diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index b727f5f7b8f9..041f0b97c45b 100644
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -28,6 +28,7 @@
 extern int boot_cpuid;
 extern int spinning_secondaries;
 extern u32 *cpu_to_phys_id;
+extern bool coregroup_enabled;
 
 extern void cpu_die(void);
 extern int cpu_to_chip_id(int cpu);
diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index f0b6300e7dd3..6609174918ab 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -88,12 +88,22 @@ static inline int cpu_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc)
 
 #if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR)
 extern int find_and_online_cpu_nid(int cpu);
+extern int cpu_to_coregroup_id(int cpu);
 #else
 static inline int find_and_online_cpu_nid(int cpu)
 {
 	return 0;
 }
 
+static inline int cpu_to_coregroup_id(int cpu)
+{
+#ifdef CONFIG_SMP
+	return cpu_to_core_id(cpu);
+#else
+	return 0;
+#endif
+}
+
 #endif /* CONFIG_NUMA && CONFIG_PPC_SPLPAR */
 
 #include <asm-generic/topology.h>
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 8261999c7d52..3d96752d6570 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -75,17 +75,28 @@ static DEFINE_PER_CPU(int, cpu_state) = { 0 };
 
 struct task_struct *secondary_current;
 bool has_big_cores;
+bool coregroup_enabled;
 
 DEFINE_PER_CPU(cpumask_var_t, cpu_sibling_map);
 DEFINE_PER_CPU(cpumask_var_t, cpu_smallcore_map);
 DEFINE_PER_CPU(cpumask_var_t, cpu_l2_cache_map);
 DEFINE_PER_CPU(cpumask_var_t, cpu_core_map);
+DEFINE_PER_CPU(cpumask_var_t, cpu_coregroup_map);
 
 EXPORT_PER_CPU_SYMBOL(cpu_sibling_map);
 EXPORT_PER_CPU_SYMBOL(cpu_l2_cache_map);
 EXPORT_PER_CPU_SYMBOL(cpu_core_map);
 EXPORT_SYMBOL_GPL(has_big_cores);
 
+enum {
+#ifdef CONFIG_SCHED_SMT
+	smt_idx,
+#endif
+	cache_idx,
+	mc_idx,
+	die_idx,
+};
+
 #define MAX_THREAD_LIST_SIZE	8
 #define THREAD_GROUP_SHARE_L1   1
 struct thread_groups {
@@ -789,10 +800,6 @@ static int init_cpu_l1_cache_map(int cpu)
 	if (err)
 		goto out;
 
-	zalloc_cpumask_var_node(&per_cpu(cpu_l1_cache_map, cpu),
-				GFP_KERNEL,
-				cpu_to_node(cpu));
-
 	cpu_group_start = get_cpu_thread_group_start(cpu, &tg);
 
 	if (unlikely(cpu_group_start == -1)) {
@@ -801,6 +808,9 @@ static int init_cpu_l1_cache_map(int cpu)
 		goto out;
 	}
 
+	zalloc_cpumask_var_node(&per_cpu(cpu_l1_cache_map, cpu),
+				GFP_KERNEL, cpu_to_node(cpu));
+
 	for (i = first_thread; i < first_thread + threads_per_core; i++) {
 		int i_group_start = get_cpu_thread_group_start(i, &tg);
 
