Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from David Miller:

 1) Don't insert ESP trailer twice in IPSEC code, from Huy Nguyen.

 2) The default crypto algorithm selection in Kconfig for IPSEC is out
    of touch with modern reality, fix this up. From Eric Biggers.

 3) bpftool is missing an entry for BPF_MAP_TYPE_RINGBUF, from Andrii
    Nakryiko.

 4) Missing init of ->frame_sz in xdp_convert_zc_to_xdp_frame(), from
    Hangbin Liu.

 5) Adjust packet alignment handling in ax88179_178a driver to match
    what the hardware actually does. From Jeremy Kerr.

 6) register_netdevice can leak in the case one of the notifiers fail,
    from Yang Yingliang.

 7) Use after free in ip_tunnel_lookup(), from Taehee Yoo.

 8) VLAN checks in sja1105 DSA driver need adjustments, from Vladimir
    Oltean.

 9) tg3 driver can sleep forever when we get enough EEH errors, fix from
    David Christensen.

10) Missing {READ,WRITE}_ONCE() annotations in various Intel ethernet
    drivers, from Ciara Loftus.

11) Fix scanning loop break condition in of_mdiobus_register(), from
    Florian Fainelli.

12) MTU limit is incorrect in ibmveth driver, from Thomas Falcon.

13) Endianness fix in mlxsw, from Ido Schimmel.

14) Use after free in smsc95xx usbnet driver, from Tuomas Tynkkynen.

15) Missing bridge mrp configuration validation, from Horatiu Vultur.

16) Fix circular netns references in wireguard, from Jason A. Donenfeld.

17) PTP initialization on recovery is not done properly in qed driver,
    from Alexander Lobakin.

18) Endian conversion of L4 ports in filters of cxgb4 driver is wrong,
    from Rahul Lakkireddy.

19) Don't clear bound device TX queue of socket prematurely otherwise we
    get problems with ktls hw offloading, from Tariq Toukan.

20) ipset can do atomics on unaligned memory, fix from Russell King.

21) Align ethernet addresses properly in bridging code, from Thomas
    Martitz.

22) Don't advertise ipv4 addresses on SCTP sockets having ipv6only set,
    from Marcelo Ricardo Leitner.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (149 commits)
  rds: transport module should be auto loaded when transport is set
  sch_cake: fix a few style nits
  sch_cake: don't call diffserv parsing code when it is not needed
  sch_cake: don't try to reallocate or unshare skb unconditionally
  ethtool: fix error handling in linkstate_prepare_data()
  wil6210: account for napi_gro_receive never returning GRO_DROP
  hns: do not cast return value of napi_gro_receive to null
  socionext: account for napi_gro_receive never returning GRO_DROP
  wireguard: receive: account for napi_gro_receive never returning GRO_DROP
  vxlan: fix last fdb index during dump of fdb with nhid
  sctp: Don't advertise IPv4 addresses if ipv6only is set on the socket
  tc-testing: avoid action cookies with odd length.
  bpf: tcp: bpf_cubic: fix spurious HYSTART_DELAY exit upon drop in min RTT
  tcp_cubic: fix spurious HYSTART_DELAY exit upon drop in min RTT
  net: dsa: sja1105: fix tc-gate schedule with single element
  net: dsa: sja1105: recalculate gating subschedule after deleting tc-gate rules
  net: dsa: sja1105: unconditionally free old gating config
  net: dsa: sja1105: move sja1105_compose_gating_subschedule at the top
  net: macb: free resources on failure path of at91ether_open()
  net: macb: call pm_runtime_put_sync on failure path
  ...

