Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:
 "The main changes are:

   - Migrate CPU-intense 'misfit' tasks on asymmetric capacity systems,
     to better utilize (much) faster 'big core' CPUs. (Morten Rasmussen,
     Valentin Schneider)

   - Topology handling improvements, in particular when CPU capacity
     changes and related load-balancing fixes/improvements (Morten
     Rasmussen)

   - ... plus misc other improvements, fixes and updates"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (28 commits)
  sched/completions/Documentation: Add recommendation for dynamic and ONSTACK completions
  sched/completions/Documentation: Clean up the document some more
  sched/completions/Documentation: Fix a couple of punctuation nits
  cpu/SMT: State SMT is disabled even with nosmt and without "=force"
  sched/core: Fix comment regarding nr_iowait_cpu() and get_iowait_load()
  sched/fair: Remove setting task's se->runnable_weight during PELT update
  sched/fair: Disable LB_BIAS by default
  sched/pelt: Fix warning and clean up IRQ PELT config
  sched/topology: Make local variables static
  sched/debug: Use symbolic names for task state constants
  sched/numa: Remove unused numa_stats::nr_running field
  sched/numa: Remove unused code from update_numa_stats()
  sched/debug: Explicitly cast sched_feat() to bool
  sched/core: Disable SD_PREFER_SIBLING on asymmetric CPU capacity domains
  sched/fair: Don't move tasks to lower capacity CPUs unless necessary
  sched/fair: Set rq->rd->overload when misfit
  sched/fair: Wrap rq->rd->overload accesses with READ/WRITE_ONCE()
  sched/core: Change root_domain->overload type to int
  sched/fair: Change 'prefer_sibling' type to bool
  sched/fair: Kick nohz balance if rq->misfit_task_load
  ...

7 files changed, 261 insertions, 84 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index ad97f3ba5ec5..fe0223121883 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -135,9 +135,8 @@ static void update_rq_clock_task(struct rq *rq, s64 delta)
  * In theory, the compile should just see 0 here, and optimize out the call
  * to sched_rt_avg_update. But I don't trust it...
  */
-#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
-	s64 steal = 0, irq_delta = 0;
-#endif
+	s64 __maybe_unused steal = 0, irq_delta = 0;
+
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
 	irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time;
 
@@ -177,7 +176,7 @@ static void update_rq_clock_task(struct rq *rq, s64 delta)
 
 	rq->clock_task += delta;
 
-#ifdef HAVE_SCHED_AVG_IRQ
+#ifdef CONFIG_HAVE_SCHED_AVG_IRQ
 	if ((irq_delta + steal) && sched_feat(NONTASK_CAPACITY))
 		update_irq_load_avg(rq, irq_delta + steal);
 #endif
@@ -701,6 +700,7 @@ static void set_load_weight(struct task_struct *p, bool update_load)
 	if (idle_policy(p->policy)) {
 		load->weight = scale_load(WEIGHT_IDLEPRIO);
 		load->inv_weight = WMULT_IDLEPRIO;
+		p->se.runnable_weight = load->weight;
 		return;
 	}
 
@@ -713,6 +713,7 @@ static void set_load_weight(struct task_struct *p, bool update_load)
 	} else {
 		load->weight = scale_load(sched_prio_to_weight[prio]);
 		load->inv_weight = sched_prio_to_wmult[prio];
+		p->se.runnable_weight = load->weight;
 	}
 }
 
@@ -2915,10 +2916,10 @@ unsigned long nr_iowait(void)
 }
 
 /*
- * Consumers of these two interfaces, like for example the cpufreq menu
- * governor are using nonsensical data. Boosting frequency for a CPU that has
- * IO-wait which might not even end up running the task when it does become
- * runnable.
+ * Consumers of these two interfaces, like for example the cpuidle menu
+ * governor, are using nonsensical data. Preferring shallow idle state selection
+ * for a CPU that has IO-wait which might not even end up running the task when
+ * it does become runnable.
  */
 
 unsigned long nr_iowait_cpu(int cpu)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 908c9cdae2f0..ee271bb661cc 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -693,6 +693,7 @@ static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se)
 
 static int select_idle_sibling(struct task_struct *p, int prev_cpu, int cpu);
 static unsigned long task_h_load(struct task_struct *p);
+static unsigned long capacity_of(int cpu);
 
 /* Give new sched_entity start runnable values to heavy its load in infant time */
 void init_entity_runnable_average(struct sched_entity *se)
@@ -1456,7 +1457,6 @@ bool should_numa_migrate_memory(struct task_struct *p, struct page * page,
 static unsigned long weighted_cpuload(struct rq *rq);
 static unsigned long source_load(int cpu, int type);
 static unsigned long target_load(int cpu, int type);
-static unsigned long capacity_of(int cpu);
 
