Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753331AbbBMOmd (ORCPT ); Fri, 13 Feb 2015 09:42:33 -0500 Received: from mx1.redhat.com ([209.132.183.28]:57869 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752603AbbBMOmb (ORCPT ); Fri, 13 Feb 2015 09:42:31 -0500 Date: Fri, 13 Feb 2015 08:41:52 -0600 From: Josh Poimboeuf To: Jiri Kosina Cc: Seth Jennings , Vojtech Pavlik , Masami Hiramatsu , live-patching@vger.kernel.org, linux-kernel@vger.kernel.org Subject: Re: [RFC PATCH 0/9] livepatch: consistency model Message-ID: <20150213144152.GD27180@treble.redhat.com> References: <20150213141904.GB27180@treble.redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.5.23.1-rc1 (2014-03-12) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1973 Lines: 46 On Fri, Feb 13, 2015 at 03:22:15PM +0100, Jiri Kosina wrote: > On Fri, 13 Feb 2015, Josh Poimboeuf wrote: > > > > How about we take a slightly different aproach -- put a probe (or ftrace) > > > on __switch_to() during a klp transition period, and examine stacktraces > > > for tasks that are just about to start running from there? > > > > > > The only tasks that would not be covered by this would be purely CPU-bound > > > tasks that never schedule. But we are likely in trouble with those anyway, > > > because odds are that non-rescheduling CPU-bound tasks are also > > > RT-priority tasks running on isolated CPUs, which we will fail to handle > > > anyway. > > > > > > I think Masami used similar trick in his kpatch-without-stopmachine > > > aproach. > > > > Yeah, that's definitely an option, though I'm really not too crazy about > > it. Hooking into the scheduler is kind of scary and disruptive. > > This is basically about running a stack checking for ->next before > switching to it, i.e. read-only operation (admittedly inducing some > latency, but that's the same with locking the runqueue). And only when in > transition phase. Yes, but it would introduce much more latency than locking rq, since there would be at least some added latency to every schedule() call during the transition phase. Locking the rq would only add latency in those cases where another CPU is trying to do a context switch while we're holding the lock. It also seems much more dangerous. A bug in __switch_to() could easily do a lot of damage. > > We'd also have to wake up all the sleeping processes. > > Yes, I don't think there is a way around that. Actually this patch set is a way around that :-) -- Josh -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/