vxlan: Flow based tunneling

Allows putting a VXLAN device into a new flow-based mode in which
skbs with a ip_tunnel_info dst metadata attached will be encapsulated
according to the instructions stored in there with the VXLAN device
defaults taken into consideration.

Similar on the receive side, if the VXLAN_F_COLLECT_METADATA flag is
set, the packet processing will populate a ip_tunnel_info struct for
each packet received and attach it to the skb using the new metadata
dst.  The metadata structure will contain the outer header and tunnel
header fields which have been stripped off. Layers further up in the
stack such as routing, tc or netfitler can later match on these fields
and perform forwarding. It is the responsibility of upper layers to
ensure that the flag is set if the metadata is needed. The flag limits
the additional cost of metadata collecting based on demand.

This prepares the VXLAN device to be steered by the routing and other
subsystems which allows to support encapsulation for a large number
of tunnel endpoints and tunnel ids through a single net_device which
improves the scalability.

It also allows for OVS to leverage this mode which in turn allows for
the removal of the OVS specific VXLAN code.

Because the skb is currently scrubed in vxlan_rcv(), the attachment of
the new dst metadata is postponed until after scrubing which requires
the temporary addition of a new member to vxlan_metadata. This member
is removed again in a later commit after the indirect VXLAN receive API
has been removed.
Signed-off-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/linux/skbuff.h

@@ -3469,5 +3469,6 @@ static inline unsigned int skb_gso_network_seglen(const struct sk_buff *skb)
 			       skb_network_header(skb);
 	return hdr_len + skb_gso_transport_seglen(skb);
 }
+
 #endif	/* __KERNEL__ */
 #endif	/* _LINUX_SKBUFF_H */

include/net/dst_metadata.h

@@ -8,6 +8,9 @@
 struct metadata_dst {
 	struct dst_entry		dst;
 	size_t				opts_len;
+	union {
+		struct ip_tunnel_info	tun_info;
+	} u;
 };
 
 static inline struct metadata_dst *skb_metadata_dst(struct sk_buff *skb)
@@ -20,6 +23,16 @@ static inline struct metadata_dst *skb_metadata_dst(struct sk_buff *skb)
 	return NULL;
 }
 
+static inline struct ip_tunnel_info *skb_tunnel_info(struct sk_buff *skb)
+{
+	struct metadata_dst *md_dst = skb_metadata_dst(skb);
+
+	if (md_dst)
+		return &md_dst->u.tun_info;
+
+	return NULL;
+}
+
 static inline bool skb_valid_dst(const struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);

include/net/ip_tunnels.h

@@ -38,10 +38,19 @@ struct ip_tunnel_key {
 	__be16			tp_dst;
 } __packed __aligned(4); /* Minimize padding. */
 
+/* Indicates whether the tunnel info structure represents receive
+ * or transmit tunnel parameters.
+ */
+enum {
+	IP_TUNNEL_INFO_RX,
+	IP_TUNNEL_INFO_TX,
+};
+
 struct ip_tunnel_info {
 	struct ip_tunnel_key	key;
 	const void		*options;
 	u8			options_len;
+	u8			mode;
 };
 
 /* 6rd prefix/relay information */
@@ -284,6 +293,11 @@ static inline void iptunnel_xmit_stats(int err,
 	}
 }
 
+static inline void *ip_tunnel_info_opts(struct ip_tunnel_info *info, size_t n)
+{
+	return info + 1;
+}
+
 #endif /* CONFIG_INET */
 
 #endif /* __NET_IP_TUNNELS_H */

include/net/vxlan.h

@@ -7,6 +7,7 @@
 #include <linux/skbuff.h>
 #include <linux/netdevice.h>
 #include <linux/udp.h>
+#include <net/dst_metadata.h>
 
 #define VNI_HASH_BITS	10
 #define VNI_HASH_SIZE	(1<<VNI_HASH_BITS)
@@ -97,6 +98,9 @@ struct vxlanhdr {
 struct vxlan_metadata {
 	__be32		vni;
 	u32		gbp;
+
+	/* Temporary until vxlan_rcv() API is gone */
+	struct metadata_dst *tun_dst;
 };
 
 struct vxlan_sock;
@@ -130,6 +134,8 @@ struct vxlan_sock {
 #define VXLAN_F_REMCSUM_RX		0x400
 #define VXLAN_F_GBP			0x800
 #define VXLAN_F_REMCSUM_NOPARTIAL	0x1000
+#define VXLAN_F_COLLECT_METADATA	0x2000
+#define VXLAN_F_FLOW_BASED		0x4000
 
 /* Flags that are used in the receive path. These flags must match in
  * order for a socket to be shareable
@@ -137,7 +143,9 @@ struct vxlan_sock {
 #define VXLAN_F_RCV_FLAGS		(VXLAN_F_GBP |			\
 					 VXLAN_F_UDP_ZERO_CSUM6_RX |	\
 					 VXLAN_F_REMCSUM_RX |		\
-					 VXLAN_F_REMCSUM_NOPARTIAL)
+					 VXLAN_F_REMCSUM_NOPARTIAL |	\
+					 VXLAN_F_COLLECT_METADATA |	\
+					 VXLAN_F_FLOW_BASED)
 
 struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port,
 				  vxlan_rcv_t *rcv, void *data,

include/uapi/linux/if_link.h

@@ -382,6 +382,7 @@ enum {
 	IFLA_VXLAN_REMCSUM_RX,
 	IFLA_VXLAN_GBP,
 	IFLA_VXLAN_REMCSUM_NOPARTIAL,
+	IFLA_VXLAN_FLOWBASED,
 	__IFLA_VXLAN_MAX
 };
 #define IFLA_VXLAN_MAX	(__IFLA_VXLAN_MAX - 1)