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

Pull scheduler changes from Ingo Molnar:
 "Major changes:

   - Reworked CPU capacity code, for better SMP load balancing on
     systems with assymetric CPUs. (Vincent Guittot, Morten Rasmussen)

   - Reworked RT task SMP balancing to be push based instead of pull
     based, to reduce latencies on large CPU count systems. (Steven
     Rostedt)

   - SCHED_DEADLINE support updates and fixes. (Juri Lelli)

   - SCHED_DEADLINE task migration support during CPU hotplug. (Wanpeng Li)

   - x86 mwait-idle optimizations and fixes. (Mike Galbraith, Len Brown)

   - sched/numa improvements. (Rik van Riel)

   - various cleanups"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (28 commits)
  sched/core: Drop debugging leftover trace_printk call
  sched/deadline: Support DL task migration during CPU hotplug
  sched/core: Check for available DL bandwidth in cpuset_cpu_inactive()
  sched/deadline: Always enqueue on previous rq when dl_task_timer() fires
  sched/core: Remove unused argument from init_[rt|dl]_rq()
  sched/deadline: Fix rt runtime corruption when dl fails its global constraints
  sched/deadline: Avoid a superfluous check
  sched: Improve load balancing in the presence of idle CPUs
  sched: Optimize freq invariant accounting
  sched: Move CFS tasks to CPUs with higher capacity
  sched: Add SD_PREFER_SIBLING for SMT level
  sched: Remove unused struct sched_group_capacity::capacity_orig
  sched: Replace capacity_factor by usage
  sched: Calculate CPU's usage statistic and put it into struct sg_lb_stats::group_usage
  sched: Add struct rq::cpu_capacity_orig
  sched: Make scale_rt invariant with frequency
  sched: Make sched entity usage tracking scale-invariant
  sched: Remove frequency scaling from cpu_capacity
  sched: Track group sched_entity usage contributions
  sched: Add sched_avg::utilization_avg_contrib
  ...

arch/x86/include/asm/mwait.h

@@ -30,6 +30,14 @@ static inline void __mwait(unsigned long eax, unsigned long ecx)
 		     :: "a" (eax), "c" (ecx));
 }
 
+static inline void __sti_mwait(unsigned long eax, unsigned long ecx)
+{
+	trace_hardirqs_on();
+	/* "mwait %eax, %ecx;" */
+	asm volatile("sti; .byte 0x0f, 0x01, 0xc9;"
+		     :: "a" (eax), "c" (ecx));
+}
+
 /*
  * This uses new MONITOR/MWAIT instructions on P4 processors with PNI,
  * which can obviate IPI to trigger checking of need_resched.

arch/x86/kernel/process.c

@@ -24,6 +24,7 @@
 #include <asm/syscalls.h>
 #include <asm/idle.h>
 #include <asm/uaccess.h>
+#include <asm/mwait.h>
 #include <asm/i387.h>
 #include <asm/fpu-internal.h>
 #include <asm/debugreg.h>
@@ -399,6 +400,53 @@ static void amd_e400_idle(void)
 		default_idle();
 }
 
+/*
+ * Intel Core2 and older machines prefer MWAIT over HALT for C1.
+ * We can't rely on cpuidle installing MWAIT, because it will not load
+ * on systems that support only C1 -- so the boot default must be MWAIT.
+ *
+ * Some AMD machines are the opposite, they depend on using HALT.
+ *
+ * So for default C1, which is used during boot until cpuidle loads,
+ * use MWAIT-C1 on Intel HW that has it, else use HALT.
+ */
+static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c)
+{
+	if (c->x86_vendor != X86_VENDOR_INTEL)
+		return 0;
+
+	if (!cpu_has(c, X86_FEATURE_MWAIT))
+		return 0;
+
+	return 1;
+}
+
+/*
+ * MONITOR/MWAIT with no hints, used for default default C1 state.
+ * This invokes MWAIT with interrutps enabled and no flags,
+ * which is backwards compatible with the original MWAIT implementation.
+ */
+
+static void mwait_idle(void)
+{
+	if (!current_set_polling_and_test()) {
+		if (this_cpu_has(X86_BUG_CLFLUSH_MONITOR)) {
+			smp_mb(); /* quirk */
+			clflush((void *)&current_thread_info()->flags);
+			smp_mb(); /* quirk */
+		}
+
+		__monitor((void *)&current_thread_info()->flags, 0, 0);
+		if (!need_resched())
+			__sti_mwait(0, 0);
+		else
+			local_irq_enable();
+	} else {
+		local_irq_enable();
+	}
+	__current_clr_polling();
+}
+
 void select_idle_routine(const struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_SMP
@@ -412,6 +460,9 @@ void select_idle_routine(const struct cpuinfo_x86 *c)
 		/* E400: APIC timer interrupt does not wake up CPU from C1e */
 		pr_info("using AMD E400 aware idle routine\n");
 		x86_idle = amd_e400_idle;
+	} else if (prefer_mwait_c1_over_halt(c)) {
+		pr_info("using mwait in idle threads\n");
+		x86_idle = mwait_idle;
 	} else
 		x86_idle = default_idle;
 }

include/linux/irq_work.h

@@ -38,16 +38,17 @@ bool irq_work_queue(struct irq_work *work);
 bool irq_work_queue_on(struct irq_work *work, int cpu);
 #endif
 
-void irq_work_run(void);
 void irq_work_tick(void);
 void irq_work_sync(struct irq_work *work);
 
 #ifdef CONFIG_IRQ_WORK
 #include <asm/irq_work.h>
 
+void irq_work_run(void);
 bool irq_work_needs_cpu(void);
 #else
 static inline bool irq_work_needs_cpu(void) { return false; }
+static inline void irq_work_run(void) { }
 #endif
 
 #endif /* _LINUX_IRQ_WORK_H */

include/linux/sched.h

@@ -1123,15 +1123,28 @@ struct load_weight {
 };
 
 struct sched_avg {
+	u64 last_runnable_update;
+	s64 decay_count;
+	/*
+	 * utilization_avg_contrib describes the amount of time that a
+	 * sched_entity is running on a CPU. It is based on running_avg_sum
+	 * and is scaled in the range [0..SCHED_LOAD_SCALE].
+	 * load_avg_contrib described the amount of time that a sched_entity
+	 * is runnable on a rq. It is based on both runnable_avg_sum and the
+	 * weight of the task.
+	 */
+	unsigned long load_avg_contrib, utilization_avg_contrib;
 	/*
 	 * These sums represent an infinite geometric series and so are bound
 	 * above by 1024/(1-y).  Thus we only need a u32 to store them for all
 	 * choices of y < 1-2^(-32)*1024.
+	 * running_avg_sum reflects the time that the sched_entity is
+	 * effectively running on the CPU.
+	 * runnable_avg_sum represents the amount of time a sched_entity is on
+	 * a runqueue which includes the running time that is monitored by
+	 * running_avg_sum.
 	 */
-	u32 runnable_avg_sum, runnable_avg_period;
-	u64 last_runnable_update;
-	s64 decay_count;
-	unsigned long load_avg_contrib;
+	u32 runnable_avg_sum, avg_period, running_avg_sum;
 };
 
 #ifdef CONFIG_SCHEDSTATS

kernel/sched/core.c

@@ -689,6 +689,23 @@ static inline bool got_nohz_idle_kick(void)
 #ifdef CONFIG_NO_HZ_FULL
 bool sched_can_stop_tick(void)
 {
+	/*
+	 * FIFO realtime policy runs the highest priority task. Other runnable
+	 * tasks are of a lower priority. The scheduler tick does nothing.
+	 */
+	if (current->policy == SCHED_FIFO)
+		return true;
+
+	/*
+	 * Round-robin realtime tasks time slice with other tasks at the same
+	 * realtime priority. Is this task the only one at this priority?
+	 */
+	if (current->policy == SCHED_RR) {
+		struct sched_rt_entity *rt_se = &current->rt;
+
+		return rt_se->run_list.prev == rt_se->run_list.next;
+	}
+
 	/*
 	 * More than one running task need preemption.
 	 * nr_running update is assumed to be visible
@@ -5335,36 +5352,13 @@ static int sched_cpu_active(struct notifier_block *nfb,
 static int sched_cpu_inactive(struct notifier_block *nfb,
 					unsigned long action, void *hcpu)
 {
-	unsigned long flags;
-	long cpu = (long)hcpu;
-	struct dl_bw *dl_b;
-
 	switch (action & ~CPU_TASKS_FROZEN) {
 	case CPU_DOWN_PREPARE:
-		set_cpu_active(cpu, false);
-
-		/* explicitly allow suspend */
-		if (!(action & CPU_TASKS_FROZEN)) {
-			bool overflow;
-			int cpus;
-
-			rcu_read_lock_sched();
-			dl_b = dl_bw_of(cpu);
-
-			raw_spin_lock_irqsave(&dl_b->lock, flags);
-			cpus = dl_bw_cpus(cpu);
-			overflow = __dl_overflow(dl_b, cpus, 0, 0);
-			raw_spin_unlock_irqrestore(&dl_b->lock, flags);
-
-			rcu_read_unlock_sched();
-
-			if (overflow)
-				return notifier_from_errno(-EBUSY);
-		}
+		set_cpu_active((long)hcpu, false);
 		return NOTIFY_OK;
+	default:
+		return NOTIFY_DONE;
 	}
-
-	return NOTIFY_DONE;
 }
 
 static int __init migration_init(void)
@@ -5445,17 +5439,6 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 			break;
 		}
 
