X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=net%2Fipv4%2Fip_gre.c;h=f36ce156cac6561da03d032e4f445f772d40b375;hb=c2f6118a3009b3606cc6e77b474a46ce4075b0a2;hp=44ed9487fa15d15833c1610999a2665fb77f00ba;hpb=e1a8000228e16212c93b23cfbed4d622e2ec7a6b;p=safe%2Fjmp%2Flinux-2.6

diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 44ed948..f36ce15 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -66,10 +66,7 @@
    solution, but it supposes maintaing new variable in ALL
    skb, even if no tunneling is used.
 
-   Current solution: t->recursion lock breaks dead loops. It looks
-   like dev->tbusy flag, but I preferred new variable, because
-   the semantics is different. One day, when hard_start_xmit
-   will be multithreaded we will have to use skb->encapsulation.
+   Current solution: HARD_TX_LOCK lock breaks dead loops.
 
 
 
@@ -126,11 +123,9 @@ static int ipgre_tunnel_bind_dev(struct net_device *dev);
 
 /* Fallback tunnel: no source, no destination, no key, no options */
 
-static int ipgre_fb_tunnel_init(struct net_device *dev);
-
 #define HASH_SIZE  16
 
-static int ipgre_net_id;
+static int ipgre_net_id __read_mostly;
 struct ipgre_net {
 	struct ip_tunnel *tunnels[4][HASH_SIZE];
 
@@ -161,72 +156,135 @@ struct ipgre_net {
 #define tunnels_r	tunnels[2]
 #define tunnels_l	tunnels[1]
 #define tunnels_wc	tunnels[0]
+/*
+ * Locking : hash tables are protected by RCU and a spinlock
+ */
+static DEFINE_SPINLOCK(ipgre_lock);
 
-static DEFINE_RWLOCK(ipgre_lock);
+#define for_each_ip_tunnel_rcu(start) \
+	for (t = rcu_dereference(start); t; t = rcu_dereference(t->next))
 
 /* Given src, dst and key, find appropriate for input tunnel. */
 
-static struct ip_tunnel * ipgre_tunnel_lookup(struct net *net,
+static struct ip_tunnel * ipgre_tunnel_lookup(struct net_device *dev,
 					      __be32 remote, __be32 local,
 					      __be32 key, __be16 gre_proto)
 {
+	struct net *net = dev_net(dev);
+	int link = dev->ifindex;
 	unsigned h0 = HASH(remote);
 	unsigned h1 = HASH(key);
-	struct ip_tunnel *t;
-	struct ip_tunnel *t2 = NULL;
+	struct ip_tunnel *t, *cand = NULL;
 	struct ipgre_net *ign = net_generic(net, ipgre_net_id);
 	int dev_type = (gre_proto == htons(ETH_P_TEB)) ?
 		       ARPHRD_ETHER : ARPHRD_IPGRE;
-
-	for (t = ign->tunnels_r_l[h0^h1]; t; t = t->next) {
-		if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr) {
-			if (t->parms.i_key == key && t->dev->flags & IFF_UP) {
-				if (t->dev->type == dev_type)
-					return t;
-				if (t->dev->type == ARPHRD_IPGRE && !t2)
-					t2 = t;
-			}
+	int score, cand_score = 4;
+
+	for_each_ip_tunnel_rcu(ign->tunnels_r_l[h0 ^ h1]) {
+		if (local != t->parms.iph.saddr ||
+		    remote != t->parms.iph.daddr ||
+		    key != t->parms.i_key ||
+		    !(t->dev->flags & IFF_UP))
+			continue;
+
+		if (t->dev->type != ARPHRD_IPGRE &&
+		    t->dev->type != dev_type)
+			continue;
+
+		score = 0;
+		if (t->parms.link != link)
+			score |= 1;
+		if (t->dev->type != dev_type)
+			score |= 2;
+		if (score == 0)
+			return t;
+
+		if (score < cand_score) {
+			cand = t;
+			cand_score = score;
 		}
 	}
 
-	for (t = ign->tunnels_r[h0^h1]; t; t = t->next) {
-		if (remote == t->parms.iph.daddr) {
-			if (t->parms.i_key == key && t->dev->flags & IFF_UP) {
-				if (t->dev->type == dev_type)
-					return t;
-				if (t->dev->type == ARPHRD_IPGRE && !t2)
-					t2 = t;
-			}
+	for_each_ip_tunnel_rcu(ign->tunnels_r[h0 ^ h1]) {
+		if (remote != t->parms.iph.daddr ||
+		    key != t->parms.i_key ||
+		    !(t->dev->flags & IFF_UP))
+			continue;
+
+		if (t->dev->type != ARPHRD_IPGRE &&
+		    t->dev->type != dev_type)
+			continue;
+
+		score = 0;
+		if (t->parms.link != link)
+			score |= 1;
+		if (t->dev->type != dev_type)
+			score |= 2;
+		if (score == 0)
+			return t;
+
+		if (score < cand_score) {
+			cand = t;
+			cand_score = score;
 		}
 	}
 
