Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753894Ab1FGNQq (ORCPT ); Tue, 7 Jun 2011 09:16:46 -0400 Received: from merlin.infradead.org ([205.233.59.134]:39792 "EHLO merlin.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751898Ab1FGNQp convert rfc822-to-8bit (ORCPT ); Tue, 7 Jun 2011 09:16:45 -0400 Subject: Re: [tip:sched/urgent] sched: Fix cross-cpu clock sync on remote wakeups From: Peter Zijlstra To: Borislav Petkov Cc: Yong Zhang , Borislav Petkov , "mingo@redhat.com" , "hpa@zytor.com" , "linux-kernel@vger.kernel.org" , "markus@trippelsdorf.de" , "tglx@linutronix.de" , "mingo@elte.hu" , "linux-tip-commits@vger.kernel.org" In-Reply-To: <20110607131216.GC27813@aftab> References: <20110531125621.GA24439@gere.osrc.amd.com> <1306847516.2353.80.camel@twins> <20110601070547.GB3368@liondog.tnic> <1306924612.2353.176.camel@twins> <20110601155017.GD24028@aftab> <1307019866.2497.675.camel@laptop> <20110602142340.GA3356@zhy> <1307029711.2497.717.camel@laptop> <20110607131216.GC27813@aftab> Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 8BIT Date: Tue, 07 Jun 2011 15:16:20 +0200 Message-ID: <1307452580.2322.252.camel@twins> Mime-Version: 1.0 X-Mailer: Evolution 2.30.3 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1817 Lines: 38 On Tue, 2011-06-07 at 15:12 +0200, Borislav Petkov wrote: > On Thu, Jun 02, 2011 at 11:48:31AM -0400, Peter Zijlstra wrote: > > Crap.. you're right. And I bet other archs don't do that either. With > > NO_HZ you really need irq_enter() for pretty much all interrupts so I > > was assuming the resched IPI had it, but its been special and never > > really needed it. If it would wake an idle cpu the idle loop exit would > > deal with it, if it interrupted userspace the thing was running and > > NO_HZ wasn't relevant. > > > > Damn. > > > > And yes, the only reason I didn't see this on my dev box was because we > > do indeed set that sched_clock_stable thing on wsm. And I never noticed > > on my desktop because firefox/X/etc. consuming heaps of CPU isn't weird > > at all. > > > > Adding it to all resched int handlers is of course a possibility but > > would slow down the thing, although with the new code, most users are > > now indeed wakeups (excepting weird and wonderful users like KVM). > > FWIW, we could set the sched_clock_stable on AMD too - at least on F10h > and later. This will take care of the problem at hand and defer the > issue of slowing down the resched ipi handlers. > > I dunno, however, whether we still would need the proper ->tick_gtod > update for correct ttwu accounting regardless of sched_clock_stable on > K8 (unstable TSCs) and maybe even other arches. Yeah, I think I'm going to commit this extra irq_enter() thing for now, and then slowly go through all the arches again and remove this one here once all archs are sorted. -- 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/