WSL2-Linux-Kernel/fs/f2fs/data.c

3334 строки
79 KiB
C
Исходник Обычный вид История

// SPDX-License-Identifier: GPL-2.0
/*
* fs/f2fs/data.c
*
* Copyright (c) 2012 Samsung Electronics Co., Ltd.
* http://www.samsung.com/
*/
#include <linux/fs.h>
#include <linux/f2fs_fs.h>
#include <linux/buffer_head.h>
#include <linux/mpage.h>
#include <linux/writeback.h>
#include <linux/backing-dev.h>
#include <linux/pagevec.h>
#include <linux/blkdev.h>
#include <linux/bio.h>
#include <linux/swap.h>
#include <linux/prefetch.h>
#include <linux/uio.h>
#include <linux/cleancache.h>
#include <linux/sched/signal.h>
#include "f2fs.h"
#include "node.h"
#include "segment.h"
#include "trace.h"
#include <trace/events/f2fs.h>
#define NUM_PREALLOC_POST_READ_CTXS 128
static struct kmem_cache *bio_post_read_ctx_cache;
static struct kmem_cache *bio_entry_slab;
static mempool_t *bio_post_read_ctx_pool;
static bool __is_cp_guaranteed(struct page *page)
{
struct address_space *mapping = page->mapping;
struct inode *inode;
struct f2fs_sb_info *sbi;
if (!mapping)
return false;
inode = mapping->host;
sbi = F2FS_I_SB(inode);
if (inode->i_ino == F2FS_META_INO(sbi) ||
inode->i_ino == F2FS_NODE_INO(sbi) ||
S_ISDIR(inode->i_mode) ||
(S_ISREG(inode->i_mode) &&
(f2fs_is_atomic_file(inode) || IS_NOQUOTA(inode))) ||
is_cold_data(page))
return true;
return false;
}
static enum count_type __read_io_type(struct page *page)
{
struct address_space *mapping = page_file_mapping(page);
if (mapping) {
struct inode *inode = mapping->host;
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
if (inode->i_ino == F2FS_META_INO(sbi))
return F2FS_RD_META;
if (inode->i_ino == F2FS_NODE_INO(sbi))
return F2FS_RD_NODE;
}
return F2FS_RD_DATA;
}
/* postprocessing steps for read bios */
enum bio_post_read_step {
STEP_INITIAL = 0,
STEP_DECRYPT,
f2fs: add fs-verity support Add fs-verity support to f2fs. fs-verity is a filesystem feature that enables transparent integrity protection and authentication of read-only files. It uses a dm-verity like mechanism at the file level: a Merkle tree is used to verify any block in the file in log(filesize) time. It is implemented mainly by helper functions in fs/verity/. See Documentation/filesystems/fsverity.rst for the full documentation. The f2fs support for fs-verity consists of: - Adding a filesystem feature flag and an inode flag for fs-verity. - Implementing the fsverity_operations to support enabling verity on an inode and reading/writing the verity metadata. - Updating ->readpages() to verify data as it's read from verity files and to support reading verity metadata pages. - Updating ->write_begin(), ->write_end(), and ->writepages() to support writing verity metadata pages. - Calling the fs-verity hooks for ->open(), ->setattr(), and ->ioctl(). Like ext4, f2fs stores the verity metadata (Merkle tree and fsverity_descriptor) past the end of the file, starting at the first 64K boundary beyond i_size. This approach works because (a) verity files are readonly, and (b) pages fully beyond i_size aren't visible to userspace but can be read/written internally by f2fs with only some relatively small changes to f2fs. Extended attributes cannot be used because (a) f2fs limits the total size of an inode's xattr entries to 4096 bytes, which wouldn't be enough for even a single Merkle tree block, and (b) f2fs encryption doesn't encrypt xattrs, yet the verity metadata *must* be encrypted when the file is because it contains hashes of the plaintext data. Acked-by: Jaegeuk Kim <jaegeuk@kernel.org> Acked-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Eric Biggers <ebiggers@google.com>
2019-07-22 19:26:24 +03:00
STEP_VERITY,
};
struct bio_post_read_ctx {
struct bio *bio;
struct work_struct work;
unsigned int cur_step;
unsigned int enabled_steps;
};
static void __read_end_io(struct bio *bio)
{
struct page *page;
struct bio_vec *bv;
struct bvec_iter_all iter_all;
bio_for_each_segment_all(bv, bio, iter_all) {
page = bv->bv_page;
/* PG_error was set if any post_read step failed */
if (bio->bi_status || PageError(page)) {
ClearPageUptodate(page);
/* will re-read again later */
ClearPageError(page);
} else {
SetPageUptodate(page);
}
dec_page_count(F2FS_P_SB(page), __read_io_type(page));
unlock_page(page);
}
if (bio->bi_private)
mempool_free(bio->bi_private, bio_post_read_ctx_pool);
bio_put(bio);
}
static void bio_post_read_processing(struct bio_post_read_ctx *ctx);
static void decrypt_work(struct work_struct *work)
{
struct bio_post_read_ctx *ctx =
container_of(work, struct bio_post_read_ctx, work);
fscrypt_decrypt_bio(ctx->bio);
bio_post_read_processing(ctx);
}
f2fs: add fs-verity support Add fs-verity support to f2fs. fs-verity is a filesystem feature that enables transparent integrity protection and authentication of read-only files. It uses a dm-verity like mechanism at the file level: a Merkle tree is used to verify any block in the file in log(filesize) time. It is implemented mainly by helper functions in fs/verity/. See Documentation/filesystems/fsverity.rst for the full documentation. The f2fs support for fs-verity consists of: - Adding a filesystem feature flag and an inode flag for fs-verity. - Implementing the fsverity_operations to support enabling verity on an inode and reading/writing the verity metadata. - Updating ->readpages() to verify data as it's read from verity files and to support reading verity metadata pages. - Updating ->write_begin(), ->write_end(), and ->writepages() to support writing verity metadata pages. - Calling the fs-verity hooks for ->open(), ->setattr(), and ->ioctl(). Like ext4, f2fs stores the verity metadata (Merkle tree and fsverity_descriptor) past the end of the file, starting at the first 64K boundary beyond i_size. This approach works because (a) verity files are readonly, and (b) pages fully beyond i_size aren't visible to userspace but can be read/written internally by f2fs with only some relatively small changes to f2fs. Extended attributes cannot be used because (a) f2fs limits the total size of an inode's xattr entries to 4096 bytes, which wouldn't be enough for even a single Merkle tree block, and (b) f2fs encryption doesn't encrypt xattrs, yet the verity metadata *must* be encrypted when the file is because it contains hashes of the plaintext data. Acked-by: Jaegeuk Kim <jaegeuk@kernel.org> Acked-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Eric Biggers <ebiggers@google.com>
2019-07-22 19:26:24 +03:00
static void verity_work(struct work_struct *work)
{
struct bio_post_read_ctx *ctx =
container_of(work, struct bio_post_read_ctx, work);
fsverity_verify_bio(ctx->bio);
bio_post_read_processing(ctx);
}
static void bio_post_read_processing(struct bio_post_read_ctx *ctx)
{
f2fs: add fs-verity support Add fs-verity support to f2fs. fs-verity is a filesystem feature that enables transparent integrity protection and authentication of read-only files. It uses a dm-verity like mechanism at the file level: a Merkle tree is used to verify any block in the file in log(filesize) time. It is implemented mainly by helper functions in fs/verity/. See Documentation/filesystems/fsverity.rst for the full documentation. The f2fs support for fs-verity consists of: - Adding a filesystem feature flag and an inode flag for fs-verity. - Implementing the fsverity_operations to support enabling verity on an inode and reading/writing the verity metadata. - Updating ->readpages() to verify data as it's read from verity files and to support reading verity metadata pages. - Updating ->write_begin(), ->write_end(), and ->writepages() to support writing verity metadata pages. - Calling the fs-verity hooks for ->open(), ->setattr(), and ->ioctl(). Like ext4, f2fs stores the verity metadata (Merkle tree and fsverity_descriptor) past the end of the file, starting at the first 64K boundary beyond i_size. This approach works because (a) verity files are readonly, and (b) pages fully beyond i_size aren't visible to userspace but can be read/written internally by f2fs with only some relatively small changes to f2fs. Extended attributes cannot be used because (a) f2fs limits the total size of an inode's xattr entries to 4096 bytes, which wouldn't be enough for even a single Merkle tree block, and (b) f2fs encryption doesn't encrypt xattrs, yet the verity metadata *must* be encrypted when the file is because it contains hashes of the plaintext data. Acked-by: Jaegeuk Kim <jaegeuk@kernel.org> Acked-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Eric Biggers <ebiggers@google.com>
2019-07-22 19:26:24 +03:00
/*
* We use different work queues for decryption and for verity because
* verity may require reading metadata pages that need decryption, and
* we shouldn't recurse to the same workqueue.
*/
switch (++ctx->cur_step) {
case STEP_DECRYPT:
if (ctx->enabled_steps & (1 << STEP_DECRYPT)) {
INIT_WORK(&ctx->work, decrypt_work);
fscrypt_enqueue_decrypt_work(&ctx->work);
return;
}
ctx->cur_step++;
/* fall-through */
f2fs: add fs-verity support Add fs-verity support to f2fs. fs-verity is a filesystem feature that enables transparent integrity protection and authentication of read-only files. It uses a dm-verity like mechanism at the file level: a Merkle tree is used to verify any block in the file in log(filesize) time. It is implemented mainly by helper functions in fs/verity/. See Documentation/filesystems/fsverity.rst for the full documentation. The f2fs support for fs-verity consists of: - Adding a filesystem feature flag and an inode flag for fs-verity. - Implementing the fsverity_operations to support enabling verity on an inode and reading/writing the verity metadata. - Updating ->readpages() to verify data as it's read from verity files and to support reading verity metadata pages. - Updating ->write_begin(), ->write_end(), and ->writepages() to support writing verity metadata pages. - Calling the fs-verity hooks for ->open(), ->setattr(), and ->ioctl(). Like ext4, f2fs stores the verity metadata (Merkle tree and fsverity_descriptor) past the end of the file, starting at the first 64K boundary beyond i_size. This approach works because (a) verity files are readonly, and (b) pages fully beyond i_size aren't visible to userspace but can be read/written internally by f2fs with only some relatively small changes to f2fs. Extended attributes cannot be used because (a) f2fs limits the total size of an inode's xattr entries to 4096 bytes, which wouldn't be enough for even a single Merkle tree block, and (b) f2fs encryption doesn't encrypt xattrs, yet the verity metadata *must* be encrypted when the file is because it contains hashes of the plaintext data. Acked-by: Jaegeuk Kim <jaegeuk@kernel.org> Acked-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Eric Biggers <ebiggers@google.com>
2019-07-22 19:26:24 +03:00
case STEP_VERITY:
if (ctx->enabled_steps & (1 << STEP_VERITY)) {
INIT_WORK(&ctx->work, verity_work);
fsverity_enqueue_verify_work(&ctx->work);
return;
}
ctx->cur_step++;
/* fall-through */
default:
__read_end_io(ctx->bio);
}
}
static bool f2fs_bio_post_read_required(struct bio *bio)
{
return bio->bi_private && !bio->bi_status;
}
static void f2fs_read_end_io(struct bio *bio)
{
if (time_to_inject(F2FS_P_SB(bio_first_page_all(bio)),
FAULT_READ_IO)) {
f2fs_show_injection_info(FAULT_READ_IO);
bio->bi_status = BLK_STS_IOERR;
}
if (f2fs_bio_post_read_required(bio)) {
struct bio_post_read_ctx *ctx = bio->bi_private;
ctx->cur_step = STEP_INITIAL;
bio_post_read_processing(ctx);
return;
}
__read_end_io(bio);
}
static void f2fs_write_end_io(struct bio *bio)
{
struct f2fs_sb_info *sbi = bio->bi_private;
Merge branch 'for-3.14/core' of git://git.kernel.dk/linux-block Pull core block IO changes from Jens Axboe: "The major piece in here is the immutable bio_ve series from Kent, the rest is fairly minor. It was supposed to go in last round, but various issues pushed it to this release instead. The pull request contains: - Various smaller blk-mq fixes from different folks. Nothing major here, just minor fixes and cleanups. - Fix for a memory leak in the error path in the block ioctl code from Christian Engelmayer. - Header export fix from CaiZhiyong. - Finally the immutable biovec changes from Kent Overstreet. This enables some nice future work on making arbitrarily sized bios possible, and splitting more efficient. Related fixes to immutable bio_vecs: - dm-cache immutable fixup from Mike Snitzer. - btrfs immutable fixup from Muthu Kumar. - bio-integrity fix from Nic Bellinger, which is also going to stable" * 'for-3.14/core' of git://git.kernel.dk/linux-block: (44 commits) xtensa: fixup simdisk driver to work with immutable bio_vecs block/blk-mq-cpu.c: use hotcpu_notifier() blk-mq: for_each_* macro correctness block: Fix memory leak in rw_copy_check_uvector() handling bio-integrity: Fix bio_integrity_verify segment start bug block: remove unrelated header files and export symbol blk-mq: uses page->list incorrectly blk-mq: use __smp_call_function_single directly btrfs: fix missing increment of bi_remaining Revert "block: Warn and free bio if bi_end_io is not set" block: Warn and free bio if bi_end_io is not set blk-mq: fix initializing request's start time block: blk-mq: don't export blk_mq_free_queue() block: blk-mq: make blk_sync_queue support mq block: blk-mq: support draining mq queue dm cache: increment bi_remaining when bi_end_io is restored block: fixup for generic bio chaining block: Really silence spurious compiler warnings block: Silence spurious compiler warnings block: Kill bio_pair_split() ...
2014-01-30 23:19:05 +04:00
struct bio_vec *bvec;
struct bvec_iter_all iter_all;
if (time_to_inject(sbi, FAULT_WRITE_IO)) {
f2fs_show_injection_info(FAULT_WRITE_IO);
bio->bi_status = BLK_STS_IOERR;
}
bio_for_each_segment_all(bvec, bio, iter_all) {
struct page *page = bvec->bv_page;
enum count_type type = WB_DATA_TYPE(page);
if (IS_DUMMY_WRITTEN_PAGE(page)) {
set_page_private(page, (unsigned long)NULL);
ClearPagePrivate(page);
unlock_page(page);
mempool_free(page, sbi->write_io_dummy);
if (unlikely(bio->bi_status))
f2fs_stop_checkpoint(sbi, true);
continue;
}
fscrypt_finalize_bounce_page(&page);
if (unlikely(bio->bi_status)) {
mapping_set_error(page->mapping, -EIO);
if (type == F2FS_WB_CP_DATA)
f2fs_stop_checkpoint(sbi, true);
}
f2fs_bug_on(sbi, page->mapping == NODE_MAPPING(sbi) &&
page->index != nid_of_node(page));
dec_page_count(sbi, type);
f2fs: fix to avoid broken of dnode block list f2fs recovery flow is relying on dnode block link list, it means fsynced file recovery depends on previous dnode's persistence in the list, so during fsync() we should wait on all regular inode's dnode writebacked before issuing flush. By this way, we can avoid dnode block list being broken by out-of-order IO submission due to IO scheduler or driver. Sheng Yong helps to do the test with this patch: Target:/data (f2fs, -) 64MB / 32768KB / 4KB / 8 1 / PERSIST / Index Base: SEQ-RD(MB/s) SEQ-WR(MB/s) RND-RD(IOPS) RND-WR(IOPS) Insert(TPS) Update(TPS) Delete(TPS) 1 867.82 204.15 41440.03 41370.54 680.8 1025.94 1031.08 2 871.87 205.87 41370.3 40275.2 791.14 1065.84 1101.7 3 866.52 205.69 41795.67 40596.16 694.69 1037.16 1031.48 Avg 868.7366667 205.2366667 41535.33333 40747.3 722.21 1042.98 1054.753333 After: SEQ-RD(MB/s) SEQ-WR(MB/s) RND-RD(IOPS) RND-WR(IOPS) Insert(TPS) Update(TPS) Delete(TPS) 1 798.81 202.5 41143 40613.87 602.71 838.08 913.83 2 805.79 206.47 40297.2 41291.46 604.44 840.75 924.27 3 814.83 206.17 41209.57 40453.62 602.85 834.66 927.91 Avg 806.4766667 205.0466667 40883.25667 40786.31667 603.3333333 837.83 922.0033333 Patched/Original: 0.928332713 0.999074239 0.984300676 1.000957528 0.835398753 0.803303994 0.874141189 It looks like atomic write will suffer performance regression. I suspect that the criminal is that we forcing to wait all dnode being in storage cache before we issue PREFLUSH+FUA. BTW, will commit ("f2fs: don't need to wait for node writes for atomic write") cause the problem: we will lose data of last transaction after SPO, even if atomic write return no error: - atomic_open(); - write() P1, P2, P3; - atomic_commit(); - writeback data: P1, P2, P3; - writeback node: N1, N2, N3; <--- If N1, N2 is not writebacked, N3 with fsync_mark is writebacked, In SPOR, we won't find N3 since node chain is broken, turns out that losing last transaction. - preflush + fua; - power-cut If we don't wait dnode writeback for atomic_write: SEQ-RD(MB/s) SEQ-WR(MB/s) RND-RD(IOPS) RND-WR(IOPS) Insert(TPS) Update(TPS) Delete(TPS) 1 779.91 206.03 41621.5 40333.16 716.9 1038.21 1034.85 2 848.51 204.35 40082.44 39486.17 791.83 1119.96 1083.77 3 772.12 206.27 41335.25 41599.65 723.29 1055.07 971.92 Avg 800.18 205.55 41013.06333 40472.99333 744.0066667 1071.08 1030.18 Patched/Original: 0.92108464 1.001526693 0.987425886 0.993268102 1.030180511 1.026942031 0.976702294 SQLite's performance recovers. Jaegeuk: "Practically, I don't see db corruption becase of this. We can excuse to lose the last transaction." Finally, we decide to keep original implementation of atomic write interface sematics that we don't wait all dnode writeback before preflush+fua submission. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-08-02 18:03:19 +03:00
if (f2fs_in_warm_node_list(sbi, page))
f2fs_del_fsync_node_entry(sbi, page);
clear_cold_data(page);
end_page_writeback(page);
Merge branch 'for-3.14/core' of git://git.kernel.dk/linux-block Pull core block IO changes from Jens Axboe: "The major piece in here is the immutable bio_ve series from Kent, the rest is fairly minor. It was supposed to go in last round, but various issues pushed it to this release instead. The pull request contains: - Various smaller blk-mq fixes from different folks. Nothing major here, just minor fixes and cleanups. - Fix for a memory leak in the error path in the block ioctl code from Christian Engelmayer. - Header export fix from CaiZhiyong. - Finally the immutable biovec changes from Kent Overstreet. This enables some nice future work on making arbitrarily sized bios possible, and splitting more efficient. Related fixes to immutable bio_vecs: - dm-cache immutable fixup from Mike Snitzer. - btrfs immutable fixup from Muthu Kumar. - bio-integrity fix from Nic Bellinger, which is also going to stable" * 'for-3.14/core' of git://git.kernel.dk/linux-block: (44 commits) xtensa: fixup simdisk driver to work with immutable bio_vecs block/blk-mq-cpu.c: use hotcpu_notifier() blk-mq: for_each_* macro correctness block: Fix memory leak in rw_copy_check_uvector() handling bio-integrity: Fix bio_integrity_verify segment start bug block: remove unrelated header files and export symbol blk-mq: uses page->list incorrectly blk-mq: use __smp_call_function_single directly btrfs: fix missing increment of bi_remaining Revert "block: Warn and free bio if bi_end_io is not set" block: Warn and free bio if bi_end_io is not set blk-mq: fix initializing request's start time block: blk-mq: don't export blk_mq_free_queue() block: blk-mq: make blk_sync_queue support mq block: blk-mq: support draining mq queue dm cache: increment bi_remaining when bi_end_io is restored block: fixup for generic bio chaining block: Really silence spurious compiler warnings block: Silence spurious compiler warnings block: Kill bio_pair_split() ...
2014-01-30 23:19:05 +04:00
}
if (!get_pages(sbi, F2FS_WB_CP_DATA) &&
wq_has_sleeper(&sbi->cp_wait))
wake_up(&sbi->cp_wait);
bio_put(bio);
}
/*
* Return true, if pre_bio's bdev is same as its target device.
*/
struct block_device *f2fs_target_device(struct f2fs_sb_info *sbi,
block_t blk_addr, struct bio *bio)
{
struct block_device *bdev = sbi->sb->s_bdev;
int i;
if (f2fs_is_multi_device(sbi)) {
for (i = 0; i < sbi->s_ndevs; i++) {
if (FDEV(i).start_blk <= blk_addr &&
FDEV(i).end_blk >= blk_addr) {
blk_addr -= FDEV(i).start_blk;
bdev = FDEV(i).bdev;
break;
}
}
}
if (bio) {
bio_set_dev(bio, bdev);
bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(blk_addr);
}
return bdev;
}
int f2fs_target_device_index(struct f2fs_sb_info *sbi, block_t blkaddr)
{
int i;
if (!f2fs_is_multi_device(sbi))
return 0;
for (i = 0; i < sbi->s_ndevs; i++)
if (FDEV(i).start_blk <= blkaddr && FDEV(i).end_blk >= blkaddr)
return i;
return 0;
}
static bool __same_bdev(struct f2fs_sb_info *sbi,
block_t blk_addr, struct bio *bio)
{
struct block_device *b = f2fs_target_device(sbi, blk_addr, NULL);
return bio->bi_disk == b->bd_disk && bio->bi_partno == b->bd_partno;
}
/*
* Low-level block read/write IO operations.
*/
static struct bio *__bio_alloc(struct f2fs_io_info *fio, int npages)
{
struct f2fs_sb_info *sbi = fio->sbi;
struct bio *bio;
bio = f2fs_bio_alloc(sbi, npages, true);
f2fs_target_device(sbi, fio->new_blkaddr, bio);
if (is_read_io(fio->op)) {
bio->bi_end_io = f2fs_read_end_io;
bio->bi_private = NULL;
} else {
bio->bi_end_io = f2fs_write_end_io;
bio->bi_private = sbi;
bio->bi_write_hint = f2fs_io_type_to_rw_hint(sbi,
fio->type, fio->temp);
}
if (fio->io_wbc)
wbc_init_bio(fio->io_wbc, bio);
return bio;
}
The major change in this version is mitigating cpu overheads on write paths by replacing redundant inode page updates with mark_inode_dirty calls. And we tried to reduce lock contentions as well to improve filesystem scalability. Other feature is setting F2FS automatically when detecting host-managed SMR. = Enhancement = - ioctl to move a range of data between files - inject orphan inode errors - avoid flush commands congestion - support lazytime = Bug fixes = - return proper results for some dentry operations - fix deadlock in add_link failure - disable extent_cache for fcollapse/finsert -----BEGIN PGP SIGNATURE----- Version: GnuPG v1 iQIcBAABAgAGBQJXmDJFAAoJEEAUqH6CSFDSJeYP/0ru8+5/ui5VTCdNPQB9KxYD DIUaDGpeoLvmn3ZdrMEdyNr6kWbgjCE9JjOGPQ7l1/apErOGVPyaBwflKcCDwloU pAlEqVM1Q9j4qH4i9SWTlvPtsHBHB7G7YSe3vDB9fJGSTqumubIlnaBm+Wfjx31U p53WcPn9LpOyzfmvZf2tOHmvZ7bWLkE/a07x9kPC6XHUFb9C17jLRFFGeuhZQHv1 Yo7HgokBnPExa8TnEILYyX/x+eecFS/1Cp/cN0STsebSu8pStTHTcAP7qEpKQB88 Cc51Lf+d5gFeydxKDFxwdH3VWOGIr9Ppako+lHW83gJcHP0zw8zdxULab+HJMa4n MOByRRiafwu1sL0dl7TCfsYNIHdEnXhWbhcRhMVZbb5C2Q6+Htuac8ZrKSOWExNN DUqRkzeTib9u+cHxUTFFPgOGdUjDLmg3XHU7mvb+2hViluVjIImC4tqD5XPpv7vt WnaDJxLCGD/6DF2yhiVY9NysuxInLTNFFCF06LworZ4L24hlg5TvN0UeUNRO9954 ux6f+lSORCzV3TmrsHP5vwjSAW26FviPXV1q1HHJeTpWKMlhsZtHmOAJOtZKKmxP WFnHT0aiWF+sQf4qfxVQL+lLqtgRKJAI9zqGRyfDJWJp5aXdRuVsZs9pWNQF7lCo 5gVnCYk3ULjXG3b23j2S =tKTR -----END PGP SIGNATURE----- Merge tag 'for-f2fs-4.8' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs Pull f2fs updates from Jaegeuk Kim: "The major change in this version is mitigating cpu overheads on write paths by replacing redundant inode page updates with mark_inode_dirty calls. And we tried to reduce lock contentions as well to improve filesystem scalability. Other feature is setting F2FS automatically when detecting host-managed SMR. Enhancements: - ioctl to move a range of data between files - inject orphan inode errors - avoid flush commands congestion - support lazytime Bug fixes: - return proper results for some dentry operations - fix deadlock in add_link failure - disable extent_cache for fcollapse/finsert" * tag 'for-f2fs-4.8' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (68 commits) f2fs: clean up coding style and redundancy f2fs: get victim segment again after new cp f2fs: handle error case with f2fs_bug_on f2fs: avoid data race when deciding checkpoin in f2fs_sync_file f2fs: support an ioctl to move a range of data blocks f2fs: fix to report error number of f2fs_find_entry f2fs: avoid memory allocation failure due to a long length f2fs: reset default idle interval value f2fs: use blk_plug in all the possible paths f2fs: fix to avoid data update racing between GC and DIO f2fs: add maximum prefree segments f2fs: disable extent_cache for fcollapse/finsert inodes f2fs: refactor __exchange_data_block for speed up f2fs: fix ERR_PTR returned by bio f2fs: avoid mark_inode_dirty f2fs: move i_size_write in f2fs_write_end f2fs: fix to avoid redundant discard during fstrim f2fs: avoid mismatching block range for discard f2fs: fix incorrect f_bfree calculation in ->statfs f2fs: use percpu_rw_semaphore ...
2016-07-27 20:36:31 +03:00
static inline void __submit_bio(struct f2fs_sb_info *sbi,
struct bio *bio, enum page_type type)
{
The major change in this version is mitigating cpu overheads on write paths by replacing redundant inode page updates with mark_inode_dirty calls. And we tried to reduce lock contentions as well to improve filesystem scalability. Other feature is setting F2FS automatically when detecting host-managed SMR. = Enhancement = - ioctl to move a range of data between files - inject orphan inode errors - avoid flush commands congestion - support lazytime = Bug fixes = - return proper results for some dentry operations - fix deadlock in add_link failure - disable extent_cache for fcollapse/finsert -----BEGIN PGP SIGNATURE----- Version: GnuPG v1 iQIcBAABAgAGBQJXmDJFAAoJEEAUqH6CSFDSJeYP/0ru8+5/ui5VTCdNPQB9KxYD DIUaDGpeoLvmn3ZdrMEdyNr6kWbgjCE9JjOGPQ7l1/apErOGVPyaBwflKcCDwloU pAlEqVM1Q9j4qH4i9SWTlvPtsHBHB7G7YSe3vDB9fJGSTqumubIlnaBm+Wfjx31U p53WcPn9LpOyzfmvZf2tOHmvZ7bWLkE/a07x9kPC6XHUFb9C17jLRFFGeuhZQHv1 Yo7HgokBnPExa8TnEILYyX/x+eecFS/1Cp/cN0STsebSu8pStTHTcAP7qEpKQB88 Cc51Lf+d5gFeydxKDFxwdH3VWOGIr9Ppako+lHW83gJcHP0zw8zdxULab+HJMa4n MOByRRiafwu1sL0dl7TCfsYNIHdEnXhWbhcRhMVZbb5C2Q6+Htuac8ZrKSOWExNN DUqRkzeTib9u+cHxUTFFPgOGdUjDLmg3XHU7mvb+2hViluVjIImC4tqD5XPpv7vt WnaDJxLCGD/6DF2yhiVY9NysuxInLTNFFCF06LworZ4L24hlg5TvN0UeUNRO9954 ux6f+lSORCzV3TmrsHP5vwjSAW26FviPXV1q1HHJeTpWKMlhsZtHmOAJOtZKKmxP WFnHT0aiWF+sQf4qfxVQL+lLqtgRKJAI9zqGRyfDJWJp5aXdRuVsZs9pWNQF7lCo 5gVnCYk3ULjXG3b23j2S =tKTR -----END PGP SIGNATURE----- Merge tag 'for-f2fs-4.8' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs Pull f2fs updates from Jaegeuk Kim: "The major change in this version is mitigating cpu overheads on write paths by replacing redundant inode page updates with mark_inode_dirty calls. And we tried to reduce lock contentions as well to improve filesystem scalability. Other feature is setting F2FS automatically when detecting host-managed SMR. Enhancements: - ioctl to move a range of data between files - inject orphan inode errors - avoid flush commands congestion - support lazytime Bug fixes: - return proper results for some dentry operations - fix deadlock in add_link failure - disable extent_cache for fcollapse/finsert" * tag 'for-f2fs-4.8' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (68 commits) f2fs: clean up coding style and redundancy f2fs: get victim segment again after new cp f2fs: handle error case with f2fs_bug_on f2fs: avoid data race when deciding checkpoin in f2fs_sync_file f2fs: support an ioctl to move a range of data blocks f2fs: fix to report error number of f2fs_find_entry f2fs: avoid memory allocation failure due to a long length f2fs: reset default idle interval value f2fs: use blk_plug in all the possible paths f2fs: fix to avoid data update racing between GC and DIO f2fs: add maximum prefree segments f2fs: disable extent_cache for fcollapse/finsert inodes f2fs: refactor __exchange_data_block for speed up f2fs: fix ERR_PTR returned by bio f2fs: avoid mark_inode_dirty f2fs: move i_size_write in f2fs_write_end f2fs: fix to avoid redundant discard during fstrim f2fs: avoid mismatching block range for discard f2fs: fix incorrect f_bfree calculation in ->statfs f2fs: use percpu_rw_semaphore ...
2016-07-27 20:36:31 +03:00
if (!is_read_io(bio_op(bio))) {
unsigned int start;
if (type != DATA && type != NODE)
goto submit_io;
if (test_opt(sbi, LFS) && current->plug)
blk_finish_plug(current->plug);
if (F2FS_IO_ALIGNED(sbi))
goto submit_io;
start = bio->bi_iter.bi_size >> F2FS_BLKSIZE_BITS;
start %= F2FS_IO_SIZE(sbi);
if (start == 0)
goto submit_io;
/* fill dummy pages */
for (; start < F2FS_IO_SIZE(sbi); start++) {
struct page *page =
mempool_alloc(sbi->write_io_dummy,
GFP_NOIO | __GFP_NOFAIL);
f2fs_bug_on(sbi, !page);
zero_user_segment(page, 0, PAGE_SIZE);
SetPagePrivate(page);
set_page_private(page, (unsigned long)DUMMY_WRITTEN_PAGE);
lock_page(page);
if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE)
f2fs_bug_on(sbi, 1);
}
/*
* In the NODE case, we lose next block address chain. So, we
* need to do checkpoint in f2fs_sync_file.
*/
if (type == NODE)
set_sbi_flag(sbi, SBI_NEED_CP);
}
submit_io:
if (is_read_io(bio_op(bio)))
trace_f2fs_submit_read_bio(sbi->sb, type, bio);
else
trace_f2fs_submit_write_bio(sbi->sb, type, bio);
submit_bio(bio);
}
static void __submit_merged_bio(struct f2fs_bio_info *io)
{
struct f2fs_io_info *fio = &io->fio;
if (!io->bio)
return;
bio_set_op_attrs(io->bio, fio->op, fio->op_flags);
if (is_read_io(fio->op))
trace_f2fs_prepare_read_bio(io->sbi->sb, fio->type, io->bio);
else
trace_f2fs_prepare_write_bio(io->sbi->sb, fio->type, io->bio);
The major change in this version is mitigating cpu overheads on write paths by replacing redundant inode page updates with mark_inode_dirty calls. And we tried to reduce lock contentions as well to improve filesystem scalability. Other feature is setting F2FS automatically when detecting host-managed SMR. = Enhancement = - ioctl to move a range of data between files - inject orphan inode errors - avoid flush commands congestion - support lazytime = Bug fixes = - return proper results for some dentry operations - fix deadlock in add_link failure - disable extent_cache for fcollapse/finsert -----BEGIN PGP SIGNATURE----- Version: GnuPG v1 iQIcBAABAgAGBQJXmDJFAAoJEEAUqH6CSFDSJeYP/0ru8+5/ui5VTCdNPQB9KxYD DIUaDGpeoLvmn3ZdrMEdyNr6kWbgjCE9JjOGPQ7l1/apErOGVPyaBwflKcCDwloU pAlEqVM1Q9j4qH4i9SWTlvPtsHBHB7G7YSe3vDB9fJGSTqumubIlnaBm+Wfjx31U p53WcPn9LpOyzfmvZf2tOHmvZ7bWLkE/a07x9kPC6XHUFb9C17jLRFFGeuhZQHv1 Yo7HgokBnPExa8TnEILYyX/x+eecFS/1Cp/cN0STsebSu8pStTHTcAP7qEpKQB88 Cc51Lf+d5gFeydxKDFxwdH3VWOGIr9Ppako+lHW83gJcHP0zw8zdxULab+HJMa4n MOByRRiafwu1sL0dl7TCfsYNIHdEnXhWbhcRhMVZbb5C2Q6+Htuac8ZrKSOWExNN DUqRkzeTib9u+cHxUTFFPgOGdUjDLmg3XHU7mvb+2hViluVjIImC4tqD5XPpv7vt WnaDJxLCGD/6DF2yhiVY9NysuxInLTNFFCF06LworZ4L24hlg5TvN0UeUNRO9954 ux6f+lSORCzV3TmrsHP5vwjSAW26FviPXV1q1HHJeTpWKMlhsZtHmOAJOtZKKmxP WFnHT0aiWF+sQf4qfxVQL+lLqtgRKJAI9zqGRyfDJWJp5aXdRuVsZs9pWNQF7lCo 5gVnCYk3ULjXG3b23j2S =tKTR -----END PGP SIGNATURE----- Merge tag 'for-f2fs-4.8' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs Pull f2fs updates from Jaegeuk Kim: "The major change in this version is mitigating cpu overheads on write paths by replacing redundant inode page updates with mark_inode_dirty calls. And we tried to reduce lock contentions as well to improve filesystem scalability. Other feature is setting F2FS automatically when detecting host-managed SMR. Enhancements: - ioctl to move a range of data between files - inject orphan inode errors - avoid flush commands congestion - support lazytime Bug fixes: - return proper results for some dentry operations - fix deadlock in add_link failure - disable extent_cache for fcollapse/finsert" * tag 'for-f2fs-4.8' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (68 commits) f2fs: clean up coding style and redundancy f2fs: get victim segment again after new cp f2fs: handle error case with f2fs_bug_on f2fs: avoid data race when deciding checkpoin in f2fs_sync_file f2fs: support an ioctl to move a range of data blocks f2fs: fix to report error number of f2fs_find_entry f2fs: avoid memory allocation failure due to a long length f2fs: reset default idle interval value f2fs: use blk_plug in all the possible paths f2fs: fix to avoid data update racing between GC and DIO f2fs: add maximum prefree segments f2fs: disable extent_cache for fcollapse/finsert inodes f2fs: refactor __exchange_data_block for speed up f2fs: fix ERR_PTR returned by bio f2fs: avoid mark_inode_dirty f2fs: move i_size_write in f2fs_write_end f2fs: fix to avoid redundant discard during fstrim f2fs: avoid mismatching block range for discard f2fs: fix incorrect f_bfree calculation in ->statfs f2fs: use percpu_rw_semaphore ...
2016-07-27 20:36:31 +03:00
__submit_bio(io->sbi, io->bio, fio->type);
io->bio = NULL;
}
f2fs: add bio cache for IPU SQLite in Wal mode may trigger sequential IPU write in db-wal file, after commit d1b3e72d5490 ("f2fs: submit bio of in-place-update pages"), we lost the chance of merging page in inner managed bio cache, result in submitting more small-sized IO. So let's add temporary bio in writepages() to cache mergeable write IO as much as possible. Test case: 1. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" 2. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" Before: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65552, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65560, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65568, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65576, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65584, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65592, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65600, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65608, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65616, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65624, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65632, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65640, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65648, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65656, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65664, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57352, size = 4096 After: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 65536 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57368, size = 4096 Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-02-19 11:15:29 +03:00
static bool __has_merged_page(struct bio *bio, struct inode *inode,
struct page *page, nid_t ino)
{
struct bio_vec *bvec;
struct page *target;
struct bvec_iter_all iter_all;
f2fs: add bio cache for IPU SQLite in Wal mode may trigger sequential IPU write in db-wal file, after commit d1b3e72d5490 ("f2fs: submit bio of in-place-update pages"), we lost the chance of merging page in inner managed bio cache, result in submitting more small-sized IO. So let's add temporary bio in writepages() to cache mergeable write IO as much as possible. Test case: 1. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" 2. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" Before: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65552, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65560, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65568, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65576, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65584, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65592, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65600, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65608, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65616, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65624, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65632, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65640, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65648, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65656, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65664, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57352, size = 4096 After: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 65536 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57368, size = 4096 Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-02-19 11:15:29 +03:00
if (!bio)
return false;
if (!inode && !page && !ino)
return true;
f2fs: add bio cache for IPU SQLite in Wal mode may trigger sequential IPU write in db-wal file, after commit d1b3e72d5490 ("f2fs: submit bio of in-place-update pages"), we lost the chance of merging page in inner managed bio cache, result in submitting more small-sized IO. So let's add temporary bio in writepages() to cache mergeable write IO as much as possible. Test case: 1. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" 2. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" Before: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65552, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65560, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65568, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65576, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65584, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65592, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65600, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65608, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65616, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65624, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65632, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65640, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65648, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65656, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65664, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57352, size = 4096 After: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 65536 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57368, size = 4096 Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-02-19 11:15:29 +03:00
bio_for_each_segment_all(bvec, bio, iter_all) {
target = bvec->bv_page;
if (fscrypt_is_bounce_page(target))
target = fscrypt_pagecache_page(target);
if (inode && inode == target->mapping->host)
return true;
if (page && page == target)
return true;
if (ino && ino == ino_of_node(target))
return true;
}
return false;
}
static void __f2fs_submit_merged_write(struct f2fs_sb_info *sbi,
enum page_type type, enum temp_type temp)
{
enum page_type btype = PAGE_TYPE_OF_BIO(type);
struct f2fs_bio_info *io = sbi->write_io[btype] + temp;
down_write(&io->io_rwsem);
/* change META to META_FLUSH in the checkpoint procedure */
if (type >= META_FLUSH) {
io->fio.type = META_FLUSH;
io->fio.op = REQ_OP_WRITE;
io->fio.op_flags = REQ_META | REQ_PRIO | REQ_SYNC;
if (!test_opt(sbi, NOBARRIER))
io->fio.op_flags |= REQ_PREFLUSH | REQ_FUA;
}
__submit_merged_bio(io);
up_write(&io->io_rwsem);
}
static void __submit_merged_write_cond(struct f2fs_sb_info *sbi,
struct inode *inode, struct page *page,
nid_t ino, enum page_type type, bool force)
{
enum temp_type temp;
bool ret = true;
for (temp = HOT; temp < NR_TEMP_TYPE; temp++) {
if (!force) {
enum page_type btype = PAGE_TYPE_OF_BIO(type);
struct f2fs_bio_info *io = sbi->write_io[btype] + temp;
down_read(&io->io_rwsem);
f2fs: add bio cache for IPU SQLite in Wal mode may trigger sequential IPU write in db-wal file, after commit d1b3e72d5490 ("f2fs: submit bio of in-place-update pages"), we lost the chance of merging page in inner managed bio cache, result in submitting more small-sized IO. So let's add temporary bio in writepages() to cache mergeable write IO as much as possible. Test case: 1. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" 2. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" Before: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65552, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65560, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65568, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65576, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65584, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65592, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65600, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65608, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65616, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65624, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65632, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65640, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65648, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65656, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65664, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57352, size = 4096 After: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 65536 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57368, size = 4096 Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-02-19 11:15:29 +03:00
ret = __has_merged_page(io->bio, inode, page, ino);
up_read(&io->io_rwsem);
}
if (ret)
__f2fs_submit_merged_write(sbi, type, temp);
/* TODO: use HOT temp only for meta pages now. */
if (type >= META)
break;
}
}
void f2fs_submit_merged_write(struct f2fs_sb_info *sbi, enum page_type type)
{
__submit_merged_write_cond(sbi, NULL, NULL, 0, type, true);
}
void f2fs_submit_merged_write_cond(struct f2fs_sb_info *sbi,
struct inode *inode, struct page *page,
nid_t ino, enum page_type type)
{
__submit_merged_write_cond(sbi, inode, page, ino, type, false);
}
void f2fs_flush_merged_writes(struct f2fs_sb_info *sbi)
{
f2fs_submit_merged_write(sbi, DATA);
f2fs_submit_merged_write(sbi, NODE);
f2fs_submit_merged_write(sbi, META);
}
/*
* Fill the locked page with data located in the block address.
* A caller needs to unlock the page on failure.
*/
int f2fs_submit_page_bio(struct f2fs_io_info *fio)
{
struct bio *bio;
struct page *page = fio->encrypted_page ?
fio->encrypted_page : fio->page;
f2fs: fix to do sanity check with block address in main area This patch add to do sanity check with below field: - cp_pack_total_block_count - blkaddr of data/node - extent info - Overview BUG() in verify_block_addr() when writing to a corrupted f2fs image - Reproduce (4.18 upstream kernel) - POC (poc.c) static void activity(char *mpoint) { char *foo_bar_baz; int err; static int buf[8192]; memset(buf, 0, sizeof(buf)); err = asprintf(&foo_bar_baz, "%s/foo/bar/baz", mpoint); int fd = open(foo_bar_baz, O_RDWR | O_TRUNC, 0777); if (fd >= 0) { write(fd, (char *)buf, sizeof(buf)); fdatasync(fd); close(fd); } } int main(int argc, char *argv[]) { activity(argv[1]); return 0; } - Kernel message [ 689.349473] F2FS-fs (loop0): Mounted with checkpoint version = 3 [ 699.728662] WARNING: CPU: 0 PID: 1309 at fs/f2fs/segment.c:2860 f2fs_inplace_write_data+0x232/0x240 [ 699.728670] Modules linked in: snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_pcm snd_timer snd mac_hid i2c_piix4 soundcore ib_iser rdma_cm iw_cm ib_cm ib_core iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx raid1 raid0 multipath linear 8139too crct10dif_pclmul crc32_pclmul qxl drm_kms_helper syscopyarea aesni_intel sysfillrect sysimgblt fb_sys_fops ttm drm aes_x86_64 crypto_simd cryptd 8139cp glue_helper mii pata_acpi floppy [ 699.729056] CPU: 0 PID: 1309 Comm: a.out Not tainted 4.18.0-rc1+ #4 [ 699.729064] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.729074] RIP: 0010:f2fs_inplace_write_data+0x232/0x240 [ 699.729076] Code: ff e9 cf fe ff ff 49 8d 7d 10 e8 39 45 ad ff 4d 8b 7d 10 be 04 00 00 00 49 8d 7f 48 e8 07 49 ad ff 45 8b 7f 48 e9 fb fe ff ff <0f> 0b f0 41 80 4d 48 04 e9 65 fe ff ff 90 66 66 66 66 90 55 48 8d [ 699.729130] RSP: 0018:ffff8801f43af568 EFLAGS: 00010202 [ 699.729139] RAX: 000000000000003f RBX: ffff8801f43af7b8 RCX: ffffffffb88c9113 [ 699.729142] RDX: 0000000000000003 RSI: dffffc0000000000 RDI: ffff8802024e5540 [ 699.729144] RBP: ffff8801f43af590 R08: 0000000000000009 R09: ffffffffffffffe8 [ 699.729147] R10: 0000000000000001 R11: ffffed0039b0596a R12: ffff8802024e5540 [ 699.729149] R13: ffff8801f0335500 R14: ffff8801e3e7a700 R15: ffff8801e1ee4450 [ 699.729154] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.729156] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.729159] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.729171] Call Trace: [ 699.729192] f2fs_do_write_data_page+0x2e2/0xe00 [ 699.729203] ? f2fs_should_update_outplace+0xd0/0xd0 [ 699.729238] ? memcg_drain_all_list_lrus+0x280/0x280 [ 699.729269] ? __radix_tree_replace+0xa3/0x120 [ 699.729276] __write_data_page+0x5c7/0xe30 [ 699.729291] ? kasan_check_read+0x11/0x20 [ 699.729310] ? page_mapped+0x8a/0x110 [ 699.729321] ? page_mkclean+0xe9/0x160 [ 699.729327] ? f2fs_do_write_data_page+0xe00/0xe00 [ 699.729331] ? invalid_page_referenced_vma+0x130/0x130 [ 699.729345] ? clear_page_dirty_for_io+0x332/0x450 [ 699.729351] f2fs_write_cache_pages+0x4ca/0x860 [ 699.729358] ? __write_data_page+0xe30/0xe30 [ 699.729374] ? percpu_counter_add_batch+0x22/0xa0 [ 699.729380] ? kasan_check_write+0x14/0x20 [ 699.729391] ? _raw_spin_lock+0x17/0x40 [ 699.729403] ? f2fs_mark_inode_dirty_sync.part.18+0x16/0x30 [ 699.729413] ? iov_iter_advance+0x113/0x640 [ 699.729418] ? f2fs_write_end+0x133/0x2e0 [ 699.729423] ? balance_dirty_pages_ratelimited+0x239/0x640 [ 699.729428] f2fs_write_data_pages+0x329/0x520 [ 699.729433] ? generic_perform_write+0x250/0x320 [ 699.729438] ? f2fs_write_cache_pages+0x860/0x860 [ 699.729454] ? current_time+0x110/0x110 [ 699.729459] ? f2fs_preallocate_blocks+0x1ef/0x370 [ 699.729464] do_writepages+0x37/0xb0 [ 699.729468] ? f2fs_write_cache_pages+0x860/0x860 [ 699.729472] ? do_writepages+0x37/0xb0 [ 699.729478] __filemap_fdatawrite_range+0x19a/0x1f0 [ 699.729483] ? delete_from_page_cache_batch+0x4e0/0x4e0 [ 699.729496] ? __vfs_write+0x2b2/0x410 [ 699.729501] file_write_and_wait_range+0x66/0xb0 [ 699.729506] f2fs_do_sync_file+0x1f9/0xd90 [ 699.729511] ? truncate_partial_data_page+0x290/0x290 [ 699.729521] ? __sb_end_write+0x30/0x50 [ 699.729526] ? vfs_write+0x20f/0x260 [ 699.729530] f2fs_sync_file+0x9a/0xb0 [ 699.729534] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.729548] vfs_fsync_range+0x68/0x100 [ 699.729554] ? __fget_light+0xc9/0xe0 [ 699.729558] do_fsync+0x3d/0x70 [ 699.729562] __x64_sys_fdatasync+0x24/0x30 [ 699.729585] do_syscall_64+0x78/0x170 [ 699.729595] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 699.729613] RIP: 0033:0x7f9bf930d800 [ 699.729615] Code: 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 83 3d 49 bf 2c 00 00 75 10 b8 4b 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 be 78 01 00 48 89 04 24 [ 699.729668] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.729673] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.729675] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.729678] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.729680] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.729683] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.729687] ---[ end trace 4ce02f25ff7d3df5 ]--- [ 699.729782] ------------[ cut here ]------------ [ 699.729785] kernel BUG at fs/f2fs/segment.h:654! [ 699.731055] invalid opcode: 0000 [#1] SMP KASAN PTI [ 699.732104] CPU: 0 PID: 1309 Comm: a.out Tainted: G W 4.18.0-rc1+ #4 [ 699.733684] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.735611] RIP: 0010:f2fs_submit_page_bio+0x29b/0x730 [ 699.736649] Code: 54 49 8d bd 18 04 00 00 e8 b2 59 af ff 41 8b 8d 18 04 00 00 8b 45 b8 41 d3 e6 44 01 f0 4c 8d 73 14 41 39 c7 0f 82 37 fe ff ff <0f> 0b 65 8b 05 2c 04 77 47 89 c0 48 0f a3 05 52 c1 d5 01 0f 92 c0 [ 699.740524] RSP: 0018:ffff8801f43af508 EFLAGS: 00010283 [ 699.741573] RAX: 0000000000000000 RBX: ffff8801f43af7b8 RCX: ffffffffb88a7cef [ 699.743006] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8801e3e7a64c [ 699.744426] RBP: ffff8801f43af558 R08: ffffed003e066b55 R09: ffffed003e066b55 [ 699.745833] R10: 0000000000000001 R11: ffffed003e066b54 R12: ffffea0007876940 [ 699.747256] R13: ffff8801f0335500 R14: ffff8801e3e7a600 R15: 0000000000000001 [ 699.748683] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.750293] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.751462] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.752874] Call Trace: [ 699.753386] ? f2fs_inplace_write_data+0x93/0x240 [ 699.754341] f2fs_inplace_write_data+0xd2/0x240 [ 699.755271] f2fs_do_write_data_page+0x2e2/0xe00 [ 699.756214] ? f2fs_should_update_outplace+0xd0/0xd0 [ 699.757215] ? memcg_drain_all_list_lrus+0x280/0x280 [ 699.758209] ? __radix_tree_replace+0xa3/0x120 [ 699.759164] __write_data_page+0x5c7/0xe30 [ 699.760002] ? kasan_check_read+0x11/0x20 [ 699.760823] ? page_mapped+0x8a/0x110 [ 699.761573] ? page_mkclean+0xe9/0x160 [ 699.762345] ? f2fs_do_write_data_page+0xe00/0xe00 [ 699.763332] ? invalid_page_referenced_vma+0x130/0x130 [ 699.764374] ? clear_page_dirty_for_io+0x332/0x450 [ 699.765347] f2fs_write_cache_pages+0x4ca/0x860 [ 699.766276] ? __write_data_page+0xe30/0xe30 [ 699.767161] ? percpu_counter_add_batch+0x22/0xa0 [ 699.768112] ? kasan_check_write+0x14/0x20 [ 699.768951] ? _raw_spin_lock+0x17/0x40 [ 699.769739] ? f2fs_mark_inode_dirty_sync.part.18+0x16/0x30 [ 699.770885] ? iov_iter_advance+0x113/0x640 [ 699.771743] ? f2fs_write_end+0x133/0x2e0 [ 699.772569] ? balance_dirty_pages_ratelimited+0x239/0x640 [ 699.773680] f2fs_write_data_pages+0x329/0x520 [ 699.774603] ? generic_perform_write+0x250/0x320 [ 699.775544] ? f2fs_write_cache_pages+0x860/0x860 [ 699.776510] ? current_time+0x110/0x110 [ 699.777299] ? f2fs_preallocate_blocks+0x1ef/0x370 [ 699.778279] do_writepages+0x37/0xb0 [ 699.779026] ? f2fs_write_cache_pages+0x860/0x860 [ 699.779978] ? do_writepages+0x37/0xb0 [ 699.780755] __filemap_fdatawrite_range+0x19a/0x1f0 [ 699.781746] ? delete_from_page_cache_batch+0x4e0/0x4e0 [ 699.782820] ? __vfs_write+0x2b2/0x410 [ 699.783597] file_write_and_wait_range+0x66/0xb0 [ 699.784540] f2fs_do_sync_file+0x1f9/0xd90 [ 699.785381] ? truncate_partial_data_page+0x290/0x290 [ 699.786415] ? __sb_end_write+0x30/0x50 [ 699.787204] ? vfs_write+0x20f/0x260 [ 699.787941] f2fs_sync_file+0x9a/0xb0 [ 699.788694] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.789572] vfs_fsync_range+0x68/0x100 [ 699.790360] ? __fget_light+0xc9/0xe0 [ 699.791128] do_fsync+0x3d/0x70 [ 699.791779] __x64_sys_fdatasync+0x24/0x30 [ 699.792614] do_syscall_64+0x78/0x170 [ 699.793371] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 699.794406] RIP: 0033:0x7f9bf930d800 [ 699.795134] Code: 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 83 3d 49 bf 2c 00 00 75 10 b8 4b 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 be 78 01 00 48 89 04 24 [ 699.798960] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.800483] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.801923] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.803373] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.804798] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.806233] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.807667] Modules linked in: snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_pcm snd_timer snd mac_hid i2c_piix4 soundcore ib_iser rdma_cm iw_cm ib_cm ib_core iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx raid1 raid0 multipath linear 8139too crct10dif_pclmul crc32_pclmul qxl drm_kms_helper syscopyarea aesni_intel sysfillrect sysimgblt fb_sys_fops ttm drm aes_x86_64 crypto_simd cryptd 8139cp glue_helper mii pata_acpi floppy [ 699.817079] ---[ end trace 4ce02f25ff7d3df6 ]--- [ 699.818068] RIP: 0010:f2fs_submit_page_bio+0x29b/0x730 [ 699.819114] Code: 54 49 8d bd 18 04 00 00 e8 b2 59 af ff 41 8b 8d 18 04 00 00 8b 45 b8 41 d3 e6 44 01 f0 4c 8d 73 14 41 39 c7 0f 82 37 fe ff ff <0f> 0b 65 8b 05 2c 04 77 47 89 c0 48 0f a3 05 52 c1 d5 01 0f 92 c0 [ 699.822919] RSP: 0018:ffff8801f43af508 EFLAGS: 00010283 [ 699.823977] RAX: 0000000000000000 RBX: ffff8801f43af7b8 RCX: ffffffffb88a7cef [ 699.825436] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8801e3e7a64c [ 699.826881] RBP: ffff8801f43af558 R08: ffffed003e066b55 R09: ffffed003e066b55 [ 699.828292] R10: 0000000000000001 R11: ffffed003e066b54 R12: ffffea0007876940 [ 699.829750] R13: ffff8801f0335500 R14: ffff8801e3e7a600 R15: 0000000000000001 [ 699.831192] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.832793] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.833981] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.835556] ================================================================== [ 699.837029] BUG: KASAN: stack-out-of-bounds in update_stack_state+0x38c/0x3e0 [ 699.838462] Read of size 8 at addr ffff8801f43af970 by task a.out/1309 [ 699.840086] CPU: 0 PID: 1309 Comm: a.out Tainted: G D W 4.18.0-rc1+ #4 [ 699.841603] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.843475] Call Trace: [ 699.843982] dump_stack+0x7b/0xb5 [ 699.844661] print_address_description+0x70/0x290 [ 699.845607] kasan_report+0x291/0x390 [ 699.846351] ? update_stack_state+0x38c/0x3e0 [ 699.853831] __asan_load8+0x54/0x90 [ 699.854569] update_stack_state+0x38c/0x3e0 [ 699.855428] ? __read_once_size_nocheck.constprop.7+0x20/0x20 [ 699.856601] ? __save_stack_trace+0x5e/0x100 [ 699.857476] unwind_next_frame.part.5+0x18e/0x490 [ 699.858448] ? unwind_dump+0x290/0x290 [ 699.859217] ? clear_page_dirty_for_io+0x332/0x450 [ 699.860185] __unwind_start+0x106/0x190 [ 699.860974] __save_stack_trace+0x5e/0x100 [ 699.861808] ? __save_stack_trace+0x5e/0x100 [ 699.862691] ? unlink_anon_vmas+0xba/0x2c0 [ 699.863525] save_stack_trace+0x1f/0x30 [ 699.864312] save_stack+0x46/0xd0 [ 699.864993] ? __alloc_pages_slowpath+0x1420/0x1420 [ 699.865990] ? flush_tlb_mm_range+0x15e/0x220 [ 699.866889] ? kasan_check_write+0x14/0x20 [ 699.867724] ? __dec_node_state+0x92/0xb0 [ 699.868543] ? lock_page_memcg+0x85/0xf0 [ 699.869350] ? unlock_page_memcg+0x16/0x80 [ 699.870185] ? page_remove_rmap+0x198/0x520 [ 699.871048] ? mark_page_accessed+0x133/0x200 [ 699.871930] ? _cond_resched+0x1a/0x50 [ 699.872700] ? unmap_page_range+0xcd4/0xe50 [ 699.873551] ? rb_next+0x58/0x80 [ 699.874217] ? rb_next+0x58/0x80 [ 699.874895] __kasan_slab_free+0x13c/0x1a0 [ 699.875734] ? unlink_anon_vmas+0xba/0x2c0 [ 699.876563] kasan_slab_free+0xe/0x10 [ 699.877315] kmem_cache_free+0x89/0x1e0 [ 699.878095] unlink_anon_vmas+0xba/0x2c0 [ 699.878913] free_pgtables+0x101/0x1b0 [ 699.879677] exit_mmap+0x146/0x2a0 [ 699.880378] ? __ia32_sys_munmap+0x50/0x50 [ 699.881214] ? kasan_check_read+0x11/0x20 [ 699.882052] ? mm_update_next_owner+0x322/0x380 [ 699.882985] mmput+0x8b/0x1d0 [ 699.883602] do_exit+0x43a/0x1390 [ 699.884288] ? mm_update_next_owner+0x380/0x380 [ 699.885212] ? f2fs_sync_file+0x9a/0xb0 [ 699.885995] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.886877] ? vfs_fsync_range+0x68/0x100 [ 699.887694] ? __fget_light+0xc9/0xe0 [ 699.888442] ? do_fsync+0x3d/0x70 [ 699.889118] ? __x64_sys_fdatasync+0x24/0x30 [ 699.889996] rewind_stack_do_exit+0x17/0x20 [ 699.890860] RIP: 0033:0x7f9bf930d800 [ 699.891585] Code: Bad RIP value. [ 699.892268] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.893781] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.895220] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.896643] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.898069] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.899505] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.901241] The buggy address belongs to the page: [ 699.902215] page:ffffea0007d0ebc0 count:0 mapcount:0 mapping:0000000000000000 index:0x0 [ 699.903811] flags: 0x2ffff0000000000() [ 699.904585] raw: 02ffff0000000000 0000000000000000 ffffffff07d00101 0000000000000000 [ 699.906125] raw: 0000000000000000 0000000000240000 00000000ffffffff 0000000000000000 [ 699.907673] page dumped because: kasan: bad access detected [ 699.909108] Memory state around the buggy address: [ 699.910077] ffff8801f43af800: 00 f1 f1 f1 f1 00 f4 f4 f4 f3 f3 f3 f3 00 00 00 [ 699.911528] ffff8801f43af880: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 699.912953] >ffff8801f43af900: 00 00 00 00 00 00 00 00 f1 01 f4 f4 f4 f2 f2 f2 [ 699.914392] ^ [ 699.915758] ffff8801f43af980: f2 00 f4 f4 00 00 00 00 f2 00 00 00 00 00 00 00 [ 699.917193] ffff8801f43afa00: 00 00 00 00 00 00 00 00 00 f3 f3 f3 00 00 00 00 [ 699.918634] ================================================================== - Location https://elixir.bootlin.com/linux/v4.18-rc1/source/fs/f2fs/segment.h#L644 Reported-by Wen Xu <wen.xu@gatech.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-08-01 14:13:44 +03:00
if (!f2fs_is_valid_blkaddr(fio->sbi, fio->new_blkaddr,
f2fs: introduce DATA_GENERIC_ENHANCE Previously, f2fs_is_valid_blkaddr(, blkaddr, DATA_GENERIC) will check whether @blkaddr locates in main area or not. That check is weak, since the block address in range of main area can point to the address which is not valid in segment info table, and we can not detect such condition, we may suffer worse corruption as system continues running. So this patch introduce DATA_GENERIC_ENHANCE to enhance the sanity check which trigger SIT bitmap check rather than only range check. This patch did below changes as wel: - set SBI_NEED_FSCK in f2fs_is_valid_blkaddr(). - get rid of is_valid_data_blkaddr() to avoid panic if blkaddr is invalid. - introduce verify_fio_blkaddr() to wrap fio {new,old}_blkaddr validation check. - spread blkaddr check in: * f2fs_get_node_info() * __read_out_blkaddrs() * f2fs_submit_page_read() * ra_data_block() * do_recover_data() This patch can fix bug reported from bugzilla below: https://bugzilla.kernel.org/show_bug.cgi?id=203215 https://bugzilla.kernel.org/show_bug.cgi?id=203223 https://bugzilla.kernel.org/show_bug.cgi?id=203231 https://bugzilla.kernel.org/show_bug.cgi?id=203235 https://bugzilla.kernel.org/show_bug.cgi?id=203241 = Update by Jaegeuk Kim = DATA_GENERIC_ENHANCE enhanced to validate block addresses on read/write paths. But, xfstest/generic/446 compalins some generated kernel messages saying invalid bitmap was detected when reading a block. The reaons is, when we get the block addresses from extent_cache, there is no lock to synchronize it from truncating the blocks in parallel. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-15 10:26:32 +03:00
fio->is_por ? META_POR : (__is_meta_io(fio) ?
