Merge tag 'net-6.5-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Including fixes from bluetooth, bpf and wireguard.

  Current release - regressions:

   - nvme-tcp: fix comma-related oops after sendpage changes

  Current release - new code bugs:

   - ptp: make max_phase_adjustment sysfs device attribute invisible
     when not supported

  Previous releases - regressions:

   - sctp: fix potential deadlock on &net->sctp.addr_wq_lock

   - mptcp:
      - ensure subflow is unhashed before cleaning the backlog
      - do not rely on implicit state check in mptcp_listen()

  Previous releases - always broken:

   - net: fix net_dev_start_xmit trace event vs skb_transport_offset()

   - Bluetooth:
      - fix use-bdaddr-property quirk
      - L2CAP: fix multiple UaFs
      - ISO: use hci_sync for setting CIG parameters
      - hci_event: fix Set CIG Parameters error status handling
      - hci_event: fix parsing of CIS Established Event
      - MGMT: fix marking SCAN_RSP as not connectable

   - wireguard: queuing: use saner cpu selection wrapping

   - sched: act_ipt: various bug fixes for iptables <> TC interactions

   - sched: act_pedit: add size check for TCA_PEDIT_PARMS_EX

   - dsa: fixes for receiving PTP packets with 8021q and sja1105 tagging

   - eth: sfc: fix null-deref in devlink port without MAE access

   - eth: ibmvnic: do not reset dql stats on NON_FATAL err

  Misc:

   - xsk: honor SO_BINDTODEVICE on bind"

* tag 'net-6.5-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (70 commits)
  nfp: clean mc addresses in application firmware when closing port
  selftests: mptcp: pm_nl_ctl: fix 32-bit support
  selftests: mptcp: depend on SYN_COOKIES
  selftests: mptcp: userspace_pm: report errors with 'remove' tests
  selftests: mptcp: userspace_pm: use correct server port
  selftests: mptcp: sockopt: return error if wrong mark
  selftests: mptcp: sockopt: use 'iptables-legacy' if available
  selftests: mptcp: connect: fail if nft supposed to work
  mptcp: do not rely on implicit state check in mptcp_listen()
  mptcp: ensure subflow is unhashed before cleaning the backlog
  s390/qeth: Fix vipa deletion
  octeontx-af: fix hardware timestamp configuration
  net: dsa: sja1105: always enable the send_meta options
  net: dsa: tag_sja1105: fix MAC DA patching from meta frames
  net: Replace strlcpy with strscpy
  pptp: Fix fib lookup calls.
  mlxsw: spectrum_router: Fix an IS_ERR() vs NULL check
  net/sched: act_pedit: Add size check for TCA_PEDIT_PARMS_EX
  xsk: Honor SO_BINDTODEVICE on bind
  ptp: Make max_phase_adjustment sysfs device attribute invisible when not supported
  ...

6 files changed, 28 insertions, 26 deletions

diff --git a/drivers/net/wireguard/netlink.c b/drivers/net/wireguard/netlink.c
index 43c8c84..6d1bd9f 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 8084e74..26d235d 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 125284b..1ea4f87 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 7135d51..0b3f0c8 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 5368f7c..95c853b 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 53d8a57..968bdb4 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);
 }