openvswitch: Add basic MPLS support to kernel

Allow datapath to recognize and extract MPLS labels into flow keys
and execute actions which push, pop, and set labels on packets.

Based heavily on work by Leo Alterman, Ravi K, Isaku Yamahata and Joe Stringer.

Cc: Ravi K <rkerur@gmail.com>
Cc: Leo Alterman <lalterman@nicira.com>
Cc: Isaku Yamahata <yamahata@valinux.co.jp>
Cc: Joe Stringer <joe@wand.net.nz>
Signed-off-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Jesse Gross <jesse@nicira.com>
Signed-off-by: Pravin B Shelar <pshelar@nicira.com>

1 files changed, 121 insertions, 18 deletions

diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 939bcb32100f..569309c49cc0 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -46,6 +46,7 @@
 #include <net/ip.h>
 #include <net/ipv6.h>
 #include <net/ndisc.h>
+#include <net/mpls.h>
 
 #include "flow_netlink.h"
 
@@ -134,7 +135,8 @@ static bool match_validate(const struct sw_flow_match *match,
 			| (1 << OVS_KEY_ATTR_ICMP)
 			| (1 << OVS_KEY_ATTR_ICMPV6)
 			| (1 << OVS_KEY_ATTR_ARP)
-			| (1 << OVS_KEY_ATTR_ND));
+			| (1 << OVS_KEY_ATTR_ND)
+			| (1 << OVS_KEY_ATTR_MPLS));
 
 	/* Always allowed mask fields. */
 	mask_allowed |= ((1 << OVS_KEY_ATTR_TUNNEL)
@@ -149,6 +151,12 @@ static bool match_validate(const struct sw_flow_match *match,
 			mask_allowed |= 1 << OVS_KEY_ATTR_ARP;
 	}
 
+	if (eth_p_mpls(match->key->eth.type)) {
+		key_expected |= 1 << OVS_KEY_ATTR_MPLS;
+		if (match->mask && (match->mask->key.eth.type == htons(0xffff)))
+			mask_allowed |= 1 << OVS_KEY_ATTR_MPLS;
+	}
+
 	if (match->key->eth.type == htons(ETH_P_IP)) {
 		key_expected |= 1 << OVS_KEY_ATTR_IPV4;
 		if (match->mask && (match->mask->key.eth.type == htons(0xffff)))
@@ -266,6 +274,7 @@ static const int ovs_key_lens[OVS_KEY_ATTR_MAX + 1] = {
 	[OVS_KEY_ATTR_RECIRC_ID] = sizeof(u32),
 	[OVS_KEY_ATTR_DP_HASH] = sizeof(u32),
 	[OVS_KEY_ATTR_TUNNEL] = -1,
+	[OVS_KEY_ATTR_MPLS] = sizeof(struct ovs_key_mpls),
 };
 
 static bool is_all_zero(const u8 *fp, size_t size)
@@ -735,6 +744,16 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, u64 attrs,
 		attrs &= ~(1 << OVS_KEY_ATTR_ARP);
 	}
 
+	if (attrs & (1 << OVS_KEY_ATTR_MPLS)) {
+		const struct ovs_key_mpls *mpls_key;
+
+		mpls_key = nla_data(a[OVS_KEY_ATTR_MPLS]);
+		SW_FLOW_KEY_PUT(match, mpls.top_lse,
+				mpls_key->mpls_lse, is_mask);
+
+		attrs &= ~(1 << OVS_KEY_ATTR_MPLS);
+	 }
+
 	if (attrs & (1 << OVS_KEY_ATTR_TCP)) {
 		const struct ovs_key_tcp *tcp_key;
 
@@ -1140,6 +1159,14 @@ int ovs_nla_put_flow(const struct sw_flow_key *swkey,
 		arp_key->arp_op = htons(output->ip.proto);
 		ether_addr_copy(arp_key->arp_sha, output->ipv4.arp.sha);
 		ether_addr_copy(arp_key->arp_tha, output->ipv4.arp.tha);
+	} else if (eth_p_mpls(swkey->eth.type)) {
+		struct ovs_key_mpls *mpls_key;
+
+		nla = nla_reserve(skb, OVS_KEY_ATTR_MPLS, sizeof(*mpls_key));
+		if (!nla)
+			goto nla_put_failure;
+		mpls_key = nla_data(nla);
+		mpls_key->mpls_lse = output->mpls.top_lse;
 	}
 
 	if ((swkey->eth.type == htons(ETH_P_IP) ||
@@ -1336,9 +1363,15 @@ static inline void add_nested_action_end(struct sw_flow_actions *sfa,
 	a->nla_len = sfa->actions_len - st_offset;
 }
 
