diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h
index 8a0fae94d45e..a2edacb56459 100644
--- a/arch/arm/include/asm/topology.h
+++ b/arch/arm/include/asm/topology.h
@@ -10,6 +10,9 @@
 /* Replace task scheduler's default frequency-invariant accounting */
 #define arch_scale_freq_capacity topology_get_freq_scale
 
+/* Replace task scheduler's default max-frequency-invariant accounting */
+#define arch_scale_max_freq_capacity topology_get_max_freq_scale
+
 /* Replace task scheduler's default cpu-invariant accounting */
 #define arch_scale_cpu_capacity topology_get_cpu_scale
 
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 8e05c39eab08..2c029af5d7e0 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -13,10 +13,12 @@ CONFIG_TASK_XACCT=y
 CONFIG_TASK_IO_ACCOUNTING=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
+CONFIG_UCLAMP_TASK=y
 CONFIG_NUMA_BALANCING=y
 CONFIG_MEMCG=y
 CONFIG_MEMCG_SWAP=y
 CONFIG_BLK_CGROUP=y
+CONFIG_UCLAMP_TASK_GROUP=y
 CONFIG_CGROUP_PIDS=y
 CONFIG_CGROUP_HUGETLB=y
 CONFIG_CPUSETS=y
@@ -71,10 +73,12 @@ CONFIG_COMPAT=y
 CONFIG_RANDOMIZE_BASE=y
 CONFIG_HIBERNATION=y
 CONFIG_WQ_POWER_EFFICIENT_DEFAULT=y
+CONFIG_ENERGY_MODEL=y
 CONFIG_ARM_CPUIDLE=y
 CONFIG_ARM_PSCI_CPUIDLE=y
 CONFIG_CPU_FREQ=y
 CONFIG_CPU_FREQ_STAT=y
+CONFIG_CPU_FREQ_DEFAULT_GOV_SCHEDUTIL=y
 CONFIG_CPU_FREQ_GOV_POWERSAVE=m
 CONFIG_CPU_FREQ_GOV_USERSPACE=y
 CONFIG_CPU_FREQ_GOV_ONDEMAND=y
diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h
index a4d945db95a2..70697177d6ec 100644
--- a/arch/arm64/include/asm/topology.h
+++ b/arch/arm64/include/asm/topology.h
@@ -19,6 +19,9 @@ int pcibus_to_node(struct pci_bus *bus);
 /* Replace task scheduler's default frequency-invariant accounting */
 #define arch_scale_freq_capacity topology_get_freq_scale
 
+/* Replace task scheduler's default max-frequency-invariant accounting */
+#define arch_scale_max_freq_capacity topology_get_max_freq_scale
+
 /* Replace task scheduler's default cpu-invariant accounting */
 #define arch_scale_cpu_capacity topology_get_cpu_scale
 
diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c
index 1eb81f113786..c0cf9ef5c2f5 100644
--- a/drivers/base/arch_topology.c
+++ b/drivers/base/arch_topology.c
@@ -22,6 +22,8 @@
 #include <linux/smp.h>
 
 DEFINE_PER_CPU(unsigned long, freq_scale) = SCHED_CAPACITY_SCALE;
+DEFINE_PER_CPU(unsigned long, max_cpu_freq);
+DEFINE_PER_CPU(unsigned long, max_freq_scale) = SCHED_CAPACITY_SCALE;
 
 void arch_set_freq_scale(struct cpumask *cpus, unsigned long cur_freq,
 			 unsigned long max_freq)
@@ -31,8 +33,29 @@ void arch_set_freq_scale(struct cpumask *cpus, unsigned long cur_freq,
 
 	scale = (cur_freq << SCHED_CAPACITY_SHIFT) / max_freq;
 
-	for_each_cpu(i, cpus)
+	for_each_cpu(i, cpus) {
 		per_cpu(freq_scale, i) = scale;
+		per_cpu(max_cpu_freq, i) = max_freq;
+	}
+}
+
+void arch_set_max_freq_scale(struct cpumask *cpus,
+			     unsigned long policy_max_freq)
+{
+	unsigned long scale, max_freq;
+	int cpu = cpumask_first(cpus);
+
+	if (cpu > nr_cpu_ids)
+		return;
+
+	max_freq = per_cpu(max_cpu_freq, cpu);
+	if (!max_freq)
+		return;
+
+	scale = (policy_max_freq << SCHED_CAPACITY_SHIFT) / max_freq;
+
+	for_each_cpu(cpu, cpus)
+		per_cpu(max_freq_scale, cpu) = scale;
 }
 
