openvswitch: Fix egress tunnel info.

While transitioning to netdev based vport we broke OVS
feature which allows user to retrieve tunnel packet egress
information for lwtunnel devices.  Following patch fixes it
by introducing ndo operation to get the tunnel egress info.
Same ndo operation can be used for lwtunnel devices and compat
ovs-tnl-vport devices. So after adding such device operation
we can remove similar operation from ovs-vport.

Fixes: 614732eaa12d ("openvswitch: Use regular VXLAN net_device device").
Signed-off-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 74 insertions, 7 deletions

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index cde29f8..445071c 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -594,14 +594,12 @@ static struct rtable *geneve_get_rt(struct sk_buff *skb,
 	rt = ip_route_output_key(geneve->net, fl4);
 	if (IS_ERR(rt)) {
 		netdev_dbg(dev, "no route to %pI4\n", &fl4->daddr);
-		dev->stats.tx_carrier_errors++;
-		return rt;
+		return ERR_PTR(-ENETUNREACH);
 	}
 	if (rt->dst.dev == dev) { /* is this necessary? */
 		netdev_dbg(dev, "circular route to %pI4\n", &fl4->daddr);
-		dev->stats.collisions++;
 		ip_rt_put(rt);
-		return ERR_PTR(-EINVAL);
+		return ERR_PTR(-ELOOP);
 	}
 	return rt;
 }
@@ -627,12 +625,12 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct ip_tunnel_info *info = NULL;
 	struct rtable *rt = NULL;
 	const struct iphdr *iip; /* interior IP header */
+	int err = -EINVAL;
 	struct flowi4 fl4;
 	__u8 tos, ttl;
 	__be16 sport;
 	bool udp_csum;
 	__be16 df;
-	int err;
 
 	if (geneve->collect_md) {
 		info = skb_tunnel_info(skb);
@@ -647,7 +645,7 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev)
 	rt = geneve_get_rt(skb, dev, &fl4, info);
 	if (IS_ERR(rt)) {
 		netdev_dbg(dev, "no route to %pI4\n", &fl4.daddr);
-		dev->stats.tx_carrier_errors++;
+		err = PTR_ERR(rt);
 		goto tx_error;
 	}
 
@@ -699,10 +697,37 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev)
 tx_error:
 	dev_kfree_skb(skb);
 err:
-	dev->stats.tx_errors++;
+	if (err == -ELOOP)
+		dev->stats.collisions++;
+	else if (err == -ENETUNREACH)
+		dev->stats.tx_carrier_errors++;
+	else
+		dev->stats.tx_errors++;
 	return NETDEV_TX_OK;
 }
 
+static int geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
+{
+	struct ip_tunnel_info *info = skb_tunnel_info(skb);
+	struct geneve_dev *geneve = netdev_priv(dev);
+	struct rtable *rt;
+	struct flowi4 fl4;
+
+	if (ip_tunnel_info_af(info) != AF_INET)
+		return -EINVAL;
+
+	rt = geneve_get_rt(skb, dev, &fl4, info);
+	if (IS_ERR(rt))
+		return PTR_ERR(rt);
+
+	ip_rt_put(rt);
+	info->key.u.ipv4.src = fl4.saddr;
+	info->key.tp_src = udp_flow_src_port(geneve->net, skb,
+					     1, USHRT_MAX, true);
+	info->key.tp_dst = geneve->dst_port;
+	return 0;
+}
+
 static const struct net_device_ops geneve_netdev_ops = {
 	.ndo_init		= geneve_init,
 	.ndo_uninit		= geneve_uninit,
@@ -713,6 +738,7 @@ static const struct net_device_ops geneve_netdev_ops = {
 	.ndo_change_mtu		= eth_change_mtu,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address	= eth_mac_addr,
+	.ndo_fill_metadata_dst	= geneve_fill_metadata_dst,
 };
 
 static void geneve_get_drvinfo(struct net_device *dev,
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index afdc65f..c1587ec 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2337,6 +2337,46 @@ static int vxlan_change_mtu(struct net_device *dev, int new_mtu)
 	return 0;
 }
 
+static int egress_ipv4_tun_info(struct net_device *dev, struct sk_buff *skb,
+				struct ip_tunnel_info *info,
+				__be16 sport, __be16 dport)
+{
+	struct vxlan_dev *vxlan = netdev_priv(dev);
+	struct rtable *rt;
+	struct flowi4 fl4;
+
+	memset(&fl4, 0, sizeof(fl4));
+	fl4.flowi4_tos = RT_TOS(info->key.tos);
+	fl4.flowi4_mark = skb->mark;
+	fl4.flowi4_proto = IPPROTO_UDP;
+	fl4.daddr = info->key.u.ipv4.dst;
+
+	rt = ip_route_output_key(vxlan->net, &fl4);
+	if (IS_ERR(rt))
+		return PTR_ERR(rt);
+	ip_rt_put(rt);
+
+	info->key.u.ipv4.src = fl4.saddr;
+	info->key.tp_src = sport;
+	info->key.tp_dst = dport;
+	return 0;
+}
+
+static int vxlan_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
+{
+	struct vxlan_dev *vxlan = netdev_priv(dev);
+	struct ip_tunnel_info *info = skb_tunnel_info(skb);
+	__be16 sport, dport;
+
+	sport = udp_flow_src_port(dev_net(dev), skb, vxlan->cfg.port_min,
+				  vxlan->cfg.port_max, true);
+	dport = info->key.tp_dst ? : vxlan->cfg.dst_port;
+
+	if (ip_tunnel_info_af(info) == AF_INET)
+		return egress_ipv4_tun_info(dev, skb, info, sport, dport);
+	return -EINVAL;
+}
+
 static const struct net_device_ops vxlan_netdev_ops = {
 	.ndo_init		= vxlan_init,
 	.ndo_uninit		= vxlan_uninit,
@@ -2351,6 +2391,7 @@ static const struct net_device_ops vxlan_netdev_ops = {
 	.ndo_fdb_add		= vxlan_fdb_add,
 	.ndo_fdb_del		= vxlan_fdb_delete,
 	.ndo_fdb_dump		= vxlan_fdb_dump,
+	.ndo_fill_metadata_dst	= vxlan_fill_metadata_dst,
 };
 
 /* Info for udev, that this is a virtual tunnel endpoint */