1 files changed, 214 insertions, 271 deletions

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index d71109321841..c95880e216f6 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -369,8 +369,9 @@ static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq)
 }
 
 /* Iterate thr' all leaf cfs_rq's on a runqueue */
-#define for_each_leaf_cfs_rq(rq, cfs_rq) \
-	list_for_each_entry_rcu(cfs_rq, &rq->leaf_cfs_rq_list, leaf_cfs_rq_list)
+#define for_each_leaf_cfs_rq_safe(rq, cfs_rq, pos)			\
+	list_for_each_entry_safe(cfs_rq, pos, &rq->leaf_cfs_rq_list,	\
+				 leaf_cfs_rq_list)
 
 /* Do the two (enqueued) entities belong to the same group ? */
 static inline struct cfs_rq *
@@ -463,8 +464,8 @@ static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq)
 {
 }
 
-#define for_each_leaf_cfs_rq(rq, cfs_rq) \
-		for (cfs_rq = &rq->cfs; cfs_rq; cfs_rq = NULL)
+#define for_each_leaf_cfs_rq_safe(rq, cfs_rq, pos)	\
+		for (cfs_rq = &rq->cfs, pos = NULL; cfs_rq; cfs_rq = pos)
 
 static inline struct sched_entity *parent_entity(struct sched_entity *se)
 {
@@ -1381,7 +1382,6 @@ static unsigned long weighted_cpuload(const int cpu);
 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);
-static long effective_load(struct task_group *tg, int cpu, long wl, long wg);
 
 /* Cached statistics for all CPUs within a node */
 struct numa_stats {
@@ -2469,7 +2469,8 @@ void task_numa_work(struct callback_head *work)
 		return;
 
 
-	down_read(&mm->mmap_sem);
+	if (!down_read_trylock(&mm->mmap_sem))
+		return;
 	vma = find_vma(mm, start);
 	if (!vma) {
 		reset_ptenuma_scan(p);
@@ -2584,6 +2585,60 @@ void task_tick_numa(struct rq *rq, struct task_struct *curr)
 		}
 	}
 }
+
+/*
+ * Can a task be moved from prev_cpu to this_cpu without causing a load
+ * imbalance that would trigger the load balancer?
+ */
+static inline bool numa_wake_affine(struct sched_domain *sd,
+				    struct task_struct *p, int this_cpu,
+				    int prev_cpu, int sync)
+{
+	struct numa_stats prev_load, this_load;
+	s64 this_eff_load, prev_eff_load;
+
+	update_numa_stats(&prev_load, cpu_to_node(prev_cpu));
+	update_numa_stats(&this_load, cpu_to_node(this_cpu));
+
+	/*
+	 * If sync wakeup then subtract the (maximum possible)
+	 * effect of the currently running task from the load
+	 * of the current CPU:
+	 */
+	if (sync) {
+		unsigned long current_load = task_h_load(current);
+
+		if (this_load.load > current_load)
+			this_load.load -= current_load;
+		else
+			this_load.load = 0;
+	}
+
+	/*
+	 * In low-load situations, where this_cpu's node is idle due to the
+	 * sync cause above having dropped this_load.load to 0, move the task.
+	 * Moving to an idle socket will not create a bad imbalance.
+	 *
+	 * Otherwise check if the nodes are near enough in load to allow this
+	 * task to be woken on this_cpu's node.
+	 */
+	if (this_load.load > 0) {
+		unsigned long task_load = task_h_load(p);
+
+		this_eff_load = 100;
+		this_eff_load *= prev_load.compute_capacity;
+
+		prev_eff_load = 100 + (sd->imbalance_pct - 100) / 2;
+		prev_eff_load *= this_load.compute_capacity;
+
+		this_eff_load *= this_load.load + task_load;
+		prev_eff_load *= prev_load.load - task_load;
+
+		return this_eff_load <= prev_eff_load;
+	}
+
+	return true;
+}
 #else
 static void task_tick_numa(struct rq *rq, struct task_struct *curr)
 {
@@ -2596,6 +2651,15 @@ static inline void account_numa_enqueue(struct rq *rq, struct task_struct *p)
 static inline void account_numa_dequeue(struct rq *rq, struct task_struct *p)
 {
 }
+
+#ifdef CONFIG_SMP
+static inline bool numa_wake_affine(struct sched_domain *sd,
+				    struct task_struct *p, int this_cpu,
+				    int prev_cpu, int sync)
+{
+	return true;
+}
+#endif /* !SMP */
 #endif /* CONFIG_NUMA_BALANCING */
 
