1 files changed, 301 insertions, 195 deletions

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index f6a05d9b5443..13950beb01a2 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -60,6 +60,14 @@ unsigned int sysctl_sched_min_granularity			= 750000ULL;
 static unsigned int normalized_sysctl_sched_min_granularity	= 750000ULL;
 
 /*
+ * Minimal preemption granularity for CPU-bound SCHED_IDLE tasks.
+ * Applies only when SCHED_IDLE tasks compete with normal tasks.
+ *
+ * (default: 0.75 msec)
+ */
+unsigned int sysctl_sched_idle_min_granularity			= 750000ULL;
+
+/*
  * This value is kept at sysctl_sched_latency/sysctl_sched_min_granularity
  */
 static unsigned int sched_nr_latency = 8;
@@ -665,6 +673,8 @@ static u64 __sched_period(unsigned long nr_running)
 		return sysctl_sched_latency;
 }
 
+static bool sched_idle_cfs_rq(struct cfs_rq *cfs_rq);
+
 /*
  * We calculate the wall-time slice from the period by taking a part
  * proportional to the weight.
@@ -674,6 +684,8 @@ static u64 __sched_period(unsigned long nr_running)
 static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	unsigned int nr_running = cfs_rq->nr_running;
+	struct sched_entity *init_se = se;
+	unsigned int min_gran;
 	u64 slice;
 
 	if (sched_feat(ALT_PERIOD))
@@ -684,12 +696,13 @@ static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	for_each_sched_entity(se) {
 		struct load_weight *load;
 		struct load_weight lw;
+		struct cfs_rq *qcfs_rq;
 
-		cfs_rq = cfs_rq_of(se);
-		load = &cfs_rq->load;
+		qcfs_rq = cfs_rq_of(se);
+		load = &qcfs_rq->load;
 
 		if (unlikely(!se->on_rq)) {
-			lw = cfs_rq->load;
+			lw = qcfs_rq->load;
 
 			update_load_add(&lw, se->load.weight);
 			load = &lw;
@@ -697,8 +710,14 @@ static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		slice = __calc_delta(slice, se->load.weight, load);
 	}
 
-	if (sched_feat(BASE_SLICE))
-		slice = max(slice, (u64)sysctl_sched_min_granularity);
+	if (sched_feat(BASE_SLICE)) {
+		if (se_is_idle(init_se) && !sched_idle_cfs_rq(cfs_rq))
+			min_gran = sysctl_sched_idle_min_granularity;
+		else
+			min_gran = sysctl_sched_min_granularity;
+
+		slice = max_t(u64, slice, min_gran);
+	}
 
 	return slice;
 }
@@ -837,8 +856,13 @@ static void update_curr(struct cfs_rq *cfs_rq)
 
 	curr->exec_start = now;
 
-	schedstat_set(curr->statistics.exec_max,
-		      max(delta_exec, curr->statistics.exec_max));
+	if (schedstat_enabled()) {
+		struct sched_statistics *stats;
+
+		stats = __schedstats_from_se(curr);
+		__schedstat_set(stats->exec_max,
+				max(delta_exec, stats->exec_max));
+	}
 
 	curr->sum_exec_runtime += delta_exec;
 	schedstat_add(cfs_rq->exec_clock, delta_exec);
@@ -863,137 +887,70 @@ static void update_curr_fair(struct rq *rq)
 }
 
 static inline void
-update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
+update_stats_wait_start_fair(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	u64 wait_start, prev_wait_start;
+	struct sched_statistics *stats;
+	struct task_struct *p = NULL;
 
 	if (!schedstat_enabled())
 		return;
 
-	wait_start = rq_clock(rq_of(cfs_rq));
-	prev_wait_start = schedstat_val(se->statistics.wait_start);
+	stats = __schedstats_from_se(se);
 
-	if (entity_is_task(se) && task_on_rq_migrating(task_of(se)) &&
-	    likely(wait_start > prev_wait_start))
-		wait_start -= prev_wait_start;
+	if (entity_is_task(se))
+		p = task_of(se);
 
-	__schedstat_set(se->statistics.wait_start, wait_start);
+	__update_stats_wait_start(rq_of(cfs_rq), p, stats);
 }
 
 static inline void
-update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
+update_stats_wait_end_fair(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	struct task_struct *p;
-	u64 delta;
+	struct sched_statistics *stats;
+	struct task_struct *p = NULL;
 
 	if (!schedstat_enabled())
 		return;
 
+	stats = __schedstats_from_se(se);
+
 	/*
 	 * 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)))
+	if (unlikely(!schedstat_val(stats->wait_start)))
 		return;
 
-	delta = rq_clock(rq_of(cfs_rq)) - schedstat_val(se->statistics.wait_start);
-
-	if (entity_is_task(se)) {
+	if (entity_is_task(se))
 		p = task_of(se);
-		if (task_on_rq_migrating(p)) {
-			/*
-			 * Preserve migrating task's wait time so wait_start
-			 * time stamp can be adjusted to accumulate wait time
-			 * prior to migration.
-			 */
-			__schedstat_set(se->statistics.wait_start, delta);
-			return;
-		}
-		trace_sched_stat_wait(p, delta);
-	}
 
