Merge commit '49caedb668e476c100d727f2174724e0610a2b92' of https://github.com/openbmc/linux into openbmc/dev-5.15-intel-bump_v5.15.36

Signed-off-by: Sujoy Ray <sujoy.ray@intel.com>

171 files changed, 3548 insertions, 1004 deletions

diff --git a/net/9p/trans_xen.c b/net/9p/trans_xen.c
index 3ec1a51a6944..432ac5a16f2e 100644
--- a/net/9p/trans_xen.c
+++ b/net/9p/trans_xen.c
@@ -304,9 +304,9 @@ static void xen_9pfs_front_free(struct xen_9pfs_front_priv *priv)
 				ref = priv->rings[i].intf->ref[j];
 				gnttab_end_foreign_access(ref, 0, 0);
 			}
-			free_pages((unsigned long)priv->rings[i].data.in,
-				   priv->rings[i].intf->ring_order -
-				   (PAGE_SHIFT - XEN_PAGE_SHIFT));
+			free_pages_exact(priv->rings[i].data.in,
+				   1UL << (priv->rings[i].intf->ring_order +
+					   XEN_PAGE_SHIFT));
 		}
 		gnttab_end_foreign_access(priv->rings[i].ref, 0, 0);
 		free_page((unsigned long)priv->rings[i].intf);
@@ -345,8 +345,8 @@ static int xen_9pfs_front_alloc_dataring(struct xenbus_device *dev,
 	if (ret < 0)
 		goto out;
 	ring->ref = ret;
-	bytes = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
-			order - (PAGE_SHIFT - XEN_PAGE_SHIFT));
+	bytes = alloc_pages_exact(1UL << (order + XEN_PAGE_SHIFT),
+				  GFP_KERNEL | __GFP_ZERO);
 	if (!bytes) {
 		ret = -ENOMEM;
 		goto out;
@@ -377,9 +377,7 @@ out:
 	if (bytes) {
 		for (i--; i >= 0; i--)
 			gnttab_end_foreign_access(ring->intf->ref[i], 0, 0);
-		free_pages((unsigned long)bytes,
-			   ring->intf->ring_order -
-			   (PAGE_SHIFT - XEN_PAGE_SHIFT));
+		free_pages_exact(bytes, 1UL << (order + XEN_PAGE_SHIFT));
 	}
 	gnttab_end_foreign_access(ring->ref, 0, 0);
 	free_page((unsigned long)ring->intf);
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index 7473e0cc6d46..7b69503dc46a 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -77,6 +77,7 @@ static void ax25_kill_by_device(struct net_device *dev)
 {
 	ax25_dev *ax25_dev;
 	ax25_cb *s;
+	struct sock *sk;
 
 	if ((ax25_dev = ax25_dev_ax25dev(dev)) == NULL)
 		return;
@@ -85,13 +86,26 @@ static void ax25_kill_by_device(struct net_device *dev)
 again:
 	ax25_for_each(s, &ax25_list) {
 		if (s->ax25_dev == ax25_dev) {
+			sk = s->sk;
+			if (!sk) {
+				spin_unlock_bh(&ax25_list_lock);
+				ax25_disconnect(s, ENETUNREACH);
+				s->ax25_dev = NULL;
+				spin_lock_bh(&ax25_list_lock);
+				goto again;
+			}
+			sock_hold(sk);
 			spin_unlock_bh(&ax25_list_lock);
-			lock_sock(s->sk);
-			s->ax25_dev = NULL;
-			release_sock(s->sk);
+			lock_sock(sk);
 			ax25_disconnect(s, ENETUNREACH);
+			s->ax25_dev = NULL;
+			if (sk->sk_socket) {
+				dev_put(ax25_dev->dev);
+				ax25_dev_put(ax25_dev);
+			}
+			release_sock(sk);
 			spin_lock_bh(&ax25_list_lock);
-
+			sock_put(sk);
 			/* The entry could have been deleted from the
 			 * list meanwhile and thus the next pointer is
 			 * no longer valid.  Play it safe and restart
@@ -355,21 +369,25 @@ static int ax25_ctl_ioctl(const unsigned int cmd, void __user *arg)
 	if (copy_from_user(&ax25_ctl, arg, sizeof(ax25_ctl)))
 		return -EFAULT;
 
-	if ((ax25_dev = ax25_addr_ax25dev(&ax25_ctl.port_addr)) == NULL)
-		return -ENODEV;
-
 	if (ax25_ctl.digi_count > AX25_MAX_DIGIS)
 		return -EINVAL;
 
 	if (ax25_ctl.arg > ULONG_MAX / HZ && ax25_ctl.cmd != AX25_KILL)
 		return -EINVAL;
 
+	ax25_dev = ax25_addr_ax25dev(&ax25_ctl.port_addr);
+	if (!ax25_dev)
+		return -ENODEV;
+
 	digi.ndigi = ax25_ctl.digi_count;
 	for (k = 0; k < digi.ndigi; k++)
 		digi.calls[k] = ax25_ctl.digi_addr[k];
 
-	if ((ax25 = ax25_find_cb(&ax25_ctl.source_addr, &ax25_ctl.dest_addr, &digi, ax25_dev->dev)) == NULL)
+	ax25 = ax25_find_cb(&ax25_ctl.source_addr, &ax25_ctl.dest_addr, &digi, ax25_dev->dev);
+	if (!ax25) {
+		ax25_dev_put(ax25_dev);
 		return -ENOTCONN;
+	}
 
 	switch (ax25_ctl.cmd) {
 	case AX25_KILL:
@@ -436,6 +454,7 @@ static int ax25_ctl_ioctl(const unsigned int cmd, void __user *arg)
 	  }
 
 out_put:
+	ax25_dev_put(ax25_dev);
 	ax25_cb_put(ax25);
 	return ret;
 
@@ -962,14 +981,16 @@ static int ax25_release(struct socket *sock)
 {
 	struct sock *sk = sock->sk;
 	ax25_cb *ax25;
+	ax25_dev *ax25_dev;
 
 	if (sk == NULL)
 		return 0;
 
 	sock_hold(sk);
-	sock_orphan(sk);
 	lock_sock(sk);
+	sock_orphan(sk);
 	ax25 = sk_to_ax25(sk);
+	ax25_dev = ax25->ax25_dev;
 
 	if (sk->sk_type == SOCK_SEQPACKET) {
 		switch (ax25->state) {
@@ -1031,6 +1052,15 @@ static int ax25_release(struct socket *sock)
 		sk->sk_state_change(sk);
 		ax25_destroy_socket(ax25);
 	}
+	if (ax25_dev) {
+		del_timer_sync(&ax25->timer);
+		del_timer_sync(&ax25->t1timer);
+		del_timer_sync(&ax25->t2timer);
+		del_timer_sync(&ax25->t3timer);
+		del_timer_sync(&ax25->idletimer);
+		dev_put(ax25_dev->dev);
+		ax25_dev_put(ax25_dev);
+	}
 
 	sock->sk   = NULL;
 	release_sock(sk);
@@ -1107,8 +1137,10 @@ static int ax25_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 		}
 	}
 
-	if (ax25_dev != NULL)
+	if (ax25_dev) {
 		ax25_fillin_cb(ax25, ax25_dev);
+		dev_hold(ax25_dev->dev);
+	}
 
 done:
 	ax25_cb_add(ax25);
diff --git a/net/ax25/ax25_dev.c b/net/ax25/ax25_dev.c
index 4ac2e0847652..d2e0cc67d91a 100644
--- a/net/ax25/ax25_dev.c
+++ b/net/ax25/ax25_dev.c
@@ -37,6 +37,7 @@ ax25_dev *ax25_addr_ax25dev(ax25_address *addr)
 	for (ax25_dev = ax25_dev_list; ax25_dev != NULL; ax25_dev = ax25_dev->next)
 		if (ax25cmp(addr, (ax25_address *)ax25_dev->dev->dev_addr) == 0) {
 			res = ax25_dev;
+			ax25_dev_hold(ax25_dev);
 		}
 	spin_unlock_bh(&ax25_dev_lock);
 
@@ -56,6 +57,7 @@ void ax25_dev_device_up(struct net_device *dev)
 		return;
 	}
 
+	refcount_set(&ax25_dev->refcount, 1);
 	dev->ax25_ptr     = ax25_dev;
 	ax25_dev->dev     = dev;
 	dev_hold(dev);
@@ -84,6 +86,7 @@ void ax25_dev_device_up(struct net_device *dev)
 	ax25_dev->next = ax25_dev_list;
 	ax25_dev_list  = ax25_dev;
 	spin_unlock_bh(&ax25_dev_lock);
+	ax25_dev_hold(ax25_dev);
 
 	ax25_register_dev_sysctl(ax25_dev);
 }
@@ -113,9 +116,10 @@ void ax25_dev_device_down(struct net_device *dev)
 	if ((s = ax25_dev_list) == ax25_dev) {
 		ax25_dev_list = s->next;
 		spin_unlock_bh(&ax25_dev_lock);
+		ax25_dev_put(ax25_dev);
 		dev->ax25_ptr = NULL;
 		dev_put(dev);
-		kfree(ax25_dev);
+		ax25_dev_put(ax25_dev);
 		return;
 	}
 
@@ -123,9 +127,10 @@ void ax25_dev_device_down(struct net_device *dev)
 		if (s->next == ax25_dev) {
 			s->next = ax25_dev->next;
 			spin_unlock_bh(&ax25_dev_lock);
+			ax25_dev_put(ax25_dev);
 			dev->ax25_ptr = NULL;
 			dev_put(dev);
-			kfree(ax25_dev);
+			ax25_dev_put(ax25_dev);
 			return;
 		}
 
@@ -133,6 +138,7 @@ void ax25_dev_device_down(struct net_device *dev)
 	}
 	spin_unlock_bh(&ax25_dev_lock);
 	dev->ax25_ptr = NULL;
+	ax25_dev_put(ax25_dev);
 }
 
 int ax25_fwd_ioctl(unsigned int cmd, struct ax25_fwd_struct *fwd)
@@ -144,20 +150,32 @@ int ax25_fwd_ioctl(unsigned int cmd, struct ax25_fwd_struct *fwd)
 
 	switch (cmd) {
 	case SIOCAX25ADDFWD:
-		if ((fwd_dev = ax25_addr_ax25dev(&fwd->port_to)) == NULL)
+		fwd_dev = ax25_addr_ax25dev(&fwd->port_to);
+		if (!fwd_dev) {
+			ax25_dev_put(ax25_dev);
 			return -EINVAL;
-		if (ax25_dev->forward != NULL)
+		}
+		if (ax25_dev->forward) {
+			ax25_dev_put(fwd_dev);
+			ax25_dev_put(ax25_dev);
 			return -EINVAL;
+		}
 		ax25_dev->forward = fwd_dev->dev;
+		ax25_dev_put(fwd_dev);
+		ax25_dev_put(ax25_dev);
 		break;
 
 	case SIOCAX25DELFWD:
-		if (ax25_dev->forward == NULL)
+		if (!ax25_dev->forward) {
+			ax25_dev_put(ax25_dev);
 			return -EINVAL;
+		}
 		ax25_dev->forward = NULL;
+		ax25_dev_put(ax25_dev);
 		break;
 
 	default:
+		ax25_dev_put(ax25_dev);
 		return -EINVAL;
 	}
 
diff --git a/net/ax25/ax25_route.c b/net/ax25/ax25_route.c
index d0b2e094bd55..9751207f7757 100644
--- a/net/ax25/ax25_route.c
+++ b/net/ax25/ax25_route.c
@@ -75,11 +75,13 @@ static int __must_check ax25_rt_add(struct ax25_routes_struct *route)
 	ax25_dev *ax25_dev;
 	int i;
 
-	if ((ax25_dev = ax25_addr_ax25dev(&route->port_addr)) == NULL)
-		return -EINVAL;
 	if (route->digi_count > AX25_MAX_DIGIS)
 		return -EINVAL;
 
+	ax25_dev = ax25_addr_ax25dev(&route->port_addr);
+	if (!ax25_dev)
+		return -EINVAL;
+
 	write_lock_bh(&ax25_route_lock);
 
 	ax25_rt = ax25_route_list;
@@ -91,6 +93,7 @@ static int __must_check ax25_rt_add(struct ax25_routes_struct *route)
 			if (route->digi_count != 0) {
 				if ((ax25_rt->digipeat = kmalloc(sizeof(ax25_digi), GFP_ATOMIC)) == NULL) {
 					write_unlock_bh(&ax25_route_lock);
+					ax25_dev_put(ax25_dev);
 					return -ENOMEM;
 				}
 				ax25_rt->digipeat->lastrepeat = -1;
@@ -101,6 +104,7 @@ static int __must_check ax25_rt_add(struct ax25_routes_struct *route)
 				}
 			}
 			write_unlock_bh(&ax25_route_lock);
+			ax25_dev_put(ax25_dev);
 			return 0;
 		}
 		ax25_rt = ax25_rt->next;
@@ -108,6 +112,7 @@ static int __must_check ax25_rt_add(struct ax25_routes_struct *route)
 
 	if ((ax25_rt = kmalloc(sizeof(ax25_route), GFP_ATOMIC)) == NULL) {
 		write_unlock_bh(&ax25_route_lock);
+		ax25_dev_put(ax25_dev);
 		return -ENOMEM;
 	}
 
@@ -120,6 +125,7 @@ static int __must_check ax25_rt_add(struct ax25_routes_struct *route)
 		if ((ax25_rt->digipeat = kmalloc(sizeof(ax25_digi), GFP_ATOMIC)) == NULL) {
 			write_unlock_bh(&ax25_route_lock);
 			kfree(ax25_rt);
+			ax25_dev_put(ax25_dev);
 			return -ENOMEM;
 		}
 		ax25_rt->digipeat->lastrepeat = -1;
@@ -132,6 +138,7 @@ static int __must_check ax25_rt_add(struct ax25_routes_struct *route)
 	ax25_rt->next   = ax25_route_list;
 	ax25_route_list = ax25_rt;
 	write_unlock_bh(&ax25_route_lock);
+	ax25_dev_put(ax25_dev);
 
 	return 0;
 }
@@ -173,6 +180,7 @@ static int ax25_rt_del(struct ax25_routes_struct *route)
 		}
 	}
 	write_unlock_bh(&ax25_route_lock);
+	ax25_dev_put(ax25_dev);
 
 	return 0;
 }
@@ -215,6 +223,7 @@ static int ax25_rt_opt(struct ax25_route_opt_struct *rt_option)
 
 out:
 	write_unlock_bh(&ax25_route_lock);
+	ax25_dev_put(ax25_dev);
 	return err;
 }
 
diff --git a/net/ax25/ax25_subr.c b/net/ax25/ax25_subr.c
index 15ab812c4fe4..3a476e4f6cd0 100644
--- a/net/ax25/ax25_subr.c
+++ b/net/ax25/ax25_subr.c
@@ -261,12 +261,20 @@ void ax25_disconnect(ax25_cb *ax25, int reason)
 {
 	ax25_clear_queues(ax25);
 
-	if (!ax25->sk || !sock_flag(ax25->sk, SOCK_DESTROY))
-		ax25_stop_heartbeat(ax25);
-	ax25_stop_t1timer(ax25);
-	ax25_stop_t2timer(ax25);
-	ax25_stop_t3timer(ax25);
-	ax25_stop_idletimer(ax25);
+	if (reason == ENETUNREACH) {
+		del_timer_sync(&ax25->timer);
+		del_timer_sync(&ax25->t1timer);
+		del_timer_sync(&ax25->t2timer);
+		del_timer_sync(&ax25->t3timer);
+		del_timer_sync(&ax25->idletimer);
+	} else {
+		if (!ax25->sk || !sock_flag(ax25->sk, SOCK_DESTROY))
+			ax25_stop_heartbeat(ax25);
+		ax25_stop_t1timer(ax25);
+		ax25_stop_t2timer(ax25);
+		ax25_stop_t3timer(ax25);
+		ax25_stop_idletimer(ax25);
+	}
 
 	ax25->state = AX25_STATE_0;
 
diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c
index 8a2b78f9c4b2..35fadb924849 100644
--- a/net/batman-adv/hard-interface.c
+++ b/net/batman-adv/hard-interface.c
@@ -149,22 +149,25 @@ static bool batadv_is_on_batman_iface(const struct net_device *net_dev)
 	struct net *net = dev_net(net_dev);
 	struct net_device *parent_dev;
 	struct net *parent_net;
+	int iflink;
 	bool ret;
 
 	/* check if this is a batman-adv mesh interface */
 	if (batadv_softif_is_valid(net_dev))
 		return true;
 
-	/* no more parents..stop recursion */
-	if (dev_get_iflink(net_dev) == 0 ||
-	    dev_get_iflink(net_dev) == net_dev->ifindex)
+	iflink = dev_get_iflink(net_dev);
+	if (iflink == 0)
 		return false;
 
 	parent_net = batadv_getlink_net(net_dev, net);
 
+	/* iflink to itself, most likely physical device */
+	if (net == parent_net && iflink == net_dev->ifindex)
+		return false;
+
 	/* recurse over the parent device */
-	parent_dev = __dev_get_by_index((struct net *)parent_net,
-					dev_get_iflink(net_dev));
+	parent_dev = __dev_get_by_index((struct net *)parent_net, iflink);
 	/* if we got a NULL parent_dev there is something broken.. */
 	if (!parent_dev) {
 		pr_err("Cannot find parent device\n");
@@ -214,14 +217,15 @@ static struct net_device *batadv_get_real_netdevice(struct net_device *netdev)
 	struct net_device *real_netdev = NULL;
 	struct net *real_net;
 	struct net *net;
-	int ifindex;
+	int iflink;
 
 	ASSERT_RTNL();
 
 	if (!netdev)
 		return NULL;
 
-	if (netdev->ifindex == dev_get_iflink(netdev)) {
+	iflink = dev_get_iflink(netdev);
+	if (iflink == 0) {
 		dev_hold(netdev);
 		return netdev;
 	}
@@ -231,9 +235,16 @@ static struct net_device *batadv_get_real_netdevice(struct net_device *netdev)
 		goto out;
 
 	net = dev_net(hard_iface->soft_iface);
-	ifindex = dev_get_iflink(netdev);
 	real_net = batadv_getlink_net(netdev, net);
-	real_netdev = dev_get_by_index(real_net, ifindex);
+
+	/* iflink to itself, most likely physical device */
+	if (net == real_net && netdev->ifindex == iflink) {
+		real_netdev = netdev;
+		dev_hold(real_netdev);
+		goto out;
+	}
+
+	real_netdev = dev_get_by_index(real_net, iflink);
 
 out:
 	batadv_hardif_put(hard_iface);
diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c
index 6e3419beca09..2853634a3979 100644
--- a/net/batman-adv/multicast.c
+++ b/net/batman-adv/multicast.c
@@ -134,7 +134,7 @@ static u8 batadv_mcast_mla_rtr_flags_softif_get_ipv6(struct net_device *dev)
 {
 	struct inet6_dev *in6_dev = __in6_dev_get(dev);
 
-	if (in6_dev && in6_dev->cnf.mc_forwarding)
+	if (in6_dev && atomic_read(&in6_dev->cnf.mc_forwarding))
 		return BATADV_NO_FLAGS;
 	else
 		return BATADV_MCAST_WANT_NO_RTR6;
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 2b5059a56cda..7a7e92be1652 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -541,7 +541,9 @@ static void le_conn_timeout(struct work_struct *work)
 	if (conn->role == HCI_ROLE_SLAVE) {
 		/* Disable LE Advertising */
 		le_disable_advertising(hdev);
+		hci_dev_lock(hdev);
 		hci_le_conn_failed(conn, HCI_ERROR_ADVERTISING_TIMEOUT);
+		hci_dev_unlock(hdev);
 		return;
 	}
 
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 53f1b08017aa..c67390367cc2 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -4083,6 +4083,7 @@ void hci_release_dev(struct hci_dev *hdev)
 	hci_dev_unlock(hdev);
 
 	ida_simple_remove(&hci_index_ida, hdev->id);
+	kfree_skb(hdev->sent_cmd);
 	kfree(hdev);
 }
 EXPORT_SYMBOL(hci_release_dev);
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 868a22df3285..e984a8b4b914 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -5153,8 +5153,9 @@ static void hci_disconn_phylink_complete_evt(struct hci_dev *hdev,
 	hci_dev_lock(hdev);
 
 	hcon = hci_conn_hash_lookup_handle(hdev, ev->phy_handle);
-	if (hcon) {
+	if (hcon && hcon->type == AMP_LINK) {
 		hcon->state = BT_CLOSED;
+		hci_disconn_cfm(hcon, ev->reason);
 		hci_conn_del(hcon);
 	}
 
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 77ba68209dbd..c57a45df7a26 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -1436,6 +1436,7 @@ static void l2cap_ecred_connect(struct l2cap_chan *chan)
 
 	l2cap_ecred_init(chan, 0);
 
+	memset(&data, 0, sizeof(data));
 	data.pdu.req.psm     = chan->psm;
 	data.pdu.req.mtu     = cpu_to_le16(chan->imtu);
 	data.pdu.req.mps     = cpu_to_le16(chan->mps);
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index b5f4ef35357c..655ee0e2de86 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -954,7 +954,7 @@ int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, const union bpf_attr *kat
 	if (!range_is_zero(user_ctx, offsetofend(typeof(*user_ctx), local_port), sizeof(*user_ctx)))
 		goto out;
 
-	if (user_ctx->local_port > U16_MAX || user_ctx->remote_port > U16_MAX) {
+	if (user_ctx->local_port > U16_MAX) {
 		ret = -ERANGE;
 		goto out;
 	}
@@ -962,7 +962,7 @@ int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, const union bpf_attr *kat
 	ctx.family = (u16)user_ctx->family;
 	ctx.protocol = (u16)user_ctx->protocol;
 	ctx.dport = (u16)user_ctx->local_port;
-	ctx.sport = (__force __be16)user_ctx->remote_port;
+	ctx.sport = user_ctx->remote_port;
 
 	switch (ctx.family) {
 	case AF_INET:
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index de2409889489..db4f2641d1cd 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -82,6 +82,9 @@ static void br_multicast_find_del_pg(struct net_bridge *br,
 				     struct net_bridge_port_group *pg);
 static void __br_multicast_stop(struct net_bridge_mcast *brmctx);
 
+static int br_mc_disabled_update(struct net_device *dev, bool value,
+				 struct netlink_ext_ack *extack);
+
 static struct net_bridge_port_group *
 br_sg_port_find(struct net_bridge *br,
 		struct net_bridge_port_group_sg_key *sg_p)
@@ -1156,6 +1159,7 @@ struct net_bridge_mdb_entry *br_multicast_new_group(struct net_bridge *br,
 		return mp;
 
 	if (atomic_read(&br->mdb_hash_tbl.nelems) >= br->hash_max) {
+		br_mc_disabled_update(br->dev, false, NULL);
 		br_opt_toggle(br, BROPT_MULTICAST_ENABLED, false);
 		return ERR_PTR(-E2BIG);
 	}
diff --git a/net/can/isotp.c b/net/can/isotp.c
index d2a430b6a13b..8c753dcefe7f 100644
--- a/net/can/isotp.c
+++ b/net/can/isotp.c
@@ -141,6 +141,7 @@ struct isotp_sock {
 	struct can_isotp_options opt;
 	struct can_isotp_fc_options rxfc, txfc;
 	struct can_isotp_ll_options ll;
+	u32 frame_txtime;
 	u32 force_tx_stmin;
 	u32 force_rx_stmin;
 	struct tpcon rx, tx;
@@ -360,7 +361,7 @@ static int isotp_rcv_fc(struct isotp_sock *so, struct canfd_frame *cf, int ae)
 
 		so->tx_gap = ktime_set(0, 0);
 		/* add transmission time for CAN frame N_As */
-		so->tx_gap = ktime_add_ns(so->tx_gap, so->opt.frame_txtime);
+		so->tx_gap = ktime_add_ns(so->tx_gap, so->frame_txtime);
 		/* add waiting time for consecutive frames N_Cs */
 		if (so->opt.flags & CAN_ISOTP_FORCE_TXSTMIN)
 			so->tx_gap = ktime_add_ns(so->tx_gap,
@@ -865,6 +866,7 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 	struct canfd_frame *cf;
 	int ae = (so->opt.flags & CAN_ISOTP_EXTEND_ADDR) ? 1 : 0;
 	int wait_tx_done = (so->opt.flags & CAN_ISOTP_WAIT_TX_DONE) ? 1 : 0;
+	s64 hrtimer_sec = 0;
 	int off;
 	int err;
 
@@ -963,7 +965,9 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 		isotp_create_fframe(cf, so, ae);
 
 		/* start timeout for FC */
-		hrtimer_start(&so->txtimer, ktime_set(1, 0), HRTIMER_MODE_REL_SOFT);
+		hrtimer_sec = 1;
+		hrtimer_start(&so->txtimer, ktime_set(hrtimer_sec, 0),
+			      HRTIMER_MODE_REL_SOFT);
 	}
 
 	/* send the first or only CAN frame */
@@ -976,6 +980,11 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 	if (err) {
 		pr_notice_once("can-isotp: %s: can_send_ret %pe\n",
 			       __func__, ERR_PTR(err));
+
+		/* no transmission -> no timeout monitoring */
+		if (hrtimer_sec)
+			hrtimer_cancel(&so->txtimer);
+
 		goto err_out_drop;
 	}
 
@@ -1005,26 +1014,29 @@ static int isotp_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
 {
 	struct sock *sk = sock->sk;
 	struct sk_buff *skb;
-	int err = 0;
-	int noblock;
+	struct isotp_sock *so = isotp_sk(sk);
+	int noblock = flags & MSG_DONTWAIT;
+	int ret = 0;
 
-	noblock = flags & MSG_DONTWAIT;
-	flags &= ~MSG_DONTWAIT;
+	if (flags & ~(MSG_DONTWAIT | MSG_TRUNC | MSG_PEEK))
+		return -EINVAL;
+
+	if (!so->bound)
+		return -EADDRNOTAVAIL;
 
-	skb = skb_recv_datagram(sk, flags, noblock, &err);
+	flags &= ~MSG_DONTWAIT;
+	skb = skb_recv_datagram(sk, flags, noblock, &ret);
 	if (!skb)
-		return err;
+		return ret;
 
 	if (size < skb->len)
 		msg->msg_flags |= MSG_TRUNC;
 	else
 		size = skb->len;
 
-	err = memcpy_to_msg(msg, skb->data, size);
-	if (err < 0) {
-		skb_free_datagram(sk, skb);
-		return err;
-	}
+	ret = memcpy_to_msg(msg, skb->data, size);
+	if (ret < 0)
+		goto out_err;
 
 	sock_recv_timestamp(msg, sk, skb);
 
@@ -1034,9 +1046,13 @@ static int isotp_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
 		memcpy(msg->msg_name, skb->cb, msg->msg_namelen);
 	}
 
+	/* set length of return value */
+	ret = (flags & MSG_TRUNC) ? skb->len : size;
+
+out_err:
 	skb_free_datagram(sk, skb);
 
-	return size;
+	return ret;
 }
 
 static int isotp_release(struct socket *sock)
@@ -1104,6 +1120,7 @@ static int isotp_bind(struct socket *sock, struct sockaddr *uaddr, int len)
 	struct net *net = sock_net(sk);
 	int ifindex;
 	struct net_device *dev;
+	canid_t tx_id, rx_id;
 	int err = 0;
 	int notify_enetdown = 0;
 	int do_rx_reg = 1;
@@ -1111,8 +1128,18 @@ static int isotp_bind(struct socket *sock, struct sockaddr *uaddr, int len)
 	if (len < ISOTP_MIN_NAMELEN)
 		return -EINVAL;
 
-	if (addr->can_addr.tp.tx_id & (CAN_ERR_FLAG | CAN_RTR_FLAG))
-		return -EADDRNOTAVAIL;
+	/* sanitize tx/rx CAN identifiers */
+	tx_id = addr->can_addr.tp.tx_id;
+	if (tx_id & CAN_EFF_FLAG)
+		tx_id &= (CAN_EFF_FLAG | CAN_EFF_MASK);
+	else
+		tx_id &= CAN_SFF_MASK;
+
+	rx_id = addr->can_addr.tp.rx_id;
+	if (rx_id & CAN_EFF_FLAG)
+		rx_id &= (CAN_EFF_FLAG | CAN_EFF_MASK);
+	else
+		rx_id &= CAN_SFF_MASK;
 
 	if (!addr->can_ifindex)
 		return -ENODEV;
@@ -1124,21 +1151,13 @@ static int isotp_bind(struct socket *sock, struct sockaddr *uaddr, int len)
 		do_rx_reg = 0;
 
 	/* do not validate rx address for functional addressing */
-	if (do_rx_reg) {
-		if (addr->can_addr.tp.rx_id == addr->can_addr.tp.tx_id) {
-			err = -EADDRNOTAVAIL;
-			goto out;
-		}
-
-		if (addr->can_addr.tp.rx_id & (CAN_ERR_FLAG | CAN_RTR_FLAG)) {
-			err = -EADDRNOTAVAIL;
-			goto out;
-		}
+	if (do_rx_reg && rx_id == tx_id) {
+		err = -EADDRNOTAVAIL;
+		goto out;
 	}
 
 	if (so->bound && addr->can_ifindex == so->ifindex &&
-	    addr->can_addr.tp.rx_id == so->rxid &&
-	    addr->can_addr.tp.tx_id == so->txid)
+	    rx_id == so->rxid && tx_id == so->txid)
 		goto out;
 
 	dev = dev_get_by_index(net, addr->can_ifindex);
@@ -1162,8 +1181,7 @@ static int isotp_bind(struct socket *sock, struct sockaddr *uaddr, int len)
 	ifindex = dev->ifindex;
 
 	if (do_rx_reg)
-		can_rx_register(net, dev, addr->can_addr.tp.rx_id,
-				SINGLE_MASK(addr->can_addr.tp.rx_id),
+		can_rx_register(net, dev, rx_id, SINGLE_MASK(rx_id),
 				isotp_rcv, sk, "isotp", sk);
 
 	dev_put(dev);
@@ -1183,8 +1201,8 @@ static int isotp_bind(struct socket *sock, struct sockaddr *uaddr, int len)
 
 	/* switch to new settings */
 	so->ifindex = ifindex;
-	so->rxid = addr->can_addr.tp.rx_id;
-	so->txid = addr->can_addr.tp.tx_id;
+	so->rxid = rx_id;
+	so->txid = tx_id;
 	so->bound = 1;
 
 out:
@@ -1238,6 +1256,14 @@ static int isotp_setsockopt_locked(struct socket *sock, int level, int optname,
 		/* no separate rx_ext_address is given => use ext_address */
 		if (!(so->opt.flags & CAN_ISOTP_RX_EXT_ADDR))
 			so->opt.rx_ext_address = so->opt.ext_address;
+
+		/* check for frame_txtime changes (0 => no changes) */
+		if (so->opt.frame_txtime) {
+			if (so->opt.frame_txtime == CAN_ISOTP_FRAME_TXTIME_ZERO)
+				so->frame_txtime = 0;
+			else
+				so->frame_txtime = so->opt.frame_txtime;
+		}
 		break;
 
 	case CAN_ISOTP_RECV_FC:
@@ -1439,6 +1465,7 @@ static int isotp_init(struct sock *sk)
 	so->opt.rxpad_content = CAN_ISOTP_DEFAULT_PAD_CONTENT;
 	so->opt.txpad_content = CAN_ISOTP_DEFAULT_PAD_CONTENT;
 	so->opt.frame_txtime = CAN_ISOTP_DEFAULT_FRAME_TXTIME;
+	so->frame_txtime = CAN_ISOTP_DEFAULT_FRAME_TXTIME;
 	so->rxfc.bs = CAN_ISOTP_DEFAULT_RECV_BS;
 	so->rxfc.stmin = CAN_ISOTP_DEFAULT_RECV_STMIN;
 	so->rxfc.wftmax = CAN_ISOTP_DEFAULT_RECV_WFTMAX;
diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c
index a271688780a2..307ee1174a6e 100644
--- a/net/can/j1939/transport.c
+++ b/net/can/j1939/transport.c
@@ -2006,7 +2006,7 @@ struct j1939_session *j1939_tp_send(struct j1939_priv *priv,
 		/* set the end-packet for broadcast */
 		session->pkt.last = session->pkt.total;
 
-	skcb->tskey = session->sk->sk_tskey++;
+	skcb->tskey = atomic_inc_return(&session->sk->sk_tskey) - 1;
 	session->tskey = skcb->tskey;
 
 	return session;
diff --git a/net/core/Makefile b/net/core/Makefile
index 35ced6201814..4268846f2f47 100644
--- a/net/core/Makefile
+++ b/net/core/Makefile
@@ -36,3 +36,4 @@ obj-$(CONFIG_FAILOVER) += failover.o
 obj-$(CONFIG_NET_SOCK_MSG) += skmsg.o
 obj-$(CONFIG_BPF_SYSCALL) += sock_map.o
 obj-$(CONFIG_BPF_SYSCALL) += bpf_sk_storage.o
+obj-$(CONFIG_OF)	+= of_net.o
diff --git a/net/core/dev.c b/net/core/dev.c
index 33dc2a3ff7d7..804aba2228c2 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -11378,8 +11378,7 @@ static int __net_init netdev_init(struct net *net)
 	BUILD_BUG_ON(GRO_HASH_BUCKETS >
 		     8 * sizeof_field(struct napi_struct, gro_bitmask));
 
-	if (net != &init_net)
-		INIT_LIST_HEAD(&net->dev_base_head);
+	INIT_LIST_HEAD(&net->dev_base_head);
 
 	net->dev_name_head = netdev_create_hash();
 	if (net->dev_name_head == NULL)
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index 49442cae6f69..1d99b731e5b2 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -280,13 +280,17 @@ static void trace_napi_poll_hit(void *ignore, struct napi_struct *napi,
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(new_stat, &hw_stats_list, list) {
+		struct net_device *dev;
+
 		/*
 		 * only add a note to our monitor buffer if:
 		 * 1) this is the dev we received on
 		 * 2) its after the last_rx delta
 		 * 3) our rx_dropped count has gone up
 		 */
-		if ((new_stat->dev == napi->dev)  &&
+		/* Paired with WRITE_ONCE() in dropmon_net_event() */
+		dev = READ_ONCE(new_stat->dev);
+		if ((dev == napi->dev)  &&
 		    (time_after(jiffies, new_stat->last_rx + dm_hw_check_delta)) &&
 		    (napi->dev->stats.rx_dropped != new_stat->last_drop_val)) {
 			trace_drop_common(NULL, NULL);
@@ -1572,7 +1576,10 @@ static int dropmon_net_event(struct notifier_block *ev_block,
 		mutex_lock(&net_dm_mutex);
 		list_for_each_entry_safe(new_stat, tmp, &hw_stats_list, list) {
 			if (new_stat->dev == dev) {
-				new_stat->dev = NULL;
+
+				/* Paired with READ_ONCE() in trace_napi_poll_hit() */
+				WRITE_ONCE(new_stat->dev, NULL);
+
 				if (trace_state == TRACE_OFF) {
 					list_del_rcu(&new_stat->list);
 					kfree_rcu(new_stat, rcu);
diff --git a/net/core/filter.c b/net/core/filter.c
index f207e4782bd0..cdd7e92db303 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2711,6 +2711,9 @@ BPF_CALL_4(bpf_msg_push_data, struct sk_msg *, msg, u32, start,
 	if (unlikely(flags))
 		return -EINVAL;
 
+	if (unlikely(len == 0))
+		return 0;
+
 	/* First find the starting scatterlist element */
 	i = msg->sg.start;
 	do {
@@ -6716,24 +6719,33 @@ BPF_CALL_5(bpf_tcp_check_syncookie, struct sock *, sk, void *, iph, u32, iph_len
 	if (!th->ack || th->rst || th->syn)
 		return -ENOENT;
 
+	if (unlikely(iph_len < sizeof(struct iphdr)))
+		return -EINVAL;
+
 	if (tcp_synq_no_recent_overflow(sk))
 		return -ENOENT;
 
 	cookie = ntohl(th->ack_seq) - 1;
 
-	switch (sk->sk_family) {
-	case AF_INET:
-		if (unlikely(iph_len < sizeof(struct iphdr)))
+	/* Both struct iphdr and struct ipv6hdr have the version field at the
+	 * same offset so we can cast to the shorter header (struct iphdr).
+	 */
+	switch (((struct iphdr *)iph)->version) {
+	case 4:
+		if (sk->sk_family == AF_INET6 && ipv6_only_sock(sk))
 			return -EINVAL;
 
 		ret = __cookie_v4_check((struct iphdr *)iph, th, cookie);
 		break;
 
 #if IS_BUILTIN(CONFIG_IPV6)
-	case AF_INET6:
+	case 6:
 		if (unlikely(iph_len < sizeof(struct ipv6hdr)))
 			return -EINVAL;
 
+		if (sk->sk_family != AF_INET6)
+			return -EINVAL;
+
 		ret = __cookie_v6_check((struct ipv6hdr *)iph, th, cookie);
 		break;
 #endif /* CONFIG_IPV6 */
@@ -7963,6 +7975,7 @@ bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type,
 			      struct bpf_insn_access_aux *info)
 {
 	const int size_default = sizeof(__u32);
+	int field_size;
 
 	if (off < 0 || off >= sizeof(struct bpf_sock))
 		return false;
@@ -7974,7 +7987,6 @@ bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type,
 	case offsetof(struct bpf_sock, family):
 	case offsetof(struct bpf_sock, type):
 	case offsetof(struct bpf_sock, protocol):
-	case offsetof(struct bpf_sock, dst_port):
 	case offsetof(struct bpf_sock, src_port):
 	case offsetof(struct bpf_sock, rx_queue_mapping):
 	case bpf_ctx_range(struct bpf_sock, src_ip4):
@@ -7983,6 +7995,14 @@ bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type,
 	case bpf_ctx_range_till(struct bpf_sock, dst_ip6[0], dst_ip6[3]):
 		bpf_ctx_record_field_size(info, size_default);
 		return bpf_ctx_narrow_access_ok(off, size, size_default);
+	case bpf_ctx_range(struct bpf_sock, dst_port):
+		field_size = size == size_default ?
+			size_default : sizeof_field(struct bpf_sock, dst_port);
+		bpf_ctx_record_field_size(info, field_size);
+		return bpf_ctx_narrow_access_ok(off, size, field_size);
+	case offsetofend(struct bpf_sock, dst_port) ...
+	     offsetof(struct bpf_sock, dst_ip4) - 1:
+		return false;
 	}
 
 	return size == size_default;
@@ -10520,7 +10540,8 @@ static bool sk_lookup_is_valid_access(int off, int size,
 	case bpf_ctx_range(struct bpf_sk_lookup, local_ip4):
 	case bpf_ctx_range_till(struct bpf_sk_lookup, remote_ip6[0], remote_ip6[3]):
 	case bpf_ctx_range_till(struct bpf_sk_lookup, local_ip6[0], local_ip6[3]):
-	case bpf_ctx_range(struct bpf_sk_lookup, remote_port):
+	case offsetof(struct bpf_sk_lookup, remote_port) ...
+	     offsetof(struct bpf_sk_lookup, local_ip4) - 1:
 	case bpf_ctx_range(struct bpf_sk_lookup, local_port):
 		bpf_ctx_record_field_size(info, sizeof(__u32));
 		return bpf_ctx_narrow_access_ok(off, size, sizeof(__u32));
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index edffdaa875f1..bc50bd331d5b 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -1181,6 +1181,7 @@ proto_again:
 					 VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT;
 			}
 			key_vlan->vlan_tpid = saved_vlan_tpid;
+			key_vlan->vlan_eth_type = proto;
 		}
 
 		fdret = FLOW_DISSECT_RET_PROTO_AGAIN;
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index a4ae65263384..9e5657f63245 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -213,7 +213,7 @@ static ssize_t speed_show(struct device *dev,
 	if (!rtnl_trylock())
 		return restart_syscall();
 
-	if (netif_running(netdev)) {
+	if (netif_running(netdev) && netif_device_present(netdev)) {
 		struct ethtool_link_ksettings cmd;
 
 		if (!__ethtool_get_link_ksettings(netdev, &cmd))
@@ -1927,7 +1927,7 @@ static struct class net_class __ro_after_init = {
 	.get_ownership = net_get_ownership,
 };
 
-#ifdef CONFIG_OF_NET
+#ifdef CONFIG_OF
 static int of_dev_node_match(struct device *dev, const void *data)
 {
 	for (; dev; dev = dev->parent) {
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 9702d2b0d920..9745cb6fdf51 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -44,13 +44,7 @@ EXPORT_SYMBOL_GPL(net_rwsem);
 static struct key_tag init_net_key_domain = { .usage = REFCOUNT_INIT(1) };
 #endif
 
-struct net init_net = {
-	.ns.count	= REFCOUNT_INIT(1),
-	.dev_base_head	= LIST_HEAD_INIT(init_net.dev_base_head),
-#ifdef CONFIG_KEYS
-	.key_domain	= &init_net_key_domain,
-#endif
-};
+struct net init_net;
 EXPORT_SYMBOL(init_net);
 
 static bool init_net_initialized;
@@ -1081,7 +1075,7 @@ out:
 	rtnl_set_sk_err(net, RTNLGRP_NSID, err);
 }
 
-static int __init net_ns_init(void)
+void __init net_ns_init(void)
 {
 	struct net_generic *ng;
 
@@ -1102,6 +1096,9 @@ static int __init net_ns_init(void)
 
 	rcu_assign_pointer(init_net.gen, ng);
 
+#ifdef CONFIG_KEYS
+	init_net.key_domain = &init_net_key_domain;
+#endif
 	down_write(&pernet_ops_rwsem);
 	if (setup_net(&init_net, &init_user_ns))
 		panic("Could not setup the initial network namespace");
@@ -1116,12 +1113,8 @@ static int __init net_ns_init(void)
 		      RTNL_FLAG_DOIT_UNLOCKED);
 	rtnl_register(PF_UNSPEC, RTM_GETNSID, rtnl_net_getid, rtnl_net_dumpid,
 		      RTNL_FLAG_DOIT_UNLOCKED);
-
-	return 0;
 }
 
-pure_initcall(net_ns_init);
-
 static void free_exit_list(struct pernet_operations *ops, struct list_head *net_exit_list)
 {
 	ops_pre_exit_list(ops, net_exit_list);
diff --git a/net/core/of_net.c b/net/core/of_net.c
new file mode 100644
index 000000000000..dbac3a172a11
--- /dev/null
+++ b/net/core/of_net.c
@@ -0,0 +1,145 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * OF helpers for network devices.
+ *
+ * Initially copied out of arch/powerpc/kernel/prom_parse.c
+ */
+#include <linux/etherdevice.h>
+#include <linux/kernel.h>
+#include <linux/of_net.h>
+#include <linux/of_platform.h>
+#include <linux/phy.h>
+#include <linux/export.h>
+#include <linux/device.h>
+#include <linux/nvmem-consumer.h>
+
+/**
+ * of_get_phy_mode - Get phy mode for given device_node
+ * @np:	Pointer to the given device_node
+ * @interface: Pointer to the result
+ *
+ * The function gets phy interface string from property 'phy-mode' or
+ * 'phy-connection-type'. The index in phy_modes table is set in
+ * interface and 0 returned. In case of error interface is set to
+ * PHY_INTERFACE_MODE_NA and an errno is returned, e.g. -ENODEV.
+ */
+int of_get_phy_mode(struct device_node *np, phy_interface_t *interface)
+{
+	const char *pm;
+	int err, i;
+
+	*interface = PHY_INTERFACE_MODE_NA;
+
+	err = of_property_read_string(np, "phy-mode", &pm);
+	if (err < 0)
+		err = of_property_read_string(np, "phy-connection-type", &pm);
+	if (err < 0)
+		return err;
+
+	for (i = 0; i < PHY_INTERFACE_MODE_MAX; i++)
+		if (!strcasecmp(pm, phy_modes(i))) {
+			*interface = i;
+			return 0;
+		}
+
+	return -ENODEV;
+}
+EXPORT_SYMBOL_GPL(of_get_phy_mode);
+
+static int of_get_mac_addr(struct device_node *np, const char *name, u8 *addr)
+{
+	struct property *pp = of_find_property(np, name, NULL);
+
+	if (pp && pp->length == ETH_ALEN && is_valid_ether_addr(pp->value)) {
+		memcpy(addr, pp->value, ETH_ALEN);
+		return 0;
+	}
+	return -ENODEV;
+}
+
+static int of_get_mac_addr_nvmem(struct device_node *np, u8 *addr)
+{
+	struct platform_device *pdev = of_find_device_by_node(np);
+	struct nvmem_cell *cell;
+	const void *mac;
+	size_t len;
+	int ret;
+
+	/* Try lookup by device first, there might be a nvmem_cell_lookup
+	 * associated with a given device.
+	 */
+	if (pdev) {
+		ret = nvmem_get_mac_address(&pdev->dev, addr);
+		put_device(&pdev->dev);
+		return ret;
+	}
+
+	cell = of_nvmem_cell_get(np, "mac-address");
+	if (IS_ERR(cell))
+		return PTR_ERR(cell);
+
+	mac = nvmem_cell_read(cell, &len);
+	nvmem_cell_put(cell);
+
+	if (IS_ERR(mac))
+		return PTR_ERR(mac);
+
+	if (len != ETH_ALEN || !is_valid_ether_addr(mac)) {
+		kfree(mac);
+		return -EINVAL;
+	}
+
+	memcpy(addr, mac, ETH_ALEN);
+	kfree(mac);
+
+	return 0;
+}
+
+/**
+ * of_get_mac_address()
+ * @np:		Caller's Device Node
+ * @addr:	Pointer to a six-byte array for the result
+ *
+ * Search the device tree for the best MAC address to use.  'mac-address' is
+ * checked first, because that is supposed to contain to "most recent" MAC
+ * address. If that isn't set, then 'local-mac-address' is checked next,
+ * because that is the default address. If that isn't set, then the obsolete
+ * 'address' is checked, just in case we're using an old device tree. If any
+ * of the above isn't set, then try to get MAC address from nvmem cell named
+ * 'mac-address'.
+ *
+ * Note that the 'address' property is supposed to contain a virtual address of
+ * the register set, but some DTS files have redefined that property to be the
+ * MAC address.
+ *
+ * All-zero MAC addresses are rejected, because those could be properties that
+ * exist in the device tree, but were not set by U-Boot.  For example, the
+ * DTS could define 'mac-address' and 'local-mac-address', with zero MAC
+ * addresses.  Some older U-Boots only initialized 'local-mac-address'.  In
+ * this case, the real MAC is in 'local-mac-address', and 'mac-address' exists
+ * but is all zeros.
+ *
+ * Return: 0 on success and errno in case of error.
+*/
+int of_get_mac_address(struct device_node *np, u8 *addr)
+{
+	int ret;
+
+	if (!np)
+		return -ENODEV;
+
+	ret = of_get_mac_addr(np, "mac-address", addr);
+	if (!ret)
+		return 0;
+
+	ret = of_get_mac_addr(np, "local-mac-address", addr);
+	if (!ret)
+		return 0;
+
+	ret = of_get_mac_addr(np, "address", addr);
+	if (!ret)
+		return 0;
+
+	return of_get_mac_addr_nvmem(np, addr);
+}
+EXPORT_SYMBOL(of_get_mac_address);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 198cc8b74dc3..9c0e8ccf9bc5 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1698,6 +1698,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb,
 {
 	struct ifinfomsg *ifm;
 	struct nlmsghdr *nlh;
+	struct Qdisc *qdisc;
 
 	ASSERT_RTNL();
 	nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ifm), flags);
@@ -1715,6 +1716,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb,
 	if (tgt_netnsid >= 0 && nla_put_s32(skb, IFLA_TARGET_NETNSID, tgt_netnsid))
 		goto nla_put_failure;
 
+	qdisc = rtnl_dereference(dev->qdisc);
 	if (nla_put_string(skb, IFLA_IFNAME, dev->name) ||
 	    nla_put_u32(skb, IFLA_TXQLEN, dev->tx_queue_len) ||
 	    nla_put_u8(skb, IFLA_OPERSTATE,
@@ -1733,8 +1735,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb,
 #endif
 	    put_master_ifindex(skb, dev) ||
 	    nla_put_u8(skb, IFLA_CARRIER, netif_carrier_ok(dev)) ||
-	    (dev->qdisc &&
-	     nla_put_string(skb, IFLA_QDISC, dev->qdisc->ops->id)) ||
+	    (qdisc &&
+	     nla_put_string(skb, IFLA_QDISC, qdisc->ops->id)) ||
 	    nla_put_ifalias(skb, dev) ||
 	    nla_put_u32(skb, IFLA_CARRIER_CHANGES,
 			atomic_read(&dev->carrier_up_count) +
@@ -3629,13 +3631,24 @@ static int rtnl_alt_ifname(int cmd, struct net_device *dev, struct nlattr *attr,
 			   bool *changed, struct netlink_ext_ack *extack)
 {
 	char *alt_ifname;
+	size_t size;
 	int err;
 
 	err = nla_validate(attr, attr->nla_len, IFLA_MAX, ifla_policy, extack);
 	if (err)
 		return err;
 
-	alt_ifname = nla_strdup(attr, GFP_KERNEL);
+	if (cmd == RTM_NEWLINKPROP) {
+		size = rtnl_prop_list_size(dev);
+		size += nla_total_size(ALTIFNAMSIZ);
+		if (size >= U16_MAX) {
+			NL_SET_ERR_MSG(extack,
+				       "effective property list too long");
+			return -EINVAL;
+		}
+	}
+
+	alt_ifname = nla_strdup(attr, GFP_KERNEL_ACCOUNT);
 	if (!alt_ifname)
 		return -ENOMEM;
 
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index f7e003571a35..0db93122adeb 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -70,6 +70,7 @@
 #include <net/xfrm.h>
 #include <net/mpls.h>
 #include <net/mptcp.h>
+#include <net/mctp.h>
 #include <net/page_pool.h>
 
