1 files changed, 287 insertions, 227 deletions

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index aa4c6227cd6d..8a8bd7b13634 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -531,12 +531,15 @@ static inline u64 min_vruntime(u64 min_vruntime, u64 vruntime)
 	return min_vruntime;
 }
 
-static inline int entity_before(struct sched_entity *a,
+static inline bool entity_before(struct sched_entity *a,
 				struct sched_entity *b)
 {
 	return (s64)(a->vruntime - b->vruntime) < 0;
 }
 
+#define __node_2_se(node) \
+	rb_entry((node), struct sched_entity, run_node)
+
 static void update_min_vruntime(struct cfs_rq *cfs_rq)
 {
 	struct sched_entity *curr = cfs_rq->curr;
@@ -552,8 +555,7 @@ static void update_min_vruntime(struct cfs_rq *cfs_rq)
 	}
 
 	if (leftmost) { /* non-empty tree */
-		struct sched_entity *se;
-		se = rb_entry(leftmost, struct sched_entity, run_node);
+		struct sched_entity *se = __node_2_se(leftmost);
 
 		if (!curr)
 			vruntime = se->vruntime;
@@ -569,37 +571,17 @@ static void update_min_vruntime(struct cfs_rq *cfs_rq)
 #endif
 }
 
+static inline bool __entity_less(struct rb_node *a, const struct rb_node *b)
+{
+	return entity_before(__node_2_se(a), __node_2_se(b));
+}
+
 /*
  * Enqueue an entity into the rb-tree:
  */
 static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	struct rb_node **link = &cfs_rq->tasks_timeline.rb_root.rb_node;
-	struct rb_node *parent = NULL;
-	struct sched_entity *entry;
-	bool leftmost = true;
-
-	/*
-	 * Find the right place in the rbtree:
-	 */
-	while (*link) {
-		parent = *link;
-		entry = rb_entry(parent, struct sched_entity, run_node);
-		/*
-		 * We dont care about collisions. Nodes with
-		 * the same key stay together.
-		 */
-		if (entity_before(se, entry)) {
-			link = &parent->rb_left;
-		} else {
-			link = &parent->rb_right;
-			leftmost = false;
-		}
-	}
-
-	rb_link_node(&se->run_node, parent, link);
-	rb_insert_color_cached(&se->run_node,
-			       &cfs_rq->tasks_timeline, leftmost);
+	rb_add_cached(&se->run_node, &cfs_rq->tasks_timeline, __entity_less);
 }
 
 static void __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
@@ -614,7 +596,7 @@ struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq)
 	if (!left)
 		return NULL;
 
-	return rb_entry(left, struct sched_entity, run_node);
+	return __node_2_se(left);
 }
 
 static struct sched_entity *__pick_next_entity(struct sched_entity *se)
@@ -624,7 +606,7 @@ static struct sched_entity *__pick_next_entity(struct sched_entity *se)
 	if (!next)
 		return NULL;
 
-	return rb_entry(next, struct sched_entity, run_node);
+	return __node_2_se(next);
 }
 
 #ifdef CONFIG_SCHED_DEBUG
@@ -635,7 +617,7 @@ struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq)
 	if (!last)
 		return NULL;
 
-	return rb_entry(last, struct sched_entity, run_node);
+	return __node_2_se(last);
 }
 
 /**************************************************************
@@ -906,6 +888,15 @@ update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	if (!schedstat_enabled())
 		return;
 
+	/*
+	 * When the sched_schedstat changes from 0 to 1, some sched se
+	 * maybe already in the runqueue, the se->statistics.wait_start
+	 * will be 0.So it will let the delta wrong. We need to avoid this
+	 * scenario.
+	 */
+	if (unlikely(!schedstat_val(se->statistics.wait_start)))
+		return;
+
 	delta = rq_clock(rq_of(cfs_rq)) - schedstat_val(se->statistics.wait_start);
 
 	if (entity_is_task(se)) {
@@ -1550,7 +1541,8 @@ struct task_numa_env {
 static unsigned long cpu_load(struct rq *rq);
 static unsigned long cpu_runnable(struct rq *rq);
 static unsigned long cpu_util(int cpu);
-static inline long adjust_numa_imbalance(int imbalance, int nr_running);
+static inline long adjust_numa_imbalance(int imbalance,
+					int dst_running, int dst_weight);
 
 static inline enum
 numa_type numa_classify(unsigned int imbalance_pct,
@@ -1930,7 +1922,8 @@ static void task_numa_find_cpu(struct task_numa_env *env,
 		src_running = env->src_stats.nr_running - 1;
 		dst_running = env->dst_stats.nr_running + 1;
 		imbalance = max(0, dst_running - src_running);
-		imbalance = adjust_numa_imbalance(imbalance, dst_running);
+		imbalance = adjust_numa_imbalance(imbalance, dst_running,
+							env->dst_stats.weight);
 
