This file already uses sysfs_emit(). So be consistent and also use
sysfs_emit_at().
This slightly simplifies the code and makes it more readable.
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
atomic write can only be used via buffered IO, let's fail direct IO on
atomic_file and return -EOPNOTSUPP.
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
In f2fs_do_write_data_page, when the data block is NULL_ADDR, it skips
writepage considering that it has been already truncated.
This results in an infinite loop as the PAGECACHE_TAG_TOWRITE tag is not
cleared during the writeback process for a compressed file including
NULL_ADDR in compress_mode=user.
This is the reproduction process:
1. dd if=/dev/zero bs=4096 count=1024 seek=1024 of=testfile
2. f2fs_io compress testfile
3. dd if=/dev/zero bs=4096 count=1 conv=notrunc of=testfile
4. f2fs_io decompress testfile
To prevent the problem, let's check whether the cluster is fully
allocated before redirty its pages.
Fixes: 5fdb322ff2 ("f2fs: add F2FS_IOC_DECOMPRESS_FILE and F2FS_IOC_COMPRESS_FILE")
Reviewed-by: Sungjong Seo <sj1557.seo@samsung.com>
Reviewed-by: Sunmin Jeong <s_min.jeong@samsung.com>
Tested-by: Jaewook Kim <jw5454.kim@samsung.com>
Signed-off-by: Yeongjin Gil <youngjin.gil@samsung.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
As the helper function f2fs_bdev_support_discard() shows, f2fs checks if
the target block devices support discard by calling
bdev_max_discard_sectors() and bdev_is_zoned(). This check works well
for most cases, but it does not work for conventional zones on zoned
block devices. F2fs assumes that zoned block devices support discard,
and calls __submit_discard_cmd(). When __submit_discard_cmd() is called
for sequential write required zones, it works fine since
__submit_discard_cmd() issues zone reset commands instead of discard
commands. However, when __submit_discard_cmd() is called for
conventional zones, __blkdev_issue_discard() is called even when the
devices do not support discard.
The inappropriate __blkdev_issue_discard() call was not a problem before
the commit 30f1e72414 ("block: move discard checks into the ioctl
handler") because __blkdev_issue_discard() checked if the target devices
support discard or not. If not, it returned EOPNOTSUPP. After the
commit, __blkdev_issue_discard() no longer checks it. It always returns
zero and sets NULL to the given bio pointer. This NULL pointer triggers
f2fs_bug_on() in __submit_discard_cmd(). The BUG is recreated with the
commands below at the umount step, where /dev/nullb0 is a zoned null_blk
with 5GB total size, 128MB zone size and 10 conventional zones.
$ mkfs.f2fs -f -m /dev/nullb0
$ mount /dev/nullb0 /mnt
$ for ((i=0;i<5;i++)); do dd if=/dev/zero of=/mnt/test bs=65536 count=1600 conv=fsync; done
$ umount /mnt
To fix the BUG, avoid the inappropriate __blkdev_issue_discard() call.
When discard is requested for conventional zones, check if the device
supports discard or not. If not, return EOPNOTSUPP.
Fixes: 30f1e72414 ("block: move discard checks into the ioctl handler")
Cc: stable@vger.kernel.org
Signed-off-by: Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Chao Yu <chao@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Soft IRQ Thread
- f2fs_write_end_io
- f2fs_defragment_range
- set_page_private_gcing
- type = WB_DATA_TYPE(page, false);
: assign type w/ F2FS_WB_CP_DATA
due to page_private_gcing() is true
- dec_page_count() w/ wrong type
- end_page_writeback()
Value of F2FS_WB_CP_DATA reference count may become negative under above
race condition, the root cause is we missed to wait page writeback before
setting gcing page private flag, let's fix it.
Fixes: 2d1fe8a86b ("f2fs: fix to tag gcing flag on page during file defragment")
Fixes: 4961acdd65 ("f2fs: fix to tag gcing flag on page during block migration")
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
The i_pino in f2fs_inode_info has the previous parent's i_ino when inode
was renamed, which may cause f2fs_ioc_start_atomic_write to fail.
If file_wrong_pino is true and i_nlink is 1, then to find a valid pino,
we should refer to the dentry from inode.
To resolve this issue, let's get parent inode using parent dentry
directly.
