diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index 159716fa0d3a..0036d6b4bd67 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -103,6 +103,11 @@ struct sched_domain {
 	u64 max_newidle_lb_cost;
 	unsigned long last_decay_max_lb_cost;
 
+#ifdef CONFIG_SCHED_CACHE
+	unsigned int llc_max;
+	unsigned int *llc_counts __counted_by_ptr(llc_max);
+#endif
+
 #ifdef CONFIG_SCHEDSTATS
 	/* sched_balance_rq() stats */
 	unsigned int lb_count[CPU_MAX_IDLE_TYPES];
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 1200670969bb..8954bf7900ff 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -634,6 +634,11 @@ static void destroy_sched_domain(struct sched_domain *sd)
 
 	if (sd->shared && atomic_dec_and_test(&sd->shared->ref))
 		kfree(sd->shared);
+
+#ifdef CONFIG_SCHED_CACHE
+	/* only the bottom sd has llc_counts array */
+	kfree(sd->llc_counts);
+#endif
 	kfree(sd);
 }
 
@@ -763,10 +768,18 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
 	if (sd && sd_degenerate(sd)) {
 		tmp = sd;
 		sd = sd->parent;
-		destroy_sched_domain(tmp);
+
 		if (sd) {
 			struct sched_group *sg = sd->groups;
 
+#ifdef CONFIG_SCHED_CACHE
+			/* move buffer to parent as child is being destroyed */
+			sd->llc_counts = tmp->llc_counts;
+			sd->llc_max = tmp->llc_max;
+			/* make sure destroy_sched_domain() does not free it */
+			tmp->llc_counts = NULL;
+			tmp->llc_max = 0;
+#endif
 			/*
 			 * sched groups hold the flags of the child sched
 			 * domain for convenience. Clear such flags since
@@ -778,6 +791,8 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
 
 			sd->child = NULL;
 		}
+
+		destroy_sched_domain(tmp);
 	}
 
 	sched_domain_debug(sd, cpu);
@@ -805,6 +820,49 @@ enum s_alloc {
 	sa_none,
 };
 
+#ifdef CONFIG_SCHED_CACHE
+static bool alloc_sd_llc(const struct cpumask *cpu_map,
+			 struct s_data *d)
+{
+	struct sched_domain *sd;
+	unsigned int *p;
+	int i;
+
+	for_each_cpu(i, cpu_map) {
+		sd = *per_cpu_ptr(d->sd, i);
+		if (!sd)
+			goto err;
+
+		p = kcalloc_node(max_lid + 1, sizeof(unsigned int),
+				 GFP_KERNEL, cpu_to_node(i));
+		if (!p)
+			goto err;
+
+		sd->llc_max = max_lid + 1;
+		sd->llc_counts = p;
+	}
+
+	return true;
+err:
+	for_each_cpu(i, cpu_map) {
+		sd = *per_cpu_ptr(d->sd, i);
+		if (sd) {
+			kfree(sd->llc_counts);
+			sd->llc_counts = NULL;
+			sd->llc_max = 0;
+		}
+	}
+
+	return false;
+}
+#else
+static bool alloc_sd_llc(const struct cpumask *cpu_map,
+			 struct s_data *d)
+{
+	return false;
+}
+#endif
+
 /*
  * Return the canonical balance CPU for this group, this is the first CPU
  * of this group that's also in the balance mask.
@@ -2828,6 +2886,8 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
 			init_sched_groups_capacity(i, sd);
 	}
 
+	alloc_sd_llc(cpu_map, &d);
+
 	/* Attach the domains */
 	rcu_read_lock();
 	for_each_cpu(i, cpu_map) {