META_GENERIC : DATA_GENERIC_ENHANCE)))
return -EFSCORRUPTED;
f2fs: fix to do sanity check with block address in main area This patch add to do sanity check with below field: - cp_pack_total_block_count - blkaddr of data/node - extent info - Overview BUG() in verify_block_addr() when writing to a corrupted f2fs image - Reproduce (4.18 upstream kernel) - POC (poc.c) static void activity(char *mpoint) { char *foo_bar_baz; int err; static int buf[8192]; memset(buf, 0, sizeof(buf)); err = asprintf(&foo_bar_baz, "%s/foo/bar/baz", mpoint); int fd = open(foo_bar_baz, O_RDWR | O_TRUNC, 0777); if (fd >= 0) { write(fd, (char *)buf, sizeof(buf)); fdatasync(fd); close(fd); } } int main(int argc, char *argv[]) { activity(argv[1]); return 0; } - Kernel message [ 689.349473] F2FS-fs (loop0): Mounted with checkpoint version = 3 [ 699.728662] WARNING: CPU: 0 PID: 1309 at fs/f2fs/segment.c:2860 f2fs_inplace_write_data+0x232/0x240 [ 699.728670] Modules linked in: snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_pcm snd_timer snd mac_hid i2c_piix4 soundcore ib_iser rdma_cm iw_cm ib_cm ib_core iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx raid1 raid0 multipath linear 8139too crct10dif_pclmul crc32_pclmul qxl drm_kms_helper syscopyarea aesni_intel sysfillrect sysimgblt fb_sys_fops ttm drm aes_x86_64 crypto_simd cryptd 8139cp glue_helper mii pata_acpi floppy [ 699.729056] CPU: 0 PID: 1309 Comm: a.out Not tainted 4.18.0-rc1+ #4 [ 699.729064] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.729074] RIP: 0010:f2fs_inplace_write_data+0x232/0x240 [ 699.729076] Code: ff e9 cf fe ff ff 49 8d 7d 10 e8 39 45 ad ff 4d 8b 7d 10 be 04 00 00 00 49 8d 7f 48 e8 07 49 ad ff 45 8b 7f 48 e9 fb fe ff ff <0f> 0b f0 41 80 4d 48 04 e9 65 fe ff ff 90 66 66 66 66 90 55 48 8d [ 699.729130] RSP: 0018:ffff8801f43af568 EFLAGS: 00010202 [ 699.729139] RAX: 000000000000003f RBX: ffff8801f43af7b8 RCX: ffffffffb88c9113 [ 699.729142] RDX: 0000000000000003 RSI: dffffc0000000000 RDI: ffff8802024e5540 [ 699.729144] RBP: ffff8801f43af590 R08: 0000000000000009 R09: ffffffffffffffe8 [ 699.729147] R10: 0000000000000001 R11: ffffed0039b0596a R12: ffff8802024e5540 [ 699.729149] R13: ffff8801f0335500 R14: ffff8801e3e7a700 R15: ffff8801e1ee4450 [ 699.729154] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.729156] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.729159] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.729171] Call Trace: [ 699.729192] f2fs_do_write_data_page+0x2e2/0xe00 [ 699.729203] ? f2fs_should_update_outplace+0xd0/0xd0 [ 699.729238] ? memcg_drain_all_list_lrus+0x280/0x280 [ 699.729269] ? __radix_tree_replace+0xa3/0x120 [ 699.729276] __write_data_page+0x5c7/0xe30 [ 699.729291] ? kasan_check_read+0x11/0x20 [ 699.729310] ? page_mapped+0x8a/0x110 [ 699.729321] ? page_mkclean+0xe9/0x160 [ 699.729327] ? f2fs_do_write_data_page+0xe00/0xe00 [ 699.729331] ? invalid_page_referenced_vma+0x130/0x130 [ 699.729345] ? clear_page_dirty_for_io+0x332/0x450 [ 699.729351] f2fs_write_cache_pages+0x4ca/0x860 [ 699.729358] ? __write_data_page+0xe30/0xe30 [ 699.729374] ? percpu_counter_add_batch+0x22/0xa0 [ 699.729380] ? kasan_check_write+0x14/0x20 [ 699.729391] ? _raw_spin_lock+0x17/0x40 [ 699.729403] ? f2fs_mark_inode_dirty_sync.part.18+0x16/0x30 [ 699.729413] ? iov_iter_advance+0x113/0x640 [ 699.729418] ? f2fs_write_end+0x133/0x2e0 [ 699.729423] ? balance_dirty_pages_ratelimited+0x239/0x640 [ 699.729428] f2fs_write_data_pages+0x329/0x520 [ 699.729433] ? generic_perform_write+0x250/0x320 [ 699.729438] ? f2fs_write_cache_pages+0x860/0x860 [ 699.729454] ? current_time+0x110/0x110 [ 699.729459] ? f2fs_preallocate_blocks+0x1ef/0x370 [ 699.729464] do_writepages+0x37/0xb0 [ 699.729468] ? f2fs_write_cache_pages+0x860/0x860 [ 699.729472] ? do_writepages+0x37/0xb0 [ 699.729478] __filemap_fdatawrite_range+0x19a/0x1f0 [ 699.729483] ? delete_from_page_cache_batch+0x4e0/0x4e0 [ 699.729496] ? __vfs_write+0x2b2/0x410 [ 699.729501] file_write_and_wait_range+0x66/0xb0 [ 699.729506] f2fs_do_sync_file+0x1f9/0xd90 [ 699.729511] ? truncate_partial_data_page+0x290/0x290 [ 699.729521] ? __sb_end_write+0x30/0x50 [ 699.729526] ? vfs_write+0x20f/0x260 [ 699.729530] f2fs_sync_file+0x9a/0xb0 [ 699.729534] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.729548] vfs_fsync_range+0x68/0x100 [ 699.729554] ? __fget_light+0xc9/0xe0 [ 699.729558] do_fsync+0x3d/0x70 [ 699.729562] __x64_sys_fdatasync+0x24/0x30 [ 699.729585] do_syscall_64+0x78/0x170 [ 699.729595] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 699.729613] RIP: 0033:0x7f9bf930d800 [ 699.729615] Code: 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 83 3d 49 bf 2c 00 00 75 10 b8 4b 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 be 78 01 00 48 89 04 24 [ 699.729668] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.729673] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.729675] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.729678] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.729680] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.729683] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.729687] ---[ end trace 4ce02f25ff7d3df5 ]--- [ 699.729782] ------------[ cut here ]------------ [ 699.729785] kernel BUG at fs/f2fs/segment.h:654! [ 699.731055] invalid opcode: 0000 [#1] SMP KASAN PTI [ 699.732104] CPU: 0 PID: 1309 Comm: a.out Tainted: G W 4.18.0-rc1+ #4 [ 699.733684] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.735611] RIP: 0010:f2fs_submit_page_bio+0x29b/0x730 [ 699.736649] Code: 54 49 8d bd 18 04 00 00 e8 b2 59 af ff 41 8b 8d 18 04 00 00 8b 45 b8 41 d3 e6 44 01 f0 4c 8d 73 14 41 39 c7 0f 82 37 fe ff ff <0f> 0b 65 8b 05 2c 04 77 47 89 c0 48 0f a3 05 52 c1 d5 01 0f 92 c0 [ 699.740524] RSP: 0018:ffff8801f43af508 EFLAGS: 00010283 [ 699.741573] RAX: 0000000000000000 RBX: ffff8801f43af7b8 RCX: ffffffffb88a7cef [ 699.743006] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8801e3e7a64c [ 699.744426] RBP: ffff8801f43af558 R08: ffffed003e066b55 R09: ffffed003e066b55 [ 699.745833] R10: 0000000000000001 R11: ffffed003e066b54 R12: ffffea0007876940 [ 699.747256] R13: ffff8801f0335500 R14: ffff8801e3e7a600 R15: 0000000000000001 [ 699.748683] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.750293] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.751462] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.752874] Call Trace: [ 699.753386] ? f2fs_inplace_write_data+0x93/0x240 [ 699.754341] f2fs_inplace_write_data+0xd2/0x240 [ 699.755271] f2fs_do_write_data_page+0x2e2/0xe00 [ 699.756214] ? f2fs_should_update_outplace+0xd0/0xd0 [ 699.757215] ? memcg_drain_all_list_lrus+0x280/0x280 [ 699.758209] ? __radix_tree_replace+0xa3/0x120 [ 699.759164] __write_data_page+0x5c7/0xe30 [ 699.760002] ? kasan_check_read+0x11/0x20 [ 699.760823] ? page_mapped+0x8a/0x110 [ 699.761573] ? page_mkclean+0xe9/0x160 [ 699.762345] ? f2fs_do_write_data_page+0xe00/0xe00 [ 699.763332] ? invalid_page_referenced_vma+0x130/0x130 [ 699.764374] ? clear_page_dirty_for_io+0x332/0x450 [ 699.765347] f2fs_write_cache_pages+0x4ca/0x860 [ 699.766276] ? __write_data_page+0xe30/0xe30 [ 699.767161] ? percpu_counter_add_batch+0x22/0xa0 [ 699.768112] ? kasan_check_write+0x14/0x20 [ 699.768951] ? _raw_spin_lock+0x17/0x40 [ 699.769739] ? f2fs_mark_inode_dirty_sync.part.18+0x16/0x30 [ 699.770885] ? iov_iter_advance+0x113/0x640 [ 699.771743] ? f2fs_write_end+0x133/0x2e0 [ 699.772569] ? balance_dirty_pages_ratelimited+0x239/0x640 [ 699.773680] f2fs_write_data_pages+0x329/0x520 [ 699.774603] ? generic_perform_write+0x250/0x320 [ 699.775544] ? f2fs_write_cache_pages+0x860/0x860 [ 699.776510] ? current_time+0x110/0x110 [ 699.777299] ? f2fs_preallocate_blocks+0x1ef/0x370 [ 699.778279] do_writepages+0x37/0xb0 [ 699.779026] ? f2fs_write_cache_pages+0x860/0x860 [ 699.779978] ? do_writepages+0x37/0xb0 [ 699.780755] __filemap_fdatawrite_range+0x19a/0x1f0 [ 699.781746] ? delete_from_page_cache_batch+0x4e0/0x4e0 [ 699.782820] ? __vfs_write+0x2b2/0x410 [ 699.783597] file_write_and_wait_range+0x66/0xb0 [ 699.784540] f2fs_do_sync_file+0x1f9/0xd90 [ 699.785381] ? truncate_partial_data_page+0x290/0x290 [ 699.786415] ? __sb_end_write+0x30/0x50 [ 699.787204] ? vfs_write+0x20f/0x260 [ 699.787941] f2fs_sync_file+0x9a/0xb0 [ 699.788694] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.789572] vfs_fsync_range+0x68/0x100 [ 699.790360] ? __fget_light+0xc9/0xe0 [ 699.791128] do_fsync+0x3d/0x70 [ 699.791779] __x64_sys_fdatasync+0x24/0x30 [ 699.792614] do_syscall_64+0x78/0x170 [ 699.793371] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 699.794406] RIP: 0033:0x7f9bf930d800 [ 699.795134] Code: 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 83 3d 49 bf 2c 00 00 75 10 b8 4b 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 be 78 01 00 48 89 04 24 [ 699.798960] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.800483] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.801923] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.803373] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.804798] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.806233] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.807667] Modules linked in: snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_pcm snd_timer snd mac_hid i2c_piix4 soundcore ib_iser rdma_cm iw_cm ib_cm ib_core iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx raid1 raid0 multipath linear 8139too crct10dif_pclmul crc32_pclmul qxl drm_kms_helper syscopyarea aesni_intel sysfillrect sysimgblt fb_sys_fops ttm drm aes_x86_64 crypto_simd cryptd 8139cp glue_helper mii pata_acpi floppy [ 699.817079] ---[ end trace 4ce02f25ff7d3df6 ]--- [ 699.818068] RIP: 0010:f2fs_submit_page_bio+0x29b/0x730 [ 699.819114] Code: 54 49 8d bd 18 04 00 00 e8 b2 59 af ff 41 8b 8d 18 04 00 00 8b 45 b8 41 d3 e6 44 01 f0 4c 8d 73 14 41 39 c7 0f 82 37 fe ff ff <0f> 0b 65 8b 05 2c 04 77 47 89 c0 48 0f a3 05 52 c1 d5 01 0f 92 c0 [ 699.822919] RSP: 0018:ffff8801f43af508 EFLAGS: 00010283 [ 699.823977] RAX: 0000000000000000 RBX: ffff8801f43af7b8 RCX: ffffffffb88a7cef [ 699.825436] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8801e3e7a64c [ 699.826881] RBP: ffff8801f43af558 R08: ffffed003e066b55 R09: ffffed003e066b55 [ 699.828292] R10: 0000000000000001 R11: ffffed003e066b54 R12: ffffea0007876940 [ 699.829750] R13: ffff8801f0335500 R14: ffff8801e3e7a600 R15: 0000000000000001 [ 699.831192] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.832793] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.833981] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.835556] ================================================================== [ 699.837029] BUG: KASAN: stack-out-of-bounds in update_stack_state+0x38c/0x3e0 [ 699.838462] Read of size 8 at addr ffff8801f43af970 by task a.out/1309 [ 699.840086] CPU: 0 PID: 1309 Comm: a.out Tainted: G D W 4.18.0-rc1+ #4 [ 699.841603] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.843475] Call Trace: [ 699.843982] dump_stack+0x7b/0xb5 [ 699.844661] print_address_description+0x70/0x290 [ 699.845607] kasan_report+0x291/0x390 [ 699.846351] ? update_stack_state+0x38c/0x3e0 [ 699.853831] __asan_load8+0x54/0x90 [ 699.854569] update_stack_state+0x38c/0x3e0 [ 699.855428] ? __read_once_size_nocheck.constprop.7+0x20/0x20 [ 699.856601] ? __save_stack_trace+0x5e/0x100 [ 699.857476] unwind_next_frame.part.5+0x18e/0x490 [ 699.858448] ? unwind_dump+0x290/0x290 [ 699.859217] ? clear_page_dirty_for_io+0x332/0x450 [ 699.860185] __unwind_start+0x106/0x190 [ 699.860974] __save_stack_trace+0x5e/0x100 [ 699.861808] ? __save_stack_trace+0x5e/0x100 [ 699.862691] ? unlink_anon_vmas+0xba/0x2c0 [ 699.863525] save_stack_trace+0x1f/0x30 [ 699.864312] save_stack+0x46/0xd0 [ 699.864993] ? __alloc_pages_slowpath+0x1420/0x1420 [ 699.865990] ? flush_tlb_mm_range+0x15e/0x220 [ 699.866889] ? kasan_check_write+0x14/0x20 [ 699.867724] ? __dec_node_state+0x92/0xb0 [ 699.868543] ? lock_page_memcg+0x85/0xf0 [ 699.869350] ? unlock_page_memcg+0x16/0x80 [ 699.870185] ? page_remove_rmap+0x198/0x520 [ 699.871048] ? mark_page_accessed+0x133/0x200 [ 699.871930] ? _cond_resched+0x1a/0x50 [ 699.872700] ? unmap_page_range+0xcd4/0xe50 [ 699.873551] ? rb_next+0x58/0x80 [ 699.874217] ? rb_next+0x58/0x80 [ 699.874895] __kasan_slab_free+0x13c/0x1a0 [ 699.875734] ? unlink_anon_vmas+0xba/0x2c0 [ 699.876563] kasan_slab_free+0xe/0x10 [ 699.877315] kmem_cache_free+0x89/0x1e0 [ 699.878095] unlink_anon_vmas+0xba/0x2c0 [ 699.878913] free_pgtables+0x101/0x1b0 [ 699.879677] exit_mmap+0x146/0x2a0 [ 699.880378] ? __ia32_sys_munmap+0x50/0x50 [ 699.881214] ? kasan_check_read+0x11/0x20 [ 699.882052] ? mm_update_next_owner+0x322/0x380 [ 699.882985] mmput+0x8b/0x1d0 [ 699.883602] do_exit+0x43a/0x1390 [ 699.884288] ? mm_update_next_owner+0x380/0x380 [ 699.885212] ? f2fs_sync_file+0x9a/0xb0 [ 699.885995] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.886877] ? vfs_fsync_range+0x68/0x100 [ 699.887694] ? __fget_light+0xc9/0xe0 [ 699.888442] ? do_fsync+0x3d/0x70 [ 699.889118] ? __x64_sys_fdatasync+0x24/0x30 [ 699.889996] rewind_stack_do_exit+0x17/0x20 [ 699.890860] RIP: 0033:0x7f9bf930d800 [ 699.891585] Code: Bad RIP value. [ 699.892268] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.893781] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.895220] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.896643] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.898069] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.899505] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.901241] The buggy address belongs to the page: [ 699.902215] page:ffffea0007d0ebc0 count:0 mapcount:0 mapping:0000000000000000 index:0x0 [ 699.903811] flags: 0x2ffff0000000000() [ 699.904585] raw: 02ffff0000000000 0000000000000000 ffffffff07d00101 0000000000000000 [ 699.906125] raw: 0000000000000000 0000000000240000 00000000ffffffff 0000000000000000 [ 699.907673] page dumped because: kasan: bad access detected [ 699.909108] Memory state around the buggy address: [ 699.910077] ffff8801f43af800: 00 f1 f1 f1 f1 00 f4 f4 f4 f3 f3 f3 f3 00 00 00 [ 699.911528] ffff8801f43af880: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 699.912953] >ffff8801f43af900: 00 00 00 00 00 00 00 00 f1 01 f4 f4 f4 f2 f2 f2 [ 699.914392] ^ [ 699.915758] ffff8801f43af980: f2 00 f4 f4 00 00 00 00 f2 00 00 00 00 00 00 00 [ 699.917193] ffff8801f43afa00: 00 00 00 00 00 00 00 00 00 f3 f3 f3 00 00 00 00 [ 699.918634] ================================================================== - Location https://elixir.bootlin.com/linux/v4.18-rc1/source/fs/f2fs/segment.h#L644 Reported-by Wen Xu <wen.xu@gatech.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-08-01 14:13:44 +03:00
trace_f2fs_submit_page_bio(page, fio);
f2fs_trace_ios(fio, 0);
/* Allocate a new bio */
bio = __bio_alloc(fio, 1);
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 15:29:47 +03:00
if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
bio_put(bio);
return -EFAULT;
}
if (fio->io_wbc && !is_read_io(fio->op))
wbc_account_cgroup_owner(fio->io_wbc, page, PAGE_SIZE);
bio_set_op_attrs(bio, fio->op, fio->op_flags);
inc_page_count(fio->sbi, is_read_io(fio->op) ?
__read_io_type(page): WB_DATA_TYPE(fio->page));
__submit_bio(fio->sbi, bio, fio->type);
return 0;
}
static bool page_is_mergeable(struct f2fs_sb_info *sbi, struct bio *bio,
block_t last_blkaddr, block_t cur_blkaddr)
{
if (last_blkaddr + 1 != cur_blkaddr)
return false;
return __same_bdev(sbi, cur_blkaddr, bio);
}
static bool io_type_is_mergeable(struct f2fs_bio_info *io,
struct f2fs_io_info *fio)
{
if (io->fio.op != fio->op)
return false;
return io->fio.op_flags == fio->op_flags;
}
static bool io_is_mergeable(struct f2fs_sb_info *sbi, struct bio *bio,
struct f2fs_bio_info *io,
struct f2fs_io_info *fio,
block_t last_blkaddr,
block_t cur_blkaddr)
{
if (F2FS_IO_ALIGNED(sbi) && (fio->type == DATA || fio->type == NODE)) {
unsigned int filled_blocks =
F2FS_BYTES_TO_BLK(bio->bi_iter.bi_size);
unsigned int io_size = F2FS_IO_SIZE(sbi);
unsigned int left_vecs = bio->bi_max_vecs - bio->bi_vcnt;
/* IOs in bio is aligned and left space of vectors is not enough */
if (!(filled_blocks % io_size) && left_vecs < io_size)
return false;
}
if (!page_is_mergeable(sbi, bio, last_blkaddr, cur_blkaddr))
return false;
return io_type_is_mergeable(io, fio);
}
static void add_bio_entry(struct f2fs_sb_info *sbi, struct bio *bio,
struct page *page, enum temp_type temp)
{
struct f2fs_bio_info *io = sbi->write_io[DATA] + temp;
struct bio_entry *be;
be = f2fs_kmem_cache_alloc(bio_entry_slab, GFP_NOFS);
be->bio = bio;
bio_get(bio);
if (bio_add_page(bio, page, PAGE_SIZE, 0) != PAGE_SIZE)
f2fs_bug_on(sbi, 1);
down_write(&io->bio_list_lock);
list_add_tail(&be->list, &io->bio_list);
up_write(&io->bio_list_lock);
}
static void del_bio_entry(struct bio_entry *be)
{
list_del(&be->list);
kmem_cache_free(bio_entry_slab, be);
}
static int add_ipu_page(struct f2fs_sb_info *sbi, struct bio **bio,
struct page *page)
{
enum temp_type temp;
bool found = false;
int ret = -EAGAIN;
for (temp = HOT; temp < NR_TEMP_TYPE && !found; temp++) {
struct f2fs_bio_info *io = sbi->write_io[DATA] + temp;
struct list_head *head = &io->bio_list;
struct bio_entry *be;
down_write(&io->bio_list_lock);
list_for_each_entry(be, head, list) {
if (be->bio != *bio)
continue;
found = true;
if (bio_add_page(*bio, page, PAGE_SIZE, 0) == PAGE_SIZE) {
ret = 0;
break;
}
/* bio is full */
del_bio_entry(be);
__submit_bio(sbi, *bio, DATA);
break;
}
up_write(&io->bio_list_lock);
}
if (ret) {
bio_put(*bio);
*bio = NULL;
}
return ret;
}
void f2fs_submit_merged_ipu_write(struct f2fs_sb_info *sbi,
struct bio **bio, struct page *page)
{
enum temp_type temp;
bool found = false;
struct bio *target = bio ? *bio : NULL;
for (temp = HOT; temp < NR_TEMP_TYPE && !found; temp++) {
struct f2fs_bio_info *io = sbi->write_io[DATA] + temp;
struct list_head *head = &io->bio_list;
struct bio_entry *be;
if (list_empty(head))
continue;
down_read(&io->bio_list_lock);
list_for_each_entry(be, head, list) {
if (target)
found = (target == be->bio);
else
found = __has_merged_page(be->bio, NULL,
page, 0);
if (found)
break;
}
up_read(&io->bio_list_lock);
if (!found)
continue;
found = false;
down_write(&io->bio_list_lock);
list_for_each_entry(be, head, list) {
if (target)
found = (target == be->bio);
else
found = __has_merged_page(be->bio, NULL,
page, 0);
if (found) {
target = be->bio;
del_bio_entry(be);
break;
}
}
up_write(&io->bio_list_lock);
}
if (found)
__submit_bio(sbi, target, DATA);
if (bio && *bio) {
bio_put(*bio);
*bio = NULL;
}
}
f2fs: add bio cache for IPU SQLite in Wal mode may trigger sequential IPU write in db-wal file, after commit d1b3e72d5490 ("f2fs: submit bio of in-place-update pages"), we lost the chance of merging page in inner managed bio cache, result in submitting more small-sized IO. So let's add temporary bio in writepages() to cache mergeable write IO as much as possible. Test case: 1. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" 2. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" Before: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65552, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65560, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65568, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65576, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65584, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65592, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65600, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65608, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65616, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65624, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65632, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65640, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65648, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65656, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65664, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57352, size = 4096 After: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 65536 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57368, size = 4096 Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-02-19 11:15:29 +03:00
int f2fs_merge_page_bio(struct f2fs_io_info *fio)
{
struct bio *bio = *fio->bio;
struct page *page = fio->encrypted_page ?
fio->encrypted_page : fio->page;
if (!f2fs_is_valid_blkaddr(fio->sbi, fio->new_blkaddr,
__is_meta_io(fio) ? META_GENERIC : DATA_GENERIC))
return -EFSCORRUPTED;
f2fs: add bio cache for IPU SQLite in Wal mode may trigger sequential IPU write in db-wal file, after commit d1b3e72d5490 ("f2fs: submit bio of in-place-update pages"), we lost the chance of merging page in inner managed bio cache, result in submitting more small-sized IO. So let's add temporary bio in writepages() to cache mergeable write IO as much as possible. Test case: 1. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" 2. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" Before: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65552, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65560, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65568, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65576, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65584, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65592, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65600, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65608, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65616, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65624, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65632, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65640, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65648, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65656, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65664, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57352, size = 4096 After: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 65536 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57368, size = 4096 Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-02-19 11:15:29 +03:00
trace_f2fs_submit_page_bio(page, fio);
f2fs_trace_ios(fio, 0);
if (bio && !page_is_mergeable(fio->sbi, bio, *fio->last_block,
fio->new_blkaddr))
f2fs_submit_merged_ipu_write(fio->sbi, &bio, NULL);
f2fs: add bio cache for IPU SQLite in Wal mode may trigger sequential IPU write in db-wal file, after commit d1b3e72d5490 ("f2fs: submit bio of in-place-update pages"), we lost the chance of merging page in inner managed bio cache, result in submitting more small-sized IO. So let's add temporary bio in writepages() to cache mergeable write IO as much as possible. Test case: 1. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" 2. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" Before: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65552, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65560, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65568, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65576, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65584, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65592, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65600, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65608, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65616, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65624, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65632, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65640, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65648, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65656, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65664, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57352, size = 4096 After: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 65536 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57368, size = 4096 Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-02-19 11:15:29 +03:00
alloc_new:
if (!bio) {
bio = __bio_alloc(fio, BIO_MAX_PAGES);
f2fs: add bio cache for IPU SQLite in Wal mode may trigger sequential IPU write in db-wal file, after commit d1b3e72d5490 ("f2fs: submit bio of in-place-update pages"), we lost the chance of merging page in inner managed bio cache, result in submitting more small-sized IO. So let's add temporary bio in writepages() to cache mergeable write IO as much as possible. Test case: 1. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" 2. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" Before: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65552, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65560, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65568, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65576, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65584, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65592, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65600, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65608, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65616, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65624, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65632, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65640, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65648, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65656, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65664, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57352, size = 4096 After: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 65536 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57368, size = 4096 Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-02-19 11:15:29 +03:00
bio_set_op_attrs(bio, fio->op, fio->op_flags);
add_bio_entry(fio->sbi, bio, page, fio->temp);
} else {
if (add_ipu_page(fio->sbi, &bio, page))
goto alloc_new;
f2fs: add bio cache for IPU SQLite in Wal mode may trigger sequential IPU write in db-wal file, after commit d1b3e72d5490 ("f2fs: submit bio of in-place-update pages"), we lost the chance of merging page in inner managed bio cache, result in submitting more small-sized IO. So let's add temporary bio in writepages() to cache mergeable write IO as much as possible. Test case: 1. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" 2. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" Before: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65552, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65560, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65568, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65576, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65584, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65592, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65600, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65608, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65616, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65624, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65632, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65640, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65648, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65656, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65664, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57352, size = 4096 After: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 65536 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57368, size = 4096 Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-02-19 11:15:29 +03:00
}
if (fio->io_wbc)
for-linus-20190715 -----BEGIN PGP SIGNATURE----- iQJEBAABCAAuFiEEwPw5LcreJtl1+l5K99NY+ylx4KYFAl0s1ZEQHGF4Ym9lQGtl cm5lbC5kawAKCRD301j7KXHgpiCEEACE9H/pXoegTTWIVPVajMlsa19UHIeilk4N GI7oKSiirQEMZnAOmrEzgB4/0zyYQsVypys0gZlYUD3GJVsXDT3zzjNXL5NpVg/O nqwSGWMHBSjWkLbaM40Pb2QLXsYgveptNL+9PtxrgtoYPoT5/+TyrJMFrRfi72EK WFeNDKOu6aJxpJ26JSsckJ0gluKeeEpRoEqsgHGIwaMIGHQf+b+ikk7tel5FAIgA uDwwD+Oxsdgh/ChsXL0d90GkcbcSp6GQ7GybxVmw/tPijx6mpeIY72xY3Zx+t8zF b71UNk6NmCKjOPO/6fiuYKKTYw+KhzlyEKO0j675HKfx2AhchEwKw0irp4yUlydA zxWYmz4U7iRgktJtymv3J4FEQQ3S6d1EnuQkQNX1LwiOsEsfzhkWi+7jy7KFhZoJ AqtYzqnOXvLx92q0vloj06HtK6zo+I/MINldy0+qn9lq0N0VF+dctyztAHLsF7P6 pUtS6i7l1JSFKAmMhC31sIj5TImaehM2e/TWMUPEDZaO96oKCmQwOF1oiloc6vlW h4xWsxP/9zOFcWNyPzy6Vo3JUXWRvFA7K+jV3Hsukw6rVHiNCGVYGSlTv8Roi5b7 I4ggu9R2JOGyku7UIlL50IRxEyjAp11LaO8yHhcCnRB65rmyBuNMQNcfOsfxpZ5Y 1mtSNhm5TQ== =g8xI -----END PGP SIGNATURE----- Merge tag 'for-linus-20190715' of git://git.kernel.dk/linux-block Pull more block updates from Jens Axboe: "A later pull request with some followup items. I had some vacation coming up to the merge window, so certain things items were delayed a bit. This pull request also contains fixes that came in within the last few days of the merge window, which I didn't want to push right before sending you a pull request. This contains: - NVMe pull request, mostly fixes, but also a few minor items on the feature side that were timing constrained (Christoph et al) - Report zones fixes (Damien) - Removal of dead code (Damien) - Turn on cgroup psi memstall (Josef) - block cgroup MAINTAINERS entry (Konstantin) - Flush init fix (Josef) - blk-throttle low iops timing fix (Konstantin) - nbd resize fixes (Mike) - nbd 0 blocksize crash fix (Xiubo) - block integrity error leak fix (Wenwen) - blk-cgroup writeback and priority inheritance fixes (Tejun)" * tag 'for-linus-20190715' of git://git.kernel.dk/linux-block: (42 commits) MAINTAINERS: add entry for block io cgroup null_blk: fixup ->report_zones() for !CONFIG_BLK_DEV_ZONED block: Limit zone array allocation size sd_zbc: Fix report zones buffer allocation block: Kill gfp_t argument of blkdev_report_zones() block: Allow mapping of vmalloc-ed buffers block/bio-integrity: fix a memory leak bug nvme: fix NULL deref for fabrics options nbd: add netlink reconfigure resize support nbd: fix crash when the blksize is zero block: Disable write plugging for zoned block devices block: Fix elevator name declaration block: Remove unused definitions nvme: fix regression upon hot device removal and insertion blk-throttle: fix zero wait time for iops throttled group block: Fix potential overflow in blk_report_zones() blkcg: implement REQ_CGROUP_PUNT blkcg, writeback: Implement wbc_blkcg_css() blkcg, writeback: Add wbc->no_cgroup_owner blkcg, writeback: Rename wbc_account_io() to wbc_account_cgroup_owner() ...
2019-07-16 07:20:52 +03:00
wbc_account_cgroup_owner(fio->io_wbc, page, PAGE_SIZE);
f2fs: add bio cache for IPU SQLite in Wal mode may trigger sequential IPU write in db-wal file, after commit d1b3e72d5490 ("f2fs: submit bio of in-place-update pages"), we lost the chance of merging page in inner managed bio cache, result in submitting more small-sized IO. So let's add temporary bio in writepages() to cache mergeable write IO as much as possible. Test case: 1. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" 2. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" Before: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65552, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65560, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65568, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65576, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65584, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65592, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65600, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65608, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65616, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65624, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65632, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65640, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65648, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65656, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65664, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57352, size = 4096 After: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 65536 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57368, size = 4096 Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-02-19 11:15:29 +03:00
inc_page_count(fio->sbi, WB_DATA_TYPE(page));
*fio->last_block = fio->new_blkaddr;
*fio->bio = bio;
return 0;
}
f2fs: fix to let caller retry allocating block address Configure io_bits with 2 and enable LFS mode, generic/013 reports below dmesg: BUG: unable to handle kernel NULL pointer dereference at 00000104 *pdpt = 0000000029b7b001 *pde = 0000000000000000 Oops: 0002 [#1] PREEMPT SMP Modules linked in: crc32_generic zram f2fs(O) rfcomm bnep bluetooth ecdh_generic snd_intel8x0 snd_ac97_codec ac97_bus snd_pcm snd_seq_midi snd_seq_midi_event snd_rawmidi snd_seq pcbc joydev snd_seq_device aesni_intel snd_timer aes_i586 snd crypto_simd cryptd soundcore i2c_piix4 serio_raw mac_hid video parport_pc ppdev lp parport hid_generic psmouse usbhid hid e1000 CPU: 0 PID: 11161 Comm: fsstress Tainted: G O 4.17.0-rc2 #38 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 EIP: f2fs_submit_page_write+0x28d/0x550 [f2fs] EFLAGS: 00010206 CPU: 0 EAX: e863dcd8 EBX: 00000000 ECX: 00000100 EDX: 00000200 ESI: e863dcf4 EDI: f6f82768 EBP: e863dbb0 ESP: e863db74 DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068 CR0: 80050033 CR2: 00000104 CR3: 29a62020 CR4: 000406f0 Call Trace: do_write_page+0x6f/0xc0 [f2fs] write_data_page+0x4a/0xd0 [f2fs] do_write_data_page+0x327/0x630 [f2fs] __write_data_page+0x34b/0x820 [f2fs] __f2fs_write_data_pages+0x42d/0x8c0 [f2fs] f2fs_write_data_pages+0x27/0x30 [f2fs] do_writepages+0x1a/0x70 __filemap_fdatawrite_range+0x94/0xd0 filemap_write_and_wait_range+0x3d/0xa0 __generic_file_write_iter+0x11a/0x1f0 f2fs_file_write_iter+0xdd/0x3b0 [f2fs] __vfs_write+0xd2/0x150 vfs_write+0x9b/0x190 ksys_write+0x45/0x90 sys_write+0x16/0x20 do_fast_syscall_32+0xaa/0x22c entry_SYSENTER_32+0x4c/0x7b EIP: 0xb7fc8c51 EFLAGS: 00000246 CPU: 0 EAX: ffffffda EBX: 00000003 ECX: 09cde000 EDX: 00001000 ESI: 00000003 EDI: 00001000 EBP: 00000000 ESP: bfbded38 DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 007b Code: e8 f9 77 34 c9 8b 45 e0 8b 80 b8 00 00 00 39 45 d8 0f 84 bb 02 00 00 8b 45 e0 8b 80 b8 00 00 00 8d 50 d8 8b 08 89 55 f0 8b 50 04 <89> 51 04 89 0a c7 00 00 01 00 00 c7 40 04 00 02 00 00 8b 45 dc EIP: f2fs_submit_page_write+0x28d/0x550 [f2fs] SS:ESP: 0068:e863db74 CR2: 0000000000000104 ---[ end trace 4cac79c0d1305ee6 ]--- allocate_data_block will submit all sequential pending IOs sorted by a FIFO list, If we failed to submit other user's IO due to unaligned write, we will retry to allocate new block address for current IO, then it will initialize fio.list again, if fio was in the list before, it can break FIFO list, result in above panic. Thread A Thread B - do_write_page - allocate_data_block - list_add_tail : fioA cached in FIFO list. - do_write_page - allocate_data_block - list_add_tail : fioB cached in FIFO list. - f2fs_submit_page_write : fail to submit IO - allocate_data_block - INIT_LIST_HEAD - f2fs_submit_page_write - list_del <-- NULL pointer dereference This patch adds fio.retry parameter to indicate failure status for each IO, and avoid bailing out if there is still pending IO in FIFO list for fixing. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-28 18:47:18 +03:00
void f2fs_submit_page_write(struct f2fs_io_info *fio)
{
struct f2fs_sb_info *sbi = fio->sbi;
enum page_type btype = PAGE_TYPE_OF_BIO(fio->type);
struct f2fs_bio_info *io = sbi->write_io[btype] + fio->temp;
struct page *bio_page;
f2fs_bug_on(sbi, is_read_io(fio->op));
down_write(&io->io_rwsem);
next:
if (fio->in_list) {
spin_lock(&io->io_lock);
if (list_empty(&io->io_list)) {
spin_unlock(&io->io_lock);
f2fs: fix to let caller retry allocating block address Configure io_bits with 2 and enable LFS mode, generic/013 reports below dmesg: BUG: unable to handle kernel NULL pointer dereference at 00000104 *pdpt = 0000000029b7b001 *pde = 0000000000000000 Oops: 0002 [#1] PREEMPT SMP Modules linked in: crc32_generic zram f2fs(O) rfcomm bnep bluetooth ecdh_generic snd_intel8x0 snd_ac97_codec ac97_bus snd_pcm snd_seq_midi snd_seq_midi_event snd_rawmidi snd_seq pcbc joydev snd_seq_device aesni_intel snd_timer aes_i586 snd crypto_simd cryptd soundcore i2c_piix4 serio_raw mac_hid video parport_pc ppdev lp parport hid_generic psmouse usbhid hid e1000 CPU: 0 PID: 11161 Comm: fsstress Tainted: G O 4.17.0-rc2 #38 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 EIP: f2fs_submit_page_write+0x28d/0x550 [f2fs] EFLAGS: 00010206 CPU: 0 EAX: e863dcd8 EBX: 00000000 ECX: 00000100 EDX: 00000200 ESI: e863dcf4 EDI: f6f82768 EBP: e863dbb0 ESP: e863db74 DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068 CR0: 80050033 CR2: 00000104 CR3: 29a62020 CR4: 000406f0 Call Trace: do_write_page+0x6f/0xc0 [f2fs] write_data_page+0x4a/0xd0 [f2fs] do_write_data_page+0x327/0x630 [f2fs] __write_data_page+0x34b/0x820 [f2fs] __f2fs_write_data_pages+0x42d/0x8c0 [f2fs] f2fs_write_data_pages+0x27/0x30 [f2fs] do_writepages+0x1a/0x70 __filemap_fdatawrite_range+0x94/0xd0 filemap_write_and_wait_range+0x3d/0xa0 __generic_file_write_iter+0x11a/0x1f0 f2fs_file_write_iter+0xdd/0x3b0 [f2fs] __vfs_write+0xd2/0x150 vfs_write+0x9b/0x190 ksys_write+0x45/0x90 sys_write+0x16/0x20 do_fast_syscall_32+0xaa/0x22c entry_SYSENTER_32+0x4c/0x7b EIP: 0xb7fc8c51 EFLAGS: 00000246 CPU: 0 EAX: ffffffda EBX: 00000003 ECX: 09cde000 EDX: 00001000 ESI: 00000003 EDI: 00001000 EBP: 00000000 ESP: bfbded38 DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 007b Code: e8 f9 77 34 c9 8b 45 e0 8b 80 b8 00 00 00 39 45 d8 0f 84 bb 02 00 00 8b 45 e0 8b 80 b8 00 00 00 8d 50 d8 8b 08 89 55 f0 8b 50 04 <89> 51 04 89 0a c7 00 00 01 00 00 c7 40 04 00 02 00 00 8b 45 dc EIP: f2fs_submit_page_write+0x28d/0x550 [f2fs] SS:ESP: 0068:e863db74 CR2: 0000000000000104 ---[ end trace 4cac79c0d1305ee6 ]--- allocate_data_block will submit all sequential pending IOs sorted by a FIFO list, If we failed to submit other user's IO due to unaligned write, we will retry to allocate new block address for current IO, then it will initialize fio.list again, if fio was in the list before, it can break FIFO list, result in above panic. Thread A Thread B - do_write_page - allocate_data_block - list_add_tail : fioA cached in FIFO list. - do_write_page - allocate_data_block - list_add_tail : fioB cached in FIFO list. - f2fs_submit_page_write : fail to submit IO - allocate_data_block - INIT_LIST_HEAD - f2fs_submit_page_write - list_del <-- NULL pointer dereference This patch adds fio.retry parameter to indicate failure status for each IO, and avoid bailing out if there is still pending IO in FIFO list for fixing. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-28 18:47:18 +03:00
goto out;
}
fio = list_first_entry(&io->io_list,
struct f2fs_io_info, list);
list_del(&fio->list);
spin_unlock(&io->io_lock);
}
f2fs: introduce DATA_GENERIC_ENHANCE Previously, f2fs_is_valid_blkaddr(, blkaddr, DATA_GENERIC) will check whether @blkaddr locates in main area or not. That check is weak, since the block address in range of main area can point to the address which is not valid in segment info table, and we can not detect such condition, we may suffer worse corruption as system continues running. So this patch introduce DATA_GENERIC_ENHANCE to enhance the sanity check which trigger SIT bitmap check rather than only range check. This patch did below changes as wel: - set SBI_NEED_FSCK in f2fs_is_valid_blkaddr(). - get rid of is_valid_data_blkaddr() to avoid panic if blkaddr is invalid. - introduce verify_fio_blkaddr() to wrap fio {new,old}_blkaddr validation check. - spread blkaddr check in: * f2fs_get_node_info() * __read_out_blkaddrs() * f2fs_submit_page_read() * ra_data_block() * do_recover_data() This patch can fix bug reported from bugzilla below: https://bugzilla.kernel.org/show_bug.cgi?id=203215 https://bugzilla.kernel.org/show_bug.cgi?id=203223 https://bugzilla.kernel.org/show_bug.cgi?id=203231 https://bugzilla.kernel.org/show_bug.cgi?id=203235 https://bugzilla.kernel.org/show_bug.cgi?id=203241 = Update by Jaegeuk Kim = DATA_GENERIC_ENHANCE enhanced to validate block addresses on read/write paths. But, xfstest/generic/446 compalins some generated kernel messages saying invalid bitmap was detected when reading a block. The reaons is, when we get the block addresses from extent_cache, there is no lock to synchronize it from truncating the blocks in parallel. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-15 10:26:32 +03:00
verify_fio_blkaddr(fio);
bio_page = fio->encrypted_page ? fio->encrypted_page : fio->page;
/* set submitted = true as a return value */
fio->submitted = true;
inc_page_count(sbi, WB_DATA_TYPE(bio_page));
if (io->bio && !io_is_mergeable(sbi, io->bio, io, fio,
io->last_block_in_bio, fio->new_blkaddr))
__submit_merged_bio(io);
alloc_new:
if (io->bio == NULL) {
if (F2FS_IO_ALIGNED(sbi) &&
(fio->type == DATA || fio->type == NODE) &&
fio->new_blkaddr & F2FS_IO_SIZE_MASK(sbi)) {
dec_page_count(sbi, WB_DATA_TYPE(bio_page));
f2fs: fix to let caller retry allocating block address Configure io_bits with 2 and enable LFS mode, generic/013 reports below dmesg: BUG: unable to handle kernel NULL pointer dereference at 00000104 *pdpt = 0000000029b7b001 *pde = 0000000000000000 Oops: 0002 [#1] PREEMPT SMP Modules linked in: crc32_generic zram f2fs(O) rfcomm bnep bluetooth ecdh_generic snd_intel8x0 snd_ac97_codec ac97_bus snd_pcm snd_seq_midi snd_seq_midi_event snd_rawmidi snd_seq pcbc joydev snd_seq_device aesni_intel snd_timer aes_i586 snd crypto_simd cryptd soundcore i2c_piix4 serio_raw mac_hid video parport_pc ppdev lp parport hid_generic psmouse usbhid hid e1000 CPU: 0 PID: 11161 Comm: fsstress Tainted: G O 4.17.0-rc2 #38 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 EIP: f2fs_submit_page_write+0x28d/0x550 [f2fs] EFLAGS: 00010206 CPU: 0 EAX: e863dcd8 EBX: 00000000 ECX: 00000100 EDX: 00000200 ESI: e863dcf4 EDI: f6f82768 EBP: e863dbb0 ESP: e863db74 DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068 CR0: 80050033 CR2: 00000104 CR3: 29a62020 CR4: 000406f0 Call Trace: do_write_page+0x6f/0xc0 [f2fs] write_data_page+0x4a/0xd0 [f2fs] do_write_data_page+0x327/0x630 [f2fs] __write_data_page+0x34b/0x820 [f2fs] __f2fs_write_data_pages+0x42d/0x8c0 [f2fs] f2fs_write_data_pages+0x27/0x30 [f2fs] do_writepages+0x1a/0x70 __filemap_fdatawrite_range+0x94/0xd0 filemap_write_and_wait_range+0x3d/0xa0 __generic_file_write_iter+0x11a/0x1f0 f2fs_file_write_iter+0xdd/0x3b0 [f2fs] __vfs_write+0xd2/0x150 vfs_write+0x9b/0x190 ksys_write+0x45/0x90 sys_write+0x16/0x20 do_fast_syscall_32+0xaa/0x22c entry_SYSENTER_32+0x4c/0x7b EIP: 0xb7fc8c51 EFLAGS: 00000246 CPU: 0 EAX: ffffffda EBX: 00000003 ECX: 09cde000 EDX: 00001000 ESI: 00000003 EDI: 00001000 EBP: 00000000 ESP: bfbded38 DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 007b Code: e8 f9 77 34 c9 8b 45 e0 8b 80 b8 00 00 00 39 45 d8 0f 84 bb 02 00 00 8b 45 e0 8b 80 b8 00 00 00 8d 50 d8 8b 08 89 55 f0 8b 50 04 <89> 51 04 89 0a c7 00 00 01 00 00 c7 40 04 00 02 00 00 8b 45 dc EIP: f2fs_submit_page_write+0x28d/0x550 [f2fs] SS:ESP: 0068:e863db74 CR2: 0000000000000104 ---[ end trace 4cac79c0d1305ee6 ]--- allocate_data_block will submit all sequential pending IOs sorted by a FIFO list, If we failed to submit other user's IO due to unaligned write, we will retry to allocate new block address for current IO, then it will initialize fio.list again, if fio was in the list before, it can break FIFO list, result in above panic. Thread A Thread B - do_write_page - allocate_data_block - list_add_tail : fioA cached in FIFO list. - do_write_page - allocate_data_block - list_add_tail : fioB cached in FIFO list. - f2fs_submit_page_write : fail to submit IO - allocate_data_block - INIT_LIST_HEAD - f2fs_submit_page_write - list_del <-- NULL pointer dereference This patch adds fio.retry parameter to indicate failure status for each IO, and avoid bailing out if there is still pending IO in FIFO list for fixing. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-28 18:47:18 +03:00
fio->retry = true;
goto skip;
}
io->bio = __bio_alloc(fio, BIO_MAX_PAGES);
io->fio = *fio;
}
if (bio_add_page(io->bio, bio_page, PAGE_SIZE, 0) < PAGE_SIZE) {
__submit_merged_bio(io);
goto alloc_new;
}
if (fio->io_wbc)
wbc_account_cgroup_owner(fio->io_wbc, bio_page, PAGE_SIZE);
io->last_block_in_bio = fio->new_blkaddr;
f2fs_trace_ios(fio, 0);
trace_f2fs_submit_page_write(fio->page, fio);
f2fs: fix to let caller retry allocating block address Configure io_bits with 2 and enable LFS mode, generic/013 reports below dmesg: BUG: unable to handle kernel NULL pointer dereference at 00000104 *pdpt = 0000000029b7b001 *pde = 0000000000000000 Oops: 0002 [#1] PREEMPT SMP Modules linked in: crc32_generic zram f2fs(O) rfcomm bnep bluetooth ecdh_generic snd_intel8x0 snd_ac97_codec ac97_bus snd_pcm snd_seq_midi snd_seq_midi_event snd_rawmidi snd_seq pcbc joydev snd_seq_device aesni_intel snd_timer aes_i586 snd crypto_simd cryptd soundcore i2c_piix4 serio_raw mac_hid video parport_pc ppdev lp parport hid_generic psmouse usbhid hid e1000 CPU: 0 PID: 11161 Comm: fsstress Tainted: G O 4.17.0-rc2 #38 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 EIP: f2fs_submit_page_write+0x28d/0x550 [f2fs] EFLAGS: 00010206 CPU: 0 EAX: e863dcd8 EBX: 00000000 ECX: 00000100 EDX: 00000200 ESI: e863dcf4 EDI: f6f82768 EBP: e863dbb0 ESP: e863db74 DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068 CR0: 80050033 CR2: 00000104 CR3: 29a62020 CR4: 000406f0 Call Trace: do_write_page+0x6f/0xc0 [f2fs] write_data_page+0x4a/0xd0 [f2fs] do_write_data_page+0x327/0x630 [f2fs] __write_data_page+0x34b/0x820 [f2fs] __f2fs_write_data_pages+0x42d/0x8c0 [f2fs] f2fs_write_data_pages+0x27/0x30 [f2fs] do_writepages+0x1a/0x70 __filemap_fdatawrite_range+0x94/0xd0 filemap_write_and_wait_range+0x3d/0xa0 __generic_file_write_iter+0x11a/0x1f0 f2fs_file_write_iter+0xdd/0x3b0 [f2fs] __vfs_write+0xd2/0x150 vfs_write+0x9b/0x190 ksys_write+0x45/0x90 sys_write+0x16/0x20 do_fast_syscall_32+0xaa/0x22c entry_SYSENTER_32+0x4c/0x7b EIP: 0xb7fc8c51 EFLAGS: 00000246 CPU: 0 EAX: ffffffda EBX: 00000003 ECX: 09cde000 EDX: 00001000 ESI: 00000003 EDI: 00001000 EBP: 00000000 ESP: bfbded38 DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 007b Code: e8 f9 77 34 c9 8b 45 e0 8b 80 b8 00 00 00 39 45 d8 0f 84 bb 02 00 00 8b 45 e0 8b 80 b8 00 00 00 8d 50 d8 8b 08 89 55 f0 8b 50 04 <89> 51 04 89 0a c7 00 00 01 00 00 c7 40 04 00 02 00 00 8b 45 dc EIP: f2fs_submit_page_write+0x28d/0x550 [f2fs] SS:ESP: 0068:e863db74 CR2: 0000000000000104 ---[ end trace 4cac79c0d1305ee6 ]--- allocate_data_block will submit all sequential pending IOs sorted by a FIFO list, If we failed to submit other user's IO due to unaligned write, we will retry to allocate new block address for current IO, then it will initialize fio.list again, if fio was in the list before, it can break FIFO list, result in above panic. Thread A Thread B - do_write_page - allocate_data_block - list_add_tail : fioA cached in FIFO list. - do_write_page - allocate_data_block - list_add_tail : fioB cached in FIFO list. - f2fs_submit_page_write : fail to submit IO - allocate_data_block - INIT_LIST_HEAD - f2fs_submit_page_write - list_del <-- NULL pointer dereference This patch adds fio.retry parameter to indicate failure status for each IO, and avoid bailing out if there is still pending IO in FIFO list for fixing. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-28 18:47:18 +03:00
skip:
if (fio->in_list)
goto next;
f2fs: fix to let caller retry allocating block address Configure io_bits with 2 and enable LFS mode, generic/013 reports below dmesg: BUG: unable to handle kernel NULL pointer dereference at 00000104 *pdpt = 0000000029b7b001 *pde = 0000000000000000 Oops: 0002 [#1] PREEMPT SMP Modules linked in: crc32_generic zram f2fs(O) rfcomm bnep bluetooth ecdh_generic snd_intel8x0 snd_ac97_codec ac97_bus snd_pcm snd_seq_midi snd_seq_midi_event snd_rawmidi snd_seq pcbc joydev snd_seq_device aesni_intel snd_timer aes_i586 snd crypto_simd cryptd soundcore i2c_piix4 serio_raw mac_hid video parport_pc ppdev lp parport hid_generic psmouse usbhid hid e1000 CPU: 0 PID: 11161 Comm: fsstress Tainted: G O 4.17.0-rc2 #38 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 EIP: f2fs_submit_page_write+0x28d/0x550 [f2fs] EFLAGS: 00010206 CPU: 0 EAX: e863dcd8 EBX: 00000000 ECX: 00000100 EDX: 00000200 ESI: e863dcf4 EDI: f6f82768 EBP: e863dbb0 ESP: e863db74 DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068 CR0: 80050033 CR2: 00000104 CR3: 29a62020 CR4: 000406f0 Call Trace: do_write_page+0x6f/0xc0 [f2fs] write_data_page+0x4a/0xd0 [f2fs] do_write_data_page+0x327/0x630 [f2fs] __write_data_page+0x34b/0x820 [f2fs] __f2fs_write_data_pages+0x42d/0x8c0 [f2fs] f2fs_write_data_pages+0x27/0x30 [f2fs] do_writepages+0x1a/0x70 __filemap_fdatawrite_range+0x94/0xd0 filemap_write_and_wait_range+0x3d/0xa0 __generic_file_write_iter+0x11a/0x1f0 f2fs_file_write_iter+0xdd/0x3b0 [f2fs] __vfs_write+0xd2/0x150 vfs_write+0x9b/0x190 ksys_write+0x45/0x90 sys_write+0x16/0x20 do_fast_syscall_32+0xaa/0x22c entry_SYSENTER_32+0x4c/0x7b EIP: 0xb7fc8c51 EFLAGS: 00000246 CPU: 0 EAX: ffffffda EBX: 00000003 ECX: 09cde000 EDX: 00001000 ESI: 00000003 EDI: 00001000 EBP: 00000000 ESP: bfbded38 DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 007b Code: e8 f9 77 34 c9 8b 45 e0 8b 80 b8 00 00 00 39 45 d8 0f 84 bb 02 00 00 8b 45 e0 8b 80 b8 00 00 00 8d 50 d8 8b 08 89 55 f0 8b 50 04 <89> 51 04 89 0a c7 00 00 01 00 00 c7 40 04 00 02 00 00 8b 45 dc EIP: f2fs_submit_page_write+0x28d/0x550 [f2fs] SS:ESP: 0068:e863db74 CR2: 0000000000000104 ---[ end trace 4cac79c0d1305ee6 ]--- allocate_data_block will submit all sequential pending IOs sorted by a FIFO list, If we failed to submit other user's IO due to unaligned write, we will retry to allocate new block address for current IO, then it will initialize fio.list again, if fio was in the list before, it can break FIFO list, result in above panic. Thread A Thread B - do_write_page - allocate_data_block - list_add_tail : fioA cached in FIFO list. - do_write_page - allocate_data_block - list_add_tail : fioB cached in FIFO list. - f2fs_submit_page_write : fail to submit IO - allocate_data_block - INIT_LIST_HEAD - f2fs_submit_page_write - list_del <-- NULL pointer dereference This patch adds fio.retry parameter to indicate failure status for each IO, and avoid bailing out if there is still pending IO in FIFO list for fixing. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-28 18:47:18 +03:00
out:
if (is_sbi_flag_set(sbi, SBI_IS_SHUTDOWN) ||
!f2fs_is_checkpoint_ready(sbi))
__submit_merged_bio(io);
up_write(&io->io_rwsem);
}
