Grab a folio instead of a page. Also convert seg_info_to_sit_page() to
seg_info_to_sit_folio() and use a folio in f2fs_flush_sit_entries().
Saves a couple of calls to compound_head().
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
The only caller which passes a page already has a folio, so pass
it in.
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
This helper returns the inode associated with the f2fs_io_info. That's a
relatively common thing to want, mildly awkward to get and provides one
place to change if we decide to record it directly, or change fio->page
to fio->folio.
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
[Jaegeuk Kim: fix wrong fio_inode conversion]
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
1. After we start atomic write in a database file, before committing
all data, we'd better not set inode w/ vfs dirty status to avoid
redundant updates, instead, we only set inode w/ atomic dirty status.
2. After we commit all data, before committing metadata, we need to
clear atomic dirty status, and set vfs dirty status to allow vfs flush
dirty inode.
Cc: Daeho Jeong <daehojeong@google.com>
Reported-by: Zhiguo Niu <zhiguo.niu@unisoc.com>
Signed-off-by: Chao Yu <chao@kernel.org>
Reviewed-by: Daeho Jeong <daehojeong@google.com>
Reviewed-by: Zhiguo Niu <zhiguo.niu@unisoc.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
During a checkpoint, the current active segment X may not be handled
properly. This occurs when segment X has 0 valid blocks and a non-zero
number of discard blocks, for the following reasons:
locate_dirty_segment() does not mark any active segment as a prefree
segment. As a result, segment X is not included in dirty_segmap[PRE], and
f2fs_clear_prefree_segments() skips it when handling prefree segments.
add_discard_addrs() skips any segment with 0 valid blocks, so segment X is
also skipped.
Consequently, no `struct discard_cmd` is actually created for segment X.
However, the ckpt_valid_map and cur_valid_map of segment X are synced by
seg_info_to_raw_sit() during the current checkpoint process. As a result,
it cannot find the missing discard bits even in subsequent checkpoints.
Consequently, the value of sbi->discard_blks remains non-zero. Thus, when
f2fs is umounted, CP_TRIMMED_FLAG will not be set due to the non-zero
sbi->discard_blks.
Relevant code process:
f2fs_write_checkpoint()
f2fs_flush_sit_entries()
list_for_each_entry_safe(ses, tmp, head, set_list) {
for_each_set_bit_from(segno, bitmap, end) {
...
add_discard_addrs(sbi, cpc, false); // skip segment X due to its 0 valid blocks
...
seg_info_to_raw_sit(); // sync ckpt_valid_map with cur_valid_map for segment X
...
}
}
f2fs_clear_prefree_segments(); // segment X is not included in dirty_segmap[PRE] and is skipped
This issue is easy to reproduce with the following operations:
root # mkfs.f2fs -f /dev/f2fs_dev
root # mount -t f2fs /dev/f2fs_dev /mnt_point
root # dd if=/dev/blk_dev of=/mnt_point/1.bin bs=4k count=256
root # sync
root # rm /mnt_point/1.bin
root # umount /mnt_point
root # dump.f2fs /dev/f2fs_dev | grep "checkpoint state"
Info: checkpoint state = 45 : crc compacted_summary unmount ---- 'trimmed' flag is missing
Since add_discard_addrs() can handle active segments with non-zero valid
blocks, it is reasonable to fix this issue by allowing it to also handle
active segments with 0 valid blocks.
Fixes: b29555505d ("f2fs: add key functions for small discards")
Signed-off-by: Chunhai Guo <guochunhai@vivo.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
All its callers now have access to a folio, so pass it in. Removes
an access to page->mapping.
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Convert fio->page to a folio then use it where folio APIs exist.
Removes a reference to page->mapping and a hidden call to
compound_head().
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Convert f2fs_wait_on_page_writeback() to f2fs_folio_wait_writeback()
and add a compatibiility wrapper. Replaces five calls to
compound_head() with one.
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
commit 4f993264fe ("f2fs: introduce discard_unit mount option") introduced
a bug, when we enable discard_unit=section option, it will set
.discard_granularity to BLKS_PER_SEC(), however discard granularity only
supports [1, 512], once section size is not equal to segment size, it will
cause issue_discard_thread() in DPOLICY_BG mode will not select discard entry
w/ any granularity to issue.
Fixes: 4f993264fe ("f2fs: introduce discard_unit mount option")
Reviewed-by: Daeho Jeong <daehojeong@google.com>
Signed-off-by: Yohan Joung <yohan.joung@sk.com>
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
syzbot reports a f2fs bug as below:
------------[ cut here ]------------
kernel BUG at fs/f2fs/segment.c:2746!
