From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932420Ab2AIQrj (ORCPT ); Mon, 9 Jan 2012 11:47:39 -0500 Received: from mail-ee0-f46.google.com ([74.125.83.46]:57825 "EHLO mail-ee0-f46.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932234Ab2AIQrh convert rfc822-to-8bit (ORCPT ); Mon, 9 Jan 2012 11:47:37 -0500 Content-Type: text/plain; charset=utf-8; format=flowed; delsp=yes To: "Gilad Ben-Yossef" , "Christoph Lameter" Cc: linux-kernel@vger.kernel.org, "Chris Metcalf" , "Peter Zijlstra" , "Frederic Weisbecker" , "Russell King" , linux-mm@kvack.org, "Pekka Enberg" , "Matt Mackall" , "Sasha Levin" , "Rik van Riel" , "Andi Kleen" , "Andrew Morton" , "Alexander Viro" , linux-fsdevel@vger.kernel.org, "Avi Kivity" , "Michal Nazarewicz" Subject: Re: [PATCH v6 7/8] mm: only IPI CPUs to drain local pages if they exist References: <1326040026-7285-8-git-send-email-gilad@benyossef.com> Date: Mon, 09 Jan 2012 17:47:30 +0100 MIME-Version: 1.0 Content-Transfer-Encoding: 8BIT From: "Michal Nazarewicz" Message-ID: In-Reply-To: User-Agent: Opera Mail/11.60 (Linux) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Mon, 09 Jan 2012 17:35:26 +0100, Christoph Lameter wrote: > On Sun, 8 Jan 2012, Gilad Ben-Yossef wrote: > >> @@ -67,6 +67,14 @@ DEFINE_PER_CPU(int, numa_node); >> EXPORT_PER_CPU_SYMBOL(numa_node); >> #endif >> >> +/* >> + * A global cpumask of CPUs with per-cpu pages that gets >> + * recomputed on each drain. We use a global cpumask >> + * here to avoid allocation on direct reclaim code path >> + * for CONFIG_CPUMASK_OFFSTACK=y >> + */ >> +static cpumask_var_t cpus_with_pcps; > > Move the static definition into drain_all_pages()? This is initialised in setup_per_cpu_pageset() so it needs to be file scoped. >> + >> #ifdef CONFIG_HAVE_MEMORYLESS_NODES >> /* >> * N.B., Do NOT reference the '_numa_mem_' per cpu variable directly. >> @@ -1097,7 +1105,19 @@ void drain_local_pages(void *arg) >> */ >> void drain_all_pages(void) >> { >> - on_each_cpu(drain_local_pages, NULL, 1); >> + int cpu; >> + struct per_cpu_pageset *pcp; >> + struct zone *zone; >> + >> + for_each_online_cpu(cpu) >> + for_each_populated_zone(zone) { >> + pcp = per_cpu_ptr(zone->pageset, cpu); >> + if (pcp->pcp.count) >> + cpumask_set_cpu(cpu, cpus_with_pcps); >> + else >> + cpumask_clear_cpu(cpu, cpus_with_pcps); >> + } >> + on_each_cpu_mask(cpus_with_pcps, drain_local_pages, NULL, 1); >> } >> >> #ifdef CONFIG_HIBERNATION >> @@ -3601,6 +3621,10 @@ static void setup_zone_pageset(struct zone *zone) >> void __init setup_per_cpu_pageset(void) >> { >> struct zone *zone; >> + int ret; >> + >> + ret = zalloc_cpumask_var(&cpus_with_pcps, GFP_KERNEL); >> + BUG_ON(!ret); >> >> for_each_populated_zone(zone) >> setup_zone_pageset(zone); >> > > -- > To unsubscribe, send a message with 'unsubscribe linux-mm' in > the body to majordomo@kvack.org. For more info on Linux MM, > see: http://www.linux-mm.org/ . > Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/ > Don't email: email@kvack.org > -- Best regards, _ _ .o. | Liege of Serenely Enlightened Majesty of o' \,=./ `o ..o | Computer Science, Michał “mina86” Nazarewicz (o o) ooo +------------------ooO--(_)--Ooo--