1 files changed, 734 insertions, 501 deletions

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index a3437a4cd07e..cf37ad9686e6 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *	IPv6 over IPv4 tunnel device - Simple Internet Transition (SIT)
  *	Linux INET6 implementation
@@ -6,11 +7,6 @@
  *	Pedro Roque		<roque@di.fc.ul.pt>
  *	Alexey Kuznetsov	<kuznet@ms2.inr.ac.ru>
  *
- *	This program is free software; you can redistribute it and/or
- *      modify it under the terms of the GNU General Public License
- *      as published by the Free Software Foundation; either version
- *      2 of the License, or (at your option) any later version.
- *
  *	Changes:
  * Roger Venning <r.venning@telstra.com>:	6to4 support
  * Nate Thompson <nate@thebog.net>:		6to4 support
@@ -31,7 +27,7 @@
 #include <linux/if_arp.h>
 #include <linux/icmp.h>
 #include <linux/slab.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/init.h>
 #include <linux/netfilter_ipv4.h>
 #include <linux/if_ether.h>
@@ -55,6 +51,8 @@
 #include <net/dsfield.h>
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
+#include <net/netdev_lock.h>
+#include <net/inet_dscp.h>
 
 /*
    This version of net/ipv6/sit.c is cloned of net/ipv4/ip_gre.c
@@ -62,7 +60,7 @@
    For comments look at net/ipv4/ip_gre.c --ANK
  */
 
-#define HASH_SIZE  16
+#define IP6_SIT_HASH_SIZE  16
 #define HASH(addr) (((__force u32)addr^((__force u32)addr>>4))&0xF)
 
 static bool log_ecn_error = true;
@@ -76,55 +74,68 @@ static bool check_6rd(struct ip_tunnel *tunnel, const struct in6_addr *v6dst,
 		      __be32 *v4dst);
 static struct rtnl_link_ops sit_link_ops __read_mostly;
 
-static int sit_net_id __read_mostly;
+static unsigned int sit_net_id __read_mostly;
 struct sit_net {
-	struct ip_tunnel __rcu *tunnels_r_l[HASH_SIZE];
-	struct ip_tunnel __rcu *tunnels_r[HASH_SIZE];
-	struct ip_tunnel __rcu *tunnels_l[HASH_SIZE];
+	struct ip_tunnel __rcu *tunnels_r_l[IP6_SIT_HASH_SIZE];
+	struct ip_tunnel __rcu *tunnels_r[IP6_SIT_HASH_SIZE];
+	struct ip_tunnel __rcu *tunnels_l[IP6_SIT_HASH_SIZE];
 	struct ip_tunnel __rcu *tunnels_wc[1];
 	struct ip_tunnel __rcu **tunnels[4];
 
 	struct net_device *fb_tunnel_dev;
 };
 
+static inline struct sit_net *dev_to_sit_net(struct net_device *dev)
+{
+	struct ip_tunnel *t = netdev_priv(dev);
+
+	return net_generic(t->net, sit_net_id);
+}
+
 /*
  * Must be invoked with rcu_read_lock
  */
 static struct ip_tunnel *ipip6_tunnel_lookup(struct net *net,
-		struct net_device *dev, __be32 remote, __be32 local)
+					     struct net_device *dev,
+					     __be32 remote, __be32 local,
+					     int sifindex)
 {
 	unsigned int h0 = HASH(remote);
 	unsigned int h1 = HASH(local);
 	struct ip_tunnel *t;
 	struct sit_net *sitn = net_generic(net, sit_net_id);
+	int ifindex = dev ? dev->ifindex : 0;
 
 	for_each_ip_tunnel_rcu(t, sitn->tunnels_r_l[h0 ^ h1]) {
 		if (local == t->parms.iph.saddr &&
 		    remote == t->parms.iph.daddr &&
-		    (!dev || !t->parms.link || dev->iflink == t->parms.link) &&
+		    (!dev || !t->parms.link || ifindex == t->parms.link ||
+		     sifindex == t->parms.link) &&
 		    (t->dev->flags & IFF_UP))
 			return t;
 	}
 	for_each_ip_tunnel_rcu(t, sitn->tunnels_r[h0]) {
 		if (remote == t->parms.iph.daddr &&
-		    (!dev || !t->parms.link || dev->iflink == t->parms.link) &&
+		    (!dev || !t->parms.link || ifindex == t->parms.link ||
+		     sifindex == t->parms.link) &&
 		    (t->dev->flags & IFF_UP))
 			return t;
 	}
 	for_each_ip_tunnel_rcu(t, sitn->tunnels_l[h1]) {
 		if (local == t->parms.iph.saddr &&
-		    (!dev || !t->parms.link || dev->iflink == t->parms.link) &&
+		    (!dev || !t->parms.link || ifindex == t->parms.link ||
+		     sifindex == t->parms.link) &&
 		    (t->dev->flags & IFF_UP))
 			return t;
 	}
 	t = rcu_dereference(sitn->tunnels_wc[0]);
-	if ((t != NULL) && (t->dev->flags & IFF_UP))
+	if (t && (t->dev->flags & IFF_UP))
 		return t;
 	return NULL;
 }
 
-static struct ip_tunnel __rcu **__ipip6_bucket(struct sit_net *sitn,
-		struct ip_tunnel_parm *parms)
+static struct ip_tunnel __rcu **
+__ipip6_bucket(struct sit_net *sitn, struct ip_tunnel_parm_kern *parms)
 {
 	__be32 remote = parms->iph.daddr;
 	__be32 local = parms->iph.saddr;
@@ -176,7 +187,7 @@ static void ipip6_tunnel_clone_6rd(struct net_device *dev, struct sit_net *sitn)
 #ifdef CONFIG_IPV6_SIT_6RD
 	struct ip_tunnel *t = netdev_priv(dev);
 
-	if (t->dev == sitn->fb_tunnel_dev) {
+	if (dev == sitn->fb_tunnel_dev || !sitn->fb_tunnel_dev) {
 		ipv6_addr_set(&t->ip6rd.prefix, htonl(0x20020000), 0, 0, 0);
 		t->ip6rd.relay_prefix = 0;
 		t->ip6rd.prefixlen = 16;
@@ -191,26 +202,22 @@ static void ipip6_tunnel_clone_6rd(struct net_device *dev, struct sit_net *sitn)
 static int ipip6_tunnel_create(struct net_device *dev)
 {
 	struct ip_tunnel *t = netdev_priv(dev);
-	struct net *net = dev_net(dev);
-	struct sit_net *sitn = net_generic(net, sit_net_id);
+	struct sit_net *sitn = net_generic(t->net, sit_net_id);
 	int err;
 
-	err = ipip6_tunnel_init(dev);
-	if (err < 0)
-		goto out;
-	ipip6_tunnel_clone_6rd(dev, sitn);
+	__dev_addr_set(dev, &t->parms.iph.saddr, 4);
+	memcpy(dev->broadcast, &t->parms.iph.daddr, 4);
 
-	if ((__force u16)t->parms.i_flags & SIT_ISATAP)
+	if (test_bit(IP_TUNNEL_SIT_ISATAP_BIT, t->parms.i_flags))
 		dev->priv_flags |= IFF_ISATAP;
 
+	dev->rtnl_link_ops = &sit_link_ops;
+
 	err = register_netdevice(dev);
 	if (err < 0)
 		goto out;
 
-	strcpy(t->parms.name, dev->name);
-	dev->rtnl_link_ops = &sit_link_ops;
-
-	dev_hold(dev);
+	ipip6_tunnel_clone_6rd(dev, sitn);
 
 	ipip6_tunnel_link(sitn, t);
 	return 0;
@@ -220,7 +227,8 @@ out:
 }
 
 static struct ip_tunnel *ipip6_tunnel_locate(struct net *net,
-		struct ip_tunnel_parm *parms, int create)
+					     struct ip_tunnel_parm_kern *parms,
+					     int create)
 {
 	__be32 remote = parms->iph.daddr;
 	__be32 local = parms->iph.saddr;
@@ -245,27 +253,34 @@ static struct ip_tunnel *ipip6_tunnel_locate(struct net *net,
 	if (!create)
 		goto failed;
 
-	if (parms->name[0])
-		strlcpy(name, parms->name, IFNAMSIZ);
-	else
+	if (parms->name[0]) {
+		if (!dev_valid_name(parms->name))
+			goto failed;
+		strscpy(name, parms->name, IFNAMSIZ);
+	} else {
 		strcpy(name, "sit%d");
-
-	dev = alloc_netdev(sizeof(*t), name, ipip6_tunnel_setup);
-	if (dev == NULL)
+	}
+	dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN,
+			   ipip6_tunnel_setup);
+	if (!dev)
 		return NULL;
 
 	dev_net_set(dev, net);
 
 	nt = netdev_priv(dev);
 
+	nt->net = net;
 	nt->parms = *parms;
 	if (ipip6_tunnel_create(dev) < 0)
 		goto failed_free;
 
+	if (!parms->name[0])
+		strcpy(parms->name, dev->name);
+
 	return nt;
 
 failed_free:
-	ipip6_dev_free(dev);
+	free_netdev(dev);
 failed:
 	return NULL;
 }
@@ -287,14 +302,17 @@ __ipip6_tunnel_locate_prl(struct ip_tunnel *t, __be32 addr)
 
 }
 
-static int ipip6_tunnel_get_prl(struct ip_tunnel *t,
-				struct ip_tunnel_prl __user *a)
+static int ipip6_tunnel_get_prl(struct net_device *dev, struct ip_tunnel_prl __user *a)
 {
+	struct ip_tunnel *t = netdev_priv(dev);
 	struct ip_tunnel_prl kprl, *kp;
 	struct ip_tunnel_prl_entry *prl;
 	unsigned int cmax, c = 0, ca, len;
 	int ret = 0;
 