Fixes: 3db1de0e58 ("f2fs: change the current atomic write way")
Reviewed-by: Sungjong Seo <sj1557.seo@samsung.com>
Reviewed-by: Sunmin Jeong <s_min.jeong@samsung.com>
Signed-off-by: Yeongjin Gil <youngjin.gil@samsung.com>
Reviewed-by: Daeho Jeong <daehojeong@google.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
The F2FS ioctls for starting and committing atomic writes check for
inode_owner_or_capable(), but this does not give LSMs like SELinux or
Landlock an opportunity to deny the write access - if the caller's FSUID
matches the inode's UID, inode_owner_or_capable() immediately returns true.
There are scenarios where LSMs want to deny a process the ability to write
particular files, even files that the FSUID of the process owns; but this
can currently partially be bypassed using atomic write ioctls in two ways:
- F2FS_IOC_START_ATOMIC_REPLACE + F2FS_IOC_COMMIT_ATOMIC_WRITE can
truncate an inode to size 0
- F2FS_IOC_START_ATOMIC_WRITE + F2FS_IOC_ABORT_ATOMIC_WRITE can revert
changes another process concurrently made to a file
Fix it by requiring FMODE_WRITE for these operations, just like for
F2FS_IOC_MOVE_RANGE. Since any legitimate caller should only be using these
ioctls when intending to write into the file, that seems unlikely to break
anything.
Fixes: 88b88a6679 ("f2fs: support atomic writes")
Cc: stable@vger.kernel.org
Signed-off-by: Jann Horn <jannh@google.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Reviewed-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Use F2FS_BYTES_TO_BLK(bytes) and F2FS_BLK_TO_BYTES(blk) for cleanup
Signed-off-by: Zhiguo Niu <zhiguo.niu@unisoc.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
This is a supplement to commit 6d1451bf7f ("f2fs: fix to use per-inode maxbytes")
for some missed cases, also cleanup redundant code in f2fs_llseek.
Cc: Chengguang Xu <cgxu519@mykernel.net>
Signed-off-by: Zhiguo Niu <zhiguo.niu@unisoc.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
We just need inode page when write inline data, use
f2fs_get_node_page() to get it instead of using dnode_of_data,
which can eliminate unnecessary struct use.
Signed-off-by: Zijie Wang <wangzijie1@honor.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
When we add "atgc" to the fstab table, ATGC is not immediately enabled.
There is a 7-day time threshold, and we can use "atgc_enabled" to
show whether ATGC is enabled.
Signed-off-by: liujinbao1 <liujinbao1@xiaomi.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
This reverts commit c550e25bca.
Commit c550e25bca ("f2fs: use flush
command instead of FUA for zoned device") used additional flush
command to keep write order.
Since Commit dd291d77cc ("block:
Introduce zone write plugging") has enabled the block layer to
handle this order issue, there is no need to use flush command.
Signed-off-by: Wenjie Cheng <cwjhust@gmail.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Convert to use folio and related functionality.
Cc: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
If lfs mode is on, buffered read may race w/ OPU dio write as below,
it may cause buffered read hits unwritten data unexpectly, and for
dio read, the race condition exists as well.
Thread A Thread B
- f2fs_file_write_iter
- f2fs_dio_write_iter
- __iomap_dio_rw
- f2fs_iomap_begin
- f2fs_map_blocks
- __allocate_data_block
- allocated blkaddr #x
- iomap_dio_submit_bio
- f2fs_file_read_iter
- filemap_read
- f2fs_read_data_folio
- f2fs_mpage_readpages
- f2fs_map_blocks
: get blkaddr #x
- f2fs_submit_read_bio
IRQ
- f2fs_read_end_io
: read IO on blkaddr #x complete
IRQ
- iomap_dio_bio_end_io
: direct write IO on blkaddr #x complete
In LFS mode, if there is inflight dio, let's wait for its completion,
this policy won't cover all race cases, however it is a tradeoff which
avoids abusing lock around IO paths.
Fixes: f847c699cf ("f2fs: allow out-place-update for direct IO in LFS mode")
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
It should wait all existing dio write IOs before block removal,
otherwise, previous direct write IO may overwrite data in the
block which may be reused by other inode.
Cc: stable@vger.kernel.org
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
We may trigger high frequent checkpoint for below case:
1. mkdir /mnt/dir1; set dir1 encrypted
2. touch /mnt/file1; fsync /mnt/file1
3. mkdir /mnt/dir2; set dir2 encrypted
4. touch /mnt/file2; fsync /mnt/file2
...