CPU: 0 UID: 0 PID: 5323 Comm: syz.0.0 Not tainted 6.13.0-rc2-syzkaller-00018-g7cb1b4663150 #0
RIP: 0010:get_new_segment fs/f2fs/segment.c:2746 [inline]
RIP: 0010:new_curseg+0x1f52/0x1f70 fs/f2fs/segment.c:2876
Call Trace:
<TASK>
__allocate_new_segment+0x1ce/0x940 fs/f2fs/segment.c:3210
f2fs_allocate_new_section fs/f2fs/segment.c:3224 [inline]
f2fs_allocate_pinning_section+0xfa/0x4e0 fs/f2fs/segment.c:3238
f2fs_expand_inode_data+0x696/0xca0 fs/f2fs/file.c:1830
f2fs_fallocate+0x537/0xa10 fs/f2fs/file.c:1940
vfs_fallocate+0x569/0x6e0 fs/open.c:327
do_vfs_ioctl+0x258c/0x2e40 fs/ioctl.c:885
__do_sys_ioctl fs/ioctl.c:904 [inline]
__se_sys_ioctl+0x80/0x170 fs/ioctl.c:892
do_syscall_x64 arch/x86/entry/common.c:52 [inline]
do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83
entry_SYSCALL_64_after_hwframe+0x77/0x7f
Concurrent pinfile allocation may run out of free section, result in
panic in get_new_segment(), let's expand pin_sem lock coverage to
include f2fs_gc(), so that we can make sure to reclaim enough free
space for following allocation.
In addition, do below changes to enhance error path handling:
- call f2fs_bug_on() only in non-pinfile allocation path in
get_new_segment().
- call reset_curseg_fields() to reset all fields of curseg in
new_curseg()
Fixes: f5a53edcf0 ("f2fs: support aligned pinned file")
Reported-by: syzbot+15669ec8c35ddf6c3d43@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/linux-f2fs-devel/675cd64e.050a0220.37aaf.00bb.GAE@google.com
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
When testing the atomic write fix patches, the f2fs_bug_on was
triggered as below:
------------[ cut here ]------------
kernel BUG at fs/f2fs/inode.c:935!
Oops: invalid opcode: 0000 [#1] PREEMPT SMP PTI
CPU: 3 UID: 0 PID: 257 Comm: bash Not tainted 6.13.0-rc1-00033-gc283a70d3497 #5
RIP: 0010:f2fs_evict_inode+0x50f/0x520
Call Trace:
<TASK>
? __die_body+0x65/0xb0
? die+0x9f/0xc0
? do_trap+0xa1/0x170
? f2fs_evict_inode+0x50f/0x520
? f2fs_evict_inode+0x50f/0x520
? handle_invalid_op+0x65/0x80
? f2fs_evict_inode+0x50f/0x520
? exc_invalid_op+0x39/0x50
? asm_exc_invalid_op+0x1a/0x20
? __pfx_f2fs_get_dquots+0x10/0x10
? f2fs_evict_inode+0x50f/0x520
? f2fs_evict_inode+0x2e5/0x520
evict+0x186/0x2f0
prune_icache_sb+0x75/0xb0
super_cache_scan+0x1a8/0x200
do_shrink_slab+0x163/0x320
shrink_slab+0x2fc/0x470
drop_slab+0x82/0xf0
drop_caches_sysctl_handler+0x4e/0xb0
proc_sys_call_handler+0x183/0x280
vfs_write+0x36d/0x450
ksys_write+0x68/0xd0
do_syscall_64+0xc8/0x1a0
? arch_exit_to_user_mode_prepare+0x11/0x60
? irqentry_exit_to_user_mode+0x7e/0xa0
The root cause is: f2fs uses FI_ATOMIC_DIRTIED to indicate dirty
atomic files during commit. If the inode is dirtied during commit,
such as by f2fs_i_pino_write, the vfs inode keeps clean and the
f2fs inode is set to FI_DIRTY_INODE. The FI_DIRTY_INODE flag cann't
be cleared by write_inode later due to the clean vfs inode. Finally,
f2fs_bug_on is triggered due to this inconsistent state when evict.
To reproduce this situation:
- fd = open("/mnt/test.db", O_WRONLY)
- ioctl(fd, F2FS_IOC_START_ATOMIC_WRITE)
- mv /mnt/test.db /mnt/test1.db
- ioctl(fd, F2FS_IOC_COMMIT_ATOMIC_WRITE)
- echo 3 > /proc/sys/vm/drop_caches
To fix this problem, clear FI_DIRTY_INODE after commit, then
f2fs_mark_inode_dirty_sync will ensure a consistent dirty state.