 static void
@@ -2916,12 +2980,12 @@ ___update_load_avg(u64 now, int cpu, struct sched_avg *sa,
 	/*
 	 * Step 2: update *_avg.
 	 */
-	sa->load_avg = div_u64(sa->load_sum, LOAD_AVG_MAX);
+	sa->load_avg = div_u64(sa->load_sum, LOAD_AVG_MAX - 1024 + sa->period_contrib);
 	if (cfs_rq) {
 		cfs_rq->runnable_load_avg =
-			div_u64(cfs_rq->runnable_load_sum, LOAD_AVG_MAX);
+			div_u64(cfs_rq->runnable_load_sum, LOAD_AVG_MAX - 1024 + sa->period_contrib);
 	}
-	sa->util_avg = sa->util_sum / LOAD_AVG_MAX;
+	sa->util_avg = sa->util_sum / (LOAD_AVG_MAX - 1024 + sa->period_contrib);
 
 	return 1;
 }
@@ -2982,8 +3046,7 @@ __update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq)
  * differential update where we store the last value we propagated. This in
  * turn allows skipping updates if the differential is 'small'.
  *
- * Updating tg's load_avg is necessary before update_cfs_share() (which is
- * done) and effective_load() (which is not done because it is too costly).
+ * Updating tg's load_avg is necessary before update_cfs_share().
  */
 static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force)
 {
@@ -3563,7 +3626,7 @@ static inline void check_schedstat_required(void)
 			trace_sched_stat_runtime_enabled())  {
 		printk_deferred_once("Scheduler tracepoints stat_sleep, stat_iowait, "
 			     "stat_blocked and stat_runtime require the "
-			     "kernel parameter schedstats=enabled or "
+			     "kernel parameter schedstats=enable or "
 			     "kernel.sched_schedstats=1\n");
 	}
 #endif
@@ -4642,24 +4705,43 @@ static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
 	hrtimer_cancel(&cfs_b->slack_timer);
 }
 
+/*
+ * Both these cpu hotplug callbacks race against unregister_fair_sched_group()
+ *
+ * The race is harmless, since modifying bandwidth settings of unhooked group
+ * bits doesn't do much.
+ */
+
+/* cpu online calback */
 static void __maybe_unused update_runtime_enabled(struct rq *rq)
 {
-	struct cfs_rq *cfs_rq;
+	struct task_group *tg;
+
+	lockdep_assert_held(&rq->lock);
 
-	for_each_leaf_cfs_rq(rq, cfs_rq) {
-		struct cfs_bandwidth *cfs_b = &cfs_rq->tg->cfs_bandwidth;
+	rcu_read_lock();
+	list_for_each_entry_rcu(tg, &task_groups, list) {
+		struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth;
+		struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)];
 
 		raw_spin_lock(&cfs_b->lock);
 		cfs_rq->runtime_enabled = cfs_b->quota != RUNTIME_INF;
 		raw_spin_unlock(&cfs_b->lock);
 	}
+	rcu_read_unlock();
 }
 
+/* cpu offline callback */
 static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq)
 {
-	struct cfs_rq *cfs_rq;
+	struct task_group *tg;
+
+	lockdep_assert_held(&rq->lock);
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(tg, &task_groups, list) {
+		struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)];
 
-	for_each_leaf_cfs_rq(rq, cfs_rq) {
 		if (!cfs_rq->runtime_enabled)
 			continue;
 