+	if (dev == dev_to_sit_net(dev)->fb_tunnel_dev)
+		return -EINVAL;
+
 	if (copy_from_user(&kprl, a, sizeof(kprl)))
 		return -EFAULT;
 	cmax = kprl.datalen / sizeof(kprl);
@@ -305,12 +323,10 @@ static int ipip6_tunnel_get_prl(struct ip_tunnel *t,
 	 * we try harder to allocate.
 	 */
 	kp = (cmax <= 1 || capable(CAP_NET_ADMIN)) ?
-		kcalloc(cmax, sizeof(*kp), GFP_KERNEL) :
+		kcalloc(cmax, sizeof(*kp), GFP_KERNEL_ACCOUNT | __GFP_NOWARN) :
 		NULL;
 
-	rcu_read_lock();
-
-	ca = t->prl_count < cmax ? t->prl_count : cmax;
+	ca = min(t->prl_count, cmax);
 
 	if (!kp) {
 		/* We don't try hard to allocate much memory for
@@ -318,14 +334,15 @@ static int ipip6_tunnel_get_prl(struct ip_tunnel *t,
 		 * For root users, retry allocating enough memory for
 		 * the answer.
 		 */
-		kp = kcalloc(ca, sizeof(*kp), GFP_ATOMIC);
+		kp = kcalloc(ca, sizeof(*kp), GFP_ATOMIC | __GFP_ACCOUNT |
+					      __GFP_NOWARN);
 		if (!kp) {
 			ret = -ENOMEM;
 			goto out;
 		}
 	}
 
-	c = 0;
+	rcu_read_lock();
 	for_each_prl_rcu(t->prl) {
 		if (c >= cmax)
 			break;
@@ -337,7 +354,7 @@ static int ipip6_tunnel_get_prl(struct ip_tunnel *t,
 		if (kprl.addr != htonl(INADDR_ANY))
 			break;
 	}
-out:
+
 	rcu_read_unlock();
 
 	len = sizeof(*kp) * c;
@@ -346,7 +363,7 @@ out:
 		ret = -EFAULT;
 
 	kfree(kp);
-
+out:
 	return ret;
 }
 
@@ -437,6 +454,35 @@ out:
 	return err;
 }
 
+static int ipip6_tunnel_prl_ctl(struct net_device *dev,
+				struct ip_tunnel_prl __user *data, int cmd)
+{
+	struct ip_tunnel *t = netdev_priv(dev);
+	struct ip_tunnel_prl prl;
+	int err;
+
+	if (!ns_capable(t->net->user_ns, CAP_NET_ADMIN))
+		return -EPERM;
+	if (dev == dev_to_sit_net(dev)->fb_tunnel_dev)
+		return -EINVAL;
+
+	if (copy_from_user(&prl, data, sizeof(prl)))
+		return -EFAULT;
+
+	switch (cmd) {
+	case SIOCDELPRL:
+		err = ipip6_tunnel_del_prl(t, &prl);
+		break;
+	case SIOCADDPRL:
+	case SIOCCHGPRL:
+		err = ipip6_tunnel_add_prl(t, &prl, cmd == SIOCCHGPRL);
+		break;
+	}
+	dst_cache_reset(&t->dst_cache);
+	netdev_state_change(dev);
+	return err;
+}
+
 static int
 isatap_chksrc(struct sk_buff *skb, const struct iphdr *iph, struct ip_tunnel *t)
 {
@@ -475,21 +521,18 @@ static void ipip6_tunnel_uninit(struct net_device *dev)
 		ipip6_tunnel_unlink(sitn, tunnel);
 		ipip6_tunnel_del_prl(tunnel, NULL);
 	}
-	dev_put(dev);
+	dst_cache_reset(&tunnel->dst_cache);
+	netdev_put(dev, &tunnel->dev_tracker);
 }
 
-
 static int ipip6_err(struct sk_buff *skb, u32 info)
 {
-
-/* All the routers (except for Linux) return only
-   8 bytes of packet payload. It means, that precise relaying of
-   ICMP in the real Internet is absolutely infeasible.
- */
 	const struct iphdr *iph = (const struct iphdr *)skb->data;
 	const int type = icmp_hdr(skb)->type;
 	const int code = icmp_hdr(skb)->code;
+	unsigned int data_len = 0;
 	struct ip_tunnel *t;
+	int sifindex;
 	int err;
 
 	switch (type) {
@@ -500,7 +543,6 @@ static int ipip6_err(struct sk_buff *skb, u32 info)
 	case ICMP_DEST_UNREACH:
 		switch (code) {
 		case ICMP_SR_FAILED:
-		case ICMP_PORT_UNREACH:
 			/* Impossible event. */
 			return 0;
 		default:
@@ -514,6 +556,7 @@ static int ipip6_err(struct sk_buff *skb, u32 info)
 	case ICMP_TIME_EXCEEDED:
 		if (code != ICMP_EXC_TTL)
 			return 0;
+		data_len = icmp_hdr(skb)->un.reserved[1] * 4; /* RFC 4884 4.1 */
 		break;
 	case ICMP_REDIRECT:
 		break;
@@ -521,30 +564,33 @@ static int ipip6_err(struct sk_buff *skb, u32 info)
 
 	err = -ENOENT;
 
-	t = ipip6_tunnel_lookup(dev_net(skb->dev),
-				skb->dev,
-				iph->daddr,
-				iph->saddr);
-	if (t == NULL)
+	sifindex = netif_is_l3_master(skb->dev) ? IPCB(skb)->iif : 0;
+	t = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev,
+				iph->daddr, iph->saddr, sifindex);
+	if (!t)
 		goto out;
 
 	if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
 		ipv4_update_pmtu(skb, dev_net(skb->dev), info,
-				 t->dev->ifindex, 0, IPPROTO_IPV6, 0);
+				 t->parms.link, iph->protocol);
 		err = 0;
 		goto out;
 	}
 	if (type == ICMP_REDIRECT) {
-		ipv4_redirect(skb, dev_net(skb->dev), t->dev->ifindex, 0,
-			      IPPROTO_IPV6, 0);
+		ipv4_redirect(skb, dev_net(skb->dev), t->parms.link,
+			      iph->protocol);
 		err = 0;
 		goto out;
 	}
 
+	err = 0;
+	if (__in6_dev_get(skb->dev) &&
+	    !ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4, type, data_len))
+		goto out;
+
 	if (t->parms.iph.daddr == 0)
 		goto out;
 
-	err = 0;
 	if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED)
 		goto out;
 
@@ -566,44 +612,104 @@ static inline bool is_spoofed_6rd(struct ip_tunnel *tunnel, const __be32 v4addr,
 	return false;
 }
 
+/* Checks if an address matches an address on the tunnel interface.
+ * Used to detect the NAT of proto 41 packets and let them pass spoofing test.
+ * Long story:
+ * This function is called after we considered the packet as spoofed
+ * in is_spoofed_6rd.
+ * We may have a router that is doing NAT for proto 41 packets
+ * for an internal station. Destination a.a.a.a/PREFIX:bbbb:bbbb
+ * will be translated to n.n.n.n/PREFIX:bbbb:bbbb. And is_spoofed_6rd
+ * function will return true, dropping the packet.
+ * But, we can still check if is spoofed against the IP
+ * addresses associated with the interface.
+ */
+static bool only_dnatted(const struct ip_tunnel *tunnel,
+	const struct in6_addr *v6dst)
+{
+	int prefix_len;
+
+#ifdef CONFIG_IPV6_SIT_6RD
+	prefix_len = tunnel->ip6rd.prefixlen + 32
+		- tunnel->ip6rd.relay_prefixlen;
+#else
+	prefix_len = 48;
+#endif
+	return ipv6_chk_custom_prefix(v6dst, prefix_len, tunnel->dev);
+}
+
+/* Returns true if a packet is spoofed */
+static bool packet_is_spoofed(struct sk_buff *skb,
+			      const struct iphdr *iph,
+			      struct ip_tunnel *tunnel)
+{
+	const struct ipv6hdr *ipv6h;
+
+	if (tunnel->dev->priv_flags & IFF_ISATAP) {
+		if (!isatap_chksrc(skb, iph, tunnel))
+			return true;
+
+		return false;
+	}
+
+	if (tunnel->dev->flags & IFF_POINTOPOINT)
+		return false;
+
+	ipv6h = ipv6_hdr(skb);
+
+	if (unlikely(is_spoofed_6rd(tunnel, iph->saddr, &ipv6h->saddr))) {
+		net_warn_ratelimited("Src spoofed %pI4/%pI6c -> %pI4/%pI6c\n",
+				     &iph->saddr, &ipv6h->saddr,
+				     &iph->daddr, &ipv6h->daddr);
+		return true;
+	}
+
+	if (likely(!is_spoofed_6rd(tunnel, iph->daddr, &ipv6h->daddr)))
+		return false;
+
+	if (only_dnatted(tunnel, &ipv6h->daddr))
+		return false;
+
+	net_warn_ratelimited("Dst spoofed %pI4/%pI6c -> %pI4/%pI6c\n",
+			     &iph->saddr, &ipv6h->saddr,
+			     &iph->daddr, &ipv6h->daddr);
+	return true;
+}
+
 static int ipip6_rcv(struct sk_buff *skb)
 {
 	const struct iphdr *iph = ip_hdr(skb);
 	struct ip_tunnel *tunnel;
+	int sifindex;
 	int err;
 
+	sifindex = netif_is_l3_master(skb->dev) ? IPCB(skb)->iif : 0;
 	tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev,
-				     iph->saddr, iph->daddr);
-	if (tunnel != NULL) {
-		struct pcpu_tstats *tstats;
-
+				     iph->saddr, iph->daddr, sifindex);
+	if (tunnel) {
 		if (tunnel->parms.iph.protocol != IPPROTO_IPV6 &&
 		    tunnel->parms.iph.protocol != 0)
 			goto out;
 
-		secpath_reset(skb);
 		skb->mac_header = skb->network_header;
 		skb_reset_network_header(skb);
 		IPCB(skb)->flags = 0;
-		skb->protocol = htons(ETH_P_IPV6);
-		skb->pkt_type = PACKET_HOST;
+		skb->dev = tunnel->dev;
 