 DEFINE_PER_CPU(unsigned long, cpu_scale) = SCHED_CAPACITY_SCALE;
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index f9de9dece70f..9c15d7f52e1c 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -153,6 +153,12 @@ __weak void arch_set_freq_scale(struct cpumask *cpus, unsigned long cur_freq,
 }
 EXPORT_SYMBOL_GPL(arch_set_freq_scale);
 
+__weak void arch_set_max_freq_scale(struct cpumask *cpus,
+				    unsigned long policy_max_freq)
+{
+}
+EXPORT_SYMBOL_GPL(arch_set_max_freq_scale);
+
 /*
  * This is a generic cpufreq init() routine which can be used by cpufreq
  * drivers of SMP systems. It will do following:
@@ -2407,6 +2413,8 @@ int cpufreq_set_policy(struct cpufreq_policy *policy,
 	policy->max = new_policy->max;
 	trace_cpu_frequency_limits(policy);
 
+	arch_set_max_freq_scale(policy->cpus, policy->max);
+
 	policy->cached_target_freq = UINT_MAX;
 
 	pr_debug("new min and max freqs are %u - %u kHz\n",
diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h
index 42f2b5126094..5402bc0e2b1e 100644
--- a/include/linux/arch_topology.h
+++ b/include/linux/arch_topology.h
@@ -33,6 +33,14 @@ unsigned long topology_get_freq_scale(int cpu)
 	return per_cpu(freq_scale, cpu);
 }
 
+DECLARE_PER_CPU(unsigned long, max_freq_scale);
+
+static inline
+unsigned long topology_get_max_freq_scale(struct sched_domain *sd, int cpu)
+{
+	return per_cpu(max_freq_scale, cpu);
+}
+
 struct cpu_topology {
 	int thread_id;
 	int core_id;
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index c57e88e85c41..fca45a2749d4 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -984,6 +984,8 @@ extern unsigned int arch_freq_get_on_cpu(int cpu);
 
 extern void arch_set_freq_scale(struct cpumask *cpus, unsigned long cur_freq,
 				unsigned long max_freq);
+extern void arch_set_max_freq_scale(struct cpumask *cpus,
+				    unsigned long policy_max_freq);
 
 /* the following are really really optional */
 extern struct freq_attr cpufreq_freq_attr_scaling_available_freqs;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 7880f4f64d0e..7571fc49af89 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7356,6 +7356,27 @@ static int cpu_uclamp_max_show(struct seq_file *sf, void *v)
 	cpu_uclamp_print(sf, UCLAMP_MAX);
 	return 0;
 }
+
+static int cpu_uclamp_ls_write_u64(struct cgroup_subsys_state *css,
+				   struct cftype *cftype, u64 ls)
+{
+	struct task_group *tg;
+
+	if (ls > 1)
+		return -EINVAL;
+	tg = css_tg(css);
+	tg->latency_sensitive = (unsigned int) ls;
+
+	return 0;
+}
+
+static u64 cpu_uclamp_ls_read_u64(struct cgroup_subsys_state *css,
+				  struct cftype *cft)
+{
+	struct task_group *tg = css_tg(css);
+
+	return (u64) tg->latency_sensitive;
+}
 #endif /* CONFIG_UCLAMP_TASK_GROUP */
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -7716,6 +7737,12 @@ static struct cftype cpu_legacy_files[] = {
 		.seq_show = cpu_uclamp_max_show,
 		.write = cpu_uclamp_max_write,
 	},
+	{
+		.name = "uclamp.latency_sensitive",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.read_u64 = cpu_uclamp_ls_read_u64,
+		.write_u64 = cpu_uclamp_ls_write_u64,
+	},
 #endif
 	{ }	/* Terminate */
 };
@@ -7897,6 +7924,12 @@ static struct cftype cpu_files[] = {
 		.seq_show = cpu_uclamp_max_show,
 		.write = cpu_uclamp_max_write,
 	},
+	{
+		.name = "uclamp.latency_sensitive",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.read_u64 = cpu_uclamp_ls_read_u64,
+		.write_u64 = cpu_uclamp_ls_write_u64,
+	},
 #endif
 	{ }	/* terminate */
 };
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 83ab35e2374f..9b43520dc248 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6026,6 +6026,19 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 	return target;
 }
 