 /* Cached statistics for all CPUs within a node */
 struct numa_stats {
@@ -1464,8 +1464,6 @@ struct numa_stats {
 
 	/* Total compute capacity of CPUs on a node */
 	unsigned long compute_capacity;
-
-	unsigned int nr_running;
 };
 
 /*
@@ -1473,36 +1471,16 @@ struct numa_stats {
  */
 static void update_numa_stats(struct numa_stats *ns, int nid)
 {
-	int smt, cpu, cpus = 0;
-	unsigned long capacity;
+	int cpu;
 
 	memset(ns, 0, sizeof(*ns));
 	for_each_cpu(cpu, cpumask_of_node(nid)) {
 		struct rq *rq = cpu_rq(cpu);
 
-		ns->nr_running += rq->nr_running;
 		ns->load += weighted_cpuload(rq);
 		ns->compute_capacity += capacity_of(cpu);
-
-		cpus++;
 	}
 
-	/*
-	 * If we raced with hotplug and there are no CPUs left in our mask
-	 * the @ns structure is NULL'ed and task_numa_compare() will
-	 * not find this node attractive.
-	 *
-	 * We'll detect a huge imbalance and bail there.
-	 */
-	if (!cpus)
-		return;
-
-	/* smt := ceil(cpus / capacity), assumes: 1 < smt_power < 2 */
-	smt = DIV_ROUND_UP(SCHED_CAPACITY_SCALE * cpus, ns->compute_capacity);
-	capacity = cpus / smt; /* cores */
-
-	capacity = min_t(unsigned, capacity,
-		DIV_ROUND_CLOSEST(ns->compute_capacity, SCHED_CAPACITY_SCALE));
 }
 
 struct task_numa_env {
@@ -3723,6 +3701,29 @@ util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep)
 	WRITE_ONCE(p->se.avg.util_est, ue);
 }
 
+static inline int task_fits_capacity(struct task_struct *p, long capacity)
+{
+	return capacity * 1024 > task_util_est(p) * capacity_margin;
+}
+
+static inline void update_misfit_status(struct task_struct *p, struct rq *rq)
+{
+	if (!static_branch_unlikely(&sched_asym_cpucapacity))
+		return;
+
+	if (!p) {
+		rq->misfit_task_load = 0;
+		return;
+	}
+
+	if (task_fits_capacity(p, capacity_of(cpu_of(rq)))) {
+		rq->misfit_task_load = 0;
+		return;
+	}
+
+	rq->misfit_task_load = task_h_load(p);
+}
+
 #else /* CONFIG_SMP */
 
 #define UPDATE_TG	0x0
@@ -3752,6 +3753,7 @@ util_est_enqueue(struct cfs_rq *cfs_rq, struct task_struct *p) {}
 static inline void
 util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p,
 		 bool task_sleep) {}
+static inline void update_misfit_status(struct task_struct *p, struct rq *rq) {}
 
 #endif /* CONFIG_SMP */
 
@@ -6280,6 +6282,9 @@ static int wake_cap(struct task_struct *p, int cpu, int prev_cpu)
 {
 	long min_cap, max_cap;
 
+	if (!static_branch_unlikely(&sched_asym_cpucapacity))
+		return 0;
+
 	min_cap = min(capacity_orig_of(prev_cpu), capacity_orig_of(cpu));
 	max_cap = cpu_rq(cpu)->rd->max_cpu_capacity;
 
@@ -6290,7 +6295,7 @@ static int wake_cap(struct task_struct *p, int cpu, int prev_cpu)
 	/* Bring task utilization in sync with prev_cpu */
 	sync_entity_load_avg(&p->se);
 
-	return min_cap * 1024 < task_util(p) * capacity_margin;
+	return !task_fits_capacity(p, min_cap);
 }
 
 /*
@@ -6709,9 +6714,12 @@ done: __maybe_unused;
 	if (hrtick_enabled(rq))
 		hrtick_start_fair(rq, p);
 
+	update_misfit_status(p, rq);
+
 	return p;
 
 idle:
+	update_misfit_status(NULL, rq);
 	new_tasks = idle_balance(rq, rf);
 
 	/*
@@ -6917,6 +6925,13 @@ static unsigned long __read_mostly max_load_balance_interval = HZ/10;
 
 enum fbq_type { regular, remote, all };
 
