1 files changed, 284 insertions, 141 deletions

diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 9748a4c8d668..cf643a5ddedd 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -3,16 +3,24 @@
  * Scheduler topology setup/handling methods
  */
 
+#include <linux/sched/isolation.h>
 #include <linux/bsearch.h>
+#include "sched.h"
 
 DEFINE_MUTEX(sched_domains_mutex);
+void sched_domains_mutex_lock(void)
+{
+	mutex_lock(&sched_domains_mutex);
+}
+void sched_domains_mutex_unlock(void)
+{
+	mutex_unlock(&sched_domains_mutex);
+}
 
 /* Protected by sched_domains_mutex: */
 static cpumask_var_t sched_domains_tmpmask;
 static cpumask_var_t sched_domains_tmpmask2;
 
-#ifdef CONFIG_SCHED_DEBUG
-
 static int __init sched_debug_setup(char *str)
 {
 	sched_debug_verbose = true;
@@ -81,7 +89,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 			break;
 		}
 
-		if (!(sd->flags & SD_OVERLAP) &&
+		if (!(sd->flags & SD_NUMA) &&
 		    cpumask_intersects(groupmask, sched_group_span(group))) {
 			printk(KERN_CONT "\n");
 			printk(KERN_ERR "ERROR: repeated CPUs\n");
@@ -94,7 +102,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 				group->sgc->id,
 				cpumask_pr_args(sched_group_span(group)));
 
-		if ((sd->flags & SD_OVERLAP) &&
+		if ((sd->flags & SD_NUMA) &&
 		    !cpumask_equal(group_balance_mask(group), sched_group_span(group))) {
 			printk(KERN_CONT " mask=%*pbl",
 				cpumask_pr_args(group_balance_mask(group)));
@@ -151,15 +159,6 @@ static void sched_domain_debug(struct sched_domain *sd, int cpu)
 			break;
 	}
 }
-#else /* !CONFIG_SCHED_DEBUG */
-
-# define sched_debug_verbose 0
-# define sched_domain_debug(sd, cpu) do { } while (0)
-static inline bool sched_debug(void)
-{
-	return false;
-}
-#endif /* CONFIG_SCHED_DEBUG */
 
 /* Generate a mask of SD flags with the SDF_NEEDS_GROUPS metaflag */
 #define SD_FLAG(name, mflags) (name * !!((mflags) & SDF_NEEDS_GROUPS)) |
@@ -215,8 +214,6 @@ static bool sched_energy_update;
 static bool sched_is_eas_possible(const struct cpumask *cpu_mask)
 {
 	bool any_asym_capacity = false;
-	struct cpufreq_policy *policy;
-	struct cpufreq_governor *gov;
 	int i;
 
 	/* EAS is enabled for asymmetric CPU capacity topologies. */
@@ -251,25 +248,12 @@ static bool sched_is_eas_possible(const struct cpumask *cpu_mask)
 		return false;
 	}
 
-	/* Do not attempt EAS if schedutil is not being used. */
-	for_each_cpu(i, cpu_mask) {
-		policy = cpufreq_cpu_get(i);
-		if (!policy) {
-			if (sched_debug()) {
-				pr_info("rd %*pbl: Checking EAS, cpufreq policy not set for CPU: %d",
-					cpumask_pr_args(cpu_mask), i);
-			}
-			return false;
-		}
-		gov = policy->governor;
-		cpufreq_cpu_put(policy);
-		if (gov != &schedutil_gov) {
-			if (sched_debug()) {
-				pr_info("rd %*pbl: Checking EAS, schedutil is mandatory\n",
-					cpumask_pr_args(cpu_mask));
-			}
-			return false;
+	if (!cpufreq_ready_for_eas(cpu_mask)) {
+		if (sched_debug()) {
+			pr_info("rd %*pbl: Checking EAS: cpufreq is not ready\n",
+				cpumask_pr_args(cpu_mask));
 		}
+		return false;
 	}
 
 	return true;
@@ -312,7 +296,7 @@ static int sched_energy_aware_handler(const struct ctl_table *table, int write,
 	return ret;
 }
 
