diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 85ab7d72b54c..2748ff639144 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -626,8 +626,11 @@ struct sk_buff {
 	__u32			hash;
 	__be16			vlan_proto;
 	__u16			vlan_tci;
-#ifdef CONFIG_NET_RX_BUSY_POLL
-	unsigned int	napi_id;
+#if defined(CONFIG_NET_RX_BUSY_POLL) || defined(CONFIG_XPS)
+	union {
+		unsigned int	napi_id;
+		unsigned int	sender_cpu;
+	};
 #endif
 #ifdef CONFIG_NETWORK_SECMARK
 	__u32			secmark;
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index beb83d1ac1c6..2c35c02a931e 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -422,7 +422,7 @@ static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
 	dev_maps = rcu_dereference(dev->xps_maps);
 	if (dev_maps) {
 		map = rcu_dereference(
-		    dev_maps->cpu_map[raw_smp_processor_id()]);
+		    dev_maps->cpu_map[skb->sender_cpu - 1]);
 		if (map) {
 			if (map->len == 1)
 				queue_index = map->queues[0];
@@ -468,6 +468,11 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev,
 {
 	int queue_index = 0;
 
+#ifdef CONFIG_XPS
+	if (skb->sender_cpu == 0)
+		skb->sender_cpu = raw_smp_processor_id() + 1;
+#endif
+
 	if (dev->real_num_tx_queues != 1) {
 		const struct net_device_ops *ops = dev->netdev_ops;
 		if (ops->ndo_select_queue)
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index a5bff2767f15..88c613eab142 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -825,6 +825,9 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	CHECK_SKB_FIELD(napi_id);
 #endif
+#ifdef CONFIG_XPS
+	CHECK_SKB_FIELD(sender_cpu);
+#endif
 #ifdef CONFIG_NET_SCHED
 	CHECK_SKB_FIELD(tc_index);
 #ifdef CONFIG_NET_CLS_ACT
@@ -4169,6 +4172,7 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet)
 	skb->ignore_df = 0;
 	skb_dst_drop(skb);
 	skb->mark = 0;
+	skb->sender_cpu = 0;
 	skb_init_secmark(skb);
 	secpath_reset(skb);
 	nf_reset(skb);