1 files changed, 52 insertions, 64 deletions

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 533547e3c90a..03be0d1330a6 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1831,6 +1831,12 @@ bool should_numa_migrate_memory(struct task_struct *p, struct folio *folio,
 	int last_cpupid, this_cpupid;
 
 	/*
+	 * Cannot migrate to memoryless nodes.
+	 */
+	if (!node_state(dst_nid, N_MEMORY))
+		return false;
+
+	/*
 	 * The pages in slow memory node should be migrated according
 	 * to hot/cold instead of private/shared.
 	 */
@@ -7289,7 +7295,7 @@ static int select_idle_core(struct task_struct *p, int core, struct cpumask *cpu
 		if (!available_idle_cpu(cpu)) {
 			idle = false;
 			if (*idle_cpu == -1) {
-				if (sched_idle_cpu(cpu) && cpumask_test_cpu(cpu, p->cpus_ptr)) {
+				if (sched_idle_cpu(cpu) && cpumask_test_cpu(cpu, cpus)) {
 					*idle_cpu = cpu;
 					break;
 				}
@@ -7297,7 +7303,7 @@ static int select_idle_core(struct task_struct *p, int core, struct cpumask *cpu
 			}
 			break;
 		}
-		if (*idle_cpu == -1 && cpumask_test_cpu(cpu, p->cpus_ptr))
+		if (*idle_cpu == -1 && cpumask_test_cpu(cpu, cpus))
 			*idle_cpu = cpu;
 	}
 
@@ -7311,13 +7317,19 @@ static int select_idle_core(struct task_struct *p, int core, struct cpumask *cpu
 /*
  * Scan the local SMT mask for idle CPUs.
  */
-static int select_idle_smt(struct task_struct *p, int target)
+static int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int target)
 {
 	int cpu;
 
 	for_each_cpu_and(cpu, cpu_smt_mask(target), p->cpus_ptr) {
 		if (cpu == target)
 			continue;
+		/*
+		 * Check if the CPU is in the LLC scheduling domain of @target.
+		 * Due to isolcpus, there is no guarantee that all the siblings are in the domain.
+		 */
+		if (!cpumask_test_cpu(cpu, sched_domain_span(sd)))
+			continue;
 		if (available_idle_cpu(cpu) || sched_idle_cpu(cpu))
 			return cpu;
 	}
@@ -7341,7 +7353,7 @@ static inline int select_idle_core(struct task_struct *p, int core, struct cpuma
 	return __select_idle_cpu(core, p);
 }
 
-static inline int select_idle_smt(struct task_struct *p, int target)
+static inline int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int target)
 {
 	return -1;
 }
@@ -7591,7 +7603,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 		has_idle_core = test_idle_cores(target);
 
 		if (!has_idle_core && cpus_share_cache(prev, target)) {
-			i = select_idle_smt(p, prev);
+			i = select_idle_smt(p, sd, prev);
 			if ((unsigned int)i < nr_cpumask_bits)
 				return i;
 		}
@@ -9237,19 +9249,17 @@ static inline bool cfs_rq_has_blocked(struct cfs_rq *cfs_rq)
 
 static inline bool others_have_blocked(struct rq *rq)
 {
-	if (READ_ONCE(rq->avg_rt.util_avg))
+	if (cpu_util_rt(rq))
 		return true;
 
-	if (READ_ONCE(rq->avg_dl.util_avg))
+	if (cpu_util_dl(rq))
 		return true;
 
 	if (thermal_load_avg(rq))
 		return true;
 
-#ifdef CONFIG_HAVE_SCHED_AVG_IRQ
-	if (READ_ONCE(rq->avg_irq.util_avg))
+	if (cpu_util_irq(rq))
 		return true;
-#endif
 
 	return false;
 }
@@ -9506,8 +9516,8 @@ static unsigned long scale_rt_capacity(int cpu)
 	 * avg_thermal.load_avg tracks thermal pressure and the weighted
 	 * average uses the actual delta max capacity(load).
 	 */
-	used = READ_ONCE(rq->avg_rt.util_avg);
-	used += READ_ONCE(rq->avg_dl.util_avg);
+	used = cpu_util_rt(rq);
+	used += cpu_util_dl(rq);
 	used += thermal_load_avg(rq);
 