 		/* Use idle CPU if there is no imbalance */
 		if (!imbalance) {
@@ -2928,7 +2921,7 @@ static void task_tick_numa(struct rq *rq, struct task_struct *curr)
 		curr->node_stamp += period;
 
 		if (!time_before(jiffies, curr->mm->numa_next_scan))
-			task_work_add(curr, work, true);
+			task_work_add(curr, work, TWA_RESUME);
 	}
 }
 
@@ -3932,6 +3925,22 @@ static inline void util_est_enqueue(struct cfs_rq *cfs_rq,
 	trace_sched_util_est_cfs_tp(cfs_rq);
 }
 
+static inline void util_est_dequeue(struct cfs_rq *cfs_rq,
+				    struct task_struct *p)
+{
+	unsigned int enqueued;
+
+	if (!sched_feat(UTIL_EST))
+		return;
+
+	/* Update root cfs_rq's estimated utilization */
+	enqueued  = cfs_rq->avg.util_est.enqueued;
+	enqueued -= min_t(unsigned int, enqueued, _task_util_est(p));
+	WRITE_ONCE(cfs_rq->avg.util_est.enqueued, enqueued);
+
+	trace_sched_util_est_cfs_tp(cfs_rq);
+}
+
 /*
  * Check if a (signed) value is within a specified (unsigned) margin,
  * based on the observation that:
@@ -3945,23 +3954,16 @@ static inline bool within_margin(int value, int margin)
 	return ((unsigned int)(value + margin - 1) < (2 * margin - 1));
 }
 
-static void
-util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep)
+static inline void util_est_update(struct cfs_rq *cfs_rq,
+				   struct task_struct *p,
+				   bool task_sleep)
 {
 	long last_ewma_diff;
 	struct util_est ue;
-	int cpu;
 
 	if (!sched_feat(UTIL_EST))
 		return;
 
-	/* Update root cfs_rq's estimated utilization */
-	ue.enqueued  = cfs_rq->avg.util_est.enqueued;
-	ue.enqueued -= min_t(unsigned int, ue.enqueued, _task_util_est(p));
-	WRITE_ONCE(cfs_rq->avg.util_est.enqueued, ue.enqueued);
-
-	trace_sched_util_est_cfs_tp(cfs_rq);
-
 	/*
 	 * Skip update of task's estimated utilization when the task has not
 	 * yet completed an activation, e.g. being migrated.
@@ -4001,8 +4003,7 @@ util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep)
 	 * To avoid overestimation of actual task utilization, skip updates if
 	 * we cannot grant there is idle time in this CPU.
 	 */
-	cpu = cpu_of(rq_of(cfs_rq));
-	if (task_util(p) > capacity_orig_of(cpu))
+	if (task_util(p) > capacity_orig_of(cpu_of(rq_of(cfs_rq))))
 		return;
 
 	/*
@@ -4041,7 +4042,7 @@ static inline void update_misfit_status(struct task_struct *p, struct rq *rq)
 	if (!static_branch_unlikely(&sched_asym_cpucapacity))
 		return;
 
-	if (!p) {
+	if (!p || p->nr_cpus_allowed == 1) {
 		rq->misfit_task_load = 0;
 		return;
 	}
@@ -4085,8 +4086,11 @@ static inline void
 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) {}
+util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p) {}
+
+static inline void
+util_est_update(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 */
@@ -4779,25 +4783,37 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq)
 		struct cfs_rq *qcfs_rq = cfs_rq_of(se);
 		/* throttled entity or throttle-on-deactivate */
 		if (!se->on_rq)
-			break;
+			goto done;
 
-		if (dequeue) {
-			dequeue_entity(qcfs_rq, se, DEQUEUE_SLEEP);
-		} else {
-			update_load_avg(qcfs_rq, se, 0);
-			se_update_runnable(se);
-		}
+		dequeue_entity(qcfs_rq, se, DEQUEUE_SLEEP);
 
 		qcfs_rq->h_nr_running -= task_delta;
 		qcfs_rq->idle_h_nr_running -= idle_task_delta;
 
-		if (qcfs_rq->load.weight)
-			dequeue = 0;
+		if (qcfs_rq->load.weight) {
+			/* Avoid re-evaluating load for this entity: */
+			se = parent_entity(se);
+			break;
+		}
 	}
 
-	if (!se)
-		sub_nr_running(rq, task_delta);
+	for_each_sched_entity(se) {
+		struct cfs_rq *qcfs_rq = cfs_rq_of(se);
+		/* throttled entity or throttle-on-deactivate */
+		if (!se->on_rq)
+			goto done;
+
+		update_load_avg(qcfs_rq, se, 0);
+		se_update_runnable(se);
+
+		qcfs_rq->h_nr_running -= task_delta;
+		qcfs_rq->idle_h_nr_running -= idle_task_delta;
+	}
+
+	/* At this point se is NULL and we are at root level*/
+	sub_nr_running(rq, task_delta);
 
