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>

include/net/mpls.h

@@ -0,0 +1,39 @@
+/*
+ * Copyright (c) 2014 Nicira, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+
+#ifndef _NET_MPLS_H
+#define _NET_MPLS_H 1
+
+#include <linux/if_ether.h>
+#include <linux/netdevice.h>
+
+#define MPLS_HLEN 4
+
+static inline bool eth_p_mpls(__be16 eth_type)
+{
+	return eth_type == htons(ETH_P_MPLS_UC) ||
+		eth_type == htons(ETH_P_MPLS_MC);
+}
+
+/*
+ * For non-MPLS skbs this will correspond to the network header.
+ * For MPLS skbs it will be before the network_header as the MPLS
+ * label stack lies between the end of the mac header and the network
+ * header. That is, for MPLS skbs the end of the mac header
+ * is the top of the MPLS label stack.
+ */
+static inline unsigned char *skb_mpls_header(struct sk_buff *skb)
+{
+	return skb_mac_header(skb) + skb->mac_len;
+}
+#endif

include/uapi/linux/openvswitch.h

@@ -293,6 +293,9 @@ enum ovs_key_attr {
 	OVS_KEY_ATTR_DP_HASH,      /* u32 hash value. Value 0 indicates the hash
 				   is not computed by the datapath. */
 	OVS_KEY_ATTR_RECIRC_ID, /* u32 recirc id */
+	OVS_KEY_ATTR_MPLS,      /* array of struct ovs_key_mpls.
+				 * The implementation may restrict
+				 * the accepted length of the array. */
 
 #ifdef __KERNEL__
 	OVS_KEY_ATTR_TUNNEL_INFO,  /* struct ovs_tunnel_info */
@@ -340,6 +343,10 @@ struct ovs_key_ethernet {
 	__u8	 eth_dst[ETH_ALEN];
 };
 
+struct ovs_key_mpls {
+	__be32 mpls_lse;
+};
+
 struct ovs_key_ipv4 {
 	__be32 ipv4_src;
 	__be32 ipv4_dst;
@@ -483,6 +490,19 @@ enum ovs_userspace_attr {
 
 #define OVS_USERSPACE_ATTR_MAX (__OVS_USERSPACE_ATTR_MAX - 1)
 
+/**
+ * struct ovs_action_push_mpls - %OVS_ACTION_ATTR_PUSH_MPLS action argument.
+ * @mpls_lse: MPLS label stack entry to push.
+ * @mpls_ethertype: Ethertype to set in the encapsulating ethernet frame.
+ *
+ * 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_push_mpls {
+	__be32 mpls_lse;
+	__be16 mpls_ethertype; /* Either %ETH_P_MPLS_UC or %ETH_P_MPLS_MC */
+};
+
 /**
  * struct ovs_action_push_vlan - %OVS_ACTION_ATTR_PUSH_VLAN action argument.
  * @vlan_tpid: Tag protocol identifier (TPID) to push.
@@ -534,6 +554,15 @@ struct ovs_action_hash {
  * @OVS_ACTION_ATTR_POP_VLAN: Pop the outermost 802.1Q header off the packet.
  * @OVS_ACTION_ATTR_SAMPLE: Probabilitically executes actions, as specified in
  * the nested %OVS_SAMPLE_ATTR_* attributes.
+ * @OVS_ACTION_ATTR_PUSH_MPLS: Push a new MPLS label stack entry onto the
+ * top of the packets MPLS label stack.  Set the ethertype of the
+ * encapsulating frame to either %ETH_P_MPLS_UC or %ETH_P_MPLS_MC to
+ * indicate the new packet contents.
+ * @OVS_ACTION_ATTR_POP_MPLS: Pop an MPLS label stack entry off of the
+ * packet's MPLS label stack.  Set the encapsulating frame's ethertype to
+ * indicate the new packet contents. This could potentially still be
+ * %ETH_P_MPLS if the resulting MPLS label stack is not empty.  If there
+ * is no MPLS label stack, as determined by ethertype, no action is taken.
  *
  * 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
@@ -550,6 +579,9 @@ enum ovs_action_attr {
 	OVS_ACTION_ATTR_SAMPLE,       /* Nested OVS_SAMPLE_ATTR_*. */
 	OVS_ACTION_ATTR_RECIRC,       /* u32 recirc_id. */
 	OVS_ACTION_ATTR_HASH,	      /* struct ovs_action_hash. */
+	OVS_ACTION_ATTR_PUSH_MPLS,    /* struct ovs_action_push_mpls. */
+	OVS_ACTION_ATTR_POP_MPLS,     /* __be16 ethertype. */
+
 	__OVS_ACTION_ATTR_MAX
 };
 