f2fs: add fs-verity support Add fs-verity support to f2fs. fs-verity is a filesystem feature that enables transparent integrity protection and authentication of read-only files. It uses a dm-verity like mechanism at the file level: a Merkle tree is used to verify any block in the file in log(filesize) time. It is implemented mainly by helper functions in fs/verity/. See Documentation/filesystems/fsverity.rst for the full documentation. The f2fs support for fs-verity consists of: - Adding a filesystem feature flag and an inode flag for fs-verity. - Implementing the fsverity_operations to support enabling verity on an inode and reading/writing the verity metadata. - Updating ->readpages() to verify data as it's read from verity files and to support reading verity metadata pages. - Updating ->write_begin(), ->write_end(), and ->writepages() to support writing verity metadata pages. - Calling the fs-verity hooks for ->open(), ->setattr(), and ->ioctl(). Like ext4, f2fs stores the verity metadata (Merkle tree and fsverity_descriptor) past the end of the file, starting at the first 64K boundary beyond i_size. This approach works because (a) verity files are readonly, and (b) pages fully beyond i_size aren't visible to userspace but can be read/written internally by f2fs with only some relatively small changes to f2fs. Extended attributes cannot be used because (a) f2fs limits the total size of an inode's xattr entries to 4096 bytes, which wouldn't be enough for even a single Merkle tree block, and (b) f2fs encryption doesn't encrypt xattrs, yet the verity metadata *must* be encrypted when the file is because it contains hashes of the plaintext data. Acked-by: Jaegeuk Kim <jaegeuk@kernel.org> Acked-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Eric Biggers <ebiggers@google.com>
2019-07-22 19:26:24 +03:00
static inline bool f2fs_need_verity(const struct inode *inode, pgoff_t idx)
{
return fsverity_active(inode) &&
idx < DIV_ROUND_UP(inode->i_size, PAGE_SIZE);
}
static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr,
f2fs: add fs-verity support Add fs-verity support to f2fs. fs-verity is a filesystem feature that enables transparent integrity protection and authentication of read-only files. It uses a dm-verity like mechanism at the file level: a Merkle tree is used to verify any block in the file in log(filesize) time. It is implemented mainly by helper functions in fs/verity/. See Documentation/filesystems/fsverity.rst for the full documentation. The f2fs support for fs-verity consists of: - Adding a filesystem feature flag and an inode flag for fs-verity. - Implementing the fsverity_operations to support enabling verity on an inode and reading/writing the verity metadata. - Updating ->readpages() to verify data as it's read from verity files and to support reading verity metadata pages. - Updating ->write_begin(), ->write_end(), and ->writepages() to support writing verity metadata pages. - Calling the fs-verity hooks for ->open(), ->setattr(), and ->ioctl(). Like ext4, f2fs stores the verity metadata (Merkle tree and fsverity_descriptor) past the end of the file, starting at the first 64K boundary beyond i_size. This approach works because (a) verity files are readonly, and (b) pages fully beyond i_size aren't visible to userspace but can be read/written internally by f2fs with only some relatively small changes to f2fs. Extended attributes cannot be used because (a) f2fs limits the total size of an inode's xattr entries to 4096 bytes, which wouldn't be enough for even a single Merkle tree block, and (b) f2fs encryption doesn't encrypt xattrs, yet the verity metadata *must* be encrypted when the file is because it contains hashes of the plaintext data. Acked-by: Jaegeuk Kim <jaegeuk@kernel.org> Acked-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Eric Biggers <ebiggers@google.com>
2019-07-22 19:26:24 +03:00
unsigned nr_pages, unsigned op_flag,
pgoff_t first_idx)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct bio *bio;
struct bio_post_read_ctx *ctx;
unsigned int post_read_steps = 0;
bio = f2fs_bio_alloc(sbi, min_t(int, nr_pages, BIO_MAX_PAGES), false);
if (!bio)
return ERR_PTR(-ENOMEM);
f2fs_target_device(sbi, blkaddr, bio);
bio->bi_end_io = f2fs_read_end_io;
bio_set_op_attrs(bio, REQ_OP_READ, op_flag);
if (f2fs_encrypted_file(inode))
post_read_steps |= 1 << STEP_DECRYPT;
f2fs: add fs-verity support Add fs-verity support to f2fs. fs-verity is a filesystem feature that enables transparent integrity protection and authentication of read-only files. It uses a dm-verity like mechanism at the file level: a Merkle tree is used to verify any block in the file in log(filesize) time. It is implemented mainly by helper functions in fs/verity/. See Documentation/filesystems/fsverity.rst for the full documentation. The f2fs support for fs-verity consists of: - Adding a filesystem feature flag and an inode flag for fs-verity. - Implementing the fsverity_operations to support enabling verity on an inode and reading/writing the verity metadata. - Updating ->readpages() to verify data as it's read from verity files and to support reading verity metadata pages. - Updating ->write_begin(), ->write_end(), and ->writepages() to support writing verity metadata pages. - Calling the fs-verity hooks for ->open(), ->setattr(), and ->ioctl(). Like ext4, f2fs stores the verity metadata (Merkle tree and fsverity_descriptor) past the end of the file, starting at the first 64K boundary beyond i_size. This approach works because (a) verity files are readonly, and (b) pages fully beyond i_size aren't visible to userspace but can be read/written internally by f2fs with only some relatively small changes to f2fs. Extended attributes cannot be used because (a) f2fs limits the total size of an inode's xattr entries to 4096 bytes, which wouldn't be enough for even a single Merkle tree block, and (b) f2fs encryption doesn't encrypt xattrs, yet the verity metadata *must* be encrypted when the file is because it contains hashes of the plaintext data. Acked-by: Jaegeuk Kim <jaegeuk@kernel.org> Acked-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Eric Biggers <ebiggers@google.com>
2019-07-22 19:26:24 +03:00
if (f2fs_need_verity(inode, first_idx))
post_read_steps |= 1 << STEP_VERITY;
if (post_read_steps) {
ctx = mempool_alloc(bio_post_read_ctx_pool, GFP_NOFS);
if (!ctx) {
bio_put(bio);
return ERR_PTR(-ENOMEM);
}
ctx->bio = bio;
ctx->enabled_steps = post_read_steps;
bio->bi_private = ctx;
}
return bio;
}
/* This can handle encryption stuffs */
static int f2fs_submit_page_read(struct inode *inode, struct page *page,
block_t blkaddr)
{
f2fs: introduce DATA_GENERIC_ENHANCE Previously, f2fs_is_valid_blkaddr(, blkaddr, DATA_GENERIC) will check whether @blkaddr locates in main area or not. That check is weak, since the block address in range of main area can point to the address which is not valid in segment info table, and we can not detect such condition, we may suffer worse corruption as system continues running. So this patch introduce DATA_GENERIC_ENHANCE to enhance the sanity check which trigger SIT bitmap check rather than only range check. This patch did below changes as wel: - set SBI_NEED_FSCK in f2fs_is_valid_blkaddr(). - get rid of is_valid_data_blkaddr() to avoid panic if blkaddr is invalid. - introduce verify_fio_blkaddr() to wrap fio {new,old}_blkaddr validation check. - spread blkaddr check in: * f2fs_get_node_info() * __read_out_blkaddrs() * f2fs_submit_page_read() * ra_data_block() * do_recover_data() This patch can fix bug reported from bugzilla below: https://bugzilla.kernel.org/show_bug.cgi?id=203215 https://bugzilla.kernel.org/show_bug.cgi?id=203223 https://bugzilla.kernel.org/show_bug.cgi?id=203231 https://bugzilla.kernel.org/show_bug.cgi?id=203235 https://bugzilla.kernel.org/show_bug.cgi?id=203241 = Update by Jaegeuk Kim = DATA_GENERIC_ENHANCE enhanced to validate block addresses on read/write paths. But, xfstest/generic/446 compalins some generated kernel messages saying invalid bitmap was detected when reading a block. The reaons is, when we get the block addresses from extent_cache, there is no lock to synchronize it from truncating the blocks in parallel. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-15 10:26:32 +03:00
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct bio *bio;
f2fs: add fs-verity support Add fs-verity support to f2fs. fs-verity is a filesystem feature that enables transparent integrity protection and authentication of read-only files. It uses a dm-verity like mechanism at the file level: a Merkle tree is used to verify any block in the file in log(filesize) time. It is implemented mainly by helper functions in fs/verity/. See Documentation/filesystems/fsverity.rst for the full documentation. The f2fs support for fs-verity consists of: - Adding a filesystem feature flag and an inode flag for fs-verity. - Implementing the fsverity_operations to support enabling verity on an inode and reading/writing the verity metadata. - Updating ->readpages() to verify data as it's read from verity files and to support reading verity metadata pages. - Updating ->write_begin(), ->write_end(), and ->writepages() to support writing verity metadata pages. - Calling the fs-verity hooks for ->open(), ->setattr(), and ->ioctl(). Like ext4, f2fs stores the verity metadata (Merkle tree and fsverity_descriptor) past the end of the file, starting at the first 64K boundary beyond i_size. This approach works because (a) verity files are readonly, and (b) pages fully beyond i_size aren't visible to userspace but can be read/written internally by f2fs with only some relatively small changes to f2fs. Extended attributes cannot be used because (a) f2fs limits the total size of an inode's xattr entries to 4096 bytes, which wouldn't be enough for even a single Merkle tree block, and (b) f2fs encryption doesn't encrypt xattrs, yet the verity metadata *must* be encrypted when the file is because it contains hashes of the plaintext data. Acked-by: Jaegeuk Kim <jaegeuk@kernel.org> Acked-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Eric Biggers <ebiggers@google.com>
2019-07-22 19:26:24 +03:00
bio = f2fs_grab_read_bio(inode, blkaddr, 1, 0, page->index);
if (IS_ERR(bio))
return PTR_ERR(bio);
/* wait for GCed page writeback via META_MAPPING */
f2fs_wait_on_block_writeback(inode, blkaddr);
if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
bio_put(bio);
return -EFAULT;
}
ClearPageError(page);
f2fs: introduce DATA_GENERIC_ENHANCE Previously, f2fs_is_valid_blkaddr(, blkaddr, DATA_GENERIC) will check whether @blkaddr locates in main area or not. That check is weak, since the block address in range of main area can point to the address which is not valid in segment info table, and we can not detect such condition, we may suffer worse corruption as system continues running. So this patch introduce DATA_GENERIC_ENHANCE to enhance the sanity check which trigger SIT bitmap check rather than only range check. This patch did below changes as wel: - set SBI_NEED_FSCK in f2fs_is_valid_blkaddr(). - get rid of is_valid_data_blkaddr() to avoid panic if blkaddr is invalid. - introduce verify_fio_blkaddr() to wrap fio {new,old}_blkaddr validation check. - spread blkaddr check in: * f2fs_get_node_info() * __read_out_blkaddrs() * f2fs_submit_page_read() * ra_data_block() * do_recover_data() This patch can fix bug reported from bugzilla below: https://bugzilla.kernel.org/show_bug.cgi?id=203215 https://bugzilla.kernel.org/show_bug.cgi?id=203223 https://bugzilla.kernel.org/show_bug.cgi?id=203231 https://bugzilla.kernel.org/show_bug.cgi?id=203235 https://bugzilla.kernel.org/show_bug.cgi?id=203241 = Update by Jaegeuk Kim = DATA_GENERIC_ENHANCE enhanced to validate block addresses on read/write paths. But, xfstest/generic/446 compalins some generated kernel messages saying invalid bitmap was detected when reading a block. The reaons is, when we get the block addresses from extent_cache, there is no lock to synchronize it from truncating the blocks in parallel. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-15 10:26:32 +03:00
inc_page_count(sbi, F2FS_RD_DATA);
__submit_bio(sbi, bio, DATA);
return 0;
}
static void __set_data_blkaddr(struct dnode_of_data *dn)
{
struct f2fs_node *rn = F2FS_NODE(dn->node_page);
__le32 *addr_array;
f2fs: enhance on-disk inode structure scalability This patch add new flag F2FS_EXTRA_ATTR storing in inode.i_inline to indicate that on-disk structure of current inode is extended. In order to extend, we changed the inode structure a bit: Original one: struct f2fs_inode { ... struct f2fs_extent i_ext; __le32 i_addr[DEF_ADDRS_PER_INODE]; __le32 i_nid[DEF_NIDS_PER_INODE]; } Extended one: struct f2fs_inode { ... struct f2fs_extent i_ext; union { struct { __le16 i_extra_isize; __le16 i_padding; __le32 i_extra_end[0]; }; __le32 i_addr[DEF_ADDRS_PER_INODE]; }; __le32 i_nid[DEF_NIDS_PER_INODE]; } Once F2FS_EXTRA_ATTR is set, we will steal four bytes in the head of i_addr field for storing i_extra_isize and i_padding. with i_extra_isize, we can calculate actual size of reserved space in i_addr, available attribute fields included in total extra attribute fields for current inode can be described as below: +--------------------+ | .i_mode | | ... | | .i_ext | +--------------------+ | .i_extra_isize |-----+ | .i_padding | | | .i_prjid | | | .i_atime_extra | | | .i_ctime_extra | | | .i_mtime_extra |<----+ | .i_inode_cs |<----- store blkaddr/inline from here | .i_xattr_cs | | ... | +--------------------+ | | | block address | | | +--------------------+ | .i_nid | +--------------------+ | node_footer | | (nid, ino, offset) | +--------------------+ Hence, with this patch, we would enhance scalability of f2fs inode for storing more newly added attribute. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2017-07-18 19:19:06 +03:00
int base = 0;
if (IS_INODE(dn->node_page) && f2fs_has_extra_attr(dn->inode))
base = get_extra_isize(dn->inode);
/* Get physical address of data block */
addr_array = blkaddr_in_node(rn);
f2fs: enhance on-disk inode structure scalability This patch add new flag F2FS_EXTRA_ATTR storing in inode.i_inline to indicate that on-disk structure of current inode is extended. In order to extend, we changed the inode structure a bit: Original one: struct f2fs_inode { ... struct f2fs_extent i_ext; __le32 i_addr[DEF_ADDRS_PER_INODE]; __le32 i_nid[DEF_NIDS_PER_INODE]; } Extended one: struct f2fs_inode { ... struct f2fs_extent i_ext; union { struct { __le16 i_extra_isize; __le16 i_padding; __le32 i_extra_end[0]; }; __le32 i_addr[DEF_ADDRS_PER_INODE]; }; __le32 i_nid[DEF_NIDS_PER_INODE]; } Once F2FS_EXTRA_ATTR is set, we will steal four bytes in the head of i_addr field for storing i_extra_isize and i_padding. with i_extra_isize, we can calculate actual size of reserved space in i_addr, available attribute fields included in total extra attribute fields for current inode can be described as below: +--------------------+ | .i_mode | | ... | | .i_ext | +--------------------+ | .i_extra_isize |-----+ | .i_padding | | | .i_prjid | | | .i_atime_extra | | | .i_ctime_extra | | | .i_mtime_extra |<----+ | .i_inode_cs |<----- store blkaddr/inline from here | .i_xattr_cs | | ... | +--------------------+ | | | block address | | | +--------------------+ | .i_nid | +--------------------+ | node_footer | | (nid, ino, offset) | +--------------------+ Hence, with this patch, we would enhance scalability of f2fs inode for storing more newly added attribute. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2017-07-18 19:19:06 +03:00
addr_array[base + dn->ofs_in_node] = cpu_to_le32(dn->data_blkaddr);
}
/*
* Lock ordering for the change of data block address:
* ->data_page
* ->node_page
* update block addresses in the node page
*/
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 19:20:41 +03:00
void f2fs_set_data_blkaddr(struct dnode_of_data *dn)
{
f2fs_wait_on_page_writeback(dn->node_page, NODE, true, true);
__set_data_blkaddr(dn);
if (set_page_dirty(dn->node_page))
dn->node_changed = true;
}
void f2fs_update_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr)
{
dn->data_blkaddr = blkaddr;
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 19:20:41 +03:00
f2fs_set_data_blkaddr(dn);
f2fs_update_extent_cache(dn);
}
/* dn->ofs_in_node will be returned with up-to-date last block pointer */
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 19:20:41 +03:00
int f2fs_reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
int err;
if (!count)
return 0;
if (unlikely(is_inode_flag_set(dn->inode, FI_NO_ALLOC)))
return -EPERM;
if (unlikely((err = inc_valid_block_count(sbi, dn->inode, &count))))
return err;
trace_f2fs_reserve_new_blocks(dn->inode, dn->nid,
dn->ofs_in_node, count);
f2fs_wait_on_page_writeback(dn->node_page, NODE, true, true);
for (; count > 0; dn->ofs_in_node++) {
f2fs: enhance on-disk inode structure scalability This patch add new flag F2FS_EXTRA_ATTR storing in inode.i_inline to indicate that on-disk structure of current inode is extended. In order to extend, we changed the inode structure a bit: Original one: struct f2fs_inode { ... struct f2fs_extent i_ext; __le32 i_addr[DEF_ADDRS_PER_INODE]; __le32 i_nid[DEF_NIDS_PER_INODE]; } Extended one: struct f2fs_inode { ... struct f2fs_extent i_ext; union { struct { __le16 i_extra_isize; __le16 i_padding; __le32 i_extra_end[0]; }; __le32 i_addr[DEF_ADDRS_PER_INODE]; }; __le32 i_nid[DEF_NIDS_PER_INODE]; } Once F2FS_EXTRA_ATTR is set, we will steal four bytes in the head of i_addr field for storing i_extra_isize and i_padding. with i_extra_isize, we can calculate actual size of reserved space in i_addr, available attribute fields included in total extra attribute fields for current inode can be described as below: +--------------------+ | .i_mode | | ... | | .i_ext | +--------------------+ | .i_extra_isize |-----+ | .i_padding | | | .i_prjid | | | .i_atime_extra | | | .i_ctime_extra | | | .i_mtime_extra |<----+ | .i_inode_cs |<----- store blkaddr/inline from here | .i_xattr_cs | | ... | +--------------------+ | | | block address | | | +--------------------+ | .i_nid | +--------------------+ | node_footer | | (nid, ino, offset) | +--------------------+ Hence, with this patch, we would enhance scalability of f2fs inode for storing more newly added attribute. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2017-07-18 19:19:06 +03:00
block_t blkaddr = datablock_addr(dn->inode,
dn->node_page, dn->ofs_in_node);
if (blkaddr == NULL_ADDR) {
dn->data_blkaddr = NEW_ADDR;
__set_data_blkaddr(dn);
count--;
}
}
if (set_page_dirty(dn->node_page))
dn->node_changed = true;
return 0;
}
/* Should keep dn->ofs_in_node unchanged */
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 19:20:41 +03:00
int f2fs_reserve_new_block(struct dnode_of_data *dn)
{
unsigned int ofs_in_node = dn->ofs_in_node;
int ret;
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 19:20:41 +03:00
ret = f2fs_reserve_new_blocks(dn, 1);
dn->ofs_in_node = ofs_in_node;
return ret;
}
int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index)
{
bool need_put = dn->inode_page ? false : true;
int err;
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 19:20:41 +03:00
err = f2fs_get_dnode_of_data(dn, index, ALLOC_NODE);
if (err)
return err;
if (dn->data_blkaddr == NULL_ADDR)
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 19:20:41 +03:00
err = f2fs_reserve_new_block(dn);
if (err || need_put)
f2fs_put_dnode(dn);
return err;
}
int f2fs_get_block(struct dnode_of_data *dn, pgoff_t index)
{
struct extent_info ei = {0,0,0};
struct inode *inode = dn->inode;
if (f2fs_lookup_extent_cache(inode, index, &ei)) {
dn->data_blkaddr = ei.blk + index - ei.fofs;
return 0;
}
return f2fs_reserve_block(dn, index);
}
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 19:20:41 +03:00
struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index,
int op_flags, bool for_write)
{
struct address_space *mapping = inode->i_mapping;
struct dnode_of_data dn;
struct page *page;
struct extent_info ei = {0,0,0};
int err;
page = f2fs_grab_cache_page(mapping, index, for_write);
if (!page)
return ERR_PTR(-ENOMEM);
if (f2fs_lookup_extent_cache(inode, index, &ei)) {
dn.data_blkaddr = ei.blk + index - ei.fofs;
f2fs: introduce DATA_GENERIC_ENHANCE Previously, f2fs_is_valid_blkaddr(, blkaddr, DATA_GENERIC) will check whether @blkaddr locates in main area or not. That check is weak, since the block address in range of main area can point to the address which is not valid in segment info table, and we can not detect such condition, we may suffer worse corruption as system continues running. So this patch introduce DATA_GENERIC_ENHANCE to enhance the sanity check which trigger SIT bitmap check rather than only range check. This patch did below changes as wel: - set SBI_NEED_FSCK in f2fs_is_valid_blkaddr(). - get rid of is_valid_data_blkaddr() to avoid panic if blkaddr is invalid. - introduce verify_fio_blkaddr() to wrap fio {new,old}_blkaddr validation check. - spread blkaddr check in: * f2fs_get_node_info() * __read_out_blkaddrs() * f2fs_submit_page_read() * ra_data_block() * do_recover_data() This patch can fix bug reported from bugzilla below: https://bugzilla.kernel.org/show_bug.cgi?id=203215 https://bugzilla.kernel.org/show_bug.cgi?id=203223 https://bugzilla.kernel.org/show_bug.cgi?id=203231 https://bugzilla.kernel.org/show_bug.cgi?id=203235 https://bugzilla.kernel.org/show_bug.cgi?id=203241 = Update by Jaegeuk Kim = DATA_GENERIC_ENHANCE enhanced to validate block addresses on read/write paths. But, xfstest/generic/446 compalins some generated kernel messages saying invalid bitmap was detected when reading a block. The reaons is, when we get the block addresses from extent_cache, there is no lock to synchronize it from truncating the blocks in parallel. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-15 10:26:32 +03:00
if (!f2fs_is_valid_blkaddr(F2FS_I_SB(inode), dn.data_blkaddr,
DATA_GENERIC_ENHANCE_READ)) {
err = -EFSCORRUPTED;
f2fs: introduce DATA_GENERIC_ENHANCE Previously, f2fs_is_valid_blkaddr(, blkaddr, DATA_GENERIC) will check whether @blkaddr locates in main area or not. That check is weak, since the block address in range of main area can point to the address which is not valid in segment info table, and we can not detect such condition, we may suffer worse corruption as system continues running. So this patch introduce DATA_GENERIC_ENHANCE to enhance the sanity check which trigger SIT bitmap check rather than only range check. This patch did below changes as wel: - set SBI_NEED_FSCK in f2fs_is_valid_blkaddr(). - get rid of is_valid_data_blkaddr() to avoid panic if blkaddr is invalid. - introduce verify_fio_blkaddr() to wrap fio {new,old}_blkaddr validation check. - spread blkaddr check in: * f2fs_get_node_info() * __read_out_blkaddrs() * f2fs_submit_page_read() * ra_data_block() * do_recover_data() This patch can fix bug reported from bugzilla below: https://bugzilla.kernel.org/show_bug.cgi?id=203215 https://bugzilla.kernel.org/show_bug.cgi?id=203223 https://bugzilla.kernel.org/show_bug.cgi?id=203231 https://bugzilla.kernel.org/show_bug.cgi?id=203235 https://bugzilla.kernel.org/show_bug.cgi?id=203241 = Update by Jaegeuk Kim = DATA_GENERIC_ENHANCE enhanced to validate block addresses on read/write paths. But, xfstest/generic/446 compalins some generated kernel messages saying invalid bitmap was detected when reading a block. The reaons is, when we get the block addresses from extent_cache, there is no lock to synchronize it from truncating the blocks in parallel. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-15 10:26:32 +03:00
goto put_err;
}
goto got_it;
}
set_new_dnode(&dn, inode, NULL, NULL, 0);
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 19:20:41 +03:00
err = f2fs_get_dnode_of_data(&dn, index, LOOKUP_NODE);
if (err)
goto put_err;
f2fs_put_dnode(&dn);
if (unlikely(dn.data_blkaddr == NULL_ADDR)) {
err = -ENOENT;
goto put_err;
}
f2fs: introduce DATA_GENERIC_ENHANCE Previously, f2fs_is_valid_blkaddr(, blkaddr, DATA_GENERIC) will check whether @blkaddr locates in main area or not. That check is weak, since the block address in range of main area can point to the address which is not valid in segment info table, and we can not detect such condition, we may suffer worse corruption as system continues running. So this patch introduce DATA_GENERIC_ENHANCE to enhance the sanity check which trigger SIT bitmap check rather than only range check. This patch did below changes as wel: - set SBI_NEED_FSCK in f2fs_is_valid_blkaddr(). - get rid of is_valid_data_blkaddr() to avoid panic if blkaddr is invalid. - introduce verify_fio_blkaddr() to wrap fio {new,old}_blkaddr validation check. - spread blkaddr check in: * f2fs_get_node_info() * __read_out_blkaddrs() * f2fs_submit_page_read() * ra_data_block() * do_recover_data() This patch can fix bug reported from bugzilla below: https://bugzilla.kernel.org/show_bug.cgi?id=203215 https://bugzilla.kernel.org/show_bug.cgi?id=203223 https://bugzilla.kernel.org/show_bug.cgi?id=203231 https://bugzilla.kernel.org/show_bug.cgi?id=203235 https://bugzilla.kernel.org/show_bug.cgi?id=203241 = Update by Jaegeuk Kim = DATA_GENERIC_ENHANCE enhanced to validate block addresses on read/write paths. But, xfstest/generic/446 compalins some generated kernel messages saying invalid bitmap was detected when reading a block. The reaons is, when we get the block addresses from extent_cache, there is no lock to synchronize it from truncating the blocks in parallel. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-15 10:26:32 +03:00
if (dn.data_blkaddr != NEW_ADDR &&
!f2fs_is_valid_blkaddr(F2FS_I_SB(inode),
dn.data_blkaddr,
DATA_GENERIC_ENHANCE)) {
err = -EFSCORRUPTED;
f2fs: introduce DATA_GENERIC_ENHANCE Previously, f2fs_is_valid_blkaddr(, blkaddr, DATA_GENERIC) will check whether @blkaddr locates in main area or not. That check is weak, since the block address in range of main area can point to the address which is not valid in segment info table, and we can not detect such condition, we may suffer worse corruption as system continues running. So this patch introduce DATA_GENERIC_ENHANCE to enhance the sanity check which trigger SIT bitmap check rather than only range check. This patch did below changes as wel: - set SBI_NEED_FSCK in f2fs_is_valid_blkaddr(). - get rid of is_valid_data_blkaddr() to avoid panic if blkaddr is invalid. - introduce verify_fio_blkaddr() to wrap fio {new,old}_blkaddr validation check. - spread blkaddr check in: * f2fs_get_node_info() * __read_out_blkaddrs() * f2fs_submit_page_read() * ra_data_block() * do_recover_data() This patch can fix bug reported from bugzilla below: https://bugzilla.kernel.org/show_bug.cgi?id=203215 https://bugzilla.kernel.org/show_bug.cgi?id=203223 https://bugzilla.kernel.org/show_bug.cgi?id=203231 https://bugzilla.kernel.org/show_bug.cgi?id=203235 https://bugzilla.kernel.org/show_bug.cgi?id=203241 = Update by Jaegeuk Kim = DATA_GENERIC_ENHANCE enhanced to validate block addresses on read/write paths. But, xfstest/generic/446 compalins some generated kernel messages saying invalid bitmap was detected when reading a block. The reaons is, when we get the block addresses from extent_cache, there is no lock to synchronize it from truncating the blocks in parallel. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-15 10:26:32 +03:00
goto put_err;
}
got_it:
if (PageUptodate(page)) {
unlock_page(page);
return page;
}
/*
* A new dentry page is allocated but not able to be written, since its
* new inode page couldn't be allocated due to -ENOSPC.
* In such the case, its blkaddr can be remained as NEW_ADDR.
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 19:20:41 +03:00
* see, f2fs_add_link -> f2fs_get_new_data_page ->
* f2fs_init_inode_metadata.
*/
if (dn.data_blkaddr == NEW_ADDR) {
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 15:29:47 +03:00
zero_user_segment(page, 0, PAGE_SIZE);
if (!PageUptodate(page))
SetPageUptodate(page);
unlock_page(page);
return page;
}
err = f2fs_submit_page_read(inode, page, dn.data_blkaddr);
if (err)
goto put_err;
return page;
put_err:
f2fs_put_page(page, 1);
return ERR_PTR(err);
}
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 19:20:41 +03:00
struct page *f2fs_find_data_page(struct inode *inode, pgoff_t index)
{
struct address_space *mapping = inode->i_mapping;
struct page *page;
page = find_get_page(mapping, index);
if (page && PageUptodate(page))
return page;
f2fs_put_page(page, 0);
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 19:20:41 +03:00
page = f2fs_get_read_data_page(inode, index, 0, false);
if (IS_ERR(page))
return page;
if (PageUptodate(page))
return page;
wait_on_page_locked(page);
if (unlikely(!PageUptodate(page))) {
f2fs_put_page(page, 0);
return ERR_PTR(-EIO);
}
return page;
}
/*
* If it tries to access a hole, return an error.
* Because, the callers, functions in dir.c and GC, should be able to know
* whether this page exists or not.
*/
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 19:20:41 +03:00
struct page *f2fs_get_lock_data_page(struct inode *inode, pgoff_t index,
bool for_write)
{
struct address_space *mapping = inode->i_mapping;
struct page *page;
repeat:
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 19:20:41 +03:00
page = f2fs_get_read_data_page(inode, index, 0, for_write);
if (IS_ERR(page))
return page;
/* wait for read completion */
lock_page(page);
if (unlikely(page->mapping != mapping)) {
f2fs_put_page(page, 1);
goto repeat;
}
if (unlikely(!PageUptodate(page))) {
f2fs_put_page(page, 1);
return ERR_PTR(-EIO);
}
return page;
}
/*
* Caller ensures that this data page is never allocated.
* A new zero-filled data page is allocated in the page cache.
f2fs: introduce a new global lock scheme In the previous version, f2fs uses global locks according to the usage types, such as directory operations, block allocation, block write, and so on. Reference the following lock types in f2fs.h. enum lock_type { RENAME, /* for renaming operations */ DENTRY_OPS, /* for directory operations */ DATA_WRITE, /* for data write */ DATA_NEW, /* for data allocation */ DATA_TRUNC, /* for data truncate */ NODE_NEW, /* for node allocation */ NODE_TRUNC, /* for node truncate */ NODE_WRITE, /* for node write */ NR_LOCK_TYPE, }; In that case, we lose the performance under the multi-threading environment, since every types of operations must be conducted one at a time. In order to address the problem, let's share the locks globally with a mutex array regardless of any types. So, let users grab a mutex and perform their jobs in parallel as much as possbile. For this, I propose a new global lock scheme as follows. 0. Data structure - f2fs_sb_info -> mutex_lock[NR_GLOBAL_LOCKS] - f2fs_sb_info -> node_write 1. mutex_lock_op(sbi) - try to get an avaiable lock from the array. - returns the index of the gottern lock variable. 2. mutex_unlock_op(sbi, index of the lock) - unlock the given index of the lock. 3. mutex_lock_all(sbi) - grab all the locks in the array before the checkpoint. 4. mutex_unlock_all(sbi) - release all the locks in the array after checkpoint. 5. block_operations() - call mutex_lock_all() - sync_dirty_dir_inodes() - grab node_write - sync_node_pages() Note that, the pairs of mutex_lock_op()/mutex_unlock_op() and mutex_lock_all()/mutex_unlock_all() should be used together. Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2012-11-22 11:21:29 +04:00
*
* Also, caller should grab and release a rwsem by calling f2fs_lock_op() and
* f2fs_unlock_op().
* Note that, ipage is set only by make_empty_dir, and if any error occur,
* ipage should be released by this function.
*/
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 19:20:41 +03:00
struct page *f2fs_get_new_data_page(struct inode *inode,
struct page *ipage, pgoff_t index, bool new_i_size)
{
struct address_space *mapping = inode->i_mapping;
struct page *page;
struct dnode_of_data dn;
int err;
page = f2fs_grab_cache_page(mapping, index, true);
if (!page) {
/*
* before exiting, we should make sure ipage will be released
* if any error occur.
*/
f2fs_put_page(ipage, 1);
return ERR_PTR(-ENOMEM);
}
set_new_dnode(&dn, inode, ipage, NULL, 0);
err = f2fs_reserve_block(&dn, index);
if (err) {
f2fs_put_page(page, 1);
return ERR_PTR(err);
}
if (!ipage)
f2fs_put_dnode(&dn);
if (PageUptodate(page))
goto got_it;
if (dn.data_blkaddr == NEW_ADDR) {
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 15:29:47 +03:00
zero_user_segment(page, 0, PAGE_SIZE);
if (!PageUptodate(page))
SetPageUptodate(page);
} else {
f2fs_put_page(page, 1);
/* if ipage exists, blkaddr should be NEW_ADDR */
f2fs_bug_on(F2FS_I_SB(inode), ipage);
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 19:20:41 +03:00
page = f2fs_get_lock_data_page(inode, index, true);
if (IS_ERR(page))
return page;
}
got_it:
if (new_i_size && i_size_read(inode) <
((loff_t)(index + 1) << PAGE_SHIFT))
f2fs_i_size_write(inode, ((loff_t)(index + 1) << PAGE_SHIFT));
return page;
}
static int __allocate_data_block(struct dnode_of_data *dn, int seg_type)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
struct f2fs_summary sum;
struct node_info ni;
f2fs: readahead encrypted block during GC During GC, for each encrypted block, we will read block synchronously into meta page, and then submit it into current cold data log area. So this block read model with 4k granularity can make poor performance, like migrating non-encrypted block, let's readahead encrypted block as well to improve migration performance. To implement this, we choose meta page that its index is old block address of the encrypted block, and readahead ciphertext into this page, later, if readaheaded page is still updated, we will load its data into target meta page, and submit the write IO. Note that for OPU, truncation, deletion, we need to invalid meta page after we invalid old block address, to make sure we won't load invalid data from target meta page during encrypted block migration. for ((i = 0; i < 1000; i++)) do { xfs_io -f /mnt/f2fs/dir/$i -c "pwrite 0 128k" -c "fsync"; } done for ((i = 0; i < 1000; i+=2)) do { rm /mnt/f2fs/dir/$i; } done ret = ioctl(fd, F2FS_IOC_GARBAGE_COLLECT, 0); Before: gc-6549 [001] d..1 214682.212797: block_rq_insert: 8,32 RA 32768 () 786400 + 64 [gc] gc-6549 [001] d..1 214682.212802: block_unplug: [gc] 1 gc-6549 [001] .... 214682.213892: block_bio_queue: 8,32 R 67494144 + 8 [gc] gc-6549 [001] .... 214682.213899: block_getrq: 8,32 R 67494144 + 8 [gc] gc-6549 [001] .... 214682.213902: block_plug: [gc] gc-6549 [001] d..1 214682.213905: block_rq_insert: 8,32 R 4096 () 67494144 + 8 [gc] gc-6549 [001] d..1 214682.213908: block_unplug: [gc] 1 gc-6549 [001] .... 214682.226405: block_bio_queue: 8,32 R 67494152 + 8 [gc] gc-6549 [001] .... 214682.226412: block_getrq: 8,32 R 67494152 + 8 [gc] gc-6549 [001] .... 214682.226414: block_plug: [gc] gc-6549 [001] d..1 214682.226417: block_rq_insert: 8,32 R 4096 () 67494152 + 8 [gc] gc-6549 [001] d..1 214682.226420: block_unplug: [gc] 1 gc-6549 [001] .... 214682.226904: block_bio_queue: 8,32 R 67494160 + 8 [gc] gc-6549 [001] .... 214682.226910: block_getrq: 8,32 R 67494160 + 8 [gc] gc-6549 [001] .... 214682.226911: block_plug: [gc] gc-6549 [001] d..1 214682.226914: block_rq_insert: 8,32 R 4096 () 67494160 + 8 [gc] gc-6549 [001] d..1 214682.226916: block_unplug: [gc] 1 After: gc-5678 [003] .... 214327.025906: block_bio_queue: 8,32 R 67493824 + 8 [gc] gc-5678 [003] .... 214327.025908: block_bio_backmerge: 8,32 R 67493824 + 8 [gc] gc-5678 [003] .... 214327.025915: block_bio_queue: 8,32 R 67493832 + 8 [gc] gc-5678 [003] .... 214327.025917: block_bio_backmerge: 8,32 R 67493832 + 8 [gc] gc-5678 [003] .... 214327.025923: block_bio_queue: 8,32 R 67493840 + 8 [gc] gc-5678 [003] .... 214327.025925: block_bio_backmerge: 8,32 R 67493840 + 8 [gc] gc-5678 [003] .... 214327.025932: block_bio_queue: 8,32 R 67493848 + 8 [gc] gc-5678 [003] .... 214327.025934: block_bio_backmerge: 8,32 R 67493848 + 8 [gc] gc-5678 [003] .... 214327.025941: block_bio_queue: 8,32 R 67493856 + 8 [gc] gc-5678 [003] .... 214327.025943: block_bio_backmerge: 8,32 R 67493856 + 8 [gc] gc-5678 [003] .... 214327.025953: block_bio_queue: 8,32 R 67493864 + 8 [gc] gc-5678 [003] .... 214327.025955: block_bio_backmerge: 8,32 R 67493864 + 8 [gc] gc-5678 [003] .... 214327.025962: block_bio_queue: 8,32 R 67493872 + 8 [gc] gc-5678 [003] .... 214327.025964: block_bio_backmerge: 8,32 R 67493872 + 8 [gc] gc-5678 [003] .... 214327.025970: block_bio_queue: 8,32 R 67493880 + 8 [gc] gc-5678 [003] .... 214327.025972: block_bio_backmerge: 8,32 R 67493880 + 8 [gc] gc-5678 [003] .... 214327.026000: block_bio_queue: 8,32 WS 34123776 + 2048 [gc] gc-5678 [003] .... 214327.026019: block_getrq: 8,32 WS 34123776 + 2048 [gc] gc-5678 [003] d..1 214327.026021: block_rq_insert: 8,32 R 131072 () 67493632 + 256 [gc] gc-5678 [003] d..1 214327.026023: block_unplug: [gc] 1 gc-5678 [003] d..1 214327.026026: block_rq_issue: 8,32 R 131072 () 67493632 + 256 [gc] gc-5678 [003] .... 214327.026046: block_plug: [gc] Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-08-14 17:37:25 +03:00
block_t old_blkaddr;
blkcnt_t count = 1;
int err;
if (unlikely(is_inode_flag_set(dn->inode, FI_NO_ALLOC)))
return -EPERM;
err = f2fs_get_node_info(sbi, dn->nid, &ni);
if (err)
return err;
f2fs: enhance on-disk inode structure scalability This patch add new flag F2FS_EXTRA_ATTR storing in inode.i_inline to indicate that on-disk structure of current inode is extended. In order to extend, we changed the inode structure a bit: Original one: struct f2fs_inode { ... struct f2fs_extent i_ext; __le32 i_addr[DEF_ADDRS_PER_INODE]; __le32 i_nid[DEF_NIDS_PER_INODE]; } Extended one: struct f2fs_inode { ... struct f2fs_extent i_ext; union { struct { __le16 i_extra_isize; __le16 i_padding; __le32 i_extra_end[0]; }; __le32 i_addr[DEF_ADDRS_PER_INODE]; }; __le32 i_nid[DEF_NIDS_PER_INODE]; } Once F2FS_EXTRA_ATTR is set, we will steal four bytes in the head of i_addr field for storing i_extra_isize and i_padding. with i_extra_isize, we can calculate actual size of reserved space in i_addr, available attribute fields included in total extra attribute fields for current inode can be described as below: +--------------------+ | .i_mode | | ... | | .i_ext | +--------------------+ | .i_extra_isize |-----+ | .i_padding | | | .i_prjid | | | .i_atime_extra | | | .i_ctime_extra | | | .i_mtime_extra |<----+ | .i_inode_cs |<----- store blkaddr/inline from here | .i_xattr_cs | | ... | +--------------------+ | | | block address | | | +--------------------+ | .i_nid | +--------------------+ | node_footer | | (nid, ino, offset) | +--------------------+ Hence, with this patch, we would enhance scalability of f2fs inode for storing more newly added attribute. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2017-07-18 19:19:06 +03:00
dn->data_blkaddr = datablock_addr(dn->inode,
dn->node_page, dn->ofs_in_node);
if (dn->data_blkaddr != NULL_ADDR)
goto alloc;
if (unlikely((err = inc_valid_block_count(sbi, dn->inode, &count))))
return err;
alloc:
set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version);
f2fs: readahead encrypted block during GC During GC, for each encrypted block, we will read block synchronously into meta page, and then submit it into current cold data log area. So this block read model with 4k granularity can make poor performance, like migrating non-encrypted block, let's readahead encrypted block as well to improve migration performance. To implement this, we choose meta page that its index is old block address of the encrypted block, and readahead ciphertext into this page, later, if readaheaded page is still updated, we will load its data into target meta page, and submit the write IO. Note that for OPU, truncation, deletion, we need to invalid meta page after we invalid old block address, to make sure we won't load invalid data from target meta page during encrypted block migration. for ((i = 0; i < 1000; i++)) do { xfs_io -f /mnt/f2fs/dir/$i -c "pwrite 0 128k" -c "fsync"; } done for ((i = 0; i < 1000; i+=2)) do { rm /mnt/f2fs/dir/$i; } done ret = ioctl(fd, F2FS_IOC_GARBAGE_COLLECT, 0); Before: gc-6549 [001] d..1 214682.212797: block_rq_insert: 8,32 RA 32768 () 786400 + 64 [gc] gc-6549 [001] d..1 214682.212802: block_unplug: [gc] 1 gc-6549 [001] .... 214682.213892: block_bio_queue: 8,32 R 67494144 + 8 [gc] gc-6549 [001] .... 214682.213899: block_getrq: 8,32 R 67494144 + 8 [gc] gc-6549 [001] .... 214682.213902: block_plug: [gc] gc-6549 [001] d..1 214682.213905: block_rq_insert: 8,32 R 4096 () 67494144 + 8 [gc] gc-6549 [001] d..1 214682.213908: block_unplug: [gc] 1 gc-6549 [001] .... 214682.226405: block_bio_queue: 8,32 R 67494152 + 8 [gc] gc-6549 [001] .... 214682.226412: block_getrq: 8,32 R 67494152 + 8 [gc] gc-6549 [001] .... 214682.226414: block_plug: [gc] gc-6549 [001] d..1 214682.226417: block_rq_insert: 8,32 R 4096 () 67494152 + 8 [gc] gc-6549 [001] d..1 214682.226420: block_unplug: [gc] 1 gc-6549 [001] .... 214682.226904: block_bio_queue: 8,32 R 67494160 + 8 [gc] gc-6549 [001] .... 214682.226910: block_getrq: 8,32 R 67494160 + 8 [gc] gc-6549 [001] .... 214682.226911: block_plug: [gc] gc-6549 [001] d..1 214682.226914: block_rq_insert: 8,32 R 4096 () 67494160 + 8 [gc] gc-6549 [001] d..1 214682.226916: block_unplug: [gc] 1 After: gc-5678 [003] .... 214327.025906: block_bio_queue: 8,32 R 67493824 + 8 [gc] gc-5678 [003] .... 214327.025908: block_bio_backmerge: 8,32 R 67493824 + 8 [gc] gc-5678 [003] .... 214327.025915: block_bio_queue: 8,32 R 67493832 + 8 [gc] gc-5678 [003] .... 214327.025917: block_bio_backmerge: 8,32 R 67493832 + 8 [gc] gc-5678 [003] .... 214327.025923: block_bio_queue: 8,32 R 67493840 + 8 [gc] gc-5678 [003] .... 214327.025925: block_bio_backmerge: 8,32 R 67493840 + 8 [gc] gc-5678 [003] .... 214327.025932: block_bio_queue: 8,32 R 67493848 + 8 [gc] gc-5678 [003] .... 214327.025934: block_bio_backmerge: 8,32 R 67493848 + 8 [gc] gc-5678 [003] .... 214327.025941: block_bio_queue: 8,32 R 67493856 + 8 [gc] gc-5678 [003] .... 214327.025943: block_bio_backmerge: 8,32 R 67493856 + 8 [gc] gc-5678 [003] .... 214327.025953: block_bio_queue: 8,32 R 67493864 + 8 [gc] gc-5678 [003] .... 214327.025955: block_bio_backmerge: 8,32 R 67493864 + 8 [gc] gc-5678 [003] .... 214327.025962: block_bio_queue: 8,32 R 67493872 + 8 [gc] gc-5678 [003] .... 214327.025964: block_bio_backmerge: 8,32 R 67493872 + 8 [gc] gc-5678 [003] .... 214327.025970: block_bio_queue: 8,32 R 67493880 + 8 [gc] gc-5678 [003] .... 214327.025972: block_bio_backmerge: 8,32 R 67493880 + 8 [gc] gc-5678 [003] .... 214327.026000: block_bio_queue: 8,32 WS 34123776 + 2048 [gc] gc-5678 [003] .... 214327.026019: block_getrq: 8,32 WS 34123776 + 2048 [gc] gc-5678 [003] d..1 214327.026021: block_rq_insert: 8,32 R 131072 () 67493632 + 256 [gc] gc-5678 [003] d..1 214327.026023: block_unplug: [gc] 1 gc-5678 [003] d..1 214327.026026: block_rq_issue: 8,32 R 131072 () 67493632 + 256 [gc] gc-5678 [003] .... 214327.026046: block_plug: [gc] Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-08-14 17:37:25 +03:00
old_blkaddr = dn->data_blkaddr;
f2fs_allocate_data_block(sbi, NULL, old_blkaddr, &dn->data_blkaddr,
&sum, seg_type, NULL, false);
f2fs: readahead encrypted block during GC During GC, for each encrypted block, we will read block synchronously into meta page, and then submit it into current cold data log area. So this block read model with 4k granularity can make poor performance, like migrating non-encrypted block, let's readahead encrypted block as well to improve migration performance. To implement this, we choose meta page that its index is old block address of the encrypted block, and readahead ciphertext into this page, later, if readaheaded page is still updated, we will load its data into target meta page, and submit the write IO. Note that for OPU, truncation, deletion, we need to invalid meta page after we invalid old block address, to make sure we won't load invalid data from target meta page during encrypted block migration. for ((i = 0; i < 1000; i++)) do { xfs_io -f /mnt/f2fs/dir/$i -c "pwrite 0 128k" -c "fsync"; } done for ((i = 0; i < 1000; i+=2)) do { rm /mnt/f2fs/dir/$i; } done ret = ioctl(fd, F2FS_IOC_GARBAGE_COLLECT, 0); Before: gc-6549 [001] d..1 214682.212797: block_rq_insert: 8,32 RA 32768 () 786400 + 64 [gc] gc-6549 [001] d..1 214682.212802: block_unplug: [gc] 1 gc-6549 [001] .... 214682.213892: block_bio_queue: 8,32 R 67494144 + 8 [gc] gc-6549 [001] .... 214682.213899: block_getrq: 8,32 R 67494144 + 8 [gc] gc-6549 [001] .... 214682.213902: block_plug: [gc] gc-6549 [001] d..1 214682.213905: block_rq_insert: 8,32 R 4096 () 67494144 + 8 [gc] gc-6549 [001] d..1 214682.213908: block_unplug: [gc] 1 gc-6549 [001] .... 214682.226405: block_bio_queue: 8,32 R 67494152 + 8 [gc] gc-6549 [001] .... 214682.226412: block_getrq: 8,32 R 67494152 + 8 [gc] gc-6549 [001] .... 214682.226414: block_plug: [gc] gc-6549 [001] d..1 214682.226417: block_rq_insert: 8,32 R 4096 () 67494152 + 8 [gc] gc-6549 [001] d..1 214682.226420: block_unplug: [gc] 1 gc-6549 [001] .... 214682.226904: block_bio_queue: 8,32 R 67494160 + 8 [gc] gc-6549 [001] .... 214682.226910: block_getrq: 8,32 R 67494160 + 8 [gc] gc-6549 [001] .... 214682.226911: block_plug: [gc] gc-6549 [001] d..1 214682.226914: block_rq_insert: 8,32 R 4096 () 67494160 + 8 [gc] gc-6549 [001] d..1 214682.226916: block_unplug: [gc] 1 After: gc-5678 [003] .... 214327.025906: block_bio_queue: 8,32 R 67493824 + 8 [gc] gc-5678 [003] .... 214327.025908: block_bio_backmerge: 8,32 R 67493824 + 8 [gc] gc-5678 [003] .... 214327.025915: block_bio_queue: 8,32 R 67493832 + 8 [gc] gc-5678 [003] .... 214327.025917: block_bio_backmerge: 8,32 R 67493832 + 8 [gc] gc-5678 [003] .... 214327.025923: block_bio_queue: 8,32 R 67493840 + 8 [gc] gc-5678 [003] .... 214327.025925: block_bio_backmerge: 8,32 R 67493840 + 8 [gc] gc-5678 [003] .... 214327.025932: block_bio_queue: 8,32 R 67493848 + 8 [gc] gc-5678 [003] .... 214327.025934: block_bio_backmerge: 8,32 R 67493848 + 8 [gc] gc-5678 [003] .... 214327.025941: block_bio_queue: 8,32 R 67493856 + 8 [gc] gc-5678 [003] .... 214327.025943: block_bio_backmerge: 8,32 R 67493856 + 8 [gc] gc-5678 [003] .... 214327.025953: block_bio_queue: 8,32 R 67493864 + 8 [gc] gc-5678 [003] .... 214327.025955: block_bio_backmerge: 8,32 R 67493864 + 8 [gc] gc-5678 [003] .... 214327.025962: block_bio_queue: 8,32 R 67493872 + 8 [gc] gc-5678 [003] .... 214327.025964: block_bio_backmerge: 8,32 R 67493872 + 8 [gc] gc-5678 [003] .... 214327.025970: block_bio_queue: 8,32 R 67493880 + 8 [gc] gc-5678 [003] .... 214327.025972: block_bio_backmerge: 8,32 R 67493880 + 8 [gc] gc-5678 [003] .... 214327.026000: block_bio_queue: 8,32 WS 34123776 + 2048 [gc] gc-5678 [003] .... 214327.026019: block_getrq: 8,32 WS 34123776 + 2048 [gc] gc-5678 [003] d..1 214327.026021: block_rq_insert: 8,32 R 131072 () 67493632 + 256 [gc] gc-5678 [003] d..1 214327.026023: block_unplug: [gc] 1 gc-5678 [003] d..1 214327.026026: block_rq_issue: 8,32 R 131072 () 67493632 + 256 [gc] gc-5678 [003] .... 214327.026046: block_plug: [gc] Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-08-14 17:37:25 +03:00
if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO)
invalidate_mapping_pages(META_MAPPING(sbi),
old_blkaddr, old_blkaddr);
f2fs_update_data_blkaddr(dn, dn->data_blkaddr);
/*
* i_size will be updated by direct_IO. Otherwise, we'll get stale
* data from unwritten block via dio_read.
*/
return 0;
}
int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from)
{
struct inode *inode = file_inode(iocb->ki_filp);
struct f2fs_map_blocks map;
int flag;
int err = 0;
bool direct_io = iocb->ki_flags & IOCB_DIRECT;
/* convert inline data for Direct I/O*/
if (direct_io) {
err = f2fs_convert_inline_inode(inode);
if (err)
return err;
}
f2fs: fix out-place-update DIO write In get_more_blocks(), we may override @create as below code: create = dio->op == REQ_OP_WRITE; if (dio->flags & DIO_SKIP_HOLES) { if (fs_startblk <= ((i_size_read(dio->inode) - 1) >> i_blkbits)) create = 0; } But in f2fs_map_blocks(), we only trigger f2fs_balance_fs() if @create is 1, so in LFS mode, dio overwrite under LFS mode can easily run out of free segments, result in below panic. Call Trace: allocate_segment_by_default+0xa8/0x270 [f2fs] f2fs_allocate_data_block+0x1ea/0x5c0 [f2fs] __allocate_data_block+0x306/0x480 [f2fs] f2fs_map_blocks+0x6f6/0x920 [f2fs] __get_data_block+0x4f/0xb0 [f2fs] get_data_block_dio_write+0x50/0x60 [f2fs] do_blockdev_direct_IO+0xcd5/0x21e0 __blockdev_direct_IO+0x3a/0x3c f2fs_direct_IO+0x1ff/0x4a0 [f2fs] generic_file_direct_write+0xd9/0x160 __generic_file_write_iter+0xbb/0x1e0 f2fs_file_write_iter+0xaf/0x220 [f2fs] __vfs_write+0xd0/0x130 vfs_write+0xb2/0x1b0 SyS_pwrite64+0x69/0xa0 ? vtime_user_exit+0x29/0x70 do_syscall_64+0x6e/0x160 entry_SYSCALL64_slow_path+0x25/0x25 RIP: new_curseg+0x36f/0x380 [f2fs] RSP: ffffac570393f7a8 So this patch introduces a parameter map.m_may_create to indicate that f2fs_map_blocks() is called from write or read path, which can give the right hint to let f2fs_map_blocks() trigger OPU allocation and call f2fs_balanc_fs() correctly. BTW, it disables physical address preallocation for direct IO in f2fs_preallocate_blocks, which is redundant to OPU allocation of f2fs_map_blocks. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-11-13 09:33:45 +03:00
if (direct_io && allow_outplace_dio(inode, iocb, from))
return 0;
if (is_inode_flag_set(inode, FI_NO_PREALLOC))
return 0;
map.m_lblk = F2FS_BLK_ALIGN(iocb->ki_pos);
map.m_len = F2FS_BYTES_TO_BLK(iocb->ki_pos + iov_iter_count(from));
if (map.m_len > map.m_lblk)
map.m_len -= map.m_lblk;
else
map.m_len = 0;
map.m_next_pgofs = NULL;
map.m_next_extent = NULL;
map.m_seg_type = NO_CHECK_TYPE;
f2fs: fix out-place-update DIO write In get_more_blocks(), we may override @create as below code: create = dio->op == REQ_OP_WRITE; if (dio->flags & DIO_SKIP_HOLES) { if (fs_startblk <= ((i_size_read(dio->inode) - 1) >> i_blkbits)) create = 0; } But in f2fs_map_blocks(), we only trigger f2fs_balance_fs() if @create is 1, so in LFS mode, dio overwrite under LFS mode can easily run out of free segments, result in below panic. Call Trace: allocate_segment_by_default+0xa8/0x270 [f2fs] f2fs_allocate_data_block+0x1ea/0x5c0 [f2fs] __allocate_data_block+0x306/0x480 [f2fs] f2fs_map_blocks+0x6f6/0x920 [f2fs] __get_data_block+0x4f/0xb0 [f2fs] get_data_block_dio_write+0x50/0x60 [f2fs] do_blockdev_direct_IO+0xcd5/0x21e0 __blockdev_direct_IO+0x3a/0x3c f2fs_direct_IO+0x1ff/0x4a0 [f2fs] generic_file_direct_write+0xd9/0x160 __generic_file_write_iter+0xbb/0x1e0 f2fs_file_write_iter+0xaf/0x220 [f2fs] __vfs_write+0xd0/0x130 vfs_write+0xb2/0x1b0 SyS_pwrite64+0x69/0xa0 ? vtime_user_exit+0x29/0x70 do_syscall_64+0x6e/0x160 entry_SYSCALL64_slow_path+0x25/0x25 RIP: new_curseg+0x36f/0x380 [f2fs] RSP: ffffac570393f7a8 So this patch introduces a parameter map.m_may_create to indicate that f2fs_map_blocks() is called from write or read path, which can give the right hint to let f2fs_map_blocks() trigger OPU allocation and call f2fs_balanc_fs() correctly. BTW, it disables physical address preallocation for direct IO in f2fs_preallocate_blocks, which is redundant to OPU allocation of f2fs_map_blocks. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-11-13 09:33:45 +03:00
map.m_may_create = true;
if (direct_io) {
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 19:20:41 +03:00
map.m_seg_type = f2fs_rw_hint_to_seg_type(iocb->ki_hint);
flag = f2fs_force_buffered_io(inode, iocb, from) ?
F2FS_GET_BLOCK_PRE_AIO :
F2FS_GET_BLOCK_PRE_DIO;
goto map_blocks;
}
if (iocb->ki_pos + iov_iter_count(from) > MAX_INLINE_DATA(inode)) {
err = f2fs_convert_inline_inode(inode);
if (err)
return err;
}
if (f2fs_has_inline_data(inode))
return err;
flag = F2FS_GET_BLOCK_PRE_AIO;
map_blocks:
err = f2fs_map_blocks(inode, &map, 1, flag);
if (map.m_len > 0 && err == -ENOSPC) {
if (!direct_io)
set_inode_flag(inode, FI_NO_PREALLOC);
err = 0;
}
return err;
}
void __do_map_lock(struct f2fs_sb_info *sbi, int flag, bool lock)
{
if (flag == F2FS_GET_BLOCK_PRE_AIO) {
if (lock)
down_read(&sbi->node_change);
else
up_read(&sbi->node_change);
} else {
if (lock)
f2fs_lock_op(sbi);
else
f2fs_unlock_op(sbi);
}
}
/*
* f2fs_map_blocks() now supported readahead/bmap/rw direct_IO with
* f2fs_map_blocks structure.
* If original data blocks are allocated, then give them to blockdev.