+done:
 	/*
 	 * Note: distribution will already see us throttled via the
 	 * throttled-list.  rq->lock protects completion.
@@ -5105,9 +5121,6 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b)
 		return;
 
 	distribute_cfs_runtime(cfs_b);
-
-	raw_spin_lock_irqsave(&cfs_b->lock, flags);
-	raw_spin_unlock_irqrestore(&cfs_b->lock, flags);
 }
 
 /*
@@ -5399,7 +5412,7 @@ static void hrtick_start_fair(struct rq *rq, struct task_struct *p)
 		s64 delta = slice - ran;
 
 		if (delta < 0) {
-			if (rq->curr == p)
+			if (task_current(rq, p))
 				resched_curr(rq);
 			return;
 		}
@@ -5416,7 +5429,7 @@ static void hrtick_update(struct rq *rq)
 {
 	struct task_struct *curr = rq->curr;
 
-	if (!hrtick_enabled(rq) || curr->sched_class != &fair_sched_class)
+	if (!hrtick_enabled_fair(rq) || curr->sched_class != &fair_sched_class)
 		return;
 
 	if (cfs_rq_of(&curr->se)->nr_running < sched_nr_latency)
@@ -5477,6 +5490,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	struct cfs_rq *cfs_rq;
 	struct sched_entity *se = &p->se;
 	int idle_h_nr_running = task_has_idle_policy(p);
+	int task_new = !(flags & ENQUEUE_WAKEUP);
 
 	/*
 	 * The code below (indirectly) updates schedutil which looks at
@@ -5549,7 +5563,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	 * into account, but that is not straightforward to implement,
 	 * and the following generally works well enough in practice.
 	 */
-	if (flags & ENQUEUE_WAKEUP)
+	if (!task_new)
 		update_overutilized_status(rq);
 
 enqueue_throttle:
@@ -5588,6 +5602,8 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	int idle_h_nr_running = task_has_idle_policy(p);
 	bool was_sched_idle = sched_idle_rq(rq);
 
+	util_est_dequeue(&rq->cfs, p);
+
 	for_each_sched_entity(se) {
 		cfs_rq = cfs_rq_of(se);
 		dequeue_entity(cfs_rq, se, flags);
@@ -5638,7 +5654,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 		rq->next_balance = jiffies;
 
 dequeue_throttle:
-	util_est_dequeue(&rq->cfs, p, task_sleep);
+	util_est_update(&rq->cfs, p, task_sleep);
 	hrtick_update(rq);
 }
 
@@ -5804,6 +5820,9 @@ wake_affine_idle(int this_cpu, int prev_cpu, int sync)
 	if (sync && cpu_rq(this_cpu)->nr_running == 1)
 		return this_cpu;
 
+	if (available_idle_cpu(prev_cpu))
+		return prev_cpu;
+
 	return nr_cpumask_bits;
 }
 
@@ -5982,6 +6001,14 @@ static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p
 	return new_cpu;
 }
 
+static inline int __select_idle_cpu(int cpu)
+{
+	if (available_idle_cpu(cpu) || sched_idle_cpu(cpu))
+		return cpu;
+
+	return -1;
+}
+
 #ifdef CONFIG_SCHED_SMT
 DEFINE_STATIC_KEY_FALSE(sched_smt_present);
 EXPORT_SYMBOL_GPL(sched_smt_present);
@@ -6040,73 +6067,51 @@ unlock:
  * there are no idle cores left in the system; tracked through
  * sd_llc->shared->has_idle_cores and enabled through update_idle_core() above.
  */
-static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int target)
+static int select_idle_core(struct task_struct *p, int core, struct cpumask *cpus, int *idle_cpu)
 {
-	struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_idle_mask);
-	int core, cpu;
+	bool idle = true;
+	int cpu;
 
 	if (!static_branch_likely(&sched_smt_present))
-		return -1;
-
-	if (!test_idle_cores(target, false))
-		return -1;
+		return __select_idle_cpu(core);
 
-	cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr);
-
-	for_each_cpu_wrap(core, cpus, target) {
-		bool idle = true;
-
-		for_each_cpu(cpu, cpu_smt_mask(core)) {
-			if (!available_idle_cpu(cpu)) {
-				idle = false;
-				break;
+	for_each_cpu(cpu, cpu_smt_mask(core)) {
+		if (!available_idle_cpu(cpu)) {
+			idle = false;
+			if (*idle_cpu == -1) {
+				if (sched_idle_cpu(cpu) && cpumask_test_cpu(cpu, p->cpus_ptr)) {
+					*idle_cpu = cpu;
+					break;
+				}
+				continue;
 			}
+			break;
 		}
-		cpumask_andnot(cpus, cpus, cpu_smt_mask(core));
-
-		if (idle)
-			return core;
+		if (*idle_cpu == -1 && cpumask_test_cpu(cpu, p->cpus_ptr))
+			*idle_cpu = cpu;
 	}
 
