From mboxrd@z Thu Jan 1 00:00:00 1970 From: Oleg Nesterov Subject: Re: [RFC PATCH v3 1/9] CPU hotplug: Provide APIs to prevent CPU offline from atomic context Date: Mon, 10 Dec 2012 18:28:59 +0100 Message-ID: <20121210172859.GB28479@redhat.com> References: <20121207173702.27305.1486.stgit@srivatsabhat.in.ibm.com> <20121207173759.27305.84316.stgit@srivatsabhat.in.ibm.com> <20121209191437.GA2816@redhat.com> <50C4EB79.5050203@linux.vnet.ibm.com> <20121209211338.GA8090@redhat.com> <50C56CC0.4000200@linux.vnet.ibm.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Received: from mx1.redhat.com ([209.132.183.28]:4703 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750696Ab2LJR3P (ORCPT ); Mon, 10 Dec 2012 12:29:15 -0500 Content-Disposition: inline In-Reply-To: <50C56CC0.4000200@linux.vnet.ibm.com> Sender: linux-pm-owner@vger.kernel.org List-Id: linux-pm@vger.kernel.org To: "Srivatsa S. Bhat" Cc: tglx@linutronix.de, peterz@infradead.org, paulmck@linux.vnet.ibm.com, rusty@rustcorp.com.au, mingo@kernel.org, akpm@linux-foundation.org, namhyung@kernel.org, vincent.guittot@linaro.org, tj@kernel.org, sbw@mit.edu, amit.kucheria@linaro.org, rostedt@goodmis.org, rjw@sisk.pl, wangyun@linux.vnet.ibm.com, xiaoguangrong@linux.vnet.ibm.com, nikunj@linux.vnet.ibm.com, linux-pm@vger.kernel.org, linux-kernel@vger.kernel.org On 12/10, Srivatsa S. Bhat wrote: > > On 12/10/2012 02:43 AM, Oleg Nesterov wrote: > > Damn, sorry for noise. I missed this part... > > > > On 12/10, Srivatsa S. Bhat wrote: > >> > >> On 12/10/2012 12:44 AM, Oleg Nesterov wrote: > >>> the latency. And I guess something like kick_all_cpus_sync() is "too heavy". > >> > >> I hadn't considered that. Thinking of it, I don't think it would help us.. > >> It won't get rid of the currently running preempt_disable() sections no? > > > > Sure. But (again, this is only my feeling so far) given that get_online_cpus_atomic() > > does cli/sti, > > Ah, that one! Actually, the only reason I do that cli/sti is because, potentially > interrupt handlers can be hotplug readers too. So we need to protect the portion > of the code of get_online_cpus_atomic() which is not re-entrant. Yes, I understand. > > this can help to implement ensure-the-readers-must-see-the-pending-writer. > > IOW this might help to implement sync-with-readers. > > > > 2 problems: > > 1. It won't help with cases like this: > > preempt_disable() > ... > preempt_disable() > ... > <------- Here > ... > preempt_enable() > ... > preempt_enable() No, I meant that kick_all_cpus_sync() can be used to synchronize with cli/sti in get_online_cpus_atomic(), just like synchronize_sched() does in the code I posted a minute ago. > 2. Part of the reason we want to get rid of stop_machine() is to avoid the > latency it induces on _all_ CPUs just to take *one* CPU offline. If we use > kick_all_cpus_sync(), we get into that territory again : we unfairly interrupt > every CPU, _even when_ that CPU's existing preempt_disabled() sections might > not actually be hotplug readers! (ie., not bothered about CPU Hotplug). I agree, that is why I said it is "too heavy". Oleg.