powerpc/smp: Create coregroup domain

Add percpu coregroup maps and masks to create coregroup domain.
If a coregroup doesn't exist, the coregroup domain will be degenerated
in favour of SMT/CACHE domain. Do note this patch is only creating stubs
for cpu_to_coregroup_id. The actual cpu_to_coregroup_id implementation
would be in a subsequent patch.

Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Reviewed-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200810071834.92514-10-srikar@linux.vnet.ibm.com

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>

arch/powerpc/kernel/smp.c

@@ -81,12 +81,22 @@ 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 {
@@ -862,11 +872,27 @@ static const struct cpumask *smallcore_smt_mask(int 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, },
 };
@@ -913,6 +939,10 @@ 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.
@@ -930,6 +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,
@@ -1234,6 +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
@@ -1294,6 +1329,20 @@ static void add_cpu_to_masks(int cpu)
 	add_cpu_to_smallcore_masks(cpu);
 	update_mask_by_l2(cpu, cpu_l2_cache_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;
 
@@ -1388,9 +1437,12 @@ static void fixup_topology(void)
 #ifdef CONFIG_SCHED_SMT
 	if (has_big_cores) {
 		pr_info("Big cores detected but using small core scheduling\n");
-		powerpc_topology[0].mask = smallcore_smt_mask;
+		powerpc_topology[smt_idx].mask = smallcore_smt_mask;
 	}
 #endif
+
+	if (!has_coregroup_support())
+		powerpc_topology[mc_idx].mask = powerpc_topology[cache_idx].mask;
 }
 
 void __init smp_cpus_done(unsigned int max_cpus)

arch/powerpc/mm/numa.c

@@ -1245,6 +1245,11 @@ int find_and_online_cpu_nid(int cpu)
 	return new_nid;
 }
 
+int cpu_to_coregroup_id(int cpu)
+{
+	return cpu_to_core_id(cpu);
+}
+
 static int topology_update_init(void)
 {
 	topology_inited = 1;