-	/*
-	 * Failed to find an idle core; stop looking for one.
-	 */
-	set_idle_cores(target, 0);
+	if (idle)
+		return core;
 
+	cpumask_andnot(cpus, cpus, cpu_smt_mask(core));
 	return -1;
 }
 
-/*
- * Scan the local SMT mask for idle CPUs.
- */
-static int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int target)
-{
-	int cpu;
-
-	if (!static_branch_likely(&sched_smt_present))
-		return -1;
-
-	for_each_cpu(cpu, cpu_smt_mask(target)) {
-		if (!cpumask_test_cpu(cpu, p->cpus_ptr) ||
-		    !cpumask_test_cpu(cpu, sched_domain_span(sd)))
-			continue;
-		if (available_idle_cpu(cpu) || sched_idle_cpu(cpu))
-			return cpu;
-	}
+#else /* CONFIG_SCHED_SMT */
 
-	return -1;
+static inline void set_idle_cores(int cpu, int val)
+{
 }
 
-#else /* CONFIG_SCHED_SMT */
-
-static inline int select_idle_core(struct task_struct *p, struct sched_domain *sd, int target)
+static inline bool test_idle_cores(int cpu, bool def)
 {
-	return -1;
+	return def;
 }
 
-static inline int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int target)
+static inline int select_idle_core(struct task_struct *p, int core, struct cpumask *cpus, int *idle_cpu)
 {
-	return -1;
+	return __select_idle_cpu(core);
 }
 
 #endif /* CONFIG_SCHED_SMT */
@@ -6119,49 +6124,61 @@ static inline int select_idle_smt(struct task_struct *p, struct sched_domain *sd
 static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int target)
 {
 	struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_idle_mask);
+	int i, cpu, idle_cpu = -1, nr = INT_MAX;
+	bool smt = test_idle_cores(target, false);
+	int this = smp_processor_id();
 	struct sched_domain *this_sd;
-	u64 avg_cost, avg_idle;
 	u64 time;
-	int this = smp_processor_id();
-	int cpu, nr = INT_MAX;
 
 	this_sd = rcu_dereference(*this_cpu_ptr(&sd_llc));
 	if (!this_sd)
 		return -1;
 
-	/*
-	 * Due to large variance we need a large fuzz factor; hackbench in
-	 * particularly is sensitive here.
-	 */
-	avg_idle = this_rq()->avg_idle / 512;
-	avg_cost = this_sd->avg_scan_cost + 1;
+	cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr);
 
-	if (sched_feat(SIS_AVG_CPU) && avg_idle < avg_cost)
-		return -1;
+	if (sched_feat(SIS_PROP) && !smt) {
+		u64 avg_cost, avg_idle, span_avg;
+
+		/*
+		 * Due to large variance we need a large fuzz factor;
+		 * hackbench in particularly is sensitive here.
+		 */
+		avg_idle = this_rq()->avg_idle / 512;
+		avg_cost = this_sd->avg_scan_cost + 1;
 
-	if (sched_feat(SIS_PROP)) {
-		u64 span_avg = sd->span_weight * avg_idle;
+		span_avg = sd->span_weight * avg_idle;
 		if (span_avg > 4*avg_cost)
 			nr = div_u64(span_avg, avg_cost);
 		else
 			nr = 4;
-	}
-
-	time = cpu_clock(this);
 
-	cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr);
+		time = cpu_clock(this);
+	}
 
 	for_each_cpu_wrap(cpu, cpus, target) {
-		if (!--nr)
-			return -1;
-		if (available_idle_cpu(cpu) || sched_idle_cpu(cpu))
-			break;
+		if (smt) {
+			i = select_idle_core(p, cpu, cpus, &idle_cpu);
+			if ((unsigned int)i < nr_cpumask_bits)
+				return i;
+
+		} else {
+			if (!--nr)
+				return -1;
+			idle_cpu = __select_idle_cpu(cpu);
+			if ((unsigned int)idle_cpu < nr_cpumask_bits)
+				break;
+		}
 	}
 
-	time = cpu_clock(this) - time;
-	update_avg(&this_sd->avg_scan_cost, time);
+	if (smt)
+		set_idle_cores(this, false);
+
+	if (sched_feat(SIS_PROP) && !smt) {
+		time = cpu_clock(this) - time;
+		update_avg(&this_sd->avg_scan_cost, time);
+	}
 
-	return cpu;
+	return idle_cpu;
 }
 
 /*
@@ -6172,21 +6189,21 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t
 static int
 select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target)
 {
-	unsigned long best_cap = 0;
+	unsigned long task_util, best_cap = 0;
 	int cpu, best_cpu = -1;
 	struct cpumask *cpus;
 
