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, 105 insertions, 1 deletions

diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 922c133..930b1b6 100644
--- a/net/openvswitch/actions.c
+++ b/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. */