@@ -819,6 +829,74 @@ out:
 	return err;
 }
 
+static bool shared_caches;
+
+#ifdef CONFIG_SCHED_SMT
+/* cpumask of CPUs with asymmetric SMT dependency */
+static int powerpc_smt_flags(void)
+{
+	int flags = SD_SHARE_CPUCAPACITY | SD_SHARE_PKG_RESOURCES;
+
+	if (cpu_has_feature(CPU_FTR_ASYM_SMT)) {
+		printk_once(KERN_INFO "Enabling Asymmetric SMT scheduling\n");
+		flags |= SD_ASYM_PACKING;
+	}
+	return flags;
+}
+#endif
+
+/*
+ * P9 has a slightly odd architecture where pairs of cores share an L2 cache.
+ * This topology makes it *much* cheaper to migrate tasks between adjacent cores
+ * since the migrated task remains cache hot. We want to take advantage of this
+ * at the scheduler level so an extra topology level is required.
+ */
+static int powerpc_shared_cache_flags(void)
+{
+	return SD_SHARE_PKG_RESOURCES;
+}
+
+/*
+ * We can't just pass cpu_l2_cache_mask() directly because
+ * returns a non-const pointer and the compiler barfs on that.
+ */
+static const struct cpumask *shared_cache_mask(int cpu)
+{
+	return per_cpu(cpu_l2_cache_map, cpu);
+}
+
+#ifdef CONFIG_SCHED_SMT
+static const struct cpumask *smallcore_smt_mask(int cpu)
+{
+	return cpu_smallcore_mask(cpu);
+}
+#endif
+
+static struct cpumask *cpu_coregroup_mask(int cpu)
+{
+	return per_cpu(cpu_coregroup_map, cpu);
+}
+
+static bool has_coregroup_support(void)
+{
+	return coregroup_enabled;
+}
+
+static const struct cpumask *cpu_mc_mask(int cpu)
+{
+	return cpu_coregroup_mask(cpu);
+}
+
+static struct sched_domain_topology_level powerpc_topology[] = {
+#ifdef CONFIG_SCHED_SMT
+	{ cpu_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT) },
+#endif
+	{ shared_cache_mask, powerpc_shared_cache_flags, SD_INIT_NAME(CACHE) },
+	{ cpu_mc_mask, SD_INIT_NAME(MC) },
+	{ cpu_cpu_mask, SD_INIT_NAME(DIE) },
+	{ NULL, },
+};
+
 static int init_big_cores(void)
 {
 	int cpu;
@@ -861,6 +939,11 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 					GFP_KERNEL, cpu_to_node(cpu));
 		zalloc_cpumask_var_node(&per_cpu(cpu_core_map, cpu),
 					GFP_KERNEL, cpu_to_node(cpu));
+		if (has_coregroup_support())
+			zalloc_cpumask_var_node(&per_cpu(cpu_coregroup_map, cpu),
+						GFP_KERNEL, cpu_to_node(cpu));
+
+#ifdef CONFIG_NEED_MULTIPLE_NODES
 		/*
 		 * numa_node_id() works after this.
 		 */
@@ -869,6 +952,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 			set_cpu_numa_mem(cpu,
 				local_memory_node(numa_cpu_lookup_table[cpu]));
 		}
+#endif
 	}
 
 	/* Init the cpumasks so the boot CPU is related to itself */
@@ -876,6 +960,9 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 	cpumask_set_cpu(boot_cpuid, cpu_l2_cache_mask(boot_cpuid));
 	cpumask_set_cpu(boot_cpuid, cpu_core_mask(boot_cpuid));
 
+	if (has_coregroup_support())
+		cpumask_set_cpu(boot_cpuid, cpu_coregroup_mask(boot_cpuid));
+
 	init_big_cores();
 	if (has_big_cores) {
 		cpumask_set_cpu(boot_cpuid,
@@ -1132,9 +1219,23 @@ static bool update_mask_by_l2(int cpu, struct cpumask *(*mask_fn)(int))
 	int i;
 
 	l2_cache = cpu_to_l2cache(cpu);
-	if (!l2_cache)
-		return false;
+	if (!l2_cache) {
+		struct cpumask *(*sibling_mask)(int) = cpu_sibling_mask;
 
+		/*
+		 * If no l2cache for this CPU, assume all siblings to share
+		 * cache with this CPU.
+		 */
+		if (has_big_cores)
+			sibling_mask = cpu_smallcore_mask;
+
+		for_each_cpu(i, sibling_mask(cpu))
+			set_cpus_related(cpu, i, cpu_l2_cache_mask);
+
+		return false;
+	}
+
+	cpumask_set_cpu(cpu, mask_fn(cpu));
 	for_each_cpu(i, cpu_online_mask) {
 		/*
 		 * when updating the marks the current CPU has not been marked
@@ -1166,6 +1267,8 @@ static void remove_cpu_from_masks(int cpu)
 		set_cpus_unrelated(cpu, i, cpu_sibling_mask);
 		if (has_big_cores)
 			set_cpus_unrelated(cpu, i, cpu_smallcore_mask);
+		if (has_coregroup_support())
+			set_cpus_unrelated(cpu, i, cpu_coregroup_mask);
 	}
 }
 #endif
@@ -1217,42 +1320,54 @@ static void add_cpu_to_masks(int cpu)
 	 * add it to it's own thread sibling mask.
 	 */
 	cpumask_set_cpu(cpu, cpu_sibling_mask(cpu));
+	cpumask_set_cpu(cpu, cpu_core_mask(cpu));
 
 	for (i = first_thread; i < first_thread + threads_per_core; i++)
 		if (cpu_online(i))
 			set_cpus_related(i, cpu, cpu_sibling_mask);
 
 	add_cpu_to_smallcore_masks(cpu);
-	/*
-	 * Copy the thread sibling mask into the cache sibling mask
-	 * and mark any CPUs that share an L2 with this CPU.
-	 */
-	for_each_cpu(i, cpu_sibling_mask(cpu))
-		set_cpus_related(cpu, i, cpu_l2_cache_mask);
 	update_mask_by_l2(cpu, cpu_l2_cache_mask);
 