-	sync_entity_load_avg(&p->se);
-
 	cpus = this_cpu_cpumask_var_ptr(select_idle_mask);
 	cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr);
 
+	task_util = uclamp_task_util(p);
+
 	for_each_cpu_wrap(cpu, cpus, target) {
 		unsigned long cpu_cap = capacity_of(cpu);
 
 		if (!available_idle_cpu(cpu) && !sched_idle_cpu(cpu))
 			continue;
-		if (task_fits_capacity(p, cpu_cap))
+		if (fits_capacity(task_util, cpu_cap))
 			return cpu;
 
 		if (cpu_cap > best_cap) {
@@ -6198,44 +6215,42 @@ select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target)
 	return best_cpu;
 }
 
+static inline bool asym_fits_capacity(int task_util, int cpu)
+{
+	if (static_branch_unlikely(&sched_asym_cpucapacity))
+		return fits_capacity(task_util, capacity_of(cpu));
+
+	return true;
+}
+
 /*
  * Try and locate an idle core/thread in the LLC cache domain.
  */
 static int select_idle_sibling(struct task_struct *p, int prev, int target)
 {
 	struct sched_domain *sd;
+	unsigned long task_util;
 	int i, recent_used_cpu;
 
 	/*
-	 * For asymmetric CPU capacity systems, our domain of interest is
-	 * sd_asym_cpucapacity rather than sd_llc.
+	 * On asymmetric system, update task utilization because we will check
+	 * that the task fits with cpu's capacity.
 	 */
 	if (static_branch_unlikely(&sched_asym_cpucapacity)) {
-		sd = rcu_dereference(per_cpu(sd_asym_cpucapacity, target));
-		/*
-		 * On an asymmetric CPU capacity system where an exclusive
-		 * cpuset defines a symmetric island (i.e. one unique
-		 * capacity_orig value through the cpuset), the key will be set
-		 * but the CPUs within that cpuset will not have a domain with
-		 * SD_ASYM_CPUCAPACITY. These should follow the usual symmetric
-		 * capacity path.
-		 */
-		if (!sd)
-			goto symmetric;
-
-		i = select_idle_capacity(p, sd, target);
-		return ((unsigned)i < nr_cpumask_bits) ? i : target;
+		sync_entity_load_avg(&p->se);
+		task_util = uclamp_task_util(p);
 	}
 
-symmetric:
-	if (available_idle_cpu(target) || sched_idle_cpu(target))
+	if ((available_idle_cpu(target) || sched_idle_cpu(target)) &&
+	    asym_fits_capacity(task_util, target))
 		return target;
 
 	/*
 	 * If the previous CPU is cache affine and idle, don't be stupid:
 	 */
 	if (prev != target && cpus_share_cache(prev, target) &&
-	    (available_idle_cpu(prev) || sched_idle_cpu(prev)))
+	    (available_idle_cpu(prev) || sched_idle_cpu(prev)) &&
+	    asym_fits_capacity(task_util, prev))
 		return prev;
 
 	/*
@@ -6258,7 +6273,8 @@ symmetric:
 	    recent_used_cpu != target &&
 	    cpus_share_cache(recent_used_cpu, target) &&
 	    (available_idle_cpu(recent_used_cpu) || sched_idle_cpu(recent_used_cpu)) &&
-	    cpumask_test_cpu(p->recent_used_cpu, p->cpus_ptr)) {
+	    cpumask_test_cpu(p->recent_used_cpu, p->cpus_ptr) &&
+	    asym_fits_capacity(task_util, recent_used_cpu)) {
 		/*
 		 * Replace recent_used_cpu with prev as it is a potential
 		 * candidate for the next wake:
@@ -6267,27 +6283,39 @@ symmetric:
 		return recent_used_cpu;
 	}
 
+	/*
+	 * For asymmetric CPU capacity systems, our domain of interest is
+	 * sd_asym_cpucapacity rather than sd_llc.
+	 */
+	if (static_branch_unlikely(&sched_asym_cpucapacity)) {
+		sd = rcu_dereference(per_cpu(sd_asym_cpucapacity, target));
+		/*
+		 * On an asymmetric CPU capacity system where an exclusive
+		 * cpuset defines a symmetric island (i.e. one unique
+		 * capacity_orig value through the cpuset), the key will be set
+		 * but the CPUs within that cpuset will not have a domain with
+		 * SD_ASYM_CPUCAPACITY. These should follow the usual symmetric
+		 * capacity path.
+		 */
+		if (sd) {
+			i = select_idle_capacity(p, sd, target);
+			return ((unsigned)i < nr_cpumask_bits) ? i : target;
+		}
+	}
+
 	sd = rcu_dereference(per_cpu(sd_llc, target));
 	if (!sd)
 		return target;
 
