diff --git a/drivers/net/wireguard/netlink.c b/drivers/net/wireguard/netlink.c
index 43c8c84e7ea8..6d1bd9f52d02 100644
--- a/drivers/net/wireguard/netlink.c
+++ b/drivers/net/wireguard/netlink.c
@@ -546,6 +546,7 @@ static int wg_set_device(struct sk_buff *skb, struct genl_info *info)
 		u8 *private_key = nla_data(info->attrs[WGDEVICE_A_PRIVATE_KEY]);
 		u8 public_key[NOISE_PUBLIC_KEY_LEN];
 		struct wg_peer *peer, *temp;
+		bool send_staged_packets;
 
 		if (!crypto_memneq(wg->static_identity.static_private,
 				   private_key, NOISE_PUBLIC_KEY_LEN))
@@ -564,14 +565,17 @@ static int wg_set_device(struct sk_buff *skb, struct genl_info *info)
 		}
 
 		down_write(&wg->static_identity.lock);
-		wg_noise_set_static_identity_private_key(&wg->static_identity,
-							 private_key);
-		list_for_each_entry_safe(peer, temp, &wg->peer_list,
-					 peer_list) {
+		send_staged_packets = !wg->static_identity.has_identity && netif_running(wg->dev);
+		wg_noise_set_static_identity_private_key(&wg->static_identity, private_key);
+		send_staged_packets = send_staged_packets && wg->static_identity.has_identity;
+
+		wg_cookie_checker_precompute_device_keys(&wg->cookie_checker);
+		list_for_each_entry_safe(peer, temp, &wg->peer_list, peer_list) {
 			wg_noise_precompute_static_static(peer);
 			wg_noise_expire_current_peer_keypairs(peer);
+			if (send_staged_packets)
+				wg_packet_send_staged_packets(peer);
 		}
-		wg_cookie_checker_precompute_device_keys(&wg->cookie_checker);
 		up_write(&wg->static_identity.lock);
 	}
 skip_set_private_key:
diff --git a/drivers/net/wireguard/queueing.c b/drivers/net/wireguard/queueing.c
index 8084e7408c0a..26d235d15235 100644
--- a/drivers/net/wireguard/queueing.c
+++ b/drivers/net/wireguard/queueing.c
@@ -28,6 +28,7 @@ int wg_packet_queue_init(struct crypt_queue *queue, work_func_t function,
 	int ret;
 
 	memset(queue, 0, sizeof(*queue));
+	queue->last_cpu = -1;
 	ret = ptr_ring_init(&queue->ring, len, GFP_KERNEL);
 	if (ret)
 		return ret;
diff --git a/drivers/net/wireguard/queueing.h b/drivers/net/wireguard/queueing.h
index 125284b346a7..1ea4f874e367 100644
--- a/drivers/net/wireguard/queueing.h
+++ b/drivers/net/wireguard/queueing.h
@@ -117,20 +117,17 @@ static inline int wg_cpumask_choose_online(int *stored_cpu, unsigned int id)
 	return cpu;
 }
 
-/* This function is racy, in the sense that next is unlocked, so it could return
- * the same CPU twice. A race-free version of this would be to instead store an
- * atomic sequence number, do an increment-and-return, and then iterate through
- * every possible CPU until we get to that index -- choose_cpu. However that's
- * a bit slower, and it doesn't seem like this potential race actually
- * introduces any performance loss, so we live with it.
+/* This function is racy, in the sense that it's called while last_cpu is
+ * unlocked, so it could return the same CPU twice. Adding locking or using
+ * atomic sequence numbers is slower though, and the consequences of racing are
+ * harmless, so live with it.
  */
-static inline int wg_cpumask_next_online(int *next)
+static inline int wg_cpumask_next_online(int *last_cpu)
 {
-	int cpu = *next;
-
-	while (unlikely(!cpumask_test_cpu(cpu, cpu_online_mask)))
-		cpu = cpumask_next(cpu, cpu_online_mask) % nr_cpumask_bits;
-	*next = cpumask_next(cpu, cpu_online_mask) % nr_cpumask_bits;
+	int cpu = cpumask_next(*last_cpu, cpu_online_mask);
+	if (cpu >= nr_cpu_ids)
+		cpu = cpumask_first(cpu_online_mask);
+	*last_cpu = cpu;
 	return cpu;
 }
 
@@ -159,7 +156,7 @@ static inline void wg_prev_queue_drop_peeked(struct prev_queue *queue)
 
 static inline int wg_queue_enqueue_per_device_and_peer(
 	struct crypt_queue *device_queue, struct prev_queue *peer_queue,
-	struct sk_buff *skb, struct workqueue_struct *wq, int *next_cpu)
+	struct sk_buff *skb, struct workqueue_struct *wq)
 {
 	int cpu;
 
