From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754095AbaCLL1R (ORCPT ); Wed, 12 Mar 2014 07:27:17 -0400 Received: from mail-vc0-f169.google.com ([209.85.220.169]:55168 "EHLO mail-vc0-f169.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753513AbaCLL1P (ORCPT ); Wed, 12 Mar 2014 07:27:15 -0400 MIME-Version: 1.0 In-Reply-To: <20140311163123.GC25564@dhcp-26-207.brq.redhat.com> References: <20140226230554.GE11655@kmo> <20140311140322.GA24065@dhcp-26-207.brq.redhat.com> <20140311163123.GC25564@dhcp-26-207.brq.redhat.com> Date: Wed, 12 Mar 2014 19:27:14 +0800 Message-ID: Subject: Re: [PATCH RESEND 1/3] percpu_ida: Fix data race on cpus_have_tags cpumask From: Ming Lei To: Alexander Gordeev Cc: Kent Overstreet , Linux Kernel Mailing List , Peter Zijlstra , Jens Axboe , "Nicholas A. Bellinger" Content-Type: text/plain; charset=ISO-8859-1 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Wed, Mar 12, 2014 at 12:31 AM, Alexander Gordeev wrote: > On Tue, Mar 11, 2014 at 11:34:21PM +0800, Ming Lei wrote: >> I mean the below block can be put inside the previous lock: > > Oh, *now* I see what you mean. Please, ignore my prevous reply. > Still, we want to release the lock as soon as possible and > there is no reason to the below bits it under lock. Actually my comment was wrong because pool->cpus_have_tags should be guarded by pool->lock instead of the percpu tag->lock. Sorry for the noise. Thanks, -- Ming Lei