Although, newly created dir and file are not related, due to
commit bbf156f7af ("f2fs: fix lost xattrs of directories"), we will
trigger checkpoint whenever fsync() comes after a new encrypted dir
created.
In order to avoid such performance regression issue, let's record an
entry including directory's ino in global cache whenever we update
directory's xattr data, and then triggerring checkpoint() only if
xattr metadata of target file's parent was updated.
This patch updates to cover below no encryption case as well:
1) parent is checkpointed
2) set_xattr(dir) w/ new xnid
3) create(file)
4) fsync(file)
Fixes: bbf156f7af ("f2fs: fix lost xattrs of directories")
Reported-by: wangzijie <wangzijie1@honor.com>
Reported-by: Zhiguo Niu <zhiguo.niu@unisoc.com>
Tested-by: Zhiguo Niu <zhiguo.niu@unisoc.com>
Reported-by: Yunlei He <heyunlei@hihonor.com>
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Case #1:
SQLite App GC Thread Kworker Shrinker
- f2fs_ioc_start_atomic_write
- f2fs_ioc_commit_atomic_write
- f2fs_commit_atomic_write
- filemap_write_and_wait_range
: write atomic_file's data to cow_inode
echo 3 > drop_caches
to drop atomic_file's
cache.
- f2fs_gc
- gc_data_segment
- move_data_page
- set_page_dirty
- writepages
- f2fs_do_write_data_page
: overwrite atomic_file's data
to cow_inode
- f2fs_down_write(&fi->i_gc_rwsem[WRITE])
- __f2fs_commit_atomic_write
- f2fs_up_write(&fi->i_gc_rwsem[WRITE])
Case #2:
SQLite App GC Thread Kworker
- f2fs_ioc_start_atomic_write
- __writeback_single_inode
- do_writepages
- f2fs_write_cache_pages
- f2fs_write_single_data_page
- f2fs_do_write_data_page
: write atomic_file's data to cow_inode
- f2fs_gc
- gc_data_segment
- move_data_page
- set_page_dirty
- writepages
- f2fs_do_write_data_page
: overwrite atomic_file's data to cow_inode
- f2fs_ioc_commit_atomic_write
In above cases racing in between atomic_write and GC, previous
data in atomic_file may be overwrited to cow_file, result in
data corruption.
This patch introduces PAGE_PRIVATE_ATOMIC_WRITE bit flag in page.private,
and use it to indicate that there is last dirty data in atomic file,
and the data should be writebacked into cow_file, if the flag is not
tagged in page, we should never write data across files.
Fixes: 3db1de0e58 ("f2fs: change the current atomic write way")
Cc: Daeho Jeong <daehojeong@google.com>
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
The macro stat_inc_cp_count accepts a parameter si,
but it was not used, rather the variable sbi was directly used,
which may be a local variable inside a function that calls the macros.
Signed-off-by: Julian Sun <sunjunchao2870@gmail.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
The macro on_f2fs_build_free_nids accepts a parameter nmi,
but it was not used, rather the variable nm_i was directly used,
which may be a local variable inside a function that calls the macros.
Signed-off-by: Julian Sun <sunjunchao2870@gmail.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Currently, we are using a mix of traditional UFS and zone UFS to support
some functionalities that cannot be achieved on zone UFS alone. However,
there are some issues with this approach. There exists a significant
performance difference between traditional UFS and zone UFS. Under normal
usage, we prioritize writes to zone UFS. However, in critical conditions
(such as when the entire UFS is almost full), we cannot determine whether
data will be written to traditional UFS or zone UFS. This can lead to
significant performance fluctuations, which is not conducive to
development and testing. To address this, we have added an option
zlu_io_enable under sys with the following three modes:
1) zlu_io_enable == 0:Normal mode, prioritize writing to zone UFS;
2) zlu_io_enable == 1:Zone UFS only mode, only allow writing to zone UFS;
3) zlu_io_enable == 2:Traditional UFS priority mode, prioritize writing to
traditional UFS.
Signed-off-by: Liao Yuanhong <liaoyuanhong@vivo.com>
Signed-off-by: Wu Bo <bo.wu@vivo.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
While calculating the end addresses of main area and segment 0, u32
may be not enough to hold the result without the danger of int
overflow.
Just in case, play it safe and cast one of the operands to a
wider type (u64).
Found by Linux Verification Center (linuxtesting.org) with static
analysis tool SVACE.
