Skip to contentSkip to conversation

f2fs: assign CURSEG_ALL_DATA_ATGC if blkaddr is valid

PATCH Applied Jaegeuk Kim 4 participants 4 messages Jun 18, 2024 – Jun 24, 2024

Subsystems (2)
lore
Share & tools
lore

Jaegeuk Kim

author maintainer
#0 lore raw

PATCH 1/1 f2fs: assign CURSEG_ALL_DATA_ATGC if blkaddr is valid

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().

Fixes 4961acdd65c9 ("f2fs: fix to tag gcing flag on page during block migration")
---
 fs/f2fs/segment.c | 1 +
 1 file changed, 1 insertion(+)
fs/f2fs/segment.c +1 -0
index 6e8a4b332ad5..ce2300391031 100644
@@ -3484,6 +3484,7 @@ static int __get_segment_type_6(struct f2fs_io_info *fio)
 			if (fio->sbi->am.atgc_enabled &&
 				(fio->io_type == FS_DATA_IO) &&
 				(fio->sbi->gc_mode != GC_URGENT_HIGH) &&
+				__is_valid_data_blkaddr(fio->old_blkaddr) &&
 				!is_inode_flag_set(inode, FI_OPU_WRITE))
 				return CURSEG_ALL_DATA_ATGC;
 			else
Signature · 1 line
2.45.2.627.g7a2c4fd464-goog
maintainer Reviewed-by on v1 1/1
#1 lore raw
Quoted 22 lines · Jaegeuk Kim

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
Quoted 6 lines

The reason is we gave CURSEG_ALL_DATA_ATGC to COMPR_ADDR where the page was set the gcing flag by set_cluster_dirty().

Fixes 4961acdd65c9 ("f2fs: fix to tag gcing flag on page during block migration")

Thanks,

#2 lore raw
Quoted 23 lines · Chao Yu
Quoted 22 lines · Jaegeuk Kim

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
Quoted 8 lines
Quoted 6 lines

The reason is we gave CURSEG_ALL_DATA_ATGC to COMPR_ADDR where the page was set the gcing flag by set_cluster_dirty().

Fixes 4961acdd65c9 ("f2fs: fix to tag gcing flag on page during block migration")

Hi Jaegeuk,

I've been running my personal Pixel 8a device with this change for the past 3 days and haven't hit any kernal panics since applying it. Feel free to include:

Thanks,
Will

#3 lore raw
In reply to Jaegeuk Kim
This patch was applied to jaegeuk/f2fs.git (dev) by Jaegeuk Kim <[email protected]>:

Hello:

This patch was applied to jaegeuk/f2fs.git (dev)
by Jaegeuk Kim <[email protected]>:

Quoted 22 lines · On Tue, 18 Jun 2024 02:23:34 +0000 you wrote:

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
Quoted 1 line

[...]

Here is the summary with links:
- [f2fs-dev] f2fs: assign CURSEG_ALL_DATA_ATGC if blkaddr is valid

    https://git.kernel.org/jaegeuk/f2fs/c/8cb1f4080dd9

You are awesome, thank you!

Signature · 2 lines
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html