+enum group_type {
+	group_other = 0,
+	group_misfit_task,
+	group_imbalanced,
+	group_overloaded,
+};
+
 #define LBF_ALL_PINNED	0x01
 #define LBF_NEED_BREAK	0x02
 #define LBF_DST_PINNED  0x04
@@ -6947,6 +6962,7 @@ struct lb_env {
 	unsigned int		loop_max;
 
 	enum fbq_type		fbq_type;
+	enum group_type		src_grp_type;
 	struct list_head	tasks;
 };
 
@@ -7327,7 +7343,7 @@ static inline bool others_have_blocked(struct rq *rq)
 	if (READ_ONCE(rq->avg_dl.util_avg))
 		return true;
 
-#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+#ifdef CONFIG_HAVE_SCHED_AVG_IRQ
 	if (READ_ONCE(rq->avg_irq.util_avg))
 		return true;
 #endif
@@ -7490,12 +7506,6 @@ static unsigned long task_h_load(struct task_struct *p)
 
 /********** Helpers for find_busiest_group ************************/
 
-enum group_type {
-	group_other = 0,
-	group_imbalanced,
-	group_overloaded,
-};
-
 /*
  * sg_lb_stats - stats of a sched_group required for load_balancing
  */
@@ -7511,6 +7521,7 @@ struct sg_lb_stats {
 	unsigned int group_weight;
 	enum group_type group_type;
 	int group_no_capacity;
+	unsigned long group_misfit_task_load; /* A CPU has a task too big for its capacity */
 #ifdef CONFIG_NUMA_BALANCING
 	unsigned int nr_numa_running;
 	unsigned int nr_preferred_running;
@@ -7619,13 +7630,14 @@ static void update_cpu_capacity(struct sched_domain *sd, int cpu)
 	cpu_rq(cpu)->cpu_capacity = capacity;
 	sdg->sgc->capacity = capacity;
 	sdg->sgc->min_capacity = capacity;
+	sdg->sgc->max_capacity = capacity;
 }
 
 void update_group_capacity(struct sched_domain *sd, int cpu)
 {
 	struct sched_domain *child = sd->child;
 	struct sched_group *group, *sdg = sd->groups;
-	unsigned long capacity, min_capacity;
+	unsigned long capacity, min_capacity, max_capacity;
 	unsigned long interval;
 
 	interval = msecs_to_jiffies(sd->balance_interval);
@@ -7639,6 +7651,7 @@ void update_group_capacity(struct sched_domain *sd, int cpu)
 
 	capacity = 0;
 	min_capacity = ULONG_MAX;
+	max_capacity = 0;
 
 	if (child->flags & SD_OVERLAP) {
 		/*
@@ -7669,6 +7682,7 @@ void update_group_capacity(struct sched_domain *sd, int cpu)
 			}
 
 			min_capacity = min(capacity, min_capacity);
+			max_capacity = max(capacity, max_capacity);
 		}
 	} else  {
 		/*
@@ -7682,12 +7696,14 @@ void update_group_capacity(struct sched_domain *sd, int cpu)
 
 			capacity += sgc->capacity;
 			min_capacity = min(sgc->min_capacity, min_capacity);
+			max_capacity = max(sgc->max_capacity, max_capacity);
 			group = group->next;
 		} while (group != child->groups);
 	}
 
 	sdg->sgc->capacity = capacity;
 	sdg->sgc->min_capacity = min_capacity;
+	sdg->sgc->max_capacity = max_capacity;
 }
 
 /*
@@ -7783,16 +7799,27 @@ group_is_overloaded(struct lb_env *env, struct sg_lb_stats *sgs)
 }
 
 /*
- * group_smaller_cpu_capacity: Returns true if sched_group sg has smaller
+ * group_smaller_min_cpu_capacity: Returns true if sched_group sg has smaller
  * per-CPU capacity than sched_group ref.
  */
 static inline bool
-group_smaller_cpu_capacity(struct sched_group *sg, struct sched_group *ref)
+group_smaller_min_cpu_capacity(struct sched_group *sg, struct sched_group *ref)
 {
 	return sg->sgc->min_capacity * capacity_margin <
 						ref->sgc->min_capacity * 1024;
 }
 
+/*
+ * group_smaller_max_cpu_capacity: Returns true if sched_group sg has smaller
+ * per-CPU capacity_orig than sched_group ref.
+ */
+static inline bool
+group_smaller_max_cpu_capacity(struct sched_group *sg, struct sched_group *ref)
+{
+	return sg->sgc->max_capacity * capacity_margin <
+						ref->sgc->max_capacity * 1024;
+}
+
 static inline enum
 group_type group_classify(struct sched_group *group,
 			  struct sg_lb_stats *sgs)
@@ -7803,6 +7830,9 @@ group_type group_classify(struct sched_group *group,
 	if (sg_imbalanced(group))
 		return group_imbalanced;
 