Fixes: fd694733d5 ("f2fs: cover large section in sanity check of super")
Cc: stable@vger.kernel.org
Signed-off-by: Nikita Zhandarovich <n.zhandarovich@fintech.ru>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
When dealing with large extents and calculating file offsets by
summing up according extent offsets and lengths of unsigned int type,
one may encounter possible integer overflow if the values are
big enough.
Prevent this from happening by expanding one of the addends to
(pgoff_t) type.
Found by Linux Verification Center (linuxtesting.org) with static
analysis tool SVACE.
Fixes: d323d005ac ("f2fs: support file defragment")
Cc: stable@vger.kernel.org
Signed-off-by: Nikita Zhandarovich <n.zhandarovich@fintech.ru>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
The result of multiplication between values derived from functions
dir_buckets() and bucket_blocks() *could* technically reach
2^30 * 2^2 = 2^32.
While unlikely to happen, it is prudent to ensure that it will not
lead to integer overflow. Thus, use mul_u32_u32() as it's more
appropriate to mitigate the issue.
Found by Linux Verification Center (linuxtesting.org) with static
analysis tool SVACE.
Fixes: 3843154598 ("f2fs: introduce large directory support")
Cc: stable@vger.kernel.org
Signed-off-by: Nikita Zhandarovich <n.zhandarovich@fintech.ru>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Introudce a new help get_dnode_base() to wrap common code from
get_dnode_addr() and data_blkaddr() for cleanup.
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
It's a pretty small update including mostly minor bug fixes in zoned storage
along with the large section support.
Enhancement:
- add support for FS_IOC_GETFSSYSFSPATH
- enable atgc dynamically if conditions are met
- use new ioprio Macro to get ckpt thread ioprio level
- remove unreachable lazytime mount option parsing
Bug fix:
- fix null reference error when checking end of zone
- fix start segno of large section
- fix to cover read extent cache access with lock
- don't dirty inode for readonly filesystem
- allocate a new section if curseg is not the first seg in its zone
- only fragment segment in the same section
- truncate preallocated blocks in f2fs_file_open()
- fix to avoid use SSR allocate when do defragment
- fix to force buffered IO on inline_data inode
And, it includes some minor code clean-ups, and sanity checks.
-----BEGIN PGP SIGNATURE-----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=4m67
-----END PGP SIGNATURE-----
Merge tag 'f2fs-for-6.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs
Pull f2fs updates from Jaegeuk Kim:
"A pretty small update including mostly minor bug fixes in zoned
storage along with the large section support.
Enhancements:
- add support for FS_IOC_GETFSSYSFSPATH
- enable atgc dynamically if conditions are met
- use new ioprio Macro to get ckpt thread ioprio level
- remove unreachable lazytime mount option parsing
Bug fixes:
- fix null reference error when checking end of zone
- fix start segno of large section
- fix to cover read extent cache access with lock
- don't dirty inode for readonly filesystem
- allocate a new section if curseg is not the first seg in its zone
- only fragment segment in the same section
- truncate preallocated blocks in f2fs_file_open()
- fix to avoid use SSR allocate when do defragment
- fix to force buffered IO on inline_data inode
And some minor code clean-ups and sanity checks"
* tag 'f2fs-for-6.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (26 commits)
f2fs: clean up addrs_per_{inode,block}()
f2fs: clean up F2FS_I()
f2fs: use meta inode for GC of COW file
f2fs: use meta inode for GC of atomic file
f2fs: only fragment segment in the same section
f2fs: fix to update user block counts in block_operations()
f2fs: remove unreachable lazytime mount option parsing
f2fs: fix null reference error when checking end of zone
f2fs: fix start segno of large section
f2fs: remove redundant sanity check in sanity_check_inode()
f2fs: assign CURSEG_ALL_DATA_ATGC if blkaddr is valid
f2fs: fix to use mnt_{want,drop}_write_file replace file_{start,end}_wrtie
f2fs: clean up set REQ_RAHEAD given rac
f2fs: enable atgc dynamically if conditions are met
f2fs: fix to truncate preallocated blocks in f2fs_file_open()
f2fs: fix to cover read extent cache access with lock
f2fs: fix return value of f2fs_convert_inline_inode()
f2fs: use new ioprio Macro to get ckpt thread ioprio level
f2fs: fix to don't dirty inode for readonly filesystem
f2fs: fix to avoid use SSR allocate when do defragment
...
