From mboxrd@z Thu Jan 1 00:00:00 1970 From: Thomas Renninger Subject: Re: [PATCH 3.6-rc6] cpufreq/powernow-k8: workqueue user shouldn't migrate the kworker to another CPU Date: Sun, 23 Sep 2012 03:53:48 +0200 Message-ID: <201209230353.49737.trenn@suse.de> References: <20120917201721.GJ18677@google.com> <201209172238.21087.rjw@sisk.pl> Mime-Version: 1.0 Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <201209172238.21087.rjw@sisk.pl> Sender: cpufreq-owner@vger.kernel.org List-ID: Content-Type: Text/Plain; charset="us-ascii" To: "Rafael J. Wysocki" Cc: Tejun Heo , Andre Przywara , Linus Torvalds , linux-kernel@vger.kernel.org, cpufreq@vger.kernel.org, linux-pm@vger.kernel.org, Duncan <1i5t5.duncan@cox.net>, Andreas Herrmann Hi, better late than never.. On Monday 17 September 2012 22:38:20 Rafael J. Wysocki wrote: > On Monday, September 17, 2012, Tejun Heo wrote: > > powernowk8_target() runs off a per-cpu work item and if the > > cpufreq_policy->cpu is different from the current one, it migrates the > > kworker to the target CPU by manipulating current->cpus_allowed. The > > function migrates the kworker back to the original CPU but this is > > still broken. Workqueue concurrency management requires the kworkers > > to stay on the same CPU and powernowk8_target() ends up triggerring > > BUG_ON(rq != this_rq()) in try_to_wake_up_local() if it contends on > > fidvid_mutex and sleeps. > > > > It is unclear why this bug is being reported now. Duncan says it > > appeared to be a regression of 3.6-rc1 and couldn't reproduce it on > > 3.5. Bisection seemed to point to 63d95a91 "workqueue: use @pool > > instead of @gcwq or @cpu where applicable" which is an non-functional > > change. Given that the reproduce case sometimes took upto days to > > trigger, it's easy to be misled while bisecting. Maybe something made > > contention on fidvid_mutex more likely? I don't know. > > > > This patch fixes the bug by punting to another per-cpu work item on > > the target CPU if it isn't the same as the current one. The code > > assumes that cpufreq_policy->cpu is kept online by the caller, which > > Rafael tells me is the case. > > > > Signed-off-by: Tejun Heo > > Reported-by: Duncan <1i5t5.duncan@cox.net> > > Cc: Rafael J. Wysocki > > Cc: Andreas Herrmann > > Cc: stable@kernel.org > > Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=47301 > > --- > > > > While it's very late in the merge cycle, the fix is limited in scope > > and fairly safe, so it wouldn't be too crazy to merge but then again > > this can go through the next -rc1 and then -stable. Linus, Rafael, > > what do you guys think? > > Well, I don't see much reason to wait with this, although I'd like some > more people to check it. > > Andre, Thomas, can you please have a look at it? The cpufreq changes are not really (functional) changes. I cannot judge the risk of the real change: > > + INIT_WORK_ONSTACK(&tw.work, powernowk8_target_on_cpu); instead of using set_cpus_allowed_ptr. Changing scheduler behavior of powernow-k8 sounds rather intrusive for rc6, but I would fully trust Tejun's advise on this. I wonder whether more drivers are affected similarly, grepping for: set_cpus_allowed_ptr shows quite some hits. My 2 cents..., Thomas