[RFC] btrfs: Allow read-only mount with corrupted extent tree

[RFC] btrfs: Allow read-only mount with corrupted extent tree

[Dāvis Mosāns]

Currently if there's any corruption at all in extent tree
(eg. even single bit) then mounting will fail with:
"failed to read block groups: -5" (-EIO)
It happens because we immediately abort on first error when
searching in extent tree for block groups.

Now with this patch if `ignorebadroots` option is specified
then we handle such case and continue by removing already
created block groups and creating dummy block groups.

Signed-off-by: Dāvis Mosāns <davispuh@gmail.com>
---
 fs/btrfs/block-group.c | 14 ++++++++++++++
 fs/btrfs/disk-io.c     |  4 ++--
 fs/btrfs/disk-io.h     |  2 ++
 3 files changed, 18 insertions(+), 2 deletions(-)

diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 48ebc106a606..827a977614b3 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -2048,6 +2048,20 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info)
 	ret = check_chunk_block_group_mappings(info);
 error:
 	btrfs_free_path(path);
+
+	if (ret == -EIO && btrfs_test_opt(info, IGNOREBADROOTS)) {
+		btrfs_put_block_group_cache(info);
+		btrfs_stop_all_workers(info);
+		btrfs_free_block_groups(info);
+		ret = btrfs_init_workqueues(info, NULL);
+		if (ret)
+			return ret;
+		ret = btrfs_init_space_info(info);
+		if (ret)
+			return ret;
+		return fill_dummy_bgs(info);
+	}
+
 	return ret;
 }
 
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 07a2b4f69b10..dc744f76d075 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1955,7 +1955,7 @@ static int read_backup_root(struct btrfs_fs_info *fs_info, u8 priority)
 }
 
 /* helper to cleanup workers */
-static void btrfs_stop_all_workers(struct btrfs_fs_info *fs_info)
+void btrfs_stop_all_workers(struct btrfs_fs_info *fs_info)
 {
 	btrfs_destroy_workqueue(fs_info->fixup_workers);
 	btrfs_destroy_workqueue(fs_info->delalloc_workers);
@@ -2122,7 +2122,7 @@ static void btrfs_init_qgroup(struct btrfs_fs_info *fs_info)
 	mutex_init(&fs_info->qgroup_rescan_lock);
 }
 
-static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info,
+int btrfs_init_workqueues(struct btrfs_fs_info *fs_info,
 		struct btrfs_fs_devices *fs_devices)
 {
 	u32 max_active = fs_info->thread_pool_size;
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index e45057c0c016..f9bfcba86a04 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -137,6 +137,8 @@ int btrfs_find_free_objectid(struct btrfs_root *root, u64 *objectid);
 int btrfs_find_highest_objectid(struct btrfs_root *root, u64 *objectid);
 int __init btrfs_end_io_wq_init(void);
 void __cold btrfs_end_io_wq_exit(void);
+void btrfs_stop_all_workers(struct btrfs_fs_info *fs_info);
+int btrfs_init_workqueues(struct btrfs_fs_info *fs_info, struct btrfs_fs_devices *fs_devices);
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 void btrfs_set_buffer_lockdep_class(u64 objectid,
-- 
2.30.2

Re: [RFC] btrfs: Allow read-only mount with corrupted extent tree

[Dāvis Mosāns]

trešd., 2021. g. 17. marts, plkst. 03:18 — lietotājs Dāvis Mosāns
(<davispuh@gmail.com>) rakstīja:
>
> Currently if there's any corruption at all in extent tree
> (eg. even single bit) then mounting will fail with:
> "failed to read block groups: -5" (-EIO)
> It happens because we immediately abort on first error when
> searching in extent tree for block groups.
>
> Now with this patch if `ignorebadroots` option is specified
> then we handle such case and continue by removing already
> created block groups and creating dummy block groups.
>
> Signed-off-by: Dāvis Mosāns <davispuh@gmail.com>
> ---
>  fs/btrfs/block-group.c | 14 ++++++++++++++
>  fs/btrfs/disk-io.c     |  4 ++--
>  fs/btrfs/disk-io.h     |  2 ++
>  3 files changed, 18 insertions(+), 2 deletions(-)
>
> diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
> index 48ebc106a606..827a977614b3 100644
> --- a/fs/btrfs/block-group.c
> +++ b/fs/btrfs/block-group.c
> @@ -2048,6 +2048,20 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info)
>         ret = check_chunk_block_group_mappings(info);
>  error:
>         btrfs_free_path(path);
> +
> +       if (ret == -EIO && btrfs_test_opt(info, IGNOREBADROOTS)) {
> +               btrfs_put_block_group_cache(info);
> +               btrfs_stop_all_workers(info);
> +               btrfs_free_block_groups(info);
> +               ret = btrfs_init_workqueues(info, NULL);
> +               if (ret)
> +                       return ret;
> +               ret = btrfs_init_space_info(info);
> +               if (ret)
> +                       return ret;
> +               return fill_dummy_bgs(info);