+	if (sgs->group_misfit_task_load)
+		return group_misfit_task;
+
 	return group_other;
 }
 
@@ -7835,7 +7865,7 @@ static bool update_nohz_stats(struct rq *rq, bool force)
  * @load_idx: Load index of sched_domain of this_cpu for load calc.
  * @local_group: Does group contain this_cpu.
  * @sgs: variable to hold the statistics for this group.
- * @overload: Indicate more than one runnable task for any CPU.
+ * @overload: Indicate pullable load (e.g. >1 runnable task).
  */
 static inline void update_sg_lb_stats(struct lb_env *env,
 			struct sched_group *group, int load_idx,
@@ -7877,6 +7907,12 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 		 */
 		if (!nr_running && idle_cpu(i))
 			sgs->idle_cpus++;
+
+		if (env->sd->flags & SD_ASYM_CPUCAPACITY &&
+		    sgs->group_misfit_task_load < rq->misfit_task_load) {
+			sgs->group_misfit_task_load = rq->misfit_task_load;
+			*overload = 1;
+		}
 	}
 
 	/* Adjust by relative CPU capacity of the group */
@@ -7912,6 +7948,17 @@ static bool update_sd_pick_busiest(struct lb_env *env,
 {
 	struct sg_lb_stats *busiest = &sds->busiest_stat;
 
+	/*
+	 * Don't try to pull misfit tasks we can't help.
+	 * We can use max_capacity here as reduction in capacity on some
+	 * CPUs in the group should either be possible to resolve
+	 * internally or be covered by avg_load imbalance (eventually).
+	 */
+	if (sgs->group_type == group_misfit_task &&
+	    (!group_smaller_max_cpu_capacity(sg, sds->local) ||
+	     !group_has_capacity(env, &sds->local_stat)))
+		return false;
+
 	if (sgs->group_type > busiest->group_type)
 		return true;
 
@@ -7931,7 +7978,14 @@ static bool update_sd_pick_busiest(struct lb_env *env,
 	 * power/energy consequences are not considered.
 	 */
 	if (sgs->sum_nr_running <= sgs->group_weight &&
-	    group_smaller_cpu_capacity(sds->local, sg))
+	    group_smaller_min_cpu_capacity(sds->local, sg))
+		return false;
+
+	/*
+	 * If we have more than one misfit sg go with the biggest misfit.
+	 */
+	if (sgs->group_type == group_misfit_task &&
+	    sgs->group_misfit_task_load < busiest->group_misfit_task_load)
 		return false;
 
 asym_packing:
@@ -8002,11 +8056,9 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
 	struct sched_group *sg = env->sd->groups;
 	struct sg_lb_stats *local = &sds->local_stat;
 	struct sg_lb_stats tmp_sgs;
-	int load_idx, prefer_sibling = 0;
+	int load_idx;
 	bool overload = false;
-
-	if (child && child->flags & SD_PREFER_SIBLING)
-		prefer_sibling = 1;
+	bool prefer_sibling = child && child->flags & SD_PREFER_SIBLING;
 
 #ifdef CONFIG_NO_HZ_COMMON
 	if (env->idle == CPU_NEWLY_IDLE && READ_ONCE(nohz.has_blocked))
@@ -8080,8 +8132,8 @@ next_group:
 
 	if (!env->sd->parent) {
 		/* update overload indicator if we are at root domain */
-		if (env->dst_rq->rd->overload != overload)
-			env->dst_rq->rd->overload = overload;
+		if (READ_ONCE(env->dst_rq->rd->overload) != overload)
+			WRITE_ONCE(env->dst_rq->rd->overload, overload);
 	}
 }
 
@@ -8231,8 +8283,9 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
 	 * factors in sg capacity and sgs with smaller group_type are
 	 * skipped when updating the busiest sg:
 	 */
-	if (busiest->avg_load <= sds->avg_load ||
-	    local->avg_load >= sds->avg_load) {
+	if (busiest->group_type != group_misfit_task &&
+	    (busiest->avg_load <= sds->avg_load ||
+	     local->avg_load >= sds->avg_load)) {
 		env->imbalance = 0;
 		return fix_small_imbalance(env, sds);
 	}
@@ -8266,6 +8319,12 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
 		(sds->avg_load - local->avg_load) * local->group_capacity
 	) / SCHED_CAPACITY_SCALE;
 
+	/* Boost imbalance to allow misfit task to be balanced. */
+	if (busiest->group_type == group_misfit_task) {
+		env->imbalance = max_t(long, env->imbalance,
+				       busiest->group_misfit_task_load);
+	}
+
 	/*
 	 * if *imbalance is less than the average load per runnable task
 	 * there is no guarantee that any tasks will be moved so we'll have
@@ -8332,6 +8391,10 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
 	    busiest->group_no_capacity)
 		goto force_balance;
 
