[RFC,v6,2/4] scheduler: add scheduler level for clusters

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 1f212b4..9432a30 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -977,6 +977,13 @@  config SCHED_MC
 	  making when dealing with multi-core CPU chips at a cost of slightly
 	  increased overhead in some places. If unsure say N here.
 
+config SCHED_CLUSTER
+	bool "Cluster scheduler support"
+	help
+	  Cluster scheduler support improves the CPU scheduler's decision
+	  making when dealing with machines that have clusters(sharing internal
+	  bus or sharing LLC cache tag). If unsure say N here.
+
 config SCHED_SMT
 	bool "SMT scheduler support"
 	help
diff --git a/include/linux/sched/cluster.h b/include/linux/sched/cluster.h
new file mode 100644
index 0000000..ea6c475
--- /dev/null
+++ b/include/linux/sched/cluster.h
@@ -0,0 +1,19 @@ 
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_SCHED_CLUSTER_H
+#define _LINUX_SCHED_CLUSTER_H
+
+#include <linux/static_key.h>
+
+#ifdef CONFIG_SCHED_CLUSTER
+extern struct static_key_false sched_cluster_present;
+
+static __always_inline bool sched_cluster_active(void)
+{
+	return static_branch_likely(&sched_cluster_present);
+}
+#else
+static inline bool sched_cluster_active(void) { return false; }
+
+#endif
+
+#endif
diff --git a/include/linux/sched/sd_flags.h b/include/linux/sched/sd_flags.h
index 34b21e9..fc3c894 100644
--- a/include/linux/sched/sd_flags.h
+++ b/include/linux/sched/sd_flags.h
@@ -100,6 +100,15 @@ 
 SD_FLAG(SD_SHARE_CPUCAPACITY, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS)
 
 /*
+ * Domain members share CPU cluster resources (i.e. llc cache tags)
+ *
+ * SHARED_CHILD: Set from the base domain up until spanned CPUs no longer share
+ *               the cluster resouces (such as llc tags and internal bus)
+ * NEEDS_GROUPS: Caches are shared between groups.
+ */
+SD_FLAG(SD_SHARE_CLS_RESOURCES, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS)
+
+/*
  * Domain members share CPU package resources (i.e. caches)
  *
  * SHARED_CHILD: Set from the base domain up until spanned CPUs no longer share
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index 8f0f778..846fcac 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -42,6 +42,13 @@  static inline int cpu_smt_flags(void)
 }
 #endif
 
+#ifdef CONFIG_SCHED_CLUSTER
+static inline int cpu_cluster_flags(void)
+{
+	return SD_SHARE_CLS_RESOURCES | SD_SHARE_PKG_RESOURCES;
+}
+#endif
+
 #ifdef CONFIG_SCHED_MC
 static inline int cpu_core_flags(void)
 {
diff --git a/include/linux/topology.h b/include/linux/topology.h
index 80d27d7..0b3704a 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -212,6 +212,13 @@  static inline const struct cpumask *cpu_smt_mask(int cpu)
 }
 #endif
 
+#if defined(CONFIG_SCHED_CLUSTER) && !defined(cpu_cluster_mask)
+static inline const struct cpumask *cpu_cluster_mask(int cpu)
+{
+	return topology_cluster_cpumask(cpu);
+}
+#endif
+
 static inline const struct cpumask *cpu_cpu_mask(int cpu)
 {
 	return cpumask_of_node(cpu_to_node(cpu));
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 95bd6ab..30c300c 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7840,6 +7840,17 @@  int sched_cpu_activate(unsigned int cpu)
 	if (cpumask_weight(cpu_smt_mask(cpu)) == 2)
 		static_branch_inc_cpuslocked(&sched_smt_present);
 #endif
+
+#ifdef CONFIG_SCHED_CLUSTER
+	/*
+	 * When going up, increment the number of cluster cpus with
+	 * cluster present.
+	 */
+	if (cpumask_weight(cpu_cluster_mask(cpu)) > cpumask_weight(cpu_smt_mask(cpu)) &&
+	    cpumask_weight(cpu_cluster_mask(cpu)) < cpumask_weight(cpu_coregroup_mask(cpu)))
+		static_branch_inc_cpuslocked(&sched_cluster_present);
+#endif
+
 	set_cpu_active(cpu, true);
 
 	if (sched_smp_initialized) {
@@ -7916,6 +7927,15 @@  int sched_cpu_deactivate(unsigned int cpu)
 		static_branch_dec_cpuslocked(&sched_smt_present);
 #endif
 
+#ifdef CONFIG_SCHED_CLUSTER
+	/*
+	 * When going down, decrement the number of cpus with cluster present.
+	 */
+	if (cpumask_weight(cpu_cluster_mask(cpu)) > cpumask_weight(cpu_smt_mask(cpu)) &&
+	    cpumask_weight(cpu_cluster_mask(cpu)) < cpumask_weight(cpu_coregroup_mask(cpu)))
+		static_branch_dec_cpuslocked(&sched_cluster_present);
+#endif
+
 	if (!sched_smp_initialized)
 		return 0;
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 6d73bdb..a327746 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6021,6 +6021,10 @@  static inline int __select_idle_cpu(int cpu)
 	return -1;
 }
 
+#ifdef CONFIG_SCHED_CLUSTER
+DEFINE_STATIC_KEY_FALSE(sched_cluster_present);
+#endif
+
 #ifdef CONFIG_SCHED_SMT
 DEFINE_STATIC_KEY_FALSE(sched_smt_present);
 EXPORT_SYMBOL_GPL(sched_smt_present);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index cbb0b01..4e938ba 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -6,6 +6,7 @@ 
 
 #include <linux/sched/autogroup.h>
 #include <linux/sched/clock.h>
+#include <linux/sched/cluster.h>
 #include <linux/sched/coredump.h>
 #include <linux/sched/cpufreq.h>
 #include <linux/sched/cputime.h>
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index d1aec24..829ac9d 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -1392,6 +1392,7 @@  static void claim_allocations(int cpu, struct sched_domain *sd)
  */
 #define TOPOLOGY_SD_FLAGS		\
 	(SD_SHARE_CPUCAPACITY	|	\
+	 SD_SHARE_CLS_RESOURCES	|	\
 	 SD_SHARE_PKG_RESOURCES |	\
 	 SD_NUMA		|	\
 	 SD_ASYM_PACKING)
@@ -1511,6 +1512,11 @@  static void claim_allocations(int cpu, struct sched_domain *sd)
 #ifdef CONFIG_SCHED_SMT
 	{ cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) },
 #endif
+
+#ifdef CONFIG_SCHED_CLUSTER
+       { cpu_clustergroup_mask, cpu_cluster_flags, SD_INIT_NAME(CLS) },
+#endif
+
 #ifdef CONFIG_SCHED_MC
 	{ cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
 #endif