1 files changed, 74 insertions, 59 deletions

diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 74e1d964a615..019f3b0839c5 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -85,9 +85,10 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
 				   __be32 remote, __be32 local,
 				   __be32 key)
 {
-	unsigned int hash;
 	struct ip_tunnel *t, *cand = NULL;
 	struct hlist_head *head;
+	struct net_device *ndev;
+	unsigned int hash;
 
 	hash = ip_tunnel_hash(key, remote);
 	head = &itn->tunnels[hash];
@@ -142,11 +143,8 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
 			cand = t;
 	}
 
-	if (flags & TUNNEL_NO_KEY)
-		goto skip_key_lookup;
-
 	hlist_for_each_entry_rcu(t, head, hash_node) {
-		if (t->parms.i_key != key ||
+		if ((!(flags & TUNNEL_NO_KEY) && t->parms.i_key != key) ||
 		    t->parms.iph.saddr != 0 ||
 		    t->parms.iph.daddr != 0 ||
 		    !(t->dev->flags & IFF_UP))
@@ -158,7 +156,6 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
 			cand = t;
 	}
 
-skip_key_lookup:
 	if (cand)
 		return cand;
 
@@ -166,8 +163,9 @@ skip_key_lookup:
 	if (t && t->dev->flags & IFF_UP)
 		return t;
 
-	if (itn->fb_tunnel_dev && itn->fb_tunnel_dev->flags & IFF_UP)
-		return netdev_priv(itn->fb_tunnel_dev);
+	ndev = READ_ONCE(itn->fb_tunnel_dev);
+	if (ndev && ndev->flags & IFF_UP)
+		return netdev_priv(ndev);
 
 	return NULL;
 }
@@ -244,7 +242,7 @@ static struct net_device *__ip_tunnel_create(struct net *net,
 	if (parms->name[0]) {
 		if (!dev_valid_name(parms->name))
 			goto failed;
-		strlcpy(name, parms->name, IFNAMSIZ);
+		strscpy(name, parms->name, IFNAMSIZ);
 	} else {
 		if (strlen(ops->kind) > (IFNAMSIZ - 3))
 			goto failed;
@@ -296,8 +294,8 @@ static int ip_tunnel_bind_dev(struct net_device *dev)
 
 		ip_tunnel_init_flow(&fl4, iph->protocol, iph->daddr,
 				    iph->saddr, tunnel->parms.o_key,
-				    RT_TOS(iph->tos), tunnel->parms.link,
-				    tunnel->fwmark, 0);
+				    RT_TOS(iph->tos), dev_net(dev),
+				    tunnel->parms.link, tunnel->fwmark, 0, 0);
 		rt = ip_route_output_key(tunnel->net, &fl4);
 
 		if (!IS_ERR(rt)) {
@@ -319,7 +317,7 @@ static int ip_tunnel_bind_dev(struct net_device *dev)
 	}
 
 	dev->needed_headroom = t_hlen + hlen;
-	mtu -= (dev->hard_header_len + t_hlen);
+	mtu -= t_hlen + (dev->type == ARPHRD_ETHER ? dev->hard_header_len : 0);
 
 	if (mtu < IPV4_MIN_MTU)
 		mtu = IPV4_MIN_MTU;
@@ -349,7 +347,10 @@ static struct ip_tunnel *ip_tunnel_create(struct net *net,
 	nt = netdev_priv(dev);
 	t_hlen = nt->hlen + sizeof(struct iphdr);
 	dev->min_mtu = ETH_MIN_MTU;
-	dev->max_mtu = IP_MAX_MTU - dev->hard_header_len - t_hlen;
+	dev->max_mtu = IP_MAX_MTU - t_hlen;
+	if (dev->type == ARPHRD_ETHER)
+		dev->max_mtu -= dev->hard_header_len;
+
 	ip_tunnel_add(itn, nt);
 	return nt;
 
