diff --git a/include/linux/sched.h b/include/linux/sched.h
index 3ed40e9f6155..c75fd46506df 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -835,6 +835,7 @@ struct task_struct {
 #endif
 
 	unsigned int			policy;
+	unsigned long			max_allowed_capacity;
 	int				nr_cpus_allowed;
 	const cpumask_t			*cpus_ptr;
 	cpumask_t			*user_cpus_ptr;
diff --git a/init/init_task.c b/init/init_task.c
index 4daee6d761c8..2558b719e053 100644
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -77,6 +77,7 @@ struct task_struct init_task __aligned(L1_CACHE_BYTES) = {
 	.cpus_ptr	= &init_task.cpus_mask,
 	.user_cpus_ptr	= NULL,
 	.cpus_mask	= CPU_MASK_ALL,
+	.max_allowed_capacity	= SCHED_CAPACITY_SCALE,
 	.nr_cpus_allowed= NR_CPUS,
 	.mm		= NULL,
 	.active_mm	= &init_mm,
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index e8270e2e15cb..c47c4f2e28f7 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5098,15 +5098,19 @@ static inline int task_fits_cpu(struct task_struct *p, int cpu)
 
 static inline void update_misfit_status(struct task_struct *p, struct rq *rq)
 {
+	int cpu = cpu_of(rq);
+
 	if (!sched_asym_cpucap_active())
 		return;
 
-	if (!p || p->nr_cpus_allowed == 1) {
-		rq->misfit_task_load = 0;
-		return;
-	}
+	/*
+	 * Affinity allows us to go somewhere higher?  Or are we on biggest
+	 * available CPU already? Or do we fit into this CPU ?
+	 */
+	if (!p || (p->nr_cpus_allowed == 1) ||
+	    (arch_scale_cpu_capacity(cpu) == p->max_allowed_capacity) ||
+	    task_fits_cpu(p, cpu)) {
 
-	if (task_fits_cpu(p, cpu_of(rq))) {
 		rq->misfit_task_load = 0;
 		return;
 	}
@@ -8253,6 +8257,36 @@ static void task_dead_fair(struct task_struct *p)
 	remove_entity_load_avg(&p->se);
 }
 
+/*
+ * Set the max capacity the task is allowed to run at for misfit detection.
+ */
+static void set_task_max_allowed_capacity(struct task_struct *p)
+{
+	struct asym_cap_data *entry;
+
+	if (!sched_asym_cpucap_active())
+		return;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(entry, &asym_cap_list, link) {
+		cpumask_t *cpumask;
+
+		cpumask = cpu_capacity_span(entry);
+		if (!cpumask_intersects(p->cpus_ptr, cpumask))
+			continue;
+
+		p->max_allowed_capacity = entry->capacity;
+		break;
+	}
+	rcu_read_unlock();
+}
+
+static void set_cpus_allowed_fair(struct task_struct *p, struct affinity_context *ctx)
+{
+	set_cpus_allowed_common(p, ctx);
+	set_task_max_allowed_capacity(p);
+}
+
 static int
 balance_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 {
@@ -8261,6 +8295,8 @@ balance_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 
 	return sched_balance_newidle(rq, rf) != 0;
 }
+#else
+static inline void set_task_max_allowed_capacity(struct task_struct *p) {}
 #endif /* CONFIG_SMP */
 
 static void set_next_buddy(struct sched_entity *se)
@@ -9610,16 +9646,10 @@ check_cpu_capacity(struct rq *rq, struct sched_domain *sd)
 				(arch_scale_cpu_capacity(cpu_of(rq)) * 100));
 }
 
-/*
- * Check whether a rq has a misfit task and if it looks like we can actually
- * help that task: we can migrate the task to a CPU of higher capacity, or
- * the task's current CPU is heavily pressured.
- */
-static inline int check_misfit_status(struct rq *rq, struct sched_domain *sd)
+/* Check if the rq has a misfit task */
+static inline bool check_misfit_status(struct rq *rq)
 {
-	return rq->misfit_task_load &&
-		(arch_scale_cpu_capacity(rq->cpu) < rq->rd->max_cpu_capacity ||
-		 check_cpu_capacity(rq, sd));
+	return rq->misfit_task_load;
 }
 
 /*
@@ -11923,7 +11953,7 @@ static void nohz_balancer_kick(struct rq *rq)
 		 * When ASYM_CPUCAPACITY; see if there's a higher capacity CPU
 		 * to run the misfit task on.
 		 */
-		if (check_misfit_status(rq, sd)) {
+		if (check_misfit_status(rq)) {
 			flags = NOHZ_STATS_KICK | NOHZ_BALANCE_KICK;
 			goto unlock;
 		}
@@ -12648,6 +12678,8 @@ static void task_fork_fair(struct task_struct *p)
 	rq_lock(rq, &rf);
 	update_rq_clock(rq);
 
+	set_task_max_allowed_capacity(p);
+
 	cfs_rq = task_cfs_rq(current);
 	curr = cfs_rq->curr;
 	if (curr)
@@ -12771,6 +12803,8 @@ static void switched_to_fair(struct rq *rq, struct task_struct *p)
 {
 	attach_task_cfs_rq(p);
 
+	set_task_max_allowed_capacity(p);
+
 	if (task_on_rq_queued(p)) {
 		/*
 		 * We were most likely switched from sched_rt, so
@@ -13142,7 +13176,7 @@ DEFINE_SCHED_CLASS(fair) = {
 	.rq_offline		= rq_offline_fair,
 
 	.task_dead		= task_dead_fair,
-	.set_cpus_allowed	= set_cpus_allowed_common,
+	.set_cpus_allowed	= set_cpus_allowed_fair,
 #endif
 
 	.task_tick		= task_tick_fair,