-	i = select_idle_core(p, sd, target);
-	if ((unsigned)i < nr_cpumask_bits)
-		return i;
-
 	i = select_idle_cpu(p, sd, target);
 	if ((unsigned)i < nr_cpumask_bits)
 		return i;
 
-	i = select_idle_smt(p, sd, target);
-	if ((unsigned)i < nr_cpumask_bits)
-		return i;
-
 	return target;
 }
 
 /**
- * Amount of capacity of a CPU that is (estimated to be) used by CFS tasks
+ * cpu_util - Estimates the amount of capacity of a CPU used by CFS tasks.
  * @cpu: the CPU to get the utilization of
  *
  * The unit of the return value must be the one of capacity so we can compare
@@ -6499,7 +6527,7 @@ compute_energy(struct task_struct *p, int dst_cpu, struct perf_domain *pd)
 		 * is already enough to scale the EM reported power
 		 * consumption at the (eventually clamped) cpu_capacity.
 		 */
-		sum_util += schedutil_cpu_util(cpu, util_cfs, cpu_cap,
+		sum_util += effective_cpu_util(cpu, util_cfs, cpu_cap,
 					       ENERGY_UTIL, NULL);
 
 		/*
@@ -6509,7 +6537,7 @@ compute_energy(struct task_struct *p, int dst_cpu, struct perf_domain *pd)
 		 * NOTE: in case RT tasks are running, by default the
 		 * FREQUENCY_UTIL's utilization can be max OPP.
 		 */
-		cpu_util = schedutil_cpu_util(cpu, util_cfs, cpu_cap,
+		cpu_util = effective_cpu_util(cpu, util_cfs, cpu_cap,
 					      FREQUENCY_UTIL, tsk);
 		max_util = max(max_util, cpu_util);
 	}
@@ -6607,7 +6635,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
 			 * IOW, placing the task there would make the CPU
 			 * overutilized. Take uclamp into account to see how
 			 * much capacity we can get out of the CPU; this is
-			 * aligned with schedutil_cpu_util().
+			 * aligned with sched_cpu_util().
 			 */
 			util = uclamp_rq_util_with(cpu_rq(cpu), util, p);
 			if (!fits_capacity(util, cpu_cap))
@@ -6663,7 +6691,7 @@ fail:
 
 /*
  * select_task_rq_fair: Select target runqueue for the waking task in domains
- * that have the 'sd_flag' flag set. In practice, this is SD_BALANCE_WAKE,
+ * that have the relevant SD flag set. In practice, this is SD_BALANCE_WAKE,
  * SD_BALANCE_FORK, or SD_BALANCE_EXEC.
  *
  * Balances load by selecting the idlest CPU in the idlest group, or under
@@ -6674,15 +6702,17 @@ fail:
  * preempt must be disabled.
  */
 static int
-select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_flags)
+select_task_rq_fair(struct task_struct *p, int prev_cpu, int wake_flags)
 {
+	int sync = (wake_flags & WF_SYNC) && !(current->flags & PF_EXITING);
 	struct sched_domain *tmp, *sd = NULL;
 	int cpu = smp_processor_id();
 	int new_cpu = prev_cpu;
 	int want_affine = 0;
-	int sync = (wake_flags & WF_SYNC) && !(current->flags & PF_EXITING);
+	/* SD_flags and WF_flags share the first nibble */
+	int sd_flag = wake_flags & 0xF;
 
-	if (sd_flag & SD_BALANCE_WAKE) {
+	if (wake_flags & WF_TTWU) {
 		record_wakee(p);
 
 		if (sched_energy_enabled()) {
@@ -6719,9 +6749,8 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
 	if (unlikely(sd)) {
 		/* Slow path */
 		new_cpu = find_idlest_cpu(sd, p, cpu, prev_cpu, sd_flag);
-	} else if (sd_flag & SD_BALANCE_WAKE) { /* XXX always ? */
+	} else if (wake_flags & WF_TTWU) { /* XXX always ? */
 		/* Fast path */
-
 		new_cpu = select_idle_sibling(p, prev_cpu, new_cpu);
 
 		if (want_affine)
@@ -7087,7 +7116,7 @@ done: __maybe_unused;
 	list_move(&p->se.group_node, &rq->cfs_tasks);
 #endif
 
-	if (hrtick_enabled(rq))
+	if (hrtick_enabled_fair(rq))
 		hrtick_start_fair(rq, p);
 
 	update_misfit_status(p, rq);
@@ -8738,6 +8767,16 @@ static bool update_pick_idlest(struct sched_group *idlest,
 }
 
 /*
+ * Allow a NUMA imbalance if busy CPUs is less than 25% of the domain.
+ * This is an approximation as the number of running tasks may not be
+ * related to the number of busy CPUs due to sched_setaffinity.
+ */
+static inline bool allow_numa_imbalance(int dst_running, int dst_weight)
+{
+	return (dst_running < (dst_weight >> 2));
+}
+
+/*
  * find_idlest_group() finds and returns the least busy CPU group within the
  * domain.
  *
@@ -8755,9 +8794,6 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu)
 			.group_type = group_overloaded,
 	};
 
