From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755441Ab2GAR2y (ORCPT ); Sun, 1 Jul 2012 13:28:54 -0400 Received: from e31.co.us.ibm.com ([32.97.110.149]:40275 "EHLO e31.co.us.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754266Ab2GAR2x (ORCPT ); Sun, 1 Jul 2012 13:28:53 -0400 Message-ID: <4FF088B9.1000308@us.ibm.com> Date: Sun, 01 Jul 2012 10:28:25 -0700 From: John Stultz User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:13.0) Gecko/20120615 Thunderbird/13.0.1 MIME-Version: 1.0 To: Prarit Bhargava CC: Linux Kernel Subject: Re: [PATCH] [RFC] Potential fix for leapsecond caused futex related load spikes References: <4FF06CAB.9020800@redhat.com> <4FF08154.3050407@redhat.com> In-Reply-To: <4FF08154.3050407@redhat.com> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit x-cbid: 12070117-7282-0000-0000-00000A7A8681 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 07/01/2012 09:56 AM, Prarit Bhargava wrote: > > John, the issue is that clock_was_set calls on_each_cpu() -- which cannot be > called from interrupt context as it calls smp_call_function_many(). > > I don't think you can call call_was_set() from update_wall_time() as > update_wall_time() is called in interrupt context. > Thanks for pointing this out. Ben Blum also mentioned this last night, but I missed the atomic bit instead of the xtime_lock issue. Reworking the patch now. thanks again -john