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>

include/uapi/linux/openvswitch.h

@@ -672,6 +672,32 @@ struct ovs_action_push_mpls {
 	__be16 mpls_ethertype; /* Either %ETH_P_MPLS_UC or %ETH_P_MPLS_MC */
 };
 
+/**
+ * struct ovs_action_add_mpls - %OVS_ACTION_ATTR_ADD_MPLS action
+ * argument.
+ * @mpls_lse: MPLS label stack entry to push.
+ * @mpls_ethertype: Ethertype to set in the encapsulating ethernet frame.
+ * @tun_flags: MPLS tunnel attributes.
+ *
+ * The only values @mpls_ethertype should ever be given are %ETH_P_MPLS_UC and
+ * %ETH_P_MPLS_MC, indicating MPLS unicast or multicast. Other are rejected.
+ */
+struct ovs_action_add_mpls {
+	__be32 mpls_lse;
+	__be16 mpls_ethertype; /* Either %ETH_P_MPLS_UC or %ETH_P_MPLS_MC */
+	__u16 tun_flags;
+};
+
+#define OVS_MPLS_L3_TUNNEL_FLAG_MASK  (1 << 0) /* Flag to specify the place of
+						* insertion of MPLS header.
+						* When false, the MPLS header
+						* will be inserted at the start
+						* of the packet.
+						* When true, the MPLS header
+						* will be inserted at the start
+						* of the l3 header.
+						*/
+
 /**
  * struct ovs_action_push_vlan - %OVS_ACTION_ATTR_PUSH_VLAN action argument.
  * @vlan_tpid: Tag protocol identifier (TPID) to push.
@@ -892,6 +918,10 @@ struct check_pkt_len_arg {
  * @OVS_ACTION_ATTR_CHECK_PKT_LEN: Check the packet length and execute a set
  * of actions if greater than the specified packet length, else execute
  * another set of actions.
+ * @OVS_ACTION_ATTR_ADD_MPLS: Push a new MPLS label stack entry at the
+ * start of the packet or at the start of the l3 header depending on the value
+ * of l3 tunnel flag in the tun_flags field of OVS_ACTION_ATTR_ADD_MPLS
+ * argument.
  *
  * Only a single header can be set with a single %OVS_ACTION_ATTR_SET.  Not all
  * fields within a header are modifiable, e.g. the IPv4 protocol and fragment
@@ -927,6 +957,7 @@ enum ovs_action_attr {
 	OVS_ACTION_ATTR_METER,        /* u32 meter ID. */
 	OVS_ACTION_ATTR_CLONE,        /* Nested OVS_CLONE_ATTR_*.  */
 	OVS_ACTION_ATTR_CHECK_PKT_LEN, /* Nested OVS_CHECK_PKT_LEN_ATTR_*. */
+	OVS_ACTION_ATTR_ADD_MPLS,     /* struct ovs_action_add_mpls. */
 
 	__OVS_ACTION_ATTR_MAX,	      /* Nothing past this will be accepted
 				       * from userspace. */

net/openvswitch/actions.c

@@ -161,16 +161,17 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 			      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 @@ static int pop_mpls(struct sk_buff *skb, struct sw_flow_key *key,
 	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 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 			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;

net/openvswitch/flow_netlink.c

@@ -79,6 +79,7 @@ static bool actions_may_change_flow(const struct nlattr *actions)
 		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 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 			[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 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 		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 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 			 * 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)