diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c
index bd95963dae80b92c34536d244de0986257e6490f..539ca3ce071b2858f437cd0d0265d473093be9e2 100644
--- a/kernel/sched/cpudeadline.c
+++ b/kernel/sched/cpudeadline.c
@@ -107,9 +107,7 @@ int cpudl_find(struct cpudl *cp, struct task_struct *p,
 	int best_cpu = -1;
 	const struct sched_dl_entity *dl_se = &p->dl;
 
-	if (later_mask && cpumask_and(later_mask, cp->free_cpus,
-			&p->cpus_allowed) && cpumask_and(later_mask,
-			later_mask, cpu_active_mask)) {
+	if (later_mask && cpumask_and(later_mask, later_mask, cp->free_cpus)) {
 		best_cpu = cpumask_any(later_mask);
 		goto out;
 	} else if (cpumask_test_cpu(cpudl_maximum(cp), &p->cpus_allowed) &&
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index efb94124420d433d7021f4e4ebfdff4d0bc12fa4..abfaf3d9a29f0f3daebaff2937c7ec0d0303daaf 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1164,6 +1164,13 @@ static int find_later_rq(struct task_struct *task)
 	if (task->nr_cpus_allowed == 1)
 		return -1;
 
+	/*
+	 * We have to consider system topology and task affinity
+	 * first, then we can look for a suitable cpu.
+	 */
+	cpumask_copy(later_mask, task_rq(task)->rd->span);
+	cpumask_and(later_mask, later_mask, cpu_active_mask);
+	cpumask_and(later_mask, later_mask, &task->cpus_allowed);
 	best_cpu = cpudl_find(&task_rq(task)->rd->cpudl,
 			task, later_mask);
 	if (best_cpu == -1)