+static unsigned int uclamp_task_util(struct task_struct *p)
+{
+#ifdef CONFIG_UCLAMP_TASK
+	unsigned int min_util = uclamp_eff_value(p, UCLAMP_MIN);
+	unsigned int max_util = uclamp_eff_value(p, UCLAMP_MAX);
+	unsigned int est_util = task_util_est(p);
+
+	return clamp(est_util, min_util, max_util);
+#else
+	return task_util_est(p);
+#endif
+}
+
 /**
  * Amount of capacity of a CPU that is (estimated to be) used by CFS tasks
  * @cpu: the CPU to get the utilization of
@@ -6182,7 +6195,7 @@ static int wake_cap(struct task_struct *p, int cpu, int prev_cpu)
 		return 0;
 
 	min_cap = min(capacity_orig_of(prev_cpu), capacity_orig_of(cpu));
-	max_cap = cpu_rq(cpu)->rd->max_cpu_capacity;
+	max_cap = cpu_rq(cpu)->rd->max_cpu_capacity.val;
 
 	/* Minimum capacity is close to max, no need to abort wake_affine */
 	if (max_cap - min_cap < max_cap >> 3)
@@ -6323,12 +6336,17 @@ compute_energy(struct task_struct *p, int dst_cpu, struct perf_domain *pd)
  * other use-cases too. So, until someone finds a better way to solve this,
  * let's keep things simple by re-using the existing slow path.
  */
-static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
+static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu, int sync)
 {
 	unsigned long prev_delta = ULONG_MAX, best_delta = ULONG_MAX;
 	struct root_domain *rd = cpu_rq(smp_processor_id())->rd;
+	int max_spare_cap_cpu_ls = prev_cpu, best_idle_cpu = -1;
+	unsigned long max_spare_cap_ls = 0, target_cap;
 	unsigned long cpu_cap, util, base_energy = 0;
+	bool boosted, latency_sensitive = false;
+	unsigned int min_exit_lat = UINT_MAX;
 	int cpu, best_energy_cpu = prev_cpu;
+	struct cpuidle_state *idle;
 	struct sched_domain *sd;
 	struct perf_domain *pd;
 
@@ -6337,6 +6355,12 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
 	if (!pd || READ_ONCE(rd->overutilized))
 		goto fail;
 
+	cpu = smp_processor_id();
+	if (sync && cpumask_test_cpu(cpu, p->cpus_ptr)) {
+		rcu_read_unlock();
+		return cpu;
+	}
+
 	/*
 	 * Energy-aware wake-up happens on the lowest sched_domain starting
 	 * from sd_asym_cpucapacity spanning over this_cpu and prev_cpu.
@@ -6351,6 +6375,10 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
 	if (!task_util_est(p))
 		goto unlock;
 
+	latency_sensitive = uclamp_latency_sensitive(p);
+	boosted = uclamp_boosted(p);
+	target_cap = boosted ? 0 : ULONG_MAX;
+
 	for (; pd; pd = pd->next) {
 		unsigned long cur_delta, spare_cap, max_spare_cap = 0;
 		unsigned long base_energy_pd;
@@ -6370,8 +6398,12 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
 			if (!fits_capacity(util, cpu_cap))
 				continue;
 
+			/* Skip CPUs which do not fit task requirements */
+			if (cpu_cap < uclamp_task_util(p))
+				continue;
+
 			/* Always use prev_cpu as a candidate. */
-			if (cpu == prev_cpu) {
+			if (!latency_sensitive && cpu == prev_cpu) {
 				prev_delta = compute_energy(p, prev_cpu, pd);
 				prev_delta -= base_energy_pd;
 				best_delta = min(best_delta, prev_delta);
@@ -6386,10 +6418,34 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
 				max_spare_cap = spare_cap;
 				max_spare_cap_cpu = cpu;
 			}
+
+			if (!latency_sensitive)
+				continue;
+
+			if (idle_cpu(cpu)) {
+				cpu_cap = capacity_orig_of(cpu);
+				if (boosted && cpu_cap < target_cap)
+					continue;
+				if (!boosted && cpu_cap > target_cap)
+					continue;
+				idle = idle_get_state(cpu_rq(cpu));
+				if (idle && idle->exit_latency > min_exit_lat &&
+						cpu_cap == target_cap)
+					continue;
+
+				if (idle)
+					min_exit_lat = idle->exit_latency;
+				target_cap = cpu_cap;
+				best_idle_cpu = cpu;
+			} else if (spare_cap > max_spare_cap_ls) {
+				max_spare_cap_ls = spare_cap;
+				max_spare_cap_cpu_ls = cpu;
+			}
 		}
 