-static struct ctl_table sched_energy_aware_sysctls[] = {
+static const struct ctl_table sched_energy_aware_sysctls[] = {
 	{
 		.procname       = "sched_energy_aware",
 		.data           = &sysctl_sched_energy_aware,
@@ -331,7 +315,7 @@ static int __init sched_energy_aware_sysctl_init(void)
 }
 
 late_initcall(sched_energy_aware_sysctl_init);
-#endif
+#endif /* CONFIG_PROC_SYSCTL */
 
 static void free_pd(struct perf_domain *pd)
 {
@@ -467,9 +451,9 @@ free:
 
 	return false;
 }
-#else
+#else /* !(CONFIG_ENERGY_MODEL && CONFIG_CPU_FREQ_GOV_SCHEDUTIL): */
 static void free_pd(struct perf_domain *pd) { }
-#endif /* CONFIG_ENERGY_MODEL && CONFIG_CPU_FREQ_GOV_SCHEDUTIL*/
+#endif /* !(CONFIG_ENERGY_MODEL && CONFIG_CPU_FREQ_GOV_SCHEDUTIL) */
 
 static void free_rootdomain(struct rcu_head *rcu)
 {
@@ -560,7 +544,7 @@ static int init_rootdomain(struct root_domain *rd)
 	rd->rto_push_work = IRQ_WORK_INIT_HARD(rto_push_irq_work_func);
 #endif
 
-	rd->visit_gen = 0;
+	rd->visit_cookie = 0;
 	init_dl_bw(&rd->dl_bw);
 	if (cpudl_init(&rd->cpudl) != 0)
 		goto free_rto_mask;
@@ -1336,6 +1320,60 @@ next:
 	update_group_capacity(sd, cpu);
 }
 
+/* Update the "asym_prefer_cpu" when arch_asym_cpu_priority() changes. */
+void sched_update_asym_prefer_cpu(int cpu, int old_prio, int new_prio)
+{
+	int asym_prefer_cpu = cpu;
+	struct sched_domain *sd;
+
+	guard(rcu)();
+
+	for_each_domain(cpu, sd) {
+		struct sched_group *sg;
+		int group_cpu;
+
+		if (!(sd->flags & SD_ASYM_PACKING))
+			continue;
+
+		/*
+		 * Groups of overlapping domain are replicated per NUMA
+		 * node and will require updating "asym_prefer_cpu" on
+		 * each local copy.
+		 *
+		 * If you are hitting this warning, consider moving
+		 * "sg->asym_prefer_cpu" to "sg->sgc->asym_prefer_cpu"
+		 * which is shared by all the overlapping groups.
+		 */
+		WARN_ON_ONCE(sd->flags & SD_NUMA);
+
+		sg = sd->groups;
+		if (cpu != sg->asym_prefer_cpu) {
+			/*
+			 * Since the parent is a superset of the current group,
+			 * if the cpu is not the "asym_prefer_cpu" at the
+			 * current level, it cannot be the preferred CPU at a
+			 * higher levels either.
+			 */
+			if (!sched_asym_prefer(cpu, sg->asym_prefer_cpu))
+				return;
+
+			WRITE_ONCE(sg->asym_prefer_cpu, cpu);
+			continue;
+		}
+
+		/* Ranking has improved; CPU is still the preferred one. */
+		if (new_prio >= old_prio)
+			continue;
+
+		for_each_cpu(group_cpu, sched_group_span(sg)) {
+			if (sched_asym_prefer(group_cpu, asym_prefer_cpu))
+				asym_prefer_cpu = group_cpu;
+		}
+
+		WRITE_ONCE(sg->asym_prefer_cpu, asym_prefer_cpu);
+	}
+}
+
 /*
  * Set of available CPUs grouped by their corresponding capacities
  * Each list entry contains a CPU mask reflecting CPUs that share the same
@@ -1552,13 +1590,19 @@ static void claim_allocations(int cpu, struct sched_domain *sd)
 #ifdef CONFIG_NUMA
 enum numa_topology_type sched_numa_topology_type;
 