* Otherwise,
* a. preallocate requested block addresses
* b. do not use extent cache for better performance
* c. give the block addresses to blockdev
*/
int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
int create, int flag)
{
unsigned int maxblocks = map->m_len;
struct dnode_of_data dn;
f2fs: fix to handle io error in ->direct_IO Here is a oops reported as following message when testing generic/019 of xfstest: ------------[ cut here ]------------ kernel BUG at /home/yuchao/git/f2fs-dev/segment.c:882! invalid opcode: 0000 [#1] SMP Modules linked in: zram lz4_compress lz4_decompress f2fs(O) ip6table_filter ip6_tables ebtable_nat ebtables nf_conntrack_ipv4 nf_def CPU: 2 PID: 25441 Comm: fio Tainted: G O 4.3.0-rc1+ #6 Hardware name: Hewlett-Packard HP Z220 CMT Workstation/1790, BIOS K51 v01.61 05/16/2013 task: ffff8803f4e85580 ti: ffff8803fd61c000 task.ti: ffff8803fd61c000 RIP: 0010:[<ffffffffa0784981>] [<ffffffffa0784981>] new_curseg+0x321/0x330 [f2fs] RSP: 0018:ffff8803fd61f918 EFLAGS: 00010246 RAX: 00000000000007ed RBX: 0000000000000224 RCX: 000000000000001f RDX: 0000000000000800 RSI: ffffffffffffffff RDI: ffff8803f56f4300 RBP: ffff8803fd61f978 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000024 R11: ffff8800d23bbd78 R12: ffff8800d0ef0000 R13: 0000000000000224 R14: 0000000000000000 R15: 0000000000000001 FS: 00007f827ff85700(0000) GS:ffff88041ea80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffffffff600000 CR3: 00000003fef17000 CR4: 00000000001406e0 Stack: 000007ea00000002 0000000100000001 ffff8803f6456248 000007ed0000002b 0000000000000224 ffff880404d1aa20 ffff8803fd61f9c8 ffff8800d0ef0000 ffff8803f6456248 0000000000000001 00000000ffffffff ffffffffa078f358 Call Trace: [<ffffffffa0785b87>] allocate_segment_by_default+0x1a7/0x1f0 [f2fs] [<ffffffffa078322c>] allocate_data_block+0x17c/0x360 [f2fs] [<ffffffffa0779521>] __allocate_data_block+0x131/0x1d0 [f2fs] [<ffffffffa077a995>] f2fs_direct_IO+0x4b5/0x580 [f2fs] [<ffffffff811510ae>] generic_file_direct_write+0xae/0x160 [<ffffffff811518f5>] __generic_file_write_iter+0xd5/0x1f0 [<ffffffff81151e07>] generic_file_write_iter+0xf7/0x200 [<ffffffff81319e38>] ? apparmor_file_permission+0x18/0x20 [<ffffffffa0768480>] ? f2fs_fallocate+0x1190/0x1190 [f2fs] [<ffffffffa07684c6>] f2fs_file_write_iter+0x46/0x90 [f2fs] [<ffffffff8120b4fe>] aio_run_iocb+0x1ee/0x290 [<ffffffff81700f7e>] ? mutex_lock+0x1e/0x50 [<ffffffff8120a1d7>] ? aio_read_events+0x207/0x2b0 [<ffffffff8120b913>] do_io_submit+0x373/0x630 [<ffffffff8120a4f6>] ? SyS_io_getevents+0x56/0xb0 [<ffffffff8120bbe0>] SyS_io_submit+0x10/0x20 [<ffffffff81703857>] entry_SYSCALL_64_fastpath+0x12/0x6a Code: 45 c8 48 8b 78 10 e8 9f 23 bf e0 41 8b 8c 24 cc 03 00 00 89 c7 31 d2 89 c6 89 d8 29 df f7 f1 29 d1 39 cf 0f 83 be fd ff ff eb RIP [<ffffffffa0784981>] new_curseg+0x321/0x330 [f2fs] RSP <ffff8803fd61f918> ---[ end trace 2e577d7f711ddb86 ]--- The reason is that: in the test of generic/019, we will trigger a manmade IO error in block layer through debugfs, after that, prefree segment will no longer be freed, because we always skip doing gc or checkpoint when there occurs an IO error. Meanwhile fio with aio engine generated a large number of direct IOs, which continue allocating spaces in free segment until we run out of them, eventually, results in panic in new_curseg as no more free segment was found. So, this patch changes to return EIO in direct_IO for this condition. Signed-off-by: Chao Yu <chao2.yu@samsung.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2015-09-21 15:17:52 +03:00
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
f2fs: fix out-place-update DIO write In get_more_blocks(), we may override @create as below code: create = dio->op == REQ_OP_WRITE; if (dio->flags & DIO_SKIP_HOLES) { if (fs_startblk <= ((i_size_read(dio->inode) - 1) >> i_blkbits)) create = 0; } But in f2fs_map_blocks(), we only trigger f2fs_balance_fs() if @create is 1, so in LFS mode, dio overwrite under LFS mode can easily run out of free segments, result in below panic. Call Trace: allocate_segment_by_default+0xa8/0x270 [f2fs] f2fs_allocate_data_block+0x1ea/0x5c0 [f2fs] __allocate_data_block+0x306/0x480 [f2fs] f2fs_map_blocks+0x6f6/0x920 [f2fs] __get_data_block+0x4f/0xb0 [f2fs] get_data_block_dio_write+0x50/0x60 [f2fs] do_blockdev_direct_IO+0xcd5/0x21e0 __blockdev_direct_IO+0x3a/0x3c f2fs_direct_IO+0x1ff/0x4a0 [f2fs] generic_file_direct_write+0xd9/0x160 __generic_file_write_iter+0xbb/0x1e0 f2fs_file_write_iter+0xaf/0x220 [f2fs] __vfs_write+0xd0/0x130 vfs_write+0xb2/0x1b0 SyS_pwrite64+0x69/0xa0 ? vtime_user_exit+0x29/0x70 do_syscall_64+0x6e/0x160 entry_SYSCALL64_slow_path+0x25/0x25 RIP: new_curseg+0x36f/0x380 [f2fs] RSP: ffffac570393f7a8 So this patch introduces a parameter map.m_may_create to indicate that f2fs_map_blocks() is called from write or read path, which can give the right hint to let f2fs_map_blocks() trigger OPU allocation and call f2fs_balanc_fs() correctly. BTW, it disables physical address preallocation for direct IO in f2fs_preallocate_blocks, which is redundant to OPU allocation of f2fs_map_blocks. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-11-13 09:33:45 +03:00
int mode = map->m_may_create ? ALLOC_NODE : LOOKUP_NODE;
pgoff_t pgofs, end_offset, end;
int err = 0, ofs = 1;
unsigned int ofs_in_node, last_ofs_in_node;
blkcnt_t prealloc;
struct extent_info ei = {0,0,0};
block_t blkaddr;
unsigned int start_pgofs;
if (!maxblocks)
return 0;
map->m_len = 0;
map->m_flags = 0;
/* it only supports block size == page size */
pgofs = (pgoff_t)map->m_lblk;
end = pgofs + maxblocks;
if (!create && f2fs_lookup_extent_cache(inode, pgofs, &ei)) {
if (test_opt(sbi, LFS) && flag == F2FS_GET_BLOCK_DIO &&
map->m_may_create)
goto next_dnode;
map->m_pblk = ei.blk + pgofs - ei.fofs;
map->m_len = min((pgoff_t)maxblocks, ei.fofs + ei.len - pgofs);
map->m_flags = F2FS_MAP_MAPPED;
if (map->m_next_extent)
*map->m_next_extent = pgofs + map->m_len;
/* for hardware encryption, but to avoid potential issue in future */
if (flag == F2FS_GET_BLOCK_DIO)
f2fs_wait_on_block_writeback_range(inode,
map->m_pblk, map->m_len);
goto out;
}
next_dnode:
f2fs: fix out-place-update DIO write In get_more_blocks(), we may override @create as below code: create = dio->op == REQ_OP_WRITE; if (dio->flags & DIO_SKIP_HOLES) { if (fs_startblk <= ((i_size_read(dio->inode) - 1) >> i_blkbits)) create = 0; } But in f2fs_map_blocks(), we only trigger f2fs_balance_fs() if @create is 1, so in LFS mode, dio overwrite under LFS mode can easily run out of free segments, result in below panic. Call Trace: allocate_segment_by_default+0xa8/0x270 [f2fs] f2fs_allocate_data_block+0x1ea/0x5c0 [f2fs] __allocate_data_block+0x306/0x480 [f2fs] f2fs_map_blocks+0x6f6/0x920 [f2fs] __get_data_block+0x4f/0xb0 [f2fs] get_data_block_dio_write+0x50/0x60 [f2fs] do_blockdev_direct_IO+0xcd5/0x21e0 __blockdev_direct_IO+0x3a/0x3c f2fs_direct_IO+0x1ff/0x4a0 [f2fs] generic_file_direct_write+0xd9/0x160 __generic_file_write_iter+0xbb/0x1e0 f2fs_file_write_iter+0xaf/0x220 [f2fs] __vfs_write+0xd0/0x130 vfs_write+0xb2/0x1b0 SyS_pwrite64+0x69/0xa0 ? vtime_user_exit+0x29/0x70 do_syscall_64+0x6e/0x160 entry_SYSCALL64_slow_path+0x25/0x25 RIP: new_curseg+0x36f/0x380 [f2fs] RSP: ffffac570393f7a8 So this patch introduces a parameter map.m_may_create to indicate that f2fs_map_blocks() is called from write or read path, which can give the right hint to let f2fs_map_blocks() trigger OPU allocation and call f2fs_balanc_fs() correctly. BTW, it disables physical address preallocation for direct IO in f2fs_preallocate_blocks, which is redundant to OPU allocation of f2fs_map_blocks. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-11-13 09:33:45 +03:00
if (map->m_may_create)
__do_map_lock(sbi, flag, true);
/* When reading holes, we need its node page */
set_new_dnode(&dn, inode, NULL, NULL, 0);
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 19:20:41 +03:00
err = f2fs_get_dnode_of_data(&dn, pgofs, mode);
if (err) {
if (flag == F2FS_GET_BLOCK_BMAP)
map->m_pblk = 0;
if (err == -ENOENT) {
err = 0;
if (map->m_next_pgofs)
*map->m_next_pgofs =
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 19:20:41 +03:00
f2fs_get_next_page_offset(&dn, pgofs);
if (map->m_next_extent)
*map->m_next_extent =
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 19:20:41 +03:00
f2fs_get_next_page_offset(&dn, pgofs);
}
goto unlock_out;
}
start_pgofs = pgofs;
prealloc = 0;
last_ofs_in_node = ofs_in_node = dn.ofs_in_node;
end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
next_block:
f2fs: enhance on-disk inode structure scalability This patch add new flag F2FS_EXTRA_ATTR storing in inode.i_inline to indicate that on-disk structure of current inode is extended. In order to extend, we changed the inode structure a bit: Original one: struct f2fs_inode { ... struct f2fs_extent i_ext; __le32 i_addr[DEF_ADDRS_PER_INODE]; __le32 i_nid[DEF_NIDS_PER_INODE]; } Extended one: struct f2fs_inode { ... struct f2fs_extent i_ext; union { struct { __le16 i_extra_isize; __le16 i_padding; __le32 i_extra_end[0]; }; __le32 i_addr[DEF_ADDRS_PER_INODE]; }; __le32 i_nid[DEF_NIDS_PER_INODE]; } Once F2FS_EXTRA_ATTR is set, we will steal four bytes in the head of i_addr field for storing i_extra_isize and i_padding. with i_extra_isize, we can calculate actual size of reserved space in i_addr, available attribute fields included in total extra attribute fields for current inode can be described as below: +--------------------+ | .i_mode | | ... | | .i_ext | +--------------------+ | .i_extra_isize |-----+ | .i_padding | | | .i_prjid | | | .i_atime_extra | | | .i_ctime_extra | | | .i_mtime_extra |<----+ | .i_inode_cs |<----- store blkaddr/inline from here | .i_xattr_cs | | ... | +--------------------+ | | | block address | | | +--------------------+ | .i_nid | +--------------------+ | node_footer | | (nid, ino, offset) | +--------------------+ Hence, with this patch, we would enhance scalability of f2fs inode for storing more newly added attribute. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2017-07-18 19:19:06 +03:00
blkaddr = datablock_addr(dn.inode, dn.node_page, dn.ofs_in_node);
f2fs: fix to do sanity check with block address in main area This patch add to do sanity check with below field: - cp_pack_total_block_count - blkaddr of data/node - extent info - Overview BUG() in verify_block_addr() when writing to a corrupted f2fs image - Reproduce (4.18 upstream kernel) - POC (poc.c) static void activity(char *mpoint) { char *foo_bar_baz; int err; static int buf[8192]; memset(buf, 0, sizeof(buf)); err = asprintf(&foo_bar_baz, "%s/foo/bar/baz", mpoint); int fd = open(foo_bar_baz, O_RDWR | O_TRUNC, 0777); if (fd >= 0) { write(fd, (char *)buf, sizeof(buf)); fdatasync(fd); close(fd); } } int main(int argc, char *argv[]) { activity(argv[1]); return 0; } - Kernel message [ 689.349473] F2FS-fs (loop0): Mounted with checkpoint version = 3 [ 699.728662] WARNING: CPU: 0 PID: 1309 at fs/f2fs/segment.c:2860 f2fs_inplace_write_data+0x232/0x240 [ 699.728670] Modules linked in: snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_pcm snd_timer snd mac_hid i2c_piix4 soundcore ib_iser rdma_cm iw_cm ib_cm ib_core iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx raid1 raid0 multipath linear 8139too crct10dif_pclmul crc32_pclmul qxl drm_kms_helper syscopyarea aesni_intel sysfillrect sysimgblt fb_sys_fops ttm drm aes_x86_64 crypto_simd cryptd 8139cp glue_helper mii pata_acpi floppy [ 699.729056] CPU: 0 PID: 1309 Comm: a.out Not tainted 4.18.0-rc1+ #4 [ 699.729064] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.729074] RIP: 0010:f2fs_inplace_write_data+0x232/0x240 [ 699.729076] Code: ff e9 cf fe ff ff 49 8d 7d 10 e8 39 45 ad ff 4d 8b 7d 10 be 04 00 00 00 49 8d 7f 48 e8 07 49 ad ff 45 8b 7f 48 e9 fb fe ff ff <0f> 0b f0 41 80 4d 48 04 e9 65 fe ff ff 90 66 66 66 66 90 55 48 8d [ 699.729130] RSP: 0018:ffff8801f43af568 EFLAGS: 00010202 [ 699.729139] RAX: 000000000000003f RBX: ffff8801f43af7b8 RCX: ffffffffb88c9113 [ 699.729142] RDX: 0000000000000003 RSI: dffffc0000000000 RDI: ffff8802024e5540 [ 699.729144] RBP: ffff8801f43af590 R08: 0000000000000009 R09: ffffffffffffffe8 [ 699.729147] R10: 0000000000000001 R11: ffffed0039b0596a R12: ffff8802024e5540 [ 699.729149] R13: ffff8801f0335500 R14: ffff8801e3e7a700 R15: ffff8801e1ee4450 [ 699.729154] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.729156] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.729159] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.729171] Call Trace: [ 699.729192] f2fs_do_write_data_page+0x2e2/0xe00 [ 699.729203] ? f2fs_should_update_outplace+0xd0/0xd0 [ 699.729238] ? memcg_drain_all_list_lrus+0x280/0x280 [ 699.729269] ? __radix_tree_replace+0xa3/0x120 [ 699.729276] __write_data_page+0x5c7/0xe30 [ 699.729291] ? kasan_check_read+0x11/0x20 [ 699.729310] ? page_mapped+0x8a/0x110 [ 699.729321] ? page_mkclean+0xe9/0x160 [ 699.729327] ? f2fs_do_write_data_page+0xe00/0xe00 [ 699.729331] ? invalid_page_referenced_vma+0x130/0x130 [ 699.729345] ? clear_page_dirty_for_io+0x332/0x450 [ 699.729351] f2fs_write_cache_pages+0x4ca/0x860 [ 699.729358] ? __write_data_page+0xe30/0xe30 [ 699.729374] ? percpu_counter_add_batch+0x22/0xa0 [ 699.729380] ? kasan_check_write+0x14/0x20 [ 699.729391] ? _raw_spin_lock+0x17/0x40 [ 699.729403] ? f2fs_mark_inode_dirty_sync.part.18+0x16/0x30 [ 699.729413] ? iov_iter_advance+0x113/0x640 [ 699.729418] ? f2fs_write_end+0x133/0x2e0 [ 699.729423] ? balance_dirty_pages_ratelimited+0x239/0x640 [ 699.729428] f2fs_write_data_pages+0x329/0x520 [ 699.729433] ? generic_perform_write+0x250/0x320 [ 699.729438] ? f2fs_write_cache_pages+0x860/0x860 [ 699.729454] ? current_time+0x110/0x110 [ 699.729459] ? f2fs_preallocate_blocks+0x1ef/0x370 [ 699.729464] do_writepages+0x37/0xb0 [ 699.729468] ? f2fs_write_cache_pages+0x860/0x860 [ 699.729472] ? do_writepages+0x37/0xb0 [ 699.729478] __filemap_fdatawrite_range+0x19a/0x1f0 [ 699.729483] ? delete_from_page_cache_batch+0x4e0/0x4e0 [ 699.729496] ? __vfs_write+0x2b2/0x410 [ 699.729501] file_write_and_wait_range+0x66/0xb0 [ 699.729506] f2fs_do_sync_file+0x1f9/0xd90 [ 699.729511] ? truncate_partial_data_page+0x290/0x290 [ 699.729521] ? __sb_end_write+0x30/0x50 [ 699.729526] ? vfs_write+0x20f/0x260 [ 699.729530] f2fs_sync_file+0x9a/0xb0 [ 699.729534] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.729548] vfs_fsync_range+0x68/0x100 [ 699.729554] ? __fget_light+0xc9/0xe0 [ 699.729558] do_fsync+0x3d/0x70 [ 699.729562] __x64_sys_fdatasync+0x24/0x30 [ 699.729585] do_syscall_64+0x78/0x170 [ 699.729595] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 699.729613] RIP: 0033:0x7f9bf930d800 [ 699.729615] Code: 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 83 3d 49 bf 2c 00 00 75 10 b8 4b 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 be 78 01 00 48 89 04 24 [ 699.729668] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.729673] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.729675] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.729678] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.729680] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.729683] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.729687] ---[ end trace 4ce02f25ff7d3df5 ]--- [ 699.729782] ------------[ cut here ]------------ [ 699.729785] kernel BUG at fs/f2fs/segment.h:654! [ 699.731055] invalid opcode: 0000 [#1] SMP KASAN PTI [ 699.732104] CPU: 0 PID: 1309 Comm: a.out Tainted: G W 4.18.0-rc1+ #4 [ 699.733684] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.735611] RIP: 0010:f2fs_submit_page_bio+0x29b/0x730 [ 699.736649] Code: 54 49 8d bd 18 04 00 00 e8 b2 59 af ff 41 8b 8d 18 04 00 00 8b 45 b8 41 d3 e6 44 01 f0 4c 8d 73 14 41 39 c7 0f 82 37 fe ff ff <0f> 0b 65 8b 05 2c 04 77 47 89 c0 48 0f a3 05 52 c1 d5 01 0f 92 c0 [ 699.740524] RSP: 0018:ffff8801f43af508 EFLAGS: 00010283 [ 699.741573] RAX: 0000000000000000 RBX: ffff8801f43af7b8 RCX: ffffffffb88a7cef [ 699.743006] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8801e3e7a64c [ 699.744426] RBP: ffff8801f43af558 R08: ffffed003e066b55 R09: ffffed003e066b55 [ 699.745833] R10: 0000000000000001 R11: ffffed003e066b54 R12: ffffea0007876940 [ 699.747256] R13: ffff8801f0335500 R14: ffff8801e3e7a600 R15: 0000000000000001 [ 699.748683] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.750293] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.751462] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.752874] Call Trace: [ 699.753386] ? f2fs_inplace_write_data+0x93/0x240 [ 699.754341] f2fs_inplace_write_data+0xd2/0x240 [ 699.755271] f2fs_do_write_data_page+0x2e2/0xe00 [ 699.756214] ? f2fs_should_update_outplace+0xd0/0xd0 [ 699.757215] ? memcg_drain_all_list_lrus+0x280/0x280 [ 699.758209] ? __radix_tree_replace+0xa3/0x120 [ 699.759164] __write_data_page+0x5c7/0xe30 [ 699.760002] ? kasan_check_read+0x11/0x20 [ 699.760823] ? page_mapped+0x8a/0x110 [ 699.761573] ? page_mkclean+0xe9/0x160 [ 699.762345] ? f2fs_do_write_data_page+0xe00/0xe00 [ 699.763332] ? invalid_page_referenced_vma+0x130/0x130 [ 699.764374] ? clear_page_dirty_for_io+0x332/0x450 [ 699.765347] f2fs_write_cache_pages+0x4ca/0x860 [ 699.766276] ? __write_data_page+0xe30/0xe30 [ 699.767161] ? percpu_counter_add_batch+0x22/0xa0 [ 699.768112] ? kasan_check_write+0x14/0x20 [ 699.768951] ? _raw_spin_lock+0x17/0x40 [ 699.769739] ? f2fs_mark_inode_dirty_sync.part.18+0x16/0x30 [ 699.770885] ? iov_iter_advance+0x113/0x640 [ 699.771743] ? f2fs_write_end+0x133/0x2e0 [ 699.772569] ? balance_dirty_pages_ratelimited+0x239/0x640 [ 699.773680] f2fs_write_data_pages+0x329/0x520 [ 699.774603] ? generic_perform_write+0x250/0x320 [ 699.775544] ? f2fs_write_cache_pages+0x860/0x860 [ 699.776510] ? current_time+0x110/0x110 [ 699.777299] ? f2fs_preallocate_blocks+0x1ef/0x370 [ 699.778279] do_writepages+0x37/0xb0 [ 699.779026] ? f2fs_write_cache_pages+0x860/0x860 [ 699.779978] ? do_writepages+0x37/0xb0 [ 699.780755] __filemap_fdatawrite_range+0x19a/0x1f0 [ 699.781746] ? delete_from_page_cache_batch+0x4e0/0x4e0 [ 699.782820] ? __vfs_write+0x2b2/0x410 [ 699.783597] file_write_and_wait_range+0x66/0xb0 [ 699.784540] f2fs_do_sync_file+0x1f9/0xd90 [ 699.785381] ? truncate_partial_data_page+0x290/0x290 [ 699.786415] ? __sb_end_write+0x30/0x50 [ 699.787204] ? vfs_write+0x20f/0x260 [ 699.787941] f2fs_sync_file+0x9a/0xb0 [ 699.788694] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.789572] vfs_fsync_range+0x68/0x100 [ 699.790360] ? __fget_light+0xc9/0xe0 [ 699.791128] do_fsync+0x3d/0x70 [ 699.791779] __x64_sys_fdatasync+0x24/0x30 [ 699.792614] do_syscall_64+0x78/0x170 [ 699.793371] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 699.794406] RIP: 0033:0x7f9bf930d800 [ 699.795134] Code: 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 83 3d 49 bf 2c 00 00 75 10 b8 4b 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 be 78 01 00 48 89 04 24 [ 699.798960] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.800483] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.801923] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.803373] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.804798] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.806233] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.807667] Modules linked in: snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_pcm snd_timer snd mac_hid i2c_piix4 soundcore ib_iser rdma_cm iw_cm ib_cm ib_core iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx raid1 raid0 multipath linear 8139too crct10dif_pclmul crc32_pclmul qxl drm_kms_helper syscopyarea aesni_intel sysfillrect sysimgblt fb_sys_fops ttm drm aes_x86_64 crypto_simd cryptd 8139cp glue_helper mii pata_acpi floppy [ 699.817079] ---[ end trace 4ce02f25ff7d3df6 ]--- [ 699.818068] RIP: 0010:f2fs_submit_page_bio+0x29b/0x730 [ 699.819114] Code: 54 49 8d bd 18 04 00 00 e8 b2 59 af ff 41 8b 8d 18 04 00 00 8b 45 b8 41 d3 e6 44 01 f0 4c 8d 73 14 41 39 c7 0f 82 37 fe ff ff <0f> 0b 65 8b 05 2c 04 77 47 89 c0 48 0f a3 05 52 c1 d5 01 0f 92 c0 [ 699.822919] RSP: 0018:ffff8801f43af508 EFLAGS: 00010283 [ 699.823977] RAX: 0000000000000000 RBX: ffff8801f43af7b8 RCX: ffffffffb88a7cef [ 699.825436] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8801e3e7a64c [ 699.826881] RBP: ffff8801f43af558 R08: ffffed003e066b55 R09: ffffed003e066b55 [ 699.828292] R10: 0000000000000001 R11: ffffed003e066b54 R12: ffffea0007876940 [ 699.829750] R13: ffff8801f0335500 R14: ffff8801e3e7a600 R15: 0000000000000001 [ 699.831192] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.832793] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.833981] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.835556] ================================================================== [ 699.837029] BUG: KASAN: stack-out-of-bounds in update_stack_state+0x38c/0x3e0 [ 699.838462] Read of size 8 at addr ffff8801f43af970 by task a.out/1309 [ 699.840086] CPU: 0 PID: 1309 Comm: a.out Tainted: G D W 4.18.0-rc1+ #4 [ 699.841603] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.843475] Call Trace: [ 699.843982] dump_stack+0x7b/0xb5 [ 699.844661] print_address_description+0x70/0x290 [ 699.845607] kasan_report+0x291/0x390 [ 699.846351] ? update_stack_state+0x38c/0x3e0 [ 699.853831] __asan_load8+0x54/0x90 [ 699.854569] update_stack_state+0x38c/0x3e0 [ 699.855428] ? __read_once_size_nocheck.constprop.7+0x20/0x20 [ 699.856601] ? __save_stack_trace+0x5e/0x100 [ 699.857476] unwind_next_frame.part.5+0x18e/0x490 [ 699.858448] ? unwind_dump+0x290/0x290 [ 699.859217] ? clear_page_dirty_for_io+0x332/0x450 [ 699.860185] __unwind_start+0x106/0x190 [ 699.860974] __save_stack_trace+0x5e/0x100 [ 699.861808] ? __save_stack_trace+0x5e/0x100 [ 699.862691] ? unlink_anon_vmas+0xba/0x2c0 [ 699.863525] save_stack_trace+0x1f/0x30 [ 699.864312] save_stack+0x46/0xd0 [ 699.864993] ? __alloc_pages_slowpath+0x1420/0x1420 [ 699.865990] ? flush_tlb_mm_range+0x15e/0x220 [ 699.866889] ? kasan_check_write+0x14/0x20 [ 699.867724] ? __dec_node_state+0x92/0xb0 [ 699.868543] ? lock_page_memcg+0x85/0xf0 [ 699.869350] ? unlock_page_memcg+0x16/0x80 [ 699.870185] ? page_remove_rmap+0x198/0x520 [ 699.871048] ? mark_page_accessed+0x133/0x200 [ 699.871930] ? _cond_resched+0x1a/0x50 [ 699.872700] ? unmap_page_range+0xcd4/0xe50 [ 699.873551] ? rb_next+0x58/0x80 [ 699.874217] ? rb_next+0x58/0x80 [ 699.874895] __kasan_slab_free+0x13c/0x1a0 [ 699.875734] ? unlink_anon_vmas+0xba/0x2c0 [ 699.876563] kasan_slab_free+0xe/0x10 [ 699.877315] kmem_cache_free+0x89/0x1e0 [ 699.878095] unlink_anon_vmas+0xba/0x2c0 [ 699.878913] free_pgtables+0x101/0x1b0 [ 699.879677] exit_mmap+0x146/0x2a0 [ 699.880378] ? __ia32_sys_munmap+0x50/0x50 [ 699.881214] ? kasan_check_read+0x11/0x20 [ 699.882052] ? mm_update_next_owner+0x322/0x380 [ 699.882985] mmput+0x8b/0x1d0 [ 699.883602] do_exit+0x43a/0x1390 [ 699.884288] ? mm_update_next_owner+0x380/0x380 [ 699.885212] ? f2fs_sync_file+0x9a/0xb0 [ 699.885995] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.886877] ? vfs_fsync_range+0x68/0x100 [ 699.887694] ? __fget_light+0xc9/0xe0 [ 699.888442] ? do_fsync+0x3d/0x70 [ 699.889118] ? __x64_sys_fdatasync+0x24/0x30 [ 699.889996] rewind_stack_do_exit+0x17/0x20 [ 699.890860] RIP: 0033:0x7f9bf930d800 [ 699.891585] Code: Bad RIP value. [ 699.892268] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.893781] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.895220] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.896643] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.898069] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.899505] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.901241] The buggy address belongs to the page: [ 699.902215] page:ffffea0007d0ebc0 count:0 mapcount:0 mapping:0000000000000000 index:0x0 [ 699.903811] flags: 0x2ffff0000000000() [ 699.904585] raw: 02ffff0000000000 0000000000000000 ffffffff07d00101 0000000000000000 [ 699.906125] raw: 0000000000000000 0000000000240000 00000000ffffffff 0000000000000000 [ 699.907673] page dumped because: kasan: bad access detected [ 699.909108] Memory state around the buggy address: [ 699.910077] ffff8801f43af800: 00 f1 f1 f1 f1 00 f4 f4 f4 f3 f3 f3 f3 00 00 00 [ 699.911528] ffff8801f43af880: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 699.912953] >ffff8801f43af900: 00 00 00 00 00 00 00 00 f1 01 f4 f4 f4 f2 f2 f2 [ 699.914392] ^ [ 699.915758] ffff8801f43af980: f2 00 f4 f4 00 00 00 00 f2 00 00 00 00 00 00 00 [ 699.917193] ffff8801f43afa00: 00 00 00 00 00 00 00 00 00 f3 f3 f3 00 00 00 00 [ 699.918634] ================================================================== - Location https://elixir.bootlin.com/linux/v4.18-rc1/source/fs/f2fs/segment.h#L644 Reported-by Wen Xu <wen.xu@gatech.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-08-01 14:13:44 +03:00
if (__is_valid_data_blkaddr(blkaddr) &&
f2fs: introduce DATA_GENERIC_ENHANCE Previously, f2fs_is_valid_blkaddr(, blkaddr, DATA_GENERIC) will check whether @blkaddr locates in main area or not. That check is weak, since the block address in range of main area can point to the address which is not valid in segment info table, and we can not detect such condition, we may suffer worse corruption as system continues running. So this patch introduce DATA_GENERIC_ENHANCE to enhance the sanity check which trigger SIT bitmap check rather than only range check. This patch did below changes as wel: - set SBI_NEED_FSCK in f2fs_is_valid_blkaddr(). - get rid of is_valid_data_blkaddr() to avoid panic if blkaddr is invalid. - introduce verify_fio_blkaddr() to wrap fio {new,old}_blkaddr validation check. - spread blkaddr check in: * f2fs_get_node_info() * __read_out_blkaddrs() * f2fs_submit_page_read() * ra_data_block() * do_recover_data() This patch can fix bug reported from bugzilla below: https://bugzilla.kernel.org/show_bug.cgi?id=203215 https://bugzilla.kernel.org/show_bug.cgi?id=203223 https://bugzilla.kernel.org/show_bug.cgi?id=203231 https://bugzilla.kernel.org/show_bug.cgi?id=203235 https://bugzilla.kernel.org/show_bug.cgi?id=203241 = Update by Jaegeuk Kim = DATA_GENERIC_ENHANCE enhanced to validate block addresses on read/write paths. But, xfstest/generic/446 compalins some generated kernel messages saying invalid bitmap was detected when reading a block. The reaons is, when we get the block addresses from extent_cache, there is no lock to synchronize it from truncating the blocks in parallel. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-15 10:26:32 +03:00
!f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC_ENHANCE)) {
err = -EFSCORRUPTED;
f2fs: fix to do sanity check with block address in main area This patch add to do sanity check with below field: - cp_pack_total_block_count - blkaddr of data/node - extent info - Overview BUG() in verify_block_addr() when writing to a corrupted f2fs image - Reproduce (4.18 upstream kernel) - POC (poc.c) static void activity(char *mpoint) { char *foo_bar_baz; int err; static int buf[8192]; memset(buf, 0, sizeof(buf)); err = asprintf(&foo_bar_baz, "%s/foo/bar/baz", mpoint); int fd = open(foo_bar_baz, O_RDWR | O_TRUNC, 0777); if (fd >= 0) { write(fd, (char *)buf, sizeof(buf)); fdatasync(fd); close(fd); } } int main(int argc, char *argv[]) { activity(argv[1]); return 0; } - Kernel message [ 689.349473] F2FS-fs (loop0): Mounted with checkpoint version = 3 [ 699.728662] WARNING: CPU: 0 PID: 1309 at fs/f2fs/segment.c:2860 f2fs_inplace_write_data+0x232/0x240 [ 699.728670] Modules linked in: snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_pcm snd_timer snd mac_hid i2c_piix4 soundcore ib_iser rdma_cm iw_cm ib_cm ib_core iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx raid1 raid0 multipath linear 8139too crct10dif_pclmul crc32_pclmul qxl drm_kms_helper syscopyarea aesni_intel sysfillrect sysimgblt fb_sys_fops ttm drm aes_x86_64 crypto_simd cryptd 8139cp glue_helper mii pata_acpi floppy [ 699.729056] CPU: 0 PID: 1309 Comm: a.out Not tainted 4.18.0-rc1+ #4 [ 699.729064] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.729074] RIP: 0010:f2fs_inplace_write_data+0x232/0x240 [ 699.729076] Code: ff e9 cf fe ff ff 49 8d 7d 10 e8 39 45 ad ff 4d 8b 7d 10 be 04 00 00 00 49 8d 7f 48 e8 07 49 ad ff 45 8b 7f 48 e9 fb fe ff ff <0f> 0b f0 41 80 4d 48 04 e9 65 fe ff ff 90 66 66 66 66 90 55 48 8d [ 699.729130] RSP: 0018:ffff8801f43af568 EFLAGS: 00010202 [ 699.729139] RAX: 000000000000003f RBX: ffff8801f43af7b8 RCX: ffffffffb88c9113 [ 699.729142] RDX: 0000000000000003 RSI: dffffc0000000000 RDI: ffff8802024e5540 [ 699.729144] RBP: ffff8801f43af590 R08: 0000000000000009 R09: ffffffffffffffe8 [ 699.729147] R10: 0000000000000001 R11: ffffed0039b0596a R12: ffff8802024e5540 [ 699.729149] R13: ffff8801f0335500 R14: ffff8801e3e7a700 R15: ffff8801e1ee4450 [ 699.729154] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.729156] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.729159] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.729171] Call Trace: [ 699.729192] f2fs_do_write_data_page+0x2e2/0xe00 [ 699.729203] ? f2fs_should_update_outplace+0xd0/0xd0 [ 699.729238] ? memcg_drain_all_list_lrus+0x280/0x280 [ 699.729269] ? __radix_tree_replace+0xa3/0x120 [ 699.729276] __write_data_page+0x5c7/0xe30 [ 699.729291] ? kasan_check_read+0x11/0x20 [ 699.729310] ? page_mapped+0x8a/0x110 [ 699.729321] ? page_mkclean+0xe9/0x160 [ 699.729327] ? f2fs_do_write_data_page+0xe00/0xe00 [ 699.729331] ? invalid_page_referenced_vma+0x130/0x130 [ 699.729345] ? clear_page_dirty_for_io+0x332/0x450 [ 699.729351] f2fs_write_cache_pages+0x4ca/0x860 [ 699.729358] ? __write_data_page+0xe30/0xe30 [ 699.729374] ? percpu_counter_add_batch+0x22/0xa0 [ 699.729380] ? kasan_check_write+0x14/0x20 [ 699.729391] ? _raw_spin_lock+0x17/0x40 [ 699.729403] ? f2fs_mark_inode_dirty_sync.part.18+0x16/0x30 [ 699.729413] ? iov_iter_advance+0x113/0x640 [ 699.729418] ? f2fs_write_end+0x133/0x2e0 [ 699.729423] ? balance_dirty_pages_ratelimited+0x239/0x640 [ 699.729428] f2fs_write_data_pages+0x329/0x520 [ 699.729433] ? generic_perform_write+0x250/0x320 [ 699.729438] ? f2fs_write_cache_pages+0x860/0x860 [ 699.729454] ? current_time+0x110/0x110 [ 699.729459] ? f2fs_preallocate_blocks+0x1ef/0x370 [ 699.729464] do_writepages+0x37/0xb0 [ 699.729468] ? f2fs_write_cache_pages+0x860/0x860 [ 699.729472] ? do_writepages+0x37/0xb0 [ 699.729478] __filemap_fdatawrite_range+0x19a/0x1f0 [ 699.729483] ? delete_from_page_cache_batch+0x4e0/0x4e0 [ 699.729496] ? __vfs_write+0x2b2/0x410 [ 699.729501] file_write_and_wait_range+0x66/0xb0 [ 699.729506] f2fs_do_sync_file+0x1f9/0xd90 [ 699.729511] ? truncate_partial_data_page+0x290/0x290 [ 699.729521] ? __sb_end_write+0x30/0x50 [ 699.729526] ? vfs_write+0x20f/0x260 [ 699.729530] f2fs_sync_file+0x9a/0xb0 [ 699.729534] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.729548] vfs_fsync_range+0x68/0x100 [ 699.729554] ? __fget_light+0xc9/0xe0 [ 699.729558] do_fsync+0x3d/0x70 [ 699.729562] __x64_sys_fdatasync+0x24/0x30 [ 699.729585] do_syscall_64+0x78/0x170 [ 699.729595] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 699.729613] RIP: 0033:0x7f9bf930d800 [ 699.729615] Code: 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 83 3d 49 bf 2c 00 00 75 10 b8 4b 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 be 78 01 00 48 89 04 24 [ 699.729668] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.729673] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.729675] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.729678] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.729680] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.729683] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.729687] ---[ end trace 4ce02f25ff7d3df5 ]--- [ 699.729782] ------------[ cut here ]------------ [ 699.729785] kernel BUG at fs/f2fs/segment.h:654! [ 699.731055] invalid opcode: 0000 [#1] SMP KASAN PTI [ 699.732104] CPU: 0 PID: 1309 Comm: a.out Tainted: G W 4.18.0-rc1+ #4 [ 699.733684] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.735611] RIP: 0010:f2fs_submit_page_bio+0x29b/0x730 [ 699.736649] Code: 54 49 8d bd 18 04 00 00 e8 b2 59 af ff 41 8b 8d 18 04 00 00 8b 45 b8 41 d3 e6 44 01 f0 4c 8d 73 14 41 39 c7 0f 82 37 fe ff ff <0f> 0b 65 8b 05 2c 04 77 47 89 c0 48 0f a3 05 52 c1 d5 01 0f 92 c0 [ 699.740524] RSP: 0018:ffff8801f43af508 EFLAGS: 00010283 [ 699.741573] RAX: 0000000000000000 RBX: ffff8801f43af7b8 RCX: ffffffffb88a7cef [ 699.743006] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8801e3e7a64c [ 699.744426] RBP: ffff8801f43af558 R08: ffffed003e066b55 R09: ffffed003e066b55 [ 699.745833] R10: 0000000000000001 R11: ffffed003e066b54 R12: ffffea0007876940 [ 699.747256] R13: ffff8801f0335500 R14: ffff8801e3e7a600 R15: 0000000000000001 [ 699.748683] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.750293] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.751462] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.752874] Call Trace: [ 699.753386] ? f2fs_inplace_write_data+0x93/0x240 [ 699.754341] f2fs_inplace_write_data+0xd2/0x240 [ 699.755271] f2fs_do_write_data_page+0x2e2/0xe00 [ 699.756214] ? f2fs_should_update_outplace+0xd0/0xd0 [ 699.757215] ? memcg_drain_all_list_lrus+0x280/0x280 [ 699.758209] ? __radix_tree_replace+0xa3/0x120 [ 699.759164] __write_data_page+0x5c7/0xe30 [ 699.760002] ? kasan_check_read+0x11/0x20 [ 699.760823] ? page_mapped+0x8a/0x110 [ 699.761573] ? page_mkclean+0xe9/0x160 [ 699.762345] ? f2fs_do_write_data_page+0xe00/0xe00 [ 699.763332] ? invalid_page_referenced_vma+0x130/0x130 [ 699.764374] ? clear_page_dirty_for_io+0x332/0x450 [ 699.765347] f2fs_write_cache_pages+0x4ca/0x860 [ 699.766276] ? __write_data_page+0xe30/0xe30 [ 699.767161] ? percpu_counter_add_batch+0x22/0xa0 [ 699.768112] ? kasan_check_write+0x14/0x20 [ 699.768951] ? _raw_spin_lock+0x17/0x40 [ 699.769739] ? f2fs_mark_inode_dirty_sync.part.18+0x16/0x30 [ 699.770885] ? iov_iter_advance+0x113/0x640 [ 699.771743] ? f2fs_write_end+0x133/0x2e0 [ 699.772569] ? balance_dirty_pages_ratelimited+0x239/0x640 [ 699.773680] f2fs_write_data_pages+0x329/0x520 [ 699.774603] ? generic_perform_write+0x250/0x320 [ 699.775544] ? f2fs_write_cache_pages+0x860/0x860 [ 699.776510] ? current_time+0x110/0x110 [ 699.777299] ? f2fs_preallocate_blocks+0x1ef/0x370 [ 699.778279] do_writepages+0x37/0xb0 [ 699.779026] ? f2fs_write_cache_pages+0x860/0x860 [ 699.779978] ? do_writepages+0x37/0xb0 [ 699.780755] __filemap_fdatawrite_range+0x19a/0x1f0 [ 699.781746] ? delete_from_page_cache_batch+0x4e0/0x4e0 [ 699.782820] ? __vfs_write+0x2b2/0x410 [ 699.783597] file_write_and_wait_range+0x66/0xb0 [ 699.784540] f2fs_do_sync_file+0x1f9/0xd90 [ 699.785381] ? truncate_partial_data_page+0x290/0x290 [ 699.786415] ? __sb_end_write+0x30/0x50 [ 699.787204] ? vfs_write+0x20f/0x260 [ 699.787941] f2fs_sync_file+0x9a/0xb0 [ 699.788694] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.789572] vfs_fsync_range+0x68/0x100 [ 699.790360] ? __fget_light+0xc9/0xe0 [ 699.791128] do_fsync+0x3d/0x70 [ 699.791779] __x64_sys_fdatasync+0x24/0x30 [ 699.792614] do_syscall_64+0x78/0x170 [ 699.793371] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 699.794406] RIP: 0033:0x7f9bf930d800 [ 699.795134] Code: 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 83 3d 49 bf 2c 00 00 75 10 b8 4b 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 be 78 01 00 48 89 04 24 [ 699.798960] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.800483] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.801923] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.803373] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.804798] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.806233] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.807667] Modules linked in: snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_pcm snd_timer snd mac_hid i2c_piix4 soundcore ib_iser rdma_cm iw_cm ib_cm ib_core iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx raid1 raid0 multipath linear 8139too crct10dif_pclmul crc32_pclmul qxl drm_kms_helper syscopyarea aesni_intel sysfillrect sysimgblt fb_sys_fops ttm drm aes_x86_64 crypto_simd cryptd 8139cp glue_helper mii pata_acpi floppy [ 699.817079] ---[ end trace 4ce02f25ff7d3df6 ]--- [ 699.818068] RIP: 0010:f2fs_submit_page_bio+0x29b/0x730 [ 699.819114] Code: 54 49 8d bd 18 04 00 00 e8 b2 59 af ff 41 8b 8d 18 04 00 00 8b 45 b8 41 d3 e6 44 01 f0 4c 8d 73 14 41 39 c7 0f 82 37 fe ff ff <0f> 0b 65 8b 05 2c 04 77 47 89 c0 48 0f a3 05 52 c1 d5 01 0f 92 c0 [ 699.822919] RSP: 0018:ffff8801f43af508 EFLAGS: 00010283 [ 699.823977] RAX: 0000000000000000 RBX: ffff8801f43af7b8 RCX: ffffffffb88a7cef [ 699.825436] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8801e3e7a64c [ 699.826881] RBP: ffff8801f43af558 R08: ffffed003e066b55 R09: ffffed003e066b55 [ 699.828292] R10: 0000000000000001 R11: ffffed003e066b54 R12: ffffea0007876940 [ 699.829750] R13: ffff8801f0335500 R14: ffff8801e3e7a600 R15: 0000000000000001 [ 699.831192] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.832793] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.833981] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.835556] ================================================================== [ 699.837029] BUG: KASAN: stack-out-of-bounds in update_stack_state+0x38c/0x3e0 [ 699.838462] Read of size 8 at addr ffff8801f43af970 by task a.out/1309 [ 699.840086] CPU: 0 PID: 1309 Comm: a.out Tainted: G D W 4.18.0-rc1+ #4 [ 699.841603] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.843475] Call Trace: [ 699.843982] dump_stack+0x7b/0xb5 [ 699.844661] print_address_description+0x70/0x290 [ 699.845607] kasan_report+0x291/0x390 [ 699.846351] ? update_stack_state+0x38c/0x3e0 [ 699.853831] __asan_load8+0x54/0x90 [ 699.854569] update_stack_state+0x38c/0x3e0 [ 699.855428] ? __read_once_size_nocheck.constprop.7+0x20/0x20 [ 699.856601] ? __save_stack_trace+0x5e/0x100 [ 699.857476] unwind_next_frame.part.5+0x18e/0x490 [ 699.858448] ? unwind_dump+0x290/0x290 [ 699.859217] ? clear_page_dirty_for_io+0x332/0x450 [ 699.860185] __unwind_start+0x106/0x190 [ 699.860974] __save_stack_trace+0x5e/0x100 [ 699.861808] ? __save_stack_trace+0x5e/0x100 [ 699.862691] ? unlink_anon_vmas+0xba/0x2c0 [ 699.863525] save_stack_trace+0x1f/0x30 [ 699.864312] save_stack+0x46/0xd0 [ 699.864993] ? __alloc_pages_slowpath+0x1420/0x1420 [ 699.865990] ? flush_tlb_mm_range+0x15e/0x220 [ 699.866889] ? kasan_check_write+0x14/0x20 [ 699.867724] ? __dec_node_state+0x92/0xb0 [ 699.868543] ? lock_page_memcg+0x85/0xf0 [ 699.869350] ? unlock_page_memcg+0x16/0x80 [ 699.870185] ? page_remove_rmap+0x198/0x520 [ 699.871048] ? mark_page_accessed+0x133/0x200 [ 699.871930] ? _cond_resched+0x1a/0x50 [ 699.872700] ? unmap_page_range+0xcd4/0xe50 [ 699.873551] ? rb_next+0x58/0x80 [ 699.874217] ? rb_next+0x58/0x80 [ 699.874895] __kasan_slab_free+0x13c/0x1a0 [ 699.875734] ? unlink_anon_vmas+0xba/0x2c0 [ 699.876563] kasan_slab_free+0xe/0x10 [ 699.877315] kmem_cache_free+0x89/0x1e0 [ 699.878095] unlink_anon_vmas+0xba/0x2c0 [ 699.878913] free_pgtables+0x101/0x1b0 [ 699.879677] exit_mmap+0x146/0x2a0 [ 699.880378] ? __ia32_sys_munmap+0x50/0x50 [ 699.881214] ? kasan_check_read+0x11/0x20 [ 699.882052] ? mm_update_next_owner+0x322/0x380 [ 699.882985] mmput+0x8b/0x1d0 [ 699.883602] do_exit+0x43a/0x1390 [ 699.884288] ? mm_update_next_owner+0x380/0x380 [ 699.885212] ? f2fs_sync_file+0x9a/0xb0 [ 699.885995] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.886877] ? vfs_fsync_range+0x68/0x100 [ 699.887694] ? __fget_light+0xc9/0xe0 [ 699.888442] ? do_fsync+0x3d/0x70 [ 699.889118] ? __x64_sys_fdatasync+0x24/0x30 [ 699.889996] rewind_stack_do_exit+0x17/0x20 [ 699.890860] RIP: 0033:0x7f9bf930d800 [ 699.891585] Code: Bad RIP value. [ 699.892268] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.893781] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.895220] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.896643] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.898069] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.899505] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.901241] The buggy address belongs to the page: [ 699.902215] page:ffffea0007d0ebc0 count:0 mapcount:0 mapping:0000000000000000 index:0x0 [ 699.903811] flags: 0x2ffff0000000000() [ 699.904585] raw: 02ffff0000000000 0000000000000000 ffffffff07d00101 0000000000000000 [ 699.906125] raw: 0000000000000000 0000000000240000 00000000ffffffff 0000000000000000 [ 699.907673] page dumped because: kasan: bad access detected [ 699.909108] Memory state around the buggy address: [ 699.910077] ffff8801f43af800: 00 f1 f1 f1 f1 00 f4 f4 f4 f3 f3 f3 f3 00 00 00 [ 699.911528] ffff8801f43af880: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 699.912953] >ffff8801f43af900: 00 00 00 00 00 00 00 00 f1 01 f4 f4 f4 f2 f2 f2 [ 699.914392] ^ [ 699.915758] ffff8801f43af980: f2 00 f4 f4 00 00 00 00 f2 00 00 00 00 00 00 00 [ 699.917193] ffff8801f43afa00: 00 00 00 00 00 00 00 00 00 f3 f3 f3 00 00 00 00 [ 699.918634] ================================================================== - Location https://elixir.bootlin.com/linux/v4.18-rc1/source/fs/f2fs/segment.h#L644 Reported-by Wen Xu <wen.xu@gatech.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-08-01 14:13:44 +03:00
goto sync_out;
}
f2fs: introduce DATA_GENERIC_ENHANCE Previously, f2fs_is_valid_blkaddr(, blkaddr, DATA_GENERIC) will check whether @blkaddr locates in main area or not. That check is weak, since the block address in range of main area can point to the address which is not valid in segment info table, and we can not detect such condition, we may suffer worse corruption as system continues running. So this patch introduce DATA_GENERIC_ENHANCE to enhance the sanity check which trigger SIT bitmap check rather than only range check. This patch did below changes as wel: - set SBI_NEED_FSCK in f2fs_is_valid_blkaddr(). - get rid of is_valid_data_blkaddr() to avoid panic if blkaddr is invalid. - introduce verify_fio_blkaddr() to wrap fio {new,old}_blkaddr validation check. - spread blkaddr check in: * f2fs_get_node_info() * __read_out_blkaddrs() * f2fs_submit_page_read() * ra_data_block() * do_recover_data() This patch can fix bug reported from bugzilla below: https://bugzilla.kernel.org/show_bug.cgi?id=203215 https://bugzilla.kernel.org/show_bug.cgi?id=203223 https://bugzilla.kernel.org/show_bug.cgi?id=203231 https://bugzilla.kernel.org/show_bug.cgi?id=203235 https://bugzilla.kernel.org/show_bug.cgi?id=203241 = Update by Jaegeuk Kim = DATA_GENERIC_ENHANCE enhanced to validate block addresses on read/write paths. But, xfstest/generic/446 compalins some generated kernel messages saying invalid bitmap was detected when reading a block. The reaons is, when we get the block addresses from extent_cache, there is no lock to synchronize it from truncating the blocks in parallel. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-15 10:26:32 +03:00
if (__is_valid_data_blkaddr(blkaddr)) {
/* use out-place-update for driect IO under LFS mode */
f2fs: fix out-place-update DIO write In get_more_blocks(), we may override @create as below code: create = dio->op == REQ_OP_WRITE; if (dio->flags & DIO_SKIP_HOLES) { if (fs_startblk <= ((i_size_read(dio->inode) - 1) >> i_blkbits)) create = 0; } But in f2fs_map_blocks(), we only trigger f2fs_balance_fs() if @create is 1, so in LFS mode, dio overwrite under LFS mode can easily run out of free segments, result in below panic. Call Trace: allocate_segment_by_default+0xa8/0x270 [f2fs] f2fs_allocate_data_block+0x1ea/0x5c0 [f2fs] __allocate_data_block+0x306/0x480 [f2fs] f2fs_map_blocks+0x6f6/0x920 [f2fs] __get_data_block+0x4f/0xb0 [f2fs] get_data_block_dio_write+0x50/0x60 [f2fs] do_blockdev_direct_IO+0xcd5/0x21e0 __blockdev_direct_IO+0x3a/0x3c f2fs_direct_IO+0x1ff/0x4a0 [f2fs] generic_file_direct_write+0xd9/0x160 __generic_file_write_iter+0xbb/0x1e0 f2fs_file_write_iter+0xaf/0x220 [f2fs] __vfs_write+0xd0/0x130 vfs_write+0xb2/0x1b0 SyS_pwrite64+0x69/0xa0 ? vtime_user_exit+0x29/0x70 do_syscall_64+0x6e/0x160 entry_SYSCALL64_slow_path+0x25/0x25 RIP: new_curseg+0x36f/0x380 [f2fs] RSP: ffffac570393f7a8 So this patch introduces a parameter map.m_may_create to indicate that f2fs_map_blocks() is called from write or read path, which can give the right hint to let f2fs_map_blocks() trigger OPU allocation and call f2fs_balanc_fs() correctly. BTW, it disables physical address preallocation for direct IO in f2fs_preallocate_blocks, which is redundant to OPU allocation of f2fs_map_blocks. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-11-13 09:33:45 +03:00
if (test_opt(sbi, LFS) && flag == F2FS_GET_BLOCK_DIO &&
map->m_may_create) {
err = __allocate_data_block(&dn, map->m_seg_type);
if (err)
goto sync_out;
blkaddr = dn.data_blkaddr;
set_inode_flag(inode, FI_APPEND_WRITE);
}
} else {
if (create) {