-		if (tunnel->dev->priv_flags & IFF_ISATAP) {
-			if (!isatap_chksrc(skb, iph, tunnel)) {
-				tunnel->dev->stats.rx_errors++;
-				goto out;
-			}
-		} else if (!(tunnel->dev->flags&IFF_POINTOPOINT)) {
-			if (is_spoofed_6rd(tunnel, iph->saddr,
-					   &ipv6_hdr(skb)->saddr) ||
-			    is_spoofed_6rd(tunnel, iph->daddr,
-					   &ipv6_hdr(skb)->daddr)) {
-				tunnel->dev->stats.rx_errors++;
-				goto out;
-			}
+		if (packet_is_spoofed(skb, iph, tunnel)) {
+			DEV_STATS_INC(tunnel->dev, rx_errors);
+			goto out;
 		}
 
-		__skb_tunnel_rx(skb, tunnel->dev);
+		if (iptunnel_pull_header(skb, 0, htons(ETH_P_IPV6),
+		    !net_eq(tunnel->net, dev_net(tunnel->dev))))
+			goto out;
+
+		/* skb can be uncloned in iptunnel_pull_header, so
+		 * old iph is no longer valid
+		 */
+		iph = (const struct iphdr *)skb_mac_header(skb);
+		skb_reset_mac_header(skb);
 
 		err = IP_ECN_decapsulate(iph, skb);
 		if (unlikely(err)) {
@@ -611,18 +717,14 @@ static int ipip6_rcv(struct sk_buff *skb)
 				net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n",
 						     &iph->saddr, iph->tos);
 			if (err > 1) {
-				++tunnel->dev->stats.rx_frame_errors;
-				++tunnel->dev->stats.rx_errors;
+				DEV_STATS_INC(tunnel->dev, rx_frame_errors);
+				DEV_STATS_INC(tunnel->dev, rx_errors);
 				goto out;
 			}
 		}
 
-		tstats = this_cpu_ptr(tunnel->dev->tstats);
-		tstats->rx_packets++;
-		tstats->rx_bytes += skb->len;
+		dev_sw_netstats_rx_add(tunnel->dev, skb->len);
 
-		if (tunnel->net != dev_net(tunnel->dev))
-			skb_scrub_packet(skb);
 		netif_rx(skb);
 
 		return 0;
@@ -635,31 +737,49 @@ out:
 	return 0;
 }
 
-static const struct tnl_ptk_info tpi = {
+static const struct tnl_ptk_info ipip_tpi = {
 	/* no tunnel info required for ipip. */
 	.proto = htons(ETH_P_IP),
 };
 
-static int ipip_rcv(struct sk_buff *skb)
+#if IS_ENABLED(CONFIG_MPLS)
+static const struct tnl_ptk_info mplsip_tpi = {
+	/* no tunnel info required for mplsip. */
+	.proto = htons(ETH_P_MPLS_UC),
+};
+#endif
+
+static int sit_tunnel_rcv(struct sk_buff *skb, u8 ipproto)
 {
 	const struct iphdr *iph;
 	struct ip_tunnel *tunnel;
+	int sifindex;
 
-	if (iptunnel_pull_header(skb, 0, tpi.proto))
-		goto drop;
+	sifindex = netif_is_l3_master(skb->dev) ? IPCB(skb)->iif : 0;
 
 	iph = ip_hdr(skb);
-
 	tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev,
-				     iph->saddr, iph->daddr);
-	if (tunnel != NULL) {
-		if (tunnel->parms.iph.protocol != IPPROTO_IPIP &&
+				     iph->saddr, iph->daddr, sifindex);
+	if (tunnel) {
+		const struct tnl_ptk_info *tpi;
+
+		if (tunnel->parms.iph.protocol != ipproto &&
 		    tunnel->parms.iph.protocol != 0)
 			goto drop;
 
 		if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
 			goto drop;
-		return ip_tunnel_rcv(tunnel, skb, &tpi, log_ecn_error);
+#if IS_ENABLED(CONFIG_MPLS)
+		if (ipproto == IPPROTO_MPLS)
+			tpi = &mplsip_tpi;
+		else
+#endif
+			tpi = &ipip_tpi;
+		if (iptunnel_pull_header(skb, 0, tpi->proto, false))
+			goto drop;
+		skb_reset_mac_header(skb);
+
+		return ip_tunnel_rcv(tunnel, skb, tpi, NULL, log_ecn_error);
 	}
 
 	return 1;
@@ -669,6 +789,18 @@ drop:
 	return 0;
 }
 
+static int ipip_rcv(struct sk_buff *skb)
+{
+	return sit_tunnel_rcv(skb, IPPROTO_IPIP);
+}
+
+#if IS_ENABLED(CONFIG_MPLS)
+static int mplsip_rcv(struct sk_buff *skb)
+{
+	return sit_tunnel_rcv(skb, IPPROTO_MPLS);
+}
+#endif
+
 /*
  * If the IPv6 address comes from 6rd / 6to4 (RFC 3056) addr space this function
  * stores the embedded IPv4 address in v4dst and returns true.
@@ -686,8 +818,9 @@ static bool check_6rd(struct ip_tunnel *tunnel, const struct in6_addr *v6dst,
 		pbw0 = tunnel->ip6rd.prefixlen >> 5;
 		pbi0 = tunnel->ip6rd.prefixlen & 0x1f;
 
-		d = (ntohl(v6dst->s6_addr32[pbw0]) << pbi0) >>
-		    tunnel->ip6rd.relay_prefixlen;
+		d = tunnel->ip6rd.relay_prefixlen < 32 ?
+			(ntohl(v6dst->s6_addr32[pbw0]) << pbi0) >>
+		    tunnel->ip6rd.relay_prefixlen : 0;
 
 		pbi1 = pbi0 - tunnel->ip6rd.relay_prefixlen;
 		if (pbi1 > 0)
@@ -715,6 +848,49 @@ static inline __be32 try_6rd(struct ip_tunnel *tunnel,
 	return dst;
 }
 
+static bool ipip6_tunnel_dst_find(struct sk_buff *skb, __be32 *dst,
+				  bool is_isatap)
+{
+	const struct ipv6hdr *iph6 = ipv6_hdr(skb);
+	struct neighbour *neigh = NULL;
+	const struct in6_addr *addr6;
+	bool found = false;
+	int addr_type;
+
+	if (skb_dst(skb))
+		neigh = dst_neigh_lookup(skb_dst(skb), &iph6->daddr);
+
+	if (!neigh) {
+		net_dbg_ratelimited("nexthop == NULL\n");
+		return false;
+	}
+
+	addr6 = (const struct in6_addr *)&neigh->primary_key;
+	addr_type = ipv6_addr_type(addr6);
+
+	if (is_isatap) {
+		if ((addr_type & IPV6_ADDR_UNICAST) &&
+		    ipv6_addr_is_isatap(addr6)) {
+			*dst = addr6->s6_addr32[3];
+			found = true;
+		}
+	} else {
+		if (addr_type == IPV6_ADDR_ANY) {
+			addr6 = &ipv6_hdr(skb)->daddr;
+			addr_type = ipv6_addr_type(addr6);
+		}
+
+		if ((addr_type & IPV6_ADDR_COMPATv4) != 0) {
+			*dst = addr6->s6_addr32[3];
+			found = true;
+		}
+	}
+
+	neigh_release(neigh);
+
+	return found;
+}
+
 /*
  *	This function assumes it is being called from dev_queue_xmit()
  *	and that skb is filled properly by that function.
@@ -728,110 +904,68 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 	const struct ipv6hdr *iph6 = ipv6_hdr(skb);
 	u8     tos = tunnel->parms.iph.tos;
 	__be16 df = tiph->frag_off;
-	struct rtable *rt;     			/* Route to the other host */
-	struct net_device *tdev;		/* Device to other host */
-	unsigned int max_headroom;		/* The extra header space needed */
+	struct rtable *rt;		/* Route to the other host */
+	struct net_device *tdev;	/* Device to other host */
+	unsigned int max_headroom;	/* The extra header space needed */
 	__be32 dst = tiph->daddr;
 	struct flowi4 fl4;
 	int    mtu;
-	const struct in6_addr *addr6;
-	int addr_type;
 	u8 ttl;
-	int err;
-
-	if (skb->protocol != htons(ETH_P_IPV6))
-		goto tx_error;
+	u8 protocol = IPPROTO_IPV6;
+	int t_hlen = tunnel->hlen + sizeof(struct iphdr);
 
 	if (tos == 1)
 		tos = ipv6_get_dsfield(iph6);
 
 	/* ISATAP (RFC4214) - must come before 6to4 */
-	if (dev->priv_flags & IFF_ISATAP) {
-		struct neighbour *neigh = NULL;
-		bool do_tx_error = false;
-
-		if (skb_dst(skb))
-			neigh = dst_neigh_lookup(skb_dst(skb), &iph6->daddr);
-
-		if (neigh == NULL) {
-			net_dbg_ratelimited("sit: nexthop == NULL\n");
-			goto tx_error;
-		}
-
-		addr6 = (const struct in6_addr *)&neigh->primary_key;
-		addr_type = ipv6_addr_type(addr6);
-
-		if ((addr_type & IPV6_ADDR_UNICAST) &&
-		     ipv6_addr_is_isatap(addr6))
-			dst = addr6->s6_addr32[3];
-		else
-			do_tx_error = true;
-
-		neigh_release(neigh);
-		if (do_tx_error)
-			goto tx_error;
-	}
+	if ((dev->priv_flags & IFF_ISATAP) &&
+	    !ipip6_tunnel_dst_find(skb, &dst, true))
+		goto tx_error;
 
 	if (!dst)
 		dst = try_6rd(tunnel, &iph6->daddr);
 
-	if (!dst) {
-		struct neighbour *neigh = NULL;
-		bool do_tx_error = false;
-
-		if (skb_dst(skb))
-			neigh = dst_neigh_lookup(skb_dst(skb), &iph6->daddr);
-
-		if (neigh == NULL) {
-			net_dbg_ratelimited("sit: nexthop == NULL\n");
-			goto tx_error;
-		}
-
-		addr6 = (const struct in6_addr *)&neigh->primary_key;
-		addr_type = ipv6_addr_type(addr6);
+	if (!dst && !ipip6_tunnel_dst_find(skb, &dst, false))
+		goto tx_error;
 