+/*
+ * sched_domains_numa_distance is derived from sched_numa_node_distance
+ * and provides a simplified view of NUMA distances used specifically
+ * for building NUMA scheduling domains.
+ */
 static int			sched_domains_numa_levels;
-static int			sched_domains_curr_level;
+static int			sched_numa_node_levels;
 
 int				sched_max_numa_distance;
 static int			*sched_domains_numa_distance;
+static int			*sched_numa_node_distance;
 static struct cpumask		***sched_domains_numa_masks;
-#endif
+#endif /* CONFIG_NUMA */
 
 /*
  * SD_flags allowed in topology descriptions.
@@ -1594,14 +1638,7 @@ sd_init(struct sched_domain_topology_level *tl,
 	int sd_id, sd_weight, sd_flags = 0;
 	struct cpumask *sd_span;
 
-#ifdef CONFIG_NUMA
-	/*
-	 * Ugly hack to pass state to sd_numa_mask()...
-	 */
-	sched_domains_curr_level = tl->numa_level;
-#endif
-
-	sd_weight = cpumask_weight(tl->mask(cpu));
+	sd_weight = cpumask_weight(tl->mask(tl, cpu));
 
 	if (tl->sd_flags)
 		sd_flags = (*tl->sd_flags)();
@@ -1632,16 +1669,20 @@ sd_init(struct sched_domain_topology_level *tl,
 
 		.last_balance		= jiffies,
 		.balance_interval	= sd_weight,
+
+		/* 50% success rate */
+		.newidle_call		= 512,
+		.newidle_success	= 256,
+		.newidle_ratio		= 512,
+
 		.max_newidle_lb_cost	= 0,
 		.last_decay_max_lb_cost	= jiffies,
 		.child			= child,
-#ifdef CONFIG_SCHED_DEBUG
 		.name			= tl->name,
-#endif
 	};
 
 	sd_span = sched_domain_span(sd);
-	cpumask_and(sd_span, cpu_map, tl->mask(cpu));
+	cpumask_and(sd_span, cpu_map, tl->mask(tl, cpu));
 	sd_id = cpumask_first(sd_span);
 
 	sd->flags |= asym_cpu_capacity_classify(sd_span, cpu_map);
@@ -1676,7 +1717,7 @@ sd_init(struct sched_domain_topology_level *tl,
 				       SD_WAKE_AFFINE);
 		}
 
-#endif
+#endif /* CONFIG_NUMA */
 	} else {
 		sd->cache_nice_tries = 1;
 	}
@@ -1696,22 +1737,63 @@ sd_init(struct sched_domain_topology_level *tl,
 	return sd;
 }
 
+#ifdef CONFIG_SCHED_SMT
+int cpu_smt_flags(void)
+{
+	return SD_SHARE_CPUCAPACITY | SD_SHARE_LLC;
+}
+
+const struct cpumask *tl_smt_mask(struct sched_domain_topology_level *tl, int cpu)
+{
+	return cpu_smt_mask(cpu);
+}
+#endif
+
+#ifdef CONFIG_SCHED_CLUSTER
+int cpu_cluster_flags(void)
+{
+	return SD_CLUSTER | SD_SHARE_LLC;
+}
+
+const struct cpumask *tl_cls_mask(struct sched_domain_topology_level *tl, int cpu)
+{
+	return cpu_clustergroup_mask(cpu);
+}
+#endif
+
+#ifdef CONFIG_SCHED_MC
+int cpu_core_flags(void)
+{
+	return SD_SHARE_LLC;
+}
+
+const struct cpumask *tl_mc_mask(struct sched_domain_topology_level *tl, int cpu)
+{
+	return cpu_coregroup_mask(cpu);
+}
+#endif
+
+const struct cpumask *tl_pkg_mask(struct sched_domain_topology_level *tl, int cpu)
+{
+	return cpu_node_mask(cpu);
+}
+
 /*
  * Topology list, bottom-up.
  */
 static struct sched_domain_topology_level default_topology[] = {
 #ifdef CONFIG_SCHED_SMT
-	{ cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) },
+	SDTL_INIT(tl_smt_mask, cpu_smt_flags, SMT),
 #endif
 