@@ -4677,6 +4759,7 @@ static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq)
 		if (cfs_rq_throttled(cfs_rq))
 			unthrottle_cfs_rq(cfs_rq);
 	}
+	rcu_read_unlock();
 }
 
 #else /* CONFIG_CFS_BANDWIDTH */
@@ -5215,126 +5298,6 @@ static unsigned long cpu_avg_load_per_task(int cpu)
 	return 0;
 }
 
-#ifdef CONFIG_FAIR_GROUP_SCHED
-/*
- * effective_load() calculates the load change as seen from the root_task_group
- *
- * Adding load to a group doesn't make a group heavier, but can cause movement
- * of group shares between cpus. Assuming the shares were perfectly aligned one
- * can calculate the shift in shares.
- *
- * Calculate the effective load difference if @wl is added (subtracted) to @tg
- * on this @cpu and results in a total addition (subtraction) of @wg to the
- * total group weight.
- *
- * Given a runqueue weight distribution (rw_i) we can compute a shares
- * distribution (s_i) using:
- *
- *   s_i = rw_i / \Sum rw_j						(1)
- *
- * Suppose we have 4 CPUs and our @tg is a direct child of the root group and
- * has 7 equal weight tasks, distributed as below (rw_i), with the resulting
- * shares distribution (s_i):
- *
- *   rw_i = {   2,   4,   1,   0 }
- *   s_i  = { 2/7, 4/7, 1/7,   0 }
- *
- * As per wake_affine() we're interested in the load of two CPUs (the CPU the
- * task used to run on and the CPU the waker is running on), we need to
- * compute the effect of waking a task on either CPU and, in case of a sync
- * wakeup, compute the effect of the current task going to sleep.
- *
- * So for a change of @wl to the local @cpu with an overall group weight change
- * of @wl we can compute the new shares distribution (s'_i) using:
- *
- *   s'_i = (rw_i + @wl) / (@wg + \Sum rw_j)				(2)
- *
- * Suppose we're interested in CPUs 0 and 1, and want to compute the load
- * differences in waking a task to CPU 0. The additional task changes the
- * weight and shares distributions like:
- *
- *   rw'_i = {   3,   4,   1,   0 }
- *   s'_i  = { 3/8, 4/8, 1/8,   0 }
- *
- * We can then compute the difference in effective weight by using:
- *
- *   dw_i = S * (s'_i - s_i)						(3)
- *
- * Where 'S' is the group weight as seen by its parent.
- *
- * Therefore the effective change in loads on CPU 0 would be 5/56 (3/8 - 2/7)
- * times the weight of the group. The effect on CPU 1 would be -4/56 (4/8 -
- * 4/7) times the weight of the group.
- */
-static long effective_load(struct task_group *tg, int cpu, long wl, long wg)
-{
-	struct sched_entity *se = tg->se[cpu];
-
-	if (!tg->parent)	/* the trivial, non-cgroup case */
-		return wl;
-
-	for_each_sched_entity(se) {
-		struct cfs_rq *cfs_rq = se->my_q;
-		long W, w = cfs_rq_load_avg(cfs_rq);
-
-		tg = cfs_rq->tg;
-
-		/*
-		 * W = @wg + \Sum rw_j
-		 */
-		W = wg + atomic_long_read(&tg->load_avg);
-
-		/* Ensure \Sum rw_j >= rw_i */
-		W -= cfs_rq->tg_load_avg_contrib;
-		W += w;
-
-		/*
-		 * w = rw_i + @wl
-		 */
-		w += wl;
-
-		/*
-		 * wl = S * s'_i; see (2)
-		 */
-		if (W > 0 && w < W)
-			wl = (w * (long)scale_load_down(tg->shares)) / W;
-		else
-			wl = scale_load_down(tg->shares);
-
-		/*
-		 * Per the above, wl is the new se->load.weight value; since
-		 * those are clipped to [MIN_SHARES, ...) do so now. See
-		 * calc_cfs_shares().
-		 */
-		if (wl < MIN_SHARES)
-			wl = MIN_SHARES;
-
-		/*
-		 * wl = dw_i = S * (s'_i - s_i); see (3)
-		 */
-		wl -= se->avg.load_avg;
-
-		/*
-		 * Recursively apply this logic to all parent groups to compute
-		 * the final effective load change on the root group. Since
-		 * only the @tg group gets extra weight, all parent groups can
-		 * only redistribute existing shares. @wl is the shift in shares
-		 * resulting from this level per the above.
-		 */
-		wg = 0;
-	}
-
-	return wl;
-}
-#else
-
-static long effective_load(struct task_group *tg, int cpu, long wl, long wg)
-{
-	return wl;
-}
-
-#endif
-
 static void record_wakee(struct task_struct *p)
 {
 	/*
@@ -5385,67 +5348,25 @@ static int wake_wide(struct task_struct *p)
 static int wake_affine(struct sched_domain *sd, struct task_struct *p,
 		       int prev_cpu, int sync)
 {
-	s64 this_load, load;
-	s64 this_eff_load, prev_eff_load;
-	int idx, this_cpu;
-	struct task_group *tg;
-	unsigned long weight;
-	int balanced;
-
-	idx	  = sd->wake_idx;
-	this_cpu  = smp_processor_id();
-	load	  = source_load(prev_cpu, idx);
-	this_load = target_load(this_cpu, idx);
+	int this_cpu = smp_processor_id();
+	bool affine = false;
 
