Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755180AbaGIIsB (ORCPT ); Wed, 9 Jul 2014 04:48:01 -0400 Received: from szxga01-in.huawei.com ([119.145.14.64]:21538 "EHLO szxga01-in.huawei.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754230AbaGIIr5 (ORCPT ); Wed, 9 Jul 2014 04:47:57 -0400 Message-ID: <53BD01B6.403@huawei.com> Date: Wed, 9 Jul 2014 16:47:50 +0800 From: Li Zefan User-Agent: Mozilla/5.0 (Windows NT 6.1; rv:17.0) Gecko/20130801 Thunderbird/17.0.8 MIME-Version: 1.0 To: Tejun Heo CC: LKML , cgroups Subject: [PATCH v3 05/12] cpuset: use effective cpumask to build sched domains References: <53BD0174.4060002@huawei.com> In-Reply-To: <53BD0174.4060002@huawei.com> Content-Type: text/plain; charset="GB2312" Content-Transfer-Encoding: 7bit X-Originating-IP: [10.177.18.230] X-CFilter-Loop: Reflected Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org We're going to have separate user-configured masks and effective ones. Eventually configured masks can only be changed by writing cpuset.cpus and cpuset.mems, and they won't be restricted by parent cpuset. While effective masks reflect cpu/memory hotplug and hierachical restriction, and these are the real masks that apply to the tasks in the cpuset. We calculate effective mask this way: - top cpuset's effective_mask == online_mask, otherwise - cpuset's effective_mask == configured_mask & parent effective_mask, if the result is empty, it inherits parent effective mask. Those behavior changes are for default hierarchy only. For legacy hierarchy, effective_mask and configured_mask are the same, so we won't break old interfaces. We should partition sched domains according to effective_cpus, which is the real cpulist that takes effects on tasks in the cpuset. This won't introduce behavior change. v2: - Add a comment for the call of rebuild_sched_domains(), suggested by Tejun. Signed-off-by: Li Zefan --- kernel/cpuset.c | 28 +++++++++++++++++----------- 1 file changed, 17 insertions(+), 11 deletions(-) diff --git a/kernel/cpuset.c b/kernel/cpuset.c index f834002..60577cc 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -494,11 +494,11 @@ out: #ifdef CONFIG_SMP /* * Helper routine for generate_sched_domains(). - * Do cpusets a, b have overlapping cpus_allowed masks? + * Do cpusets a, b have overlapping effective cpus_allowed masks? */ static int cpusets_overlap(struct cpuset *a, struct cpuset *b) { - return cpumask_intersects(a->cpus_allowed, b->cpus_allowed); + return cpumask_intersects(a->effective_cpus, b->effective_cpus); } static void @@ -615,7 +615,7 @@ static int generate_sched_domains(cpumask_var_t **domains, *dattr = SD_ATTR_INIT; update_domain_attr_tree(dattr, &top_cpuset); } - cpumask_copy(doms[0], top_cpuset.cpus_allowed); + cpumask_copy(doms[0], top_cpuset.effective_cpus); goto done; } @@ -719,7 +719,7 @@ restart: struct cpuset *b = csa[j]; if (apn == b->pn) { - cpumask_or(dp, dp, b->cpus_allowed); + cpumask_or(dp, dp, b->effective_cpus); if (dattr) update_domain_attr_tree(dattr + nslot, b); @@ -771,7 +771,7 @@ static void rebuild_sched_domains_locked(void) * passing doms with offlined cpu to partition_sched_domains(). * Anyways, hotplug work item will rebuild sched domains. */ - if (!cpumask_equal(top_cpuset.cpus_allowed, cpu_active_mask)) + if (!cpumask_equal(top_cpuset.effective_cpus, cpu_active_mask)) goto out; /* Generate domain masks and attrs */ @@ -870,6 +870,7 @@ static void update_cpumasks_hier(struct cpuset *cs, struct cpumask *new_cpus) { struct cpuset *cp; struct cgroup_subsys_state *pos_css; + bool need_rebuild_sched_domains = false; rcu_read_lock(); cpuset_for_each_descendant_pre(cp, pos_css, cs) { @@ -903,10 +904,21 @@ static void update_cpumasks_hier(struct cpuset *cs, struct cpumask *new_cpus) update_tasks_cpumask(cp); + /* + * If the effective cpumask of any non-empty cpuset is changed, + * we need to rebuild sched domains. + */ + if (!cpumask_empty(cp->cpus_allowed) && + is_sched_load_balance(cp)) + need_rebuild_sched_domains = true; + rcu_read_lock(); css_put(&cp->css); } rcu_read_unlock(); + + if (need_rebuild_sched_domains) + rebuild_sched_domains_locked(); } /** @@ -919,7 +931,6 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, const char *buf) { int retval; - int is_load_balanced; /* top_cpuset.cpus_allowed tracks cpu_online_mask; it's read-only */ if (cs == &top_cpuset) @@ -950,17 +961,12 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, if (retval < 0) return retval; - is_load_balanced = is_sched_load_balance(trialcs); - mutex_lock(&callback_mutex); cpumask_copy(cs->cpus_allowed, trialcs->cpus_allowed); mutex_unlock(&callback_mutex); /* use trialcs->cpus_allowed as a temp variable */ update_cpumasks_hier(cs, trialcs->cpus_allowed); - - if (is_load_balanced) - rebuild_sched_domains_locked(); return 0; } -- 1.8.0.2 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/