-	__schedstat_set(se->statistics.wait_max,
-		      max(schedstat_val(se->statistics.wait_max), delta));
-	__schedstat_inc(se->statistics.wait_count);
-	__schedstat_add(se->statistics.wait_sum, delta);
-	__schedstat_set(se->statistics.wait_start, 0);
+	__update_stats_wait_end(rq_of(cfs_rq), p, stats);
 }
 
 static inline void
-update_stats_enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
+update_stats_enqueue_sleeper_fair(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
+	struct sched_statistics *stats;
 	struct task_struct *tsk = NULL;
-	u64 sleep_start, block_start;
 
 	if (!schedstat_enabled())
 		return;
 
-	sleep_start = schedstat_val(se->statistics.sleep_start);
-	block_start = schedstat_val(se->statistics.block_start);
+	stats = __schedstats_from_se(se);
 
 	if (entity_is_task(se))
 		tsk = task_of(se);
 
-	if (sleep_start) {
-		u64 delta = rq_clock(rq_of(cfs_rq)) - sleep_start;
-
-		if ((s64)delta < 0)
-			delta = 0;
-
-		if (unlikely(delta > schedstat_val(se->statistics.sleep_max)))
-			__schedstat_set(se->statistics.sleep_max, delta);
-
-		__schedstat_set(se->statistics.sleep_start, 0);
-		__schedstat_add(se->statistics.sum_sleep_runtime, delta);
-
-		if (tsk) {
-			account_scheduler_latency(tsk, delta >> 10, 1);
-			trace_sched_stat_sleep(tsk, delta);
-		}
-	}
-	if (block_start) {
-		u64 delta = rq_clock(rq_of(cfs_rq)) - block_start;
-
-		if ((s64)delta < 0)
-			delta = 0;
-
-		if (unlikely(delta > schedstat_val(se->statistics.block_max)))
-			__schedstat_set(se->statistics.block_max, delta);
-
-		__schedstat_set(se->statistics.block_start, 0);
-		__schedstat_add(se->statistics.sum_sleep_runtime, delta);
-
-		if (tsk) {
-			if (tsk->in_iowait) {
-				__schedstat_add(se->statistics.iowait_sum, delta);
-				__schedstat_inc(se->statistics.iowait_count);
-				trace_sched_stat_iowait(tsk, delta);
-			}
-
-			trace_sched_stat_blocked(tsk, delta);
-
-			/*
-			 * Blocking time is in units of nanosecs, so shift by
-			 * 20 to get a milliseconds-range estimation of the
-			 * amount of time that the task spent sleeping:
-			 */
-			if (unlikely(prof_on == SLEEP_PROFILING)) {
-				profile_hits(SLEEP_PROFILING,
-						(void *)get_wchan(tsk),
-						delta >> 20);
-			}
-			account_scheduler_latency(tsk, delta >> 10, 0);
-		}
-	}
+	__update_stats_enqueue_sleeper(rq_of(cfs_rq), tsk, stats);
 }
 
 /*
  * Task is being enqueued - update stats:
  */
 static inline void
-update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
+update_stats_enqueue_fair(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 {
 	if (!schedstat_enabled())
 		return;
@@ -1003,14 +960,14 @@ update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	 * a dequeue/enqueue event is a NOP)
 	 */
 	if (se != cfs_rq->curr)
-		update_stats_wait_start(cfs_rq, se);
+		update_stats_wait_start_fair(cfs_rq, se);
 
 	if (flags & ENQUEUE_WAKEUP)
-		update_stats_enqueue_sleeper(cfs_rq, se);
+		update_stats_enqueue_sleeper_fair(cfs_rq, se);
 }
 
 static inline void
-update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
+update_stats_dequeue_fair(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 {
 
 	if (!schedstat_enabled())
@@ -1021,7 +978,7 @@ update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	 * waiting task:
 	 */
 	if (se != cfs_rq->curr)
-		update_stats_wait_end(cfs_rq, se);
+		update_stats_wait_end_fair(cfs_rq, se);
 
 	if ((flags & DEQUEUE_SLEEP) && entity_is_task(se)) {
 		struct task_struct *tsk = task_of(se);
@@ -1030,10 +987,10 @@ update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 		/* XXX racy against TTWU */
 		state = READ_ONCE(tsk->__state);
 		if (state & TASK_INTERRUPTIBLE)
-			__schedstat_set(se->statistics.sleep_start,
+			__schedstat_set(tsk->stats.sleep_start,
 				      rq_clock(rq_of(cfs_rq)));
 		if (state & TASK_UNINTERRUPTIBLE)
-			__schedstat_set(se->statistics.block_start,
+			__schedstat_set(tsk->stats.block_start,
 				      rq_clock(rq_of(cfs_rq)));
 	}
 }
@@ -1081,11 +1038,12 @@ struct numa_group {
 	unsigned long total_faults;
 	unsigned long max_faults_cpu;
 	/*
+	 * faults[] array is split into two regions: faults_mem and faults_cpu.
+	 *
 	 * Faults_cpu is used to decide whether memory should move
 	 * towards the CPU. As a consequence, these stats are weighted
 	 * more by CPU use than by memory faults.
 	 */
-	unsigned long *faults_cpu;
 	unsigned long faults[];
 };
 