+	/* Misfit tasks should be dealt with regardless of the avg load */
+	if (busiest->group_type == group_misfit_task)
+		goto force_balance;
+
 	/*
 	 * If the local group is busier than the selected busiest group
 	 * don't try and pull any tasks.
@@ -8369,6 +8432,7 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
 
 force_balance:
 	/* Looks like there is an imbalance. Compute it */
+	env->src_grp_type = busiest->group_type;
 	calculate_imbalance(env, &sds);
 	return env->imbalance ? sds.busiest : NULL;
 
@@ -8416,8 +8480,32 @@ static struct rq *find_busiest_queue(struct lb_env *env,
 		if (rt > env->fbq_type)
 			continue;
 
+		/*
+		 * For ASYM_CPUCAPACITY domains with misfit tasks we simply
+		 * seek the "biggest" misfit task.
+		 */
+		if (env->src_grp_type == group_misfit_task) {
+			if (rq->misfit_task_load > busiest_load) {
+				busiest_load = rq->misfit_task_load;
+				busiest = rq;
+			}
+
+			continue;
+		}
+
 		capacity = capacity_of(i);
 
+		/*
+		 * For ASYM_CPUCAPACITY domains, don't pick a CPU that could
+		 * eventually lead to active_balancing high->low capacity.
+		 * Higher per-CPU capacity is considered better than balancing
+		 * average load.
+		 */
+		if (env->sd->flags & SD_ASYM_CPUCAPACITY &&
+		    capacity_of(env->dst_cpu) < capacity &&
+		    rq->nr_running == 1)
+			continue;
+
 		wl = weighted_cpuload(rq);
 
 		/*
@@ -8485,6 +8573,9 @@ static int need_active_balance(struct lb_env *env)
 			return 1;
 	}
 
+	if (env->src_grp_type == group_misfit_task)
+		return 1;
+
 	return unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2);
 }
 
@@ -9127,7 +9218,7 @@ static void nohz_balancer_kick(struct rq *rq)
 	if (time_before(now, nohz.next_balance))
 		goto out;
 
-	if (rq->nr_running >= 2) {
+	if (rq->nr_running >= 2 || rq->misfit_task_load) {
 		flags = NOHZ_KICK_MASK;
 		goto out;
 	}
@@ -9496,7 +9587,7 @@ static int idle_balance(struct rq *this_rq, struct rq_flags *rf)
 	rq_unpin_lock(this_rq, rf);
 
 	if (this_rq->avg_idle < sysctl_sched_migration_cost ||
-	    !this_rq->rd->overload) {
+	    !READ_ONCE(this_rq->rd->overload)) {
 
 		rcu_read_lock();
 		sd = rcu_dereference_check_sched_domain(this_rq->sd);
@@ -9658,6 +9749,8 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued)
 
 	if (static_branch_unlikely(&sched_numa_balancing))
 		task_tick_numa(rq, curr);
+
+	update_misfit_status(curr, rq);
 }
 
 /*
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index 85ae8488039c..858589b83377 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -39,7 +39,7 @@ SCHED_FEAT(WAKEUP_PREEMPTION, true)
 
 SCHED_FEAT(HRTICK, false)
 SCHED_FEAT(DOUBLE_TICK, false)
-SCHED_FEAT(LB_BIAS, true)
+SCHED_FEAT(LB_BIAS, false)
 
 /*
  * Decrement CPU capacity based on time not spent running tasks
diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c
index 35475c0c5419..90fb5bc12ad4 100644
--- a/kernel/sched/pelt.c
+++ b/kernel/sched/pelt.c
@@ -269,9 +269,6 @@ ___update_load_avg(struct sched_avg *sa, unsigned long load, unsigned long runna
 
 int __update_load_avg_blocked_se(u64 now, int cpu, struct sched_entity *se)
 {
-	if (entity_is_task(se))
-		se->runnable_weight = se->load.weight;
-
 	if (___update_load_sum(now, cpu, &se->avg, 0, 0, 0)) {
 		___update_load_avg(&se->avg, se_weight(se), se_runnable(se));
 		return 1;
@@ -282,9 +279,6 @@ int __update_load_avg_blocked_se(u64 now, int cpu, struct sched_entity *se)
 
 int __update_load_avg_se(u64 now, int cpu, struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	if (entity_is_task(se))
-		se->runnable_weight = se->load.weight;
-
 	if (___update_load_sum(now, cpu, &se->avg, !!se->on_rq, !!se->on_rq,
 				cfs_rq->curr == se)) {
 
