From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754752Ab2LKUQx (ORCPT ); Tue, 11 Dec 2012 15:16:53 -0500 Received: from mail.skyhub.de ([78.46.96.112]:41850 "EHLO mail.skyhub.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753034Ab2LKUQw (ORCPT ); Tue, 11 Dec 2012 15:16:52 -0500 Date: Tue, 11 Dec 2012 21:16:47 +0100 From: Borislav Petkov To: =?utf-8?B?RnLDqWTDqXJpYyBMLiBXLg==?= Meunier Cc: Linux Kernel Subject: Re: BUG: soft lockup with 3.7.0 but not 3.6.10 Message-ID: <20121211201647.GD8873@liondog.tnic> Mail-Followup-To: Borislav Petkov , =?utf-8?B?RnLDqWTDqXJpYyBMLiBXLg==?= Meunier , Linux Kernel References: <20121211213636.GA19943@pervalidus> MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Disposition: inline Content-Transfer-Encoding: 8bit In-Reply-To: <20121211213636.GA19943@pervalidus> User-Agent: Mutt/1.5.21 (2010-09-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, Dec 11, 2012 at 07:36:36PM -0200, Frédéric L. W. Meunier wrote: > While compiling MPlayer git on 3.7.0, I noticed the attached messages. I > then compiled 3.6.10, without any message being printed by the kernel, > and thought it could be due to MPlayer being compiled on tmpfs, while > the kernel on ext4. But compiling MPlayer on ext4 didn't change > anything. > > I booted on 3.6.10 and couldn't reproduce it. > > According to 'free', swap isn't used at all during the compilation. > > I'm also attaching my .config. > > It's an Athlon 64 X2 Dual Core Processor 4000+ with 2Gb of DDR2. What family is that? Can you give /proc/cpuinfo? > Dec 11 16:02:15 pervalidus kernel: [11260.096015] BUG: soft lockup - CPU#1 stuck for 22s! [cc1:20906] Hmm, this says that gcc gets stuck at some point. Is this always reproducible on 3.7? What about using another version of gcc, can you repro it then too? It would be interesting to know where all those cc1 processes get stuck. Can you break into them with gdb and dump the code around RIP everytime those tasks gets stuck? Try doing a couple of them to see whether it is repeatable. Thanks. -- Regards/Gruss, Boris. Sent from a fat crate under my desk. Formatting is fine. --