-		/*
-		 * Even though we initialize ->capacity to something semi-sane,
-		 * we leave capacity_orig unset. This allows us to detect if
-		 * domain iteration is still funny without causing /0 traps.
-		 */
-		if (!group->sgc->capacity_orig) {
-			printk(KERN_CONT "\n");
-			printk(KERN_ERR "ERROR: domain->cpu_capacity not set\n");
-			break;
-		}
-
 		if (!cpumask_weight(sched_group_cpus(group))) {
 			printk(KERN_CONT "\n");
 			printk(KERN_ERR "ERROR: empty group\n");
@@ -5939,7 +5922,6 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu)
 		 * die on a /0 trap.
 		 */
 		sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sg_span);
-		sg->sgc->capacity_orig = sg->sgc->capacity;
 
 		/*
 		 * Make sure the first group of this domain contains the
@@ -6250,6 +6232,7 @@ sd_init(struct sched_domain_topology_level *tl, int cpu)
 	 */
 
 	if (sd->flags & SD_SHARE_CPUCAPACITY) {
+		sd->flags |= SD_PREFER_SIBLING;
 		sd->imbalance_pct = 110;
 		sd->smt_gain = 1178; /* ~15% */
 
@@ -7015,7 +6998,6 @@ static int cpuset_cpu_active(struct notifier_block *nfb, unsigned long action,
 		 */
 
 	case CPU_ONLINE:
-	case CPU_DOWN_FAILED:
 		cpuset_update_active_cpus(true);
 		break;
 	default:
@@ -7027,8 +7009,30 @@ static int cpuset_cpu_active(struct notifier_block *nfb, unsigned long action,
 static int cpuset_cpu_inactive(struct notifier_block *nfb, unsigned long action,
 			       void *hcpu)
 {
-	switch (action) {
+	unsigned long flags;
+	long cpu = (long)hcpu;
+	struct dl_bw *dl_b;
+
+	switch (action & ~CPU_TASKS_FROZEN) {
 	case CPU_DOWN_PREPARE:
+		/* explicitly allow suspend */
+		if (!(action & CPU_TASKS_FROZEN)) {
+			bool overflow;
+			int cpus;
+
+			rcu_read_lock_sched();
+			dl_b = dl_bw_of(cpu);
+
+			raw_spin_lock_irqsave(&dl_b->lock, flags);
+			cpus = dl_bw_cpus(cpu);
+			overflow = __dl_overflow(dl_b, cpus, 0, 0);
+			raw_spin_unlock_irqrestore(&dl_b->lock, flags);
+
+			rcu_read_unlock_sched();
+
+			if (overflow)
+				return notifier_from_errno(-EBUSY);
+		}
 		cpuset_update_active_cpus(false);
 		break;
 	case CPU_DOWN_PREPARE_FROZEN:
@@ -7173,8 +7177,8 @@ void __init sched_init(void)
 		rq->calc_load_active = 0;
 		rq->calc_load_update = jiffies + LOAD_FREQ;
 		init_cfs_rq(&rq->cfs);
-		init_rt_rq(&rq->rt, rq);
-		init_dl_rq(&rq->dl, rq);
+		init_rt_rq(&rq->rt);
+		init_dl_rq(&rq->dl);
 #ifdef CONFIG_FAIR_GROUP_SCHED
 		root_task_group.shares = ROOT_TASK_GROUP_LOAD;
 		INIT_LIST_HEAD(&rq->leaf_cfs_rq_list);
@@ -7214,7 +7218,7 @@ void __init sched_init(void)
 #ifdef CONFIG_SMP
 		rq->sd = NULL;
 		rq->rd = NULL;
-		rq->cpu_capacity = SCHED_CAPACITY_SCALE;
+		rq->cpu_capacity = rq->cpu_capacity_orig = SCHED_CAPACITY_SCALE;
 		rq->post_schedule = 0;
 		rq->active_balance = 0;
 		rq->next_balance = jiffies;
@@ -7813,7 +7817,7 @@ static int sched_rt_global_constraints(void)
 }
 #endif /* CONFIG_RT_GROUP_SCHED */
 
-static int sched_dl_global_constraints(void)
+static int sched_dl_global_validate(void)
 {
 	u64 runtime = global_rt_runtime();
 	u64 period = global_rt_period();
@@ -7914,11 +7918,11 @@ int sched_rt_handler(struct ctl_table *table, int write,
 		if (ret)
 			goto undo;
 
-		ret = sched_rt_global_constraints();
+		ret = sched_dl_global_validate();
 		if (ret)
 			goto undo;
 
-		ret = sched_dl_global_constraints();
+		ret = sched_rt_global_constraints();
 		if (ret)
 			goto undo;
 

kernel/sched/deadline.c

@@ -69,7 +69,7 @@ void init_dl_bw(struct dl_bw *dl_b)
 	dl_b->total_bw = 0;
 }
 
-void init_dl_rq(struct dl_rq *dl_rq, struct rq *rq)
+void init_dl_rq(struct dl_rq *dl_rq)
 {
 	dl_rq->rb_root = RB_ROOT;
 
@@ -218,6 +218,52 @@ static inline void set_post_schedule(struct rq *rq)
 	rq->post_schedule = has_pushable_dl_tasks(rq);
 }
 
+static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq);
+
+static void dl_task_offline_migration(struct rq *rq, struct task_struct *p)
+{
+	struct rq *later_rq = NULL;
+	bool fallback = false;
+
+	later_rq = find_lock_later_rq(p, rq);
+
+	if (!later_rq) {
+		int cpu;
+
+		/*
+		 * If we cannot preempt any rq, fall back to pick any
+		 * online cpu.
+		 */
+		fallback = true;
+		cpu = cpumask_any_and(cpu_active_mask, tsk_cpus_allowed(p));
+		if (cpu >= nr_cpu_ids) {
+			/*
+			 * Fail to find any suitable cpu.
+			 * The task will never come back!
+			 */
+			BUG_ON(dl_bandwidth_enabled());
+
+			/*
+			 * If admission control is disabled we
+			 * try a little harder to let the task
+			 * run.
+			 */
+			cpu = cpumask_any(cpu_active_mask);
+		}
+		later_rq = cpu_rq(cpu);
+		double_lock_balance(rq, later_rq);
+	}
+
+	deactivate_task(rq, p, 0);
+	set_task_cpu(p, later_rq->cpu);
+	activate_task(later_rq, p, ENQUEUE_REPLENISH);
+
+	if (!fallback)
+		resched_curr(later_rq);
+
+	double_unlock_balance(rq, later_rq);
+}
+
 #else
 
 static inline
@@ -514,7 +560,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
 	unsigned long flags;
 	struct rq *rq;
 
-	rq = task_rq_lock(current, &flags);
+	rq = task_rq_lock(p, &flags);
 
 	/*
 	 * We need to take care of several possible races here:
@@ -536,6 +582,17 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
 	sched_clock_tick();
 	update_rq_clock(rq);
 