@@ -358,7 +352,7 @@ int update_dl_rq_load_avg(u64 now, struct rq *rq, int running)
 	return 0;
 }
 
-#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+#ifdef CONFIG_HAVE_SCHED_AVG_IRQ
 /*
  * irq:
  *
diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h
index d2894db28955..7e56b489ff32 100644
--- a/kernel/sched/pelt.h
+++ b/kernel/sched/pelt.h
@@ -6,7 +6,7 @@ int __update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq);
 int update_rt_rq_load_avg(u64 now, struct rq *rq, int running);
 int update_dl_rq_load_avg(u64 now, struct rq *rq, int running);
 
-#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+#ifdef CONFIG_HAVE_SCHED_AVG_IRQ
 int update_irq_load_avg(struct rq *rq, u64 running);
 #else
 static inline int
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 9683f458aec7..fc24f2b8c646 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -717,8 +717,12 @@ struct root_domain {
 	cpumask_var_t		span;
 	cpumask_var_t		online;
 
-	/* Indicate more than one runnable task for any CPU */
-	bool			overload;
+	/*
+	 * Indicate pullable load on at least one CPU, e.g:
+	 * - More than one runnable task
+	 * - Running task is misfit
+	 */
+	int			overload;
 
 	/*
 	 * The bit corresponding to a CPU gets set here if such CPU has more
@@ -845,6 +849,8 @@ struct rq {
 
 	unsigned char		idle_balance;
 
+	unsigned long		misfit_task_load;
+
 	/* For active balancing */
 	int			active_balance;
 	int			push_cpu;
@@ -858,8 +864,7 @@ struct rq {
 
 	struct sched_avg	avg_rt;
 	struct sched_avg	avg_dl;
-#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
-#define HAVE_SCHED_AVG_IRQ
+#ifdef CONFIG_HAVE_SCHED_AVG_IRQ
 	struct sched_avg	avg_irq;
 #endif
 	u64			idle_stamp;
@@ -1188,6 +1193,7 @@ DECLARE_PER_CPU(int, sd_llc_id);
 DECLARE_PER_CPU(struct sched_domain_shared *, sd_llc_shared);
 DECLARE_PER_CPU(struct sched_domain *, sd_numa);
 DECLARE_PER_CPU(struct sched_domain *, sd_asym);
+extern struct static_key_false sched_asym_cpucapacity;
 
 struct sched_group_capacity {
 	atomic_t		ref;
@@ -1197,6 +1203,7 @@ struct sched_group_capacity {
 	 */
 	unsigned long		capacity;
 	unsigned long		min_capacity;		/* Min per-CPU capacity in group */
+	unsigned long		max_capacity;		/* Max per-CPU capacity in group */
 	unsigned long		next_update;
 	int			imbalance;		/* XXX unrelated to capacity but shared group state */
 
@@ -1396,7 +1403,7 @@ static const_debug __maybe_unused unsigned int sysctl_sched_features =
 	0;
 #undef SCHED_FEAT
 
-#define sched_feat(x) (sysctl_sched_features & (1UL << __SCHED_FEAT_##x))
+#define sched_feat(x) !!(sysctl_sched_features & (1UL << __SCHED_FEAT_##x))
 
 #endif /* SCHED_DEBUG && HAVE_JUMP_LABEL */
 
@@ -1696,8 +1703,8 @@ static inline void add_nr_running(struct rq *rq, unsigned count)
 
 	if (prev_nr < 2 && rq->nr_running >= 2) {
 #ifdef CONFIG_SMP
-		if (!rq->rd->overload)
-			rq->rd->overload = true;
+		if (!READ_ONCE(rq->rd->overload))
+			WRITE_ONCE(rq->rd->overload, 1);
 #endif
 	}
 
@@ -2217,7 +2224,7 @@ static inline unsigned long cpu_util_rt(struct rq *rq)
 }
 #endif
 
-#ifdef HAVE_SCHED_AVG_IRQ
+#ifdef CONFIG_HAVE_SCHED_AVG_IRQ
 static inline unsigned long cpu_util_irq(struct rq *rq)
 {
 	return rq->avg_irq.util_avg;
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 505a41c42b96..9d74371e4aad 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -7,8 +7,8 @@
 DEFINE_MUTEX(sched_domains_mutex);
 
 /* Protected by sched_domains_mutex: */
-cpumask_var_t sched_domains_tmpmask;
-cpumask_var_t sched_domains_tmpmask2;
+static cpumask_var_t sched_domains_tmpmask;
+static cpumask_var_t sched_domains_tmpmask2;
 