-	for (t = ign->tunnels_l[h1]; t; t = t->next) {
-		if (local == t->parms.iph.saddr ||
-		     (local == t->parms.iph.daddr &&
-		      ipv4_is_multicast(local))) {
-			if (t->parms.i_key == key && t->dev->flags & IFF_UP) {
-				if (t->dev->type == dev_type)
-					return t;
-				if (t->dev->type == ARPHRD_IPGRE && !t2)
-					t2 = t;
-			}
+	for_each_ip_tunnel_rcu(ign->tunnels_l[h1]) {
+		if ((local != t->parms.iph.saddr &&
+		     (local != t->parms.iph.daddr ||
+		      !ipv4_is_multicast(local))) ||
+		    key != t->parms.i_key ||
+		    !(t->dev->flags & IFF_UP))
+			continue;
+
+		if (t->dev->type != ARPHRD_IPGRE &&
+		    t->dev->type != dev_type)
+			continue;
+
+		score = 0;
+		if (t->parms.link != link)
+			score |= 1;
+		if (t->dev->type != dev_type)
+			score |= 2;
+		if (score == 0)
+			return t;
+
+		if (score < cand_score) {
+			cand = t;
+			cand_score = score;
 		}
 	}
 
-	for (t = ign->tunnels_wc[h1]; t; t = t->next) {
-		if (t->parms.i_key == key && t->dev->flags & IFF_UP) {
-			if (t->dev->type == dev_type)
-				return t;
-			if (t->dev->type == ARPHRD_IPGRE && !t2)
-				t2 = t;
+	for_each_ip_tunnel_rcu(ign->tunnels_wc[h1]) {
+		if (t->parms.i_key != key ||
+		    !(t->dev->flags & IFF_UP))
+			continue;
+
+		if (t->dev->type != ARPHRD_IPGRE &&
+		    t->dev->type != dev_type)
+			continue;
+
+		score = 0;
+		if (t->parms.link != link)
+			score |= 1;
+		if (t->dev->type != dev_type)
+			score |= 2;
+		if (score == 0)
+			return t;
+
+		if (score < cand_score) {
+			cand = t;
+			cand_score = score;
 		}
 	}
 
-	if (t2)
-		return t2;
+	if (cand != NULL)
+		return cand;
+
+	dev = ign->fb_tunnel_dev;
+	if (dev->flags & IFF_UP)
+		return netdev_priv(dev);
 
-	if (ign->fb_tunnel_dev->flags&IFF_UP)
-		return netdev_priv(ign->fb_tunnel_dev);
 	return NULL;
 }
 
@@ -259,10 +317,10 @@ static void ipgre_tunnel_link(struct ipgre_net *ign, struct ip_tunnel *t)
 {
 	struct ip_tunnel **tp = ipgre_bucket(ign, t);
 
+	spin_lock_bh(&ipgre_lock);
 	t->next = *tp;
-	write_lock_bh(&ipgre_lock);
-	*tp = t;
-	write_unlock_bh(&ipgre_lock);
+	rcu_assign_pointer(*tp, t);
+	spin_unlock_bh(&ipgre_lock);
 }
 
 static void ipgre_tunnel_unlink(struct ipgre_net *ign, struct ip_tunnel *t)
@@ -271,9 +329,9 @@ static void ipgre_tunnel_unlink(struct ipgre_net *ign, struct ip_tunnel *t)
 
 	for (tp = ipgre_bucket(ign, t); *tp; tp = &(*tp)->next) {
 		if (t == *tp) {
-			write_lock_bh(&ipgre_lock);
+			spin_lock_bh(&ipgre_lock);
 			*tp = t->next;
-			write_unlock_bh(&ipgre_lock);
+			spin_unlock_bh(&ipgre_lock);
 			break;
 		}
 	}
@@ -286,6 +344,7 @@ static struct ip_tunnel *ipgre_tunnel_find(struct net *net,
 	__be32 remote = parms->iph.daddr;
 	__be32 local = parms->iph.saddr;
 	__be32 key = parms->i_key;
+	int link = parms->link;
 	struct ip_tunnel *t, **tp;
 	struct ipgre_net *ign = net_generic(net, ipgre_net_id);
 