f2fs: fix to handle io error in ->direct_IO Here is a oops reported as following message when testing generic/019 of xfstest: ------------[ cut here ]------------ kernel BUG at /home/yuchao/git/f2fs-dev/segment.c:882! invalid opcode: 0000 [#1] SMP Modules linked in: zram lz4_compress lz4_decompress f2fs(O) ip6table_filter ip6_tables ebtable_nat ebtables nf_conntrack_ipv4 nf_def CPU: 2 PID: 25441 Comm: fio Tainted: G O 4.3.0-rc1+ #6 Hardware name: Hewlett-Packard HP Z220 CMT Workstation/1790, BIOS K51 v01.61 05/16/2013 task: ffff8803f4e85580 ti: ffff8803fd61c000 task.ti: ffff8803fd61c000 RIP: 0010:[<ffffffffa0784981>] [<ffffffffa0784981>] new_curseg+0x321/0x330 [f2fs] RSP: 0018:ffff8803fd61f918 EFLAGS: 00010246 RAX: 00000000000007ed RBX: 0000000000000224 RCX: 000000000000001f RDX: 0000000000000800 RSI: ffffffffffffffff RDI: ffff8803f56f4300 RBP: ffff8803fd61f978 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000024 R11: ffff8800d23bbd78 R12: ffff8800d0ef0000 R13: 0000000000000224 R14: 0000000000000000 R15: 0000000000000001 FS: 00007f827ff85700(0000) GS:ffff88041ea80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffffffff600000 CR3: 00000003fef17000 CR4: 00000000001406e0 Stack: 000007ea00000002 0000000100000001 ffff8803f6456248 000007ed0000002b 0000000000000224 ffff880404d1aa20 ffff8803fd61f9c8 ffff8800d0ef0000 ffff8803f6456248 0000000000000001 00000000ffffffff ffffffffa078f358 Call Trace: [<ffffffffa0785b87>] allocate_segment_by_default+0x1a7/0x1f0 [f2fs] [<ffffffffa078322c>] allocate_data_block+0x17c/0x360 [f2fs] [<ffffffffa0779521>] __allocate_data_block+0x131/0x1d0 [f2fs] [<ffffffffa077a995>] f2fs_direct_IO+0x4b5/0x580 [f2fs] [<ffffffff811510ae>] generic_file_direct_write+0xae/0x160 [<ffffffff811518f5>] __generic_file_write_iter+0xd5/0x1f0 [<ffffffff81151e07>] generic_file_write_iter+0xf7/0x200 [<ffffffff81319e38>] ? apparmor_file_permission+0x18/0x20 [<ffffffffa0768480>] ? f2fs_fallocate+0x1190/0x1190 [f2fs] [<ffffffffa07684c6>] f2fs_file_write_iter+0x46/0x90 [f2fs] [<ffffffff8120b4fe>] aio_run_iocb+0x1ee/0x290 [<ffffffff81700f7e>] ? mutex_lock+0x1e/0x50 [<ffffffff8120a1d7>] ? aio_read_events+0x207/0x2b0 [<ffffffff8120b913>] do_io_submit+0x373/0x630 [<ffffffff8120a4f6>] ? SyS_io_getevents+0x56/0xb0 [<ffffffff8120bbe0>] SyS_io_submit+0x10/0x20 [<ffffffff81703857>] entry_SYSCALL_64_fastpath+0x12/0x6a Code: 45 c8 48 8b 78 10 e8 9f 23 bf e0 41 8b 8c 24 cc 03 00 00 89 c7 31 d2 89 c6 89 d8 29 df f7 f1 29 d1 39 cf 0f 83 be fd ff ff eb RIP [<ffffffffa0784981>] new_curseg+0x321/0x330 [f2fs] RSP <ffff8803fd61f918> ---[ end trace 2e577d7f711ddb86 ]--- The reason is that: in the test of generic/019, we will trigger a manmade IO error in block layer through debugfs, after that, prefree segment will no longer be freed, because we always skip doing gc or checkpoint when there occurs an IO error. Meanwhile fio with aio engine generated a large number of direct IOs, which continue allocating spaces in free segment until we run out of them, eventually, results in panic in new_curseg as no more free segment was found. So, this patch changes to return EIO in direct_IO for this condition. Signed-off-by: Chao Yu <chao2.yu@samsung.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2015-09-21 15:17:52 +03:00
if (unlikely(f2fs_cp_error(sbi))) {
err = -EIO;
goto sync_out;
f2fs: fix to handle io error in ->direct_IO Here is a oops reported as following message when testing generic/019 of xfstest: ------------[ cut here ]------------ kernel BUG at /home/yuchao/git/f2fs-dev/segment.c:882! invalid opcode: 0000 [#1] SMP Modules linked in: zram lz4_compress lz4_decompress f2fs(O) ip6table_filter ip6_tables ebtable_nat ebtables nf_conntrack_ipv4 nf_def CPU: 2 PID: 25441 Comm: fio Tainted: G O 4.3.0-rc1+ #6 Hardware name: Hewlett-Packard HP Z220 CMT Workstation/1790, BIOS K51 v01.61 05/16/2013 task: ffff8803f4e85580 ti: ffff8803fd61c000 task.ti: ffff8803fd61c000 RIP: 0010:[<ffffffffa0784981>] [<ffffffffa0784981>] new_curseg+0x321/0x330 [f2fs] RSP: 0018:ffff8803fd61f918 EFLAGS: 00010246 RAX: 00000000000007ed RBX: 0000000000000224 RCX: 000000000000001f RDX: 0000000000000800 RSI: ffffffffffffffff RDI: ffff8803f56f4300 RBP: ffff8803fd61f978 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000024 R11: ffff8800d23bbd78 R12: ffff8800d0ef0000 R13: 0000000000000224 R14: 0000000000000000 R15: 0000000000000001 FS: 00007f827ff85700(0000) GS:ffff88041ea80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffffffff600000 CR3: 00000003fef17000 CR4: 00000000001406e0 Stack: 000007ea00000002 0000000100000001 ffff8803f6456248 000007ed0000002b 0000000000000224 ffff880404d1aa20 ffff8803fd61f9c8 ffff8800d0ef0000 ffff8803f6456248 0000000000000001 00000000ffffffff ffffffffa078f358 Call Trace: [<ffffffffa0785b87>] allocate_segment_by_default+0x1a7/0x1f0 [f2fs] [<ffffffffa078322c>] allocate_data_block+0x17c/0x360 [f2fs] [<ffffffffa0779521>] __allocate_data_block+0x131/0x1d0 [f2fs] [<ffffffffa077a995>] f2fs_direct_IO+0x4b5/0x580 [f2fs] [<ffffffff811510ae>] generic_file_direct_write+0xae/0x160 [<ffffffff811518f5>] __generic_file_write_iter+0xd5/0x1f0 [<ffffffff81151e07>] generic_file_write_iter+0xf7/0x200 [<ffffffff81319e38>] ? apparmor_file_permission+0x18/0x20 [<ffffffffa0768480>] ? f2fs_fallocate+0x1190/0x1190 [f2fs] [<ffffffffa07684c6>] f2fs_file_write_iter+0x46/0x90 [f2fs] [<ffffffff8120b4fe>] aio_run_iocb+0x1ee/0x290 [<ffffffff81700f7e>] ? mutex_lock+0x1e/0x50 [<ffffffff8120a1d7>] ? aio_read_events+0x207/0x2b0 [<ffffffff8120b913>] do_io_submit+0x373/0x630 [<ffffffff8120a4f6>] ? SyS_io_getevents+0x56/0xb0 [<ffffffff8120bbe0>] SyS_io_submit+0x10/0x20 [<ffffffff81703857>] entry_SYSCALL_64_fastpath+0x12/0x6a Code: 45 c8 48 8b 78 10 e8 9f 23 bf e0 41 8b 8c 24 cc 03 00 00 89 c7 31 d2 89 c6 89 d8 29 df f7 f1 29 d1 39 cf 0f 83 be fd ff ff eb RIP [<ffffffffa0784981>] new_curseg+0x321/0x330 [f2fs] RSP <ffff8803fd61f918> ---[ end trace 2e577d7f711ddb86 ]--- The reason is that: in the test of generic/019, we will trigger a manmade IO error in block layer through debugfs, after that, prefree segment will no longer be freed, because we always skip doing gc or checkpoint when there occurs an IO error. Meanwhile fio with aio engine generated a large number of direct IOs, which continue allocating spaces in free segment until we run out of them, eventually, results in panic in new_curseg as no more free segment was found. So, this patch changes to return EIO in direct_IO for this condition. Signed-off-by: Chao Yu <chao2.yu@samsung.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2015-09-21 15:17:52 +03:00
}
if (flag == F2FS_GET_BLOCK_PRE_AIO) {
if (blkaddr == NULL_ADDR) {
prealloc++;
last_ofs_in_node = dn.ofs_in_node;
}
} else {
WARN_ON(flag != F2FS_GET_BLOCK_PRE_DIO &&
flag != F2FS_GET_BLOCK_DIO);
err = __allocate_data_block(&dn,
map->m_seg_type);
if (!err)
set_inode_flag(inode, FI_APPEND_WRITE);
}
if (err)
goto sync_out;
map->m_flags |= F2FS_MAP_NEW;
blkaddr = dn.data_blkaddr;
} else {
if (flag == F2FS_GET_BLOCK_BMAP) {
map->m_pblk = 0;
goto sync_out;
}
if (flag == F2FS_GET_BLOCK_PRECACHE)
goto sync_out;
if (flag == F2FS_GET_BLOCK_FIEMAP &&
blkaddr == NULL_ADDR) {
if (map->m_next_pgofs)
*map->m_next_pgofs = pgofs + 1;
goto sync_out;
}
if (flag != F2FS_GET_BLOCK_FIEMAP) {
/* for defragment case */
if (map->m_next_pgofs)
*map->m_next_pgofs = pgofs + 1;
goto sync_out;
}
}
}
if (flag == F2FS_GET_BLOCK_PRE_AIO)
goto skip;
if (map->m_len == 0) {
/* preallocated unwritten block should be mapped for fiemap. */
if (blkaddr == NEW_ADDR)
map->m_flags |= F2FS_MAP_UNWRITTEN;
map->m_flags |= F2FS_MAP_MAPPED;
map->m_pblk = blkaddr;
map->m_len = 1;
} else if ((map->m_pblk != NEW_ADDR &&
blkaddr == (map->m_pblk + ofs)) ||
(map->m_pblk == NEW_ADDR && blkaddr == NEW_ADDR) ||
flag == F2FS_GET_BLOCK_PRE_DIO) {
ofs++;
map->m_len++;
} else {
goto sync_out;
}
skip:
dn.ofs_in_node++;
pgofs++;
/* preallocate blocks in batch for one dnode page */
if (flag == F2FS_GET_BLOCK_PRE_AIO &&
(pgofs == end || dn.ofs_in_node == end_offset)) {
dn.ofs_in_node = ofs_in_node;
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 19:20:41 +03:00
err = f2fs_reserve_new_blocks(&dn, prealloc);
if (err)
goto sync_out;
map->m_len += dn.ofs_in_node - ofs_in_node;
if (prealloc && dn.ofs_in_node != last_ofs_in_node + 1) {
err = -ENOSPC;
goto sync_out;
}
dn.ofs_in_node = end_offset;
}
if (pgofs >= end)
goto sync_out;
else if (dn.ofs_in_node < end_offset)
goto next_block;
if (flag == F2FS_GET_BLOCK_PRECACHE) {
if (map->m_flags & F2FS_MAP_MAPPED) {
unsigned int ofs = start_pgofs - map->m_lblk;
f2fs_update_extent_cache_range(&dn,
start_pgofs, map->m_pblk + ofs,
map->m_len - ofs);
}
}
f2fs_put_dnode(&dn);
f2fs: fix out-place-update DIO write In get_more_blocks(), we may override @create as below code: create = dio->op == REQ_OP_WRITE; if (dio->flags & DIO_SKIP_HOLES) { if (fs_startblk <= ((i_size_read(dio->inode) - 1) >> i_blkbits)) create = 0; } But in f2fs_map_blocks(), we only trigger f2fs_balance_fs() if @create is 1, so in LFS mode, dio overwrite under LFS mode can easily run out of free segments, result in below panic. Call Trace: allocate_segment_by_default+0xa8/0x270 [f2fs] f2fs_allocate_data_block+0x1ea/0x5c0 [f2fs] __allocate_data_block+0x306/0x480 [f2fs] f2fs_map_blocks+0x6f6/0x920 [f2fs] __get_data_block+0x4f/0xb0 [f2fs] get_data_block_dio_write+0x50/0x60 [f2fs] do_blockdev_direct_IO+0xcd5/0x21e0 __blockdev_direct_IO+0x3a/0x3c f2fs_direct_IO+0x1ff/0x4a0 [f2fs] generic_file_direct_write+0xd9/0x160 __generic_file_write_iter+0xbb/0x1e0 f2fs_file_write_iter+0xaf/0x220 [f2fs] __vfs_write+0xd0/0x130 vfs_write+0xb2/0x1b0 SyS_pwrite64+0x69/0xa0 ? vtime_user_exit+0x29/0x70 do_syscall_64+0x6e/0x160 entry_SYSCALL64_slow_path+0x25/0x25 RIP: new_curseg+0x36f/0x380 [f2fs] RSP: ffffac570393f7a8 So this patch introduces a parameter map.m_may_create to indicate that f2fs_map_blocks() is called from write or read path, which can give the right hint to let f2fs_map_blocks() trigger OPU allocation and call f2fs_balanc_fs() correctly. BTW, it disables physical address preallocation for direct IO in f2fs_preallocate_blocks, which is redundant to OPU allocation of f2fs_map_blocks. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-11-13 09:33:45 +03:00
if (map->m_may_create) {
__do_map_lock(sbi, flag, false);
f2fs_balance_fs(sbi, dn.node_changed);
}
goto next_dnode;
sync_out:
/* for hardware encryption, but to avoid potential issue in future */
if (flag == F2FS_GET_BLOCK_DIO && map->m_flags & F2FS_MAP_MAPPED)
f2fs_wait_on_block_writeback_range(inode,
map->m_pblk, map->m_len);
if (flag == F2FS_GET_BLOCK_PRECACHE) {
if (map->m_flags & F2FS_MAP_MAPPED) {
unsigned int ofs = start_pgofs - map->m_lblk;
f2fs_update_extent_cache_range(&dn,
start_pgofs, map->m_pblk + ofs,
map->m_len - ofs);
}
if (map->m_next_extent)
*map->m_next_extent = pgofs + 1;
}
f2fs_put_dnode(&dn);
unlock_out:
f2fs: fix out-place-update DIO write In get_more_blocks(), we may override @create as below code: create = dio->op == REQ_OP_WRITE; if (dio->flags & DIO_SKIP_HOLES) { if (fs_startblk <= ((i_size_read(dio->inode) - 1) >> i_blkbits)) create = 0; } But in f2fs_map_blocks(), we only trigger f2fs_balance_fs() if @create is 1, so in LFS mode, dio overwrite under LFS mode can easily run out of free segments, result in below panic. Call Trace: allocate_segment_by_default+0xa8/0x270 [f2fs] f2fs_allocate_data_block+0x1ea/0x5c0 [f2fs] __allocate_data_block+0x306/0x480 [f2fs] f2fs_map_blocks+0x6f6/0x920 [f2fs] __get_data_block+0x4f/0xb0 [f2fs] get_data_block_dio_write+0x50/0x60 [f2fs] do_blockdev_direct_IO+0xcd5/0x21e0 __blockdev_direct_IO+0x3a/0x3c f2fs_direct_IO+0x1ff/0x4a0 [f2fs] generic_file_direct_write+0xd9/0x160 __generic_file_write_iter+0xbb/0x1e0 f2fs_file_write_iter+0xaf/0x220 [f2fs] __vfs_write+0xd0/0x130 vfs_write+0xb2/0x1b0 SyS_pwrite64+0x69/0xa0 ? vtime_user_exit+0x29/0x70 do_syscall_64+0x6e/0x160 entry_SYSCALL64_slow_path+0x25/0x25 RIP: new_curseg+0x36f/0x380 [f2fs] RSP: ffffac570393f7a8 So this patch introduces a parameter map.m_may_create to indicate that f2fs_map_blocks() is called from write or read path, which can give the right hint to let f2fs_map_blocks() trigger OPU allocation and call f2fs_balanc_fs() correctly. BTW, it disables physical address preallocation for direct IO in f2fs_preallocate_blocks, which is redundant to OPU allocation of f2fs_map_blocks. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-11-13 09:33:45 +03:00
if (map->m_may_create) {
__do_map_lock(sbi, flag, false);
f2fs_balance_fs(sbi, dn.node_changed);
}
out:
trace_f2fs_map_blocks(inode, map, err);
return err;
}
bool f2fs_overwrite_io(struct inode *inode, loff_t pos, size_t len)
{
struct f2fs_map_blocks map;
block_t last_lblk;
int err;
if (pos + len > i_size_read(inode))
return false;
map.m_lblk = F2FS_BYTES_TO_BLK(pos);
map.m_next_pgofs = NULL;
map.m_next_extent = NULL;
map.m_seg_type = NO_CHECK_TYPE;
map.m_may_create = false;
last_lblk = F2FS_BLK_ALIGN(pos + len);
while (map.m_lblk < last_lblk) {
map.m_len = last_lblk - map.m_lblk;
err = f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_DEFAULT);
if (err || map.m_len == 0)
return false;
map.m_lblk += map.m_len;
}
return true;
}
static int __get_data_block(struct inode *inode, sector_t iblock,
struct buffer_head *bh, int create, int flag,
f2fs: fix out-place-update DIO write In get_more_blocks(), we may override @create as below code: create = dio->op == REQ_OP_WRITE; if (dio->flags & DIO_SKIP_HOLES) { if (fs_startblk <= ((i_size_read(dio->inode) - 1) >> i_blkbits)) create = 0; } But in f2fs_map_blocks(), we only trigger f2fs_balance_fs() if @create is 1, so in LFS mode, dio overwrite under LFS mode can easily run out of free segments, result in below panic. Call Trace: allocate_segment_by_default+0xa8/0x270 [f2fs] f2fs_allocate_data_block+0x1ea/0x5c0 [f2fs] __allocate_data_block+0x306/0x480 [f2fs] f2fs_map_blocks+0x6f6/0x920 [f2fs] __get_data_block+0x4f/0xb0 [f2fs] get_data_block_dio_write+0x50/0x60 [f2fs] do_blockdev_direct_IO+0xcd5/0x21e0 __blockdev_direct_IO+0x3a/0x3c f2fs_direct_IO+0x1ff/0x4a0 [f2fs] generic_file_direct_write+0xd9/0x160 __generic_file_write_iter+0xbb/0x1e0 f2fs_file_write_iter+0xaf/0x220 [f2fs] __vfs_write+0xd0/0x130 vfs_write+0xb2/0x1b0 SyS_pwrite64+0x69/0xa0 ? vtime_user_exit+0x29/0x70 do_syscall_64+0x6e/0x160 entry_SYSCALL64_slow_path+0x25/0x25 RIP: new_curseg+0x36f/0x380 [f2fs] RSP: ffffac570393f7a8 So this patch introduces a parameter map.m_may_create to indicate that f2fs_map_blocks() is called from write or read path, which can give the right hint to let f2fs_map_blocks() trigger OPU allocation and call f2fs_balanc_fs() correctly. BTW, it disables physical address preallocation for direct IO in f2fs_preallocate_blocks, which is redundant to OPU allocation of f2fs_map_blocks. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-11-13 09:33:45 +03:00
pgoff_t *next_pgofs, int seg_type, bool may_write)
{
struct f2fs_map_blocks map;
int err;
map.m_lblk = iblock;
map.m_len = bh->b_size >> inode->i_blkbits;
map.m_next_pgofs = next_pgofs;
map.m_next_extent = NULL;
map.m_seg_type = seg_type;
f2fs: fix out-place-update DIO write In get_more_blocks(), we may override @create as below code: create = dio->op == REQ_OP_WRITE; if (dio->flags & DIO_SKIP_HOLES) { if (fs_startblk <= ((i_size_read(dio->inode) - 1) >> i_blkbits)) create = 0; } But in f2fs_map_blocks(), we only trigger f2fs_balance_fs() if @create is 1, so in LFS mode, dio overwrite under LFS mode can easily run out of free segments, result in below panic. Call Trace: allocate_segment_by_default+0xa8/0x270 [f2fs] f2fs_allocate_data_block+0x1ea/0x5c0 [f2fs] __allocate_data_block+0x306/0x480 [f2fs] f2fs_map_blocks+0x6f6/0x920 [f2fs] __get_data_block+0x4f/0xb0 [f2fs] get_data_block_dio_write+0x50/0x60 [f2fs] do_blockdev_direct_IO+0xcd5/0x21e0 __blockdev_direct_IO+0x3a/0x3c f2fs_direct_IO+0x1ff/0x4a0 [f2fs] generic_file_direct_write+0xd9/0x160 __generic_file_write_iter+0xbb/0x1e0 f2fs_file_write_iter+0xaf/0x220 [f2fs] __vfs_write+0xd0/0x130 vfs_write+0xb2/0x1b0 SyS_pwrite64+0x69/0xa0 ? vtime_user_exit+0x29/0x70 do_syscall_64+0x6e/0x160 entry_SYSCALL64_slow_path+0x25/0x25 RIP: new_curseg+0x36f/0x380 [f2fs] RSP: ffffac570393f7a8 So this patch introduces a parameter map.m_may_create to indicate that f2fs_map_blocks() is called from write or read path, which can give the right hint to let f2fs_map_blocks() trigger OPU allocation and call f2fs_balanc_fs() correctly. BTW, it disables physical address preallocation for direct IO in f2fs_preallocate_blocks, which is redundant to OPU allocation of f2fs_map_blocks. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-11-13 09:33:45 +03:00
map.m_may_create = may_write;
err = f2fs_map_blocks(inode, &map, create, flag);
if (!err) {
map_bh(bh, inode->i_sb, map.m_pblk);
bh->b_state = (bh->b_state & ~F2FS_MAP_FLAGS) | map.m_flags;
bh->b_size = (u64)map.m_len << inode->i_blkbits;
}
return err;
}
static int get_data_block(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create, int flag,
pgoff_t *next_pgofs)
{
return __get_data_block(inode, iblock, bh_result, create,
flag, next_pgofs,
f2fs: fix out-place-update DIO write In get_more_blocks(), we may override @create as below code: create = dio->op == REQ_OP_WRITE; if (dio->flags & DIO_SKIP_HOLES) { if (fs_startblk <= ((i_size_read(dio->inode) - 1) >> i_blkbits)) create = 0; } But in f2fs_map_blocks(), we only trigger f2fs_balance_fs() if @create is 1, so in LFS mode, dio overwrite under LFS mode can easily run out of free segments, result in below panic. Call Trace: allocate_segment_by_default+0xa8/0x270 [f2fs] f2fs_allocate_data_block+0x1ea/0x5c0 [f2fs] __allocate_data_block+0x306/0x480 [f2fs] f2fs_map_blocks+0x6f6/0x920 [f2fs] __get_data_block+0x4f/0xb0 [f2fs] get_data_block_dio_write+0x50/0x60 [f2fs] do_blockdev_direct_IO+0xcd5/0x21e0 __blockdev_direct_IO+0x3a/0x3c f2fs_direct_IO+0x1ff/0x4a0 [f2fs] generic_file_direct_write+0xd9/0x160 __generic_file_write_iter+0xbb/0x1e0 f2fs_file_write_iter+0xaf/0x220 [f2fs] __vfs_write+0xd0/0x130 vfs_write+0xb2/0x1b0 SyS_pwrite64+0x69/0xa0 ? vtime_user_exit+0x29/0x70 do_syscall_64+0x6e/0x160 entry_SYSCALL64_slow_path+0x25/0x25 RIP: new_curseg+0x36f/0x380 [f2fs] RSP: ffffac570393f7a8 So this patch introduces a parameter map.m_may_create to indicate that f2fs_map_blocks() is called from write or read path, which can give the right hint to let f2fs_map_blocks() trigger OPU allocation and call f2fs_balanc_fs() correctly. BTW, it disables physical address preallocation for direct IO in f2fs_preallocate_blocks, which is redundant to OPU allocation of f2fs_map_blocks. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-11-13 09:33:45 +03:00
NO_CHECK_TYPE, create);
}
static int get_data_block_dio_write(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create)
{
return __get_data_block(inode, iblock, bh_result, create,
F2FS_GET_BLOCK_DIO, NULL,
f2fs_rw_hint_to_seg_type(inode->i_write_hint),
f2fs: fix livelock in swapfile writes This patch fixes livelock in the below call path when writing swap pages. [46374.617256] c2 701 __switch_to+0xe4/0x100 [46374.617265] c2 701 __schedule+0x80c/0xbc4 [46374.617273] c2 701 schedule+0x74/0x98 [46374.617281] c2 701 rwsem_down_read_failed+0x190/0x234 [46374.617291] c2 701 down_read+0x58/0x5c [46374.617300] c2 701 f2fs_map_blocks+0x138/0x9a8 [46374.617310] c2 701 get_data_block_dio_write+0x74/0x104 [46374.617320] c2 701 __blockdev_direct_IO+0x1350/0x3930 [46374.617331] c2 701 f2fs_direct_IO+0x55c/0x8bc [46374.617341] c2 701 __swap_writepage+0x1d0/0x3e8 [46374.617351] c2 701 swap_writepage+0x44/0x54 [46374.617360] c2 701 shrink_page_list+0x140/0xe80 [46374.617371] c2 701 shrink_inactive_list+0x510/0x918 [46374.617381] c2 701 shrink_node_memcg+0x2d4/0x804 [46374.617391] c2 701 shrink_node+0x10c/0x2f8 [46374.617400] c2 701 do_try_to_free_pages+0x178/0x38c [46374.617410] c2 701 try_to_free_pages+0x348/0x4b8 [46374.617419] c2 701 __alloc_pages_nodemask+0x7f8/0x1014 [46374.617429] c2 701 pagecache_get_page+0x184/0x2cc [46374.617438] c2 701 f2fs_new_node_page+0x60/0x41c [46374.617449] c2 701 f2fs_new_inode_page+0x50/0x7c [46374.617460] c2 701 f2fs_init_inode_metadata+0x128/0x530 [46374.617472] c2 701 f2fs_add_inline_entry+0x138/0xd64 [46374.617480] c2 701 f2fs_do_add_link+0xf4/0x178 [46374.617488] c2 701 f2fs_create+0x1e4/0x3ac [46374.617497] c2 701 path_openat+0xdc0/0x1308 [46374.617507] c2 701 do_filp_open+0x78/0x124 [46374.617516] c2 701 do_sys_open+0x134/0x248 [46374.617525] c2 701 SyS_openat+0x14/0x20 Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-07-31 23:27:05 +03:00
IS_SWAPFILE(inode) ? false : true);
}
static int get_data_block_dio(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create)
{
return __get_data_block(inode, iblock, bh_result, create,
f2fs: fix out-place-update DIO write In get_more_blocks(), we may override @create as below code: create = dio->op == REQ_OP_WRITE; if (dio->flags & DIO_SKIP_HOLES) { if (fs_startblk <= ((i_size_read(dio->inode) - 1) >> i_blkbits)) create = 0; } But in f2fs_map_blocks(), we only trigger f2fs_balance_fs() if @create is 1, so in LFS mode, dio overwrite under LFS mode can easily run out of free segments, result in below panic. Call Trace: allocate_segment_by_default+0xa8/0x270 [f2fs] f2fs_allocate_data_block+0x1ea/0x5c0 [f2fs] __allocate_data_block+0x306/0x480 [f2fs] f2fs_map_blocks+0x6f6/0x920 [f2fs] __get_data_block+0x4f/0xb0 [f2fs] get_data_block_dio_write+0x50/0x60 [f2fs] do_blockdev_direct_IO+0xcd5/0x21e0 __blockdev_direct_IO+0x3a/0x3c f2fs_direct_IO+0x1ff/0x4a0 [f2fs] generic_file_direct_write+0xd9/0x160 __generic_file_write_iter+0xbb/0x1e0 f2fs_file_write_iter+0xaf/0x220 [f2fs] __vfs_write+0xd0/0x130 vfs_write+0xb2/0x1b0 SyS_pwrite64+0x69/0xa0 ? vtime_user_exit+0x29/0x70 do_syscall_64+0x6e/0x160 entry_SYSCALL64_slow_path+0x25/0x25 RIP: new_curseg+0x36f/0x380 [f2fs] RSP: ffffac570393f7a8 So this patch introduces a parameter map.m_may_create to indicate that f2fs_map_blocks() is called from write or read path, which can give the right hint to let f2fs_map_blocks() trigger OPU allocation and call f2fs_balanc_fs() correctly. BTW, it disables physical address preallocation for direct IO in f2fs_preallocate_blocks, which is redundant to OPU allocation of f2fs_map_blocks. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-11-13 09:33:45 +03:00
F2FS_GET_BLOCK_DIO, NULL,
f2fs_rw_hint_to_seg_type(inode->i_write_hint),
false);
}
static int get_data_block_bmap(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create)
{
/* Block number less than F2FS MAX BLOCKS */
if (unlikely(iblock >= F2FS_I_SB(inode)->max_file_blocks))
return -EFBIG;
return __get_data_block(inode, iblock, bh_result, create,
F2FS_GET_BLOCK_BMAP, NULL,
f2fs: fix out-place-update DIO write In get_more_blocks(), we may override @create as below code: create = dio->op == REQ_OP_WRITE; if (dio->flags & DIO_SKIP_HOLES) { if (fs_startblk <= ((i_size_read(dio->inode) - 1) >> i_blkbits)) create = 0; } But in f2fs_map_blocks(), we only trigger f2fs_balance_fs() if @create is 1, so in LFS mode, dio overwrite under LFS mode can easily run out of free segments, result in below panic. Call Trace: allocate_segment_by_default+0xa8/0x270 [f2fs] f2fs_allocate_data_block+0x1ea/0x5c0 [f2fs] __allocate_data_block+0x306/0x480 [f2fs] f2fs_map_blocks+0x6f6/0x920 [f2fs] __get_data_block+0x4f/0xb0 [f2fs] get_data_block_dio_write+0x50/0x60 [f2fs] do_blockdev_direct_IO+0xcd5/0x21e0 __blockdev_direct_IO+0x3a/0x3c f2fs_direct_IO+0x1ff/0x4a0 [f2fs] generic_file_direct_write+0xd9/0x160 __generic_file_write_iter+0xbb/0x1e0 f2fs_file_write_iter+0xaf/0x220 [f2fs] __vfs_write+0xd0/0x130 vfs_write+0xb2/0x1b0 SyS_pwrite64+0x69/0xa0 ? vtime_user_exit+0x29/0x70 do_syscall_64+0x6e/0x160 entry_SYSCALL64_slow_path+0x25/0x25 RIP: new_curseg+0x36f/0x380 [f2fs] RSP: ffffac570393f7a8 So this patch introduces a parameter map.m_may_create to indicate that f2fs_map_blocks() is called from write or read path, which can give the right hint to let f2fs_map_blocks() trigger OPU allocation and call f2fs_balanc_fs() correctly. BTW, it disables physical address preallocation for direct IO in f2fs_preallocate_blocks, which is redundant to OPU allocation of f2fs_map_blocks. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-11-13 09:33:45 +03:00
NO_CHECK_TYPE, create);
}
static inline sector_t logical_to_blk(struct inode *inode, loff_t offset)
{
return (offset >> inode->i_blkbits);
}
static inline loff_t blk_to_logical(struct inode *inode, sector_t blk)
{
return (blk << inode->i_blkbits);
}
static int f2fs_xattr_fiemap(struct inode *inode,
struct fiemap_extent_info *fieinfo)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct page *page;
struct node_info ni;
__u64 phys = 0, len;
__u32 flags;
nid_t xnid = F2FS_I(inode)->i_xattr_nid;
int err = 0;
if (f2fs_has_inline_xattr(inode)) {
int offset;
page = f2fs_grab_cache_page(NODE_MAPPING(sbi),
inode->i_ino, false);
if (!page)
return -ENOMEM;
err = f2fs_get_node_info(sbi, inode->i_ino, &ni);
if (err) {
f2fs_put_page(page, 1);
return err;
}
phys = (__u64)blk_to_logical(inode, ni.blk_addr);
offset = offsetof(struct f2fs_inode, i_addr) +
sizeof(__le32) * (DEF_ADDRS_PER_INODE -
get_inline_xattr_addrs(inode));
phys += offset;
len = inline_xattr_size(inode);
f2fs_put_page(page, 1);
flags = FIEMAP_EXTENT_DATA_INLINE | FIEMAP_EXTENT_NOT_ALIGNED;
if (!xnid)
flags |= FIEMAP_EXTENT_LAST;
err = fiemap_fill_next_extent(fieinfo, 0, phys, len, flags);
if (err || err == 1)
return err;
}
if (xnid) {
page = f2fs_grab_cache_page(NODE_MAPPING(sbi), xnid, false);
if (!page)
return -ENOMEM;
err = f2fs_get_node_info(sbi, xnid, &ni);
if (err) {
f2fs_put_page(page, 1);
return err;
}
phys = (__u64)blk_to_logical(inode, ni.blk_addr);
len = inode->i_sb->s_blocksize;
f2fs_put_page(page, 1);
flags = FIEMAP_EXTENT_LAST;
}
if (phys)
err = fiemap_fill_next_extent(fieinfo, 0, phys, len, flags);
return (err < 0 ? err : 0);
}
int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
u64 start, u64 len)
{
struct buffer_head map_bh;
sector_t start_blk, last_blk;
pgoff_t next_pgofs;
u64 logical = 0, phys = 0, size = 0;
u32 flags = 0;
int ret = 0;
if (fieinfo->fi_flags & FIEMAP_FLAG_CACHE) {
ret = f2fs_precache_extents(inode);
if (ret)
return ret;
}
ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC | FIEMAP_FLAG_XATTR);
if (ret)
return ret;
inode_lock(inode);
if (fieinfo->fi_flags & FIEMAP_FLAG_XATTR) {
ret = f2fs_xattr_fiemap(inode, fieinfo);
goto out;
}
if (f2fs_has_inline_data(inode) || f2fs_has_inline_dentry(inode)) {
ret = f2fs_inline_data_fiemap(inode, fieinfo, start, len);
if (ret != -EAGAIN)
goto out;
}
if (logical_to_blk(inode, len) == 0)
len = blk_to_logical(inode, 1);
start_blk = logical_to_blk(inode, start);
last_blk = logical_to_blk(inode, start + len - 1);
next:
memset(&map_bh, 0, sizeof(struct buffer_head));
map_bh.b_size = len;
ret = get_data_block(inode, start_blk, &map_bh, 0,
F2FS_GET_BLOCK_FIEMAP, &next_pgofs);
if (ret)
goto out;
/* HOLE */
if (!buffer_mapped(&map_bh)) {
start_blk = next_pgofs;
if (blk_to_logical(inode, start_blk) < blk_to_logical(inode,
F2FS_I_SB(inode)->max_file_blocks))
goto prep_next;
flags |= FIEMAP_EXTENT_LAST;
}
if (size) {
if (IS_ENCRYPTED(inode))
flags |= FIEMAP_EXTENT_DATA_ENCRYPTED;
ret = fiemap_fill_next_extent(fieinfo, logical,
phys, size, flags);
}
if (start_blk > last_blk || ret)
goto out;
logical = blk_to_logical(inode, start_blk);
phys = blk_to_logical(inode, map_bh.b_blocknr);
size = map_bh.b_size;
flags = 0;
if (buffer_unwritten(&map_bh))
flags = FIEMAP_EXTENT_UNWRITTEN;
start_blk += logical_to_blk(inode, size);
prep_next:
cond_resched();
if (fatal_signal_pending(current))
ret = -EINTR;
else
goto next;
out:
if (ret == 1)
ret = 0;
inode_unlock(inode);
return ret;
}
f2fs: add fs-verity support Add fs-verity support to f2fs. fs-verity is a filesystem feature that enables transparent integrity protection and authentication of read-only files. It uses a dm-verity like mechanism at the file level: a Merkle tree is used to verify any block in the file in log(filesize) time. It is implemented mainly by helper functions in fs/verity/. See Documentation/filesystems/fsverity.rst for the full documentation. The f2fs support for fs-verity consists of: - Adding a filesystem feature flag and an inode flag for fs-verity. - Implementing the fsverity_operations to support enabling verity on an inode and reading/writing the verity metadata. - Updating ->readpages() to verify data as it's read from verity files and to support reading verity metadata pages. - Updating ->write_begin(), ->write_end(), and ->writepages() to support writing verity metadata pages. - Calling the fs-verity hooks for ->open(), ->setattr(), and ->ioctl(). Like ext4, f2fs stores the verity metadata (Merkle tree and fsverity_descriptor) past the end of the file, starting at the first 64K boundary beyond i_size. This approach works because (a) verity files are readonly, and (b) pages fully beyond i_size aren't visible to userspace but can be read/written internally by f2fs with only some relatively small changes to f2fs. Extended attributes cannot be used because (a) f2fs limits the total size of an inode's xattr entries to 4096 bytes, which wouldn't be enough for even a single Merkle tree block, and (b) f2fs encryption doesn't encrypt xattrs, yet the verity metadata *must* be encrypted when the file is because it contains hashes of the plaintext data. Acked-by: Jaegeuk Kim <jaegeuk@kernel.org> Acked-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Eric Biggers <ebiggers@google.com>
2019-07-22 19:26:24 +03:00
static inline loff_t f2fs_readpage_limit(struct inode *inode)
{
if (IS_ENABLED(CONFIG_FS_VERITY) &&
(IS_VERITY(inode) || f2fs_verity_in_progress(inode)))
return inode->i_sb->s_maxbytes;
return i_size_read(inode);
}
static int f2fs_read_single_page(struct inode *inode, struct page *page,
unsigned nr_pages,
struct f2fs_map_blocks *map,
struct bio **bio_ret,
sector_t *last_block_in_bio,
bool is_readahead)
{
struct bio *bio = *bio_ret;
const unsigned blkbits = inode->i_blkbits;
const unsigned blocksize = 1 << blkbits;
sector_t block_in_file;
sector_t last_block;
sector_t last_block_in_file;
sector_t block_nr;
int ret = 0;
block_in_file = (sector_t)page_index(page);
last_block = block_in_file + nr_pages;
f2fs: add fs-verity support Add fs-verity support to f2fs. fs-verity is a filesystem feature that enables transparent integrity protection and authentication of read-only files. It uses a dm-verity like mechanism at the file level: a Merkle tree is used to verify any block in the file in log(filesize) time. It is implemented mainly by helper functions in fs/verity/. See Documentation/filesystems/fsverity.rst for the full documentation. The f2fs support for fs-verity consists of: - Adding a filesystem feature flag and an inode flag for fs-verity. - Implementing the fsverity_operations to support enabling verity on an inode and reading/writing the verity metadata. - Updating ->readpages() to verify data as it's read from verity files and to support reading verity metadata pages. - Updating ->write_begin(), ->write_end(), and ->writepages() to support writing verity metadata pages. - Calling the fs-verity hooks for ->open(), ->setattr(), and ->ioctl(). Like ext4, f2fs stores the verity metadata (Merkle tree and fsverity_descriptor) past the end of the file, starting at the first 64K boundary beyond i_size. This approach works because (a) verity files are readonly, and (b) pages fully beyond i_size aren't visible to userspace but can be read/written internally by f2fs with only some relatively small changes to f2fs. Extended attributes cannot be used because (a) f2fs limits the total size of an inode's xattr entries to 4096 bytes, which wouldn't be enough for even a single Merkle tree block, and (b) f2fs encryption doesn't encrypt xattrs, yet the verity metadata *must* be encrypted when the file is because it contains hashes of the plaintext data. Acked-by: Jaegeuk Kim <jaegeuk@kernel.org> Acked-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Eric Biggers <ebiggers@google.com>
2019-07-22 19:26:24 +03:00
last_block_in_file = (f2fs_readpage_limit(inode) + blocksize - 1) >>
blkbits;
if (last_block > last_block_in_file)
last_block = last_block_in_file;
/* just zeroing out page which is beyond EOF */
if (block_in_file >= last_block)
goto zero_out;
/*
* Map blocks using the previous result first.
*/
if ((map->m_flags & F2FS_MAP_MAPPED) &&
block_in_file > map->m_lblk &&
block_in_file < (map->m_lblk + map->m_len))
goto got_it;
/*
* Then do more f2fs_map_blocks() calls until we are
* done with this page.
*/
map->m_lblk = block_in_file;
map->m_len = last_block - block_in_file;
ret = f2fs_map_blocks(inode, map, 0, F2FS_GET_BLOCK_DEFAULT);
if (ret)
goto out;
got_it:
if ((map->m_flags & F2FS_MAP_MAPPED)) {
block_nr = map->m_pblk + block_in_file - map->m_lblk;
SetPageMappedToDisk(page);
if (!PageUptodate(page) && (!PageSwapCache(page) &&
!cleancache_get_page(page))) {
SetPageUptodate(page);
goto confused;
}
if (!f2fs_is_valid_blkaddr(F2FS_I_SB(inode), block_nr,
f2fs: introduce DATA_GENERIC_ENHANCE Previously, f2fs_is_valid_blkaddr(, blkaddr, DATA_GENERIC) will check whether @blkaddr locates in main area or not. That check is weak, since the block address in range of main area can point to the address which is not valid in segment info table, and we can not detect such condition, we may suffer worse corruption as system continues running. So this patch introduce DATA_GENERIC_ENHANCE to enhance the sanity check which trigger SIT bitmap check rather than only range check. This patch did below changes as wel: - set SBI_NEED_FSCK in f2fs_is_valid_blkaddr(). - get rid of is_valid_data_blkaddr() to avoid panic if blkaddr is invalid. - introduce verify_fio_blkaddr() to wrap fio {new,old}_blkaddr validation check. - spread blkaddr check in: * f2fs_get_node_info() * __read_out_blkaddrs() * f2fs_submit_page_read() * ra_data_block() * do_recover_data() This patch can fix bug reported from bugzilla below: https://bugzilla.kernel.org/show_bug.cgi?id=203215 https://bugzilla.kernel.org/show_bug.cgi?id=203223 https://bugzilla.kernel.org/show_bug.cgi?id=203231 https://bugzilla.kernel.org/show_bug.cgi?id=203235 https://bugzilla.kernel.org/show_bug.cgi?id=203241 = Update by Jaegeuk Kim = DATA_GENERIC_ENHANCE enhanced to validate block addresses on read/write paths. But, xfstest/generic/446 compalins some generated kernel messages saying invalid bitmap was detected when reading a block. The reaons is, when we get the block addresses from extent_cache, there is no lock to synchronize it from truncating the blocks in parallel. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-15 10:26:32 +03:00
DATA_GENERIC_ENHANCE_READ)) {
ret = -EFSCORRUPTED;
goto out;
}
} else {
zero_out:
zero_user_segment(page, 0, PAGE_SIZE);
f2fs: add fs-verity support Add fs-verity support to f2fs. fs-verity is a filesystem feature that enables transparent integrity protection and authentication of read-only files. It uses a dm-verity like mechanism at the file level: a Merkle tree is used to verify any block in the file in log(filesize) time. It is implemented mainly by helper functions in fs/verity/. See Documentation/filesystems/fsverity.rst for the full documentation. The f2fs support for fs-verity consists of: - Adding a filesystem feature flag and an inode flag for fs-verity. - Implementing the fsverity_operations to support enabling verity on an inode and reading/writing the verity metadata. - Updating ->readpages() to verify data as it's read from verity files and to support reading verity metadata pages. - Updating ->write_begin(), ->write_end(), and ->writepages() to support writing verity metadata pages. - Calling the fs-verity hooks for ->open(), ->setattr(), and ->ioctl(). Like ext4, f2fs stores the verity metadata (Merkle tree and fsverity_descriptor) past the end of the file, starting at the first 64K boundary beyond i_size. This approach works because (a) verity files are readonly, and (b) pages fully beyond i_size aren't visible to userspace but can be read/written internally by f2fs with only some relatively small changes to f2fs. Extended attributes cannot be used because (a) f2fs limits the total size of an inode's xattr entries to 4096 bytes, which wouldn't be enough for even a single Merkle tree block, and (b) f2fs encryption doesn't encrypt xattrs, yet the verity metadata *must* be encrypted when the file is because it contains hashes of the plaintext data. Acked-by: Jaegeuk Kim <jaegeuk@kernel.org> Acked-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Eric Biggers <ebiggers@google.com>
2019-07-22 19:26:24 +03:00
if (f2fs_need_verity(inode, page->index) &&
!fsverity_verify_page(page)) {
ret = -EIO;
goto out;
}
if (!PageUptodate(page))
SetPageUptodate(page);
unlock_page(page);
goto out;
}
/*
* This page will go to BIO. Do we need to send this
* BIO off first?
*/
if (bio && !page_is_mergeable(F2FS_I_SB(inode), bio,
*last_block_in_bio, block_nr)) {
submit_and_realloc:
__submit_bio(F2FS_I_SB(inode), bio, DATA);
bio = NULL;
}
if (bio == NULL) {
bio = f2fs_grab_read_bio(inode, block_nr, nr_pages,
f2fs: add fs-verity support Add fs-verity support to f2fs. fs-verity is a filesystem feature that enables transparent integrity protection and authentication of read-only files. It uses a dm-verity like mechanism at the file level: a Merkle tree is used to verify any block in the file in log(filesize) time. It is implemented mainly by helper functions in fs/verity/. See Documentation/filesystems/fsverity.rst for the full documentation. The f2fs support for fs-verity consists of: - Adding a filesystem feature flag and an inode flag for fs-verity. - Implementing the fsverity_operations to support enabling verity on an inode and reading/writing the verity metadata. - Updating ->readpages() to verify data as it's read from verity files and to support reading verity metadata pages. - Updating ->write_begin(), ->write_end(), and ->writepages() to support writing verity metadata pages. - Calling the fs-verity hooks for ->open(), ->setattr(), and ->ioctl(). Like ext4, f2fs stores the verity metadata (Merkle tree and fsverity_descriptor) past the end of the file, starting at the first 64K boundary beyond i_size. This approach works because (a) verity files are readonly, and (b) pages fully beyond i_size aren't visible to userspace but can be read/written internally by f2fs with only some relatively small changes to f2fs. Extended attributes cannot be used because (a) f2fs limits the total size of an inode's xattr entries to 4096 bytes, which wouldn't be enough for even a single Merkle tree block, and (b) f2fs encryption doesn't encrypt xattrs, yet the verity metadata *must* be encrypted when the file is because it contains hashes of the plaintext data. Acked-by: Jaegeuk Kim <jaegeuk@kernel.org> Acked-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Eric Biggers <ebiggers@google.com>
2019-07-22 19:26:24 +03:00
is_readahead ? REQ_RAHEAD : 0, page->index);
if (IS_ERR(bio)) {
ret = PTR_ERR(bio);
bio = NULL;
goto out;
}
}
/*
* If the page is under writeback, we need to wait for
* its completion to see the correct decrypted data.
*/
f2fs_wait_on_block_writeback(inode, block_nr);
if (bio_add_page(bio, page, blocksize, 0) < blocksize)
goto submit_and_realloc;
inc_page_count(F2FS_I_SB(inode), F2FS_RD_DATA);
ClearPageError(page);
*last_block_in_bio = block_nr;
goto out;
confused:
if (bio) {
__submit_bio(F2FS_I_SB(inode), bio, DATA);
bio = NULL;
}
unlock_page(page);
out:
*bio_ret = bio;
return ret;
}
/*
* This function was originally taken from fs/mpage.c, and customized for f2fs.
* Major change was from block_size == page_size in f2fs by default.
*
* Note that the aops->readpages() function is ONLY used for read-ahead. If
* this function ever deviates from doing just read-ahead, it should either
* use ->readpage() or do the necessary surgery to decouple ->readpages()
* from read-ahead.
*/
static int f2fs_mpage_readpages(struct address_space *mapping,
struct list_head *pages, struct page *page,
unsigned nr_pages, bool is_readahead)
{
struct bio *bio = NULL;
sector_t last_block_in_bio = 0;
struct inode *inode = mapping->host;
struct f2fs_map_blocks map;
int ret = 0;
map.m_pblk = 0;
map.m_lblk = 0;
map.m_len = 0;
map.m_flags = 0;
map.m_next_pgofs = NULL;
map.m_next_extent = NULL;
map.m_seg_type = NO_CHECK_TYPE;
f2fs: fix out-place-update DIO write In get_more_blocks(), we may override @create as below code: create = dio->op == REQ_OP_WRITE; if (dio->flags & DIO_SKIP_HOLES) { if (fs_startblk <= ((i_size_read(dio->inode) - 1) >> i_blkbits)) create = 0; } But in f2fs_map_blocks(), we only trigger f2fs_balance_fs() if @create is 1, so in LFS mode, dio overwrite under LFS mode can easily run out of free segments, result in below panic. Call Trace: allocate_segment_by_default+0xa8/0x270 [f2fs] f2fs_allocate_data_block+0x1ea/0x5c0 [f2fs] __allocate_data_block+0x306/0x480 [f2fs] f2fs_map_blocks+0x6f6/0x920 [f2fs] __get_data_block+0x4f/0xb0 [f2fs] get_data_block_dio_write+0x50/0x60 [f2fs] do_blockdev_direct_IO+0xcd5/0x21e0 __blockdev_direct_IO+0x3a/0x3c f2fs_direct_IO+0x1ff/0x4a0 [f2fs] generic_file_direct_write+0xd9/0x160 __generic_file_write_iter+0xbb/0x1e0 f2fs_file_write_iter+0xaf/0x220 [f2fs] __vfs_write+0xd0/0x130 vfs_write+0xb2/0x1b0 SyS_pwrite64+0x69/0xa0 ? vtime_user_exit+0x29/0x70 do_syscall_64+0x6e/0x160 entry_SYSCALL64_slow_path+0x25/0x25 RIP: new_curseg+0x36f/0x380 [f2fs] RSP: ffffac570393f7a8 So this patch introduces a parameter map.m_may_create to indicate that f2fs_map_blocks() is called from write or read path, which can give the right hint to let f2fs_map_blocks() trigger OPU allocation and call f2fs_balanc_fs() correctly. BTW, it disables physical address preallocation for direct IO in f2fs_preallocate_blocks, which is redundant to OPU allocation of f2fs_map_blocks. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-11-13 09:33:45 +03:00
map.m_may_create = false;
for (; nr_pages; nr_pages--) {
if (pages) {
page = list_last_entry(pages, struct page, lru);
prefetchw(&page->flags);
list_del(&page->lru);
if (add_to_page_cache_lru(page, mapping,
page_index(page),
mm, memcg: use consistent gfp flags during readahead Vladimir has noticed that we might declare memcg oom even during readahead because read_pages only uses GFP_KERNEL (with mapping_gfp restriction) while __do_page_cache_readahead uses page_cache_alloc_readahead which adds __GFP_NORETRY to prevent from OOMs. This gfp mask discrepancy is really unfortunate and easily fixable. Drop page_cache_alloc_readahead() which only has one user and outsource the gfp_mask logic into readahead_gfp_mask and propagate this mask from __do_page_cache_readahead down to read_pages. This alone would have only very limited impact as most filesystems are implementing ->readpages and the common implementation mpage_readpages does GFP_KERNEL (with mapping_gfp restriction) again. We can tell it to use readahead_gfp_mask instead as this function is called only during readahead as well. The same applies to read_cache_pages. ext4 has its own ext4_mpage_readpages but the path which has pages != NULL can use the same gfp mask. Btrfs, cifs, f2fs and orangefs are doing a very similar pattern to mpage_readpages so the same can be applied to them as well. [akpm@linux-foundation.org: coding-style fixes] [mhocko@suse.com: restrict gfp mask in mpage_alloc] Link: http://lkml.kernel.org/r/20160610074223.GC32285@dhcp22.suse.cz Link: http://lkml.kernel.org/r/1465301556-26431-1-git-send-email-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Cc: Vladimir Davydov <vdavydov@parallels.com> Cc: Chris Mason <clm@fb.com> Cc: Steve French <sfrench@samba.org> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Jan Kara <jack@suse.cz> Cc: Mike Marshall <hubcap@omnibond.com> Cc: Jaegeuk Kim <jaegeuk@kernel.org> Cc: Changman Lee <cm224.lee@samsung.com> Cc: Chao Yu <yuchao0@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-07-27 01:24:53 +03:00
readahead_gfp_mask(mapping)))
goto next_page;
}
ret = f2fs_read_single_page(inode, page, nr_pages, &map, &bio,
&last_block_in_bio, is_readahead);
if (ret) {
SetPageError(page);
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 15:29:47 +03:00
zero_user_segment(page, 0, PAGE_SIZE);
unlock_page(page);
}
next_page:
if (pages)
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 15:29:47 +03:00
put_page(page);
}
BUG_ON(pages && !list_empty(pages));
if (bio)
The major change in this version is mitigating cpu overheads on write paths by replacing redundant inode page updates with mark_inode_dirty calls. And we tried to reduce lock contentions as well to improve filesystem scalability. Other feature is setting F2FS automatically when detecting host-managed SMR. = Enhancement = - ioctl to move a range of data between files - inject orphan inode errors - avoid flush commands congestion - support lazytime = Bug fixes = - return proper results for some dentry operations - fix deadlock in add_link failure - disable extent_cache for fcollapse/finsert -----BEGIN PGP SIGNATURE----- Version: GnuPG v1 iQIcBAABAgAGBQJXmDJFAAoJEEAUqH6CSFDSJeYP/0ru8+5/ui5VTCdNPQB9KxYD DIUaDGpeoLvmn3ZdrMEdyNr6kWbgjCE9JjOGPQ7l1/apErOGVPyaBwflKcCDwloU pAlEqVM1Q9j4qH4i9SWTlvPtsHBHB7G7YSe3vDB9fJGSTqumubIlnaBm+Wfjx31U p53WcPn9LpOyzfmvZf2tOHmvZ7bWLkE/a07x9kPC6XHUFb9C17jLRFFGeuhZQHv1 Yo7HgokBnPExa8TnEILYyX/x+eecFS/1Cp/cN0STsebSu8pStTHTcAP7qEpKQB88 Cc51Lf+d5gFeydxKDFxwdH3VWOGIr9Ppako+lHW83gJcHP0zw8zdxULab+HJMa4n MOByRRiafwu1sL0dl7TCfsYNIHdEnXhWbhcRhMVZbb5C2Q6+Htuac8ZrKSOWExNN DUqRkzeTib9u+cHxUTFFPgOGdUjDLmg3XHU7mvb+2hViluVjIImC4tqD5XPpv7vt WnaDJxLCGD/6DF2yhiVY9NysuxInLTNFFCF06LworZ4L24hlg5TvN0UeUNRO9954 ux6f+lSORCzV3TmrsHP5vwjSAW26FviPXV1q1HHJeTpWKMlhsZtHmOAJOtZKKmxP WFnHT0aiWF+sQf4qfxVQL+lLqtgRKJAI9zqGRyfDJWJp5aXdRuVsZs9pWNQF7lCo 5gVnCYk3ULjXG3b23j2S =tKTR -----END PGP SIGNATURE----- Merge tag 'for-f2fs-4.8' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs Pull f2fs updates from Jaegeuk Kim: "The major change in this version is mitigating cpu overheads on write paths by replacing redundant inode page updates with mark_inode_dirty calls. And we tried to reduce lock contentions as well to improve filesystem scalability. Other feature is setting F2FS automatically when detecting host-managed SMR. Enhancements: - ioctl to move a range of data between files - inject orphan inode errors - avoid flush commands congestion - support lazytime Bug fixes: - return proper results for some dentry operations - fix deadlock in add_link failure - disable extent_cache for fcollapse/finsert" * tag 'for-f2fs-4.8' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (68 commits) f2fs: clean up coding style and redundancy f2fs: get victim segment again after new cp f2fs: handle error case with f2fs_bug_on f2fs: avoid data race when deciding checkpoin in f2fs_sync_file f2fs: support an ioctl to move a range of data blocks f2fs: fix to report error number of f2fs_find_entry f2fs: avoid memory allocation failure due to a long length f2fs: reset default idle interval value f2fs: use blk_plug in all the possible paths f2fs: fix to avoid data update racing between GC and DIO f2fs: add maximum prefree segments f2fs: disable extent_cache for fcollapse/finsert inodes f2fs: refactor __exchange_data_block for speed up f2fs: fix ERR_PTR returned by bio f2fs: avoid mark_inode_dirty f2fs: move i_size_write in f2fs_write_end f2fs: fix to avoid redundant discard during fstrim f2fs: avoid mismatching block range for discard f2fs: fix incorrect f_bfree calculation in ->statfs f2fs: use percpu_rw_semaphore ...