 	/*
-	 * If sync wakeup then subtract the (maximum possible)
-	 * effect of the currently running task from the load
-	 * of the current CPU:
-	 */
-	if (sync) {
-		tg = task_group(current);
-		weight = current->se.avg.load_avg;
-
-		this_load += effective_load(tg, this_cpu, -weight, -weight);
-		load += effective_load(tg, prev_cpu, 0, -weight);
-	}
-
-	tg = task_group(p);
-	weight = p->se.avg.load_avg;
-
-	/*
-	 * In low-load situations, where prev_cpu is idle and this_cpu is idle
-	 * due to the sync cause above having dropped this_load to 0, we'll
-	 * always have an imbalance, but there's really nothing you can do
-	 * about that, so that's good too.
-	 *
-	 * Otherwise check if either cpus are near enough in load to allow this
-	 * task to be woken on this_cpu.
+	 * Common case: CPUs are in the same socket, and select_idle_sibling()
+	 * will do its thing regardless of what we return:
 	 */
-	this_eff_load = 100;
-	this_eff_load *= capacity_of(prev_cpu);
-
-	prev_eff_load = 100 + (sd->imbalance_pct - 100) / 2;
-	prev_eff_load *= capacity_of(this_cpu);
-
-	if (this_load > 0) {
-		this_eff_load *= this_load +
-			effective_load(tg, this_cpu, weight, weight);
-
-		prev_eff_load *= load + effective_load(tg, prev_cpu, 0, weight);
-	}
-
-	balanced = this_eff_load <= prev_eff_load;
+	if (cpus_share_cache(prev_cpu, this_cpu))
+		affine = true;
+	else
+		affine = numa_wake_affine(sd, p, this_cpu, prev_cpu, sync);
 
 	schedstat_inc(p->se.statistics.nr_wakeups_affine_attempts);
+	if (affine) {
+		schedstat_inc(sd->ttwu_move_affine);
+		schedstat_inc(p->se.statistics.nr_wakeups_affine);
+	}
 
-	if (!balanced)
-		return 0;
-
-	schedstat_inc(sd->ttwu_move_affine);
-	schedstat_inc(p->se.statistics.nr_wakeups_affine);
-
-	return 1;
+	return affine;
 }
 
 static inline int task_util(struct task_struct *p);
@@ -5484,12 +5405,12 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
 		int i;
 