@@ -293,6 +352,7 @@ static struct ip_tunnel *ipgre_tunnel_find(struct net *net,
 		if (local == t->parms.iph.saddr &&
 		    remote == t->parms.iph.daddr &&
 		    key == t->parms.i_key &&
+		    link == t->parms.link &&
 		    type == t->dev->type)
 			break;
 
@@ -371,7 +431,7 @@ static void ipgre_err(struct sk_buff *skb, u32 info)
    by themself???
  */
 
-	struct iphdr *iph = (struct iphdr*)skb->data;
+	struct iphdr *iph = (struct iphdr *)skb->data;
 	__be16	     *p = (__be16*)(skb->data+(iph->ihl<<2));
 	int grehlen = (iph->ihl<<2) + 4;
 	const int type = icmp_hdr(skb)->type;
@@ -422,8 +482,8 @@ static void ipgre_err(struct sk_buff *skb, u32 info)
 		break;
 	}
 
-	read_lock(&ipgre_lock);
-	t = ipgre_tunnel_lookup(dev_net(skb->dev), iph->daddr, iph->saddr,
+	rcu_read_lock();
+	t = ipgre_tunnel_lookup(skb->dev, iph->daddr, iph->saddr,
 				flags & GRE_KEY ?
 				*(((__be32 *)p) + (grehlen / 4) - 1) : 0,
 				p[1]);
@@ -434,13 +494,13 @@ static void ipgre_err(struct sk_buff *skb, u32 info)
 	if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED)
 		goto out;
 
-	if (jiffies - t->err_time < IPTUNNEL_ERR_TIMEO)
+	if (time_before(jiffies, t->err_time + IPTUNNEL_ERR_TIMEO))
 		t->err_count++;
 	else
 		t->err_count = 1;
 	t->err_time = jiffies;
 out:
-	read_unlock(&ipgre_lock);
+	rcu_read_unlock();
 	return;
 }
 
@@ -477,6 +537,7 @@ static int ipgre_rcv(struct sk_buff *skb)
 	struct ip_tunnel *tunnel;
 	int    offset = 4;
 	__be16 gre_proto;
+	unsigned int len;
 
 	if (!pskb_may_pull(skb, 16))
 		goto drop_nolock;
@@ -518,8 +579,8 @@ static int ipgre_rcv(struct sk_buff *skb)
 
 	gre_proto = *(__be16 *)(h + 2);
 
-	read_lock(&ipgre_lock);
-	if ((tunnel = ipgre_tunnel_lookup(dev_net(skb->dev),
+	rcu_read_lock();
+	if ((tunnel = ipgre_tunnel_lookup(skb->dev,
 					  iph->saddr, iph->daddr, key,
 					  gre_proto))) {
 		struct net_device_stats *stats = &tunnel->dev->stats;
@@ -544,7 +605,7 @@ static int ipgre_rcv(struct sk_buff *skb)
 #ifdef CONFIG_NET_IPGRE_BROADCAST
 		if (ipv4_is_multicast(iph->daddr)) {
 			/* Looped back packet, drop it! */
-			if (skb->rtable->fl.iif == 0)
+			if (skb_rtable(skb)->fl.iif == 0)
 				goto drop;
 			stats->multicast++;
 			skb->pkt_type = PACKET_BROADCAST;
@@ -567,6 +628,8 @@ static int ipgre_rcv(struct sk_buff *skb)
 			tunnel->i_seqno = seqno + 1;
 		}
 
+		len = skb->len;
+
 		/* Warning: All skb pointers will be invalidated! */
 		if (tunnel->dev->type == ARPHRD_ETHER) {
 			if (!pskb_may_pull(skb, ETH_HLEN)) {
@@ -581,32 +644,32 @@ static int ipgre_rcv(struct sk_buff *skb)
 		}
 
 		stats->rx_packets++;
-		stats->rx_bytes += skb->len;
+		stats->rx_bytes += len;
 		skb->dev = tunnel->dev;
-		dst_release(skb->dst);
-		skb->dst = NULL;
+		skb_dst_drop(skb);
 		nf_reset(skb);
 
 		skb_reset_network_header(skb);
 		ipgre_ecn_decapsulate(iph, skb);
 
 		netif_rx(skb);
-		read_unlock(&ipgre_lock);
+		rcu_read_unlock();
 		return(0);
 	}
 	icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
 
 drop:
-	read_unlock(&ipgre_lock);
+	rcu_read_unlock();
 drop_nolock:
 	kfree_skb(skb);
 	return(0);
 }
 