+#ifdef CONFIG_SMP
+	/*
+	 * If we find that the rq the task was on is no longer
+	 * available, we need to select a new rq.
+	 */
+	if (unlikely(!rq->online)) {
+		dl_task_offline_migration(rq, p);
+		goto unlock;
+	}
+#endif
+
 	/*
 	 * If the throttle happened during sched-out; like:
 	 *
@@ -569,7 +626,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
 		push_dl_task(rq);
 #endif
 unlock:
-	task_rq_unlock(rq, current, &flags);
+	task_rq_unlock(rq, p, &flags);
 
 	return HRTIMER_NORESTART;
 }
@@ -914,6 +971,12 @@ static void yield_task_dl(struct rq *rq)
 	}
 	update_rq_clock(rq);
 	update_curr_dl(rq);
+	/*
+	 * Tell update_rq_clock() that we've just updated,
+	 * so we don't do microscopic update in schedule()
+	 * and double the fastpath cost.
+	 */
+	rq_clock_skip_update(rq, true);
 }
 
 #ifdef CONFIG_SMP
@@ -1659,14 +1722,6 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p)
 {
 	int check_resched = 1;
 
-	/*
-	 * If p is throttled, don't consider the possibility
-	 * of preempting rq->curr, the check will be done right
-	 * after its runtime will get replenished.
-	 */
-	if (unlikely(p->dl.dl_throttled))
-		return;
-
 	if (task_on_rq_queued(p) && rq->curr != p) {
 #ifdef CONFIG_SMP
 		if (p->nr_cpus_allowed > 1 && rq->dl.overloaded &&

kernel/sched/debug.c

@@ -71,7 +71,7 @@ static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group
 	if (!se) {
 		struct sched_avg *avg = &cpu_rq(cpu)->avg;
 		P(avg->runnable_avg_sum);
-		P(avg->runnable_avg_period);
+		P(avg->avg_period);
 		return;
 	}
 
@@ -94,8 +94,10 @@ static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group
 	P(se->load.weight);
 #ifdef CONFIG_SMP
 	P(se->avg.runnable_avg_sum);
-	P(se->avg.runnable_avg_period);
+	P(se->avg.running_avg_sum);
+	P(se->avg.avg_period);
 	P(se->avg.load_avg_contrib);
+	P(se->avg.utilization_avg_contrib);
 	P(se->avg.decay_count);
 #endif
 #undef PN
@@ -214,6 +216,8 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 			cfs_rq->runnable_load_avg);
 	SEQ_printf(m, "  .%-30s: %ld\n", "blocked_load_avg",
 			cfs_rq->blocked_load_avg);
+	SEQ_printf(m, "  .%-30s: %ld\n", "utilization_load_avg",
+			cfs_rq->utilization_load_avg);
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	SEQ_printf(m, "  .%-30s: %ld\n", "tg_load_contrib",
 			cfs_rq->tg_load_contrib);
@@ -636,8 +640,10 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 	P(se.load.weight);
 #ifdef CONFIG_SMP
 	P(se.avg.runnable_avg_sum);
-	P(se.avg.runnable_avg_period);
+	P(se.avg.running_avg_sum);
+	P(se.avg.avg_period);
 	P(se.avg.load_avg_contrib);
+	P(se.avg.utilization_avg_contrib);
 	P(se.avg.decay_count);
 #endif
 	P(policy);

kernel/sched/fair.c

@@ -670,6 +670,7 @@ static int select_idle_sibling(struct task_struct *p, int cpu);
 static unsigned long task_h_load(struct task_struct *p);
 
 static inline void __update_task_entity_contrib(struct sched_entity *se);
+static inline void __update_task_entity_utilization(struct sched_entity *se);
 
 /* Give new task start runnable values to heavy its load in infant time */
 void init_task_runnable_average(struct task_struct *p)
@@ -677,9 +678,10 @@ void init_task_runnable_average(struct task_struct *p)
 	u32 slice;
 
 	slice = sched_slice(task_cfs_rq(p), &p->se) >> 10;
-	p->se.avg.runnable_avg_sum = slice;
-	p->se.avg.runnable_avg_period = slice;
+	p->se.avg.runnable_avg_sum = p->se.avg.running_avg_sum = slice;
+	p->se.avg.avg_period = slice;
 	__update_task_entity_contrib(&p->se);
+	__update_task_entity_utilization(&p->se);
 }
 #else
 void init_task_runnable_average(struct task_struct *p)
@@ -1196,9 +1198,11 @@ static void task_numa_assign(struct task_numa_env *env,
 static bool load_too_imbalanced(long src_load, long dst_load,
 				struct task_numa_env *env)
 {
-	long imb, old_imb;
-	long orig_src_load, orig_dst_load;
 	long src_capacity, dst_capacity;
+	long orig_src_load;
+	long load_a, load_b;
+	long moved_load;
+	long imb;
 
 	/*
 	 * The load is corrected for the CPU capacity available on each node.
@@ -1211,30 +1215,39 @@ static bool load_too_imbalanced(long src_load, long dst_load,
 	dst_capacity = env->dst_stats.compute_capacity;
 
 	/* We care about the slope of the imbalance, not the direction. */
-	if (dst_load < src_load)
-		swap(dst_load, src_load);
+	load_a = dst_load;
+	load_b = src_load;
+	if (load_a < load_b)
+		swap(load_a, load_b);
 
 	/* Is the difference below the threshold? */
-	imb = dst_load * src_capacity * 100 -
-	      src_load * dst_capacity * env->imbalance_pct;
+	imb = load_a * src_capacity * 100 -
+		load_b * dst_capacity * env->imbalance_pct;
 	if (imb <= 0)
 		return false;
 
 	/*
 	 * The imbalance is above the allowed threshold.
-	 * Compare it with the old imbalance.
+	 * Allow a move that brings us closer to a balanced situation,
+	 * without moving things past the point of balance.
 	 */
 	orig_src_load = env->src_stats.load;
-	orig_dst_load = env->dst_stats.load;
 
-	if (orig_dst_load < orig_src_load)
-		swap(orig_dst_load, orig_src_load);
-
-	old_imb = orig_dst_load * src_capacity * 100 -
-		  orig_src_load * dst_capacity * env->imbalance_pct;
+	/*
+	 * In a task swap, there will be one load moving from src to dst,
+	 * and another moving back. This is the net sum of both moves.
+	 * A simple task move will always have a positive value.
+	 * Allow the move if it brings the system closer to a balanced
+	 * situation, without crossing over the balance point.
+	 */
+	moved_load = orig_src_load - src_load;
 
-	/* Would this change make things worse? */
-	return (imb > old_imb);
+	if (moved_load > 0)
+		/* Moving src -> dst. Did we overshoot balance? */
+		return src_load * dst_capacity < dst_load * src_capacity;
+	else
+		/* Moving dst -> src. Did we overshoot balance? */
+		return dst_load * src_capacity < src_load * dst_capacity;
 }
 
 /*
@@ -1675,7 +1688,7 @@ static u64 numa_get_avg_runtime(struct task_struct *p, u64 *period)
 		*period = now - p->last_task_numa_placement;
 	} else {
 		delta = p->se.avg.runnable_avg_sum;
-		*period = p->se.avg.runnable_avg_period;
+		*period = p->se.avg.avg_period;
 	}
 
 	p->last_sum_exec_runtime = runtime;
@@ -1765,6 +1778,8 @@ static int preferred_group_nid(struct task_struct *p, int nid)
 			}
 		}
 		/* Next round, evaluate the nodes within max_group. */
+		if (!max_faults)
+			break;
 		nodes = max_group;
 	}
 	return nid;
@@ -2503,13 +2518,15 @@ static u32 __compute_runnable_contrib(u64 n)
  *   load_avg = u_0` + y*(u_0 + u_1*y + u_2*y^2 + ... )
  *            = u_0 + u_1*y + u_2*y^2 + ... [re-labeling u_i --> u_{i+1}]
  */
-static __always_inline int __update_entity_runnable_avg(u64 now,
+static __always_inline int __update_entity_runnable_avg(u64 now, int cpu,
 							struct sched_avg *sa,
-							int runnable)
+							int runnable,
+							int running)
 {
 	u64 delta, periods;
 	u32 runnable_contrib;
 	int delta_w, decayed = 0;
+	unsigned long scale_freq = arch_scale_freq_capacity(NULL, cpu);
 
 	delta = now - sa->last_runnable_update;
 	/*
@@ -2531,7 +2548,7 @@ static __always_inline int __update_entity_runnable_avg(u64 now,
 	sa->last_runnable_update = now;
 