-	/*
-	 * Copy the cache sibling mask into core sibling mask and mark
-	 * any CPUs on the same chip as this CPU.
-	 */
-	for_each_cpu(i, cpu_l2_cache_mask(cpu))
-		set_cpus_related(cpu, i, cpu_core_mask);
+	if (has_coregroup_support()) {
+		int coregroup_id = cpu_to_coregroup_id(cpu);
+
+		cpumask_set_cpu(cpu, cpu_coregroup_mask(cpu));
+		for_each_cpu_and(i, cpu_online_mask, cpu_cpu_mask(cpu)) {
+			int fcpu = cpu_first_thread_sibling(i);
+
+			if (fcpu == first_thread)
+				set_cpus_related(cpu, i, cpu_coregroup_mask);
+			else if (coregroup_id == cpu_to_coregroup_id(i))
+				set_cpus_related(cpu, i, cpu_coregroup_mask);
+		}
+	}
+
+	if (pkg_id == -1) {
+		struct cpumask *(*mask)(int) = cpu_sibling_mask;
+
+		/*
+		 * Copy the sibling mask into core sibling mask and
+		 * mark any CPUs on the same chip as this CPU.
+		 */
+		if (shared_caches)
+			mask = cpu_l2_cache_mask;
+
+		for_each_cpu(i, mask(cpu))
+			set_cpus_related(cpu, i, cpu_core_mask);
 
-	if (pkg_id == -1)
 		return;
+	}
 
 	for_each_cpu(i, cpu_online_mask)
 		if (get_physical_package_id(i) == pkg_id)
 			set_cpus_related(cpu, i, cpu_core_mask);
 }
 
-static bool shared_caches;
-
 /* Activate a secondary processor. */
 void start_secondary(void *unused)
 {
 	unsigned int cpu = smp_processor_id();
-	struct cpumask *(*sibling_mask)(int) = cpu_sibling_mask;
 
 	mmgrab(&init_mm);
 	current->active_mm = &init_mm;
@@ -1278,14 +1393,20 @@ void start_secondary(void *unused)
 	/* Update topology CPU masks */
 	add_cpu_to_masks(cpu);
 
-	if (has_big_cores)
-		sibling_mask = cpu_smallcore_mask;
 	/*
 	 * Check for any shared caches. Note that this must be done on a
 	 * per-core basis because one core in the pair might be disabled.
 	 */
-	if (!cpumask_equal(cpu_l2_cache_mask(cpu), sibling_mask(cpu)))
-		shared_caches = true;
+	if (!shared_caches) {
+		struct cpumask *(*sibling_mask)(int) = cpu_sibling_mask;
+		struct cpumask *mask = cpu_l2_cache_mask(cpu);
+
+		if (has_big_cores)
+			sibling_mask = cpu_smallcore_mask;
+
+		if (cpumask_weight(mask) > cpumask_weight(sibling_mask(cpu)))
+			shared_caches = true;
+	}
 
 	set_numa_node(numa_cpu_lookup_table[cpu]);
 	set_numa_mem(local_memory_node(numa_cpu_lookup_table[cpu]));
@@ -1311,64 +1432,19 @@ int setup_profiling_timer(unsigned int multiplier)
 	return 0;
 }
 
-#ifdef CONFIG_SCHED_SMT
-/* cpumask of CPUs with asymetric SMT dependancy */
-static int powerpc_smt_flags(void)
+static void fixup_topology(void)
 {
-	int flags = SD_SHARE_CPUCAPACITY | SD_SHARE_PKG_RESOURCES;
-
-	if (cpu_has_feature(CPU_FTR_ASYM_SMT)) {
-		printk_once(KERN_INFO "Enabling Asymmetric SMT scheduling\n");
-		flags |= SD_ASYM_PACKING;
+#ifdef CONFIG_SCHED_SMT
+	if (has_big_cores) {
+		pr_info("Big cores detected but using small core scheduling\n");
+		powerpc_topology[smt_idx].mask = smallcore_smt_mask;
 	}
-	return flags;
-}
 #endif
 
-static struct sched_domain_topology_level powerpc_topology[] = {
-#ifdef CONFIG_SCHED_SMT
-	{ cpu_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT) },
-#endif
-	{ cpu_cpu_mask, SD_INIT_NAME(DIE) },
-	{ NULL, },
-};
-
-/*
- * P9 has a slightly odd architecture where pairs of cores share an L2 cache.
- * This topology makes it *much* cheaper to migrate tasks between adjacent cores
- * since the migrated task remains cache hot. We want to take advantage of this
- * at the scheduler level so an extra topology level is required.
- */
-static int powerpc_shared_cache_flags(void)
-{
-	return SD_SHARE_PKG_RESOURCES;
+	if (!has_coregroup_support())
+		powerpc_topology[mc_idx].mask = powerpc_topology[cache_idx].mask;
 }
 