net/core/dev.c

@@ -118,6 +118,7 @@
 #include <linux/if_vlan.h>
 #include <linux/ip.h>
 #include <net/ip.h>
+#include <net/mpls.h>
 #include <linux/ipv6.h>
 #include <linux/in.h>
 #include <linux/jhash.h>
@@ -2530,7 +2531,7 @@ static netdev_features_t net_mpls_features(struct sk_buff *skb,
 					   netdev_features_t features,
 					   __be16 type)
 {
-	if (type == htons(ETH_P_MPLS_UC) || type == htons(ETH_P_MPLS_MC))
+	if (eth_p_mpls(type))
 		features &= skb->dev->mpls_features;
 
 	return features;

net/openvswitch/Kconfig

@@ -30,6 +30,7 @@ config OPENVSWITCH
 
 config OPENVSWITCH_GRE
 	tristate "Open vSwitch GRE tunneling support"
+	select NET_MPLS_GSO
 	depends on INET
 	depends on OPENVSWITCH
 	depends on NET_IPGRE_DEMUX

net/openvswitch/actions.c

@@ -28,10 +28,12 @@
 #include <linux/in6.h>
 #include <linux/if_arp.h>
 #include <linux/if_vlan.h>
+
 #include <net/ip.h>
 #include <net/ipv6.h>
 #include <net/checksum.h>
 #include <net/dsfield.h>
+#include <net/mpls.h>
 #include <net/sctp/checksum.h>
 
 #include "datapath.h"
@@ -118,6 +120,92 @@ static int make_writable(struct sk_buff *skb, int write_len)
 	return pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
 }
 
