From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1759522AbYCZPxm (ORCPT ); Wed, 26 Mar 2008 11:53:42 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1759340AbYCZPxa (ORCPT ); Wed, 26 Mar 2008 11:53:30 -0400 Received: from relay1.sgi.com ([192.48.171.29]:54663 "EHLO relay.sgi.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1759330AbYCZPx3 (ORCPT ); Wed, 26 Mar 2008 11:53:29 -0400 Message-ID: <47EA7177.8010605@sgi.com> Date: Wed, 26 Mar 2008 08:53:27 -0700 From: Mike Travis User-Agent: Thunderbird 2.0.0.6 (X11/20070801) MIME-Version: 1.0 To: Ingo Molnar CC: Andrew Morton , linux-mm@kvack.org, linux-kernel@vger.kernel.org Subject: Re: [PATCH 00/12] cpumask: reduce stack pressure from local/passed cpumask variables v2 References: <20080326013811.569646000@polaris-admin.engr.sgi.com> <20080326061824.GB18301@elte.hu> In-Reply-To: <20080326061824.GB18301@elte.hu> Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Ingo Molnar wrote: > * Mike Travis wrote: > >> Modify usage of cpumask_t variables to use pointers as much as >> possible. > > hm, why is there no minimal patch against -git that does nothing but > introduces the new pointer based generic APIs (without using them) - > such as set_cpus_allowed_ptr(), etc.? Once that is upstream all the > remaining changes can trickle one arch and one subsystem at a time, and > once that's done, the old set_cpus_allowed() can be removed. This is far > more manageable than one large patch. > > and the cpumask_of_cpu() change should be Kconfig based initially - once > all arches have moved to it (or even sooner) we can remove that. > > Ingo Yes, good idea! I'll see about dividing them up. Though 99% seems to be in generic kernel code (kernel/sched.c is by far the biggest user.) There is one function pointer in a struct that would need an additional entry if we keep both interfaces. Thanks, Mike