 	if (unlikely(used >= max))
@@ -9740,51 +9750,49 @@ group_type group_classify(unsigned int imbalance_pct,
  */
 static bool sched_use_asym_prio(struct sched_domain *sd, int cpu)
 {
+	if (!(sd->flags & SD_ASYM_PACKING))
+		return false;
+
 	if (!sched_smt_active())
 		return true;
 
 	return sd->flags & SD_SHARE_CPUCAPACITY || is_core_idle(cpu);
 }
 
+static inline bool sched_asym(struct sched_domain *sd, int dst_cpu, int src_cpu)
+{
+	/*
+	 * First check if @dst_cpu can do asym_packing load balance. Only do it
+	 * if it has higher priority than @src_cpu.
+	 */
+	return sched_use_asym_prio(sd, dst_cpu) &&
+		sched_asym_prefer(dst_cpu, src_cpu);
+}
+
 /**
- * sched_asym - Check if the destination CPU can do asym_packing load balance
+ * sched_group_asym - Check if the destination CPU can do asym_packing balance
  * @env:	The load balancing environment
- * @sds:	Load-balancing data with statistics of the local group
  * @sgs:	Load-balancing statistics of the candidate busiest group
  * @group:	The candidate busiest group
  *
  * @env::dst_cpu can do asym_packing if it has higher priority than the
  * preferred CPU of @group.
  *
- * SMT is a special case. If we are balancing load between cores, @env::dst_cpu
- * can do asym_packing balance only if all its SMT siblings are idle. Also, it
- * can only do it if @group is an SMT group and has exactly on busy CPU. Larger
- * imbalances in the number of CPUS are dealt with in find_busiest_group().
- *
- * If we are balancing load within an SMT core, or at PKG domain level, always
- * proceed.
- *
  * Return: true if @env::dst_cpu can do with asym_packing load balance. False
  * otherwise.
  */
 static inline bool
-sched_asym(struct lb_env *env, struct sd_lb_stats *sds,  struct sg_lb_stats *sgs,
-	   struct sched_group *group)
+sched_group_asym(struct lb_env *env, struct sg_lb_stats *sgs, struct sched_group *group)
 {
-	/* Ensure that the whole local core is idle, if applicable. */
-	if (!sched_use_asym_prio(env->sd, env->dst_cpu))
-		return false;
-
 	/*
-	 * CPU priorities does not make sense for SMT cores with more than one
+	 * CPU priorities do not make sense for SMT cores with more than one
 	 * busy sibling.
 	 */
-	if (group->flags & SD_SHARE_CPUCAPACITY) {
-		if (sgs->group_weight - sgs->idle_cpus != 1)
-			return false;
-	}
+	if ((group->flags & SD_SHARE_CPUCAPACITY) &&
+	    (sgs->group_weight - sgs->idle_cpus != 1))
+		return false;
 
-	return sched_asym_prefer(env->dst_cpu, group->asym_prefer_cpu);
+	return sched_asym(env->sd, env->dst_cpu, group->asym_prefer_cpu);
 }
 
 /* One group has more than one SMT CPU while the other group does not */
@@ -9938,11 +9946,9 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 	sgs->group_weight = group->group_weight;
 
 	/* Check if dst CPU is idle and preferred to this group */
-	if (!local_group && env->sd->flags & SD_ASYM_PACKING &&
-	    env->idle != CPU_NOT_IDLE && sgs->sum_h_nr_running &&
-	    sched_asym(env, sds, sgs, group)) {
+	if (!local_group && env->idle != CPU_NOT_IDLE && sgs->sum_h_nr_running &&
+	    sched_group_asym(env, sgs, group))
 		sgs->group_asym_packing = 1;
-	}
 