@@ -1259,8 +1217,8 @@ static inline unsigned long group_faults(struct task_struct *p, int nid)
 
 static inline unsigned long group_faults_cpu(struct numa_group *group, int nid)
 {
-	return group->faults_cpu[task_faults_idx(NUMA_MEM, nid, 0)] +
-		group->faults_cpu[task_faults_idx(NUMA_MEM, nid, 1)];
+	return group->faults[task_faults_idx(NUMA_CPU, nid, 0)] +
+		group->faults[task_faults_idx(NUMA_CPU, nid, 1)];
 }
 
 static inline unsigned long group_faults_priv(struct numa_group *ng)
@@ -2116,7 +2074,7 @@ static void numa_migrate_preferred(struct task_struct *p)
 }
 
 /*
- * Find out how many nodes on the workload is actively running on. Do this by
+ * Find out how many nodes the workload is actively running on. Do this by
  * tracking the nodes from which NUMA hinting faults are triggered. This can
  * be different from the set of nodes where the workload's memory is currently
  * located.
@@ -2170,7 +2128,7 @@ static void update_task_scan_period(struct task_struct *p,
 
 	/*
 	 * If there were no record hinting faults then either the task is
-	 * completely idle or all activity is areas that are not of interest
+	 * completely idle or all activity is in areas that are not of interest
 	 * to automatic numa balancing. Related to that, if there were failed
 	 * migration then it implies we are migrating too quickly or the local
 	 * node is overloaded. In either case, scan slower
@@ -2427,7 +2385,7 @@ static void task_numa_placement(struct task_struct *p)
 				 * is at the beginning of the numa_faults array.
 				 */
 				ng->faults[mem_idx] += diff;
-				ng->faults_cpu[mem_idx] += f_diff;
+				ng->faults[cpu_idx] += f_diff;
 				ng->total_faults += diff;
 				group_faults += ng->faults[mem_idx];
 			}
@@ -2481,7 +2439,8 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags,
 
 	if (unlikely(!deref_curr_numa_group(p))) {
 		unsigned int size = sizeof(struct numa_group) +
-				    4*nr_node_ids*sizeof(unsigned long);
+				    NR_NUMA_HINT_FAULT_STATS *
+				    nr_node_ids * sizeof(unsigned long);
 
 		grp = kzalloc(size, GFP_KERNEL | __GFP_NOWARN);
 		if (!grp)
@@ -2492,9 +2451,6 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags,
 		grp->max_faults_cpu = 0;
 		spin_lock_init(&grp->lock);
 		grp->gid = p->pid;
-		/* Second half of the array tracks nids where faults happen */
-		grp->faults_cpu = grp->faults + NR_NUMA_HINT_FAULT_TYPES *
-						nr_node_ids;
 
 		for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++)
 			grp->faults[i] = p->numa_faults[i];
@@ -2995,6 +2951,8 @@ account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	}
 #endif
 	cfs_rq->nr_running++;
+	if (se_is_idle(se))
+		cfs_rq->idle_nr_running++;
 }
 
 static void
@@ -3008,6 +2966,8 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	}
 #endif
 	cfs_rq->nr_running--;
+	if (se_is_idle(se))
+		cfs_rq->idle_nr_running--;
 }
 
 /*
@@ -4207,7 +4167,12 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 
 	/* sleeps up to a single latency don't count. */
 	if (!initial) {
-		unsigned long thresh = sysctl_sched_latency;
+		unsigned long thresh;
+
+		if (se_is_idle(se))
+			thresh = sysctl_sched_min_granularity;
+		else
+			thresh = sysctl_sched_latency;
 
 		/*
 		 * Halve their sleep time's effect, to allow
@@ -4225,26 +4190,6 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 
 static void check_enqueue_throttle(struct cfs_rq *cfs_rq);
 
-static inline void check_schedstat_required(void)
-{
-#ifdef CONFIG_SCHEDSTATS
-	if (schedstat_enabled())
-		return;
-
-	/* Force schedstat enabled if a dependent tracepoint is active */
-	if (trace_sched_stat_wait_enabled()    ||
-			trace_sched_stat_sleep_enabled()   ||
-			trace_sched_stat_iowait_enabled()  ||
-			trace_sched_stat_blocked_enabled() ||
-			trace_sched_stat_runtime_enabled())  {
-		printk_deferred_once("Scheduler tracepoints stat_sleep, stat_iowait, "
-			     "stat_blocked and stat_runtime require the "
-			     "kernel parameter schedstats=enable or "
-			     "kernel.sched_schedstats=1\n");
-	}
-#endif
-}
-
 static inline bool cfs_bandwidth_used(void);
 
