From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752109Ab2IKXuk (ORCPT ); Tue, 11 Sep 2012 19:50:40 -0400 Received: from e7.ny.us.ibm.com ([32.97.182.137]:47052 "EHLO e7.ny.us.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751484Ab2IKXuj (ORCPT ); Tue, 11 Sep 2012 19:50:39 -0400 Message-ID: <504FCE48.1050409@linaro.org> Date: Tue, 11 Sep 2012 16:50:32 -0700 From: John Stultz User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:15.0) Gecko/20120827 Thunderbird/15.0 MIME-Version: 1.0 To: Fengguang Wu CC: Thomas Gleixner , Ingo Molnar , LKML Subject: Re: BUG: soft lockup - CPU#1 stuck for 1024s! References: <20120909075927.GA13058@localhost> <504E1E19.9050106@linaro.org> <20120911234130.GA13382@localhost> In-Reply-To: <20120911234130.GA13382@localhost> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-Content-Scanned: Fidelis XPS MAILER x-cbid: 12091123-5806-0000-0000-0000197FDD92 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 09/11/2012 04:41 PM, Fengguang Wu wrote: > On Mon, Sep 10, 2012 at 10:06:33AM -0700, John Stultz wrote: >> On 09/09/2012 12:59 AM, Fengguang Wu wrote: >>> Hi John, >>> >>> The below lockup warning pops up very occasionally in kvm guest >>> kernels and it's bisected down to >>> >>> commit 2a8c0883c3cfffcc148ea606e2a4e7453cd75e73 >>> Author: John Stultz >>> Date: Fri Jul 13 01:21:56 2012 -0400 >>> >>> time: Move xtime_nsec adjustment underflow handling timekeeping_adjust >>> >>> [ 8.340327] Freeing unused kernel memory: 460k freed >>> [ 1107.515496] [sched_delayed] sched: RT throttling activated >>> [ 1107.516439] BUG: soft lockup - CPU#1 stuck for 1024s! [swapper/1:0] >> >> Thanks so much for sending this. One detail I'm curious about is >> that these kernels from the Bug messages seem to be v3.6-rc1 or >> earlier. >> >> Ingo had a fix 1d17d17484d40f2d5b35c79518597a2b25296996 ("time: Fix >> adjustment cleanup bug in timekeeping_adjust") that landed in >> 3.6-rc2 >> >> Has this issue actually been seen on a 3.6-rc2+ kernel? > Nope. I tested -rc5 for 10000+ boots and it's obviously free from the bug. > Sorry for the noise! No worries. Thanks so much for following up on this, and your continued testing! -john