 #ifdef CONFIG_SCHED_CLUSTER
-	{ cpu_clustergroup_mask, cpu_cluster_flags, SD_INIT_NAME(CLS) },
+	SDTL_INIT(tl_cls_mask, cpu_cluster_flags, CLS),
 #endif
 
 #ifdef CONFIG_SCHED_MC
-	{ cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
+	SDTL_INIT(tl_mc_mask, cpu_core_flags, MC),
 #endif
-	{ cpu_cpu_mask, SD_INIT_NAME(PKG) },
+	SDTL_INIT(tl_pkg_mask, NULL, PKG),
 	{ NULL, },
 };
 
@@ -1732,10 +1814,14 @@ void __init set_sched_topology(struct sched_domain_topology_level *tl)
 }
 
 #ifdef CONFIG_NUMA
+static int cpu_numa_flags(void)
+{
+	return SD_NUMA;
+}
 
-static const struct cpumask *sd_numa_mask(int cpu)
+static const struct cpumask *sd_numa_mask(struct sched_domain_topology_level *tl, int cpu)
 {
-	return sched_domains_numa_masks[sched_domains_curr_level][cpu_to_node(cpu)];
+	return sched_domains_numa_masks[tl->numa_level][cpu_to_node(cpu)];
 }
 
 static void sched_numa_warn(const char *str)
@@ -1772,10 +1858,10 @@ bool find_numa_distance(int distance)
 		return true;
 
 	rcu_read_lock();
-	distances = rcu_dereference(sched_domains_numa_distance);
+	distances = rcu_dereference(sched_numa_node_distance);
 	if (!distances)
 		goto unlock;
-	for (i = 0; i < sched_domains_numa_levels; i++) {
+	for (i = 0; i < sched_numa_node_levels; i++) {
 		if (distances[i] == distance) {
 			found = true;
 			break;
@@ -1851,14 +1937,34 @@ static void init_numa_topology_type(int offline_node)
 
 #define NR_DISTANCE_VALUES (1 << DISTANCE_BITS)
 
-void sched_init_numa(int offline_node)
+/*
+ * An architecture could modify its NUMA distance, to change
+ * grouping of NUMA nodes and number of NUMA levels when creating
+ * NUMA level sched domains.
+ *
+ * A NUMA level is created for each unique
+ * arch_sched_node_distance.
+ */
+static int numa_node_dist(int i, int j)
 {
-	struct sched_domain_topology_level *tl;
-	unsigned long *distance_map;
+	return node_distance(i, j);
+}
+
+int arch_sched_node_distance(int from, int to)
+			     __weak __alias(numa_node_dist);
+
+static bool modified_sched_node_distance(void)
+{
+	return numa_node_dist != arch_sched_node_distance;
+}
+
+static int sched_record_numa_dist(int offline_node, int (*n_dist)(int, int),
+				  int **dist, int *levels)
+{
+	unsigned long *distance_map __free(bitmap) = NULL;
 	int nr_levels = 0;
 	int i, j;
 	int *distances;
-	struct cpumask ***masks;
 
