mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-19 22:49:55 +07:00
063d99b4fa
Commit6afdb859b7
("mm: do not ignore mapping_gfp_mask in page cache allocation paths") has caught some users of hardcoded GFP_KERNEL used in the page cache allocation paths. This, however, wasn't complete and there were others which went unnoticed. Dave Chinner has reported the following deadlock for xfs on loop device: : With the recent merge of the loop device changes, I'm now seeing : XFS deadlock on my single CPU, 1GB RAM VM running xfs/073. : : The deadlocked is as follows: : : kloopd1: loop_queue_read_work : xfs_file_iter_read : lock XFS inode XFS_IOLOCK_SHARED (on image file) : page cache read (GFP_KERNEL) : radix tree alloc : memory reclaim : reclaim XFS inodes : log force to unpin inodes : <wait for log IO completion> : : xfs-cil/loop1: <does log force IO work> : xlog_cil_push : xlog_write : <loop issuing log writes> : xlog_state_get_iclog_space() : <blocks due to all log buffers under write io> : <waits for IO completion> : : kloopd1: loop_queue_write_work : xfs_file_write_iter : lock XFS inode XFS_IOLOCK_EXCL (on image file) : <wait for inode to be unlocked> : : i.e. the kloopd, with it's split read and write work queues, has : introduced a dependency through memory reclaim. i.e. that writes : need to be able to progress for reads make progress. : : The problem, fundamentally, is that mpage_readpages() does a : GFP_KERNEL allocation, rather than paying attention to the inode's : mapping gfp mask, which is set to GFP_NOFS. : : The didn't used to happen, because the loop device used to issue : reads through the splice path and that does: : : error = add_to_page_cache_lru(page, mapping, index, : GFP_KERNEL & mapping_gfp_mask(mapping)); This has changed by commitaa4d86163e
("block: loop: switch to VFS ITER_BVEC"). This patch changes mpage_readpage{s} to follow gfp mask set for the mapping. There are, however, other places which are doing basically the same. lustre:ll_dir_filler is doing GFP_KERNEL from the function which apparently uses GFP_NOFS for other allocations so let's make this consistent. cifs:readpages_get_pages is called from cifs_readpages and __cifs_readpages_from_fscache called from the same path obeys mapping gfp. ramfs_nommu_expand_for_mapping is hardcoding GFP_KERNEL as well regardless it uses mapping_gfp_mask for the page allocation. ext4_mpage_readpages is the called from the page cache allocation path same as read_pages and read_cache_pages As I've noticed in my previous post I cannot say I would be happy about sprinkling mapping_gfp_mask all over the place and it sounds like we should drop gfp_mask argument altogether and use it internally in __add_to_page_cache_locked that would require all the filesystems to use mapping gfp consistently which I am not sure is the case here. From a quick glance it seems that some file system use it all the time while others are selective. Signed-off-by: Michal Hocko <mhocko@suse.com> Reported-by: Dave Chinner <david@fromorbit.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Ming Lei <ming.lei@canonical.com> Cc: Andreas Dilger <andreas.dilger@intel.com> Cc: Oleg Drokin <oleg.drokin@intel.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
329 lines
8.2 KiB
C
329 lines
8.2 KiB
C
/*
|
|
* linux/fs/ext4/readpage.c
|
|
*
|
|
* Copyright (C) 2002, Linus Torvalds.
|
|
* Copyright (C) 2015, Google, Inc.
|
|
*
|
|
* This was originally taken from fs/mpage.c
|
|
*
|
|
* The intent is the ext4_mpage_readpages() function here is intended
|
|
* to replace mpage_readpages() in the general case, not just for
|
|
* encrypted files. It has some limitations (see below), where it
|
|
* will fall back to read_block_full_page(), but these limitations
|
|
* should only be hit when page_size != block_size.
|
|
*
|
|
* This will allow us to attach a callback function to support ext4
|
|
* encryption.