 	/* delta_w is the amount already accumulated against our next period */
-	delta_w = sa->runnable_avg_period % 1024;
+	delta_w = sa->avg_period % 1024;
 	if (delta + delta_w >= 1024) {
 		/* period roll-over */
 		decayed = 1;
@@ -2544,7 +2561,10 @@ static __always_inline int __update_entity_runnable_avg(u64 now,
 		delta_w = 1024 - delta_w;
 		if (runnable)
 			sa->runnable_avg_sum += delta_w;
-		sa->runnable_avg_period += delta_w;
+		if (running)
+			sa->running_avg_sum += delta_w * scale_freq
+				>> SCHED_CAPACITY_SHIFT;
+		sa->avg_period += delta_w;
 
 		delta -= delta_w;
 
@@ -2554,20 +2574,28 @@ static __always_inline int __update_entity_runnable_avg(u64 now,
 
 		sa->runnable_avg_sum = decay_load(sa->runnable_avg_sum,
 						  periods + 1);
-		sa->runnable_avg_period = decay_load(sa->runnable_avg_period,
+		sa->running_avg_sum = decay_load(sa->running_avg_sum,
+						  periods + 1);
+		sa->avg_period = decay_load(sa->avg_period,
 						     periods + 1);
 
 		/* Efficiently calculate \sum (1..n_period) 1024*y^i */
 		runnable_contrib = __compute_runnable_contrib(periods);
 		if (runnable)
 			sa->runnable_avg_sum += runnable_contrib;
-		sa->runnable_avg_period += runnable_contrib;
+		if (running)
+			sa->running_avg_sum += runnable_contrib * scale_freq
+				>> SCHED_CAPACITY_SHIFT;
+		sa->avg_period += runnable_contrib;
 	}
 
 	/* Remainder of delta accrued against u_0` */
 	if (runnable)
 		sa->runnable_avg_sum += delta;
-	sa->runnable_avg_period += delta;
+	if (running)
+		sa->running_avg_sum += delta * scale_freq
+			>> SCHED_CAPACITY_SHIFT;
+	sa->avg_period += delta;
 
 	return decayed;
 }
@@ -2584,6 +2612,8 @@ static inline u64 __synchronize_entity_decay(struct sched_entity *se)
 		return 0;
 
 	se->avg.load_avg_contrib = decay_load(se->avg.load_avg_contrib, decays);
+	se->avg.utilization_avg_contrib =
+		decay_load(se->avg.utilization_avg_contrib, decays);
 
 	return decays;
 }
@@ -2619,7 +2649,7 @@ static inline void __update_tg_runnable_avg(struct sched_avg *sa,
 
 	/* The fraction of a cpu used by this cfs_rq */
 	contrib = div_u64((u64)sa->runnable_avg_sum << NICE_0_SHIFT,
-			  sa->runnable_avg_period + 1);
+			  sa->avg_period + 1);
 	contrib -= cfs_rq->tg_runnable_contrib;
 
 	if (abs(contrib) > cfs_rq->tg_runnable_contrib / 64) {
@@ -2672,7 +2702,8 @@ static inline void __update_group_entity_contrib(struct sched_entity *se)
 
 static inline void update_rq_runnable_avg(struct rq *rq, int runnable)
 {
-	__update_entity_runnable_avg(rq_clock_task(rq), &rq->avg, runnable);
+	__update_entity_runnable_avg(rq_clock_task(rq), cpu_of(rq), &rq->avg,
+			runnable, runnable);
 	__update_tg_runnable_avg(&rq->avg, &rq->cfs);
 }
 #else /* CONFIG_FAIR_GROUP_SCHED */
@@ -2690,7 +2721,7 @@ static inline void __update_task_entity_contrib(struct sched_entity *se)
 
 	/* avoid overflowing a 32-bit type w/ SCHED_LOAD_SCALE */
 	contrib = se->avg.runnable_avg_sum * scale_load_down(se->load.weight);
-	contrib /= (se->avg.runnable_avg_period + 1);
+	contrib /= (se->avg.avg_period + 1);
 	se->avg.load_avg_contrib = scale_load(contrib);
 }
 
@@ -2709,6 +2740,30 @@ static long __update_entity_load_avg_contrib(struct sched_entity *se)
 	return se->avg.load_avg_contrib - old_contrib;
 }
 
+
+static inline void __update_task_entity_utilization(struct sched_entity *se)
+{
+	u32 contrib;
+
+	/* avoid overflowing a 32-bit type w/ SCHED_LOAD_SCALE */
+	contrib = se->avg.running_avg_sum * scale_load_down(SCHED_LOAD_SCALE);
+	contrib /= (se->avg.avg_period + 1);
+	se->avg.utilization_avg_contrib = scale_load(contrib);
+}
+
+static long __update_entity_utilization_avg_contrib(struct sched_entity *se)
+{
+	long old_contrib = se->avg.utilization_avg_contrib;
+
+	if (entity_is_task(se))
+		__update_task_entity_utilization(se);
+	else
+		se->avg.utilization_avg_contrib =
+					group_cfs_rq(se)->utilization_load_avg;
+
+	return se->avg.utilization_avg_contrib - old_contrib;
+}
+
 static inline void subtract_blocked_load_contrib(struct cfs_rq *cfs_rq,
 						 long load_contrib)
 {
@@ -2725,7 +2780,8 @@ static inline void update_entity_load_avg(struct sched_entity *se,
 					  int update_cfs_rq)
 {
 	struct cfs_rq *cfs_rq = cfs_rq_of(se);
-	long contrib_delta;
+	long contrib_delta, utilization_delta;
+	int cpu = cpu_of(rq_of(cfs_rq));
 	u64 now;
 
 	/*
@@ -2737,18 +2793,22 @@ static inline void update_entity_load_avg(struct sched_entity *se,
 	else
 		now = cfs_rq_clock_task(group_cfs_rq(se));
 
-	if (!__update_entity_runnable_avg(now, &se->avg, se->on_rq))
+	if (!__update_entity_runnable_avg(now, cpu, &se->avg, se->on_rq,
+					cfs_rq->curr == se))
 		return;
 
 	contrib_delta = __update_entity_load_avg_contrib(se);
+	utilization_delta = __update_entity_utilization_avg_contrib(se);
 
 	if (!update_cfs_rq)
 		return;
 
-	if (se->on_rq)
+	if (se->on_rq) {
 		cfs_rq->runnable_load_avg += contrib_delta;
-	else
+		cfs_rq->utilization_load_avg += utilization_delta;
+	} else {
 		subtract_blocked_load_contrib(cfs_rq, -contrib_delta);
+	}
 }
 
 /*
@@ -2823,6 +2883,7 @@ static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq,
 	}
 
 	cfs_rq->runnable_load_avg += se->avg.load_avg_contrib;
+	cfs_rq->utilization_load_avg += se->avg.utilization_avg_contrib;
 	/* we force update consideration on load-balancer moves */
 	update_cfs_rq_blocked_load(cfs_rq, !wakeup);
 }
@@ -2841,6 +2902,7 @@ static inline void dequeue_entity_load_avg(struct cfs_rq *cfs_rq,
 	update_cfs_rq_blocked_load(cfs_rq, !sleep);
 
 	cfs_rq->runnable_load_avg -= se->avg.load_avg_contrib;
+	cfs_rq->utilization_load_avg -= se->avg.utilization_avg_contrib;
 	if (sleep) {
 		cfs_rq->blocked_load_avg += se->avg.load_avg_contrib;
 		se->avg.decay_count = atomic64_read(&cfs_rq->decay_counter);
@@ -3178,6 +3240,7 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		 */
 		update_stats_wait_end(cfs_rq, se);
 		__dequeue_entity(cfs_rq, se);
+		update_entity_load_avg(se, 1);
 	}
 
 	update_stats_curr_start(cfs_rq, se);
@@ -4304,6 +4367,11 @@ static unsigned long capacity_of(int cpu)
 	return cpu_rq(cpu)->cpu_capacity;
 }
 