2016-07-27 20:36:31 +03:00
__submit_bio(F2FS_I_SB(inode), bio, DATA);
return pages ? 0 : ret;
}
static int f2fs_read_data_page(struct file *file, struct page *page)
{
struct inode *inode = page_file_mapping(page)->host;
int ret = -EAGAIN;
trace_f2fs_readpage(page, DATA);
/* If the file has inline data, try to read it directly */
if (f2fs_has_inline_data(inode))
ret = f2fs_read_inline_data(inode, page);
if (ret == -EAGAIN)
ret = f2fs_mpage_readpages(page_file_mapping(page),
NULL, page, 1, false);
return ret;
}
static int f2fs_read_data_pages(struct file *file,
struct address_space *mapping,
struct list_head *pages, unsigned nr_pages)
{
struct inode *inode = mapping->host;
struct page *page = list_last_entry(pages, struct page, lru);
trace_f2fs_readpages(inode, page, nr_pages);
/* If the file has inline data, skip readpages */
if (f2fs_has_inline_data(inode))
return 0;
return f2fs_mpage_readpages(mapping, pages, NULL, nr_pages, true);
}
static int encrypt_one_page(struct f2fs_io_info *fio)
{
struct inode *inode = fio->page->mapping->host;
f2fs: readahead encrypted block during GC During GC, for each encrypted block, we will read block synchronously into meta page, and then submit it into current cold data log area. So this block read model with 4k granularity can make poor performance, like migrating non-encrypted block, let's readahead encrypted block as well to improve migration performance. To implement this, we choose meta page that its index is old block address of the encrypted block, and readahead ciphertext into this page, later, if readaheaded page is still updated, we will load its data into target meta page, and submit the write IO. Note that for OPU, truncation, deletion, we need to invalid meta page after we invalid old block address, to make sure we won't load invalid data from target meta page during encrypted block migration. for ((i = 0; i < 1000; i++)) do { xfs_io -f /mnt/f2fs/dir/$i -c "pwrite 0 128k" -c "fsync"; } done for ((i = 0; i < 1000; i+=2)) do { rm /mnt/f2fs/dir/$i; } done ret = ioctl(fd, F2FS_IOC_GARBAGE_COLLECT, 0); Before: gc-6549 [001] d..1 214682.212797: block_rq_insert: 8,32 RA 32768 () 786400 + 64 [gc] gc-6549 [001] d..1 214682.212802: block_unplug: [gc] 1 gc-6549 [001] .... 214682.213892: block_bio_queue: 8,32 R 67494144 + 8 [gc] gc-6549 [001] .... 214682.213899: block_getrq: 8,32 R 67494144 + 8 [gc] gc-6549 [001] .... 214682.213902: block_plug: [gc] gc-6549 [001] d..1 214682.213905: block_rq_insert: 8,32 R 4096 () 67494144 + 8 [gc] gc-6549 [001] d..1 214682.213908: block_unplug: [gc] 1 gc-6549 [001] .... 214682.226405: block_bio_queue: 8,32 R 67494152 + 8 [gc] gc-6549 [001] .... 214682.226412: block_getrq: 8,32 R 67494152 + 8 [gc] gc-6549 [001] .... 214682.226414: block_plug: [gc] gc-6549 [001] d..1 214682.226417: block_rq_insert: 8,32 R 4096 () 67494152 + 8 [gc] gc-6549 [001] d..1 214682.226420: block_unplug: [gc] 1 gc-6549 [001] .... 214682.226904: block_bio_queue: 8,32 R 67494160 + 8 [gc] gc-6549 [001] .... 214682.226910: block_getrq: 8,32 R 67494160 + 8 [gc] gc-6549 [001] .... 214682.226911: block_plug: [gc] gc-6549 [001] d..1 214682.226914: block_rq_insert: 8,32 R 4096 () 67494160 + 8 [gc] gc-6549 [001] d..1 214682.226916: block_unplug: [gc] 1 After: gc-5678 [003] .... 214327.025906: block_bio_queue: 8,32 R 67493824 + 8 [gc] gc-5678 [003] .... 214327.025908: block_bio_backmerge: 8,32 R 67493824 + 8 [gc] gc-5678 [003] .... 214327.025915: block_bio_queue: 8,32 R 67493832 + 8 [gc] gc-5678 [003] .... 214327.025917: block_bio_backmerge: 8,32 R 67493832 + 8 [gc] gc-5678 [003] .... 214327.025923: block_bio_queue: 8,32 R 67493840 + 8 [gc] gc-5678 [003] .... 214327.025925: block_bio_backmerge: 8,32 R 67493840 + 8 [gc] gc-5678 [003] .... 214327.025932: block_bio_queue: 8,32 R 67493848 + 8 [gc] gc-5678 [003] .... 214327.025934: block_bio_backmerge: 8,32 R 67493848 + 8 [gc] gc-5678 [003] .... 214327.025941: block_bio_queue: 8,32 R 67493856 + 8 [gc] gc-5678 [003] .... 214327.025943: block_bio_backmerge: 8,32 R 67493856 + 8 [gc] gc-5678 [003] .... 214327.025953: block_bio_queue: 8,32 R 67493864 + 8 [gc] gc-5678 [003] .... 214327.025955: block_bio_backmerge: 8,32 R 67493864 + 8 [gc] gc-5678 [003] .... 214327.025962: block_bio_queue: 8,32 R 67493872 + 8 [gc] gc-5678 [003] .... 214327.025964: block_bio_backmerge: 8,32 R 67493872 + 8 [gc] gc-5678 [003] .... 214327.025970: block_bio_queue: 8,32 R 67493880 + 8 [gc] gc-5678 [003] .... 214327.025972: block_bio_backmerge: 8,32 R 67493880 + 8 [gc] gc-5678 [003] .... 214327.026000: block_bio_queue: 8,32 WS 34123776 + 2048 [gc] gc-5678 [003] .... 214327.026019: block_getrq: 8,32 WS 34123776 + 2048 [gc] gc-5678 [003] d..1 214327.026021: block_rq_insert: 8,32 R 131072 () 67493632 + 256 [gc] gc-5678 [003] d..1 214327.026023: block_unplug: [gc] 1 gc-5678 [003] d..1 214327.026026: block_rq_issue: 8,32 R 131072 () 67493632 + 256 [gc] gc-5678 [003] .... 214327.026046: block_plug: [gc] Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-08-14 17:37:25 +03:00
struct page *mpage;
gfp_t gfp_flags = GFP_NOFS;
if (!f2fs_encrypted_file(inode))
return 0;
/* wait for GCed page writeback via META_MAPPING */
f2fs_wait_on_block_writeback(inode, fio->old_blkaddr);
retry_encrypt:
fio->encrypted_page = fscrypt_encrypt_pagecache_blocks(fio->page,
PAGE_SIZE, 0,
gfp_flags);
f2fs: readahead encrypted block during GC During GC, for each encrypted block, we will read block synchronously into meta page, and then submit it into current cold data log area. So this block read model with 4k granularity can make poor performance, like migrating non-encrypted block, let's readahead encrypted block as well to improve migration performance. To implement this, we choose meta page that its index is old block address of the encrypted block, and readahead ciphertext into this page, later, if readaheaded page is still updated, we will load its data into target meta page, and submit the write IO. Note that for OPU, truncation, deletion, we need to invalid meta page after we invalid old block address, to make sure we won't load invalid data from target meta page during encrypted block migration. for ((i = 0; i < 1000; i++)) do { xfs_io -f /mnt/f2fs/dir/$i -c "pwrite 0 128k" -c "fsync"; } done for ((i = 0; i < 1000; i+=2)) do { rm /mnt/f2fs/dir/$i; } done ret = ioctl(fd, F2FS_IOC_GARBAGE_COLLECT, 0); Before: gc-6549 [001] d..1 214682.212797: block_rq_insert: 8,32 RA 32768 () 786400 + 64 [gc] gc-6549 [001] d..1 214682.212802: block_unplug: [gc] 1 gc-6549 [001] .... 214682.213892: block_bio_queue: 8,32 R 67494144 + 8 [gc] gc-6549 [001] .... 214682.213899: block_getrq: 8,32 R 67494144 + 8 [gc] gc-6549 [001] .... 214682.213902: block_plug: [gc] gc-6549 [001] d..1 214682.213905: block_rq_insert: 8,32 R 4096 () 67494144 + 8 [gc] gc-6549 [001] d..1 214682.213908: block_unplug: [gc] 1 gc-6549 [001] .... 214682.226405: block_bio_queue: 8,32 R 67494152 + 8 [gc] gc-6549 [001] .... 214682.226412: block_getrq: 8,32 R 67494152 + 8 [gc] gc-6549 [001] .... 214682.226414: block_plug: [gc] gc-6549 [001] d..1 214682.226417: block_rq_insert: 8,32 R 4096 () 67494152 + 8 [gc] gc-6549 [001] d..1 214682.226420: block_unplug: [gc] 1 gc-6549 [001] .... 214682.226904: block_bio_queue: 8,32 R 67494160 + 8 [gc] gc-6549 [001] .... 214682.226910: block_getrq: 8,32 R 67494160 + 8 [gc] gc-6549 [001] .... 214682.226911: block_plug: [gc] gc-6549 [001] d..1 214682.226914: block_rq_insert: 8,32 R 4096 () 67494160 + 8 [gc] gc-6549 [001] d..1 214682.226916: block_unplug: [gc] 1 After: gc-5678 [003] .... 214327.025906: block_bio_queue: 8,32 R 67493824 + 8 [gc] gc-5678 [003] .... 214327.025908: block_bio_backmerge: 8,32 R 67493824 + 8 [gc] gc-5678 [003] .... 214327.025915: block_bio_queue: 8,32 R 67493832 + 8 [gc] gc-5678 [003] .... 214327.025917: block_bio_backmerge: 8,32 R 67493832 + 8 [gc] gc-5678 [003] .... 214327.025923: block_bio_queue: 8,32 R 67493840 + 8 [gc] gc-5678 [003] .... 214327.025925: block_bio_backmerge: 8,32 R 67493840 + 8 [gc] gc-5678 [003] .... 214327.025932: block_bio_queue: 8,32 R 67493848 + 8 [gc] gc-5678 [003] .... 214327.025934: block_bio_backmerge: 8,32 R 67493848 + 8 [gc] gc-5678 [003] .... 214327.025941: block_bio_queue: 8,32 R 67493856 + 8 [gc] gc-5678 [003] .... 214327.025943: block_bio_backmerge: 8,32 R 67493856 + 8 [gc] gc-5678 [003] .... 214327.025953: block_bio_queue: 8,32 R 67493864 + 8 [gc] gc-5678 [003] .... 214327.025955: block_bio_backmerge: 8,32 R 67493864 + 8 [gc] gc-5678 [003] .... 214327.025962: block_bio_queue: 8,32 R 67493872 + 8 [gc] gc-5678 [003] .... 214327.025964: block_bio_backmerge: 8,32 R 67493872 + 8 [gc] gc-5678 [003] .... 214327.025970: block_bio_queue: 8,32 R 67493880 + 8 [gc] gc-5678 [003] .... 214327.025972: block_bio_backmerge: 8,32 R 67493880 + 8 [gc] gc-5678 [003] .... 214327.026000: block_bio_queue: 8,32 WS 34123776 + 2048 [gc] gc-5678 [003] .... 214327.026019: block_getrq: 8,32 WS 34123776 + 2048 [gc] gc-5678 [003] d..1 214327.026021: block_rq_insert: 8,32 R 131072 () 67493632 + 256 [gc] gc-5678 [003] d..1 214327.026023: block_unplug: [gc] 1 gc-5678 [003] d..1 214327.026026: block_rq_issue: 8,32 R 131072 () 67493632 + 256 [gc] gc-5678 [003] .... 214327.026046: block_plug: [gc] Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-08-14 17:37:25 +03:00
if (IS_ERR(fio->encrypted_page)) {
/* flush pending IOs and wait for a while in the ENOMEM case */
if (PTR_ERR(fio->encrypted_page) == -ENOMEM) {
f2fs_flush_merged_writes(fio->sbi);
congestion_wait(BLK_RW_ASYNC, HZ/50);
gfp_flags |= __GFP_NOFAIL;
goto retry_encrypt;
}
return PTR_ERR(fio->encrypted_page);
}
f2fs: readahead encrypted block during GC During GC, for each encrypted block, we will read block synchronously into meta page, and then submit it into current cold data log area. So this block read model with 4k granularity can make poor performance, like migrating non-encrypted block, let's readahead encrypted block as well to improve migration performance. To implement this, we choose meta page that its index is old block address of the encrypted block, and readahead ciphertext into this page, later, if readaheaded page is still updated, we will load its data into target meta page, and submit the write IO. Note that for OPU, truncation, deletion, we need to invalid meta page after we invalid old block address, to make sure we won't load invalid data from target meta page during encrypted block migration. for ((i = 0; i < 1000; i++)) do { xfs_io -f /mnt/f2fs/dir/$i -c "pwrite 0 128k" -c "fsync"; } done for ((i = 0; i < 1000; i+=2)) do { rm /mnt/f2fs/dir/$i; } done ret = ioctl(fd, F2FS_IOC_GARBAGE_COLLECT, 0); Before: gc-6549 [001] d..1 214682.212797: block_rq_insert: 8,32 RA 32768 () 786400 + 64 [gc] gc-6549 [001] d..1 214682.212802: block_unplug: [gc] 1 gc-6549 [001] .... 214682.213892: block_bio_queue: 8,32 R 67494144 + 8 [gc] gc-6549 [001] .... 214682.213899: block_getrq: 8,32 R 67494144 + 8 [gc] gc-6549 [001] .... 214682.213902: block_plug: [gc] gc-6549 [001] d..1 214682.213905: block_rq_insert: 8,32 R 4096 () 67494144 + 8 [gc] gc-6549 [001] d..1 214682.213908: block_unplug: [gc] 1 gc-6549 [001] .... 214682.226405: block_bio_queue: 8,32 R 67494152 + 8 [gc] gc-6549 [001] .... 214682.226412: block_getrq: 8,32 R 67494152 + 8 [gc] gc-6549 [001] .... 214682.226414: block_plug: [gc] gc-6549 [001] d..1 214682.226417: block_rq_insert: 8,32 R 4096 () 67494152 + 8 [gc] gc-6549 [001] d..1 214682.226420: block_unplug: [gc] 1 gc-6549 [001] .... 214682.226904: block_bio_queue: 8,32 R 67494160 + 8 [gc] gc-6549 [001] .... 214682.226910: block_getrq: 8,32 R 67494160 + 8 [gc] gc-6549 [001] .... 214682.226911: block_plug: [gc] gc-6549 [001] d..1 214682.226914: block_rq_insert: 8,32 R 4096 () 67494160 + 8 [gc] gc-6549 [001] d..1 214682.226916: block_unplug: [gc] 1 After: gc-5678 [003] .... 214327.025906: block_bio_queue: 8,32 R 67493824 + 8 [gc] gc-5678 [003] .... 214327.025908: block_bio_backmerge: 8,32 R 67493824 + 8 [gc] gc-5678 [003] .... 214327.025915: block_bio_queue: 8,32 R 67493832 + 8 [gc] gc-5678 [003] .... 214327.025917: block_bio_backmerge: 8,32 R 67493832 + 8 [gc] gc-5678 [003] .... 214327.025923: block_bio_queue: 8,32 R 67493840 + 8 [gc] gc-5678 [003] .... 214327.025925: block_bio_backmerge: 8,32 R 67493840 + 8 [gc] gc-5678 [003] .... 214327.025932: block_bio_queue: 8,32 R 67493848 + 8 [gc] gc-5678 [003] .... 214327.025934: block_bio_backmerge: 8,32 R 67493848 + 8 [gc] gc-5678 [003] .... 214327.025941: block_bio_queue: 8,32 R 67493856 + 8 [gc] gc-5678 [003] .... 214327.025943: block_bio_backmerge: 8,32 R 67493856 + 8 [gc] gc-5678 [003] .... 214327.025953: block_bio_queue: 8,32 R 67493864 + 8 [gc] gc-5678 [003] .... 214327.025955: block_bio_backmerge: 8,32 R 67493864 + 8 [gc] gc-5678 [003] .... 214327.025962: block_bio_queue: 8,32 R 67493872 + 8 [gc] gc-5678 [003] .... 214327.025964: block_bio_backmerge: 8,32 R 67493872 + 8 [gc] gc-5678 [003] .... 214327.025970: block_bio_queue: 8,32 R 67493880 + 8 [gc] gc-5678 [003] .... 214327.025972: block_bio_backmerge: 8,32 R 67493880 + 8 [gc] gc-5678 [003] .... 214327.026000: block_bio_queue: 8,32 WS 34123776 + 2048 [gc] gc-5678 [003] .... 214327.026019: block_getrq: 8,32 WS 34123776 + 2048 [gc] gc-5678 [003] d..1 214327.026021: block_rq_insert: 8,32 R 131072 () 67493632 + 256 [gc] gc-5678 [003] d..1 214327.026023: block_unplug: [gc] 1 gc-5678 [003] d..1 214327.026026: block_rq_issue: 8,32 R 131072 () 67493632 + 256 [gc] gc-5678 [003] .... 214327.026046: block_plug: [gc] Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-08-14 17:37:25 +03:00
mpage = find_lock_page(META_MAPPING(fio->sbi), fio->old_blkaddr);
if (mpage) {
if (PageUptodate(mpage))
memcpy(page_address(mpage),
page_address(fio->encrypted_page), PAGE_SIZE);
f2fs_put_page(mpage, 1);
}
f2fs: readahead encrypted block during GC During GC, for each encrypted block, we will read block synchronously into meta page, and then submit it into current cold data log area. So this block read model with 4k granularity can make poor performance, like migrating non-encrypted block, let's readahead encrypted block as well to improve migration performance. To implement this, we choose meta page that its index is old block address of the encrypted block, and readahead ciphertext into this page, later, if readaheaded page is still updated, we will load its data into target meta page, and submit the write IO. Note that for OPU, truncation, deletion, we need to invalid meta page after we invalid old block address, to make sure we won't load invalid data from target meta page during encrypted block migration. for ((i = 0; i < 1000; i++)) do { xfs_io -f /mnt/f2fs/dir/$i -c "pwrite 0 128k" -c "fsync"; } done for ((i = 0; i < 1000; i+=2)) do { rm /mnt/f2fs/dir/$i; } done ret = ioctl(fd, F2FS_IOC_GARBAGE_COLLECT, 0); Before: gc-6549 [001] d..1 214682.212797: block_rq_insert: 8,32 RA 32768 () 786400 + 64 [gc] gc-6549 [001] d..1 214682.212802: block_unplug: [gc] 1 gc-6549 [001] .... 214682.213892: block_bio_queue: 8,32 R 67494144 + 8 [gc] gc-6549 [001] .... 214682.213899: block_getrq: 8,32 R 67494144 + 8 [gc] gc-6549 [001] .... 214682.213902: block_plug: [gc] gc-6549 [001] d..1 214682.213905: block_rq_insert: 8,32 R 4096 () 67494144 + 8 [gc] gc-6549 [001] d..1 214682.213908: block_unplug: [gc] 1 gc-6549 [001] .... 214682.226405: block_bio_queue: 8,32 R 67494152 + 8 [gc] gc-6549 [001] .... 214682.226412: block_getrq: 8,32 R 67494152 + 8 [gc] gc-6549 [001] .... 214682.226414: block_plug: [gc] gc-6549 [001] d..1 214682.226417: block_rq_insert: 8,32 R 4096 () 67494152 + 8 [gc] gc-6549 [001] d..1 214682.226420: block_unplug: [gc] 1 gc-6549 [001] .... 214682.226904: block_bio_queue: 8,32 R 67494160 + 8 [gc] gc-6549 [001] .... 214682.226910: block_getrq: 8,32 R 67494160 + 8 [gc] gc-6549 [001] .... 214682.226911: block_plug: [gc] gc-6549 [001] d..1 214682.226914: block_rq_insert: 8,32 R 4096 () 67494160 + 8 [gc] gc-6549 [001] d..1 214682.226916: block_unplug: [gc] 1 After: gc-5678 [003] .... 214327.025906: block_bio_queue: 8,32 R 67493824 + 8 [gc] gc-5678 [003] .... 214327.025908: block_bio_backmerge: 8,32 R 67493824 + 8 [gc] gc-5678 [003] .... 214327.025915: block_bio_queue: 8,32 R 67493832 + 8 [gc] gc-5678 [003] .... 214327.025917: block_bio_backmerge: 8,32 R 67493832 + 8 [gc] gc-5678 [003] .... 214327.025923: block_bio_queue: 8,32 R 67493840 + 8 [gc] gc-5678 [003] .... 214327.025925: block_bio_backmerge: 8,32 R 67493840 + 8 [gc] gc-5678 [003] .... 214327.025932: block_bio_queue: 8,32 R 67493848 + 8 [gc] gc-5678 [003] .... 214327.025934: block_bio_backmerge: 8,32 R 67493848 + 8 [gc] gc-5678 [003] .... 214327.025941: block_bio_queue: 8,32 R 67493856 + 8 [gc] gc-5678 [003] .... 214327.025943: block_bio_backmerge: 8,32 R 67493856 + 8 [gc] gc-5678 [003] .... 214327.025953: block_bio_queue: 8,32 R 67493864 + 8 [gc] gc-5678 [003] .... 214327.025955: block_bio_backmerge: 8,32 R 67493864 + 8 [gc] gc-5678 [003] .... 214327.025962: block_bio_queue: 8,32 R 67493872 + 8 [gc] gc-5678 [003] .... 214327.025964: block_bio_backmerge: 8,32 R 67493872 + 8 [gc] gc-5678 [003] .... 214327.025970: block_bio_queue: 8,32 R 67493880 + 8 [gc] gc-5678 [003] .... 214327.025972: block_bio_backmerge: 8,32 R 67493880 + 8 [gc] gc-5678 [003] .... 214327.026000: block_bio_queue: 8,32 WS 34123776 + 2048 [gc] gc-5678 [003] .... 214327.026019: block_getrq: 8,32 WS 34123776 + 2048 [gc] gc-5678 [003] d..1 214327.026021: block_rq_insert: 8,32 R 131072 () 67493632 + 256 [gc] gc-5678 [003] d..1 214327.026023: block_unplug: [gc] 1 gc-5678 [003] d..1 214327.026026: block_rq_issue: 8,32 R 131072 () 67493632 + 256 [gc] gc-5678 [003] .... 214327.026046: block_plug: [gc] Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-08-14 17:37:25 +03:00
return 0;
}
static inline bool check_inplace_update_policy(struct inode *inode,
struct f2fs_io_info *fio)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
unsigned int policy = SM_I(sbi)->ipu_policy;
if (policy & (0x1 << F2FS_IPU_FORCE))
return true;
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 19:20:41 +03:00
if (policy & (0x1 << F2FS_IPU_SSR) && f2fs_need_SSR(sbi))
return true;
if (policy & (0x1 << F2FS_IPU_UTIL) &&
utilization(sbi) > SM_I(sbi)->min_ipu_util)
return true;
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 19:20:41 +03:00
if (policy & (0x1 << F2FS_IPU_SSR_UTIL) && f2fs_need_SSR(sbi) &&
utilization(sbi) > SM_I(sbi)->min_ipu_util)
return true;
/*
* IPU for rewrite async pages
*/
if (policy & (0x1 << F2FS_IPU_ASYNC) &&
fio && fio->op == REQ_OP_WRITE &&
!(fio->op_flags & REQ_SYNC) &&
!IS_ENCRYPTED(inode))
return true;
/* this is only set during fdatasync */
if (policy & (0x1 << F2FS_IPU_FSYNC) &&
is_inode_flag_set(inode, FI_NEED_IPU))
return true;
if (unlikely(fio && is_sbi_flag_set(sbi, SBI_CP_DISABLED) &&
!f2fs_is_checkpointed_data(sbi, fio->old_blkaddr)))
return true;
return false;
}
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 19:20:41 +03:00
bool f2fs_should_update_inplace(struct inode *inode, struct f2fs_io_info *fio)
{
if (f2fs_is_pinned_file(inode))
return true;
/* if this is cold file, we should overwrite to avoid fragmentation */
if (file_is_cold(inode))
return true;
return check_inplace_update_policy(inode, fio);
}
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 19:20:41 +03:00
bool f2fs_should_update_outplace(struct inode *inode, struct f2fs_io_info *fio)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
if (test_opt(sbi, LFS))
return true;
if (S_ISDIR(inode->i_mode))
return true;
if (IS_NOQUOTA(inode))
return true;
if (f2fs_is_atomic_file(inode))
return true;
if (fio) {
if (is_cold_data(fio->page))
return true;
if (IS_ATOMIC_WRITTEN_PAGE(fio->page))
return true;
if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED) &&
f2fs_is_checkpointed_data(sbi, fio->old_blkaddr)))
return true;
}
return false;
}
static inline bool need_inplace_update(struct f2fs_io_info *fio)
{
struct inode *inode = fio->page->mapping->host;
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 19:20:41 +03:00
if (f2fs_should_update_outplace(inode, fio))
return false;
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 19:20:41 +03:00
return f2fs_should_update_inplace(inode, fio);
}
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 19:20:41 +03:00
int f2fs_do_write_data_page(struct f2fs_io_info *fio)
{
struct page *page = fio->page;
struct inode *inode = page->mapping->host;
struct dnode_of_data dn;
struct extent_info ei = {0,0,0};
struct node_info ni;
bool ipu_force = false;
int err = 0;
set_new_dnode(&dn, inode, NULL, NULL, 0);
if (need_inplace_update(fio) &&
f2fs_lookup_extent_cache(inode, page->index, &ei)) {
fio->old_blkaddr = ei.blk + page->index - ei.fofs;
f2fs: fix to do sanity check with block address in main area This patch add to do sanity check with below field: - cp_pack_total_block_count - blkaddr of data/node - extent info - Overview BUG() in verify_block_addr() when writing to a corrupted f2fs image - Reproduce (4.18 upstream kernel) - POC (poc.c) static void activity(char *mpoint) { char *foo_bar_baz; int err; static int buf[8192]; memset(buf, 0, sizeof(buf)); err = asprintf(&foo_bar_baz, "%s/foo/bar/baz", mpoint); int fd = open(foo_bar_baz, O_RDWR | O_TRUNC, 0777); if (fd >= 0) { write(fd, (char *)buf, sizeof(buf)); fdatasync(fd); close(fd); } } int main(int argc, char *argv[]) { activity(argv[1]); return 0; } - Kernel message [ 689.349473] F2FS-fs (loop0): Mounted with checkpoint version = 3 [ 699.728662] WARNING: CPU: 0 PID: 1309 at fs/f2fs/segment.c:2860 f2fs_inplace_write_data+0x232/0x240 [ 699.728670] Modules linked in: snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_pcm snd_timer snd mac_hid i2c_piix4 soundcore ib_iser rdma_cm iw_cm ib_cm ib_core iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx raid1 raid0 multipath linear 8139too crct10dif_pclmul crc32_pclmul qxl drm_kms_helper syscopyarea aesni_intel sysfillrect sysimgblt fb_sys_fops ttm drm aes_x86_64 crypto_simd cryptd 8139cp glue_helper mii pata_acpi floppy [ 699.729056] CPU: 0 PID: 1309 Comm: a.out Not tainted 4.18.0-rc1+ #4 [ 699.729064] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.729074] RIP: 0010:f2fs_inplace_write_data+0x232/0x240 [ 699.729076] Code: ff e9 cf fe ff ff 49 8d 7d 10 e8 39 45 ad ff 4d 8b 7d 10 be 04 00 00 00 49 8d 7f 48 e8 07 49 ad ff 45 8b 7f 48 e9 fb fe ff ff <0f> 0b f0 41 80 4d 48 04 e9 65 fe ff ff 90 66 66 66 66 90 55 48 8d [ 699.729130] RSP: 0018:ffff8801f43af568 EFLAGS: 00010202 [ 699.729139] RAX: 000000000000003f RBX: ffff8801f43af7b8 RCX: ffffffffb88c9113 [ 699.729142] RDX: 0000000000000003 RSI: dffffc0000000000 RDI: ffff8802024e5540 [ 699.729144] RBP: ffff8801f43af590 R08: 0000000000000009 R09: ffffffffffffffe8 [ 699.729147] R10: 0000000000000001 R11: ffffed0039b0596a R12: ffff8802024e5540 [ 699.729149] R13: ffff8801f0335500 R14: ffff8801e3e7a700 R15: ffff8801e1ee4450 [ 699.729154] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.729156] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.729159] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.729171] Call Trace: [ 699.729192] f2fs_do_write_data_page+0x2e2/0xe00 [ 699.729203] ? f2fs_should_update_outplace+0xd0/0xd0 [ 699.729238] ? memcg_drain_all_list_lrus+0x280/0x280 [ 699.729269] ? __radix_tree_replace+0xa3/0x120 [ 699.729276] __write_data_page+0x5c7/0xe30 [ 699.729291] ? kasan_check_read+0x11/0x20 [ 699.729310] ? page_mapped+0x8a/0x110 [ 699.729321] ? page_mkclean+0xe9/0x160 [ 699.729327] ? f2fs_do_write_data_page+0xe00/0xe00 [ 699.729331] ? invalid_page_referenced_vma+0x130/0x130 [ 699.729345] ? clear_page_dirty_for_io+0x332/0x450 [ 699.729351] f2fs_write_cache_pages+0x4ca/0x860 [ 699.729358] ? __write_data_page+0xe30/0xe30 [ 699.729374] ? percpu_counter_add_batch+0x22/0xa0 [ 699.729380] ? kasan_check_write+0x14/0x20 [ 699.729391] ? _raw_spin_lock+0x17/0x40 [ 699.729403] ? f2fs_mark_inode_dirty_sync.part.18+0x16/0x30 [ 699.729413] ? iov_iter_advance+0x113/0x640 [ 699.729418] ? f2fs_write_end+0x133/0x2e0 [ 699.729423] ? balance_dirty_pages_ratelimited+0x239/0x640 [ 699.729428] f2fs_write_data_pages+0x329/0x520 [ 699.729433] ? generic_perform_write+0x250/0x320 [ 699.729438] ? f2fs_write_cache_pages+0x860/0x860 [ 699.729454] ? current_time+0x110/0x110 [ 699.729459] ? f2fs_preallocate_blocks+0x1ef/0x370 [ 699.729464] do_writepages+0x37/0xb0 [ 699.729468] ? f2fs_write_cache_pages+0x860/0x860 [ 699.729472] ? do_writepages+0x37/0xb0 [ 699.729478] __filemap_fdatawrite_range+0x19a/0x1f0 [ 699.729483] ? delete_from_page_cache_batch+0x4e0/0x4e0 [ 699.729496] ? __vfs_write+0x2b2/0x410 [ 699.729501] file_write_and_wait_range+0x66/0xb0 [ 699.729506] f2fs_do_sync_file+0x1f9/0xd90 [ 699.729511] ? truncate_partial_data_page+0x290/0x290 [ 699.729521] ? __sb_end_write+0x30/0x50 [ 699.729526] ? vfs_write+0x20f/0x260 [ 699.729530] f2fs_sync_file+0x9a/0xb0 [ 699.729534] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.729548] vfs_fsync_range+0x68/0x100 [ 699.729554] ? __fget_light+0xc9/0xe0 [ 699.729558] do_fsync+0x3d/0x70 [ 699.729562] __x64_sys_fdatasync+0x24/0x30 [ 699.729585] do_syscall_64+0x78/0x170 [ 699.729595] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 699.729613] RIP: 0033:0x7f9bf930d800 [ 699.729615] Code: 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 83 3d 49 bf 2c 00 00 75 10 b8 4b 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 be 78 01 00 48 89 04 24 [ 699.729668] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.729673] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.729675] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.729678] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.729680] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.729683] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.729687] ---[ end trace 4ce02f25ff7d3df5 ]--- [ 699.729782] ------------[ cut here ]------------ [ 699.729785] kernel BUG at fs/f2fs/segment.h:654! [ 699.731055] invalid opcode: 0000 [#1] SMP KASAN PTI [ 699.732104] CPU: 0 PID: 1309 Comm: a.out Tainted: G W 4.18.0-rc1+ #4 [ 699.733684] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.735611] RIP: 0010:f2fs_submit_page_bio+0x29b/0x730 [ 699.736649] Code: 54 49 8d bd 18 04 00 00 e8 b2 59 af ff 41 8b 8d 18 04 00 00 8b 45 b8 41 d3 e6 44 01 f0 4c 8d 73 14 41 39 c7 0f 82 37 fe ff ff <0f> 0b 65 8b 05 2c 04 77 47 89 c0 48 0f a3 05 52 c1 d5 01 0f 92 c0 [ 699.740524] RSP: 0018:ffff8801f43af508 EFLAGS: 00010283 [ 699.741573] RAX: 0000000000000000 RBX: ffff8801f43af7b8 RCX: ffffffffb88a7cef [ 699.743006] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8801e3e7a64c [ 699.744426] RBP: ffff8801f43af558 R08: ffffed003e066b55 R09: ffffed003e066b55 [ 699.745833] R10: 0000000000000001 R11: ffffed003e066b54 R12: ffffea0007876940 [ 699.747256] R13: ffff8801f0335500 R14: ffff8801e3e7a600 R15: 0000000000000001 [ 699.748683] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.750293] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.751462] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.752874] Call Trace: [ 699.753386] ? f2fs_inplace_write_data+0x93/0x240 [ 699.754341] f2fs_inplace_write_data+0xd2/0x240 [ 699.755271] f2fs_do_write_data_page+0x2e2/0xe00 [ 699.756214] ? f2fs_should_update_outplace+0xd0/0xd0 [ 699.757215] ? memcg_drain_all_list_lrus+0x280/0x280 [ 699.758209] ? __radix_tree_replace+0xa3/0x120 [ 699.759164] __write_data_page+0x5c7/0xe30 [ 699.760002] ? kasan_check_read+0x11/0x20 [ 699.760823] ? page_mapped+0x8a/0x110 [ 699.761573] ? page_mkclean+0xe9/0x160 [ 699.762345] ? f2fs_do_write_data_page+0xe00/0xe00 [ 699.763332] ? invalid_page_referenced_vma+0x130/0x130 [ 699.764374] ? clear_page_dirty_for_io+0x332/0x450 [ 699.765347] f2fs_write_cache_pages+0x4ca/0x860 [ 699.766276] ? __write_data_page+0xe30/0xe30 [ 699.767161] ? percpu_counter_add_batch+0x22/0xa0 [ 699.768112] ? kasan_check_write+0x14/0x20 [ 699.768951] ? _raw_spin_lock+0x17/0x40 [ 699.769739] ? f2fs_mark_inode_dirty_sync.part.18+0x16/0x30 [ 699.770885] ? iov_iter_advance+0x113/0x640 [ 699.771743] ? f2fs_write_end+0x133/0x2e0 [ 699.772569] ? balance_dirty_pages_ratelimited+0x239/0x640 [ 699.773680] f2fs_write_data_pages+0x329/0x520 [ 699.774603] ? generic_perform_write+0x250/0x320 [ 699.775544] ? f2fs_write_cache_pages+0x860/0x860 [ 699.776510] ? current_time+0x110/0x110 [ 699.777299] ? f2fs_preallocate_blocks+0x1ef/0x370 [ 699.778279] do_writepages+0x37/0xb0 [ 699.779026] ? f2fs_write_cache_pages+0x860/0x860 [ 699.779978] ? do_writepages+0x37/0xb0 [ 699.780755] __filemap_fdatawrite_range+0x19a/0x1f0 [ 699.781746] ? delete_from_page_cache_batch+0x4e0/0x4e0 [ 699.782820] ? __vfs_write+0x2b2/0x410 [ 699.783597] file_write_and_wait_range+0x66/0xb0 [ 699.784540] f2fs_do_sync_file+0x1f9/0xd90 [ 699.785381] ? truncate_partial_data_page+0x290/0x290 [ 699.786415] ? __sb_end_write+0x30/0x50 [ 699.787204] ? vfs_write+0x20f/0x260 [ 699.787941] f2fs_sync_file+0x9a/0xb0 [ 699.788694] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.789572] vfs_fsync_range+0x68/0x100 [ 699.790360] ? __fget_light+0xc9/0xe0 [ 699.791128] do_fsync+0x3d/0x70 [ 699.791779] __x64_sys_fdatasync+0x24/0x30 [ 699.792614] do_syscall_64+0x78/0x170 [ 699.793371] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 699.794406] RIP: 0033:0x7f9bf930d800 [ 699.795134] Code: 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 83 3d 49 bf 2c 00 00 75 10 b8 4b 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 be 78 01 00 48 89 04 24 [ 699.798960] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.800483] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.801923] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.803373] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.804798] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.806233] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.807667] Modules linked in: snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_pcm snd_timer snd mac_hid i2c_piix4 soundcore ib_iser rdma_cm iw_cm ib_cm ib_core iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx raid1 raid0 multipath linear 8139too crct10dif_pclmul crc32_pclmul qxl drm_kms_helper syscopyarea aesni_intel sysfillrect sysimgblt fb_sys_fops ttm drm aes_x86_64 crypto_simd cryptd 8139cp glue_helper mii pata_acpi floppy [ 699.817079] ---[ end trace 4ce02f25ff7d3df6 ]--- [ 699.818068] RIP: 0010:f2fs_submit_page_bio+0x29b/0x730 [ 699.819114] Code: 54 49 8d bd 18 04 00 00 e8 b2 59 af ff 41 8b 8d 18 04 00 00 8b 45 b8 41 d3 e6 44 01 f0 4c 8d 73 14 41 39 c7 0f 82 37 fe ff ff <0f> 0b 65 8b 05 2c 04 77 47 89 c0 48 0f a3 05 52 c1 d5 01 0f 92 c0 [ 699.822919] RSP: 0018:ffff8801f43af508 EFLAGS: 00010283 [ 699.823977] RAX: 0000000000000000 RBX: ffff8801f43af7b8 RCX: ffffffffb88a7cef [ 699.825436] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8801e3e7a64c [ 699.826881] RBP: ffff8801f43af558 R08: ffffed003e066b55 R09: ffffed003e066b55 [ 699.828292] R10: 0000000000000001 R11: ffffed003e066b54 R12: ffffea0007876940 [ 699.829750] R13: ffff8801f0335500 R14: ffff8801e3e7a600 R15: 0000000000000001 [ 699.831192] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.832793] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.833981] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.835556] ================================================================== [ 699.837029] BUG: KASAN: stack-out-of-bounds in update_stack_state+0x38c/0x3e0 [ 699.838462] Read of size 8 at addr ffff8801f43af970 by task a.out/1309 [ 699.840086] CPU: 0 PID: 1309 Comm: a.out Tainted: G D W 4.18.0-rc1+ #4 [ 699.841603] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.843475] Call Trace: [ 699.843982] dump_stack+0x7b/0xb5 [ 699.844661] print_address_description+0x70/0x290 [ 699.845607] kasan_report+0x291/0x390 [ 699.846351] ? update_stack_state+0x38c/0x3e0 [ 699.853831] __asan_load8+0x54/0x90 [ 699.854569] update_stack_state+0x38c/0x3e0 [ 699.855428] ? __read_once_size_nocheck.constprop.7+0x20/0x20 [ 699.856601] ? __save_stack_trace+0x5e/0x100 [ 699.857476] unwind_next_frame.part.5+0x18e/0x490 [ 699.858448] ? unwind_dump+0x290/0x290 [ 699.859217] ? clear_page_dirty_for_io+0x332/0x450 [ 699.860185] __unwind_start+0x106/0x190 [ 699.860974] __save_stack_trace+0x5e/0x100 [ 699.861808] ? __save_stack_trace+0x5e/0x100 [ 699.862691] ? unlink_anon_vmas+0xba/0x2c0 [ 699.863525] save_stack_trace+0x1f/0x30 [ 699.864312] save_stack+0x46/0xd0 [ 699.864993] ? __alloc_pages_slowpath+0x1420/0x1420 [ 699.865990] ? flush_tlb_mm_range+0x15e/0x220 [ 699.866889] ? kasan_check_write+0x14/0x20 [ 699.867724] ? __dec_node_state+0x92/0xb0 [ 699.868543] ? lock_page_memcg+0x85/0xf0 [ 699.869350] ? unlock_page_memcg+0x16/0x80 [ 699.870185] ? page_remove_rmap+0x198/0x520 [ 699.871048] ? mark_page_accessed+0x133/0x200 [ 699.871930] ? _cond_resched+0x1a/0x50 [ 699.872700] ? unmap_page_range+0xcd4/0xe50 [ 699.873551] ? rb_next+0x58/0x80 [ 699.874217] ? rb_next+0x58/0x80 [ 699.874895] __kasan_slab_free+0x13c/0x1a0 [ 699.875734] ? unlink_anon_vmas+0xba/0x2c0 [ 699.876563] kasan_slab_free+0xe/0x10 [ 699.877315] kmem_cache_free+0x89/0x1e0 [ 699.878095] unlink_anon_vmas+0xba/0x2c0 [ 699.878913] free_pgtables+0x101/0x1b0 [ 699.879677] exit_mmap+0x146/0x2a0 [ 699.880378] ? __ia32_sys_munmap+0x50/0x50 [ 699.881214] ? kasan_check_read+0x11/0x20 [ 699.882052] ? mm_update_next_owner+0x322/0x380 [ 699.882985] mmput+0x8b/0x1d0 [ 699.883602] do_exit+0x43a/0x1390 [ 699.884288] ? mm_update_next_owner+0x380/0x380 [ 699.885212] ? f2fs_sync_file+0x9a/0xb0 [ 699.885995] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.886877] ? vfs_fsync_range+0x68/0x100 [ 699.887694] ? __fget_light+0xc9/0xe0 [ 699.888442] ? do_fsync+0x3d/0x70 [ 699.889118] ? __x64_sys_fdatasync+0x24/0x30 [ 699.889996] rewind_stack_do_exit+0x17/0x20 [ 699.890860] RIP: 0033:0x7f9bf930d800 [ 699.891585] Code: Bad RIP value. [ 699.892268] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.893781] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.895220] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.896643] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.898069] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.899505] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.901241] The buggy address belongs to the page: [ 699.902215] page:ffffea0007d0ebc0 count:0 mapcount:0 mapping:0000000000000000 index:0x0 [ 699.903811] flags: 0x2ffff0000000000() [ 699.904585] raw: 02ffff0000000000 0000000000000000 ffffffff07d00101 0000000000000000 [ 699.906125] raw: 0000000000000000 0000000000240000 00000000ffffffff 0000000000000000 [ 699.907673] page dumped because: kasan: bad access detected [ 699.909108] Memory state around the buggy address: [ 699.910077] ffff8801f43af800: 00 f1 f1 f1 f1 00 f4 f4 f4 f3 f3 f3 f3 00 00 00 [ 699.911528] ffff8801f43af880: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 699.912953] >ffff8801f43af900: 00 00 00 00 00 00 00 00 f1 01 f4 f4 f4 f2 f2 f2 [ 699.914392] ^ [ 699.915758] ffff8801f43af980: f2 00 f4 f4 00 00 00 00 f2 00 00 00 00 00 00 00 [ 699.917193] ffff8801f43afa00: 00 00 00 00 00 00 00 00 00 f3 f3 f3 00 00 00 00 [ 699.918634] ================================================================== - Location https://elixir.bootlin.com/linux/v4.18-rc1/source/fs/f2fs/segment.h#L644 Reported-by Wen Xu <wen.xu@gatech.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-08-01 14:13:44 +03:00
if (!f2fs_is_valid_blkaddr(fio->sbi, fio->old_blkaddr,
f2fs: introduce DATA_GENERIC_ENHANCE Previously, f2fs_is_valid_blkaddr(, blkaddr, DATA_GENERIC) will check whether @blkaddr locates in main area or not. That check is weak, since the block address in range of main area can point to the address which is not valid in segment info table, and we can not detect such condition, we may suffer worse corruption as system continues running. So this patch introduce DATA_GENERIC_ENHANCE to enhance the sanity check which trigger SIT bitmap check rather than only range check. This patch did below changes as wel: - set SBI_NEED_FSCK in f2fs_is_valid_blkaddr(). - get rid of is_valid_data_blkaddr() to avoid panic if blkaddr is invalid. - introduce verify_fio_blkaddr() to wrap fio {new,old}_blkaddr validation check. - spread blkaddr check in: * f2fs_get_node_info() * __read_out_blkaddrs() * f2fs_submit_page_read() * ra_data_block() * do_recover_data() This patch can fix bug reported from bugzilla below: https://bugzilla.kernel.org/show_bug.cgi?id=203215 https://bugzilla.kernel.org/show_bug.cgi?id=203223 https://bugzilla.kernel.org/show_bug.cgi?id=203231 https://bugzilla.kernel.org/show_bug.cgi?id=203235 https://bugzilla.kernel.org/show_bug.cgi?id=203241 = Update by Jaegeuk Kim = DATA_GENERIC_ENHANCE enhanced to validate block addresses on read/write paths. But, xfstest/generic/446 compalins some generated kernel messages saying invalid bitmap was detected when reading a block. The reaons is, when we get the block addresses from extent_cache, there is no lock to synchronize it from truncating the blocks in parallel. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-15 10:26:32 +03:00
DATA_GENERIC_ENHANCE))
return -EFSCORRUPTED;
f2fs: fix to do sanity check with block address in main area This patch add to do sanity check with below field: - cp_pack_total_block_count - blkaddr of data/node - extent info - Overview BUG() in verify_block_addr() when writing to a corrupted f2fs image - Reproduce (4.18 upstream kernel) - POC (poc.c) static void activity(char *mpoint) { char *foo_bar_baz; int err; static int buf[8192]; memset(buf, 0, sizeof(buf)); err = asprintf(&foo_bar_baz, "%s/foo/bar/baz", mpoint); int fd = open(foo_bar_baz, O_RDWR | O_TRUNC, 0777); if (fd >= 0) { write(fd, (char *)buf, sizeof(buf)); fdatasync(fd); close(fd); } } int main(int argc, char *argv[]) { activity(argv[1]); return 0; } - Kernel message [ 689.349473] F2FS-fs (loop0): Mounted with checkpoint version = 3 [ 699.728662] WARNING: CPU: 0 PID: 1309 at fs/f2fs/segment.c:2860 f2fs_inplace_write_data+0x232/0x240 [ 699.728670] Modules linked in: snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_pcm snd_timer snd mac_hid i2c_piix4 soundcore ib_iser rdma_cm iw_cm ib_cm ib_core iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx raid1 raid0 multipath linear 8139too crct10dif_pclmul crc32_pclmul qxl drm_kms_helper syscopyarea aesni_intel sysfillrect sysimgblt fb_sys_fops ttm drm aes_x86_64 crypto_simd cryptd 8139cp glue_helper mii pata_acpi floppy [ 699.729056] CPU: 0 PID: 1309 Comm: a.out Not tainted 4.18.0-rc1+ #4 [ 699.729064] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.729074] RIP: 0010:f2fs_inplace_write_data+0x232/0x240 [ 699.729076] Code: ff e9 cf fe ff ff 49 8d 7d 10 e8 39 45 ad ff 4d 8b 7d 10 be 04 00 00 00 49 8d 7f 48 e8 07 49 ad ff 45 8b 7f 48 e9 fb fe ff ff <0f> 0b f0 41 80 4d 48 04 e9 65 fe ff ff 90 66 66 66 66 90 55 48 8d [ 699.729130] RSP: 0018:ffff8801f43af568 EFLAGS: 00010202 [ 699.729139] RAX: 000000000000003f RBX: ffff8801f43af7b8 RCX: ffffffffb88c9113 [ 699.729142] RDX: 0000000000000003 RSI: dffffc0000000000 RDI: ffff8802024e5540 [ 699.729144] RBP: ffff8801f43af590 R08: 0000000000000009 R09: ffffffffffffffe8 [ 699.729147] R10: 0000000000000001 R11: ffffed0039b0596a R12: ffff8802024e5540 [ 699.729149] R13: ffff8801f0335500 R14: ffff8801e3e7a700 R15: ffff8801e1ee4450 [ 699.729154] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.729156] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.729159] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.729171] Call Trace: [ 699.729192] f2fs_do_write_data_page+0x2e2/0xe00 [ 699.729203] ? f2fs_should_update_outplace+0xd0/0xd0 [ 699.729238] ? memcg_drain_all_list_lrus+0x280/0x280 [ 699.729269] ? __radix_tree_replace+0xa3/0x120 [ 699.729276] __write_data_page+0x5c7/0xe30 [ 699.729291] ? kasan_check_read+0x11/0x20 [ 699.729310] ? page_mapped+0x8a/0x110 [ 699.729321] ? page_mkclean+0xe9/0x160 [ 699.729327] ? f2fs_do_write_data_page+0xe00/0xe00 [ 699.729331] ? invalid_page_referenced_vma+0x130/0x130 [ 699.729345] ? clear_page_dirty_for_io+0x332/0x450 [ 699.729351] f2fs_write_cache_pages+0x4ca/0x860 [ 699.729358] ? __write_data_page+0xe30/0xe30 [ 699.729374] ? percpu_counter_add_batch+0x22/0xa0 [ 699.729380] ? kasan_check_write+0x14/0x20 [ 699.729391] ? _raw_spin_lock+0x17/0x40 [ 699.729403] ? f2fs_mark_inode_dirty_sync.part.18+0x16/0x30 [ 699.729413] ? iov_iter_advance+0x113/0x640 [ 699.729418] ? f2fs_write_end+0x133/0x2e0 [ 699.729423] ? balance_dirty_pages_ratelimited+0x239/0x640 [ 699.729428] f2fs_write_data_pages+0x329/0x520 [ 699.729433] ? generic_perform_write+0x250/0x320 [ 699.729438] ? f2fs_write_cache_pages+0x860/0x860 [ 699.729454] ? current_time+0x110/0x110 [ 699.729459] ? f2fs_preallocate_blocks+0x1ef/0x370 [ 699.729464] do_writepages+0x37/0xb0 [ 699.729468] ? f2fs_write_cache_pages+0x860/0x860 [ 699.729472] ? do_writepages+0x37/0xb0 [ 699.729478] __filemap_fdatawrite_range+0x19a/0x1f0 [ 699.729483] ? delete_from_page_cache_batch+0x4e0/0x4e0 [ 699.729496] ? __vfs_write+0x2b2/0x410 [ 699.729501] file_write_and_wait_range+0x66/0xb0 [ 699.729506] f2fs_do_sync_file+0x1f9/0xd90 [ 699.729511] ? truncate_partial_data_page+0x290/0x290 [ 699.729521] ? __sb_end_write+0x30/0x50 [ 699.729526] ? vfs_write+0x20f/0x260 [ 699.729530] f2fs_sync_file+0x9a/0xb0 [ 699.729534] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.729548] vfs_fsync_range+0x68/0x100 [ 699.729554] ? __fget_light+0xc9/0xe0 [ 699.729558] do_fsync+0x3d/0x70 [ 699.729562] __x64_sys_fdatasync+0x24/0x30 [ 699.729585] do_syscall_64+0x78/0x170 [ 699.729595] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 699.729613] RIP: 0033:0x7f9bf930d800 [ 699.729615] Code: 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 83 3d 49 bf 2c 00 00 75 10 b8 4b 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 be 78 01 00 48 89 04 24 [ 699.729668] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.729673] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.729675] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.729678] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.729680] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.729683] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.729687] ---[ end trace 4ce02f25ff7d3df5 ]--- [ 699.729782] ------------[ cut here ]------------ [ 699.729785] kernel BUG at fs/f2fs/segment.h:654! [ 699.731055] invalid opcode: 0000 [#1] SMP KASAN PTI [ 699.732104] CPU: 0 PID: 1309 Comm: a.out Tainted: G W 4.18.0-rc1+ #4 [ 699.733684] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.735611] RIP: 0010:f2fs_submit_page_bio+0x29b/0x730 [ 699.736649] Code: 54 49 8d bd 18 04 00 00 e8 b2 59 af ff 41 8b 8d 18 04 00 00 8b 45 b8 41 d3 e6 44 01 f0 4c 8d 73 14 41 39 c7 0f 82 37 fe ff ff <0f> 0b 65 8b 05 2c 04 77 47 89 c0 48 0f a3 05 52 c1 d5 01 0f 92 c0 [ 699.740524] RSP: 0018:ffff8801f43af508 EFLAGS: 00010283 [ 699.741573] RAX: 0000000000000000 RBX: ffff8801f43af7b8 RCX: ffffffffb88a7cef [ 699.743006] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8801e3e7a64c [ 699.744426] RBP: ffff8801f43af558 R08: ffffed003e066b55 R09: ffffed003e066b55 [ 699.745833] R10: 0000000000000001 R11: ffffed003e066b54 R12: ffffea0007876940 [ 699.747256] R13: ffff8801f0335500 R14: ffff8801e3e7a600 R15: 0000000000000001 [ 699.748683] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.750293] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.751462] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.752874] Call Trace: [ 699.753386] ? f2fs_inplace_write_data+0x93/0x240 [ 699.754341] f2fs_inplace_write_data+0xd2/0x240 [ 699.755271] f2fs_do_write_data_page+0x2e2/0xe00 [ 699.756214] ? f2fs_should_update_outplace+0xd0/0xd0 [ 699.757215] ? memcg_drain_all_list_lrus+0x280/0x280 [ 699.758209] ? __radix_tree_replace+0xa3/0x120 [ 699.759164] __write_data_page+0x5c7/0xe30 [ 699.760002] ? kasan_check_read+0x11/0x20 [ 699.760823] ? page_mapped+0x8a/0x110 [ 699.761573] ? page_mkclean+0xe9/0x160 [ 699.762345] ? f2fs_do_write_data_page+0xe00/0xe00 [ 699.763332] ? invalid_page_referenced_vma+0x130/0x130 [ 699.764374] ? clear_page_dirty_for_io+0x332/0x450 [ 699.765347] f2fs_write_cache_pages+0x4ca/0x860 [ 699.766276] ? __write_data_page+0xe30/0xe30 [ 699.767161] ? percpu_counter_add_batch+0x22/0xa0 [ 699.768112] ? kasan_check_write+0x14/0x20 [ 699.768951] ? _raw_spin_lock+0x17/0x40 [ 699.769739] ? f2fs_mark_inode_dirty_sync.part.18+0x16/0x30 [ 699.770885] ? iov_iter_advance+0x113/0x640 [ 699.771743] ? f2fs_write_end+0x133/0x2e0 [ 699.772569] ? balance_dirty_pages_ratelimited+0x239/0x640 [ 699.773680] f2fs_write_data_pages+0x329/0x520 [ 699.774603] ? generic_perform_write+0x250/0x320 [ 699.775544] ? f2fs_write_cache_pages+0x860/0x860 [ 699.776510] ? current_time+0x110/0x110 [ 699.777299] ? f2fs_preallocate_blocks+0x1ef/0x370 [ 699.778279] do_writepages+0x37/0xb0 [ 699.779026] ? f2fs_write_cache_pages+0x860/0x860 [ 699.779978] ? do_writepages+0x37/0xb0 [ 699.780755] __filemap_fdatawrite_range+0x19a/0x1f0 [ 699.781746] ? delete_from_page_cache_batch+0x4e0/0x4e0 [ 699.782820] ? __vfs_write+0x2b2/0x410 [ 699.783597] file_write_and_wait_range+0x66/0xb0 [ 699.784540] f2fs_do_sync_file+0x1f9/0xd90 [ 699.785381] ? truncate_partial_data_page+0x290/0x290 [ 699.786415] ? __sb_end_write+0x30/0x50 [ 699.787204] ? vfs_write+0x20f/0x260 [ 699.787941] f2fs_sync_file+0x9a/0xb0 [ 699.788694] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.789572] vfs_fsync_range+0x68/0x100 [ 699.790360] ? __fget_light+0xc9/0xe0 [ 699.791128] do_fsync+0x3d/0x70 [ 699.791779] __x64_sys_fdatasync+0x24/0x30 [ 699.792614] do_syscall_64+0x78/0x170 [ 699.793371] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 699.794406] RIP: 0033:0x7f9bf930d800 [ 699.795134] Code: 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 83 3d 49 bf 2c 00 00 75 10 b8 4b 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 be 78 01 00 48 89 04 24 [ 699.798960] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.800483] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.801923] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.803373] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.804798] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.806233] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.807667] Modules linked in: snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_pcm snd_timer snd mac_hid i2c_piix4 soundcore ib_iser rdma_cm iw_cm ib_cm ib_core iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx raid1 raid0 multipath linear 8139too crct10dif_pclmul crc32_pclmul qxl drm_kms_helper syscopyarea aesni_intel sysfillrect sysimgblt fb_sys_fops ttm drm aes_x86_64 crypto_simd cryptd 8139cp glue_helper mii pata_acpi floppy [ 699.817079] ---[ end trace 4ce02f25ff7d3df6 ]--- [ 699.818068] RIP: 0010:f2fs_submit_page_bio+0x29b/0x730 [ 699.819114] Code: 54 49 8d bd 18 04 00 00 e8 b2 59 af ff 41 8b 8d 18 04 00 00 8b 45 b8 41 d3 e6 44 01 f0 4c 8d 73 14 41 39 c7 0f 82 37 fe ff ff <0f> 0b 65 8b 05 2c 04 77 47 89 c0 48 0f a3 05 52 c1 d5 01 0f 92 c0 [ 699.822919] RSP: 0018:ffff8801f43af508 EFLAGS: 00010283 [ 699.823977] RAX: 0000000000000000 RBX: ffff8801f43af7b8 RCX: ffffffffb88a7cef [ 699.825436] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8801e3e7a64c [ 699.826881] RBP: ffff8801f43af558 R08: ffffed003e066b55 R09: ffffed003e066b55 [ 699.828292] R10: 0000000000000001 R11: ffffed003e066b54 R12: ffffea0007876940 [ 699.829750] R13: ffff8801f0335500 R14: ffff8801e3e7a600 R15: 0000000000000001 [ 699.831192] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.832793] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.833981] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.835556] ================================================================== [ 699.837029] BUG: KASAN: stack-out-of-bounds in update_stack_state+0x38c/0x3e0 [ 699.838462] Read of size 8 at addr ffff8801f43af970 by task a.out/1309 [ 699.840086] CPU: 0 PID: 1309 Comm: a.out Tainted: G D W 4.18.0-rc1+ #4 [ 699.841603] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.843475] Call Trace: [ 699.843982] dump_stack+0x7b/0xb5 [ 699.844661] print_address_description+0x70/0x290 [ 699.845607] kasan_report+0x291/0x390 [ 699.846351] ? update_stack_state+0x38c/0x3e0 [ 699.853831] __asan_load8+0x54/0x90 [ 699.854569] update_stack_state+0x38c/0x3e0 [ 699.855428] ? __read_once_size_nocheck.constprop.7+0x20/0x20 [ 699.856601] ? __save_stack_trace+0x5e/0x100 [ 699.857476] unwind_next_frame.part.5+0x18e/0x490 [ 699.858448] ? unwind_dump+0x290/0x290 [ 699.859217] ? clear_page_dirty_for_io+0x332/0x450 [ 699.860185] __unwind_start+0x106/0x190 [ 699.860974] __save_stack_trace+0x5e/0x100 [ 699.861808] ? __save_stack_trace+0x5e/0x100 [ 699.862691] ? unlink_anon_vmas+0xba/0x2c0 [ 699.863525] save_stack_trace+0x1f/0x30 [ 699.864312] save_stack+0x46/0xd0 [ 699.864993] ? __alloc_pages_slowpath+0x1420/0x1420 [ 699.865990] ? flush_tlb_mm_range+0x15e/0x220 [ 699.866889] ? kasan_check_write+0x14/0x20 [ 699.867724] ? __dec_node_state+0x92/0xb0 [ 699.868543] ? lock_page_memcg+0x85/0xf0 [ 699.869350] ? unlock_page_memcg+0x16/0x80 [ 699.870185] ? page_remove_rmap+0x198/0x520 [ 699.871048] ? mark_page_accessed+0x133/0x200 [ 699.871930] ? _cond_resched+0x1a/0x50 [ 699.872700] ? unmap_page_range+0xcd4/0xe50 [ 699.873551] ? rb_next+0x58/0x80 [ 699.874217] ? rb_next+0x58/0x80 [ 699.874895] __kasan_slab_free+0x13c/0x1a0 [ 699.875734] ? unlink_anon_vmas+0xba/0x2c0 [ 699.876563] kasan_slab_free+0xe/0x10 [ 699.877315] kmem_cache_free+0x89/0x1e0 [ 699.878095] unlink_anon_vmas+0xba/0x2c0 [ 699.878913] free_pgtables+0x101/0x1b0 [ 699.879677] exit_mmap+0x146/0x2a0 [ 699.880378] ? __ia32_sys_munmap+0x50/0x50 [ 699.881214] ? kasan_check_read+0x11/0x20 [ 699.882052] ? mm_update_next_owner+0x322/0x380 [ 699.882985] mmput+0x8b/0x1d0 [ 699.883602] do_exit+0x43a/0x1390 [ 699.884288] ? mm_update_next_owner+0x380/0x380 [ 699.885212] ? f2fs_sync_file+0x9a/0xb0 [ 699.885995] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.886877] ? vfs_fsync_range+0x68/0x100 [ 699.887694] ? __fget_light+0xc9/0xe0 [ 699.888442] ? do_fsync+0x3d/0x70 [ 699.889118] ? __x64_sys_fdatasync+0x24/0x30 [ 699.889996] rewind_stack_do_exit+0x17/0x20 [ 699.890860] RIP: 0033:0x7f9bf930d800 [ 699.891585] Code: Bad RIP value. [ 699.892268] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.893781] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.895220] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.896643] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.898069] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.899505] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.901241] The buggy address belongs to the page: [ 699.902215] page:ffffea0007d0ebc0 count:0 mapcount:0 mapping:0000000000000000 index:0x0 [ 699.903811] flags: 0x2ffff0000000000() [ 699.904585] raw: 02ffff0000000000 0000000000000000 ffffffff07d00101 0000000000000000 [ 699.906125] raw: 0000000000000000 0000000000240000 00000000ffffffff 0000000000000000 [ 699.907673] page dumped because: kasan: bad access detected [ 699.909108] Memory state around the buggy address: [ 699.910077] ffff8801f43af800: 00 f1 f1 f1 f1 00 f4 f4 f4 f3 f3 f3 f3 00 00 00 [ 699.911528] ffff8801f43af880: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 699.912953] >ffff8801f43af900: 00 00 00 00 00 00 00 00 f1 01 f4 f4 f4 f2 f2 f2 [ 699.914392] ^ [ 699.915758] ffff8801f43af980: f2 00 f4 f4 00 00 00 00 f2 00 00 00 00 00 00 00 [ 699.917193] ffff8801f43afa00: 00 00 00 00 00 00 00 00 00 f3 f3 f3 00 00 00 00 [ 699.918634] ================================================================== - Location https://elixir.bootlin.com/linux/v4.18-rc1/source/fs/f2fs/segment.h#L644 Reported-by Wen Xu <wen.xu@gatech.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-08-01 14:13:44 +03:00
ipu_force = true;
fio->need_lock = LOCK_DONE;
goto got_it;
}
/* Deadlock due to between page->lock and f2fs_lock_op */
if (fio->need_lock == LOCK_REQ && !f2fs_trylock_op(fio->sbi))
return -EAGAIN;
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 19:20:41 +03:00
err = f2fs_get_dnode_of_data(&dn, page->index, LOOKUP_NODE);
if (err)
goto out;
fio->old_blkaddr = dn.data_blkaddr;
/* This page is already truncated */
if (fio->old_blkaddr == NULL_ADDR) {
ClearPageUptodate(page);
clear_cold_data(page);
goto out_writepage;
}
got_it:
f2fs: fix to do sanity check with block address in main area This patch add to do sanity check with below field: - cp_pack_total_block_count - blkaddr of data/node - extent info - Overview BUG() in verify_block_addr() when writing to a corrupted f2fs image - Reproduce (4.18 upstream kernel) - POC (poc.c) static void activity(char *mpoint) { char *foo_bar_baz; int err; static int buf[8192]; memset(buf, 0, sizeof(buf)); err = asprintf(&foo_bar_baz, "%s/foo/bar/baz", mpoint); int fd = open(foo_bar_baz, O_RDWR | O_TRUNC, 0777); if (fd >= 0) { write(fd, (char *)buf, sizeof(buf)); fdatasync(fd); close(fd); } } int main(int argc, char *argv[]) { activity(argv[1]); return 0; } - Kernel message [ 689.349473] F2FS-fs (loop0): Mounted with checkpoint version = 3 [ 699.728662] WARNING: CPU: 0 PID: 1309 at fs/f2fs/segment.c:2860 f2fs_inplace_write_data+0x232/0x240 [ 699.728670] Modules linked in: snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_pcm snd_timer snd mac_hid i2c_piix4 soundcore ib_iser rdma_cm iw_cm ib_cm ib_core iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx raid1 raid0 multipath linear 8139too crct10dif_pclmul crc32_pclmul qxl drm_kms_helper syscopyarea aesni_intel sysfillrect sysimgblt fb_sys_fops ttm drm aes_x86_64 crypto_simd cryptd 8139cp glue_helper mii pata_acpi floppy [ 699.729056] CPU: 0 PID: 1309 Comm: a.out Not tainted 4.18.0-rc1+ #4 [ 699.729064] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.729074] RIP: 0010:f2fs_inplace_write_data+0x232/0x240 [ 699.729076] Code: ff e9 cf fe ff ff 49 8d 7d 10 e8 39 45 ad ff 4d 8b 7d 10 be 04 00 00 00 49 8d 7f 48 e8 07 49 ad ff 45 8b 7f 48 e9 fb fe ff ff <0f> 0b f0 41 80 4d 48 04 e9 65 fe ff ff 90 66 66 66 66 90 55 48 8d [ 699.729130] RSP: 0018:ffff8801f43af568 EFLAGS: 00010202 [ 699.729139] RAX: 000000000000003f RBX: ffff8801f43af7b8 RCX: ffffffffb88c9113 [ 699.729142] RDX: 0000000000000003 RSI: dffffc0000000000 RDI: ffff8802024e5540 [ 699.729144] RBP: ffff8801f43af590 R08: 0000000000000009 R09: ffffffffffffffe8 [ 699.729147] R10: 0000000000000001 R11: ffffed0039b0596a R12: ffff8802024e5540 [ 699.729149] R13: ffff8801f0335500 R14: ffff8801e3e7a700 R15: ffff8801e1ee4450 [ 699.729154] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.729156] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.729159] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.729171] Call Trace: [ 699.729192] f2fs_do_write_data_page+0x2e2/0xe00 [ 699.729203] ? f2fs_should_update_outplace+0xd0/0xd0 [ 699.729238] ? memcg_drain_all_list_lrus+0x280/0x280 [ 699.729269] ? __radix_tree_replace+0xa3/0x120 [ 699.729276] __write_data_page+0x5c7/0xe30 [ 699.729291] ? kasan_check_read+0x11/0x20 [ 699.729310] ? page_mapped+0x8a/0x110 [ 699.729321] ? page_mkclean+0xe9/0x160 [ 699.729327] ? f2fs_do_write_data_page+0xe00/0xe00 [ 699.729331] ? invalid_page_referenced_vma+0x130/0x130 [ 699.729345] ? clear_page_dirty_for_io+0x332/0x450 [ 699.729351] f2fs_write_cache_pages+0x4ca/0x860 [ 699.729358] ? __write_data_page+0xe30/0xe30 [ 699.729374] ? percpu_counter_add_batch+0x22/0xa0 [ 699.729380] ? kasan_check_write+0x14/0x20 [ 699.729391] ? _raw_spin_lock+0x17/0x40 [ 699.729403] ? f2fs_mark_inode_dirty_sync.part.18+0x16/0x30 [ 699.729413] ? iov_iter_advance+0x113/0x640 [ 699.729418] ? f2fs_write_end+0x133/0x2e0 [ 699.729423] ? balance_dirty_pages_ratelimited+0x239/0x640 [ 699.729428] f2fs_write_data_pages+0x329/0x520 [ 699.729433] ? generic_perform_write+0x250/0x320 [ 699.729438] ? f2fs_write_cache_pages+0x860/0x860 [ 699.729454] ? current_time+0x110/0x110 [ 699.729459] ? f2fs_preallocate_blocks+0x1ef/0x370 [ 699.729464] do_writepages+0x37/0xb0 [ 699.729468] ? f2fs_write_cache_pages+0x860/0x860 [ 699.729472] ? do_writepages+0x37/0xb0 [ 699.729478] __filemap_fdatawrite_range+0x19a/0x1f0 [ 699.729483] ? delete_from_page_cache_batch+0x4e0/0x4e0 [ 699.729496] ? __vfs_write+0x2b2/0x410 [ 699.729501] file_write_and_wait_range+0x66/0xb0 [ 699.729506] f2fs_do_sync_file+0x1f9/0xd90 [ 699.729511] ? truncate_partial_data_page+0x290/0x290 [ 699.729521] ? __sb_end_write+0x30/0x50 [ 699.729526] ? vfs_write+0x20f/0x260 [ 699.729530] f2fs_sync_file+0x9a/0xb0 [ 699.729534] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.729548] vfs_fsync_range+0x68/0x100 [ 699.729554] ? __fget_light+0xc9/0xe0 [ 699.729558] do_fsync+0x3d/0x70 [ 699.729562] __x64_sys_fdatasync+0x24/0x30 [ 699.729585] do_syscall_64+0x78/0x170 [ 699.729595] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 699.729613] RIP: 0033:0x7f9bf930d800 [ 699.729615] Code: 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 83 3d 49 bf 2c 00 00 75 10 b8 4b 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 be 78 01 00 48 89 04 24 [ 699.729668] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.729673] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.729675] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.729678] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.729680] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.729683] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.729687] ---[ end trace 4ce02f25ff7d3df5 ]--- [ 699.729782] ------------[ cut here ]------------ [ 699.729785] kernel BUG at fs/f2fs/segment.h:654! [ 699.731055] invalid opcode: 0000 [#1] SMP KASAN PTI [ 699.732104] CPU: 0 PID: 1309 Comm: a.out Tainted: G W 4.18.0-rc1+ #4 [ 699.733684] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.735611] RIP: 0010:f2fs_submit_page_bio+0x29b/0x730 [ 699.736649] Code: 54 49 8d bd 18 04 00 00 e8 b2 59 af ff 41 8b 8d 18 04 00 00 8b 45 b8 41 d3 e6 44 01 f0 4c 8d 73 14 41 39 c7 0f 82 37 fe ff ff <0f> 0b 65 8b 05 2c 04 77 47 89 c0 48 0f a3 05 52 c1 d5 01 0f 92 c0 [ 699.740524] RSP: 0018:ffff8801f43af508 EFLAGS: 00010283 [ 699.741573] RAX: 0000000000000000 RBX: ffff8801f43af7b8 RCX: ffffffffb88a7cef [ 699.743006] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8801e3e7a64c [ 699.744426] RBP: ffff8801f43af558 R08: ffffed003e066b55 R09: ffffed003e066b55 [ 699.745833] R10: 0000000000000001 R11: ffffed003e066b54 R12: ffffea0007876940 [ 699.747256] R13: ffff8801f0335500 R14: ffff8801e3e7a600 R15: 0000000000000001 [ 699.748683] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.750293] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.751462] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.752874] Call Trace: [ 699.753386] ? f2fs_inplace_write_data+0x93/0x240 [ 699.754341] f2fs_inplace_write_data+0xd2/0x240 [ 699.755271] f2fs_do_write_data_page+0x2e2/0xe00 [ 699.756214] ? f2fs_should_update_outplace+0xd0/0xd0 [ 699.757215] ? memcg_drain_all_list_lrus+0x280/0x280 [ 699.758209] ? __radix_tree_replace+0xa3/0x120 [ 699.759164] __write_data_page+0x5c7/0xe30 [ 699.760002] ? kasan_check_read+0x11/0x20 [ 699.760823] ? page_mapped+0x8a/0x110 [ 699.761573] ? page_mkclean+0xe9/0x160 [ 699.762345] ? f2fs_do_write_data_page+0xe00/0xe00 [ 699.763332] ? invalid_page_referenced_vma+0x130/0x130 [ 699.764374] ? clear_page_dirty_for_io+0x332/0x450 [ 699.765347] f2fs_write_cache_pages+0x4ca/0x860 [ 699.766276] ? __write_data_page+0xe30/0xe30 [ 699.767161] ? percpu_counter_add_batch+0x22/0xa0 [ 699.768112] ? kasan_check_write+0x14/0x20 [ 699.768951] ? _raw_spin_lock+0x17/0x40 [ 699.769739] ? f2fs_mark_inode_dirty_sync.part.18+0x16/0x30 [ 699.770885] ? iov_iter_advance+0x113/0x640 [ 699.771743] ? f2fs_write_end+0x133/0x2e0 [ 699.772569] ? balance_dirty_pages_ratelimited+0x239/0x640 [ 699.773680] f2fs_write_data_pages+0x329/0x520 [ 699.774603] ? generic_perform_write+0x250/0x320 [ 699.775544] ? f2fs_write_cache_pages+0x860/0x860 [ 699.776510] ? current_time+0x110/0x110 [ 699.777299] ? f2fs_preallocate_blocks+0x1ef/0x370 [ 699.778279] do_writepages+0x37/0xb0 [ 699.779026] ? f2fs_write_cache_pages+0x860/0x860 [ 699.779978] ? do_writepages+0x37/0xb0 [ 699.780755] __filemap_fdatawrite_range+0x19a/0x1f0 [ 699.781746] ? delete_from_page_cache_batch+0x4e0/0x4e0 [ 699.782820] ? __vfs_write+0x2b2/0x410 [ 699.783597] file_write_and_wait_range+0x66/0xb0 [ 699.784540] f2fs_do_sync_file+0x1f9/0xd90 [ 699.785381] ? truncate_partial_data_page+0x290/0x290 [ 699.786415] ? __sb_end_write+0x30/0x50 [ 699.787204] ? vfs_write+0x20f/0x260 [ 699.787941] f2fs_sync_file+0x9a/0xb0 [ 699.788694] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.789572] vfs_fsync_range+0x68/0x100 [ 699.790360] ? __fget_light+0xc9/0xe0 [ 699.791128] do_fsync+0x3d/0x70 [ 699.791779] __x64_sys_fdatasync+0x24/0x30 [ 699.792614] do_syscall_64+0x78/0x170 [ 699.793371] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 699.794406] RIP: 0033:0x7f9bf930d800 [ 699.795134] Code: 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 83 3d 49 bf 2c 00 00 75 10 b8 4b 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 be 78 01 00 48 89 04 24 [ 699.798960] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.800483] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.801923] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.803373] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.804798] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.806233] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.807667] Modules linked in: snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_pcm snd_timer snd mac_hid i2c_piix4 soundcore ib_iser rdma_cm iw_cm ib_cm ib_core iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx raid1 raid0 multipath linear 8139too crct10dif_pclmul crc32_pclmul qxl drm_kms_helper syscopyarea aesni_intel sysfillrect sysimgblt fb_sys_fops ttm drm aes_x86_64 crypto_simd cryptd 8139cp glue_helper mii pata_acpi floppy [ 699.817079] ---[ end trace 4ce02f25ff7d3df6 ]--- [ 699.818068] RIP: 0010:f2fs_submit_page_bio+0x29b/0x730 [ 699.819114] Code: 54 49 8d bd 18 04 00 00 e8 b2 59 af ff 41 8b 8d 18 04 00 00 8b 45 b8 41 d3 e6 44 01 f0 4c 8d 73 14 41 39 c7 0f 82 37 fe ff ff <0f> 0b 65 8b 05 2c 04 77 47 89 c0 48 0f a3 05 52 c1 d5 01 0f 92 c0 [ 699.822919] RSP: 0018:ffff8801f43af508 EFLAGS: 00010283 [ 699.823977] RAX: 0000000000000000 RBX: ffff8801f43af7b8 RCX: ffffffffb88a7cef [ 699.825436] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8801e3e7a64c [ 699.826881] RBP: ffff8801f43af558 R08: ffffed003e066b55 R09: ffffed003e066b55 [ 699.828292] R10: 0000000000000001 R11: ffffed003e066b54 R12: ffffea0007876940 [ 699.829750] R13: ffff8801f0335500 R14: ffff8801e3e7a600 R15: 0000000000000001 [ 699.831192] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.832793] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.833981] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.835556] ================================================================== [ 699.837029] BUG: KASAN: stack-out-of-bounds in update_stack_state+0x38c/0x3e0 [ 699.838462] Read of size 8 at addr ffff8801f43af970 by task a.out/1309 [ 699.840086] CPU: 0 PID: 1309 Comm: a.out Tainted: G D W 4.18.0-rc1+ #4 [ 699.841603] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.843475] Call Trace: [ 699.843982] dump_stack+0x7b/0xb5 [ 699.844661] print_address_description+0x70/0x290 [ 699.845607] kasan_report+0x291/0x390 [ 699.846351] ? update_stack_state+0x38c/0x3e0 [ 699.853831] __asan_load8+0x54/0x90 [ 699.854569] update_stack_state+0x38c/0x3e0 [ 699.855428] ? __read_once_size_nocheck.constprop.7+0x20/0x20 [ 699.856601] ? __save_stack_trace+0x5e/0x100 [ 699.857476] unwind_next_frame.part.5+0x18e/0x490 [ 699.858448] ? unwind_dump+0x290/0x290 [ 699.859217] ? clear_page_dirty_for_io+0x332/0x450 [ 699.860185] __unwind_start+0x106/0x190 [ 699.860974] __save_stack_trace+0x5e/0x100 [ 699.861808] ? __save_stack_trace+0x5e/0x100 [ 699.862691] ? unlink_anon_vmas+0xba/0x2c0 [ 699.863525] save_stack_trace+0x1f/0x30 [ 699.864312] save_stack+0x46/0xd0 [ 699.864993] ? __alloc_pages_slowpath+0x1420/0x1420 [ 699.865990] ? flush_tlb_mm_range+0x15e/0x220 [ 699.866889] ? kasan_check_write+0x14/0x20 [ 699.867724] ? __dec_node_state+0x92/0xb0 [ 699.868543] ? lock_page_memcg+0x85/0xf0 [ 699.869350] ? unlock_page_memcg+0x16/0x80 [ 699.870185] ? page_remove_rmap+0x198/0x520 [ 699.871048] ? mark_page_accessed+0x133/0x200 [ 699.871930] ? _cond_resched+0x1a/0x50 [ 699.872700] ? unmap_page_range+0xcd4/0xe50 [ 699.873551] ? rb_next+0x58/0x80 [ 699.874217] ? rb_next+0x58/0x80 [ 699.874895] __kasan_slab_free+0x13c/0x1a0 [ 699.875734] ? unlink_anon_vmas+0xba/0x2c0 [ 699.876563] kasan_slab_free+0xe/0x10 [ 699.877315] kmem_cache_free+0x89/0x1e0 [ 699.878095] unlink_anon_vmas+0xba/0x2c0 [ 699.878913] free_pgtables+0x101/0x1b0 [ 699.879677] exit_mmap+0x146/0x2a0 [ 699.880378] ? __ia32_sys_munmap+0x50/0x50 [ 699.881214] ? kasan_check_read+0x11/0x20 [ 699.882052] ? mm_update_next_owner+0x322/0x380 [ 699.882985] mmput+0x8b/0x1d0 [ 699.883602] do_exit+0x43a/0x1390 [ 699.884288] ? mm_update_next_owner+0x380/0x380 [ 699.885212] ? f2fs_sync_file+0x9a/0xb0 [ 699.885995] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.886877] ? vfs_fsync_range+0x68/0x100 [ 699.887694] ? __fget_light+0xc9/0xe0 [ 699.888442] ? do_fsync+0x3d/0x70 [ 699.889118] ? __x64_sys_fdatasync+0x24/0x30 [ 699.889996] rewind_stack_do_exit+0x17/0x20 [ 699.890860] RIP: 0033:0x7f9bf930d800 [ 699.891585] Code: Bad RIP value. [ 699.892268] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.893781] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.895220] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.896643] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.898069] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.899505] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.901241] The buggy address belongs to the page: [ 699.902215] page:ffffea0007d0ebc0 count:0 mapcount:0 mapping:0000000000000000 index:0x0 [ 699.903811] flags: 0x2ffff0000000000() [ 699.904585] raw: 02ffff0000000000 0000000000000000 ffffffff07d00101 0000000000000000 [ 699.906125] raw: 0000000000000000 0000000000240000 00000000ffffffff 0000000000000000 [ 699.907673] page dumped because: kasan: bad access detected [ 699.909108] Memory state around the buggy address: [ 699.910077] ffff8801f43af800: 00 f1 f1 f1 f1 00 f4 f4 f4 f3 f3 f3 f3 00 00 00 [ 699.911528] ffff8801f43af880: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 699.912953] >ffff8801f43af900: 00 00 00 00 00 00 00 00 f1 01 f4 f4 f4 f2 f2 f2 [ 699.914392] ^ [ 699.915758] ffff8801f43af980: f2 00 f4 f4 00 00 00 00 f2 00 00 00 00 00 00 00 [ 699.917193] ffff8801f43afa00: 00 00 00 00 00 00 00 00 00 f3 f3 f3 00 00 00 00 [ 699.918634] ================================================================== - Location https://elixir.bootlin.com/linux/v4.18-rc1/source/fs/f2fs/segment.h#L644 Reported-by Wen Xu <wen.xu@gatech.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-08-01 14:13:44 +03:00
if (__is_valid_data_blkaddr(fio->old_blkaddr) &&
!f2fs_is_valid_blkaddr(fio->sbi, fio->old_blkaddr,
f2fs: introduce DATA_GENERIC_ENHANCE Previously, f2fs_is_valid_blkaddr(, blkaddr, DATA_GENERIC) will check whether @blkaddr locates in main area or not. That check is weak, since the block address in range of main area can point to the address which is not valid in segment info table, and we can not detect such condition, we may suffer worse corruption as system continues running. So this patch introduce DATA_GENERIC_ENHANCE to enhance the sanity check which trigger SIT bitmap check rather than only range check. This patch did below changes as wel: - set SBI_NEED_FSCK in f2fs_is_valid_blkaddr(). - get rid of is_valid_data_blkaddr() to avoid panic if blkaddr is invalid. - introduce verify_fio_blkaddr() to wrap fio {new,old}_blkaddr validation check. - spread blkaddr check in: * f2fs_get_node_info() * __read_out_blkaddrs() * f2fs_submit_page_read() * ra_data_block() * do_recover_data() This patch can fix bug reported from bugzilla below: https://bugzilla.kernel.org/show_bug.cgi?id=203215 https://bugzilla.kernel.org/show_bug.cgi?id=203223 https://bugzilla.kernel.org/show_bug.cgi?id=203231 https://bugzilla.kernel.org/show_bug.cgi?id=203235 https://bugzilla.kernel.org/show_bug.cgi?id=203241 = Update by Jaegeuk Kim = DATA_GENERIC_ENHANCE enhanced to validate block addresses on read/write paths. But, xfstest/generic/446 compalins some generated kernel messages saying invalid bitmap was detected when reading a block. The reaons is, when we get the block addresses from extent_cache, there is no lock to synchronize it from truncating the blocks in parallel. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-15 10:26:32 +03:00
DATA_GENERIC_ENHANCE)) {
err = -EFSCORRUPTED;
f2fs: fix to do sanity check with block address in main area This patch add to do sanity check with below field: - cp_pack_total_block_count - blkaddr of data/node - extent info - Overview BUG() in verify_block_addr() when writing to a corrupted f2fs image - Reproduce (4.18 upstream kernel) - POC (poc.c) static void activity(char *mpoint) { char *foo_bar_baz; int err; static int buf[8192]; memset(buf, 0, sizeof(buf)); err = asprintf(&foo_bar_baz, "%s/foo/bar/baz", mpoint); int fd = open(foo_bar_baz, O_RDWR | O_TRUNC, 0777); if (fd >= 0) { write(fd, (char *)buf, sizeof(buf)); fdatasync(fd); close(fd); } } int main(int argc, char *argv[]) { activity(argv[1]); return 0; } - Kernel message [ 689.349473] F2FS-fs (loop0): Mounted with checkpoint version = 3 [ 699.728662] WARNING: CPU: 0 PID: 1309 at fs/f2fs/segment.c:2860 f2fs_inplace_write_data+0x232/0x240 [ 699.728670] Modules linked in: snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_pcm snd_timer snd mac_hid i2c_piix4 soundcore ib_iser rdma_cm iw_cm ib_cm ib_core iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx raid1 raid0 multipath linear 8139too crct10dif_pclmul crc32_pclmul qxl drm_kms_helper syscopyarea aesni_intel sysfillrect sysimgblt fb_sys_fops ttm drm aes_x86_64 crypto_simd cryptd 8139cp glue_helper mii pata_acpi floppy [ 699.729056] CPU: 0 PID: 1309 Comm: a.out Not tainted 4.18.0-rc1+ #4 [ 699.729064] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.729074] RIP: 0010:f2fs_inplace_write_data+0x232/0x240 [ 699.729076] Code: ff e9 cf fe ff ff 49 8d 7d 10 e8 39 45 ad ff 4d 8b 7d 10 be 04 00 00 00 49 8d 7f 48 e8 07 49 ad ff 45 8b 7f 48 e9 fb fe ff ff <0f> 0b f0 41 80 4d 48 04 e9 65 fe ff ff 90 66 66 66 66 90 55 48 8d [ 699.729130] RSP: 0018:ffff8801f43af568 EFLAGS: 00010202 [ 699.729139] RAX: 000000000000003f RBX: ffff8801f43af7b8 RCX: ffffffffb88c9113 [ 699.729142] RDX: 0000000000000003 RSI: dffffc0000000000 RDI: ffff8802024e5540 [ 699.729144] RBP: ffff8801f43af590 R08: 0000000000000009 R09: ffffffffffffffe8 [ 699.729147] R10: 0000000000000001 R11: ffffed0039b0596a R12: ffff8802024e5540 [ 699.729149] R13: ffff8801f0335500 R14: ffff8801e3e7a700 R15: ffff8801e1ee4450 [ 699.729154] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.729156] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.729159] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.729171] Call Trace: [ 699.729192] f2fs_do_write_data_page+0x2e2/0xe00 [ 699.729203] ? f2fs_should_update_outplace+0xd0/0xd0 [ 699.729238] ? memcg_drain_all_list_lrus+0x280/0x280 [ 699.729269] ? __radix_tree_replace+0xa3/0x120 [ 699.729276] __write_data_page+0x5c7/0xe30 [ 699.729291] ? kasan_check_read+0x11/0x20 [ 699.729310] ? page_mapped+0x8a/0x110 [ 699.729321] ? page_mkclean+0xe9/0x160 [ 699.729327] ? f2fs_do_write_data_page+0xe00/0xe00 [ 699.729331] ? invalid_page_referenced_vma+0x130/0x130 [ 699.729345] ? clear_page_dirty_for_io+0x332/0x450 [ 699.729351] f2fs_write_cache_pages+0x4ca/0x860 [ 699.729358] ? __write_data_page+0xe30/0xe30 [ 699.729374] ? percpu_counter_add_batch+0x22/0xa0 [ 699.729380] ? kasan_check_write+0x14/0x20 [ 699.729391] ? _raw_spin_lock+0x17/0x40 [ 699.729403] ? f2fs_mark_inode_dirty_sync.part.18+0x16/0x30 [ 699.729413] ? iov_iter_advance+0x113/0x640 [ 699.729418] ? f2fs_write_end+0x133/0x2e0 [ 699.729423] ? balance_dirty_pages_ratelimited+0x239/0x640 [ 699.729428] f2fs_write_data_pages+0x329/0x520 [ 699.729433] ? generic_perform_write+0x250/0x320 [ 699.729438] ? f2fs_write_cache_pages+0x860/0x860 [ 699.729454] ? current_time+0x110/0x110 [ 699.729459] ? f2fs_preallocate_blocks+0x1ef/0x370 [ 699.729464] do_writepages+0x37/0xb0 [ 699.729468] ? f2fs_write_cache_pages+0x860/0x860 [ 699.729472] ? do_writepages+0x37/0xb0 [ 699.729478] __filemap_fdatawrite_range+0x19a/0x1f0 [ 699.729483] ? delete_from_page_cache_batch+0x4e0/0x4e0 [ 699.729496] ? __vfs_write+0x2b2/0x410 [ 699.729501] file_write_and_wait_range+0x66/0xb0 [ 699.729506] f2fs_do_sync_file+0x1f9/0xd90 [ 699.729511] ? truncate_partial_data_page+0x290/0x290 [ 699.729521] ? __sb_end_write+0x30/0x50 [ 699.729526] ? vfs_write+0x20f/0x260 [ 699.729530] f2fs_sync_file+0x9a/0xb0 [ 699.729534] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.729548] vfs_fsync_range+0x68/0x100 [ 699.729554] ? __fget_light+0xc9/0xe0 [ 699.729558] do_fsync+0x3d/0x70 [ 699.729562] __x64_sys_fdatasync+0x24/0x30 [ 699.729585] do_syscall_64+0x78/0x170 [ 699.729595] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 699.729613] RIP: 0033:0x7f9bf930d800 [ 699.729615] Code: 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 83 3d 49 bf 2c 00 00 75 10 b8 4b 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 be 78 01 00 48 89 04 24 [ 699.729668] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.729673] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.729675] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.729678] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.729680] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.729683] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.729687] ---[ end trace 4ce02f25ff7d3df5 ]--- [ 699.729782] ------------[ cut here ]------------ [ 699.729785] kernel BUG at fs/f2fs/segment.h:654! [ 699.731055] invalid opcode: 0000 [#1] SMP KASAN PTI [ 699.732104] CPU: 0 PID: 1309 Comm: a.out Tainted: G W 4.18.0-rc1+ #4 [ 699.733684] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.735611] RIP: 0010:f2fs_submit_page_bio+0x29b/0x730 [ 699.736649] Code: 54 49 8d bd 18 04 00 00 e8 b2 59 af ff 41 8b 8d 18 04 00 00 8b 45 b8 41 d3 e6 44 01 f0 4c 8d 73 14 41 39 c7 0f 82 37 fe ff ff <0f> 0b 65 8b 05 2c 04 77 47 89 c0 48 0f a3 05 52 c1 d5 01 0f 92 c0 [ 699.740524] RSP: 0018:ffff8801f43af508 EFLAGS: 00010283 [ 699.741573] RAX: 0000000000000000 RBX: ffff8801f43af7b8 RCX: ffffffffb88a7cef [ 699.743006] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8801e3e7a64c [ 699.744426] RBP: ffff8801f43af558 R08: ffffed003e066b55 R09: ffffed003e066b55 [ 699.745833] R10: 0000000000000001 R11: ffffed003e066b54 R12: ffffea0007876940 [ 699.747256] R13: ffff8801f0335500 R14: ffff8801e3e7a600 R15: 0000000000000001 [ 699.748683] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.750293] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.751462] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.752874] Call Trace: [ 699.753386] ? f2fs_inplace_write_data+0x93/0x240 [ 699.754341] f2fs_inplace_write_data+0xd2/0x240 [ 699.755271] f2fs_do_write_data_page+0x2e2/0xe00 [ 699.756214] ? f2fs_should_update_outplace+0xd0/0xd0 [ 699.757215] ? memcg_drain_all_list_lrus+0x280/0x280 [ 699.758209] ? __radix_tree_replace+0xa3/0x120 [ 699.759164] __write_data_page+0x5c7/0xe30 [ 699.760002] ? kasan_check_read+0x11/0x20 [ 699.760823] ? page_mapped+0x8a/0x110 [ 699.761573] ? page_mkclean+0xe9/0x160 [ 699.762345] ? f2fs_do_write_data_page+0xe00/0xe00 [ 699.763332] ? invalid_page_referenced_vma+0x130/0x130 [ 699.764374] ? clear_page_dirty_for_io+0x332/0x450 [ 699.765347] f2fs_write_cache_pages+0x4ca/0x860 [ 699.766276] ? __write_data_page+0xe30/0xe30 [ 699.767161] ? percpu_counter_add_batch+0x22/0xa0 [ 699.768112] ? kasan_check_write+0x14/0x20 [ 699.768951] ? _raw_spin_lock+0x17/0x40 [ 699.769739] ? f2fs_mark_inode_dirty_sync.part.18+0x16/0x30 [ 699.770885] ? iov_iter_advance+0x113/0x640 [ 699.771743] ? f2fs_write_end+0x133/0x2e0 [ 699.772569] ? balance_dirty_pages_ratelimited+0x239/0x640 [ 699.773680] f2fs_write_data_pages+0x329/0x520 [ 699.774603] ? generic_perform_write+0x250/0x320 [ 699.775544] ? f2fs_write_cache_pages+0x860/0x860 [ 699.776510] ? current_time+0x110/0x110 [ 699.777299] ? f2fs_preallocate_blocks+0x1ef/0x370 [ 699.778279] do_writepages+0x37/0xb0 [ 699.779026] ? f2fs_write_cache_pages+0x860/0x860 [ 699.779978] ? do_writepages+0x37/0xb0 [ 699.780755] __filemap_fdatawrite_range+0x19a/0x1f0 [ 699.781746] ? delete_from_page_cache_batch+0x4e0/0x4e0 [ 699.782820] ? __vfs_write+0x2b2/0x410 [ 699.783597] file_write_and_wait_range+0x66/0xb0 [ 699.784540] f2fs_do_sync_file+0x1f9/0xd90 [ 699.785381] ? truncate_partial_data_page+0x290/0x290 [ 699.786415] ? __sb_end_write+0x30/0x50 [ 699.787204] ? vfs_write+0x20f/0x260 [ 699.787941] f2fs_sync_file+0x9a/0xb0 [ 699.788694] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.789572] vfs_fsync_range+0x68/0x100 [ 699.790360] ? __fget_light+0xc9/0xe0 [ 699.791128] do_fsync+0x3d/0x70 [ 699.791779] __x64_sys_fdatasync+0x24/0x30 [ 699.792614] do_syscall_64+0x78/0x170 [ 699.793371] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 699.794406] RIP: 0033:0x7f9bf930d800 [ 699.795134] Code: 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 83 3d 49 bf 2c 00 00 75 10 b8 4b 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 be 78 01 00 48 89 04 24 [ 699.798960] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.800483] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.801923] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.803373] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.804798] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.806233] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.807667] Modules linked in: snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_pcm snd_timer snd mac_hid i2c_piix4 soundcore ib_iser rdma_cm iw_cm ib_cm ib_core iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx raid1 raid0 multipath linear 8139too crct10dif_pclmul crc32_pclmul qxl drm_kms_helper syscopyarea aesni_intel sysfillrect sysimgblt fb_sys_fops ttm drm aes_x86_64 crypto_simd cryptd 8139cp glue_helper mii pata_acpi floppy [ 699.817079] ---[ end trace 4ce02f25ff7d3df6 ]--- [ 699.818068] RIP: 0010:f2fs_submit_page_bio+0x29b/0x730 [ 699.819114] Code: 54 49 8d bd 18 04 00 00 e8 b2 59 af ff 41 8b 8d 18 04 00 00 8b 45 b8 41 d3 e6 44 01 f0 4c 8d 73 14 41 39 c7 0f 82 37 fe ff ff <0f> 0b 65 8b 05 2c 04 77 47 89 c0 48 0f a3 05 52 c1 d5 01 0f 92 c0 [ 699.822919] RSP: 0018:ffff8801f43af508 EFLAGS: 00010283 [ 699.823977] RAX: 0000000000000000 RBX: ffff8801f43af7b8 RCX: ffffffffb88a7cef [ 699.825436] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8801e3e7a64c [ 699.826881] RBP: ffff8801f43af558 R08: ffffed003e066b55 R09: ffffed003e066b55 [ 699.828292] R10: 0000000000000001 R11: ffffed003e066b54 R12: ffffea0007876940 [ 699.829750] R13: ffff8801f0335500 R14: ffff8801e3e7a600 R15: 0000000000000001 [ 699.831192] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.832793] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.833981] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.835556] ================================================================== [ 699.837029] BUG: KASAN: stack-out-of-bounds in update_stack_state+0x38c/0x3e0 [ 699.838462] Read of size 8 at addr ffff8801f43af970 by task a.out/1309 [ 699.840086] CPU: 0 PID: 1309 Comm: a.out Tainted: G D W 4.18.0-rc1+ #4 [ 699.841603] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.843475] Call Trace: [ 699.843982] dump_stack+0x7b/0xb5 [ 699.844661] print_address_description+0x70/0x290 [ 699.845607] kasan_report+0x291/0x390 [ 699.846351] ? update_stack_state+0x38c/0x3e0 [ 699.853831] __asan_load8+0x54/0x90 [ 699.854569] update_stack_state+0x38c/0x3e0 [ 699.855428] ? __read_once_size_nocheck.constprop.7+0x20/0x20 [ 699.856601] ? __save_stack_trace+0x5e/0x100 [ 699.857476] unwind_next_frame.part.5+0x18e/0x490 [ 699.858448] ? unwind_dump+0x290/0x290 [ 699.859217] ? clear_page_dirty_for_io+0x332/0x450 [ 699.860185] __unwind_start+0x106/0x190 [ 699.860974] __save_stack_trace+0x5e/0x100 [ 699.861808] ? __save_stack_trace+0x5e/0x100 [ 699.862691] ? unlink_anon_vmas+0xba/0x2c0 [ 699.863525] save_stack_trace+0x1f/0x30 [ 699.864312] save_stack+0x46/0xd0 [ 699.864993] ? __alloc_pages_slowpath+0x1420/0x1420 [ 699.865990] ? flush_tlb_mm_range+0x15e/0x220 [ 699.866889] ? kasan_check_write+0x14/0x20 [ 699.867724] ? __dec_node_state+0x92/0xb0 [ 699.868543] ? lock_page_memcg+0x85/0xf0 [ 699.869350] ? unlock_page_memcg+0x16/0x80 [ 699.870185] ? page_remove_rmap+0x198/0x520 [ 699.871048] ? mark_page_accessed+0x133/0x200 [ 699.871930] ? _cond_resched+0x1a/0x50 [ 699.872700] ? unmap_page_range+0xcd4/0xe50 [ 699.873551] ? rb_next+0x58/0x80 [ 699.874217] ? rb_next+0x58/0x80 [ 699.874895] __kasan_slab_free+0x13c/0x1a0 [ 699.875734] ? unlink_anon_vmas+0xba/0x2c0 [ 699.876563] kasan_slab_free+0xe/0x10 [ 699.877315] kmem_cache_free+0x89/0x1e0 [ 699.878095] unlink_anon_vmas+0xba/0x2c0 [ 699.878913] free_pgtables+0x101/0x1b0 [ 699.879677] exit_mmap+0x146/0x2a0 [ 699.880378] ? __ia32_sys_munmap+0x50/0x50 [ 699.881214] ? kasan_check_read+0x11/0x20 [ 699.882052] ? mm_update_next_owner+0x322/0x380 [ 699.882985] mmput+0x8b/0x1d0 [ 699.883602] do_exit+0x43a/0x1390 [ 699.884288] ? mm_update_next_owner+0x380/0x380 [ 699.885212] ? f2fs_sync_file+0x9a/0xb0 [ 699.885995] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.886877] ? vfs_fsync_range+0x68/0x100 [ 699.887694] ? __fget_light+0xc9/0xe0 [ 699.888442] ? do_fsync+0x3d/0x70 [ 699.889118] ? __x64_sys_fdatasync+0x24/0x30 [ 699.889996] rewind_stack_do_exit+0x17/0x20 [ 699.890860] RIP: 0033:0x7f9bf930d800 [ 699.891585] Code: Bad RIP value. [ 699.892268] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.893781] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.895220] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.896643] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.898069] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.899505] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.901241] The buggy address belongs to the page: [ 699.902215] page:ffffea0007d0ebc0 count:0 mapcount:0 mapping:0000000000000000 index:0x0 [ 699.903811] flags: 0x2ffff0000000000() [ 699.904585] raw: 02ffff0000000000 0000000000000000 ffffffff07d00101 0000000000000000 [ 699.906125] raw: 0000000000000000 0000000000240000 00000000ffffffff 0000000000000000 [ 699.907673] page dumped because: kasan: bad access detected [ 699.909108] Memory state around the buggy address: [ 699.910077] ffff8801f43af800: 00 f1 f1 f1 f1 00 f4 f4 f4 f3 f3 f3 f3 00 00 00 [ 699.911528] ffff8801f43af880: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 699.912953] >ffff8801f43af900: 00 00 00 00 00 00 00 00 f1 01 f4 f4 f4 f2 f2 f2 [ 699.914392] ^ [ 699.915758] ffff8801f43af980: f2 00 f4 f4 00 00 00 00 f2 00 00 00 00 00 00 00 [ 699.917193] ffff8801f43afa00: 00 00 00 00 00 00 00 00 00 f3 f3 f3 00 00 00 00 [ 699.918634] ================================================================== - Location https://elixir.bootlin.com/linux/v4.18-rc1/source/fs/f2fs/segment.h#L644 Reported-by Wen Xu <wen.xu@gatech.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-08-01 14:13:44 +03:00
goto out_writepage;
}
/*
* If current allocation needs SSR,
* it had better in-place writes for updated data.
*/
f2fs: introduce DATA_GENERIC_ENHANCE Previously, f2fs_is_valid_blkaddr(, blkaddr, DATA_GENERIC) will check whether @blkaddr locates in main area or not. That check is weak, since the block address in range of main area can point to the address which is not valid in segment info table, and we can not detect such condition, we may suffer worse corruption as system continues running. So this patch introduce DATA_GENERIC_ENHANCE to enhance the sanity check which trigger SIT bitmap check rather than only range check. This patch did below changes as wel: - set SBI_NEED_FSCK in f2fs_is_valid_blkaddr(). - get rid of is_valid_data_blkaddr() to avoid panic if blkaddr is invalid. - introduce verify_fio_blkaddr() to wrap fio {new,old}_blkaddr validation check. - spread blkaddr check in: * f2fs_get_node_info() * __read_out_blkaddrs() * f2fs_submit_page_read() * ra_data_block() * do_recover_data() This patch can fix bug reported from bugzilla below: https://bugzilla.kernel.org/show_bug.cgi?id=203215 https://bugzilla.kernel.org/show_bug.cgi?id=203223 https://bugzilla.kernel.org/show_bug.cgi?id=203231 https://bugzilla.kernel.org/show_bug.cgi?id=203235 https://bugzilla.kernel.org/show_bug.cgi?id=203241 = Update by Jaegeuk Kim = DATA_GENERIC_ENHANCE enhanced to validate block addresses on read/write paths. But, xfstest/generic/446 compalins some generated kernel messages saying invalid bitmap was detected when reading a block. The reaons is, when we get the block addresses from extent_cache, there is no lock to synchronize it from truncating the blocks in parallel. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-15 10:26:32 +03:00
if (ipu_force ||
(__is_valid_data_blkaddr(fio->old_blkaddr) &&
need_inplace_update(fio))) {
err = encrypt_one_page(fio);
if (err)
goto out_writepage;
set_page_writeback(page);
ClearPageError(page);
f2fs_put_dnode(&dn);
if (fio->need_lock == LOCK_REQ)
f2fs_unlock_op(fio->sbi);
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 19:20:41 +03:00
err = f2fs_inplace_write_data(fio);
if (err) {
if (f2fs_encrypted_file(inode))
fscrypt_finalize_bounce_page(&fio->encrypted_page);
if (PageWriteback(page))
end_page_writeback(page);
} else {
set_inode_flag(inode, FI_UPDATE_WRITE);
}
trace_f2fs_do_write_data_page(fio->page, IPU);
return err;
}
if (fio->need_lock == LOCK_RETRY) {
if (!f2fs_trylock_op(fio->sbi)) {
err = -EAGAIN;
goto out_writepage;
}
fio->need_lock = LOCK_REQ;
}
err = f2fs_get_node_info(fio->sbi, dn.nid, &ni);
if (err)
goto out_writepage;
fio->version = ni.version;
err = encrypt_one_page(fio);
if (err)
goto out_writepage;
set_page_writeback(page);
ClearPageError(page);
/* LFS mode write path */
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 19:20:41 +03:00
f2fs_outplace_write_data(&dn, fio);
trace_f2fs_do_write_data_page(page, OPU);
set_inode_flag(inode, FI_APPEND_WRITE);
if (page->index == 0)
set_inode_flag(inode, FI_FIRST_BLOCK_WRITTEN);
out_writepage:
f2fs_put_dnode(&dn);
out:
if (fio->need_lock == LOCK_REQ)
f2fs_unlock_op(fio->sbi);
return err;
}
static int __write_data_page(struct page *page, bool *submitted,
f2fs: add bio cache for IPU SQLite in Wal mode may trigger sequential IPU write in db-wal file, after commit d1b3e72d5490 ("f2fs: submit bio of in-place-update pages"), we lost the chance of merging page in inner managed bio cache, result in submitting more small-sized IO. So let's add temporary bio in writepages() to cache mergeable write IO as much as possible. Test case: 1. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" 2. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" Before: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65552, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65560, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65568, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65576, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65584, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65592, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65600, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65608, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65616, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65624, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65632, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65640, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65648, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65656, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65664, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57352, size = 4096 After: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 65536 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57368, size = 4096 Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-02-19 11:15:29 +03:00
struct bio **bio,
sector_t *last_block,
struct writeback_control *wbc,
enum iostat_type io_type)
{
struct inode *inode = page->mapping->host;
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
loff_t i_size = i_size_read(inode);
const pgoff_t end_index = ((unsigned long long) i_size)
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 15:29:47 +03:00
>> PAGE_SHIFT;
loff_t psize = (loff_t)(page->index + 1) << PAGE_SHIFT;
unsigned offset = 0;
f2fs: introduce a new global lock scheme In the previous version, f2fs uses global locks according to the usage types, such as directory operations, block allocation, block write, and so on. Reference the following lock types in f2fs.h. enum lock_type { RENAME, /* for renaming operations */ DENTRY_OPS, /* for directory operations */ DATA_WRITE, /* for data write */ DATA_NEW, /* for data allocation */ DATA_TRUNC, /* for data truncate */ NODE_NEW, /* for node allocation */ NODE_TRUNC, /* for node truncate */ NODE_WRITE, /* for node write */ NR_LOCK_TYPE, }; In that case, we lose the performance under the multi-threading environment, since every types of operations must be conducted one at a time. In order to address the problem, let's share the locks globally with a mutex array regardless of any types. So, let users grab a mutex and perform their jobs in parallel as much as possbile. For this, I propose a new global lock scheme as follows. 0. Data structure - f2fs_sb_info -> mutex_lock[NR_GLOBAL_LOCKS] - f2fs_sb_info -> node_write 1. mutex_lock_op(sbi) - try to get an avaiable lock from the array. - returns the index of the gottern lock variable. 2. mutex_unlock_op(sbi, index of the lock) - unlock the given index of the lock. 3. mutex_lock_all(sbi) - grab all the locks in the array before the checkpoint. 4. mutex_unlock_all(sbi) - release all the locks in the array after checkpoint. 5. block_operations() - call mutex_lock_all() - sync_dirty_dir_inodes() - grab node_write - sync_node_pages() Note that, the pairs of mutex_lock_op()/mutex_unlock_op() and mutex_lock_all()/mutex_unlock_all() should be used together. Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2012-11-22 11:21:29 +04:00
bool need_balance_fs = false;
int err = 0;
struct f2fs_io_info fio = {
.sbi = sbi,
.ino = inode->i_ino,
.type = DATA,
.op = REQ_OP_WRITE,
.op_flags = wbc_to_write_flags(wbc),
.old_blkaddr = NULL_ADDR,
.page = page,
.encrypted_page = NULL,
.submitted = false,
.need_lock = LOCK_RETRY,
.io_type = io_type,
.io_wbc = wbc,
f2fs: add bio cache for IPU SQLite in Wal mode may trigger sequential IPU write in db-wal file, after commit d1b3e72d5490 ("f2fs: submit bio of in-place-update pages"), we lost the chance of merging page in inner managed bio cache, result in submitting more small-sized IO. So let's add temporary bio in writepages() to cache mergeable write IO as much as possible. Test case: 1. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" 2. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" Before: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65552, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65560, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65568, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65576, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65584, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65592, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65600, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65608, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65616, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65624, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65632, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65640, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65648, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65656, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65664, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57352, size = 4096 After: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 65536 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57368, size = 4096 Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-02-19 11:15:29 +03:00
.bio = bio,
.last_block = last_block,
};
trace_f2fs_writepage(page, DATA);
/* we should bypass data pages to proceed the kworkder jobs */
if (unlikely(f2fs_cp_error(sbi))) {
mapping_set_error(page->mapping, -EIO);
/*
* don't drop any dirty dentry pages for keeping lastest
* directory structure.
*/
if (S_ISDIR(inode->i_mode))
goto redirty_out;
goto out;
}
if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
goto redirty_out;
f2fs: add fs-verity support Add fs-verity support to f2fs. fs-verity is a filesystem feature that enables transparent integrity protection and authentication of read-only files. It uses a dm-verity like mechanism at the file level: a Merkle tree is used to verify any block in the file in log(filesize) time. It is implemented mainly by helper functions in fs/verity/. See Documentation/filesystems/fsverity.rst for the full documentation. The f2fs support for fs-verity consists of: - Adding a filesystem feature flag and an inode flag for fs-verity. - Implementing the fsverity_operations to support enabling verity on an inode and reading/writing the verity metadata. - Updating ->readpages() to verify data as it's read from verity files and to support reading verity metadata pages. - Updating ->write_begin(), ->write_end(), and ->writepages() to support writing verity metadata pages. - Calling the fs-verity hooks for ->open(), ->setattr(), and ->ioctl(). Like ext4, f2fs stores the verity metadata (Merkle tree and fsverity_descriptor) past the end of the file, starting at the first 64K boundary beyond i_size. This approach works because (a) verity files are readonly, and (b) pages fully beyond i_size aren't visible to userspace but can be read/written internally by f2fs with only some relatively small changes to f2fs. Extended attributes cannot be used because (a) f2fs limits the total size of an inode's xattr entries to 4096 bytes, which wouldn't be enough for even a single Merkle tree block, and (b) f2fs encryption doesn't encrypt xattrs, yet the verity metadata *must* be encrypted when the file is because it contains hashes of the plaintext data. Acked-by: Jaegeuk Kim <jaegeuk@kernel.org> Acked-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Eric Biggers <ebiggers@google.com>
2019-07-22 19:26:24 +03:00
if (page->index < end_index || f2fs_verity_in_progress(inode))
f2fs: introduce a new global lock scheme In the previous version, f2fs uses global locks according to the usage types, such as directory operations, block allocation, block write, and so on. Reference the following lock types in f2fs.h. enum lock_type { RENAME, /* for renaming operations */ DENTRY_OPS, /* for directory operations */ DATA_WRITE, /* for data write */ DATA_NEW, /* for data allocation */ DATA_TRUNC, /* for data truncate */ NODE_NEW, /* for node allocation */ NODE_TRUNC, /* for node truncate */ NODE_WRITE, /* for node write */ NR_LOCK_TYPE, }; In that case, we lose the performance under the multi-threading environment, since every types of operations must be conducted one at a time. In order to address the problem, let's share the locks globally with a mutex array regardless of any types. So, let users grab a mutex and perform their jobs in parallel as much as possbile. For this, I propose a new global lock scheme as follows. 0. Data structure - f2fs_sb_info -> mutex_lock[NR_GLOBAL_LOCKS] - f2fs_sb_info -> node_write 1. mutex_lock_op(sbi) - try to get an avaiable lock from the array. - returns the index of the gottern lock variable. 2. mutex_unlock_op(sbi, index of the lock) - unlock the given index of the lock. 3. mutex_lock_all(sbi) - grab all the locks in the array before the checkpoint. 4. mutex_unlock_all(sbi) - release all the locks in the array after checkpoint. 5. block_operations() - call mutex_lock_all() - sync_dirty_dir_inodes() - grab node_write - sync_node_pages() Note that, the pairs of mutex_lock_op()/mutex_unlock_op() and mutex_lock_all()/mutex_unlock_all() should be used together. Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2012-11-22 11:21:29 +04:00
goto write;
/*
* If the offset is out-of-range of file size,
* this page does not have to be written to disk.
*/
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 15:29:47 +03:00
offset = i_size & (PAGE_SIZE - 1);
if ((page->index >= end_index + 1) || !offset)
f2fs: introduce a new global lock scheme In the previous version, f2fs uses global locks according to the usage types, such as directory operations, block allocation, block write, and so on. Reference the following lock types in f2fs.h. enum lock_type { RENAME, /* for renaming operations */ DENTRY_OPS, /* for directory operations */ DATA_WRITE, /* for data write */ DATA_NEW, /* for data allocation */ DATA_TRUNC, /* for data truncate */ NODE_NEW, /* for node allocation */ NODE_TRUNC, /* for node truncate */ NODE_WRITE, /* for node write */ NR_LOCK_TYPE, }; In that case, we lose the performance under the multi-threading environment, since every types of operations must be conducted one at a time. In order to address the problem, let's share the locks globally with a mutex array regardless of any types. So, let users grab a mutex and perform their jobs in parallel as much as possbile. For this, I propose a new global lock scheme as follows. 0. Data structure - f2fs_sb_info -> mutex_lock[NR_GLOBAL_LOCKS] - f2fs_sb_info -> node_write 1. mutex_lock_op(sbi) - try to get an avaiable lock from the array. - returns the index of the gottern lock variable. 2. mutex_unlock_op(sbi, index of the lock) - unlock the given index of the lock. 3. mutex_lock_all(sbi) - grab all the locks in the array before the checkpoint. 4. mutex_unlock_all(sbi) - release all the locks in the array after checkpoint. 5. block_operations() - call mutex_lock_all() - sync_dirty_dir_inodes() - grab node_write - sync_node_pages() Note that, the pairs of mutex_lock_op()/mutex_unlock_op() and mutex_lock_all()/mutex_unlock_all() should be used together. Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2012-11-22 11:21:29 +04:00
goto out;
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 15:29:47 +03:00
zero_user_segment(page, offset, PAGE_SIZE);
f2fs: introduce a new global lock scheme In the previous version, f2fs uses global locks according to the usage types, such as directory operations, block allocation, block write, and so on. Reference the following lock types in f2fs.h. enum lock_type { RENAME, /* for renaming operations */ DENTRY_OPS, /* for directory operations */ DATA_WRITE, /* for data write */ DATA_NEW, /* for data allocation */ DATA_TRUNC, /* for data truncate */ NODE_NEW, /* for node allocation */ NODE_TRUNC, /* for node truncate */ NODE_WRITE, /* for node write */ NR_LOCK_TYPE, }; In that case, we lose the performance under the multi-threading environment, since every types of operations must be conducted one at a time. In order to address the problem, let's share the locks globally with a mutex array regardless of any types. So, let users grab a mutex and perform their jobs in parallel as much as possbile. For this, I propose a new global lock scheme as follows. 0. Data structure - f2fs_sb_info -> mutex_lock[NR_GLOBAL_LOCKS] - f2fs_sb_info -> node_write 1. mutex_lock_op(sbi) - try to get an avaiable lock from the array. - returns the index of the gottern lock variable. 2. mutex_unlock_op(sbi, index of the lock) - unlock the given index of the lock. 3. mutex_lock_all(sbi) - grab all the locks in the array before the checkpoint. 4. mutex_unlock_all(sbi) - release all the locks in the array after checkpoint. 5. block_operations() - call mutex_lock_all() - sync_dirty_dir_inodes() - grab node_write - sync_node_pages() Note that, the pairs of mutex_lock_op()/mutex_unlock_op() and mutex_lock_all()/mutex_unlock_all() should be used together. Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2012-11-22 11:21:29 +04:00
write:
if (f2fs_is_drop_cache(inode))
goto out;
/* we should not write 0'th page having journal header */
if (f2fs_is_volatile_file(inode) && (!page->index ||
(!wbc->for_reclaim &&
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 19:20:41 +03:00
f2fs_available_free_memory(sbi, BASE_CHECK))))
goto redirty_out;
f2fs: introduce a new global lock scheme In the previous version, f2fs uses global locks according to the usage types, such as directory operations, block allocation, block write, and so on. Reference the following lock types in f2fs.h. enum lock_type { RENAME, /* for renaming operations */ DENTRY_OPS, /* for directory operations */ DATA_WRITE, /* for data write */ DATA_NEW, /* for data allocation */ DATA_TRUNC, /* for data truncate */ NODE_NEW, /* for node allocation */ NODE_TRUNC, /* for node truncate */ NODE_WRITE, /* for node write */ NR_LOCK_TYPE, }; In that case, we lose the performance under the multi-threading environment, since every types of operations must be conducted one at a time. In order to address the problem, let's share the locks globally with a mutex array regardless of any types. So, let users grab a mutex and perform their jobs in parallel as much as possbile. For this, I propose a new global lock scheme as follows. 0. Data structure - f2fs_sb_info -> mutex_lock[NR_GLOBAL_LOCKS] - f2fs_sb_info -> node_write 1. mutex_lock_op(sbi) - try to get an avaiable lock from the array. - returns the index of the gottern lock variable. 2. mutex_unlock_op(sbi, index of the lock) - unlock the given index of the lock. 3. mutex_lock_all(sbi) - grab all the locks in the array before the checkpoint. 4. mutex_unlock_all(sbi) - release all the locks in the array after checkpoint. 5. block_operations() - call mutex_lock_all() - sync_dirty_dir_inodes() - grab node_write - sync_node_pages() Note that, the pairs of mutex_lock_op()/mutex_unlock_op() and mutex_lock_all()/mutex_unlock_all() should be used together. Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2012-11-22 11:21:29 +04:00
/* Dentry blocks are controlled by checkpoint */
if (S_ISDIR(inode->i_mode)) {
fio.need_lock = LOCK_DONE;
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 19:20:41 +03:00
err = f2fs_do_write_data_page(&fio);
goto done;
}
if (!wbc->for_reclaim)
f2fs: introduce a new global lock scheme In the previous version, f2fs uses global locks according to the usage types, such as directory operations, block allocation, block write, and so on. Reference the following lock types in f2fs.h. enum lock_type { RENAME, /* for renaming operations */ DENTRY_OPS, /* for directory operations */ DATA_WRITE, /* for data write */ DATA_NEW, /* for data allocation */ DATA_TRUNC, /* for data truncate */ NODE_NEW, /* for node allocation */ NODE_TRUNC, /* for node truncate */ NODE_WRITE, /* for node write */ NR_LOCK_TYPE, }; In that case, we lose the performance under the multi-threading environment, since every types of operations must be conducted one at a time. In order to address the problem, let's share the locks globally with a mutex array regardless of any types. So, let users grab a mutex and perform their jobs in parallel as much as possbile. For this, I propose a new global lock scheme as follows. 0. Data structure - f2fs_sb_info -> mutex_lock[NR_GLOBAL_LOCKS] - f2fs_sb_info -> node_write 1. mutex_lock_op(sbi) - try to get an avaiable lock from the array. - returns the index of the gottern lock variable. 2. mutex_unlock_op(sbi, index of the lock) - unlock the given index of the lock. 3. mutex_lock_all(sbi) - grab all the locks in the array before the checkpoint. 4. mutex_unlock_all(sbi) - release all the locks in the array after checkpoint. 5. block_operations() - call mutex_lock_all() - sync_dirty_dir_inodes() - grab node_write - sync_node_pages() Note that, the pairs of mutex_lock_op()/mutex_unlock_op() and mutex_lock_all()/mutex_unlock_all() should be used together. Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2012-11-22 11:21:29 +04:00
need_balance_fs = true;
else if (has_not_enough_free_secs(sbi, 0, 0))
f2fs: introduce a new global lock scheme In the previous version, f2fs uses global locks according to the usage types, such as directory operations, block allocation, block write, and so on. Reference the following lock types in f2fs.h. enum lock_type { RENAME, /* for renaming operations */ DENTRY_OPS, /* for directory operations */ DATA_WRITE, /* for data write */ DATA_NEW, /* for data allocation */ DATA_TRUNC, /* for data truncate */ NODE_NEW, /* for node allocation */ NODE_TRUNC, /* for node truncate */ NODE_WRITE, /* for node write */ NR_LOCK_TYPE, }; In that case, we lose the performance under the multi-threading environment, since every types of operations must be conducted one at a time. In order to address the problem, let's share the locks globally with a mutex array regardless of any types. So, let users grab a mutex and perform their jobs in parallel as much as possbile. For this, I propose a new global lock scheme as follows. 0. Data structure - f2fs_sb_info -> mutex_lock[NR_GLOBAL_LOCKS] - f2fs_sb_info -> node_write 1. mutex_lock_op(sbi) - try to get an avaiable lock from the array. - returns the index of the gottern lock variable. 2. mutex_unlock_op(sbi, index of the lock) - unlock the given index of the lock. 3. mutex_lock_all(sbi) - grab all the locks in the array before the checkpoint. 4. mutex_unlock_all(sbi) - release all the locks in the array after checkpoint. 5. block_operations() - call mutex_lock_all() - sync_dirty_dir_inodes() - grab node_write - sync_node_pages() Note that, the pairs of mutex_lock_op()/mutex_unlock_op() and mutex_lock_all()/mutex_unlock_all() should be used together. Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2012-11-22 11:21:29 +04:00
goto redirty_out;
else
set_inode_flag(inode, FI_HOT_DATA);
err = -EAGAIN;
if (f2fs_has_inline_data(inode)) {
err = f2fs_write_inline_data(inode, page);
if (!err)
goto out;
}
if (err == -EAGAIN) {
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 19:20:41 +03:00
err = f2fs_do_write_data_page(&fio);
if (err == -EAGAIN) {
fio.need_lock = LOCK_REQ;
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 19:20:41 +03:00
err = f2fs_do_write_data_page(&fio);
}
}
if (err) {
file_set_keep_isize(inode);
} else {
down_write(&F2FS_I(inode)->i_sem);
if (F2FS_I(inode)->last_disk_size < psize)
F2FS_I(inode)->last_disk_size = psize;
up_write(&F2FS_I(inode)->i_sem);
}
done:
if (err && err != -ENOENT)
goto redirty_out;
f2fs: introduce a new global lock scheme In the previous version, f2fs uses global locks according to the usage types, such as directory operations, block allocation, block write, and so on. Reference the following lock types in f2fs.h. enum lock_type { RENAME, /* for renaming operations */ DENTRY_OPS, /* for directory operations */ DATA_WRITE, /* for data write */ DATA_NEW, /* for data allocation */ DATA_TRUNC, /* for data truncate */ NODE_NEW, /* for node allocation */ NODE_TRUNC, /* for node truncate */ NODE_WRITE, /* for node write */ NR_LOCK_TYPE, }; In that case, we lose the performance under the multi-threading environment, since every types of operations must be conducted one at a time. In order to address the problem, let's share the locks globally with a mutex array regardless of any types. So, let users grab a mutex and perform their jobs in parallel as much as possbile. For this, I propose a new global lock scheme as follows. 0. Data structure - f2fs_sb_info -> mutex_lock[NR_GLOBAL_LOCKS] - f2fs_sb_info -> node_write 1. mutex_lock_op(sbi) - try to get an avaiable lock from the array. - returns the index of the gottern lock variable. 2. mutex_unlock_op(sbi, index of the lock) - unlock the given index of the lock. 3. mutex_lock_all(sbi) - grab all the locks in the array before the checkpoint. 4. mutex_unlock_all(sbi) - release all the locks in the array after checkpoint. 5. block_operations() - call mutex_lock_all() - sync_dirty_dir_inodes() - grab node_write - sync_node_pages() Note that, the pairs of mutex_lock_op()/mutex_unlock_op() and mutex_lock_all()/mutex_unlock_all() should be used together. Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2012-11-22 11:21:29 +04:00
out:
inode_dec_dirty_pages(inode);
if (err) {
ClearPageUptodate(page);
clear_cold_data(page);
}
if (wbc->for_reclaim) {
f2fs_submit_merged_write_cond(sbi, NULL, page, 0, DATA);
clear_inode_flag(inode, FI_HOT_DATA);
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 19:20:41 +03:00
f2fs_remove_dirty_inode(inode);
submitted = NULL;
}
unlock_page(page);
f2fs: fix potential recursive call when enabling data_flush As Hagbard Celine reported: Hi, this is a long standing bug that I've hit before on older kernels, but I was not able to get the syslog saved because of the nature of the bug. This time I had booted form a pen-drive, and was able to save the log to it's efi-partition. What i did to trigger it was to create a partition and format it f2fs, then mount it with options: "rw,relatime,lazytime,background_gc=on,disable_ext_identify,discard,heap,user_xattr,inline_xattr,acl,inline_data,inline_dentry,flush_merge,data_flush,extent_cache,mode=adaptive,active_logs=6,whint_mode=fs-based,alloc_mode=default,fsync_mode=strict". Then I unpacked a big .tar.xz to the partition (I used a gentoo-stage3-tarball as I was in process of installing Gentoo). Same options just without data_flush gives no problems. Mar 20 20:54:01 usbgentoo kernel: FAT-fs (nvme0n1p4): Volume was not properly unmounted. Some data may be corrupt. Please run fsck. Mar 20 21:05:23 usbgentoo kernel: kworker/dying (1588) used greatest stack depth: 12064 bytes left Mar 20 21:06:40 usbgentoo kernel: BUG: stack guard page was hit at 00000000a4b0733c (stack is 0000000056016422..0000000096e7463f) Mar 20 21:06:40 usbgentoo kernel: kernel stack overflow ...... Mar 20 21:06:40 usbgentoo kernel: Call Trace: Mar 20 21:06:40 usbgentoo kernel: read_node_page+0x71/0xf0 Mar 20 21:06:40 usbgentoo kernel: ? xas_load+0x8/0x50 Mar 20 21:06:40 usbgentoo kernel: __get_node_page+0x73/0x2a0 Mar 20 21:06:40 usbgentoo kernel: f2fs_get_dnode_of_data+0x34e/0x580 Mar 20 21:06:40 usbgentoo kernel: f2fs_write_inline_data+0x5e/0x2a0 Mar 20 21:06:40 usbgentoo kernel: __write_data_page+0x421/0x690 Mar 20 21:06:40 usbgentoo kernel: f2fs_write_cache_pages+0x1cf/0x460 Mar 20 21:06:40 usbgentoo kernel: f2fs_write_data_pages+0x2b3/0x2e0 Mar 20 21:06:40 usbgentoo kernel: ? f2fs_inode_chksum_verify+0x1d/0xc0 Mar 20 21:06:40 usbgentoo kernel: ? read_node_page+0x71/0xf0 Mar 20 21:06:40 usbgentoo kernel: do_writepages+0x3c/0xd0 Mar 20 21:06:40 usbgentoo kernel: __filemap_fdatawrite_range+0x7c/0xb0 Mar 20 21:06:40 usbgentoo kernel: f2fs_sync_dirty_inodes+0xf2/0x200 Mar 20 21:06:40 usbgentoo kernel: f2fs_balance_fs_bg+0x2a3/0x2c0 Mar 20 21:06:40 usbgentoo kernel: ? f2fs_inode_dirtied+0x21/0xc0 Mar 20 21:06:40 usbgentoo kernel: f2fs_balance_fs+0xd6/0x2b0 Mar 20 21:06:40 usbgentoo kernel: __write_data_page+0x4fb/0x690 ...... Mar 20 21:06:40 usbgentoo kernel: __writeback_single_inode+0x2a1/0x340 Mar 20 21:06:40 usbgentoo kernel: ? soft_cursor+0x1b4/0x220 Mar 20 21:06:40 usbgentoo kernel: writeback_sb_inodes+0x1d5/0x3e0 Mar 20 21:06:40 usbgentoo kernel: __writeback_inodes_wb+0x58/0xa0 Mar 20 21:06:40 usbgentoo kernel: wb_writeback+0x250/0x2e0 Mar 20 21:06:40 usbgentoo kernel: ? 0xffffffff8c000000 Mar 20 21:06:40 usbgentoo kernel: ? cpumask_next+0x16/0x20 Mar 20 21:06:40 usbgentoo kernel: wb_workfn+0x2f6/0x3b0 Mar 20 21:06:40 usbgentoo kernel: ? __switch_to_asm+0x40/0x70 Mar 20 21:06:40 usbgentoo kernel: process_one_work+0x1f5/0x3f0 Mar 20 21:06:40 usbgentoo kernel: worker_thread+0x28/0x3c0 Mar 20 21:06:40 usbgentoo kernel: ? rescuer_thread+0x330/0x330 Mar 20 21:06:40 usbgentoo kernel: kthread+0x10e/0x130 Mar 20 21:06:40 usbgentoo kernel: ? kthread_create_on_node+0x60/0x60 Mar 20 21:06:40 usbgentoo kernel: ret_from_fork+0x35/0x40 The root cause is that we run into an infinite recursive calling in between f2fs_balance_fs_bg and writepage() as described below: - f2fs_write_data_pages --- A - __write_data_page - f2fs_balance_fs - f2fs_balance_fs_bg --- B - f2fs_sync_dirty_inodes - filemap_fdatawrite - f2fs_write_data_pages --- A ... - f2fs_balance_fs_bg --- B ... In order to fix this issue, let's detect such condition in __write_data_page() and just skip calling f2fs_balance_fs() recursively. Reported-by: Hagbard Celine <hagbardcelin@gmail.com> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-02 13:52:19 +03:00
if (!S_ISDIR(inode->i_mode) && !IS_NOQUOTA(inode) &&
!F2FS_I(inode)->cp_task)
f2fs_balance_fs(sbi, need_balance_fs);
if (unlikely(f2fs_cp_error(sbi))) {
f2fs_submit_merged_write(sbi, DATA);
f2fs_submit_merged_ipu_write(sbi, bio, NULL);
submitted = NULL;
}
if (submitted)
*submitted = fio.submitted;
return 0;
redirty_out:
redirty_page_for_writepage(wbc, page);
/*
* pageout() in MM traslates EAGAIN, so calls handle_write_error()
* -> mapping_set_error() -> set_bit(AS_EIO, ...).