|
|
*
|
|
* If anything unusual happens, such as:
|
|
*
|
|
* - encountering a page which has buffers
|
|
* - encountering a page which has a non-hole after a hole
|
|
* - encountering a page with non-contiguous blocks
|
|
*
|
|
* then this code just gives up and calls the buffer_head-based read function.
|
|
* It does handle a page which has holes at the end - that is a common case:
|
|
* the end-of-file on blocksize < PAGE_CACHE_SIZE setups.
|
|
*
|
|
*/
|
|
|
|
#include <linux/kernel.h>
|
|
#include <linux/export.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/kdev_t.h>
|
|
#include <linux/gfp.h>
|
|
#include <linux/bio.h>
|
|
#include <linux/fs.h>
|
|
#include <linux/buffer_head.h>
|
|
#include <linux/blkdev.h>
|
|
#include <linux/highmem.h>
|
|
#include <linux/prefetch.h>
|
|
#include <linux/mpage.h>
|
|
#include <linux/writeback.h>
|
|
#include <linux/backing-dev.h>
|
|
#include <linux/pagevec.h>
|
|
#include <linux/cleancache.h>
|
|
|
|
#include "ext4.h"
|
|
|
|
/*
|
|
* Call ext4_decrypt on every single page, reusing the encryption
|
|
* context.
|
|
*/
|
|
static void completion_pages(struct work_struct *work)
|
|
{
|
|
#ifdef CONFIG_EXT4_FS_ENCRYPTION
|
|
struct ext4_crypto_ctx *ctx =
|
|
container_of(work, struct ext4_crypto_ctx, r.work);
|
|
struct bio *bio = ctx->r.bio;
|
|
struct bio_vec *bv;
|
|
int i;
|
|
|
|
bio_for_each_segment_all(bv, bio, i) {
|
|
struct page *page = bv->bv_page;
|
|
|
|
int ret = ext4_decrypt(ctx, page);
|
|
if (ret) {
|
|
WARN_ON_ONCE(1);
|
|
SetPageError(page);
|
|
} else
|
|
SetPageUptodate(page);
|
|
unlock_page(page);
|
|
}
|
|
ext4_release_crypto_ctx(ctx);
|
|
bio_put(bio);
|
|
#else
|
|
BUG();
|
|
#endif
|
|
}
|
|
|
|
static inline bool ext4_bio_encrypted(struct bio *bio)
|
|
{
|
|
#ifdef CONFIG_EXT4_FS_ENCRYPTION
|
|
return unlikely(bio->bi_private != NULL);
|
|
#else
|
|
return false;
|
|
#endif
|
|
}
|
|
|
|
/*
|
|
* I/O completion handler for multipage BIOs.
|
|
*
|
|
* The mpage code never puts partial pages into a BIO (except for end-of-file).
|
|
* If a page does not map to a contiguous run of blocks then it simply falls
|
|
* back to block_read_full_page().
|
|
*
|
|
* Why is this? If a page's completion depends on a number of different BIOs
|
|
* which can complete in any order (or at the same time) then determining the
|
|
* status of that page is hard. See end_buffer_async_read() for the details.
|
|
* There is no point in duplicating all that complexity.