This isn't that nice, but I don't really know how to properly clean up
everything related to already created block groups so this was easiest
way. It seems to work fine.
But looks like need to do something about replay log aswell because if
it's not disabled then it fails with:

[ 1397.246869] BTRFS info (device sde): start tree-log replay
[ 1398.218685] BTRFS warning (device sde): sde checksum verify failed
on 21057127661568 wanted 0xd1506ed9 found 0x22ab750a level 0
[ 1398.218803] BTRFS warning (device sde): sde checksum verify failed
on 21057127661568 wanted 0xd1506ed9 found 0x7dd54bb9 level 0
[ 1398.218813] BTRFS: error (device sde) in __btrfs_free_extent:3054:
errno=-5 IO failure
[ 1398.218828] BTRFS: error (device sde) in
btrfs_run_delayed_refs:2124: errno=-5 IO failure
[ 1398.219002] BTRFS: error (device sde) in btrfs_replay_log:2254:
errno=-5 IO failure (Failed to recover log tree)
[ 1398.229048] BTRFS error (device sde): open_ctree failed

Ideally it should replay everything except extent refs.


I also noticed that after unmount there is:

[11000.562504] BTRFS warning (device sde): page private not zero on
page 21057098481664
[11000.562510] BTRFS warning (device sde): page private not zero on
page 21057098485760

not sure what it means.


Best regards,
Dāvis

Re: [RFC] btrfs: Allow read-only mount with corrupted extent tree

[Qu Wenruo]

On 2021/3/17 上午9:29, Dāvis Mosāns wrote:
> trešd., 2021. g. 17. marts, plkst. 03:18 — lietotājs Dāvis Mosāns
> (<davispuh@gmail.com>) rakstīja:
>>
>> Currently if there's any corruption at all in extent tree
>> (eg. even single bit) then mounting will fail with:
>> "failed to read block groups: -5" (-EIO)
>> It happens because we immediately abort on first error when
>> searching in extent tree for block groups.
>>
>> Now with this patch if `ignorebadroots` option is specified
>> then we handle such case and continue by removing already
>> created block groups and creating dummy block groups.
>>
>> Signed-off-by: Dāvis Mosāns <davispuh@gmail.com>
>> ---
>>   fs/btrfs/block-group.c | 14 ++++++++++++++
>>   fs/btrfs/disk-io.c     |  4 ++--
>>   fs/btrfs/disk-io.h     |  2 ++
>>   3 files changed, 18 insertions(+), 2 deletions(-)
>>
>> diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
>> index 48ebc106a606..827a977614b3 100644
>> --- a/fs/btrfs/block-group.c
>> +++ b/fs/btrfs/block-group.c
>> @@ -2048,6 +2048,20 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info)
>>          ret = check_chunk_block_group_mappings(info);
>>   error:
>>          btrfs_free_path(path);
>> +
>> +       if (ret == -EIO && btrfs_test_opt(info, IGNOREBADROOTS)) {
>> +               btrfs_put_block_group_cache(info);
>> +               btrfs_stop_all_workers(info);
>> +               btrfs_free_block_groups(info);
>> +               ret = btrfs_init_workqueues(info, NULL);
>> +               if (ret)
>> +                       return ret;
>> +               ret = btrfs_init_space_info(info);
>> +               if (ret)
>> +                       return ret;
>> +               return fill_dummy_bgs(info);

When we hit bad things in extent tree, we should ensure we're mounting
the fs RO, or we can't continue.

And we should also refuse to mount back to RW if we hit such case, so
that we don't need anything complex, just ignore the whole extent tree
and create the dummy block groups.

>
> This isn't that nice, but I don't really know how to properly clean up
> everything related to already created block groups so this was easiest
> way. It seems to work fine.
> But looks like need to do something about replay log aswell because if
> it's not disabled then it fails with:
>
> [ 1397.246869] BTRFS info (device sde): start tree-log replay
> [ 1398.218685] BTRFS warning (device sde): sde checksum verify failed
> on 21057127661568 wanted 0xd1506ed9 found 0x22ab750a level 0
> [ 1398.218803] BTRFS warning (device sde): sde checksum verify failed
> on 21057127661568 wanted 0xd1506ed9 found 0x7dd54bb9 level 0
> [ 1398.218813] BTRFS: error (device sde) in __btrfs_free_extent:3054:
> errno=-5 IO failure
> [ 1398.218828] BTRFS: error (device sde) in
> btrfs_run_delayed_refs:2124: errno=-5 IO failure
> [ 1398.219002] BTRFS: error (device sde) in btrfs_replay_log:2254:
> errno=-5 IO failure (Failed to recover log tree)
> [ 1398.229048] BTRFS error (device sde): open_ctree failed

This is because we shouldn't allow to do anything write to the fs if we
have anything wrong in extent tree.