-----BEGIN PGP SIGNATURE-----
iHUEABYKAB0WIQRAhzRXHqcMeLMyaSiRxhvAZXjcogUCZpEGnAAKCRCRxhvAZXjc
om4UAP4xnLigNBMHqoWTvfbBjxfoPcWTq53M9CM/T2t2iz4AsQD+NiUQLmNO/LDJ
8aZ0K5TI2+uWYUHbyLabmKWwAm33UQ0=
=ZeeN
-----END PGP SIGNATURE-----
Merge tag 'vfs-6.11.casefold' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs
Pull vfs casefolding updates from Christian Brauner:
"This contains some work to simplify the handling of casefolded names:
- Simplify the handling of casefolded names in f2fs and ext4 by
keeping the names as a qstr to avoiding unnecessary conversions
- Introduce a new generic_ci_match() libfs case-insensitive lookup
helper and use it in both f2fs and ext4 allowing to remove the
filesystem specific implementations
- Remove a bunch of ifdefs by making the unicode build checks part of
the code flow"
* tag 'vfs-6.11.casefold' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs:
f2fs: Move CONFIG_UNICODE defguards into the code flow
ext4: Move CONFIG_UNICODE defguards into the code flow
f2fs: Reuse generic_ci_match for ci comparisons
ext4: Reuse generic_ci_match for ci comparisons
libfs: Introduce case-insensitive string comparison helper
f2fs: Simplify the handling of cached casefolded names
ext4: Simplify the handling of cached casefolded names
Introduce a new help addrs_per_page() to wrap common code
from addrs_per_inode() and addrs_per_block() for cleanup.
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
In case of the COW file, new updates and GC writes are already
separated to page caches of the atomic file and COW file. As some cases
that use the meta inode for GC, there are some race issues between a
foreground thread and GC thread.
To handle them, we need to take care when to invalidate and wait
writeback of GC pages in COW files as the case of using the meta inode.
Also, a pointer from the COW inode to the original inode is required to
check the state of original pages.
For the former, we can solve the problem by using the meta inode for GC
of COW files. Then let's get a page from the original inode in
move_data_block when GCing the COW file to avoid race condition.
Fixes: 3db1de0e58 ("f2fs: change the current atomic write way")
Cc: stable@vger.kernel.org #v5.19+
Reviewed-by: Sungjong Seo <sj1557.seo@samsung.com>
Reviewed-by: Yeongjin Gil <youngjin.gil@samsung.com>
Signed-off-by: Sunmin Jeong <s_min.jeong@samsung.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
The page cache of the atomic file keeps new data pages which will be
stored in the COW file. It can also keep old data pages when GCing the
atomic file. In this case, new data can be overwritten by old data if a
GC thread sets the old data page as dirty after new data page was
evicted.
Also, since all writes to the atomic file are redirected to COW inodes,
GC for the atomic file is not working well as below.
f2fs_gc(gc_type=FG_GC)
- select A as a victim segment
do_garbage_collect
- iget atomic file's inode for block B
move_data_page
f2fs_do_write_data_page
- use dn of cow inode
- set fio->old_blkaddr from cow inode
- seg_freed is 0 since block B is still valid
- goto gc_more and A is selected as victim again
To solve the problem, let's separate GC writes and updates in the atomic
file by using the meta inode for GC writes.
Fixes: 3db1de0e58 ("f2fs: change the current atomic write way")
Cc: stable@vger.kernel.org #v5.19+
Reviewed-by: Sungjong Seo <sj1557.seo@samsung.com>
Reviewed-by: Yeongjin Gil <youngjin.gil@samsung.com>
Signed-off-by: Sunmin Jeong <s_min.jeong@samsung.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
When new_curseg() is allocating a new segment, if mode=fragment:xxx is
switched on in large section scenario, __get_next_segno() will select
the next segno randomly in the range of [0, maxsegno] in order to
fragment segments.
If the candidate segno is free, get_new_segment() will use it directly
as the new segment.
However, if the section of the candidate is not empty, and some other
segments have already been used, and have a different type (e.g NODE)
with the candidate (e.g DATA), GC will complain inconsistent segment
type later.