 		/* Skip over this group if it has no CPUs allowed */
-		if (!cpumask_intersects(sched_group_cpus(group),
+		if (!cpumask_intersects(sched_group_span(group),
 					&p->cpus_allowed))
 			continue;
 
 		local_group = cpumask_test_cpu(this_cpu,
-					       sched_group_cpus(group));
+					       sched_group_span(group));
 
 		/*
 		 * Tally up the load of all CPUs in the group and find
@@ -5499,7 +5420,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
 		runnable_load = 0;
 		max_spare_cap = 0;
 
-		for_each_cpu(i, sched_group_cpus(group)) {
+		for_each_cpu(i, sched_group_span(group)) {
 			/* Bias balancing toward cpus of our domain */
 			if (local_group)
 				load = source_load(i, load_idx);
@@ -5602,10 +5523,10 @@ find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
 
 	/* Check if we have any choice: */
 	if (group->group_weight == 1)
-		return cpumask_first(sched_group_cpus(group));
+		return cpumask_first(sched_group_span(group));
 
 	/* Traverse only the allowed CPUs */
-	for_each_cpu_and(i, sched_group_cpus(group), &p->cpus_allowed) {
+	for_each_cpu_and(i, sched_group_span(group), &p->cpus_allowed) {
 		if (idle_cpu(i)) {
 			struct rq *rq = cpu_rq(i);
 			struct cpuidle_state *idle = idle_get_state(rq);
@@ -5640,43 +5561,6 @@ find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
 	return shallowest_idle_cpu != -1 ? shallowest_idle_cpu : least_loaded_cpu;
 }
 
-/*
- * Implement a for_each_cpu() variant that starts the scan at a given cpu
- * (@start), and wraps around.
- *
- * This is used to scan for idle CPUs; such that not all CPUs looking for an
- * idle CPU find the same CPU. The down-side is that tasks tend to cycle
- * through the LLC domain.
- *
- * Especially tbench is found sensitive to this.
- */
-
-static int cpumask_next_wrap(int n, const struct cpumask *mask, int start, int *wrapped)
-{
-	int next;
-
-again:
-	next = find_next_bit(cpumask_bits(mask), nr_cpumask_bits, n+1);
-
-	if (*wrapped) {
-		if (next >= start)
-			return nr_cpumask_bits;
-	} else {
-		if (next >= nr_cpumask_bits) {
-			*wrapped = 1;
-			n = -1;
-			goto again;
-		}
-	}
-
-	return next;
-}
-
-#define for_each_cpu_wrap(cpu, mask, start, wrap)				\
-	for ((wrap) = 0, (cpu) = (start)-1;					\
-		(cpu) = cpumask_next_wrap((cpu), (mask), (start), &(wrap)),	\
-		(cpu) < nr_cpumask_bits; )
-
 #ifdef CONFIG_SCHED_SMT
 
 static inline void set_idle_cores(int cpu, int val)
@@ -5736,7 +5620,7 @@ unlock:
 static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int target)
 {
 	struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_idle_mask);
-	int core, cpu, wrap;
+	int core, cpu;
 
 	if (!static_branch_likely(&sched_smt_present))
 		return -1;
@@ -5746,7 +5630,7 @@ static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int
 
 	cpumask_and(cpus, sched_domain_span(sd), &p->cpus_allowed);
 
-	for_each_cpu_wrap(core, cpus, target, wrap) {
+	for_each_cpu_wrap(core, cpus, target) {
 		bool idle = true;
 
 		for_each_cpu(cpu, cpu_smt_mask(core)) {
@@ -5809,27 +5693,38 @@ 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 sched_domain *this_sd;
-	u64 avg_cost, avg_idle = this_rq()->avg_idle;
+	u64 avg_cost, avg_idle;
 	u64 time, cost;
 	s64 delta;
-	int cpu, wrap;
+	int cpu, nr = INT_MAX;
 
 	this_sd = rcu_dereference(*this_cpu_ptr(&sd_llc));
 	if (!this_sd)
 		return -1;
 