+static int ovs_nla_copy_actions__(const struct nlattr *attr,
+				  const struct sw_flow_key *key,
+				  int depth, struct sw_flow_actions **sfa,
+				  __be16 eth_type, __be16 vlan_tci);
+
 static int validate_and_copy_sample(const struct nlattr *attr,
 				    const struct sw_flow_key *key, int depth,
-				    struct sw_flow_actions **sfa)
+				    struct sw_flow_actions **sfa,
+				    __be16 eth_type, __be16 vlan_tci)
 {
 	const struct nlattr *attrs[OVS_SAMPLE_ATTR_MAX + 1];
 	const struct nlattr *probability, *actions;
@@ -1375,7 +1408,8 @@ static int validate_and_copy_sample(const struct nlattr *attr,
 	if (st_acts < 0)
 		return st_acts;
 
-	err = ovs_nla_copy_actions(actions, key, depth + 1, sfa);
+	err = ovs_nla_copy_actions__(actions, key, depth + 1, sfa,
+				     eth_type, vlan_tci);
 	if (err)
 		return err;
 
@@ -1385,10 +1419,10 @@ static int validate_and_copy_sample(const struct nlattr *attr,
 	return 0;
 }
 
-static int validate_tp_port(const struct sw_flow_key *flow_key)
+static int validate_tp_port(const struct sw_flow_key *flow_key,
+			    __be16 eth_type)
 {
-	if ((flow_key->eth.type == htons(ETH_P_IP) ||
-	     flow_key->eth.type == htons(ETH_P_IPV6)) &&
+	if ((eth_type == htons(ETH_P_IP) || eth_type == htons(ETH_P_IPV6)) &&
 	    (flow_key->tp.src || flow_key->tp.dst))
 		return 0;
 
@@ -1483,7 +1517,7 @@ static int validate_and_copy_set_tun(const struct nlattr *attr,
 static int validate_set(const struct nlattr *a,
 			const struct sw_flow_key *flow_key,
 			struct sw_flow_actions **sfa,
-			bool *set_tun)
+			bool *set_tun, __be16 eth_type)
 {
 	const struct nlattr *ovs_key = nla_data(a);
 	int key_type = nla_type(ovs_key);
@@ -1508,6 +1542,9 @@ static int validate_set(const struct nlattr *a,
 		break;
 
 	case OVS_KEY_ATTR_TUNNEL:
+		if (eth_p_mpls(eth_type))
+			return -EINVAL;
+
 		*set_tun = true;
 		err = validate_and_copy_set_tun(a, sfa);
 		if (err)
@@ -1515,7 +1552,7 @@ static int validate_set(const struct nlattr *a,
 		break;
 
 	case OVS_KEY_ATTR_IPV4:
-		if (flow_key->eth.type != htons(ETH_P_IP))
+		if (eth_type != htons(ETH_P_IP))
 			return -EINVAL;
 
 		if (!flow_key->ip.proto)
@@ -1531,7 +1568,7 @@ static int validate_set(const struct nlattr *a,
 		break;
 
 	case OVS_KEY_ATTR_IPV6:
-		if (flow_key->eth.type != htons(ETH_P_IPV6))
+		if (eth_type != htons(ETH_P_IPV6))
 			return -EINVAL;
 
 		if (!flow_key->ip.proto)
@@ -1553,19 +1590,24 @@ static int validate_set(const struct nlattr *a,
 		if (flow_key->ip.proto != IPPROTO_TCP)
 			return -EINVAL;
 
-		return validate_tp_port(flow_key);
+		return validate_tp_port(flow_key, eth_type);
 
 	case OVS_KEY_ATTR_UDP:
 		if (flow_key->ip.proto != IPPROTO_UDP)
 			return -EINVAL;
 
-		return validate_tp_port(flow_key);
+		return validate_tp_port(flow_key, eth_type);
+
+	case OVS_KEY_ATTR_MPLS:
+		if (!eth_p_mpls(eth_type))
+			return -EINVAL;
+		break;
 
 	case OVS_KEY_ATTR_SCTP:
 		if (flow_key->ip.proto != IPPROTO_SCTP)
 			return -EINVAL;
 
-		return validate_tp_port(flow_key);
+		return validate_tp_port(flow_key, eth_type);
 
 	default:
 		return -EINVAL;
@@ -1609,12 +1651,13 @@ static int copy_action(const struct nlattr *from,
 	return 0;
 }
 