 #include <linux/uaccess.h>
@@ -203,7 +204,7 @@ static void __build_skb_around(struct sk_buff *skb, void *data,
 	skb->head = data;
 	skb->data = data;
 	skb_reset_tail_pointer(skb);
-	skb->end = skb->tail + size;
+	skb_set_end_offset(skb, size);
 	skb->mac_header = (typeof(skb->mac_header))~0U;
 	skb->transport_header = (typeof(skb->transport_header))~0U;
 
@@ -1738,11 +1739,10 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail,
 	skb->head     = data;
 	skb->head_frag = 0;
 	skb->data    += off;
+
+	skb_set_end_offset(skb, size);
 #ifdef NET_SKBUFF_DATA_USES_OFFSET
-	skb->end      = size;
 	off           = nhead;
-#else
-	skb->end      = skb->head + size;
 #endif
 	skb->tail	      += off;
 	skb_headers_offset_update(skb, nhead);
@@ -1790,6 +1790,38 @@ struct sk_buff *skb_realloc_headroom(struct sk_buff *skb, unsigned int headroom)
 }
 EXPORT_SYMBOL(skb_realloc_headroom);
 
+int __skb_unclone_keeptruesize(struct sk_buff *skb, gfp_t pri)
+{
+	unsigned int saved_end_offset, saved_truesize;
+	struct skb_shared_info *shinfo;
+	int res;
+
+	saved_end_offset = skb_end_offset(skb);
+	saved_truesize = skb->truesize;
+
+	res = pskb_expand_head(skb, 0, 0, pri);
+	if (res)
+		return res;
+
+	skb->truesize = saved_truesize;
+
+	if (likely(skb_end_offset(skb) == saved_end_offset))
+		return 0;
+
+	shinfo = skb_shinfo(skb);
+
+	/* We are about to change back skb->end,
+	 * we need to move skb_shinfo() to its new location.
+	 */
+	memmove(skb->head + saved_end_offset,
+		shinfo,
+		offsetof(struct skb_shared_info, frags[shinfo->nr_frags]));
+
+	skb_set_end_offset(skb, saved_end_offset);
+
+	return 0;
+}
+
 /**
  *	skb_expand_head - reallocate header of &sk_buff
  *	@skb: buffer to reallocate
@@ -2254,7 +2286,7 @@ void *__pskb_pull_tail(struct sk_buff *skb, int delta)
 		/* Free pulled out fragments. */
 		while ((list = skb_shinfo(skb)->frag_list) != insp) {
 			skb_shinfo(skb)->frag_list = list->next;
-			kfree_skb(list);
+			consume_skb(list);
 		}
 		/* And insert new clone at head. */
 		if (clone) {
@@ -3853,6 +3885,7 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb,
 		list_skb = list_skb->next;
 
 		err = 0;
+		delta_truesize += nskb->truesize;
 		if (skb_shared(nskb)) {
 			tmp = skb_clone(nskb, GFP_ATOMIC);
 			if (tmp) {
@@ -3877,7 +3910,6 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb,
 		tail = nskb;
 
 		delta_len += nskb->len;
-		delta_truesize += nskb->truesize;
 
 		skb_push(nskb, -skb_network_offset(nskb) + offset);
 
@@ -4429,6 +4461,9 @@ static const u8 skb_ext_type_len[] = {
 #if IS_ENABLED(CONFIG_MPTCP)
 	[SKB_EXT_MPTCP] = SKB_EXT_CHUNKSIZEOF(struct mptcp_ext),
 #endif
+#if IS_ENABLED(CONFIG_MCTP_FLOWS)
+	[SKB_EXT_MCTP] = SKB_EXT_CHUNKSIZEOF(struct mctp_flow),
+#endif
 };
 
 static __always_inline unsigned int skb_ext_total_length(void)
@@ -4446,6 +4481,9 @@ static __always_inline unsigned int skb_ext_total_length(void)
 #if IS_ENABLED(CONFIG_MPTCP)
 		skb_ext_type_len[SKB_EXT_MPTCP] +
 #endif
+#if IS_ENABLED(CONFIG_MCTP_FLOWS)
+		skb_ext_type_len[SKB_EXT_MCTP] +
+#endif
 		0;
 }
 
@@ -4844,7 +4882,7 @@ static void __skb_complete_tx_timestamp(struct sk_buff *skb,
 		serr->ee.ee_data = skb_shinfo(skb)->tskey;
 		if (sk->sk_protocol == IPPROTO_TCP &&
 		    sk->sk_type == SOCK_STREAM)
-			serr->ee.ee_data -= sk->sk_tskey;
+			serr->ee.ee_data -= atomic_read(&sk->sk_tskey);
 	}
 
 	err = sock_queue_err_skb(sk, skb);
@@ -5359,11 +5397,18 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
 	if (skb_cloned(to))
 		return false;
 
-	/* The page pool signature of struct page will eventually figure out
-	 * which pages can be recycled or not but for now let's prohibit slab
-	 * allocated and page_pool allocated SKBs from being coalesced.
+	/* In general, avoid mixing slab allocated and page_pool allocated
+	 * pages within the same SKB. However when @to is not pp_recycle and
+	 * @from is cloned, we can transition frag pages from page_pool to
+	 * reference counted.
+	 *
+	 * On the other hand, don't allow coalescing two pp_recycle SKBs if
+	 * @from is cloned, in case the SKB is using page_pool fragment
+	 * references (PP_FLAG_PAGE_FRAG). Since we only take full page
+	 * references for cloned SKBs at the moment that would result in
+	 * inconsistent reference counts.
 	 */
-	if (to->pp_recycle != from->pp_recycle)
+	if (to->pp_recycle != (from->pp_recycle && !skb_cloned(from)))
 		return false;
 
 	if (len <= skb_tailroom(to)) {
@@ -6159,11 +6204,7 @@ static int pskb_carve_inside_header(struct sk_buff *skb, const u32 off,
 	skb->head = data;
 	skb->data = data;
 	skb->head_frag = 0;
-#ifdef NET_SKBUFF_DATA_USES_OFFSET
-	skb->end = size;
-#else
-	skb->end = skb->head + size;
-#endif
+	skb_set_end_offset(skb, size);
 	skb_set_tail_pointer(skb, skb_headlen(skb));
 	skb_headers_offset_update(skb, 0);
 	skb->cloned = 0;
@@ -6220,7 +6261,7 @@ static int pskb_carve_frag_list(struct sk_buff *skb,
 	/* Free pulled out fragments. */
 	while ((list = shinfo->frag_list) != insp) {
 		shinfo->frag_list = list->next;
-		kfree_skb(list);
+		consume_skb(list);
 	}
 	/* And insert new clone at head. */
 	if (clone) {
@@ -6301,11 +6342,7 @@ static int pskb_carve_inside_nonlinear(struct sk_buff *skb, const u32 off,
 	skb->head = data;
 	skb->head_frag = 0;
 	skb->data = data;
-#ifdef NET_SKBUFF_DATA_USES_OFFSET
-	skb->end = size;
-#else
-	skb->end = skb->head + size;
-#endif
+	skb_set_end_offset(skb, size);
 	skb_reset_tail_pointer(skb);
 	skb_headers_offset_update(skb, 0);
 	skb->cloned   = 0;
@@ -6518,6 +6555,14 @@ static void skb_ext_put_sp(struct sec_path *sp)
 }
 #endif
 
+#ifdef CONFIG_MCTP_FLOWS
+static void skb_ext_put_mctp(struct mctp_flow *flow)
+{
+	if (flow->key)
+		mctp_key_unref(flow->key);
+}
+#endif
+
 void __skb_ext_del(struct sk_buff *skb, enum skb_ext_id id)
 {
 	struct skb_ext *ext = skb->extensions;
@@ -6553,6 +6598,10 @@ free_now:
 	if (__skb_ext_exist(ext, SKB_EXT_SEC_PATH))
 		skb_ext_put_sp(skb_ext_get_ptr(ext, SKB_EXT_SEC_PATH));
 #endif
+#ifdef CONFIG_MCTP_FLOWS
+	if (__skb_ext_exist(ext, SKB_EXT_MCTP))
+		skb_ext_put_mctp(skb_ext_get_ptr(ext, SKB_EXT_MCTP));
+#endif
 
 	kmem_cache_free(skbuff_ext_cache, ext);
 }
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 8eb671c827f9..cc381165ea08 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -27,6 +27,7 @@ int sk_msg_alloc(struct sock *sk, struct sk_msg *msg, int len,
 		 int elem_first_coalesce)
 {
 	struct page_frag *pfrag = sk_page_frag(sk);
+	u32 osize = msg->sg.size;
 	int ret = 0;
 
 	len -= msg->sg.size;
@@ -35,13 +36,17 @@ int sk_msg_alloc(struct sock *sk, struct sk_msg *msg, int len,
 		u32 orig_offset;
 		int use, i;
 
-		if (!sk_page_frag_refill(sk, pfrag))
-			return -ENOMEM;
+		if (!sk_page_frag_refill(sk, pfrag)) {
+			ret = -ENOMEM;
+			goto msg_trim;
+		}
 
 		orig_offset = pfrag->offset;
 		use = min_t(int, len, pfrag->size - orig_offset);
-		if (!sk_wmem_schedule(sk, use))
-			return -ENOMEM;
+		if (!sk_wmem_schedule(sk, use)) {
+			ret = -ENOMEM;
+			goto msg_trim;
+		}
 
 		i = msg->sg.end;
 		sk_msg_iter_var_prev(i);
@@ -71,6 +76,10 @@ int sk_msg_alloc(struct sock *sk, struct sk_msg *msg, int len,
 	}
 
 	return ret;
+
+msg_trim:
+	sk_msg_trim(sk, msg, osize);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(sk_msg_alloc);
 
@@ -1153,7 +1162,7 @@ static int sk_psock_verdict_recv(read_descriptor_t *desc, struct sk_buff *skb,
 	struct sk_psock *psock;
 	struct bpf_prog *prog;
 	int ret = __SK_DROP;
-	int len = skb->len;
+	int len = orig_len;
 
 	/* clone here so sk_eat_skb() in tcp_read_sock does not drop our data */
 	skb = skb_clone(skb, GFP_ATOMIC);
diff --git a/net/core/sock.c b/net/core/sock.c
index 6ea317f84edd..deaed1b20682 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -866,9 +866,9 @@ int sock_set_timestamping(struct sock *sk, int optname,
 			if ((1 << sk->sk_state) &
 			    (TCPF_CLOSE | TCPF_LISTEN))
 				return -EINVAL;
-			sk->sk_tskey = tcp_sk(sk)->snd_una;
+			atomic_set(&sk->sk_tskey, tcp_sk(sk)->snd_una);
 		} else {
-			sk->sk_tskey = 0;
+			atomic_set(&sk->sk_tskey, 0);
 		}
 	}
 
diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
index b441ab330fd3..dc4fb699b56c 100644
--- a/net/dcb/dcbnl.c
+++ b/net/dcb/dcbnl.c
@@ -2073,8 +2073,52 @@ u8 dcb_ieee_getapp_default_prio_mask(const struct net_device *dev)
 }
 EXPORT_SYMBOL(dcb_ieee_getapp_default_prio_mask);
 
+static void dcbnl_flush_dev(struct net_device *dev)
+{
+	struct dcb_app_type *itr, *tmp;
+
+	spin_lock_bh(&dcb_lock);
+
+	list_for_each_entry_safe(itr, tmp, &dcb_app_list, list) {
+		if (itr->ifindex == dev->ifindex) {
+			list_del(&itr->list);
+			kfree(itr);
+		}
+	}
+
+	spin_unlock_bh(&dcb_lock);
+}
+
+static int dcbnl_netdevice_event(struct notifier_block *nb,
+				 unsigned long event, void *ptr)
+{
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+
+	switch (event) {
+	case NETDEV_UNREGISTER:
+		if (!dev->dcbnl_ops)
+			return NOTIFY_DONE;
+
+		dcbnl_flush_dev(dev);
+
+		return NOTIFY_OK;
+	default:
+		return NOTIFY_DONE;
+	}
+}
+
+static struct notifier_block dcbnl_nb __read_mostly = {
+	.notifier_call  = dcbnl_netdevice_event,
+};
+
 static int __init dcbnl_init(void)
 {
+	int err;
+
+	err = register_netdevice_notifier(&dcbnl_nb);
+	if (err)
+		return err;
+
 	rtnl_register(PF_UNSPEC, RTM_GETDCB, dcb_doit, NULL, 0);
 	rtnl_register(PF_UNSPEC, RTM_SETDCB, dcb_doit, NULL, 0);
 
diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index e9911b18bdbf..64a56db3de58 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -1341,6 +1341,7 @@ static int dsa_port_parse_of(struct dsa_port *dp, struct device_node *dn)
 		const char *user_protocol;
 
 		master = of_find_net_device_by_node(ethernet);
+		of_node_put(ethernet);
 		if (!master)
 			return -EPROBE_DEFER;
 
@@ -1630,6 +1631,10 @@ void dsa_switch_shutdown(struct dsa_switch *ds)
 	struct dsa_port *dp;
 
 	mutex_lock(&dsa2_mutex);
+
+	if (!ds->setup)
+		goto out;
+
 	rtnl_lock();
 
 	list_for_each_entry(dp, &ds->dst->ports, list) {
@@ -1664,6 +1669,7 @@ void dsa_switch_shutdown(struct dsa_switch *ds)
 	unregister_netdevice_many(&unregister_list);
 
 	rtnl_unlock();
+out:
 	mutex_unlock(&dsa2_mutex);
 }
 EXPORT_SYMBOL_GPL(dsa_switch_shutdown);
diff --git a/net/dsa/tag_hellcreek.c b/net/dsa/tag_hellcreek.c
index f64b805303cd..eb204ad36eee 100644
--- a/net/dsa/tag_hellcreek.c
+++ b/net/dsa/tag_hellcreek.c
@@ -21,6 +21,14 @@ static struct sk_buff *hellcreek_xmit(struct sk_buff *skb,
 	struct dsa_port *dp = dsa_slave_to_port(dev);
 	u8 *tag;
 
+	/* Calculate checksums (if required) before adding the trailer tag to
+	 * avoid including it in calculations. That would lead to wrong
+	 * checksums after the switch strips the tag.
+	 */
+	if (skb->ip_summed == CHECKSUM_PARTIAL &&
+	    skb_checksum_help(skb))
+		return NULL;
+
 	/* Tag encoding */
 	tag  = skb_put(skb, HELLCREEK_TAG_LEN);
 	*tag = BIT(dp->index);
diff --git a/net/dsa/tag_lan9303.c b/net/dsa/tag_lan9303.c
index cb548188f813..98d7d7120bab 100644
--- a/net/dsa/tag_lan9303.c
+++ b/net/dsa/tag_lan9303.c
@@ -77,7 +77,6 @@ static struct sk_buff *lan9303_xmit(struct sk_buff *skb, struct net_device *dev)
 
 static struct sk_buff *lan9303_rcv(struct sk_buff *skb, struct net_device *dev)
 {
-	__be16 *lan9303_tag;
 	u16 lan9303_tag1;
 	unsigned int source_port;
 
@@ -87,14 +86,15 @@ static struct sk_buff *lan9303_rcv(struct sk_buff *skb, struct net_device *dev)
 		return NULL;
 	}
 
-	lan9303_tag = dsa_etype_header_pos_rx(skb);
-
-	if (lan9303_tag[0] != htons(ETH_P_8021Q)) {
-		dev_warn_ratelimited(&dev->dev, "Dropping packet due to invalid VLAN marker\n");
-		return NULL;
+	if (skb_vlan_tag_present(skb)) {
+		lan9303_tag1 = skb_vlan_tag_get(skb);
+		__vlan_hwaccel_clear_tag(skb);
+	} else {
+		skb_push_rcsum(skb, ETH_HLEN);
+		__skb_vlan_pop(skb, &lan9303_tag1);
+		skb_pull_rcsum(skb, ETH_HLEN);
 	}
 
-	lan9303_tag1 = ntohs(lan9303_tag[1]);
 	source_port = lan9303_tag1 & 0x3;
 
 	skb->dev = dsa_master_find_slave(dev, 0, source_port);
@@ -103,13 +103,6 @@ static struct sk_buff *lan9303_rcv(struct sk_buff *skb, struct net_device *dev)
 		return NULL;
 	}
 
-	/* remove the special VLAN tag between the MAC addresses
-	 * and the current ethertype field.
-	 */
-	skb_pull_rcsum(skb, 2 + 2);
-
-	dsa_strip_etype_header(skb, LAN9303_TAG_LEN);
-
 	if (!(lan9303_tag1 & LAN9303_TAG_RX_TRAPPED_TO_CPU))
 		dsa_default_offload_fwd_mark(skb);
 
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index dcea653a5204..77534b44b8c7 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1380,8 +1380,11 @@ struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 	}
 
 	ops = rcu_dereference(inet_offloads[proto]);
-	if (likely(ops && ops->callbacks.gso_segment))
+	if (likely(ops && ops->callbacks.gso_segment)) {
 		segs = ops->callbacks.gso_segment(skb, features);
+		if (!segs)
+			skb->network_header = skb_mac_header(skb) + nhoff - skb->head;
+	}
 
 	if (IS_ERR_OR_NULL(segs))
 		goto out;
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 922dd73e5740..83a47998c4b1 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -1116,13 +1116,18 @@ static int arp_req_get(struct arpreq *r, struct net_device *dev)
 	return err;
 }
 
-static int arp_invalidate(struct net_device *dev, __be32 ip)
+int arp_invalidate(struct net_device *dev, __be32 ip, bool force)
 {
 	struct neighbour *neigh = neigh_lookup(&arp_tbl, &ip, dev);
 	int err = -ENXIO;
 	struct neigh_table *tbl = &arp_tbl;
 
 	if (neigh) {
+		if ((neigh->nud_state & NUD_VALID) && !force) {
+			neigh_release(neigh);
+			return 0;
+		}
+
 		if (neigh->nud_state & ~NUD_NOARP)
 			err = neigh_update(neigh, NULL, NUD_FAILED,
 					   NEIGH_UPDATE_F_OVERRIDE|
@@ -1169,7 +1174,7 @@ static int arp_req_delete(struct net *net, struct arpreq *r,
 		if (!dev)
 			return -EINVAL;
 	}
-	return arp_invalidate(dev, ip);
+	return arp_invalidate(dev, ip, true);
 }
 
 /*
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 851f542928a3..d747166bb291 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -455,6 +455,10 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *
 			return err;
 	}
 
+	if (ALIGN(tailen, L1_CACHE_BYTES) > PAGE_SIZE ||
+	    ALIGN(skb->data_len, L1_CACHE_BYTES) > PAGE_SIZE)
+		goto cow;
+
 	if (!skb_cloned(skb)) {
 		if (tailen <= skb_tailroom(skb)) {
 			nfrags = 1;
@@ -671,7 +675,7 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 		struct xfrm_dst *dst = (struct xfrm_dst *)skb_dst(skb);
 		u32 padto;
 
-		padto = min(x->tfcpad, __xfrm_state_mtu(x, dst->child_mtu_cached));
+		padto = min(x->tfcpad, xfrm_state_mtu(x, dst->child_mtu_cached));
 		if (skb->len < padto)
 			esp.tfclen = padto - skb->len;
 	}
diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c
index 8e4e9aa12130..dad5d29a6a8d 100644
--- a/net/ipv4/esp4_offload.c
+++ b/net/ipv4/esp4_offload.c
@@ -159,6 +159,9 @@ static struct sk_buff *xfrm4_beet_gso_segment(struct xfrm_state *x,
 			skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV4;
 	}
 
+	if (proto == IPPROTO_IPV6)
+		skb_shinfo(skb)->gso_type |= SKB_GSO_IPXIP4;
+
 	__skb_pull(skb, skb_transport_offset(skb));
 	ops = rcu_dereference(inet_offloads[proto]);
 	if (likely(ops && ops->callbacks.gso_segment))
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 4d61ddd8a0ec..1eb7795edb9d 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1112,9 +1112,11 @@ void fib_add_ifaddr(struct in_ifaddr *ifa)
 		return;
 
 	/* Add broadcast address, if it is explicitly assigned. */
-	if (ifa->ifa_broadcast && ifa->ifa_broadcast != htonl(0xFFFFFFFF))
+	if (ifa->ifa_broadcast && ifa->ifa_broadcast != htonl(0xFFFFFFFF)) {
 		fib_magic(RTM_NEWROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32,
 			  prim, 0);
+		arp_invalidate(dev, ifa->ifa_broadcast, false);
+	}
 
 	if (!ipv4_is_zeronet(prefix) && !(ifa->ifa_flags & IFA_F_SECONDARY) &&
 	    (prefix != addr || ifa->ifa_prefixlen < 32)) {
@@ -1128,6 +1130,7 @@ void fib_add_ifaddr(struct in_ifaddr *ifa)
 		if (ifa->ifa_prefixlen < 31) {
 			fib_magic(RTM_NEWROUTE, RTN_BROADCAST, prefix | ~mask,
 				  32, prim, 0);
+			arp_invalidate(dev, prefix | ~mask, false);
 		}
 	}
 }
diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h
index e184bcb19943..78e40ea42e58 100644
--- a/net/ipv4/fib_lookup.h
+++ b/net/ipv4/fib_lookup.h
@@ -16,10 +16,9 @@ struct fib_alias {
 	u8			fa_slen;
 	u32			tb_id;
 	s16			fa_default;
-	u8			offload:1,
-				trap:1,
-				offload_failed:1,
-				unused:5;
+	u8			offload;
+	u8			trap;
+	u8			offload_failed;
 	struct rcu_head		rcu;
 };
 
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 5dfb94abe7b1..b5563f5ff176 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -524,9 +524,9 @@ void rtmsg_fib(int event, __be32 key, struct fib_alias *fa,
 	fri.dst_len = dst_len;
 	fri.tos = fa->fa_tos;
 	fri.type = fa->fa_type;
-	fri.offload = fa->offload;
-	fri.trap = fa->trap;
-	fri.offload_failed = fa->offload_failed;
+	fri.offload = READ_ONCE(fa->offload);
+	fri.trap = READ_ONCE(fa->trap);
+	fri.offload_failed = READ_ONCE(fa->offload_failed);
 	err = fib_dump_info(skb, info->portid, seq, event, &fri, nlm_flags);
 	if (err < 0) {
 		/* -EMSGSIZE implies BUG in fib_nlmsg_size() */
@@ -887,8 +887,13 @@ int fib_nh_match(struct net *net, struct fib_config *cfg, struct fib_info *fi,
 	}
 
 	if (cfg->fc_oif || cfg->fc_gw_family) {
-		struct fib_nh *nh = fib_info_nh(fi, 0);
+		struct fib_nh *nh;
+
+		/* cannot match on nexthop object attributes */
+		if (fi->nh)
+			return 1;
 
+		nh = fib_info_nh(fi, 0);
 		if (cfg->fc_encap) {
 			if (fib_encap_match(net, cfg->fc_encap_type,
 					    cfg->fc_encap, nh, cfg, extack))
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 8060524f4256..f7f74d5c14da 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1047,19 +1047,23 @@ void fib_alias_hw_flags_set(struct net *net, const struct fib_rt_info *fri)
 	if (!fa_match)
 		goto out;
 
-	if (fa_match->offload == fri->offload && fa_match->trap == fri->trap &&
-	    fa_match->offload_failed == fri->offload_failed)
+	/* These are paired with the WRITE_ONCE() happening in this function.
+	 * The reason is that we are only protected by RCU at this point.
+	 */
+	if (READ_ONCE(fa_match->offload) == fri->offload &&
+	    READ_ONCE(fa_match->trap) == fri->trap &&
+	    READ_ONCE(fa_match->offload_failed) == fri->offload_failed)
 		goto out;
 
-	fa_match->offload = fri->offload;
-	fa_match->trap = fri->trap;
+	WRITE_ONCE(fa_match->offload, fri->offload);
+	WRITE_ONCE(fa_match->trap, fri->trap);
 
 	/* 2 means send notifications only if offload_failed was changed. */
 	if (net->ipv4.sysctl_fib_notify_on_flag_change == 2 &&
-	    fa_match->offload_failed == fri->offload_failed)
+	    READ_ONCE(fa_match->offload_failed) == fri->offload_failed)
 		goto out;
 
-	fa_match->offload_failed = fri->offload_failed;
+	WRITE_ONCE(fa_match->offload_failed, fri->offload_failed);
 
 	if (!net->ipv4.sysctl_fib_notify_on_flag_change)
 		goto out;
@@ -2297,9 +2301,9 @@ static int fn_trie_dump_leaf(struct key_vector *l, struct fib_table *tb,
 				fri.dst_len = KEYLENGTH - fa->fa_slen;
 				fri.tos = fa->fa_tos;
 				fri.type = fa->fa_type;
-				fri.offload = fa->offload;
-				fri.trap = fa->trap;
-				fri.offload_failed = fa->offload_failed;
+				fri.offload = READ_ONCE(fa->offload);
+				fri.trap = READ_ONCE(fa->trap);
+				fri.offload_failed = READ_ONCE(fa->offload_failed);
 				err = fib_dump_info(skb,
 						    NETLINK_CB(cb->skb).portid,
 						    cb->nlh->nlmsg_seq,
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 75737267746f..7bd1e10086f0 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -637,7 +637,9 @@ int __inet_hash(struct sock *sk, struct sock *osk)
 	int err = 0;
 
 	if (sk->sk_state != TCP_LISTEN) {
+		local_bh_disable();
 		inet_ehash_nolisten(sk, osk, NULL);
+		local_bh_enable();
 		return 0;
 	}
 	WARN_ON(!sk_unhashed(sk));
@@ -669,45 +671,54 @@ int inet_hash(struct sock *sk)
 {
 	int err = 0;
 
-	if (sk->sk_state != TCP_CLOSE) {
-		local_bh_disable();
+	if (sk->sk_state != TCP_CLOSE)
 		err = __inet_hash(sk, NULL);
-		local_bh_enable();
-	}
 
 	return err;
 }
 EXPORT_SYMBOL_GPL(inet_hash);
 
-void inet_unhash(struct sock *sk)
+static void __inet_unhash(struct sock *sk, struct inet_listen_hashbucket *ilb)
 {
-	struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
-	struct inet_listen_hashbucket *ilb = NULL;
-	spinlock_t *lock;
-
 	if (sk_unhashed(sk))
 		return;
 
-	if (sk->sk_state == TCP_LISTEN) {
-		ilb = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)];
-		lock = &ilb->lock;
-	} else {
-		lock = inet_ehash_lockp(hashinfo, sk->sk_hash);
-	}
-	spin_lock_bh(lock);
-	if (sk_unhashed(sk))
-		goto unlock;
-
 	if (rcu_access_pointer(sk->sk_reuseport_cb))
 		reuseport_stop_listen_sock(sk);
 	if (ilb) {
+		struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
+
 		inet_unhash2(hashinfo, sk);
 		ilb->count--;
 	}
 	__sk_nulls_del_node_init_rcu(sk);
 	sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
-unlock:
-	spin_unlock_bh(lock);
+}
+
+void inet_unhash(struct sock *sk)
+{
+	struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
+
+	if (sk_unhashed(sk))
+		return;
+
+	if (sk->sk_state == TCP_LISTEN) {
+		struct inet_listen_hashbucket *ilb;
+
+		ilb = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)];
+		/* Don't disable bottom halves while acquiring the lock to
+		 * avoid circular locking dependency on PREEMPT_RT.
+		 */
+		spin_lock(&ilb->lock);
+		__inet_unhash(sk, ilb);
+		spin_unlock(&ilb->lock);
+	} else {
+		spinlock_t *lock = inet_ehash_lockp(hashinfo, sk->sk_hash);
+
+		spin_lock_bh(lock);
+		__inet_unhash(sk, NULL);
+		spin_unlock_bh(lock);
+	}
 }
 EXPORT_SYMBOL_GPL(inet_unhash);
 
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index a4d2eb691cbc..131066d0319a 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -992,7 +992,7 @@ static int __ip_append_data(struct sock *sk,
 
 	if (cork->tx_flags & SKBTX_ANY_SW_TSTAMP &&
 	    sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)
-		tskey = sk->sk_tskey++;
+		tskey = atomic_inc_return(&sk->sk_tskey) - 1;
 
 	hh_len = LL_RESERVED_SPACE(rt->dst.dev);
 
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 086822cb1cc9..36e89b687387 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -172,16 +172,22 @@ static struct sock *ping_lookup(struct net *net, struct sk_buff *skb, u16 ident)
 	struct sock *sk = NULL;
 	struct inet_sock *isk;
 	struct hlist_nulls_node *hnode;
-	int dif = skb->dev->ifindex;
+	int dif, sdif;
 
 	if (skb->protocol == htons(ETH_P_IP)) {
+		dif = inet_iif(skb);
+		sdif = inet_sdif(skb);
 		pr_debug("try to find: num = %d, daddr = %pI4, dif = %d\n",
 			 (int)ident, &ip_hdr(skb)->daddr, dif);
 #if IS_ENABLED(CONFIG_IPV6)
 	} else if (skb->protocol == htons(ETH_P_IPV6)) {
+		dif = inet6_iif(skb);
+		sdif = inet6_sdif(skb);
 		pr_debug("try to find: num = %d, daddr = %pI6c, dif = %d\n",
 			 (int)ident, &ipv6_hdr(skb)->daddr, dif);
 #endif
+	} else {
+		return NULL;
 	}
 
 	read_lock_bh(&ping_table.lock);
@@ -221,7 +227,7 @@ static struct sock *ping_lookup(struct net *net, struct sk_buff *skb, u16 ident)
 		}
 
 		if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif &&
-		    sk->sk_bound_dev_if != inet_sdif(skb))
+		    sk->sk_bound_dev_if != sdif)
 			continue;
 
 		sock_hold(sk);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index d6899ab5fb39..ed9b6842a9a0 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -506,6 +506,15 @@ void __ip_select_ident(struct net *net, struct iphdr *iph, int segs)
 }
 EXPORT_SYMBOL(__ip_select_ident);
 
+static void ip_rt_fix_tos(struct flowi4 *fl4)
+{
+	__u8 tos = RT_FL_TOS(fl4);
+
+	fl4->flowi4_tos = tos & IPTOS_RT_MASK;
+	fl4->flowi4_scope = tos & RTO_ONLINK ?
+			    RT_SCOPE_LINK : RT_SCOPE_UNIVERSE;
+}
+
 static void __build_flow_key(const struct net *net, struct flowi4 *fl4,
 			     const struct sock *sk,
 			     const struct iphdr *iph,
@@ -831,6 +840,7 @@ static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buf
 	rt = (struct rtable *) dst;
 
 	__build_flow_key(net, &fl4, sk, iph, oif, tos, prot, mark, 0);
+	ip_rt_fix_tos(&fl4);
 	__ip_do_redirect(rt, skb, &fl4, true);
 }
 
@@ -1055,6 +1065,7 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
 	struct flowi4 fl4;
 
 	ip_rt_build_flow_key(&fl4, sk, skb);
+	ip_rt_fix_tos(&fl4);
 
 	/* Don't make lookup fail for bridged encapsulations */
 	if (skb && netif_is_any_bridge_port(skb->dev))
@@ -1129,6 +1140,8 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
 			goto out;
 
 		new = true;
+	} else {
+		ip_rt_fix_tos(&fl4);
 	}
 
 	__ip_rt_update_pmtu((struct rtable *)xfrm_dst_path(&rt->dst), &fl4, mtu);
@@ -2609,7 +2622,6 @@ add:
 struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *fl4,
 					const struct sk_buff *skb)
 {
-	__u8 tos = RT_FL_TOS(fl4);
 	struct fib_result res = {
 		.type		= RTN_UNSPEC,
 		.fi		= NULL,
@@ -2619,9 +2631,7 @@ struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *fl4,
 	struct rtable *rth;
 
 	fl4->flowi4_iif = LOOPBACK_IFINDEX;
-	fl4->flowi4_tos = tos & IPTOS_RT_MASK;
-	fl4->flowi4_scope = ((tos & RTO_ONLINK) ?
-			 RT_SCOPE_LINK : RT_SCOPE_UNIVERSE);
+	ip_rt_fix_tos(fl4);
 
 	rcu_read_lock();
 	rth = ip_route_output_key_hash_rcu(net, fl4, &res, skb);
@@ -3401,8 +3411,8 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 				    fa->fa_tos == fri.tos &&
 				    fa->fa_info == res.fi &&
 				    fa->fa_type == fri.type) {
-					fri.offload = fa->offload;
-					fri.trap = fa->trap;
+					fri.offload = READ_ONCE(fa->offload);
+					fri.trap = READ_ONCE(fa->trap);
 					break;
 				}
 			}
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index f48f1059b31a..ef68d55e0944 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1663,11 +1663,13 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
 				if (!copied)
 					copied = used;
 				break;
-			} else if (used <= len) {
-				seq += used;
-				copied += used;
-				offset += used;
 			}
+			if (WARN_ON_ONCE(used > len))
+				used = len;
+			seq += used;
+			copied += used;
+			offset += used;
+
 			/* If recv_actor drops the lock (e.g. TCP splice
 			 * receive) the skb pointer might be invalid when
 			 * getting here: tcp_collapse might have deleted it
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 9b9b02052fd3..1cdcb4df0eb7 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -138,10 +138,9 @@ int tcp_bpf_sendmsg_redir(struct sock *sk, struct sk_msg *msg,
 	struct sk_psock *psock = sk_psock_get(sk);
 	int ret;
 
-	if (unlikely(!psock)) {
-		sk_msg_free(sk, msg);
-		return 0;
-	}
+	if (unlikely(!psock))
+		return -EPIPE;
+
 	ret = ingress ? bpf_tcp_ingress(sk, psock, msg, bytes, flags) :
 			tcp_bpf_push_locked(sk, msg, bytes, flags, false);
 	sk_psock_put(sk, psock);
@@ -335,7 +334,7 @@ more_data:
 			cork = true;
 			psock->cork = NULL;
 		}
-		sk_msg_return(sk, msg, tosend);
+		sk_msg_return(sk, msg, msg->sg.size);
 		release_sock(sk);
 
 		ret = tcp_bpf_sendmsg_redir(sk_redir, msg, tosend, flags);
@@ -375,8 +374,11 @@ more_data:
 		}
 		if (msg &&
 		    msg->sg.data[msg->sg.start].page_link &&
-		    msg->sg.data[msg->sg.start].length)
+		    msg->sg.data[msg->sg.start].length) {
+			if (eval == __SK_REDIRECT)
+				sk_mem_charge(sk, msg->sg.size);
 			goto more_data;
+		}
 	}
 	return ret;
 }
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 0492f6942778..369752f5f676 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3734,6 +3734,7 @@ static void tcp_connect_queue_skb(struct sock *sk, struct sk_buff *skb)
  */
 static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 {
+	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct tcp_fastopen_request *fo = tp->fastopen_req;
 	int space, err = 0;
@@ -3748,8 +3749,10 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 	 * private TCP options. The cost is reduced data space in SYN :(
 	 */
 	tp->rx_opt.mss_clamp = tcp_mss_clamp(tp, tp->rx_opt.mss_clamp);
+	/* Sync mss_cache after updating the mss_clamp */
+	tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
 
-	space = __tcp_mtu_to_mss(sk, inet_csk(sk)->icsk_pmtu_cookie) -
+	space = __tcp_mtu_to_mss(sk, icsk->icsk_pmtu_cookie) -
 		MAX_TCP_OPTION_SPACE;
 
 	space = min_t(size_t, space, fo->size);
diff --git a/net/ipv4/udp_tunnel_nic.c b/net/ipv4/udp_tunnel_nic.c
index b91003538d87..bc3a043a5d5c 100644
--- a/net/ipv4/udp_tunnel_nic.c
+++ b/net/ipv4/udp_tunnel_nic.c
@@ -846,7 +846,7 @@ udp_tunnel_nic_unregister(struct net_device *dev, struct udp_tunnel_nic *utn)
 		list_for_each_entry(node, &info->shared->devices, list)
 			if (node->dev == dev)
 				break;
-		if (node->dev != dev)
+		if (list_entry_is_head(node, &info->shared->devices, list))
 			return;
 
 		list_del(&node->list);
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index bf1386542634..3a8838b79bb6 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -552,7 +552,7 @@ static int inet6_netconf_fill_devconf(struct sk_buff *skb, int ifindex,
 #ifdef CONFIG_IPV6_MROUTE
 	if ((all || type == NETCONFA_MC_FORWARDING) &&
 	    nla_put_s32(skb, NETCONFA_MC_FORWARDING,
-			devconf->mc_forwarding) < 0)
+			atomic_read(&devconf->mc_forwarding)) < 0)
 		goto nla_put_failure;
 #endif
 	if ((all || type == NETCONFA_PROXY_NEIGH) &&
@@ -1837,8 +1837,8 @@ out:
 }
 EXPORT_SYMBOL(ipv6_dev_get_saddr);
 
-int __ipv6_get_lladdr(struct inet6_dev *idev, struct in6_addr *addr,
-		      u32 banned_flags)
+static int __ipv6_get_lladdr(struct inet6_dev *idev, struct in6_addr *addr,
+			      u32 banned_flags)
 {
 	struct inet6_ifaddr *ifp;
 	int err = -EADDRNOTAVAIL;
@@ -3730,6 +3730,7 @@ static int addrconf_ifdown(struct net_device *dev, bool unregister)
 	struct inet6_dev *idev;
 	struct inet6_ifaddr *ifa, *tmp;
 	bool keep_addr = false;
+	bool was_ready;
 	int state, i;
 
 	ASSERT_RTNL();
@@ -3795,7 +3796,10 @@ restart:
 
 	addrconf_del_rs_timer(idev);
 
-	/* Step 2: clear flags for stateless addrconf */
+	/* Step 2: clear flags for stateless addrconf, repeated down
+	 *         detection
+	 */
+	was_ready = idev->if_flags & IF_READY;
 	if (!unregister)
 		idev->if_flags &= ~(IF_RS_SENT|IF_RA_RCVD|IF_READY);
 
@@ -3869,7 +3873,7 @@ restart:
 	if (unregister) {
 		ipv6_ac_destroy_dev(idev);
 		ipv6_mc_destroy_dev(idev);
-	} else {
+	} else if (was_ready) {
 		ipv6_mc_down(idev);
 	}
 
@@ -4996,6 +5000,7 @@ static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa,
 	    nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid))
 		goto error;
 
+	spin_lock_bh(&ifa->lock);
 	if (!((ifa->flags&IFA_F_PERMANENT) &&
 	      (ifa->prefered_lft == INFINITY_LIFE_TIME))) {
 		preferred = ifa->prefered_lft;
@@ -5017,6 +5022,7 @@ static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa,
 		preferred = INFINITY_LIFE_TIME;
 		valid = INFINITY_LIFE_TIME;
 	}
+	spin_unlock_bh(&ifa->lock);
 
 	if (!ipv6_addr_any(&ifa->peer_addr)) {
 		if (nla_put_in6_addr(skb, IFA_LOCAL, &ifa->addr) < 0 ||
@@ -5531,7 +5537,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf,
 	array[DEVCONF_USE_OPTIMISTIC] = cnf->use_optimistic;
 #endif
 #ifdef CONFIG_IPV6_MROUTE
-	array[DEVCONF_MC_FORWARDING] = cnf->mc_forwarding;
+	array[DEVCONF_MC_FORWARDING] = atomic_read(&cnf->mc_forwarding);
 #endif
 	array[DEVCONF_DISABLE_IPV6] = cnf->disable_ipv6;
 	array[DEVCONF_ACCEPT_DAD] = cnf->accept_dad;
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index f0bac6f7ab6b..6219d97cac7a 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -491,6 +491,10 @@ int esp6_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info
 			return err;
 	}
 
+	if (ALIGN(tailen, L1_CACHE_BYTES) > PAGE_SIZE ||
+	    ALIGN(skb->data_len, L1_CACHE_BYTES) > PAGE_SIZE)
+		goto cow;
+
 	if (!skb_cloned(skb)) {
 		if (tailen <= skb_tailroom(skb)) {
 			nfrags = 1;
@@ -708,7 +712,7 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb)
 		struct xfrm_dst *dst = (struct xfrm_dst *)skb_dst(skb);
 		u32 padto;
 
-		padto = min(x->tfcpad, __xfrm_state_mtu(x, dst->child_mtu_cached));
+		padto = min(x->tfcpad, xfrm_state_mtu(x, dst->child_mtu_cached));
 		if (skb->len < padto)
 			esp.tfclen = padto - skb->len;
 	}
@@ -808,8 +812,7 @@ int esp6_input_done2(struct sk_buff *skb, int err)
 		struct tcphdr *th;
 
 		offset = ipv6_skip_exthdr(skb, offset, &nexthdr, &frag_off);
-
-		if (offset < 0) {
+		if (offset == -1) {
 			err = -EINVAL;
 			goto out;
 		}
diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c
index a349d4798077..302170882382 100644
--- a/net/ipv6/esp6_offload.c
+++ b/net/ipv6/esp6_offload.c
@@ -198,6 +198,9 @@ static struct sk_buff *xfrm6_beet_gso_segment(struct xfrm_state *x,
 			ipv6_skip_exthdr(skb, 0, &proto, &frag);
 	}
 
+	if (proto == IPPROTO_IPIP)
+		skb_shinfo(skb)->gso_type |= SKB_GSO_IPXIP6;
+
 	__skb_pull(skb, skb_transport_offset(skb));
 	ops = rcu_dereference(inet6_offloads[proto]);
 	if (likely(ops && ops->callbacks.gso_segment))
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 67c9114835c8..0a2e7f228391 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -333,11 +333,8 @@ int inet6_hash(struct sock *sk)
 {
 	int err = 0;
 
-	if (sk->sk_state != TCP_CLOSE) {
-		local_bh_disable();
+	if (sk->sk_state != TCP_CLOSE)
 		err = __inet_hash(sk, NULL);
-		local_bh_enable();
-	}
 
 	return err;
 }
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index aa673a6a7e43..ceb85c67ce39 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -450,8 +450,10 @@ fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq,
 		err = -EINVAL;
 		goto done;
 	}
-	if (fl_shared_exclusive(fl) || fl->opt)
+	if (fl_shared_exclusive(fl) || fl->opt) {
+		WRITE_ONCE(sock_net(sk)->ipv6.flowlabel_has_excl, 1);
 		static_branch_deferred_inc(&ipv6_flowlabel_exclusive);
+	}
 	return fl;
 
 done:
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 466a5610e3ca..869c3337e319 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -733,9 +733,6 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb,
 	else
 		fl6->daddr = tunnel->parms.raddr;
 
-	if (skb_cow_head(skb, dev->needed_headroom ?: tunnel->hlen))
-		return -ENOMEM;
-
 	/* Push GRE header. */
 	protocol = (dev->type == ARPHRD_ETHER) ? htons(ETH_P_TEB) : proto;
 
@@ -743,6 +740,7 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb,
 		struct ip_tunnel_info *tun_info;
 		const struct ip_tunnel_key *key;
 		__be16 flags;
+		int tun_hlen;
 
 		tun_info = skb_tunnel_info_txcheck(skb);
 		if (IS_ERR(tun_info) ||
@@ -760,9 +758,12 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb,
 		dsfield = key->tos;
 		flags = key->tun_flags &
 			(TUNNEL_CSUM | TUNNEL_KEY | TUNNEL_SEQ);
-		tunnel->tun_hlen = gre_calc_hlen(flags);
+		tun_hlen = gre_calc_hlen(flags);
 
-		gre_build_header(skb, tunnel->tun_hlen,
+		if (skb_cow_head(skb, dev->needed_headroom ?: tun_hlen + tunnel->encap_hlen))
+			return -ENOMEM;
+
+		gre_build_header(skb, tun_hlen,
 				 flags, protocol,
 				 tunnel_id_to_key32(tun_info->key.tun_id),
 				 (flags & TUNNEL_SEQ) ? htonl(tunnel->o_seqno++)
@@ -772,6 +773,9 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb,
 		if (tunnel->parms.o_flags & TUNNEL_SEQ)
 			tunnel->o_seqno++;
 
+		if (skb_cow_head(skb, dev->needed_headroom ?: tunnel->hlen))
+			return -ENOMEM;
+
 		gre_build_header(skb, tunnel->tun_hlen, tunnel->parms.o_flags,
 				 protocol, tunnel->parms.o_key,
 				 htonl(tunnel->o_seqno));
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index 80256717868e..d4b1e2c5aa76 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -508,7 +508,7 @@ int ip6_mc_input(struct sk_buff *skb)
 	/*
 	 *      IPv6 multicast router mode is now supported ;)
 	 */
-	if (dev_net(skb->dev)->ipv6.devconf_all->mc_forwarding &&
+	if (atomic_read(&dev_net(skb->dev)->ipv6.devconf_all->mc_forwarding) &&
 	    !(ipv6_addr_type(&hdr->daddr) &
 	      (IPV6_ADDR_LOOPBACK|IPV6_ADDR_LINKLOCAL)) &&
 	    likely(!(IP6CB(skb)->flags & IP6SKB_FORWARDED))) {
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 1b9827ff8ccf..172565d12570 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -114,6 +114,8 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 	if (likely(ops && ops->callbacks.gso_segment)) {
 		skb_reset_transport_header(skb);
 		segs = ops->callbacks.gso_segment(skb, features);
+		if (!segs)
+			skb->network_header = skb_mac_header(skb) + nhoff - skb->head;
 	}
 
 	if (IS_ERR_OR_NULL(segs))
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index ff4e83e2a506..04c3cb4c5fec 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -485,7 +485,7 @@ int ip6_forward(struct sk_buff *skb)
 		goto drop;
 
 	if (!net->ipv6.devconf_all->disable_policy &&
-	    !idev->cnf.disable_policy &&
+	    (!idev || !idev->cnf.disable_policy) &&
 	    !xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) {
 		__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
 		goto drop;
@@ -1408,8 +1408,6 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork,
 		if (np->frag_size)
 			mtu = np->frag_size;
 	}
-	if (mtu < IPV6_MIN_MTU)
-		return -EINVAL;
 	cork->base.fragsize = mtu;
 	cork->base.gso_size = ipc6->gso_size;
 	cork->base.tx_flags = 0;
@@ -1465,14 +1463,12 @@ static int __ip6_append_data(struct sock *sk,
 
 	if (cork->tx_flags & SKBTX_ANY_SW_TSTAMP &&
 	    sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)
-		tskey = sk->sk_tskey++;
+		tskey = atomic_inc_return(&sk->sk_tskey) - 1;
 
 	hh_len = LL_RESERVED_SPACE(rt->dst.dev);
 
 	fragheaderlen = sizeof(struct ipv6hdr) + rt->rt6i_nfheader_len +
 			(opt ? opt->opt_nflen : 0);
-	maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen -
-		     sizeof(struct frag_hdr);
 
 	headersize = sizeof(struct ipv6hdr) +
 		     (opt ? opt->opt_flen + opt->opt_nflen : 0) +
@@ -1480,6 +1476,13 @@ static int __ip6_append_data(struct sock *sk,
 		      sizeof(struct frag_hdr) : 0) +
 		     rt->rt6i_nfheader_len;
 
+	if (mtu <= fragheaderlen ||
+	    ((mtu - fragheaderlen) & ~7) + fragheaderlen <= sizeof(struct frag_hdr))
+		goto emsgsize;
+
+	maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen -
+		     sizeof(struct frag_hdr);
+
 	/* as per RFC 7112 section 5, the entire IPv6 Header Chain must fit
 	 * the first fragment
 	 */
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 6a4065d81aa9..91f1c5f56d5f 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -739,7 +739,7 @@ static int mif6_delete(struct mr_table *mrt, int vifi, int notify,
 
 	in6_dev = __in6_dev_get(dev);
 	if (in6_dev) {
-		in6_dev->cnf.mc_forwarding--;
+		atomic_dec(&in6_dev->cnf.mc_forwarding);
 		inet6_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF,
 					     NETCONFA_MC_FORWARDING,
 					     dev->ifindex, &in6_dev->cnf);
@@ -907,7 +907,7 @@ static int mif6_add(struct net *net, struct mr_table *mrt,
 
 	in6_dev = __in6_dev_get(dev);
 	if (in6_dev) {
-		in6_dev->cnf.mc_forwarding++;
+		atomic_inc(&in6_dev->cnf.mc_forwarding);
 		inet6_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF,
 					     NETCONFA_MC_FORWARDING,
 					     dev->ifindex, &in6_dev->cnf);
@@ -1557,7 +1557,7 @@ static int ip6mr_sk_init(struct mr_table *mrt, struct sock *sk)
 	} else {
 		rcu_assign_pointer(mrt->mroute_sk, sk);
 		sock_set_flag(sk, SOCK_RCU_FREE);
-		net->ipv6.devconf_all->mc_forwarding++;
+		atomic_inc(&net->ipv6.devconf_all->mc_forwarding);
 	}
 	write_unlock_bh(&mrt_lock);
 
@@ -1590,7 +1590,7 @@ int ip6mr_sk_done(struct sock *sk)
 			 * so the RCU grace period before sk freeing
 			 * is guaranteed by sk_destruct()
 			 */
-			net->ipv6.devconf_all->mc_forwarding--;
+			atomic_dec(&net->ipv6.devconf_all->mc_forwarding);
 			write_unlock_bh(&mrt_lock);
 			inet6_netconf_notify_devconf(net, RTM_NEWNETCONF,
 						     NETCONFA_MC_FORWARDING,
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index bed8155508c8..909f937befd7 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -1371,27 +1371,23 @@ static void mld_process_v2(struct inet6_dev *idev, struct mld2_query *mld,
 }
 
 /* called with rcu_read_lock() */
-int igmp6_event_query(struct sk_buff *skb)
+void igmp6_event_query(struct sk_buff *skb)
 {
 	struct inet6_dev *idev = __in6_dev_get(skb->dev);
 