+static unsigned long capacity_orig_of(int cpu)
+{
+	return cpu_rq(cpu)->cpu_capacity_orig;
+}
+
 static unsigned long cpu_avg_load_per_task(int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
@@ -4717,6 +4785,33 @@ next:
 done:
 	return target;
 }
+/*
+ * get_cpu_usage returns the amount of capacity of a CPU that is used by CFS
+ * tasks. The unit of the return value must be the one of capacity so we can
+ * compare the usage with the capacity of the CPU that is available for CFS
+ * task (ie cpu_capacity).
+ * cfs.utilization_load_avg is the sum of running time of runnable tasks on a
+ * CPU. It represents the amount of utilization of a CPU in the range
+ * [0..SCHED_LOAD_SCALE].  The usage of a CPU can't be higher than the full
+ * capacity of the CPU because it's about the running time on this CPU.
+ * Nevertheless, cfs.utilization_load_avg can be higher than SCHED_LOAD_SCALE
+ * because of unfortunate rounding in avg_period and running_load_avg or just
+ * after migrating tasks until the average stabilizes with the new running
+ * time. So we need to check that the usage stays into the range
+ * [0..cpu_capacity_orig] and cap if necessary.
+ * Without capping the usage, a group could be seen as overloaded (CPU0 usage
+ * at 121% + CPU1 usage at 80%) whereas CPU1 has 20% of available capacity
+ */
+static int get_cpu_usage(int cpu)
+{
+	unsigned long usage = cpu_rq(cpu)->cfs.utilization_load_avg;
+	unsigned long capacity = capacity_orig_of(cpu);
+
+	if (usage >= SCHED_LOAD_SCALE)
+		return capacity;
+
+	return (usage * capacity) >> SCHED_LOAD_SHIFT;
+}
 
 /*
  * select_task_rq_fair: Select target runqueue for the waking task in domains
@@ -5843,12 +5938,12 @@ struct sg_lb_stats {
 	unsigned long sum_weighted_load; /* Weighted load of group's tasks */
 	unsigned long load_per_task;
 	unsigned long group_capacity;
+	unsigned long group_usage; /* Total usage of the group */
 	unsigned int sum_nr_running; /* Nr tasks running in the group */
-	unsigned int group_capacity_factor;
 	unsigned int idle_cpus;
 	unsigned int group_weight;
 	enum group_type group_type;
-	int group_has_free_capacity;
+	int group_no_capacity;
 #ifdef CONFIG_NUMA_BALANCING
 	unsigned int nr_numa_running;
 	unsigned int nr_preferred_running;
@@ -5919,16 +6014,6 @@ static inline int get_sd_load_idx(struct sched_domain *sd,
 	return load_idx;
 }
 
-static unsigned long default_scale_capacity(struct sched_domain *sd, int cpu)
-{
-	return SCHED_CAPACITY_SCALE;
-}
-
-unsigned long __weak arch_scale_freq_capacity(struct sched_domain *sd, int cpu)
-{
-	return default_scale_capacity(sd, cpu);
-}
-
 static unsigned long default_scale_cpu_capacity(struct sched_domain *sd, int cpu)
 {
 	if ((sd->flags & SD_SHARE_CPUCAPACITY) && (sd->span_weight > 1))
@@ -5945,7 +6030,7 @@ unsigned long __weak arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
 static unsigned long scale_rt_capacity(int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
-	u64 total, available, age_stamp, avg;
+	u64 total, used, age_stamp, avg;
 	s64 delta;
 
 	/*
@@ -5961,19 +6046,12 @@ static unsigned long scale_rt_capacity(int cpu)
 
 	total = sched_avg_period() + delta;
 
-	if (unlikely(total < avg)) {
-		/* Ensures that capacity won't end up being negative */
-		available = 0;
-	} else {
-		available = total - avg;
-	}
+	used = div_u64(avg, total);
 
-	if (unlikely((s64)total < SCHED_CAPACITY_SCALE))
-		total = SCHED_CAPACITY_SCALE;
+	if (likely(used < SCHED_CAPACITY_SCALE))
+		return SCHED_CAPACITY_SCALE - used;
 
-	total >>= SCHED_CAPACITY_SHIFT;
-
-	return div_u64(available, total);
+	return 1;
 }
 
 static void update_cpu_capacity(struct sched_domain *sd, int cpu)
@@ -5988,14 +6066,7 @@ static void update_cpu_capacity(struct sched_domain *sd, int cpu)
 
 	capacity >>= SCHED_CAPACITY_SHIFT;
 
-	sdg->sgc->capacity_orig = capacity;
-
-	if (sched_feat(ARCH_CAPACITY))
-		capacity *= arch_scale_freq_capacity(sd, cpu);
-	else
-		capacity *= default_scale_capacity(sd, cpu);
-
-	capacity >>= SCHED_CAPACITY_SHIFT;
+	cpu_rq(cpu)->cpu_capacity_orig = capacity;
 
 	capacity *= scale_rt_capacity(cpu);
 	capacity >>= SCHED_CAPACITY_SHIFT;
@@ -6011,7 +6082,7 @@ 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, capacity_orig;
+	unsigned long capacity;
 	unsigned long interval;
 
 	interval = msecs_to_jiffies(sd->balance_interval);
@@ -6023,7 +6094,7 @@ void update_group_capacity(struct sched_domain *sd, int cpu)
 		return;
 	}
 
-	capacity_orig = capacity = 0;
+	capacity = 0;
 
 	if (child->flags & SD_OVERLAP) {
 		/*
@@ -6043,19 +6114,15 @@ void update_group_capacity(struct sched_domain *sd, int cpu)
 			 * Use capacity_of(), which is set irrespective of domains
 			 * in update_cpu_capacity().
 			 *
-			 * This avoids capacity/capacity_orig from being 0 and
+			 * This avoids capacity from being 0 and
 			 * causing divide-by-zero issues on boot.
-			 *
-			 * Runtime updates will correct capacity_orig.
 			 */
 			if (unlikely(!rq->sd)) {
-				capacity_orig += capacity_of(cpu);
 				capacity += capacity_of(cpu);
 				continue;
 			}
 
 			sgc = rq->sd->groups->sgc;
-			capacity_orig += sgc->capacity_orig;
 			capacity += sgc->capacity;
 		}
 	} else  {
@@ -6066,39 +6133,24 @@ void update_group_capacity(struct sched_domain *sd, int cpu)
 
 		group = child->groups;
 		do {
-			capacity_orig += group->sgc->capacity_orig;
 			capacity += group->sgc->capacity;
 			group = group->next;
 		} while (group != child->groups);
 	}
 
-	sdg->sgc->capacity_orig = capacity_orig;
 	sdg->sgc->capacity = capacity;
 }
 
 /*
- * Try and fix up capacity for tiny siblings, this is needed when
- * things like SD_ASYM_PACKING need f_b_g to select another sibling
- * which on its own isn't powerful enough.
- *
- * See update_sd_pick_busiest() and check_asym_packing().
+ * Check whether the capacity of the rq has been noticeably reduced by side
+ * activity. The imbalance_pct is used for the threshold.
+ * Return true is the capacity is reduced
  */
 static inline int
-fix_small_capacity(struct sched_domain *sd, struct sched_group *group)
+check_cpu_capacity(struct rq *rq, struct sched_domain *sd)
 {
-	/*
-	 * Only siblings can have significantly less than SCHED_CAPACITY_SCALE
-	 */
-	if (!(sd->flags & SD_SHARE_CPUCAPACITY))
-		return 0;
-
-	/*
-	 * If ~90% of the cpu_capacity is still there, we're good.
-	 */
-	if (group->sgc->capacity * 32 > group->sgc->capacity_orig * 29)
-		return 1;
-
-	return 0;
+	return ((rq->cpu_capacity * sd->imbalance_pct) <
+				(rq->cpu_capacity_orig * 100));
 }
 
 /*
@@ -6136,37 +6188,56 @@ static inline int sg_imbalanced(struct sched_group *group)
 }
 
 /*
- * Compute the group capacity factor.
- *
- * Avoid the issue where N*frac(smt_capacity) >= 1 creates 'phantom' cores by
- * first dividing out the smt factor and computing the actual number of cores
- * and limit unit capacity with that.
+ * group_has_capacity returns true if the group has spare capacity that could
+ * be used by some tasks.
+ * We consider that a group has spare capacity if the  * number of task is
+ * smaller than the number of CPUs or if the usage is lower than the available
+ * capacity for CFS tasks.
+ * For the latter, we use a threshold to stabilize the state, to take into
+ * account the variance of the tasks' load and to return true if the available
+ * capacity in meaningful for the load balancer.
+ * As an example, an available capacity of 1% can appear but it doesn't make
+ * any benefit for the load balance.
  */
-static inline int sg_capacity_factor(struct lb_env *env, struct sched_group *group)
+static inline bool
+group_has_capacity(struct lb_env *env, struct sg_lb_stats *sgs)
 {
-	unsigned int capacity_factor, smt, cpus;
-	unsigned int capacity, capacity_orig;
+	if (sgs->sum_nr_running < sgs->group_weight)
+		return true;
 
