net: Changes to ip_tunnel to support foo-over-udp encapsulation

This patch changes IP tunnel to support (secondary) encapsulation,
Foo-over-UDP. Changes include:

1) Adding tun_hlen as the tunnel header length, encap_hlen as the
   encapsulation header length, and hlen becomes the grand total
   of these.
2) Added common netlink define to support FOU encapsulation.
3) Routines to perform FOU encapsulation.

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 90 insertions, 1 deletions

diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index afed1aac2638..e3a3dc91e49c 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -55,6 +55,7 @@
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
 #include <net/rtnetlink.h>
+#include <net/udp.h>
 
 #if IS_ENABLED(CONFIG_IPV6)
 #include <net/ipv6.h>
@@ -487,6 +488,91 @@ drop:
 }
 EXPORT_SYMBOL_GPL(ip_tunnel_rcv);
 
+static int ip_encap_hlen(struct ip_tunnel_encap *e)
+{
+        switch (e->type) {
+        case TUNNEL_ENCAP_NONE:
+                return 0;
+        case TUNNEL_ENCAP_FOU:
+                return sizeof(struct udphdr);
+        default:
+                return -EINVAL;
+        }
+}
+
+int ip_tunnel_encap_setup(struct ip_tunnel *t,
+                          struct ip_tunnel_encap *ipencap)
+{
+        int hlen;
+
+        memset(&t->encap, 0, sizeof(t->encap));
+
+        hlen = ip_encap_hlen(ipencap);
+        if (hlen < 0)
+                return hlen;
+
+        t->encap.type = ipencap->type;
+        t->encap.sport = ipencap->sport;
+        t->encap.dport = ipencap->dport;
+        t->encap.flags = ipencap->flags;
+
+        t->encap_hlen = hlen;
+        t->hlen = t->encap_hlen + t->tun_hlen;
+
+        return 0;
+}
+EXPORT_SYMBOL_GPL(ip_tunnel_encap_setup);
+
+static int fou_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
+                            size_t hdr_len, u8 *protocol, struct flowi4 *fl4)
+{
+        struct udphdr *uh;
+        __be16 sport;
+        bool csum = !!(e->flags & TUNNEL_ENCAP_FLAG_CSUM);
+        int type = csum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL;
+
+        skb = iptunnel_handle_offloads(skb, csum, type);
+
+        if (IS_ERR(skb))
+                return PTR_ERR(skb);
+
+        /* Get length and hash before making space in skb */
+
+        sport = e->sport ? : udp_flow_src_port(dev_net(skb->dev),
+                                               skb, 0, 0, false);
+
+        skb_push(skb, hdr_len);
+
+        skb_reset_transport_header(skb);
+        uh = udp_hdr(skb);
+
+        uh->dest = e->dport;
+        uh->source = sport;
+        uh->len = htons(skb->len);
+        uh->check = 0;
+        udp_set_csum(!(e->flags & TUNNEL_ENCAP_FLAG_CSUM), skb,
+                     fl4->saddr, fl4->daddr, skb->len);
+
+        *protocol = IPPROTO_UDP;
+
+        return 0;
+}
+
+int ip_tunnel_encap(struct sk_buff *skb, struct ip_tunnel *t,
+                    u8 *protocol, struct flowi4 *fl4)
+{
+        switch (t->encap.type) {
+        case TUNNEL_ENCAP_NONE:
+                return 0;
+        case TUNNEL_ENCAP_FOU:
+                return fou_build_header(skb, &t->encap, t->encap_hlen,
+                                        protocol, fl4);
+        default:
+                return -EINVAL;
+        }
+}
+EXPORT_SYMBOL(ip_tunnel_encap);
+
 static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
                             struct rtable *rt, __be16 df)
 {
@@ -536,7 +622,7 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
 }
 
 void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
-                    const struct iphdr *tnl_params, const u8 protocol)
+                    const struct iphdr *tnl_params, u8 protocol)
 {
         struct ip_tunnel *tunnel = netdev_priv(dev);
         const struct iphdr *inner_iph;
@@ -617,6 +703,9 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
         init_tunnel_flow(&fl4, protocol, dst, tnl_params->saddr,
                          tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link);
 
+        if (ip_tunnel_encap(skb, tunnel, &protocol, &fl4) < 0)
+                goto tx_error;
+
         rt = connected ? tunnel_rtable_get(tunnel, 0, &fl4.saddr) : NULL;
 
         if (!rt) {