-	imbalance = scale_load_down(NICE_0_LOAD) *
-				(sd->imbalance_pct-100) / 100;
-
 	do {
 		int local_group;
 
@@ -8811,6 +8847,11 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu)
 	switch (local_sgs.group_type) {
 	case group_overloaded:
 	case group_fully_busy:
+
+		/* Calculate allowed imbalance based on load */
+		imbalance = scale_load_down(NICE_0_LOAD) *
+				(sd->imbalance_pct-100) / 100;
+
 		/*
 		 * When comparing groups across NUMA domains, it's possible for
 		 * the local domain to be very lightly loaded relative to the
@@ -8867,7 +8908,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu)
 			 * a real need of migration, periodic load balance will
 			 * take care of it.
 			 */
-			if (local_sgs.idle_cpus)
+			if (allow_numa_imbalance(local_sgs.sum_nr_running, sd->span_weight))
 				return NULL;
 		}
 
@@ -8969,16 +9010,19 @@ next_group:
 	}
 }
 
-static inline long adjust_numa_imbalance(int imbalance, int nr_running)
+#define NUMA_IMBALANCE_MIN 2
+
+static inline long adjust_numa_imbalance(int imbalance,
+				int dst_running, int dst_weight)
 {
-	unsigned int imbalance_min;
+	if (!allow_numa_imbalance(dst_running, dst_weight))
+		return imbalance;
 
 	/*
 	 * Allow a small imbalance based on a simple pair of communicating
-	 * tasks that remain local when the source domain is almost idle.
+	 * tasks that remain local when the destination is lightly loaded.
 	 */
-	imbalance_min = 2;
-	if (nr_running <= imbalance_min)
+	if (imbalance <= NUMA_IMBALANCE_MIN)
 		return 0;
 
 	return imbalance;
@@ -9031,7 +9075,8 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
 	 * emptying busiest.
 	 */
 	if (local->group_type == group_has_spare) {
-		if (busiest->group_type > group_fully_busy) {
+		if ((busiest->group_type > group_fully_busy) &&
+		    !(env->sd->flags & SD_SHARE_PKG_RESOURCES)) {
 			/*
 			 * If busiest is overloaded, try to fill spare
 			 * capacity. This might end up creating spare capacity
@@ -9080,9 +9125,10 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
 		}
 
 		/* Consider allowing a small imbalance between NUMA groups */
-		if (env->sd->flags & SD_NUMA)
+		if (env->sd->flags & SD_NUMA) {
 			env->imbalance = adjust_numa_imbalance(env->imbalance,
-						busiest->sum_nr_running);
+				busiest->sum_nr_running, busiest->group_weight);
+		}
 
 		return;
 	}
@@ -9327,8 +9373,11 @@ static struct rq *find_busiest_queue(struct lb_env *env,
 		if (rt > env->fbq_type)
 			continue;
 
-		capacity = capacity_of(i);
 		nr_running = rq->cfs.h_nr_running;
+		if (!nr_running)
+			continue;
+
+		capacity = capacity_of(i);
 
 		/*
 		 * For ASYM_CPUCAPACITY domains, don't pick a CPU that could
@@ -9434,13 +9483,32 @@ asym_active_balance(struct lb_env *env)
 }
 
 static inline bool
-voluntary_active_balance(struct lb_env *env)
+imbalanced_active_balance(struct lb_env *env)
+{
+	struct sched_domain *sd = env->sd;
+
+	/*
+	 * The imbalanced case includes the case of pinned tasks preventing a fair
+	 * distribution of the load on the system but also the even distribution of the
+	 * threads on a system with spare capacity
+	 */
+	if ((env->migration_type == migrate_task) &&
+	    (sd->nr_balance_failed > sd->cache_nice_tries+2))
+		return 1;
+
+	return 0;
+}
+
+static int need_active_balance(struct lb_env *env)
 {
 	struct sched_domain *sd = env->sd;
 
 	if (asym_active_balance(env))
 		return 1;
 
+	if (imbalanced_active_balance(env))
+		return 1;
+
 	/*
 	 * The dst_cpu is idle and the src_cpu CPU has only 1 CFS task.
 	 * It's worth migrating the task if the src_cpu's capacity is reduced
@@ -9460,16 +9528,6 @@ voluntary_active_balance(struct lb_env *env)
 	return 0;
 }
 