-	if (!idev)
-		return -EINVAL;
-
-	if (idev->dead) {
-		kfree_skb(skb);
-		return -ENODEV;
-	}
+	if (!idev || idev->dead)
+		goto out;
 
 	spin_lock_bh(&idev->mc_query_lock);
 	if (skb_queue_len(&idev->mc_query_queue) < MLD_MAX_SKBS) {
 		__skb_queue_tail(&idev->mc_query_queue, skb);
 		if (!mod_delayed_work(mld_wq, &idev->mc_query_work, 0))
 			in6_dev_hold(idev);
+		skb = NULL;
 	}
 	spin_unlock_bh(&idev->mc_query_lock);
-
-	return 0;
+out:
+	kfree_skb(skb);
 }
 
 static void __mld_query_work(struct sk_buff *skb)
@@ -1542,27 +1538,23 @@ static void mld_query_work(struct work_struct *work)
 }
 
 /* called with rcu_read_lock() */
-int igmp6_event_report(struct sk_buff *skb)
+void igmp6_event_report(struct sk_buff *skb)
 {
 	struct inet6_dev *idev = __in6_dev_get(skb->dev);
 
-	if (!idev)
-		return -EINVAL;
-
-	if (idev->dead) {
-		kfree_skb(skb);
-		return -ENODEV;
-	}
+	if (!idev || idev->dead)
+		goto out;
 
 	spin_lock_bh(&idev->mc_report_lock);
 	if (skb_queue_len(&idev->mc_report_queue) < MLD_MAX_SKBS) {
 		__skb_queue_tail(&idev->mc_report_queue, skb);
 		if (!mod_delayed_work(mld_wq, &idev->mc_report_work, 0))
 			in6_dev_hold(idev);
+		skb = NULL;
 	}
 	spin_unlock_bh(&idev->mc_report_lock);
-
-	return 0;
+out:
+	kfree_skb(skb);
 }
 
 static void __mld_report_work(struct sk_buff *skb)
@@ -1759,7 +1751,7 @@ static struct sk_buff *mld_newpack(struct inet6_dev *idev, unsigned int mtu)
 	skb_reserve(skb, hlen);
 	skb_tailroom_reserve(skb, mtu, tlen);
 
-	if (__ipv6_get_lladdr(idev, &addr_buf, IFA_F_TENTATIVE)) {
+	if (ipv6_get_lladdr(dev, &addr_buf, IFA_F_TENTATIVE)) {
 		/* <draft-ietf-magma-mld-source-05.txt>:
 		 * use unspecified address as the source address
 		 * when a valid link-local address is not available.
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 3c5bb4969220..0ca7c780d97a 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3303,6 +3303,7 @@ static int ip6_dst_gc(struct dst_ops *ops)
 	int rt_elasticity = net->ipv6.sysctl.ip6_rt_gc_elasticity;
 	int rt_gc_timeout = net->ipv6.sysctl.ip6_rt_gc_timeout;
 	unsigned long rt_last_gc = net->ipv6.ip6_rt_last_gc;
+	unsigned int val;
 	int entries;
 
 	entries = dst_entries_get_fast(ops);
@@ -3313,13 +3314,13 @@ static int ip6_dst_gc(struct dst_ops *ops)
 	    entries <= rt_max_size)
 		goto out;
 
-	net->ipv6.ip6_rt_gc_expire++;
-	fib6_run_gc(net->ipv6.ip6_rt_gc_expire, net, true);
+	fib6_run_gc(atomic_inc_return(&net->ipv6.ip6_rt_gc_expire), net, true);
 	entries = dst_entries_get_slow(ops);
 	if (entries < ops->gc_thresh)
-		net->ipv6.ip6_rt_gc_expire = rt_gc_timeout>>1;
+		atomic_set(&net->ipv6.ip6_rt_gc_expire, rt_gc_timeout >> 1);
 out:
-	net->ipv6.ip6_rt_gc_expire -= net->ipv6.ip6_rt_gc_expire>>rt_elasticity;
+	val = atomic_read(&net->ipv6.ip6_rt_gc_expire);
+	atomic_set(&net->ipv6.ip6_rt_gc_expire, val - (val >> rt_elasticity));
 	return entries > rt_max_size;
 }
 
@@ -4509,7 +4510,7 @@ static int ip6_pkt_drop(struct sk_buff *skb, u8 code, int ipstats_mib_noroutes)
 	struct inet6_dev *idev;
 	int type;
 
-	if (netif_is_l3_master(skb->dev) &&
+	if (netif_is_l3_master(skb->dev) ||
 	    dst->dev == net->loopback_dev)
 		idev = __in6_dev_get_safely(dev_get_by_index_rcu(net, IP6CB(skb)->iif));
 	else
@@ -5767,11 +5768,11 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
 	}
 
 	if (!dst) {
-		if (rt->offload)
+		if (READ_ONCE(rt->offload))
 			rtm->rtm_flags |= RTM_F_OFFLOAD;
-		if (rt->trap)
+		if (READ_ONCE(rt->trap))
 			rtm->rtm_flags |= RTM_F_TRAP;
-		if (rt->offload_failed)
+		if (READ_ONCE(rt->offload_failed))
 			rtm->rtm_flags |= RTM_F_OFFLOAD_FAILED;
 	}
 
@@ -6229,19 +6230,20 @@ void fib6_info_hw_flags_set(struct net *net, struct fib6_info *f6i,
 	struct sk_buff *skb;
 	int err;
 
-	if (f6i->offload == offload && f6i->trap == trap &&
-	    f6i->offload_failed == offload_failed)
+	if (READ_ONCE(f6i->offload) == offload &&
+	    READ_ONCE(f6i->trap) == trap &&
+	    READ_ONCE(f6i->offload_failed) == offload_failed)
 		return;
 
-	f6i->offload = offload;
-	f6i->trap = trap;
+	WRITE_ONCE(f6i->offload, offload);
+	WRITE_ONCE(f6i->trap, trap);
 
 	/* 2 means send notifications only if offload_failed was changed. */
 	if (net->ipv6.sysctl.fib_notify_on_flag_change == 2 &&
-	    f6i->offload_failed == offload_failed)
+	    READ_ONCE(f6i->offload_failed) == offload_failed)
 		return;
 
-	f6i->offload_failed = offload_failed;
+	WRITE_ONCE(f6i->offload_failed, offload_failed);
 
 	if (!rcu_access_pointer(f6i->fib6_node))
 		/* The route was removed from the tree, do not send
@@ -6527,7 +6529,7 @@ static int __net_init ip6_route_net_init(struct net *net)
 	net->ipv6.sysctl.ip6_rt_min_advmss = IPV6_MIN_MTU - 20 - 40;
 	net->ipv6.sysctl.skip_notify_on_dev_down = 0;
 
-	net->ipv6.ip6_rt_gc_expire = 30*HZ;
+	atomic_set(&net->ipv6.ip6_rt_gc_expire, 30*HZ);
 
 	ret = 0;
 out:
diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c
index d0d280077721..ad07904642ca 100644
--- a/net/ipv6/xfrm6_output.c
+++ b/net/ipv6/xfrm6_output.c
@@ -45,6 +45,19 @@ static int __xfrm6_output_finish(struct net *net, struct sock *sk, struct sk_buf
 	return xfrm_output(sk, skb);
 }
 
+static int xfrm6_noneed_fragment(struct sk_buff *skb)
+{
+	struct frag_hdr *fh;
+	u8 prevhdr = ipv6_hdr(skb)->nexthdr;
+
+	if (prevhdr != NEXTHDR_FRAGMENT)
+		return 0;
+	fh = (struct frag_hdr *)(skb->data + sizeof(struct ipv6hdr));
+	if (fh->nexthdr == NEXTHDR_ESP || fh->nexthdr == NEXTHDR_AUTH)
+		return 1;
+	return 0;
+}
+
 static int __xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
@@ -73,6 +86,9 @@ static int __xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 		xfrm6_local_rxpmtu(skb, mtu);
 		kfree_skb(skb);
 		return -EMSGSIZE;
+	} else if (toobig && xfrm6_noneed_fragment(skb)) {
+		skb->ignore_df = 1;
+		goto skip_frag;
 	} else if (!skb->ignore_df && toobig && skb->sk) {
 		xfrm_local_error(skb, mtu);
 		kfree_skb(skb);
diff --git a/net/key/af_key.c b/net/key/af_key.c
index de24a7d474df..fd51db3be91c 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -1699,7 +1699,7 @@ static int pfkey_register(struct sock *sk, struct sk_buff *skb, const struct sad
 
 	xfrm_probe_algs();
 
-	supp_skb = compose_sadb_supported(hdr, GFP_KERNEL);
+	supp_skb = compose_sadb_supported(hdr, GFP_KERNEL | __GFP_ZERO);
 	if (!supp_skb) {
 		if (hdr->sadb_msg_satype != SADB_SATYPE_UNSPEC)
 			pfk->registered &= ~(1<<hdr->sadb_msg_satype);
@@ -2623,7 +2623,7 @@ static int pfkey_migrate(struct sock *sk, struct sk_buff *skb,
 	}
 
 	return xfrm_migrate(&sel, dir, XFRM_POLICY_TYPE_MAIN, m, i,
-			    kma ? &k : NULL, net, NULL);
+			    kma ? &k : NULL, net, NULL, 0);
 
  out:
 	return err;
diff --git a/net/l3mdev/l3mdev.c b/net/l3mdev/l3mdev.c
index 17927966abb3..8b14a24f1040 100644
--- a/net/l3mdev/l3mdev.c
+++ b/net/l3mdev/l3mdev.c
@@ -147,7 +147,7 @@ int l3mdev_master_upper_ifindex_by_index_rcu(struct net *net, int ifindex)
 
 	dev = dev_get_by_index_rcu(net, ifindex);
 	while (dev && !netif_is_l3_master(dev))
-		dev = netdev_master_upper_dev_get(dev);
+		dev = netdev_master_upper_dev_get_rcu(dev);
 
 	return dev ? dev->ifindex : 0;
 }
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index 3086f4a6ae68..99305aadaa08 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -275,6 +275,7 @@ static int llc_ui_autobind(struct socket *sock, struct sockaddr_llc *addr)
 {
 	struct sock *sk = sock->sk;
 	struct llc_sock *llc = llc_sk(sk);
+	struct net_device *dev = NULL;
 	struct llc_sap *sap;
 	int rc = -EINVAL;
 
@@ -286,14 +287,14 @@ static int llc_ui_autobind(struct socket *sock, struct sockaddr_llc *addr)
 		goto out;
 	rc = -ENODEV;
 	if (sk->sk_bound_dev_if) {
-		llc->dev = dev_get_by_index(&init_net, sk->sk_bound_dev_if);
-		if (llc->dev && addr->sllc_arphrd != llc->dev->type) {
-			dev_put(llc->dev);
-			llc->dev = NULL;
+		dev = dev_get_by_index(&init_net, sk->sk_bound_dev_if);
+		if (dev && addr->sllc_arphrd != dev->type) {
+			dev_put(dev);
+			dev = NULL;
 		}
 	} else
-		llc->dev = dev_getfirstbyhwtype(&init_net, addr->sllc_arphrd);
-	if (!llc->dev)
+		dev = dev_getfirstbyhwtype(&init_net, addr->sllc_arphrd);
+	if (!dev)
 		goto out;
 	rc = -EUSERS;
 	llc->laddr.lsap = llc_ui_autoport();
@@ -303,6 +304,11 @@ static int llc_ui_autobind(struct socket *sock, struct sockaddr_llc *addr)
 	sap = llc_sap_open(llc->laddr.lsap, NULL);
 	if (!sap)
 		goto out;
+
+	/* Note: We do not expect errors from this point. */
+	llc->dev = dev;
+	dev = NULL;
+
 	memcpy(llc->laddr.mac, llc->dev->dev_addr, IFHWADDRLEN);
 	memcpy(&llc->addr, addr, sizeof(llc->addr));
 	/* assign new connection to its SAP */
@@ -310,6 +316,7 @@ static int llc_ui_autobind(struct socket *sock, struct sockaddr_llc *addr)
 	sock_reset_flag(sk, SOCK_ZAPPED);
 	rc = 0;
 out:
+	dev_put(dev);
 	return rc;
 }
 
@@ -332,6 +339,7 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen)
 	struct sockaddr_llc *addr = (struct sockaddr_llc *)uaddr;
 	struct sock *sk = sock->sk;
 	struct llc_sock *llc = llc_sk(sk);
+	struct net_device *dev = NULL;
 	struct llc_sap *sap;
 	int rc = -EINVAL;
 
@@ -347,25 +355,27 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen)
 	rc = -ENODEV;
 	rcu_read_lock();
 	if (sk->sk_bound_dev_if) {
-		llc->dev = dev_get_by_index_rcu(&init_net, sk->sk_bound_dev_if);
-		if (llc->dev) {
+		dev = dev_get_by_index_rcu(&init_net, sk->sk_bound_dev_if);
+		if (dev) {
 			if (is_zero_ether_addr(addr->sllc_mac))
-				memcpy(addr->sllc_mac, llc->dev->dev_addr,
+				memcpy(addr->sllc_mac, dev->dev_addr,
 				       IFHWADDRLEN);
-			if (addr->sllc_arphrd != llc->dev->type ||
+			if (addr->sllc_arphrd != dev->type ||
 			    !ether_addr_equal(addr->sllc_mac,
-					      llc->dev->dev_addr)) {
+					      dev->dev_addr)) {
 				rc = -EINVAL;
-				llc->dev = NULL;
+				dev = NULL;
 			}
 		}
-	} else
-		llc->dev = dev_getbyhwaddr_rcu(&init_net, addr->sllc_arphrd,
+	} else {
+		dev = dev_getbyhwaddr_rcu(&init_net, addr->sllc_arphrd,
 					   addr->sllc_mac);
-	dev_hold(llc->dev);
+	}
+	dev_hold(dev);
 	rcu_read_unlock();
-	if (!llc->dev)
+	if (!dev)
 		goto out;
+
 	if (!addr->sllc_sap) {
 		rc = -EUSERS;
 		addr->sllc_sap = llc_ui_autoport();
@@ -397,6 +407,11 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen)
 			goto out_put;
 		}
 	}
+
+	/* Note: We do not expect errors from this point. */
+	llc->dev = dev;
+	dev = NULL;
+
 	llc->laddr.lsap = addr->sllc_sap;
 	memcpy(llc->laddr.mac, addr->sllc_mac, IFHWADDRLEN);
 	memcpy(&llc->addr, addr, sizeof(llc->addr));
@@ -407,6 +422,7 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen)
 out_put:
 	llc_sap_put(sap);
 out:
+	dev_put(dev);
 	release_sock(sk);
 	return rc;
 }
diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c
index 74a878f213d3..1deb3d874a4b 100644
--- a/net/mac80211/agg-tx.c
+++ b/net/mac80211/agg-tx.c
@@ -9,7 +9,7 @@
  * Copyright 2007, Michael Wu <flamingice@sourmilk.net>
  * Copyright 2007-2010, Intel Corporation
  * Copyright(c) 2015-2017 Intel Deutschland GmbH
- * Copyright (C) 2018 - 2021 Intel Corporation
+ * Copyright (C) 2018 - 2022 Intel Corporation
  */
 
 #include <linux/ieee80211.h>
@@ -626,6 +626,14 @@ int ieee80211_start_tx_ba_session(struct ieee80211_sta *pubsta, u16 tid,
 		return -EINVAL;
 	}
 
+	if (test_sta_flag(sta, WLAN_STA_MFP) &&
+	    !test_sta_flag(sta, WLAN_STA_AUTHORIZED)) {
+		ht_dbg(sdata,
+		       "MFP STA not authorized - deny BA session request %pM tid %d\n",
+		       sta->sta.addr, tid);
+		return -EINVAL;
+	}
+
 	/*
 	 * 802.11n-2009 11.5.1.1: If the initiating STA is an HT STA, is a
 	 * member of an IBSS, and has no other existing Block Ack agreement
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 1bf83b8d8402..3f625e836a03 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -2110,14 +2110,12 @@ static int copy_mesh_setup(struct ieee80211_if_mesh *ifmsh,
 		const struct mesh_setup *setup)
 {
 	u8 *new_ie;
-	const u8 *old_ie;
 	struct ieee80211_sub_if_data *sdata = container_of(ifmsh,
 					struct ieee80211_sub_if_data, u.mesh);
 	int i;
 
 	/* allocate information elements */
 	new_ie = NULL;
-	old_ie = ifmsh->ie;
 
 	if (setup->ie_len) {
 		new_ie = kmemdup(setup->ie, setup->ie_len,
@@ -2127,7 +2125,6 @@ static int copy_mesh_setup(struct ieee80211_if_mesh *ifmsh,
 	}
 	ifmsh->ie_len = setup->ie_len;
 	ifmsh->ie = new_ie;
-	kfree(old_ie);
 
 	/* now copy the rest of the setup parameters */
 	ifmsh->mesh_id_len = setup->mesh_id_len;
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index e43804c9387e..d30bd21697a3 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -376,7 +376,7 @@ struct ieee80211_mgd_auth_data {
 
 	u8 key[WLAN_KEY_LEN_WEP104];
 	u8 key_len, key_idx;
-	bool done;
+	bool done, waiting;
 	bool peer_confirmed;
 	bool timeout_started;
 
@@ -2379,7 +2379,7 @@ u8 *ieee80211_ie_build_vht_cap(u8 *pos, struct ieee80211_sta_vht_cap *vht_cap,
 u8 *ieee80211_ie_build_vht_oper(u8 *pos, struct ieee80211_sta_vht_cap *vht_cap,
 				const struct cfg80211_chan_def *chandef);
 u8 ieee80211_ie_len_he_cap(struct ieee80211_sub_if_data *sdata, u8 iftype);
-u8 *ieee80211_ie_build_he_cap(u8 *pos,
+u8 *ieee80211_ie_build_he_cap(u32 disable_flags, u8 *pos,
 			      const struct ieee80211_sta_he_cap *he_cap,
 			      u8 *end);
 void ieee80211_ie_build_he_6ghz_cap(struct ieee80211_sub_if_data *sdata,
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 45fb517591ee..5311c3cd3050 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -1131,17 +1131,14 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 		local->scan_ies_len +=
 			2 + sizeof(struct ieee80211_vht_cap);
 
-	/* HE cap element is variable in size - set len to allow max size */
 	/*
-	 * TODO: 1 is added at the end of the calculation to accommodate for
-	 *	the temporary placing of the HE capabilities IE under EXT.
-	 *	Remove it once it is placed in the final place.
-	 */
-	if (supp_he)
+	 * HE cap element is variable in size - set len to allow max size */
+	if (supp_he) {
 		local->scan_ies_len +=
-			2 + sizeof(struct ieee80211_he_cap_elem) +
+			3 + sizeof(struct ieee80211_he_cap_elem) +
 			sizeof(struct ieee80211_he_mcs_nss_supp) +
-			IEEE80211_HE_PPE_THRES_MAX_LEN + 1;
+			IEEE80211_HE_PPE_THRES_MAX_LEN;
+	}
 
 	if (!local->ops->hw_scan) {
 		/* For hw_scan, driver needs to set these up. */
diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c
index 5dcfd53a4ab6..42bd81a30310 100644
--- a/net/mac80211/mesh.c
+++ b/net/mac80211/mesh.c
@@ -580,7 +580,7 @@ int mesh_add_he_cap_ie(struct ieee80211_sub_if_data *sdata,
 		return -ENOMEM;
 
 	pos = skb_put(skb, ie_len);
-	ieee80211_ie_build_he_cap(pos, he_cap, pos + ie_len);
+	ieee80211_ie_build_he_cap(0, pos, he_cap, pos + ie_len);
 
 	return 0;
 }
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 89c648b035b9..c8332452c118 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -37,6 +37,7 @@
 #define IEEE80211_AUTH_TIMEOUT_SAE	(HZ * 2)
 #define IEEE80211_AUTH_MAX_TRIES	3
 #define IEEE80211_AUTH_WAIT_ASSOC	(HZ * 5)
+#define IEEE80211_AUTH_WAIT_SAE_RETRY	(HZ * 2)
 #define IEEE80211_ASSOC_TIMEOUT		(HZ / 5)
 #define IEEE80211_ASSOC_TIMEOUT_LONG	(HZ / 2)
 #define IEEE80211_ASSOC_TIMEOUT_SHORT	(HZ / 10)
@@ -629,7 +630,7 @@ static void ieee80211_add_he_ie(struct ieee80211_sub_if_data *sdata,
 				struct sk_buff *skb,
 				struct ieee80211_supported_band *sband)
 {
-	u8 *pos;
+	u8 *pos, *pre_he_pos;
 	const struct ieee80211_sta_he_cap *he_cap = NULL;
 	struct ieee80211_chanctx_conf *chanctx_conf;
 	u8 he_cap_size;
@@ -646,25 +647,26 @@ static void ieee80211_add_he_ie(struct ieee80211_sub_if_data *sdata,
 
 	he_cap = ieee80211_get_he_iftype_cap(sband,
 					     ieee80211_vif_type_p2p(&sdata->vif));
-	if (!he_cap || !reg_cap)
+	if (!he_cap || !chanctx_conf || !reg_cap)
 		return;
 
-	/*
-	 * TODO: the 1 added is because this temporarily is under the EXTENSION
-	 * IE. Get rid of it when it moves.
-	 */
+	/* get a max size estimate */
 	he_cap_size =
 		2 + 1 + sizeof(he_cap->he_cap_elem) +
 		ieee80211_he_mcs_nss_size(&he_cap->he_cap_elem) +
 		ieee80211_he_ppe_size(he_cap->ppe_thres[0],
 				      he_cap->he_cap_elem.phy_cap_info);
 	pos = skb_put(skb, he_cap_size);
-	ieee80211_ie_build_he_cap(pos, he_cap, pos + he_cap_size);
+	pre_he_pos = pos;
+	pos = ieee80211_ie_build_he_cap(sdata->u.mgd.flags,
+					pos, he_cap, pos + he_cap_size);
+	/* trim excess if any */
+	skb_trim(skb, skb->len - (pre_he_pos + he_cap_size - pos));
 
 	ieee80211_ie_build_he_6ghz_cap(sdata, skb);
 }
 
-static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
+static int ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
 {
 	struct ieee80211_local *local = sdata->local;
 	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
@@ -684,6 +686,7 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
 	enum nl80211_iftype iftype = ieee80211_vif_type_p2p(&sdata->vif);
 	const struct ieee80211_sband_iftype_data *iftd;
 	struct ieee80211_prep_tx_info info = {};
+	int ret;
 
 	/* we know it's writable, cast away the const */
 	if (assoc_data->ie_len)
@@ -697,7 +700,7 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
 	chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf);
 	if (WARN_ON(!chanctx_conf)) {
 		rcu_read_unlock();
-		return;
+		return -EINVAL;
 	}
 	chan = chanctx_conf->def.chan;
 	rcu_read_unlock();
@@ -748,7 +751,7 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
 			(iftd ? iftd->vendor_elems.len : 0),
 			GFP_KERNEL);
 	if (!skb)
-		return;
+		return -ENOMEM;
 
 	skb_reserve(skb, local->hw.extra_tx_headroom);
 
@@ -1029,15 +1032,22 @@ skip_rates:
 		skb_put_data(skb, assoc_data->ie + offset, noffset - offset);
 	}
 
-	if (assoc_data->fils_kek_len &&
-	    fils_encrypt_assoc_req(skb, assoc_data) < 0) {
-		dev_kfree_skb(skb);
-		return;
+	if (assoc_data->fils_kek_len) {
+		ret = fils_encrypt_assoc_req(skb, assoc_data);
+		if (ret < 0) {
+			dev_kfree_skb(skb);
+			return ret;
+		}
 	}
 
 	pos = skb_tail_pointer(skb);
 	kfree(ifmgd->assoc_req_ies);
 	ifmgd->assoc_req_ies = kmemdup(ie_start, pos - ie_start, GFP_ATOMIC);
+	if (!ifmgd->assoc_req_ies) {
+		dev_kfree_skb(skb);
+		return -ENOMEM;
+	}
+
 	ifmgd->assoc_req_ies_len = pos - ie_start;
 
 	drv_mgd_prepare_tx(local, sdata, &info);
@@ -1047,6 +1057,8 @@ skip_rates:
 		IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_CTL_REQ_TX_STATUS |
 						IEEE80211_TX_INTFL_MLME_CONN_TX;
 	ieee80211_tx_skb(sdata, skb);
+
+	return 0;
 }
 
 void ieee80211_send_pspoll(struct ieee80211_local *local,
@@ -2984,8 +2996,15 @@ static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata,
 		    (status_code == WLAN_STATUS_ANTI_CLOG_REQUIRED ||
 		     (auth_transaction == 1 &&
 		      (status_code == WLAN_STATUS_SAE_HASH_TO_ELEMENT ||
-		       status_code == WLAN_STATUS_SAE_PK))))
+		       status_code == WLAN_STATUS_SAE_PK)))) {
+			/* waiting for userspace now */
+			ifmgd->auth_data->waiting = true;
+			ifmgd->auth_data->timeout =
+				jiffies + IEEE80211_AUTH_WAIT_SAE_RETRY;
+			ifmgd->auth_data->timeout_started = true;
+			run_again(sdata, ifmgd->auth_data->timeout);
 			goto notify_driver;
+		}
 
 		sdata_info(sdata, "%pM denied authentication (status %d)\n",
 			   mgmt->sa, status_code);
@@ -4451,6 +4470,7 @@ static int ieee80211_do_assoc(struct ieee80211_sub_if_data *sdata)
 {
 	struct ieee80211_mgd_assoc_data *assoc_data = sdata->u.mgd.assoc_data;
 	struct ieee80211_local *local = sdata->local;
+	int ret;
 
 	sdata_assert_lock(sdata);
 
@@ -4471,7 +4491,9 @@ static int ieee80211_do_assoc(struct ieee80211_sub_if_data *sdata)
 	sdata_info(sdata, "associate with %pM (try %d/%d)\n",
 		   assoc_data->bss->bssid, assoc_data->tries,
 		   IEEE80211_ASSOC_MAX_TRIES);
-	ieee80211_send_assoc(sdata);
+	ret = ieee80211_send_assoc(sdata);
+	if (ret)
+		return ret;
 
 	if (!ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS)) {
 		assoc_data->timeout = jiffies + IEEE80211_ASSOC_TIMEOUT;
@@ -4544,10 +4566,10 @@ void ieee80211_sta_work(struct ieee80211_sub_if_data *sdata)
 
 	if (ifmgd->auth_data && ifmgd->auth_data->timeout_started &&
 	    time_after(jiffies, ifmgd->auth_data->timeout)) {
-		if (ifmgd->auth_data->done) {
+		if (ifmgd->auth_data->done || ifmgd->auth_data->waiting) {
 			/*
-			 * ok ... we waited for assoc but userspace didn't,
-			 * so let's just kill the auth data
+			 * ok ... we waited for assoc or continuation but
+			 * userspace didn't do it, so kill the auth data
 			 */
 			ieee80211_destroy_auth_data(sdata, false);
 		} else if (ieee80211_auth(sdata)) {
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 92ce173dd0c1..eab6283b3479 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -2602,7 +2602,8 @@ static void ieee80211_deliver_skb_to_local_stack(struct sk_buff *skb,
 		 * address, so that the authenticator (e.g. hostapd) will see
 		 * the frame, but bridge won't forward it anywhere else. Note
 		 * that due to earlier filtering, the only other address can
-		 * be the PAE group address.
+		 * be the PAE group address, unless the hardware allowed them
+		 * through in 802.3 offloaded mode.
 		 */
 		if (unlikely(skb->protocol == sdata->control_port_protocol &&
 			     !ether_addr_equal(ehdr->h_dest, sdata->vif.addr)))
@@ -2917,13 +2918,13 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx)
 	    ether_addr_equal(sdata->vif.addr, hdr->addr3))
 		return RX_CONTINUE;
 
-	ac = ieee80211_select_queue_80211(sdata, skb, hdr);
+	ac = ieee802_1d_to_ac[skb->priority];
 	q = sdata->vif.hw_queue[ac];
 	if (ieee80211_queue_stopped(&local->hw, q)) {
 		IEEE80211_IFSTA_MESH_CTR_INC(ifmsh, dropped_frames_congestion);
 		return RX_DROP_MONITOR;
 	}
-	skb_set_queue_mapping(skb, q);
+	skb_set_queue_mapping(skb, ac);
 
 	if (!--mesh_hdr->ttl) {
 		if (!is_multicast_ether_addr(hdr->addr1))
@@ -4518,12 +4519,7 @@ static void ieee80211_rx_8023(struct ieee80211_rx_data *rx,
 
 	/* deliver to local stack */
 	skb->protocol = eth_type_trans(skb, fast_rx->dev);
-	memset(skb->cb, 0, sizeof(skb->cb));
-	if (rx->list)
-		list_add_tail(&skb->list, rx->list);
-	else
-		netif_receive_skb(skb);
-
+	ieee80211_deliver_skb_to_local_stack(skb, rx);
 }
 
 static bool ieee80211_invoke_fast_rx(struct ieee80211_rx_data *rx,
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 2fe71ed9137b..be1911d8089f 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -1959,7 +1959,7 @@ static int ieee80211_build_preq_ies_band(struct ieee80211_sub_if_data *sdata,
 	if (he_cap &&
 	    cfg80211_any_usable_channels(local->hw.wiphy, BIT(sband->band),
 					 IEEE80211_CHAN_NO_HE)) {
-		pos = ieee80211_ie_build_he_cap(pos, he_cap, end);
+		pos = ieee80211_ie_build_he_cap(0, pos, he_cap, end);
 		if (!pos)
 			goto out_err;
 	}
@@ -2903,10 +2903,11 @@ u8 ieee80211_ie_len_he_cap(struct ieee80211_sub_if_data *sdata, u8 iftype)
 				     he_cap->he_cap_elem.phy_cap_info);
 }
 
-u8 *ieee80211_ie_build_he_cap(u8 *pos,
+u8 *ieee80211_ie_build_he_cap(u32 disable_flags, u8 *pos,
 			      const struct ieee80211_sta_he_cap *he_cap,
 			      u8 *end)
 {
+	struct ieee80211_he_cap_elem elem;
 	u8 n;
 	u8 ie_len;
 	u8 *orig_pos = pos;
@@ -2919,7 +2920,23 @@ u8 *ieee80211_ie_build_he_cap(u8 *pos,
 	if (!he_cap)
 		return orig_pos;
 
-	n = ieee80211_he_mcs_nss_size(&he_cap->he_cap_elem);
+	/* modify on stack first to calculate 'n' and 'ie_len' correctly */
+	elem = he_cap->he_cap_elem;
+
+	if (disable_flags & IEEE80211_STA_DISABLE_40MHZ)
+		elem.phy_cap_info[0] &=
+			~(IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G |
+			  IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G);
+
+	if (disable_flags & IEEE80211_STA_DISABLE_160MHZ)
+		elem.phy_cap_info[0] &=
+			~IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G;
+
+	if (disable_flags & IEEE80211_STA_DISABLE_80P80MHZ)
+		elem.phy_cap_info[0] &=
+			~IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G;
+
+	n = ieee80211_he_mcs_nss_size(&elem);
 	ie_len = 2 + 1 +
 		 sizeof(he_cap->he_cap_elem) + n +
 		 ieee80211_he_ppe_size(he_cap->ppe_thres[0],
@@ -2933,8 +2950,8 @@ u8 *ieee80211_ie_build_he_cap(u8 *pos,
 	*pos++ = WLAN_EID_EXT_HE_CAPABILITY;
 
 	/* Fixed data */
-	memcpy(pos, &he_cap->he_cap_elem, sizeof(he_cap->he_cap_elem));
-	pos += sizeof(he_cap->he_cap_elem);
+	memcpy(pos, &elem, sizeof(elem));
+	pos += sizeof(elem);
 
 	memcpy(pos, &he_cap->he_mcs_nss_supp, n);
 	pos += n;
diff --git a/net/mctp/Kconfig b/net/mctp/Kconfig
index 2cdf3d0a28c9..3a5c0e70da77 100644
--- a/net/mctp/Kconfig
+++ b/net/mctp/Kconfig
@@ -1,7 +1,7 @@
 
 menuconfig MCTP
 	depends on NET
-	tristate "MCTP core protocol support"
+	bool "MCTP core protocol support"
 	help
 	  Management Component Transport Protocol (MCTP) is an in-system
 	  protocol for communicating between management controllers and
@@ -11,3 +11,13 @@ menuconfig MCTP
 	  This option enables core MCTP support. For communicating with other
 	  devices, you'll want to enable a driver for a specific hardware
 	  channel.
+
+config MCTP_TEST
+        bool "MCTP core tests" if !KUNIT_ALL_TESTS
+        depends on MCTP=y && KUNIT=y
+        default KUNIT_ALL_TESTS
+
+config MCTP_FLOWS
+	bool
+	depends on MCTP
+	select SKB_EXTENSIONS
diff --git a/net/mctp/Makefile b/net/mctp/Makefile
index 0171333384d7..6cd55233e685 100644
--- a/net/mctp/Makefile
+++ b/net/mctp/Makefile
@@ -1,3 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-$(CONFIG_MCTP) += mctp.o
 mctp-objs := af_mctp.o device.o route.o neigh.o
+
+# tests
+obj-$(CONFIG_MCTP_TEST) += test/utils.o
diff --git a/net/mctp/af_mctp.c b/net/mctp/af_mctp.c
index 85cc1a28cbe9..f0702d920d8d 100644
--- a/net/mctp/af_mctp.c
+++ b/net/mctp/af_mctp.c
@@ -6,6 +6,7 @@
  * Copyright (c) 2021 Google
  */
 
+#include <linux/compat.h>
 #include <linux/if_arp.h>
 #include <linux/net.h>
 #include <linux/mctp.h>
@@ -16,8 +17,13 @@
 #include <net/mctpdevice.h>
 #include <net/sock.h>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/mctp.h>
+
 /* socket implementation */
 
+static void mctp_sk_expire_keys(struct timer_list *timer);
+
 static int mctp_release(struct socket *sock)
 {
 	struct sock *sk = sock->sk;
@@ -36,6 +42,13 @@ static bool mctp_sockaddr_is_ok(const struct sockaddr_mctp *addr)
 	return !addr->__smctp_pad0 && !addr->__smctp_pad1;
 }
 
+static bool mctp_sockaddr_ext_is_ok(const struct sockaddr_mctp_ext *addr)
+{
+	return !addr->__smctp_pad0[0] &&
+	       !addr->__smctp_pad0[1] &&
+	       !addr->__smctp_pad0[2];
+}
+
 static int mctp_bind(struct socket *sock, struct sockaddr *addr, int addrlen)
 {
 	struct sock *sk = sock->sk;
@@ -83,18 +96,26 @@ static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 	const int hlen = MCTP_HEADER_MAXLEN + sizeof(struct mctp_hdr);
 	int rc, addrlen = msg->msg_namelen;
 	struct sock *sk = sock->sk;
+	struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk);
 	struct mctp_skb_cb *cb;
 	struct mctp_route *rt;
 	struct sk_buff *skb;
 
 	if (addr) {
+		const u8 tagbits = MCTP_TAG_MASK | MCTP_TAG_OWNER |
+			MCTP_TAG_PREALLOC;
+
 		if (addrlen < sizeof(struct sockaddr_mctp))
 			return -EINVAL;
 		if (addr->smctp_family != AF_MCTP)
 			return -EINVAL;
 		if (!mctp_sockaddr_is_ok(addr))
 			return -EINVAL;
-		if (addr->smctp_tag & ~(MCTP_TAG_MASK | MCTP_TAG_OWNER))
+		if (addr->smctp_tag & ~tagbits)
+			return -EINVAL;
+		/* can't preallocate a non-owned tag */
+		if (addr->smctp_tag & MCTP_TAG_PREALLOC &&
+		    !(addr->smctp_tag & MCTP_TAG_OWNER))
 			return -EINVAL;
 
 	} else {
@@ -108,11 +129,6 @@ static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 	if (addr->smctp_network == MCTP_NET_ANY)
 		addr->smctp_network = mctp_default_net(sock_net(sk));
 
-	rt = mctp_route_lookup(sock_net(sk), addr->smctp_network,
-			       addr->smctp_addr.s_addr);
-	if (!rt)
-		return -EHOSTUNREACH;
-
 	skb = sock_alloc_send_skb(sk, hlen + 1 + len,
 				  msg->msg_flags & MSG_DONTWAIT, &rc);
 	if (!skb)
@@ -124,19 +140,46 @@ static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 	*(u8 *)skb_put(skb, 1) = addr->smctp_type;
 
 	rc = memcpy_from_msg((void *)skb_put(skb, len), msg, len);
-	if (rc < 0) {
-		kfree_skb(skb);
-		return rc;
-	}
+	if (rc < 0)
+		goto err_free;
 
 	/* set up cb */
 	cb = __mctp_cb(skb);
 	cb->net = addr->smctp_network;
 
+	/* direct addressing */
+	if (msk->addr_ext && addrlen >= sizeof(struct sockaddr_mctp_ext)) {
+		DECLARE_SOCKADDR(struct sockaddr_mctp_ext *,
+				 extaddr, msg->msg_name);
+
+		if (!mctp_sockaddr_ext_is_ok(extaddr) ||
+		    extaddr->smctp_halen > sizeof(cb->haddr)) {
+			rc = -EINVAL;
+			goto err_free;
+		}
+
+		cb->ifindex = extaddr->smctp_ifindex;
+		cb->halen = extaddr->smctp_halen;
+		memcpy(cb->haddr, extaddr->smctp_haddr, cb->halen);
+
+		rt = NULL;
+	} else {
+		rt = mctp_route_lookup(sock_net(sk), addr->smctp_network,
+				       addr->smctp_addr.s_addr);
+		if (!rt) {
+			rc = -EHOSTUNREACH;
+			goto err_free;
+		}
+	}
+
 	rc = mctp_local_output(sk, rt, skb, addr->smctp_addr.s_addr,
 			       addr->smctp_tag);
 
 	return rc ? : len;
+
+err_free:
+	kfree_skb(skb);
+	return rc;
 }
 
 static int mctp_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
@@ -144,6 +187,7 @@ static int mctp_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 {
 	DECLARE_SOCKADDR(struct sockaddr_mctp *, addr, msg->msg_name);
 	struct sock *sk = sock->sk;
+	struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk);
 	struct sk_buff *skb;
 	size_t msglen;
 	u8 type;
@@ -191,6 +235,17 @@ static int mctp_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 					(MCTP_HDR_TAG_MASK | MCTP_HDR_FLAG_TO);
 		addr->__smctp_pad1 = 0;
 		msg->msg_namelen = sizeof(*addr);
+
+		if (msk->addr_ext) {
+			DECLARE_SOCKADDR(struct sockaddr_mctp_ext *, ae,
+					 msg->msg_name);
+			msg->msg_namelen = sizeof(*ae);
+			ae->smctp_ifindex = cb->ifindex;
+			ae->smctp_halen = cb->halen;
+			memset(ae->__smctp_pad0, 0x0, sizeof(ae->__smctp_pad0));
+			memset(ae->smctp_haddr, 0x0, sizeof(ae->smctp_haddr));
+			memcpy(ae->smctp_haddr, cb->haddr, cb->halen);
+		}
 	}
 
 	rc = len;
@@ -203,18 +258,186 @@ out_free:
 	return rc;
 }
 
+/* We're done with the key; invalidate, stop reassembly, and remove from lists.
+ */
+static void __mctp_key_remove(struct mctp_sk_key *key, struct net *net,
+			      unsigned long flags, unsigned long reason)
+__releases(&key->lock)
+__must_hold(&net->mctp.keys_lock)
+{
+	struct sk_buff *skb;
+
+	trace_mctp_key_release(key, reason);
+	skb = key->reasm_head;
+	key->reasm_head = NULL;
+	key->reasm_dead = true;
+	key->valid = false;
+	mctp_dev_release_key(key->dev, key);
+	spin_unlock_irqrestore(&key->lock, flags);
+
+	hlist_del(&key->hlist);
+	hlist_del(&key->sklist);
+
+	/* unref for the lists */
+	mctp_key_unref(key);
+
+	kfree_skb(skb);
+}
+
 static int mctp_setsockopt(struct socket *sock, int level, int optname,
 			   sockptr_t optval, unsigned int optlen)
 {
-	return -EINVAL;
+	struct mctp_sock *msk = container_of(sock->sk, struct mctp_sock, sk);
+	int val;
+
+	if (level != SOL_MCTP)
+		return -EINVAL;
+
+	if (optname == MCTP_OPT_ADDR_EXT) {
+		if (optlen != sizeof(int))
+			return -EINVAL;
+		if (copy_from_sockptr(&val, optval, sizeof(int)))
+			return -EFAULT;
+		msk->addr_ext = val;
+		return 0;
+	}
+
+	return -ENOPROTOOPT;
 }
 
 static int mctp_getsockopt(struct socket *sock, int level, int optname,
 			   char __user *optval, int __user *optlen)
 {
+	struct mctp_sock *msk = container_of(sock->sk, struct mctp_sock, sk);
+	int len, val;
+
+	if (level != SOL_MCTP)
+		return -EINVAL;
+
+	if (get_user(len, optlen))
+		return -EFAULT;
+
+	if (optname == MCTP_OPT_ADDR_EXT) {
+		if (len != sizeof(int))
+			return -EINVAL;
+		val = !!msk->addr_ext;
+		if (copy_to_user(optval, &val, len))
+			return -EFAULT;
+		return 0;
+	}
+
 	return -EINVAL;
 }
 
+static int mctp_ioctl_alloctag(struct mctp_sock *msk, unsigned long arg)
+{
+	struct net *net = sock_net(&msk->sk);
+	struct mctp_sk_key *key = NULL;
+	struct mctp_ioc_tag_ctl ctl;
+	unsigned long flags;
+	u8 tag;
+
+	if (copy_from_user(&ctl, (void __user *)arg, sizeof(ctl)))
+		return -EFAULT;
+
+	if (ctl.tag)
+		return -EINVAL;
+
+	if (ctl.flags)
+		return -EINVAL;
+
+	key = mctp_alloc_local_tag(msk, ctl.peer_addr, MCTP_ADDR_ANY,
+				   true, &tag);
+	if (IS_ERR(key))
+		return PTR_ERR(key);
+
+	ctl.tag = tag | MCTP_TAG_OWNER | MCTP_TAG_PREALLOC;
+	if (copy_to_user((void __user *)arg, &ctl, sizeof(ctl))) {
+		spin_lock_irqsave(&key->lock, flags);
+		__mctp_key_remove(key, net, flags, MCTP_TRACE_KEY_DROPPED);
+		mctp_key_unref(key);
+		return -EFAULT;
+	}
+
+	mctp_key_unref(key);
+	return 0;
+}
+
+static int mctp_ioctl_droptag(struct mctp_sock *msk, unsigned long arg)
+{
+	struct net *net = sock_net(&msk->sk);
+	struct mctp_ioc_tag_ctl ctl;
+	unsigned long flags, fl2;
+	struct mctp_sk_key *key;
+	struct hlist_node *tmp;
+	int rc;
+	u8 tag;
+
+	if (copy_from_user(&ctl, (void __user *)arg, sizeof(ctl)))
+		return -EFAULT;
+
+	if (ctl.flags)
+		return -EINVAL;
+
+	/* Must be a local tag, TO set, preallocated */
+	if ((ctl.tag & ~MCTP_TAG_MASK) != (MCTP_TAG_OWNER | MCTP_TAG_PREALLOC))
+		return -EINVAL;
+
+	tag = ctl.tag & MCTP_TAG_MASK;
+	rc = -EINVAL;
+
+	spin_lock_irqsave(&net->mctp.keys_lock, flags);
+	hlist_for_each_entry_safe(key, tmp, &msk->keys, sklist) {
+		/* we do an irqsave here, even though we know the irq state,
+		 * so we have the flags to pass to __mctp_key_remove
+		 */
+		spin_lock_irqsave(&key->lock, fl2);
+		if (key->manual_alloc &&
+		    ctl.peer_addr == key->peer_addr &&
+		    tag == key->tag) {
+			__mctp_key_remove(key, net, fl2,
+					  MCTP_TRACE_KEY_DROPPED);
+			rc = 0;
+		} else {
+			spin_unlock_irqrestore(&key->lock, fl2);
+		}
+	}
+	spin_unlock_irqrestore(&net->mctp.keys_lock, flags);
+
+	return rc;
+}
+
+static int mctp_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
+{
+	struct mctp_sock *msk = container_of(sock->sk, struct mctp_sock, sk);
+
+	switch (cmd) {
+	case SIOCMCTPALLOCTAG:
+		return mctp_ioctl_alloctag(msk, arg);
+	case SIOCMCTPDROPTAG:
+		return mctp_ioctl_droptag(msk, arg);
+	}
+
+	return -EINVAL;
+}
+
+#ifdef CONFIG_COMPAT
+static int mctp_compat_ioctl(struct socket *sock, unsigned int cmd,
+			     unsigned long arg)
+{
+	void __user *argp = compat_ptr(arg);
+
+	switch (cmd) {
+	/* These have compatible ptr layouts */
+	case SIOCMCTPALLOCTAG:
+	case SIOCMCTPDROPTAG:
+		return mctp_ioctl(sock, cmd, (unsigned long)argp);
+	}
+
+	return -ENOIOCTLCMD;
+}
+#endif
+
 static const struct proto_ops mctp_dgram_ops = {
 	.family		= PF_MCTP,
 	.release	= mctp_release,
@@ -224,7 +447,7 @@ static const struct proto_ops mctp_dgram_ops = {
 	.accept		= sock_no_accept,
 	.getname	= sock_no_getname,
 	.poll		= datagram_poll,
-	.ioctl		= sock_no_ioctl,
+	.ioctl		= mctp_ioctl,
 	.gettstamp	= sock_gettstamp,
 	.listen		= sock_no_listen,
 	.shutdown	= sock_no_shutdown,
@@ -234,18 +457,67 @@ static const struct proto_ops mctp_dgram_ops = {
 	.recvmsg	= mctp_recvmsg,
 	.mmap		= sock_no_mmap,
 	.sendpage	= sock_no_sendpage,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= mctp_compat_ioctl,
+#endif
 };
 
+static void mctp_sk_expire_keys(struct timer_list *timer)
+{
+	struct mctp_sock *msk = container_of(timer, struct mctp_sock,
+					     key_expiry);
+	struct net *net = sock_net(&msk->sk);
+	unsigned long next_expiry, flags, fl2;
+	struct mctp_sk_key *key;
+	struct hlist_node *tmp;
+	bool next_expiry_valid = false;
+
+	spin_lock_irqsave(&net->mctp.keys_lock, flags);
+
+	hlist_for_each_entry_safe(key, tmp, &msk->keys, sklist) {
+		/* don't expire. manual_alloc is immutable, no locking
+		 * required.
+		 */
+		if (key->manual_alloc)
+			continue;
+
+		spin_lock_irqsave(&key->lock, fl2);
+		if (!time_after_eq(key->expiry, jiffies)) {
+			__mctp_key_remove(key, net, fl2,
+					  MCTP_TRACE_KEY_TIMEOUT);
+			continue;
+		}
+
+		if (next_expiry_valid) {
+			if (time_before(key->expiry, next_expiry))
+				next_expiry = key->expiry;
+		} else {
+			next_expiry = key->expiry;
+			next_expiry_valid = true;
+		}
+		spin_unlock_irqrestore(&key->lock, fl2);
+	}
+
+	spin_unlock_irqrestore(&net->mctp.keys_lock, flags);
+
+	if (next_expiry_valid)
+		mod_timer(timer, next_expiry);
+}
+
 static int mctp_sk_init(struct sock *sk)
 {
 	struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk);
 
 	INIT_HLIST_HEAD(&msk->keys);
+	timer_setup(&msk->key_expiry, mctp_sk_expire_keys, 0);
 	return 0;
 }
 
 static void mctp_sk_close(struct sock *sk, long timeout)
 {
+	struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk);
+
+	del_timer_sync(&msk->key_expiry);
 	sk_common_release(sk);
 }
 
@@ -264,9 +536,9 @@ static void mctp_sk_unhash(struct sock *sk)
 {
 	struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk);
 	struct net *net = sock_net(sk);
+	unsigned long flags, fl2;
 	struct mctp_sk_key *key;
 	struct hlist_node *tmp;
-	unsigned long flags;
 
 	/* remove from any type-based binds */
 	mutex_lock(&net->mctp.bind_lock);
@@ -276,21 +548,10 @@ static void mctp_sk_unhash(struct sock *sk)
 	/* remove tag allocations */
 	spin_lock_irqsave(&net->mctp.keys_lock, flags);
 	hlist_for_each_entry_safe(key, tmp, &msk->keys, sklist) {
-		hlist_del_rcu(&key->sklist);
-		hlist_del_rcu(&key->hlist);
-
-		spin_lock(&key->reasm_lock);
-		if (key->reasm_head)
-			kfree_skb(key->reasm_head);
-		key->reasm_head = NULL;
-		key->reasm_dead = true;
-		spin_unlock(&key->reasm_lock);
-
-		kfree_rcu(key, rcu);
+		spin_lock_irqsave(&key->lock, fl2);
+		__mctp_key_remove(key, net, fl2, MCTP_TRACE_KEY_CLOSED);
 	}
 	spin_unlock_irqrestore(&net->mctp.keys_lock, flags);
-
-	synchronize_rcu();
 }
 
 static struct proto mctp_proto = {
@@ -398,7 +659,7 @@ static __exit void mctp_exit(void)
 	sock_unregister(PF_MCTP);
 }
 
-module_init(mctp_init);
+subsys_initcall(mctp_init);
 module_exit(mctp_exit);
 
 MODULE_DESCRIPTION("MCTP core");
diff --git a/net/mctp/device.c b/net/mctp/device.c
index b9f38e765f61..ffcd7d8d2fb6 100644
--- a/net/mctp/device.c
+++ b/net/mctp/device.c
@@ -24,33 +24,48 @@ struct mctp_dump_cb {
 	size_t a_idx;
 };
 