Fixes: fccaa81de8 ("f2fs: prevent atomic file from being dirtied before commit")
Signed-off-by: Yunlei He <heyunlei@xiaomi.com>
Signed-off-by: Jianan Huang <huangjianan@xiaomi.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
The following two 'check only recovery' processes are very dependent on
the return value of f2fs_recover_fsync_data, especially when the return
value is greater than 0.
1. when device has readonly mode, shown as commit
23738e7447 ("f2fs: fix to restrict mount condition on readonly block device")
2. mount optiont NORECOVERY or DISABLE_ROLL_FORWARD is set, shown as commit
6781eabba1 ("f2fs: give -EINVAL for norecovery and rw mount")
However, commit c426d99127 ("f2fs: Check write pointer consistency of open zones")
will change the return value unexpectedly, thereby changing the caller's behavior
This patch let the f2fs_recover_fsync_data return correct value,and not do
f2fs_check_and_fix_write_pointer when the device is read-only.
Fixes: c426d99127 ("f2fs: Check write pointer consistency of open zones")
Signed-off-by: Zhiguo Niu <zhiguo.niu@unisoc.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
New function can process some consecutive blocks at a time.
Function f2fs_invalidate_blocks()->down_write() and up_write()
are very time-consuming, so if f2fs_invalidate_blocks() can
process consecutive blocks at one time, it will save a lot of time.
Signed-off-by: Yi Sun <yi.sun@unisoc.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
This function can process some consecutive blocks at a time.
When using update_sit_entry() to release consecutive blocks,
ensure that the consecutive blocks belong to the same segment.
Because after update_sit_entry_for_realese(), @segno is still
in use in update_sit_entry().
Signed-off-by: Yi Sun <yi.sun@unisoc.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
No logical changes, just for cleanliness.
Signed-off-by: Yi Sun <yi.sun@unisoc.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
New function can process some consecutive blocks at a time.
Signed-off-by: Yi Sun <yi.sun@unisoc.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Piergiorgio reported a bug in bugzilla as below:
------------[ cut here ]------------
WARNING: CPU: 2 PID: 969 at fs/f2fs/segment.c:1330
RIP: 0010:__submit_discard_cmd+0x27d/0x400 [f2fs]
Call Trace:
__issue_discard_cmd+0x1ca/0x350 [f2fs]
issue_discard_thread+0x191/0x480 [f2fs]
kthread+0xcf/0x100
ret_from_fork+0x31/0x50
ret_from_fork_asm+0x1a/0x30
w/ below testcase, it can reproduce this bug quickly:
- pvcreate /dev/vdb
- vgcreate myvg1 /dev/vdb
- lvcreate -L 1024m -n mylv1 myvg1
- mount /dev/myvg1/mylv1 /mnt/f2fs
- dd if=/dev/zero of=/mnt/f2fs/file bs=1M count=20
- sync
- rm /mnt/f2fs/file
- sync
- lvcreate -L 1024m -s -n mylv1-snapshot /dev/myvg1/mylv1
- umount /mnt/f2fs
The root cause is: it will update discard_max_bytes of mounted lvm
device to zero after creating snapshot on this lvm device, then,
__submit_discard_cmd() will pass parameter @nr_sects w/ zero value
to __blkdev_issue_discard(), it returns a NULL bio pointer, result
in panic.
This patch changes as below for fixing:
1. Let's drop all remained discards in f2fs_unfreeze() if snapshot
of lvm device is created.
2. Checking discard_max_bytes before submitting discard during
__submit_discard_cmd().
Cc: stable@vger.kernel.org
Fixes: 35ec7d5748 ("f2fs: split discard command in prior to block layer")
Reported-by: Piergiorgio Sartor <piergiorgio.sartor@nexgo.de>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=219484
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Fsync data recovery attempts to check and fix write pointer consistency
of cursegs and all other zones. If the write pointers of cursegs are
unaligned, cursegs are changed to new sections.
If recovery fails, zone write pointers are still checked and fixed,
but the latest checkpoint cannot be written back. Additionally, retry-
mount skips recovery and rolls back to reuse the old cursegs whose
zones are already finished. This can lead to unaligned write later.
This patch addresses the issue by leaving writer pointers untouched if
recovery fails. When retry-mount is performed, cursegs and other zones
are checked and fixed after skipping recovery.
Signed-off-by: Song Feng <songfeng@oppo.com>
Signed-off-by: Yongpeng Yang <yangyongpeng1@oppo.com>
Signed-off-by: Sheng Yong <shengyong@oppo.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
This patch introduces a new helper log_type_to_seg_type() to convert
log type to segment data type, and uses it to clean up opened codes
in build_curseg(), and also it fixes to convert log type before use
in do_write_page().