-static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
-	struct net_device_stats *stats = &tunnel->dev->stats;
+	struct net_device_stats *stats = &dev->stats;
+	struct netdev_queue *txq = netdev_get_tx_queue(dev, 0);
 	struct iphdr  *old_iph = ip_hdr(skb);
 	struct iphdr  *tiph;
 	u8     tos;
@@ -619,17 +682,12 @@ static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 	__be32 dst;
 	int    mtu;
 
-	if (tunnel->recursion++) {
-		stats->collisions++;
-		goto tx_error;
-	}
-
 	if (dev->type == ARPHRD_ETHER)
 		IPCB(skb)->flags = 0;
 
 	if (dev->header_ops && dev->type == ARPHRD_IPGRE) {
 		gre_hlen = 0;
-		tiph = (struct iphdr*)skb->data;
+		tiph = (struct iphdr *)skb->data;
 	} else {
 		gre_hlen = tunnel->hlen;
 		tiph = &tunnel->parms.iph;
@@ -638,13 +696,13 @@ static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 	if ((dst = tiph->daddr) == 0) {
 		/* NBMA tunnel */
 
-		if (skb->dst == NULL) {
+		if (skb_dst(skb) == NULL) {
 			stats->tx_fifo_errors++;
 			goto tx_error;
 		}
 
 		if (skb->protocol == htons(ETH_P_IP)) {
-			rt = skb->rtable;
+			rt = skb_rtable(skb);
 			if ((dst = rt->rt_gateway) == 0)
 				goto tx_error_icmp;
 		}
@@ -652,12 +710,12 @@ static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 		else if (skb->protocol == htons(ETH_P_IPV6)) {
 			struct in6_addr *addr6;
 			int addr_type;
-			struct neighbour *neigh = skb->dst->neighbour;
+			struct neighbour *neigh = skb_dst(skb)->neighbour;
 
 			if (neigh == NULL)
 				goto tx_error;
 
-			addr6 = (struct in6_addr*)&neigh->primary_key;
+			addr6 = (struct in6_addr *)&neigh->primary_key;
 			addr_type = ipv6_addr_type(addr6);
 
 			if (addr_type == IPV6_ADDR_ANY) {
@@ -676,10 +734,10 @@ static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	tos = tiph->tos;
-	if (tos&1) {
+	if (tos == 1) {
+		tos = 0;
 		if (skb->protocol == htons(ETH_P_IP))
 			tos = old_iph->tos;
-		tos &= ~1;
 	}
 
 	{
@@ -706,10 +764,10 @@ static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (df)
 		mtu = dst_mtu(&rt->u.dst) - dev->hard_header_len - tunnel->hlen;
 	else
-		mtu = skb->dst ? dst_mtu(skb->dst) : dev->mtu;
+		mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu;
 
-	if (skb->dst)
-		skb->dst->ops->update_pmtu(skb->dst, mtu);
+	if (skb_dst(skb))
+		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu);
 
 	if (skb->protocol == htons(ETH_P_IP)) {
 		df |= (old_iph->frag_off&htons(IP_DF));
@@ -723,14 +781,14 @@ static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 #ifdef CONFIG_IPV6
 	else if (skb->protocol == htons(ETH_P_IPV6)) {
-		struct rt6_info *rt6 = (struct rt6_info*)skb->dst;
+		struct rt6_info *rt6 = (struct rt6_info *)skb_dst(skb);
 
-		if (rt6 && mtu < dst_mtu(skb->dst) && mtu >= IPV6_MIN_MTU) {
+		if (rt6 && mtu < dst_mtu(skb_dst(skb)) && mtu >= IPV6_MIN_MTU) {
 			if ((tunnel->parms.iph.daddr &&
 			     !ipv4_is_multicast(tunnel->parms.iph.daddr)) ||
 			    rt6->rt6i_dst.plen == 128) {
 				rt6->rt6i_flags |= RTF_MODIFIED;
-				skb->dst->metrics[RTAX_MTU-1] = mtu;
+				skb_dst(skb)->metrics[RTAX_MTU-1] = mtu;
 			}
 		}
 