+static int push_mpls(struct sk_buff *skb,
+		     const struct ovs_action_push_mpls *mpls)
+{
+	__be32 *new_mpls_lse;
+	struct ethhdr *hdr;
+
+	/* Networking stack do not allow simultaneous Tunnel and MPLS GSO. */
+	if (skb->encapsulation)
+		return -ENOTSUPP;
+
+	if (skb_cow_head(skb, MPLS_HLEN) < 0)
+		return -ENOMEM;
+
+	skb_push(skb, MPLS_HLEN);
+	memmove(skb_mac_header(skb) - MPLS_HLEN, skb_mac_header(skb),
+		skb->mac_len);
+	skb_reset_mac_header(skb);
+
+	new_mpls_lse = (__be32 *)skb_mpls_header(skb);
+	*new_mpls_lse = mpls->mpls_lse;
+
+	if (skb->ip_summed == CHECKSUM_COMPLETE)
+		skb->csum = csum_add(skb->csum, csum_partial(new_mpls_lse,
+							     MPLS_HLEN, 0));
+
+	hdr = eth_hdr(skb);
+	hdr->h_proto = mpls->mpls_ethertype;
+
+	skb_set_inner_protocol(skb, skb->protocol);
+	skb->protocol = mpls->mpls_ethertype;
+
+	return 0;
+}
+
+static int pop_mpls(struct sk_buff *skb, const __be16 ethertype)
+{
+	struct ethhdr *hdr;
+	int err;
+
+	err = make_writable(skb, skb->mac_len + MPLS_HLEN);
+	if (unlikely(err))
+		return err;
+
+	if (skb->ip_summed == CHECKSUM_COMPLETE)
+		skb->csum = csum_sub(skb->csum,
+				     csum_partial(skb_mpls_header(skb),
+						  MPLS_HLEN, 0));
+
+	memmove(skb_mac_header(skb) + MPLS_HLEN, skb_mac_header(skb),
+		skb->mac_len);
+
+	__skb_pull(skb, MPLS_HLEN);
+	skb_reset_mac_header(skb);
+
+	/* skb_mpls_header() is used to locate the ethertype
+	 * field correctly in the presence of VLAN tags.
+	 */
+	hdr = (struct ethhdr *)(skb_mpls_header(skb) - ETH_HLEN);
+	hdr->h_proto = ethertype;
+	if (eth_p_mpls(skb->protocol))
+		skb->protocol = ethertype;
+	return 0;
+}
+
+static int set_mpls(struct sk_buff *skb, const __be32 *mpls_lse)
+{
+	__be32 *stack;
+	int err;
+
+	err = make_writable(skb, skb->mac_len + MPLS_HLEN);
+	if (unlikely(err))
+		return err;
+
+	stack = (__be32 *)skb_mpls_header(skb);
+	if (skb->ip_summed == CHECKSUM_COMPLETE) {
+		__be32 diff[] = { ~(*stack), *mpls_lse };
+
+		skb->csum = ~csum_partial((char *)diff, sizeof(diff),
+					  ~skb->csum);
+	}
+
+	*stack = *mpls_lse;
+
+	return 0;
+}
+
 /* remove VLAN header from packet and update csum accordingly. */
 static int __pop_vlan_tci(struct sk_buff *skb, __be16 *current_tci)
 {
@@ -140,10 +228,12 @@ static int __pop_vlan_tci(struct sk_buff *skb, __be16 *current_tci)
 
 	vlan_set_encap_proto(skb, vhdr);
 	skb->mac_header += VLAN_HLEN;
+
 	if (skb_network_offset(skb) < ETH_HLEN)
 		skb_set_network_header(skb, ETH_HLEN);
-	skb_reset_mac_len(skb);
 
+	/* Update mac_len for subsequent MPLS actions */
+	skb_reset_mac_len(skb);
 	return 0;
 }
 
@@ -186,6 +276,8 @@ static int push_vlan(struct sk_buff *skb, const struct ovs_action_push_vlan *vla
 
 		if (!__vlan_put_tag(skb, skb->vlan_proto, current_tag))
 			return -ENOMEM;
+		/* Update mac_len for subsequent MPLS actions */
+		skb->mac_len += VLAN_HLEN;
 
 		if (skb->ip_summed == CHECKSUM_COMPLETE)
 			skb->csum = csum_add(skb->csum, csum_partial(skb->data
@@ -612,6 +704,10 @@ static int execute_set_action(struct sk_buff *skb,
 	case OVS_KEY_ATTR_SCTP:
 		err = set_sctp(skb, nla_data(nested_attr));
 		break;
+
+	case OVS_KEY_ATTR_MPLS:
+		err = set_mpls(skb, nla_data(nested_attr));
+		break;
 	}
 
 	return err;
@@ -690,6 +786,14 @@ 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, nla_data(a));
+			break;
+
+		case OVS_ACTION_ATTR_POP_MPLS:
+			err = pop_mpls(skb, nla_get_be16(a));
+			break;
+
 		case OVS_ACTION_ATTR_PUSH_VLAN:
 			err = push_vlan(skb, nla_data(a));
 			if (unlikely(err)) /* skb already freed. */

net/openvswitch/datapath.c

@@ -560,7 +560,7 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
 		goto err_flow_free;
 
 	err = ovs_nla_copy_actions(a[OVS_PACKET_ATTR_ACTIONS],
-				   &flow->key, 0, &acts);
+				   &flow->key, &acts);
 	if (err)
 		goto err_flow_free;
 
