From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-16.5 required=3.0 tests=BAYES_00,DKIMWL_WL_HIGH, DKIM_SIGNED,DKIM_VALID,DKIM_VALID_AU,HEADER_FROM_DIFFERENT_DOMAINS, INCLUDES_CR_TRAILER,INCLUDES_PATCH,MAILING_LIST_MULTI,SPF_HELO_NONE,SPF_PASS autolearn=unavailable autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 0C0A8C4320E for ; Sat, 14 Aug 2021 20:58:29 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id EAE7960EB2 for ; Sat, 14 Aug 2021 20:58:28 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S233743AbhHNU64 (ORCPT ); Sat, 14 Aug 2021 16:58:56 -0400 Received: from us-smtp-delivery-124.mimecast.com ([170.10.133.124]:39948 "EHLO us-smtp-delivery-124.mimecast.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S233431AbhHNU6s (ORCPT ); Sat, 14 Aug 2021 16:58:48 -0400 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1628974699; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:in-reply-to:in-reply-to:references:references; bh=lpu5auuJaje8CJMsJfHNRxZ5/pmu8HTHLFzgxecJ2Mw=; b=fR4eYIy5EviDuSVg/OUj7NYNbn+zmu3teO0pRd2sg+Xtz9eW6EsF4Ss6K1294zQUgN1seO wHfgMXhCdcxG7pqJ2+tcWQoUEfIP4LSOzR65Bu6Elvc1Zulwre5trA2E4WklbNV8vuC3tb TC2tLSXFfJ4/e+PeoXL7WabB0LSNCcA= Received: from mimecast-mx01.redhat.com (mimecast-mx01.redhat.com [209.132.183.4]) (Using TLS) by relay.mimecast.com with ESMTP id us-mta-518-LS5yhK_kNLWnSOHrM20c7g-1; Sat, 14 Aug 2021 16:58:16 -0400 X-MC-Unique: LS5yhK_kNLWnSOHrM20c7g-1 Received: from smtp.corp.redhat.com (int-mx01.intmail.prod.int.phx2.redhat.com [10.5.11.11]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx01.redhat.com (Postfix) with ESMTPS id A99BF801AC0; Sat, 14 Aug 2021 20:58:14 +0000 (UTC) Received: from llong.com (unknown [10.22.8.26]) by smtp.corp.redhat.com (Postfix) with ESMTP id AE41B6E0B6; Sat, 14 Aug 2021 20:58:12 +0000 (UTC) From: Waiman Long To: Tejun Heo , Zefan Li , Johannes Weiner , Jonathan Corbet , Shuah Khan Cc: cgroups@vger.kernel.org, linux-kernel@vger.kernel.org, linux-doc@vger.kernel.org, linux-kselftest@vger.kernel.org, Andrew Morton , Roman Gushchin , Phil Auld , Peter Zijlstra , Juri Lelli , Frederic Weisbecker , Marcelo Tosatti , =?UTF-8?q?Michal=20Koutn=C3=BD?= , Waiman Long Subject: [PATCH v6 4/6] cgroup/cpuset: Allow non-top parent partition to distribute out all CPUs Date: Sat, 14 Aug 2021 16:57:41 -0400 Message-Id: <20210814205743.3039-5-longman@redhat.com> In-Reply-To: <20210814205743.3039-1-longman@redhat.com> References: <20210814205743.3039-1-longman@redhat.com> X-Scanned-By: MIMEDefang 2.79 on 10.5.11.11 Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Currently, a parent partition cannot distribute all its CPUs to child partitions with no CPUs left. However in some use cases, a management application may want to create a parent partition as a management unit with no task associated with it and has all its CPUs distributed to various child partitions dynamically according to their needs. Leaving a cpu in the parent partition in such a case is now a waste. To accommodate such use cases, a parent partition can now have all its CPUs distributed to its child partitions with 0 effective cpu left as long as it is not the top cpuset and it has no task at the time the child partition is being created. A terminal partition with no child partition underlying it, however, cannot have 0 effective cpu which will make the partition invalid. Once an empty parent partition is formed, no new task can be moved into it. Signed-off-by: Waiman Long --- kernel/cgroup/cpuset.c | 96 ++++++++++++++++++++++++++++++------------ 1 file changed, 69 insertions(+), 27 deletions(-) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 0d4a2ed6fb24..02115e5c818a 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -305,6 +305,21 @@ static inline void notify_partition_change(struct cpuset *cs, WRITE_ONCE(cs->prs_err, PERR_NONE); } +static inline int cpuset_has_tasks(const struct cpuset *cs) +{ + return cs->css.cgroup->nr_populated_csets; +} + +/* + * A empty partition (one with no effective cpu) is valid if it has no + * associated task and all its cpus have been distributed out to child + * partitions. + */ +static inline bool valid_empty_partition(const struct cpuset *cs) +{ + return !cpuset_has_tasks(cs) && cs->nr_subparts_cpus; +} + static struct cpuset top_cpuset = { .flags = ((1 << CS_ONLINE) | (1 << CS_CPU_EXCLUSIVE) | (1 << CS_MEM_EXCLUSIVE)), @@ -1211,22 +1226,32 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, if ((cmd == partcmd_enable) && css_has_online_children(&cpuset->css)) return -EBUSY; - /* - * Enabling partition root is not allowed if not all the CPUs - * can be granted from parent's effective_cpus or at least one - * CPU will be left after that. - */ - if ((cmd == partcmd_enable) && - (!cpumask_subset(cpuset->cpus_allowed, parent->effective_cpus) || - cpumask_equal(cpuset->cpus_allowed, parent->effective_cpus))) - return -EINVAL; - /* * A cpumask update cannot make parent's effective_cpus become empty. */ adding = deleting = false; old_prs = new_prs = cpuset->partition_root_state; if (cmd == partcmd_enable) { + bool parent_is_top_cpuset = !parent_cs(parent); + bool no_cpu_in_parent = cpumask_equal(cpuset->cpus_allowed, + parent->effective_cpus); + /* + * Enabling partition root is not allowed if not all the CPUs + * can be granted from parent's effective_cpus. If the parent + * is the top cpuset, at least one CPU must be left after that. + */ + if (!cpumask_subset(cpuset->cpus_allowed, parent->effective_cpus) || + (parent_is_top_cpuset && no_cpu_in_parent)) + return -EINVAL; + + /* + * A non-top parent can be left with no CPU as long as there + * is no task directly associated with the parent. For such + * a parent, no new task can be moved into it. + */ + if (no_cpu_in_parent && cpuset_has_tasks(parent)) + return -EINVAL; + cpumask_copy(tmp->addmask, cpuset->cpus_allowed); adding = true; } else if (cmd == partcmd_disable) { @@ -1257,9 +1282,9 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, parent->subparts_cpus); /* * Make partition invalid if parent's effective_cpus could - * become empty. + * become empty and there are tasks in the parent. */ - if (adding && + if (adding && cpuset_has_tasks(parent) && cpumask_equal(parent->effective_cpus, tmp->addmask)) { if (!deleting) part_error = true; @@ -1294,7 +1319,9 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, parent->effective_cpus); part_error = (is_partition_root(cpuset) && !parent->nr_subparts_cpus) || - cpumask_equal(tmp->addmask, parent->effective_cpus); + (cpumask_equal(tmp->addmask, parent->effective_cpus) && + cpuset_has_tasks(parent)); + if (is_partition_root(cpuset) && part_error) WRITE_ONCE(cpuset->prs_err, PERR_NOCPUS); } @@ -1397,9 +1424,15 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp) /* * If it becomes empty, inherit the effective mask of the - * parent, which is guaranteed to have some CPUs. + * parent, which is guaranteed to have some CPUs unless + * it is a partition root that has explicitly distributed + * out all its CPUs. */ if (is_in_v2_mode() && cpumask_empty(tmp->new_cpus)) { + if (is_partition_root(cp) && + cpumask_equal(cp->cpus_allowed, cp->subparts_cpus)) + goto update_parent_subparts; + cpumask_copy(tmp->new_cpus, parent->effective_cpus); if (!cp->use_parent_ecpus) { cp->use_parent_ecpus = true; @@ -1421,6 +1454,7 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp) continue; } +update_parent_subparts: /* * update_parent_subparts_cpumask() should have been called * for cs already in update_cpumask(). We should also call @@ -1497,12 +1531,9 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp) */ cpumask_andnot(cp->effective_cpus, cp->effective_cpus, cp->subparts_cpus); - WARN_ON_ONCE(cpumask_empty(cp->effective_cpus)); } - if (new_prs != old_prs) - cp->partition_root_state = new_prs; - + cp->partition_root_state = new_prs; spin_unlock_irq(&callback_lock); notify_partition_change(cp, old_prs, new_prs); @@ -2244,6 +2275,13 @@ static int cpuset_can_attach(struct cgroup_taskset *tset) (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed))) goto out_unlock; + /* + * On default hierarchy, task cannot be moved to a cpuset with empty + * effective cpus. + */ + if (is_in_v2_mode() && cpumask_empty(cs->effective_cpus)) + goto out_unlock; + cgroup_taskset_for_each(task, css, tset) { ret = task_can_attach(task, cs->cpus_allowed); if (ret) @@ -3120,7 +3158,8 @@ hotplug_update_tasks(struct cpuset *cs, struct cpumask *new_cpus, nodemask_t *new_mems, bool cpus_updated, bool mems_updated) { - if (cpumask_empty(new_cpus)) + /* A partition root is allowed to have empty effective cpus */ + if (cpumask_empty(new_cpus) && !is_partition_root(cs)) cpumask_copy(new_cpus, parent_cs(cs)->effective_cpus); if (nodes_empty(*new_mems)) *new_mems = parent_cs(cs)->effective_mems; @@ -3189,22 +3228,25 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp) /* * In the unlikely event that a partition root has empty - * effective_cpus, we will have to force any child partitions, - * if present, to become invalid by setting nr_subparts_cpus to 0 - * without causing itself to become invalid. + * effective_cpus with tasks, we will have to force any child + * partitions, if present, to become invalid by setting + * nr_subparts_cpus to 0 without causing itself to become invalid. */ - if (is_partition_root(cs) && cs->nr_subparts_cpus && - cpumask_empty(&new_cpus)) { + if (is_partition_root(cs) && cpumask_empty(&new_cpus) && + !valid_empty_partition(cs)) { cs->nr_subparts_cpus = 0; cpumask_clear(cs->subparts_cpus); compute_effective_cpumask(&new_cpus, cs, parent); } /* - * If empty effective_cpus or zero nr_subparts_cpus or its parent - * becomes erroneous, we have to transition it to the erroneous state. + * Force the partition to become invalid if either one of + * the following conditions hold: + * 1) empty effective cpus but not valid empty partition. + * 2) parent is invalid or doesn't grant any cpus to child partitions. */ - if (is_partition_root(cs) && (cpumask_empty(&new_cpus) || + if (is_partition_root(cs) && + ((cpumask_empty(&new_cpus) && !valid_empty_partition(cs)) || (parent->partition_root_state == PRS_ERROR) || !parent->nr_subparts_cpus)) { int old_prs; -- 2.18.1 From mboxrd@z Thu Jan 1 00:00:00 1970 From: Waiman Long Subject: [PATCH v6 4/6] cgroup/cpuset: Allow non-top parent partition to distribute out all CPUs Date: Sat, 14 Aug 2021 16:57:41 -0400 Message-ID: <20210814205743.3039-5-longman@redhat.com> References: <20210814205743.3039-1-longman@redhat.com> Return-path: DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1628974697; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:in-reply-to:in-reply-to:references:references; bh=lpu5auuJaje8CJMsJfHNRxZ5/pmu8HTHLFzgxecJ2Mw=; b=E+QmmUItThe6LImS+6a0pACHGVjcLCxB7qqrL9y6c/JXy+ZKxzrlwL2Pvwv+QHRkEXxWuP P/uguOeoflhJ0TbUVJ9hZx/S+HeMWLRj7OKxlyM9m+Wv8yDqc9lVOf+He45ZTtuRa2D9K+ 3vicsEPW2iHmc6e0yDHaFYGGoh0ZcKA= In-Reply-To: <20210814205743.3039-1-longman-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org> List-ID: MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit To: Tejun Heo , Zefan Li , Johannes Weiner , Jonathan Corbet , Shuah Khan Cc: cgroups-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, linux-doc-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, linux-kselftest-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, Andrew Morton , Roman Gushchin , Phil Auld , Peter Zijlstra , Juri Lelli , Frederic Weisbecker , Marcelo Tosatti , =?UTF-8?q?Michal=20Koutn=C3=BD?