 	/*
 	 * O(nr_nodes^2) de-duplicating selection sort -- in order to find the
@@ -1866,17 +1972,16 @@ void sched_init_numa(int offline_node)
 	 */
 	distance_map = bitmap_alloc(NR_DISTANCE_VALUES, GFP_KERNEL);
 	if (!distance_map)
-		return;
+		return -ENOMEM;
 
 	bitmap_zero(distance_map, NR_DISTANCE_VALUES);
 	for_each_cpu_node_but(i, offline_node) {
 		for_each_cpu_node_but(j, offline_node) {
-			int distance = node_distance(i, j);
+			int distance = n_dist(i, j);
 
 			if (distance < LOCAL_DISTANCE || distance >= NR_DISTANCE_VALUES) {
 				sched_numa_warn("Invalid distance value range");
-				bitmap_free(distance_map);
-				return;
+				return -EINVAL;
 			}
 
 			bitmap_set(distance_map, distance, 1);
@@ -1889,18 +1994,46 @@ void sched_init_numa(int offline_node)
 	nr_levels = bitmap_weight(distance_map, NR_DISTANCE_VALUES);
 
 	distances = kcalloc(nr_levels, sizeof(int), GFP_KERNEL);
-	if (!distances) {
-		bitmap_free(distance_map);
-		return;
-	}
+	if (!distances)
+		return -ENOMEM;
 
 	for (i = 0, j = 0; i < nr_levels; i++, j++) {
 		j = find_next_bit(distance_map, NR_DISTANCE_VALUES, j);
 		distances[i] = j;
 	}
-	rcu_assign_pointer(sched_domains_numa_distance, distances);
+	*dist = distances;
+	*levels = nr_levels;
 
-	bitmap_free(distance_map);
+	return 0;
+}
+
+void sched_init_numa(int offline_node)
+{
+	struct sched_domain_topology_level *tl;
+	int nr_levels, nr_node_levels;
+	int i, j;
+	int *distances, *domain_distances;
+	struct cpumask ***masks;
+
+	/* Record the NUMA distances from SLIT table */
+	if (sched_record_numa_dist(offline_node, numa_node_dist, &distances,
+				   &nr_node_levels))
+		return;
+
+	/* Record modified NUMA distances for building sched domains */
+	if (modified_sched_node_distance()) {
+		if (sched_record_numa_dist(offline_node, arch_sched_node_distance,
+					   &domain_distances, &nr_levels)) {
+			kfree(distances);
+			return;
+		}
+	} else {
+		domain_distances = distances;
+		nr_levels = nr_node_levels;
+	}
+	rcu_assign_pointer(sched_numa_node_distance, distances);
+	WRITE_ONCE(sched_max_numa_distance, distances[nr_node_levels - 1]);
+	WRITE_ONCE(sched_numa_node_levels, nr_node_levels);
 
 	/*
 	 * 'nr_levels' contains the number of unique distances
@@ -1918,6 +2051,8 @@ void sched_init_numa(int offline_node)
 	 *
 	 * We reset it to 'nr_levels' at the end of this function.
 	 */
+	rcu_assign_pointer(sched_domains_numa_distance, domain_distances);
+
 	sched_domains_numa_levels = 0;
 
 	masks = kzalloc(sizeof(void *) * nr_levels, GFP_KERNEL);
@@ -1943,10 +2078,13 @@ void sched_init_numa(int offline_node)
 			masks[i][j] = mask;
 
 			for_each_cpu_node_but(k, offline_node) {
-				if (sched_debug() && (node_distance(j, k) != node_distance(k, j)))
+				if (sched_debug() &&
+				    (arch_sched_node_distance(j, k) !=
+				     arch_sched_node_distance(k, j)))
 					sched_numa_warn("Node-distance not symmetric");
 
-				if (node_distance(j, k) > sched_domains_numa_distance[i])
+				if (arch_sched_node_distance(j, k) >
+				    sched_domains_numa_distance[i])
 					continue;
 
 				cpumask_or(mask, mask, cpumask_of_node(k));
@@ -1972,30 +2110,20 @@ void sched_init_numa(int offline_node)
 	/*
 	 * Add the NUMA identity distance, aka single NODE.
 	 */
-	tl[i++] = (struct sched_domain_topology_level){
-		.mask = sd_numa_mask,
-		.numa_level = 0,
-		SD_INIT_NAME(NODE)
-	};
+	tl[i++] = SDTL_INIT(sd_numa_mask, NULL, NODE);
 
