From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1761627Ab2COALg (ORCPT ); Wed, 14 Mar 2012 20:11:36 -0400 Received: from mga14.intel.com ([143.182.124.37]:14388 "EHLO mga14.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1759355Ab2COALf convert rfc822-to-8bit (ORCPT ); Wed, 14 Mar 2012 20:11:35 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.71,315,1320652800"; d="scan'208";a="77663195" From: "Liu, Chuansheng" To: Peter Zijlstra CC: "linux-kernel@vger.kernel.org" , Yanmin Zhang , "tglx@linutronix.de" Subject: RE: [PATCH] Fix the race between smp_call_function and CPU booting Thread-Topic: [PATCH] Fix the race between smp_call_function and CPU booting Thread-Index: AQHNAcbuNZzs3JjW0Uu/4BUvgje4I5Zqe/Ag Date: Thu, 15 Mar 2012 00:11:32 +0000 Message-ID: <27240C0AC20F114CBF8149A2696CBE4A056F47@SHSMSX101.ccr.corp.intel.com> References: <27240C0AC20F114CBF8149A2696CBE4A053BE8@SHSMSX101.ccr.corp.intel.com> <1331546307.18960.26.camel@twins> <27240C0AC20F114CBF8149A2696CBE4A054D70@SHSMSX101.ccr.corp.intel.com> <1331654251.18960.78.camel@twins> <27240C0AC20F114CBF8149A2696CBE4A0556FA@SHSMSX101.ccr.corp.intel.com> <1331718197.18960.106.camel@twins> In-Reply-To: <1331718197.18960.106.camel@twins> Accept-Language: zh-CN, en-US Content-Language: en-US X-MS-Has-Attach: X-MS-TNEF-Correlator: x-originating-ip: [10.239.127.40] Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 8BIT MIME-Version: 1.0 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org > -----Original Message----- > From: Peter Zijlstra [mailto:peterz@infradead.org] > Sent: Wednesday, March 14, 2012 5:43 PM > To: Liu, Chuansheng > Cc: linux-kernel@vger.kernel.org; Yanmin Zhang; tglx@linutronix.de > Subject: RE: [PATCH] Fix the race between smp_call_function and CPU booting > > On Wed, 2012-03-14 at 06:27 +0000, Liu, Chuansheng wrote: > > On the unplug case, after set the CPU to !active, we do not need IPI > > handling for the corresponding CPU before it is set to offline. I did > > not find any impact that limiting the smp_call_function just after CPU > > is active. > > Have a look at Alpha, it's flush_tlb_mm() can use smp_call_function(), in > the !active,online case you very much still need to tlb flush that cpu. > > The fact that it works on a limited use case on x86 doesn't say anything much > at all. Thanks your pointing out, do you have any other perfect solution for this issue? As for the stress test result, advancing the setting active before setting online broken something either.