@@ -743,7 +801,8 @@ static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 #endif
 
 	if (tunnel->err_count > 0) {
-		if (jiffies - tunnel->err_time < IPTUNNEL_ERR_TIMEO) {
+		if (time_before(jiffies,
+				tunnel->err_time + IPTUNNEL_ERR_TIMEO)) {
 			tunnel->err_count--;
 
 			dst_link_failure(skb);
@@ -758,10 +817,9 @@ static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 		struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom);
 		if (!new_skb) {
 			ip_rt_put(rt);
-			stats->tx_dropped++;
+			txq->tx_dropped++;
 			dev_kfree_skb(skb);
-			tunnel->recursion--;
-			return 0;
+			return NETDEV_TX_OK;
 		}
 		if (skb->sk)
 			skb_set_owner_w(new_skb, skb->sk);
@@ -770,14 +828,14 @@ static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 		old_iph = ip_hdr(skb);
 	}
 
-	skb->transport_header = skb->network_header;
+	skb_reset_transport_header(skb);
 	skb_push(skb, gre_hlen);
 	skb_reset_network_header(skb);
 	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
 	IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED |
 			      IPSKB_REROUTED);
-	dst_release(skb->dst);
-	skb->dst = &rt->u.dst;
+	skb_dst_drop(skb);
+	skb_dst_set(skb, &rt->u.dst);
 
 	/*
 	 *	Push down and install the IPIP header.
@@ -797,7 +855,7 @@ static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 			iph->ttl = old_iph->ttl;
 #ifdef CONFIG_IPV6
 		else if (skb->protocol == htons(ETH_P_IPV6))
-			iph->ttl = ((struct ipv6hdr*)old_iph)->hop_limit;
+			iph->ttl = ((struct ipv6hdr *)old_iph)->hop_limit;
 #endif
 		else
 			iph->ttl = dst_metric(&rt->u.dst, RTAX_HOPLIMIT);
@@ -828,8 +886,7 @@ static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 	nf_reset(skb);
 
 	IPTUNNEL_XMIT();
-	tunnel->recursion--;
-	return 0;
+	return NETDEV_TX_OK;
 
 tx_error_icmp:
 	dst_link_failure(skb);
@@ -837,8 +894,7 @@ tx_error_icmp:
 tx_error:
 	stats->tx_errors++;
 	dev_kfree_skb(skb);
-	tunnel->recursion--;
-	return 0;
+	return NETDEV_TX_OK;
 }
 
 static int ipgre_tunnel_bind_dev(struct net_device *dev)
@@ -891,7 +947,7 @@ static int ipgre_tunnel_bind_dev(struct net_device *dev)
 			addend += 4;
 	}
 	dev->needed_headroom = addend + hlen;
-	mtu -= dev->hard_header_len - addend;
+	mtu -= dev->hard_header_len + addend;
 
 	if (mtu < 68)
 		mtu = 68;
@@ -959,7 +1015,7 @@ ipgre_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
 					break;
 				}
 			} else {
-				unsigned nflags=0;
+				unsigned nflags = 0;
 
 				t = netdev_priv(dev);
 
@@ -1101,7 +1157,7 @@ static int ipgre_header(struct sk_buff *skb, struct net_device *dev,
 
 static int ipgre_header_parse(const struct sk_buff *skb, unsigned char *haddr)
 {
-	struct iphdr *iph = (struct iphdr*) skb_mac_header(skb);
+	struct iphdr *iph = (struct iphdr *) skb_mac_header(skb);
 	memcpy(haddr, &iph->saddr, 4);
 	return 4;
 }
@@ -1139,6 +1195,7 @@ static int ipgre_open(struct net_device *dev)
 static int ipgre_close(struct net_device *dev)
 {
 	struct ip_tunnel *t = netdev_priv(dev);
+
 	if (ipv4_is_multicast(t->parms.iph.daddr) && t->mlink) {
 		struct in_device *in_dev;
 		in_dev = inetdev_by_index(dev_net(dev), t->mlink);
@@ -1152,14 +1209,22 @@ static int ipgre_close(struct net_device *dev)
 
 #endif
 
+static const struct net_device_ops ipgre_netdev_ops = {
+	.ndo_init		= ipgre_tunnel_init,
+	.ndo_uninit		= ipgre_tunnel_uninit,
+#ifdef CONFIG_NET_IPGRE_BROADCAST
+	.ndo_open		= ipgre_open,
+	.ndo_stop		= ipgre_close,
+#endif
+	.ndo_start_xmit		= ipgre_tunnel_xmit,
+	.ndo_do_ioctl		= ipgre_tunnel_ioctl,
+	.ndo_change_mtu		= ipgre_tunnel_change_mtu,
+};
+
 static void ipgre_tunnel_setup(struct net_device *dev)
 {
-	dev->init		= ipgre_tunnel_init;
-	dev->uninit		= ipgre_tunnel_uninit;
+	dev->netdev_ops		= &ipgre_netdev_ops;
 	dev->destructor 	= free_netdev;
-	dev->hard_start_xmit	= ipgre_tunnel_xmit;
-	dev->do_ioctl		= ipgre_tunnel_ioctl;
-	dev->change_mtu		= ipgre_tunnel_change_mtu;
 