 /*
@@ -4318,7 +4263,7 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 		place_entity(cfs_rq, se, 0);
 
 	check_schedstat_required();
-	update_stats_enqueue(cfs_rq, se, flags);
+	update_stats_enqueue_fair(cfs_rq, se, flags);
 	check_spread(cfs_rq, se);
 	if (!curr)
 		__enqueue_entity(cfs_rq, se);
@@ -4402,7 +4347,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	update_load_avg(cfs_rq, se, UPDATE_TG);
 	se_update_runnable(se);
 
-	update_stats_dequeue(cfs_rq, se, flags);
+	update_stats_dequeue_fair(cfs_rq, se, flags);
 
 	clear_buddies(cfs_rq, se);
 
@@ -4487,7 +4432,7 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		 * a CPU. So account for the time it spent waiting on the
 		 * runqueue.
 		 */
-		update_stats_wait_end(cfs_rq, se);
+		update_stats_wait_end_fair(cfs_rq, se);
 		__dequeue_entity(cfs_rq, se);
 		update_load_avg(cfs_rq, se, UPDATE_TG);
 	}
@@ -4502,9 +4447,12 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	 */
 	if (schedstat_enabled() &&
 	    rq_of(cfs_rq)->cfs.load.weight >= 2*se->load.weight) {
-		schedstat_set(se->statistics.slice_max,
-			max((u64)schedstat_val(se->statistics.slice_max),
-			    se->sum_exec_runtime - se->prev_sum_exec_runtime));
+		struct sched_statistics *stats;
+
+		stats = __schedstats_from_se(se);
+		__schedstat_set(stats->slice_max,
+				max((u64)stats->slice_max,
+				    se->sum_exec_runtime - se->prev_sum_exec_runtime));
 	}
 
 	se->prev_sum_exec_runtime = se->sum_exec_runtime;
@@ -4586,7 +4534,7 @@ static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev)
 	check_spread(cfs_rq, prev);
 
 	if (prev->on_rq) {
-		update_stats_wait_start(cfs_rq, prev);
+		update_stats_wait_start_fair(cfs_rq, prev);
 		/* Put 'current' back into the tree. */
 		__enqueue_entity(cfs_rq, prev);
 		/* in !on_rq case, update occurred at dequeue */
@@ -4687,11 +4635,20 @@ static inline u64 sched_cfs_bandwidth_slice(void)
  */
 void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b)
 {
+	s64 runtime;
+
 	if (unlikely(cfs_b->quota == RUNTIME_INF))
 		return;
 
 	cfs_b->runtime += cfs_b->quota;
+	runtime = cfs_b->runtime_snap - cfs_b->runtime;
+	if (runtime > 0) {
+		cfs_b->burst_time += runtime;
+		cfs_b->nr_burst++;
+	}
+
 	cfs_b->runtime = min(cfs_b->runtime, cfs_b->quota + cfs_b->burst);
+	cfs_b->runtime_snap = cfs_b->runtime;
 }
 
 static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg)
@@ -5577,6 +5534,17 @@ static int sched_idle_rq(struct rq *rq)
 			rq->nr_running);
 }
 
+/*
+ * Returns true if cfs_rq only has SCHED_IDLE entities enqueued. Note the use
+ * of idle_nr_running, which does not consider idle descendants of normal
+ * entities.
+ */
+static bool sched_idle_cfs_rq(struct cfs_rq *cfs_rq)
+{
+	return cfs_rq->nr_running &&
+		cfs_rq->nr_running == cfs_rq->idle_nr_running;
+}
+
 #ifdef CONFIG_SMP
 static int sched_idle_cpu(int cpu)
 {
@@ -5787,6 +5755,7 @@ static struct {
 	cpumask_var_t idle_cpus_mask;
 	atomic_t nr_cpus;
 	int has_blocked;		/* Idle CPUS has blocked load */
+	int needs_update;		/* Newly idle CPUs need their next_balance collated */
 	unsigned long next_balance;     /* in jiffy units */
 	unsigned long next_blocked;	/* Next update of blocked load in jiffies */
 } nohz ____cacheline_aligned;
@@ -5997,12 +5966,12 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p,
 	if (sched_feat(WA_WEIGHT) && target == nr_cpumask_bits)
 		target = wake_affine_weight(sd, p, this_cpu, prev_cpu, sync);
 
-	schedstat_inc(p->se.statistics.nr_wakeups_affine_attempts);
+	schedstat_inc(p->stats.nr_wakeups_affine_attempts);
 	if (target == nr_cpumask_bits)
 		return prev_cpu;
 
 	schedstat_inc(sd->ttwu_move_affine);
-	schedstat_inc(p->se.statistics.nr_wakeups_affine);
+	schedstat_inc(p->stats.nr_wakeups_affine);
 	return target;
 }
 