-		if (addr_type == IPV6_ADDR_ANY) {
-			addr6 = &ipv6_hdr(skb)->daddr;
-			addr_type = ipv6_addr_type(addr6);
+	flowi4_init_output(&fl4, tunnel->parms.link, tunnel->fwmark,
+			   tos & INET_DSCP_MASK, RT_SCOPE_UNIVERSE,
+			   IPPROTO_IPV6, 0, dst, tiph->saddr, 0, 0,
+			   sock_net_uid(tunnel->net, NULL));
+
+	rt = dst_cache_get_ip4(&tunnel->dst_cache, &fl4.saddr);
+	if (!rt) {
+		rt = ip_route_output_flow(tunnel->net, &fl4, NULL);
+		if (IS_ERR(rt)) {
+			DEV_STATS_INC(dev, tx_carrier_errors);
+			goto tx_error_icmp;
 		}
-
-		if ((addr_type & IPV6_ADDR_COMPATv4) != 0)
-			dst = addr6->s6_addr32[3];
-		else
-			do_tx_error = true;
-
-		neigh_release(neigh);
-		if (do_tx_error)
-			goto tx_error;
+		dst_cache_set_ip4(&tunnel->dst_cache, &rt->dst, fl4.saddr);
 	}
 
-	rt = ip_route_output_ports(tunnel->net, &fl4, NULL,
-				   dst, tiph->saddr,
-				   0, 0,
-				   IPPROTO_IPV6, RT_TOS(tos),
-				   tunnel->parms.link);
-	if (IS_ERR(rt)) {
-		dev->stats.tx_carrier_errors++;
-		goto tx_error_icmp;
-	}
-	if (rt->rt_type != RTN_UNICAST) {
+	if (rt->rt_type != RTN_UNICAST && rt->rt_type != RTN_LOCAL) {
 		ip_rt_put(rt);
-		dev->stats.tx_carrier_errors++;
+		DEV_STATS_INC(dev, tx_carrier_errors);
 		goto tx_error_icmp;
 	}
 	tdev = rt->dst.dev;
 
 	if (tdev == dev) {
 		ip_rt_put(rt);
-		dev->stats.collisions++;
+		DEV_STATS_INC(dev, collisions);
+		goto tx_error;
+	}
+
+	if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP4)) {
+		ip_rt_put(rt);
 		goto tx_error;
 	}
 
 	if (df) {
-		mtu = dst_mtu(&rt->dst) - sizeof(struct iphdr);
+		mtu = dst_mtu(&rt->dst) - t_hlen;
 
-		if (mtu < 68) {
-			dev->stats.collisions++;
+		if (mtu < IPV4_MIN_MTU) {
+			DEV_STATS_INC(dev, collisions);
 			ip_rt_put(rt);
 			goto tx_error;
 		}
@@ -841,11 +975,11 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 			df = 0;
 		}
 
-		if (tunnel->parms.iph.daddr && skb_dst(skb))
-			skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
+		if (tunnel->parms.iph.daddr)
+			skb_dst_update_pmtu_no_confirm(skb, mtu);
 
-		if (skb->len > mtu) {
-			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+		if (skb->len > mtu && !skb_is_gso(skb)) {
+			icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
 			ip_rt_put(rt);
 			goto tx_error;
 		}
@@ -860,21 +994,18 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 			tunnel->err_count = 0;
 	}
 
-	if (tunnel->net != dev_net(dev))
-		skb_scrub_packet(skb);
-
 	/*
 	 * Okay, now see if we can stuff it in the buffer as-is.
 	 */
-	max_headroom = LL_RESERVED_SPACE(tdev)+sizeof(struct iphdr);
+	max_headroom = LL_RESERVED_SPACE(tdev) + t_hlen;
 
 	if (skb_headroom(skb) < max_headroom || skb_shared(skb) ||
 	    (skb_cloned(skb) && !skb_clone_writable(skb, 0))) {
 		struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom);
 		if (!new_skb) {
 			ip_rt_put(rt);
-			dev->stats.tx_dropped++;
-			dev_kfree_skb(skb);
+			DEV_STATS_INC(dev, tx_dropped);
+			kfree_skb(skb);
 			return NETDEV_TX_OK;
 		}
 		if (skb->sk)
@@ -888,43 +1019,62 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 		ttl = iph6->hop_limit;
 	tos = INET_ECN_encapsulate(tos, ipv6_get_dsfield(iph6));
 
-	err = iptunnel_xmit(dev_net(dev), rt, skb, fl4.saddr, fl4.daddr,
-			    IPPROTO_IPV6, tos, ttl, df);
-	iptunnel_xmit_stats(err, &dev->stats, dev->tstats);
+	if (ip_tunnel_encap(skb, &tunnel->encap, &protocol, &fl4) < 0) {
+		ip_rt_put(rt);
+		goto tx_error;
+	}
+
+	skb_set_inner_ipproto(skb, IPPROTO_IPV6);
+
+	iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, protocol, tos, ttl,
+		      df, !net_eq(tunnel->net, dev_net(dev)), 0);
 	return NETDEV_TX_OK;
 
 tx_error_icmp:
 	dst_link_failure(skb);
 tx_error:
-	dev->stats.tx_errors++;
-	dev_kfree_skb(skb);
+	kfree_skb(skb);
+	DEV_STATS_INC(dev, tx_errors);
 	return NETDEV_TX_OK;
 }
 
-static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t sit_tunnel_xmit__(struct sk_buff *skb,
+				     struct net_device *dev, u8 ipproto)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	const struct iphdr  *tiph = &tunnel->parms.iph;
 
-	if (likely(!skb->encapsulation)) {
-		skb_reset_inner_headers(skb);
-		skb->encapsulation = 1;
-	}
+	if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP4))
+		goto tx_error;
+
+	skb_set_inner_ipproto(skb, ipproto);
 
-	ip_tunnel_xmit(skb, dev, tiph, IPPROTO_IPIP);
+	ip_tunnel_xmit(skb, dev, tiph, ipproto);
+	return NETDEV_TX_OK;
+tx_error:
+	kfree_skb(skb);
+	DEV_STATS_INC(dev, tx_errors);
 	return NETDEV_TX_OK;
 }
 
 static netdev_tx_t sit_tunnel_xmit(struct sk_buff *skb,
 				   struct net_device *dev)
 {
+	if (!pskb_inet_may_pull(skb))
+		goto tx_err;
+
 	switch (skb->protocol) {
 	case htons(ETH_P_IP):
-		ipip_tunnel_xmit(skb, dev);
+		sit_tunnel_xmit__(skb, dev, IPPROTO_IPIP);
 		break;
 	case htons(ETH_P_IPV6):
 		ipip6_tunnel_xmit(skb, dev);
 		break;
+#if IS_ENABLED(CONFIG_MPLS)
+	case htons(ETH_P_MPLS_UC):
+		sit_tunnel_xmit__(skb, dev, IPPROTO_MPLS);
+		break;
+#endif
 	default:
 		goto tx_err;
 	}
@@ -932,20 +1082,21 @@ static netdev_tx_t sit_tunnel_xmit(struct sk_buff *skb,
 	return NETDEV_TX_OK;
 
 tx_err:
-	dev->stats.tx_errors++;
-	dev_kfree_skb(skb);
+	DEV_STATS_INC(dev, tx_errors);
+	kfree_skb(skb);
 	return NETDEV_TX_OK;
 
 }
 
 static void ipip6_tunnel_bind_dev(struct net_device *dev)
 {
+	struct ip_tunnel *tunnel = netdev_priv(dev);
+	int t_hlen = tunnel->hlen + sizeof(struct iphdr);
 	struct net_device *tdev = NULL;
-	struct ip_tunnel *tunnel;
+	int hlen = LL_MAX_HEADER;
 	const struct iphdr *iph;
 	struct flowi4 fl4;
 
-	tunnel = netdev_priv(dev);
 	iph = &tunnel->parms.iph;
 
 	if (iph->daddr) {
@@ -954,7 +1105,7 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev)
 							  iph->daddr, iph->saddr,
 							  0, 0,
 							  IPPROTO_IPV6,
-							  RT_TOS(iph->tos),
+							  iph->tos & INET_DSCP_MASK,
 							  tunnel->parms.link);
 
 		if (!IS_ERR(rt)) {
@@ -967,16 +1118,21 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev)
 	if (!tdev && tunnel->parms.link)
 		tdev = __dev_get_by_index(tunnel->net, tunnel->parms.link);
 
-	if (tdev) {
-		dev->hard_header_len = tdev->hard_header_len + sizeof(struct iphdr);
-		dev->mtu = tdev->mtu - sizeof(struct iphdr);
-		if (dev->mtu < IPV6_MIN_MTU)
-			dev->mtu = IPV6_MIN_MTU;
+	if (tdev && !netif_is_l3_master(tdev)) {
+		int mtu;
+
+		mtu = tdev->mtu - t_hlen;
+		if (mtu < IPV6_MIN_MTU)
+			mtu = IPV6_MIN_MTU;
+		WRITE_ONCE(dev->mtu, mtu);
+		hlen = tdev->hard_header_len + tdev->needed_headroom;
 	}
-	dev->iflink = tunnel->parms.link;
+	dev->needed_headroom = t_hlen + hlen;
 }
 
