From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751944Ab1LTQbZ (ORCPT ); Tue, 20 Dec 2011 11:31:25 -0500 Received: from smtp107.prem.mail.ac4.yahoo.com ([76.13.13.46]:45383 "HELO smtp107.prem.mail.ac4.yahoo.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with SMTP id S1751418Ab1LTQbN (ORCPT ); Tue, 20 Dec 2011 11:31:13 -0500 X-Yahoo-Newman-Property: ymail-3 X-YMail-OSG: HIshzKQVM1ladIzPWTJScIznoT3Opb2vAM_12C9yXrbYkpJ vHwBvXXUGst64HBYLwIIPReLXhBPQFnrpQMa62Rn3uWFdWLZMrsDylrH5y7m 79WRxSmyE7DBseyi.68asoGUwuhbBnbiOFnmcQk6kkvI7JB8UEU4Pbmrzv7p 4X_DQTOZ4.DQER.BWyh3mKEg6WeY57Q8_b2WVOcRWjVACF0HAJHYXO.OD5y_ SPzAZMyXakX_x_sg4K9YldNe7V1Yw9EBxJt.6INwNykE7TUfrg4NLF.Ve9Ew xtbVrI5C7la1pxg_41XfxxYMsK23QA5wVyCqd1UTR5b9TUY8EPTfwWmevx4g mAvUNparS.KN3aCHAAUU2ndurOVcrjk0O6X91uQkgTLDqbTtDudCVzct83ZK q_g0q8lJaYB6pZAaq9I8Dmw-- X-Yahoo-SMTP: _Dag8S.swBC1p4FJKLCXbs8NQzyse1SYSgnAbY0- Date: Tue, 20 Dec 2011 10:31:09 -0600 (CST) From: Christoph Lameter X-X-Sender: cl@router.home To: Tejun Heo cc: Pekka Enberg , Linus Torvalds , Ingo Molnar , Andrew Morton , linux-kernel@vger.kernel.org, linux-arch@vger.kernel.org, Thomas Gleixner Subject: Re: [GIT PULL] slab fixes for 3.2-rc4 In-Reply-To: <20111220162315.GC10752@google.com> Message-ID: References: <20111220162315.GC10752@google.com> User-Agent: Alpine 2.00 (DEB 1167 2008-08-23) MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, 20 Dec 2011, Tejun Heo wrote: > This is __this_cpu_add() + preemption disabled check. Should be > removed. Christoph, is there a use case where __this_cpu_XXX() is > used without preemption disabled? Why doesn't it have preemption > check? We discussed this before and said that it would be possible to add a preemption check there. We would need to verify that there is no use case of __this_cpu_XXX operations in preemptable context. There used to be a case where we did not care about the races for the vmstat counters but that seems to have been changed. Not aware of any other use case like that.