-	avg_cost = this_sd->avg_scan_cost;
-
 	/*
 	 * Due to large variance we need a large fuzz factor; hackbench in
 	 * particularly is sensitive here.
 	 */
-	if (sched_feat(SIS_AVG_CPU) && (avg_idle / 512) < avg_cost)
+	avg_idle = this_rq()->avg_idle / 512;
+	avg_cost = this_sd->avg_scan_cost + 1;
+
+	if (sched_feat(SIS_AVG_CPU) && avg_idle < avg_cost)
 		return -1;
 
+	if (sched_feat(SIS_PROP)) {
+		u64 span_avg = sd->span_weight * avg_idle;
+		if (span_avg > 4*avg_cost)
+			nr = div_u64(span_avg, avg_cost);
+		else
+			nr = 4;
+	}
+
 	time = local_clock();
 
-	for_each_cpu_wrap(cpu, sched_domain_span(sd), target, wrap) {
+	for_each_cpu_wrap(cpu, sched_domain_span(sd), target) {
+		if (!--nr)
+			return -1;
 		if (!cpumask_test_cpu(cpu, &p->cpus_allowed))
 			continue;
 		if (idle_cpu(cpu))
@@ -6011,11 +5906,15 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
 
 	if (affine_sd) {
 		sd = NULL; /* Prefer wake_affine over balance flags */
-		if (cpu != prev_cpu && wake_affine(affine_sd, p, prev_cpu, sync))
+		if (cpu == prev_cpu)
+			goto pick_cpu;
+
+		if (wake_affine(affine_sd, p, prev_cpu, sync))
 			new_cpu = cpu;
 	}
 
 	if (!sd) {
+ pick_cpu:
 		if (sd_flag & SD_BALANCE_WAKE) /* XXX always ? */
 			new_cpu = select_idle_sibling(p, prev_cpu, new_cpu);
 
@@ -6168,8 +6067,11 @@ static void set_last_buddy(struct sched_entity *se)
 	if (entity_is_task(se) && unlikely(task_of(se)->policy == SCHED_IDLE))
 		return;
 
-	for_each_sched_entity(se)
+	for_each_sched_entity(se) {
+		if (SCHED_WARN_ON(!se->on_rq))
+			return;
 		cfs_rq_of(se)->last = se;
+	}
 }
 
 static void set_next_buddy(struct sched_entity *se)
@@ -6177,8 +6079,11 @@ static void set_next_buddy(struct sched_entity *se)
 	if (entity_is_task(se) && unlikely(task_of(se)->policy == SCHED_IDLE))
 		return;
 
-	for_each_sched_entity(se)
+	for_each_sched_entity(se) {
+		if (SCHED_WARN_ON(!se->on_rq))
+			return;
 		cfs_rq_of(se)->next = se;
+	}
 }
 
 static void set_skip_buddy(struct sched_entity *se)
@@ -6686,6 +6591,10 @@ static int migrate_degrades_locality(struct task_struct *p, struct lb_env *env)
 	if (dst_nid == p->numa_preferred_nid)
 		return 0;
 
+	/* Leaving a core idle is often worse than degrading locality. */
+	if (env->idle != CPU_NOT_IDLE)
+		return -1;
+
 	if (numa_group) {
 		src_faults = group_faults(p, src_nid);
 		dst_faults = group_faults(p, dst_nid);
@@ -6737,10 +6646,10 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
 		 * our sched_group. We may want to revisit it if we couldn't
 		 * meet load balance goals by pulling other tasks on src_cpu.
 		 *
-		 * Also avoid computing new_dst_cpu if we have already computed
-		 * one in current iteration.
+		 * Avoid computing new_dst_cpu for NEWLY_IDLE or if we have
+		 * already computed one in current iteration.
 		 */
-		if (!env->dst_grpmask || (env->flags & LBF_DST_PINNED))
+		if (env->idle == CPU_NEWLY_IDLE || (env->flags & LBF_DST_PINNED))
 			return 0;
 
