Initial L2 LISP support

This introduces support for layer 2 overlays with LISP. Similarly to L3,
all tenant packets to be encapsulated are captured by an interface, but
the mapping (layer binding) instead of being between an L3 VRF and a
LISP VNI, it is between and an L2 bridge domain and a VNI. At a high
level, this results in two important properties:
1) the source and destinations of all packets flooded in the
   bridge-domain are mapped via the LISP control plane and the replies are
   converted into data-plane tunnels tracked via a LISP specific
   source/dest L2 FIB
2) All packets reaching the interface and matching a source/dest L2 LISP
   FIB entry are L3 (IP4/6) encapsulated.

This is solely a unicast feature, therefore at this time ARPs are not
handled in any special way.

Change-Id: I0b7badcd7c6d5166db07d4acd2cc4ae7fba3e18e
Signed-off-by: Florin Coras <fcoras@cisco.com>

1 files changed, 13 insertions, 3 deletions

diff --git a/vnet/vnet/lisp-cp/lisp_msg_serdes.c b/vnet/vnet/lisp-cp/lisp_msg_serdes.c
index c1713b36c99..d7b734e9679 100644
--- a/vnet/vnet/lisp-cp/lisp_msg_serdes.c
+++ b/vnet/vnet/lisp-cp/lisp_msg_serdes.c
@@ -114,11 +114,21 @@ lisp_msg_push_ecm (vlib_main_t * vm, vlib_buffer_t *b, int lp, int rp,
                    gid_address_t *la, gid_address_t *ra)
 {
   ecm_hdr_t *h;
-  ASSERT(gid_address_type(la) == GID_ADDR_IP_PREFIX);
+  ip_address_t _src_ip, * src_ip = &_src_ip, _dst_ip, * dst_ip = &_dst_ip;
+  if (gid_address_type(la) != GID_ADDR_IP_PREFIX)
+    {
+      /* empty ip4 */
+      memset(src_ip, 0, sizeof(src_ip[0]));
+      memset(dst_ip, 0, sizeof(dst_ip[0]));
+    }
+  else
+    {
+      src_ip = &gid_address_ip(la);
+      dst_ip = &gid_address_ip(ra);
+    }
 
   /* Push inner ip and udp */
-  pkt_push_udp_and_ip (vm, b, lp, rp, &gid_address_ip(la),
-                              &gid_address_ip(ra));
+  pkt_push_udp_and_ip (vm, b, lp, rp, src_ip, dst_ip);
 
   /* Push lisp ecm hdr */
   h = pkt_push_ecm_hdr (b);