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
In __get_segment_type(), __get_segment_type_6() may return
CURSEG_COLD_DATA_PINNED or CURSEG_ALL_DATA_ATGC log type, but
following f2fs_get_segment_temp() can only handle persistent
log type, fix it.
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
In the __f2fs_init_atgc_curseg->get_atssr_segment calling,
curseg->segno is NULL_SEGNO, indicating that there is no summary
block that needs to be written.
Fixes: 093749e296 ("f2fs: support age threshold based garbage collection")
Signed-off-by: Yongpeng Yang <yangyongpeng1@oppo.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
This f2fs_bug_on was introduced by commit 2c1905042c ("f2fs: check
segment type in __f2fs_replace_block") when there were only 6 curseg types.
After commit d0b9e42ab6 ("f2fs: introduce inmem curseg") was introduced,
the condition should be changed to checking curseg->seg_type.
Fixes: d0b9e42ab6 ("f2fs: introduce inmem curseg")
Signed-off-by: LongPing Wei <weilongping@oppo.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
first_zoned_segno() returns a fixed value, let's cache it in
structure f2fs_sb_info to avoid redundant calculation.
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Now we reclaim too much space before allocating pinned space for zoned
devices.
Signed-off-by: Daeho Jeong <daehojeong@google.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
When segs_per_sec is larger than 1, section may contain invalid segments,
mtime should be the average value of each valid blocks,
so introduce f2fs_get_section_mtime to
record the average mtime of all valid blocks in a section.
Signed-off-by: liuderong <liuderong@oppo.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
We need to introduce a valid block ratio threshold not to trigger
excessive GC for zoned deivces. The initial value of it is 95%. So, F2FS
will stop the thread from intiating GC for sections having valid blocks
exceeding the ratio.
Signed-off-by: Daeho Jeong <daehojeong@google.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Keep atomic file clean while updating and make it dirtied during commit
in order to avoid unnecessary and excessive inode updates in the previous
fix.
Fixes: 4bf7832234 ("f2fs: mark inode dirty for FI_ATOMIC_COMMITTED flag")
Signed-off-by: Daeho Jeong <daehojeong@google.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Convert to use folio, so that we can get rid of 'page->index' to
prepare for removal of 'index' field in structure page [1].
[1] https://lore.kernel.org/all/Zp8fgUSIBGQ1TN0D@casper.infradead.org/
Cc: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Chao Yu <chao@kernel.org>
Reviewed-by: Li Zetao <lizetao1@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Convert to use folio, so that we can get rid of 'page->index' to
prepare for removal of 'index' field in structure page [1].
[1] https://lore.kernel.org/all/Zp8fgUSIBGQ1TN0D@casper.infradead.org/
Cc: Matthew Wilcox <willy@infradead.org>
Signed-off-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>
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>
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>
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>
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>
If curseg is not the first segment in its zone, the zone is not empty.
A new section should be allocated and avoid resetting the old zone.
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Sheng Yong <shengyong@oppo.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Following the semantic for dirty segments in checkpoint disabled mode,
apply the same rule to dirty sections.
Signed-off-by: Daeho Jeong <daehojeong@google.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Commit b1c9d3f833 ("f2fs: support printk_ratelimited() in f2fs_printk()")
missed some cases, cover all remains for cleanup.
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
If active_log is not 6, we never use WARM_DATA segment, let's
avoid allocating WARM_DATA segment for direct IO.
Signed-off-by: Yunlei He <heyunlei@oppo.com>
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
To make code clean, use blk_zone_cond_str() to print debug information.
Signed-off-by: Wu Bo <bo.wu@vivo.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
This reverts commit 930e260763 ("f2fs: remove obsolete whint_mode"), as we
decide to pass write hints to the disk.
Cc: Hyunchul Lee <cheol.lee@lge.com>
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
While do not allocating a new section in advance for file pinning area, I
missed that we should write the sum block for the last segment of a file
pinning section.
Fixes: 9703d69d9d ("f2fs: support file pinning for zoned devices")
Signed-off-by: Daeho Jeong <daehojeong@google.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
In this round, there are a number of updates on mainly two areas: Zoned block
device support and Per-file compression. For example, we've found several issues
to support Zoned block device especially having large sections regarding to GC
and file pinning used for Android devices. In compression side, we've fixed many
corner race conditions that had broken the design assumption.
Enhancement:
- Support file pinning for Zoned block device having large section
- Enhance the data recovery after sudden power cut on Zoned block device
- Add more error injection cases to easily detect the kernel panics
- add a proc entry show the entire disk layout
- Improve various error paths paniced by BUG_ON in block allocation and GC
- support SEEK_DATA and SEEK_HOLE for compression files
Bug fix:
- fix to avoid use-after-free issue in f2fs_filemap_fault
- fix some race conditions to break the atomic write design assumption
- fix to truncate meta inode pages forcely
- resolve various per-file compression issues wrt the space management and
compression policies
- fix some swap-related bugs
In addition, we removed deprecated codes such as io_bits and heap_allocation,
and also fixed minor error handling routines with neat debugging messages.
