system/linux
system/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux synced 2024-11-05 18:23:50 +00:00
Code Issues Projects Releases Packages Wiki Activity

btrfs: dev-replace: fail mount if we don't have replace item with target device

Browse source 
If there is a device BTRFS_DEV_REPLACE_DEVID without the device replace
item, then it means the filesystem is inconsistent state. This is either
corruption or a crafted image.  Fail the mount as this needs a closer
look what is actually wrong.

As of now if BTRFS_DEV_REPLACE_DEVID is present without the replace
item, in __btrfs_free_extra_devids() we determine that there is an
extra device, and free those extra devices but continue to mount the
device.
However, we were wrong in keeping tack of the rw_devices so the syzbot
testcase failed:

  WARNING: CPU: 1 PID: 3612 at fs/btrfs/volumes.c:1166 close_fs_devices.part.0+0x607/0x800 fs/btrfs/volumes.c:1166
  Kernel panic - not syncing: panic_on_warn set ...
  CPU: 1 PID: 3612 Comm: syz-executor.2 Not tainted 5.9.0-rc4-syzkaller #0
  Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
  Call Trace:
   __dump_stack lib/dump_stack.c:77 [inline]
   dump_stack+0x198/0x1fd lib/dump_stack.c:118
   panic+0x347/0x7c0 kernel/panic.c:231
   __warn.cold+0x20/0x46 kernel/panic.c:600
   report_bug+0x1bd/0x210 lib/bug.c:198
   handle_bug+0x38/0x90 arch/x86/kernel/traps.c:234
   exc_invalid_op+0x14/0x40 arch/x86/kernel/traps.c:254
   asm_exc_invalid_op+0x12/0x20 arch/x86/include/asm/idtentry.h:536
  RIP: 0010:close_fs_devices.part.0+0x607/0x800 fs/btrfs/volumes.c:1166
  RSP: 0018:ffffc900091777e0 EFLAGS: 00010246
  RAX: 0000000000040000 RBX: ffffffffffffffff RCX: ffffc9000c8b7000
  RDX: 0000000000040000 RSI: ffffffff83097f47 RDI: 0000000000000007
  RBP: dffffc0000000000 R08: 0000000000000001 R09: ffff8880988a187f
  R10: 0000000000000000 R11: 0000000000000001 R12: ffff88809593a130
  R13: ffff88809593a1ec R14: ffff8880988a1908 R15: ffff88809593a050
   close_fs_devices fs/btrfs/volumes.c:1193 [inline]
   btrfs_close_devices+0x95/0x1f0 fs/btrfs/volumes.c:1179
   open_ctree+0x4984/0x4a2d fs/btrfs/disk-io.c:3434
   btrfs_fill_super fs/btrfs/super.c:1316 [inline]
   btrfs_mount_root.cold+0x14/0x165 fs/btrfs/super.c:1672

The fix here is, when we determine that there isn't a replace item
then fail the mount if there is a replace target device (devid 0).

CC: stable@vger.kernel.org # 4.19+
Reported-by: syzbot+4cfe71a4da060be47502@syzkaller.appspotmail.com
Signed-off-by: Anand Jain <anand.jain@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
This commit is contained in:
Anand Jain 2020-10-30 06:53:56 +08:00 committed by David Sterba
parent a4852cf268
commit cf89af146b
2 changed files with 31 additions and 21 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

26
fs/btrfs/dev-replace.c
View file

@ -91,6 +91,17 @@ int btrfs_init_dev_replace(struct btrfs_fs_info *fs_info)
ret = btrfs_search_slot(NULL, dev_root, &key, path, 0, 0);
if (ret) {
no_valid_dev_replace_entry_found:
/*
* We don't have a replace item or it's corrupted. If there is
* a replace target, fail the mount.
*/
if (btrfs_find_device(fs_info->fs_devices,
BTRFS_DEV_REPLACE_DEVID, NULL, NULL, false)) {
btrfs_err(fs_info,
"found replace target device without a valid replace item");
ret = -EUCLEAN;
goto out;
}
ret = 0;
dev_replace->replace_state =
BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED;
@ -143,8 +154,19 @@ int btrfs_init_dev_replace(struct btrfs_fs_info *fs_info)
case BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED:
case BTRFS_IOCTL_DEV_REPLACE_STATE_FINISHED:
case BTRFS_IOCTL_DEV_REPLACE_STATE_CANCELED:
dev_replace->srcdev = NULL;
dev_replace->tgtdev = NULL;
/*
* We don't have an active replace item but if there is a
* replace target, fail the mount.
*/
if (btrfs_find_device(fs_info->fs_devices,
BTRFS_DEV_REPLACE_DEVID, NULL, NULL, false)) {
btrfs_err(fs_info,
"replace devid present without an active replace item");
ret = -EUCLEAN;
} else {
dev_replace->srcdev = NULL;
dev_replace->tgtdev = NULL;
}
break;
case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED:
case BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED:

26
fs/btrfs/volumes.c
View file

@ -1056,22 +1056,13 @@ static void __btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices,
continue;
}
if (device->devid == BTRFS_DEV_REPLACE_DEVID) {
/*
* In the first step, keep the device which has
* the correct fsid and the devid that is used
* for the dev_replace procedure.
* In the second step, the dev_replace state is
* read from the device tree and it is known
* whether the procedure is really active or
* not, which means whether this device is
* used or whether it should be removed.
*/
if (step == 0 || test_bit(BTRFS_DEV_STATE_REPLACE_TGT,
&device->dev_state)) {
continue;
}
}
/*
* We have already validated the presence of BTRFS_DEV_REPLACE_DEVID,
* in btrfs_init_dev_replace() so just continue.
*/
if (device->devid == BTRFS_DEV_REPLACE_DEVID)
continue;
if (device->bdev) {
blkdev_put(device->bdev, device->mode);
device->bdev = NULL;
@ -1080,9 +1071,6 @@ static void __btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices,
if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) {
list_del_init(&device->dev_alloc_list);
clear_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state);
if (!test_bit(BTRFS_DEV_STATE_REPLACE_TGT,
&device->dev_state))
fs_devices->rw_devices--;
}
list_del_init(&device->dev_list);
fs_devices->num_devices--;