diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 0d97ebdc58f078f821a59c29965509a5e47f02f5..e9553640c1c3b679b6ae80b6ff4446b05b486c4b 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -784,7 +784,7 @@ account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		update_load_add(&rq_of(cfs_rq)->load, se->load.weight);
 #ifdef CONFIG_SMP
 	if (entity_is_task(se))
-		list_add_tail(&se->group_node, &rq_of(cfs_rq)->cfs_tasks);
+		list_add(&se->group_node, &rq_of(cfs_rq)->cfs_tasks);
 #endif
 	cfs_rq->nr_running++;
 }
@@ -3215,6 +3215,8 @@ static int move_one_task(struct lb_env *env)
 
 static unsigned long task_h_load(struct task_struct *p);
 
+static const unsigned int sched_nr_migrate_break = 32;
+
 /*
  * move_tasks tries to move up to load_move weighted load from busiest to
  * this_rq, as part of a balancing operation within domain "sd".
@@ -3242,7 +3244,7 @@ static int move_tasks(struct lb_env *env)
 
 		/* take a breather every nr_migrate tasks */
 		if (env->loop > env->loop_break) {
-			env->loop_break += sysctl_sched_nr_migrate;
+			env->loop_break += sched_nr_migrate_break;
 			env->flags |= LBF_NEED_BREAK;
 			break;
 		}
@@ -3252,7 +3254,7 @@ static int move_tasks(struct lb_env *env)
 
 		load = task_h_load(p);
 
-		if (load < 16 && !env->sd->nr_balance_failed)
+		if (sched_feat(LB_MIN) && load < 16 && !env->sd->nr_balance_failed)
 			goto next;
 
 		if ((load / 2) > env->load_move)
@@ -4407,7 +4409,7 @@ static int load_balance(int this_cpu, struct rq *this_rq,
 		.dst_cpu	= this_cpu,
 		.dst_rq		= this_rq,
 		.idle		= idle,
-		.loop_break	= sysctl_sched_nr_migrate,
+		.loop_break	= sched_nr_migrate_break,
 	};
 
 	cpumask_copy(cpus, cpu_active_mask);
@@ -4445,10 +4447,10 @@ static int load_balance(int this_cpu, struct rq *this_rq,
 		 * correctly treated as an imbalance.
 		 */
 		env.flags |= LBF_ALL_PINNED;
-		env.load_move = imbalance;
-		env.src_cpu = busiest->cpu;
-		env.src_rq = busiest;
-		env.loop_max = busiest->nr_running;
+		env.load_move	= imbalance;
+		env.src_cpu	= busiest->cpu;
+		env.src_rq	= busiest;
+		env.loop_max	= min_t(unsigned long, sysctl_sched_nr_migrate, busiest->nr_running);
 
 more_balance:
 		local_irq_save(flags);
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index e61fd73913d0613d7fc66a3f8e7dec5c6a55b58b..de00a486c5c693ac7038fa3c5dd139e642a1c307 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -68,3 +68,4 @@ SCHED_FEAT(TTWU_QUEUE, true)
 
 SCHED_FEAT(FORCE_SD_OVERLAP, false)
 SCHED_FEAT(RT_RUNTIME_SHARE, true)
+SCHED_FEAT(LB_MIN, false)