cpuset: Make generate_sched_domains() work with partition

The generate_sched_domains() function is modified to make it work
correctly with the newly introduced subparts_cpus mask for scheduling
domains generation.
Signed-off-by: Waiman Long <longman@redhat.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Tejun Heo <tj@kernel.org>

kernel/cgroup/cpuset.c

@@ -769,13 +769,14 @@ static int generate_sched_domains(cpumask_var_t **domains,
 	int ndoms = 0;		/* number of sched domains in result */
 	int nslot;		/* next empty doms[] struct cpumask slot */
 	struct cgroup_subsys_state *pos_css;
+	bool root_load_balance = is_sched_load_balance(&top_cpuset);
 
 	doms = NULL;
 	dattr = NULL;
 	csa = NULL;
 
 	/* Special case for the 99% of systems with one, full, sched domain */
-	if (is_sched_load_balance(&top_cpuset)) {
+	if (root_load_balance && !top_cpuset.nr_subparts_cpus) {
 		ndoms = 1;
 		doms = alloc_sched_domains(ndoms);
 		if (!doms)
@@ -798,6 +799,8 @@ static int generate_sched_domains(cpumask_var_t **domains,
 	csn = 0;
 
 	rcu_read_lock();
+	if (root_load_balance)
+		csa[csn++] = &top_cpuset;
 	cpuset_for_each_descendant_pre(cp, pos_css, &top_cpuset) {
 		if (cp == &top_cpuset)
 			continue;
@@ -808,6 +811,9 @@ static int generate_sched_domains(cpumask_var_t **domains,
 		 * parent's cpus, so just skip them, and then we call
 		 * update_domain_attr_tree() to calc relax_domain_level of
 		 * the corresponding sched domain.
+		 *
+		 * If root is load-balancing, we can skip @cp if it
+		 * is a subset of the root's effective_cpus.
 		 */
 		if (!cpumask_empty(cp->cpus_allowed) &&
 		    !(is_sched_load_balance(cp) &&
@@ -815,11 +821,16 @@ static int generate_sched_domains(cpumask_var_t **domains,
 					 housekeeping_cpumask(HK_FLAG_DOMAIN))))
 			continue;
 
+		if (root_load_balance &&
+		    cpumask_subset(cp->cpus_allowed, top_cpuset.effective_cpus))
+			continue;
+
 		if (is_sched_load_balance(cp))
 			csa[csn++] = cp;
 
-		/* skip @cp's subtree */
-		pos_css = css_rightmost_descendant(pos_css);
+		/* skip @cp's subtree if not a partition root */
+		if (!is_partition_root(cp))
+			pos_css = css_rightmost_descendant(pos_css);
 	}
 	rcu_read_unlock();
 
@@ -947,7 +958,12 @@ 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.effective_cpus, cpu_active_mask))
+	if (!top_cpuset.nr_subparts_cpus &&
+	    !cpumask_equal(top_cpuset.effective_cpus, cpu_active_mask))
+		goto out;
+
+	if (top_cpuset.nr_subparts_cpus &&
+	   !cpumask_subset(top_cpuset.effective_cpus, cpu_active_mask))
 		goto out;
 
 	/* Generate domain masks and attrs */
@@ -1367,11 +1383,15 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp)
 		update_tasks_cpumask(cp);
 
 		/*
-		 * If the effective cpumask of any non-empty cpuset is changed,
-		 * we need to rebuild sched domains.
+		 * On legacy hierarchy, if the effective cpumask of any non-
+		 * empty cpuset is changed, we need to rebuild sched domains.
+		 * On default hierarchy, the cpuset needs to be a partition
+		 * root as well.
 		 */
 		if (!cpumask_empty(cp->cpus_allowed) &&
-		    is_sched_load_balance(cp))
+		    is_sched_load_balance(cp) &&
+		   (!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) ||
+		    is_partition_root(cp)))
 			need_rebuild_sched_domains = true;
 
 		rcu_read_lock();