@@ -6443,11 +6412,6 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 	    (available_idle_cpu(recent_used_cpu) || sched_idle_cpu(recent_used_cpu)) &&
 	    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:
-		 */
-		p->recent_used_cpu = prev;
 		return recent_used_cpu;
 	}
 
@@ -7806,7 +7770,7 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
 	if (!cpumask_test_cpu(env->dst_cpu, p->cpus_ptr)) {
 		int cpu;
 
-		schedstat_inc(p->se.statistics.nr_failed_migrations_affine);
+		schedstat_inc(p->stats.nr_failed_migrations_affine);
 
 		env->flags |= LBF_SOME_PINNED;
 
@@ -7840,7 +7804,7 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
 	env->flags &= ~LBF_ALL_PINNED;
 
 	if (task_running(env->src_rq, p)) {
-		schedstat_inc(p->se.statistics.nr_failed_migrations_running);
+		schedstat_inc(p->stats.nr_failed_migrations_running);
 		return 0;
 	}
 
@@ -7862,12 +7826,12 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
 	    env->sd->nr_balance_failed > env->sd->cache_nice_tries) {
 		if (tsk_cache_hot == 1) {
 			schedstat_inc(env->sd->lb_hot_gained[env->idle]);
-			schedstat_inc(p->se.statistics.nr_forced_migrations);
+			schedstat_inc(p->stats.nr_forced_migrations);
 		}
 		return 1;
 	}
 
-	schedstat_inc(p->se.statistics.nr_failed_migrations_hot);
+	schedstat_inc(p->stats.nr_failed_migrations_hot);
 	return 0;
 }
 
@@ -8602,6 +8566,99 @@ group_type group_classify(unsigned int imbalance_pct,
 }
 
 /**
+ * asym_smt_can_pull_tasks - Check whether the load balancing CPU can pull tasks
+ * @dst_cpu:	Destination CPU of the load balancing
+ * @sds:	Load-balancing data with statistics of the local group
+ * @sgs:	Load-balancing statistics of the candidate busiest group
+ * @sg:		The candidate busiest group
+ *
+ * Check the state of the SMT siblings of both @sds::local and @sg and decide
+ * if @dst_cpu can pull tasks.
+ *
+ * If @dst_cpu does not have SMT siblings, it can pull tasks if two or more of
+ * the SMT siblings of @sg are busy. If only one CPU in @sg is busy, pull tasks
+ * only if @dst_cpu has higher priority.
+ *
+ * If both @dst_cpu and @sg have SMT siblings, and @sg has exactly one more
+ * busy CPU than @sds::local, let @dst_cpu pull tasks if it has higher priority.
+ * Bigger imbalances in the number of busy CPUs will be dealt with in
+ * update_sd_pick_busiest().
+ *
+ * If @sg does not have SMT siblings, only pull tasks if all of the SMT siblings
+ * of @dst_cpu are idle and @sg has lower priority.
+ */
+static bool asym_smt_can_pull_tasks(int dst_cpu, struct sd_lb_stats *sds,
+				    struct sg_lb_stats *sgs,
+				    struct sched_group *sg)
+{
+#ifdef CONFIG_SCHED_SMT
+	bool local_is_smt, sg_is_smt;
+	int sg_busy_cpus;
+
+	local_is_smt = sds->local->flags & SD_SHARE_CPUCAPACITY;
+	sg_is_smt = sg->flags & SD_SHARE_CPUCAPACITY;
+
+	sg_busy_cpus = sgs->group_weight - sgs->idle_cpus;
+
+	if (!local_is_smt) {
+		/*
+		 * If we are here, @dst_cpu is idle and does not have SMT
+		 * siblings. Pull tasks if candidate group has two or more
+		 * busy CPUs.
+		 */
+		if (sg_busy_cpus >= 2) /* implies sg_is_smt */
+			return true;
+
+		/*
+		 * @dst_cpu does not have SMT siblings. @sg may have SMT
+		 * siblings and only one is busy. In such case, @dst_cpu
+		 * can help if it has higher priority and is idle (i.e.,
+		 * it has no running tasks).
+		 */
+		return sched_asym_prefer(dst_cpu, sg->asym_prefer_cpu);
+	}
+
+	/* @dst_cpu has SMT siblings. */
+
+	if (sg_is_smt) {
+		int local_busy_cpus = sds->local->group_weight -
+				      sds->local_stat.idle_cpus;
+		int busy_cpus_delta = sg_busy_cpus - local_busy_cpus;
+
+		if (busy_cpus_delta == 1)
+			return sched_asym_prefer(dst_cpu, sg->asym_prefer_cpu);
+
+		return false;
+	}
+
+	/*
+	 * @sg does not have SMT siblings. Ensure that @sds::local does not end
+	 * up with more than one busy SMT sibling and only pull tasks if there
+	 * are not busy CPUs (i.e., no CPU has running tasks).
+	 */
+	if (!sds->local_stat.sum_nr_running)
+		return sched_asym_prefer(dst_cpu, sg->asym_prefer_cpu);
+
+	return false;
+#else
+	/* Always return false so that callers deal with non-SMT cases. */
+	return false;
+#endif
+}
+
+static inline bool
+sched_asym(struct lb_env *env, struct sd_lb_stats *sds,  struct sg_lb_stats *sgs,
+	   struct sched_group *group)
+{
+	/* Only do SMT checks if either local or candidate have SMT siblings */
+	if ((sds->local->flags & SD_SHARE_CPUCAPACITY) ||
+	    (group->flags & SD_SHARE_CPUCAPACITY))
+		return asym_smt_can_pull_tasks(env->dst_cpu, sds, sgs, group);
+
+	return sched_asym_prefer(env->dst_cpu, group->asym_prefer_cpu);
+}
+
+/**
  * update_sg_lb_stats - Update sched_group's statistics for load balancing.
  * @env: The load balancing environment.
  * @group: sched_group whose statistics are to be updated.
@@ -8609,6 +8666,7 @@ group_type group_classify(unsigned int imbalance_pct,
  * @sg_status: Holds flag indicating the status of the sched_group
  */
 static inline void update_sg_lb_stats(struct lb_env *env,
+				      struct sd_lb_stats *sds,
 				      struct sched_group *group,
 				      struct sg_lb_stats *sgs,
 				      int *sg_status)
@@ -8617,7 +8675,7 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 
 	memset(sgs, 0, sizeof(*sgs));
 