 	dev->type		= ARPHRD_IPGRE;
 	dev->needed_headroom 	= LL_MAX_HEADER + sizeof(struct iphdr) + 4;
@@ -1168,6 +1233,7 @@ static void ipgre_tunnel_setup(struct net_device *dev)
 	dev->iflink		= 0;
 	dev->addr_len		= 4;
 	dev->features		|= NETIF_F_NETNS_LOCAL;
+	dev->priv_flags		&= ~IFF_XMIT_DST_RELEASE;
 }
 
 static int ipgre_tunnel_init(struct net_device *dev)
@@ -1191,8 +1257,6 @@ static int ipgre_tunnel_init(struct net_device *dev)
 				return -EINVAL;
 			dev->flags = IFF_BROADCAST;
 			dev->header_ops = &ipgre_header_ops;
-			dev->open = ipgre_open;
-			dev->stop = ipgre_close;
 		}
 #endif
 	} else
@@ -1201,7 +1265,7 @@ static int ipgre_tunnel_init(struct net_device *dev)
 	return 0;
 }
 
-static int ipgre_fb_tunnel_init(struct net_device *dev)
+static void ipgre_fb_tunnel_init(struct net_device *dev)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	struct iphdr *iph = &tunnel->parms.iph;
@@ -1217,43 +1281,36 @@ static int ipgre_fb_tunnel_init(struct net_device *dev)
 
 	dev_hold(dev);
 	ign->tunnels_wc[0]	= tunnel;
-	return 0;
 }
 
 
-static struct net_protocol ipgre_protocol = {
+static const struct net_protocol ipgre_protocol = {
 	.handler	=	ipgre_rcv,
 	.err_handler	=	ipgre_err,
 	.netns_ok	=	1,
 };
 
-static void ipgre_destroy_tunnels(struct ipgre_net *ign)
+static void ipgre_destroy_tunnels(struct ipgre_net *ign, struct list_head *head)
 {
 	int prio;
 
 	for (prio = 0; prio < 4; prio++) {
 		int h;
 		for (h = 0; h < HASH_SIZE; h++) {
-			struct ip_tunnel *t;
-			while ((t = ign->tunnels[prio][h]) != NULL)
-				unregister_netdevice(t->dev);
+			struct ip_tunnel *t = ign->tunnels[prio][h];
+
+			while (t != NULL) {
+				unregister_netdevice_queue(t->dev, head);
+				t = t->next;
+			}
 		}
 	}
 }
 
 static int ipgre_init_net(struct net *net)
 {
+	struct ipgre_net *ign = net_generic(net, ipgre_net_id);
 	int err;
-	struct ipgre_net *ign;
-
-	err = -ENOMEM;
-	ign = kzalloc(sizeof(struct ipgre_net), GFP_KERNEL);
-	if (ign == NULL)
-		goto err_alloc;
-
-	err = net_assign_generic(net, ipgre_net_id, ign);
-	if (err < 0)
-		goto err_assign;
 
 	ign->fb_tunnel_dev = alloc_netdev(sizeof(struct ip_tunnel), "gre0",
 					   ipgre_tunnel_setup);
@@ -1261,9 +1318,9 @@ static int ipgre_init_net(struct net *net)
 		err = -ENOMEM;
 		goto err_alloc_dev;
 	}
-
-	ign->fb_tunnel_dev->init = ipgre_fb_tunnel_init;
 	dev_net_set(ign->fb_tunnel_dev, net);
+
+	ipgre_fb_tunnel_init(ign->fb_tunnel_dev);
 	ign->fb_tunnel_dev->rtnl_link_ops = &ipgre_link_ops;
 
 	if ((err = register_netdev(ign->fb_tunnel_dev)))
@@ -1274,27 +1331,26 @@ static int ipgre_init_net(struct net *net)
 err_reg_dev:
 	free_netdev(ign->fb_tunnel_dev);
 err_alloc_dev:
-	/* nothing */
-err_assign:
-	kfree(ign);
-err_alloc:
 	return err;
 }
 
 static void ipgre_exit_net(struct net *net)
 {
 	struct ipgre_net *ign;
+	LIST_HEAD(list);
 
