f2fs: fix to do sanity check with current segment number
authorChao Yu <yuchao0@huawei.com>
Thu, 6 Sep 2018 12:34:12 +0000 (20:34 +0800)
committerJaegeuk Kim <jaegeuk@kernel.org>
Wed, 12 Sep 2018 00:09:32 +0000 (17:09 -0700)
https://bugzilla.kernel.org/show_bug.cgi?id=200219

Reproduction way:
- mount image
- run poc code
- umount image

F2FS-fs (loop1): Bitmap was wrongly set, blk:15364
------------[ cut here ]------------
kernel BUG at /home/yuchao/git/devf2fs/segment.c:2061!
invalid opcode: 0000 [#1] PREEMPT SMP
CPU: 2 PID: 17686 Comm: umount Tainted: G        W  O      4.18.0-rc2+ #39
Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
EIP: update_sit_entry+0x459/0x4e0 [f2fs]
Code: e8 1c b5 fd ff 0f 0b 0f 0b 8b 45 e4 c7 44 24 08 9c 7a 6c f8 c7 44 24 04 bc 4a 6c f8 89 44 24 0c 8b 06 89 04 24 e8 f7 b4 fd ff <0f> 0b 8b 45 e4 0f b6 d2 89 54 24 10 c7 44 24 08 60 7a 6c f8 c7 44
EAX: 00000032 EBX: 000000f8 ECX: 00000002 EDX: 00000001
ESI: d7177000 EDI: f520fe68 EBP: d6477c6c ESP: d6477c34
DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068 EFLAGS: 00010282
CR0: 80050033 CR2: b7fbe000 CR3: 2a99b3c0 CR4: 000406f0
Call Trace:
 f2fs_allocate_data_block+0x124/0x580 [f2fs]
 do_write_page+0x78/0x150 [f2fs]
 f2fs_do_write_node_page+0x25/0xa0 [f2fs]
 __write_node_page+0x2bf/0x550 [f2fs]
 f2fs_sync_node_pages+0x60e/0x6d0 [f2fs]
 ? sync_inode_metadata+0x2f/0x40
 ? f2fs_write_checkpoint+0x28f/0x7d0 [f2fs]
 ? up_write+0x1e/0x80
 f2fs_write_checkpoint+0x2a9/0x7d0 [f2fs]
 ? mark_held_locks+0x5d/0x80
 ? _raw_spin_unlock_irq+0x27/0x50
 kill_f2fs_super+0x68/0x90 [f2fs]
 deactivate_locked_super+0x3d/0x70
 deactivate_super+0x40/0x60
 cleanup_mnt+0x39/0x70
 __cleanup_mnt+0x10/0x20
 task_work_run+0x81/0xa0
 exit_to_usermode_loop+0x59/0xa7
 do_fast_syscall_32+0x1f5/0x22c
 entry_SYSENTER_32+0x53/0x86
EIP: 0xb7f95c51
Code: c1 1e f7 ff ff 89 e5 8b 55 08 85 d2 8b 81 64 cd ff ff 74 02 89 02 5d c3 8b 0c 24 c3 8b 1c 24 c3 90 51 52 55 89 e5 0f 34 cd 80 <5d> 5a 59 c3 90 90 90 90 8d 76 00 58 b8 77 00 00 00 cd 80 90 8d 76
EAX: 00000000 EBX: 0871ab90 ECX: bfb2cd00 EDX: 00000000
ESI: 00000000 EDI: 0871ab90 EBP: 0871ab90 ESP: bfb2cd7c
DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 007b EFLAGS: 00000246
Modules linked in: f2fs(O) crc32_generic bnep rfcomm bluetooth ecdh_generic snd_intel8x0 snd_ac97_codec ac97_bus snd_pcm snd_seq_midi snd_seq_midi_event snd_rawmidi snd_seq pcbc joydev aesni_intel snd_seq_device aes_i586 snd_timer crypto_simd snd cryptd soundcore mac_hid serio_raw video i2c_piix4 parport_pc ppdev lp parport hid_generic psmouse usbhid hid e1000 [last unloaded: f2fs]
---[ end trace d423f83982cfcdc5 ]---

The reason is, different log headers using the same segment, once
one log's next block address is used by another log, it will cause
panic as above.

Main area: 24 segs, 24 secs 24 zones
  - COLD  data: 0, 0, 0
  - WARM  data: 1, 1, 1
  - HOT   data: 20, 20, 20
  - Dir   dnode: 22, 22, 22
  - File   dnode: 22, 22, 22
  - Indir nodes: 21, 21, 21

So this patch adds sanity check to detect such condition to avoid
this issue.

Signed-off-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
fs/f2fs/super.c

index b2acb7f..32402f0 100644 (file)
@@ -2325,7 +2325,7 @@ int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi)
        unsigned int segment_count_main;
        unsigned int cp_pack_start_sum, cp_payload;
        block_t user_block_count;
-       int i;
+       int i, j;
 
        total = le32_to_cpu(raw_super->segment_count);
        fsmeta = le32_to_cpu(raw_super->segment_count_ckpt);
@@ -2366,11 +2366,43 @@ int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi)
                if (le32_to_cpu(ckpt->cur_node_segno[i]) >= main_segs ||
                        le16_to_cpu(ckpt->cur_node_blkoff[i]) >= blocks_per_seg)
                        return 1;
+               for (j = i + 1; j < NR_CURSEG_NODE_TYPE; j++) {
+                       if (le32_to_cpu(ckpt->cur_node_segno[i]) ==
+                               le32_to_cpu(ckpt->cur_node_segno[j])) {
+                               f2fs_msg(sbi->sb, KERN_ERR,
+                                       "Node segment (%u, %u) has the same "
+                                       "segno: %u", i, j,
+                                       le32_to_cpu(ckpt->cur_node_segno[i]));
+                               return 1;
+                       }
+               }
        }
        for (i = 0; i < NR_CURSEG_DATA_TYPE; i++) {
                if (le32_to_cpu(ckpt->cur_data_segno[i]) >= main_segs ||
                        le16_to_cpu(ckpt->cur_data_blkoff[i]) >= blocks_per_seg)
                        return 1;
+               for (j = i + 1; j < NR_CURSEG_DATA_TYPE; j++) {
+                       if (le32_to_cpu(ckpt->cur_data_segno[i]) ==
+                               le32_to_cpu(ckpt->cur_data_segno[j])) {
+                               f2fs_msg(sbi->sb, KERN_ERR,
+                                       "Data segment (%u, %u) has the same "
+                                       "segno: %u", i, j,
+                                       le32_to_cpu(ckpt->cur_data_segno[i]));
+                               return 1;
+                       }
+               }
+       }
+       for (i = 0; i < NR_CURSEG_NODE_TYPE; i++) {
+               for (j = i; j < NR_CURSEG_DATA_TYPE; j++) {
+                       if (le32_to_cpu(ckpt->cur_node_segno[i]) ==
+                               le32_to_cpu(ckpt->cur_data_segno[j])) {
+                               f2fs_msg(sbi->sb, KERN_ERR,
+                                       "Data segment (%u) and Data segment (%u)"
+                                       " has the same segno: %u", i, j,
+                                       le32_to_cpu(ckpt->cur_node_segno[i]));
+                               return 1;
+                       }
+               }
        }
 
        sit_bitmap_size = le32_to_cpu(ckpt->sit_ver_bitmap_bytesize);