[Deepin-Kernel-SIG] [linux 6.6-y] [Upstream] [Intel] Intel-SIG: backport cluster scheduler wakeup optimization

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)
  *

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_resources(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_resources(int this_cpu, int that_cpu)
+{
+	return true;
+}
+
 #endif	/* !CONFIG_SMP */
 
 #if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)

kernel/sched/core.c

@@ -3962,6 +3962,18 @@ 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 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/fair.c

@@ -7437,14 +7437,38 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, bool
 		}
 	}
 
+	if (static_branch_unlikely(&sched_cluster_active)) {
+		struct sched_group *sg = sd->groups;
+
+		if (sg->flags & SD_CLUSTER) {
+			for_each_cpu_wrap(cpu, sched_group_span(sg), target + 1) {
+				if (!cpumask_test_cpu(cpu, cpus))
+					continue;
+
+				if (has_idle_core) {
+					i = select_idle_core(p, cpu, cpus, &idle_cpu);
+					if ((unsigned int)i < nr_cpumask_bits)
+						return i;
+				} else {
+					if (--nr <= 0)
+						return -1;
+					idle_cpu = __select_idle_cpu(cpu, p);
+					if ((unsigned int)idle_cpu < nr_cpumask_bits)
+						return idle_cpu;
+				}
+			}
+			cpumask_andnot(cpus, cpus, sched_group_span(sg));
+		}
+	}
+
 	for_each_cpu_wrap(cpu, cpus, target + 1) {
 		if (has_idle_core) {
 			i = select_idle_core(p, cpu, cpus, &idle_cpu);
 			if ((unsigned int)i < nr_cpumask_bits)
 				return i;
 
 		} else {
-			if (!--nr)
+			if (--nr <= 0)
 				return -1;
 			idle_cpu = __select_idle_cpu(cpu, p);
 			if ((unsigned int)idle_cpu < nr_cpumask_bits)
@@ -7546,7 +7570,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 	bool has_idle_core = false;
 	struct sched_domain *sd;
 	unsigned long task_util, util_min, util_max;
-	int i, recent_used_cpu;
+	int i, recent_used_cpu, prev_aff = -1;
 
 	/*
 	 * On asymmetric system, update task utilization because we will check
@@ -7573,8 +7597,14 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 	 */
 	if (prev != target && cpus_share_cache(prev, target) &&
 	    (available_idle_cpu(prev) || sched_idle_cpu(prev)) &&
-	    asym_fits_cpu(task_util, util_min, util_max, prev))
-		return prev;
+	    asym_fits_cpu(task_util, util_min, util_max, prev)) {
+
+		if (!static_branch_unlikely(&sched_cluster_active) ||
+		    cpus_share_resources(prev, target))
+			return prev;
+
+		prev_aff = prev;
+	}
 
 	/*
 	 * Allow a per-cpu kthread to stack with the wakee if the
@@ -7601,7 +7631,13 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 	    (available_idle_cpu(recent_used_cpu) || sched_idle_cpu(recent_used_cpu)) &&
 	    cpumask_test_cpu(recent_used_cpu, p->cpus_ptr) &&
 	    asym_fits_cpu(task_util, util_min, util_max, recent_used_cpu)) {
-		return recent_used_cpu;
+
+		if (!static_branch_unlikely(&sched_cluster_active) ||
+		    cpus_share_resources(recent_used_cpu, target))
+			return recent_used_cpu;
+
+	} else {
+		recent_used_cpu = -1;
 	}
 
 	/*
@@ -7642,6 +7678,17 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 	if ((unsigned)i < nr_cpumask_bits)
 		return i;
 
+	/*
+	 * For cluster machines which have lower sharing cache like L2 or
+	 * LLC Tag, we tend to find an idle CPU in the target's cluster
+	 * first. But prev_cpu or recent_used_cpu may also be a good candidate,
+	 * use them if possible when no idle CPU found in select_idle_cpu().
+	 */
+	if ((unsigned int)prev_aff < nr_cpumask_bits)
+		return prev_aff;
+	if ((unsigned int)recent_used_cpu < nr_cpumask_bits)
+		return recent_used_cpu;
+
 	return target;
 }
 

kernel/sched/sched.h

@@ -1898,11 +1898,13 @@ 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_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);
 DECLARE_PER_CPU(struct sched_domain __rcu *, sd_asym_cpucapacity);
 extern struct static_key_false sched_asym_cpucapacity;
+extern struct static_key_false sched_cluster_active;
 
 static __always_inline bool sched_asym_cpucap_active(void)
 {

kernel/sched/topology.c

@@ -666,11 +666,14 @@ 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_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);
 DEFINE_PER_CPU(struct sched_domain __rcu *, sd_asym_cpucapacity);
+
 DEFINE_STATIC_KEY_FALSE(sched_asym_cpucapacity);
+DEFINE_STATIC_KEY_FALSE(sched_cluster_active);
 
 static void update_top_cache_domain(int cpu)
 {
@@ -691,6 +694,17 @@ 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));
+
+	/*
+	 * 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);
 
@@ -1548,6 +1562,7 @@ 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)
@@ -2369,6 +2384,7 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
 	struct rq *rq = NULL;
 	int i, ret = -ENOMEM;
 	bool has_asym = false;
+	bool has_cluster = false;
 
 	if (WARN_ON(cpumask_empty(cpu_map)))
 		goto error;
@@ -2508,12 +2524,18 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
 			WRITE_ONCE(d.rd->max_cpu_capacity, capacity);
 
 		cpu_attach_domain(sd, d.rd, i);
+
+		if (lowest_flag_domain(i, SD_CLUSTER))
+			has_cluster = true;
 	}
 	rcu_read_unlock();
 
 	if (has_asym)
 		static_branch_inc_cpuslocked(&sched_asym_cpucapacity);
 
+	if (has_cluster)
+		static_branch_inc_cpuslocked(&sched_cluster_active);
+
 	if (rq && sched_debug_verbose) {
 		pr_info("root domain span: %*pbl (max cpu_capacity = %lu)\n",
 			cpumask_pr_args(cpu_map), rq->rd->max_cpu_capacity);
@@ -2613,6 +2635,9 @@ static void detach_destroy_domains(const struct cpumask *cpu_map)
 	if (rcu_access_pointer(per_cpu(sd_asym_cpucapacity, cpu)))
 		static_branch_dec_cpuslocked(&sched_asym_cpucapacity);
 
+	if (static_branch_unlikely(&sched_cluster_active))
+		static_branch_dec_cpuslocked(&sched_cluster_active);
+
 	rcu_read_lock();
 	for_each_cpu(i, cpu_map)
 		cpu_attach_domain(NULL, &def_root_domain, i);