 #ifdef CONFIG_SCHED_DEBUG
 
@@ -398,6 +398,7 @@ DEFINE_PER_CPU(int, sd_llc_id);
 DEFINE_PER_CPU(struct sched_domain_shared *, sd_llc_shared);
 DEFINE_PER_CPU(struct sched_domain *, sd_numa);
 DEFINE_PER_CPU(struct sched_domain *, sd_asym);
+DEFINE_STATIC_KEY_FALSE(sched_asym_cpucapacity);
 
 static void update_top_cache_domain(int cpu)
 {
@@ -692,6 +693,7 @@ static void init_overlap_sched_group(struct sched_domain *sd,
 	sg_span = sched_group_span(sg);
 	sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sg_span);
 	sg->sgc->min_capacity = SCHED_CAPACITY_SCALE;
+	sg->sgc->max_capacity = SCHED_CAPACITY_SCALE;
 }
 
 static int
@@ -851,6 +853,7 @@ static struct sched_group *get_group(int cpu, struct sd_data *sdd)
 
 	sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sched_group_span(sg));
 	sg->sgc->min_capacity = SCHED_CAPACITY_SCALE;
+	sg->sgc->max_capacity = SCHED_CAPACITY_SCALE;
 
 	return sg;
 }
@@ -1061,7 +1064,6 @@ static struct cpumask		***sched_domains_numa_masks;
  *   SD_SHARE_PKG_RESOURCES - describes shared caches
  *   SD_NUMA                - describes NUMA topologies
  *   SD_SHARE_POWERDOMAIN   - describes shared power domain
- *   SD_ASYM_CPUCAPACITY    - describes mixed capacity topologies
  *
  * Odd one out, which beside describing the topology has a quirk also
  * prescribes the desired behaviour that goes along with it:
@@ -1073,13 +1075,12 @@ static struct cpumask		***sched_domains_numa_masks;
 	 SD_SHARE_PKG_RESOURCES |	\
 	 SD_NUMA		|	\
 	 SD_ASYM_PACKING	|	\
-	 SD_ASYM_CPUCAPACITY	|	\
 	 SD_SHARE_POWERDOMAIN)
 
 static struct sched_domain *
 sd_init(struct sched_domain_topology_level *tl,
 	const struct cpumask *cpu_map,
-	struct sched_domain *child, int cpu)
+	struct sched_domain *child, int dflags, int cpu)
 {
 	struct sd_data *sdd = &tl->data;
 	struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu);
@@ -1100,6 +1101,9 @@ sd_init(struct sched_domain_topology_level *tl,
 			"wrong sd_flags in topology description\n"))
 		sd_flags &= ~TOPOLOGY_SD_FLAGS;
 
+	/* Apply detected topology flags */
+	sd_flags |= dflags;
+
 	*sd = (struct sched_domain){
 		.min_interval		= sd_weight,
 		.max_interval		= 2*sd_weight,
@@ -1122,7 +1126,7 @@ sd_init(struct sched_domain_topology_level *tl,
 					| 0*SD_SHARE_CPUCAPACITY
 					| 0*SD_SHARE_PKG_RESOURCES
 					| 0*SD_SERIALIZE
-					| 0*SD_PREFER_SIBLING
+					| 1*SD_PREFER_SIBLING
 					| 0*SD_NUMA
 					| sd_flags
 					,
@@ -1148,17 +1152,21 @@ sd_init(struct sched_domain_topology_level *tl,
 	if (sd->flags & SD_ASYM_CPUCAPACITY) {
 		struct sched_domain *t = sd;
 
+		/*
+		 * Don't attempt to spread across CPUs of different capacities.
+		 */
+		if (sd->child)
+			sd->child->flags &= ~SD_PREFER_SIBLING;
+
 		for_each_lower_domain(t)
 			t->flags |= SD_BALANCE_WAKE;
 	}
 
 	if (sd->flags & SD_SHARE_CPUCAPACITY) {
-		sd->flags |= SD_PREFER_SIBLING;
 		sd->imbalance_pct = 110;
 		sd->smt_gain = 1178; /* ~15% */
 
 	} else if (sd->flags & SD_SHARE_PKG_RESOURCES) {
-		sd->flags |= SD_PREFER_SIBLING;
 		sd->imbalance_pct = 117;
 		sd->cache_nice_tries = 1;
 		sd->busy_idx = 2;
@@ -1169,6 +1177,7 @@ sd_init(struct sched_domain_topology_level *tl,
 		sd->busy_idx = 3;
 		sd->idle_idx = 2;
 