 		/* Prevent to re-select dst_cpu via env's cpus */
@@ -6970,10 +6879,28 @@ static void attach_tasks(struct lb_env *env)
 }
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
+
+static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq)
+{
+	if (cfs_rq->load.weight)
+		return false;
+
+	if (cfs_rq->avg.load_sum)
+		return false;
+
+	if (cfs_rq->avg.util_sum)
+		return false;
+
+	if (cfs_rq->runnable_load_sum)
+		return false;
+
+	return true;
+}
+
 static void update_blocked_averages(int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
-	struct cfs_rq *cfs_rq;
+	struct cfs_rq *cfs_rq, *pos;
 	struct rq_flags rf;
 
 	rq_lock_irqsave(rq, &rf);
@@ -6983,7 +6910,7 @@ static void update_blocked_averages(int cpu)
 	 * Iterates the task_group tree in a bottom up fashion, see
 	 * list_add_leaf_cfs_rq() for details.
 	 */
-	for_each_leaf_cfs_rq(rq, cfs_rq) {
+	for_each_leaf_cfs_rq_safe(rq, cfs_rq, pos) {
 		struct sched_entity *se;
 
 		/* throttled entities do not contribute to load */
@@ -6997,6 +6924,13 @@ static void update_blocked_averages(int cpu)
 		se = cfs_rq->tg->se[cpu];
 		if (se && !skip_blocked_update(se))
 			update_load_avg(se, 0);
+
+		/*
+		 * There can be a lot of idle CPU cgroups.  Don't let fully
+		 * decayed cfs_rqs linger on the list.
+		 */
+		if (cfs_rq_is_decayed(cfs_rq))
+			list_del_leaf_cfs_rq(cfs_rq);
 	}
 	rq_unlock_irqrestore(rq, &rf);
 }
@@ -7229,7 +7163,7 @@ void update_group_capacity(struct sched_domain *sd, int cpu)
 		 * span the current group.
 		 */
 
-		for_each_cpu(cpu, sched_group_cpus(sdg)) {
+		for_each_cpu(cpu, sched_group_span(sdg)) {
 			struct sched_group_capacity *sgc;
 			struct rq *rq = cpu_rq(cpu);
 
@@ -7408,7 +7342,7 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 
 	memset(sgs, 0, sizeof(*sgs));
 
-	for_each_cpu_and(i, sched_group_cpus(group), env->cpus) {
+	for_each_cpu_and(i, sched_group_span(group), env->cpus) {
 		struct rq *rq = cpu_rq(i);
 
 		/* Bias balancing toward cpus of our domain */
@@ -7572,7 +7506,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
 		struct sg_lb_stats *sgs = &tmp_sgs;
 		int local_group;
 
-		local_group = cpumask_test_cpu(env->dst_cpu, sched_group_cpus(sg));
+		local_group = cpumask_test_cpu(env->dst_cpu, sched_group_span(sg));
 		if (local_group) {
 			sds->local = sg;
 			sgs = local;
@@ -7927,7 +7861,7 @@ static struct rq *find_busiest_queue(struct lb_env *env,
 	unsigned long busiest_load = 0, busiest_capacity = 1;
 	int i;
 
-	for_each_cpu_and(i, sched_group_cpus(group), env->cpus) {
+	for_each_cpu_and(i, sched_group_span(group), env->cpus) {
 		unsigned long capacity, wl;
 		enum fbq_type rt;
 
@@ -8033,7 +7967,6 @@ static int active_load_balance_cpu_stop(void *data);
 static int should_we_balance(struct lb_env *env)
 {
 	struct sched_group *sg = env->sd->groups;
-	struct cpumask *sg_cpus, *sg_mask;
 	int cpu, balance_cpu = -1;
 
 	/*
@@ -8043,11 +7976,9 @@ static int should_we_balance(struct lb_env *env)
 	if (env->idle == CPU_NEWLY_IDLE)
 		return 1;
 
