Re: REGRESSION: kernel BUG at arch/arm64/kernel/alternative.c:157!

From: John Stultz
Date: Wed May 19 2021 - 21:17:03 EST


On Tue, May 18, 2021 at 1:49 AM Will Deacon <will@xxxxxxxxxx> wrote:
>
> Hi John,
>
> On Mon, May 17, 2021 at 02:52:59PM -0700, John Stultz wrote:
> > With v5.13-rc2, I've been seeing an odd boot regression with the
> > DragonBoard 845c:
> >
> > Unfortunately, trying to bisect it down (v5.13-rc1 works ok) is giving
> > me inconsistent results so far. It feels a bit like maybe some config
> > option gets enabled moving forward, and then sticks around when we go
> > back. I'll take another swing at bisecting it later today, but I have
> > to move on to some other work right now, so I figured I'd share (with
> > folks who better know the recent __apply_alternatives changes) in case
> > folks have a better idea:
>
> Please can you try reverting af44068c581c and 0c6c2d3615ef?

Hey Will,
I realized I didn't get back to you on this. As MarkR already noted
it does seem to be coming from 0c6c2d3615ef. Jumping to 5.13-rc1,
doing a make clean, building/booting then jumping to 5.13-rc2 + the
two reverts above, building/booting, and the issue won't appear. If we
just jump to 5.13-rc2 or 5.13-rc2 with af44068c581c reverted, after
building and booting I'll be able to see the issue.

Given it disappears after a make clean, I'm guessing this isn't a
major issue, mostly just a concern for folks to accidently hit it
bisecting things, so I'm not sure if there's anything else to do.

Let me know if you'd like me to try anything else.

thanks
-john