-int ovs_nla_copy_actions(const struct nlattr *attr,
-			 const struct sw_flow_key *key,
-			 int depth,
-			 struct sw_flow_actions **sfa)
+static int ovs_nla_copy_actions__(const struct nlattr *attr,
+				  const struct sw_flow_key *key,
+				  int depth, struct sw_flow_actions **sfa,
+				  __be16 eth_type, __be16 vlan_tci)
 {
 	const struct nlattr *a;
+	bool out_tnl_port = false;
 	int rem, err;
 
 	if (depth >= SAMPLE_ACTION_DEPTH)
@@ -1626,6 +1669,8 @@ int ovs_nla_copy_actions(const struct nlattr *attr,
 			[OVS_ACTION_ATTR_OUTPUT] = sizeof(u32),
 			[OVS_ACTION_ATTR_RECIRC] = sizeof(u32),
 			[OVS_ACTION_ATTR_USERSPACE] = (u32)-1,
+			[OVS_ACTION_ATTR_PUSH_MPLS] = sizeof(struct ovs_action_push_mpls),
+			[OVS_ACTION_ATTR_POP_MPLS] = sizeof(__be16),
 			[OVS_ACTION_ATTR_PUSH_VLAN] = sizeof(struct ovs_action_push_vlan),
 			[OVS_ACTION_ATTR_POP_VLAN] = 0,
 			[OVS_ACTION_ATTR_SET] = (u32)-1,
@@ -1655,6 +1700,8 @@ int ovs_nla_copy_actions(const struct nlattr *attr,
 		case OVS_ACTION_ATTR_OUTPUT:
 			if (nla_get_u32(a) >= DP_MAX_PORTS)
 				return -EINVAL;
+			out_tnl_port = false;
+
 			break;
 
 		case OVS_ACTION_ATTR_HASH: {
@@ -1671,6 +1718,7 @@ int ovs_nla_copy_actions(const struct nlattr *attr,
 		}
 
 		case OVS_ACTION_ATTR_POP_VLAN:
+			vlan_tci = htons(0);
 			break;
 
 		case OVS_ACTION_ATTR_PUSH_VLAN:
@@ -1679,19 +1727,66 @@ int ovs_nla_copy_actions(const struct nlattr *attr,
 				return -EINVAL;
 			if (!(vlan->vlan_tci & htons(VLAN_TAG_PRESENT)))
 				return -EINVAL;
+			vlan_tci = vlan->vlan_tci;
 			break;
 
 		case OVS_ACTION_ATTR_RECIRC:
 			break;
 
+		case OVS_ACTION_ATTR_PUSH_MPLS: {
+			const struct ovs_action_push_mpls *mpls = nla_data(a);
+
+			/* Networking stack do not allow simultaneous Tunnel
+			 * and MPLS GSO.
+			 */
+			if (out_tnl_port)
+				return -EINVAL;
+
+			if (!eth_p_mpls(mpls->mpls_ethertype))
+				return -EINVAL;
+			/* Prohibit push MPLS other than to a white list
+			 * for packets that have a known tag order.
+			 */
+			if (vlan_tci & htons(VLAN_TAG_PRESENT) ||
+			    (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;
+			eth_type = mpls->mpls_ethertype;
+			break;
+		}
+
+		case OVS_ACTION_ATTR_POP_MPLS:
+			if (vlan_tci & htons(VLAN_TAG_PRESENT) ||
+			    !eth_p_mpls(eth_type))
+				return -EINVAL;
+
+			/* Disallow subsequent L2.5+ set and mpls_pop actions
+			 * as there is no check here to ensure that the new
+			 * eth_type is valid and thus set actions could
+			 * write off the end of the packet or otherwise
+			 * corrupt it.
+			 *
+			 * Support for these actions is planned using packet
+			 * recirculation.
+			 */
+			eth_type = htons(0);
+			break;
+
 		case OVS_ACTION_ATTR_SET:
-			err = validate_set(a, key, sfa, &skip_copy);
+			err = validate_set(a, key, sfa,
+					   &out_tnl_port, eth_type);
 			if (err)
 				return err;
+
+			skip_copy = out_tnl_port;
 			break;
 
 		case OVS_ACTION_ATTR_SAMPLE:
-			err = validate_and_copy_sample(a, key, depth, sfa);
+			err = validate_and_copy_sample(a, key, depth, sfa,
+						       eth_type, vlan_tci);
 			if (err)
 				return err;
 			skip_copy = true;
@@ -1713,6 +1808,14 @@ int ovs_nla_copy_actions(const struct nlattr *attr,
 	return 0;
 }
 
+int ovs_nla_copy_actions(const struct nlattr *attr,
+			 const struct sw_flow_key *key,
+			 struct sw_flow_actions **sfa)
+{
+	return ovs_nla_copy_actions__(attr, key, 0, sfa, key->eth.type,
+				      key->eth.tci);
+}
+
 static int sample_action_to_attr(const struct nlattr *attr, struct sk_buff *skb)
 {
 	const struct nlattr *a;