-/* unlocked: caller must hold rcu_read_lock */
+/* unlocked: caller must hold rcu_read_lock.
+ * Returned mctp_dev has its refcount incremented, or NULL if unset.
+ */
 struct mctp_dev *__mctp_dev_get(const struct net_device *dev)
 {
-	return rcu_dereference(dev->mctp_ptr);
+	struct mctp_dev *mdev = rcu_dereference(dev->mctp_ptr);
+
+	/* RCU guarantees that any mdev is still live.
+	 * Zero refcount implies a pending free, return NULL.
+	 */
+	if (mdev)
+		if (!refcount_inc_not_zero(&mdev->refs))
+			return NULL;
+	return mdev;
 }
 
+/* Returned mctp_dev does not have refcount incremented. The returned pointer
+ * remains live while rtnl_lock is held, as that prevents mctp_unregister()
+ */
 struct mctp_dev *mctp_dev_get_rtnl(const struct net_device *dev)
 {
 	return rtnl_dereference(dev->mctp_ptr);
 }
 
-static void mctp_dev_destroy(struct mctp_dev *mdev)
+static int mctp_addrinfo_size(void)
 {
-	struct net_device *dev = mdev->dev;
-
-	dev_put(dev);
-	kfree_rcu(mdev, rcu);
+	return NLMSG_ALIGN(sizeof(struct ifaddrmsg))
+		+ nla_total_size(1) // IFA_LOCAL
+		+ nla_total_size(1) // IFA_ADDRESS
+		;
 }
 
-static int mctp_fill_addrinfo(struct sk_buff *skb, struct netlink_callback *cb,
-			      struct mctp_dev *mdev, mctp_eid_t eid)
+/* flag should be NLM_F_MULTI for dump calls */
+static int mctp_fill_addrinfo(struct sk_buff *skb,
+			      struct mctp_dev *mdev, mctp_eid_t eid,
+			      int msg_type, u32 portid, u32 seq, int flag)
 {
 	struct ifaddrmsg *hdr;
 	struct nlmsghdr *nlh;
 
-	nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
-			RTM_NEWADDR, sizeof(*hdr), NLM_F_MULTI);
+	nlh = nlmsg_put(skb, portid, seq,
+			msg_type, sizeof(*hdr), flag);
 	if (!nlh)
 		return -EMSGSIZE;
 
@@ -80,10 +95,14 @@ static int mctp_dump_dev_addrinfo(struct mctp_dev *mdev, struct sk_buff *skb,
 				  struct netlink_callback *cb)
 {
 	struct mctp_dump_cb *mcb = (void *)cb->ctx;
+	u32 portid, seq;
 	int rc = 0;
 
+	portid = NETLINK_CB(cb->skb).portid;
+	seq = cb->nlh->nlmsg_seq;
 	for (; mcb->a_idx < mdev->num_addrs; mcb->a_idx++) {
-		rc = mctp_fill_addrinfo(skb, cb, mdev, mdev->addrs[mcb->a_idx]);
+		rc = mctp_fill_addrinfo(skb, mdev, mdev->addrs[mcb->a_idx],
+					RTM_NEWADDR, portid, seq, NLM_F_MULTI);
 		if (rc < 0)
 			break;
 	}
@@ -100,7 +119,7 @@ static int mctp_dump_addrinfo(struct sk_buff *skb, struct netlink_callback *cb)
 	struct ifaddrmsg *hdr;
 	struct mctp_dev *mdev;
 	int ifindex;
-	int idx, rc;
+	int idx = 0, rc;
 
 	hdr = nlmsg_data(cb->nlh);
 	// filter by ifindex if requested
@@ -117,6 +136,7 @@ static int mctp_dump_addrinfo(struct sk_buff *skb, struct netlink_callback *cb)
 				if (mdev) {
 					rc = mctp_dump_dev_addrinfo(mdev,
 								    skb, cb);
+					mctp_dev_put(mdev);
 					// Error indicates full buffer, this
 					// callback will get retried.
 					if (rc < 0)
@@ -135,6 +155,32 @@ out:
 	return skb->len;
 }
 
+static void mctp_addr_notify(struct mctp_dev *mdev, mctp_eid_t eid, int msg_type,
+			     struct sk_buff *req_skb, struct nlmsghdr *req_nlh)
+{
+	u32 portid = NETLINK_CB(req_skb).portid;
+	struct net *net = dev_net(mdev->dev);
+	struct sk_buff *skb;
+	int rc = -ENOBUFS;
+
+	skb = nlmsg_new(mctp_addrinfo_size(), GFP_KERNEL);
+	if (!skb)
+		goto out;
+
+	rc = mctp_fill_addrinfo(skb, mdev, eid, msg_type,
+				portid, req_nlh->nlmsg_seq, 0);
+	if (rc < 0) {
+		WARN_ON_ONCE(rc == -EMSGSIZE);
+		goto out;
+	}
+
+	rtnl_notify(skb, net, portid, RTNLGRP_MCTP_IFADDR, req_nlh, GFP_KERNEL);
+	return;
+out:
+	kfree_skb(skb);
+	rtnl_set_sk_err(net, RTNLGRP_MCTP_IFADDR, rc);
+}
+
 static const struct nla_policy ifa_mctp_policy[IFA_MAX + 1] = {
 	[IFA_ADDRESS]		= { .type = NLA_U8 },
 	[IFA_LOCAL]		= { .type = NLA_U8 },
@@ -176,7 +222,7 @@ static int mctp_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (!mdev)
 		return -ENODEV;
 
-	if (!mctp_address_ok(addr->s_addr))
+	if (!mctp_address_unicast(addr->s_addr))
 		return -EINVAL;
 
 	/* Prevent duplicates. Under RTNL so don't need to lock for reading */
@@ -197,6 +243,7 @@ static int mctp_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 	kfree(tmp_addrs);
 
+	mctp_addr_notify(mdev, addr->s_addr, RTM_NEWADDR, skb, nlh);
 	mctp_route_add_local(mdev, addr->s_addr);
 
 	return 0;
@@ -252,9 +299,42 @@ static int mctp_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh,
 	mdev->num_addrs--;
 	spin_unlock_irqrestore(&mdev->addrs_lock, flags);
 
+	mctp_addr_notify(mdev, addr->s_addr, RTM_DELADDR, skb, nlh);
+
 	return 0;
 }
 
+void mctp_dev_hold(struct mctp_dev *mdev)
+{
+	refcount_inc(&mdev->refs);
+}
+
+void mctp_dev_put(struct mctp_dev *mdev)
+{
+	if (mdev && refcount_dec_and_test(&mdev->refs)) {
+		dev_put(mdev->dev);
+		kfree_rcu(mdev, rcu);
+	}
+}
+
+void mctp_dev_release_key(struct mctp_dev *dev, struct mctp_sk_key *key)
+	__must_hold(&key->lock)
+{
+	if (!dev)
+		return;
+	if (dev->ops && dev->ops->release_flow)
+		dev->ops->release_flow(dev, key);
+	key->dev = NULL;
+	mctp_dev_put(dev);
+}
+
+void mctp_dev_set_key(struct mctp_dev *dev, struct mctp_sk_key *key)
+	__must_hold(&key->lock)
+{
+	mctp_dev_hold(dev);
+	key->dev = dev;
+}
+
 static struct mctp_dev *mctp_add_dev(struct net_device *dev)
 {
 	struct mctp_dev *mdev;
@@ -270,7 +350,9 @@ static struct mctp_dev *mctp_add_dev(struct net_device *dev)
 	mdev->net = mctp_default_net(dev_net(dev));
 
 	/* associate to net_device */
+	refcount_set(&mdev->refs, 1);
 	rcu_assign_pointer(dev->mctp_ptr, mdev);
+
 	dev_hold(dev);
 	mdev->dev = dev;
 
@@ -301,6 +383,7 @@ static size_t mctp_get_link_af_size(const struct net_device *dev,
 	if (!mdev)
 		return 0;
 	ret = nla_total_size(4); /* IFLA_MCTP_NET */
+	mctp_dev_put(mdev);
 	return ret;
 }
 
@@ -330,12 +413,26 @@ static int mctp_set_link_af(struct net_device *dev, const struct nlattr *attr,
 	return 0;
 }
 
+/* Matches netdev types that should have MCTP handling */
+static bool mctp_known(struct net_device *dev)
+{
+	/* only register specific types (inc. NONE for TUN devices) */
+	return dev->type == ARPHRD_MCTP ||
+		   dev->type == ARPHRD_LOOPBACK ||
+		   dev->type == ARPHRD_NONE;
+}
+
 static void mctp_unregister(struct net_device *dev)
 {
 	struct mctp_dev *mdev;
 
 	mdev = mctp_dev_get_rtnl(dev);
-
+	if (mdev && !mctp_known(dev)) {
+		// Sanity check, should match what was set in mctp_register
+		netdev_warn(dev, "%s: BUG mctp_ptr set for unknown type %d",
+			    __func__, dev->type);
+		return;
+	}
 	if (!mdev)
 		return;
 
@@ -345,7 +442,7 @@ static void mctp_unregister(struct net_device *dev)
 	mctp_neigh_remove_dev(mdev);
 	kfree(mdev->addrs);
 
-	mctp_dev_destroy(mdev);
+	mctp_dev_put(mdev);
 }
 
 static int mctp_register(struct net_device *dev)
@@ -353,11 +450,17 @@ static int mctp_register(struct net_device *dev)
 	struct mctp_dev *mdev;
 
 	/* Already registered? */
-	if (rtnl_dereference(dev->mctp_ptr))
+	mdev = rtnl_dereference(dev->mctp_ptr);
+
+	if (mdev) {
+		if (!mctp_known(dev))
+			netdev_warn(dev, "%s: BUG mctp_ptr set for unknown type %d",
+				    __func__, dev->type);
 		return 0;
+	}
 
-	/* only register specific types; MCTP-specific and loopback for now */
-	if (dev->type != ARPHRD_MCTP && dev->type != ARPHRD_LOOPBACK)
+	/* only register specific types */
+	if (!mctp_known(dev))
 		return 0;
 
 	mdev = mctp_add_dev(dev);
@@ -387,6 +490,39 @@ static int mctp_dev_notify(struct notifier_block *this, unsigned long event,
 	return NOTIFY_OK;
 }
 
+static int mctp_register_netdevice(struct net_device *dev,
+				   const struct mctp_netdev_ops *ops)
+{
+	struct mctp_dev *mdev;
+
+	mdev = mctp_add_dev(dev);
+	if (IS_ERR(mdev))
+		return PTR_ERR(mdev);
+
+	mdev->ops = ops;
+
+	return register_netdevice(dev);
+}
+
+int mctp_register_netdev(struct net_device *dev,
+			 const struct mctp_netdev_ops *ops)
+{
+	int rc;
+
+	rtnl_lock();
+	rc = mctp_register_netdevice(dev, ops);
+	rtnl_unlock();
+
+	return rc;
+}
+EXPORT_SYMBOL_GPL(mctp_register_netdev);
+
+void mctp_unregister_netdev(struct net_device *dev)
+{
+	unregister_netdev(dev);
+}
+EXPORT_SYMBOL_GPL(mctp_unregister_netdev);
+
 static struct rtnl_af_ops mctp_af_ops = {
 	.family = AF_MCTP,
 	.fill_link_af = mctp_fill_link_af,
diff --git a/net/mctp/neigh.c b/net/mctp/neigh.c
index 90ed2f02d1fb..ffa0f9e0983f 100644
--- a/net/mctp/neigh.c
+++ b/net/mctp/neigh.c
@@ -47,7 +47,7 @@ static int mctp_neigh_add(struct mctp_dev *mdev, mctp_eid_t eid,
 	}
 	INIT_LIST_HEAD(&neigh->list);
 	neigh->dev = mdev;
-	dev_hold(neigh->dev->dev);
+	mctp_dev_hold(neigh->dev);
 	neigh->eid = eid;
 	neigh->source = source;
 	memcpy(neigh->ha, lladdr, lladdr_len);
@@ -63,7 +63,7 @@ static void __mctp_neigh_free(struct rcu_head *rcu)
 {
 	struct mctp_neigh *neigh = container_of(rcu, struct mctp_neigh, rcu);
 
-	dev_put(neigh->dev->dev);
+	mctp_dev_put(neigh->dev);
 	kfree(neigh);
 }
 
@@ -85,8 +85,8 @@ void mctp_neigh_remove_dev(struct mctp_dev *mdev)
 	mutex_unlock(&net->mctp.neigh_lock);
 }
 
-// TODO: add a "source" flag so netlink can only delete static neighbours?
-static int mctp_neigh_remove(struct mctp_dev *mdev, mctp_eid_t eid)
+static int mctp_neigh_remove(struct mctp_dev *mdev, mctp_eid_t eid,
+			     enum mctp_neigh_source source)
 {
 	struct net *net = dev_net(mdev->dev);
 	struct mctp_neigh *neigh, *tmp;
@@ -94,7 +94,8 @@ static int mctp_neigh_remove(struct mctp_dev *mdev, mctp_eid_t eid)
 
 	mutex_lock(&net->mctp.neigh_lock);
 	list_for_each_entry_safe(neigh, tmp, &net->mctp.neighbours, list) {
-		if (neigh->dev == mdev && neigh->eid == eid) {
+		if (neigh->dev == mdev && neigh->eid == eid &&
+		    neigh->source == source) {
 			list_del_rcu(&neigh->list);
 			/* TODO: immediate RTM_DELNEIGH */
 			call_rcu(&neigh->rcu, __mctp_neigh_free);
@@ -142,7 +143,7 @@ static int mctp_rtm_newneigh(struct sk_buff *skb, struct nlmsghdr *nlh,
 	}
 
 	eid = nla_get_u8(tb[NDA_DST]);
-	if (!mctp_address_ok(eid)) {
+	if (!mctp_address_unicast(eid)) {
 		NL_SET_ERR_MSG(extack, "Invalid neighbour EID");
 		return -EINVAL;
 	}
@@ -202,7 +203,7 @@ static int mctp_rtm_delneigh(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (!mdev)
 		return -ENODEV;
 
-	return mctp_neigh_remove(mdev, eid);
+	return mctp_neigh_remove(mdev, eid, MCTP_NEIGH_STATIC);
 }
 
 static int mctp_fill_neigh(struct sk_buff *skb, u32 portid, u32 seq, int event,
diff --git a/net/mctp/route.c b/net/mctp/route.c
index fb1bf4ec8529..ee548c46c78f 100644
--- a/net/mctp/route.c
+++ b/net/mctp/route.c
@@ -11,6 +11,7 @@
  */
 
 #include <linux/idr.h>
+#include <linux/kconfig.h>
 #include <linux/mctp.h>
 #include <linux/netdevice.h>
 #include <linux/rtnetlink.h>
@@ -23,7 +24,12 @@
 #include <net/netlink.h>
 #include <net/sock.h>
 
+#include <trace/events/mctp.h>
+
 static const unsigned int mctp_message_maxlen = 64 * 1024;
+static const unsigned long mctp_key_lifetime = 6 * CONFIG_HZ;
+
+static void mctp_flow_prepare_output(struct sk_buff *skb, struct mctp_dev *dev);
 
 /* route output callbacks */
 static int mctp_route_discard(struct mctp_route *route, struct sk_buff *skb)
@@ -58,8 +64,7 @@ static struct mctp_sock *mctp_lookup_bind(struct net *net, struct sk_buff *skb)
 		if (msk->bind_type != type)
 			continue;
 
-		if (msk->bind_addr != MCTP_ADDR_ANY &&
-		    msk->bind_addr != mh->dest)
+		if (!mctp_address_matches(msk->bind_addr, mh->dest))
 			continue;
 
 		return msk;
@@ -71,7 +76,7 @@ static struct mctp_sock *mctp_lookup_bind(struct net *net, struct sk_buff *skb)
 static bool mctp_key_match(struct mctp_sk_key *key, mctp_eid_t local,
 			   mctp_eid_t peer, u8 tag)
 {
-	if (key->local_addr != local)
+	if (!mctp_address_matches(key->local_addr, local))
 		return false;
 
 	if (key->peer_addr != peer)
@@ -83,25 +88,43 @@ static bool mctp_key_match(struct mctp_sk_key *key, mctp_eid_t local,
 	return true;
 }
 
+/* returns a key (with key->lock held, and refcounted), or NULL if no such
+ * key exists.
+ */
 static struct mctp_sk_key *mctp_lookup_key(struct net *net, struct sk_buff *skb,
-					   mctp_eid_t peer)
+					   mctp_eid_t peer,
+					   unsigned long *irqflags)
+	__acquires(&key->lock)
 {
 	struct mctp_sk_key *key, *ret;
+	unsigned long flags;
 	struct mctp_hdr *mh;
 	u8 tag;
 
-	WARN_ON(!rcu_read_lock_held());
-
 	mh = mctp_hdr(skb);
 	tag = mh->flags_seq_tag & (MCTP_HDR_TAG_MASK | MCTP_HDR_FLAG_TO);
 
 	ret = NULL;
+	spin_lock_irqsave(&net->mctp.keys_lock, flags);
 
-	hlist_for_each_entry_rcu(key, &net->mctp.keys, hlist) {
-		if (mctp_key_match(key, mh->dest, peer, tag)) {
+	hlist_for_each_entry(key, &net->mctp.keys, hlist) {
+		if (!mctp_key_match(key, mh->dest, peer, tag))
+			continue;
+
+		spin_lock(&key->lock);
+		if (key->valid) {
+			refcount_inc(&key->refs);
 			ret = key;
 			break;
 		}
+		spin_unlock(&key->lock);
+	}
+
+	if (ret) {
+		spin_unlock(&net->mctp.keys_lock);
+		*irqflags = flags;
+	} else {
+		spin_unlock_irqrestore(&net->mctp.keys_lock, flags);
 	}
 
 	return ret;
@@ -121,11 +144,30 @@ static struct mctp_sk_key *mctp_key_alloc(struct mctp_sock *msk,
 	key->local_addr = local;
 	key->tag = tag;
 	key->sk = &msk->sk;
-	spin_lock_init(&key->reasm_lock);
+	key->valid = true;
+	spin_lock_init(&key->lock);
+	refcount_set(&key->refs, 1);
 
 	return key;
 }
 
+void mctp_key_unref(struct mctp_sk_key *key)
+{
+	unsigned long flags;
+
+	if (!refcount_dec_and_test(&key->refs))
+		return;
+
+	/* even though no refs exist here, the lock allows us to stay
+	 * consistent with the locking requirement of mctp_dev_release_key
+	 */
+	spin_lock_irqsave(&key->lock, flags);
+	mctp_dev_release_key(key->dev, key);
+	spin_unlock_irqrestore(&key->lock, flags);
+
+	kfree(key);
+}
+
 static int mctp_key_add(struct mctp_sk_key *key, struct mctp_sock *msk)
 {
 	struct net *net = sock_net(&msk->sk);
@@ -138,12 +180,20 @@ static int mctp_key_add(struct mctp_sk_key *key, struct mctp_sock *msk)
 	hlist_for_each_entry(tmp, &net->mctp.keys, hlist) {
 		if (mctp_key_match(tmp, key->local_addr, key->peer_addr,
 				   key->tag)) {
-			rc = -EEXIST;
-			break;
+			spin_lock(&tmp->lock);
+			if (tmp->valid)
+				rc = -EEXIST;
+			spin_unlock(&tmp->lock);
+			if (rc)
+				break;
 		}
 	}
 
 	if (!rc) {
+		refcount_inc(&key->refs);
+		key->expiry = jiffies + mctp_key_lifetime;
+		timer_reduce(&msk->key_expiry, key->expiry);
+
 		hlist_add_head(&key->hlist, &net->mctp.keys);
 		hlist_add_head(&key->sklist, &msk->keys);
 	}
@@ -153,29 +203,78 @@ static int mctp_key_add(struct mctp_sk_key *key, struct mctp_sock *msk)
 	return rc;
 }
 
-/* Must be called with key->reasm_lock, which it will release. Will schedule
- * the key for an RCU free.
+/* Helper for mctp_route_input().
+ * We're done with the key; unlock and unref the key.
+ * For the usual case of automatic expiry we remove the key from lists.
+ * In the case that manual allocation is set on a key we release the lock
+ * and local ref, reset reassembly, but don't remove from lists.
  */
-static void __mctp_key_unlock_drop(struct mctp_sk_key *key, struct net *net,
-				   unsigned long flags)
-	__releases(&key->reasm_lock)
+static void __mctp_key_done_in(struct mctp_sk_key *key, struct net *net,
+			       unsigned long flags, unsigned long reason)
+__releases(&key->lock)
 {
 	struct sk_buff *skb;
 
+	trace_mctp_key_release(key, reason);
 	skb = key->reasm_head;
 	key->reasm_head = NULL;
-	key->reasm_dead = true;
-	spin_unlock_irqrestore(&key->reasm_lock, flags);
 
-	spin_lock_irqsave(&net->mctp.keys_lock, flags);
-	hlist_del_rcu(&key->hlist);
-	hlist_del_rcu(&key->sklist);
-	spin_unlock_irqrestore(&net->mctp.keys_lock, flags);
-	kfree_rcu(key, rcu);
+	if (!key->manual_alloc) {
+		key->reasm_dead = true;
+		key->valid = false;
+		mctp_dev_release_key(key->dev, key);
+	}
+	spin_unlock_irqrestore(&key->lock, flags);
 
-	if (skb)
-		kfree_skb(skb);
+	if (!key->manual_alloc) {
+		spin_lock_irqsave(&net->mctp.keys_lock, flags);
+		hlist_del(&key->hlist);
+		hlist_del(&key->sklist);
+		spin_unlock_irqrestore(&net->mctp.keys_lock, flags);
+
+		/* unref for the lists */
+		mctp_key_unref(key);
+	}
+
+	/* and one for the local reference */
+	mctp_key_unref(key);
+
+	kfree_skb(skb);
+}
+
+#ifdef CONFIG_MCTP_FLOWS
+static void mctp_skb_set_flow(struct sk_buff *skb, struct mctp_sk_key *key)
+{
+	struct mctp_flow *flow;
+
+	flow = skb_ext_add(skb, SKB_EXT_MCTP);
+	if (!flow)
+		return;
+
+	refcount_inc(&key->refs);
+	flow->key = key;
+}
+
+static void mctp_flow_prepare_output(struct sk_buff *skb, struct mctp_dev *dev)
+{
+	struct mctp_sk_key *key;
+	struct mctp_flow *flow;
+
+	flow = skb_ext_find(skb, SKB_EXT_MCTP);
+	if (!flow)
+		return;
+
+	key = flow->key;
+
+	if (WARN_ON(key->dev && key->dev != dev))
+		return;
+
+	mctp_dev_set_key(dev, key);
 }
+#else
+static void mctp_skb_set_flow(struct sk_buff *skb, struct mctp_sk_key *key) {}
+static void mctp_flow_prepare_output(struct sk_buff *skb, struct mctp_dev *dev) {}
+#endif
 
 static int mctp_frag_queue(struct mctp_sk_key *key, struct sk_buff *skb)
 {
@@ -248,8 +347,10 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb)
 
 	rcu_read_lock();
 
-	/* lookup socket / reasm context, exactly matching (src,dest,tag) */
-	key = mctp_lookup_key(net, skb, mh->src);
+	/* lookup socket / reasm context, exactly matching (src,dest,tag).
+	 * we hold a ref on the key, and key->lock held.
+	 */
+	key = mctp_lookup_key(net, skb, mh->src, &f);
 
 	if (flags & MCTP_HDR_FLAG_SOM) {
 		if (key) {
@@ -260,10 +361,12 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb)
 			 * key for reassembly - we'll create a more specific
 			 * one for future packets if required (ie, !EOM).
 			 */
-			key = mctp_lookup_key(net, skb, MCTP_ADDR_ANY);
+			key = mctp_lookup_key(net, skb, MCTP_ADDR_ANY, &f);
 			if (key) {
 				msk = container_of(key->sk,
 						   struct mctp_sock, sk);
+				spin_unlock_irqrestore(&key->lock, f);
+				mctp_key_unref(key);
 				key = NULL;
 			}
 		}
@@ -282,11 +385,12 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb)
 		if (flags & MCTP_HDR_FLAG_EOM) {
 			sock_queue_rcv_skb(&msk->sk, skb);
 			if (key) {
-				spin_lock_irqsave(&key->reasm_lock, f);
 				/* we've hit a pending reassembly; not much we
 				 * can do but drop it
 				 */
-				__mctp_key_unlock_drop(key, net, f);
+				__mctp_key_done_in(key, net, f,
+						   MCTP_TRACE_KEY_REPLIED);
+				key = NULL;
 			}
 			rc = 0;
 			goto out_unlock;
@@ -303,7 +407,7 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb)
 				goto out_unlock;
 			}
 
-			/* we can queue without the reasm lock here, as the
+			/* we can queue without the key lock here, as the
 			 * key isn't observable yet
 			 */
 			mctp_frag_queue(key, skb);
@@ -315,20 +419,25 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb)
 			 * this function.
 			 */
 			rc = mctp_key_add(key, msk);
-			if (rc)
+			if (rc) {
 				kfree(key);
+			} else {
+				trace_mctp_key_acquire(key);
 
-		} else {
-			/* existing key: start reassembly */
-			spin_lock_irqsave(&key->reasm_lock, f);
+				/* we don't need to release key->lock on exit */
+				mctp_key_unref(key);
+			}
+			key = NULL;
 
+		} else {
 			if (key->reasm_head || key->reasm_dead) {
 				/* duplicate start? drop everything */
-				__mctp_key_unlock_drop(key, net, f);
+				__mctp_key_done_in(key, net, f,
+						   MCTP_TRACE_KEY_INVALIDATED);
 				rc = -EEXIST;
+				key = NULL;
 			} else {
 				rc = mctp_frag_queue(key, skb);
-				spin_unlock_irqrestore(&key->reasm_lock, f);
 			}
 		}
 
@@ -337,8 +446,6 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb)
 		 * using the message-specific key
 		 */
 
-		spin_lock_irqsave(&key->reasm_lock, f);
-
 		/* we need to be continuing an existing reassembly... */
 		if (!key->reasm_head)
 			rc = -EINVAL;
@@ -351,9 +458,8 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb)
 		if (!rc && flags & MCTP_HDR_FLAG_EOM) {
 			sock_queue_rcv_skb(key->sk, key->reasm_head);
 			key->reasm_head = NULL;
-			__mctp_key_unlock_drop(key, net, f);
-		} else {
-			spin_unlock_irqrestore(&key->reasm_lock, f);
+			__mctp_key_done_in(key, net, f, MCTP_TRACE_KEY_REPLIED);
+			key = NULL;
 		}
 
 	} else {
@@ -363,6 +469,10 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb)
 
 out_unlock:
 	rcu_read_unlock();
+	if (key) {
+		spin_unlock_irqrestore(&key->lock, f);
+		mctp_key_unref(key);
+	}
 out:
 	if (rc)
 		kfree_skb(skb);
@@ -376,6 +486,7 @@ static unsigned int mctp_route_mtu(struct mctp_route *rt)
 
 static int mctp_route_output(struct mctp_route *route, struct sk_buff *skb)
 {
+	struct mctp_skb_cb *cb = mctp_cb(skb);
 	struct mctp_hdr *hdr = mctp_hdr(skb);
 	char daddr_buf[MAX_ADDR_LEN];
 	char *daddr = NULL;
@@ -390,17 +501,24 @@ static int mctp_route_output(struct mctp_route *route, struct sk_buff *skb)
 		return -EMSGSIZE;
 	}
 
-	/* If lookup fails let the device handle daddr==NULL */
-	if (mctp_neigh_lookup(route->dev, hdr->dest, daddr_buf) == 0)
-		daddr = daddr_buf;
+	if (cb->ifindex) {
+		/* direct route; use the hwaddr we stashed in sendmsg */
+		daddr = cb->haddr;
+	} else {
+		/* If lookup fails let the device handle daddr==NULL */
+		if (mctp_neigh_lookup(route->dev, hdr->dest, daddr_buf) == 0)
+			daddr = daddr_buf;
+	}
 
 	rc = dev_hard_header(skb, skb->dev, ntohs(skb->protocol),
 			     daddr, skb->dev->dev_addr, skb->len);
-	if (rc) {
+	if (rc < 0) {
 		kfree_skb(skb);
 		return -EHOSTUNREACH;
 	}
 
+	mctp_flow_prepare_output(skb, route->dev);
+
 	rc = dev_queue_xmit(skb);
 	if (rc)
 		rc = net_xmit_errno(rc);
@@ -412,7 +530,7 @@ static int mctp_route_output(struct mctp_route *route, struct sk_buff *skb)
 static void mctp_route_release(struct mctp_route *rt)
 {
 	if (refcount_dec_and_test(&rt->refs)) {
-		dev_put(rt->dev->dev);
+		mctp_dev_put(rt->dev);
 		kfree_rcu(rt, rcu);
 	}
 }
@@ -454,30 +572,38 @@ static void mctp_reserve_tag(struct net *net, struct mctp_sk_key *key,
 
 	lockdep_assert_held(&mns->keys_lock);
 
+	key->expiry = jiffies + mctp_key_lifetime;
+	timer_reduce(&msk->key_expiry, key->expiry);
+
 	/* we hold the net->key_lock here, allowing updates to both
 	 * then net and sk
 	 */
 	hlist_add_head_rcu(&key->hlist, &mns->keys);
 	hlist_add_head_rcu(&key->sklist, &msk->keys);
+	refcount_inc(&key->refs);
 }
 
 /* Allocate a locally-owned tag value for (saddr, daddr), and reserve
  * it for the socket msk
  */
-static int mctp_alloc_local_tag(struct mctp_sock *msk,
-				mctp_eid_t saddr, mctp_eid_t daddr, u8 *tagp)
+struct mctp_sk_key *mctp_alloc_local_tag(struct mctp_sock *msk,
+					 mctp_eid_t daddr, mctp_eid_t saddr,
+					 bool manual, u8 *tagp)
 {
 	struct net *net = sock_net(&msk->sk);
 	struct netns_mctp *mns = &net->mctp;
 	struct mctp_sk_key *key, *tmp;
 	unsigned long flags;
-	int rc = -EAGAIN;
 	u8 tagbits;
 
+	/* for NULL destination EIDs, we may get a response from any peer */
+	if (daddr == MCTP_ADDR_NULL)
+		daddr = MCTP_ADDR_ANY;
+
 	/* be optimistic, alloc now */
 	key = mctp_key_alloc(msk, saddr, daddr, 0, GFP_KERNEL);
 	if (!key)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	/* 8 possible tag values */
 	tagbits = 0xff;
@@ -488,14 +614,25 @@ static int mctp_alloc_local_tag(struct mctp_sock *msk,
 	 * tags. If we find a conflict, clear that bit from tagbits
 	 */
 	hlist_for_each_entry(tmp, &mns->keys, hlist) {
+		/* We can check the lookup fields (*_addr, tag) without the
+		 * lock held, they don't change over the lifetime of the key.
+		 */
+
 		/* if we don't own the tag, it can't conflict */
 		if (tmp->tag & MCTP_HDR_FLAG_TO)
 			continue;
 
-		if ((tmp->peer_addr == daddr ||
-		     tmp->peer_addr == MCTP_ADDR_ANY) &&
-		    tmp->local_addr == saddr)
+		if (!(mctp_address_matches(tmp->peer_addr, daddr) &&
+		      mctp_address_matches(tmp->local_addr, saddr)))
+			continue;
+
+		spin_lock(&tmp->lock);
+		/* key must still be valid. If we find a match, clear the
+		 * potential tag value
+		 */
+		if (tmp->valid)
 			tagbits &= ~(1 << tmp->tag);
+		spin_unlock(&tmp->lock);
 
 		if (!tagbits)
 			break;
@@ -504,16 +641,64 @@ static int mctp_alloc_local_tag(struct mctp_sock *msk,
 	if (tagbits) {
 		key->tag = __ffs(tagbits);
 		mctp_reserve_tag(net, key, msk);
+		trace_mctp_key_acquire(key);
+
+		key->manual_alloc = manual;
 		*tagp = key->tag;
-		rc = 0;
 	}
 
 	spin_unlock_irqrestore(&mns->keys_lock, flags);
 
-	if (!tagbits)
+	if (!tagbits) {
 		kfree(key);
+		return ERR_PTR(-EBUSY);
+	}
 
-	return rc;
+	return key;
+}
+
+static struct mctp_sk_key *mctp_lookup_prealloc_tag(struct mctp_sock *msk,
+						    mctp_eid_t daddr,
+						    u8 req_tag, u8 *tagp)
+{
+	struct net *net = sock_net(&msk->sk);
+	struct netns_mctp *mns = &net->mctp;
+	struct mctp_sk_key *key, *tmp;
+	unsigned long flags;
+
+	req_tag &= ~(MCTP_TAG_PREALLOC | MCTP_TAG_OWNER);
+	key = NULL;
+
+	spin_lock_irqsave(&mns->keys_lock, flags);
+
+	hlist_for_each_entry(tmp, &mns->keys, hlist) {
+		if (tmp->tag != req_tag)
+			continue;
+
+		if (!mctp_address_matches(tmp->peer_addr, daddr))
+			continue;
+
+		if (!tmp->manual_alloc)
+			continue;
+
+		spin_lock(&tmp->lock);
+		if (tmp->valid) {
+			key = tmp;
+			refcount_inc(&key->refs);
+			spin_unlock(&tmp->lock);
+			break;
+		}
+		spin_unlock(&tmp->lock);
+	}
+	spin_unlock_irqrestore(&mns->keys_lock, flags);
+
+	if (!key)
+		return ERR_PTR(-ENOENT);
+
+	if (tagp)
+		*tagp = key->tag;
+
+	return key;
 }
 
 /* routing lookups */
@@ -552,14 +737,18 @@ struct mctp_route *mctp_route_lookup(struct net *net, unsigned int dnet,
 	return rt;
 }
 
-/* sends a skb to rt and releases the route. */
-int mctp_do_route(struct mctp_route *rt, struct sk_buff *skb)
+static struct mctp_route *mctp_route_lookup_null(struct net *net,
+						 struct net_device *dev)
 {
-	int rc;
+	struct mctp_route *rt;
 
-	rc = rt->output(rt, skb);
-	mctp_route_release(rt);
-	return rc;
+	list_for_each_entry_rcu(rt, &net->mctp.routes, list) {
+		if (rt->dev->dev == dev && rt->type == RTN_LOCAL &&
+		    refcount_inc_not_zero(&rt->refs))
+			return rt;
+	}
+
+	return NULL;
 }
 
 static int mctp_do_fragment_route(struct mctp_route *rt, struct sk_buff *skb,
@@ -628,7 +817,7 @@ static int mctp_do_fragment_route(struct mctp_route *rt, struct sk_buff *skb,
 		/* copy message payload */
 		skb_copy_bits(skb, pos, skb_transport_header(skb2), size);
 
-		/* do route, but don't drop the rt reference */
+		/* do route */
 		rc = rt->output(rt, skb2);
 		if (rc)
 			break;
@@ -637,7 +826,6 @@ static int mctp_do_fragment_route(struct mctp_route *rt, struct sk_buff *skb,
 		pos += size;
 	}
 
-	mctp_route_release(rt);
 	consume_skb(skb);
 	return rc;
 }
@@ -647,15 +835,50 @@ int mctp_local_output(struct sock *sk, struct mctp_route *rt,
 {
 	struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk);
 	struct mctp_skb_cb *cb = mctp_cb(skb);
+	struct mctp_route tmp_rt = {0};
+	struct mctp_sk_key *key;
 	struct mctp_hdr *hdr;
 	unsigned long flags;
 	unsigned int mtu;
 	mctp_eid_t saddr;
+	bool ext_rt;
 	int rc;
 	u8 tag;
 
-	if (WARN_ON(!rt->dev))
+	rc = -ENODEV;
+
+	if (rt) {
+		ext_rt = false;
+		if (WARN_ON(!rt->dev))
+			goto out_release;
+
+	} else if (cb->ifindex) {
+		struct net_device *dev;
+
+		ext_rt = true;
+		rt = &tmp_rt;
+
+		rcu_read_lock();
+		dev = dev_get_by_index_rcu(sock_net(sk), cb->ifindex);
+		if (!dev) {
+			rcu_read_unlock();
+			return rc;
+		}
+		rt->dev = __mctp_dev_get(dev);
+		rcu_read_unlock();
+
+		if (!rt->dev)
+			goto out_release;
+
+		/* establish temporary route - we set up enough to keep
+		 * mctp_route_output happy
+		 */
+		rt->output = mctp_route_output;
+		rt->mtu = 0;
+
+	} else {
 		return -EINVAL;
+	}
 
 	spin_lock_irqsave(&rt->dev->addrs_lock, flags);
 	if (rt->dev->num_addrs == 0) {
@@ -668,18 +891,29 @@ int mctp_local_output(struct sock *sk, struct mctp_route *rt,
 	spin_unlock_irqrestore(&rt->dev->addrs_lock, flags);
 
 	if (rc)
-		return rc;
+		goto out_release;
 
-	if (req_tag & MCTP_HDR_FLAG_TO) {
-		rc = mctp_alloc_local_tag(msk, saddr, daddr, &tag);
-		if (rc)
-			return rc;
+	if (req_tag & MCTP_TAG_OWNER) {
+		if (req_tag & MCTP_TAG_PREALLOC)
+			key = mctp_lookup_prealloc_tag(msk, daddr,
+						       req_tag, &tag);
+		else
+			key = mctp_alloc_local_tag(msk, daddr, saddr,
+						   false, &tag);
+
+		if (IS_ERR(key)) {
+			rc = PTR_ERR(key);
+			goto out_release;
+		}
+		mctp_skb_set_flow(skb, key);
+		/* done with the key in this scope */
+		mctp_key_unref(key);
 		tag |= MCTP_HDR_FLAG_TO;
 	} else {
-		tag = req_tag;
+		key = NULL;
+		tag = req_tag & MCTP_TAG_MASK;
 	}
 
-
 	skb->protocol = htons(ETH_P_MCTP);
 	skb->priority = 0;
 	skb_reset_transport_header(skb);
@@ -699,12 +933,20 @@ int mctp_local_output(struct sock *sk, struct mctp_route *rt,
 	mtu = mctp_route_mtu(rt);
 
 	if (skb->len + sizeof(struct mctp_hdr) <= mtu) {
-		hdr->flags_seq_tag = MCTP_HDR_FLAG_SOM | MCTP_HDR_FLAG_EOM |
-			tag;
-		return mctp_do_route(rt, skb);
+		hdr->flags_seq_tag = MCTP_HDR_FLAG_SOM |
+			MCTP_HDR_FLAG_EOM | tag;
+		rc = rt->output(rt, skb);
 	} else {
-		return mctp_do_fragment_route(rt, skb, mtu, tag);
+		rc = mctp_do_fragment_route(rt, skb, mtu, tag);
 	}
+
+out_release:
+	if (!ext_rt)
+		mctp_route_release(rt);
+
+	mctp_dev_put(tmp_rt.dev);
+
+	return rc;
 }
 
 /* route management */
@@ -716,7 +958,7 @@ static int mctp_route_add(struct mctp_dev *mdev, mctp_eid_t daddr_start,
 	struct net *net = dev_net(mdev->dev);
 	struct mctp_route *rt, *ert;
 
-	if (!mctp_address_ok(daddr_start))
+	if (!mctp_address_unicast(daddr_start))
 		return -EINVAL;
 
 	if (daddr_extent > 0xff || daddr_start + daddr_extent >= 255)
@@ -741,7 +983,7 @@ static int mctp_route_add(struct mctp_dev *mdev, mctp_eid_t daddr_start,
 	rt->max = daddr_start + daddr_extent;
 	rt->mtu = mtu;
 	rt->dev = mdev;
-	dev_hold(rt->dev->dev);
+	mctp_dev_hold(rt->dev);
 	rt->type = type;
 	rt->output = rtfn;
 
@@ -822,13 +1064,18 @@ static int mctp_pkttype_receive(struct sk_buff *skb, struct net_device *dev,
 				struct net_device *orig_dev)
 {
 	struct net *net = dev_net(dev);
+	struct mctp_dev *mdev;
 	struct mctp_skb_cb *cb;
 	struct mctp_route *rt;
 	struct mctp_hdr *mh;
 
-	/* basic non-data sanity checks */
-	if (dev->type != ARPHRD_MCTP)
+	rcu_read_lock();
+	mdev = __mctp_dev_get(dev);
+	rcu_read_unlock();
+	if (!mdev) {
+		/* basic non-data sanity checks */
 		goto err_drop;
+	}
 
 	if (!pskb_may_pull(skb, sizeof(struct mctp_hdr)))
 		goto err_drop;
@@ -841,21 +1088,45 @@ static int mctp_pkttype_receive(struct sk_buff *skb, struct net_device *dev,
 	if (mh->ver < MCTP_VER_MIN || mh->ver > MCTP_VER_MAX)
 		goto err_drop;
 
-	cb = __mctp_cb(skb);
-	rcu_read_lock();
-	cb->net = READ_ONCE(__mctp_dev_get(dev)->net);
-	rcu_read_unlock();
+	/* source must be valid unicast or null; drop reserved ranges and
+	 * broadcast
+	 */
+	if (!(mctp_address_unicast(mh->src) || mctp_address_null(mh->src)))
+		goto err_drop;
+
+	/* dest address: as above, but allow broadcast */
+	if (!(mctp_address_unicast(mh->dest) || mctp_address_null(mh->dest) ||
+	      mctp_address_broadcast(mh->dest)))
+		goto err_drop;
+
+	/* MCTP drivers must populate halen/haddr */
+	if (dev->type == ARPHRD_MCTP) {
+		cb = mctp_cb(skb);
+	} else {
+		cb = __mctp_cb(skb);
+		cb->halen = 0;
+	}
+	cb->net = READ_ONCE(mdev->net);
+	cb->ifindex = dev->ifindex;
 
 	rt = mctp_route_lookup(net, cb->net, mh->dest);
+
+	/* NULL EID, but addressed to our physical address */
+	if (!rt && mh->dest == MCTP_ADDR_NULL && skb->pkt_type == PACKET_HOST)
+		rt = mctp_route_lookup_null(net, dev);
+
 	if (!rt)
 		goto err_drop;
 
-	mctp_do_route(rt, skb);
+	rt->output(rt, skb);
+	mctp_route_release(rt);
+	mctp_dev_put(mdev);
 
 	return NET_RX_SUCCESS;
 
 err_drop:
 	kfree_skb(skb);
+	mctp_dev_put(mdev);
 	return NET_RX_DROP;
 }
 
@@ -927,10 +1198,15 @@ static int mctp_route_nlparse(struct sk_buff *skb, struct nlmsghdr *nlh,
 	return 0;
 }
 
+static const struct nla_policy rta_metrics_policy[RTAX_MAX + 1] = {
+	[RTAX_MTU]		= { .type = NLA_U32 },
+};
+
 static int mctp_newroute(struct sk_buff *skb, struct nlmsghdr *nlh,
 			 struct netlink_ext_ack *extack)
 {
 	struct nlattr *tb[RTA_MAX + 1];
+	struct nlattr *tbx[RTAX_MAX + 1];
 	mctp_eid_t daddr_start;
 	struct mctp_dev *mdev;
 	struct rtmsg *rtm;
@@ -947,8 +1223,15 @@ static int mctp_newroute(struct sk_buff *skb, struct nlmsghdr *nlh,
 		return -EINVAL;
 	}
 
