tunnel: Bareudp Tunnel Support.

There are various L3 encapsulation standards using UDP being discussed to
leverage the UDP based load balancing capability of different networks.
MPLSoUDP (__ https://tools.ietf.org/html/rfc7510) is one among them.

The Bareudp tunnel provides a generic L3 encapsulation support for
tunnelling different L3 protocols like MPLS, IP, NSH etc. inside a UDP
tunnel.

An example to create bareudp device to tunnel MPLS traffic is
given

$ ovs-vsctl add-port br_mpls udp_port -- set interface udp_port \
             type=bareudp options:remote_ip=2.1.1.3
             options:local_ip=2.1.1.2 \
             options:payload_type=0x8847 options:dst_port=6635

The bareudp device supports special handling for MPLS & IP as
they can have multiple ethertypes. MPLS procotcol can have ethertypes
ETH_P_MPLS_UC (unicast) & ETH_P_MPLS_MC (multicast). IP protocol can have
ethertypes ETH_P_IP (v4) & ETH_P_IPV6 (v6).

The bareudp device to tunnel L3 traffic with multiple ethertypes
(MPLS & IP) can be created by passing the L3 protocol name as string in
the field payload_type. An example to create bareudp device to tunnel
MPLS unicast & multicast traffic is given below.::

$ ovs-vsctl add-port  br_mpls udp_port -- set interface
            udp_port \
            type=bareudp options:remote_ip=2.1.1.3
            options:local_ip=2.1.1.2 \
            options:payload_type=mpls options:dst_port=6635

Signed-off-by: Martin Varghese <martin.varghese@nokia.com>
Acked-By: Greg Rose <gvrose8192@gmail.com>
Tested-by: Greg Rose <gvrose8192@gmail.com>
Acked-by: Eelco Chaudron <echaudro@redhat.com>
Signed-off-by: Ilya Maximets <i.maximets@ovn.org>

4 files changed, 89 insertions, 2 deletions

diff --git a/lib/dpif-netlink-rtnl.c b/lib/dpif-netlink-rtnl.c
index fd157ce2d..4fc42daed 100644
--- a/lib/dpif-netlink-rtnl.c
+++ b/lib/dpif-netlink-rtnl.c
@@ -58,6 +58,18 @@ VLOG_DEFINE_THIS_MODULE(dpif_netlink_rtnl);
 #define IFLA_GENEVE_UDP_ZERO_CSUM6_RX 10
 #endif
 
+#ifndef IFLA_BAREUDP_MAX
+#define IFLA_BAREUDP_MAX 0
+#endif
+#if IFLA_BAREUDP_MAX < 4
+#define IFLA_BAREUDP_PORT 1
+#define IFLA_BAREUDP_ETHERTYPE 2
+#define IFLA_BAREUDP_SRCPORT_MIN 3
+#define IFLA_BAREUDP_MULTIPROTO_MODE 4
+#endif
+
+#define BAREUDP_SRCPORT_MIN 49153
+
 static const struct nl_policy rtlink_policy[] = {
     [IFLA_LINKINFO] = { .type = NL_A_NESTED },
 };
@@ -81,6 +93,10 @@ static const struct nl_policy geneve_policy[] = {
     [IFLA_GENEVE_UDP_ZERO_CSUM6_RX] = { .type = NL_A_U8 },
     [IFLA_GENEVE_PORT] = { .type = NL_A_U16 },
 };
+static const struct nl_policy bareudp_policy[] = {
+    [IFLA_BAREUDP_PORT] = { .type = NL_A_U16 },
+    [IFLA_BAREUDP_ETHERTYPE] = { .type = NL_A_U16 },
+};
 
 static const char *
 vport_type_to_kind(enum ovs_vport_type type,
@@ -113,6 +129,8 @@ vport_type_to_kind(enum ovs_vport_type type,
         }
     case OVS_VPORT_TYPE_GTPU:
         return NULL;
+    case OVS_VPORT_TYPE_BAREUDP:
+        return "bareudp";
     case OVS_VPORT_TYPE_NETDEV:
     case OVS_VPORT_TYPE_INTERNAL:
     case OVS_VPORT_TYPE_LISP:
@@ -243,6 +261,24 @@ dpif_netlink_rtnl_geneve_verify(const struct netdev_tunnel_config *tnl_cfg,
 
