| Message ID | 20240618022334.1576056-1-jaegeuk@kernel.org (mailing list archive) |
|---|---|
| State | Accepted |
| Commit | 8cb1f4080dd91c6e6b01dbea013a3f42341cb6a1 |
| Headers | show |
| Series | [f2fs-dev] f2fs: assign CURSEG_ALL_DATA_ATGC if blkaddr is valid | expand |
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,
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
Hello: This patch was applied to jaegeuk/f2fs.git (dev) by Jaegeuk Kim <jaegeuk@kernel.org>: 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 > > [...] 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!
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
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(+)