Merge branch 'net_next_ovs' of git://git.kernel.org/pub/scm/linux/kernel/git/pshelar/openvswitch

Pravin B Shelar says:

====================
Open vSwitch

First two patches are related to OVS MPLS support. Rest of patches
are mostly refactoring and minor improvements to openvswitch.

v1-v2:
 - Fix conflicts due to "gue: Remote checksum offload"
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

include/linux/netdev_features.h

@@ -47,7 +47,6 @@ enum {
 	NETIF_F_GSO_SIT_BIT,		/* ... SIT tunnel with TSO */
 	NETIF_F_GSO_UDP_TUNNEL_BIT,	/* ... UDP TUNNEL with TSO */
 	NETIF_F_GSO_UDP_TUNNEL_CSUM_BIT,/* ... UDP TUNNEL with TSO & CSUM */
-	NETIF_F_GSO_MPLS_BIT,		/* ... MPLS segmentation */
 	NETIF_F_GSO_TUNNEL_REMCSUM_BIT, /* ... TUNNEL with TSO & REMCSUM */
 	/**/NETIF_F_GSO_LAST =		/* last bit, see GSO_MASK */
 		NETIF_F_GSO_TUNNEL_REMCSUM_BIT,
@@ -119,7 +118,6 @@ enum {
 #define NETIF_F_GSO_SIT		__NETIF_F(GSO_SIT)
 #define NETIF_F_GSO_UDP_TUNNEL	__NETIF_F(GSO_UDP_TUNNEL)
 #define NETIF_F_GSO_UDP_TUNNEL_CSUM __NETIF_F(GSO_UDP_TUNNEL_CSUM)
-#define NETIF_F_GSO_MPLS	__NETIF_F(GSO_MPLS)
 #define NETIF_F_GSO_TUNNEL_REMCSUM __NETIF_F(GSO_TUNNEL_REMCSUM)
 #define NETIF_F_HW_VLAN_STAG_FILTER __NETIF_F(HW_VLAN_STAG_FILTER)
 #define NETIF_F_HW_VLAN_STAG_RX	__NETIF_F(HW_VLAN_STAG_RX)
@@ -183,7 +181,6 @@ enum {
 				 NETIF_F_GSO_IPIP |			\
 				 NETIF_F_GSO_SIT |			\
 				 NETIF_F_GSO_UDP_TUNNEL |		\
-				 NETIF_F_GSO_UDP_TUNNEL_CSUM |		\
-				 NETIF_F_GSO_MPLS)
+				 NETIF_F_GSO_UDP_TUNNEL_CSUM)
 
 #endif	/* _LINUX_NETDEV_FEATURES_H */

include/linux/netdevice.h

@@ -3583,7 +3583,6 @@ static inline bool net_gso_ok(netdev_features_t features, int gso_type)
 	BUILD_BUG_ON(SKB_GSO_SIT     != (NETIF_F_GSO_SIT >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_UDP_TUNNEL != (NETIF_F_GSO_UDP_TUNNEL >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_UDP_TUNNEL_CSUM != (NETIF_F_GSO_UDP_TUNNEL_CSUM >> NETIF_F_GSO_SHIFT));
-	BUILD_BUG_ON(SKB_GSO_MPLS    != (NETIF_F_GSO_MPLS >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_TUNNEL_REMCSUM != (NETIF_F_GSO_TUNNEL_REMCSUM >> NETIF_F_GSO_SHIFT));
 
 	return (features & feature) == feature;

include/linux/skbuff.h

@@ -372,9 +372,7 @@ enum {
 
 	SKB_GSO_UDP_TUNNEL_CSUM = 1 << 11,
 
-	SKB_GSO_MPLS = 1 << 12,
-
-	SKB_GSO_TUNNEL_REMCSUM = 1 << 13,
+	SKB_GSO_TUNNEL_REMCSUM = 1 << 12,
 };
 
 #if BITS_PER_LONG > 32

include/net/mpls.h

+/*
+ * 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;
@@ -393,9 +400,9 @@ struct ovs_key_arp {
 };
 
 struct ovs_key_nd {
-	__u32 nd_target[4];
-	__u8  nd_sll[ETH_ALEN];
-	__u8  nd_tll[ETH_ALEN];
+	__be32	nd_target[4];
+	__u8	nd_sll[ETH_ALEN];
+	__u8	nd_tll[ETH_ALEN];
 };
 