6 files changed, 59 insertions, 55 deletions

diff --git a/drivers/net/wireguard/device.c b/drivers/net/wireguard/device.c
index 3ac3f8570ca1..a8f151b1b5fa 100644
--- a/drivers/net/wireguard/device.c
+++ b/drivers/net/wireguard/device.c
@@ -45,17 +45,18 @@ static int wg_open(struct net_device *dev)
 	if (dev_v6)
 		dev_v6->cnf.addr_gen_mode = IN6_ADDR_GEN_MODE_NONE;
 
+	mutex_lock(&wg->device_update_lock);
 	ret = wg_socket_init(wg, wg->incoming_port);
 	if (ret < 0)
-		return ret;
-	mutex_lock(&wg->device_update_lock);
+		goto out;
 	list_for_each_entry(peer, &wg->peer_list, peer_list) {
 		wg_packet_send_staged_packets(peer);
 		if (peer->persistent_keepalive_interval)
 			wg_packet_send_keepalive(peer);
 	}
+out:
 	mutex_unlock(&wg->device_update_lock);
-	return 0;
+	return ret;
 }
 
 #ifdef CONFIG_PM_SLEEP
@@ -225,6 +226,7 @@ static void wg_destruct(struct net_device *dev)
 	list_del(&wg->device_list);
 	rtnl_unlock();
 	mutex_lock(&wg->device_update_lock);
+	rcu_assign_pointer(wg->creating_net, NULL);
 	wg->incoming_port = 0;
 	wg_socket_reinit(wg, NULL, NULL);
 	/* The final references are cleared in the below calls to destroy_workqueue. */
@@ -240,13 +242,11 @@ static void wg_destruct(struct net_device *dev)
 	skb_queue_purge(&wg->incoming_handshakes);
 	free_percpu(dev->tstats);
 	free_percpu(wg->incoming_handshakes_worker);
-	if (wg->have_creating_net_ref)
-		put_net(wg->creating_net);
 	kvfree(wg->index_hashtable);
 	kvfree(wg->peer_hashtable);
 	mutex_unlock(&wg->device_update_lock);
 
-	pr_debug("%s: Interface deleted\n", dev->name);
+	pr_debug("%s: Interface destroyed\n", dev->name);
 	free_netdev(dev);
 }
 
@@ -292,7 +292,7 @@ static int wg_newlink(struct net *src_net, struct net_device *dev,
 	struct wg_device *wg = netdev_priv(dev);
 	int ret = -ENOMEM;
 
-	wg->creating_net = src_net;
+	rcu_assign_pointer(wg->creating_net, src_net);
 	init_rwsem(&wg->static_identity.lock);
 	mutex_init(&wg->socket_update_lock);
 	mutex_init(&wg->device_update_lock);
@@ -393,30 +393,26 @@ static struct rtnl_link_ops link_ops __read_mostly = {
 	.newlink		= wg_newlink,
 };
 
-static int wg_netdevice_notification(struct notifier_block *nb,
-				     unsigned long action, void *data)
+static void wg_netns_pre_exit(struct net *net)
 {
-	struct net_device *dev = ((struct netdev_notifier_info *)data)->dev;
-	struct wg_device *wg = netdev_priv(dev);
-
-	ASSERT_RTNL();
-
-	if (action != NETDEV_REGISTER || dev->netdev_ops != &netdev_ops)
-		return 0;
+	struct wg_device *wg;
 
-	if (dev_net(dev) == wg->creating_net && wg->have_creating_net_ref) {
-		put_net(wg->creating_net);
-		wg->have_creating_net_ref = false;
-	} else if (dev_net(dev) != wg->creating_net &&
-		   !wg->have_creating_net_ref) {
-		wg->have_creating_net_ref = true;
-		get_net(wg->creating_net);
+	rtnl_lock();
+	list_for_each_entry(wg, &device_list, device_list) {
+		if (rcu_access_pointer(wg->creating_net) == net) {
+			pr_debug("%s: Creating namespace exiting\n", wg->dev->name);
+			netif_carrier_off(wg->dev);
+			mutex_lock(&wg->device_update_lock);
+			rcu_assign_pointer(wg->creating_net, NULL);
+			wg_socket_reinit(wg, NULL, NULL);
+			mutex_unlock(&wg->device_update_lock);
+		}
 	}
-	return 0;
+	rtnl_unlock();
 }
 
-static struct notifier_block netdevice_notifier = {
-	.notifier_call = wg_netdevice_notification
+static struct pernet_operations pernet_ops = {
+	.pre_exit = wg_netns_pre_exit
 };
 
 int __init wg_device_init(void)
@@ -429,18 +425,18 @@ int __init wg_device_init(void)
 		return ret;
 #endif
 
