Re: 6.12-rc1: general protection fault at pick_task_fair()
From: Breno Leitao
Date: Mon Sep 30 2024 - 12:57:01 EST
Hello Peter,
On Mon, Sep 30, 2024 at 04:48:09PM +0200, Peter Zijlstra wrote:
> On Mon, Sep 30, 2024 at 05:52:49AM -0700, Breno Leitao wrote:
> > Important to say that I am also seeing the following warning before the
> > crash:
> >
> > workqueue: drain_vmap_area_work hogged CPU for >20000us 4 times, consider switching to WQ_UNBOUND
> > ------------[ cut here ]------------
> > !se->on_rq
> > WARNING: CPU: 24 PID: 17 at kernel/sched/fair.c:704 dequeue_entity+0xd21/0x17c0
> >
> This looks to be the same issue as reported here:
>
> https://lkml.kernel.org/r/20240930144157.GH5594@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
Ok, I though they would be different given that it was crashing at
update_entity_lag() and not at pick_task_fair().
> Is there anything you can share about your setup / workload that manages
> to trigger this?
Nothing really. I have a test system where I install a debug kernel
(with some DEBUG+KASAN+LOCKDEP) and keep the host mostly idle, when I
hit it ~2x a day on average.
PS: I have the crashdump if you need me to investigate anything.