Thanks,
Qu
>
> Ideally it should replay everything except extent refs. >
>
> I also noticed that after unmount there is:
>
> [11000.562504] BTRFS warning (device sde): page private not zero on
> page 21057098481664
> [11000.562510] BTRFS warning (device sde): page private not zero on
> page 21057098485760
>
> not sure what it means.
>
>
> Best regards,
> Dāvis
>

Re: [RFC] btrfs: Allow read-only mount with corrupted extent tree

[Dāvis Mosāns]

trešd., 2021. g. 17. marts, plkst. 12:28 — lietotājs Qu Wenruo
(<quwenruo.btrfs@gmx.com>) rakstīja:
>
>
>
> On 2021/3/17 上午9:29, Dāvis Mosāns wrote:
> > trešd., 2021. g. 17. marts, plkst. 03:18 — lietotājs Dāvis Mosāns
> > (<davispuh@gmail.com>) rakstīja:
> >>
> >> Currently if there's any corruption at all in extent tree
> >> (eg. even single bit) then mounting will fail with:
> >> "failed to read block groups: -5" (-EIO)
> >> It happens because we immediately abort on first error when
> >> searching in extent tree for block groups.
> >>
> >> Now with this patch if `ignorebadroots` option is specified
> >> then we handle such case and continue by removing already
> >> created block groups and creating dummy block groups.
> >>
> >> Signed-off-by: Dāvis Mosāns <davispuh@gmail.com>
> >> ---
> >>   fs/btrfs/block-group.c | 14 ++++++++++++++
> >>   fs/btrfs/disk-io.c     |  4 ++--
> >>   fs/btrfs/disk-io.h     |  2 ++
> >>   3 files changed, 18 insertions(+), 2 deletions(-)
> >>
> >> diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
> >> index 48ebc106a606..827a977614b3 100644
> >> --- a/fs/btrfs/block-group.c
> >> +++ b/fs/btrfs/block-group.c
> >> @@ -2048,6 +2048,20 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info)
> >>          ret = check_chunk_block_group_mappings(info);
> >>   error:
> >>          btrfs_free_path(path);
> >> +
> >> +       if (ret == -EIO && btrfs_test_opt(info, IGNOREBADROOTS)) {
> >> +               btrfs_put_block_group_cache(info);
> >> +               btrfs_stop_all_workers(info);
> >> +               btrfs_free_block_groups(info);
> >> +               ret = btrfs_init_workqueues(info, NULL);
> >> +               if (ret)
> >> +                       return ret;
> >> +               ret = btrfs_init_space_info(info);
> >> +               if (ret)
> >> +                       return ret;
> >> +               return fill_dummy_bgs(info);
>
> When we hit bad things in extent tree, we should ensure we're mounting
> the fs RO, or we can't continue.
>
> And we should also refuse to mount back to RW if we hit such case, so
> that we don't need anything complex, just ignore the whole extent tree
> and create the dummy block groups.
>

That's what we're doing here, `ignorebadroots` implies RO mount and
without specifying it doesn't mount at all.

> >
> > This isn't that nice, but I don't really know how to properly clean up
> > everything related to already created block groups so this was easiest
> > way. It seems to work fine.
> > But looks like need to do something about replay log aswell because if
> > it's not disabled then it fails with:
> >
> > [ 1397.246869] BTRFS info (device sde): start tree-log replay
> > [ 1398.218685] BTRFS warning (device sde): sde checksum verify failed
> > on 21057127661568 wanted 0xd1506ed9 found 0x22ab750a level 0
> > [ 1398.218803] BTRFS warning (device sde): sde checksum verify failed
> > on 21057127661568 wanted 0xd1506ed9 found 0x7dd54bb9 level 0
> > [ 1398.218813] BTRFS: error (device sde) in __btrfs_free_extent:3054:
> > errno=-5 IO failure
> > [ 1398.218828] BTRFS: error (device sde) in
> > btrfs_run_delayed_refs:2124: errno=-5 IO failure
> > [ 1398.219002] BTRFS: error (device sde) in btrfs_replay_log:2254:
> > errno=-5 IO failure (Failed to recover log tree)
> > [ 1398.229048] BTRFS error (device sde): open_ctree failed
>
> This is because we shouldn't allow to do anything write to the fs if we
> have anything wrong in extent tree.
>

This is happening when mounting read-only. My assumption is that it
only tries to replay in memory without writing anything to disk.

