1 files changed, 180 insertions, 57 deletions

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 7ee5cb96db3..4f408176dc6 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -475,17 +475,48 @@ static void ipip6_tunnel_uninit(struct net_device *dev)
 		ipip6_tunnel_unlink(sitn, tunnel);
 		ipip6_tunnel_del_prl(tunnel, NULL);
 	}
+	ip_tunnel_dst_reset_all(tunnel);
 	dev_put(dev);
 }
 
+/* Generate icmpv6 with type/code ICMPV6_DEST_UNREACH/ICMPV6_ADDR_UNREACH
+ * if sufficient data bytes are available
+ */
+static int ipip6_err_gen_icmpv6_unreach(struct sk_buff *skb)
+{
+	const struct iphdr *iph = (const struct iphdr *) skb->data;
+	struct rt6_info *rt;
+	struct sk_buff *skb2;
+
+	if (!pskb_may_pull(skb, iph->ihl * 4 + sizeof(struct ipv6hdr) + 8))
+		return 1;
+
+	skb2 = skb_clone(skb, GFP_ATOMIC);
+
+	if (!skb2)
+		return 1;
+
+	skb_dst_drop(skb2);
+	skb_pull(skb2, iph->ihl * 4);
+	skb_reset_network_header(skb2);
+
+	rt = rt6_lookup(dev_net(skb->dev), &ipv6_hdr(skb2)->saddr, NULL, 0, 0);
+
+	if (rt && rt->dst.dev)
+		skb2->dev = rt->dst.dev;
+
+	icmpv6_send(skb2, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0);
+
+	if (rt)
+		ip6_rt_put(rt);
+
+	kfree_skb(skb2);
+
+	return 0;
+}
 
 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;
@@ -500,7 +531,6 @@ 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:
@@ -530,12 +560,12 @@ static int ipip6_err(struct sk_buff *skb, u32 info)
 
 	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, 0, IPPROTO_IPV6, 0);
 		err = 0;
 		goto out;
 	}
 	if (type == ICMP_REDIRECT) {
-		ipv4_redirect(skb, dev_net(skb->dev), t->dev->ifindex, 0,
+		ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, 0,
 			      IPPROTO_IPV6, 0);
 		err = 0;
 		goto out;
@@ -545,6 +575,9 @@ static int ipip6_err(struct sk_buff *skb, u32 info)
 		goto out;
 
 	err = 0;
+	if (!ipip6_err_gen_icmpv6_unreach(skb))
+		goto out;
+
 	if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED)
 		goto out;
 
@@ -566,6 +599,70 @@ 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);
@@ -575,7 +672,7 @@ static int ipip6_rcv(struct sk_buff *skb)
 	tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev,
 				     iph->saddr, iph->daddr);
 	if (tunnel != NULL) {
-		struct pcpu_tstats *tstats;
+		struct pcpu_sw_netstats *tstats;
 
 		if (tunnel->parms.iph.protocol != IPPROTO_IPV6 &&
 		    tunnel->parms.iph.protocol != 0)
@@ -586,19 +683,9 @@ static int ipip6_rcv(struct sk_buff *skb)
 		IPCB(skb)->flags = 0;
 		skb->protocol = htons(ETH_P_IPV6);
 
-		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)) {
+			tunnel->dev->stats.rx_errors++;
+			goto out;
 		}
 
 		__skb_tunnel_rx(skb, tunnel->dev, tunnel->net);
@@ -616,8 +703,10 @@ static int ipip6_rcv(struct sk_buff *skb)
 		}
 
 		tstats = this_cpu_ptr(tunnel->dev->tstats);
+		u64_stats_update_begin(&tstats->syncp);
 		tstats->rx_packets++;
 		tstats->rx_bytes += skb->len;
+		u64_stats_update_end(&tstats->syncp);
 
 		netif_rx(skb);
 
@@ -748,7 +837,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 			neigh = dst_neigh_lookup(skb_dst(skb), &iph6->daddr);
 
 		if (neigh == NULL) {
-			net_dbg_ratelimited("sit: nexthop == NULL\n");
+			net_dbg_ratelimited("nexthop == NULL\n");
 			goto tx_error;
 		}
 
