linux.git/fs/f2fs/segment.c, branch v6.7

f2fs: clean up zones when not successfully unmounted

2023-10-16T19:51:32+00:00

We can't trust write pointers when the previous mount was not
successfully unmounted.

Signed-off-by: Daeho Jeong 
Reviewed-by: Chao Yu 
Signed-off-by: Jaegeuk Kim

f2fs: use finish zone command when closing a zone

2023-08-25T17:30:37+00:00

Use the finish zone command first when a zone should be closed.

Signed-off-by: Daeho Jeong 
Signed-off-by: Jaegeuk Kim

Revert "f2fs: do not issue small discard commands during checkpoint"

2023-08-18T21:28:34+00:00

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 9ac00e7cef10 ("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 9ac00e7cef10 ("f2fs: do not issue small discard
commands during checkpoint") in order to fix this issue.

Fixes: 9ac00e7cef10 ("f2fs: do not issue small discard commands during checkpoint")
Signed-off-by: Chao Yu 
Signed-off-by: Jaegeuk Kim

f2fs: fix to account cp stats correctly

2023-08-14T20:42:05+00:00

cp_foreground_calls sysfs entry shows total CP call count rather than
foreground CP call count, fix it.

Fixes: fc7100ea2a52 ("f2fs: Add f2fs stats to sysfs")
Signed-off-by: Chao Yu 
Signed-off-by: Jaegeuk Kim

f2fs: fix to account gc stats correctly

2023-08-14T20:41:57+00:00

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: fc7100ea2a52 ("f2fs: Add f2fs stats to sysfs")
Signed-off-by: Chao Yu 
Signed-off-by: Jaegeuk Kim

f2fs: check zone type before sending async reset zone command

2023-08-14T20:41:09+00:00

The commit 25f9080576b9 ("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: 25f9080576b9 ("f2fs: add async reset zone command support")
Signed-off-by: Shin'ichiro Kawasaki 
Reviewed-by: Chao Yu 
Signed-off-by: Jaegeuk Kim

f2fs: flush inode if atomic file is aborted

2023-08-14T20:41:07+00:00

Let's flush the inode being aborted atomic operation to avoid stale dirty
inode during eviction in this call stack:

  f2fs_mark_inode_dirty_sync+0x22/0x40 [f2fs]
  f2fs_abort_atomic_write+0xc4/0xf0 [f2fs]
  f2fs_evict_inode+0x3f/0x690 [f2fs]
  ? sugov_start+0x140/0x140
  evict+0xc3/0x1c0
  evict_inodes+0x17b/0x210
  generic_shutdown_super+0x32/0x120
  kill_block_super+0x21/0x50
  deactivate_locked_super+0x31/0x90
  cleanup_mnt+0x100/0x160
  task_work_run+0x59/0x90
  do_exit+0x33b/0xa50
  do_group_exit+0x2d/0x80
  __x64_sys_exit_group+0x14/0x20
  do_syscall_64+0x3b/0x90
  entry_SYSCALL_64_after_hwframe+0x63/0xcd

This triggers f2fs_bug_on() in f2fs_evict_inode:
 f2fs_bug_on(sbi, is_inode_flag_set(inode, FI_DIRTY_INODE));

This fixes the syzbot report:

loop0: detected capacity change from 0 to 131072
F2FS-fs (loop0): invalid crc value
F2FS-fs (loop0): Found nat_bits in checkpoint
F2FS-fs (loop0): Mounted with checkpoint version = 48b305e4
------------[ cut here ]------------
kernel BUG at fs/f2fs/inode.c:869!
invalid opcode: 0000 [#1] PREEMPT SMP KASAN
CPU: 0 PID: 5014 Comm: syz-executor220 Not tainted 6.4.0-syzkaller-11479-g6cd06ab12d1a #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/27/2023
RIP: 0010:f2fs_evict_inode+0x172d/0x1e00 fs/f2fs/inode.c:869
Code: ff df 48 c1 ea 03 80 3c 02 00 0f 85 6a 06 00 00 8b 75 40 ba 01 00 00 00 4c 89 e7 e8 6d ce 06 00 e9 aa fc ff ff e8 63 22 e2 fd <0f> 0b e8 5c 22 e2 fd 48 c7 c0 a8 3a 18 8d 48 ba 00 00 00 00 00 fc
RSP: 0018:ffffc90003a6fa00 EFLAGS: 00010293
RAX: 0000000000000000 RBX: 0000000000000001 RCX: 0000000000000000
RDX: ffff8880273b8000 RSI: ffffffff83a2bd0d RDI: 0000000000000007
RBP: ffff888077db91b0 R08: 0000000000000007 R09: 0000000000000000
R10: 0000000000000001 R11: 0000000000000001 R12: ffff888029a3c000
R13: ffff888077db9660 R14: ffff888029a3c0b8 R15: ffff888077db9c50
FS:  0000000000000000(0000) GS:ffff8880b9800000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f1909bb9000 CR3: 00000000276a9000 CR4: 0000000000350ef0
Call Trace:
 
