From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753140Ab2ARTUS (ORCPT ); Wed, 18 Jan 2012 14:20:18 -0500 Received: from mail-iy0-f174.google.com ([209.85.210.174]:54028 "EHLO mail-iy0-f174.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751068Ab2ARTUQ (ORCPT ); Wed, 18 Jan 2012 14:20:16 -0500 Message-ID: <4F171B6B.2040303@gmail.com> Date: Wed, 18 Jan 2012 14:20:11 -0500 From: KOSAKI Motohiro User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10.7; rv:9.0) Gecko/20111222 Thunderbird/9.0.1 MIME-Version: 1.0 To: Venki Pallipadi CC: Andrew Morton , KOSAKI Motohiro , Mike Travis , "Srivatsa S. Bhat" , "Paul E. McKenney" , "Rafael J. Wysocki" , Paul Gortmaker , linux-kernel@vger.kernel.org Subject: Re: [PATCH] Avoid mask based num_possible_cpus and num_online_cpus References: <1326852454-26117-1-git-send-email-venki@google.com> <4F165EB4.9090309@gmail.com> In-Reply-To: Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org (1/18/12 1:52 PM), Venki Pallipadi wrote: > On Tue, Jan 17, 2012 at 9:55 PM, KOSAKI Motohiro > wrote: >> (1/17/12 9:07 PM), Venkatesh Pallipadi wrote: >>> Kernel's notion of possible cpus (from include/linux/cpumask.h) >>> * cpu_possible_mask- has bit 'cpu' set iff cpu is populatable >>> >>> * The cpu_possible_mask is fixed at boot time, as the set of CPU id's >>> * that it is possible might ever be plugged in at anytime during the >>> * life of that system boot. >>> >>> #define num_possible_cpus() cpumask_weight(cpu_possible_mask) >>> >>> and on x86 cpumask_weight() calls hweight64 and hweight64 (on older kernels >>> and systems with !X86_FEATURE_POPCNT) or a popcnt based alternative. >>> >>> i.e, We needlessly go through this mask based calculation everytime >>> num_possible_cpus() is called. >>> >>> The problem is there with cpu_online_mask() as well, which is fixed value at >>> boot time in !CONFIG_HOTPLUG_CPU case and should not change that often even >>> in HOTPLUG case. >>> >>> Though most of the callers of these two routines are init time (with few >>> exceptions of runtime calls), it is cleaner to use variables >>> and not go through this repeated mask based calculation. >>> >>> Signed-off-by: Venkatesh Pallipadi >>> --- >>> include/linux/cpumask.h | 8 ++++++-- >>> kernel/cpu.c | 9 +++++++++ >>> 2 files changed, 15 insertions(+), 2 deletions(-) >>> >>> diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h >>> index 4f7a632..2eb04dd 100644 >>> --- a/include/linux/cpumask.h >>> +++ b/include/linux/cpumask.h >>> @@ -80,9 +80,13 @@ extern const struct cpumask *const cpu_online_mask; >>> extern const struct cpumask *const cpu_present_mask; >>> extern const struct cpumask *const cpu_active_mask; >>> >>> +extern int nr_online_cpus; >>> + >>> #if NR_CPUS> 1 >>> -#define num_online_cpus() cpumask_weight(cpu_online_mask) >>> -#define num_possible_cpus() cpumask_weight(cpu_possible_mask) >>> + >>> +#define num_online_cpus() (nr_online_cpus) >>> +#define num_possible_cpus() (nr_cpu_ids) >> >> nr_cpu_ids mean maximum cpu id of cpus. if cpu id are sparse, maximum id >> doesn't match number of cpus. >> > > Yes. But will it be sparse in any arch? I saw some of the users of > num_possible_cpus() doing things like allocating a buffer for that > size and then indexing it using get_cpu(). So, I thought it would be > better to use the existing nr_cpu_ids instead of inventing another > variable. If indeed any arch is depending on this being sparse, we can > have a new variable similar to num_possible_cpus and also audit all > users of num_possible_cpus to see whether they should be using > nr_cpu_ids instead. If my remember is correct, sparc does.