|
|
*/
|
|
static void mpage_end_io(struct bio *bio)
|
|
{
|
|
struct bio_vec *bv;
|
|
int i;
|
|
|
|
if (ext4_bio_encrypted(bio)) {
|
|
struct ext4_crypto_ctx *ctx = bio->bi_private;
|
|
|
|
if (bio->bi_error) {
|
|
ext4_release_crypto_ctx(ctx);
|
|
} else {
|
|
INIT_WORK(&ctx->r.work, completion_pages);
|
|
ctx->r.bio = bio;
|
|
queue_work(ext4_read_workqueue, &ctx->r.work);
|
|
return;
|
|
}
|
|
}
|
|
bio_for_each_segment_all(bv, bio, i) {
|
|
struct page *page = bv->bv_page;
|
|
|
|
if (!bio->bi_error) {
|
|
SetPageUptodate(page);
|
|
} else {
|
|
ClearPageUptodate(page);
|
|
SetPageError(page);
|
|
}
|
|
unlock_page(page);
|
|
}
|
|
|
|
bio_put(bio);
|
|
}
|
|
|
|
int ext4_mpage_readpages(struct address_space *mapping,
|
|
struct list_head *pages, struct page *page,
|
|
unsigned nr_pages)
|
|
{
|
|
struct bio *bio = NULL;
|
|
unsigned page_idx;
|
|
sector_t last_block_in_bio = 0;
|
|
|
|
struct inode *inode = mapping->host;
|
|
const unsigned blkbits = inode->i_blkbits;
|
|
const unsigned blocks_per_page = PAGE_CACHE_SIZE >> blkbits;
|
|
const unsigned blocksize = 1 << blkbits;
|
|
sector_t block_in_file;
|
|
sector_t last_block;
|
|
sector_t last_block_in_file;
|
|
sector_t blocks[MAX_BUF_PER_PAGE];
|
|
unsigned page_block;
|
|
struct block_device *bdev = inode->i_sb->s_bdev;
|
|
int length;
|
|
unsigned relative_block = 0;
|
|
struct ext4_map_blocks map;
|
|
|
|
map.m_pblk = 0;
|
|
map.m_lblk = 0;
|
|
map.m_len = 0;
|
|
map.m_flags = 0;
|
|
|
|
for (page_idx = 0; nr_pages; page_idx++, nr_pages--) {
|
|
int fully_mapped = 1;
|
|
unsigned first_hole = blocks_per_page;
|
|
|
|
prefetchw(&page->flags);
|
|
if (pages) {
|
|
page = list_entry(pages->prev, struct page, lru);
|
|
list_del(&page->lru);
|
|
if (add_to_page_cache_lru(page, mapping, page->index,
|
|
GFP_KERNEL & mapping_gfp_mask(mapping)))
|
|
goto next_page;
|
|
}
|
|
|
|
if (page_has_buffers(page))
|
|
goto confused;
|
|
|
|
block_in_file = (sector_t)page->index << (PAGE_CACHE_SHIFT - blkbits);
|
|
last_block = block_in_file + nr_pages * blocks_per_page;
|
|
last_block_in_file = (i_size_read(inode) + blocksize - 1) >> blkbits;
|
|
if (last_block > last_block_in_file)
|
|
last_block = last_block_in_file;
|
|
page_block = 0;
|
|
|
|
/*
|
|
* Map blocks using the previous result first.
|
|
*/
|
|
if ((map.m_flags & EXT4_MAP_MAPPED) &&
|
|
block_in_file > map.m_lblk &&
|
|
block_in_file < (map.m_lblk + map.m_len)) {
|
|
unsigned map_offset = block_in_file - map.m_lblk;
|
|
unsigned last = map.m_len - map_offset;
|
|
|
|
for (relative_block = 0; ; relative_block++) {
|
|
if (relative_block == last) {
|
|
/* needed? */
|
|
map.m_flags &= ~EXT4_MAP_MAPPED;
|
|
break;
|
|
}
|
|
if (page_block == blocks_per_page)
|
|
break;
|
|
blocks[page_block] = map.m_pblk + map_offset +
|
|
relative_block;
|
|
page_block++;
|
|
block_in_file++;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Then do more ext4_map_blocks() calls until we are
|
|
* done with this page.
