openvswitch: New MPLS actions for layer 2 tunnelling

The existing PUSH MPLS action inserts MPLS header between ethernet header
and the IP header. Though this behaviour is fine for L3 VPN where an IP
packet is encapsulated inside a MPLS tunnel, it does not suffice the L2
VPN (l2 tunnelling) requirements. In L2 VPN the MPLS header should
encapsulate the ethernet packet.

The new mpls action ADD_MPLS inserts MPLS header at the start of the
packet or at the start of the l3 header depending on the value of l3 tunnel
flag in the ADD_MPLS arguments.

POP_MPLS action is extended to support ethertype 0x6558.

Signed-off-by: Martin Varghese <martin.varghese@nokia.com>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 4c83954..7fbfe2a 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -161,16 +161,17 @@
 			      const struct nlattr *attr, int len);
 
 static int push_mpls(struct sk_buff *skb, struct sw_flow_key *key,
-		     const struct ovs_action_push_mpls *mpls)
+		     __be32 mpls_lse, __be16 mpls_ethertype, __u16 mac_len)
 {
 	int err;
 
-	err = skb_mpls_push(skb, mpls->mpls_lse, mpls->mpls_ethertype,
-			    skb->mac_len,
-			    ovs_key_mac_proto(key) == MAC_PROTO_ETHERNET);
+	err = skb_mpls_push(skb, mpls_lse, mpls_ethertype, mac_len, !!mac_len);
 	if (err)
 		return err;
 
+	if (!mac_len)
+		key->mac_proto = MAC_PROTO_NONE;
+
 	invalidate_flow_key(key);
 	return 0;
 }
@@ -185,6 +186,9 @@
 	if (err)
 		return err;
 
+	if (ethertype == htons(ETH_P_TEB))
+		key->mac_proto = MAC_PROTO_ETHERNET;
+
 	invalidate_flow_key(key);
 	return 0;
 }
@@ -1229,10 +1233,24 @@
 			execute_hash(skb, key, a);
 			break;
 
-		case OVS_ACTION_ATTR_PUSH_MPLS:
-			err = push_mpls(skb, key, nla_data(a));
-			break;
+		case OVS_ACTION_ATTR_PUSH_MPLS: {
+			struct ovs_action_push_mpls *mpls = nla_data(a);
 
+			err = push_mpls(skb, key, mpls->mpls_lse,
+					mpls->mpls_ethertype, skb->mac_len);
+			break;
+		}
+		case OVS_ACTION_ATTR_ADD_MPLS: {
+			struct ovs_action_add_mpls *mpls = nla_data(a);
+			__u16 mac_len = 0;
+
+			if (mpls->tun_flags & OVS_MPLS_L3_TUNNEL_FLAG_MASK)
+				mac_len = skb->mac_len;
+
+			err = push_mpls(skb, key, mpls->mpls_lse,
+					mpls->mpls_ethertype, mac_len);
+			break;
+		}
 		case OVS_ACTION_ATTR_POP_MPLS:
 			err = pop_mpls(skb, key, nla_get_be16(a));
 			break;
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 65c2e34..7da4230 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -79,6 +79,7 @@
 		case OVS_ACTION_ATTR_SET_MASKED:
 		case OVS_ACTION_ATTR_METER:
 		case OVS_ACTION_ATTR_CHECK_PKT_LEN:
+		case OVS_ACTION_ATTR_ADD_MPLS:
 		default:
 			return true;
 		}
@@ -3005,6 +3006,7 @@
 			[OVS_ACTION_ATTR_METER] = sizeof(u32),
 			[OVS_ACTION_ATTR_CLONE] = (u32)-1,
 			[OVS_ACTION_ATTR_CHECK_PKT_LEN] = (u32)-1,
+			[OVS_ACTION_ATTR_ADD_MPLS] = sizeof(struct ovs_action_add_mpls),
 		};
 		const struct ovs_action_push_vlan *vlan;
 		int type = nla_type(a);
@@ -3072,6 +3074,33 @@
 		case OVS_ACTION_ATTR_RECIRC:
 			break;
 
+		case OVS_ACTION_ATTR_ADD_MPLS: {
+			const struct ovs_action_add_mpls *mpls = nla_data(a);
+
+			if (!eth_p_mpls(mpls->mpls_ethertype))
+				return -EINVAL;
+
+			if (mpls->tun_flags & OVS_MPLS_L3_TUNNEL_FLAG_MASK) {
+				if (vlan_tci & htons(VLAN_CFI_MASK) ||
+				    (eth_type != htons(ETH_P_IP) &&
+				     eth_type != htons(ETH_P_IPV6) &&
+				     eth_type != htons(ETH_P_ARP) &&
+				     eth_type != htons(ETH_P_RARP) &&
+				     !eth_p_mpls(eth_type)))
+					return -EINVAL;
+				mpls_label_count++;
+			} else {
+				if (mac_proto == MAC_PROTO_ETHERNET) {
+					mpls_label_count = 1;
+					mac_proto = MAC_PROTO_NONE;
+				} else {
+					mpls_label_count++;
+				}
+			}
+			eth_type = mpls->mpls_ethertype;
+			break;
+		}
+
 		case OVS_ACTION_ATTR_PUSH_MPLS: {
 			const struct ovs_action_push_mpls *mpls = nla_data(a);
 
@@ -3109,6 +3138,11 @@
 			 * recirculation.
 			 */
 			proto = nla_get_be16(a);
+
+			if (proto == htons(ETH_P_TEB) &&
+			    mac_proto != MAC_PROTO_NONE)
+				return -EINVAL;
+
 			mpls_label_count--;
 
 			if (!eth_p_mpls(proto) || !mpls_label_count)