Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
DMARC-Filter: OpenDMARC Filter v1.3.2 smtp.codeaurora.org E7BF5604BE
Date:   Mon, 6 Aug 2018 14:07:36 +0530
From:   Pavan Kondeti <pkondeti@codeaurora.org>
To:     Sodagudi Prasad <psodagud@codeaurora.org>
Cc:     Peter Zijlstra <peterz@infradead.org>,
        Thomas Gleixner <tglx@linutronix.de>,
        Sebastian Andrzej Siewior <bigeasy@linutronix.de>,
        isaacm@codeaurora.org, matt@codeblueprint.co.uk, mingo@kernel.org,
        linux-kernel@vger.kernel.org, gregkh@linuxfoundation.org,
        stable@vger.kernel.org
Subject: Re: [PATCH] stop_machine: Disable preemption after queueing stopper
 threads
Message-ID: <20180806083736.GA2661@codeaurora.org>
References: <1531856129-9871-1-git-send-email-isaacm@codeaurora.org>
 <a30d1e147d3181fc7b294262e380a10c@codeaurora.org>
 <20180724062350.nlem2suuy5wlxpts@linutronix.de>
 <alpine.DEB.2.21.1807301220280.2518@nanos.tec.linutronix.de>
 <20180730112140.GH2494@hirez.programming.kicks-ass.net>
 <alpine.DEB.2.21.1807301440340.2518@nanos.tec.linutronix.de>
 <109d0e70606ccd34861a80525d6d11aa@codeaurora.org>
 <20180730210728.GQ2494@hirez.programming.kicks-ass.net>
 <52a34ed365cd560457e9abf5877c5b37@codeaurora.org>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <52a34ed365cd560457e9abf5877c5b37@codeaurora.org>
User-Agent: Mutt/1.5.21 (2010-09-15)
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

Hi Prasad,

On Wed, Aug 01, 2018 at 01:07:03AM -0700, Sodagudi Prasad wrote:
> On 2018-07-30 14:07, Peter Zijlstra wrote:
> >On Mon, Jul 30, 2018 at 10:12:43AM -0700, Sodagudi Prasad wrote:
> >>How about including below change as well?  Currently, there is
> >>no way to
> >>identify thread migrations completed or not.  When we observe
> >>this issue,
> >>the symptom was work queue lock up. It is better to have some
> >>timeout here
> >>and induce the bug_on.
> >
> >You'd trigger the soft-lockup or hung-task detector I think. And
> >if not,
> >we ought to look at making it trigger at least one of those.
> >
> >>There is no way to identify the migration threads stuck or not.
> >
> >Should be pretty obvious from the splat generated by the above, no?
> Hi Peter and Thomas,
> 
> Thanks for your support.
> I have another question on this flow and retry mechanism used in
> this cpu_stop_queue_two_works() function using the global variable
> stop_cpus_in_progress.
> 
> This variable is getting used in various paths, such as task
> migration, set task affinity, and CPU hotplug.
> 
> For example cpu hotplug path, stop_cpus_in_progress variable getting
> set with true with out checking.
> takedown_cpu()
> --stop_machine_cpuslocked()
> ---stop_cpus()
> ---__stop_cpus()
> ----queue_stop_cpus_work()
> setting stop_cpus_in_progress to true directly.
> 
> But in the task migration path only, the stop_cpus_in_progress
> variable is used for retry.
> 
> I am thinking that stop_cpus_in_progress variable lead race
> conditions, where CPU hotplug and task migration happening
> simultaneously. Please correct me If my understanding wrong.
> 

The stop_cpus_in_progress variable is to guard against out of order queuing.
The stopper locks does not protect this when cpu_stop_queue_two_works() and
stop_cpus() are executing in parallel.

stop_one_cpu_{nowait} functions are called to handle affinity change and
load balance. Since we are queuing the work only on 1 CPU,
stop_cpus_in_progress variable protection is not needed.

Thanks,
Pavan
-- 
Qualcomm India Private Limited, on behalf of Qualcomm Innovation Center, Inc.
Qualcomm Innovation Center, Inc. is a member of Code Aurora Forum, a Linux Foundation Collaborative Project.