@@ -777,7 +866,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 			neigh = dst_neigh_lookup(skb_dst(skb), &iph6->daddr);
 
 		if (neigh == NULL) {
-			net_dbg_ratelimited("sit: nexthop == NULL\n");
+			net_dbg_ratelimited("nexthop == NULL\n");
 			goto tx_error;
 		}
 
@@ -838,7 +927,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 		if (tunnel->parms.iph.daddr && skb_dst(skb))
 			skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
 
-		if (skb->len > mtu) {
+		if (skb->len > mtu && !skb_is_gso(skb)) {
 			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
 			ip_rt_put(rt);
 			goto tx_error;
@@ -865,7 +954,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 		if (!new_skb) {
 			ip_rt_put(rt);
 			dev->stats.tx_dropped++;
-			dev_kfree_skb(skb);
+			kfree_skb(skb);
 			return NETDEV_TX_OK;
 		}
 		if (skb->sk)
@@ -879,21 +968,24 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 		ttl = iph6->hop_limit;
 	tos = INET_ECN_encapsulate(tos, ipv6_get_dsfield(iph6));
 
-	if (likely(!skb->encapsulation)) {
-		skb_reset_inner_headers(skb);
-		skb->encapsulation = 1;
+	skb = iptunnel_handle_offloads(skb, false, SKB_GSO_SIT);
+	if (IS_ERR(skb)) {
+		ip_rt_put(rt);
+		goto out;
 	}
 
-	err = iptunnel_xmit(rt, skb, fl4.saddr, fl4.daddr, IPPROTO_IPV6, tos,
-			    ttl, df, !net_eq(tunnel->net, dev_net(dev)));
+	err = iptunnel_xmit(skb->sk, rt, skb, fl4.saddr, fl4.daddr,
+			    IPPROTO_IPV6, tos, ttl, df,
+			    !net_eq(tunnel->net, dev_net(dev)));
 	iptunnel_xmit_stats(err, &dev->stats, dev->tstats);
 	return NETDEV_TX_OK;
 
 tx_error_icmp:
 	dst_link_failure(skb);
 tx_error:
+	kfree_skb(skb);
+out:
 	dev->stats.tx_errors++;
-	dev_kfree_skb(skb);
 	return NETDEV_TX_OK;
 }
 
@@ -902,13 +994,15 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 	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;
-	}
+	skb = iptunnel_handle_offloads(skb, false, SKB_GSO_IPIP);
+	if (IS_ERR(skb))
+		goto out;
 
 	ip_tunnel_xmit(skb, dev, tiph, IPPROTO_IPIP);
 	return NETDEV_TX_OK;
+out:
+	dev->stats.tx_errors++;
+	return NETDEV_TX_OK;
 }
 
 static netdev_tx_t sit_tunnel_xmit(struct sk_buff *skb,
@@ -929,7 +1023,7 @@ static netdev_tx_t sit_tunnel_xmit(struct sk_buff *skb,
 
 tx_err:
 	dev->stats.tx_errors++;
-	dev_kfree_skb(skb);
+	kfree_skb(skb);
 	return NETDEV_TX_OK;
 
 }
@@ -990,6 +1084,7 @@ static void ipip6_tunnel_update(struct ip_tunnel *t, struct ip_tunnel_parm *p)
 		t->parms.link = p->link;
 		ipip6_tunnel_bind_dev(t->dev);
 	}
+	ip_tunnel_dst_reset_all(t);
 	netdev_state_change(t->dev);
 }
 
@@ -1020,6 +1115,7 @@ 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;
+	ip_tunnel_dst_reset_all(t);
 	netdev_state_change(t->dev);
 	return 0;
 }
@@ -1031,8 +1127,8 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
 	int err = 0;
 	struct ip_tunnel_parm p;
 	struct ip_tunnel_prl prl;
-	struct ip_tunnel *t;
-	struct net *net = dev_net(dev);
+	struct ip_tunnel *t = netdev_priv(dev);
+	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;
@@ -1043,16 +1139,15 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
 #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 (t == NULL)
-			t = netdev_priv(dev);
 
 		err = -EFAULT;
 		if (cmd == SIOCGETTUNNEL) {
@@ -1148,9 +1243,6 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
 		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;
 
