[PATCH v7 1/2] sched: Add per_cpu cluster domain info and cpus_share_lowest_cache API

[Yicong Yang]

From: Barry Song <song.bao.hua@xxxxxxxxxxxxx>

Add per-cpu cluster domain info and cpus_share_lowest_cache() API.
This is the preparation for the optimization of select_idle_cpu()
on platforms with cluster scheduler level.

Tested-by: K Prateek Nayak <kprateek.nayak@xxxxxxx>
Signed-off-by: Barry Song <song.bao.hua@xxxxxxxxxxxxx>
Signed-off-by: Yicong Yang <yangyicong@xxxxxxxxxxxxx>
Reviewed-by: Gautham R. Shenoy <gautham.shenoy@xxxxxxx>
Reviewed-by: Tim Chen <tim.c.chen@xxxxxxxxxxxxxxx>
Reviewed-by: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
---
 include/linux/sched/sd_flags.h |  7 +++++++
 include/linux/sched/topology.h |  8 +++++++-
 kernel/sched/core.c            | 12 ++++++++++++
 kernel/sched/sched.h           |  2 ++
 kernel/sched/topology.c        | 15 +++++++++++++++
 5 files changed, 43 insertions(+), 1 deletion(-)

diff --git a/include/linux/sched/sd_flags.h b/include/linux/sched/sd_flags.h
index 57bde66d95f7..42ed454e8b18 100644
--- a/include/linux/sched/sd_flags.h
+++ b/include/linux/sched/sd_flags.h
@@ -109,6 +109,13 @@ SD_FLAG(SD_ASYM_CPUCAPACITY_FULL, SDF_SHARED_PARENT | SDF_NEEDS_GROUPS)
  */
 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)
  *
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index 816df6cc444e..c0d21667ddf3 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -45,7 +45,7 @@ static inline int cpu_smt_flags(void)
 #ifdef CONFIG_SCHED_CLUSTER
 static inline int cpu_cluster_flags(void)
 {
-	return SD_SHARE_PKG_RESOURCES;
+	return SD_CLUSTER | SD_SHARE_PKG_RESOURCES;
 }
 #endif
 
@@ -179,6 +179,7 @@ cpumask_var_t *alloc_sched_domains(unsigned int ndoms);
 void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms);
 
 bool cpus_share_cache(int this_cpu, int that_cpu);
+bool cpus_share_lowest_cache(int this_cpu, int that_cpu);
 
 typedef const struct cpumask *(*sched_domain_mask_f)(int cpu);
 typedef int (*sched_domain_flags_f)(void);
@@ -232,6 +233,11 @@ static inline bool cpus_share_cache(int this_cpu, int that_cpu)
 	return true;
 }
 
+static inline bool cpus_share_lowest_cache(int this_cpu, int that_cpu)
+{
+	return true;
+}
+
 #endif	/* !CONFIG_SMP */
 
 #if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index ee28253c9ac0..2d647598d26c 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3802,6 +3802,18 @@ bool cpus_share_cache(int this_cpu, int that_cpu)
 	return per_cpu(sd_llc_id, this_cpu) == per_cpu(sd_llc_id, that_cpu);
 }
 
+/*
+ * Whether CPUs are share lowest cache, which means LLC on non-cluster
+ * machines and LLC tag or L2 on machines with clusters.
+ */
+bool cpus_share_lowest_cache(int this_cpu, int that_cpu)
+{
+	if (this_cpu == that_cpu)
+		return true;
+
+	return per_cpu(sd_lowest_cache_id, this_cpu) == per_cpu(sd_lowest_cache_id, that_cpu);
+}
+
 static inline bool ttwu_queue_cond(struct task_struct *p, int cpu)
 {
 	/*
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index e26688d387ae..e9f0935605e2 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1809,7 +1809,9 @@ static inline struct sched_domain *lowest_flag_domain(int cpu, int flag)
 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_lowest_cache_id);
 DECLARE_PER_CPU(struct sched_domain_shared __rcu *, sd_llc_shared);
+DECLARE_PER_CPU(struct sched_domain __rcu *, sd_cluster);
 DECLARE_PER_CPU(struct sched_domain __rcu *, sd_numa);
 DECLARE_PER_CPU(struct sched_domain __rcu *, sd_asym_packing);
 DECLARE_PER_CPU(struct sched_domain __rcu *, sd_asym_cpucapacity);
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 8739c2a5a54e..8ab27c0d6d1f 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -664,6 +664,8 @@ static void destroy_sched_domains(struct sched_domain *sd)
 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_lowest_cache_id);
+DEFINE_PER_CPU(struct sched_domain __rcu *, sd_cluster);
 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);
@@ -689,6 +691,18 @@ static void update_top_cache_domain(int cpu)
 	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));
+	rcu_assign_pointer(per_cpu(sd_cluster, cpu), 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_lowest_cache_id, cpu) = id;
+
 	sd = lowest_flag_domain(cpu, SD_NUMA);
 	rcu_assign_pointer(per_cpu(sd_numa, cpu), sd);
 
@@ -1532,6 +1546,7 @@ static struct cpumask		***sched_domains_numa_masks;
  */
 #define TOPOLOGY_SD_FLAGS		\
 	(SD_SHARE_CPUCAPACITY	|	\
+	 SD_CLUSTER		|	\
 	 SD_SHARE_PKG_RESOURCES |	\
 	 SD_NUMA		|	\
 	 SD_ASYM_PACKING)
-- 
2.24.0