diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 4e0ebae045dc..102c36c317dc 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2177,27 +2177,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 	INIT_HLIST_HEAD(&p->preempt_notifiers);
 #endif
 
-#ifdef CONFIG_NUMA_BALANCING
-	if (p->mm && atomic_read(&p->mm->mm_users) == 1) {
-		p->mm->numa_next_scan = jiffies + msecs_to_jiffies(sysctl_numa_balancing_scan_delay);
-		p->mm->numa_scan_seq = 0;
-	}
-
-	if (clone_flags & CLONE_VM)
-		p->numa_preferred_nid = current->numa_preferred_nid;
-	else
-		p->numa_preferred_nid = -1;
-
-	p->node_stamp = 0ULL;
-	p->numa_scan_seq = p->mm ? p->mm->numa_scan_seq : 0;
-	p->numa_scan_period = sysctl_numa_balancing_scan_delay;
-	p->numa_work.next = &p->numa_work;
-	p->numa_faults = NULL;
-	p->last_task_numa_placement = 0;
-	p->last_sum_exec_runtime = 0;
-
-	p->numa_group = NULL;
-#endif /* CONFIG_NUMA_BALANCING */
+	init_numa_balancing(clone_flags, p);
 }
 
 DEFINE_STATIC_KEY_FALSE(sched_numa_balancing);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 43c7b45f20be..f32b97d4c63b 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1139,6 +1139,47 @@ static unsigned int task_scan_max(struct task_struct *p)
 	return max(smin, smax);
 }
 
+void init_numa_balancing(unsigned long clone_flags, struct task_struct *p)
+{
+	int mm_users = 0;
+	struct mm_struct *mm = p->mm;
+
+	if (mm) {
+		mm_users = atomic_read(&mm->mm_users);
+		if (mm_users == 1) {
+			mm->numa_next_scan = jiffies + msecs_to_jiffies(sysctl_numa_balancing_scan_delay);
+			mm->numa_scan_seq = 0;
+		}
+	}
+	p->node_stamp			= 0;
+	p->numa_scan_seq		= mm ? mm->numa_scan_seq : 0;
+	p->numa_scan_period		= sysctl_numa_balancing_scan_delay;
+	p->numa_work.next		= &p->numa_work;
+	p->numa_faults			= NULL;
+	p->numa_group			= NULL;
+	p->last_task_numa_placement	= 0;
+	p->last_sum_exec_runtime	= 0;
+
+	/* New address space, reset the preferred nid */
+	if (!(clone_flags & CLONE_VM)) {
+		p->numa_preferred_nid = -1;
+		return;
+	}
+
+	/*
+	 * New thread, keep existing numa_preferred_nid which should be copied
+	 * already by arch_dup_task_struct but stagger when scans start.
+	 */
+	if (mm) {
+		unsigned int delay;
+
+		delay = min_t(unsigned int, task_scan_max(current),
+			current->numa_scan_period * mm_users * NSEC_PER_MSEC);
+		delay += 2 * TICK_NSEC;
+		p->node_stamp = delay;
+	}
+}
+
 static void account_numa_enqueue(struct rq *rq, struct task_struct *p)
 {
 	rq->nr_numa_running += (p->numa_preferred_nid != -1);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 15750c222ca2..c9895d35c5f7 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1069,6 +1069,12 @@ enum numa_faults_stats {
 extern void sched_setnuma(struct task_struct *p, int node);
 extern int migrate_task_to(struct task_struct *p, int cpu);
 extern int migrate_swap(struct task_struct *, struct task_struct *);
+extern void init_numa_balancing(unsigned long clone_flags, struct task_struct *p);
+#else
+static inline void
+init_numa_balancing(unsigned long clone_flags, struct task_struct *p)
+{
+}
 #endif /* CONFIG_NUMA_BALANCING */
 
 #ifdef CONFIG_SMP