 		/* Evaluate the energy impact of using this CPU. */
-		if (max_spare_cap_cpu >= 0 && max_spare_cap_cpu != prev_cpu) {
+		if (!latency_sensitive && max_spare_cap_cpu >= 0 &&
+						max_spare_cap_cpu != prev_cpu) {
 			cur_delta = compute_energy(p, max_spare_cap_cpu, pd);
 			cur_delta -= base_energy_pd;
 			if (cur_delta < best_delta) {
@@ -6401,6 +6457,9 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
 unlock:
 	rcu_read_unlock();
 
+	if (latency_sensitive)
+		return best_idle_cpu >= 0 ? best_idle_cpu : max_spare_cap_cpu_ls;
+
 	/*
 	 * Pick the best CPU if prev_cpu cannot be used, or if it saves at
 	 * least 6% of the energy used by prev_cpu.
@@ -6444,7 +6503,7 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
 		record_wakee(p);
 
 		if (sched_energy_enabled()) {
-			new_cpu = find_energy_efficient_cpu(p, prev_cpu);
+			new_cpu = find_energy_efficient_cpu(p, prev_cpu, sync);
 			if (new_cpu >= 0)
 				return new_cpu;
 			new_cpu = prev_cpu;
@@ -7089,6 +7148,7 @@ struct lb_env {
 	int			new_dst_cpu;
 	enum cpu_idle_type	idle;
 	long			imbalance;
+	unsigned int		src_grp_nr_running;
 	/* The set of CPUs under consideration for load-balancing */
 	struct cpumask		*cpus;
 
@@ -7702,10 +7762,9 @@ static inline void init_sd_lb_stats(struct sd_lb_stats *sds)
 	};
 }
 
-static unsigned long scale_rt_capacity(struct sched_domain *sd, int cpu)
+static unsigned long scale_rt_capacity(int cpu, unsigned long max)
 {
 	struct rq *rq = cpu_rq(cpu);
-	unsigned long max = arch_scale_cpu_capacity(cpu);
 	unsigned long used, free;
 	unsigned long irq;
 
@@ -7725,12 +7784,47 @@ static unsigned long scale_rt_capacity(struct sched_domain *sd, int cpu)
 	return scale_irq_capacity(free, irq, max);
 }
 
+void init_max_cpu_capacity(struct max_cpu_capacity *mcc) {
+	raw_spin_lock_init(&mcc->lock);
+	mcc->val = 0;
+	mcc->cpu = -1;
+}
+
 static void update_cpu_capacity(struct sched_domain *sd, int cpu)
 {
-	unsigned long capacity = scale_rt_capacity(sd, cpu);
+	unsigned long capacity = arch_scale_cpu_capacity(cpu);
 	struct sched_group *sdg = sd->groups;
+	struct max_cpu_capacity *mcc;
+	unsigned long max_capacity;
+	int max_cap_cpu;
+	unsigned long flags;
 
-	cpu_rq(cpu)->cpu_capacity_orig = arch_scale_cpu_capacity(cpu);
+	cpu_rq(cpu)->cpu_capacity_orig = capacity;
+
+	capacity *= arch_scale_max_freq_capacity(sd, cpu);
+	capacity >>= SCHED_CAPACITY_SHIFT;
+
+	mcc = &cpu_rq(cpu)->rd->max_cpu_capacity;
+
+	raw_spin_lock_irqsave(&mcc->lock, flags);
+	max_capacity = mcc->val;
+	max_cap_cpu = mcc->cpu;
+
+	if ((max_capacity > capacity && max_cap_cpu == cpu) ||
+	    (max_capacity < capacity)) {
+		mcc->val = capacity;
+		mcc->cpu = cpu;
+#ifdef CONFIG_SCHED_DEBUG
+		raw_spin_unlock_irqrestore(&mcc->lock, flags);
+		printk_deferred(KERN_INFO "CPU%d: update max cpu_capacity %lu\n",
+				cpu, capacity);
+		goto skip_unlock;
+#endif
+	}
+	raw_spin_unlock_irqrestore(&mcc->lock, flags);
+
+skip_unlock: __attribute__ ((unused));
+	capacity = scale_rt_capacity(cpu, capacity);
 
 	if (!capacity)
 		capacity = 1;
@@ -7834,7 +7928,7 @@ check_cpu_capacity(struct rq *rq, struct sched_domain *sd)
 static inline int check_misfit_status(struct rq *rq, struct sched_domain *sd)
 {
 	return rq->misfit_task_load &&
-		(rq->cpu_capacity_orig < rq->rd->max_cpu_capacity ||
+		(rq->cpu_capacity_orig < rq->rd->max_cpu_capacity.val ||
 		 check_cpu_capacity(rq, sd));
 }
 
