From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753628Ab2AaRjZ (ORCPT ); Tue, 31 Jan 2012 12:39:25 -0500 Received: from e9.ny.us.ibm.com ([32.97.182.139]:35669 "EHLO e9.ny.us.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752270Ab2AaRjX (ORCPT ); Tue, 31 Jan 2012 12:39:23 -0500 Date: Tue, 31 Jan 2012 09:38:59 -0800 From: "Paul E. McKenney" To: Steffen Persvold Cc: Daniel J Blueman , Dipankar Sarma , linux-kernel@vger.kernel.org, x86@kernel.org Subject: Re: RCU qsmask !=0 warnings on large-SMP... Message-ID: <20120131173859.GD2391@linux.vnet.ibm.com> Reply-To: paulmck@linux.vnet.ibm.com References: <4F2070B9.2000104@numascale.com> <20120125213450.GJ2849@linux.vnet.ibm.com> <4F2086DA.4040203@numascale.com> <20120126015843.GN2849@linux.vnet.ibm.com> <4F216B85.7010208@numascale.com> <20120126192653.GC2437@linux.vnet.ibm.com> <4F2285E5.9050705@numascale.com> <20120129060921.GC17696@linux.vnet.ibm.com> <20120130161529.GA5118@linux.vnet.ibm.com> <4F2825D1.3030306@numascale.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <4F2825D1.3030306@numascale.com> User-Agent: Mutt/1.5.21 (2010-09-15) X-Content-Scanned: Fidelis XPS MAILER x-cbid: 12013117-7182-0000-0000-0000009DE0CE Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, Jan 31, 2012 at 06:33:05PM +0100, Steffen Persvold wrote: > On 1/30/2012 17:15, Paul E. McKenney wrote: > [] > >> > >>Hmmm... I wonder if it waits for a grace period? > >> > >>If it cannot be made to work, I can probably put together some > >>alternative diagnostics, but it will take me a day or three. > > > >Actually, another thing to try is "torture_type=rcu_bh" on the modprobe > >line for rcutorture. Also, it would be good to get a stack dump of the > >hung process -- it might be hung for some other reason. > > Paul, > > Do not dwell more over this issue at the moment. I have indications > that the inconsistency we're seeing is related to something else > than the RCU code itself. Thank you for letting me know! Thanx, Paul