Re: INFO: rcu detected stall in sys_sendfile64 (2)

From: Tetsuo Handa
Date: Sat Jan 19 2019 - 08:01:24 EST


On 2019/01/19 20:41, Dmitry Vyukov wrote:
> On Sat, Jan 19, 2019 at 12:32 PM syzbot
> <syzbot+1505c80c74256c6118a5@xxxxxxxxxxxxxxxxxxxxxxxxx> wrote:
>>
>> Hello,
>>
>> syzbot found the following crash on:
>>
>> HEAD commit: 2339e91d0e66 Merge tag 'media/v5.0-1' of git://git.kernel...
>> git tree: upstream
>> console output: https://syzkaller.appspot.com/x/log.txt?x=175f2638c00000
>> kernel config: https://syzkaller.appspot.com/x/.config?x=abc3dc9b7a900258
>> dashboard link: https://syzkaller.appspot.com/bug?extid=1505c80c74256c6118a5
>> compiler: gcc (GCC) 9.0.0 20181231 (experimental)
>> syz repro: https://syzkaller.appspot.com/x/repro.syz?x=12c4dc28c00000
>> C reproducer: https://syzkaller.appspot.com/x/repro.c?x=15df4108c00000
>
> Looking at the reproducer it looks like something with scheduler as it
> involves perf_event_open and sched_setattr. So +Peter and Mingo.
> Is it the same root cause as the other stalls involving sched_setattr?

Yes. I think sched_setattr() involves this problem.

Reproducers from "BUG: workqueue lockup (4)" at
https://syzkaller.appspot.com/text?tag=ReproC&x=13ec31a5400000
involves sched_setattr(SCHED_DEADLINE) and
https://syzkaller.appspot.com/text?tag=ReproC&x=104da690c00000
also involves sched_setattr().