 	ign = net_generic(net, ipgre_net_id);
 	rtnl_lock();
-	ipgre_destroy_tunnels(ign);
+	ipgre_destroy_tunnels(ign, &list);
+	unregister_netdevice_many(&list);
 	rtnl_unlock();
-	kfree(ign);
 }
 
 static struct pernet_operations ipgre_net_ops = {
 	.init = ipgre_init_net,
 	.exit = ipgre_exit_net,
+	.id   = &ipgre_net_id,
+	.size = sizeof(struct ipgre_net),
 };
 
 static int ipgre_tunnel_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -1342,7 +1398,7 @@ out:
 static void ipgre_netlink_parms(struct nlattr *data[],
 				struct ip_tunnel_parm *parms)
 {
-	memset(parms, 0, sizeof(parms));
+	memset(parms, 0, sizeof(*parms));
 
 	parms->iph.protocol = IPPROTO_GRE;
 
@@ -1365,10 +1421,10 @@ static void ipgre_netlink_parms(struct nlattr *data[],
 		parms->o_key = nla_get_be32(data[IFLA_GRE_OKEY]);
 
 	if (data[IFLA_GRE_LOCAL])
-		memcpy(&parms->iph.saddr, nla_data(data[IFLA_GRE_LOCAL]), 4);
+		parms->iph.saddr = nla_get_be32(data[IFLA_GRE_LOCAL]);
 
 	if (data[IFLA_GRE_REMOTE])
-		memcpy(&parms->iph.daddr, nla_data(data[IFLA_GRE_REMOTE]), 4);
+		parms->iph.daddr = nla_get_be32(data[IFLA_GRE_REMOTE]);
 
 	if (data[IFLA_GRE_TTL])
 		parms->iph.ttl = nla_get_u8(data[IFLA_GRE_TTL]);
@@ -1394,22 +1450,28 @@ static int ipgre_tap_init(struct net_device *dev)
 	return 0;
 }
 
+static const struct net_device_ops ipgre_tap_netdev_ops = {
+	.ndo_init		= ipgre_tap_init,
+	.ndo_uninit		= ipgre_tunnel_uninit,
+	.ndo_start_xmit		= ipgre_tunnel_xmit,
+	.ndo_set_mac_address 	= eth_mac_addr,
+	.ndo_validate_addr	= eth_validate_addr,
+	.ndo_change_mtu		= ipgre_tunnel_change_mtu,
+};
+
 static void ipgre_tap_setup(struct net_device *dev)
 {
 
 	ether_setup(dev);
 
-	dev->init		= ipgre_tap_init;
-	dev->uninit		= ipgre_tunnel_uninit;
+	dev->netdev_ops		= &ipgre_tap_netdev_ops;
 	dev->destructor 	= free_netdev;
-	dev->hard_start_xmit	= ipgre_tunnel_xmit;
-	dev->change_mtu		= ipgre_tunnel_change_mtu;
 
 	dev->iflink		= 0;
 	dev->features		|= NETIF_F_NETNS_LOCAL;
 }
 
-static int ipgre_newlink(struct net_device *dev, struct nlattr *tb[],
+static int ipgre_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[],
 			 struct nlattr *data[])
 {
 	struct ip_tunnel *nt;
@@ -1463,25 +1525,29 @@ static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[],
 		if (t->dev != dev)
 			return -EEXIST;
 	} else {
-		unsigned nflags = 0;
-
 		t = nt;
 
-		if (ipv4_is_multicast(p.iph.daddr))
-			nflags = IFF_BROADCAST;
-		else if (p.iph.daddr)
-			nflags = IFF_POINTOPOINT;
+		if (dev->type != ARPHRD_ETHER) {
+			unsigned nflags = 0;
 
-		if ((dev->flags ^ nflags) &
-		    (IFF_POINTOPOINT | IFF_BROADCAST))
-			return -EINVAL;
+			if (ipv4_is_multicast(p.iph.daddr))
+				nflags = IFF_BROADCAST;
+			else if (p.iph.daddr)
+				nflags = IFF_POINTOPOINT;
+
+			if ((dev->flags ^ nflags) &
+			    (IFF_POINTOPOINT | IFF_BROADCAST))
+				return -EINVAL;
+		}
 
