Merge tag 'sched-urgent-2023-09-17' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler fixes from Ingo Molnar:
 "Fix a performance regression on large SMT systems, an Intel SMT4
  balancing bug, and a topology setup bug on (Intel) hybrid processors"

* tag 'sched-urgent-2023-09-17' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/sched: Restore the SD_ASYM_PACKING flag in the DIE domain
  sched/fair: Fix SMT4 group_smt_balance handling
  sched/fair: Optimize should_we_balance() for large SMT systems

Author: torvalds

arch/x86/kernel/smpboot.c

@@ -579,7 +579,6 @@ static bool match_llc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 }
 
 
-#if defined(CONFIG_SCHED_SMT) || defined(CONFIG_SCHED_CLUSTER) || defined(CONFIG_SCHED_MC)
 static inline int x86_sched_itmt_flags(void)
 {
 	return sysctl_sched_itmt_enabled ? SD_ASYM_PACKING : 0;
@@ -603,7 +602,14 @@ static int x86_cluster_flags(void)
 	return cpu_cluster_flags() | x86_sched_itmt_flags();
 }
 #endif
-#endif
+
+static int x86_die_flags(void)
+{
+	if (cpu_feature_enabled(X86_FEATURE_HYBRID_CPU))
+	       return x86_sched_itmt_flags();
+
+	return 0;
+}
 
 /*
  * Set if a package/die has multiple NUMA nodes inside.
@@ -640,7 +646,7 @@ static void __init build_sched_topology(void)
 	 */
 	if (!x86_has_numa_in_package) {
 		x86_topology[i++] = (struct sched_domain_topology_level){
-			cpu_cpu_mask, SD_INIT_NAME(DIE)
+			cpu_cpu_mask, x86_die_flags, SD_INIT_NAME(DIE)
 		};
 	}
 

kernel/sched/fair.c

@@ -6619,6 +6619,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 /* Working cpumask for: load_balance, load_balance_newidle. */
 static DEFINE_PER_CPU(cpumask_var_t, load_balance_mask);
 static DEFINE_PER_CPU(cpumask_var_t, select_rq_mask);
+static DEFINE_PER_CPU(cpumask_var_t, should_we_balance_tmpmask);
 
 #ifdef CONFIG_NO_HZ_COMMON
 
@@ -9579,7 +9580,7 @@ static inline long sibling_imbalance(struct lb_env *env,
 	imbalance /= ncores_local + ncores_busiest;
 
 	/* Take advantage of resource in an empty sched group */
-	if (imbalance == 0 && local->sum_nr_running == 0 &&
+	if (imbalance <= 1 && local->sum_nr_running == 0 &&
 	    busiest->sum_nr_running > 1)
 		imbalance = 2;
 
@@ -9767,6 +9768,15 @@ static bool update_sd_pick_busiest(struct lb_env *env,
 		break;
 
 	case group_smt_balance:
+		/*
+		 * Check if we have spare CPUs on either SMT group to
+		 * choose has spare or fully busy handling.
+		 */
+		if (sgs->idle_cpus != 0 || busiest->idle_cpus != 0)
+			goto has_spare;
+
+		fallthrough;
+
 	case group_fully_busy:
 		/*
 		 * Select the fully busy group with highest avg_load. In
@@ -9806,6 +9816,7 @@ static bool update_sd_pick_busiest(struct lb_env *env,
 			else
 				return true;
 		}
+has_spare:
 
 		/*
 		 * Select not overloaded group with lowest number of idle cpus
@@ -10917,6 +10928,7 @@ static int active_load_balance_cpu_stop(void *data);
 
 static int should_we_balance(struct lb_env *env)
 {
+	struct cpumask *swb_cpus = this_cpu_cpumask_var_ptr(should_we_balance_tmpmask);
 	struct sched_group *sg = env->sd->groups;
 	int cpu, idle_smt = -1;
 
@@ -10940,8 +10952,9 @@ static int should_we_balance(struct lb_env *env)
 		return 1;
 	}
 
+	cpumask_copy(swb_cpus, group_balance_mask(sg));
 	/* Try to find first idle CPU */
-	for_each_cpu_and(cpu, group_balance_mask(sg), env->cpus) {
+	for_each_cpu_and(cpu, swb_cpus, env->cpus) {
 		if (!idle_cpu(cpu))
 			continue;
 
@@ -10953,6 +10966,14 @@ static int should_we_balance(struct lb_env *env)
 		if (!(env->sd->flags & SD_SHARE_CPUCAPACITY) && !is_core_idle(cpu)) {
 			if (idle_smt == -1)
 				idle_smt = cpu;
+			/*
+			 * If the core is not idle, and first SMT sibling which is
+			 * idle has been found, then its not needed to check other
+			 * SMT siblings for idleness:
+			 */
+#ifdef CONFIG_SCHED_SMT
+			cpumask_andnot(swb_cpus, swb_cpus, cpu_smt_mask(cpu));
+#endif
 			continue;
 		}
 
@@ -12918,6 +12939,8 @@ __init void init_sched_fair_class(void)
 	for_each_possible_cpu(i) {
 		zalloc_cpumask_var_node(&per_cpu(load_balance_mask, i), GFP_KERNEL, cpu_to_node(i));
 		zalloc_cpumask_var_node(&per_cpu(select_rq_mask,    i), GFP_KERNEL, cpu_to_node(i));
+		zalloc_cpumask_var_node(&per_cpu(should_we_balance_tmpmask, i),
+					GFP_KERNEL, cpu_to_node(i));
 
 #ifdef CONFIG_CFS_BANDWIDTH
 		INIT_CSD(&cpu_rq(i)->cfsb_csd, __cfsb_csd_unthrottle, cpu_rq(i));