-----BEGIN PGP SIGNATURE-----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=Qpvy
-----END PGP SIGNATURE-----
Merge tag 'f2fs-for-6.9-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs
Pull f2fs update from Jaegeuk Kim:
"In this round, there are a number of updates on mainly two areas:
Zoned block device support and Per-file compression. For example,
we've found several issues to support Zoned block device especially
having large sections regarding to GC and file pinning used for
Android devices. In compression side, we've fixed many corner race
conditions that had broken the design assumption.
Enhancements:
- Support file pinning for Zoned block device having large section
- Enhance the data recovery after sudden power cut on Zoned block
device
- Add more error injection cases to easily detect the kernel panics
- add a proc entry show the entire disk layout
- Improve various error paths paniced by BUG_ON in block allocation
and GC
- support SEEK_DATA and SEEK_HOLE for compression files
Bug fixes:
- avoid use-after-free issue in f2fs_filemap_fault
- fix some race conditions to break the atomic write design
assumption
- fix to truncate meta inode pages forcely
- resolve various per-file compression issues wrt the space
management and compression policies
- fix some swap-related bugs
In addition, we removed deprecated codes such as io_bits and
heap_allocation, and also fixed minor error handling routines with
neat debugging messages"
* tag 'f2fs-for-6.9-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (60 commits)
f2fs: fix to avoid use-after-free issue in f2fs_filemap_fault
f2fs: truncate page cache before clearing flags when aborting atomic write
f2fs: mark inode dirty for FI_ATOMIC_COMMITTED flag
f2fs: prevent atomic write on pinned file
f2fs: fix to handle error paths of {new,change}_curseg()
f2fs: unify the error handling of f2fs_is_valid_blkaddr
f2fs: zone: fix to remove pow2 check condition for zoned block device
f2fs: fix to truncate meta inode pages forcely
f2fs: compress: fix reserve_cblocks counting error when out of space
f2fs: compress: relocate some judgments in f2fs_reserve_compress_blocks
f2fs: add a proc entry show disk layout
f2fs: introduce SEGS_TO_BLKS/BLKS_TO_SEGS for cleanup
f2fs: fix to check return value of f2fs_gc_range
f2fs: fix to check return value __allocate_new_segment
f2fs: fix to do sanity check in update_sit_entry
f2fs: fix to reset fields for unloaded curseg
f2fs: clean up new_curseg()
f2fs: relocate f2fs_precache_extents() in f2fs_swap_activate()
f2fs: fix blkofs_end correctly in f2fs_migrate_blocks()
f2fs: ro: don't start discard thread for readonly image
...
In f2fs_do_write_data_page, FI_ATOMIC_FILE flag selects the target inode
between the original inode and COW inode. When aborting atomic write and
writeback occur simultaneously, invalid data can be written to original
inode if the FI_ATOMIC_FILE flag is cleared meanwhile.
To prevent the problem, let's truncate all pages before clearing the flag
Atomic write thread Writeback thread
f2fs_abort_atomic_write
clear_inode_flag(inode, FI_ATOMIC_FILE)
__writeback_single_inode
do_writepages
f2fs_do_write_data_page
- use dn of original inode
truncate_inode_pages_final
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: Daeho Jeong <daehojeong@google.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
{new,change}_curseg() may return error in some special cases,
error handling should be did in their callers, and this will also
facilitate subsequent error path expansion in {new,change}_curseg().
Signed-off-by: Zhiguo Niu <zhiguo.niu@unisoc.com>
Signed-off-by: Chao Yu <chao@kernel.org>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
There are some cases of f2fs_is_valid_blkaddr not handled as
ERROR_INVALID_BLKADDR,so unify the error handling about all of
f2fs_is_valid_blkaddr.
Do f2fs_handle_error in __f2fs_is_valid_blkaddr for cleanup.
Signed-off-by: Zhiguo Niu <zhiguo.niu@unisoc.com>
Signed-off-by: Chao Yu <chao@kernel.org>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Below race case can cause data corruption:
Thread A GC thread
- gc_data_segment
- ra_data_block
- locked meta_inode page
- f2fs_inplace_write_data
- invalidate_mapping_pages
: fail to invalidate meta_inode page
due to lock failure or dirty|writeback
status
- f2fs_submit_page_bio
: write last dirty data to old blkaddr
- move_data_block
- load old data from meta_inode page
- f2fs_submit_page_write
: write old data to new blkaddr
Because invalidate_mapping_pages() will skip invalidating page which
has unclear status including locked, dirty, writeback and so on, so
we need to use truncate_inode_pages_range() instead of
invalidate_mapping_pages() to make sure meta_inode page will be dropped.
