diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index d98175d..51a7600 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -901,28 +901,114 @@
 }
 
 static unsigned long weighted_cpuload(const int cpu);
+static unsigned long source_load(int cpu, int type);
+static unsigned long target_load(int cpu, int type);
+static unsigned long power_of(int cpu);
+static long effective_load(struct task_group *tg, int cpu, long wl, long wg);
 
+struct numa_stats {
+	unsigned long load;
+	s64 eff_load;
+	unsigned long faults;
+};
 
-static int
-find_idlest_cpu_node(int this_cpu, int nid)
+struct task_numa_env {
+	struct task_struct *p;
+
+	int src_cpu, src_nid;
+	int dst_cpu, dst_nid;
+
+	struct numa_stats src_stats, dst_stats;
+
+	unsigned long best_load;
+	int best_cpu;
+};
+
+static int task_numa_migrate(struct task_struct *p)
 {
-	unsigned long load, min_load = ULONG_MAX;
-	int i, idlest_cpu = this_cpu;
+	int node_cpu = cpumask_first(cpumask_of_node(p->numa_preferred_nid));
+	struct task_numa_env env = {
+		.p = p,
+		.src_cpu = task_cpu(p),
+		.src_nid = cpu_to_node(task_cpu(p)),
+		.dst_cpu = node_cpu,
+		.dst_nid = p->numa_preferred_nid,
+		.best_load = ULONG_MAX,
+		.best_cpu = task_cpu(p),
+	};
+	struct sched_domain *sd;
+	int cpu;
+	struct task_group *tg = task_group(p);
+	unsigned long weight;
+	bool balanced;
+	int imbalance_pct, idx = -1;
 
-	BUG_ON(cpu_to_node(this_cpu) == nid);
-
+	/*
+	 * Find the lowest common scheduling domain covering the nodes of both
+	 * the CPU the task is currently running on and the target NUMA node.
+	 */
 	rcu_read_lock();
-	for_each_cpu(i, cpumask_of_node(nid)) {
-		load = weighted_cpuload(i);
-
-		if (load < min_load) {
-			min_load = load;
-			idlest_cpu = i;
+	for_each_domain(env.src_cpu, sd) {
+		if (cpumask_test_cpu(node_cpu, sched_domain_span(sd))) {
+			/*
+			 * busy_idx is used for the load decision as it is the
+			 * same index used by the regular load balancer for an
+			 * active cpu.
+			 */
+			idx = sd->busy_idx;
+			imbalance_pct = sd->imbalance_pct;
+			break;
 		}
 	}
 	rcu_read_unlock();
 
-	return idlest_cpu;
+	if (WARN_ON_ONCE(idx == -1))
+		return 0;
+
+	/*
+	 * XXX the below is mostly nicked from wake_affine(); we should
+	 * see about sharing a bit if at all possible; also it might want
+	 * some per entity weight love.
+	 */
+	weight = p->se.load.weight;
+	env.src_stats.load = source_load(env.src_cpu, idx);
+	env.src_stats.eff_load = 100 + (imbalance_pct - 100) / 2;
+	env.src_stats.eff_load *= power_of(env.src_cpu);
+	env.src_stats.eff_load *= env.src_stats.load + effective_load(tg, env.src_cpu, -weight, -weight);
+
+	for_each_cpu(cpu, cpumask_of_node(env.dst_nid)) {
+		env.dst_cpu = cpu;
+		env.dst_stats.load = target_load(cpu, idx);
+
+		/* If the CPU is idle, use it */
+		if (!env.dst_stats.load) {
+			env.best_cpu = cpu;
+			goto migrate;
+		}
+
+		/* Otherwise check the target CPU load */
+		env.dst_stats.eff_load = 100;
+		env.dst_stats.eff_load *= power_of(cpu);
+		env.dst_stats.eff_load *= env.dst_stats.load + effective_load(tg, cpu, weight, weight);
+
+		/*
+		 * Destination is considered balanced if the destination CPU is
+		 * less loaded than the source CPU. Unfortunately there is a
+		 * risk that a task running on a lightly loaded CPU will not
+		 * migrate to its preferred node due to load imbalances.
+		 */
+		balanced = (env.dst_stats.eff_load <= env.src_stats.eff_load);
+		if (!balanced)
+			continue;
+
+		if (env.dst_stats.eff_load < env.best_load) {
+			env.best_load = env.dst_stats.eff_load;
+			env.best_cpu = cpu;
+		}
+	}
+
+migrate:
+	return migrate_task_to(p, env.best_cpu);
 }
 
 static void task_numa_placement(struct task_struct *p)
@@ -966,22 +1052,10 @@
 	 * the working set placement.
 	 */
 	if (max_faults && max_nid != p->numa_preferred_nid) {
-		int preferred_cpu;
-
-		/*
-		 * If the task is not on the preferred node then find the most
-		 * idle CPU to migrate to.
-		 */
-		preferred_cpu = task_cpu(p);
-		if (cpu_to_node(preferred_cpu) != max_nid) {
-			preferred_cpu = find_idlest_cpu_node(preferred_cpu,
-							     max_nid);
-		}
-
 		/* Update the preferred nid and migrate task if possible */
 		p->numa_preferred_nid = max_nid;
 		p->numa_migrate_seq = 1;
-		migrate_task_to(p, preferred_cpu);
+		task_numa_migrate(p);
 	}
 }
 
@@ -3292,7 +3366,7 @@
 {
 	struct sched_entity *se = tg->se[cpu];
 
-	if (!tg->parent)	/* the trivial, non-cgroup case */
+	if (!tg->parent || !wl)	/* the trivial, non-cgroup case */
 		return wl;
 
 	for_each_sched_entity(se) {
@@ -3345,8 +3419,7 @@
 }
 #else
 
-static inline unsigned long effective_load(struct task_group *tg, int cpu,
-		unsigned long wl, unsigned long wg)
+static long effective_load(struct task_group *tg, int cpu, long wl, long wg)
 {
 	return wl;
 }