Re: [RFC] btrfs: Allow read-only mount with corrupted extent tree

[Qu Wenruo]

On 2021/3/18 上午5:03, Dāvis Mosāns wrote:
> trešd., 2021. g. 17. marts, plkst. 12:28 — lietotājs Qu Wenruo
> (<quwenruo.btrfs@gmx.com>) rakstīja:
>>
>>
>>
>> On 2021/3/17 上午9:29, Dāvis Mosāns wrote:
>>> trešd., 2021. g. 17. marts, plkst. 03:18 — lietotājs Dāvis Mosāns
>>> (<davispuh@gmail.com>) rakstīja:
>>>>
>>>> Currently if there's any corruption at all in extent tree
>>>> (eg. even single bit) then mounting will fail with:
>>>> "failed to read block groups: -5" (-EIO)
>>>> It happens because we immediately abort on first error when
>>>> searching in extent tree for block groups.
>>>>
>>>> Now with this patch if `ignorebadroots` option is specified
>>>> then we handle such case and continue by removing already
>>>> created block groups and creating dummy block groups.
>>>>
>>>> Signed-off-by: Dāvis Mosāns <davispuh@gmail.com>
>>>> ---
>>>>    fs/btrfs/block-group.c | 14 ++++++++++++++
>>>>    fs/btrfs/disk-io.c     |  4 ++--
>>>>    fs/btrfs/disk-io.h     |  2 ++
>>>>    3 files changed, 18 insertions(+), 2 deletions(-)
>>>>
>>>> diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
>>>> index 48ebc106a606..827a977614b3 100644
>>>> --- a/fs/btrfs/block-group.c
>>>> +++ b/fs/btrfs/block-group.c
>>>> @@ -2048,6 +2048,20 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info)
>>>>           ret = check_chunk_block_group_mappings(info);
>>>>    error:
>>>>           btrfs_free_path(path);
>>>> +
>>>> +       if (ret == -EIO && btrfs_test_opt(info, IGNOREBADROOTS)) {
>>>> +               btrfs_put_block_group_cache(info);
>>>> +               btrfs_stop_all_workers(info);
>>>> +               btrfs_free_block_groups(info);
>>>> +               ret = btrfs_init_workqueues(info, NULL);
>>>> +               if (ret)
>>>> +                       return ret;
>>>> +               ret = btrfs_init_space_info(info);
>>>> +               if (ret)
>>>> +                       return ret;
>>>> +               return fill_dummy_bgs(info);
>>
>> When we hit bad things in extent tree, we should ensure we're mounting
>> the fs RO, or we can't continue.
>>
>> And we should also refuse to mount back to RW if we hit such case, so
>> that we don't need anything complex, just ignore the whole extent tree
>> and create the dummy block groups.
>>
>
> That's what we're doing here, `ignorebadroots` implies RO mount and
> without specifying it doesn't mount at all.
>
>>>
>>> This isn't that nice, but I don't really know how to properly clean up
>>> everything related to already created block groups so this was easiest
>>> way. It seems to work fine.
>>> But looks like need to do something about replay log aswell because if
>>> it's not disabled then it fails with:
>>>
>>> [ 1397.246869] BTRFS info (device sde): start tree-log replay
>>> [ 1398.218685] BTRFS warning (device sde): sde checksum verify failed
>>> on 21057127661568 wanted 0xd1506ed9 found 0x22ab750a level 0
>>> [ 1398.218803] BTRFS warning (device sde): sde checksum verify failed
>>> on 21057127661568 wanted 0xd1506ed9 found 0x7dd54bb9 level 0
>>> [ 1398.218813] BTRFS: error (device sde) in __btrfs_free_extent:3054:
>>> errno=-5 IO failure
>>> [ 1398.218828] BTRFS: error (device sde) in
>>> btrfs_run_delayed_refs:2124: errno=-5 IO failure
>>> [ 1398.219002] BTRFS: error (device sde) in btrfs_replay_log:2254:
>>> errno=-5 IO failure (Failed to recover log tree)
>>> [ 1398.229048] BTRFS error (device sde): open_ctree failed
>>
>> This is because we shouldn't allow to do anything write to the fs if we
>> have anything wrong in extent tree.
>>
>
> This is happening when mounting read-only. My assumption is that it
> only tries to replay in memory without writing anything to disk.
>

We lacks the check on log tree.

