From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1758090AbXIKVuK (ORCPT ); Tue, 11 Sep 2007 17:50:10 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753225AbXIKVt5 (ORCPT ); Tue, 11 Sep 2007 17:49:57 -0400 Received: from www.osadl.org ([213.239.205.134]:54747 "EHLO mail.tglx.de" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1755558AbXIKVt4 (ORCPT ); Tue, 11 Sep 2007 17:49:56 -0400 Subject: Re: clockevents: fix resume logic From: Thomas Gleixner To: Andrew Morton Cc: "Rafael J. Wysocki" , Linux Kernel Mailing List , john stultz , Ingo Molnar , Len Brown , Venkatesh Pallipadi In-Reply-To: <1189540321.5235.21.camel@chaos> References: <200707220159.l6M1xBgH001236@hera.kernel.org> <200709111323.56030.rjw@sisk.pl> <20070911042228.1ef690e0.akpm@linux-foundation.org> <200709111409.13796.rjw@sisk.pl> <20070911112531.80bac380.akpm@linux-foundation.org> <1189535883.5235.13.camel@chaos> <20070911114417.3f6e9e1b.akpm@linux-foundation.org> <1189540321.5235.21.camel@chaos> Content-Type: text/plain Date: Tue, 11 Sep 2007 23:49:47 +0200 Message-Id: <1189547387.5235.69.camel@chaos> Mime-Version: 1.0 X-Mailer: Evolution 2.11.92 (2.11.92-1.fc8) Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org On Tue, 2007-09-11 at 21:52 +0200, Thomas Gleixner wrote: > > C1: type[C1] promotion[C2] demotion[--] latency[001] usage[00000010] duration[00000000000000000000] > > *C2: type[C2] promotion[--] demotion[C1] latency[001] usage[00008316] duration[00000000000170717293] > > Ok, here we are. The bad one uses C2 which stops the local apic on the > VAIO. I suspect we end up in the suspend/resume with going into C2 > without the broadcast active. > > Can you try to get the output of SysRq-Q during the "it needs help from > keyboard" period ? Summary of the oddities we are seing: 1.) disabling local apic timer makes the problem go away 2.) disabling nohz and highres makes the problem go away 3.) adding the cpuidle patches from the acpi tree makes the problem go away The obvious conclusion is, that in all other cases we run into a state, where the local apic timer is not working. 1) we do not use it 2) it is used in periodic mode 3) the cpu does not enter C2 (which turns the lapic timer off on the VAIO) While 1) and 3) are understandable, the reason why 2) is working is a mystery because the periodic mode is affected by the C state as well. Andrew, can you please provide the output of /proc/timer_list when you boot the kernel with "nohz=off highres=off", but honestly I do not expect a lot of enlightenment from it. The Sysrq-Q output from the point where the box is stuck without keystrokes might give us more information. tglx