@@ -8237,6 +8331,8 @@ next_group:
 	if (env->sd->flags & SD_NUMA)
 		env->fbq_type = fbq_classify_group(&sds->busiest_stat);
 
+	env->src_grp_nr_running = sds->busiest_stat.sum_nr_running;
+
 	if (!env->sd->parent) {
 		struct root_domain *rd = env->dst_rq->rd;
 
@@ -8365,7 +8461,22 @@ void fix_small_imbalance(struct lb_env *env, struct sd_lb_stats *sds)
 	capa_move /= SCHED_CAPACITY_SCALE;
 
 	/* Move if we gain throughput */
-	if (capa_move > capa_now)
+	if (capa_move > capa_now) {
+		env->imbalance = busiest->load_per_task;
+		return;
+	}
+
+	/* We can't see throughput improvement with the load-based
+	 * method, but it is possible depending upon group size and
+	 * capacity range that there might still be an underutilized
+	 * cpu available in an asymmetric capacity system. Do one last
+	 * check just in case.
+	 */
+	if (env->sd->flags & SD_ASYM_CPUCAPACITY &&
+		busiest->group_type == group_overloaded &&
+		busiest->sum_nr_running > busiest->group_weight &&
+		local->sum_nr_running < local->group_weight &&
+		local->group_capacity < busiest->group_capacity)
 		env->imbalance = busiest->load_per_task;
 }
 
@@ -8434,8 +8545,18 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
 		(sds->avg_load - local->avg_load) * local->group_capacity
 	) / SCHED_CAPACITY_SCALE;
 
-	/* Boost imbalance to allow misfit task to be balanced. */
-	if (busiest->group_type == group_misfit_task) {
+	/* Boost imbalance to allow misfit task to be balanced.
+	 * Always do this if we are doing a NEWLY_IDLE balance
+	 * on the assumption that any tasks we have must not be
+	 * long-running (and hence we cannot rely upon load).
+	 * However if we are not idle, we should assume the tasks
+	 * we have are longer running and not override load-based
+	 * calculations above unless we are sure that the local
+	 * group is underutilized.
+	 */
+	if (busiest->group_type == group_misfit_task &&
+		(env->idle == CPU_NEWLY_IDLE ||
+		local->sum_nr_running < local->group_weight)) {
 		env->imbalance = max_t(long, env->imbalance,
 				       busiest->group_misfit_task_load);
 	}
@@ -8713,6 +8834,9 @@ static int need_active_balance(struct lb_env *env)
 	if (voluntary_active_balance(env))
 		return 1;
 
+	if (env->src_grp_type == group_overloaded && env->src_rq->misfit_task_load)
+		return 1;
+
 	return unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2);
 }
 
@@ -8931,7 +9055,8 @@ more_balance:
 		 * excessive cache_hot migrations and active balances.
 		 */
 		if (idle != CPU_NEWLY_IDLE)
-			sd->nr_balance_failed++;
+			if (env.src_grp_nr_running > 1)
+				sd->nr_balance_failed++;
 
 		if (need_active_balance(&env)) {
 			unsigned long flags;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 0db2c1b3361e..4f0d1668c283 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -399,6 +399,8 @@ struct task_group {
 	struct uclamp_se	uclamp_req[UCLAMP_CNT];
 	/* Effective clamp values used for a task group */
 	struct uclamp_se	uclamp[UCLAMP_CNT];
+	/* Latency-sensitive flag used for a task group */
+	unsigned int		latency_sensitive;
 #endif
 
 };
@@ -717,6 +719,12 @@ struct perf_domain {
 	struct rcu_head rcu;
 };
 
+struct max_cpu_capacity {
+	raw_spinlock_t lock;
+	unsigned long val;
+	int cpu;
+};
+
 /* Scheduling group status flags */
 #define SG_OVERLOAD		0x1 /* More than one runnable task on a CPU. */
 #define SG_OVERUTILIZED		0x2 /* One or more CPUs are over-utilized. */
@@ -775,7 +783,8 @@ struct root_domain {
 	cpumask_var_t		rto_mask;
 	struct cpupri		cpupri;
 
-	unsigned long		max_cpu_capacity;
+	/* Maximum cpu capacity in the system. */
+	struct max_cpu_capacity max_cpu_capacity;
 