-	capacity = group->sgc->capacity;
-	capacity_orig = group->sgc->capacity_orig;
-	cpus = group->group_weight;
+	if ((sgs->group_capacity * 100) >
+			(sgs->group_usage * env->sd->imbalance_pct))
+		return true;
 
-	/* smt := ceil(cpus / capacity), assumes: 1 < smt_capacity < 2 */
-	smt = DIV_ROUND_UP(SCHED_CAPACITY_SCALE * cpus, capacity_orig);
-	capacity_factor = cpus / smt; /* cores */
+	return false;
+}
+
+/*
+ *  group_is_overloaded returns true if the group has more tasks than it can
+ *  handle.
+ *  group_is_overloaded is not equals to !group_has_capacity because a group
+ *  with the exact right number of tasks, has no more spare capacity but is not
+ *  overloaded so both group_has_capacity and group_is_overloaded return
+ *  false.
+ */
+static inline bool
+group_is_overloaded(struct lb_env *env, struct sg_lb_stats *sgs)
+{
+	if (sgs->sum_nr_running <= sgs->group_weight)
+		return false;
 
-	capacity_factor = min_t(unsigned,
-		capacity_factor, DIV_ROUND_CLOSEST(capacity, SCHED_CAPACITY_SCALE));
-	if (!capacity_factor)
-		capacity_factor = fix_small_capacity(env->sd, group);
+	if ((sgs->group_capacity * 100) <
+			(sgs->group_usage * env->sd->imbalance_pct))
+		return true;
 
-	return capacity_factor;
+	return false;
 }
 
-static enum group_type
-group_classify(struct sched_group *group, struct sg_lb_stats *sgs)
+static enum group_type group_classify(struct lb_env *env,
+		struct sched_group *group,
+		struct sg_lb_stats *sgs)
 {
-	if (sgs->sum_nr_running > sgs->group_capacity_factor)
+	if (sgs->group_no_capacity)
 		return group_overloaded;
 
 	if (sg_imbalanced(group))
@@ -6204,6 +6275,7 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 			load = source_load(i, load_idx);
 
 		sgs->group_load += load;
+		sgs->group_usage += get_cpu_usage(i);
 		sgs->sum_nr_running += rq->cfs.h_nr_running;
 
 		if (rq->nr_running > 1)
@@ -6226,11 +6298,9 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 		sgs->load_per_task = sgs->sum_weighted_load / sgs->sum_nr_running;
 
 	sgs->group_weight = group->group_weight;
-	sgs->group_capacity_factor = sg_capacity_factor(env, group);
-	sgs->group_type = group_classify(group, sgs);
 
-	if (sgs->group_capacity_factor > sgs->sum_nr_running)
-		sgs->group_has_free_capacity = 1;
+	sgs->group_no_capacity = group_is_overloaded(env, sgs);
+	sgs->group_type = group_classify(env, group, sgs);
 }
 
 /**
@@ -6352,18 +6422,19 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
 
 		/*
 		 * In case the child domain prefers tasks go to siblings
-		 * first, lower the sg capacity factor to one so that we'll try
+		 * first, lower the sg capacity so that we'll try
 		 * and move all the excess tasks away. We lower the capacity
 		 * of a group only if the local group has the capacity to fit
-		 * these excess tasks, i.e. nr_running < group_capacity_factor. The
-		 * extra check prevents the case where you always pull from the
-		 * heaviest group when it is already under-utilized (possible
-		 * with a large weight task outweighs the tasks on the system).
+		 * these excess tasks. The extra check prevents the case where
+		 * you always pull from the heaviest group when it is already
+		 * under-utilized (possible with a large weight task outweighs
+		 * the tasks on the system).
 		 */
 		if (prefer_sibling && sds->local &&
-		    sds->local_stat.group_has_free_capacity) {
-			sgs->group_capacity_factor = min(sgs->group_capacity_factor, 1U);
-			sgs->group_type = group_classify(sg, sgs);
+		    group_has_capacity(env, &sds->local_stat) &&
+		    (sgs->sum_nr_running > 1)) {
+			sgs->group_no_capacity = 1;
+			sgs->group_type = group_overloaded;
 		}
 
 		if (update_sd_pick_busiest(env, sds, sg, sgs)) {
@@ -6543,11 +6614,12 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
 	 */
 	if (busiest->group_type == group_overloaded &&
 	    local->group_type   == group_overloaded) {
-		load_above_capacity =
-			(busiest->sum_nr_running - busiest->group_capacity_factor);
-
-		load_above_capacity *= (SCHED_LOAD_SCALE * SCHED_CAPACITY_SCALE);
-		load_above_capacity /= busiest->group_capacity;
+		load_above_capacity = busiest->sum_nr_running *
+					SCHED_LOAD_SCALE;
+		if (load_above_capacity > busiest->group_capacity)
+			load_above_capacity -= busiest->group_capacity;
+		else
+			load_above_capacity = ~0UL;
 	}
 
 	/*
@@ -6610,6 +6682,7 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
 	local = &sds.local_stat;
 	busiest = &sds.busiest_stat;
 
+	/* ASYM feature bypasses nice load balance check */
 	if ((env->idle == CPU_IDLE || env->idle == CPU_NEWLY_IDLE) &&
 	    check_asym_packing(env, &sds))
 		return sds.busiest;
@@ -6630,8 +6703,8 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
 		goto force_balance;
 
 	/* SD_BALANCE_NEWIDLE trumps SMP nice when underutilized */
-	if (env->idle == CPU_NEWLY_IDLE && local->group_has_free_capacity &&
-	    !busiest->group_has_free_capacity)
+	if (env->idle == CPU_NEWLY_IDLE && group_has_capacity(env, local) &&
+	    busiest->group_no_capacity)
 		goto force_balance;
 
 	/*
@@ -6690,7 +6763,7 @@ static struct rq *find_busiest_queue(struct lb_env *env,
 	int i;
 
 	for_each_cpu_and(i, sched_group_cpus(group), env->cpus) {
-		unsigned long capacity, capacity_factor, wl;
+		unsigned long capacity, wl;
 		enum fbq_type rt;
 
 		rq = cpu_rq(i);
@@ -6719,9 +6792,6 @@ static struct rq *find_busiest_queue(struct lb_env *env,
 			continue;
 
 		capacity = capacity_of(i);
-		capacity_factor = DIV_ROUND_CLOSEST(capacity, SCHED_CAPACITY_SCALE);
-		if (!capacity_factor)
-			capacity_factor = fix_small_capacity(env->sd, group);
 
 		wl = weighted_cpuload(i);
 
@@ -6729,7 +6799,9 @@ static struct rq *find_busiest_queue(struct lb_env *env,
 		 * When comparing with imbalance, use weighted_cpuload()
 		 * which is not scaled with the cpu capacity.
 		 */
-		if (capacity_factor && rq->nr_running == 1 && wl > env->imbalance)
+
+		if (rq->nr_running == 1 && wl > env->imbalance &&
+		    !check_cpu_capacity(rq, env->sd))
 			continue;
 
 		/*
@@ -6777,6 +6849,19 @@ static int need_active_balance(struct lb_env *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
+	 * because of other sched_class or IRQs if more capacity stays
+	 * available on dst_cpu.
+	 */
+	if ((env->idle != CPU_NOT_IDLE) &&
+	    (env->src_rq->cfs.h_nr_running == 1)) {
+		if ((check_cpu_capacity(env->src_rq, sd)) &&
+		    (capacity_of(env->src_cpu)*sd->imbalance_pct < capacity_of(env->dst_cpu)*100))
+			return 1;
+	}
+
 	return unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2);
 }
 
@@ -6876,6 +6961,9 @@ redo:
 
 	schedstat_add(sd, lb_imbalance[idle], env.imbalance);
 
+	env.src_cpu = busiest->cpu;
+	env.src_rq = busiest;
+
 	ld_moved = 0;
 	if (busiest->nr_running > 1) {
 		/*
@@ -6885,8 +6973,6 @@ redo:
 		 * correctly treated as an imbalance.
 		 */
 		env.flags |= LBF_ALL_PINNED;
-		env.src_cpu   = busiest->cpu;
-		env.src_rq    = busiest;
 		env.loop_max  = min(sysctl_sched_nr_migrate, busiest->nr_running);
 
 more_balance:
@@ -7586,22 +7672,25 @@ end:
 