 	/*
 	 * .. and append 'j' levels of NUMA goodness.
 	 */
 	for (j = 1; j < nr_levels; i++, j++) {
-		tl[i] = (struct sched_domain_topology_level){
-			.mask = sd_numa_mask,
-			.sd_flags = cpu_numa_flags,
-			.flags = SDTL_OVERLAP,
-			.numa_level = j,
-			SD_INIT_NAME(NUMA)
-		};
+		tl[i] = SDTL_INIT(sd_numa_mask, cpu_numa_flags, NUMA);
+		tl[i].numa_level = j;
 	}
 
 	sched_domain_topology_saved = sched_domain_topology;
 	sched_domain_topology = tl;
 
 	sched_domains_numa_levels = nr_levels;
-	WRITE_ONCE(sched_max_numa_distance, sched_domains_numa_distance[nr_levels - 1]);
 
 	init_numa_topology_type(offline_node);
 }
@@ -2003,14 +2131,18 @@ void sched_init_numa(int offline_node)
 
 static void sched_reset_numa(void)
 {
-	int nr_levels, *distances;
+	int nr_levels, *distances, *dom_distances = NULL;
 	struct cpumask ***masks;
 
 	nr_levels = sched_domains_numa_levels;
+	sched_numa_node_levels = 0;
 	sched_domains_numa_levels = 0;
 	sched_max_numa_distance = 0;
 	sched_numa_topology_type = NUMA_DIRECT;
-	distances = sched_domains_numa_distance;
+	distances = sched_numa_node_distance;
+	if (sched_numa_node_distance != sched_domains_numa_distance)
+		dom_distances = sched_domains_numa_distance;
+	rcu_assign_pointer(sched_numa_node_distance, NULL);
 	rcu_assign_pointer(sched_domains_numa_distance, NULL);
 	masks = sched_domains_numa_masks;
 	rcu_assign_pointer(sched_domains_numa_masks, NULL);
@@ -2019,6 +2151,7 @@ static void sched_reset_numa(void)
 
 		synchronize_rcu();
 		kfree(distances);
+		kfree(dom_distances);
 		for (i = 0; i < nr_levels && masks; i++) {
 			if (!masks[i])
 				continue;
@@ -2065,7 +2198,8 @@ void sched_domains_numa_masks_set(unsigned int cpu)
 				continue;
 
 			/* Set ourselves in the remote node's masks */
-			if (node_distance(j, node) <= sched_domains_numa_distance[i])
+			if (arch_sched_node_distance(j, node) <=
+			    sched_domains_numa_distance[i])
 				cpumask_set_cpu(cpu, sched_domains_numa_masks[i][j]);
 		}
 	}
@@ -2103,7 +2237,7 @@ int sched_numa_find_closest(const struct cpumask *cpus, int cpu)
 	for (i = 0; i < sched_domains_numa_levels; i++) {
 		if (!masks[i][j])
 			break;
-		cpu = cpumask_any_and(cpus, masks[i][j]);
+		cpu = cpumask_any_and_distribute(cpus, masks[i][j]);
 		if (cpu < nr_cpu_ids) {
 			found = cpu;
 			break;
@@ -2174,6 +2308,8 @@ int sched_numa_find_nth_cpu(const struct cpumask *cpus, int cpu, int node)
 		goto unlock;
 
 	hop_masks = bsearch(&k, k.masks, sched_domains_numa_levels, sizeof(k.masks[0]), hop_cmp);
+	if (!hop_masks)
+		goto unlock;
 	hop = hop_masks	- k.masks;
 
 	ret = hop ?
@@ -2277,9 +2413,7 @@ static int __sdt_alloc(const struct cpumask *cpu_map)
 			if (!sgc)
 				return -ENOMEM;
 
