cgroup/cpuset: Allow no-task partition to have empty cpuset.cpus.effective

Currently, a partition root cannot have empty "cpuset.cpus.effective".
As a result, a parent partition root cannot distribute out all its
CPUs to child partitions with no CPUs left. However in most cases,
there shouldn't be any tasks associated with intermediate nodes of the
default hierarchy. So the current rule is too restrictive and can waste
valuable CPU resource.

To address this issue, we are now allowing a partition to have empty
"cpuset.cpus.effective" as long as it has no task. Since cpuset is
threaded, no-internal-process rule does not apply. So it is possible
to have tasks in a partition root with child sub-partitions even though
that should be uncommon.

A parent partition with no task can now have all its CPUs distributed out
to its child partitions. The top cpuset always have some house-keeping
tasks running and so its list of effective cpu can't be empty.

Once a partition with empty "cpuset.cpus.effective" is formed, no
new task can be moved into it until "cpuset.cpus.effective" becomes
non-empty.

Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>

kernel/cgroup/cpuset.c

@@ -416,6 +416,41 @@ static inline bool is_in_v2_mode(void)
 	      (cpuset_cgrp_subsys.root->flags & CGRP_ROOT_CPUSET_V2_MODE);
 }
 
+/**
+ * partition_is_populated - check if partition has tasks
+ * @cs: partition root to be checked
+ * @excluded_child: a child cpuset to be excluded in task checking
+ * Return: true if there are tasks, false otherwise
+ *
+ * It is assumed that @cs is a valid partition root. @excluded_child should
+ * be non-NULL when this cpuset is going to become a partition itself.
+ */
+static inline bool partition_is_populated(struct cpuset *cs,
+					  struct cpuset *excluded_child)
+{
+	struct cgroup_subsys_state *css;
+	struct cpuset *child;
+
+	if (cs->css.cgroup->nr_populated_csets)
+		return true;
+	if (!excluded_child && !cs->nr_subparts_cpus)
+		return cgroup_is_populated(cs->css.cgroup);
+
+	rcu_read_lock();
+	cpuset_for_each_child(child, css, cs) {
+		if (child == excluded_child)
+			continue;
+		if (is_partition_valid(child))
+			continue;
+		if (cgroup_is_populated(child->css.cgroup)) {
+			rcu_read_unlock();
+			return true;
+		}
+	}
+	rcu_read_unlock();
+	return false;
+}
+
 /*
  * Return in pmask the portion of a task's cpusets's cpus_allowed that
  * are online and are capable of running the task.  If none are found,
@@ -1257,22 +1292,27 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd,
 		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(cs->cpus_allowed, parent->effective_cpus) ||
-	     cpumask_equal(cs->cpus_allowed, parent->effective_cpus)))
-		return -EINVAL;
-
-	/*
-	 * A cpumask update cannot make parent's effective_cpus become empty.
 	 * new_prs will only be changed for the partcmd_update command.
 	 */
 	adding = deleting = false;
 	old_prs = new_prs = cs->partition_root_state;
 	if (cmd == partcmd_enable) {
+		/*
+		 * Enabling partition root is not allowed if not all the CPUs
+		 * can be granted from parent's effective_cpus.
+		 */
+		if (!cpumask_subset(cs->cpus_allowed, parent->effective_cpus))
+			return -EINVAL;
+
+		/*
+		 * A parent can be left with no CPU as long as there is no
+		 * task directly associated with the parent partition. For
+		 * such a parent, no new task can be moved into it.
+		 */
+		if (cpumask_equal(cs->cpus_allowed, parent->effective_cpus) &&
+		    partition_is_populated(parent, cs))
+			return -EINVAL;
+
 		cpumask_copy(tmp->addmask, cs->cpus_allowed);
 		adding = true;
 	} else if (cmd == partcmd_disable) {
@@ -1294,10 +1334,12 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd,
 		adding = cpumask_andnot(tmp->addmask, tmp->addmask,
 					parent->subparts_cpus);
 		/*
-		 * Return error if the new effective_cpus could become empty.
+		 * Return error if the new effective_cpus could become empty
+		 * and there are tasks in the parent.
 		 */
 		if (adding &&
-		    cpumask_equal(parent->effective_cpus, tmp->addmask)) {
+		    cpumask_equal(parent->effective_cpus, tmp->addmask) &&
+		    partition_is_populated(parent, cs)) {
 			if (!deleting)
 				return -EINVAL;
 			/*
@@ -1322,8 +1364,8 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd,
 		 */
 		adding = cpumask_and(tmp->addmask, cs->cpus_allowed,
 				     parent->effective_cpus);
-		part_error = cpumask_equal(tmp->addmask,
+		part_error = cpumask_equal(tmp->addmask, parent->effective_cpus) &&
-					   parent->effective_cpus);
+			     partition_is_populated(parent, cs);
 	}
 
 	if (cmd == partcmd_update) {
@@ -1425,9 +1467,15 @@ 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_valid(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;
@@ -1449,6 +1497,7 @@ 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
@@ -2254,6 +2303,12 @@ static int cpuset_can_attach(struct cgroup_taskset *tset)
 	    (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed)))
 		goto out_unlock;
 
+	/*
+	 * Task cannot be moved to a cpuset with empty effective cpus.
+	 */
+	if (cpumask_empty(cs->effective_cpus))
+		goto out_unlock;
+
 	cgroup_taskset_for_each(task, css, tset) {
 		ret = task_can_attach(task, cs->effective_cpus);
 		if (ret)
@@ -3119,7 +3174,8 @@ 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_valid(cs))
 		cpumask_copy(new_cpus, parent_cs(cs)->effective_cpus);
 	if (nodes_empty(*new_mems))
 		*new_mems = parent_cs(cs)->effective_mems;
@@ -3188,10 +3244,11 @@ retry:
 
 	/*
 	 * In the unlikely event that a partition root has empty
-	 * effective_cpus or its parent becomes invalid, we have to
+	 * effective_cpus with tasks or its parent becomes invalid, we
-	 * transition it to the invalid state.
+	 * have to transition it to the invalid state.
 	 */
-	if (is_partition_valid(cs) && (cpumask_empty(&new_cpus) ||
+	if (is_partition_valid(cs) &&
+	   ((cpumask_empty(&new_cpus) && partition_is_populated(cs, NULL)) ||
 	    is_partition_invalid(parent))) {
 		if (cs->nr_subparts_cpus) {
 			spin_lock_irq(&callback_lock);
@@ -3202,13 +3259,15 @@ retry:
 		}
 
 		/*
-		 * If the effective_cpus is empty because the child
+		 * Force the partition to become invalid if either one of
-		 * partitions take away all the CPUs, we can keep
+		 * the following conditions hold:
-		 * the current partition and let the child partitions
+		 * 1) empty effective cpus but not valid empty partition.
-		 * fight for available CPUs.
+		 * 2) parent is invalid or doesn't grant any cpus to child
+		 *    partitions.
 		 */
 		if (is_partition_invalid(parent) ||
-		     cpumask_empty(&new_cpus)) {
+		    (cpumask_empty(&new_cpus) &&
+		     partition_is_populated(cs, NULL))) {
 			int old_prs;
 
 			update_parent_subparts_cpumask(cs, partcmd_disable,