-	ret = register_netdevice_notifier(&netdevice_notifier);
+	ret = register_pernet_device(&pernet_ops);
 	if (ret)
 		goto error_pm;
 
 	ret = rtnl_link_register(&link_ops);
 	if (ret)
-		goto error_netdevice;
+		goto error_pernet;
 
 	return 0;
 
-error_netdevice:
-	unregister_netdevice_notifier(&netdevice_notifier);
+error_pernet:
+	unregister_pernet_device(&pernet_ops);
 error_pm:
 #ifdef CONFIG_PM_SLEEP
 	unregister_pm_notifier(&pm_notifier);
@@ -451,7 +447,7 @@ error_pm:
 void wg_device_uninit(void)
 {
 	rtnl_link_unregister(&link_ops);
-	unregister_netdevice_notifier(&netdevice_notifier);
+	unregister_pernet_device(&pernet_ops);
 #ifdef CONFIG_PM_SLEEP
 	unregister_pm_notifier(&pm_notifier);
 #endif
diff --git a/drivers/net/wireguard/device.h b/drivers/net/wireguard/device.h
index b15a8be9d816..4d0144e16947 100644
--- a/drivers/net/wireguard/device.h
+++ b/drivers/net/wireguard/device.h
@@ -40,7 +40,7 @@ struct wg_device {
 	struct net_device *dev;
 	struct crypt_queue encrypt_queue, decrypt_queue;
 	struct sock __rcu *sock4, *sock6;
-	struct net *creating_net;
+	struct net __rcu *creating_net;
 	struct noise_static_identity static_identity;
 	struct workqueue_struct *handshake_receive_wq, *handshake_send_wq;
 	struct workqueue_struct *packet_crypt_wq;
@@ -56,7 +56,6 @@ struct wg_device {
 	unsigned int num_peers, device_update_gen;
 	u32 fwmark;
 	u16 incoming_port;
-	bool have_creating_net_ref;
 };
 
 int wg_device_init(void);
diff --git a/drivers/net/wireguard/netlink.c b/drivers/net/wireguard/netlink.c
index 802099c8828a..20a4f3c0a0a1 100644
--- a/drivers/net/wireguard/netlink.c
+++ b/drivers/net/wireguard/netlink.c
@@ -511,11 +511,15 @@ static int wg_set_device(struct sk_buff *skb, struct genl_info *info)
 	if (flags & ~__WGDEVICE_F_ALL)
 		goto out;
 
-	ret = -EPERM;
-	if ((info->attrs[WGDEVICE_A_LISTEN_PORT] ||
-	     info->attrs[WGDEVICE_A_FWMARK]) &&
-	    !ns_capable(wg->creating_net->user_ns, CAP_NET_ADMIN))
-		goto out;
+	if (info->attrs[WGDEVICE_A_LISTEN_PORT] || info->attrs[WGDEVICE_A_FWMARK]) {
+		struct net *net;
+		rcu_read_lock();
+		net = rcu_dereference(wg->creating_net);
+		ret = !net || !ns_capable(net->user_ns, CAP_NET_ADMIN) ? -EPERM : 0;
+		rcu_read_unlock();
+		if (ret)
+			goto out;
+	}
 
 	++wg->device_update_gen;
 