 /**
@@ -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/core/ethtool.c

@@ -84,7 +84,6 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]
 	[NETIF_F_GSO_IPIP_BIT] =	 "tx-ipip-segmentation",
 	[NETIF_F_GSO_SIT_BIT] =		 "tx-sit-segmentation",
 	[NETIF_F_GSO_UDP_TUNNEL_BIT] =	 "tx-udp_tnl-segmentation",
-	[NETIF_F_GSO_MPLS_BIT] =	 "tx-mpls-segmentation",
 
 	[NETIF_F_FCOE_CRC_BIT] =         "tx-checksum-fcoe-crc",
 	[NETIF_F_SCTP_CSUM_BIT] =        "tx-checksum-sctp",

net/ipv4/af_inet.c

@@ -1223,7 +1223,6 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 		       SKB_GSO_UDP_TUNNEL |
 		       SKB_GSO_UDP_TUNNEL_CSUM |
 		       SKB_GSO_TUNNEL_REMCSUM |
-		       SKB_GSO_MPLS |
 		       0)))
 		goto out;
 

net/ipv4/tcp_offload.c

@@ -94,7 +94,6 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 			       SKB_GSO_GRE_CSUM |
 			       SKB_GSO_IPIP |
 			       SKB_GSO_SIT |
-			       SKB_GSO_MPLS |
 			       SKB_GSO_UDP_TUNNEL |
 			       SKB_GSO_UDP_TUNNEL_CSUM |
 			       SKB_GSO_TUNNEL_REMCSUM |

net/ipv4/udp_offload.c

@@ -207,8 +207,7 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
 				      SKB_GSO_UDP_TUNNEL_CSUM |
 				      SKB_GSO_TUNNEL_REMCSUM |
 				      SKB_GSO_IPIP |
-				      SKB_GSO_GRE | SKB_GSO_GRE_CSUM |
-				      SKB_GSO_MPLS) ||
+				      SKB_GSO_GRE | SKB_GSO_GRE_CSUM) ||
 			     !(type & (SKB_GSO_UDP))))
 			goto out;
 

net/ipv6/ip6_offload.c

@@ -79,7 +79,6 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 		       SKB_GSO_UDP_TUNNEL |
 		       SKB_GSO_UDP_TUNNEL_CSUM |
 		       SKB_GSO_TUNNEL_REMCSUM |
-		       SKB_GSO_MPLS |
 		       SKB_GSO_TCPV6 |
 		       0)))
 		goto out;

net/ipv6/udp_offload.c

@@ -46,8 +46,7 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
 				      SKB_GSO_GRE |
 				      SKB_GSO_GRE_CSUM |
 				      SKB_GSO_IPIP |
-				      SKB_GSO_SIT |
-				      SKB_GSO_MPLS) ||
+				      SKB_GSO_SIT) ||
 			     !(type & (SKB_GSO_UDP))))
 			goto out;
 

net/mpls/mpls_gso.c

@@ -34,8 +34,7 @@ static struct sk_buff *mpls_gso_segment(struct sk_buff *skb,
 				  SKB_GSO_TCP_ECN |
 				  SKB_GSO_GRE |
 				  SKB_GSO_GRE_CSUM |
-				  SKB_GSO_IPIP |
-				  SKB_GSO_MPLS)))
+				  SKB_GSO_IPIP)))
 		goto out;
 
 	/* Setup inner SKB. */

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
@@ -459,21 +551,14 @@ static int set_sctp(struct sk_buff *skb,
 	return 0;
 }
 
-static int do_output(struct datapath *dp, struct sk_buff *skb, int out_port)
+static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port)
 {
-	struct vport *vport;
+	struct vport *vport = ovs_vport_rcu(dp, out_port);
 
-	if (unlikely(!skb))
-		return -ENOMEM;
-
-	vport = ovs_vport_rcu(dp, out_port);
-	if (unlikely(!vport)) {
+	if (likely(vport))
+		ovs_vport_send(vport, skb);
+	else
 		kfree_skb(skb);
-		return -ENODEV;
-	}
-
-	ovs_vport_send(vport, skb);
-	return 0;
 }
 
 static int output_userspace(struct datapath *dp, struct sk_buff *skb,
@@ -612,6 +697,10 @@ 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;
@@ -672,8 +761,12 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 	     a = nla_next(a, &rem)) {
 		int err = 0;
 
-		if (prev_port != -1) {
-			do_output(dp, skb_clone(skb, GFP_ATOMIC), prev_port);
+		if (unlikely(prev_port != -1)) {
+			struct sk_buff *out_skb = skb_clone(skb, GFP_ATOMIC);
+
+			if (out_skb)
+				do_output(dp, out_skb, prev_port);
+
 			prev_port = -1;
 		}
 
