From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753745Ab1HQTuc (ORCPT ); Wed, 17 Aug 2011 15:50:32 -0400 Received: from mx1.redhat.com ([209.132.183.28]:59796 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751200Ab1HQTub (ORCPT ); Wed, 17 Aug 2011 15:50:31 -0400 Date: Wed, 17 Aug 2011 21:49:27 +0200 From: Johannes Weiner To: KAMEZAWA Hiroyuki Cc: Michal Hocko , linux-mm@kvack.org, Balbir Singh , Andrew Morton , linux-kernel@vger.kernel.org Subject: [patch] memcg: pin execution to current cpu while draining stock Message-ID: <20110817194927.GA10982@redhat.com> References: <2f17df54db6661c39a05669d08a9e6257435b898.1311338634.git.mhocko@suse.cz> <20110725101657.21f85bf0.kamezawa.hiroyu@jp.fujitsu.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20110725101657.21f85bf0.kamezawa.hiroyu@jp.fujitsu.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Commit d1a05b6 'memcg: do not try to drain per-cpu caches without pages' added a drain_local_stock() call to a preemptible section. The draining task looks up the cpu-local stock twice to set the draining-flag, then to drain the stock and clear the flag again. If the task is migrated to a different CPU in between, noone will clear the flag on the first stock and it will be forever undrainable. Its charge can not be recovered and the cgroup can not be deleted anymore. Properly pin the task to the executing CPU while draining stocks. Signed-off-by: Johannes Weiner Cc: KAMEZAWA Hiroyuki --- mm/memcontrol.c | 9 ++------- 1 files changed, 2 insertions(+), 7 deletions(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 697a1d5..e9b1206 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2085,13 +2085,7 @@ static void drain_all_stock(struct mem_cgroup *root_mem, bool sync) /* Notify other cpus that system-wide "drain" is running */ get_online_cpus(); - /* - * Get a hint for avoiding draining charges on the current cpu, - * which must be exhausted by our charging. It is not required that - * this be a precise check, so we use raw_smp_processor_id() instead of - * getcpu()/putcpu(). - */ - curcpu = raw_smp_processor_id(); + curcpu = get_cpu(); for_each_online_cpu(cpu) { struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu); struct mem_cgroup *mem; @@ -2108,6 +2102,7 @@ static void drain_all_stock(struct mem_cgroup *root_mem, bool sync) schedule_work_on(cpu, &stock->work); } } + put_cpu(); if (!sync) goto out; -- 1.7.6