     return err;
 }
+static int
+dpif_netlink_rtnl_bareudp_verify(const struct netdev_tunnel_config *tnl_cfg,
+                                const char *kind, struct ofpbuf *reply)
+{
+    struct nlattr *bareudp[ARRAY_SIZE(bareudp_policy)];
+    int err;
+
+    err = rtnl_policy_parse(kind, reply, bareudp_policy, bareudp,
+                            ARRAY_SIZE(bareudp_policy));
+    if (!err) {
+        if ((tnl_cfg->dst_port != nl_attr_get_be16(bareudp[IFLA_BAREUDP_PORT]))
+            || (tnl_cfg->payload_ethertype
+                != nl_attr_get_be16(bareudp[IFLA_BAREUDP_ETHERTYPE]))) {
+            err = EINVAL;
+        }
+    }
+    return err;
+}
 
 static int
 dpif_netlink_rtnl_verify(const struct netdev_tunnel_config *tnl_cfg,
@@ -275,6 +311,9 @@ dpif_netlink_rtnl_verify(const struct netdev_tunnel_config *tnl_cfg,
     case OVS_VPORT_TYPE_GENEVE:
         err = dpif_netlink_rtnl_geneve_verify(tnl_cfg, kind, reply);
         break;
+    case OVS_VPORT_TYPE_BAREUDP:
+        err = dpif_netlink_rtnl_bareudp_verify(tnl_cfg, kind, reply);
+        break;
     case OVS_VPORT_TYPE_NETDEV:
     case OVS_VPORT_TYPE_INTERNAL:
     case OVS_VPORT_TYPE_LISP:
@@ -357,6 +396,16 @@ dpif_netlink_rtnl_create(const struct netdev_tunnel_config *tnl_cfg,
         nl_msg_put_u8(&request, IFLA_GENEVE_UDP_ZERO_CSUM6_RX, 1);
         nl_msg_put_be16(&request, IFLA_GENEVE_PORT, tnl_cfg->dst_port);
         break;
+    case OVS_VPORT_TYPE_BAREUDP:
+        nl_msg_put_be16(&request, IFLA_BAREUDP_ETHERTYPE,
+                        tnl_cfg->payload_ethertype);
+        nl_msg_put_u16(&request, IFLA_BAREUDP_SRCPORT_MIN,
+                       BAREUDP_SRCPORT_MIN);
+        nl_msg_put_be16(&request, IFLA_BAREUDP_PORT, tnl_cfg->dst_port);
+        if (tnl_cfg->exts & (1 << OVS_BAREUDP_EXT_MULTIPROTO_MODE)) {
+            nl_msg_put_flag(&request, IFLA_BAREUDP_MULTIPROTO_MODE);
+        }
+        break;
     case OVS_VPORT_TYPE_NETDEV:
     case OVS_VPORT_TYPE_INTERNAL:
     case OVS_VPORT_TYPE_LISP:
@@ -470,6 +519,7 @@ dpif_netlink_rtnl_port_destroy(const char *name, const char *type)
     case OVS_VPORT_TYPE_ERSPAN:
     case OVS_VPORT_TYPE_IP6ERSPAN:
     case OVS_VPORT_TYPE_IP6GRE:
+    case OVS_VPORT_TYPE_BAREUDP:
         return dpif_netlink_rtnl_destroy(name);
     case OVS_VPORT_TYPE_NETDEV:
     case OVS_VPORT_TYPE_INTERNAL:
diff --git a/lib/dpif-netlink.c b/lib/dpif-netlink.c
index 2f881e4fa..ceb56c685 100644
--- a/lib/dpif-netlink.c
+++ b/lib/dpif-netlink.c
@@ -749,6 +749,9 @@ get_vport_type(const struct dpif_netlink_vport *vport)
     case OVS_VPORT_TYPE_GTPU:
         return "gtpu";
 
+    case OVS_VPORT_TYPE_BAREUDP:
+        return "bareudp";
+
     case OVS_VPORT_TYPE_UNSPEC:
     case __OVS_VPORT_TYPE_MAX:
         break;
@@ -784,6 +787,8 @@ netdev_to_ovs_vport_type(const char *type)
         return OVS_VPORT_TYPE_GRE;
     } else if (!strcmp(type, "gtpu")) {
         return OVS_VPORT_TYPE_GTPU;
+    } else if (!strcmp(type, "bareudp")) {
+        return OVS_VPORT_TYPE_BAREUDP;
     } else {
         return OVS_VPORT_TYPE_UNSPEC;
     }
diff --git a/lib/netdev-vport.c b/lib/netdev-vport.c
index 0252b61de..15567e524 100644
--- a/lib/netdev-vport.c
+++ b/lib/netdev-vport.c
@@ -47,6 +47,7 @@
 #include "unaligned.h"
 #include "unixctl.h"
 #include "openvswitch/vlog.h"
+#include "openvswitch/ofp-parse.h"
 #ifdef __linux__
 #include "netdev-linux.h"
 #endif
@@ -112,7 +113,7 @@ netdev_vport_needs_dst_port(const struct netdev *dev)
     return (class->get_config == get_tunnel_config &&
             (!strcmp("geneve", type) || !strcmp("vxlan", type) ||
              !strcmp("lisp", type) || !strcmp("stt", type) ||
-             !strcmp("gtpu", type)));
+             !strcmp("gtpu", type) || !strcmp("bareudp",type)));
 }
 
