openvswitch: Add support for Geneve tunneling.

The Openvswitch 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.

Signed-off-by: Jesse Gross <jesse@nicira.com>
Singed-off-by: Ansis Atteka <aatteka@nicira.com>
Signed-off-by: Andy Zhou <azhou@nicira.com>
Acked-by: Thomas Graf <tgraf@noironetworks.com>
Acked-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/ip_tunnels.h

@@ -86,17 +86,18 @@ struct ip_tunnel {
 	struct gro_cells	gro_cells;
 };
 
-#define TUNNEL_CSUM	__cpu_to_be16(0x01)
-#define TUNNEL_ROUTING	__cpu_to_be16(0x02)
-#define TUNNEL_KEY	__cpu_to_be16(0x04)
-#define TUNNEL_SEQ	__cpu_to_be16(0x08)
-#define TUNNEL_STRICT	__cpu_to_be16(0x10)
-#define TUNNEL_REC	__cpu_to_be16(0x20)
-#define TUNNEL_VERSION	__cpu_to_be16(0x40)
-#define TUNNEL_NO_KEY	__cpu_to_be16(0x80)
+#define TUNNEL_CSUM		__cpu_to_be16(0x01)
+#define TUNNEL_ROUTING		__cpu_to_be16(0x02)
+#define TUNNEL_KEY		__cpu_to_be16(0x04)
+#define TUNNEL_SEQ		__cpu_to_be16(0x08)
+#define TUNNEL_STRICT		__cpu_to_be16(0x10)
+#define TUNNEL_REC		__cpu_to_be16(0x20)
+#define TUNNEL_VERSION		__cpu_to_be16(0x40)
+#define TUNNEL_NO_KEY		__cpu_to_be16(0x80)
 #define TUNNEL_DONT_FRAGMENT    __cpu_to_be16(0x0100)
-#define TUNNEL_OAM	__cpu_to_be16(0x0200)
-#define TUNNEL_CRIT_OPT	__cpu_to_be16(0x0400)
+#define TUNNEL_OAM		__cpu_to_be16(0x0200)
+#define TUNNEL_CRIT_OPT		__cpu_to_be16(0x0400)
+#define TUNNEL_OPTIONS_PRESENT	__cpu_to_be16(0x0800)
 
 struct tnl_ptk_info {
 	__be16 flags;

include/uapi/linux/openvswitch.h

@@ -192,6 +192,7 @@ enum ovs_vport_type {
 	OVS_VPORT_TYPE_INTERNAL, /* network device implemented by datapath */
 	OVS_VPORT_TYPE_GRE,      /* GRE tunnel. */
 	OVS_VPORT_TYPE_VXLAN,	 /* VXLAN tunnel. */
+	OVS_VPORT_TYPE_GENEVE,	 /* Geneve tunnel. */
 	__OVS_VPORT_TYPE_MAX
 };
 
@@ -310,6 +311,7 @@ enum ovs_tunnel_key_attr {
 	OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT,      /* No argument, set DF. */
 	OVS_TUNNEL_KEY_ATTR_CSUM,               /* No argument. CSUM packet. */
 	OVS_TUNNEL_KEY_ATTR_OAM,                /* No argument. OAM frame.  */
+	OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS,        /* Array of Geneve options. */
 	__OVS_TUNNEL_KEY_ATTR_MAX
 };
 

net/openvswitch/Kconfig

@@ -54,3 +54,14 @@ config OPENVSWITCH_VXLAN
 	  Say N to exclude this support and reduce the binary size.
 
 	  If unsure, say Y.
+
+config OPENVSWITCH_GENEVE
+	bool "Open vSwitch Geneve tunneling support"
+	depends on INET
+	depends on OPENVSWITCH
+	depends on GENEVE && !(OPENVSWITCH=y && GENEVE=m)
+	default y
+	---help---
+	  If you say Y here, then the Open vSwitch will be able create geneve vport.
+
+	  Say N to exclude this support and reduce the binary size.

net/openvswitch/Makefile

@@ -15,6 +15,10 @@ openvswitch-y := \
 	vport-internal_dev.o \
 	vport-netdev.o
 
+ifneq ($(CONFIG_OPENVSWITCH_GENEVE),)
+openvswitch-y += vport-geneve.o
+endif
+
 ifneq ($(CONFIG_OPENVSWITCH_VXLAN),)
 openvswitch-y += vport-vxlan.o
 endif

net/openvswitch/datapath.c

@@ -370,6 +370,7 @@ 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(12)  /* OVS_KEY_ATTR_ETHERNET */
@@ -556,10 +557,12 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
 
 	err = ovs_nla_copy_actions(a[OVS_PACKET_ATTR_ACTIONS],
 				   &flow->key, 0, &acts);
-	rcu_assign_pointer(flow->sf_acts, acts);
 	if (err)
 		goto err_flow_free;
 
+	rcu_assign_pointer(flow->sf_acts, acts);
+
+	OVS_CB(packet)->egress_tun_info = NULL;
 	OVS_CB(packet)->flow = flow;
 	packet->priority = flow->key.phy.priority;
 	packet->mark = flow->key.phy.skb_mark;

net/openvswitch/flow.c

@@ -448,6 +448,9 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
 	int error;
 	struct ethhdr *eth;
 
+	/* Flags are always used as part of stats */
+	key->tp.flags = 0;
+
 	skb_reset_mac_header(skb);
 
 	/* Link layer.  We are guaranteed to have at least the 14 byte Ethernet
@@ -646,10 +649,23 @@ int ovs_flow_key_extract(struct ovs_tunnel_info *tun_info,
 			 struct sk_buff *skb, struct sw_flow_key *key)
 {
 	/* Extract metadata from packet. */
-	if (tun_info)
+	if (tun_info) {
 		memcpy(&key->tun_key, &tun_info->tunnel, sizeof(key->tun_key));
-	else
+
+		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));
+	}
 
 	key->phy.priority = skb->priority;
 	key->phy.in_port = OVS_CB(skb)->input_vport->port_no;

net/openvswitch/flow.h

@@ -51,11 +51,24 @@ 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)
+					  __be64 tun_id, __be16 tun_flags,
+					  struct geneve_opt *opts,
+					  u8 opts_len)
 {
 	tun_info->tunnel.tun_id = tun_id;
 	tun_info->tunnel.ipv4_src = iph->saddr;
@@ -67,9 +80,14 @@ 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. */