 	/*
 	 * NULL-terminated list of performance domains intersecting with the
@@ -785,6 +794,7 @@ struct root_domain {
 };
 
 extern void init_defrootdomain(void);
+extern void init_max_cpu_capacity(struct max_cpu_capacity *mcc);
 extern int sched_init_domains(const struct cpumask *cpu_map);
 extern void rq_attach_root(struct rq *rq, struct root_domain *rd);
 extern void sched_get_rd(struct root_domain *rd);
@@ -1961,6 +1971,15 @@ unsigned long arch_scale_freq_capacity(int cpu)
 }
 #endif
 
+#ifndef arch_scale_max_freq_capacity
+struct sched_domain;
+static __always_inline
+unsigned long arch_scale_max_freq_capacity(struct sched_domain *sd, int cpu)
+{
+	return SCHED_CAPACITY_SCALE;
+}
+#endif
+
 #ifdef CONFIG_SMP
 #ifdef CONFIG_PREEMPTION
 
@@ -2314,6 +2333,11 @@ static inline unsigned int uclamp_util(struct rq *rq, unsigned int util)
 {
 	return uclamp_util_with(rq, util, NULL);
 }
+
+static inline bool uclamp_boosted(struct task_struct *p)
+{
+	return uclamp_eff_value(p, UCLAMP_MIN) > 0;
+}
 #else /* CONFIG_UCLAMP_TASK */
 static inline unsigned int uclamp_util_with(struct rq *rq, unsigned int util,
 					    struct task_struct *p)
@@ -2324,8 +2348,31 @@ static inline unsigned int uclamp_util(struct rq *rq, unsigned int util)
 {
 	return util;
 }
+static inline bool uclamp_boosted(struct task_struct *p)
+{
+	return false;
+}
 #endif /* CONFIG_UCLAMP_TASK */
 
+#ifdef CONFIG_UCLAMP_TASK_GROUP
+static inline bool uclamp_latency_sensitive(struct task_struct *p)
+{
+	struct cgroup_subsys_state *css = task_css(p, cpu_cgrp_id);
+	struct task_group *tg;
+
+	if (!css)
+		return false;
+	tg = container_of(css, struct task_group, css);
+
+	return tg->latency_sensitive;
+}
+#else
+static inline bool uclamp_latency_sensitive(struct task_struct *p)
+{
+	return false;
+}
+#endif /* CONFIG_UCLAMP_TASK_GROUP */
+
 #ifdef arch_scale_freq_capacity
 # ifndef arch_scale_freq_invariant
 #  define arch_scale_freq_invariant()	true
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index b5667a273bf6..4ad1e5194555 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -510,6 +510,9 @@ static int init_rootdomain(struct root_domain *rd)
 
 	if (cpupri_init(&rd->cpupri) != 0)
 		goto free_cpudl;
+
+	init_max_cpu_capacity(&rd->max_cpu_capacity);
+
 	return 0;
 
 free_cpudl:
@@ -1951,7 +1954,6 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
 	enum s_alloc alloc_state;
 	struct sched_domain *sd;
 	struct s_data d;
-	struct rq *rq = NULL;
 	int i, ret = -ENOMEM;
 	struct sched_domain_topology_level *tl_asym;
 	bool has_asym = false;
@@ -2014,13 +2016,7 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
 	/* Attach the domains */
 	rcu_read_lock();
 	for_each_cpu(i, cpu_map) {
-		rq = cpu_rq(i);
 		sd = *per_cpu_ptr(d.sd, i);
-
-		/* Use READ_ONCE()/WRITE_ONCE() to avoid load/store tearing: */
-		if (rq->cpu_capacity_orig > READ_ONCE(d.rd->max_cpu_capacity))
-			WRITE_ONCE(d.rd->max_cpu_capacity, rq->cpu_capacity_orig);
-
 		cpu_attach_domain(sd, d.rd, i);
 	}
 	rcu_read_unlock();
@@ -2028,11 +2024,6 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
 	if (has_asym)
 		static_branch_enable_cpuslocked(&sched_asym_cpucapacity);
 
-	if (rq && sched_debug_enabled) {
-		pr_info("root domain span: %*pbl (max cpu_capacity = %lu)\n",
-			cpumask_pr_args(cpu_map), rq->rd->max_cpu_capacity);
-	}
-
 	ret = 0;
 error:
 	__free_domain_allocs(&d, alloc_state, cpu_map);