 	/* Check for loaded SMT group to be balanced to dst CPU */
 	if (!local_group && smt_balance(env, sgs, group))
@@ -10006,9 +10012,7 @@ static bool update_sd_pick_busiest(struct lb_env *env,
 	switch (sgs->group_type) {
 	case group_overloaded:
 		/* Select the overloaded group with highest avg_load. */
-		if (sgs->avg_load <= busiest->avg_load)
-			return false;
-		break;
+		return sgs->avg_load > busiest->avg_load;
 
 	case group_imbalanced:
 		/*
@@ -10019,18 +10023,14 @@ static bool update_sd_pick_busiest(struct lb_env *env,
 
 	case group_asym_packing:
 		/* Prefer to move from lowest priority CPU's work */
-		if (sched_asym_prefer(sg->asym_prefer_cpu, sds->busiest->asym_prefer_cpu))
-			return false;
-		break;
+		return sched_asym_prefer(sds->busiest->asym_prefer_cpu, sg->asym_prefer_cpu);
 
 	case group_misfit_task:
 		/*
 		 * If we have more than one misfit sg go with the biggest
 		 * misfit.
 		 */
-		if (sgs->group_misfit_task_load < busiest->group_misfit_task_load)
-			return false;
-		break;
+		return sgs->group_misfit_task_load > busiest->group_misfit_task_load;
 
 	case group_smt_balance:
 		/*
@@ -10182,10 +10182,8 @@ static int idle_cpu_without(int cpu, struct task_struct *p)
 	 * be computed and tested before calling idle_cpu_without().
 	 */
 
-#ifdef CONFIG_SMP
 	if (rq->ttwu_pending)
 		return 0;
-#endif
 
 	return 1;
 }
@@ -10578,16 +10576,11 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
 
 		update_sg_lb_stats(env, sds, sg, sgs, &sg_status);
 
-		if (local_group)
-			goto next_group;
-
-
-		if (update_sd_pick_busiest(env, sds, sg, sgs)) {
+		if (!local_group && update_sd_pick_busiest(env, sds, sg, sgs)) {
 			sds->busiest = sg;
 			sds->busiest_stat = *sgs;
 		}
 
-next_group:
 		/* Now, start updating sd_lb_stats */
 		sds->total_load += sgs->group_load;
 		sds->total_capacity += sgs->group_capacity;
@@ -10691,7 +10684,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
 	 */
 	if (local->group_type == group_has_spare) {
 		if ((busiest->group_type > group_fully_busy) &&
-		    !(env->sd->flags & SD_SHARE_PKG_RESOURCES)) {
+		    !(env->sd->flags & SD_SHARE_LLC)) {
 			/*
 			 * If busiest is overloaded, try to fill spare
 			 * capacity. This might end up creating spare capacity
@@ -11038,10 +11031,7 @@ static struct rq *find_busiest_queue(struct lb_env *env,
 		 * If balancing between cores, let lower priority CPUs help
 		 * SMT cores with more than one busy sibling.
 		 */
-		if ((env->sd->flags & SD_ASYM_PACKING) &&
-		    sched_use_asym_prio(env->sd, i) &&
-		    sched_asym_prefer(i, env->dst_cpu) &&
-		    nr_running == 1)
+		if (sched_asym(env->sd, i, env->dst_cpu) && nr_running == 1)
 			continue;
 
 		switch (env->migration_type) {
@@ -11137,8 +11127,7 @@ asym_active_balance(struct lb_env *env)
 	 * the lower priority @env::dst_cpu help it. Do not follow
 	 * CPU priority.
 	 */
-	return env->idle != CPU_NOT_IDLE && (env->sd->flags & SD_ASYM_PACKING) &&
-	       sched_use_asym_prio(env->sd, env->dst_cpu) &&
+	return env->idle != CPU_NOT_IDLE && sched_use_asym_prio(env->sd, env->dst_cpu) &&
 	       (sched_asym_prefer(env->dst_cpu, env->src_cpu) ||
 		!sched_use_asym_prio(env->sd, env->src_cpu));
 }
@@ -11910,8 +11899,7 @@ static void nohz_balancer_kick(struct rq *rq)
 		 * preferred CPU must be idle.
 		 */
 		for_each_cpu_and(i, sched_domain_span(sd), nohz.idle_cpus_mask) {
-			if (sched_use_asym_prio(sd, i) &&
-			    sched_asym_prefer(i, cpu)) {
+			if (sched_asym(sd, i, cpu)) {
 				flags = NOHZ_STATS_KICK | NOHZ_BALANCE_KICK;
 				goto unlock;
 			}