-	/* TODO: parse mtu from nlparse */
 	mtu = 0;
+	if (tb[RTA_METRICS]) {
+		rc = nla_parse_nested(tbx, RTAX_MAX, tb[RTA_METRICS],
+				      rta_metrics_policy, NULL);
+		if (rc < 0)
+			return rc;
+		if (tbx[RTAX_MTU])
+			mtu = nla_get_u32(tbx[RTAX_MTU]);
+	}
 
 	if (rtm->rtm_type != RTN_UNICAST)
 		return -EINVAL;
@@ -1117,3 +1400,7 @@ void __exit mctp_routes_exit(void)
 	rtnl_unregister(PF_MCTP, RTM_GETROUTE);
 	dev_remove_pack(&mctp_packet_type);
 }
+
+#if IS_ENABLED(CONFIG_MCTP_TEST)
+#include "test/route-test.c"
+#endif
diff --git a/net/mctp/test/route-test.c b/net/mctp/test/route-test.c
new file mode 100644
index 000000000000..61205cf40074
--- /dev/null
+++ b/net/mctp/test/route-test.c
@@ -0,0 +1,684 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <kunit/test.h>
+
+#include "utils.h"
+
+struct mctp_test_route {
+	struct mctp_route	rt;
+	struct sk_buff_head	pkts;
+};
+
+static int mctp_test_route_output(struct mctp_route *rt, struct sk_buff *skb)
+{
+	struct mctp_test_route *test_rt = container_of(rt, struct mctp_test_route, rt);
+
+	skb_queue_tail(&test_rt->pkts, skb);
+
+	return 0;
+}
+
+/* local version of mctp_route_alloc() */
+static struct mctp_test_route *mctp_route_test_alloc(void)
+{
+	struct mctp_test_route *rt;
+
+	rt = kzalloc(sizeof(*rt), GFP_KERNEL);
+	if (!rt)
+		return NULL;
+
+	INIT_LIST_HEAD(&rt->rt.list);
+	refcount_set(&rt->rt.refs, 1);
+	rt->rt.output = mctp_test_route_output;
+
+	skb_queue_head_init(&rt->pkts);
+
+	return rt;
+}
+
+static struct mctp_test_route *mctp_test_create_route(struct net *net,
+						      struct mctp_dev *dev,
+						      mctp_eid_t eid,
+						      unsigned int mtu)
+{
+	struct mctp_test_route *rt;
+
+	rt = mctp_route_test_alloc();
+	if (!rt)
+		return NULL;
+
+	rt->rt.min = eid;
+	rt->rt.max = eid;
+	rt->rt.mtu = mtu;
+	rt->rt.type = RTN_UNSPEC;
+	if (dev)
+		mctp_dev_hold(dev);
+	rt->rt.dev = dev;
+
+	list_add_rcu(&rt->rt.list, &net->mctp.routes);
+
+	return rt;
+}
+
+static void mctp_test_route_destroy(struct kunit *test,
+				    struct mctp_test_route *rt)
+{
+	unsigned int refs;
+
+	rtnl_lock();
+	list_del_rcu(&rt->rt.list);
+	rtnl_unlock();
+
+	skb_queue_purge(&rt->pkts);
+	if (rt->rt.dev)
+		mctp_dev_put(rt->rt.dev);
+
+	refs = refcount_read(&rt->rt.refs);
+	KUNIT_ASSERT_EQ_MSG(test, refs, 1, "route ref imbalance");
+
+	kfree_rcu(&rt->rt, rcu);
+}
+
+static struct sk_buff *mctp_test_create_skb(const struct mctp_hdr *hdr,
+					    unsigned int data_len)
+{
+	size_t hdr_len = sizeof(*hdr);
+	struct sk_buff *skb;
+	unsigned int i;
+	u8 *buf;
+
+	skb = alloc_skb(hdr_len + data_len, GFP_KERNEL);
+	if (!skb)
+		return NULL;
+
+	memcpy(skb_put(skb, hdr_len), hdr, hdr_len);
+
+	buf = skb_put(skb, data_len);
+	for (i = 0; i < data_len; i++)
+		buf[i] = i & 0xff;
+
+	return skb;
+}
+
+static struct sk_buff *__mctp_test_create_skb_data(const struct mctp_hdr *hdr,
+						   const void *data,
+						   size_t data_len)
+{
+	size_t hdr_len = sizeof(*hdr);
+	struct sk_buff *skb;
+
+	skb = alloc_skb(hdr_len + data_len, GFP_KERNEL);
+	if (!skb)
+		return NULL;
+
+	memcpy(skb_put(skb, hdr_len), hdr, hdr_len);
+	memcpy(skb_put(skb, data_len), data, data_len);
+
+	return skb;
+}
+
+#define mctp_test_create_skb_data(h, d) \
+	__mctp_test_create_skb_data(h, d, sizeof(*d))
+
+struct mctp_frag_test {
+	unsigned int mtu;
+	unsigned int msgsize;
+	unsigned int n_frags;
+};
+
+static void mctp_test_fragment(struct kunit *test)
+{
+	const struct mctp_frag_test *params;
+	int rc, i, n, mtu, msgsize;
+	struct mctp_test_route *rt;
+	struct sk_buff *skb;
+	struct mctp_hdr hdr;
+	u8 seq;
+
+	params = test->param_value;
+	mtu = params->mtu;
+	msgsize = params->msgsize;
+
+	hdr.ver = 1;
+	hdr.src = 8;
+	hdr.dest = 10;
+	hdr.flags_seq_tag = MCTP_HDR_FLAG_TO;
+
+	skb = mctp_test_create_skb(&hdr, msgsize);
+	KUNIT_ASSERT_TRUE(test, skb);
+
+	rt = mctp_test_create_route(&init_net, NULL, 10, mtu);
+	KUNIT_ASSERT_TRUE(test, rt);
+
+	rc = mctp_do_fragment_route(&rt->rt, skb, mtu, MCTP_TAG_OWNER);
+	KUNIT_EXPECT_FALSE(test, rc);
+
+	n = rt->pkts.qlen;
+
+	KUNIT_EXPECT_EQ(test, n, params->n_frags);
+
+	for (i = 0;; i++) {
+		struct mctp_hdr *hdr2;
+		struct sk_buff *skb2;
+		u8 tag_mask, seq2;
+		bool first, last;
+
+		first = i == 0;
+		last = i == (n - 1);
+
+		skb2 = skb_dequeue(&rt->pkts);
+
+		if (!skb2)
+			break;
+
+		hdr2 = mctp_hdr(skb2);
+
+		tag_mask = MCTP_HDR_TAG_MASK | MCTP_HDR_FLAG_TO;
+
+		KUNIT_EXPECT_EQ(test, hdr2->ver, hdr.ver);
+		KUNIT_EXPECT_EQ(test, hdr2->src, hdr.src);
+		KUNIT_EXPECT_EQ(test, hdr2->dest, hdr.dest);
+		KUNIT_EXPECT_EQ(test, hdr2->flags_seq_tag & tag_mask,
+				hdr.flags_seq_tag & tag_mask);
+
+		KUNIT_EXPECT_EQ(test,
+				!!(hdr2->flags_seq_tag & MCTP_HDR_FLAG_SOM), first);
+		KUNIT_EXPECT_EQ(test,
+				!!(hdr2->flags_seq_tag & MCTP_HDR_FLAG_EOM), last);
+
+		seq2 = (hdr2->flags_seq_tag >> MCTP_HDR_SEQ_SHIFT) &
+			MCTP_HDR_SEQ_MASK;
+
+		if (first) {
+			seq = seq2;
+		} else {
+			seq++;
+			KUNIT_EXPECT_EQ(test, seq2, seq & MCTP_HDR_SEQ_MASK);
+		}
+
+		if (!last)
+			KUNIT_EXPECT_EQ(test, skb2->len, mtu);
+		else
+			KUNIT_EXPECT_LE(test, skb2->len, mtu);
+
+		kfree_skb(skb2);
+	}
+
+	mctp_test_route_destroy(test, rt);
+}
+
+static const struct mctp_frag_test mctp_frag_tests[] = {
+	{.mtu = 68, .msgsize = 63, .n_frags = 1},
+	{.mtu = 68, .msgsize = 64, .n_frags = 1},
+	{.mtu = 68, .msgsize = 65, .n_frags = 2},
+	{.mtu = 68, .msgsize = 66, .n_frags = 2},
+	{.mtu = 68, .msgsize = 127, .n_frags = 2},
+	{.mtu = 68, .msgsize = 128, .n_frags = 2},
+	{.mtu = 68, .msgsize = 129, .n_frags = 3},
+	{.mtu = 68, .msgsize = 130, .n_frags = 3},
+};
+
+static void mctp_frag_test_to_desc(const struct mctp_frag_test *t, char *desc)
+{
+	sprintf(desc, "mtu %d len %d -> %d frags",
+		t->msgsize, t->mtu, t->n_frags);
+}
+
+KUNIT_ARRAY_PARAM(mctp_frag, mctp_frag_tests, mctp_frag_test_to_desc);
+
+struct mctp_rx_input_test {
+	struct mctp_hdr hdr;
+	bool input;
+};
+
+static void mctp_test_rx_input(struct kunit *test)
+{
+	const struct mctp_rx_input_test *params;
+	struct mctp_test_route *rt;
+	struct mctp_test_dev *dev;
+	struct sk_buff *skb;
+
+	params = test->param_value;
+
+	dev = mctp_test_create_dev();
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, dev);
+
+	rt = mctp_test_create_route(&init_net, dev->mdev, 8, 68);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, rt);
+
+	skb = mctp_test_create_skb(&params->hdr, 1);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, skb);
+
+	__mctp_cb(skb);
+
+	mctp_pkttype_receive(skb, dev->ndev, &mctp_packet_type, NULL);
+
+	KUNIT_EXPECT_EQ(test, !!rt->pkts.qlen, params->input);
+
+	mctp_test_route_destroy(test, rt);
+	mctp_test_destroy_dev(dev);
+}
+
+#define RX_HDR(_ver, _src, _dest, _fst) \
+	{ .ver = _ver, .src = _src, .dest = _dest, .flags_seq_tag = _fst }
+
+/* we have a route for EID 8 only */
+static const struct mctp_rx_input_test mctp_rx_input_tests[] = {
+	{ .hdr = RX_HDR(1, 10, 8, 0), .input = true },
+	{ .hdr = RX_HDR(1, 10, 9, 0), .input = false }, /* no input route */
+	{ .hdr = RX_HDR(2, 10, 8, 0), .input = false }, /* invalid version */
+};
+
+static void mctp_rx_input_test_to_desc(const struct mctp_rx_input_test *t,
+				       char *desc)
+{
+	sprintf(desc, "{%x,%x,%x,%x}", t->hdr.ver, t->hdr.src, t->hdr.dest,
+		t->hdr.flags_seq_tag);
+}
+
+KUNIT_ARRAY_PARAM(mctp_rx_input, mctp_rx_input_tests,
+		  mctp_rx_input_test_to_desc);
+
+/* set up a local dev, route on EID 8, and a socket listening on type 0 */
+static void __mctp_route_test_init(struct kunit *test,
+				   struct mctp_test_dev **devp,
+				   struct mctp_test_route **rtp,
+				   struct socket **sockp)
+{
+	struct sockaddr_mctp addr = {0};
+	struct mctp_test_route *rt;
+	struct mctp_test_dev *dev;
+	struct socket *sock;
+	int rc;
+
+	dev = mctp_test_create_dev();
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, dev);
+
+	rt = mctp_test_create_route(&init_net, dev->mdev, 8, 68);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, rt);
+
+	rc = sock_create_kern(&init_net, AF_MCTP, SOCK_DGRAM, 0, &sock);
+	KUNIT_ASSERT_EQ(test, rc, 0);
+
+	addr.smctp_family = AF_MCTP;
+	addr.smctp_network = MCTP_NET_ANY;
+	addr.smctp_addr.s_addr = 8;
+	addr.smctp_type = 0;
+	rc = kernel_bind(sock, (struct sockaddr *)&addr, sizeof(addr));
+	KUNIT_ASSERT_EQ(test, rc, 0);
+
+	*rtp = rt;
+	*devp = dev;
+	*sockp = sock;
+}
+
+static void __mctp_route_test_fini(struct kunit *test,
+				   struct mctp_test_dev *dev,
+				   struct mctp_test_route *rt,
+				   struct socket *sock)
+{
+	sock_release(sock);
+	mctp_test_route_destroy(test, rt);
+	mctp_test_destroy_dev(dev);
+}
+
+struct mctp_route_input_sk_test {
+	struct mctp_hdr hdr;
+	u8 type;
+	bool deliver;
+};
+
+static void mctp_test_route_input_sk(struct kunit *test)
+{
+	const struct mctp_route_input_sk_test *params;
+	struct sk_buff *skb, *skb2;
+	struct mctp_test_route *rt;
+	struct mctp_test_dev *dev;
+	struct socket *sock;
+	int rc;
+
+	params = test->param_value;
+
+	__mctp_route_test_init(test, &dev, &rt, &sock);
+
+	skb = mctp_test_create_skb_data(&params->hdr, &params->type);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, skb);
+
+	skb->dev = dev->ndev;
+	__mctp_cb(skb);
+
+	rc = mctp_route_input(&rt->rt, skb);
+
+	if (params->deliver) {
+		KUNIT_EXPECT_EQ(test, rc, 0);
+
+		skb2 = skb_recv_datagram(sock->sk, 0, 1, &rc);
+		KUNIT_EXPECT_NOT_ERR_OR_NULL(test, skb2);
+		KUNIT_EXPECT_EQ(test, skb->len, 1);
+
+		skb_free_datagram(sock->sk, skb2);
+
+	} else {
+		KUNIT_EXPECT_NE(test, rc, 0);
+		skb2 = skb_recv_datagram(sock->sk, 0, 1, &rc);
+		KUNIT_EXPECT_PTR_EQ(test, skb2, NULL);
+	}
+
+	__mctp_route_test_fini(test, dev, rt, sock);
+}
+
+#define FL_S	(MCTP_HDR_FLAG_SOM)
+#define FL_E	(MCTP_HDR_FLAG_EOM)
+#define FL_TO	(MCTP_HDR_FLAG_TO)
+#define FL_T(t)	((t) & MCTP_HDR_TAG_MASK)
+
+static const struct mctp_route_input_sk_test mctp_route_input_sk_tests[] = {
+	{ .hdr = RX_HDR(1, 10, 8, FL_S | FL_E | FL_TO), .type = 0, .deliver = true },
+	{ .hdr = RX_HDR(1, 10, 8, FL_S | FL_E | FL_TO), .type = 1, .deliver = false },
+	{ .hdr = RX_HDR(1, 10, 8, FL_S | FL_E), .type = 0, .deliver = false },
+	{ .hdr = RX_HDR(1, 10, 8, FL_E | FL_TO), .type = 0, .deliver = false },
+	{ .hdr = RX_HDR(1, 10, 8, FL_TO), .type = 0, .deliver = false },
+	{ .hdr = RX_HDR(1, 10, 8, 0), .type = 0, .deliver = false },
+};
+
+static void mctp_route_input_sk_to_desc(const struct mctp_route_input_sk_test *t,
+					char *desc)
+{
+	sprintf(desc, "{%x,%x,%x,%x} type %d", t->hdr.ver, t->hdr.src,
+		t->hdr.dest, t->hdr.flags_seq_tag, t->type);
+}
+
+KUNIT_ARRAY_PARAM(mctp_route_input_sk, mctp_route_input_sk_tests,
+		  mctp_route_input_sk_to_desc);
+
+struct mctp_route_input_sk_reasm_test {
+	const char *name;
+	struct mctp_hdr hdrs[4];
+	int n_hdrs;
+	int rx_len;
+};
+
+static void mctp_test_route_input_sk_reasm(struct kunit *test)
+{
+	const struct mctp_route_input_sk_reasm_test *params;
+	struct sk_buff *skb, *skb2;
+	struct mctp_test_route *rt;
+	struct mctp_test_dev *dev;
+	struct socket *sock;
+	int i, rc;
+	u8 c;
+
+	params = test->param_value;
+
+	__mctp_route_test_init(test, &dev, &rt, &sock);
+
+	for (i = 0; i < params->n_hdrs; i++) {
+		c = i;
+		skb = mctp_test_create_skb_data(&params->hdrs[i], &c);
+		KUNIT_ASSERT_NOT_ERR_OR_NULL(test, skb);
+
+		skb->dev = dev->ndev;
+		__mctp_cb(skb);
+
+		rc = mctp_route_input(&rt->rt, skb);
+	}
+
+	skb2 = skb_recv_datagram(sock->sk, 0, 1, &rc);
+
+	if (params->rx_len) {
+		KUNIT_EXPECT_NOT_ERR_OR_NULL(test, skb2);
+		KUNIT_EXPECT_EQ(test, skb2->len, params->rx_len);
+		skb_free_datagram(sock->sk, skb2);
+
+	} else {
+		KUNIT_EXPECT_PTR_EQ(test, skb2, NULL);
+	}
+
+	__mctp_route_test_fini(test, dev, rt, sock);
+}
+
+#define RX_FRAG(f, s) RX_HDR(1, 10, 8, FL_TO | (f) | ((s) << MCTP_HDR_SEQ_SHIFT))
+
+static const struct mctp_route_input_sk_reasm_test mctp_route_input_sk_reasm_tests[] = {
+	{
+		.name = "single packet",
+		.hdrs = {
+			RX_FRAG(FL_S | FL_E, 0),
+		},
+		.n_hdrs = 1,
+		.rx_len = 1,
+	},
+	{
+		.name = "single packet, offset seq",
+		.hdrs = {
+			RX_FRAG(FL_S | FL_E, 1),
+		},
+		.n_hdrs = 1,
+		.rx_len = 1,
+	},
+	{
+		.name = "start & end packets",
+		.hdrs = {
+			RX_FRAG(FL_S, 0),
+			RX_FRAG(FL_E, 1),
+		},
+		.n_hdrs = 2,
+		.rx_len = 2,
+	},
+	{
+		.name = "start & end packets, offset seq",
+		.hdrs = {
+			RX_FRAG(FL_S, 1),
+			RX_FRAG(FL_E, 2),
+		},
+		.n_hdrs = 2,
+		.rx_len = 2,
+	},
+	{
+		.name = "start & end packets, out of order",
+		.hdrs = {
+			RX_FRAG(FL_E, 1),
+			RX_FRAG(FL_S, 0),
+		},
+		.n_hdrs = 2,
+		.rx_len = 0,
+	},
+	{
+		.name = "start, middle & end packets",
+		.hdrs = {
+			RX_FRAG(FL_S, 0),
+			RX_FRAG(0,    1),
+			RX_FRAG(FL_E, 2),
+		},
+		.n_hdrs = 3,
+		.rx_len = 3,
+	},
+	{
+		.name = "missing seq",
+		.hdrs = {
+			RX_FRAG(FL_S, 0),
+			RX_FRAG(FL_E, 2),
+		},
+		.n_hdrs = 2,
+		.rx_len = 0,
+	},
+	{
+		.name = "seq wrap",
+		.hdrs = {
+			RX_FRAG(FL_S, 3),
+			RX_FRAG(FL_E, 0),
+		},
+		.n_hdrs = 2,
+		.rx_len = 2,
+	},
+};
+
+static void mctp_route_input_sk_reasm_to_desc(
+				const struct mctp_route_input_sk_reasm_test *t,
+				char *desc)
+{
+	sprintf(desc, "%s", t->name);
+}
+
+KUNIT_ARRAY_PARAM(mctp_route_input_sk_reasm, mctp_route_input_sk_reasm_tests,
+		  mctp_route_input_sk_reasm_to_desc);
+
+struct mctp_route_input_sk_keys_test {
+	const char	*name;
+	mctp_eid_t	key_peer_addr;
+	mctp_eid_t	key_local_addr;
+	u8		key_tag;
+	struct mctp_hdr hdr;
+	bool		deliver;
+};
+
+/* test packet rx in the presence of various key configurations */
+static void mctp_test_route_input_sk_keys(struct kunit *test)
+{
+	const struct mctp_route_input_sk_keys_test *params;
+	struct mctp_test_route *rt;
+	struct sk_buff *skb, *skb2;
+	struct mctp_test_dev *dev;
+	struct mctp_sk_key *key;
+	struct netns_mctp *mns;
+	struct mctp_sock *msk;
+	struct socket *sock;
+	unsigned long flags;
+	int rc;
+	u8 c;
+
+	params = test->param_value;
+
+	dev = mctp_test_create_dev();
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, dev);
+
+	rt = mctp_test_create_route(&init_net, dev->mdev, 8, 68);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, rt);
+
+	rc = sock_create_kern(&init_net, AF_MCTP, SOCK_DGRAM, 0, &sock);
+	KUNIT_ASSERT_EQ(test, rc, 0);
+
+	msk = container_of(sock->sk, struct mctp_sock, sk);
+	mns = &sock_net(sock->sk)->mctp;
+
+	/* set the incoming tag according to test params */
+	key = mctp_key_alloc(msk, params->key_local_addr, params->key_peer_addr,
+			     params->key_tag, GFP_KERNEL);
+
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, key);
+
+	spin_lock_irqsave(&mns->keys_lock, flags);
+	mctp_reserve_tag(&init_net, key, msk);
+	spin_unlock_irqrestore(&mns->keys_lock, flags);
+
+	/* create packet and route */
+	c = 0;
+	skb = mctp_test_create_skb_data(&params->hdr, &c);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, skb);
+
+	skb->dev = dev->ndev;
+	__mctp_cb(skb);
+
+	rc = mctp_route_input(&rt->rt, skb);
+
+	/* (potentially) receive message */
+	skb2 = skb_recv_datagram(sock->sk, 0, 1, &rc);
+
+	if (params->deliver)
+		KUNIT_EXPECT_NOT_ERR_OR_NULL(test, skb2);
+	else
+		KUNIT_EXPECT_PTR_EQ(test, skb2, NULL);
+
+	if (skb2)
+		skb_free_datagram(sock->sk, skb2);
+
+	mctp_key_unref(key);
+	__mctp_route_test_fini(test, dev, rt, sock);
+}
+
+static const struct mctp_route_input_sk_keys_test mctp_route_input_sk_keys_tests[] = {
+	{
+		.name = "direct match",
+		.key_peer_addr = 9,
+		.key_local_addr = 8,
+		.key_tag = 1,
+		.hdr = RX_HDR(1, 9, 8, FL_S | FL_E | FL_T(1)),
+		.deliver = true,
+	},
+	{
+		.name = "flipped src/dest",
+		.key_peer_addr = 8,
+		.key_local_addr = 9,
+		.key_tag = 1,
+		.hdr = RX_HDR(1, 9, 8, FL_S | FL_E | FL_T(1)),
+		.deliver = false,
+	},
+	{
+		.name = "peer addr mismatch",
+		.key_peer_addr = 9,
+		.key_local_addr = 8,
+		.key_tag = 1,
+		.hdr = RX_HDR(1, 10, 8, FL_S | FL_E | FL_T(1)),
+		.deliver = false,
+	},
+	{
+		.name = "tag value mismatch",
+		.key_peer_addr = 9,
+		.key_local_addr = 8,
+		.key_tag = 1,
+		.hdr = RX_HDR(1, 9, 8, FL_S | FL_E | FL_T(2)),
+		.deliver = false,
+	},
+	{
+		.name = "TO mismatch",
+		.key_peer_addr = 9,
+		.key_local_addr = 8,
+		.key_tag = 1,
+		.hdr = RX_HDR(1, 9, 8, FL_S | FL_E | FL_T(1) | FL_TO),
+		.deliver = false,
+	},
+	{
+		.name = "broadcast response",
+		.key_peer_addr = MCTP_ADDR_ANY,
+		.key_local_addr = 8,
+		.key_tag = 1,
+		.hdr = RX_HDR(1, 11, 8, FL_S | FL_E | FL_T(1)),
+		.deliver = true,
+	},
+	{
+		.name = "any local match",
+		.key_peer_addr = 12,
+		.key_local_addr = MCTP_ADDR_ANY,
+		.key_tag = 1,
+		.hdr = RX_HDR(1, 12, 8, FL_S | FL_E | FL_T(1)),
+		.deliver = true,
+	},
+};
+
+static void mctp_route_input_sk_keys_to_desc(
+				const struct mctp_route_input_sk_keys_test *t,
+				char *desc)
+{
+	sprintf(desc, "%s", t->name);
+}
+
+KUNIT_ARRAY_PARAM(mctp_route_input_sk_keys, mctp_route_input_sk_keys_tests,
+		  mctp_route_input_sk_keys_to_desc);
+
+static struct kunit_case mctp_test_cases[] = {
+	KUNIT_CASE_PARAM(mctp_test_fragment, mctp_frag_gen_params),
+	KUNIT_CASE_PARAM(mctp_test_rx_input, mctp_rx_input_gen_params),
+	KUNIT_CASE_PARAM(mctp_test_route_input_sk, mctp_route_input_sk_gen_params),
+	KUNIT_CASE_PARAM(mctp_test_route_input_sk_reasm,
+			 mctp_route_input_sk_reasm_gen_params),
+	KUNIT_CASE_PARAM(mctp_test_route_input_sk_keys,
+			 mctp_route_input_sk_keys_gen_params),
+	{}
+};
+
+static struct kunit_suite mctp_test_suite = {
+	.name = "mctp",
+	.test_cases = mctp_test_cases,
+};
+
+kunit_test_suite(mctp_test_suite);
diff --git a/net/mctp/test/utils.c b/net/mctp/test/utils.c
new file mode 100644
index 000000000000..e03ba66bbe18
--- /dev/null
+++ b/net/mctp/test/utils.c
@@ -0,0 +1,66 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/netdevice.h>
+#include <linux/mctp.h>
+#include <linux/if_arp.h>
+
+#include <net/mctpdevice.h>
+#include <net/pkt_sched.h>
+
+#include "utils.h"
+
+static netdev_tx_t mctp_test_dev_tx(struct sk_buff *skb,
+				    struct net_device *ndev)
+{
+	kfree_skb(skb);
+	return NETDEV_TX_OK;
+}
+
+static const struct net_device_ops mctp_test_netdev_ops = {
+	.ndo_start_xmit = mctp_test_dev_tx,
+};
+
+static void mctp_test_dev_setup(struct net_device *ndev)
+{
+	ndev->type = ARPHRD_MCTP;
+	ndev->mtu = MCTP_DEV_TEST_MTU;
+	ndev->hard_header_len = 0;
+	ndev->addr_len = 0;
+	ndev->tx_queue_len = DEFAULT_TX_QUEUE_LEN;
+	ndev->flags = IFF_NOARP;
+	ndev->netdev_ops = &mctp_test_netdev_ops;
+	ndev->needs_free_netdev = true;
+}
+
+struct mctp_test_dev *mctp_test_create_dev(void)
+{
+	struct mctp_test_dev *dev;
+	struct net_device *ndev;
+	int rc;
+
+	ndev = alloc_netdev(sizeof(*dev), "mctptest%d", NET_NAME_ENUM,
+			    mctp_test_dev_setup);
+	if (!ndev)
+		return NULL;
+
+	dev = netdev_priv(ndev);
+	dev->ndev = ndev;
+
+	rc = register_netdev(ndev);
+	if (rc) {
+		free_netdev(ndev);
+		return NULL;
+	}
+
+	rcu_read_lock();
+	dev->mdev = __mctp_dev_get(ndev);
+	rcu_read_unlock();
+
+	return dev;
+}
+
+void mctp_test_destroy_dev(struct mctp_test_dev *dev)
+{
+	mctp_dev_put(dev->mdev);
+	unregister_netdev(dev->ndev);
+}
diff --git a/net/mctp/test/utils.h b/net/mctp/test/utils.h
new file mode 100644
index 000000000000..df6aa1c03440
--- /dev/null
+++ b/net/mctp/test/utils.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __NET_MCTP_TEST_UTILS_H
+#define __NET_MCTP_TEST_UTILS_H
+
+#include <kunit/test.h>
+
+#define MCTP_DEV_TEST_MTU	68
+
+struct mctp_test_dev {
+	struct net_device *ndev;
+	struct mctp_dev *mdev;
+};
+
+struct mctp_test_dev;
+
+struct mctp_test_dev *mctp_test_create_dev(void);
+void mctp_test_destroy_dev(struct mctp_test_dev *dev);
+
+#endif /* __NET_MCTP_TEST_UTILS_H */
diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c
index b21ff9be04c6..8d1c67b93591 100644
--- a/net/mptcp/mib.c
+++ b/net/mptcp/mib.c
@@ -35,12 +35,14 @@ static const struct snmp_mib mptcp_snmp_list[] = {
 	SNMP_MIB_ITEM("AddAddr", MPTCP_MIB_ADDADDR),
 	SNMP_MIB_ITEM("EchoAdd", MPTCP_MIB_ECHOADD),
 	SNMP_MIB_ITEM("PortAdd", MPTCP_MIB_PORTADD),
+	SNMP_MIB_ITEM("AddAddrDrop", MPTCP_MIB_ADDADDRDROP),
 	SNMP_MIB_ITEM("MPJoinPortSynRx", MPTCP_MIB_JOINPORTSYNRX),
 	SNMP_MIB_ITEM("MPJoinPortSynAckRx", MPTCP_MIB_JOINPORTSYNACKRX),
 	SNMP_MIB_ITEM("MPJoinPortAckRx", MPTCP_MIB_JOINPORTACKRX),
 	SNMP_MIB_ITEM("MismatchPortSynRx", MPTCP_MIB_MISMATCHPORTSYNRX),
 	SNMP_MIB_ITEM("MismatchPortAckRx", MPTCP_MIB_MISMATCHPORTACKRX),
 	SNMP_MIB_ITEM("RmAddr", MPTCP_MIB_RMADDR),
+	SNMP_MIB_ITEM("RmAddrDrop", MPTCP_MIB_RMADDRDROP),
 	SNMP_MIB_ITEM("RmSubflow", MPTCP_MIB_RMSUBFLOW),
 	SNMP_MIB_ITEM("MPPrioTx", MPTCP_MIB_MPPRIOTX),
 	SNMP_MIB_ITEM("MPPrioRx", MPTCP_MIB_MPPRIORX),
diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h
index ecd3d8b117e0..2966fcb6548b 100644
--- a/net/mptcp/mib.h
+++ b/net/mptcp/mib.h
@@ -28,12 +28,14 @@ enum linux_mptcp_mib_field {
 	MPTCP_MIB_ADDADDR,		/* Received ADD_ADDR with echo-flag=0 */
 	MPTCP_MIB_ECHOADD,		/* Received ADD_ADDR with echo-flag=1 */
 	MPTCP_MIB_PORTADD,		/* Received ADD_ADDR with a port-number */
+	MPTCP_MIB_ADDADDRDROP,		/* Dropped incoming ADD_ADDR */
 	MPTCP_MIB_JOINPORTSYNRX,	/* Received a SYN MP_JOIN with a different port-number */
 	MPTCP_MIB_JOINPORTSYNACKRX,	/* Received a SYNACK MP_JOIN with a different port-number */
 	MPTCP_MIB_JOINPORTACKRX,	/* Received an ACK MP_JOIN with a different port-number */
 	MPTCP_MIB_MISMATCHPORTSYNRX,	/* Received a SYN MP_JOIN with a mismatched port-number */
 	MPTCP_MIB_MISMATCHPORTACKRX,	/* Received an ACK MP_JOIN with a mismatched port-number */
 	MPTCP_MIB_RMADDR,		/* Received RM_ADDR */
+	MPTCP_MIB_RMADDRDROP,		/* Dropped incoming RM_ADDR */
 	MPTCP_MIB_RMSUBFLOW,		/* Remove a subflow */
 	MPTCP_MIB_MPPRIOTX,		/* Transmit a MP_PRIO */
 	MPTCP_MIB_MPPRIORX,		/* Received a MP_PRIO */
diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 6ab386ff3294..d9790d6fbce9 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -194,6 +194,8 @@ void mptcp_pm_add_addr_received(struct mptcp_sock *msk,
 		mptcp_pm_add_addr_send_ack(msk);
 	} else if (mptcp_pm_schedule_work(msk, MPTCP_PM_ADD_ADDR_RECEIVED)) {
 		pm->remote = *addr;
+	} else {
+		__MPTCP_INC_STATS(sock_net((struct sock *)msk), MPTCP_MIB_ADDADDRDROP);
 	}
 
 	spin_unlock_bh(&pm->lock);
@@ -234,8 +236,10 @@ void mptcp_pm_rm_addr_received(struct mptcp_sock *msk,
 		mptcp_event_addr_removed(msk, rm_list->ids[i]);
 
 	spin_lock_bh(&pm->lock);
-	mptcp_pm_schedule_work(msk, MPTCP_PM_RM_ADDR_RECEIVED);
-	pm->rm_list_rx = *rm_list;
+	if (mptcp_pm_schedule_work(msk, MPTCP_PM_RM_ADDR_RECEIVED))
+		pm->rm_list_rx = *rm_list;
+	else
+		__MPTCP_INC_STATS(sock_net((struct sock *)msk), MPTCP_MIB_RMADDRDROP);
 	spin_unlock_bh(&pm->lock);
 }
 
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 320f89b5c59d..cf0f700f46dd 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -606,6 +606,7 @@ static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk)
 	unsigned int add_addr_accept_max;
 	struct mptcp_addr_info remote;
 	unsigned int subflows_max;
+	bool reset_port = false;
 	int i, nr;
 
 	add_addr_accept_max = mptcp_pm_get_add_addr_accept_max(msk);
@@ -615,15 +616,19 @@ static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk)
 		 msk->pm.add_addr_accepted, add_addr_accept_max,
 		 msk->pm.remote.family);
 
-	if (lookup_subflow_by_daddr(&msk->conn_list, &msk->pm.remote))
+	remote = msk->pm.remote;
+	if (lookup_subflow_by_daddr(&msk->conn_list, &remote))
 		goto add_addr_echo;
 
+	/* pick id 0 port, if none is provided the remote address */
+	if (!remote.port) {
+		reset_port = true;
+		remote.port = sk->sk_dport;
+	}
+
 	/* connect to the specified remote address, using whatever
 	 * local address the routing configuration will pick.
 	 */
-	remote = msk->pm.remote;
-	if (!remote.port)
-		remote.port = sk->sk_dport;
 	nr = fill_local_addresses_vec(msk, addrs);
 
 	msk->pm.add_addr_accepted++;
@@ -636,8 +641,12 @@ static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk)
 		__mptcp_subflow_connect(sk, &addrs[i], &remote);
 	spin_lock_bh(&msk->pm.lock);
 
+	/* be sure to echo exactly the received address */
+	if (reset_port)
+		remote.port = 0;
+
 add_addr_echo:
-	mptcp_pm_announce_addr(msk, &msk->pm.remote, true);
+	mptcp_pm_announce_addr(msk, &remote, true);
 	mptcp_pm_nl_addr_send_ack(msk);
 }
 
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 4c889552cde7..d6def23b8cba 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -406,9 +406,12 @@ static bool mptcp_pending_data_fin(struct sock *sk, u64 *seq)
 static void mptcp_set_datafin_timeout(const struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
+	u32 retransmits;
 
-	mptcp_sk(sk)->timer_ival = min(TCP_RTO_MAX,
-				       TCP_RTO_MIN << icsk->icsk_retransmits);
+	retransmits = min_t(u32, icsk->icsk_retransmits,
+			    ilog2(TCP_RTO_MAX / TCP_RTO_MIN));
+
+	mptcp_sk(sk)->timer_ival = TCP_RTO_MIN << retransmits;
 }
 
 static void __mptcp_set_timeout(struct sock *sk, long tout)
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index 63d032191e62..60332fdb6dd4 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -406,14 +406,15 @@ static int __nf_register_net_hook(struct net *net, int pf,
 	p = nf_entry_dereference(*pp);
 	new_hooks = nf_hook_entries_grow(p, reg);
 
-	if (!IS_ERR(new_hooks))
+	if (!IS_ERR(new_hooks)) {
+		hooks_validate(new_hooks);
 		rcu_assign_pointer(*pp, new_hooks);
+	}
 
 	mutex_unlock(&nf_hook_mutex);
 	if (IS_ERR(new_hooks))
 		return PTR_ERR(new_hooks);
 
-	hooks_validate(new_hooks);
 #ifdef CONFIG_NETFILTER_INGRESS
 	if (nf_ingress_hook(reg, pf))
 		net_inc_ingress_queue();
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 7f7997460764..31399c53dfb1 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -66,6 +66,8 @@ EXPORT_SYMBOL_GPL(nf_conntrack_hash);
 struct conntrack_gc_work {
 	struct delayed_work	dwork;
 	u32			next_bucket;
+	u32			avg_timeout;
+	u32			start_time;
 	bool			exiting;
 	bool			early_drop;
 };
@@ -77,8 +79,19 @@ static __read_mostly bool nf_conntrack_locks_all;
 /* serialize hash resizes and nf_ct_iterate_cleanup */
 static DEFINE_MUTEX(nf_conntrack_mutex);
 
-#define GC_SCAN_INTERVAL	(120u * HZ)
+#define GC_SCAN_INTERVAL_MAX	(60ul * HZ)
+#define GC_SCAN_INTERVAL_MIN	(1ul * HZ)
+
+/* clamp timeouts to this value (TCP unacked) */
+#define GC_SCAN_INTERVAL_CLAMP	(300ul * HZ)
+
+/* large initial bias so that we don't scan often just because we have
+ * three entries with a 1s timeout.
+ */
+#define GC_SCAN_INTERVAL_INIT	INT_MAX
+
 #define GC_SCAN_MAX_DURATION	msecs_to_jiffies(10)
+#define GC_SCAN_EXPIRED_MAX	(64000u / HZ)
 
 #define MIN_CHAINLEN	8u
 #define MAX_CHAINLEN	(32u - MIN_CHAINLEN)
@@ -558,7 +571,7 @@ static void nf_ct_del_from_dying_or_unconfirmed_list(struct nf_conn *ct)
 
 #define NFCT_ALIGN(len)	(((len) + NFCT_INFOMASK) & ~NFCT_INFOMASK)
 
-/* Released via destroy_conntrack() */
+/* Released via nf_ct_destroy() */
 struct nf_conn *nf_ct_tmpl_alloc(struct net *net,
 				 const struct nf_conntrack_zone *zone,
 				 gfp_t flags)
@@ -585,7 +598,7 @@ struct nf_conn *nf_ct_tmpl_alloc(struct net *net,
 	tmpl->status = IPS_TEMPLATE;
 	write_pnet(&tmpl->ct_net, net);
 	nf_ct_zone_add(tmpl, zone);
-	atomic_set(&tmpl->ct_general.use, 0);
+	refcount_set(&tmpl->ct_general.use, 1);
 
 	return tmpl;
 }
@@ -612,13 +625,12 @@ static void destroy_gre_conntrack(struct nf_conn *ct)
 #endif
 }
 
-static void
-destroy_conntrack(struct nf_conntrack *nfct)
+void nf_ct_destroy(struct nf_conntrack *nfct)
 {
 	struct nf_conn *ct = (struct nf_conn *)nfct;
 
-	pr_debug("destroy_conntrack(%p)\n", ct);
-	WARN_ON(atomic_read(&nfct->use) != 0);
+	pr_debug("%s(%p)\n", __func__, ct);
+	WARN_ON(refcount_read(&nfct->use) != 0);
 
 	if (unlikely(nf_ct_is_template(ct))) {
 		nf_ct_tmpl_free(ct);
@@ -643,9 +655,10 @@ destroy_conntrack(struct nf_conntrack *nfct)
 	if (ct->master)
 		nf_ct_put(ct->master);
 
-	pr_debug("destroy_conntrack: returning ct=%p to slab\n", ct);
+	pr_debug("%s: returning ct=%p to slab\n", __func__, ct);
 	nf_conntrack_free(ct);
 }
+EXPORT_SYMBOL(nf_ct_destroy);
 
 static void nf_ct_delete_from_lists(struct nf_conn *ct)
 {
@@ -742,7 +755,7 @@ nf_ct_match(const struct nf_conn *ct1, const struct nf_conn *ct2)
 /* caller must hold rcu readlock and none of the nf_conntrack_locks */
 static void nf_ct_gc_expired(struct nf_conn *ct)
 {
-	if (!atomic_inc_not_zero(&ct->ct_general.use))
+	if (!refcount_inc_not_zero(&ct->ct_general.use))
 		return;
 
 	if (nf_ct_should_gc(ct))
@@ -810,7 +823,7 @@ __nf_conntrack_find_get(struct net *net, const struct nf_conntrack_zone *zone,
 		 * in, try to obtain a reference and re-check tuple
 		 */
 		ct = nf_ct_tuplehash_to_ctrack(h);
-		if (likely(atomic_inc_not_zero(&ct->ct_general.use))) {
+		if (likely(refcount_inc_not_zero(&ct->ct_general.use))) {
 			if (likely(nf_ct_key_equal(h, tuple, zone, net)))
 				goto found;
 
@@ -907,7 +920,7 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct)
 
 	smp_wmb();
 	/* The caller holds a reference to this object */
-	atomic_set(&ct->ct_general.use, 2);
+	refcount_set(&ct->ct_general.use, 2);
 	__nf_conntrack_hash_insert(ct, hash, reply_hash);
 	nf_conntrack_double_unlock(hash, reply_hash);
 	NF_CT_STAT_INC(net, insert);
@@ -958,7 +971,7 @@ static void __nf_conntrack_insert_prepare(struct nf_conn *ct)
 {
 	struct nf_conn_tstamp *tstamp;
 
-	atomic_inc(&ct->ct_general.use);
+	refcount_inc(&ct->ct_general.use);
 	ct->status |= IPS_CONFIRMED;
 
 	/* set conntrack timestamp, if enabled. */
@@ -989,7 +1002,7 @@ static int __nf_ct_resolve_clash(struct sk_buff *skb,
 
 		nf_ct_acct_merge(ct, ctinfo, loser_ct);
 		nf_ct_add_to_dying_list(loser_ct);
-		nf_conntrack_put(&loser_ct->ct_general);
+		nf_ct_put(loser_ct);
 		nf_ct_set(skb, ct, ctinfo);
 
 		NF_CT_STAT_INC(net, clash_resolve);
@@ -1351,7 +1364,7 @@ static unsigned int early_drop_list(struct net *net,
 		    nf_ct_is_dying(tmp))
 			continue;
 
-		if (!atomic_inc_not_zero(&tmp->ct_general.use))
+		if (!refcount_inc_not_zero(&tmp->ct_general.use))
 			continue;
 
 		/* kill only if still in same netns -- might have moved due to
@@ -1420,16 +1433,28 @@ static bool gc_worker_can_early_drop(const struct nf_conn *ct)
 
 static void gc_worker(struct work_struct *work)
 {
-	unsigned long end_time = jiffies + GC_SCAN_MAX_DURATION;
 	unsigned int i, hashsz, nf_conntrack_max95 = 0;
-	unsigned long next_run = GC_SCAN_INTERVAL;
+	u32 end_time, start_time = nfct_time_stamp;
 	struct conntrack_gc_work *gc_work;
+	unsigned int expired_count = 0;
+	unsigned long next_run;
+	s32 delta_time;
+
 	gc_work = container_of(work, struct conntrack_gc_work, dwork.work);
 
 	i = gc_work->next_bucket;
 	if (gc_work->early_drop)
 		nf_conntrack_max95 = nf_conntrack_max / 100u * 95u;
 
+	if (i == 0) {
+		gc_work->avg_timeout = GC_SCAN_INTERVAL_INIT;
+		gc_work->start_time = start_time;
+	}
+
+	next_run = gc_work->avg_timeout;
+
+	end_time = start_time + GC_SCAN_MAX_DURATION;
+
 	do {
 		struct nf_conntrack_tuple_hash *h;
 		struct hlist_nulls_head *ct_hash;
@@ -1446,6 +1471,7 @@ static void gc_worker(struct work_struct *work)
 
 		hlist_nulls_for_each_entry_rcu(h, n, &ct_hash[i], hnnode) {
 			struct nf_conntrack_net *cnet;
+			unsigned long expires;
 			struct net *net;
 
 			tmp = nf_ct_tuplehash_to_ctrack(h);
@@ -1455,11 +1481,29 @@ static void gc_worker(struct work_struct *work)
 				continue;
 			}
 
+			if (expired_count > GC_SCAN_EXPIRED_MAX) {
+				rcu_read_unlock();
+
+				gc_work->next_bucket = i;
+				gc_work->avg_timeout = next_run;
+
+				delta_time = nfct_time_stamp - gc_work->start_time;
+
+				/* re-sched immediately if total cycle time is exceeded */
+				next_run = delta_time < (s32)GC_SCAN_INTERVAL_MAX;
+				goto early_exit;
+			}
+
 			if (nf_ct_is_expired(tmp)) {
 				nf_ct_gc_expired(tmp);
+				expired_count++;
 				continue;
 			}
 
+			expires = clamp(nf_ct_expires(tmp), GC_SCAN_INTERVAL_MIN, GC_SCAN_INTERVAL_CLAMP);
+			next_run += expires;
+			next_run /= 2u;
+
 			if (nf_conntrack_max95 == 0 || gc_worker_skip_ct(tmp))
 				continue;
 
@@ -1469,7 +1513,7 @@ static void gc_worker(struct work_struct *work)
 				continue;
 
 			/* need to take reference to avoid possible races */
-			if (!atomic_inc_not_zero(&tmp->ct_general.use))
+			if (!refcount_inc_not_zero(&tmp->ct_general.use))
 				continue;
 
 			if (gc_worker_skip_ct(tmp)) {
@@ -1477,8 +1521,10 @@ static void gc_worker(struct work_struct *work)
 				continue;
 			}
 
-			if (gc_worker_can_early_drop(tmp))
+			if (gc_worker_can_early_drop(tmp)) {
 				nf_ct_kill(tmp);
+				expired_count++;
+			}
 
 			nf_ct_put(tmp);
 		}
@@ -1491,33 +1537,38 @@ static void gc_worker(struct work_struct *work)
 		cond_resched();
 		i++;
 
-		if (time_after(jiffies, end_time) && i < hashsz) {
+		delta_time = nfct_time_stamp - end_time;
+		if (delta_time > 0 && i < hashsz) {
+			gc_work->avg_timeout = next_run;
 			gc_work->next_bucket = i;
 			next_run = 0;
-			break;
+			goto early_exit;
 		}
 	} while (i < hashsz);
 
+	gc_work->next_bucket = 0;
+
+	next_run = clamp(next_run, GC_SCAN_INTERVAL_MIN, GC_SCAN_INTERVAL_MAX);
+
+	delta_time = max_t(s32, nfct_time_stamp - gc_work->start_time, 1);
+	if (next_run > (unsigned long)delta_time)
+		next_run -= delta_time;
+	else
+		next_run = 1;
+
+early_exit:
 	if (gc_work->exiting)
 		return;
 
-	/*
-	 * Eviction will normally happen from the packet path, and not
-	 * from this gc worker.
-	 *
-	 * This worker is only here to reap expired entries when system went
-	 * idle after a busy period.
-	 */
-	if (next_run) {
+	if (next_run)
 		gc_work->early_drop = false;
-		gc_work->next_bucket = 0;
-	}
+
 	queue_delayed_work(system_power_efficient_wq, &gc_work->dwork, next_run);
 }
 
 static void conntrack_gc_work_init(struct conntrack_gc_work *gc_work)
 {
-	INIT_DEFERRABLE_WORK(&gc_work->dwork, gc_worker);
+	INIT_DELAYED_WORK(&gc_work->dwork, gc_worker);
 	gc_work->exiting = false;
 }
 
@@ -1571,7 +1622,7 @@ __nf_conntrack_alloc(struct net *net,
 	/* Because we use RCU lookups, we set ct_general.use to zero before
 	 * this is inserted in any list.
 	 */
-	atomic_set(&ct->ct_general.use, 0);
+	refcount_set(&ct->ct_general.use, 0);
 	return ct;
 out:
 	atomic_dec(&cnet->count);
@@ -1596,7 +1647,7 @@ void nf_conntrack_free(struct nf_conn *ct)
 	/* A freed object has refcnt == 0, that's
 	 * the golden rule for SLAB_TYPESAFE_BY_RCU
 	 */
-	WARN_ON(atomic_read(&ct->ct_general.use) != 0);
+	WARN_ON(refcount_read(&ct->ct_general.use) != 0);
 
 	nf_ct_ext_destroy(ct);
 	kmem_cache_free(nf_conntrack_cachep, ct);
@@ -1688,8 +1739,8 @@ init_conntrack(struct net *net, struct nf_conn *tmpl,
 	if (!exp)
 		__nf_ct_try_assign_helper(ct, tmpl, GFP_ATOMIC);
 
-	/* Now it is inserted into the unconfirmed list, bump refcount */
-	nf_conntrack_get(&ct->ct_general);
+	/* Now it is inserted into the unconfirmed list, set refcount to 1. */
+	refcount_set(&ct->ct_general.use, 1);
 	nf_ct_add_to_unconfirmed_list(ct);
 
 	local_bh_enable();
@@ -1920,7 +1971,7 @@ repeat:
 		/* Invalid: inverse of the return code tells
 		 * the netfilter core what to do */
 		pr_debug("nf_conntrack_in: Can't track with proto module\n");
-		nf_conntrack_put(&ct->ct_general);
+		nf_ct_put(ct);
 		skb->_nfct = 0;
 		/* Special case: TCP tracker reports an attempt to reopen a
 		 * closed/aborted connection. We have to go back and create a
@@ -2301,7 +2352,7 @@ get_next_corpse(int (*iter)(struct nf_conn *i, void *data),
 
 	return NULL;
 found:
-	atomic_inc(&ct->ct_general.use);
+	refcount_inc(&ct->ct_general.use);
 	spin_unlock(lockp);
 	local_bh_enable();
 	return ct;
@@ -2774,7 +2825,7 @@ err_cachep:
 
 static struct nf_ct_hook nf_conntrack_hook = {
 	.update		= nf_conntrack_update,
-	.destroy	= destroy_conntrack,
+	.destroy	= nf_ct_destroy,
 	.get_tuple_skb  = nf_conntrack_get_tuple_skb,
 };
 
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index f562eeef4234..6d056ebba57c 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -203,12 +203,12 @@ nf_ct_find_expectation(struct net *net,
 	 * about to invoke ->destroy(), or nf_ct_delete() via timeout
 	 * or early_drop().
 	 *
-	 * The atomic_inc_not_zero() check tells:  If that fails, we
+	 * The refcount_inc_not_zero() check tells:  If that fails, we
 	 * know that the ct is being destroyed.  If it succeeds, we
 	 * can be sure the ct cannot disappear underneath.
 	 */
 	if (unlikely(nf_ct_is_dying(exp->master) ||
-		     !atomic_inc_not_zero(&exp->master->ct_general.use)))
+		     !refcount_inc_not_zero(&exp->master->ct_general.use)))
 		return NULL;
 
 	if (exp->flags & NF_CT_EXPECT_PERMANENT) {
diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c
index ae4488a13c70..ceb38a7b37cb 100644
--- a/net/netfilter/nf_conntrack_helper.c
+++ b/net/netfilter/nf_conntrack_helper.c
@@ -556,6 +556,12 @@ static const struct nf_ct_ext_type helper_extend = {
 	.id	= NF_CT_EXT_HELPER,
 };
 
+void nf_ct_set_auto_assign_helper_warned(struct net *net)
+{
+	nf_ct_pernet(net)->auto_assign_helper_warned = true;
+}
+EXPORT_SYMBOL_GPL(nf_ct_set_auto_assign_helper_warned);
+
 void nf_conntrack_helper_pernet_init(struct net *net)
 {
 	struct nf_conntrack_net *cnet = nf_ct_pernet(net);
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 1c02be04aaf5..ef0a78aa9ba9 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -508,7 +508,7 @@ nla_put_failure:
 
 static int ctnetlink_dump_use(struct sk_buff *skb, const struct nf_conn *ct)
 {
-	if (nla_put_be32(skb, CTA_USE, htonl(atomic_read(&ct->ct_general.use))))
+	if (nla_put_be32(skb, CTA_USE, htonl(refcount_read(&ct->ct_general.use))))
 		goto nla_put_failure;
 	return 0;
 
@@ -1200,7 +1200,7 @@ restart:
 			ct = nf_ct_tuplehash_to_ctrack(h);
 			if (nf_ct_is_expired(ct)) {
 				if (i < ARRAY_SIZE(nf_ct_evict) &&
-				    atomic_inc_not_zero(&ct->ct_general.use))
+				    refcount_inc_not_zero(&ct->ct_general.use))
 					nf_ct_evict[i++] = ct;
 				continue;
 			}
@@ -1748,7 +1748,7 @@ restart:
 						  NFNL_MSG_TYPE(cb->nlh->nlmsg_type),
 						  ct, dying ? true : false, 0);
 			if (res < 0) {
-				if (!atomic_inc_not_zero(&ct->ct_general.use))
+				if (!refcount_inc_not_zero(&ct->ct_general.use))
 					continue;
 				cb->args[0] = cpu;
 				cb->args[1] = (unsigned long)ct;
diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c
index 2394238d01c9..5a936334b517 100644
--- a/net/netfilter/nf_conntrack_proto_sctp.c
+++ b/net/netfilter/nf_conntrack_proto_sctp.c
@@ -489,6 +489,15 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct,
 			pr_debug("Setting vtag %x for dir %d\n",
 				 ih->init_tag, !dir);
 			ct->proto.sctp.vtag[!dir] = ih->init_tag;
+
+			/* don't renew timeout on init retransmit so
+			 * port reuse by client or NAT middlebox cannot
+			 * keep entry alive indefinitely (incl. nat info).
+			 */
+			if (new_state == SCTP_CONNTRACK_CLOSED &&
+			    old_state == SCTP_CONNTRACK_CLOSED &&
+			    nf_ct_is_confirmed(ct))
+				ignore = true;
 		}
 
 		ct->proto.sctp.state = new_state;
diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index af5115e127cf..3cee5d8ee702 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -341,8 +341,8 @@ static void tcp_options(const struct sk_buff *skb,
 	if (!ptr)
 		return;
 
-	state->td_scale =
-	state->flags = 0;
+	state->td_scale = 0;
+	state->flags &= IP_CT_TCP_FLAG_BE_LIBERAL;
 
 	while (length > 0) {
 		int opcode=*ptr++;
@@ -839,6 +839,16 @@ static bool tcp_can_early_drop(const struct nf_conn *ct)
 	return false;
 }
 
+static void nf_ct_tcp_state_reset(struct ip_ct_tcp_state *state)
+{
+	state->td_end		= 0;
+	state->td_maxend	= 0;
+	state->td_maxwin	= 0;
+	state->td_maxack	= 0;
+	state->td_scale		= 0;
+	state->flags		&= IP_CT_TCP_FLAG_BE_LIBERAL;
+}
+
 /* Returns verdict for packet, or -1 for invalid. */
 int nf_conntrack_tcp_packet(struct nf_conn *ct,
 			    struct sk_buff *skb,
@@ -945,8 +955,7 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct,
 			ct->proto.tcp.last_flags &= ~IP_CT_EXP_CHALLENGE_ACK;
 			ct->proto.tcp.seen[ct->proto.tcp.last_dir].flags =
 				ct->proto.tcp.last_flags;
-			memset(&ct->proto.tcp.seen[dir], 0,
-			       sizeof(struct ip_ct_tcp_state));
+			nf_ct_tcp_state_reset(&ct->proto.tcp.seen[dir]);
 			break;
 		}
 		ct->proto.tcp.last_index = index;
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 80f675d884b2..3e1afd10a9b6 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -303,7 +303,7 @@ static int ct_seq_show(struct seq_file *s, void *v)
 	int ret = 0;
 
 	WARN_ON(!ct);
-	if (unlikely(!atomic_inc_not_zero(&ct->ct_general.use)))
+	if (unlikely(!refcount_inc_not_zero(&ct->ct_general.use)))
 		return 0;
 
 	if (nf_ct_should_gc(ct)) {
@@ -370,7 +370,7 @@ static int ct_seq_show(struct seq_file *s, void *v)
 	ct_show_zone(s, ct, NF_CT_DEFAULT_ZONE_DIR);
 	ct_show_delta_time(s, ct);
 