@@ -690,6 +783,14 @@ 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. */
@@ -764,14 +865,11 @@ static void process_deferred_actions(struct datapath *dp)
 
 /* Execute a list of actions against 'skb'. */
 int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb,
-			struct sw_flow_key *key)
+			struct sw_flow_actions *acts, struct sw_flow_key *key)
 {
 	int level = this_cpu_read(exec_actions_level);
-	struct sw_flow_actions *acts;
 	int err;
 
-	acts = rcu_dereference(OVS_CB(skb)->flow->sf_acts);
-
 	this_cpu_inc(exec_actions_level);
 	OVS_CB(skb)->egress_tun_info = NULL;
 	err = do_execute_actions(dp, skb, key,

net/openvswitch/datapath.h

@@ -94,14 +94,12 @@ struct datapath {
 
 /**
  * struct ovs_skb_cb - OVS data in skb CB
- * @flow: The flow associated with this packet.  May be %NULL if no flow.
  * @egress_tun_key: Tunnel information about this packet on egress path.
  * NULL if the packet is not being tunneled.
  * @input_vport: The original vport packet came in on. This value is cached
  * when a packet is received by OVS.
  */
 struct ovs_skb_cb {
-	struct sw_flow		*flow;
 	struct ovs_tunnel_info  *egress_tun_info;
 	struct vport		*input_vport;
 };
@@ -194,7 +192,7 @@ struct sk_buff *ovs_vport_cmd_build_info(struct vport *, u32 pid, u32 seq,
 					 u8 cmd);
 
 int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb,
-			struct sw_flow_key *);
+			struct sw_flow_actions *acts, struct sw_flow_key *);
 
 void ovs_dp_notify_wq(struct work_struct *work);
 

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. */

net/openvswitch/flow_netlink.h

@@ -37,6 +37,8 @@
 
 #include "flow.h"
 
+size_t ovs_key_attr_size(void);
+
 void ovs_match_init(struct sw_flow_match *match,
 		    struct sw_flow_key *key, struct sw_flow_mask *mask);
 
@@ -49,12 +51,11 @@ int ovs_nla_get_match(struct sw_flow_match *match,
 		      const struct nlattr *);
 
 int ovs_nla_copy_actions(const struct nlattr *attr,
-			 const struct sw_flow_key *key, int depth,
+			 const struct sw_flow_key *key,
 			 struct sw_flow_actions **sfa);
 int ovs_nla_put_actions(const struct nlattr *attr,
 			int len, struct sk_buff *skb);
 
-struct sw_flow_actions *ovs_nla_alloc_flow_actions(int actions_len);
 void ovs_nla_free_flow_actions(struct sw_flow_actions *);
 
 #endif /* flow_netlink.h */

net/openvswitch/flow_table.c

 /*
- * Copyright (c) 2007-2013 Nicira, Inc.
+ * Copyright (c) 2007-2014 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
@@ -250,11 +250,14 @@ static void table_instance_destroy(struct table_instance *ti, bool deferred)
 		__table_instance_destroy(ti);
 }
 
-void ovs_flow_tbl_destroy(struct flow_table *table, bool deferred)
+/* No need for locking this function is called from RCU callback or
+ * error path.
+ */
+void ovs_flow_tbl_destroy(struct flow_table *table)
 {
-	struct table_instance *ti = ovsl_dereference(table->ti);
+	struct table_instance *ti = rcu_dereference_raw(table->ti);
 
-	table_instance_destroy(ti, deferred);
+	table_instance_destroy(ti, false);
 }
 
 struct sw_flow *ovs_flow_tbl_dump_next(struct table_instance *ti,

net/openvswitch/flow_table.h

@@ -62,7 +62,7 @@ void ovs_flow_free(struct sw_flow *, bool deferred);
 
 int ovs_flow_tbl_init(struct flow_table *);
 int ovs_flow_tbl_count(struct flow_table *table);
-void ovs_flow_tbl_destroy(struct flow_table *table, bool deferred);
+void ovs_flow_tbl_destroy(struct flow_table *table);
 int ovs_flow_tbl_flush(struct flow_table *flow_table);
 
 int ovs_flow_tbl_insert(struct flow_table *table, struct sw_flow *flow,

net/openvswitch/vport-internal_dev.c

@@ -224,6 +224,11 @@ static int internal_dev_recv(struct vport *vport, struct sk_buff *skb)
 	struct net_device *netdev = netdev_vport_priv(vport)->dev;
 	int len;
 
+	if (unlikely(!(netdev->flags & IFF_UP))) {
+		kfree_skb(skb);
+		return 0;
+	}
+
 	len = skb->len;
 
 	skb_dst_drop(skb);