f2fs: assign CURSEG_ALL_DATA_ATGC if blkaddr is valid

[ Upstream commit 8cb1f4080dd91c6e6b01dbea013a3f42341cb6a1 ]

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")
Reviewed-by: Chao Yu <chao@kernel.org>
Tested-by: Will McVicker <willmcvicker@google.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>

diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 92331f8dbe4e36f379f1dbf98d29b91d6bd66bd0..601825785226d2181f49d44ee45c7dc640dbdb5d 100644 (file)
--- 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