Normally for such forced RO mount, log replay is not allowed.

We should output a warning to prompt user to use nologreplay, and reject
the mount.

Thanks,
Qu

Re: [RFC] btrfs: Allow read-only mount with corrupted extent tree

[Dāvis Mosāns]

ceturtd., 2021. g. 18. marts, plkst. 01:49 — lietotājs Qu Wenruo
(<quwenruo.btrfs@gmx.com>) rakstīja:
>
>
>
> On 2021/3/18 上午5:03, Dāvis Mosāns wrote:
> > trešd., 2021. g. 17. marts, plkst. 12:28 — lietotājs Qu Wenruo
> > (<quwenruo.btrfs@gmx.com>) rakstīja:
> >>
> >>
> >>
> >> On 2021/3/17 上午9:29, Dāvis Mosāns wrote:
> >>> trešd., 2021. g. 17. marts, plkst. 03:18 — lietotājs Dāvis Mosāns
> >>> (<davispuh@gmail.com>) rakstīja:
> >>>>
> >>>> Currently if there's any corruption at all in extent tree
> >>>> (eg. even single bit) then mounting will fail with:
> >>>> "failed to read block groups: -5" (-EIO)
> >>>> It happens because we immediately abort on first error when
> >>>> searching in extent tree for block groups.
> >>>>
> >>>> Now with this patch if `ignorebadroots` option is specified
> >>>> then we handle such case and continue by removing already
> >>>> created block groups and creating dummy block groups.
> >>>>
> >>>> Signed-off-by: Dāvis Mosāns <davispuh@gmail.com>
> >>>> ---
> >>>>    fs/btrfs/block-group.c | 14 ++++++++++++++
> >>>>    fs/btrfs/disk-io.c     |  4 ++--
> >>>>    fs/btrfs/disk-io.h     |  2 ++
> >>>>    3 files changed, 18 insertions(+), 2 deletions(-)
> >>>>
> >>>> diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
> >>>> index 48ebc106a606..827a977614b3 100644
> >>>> --- a/fs/btrfs/block-group.c
> >>>> +++ b/fs/btrfs/block-group.c
> >>>> @@ -2048,6 +2048,20 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info)
> >>>>           ret = check_chunk_block_group_mappings(info);
> >>>>    error:
> >>>>           btrfs_free_path(path);
> >>>> +
> >>>> +       if (ret == -EIO && btrfs_test_opt(info, IGNOREBADROOTS)) {
> >>>> +               btrfs_put_block_group_cache(info);
> >>>> +               btrfs_stop_all_workers(info);
> >>>> +               btrfs_free_block_groups(info);
> >>>> +               ret = btrfs_init_workqueues(info, NULL);
> >>>> +               if (ret)
> >>>> +                       return ret;
> >>>> +               ret = btrfs_init_space_info(info);
> >>>> +               if (ret)
> >>>> +                       return ret;
> >>>> +               return fill_dummy_bgs(info);
> >>
> >> When we hit bad things in extent tree, we should ensure we're mounting
> >> the fs RO, or we can't continue.
> >>
> >> And we should also refuse to mount back to RW if we hit such case, so
> >> that we don't need anything complex, just ignore the whole extent tree
> >> and create the dummy block groups.
> >>
> >
> > That's what we're doing here, `ignorebadroots` implies RO mount and
> > without specifying it doesn't mount at all.
> >
> >>>
> >>> This isn't that nice, but I don't really know how to properly clean up
> >>> everything related to already created block groups so this was easiest
> >>> way. It seems to work fine.
> >>> But looks like need to do something about replay log aswell because if
> >>> it's not disabled then it fails with:
> >>>
> >>> [ 1397.246869] BTRFS info (device sde): start tree-log replay
> >>> [ 1398.218685] BTRFS warning (device sde): sde checksum verify failed
> >>> on 21057127661568 wanted 0xd1506ed9 found 0x22ab750a level 0
> >>> [ 1398.218803] BTRFS warning (device sde): sde checksum verify failed
> >>> on 21057127661568 wanted 0xd1506ed9 found 0x7dd54bb9 level 0
> >>> [ 1398.218813] BTRFS: error (device sde) in __btrfs_free_extent:3054:
> >>> errno=-5 IO failure
> >>> [ 1398.218828] BTRFS: error (device sde) in
> >>> btrfs_run_delayed_refs:2124: errno=-5 IO failure
> >>> [ 1398.219002] BTRFS: error (device sde) in btrfs_replay_log:2254:
> >>> errno=-5 IO failure (Failed to recover log tree)
> >>> [ 1398.229048] BTRFS error (device sde): open_ctree failed
> >>
> >> This is because we shouldn't allow to do anything write to the fs if we
> >> have anything wrong in extent tree.
> >>
> >
> > This is happening when mounting read-only. My assumption is that it
> > only tries to replay in memory without writing anything to disk.
> >
>
> We lacks the check on log tree.
>
> Normally for such forced RO mount, log replay is not allowed.
>
> We should output a warning to prompt user to use nologreplay, and reject
> the mount.
>

I'm not familiar with log replay but couldn't there be something
useful (ignoring ref counts) that would still be worth replaying in
memory?