|
|
*/
|
|
while (page_block < blocks_per_page) {
|
|
if (block_in_file < last_block) {
|
|
map.m_lblk = block_in_file;
|
|
map.m_len = last_block - block_in_file;
|
|
|
|
if (ext4_map_blocks(NULL, inode, &map, 0) < 0) {
|
|
set_error_page:
|
|
SetPageError(page);
|
|
zero_user_segment(page, 0,
|
|
PAGE_CACHE_SIZE);
|
|
unlock_page(page);
|
|
goto next_page;
|
|
}
|
|
}
|
|
if ((map.m_flags & EXT4_MAP_MAPPED) == 0) {
|
|
fully_mapped = 0;
|
|
if (first_hole == blocks_per_page)
|
|
first_hole = page_block;
|
|
page_block++;
|
|
block_in_file++;
|
|
continue;
|
|
}
|
|
if (first_hole != blocks_per_page)
|
|
goto confused; /* hole -> non-hole */
|
|
|
|
/* Contiguous blocks? */
|
|
if (page_block && blocks[page_block-1] != map.m_pblk-1)
|
|
goto confused;
|
|
for (relative_block = 0; ; relative_block++) {
|
|
if (relative_block == map.m_len) {
|
|
/* needed? */
|
|
map.m_flags &= ~EXT4_MAP_MAPPED;
|
|
break;
|
|
} else if (page_block == blocks_per_page)
|
|
break;
|
|
blocks[page_block] = map.m_pblk+relative_block;
|
|
page_block++;
|
|
block_in_file++;
|
|
}
|
|
}
|
|
if (first_hole != blocks_per_page) {
|
|
zero_user_segment(page, first_hole << blkbits,
|
|
PAGE_CACHE_SIZE);
|
|
if (first_hole == 0) {
|
|
SetPageUptodate(page);
|
|
unlock_page(page);
|
|
goto next_page;
|
|
}
|
|
} else if (fully_mapped) {
|
|
SetPageMappedToDisk(page);
|
|
}
|
|
if (fully_mapped && blocks_per_page == 1 &&
|
|
!PageUptodate(page) && cleancache_get_page(page) == 0) {
|
|
SetPageUptodate(page);
|
|
goto confused;
|
|
}
|
|
|
|
/*
|
|
* This page will go to BIO. Do we need to send this
|
|
* BIO off first?
|
|
*/
|
|
if (bio && (last_block_in_bio != blocks[0] - 1)) {
|
|
submit_and_realloc:
|
|
submit_bio(READ, bio);
|
|
bio = NULL;
|
|
}
|
|
if (bio == NULL) {
|
|
struct ext4_crypto_ctx *ctx = NULL;
|
|
|
|
if (ext4_encrypted_inode(inode) &&
|
|
S_ISREG(inode->i_mode)) {
|
|
ctx = ext4_get_crypto_ctx(inode);
|
|
if (IS_ERR(ctx))
|
|
goto set_error_page;
|
|
}
|
|
bio = bio_alloc(GFP_KERNEL,
|
|
min_t(int, nr_pages, BIO_MAX_PAGES));
|
|
if (!bio) {
|
|
if (ctx)
|
|
ext4_release_crypto_ctx(ctx);
|
|
goto set_error_page;
|
|
}
|
|
bio->bi_bdev = bdev;
|
|
bio->bi_iter.bi_sector = blocks[0] << (blkbits - 9);
|
|
bio->bi_end_io = mpage_end_io;
|
|
bio->bi_private = ctx;
|
|
}
|
|
|
|
length = first_hole << blkbits;
|
|
if (bio_add_page(bio, page, length, 0) < length)
|
|
goto submit_and_realloc;
|
|
|
|
if (((map.m_flags & EXT4_MAP_BOUNDARY) &&
|
|
(relative_block == map.m_len)) ||
|
|
(first_hole != blocks_per_page)) {
|
|
submit_bio(READ, bio);
|
|
bio = NULL;
|
|
} else
|
|
last_block_in_bio = blocks[blocks_per_page - 1];
|
|
goto next_page;
|
|
confused:
|
|
if (bio) {
|
|
submit_bio(READ, bio);
|
|
bio = NULL;
|
|
}
|
|
if (!PageUptodate(page))
|
|
block_read_full_page(page, ext4_get_block);
|
|
else
|
|
unlock_page(page);
|
|
next_page:
|
|
if (pages)
|
|
page_cache_release(page);
|
|
}
|
|
BUG_ON(pages && !list_empty(pages));
|
|
if (bio)
|
|
submit_bio(READ, bio);
|
|
return 0;
|
|
}
|