linux-kernel - Re: [PATCH] sched/isolation: Make NO_HZ_FULL select CPU

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Sat, 2 Dec 2017 14:59:12 +0100
From:   Frederic Weisbecker <frederic@...nel.org>
To:     paulmck@...ux.vnet.ibm.com
Cc:     linux-kernel@...r.kernel.org, xiaolong.ye@...el.com,
        tglx@...utronix.de, cmetcalf@...lanox.com, cl@...ux.com,
        torvalds@...ux-foundation.org, lcapitulino@...hat.com,
        efault@....de, peterz@...radead.org, riel@...hat.com,
        kernellwp@...il.com, mingo@...nel.org, john.stultz@...aro.org
Subject: Re: [PATCH] sched/isolation: Make NO_HZ_FULL select CPU_ISOLATION

2017-11-30 21:20 UTC+01:00, Paul E. McKenney <paulmck@...ux.vnet.ibm.com>:
> Commit 5c4991e24c69 ("sched/isolation: Split out new
> CONFIG_CPU_ISOLATION=y config from CONFIG_NO_HZ_FULL") can result in RCU
> CPU stall warnings when running rcutorture with CONFIG_NO_HZ_FULL_ALL=y
> and CONFIG_CPU_ISOLATION=n.  These warnings are caused by RCU's
> grace-period kthreads sleeping for a few jiffies, but never being
> awakened:
>
> [  116.353432] rcu_preempt kthread starved for 9974 jiffies! g4294967208
> +c4294967207 f0x0 RCU_GP_WAIT_FQS(3) ->state=0x402 ->cpu=0
> [  116.355517] rcu_preempt     I 7464     8      2 0x80000000
> [  116.356543] Call Trace:
> [  116.357008]  __schedule+0x493/0x620
> [  116.357682]  schedule+0x24/0x40
> [  116.358291]  schedule_timeout+0x330/0x3b0
> [  116.359024]  ? preempt_count_sub+0xea/0x140
> [  116.359806]  ? collect_expired_timers+0xb0/0xb0
> [  116.360660]  rcu_gp_kthread+0x6bf/0xef0
>
> This commit therefore makes NO_HZ_FULL select CPU_ISOLATION, which
> prevents this behavior and seems like it was the original intention in
> any case.

Although CONFIG_NO_HZ should indeed select CONFIG_CPU_ISOLATION, I'm
surprised about this stall. I'm even  more surprised that setting
CONFIG_CPU_ISOLATION=y is enough to fix the issue because
CONFIG_NO_HZ_FULL_ALL shortcuts CONFIG_CPU_ISOLATION entirely (which
is not good, but work in progress...).

Did you have any nohz_full= or isolcpus= boot options?

Thanks.