-static void ipip6_tunnel_update(struct ip_tunnel *t, struct ip_tunnel_parm *p)
+static void ipip6_tunnel_update(struct ip_tunnel *t,
+				struct ip_tunnel_parm_kern *p,
+				__u32 fwmark)
 {
 	struct net *net = t->net;
 	struct sit_net *sitn = net_generic(net, sit_net_id);
@@ -985,15 +1141,18 @@ static void ipip6_tunnel_update(struct ip_tunnel *t, struct ip_tunnel_parm *p)
 	synchronize_net();
 	t->parms.iph.saddr = p->iph.saddr;
 	t->parms.iph.daddr = p->iph.daddr;
-	memcpy(t->dev->dev_addr, &p->iph.saddr, 4);
+	__dev_addr_set(t->dev, &p->iph.saddr, 4);
 	memcpy(t->dev->broadcast, &p->iph.daddr, 4);
 	ipip6_tunnel_link(sitn, t);
 	t->parms.iph.ttl = p->iph.ttl;
 	t->parms.iph.tos = p->iph.tos;
-	if (t->parms.link != p->link) {
+	t->parms.iph.frag_off = p->iph.frag_off;
+	if (t->parms.link != p->link || t->fwmark != fwmark) {
 		t->parms.link = p->link;
+		t->fwmark = fwmark;
 		ipip6_tunnel_bind_dev(t->dev);
 	}
+	dst_cache_reset(&t->dst_cache);
 	netdev_state_change(t->dev);
 }
 
@@ -1024,282 +1183,295 @@ static int ipip6_tunnel_update_6rd(struct ip_tunnel *t,
 	t->ip6rd.relay_prefix = relay_prefix;
 	t->ip6rd.prefixlen = ip6rd->prefixlen;
 	t->ip6rd.relay_prefixlen = ip6rd->relay_prefixlen;
+	dst_cache_reset(&t->dst_cache);
 	netdev_state_change(t->dev);
 	return 0;
 }
-#endif
 
 static int
-ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
+ipip6_tunnel_get6rd(struct net_device *dev, struct ip_tunnel_parm __user *data)
 {
-	int err = 0;
-	struct ip_tunnel_parm p;
-	struct ip_tunnel_prl prl;
-	struct ip_tunnel *t;
-	struct net *net = dev_net(dev);
-	struct sit_net *sitn = net_generic(net, sit_net_id);
-#ifdef CONFIG_IPV6_SIT_6RD
+	struct ip_tunnel *t = netdev_priv(dev);
+	struct ip_tunnel_parm_kern p;
 	struct ip_tunnel_6rd ip6rd;
-#endif
 
-	switch (cmd) {
-	case SIOCGETTUNNEL:
-#ifdef CONFIG_IPV6_SIT_6RD
-	case SIOCGET6RD:
-#endif
-		t = NULL;
-		if (dev == sitn->fb_tunnel_dev) {
-			if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) {
-				err = -EFAULT;
-				break;
-			}
-			t = ipip6_tunnel_locate(net, &p, 0);
-		}
-		if (t == NULL)
-			t = netdev_priv(dev);
+	if (dev == dev_to_sit_net(dev)->fb_tunnel_dev) {
+		if (!ip_tunnel_parm_from_user(&p, data))
+			return -EFAULT;
+		t = ipip6_tunnel_locate(t->net, &p, 0);
+	}
+	if (!t)
+		t = netdev_priv(dev);
 
-		err = -EFAULT;
-		if (cmd == SIOCGETTUNNEL) {
-			memcpy(&p, &t->parms, sizeof(p));
-			if (copy_to_user(ifr->ifr_ifru.ifru_data, &p,
-					 sizeof(p)))
-				goto done;
-#ifdef CONFIG_IPV6_SIT_6RD
-		} else {
-			ip6rd.prefix = t->ip6rd.prefix;
-			ip6rd.relay_prefix = t->ip6rd.relay_prefix;
-			ip6rd.prefixlen = t->ip6rd.prefixlen;
-			ip6rd.relay_prefixlen = t->ip6rd.relay_prefixlen;
-			if (copy_to_user(ifr->ifr_ifru.ifru_data, &ip6rd,
-					 sizeof(ip6rd)))
-				goto done;
+	ip6rd.prefix = t->ip6rd.prefix;
+	ip6rd.relay_prefix = t->ip6rd.relay_prefix;
+	ip6rd.prefixlen = t->ip6rd.prefixlen;
+	ip6rd.relay_prefixlen = t->ip6rd.relay_prefixlen;
+	if (copy_to_user(data, &ip6rd, sizeof(ip6rd)))
+		return -EFAULT;
+	return 0;
+}
+
+static int
+ipip6_tunnel_6rdctl(struct net_device *dev, struct ip_tunnel_6rd __user *data,
+		    int cmd)
+{
+	struct ip_tunnel *t = netdev_priv(dev);
+	struct ip_tunnel_6rd ip6rd;
+	int err;
+
+	if (!ns_capable(t->net->user_ns, CAP_NET_ADMIN))
+		return -EPERM;
+	if (copy_from_user(&ip6rd, data, sizeof(ip6rd)))
+		return -EFAULT;
+
+	if (cmd != SIOCDEL6RD) {
+		err = ipip6_tunnel_update_6rd(t, &ip6rd);
+		if (err < 0)
+			return err;
+	} else
+		ipip6_tunnel_clone_6rd(dev, dev_to_sit_net(dev));
+	return 0;
+}
+
+#endif /* CONFIG_IPV6_SIT_6RD */
+
+static bool ipip6_valid_ip_proto(u8 ipproto)
+{
+	return ipproto == IPPROTO_IPV6 ||
+		ipproto == IPPROTO_IPIP ||
+#if IS_ENABLED(CONFIG_MPLS)
+		ipproto == IPPROTO_MPLS ||
 #endif
-		}
-		err = 0;
-		break;
+		ipproto == 0;
+}
 
-	case SIOCADDTUNNEL:
-	case SIOCCHGTUNNEL:
-		err = -EPERM;
-		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
-			goto done;
-
-		err = -EFAULT;
-		if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
-			goto done;
-
-		err = -EINVAL;
-		if (p.iph.protocol != IPPROTO_IPV6 &&
-		    p.iph.protocol != IPPROTO_IPIP &&
-		    p.iph.protocol != 0)
-			goto done;
-		if (p.iph.version != 4 ||
-		    p.iph.ihl != 5 || (p.iph.frag_off&htons(~IP_DF)))
-			goto done;
-		if (p.iph.ttl)
-			p.iph.frag_off |= htons(IP_DF);
-
-		t = ipip6_tunnel_locate(net, &p, cmd == SIOCADDTUNNEL);
-
-		if (dev != sitn->fb_tunnel_dev && cmd == SIOCCHGTUNNEL) {
-			if (t != NULL) {
-				if (t->dev != dev) {
-					err = -EEXIST;
-					break;
-				}
-			} else {
-				if (((dev->flags&IFF_POINTOPOINT) && !p.iph.daddr) ||
-				    (!(dev->flags&IFF_POINTOPOINT) && p.iph.daddr)) {
-					err = -EINVAL;
-					break;
-				}
-				t = netdev_priv(dev);
-			}
+static int
+__ipip6_tunnel_ioctl_validate(struct net *net, struct ip_tunnel_parm_kern *p)
+{
+	if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
+		return -EPERM;
 
-			ipip6_tunnel_update(t, &p);
-		}
+	if (!ipip6_valid_ip_proto(p->iph.protocol))
+		return -EINVAL;
+	if (p->iph.version != 4 ||
+	    p->iph.ihl != 5 || (p->iph.frag_off & htons(~IP_DF)))
+		return -EINVAL;
 
-		if (t) {
-			err = 0;
-			if (copy_to_user(ifr->ifr_ifru.ifru_data, &t->parms, sizeof(p)))
-				err = -EFAULT;
-		} else
-			err = (cmd == SIOCADDTUNNEL ? -ENOBUFS : -ENOENT);
-		break;
+	if (p->iph.ttl)
+		p->iph.frag_off |= htons(IP_DF);
+	return 0;
+}
 
-	case SIOCDELTUNNEL:
-		err = -EPERM;
-		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
-			goto done;
-
-		if (dev == sitn->fb_tunnel_dev) {
-			err = -EFAULT;
-			if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
-				goto done;
-			err = -ENOENT;
-			if ((t = ipip6_tunnel_locate(net, &p, 0)) == NULL)
-				goto done;
-			err = -EPERM;
-			if (t == netdev_priv(sitn->fb_tunnel_dev))
-				goto done;
-			dev = t->dev;
-		}
-		unregister_netdevice(dev);
-		err = 0;
-		break;
+static int
+ipip6_tunnel_get(struct net_device *dev, struct ip_tunnel_parm_kern *p)
+{
+	struct ip_tunnel *t = netdev_priv(dev);
 
-	case SIOCGETPRL:
-		err = -EINVAL;
-		if (dev == sitn->fb_tunnel_dev)
-			goto done;
-		err = -ENOENT;
-		if (!(t = netdev_priv(dev)))
-			goto done;
-		err = ipip6_tunnel_get_prl(t, ifr->ifr_ifru.ifru_data);
-		break;
+	if (dev == dev_to_sit_net(dev)->fb_tunnel_dev)
+		t = ipip6_tunnel_locate(t->net, p, 0);
+	if (!t)
+		t = netdev_priv(dev);
+	memcpy(p, &t->parms, sizeof(*p));
+	return 0;
+}
 