@@ -846,7 +846,7 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
 		goto err_kfree_flow;
 
 	error = ovs_nla_copy_actions(a[OVS_FLOW_ATTR_ACTIONS], &new_flow->key,
-				     0, &acts);
+				     &acts);
 	if (error) {
 		OVS_NLERR("Flow actions may not be safe on all matching packets.\n");
 		goto err_kfree_acts;
@@ -953,7 +953,7 @@ static struct sw_flow_actions *get_flow_actions(const struct nlattr *a,
 		return acts;
 
 	ovs_flow_mask_key(&masked_key, key, mask);
-	error = ovs_nla_copy_actions(a, &masked_key, 0, &acts);
+	error = ovs_nla_copy_actions(a, &masked_key, &acts);
 	if (error) {
 		OVS_NLERR("Flow actions may not be safe on all matching packets.\n");
 		kfree(acts);

net/openvswitch/flow.c

@@ -32,6 +32,7 @@
 #include <linux/if_arp.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
+#include <linux/mpls.h>
 #include <linux/sctp.h>
 #include <linux/smp.h>
 #include <linux/tcp.h>
@@ -42,6 +43,7 @@
 #include <net/ip.h>
 #include <net/ip_tunnels.h>
 #include <net/ipv6.h>
+#include <net/mpls.h>
 #include <net/ndisc.h>
 
 #include "datapath.h"
@@ -480,6 +482,7 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
 		return -ENOMEM;
 
 	skb_reset_network_header(skb);
+	skb_reset_mac_len(skb);
 	__skb_push(skb, skb->data - skb_mac_header(skb));
 
 	/* Network layer. */
@@ -584,6 +587,33 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
 			memset(&key->ip, 0, sizeof(key->ip));
 			memset(&key->ipv4, 0, sizeof(key->ipv4));
 		}
+	} else if (eth_p_mpls(key->eth.type)) {
+		size_t stack_len = MPLS_HLEN;
+
+		/* In the presence of an MPLS label stack the end of the L2
+		 * header and the beginning of the L3 header differ.
+		 *
+		 * Advance network_header to the beginning of the L3
+		 * header. mac_len corresponds to the end of the L2 header.
+		 */
+		while (1) {
+			__be32 lse;
+
+			error = check_header(skb, skb->mac_len + stack_len);
+			if (unlikely(error))
+				return 0;
+
+			memcpy(&lse, skb_network_header(skb), MPLS_HLEN);
+
+			if (stack_len == MPLS_HLEN)
+				memcpy(&key->mpls.top_lse, &lse, MPLS_HLEN);
+
+			skb_set_network_header(skb, skb->mac_len + stack_len);
+			if (lse & htonl(MPLS_LS_S_MASK))
+				break;
+
+			stack_len += MPLS_HLEN;
+		}
 	} else if (key->eth.type == htons(ETH_P_IPV6)) {
 		int nh_len;             /* IPv6 Header + Extensions */
 

net/openvswitch/flow.h

@@ -102,12 +102,17 @@ struct sw_flow_key {
 		__be16 tci;		/* 0 if no VLAN, VLAN_TAG_PRESENT set otherwise. */
 		__be16 type;		/* Ethernet frame type. */
 	} eth;
-	struct {
-		u8     proto;		/* IP protocol or lower 8 bits of ARP opcode. */
-		u8     tos;		/* IP ToS. */
-		u8     ttl;		/* IP TTL/hop limit. */
-		u8     frag;		/* One of OVS_FRAG_TYPE_*. */
-	} ip;
+	union {
+		struct {
+			__be32 top_lse;	/* top label stack entry */
+		} mpls;
+		struct {
+			u8     proto;	/* IP protocol or lower 8 bits of ARP opcode. */
+			u8     tos;	    /* IP ToS. */
+			u8     ttl;	    /* IP TTL/hop limit. */
+			u8     frag;	/* One of OVS_FRAG_TYPE_*. */
+		} ip;
+	};
 	struct {
 		__be16 src;		/* TCP/UDP/SCTP source port. */
 		__be16 dst;		/* TCP/UDP/SCTP destination port. */