datapath: Add support for Geneve tunneling.

This adds support for Geneve - Generic Network Virtualization
Encapsulation. The protocol is documented at
http://tools.ietf.org/html/draft-gross-geneve-00

The kernel implementation is completely agnostic to the options
that are in use and can handle newly defined options without
further work. It does this by simply matching on a byte array
of options and allowing userspace to setup flows on this array.

Userspace currently implements only support for basic version of
Geneve. It can work with the base header (including the VNI) and
is capable of parsing options but does not currently support any
particular option definitions. Over time, the intention is to
allow options to be matched through OpenFlow without requiring
explicit support in OVS userspace.

Signed-off-by: Jesse Gross <[email protected]>
Acked-by: Thomas Graf <[email protected]>
Acked-by: Pravin B Shelar <[email protected]>

NEWS

@@ -3,6 +3,10 @@ Post-v2.3.0
    - The "learn" action supports a new flag "delete_learned" that causes
      the learned flows to be deleted when the flow with the "learn" action
      is deleted.
+   - Basic support for the Geneve tunneling protocol. It is not yet
+     possible to generate or match options. This is planned for a future
+     release. The protocol is documented at
+     http://tools.ietf.org/html/draft-gross-geneve-00
 
 
 v2.3.0 - xx xxx xxxx

datapath/Modules.mk

@@ -14,6 +14,7 @@ openvswitch_sources = \
 	flow_netlink.c \
 	flow_table.c \
 	vport.c \
+	vport-geneve.c \
 	vport-gre.c \
 	vport-internal_dev.c \
 	vport-lisp.c \

datapath/datapath.c

@@ -394,6 +394,7 @@ static size_t key_attr_size(void)
 		  + nla_total_size(0)   /* OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT */
 		  + nla_total_size(0)   /* OVS_TUNNEL_KEY_ATTR_CSUM */
 		  + nla_total_size(0)   /* OVS_TUNNEL_KEY_ATTR_OAM */
+		  + nla_total_size(256) /* OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS */
 		+ nla_total_size(4)   /* OVS_KEY_ATTR_IN_PORT */
 		+ nla_total_size(4)   /* OVS_KEY_ATTR_SKB_MARK */
 		+ nla_total_size(4)   /* OVS_KEY_ATTR_DP_HASH */
@@ -488,7 +489,8 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
 	upcall->dp_ifindex = dp_ifindex;
 
 	nla = nla_nest_start(user_skb, OVS_PACKET_ATTR_KEY);
-	err = ovs_nla_put_flow(upcall_info->key, upcall_info->key, user_skb);
+	err = ovs_nla_put_flow(dp, upcall_info->key,
+			       upcall_info->key, user_skb);
 	BUG_ON(err);
 	nla_nest_end(user_skb, nla);
 
@@ -696,7 +698,8 @@ static size_t ovs_flow_cmd_msg_size(const struct sw_flow_actions *acts)
 }
 
 /* Called with ovs_mutex or RCU read lock. */
-static int ovs_flow_cmd_fill_info(const struct sw_flow *flow, int dp_ifindex,
+static int ovs_flow_cmd_fill_info(struct datapath *dp,
+				  const struct sw_flow *flow, int dp_ifindex,
 				  struct sk_buff *skb, u32 portid,
 				  u32 seq, u32 flags, u8 cmd)
 {
@@ -720,7 +723,8 @@ static int ovs_flow_cmd_fill_info(const struct sw_flow *flow, int dp_ifindex,
 	if (!nla)
 		goto nla_put_failure;
 
-	err = ovs_nla_put_flow(&flow->unmasked_key, &flow->unmasked_key, skb);
+	err = ovs_nla_put_flow(dp, &flow->unmasked_key,
+			       &flow->unmasked_key, skb);
 	if (err)
 		goto error;
 	nla_nest_end(skb, nla);
@@ -729,7 +733,7 @@ static int ovs_flow_cmd_fill_info(const struct sw_flow *flow, int dp_ifindex,
 	if (!nla)
 		goto nla_put_failure;
 
-	err = ovs_nla_put_flow(&flow->key, &flow->mask->key, skb);
+	err = ovs_nla_put_flow(dp, &flow->key, &flow->mask->key, skb);
 	if (err)
 		goto error;
 
@@ -806,7 +810,8 @@ static struct sk_buff *ovs_flow_cmd_alloc_info(const struct sw_flow_actions *act
 }
 
 /* Called with ovs_mutex. */
-static struct sk_buff *ovs_flow_cmd_build_info(const struct sw_flow *flow,
+static struct sk_buff *ovs_flow_cmd_build_info(struct datapath *dp,
+					       const struct sw_flow *flow,
 					       int dp_ifindex,
 					       struct genl_info *info, u8 cmd,
 					       bool always)
@@ -819,7 +824,7 @@ static struct sk_buff *ovs_flow_cmd_build_info(const struct sw_flow *flow,
 	if (!skb || IS_ERR(skb))
 		return skb;
 