-	case SIOCADDPRL:
-	case SIOCDELPRL:
-	case SIOCCHGPRL:
-		err = -EPERM;
-		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
-			goto done;
-		err = -EINVAL;
-		if (dev == sitn->fb_tunnel_dev)
-			goto done;
-		err = -EFAULT;
-		if (copy_from_user(&prl, ifr->ifr_ifru.ifru_data, sizeof(prl)))
-			goto done;
-		err = -ENOENT;
-		if (!(t = netdev_priv(dev)))
-			goto done;
-
-		switch (cmd) {
-		case SIOCDELPRL:
-			err = ipip6_tunnel_del_prl(t, &prl);
-			break;
-		case SIOCADDPRL:
-		case SIOCCHGPRL:
-			err = ipip6_tunnel_add_prl(t, &prl, cmd == SIOCCHGPRL);
-			break;
+static int
+ipip6_tunnel_add(struct net_device *dev, struct ip_tunnel_parm_kern *p)
+{
+	struct ip_tunnel *t = netdev_priv(dev);
+	int err;
+
+	err = __ipip6_tunnel_ioctl_validate(t->net, p);
+	if (err)
+		return err;
+
+	t = ipip6_tunnel_locate(t->net, p, 1);
+	if (!t)
+		return -ENOBUFS;
+	return 0;
+}
+
+static int
+ipip6_tunnel_change(struct net_device *dev, struct ip_tunnel_parm_kern *p)
+{
+	struct ip_tunnel *t = netdev_priv(dev);
+	int err;
+
+	err = __ipip6_tunnel_ioctl_validate(t->net, p);
+	if (err)
+		return err;
+
+	t = ipip6_tunnel_locate(t->net, p, 0);
+	if (dev == dev_to_sit_net(dev)->fb_tunnel_dev) {
+		if (!t)
+			return -ENOENT;
+	} else {
+		if (t) {
+			if (t->dev != dev)
+				return -EEXIST;
+		} else {
+			if (((dev->flags & IFF_POINTOPOINT) && !p->iph.daddr) ||
+			    (!(dev->flags & IFF_POINTOPOINT) && p->iph.daddr))
+				return -EINVAL;
+			t = netdev_priv(dev);
 		}
-		netdev_state_change(dev);
-		break;
 
-#ifdef CONFIG_IPV6_SIT_6RD
-	case SIOCADD6RD:
-	case SIOCCHG6RD:
-	case SIOCDEL6RD:
-		err = -EPERM;
-		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
-			goto done;
+		ipip6_tunnel_update(t, p, t->fwmark);
+	}
 
-		err = -EFAULT;
-		if (copy_from_user(&ip6rd, ifr->ifr_ifru.ifru_data,
-				   sizeof(ip6rd)))
-			goto done;
+	return 0;
+}
 
-		t = netdev_priv(dev);
+static int
+ipip6_tunnel_del(struct net_device *dev, struct ip_tunnel_parm_kern *p)
+{
+	struct ip_tunnel *t = netdev_priv(dev);
 
-		if (cmd != SIOCDEL6RD) {
-			err = ipip6_tunnel_update_6rd(t, &ip6rd);
-			if (err < 0)
-				goto done;
-		} else
-			ipip6_tunnel_clone_6rd(dev, sitn);
+	if (!ns_capable(t->net->user_ns, CAP_NET_ADMIN))
+		return -EPERM;
 
-		err = 0;
-		break;
-#endif
+	if (dev == dev_to_sit_net(dev)->fb_tunnel_dev) {
+		t = ipip6_tunnel_locate(t->net, p, 0);
+		if (!t)
+			return -ENOENT;
+		if (t == netdev_priv(dev_to_sit_net(dev)->fb_tunnel_dev))
+			return -EPERM;
+		dev = t->dev;
+	}
+	unregister_netdevice(dev);
+	return 0;
+}
 
+static int
+ipip6_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm_kern *p,
+		 int cmd)
+{
+	switch (cmd) {
+	case SIOCGETTUNNEL:
+		return ipip6_tunnel_get(dev, p);
+	case SIOCADDTUNNEL:
+		return ipip6_tunnel_add(dev, p);
+	case SIOCCHGTUNNEL:
+		return ipip6_tunnel_change(dev, p);
+	case SIOCDELTUNNEL:
+		return ipip6_tunnel_del(dev, p);
 	default:
-		err = -EINVAL;
+		return -EINVAL;
 	}
-
-done:
-	return err;
 }
 
-static int ipip6_tunnel_change_mtu(struct net_device *dev, int new_mtu)
+static int
+ipip6_tunnel_siocdevprivate(struct net_device *dev, struct ifreq *ifr,
+			    void __user *data, int cmd)
 {
-	if (new_mtu < IPV6_MIN_MTU || new_mtu > 0xFFF8 - sizeof(struct iphdr))
+	switch (cmd) {
+	case SIOCGETTUNNEL:
+	case SIOCADDTUNNEL:
+	case SIOCCHGTUNNEL:
+	case SIOCDELTUNNEL:
+		return ip_tunnel_siocdevprivate(dev, ifr, data, cmd);
+	case SIOCGETPRL:
+		return ipip6_tunnel_get_prl(dev, data);
+	case SIOCADDPRL:
+	case SIOCDELPRL:
+	case SIOCCHGPRL:
+		return ipip6_tunnel_prl_ctl(dev, data, cmd);
+#ifdef CONFIG_IPV6_SIT_6RD
+	case SIOCGET6RD:
+		return ipip6_tunnel_get6rd(dev, data);
+	case SIOCADD6RD:
+	case SIOCCHG6RD:
+	case SIOCDEL6RD:
+		return ipip6_tunnel_6rdctl(dev, data, cmd);
+#endif
+	default:
 		return -EINVAL;
-	dev->mtu = new_mtu;
-	return 0;
+	}
 }
 
 static const struct net_device_ops ipip6_netdev_ops = {
+	.ndo_init	= ipip6_tunnel_init,
 	.ndo_uninit	= ipip6_tunnel_uninit,
 	.ndo_start_xmit	= sit_tunnel_xmit,
-	.ndo_do_ioctl	= ipip6_tunnel_ioctl,
-	.ndo_change_mtu	= ipip6_tunnel_change_mtu,
-	.ndo_get_stats64 = ip_tunnel_get_stats64,
+	.ndo_siocdevprivate = ipip6_tunnel_siocdevprivate,
+	.ndo_get_iflink = ip_tunnel_get_iflink,
+	.ndo_tunnel_ctl = ipip6_tunnel_ctl,
 };
 
 static void ipip6_dev_free(struct net_device *dev)
 {
-	free_percpu(dev->tstats);
-	free_netdev(dev);
+	struct ip_tunnel *tunnel = netdev_priv(dev);
+
+	dst_cache_destroy(&tunnel->dst_cache);
 }
 
+#define SIT_FEATURES (NETIF_F_SG	   | \
+		      NETIF_F_FRAGLIST	   | \
+		      NETIF_F_HIGHDMA	   | \
+		      NETIF_F_GSO_SOFTWARE | \
+		      NETIF_F_HW_CSUM)
+
 static void ipip6_tunnel_setup(struct net_device *dev)
 {
+	struct ip_tunnel *tunnel = netdev_priv(dev);
+	int t_hlen = tunnel->hlen + sizeof(struct iphdr);
+
 	dev->netdev_ops		= &ipip6_netdev_ops;
-	dev->destructor 	= ipip6_dev_free;
+	dev->header_ops		= &ip_tunnel_header_ops;
+	dev->needs_free_netdev	= true;
+	dev->priv_destructor	= ipip6_dev_free;
 
 	dev->type		= ARPHRD_SIT;
-	dev->hard_header_len 	= LL_MAX_HEADER + sizeof(struct iphdr);
-	dev->mtu		= ETH_DATA_LEN - sizeof(struct iphdr);
+	dev->mtu		= ETH_DATA_LEN - t_hlen;
+	dev->min_mtu		= IPV6_MIN_MTU;
+	dev->max_mtu		= IP6_MAX_MTU - t_hlen;
 	dev->flags		= IFF_NOARP;
-	dev->priv_flags	       &= ~IFF_XMIT_DST_RELEASE;
-	dev->iflink		= 0;
+	netif_keep_dst(dev);
 	dev->addr_len		= 4;
-	dev->features		|= NETIF_F_LLTX;
+	dev->lltx		= true;
+	dev->features		|= SIT_FEATURES;
+	dev->hw_features	|= SIT_FEATURES;
+	dev->pcpu_stat_type	= NETDEV_PCPU_STAT_TSTATS;
+
 }
 
 static int ipip6_tunnel_init(struct net_device *dev)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
+	int err;
 
 	tunnel->dev = dev;
-	tunnel->net = dev_net(dev);
-
-	memcpy(dev->dev_addr, &tunnel->parms.iph.saddr, 4);
-	memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4);
+	strcpy(tunnel->parms.name, dev->name);
 
 	ipip6_tunnel_bind_dev(dev);
-	dev->tstats = alloc_percpu(struct pcpu_tstats);
-	if (!dev->tstats)
-		return -ENOMEM;
 
+	err = dst_cache_init(&tunnel->dst_cache, GFP_KERNEL);
+	if (err)
+		return err;
+
+	netdev_hold(dev, &tunnel->dev_tracker, GFP_KERNEL);
+	netdev_lockdep_set_classes(dev);
 	return 0;
 }
 
-static int __net_init ipip6_fb_tunnel_init(struct net_device *dev)
+static void __net_init ipip6_fb_tunnel_init(struct net_device *dev)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	struct iphdr *iph = &tunnel->parms.iph;
 	struct net *net = dev_net(dev);
 	struct sit_net *sitn = net_generic(net, sit_net_id);
 
-	tunnel->dev = dev;
-	tunnel->net = dev_net(dev);
-	strcpy(tunnel->parms.name, dev->name);
-
 	iph->version		= 4;
 	iph->protocol		= IPPROTO_IPV6;
 	iph->ihl		= 5;
 	iph->ttl		= 64;
 
-	dev->tstats = alloc_percpu(struct pcpu_tstats);
-	if (!dev->tstats)
-		return -ENOMEM;
-	dev_hold(dev);
 	rcu_assign_pointer(sitn->tunnels_wc[0], tunnel);
-	return 0;
 }
 
-static int ipip6_validate(struct nlattr *tb[], struct nlattr *data[])
+static int ipip6_validate(struct nlattr *tb[], struct nlattr *data[],
+			  struct netlink_ext_ack *extack)
 {
 	u8 proto;
 
@@ -1307,16 +1479,15 @@ static int ipip6_validate(struct nlattr *tb[], struct nlattr *data[])
 		return 0;
 
 	proto = nla_get_u8(data[IFLA_IPTUN_PROTO]);
-	if (proto != IPPROTO_IPV6 &&
-	    proto != IPPROTO_IPIP &&
-	    proto != 0)
+	if (!ipip6_valid_ip_proto(proto))
 		return -EINVAL;
 
 	return 0;
 }
 
 static void ipip6_netlink_parms(struct nlattr *data[],
-				struct ip_tunnel_parm *parms)
+				struct ip_tunnel_parm_kern *parms,
+				__u32 *fwmark)
 {
 	memset(parms, 0, sizeof(*parms));
 