Fixes: 6aa58d8ad2 ("f2fs: readahead encrypted block during GC")
Fixes: e3b49ea368 ("f2fs: invalidate META_MAPPING before IPU/DIO write")
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
f2fs_gc_range may return error, so its caller
f2fs_allocate_pinning_section should determine whether
to do retry based on ist return value.
Also just do f2fs_gc_range when f2fs_allocate_new_section
return -EAGAIN, and check cp error case in f2fs_gc_range.
Signed-off-by: Zhiguo Niu <zhiguo.niu@unisoc.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
__allocate_new_segment may return error when get_new_segment
fails, so its caller should check its return value.
Signed-off-by: Zhiguo Niu <zhiguo.niu@unisoc.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
If GET_SEGNO return NULL_SEGNO for some unecpected case,
update_sit_entry will access invalid memory address,
cause system crash. It is better to do sanity check about
GET_SEGNO just like update_segment_mtime & locate_dirty_segment.
Also remove some redundant judgment code.
Signed-off-by: Zhiguo Niu <zhiguo.niu@unisoc.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
In f2fs_allocate_data_block(), before skip allocating new segment
for DATA_PINNED log header, it needs to tag log header as unloaded
one to avoid skipping logic in locate_dirty_segment() and
__f2fs_save_inmem_curseg().
Signed-off-by: Chao Yu <chao@kernel.org>
Reviewed-by: Daeho Jeong <daehojeong@google.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Move f2fs_valid_pinned_area() check logic from new_curseg() to
get_new_segment(), it can avoid calling __set_free() if it fails
to find free segment in conventional zone for pinned file.
Signed-off-by: Chao Yu <chao@kernel.org>
Reviewed-by: Daeho Jeong <daehojeong@google.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
@type in f2fs_allocate_data_block() indicates log header's type, it
can be CURSEG_COLD_DATA_PINNED or CURSEG_ALL_DATA_ATGC, rather than
type of data/node, however IS_DATASEG()/IS_NODESEG() only accept later
one, fix it.
Fixes: 093749e296 ("f2fs: support age threshold based garbage collection")
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Don't block mounting the partition, if cap is 100%.
Reviewed-by: Chao Yu <chao@kernel.org>
Reviewed-by: Daeho Jeong <daehojeong@google.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
No functional change, but add some more logs.
Note, it includes the spelling mistakes pointed by Colin Ian King.
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Use it to simulate no free segment case during block allocation.
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
If CONFIG_F2FS_CHECK_FS is off, and for very rare corner case that
we run out of free segment, we should not panic kernel, instead,
let's handle such error correctly in its caller.
Signed-off-by: Chao Yu <chao@kernel.org>
Tested-by: Zhiguo Niu <zhiguo.niu@unisoc.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
There is low probability that an out-of-bounds segment will be got
on a small-capacity device. In order to prevent subsequent write requests
allocating block address from this invalid segment, which may cause
unexpected issue, stop checkpoint should be performed.
Also introduce a new stop cp reason: STOP_CP_REASON_NO_SEGMENT.
Note, f2fs_stop_checkpoint(, false) is complex and it may sleep, so we should
move it outside segmap_lock spinlock coverage in get_new_segment().
Signed-off-by: Zhiguo Niu <zhiguo.niu@unisoc.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Support file pinning with conventional storage area for zoned devices
Signed-off-by: Daeho Jeong <daehojeong@google.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
No one uses this feature. Let's kill it.
Reviewed-by: Daeho Jeong <daehojeong@google.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Let's deprecate an unused io_bits feature to save CPU cycles and memory.
Reviewed-by: Daeho Jeong <daehojeong@google.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Now that all callers pass in GFP_KERNEL to blkdev_zone_mgmt() and use
memalloc_no{io,fs}_{save,restore}() to define the allocation scope, we can
drop the gfp_mask parameter from blkdev_zone_mgmt() as well as
blkdev_zone_reset_all() and blkdev_zone_reset_all_emulated().
Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Mike Snitzer <snitzer@kernel.org>
Link: https://lore.kernel.org/r/20240128-zonefs_nofs-v3-5-ae3b7c8def61@wdc.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Guard the calls to blkdev_zone_mgmt() with a memalloc_nofs scope.
