f2fs: assign CURSEG_ALL_DATA_ATGC if blkaddr is valid

[PATCH] f2fs: assign CURSEG_ALL_DATA_ATGC if blkaddr is valid

Posted by Jaegeuk Kim 1 year, 6 months ago

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: 4961acdd65c9 ("f2fs: fix to tag gcing flag on page during block migration")
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/segment.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 6e8a4b332ad5..ce2300391031 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -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
-- 
2.45.2.627.g7a2c4fd464-goog

Re: [f2fs-dev] [PATCH] f2fs: assign CURSEG_ALL_DATA_ATGC if blkaddr is valid

Posted by Chao Yu 1 year, 6 months ago

On 2024/6/18 10:23, Jaegeuk Kim 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
> 
> 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: 4961acdd65c9 ("f2fs: fix to tag gcing flag on page during block migration")
> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

Reviewed-by: Chao Yu <chao@kernel.org>

Thanks,

Re: [f2fs-dev] [PATCH] f2fs: assign CURSEG_ALL_DATA_ATGC if blkaddr is valid

Posted by William McVicker 1 year, 5 months ago

On 06/19/2024, Chao Yu wrote:
> On 2024/6/18 10:23, Jaegeuk Kim 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
> > 
> > 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: 4961acdd65c9 ("f2fs: fix to tag gcing flag on page during block migration")
> > Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
> 
> Reviewed-by: Chao Yu <chao@kernel.org>

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:

Tested-by: Will McVicker <willmcvicker@google.com>

Thanks,
Will