 		ipgre_tunnel_unlink(ign, t);
 		t->parms.iph.saddr = p.iph.saddr;
 		t->parms.iph.daddr = p.iph.daddr;
 		t->parms.i_key = p.i_key;
-		memcpy(dev->dev_addr, &p.iph.saddr, 4);
-		memcpy(dev->broadcast, &p.iph.daddr, 4);
+		if (dev->type != ARPHRD_ETHER) {
+			memcpy(dev->dev_addr, &p.iph.saddr, 4);
+			memcpy(dev->broadcast, &p.iph.daddr, 4);
+		}
 		ipgre_tunnel_link(ign, t);
 		netdev_state_change(dev);
 	}
@@ -1536,10 +1602,10 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	NLA_PUT_U32(skb, IFLA_GRE_LINK, p->link);
 	NLA_PUT_BE16(skb, IFLA_GRE_IFLAGS, p->i_flags);
 	NLA_PUT_BE16(skb, IFLA_GRE_OFLAGS, p->o_flags);
-	NLA_PUT_BE32(skb, IFLA_GRE_IFLAGS, p->i_flags);
-	NLA_PUT_BE32(skb, IFLA_GRE_OFLAGS, p->o_flags);
-	NLA_PUT(skb, IFLA_GRE_LOCAL, 4, &p->iph.saddr);
-	NLA_PUT(skb, IFLA_GRE_REMOTE, 4, &p->iph.daddr);
+	NLA_PUT_BE32(skb, IFLA_GRE_IKEY, p->i_key);
+	NLA_PUT_BE32(skb, IFLA_GRE_OKEY, p->o_key);
+	NLA_PUT_BE32(skb, IFLA_GRE_LOCAL, p->iph.saddr);
+	NLA_PUT_BE32(skb, IFLA_GRE_REMOTE, p->iph.daddr);
 	NLA_PUT_U8(skb, IFLA_GRE_TTL, p->iph.ttl);
 	NLA_PUT_U8(skb, IFLA_GRE_TOS, p->iph.tos);
 	NLA_PUT_U8(skb, IFLA_GRE_PMTUDISC, !!(p->iph.frag_off & htons(IP_DF)));
@@ -1556,8 +1622,8 @@ static const struct nla_policy ipgre_policy[IFLA_GRE_MAX + 1] = {
 	[IFLA_GRE_OFLAGS]	= { .type = NLA_U16 },
 	[IFLA_GRE_IKEY]		= { .type = NLA_U32 },
 	[IFLA_GRE_OKEY]		= { .type = NLA_U32 },
-	[IFLA_GRE_LOCAL]	= { .len = 4 },
-	[IFLA_GRE_REMOTE]	= { .len = 4 },
+	[IFLA_GRE_LOCAL]	= { .len = FIELD_SIZEOF(struct iphdr, saddr) },
+	[IFLA_GRE_REMOTE]	= { .len = FIELD_SIZEOF(struct iphdr, daddr) },
 	[IFLA_GRE_TTL]		= { .type = NLA_U8 },
 	[IFLA_GRE_TOS]		= { .type = NLA_U8 },
 	[IFLA_GRE_PMTUDISC]	= { .type = NLA_U8 },
@@ -1604,7 +1670,7 @@ static int __init ipgre_init(void)
 		return -EAGAIN;
 	}
 
-	err = register_pernet_gen_device(&ipgre_net_id, &ipgre_net_ops);
+	err = register_pernet_device(&ipgre_net_ops);
 	if (err < 0)
 		goto gen_device_failed;
 
@@ -1622,7 +1688,7 @@ out:
 tap_ops_failed:
 	rtnl_link_unregister(&ipgre_link_ops);
 rtnl_link_failed:
-	unregister_pernet_gen_device(ipgre_net_id, &ipgre_net_ops);
+	unregister_pernet_device(&ipgre_net_ops);
 gen_device_failed:
 	inet_del_protocol(&ipgre_protocol, IPPROTO_GRE);
 	goto out;
@@ -1632,7 +1698,7 @@ static void __exit ipgre_fini(void)
 {
 	rtnl_link_unregister(&ipgre_tap_ops);
 	rtnl_link_unregister(&ipgre_link_ops);
-	unregister_pernet_gen_device(ipgre_net_id, &ipgre_net_ops);
+	unregister_pernet_device(&ipgre_net_ops);
 	if (inet_del_protocol(&ipgre_protocol, IPPROTO_GRE) < 0)
 		printk(KERN_INFO "ipgre close: can't remove protocol\n");
 }
@@ -1640,5 +1706,5 @@ static void __exit ipgre_fini(void)
 module_init(ipgre_init);
 module_exit(ipgre_fini);
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("rtnl-link-gre");
-MODULE_ALIAS("rtnl-link-gretap");
+MODULE_ALIAS_RTNL_LINK("gre");
+MODULE_ALIAS_RTNL_LINK("gretap");