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().

Cc: [email protected]
Fixes: 4961acd ("f2fs: fix to tag gcing flag on page during block migration")
Reviewed-by: Chao Yu <[email protected]>
Tested-by: Will McVicker <[email protected]>
Signed-off-by: Jaegeuk Kim <[email protected]>

Author: Jaegeuk Kim

fs/f2fs/segment.c

@@ -3505,6 +3505,7 @@ 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