Re: [RFC] btrfs: Allow read-only mount with corrupted extent tree

[Qu Wenruo]

On 2021/3/19 下午11:34, Dāvis Mosāns wrote:
> ceturtd., 2021. g. 18. marts, plkst. 01:49 — lietotājs Qu Wenruo
> (<quwenruo.btrfs@gmx.com>) rakstīja:
>>
>>
>>
>> On 2021/3/18 上午5:03, Dāvis Mosāns wrote:
>>> trešd., 2021. g. 17. marts, plkst. 12:28 — lietotājs Qu Wenruo
>>> (<quwenruo.btrfs@gmx.com>) rakstīja:
>>>>
>>>>
>>>>
>>>> On 2021/3/17 上午9:29, Dāvis Mosāns wrote:
>>>>> trešd., 2021. g. 17. marts, plkst. 03:18 — lietotājs Dāvis Mosāns
>>>>> (<davispuh@gmail.com>) rakstīja:
>>>>>>
>>>>>> Currently if there's any corruption at all in extent tree
>>>>>> (eg. even single bit) then mounting will fail with:
>>>>>> "failed to read block groups: -5" (-EIO)
>>>>>> It happens because we immediately abort on first error when
>>>>>> searching in extent tree for block groups.
>>>>>>
>>>>>> Now with this patch if `ignorebadroots` option is specified
>>>>>> then we handle such case and continue by removing already
>>>>>> created block groups and creating dummy block groups.
>>>>>>
>>>>>> Signed-off-by: Dāvis Mosāns <davispuh@gmail.com>
>>>>>> ---
>>>>>>     fs/btrfs/block-group.c | 14 ++++++++++++++
>>>>>>     fs/btrfs/disk-io.c     |  4 ++--
>>>>>>     fs/btrfs/disk-io.h     |  2 ++
>>>>>>     3 files changed, 18 insertions(+), 2 deletions(-)
>>>>>>
>>>>>> diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
>>>>>> index 48ebc106a606..827a977614b3 100644
>>>>>> --- a/fs/btrfs/block-group.c
>>>>>> +++ b/fs/btrfs/block-group.c
>>>>>> @@ -2048,6 +2048,20 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info)
>>>>>>            ret = check_chunk_block_group_mappings(info);
>>>>>>     error:
>>>>>>            btrfs_free_path(path);
>>>>>> +
>>>>>> +       if (ret == -EIO && btrfs_test_opt(info, IGNOREBADROOTS)) {
>>>>>> +               btrfs_put_block_group_cache(info);
>>>>>> +               btrfs_stop_all_workers(info);
>>>>>> +               btrfs_free_block_groups(info);
>>>>>> +               ret = btrfs_init_workqueues(info, NULL);
>>>>>> +               if (ret)
>>>>>> +                       return ret;
>>>>>> +               ret = btrfs_init_space_info(info);
>>>>>> +               if (ret)
>>>>>> +                       return ret;
>>>>>> +               return fill_dummy_bgs(info);
>>>>
>>>> When we hit bad things in extent tree, we should ensure we're mounting
>>>> the fs RO, or we can't continue.
>>>>
>>>> And we should also refuse to mount back to RW if we hit such case, so
>>>> that we don't need anything complex, just ignore the whole extent tree
>>>> and create the dummy block groups.
>>>>
>>>
>>> That's what we're doing here, `ignorebadroots` implies RO mount and
>>> without specifying it doesn't mount at all.
>>>
>>>>>
>>>>> This isn't that nice, but I don't really know how to properly clean up
>>>>> everything related to already created block groups so this was easiest
>>>>> way. It seems to work fine.
>>>>> But looks like need to do something about replay log aswell because if
>>>>> it's not disabled then it fails with:
>>>>>
>>>>> [ 1397.246869] BTRFS info (device sde): start tree-log replay
>>>>> [ 1398.218685] BTRFS warning (device sde): sde checksum verify failed
>>>>> on 21057127661568 wanted 0xd1506ed9 found 0x22ab750a level 0
>>>>> [ 1398.218803] BTRFS warning (device sde): sde checksum verify failed
>>>>> on 21057127661568 wanted 0xd1506ed9 found 0x7dd54bb9 level 0
>>>>> [ 1398.218813] BTRFS: error (device sde) in __btrfs_free_extent:3054:
>>>>> errno=-5 IO failure
>>>>> [ 1398.218828] BTRFS: error (device sde) in
>>>>> btrfs_run_delayed_refs:2124: errno=-5 IO failure
>>>>> [ 1398.219002] BTRFS: error (device sde) in btrfs_replay_log:2254:
>>>>> errno=-5 IO failure (Failed to recover log tree)
>>>>> [ 1398.229048] BTRFS error (device sde): open_ctree failed
>>>>
>>>> This is because we shouldn't allow to do anything write to the fs if we
>>>> have anything wrong in extent tree.
>>>>
>>>
>>> This is happening when mounting read-only. My assumption is that it
>>> only tries to replay in memory without writing anything to disk.
>>>
>>
>> We lacks the check on log tree.
>>
>> Normally for such forced RO mount, log replay is not allowed.
>>
>> We should output a warning to prompt user to use nologreplay, and reject
>> the mount.
>>
>
> I'm not familiar with log replay but couldn't there be something
> useful (ignoring ref counts) that would still be worth replaying in
> memory?
>
Log replay means metadata write.

