sched: Add cpus_share_resources API

Add cpus_share_resources() API. This is the preparation for the
optimization of select_idle_cpu() on platforms with cluster scheduler
level.

On a machine with clusters cpus_share_resources() will test whether
two cpus are within the same cluster. On a non-cluster machine it
will behaves the same as cpus_share_cache(). So we use "resources"
here for cache resources.

Signed-off-by: Barry Song <[e-mail]>
Signed-off-by: Yicong Yang <[e-mail]>
Signed-off-by: Peter Zijlstra (Intel) <[e-mail]>
Reviewed-by: Gautham R. Shenoy <[e-mail]>
Reviewed-by: Tim Chen <[e-mail]>
Reviewed-by: Vincent Guittot <[e-mail]>
Tested-and-reviewed-by: Chen Yu <[e-mail]>
Tested-by: K Prateek Nayak <[e-mail]>
Link: https://lkml.kernel.org/r/[e-mail]

include/linux/sched/sd_flags.h

···
 SD_FLAG(SD_SHARE_CPUCAPACITY, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS)
 
 /*
+ * Domain members share CPU cluster (LLC tags or L2 cache)
+ *
+ * NEEDS_GROUPS: Clusters are shared between groups.
+ */
+SD_FLAG(SD_CLUSTER, 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

include/linux/sched/topology.h

···
 #ifdef CONFIG_SCHED_CLUSTER
 static inline int cpu_cluster_flags(void)
 {
-	return SD_SHARE_PKG_RESOURCES;
+	return SD_CLUSTER | SD_SHARE_PKG_RESOURCES;
 }
 #endif
 
···
 void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms);
 
 bool cpus_share_cache(int this_cpu, int that_cpu);
+bool cpus_share_resources(int this_cpu, int that_cpu);
 
 typedef const struct cpumask *(*sched_domain_mask_f)(int cpu);
 typedef int (*sched_domain_flags_f)(void);
···
 }
 
 static inline bool cpus_share_cache(int this_cpu, int that_cpu)
+{
+	return true;
+}
+
+static inline bool cpus_share_resources(int this_cpu, int that_cpu)
 {
 	return true;
 }

kernel/sched/core.c

···
 	return per_cpu(sd_llc_id, this_cpu) == per_cpu(sd_llc_id, that_cpu);
 }
 
+/*
+ * Whether CPUs are share cache resources, which means LLC on non-cluster
+ * machines and LLC tag or L2 on machines with clusters.
+ */
+bool cpus_share_resources(int this_cpu, int that_cpu)
+{
+	if (this_cpu == that_cpu)
+		return true;
+
+	return per_cpu(sd_share_id, this_cpu) == per_cpu(sd_share_id, that_cpu);
+}
+
 static inline bool ttwu_queue_cond(struct task_struct *p, int cpu)
 {
 	/*

kernel/sched/sched.h

···
 DECLARE_PER_CPU(struct sched_domain __rcu *, sd_llc);
 DECLARE_PER_CPU(int, sd_llc_size);
 DECLARE_PER_CPU(int, sd_llc_id);
+DECLARE_PER_CPU(int, sd_share_id);
 DECLARE_PER_CPU(struct sched_domain_shared __rcu *, sd_llc_shared);
 DECLARE_PER_CPU(struct sched_domain __rcu *, sd_numa);
 DECLARE_PER_CPU(struct sched_domain __rcu *, sd_asym_packing);

kernel/sched/topology.c

···
 DEFINE_PER_CPU(struct sched_domain __rcu *, sd_llc);
 DEFINE_PER_CPU(int, sd_llc_size);
 DEFINE_PER_CPU(int, sd_llc_id);
+DEFINE_PER_CPU(int, sd_share_id);
 DEFINE_PER_CPU(struct sched_domain_shared __rcu *, sd_llc_shared);
 DEFINE_PER_CPU(struct sched_domain __rcu *, sd_numa);
 DEFINE_PER_CPU(struct sched_domain __rcu *, sd_asym_packing);
···
 	per_cpu(sd_llc_size, cpu) = size;
 	per_cpu(sd_llc_id, cpu) = id;
 	rcu_assign_pointer(per_cpu(sd_llc_shared, cpu), sds);
+
+	sd = lowest_flag_domain(cpu, SD_CLUSTER);
+	if (sd)
+		id = cpumask_first(sched_domain_span(sd));
+
+	/*
+	 * This assignment should be placed after the sd_llc_id as
+	 * we want this id equals to cluster id on cluster machines
+	 * but equals to LLC id on non-Cluster machines.
+	 */
+	per_cpu(sd_share_id, cpu) = id;
 
 	sd = lowest_flag_domain(cpu, SD_NUMA);
 	rcu_assign_pointer(per_cpu(sd_numa, cpu), sd);
···
  */
 #define TOPOLOGY_SD_FLAGS		\
 	(SD_SHARE_CPUCAPACITY	|	\
+	 SD_CLUSTER		|	\
 	 SD_SHARE_PKG_RESOURCES |	\
 	 SD_NUMA		|	\
 	 SD_ASYM_PACKING)