Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755436AbaGIIrO (ORCPT ); Wed, 9 Jul 2014 04:47:14 -0400 Received: from szxga02-in.huawei.com ([119.145.14.65]:54679 "EHLO szxga02-in.huawei.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751635AbaGIIrK (ORCPT ); Wed, 9 Jul 2014 04:47:10 -0400 Message-ID: <53BD0187.9060309@huawei.com> Date: Wed, 9 Jul 2014 16:47:03 +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 01/12] cpuset: add cs->effective_cpus and cs->effective_mems 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 hierachy, effective_mask and configured_mask are the same, so we won't break old interfaces. This patch adds the effective masks to struct cpuset and initializes them. The effective masks of the top cpuset is the same with configured masks, and a child cpuset inherits its parent's effective masks. This won't introduce behavior change. v2: - s/real_{mems,cpus}_allowed/effective_{mems,cpus}, suggested by Tejun. - don't init effective masks in cpuset_css_online() if !cgroup_on_dfl. Signed-off-by: Li Zefan --- kernel/cpuset.c | 59 ++++++++++++++++++++++++++++++++++++++++++++++----------- 1 file changed, 48 insertions(+), 11 deletions(-) diff --git a/kernel/cpuset.c b/kernel/cpuset.c index f9d4807..ef0974c 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -76,8 +76,14 @@ struct cpuset { struct cgroup_subsys_state css; unsigned long flags; /* "unsigned long" so bitops work */ - cpumask_var_t cpus_allowed; /* CPUs allowed to tasks in cpuset */ - nodemask_t mems_allowed; /* Memory Nodes allowed to tasks */ + + /* user-configured CPUs and Memory Nodes allow to tasks */ + cpumask_var_t cpus_allowed; + nodemask_t mems_allowed; + + /* effective CPUs and Memory Nodes allow to tasks */ + cpumask_var_t effective_cpus; + nodemask_t effective_mems; /* * This is old Memory Nodes tasks took on. @@ -376,13 +382,20 @@ static struct cpuset *alloc_trial_cpuset(struct cpuset *cs) if (!trial) return NULL; - if (!alloc_cpumask_var(&trial->cpus_allowed, GFP_KERNEL)) { - kfree(trial); - return NULL; - } - cpumask_copy(trial->cpus_allowed, cs->cpus_allowed); + if (!alloc_cpumask_var(&trial->cpus_allowed, GFP_KERNEL)) + goto free_cs; + if (!alloc_cpumask_var(&trial->effective_cpus, GFP_KERNEL)) + goto free_cpus; + cpumask_copy(trial->cpus_allowed, cs->cpus_allowed); + cpumask_copy(trial->effective_cpus, cs->effective_cpus); return trial; + +free_cpus: + free_cpumask_var(trial->cpus_allowed); +free_cs: + kfree(trial); + return NULL; } /** @@ -391,6 +404,7 @@ static struct cpuset *alloc_trial_cpuset(struct cpuset *cs) */ static void free_trial_cpuset(struct cpuset *trial) { + free_cpumask_var(trial->effective_cpus); free_cpumask_var(trial->cpus_allowed); kfree(trial); } @@ -1848,18 +1862,26 @@ cpuset_css_alloc(struct cgroup_subsys_state *parent_css) cs = kzalloc(sizeof(*cs), GFP_KERNEL); if (!cs) return ERR_PTR(-ENOMEM); - if (!alloc_cpumask_var(&cs->cpus_allowed, GFP_KERNEL)) { - kfree(cs); - return ERR_PTR(-ENOMEM); - } + if (!alloc_cpumask_var(&cs->cpus_allowed, GFP_KERNEL)) + goto free_cs; + if (!alloc_cpumask_var(&cs->effective_cpus, GFP_KERNEL)) + goto free_cpus; set_bit(CS_SCHED_LOAD_BALANCE, &cs->flags); cpumask_clear(cs->cpus_allowed); nodes_clear(cs->mems_allowed); + cpumask_clear(cs->effective_cpus); + nodes_clear(cs->effective_mems); fmeter_init(&cs->fmeter); cs->relax_domain_level = -1; return &cs->css; + +free_cpus: + free_cpumask_var(cs->cpus_allowed); +free_cs: + kfree(cs); + return ERR_PTR(-ENOMEM); } static int cpuset_css_online(struct cgroup_subsys_state *css) @@ -1882,6 +1904,13 @@ static int cpuset_css_online(struct cgroup_subsys_state *css) cpuset_inc(); + mutex_lock(&callback_mutex); + if (cgroup_on_dfl(cs->css.cgroup)) { + cpumask_copy(cs->effective_cpus, parent->effective_cpus); + cs->effective_mems = parent->effective_mems; + } + mutex_unlock(&callback_mutex); + if (!test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags)) goto out_unlock; @@ -1941,6 +1970,7 @@ static void cpuset_css_free(struct cgroup_subsys_state *css) { struct cpuset *cs = css_cs(css); + free_cpumask_var(cs->effective_cpus); free_cpumask_var(cs->cpus_allowed); kfree(cs); } @@ -1969,9 +1999,13 @@ int __init cpuset_init(void) if (!alloc_cpumask_var(&top_cpuset.cpus_allowed, GFP_KERNEL)) BUG(); + if (!alloc_cpumask_var(&top_cpuset.effective_cpus, GFP_KERNEL)) + BUG(); cpumask_setall(top_cpuset.cpus_allowed); nodes_setall(top_cpuset.mems_allowed); + cpumask_setall(top_cpuset.effective_cpus); + nodes_setall(top_cpuset.effective_mems); fmeter_init(&top_cpuset.fmeter); set_bit(CS_SCHED_LOAD_BALANCE, &top_cpuset.flags); @@ -2207,6 +2241,9 @@ void __init cpuset_init_smp(void) top_cpuset.mems_allowed = node_states[N_MEMORY]; top_cpuset.old_mems_allowed = top_cpuset.mems_allowed; + cpumask_copy(top_cpuset.effective_cpus, cpu_active_mask); + top_cpuset.effective_mems = node_states[N_MEMORY]; + register_hotmemory_notifier(&cpuset_track_online_nodes_nb); } -- 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/