-	seq_printf(s, "use=%u\n", atomic_read(&ct->ct_general.use));
+	seq_printf(s, "use=%u\n", refcount_read(&ct->ct_general.use));
 
 	if (seq_has_overflowed(s))
 		goto release;
diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c
index ed37bb9b4e58..b90eca7a2f22 100644
--- a/net/netfilter/nf_flow_table_core.c
+++ b/net/netfilter/nf_flow_table_core.c
@@ -48,7 +48,7 @@ struct flow_offload *flow_offload_alloc(struct nf_conn *ct)
 	struct flow_offload *flow;
 
 	if (unlikely(nf_ct_is_dying(ct) ||
-	    !atomic_inc_not_zero(&ct->ct_general.use)))
+	    !refcount_inc_not_zero(&ct->ct_general.use)))
 		return NULL;
 
 	flow = kzalloc(sizeof(*flow), GFP_ATOMIC);
diff --git a/net/netfilter/nf_flow_table_inet.c b/net/netfilter/nf_flow_table_inet.c
index bc4126d8ef65..280fdd32965f 100644
--- a/net/netfilter/nf_flow_table_inet.c
+++ b/net/netfilter/nf_flow_table_inet.c
@@ -6,12 +6,29 @@
 #include <linux/rhashtable.h>
 #include <net/netfilter/nf_flow_table.h>
 #include <net/netfilter/nf_tables.h>
+#include <linux/if_vlan.h>
 
 static unsigned int
 nf_flow_offload_inet_hook(void *priv, struct sk_buff *skb,
 			  const struct nf_hook_state *state)
 {
+	struct vlan_ethhdr *veth;
+	__be16 proto;
+
 	switch (skb->protocol) {
+	case htons(ETH_P_8021Q):
+		veth = (struct vlan_ethhdr *)skb_mac_header(skb);
+		proto = veth->h_vlan_encapsulated_proto;
+		break;
+	case htons(ETH_P_PPP_SES):
+		proto = nf_flow_pppoe_proto(skb);
+		break;
+	default:
+		proto = skb->protocol;
+		break;
+	}
+
+	switch (proto) {
 	case htons(ETH_P_IP):
 		return nf_flow_offload_ip_hook(priv, skb, state);
 	case htons(ETH_P_IPV6):
diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c
index 889cf88d3dba..6257d87c3a56 100644
--- a/net/netfilter/nf_flow_table_ip.c
+++ b/net/netfilter/nf_flow_table_ip.c
@@ -8,8 +8,6 @@
 #include <linux/ipv6.h>
 #include <linux/netdevice.h>
 #include <linux/if_ether.h>
-#include <linux/if_pppox.h>
-#include <linux/ppp_defs.h>
 #include <net/ip.h>
 #include <net/ipv6.h>
 #include <net/ip6_route.h>
@@ -239,22 +237,6 @@ static unsigned int nf_flow_xmit_xfrm(struct sk_buff *skb,
 	return NF_STOLEN;
 }
 
-static inline __be16 nf_flow_pppoe_proto(const struct sk_buff *skb)
-{
-	__be16 proto;
-
-	proto = *((__be16 *)(skb_mac_header(skb) + ETH_HLEN +
-			     sizeof(struct pppoe_hdr)));
-	switch (proto) {
-	case htons(PPP_IP):
-		return htons(ETH_P_IP);
-	case htons(PPP_IPV6):
-		return htons(ETH_P_IPV6);
-	}
-
-	return 0;
-}
-
 static bool nf_flow_skb_encap_protocol(const struct sk_buff *skb, __be16 proto,
 				       u32 *offset)
 {
diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c
index 6d12afabfe8a..63d1516816b1 100644
--- a/net/netfilter/nf_queue.c
+++ b/net/netfilter/nf_queue.c
@@ -46,6 +46,15 @@ void nf_unregister_queue_handler(void)
 }
 EXPORT_SYMBOL(nf_unregister_queue_handler);
 
+static void nf_queue_sock_put(struct sock *sk)
+{
+#ifdef CONFIG_INET
+	sock_gen_put(sk);
+#else
+	sock_put(sk);
+#endif
+}
+
 static void nf_queue_entry_release_refs(struct nf_queue_entry *entry)
 {
 	struct nf_hook_state *state = &entry->state;
@@ -54,7 +63,7 @@ static void nf_queue_entry_release_refs(struct nf_queue_entry *entry)
 	dev_put(state->in);
 	dev_put(state->out);
 	if (state->sk)
-		sock_put(state->sk);
+		nf_queue_sock_put(state->sk);
 
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	dev_put(entry->physin);
@@ -87,19 +96,21 @@ static void __nf_queue_entry_init_physdevs(struct nf_queue_entry *entry)
 }
 
 /* Bump dev refs so they don't vanish while packet is out */
-void nf_queue_entry_get_refs(struct nf_queue_entry *entry)
+bool nf_queue_entry_get_refs(struct nf_queue_entry *entry)
 {
 	struct nf_hook_state *state = &entry->state;
 
+	if (state->sk && !refcount_inc_not_zero(&state->sk->sk_refcnt))
+		return false;
+
 	dev_hold(state->in);
 	dev_hold(state->out);
-	if (state->sk)
-		sock_hold(state->sk);
 
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	dev_hold(entry->physin);
 	dev_hold(entry->physout);
 #endif
+	return true;
 }
 EXPORT_SYMBOL_GPL(nf_queue_entry_get_refs);
 
@@ -169,6 +180,18 @@ static int __nf_queue(struct sk_buff *skb, const struct nf_hook_state *state,
 		break;
 	}
 
+	if (skb_sk_is_prefetched(skb)) {
+		struct sock *sk = skb->sk;
+
+		if (!sk_is_refcounted(sk)) {
+			if (!refcount_inc_not_zero(&sk->sk_refcnt))
+				return -ENOTCONN;
+
+			/* drop refcount on skb_orphan */
+			skb->destructor = sock_edemux;
+		}
+	}
+
 	entry = kmalloc(sizeof(*entry) + route_key_size, GFP_ATOMIC);
 	if (!entry)
 		return -ENOMEM;
@@ -187,7 +210,10 @@ static int __nf_queue(struct sk_buff *skb, const struct nf_hook_state *state,
 
 	__nf_queue_entry_init_physdevs(entry);
 
-	nf_queue_entry_get_refs(entry);
+	if (!nf_queue_entry_get_refs(entry)) {
+		kfree(entry);
+		return -ENOTCONN;
+	}
 
 	switch (entry->state.pf) {
 	case AF_INET:
diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c
index 3d6d49420db8..2dfc5dae0656 100644
--- a/net/netfilter/nf_synproxy_core.c
+++ b/net/netfilter/nf_synproxy_core.c
@@ -349,7 +349,6 @@ static int __net_init synproxy_net_init(struct net *net)
 		goto err2;
 
 	__set_bit(IPS_CONFIRMED_BIT, &ct->status);
-	nf_conntrack_get(&ct->ct_general);
 	snet->tmpl = ct;
 
 	snet->stats = alloc_percpu(struct synproxy_stats);
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index c20772822637..2feb88ffcd81 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -4486,7 +4486,7 @@ static void nft_set_catchall_destroy(const struct nft_ctx *ctx,
 	list_for_each_entry_safe(catchall, next, &set->catchall_list, list) {
 		list_del_rcu(&catchall->list);
 		nft_set_elem_destroy(set, catchall->elem, true);
-		kfree_rcu(catchall);
+		kfree_rcu(catchall, rcu);
 	}
 }
 
@@ -5653,7 +5653,7 @@ static void nft_setelem_catchall_remove(const struct net *net,
 	list_for_each_entry_safe(catchall, next, &set->catchall_list, list) {
 		if (catchall->elem == elem->priv) {
 			list_del_rcu(&catchall->list);
-			kfree_rcu(catchall);
+			kfree_rcu(catchall, rcu);
 			break;
 		}
 	}
@@ -6535,12 +6535,15 @@ static int nf_tables_updobj(const struct nft_ctx *ctx,
 {
 	struct nft_object *newobj;
 	struct nft_trans *trans;
-	int err;
+	int err = -ENOMEM;
+
+	if (!try_module_get(type->owner))
+		return -ENOENT;
 
 	trans = nft_trans_alloc(ctx, NFT_MSG_NEWOBJ,
 				sizeof(struct nft_trans_obj));
 	if (!trans)
-		return -ENOMEM;
+		goto err_trans;
 
 	newobj = nft_obj_init(ctx, type, attr);
 	if (IS_ERR(newobj)) {
@@ -6557,6 +6560,8 @@ static int nf_tables_updobj(const struct nft_ctx *ctx,
 
 err_free_trans:
 	kfree(trans);
+err_trans:
+	module_put(type->owner);
 	return err;
 }
 
@@ -8169,7 +8174,7 @@ static void nft_obj_commit_update(struct nft_trans *trans)
 	if (obj->ops->update)
 		obj->ops->update(obj, newobj);
 
-	kfree(newobj);
+	nft_obj_destroy(&trans->ctx, newobj);
 }
 
 static void nft_commit_release(struct nft_trans *trans)
@@ -8914,7 +8919,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action)
 			break;
 		case NFT_MSG_NEWOBJ:
 			if (nft_trans_obj_update(trans)) {
-				kfree(nft_trans_obj_newobj(trans));
+				nft_obj_destroy(&trans->ctx, nft_trans_obj_newobj(trans));
 				nft_trans_destroy(trans);
 			} else {
 				trans->ctx.table->use--;
@@ -9203,17 +9208,23 @@ int nft_parse_u32_check(const struct nlattr *attr, int max, u32 *dest)
 }
 EXPORT_SYMBOL_GPL(nft_parse_u32_check);
 
-static unsigned int nft_parse_register(const struct nlattr *attr)
+static int nft_parse_register(const struct nlattr *attr, u32 *preg)
 {
 	unsigned int reg;
 
 	reg = ntohl(nla_get_be32(attr));
 	switch (reg) {
 	case NFT_REG_VERDICT...NFT_REG_4:
-		return reg * NFT_REG_SIZE / NFT_REG32_SIZE;
+		*preg = reg * NFT_REG_SIZE / NFT_REG32_SIZE;
+		break;
+	case NFT_REG32_00...NFT_REG32_15:
+		*preg = reg + NFT_REG_SIZE / NFT_REG32_SIZE - NFT_REG32_00;
+		break;
 	default:
-		return reg + NFT_REG_SIZE / NFT_REG32_SIZE - NFT_REG32_00;
+		return -ERANGE;
 	}
+
+	return 0;
 }
 
 /**
@@ -9255,7 +9266,10 @@ int nft_parse_register_load(const struct nlattr *attr, u8 *sreg, u32 len)
 	u32 reg;
 	int err;
 
-	reg = nft_parse_register(attr);
+	err = nft_parse_register(attr, &reg);
+	if (err < 0)
+		return err;
+
 	err = nft_validate_register_load(reg, len);
 	if (err < 0)
 		return err;
@@ -9310,7 +9324,10 @@ int nft_parse_register_store(const struct nft_ctx *ctx,
 	int err;
 	u32 reg;
 
-	reg = nft_parse_register(attr);
+	err = nft_parse_register(attr, &reg);
+	if (err < 0)
+		return err;
+
 	err = nft_validate_register_store(ctx, reg, data, type, len);
 	if (err < 0)
 		return err;
@@ -9574,10 +9591,13 @@ EXPORT_SYMBOL_GPL(__nft_release_basechain);
 
 static void __nft_release_hook(struct net *net, struct nft_table *table)
 {
+	struct nft_flowtable *flowtable;
 	struct nft_chain *chain;
 
 	list_for_each_entry(chain, &table->chains, list)
 		nf_tables_unregister_hook(net, table, chain);
+	list_for_each_entry(flowtable, &table->flowtables, list)
+		nft_unregister_flowtable_net_hooks(net, &flowtable->hook_list);
 }
 
 static void __nft_release_hooks(struct net *net)
diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c
index 866cfba04d6c..907e848dbc17 100644
--- a/net/netfilter/nf_tables_core.c
+++ b/net/netfilter/nf_tables_core.c
@@ -162,7 +162,7 @@ nft_do_chain(struct nft_pktinfo *pkt, void *priv)
 	struct nft_rule *const *rules;
 	const struct nft_rule *rule;
 	const struct nft_expr *expr, *last;
-	struct nft_regs regs;
+	struct nft_regs regs = {};
 	unsigned int stackptr = 0;
 	struct nft_jumpstack jumpstack[NFT_JUMP_STACK_SIZE];
 	bool genbit = READ_ONCE(net->nft.gencursor);
diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c
index 9656c1646222..2d36952b1392 100644
--- a/net/netfilter/nf_tables_offload.c
+++ b/net/netfilter/nf_tables_offload.c
@@ -94,7 +94,8 @@ struct nft_flow_rule *nft_flow_rule_create(struct net *net,
 
 	expr = nft_expr_first(rule);
 	while (nft_expr_more(rule, expr)) {
-		if (expr->ops->offload_flags & NFT_OFFLOAD_F_ACTION)
+		if (expr->ops->offload_action &&
+		    expr->ops->offload_action(expr))
 			num_actions++;
 
 		expr = nft_expr_next(expr);
diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index 959527708e38..8787d0613ad8 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -710,9 +710,15 @@ static struct nf_queue_entry *
 nf_queue_entry_dup(struct nf_queue_entry *e)
 {
 	struct nf_queue_entry *entry = kmemdup(e, e->size, GFP_ATOMIC);
-	if (entry)
-		nf_queue_entry_get_refs(entry);
-	return entry;
+
+	if (!entry)
+		return NULL;
+
+	if (nf_queue_entry_get_refs(entry))
+		return entry;
+
+	kfree(entry);
+	return NULL;
 }
 
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index 99b1de14ff7e..9c7472af9e4a 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -259,10 +259,13 @@ static void nft_ct_set_zone_eval(const struct nft_expr *expr,
 
 	ct = this_cpu_read(nft_ct_pcpu_template);
 
-	if (likely(atomic_read(&ct->ct_general.use) == 1)) {
+	if (likely(refcount_read(&ct->ct_general.use) == 1)) {
+		refcount_inc(&ct->ct_general.use);
 		nf_ct_zone_add(ct, &zone);
 	} else {
-		/* previous skb got queued to userspace */
+		/* previous skb got queued to userspace, allocate temporary
+		 * one until percpu template can be reused.
+		 */
 		ct = nf_ct_tmpl_alloc(nft_net(pkt), &zone, GFP_ATOMIC);
 		if (!ct) {
 			regs->verdict.code = NF_DROP;
@@ -270,7 +273,6 @@ static void nft_ct_set_zone_eval(const struct nft_expr *expr,
 		}
 	}
 
-	atomic_inc(&ct->ct_general.use);
 	nf_ct_set(skb, ct, IP_CT_NEW);
 }
 #endif
@@ -375,7 +377,6 @@ static bool nft_ct_tmpl_alloc_pcpu(void)
 			return false;
 		}
 
-		atomic_set(&tmp->ct_general.use, 1);
 		per_cpu(nft_ct_pcpu_template, cpu) = tmp;
 	}
 
@@ -1040,6 +1041,9 @@ static int nft_ct_helper_obj_init(const struct nft_ctx *ctx,
 	if (err < 0)
 		goto err_put_helper;
 
+	/* Avoid the bogus warning, helper will be assigned after CT init */
+	nf_ct_set_auto_assign_helper_warned(ctx->net);
+
 	return 0;
 
 err_put_helper:
diff --git a/net/netfilter/nft_dup_netdev.c b/net/netfilter/nft_dup_netdev.c
index bbf3fcba3df4..5b5c607fbf83 100644
--- a/net/netfilter/nft_dup_netdev.c
+++ b/net/netfilter/nft_dup_netdev.c
@@ -67,6 +67,11 @@ static int nft_dup_netdev_offload(struct nft_offload_ctx *ctx,
 	return nft_fwd_dup_netdev_offload(ctx, flow, FLOW_ACTION_MIRRED, oif);
 }
 
+static bool nft_dup_netdev_offload_action(const struct nft_expr *expr)
+{
+	return true;
+}
+
 static struct nft_expr_type nft_dup_netdev_type;
 static const struct nft_expr_ops nft_dup_netdev_ops = {
 	.type		= &nft_dup_netdev_type,
@@ -75,6 +80,7 @@ static const struct nft_expr_ops nft_dup_netdev_ops = {
 	.init		= nft_dup_netdev_init,
 	.dump		= nft_dup_netdev_dump,
 	.offload	= nft_dup_netdev_offload,
+	.offload_action	= nft_dup_netdev_offload_action,
 };
 
 static struct nft_expr_type nft_dup_netdev_type __read_mostly = {
diff --git a/net/netfilter/nft_fwd_netdev.c b/net/netfilter/nft_fwd_netdev.c
index cd59afde5b2f..7730409f6f09 100644
--- a/net/netfilter/nft_fwd_netdev.c
+++ b/net/netfilter/nft_fwd_netdev.c
@@ -77,6 +77,11 @@ static int nft_fwd_netdev_offload(struct nft_offload_ctx *ctx,
 	return nft_fwd_dup_netdev_offload(ctx, flow, FLOW_ACTION_REDIRECT, oif);
 }
 
+static bool nft_fwd_netdev_offload_action(const struct nft_expr *expr)
+{
+	return true;
+}
+
 struct nft_fwd_neigh {
 	u8			sreg_dev;
 	u8			sreg_addr;
@@ -219,6 +224,7 @@ static const struct nft_expr_ops nft_fwd_netdev_ops = {
 	.dump		= nft_fwd_netdev_dump,
 	.validate	= nft_fwd_validate,
 	.offload	= nft_fwd_netdev_offload,
+	.offload_action	= nft_fwd_netdev_offload_action,
 };
 
 static const struct nft_expr_ops *
diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c
index 90c64d27ae53..d0f67d325bdf 100644
--- a/net/netfilter/nft_immediate.c
+++ b/net/netfilter/nft_immediate.c
@@ -213,6 +213,16 @@ static int nft_immediate_offload(struct nft_offload_ctx *ctx,
 	return 0;
 }
 
+static bool nft_immediate_offload_action(const struct nft_expr *expr)
+{
+	const struct nft_immediate_expr *priv = nft_expr_priv(expr);
+
+	if (priv->dreg == NFT_REG_VERDICT)
+		return true;
+
+	return false;
+}
+
 static const struct nft_expr_ops nft_imm_ops = {
 	.type		= &nft_imm_type,
 	.size		= NFT_EXPR_SIZE(sizeof(struct nft_immediate_expr)),
@@ -224,7 +234,7 @@ static const struct nft_expr_ops nft_imm_ops = {
 	.dump		= nft_immediate_dump,
 	.validate	= nft_immediate_validate,
 	.offload	= nft_immediate_offload,
-	.offload_flags	= NFT_OFFLOAD_F_ACTION,
+	.offload_action	= nft_immediate_offload_action,
 };
 
 struct nft_expr_type nft_imm_type __read_mostly = {
diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c
index d601974c9d2e..b8f011145765 100644
--- a/net/netfilter/nft_socket.c
+++ b/net/netfilter/nft_socket.c
@@ -36,12 +36,11 @@ static void nft_socket_wildcard(const struct nft_pktinfo *pkt,
 
 #ifdef CONFIG_SOCK_CGROUP_DATA
 static noinline bool
-nft_sock_get_eval_cgroupv2(u32 *dest, const struct nft_pktinfo *pkt, u32 level)
+nft_sock_get_eval_cgroupv2(u32 *dest, struct sock *sk, const struct nft_pktinfo *pkt, u32 level)
 {
-	struct sock *sk = skb_to_full_sk(pkt->skb);
 	struct cgroup *cgrp;
 
-	if (!sk || !sk_fullsock(sk) || !net_eq(nft_net(pkt), sock_net(sk)))
+	if (!sk_fullsock(sk))
 		return false;
 
 	cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
@@ -108,7 +107,7 @@ static void nft_socket_eval(const struct nft_expr *expr,
 		break;
 #ifdef CONFIG_SOCK_CGROUP_DATA
 	case NFT_SOCKET_CGROUPV2:
-		if (!nft_sock_get_eval_cgroupv2(dest, pkt, priv->level)) {
+		if (!nft_sock_get_eval_cgroupv2(dest, sk, pkt, priv->level)) {
 			regs->verdict.code = NFT_BREAK;
 			return;
 		}
diff --git a/net/netfilter/nft_synproxy.c b/net/netfilter/nft_synproxy.c
index a0109fa1e92d..1133e06f3c40 100644
--- a/net/netfilter/nft_synproxy.c
+++ b/net/netfilter/nft_synproxy.c
@@ -191,8 +191,10 @@ static int nft_synproxy_do_init(const struct nft_ctx *ctx,
 		if (err)
 			goto nf_ct_failure;
 		err = nf_synproxy_ipv6_init(snet, ctx->net);
-		if (err)
+		if (err) {
+			nf_synproxy_ipv4_fini(snet, ctx->net);
 			goto nf_ct_failure;
+		}
 		break;
 	}
 
diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c
index 0a913ce07425..267757b0392a 100644
--- a/net/netfilter/xt_CT.c
+++ b/net/netfilter/xt_CT.c
@@ -24,7 +24,7 @@ static inline int xt_ct_target(struct sk_buff *skb, struct nf_conn *ct)
 		return XT_CONTINUE;
 
 	if (ct) {
-		atomic_inc(&ct->ct_general.use);
+		refcount_inc(&ct->ct_general.use);
 		nf_ct_set(skb, ct, IP_CT_NEW);
 	} else {
 		nf_ct_set(skb, ct, IP_CT_UNTRACKED);
@@ -201,7 +201,6 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par,
 			goto err4;
 	}
 	__set_bit(IPS_CONFIRMED_BIT, &ct->status);
-	nf_conntrack_get(&ct->ct_general);
 out:
 	info->ct = ct;
 	return 0;
diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c
index 5e6459e11605..7013f55f05d1 100644
--- a/net/netfilter/xt_socket.c
+++ b/net/netfilter/xt_socket.c
@@ -220,8 +220,10 @@ static void socket_mt_destroy(const struct xt_mtdtor_param *par)
 {
 	if (par->family == NFPROTO_IPV4)
 		nf_defrag_ipv4_disable(par->net);
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
 	else if (par->family == NFPROTO_IPV6)
-		nf_defrag_ipv4_disable(par->net);
+		nf_defrag_ipv6_disable(par->net);
+#endif
 }
 
 static struct xt_match socket_mt_reg[] __read_mostly = {
diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c
index beb0e573266d..54c083003947 100644
--- a/net/netlabel/netlabel_kapi.c
+++ b/net/netlabel/netlabel_kapi.c
@@ -885,6 +885,8 @@ int netlbl_bitmap_walk(const unsigned char *bitmap, u32 bitmap_len,
 	unsigned char bitmask;
 	unsigned char byte;
 
+	if (offset >= bitmap_len)
+		return -1;
 	byte_offset = offset / 8;
 	byte = bitmap[byte_offset];
 	bit_spot = offset;
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 81ba8e51e01f..fb7f7b17c78c 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -157,6 +157,8 @@ EXPORT_SYMBOL(do_trace_netlink_extack);
 
 static inline u32 netlink_group_mask(u32 group)
 {
+	if (group > 32)
+		return 0;
 	return group ? 1 << (group - 1) : 0;
 }
 
@@ -2282,6 +2284,13 @@ static int netlink_dump(struct sock *sk)
 	 * single netdev. The outcome is MSG_TRUNC error.
 	 */
 	skb_reserve(skb, skb_tailroom(skb) - alloc_size);
+
+	/* Make sure malicious BPF programs can not read unitialized memory
+	 * from skb->head -> skb->data
+	 */
+	skb_reset_network_header(skb);
+	skb_reset_mac_header(skb);
+
 	netlink_skb_set_owner_r(skb, sk);
 
 	if (nlk->dump_done_errno > 0) {
diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c
index e41e2e9e5498..189c9f428a3c 100644
--- a/net/nfc/nci/core.c
+++ b/net/nfc/nci/core.c
@@ -560,6 +560,10 @@ static int nci_close_device(struct nci_dev *ndev)
 	mutex_lock(&ndev->req_lock);
 
 	if (!test_and_clear_bit(NCI_UP, &ndev->flags)) {
+		/* Need to flush the cmd wq in case
+		 * there is a queued/running cmd_work
+		 */
+		flush_workqueue(ndev->cmd_wq);
 		del_timer_sync(&ndev->cmd_timer);
 		del_timer_sync(&ndev->data_timer);
 		mutex_unlock(&ndev->req_lock);
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 076774034bb9..8955f31fa47e 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -423,12 +423,43 @@ static void set_ipv6_addr(struct sk_buff *skb, u8 l4_proto,
 	memcpy(addr, new_addr, sizeof(__be32[4]));
 }
 
-static void set_ipv6_fl(struct ipv6hdr *nh, u32 fl, u32 mask)
+static void set_ipv6_dsfield(struct sk_buff *skb, struct ipv6hdr *nh, u8 ipv6_tclass, u8 mask)
 {
+	u8 old_ipv6_tclass = ipv6_get_dsfield(nh);
+
+	ipv6_tclass = OVS_MASKED(old_ipv6_tclass, ipv6_tclass, mask);
+
+	if (skb->ip_summed == CHECKSUM_COMPLETE)
+		csum_replace(&skb->csum, (__force __wsum)(old_ipv6_tclass << 12),
+			     (__force __wsum)(ipv6_tclass << 12));
+
+	ipv6_change_dsfield(nh, ~mask, ipv6_tclass);
+}
+
+static void set_ipv6_fl(struct sk_buff *skb, struct ipv6hdr *nh, u32 fl, u32 mask)
+{
+	u32 ofl;
+
+	ofl = nh->flow_lbl[0] << 16 |  nh->flow_lbl[1] << 8 |  nh->flow_lbl[2];
+	fl = OVS_MASKED(ofl, fl, mask);
+
 	/* Bits 21-24 are always unmasked, so this retains their values. */
-	OVS_SET_MASKED(nh->flow_lbl[0], (u8)(fl >> 16), (u8)(mask >> 16));
-	OVS_SET_MASKED(nh->flow_lbl[1], (u8)(fl >> 8), (u8)(mask >> 8));
-	OVS_SET_MASKED(nh->flow_lbl[2], (u8)fl, (u8)mask);
+	nh->flow_lbl[0] = (u8)(fl >> 16);
+	nh->flow_lbl[1] = (u8)(fl >> 8);
+	nh->flow_lbl[2] = (u8)fl;
+
+	if (skb->ip_summed == CHECKSUM_COMPLETE)
+		csum_replace(&skb->csum, (__force __wsum)htonl(ofl), (__force __wsum)htonl(fl));
+}
+
+static void set_ipv6_ttl(struct sk_buff *skb, struct ipv6hdr *nh, u8 new_ttl, u8 mask)
+{
+	new_ttl = OVS_MASKED(nh->hop_limit, new_ttl, mask);
+
+	if (skb->ip_summed == CHECKSUM_COMPLETE)
+		csum_replace(&skb->csum, (__force __wsum)(nh->hop_limit << 8),
+			     (__force __wsum)(new_ttl << 8));
+	nh->hop_limit = new_ttl;
 }
 
 static void set_ip_ttl(struct sk_buff *skb, struct iphdr *nh, u8 new_ttl,
@@ -546,18 +577,17 @@ static int set_ipv6(struct sk_buff *skb, struct sw_flow_key *flow_key,
 		}
 	}
 	if (mask->ipv6_tclass) {
-		ipv6_change_dsfield(nh, ~mask->ipv6_tclass, key->ipv6_tclass);
+		set_ipv6_dsfield(skb, nh, key->ipv6_tclass, mask->ipv6_tclass);
 		flow_key->ip.tos = ipv6_get_dsfield(nh);
 	}
 	if (mask->ipv6_label) {
-		set_ipv6_fl(nh, ntohl(key->ipv6_label),
+		set_ipv6_fl(skb, nh, ntohl(key->ipv6_label),
 			    ntohl(mask->ipv6_label));
 		flow_key->ipv6.label =
 		    *(__be32 *)nh & htonl(IPV6_FLOWINFO_FLOWLABEL);
 	}
 	if (mask->ipv6_hlimit) {
-		OVS_SET_MASKED(nh->hop_limit, key->ipv6_hlimit,
-			       mask->ipv6_hlimit);
+		set_ipv6_ttl(skb, nh, key->ipv6_hlimit, mask->ipv6_hlimit);
 		flow_key->ip.ttl = nh->hop_limit;
 	}
 	return 0;
@@ -1021,7 +1051,7 @@ static int clone(struct datapath *dp, struct sk_buff *skb,
 	int rem = nla_len(attr);
 	bool dont_clone_flow_key;
 
-	/* The first action is always 'OVS_CLONE_ATTR_ARG'. */
+	/* The first action is always 'OVS_CLONE_ATTR_EXEC'. */
 	clone_arg = nla_data(attr);
 	dont_clone_flow_key = nla_get_u32(clone_arg);
 	actions = nla_next(clone_arg, &rem);
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 1b5eae57bc90..815916056e0d 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -574,7 +574,7 @@ ovs_ct_expect_find(struct net *net, const struct nf_conntrack_zone *zone,
 			struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h);
 
 			nf_ct_delete(ct, 0, 0);
-			nf_conntrack_put(&ct->ct_general);
+			nf_ct_put(ct);
 		}
 	}
 
@@ -723,7 +723,7 @@ static bool skb_nfct_cached(struct net *net,
 		if (nf_ct_is_confirmed(ct))
 			nf_ct_delete(ct, 0, 0);
 
-		nf_conntrack_put(&ct->ct_general);
+		nf_ct_put(ct);
 		nf_ct_set(skb, NULL, 0);
 		return false;
 	}
@@ -732,6 +732,57 @@ static bool skb_nfct_cached(struct net *net,
 }
 
 #if IS_ENABLED(CONFIG_NF_NAT)
+static void ovs_nat_update_key(struct sw_flow_key *key,
+			       const struct sk_buff *skb,
+			       enum nf_nat_manip_type maniptype)
+{
+	if (maniptype == NF_NAT_MANIP_SRC) {
+		__be16 src;
+
+		key->ct_state |= OVS_CS_F_SRC_NAT;
+		if (key->eth.type == htons(ETH_P_IP))
+			key->ipv4.addr.src = ip_hdr(skb)->saddr;
+		else if (key->eth.type == htons(ETH_P_IPV6))
+			memcpy(&key->ipv6.addr.src, &ipv6_hdr(skb)->saddr,
+			       sizeof(key->ipv6.addr.src));
+		else
+			return;
+
+		if (key->ip.proto == IPPROTO_UDP)
+			src = udp_hdr(skb)->source;
+		else if (key->ip.proto == IPPROTO_TCP)
+			src = tcp_hdr(skb)->source;
+		else if (key->ip.proto == IPPROTO_SCTP)
+			src = sctp_hdr(skb)->source;
+		else
+			return;
+
+		key->tp.src = src;
+	} else {
+		__be16 dst;
+
+		key->ct_state |= OVS_CS_F_DST_NAT;
+		if (key->eth.type == htons(ETH_P_IP))
+			key->ipv4.addr.dst = ip_hdr(skb)->daddr;
+		else if (key->eth.type == htons(ETH_P_IPV6))
+			memcpy(&key->ipv6.addr.dst, &ipv6_hdr(skb)->daddr,
+			       sizeof(key->ipv6.addr.dst));
+		else
+			return;
+
+		if (key->ip.proto == IPPROTO_UDP)
+			dst = udp_hdr(skb)->dest;
+		else if (key->ip.proto == IPPROTO_TCP)
+			dst = tcp_hdr(skb)->dest;
+		else if (key->ip.proto == IPPROTO_SCTP)
+			dst = sctp_hdr(skb)->dest;
+		else
+			return;
+
+		key->tp.dst = dst;
+	}
+}
+
 /* Modelled after nf_nat_ipv[46]_fn().
  * range is only used for new, uninitialized NAT state.
  * Returns either NF_ACCEPT or NF_DROP.
@@ -739,7 +790,7 @@ static bool skb_nfct_cached(struct net *net,
 static int ovs_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct,
 			      enum ip_conntrack_info ctinfo,
 			      const struct nf_nat_range2 *range,
-			      enum nf_nat_manip_type maniptype)
+			      enum nf_nat_manip_type maniptype, struct sw_flow_key *key)
 {
 	int hooknum, nh_off, err = NF_ACCEPT;
 
@@ -811,58 +862,11 @@ static int ovs_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct,
 push:
 	skb_push_rcsum(skb, nh_off);
 
-	return err;
-}
-
-static void ovs_nat_update_key(struct sw_flow_key *key,
-			       const struct sk_buff *skb,
-			       enum nf_nat_manip_type maniptype)
-{
-	if (maniptype == NF_NAT_MANIP_SRC) {
-		__be16 src;
-
-		key->ct_state |= OVS_CS_F_SRC_NAT;
-		if (key->eth.type == htons(ETH_P_IP))
-			key->ipv4.addr.src = ip_hdr(skb)->saddr;
-		else if (key->eth.type == htons(ETH_P_IPV6))
-			memcpy(&key->ipv6.addr.src, &ipv6_hdr(skb)->saddr,
-			       sizeof(key->ipv6.addr.src));
-		else
-			return;
-
-		if (key->ip.proto == IPPROTO_UDP)
-			src = udp_hdr(skb)->source;
-		else if (key->ip.proto == IPPROTO_TCP)
-			src = tcp_hdr(skb)->source;
-		else if (key->ip.proto == IPPROTO_SCTP)
-			src = sctp_hdr(skb)->source;
-		else
-			return;
-
-		key->tp.src = src;
-	} else {
-		__be16 dst;
-
-		key->ct_state |= OVS_CS_F_DST_NAT;
-		if (key->eth.type == htons(ETH_P_IP))
-			key->ipv4.addr.dst = ip_hdr(skb)->daddr;
-		else if (key->eth.type == htons(ETH_P_IPV6))
-			memcpy(&key->ipv6.addr.dst, &ipv6_hdr(skb)->daddr,
-			       sizeof(key->ipv6.addr.dst));
-		else
-			return;
-
-		if (key->ip.proto == IPPROTO_UDP)
-			dst = udp_hdr(skb)->dest;
-		else if (key->ip.proto == IPPROTO_TCP)
-			dst = tcp_hdr(skb)->dest;
-		else if (key->ip.proto == IPPROTO_SCTP)
-			dst = sctp_hdr(skb)->dest;
-		else
-			return;
+	/* Update the flow key if NAT successful. */
+	if (err == NF_ACCEPT)
+		ovs_nat_update_key(key, skb, maniptype);
 
-		key->tp.dst = dst;
-	}
+	return err;
 }
 
 /* Returns NF_DROP if the packet should be dropped, NF_ACCEPT otherwise. */
@@ -904,7 +908,7 @@ static int ovs_ct_nat(struct net *net, struct sw_flow_key *key,
 	} else {
 		return NF_ACCEPT; /* Connection is not NATed. */
 	}
-	err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range, maniptype);
+	err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range, maniptype, key);
 
 	if (err == NF_ACCEPT && ct->status & IPS_DST_NAT) {
 		if (ct->status & IPS_SRC_NAT) {
@@ -914,17 +918,13 @@ static int ovs_ct_nat(struct net *net, struct sw_flow_key *key,
 				maniptype = NF_NAT_MANIP_SRC;
 
 			err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range,
-						 maniptype);
+						 maniptype, key);
 		} else if (CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) {
 			err = ovs_ct_nat_execute(skb, ct, ctinfo, NULL,
-						 NF_NAT_MANIP_SRC);
+						 NF_NAT_MANIP_SRC, key);
 		}
 	}
 
-	/* Mark NAT done if successful and update the flow key. */
-	if (err == NF_ACCEPT)
-		ovs_nat_update_key(key, skb, maniptype);
-
 	return err;
 }
 #else /* !CONFIG_NF_NAT */
@@ -967,7 +967,8 @@ static int __ovs_ct_lookup(struct net *net, struct sw_flow_key *key,
 
 		/* Associate skb with specified zone. */
 		if (tmpl) {
-			nf_conntrack_put(skb_nfct(skb));
+			ct = nf_ct_get(skb, &ctinfo);
+			nf_ct_put(ct);
 			nf_conntrack_get(&tmpl->ct_general);
 			nf_ct_set(skb, tmpl, IP_CT_NEW);
 		}
@@ -1328,7 +1329,12 @@ int ovs_ct_execute(struct net *net, struct sk_buff *skb,
 
 int ovs_ct_clear(struct sk_buff *skb, struct sw_flow_key *key)
 {
-	nf_conntrack_put(skb_nfct(skb));
+	enum ip_conntrack_info ctinfo;
+	struct nf_conn *ct;
+
+	ct = nf_ct_get(skb, &ctinfo);
+
+	nf_ct_put(ct);
 	nf_ct_set(skb, NULL, IP_CT_UNTRACKED);
 	ovs_ct_fill_key(skb, key, false);
 
@@ -1716,7 +1722,6 @@ int ovs_ct_copy_action(struct net *net, const struct nlattr *attr,
 		goto err_free_ct;
 
 	__set_bit(IPS_CONFIRMED_BIT, &ct_info.ct->status);
-	nf_conntrack_get(&ct_info.ct->ct_general);
 	return 0;
 err_free_ct:
 	__ovs_ct_free_action(&ct_info);
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index fd1f809e9bc1..d77c21ff066c 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -2201,8 +2201,8 @@ static int __ovs_nla_put_key(const struct sw_flow_key *swkey,
 			icmpv6_key->icmpv6_type = ntohs(output->tp.src);
 			icmpv6_key->icmpv6_code = ntohs(output->tp.dst);
 
-			if (icmpv6_key->icmpv6_type == NDISC_NEIGHBOUR_SOLICITATION ||
-			    icmpv6_key->icmpv6_type == NDISC_NEIGHBOUR_ADVERTISEMENT) {
+			if (swkey->tp.src == htons(NDISC_NEIGHBOUR_SOLICITATION) ||
+			    swkey->tp.src == htons(NDISC_NEIGHBOUR_ADVERTISEMENT)) {
 				struct ovs_key_nd *nd_key;
 
 				nla = nla_reserve(skb, OVS_KEY_ATTR_ND, sizeof(*nd_key));
@@ -2288,6 +2288,62 @@ static struct sw_flow_actions *nla_alloc_flow_actions(int size)
 	return sfa;
 }
 
+static void ovs_nla_free_nested_actions(const struct nlattr *actions, int len);
+
+static void ovs_nla_free_check_pkt_len_action(const struct nlattr *action)
+{
+	const struct nlattr *a;
+	int rem;
+
+	nla_for_each_nested(a, action, rem) {
+		switch (nla_type(a)) {
+		case OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL:
+		case OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER:
+			ovs_nla_free_nested_actions(nla_data(a), nla_len(a));
+			break;
+		}
+	}
+}
+
+static void ovs_nla_free_clone_action(const struct nlattr *action)
+{
+	const struct nlattr *a = nla_data(action);
+	int rem = nla_len(action);
+
+	switch (nla_type(a)) {
+	case OVS_CLONE_ATTR_EXEC:
+		/* The real list of actions follows this attribute. */
+		a = nla_next(a, &rem);
+		ovs_nla_free_nested_actions(a, rem);
+		break;
+	}
+}
+
+static void ovs_nla_free_dec_ttl_action(const struct nlattr *action)
+{
+	const struct nlattr *a = nla_data(action);
+
+	switch (nla_type(a)) {
+	case OVS_DEC_TTL_ATTR_ACTION:
+		ovs_nla_free_nested_actions(nla_data(a), nla_len(a));
+		break;
+	}
+}
+
+static void ovs_nla_free_sample_action(const struct nlattr *action)
+{
+	const struct nlattr *a = nla_data(action);
+	int rem = nla_len(action);
+
+	switch (nla_type(a)) {
+	case OVS_SAMPLE_ATTR_ARG:
+		/* The real list of actions follows this attribute. */
+		a = nla_next(a, &rem);
+		ovs_nla_free_nested_actions(a, rem);
+		break;
+	}
+}
+
 static void ovs_nla_free_set_action(const struct nlattr *a)
 {
 	const struct nlattr *ovs_key = nla_data(a);
@@ -2301,25 +2357,54 @@ static void ovs_nla_free_set_action(const struct nlattr *a)
 	}
 }
 
-void ovs_nla_free_flow_actions(struct sw_flow_actions *sf_acts)
+static void ovs_nla_free_nested_actions(const struct nlattr *actions, int len)
 {
 	const struct nlattr *a;
 	int rem;
 
-	if (!sf_acts)
+	/* Whenever new actions are added, the need to update this
+	 * function should be considered.
+	 */
+	BUILD_BUG_ON(OVS_ACTION_ATTR_MAX != 23);
+
+	if (!actions)
 		return;
 
-	nla_for_each_attr(a, sf_acts->actions, sf_acts->actions_len, rem) {
+	nla_for_each_attr(a, actions, len, rem) {
 		switch (nla_type(a)) {
-		case OVS_ACTION_ATTR_SET:
-			ovs_nla_free_set_action(a);
+		case OVS_ACTION_ATTR_CHECK_PKT_LEN:
+			ovs_nla_free_check_pkt_len_action(a);
+			break;
+
+		case OVS_ACTION_ATTR_CLONE:
+			ovs_nla_free_clone_action(a);
 			break;
+
 		case OVS_ACTION_ATTR_CT:
 			ovs_ct_free_action(a);
 			break;
+
+		case OVS_ACTION_ATTR_DEC_TTL:
+			ovs_nla_free_dec_ttl_action(a);
+			break;
+
+		case OVS_ACTION_ATTR_SAMPLE:
+			ovs_nla_free_sample_action(a);
+			break;
+
+		case OVS_ACTION_ATTR_SET:
+			ovs_nla_free_set_action(a);
+			break;
 		}
 	}
+}
+
+void ovs_nla_free_flow_actions(struct sw_flow_actions *sf_acts)
+{
+	if (!sf_acts)
+		return;
 
+	ovs_nla_free_nested_actions(sf_acts->actions, sf_acts->actions_len);
 	kfree(sf_acts);
 }
 
@@ -2351,7 +2436,7 @@ static struct nlattr *reserve_sfa_size(struct sw_flow_actions **sfa,
 	new_acts_size = max(next_offset + req_size, ksize(*sfa) * 2);
 
 	if (new_acts_size > MAX_ACTIONS_BUFSIZE) {
-		if ((MAX_ACTIONS_BUFSIZE - next_offset) < req_size) {
+		if ((next_offset + req_size) > MAX_ACTIONS_BUFSIZE) {
 			OVS_NLERR(log, "Flow action size exceeds max %u",
 				  MAX_ACTIONS_BUFSIZE);
 			return ERR_PTR(-EMSGSIZE);
@@ -3429,7 +3514,9 @@ static int clone_action_to_attr(const struct nlattr *attr,
 	if (!start)
 		return -EMSGSIZE;
 
-	err = ovs_nla_put_actions(nla_data(attr), rem, skb);
+	/* Skipping the OVS_CLONE_ATTR_EXEC that is always the first attribute. */
+	attr = nla_next(nla_data(attr), &rem);
+	err = ovs_nla_put_actions(attr, rem, skb);
 
 	if (err)
 		nla_nest_cancel(skb, start);
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index e00c38f242c3..88c3b5cf8d94 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2281,8 +2281,11 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 					copy_skb = skb_get(skb);
 					skb_head = skb->data;
 				}
-				if (copy_skb)
+				if (copy_skb) {
+					memset(&PACKET_SKB_CB(copy_skb)->sa.ll, 0,
+					       sizeof(PACKET_SKB_CB(copy_skb)->sa.ll));
 					skb_set_owner_r(copy_skb, sk);
+				}
 			}
 			snaplen = po->rx_ring.frame_size - macoff;
 			if ((int)snaplen < 0) {
@@ -2817,8 +2820,9 @@ tpacket_error:
 
 		status = TP_STATUS_SEND_REQUEST;
 		err = po->xmit(skb);
-		if (unlikely(err > 0)) {
-			err = net_xmit_errno(err);
+		if (unlikely(err != 0)) {
+			if (err > 0)
+				err = net_xmit_errno(err);
 			if (err && __packet_get_status(po, ph) ==
 				   TP_STATUS_AVAILABLE) {
 				/* skb was destructed already */
@@ -3019,8 +3023,12 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 		skb->no_fcs = 1;
 
 	err = po->xmit(skb);
-	if (err > 0 && (err = net_xmit_errno(err)) != 0)
-		goto out_unlock;
+	if (unlikely(err != 0)) {
+		if (err > 0)
+			err = net_xmit_errno(err);
+		if (err)
+			goto out_unlock;
+	}
 
 	dev_put(dev);
 
@@ -3434,6 +3442,8 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 	sock_recv_ts_and_drops(msg, sk, skb);
 
 	if (msg->msg_name) {
+		const size_t max_len = min(sizeof(skb->cb),
+					   sizeof(struct sockaddr_storage));
 		int copy_len;
 
 		/* If the address length field is there to be filled
@@ -3456,6 +3466,10 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 				msg->msg_namelen = sizeof(struct sockaddr_ll);
 			}
 		}
+		if (WARN_ON_ONCE(copy_len > max_len)) {
+			copy_len = max_len;
+			msg->msg_namelen = copy_len;
+		}
 		memcpy(msg->msg_name, &PACKET_SKB_CB(skb)->sa, copy_len);
 	}
 
diff --git a/net/rfkill/core.c b/net/rfkill/core.c
index ac15a944573f..068c7bcd30c9 100644
--- a/net/rfkill/core.c
+++ b/net/rfkill/core.c
@@ -78,6 +78,7 @@ struct rfkill_data {
 	struct mutex		mtx;
 	wait_queue_head_t	read_wait;
 	bool			input_handler;
+	u8			max_size;
 };
 
 
@@ -1141,6 +1142,8 @@ static int rfkill_fop_open(struct inode *inode, struct file *file)
 	if (!data)
 		return -ENOMEM;
 
+	data->max_size = RFKILL_EVENT_SIZE_V1;
+
 	INIT_LIST_HEAD(&data->events);
 	mutex_init(&data->mtx);
 	init_waitqueue_head(&data->read_wait);
@@ -1223,6 +1226,7 @@ static ssize_t rfkill_fop_read(struct file *file, char __user *buf,
 				list);
 
 	sz = min_t(unsigned long, sizeof(ev->ev), count);
+	sz = min_t(unsigned long, sz, data->max_size);
 	ret = sz;
 	if (copy_to_user(buf, &ev->ev, sz))
 		ret = -EFAULT;
@@ -1237,6 +1241,7 @@ static ssize_t rfkill_fop_read(struct file *file, char __user *buf,
 static ssize_t rfkill_fop_write(struct file *file, const char __user *buf,
 				size_t count, loff_t *pos)
 {
+	struct rfkill_data *data = file->private_data;
 	struct rfkill *rfkill;
 	struct rfkill_event_ext ev;
 	int ret;
@@ -1251,6 +1256,7 @@ static ssize_t rfkill_fop_write(struct file *file, const char __user *buf,
 	 * our API version even in a write() call, if it cares.
 	 */
 	count = min(count, sizeof(ev));
+	count = min_t(size_t, count, data->max_size);
 	if (copy_from_user(&ev, buf, count))
 		return -EFAULT;
 
@@ -1310,31 +1316,47 @@ static int rfkill_fop_release(struct inode *inode, struct file *file)
 	return 0;
 }
 
-#ifdef CONFIG_RFKILL_INPUT
 static long rfkill_fop_ioctl(struct file *file, unsigned int cmd,
 			     unsigned long arg)
 {
 	struct rfkill_data *data = file->private_data;
+	int ret = -ENOSYS;
+	u32 size;
 
 	if (_IOC_TYPE(cmd) != RFKILL_IOC_MAGIC)
 		return -ENOSYS;
 
-	if (_IOC_NR(cmd) != RFKILL_IOC_NOINPUT)
-		return -ENOSYS;
-
 	mutex_lock(&data->mtx);
-
-	if (!data->input_handler) {
-		if (atomic_inc_return(&rfkill_input_disabled) == 1)
-			printk(KERN_DEBUG "rfkill: input handler disabled\n");
-		data->input_handler = true;
+	switch (_IOC_NR(cmd)) {
+#ifdef CONFIG_RFKILL_INPUT
+	case RFKILL_IOC_NOINPUT:
+		if (!data->input_handler) {
+			if (atomic_inc_return(&rfkill_input_disabled) == 1)
+				printk(KERN_DEBUG "rfkill: input handler disabled\n");
+			data->input_handler = true;
+		}
+		ret = 0;
+		break;
+#endif
+	case RFKILL_IOC_MAX_SIZE:
+		if (get_user(size, (__u32 __user *)arg)) {
+			ret = -EFAULT;
+			break;
+		}
+		if (size < RFKILL_EVENT_SIZE_V1 || size > U8_MAX) {
+			ret = -EINVAL;
+			break;
+		}
+		data->max_size = size;
+		ret = 0;
+		break;
+	default:
+		break;
 	}
-
 	mutex_unlock(&data->mtx);
 
-	return 0;
+	return ret;
 }
-#endif
 
 static const struct file_operations rfkill_fops = {
 	.owner		= THIS_MODULE,
@@ -1343,10 +1365,8 @@ static const struct file_operations rfkill_fops = {
 	.write		= rfkill_fop_write,
 	.poll		= rfkill_fop_poll,
 	.release	= rfkill_fop_release,
-#ifdef CONFIG_RFKILL_INPUT
 	.unlocked_ioctl	= rfkill_fop_ioctl,
 	.compat_ioctl	= compat_ptr_ioctl,
-#endif
 	.llseek		= no_llseek,
 };
 
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 7bd6f8a66a3e..969e532f77a9 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -777,14 +777,12 @@ void rxrpc_propose_ACK(struct rxrpc_call *, u8, u32, bool, bool,
 		       enum rxrpc_propose_ack_trace);
 void rxrpc_process_call(struct work_struct *);
 
