From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S933053Ab2GBKca (ORCPT ); Mon, 2 Jul 2012 06:32:30 -0400 Received: from merlin.infradead.org ([205.233.59.134]:55434 "EHLO merlin.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932938Ab2GBKc2 convert rfc822-to-8bit (ORCPT ); Mon, 2 Jul 2012 06:32:28 -0400 Message-ID: <1341225139.23484.4.camel@twins> Subject: Re: rcu: BUG: spinlock recursion on CPU#3, trinity-child19/5970 From: Peter Zijlstra To: Sasha Levin Cc: paulmck@linux.vnet.ibm.com, Dave Jones , "linux-kernel@vger.kernel.org" Date: Mon, 02 Jul 2012 12:32:19 +0200 In-Reply-To: <1341006040.26928.4.camel@lappy> References: <1340964584.2936.40.camel@lappy> <20120629172320.GA2416@linux.vnet.ibm.com> <1341006040.26928.4.camel@lappy> Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7BIT X-Mailer: Evolution 3.2.2- Mime-Version: 1.0 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Fri, 2012-06-29 at 23:40 +0200, Sasha Levin wrote: > > The bad news are that what you saw was a lockdep enabled run > (CONFIG_PROVE_RCU is enabled, and lockdep was enabled). There were no > lockdep warnings at any point while reproducing it. rcu_switch_from() -> rcu_preempt_note_context_switch() is called _after_ the lockdep context switch annotation. Therefore lockdep things the prev task isn't holding any locks anymore.