-	retval = ovs_flow_cmd_fill_info(flow, dp_ifindex, skb,
+	retval = ovs_flow_cmd_fill_info(dp, flow, dp_ifindex, skb,
 					info->snd_portid, info->snd_seq, 0,
 					cmd);
 	BUG_ON(retval < 0);
@@ -900,7 +905,7 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
 		}
 
 		if (unlikely(reply)) {
-			error = ovs_flow_cmd_fill_info(new_flow,
+			error = ovs_flow_cmd_fill_info(dp, new_flow,
 						       ovs_header->dp_ifindex,
 						       reply, info->snd_portid,
 						       info->snd_seq, 0,
@@ -932,7 +937,7 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
 		rcu_assign_pointer(flow->sf_acts, acts);
 
 		if (unlikely(reply)) {
-			error = ovs_flow_cmd_fill_info(flow,
+			error = ovs_flow_cmd_fill_info(dp, flow,
 						       ovs_header->dp_ifindex,
 						       reply, info->snd_portid,
 						       info->snd_seq, 0,
@@ -1048,7 +1053,7 @@ static int ovs_flow_cmd_set(struct sk_buff *skb, struct genl_info *info)
 		rcu_assign_pointer(flow->sf_acts, acts);
 
 		if (unlikely(reply)) {
-			error = ovs_flow_cmd_fill_info(flow,
+			error = ovs_flow_cmd_fill_info(dp, flow,
 						       ovs_header->dp_ifindex,
 						       reply, info->snd_portid,
 						       info->snd_seq, 0,
@@ -1057,7 +1062,8 @@ static int ovs_flow_cmd_set(struct sk_buff *skb, struct genl_info *info)
 		}
 	} else {
 		/* Could not alloc without acts before locking. */
-		reply = ovs_flow_cmd_build_info(flow, ovs_header->dp_ifindex,
+		reply = ovs_flow_cmd_build_info(dp, flow,
+						ovs_header->dp_ifindex,
 						info, OVS_FLOW_CMD_NEW, false);
 		if (unlikely(IS_ERR(reply))) {
 			error = PTR_ERR(reply);
@@ -1119,7 +1125,7 @@ static int ovs_flow_cmd_get(struct sk_buff *skb, struct genl_info *info)
 		goto unlock;
 	}
 
-	reply = ovs_flow_cmd_build_info(flow, ovs_header->dp_ifindex, info,
+	reply = ovs_flow_cmd_build_info(dp, flow, ovs_header->dp_ifindex, info,
 					OVS_FLOW_CMD_NEW, true);
 	if (IS_ERR(reply)) {
 		err = PTR_ERR(reply);
@@ -1176,7 +1182,7 @@ static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info)
 	if (likely(reply)) {
 		if (likely(!IS_ERR(reply))) {
 			rcu_read_lock(); /* Keep RCU checker happy. */
-			err = ovs_flow_cmd_fill_info(flow,
+			err = ovs_flow_cmd_fill_info(dp, flow,
 						     ovs_header->dp_ifindex,
 						     reply, info->snd_portid,
 						     info->snd_seq, 0,
@@ -1222,7 +1228,7 @@ static int ovs_flow_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb)
 		if (!flow)
 			break;
 
-		if (ovs_flow_cmd_fill_info(flow, ovs_header->dp_ifindex, skb,
+		if (ovs_flow_cmd_fill_info(dp, flow, ovs_header->dp_ifindex, skb,
 					   NETLINK_CB(cb->skb).portid,
 					   cb->nlh->nlmsg_seq, NLM_F_MULTI,
 					   OVS_FLOW_CMD_NEW) < 0)

datapath/flow.c

@@ -455,7 +455,17 @@ int ovs_flow_extract(struct sk_buff *skb, u16 in_port, struct sw_flow_key *key)
 		struct ovs_tunnel_info *tun_info = OVS_CB(skb)->tun_info;
 		memcpy(&key->tun_key, &tun_info->tunnel,
 			sizeof(key->tun_key));
+		if (tun_info->options) {
+			BUILD_BUG_ON((1 << (sizeof(tun_info->options_len) * 8)) - 1
+					> sizeof(key->tun_opts));
+			memcpy(GENEVE_OPTS(key, tun_info->options_len),
+				tun_info->options, tun_info->options_len);
+			key->tun_opts_len = tun_info->options_len;
+		} else {
+			key->tun_opts_len = 0;
+		}
 	} else {
+		key->tun_opts_len = 0;
 		memset(&key->tun_key, 0, sizeof(key->tun_key));
 	}
 

datapath/flow.h

@@ -53,11 +53,24 @@ struct ovs_key_ipv4_tunnel {
 
 struct ovs_tunnel_info {
 	struct ovs_key_ipv4_tunnel tunnel;
+	struct geneve_opt *options;
+	u8 options_len;
 };
 
+/* Store options at the end of the array if they are less than the
+ * maximum size. This allows us to get the benefits of variable length
+ * matching for small options.
+ */
+#define GENEVE_OPTS(flow_key, opt_len) (struct geneve_opt *) \
+					((flow_key)->tun_opts + \
+					FIELD_SIZEOF(struct sw_flow_key, tun_opts) - \
+					   opt_len)
+
 static inline void ovs_flow_tun_info_init(struct ovs_tunnel_info *tun_info,
 					 const struct iphdr *iph, __be64 tun_id,
-					 __be16 tun_flags)
+					 __be16 tun_flags,
+					 struct geneve_opt *opts,
+					 u8 opts_len)
 {
 	tun_info->tunnel.tun_id = tun_id;
 	tun_info->tunnel.ipv4_src = iph->saddr;
@@ -69,9 +82,14 @@ static inline void ovs_flow_tun_info_init(struct ovs_tunnel_info *tun_info,
 	/* clear struct padding. */
 	memset((unsigned char *) &tun_info->tunnel + OVS_TUNNEL_KEY_SIZE, 0,
 	       sizeof(tun_info->tunnel) - OVS_TUNNEL_KEY_SIZE);
+
+	tun_info->options = opts;
+	tun_info->options_len = opts_len;
 }
 
 struct sw_flow_key {
+	u8 tun_opts[255];
+	u8 tun_opts_len;
 	struct ovs_key_ipv4_tunnel tun_key;  /* Encapsulating tunnel key. */
 	struct {
 		u32	priority;	/* Packet QoS priority. */