Any write needs a valid extent tree to find out free space for new
metadata/data.

So no, we can't do anything but completely ignoring the log.

Thanks,
Qu

[PATCH] btrfs: Allow read-only mount with corrupted extent tree

[Dāvis Mosāns]

Currently if there's any corruption at all in extent tree
(eg. even single bit) then mounting will fail with:
"failed to read block groups: -5" (-EIO)
It happens because we immediately abort on first error when
searching in extent tree for block groups.

Now with this patch if `ignorebadroots` option is specified
then we handle such case and continue by removing already
created block groups and creating dummy block groups.

Signed-off-by: Dāvis Mosāns <davispuh@gmail.com>
---
 fs/btrfs/block-group.c | 20 ++++++++++++++++++++
 fs/btrfs/disk-io.c     |  4 ++--
 fs/btrfs/disk-io.h     |  2 ++
 3 files changed, 24 insertions(+), 2 deletions(-)

diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 48ebc106a606..f485cf14c2f8 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -2048,6 +2048,26 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info)
 	ret = check_chunk_block_group_mappings(info);
 error:
 	btrfs_free_path(path);
+
+	if (ret == -EIO && btrfs_test_opt(info, IGNOREBADROOTS)) {
+
+		if (btrfs_super_log_root(info->super_copy) != 0) {
+			btrfs_warn(info, "Ignoring tree-log replay due to extent tree corruption!");
+			btrfs_set_super_log_root(info->super_copy, 0);
+		}
+
+		btrfs_put_block_group_cache(info);
+		btrfs_stop_all_workers(info);
+		btrfs_free_block_groups(info);
+		ret = btrfs_init_workqueues(info, NULL);
+		if (ret)
+			return ret;
+		ret = btrfs_init_space_info(info);
+		if (ret)
+			return ret;
+		return fill_dummy_bgs(info);
+	}
+
 	return ret;
 }
 
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 07a2b4f69b10..dc744f76d075 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1955,7 +1955,7 @@ static int read_backup_root(struct btrfs_fs_info *fs_info, u8 priority)
 }
 
 /* helper to cleanup workers */
-static void btrfs_stop_all_workers(struct btrfs_fs_info *fs_info)
+void btrfs_stop_all_workers(struct btrfs_fs_info *fs_info)
 {
 	btrfs_destroy_workqueue(fs_info->fixup_workers);
 	btrfs_destroy_workqueue(fs_info->delalloc_workers);
@@ -2122,7 +2122,7 @@ static void btrfs_init_qgroup(struct btrfs_fs_info *fs_info)
 	mutex_init(&fs_info->qgroup_rescan_lock);
 }
 
-static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info,
+int btrfs_init_workqueues(struct btrfs_fs_info *fs_info,
 		struct btrfs_fs_devices *fs_devices)
 {
 	u32 max_active = fs_info->thread_pool_size;
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index e45057c0c016..f9bfcba86a04 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -137,6 +137,8 @@ int btrfs_find_free_objectid(struct btrfs_root *root, u64 *objectid);
 int btrfs_find_highest_objectid(struct btrfs_root *root, u64 *objectid);
 int __init btrfs_end_io_wq_init(void);
 void __cold btrfs_end_io_wq_exit(void);
+void btrfs_stop_all_workers(struct btrfs_fs_info *fs_info);
+int btrfs_init_workqueues(struct btrfs_fs_info *fs_info, struct btrfs_fs_devices *fs_devices);
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 void btrfs_set_buffer_lockdep_class(u64 objectid,
-- 
2.30.2

