[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <Y+WSJRjlB4qDI1ul@lothringen>
Date: Fri, 10 Feb 2023 01:39:01 +0100
From: Frederic Weisbecker <frederic@...nel.org>
To: Zqiang <qiang1.zhang@...el.com>,
Nicholas Piggin <npiggin@...il.com>
Cc: mingo@...hat.com, peterz@...radead.org, juri.lelli@...hat.com,
paulmck@...nel.org, joel@...lfernandes.org, rcu@...r.kernel.org,
linux-kernel@...r.kernel.org
Subject: Re: [PATCH v2] sched/isolation: Fix illegal CPU value by
housekeeping_any_cpu() return
Thanks for checking this!
On Fri, Feb 10, 2023 at 08:00:21AM +0800, Zqiang wrote:
> For kernels built with CONFIG_NO_HZ_FULL=y, running the following tests:
>
> runqemu kvm slirp nographic qemuparams="-m 1024 -smp 4" bootparams=
> "console=ttyS0 nohz_full=0,1 rcu_nocbs=0,1 sched_verbose" -d
Has this ever worked? Again I'm tempted to just:
git revert 08ae95f4fd3b38b257f5dc7e6507e071c27ba0d5
>
> root@...ux86-64:~# echo 0 > /sys/devices/system/cpu/cpu2/online
> root@...ux86-64:~# echo 0 > /sys/devices/system/cpu/cpu3/online
>
> [ 22.838290] BUG: unable to handle page fault for address: ffffffff84cd48c0
Powered by blists - more mailing lists