-	local_group = cpumask_test_cpu(env->dst_cpu, sched_group_span(group));
+	local_group = group == sds->local;
 
 	for_each_cpu_and(i, sched_group_span(group), env->cpus) {
 		struct rq *rq = cpu_rq(i);
@@ -8660,18 +8718,17 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 		}
 	}
 
-	/* Check if dst CPU is idle and preferred to this group */
-	if (env->sd->flags & SD_ASYM_PACKING &&
-	    env->idle != CPU_NOT_IDLE &&
-	    sgs->sum_h_nr_running &&
-	    sched_asym_prefer(env->dst_cpu, group->asym_prefer_cpu)) {
-		sgs->group_asym_packing = 1;
-	}
-
 	sgs->group_capacity = group->sgc->capacity;
 
 	sgs->group_weight = group->group_weight;
 
+	/* Check if dst CPU is idle and preferred to this group */
+	if (!local_group && env->sd->flags & SD_ASYM_PACKING &&
+	    env->idle != CPU_NOT_IDLE && sgs->sum_h_nr_running &&
+	    sched_asym(env, sds, sgs, group)) {
+		sgs->group_asym_packing = 1;
+	}
+
 	sgs->group_type = group_classify(env->sd->imbalance_pct, group, sgs);
 
 	/* Computing avg_load makes sense only when group is overloaded */
@@ -9180,7 +9237,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
 				update_group_capacity(env->sd, env->dst_cpu);
 		}
 
-		update_sg_lb_stats(env, sg, sgs, &sg_status);
+		update_sg_lb_stats(env, sds, sg, sgs, &sg_status);
 
 		if (local_group)
 			goto next_group;
@@ -9603,6 +9660,12 @@ static struct rq *find_busiest_queue(struct lb_env *env,
 		    nr_running == 1)
 			continue;
 
+		/* Make sure we only pull tasks from a CPU of lower priority */
+		if ((env->sd->flags & SD_ASYM_PACKING) &&
+		    sched_asym_prefer(i, env->dst_cpu) &&
+		    nr_running == 1)
+			continue;
+
 		switch (env->migration_type) {
 		case migrate_load:
 			/*
@@ -10176,6 +10239,30 @@ void update_max_interval(void)
 	max_load_balance_interval = HZ*num_online_cpus()/10;
 }
 
+static inline bool update_newidle_cost(struct sched_domain *sd, u64 cost)
+{
+	if (cost > sd->max_newidle_lb_cost) {
+		/*
+		 * Track max cost of a domain to make sure to not delay the
+		 * next wakeup on the CPU.
+		 */
+		sd->max_newidle_lb_cost = cost;
+		sd->last_decay_max_lb_cost = jiffies;
+	} else if (time_after(jiffies, sd->last_decay_max_lb_cost + HZ)) {
+		/*
+		 * Decay the newidle max times by ~1% per second to ensure that
+		 * it is not outdated and the current max cost is actually
+		 * shorter.
+		 */
+		sd->max_newidle_lb_cost = (sd->max_newidle_lb_cost * 253) / 256;
+		sd->last_decay_max_lb_cost = jiffies;
+
+		return true;
+	}
+
+	return false;
+}
+
 /*
  * It checks each scheduling domain to see if it is due to be balanced,
  * and initiates a balancing operation if so.
@@ -10199,14 +10286,9 @@ static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle)
 	for_each_domain(cpu, sd) {
 		/*
 		 * Decay the newidle max times here because this is a regular
-		 * visit to all the domains. Decay ~1% per second.
+		 * visit to all the domains.
 		 */
-		if (time_after(jiffies, sd->next_decay_max_lb_cost)) {
-			sd->max_newidle_lb_cost =
-				(sd->max_newidle_lb_cost * 253) / 256;
-			sd->next_decay_max_lb_cost = jiffies + HZ;
-			need_decay = 1;
-		}
+		need_decay = update_newidle_cost(sd, 0);
 		max_cost += sd->max_newidle_lb_cost;
 