-#ifdef CONFIG_SCHED_DEBUG
 			sgc->id = j;
-#endif
 
 			*per_cpu_ptr(sdd->sgc, j) = sgc;
 		}
@@ -2301,7 +2435,7 @@ static void __sdt_free(const struct cpumask *cpu_map)
 
 			if (sdd->sd) {
 				sd = *per_cpu_ptr(sdd->sd, j);
-				if (sd && (sd->flags & SD_OVERLAP))
+				if (sd && (sd->flags & SD_NUMA))
 					free_sched_groups(sd->groups, 0);
 				kfree(*per_cpu_ptr(sdd->sd, j));
 			}
@@ -2338,10 +2472,8 @@ static struct sched_domain *build_sched_domain(struct sched_domain_topology_leve
 		if (!cpumask_subset(sched_domain_span(child),
 				    sched_domain_span(sd))) {
 			pr_err("BUG: arch topology borken\n");
-#ifdef CONFIG_SCHED_DEBUG
 			pr_err("     the %s domain not a subset of the %s domain\n",
 					child->name, sd->name);
-#endif
 			/* Fixup, ensure @sd has at least @child CPUs. */
 			cpumask_or(sched_domain_span(sd),
 				   sched_domain_span(sd),
@@ -2356,35 +2488,58 @@ static struct sched_domain *build_sched_domain(struct sched_domain_topology_leve
 
 /*
  * Ensure topology masks are sane, i.e. there are no conflicts (overlaps) for
- * any two given CPUs at this (non-NUMA) topology level.
+ * any two given CPUs on non-NUMA topology levels.
  */
-static bool topology_span_sane(struct sched_domain_topology_level *tl,
-			      const struct cpumask *cpu_map, int cpu)
+static bool topology_span_sane(const struct cpumask *cpu_map)
 {
-	int i = cpu + 1;
+	struct sched_domain_topology_level *tl;
+	struct cpumask *covered, *id_seen;
+	int cpu;
 
-	/* NUMA levels are allowed to overlap */
-	if (tl->flags & SDTL_OVERLAP)
-		return true;
+	lockdep_assert_held(&sched_domains_mutex);
+	covered = sched_domains_tmpmask;
+	id_seen = sched_domains_tmpmask2;
+
+	for_each_sd_topology(tl) {
+		int tl_common_flags = 0;
+
+		if (tl->sd_flags)
+			tl_common_flags = (*tl->sd_flags)();
+
+		/* NUMA levels are allowed to overlap */
+		if (tl_common_flags & SD_NUMA)
+			continue;
+
+		cpumask_clear(covered);
+		cpumask_clear(id_seen);
 
-	/*
-	 * Non-NUMA levels cannot partially overlap - they must be either
-	 * completely equal or completely disjoint. Otherwise we can end up
-	 * breaking the sched_group lists - i.e. a later get_group() pass
-	 * breaks the linking done for an earlier span.
-	 */
-	for_each_cpu_from(i, cpu_map) {
 		/*
-		 * We should 'and' all those masks with 'cpu_map' to exactly
-		 * match the topology we're about to build, but that can only
-		 * remove CPUs, which only lessens our ability to detect
-		 * overlaps
+		 * Non-NUMA levels cannot partially overlap - they must be either
+		 * completely equal or completely disjoint. Otherwise we can end up
+		 * breaking the sched_group lists - i.e. a later get_group() pass
+		 * breaks the linking done for an earlier span.
 		 */
-		if (!cpumask_equal(tl->mask(cpu), tl->mask(i)) &&
-		    cpumask_intersects(tl->mask(cpu), tl->mask(i)))
-			return false;
-	}
+		for_each_cpu(cpu, cpu_map) {
+			const struct cpumask *tl_cpu_mask = tl->mask(tl, cpu);
+			int id;
+
+			/* lowest bit set in this mask is used as a unique id */
+			id = cpumask_first(tl_cpu_mask);
 