Re: [PATCH] btrfs: Allow read-only mount with corrupted extent tree

[Dāvis Mosāns]

svētd., 2021. g. 21. marts, plkst. 23:46 — lietotājs Dāvis Mosāns
(<davispuh@gmail.com>) rakstīja:
>
> Currently if there's any corruption at all in extent tree
> (eg. even single bit) then mounting will fail with:
> "failed to read block groups: -5" (-EIO)
> It happens because we immediately abort on first error when
> searching in extent tree for block groups.
>
> Now with this patch if `ignorebadroots` option is specified
> then we handle such case and continue by removing already
> created block groups and creating dummy block groups.
>
> Signed-off-by: Dāvis Mosāns <davispuh@gmail.com>
> ---
>  fs/btrfs/block-group.c | 20 ++++++++++++++++++++
>  fs/btrfs/disk-io.c     |  4 ++--
>  fs/btrfs/disk-io.h     |  2 ++
>  3 files changed, 24 insertions(+), 2 deletions(-)
>
> diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
> index 48ebc106a606..f485cf14c2f8 100644
> --- a/fs/btrfs/block-group.c
> +++ b/fs/btrfs/block-group.c
> @@ -2048,6 +2048,26 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info)
>         ret = check_chunk_block_group_mappings(info);
>  error:
>         btrfs_free_path(path);
> +
> +       if (ret == -EIO && btrfs_test_opt(info, IGNOREBADROOTS)) {
> +
> +               if (btrfs_super_log_root(info->super_copy) != 0) {
> +                       btrfs_warn(info, "Ignoring tree-log replay due to extent tree corruption!");
> +                       btrfs_set_super_log_root(info->super_copy, 0);
> +               }
> +
> +               btrfs_put_block_group_cache(info);
> +               btrfs_stop_all_workers(info);
> +               btrfs_free_block_groups(info);
> +               ret = btrfs_init_workqueues(info, NULL);
> +               if (ret)
> +                       return ret;
> +               ret = btrfs_init_space_info(info);
> +               if (ret)
> +                       return ret;
> +               return fill_dummy_bgs(info);
> +       }
> +
>         return ret;
>  }
>
> diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
> index 07a2b4f69b10..dc744f76d075 100644
> --- a/fs/btrfs/disk-io.c
> +++ b/fs/btrfs/disk-io.c
> @@ -1955,7 +1955,7 @@ static int read_backup_root(struct btrfs_fs_info *fs_info, u8 priority)
>  }
>
>  /* helper to cleanup workers */
> -static void btrfs_stop_all_workers(struct btrfs_fs_info *fs_info)
> +void btrfs_stop_all_workers(struct btrfs_fs_info *fs_info)
>  {
>         btrfs_destroy_workqueue(fs_info->fixup_workers);
>         btrfs_destroy_workqueue(fs_info->delalloc_workers);
> @@ -2122,7 +2122,7 @@ static void btrfs_init_qgroup(struct btrfs_fs_info *fs_info)
>         mutex_init(&fs_info->qgroup_rescan_lock);
>  }
>
> -static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info,
> +int btrfs_init_workqueues(struct btrfs_fs_info *fs_info,
>                 struct btrfs_fs_devices *fs_devices)
>  {
>         u32 max_active = fs_info->thread_pool_size;
> diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
> index e45057c0c016..f9bfcba86a04 100644
> --- a/fs/btrfs/disk-io.h
> +++ b/fs/btrfs/disk-io.h
> @@ -137,6 +137,8 @@ int btrfs_find_free_objectid(struct btrfs_root *root, u64 *objectid);
>  int btrfs_find_highest_objectid(struct btrfs_root *root, u64 *objectid);
>  int __init btrfs_end_io_wq_init(void);
>  void __cold btrfs_end_io_wq_exit(void);
> +void btrfs_stop_all_workers(struct btrfs_fs_info *fs_info);
> +int btrfs_init_workqueues(struct btrfs_fs_info *fs_info, struct btrfs_fs_devices *fs_devices);
>
>  #ifdef CONFIG_DEBUG_LOCK_ALLOC
>  void btrfs_set_buffer_lockdep_class(u64 objectid,
> --
> 2.30.2
>

Ping? Could anyone take a look?