This helps us getting rid of the GFP_NOFS argument to blkdev_zone_mgmt();
Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Chao Yu <chao@kernel.org>
Link: https://lore.kernel.org/r/20240128-zonefs_nofs-v3-4-ae3b7c8def61@wdc.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
In reserve_compress_blocks(), we update blkaddrs of dnode in prior to
inc_valid_block_count(), it may cause inconsistent status bewteen
i_blocks and blkaddrs once inc_valid_block_count() fails.
To fix this issue, it needs to reverse their invoking order.
Fixes: c75488fb4d ("f2fs: introduce F2FS_IOC_RESERVE_COMPRESS_BLOCKS")
Reviewed-by: Daeho Jeong <daehojeong@google.com>
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
'f2fs_is_checkpoint_ready()' checks free sections. If there is not
enough free sections, most f2fs operations will return -ENOSPC when
checkpoint is disabled.
It would be better to check free sections before disable checkpoint.
Signed-off-by: Wu Bo <bo.wu@vivo.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
A freezable kernel thread can enter frozen state during freezing by
either calling try_to_freeze() or using wait_event_freezable() and its
variants. So for the following snippet of code in a kernel thread loop:
wait_event_interruptible_timeout();
try_to_freeze();
We can change it to a simple wait_event_freezable_timeout() and then
eliminate the function calls to try_to_freeze() and freezing().
Signed-off-by: Kevin Hao <haokexin@gmail.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
In order to limit # of open zones, let's finish or reset zones given # of
valid blocks per section and its zone condition.
Reviewed-by: Daeho Jeong <daehojeong@google.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
If fsck can allocate a new zone, it'd be better to use that instead of
allocating a new one.
And, it modifies kernel messages.
Reviewed-by: Daeho Jeong <daehojeong@google.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
It gives a way to enable/disable IO aware feature for background
discard, so that we can tune background discard more precisely
based on undiscard condition. e.g. force to disable IO aware if
there are large number of discard extents, and discard IO may
always be interrupted by frequent common IO.
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
When recovering zoned UFS, sometimes we add the same zone to discard multiple
times. Simple workaround is to bypass adding it.
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
We can't trust write pointers when the previous mount was not
successfully unmounted.
Signed-off-by: Daeho Jeong <daehojeong@google.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Use the finish zone command first when a zone should be closed.
Signed-off-by: Daeho Jeong <daehojeong@google.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Previously, we have two mechanisms to cache & submit small discards:
a) set max small discard number in /sys/fs/f2fs/vdb/max_small_discards,
and checkpoint will cache small discard candidates w/ configured maximum
number.
b) call FITRIM ioctl, also, checkpoint in f2fs_trim_fs() will cache small
discard candidates w/ configured discard granularity, but w/o limitation
of number. FSTRIM interface is asynchronized, so it won't submit discard
directly.
Finally, discard thread will submit them in background periodically.
However, after commit 9ac00e7cef ("f2fs: do not issue small discard
commands during checkpoint"), the mechanism a) is broken, since no matter
how we configure the sysfs entry /sys/fs/f2fs/vdb/max_small_discards,
checkpoint will not cache small discard candidates any more.
echo 0 > /sys/fs/f2fs/vdb/max_small_discards
xfs_io -f /mnt/f2fs/file -c "pwrite 0 2m" -c "fsync"
xfs_io /mnt/f2fs/file -c "fpunch 0 4k"
sync
cat /proc/fs/f2fs/vdb/discard_plist_info |head -2
echo 100 > /sys/fs/f2fs/vdb/max_small_discards
rm /mnt/f2fs/file
xfs_io -f /mnt/f2fs/file -c "pwrite 0 2m" -c "fsync"
xfs_io /mnt/f2fs/file -c "fpunch 0 4k"
sync
cat /proc/fs/f2fs/vdb/discard_plist_info |head -2
Before the patch:
Discard pend list(Show diacrd_cmd count on each entry, .:not exist):
0 . . . . . . . .
Discard pend list(Show diacrd_cmd count on each entry, .:not exist):
0 3 1 . . . . . .
After the patch:
Discard pend list(Show diacrd_cmd count on each entry, .:not exist):
0 . . . . . . . .
Discard pend list(Show diacrd_cmd count on each entry, .:not exist):
0 . . . . . . . .
This patch reverts commit 9ac00e7cef ("f2fs: do not issue small discard
commands during checkpoint") in order to fix this issue.
Fixes: 9ac00e7cef ("f2fs: do not issue small discard commands during checkpoint")
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
As reported, status debugfs entry shows inconsistent GC stats as below:
GC calls: 6008 (BG: 6161)
- data segments : 3053 (BG: 3053)
- node segments : 2955 (BG: 2955)
Total GC calls is larger than BGGC calls, the reason is:
- f2fs_stat_info.call_count accounts total migrated section count
by f2fs_gc()
- f2fs_stat_info.bg_gc accounts total call times of f2fs_gc() from
background gc_thread
Another issue is gc_foreground_calls sysfs entry shows total GC call
count rather than FGGC call count.