@@ -362,7 +363,6 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
 		  const struct tnl_ptk_info *tpi, struct metadata_dst *tun_dst,
 		  bool log_ecn_error)
 {
-	struct pcpu_sw_netstats *tstats;
 	const struct iphdr *iph = ip_hdr(skb);
 	int err;
 
@@ -390,7 +390,7 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
 		tunnel->i_seqno = ntohl(tpi->seq) + 1;
 	}
 
-	skb_reset_network_header(skb);
+	skb_set_network_header(skb, (tunnel->dev->type == ARPHRD_ETHER) ? ETH_HLEN : 0);
 
 	err = IP_ECN_decapsulate(iph, skb);
 	if (unlikely(err)) {
@@ -404,12 +404,7 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, 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);
-
+	dev_sw_netstats_rx_add(tunnel->dev, skb->len);
 	skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(tunnel->dev)));
 
 	if (tunnel->dev->type == ARPHRD_ETHER) {
@@ -496,13 +491,15 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
 	int mtu;
 
 	tunnel_hlen = md ? tunnel_hlen : tunnel->hlen;
-	pkt_size = skb->len - tunnel_hlen - dev->hard_header_len;
+	pkt_size = skb->len - tunnel_hlen;
+	pkt_size -= dev->type == ARPHRD_ETHER ? dev->hard_header_len : 0;
 
-	if (df)
-		mtu = dst_mtu(&rt->dst) - dev->hard_header_len
-					- sizeof(struct iphdr) - tunnel_hlen;
-	else
+	if (df) {
+		mtu = dst_mtu(&rt->dst) - (sizeof(struct iphdr) + tunnel_hlen);
+		mtu -= dev->type == ARPHRD_ETHER ? dev->hard_header_len : 0;
+	} else {
 		mtu = skb_valid_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu;
+	}
 
 	if (skb_valid_dst(skb))
 		skb_dst_update_pmtu_no_confirm(skb, mtu);
@@ -511,8 +508,7 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
 		if (!skb_is_gso(skb) &&
 		    (inner_iph->frag_off & htons(IP_DF)) &&
 		    mtu < pkt_size) {
-			memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
-			icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
+			icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
 			return -E2BIG;
 		}
 	}
@@ -536,7 +532,7 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
 
 		if (!skb_is_gso(skb) && mtu >= IPV6_MIN_MTU &&
 					mtu < pkt_size) {
-			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+			icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
 			return -E2BIG;
 		}
 	}
@@ -574,7 +570,8 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	}
 	ip_tunnel_init_flow(&fl4, proto, key->u.ipv4.dst, key->u.ipv4.src,
 			    tunnel_id_to_key32(key->tun_id), RT_TOS(tos),
-			    0, skb->mark, skb_get_hash(skb));
+			    dev_net(dev), 0, skb->mark, skb_get_hash(skb),
+			    key->flow_flags);
 	if (tunnel->encap.type != TUNNEL_ENCAP_NONE)
 		goto tx_error;
 
@@ -616,9 +613,6 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 			ttl = ip4_dst_hoplimit(&rt->dst);
 	}
 
-	if (!df && skb->protocol == htons(ETH_P_IP))
-		df = inner_iph->frag_off & htons(IP_DF);
-
 	headroom += LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len;
 	if (headroom > dev->needed_headroom)
 		dev->needed_headroom = headroom;
@@ -648,6 +642,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	const struct iphdr *inner_iph;
 	unsigned int max_headroom;	/* The extra header space needed */
 	struct rtable *rt = NULL;		/* Route to the other host */
+	__be16 payload_protocol;
 	bool use_cache = false;
 	struct flowi4 fl4;
 	bool md = false;
@@ -658,6 +653,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 
 	inner_iph = (const struct iphdr *)skb_inner_network_header(skb);
 	connected = (tunnel->parms.iph.daddr != 0);
+	payload_protocol = skb_protocol(skb, true);
 