-static inline void rxrpc_reduce_call_timer(struct rxrpc_call *call,
-					   unsigned long expire_at,
-					   unsigned long now,
-					   enum rxrpc_timer_trace why)
-{
-	trace_rxrpc_timer(call, why, now);
-	timer_reduce(&call->timer, expire_at);
-}
+void rxrpc_reduce_call_timer(struct rxrpc_call *call,
+			     unsigned long expire_at,
+			     unsigned long now,
+			     enum rxrpc_timer_trace why);
+
+void rxrpc_delete_call_timer(struct rxrpc_call *call);
 
 /*
  * call_object.c
@@ -808,6 +806,7 @@ void rxrpc_release_calls_on_socket(struct rxrpc_sock *);
 bool __rxrpc_queue_call(struct rxrpc_call *);
 bool rxrpc_queue_call(struct rxrpc_call *);
 void rxrpc_see_call(struct rxrpc_call *);
+bool rxrpc_try_get_call(struct rxrpc_call *call, enum rxrpc_call_trace op);
 void rxrpc_get_call(struct rxrpc_call *, enum rxrpc_call_trace);
 void rxrpc_put_call(struct rxrpc_call *, enum rxrpc_call_trace);
 void rxrpc_cleanup_call(struct rxrpc_call *);
diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c
index df864e692267..22e05de5d1ca 100644
--- a/net/rxrpc/call_event.c
+++ b/net/rxrpc/call_event.c
@@ -310,7 +310,7 @@ recheck_state:
 	}
 
 	if (call->state == RXRPC_CALL_COMPLETE) {
-		del_timer_sync(&call->timer);
+		rxrpc_delete_call_timer(call);
 		goto out_put;
 	}
 
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index 4eb91d958a48..043508fd8d8a 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -53,10 +53,30 @@ static void rxrpc_call_timer_expired(struct timer_list *t)
 
 	if (call->state < RXRPC_CALL_COMPLETE) {
 		trace_rxrpc_timer(call, rxrpc_timer_expired, jiffies);
-		rxrpc_queue_call(call);
+		__rxrpc_queue_call(call);
+	} else {
+		rxrpc_put_call(call, rxrpc_call_put);
+	}
+}
+
+void rxrpc_reduce_call_timer(struct rxrpc_call *call,
+			     unsigned long expire_at,
+			     unsigned long now,
+			     enum rxrpc_timer_trace why)
+{
+	if (rxrpc_try_get_call(call, rxrpc_call_got_timer)) {
+		trace_rxrpc_timer(call, why, now);
+		if (timer_reduce(&call->timer, expire_at))
+			rxrpc_put_call(call, rxrpc_call_put_notimer);
 	}
 }
 
+void rxrpc_delete_call_timer(struct rxrpc_call *call)
+{
+	if (del_timer_sync(&call->timer))
+		rxrpc_put_call(call, rxrpc_call_put_timer);
+}
+
 static struct lock_class_key rxrpc_call_user_mutex_lock_class_key;
 
 /*
@@ -463,6 +483,17 @@ void rxrpc_see_call(struct rxrpc_call *call)
 	}
 }
 
+bool rxrpc_try_get_call(struct rxrpc_call *call, enum rxrpc_call_trace op)
+{
+	const void *here = __builtin_return_address(0);
+	int n = atomic_fetch_add_unless(&call->usage, 1, 0);
+
+	if (n == 0)
+		return false;
+	trace_rxrpc_call(call->debug_id, op, n, here, NULL);
+	return true;
+}
+
 /*
  * Note the addition of a ref on a call.
  */
@@ -510,8 +541,7 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call)
 	spin_unlock_bh(&call->lock);
 
 	rxrpc_put_call_slot(call);
-
-	del_timer_sync(&call->timer);
+	rxrpc_delete_call_timer(call);
 
 	/* Make sure we don't get any more notifications */
 	write_lock_bh(&rx->recvmsg_lock);
@@ -618,6 +648,8 @@ static void rxrpc_destroy_call(struct work_struct *work)
 	struct rxrpc_call *call = container_of(work, struct rxrpc_call, processor);
 	struct rxrpc_net *rxnet = call->rxnet;
 
+	rxrpc_delete_call_timer(call);
+
 	rxrpc_put_connection(call->conn);
 	rxrpc_put_peer(call->peer);
 	kfree(call->rxtx_buffer);
@@ -652,8 +684,6 @@ void rxrpc_cleanup_call(struct rxrpc_call *call)
 
 	memset(&call->sock_node, 0xcd, sizeof(call->sock_node));
 
-	del_timer_sync(&call->timer);
-
 	ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE);
 	ASSERT(test_bit(RXRPC_CALL_RELEASED, &call->flags));
 
diff --git a/net/rxrpc/net_ns.c b/net/rxrpc/net_ns.c
index 25bbc4cc8b13..cc7e30733feb 100644
--- a/net/rxrpc/net_ns.c
+++ b/net/rxrpc/net_ns.c
@@ -115,6 +115,8 @@ static __net_exit void rxrpc_exit_net(struct net *net)
 	rxnet->live = false;
 	del_timer_sync(&rxnet->peer_keepalive_timer);
 	cancel_work_sync(&rxnet->peer_keepalive_work);
+	/* Remove the timer again as the worker may have restarted it. */
+	del_timer_sync(&rxnet->peer_keepalive_timer);
 	rxrpc_destroy_all_calls(rxnet);
 	rxrpc_destroy_all_connections(rxnet);
 	rxrpc_destroy_all_peers(rxnet);
diff --git a/net/rxrpc/server_key.c b/net/rxrpc/server_key.c
index ead3471307ee..ee269e0e6ee8 100644
--- a/net/rxrpc/server_key.c
+++ b/net/rxrpc/server_key.c
@@ -84,6 +84,9 @@ static int rxrpc_preparse_s(struct key_preparsed_payload *prep)
 
 	prep->payload.data[1] = (struct rxrpc_security *)sec;
 
+	if (!sec->preparse_server_key)
+		return -EINVAL;
+
 	return sec->preparse_server_key(prep);
 }
 
@@ -91,7 +94,7 @@ static void rxrpc_free_preparse_s(struct key_preparsed_payload *prep)
 {
 	const struct rxrpc_security *sec = prep->payload.data[1];
 
-	if (sec)
+	if (sec && sec->free_preparse_server_key)
 		sec->free_preparse_server_key(prep);
 }
 
@@ -99,7 +102,7 @@ static void rxrpc_destroy_s(struct key *key)
 {
 	const struct rxrpc_security *sec = key->payload.data[1];
 
-	if (sec)
+	if (sec && sec->destroy_server_key)
 		sec->destroy_server_key(key);
 }
 
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 7dd3a2dc5fa4..7d53272727bf 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -728,15 +728,24 @@ int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions,
 restart_act_graph:
 	for (i = 0; i < nr_actions; i++) {
 		const struct tc_action *a = actions[i];
+		int repeat_ttl;
 
 		if (jmp_prgcnt > 0) {
 			jmp_prgcnt -= 1;
 			continue;
 		}
+
+		repeat_ttl = 32;
 repeat:
 		ret = a->ops->act(skb, a, res);
-		if (ret == TC_ACT_REPEAT)
-			goto repeat;	/* we need a ttl - JHS */
+
+		if (unlikely(ret == TC_ACT_REPEAT)) {
+			if (--repeat_ttl != 0)
+				goto repeat;
+			/* suspicious opcode, stop pipeline */
+			net_warn_ratelimited("TC_ACT_REPEAT abuse ?\n");
+			return TC_ACT_OK;
+		}
 
 		if (TC_ACT_EXT_CMP(ret, TC_ACT_JUMP)) {
 			jmp_prgcnt = ret & TCA_ACT_MAX_PRIO_MASK;
diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index 2a17eb77c904..f4fd584fba08 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -516,11 +516,6 @@ static bool tcf_ct_flow_table_lookup(struct tcf_ct_params *p,
 	struct nf_conn *ct;
 	u8 dir;
 
-	/* Previously seen or loopback */
-	ct = nf_ct_get(skb, &ctinfo);
-	if ((ct && !nf_ct_is_template(ct)) || ctinfo == IP_CT_UNTRACKED)
-		return false;
-
 	switch (family) {
 	case NFPROTO_IPV4:
 		if (!tcf_ct_flow_table_fill_tuple_ipv4(skb, &tuple, &tcph))
@@ -588,22 +583,25 @@ static bool tcf_ct_skb_nfct_cached(struct net *net, struct sk_buff *skb,
 	if (!ct)
 		return false;
 	if (!net_eq(net, read_pnet(&ct->ct_net)))
-		return false;
+		goto drop_ct;
 	if (nf_ct_zone(ct)->id != zone_id)
-		return false;
+		goto drop_ct;
 
 	/* Force conntrack entry direction. */
 	if (force && CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) {
 		if (nf_ct_is_confirmed(ct))
 			nf_ct_kill(ct);
 
-		nf_conntrack_put(&ct->ct_general);
-		nf_ct_set(skb, NULL, IP_CT_UNTRACKED);
-
-		return false;
+		goto drop_ct;
 	}
 
 	return true;
+
+drop_ct:
+	nf_ct_put(ct);
+	nf_ct_set(skb, NULL, IP_CT_UNTRACKED);
+
+	return false;
 }
 
 /* Trim the skb to the length specified by the IP/IPv6 header,
@@ -762,7 +760,7 @@ static void tcf_ct_params_free(struct rcu_head *head)
 	tcf_ct_flow_table_put(params);
 
 	if (params->tmpl)
-		nf_conntrack_put(&params->tmpl->ct_general);
+		nf_ct_put(params->tmpl);
 	kfree(params);
 }
 
@@ -972,7 +970,7 @@ static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a,
 		tc_skb_cb(skb)->post_ct = false;
 		ct = nf_ct_get(skb, &ctinfo);
 		if (ct) {
-			nf_conntrack_put(&ct->ct_general);
+			nf_ct_put(ct);
 			nf_ct_set(skb, NULL, IP_CT_UNTRACKED);
 		}
 
@@ -1234,7 +1232,6 @@ static int tcf_ct_fill_params(struct net *net,
 		return -ENOMEM;
 	}
 	__set_bit(IPS_CONFIRMED_BIT, &tmpl->status);
-	nf_conntrack_get(&tmpl->ct_general);
 	p->tmpl = tmpl;
 
 	return 0;
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 56dba8519d7c..4b552c10e7b9 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1044,7 +1044,7 @@ static int __tcf_qdisc_find(struct net *net, struct Qdisc **q,
 
 	/* Find qdisc */
 	if (!*parent) {
-		*q = dev->qdisc;
+		*q = rcu_dereference(dev->qdisc);
 		*parent = (*q)->handle;
 	} else {
 		*q = qdisc_lookup_rcu(dev, TC_H_MAJ(*parent));
@@ -1653,10 +1653,10 @@ static int tcf_chain_tp_insert(struct tcf_chain *chain,
 	if (chain->flushing)
 		return -EAGAIN;
 
+	RCU_INIT_POINTER(tp->next, tcf_chain_tp_prev(chain, chain_info));
 	if (*chain_info->pprev == chain->filter_chain)
 		tcf_chain0_head_change(chain, tp);
 	tcf_proto_get(tp);
-	RCU_INIT_POINTER(tp->next, tcf_chain_tp_prev(chain, chain_info));
 	rcu_assign_pointer(*chain_info->pprev, tp);
 
 	return 0;
@@ -2587,7 +2587,7 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
 
 		parent = tcm->tcm_parent;
 		if (!parent)
-			q = dev->qdisc;
+			q = rtnl_dereference(dev->qdisc);
 		else
 			q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent));
 		if (!q)
@@ -2962,7 +2962,7 @@ static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb)
 			return skb->len;
 
 		if (!tcm->tcm_parent)
-			q = dev->qdisc;
+			q = rtnl_dereference(dev->qdisc);
 		else
 			q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent));
 
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 709348262410..32b03a13f9b2 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -1004,6 +1004,7 @@ static int fl_set_key_mpls(struct nlattr **tb,
 static void fl_set_key_vlan(struct nlattr **tb,
 			    __be16 ethertype,
 			    int vlan_id_key, int vlan_prio_key,
+			    int vlan_next_eth_type_key,
 			    struct flow_dissector_key_vlan *key_val,
 			    struct flow_dissector_key_vlan *key_mask)
 {
@@ -1022,6 +1023,11 @@ static void fl_set_key_vlan(struct nlattr **tb,
 	}
 	key_val->vlan_tpid = ethertype;
 	key_mask->vlan_tpid = cpu_to_be16(~0);
+	if (tb[vlan_next_eth_type_key]) {
+		key_val->vlan_eth_type =
+			nla_get_be16(tb[vlan_next_eth_type_key]);
+		key_mask->vlan_eth_type = cpu_to_be16(~0);
+	}
 }
 
 static void fl_set_key_flag(u32 flower_key, u32 flower_mask,
@@ -1518,8 +1524,9 @@ static int fl_set_key(struct net *net, struct nlattr **tb,
 
 		if (eth_type_vlan(ethertype)) {
 			fl_set_key_vlan(tb, ethertype, TCA_FLOWER_KEY_VLAN_ID,
-					TCA_FLOWER_KEY_VLAN_PRIO, &key->vlan,
-					&mask->vlan);
+					TCA_FLOWER_KEY_VLAN_PRIO,
+					TCA_FLOWER_KEY_VLAN_ETH_TYPE,
+					&key->vlan, &mask->vlan);
 
 			if (tb[TCA_FLOWER_KEY_VLAN_ETH_TYPE]) {
 				ethertype = nla_get_be16(tb[TCA_FLOWER_KEY_VLAN_ETH_TYPE]);
@@ -1527,6 +1534,7 @@ static int fl_set_key(struct net *net, struct nlattr **tb,
 					fl_set_key_vlan(tb, ethertype,
 							TCA_FLOWER_KEY_CVLAN_ID,
 							TCA_FLOWER_KEY_CVLAN_PRIO,
+							TCA_FLOWER_KEY_CVLAN_ETH_TYPE,
 							&key->cvlan, &mask->cvlan);
 					fl_set_key_val(tb, &key->basic.n_proto,
 						       TCA_FLOWER_KEY_CVLAN_ETH_TYPE,
@@ -2882,13 +2890,13 @@ static int fl_dump_key(struct sk_buff *skb, struct net *net,
 		goto nla_put_failure;
 
 	if (mask->basic.n_proto) {
-		if (mask->cvlan.vlan_tpid) {
+		if (mask->cvlan.vlan_eth_type) {
 			if (nla_put_be16(skb, TCA_FLOWER_KEY_CVLAN_ETH_TYPE,
 					 key->basic.n_proto))
 				goto nla_put_failure;
-		} else if (mask->vlan.vlan_tpid) {
+		} else if (mask->vlan.vlan_eth_type) {
 			if (nla_put_be16(skb, TCA_FLOWER_KEY_VLAN_ETH_TYPE,
-					 key->basic.n_proto))
+					 key->vlan.vlan_eth_type))
 				goto nla_put_failure;
 		}
 	}
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index 4272814487f0..5d30db0d7157 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -386,14 +386,19 @@ static int u32_init(struct tcf_proto *tp)
 	return 0;
 }
 
-static int u32_destroy_key(struct tc_u_knode *n, bool free_pf)
+static void __u32_destroy_key(struct tc_u_knode *n)
 {
 	struct tc_u_hnode *ht = rtnl_dereference(n->ht_down);
 
 	tcf_exts_destroy(&n->exts);
-	tcf_exts_put_net(&n->exts);
 	if (ht && --ht->refcnt == 0)
 		kfree(ht);
+	kfree(n);
+}
+
+static void u32_destroy_key(struct tc_u_knode *n, bool free_pf)
+{
+	tcf_exts_put_net(&n->exts);
 #ifdef CONFIG_CLS_U32_PERF
 	if (free_pf)
 		free_percpu(n->pf);
@@ -402,8 +407,7 @@ static int u32_destroy_key(struct tc_u_knode *n, bool free_pf)
 	if (free_pf)
 		free_percpu(n->pcpu_success);
 #endif
-	kfree(n);
-	return 0;
+	__u32_destroy_key(n);
 }
 
 /* u32_delete_key_rcu should be called when free'ing a copied
@@ -810,10 +814,6 @@ static struct tc_u_knode *u32_init_knode(struct net *net, struct tcf_proto *tp,
 	new->flags = n->flags;
 	RCU_INIT_POINTER(new->ht_down, ht);
 
-	/* bump reference count as long as we hold pointer to structure */
-	if (ht)
-		ht->refcnt++;
-
 #ifdef CONFIG_CLS_U32_PERF
 	/* Statistics may be incremented by readers during update
 	 * so we must keep them in tact. When the node is later destroyed
@@ -835,6 +835,10 @@ static struct tc_u_knode *u32_init_knode(struct net *net, struct tcf_proto *tp,
 		return NULL;
 	}
 
+	/* bump reference count as long as we hold pointer to structure */
+	if (ht)
+		ht->refcnt++;
+
 	return new;
 }
 
@@ -898,13 +902,13 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 				    tca[TCA_RATE], flags, extack);
 
 		if (err) {
-			u32_destroy_key(new, false);
+			__u32_destroy_key(new);
 			return err;
 		}
 
 		err = u32_replace_hw_knode(tp, new, flags, extack);
 		if (err) {
-			u32_destroy_key(new, false);
+			__u32_destroy_key(new);
 			return err;
 		}
 
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 8e629c356e69..0fb387c9d706 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -301,7 +301,7 @@ struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle)
 
 	if (!handle)
 		return NULL;
-	q = qdisc_match_from_root(dev->qdisc, handle);
+	q = qdisc_match_from_root(rtnl_dereference(dev->qdisc), handle);
 	if (q)
 		goto out;
 
@@ -320,7 +320,7 @@ struct Qdisc *qdisc_lookup_rcu(struct net_device *dev, u32 handle)
 
 	if (!handle)
 		return NULL;
-	q = qdisc_match_from_root(dev->qdisc, handle);
+	q = qdisc_match_from_root(rcu_dereference(dev->qdisc), handle);
 	if (q)
 		goto out;
 
@@ -1082,10 +1082,10 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent,
 skip:
 		if (!ingress) {
 			notify_and_destroy(net, skb, n, classid,
-					   dev->qdisc, new);
+					   rtnl_dereference(dev->qdisc), new);
 			if (new && !new->ops->attach)
 				qdisc_refcount_inc(new);
-			dev->qdisc = new ? : &noop_qdisc;
+			rcu_assign_pointer(dev->qdisc, new ? : &noop_qdisc);
 
 			if (new && new->ops->attach)
 				new->ops->attach(new);
@@ -1460,7 +1460,7 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n,
 				q = dev_ingress_queue(dev)->qdisc_sleeping;
 			}
 		} else {
-			q = dev->qdisc;
+			q = rtnl_dereference(dev->qdisc);
 		}
 		if (!q) {
 			NL_SET_ERR_MSG(extack, "Cannot find specified qdisc on specified device");
@@ -1549,7 +1549,7 @@ replay:
 				q = dev_ingress_queue(dev)->qdisc_sleeping;
 			}
 		} else {
-			q = dev->qdisc;
+			q = rtnl_dereference(dev->qdisc);
 		}
 
 		/* It may be default qdisc, ignore it */
@@ -1771,7 +1771,8 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb)
 			s_q_idx = 0;
 		q_idx = 0;
 
-		if (tc_dump_qdisc_root(dev->qdisc, skb, cb, &q_idx, s_q_idx,
+		if (tc_dump_qdisc_root(rtnl_dereference(dev->qdisc),
+				       skb, cb, &q_idx, s_q_idx,
 				       true, tca[TCA_DUMP_INVISIBLE]) < 0)
 			goto done;
 
@@ -2042,7 +2043,7 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n,
 		} else if (qid1) {
 			qid = qid1;
 		} else if (qid == 0)
-			qid = dev->qdisc->handle;
+			qid = rtnl_dereference(dev->qdisc)->handle;
 
 		/* Now qid is genuine qdisc handle consistent
 		 * both with parent and child.
@@ -2053,7 +2054,7 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n,
 			portid = TC_H_MAKE(qid, portid);
 	} else {
 		if (qid == 0)
-			qid = dev->qdisc->handle;
+			qid = rtnl_dereference(dev->qdisc)->handle;
 	}
 
 	/* OK. Locate qdisc */
@@ -2214,7 +2215,8 @@ static int tc_dump_tclass(struct sk_buff *skb, struct netlink_callback *cb)
 	s_t = cb->args[0];
 	t = 0;
 
-	if (tc_dump_tclass_root(dev->qdisc, skb, tcm, cb, &t, s_t, true) < 0)
+	if (tc_dump_tclass_root(rtnl_dereference(dev->qdisc),
+				skb, tcm, cb, &t, s_t, true) < 0)
 		goto done;
 
 	dev_queue = dev_ingress_queue(dev);
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 47ca76ba7ffa..30c29a9a2efd 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -1114,30 +1114,33 @@ static void attach_default_qdiscs(struct net_device *dev)
 	if (!netif_is_multiqueue(dev) ||
 	    dev->priv_flags & IFF_NO_QUEUE) {
 		netdev_for_each_tx_queue(dev, attach_one_default_qdisc, NULL);
-		dev->qdisc = txq->qdisc_sleeping;
-		qdisc_refcount_inc(dev->qdisc);
+		qdisc = txq->qdisc_sleeping;
+		rcu_assign_pointer(dev->qdisc, qdisc);
+		qdisc_refcount_inc(qdisc);
 	} else {
 		qdisc = qdisc_create_dflt(txq, &mq_qdisc_ops, TC_H_ROOT, NULL);
 		if (qdisc) {
-			dev->qdisc = qdisc;
+			rcu_assign_pointer(dev->qdisc, qdisc);
 			qdisc->ops->attach(qdisc);
 		}
 	}
+	qdisc = rtnl_dereference(dev->qdisc);
 
 	/* Detect default qdisc setup/init failed and fallback to "noqueue" */
-	if (dev->qdisc == &noop_qdisc) {
+	if (qdisc == &noop_qdisc) {
 		netdev_warn(dev, "default qdisc (%s) fail, fallback to %s\n",
 			    default_qdisc_ops->id, noqueue_qdisc_ops.id);
 		dev->priv_flags |= IFF_NO_QUEUE;
 		netdev_for_each_tx_queue(dev, attach_one_default_qdisc, NULL);
-		dev->qdisc = txq->qdisc_sleeping;
-		qdisc_refcount_inc(dev->qdisc);
+		qdisc = txq->qdisc_sleeping;
+		rcu_assign_pointer(dev->qdisc, qdisc);
+		qdisc_refcount_inc(qdisc);
 		dev->priv_flags ^= IFF_NO_QUEUE;
 	}
 
 #ifdef CONFIG_NET_SCHED
-	if (dev->qdisc != &noop_qdisc)
-		qdisc_hash_add(dev->qdisc, false);
+	if (qdisc != &noop_qdisc)
+		qdisc_hash_add(qdisc, false);
 #endif
 }
 
@@ -1167,7 +1170,7 @@ void dev_activate(struct net_device *dev)
 	 * and noqueue_qdisc for virtual interfaces
 	 */
 
-	if (dev->qdisc == &noop_qdisc)
+	if (rtnl_dereference(dev->qdisc) == &noop_qdisc)
 		attach_default_qdiscs(dev);
 
 	if (!netif_carrier_ok(dev))
@@ -1333,7 +1336,7 @@ static int qdisc_change_tx_queue_len(struct net_device *dev,
 void dev_qdisc_change_real_num_tx(struct net_device *dev,
 				  unsigned int new_real_tx)
 {
-	struct Qdisc *qdisc = dev->qdisc;
+	struct Qdisc *qdisc = rtnl_dereference(dev->qdisc);
 
 	if (qdisc->ops->change_real_num_tx)
 		qdisc->ops->change_real_num_tx(qdisc, new_real_tx);
@@ -1373,7 +1376,7 @@ static void dev_init_scheduler_queue(struct net_device *dev,
 
 void dev_init_scheduler(struct net_device *dev)
 {
-	dev->qdisc = &noop_qdisc;
+	rcu_assign_pointer(dev->qdisc, &noop_qdisc);
 	netdev_for_each_tx_queue(dev, dev_init_scheduler_queue, &noop_qdisc);
 	if (dev_ingress_queue(dev))
 		dev_init_scheduler_queue(dev, dev_ingress_queue(dev), &noop_qdisc);
@@ -1401,8 +1404,8 @@ void dev_shutdown(struct net_device *dev)
 	netdev_for_each_tx_queue(dev, shutdown_scheduler_queue, &noop_qdisc);
 	if (dev_ingress_queue(dev))
 		shutdown_scheduler_queue(dev, dev_ingress_queue(dev), &noop_qdisc);
-	qdisc_put(dev->qdisc);
-	dev->qdisc = &noop_qdisc;
+	qdisc_put(rtnl_dereference(dev->qdisc));
+	rcu_assign_pointer(dev->qdisc, &noop_qdisc);
 
 	WARN_ON(timer_pending(&dev->watchdog_timer));
 }
diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index a66398fb2d6d..474ba4db5de2 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -417,7 +417,8 @@ static int taprio_enqueue_one(struct sk_buff *skb, struct Qdisc *sch,
 {
 	struct taprio_sched *q = qdisc_priv(sch);
 
-	if (skb->sk && sock_flag(skb->sk, SOCK_TXTIME)) {
+	/* sk_flags are only safe to use on full sockets. */
+	if (skb->sk && sk_fullsock(skb->sk) && sock_flag(skb->sk, SOCK_TXTIME)) {
 		if (!is_valid_interval(skb, sch))
 			return qdisc_drop(skb, sch, to_free);
 	} else if (TXTIME_ASSIST_IS_ENABLED(q->flags)) {
diff --git a/net/sctp/diag.c b/net/sctp/diag.c
index 034e2c74497d..d9c6d8f30f09 100644
--- a/net/sctp/diag.c
+++ b/net/sctp/diag.c
@@ -61,10 +61,6 @@ static void inet_diag_msg_sctpasoc_fill(struct inet_diag_msg *r,
 		r->idiag_timer = SCTP_EVENT_TIMEOUT_T3_RTX;
 		r->idiag_retrans = asoc->rtx_data_chunks;
 		r->idiag_expires = jiffies_to_msecs(t3_rtx->expires - jiffies);
-	} else {
-		r->idiag_timer = 0;
-		r->idiag_retrans = 0;
-		r->idiag_expires = 0;
 	}
 }
 
@@ -144,13 +140,14 @@ static int inet_sctp_diag_fill(struct sock *sk, struct sctp_association *asoc,
 	r = nlmsg_data(nlh);
 	BUG_ON(!sk_fullsock(sk));
 
+	r->idiag_timer = 0;
+	r->idiag_retrans = 0;
+	r->idiag_expires = 0;
 	if (asoc) {
 		inet_diag_msg_sctpasoc_fill(r, sk, asoc);
 	} else {
 		inet_diag_msg_common_fill(r, sk);
 		r->idiag_state = sk->sk_state;
-		r->idiag_timer = 0;
-		r->idiag_retrans = 0;
 	}
 
 	if (inet_diag_msg_attrs_fill(sk, skb, r, ext, user_ns, net_admin))
diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c
index ff47091c385e..b3950963fc8f 100644
--- a/net/sctp/outqueue.c
+++ b/net/sctp/outqueue.c
@@ -911,6 +911,7 @@ static void sctp_outq_flush_ctrl(struct sctp_flush_ctx *ctx)
 				ctx->asoc->base.sk->sk_err = -error;
 				return;
 			}
+			ctx->asoc->stats.octrlchunks++;
 			break;
 
 		case SCTP_CID_ABORT:
@@ -935,7 +936,10 @@ static void sctp_outq_flush_ctrl(struct sctp_flush_ctx *ctx)
 
 		case SCTP_CID_HEARTBEAT:
 			if (chunk->pmtu_probe) {
-				sctp_packet_singleton(ctx->transport, chunk, ctx->gfp);
+				error = sctp_packet_singleton(ctx->transport,
+							      chunk, ctx->gfp);
+				if (!error)
+					ctx->asoc->stats.octrlchunks++;
 				break;
 			}
 			fallthrough;
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 6b3c32264cbc..5f6e6a6e91b3 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -5641,7 +5641,7 @@ int sctp_do_peeloff(struct sock *sk, sctp_assoc_t id, struct socket **sockp)
 	 * Set the daddr and initialize id to something more random and also
 	 * copy over any ip options.
 	 */
-	sp->pf->to_sk_daddr(&asoc->peer.primary_addr, sk);
+	sp->pf->to_sk_daddr(&asoc->peer.primary_addr, sock->sk);
 	sp->pf->copy_ip_options(sk, sock->sk);
 
 	/* Populate the fields of the newsk from the oldsk and migrate the
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 96dee4a62385..499058248bdb 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -182,7 +182,7 @@ static int smc_release(struct socket *sock)
 {
 	struct sock *sk = sock->sk;
 	struct smc_sock *smc;
-	int rc = 0;
+	int old_state, rc = 0;
 
 	if (!sk)
 		goto out;
@@ -190,8 +190,10 @@ static int smc_release(struct socket *sock)
 	sock_hold(sk); /* sock_put below */
 	smc = smc_sk(sk);
 
+	old_state = sk->sk_state;
+
 	/* cleanup for a dangling non-blocking connect */
-	if (smc->connect_nonblock && sk->sk_state == SMC_INIT)
+	if (smc->connect_nonblock && old_state == SMC_INIT)
 		tcp_abort(smc->clcsock->sk, ECONNABORTED);
 
 	if (cancel_work_sync(&smc->connect_work))
@@ -205,6 +207,10 @@ static int smc_release(struct socket *sock)
 	else
 		lock_sock(sk);
 
+	if (old_state == SMC_INIT && sk->sk_state == SMC_ACTIVE &&
+	    !smc->use_fallback)
+		smc_close_active_abort(smc);
+
 	rc = __smc_release(smc);
 
 	/* detach socket */
@@ -649,14 +655,17 @@ static void smc_fback_error_report(struct sock *clcsk)
 static int smc_switch_to_fallback(struct smc_sock *smc, int reason_code)
 {
 	struct sock *clcsk;
+	int rc = 0;
 
 	mutex_lock(&smc->clcsock_release_lock);
 	if (!smc->clcsock) {
-		mutex_unlock(&smc->clcsock_release_lock);
-		return -EBADF;
+		rc = -EBADF;
+		goto out;
 	}
 	clcsk = smc->clcsock->sk;
 
+	if (smc->use_fallback)
+		goto out;
 	smc->use_fallback = true;
 	smc->fallback_rsn = reason_code;
 	smc_stat_fallback(smc);
@@ -683,8 +692,9 @@ static int smc_switch_to_fallback(struct smc_sock *smc, int reason_code)
 		smc->clcsock->sk->sk_user_data =
 			(void *)((uintptr_t)smc | SK_USER_DATA_NOCOPY);
 	}
+out:
 	mutex_unlock(&smc->clcsock_release_lock);
-	return 0;
+	return rc;
 }
 
 /* fall back during connect */
@@ -2322,8 +2332,10 @@ static int smc_shutdown(struct socket *sock, int how)
 	if (smc->use_fallback) {
 		rc = kernel_sock_shutdown(smc->clcsock, how);
 		sk->sk_shutdown = smc->clcsock->sk->sk_shutdown;
-		if (sk->sk_shutdown == SHUTDOWN_MASK)
+		if (sk->sk_shutdown == SHUTDOWN_MASK) {
 			sk->sk_state = SMC_CLOSED;
+			sock_put(sk);
+		}
 		goto out;
 	}
 	switch (how) {
@@ -2409,8 +2421,8 @@ static int smc_setsockopt(struct socket *sock, int level, int optname,
 		    sk->sk_state != SMC_CLOSED) {
 			if (val) {
 				SMC_STAT_INC(smc, ndly_cnt);
-				mod_delayed_work(smc->conn.lgr->tx_wq,
-						 &smc->conn.tx_work, 0);
+				smc_tx_pending(&smc->conn);
+				cancel_delayed_work(&smc->conn.tx_work);
 			}
 		}
 		break;
@@ -2420,8 +2432,8 @@ static int smc_setsockopt(struct socket *sock, int level, int optname,
 		    sk->sk_state != SMC_CLOSED) {
 			if (!val) {
 				SMC_STAT_INC(smc, cork_cnt);
-				mod_delayed_work(smc->conn.lgr->tx_wq,
-						 &smc->conn.tx_work, 0);
+				smc_tx_pending(&smc->conn);
+				cancel_delayed_work(&smc->conn.tx_work);
 			}
 		}
 		break;
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 36e93a3f284d..7401ec67ebcf 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -1061,8 +1061,8 @@ void smc_conn_free(struct smc_connection *conn)
 			cancel_work_sync(&conn->abort_work);
 	}
 	if (!list_empty(&lgr->list)) {
-		smc_lgr_unregister_conn(conn);
 		smc_buf_unuse(conn, lgr); /* allow buffer reuse */
+		smc_lgr_unregister_conn(conn);
 	}
 
 	if (!lgr->conns_num)
@@ -1701,7 +1701,8 @@ int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini)
 		    (ini->smcd_version == SMC_V2 ||
 		     lgr->vlan_id == ini->vlan_id) &&
 		    (role == SMC_CLNT || ini->is_smcd ||
-		     lgr->conns_num < SMC_RMBS_PER_LGR_MAX)) {
+		    (lgr->conns_num < SMC_RMBS_PER_LGR_MAX &&
+		      !bitmap_full(lgr->rtokens_used_mask, SMC_RMBS_PER_LGR_MAX)))) {
 			/* link group found */
 			ini->first_contact_local = 0;
 			conn->lgr = lgr;
@@ -1821,7 +1822,7 @@ static struct smc_buf_desc *smc_buf_get_slot(int compressed_bufsize,
  */
 static inline int smc_rmb_wnd_update_limit(int rmbe_size)
 {
-	return min_t(int, rmbe_size / 10, SOCK_MIN_SNDBUF / 2);
+	return max_t(int, rmbe_size / 10, SOCK_MIN_SNDBUF / 2);
 }
 
 /* map an rmb buf to a link */
diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c
index 4a964e9190b0..79ee0618d919 100644
--- a/net/smc/smc_pnet.c
+++ b/net/smc/smc_pnet.c
@@ -112,7 +112,7 @@ static int smc_pnet_remove_by_pnetid(struct net *net, char *pnet_name)
 	pnettable = &sn->pnettable;
 
 	/* remove table entry */
-	write_lock(&pnettable->lock);
+	mutex_lock(&pnettable->lock);
 	list_for_each_entry_safe(pnetelem, tmp_pe, &pnettable->pnetlist,
 				 list) {
 		if (!pnet_name ||
@@ -130,7 +130,7 @@ static int smc_pnet_remove_by_pnetid(struct net *net, char *pnet_name)
 			rc = 0;
 		}
 	}
-	write_unlock(&pnettable->lock);
+	mutex_unlock(&pnettable->lock);
 
 	/* if this is not the initial namespace, stop here */
 	if (net != &init_net)
@@ -191,7 +191,7 @@ static int smc_pnet_add_by_ndev(struct net_device *ndev)
 	sn = net_generic(net, smc_net_id);
 	pnettable = &sn->pnettable;
 
-	write_lock(&pnettable->lock);
+	mutex_lock(&pnettable->lock);
 	list_for_each_entry_safe(pnetelem, tmp_pe, &pnettable->pnetlist, list) {
 		if (pnetelem->type == SMC_PNET_ETH && !pnetelem->ndev &&
 		    !strncmp(pnetelem->eth_name, ndev->name, IFNAMSIZ)) {
@@ -205,7 +205,7 @@ static int smc_pnet_add_by_ndev(struct net_device *ndev)
 			break;
 		}
 	}
-	write_unlock(&pnettable->lock);
+	mutex_unlock(&pnettable->lock);
 	return rc;
 }
 
@@ -223,7 +223,7 @@ static int smc_pnet_remove_by_ndev(struct net_device *ndev)
 	sn = net_generic(net, smc_net_id);
 	pnettable = &sn->pnettable;
 
-	write_lock(&pnettable->lock);
+	mutex_lock(&pnettable->lock);
 	list_for_each_entry_safe(pnetelem, tmp_pe, &pnettable->pnetlist, list) {
 		if (pnetelem->type == SMC_PNET_ETH && pnetelem->ndev == ndev) {
 			dev_put(pnetelem->ndev);
@@ -236,7 +236,7 @@ static int smc_pnet_remove_by_ndev(struct net_device *ndev)
 			break;
 		}
 	}
-	write_unlock(&pnettable->lock);
+	mutex_unlock(&pnettable->lock);
 	return rc;
 }
 
@@ -310,8 +310,9 @@ static struct smc_ib_device *smc_pnet_find_ib(char *ib_name)
 	list_for_each_entry(ibdev, &smc_ib_devices.list, list) {
 		if (!strncmp(ibdev->ibdev->name, ib_name,
 			     sizeof(ibdev->ibdev->name)) ||
-		    !strncmp(dev_name(ibdev->ibdev->dev.parent), ib_name,
-			     IB_DEVICE_NAME_MAX - 1)) {
+		    (ibdev->ibdev->dev.parent &&
+		     !strncmp(dev_name(ibdev->ibdev->dev.parent), ib_name,
+			     IB_DEVICE_NAME_MAX - 1))) {
 			goto out;
 		}
 	}
@@ -371,7 +372,7 @@ static int smc_pnet_add_eth(struct smc_pnettable *pnettable, struct net *net,
 
 	rc = -EEXIST;
 	new_netdev = true;
-	write_lock(&pnettable->lock);
+	mutex_lock(&pnettable->lock);
 	list_for_each_entry(tmp_pe, &pnettable->pnetlist, list) {
 		if (tmp_pe->type == SMC_PNET_ETH &&
 		    !strncmp(tmp_pe->eth_name, eth_name, IFNAMSIZ)) {
@@ -381,9 +382,9 @@ static int smc_pnet_add_eth(struct smc_pnettable *pnettable, struct net *net,
 	}
 	if (new_netdev) {
 		list_add_tail(&new_pe->list, &pnettable->pnetlist);
-		write_unlock(&pnettable->lock);
+		mutex_unlock(&pnettable->lock);
 	} else {
-		write_unlock(&pnettable->lock);
+		mutex_unlock(&pnettable->lock);
 		kfree(new_pe);
 		goto out_put;
 	}
@@ -444,7 +445,7 @@ static int smc_pnet_add_ib(struct smc_pnettable *pnettable, char *ib_name,
 	new_pe->ib_port = ib_port;
 
 	new_ibdev = true;
-	write_lock(&pnettable->lock);
+	mutex_lock(&pnettable->lock);
 	list_for_each_entry(tmp_pe, &pnettable->pnetlist, list) {
 		if (tmp_pe->type == SMC_PNET_IB &&
 		    !strncmp(tmp_pe->ib_name, ib_name, IB_DEVICE_NAME_MAX)) {
@@ -454,9 +455,9 @@ static int smc_pnet_add_ib(struct smc_pnettable *pnettable, char *ib_name,
 	}
 	if (new_ibdev) {
 		list_add_tail(&new_pe->list, &pnettable->pnetlist);
-		write_unlock(&pnettable->lock);
+		mutex_unlock(&pnettable->lock);
 	} else {
-		write_unlock(&pnettable->lock);
+		mutex_unlock(&pnettable->lock);
 		kfree(new_pe);
 	}
 	return (new_ibdev) ? 0 : -EEXIST;
@@ -601,7 +602,7 @@ static int _smc_pnet_dump(struct net *net, struct sk_buff *skb, u32 portid,
 	pnettable = &sn->pnettable;
 
 	/* dump pnettable entries */
-	read_lock(&pnettable->lock);
+	mutex_lock(&pnettable->lock);
 	list_for_each_entry(pnetelem, &pnettable->pnetlist, list) {
 		if (pnetid && !smc_pnet_match(pnetelem->pnet_name, pnetid))
 			continue;
@@ -616,7 +617,7 @@ static int _smc_pnet_dump(struct net *net, struct sk_buff *skb, u32 portid,
 			break;
 		}
 	}
-	read_unlock(&pnettable->lock);
+	mutex_unlock(&pnettable->lock);
 	return idx;
 }
 
@@ -860,7 +861,7 @@ int smc_pnet_net_init(struct net *net)
 	struct smc_pnetids_ndev *pnetids_ndev = &sn->pnetids_ndev;
 
 	INIT_LIST_HEAD(&pnettable->pnetlist);
-	rwlock_init(&pnettable->lock);
+	mutex_init(&pnettable->lock);
 	INIT_LIST_HEAD(&pnetids_ndev->list);
 	rwlock_init(&pnetids_ndev->lock);
 
@@ -940,7 +941,7 @@ static int smc_pnet_find_ndev_pnetid_by_table(struct net_device *ndev,
 	sn = net_generic(net, smc_net_id);
 	pnettable = &sn->pnettable;
 
-	read_lock(&pnettable->lock);
+	mutex_lock(&pnettable->lock);
 	list_for_each_entry(pnetelem, &pnettable->pnetlist, list) {
 		if (pnetelem->type == SMC_PNET_ETH && ndev == pnetelem->ndev) {
 			/* get pnetid of netdev device */
@@ -949,7 +950,7 @@ static int smc_pnet_find_ndev_pnetid_by_table(struct net_device *ndev,
 			break;
 		}
 	}
-	read_unlock(&pnettable->lock);
+	mutex_unlock(&pnettable->lock);
 	return rc;
 }
 
@@ -1130,7 +1131,7 @@ int smc_pnetid_by_table_ib(struct smc_ib_device *smcibdev, u8 ib_port)
 	sn = net_generic(&init_net, smc_net_id);
 	pnettable = &sn->pnettable;
 
-	read_lock(&pnettable->lock);
+	mutex_lock(&pnettable->lock);
 	list_for_each_entry(tmp_pe, &pnettable->pnetlist, list) {
 		if (tmp_pe->type == SMC_PNET_IB &&
 		    !strncmp(tmp_pe->ib_name, ib_name, IB_DEVICE_NAME_MAX) &&
@@ -1140,7 +1141,7 @@ int smc_pnetid_by_table_ib(struct smc_ib_device *smcibdev, u8 ib_port)
 			break;
 		}
 	}
-	read_unlock(&pnettable->lock);
+	mutex_unlock(&pnettable->lock);
 
 	return rc;
 }
@@ -1159,7 +1160,7 @@ int smc_pnetid_by_table_smcd(struct smcd_dev *smcddev)
 	sn = net_generic(&init_net, smc_net_id);
 	pnettable = &sn->pnettable;
 
-	read_lock(&pnettable->lock);
+	mutex_lock(&pnettable->lock);
 	list_for_each_entry(tmp_pe, &pnettable->pnetlist, list) {
 		if (tmp_pe->type == SMC_PNET_IB &&
 		    !strncmp(tmp_pe->ib_name, ib_name, IB_DEVICE_NAME_MAX)) {
@@ -1168,7 +1169,7 @@ int smc_pnetid_by_table_smcd(struct smcd_dev *smcddev)
 			break;
 		}
 	}
-	read_unlock(&pnettable->lock);
+	mutex_unlock(&pnettable->lock);
 
 	return rc;
 }
diff --git a/net/smc/smc_pnet.h b/net/smc/smc_pnet.h
index 14039272f7e4..80a88eea4949 100644
--- a/net/smc/smc_pnet.h
+++ b/net/smc/smc_pnet.h
@@ -29,7 +29,7 @@ struct smc_link_group;
  * @pnetlist: List of PNETIDs
  */
 struct smc_pnettable {
-	rwlock_t lock;
+	struct mutex lock;
 	struct list_head pnetlist;
 };
 
diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c
index 738a4a99c827..31ee76131a79 100644
--- a/net/smc/smc_tx.c
+++ b/net/smc/smc_tx.c
@@ -594,27 +594,32 @@ int smc_tx_sndbuf_nonempty(struct smc_connection *conn)
 	return rc;
 }
 
-/* Wakeup sndbuf consumers from process context
- * since there is more data to transmit
- */
-void smc_tx_work(struct work_struct *work)
+void smc_tx_pending(struct smc_connection *conn)
 {
-	struct smc_connection *conn = container_of(to_delayed_work(work),
-						   struct smc_connection,
-						   tx_work);
 	struct smc_sock *smc = container_of(conn, struct smc_sock, conn);
 	int rc;
 
-	lock_sock(&smc->sk);
 	if (smc->sk.sk_err)
-		goto out;
+		return;
 
 	rc = smc_tx_sndbuf_nonempty(conn);
 	if (!rc && conn->local_rx_ctrl.prod_flags.write_blocked &&
 	    !atomic_read(&conn->bytes_to_rcv))
 		conn->local_rx_ctrl.prod_flags.write_blocked = 0;
+}
+
+/* Wakeup sndbuf consumers from process context
+ * since there is more data to transmit
+ */
+void smc_tx_work(struct work_struct *work)
+{
+	struct smc_connection *conn = container_of(to_delayed_work(work),
+						   struct smc_connection,
+						   tx_work);
+	struct smc_sock *smc = container_of(conn, struct smc_sock, conn);
 
-out:
+	lock_sock(&smc->sk);
+	smc_tx_pending(conn);
 	release_sock(&smc->sk);
 }
 
diff --git a/net/smc/smc_tx.h b/net/smc/smc_tx.h
index 07e6ad76224a..a59f370b8b43 100644
--- a/net/smc/smc_tx.h
+++ b/net/smc/smc_tx.h
@@ -27,6 +27,7 @@ static inline int smc_tx_prepared_sends(struct smc_connection *conn)
 	return smc_curs_diff(conn->sndbuf_desc->len, &sent, &prep);
 }
 
+void smc_tx_pending(struct smc_connection *conn);
 void smc_tx_work(struct work_struct *work);
 void smc_tx_init(struct smc_sock *smc);
 int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len);
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 5da1d7e8468a..3286add1a958 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -1065,7 +1065,9 @@ rpc_task_get_next_xprt(struct rpc_clnt *clnt)
 static
 void rpc_task_set_transport(struct rpc_task *task, struct rpc_clnt *clnt)
 {
-	if (task->tk_xprt)
+	if (task->tk_xprt &&
+			!(test_bit(XPRT_OFFLINE, &task->tk_xprt->state) &&
+                        (task->tk_flags & RPC_TASK_MOVEABLE)))
 		return;
 	if (task->tk_flags & RPC_TASK_NO_ROUND_ROBIN)
 		task->tk_xprt = rpc_task_get_first_xprt(clnt);
@@ -2200,6 +2202,7 @@ call_transmit_status(struct rpc_task *task)
 		 * socket just returned a connection error,
 		 * then hold onto the transport lock.
 		 */
+	case -ENOMEM:
 	case -ENOBUFS:
 		rpc_delay(task, HZ>>2);
 		fallthrough;
@@ -2283,6 +2286,7 @@ call_bc_transmit_status(struct rpc_task *task)
 	case -ENOTCONN:
 	case -EPIPE:
 		break;
+	case -ENOMEM:
 	case -ENOBUFS:
 		rpc_delay(task, HZ>>2);
 		fallthrough;
@@ -2365,6 +2369,11 @@ call_status(struct rpc_task *task)
 	case -EPIPE:
 	case -EAGAIN:
 		break;
+	case -ENFILE:
+	case -ENOBUFS:
+	case -ENOMEM:
+		rpc_delay(task, HZ>>2);
+		break;
 	case -EIO:
 		/* shutdown or soft timeout */
 		goto out_exit;
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index c045f63d11fa..f0f55fbd1375 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -186,11 +186,6 @@ static void __rpc_add_wait_queue_priority(struct rpc_wait_queue *queue,
 
 /*
  * Add new request to wait queue.
- *
- * Swapper tasks always get inserted at the head of the queue.
- * This should avoid many nasty memory deadlocks and hopefully
- * improve overall performance.
- * Everyone else gets appended to the queue to ensure proper FIFO behavior.
  */
 static void __rpc_add_wait_queue(struct rpc_wait_queue *queue,
 		struct rpc_task *task,
@@ -199,8 +194,6 @@ static void __rpc_add_wait_queue(struct rpc_wait_queue *queue,
 	INIT_LIST_HEAD(&task->u.tk_wait.timer_list);
 	if (RPC_IS_PRIORITY(queue))
 		__rpc_add_wait_queue_priority(queue, task, queue_priority);
-	else if (RPC_IS_SWAPPER(task))
-		list_add(&task->u.tk_wait.list, &queue->tasks[0]);
 	else
 		list_add_tail(&task->u.tk_wait.list, &queue->tasks[0]);
 	task->tk_waitqueue = queue;
@@ -1012,8 +1005,10 @@ int rpc_malloc(struct rpc_task *task)
 	struct rpc_buffer *buf;
 	gfp_t gfp = GFP_NOFS;
 
+	if (RPC_IS_ASYNC(task))
+		gfp = GFP_NOWAIT | __GFP_NOWARN;
 	if (RPC_IS_SWAPPER(task))
-		gfp = __GFP_MEMALLOC | GFP_NOWAIT | __GFP_NOWARN;
+		gfp |= __GFP_MEMALLOC;
 
 	size += sizeof(struct rpc_buffer);
 	if (size <= RPC_BUFFER_MAXSIZE)
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index a3bbe5ce4570..08ca797bb8a4 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1676,16 +1676,17 @@ EXPORT_SYMBOL_GPL(svc_encode_result_payload);
 /**
  * svc_fill_write_vector - Construct data argument for VFS write call
  * @rqstp: svc_rqst to operate on
- * @pages: list of pages containing data payload
- * @first: buffer containing first section of write payload
- * @total: total number of bytes of write payload
+ * @payload: xdr_buf containing only the write data payload
  *
  * Fills in rqstp::rq_vec, and returns the number of elements.
  */
-unsigned int svc_fill_write_vector(struct svc_rqst *rqstp, struct page **pages,
-				   struct kvec *first, size_t total)
+unsigned int svc_fill_write_vector(struct svc_rqst *rqstp,
+				   struct xdr_buf *payload)
 {
+	struct page **pages = payload->pages;
+	struct kvec *first = payload->head;
 	struct kvec *vec = rqstp->rq_vec;
+	size_t total = payload->len;
 	unsigned int i;
 
