From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752321Ab2FLPUR (ORCPT ); Tue, 12 Jun 2012 11:20:17 -0400 Received: from www.linutronix.de ([62.245.132.108]:44378 "EHLO Galois.linutronix.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751954Ab2FLPUQ (ORCPT ); Tue, 12 Jun 2012 11:20:16 -0400 Date: Tue, 12 Jun 2012 17:20:10 +0200 (CEST) From: Thomas Gleixner To: Peter Zijlstra cc: "Paul E. McKenney" , Sasha Levin , Ingo Molnar , "linux-kernel@vger.kernel.org" , Dave Jones Subject: Re: rcu,sched: spinlock recursion on 3.5-rc2 In-Reply-To: <1339514114.31548.78.camel@twins> Message-ID: References: <1339500907.4999.99.camel@lappy> <20120612144705.GB2423@linux.vnet.ibm.com> <1339514114.31548.78.camel@twins> User-Agent: Alpine 2.02 (LFD 1266 2009-07-14) MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII X-Linutronix-Spam-Score: -1.0 X-Linutronix-Spam-Level: - X-Linutronix-Spam-Status: No , -1.0 points, 5.0 required, ALL_TRUSTED=-1,SHORTCIRCUIT=-0.0001 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, 12 Jun 2012, Peter Zijlstra wrote: > On Tue, 2012-06-12 at 17:07 +0200, Thomas Gleixner wrote: > > Hmm, not sure. The deadlock was not triggered in switch_to. It was > > just at the beginning of __schedule() > > > > > How can you tell? switch_to() is a macro not a function, it won't ever > show up on a stack-trace.. but I think you meant context_switch() but > that typically gets inlined, similar problem. Bah, I misread the trace and the rcu code. :( So, yes the revert should solve the problem. Looks like I need more coffee, not Paul :) Thanks, tglx