 /*
  * Current heuristic for kicking the idle load balancer in the presence
- * of an idle cpu is the system.
+ * of an idle cpu in the system.
  *   - This rq has more than one task.
- *   - At any scheduler domain level, this cpu's scheduler group has multiple
- *     busy cpu's exceeding the group's capacity.
+ *   - This rq has at least one CFS task and the capacity of the CPU is
+ *     significantly reduced because of RT tasks or IRQs.
+ *   - At parent of LLC scheduler domain level, this cpu's scheduler group has
+ *     multiple busy cpu.
  *   - For SD_ASYM_PACKING, if the lower numbered cpu's in the scheduler
  *     domain span are idle.
  */
-static inline int nohz_kick_needed(struct rq *rq)
+static inline bool nohz_kick_needed(struct rq *rq)
 {
 	unsigned long now = jiffies;
 	struct sched_domain *sd;
 	struct sched_group_capacity *sgc;
 	int nr_busy, cpu = rq->cpu;
+	bool kick = false;
 
 	if (unlikely(rq->idle_balance))
-		return 0;
+		return false;
 
        /*
 	* We may be recently in ticked or tickless idle mode. At the first
@@ -7615,38 +7704,46 @@ static inline int nohz_kick_needed(struct rq *rq)
 	 * balancing.
 	 */
 	if (likely(!atomic_read(&nohz.nr_cpus)))
-		return 0;
+		return false;
 
 	if (time_before(now, nohz.next_balance))
-		return 0;
+		return false;
 
 	if (rq->nr_running >= 2)
-		goto need_kick;
+		return true;
 
 	rcu_read_lock();
 	sd = rcu_dereference(per_cpu(sd_busy, cpu));
-
 	if (sd) {
 		sgc = sd->groups->sgc;
 		nr_busy = atomic_read(&sgc->nr_busy_cpus);
 
-		if (nr_busy > 1)
-			goto need_kick_unlock;
+		if (nr_busy > 1) {
+			kick = true;
+			goto unlock;
+		}
+
 	}
 
-	sd = rcu_dereference(per_cpu(sd_asym, cpu));
+	sd = rcu_dereference(rq->sd);
+	if (sd) {
+		if ((rq->cfs.h_nr_running >= 1) &&
+				check_cpu_capacity(rq, sd)) {
+			kick = true;
+			goto unlock;
+		}
+	}
 
+	sd = rcu_dereference(per_cpu(sd_asym, cpu));
 	if (sd && (cpumask_first_and(nohz.idle_cpus_mask,
-				  sched_domain_span(sd)) < cpu))
-		goto need_kick_unlock;
-
-	rcu_read_unlock();
-	return 0;
+				  sched_domain_span(sd)) < cpu)) {
+		kick = true;
+		goto unlock;
+	}
 
-need_kick_unlock:
+unlock:
 	rcu_read_unlock();
-need_kick:
-	return 1;
+	return kick;
 }
 #else
 static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle) { }
@@ -7662,14 +7759,16 @@ static void run_rebalance_domains(struct softirq_action *h)
 	enum cpu_idle_type idle = this_rq->idle_balance ?
 						CPU_IDLE : CPU_NOT_IDLE;
 
-	rebalance_domains(this_rq, idle);
-
 	/*
 	 * If this cpu has a pending nohz_balance_kick, then do the
 	 * balancing on behalf of the other idle cpus whose ticks are
-	 * stopped.
+	 * stopped. Do nohz_idle_balance *before* rebalance_domains to
+	 * give the idle cpus a chance to load balance. Else we may
+	 * load balance only within the local sched_domain hierarchy
+	 * and abort nohz_idle_balance altogether if we pull some load.
 	 */
 	nohz_idle_balance(this_rq, idle);
+	rebalance_domains(this_rq, idle);
 }
 
 /*

kernel/sched/features.h

@@ -56,6 +56,19 @@ SCHED_FEAT(NONTASK_CAPACITY, true)
  */
 SCHED_FEAT(TTWU_QUEUE, true)
 
+#ifdef HAVE_RT_PUSH_IPI
+/*
+ * In order to avoid a thundering herd attack of CPUs that are
+ * lowering their priorities at the same time, and there being
+ * a single CPU that has an RT task that can migrate and is waiting
+ * to run, where the other CPUs will try to take that CPUs
+ * rq lock and possibly create a large contention, sending an
+ * IPI to that CPU and let that CPU push the RT task to where
+ * it should go may be a better scenario.
+ */
+SCHED_FEAT(RT_PUSH_IPI, true)
+#endif
+
 SCHED_FEAT(FORCE_SD_OVERLAP, false)
 SCHED_FEAT(RT_RUNTIME_SHARE, true)
 SCHED_FEAT(LB_MIN, false)

kernel/sched/rt.c

@@ -6,6 +6,7 @@
 #include "sched.h"
 
 #include <linux/slab.h>
+#include <linux/irq_work.h>
 
 int sched_rr_timeslice = RR_TIMESLICE;
 
@@ -59,7 +60,11 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
 	raw_spin_unlock(&rt_b->rt_runtime_lock);
 }
 
-void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq)
+#ifdef CONFIG_SMP
+static void push_irq_work_func(struct irq_work *work);
+#endif
+
+void init_rt_rq(struct rt_rq *rt_rq)
 {
 	struct rt_prio_array *array;
 	int i;
@@ -78,7 +83,14 @@ void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq)
 	rt_rq->rt_nr_migratory = 0;
 	rt_rq->overloaded = 0;
 	plist_head_init(&rt_rq->pushable_tasks);
+
+#ifdef HAVE_RT_PUSH_IPI
+	rt_rq->push_flags = 0;
+	rt_rq->push_cpu = nr_cpu_ids;
+	raw_spin_lock_init(&rt_rq->push_lock);
+	init_irq_work(&rt_rq->push_work, push_irq_work_func);
 #endif
+#endif /* CONFIG_SMP */
 	/* We start is dequeued state, because no RT tasks are queued */
 	rt_rq->rt_queued = 0;
 
@@ -193,7 +205,7 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
 		if (!rt_se)
 			goto err_free_rq;
 
-		init_rt_rq(rt_rq, cpu_rq(i));
+		init_rt_rq(rt_rq);
 		rt_rq->rt_runtime = tg->rt_bandwidth.rt_runtime;
 		init_tg_rt_entry(tg, rt_rq, rt_se, i, parent->rt_se[i]);
 	}
@@ -1778,6 +1790,164 @@ static void push_rt_tasks(struct rq *rq)
 		;
 }
 