diff --git a/drivers/net/wireguard/noise.c b/drivers/net/wireguard/noise.c
index 626433690abb..201a22681945 100644
--- a/drivers/net/wireguard/noise.c
+++ b/drivers/net/wireguard/noise.c
@@ -617,8 +617,8 @@ wg_noise_handshake_consume_initiation(struct message_handshake_initiation *src,
 	memcpy(handshake->hash, hash, NOISE_HASH_LEN);
 	memcpy(handshake->chaining_key, chaining_key, NOISE_HASH_LEN);
 	handshake->remote_index = src->sender_index;
-	if ((s64)(handshake->last_initiation_consumption -
-	    (initiation_consumption = ktime_get_coarse_boottime_ns())) < 0)
+	initiation_consumption = ktime_get_coarse_boottime_ns();
+	if ((s64)(handshake->last_initiation_consumption - initiation_consumption) < 0)
 		handshake->last_initiation_consumption = initiation_consumption;
 	handshake->state = HANDSHAKE_CONSUMED_INITIATION;
 	up_write(&handshake->lock);
diff --git a/drivers/net/wireguard/receive.c b/drivers/net/wireguard/receive.c
index 91438144e4f7..9b2ab6fc91cd 100644
--- a/drivers/net/wireguard/receive.c
+++ b/drivers/net/wireguard/receive.c
@@ -414,14 +414,8 @@ static void wg_packet_consume_data_done(struct wg_peer *peer,
 	if (unlikely(routed_peer != peer))
 		goto dishonest_packet_peer;
 
-	if (unlikely(napi_gro_receive(&peer->napi, skb) == GRO_DROP)) {
-		++dev->stats.rx_dropped;
-		net_dbg_ratelimited("%s: Failed to give packet to userspace from peer %llu (%pISpfsc)\n",
-				    dev->name, peer->internal_id,
-				    &peer->endpoint.addr);
-	} else {
-		update_rx_stats(peer, message_data_len(len_before_trim));
-	}
+	napi_gro_receive(&peer->napi, skb);
+	update_rx_stats(peer, message_data_len(len_before_trim));
 	return;
 
 dishonest_packet_peer:
diff --git a/drivers/net/wireguard/socket.c b/drivers/net/wireguard/socket.c
index f9018027fc13..c33e2c81635f 100644
--- a/drivers/net/wireguard/socket.c
+++ b/drivers/net/wireguard/socket.c
@@ -347,6 +347,7 @@ static void set_sock_opts(struct socket *sock)
 
 int wg_socket_init(struct wg_device *wg, u16 port)
 {
+	struct net *net;
 	int ret;
 	struct udp_tunnel_sock_cfg cfg = {
 		.sk_user_data = wg,
@@ -371,37 +372,47 @@ int wg_socket_init(struct wg_device *wg, u16 port)
 	};
 #endif
 
+	rcu_read_lock();
+	net = rcu_dereference(wg->creating_net);
+	net = net ? maybe_get_net(net) : NULL;
+	rcu_read_unlock();
+	if (unlikely(!net))
+		return -ENONET;
+
 #if IS_ENABLED(CONFIG_IPV6)
 retry:
 #endif
 
-	ret = udp_sock_create(wg->creating_net, &port4, &new4);
+	ret = udp_sock_create(net, &port4, &new4);
 	if (ret < 0) {
 		pr_err("%s: Could not create IPv4 socket\n", wg->dev->name);
-		return ret;
+		goto out;
 	}
 	set_sock_opts(new4);
-	setup_udp_tunnel_sock(wg->creating_net, new4, &cfg);
+	setup_udp_tunnel_sock(net, new4, &cfg);
 
 #if IS_ENABLED(CONFIG_IPV6)
 	if (ipv6_mod_enabled()) {
 		port6.local_udp_port = inet_sk(new4->sk)->inet_sport;
-		ret = udp_sock_create(wg->creating_net, &port6, &new6);
+		ret = udp_sock_create(net, &port6, &new6);
 		if (ret < 0) {
 			udp_tunnel_sock_release(new4);
 			if (ret == -EADDRINUSE && !port && retries++ < 100)
 				goto retry;
 			pr_err("%s: Could not create IPv6 socket\n",
 			       wg->dev->name);
-			return ret;
+			goto out;
 		}
 		set_sock_opts(new6);
-		setup_udp_tunnel_sock(wg->creating_net, new6, &cfg);
+		setup_udp_tunnel_sock(net, new6, &cfg);
 	}
 #endif
 
 	wg_socket_reinit(wg, new4->sk, new6 ? new6->sk : NULL);
-	return 0;
+	ret = 0;
+out:
+	put_net(net);
+	return ret;
 }
 
 void wg_socket_reinit(struct wg_device *wg, struct sock *new4,