From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755766AbYEDCXf (ORCPT ); Sat, 3 May 2008 22:23:35 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1754107AbYEDCX1 (ORCPT ); Sat, 3 May 2008 22:23:27 -0400 Received: from gate.crashing.org ([63.228.1.57]:46657 "EHLO gate.crashing.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753375AbYEDCX0 (ORCPT ); Sat, 3 May 2008 22:23:26 -0400 Subject: Re: 'global' rq->clock From: Benjamin Herrenschmidt Reply-To: benh@kernel.crashing.org To: Ingo Molnar Cc: David Miller , a.p.zijlstra@chello.nl, efault@gmx.de, elendil@planet.nl, parag.warudkar@gmail.com, linux-kernel@vger.kernel.org, guichaz@yahoo.fr, andi@firstfloor.org In-Reply-To: <20080503223844.GA18344@elte.hu> References: <20080503082849.GA29605@elte.hu> <20080503.020502.226847930.davem@davemloft.net> <20080503101016.GA18801@elte.hu> <20080503.122734.01023096.davem@davemloft.net> <1209853855.26383.28.camel@pasglop> <20080503223844.GA18344@elte.hu> Content-Type: text/plain Date: Sun, 04 May 2008 12:22:47 +1000 Message-Id: <1209867767.26383.35.camel@pasglop> Mime-Version: 1.0 X-Mailer: Evolution 2.12.1 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org > on nohz we still keep jiffies uptodate - despite there not being an > explicit 'keep jiffies uptodate' tick interrupt anymore. So on every > irq_enter() we roll jiffies forward - if needed - and thus emulate > jiffies behavior to drivers and core kernel code, etc. > > if an IPI on Power does not do an irq_enter() then you might miss out on > updated jiffies. That might not matter for most jiffies, but you might > also miss out on the 'touch the softlockup watchdog because we just woke > from idle' action. This is what triggered the false positive warnings on > Sparc64. > > the same bug existed on x86 too: that too does a few IPIs without > irq_enter/irq_exit. We now removed the softlockup dependency so it > should not be required to do an irq_enter()/exit anymore - unless the > code that the IPI uses accesses jiffies. (but that would be unusual) Allright, so it looks like we don't have a problem today, though I'll be careful if some of our CPUs come up with more fancy ways to do IPIs. Currently they are just normal interrupts, so we do irq_enter/exit and we process softirqs on the way out. Ben.