This could be reproduced by the following steps:
dd if=/dev/zero of=test.img bs=1M count=10240
mkfs.f2fs -s 128 test.img
mount -t f2fs test.img /mnt -o mode=fragment:block
echo 1 > /sys/fs/f2fs/loop0/max_fragment_chunk
echo 512 > /sys/fs/f2fs/loop0/max_fragment_hole
dd if=/dev/zero of=/mnt/testfile bs=4K count=100
umount /mnt
F2FS-fs (loop0): Inconsistent segment (4377) type [0, 1] in SSA and SIT
In order to allow simulating segment fragmentation in large section
scenario, this patch reduces the candidate range:
* if curseg is the last segment in the section, return curseg->segno
to make get_new_segment() itself find the next free segment.
* if curseg is in the middle of the section, select candicate randomly
in the range of [curseg + 1, last_seg_in_the_same_section] to keep
type consistent.
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Sheng Yong <shengyong@oppo.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Commit 59c9081bc8 ("f2fs: allow write page cache when writting cp")
allows write() to write data to page cache during checkpoint, so block
count fields like .total_valid_block_count, .alloc_valid_block_count
and .rf_node_block_count may encounter race condition as below:
CP Thread A
- write_checkpoint
- block_operations
- f2fs_down_write(&sbi->node_change)
- __prepare_cp_block
: ckpt->valid_block_count = .total_valid_block_count
- f2fs_up_write(&sbi->node_change)
- write
- f2fs_preallocate_blocks
- f2fs_map_blocks(,F2FS_GET_BLOCK_PRE_AIO)
- f2fs_map_lock
- f2fs_down_read(&sbi->node_change)
- f2fs_reserve_new_blocks
- inc_valid_block_count
: percpu_counter_add(&sbi->alloc_valid_block_count, count)
: sbi->total_valid_block_count += count
- f2fs_up_read(&sbi->node_change)
- do_checkpoint
: sbi->last_valid_block_count = sbi->total_valid_block_count
: percpu_counter_set(&sbi->alloc_valid_block_count, 0)
: percpu_counter_set(&sbi->rf_node_block_count, 0)
- fsync
- need_do_checkpoint
- f2fs_space_for_roll_forward
: alloc_valid_block_count was reset to zero,
so, it may missed last data during checkpoint
Let's change to update .total_valid_block_count, .alloc_valid_block_count
and .rf_node_block_count in block_operations(), then their access can be
protected by .node_change and .cp_rwsem lock, so that it can avoid above
race condition.
Fixes: 59c9081bc8 ("f2fs: allow write page cache when writting cp")
Cc: Yunlei He <heyunlei@oppo.com>
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
The lazytime/nolazytime options are now handled in the VFS, and are
never seen in filesystem parsers, so remove handling of these
options from f2fs.
Note: when lazytime support was added in 6d94c74ab8 it made
lazytime the default in default_options() - as a result, lazytime
cannot be disabled (because Opt_nolazytime is never seen in f2fs
parsing).
If lazytime is desired to be configurable, and default off is OK,
default_options() could be updated to stop setting it by default
and allow mount option control.
Signed-off-by: Eric Sandeen <sandeen@redhat.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
This patch fixes a potentially null pointer being accessed by
is_end_zone_blkaddr() that checks the last block of a zone
when f2fs is mounted as a single device.
Fixes: e067dc3c6b ("f2fs: maintain six open zones for zoned devices")
Signed-off-by: Daejun Park <daejun7.park@samsung.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Reviewed-by: Daeho Jeong <daehojeong@google.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
get_ckpt_valid_blocks() checks valid ckpt blocks in current section.
It counts all vblocks from the first to the last segment in the
large section. However, START_SEGNO() is used to get the first segno
in an SIT block. This patch fixes that to get the correct start segno.
Fixes: 61461fc921 ("f2fs: fix to avoid touching checkpointed data in get_victim()")
Signed-off-by: Sheng Yong <shengyong@oppo.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
The routine is used by procfs through dir_emit_dots.
The combined RCU and lock fallback implementation is too big for an
inline. Given that the routine takes a dentry argument fs/dcache.c seems
like the place to put it in.
Signed-off-by: Mateusz Guzik <mjguzik@gmail.com>
Link: https://lore.kernel.org/r/20240627161152.802567-1-mjguzik@gmail.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
Commit f240d3aaf5 ("f2fs: do more sanity check on inode") missed
to remove redundant sanity check on flexible_inline_xattr flag, fix
it.