 		/*
@@ -10375,7 +10457,7 @@ static void nohz_balancer_kick(struct rq *rq)
 		goto out;
 
 	if (rq->nr_running >= 2) {
-		flags = NOHZ_KICK_MASK;
+		flags = NOHZ_STATS_KICK | NOHZ_BALANCE_KICK;
 		goto out;
 	}
 
@@ -10389,7 +10471,7 @@ static void nohz_balancer_kick(struct rq *rq)
 		 * on.
 		 */
 		if (rq->cfs.h_nr_running >= 1 && check_cpu_capacity(rq, sd)) {
-			flags = NOHZ_KICK_MASK;
+			flags = NOHZ_STATS_KICK | NOHZ_BALANCE_KICK;
 			goto unlock;
 		}
 	}
@@ -10403,7 +10485,7 @@ static void nohz_balancer_kick(struct rq *rq)
 		 */
 		for_each_cpu_and(i, sched_domain_span(sd), nohz.idle_cpus_mask) {
 			if (sched_asym_prefer(i, cpu)) {
-				flags = NOHZ_KICK_MASK;
+				flags = NOHZ_STATS_KICK | NOHZ_BALANCE_KICK;
 				goto unlock;
 			}
 		}
@@ -10416,7 +10498,7 @@ static void nohz_balancer_kick(struct rq *rq)
 		 * to run the misfit task on.
 		 */
 		if (check_misfit_status(rq, sd)) {
-			flags = NOHZ_KICK_MASK;
+			flags = NOHZ_STATS_KICK | NOHZ_BALANCE_KICK;
 			goto unlock;
 		}
 
@@ -10443,13 +10525,16 @@ static void nohz_balancer_kick(struct rq *rq)
 		 */
 		nr_busy = atomic_read(&sds->nr_busy_cpus);
 		if (nr_busy > 1) {
-			flags = NOHZ_KICK_MASK;
+			flags = NOHZ_STATS_KICK | NOHZ_BALANCE_KICK;
 			goto unlock;
 		}
 	}
 unlock:
 	rcu_read_unlock();
 out:
+	if (READ_ONCE(nohz.needs_update))
+		flags |= NOHZ_NEXT_KICK;
+
 	if (flags)
 		kick_ilb(flags);
 }
@@ -10546,12 +10631,13 @@ void nohz_balance_enter_idle(int cpu)
 	/*
 	 * Ensures that if nohz_idle_balance() fails to observe our
 	 * @idle_cpus_mask store, it must observe the @has_blocked
-	 * store.
+	 * and @needs_update stores.
 	 */
 	smp_mb__after_atomic();
 
 	set_cpu_sd_state_idle(cpu);
 
+	WRITE_ONCE(nohz.needs_update, 1);
 out:
 	/*
 	 * Each time a cpu enter idle, we assume that it has blocked load and
@@ -10600,12 +10686,17 @@ static void _nohz_idle_balance(struct rq *this_rq, unsigned int flags,
 	/*
 	 * We assume there will be no idle load after this update and clear
 	 * the has_blocked flag. If a cpu enters idle in the mean time, it will
-	 * set the has_blocked flag and trig another update of idle load.
+	 * set the has_blocked flag and trigger another update of idle load.
 	 * Because a cpu that becomes idle, is added to idle_cpus_mask before
 	 * setting the flag, we are sure to not clear the state and not
 	 * check the load of an idle cpu.
+	 *
+	 * Same applies to idle_cpus_mask vs needs_update.
 	 */
-	WRITE_ONCE(nohz.has_blocked, 0);
+	if (flags & NOHZ_STATS_KICK)
+		WRITE_ONCE(nohz.has_blocked, 0);
+	if (flags & NOHZ_NEXT_KICK)
+		WRITE_ONCE(nohz.needs_update, 0);
 
 	/*
 	 * Ensures that if we miss the CPU, we must see the has_blocked
@@ -10627,13 +10718,17 @@ static void _nohz_idle_balance(struct rq *this_rq, unsigned int flags,
 		 * balancing owner will pick it up.
 		 */
 		if (need_resched()) {
-			has_blocked_load = true;
+			if (flags & NOHZ_STATS_KICK)
+				has_blocked_load = true;
+			if (flags & NOHZ_NEXT_KICK)
+				WRITE_ONCE(nohz.needs_update, 1);
 			goto abort;
 		}
 
 		rq = cpu_rq(balance_cpu);
 
-		has_blocked_load |= update_nohz_stats(rq);
+		if (flags & NOHZ_STATS_KICK)
+			has_blocked_load |= update_nohz_stats(rq);
 