@@ -173,7 +170,7 @@ static inline int wg_queue_enqueue_per_device_and_peer(
 	/* Then we queue it up in the device queue, which consumes the
 	 * packet as soon as it can.
 	 */
-	cpu = wg_cpumask_next_online(next_cpu);
+	cpu = wg_cpumask_next_online(&device_queue->last_cpu);
 	if (unlikely(ptr_ring_produce_bh(&device_queue->ring, skb)))
 		return -EPIPE;
 	queue_work_on(cpu, wq, &per_cpu_ptr(device_queue->worker, cpu)->work);
diff --git a/drivers/net/wireguard/receive.c b/drivers/net/wireguard/receive.c
index 7135d51d2d87..0b3f0c843550 100644
--- a/drivers/net/wireguard/receive.c
+++ b/drivers/net/wireguard/receive.c
@@ -524,7 +524,7 @@ static void wg_packet_consume_data(struct wg_device *wg, struct sk_buff *skb)
 		goto err;
 
 	ret = wg_queue_enqueue_per_device_and_peer(&wg->decrypt_queue, &peer->rx_queue, skb,
-						   wg->packet_crypt_wq, &wg->decrypt_queue.last_cpu);
+						   wg->packet_crypt_wq);
 	if (unlikely(ret == -EPIPE))
 		wg_queue_enqueue_per_peer_rx(skb, PACKET_STATE_DEAD);
 	if (likely(!ret || ret == -EPIPE)) {
diff --git a/drivers/net/wireguard/send.c b/drivers/net/wireguard/send.c
index 5368f7c35b4b..95c853b59e1d 100644
--- a/drivers/net/wireguard/send.c
+++ b/drivers/net/wireguard/send.c
@@ -318,7 +318,7 @@ static void wg_packet_create_data(struct wg_peer *peer, struct sk_buff *first)
 		goto err;
 
 	ret = wg_queue_enqueue_per_device_and_peer(&wg->encrypt_queue, &peer->tx_queue, first,
-						   wg->packet_crypt_wq, &wg->encrypt_queue.last_cpu);
+						   wg->packet_crypt_wq);
 	if (unlikely(ret == -EPIPE))
 		wg_queue_enqueue_per_peer_tx(first, PACKET_STATE_DEAD);
 err:
diff --git a/drivers/net/wireguard/timers.c b/drivers/net/wireguard/timers.c
index 53d8a57a0dfa..968bdb4df0b3 100644
--- a/drivers/net/wireguard/timers.c
+++ b/drivers/net/wireguard/timers.c
@@ -234,10 +234,10 @@ void wg_timers_init(struct wg_peer *peer)
 
 void wg_timers_stop(struct wg_peer *peer)
 {
-	del_timer_sync(&peer->timer_retransmit_handshake);
-	del_timer_sync(&peer->timer_send_keepalive);
-	del_timer_sync(&peer->timer_new_handshake);
-	del_timer_sync(&peer->timer_zero_key_material);
-	del_timer_sync(&peer->timer_persistent_keepalive);
+	timer_delete_sync(&peer->timer_retransmit_handshake);
+	timer_delete_sync(&peer->timer_send_keepalive);
+	timer_delete_sync(&peer->timer_new_handshake);
+	timer_delete_sync(&peer->timer_zero_key_material);
+	timer_delete_sync(&peer->timer_persistent_keepalive);
 	flush_work(&peer->clear_peer_work);
 }
diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh
index 69c7796c7ca9..405ff262ca93 100755
--- a/tools/testing/selftests/wireguard/netns.sh
+++ b/tools/testing/selftests/wireguard/netns.sh
@@ -514,10 +514,32 @@ n2 bash -c 'printf 0 > /proc/sys/net/ipv4/conf/all/rp_filter'
 n1 ping -W 1 -c 1 192.168.241.2
 [[ $(n2 wg show wg0 endpoints) == "$pub1	10.0.0.3:1" ]]
 
-ip1 link del veth1
-ip1 link del veth3
-ip1 link del wg0
-ip2 link del wg0
+ip1 link del dev veth3
+ip1 link del dev wg0
+ip2 link del dev wg0
+
+# Make sure persistent keep alives are sent when an adapter comes up
+ip1 link add dev wg0 type wireguard
+n1 wg set wg0 private-key <(echo "$key1") peer "$pub2" endpoint 10.0.0.1:1 persistent-keepalive 1
+read _ _ tx_bytes < <(n1 wg show wg0 transfer)
+[[ $tx_bytes -eq 0 ]]
+ip1 link set dev wg0 up
+read _ _ tx_bytes < <(n1 wg show wg0 transfer)
+[[ $tx_bytes -gt 0 ]]
+ip1 link del dev wg0
+# This should also happen even if the private key is set later
+ip1 link add dev wg0 type wireguard
+n1 wg set wg0 peer "$pub2" endpoint 10.0.0.1:1 persistent-keepalive 1
+read _ _ tx_bytes < <(n1 wg show wg0 transfer)
+[[ $tx_bytes -eq 0 ]]
+ip1 link set dev wg0 up
+read _ _ tx_bytes < <(n1 wg show wg0 transfer)
+[[ $tx_bytes -eq 0 ]]
+n1 wg set wg0 private-key <(echo "$key1")
+read _ _ tx_bytes < <(n1 wg show wg0 transfer)
+[[ $tx_bytes -gt 0 ]]
+ip1 link del dev veth1
+ip1 link del dev wg0
 
 # We test that Netlink/IPC is working properly by doing things that usually cause split responses
 ip0 link add dev wg0 type wireguard