Re: WARNING in __debug_object_init (3)

From: Dmitry Vyukov
Date: Mon Oct 29 2018 - 05:27:57 EST


On Mon, Oct 29, 2018 at 7:47 AM, Song Liu <liu.song.a23@xxxxxxxxx> wrote:
> On Sun, Oct 28, 2018 at 10:45 AM Eric Dumazet <eric.dumazet@xxxxxxxxx> wrote:
>>
>>
>>
>> On 10/28/2018 08:13 AM, Dmitry Vyukov wrote:
>> > On Sun, Oct 28, 2018 at 3:18 AM, syzbot
>> > <syzbot+6e682caa546b7c96c859@xxxxxxxxxxxxxxxxxxxxxxxxx> wrote:
>> >> Hello,
>> >>
>> >> syzbot found the following crash on:
>> >>
>> >> HEAD commit: 8c60c36d0b8c Add linux-next specific files for 20181019
>> >> git tree: linux-next
>> >> console output: https://syzkaller.appspot.com/x/log.txt?x=100feec5400000
>> >> kernel config: https://syzkaller.appspot.com/x/.config?x=8b6d7c4c81535e89
>> >> dashboard link: https://syzkaller.appspot.com/bug?extid=6e682caa546b7c96c859
>> >> compiler: gcc (GCC) 8.0.1 20180413 (experimental)
>> >> syz repro: https://syzkaller.appspot.com/x/repro.syz?x=13579abd400000
>> >> C reproducer: https://syzkaller.appspot.com/x/repro.c?x=13654f6b400000
>> >>
>> >> IMPORTANT: if you fix the bug, please add the following tag to the commit:
>> >> Reported-by: syzbot+6e682caa546b7c96c859@xxxxxxxxxxxxxxxxxxxxxxxxx
>> >
>> > +Eric knows what's wrong here. Something about "bpf: add tests for
>> > direct packet access from CGROUP_SKB" commit. Was is amended to fix a
>> > bug?
>> >
>>
>> I know little.
>>
>> It seems that this linux-next tree contains a (buggy) pre-version of
>> this commit :
>>
>> commit 2cb494a36c98279c5c6ce8e99cf9776f15449ade
>> Author: Song Liu <songliubraving@xxxxxx>
>> Date: Fri Oct 19 09:57:58 2018 -0700
>>
>> bpf: add tests for direct packet access from CGROUP_SKB
>>
>> Tests are added to make sure CGROUP_SKB cannot access:
>> tc_classid, data_meta, flow_keys
>>
>> and can read and write:
>> mark, prority, and cb[0-4]
>>
>> and can read other fields.
>>
>> To make selftest with skb->sk work, a dummy sk is added in
>> bpf_prog_test_run_skb().
>>
>> Signed-off-by: Song Liu <songliubraving@xxxxxx>
>> Signed-off-by: Alexei Starovoitov <ast@xxxxxxxxxx>
>>
>> Maybe bpf maintainers chose to pre-submit a buggy patch and rebased their tree.
>>
>> The buggy patch in linux-next was :
>>
>> commit 75079847e9d05d4cc1b7e09b29e22cbc8318a6b7
>> Author: Song Liu <songliubraving@xxxxxx>
>> Date: Thu Oct 18 09:06:49 2018 -0700
>>
>> bpf: add tests for direct packet access from CGROUP_SKB
>>
>> Tests are added to make sure CGROUP_SKB cannot access:
>> tc_classid, data_meta, flow_keys
>>
>> and can read and write:
>> mark, prority, and cb[0-4]
>>
>> and can read other fields.
>>
>> To make selftest with skb->sk work, a dummy sk is added in
>> bpf_prog_test_run_skb().
>>
>> Signed-off-by: Song Liu <songliubraving@xxxxxx>
>> Signed-off-by: Alexei Starovoitov <ast@xxxxxxxxxx>
>>
>
> Thanks Eric.
>
> Yeah, the version in the linux-next tree was a buggy version. The one
> in Linus' tree is correct. I confirmed that this issue doesn't repro in Linus'
> tree.

Then let's wait when linux-next drops the bad commit and then mark
this as invalid.