 const char *
@@ -219,6 +220,8 @@ netdev_vport_construct(struct netdev *netdev_)
         dev->tnl_cfg.dst_port = port ? htons(port) : htons(STT_DST_PORT);
     } else if (!strcmp(type, "gtpu")) {
         dev->tnl_cfg.dst_port = port ? htons(port) : htons(GTPU_DST_PORT);
+    } else if (!strcmp(type, "bareudp")) {
+        dev->tnl_cfg.dst_port = htons(port);
     }
 
     dev->tnl_cfg.dont_fragment = true;
@@ -438,6 +441,8 @@ tunnel_supported_layers(const char *type,
         return TNL_L2 | TNL_L3;
     } else if (!strcmp(type, "gtpu")) {
         return TNL_L3;
+    } else if (!strcmp(type, "bareudp")) {
+        return TNL_L3;
     } else {
         return TNL_L2;
     }
@@ -745,6 +750,23 @@ set_tunnel_config(struct netdev *dev_, const struct smap *args, char **errp)
                     goto out;
                 }
             }
+        } else if (!strcmp(node->key, "payload_type")) {
+            if (!strcmp(node->value, "mpls")) {
+                 tnl_cfg.payload_ethertype = htons(ETH_TYPE_MPLS);
+                 tnl_cfg.exts |= (1 << OVS_BAREUDP_EXT_MULTIPROTO_MODE);
+            } else if (!strcmp(node->value, "ip")) {
+                 tnl_cfg.payload_ethertype = htons(ETH_TYPE_IP);
+                 tnl_cfg.exts |= (1 << OVS_BAREUDP_EXT_MULTIPROTO_MODE);
+            } else {
+                 uint16_t payload_ethertype;
+
+                 if (str_to_u16(node->value, "payload_type",
+                                &payload_ethertype)) {
+                     err = EINVAL;
+                     goto out;
+                 }
+                 tnl_cfg.payload_ethertype = htons(payload_ethertype);
+            }
         } else {
             ds_put_format(&errors, "%s: unknown %s argument '%s'\n", name,
                           type, node->key);
@@ -917,7 +939,8 @@ get_tunnel_config(const struct netdev *dev, struct smap *args)
             (!strcmp("vxlan", type) && dst_port != VXLAN_DST_PORT) ||
             (!strcmp("lisp", type) && dst_port != LISP_DST_PORT) ||
             (!strcmp("stt", type) && dst_port != STT_DST_PORT) ||
-            (!strcmp("gtpu", type) && dst_port != GTPU_DST_PORT)) {
+            (!strcmp("gtpu", type) && dst_port != GTPU_DST_PORT) ||
+            !strcmp("bareudp", type)) {
             smap_add_format(args, "dst_port", "%d", dst_port);
         }
     }
@@ -1243,6 +1266,14 @@ netdev_vport_tunnel_register(void)
           },
           {{NULL, NULL, 0, 0}}
         },
+        { "udp_sys",
+          {
+              TUNNEL_FUNCTIONS_COMMON,
+              .type = "bareudp",
+              .get_ifindex = NETDEV_VPORT_GET_IFINDEX,
+          },
+          {{NULL, NULL, 0, 0}}
+        },
 
     };
     static struct ovsthread_once once = OVSTHREAD_ONCE_INITIALIZER;
diff --git a/lib/netdev.h b/lib/netdev.h
index fb5073056..b705a9e56 100644
--- a/lib/netdev.h
+++ b/lib/netdev.h
@@ -107,6 +107,7 @@ struct netdev_tunnel_config {
     bool out_key_flow;
     ovs_be64 out_key;
 
+    ovs_be16 payload_ethertype;
     ovs_be16 dst_port;
 
     bool ip_src_flow;