@@ -1166,9 +1258,6 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
 		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:
@@ -1179,6 +1268,7 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
 			err = ipip6_tunnel_add_prl(t, &prl, cmd == SIOCCHGPRL);
 			break;
 		}
+		ip_tunnel_dst_reset_all(t);
 		netdev_state_change(dev);
 		break;
 
@@ -1195,8 +1285,6 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
 				   sizeof(ip6rd)))
 			goto done;
 
-		t = netdev_priv(dev);
-
 		if (cmd != SIOCDEL6RD) {
 			err = ipip6_tunnel_update_6rd(t, &ip6rd);
 			if (err < 0)
@@ -1234,10 +1322,19 @@ static const struct net_device_ops ipip6_netdev_ops = {
 
 static void ipip6_dev_free(struct net_device *dev)
 {
+	struct ip_tunnel *tunnel = netdev_priv(dev);
+
+	free_percpu(tunnel->dst_cache);
 	free_percpu(dev->tstats);
 	free_netdev(dev);
 }
 
+#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)
 {
 	dev->netdev_ops		= &ipip6_netdev_ops;
@@ -1251,6 +1348,8 @@ static void ipip6_tunnel_setup(struct net_device *dev)
 	dev->iflink		= 0;
 	dev->addr_len		= 4;
 	dev->features		|= NETIF_F_LLTX;
+	dev->features		|= SIT_FEATURES;
+	dev->hw_features	|= SIT_FEATURES;
 }
 
 static int ipip6_tunnel_init(struct net_device *dev)
@@ -1264,10 +1363,16 @@ static int ipip6_tunnel_init(struct net_device *dev)
 	memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4);
 
 	ipip6_tunnel_bind_dev(dev);
-	dev->tstats = alloc_percpu(struct pcpu_tstats);
+	dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
 	if (!dev->tstats)
 		return -ENOMEM;
 
+	tunnel->dst_cache = alloc_percpu(struct ip_tunnel_dst);
+	if (!tunnel->dst_cache) {
+		free_percpu(dev->tstats);
+		return -ENOMEM;
+	}
+
 	return 0;
 }
 
@@ -1287,9 +1392,16 @@ static int __net_init ipip6_fb_tunnel_init(struct net_device *dev)
 	iph->ihl		= 5;
 	iph->ttl		= 64;
 
-	dev->tstats = alloc_percpu(struct pcpu_tstats);
+	dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
 	if (!dev->tstats)
 		return -ENOMEM;
+
+	tunnel->dst_cache = alloc_percpu(struct ip_tunnel_dst);
+	if (!tunnel->dst_cache) {
+		free_percpu(dev->tstats);
+		return -ENOMEM;
+	}
+
 	dev_hold(dev);
 	rcu_assign_pointer(sitn->tunnels_wc[0], tunnel);
 	return 0;
@@ -1540,6 +1652,15 @@ static const struct nla_policy ipip6_policy[IFLA_IPTUN_MAX + 1] = {
 #endif
 };
 
+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,
@@ -1551,6 +1672,7 @@ 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,
 };
 
 static struct xfrm_tunnel sit_handler __read_mostly = {
@@ -1565,9 +1687,10 @@ 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)
+static void __net_exit sit_destroy_tunnels(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;
 
@@ -1612,6 +1735,7 @@ static int __net_init sit_init_net(struct net *net)
 		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.
 	 */
@@ -1641,12 +1765,10 @@ err_alloc_dev:
 
 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);
+	sit_destroy_tunnels(net, &list);
 	unregister_netdevice_many(&list);
 	rtnl_unlock();
 }
@@ -1706,4 +1828,5 @@ xfrm_tunnel_failed:
 module_init(sit_init);
 module_exit(sit_cleanup);
 MODULE_LICENSE("GPL");
+MODULE_ALIAS_RTNL_LINK("sit");
 MODULE_ALIAS_NETDEV("sit0");