read(inode) >> LOG_BLOCK_SIZE;
if (block >> LOG_SECTORS_PER_BLOCK >= blks)
return 0;
}
return generic_block_bmap(mapping, block, erofs_get_block);
}
/* for uncompressed (aligned) files and raw access for other files */
const struct address_space_operations erofs_raw_access_aops = {
.readpage = erofs_raw_access_readpage,
.readpages = erofs_raw_access_readpages,
.bmap = erofs_bmap,
};