@@ -1328,33 +1499,10 @@ static void ipip6_netlink_parms(struct nlattr *data[],
 	if (!data)
 		return;
 
-	if (data[IFLA_IPTUN_LINK])
-		parms->link = nla_get_u32(data[IFLA_IPTUN_LINK]);
-
-	if (data[IFLA_IPTUN_LOCAL])
-		parms->iph.saddr = nla_get_be32(data[IFLA_IPTUN_LOCAL]);
-
-	if (data[IFLA_IPTUN_REMOTE])
-		parms->iph.daddr = nla_get_be32(data[IFLA_IPTUN_REMOTE]);
-
-	if (data[IFLA_IPTUN_TTL]) {
-		parms->iph.ttl = nla_get_u8(data[IFLA_IPTUN_TTL]);
-		if (parms->iph.ttl)
-			parms->iph.frag_off = htons(IP_DF);
-	}
-
-	if (data[IFLA_IPTUN_TOS])
-		parms->iph.tos = nla_get_u8(data[IFLA_IPTUN_TOS]);
-
-	if (!data[IFLA_IPTUN_PMTUDISC] || nla_get_u8(data[IFLA_IPTUN_PMTUDISC]))
-		parms->iph.frag_off = htons(IP_DF);
-
-	if (data[IFLA_IPTUN_FLAGS])
-		parms->i_flags = nla_get_be16(data[IFLA_IPTUN_FLAGS]);
-
-	if (data[IFLA_IPTUN_PROTO])
-		parms->iph.protocol = nla_get_u8(data[IFLA_IPTUN_PROTO]);
+	ip_tunnel_netlink_parms(data, parms);
 
+	if (data[IFLA_IPTUN_FWMARK])
+		*fwmark = nla_get_u32(data[IFLA_IPTUN_FWMARK]);
 }
 
 #ifdef CONFIG_IPV6_SIT_6RD
@@ -1370,8 +1518,7 @@ static bool ipip6_netlink_6rd_parms(struct nlattr *data[],
 
 	if (data[IFLA_IPTUN_6RD_PREFIX]) {
 		ret = true;
-		nla_memcpy(&ip6rd->prefix, data[IFLA_IPTUN_6RD_PREFIX],
-			   sizeof(struct in6_addr));
+		ip6rd->prefix = nla_get_in6_addr(data[IFLA_IPTUN_6RD_PREFIX]);
 	}
 
 	if (data[IFLA_IPTUN_6RD_RELAY_PREFIX]) {
@@ -1395,18 +1542,31 @@ static bool ipip6_netlink_6rd_parms(struct nlattr *data[],
 }
 #endif
 
-static int ipip6_newlink(struct net *src_net, struct net_device *dev,
-			 struct nlattr *tb[], struct nlattr *data[])
+static int ipip6_newlink(struct net_device *dev,
+			 struct rtnl_newlink_params *params,
+			 struct netlink_ext_ack *extack)
 {
-	struct net *net = dev_net(dev);
+	struct nlattr **data = params->data;
+	struct nlattr **tb = params->tb;
 	struct ip_tunnel *nt;
+	struct ip_tunnel_encap ipencap;
 #ifdef CONFIG_IPV6_SIT_6RD
 	struct ip_tunnel_6rd ip6rd;
 #endif
+	struct net *net;
 	int err;
 
+	net = params->link_net ? : dev_net(dev);
 	nt = netdev_priv(dev);
-	ipip6_netlink_parms(data, &nt->parms);
+	nt->net = net;
+
+	if (ip_tunnel_netlink_encap_parms(data, &ipencap)) {
+		err = ip_tunnel_encap_setup(nt, &ipencap);
+		if (err < 0)
+			return err;
+	}
+
+	ipip6_netlink_parms(data, &nt->parms, &nt->fwmark);
 
 	if (ipip6_tunnel_locate(net, &nt->parms, 0))
 		return -EEXIST;
@@ -1415,29 +1575,50 @@ static int ipip6_newlink(struct net *src_net, struct net_device *dev,
 	if (err < 0)
 		return err;
 
+	if (tb[IFLA_MTU]) {
+		u32 mtu = nla_get_u32(tb[IFLA_MTU]);
+
+		if (mtu >= IPV6_MIN_MTU &&
+		    mtu <= IP6_MAX_MTU - dev->hard_header_len)
+			dev->mtu = mtu;
+	}
+
 #ifdef CONFIG_IPV6_SIT_6RD
-	if (ipip6_netlink_6rd_parms(data, &ip6rd))
+	if (ipip6_netlink_6rd_parms(data, &ip6rd)) {
 		err = ipip6_tunnel_update_6rd(nt, &ip6rd);
+		if (err < 0)
+			unregister_netdevice_queue(dev, NULL);
+	}
 #endif
 
 	return err;
 }
 
 static int ipip6_changelink(struct net_device *dev, struct nlattr *tb[],
-			  struct nlattr *data[])
+			    struct nlattr *data[],
+			    struct netlink_ext_ack *extack)
 {
 	struct ip_tunnel *t = netdev_priv(dev);
-	struct ip_tunnel_parm p;
+	struct ip_tunnel_encap ipencap;
+	struct ip_tunnel_parm_kern p;
 	struct net *net = t->net;
 	struct sit_net *sitn = net_generic(net, sit_net_id);
 #ifdef CONFIG_IPV6_SIT_6RD
 	struct ip_tunnel_6rd ip6rd;
 #endif
+	__u32 fwmark = t->fwmark;
+	int err;
 
 	if (dev == sitn->fb_tunnel_dev)
 		return -EINVAL;
 
-	ipip6_netlink_parms(data, &p);
+	if (ip_tunnel_netlink_encap_parms(data, &ipencap)) {
+		err = ip_tunnel_encap_setup(t, &ipencap);
+		if (err < 0)
+			return err;
+	}
+
+	ipip6_netlink_parms(data, &p, &fwmark);
 
 	if (((dev->flags & IFF_POINTOPOINT) && !p.iph.daddr) ||
 	    (!(dev->flags & IFF_POINTOPOINT) && p.iph.daddr))
@@ -1451,7 +1632,7 @@ static int ipip6_changelink(struct net_device *dev, struct nlattr *tb[],
 	} else
 		t = netdev_priv(dev);
 
-	ipip6_tunnel_update(t, &p);
+	ipip6_tunnel_update(t, &p, fwmark);
 
 #ifdef CONFIG_IPV6_SIT_6RD
 	if (ipip6_netlink_6rd_parms(data, &ip6rd))
@@ -1490,30 +1671,42 @@ static size_t ipip6_get_size(const struct net_device *dev)
 		/* IFLA_IPTUN_6RD_RELAY_PREFIXLEN */
 		nla_total_size(2) +
 #endif
+		/* IFLA_IPTUN_ENCAP_TYPE */
+		nla_total_size(2) +
+		/* IFLA_IPTUN_ENCAP_FLAGS */
+		nla_total_size(2) +
+		/* IFLA_IPTUN_ENCAP_SPORT */
+		nla_total_size(2) +
+		/* IFLA_IPTUN_ENCAP_DPORT */
+		nla_total_size(2) +
+		/* IFLA_IPTUN_FWMARK */
+		nla_total_size(4) +
 		0;
 }
 
 static int ipip6_fill_info(struct sk_buff *skb, const struct net_device *dev)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
-	struct ip_tunnel_parm *parm = &tunnel->parms;
+	struct ip_tunnel_parm_kern *parm = &tunnel->parms;
 
 	if (nla_put_u32(skb, IFLA_IPTUN_LINK, parm->link) ||
-	    nla_put_be32(skb, IFLA_IPTUN_LOCAL, parm->iph.saddr) ||
-	    nla_put_be32(skb, IFLA_IPTUN_REMOTE, parm->iph.daddr) ||
+	    nla_put_in_addr(skb, IFLA_IPTUN_LOCAL, parm->iph.saddr) ||
+	    nla_put_in_addr(skb, IFLA_IPTUN_REMOTE, parm->iph.daddr) ||
 	    nla_put_u8(skb, IFLA_IPTUN_TTL, parm->iph.ttl) ||
 	    nla_put_u8(skb, IFLA_IPTUN_TOS, parm->iph.tos) ||
 	    nla_put_u8(skb, IFLA_IPTUN_PMTUDISC,
 		       !!(parm->iph.frag_off & htons(IP_DF))) ||
 	    nla_put_u8(skb, IFLA_IPTUN_PROTO, parm->iph.protocol) ||
-	    nla_put_be16(skb, IFLA_IPTUN_FLAGS, parm->i_flags))
+	    nla_put_be16(skb, IFLA_IPTUN_FLAGS,
+			 ip_tunnel_flags_to_be16(parm->i_flags)) ||
+	    nla_put_u32(skb, IFLA_IPTUN_FWMARK, tunnel->fwmark))
 		goto nla_put_failure;
 
 #ifdef CONFIG_IPV6_SIT_6RD
-	if (nla_put(skb, IFLA_IPTUN_6RD_PREFIX, sizeof(struct in6_addr),
-		    &tunnel->ip6rd.prefix) ||
-	    nla_put_be32(skb, IFLA_IPTUN_6RD_RELAY_PREFIX,
-			 tunnel->ip6rd.relay_prefix) ||
+	if (nla_put_in6_addr(skb, IFLA_IPTUN_6RD_PREFIX,
+			     &tunnel->ip6rd.prefix) ||
+	    nla_put_in_addr(skb, IFLA_IPTUN_6RD_RELAY_PREFIX,
+			    tunnel->ip6rd.relay_prefix) ||
 	    nla_put_u16(skb, IFLA_IPTUN_6RD_PREFIXLEN,
 			tunnel->ip6rd.prefixlen) ||
 	    nla_put_u16(skb, IFLA_IPTUN_6RD_RELAY_PREFIXLEN,
@@ -1521,6 +1714,16 @@ static int ipip6_fill_info(struct sk_buff *skb, const struct net_device *dev)
 		goto nla_put_failure;
 #endif
 