 	/* Some types of transport can present the write payload
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 6316bd2b8f37..935bba065636 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -243,7 +243,7 @@ static struct svc_xprt *__svc_xpo_create(struct svc_xprt_class *xcl,
 	xprt = xcl->xcl_ops->xpo_create(serv, net, sap, len, flags);
 	if (IS_ERR(xprt))
 		trace_svc_xprt_create_err(serv->sv_program->pg_name,
-					  xcl->xcl_name, sap, xprt);
+					  xcl->xcl_name, sap, len, xprt);
 	return xprt;
 }
 
@@ -1213,6 +1213,8 @@ static struct cache_deferred_req *svc_defer(struct cache_req *req)
 		dr->daddr = rqstp->rq_daddr;
 		dr->argslen = rqstp->rq_arg.len >> 2;
 		dr->xprt_hlen = rqstp->rq_xprt_hlen;
+		dr->xprt_ctxt = rqstp->rq_xprt_ctxt;
+		rqstp->rq_xprt_ctxt = NULL;
 
 		/* back up head to the start of the buffer and copy */
 		skip = rqstp->rq_arg.len - rqstp->rq_arg.head[0].iov_len;
@@ -1251,6 +1253,7 @@ static noinline int svc_deferred_recv(struct svc_rqst *rqstp)
 	rqstp->rq_xprt_hlen   = dr->xprt_hlen;
 	rqstp->rq_daddr       = dr->daddr;
 	rqstp->rq_respages    = rqstp->rq_pages;
+	rqstp->rq_xprt_ctxt   = dr->xprt_ctxt;
 	svc_xprt_received(rqstp->rq_xprt);
 	return (dr->argslen<<2) - dr->xprt_hlen;
 }
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 478f857cdaed..6ea3d87e1147 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -1096,7 +1096,9 @@ static int svc_tcp_sendmsg(struct socket *sock, struct xdr_buf *xdr,
 	int ret;
 
 	*sentp = 0;
-	xdr_alloc_bvec(xdr, GFP_KERNEL);
+	ret = xdr_alloc_bvec(xdr, GFP_KERNEL);
+	if (ret < 0)
+		return ret;
 
 	ret = kernel_sendmsg(sock, &msg, &rm, 1, rm.iov_len);
 	if (ret < 0)
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index d4aeee83763e..e4adb780b69e 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -767,7 +767,8 @@ EXPORT_SYMBOL_GPL(xprt_disconnect_done);
  */
 static void xprt_schedule_autoclose_locked(struct rpc_xprt *xprt)
 {
-	set_bit(XPRT_CLOSE_WAIT, &xprt->state);
+	if (test_and_set_bit(XPRT_CLOSE_WAIT, &xprt->state))
+		return;
 	if (test_and_set_bit(XPRT_LOCKED, &xprt->state) == 0)
 		queue_work(xprtiod_workqueue, &xprt->task_cleanup);
 	else if (xprt->snd_task && !test_bit(XPRT_SND_IS_COOKIE, &xprt->state))
@@ -1353,17 +1354,6 @@ xprt_request_enqueue_transmit(struct rpc_task *task)
 				INIT_LIST_HEAD(&req->rq_xmit2);
 				goto out;
 			}
-		} else if (RPC_IS_SWAPPER(task)) {
-			list_for_each_entry(pos, &xprt->xmit_queue, rq_xmit) {
-				if (pos->rq_cong || pos->rq_bytes_sent)
-					continue;
-				if (RPC_IS_SWAPPER(pos->rq_task))
-					continue;
-				/* Note: req is added _before_ pos */
-				list_add_tail(&req->rq_xmit, &pos->rq_xmit);
-				INIT_LIST_HEAD(&req->rq_xmit2);
-				goto out;
-			}
 		} else if (!req->rq_seqno) {
 			list_for_each_entry(pos, &xprt->xmit_queue, rq_xmit) {
 				if (pos->rq_task->tk_owner != task->tk_owner)
@@ -1686,12 +1676,15 @@ out:
 static struct rpc_rqst *xprt_dynamic_alloc_slot(struct rpc_xprt *xprt)
 {
 	struct rpc_rqst *req = ERR_PTR(-EAGAIN);
+	gfp_t gfp_mask = GFP_KERNEL;
 
 	if (xprt->num_reqs >= xprt->max_reqs)
 		goto out;
 	++xprt->num_reqs;
 	spin_unlock(&xprt->reserve_lock);
-	req = kzalloc(sizeof(struct rpc_rqst), GFP_NOFS);
+	if (current->flags & PF_WQ_WORKER)
+		gfp_mask |= __GFP_NORETRY | __GFP_NOWARN;
+	req = kzalloc(sizeof(*req), gfp_mask);
 	spin_lock(&xprt->reserve_lock);
 	if (req != NULL)
 		goto out;
@@ -2111,7 +2104,14 @@ static void xprt_destroy(struct rpc_xprt *xprt)
 	 */
 	wait_on_bit_lock(&xprt->state, XPRT_LOCKED, TASK_UNINTERRUPTIBLE);
 
+	/*
+	 * xprt_schedule_autodisconnect() can run after XPRT_LOCKED
+	 * is cleared.  We use ->transport_lock to ensure the mod_timer()
+	 * can only run *before* del_time_sync(), never after.
+	 */
+	spin_lock(&xprt->transport_lock);
 	del_timer_sync(&xprt->timer);
+	spin_unlock(&xprt->transport_lock);
 
 	/*
 	 * Destroy sockets etc from the system workqueue so they can
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index 6be23ce7a93d..387a5da09daf 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -826,7 +826,7 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
 		goto out_err;
 	if (ret == 0)
 		goto out_drop;
-	rqstp->rq_xprt_hlen = ret;
+	rqstp->rq_xprt_hlen = 0;
 
 	if (svc_rdma_is_reverse_direction_reply(xprt, ctxt))
 		goto out_backchannel;
diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index 16e5696314a4..32df23796747 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -521,7 +521,7 @@ xprt_rdma_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task)
 	return;
 
 out_sleep:
-	task->tk_status = -EAGAIN;
+	task->tk_status = -ENOMEM;
 	xprt_add_backlog(xprt, task);
 }
 
@@ -574,8 +574,10 @@ xprt_rdma_allocate(struct rpc_task *task)
 	gfp_t flags;
 
 	flags = RPCRDMA_DEF_GFP;
+	if (RPC_IS_ASYNC(task))
+		flags = GFP_NOWAIT | __GFP_NOWARN;
 	if (RPC_IS_SWAPPER(task))
-		flags = __GFP_MEMALLOC | GFP_NOWAIT | __GFP_NOWARN;
+		flags |= __GFP_MEMALLOC;
 
 	if (!rpcrdma_check_regbuf(r_xprt, req->rl_sendbuf, rqst->rq_callsize,
 				  flags))
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index aaec3c9be8db..1295f9ab839f 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -438,6 +438,7 @@ static int rpcrdma_ep_create(struct rpcrdma_xprt *r_xprt)
 					      IB_POLL_WORKQUEUE);
 	if (IS_ERR(ep->re_attr.send_cq)) {
 		rc = PTR_ERR(ep->re_attr.send_cq);
+		ep->re_attr.send_cq = NULL;
 		goto out_destroy;
 	}
 
@@ -446,6 +447,7 @@ static int rpcrdma_ep_create(struct rpcrdma_xprt *r_xprt)
 					      IB_POLL_WORKQUEUE);
 	if (IS_ERR(ep->re_attr.recv_cq)) {
 		rc = PTR_ERR(ep->re_attr.recv_cq);
+		ep->re_attr.recv_cq = NULL;
 		goto out_destroy;
 	}
 	ep->re_receive_count = 0;
@@ -484,6 +486,7 @@ static int rpcrdma_ep_create(struct rpcrdma_xprt *r_xprt)
 	ep->re_pd = ib_alloc_pd(device, 0);
 	if (IS_ERR(ep->re_pd)) {
 		rc = PTR_ERR(ep->re_pd);
+		ep->re_pd = NULL;
 		goto out_destroy;
 	}
 
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 04f1b78bcbca..c2f7819827b6 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -763,12 +763,12 @@ xs_stream_start_connect(struct sock_xprt *transport)
 /**
  * xs_nospace - handle transmit was incomplete
  * @req: pointer to RPC request
+ * @transport: pointer to struct sock_xprt
  *
  */
-static int xs_nospace(struct rpc_rqst *req)
+static int xs_nospace(struct rpc_rqst *req, struct sock_xprt *transport)
 {
-	struct rpc_xprt *xprt = req->rq_xprt;
-	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
+	struct rpc_xprt *xprt = &transport->xprt;
 	struct sock *sk = transport->inet;
 	int ret = -EAGAIN;
 
@@ -779,25 +779,49 @@ static int xs_nospace(struct rpc_rqst *req)
 
 	/* Don't race with disconnect */
 	if (xprt_connected(xprt)) {
+		struct socket_wq *wq;
+
+		rcu_read_lock();
+		wq = rcu_dereference(sk->sk_wq);
+		set_bit(SOCKWQ_ASYNC_NOSPACE, &wq->flags);
+		rcu_read_unlock();
+
 		/* wait for more buffer space */
+		set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
 		sk->sk_write_pending++;
 		xprt_wait_for_buffer_space(xprt);
 	} else
 		ret = -ENOTCONN;
 
 	spin_unlock(&xprt->transport_lock);
+	return ret;
+}
 
-	/* Race breaker in case memory is freed before above code is called */
-	if (ret == -EAGAIN) {
-		struct socket_wq *wq;
+static int xs_sock_nospace(struct rpc_rqst *req)
+{
+	struct sock_xprt *transport =
+		container_of(req->rq_xprt, struct sock_xprt, xprt);
+	struct sock *sk = transport->inet;
+	int ret = -EAGAIN;
 
-		rcu_read_lock();
-		wq = rcu_dereference(sk->sk_wq);
-		set_bit(SOCKWQ_ASYNC_NOSPACE, &wq->flags);
-		rcu_read_unlock();
+	lock_sock(sk);
+	if (!sock_writeable(sk))
+		ret = xs_nospace(req, transport);
+	release_sock(sk);
+	return ret;
+}
 
-		sk->sk_write_space(sk);
-	}
+static int xs_stream_nospace(struct rpc_rqst *req)
+{
+	struct sock_xprt *transport =
+		container_of(req->rq_xprt, struct sock_xprt, xprt);
+	struct sock *sk = transport->inet;
+	int ret = -EAGAIN;
+
+	lock_sock(sk);
+	if (!sk_stream_memory_free(sk))
+		ret = xs_nospace(req, transport);
+	release_sock(sk);
 	return ret;
 }
 
@@ -887,7 +911,7 @@ static int xs_local_send_request(struct rpc_rqst *req)
 	case -ENOBUFS:
 		break;
 	case -EAGAIN:
-		status = xs_nospace(req);
+		status = xs_stream_nospace(req);
 		break;
 	default:
 		dprintk("RPC:       sendmsg returned unrecognized error %d\n",
@@ -963,7 +987,7 @@ process_status:
 		/* Should we call xs_close() here? */
 		break;
 	case -EAGAIN:
-		status = xs_nospace(req);
+		status = xs_sock_nospace(req);
 		break;
 	case -ENETUNREACH:
 	case -ENOBUFS:
@@ -1083,7 +1107,7 @@ static int xs_tcp_send_request(struct rpc_rqst *req)
 		/* Should we call xs_close() here? */
 		break;
 	case -EAGAIN:
-		status = xs_nospace(req);
+		status = xs_stream_nospace(req);
 		break;
 	case -ECONNRESET:
 	case -ECONNREFUSED:
@@ -2233,6 +2257,7 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
 		fallthrough;
 	case -EINPROGRESS:
 		/* SYN_SENT! */
+		set_bit(XPRT_SOCK_CONNECT_SENT, &transport->sock_state);
 		if (xprt->reestablish_timeout < XS_TCP_INIT_REEST_TO)
 			xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO;
 		break;
@@ -2258,10 +2283,14 @@ static void xs_tcp_setup_socket(struct work_struct *work)
 	struct rpc_xprt *xprt = &transport->xprt;
 	int status = -EIO;
 
-	if (!sock) {
-		sock = xs_create_sock(xprt, transport,
-				xs_addr(xprt)->sa_family, SOCK_STREAM,
-				IPPROTO_TCP, true);
+	if (xprt_connected(xprt))
+		goto out;
+	if (test_and_clear_bit(XPRT_SOCK_CONNECT_SENT,
+			       &transport->sock_state) ||
+	    !sock) {
+		xs_reset_transport(transport);
+		sock = xs_create_sock(xprt, transport, xs_addr(xprt)->sa_family,
+				      SOCK_STREAM, IPPROTO_TCP, true);
 		if (IS_ERR(sock)) {
 			status = PTR_ERR(sock);
 			goto out;
@@ -2343,11 +2372,7 @@ static void xs_connect(struct rpc_xprt *xprt, struct rpc_task *task)
 
 	if (transport->sock != NULL) {
 		dprintk("RPC:       xs_connect delayed xprt %p for %lu "
-				"seconds\n",
-				xprt, xprt->reestablish_timeout / HZ);
-
-		/* Start by resetting any existing state */
-		xs_reset_transport(transport);
+			"seconds\n", xprt, xprt->reestablish_timeout / HZ);
 
 		delay = xprt_reconnect_delay(xprt);
 		xprt_reconnect_backoff(xprt, XS_TCP_INIT_REEST_TO);
diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c
index 443f8e5b9477..36b466cfd9e1 100644
--- a/net/tipc/bearer.c
+++ b/net/tipc/bearer.c
@@ -352,16 +352,18 @@ static int tipc_enable_bearer(struct net *net, const char *name,
 		goto rejected;
 	}
 
-	test_and_set_bit_lock(0, &b->up);
-	rcu_assign_pointer(tn->bearer_list[bearer_id], b);
-	if (skb)
-		tipc_bearer_xmit_skb(net, bearer_id, skb, &b->bcast_addr);
-
+	/* Create monitoring data before accepting activate messages */
 	if (tipc_mon_create(net, bearer_id)) {
 		bearer_disable(net, b);
+		kfree_skb(skb);
 		return -ENOMEM;
 	}
 
+	test_and_set_bit_lock(0, &b->up);
+	rcu_assign_pointer(tn->bearer_list[bearer_id], b);
+	if (skb)
+		tipc_bearer_xmit_skb(net, bearer_id, skb, &b->bcast_addr);
+
 	pr_info("Enabled bearer <%s>, priority %u\n", name, prio);
 
 	return res;
diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c
index d293614d5fc6..b5074957e881 100644
--- a/net/tipc/crypto.c
+++ b/net/tipc/crypto.c
@@ -2287,7 +2287,7 @@ static bool tipc_crypto_key_rcv(struct tipc_crypto *rx, struct tipc_msg *hdr)
 	struct tipc_crypto *tx = tipc_net(rx->net)->crypto_tx;
 	struct tipc_aead_key *skey = NULL;
 	u16 key_gen = msg_key_gen(hdr);
-	u16 size = msg_data_sz(hdr);
+	u32 size = msg_data_sz(hdr);
 	u8 *data = msg_data(hdr);
 	unsigned int keylen;
 
diff --git a/net/tipc/link.c b/net/tipc/link.c
index 4e7936d9b442..115a4a7950f5 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -2285,6 +2285,11 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb,
 		break;
 
 	case STATE_MSG:
+		/* Validate Gap ACK blocks, drop if invalid */
+		glen = tipc_get_gap_ack_blks(&ga, l, hdr, true);
+		if (glen > dlen)
+			break;
+
 		l->rcv_nxt_state = msg_seqno(hdr) + 1;
 
 		/* Update own tolerance if peer indicates a non-zero value */
@@ -2310,10 +2315,6 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb,
 			break;
 		}
 
-		/* Receive Gap ACK blocks from peer if any */
-		glen = tipc_get_gap_ack_blks(&ga, l, hdr, true);
-		if(glen > dlen)
-			break;
 		tipc_mon_rcv(l->net, data + glen, dlen - glen, l->addr,
 			     &l->mon_state, l->bearer_id);
 
diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c
index 01396dd1c899..1d8ba233d047 100644
--- a/net/tipc/name_table.c
+++ b/net/tipc/name_table.c
@@ -967,7 +967,7 @@ static int __tipc_nl_add_nametable_publ(struct tipc_nl_msg *msg,
 		list_for_each_entry(p, &sr->all_publ, all_publ)
 			if (p->key == *last_key)
 				break;
-		if (p->key != *last_key)
+		if (list_entry_is_head(p, &sr->all_publ, all_publ))
 			return -EPIPE;
 	} else {
 		p = list_first_entry(&sr->all_publ,
diff --git a/net/tipc/node.c b/net/tipc/node.c
index 9947b7dfe1d2..6ef95ce565bd 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -403,7 +403,7 @@ static void tipc_node_write_unlock(struct tipc_node *n)
 	u32 flags = n->action_flags;
 	struct list_head *publ_list;
 	struct tipc_uaddr ua;
-	u32 bearer_id;
+	u32 bearer_id, node;
 
 	if (likely(!flags)) {
 		write_unlock_bh(&n->lock);
@@ -413,7 +413,8 @@ static void tipc_node_write_unlock(struct tipc_node *n)
 	tipc_uaddr(&ua, TIPC_SERVICE_RANGE, TIPC_NODE_SCOPE,
 		   TIPC_LINK_STATE, n->addr, n->addr);
 	sk.ref = n->link_id;
-	sk.node = n->addr;
+	sk.node = tipc_own_addr(net);
+	node = n->addr;
 	bearer_id = n->link_id & 0xffff;
 	publ_list = &n->publ_list;
 
@@ -423,17 +424,17 @@ static void tipc_node_write_unlock(struct tipc_node *n)
 	write_unlock_bh(&n->lock);
 
 	if (flags & TIPC_NOTIFY_NODE_DOWN)
-		tipc_publ_notify(net, publ_list, sk.node, n->capabilities);
+		tipc_publ_notify(net, publ_list, node, n->capabilities);
 
 	if (flags & TIPC_NOTIFY_NODE_UP)
-		tipc_named_node_up(net, sk.node, n->capabilities);
+		tipc_named_node_up(net, node, n->capabilities);
 
 	if (flags & TIPC_NOTIFY_LINK_UP) {
-		tipc_mon_peer_up(net, sk.node, bearer_id);
+		tipc_mon_peer_up(net, node, bearer_id);
 		tipc_nametbl_publish(net, &ua, &sk, sk.ref);
 	}
 	if (flags & TIPC_NOTIFY_LINK_DOWN) {
-		tipc_mon_peer_down(net, sk.node, bearer_id);
+		tipc_mon_peer_down(net, node, bearer_id);
 		tipc_nametbl_withdraw(net, &ua, &sk, sk.ref);
 	}
 }
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 3e63c83e641c..17f8c523e33b 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -2852,7 +2852,8 @@ static void tipc_sk_retry_connect(struct sock *sk, struct sk_buff_head *list)
 
 	/* Try again later if dest link is congested */
 	if (tsk->cong_link_cnt) {
-		sk_reset_timer(sk, &sk->sk_timer, msecs_to_jiffies(100));
+		sk_reset_timer(sk, &sk->sk_timer,
+			       jiffies + msecs_to_jiffies(100));
 		return;
 	}
 	/* Prepare SYN for retransmit */
@@ -3749,7 +3750,7 @@ static int __tipc_nl_list_sk_publ(struct sk_buff *skb,
 			if (p->key == *last_publ)
 				break;
 		}
-		if (p->key != *last_publ) {
+		if (list_entry_is_head(p, &tsk->publications, binding_sock)) {
 			/* We never set seq or call nl_dump_check_consistent()
 			 * this means that setting prev_seq here will cause the
 			 * consistence check to fail in the netlink callback
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index bd96ec26f4f9..794ef3b3d7d4 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -1483,7 +1483,7 @@ static int decrypt_internal(struct sock *sk, struct sk_buff *skb,
 	if (prot->version == TLS_1_3_VERSION ||
 	    prot->cipher_type == TLS_CIPHER_CHACHA20_POLY1305)
 		memcpy(iv + iv_offset, tls_ctx->rx.iv,
-		       crypto_aead_ivsize(ctx->aead_recv));
+		       prot->iv_size + prot->salt_size);
 	else
 		memcpy(iv + iv_offset, tls_ctx->rx.iv, prot->salt_size);
 
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index b0bfc78e421c..62f47821d783 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1996,7 +1996,7 @@ static int queue_oob(struct socket *sock, struct msghdr *msg, struct sock *other
 	if (ousk->oob_skb)
 		consume_skb(ousk->oob_skb);
 
-	ousk->oob_skb = skb;
+	WRITE_ONCE(ousk->oob_skb, skb);
 
 	scm_stat_add(other, skb);
 	skb_queue_tail(&other->sk_receive_queue, skb);
@@ -2514,9 +2514,8 @@ static int unix_stream_recv_urg(struct unix_stream_read_state *state)
 
 	oob_skb = u->oob_skb;
 
-	if (!(state->flags & MSG_PEEK)) {
-		u->oob_skb = NULL;
-	}
+	if (!(state->flags & MSG_PEEK))
+		WRITE_ONCE(u->oob_skb, NULL);
 
 	unix_state_unlock(sk);
 
@@ -2551,7 +2550,7 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk,
 				skb = NULL;
 			} else if (sock_flag(sk, SOCK_URGINLINE)) {
 				if (!(flags & MSG_PEEK)) {
-					u->oob_skb = NULL;
+					WRITE_ONCE(u->oob_skb, NULL);
 					consume_skb(skb);
 				}
 			} else if (!(flags & MSG_PEEK)) {
@@ -3006,11 +3005,10 @@ static int unix_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 	case SIOCATMARK:
 		{
 			struct sk_buff *skb;
-			struct unix_sock *u = unix_sk(sk);
 			int answ = 0;
 
 			skb = skb_peek(&sk->sk_receive_queue);
-			if (skb && skb == u->oob_skb)
+			if (skb && skb == READ_ONCE(unix_sk(sk)->oob_skb))
 				answ = 1;
 			err = put_user(answ, (int __user *)arg);
 		}
@@ -3051,6 +3049,10 @@ static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wa
 		mask |= EPOLLIN | EPOLLRDNORM;
 	if (sk_is_readable(sk))
 		mask |= EPOLLIN | EPOLLRDNORM;
+#if IS_ENABLED(CONFIG_AF_UNIX_OOB)
+	if (READ_ONCE(unix_sk(sk)->oob_skb))
+		mask |= EPOLLPRI;
+#endif
 
 	/* Connection-based need to check for termination and startup */
 	if ((sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) &&
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index fa8c1b623fa2..5df530e89e5a 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -333,7 +333,8 @@ void vsock_remove_sock(struct vsock_sock *vsk)
 }
 EXPORT_SYMBOL_GPL(vsock_remove_sock);
 
-void vsock_for_each_connected_socket(void (*fn)(struct sock *sk))
+void vsock_for_each_connected_socket(struct vsock_transport *transport,
+				     void (*fn)(struct sock *sk))
 {
 	int i;
 
@@ -342,8 +343,12 @@ void vsock_for_each_connected_socket(void (*fn)(struct sock *sk))
 	for (i = 0; i < ARRAY_SIZE(vsock_connected_table); i++) {
 		struct vsock_sock *vsk;
 		list_for_each_entry(vsk, &vsock_connected_table[i],
-				    connected_table)
+				    connected_table) {
+			if (vsk->transport != transport)
+				continue;
+
 			fn(sk_vsock(vsk));
+		}
 	}
 
 	spin_unlock_bh(&vsock_table_lock);
@@ -1400,6 +1405,7 @@ static int vsock_connect(struct socket *sock, struct sockaddr *addr,
 			sk->sk_state = sk->sk_state == TCP_ESTABLISHED ? TCP_CLOSING : TCP_CLOSE;
 			sock->state = SS_UNCONNECTED;
 			vsock_transport_cancel_pkt(vsk);
+			vsock_remove_connected(vsk);
 			goto out_wait;
 		} else if (timeout == 0) {
 			err = -ETIMEDOUT;
diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
index 4f7c99dfd16c..c5f936fbf876 100644
--- a/net/vmw_vsock/virtio_transport.c
+++ b/net/vmw_vsock/virtio_transport.c
@@ -24,6 +24,7 @@
 static struct workqueue_struct *virtio_vsock_workqueue;
 static struct virtio_vsock __rcu *the_virtio_vsock;
 static DEFINE_MUTEX(the_virtio_vsock_mutex); /* protects the_virtio_vsock */
+static struct virtio_transport virtio_transport; /* forward declaration */
 
 struct virtio_vsock {
 	struct virtio_device *vdev;
@@ -384,7 +385,8 @@ static void virtio_vsock_event_handle(struct virtio_vsock *vsock,
 	switch (le32_to_cpu(event->id)) {
 	case VIRTIO_VSOCK_EVENT_TRANSPORT_RESET:
 		virtio_vsock_update_guest_cid(vsock);
-		vsock_for_each_connected_socket(virtio_vsock_reset_sock);
+		vsock_for_each_connected_socket(&virtio_transport.transport,
+						virtio_vsock_reset_sock);
 		break;
 	}
 }
@@ -620,6 +622,13 @@ static int virtio_vsock_probe(struct virtio_device *vdev)
 	INIT_WORK(&vsock->event_work, virtio_transport_event_work);
 	INIT_WORK(&vsock->send_pkt_work, virtio_transport_send_pkt_work);
 
+	if (virtio_has_feature(vdev, VIRTIO_VSOCK_F_SEQPACKET))
+		vsock->seqpacket_allow = true;
+
+	vdev->priv = vsock;
+
+	virtio_device_ready(vdev);
+
 	mutex_lock(&vsock->tx_lock);
 	vsock->tx_run = true;
 	mutex_unlock(&vsock->tx_lock);
@@ -634,10 +643,6 @@ static int virtio_vsock_probe(struct virtio_device *vdev)
 	vsock->event_run = true;
 	mutex_unlock(&vsock->event_lock);
 
-	if (virtio_has_feature(vdev, VIRTIO_VSOCK_F_SEQPACKET))
-		vsock->seqpacket_allow = true;
-
-	vdev->priv = vsock;
 	rcu_assign_pointer(the_virtio_vsock, vsock);
 
 	mutex_unlock(&the_virtio_vsock_mutex);
@@ -662,7 +667,8 @@ static void virtio_vsock_remove(struct virtio_device *vdev)
 	synchronize_rcu();
 
 	/* Reset all connected sockets when the device disappear */
-	vsock_for_each_connected_socket(virtio_vsock_reset_sock);
+	vsock_for_each_connected_socket(&virtio_transport.transport,
+					virtio_vsock_reset_sock);
 
 	/* Stop all work handlers to make sure no one is accessing the device,
 	 * so we can safely call vdev->config->reset().
diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c
index 7aef34e32bdf..b17dc9745188 100644
--- a/net/vmw_vsock/vmci_transport.c
+++ b/net/vmw_vsock/vmci_transport.c
@@ -75,6 +75,8 @@ static u32 vmci_transport_qp_resumed_sub_id = VMCI_INVALID_ID;
 
 static int PROTOCOL_OVERRIDE = -1;
 
+static struct vsock_transport vmci_transport; /* forward declaration */
+
 /* Helper function to convert from a VMCI error code to a VSock error code. */
 
 static s32 vmci_transport_error_to_vsock_error(s32 vmci_error)
@@ -882,7 +884,8 @@ static void vmci_transport_qp_resumed_cb(u32 sub_id,
 					 const struct vmci_event_data *e_data,
 					 void *client_data)
 {
-	vsock_for_each_connected_socket(vmci_transport_handle_detach);
+	vsock_for_each_connected_socket(&vmci_transport,
+					vmci_transport_handle_detach);
 }
 
 static void vmci_transport_recv_pkt_work(struct work_struct *work)
diff --git a/net/wireless/core.c b/net/wireless/core.c
index eb297e1015e0..441136646f89 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -5,7 +5,7 @@
  * Copyright 2006-2010		Johannes Berg <johannes@sipsolutions.net>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
  * Copyright 2015-2017	Intel Deutschland GmbH
- * Copyright (C) 2018-2021 Intel Corporation
+ * Copyright (C) 2018-2022 Intel Corporation
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -332,29 +332,20 @@ static void cfg80211_event_work(struct work_struct *work)
 void cfg80211_destroy_ifaces(struct cfg80211_registered_device *rdev)
 {
 	struct wireless_dev *wdev, *tmp;
-	bool found = false;
 
 	ASSERT_RTNL();
 
-	list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) {
+	list_for_each_entry_safe(wdev, tmp, &rdev->wiphy.wdev_list, list) {
 		if (wdev->nl_owner_dead) {
 			if (wdev->netdev)
 				dev_close(wdev->netdev);
-			found = true;
-		}
-	}
-
-	if (!found)
-		return;
 
-	wiphy_lock(&rdev->wiphy);
-	list_for_each_entry_safe(wdev, tmp, &rdev->wiphy.wdev_list, list) {
-		if (wdev->nl_owner_dead) {
+			wiphy_lock(&rdev->wiphy);
 			cfg80211_leave(rdev, wdev);
 			rdev_del_virtual_intf(rdev, wdev);
+			wiphy_unlock(&rdev->wiphy);
 		}
 	}
-	wiphy_unlock(&rdev->wiphy);
 }
 
 static void cfg80211_destroy_iface_wk(struct work_struct *work)
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 16b3d0cc0bdb..fe9cade6b4fb 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -509,7 +509,8 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
 				   .len = IEEE80211_MAX_MESH_ID_LEN },
 	[NL80211_ATTR_MPATH_NEXT_HOP] = NLA_POLICY_ETH_ADDR_COMPAT,
 
-	[NL80211_ATTR_REG_ALPHA2] = { .type = NLA_STRING, .len = 2 },
+	/* allow 3 for NUL-termination, we used to declare this NLA_STRING */
+	[NL80211_ATTR_REG_ALPHA2] = NLA_POLICY_RANGE(NLA_BINARY, 2, 3),
 	[NL80211_ATTR_REG_RULES] = { .type = NLA_NESTED },
 
 	[NL80211_ATTR_BSS_CTS_PROT] = { .type = NLA_U8 },
@@ -13177,6 +13178,9 @@ static int handle_nan_filter(struct nlattr *attr_filter,
 	i = 0;
 	nla_for_each_nested(attr, attr_filter, rem) {
 		filter[i].filter = nla_memdup(attr, GFP_KERNEL);
+		if (!filter[i].filter)
+			goto err;
+
 		filter[i].len = nla_len(attr);
 		i++;
 	}
@@ -13189,6 +13193,15 @@ static int handle_nan_filter(struct nlattr *attr_filter,
 	}
 
 	return 0;
+
+err:
+	i = 0;
+	nla_for_each_nested(attr, attr_filter, rem) {
+		kfree(filter[i].filter);
+		i++;
+	}
+	kfree(filter);
+	return -ENOMEM;
 }
 
 static int nl80211_nan_add_func(struct sk_buff *skb,
@@ -17513,7 +17526,8 @@ void cfg80211_ch_switch_notify(struct net_device *dev,
 	wdev->chandef = *chandef;
 	wdev->preset_chandef = *chandef;
 
-	if (wdev->iftype == NL80211_IFTYPE_STATION &&
+	if ((wdev->iftype == NL80211_IFTYPE_STATION ||
+	     wdev->iftype == NL80211_IFTYPE_P2P_CLIENT) &&
 	    !WARN_ON(!wdev->current_bss))
 		cfg80211_update_assoc_bss_entry(wdev, chandef->chan);
 
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index adc0d14cfd86..1a8b76c9dd56 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -702,8 +702,12 @@ static bool cfg80211_find_ssid_match(struct cfg80211_colocated_ap *ap,
 
 	for (i = 0; i < request->n_ssids; i++) {
 		/* wildcard ssid in the scan request */
-		if (!request->ssids[i].ssid_len)
+		if (!request->ssids[i].ssid_len) {
+			if (ap->multi_bss && !ap->transmitted_bssid)
+				continue;
+
 			return true;
+		}
 
 		if (ap->ssid_len &&
 		    ap->ssid_len == request->ssids[i].ssid_len) {
@@ -829,6 +833,9 @@ static int cfg80211_scan_6ghz(struct cfg80211_registered_device *rdev)
 		    !cfg80211_find_ssid_match(ap, request))
 			continue;
 
+		if (!request->n_ssids && ap->multi_bss && !ap->transmitted_bssid)
+			continue;
+
 		cfg80211_scan_req_add_chan(request, chan, true);
 		memcpy(scan_6ghz_params->bssid, ap->bssid, ETH_ALEN);
 		scan_6ghz_params->short_ssid = ap->short_ssid;
@@ -1971,11 +1978,13 @@ cfg80211_inform_single_bss_data(struct wiphy *wiphy,
 		/* this is a nontransmitting bss, we need to add it to
 		 * transmitting bss' list if it is not there
 		 */
+		spin_lock_bh(&rdev->bss_lock);
 		if (cfg80211_add_nontrans_list(non_tx_data->tx_bss,
 					       &res->pub)) {
 			if (__cfg80211_unlink_bss(rdev, res))
 				rdev->bss_generation++;
 		}
+		spin_unlock_bh(&rdev->bss_lock);
 	}
 
 	trace_cfg80211_return_bss(&res->pub);
diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index 3583354a7d7f..3a171828638b 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -1765,10 +1765,15 @@ void x25_kill_by_neigh(struct x25_neigh *nb)
 
 	write_lock_bh(&x25_list_lock);
 
-	sk_for_each(s, &x25_list)
-		if (x25_sk(s)->neighbour == nb)
+	sk_for_each(s, &x25_list) {
+		if (x25_sk(s)->neighbour == nb) {
+			write_unlock_bh(&x25_list_lock);
+			lock_sock(s);
 			x25_disconnect(s, ENETUNREACH, 0, 0);
-
+			release_sock(s);
+			write_lock_bh(&x25_list_lock);
+		}
+	}
 	write_unlock_bh(&x25_list_lock);
 
 	/* Remove any related forwards */
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index d6b500dc4208..426e287431d2 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -418,18 +418,8 @@ EXPORT_SYMBOL(xsk_tx_peek_release_desc_batch);
 static int xsk_wakeup(struct xdp_sock *xs, u8 flags)
 {
 	struct net_device *dev = xs->dev;
-	int err;
-
-	rcu_read_lock();
-	err = dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id, flags);
-	rcu_read_unlock();
-
-	return err;
-}
 
-static int xsk_zc_xmit(struct xdp_sock *xs)
-{
-	return xsk_wakeup(xs, XDP_WAKEUP_TX);
+	return dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id, flags);
 }
 
 static void xsk_destruct_skb(struct sk_buff *skb)
@@ -548,6 +538,12 @@ static int xsk_generic_xmit(struct sock *sk)
 
 	mutex_lock(&xs->mutex);
 
+	/* Since we dropped the RCU read lock, the socket state might have changed. */
+	if (unlikely(!xsk_is_bound(xs))) {
+		err = -ENXIO;
+		goto out;
+	}
+
 	if (xs->queue_id >= xs->dev->real_num_tx_queues)
 		goto out;
 
@@ -611,16 +607,26 @@ out:
 	return err;
 }
 
-static int __xsk_sendmsg(struct sock *sk)
+static int xsk_xmit(struct sock *sk)
 {
 	struct xdp_sock *xs = xdp_sk(sk);
+	int ret;
 
 	if (unlikely(!(xs->dev->flags & IFF_UP)))
 		return -ENETDOWN;
 	if (unlikely(!xs->tx))
 		return -ENOBUFS;
 
-	return xs->zc ? xsk_zc_xmit(xs) : xsk_generic_xmit(sk);
+	if (xs->zc)
+		return xsk_wakeup(xs, XDP_WAKEUP_TX);
+
+	/* Drop the RCU lock since the SKB path might sleep. */
+	rcu_read_unlock();
+	ret = xsk_generic_xmit(sk);
+	/* Reaquire RCU lock before going into common code. */
+	rcu_read_lock();
+
+	return ret;
 }
 
 static bool xsk_no_wakeup(struct sock *sk)
@@ -634,7 +640,7 @@ static bool xsk_no_wakeup(struct sock *sk)
 #endif
 }
 
-static int xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len)
+static int __xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len)
 {
 	bool need_wait = !(m->msg_flags & MSG_DONTWAIT);
 	struct sock *sk = sock->sk;
@@ -654,11 +660,22 @@ static int xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len)
 
 	pool = xs->pool;
 	if (pool->cached_need_wakeup & XDP_WAKEUP_TX)
-		return __xsk_sendmsg(sk);
+		return xsk_xmit(sk);
 	return 0;
 }
 
-static int xsk_recvmsg(struct socket *sock, struct msghdr *m, size_t len, int flags)
+static int xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len)
+{
+	int ret;
+
+	rcu_read_lock();
+	ret = __xsk_sendmsg(sock, m, total_len);
+	rcu_read_unlock();
+
+	return ret;
+}
+
+static int __xsk_recvmsg(struct socket *sock, struct msghdr *m, size_t len, int flags)
 {
 	bool need_wait = !(flags & MSG_DONTWAIT);
 	struct sock *sk = sock->sk;
@@ -684,6 +701,17 @@ static int xsk_recvmsg(struct socket *sock, struct msghdr *m, size_t len, int fl
 	return 0;
 }
 
+static int xsk_recvmsg(struct socket *sock, struct msghdr *m, size_t len, int flags)
+{
+	int ret;
+
+	rcu_read_lock();
+	ret = __xsk_recvmsg(sock, m, len, flags);
+	rcu_read_unlock();
+
+	return ret;
+}
+
 static __poll_t xsk_poll(struct file *file, struct socket *sock,
 			     struct poll_table_struct *wait)
 {
@@ -694,8 +722,11 @@ static __poll_t xsk_poll(struct file *file, struct socket *sock,
 
 	sock_poll_wait(file, sock, wait);
 
-	if (unlikely(!xsk_is_bound(xs)))
+	rcu_read_lock();
+	if (unlikely(!xsk_is_bound(xs))) {
+		rcu_read_unlock();
 		return mask;
+	}
 
 	pool = xs->pool;
 
@@ -704,7 +735,7 @@ static __poll_t xsk_poll(struct file *file, struct socket *sock,
 			xsk_wakeup(xs, pool->cached_need_wakeup);
 		else
 			/* Poll needs to drive Tx also in copy mode */
-			__xsk_sendmsg(sk);
+			xsk_xmit(sk);
 	}
 
 	if (xs->rx && !xskq_prod_is_empty(xs->rx))
@@ -712,6 +743,7 @@ static __poll_t xsk_poll(struct file *file, struct socket *sock,
 	if (xs->tx && xsk_tx_writeable(xs))
 		mask |= EPOLLOUT | EPOLLWRNORM;
 
+	rcu_read_unlock();
 	return mask;
 }
 
@@ -743,7 +775,6 @@ static void xsk_unbind_dev(struct xdp_sock *xs)
 
 	/* Wait for driver to stop using the xdp socket. */
 	xp_del_xsk(xs->pool, xs);
-	xs->dev = NULL;
 	synchronize_net();
 	dev_put(dev);
 }
diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c
index e843b0d9e2a6..c255aac6b816 100644
--- a/net/xfrm/xfrm_device.c
+++ b/net/xfrm/xfrm_device.c
@@ -223,6 +223,9 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x,
 	if (x->encap || x->tfcpad)
 		return -EINVAL;
 
+	if (xuo->flags & ~(XFRM_OFFLOAD_IPV6 | XFRM_OFFLOAD_INBOUND))
+		return -EINVAL;
+
 	dev = dev_get_by_index(net, xuo->ifindex);
 	if (!dev) {
 		if (!(xuo->flags & XFRM_OFFLOAD_INBOUND)) {
@@ -261,7 +264,8 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x,
 	xso->dev = dev;
 	xso->real_dev = dev;
 	xso->num_exthdrs = 1;
-	xso->flags = xuo->flags;
+	/* Don't forward bit that is not implemented */
+	xso->flags = xuo->flags & ~XFRM_OFFLOAD_IPV6;
 
 	err = dev->xfrmdev_ops->xdo_dev_state_add(x);
 	if (err) {
diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c
index 57448fc519fc..1e8b26eecb3f 100644
--- a/net/xfrm/xfrm_interface.c
+++ b/net/xfrm/xfrm_interface.c
@@ -304,7 +304,10 @@ xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
 			if (mtu < IPV6_MIN_MTU)
 				mtu = IPV6_MIN_MTU;
 
-			icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+			if (skb->len > 1280)
+				icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+			else
+				goto xmit;
 		} else {
 			if (!(ip_hdr(skb)->frag_off & htons(IP_DF)))
 				goto xmit;
@@ -673,12 +676,12 @@ static int xfrmi_changelink(struct net_device *dev, struct nlattr *tb[],
 	struct net *net = xi->net;
 	struct xfrm_if_parms p = {};
 
+	xfrmi_netlink_parms(data, &p);
 	if (!p.if_id) {
 		NL_SET_ERR_MSG(extack, "if_id must be non zero");
 		return -EINVAL;
 	}
 
-	xfrmi_netlink_parms(data, &p);
 	xi = xfrmi_locate(net, &p);
 	if (!xi) {
 		xi = netdev_priv(dev);
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 37b149f63262..02099d113a0a 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -4259,7 +4259,7 @@ static bool xfrm_migrate_selector_match(const struct xfrm_selector *sel_cmp,
 }
 
 static struct xfrm_policy *xfrm_migrate_policy_find(const struct xfrm_selector *sel,
-						    u8 dir, u8 type, struct net *net)
+						    u8 dir, u8 type, struct net *net, u32 if_id)
 {
 	struct xfrm_policy *pol, *ret = NULL;
 	struct hlist_head *chain;
@@ -4268,7 +4268,8 @@ static struct xfrm_policy *xfrm_migrate_policy_find(const struct xfrm_selector *
 	spin_lock_bh(&net->xfrm.xfrm_policy_lock);
 	chain = policy_hash_direct(net, &sel->daddr, &sel->saddr, sel->family, dir);
 	hlist_for_each_entry(pol, chain, bydst) {
-		if (xfrm_migrate_selector_match(sel, &pol->selector) &&
+		if ((if_id == 0 || pol->if_id == if_id) &&
+		    xfrm_migrate_selector_match(sel, &pol->selector) &&
 		    pol->type == type) {
 			ret = pol;
 			priority = ret->priority;
@@ -4280,7 +4281,8 @@ static struct xfrm_policy *xfrm_migrate_policy_find(const struct xfrm_selector *
 		if ((pol->priority >= priority) && ret)
 			break;
 
-		if (xfrm_migrate_selector_match(sel, &pol->selector) &&
+		if ((if_id == 0 || pol->if_id == if_id) &&
+		    xfrm_migrate_selector_match(sel, &pol->selector) &&
 		    pol->type == type) {
 			ret = pol;
 			break;
@@ -4396,7 +4398,7 @@ static int xfrm_migrate_check(const struct xfrm_migrate *m, int num_migrate)
 int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 		 struct xfrm_migrate *m, int num_migrate,
 		 struct xfrm_kmaddress *k, struct net *net,
-		 struct xfrm_encap_tmpl *encap)
+		 struct xfrm_encap_tmpl *encap, u32 if_id)
 {
 	int i, err, nx_cur = 0, nx_new = 0;
 	struct xfrm_policy *pol = NULL;
@@ -4415,14 +4417,14 @@ int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 	}
 
 	/* Stage 1 - find policy */
-	if ((pol = xfrm_migrate_policy_find(sel, dir, type, net)) == NULL) {
+	if ((pol = xfrm_migrate_policy_find(sel, dir, type, net, if_id)) == NULL) {
 		err = -ENOENT;
 		goto out;
 	}
 
 	/* Stage 2 - find and update state(s) */
 	for (i = 0, mp = m; i < num_migrate; i++, mp++) {
-		if ((x = xfrm_migrate_state_find(mp, net))) {
+		if ((x = xfrm_migrate_state_find(mp, net, if_id))) {
 			x_cur[nx_cur] = x;
 			nx_cur++;
 			xc = xfrm_state_migrate(x, mp, encap);
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 78d51399a0f4..f7bfa1916968 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -1578,9 +1578,6 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig,
 	memcpy(&x->mark, &orig->mark, sizeof(x->mark));
 	memcpy(&x->props.smark, &orig->props.smark, sizeof(x->props.smark));
 
-	if (xfrm_init_state(x) < 0)
-		goto error;
-
 	x->props.flags = orig->props.flags;
 	x->props.extra_flags = orig->props.extra_flags;
 
@@ -1605,7 +1602,8 @@ out:
 	return NULL;
 }
 
-struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *net)
+struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *net,
+						u32 if_id)
 {
 	unsigned int h;
 	struct xfrm_state *x = NULL;
@@ -1621,6 +1619,8 @@ struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *n
 				continue;
 			if (m->reqid && x->props.reqid != m->reqid)
 				continue;
+			if (if_id != 0 && x->if_id != if_id)
+				continue;
 			if (!xfrm_addr_equal(&x->id.daddr, &m->old_daddr,
 					     m->old_family) ||
 			    !xfrm_addr_equal(&x->props.saddr, &m->old_saddr,
@@ -1636,6 +1636,8 @@ struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *n
 			if (x->props.mode != m->mode ||
 			    x->id.proto != m->proto)
 				continue;
+			if (if_id != 0 && x->if_id != if_id)
+				continue;
 			if (!xfrm_addr_equal(&x->id.daddr, &m->old_daddr,
 					     m->old_family) ||
 			    !xfrm_addr_equal(&x->props.saddr, &m->old_saddr,
@@ -1662,6 +1664,11 @@ struct xfrm_state *xfrm_state_migrate(struct xfrm_state *x,
 	if (!xc)
 		return NULL;
 
+	xc->props.family = m->new_family;
+
+	if (xfrm_init_state(xc) < 0)
+		goto error;
+
 	memcpy(&xc->id.daddr, &m->new_daddr, sizeof(xc->id.daddr));
 	memcpy(&xc->props.saddr, &m->new_saddr, sizeof(xc->props.saddr));
 
@@ -2571,7 +2578,7 @@ void xfrm_state_delete_tunnel(struct xfrm_state *x)
 }
 EXPORT_SYMBOL(xfrm_state_delete_tunnel);
 
-u32 __xfrm_state_mtu(struct xfrm_state *x, int mtu)
+u32 xfrm_state_mtu(struct xfrm_state *x, int mtu)
 {
 	const struct xfrm_type *type = READ_ONCE(x->type);
 	struct crypto_aead *aead;
@@ -2602,17 +2609,7 @@ u32 __xfrm_state_mtu(struct xfrm_state *x, int mtu)
 	return ((mtu - x->props.header_len - crypto_aead_authsize(aead) -
 		 net_adj) & ~(blksize - 1)) + net_adj - 2;
 }
-EXPORT_SYMBOL_GPL(__xfrm_state_mtu);
-
-u32 xfrm_state_mtu(struct xfrm_state *x, int mtu)
-{
-	mtu = __xfrm_state_mtu(x, mtu);
-
-	if (x->props.family == AF_INET6 && mtu < IPV6_MIN_MTU)
-		return IPV6_MIN_MTU;
-
-	return mtu;
-}
+EXPORT_SYMBOL_GPL(xfrm_state_mtu);
 
 int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload)
 {
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index b10f88822c0d..2acba159327c 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -629,13 +629,8 @@ static struct xfrm_state *xfrm_state_construct(struct net *net,
 
 	xfrm_smark_init(attrs, &x->props.smark);
 
-	if (attrs[XFRMA_IF_ID]) {
+	if (attrs[XFRMA_IF_ID])
 		x->if_id = nla_get_u32(attrs[XFRMA_IF_ID]);
-		if (!x->if_id) {
-			err = -EINVAL;
-			goto error;
-		}
-	}
 
 	err = __xfrm_init_state(x, false, attrs[XFRMA_OFFLOAD_DEV]);
 	if (err)
@@ -1431,13 +1426,8 @@ static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 	mark = xfrm_mark_get(attrs, &m);
 
-	if (attrs[XFRMA_IF_ID]) {
+	if (attrs[XFRMA_IF_ID])
 		if_id = nla_get_u32(attrs[XFRMA_IF_ID]);
-		if (!if_id) {
-			err = -EINVAL;
-			goto out_noput;
-		}
-	}
 
 	if (p->info.seq) {
 		x = xfrm_find_acq_byseq(net, mark, p->info.seq);
@@ -1750,13 +1740,8 @@ static struct xfrm_policy *xfrm_policy_construct(struct net *net, struct xfrm_us
 
 	xfrm_mark_get(attrs, &xp->mark);
 
-	if (attrs[XFRMA_IF_ID]) {
+	if (attrs[XFRMA_IF_ID])
 		xp->if_id = nla_get_u32(attrs[XFRMA_IF_ID]);
-		if (!xp->if_id) {
-			err = -EINVAL;
-			goto error;
-		}
-	}
 
 	return xp;
  error:
@@ -2607,6 +2592,7 @@ static int xfrm_do_migrate(struct sk_buff *skb, struct nlmsghdr *nlh,
 	int n = 0;
 	struct net *net = sock_net(skb->sk);
 	struct xfrm_encap_tmpl  *encap = NULL;
+	u32 if_id = 0;
 
 	if (attrs[XFRMA_MIGRATE] == NULL)
 		return -EINVAL;
@@ -2631,7 +2617,10 @@ static int xfrm_do_migrate(struct sk_buff *skb, struct nlmsghdr *nlh,
 			return -ENOMEM;
 	}
 
-	err = xfrm_migrate(&pi->sel, pi->dir, type, m, n, kmp, net, encap);
+	if (attrs[XFRMA_IF_ID])
+		if_id = nla_get_u32(attrs[XFRMA_IF_ID]);
+
+	err = xfrm_migrate(&pi->sel, pi->dir, type, m, n, kmp, net, encap, if_id);
 
 	kfree(encap);