-/*
- * We can't just pass cpu_l2_cache_mask() directly because
- * returns a non-const pointer and the compiler barfs on that.
- */
-static const struct cpumask *shared_cache_mask(int cpu)
-{
-	return cpu_l2_cache_mask(cpu);
-}
-
-#ifdef CONFIG_SCHED_SMT
-static const struct cpumask *smallcore_smt_mask(int cpu)
-{
-	return cpu_smallcore_mask(cpu);
-}
-#endif
-
-static struct sched_domain_topology_level power9_topology[] = {
-#ifdef CONFIG_SCHED_SMT
-	{ cpu_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT) },
-#endif
-	{ shared_cache_mask, powerpc_shared_cache_flags, SD_INIT_NAME(CACHE) },
-	{ cpu_cpu_mask, SD_INIT_NAME(DIE) },
-	{ NULL, },
-};
-
 void __init smp_cpus_done(unsigned int max_cpus)
 {
 	/*
@@ -1382,24 +1458,8 @@ void __init smp_cpus_done(unsigned int max_cpus)
 
 	dump_numa_cpu_topology();
 
-#ifdef CONFIG_SCHED_SMT
-	if (has_big_cores) {
-		pr_info("Big cores detected but using small core scheduling\n");
-		power9_topology[0].mask = smallcore_smt_mask;
-		powerpc_topology[0].mask = smallcore_smt_mask;
-	}
-#endif
-	/*
-	 * If any CPU detects that it's sharing a cache with another CPU then
-	 * use the deeper topology that is aware of this sharing.
-	 */
-	if (shared_caches) {
-		pr_info("Using shared cache scheduler topology\n");
-		set_sched_topology(power9_topology);
-	} else {
-		pr_info("Using standard scheduler topology\n");
-		set_sched_topology(powerpc_topology);
-	}
+	fixup_topology();
+	set_sched_topology(powerpc_topology);
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 481951ac3e55..b725fb66e913 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -897,7 +897,9 @@ static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn)
 static void __init find_possible_nodes(void)
 {
 	struct device_node *rtas;
-	u32 numnodes, i;
+	const __be32 *domains;
+	int prop_length, max_nodes;
+	u32 i;
 
 	if (!numa_enabled)
 		return;
@@ -906,25 +908,31 @@ static void __init find_possible_nodes(void)
 	if (!rtas)
 		return;
 
-	if (of_property_read_u32_index(rtas, "ibm,current-associativity-domains",
-				min_common_depth, &numnodes)) {
-		/*
-		 * ibm,current-associativity-domains is a fairly recent
-		 * property. If it doesn't exist, then fallback on
-		 * ibm,max-associativity-domains. Current denotes what the
-		 * platform can support compared to max which denotes what the
-		 * Hypervisor can support.
-		 */
-		if (of_property_read_u32_index(rtas, "ibm,max-associativity-domains",
-				min_common_depth, &numnodes))
+	/*
+	 * ibm,current-associativity-domains is a fairly recent property. If
+	 * it doesn't exist, then fallback on ibm,max-associativity-domains.
+	 * Current denotes what the platform can support compared to max
+	 * which denotes what the Hypervisor can support.
+	 */
+	domains = of_get_property(rtas, "ibm,current-associativity-domains",
+					&prop_length);
+	if (!domains) {
+		domains = of_get_property(rtas, "ibm,max-associativity-domains",
+					&prop_length);
+		if (!domains)
 			goto out;
 	}
 
-	for (i = 0; i < numnodes; i++) {
+	max_nodes = of_read_number(&domains[min_common_depth], 1);
+	for (i = 0; i < max_nodes; i++) {
 		if (!node_possible(i))
 			node_set(i, node_possible_map);
 	}
 
+	prop_length /= sizeof(int);
+	if (prop_length > min_common_depth + 2)
+		coregroup_enabled = 1;
+
 out:
 	of_node_put(rtas);
 }
@@ -1237,6 +1245,31 @@ int find_and_online_cpu_nid(int cpu)
 	return new_nid;
 }
 
+int cpu_to_coregroup_id(int cpu)
+{
+	__be32 associativity[VPHN_ASSOC_BUFSIZE] = {0};
+	int index;
+
+	if (cpu < 0 || cpu > nr_cpu_ids)
+		return -1;
+
+	if (!coregroup_enabled)
+		goto out;
+
+	if (!firmware_has_feature(FW_FEATURE_VPHN))
+		goto out;
+
+	if (vphn_get_associativity(cpu, associativity))
+		goto out;
+
+	index = of_read_number(associativity, 1);
+	if (index > min_common_depth + 1)
+		return of_read_number(&associativity[index - 1], 1);
+
+out:
+	return cpu_to_core_id(cpu);
+}
+
 static int topology_update_init(void)
 {
 	topology_inited = 1;