 	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
 
@@ -677,13 +673,12 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 			dst = tun_info->key.u.ipv4.dst;
 			md = true;
 			connected = true;
-		}
-		else if (skb->protocol == htons(ETH_P_IP)) {
+		} else if (payload_protocol == htons(ETH_P_IP)) {
 			rt = skb_rtable(skb);
 			dst = rt_nexthop(rt, inner_iph->daddr);
 		}
 #if IS_ENABLED(CONFIG_IPV6)
-		else if (skb->protocol == htons(ETH_P_IPV6)) {
+		else if (payload_protocol == htons(ETH_P_IPV6)) {
 			const struct in6_addr *addr6;
 			struct neighbour *neigh;
 			bool do_tx_error_icmp;
@@ -723,18 +718,19 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	tos = tnl_params->tos;
 	if (tos & 0x1) {
 		tos &= ~0x1;
-		if (skb->protocol == htons(ETH_P_IP)) {
+		if (payload_protocol == htons(ETH_P_IP)) {
 			tos = inner_iph->tos;
 			connected = false;
-		} else if (skb->protocol == htons(ETH_P_IPV6)) {
+		} else if (payload_protocol == htons(ETH_P_IPV6)) {
 			tos = ipv6_get_dsfield((const struct ipv6hdr *)inner_iph);
 			connected = false;
 		}
 	}
 
 	ip_tunnel_init_flow(&fl4, protocol, dst, tnl_params->saddr,
-			    tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link,
-			    tunnel->fwmark, skb_get_hash(skb));
+			    tunnel->parms.o_key, RT_TOS(tos),
+			    dev_net(dev), tunnel->parms.link,
+			    tunnel->fwmark, skb_get_hash(skb), 0);
 
 	if (ip_tunnel_encap(skb, tunnel, &protocol, &fl4) < 0)
 		goto tx_error;
@@ -770,8 +766,11 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 		goto tx_error;
 	}
 
-	if (tnl_update_pmtu(dev, skb, rt, tnl_params->frag_off, inner_iph,
-			    0, 0, false)) {
+	df = tnl_params->frag_off;
+	if (payload_protocol == htons(ETH_P_IP) && !tunnel->ignore_df)
+		df |= (inner_iph->frag_off & htons(IP_DF));
+
+	if (tnl_update_pmtu(dev, skb, rt, df, inner_iph, 0, 0, false)) {
 		ip_rt_put(rt);
 		goto tx_error;
 	}
@@ -789,20 +788,16 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	tos = ip_tunnel_ecn_encap(tos, inner_iph, skb);
 	ttl = tnl_params->ttl;
 	if (ttl == 0) {
-		if (skb->protocol == htons(ETH_P_IP))
+		if (payload_protocol == htons(ETH_P_IP))
 			ttl = inner_iph->ttl;
 #if IS_ENABLED(CONFIG_IPV6)
-		else if (skb->protocol == htons(ETH_P_IPV6))
+		else if (payload_protocol == htons(ETH_P_IPV6))
 			ttl = ((const struct ipv6hdr *)inner_iph)->hop_limit;
 #endif
 		else
 			ttl = ip4_dst_hoplimit(&rt->dst);
 	}
 
-	df = tnl_params->frag_off;
-	if (skb->protocol == htons(ETH_P_IP) && !tunnel->ignore_df)
-		df |= (inner_iph->frag_off&htons(IP_DF));
-
 	max_headroom = LL_RESERVED_SPACE(rt->dst.dev) + sizeof(struct iphdr)
 			+ rt->dst.header_len + ip_encap_hlen(&tunnel->encap);
 	if (max_headroom > dev->needed_headroom)
@@ -842,7 +837,7 @@ static void ip_tunnel_update(struct ip_tunnel_net *itn,
 	t->parms.i_key = p->i_key;
 	t->parms.o_key = p->o_key;
 	if (dev->type != ARPHRD_ETHER) {
-		memcpy(dev->dev_addr, &p->iph.saddr, 4);
+		__dev_addr_set(dev, &p->iph.saddr, 4);
 		memcpy(dev->broadcast, &p->iph.daddr, 4);
 	}
 	ip_tunnel_add(itn, t);
@@ -864,7 +859,7 @@ static void ip_tunnel_update(struct ip_tunnel_net *itn,
 	netdev_state_change(dev);
 }
 