-static int need_active_balance(struct lb_env *env)
-{
-	struct sched_domain *sd = env->sd;
-
-	if (voluntary_active_balance(env))
-		return 1;
-
-	return unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2);
-}
-
 static int active_load_balance_cpu_stop(void *data);
 
 static int should_we_balance(struct lb_env *env)
@@ -9561,6 +9619,8 @@ redo:
 	env.src_rq = busiest;
 
 	ld_moved = 0;
+	/* Clear this flag as soon as we find a pullable task */
+	env.flags |= LBF_ALL_PINNED;
 	if (busiest->nr_running > 1) {
 		/*
 		 * Attempt to move tasks. If find_busiest_group has found
@@ -9568,7 +9628,6 @@ redo:
 		 * still unbalanced. ld_moved simply stays zero, so it is
 		 * correctly treated as an imbalance.
 		 */
-		env.flags |= LBF_ALL_PINNED;
 		env.loop_max  = min(sysctl_sched_nr_migrate, busiest->nr_running);
 
 more_balance:
@@ -9694,10 +9753,12 @@ more_balance:
 			if (!cpumask_test_cpu(this_cpu, busiest->curr->cpus_ptr)) {
 				raw_spin_unlock_irqrestore(&busiest->lock,
 							    flags);
-				env.flags |= LBF_ALL_PINNED;
 				goto out_one_pinned;
 			}
 
+			/* Record that we found at least one task that could run on this_cpu */
+			env.flags &= ~LBF_ALL_PINNED;
+
 			/*
 			 * ->active_balance synchronizes accesses to
 			 * ->active_balance_work.  Once set, it's cleared
@@ -9719,21 +9780,13 @@ more_balance:
 			/* We've kicked active balancing, force task migration. */
 			sd->nr_balance_failed = sd->cache_nice_tries+1;
 		}
-	} else
+	} else {
 		sd->nr_balance_failed = 0;
+	}
 
-	if (likely(!active_balance) || voluntary_active_balance(&env)) {
+	if (likely(!active_balance) || need_active_balance(&env)) {
 		/* We were unbalanced, so reset the balancing interval */
 		sd->balance_interval = sd->min_interval;
-	} else {
-		/*
-		 * If we've begun active balancing, start to back off. This
-		 * case may not be covered by the all_pinned logic if there
-		 * is only 1 task on the busy runqueue (because we don't call
-		 * detach_tasks).
-		 */
-		if (sd->balance_interval < sd->max_interval)
-			sd->balance_interval *= 2;
 	}
 
 	goto out;
@@ -10047,6 +10100,10 @@ static inline int find_new_ilb(void)
 
 	for_each_cpu_and(ilb, nohz.idle_cpus_mask,
 			      housekeeping_cpumask(HK_FLAG_MISC)) {
+
+		if (ilb == smp_processor_id())
+			continue;
+
 		if (idle_cpu(ilb))
 			return ilb;
 	}
@@ -10484,7 +10541,7 @@ static inline void nohz_newidle_balance(struct rq *this_rq) { }
 #endif /* CONFIG_NO_HZ_COMMON */
 
 /*
- * idle_balance is called by schedule() if this_cpu is about to become
+ * newidle_balance is called by schedule() if this_cpu is about to become
  * idle. Attempts to pull tasks from other CPUs.
  *
  * Returns:
@@ -10634,8 +10691,11 @@ static __latent_entropy void run_rebalance_domains(struct softirq_action *h)
  */
 void trigger_load_balance(struct rq *rq)
 {
-	/* Don't need to rebalance while attached to NULL domain */
-	if (unlikely(on_null_domain(rq)))
+	/*
+	 * Don't need to rebalance while attached to NULL domain or
+	 * runqueue CPU is not active
+	 */
+	if (unlikely(on_null_domain(rq) || !cpu_active(cpu_of(rq))))
 		return;
 
 	if (time_after_eq(jiffies, rq->next_balance))
@@ -10740,7 +10800,7 @@ prio_changed_fair(struct rq *rq, struct task_struct *p, int oldprio)
 	 * our priority decreased, or if we are not currently running on
 	 * this runqueue and our priority is higher than the current's
 	 */
-	if (rq->curr == p) {
+	if (task_current(rq, p)) {
 		if (p->prio > oldprio)
 			resched_curr(rq);
 	} else
@@ -10873,7 +10933,7 @@ static void switched_to_fair(struct rq *rq, struct task_struct *p)
 		 * kick off the schedule if running, otherwise just see
 		 * if we can still preempt the current task.
 		 */
-		if (rq->curr == p)
+		if (task_current(rq, p))
 			resched_curr(rq);
 		else
 			check_preempt_curr(rq, p, 0);
@@ -11158,8 +11218,8 @@ static unsigned int get_rr_interval_fair(struct rq *rq, struct task_struct *task
 /*
  * All the scheduling class methods:
  */
-const struct sched_class fair_sched_class
-	__attribute__((section("__fair_sched_class"))) = {
+DEFINE_SCHED_CLASS(fair) = {
+
 	.enqueue_task		= enqueue_task_fair,
 	.dequeue_task		= dequeue_task_fair,
 	.yield_task		= yield_task_fair,