-	sg_cpus = sched_group_cpus(sg);
-	sg_mask = sched_group_mask(sg);
 	/* Try to find first idle cpu */
-	for_each_cpu_and(cpu, sg_cpus, env->cpus) {
-		if (!cpumask_test_cpu(cpu, sg_mask) || !idle_cpu(cpu))
+	for_each_cpu_and(cpu, group_balance_mask(sg), env->cpus) {
+		if (!idle_cpu(cpu))
 			continue;
 
 		balance_cpu = cpu;
@@ -8083,7 +8014,7 @@ static int load_balance(int this_cpu, struct rq *this_rq,
 		.sd		= sd,
 		.dst_cpu	= this_cpu,
 		.dst_rq		= this_rq,
-		.dst_grpmask    = sched_group_cpus(sd->groups),
+		.dst_grpmask    = sched_group_span(sd->groups),
 		.idle		= idle,
 		.loop_break	= sched_nr_migrate_break,
 		.cpus		= cpus,
@@ -8091,14 +8022,7 @@ static int load_balance(int this_cpu, struct rq *this_rq,
 		.tasks		= LIST_HEAD_INIT(env.tasks),
 	};
 
-	/*
-	 * For NEWLY_IDLE load_balancing, we don't need to consider
-	 * other cpus in our group
-	 */
-	if (idle == CPU_NEWLY_IDLE)
-		env.dst_grpmask = NULL;
-
-	cpumask_copy(cpus, cpu_active_mask);
+	cpumask_and(cpus, sched_domain_span(sd), cpu_active_mask);
 
 	schedstat_inc(sd->lb_count[idle]);
 
@@ -8220,7 +8144,15 @@ more_balance:
 		/* All tasks on this runqueue were pinned by CPU affinity */
 		if (unlikely(env.flags & LBF_ALL_PINNED)) {
 			cpumask_clear_cpu(cpu_of(busiest), cpus);
-			if (!cpumask_empty(cpus)) {
+			/*
+			 * Attempting to continue load balancing at the current
+			 * sched_domain level only makes sense if there are
+			 * active CPUs remaining as possible busiest CPUs to
+			 * pull load from which are not contained within the
+			 * destination group that is receiving any migrated
+			 * load.
+			 */
+			if (!cpumask_subset(cpus, env.dst_grpmask)) {
 				env.loop = 0;
 				env.loop_break = sched_nr_migrate_break;
 				goto redo;
@@ -8516,6 +8448,13 @@ static int active_load_balance_cpu_stop(void *data)
 			.src_cpu	= busiest_rq->cpu,
 			.src_rq		= busiest_rq,
 			.idle		= CPU_IDLE,
+			/*
+			 * can_migrate_task() doesn't need to compute new_dst_cpu
+			 * for active balancing. Since we have CPU_IDLE, but no
+			 * @dst_grpmask we need to make that test go away with lying
+			 * about DST_PINNED.
+			 */
+			.flags		= LBF_DST_PINNED,
 		};
 
 		schedstat_inc(sd->alb_count);
@@ -8659,6 +8598,10 @@ void nohz_balance_enter_idle(int cpu)
 	if (!cpu_active(cpu))
 		return;
 
+	/* Spare idle load balancing on CPUs that don't want to be disturbed: */
+	if (!is_housekeeping_cpu(cpu))
+		return;
+
 	if (test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)))
 		return;
 
@@ -9523,10 +9466,10 @@ const struct sched_class fair_sched_class = {
 #ifdef CONFIG_SCHED_DEBUG
 void print_cfs_stats(struct seq_file *m, int cpu)
 {
-	struct cfs_rq *cfs_rq;
+	struct cfs_rq *cfs_rq, *pos;
 
 	rcu_read_lock();
-	for_each_leaf_cfs_rq(cpu_rq(cpu), cfs_rq)
+	for_each_leaf_cfs_rq_safe(cpu_rq(cpu), cfs_rq, pos)
 		print_cfs_rq(m, cpu, cfs_rq);
 	rcu_read_unlock();
 }