-int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd)
+int ip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd)
 {
 	int err = 0;
 	struct ip_tunnel *t = netdev_priv(dev);
@@ -964,13 +959,31 @@ int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd)
 done:
 	return err;
 }
-EXPORT_SYMBOL_GPL(ip_tunnel_ioctl);
+EXPORT_SYMBOL_GPL(ip_tunnel_ctl);
+
+int ip_tunnel_siocdevprivate(struct net_device *dev, struct ifreq *ifr,
+			     void __user *data, int cmd)
+{
+	struct ip_tunnel_parm p;
+	int err;
+
+	if (copy_from_user(&p, data, sizeof(p)))
+		return -EFAULT;
+	err = dev->netdev_ops->ndo_tunnel_ctl(dev, &p, cmd);
+	if (!err && copy_to_user(data, &p, sizeof(p)))
+		return -EFAULT;
+	return err;
+}
+EXPORT_SYMBOL_GPL(ip_tunnel_siocdevprivate);
 
 int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	int t_hlen = tunnel->hlen + sizeof(struct iphdr);
-	int max_mtu = IP_MAX_MTU - dev->hard_header_len - t_hlen;
+	int max_mtu = IP_MAX_MTU - t_hlen;
+
+	if (dev->type == ARPHRD_ETHER)
+		max_mtu -= dev->hard_header_len;
 
 	if (new_mtu < ETH_MIN_MTU)
 		return -EINVAL;
@@ -1054,7 +1067,7 @@ int ip_tunnel_init_net(struct net *net, unsigned int ip_tnl_net_id,
 
 	memset(&parms, 0, sizeof(parms));
 	if (devname)
-		strlcpy(parms.name, devname, IFNAMSIZ);
+		strscpy(parms.name, devname, IFNAMSIZ);
 
 	rtnl_lock();
 	itn->fb_tunnel_dev = __ip_tunnel_create(net, ops, &parms);
@@ -1147,10 +1160,12 @@ int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[],
 
 	mtu = ip_tunnel_bind_dev(dev);
 	if (tb[IFLA_MTU]) {
-		unsigned int max = IP_MAX_MTU - dev->hard_header_len - nt->hlen;
+		unsigned int max = IP_MAX_MTU - (nt->hlen + sizeof(struct iphdr));
+
+		if (dev->type == ARPHRD_ETHER)
+			max -= dev->hard_header_len;
 
-		mtu = clamp(dev->mtu, (unsigned int)ETH_MIN_MTU,
-			    (unsigned int)(max - sizeof(struct iphdr)));
+		mtu = clamp(dev->mtu, (unsigned int)ETH_MIN_MTU, max);
 	}
 
 	err = dev_set_mtu(dev, mtu);
@@ -1249,9 +1264,9 @@ void ip_tunnel_uninit(struct net_device *dev)
 	struct ip_tunnel_net *itn;
 
 	itn = net_generic(net, tunnel->ip_tnl_net_id);
-	/* fb_tunnel_dev will be unregisted in net-exit call. */
-	if (itn->fb_tunnel_dev != dev)
-		ip_tunnel_del(itn, netdev_priv(dev));
+	ip_tunnel_del(itn, netdev_priv(dev));
+	if (itn->fb_tunnel_dev == dev)
+		WRITE_ONCE(itn->fb_tunnel_dev, NULL);
 
 	dst_cache_reset(&tunnel->dst_cache);
 }