On Tue, 2021-03-02 at 20:01 +0100, Dmitry Vyukov wrote:
>
> Looking at the reproducer that mostly contains just perf_event_open,
> It may be the old known issue of perf_event_open with some extreme
> parameters bringing down kernel.
> +perf maintainers
> And as far as I remember +Peter had some patch to restrict
> perf_event_open parameters.
>
> r0 = perf_event_open(&(0x7f000001d000)={0x1, 0x70, 0x0, 0x0, 0x0, 0x0,
> 0x0, 0x3ff, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0,
> 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0,
> 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0xfffffffe, 0x0, @perf_config_ext}, 0x0,
> 0x0, 0xffffffffffffffff, 0x0)
Oh! Thanks for looking.
Seems that also applies to
https://syzkaller.appspot.com/bug?extid=d6219cf21f26bdfcc22e
FWIW. I was still tracking that one, but never had a chance to look at
it (also way down the list since it was reported as directly in hwsim)
johannes