= , Waiman Long Currently, a parent partition cannot distribute all its CPUs to child partitions with no CPUs left. However in some use cases, a management application may want to create a parent partition as a management unit with no task associated with it and has all its CPUs distributed to various child partitions dynamically according to their needs. Leaving a cpu in the parent partition in such a case is now a waste. To accommodate such use cases, a parent partition can now have all its CPUs distributed to its child partitions with 0 effective cpu left as long as it is not the top cpuset and it has no task at the time the child partition is being created. A terminal partition with no child partition underlying it, however, cannot have 0 effective cpu which will make the partition invalid. Once an empty parent partition is formed, no new task can be moved into it. Signed-off-by: Waiman Long --- kernel/cgroup/cpuset.c | 96 ++++++++++++++++++++++++++++++------------ 1 file changed, 69 insertions(+), 27 deletions(-) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 0d4a2ed6fb24..02115e5c818a 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -305,6 +305,21 @@ static inline void notify_partition_change(struct cpuset *cs, WRITE_ONCE(cs->prs_err, PERR_NONE); } +static inline int cpuset_has_tasks(const struct cpuset *cs) +{ + return cs->css.cgroup->nr_populated_csets; +} + +/* + * A empty partition (one with no effective cpu) is valid if it has no + * associated task and all its cpus have been distributed out to child + * partitions. + */ +static inline bool valid_empty_partition(const struct cpuset *cs) +{ + return !cpuset_has_tasks(cs) && cs->nr_subparts_cpus; +} + static struct cpuset top_cpuset = { .flags = ((1 << CS_ONLINE) | (1 << CS_CPU_EXCLUSIVE) | (1 << CS_MEM_EXCLUSIVE)), @@ -1211,22 +1226,32 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, if ((cmd == partcmd_enable) && css_has_online_children(&cpuset->css)) return -EBUSY; - /* - * Enabling partition root is not allowed if not all the CPUs - * can be granted from parent's effective_cpus or at least one - * CPU will be left after that. - */ - if ((cmd == partcmd_enable) && - (!cpumask_subset(cpuset->cpus_allowed, parent->effective_cpus) || - cpumask_equal(cpuset->cpus_allowed, parent->effective_cpus))) - return -EINVAL; - /* * A cpumask update cannot make parent's effective_cpus become empty. */ adding = deleting = false; old_prs = new_prs = cpuset->partition_root_state; if (cmd == partcmd_enable) { + bool parent_is_top_cpuset = !parent_cs(parent); + bool no_cpu_in_parent = cpumask_equal(cpuset->cpus_allowed, + parent->effective_cpus); + /* + * Enabling partition root is not allowed if not all the CPUs + * can be granted from parent's effective_cpus. If the parent + * is the top cpuset, at least one CPU must be left after that. + */ + if (!cpumask_subset(cpuset->cpus_allowed, parent->effective_cpus) || + (parent_is_top_cpuset && no_cpu_in_parent)) + return -EINVAL; + + /* + * A non-top parent can be left with no CPU as long as there + * is no task directly associated with the parent. For such + * a parent, no new task can be moved into it. + */ + if (no_cpu_in_parent && cpuset_has_tasks(parent)) + return -EINVAL; + cpumask_copy(tmp->addmask, cpuset->cpus_allowed); adding = true; } else if (cmd == partcmd_disable) { @@ -1257,9 +1282,9 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, parent->subparts_cpus); /* * Make partition invalid if parent's effective_cpus could - * become empty. + * become empty and there are tasks in the parent. */ - if (adding && + if (adding && cpuset_has_tasks(parent) && cpumask_equal(parent->effective_cpus, tmp->addmask)) { if (!deleting) part_error = true; @@ -1294,7 +1319,9 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, parent->effective_cpus); part_error = (is_partition_root(cpuset) && !parent->nr_subparts_cpus) || - cpumask_equal(tmp->addmask, parent->effective_cpus); + (cpumask_equal(tmp->addmask, parent->effective_cpus) && + cpuset_has_tasks(parent)); + if (is_partition_root(cpuset) && part_error) WRITE_ONCE(cpuset->prs_err, PERR_NOCPUS); } @@ -1397,9 +1424,15 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp) /* * If it becomes empty, inherit the effective mask of the - * parent, which is guaranteed to have some CPUs. + * parent, which is guaranteed to have some CPUs unless + * it is a partition root that has explicitly distributed + * out all its CPUs. */ if (is_in_v2_mode() && cpumask_empty(tmp->new_cpus)) { + if (is_partition_root(cp) && + cpumask_equal(cp->cpus_allowed, cp->subparts_cpus)) + goto update_parent_subparts; + cpumask_copy(tmp->new_cpus, parent->effective_cpus); if (!cp->use_parent_ecpus) { cp->use_parent_ecpus = true; @@ -1421,6 +1454,7 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp) continue; } +update_parent_subparts: /* * update_parent_subparts_cpumask() should have been called * for cs already in update_cpumask(). We should also call @@ -1497,12 +1531,9 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp) */ cpumask_andnot(cp->effective_cpus, cp->effective_cpus, cp->subparts_cpus); - WARN_ON_ONCE(cpumask_empty(cp->effective_cpus)); } - if (new_prs != old_prs) - cp->partition_root_state = new_prs; - + cp->partition_root_state = new_prs; spin_unlock_irq(&callback_lock); notify_partition_change(cp, old_prs, new_prs); @@ -2244,6 +2275,13 @@ static int cpuset_can_attach(struct cgroup_taskset *tset) (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed))) goto out_unlock; + /* + * On default hierarchy, task cannot be moved to a cpuset with empty + * effective cpus. + */ + if (is_in_v2_mode() && cpumask_empty(cs->effective_cpus)) + goto out_unlock; + cgroup_taskset_for_each(task, css, tset) { ret = task_can_attach(task, cs->cpus_allowed); if (ret) @@ -3120,7 +3158,8 @@ hotplug_update_tasks(struct cpuset *cs, struct cpumask *new_cpus, nodemask_t *new_mems, bool cpus_updated, bool mems_updated) { - if (cpumask_empty(new_cpus)) + /* A partition root is allowed to have empty effective cpus */ + if (cpumask_empty(new_cpus) && !is_partition_root(cs)) cpumask_copy(new_cpus, parent_cs(cs)->effective_cpus); if (nodes_empty(*new_mems)) *new_mems = parent_cs(cs)->effective_mems; @@ -3189,22 +3228,25 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp) /* * In the unlikely event that a partition root has empty - * effective_cpus, we will have to force any child partitions, - * if present, to become invalid by setting nr_subparts_cpus to 0 - * without causing itself to become invalid. + * effective_cpus with tasks, we will have to force any child + * partitions, if present, to become invalid by setting + * nr_subparts_cpus to 0 without causing itself to become invalid. */ - if (is_partition_root(cs) && cs->nr_subparts_cpus && - cpumask_empty(&new_cpus)) { + if (is_partition_root(cs) && cpumask_empty(&new_cpus) && + !valid_empty_partition(cs)) { cs->nr_subparts_cpus = 0; cpumask_clear(cs->subparts_cpus); compute_effective_cpumask(&new_cpus, cs, parent); } /* - * If empty effective_cpus or zero nr_subparts_cpus or its parent - * becomes erroneous, we have to transition it to the erroneous state. + * Force the partition to become invalid if either one of + * the following conditions hold: + * 1) empty effective cpus but not valid empty partition. + * 2) parent is invalid or doesn't grant any cpus to child partitions. */ - if (is_partition_root(cs) && (cpumask_empty(&new_cpus) || + if (is_partition_root(cs) && + ((cpumask_empty(&new_cpus) && !valid_empty_partition(cs)) || (parent->partition_root_state == PRS_ERROR) || !parent->nr_subparts_cpus)) { int old_prs; -- 2.18.1