+		sd->flags &= ~SD_PREFER_SIBLING;
 		sd->flags |= SD_SERIALIZE;
 		if (sched_domains_numa_distance[tl->numa_level] > RECLAIM_DISTANCE) {
 			sd->flags &= ~(SD_BALANCE_EXEC |
@@ -1178,7 +1187,6 @@ sd_init(struct sched_domain_topology_level *tl,
 
 #endif
 	} else {
-		sd->flags |= SD_PREFER_SIBLING;
 		sd->cache_nice_tries = 1;
 		sd->busy_idx = 2;
 		sd->idle_idx = 1;
@@ -1604,9 +1612,9 @@ static void __sdt_free(const struct cpumask *cpu_map)
 
 static struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl,
 		const struct cpumask *cpu_map, struct sched_domain_attr *attr,
-		struct sched_domain *child, int cpu)
+		struct sched_domain *child, int dflags, int cpu)
 {
-	struct sched_domain *sd = sd_init(tl, cpu_map, child, cpu);
+	struct sched_domain *sd = sd_init(tl, cpu_map, child, dflags, cpu);
 
 	if (child) {
 		sd->level = child->level + 1;
@@ -1633,6 +1641,65 @@ static struct sched_domain *build_sched_domain(struct sched_domain_topology_leve
 }
 
 /*
+ * Find the sched_domain_topology_level where all CPU capacities are visible
+ * for all CPUs.
+ */
+static struct sched_domain_topology_level
+*asym_cpu_capacity_level(const struct cpumask *cpu_map)
+{
+	int i, j, asym_level = 0;
+	bool asym = false;
+	struct sched_domain_topology_level *tl, *asym_tl = NULL;
+	unsigned long cap;
+
+	/* Is there any asymmetry? */
+	cap = arch_scale_cpu_capacity(NULL, cpumask_first(cpu_map));
+
+	for_each_cpu(i, cpu_map) {
+		if (arch_scale_cpu_capacity(NULL, i) != cap) {
+			asym = true;
+			break;
+		}
+	}
+
+	if (!asym)
+		return NULL;
+
+	/*
+	 * Examine topology from all CPU's point of views to detect the lowest
+	 * sched_domain_topology_level where a highest capacity CPU is visible
+	 * to everyone.
+	 */
+	for_each_cpu(i, cpu_map) {
+		unsigned long max_capacity = arch_scale_cpu_capacity(NULL, i);
+		int tl_id = 0;
+
+		for_each_sd_topology(tl) {
+			if (tl_id < asym_level)
+				goto next_level;
+
+			for_each_cpu_and(j, tl->mask(i), cpu_map) {
+				unsigned long capacity;
+
+				capacity = arch_scale_cpu_capacity(NULL, j);
+
+				if (capacity <= max_capacity)
+					continue;
+
+				max_capacity = capacity;
+				asym_level = tl_id;
+				asym_tl = tl;
+			}
+next_level:
+			tl_id++;
+		}
+	}
+
+	return asym_tl;
+}
+
+
+/*
  * Build sched domains for a given set of CPUs and attach the sched domains
  * to the individual CPUs
  */
@@ -1644,18 +1711,30 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
 	struct s_data d;
 	struct rq *rq = NULL;
 	int i, ret = -ENOMEM;
+	struct sched_domain_topology_level *tl_asym;
+	bool has_asym = false;
 
 	alloc_state = __visit_domain_allocation_hell(&d, cpu_map);
 	if (alloc_state != sa_rootdomain)
 		goto error;
 
+	tl_asym = asym_cpu_capacity_level(cpu_map);
+
 	/* Set up domains for CPUs specified by the cpu_map: */
 	for_each_cpu(i, cpu_map) {
 		struct sched_domain_topology_level *tl;
 
 		sd = NULL;
 		for_each_sd_topology(tl) {
-			sd = build_sched_domain(tl, cpu_map, attr, sd, i);
+			int dflags = 0;
+
+			if (tl == tl_asym) {
+				dflags |= SD_ASYM_CPUCAPACITY;
+				has_asym = true;
+			}
+
+			sd = build_sched_domain(tl, cpu_map, attr, sd, dflags, i);
+
 			if (tl == sched_domain_topology)
 				*per_cpu_ptr(d.sd, i) = sd;
 			if (tl->flags & SDTL_OVERLAP)
@@ -1704,6 +1783,9 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
 	}
 	rcu_read_unlock();
 
+	if (has_asym)
+		static_branch_enable_cpuslocked(&sched_asym_cpucapacity);
+
 	if (rq && sched_debug_enabled) {
 		pr_info("root domain span: %*pbl (max cpu_capacity = %lu)\n",
 			cpumask_pr_args(cpu_map), rq->rd->max_cpu_capacity);