+			if (cpumask_test_cpu(id, id_seen)) {
+				/* First CPU has already been seen, ensure identical spans */
+				if (!cpumask_equal(tl->mask(tl, id), tl_cpu_mask))
+					return false;
+			} else {
+				/* First CPU hasn't been seen before, ensure it's a completely new span */
+				if (cpumask_intersects(tl_cpu_mask, covered))
+					return false;
+
+				cpumask_or(covered, covered, tl_cpu_mask);
+				cpumask_set_cpu(id, id_seen);
+			}
+		}
+	}
 	return true;
 }
 
@@ -2417,27 +2572,25 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
 		sd = NULL;
 		for_each_sd_topology(tl) {
 
-			if (WARN_ON(!topology_span_sane(tl, cpu_map, i)))
-				goto error;
-
 			sd = build_sched_domain(tl, cpu_map, attr, sd, i);
 
 			has_asym |= sd->flags & SD_ASYM_CPUCAPACITY;
 
 			if (tl == sched_domain_topology)
 				*per_cpu_ptr(d.sd, i) = sd;
-			if (tl->flags & SDTL_OVERLAP)
-				sd->flags |= SD_OVERLAP;
 			if (cpumask_equal(cpu_map, sched_domain_span(sd)))
 				break;
 		}
 	}
 
+	if (WARN_ON(!topology_span_sane(cpu_map)))
+		goto error;
+
 	/* Build the groups for the domains */
 	for_each_cpu(i, cpu_map) {
 		for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) {
 			sd->span_weight = cpumask_weight(sched_domain_span(sd));
-			if (sd->flags & SD_OVERLAP) {
+			if (sd->flags & SD_NUMA) {
 				if (build_overlap_sched_groups(sd, i))
 					goto error;
 			} else {
@@ -2684,7 +2837,7 @@ static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur,
  *
  * Call with hotplug lock and sched_domains_mutex held
  */
-void partition_sched_domains_locked(int ndoms_new, cpumask_var_t doms_new[],
+static void partition_sched_domains_locked(int ndoms_new, cpumask_var_t doms_new[],
 				    struct sched_domain_attr *dattr_new)
 {
 	bool __maybe_unused has_eas = false;
@@ -2716,19 +2869,8 @@ void partition_sched_domains_locked(int ndoms_new, cpumask_var_t doms_new[],
 	for (i = 0; i < ndoms_cur; i++) {
 		for (j = 0; j < n && !new_topology; j++) {
 			if (cpumask_equal(doms_cur[i], doms_new[j]) &&
-			    dattrs_equal(dattr_cur, i, dattr_new, j)) {
-				struct root_domain *rd;
-
-				/*
-				 * This domain won't be destroyed and as such
-				 * its dl_bw->total_bw needs to be cleared.  It
-				 * will be recomputed in function
-				 * update_tasks_root_domain().
-				 */
-				rd = cpu_rq(cpumask_any(doms_cur[i]))->rd;
-				dl_clear_root_domain(rd);
+			    dattrs_equal(dattr_cur, i, dattr_new, j))
 				goto match1;
-			}
 		}
 		/* No match - a current sched domain not in new doms_new[] */
 		detach_destroy_domains(doms_cur[i]);
@@ -2785,6 +2927,7 @@ match3:
 	ndoms_cur = ndoms_new;
 
 	update_sched_domain_debugfs();
+	dl_rebuild_rd_accounting();
 }
 
 /*
@@ -2793,7 +2936,7 @@ match3:
 void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
 			     struct sched_domain_attr *dattr_new)
 {
-	mutex_lock(&sched_domains_mutex);
+	sched_domains_mutex_lock();
 	partition_sched_domains_locked(ndoms_new, doms_new, dattr_new);
-	mutex_unlock(&sched_domains_mutex);
+	sched_domains_mutex_unlock();
 }