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
mkdir /mnt/test/comp
f2fs_io setflags compression /mnt/test/comp
dd if=/dev/zero of=/mnt/test/comp/testfile bs=16k count=1
truncate --size 13 /mnt/test/comp/testfile
In the above scenario, we can get a BUG_ON.
kernel BUG at fs/f2fs/segment.c:3589!
Call Trace:
do_write_page+0x78/0x390 [f2fs]
f2fs_outplace_write_data+0x62/0xb0 [f2fs]
f2fs_do_write_data_page+0x275/0x740 [f2fs]
f2fs_write_single_data_page+0x1dc/0x8f0 [f2fs]
f2fs_write_multi_pages+0x1e5/0xae0 [f2fs]
f2fs_write_cache_pages+0xab1/0xc60 [f2fs]
f2fs_write_data_pages+0x2d8/0x330 [f2fs]
do_writepages+0xcf/0x270
__writeback_single_inode+0x44/0x350
writeback_sb_inodes+0x242/0x530
__writeback_inodes_wb+0x54/0xf0
wb_writeback+0x192/0x310
wb_workfn+0x30d/0x400
The reason is we gave CURSEG_ALL_DATA_ATGC to COMPR_ADDR where the
page was set the gcing flag by set_cluster_dirty().
Cc: stable@vger.kernel.org
Fixes: 4961acdd65 ("f2fs: fix to tag gcing flag on page during block migration")
Reviewed-by: Chao Yu <chao@kernel.org>
Tested-by: Will McVicker <willmcvicker@google.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
mnt_{want,drop}_write_file is more suitable than
file_{start,end}_wrtie and also is consistent with
other ioctl operations.
Signed-off-by: Zhiguo Niu <zhiguo.niu@unisoc.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Now atgc can only be enabled when umounted->mounted device
even related conditions have reached. If the device has not
be umounted->mounted for a long time, atgc can not work.
So enable atgc dynamically when atgc_age_threshold is less than
elapsed_time and ATGC mount option is on.
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Zhiguo Niu <zhiguo.niu@unisoc.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
chenyuwen reports a f2fs bug as below:
Unable to handle kernel NULL pointer dereference at virtual address 0000000000000011
fscrypt_set_bio_crypt_ctx+0x78/0x1e8
f2fs_grab_read_bio+0x78/0x208
f2fs_submit_page_read+0x44/0x154
f2fs_get_read_data_page+0x288/0x5f4
f2fs_get_lock_data_page+0x60/0x190
truncate_partial_data_page+0x108/0x4fc
f2fs_do_truncate_blocks+0x344/0x5f0
f2fs_truncate_blocks+0x6c/0x134
f2fs_truncate+0xd8/0x200
f2fs_iget+0x20c/0x5ac
do_garbage_collect+0x5d0/0xf6c
f2fs_gc+0x22c/0x6a4
f2fs_disable_checkpoint+0xc8/0x310
f2fs_fill_super+0x14bc/0x1764
mount_bdev+0x1b4/0x21c
f2fs_mount+0x20/0x30
legacy_get_tree+0x50/0xbc
vfs_get_tree+0x5c/0x1b0
do_new_mount+0x298/0x4cc
path_mount+0x33c/0x5fc
__arm64_sys_mount+0xcc/0x15c
invoke_syscall+0x60/0x150
el0_svc_common+0xb8/0xf8
do_el0_svc+0x28/0xa0
el0_svc+0x24/0x84
el0t_64_sync_handler+0x88/0xec
It is because inode.i_crypt_info is not initialized during below path:
- mount
- f2fs_fill_super
- f2fs_disable_checkpoint
- f2fs_gc
- f2fs_iget
- f2fs_truncate
So, let's relocate truncation of preallocated blocks to f2fs_file_open(),
after fscrypt_file_open().
Fixes: d4dd19ec1e ("f2fs: do not expose unwritten blocks to user by DIO")
Reported-by: chenyuwen <yuwen.chen@xjmz.com>
Closes: https://lore.kernel.org/linux-kernel/20240517085327.1188515-1-yuwen.chen@xjmz.com
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
IOPRIO_PRIO_DATA in the new kernel version includes level and hint,
So Macro IOPRIO_PRIO_LEVEL is more accurate to get ckpt thread
ioprio data/level, and it is also consisten with the way setting
ckpt thread ioprio by IOPRIO_PRIO_VALUE(class, data/level).
Besides, change variable name from "data" to "level" for more readable.
Signed-off-by: Zhiguo Niu <zhiguo.niu@unisoc.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