+	if (nla_put_u16(skb, IFLA_IPTUN_ENCAP_TYPE,
+			tunnel->encap.type) ||
+	    nla_put_be16(skb, IFLA_IPTUN_ENCAP_SPORT,
+			tunnel->encap.sport) ||
+	    nla_put_be16(skb, IFLA_IPTUN_ENCAP_DPORT,
+			tunnel->encap.dport) ||
+	    nla_put_u16(skb, IFLA_IPTUN_ENCAP_FLAGS,
+			tunnel->encap.flags))
+		goto nla_put_failure;
+
 	return 0;
 
 nla_put_failure:
@@ -1542,8 +1745,22 @@ static const struct nla_policy ipip6_policy[IFLA_IPTUN_MAX + 1] = {
 	[IFLA_IPTUN_6RD_PREFIXLEN]	= { .type = NLA_U16 },
 	[IFLA_IPTUN_6RD_RELAY_PREFIXLEN] = { .type = NLA_U16 },
 #endif
+	[IFLA_IPTUN_ENCAP_TYPE]		= { .type = NLA_U16 },
+	[IFLA_IPTUN_ENCAP_FLAGS]	= { .type = NLA_U16 },
+	[IFLA_IPTUN_ENCAP_SPORT]	= { .type = NLA_U16 },
+	[IFLA_IPTUN_ENCAP_DPORT]	= { .type = NLA_U16 },
+	[IFLA_IPTUN_FWMARK]		= { .type = NLA_U32 },
 };
 
+static void ipip6_dellink(struct net_device *dev, struct list_head *head)
+{
+	struct net *net = dev_net(dev);
+	struct sit_net *sitn = net_generic(net, sit_net_id);
+
+	if (dev != sitn->fb_tunnel_dev)
+		unregister_netdevice_queue(dev, head);
+}
+
 static struct rtnl_link_ops sit_link_ops __read_mostly = {
 	.kind		= "sit",
 	.maxtype	= IFLA_IPTUN_MAX,
@@ -1555,6 +1772,8 @@ static struct rtnl_link_ops sit_link_ops __read_mostly = {
 	.changelink	= ipip6_changelink,
 	.get_size	= ipip6_get_size,
 	.fill_info	= ipip6_fill_info,
+	.dellink	= ipip6_dellink,
+	.get_link_net	= ip_tunnel_get_link_net,
 };
 
 static struct xfrm_tunnel sit_handler __read_mostly = {
@@ -1569,9 +1788,17 @@ static struct xfrm_tunnel ipip_handler __read_mostly = {
 	.priority	=	2,
 };
 
-static void __net_exit sit_destroy_tunnels(struct sit_net *sitn, struct list_head *head)
+#if IS_ENABLED(CONFIG_MPLS)
+static struct xfrm_tunnel mplsip_handler __read_mostly = {
+	.handler	=	mplsip_rcv,
+	.err_handler	=	ipip6_err,
+	.priority	=	2,
+};
+#endif
+
+static void __net_exit sit_exit_rtnl_net(struct net *net, struct list_head *head)
 {
-	struct net *net = dev_net(sitn->fb_tunnel_dev);
+	struct sit_net *sitn = net_generic(net, sit_net_id);
 	struct net_device *dev, *aux;
 	int prio;
 
@@ -1579,20 +1806,20 @@ static void __net_exit sit_destroy_tunnels(struct sit_net *sitn, struct list_hea
 		if (dev->rtnl_link_ops == &sit_link_ops)
 			unregister_netdevice_queue(dev, head);
 
-	for (prio = 1; prio < 4; prio++) {
+	for (prio = 0; prio < 4; prio++) {
 		int h;
-		for (h = 0; h < HASH_SIZE; h++) {
+		for (h = 0; h < (prio ? IP6_SIT_HASH_SIZE : 1); h++) {
 			struct ip_tunnel *t;
 
-			t = rtnl_dereference(sitn->tunnels[prio][h]);
-			while (t != NULL) {
+			t = rtnl_net_dereference(net, sitn->tunnels[prio][h]);
+			while (t) {
 				/* If dev is in the same netns, it has already
 				 * been added to the list by the previous loop.
 				 */
-				if (dev_net(t->dev) != net)
-					unregister_netdevice_queue(t->dev,
-								   head);
-				t = rtnl_dereference(t->next);
+				if (!net_eq(dev_net(t->dev), net))
+					unregister_netdevice_queue(t->dev, head);
+
+				t = rtnl_net_dereference(net, t->next);
 			}
 		}
 	}
@@ -1609,55 +1836,45 @@ static int __net_init sit_init_net(struct net *net)
 	sitn->tunnels[2] = sitn->tunnels_r;
 	sitn->tunnels[3] = sitn->tunnels_r_l;
 
+	if (!net_has_fallback_tunnels(net))
+		return 0;
+
 	sitn->fb_tunnel_dev = alloc_netdev(sizeof(struct ip_tunnel), "sit0",
+					   NET_NAME_UNKNOWN,
 					   ipip6_tunnel_setup);
 	if (!sitn->fb_tunnel_dev) {
 		err = -ENOMEM;
 		goto err_alloc_dev;
 	}
 	dev_net_set(sitn->fb_tunnel_dev, net);
+	sitn->fb_tunnel_dev->rtnl_link_ops = &sit_link_ops;
 	/* FB netdevice is special: we have one, and only one per netns.
 	 * Allowing to move it to another netns is clearly unsafe.
 	 */
-	sitn->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL;
-
-	err = ipip6_fb_tunnel_init(sitn->fb_tunnel_dev);
-	if (err)
-		goto err_dev_free;
+	sitn->fb_tunnel_dev->netns_immutable = true;
 
-	ipip6_tunnel_clone_6rd(sitn->fb_tunnel_dev, sitn);
+	t = netdev_priv(sitn->fb_tunnel_dev);
+	t->net = net;
 
-	if ((err = register_netdev(sitn->fb_tunnel_dev)))
+	err = register_netdev(sitn->fb_tunnel_dev);
+	if (err)
 		goto err_reg_dev;
 
-	t = netdev_priv(sitn->fb_tunnel_dev);
+	ipip6_tunnel_clone_6rd(sitn->fb_tunnel_dev, sitn);
+	ipip6_fb_tunnel_init(sitn->fb_tunnel_dev);
 
 	strcpy(t->parms.name, sitn->fb_tunnel_dev->name);
 	return 0;
 
 err_reg_dev:
-	dev_put(sitn->fb_tunnel_dev);
-err_dev_free:
-	ipip6_dev_free(sitn->fb_tunnel_dev);
+	free_netdev(sitn->fb_tunnel_dev);
 err_alloc_dev:
 	return err;
 }
 
-static void __net_exit sit_exit_net(struct net *net)
-{
-	struct sit_net *sitn = net_generic(net, sit_net_id);
-	LIST_HEAD(list);
-
-	rtnl_lock();
-	sit_destroy_tunnels(sitn, &list);
-	unregister_netdevice_queue(sitn->fb_tunnel_dev, &list);
-	unregister_netdevice_many(&list);
-	rtnl_unlock();
-}
-
 static struct pernet_operations sit_net_ops = {
 	.init = sit_init_net,
-	.exit = sit_exit_net,
+	.exit_rtnl = sit_exit_rtnl_net,
 	.id   = &sit_net_id,
 	.size = sizeof(struct sit_net),
 };
@@ -1667,6 +1884,9 @@ static void __exit sit_cleanup(void)
 	rtnl_link_unregister(&sit_link_ops);
 	xfrm4_tunnel_deregister(&sit_handler, AF_INET6);
 	xfrm4_tunnel_deregister(&ipip_handler, AF_INET);
+#if IS_ENABLED(CONFIG_MPLS)
+	xfrm4_tunnel_deregister(&mplsip_handler, AF_MPLS);
+#endif
 
 	unregister_pernet_device(&sit_net_ops);
 	rcu_barrier(); /* Wait for completion of call_rcu()'s */
@@ -1676,7 +1896,7 @@ static int __init sit_init(void)
 {
 	int err;
 
-	pr_info("IPv6 over IPv4 tunneling driver\n");
+	pr_info("IPv6, IPv4 and MPLS over IPv4 tunneling driver\n");
 
 	err = register_pernet_device(&sit_net_ops);
 	if (err < 0)
@@ -1691,6 +1911,13 @@ static int __init sit_init(void)
 		pr_info("%s: can't register ip4ip4\n", __func__);
 		goto xfrm_tunnel4_failed;
 	}
+#if IS_ENABLED(CONFIG_MPLS)
+	err = xfrm4_tunnel_register(&mplsip_handler, AF_MPLS);
+	if (err < 0) {
+		pr_info("%s: can't register mplsip\n", __func__);
+		goto xfrm_tunnel_mpls_failed;
+	}
+#endif
 	err = rtnl_link_register(&sit_link_ops);
 	if (err < 0)
 		goto rtnl_link_failed;
@@ -1699,6 +1926,10 @@ out:
 	return err;
 
 rtnl_link_failed:
+#if IS_ENABLED(CONFIG_MPLS)
+	xfrm4_tunnel_deregister(&mplsip_handler, AF_MPLS);
+xfrm_tunnel_mpls_failed:
+#endif
 	xfrm4_tunnel_deregister(&ipip_handler, AF_INET);
 xfrm_tunnel4_failed:
 	xfrm4_tunnel_deregister(&sit_handler, AF_INET6);
@@ -1709,5 +1940,7 @@ xfrm_tunnel_failed:
 
 module_init(sit_init);
 module_exit(sit_cleanup);
+MODULE_DESCRIPTION("IPv6-in-IPv4 tunnel SIT driver");
 MODULE_LICENSE("GPL");
+MODULE_ALIAS_RTNL_LINK("sit");
 MODULE_ALIAS_NETDEV("sit0");