* file_write_and_wait_range() will see EIO error, which is critical
* to return value of fsync() followed by atomic_write failure to user.
*/
if (!err || wbc->for_reclaim)
return AOP_WRITEPAGE_ACTIVATE;
unlock_page(page);
return err;
}
static int f2fs_write_data_page(struct page *page,
struct writeback_control *wbc)
{
f2fs: add bio cache for IPU SQLite in Wal mode may trigger sequential IPU write in db-wal file, after commit d1b3e72d5490 ("f2fs: submit bio of in-place-update pages"), we lost the chance of merging page in inner managed bio cache, result in submitting more small-sized IO. So let's add temporary bio in writepages() to cache mergeable write IO as much as possible. Test case: 1. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" 2. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" Before: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65552, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65560, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65568, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65576, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65584, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65592, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65600, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65608, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65616, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65624, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65632, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65640, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65648, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65656, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65664, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57352, size = 4096 After: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 65536 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57368, size = 4096 Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-02-19 11:15:29 +03:00
return __write_data_page(page, NULL, NULL, NULL, wbc, FS_DATA_IO);
}
/*
* This function was copied from write_cche_pages from mm/page-writeback.c.
* The major change is making write step of cold data page separately from
* warm/hot data page.
*/
static int f2fs_write_cache_pages(struct address_space *mapping,
struct writeback_control *wbc,
enum iostat_type io_type)
{
int ret = 0;
int done = 0;
struct pagevec pvec;
struct f2fs_sb_info *sbi = F2FS_M_SB(mapping);
f2fs: add bio cache for IPU SQLite in Wal mode may trigger sequential IPU write in db-wal file, after commit d1b3e72d5490 ("f2fs: submit bio of in-place-update pages"), we lost the chance of merging page in inner managed bio cache, result in submitting more small-sized IO. So let's add temporary bio in writepages() to cache mergeable write IO as much as possible. Test case: 1. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" 2. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" Before: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65552, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65560, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65568, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65576, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65584, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65592, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65600, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65608, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65616, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65624, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65632, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65640, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65648, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65656, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65664, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57352, size = 4096 After: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 65536 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57368, size = 4096 Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-02-19 11:15:29 +03:00
struct bio *bio = NULL;
sector_t last_block;
int nr_pages;
pgoff_t uninitialized_var(writeback_index);
pgoff_t index;
pgoff_t end; /* Inclusive */
pgoff_t done_index;
int cycled;
int range_whole = 0;
xa_mark_t tag;
int nwritten = 0;
pagevec_init(&pvec);
if (get_dirty_pages(mapping->host) <=
SM_I(F2FS_M_SB(mapping))->min_hot_blocks)
set_inode_flag(mapping->host, FI_HOT_DATA);
else
clear_inode_flag(mapping->host, FI_HOT_DATA);
if (wbc->range_cyclic) {
writeback_index = mapping->writeback_index; /* prev offset */
index = writeback_index;
if (index == 0)
cycled = 1;
else
cycled = 0;
end = -1;
} else {
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 15:29:47 +03:00
index = wbc->range_start >> PAGE_SHIFT;
end = wbc->range_end >> PAGE_SHIFT;
if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
range_whole = 1;
cycled = 1; /* ignore range_cyclic tests */
}
if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
tag = PAGECACHE_TAG_TOWRITE;
else
tag = PAGECACHE_TAG_DIRTY;
retry:
if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
tag_pages_for_writeback(mapping, index, end);
done_index = index;
while (!done && (index <= end)) {
int i;
nr_pages = pagevec_lookup_range_tag(&pvec, mapping, &index, end,
tag);
if (nr_pages == 0)
break;
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
bool submitted = false;
/* give a priority to WB_SYNC threads */
if (atomic_read(&sbi->wb_sync_req[DATA]) &&
wbc->sync_mode == WB_SYNC_NONE) {
done = 1;
break;
}
done_index = page->index;
retry_write:
lock_page(page);
if (unlikely(page->mapping != mapping)) {
continue_unlock:
unlock_page(page);
continue;
}
if (!PageDirty(page)) {
/* someone wrote it for us */
goto continue_unlock;
}
if (PageWriteback(page)) {
if (wbc->sync_mode != WB_SYNC_NONE)
f2fs_wait_on_page_writeback(page,
DATA, true, true);
else
goto continue_unlock;
}
if (!clear_page_dirty_for_io(page))
goto continue_unlock;
f2fs: add bio cache for IPU SQLite in Wal mode may trigger sequential IPU write in db-wal file, after commit d1b3e72d5490 ("f2fs: submit bio of in-place-update pages"), we lost the chance of merging page in inner managed bio cache, result in submitting more small-sized IO. So let's add temporary bio in writepages() to cache mergeable write IO as much as possible. Test case: 1. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" 2. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" Before: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65552, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65560, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65568, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65576, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65584, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65592, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65600, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65608, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65616, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65624, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65632, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65640, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65648, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65656, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65664, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57352, size = 4096 After: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 65536 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57368, size = 4096 Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-02-19 11:15:29 +03:00
ret = __write_data_page(page, &submitted, &bio,
&last_block, wbc, io_type);
if (unlikely(ret)) {
/*
* keep nr_to_write, since vfs uses this to
* get # of written pages.
*/
if (ret == AOP_WRITEPAGE_ACTIVATE) {
unlock_page(page);
ret = 0;
continue;
} else if (ret == -EAGAIN) {
ret = 0;
if (wbc->sync_mode == WB_SYNC_ALL) {
cond_resched();
congestion_wait(BLK_RW_ASYNC,
HZ/50);
goto retry_write;
}
continue;
}
done_index = page->index + 1;
done = 1;
break;
} else if (submitted) {
nwritten++;
}
if (--wbc->nr_to_write <= 0 &&
wbc->sync_mode == WB_SYNC_NONE) {
done = 1;
break;
}
}
pagevec_release(&pvec);
cond_resched();
}
if (!cycled && !done) {
cycled = 1;
index = 0;
end = writeback_index - 1;
goto retry;
}
if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
mapping->writeback_index = done_index;
if (nwritten)
f2fs_submit_merged_write_cond(F2FS_M_SB(mapping), mapping->host,
NULL, 0, DATA);
f2fs: add bio cache for IPU SQLite in Wal mode may trigger sequential IPU write in db-wal file, after commit d1b3e72d5490 ("f2fs: submit bio of in-place-update pages"), we lost the chance of merging page in inner managed bio cache, result in submitting more small-sized IO. So let's add temporary bio in writepages() to cache mergeable write IO as much as possible. Test case: 1. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" 2. xfs_io -f /mnt/f2fs/file -c "pwrite 0 65536" -c "fsync" Before: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65552, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65560, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65568, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65576, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65584, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65592, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65600, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65608, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65616, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65624, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65632, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65640, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65648, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65656, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65664, size = 4096 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57352, size = 4096 After: f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), DATA, sector = 65544, size = 65536 f2fs_submit_write_bio: dev = (251,0)/(251,0), rw = WRITE(S), NODE, sector = 57368, size = 4096 Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-02-19 11:15:29 +03:00
/* submit cached bio of IPU write */
if (bio)
f2fs_submit_merged_ipu_write(sbi, &bio, NULL);
return ret;
}
static inline bool __should_serialize_io(struct inode *inode,
struct writeback_control *wbc)
{
if (!S_ISREG(inode->i_mode))
return false;
if (IS_NOQUOTA(inode))
return false;
f2fs: fix to avoid deadloop if data_flush is on As Hagbard Celine reported: [ 615.697824] INFO: task kworker/u16:5:344 blocked for more than 120 seconds. [ 615.697825] Not tainted 5.0.15-gentoo-f2fslog #4 [ 615.697826] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 615.697827] kworker/u16:5 D 0 344 2 0x80000000 [ 615.697831] Workqueue: writeback wb_workfn (flush-259:0) [ 615.697832] Call Trace: [ 615.697836] ? __schedule+0x2c5/0x8b0 [ 615.697839] schedule+0x32/0x80 [ 615.697841] schedule_preempt_disabled+0x14/0x20 [ 615.697842] __mutex_lock.isra.8+0x2ba/0x4d0 [ 615.697845] ? log_store+0xf5/0x260 [ 615.697848] f2fs_write_data_pages+0x133/0x320 [ 615.697851] ? trace_hardirqs_on+0x2c/0xe0 [ 615.697854] do_writepages+0x41/0xd0 [ 615.697857] __filemap_fdatawrite_range+0x81/0xb0 [ 615.697859] f2fs_sync_dirty_inodes+0x1dd/0x200 [ 615.697861] f2fs_balance_fs_bg+0x2a7/0x2c0 [ 615.697863] ? up_read+0x5/0x20 [ 615.697865] ? f2fs_do_write_data_page+0x2cb/0x940 [ 615.697867] f2fs_balance_fs+0xe5/0x2c0 [ 615.697869] __write_data_page+0x1c8/0x6e0 [ 615.697873] f2fs_write_cache_pages+0x1e0/0x450 [ 615.697878] f2fs_write_data_pages+0x14b/0x320 [ 615.697880] ? trace_hardirqs_on+0x2c/0xe0 [ 615.697883] do_writepages+0x41/0xd0 [ 615.697885] __filemap_fdatawrite_range+0x81/0xb0 [ 615.697887] f2fs_sync_dirty_inodes+0x1dd/0x200 [ 615.697889] f2fs_balance_fs_bg+0x2a7/0x2c0 [ 615.697891] f2fs_write_node_pages+0x51/0x220 [ 615.697894] do_writepages+0x41/0xd0 [ 615.697897] __writeback_single_inode+0x3d/0x3d0 [ 615.697899] writeback_sb_inodes+0x1e8/0x410 [ 615.697902] __writeback_inodes_wb+0x5d/0xb0 [ 615.697904] wb_writeback+0x28f/0x340 [ 615.697906] ? cpumask_next+0x16/0x20 [ 615.697908] wb_workfn+0x33e/0x420 [ 615.697911] process_one_work+0x1a1/0x3d0 [ 615.697913] worker_thread+0x30/0x380 [ 615.697915] ? process_one_work+0x3d0/0x3d0 [ 615.697916] kthread+0x116/0x130 [ 615.697918] ? kthread_create_worker_on_cpu+0x70/0x70 [ 615.697921] ret_from_fork+0x3a/0x50 There is still deadloop in below condition: d A - do_writepages - f2fs_write_node_pages - f2fs_balance_fs_bg - f2fs_sync_dirty_inodes - f2fs_write_cache_pages - mutex_lock(&sbi->writepages) -- lock once - __write_data_page - f2fs_balance_fs_bg - f2fs_sync_dirty_inodes - f2fs_write_data_pages - mutex_lock(&sbi->writepages) -- lock again Thread A Thread B - do_writepages - f2fs_write_node_pages - f2fs_balance_fs_bg - f2fs_sync_dirty_inodes - .cp_task = current - f2fs_sync_dirty_inodes - .cp_task = current - filemap_fdatawrite - .cp_task = NULL - filemap_fdatawrite - f2fs_write_cache_pages - enter f2fs_balance_fs_bg since .cp_task is NULL - .cp_task = NULL Change as below to avoid this: - add condition to avoid holding .writepages mutex lock in path of data flush - introduce mutex lock sbi.flush_lock to exclude concurrent data flush in background. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-05-20 12:36:59 +03:00
/* to avoid deadlock in path of data flush */
if (F2FS_I(inode)->cp_task)
return false;
if (wbc->sync_mode != WB_SYNC_ALL)
return true;
if (get_dirty_pages(inode) >= SM_I(F2FS_I_SB(inode))->min_seq_blocks)
return true;
return false;
}
static int __f2fs_write_data_pages(struct address_space *mapping,
struct writeback_control *wbc,
enum iostat_type io_type)
{
struct inode *inode = mapping->host;
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct blk_plug plug;
int ret;
bool locked = false;
/* deal with chardevs and other special file */
if (!mapping->a_ops->writepage)
return 0;
/* skip writing if there is no dirty page in this inode */
if (!get_dirty_pages(inode) && wbc->sync_mode == WB_SYNC_NONE)
return 0;
/* during POR, we don't need to trigger writepage at all. */
if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
goto skip_write;
if ((S_ISDIR(inode->i_mode) || IS_NOQUOTA(inode)) &&
wbc->sync_mode == WB_SYNC_NONE &&
get_dirty_pages(inode) < nr_pages_to_skip(sbi, DATA) &&
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 19:20:41 +03:00
f2fs_available_free_memory(sbi, DIRTY_DENTS))
goto skip_write;
/* skip writing during file defragment */
if (is_inode_flag_set(inode, FI_DO_DEFRAG))
goto skip_write;
trace_f2fs_writepages(mapping->host, wbc, DATA);
/* to avoid spliting IOs due to mixed WB_SYNC_ALL and WB_SYNC_NONE */
if (wbc->sync_mode == WB_SYNC_ALL)
atomic_inc(&sbi->wb_sync_req[DATA]);
else if (atomic_read(&sbi->wb_sync_req[DATA]))
goto skip_write;
if (__should_serialize_io(inode, wbc)) {
mutex_lock(&sbi->writepages);
locked = true;
}
blk_start_plug(&plug);
ret = f2fs_write_cache_pages(mapping, wbc, io_type);
blk_finish_plug(&plug);
if (locked)
mutex_unlock(&sbi->writepages);
if (wbc->sync_mode == WB_SYNC_ALL)
atomic_dec(&sbi->wb_sync_req[DATA]);
/*
* if some pages were truncated, we cannot guarantee its mapping->host
* to detect pending bios.
*/
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 19:20:41 +03:00
f2fs_remove_dirty_inode(inode);
return ret;
skip_write:
wbc->pages_skipped += get_dirty_pages(inode);
trace_f2fs_writepages(mapping->host, wbc, DATA);
return 0;
}
static int f2fs_write_data_pages(struct address_space *mapping,
struct writeback_control *wbc)
{
struct inode *inode = mapping->host;
return __f2fs_write_data_pages(mapping, wbc,
F2FS_I(inode)->cp_task == current ?
FS_CP_DATA_IO : FS_DATA_IO);
}
static void f2fs_write_failed(struct address_space *mapping, loff_t to)
{
struct inode *inode = mapping->host;
loff_t i_size = i_size_read(inode);
f2fs: add fs-verity support Add fs-verity support to f2fs. fs-verity is a filesystem feature that enables transparent integrity protection and authentication of read-only files. It uses a dm-verity like mechanism at the file level: a Merkle tree is used to verify any block in the file in log(filesize) time. It is implemented mainly by helper functions in fs/verity/. See Documentation/filesystems/fsverity.rst for the full documentation. The f2fs support for fs-verity consists of: - Adding a filesystem feature flag and an inode flag for fs-verity. - Implementing the fsverity_operations to support enabling verity on an inode and reading/writing the verity metadata. - Updating ->readpages() to verify data as it's read from verity files and to support reading verity metadata pages. - Updating ->write_begin(), ->write_end(), and ->writepages() to support writing verity metadata pages. - Calling the fs-verity hooks for ->open(), ->setattr(), and ->ioctl(). Like ext4, f2fs stores the verity metadata (Merkle tree and fsverity_descriptor) past the end of the file, starting at the first 64K boundary beyond i_size. This approach works because (a) verity files are readonly, and (b) pages fully beyond i_size aren't visible to userspace but can be read/written internally by f2fs with only some relatively small changes to f2fs. Extended attributes cannot be used because (a) f2fs limits the total size of an inode's xattr entries to 4096 bytes, which wouldn't be enough for even a single Merkle tree block, and (b) f2fs encryption doesn't encrypt xattrs, yet the verity metadata *must* be encrypted when the file is because it contains hashes of the plaintext data. Acked-by: Jaegeuk Kim <jaegeuk@kernel.org> Acked-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Eric Biggers <ebiggers@google.com>
2019-07-22 19:26:24 +03:00
/* In the fs-verity case, f2fs_end_enable_verity() does the truncate */
if (to > i_size && !f2fs_verity_in_progress(inode)) {
down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
down_write(&F2FS_I(inode)->i_mmap_sem);
truncate_pagecache(inode, i_size);
if (!IS_NOQUOTA(inode))
f2fs_truncate_blocks(inode, i_size, true);
up_write(&F2FS_I(inode)->i_mmap_sem);
up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
}
}
static int prepare_write_begin(struct f2fs_sb_info *sbi,
struct page *page, loff_t pos, unsigned len,
block_t *blk_addr, bool *node_changed)
{
struct inode *inode = page->mapping->host;
pgoff_t index = page->index;
struct dnode_of_data dn;
struct page *ipage;
bool locked = false;
struct extent_info ei = {0,0,0};
int err = 0;
int flag;
/*
* we already allocated all the blocks, so we don't need to get
* the block addresses when there is no need to fill the page.
*/
if (!f2fs_has_inline_data(inode) && len == PAGE_SIZE &&
f2fs: add fs-verity support Add fs-verity support to f2fs. fs-verity is a filesystem feature that enables transparent integrity protection and authentication of read-only files. It uses a dm-verity like mechanism at the file level: a Merkle tree is used to verify any block in the file in log(filesize) time. It is implemented mainly by helper functions in fs/verity/. See Documentation/filesystems/fsverity.rst for the full documentation. The f2fs support for fs-verity consists of: - Adding a filesystem feature flag and an inode flag for fs-verity. - Implementing the fsverity_operations to support enabling verity on an inode and reading/writing the verity metadata. - Updating ->readpages() to verify data as it's read from verity files and to support reading verity metadata pages. - Updating ->write_begin(), ->write_end(), and ->writepages() to support writing verity metadata pages. - Calling the fs-verity hooks for ->open(), ->setattr(), and ->ioctl(). Like ext4, f2fs stores the verity metadata (Merkle tree and fsverity_descriptor) past the end of the file, starting at the first 64K boundary beyond i_size. This approach works because (a) verity files are readonly, and (b) pages fully beyond i_size aren't visible to userspace but can be read/written internally by f2fs with only some relatively small changes to f2fs. Extended attributes cannot be used because (a) f2fs limits the total size of an inode's xattr entries to 4096 bytes, which wouldn't be enough for even a single Merkle tree block, and (b) f2fs encryption doesn't encrypt xattrs, yet the verity metadata *must* be encrypted when the file is because it contains hashes of the plaintext data. Acked-by: Jaegeuk Kim <jaegeuk@kernel.org> Acked-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Eric Biggers <ebiggers@google.com>
2019-07-22 19:26:24 +03:00
!is_inode_flag_set(inode, FI_NO_PREALLOC) &&
!f2fs_verity_in_progress(inode))
return 0;
/* f2fs_lock_op avoids race between write CP and convert_inline_page */
if (f2fs_has_inline_data(inode) && pos + len > MAX_INLINE_DATA(inode))
flag = F2FS_GET_BLOCK_DEFAULT;
else
flag = F2FS_GET_BLOCK_PRE_AIO;
if (f2fs_has_inline_data(inode) ||
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 15:29:47 +03:00
(pos & PAGE_MASK) >= i_size_read(inode)) {
__do_map_lock(sbi, flag, true);
locked = true;
}
restart:
/* check inline_data */
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 19:20:41 +03:00
ipage = f2fs_get_node_page(sbi, inode->i_ino);
if (IS_ERR(ipage)) {
err = PTR_ERR(ipage);
goto unlock_out;
}
set_new_dnode(&dn, inode, ipage, ipage, 0);
if (f2fs_has_inline_data(inode)) {
if (pos + len <= MAX_INLINE_DATA(inode)) {
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 19:20:41 +03:00
f2fs_do_read_inline_data(page, ipage);
set_inode_flag(inode, FI_DATA_EXIST);
f2fs: fix deadlock when flush inline data Below backtrace info was reported by Yunlei He: Call Trace: [<ffffffff817a9395>] schedule+0x35/0x80 [<ffffffff817abb7d>] rwsem_down_read_failed+0xed/0x130 [<ffffffff813c12a8>] call_rwsem_down_read_failed+0x18/0x [<ffffffff817ab1d0>] down_read+0x20/0x30 [<ffffffffa02a1a12>] f2fs_evict_inode+0x242/0x3a0 [f2fs] [<ffffffff81217057>] evict+0xc7/0x1a0 [<ffffffff81217cd6>] iput+0x196/0x200 [<ffffffff812134f9>] __dentry_kill+0x179/0x1e0 [<ffffffff812136f9>] dput+0x199/0x1f0 [<ffffffff811fe77b>] __fput+0x18b/0x220 [<ffffffff811fe84e>] ____fput+0xe/0x10 [<ffffffff81097427>] task_work_run+0x77/0x90 [<ffffffff81074d62>] exit_to_usermode_loop+0x73/0xa2 [<ffffffff81003b7a>] do_syscall_64+0xfa/0x110 [<ffffffff817acf65>] entry_SYSCALL64_slow_path+0x25/0x25 Call Trace: [<ffffffff817a9395>] schedule+0x35/0x80 [<ffffffff81216dc3>] __wait_on_freeing_inode+0xa3/0xd0 [<ffffffff810bc300>] ? autoremove_wake_function+0x40/0x4 [<ffffffff8121771d>] find_inode_fast+0x7d/0xb0 [<ffffffff8121794a>] ilookup+0x6a/0xd0 [<ffffffffa02bc740>] sync_node_pages+0x210/0x650 [f2fs] [<ffffffff8122e690>] ? do_fsync+0x70/0x70 [<ffffffffa02b085e>] block_operations+0x9e/0xf0 [f2fs] [<ffffffff8137b795>] ? bio_endio+0x55/0x60 [<ffffffffa02b0942>] write_checkpoint+0x92/0xba0 [f2fs] [<ffffffff8117da57>] ? mempool_free_slab+0x17/0x20 [<ffffffff8117de8b>] ? mempool_free+0x2b/0x80 [<ffffffff8122e690>] ? do_fsync+0x70/0x70 [<ffffffffa02a53e3>] f2fs_sync_fs+0x63/0xd0 [f2fs] [<ffffffff8129630f>] ? ext4_sync_fs+0xbf/0x190 [<ffffffff8122e6b0>] sync_fs_one_sb+0x20/0x30 [<ffffffff812002e9>] iterate_supers+0xb9/0x110 [<ffffffff8122e7b5>] sys_sync+0x55/0x90 [<ffffffff81003ae9>] do_syscall_64+0x69/0x110 [<ffffffff817acf65>] entry_SYSCALL64_slow_path+0x25/0x25 With following excuting serials, we will set inline_node in inode page after inode was unlinked, result in a deadloop described as below: 1. open file 2. write file 3. unlink file 4. write file 5. close file Thread A Thread B - dput - iput_final - inode->i_state |= I_FREEING - evict - f2fs_evict_inode - f2fs_sync_fs - write_checkpoint - block_operations - f2fs_lock_all (down_write(cp_rwsem)) - f2fs_lock_op (down_read(cp_rwsem)) - sync_node_pages - ilookup - find_inode_fast - __wait_on_freeing_inode (wait on I_FREEING clear) Here, we change to set inline_node flag only for linked inode for fixing. Reported-by: Yunlei He <heyunlei@huawei.com> Signed-off-by: Chao Yu <yuchao0@huawei.com> Tested-by: Jaegeuk Kim <jaegeuk@kernel.org> Cc: stable@vger.kernel.org # v4.6 Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2016-05-11 14:48:44 +03:00
if (inode->i_nlink)
set_inline_node(ipage);
} else {
err = f2fs_convert_inline_page(&dn, page);
if (err)
goto out;
if (dn.data_blkaddr == NULL_ADDR)
err = f2fs_get_block(&dn, index);
}
} else if (locked) {
err = f2fs_get_block(&dn, index);
} else {
if (f2fs_lookup_extent_cache(inode, index, &ei)) {
dn.data_blkaddr = ei.blk + index - ei.fofs;
} else {
/* hole case */
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 19:20:41 +03:00
err = f2fs_get_dnode_of_data(&dn, index, LOOKUP_NODE);
if (err || dn.data_blkaddr == NULL_ADDR) {
f2fs_put_dnode(&dn);
__do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO,
true);
WARN_ON(flag != F2FS_GET_BLOCK_PRE_AIO);
locked = true;
goto restart;
}
}
}
/* convert_inline_page can make node_changed */
*blk_addr = dn.data_blkaddr;
*node_changed = dn.node_changed;
out:
f2fs_put_dnode(&dn);
unlock_out:
if (locked)
__do_map_lock(sbi, flag, false);
return err;
}
static int f2fs_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;
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct page *page = NULL;
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 15:29:47 +03:00
pgoff_t index = ((unsigned long long) pos) >> PAGE_SHIFT;
bool need_balance = false, drop_atomic = false;
block_t blkaddr = NULL_ADDR;
int err = 0;
trace_f2fs_write_begin(inode, pos, len, flags);
if (!f2fs_is_checkpoint_ready(sbi)) {
err = -ENOSPC;
goto fail;
}
if ((f2fs_is_atomic_file(inode) &&
!f2fs_available_free_memory(sbi, INMEM_PAGES)) ||
is_inode_flag_set(inode, FI_ATOMIC_REVOKE_REQUEST)) {
err = -ENOMEM;
drop_atomic = true;
goto fail;
}
/*
* We should check this at this moment to avoid deadlock on inode page
* and #0 page. The locking rule for inline_data conversion should be:
* lock_page(page #0) -> lock_page(inode_page)
*/
if (index != 0) {
err = f2fs_convert_inline_inode(inode);
if (err)
goto fail;
}
repeat:
/*
* Do not use grab_cache_page_write_begin() to avoid deadlock due to
* wait_for_stable_page. Will wait that below with our IO control.
*/
page = f2fs_pagecache_get_page(mapping, index,
FGP_LOCK | FGP_WRITE | FGP_CREAT, GFP_NOFS);
if (!page) {
err = -ENOMEM;
goto fail;
}
*pagep = page;
err = prepare_write_begin(sbi, page, pos, len,
&blkaddr, &need_balance);
if (err)
goto fail;
if (need_balance && !IS_NOQUOTA(inode) &&
has_not_enough_free_secs(sbi, 0, 0)) {
unlock_page(page);
f2fs_balance_fs(sbi, true);
lock_page(page);
if (page->mapping != mapping) {
/* The page got truncated from under us */
f2fs_put_page(page, 1);
goto repeat;
}
}
f2fs_wait_on_page_writeback(page, DATA, false, true);
if (len == PAGE_SIZE || PageUptodate(page))
return 0;
f2fs: add fs-verity support Add fs-verity support to f2fs. fs-verity is a filesystem feature that enables transparent integrity protection and authentication of read-only files. It uses a dm-verity like mechanism at the file level: a Merkle tree is used to verify any block in the file in log(filesize) time. It is implemented mainly by helper functions in fs/verity/. See Documentation/filesystems/fsverity.rst for the full documentation. The f2fs support for fs-verity consists of: - Adding a filesystem feature flag and an inode flag for fs-verity. - Implementing the fsverity_operations to support enabling verity on an inode and reading/writing the verity metadata. - Updating ->readpages() to verify data as it's read from verity files and to support reading verity metadata pages. - Updating ->write_begin(), ->write_end(), and ->writepages() to support writing verity metadata pages. - Calling the fs-verity hooks for ->open(), ->setattr(), and ->ioctl(). Like ext4, f2fs stores the verity metadata (Merkle tree and fsverity_descriptor) past the end of the file, starting at the first 64K boundary beyond i_size. This approach works because (a) verity files are readonly, and (b) pages fully beyond i_size aren't visible to userspace but can be read/written internally by f2fs with only some relatively small changes to f2fs. Extended attributes cannot be used because (a) f2fs limits the total size of an inode's xattr entries to 4096 bytes, which wouldn't be enough for even a single Merkle tree block, and (b) f2fs encryption doesn't encrypt xattrs, yet the verity metadata *must* be encrypted when the file is because it contains hashes of the plaintext data. Acked-by: Jaegeuk Kim <jaegeuk@kernel.org> Acked-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Eric Biggers <ebiggers@google.com>
2019-07-22 19:26:24 +03:00
if (!(pos & (PAGE_SIZE - 1)) && (pos + len) >= i_size_read(inode) &&
!f2fs_verity_in_progress(inode)) {
zero_user_segment(page, len, PAGE_SIZE);
return 0;
}
if (blkaddr == NEW_ADDR) {
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 15:29:47 +03:00
zero_user_segment(page, 0, PAGE_SIZE);
SetPageUptodate(page);
} else {
f2fs: introduce DATA_GENERIC_ENHANCE Previously, f2fs_is_valid_blkaddr(, blkaddr, DATA_GENERIC) will check whether @blkaddr locates in main area or not. That check is weak, since the block address in range of main area can point to the address which is not valid in segment info table, and we can not detect such condition, we may suffer worse corruption as system continues running. So this patch introduce DATA_GENERIC_ENHANCE to enhance the sanity check which trigger SIT bitmap check rather than only range check. This patch did below changes as wel: - set SBI_NEED_FSCK in f2fs_is_valid_blkaddr(). - get rid of is_valid_data_blkaddr() to avoid panic if blkaddr is invalid. - introduce verify_fio_blkaddr() to wrap fio {new,old}_blkaddr validation check. - spread blkaddr check in: * f2fs_get_node_info() * __read_out_blkaddrs() * f2fs_submit_page_read() * ra_data_block() * do_recover_data() This patch can fix bug reported from bugzilla below: https://bugzilla.kernel.org/show_bug.cgi?id=203215 https://bugzilla.kernel.org/show_bug.cgi?id=203223 https://bugzilla.kernel.org/show_bug.cgi?id=203231 https://bugzilla.kernel.org/show_bug.cgi?id=203235 https://bugzilla.kernel.org/show_bug.cgi?id=203241 = Update by Jaegeuk Kim = DATA_GENERIC_ENHANCE enhanced to validate block addresses on read/write paths. But, xfstest/generic/446 compalins some generated kernel messages saying invalid bitmap was detected when reading a block. The reaons is, when we get the block addresses from extent_cache, there is no lock to synchronize it from truncating the blocks in parallel. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-15 10:26:32 +03:00
if (!f2fs_is_valid_blkaddr(sbi, blkaddr,
DATA_GENERIC_ENHANCE_READ)) {
err = -EFSCORRUPTED;
f2fs: introduce DATA_GENERIC_ENHANCE Previously, f2fs_is_valid_blkaddr(, blkaddr, DATA_GENERIC) will check whether @blkaddr locates in main area or not. That check is weak, since the block address in range of main area can point to the address which is not valid in segment info table, and we can not detect such condition, we may suffer worse corruption as system continues running. So this patch introduce DATA_GENERIC_ENHANCE to enhance the sanity check which trigger SIT bitmap check rather than only range check. This patch did below changes as wel: - set SBI_NEED_FSCK in f2fs_is_valid_blkaddr(). - get rid of is_valid_data_blkaddr() to avoid panic if blkaddr is invalid. - introduce verify_fio_blkaddr() to wrap fio {new,old}_blkaddr validation check. - spread blkaddr check in: * f2fs_get_node_info() * __read_out_blkaddrs() * f2fs_submit_page_read() * ra_data_block() * do_recover_data() This patch can fix bug reported from bugzilla below: https://bugzilla.kernel.org/show_bug.cgi?id=203215 https://bugzilla.kernel.org/show_bug.cgi?id=203223 https://bugzilla.kernel.org/show_bug.cgi?id=203231 https://bugzilla.kernel.org/show_bug.cgi?id=203235 https://bugzilla.kernel.org/show_bug.cgi?id=203241 = Update by Jaegeuk Kim = DATA_GENERIC_ENHANCE enhanced to validate block addresses on read/write paths. But, xfstest/generic/446 compalins some generated kernel messages saying invalid bitmap was detected when reading a block. The reaons is, when we get the block addresses from extent_cache, there is no lock to synchronize it from truncating the blocks in parallel. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-15 10:26:32 +03:00
goto fail;
}
err = f2fs_submit_page_read(inode, page, blkaddr);
if (err)
goto fail;
lock_page(page);
if (unlikely(page->mapping != mapping)) {
f2fs_put_page(page, 1);
goto repeat;
}
if (unlikely(!PageUptodate(page))) {
err = -EIO;
goto fail;
}
}
return 0;
fail:
f2fs_put_page(page, 1);
f2fs_write_failed(mapping, pos + len);
if (drop_atomic)
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 19:20:41 +03:00
f2fs_drop_inmem_pages_all(sbi, false);
return err;
}
static int f2fs_write_end(struct file *file,
struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct page *page, void *fsdata)
{
struct inode *inode = page->mapping->host;
trace_f2fs_write_end(inode, pos, len, copied);
/*
* This should be come from len == PAGE_SIZE, and we expect copied
* should be PAGE_SIZE. Otherwise, we treat it with zero copied and
* let generic_perform_write() try to copy data again through copied=0.
*/
if (!PageUptodate(page)) {
if (unlikely(copied != len))
copied = 0;
else
SetPageUptodate(page);
}
if (!copied)
goto unlock_out;
set_page_dirty(page);
f2fs: add fs-verity support Add fs-verity support to f2fs. fs-verity is a filesystem feature that enables transparent integrity protection and authentication of read-only files. It uses a dm-verity like mechanism at the file level: a Merkle tree is used to verify any block in the file in log(filesize) time. It is implemented mainly by helper functions in fs/verity/. See Documentation/filesystems/fsverity.rst for the full documentation. The f2fs support for fs-verity consists of: - Adding a filesystem feature flag and an inode flag for fs-verity. - Implementing the fsverity_operations to support enabling verity on an inode and reading/writing the verity metadata. - Updating ->readpages() to verify data as it's read from verity files and to support reading verity metadata pages. - Updating ->write_begin(), ->write_end(), and ->writepages() to support writing verity metadata pages. - Calling the fs-verity hooks for ->open(), ->setattr(), and ->ioctl(). Like ext4, f2fs stores the verity metadata (Merkle tree and fsverity_descriptor) past the end of the file, starting at the first 64K boundary beyond i_size. This approach works because (a) verity files are readonly, and (b) pages fully beyond i_size aren't visible to userspace but can be read/written internally by f2fs with only some relatively small changes to f2fs. Extended attributes cannot be used because (a) f2fs limits the total size of an inode's xattr entries to 4096 bytes, which wouldn't be enough for even a single Merkle tree block, and (b) f2fs encryption doesn't encrypt xattrs, yet the verity metadata *must* be encrypted when the file is because it contains hashes of the plaintext data. Acked-by: Jaegeuk Kim <jaegeuk@kernel.org> Acked-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Eric Biggers <ebiggers@google.com>
2019-07-22 19:26:24 +03:00
if (pos + copied > i_size_read(inode) &&
!f2fs_verity_in_progress(inode))
f2fs_i_size_write(inode, pos + copied);
unlock_out:
f2fs_put_page(page, 1);
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
return copied;
}
static int check_direct_IO(struct inode *inode, struct iov_iter *iter,
loff_t offset)
{
unsigned i_blkbits = READ_ONCE(inode->i_blkbits);
unsigned blkbits = i_blkbits;
unsigned blocksize_mask = (1 << blkbits) - 1;
unsigned long align = offset | iov_iter_alignment(iter);
struct block_device *bdev = inode->i_sb->s_bdev;
if (align & blocksize_mask) {
if (bdev)
blkbits = blksize_bits(bdev_logical_block_size(bdev));
blocksize_mask = (1 << blkbits) - 1;
if (align & blocksize_mask)
return -EINVAL;
return 1;
}
return 0;
}
static void f2fs_dio_end_io(struct bio *bio)
{
struct f2fs_private_dio *dio = bio->bi_private;
dec_page_count(F2FS_I_SB(dio->inode),
dio->write ? F2FS_DIO_WRITE : F2FS_DIO_READ);
bio->bi_private = dio->orig_private;
bio->bi_end_io = dio->orig_end_io;
kvfree(dio);
bio_endio(bio);
}
static void f2fs_dio_submit_bio(struct bio *bio, struct inode *inode,
loff_t file_offset)
{
struct f2fs_private_dio *dio;
bool write = (bio_op(bio) == REQ_OP_WRITE);
dio = f2fs_kzalloc(F2FS_I_SB(inode),
sizeof(struct f2fs_private_dio), GFP_NOFS);
if (!dio)
goto out;
dio->inode = inode;
dio->orig_end_io = bio->bi_end_io;
dio->orig_private = bio->bi_private;
dio->write = write;
bio->bi_end_io = f2fs_dio_end_io;
bio->bi_private = dio;
inc_page_count(F2FS_I_SB(inode),
write ? F2FS_DIO_WRITE : F2FS_DIO_READ);
submit_bio(bio);
return;
out:
bio->bi_status = BLK_STS_IOERR;
bio_endio(bio);
}
static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
{
struct address_space *mapping = iocb->ki_filp->f_mapping;
struct inode *inode = mapping->host;
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_inode_info *fi = F2FS_I(inode);
size_t count = iov_iter_count(iter);
loff_t offset = iocb->ki_pos;
int rw = iov_iter_rw(iter);
int err;
enum rw_hint hint = iocb->ki_hint;
int whint_mode = F2FS_OPTION(sbi).whint_mode;
bool do_opu;
err = check_direct_IO(inode, iter, offset);
if (err)
return err < 0 ? err : 0;
if (f2fs_force_buffered_io(inode, iocb, iter))
return 0;
do_opu = allow_outplace_dio(inode, iocb, iter);
trace_f2fs_direct_IO_enter(inode, offset, count, rw);
if (rw == WRITE && whint_mode == WHINT_MODE_OFF)
iocb->ki_hint = WRITE_LIFE_NOT_SET;
if (iocb->ki_flags & IOCB_NOWAIT) {
if (!down_read_trylock(&fi->i_gc_rwsem[rw])) {
iocb->ki_hint = hint;
err = -EAGAIN;
goto out;
}
if (do_opu && !down_read_trylock(&fi->i_gc_rwsem[READ])) {
up_read(&fi->i_gc_rwsem[rw]);
iocb->ki_hint = hint;
err = -EAGAIN;
goto out;
}
} else {
down_read(&fi->i_gc_rwsem[rw]);
if (do_opu)
down_read(&fi->i_gc_rwsem[READ]);
}
err = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev,
f2fs: fix out-place-update DIO write In get_more_blocks(), we may override @create as below code: create = dio->op == REQ_OP_WRITE; if (dio->flags & DIO_SKIP_HOLES) { if (fs_startblk <= ((i_size_read(dio->inode) - 1) >> i_blkbits)) create = 0; } But in f2fs_map_blocks(), we only trigger f2fs_balance_fs() if @create is 1, so in LFS mode, dio overwrite under LFS mode can easily run out of free segments, result in below panic. Call Trace: allocate_segment_by_default+0xa8/0x270 [f2fs] f2fs_allocate_data_block+0x1ea/0x5c0 [f2fs] __allocate_data_block+0x306/0x480 [f2fs] f2fs_map_blocks+0x6f6/0x920 [f2fs] __get_data_block+0x4f/0xb0 [f2fs] get_data_block_dio_write+0x50/0x60 [f2fs] do_blockdev_direct_IO+0xcd5/0x21e0 __blockdev_direct_IO+0x3a/0x3c f2fs_direct_IO+0x1ff/0x4a0 [f2fs] generic_file_direct_write+0xd9/0x160 __generic_file_write_iter+0xbb/0x1e0 f2fs_file_write_iter+0xaf/0x220 [f2fs] __vfs_write+0xd0/0x130 vfs_write+0xb2/0x1b0 SyS_pwrite64+0x69/0xa0 ? vtime_user_exit+0x29/0x70 do_syscall_64+0x6e/0x160 entry_SYSCALL64_slow_path+0x25/0x25 RIP: new_curseg+0x36f/0x380 [f2fs] RSP: ffffac570393f7a8 So this patch introduces a parameter map.m_may_create to indicate that f2fs_map_blocks() is called from write or read path, which can give the right hint to let f2fs_map_blocks() trigger OPU allocation and call f2fs_balanc_fs() correctly. BTW, it disables physical address preallocation for direct IO in f2fs_preallocate_blocks, which is redundant to OPU allocation of f2fs_map_blocks. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-11-13 09:33:45 +03:00
iter, rw == WRITE ? get_data_block_dio_write :
get_data_block_dio, NULL, f2fs_dio_submit_bio,
DIO_LOCKING | DIO_SKIP_HOLES);
if (do_opu)
up_read(&fi->i_gc_rwsem[READ]);
up_read(&fi->i_gc_rwsem[rw]);
if (rw == WRITE) {
if (whint_mode == WHINT_MODE_OFF)
iocb->ki_hint = hint;
if (err > 0) {
f2fs_update_iostat(F2FS_I_SB(inode), APP_DIRECT_IO,
err);
if (!do_opu)
set_inode_flag(inode, FI_UPDATE_WRITE);
} else if (err < 0) {
f2fs_write_failed(mapping, offset + count);
}
}
out:
trace_f2fs_direct_IO_exit(inode, offset, count, rw, err);
return err;
}
void f2fs_invalidate_page(struct page *page, unsigned int offset,
unsigned int length)
{
struct inode *inode = page->mapping->host;
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
if (inode->i_ino >= F2FS_ROOT_INO(sbi) &&
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 15:29:47 +03:00
(offset % PAGE_SIZE || length != PAGE_SIZE))
return;
if (PageDirty(page)) {
if (inode->i_ino == F2FS_META_INO(sbi)) {
dec_page_count(sbi, F2FS_DIRTY_META);
} else if (inode->i_ino == F2FS_NODE_INO(sbi)) {
dec_page_count(sbi, F2FS_DIRTY_NODES);
} else {
inode_dec_dirty_pages(inode);
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 19:20:41 +03:00
f2fs_remove_dirty_inode(inode);
}
}
clear_cold_data(page);
if (IS_ATOMIC_WRITTEN_PAGE(page))
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 19:20:41 +03:00
return f2fs_drop_inmem_page(inode, page);
f2fs_clear_page_private(page);
}
int f2fs_release_page(struct page *page, gfp_t wait)
{
/* If this is dirty page, keep PagePrivate */
if (PageDirty(page))
return 0;
/* This is atomic written page, keep Private */
if (IS_ATOMIC_WRITTEN_PAGE(page))
return 0;
clear_cold_data(page);
f2fs_clear_page_private(page);
return 1;
}
static int f2fs_set_data_page_dirty(struct page *page)
{
struct inode *inode = page_file_mapping(page)->host;
trace_f2fs_set_page_dirty(page, DATA);
if (!PageUptodate(page))
SetPageUptodate(page);
if (PageSwapCache(page))
return __set_page_dirty_nobuffers(page);
if (f2fs_is_atomic_file(inode) && !f2fs_is_commit_atomic_write(inode)) {
if (!IS_ATOMIC_WRITTEN_PAGE(page)) {
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 19:20:41 +03:00
f2fs_register_inmem_page(inode, page);
return 1;
}
/*
* Previously, this page has been registered, we just
* return here.
*/
return 0;
}
if (!PageDirty(page)) {
__set_page_dirty_nobuffers(page);
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 19:20:41 +03:00
f2fs_update_dirty_page(inode, page);
return 1;
}
return 0;
}
static sector_t f2fs_bmap(struct address_space *mapping, sector_t block)
{
struct inode *inode = mapping->host;
if (f2fs_has_inline_data(inode))
return 0;
/* make sure allocating whole blocks */
if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
filemap_write_and_wait(mapping);
return generic_block_bmap(mapping, block, get_data_block_bmap);
}
#ifdef CONFIG_MIGRATION
#include <linux/migrate.h>
int f2fs_migrate_page(struct address_space *mapping,
struct page *newpage, struct page *page, enum migrate_mode mode)
{
int rc, extra_count;
struct f2fs_inode_info *fi = F2FS_I(mapping->host);
bool atomic_written = IS_ATOMIC_WRITTEN_PAGE(page);
BUG_ON(PageWriteback(page));
/* migrating an atomic written page is safe with the inmem_lock hold */
if (atomic_written) {
if (mode != MIGRATE_SYNC)
return -EBUSY;
if (!mutex_trylock(&fi->inmem_lock))
return -EAGAIN;
}
/* one extra reference was held for atomic_write page */
extra_count = atomic_written ? 1 : 0;
rc = migrate_page_move_mapping(mapping, newpage,
page, extra_count);
if (rc != MIGRATEPAGE_SUCCESS) {
if (atomic_written)
mutex_unlock(&fi->inmem_lock);
return rc;
}
if (atomic_written) {
struct inmem_pages *cur;
list_for_each_entry(cur, &fi->inmem_pages, list)
if (cur->page == page) {
cur->page = newpage;
break;
}
mutex_unlock(&fi->inmem_lock);
put_page(page);
get_page(newpage);
}
if (PagePrivate(page)) {
f2fs_set_page_private(newpage, page_private(page));
f2fs_clear_page_private(page);
}
mm/migrate: new migrate mode MIGRATE_SYNC_NO_COPY Introduce a new migration mode that allow to offload the copy to a device DMA engine. This changes the workflow of migration and not all address_space migratepage callback can support this. This is intended to be use by migrate_vma() which itself is use for thing like HMM (see include/linux/hmm.h). No additional per-filesystem migratepage testing is needed. I disables MIGRATE_SYNC_NO_COPY in all problematic migratepage() callback and i added comment in those to explain why (part of this patch). The commit message is unclear it should say that any callback that wish to support this new mode need to be aware of the difference in the migration flow from other mode. Some of these callbacks do extra locking while copying (aio, zsmalloc, balloon, ...) and for DMA to be effective you want to copy multiple pages in one DMA operations. But in the problematic case you can not easily hold the extra lock accross multiple call to this callback. Usual flow is: For each page { 1 - lock page 2 - call migratepage() callback 3 - (extra locking in some migratepage() callback) 4 - migrate page state (freeze refcount, update page cache, buffer head, ...) 5 - copy page 6 - (unlock any extra lock of migratepage() callback) 7 - return from migratepage() callback 8 - unlock page } The new mode MIGRATE_SYNC_NO_COPY: 1 - lock multiple pages For each page { 2 - call migratepage() callback 3 - abort in all problematic migratepage() callback 4 - migrate page state (freeze refcount, update page cache, buffer head, ...) } // finished all calls to migratepage() callback 5 - DMA copy multiple pages 6 - unlock all the pages To support MIGRATE_SYNC_NO_COPY in the problematic case we would need a new callback migratepages() (for instance) that deals with multiple pages in one transaction. Because the problematic cases are not important for current usage I did not wanted to complexify this patchset even more for no good reason. Link: http://lkml.kernel.org/r/20170817000548.32038-14-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Nellans <dnellans@nvidia.com> Cc: Evgeny Baskakov <ebaskakov@nvidia.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Mark Hairgrove <mhairgrove@nvidia.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Sherry Cheung <SCheung@nvidia.com> Cc: Subhash Gutti <sgutti@nvidia.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Bob Liu <liubo95@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-09 02:12:06 +03:00
if (mode != MIGRATE_SYNC_NO_COPY)
migrate_page_copy(newpage, page);
else
migrate_page_states(newpage, page);
return MIGRATEPAGE_SUCCESS;
}
#endif
#ifdef CONFIG_SWAP
/* Copied from generic_swapfile_activate() to check any holes */
static int check_swap_activate(struct file *swap_file, unsigned int max)
{
struct address_space *mapping = swap_file->f_mapping;
struct inode *inode = mapping->host;
unsigned blocks_per_page;
unsigned long page_no;
unsigned blkbits;
sector_t probe_block;
sector_t last_block;
sector_t lowest_block = -1;
sector_t highest_block = 0;
blkbits = inode->i_blkbits;
blocks_per_page = PAGE_SIZE >> blkbits;
/*
* Map all the blocks into the extent list. This code doesn't try
* to be very smart.
*/
probe_block = 0;
page_no = 0;
last_block = i_size_read(inode) >> blkbits;
while ((probe_block + blocks_per_page) <= last_block && page_no < max) {
unsigned block_in_page;
sector_t first_block;
cond_resched();
first_block = bmap(inode, probe_block);
if (first_block == 0)
goto bad_bmap;
/*
* It must be PAGE_SIZE aligned on-disk
*/
if (first_block & (blocks_per_page - 1)) {
probe_block++;
goto reprobe;
}
for (block_in_page = 1; block_in_page < blocks_per_page;
block_in_page++) {
sector_t block;
block = bmap(inode, probe_block + block_in_page);
if (block == 0)
goto bad_bmap;
if (block != first_block + block_in_page) {
/* Discontiguity */
probe_block++;
goto reprobe;
}
}
first_block >>= (PAGE_SHIFT - blkbits);
if (page_no) { /* exclude the header page */
if (first_block < lowest_block)
lowest_block = first_block;
if (first_block > highest_block)
highest_block = first_block;
}
page_no++;
probe_block += blocks_per_page;
reprobe:
continue;
}
return 0;
bad_bmap:
pr_err("swapon: swapfile has holes\n");
return -EINVAL;
}
static int f2fs_swap_activate(struct swap_info_struct *sis, struct file *file,
sector_t *span)
{
struct inode *inode = file_inode(file);
int ret;
if (!S_ISREG(inode->i_mode))
return -EINVAL;
if (f2fs_readonly(F2FS_I_SB(inode)->sb))
return -EROFS;
ret = f2fs_convert_inline_inode(inode);
if (ret)
return ret;
ret = check_swap_activate(file, sis->max);
if (ret)
return ret;
set_inode_flag(inode, FI_PIN_FILE);
f2fs_precache_extents(inode);
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
return 0;
}
static void f2fs_swap_deactivate(struct file *file)
{
struct inode *inode = file_inode(file);
clear_inode_flag(inode, FI_PIN_FILE);
}
#else
static int f2fs_swap_activate(struct swap_info_struct *sis, struct file *file,
sector_t *span)
{
return -EOPNOTSUPP;
}
static void f2fs_swap_deactivate(struct file *file)
{
}
#endif
const struct address_space_operations f2fs_dblock_aops = {
.readpage = f2fs_read_data_page,
.readpages = f2fs_read_data_pages,
.writepage = f2fs_write_data_page,
.writepages = f2fs_write_data_pages,
.write_begin = f2fs_write_begin,
.write_end = f2fs_write_end,
.set_page_dirty = f2fs_set_data_page_dirty,
.invalidatepage = f2fs_invalidate_page,
.releasepage = f2fs_release_page,
.direct_IO = f2fs_direct_IO,
.bmap = f2fs_bmap,
.swap_activate = f2fs_swap_activate,
.swap_deactivate = f2fs_swap_deactivate,
#ifdef CONFIG_MIGRATION
.migratepage = f2fs_migrate_page,
#endif
};
void f2fs_clear_page_cache_dirty_tag(struct page *page)
{
struct address_space *mapping = page_mapping(page);
unsigned long flags;
xa_lock_irqsave(&mapping->i_pages, flags);
__xa_clear_mark(&mapping->i_pages, page_index(page),
PAGECACHE_TAG_DIRTY);
xa_unlock_irqrestore(&mapping->i_pages, flags);
}
int __init f2fs_init_post_read_processing(void)
{
f2fs: add fs-verity support Add fs-verity support to f2fs. fs-verity is a filesystem feature that enables transparent integrity protection and authentication of read-only files. It uses a dm-verity like mechanism at the file level: a Merkle tree is used to verify any block in the file in log(filesize) time. It is implemented mainly by helper functions in fs/verity/. See Documentation/filesystems/fsverity.rst for the full documentation. The f2fs support for fs-verity consists of: - Adding a filesystem feature flag and an inode flag for fs-verity. - Implementing the fsverity_operations to support enabling verity on an inode and reading/writing the verity metadata. - Updating ->readpages() to verify data as it's read from verity files and to support reading verity metadata pages. - Updating ->write_begin(), ->write_end(), and ->writepages() to support writing verity metadata pages. - Calling the fs-verity hooks for ->open(), ->setattr(), and ->ioctl(). Like ext4, f2fs stores the verity metadata (Merkle tree and fsverity_descriptor) past the end of the file, starting at the first 64K boundary beyond i_size. This approach works because (a) verity files are readonly, and (b) pages fully beyond i_size aren't visible to userspace but can be read/written internally by f2fs with only some relatively small changes to f2fs. Extended attributes cannot be used because (a) f2fs limits the total size of an inode's xattr entries to 4096 bytes, which wouldn't be enough for even a single Merkle tree block, and (b) f2fs encryption doesn't encrypt xattrs, yet the verity metadata *must* be encrypted when the file is because it contains hashes of the plaintext data. Acked-by: Jaegeuk Kim <jaegeuk@kernel.org> Acked-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Eric Biggers <ebiggers@google.com>
2019-07-22 19:26:24 +03:00
bio_post_read_ctx_cache =
kmem_cache_create("f2fs_bio_post_read_ctx",
sizeof(struct bio_post_read_ctx), 0, 0, NULL);
if (!bio_post_read_ctx_cache)
goto fail;
bio_post_read_ctx_pool =
mempool_create_slab_pool(NUM_PREALLOC_POST_READ_CTXS,
bio_post_read_ctx_cache);
if (!bio_post_read_ctx_pool)
goto fail_free_cache;
return 0;
fail_free_cache:
kmem_cache_destroy(bio_post_read_ctx_cache);
fail:
return -ENOMEM;
}
void f2fs_destroy_post_read_processing(void)
{
mempool_destroy(bio_post_read_ctx_pool);
kmem_cache_destroy(bio_post_read_ctx_cache);
}
int __init f2fs_init_bio_entry_cache(void)
{
bio_entry_slab = f2fs_kmem_cache_create("bio_entry_slab",
sizeof(struct bio_entry));
if (!bio_entry_slab)
return -ENOMEM;
return 0;
}
void __exit f2fs_destroy_bio_entry_cache(void)
{
kmem_cache_destroy(bio_entry_slab);
}