 evict+0x2ed/0x6b0 fs/inode.c:665
 dispose_list+0x117/0x1e0 fs/inode.c:698
 evict_inodes+0x345/0x440 fs/inode.c:748
 generic_shutdown_super+0xaf/0x480 fs/super.c:478
 kill_block_super+0x64/0xb0 fs/super.c:1417
 kill_f2fs_super+0x2af/0x3c0 fs/f2fs/super.c:4704
 deactivate_locked_super+0x98/0x160 fs/super.c:330
 deactivate_super+0xb1/0xd0 fs/super.c:361
 cleanup_mnt+0x2ae/0x3d0 fs/namespace.c:1254
 task_work_run+0x16f/0x270 kernel/task_work.c:179
 exit_task_work include/linux/task_work.h:38 [inline]
 do_exit+0xa9a/0x29a0 kernel/exit.c:874
 do_group_exit+0xd4/0x2a0 kernel/exit.c:1024
 __do_sys_exit_group kernel/exit.c:1035 [inline]
 __se_sys_exit_group kernel/exit.c:1033 [inline]
 __x64_sys_exit_group+0x3e/0x50 kernel/exit.c:1033
 do_syscall_x64 arch/x86/entry/common.c:50 [inline]
 do_syscall_64+0x39/0xb0 arch/x86/entry/common.c:80
 entry_SYSCALL_64_after_hwframe+0x63/0xcd
RIP: 0033:0x7f309be71a09
Code: Unable to access opcode bytes at 0x7f309be719df.
RSP: 002b:00007fff171df518 EFLAGS: 00000246 ORIG_RAX: 00000000000000e7
RAX: ffffffffffffffda RBX: 00007f309bef7330 RCX: 00007f309be71a09
RDX: 000000000000003c RSI: 00000000000000e7 RDI: 0000000000000001
RBP: 0000000000000001 R08: ffffffffffffffc0 R09: 00007f309bef1e40
R10: 0000000000010600 R11: 0000000000000246 R12: 00007f309bef7330
R13: 0000000000000001 R14: 0000000000000000 R15: 0000000000000001
 
Modules linked in:
---[ end trace 0000000000000000 ]---
RIP: 0010:f2fs_evict_inode+0x172d/0x1e00 fs/f2fs/inode.c:869
Code: ff df 48 c1 ea 03 80 3c 02 00 0f 85 6a 06 00 00 8b 75 40 ba 01 00 00 00 4c 89 e7 e8 6d ce 06 00 e9 aa fc ff ff e8 63 22 e2 fd <0f> 0b e8 5c 22 e2 fd 48 c7 c0 a8 3a 18 8d 48 ba 00 00 00 00 00 fc
RSP: 0018:ffffc90003a6fa00 EFLAGS: 00010293
RAX: 0000000000000000 RBX: 0000000000000001 RCX: 0000000000000000
RDX: ffff8880273b8000 RSI: ffffffff83a2bd0d RDI: 0000000000000007
RBP: ffff888077db91b0 R08: 0000000000000007 R09: 0000000000000000
R10: 0000000000000001 R11: 0000000000000001 R12: ffff888029a3c000
R13: ffff888077db9660 R14: ffff888029a3c0b8 R15: ffff888077db9c50
FS:  0000000000000000(0000) GS:ffff8880b9800000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f1909bb9000 CR3: 00000000276a9000 CR4: 0000000000350ef0

Cc: 
Reported-and-tested-by: syzbot+e1246909d526a9d470fa@syzkaller.appspotmail.com
Reviewed-by: Chao Yu 
Signed-off-by: Jaegeuk Kim

Revert "f2fs: clean up w/ sbi->log_sectors_per_block"

2023-08-14T20:40:27+00:00

This reverts commit bfd476623999118d9c509cb0fa9380f2912bc225.

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 
Fixes: bfd476623999 ("f2fs: clean up w/ sbi->log_sectors_per_block")
Reviewed-by: Chao Yu 
Signed-off-by: Jaegeuk Kim

f2fs: do not issue small discard commands during checkpoint

2023-06-26T13:21:41+00:00

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

f2fs: check zone write pointer points to the end of zone

2023-06-26T13:07:10+00:00

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 
Signed-off-by: Jaegeuk Kim