 		/*
 		 * If time for next balance is due,
@@ -10664,8 +10759,9 @@ static void _nohz_idle_balance(struct rq *this_rq, unsigned int flags,
 	if (likely(update_next_balance))
 		nohz.next_balance = next_balance;
 
-	WRITE_ONCE(nohz.next_blocked,
-		now + msecs_to_jiffies(LOAD_AVG_PERIOD));
+	if (flags & NOHZ_STATS_KICK)
+		WRITE_ONCE(nohz.next_blocked,
+			   now + msecs_to_jiffies(LOAD_AVG_PERIOD));
 
 abort:
 	/* There is still blocked load, enable periodic update */
@@ -10763,9 +10859,9 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf)
 {
 	unsigned long next_balance = jiffies + HZ;
 	int this_cpu = this_rq->cpu;
+	u64 t0, t1, curr_cost = 0;
 	struct sched_domain *sd;
 	int pulled_task = 0;
-	u64 curr_cost = 0;
 
 	update_misfit_status(NULL, this_rq);
 
@@ -10796,47 +10892,49 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf)
 	 */
 	rq_unpin_lock(this_rq, rf);
 
-	if (this_rq->avg_idle < sysctl_sched_migration_cost ||
-	    !READ_ONCE(this_rq->rd->overload)) {
+	rcu_read_lock();
+	sd = rcu_dereference_check_sched_domain(this_rq->sd);
+
+	if (!READ_ONCE(this_rq->rd->overload) ||
+	    (sd && this_rq->avg_idle < sd->max_newidle_lb_cost)) {
 
-		rcu_read_lock();
-		sd = rcu_dereference_check_sched_domain(this_rq->sd);
 		if (sd)
 			update_next_balance(sd, &next_balance);
 		rcu_read_unlock();
 
 		goto out;
 	}
+	rcu_read_unlock();
 
 	raw_spin_rq_unlock(this_rq);
 
+	t0 = sched_clock_cpu(this_cpu);
 	update_blocked_averages(this_cpu);
+
 	rcu_read_lock();
 	for_each_domain(this_cpu, sd) {
 		int continue_balancing = 1;
-		u64 t0, domain_cost;
+		u64 domain_cost;
 
-		if (this_rq->avg_idle < curr_cost + sd->max_newidle_lb_cost) {
-			update_next_balance(sd, &next_balance);
+		update_next_balance(sd, &next_balance);
+
+		if (this_rq->avg_idle < curr_cost + sd->max_newidle_lb_cost)
 			break;
-		}
 
 		if (sd->flags & SD_BALANCE_NEWIDLE) {
-			t0 = sched_clock_cpu(this_cpu);
 
 			pulled_task = load_balance(this_cpu, this_rq,
 						   sd, CPU_NEWLY_IDLE,
 						   &continue_balancing);
 
-			domain_cost = sched_clock_cpu(this_cpu) - t0;
-			if (domain_cost > sd->max_newidle_lb_cost)
-				sd->max_newidle_lb_cost = domain_cost;
+			t1 = sched_clock_cpu(this_cpu);
+			domain_cost = t1 - t0;
+			update_newidle_cost(sd, domain_cost);
 
 			curr_cost += domain_cost;
+			t0 = t1;
 		}
 
-		update_next_balance(sd, &next_balance);
-
 		/*
 		 * Stop searching for tasks to pull if there are
 		 * now runnable tasks on this rq.
@@ -11394,7 +11492,7 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
 		if (!cfs_rq)
 			goto err;
 
-		se = kzalloc_node(sizeof(struct sched_entity),
+		se = kzalloc_node(sizeof(struct sched_entity_stats),
 				  GFP_KERNEL, cpu_to_node(i));
 		if (!se)
 			goto err_free_rq;
@@ -11560,7 +11658,7 @@ int sched_group_set_idle(struct task_group *tg, long idle)
 	for_each_possible_cpu(i) {
 		struct rq *rq = cpu_rq(i);
 		struct sched_entity *se = tg->se[i];
-		struct cfs_rq *grp_cfs_rq = tg->cfs_rq[i];
+		struct cfs_rq *parent_cfs_rq, *grp_cfs_rq = tg->cfs_rq[i];
 		bool was_idle = cfs_rq_is_idle(grp_cfs_rq);
 		long idle_task_delta;
 		struct rq_flags rf;
@@ -11571,6 +11669,14 @@ int sched_group_set_idle(struct task_group *tg, long idle)
 		if (WARN_ON_ONCE(was_idle == cfs_rq_is_idle(grp_cfs_rq)))
 			goto next_cpu;
 
+		if (se->on_rq) {
+			parent_cfs_rq = cfs_rq_of(se);
+			if (cfs_rq_is_idle(grp_cfs_rq))
+				parent_cfs_rq->idle_nr_running++;
+			else
+				parent_cfs_rq->idle_nr_running--;
+		}
+
 		idle_task_delta = grp_cfs_rq->h_nr_running -
 				  grp_cfs_rq->idle_h_nr_running;
 		if (!cfs_rq_is_idle(grp_cfs_rq))