+#ifdef HAVE_RT_PUSH_IPI
+/*
+ * The search for the next cpu always starts at rq->cpu and ends
+ * when we reach rq->cpu again. It will never return rq->cpu.
+ * This returns the next cpu to check, or nr_cpu_ids if the loop
+ * is complete.
+ *
+ * rq->rt.push_cpu holds the last cpu returned by this function,
+ * or if this is the first instance, it must hold rq->cpu.
+ */
+static int rto_next_cpu(struct rq *rq)
+{
+	int prev_cpu = rq->rt.push_cpu;
+	int cpu;
+
+	cpu = cpumask_next(prev_cpu, rq->rd->rto_mask);
+
+	/*
+	 * If the previous cpu is less than the rq's CPU, then it already
+	 * passed the end of the mask, and has started from the beginning.
+	 * We end if the next CPU is greater or equal to rq's CPU.
+	 */
+	if (prev_cpu < rq->cpu) {
+		if (cpu >= rq->cpu)
+			return nr_cpu_ids;
+
+	} else if (cpu >= nr_cpu_ids) {
+		/*
+		 * We passed the end of the mask, start at the beginning.
+		 * If the result is greater or equal to the rq's CPU, then
+		 * the loop is finished.
+		 */
+		cpu = cpumask_first(rq->rd->rto_mask);
+		if (cpu >= rq->cpu)
+			return nr_cpu_ids;
+	}
+	rq->rt.push_cpu = cpu;
+
+	/* Return cpu to let the caller know if the loop is finished or not */
+	return cpu;
+}
+
+static int find_next_push_cpu(struct rq *rq)
+{
+	struct rq *next_rq;
+	int cpu;
+
+	while (1) {
+		cpu = rto_next_cpu(rq);
+		if (cpu >= nr_cpu_ids)
+			break;
+		next_rq = cpu_rq(cpu);
+
+		/* Make sure the next rq can push to this rq */
+		if (next_rq->rt.highest_prio.next < rq->rt.highest_prio.curr)
+			break;
+	}
+
+	return cpu;
+}
+
+#define RT_PUSH_IPI_EXECUTING		1
+#define RT_PUSH_IPI_RESTART		2
+
+static void tell_cpu_to_push(struct rq *rq)
+{
+	int cpu;
+
+	if (rq->rt.push_flags & RT_PUSH_IPI_EXECUTING) {
+		raw_spin_lock(&rq->rt.push_lock);
+		/* Make sure it's still executing */
+		if (rq->rt.push_flags & RT_PUSH_IPI_EXECUTING) {
+			/*
+			 * Tell the IPI to restart the loop as things have
+			 * changed since it started.
+			 */
+			rq->rt.push_flags |= RT_PUSH_IPI_RESTART;
+			raw_spin_unlock(&rq->rt.push_lock);
+			return;
+		}
+		raw_spin_unlock(&rq->rt.push_lock);
+	}
+
+	/* When here, there's no IPI going around */
+
+	rq->rt.push_cpu = rq->cpu;
+	cpu = find_next_push_cpu(rq);
+	if (cpu >= nr_cpu_ids)
+		return;
+
+	rq->rt.push_flags = RT_PUSH_IPI_EXECUTING;
+
+	irq_work_queue_on(&rq->rt.push_work, cpu);
+}
+
+/* Called from hardirq context */
+static void try_to_push_tasks(void *arg)
+{
+	struct rt_rq *rt_rq = arg;
+	struct rq *rq, *src_rq;
+	int this_cpu;
+	int cpu;
+
+	this_cpu = rt_rq->push_cpu;
+
+	/* Paranoid check */
+	BUG_ON(this_cpu != smp_processor_id());
+
+	rq = cpu_rq(this_cpu);
+	src_rq = rq_of_rt_rq(rt_rq);
+
+again:
+	if (has_pushable_tasks(rq)) {
+		raw_spin_lock(&rq->lock);
+		push_rt_task(rq);
+		raw_spin_unlock(&rq->lock);
+	}
+
+	/* Pass the IPI to the next rt overloaded queue */
+	raw_spin_lock(&rt_rq->push_lock);
+	/*
+	 * If the source queue changed since the IPI went out,
+	 * we need to restart the search from that CPU again.
+	 */
+	if (rt_rq->push_flags & RT_PUSH_IPI_RESTART) {
+		rt_rq->push_flags &= ~RT_PUSH_IPI_RESTART;
+		rt_rq->push_cpu = src_rq->cpu;
+	}
+
+	cpu = find_next_push_cpu(src_rq);
+
+	if (cpu >= nr_cpu_ids)
+		rt_rq->push_flags &= ~RT_PUSH_IPI_EXECUTING;
+	raw_spin_unlock(&rt_rq->push_lock);
+
+	if (cpu >= nr_cpu_ids)
+		return;
+
+	/*
+	 * It is possible that a restart caused this CPU to be
+	 * chosen again. Don't bother with an IPI, just see if we
+	 * have more to push.
+	 */
+	if (unlikely(cpu == rq->cpu))
+		goto again;
+
+	/* Try the next RT overloaded CPU */
+	irq_work_queue_on(&rt_rq->push_work, cpu);
+}
+
+static void push_irq_work_func(struct irq_work *work)
+{
+	struct rt_rq *rt_rq = container_of(work, struct rt_rq, push_work);
+
+	try_to_push_tasks(rt_rq);
+}
+#endif /* HAVE_RT_PUSH_IPI */
+
 static int pull_rt_task(struct rq *this_rq)
 {
 	int this_cpu = this_rq->cpu, ret = 0, cpu;
@@ -1793,6 +1963,13 @@ static int pull_rt_task(struct rq *this_rq)
 	 */
 	smp_rmb();
 
+#ifdef HAVE_RT_PUSH_IPI
+	if (sched_feat(RT_PUSH_IPI)) {
+		tell_cpu_to_push(this_rq);
+		return 0;
+	}
+#endif
+
 	for_each_cpu(cpu, this_rq->rd->rto_mask) {
 		if (this_cpu == cpu)
 			continue;

kernel/sched/sched.h

@@ -6,6 +6,7 @@
 #include <linux/mutex.h>
 #include <linux/spinlock.h>
 #include <linux/stop_machine.h>
+#include <linux/irq_work.h>
 #include <linux/tick.h>
 #include <linux/slab.h>
 
@@ -362,8 +363,14 @@ struct cfs_rq {
 	 * Under CFS, load is tracked on a per-entity basis and aggregated up.
 	 * This allows for the description of both thread and group usage (in
 	 * the FAIR_GROUP_SCHED case).
+	 * runnable_load_avg is the sum of the load_avg_contrib of the
+	 * sched_entities on the rq.
+	 * blocked_load_avg is similar to runnable_load_avg except that its
+	 * the blocked sched_entities on the rq.
+	 * utilization_load_avg is the sum of the average running time of the
+	 * sched_entities on the rq.
 	 */
-	unsigned long runnable_load_avg, blocked_load_avg;
+	unsigned long runnable_load_avg, blocked_load_avg, utilization_load_avg;
 	atomic64_t decay_counter;
 	u64 last_decay;
 	atomic_long_t removed_load;
@@ -418,6 +425,11 @@ static inline int rt_bandwidth_enabled(void)
 	return sysctl_sched_rt_runtime >= 0;
 }
 
+/* RT IPI pull logic requires IRQ_WORK */
+#ifdef CONFIG_IRQ_WORK
+# define HAVE_RT_PUSH_IPI
+#endif
+
 /* Real-Time classes' related field in a runqueue: */
 struct rt_rq {
 	struct rt_prio_array active;
@@ -435,7 +447,13 @@ struct rt_rq {
 	unsigned long rt_nr_total;
 	int overloaded;
 	struct plist_head pushable_tasks;
+#ifdef HAVE_RT_PUSH_IPI
+	int push_flags;
+	int push_cpu;
+	struct irq_work push_work;
+	raw_spinlock_t push_lock;
 #endif
+#endif /* CONFIG_SMP */
 	int rt_queued;
 
 	int rt_throttled;
@@ -597,6 +615,7 @@ struct rq {
 	struct sched_domain *sd;
 
 	unsigned long cpu_capacity;
+	unsigned long cpu_capacity_orig;
 
 	unsigned char idle_balance;
 	/* For active balancing */
@@ -807,7 +826,7 @@ struct sched_group_capacity {
 	 * CPU capacity of this group, SCHED_LOAD_SCALE being max capacity
 	 * for a single CPU.
 	 */
-	unsigned int capacity, capacity_orig;
+	unsigned int capacity;
 	unsigned long next_update;
 	int imbalance; /* XXX unrelated to capacity but shared group state */
 	/*
@@ -1368,9 +1387,18 @@ static inline int hrtick_enabled(struct rq *rq)
 
 #ifdef CONFIG_SMP
 extern void sched_avg_update(struct rq *rq);
+
+#ifndef arch_scale_freq_capacity
+static __always_inline
+unsigned long arch_scale_freq_capacity(struct sched_domain *sd, int cpu)
+{
+	return SCHED_CAPACITY_SCALE;
+}
+#endif
+
 static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta)
 {
-	rq->rt_avg += rt_delta;
+	rq->rt_avg += rt_delta * arch_scale_freq_capacity(NULL, cpu_of(rq));
 	sched_avg_update(rq);
 }
 #else
@@ -1643,8 +1671,8 @@ extern void print_rt_stats(struct seq_file *m, int cpu);
 extern void print_dl_stats(struct seq_file *m, int cpu);
 
 extern void init_cfs_rq(struct cfs_rq *cfs_rq);
-extern void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq);
-extern void init_dl_rq(struct dl_rq *dl_rq, struct rq *rq);
+extern void init_rt_rq(struct rt_rq *rt_rq);
+extern void init_dl_rq(struct dl_rq *dl_rq);
 
 extern void cfs_bandwidth_usage_inc(void);
 extern void cfs_bandwidth_usage_dec(void);