This patch changes as below for fix:
- account GC calls and migrated segment count separately
- support to account migrated section count if it enables large section
mode
- fix to show correct value in gc_foreground_calls sysfs entry
Fixes: fc7100ea2a ("f2fs: Add f2fs stats to sysfs")
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
The commit 25f9080576 ("f2fs: add async reset zone command support")
introduced "async reset zone commands" by calling
__submit_zone_reset_cmd() in async discard operations. However,
__submit_zone_reset_cmd() is called regardless of zone type of discard
target zone. When devices have conventional zones, zone reset commands
are sent to the conventional zones and cause I/O errors.
Avoid the I/O errors by checking that the discard target zone type is
sequential write required. If not, handle the discard operation in same
manner as non-zoned, regular block devices. For that purpose, add a new
helper function f2fs_bdev_index() which gets index of the zone reset
target device.
Fixes: 25f9080576 ("f2fs: add async reset zone command support")
Signed-off-by: Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
This reverts commit bfd4766239.
Shinichiro Kawasaki reported:
When I ran workloads on f2fs using v6.5-rcX with fixes [1][2] and a zoned block
devices with 4kb logical block size, I observe mount failure as follows. When
I revert this commit, the failure goes away.
[ 167.781975][ T1555] F2FS-fs (dm-0): IO Block Size: 4 KB
[ 167.890728][ T1555] F2FS-fs (dm-0): Found nat_bits in checkpoint
[ 171.482588][ T1555] F2FS-fs (dm-0): Zone without valid block has non-zero write pointer. Reset the write pointer: wp[0x1300,0x8]
[ 171.496000][ T1555] F2FS-fs (dm-0): (0) : Unaligned zone reset attempted (block 280000 + 80000)
[ 171.505037][ T1555] F2FS-fs (dm-0): Discard zone failed: (errno=-5)
The patch replaced "sbi->log_blocksize - SECTOR_SHIFT" with
"sbi->log_sectors_per_block". However, I think these two are not equal when the
device has 4k logical block size. The former uses Linux kernel sector size 512
byte. The latter use 512b sector size or 4kb sector size depending on the
device. mkfs.f2fs obtains logical block size via BLKSSZGET ioctl from the device
and reflects it to the value sbi->log_sector_size_per_block. This causes
unexpected write pointer calculations in check_zone_write_pointer(). This
resulted in unexpected zone reset and the mount failure.
[1] https://lkml.kernel.org/linux-f2fs-devel/20230711050101.GA19128@lst.de/
[2] https://lore.kernel.org/linux-f2fs-devel/20230804091556.2372567-1-shinichiro.kawasaki@wdc.com/
Cc: stable@vger.kernel.org
Reported-by: Shinichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Fixes: bfd4766239 ("f2fs: clean up w/ sbi->log_sectors_per_block")
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
If there're huge # of small discards, this will increase checkpoint latency
insanely. Let's issue small discards only by trim.
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
We don't need to report an issue, when the zone write pointer already
points to the end of the zone, since the zone mismatch is already taken
care.
Signed-off-by: Daeho Jeong <daehojeong@google.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
This patch enables submit reset zone command asynchornously. It helps
decrease average latency of write IOs in high utilization scenario by
faster checkpointing.
Signed-off-by: Daejun Park <daejun7.park@samsung.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Use sbi->log_sectors_per_block to clean up below calculated one:
unsigned int log_sectors_per_block = sbi->log_blocksize - SECTOR_SHIFT;
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Zoned UFS allows only 6 open zones at the same time, so we need to take
care of the count of open zones while mounting.
Signed-off-by: Daeho Jeong <daehojeong@google.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
When a node block is missing for atomic write block replacement, we need
to allocate it in advance of the replacement.
Signed-off-by: Daeho Jeong <daehojeong@google.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
In __replace_atomic_write_block(), we missed to check return value
of inc_valid_block_count(), for extreme testcase that f2fs image is
run out of space, it may cause inconsistent status in between SIT
table and total valid block count.
Cc: Daeho Jeong <daehojeong@google.com>
Fixes: 3db1de0e58 ("f2fs: change the current atomic write way")
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
We should not pass relative address in a zone to
__f2fs_issue_discard_zone().
Signed-off-by: Daeho Jeong <daehojeong@google.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
There is only single instance of these ops, and Jaegeuk point out that:
Originally this was intended to give a chance to provide other
allocation option. Anyway, it seems quit hard to do it anymore.
So remove the indirection and call f2fs_get_victim() directly.
Signed-off-by: Yangtao Li <frank.li@vivo.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
