Merge branch 'Bare-UDP-L3-Encapsulation-Module'

Martin Varghese says:

====================
Bare UDP L3 Encapsulation Module

There are various L3 encapsulation standards using UDP being discussed to
leverage the UDP based load balancing capability of different networks.
MPLSoUDP (__ https://tools.ietf.org/html/rfc7510) is one among them.

The Bareudp tunnel module provides a generic L3 encapsulation tunnelling
support for tunnelling different L3 protocols like MPLS, IP, NSH etc. inside
a UDP tunnel.

Special Handling
----------------
The bareudp device supports special handling for MPLS & IP as they can have
multiple ethertypes.
MPLS procotcol can have ethertypes ETH_P_MPLS_UC  (unicast) & ETH_P_MPLS_MC (multicast).
IP protocol can have ethertypes ETH_P_IP (v4) & ETH_P_IPV6 (v6).
This special handling can be enabled only for ethertypes ETH_P_IP & ETH_P_MPLS_UC
with a flag called multiproto mode.

Usage
------

1) Device creation & deletion

    a) ip link add dev bareudp0 type bareudp dstport 6635 ethertype 0x8847.

       This creates a bareudp tunnel device which tunnels L3 traffic with ethertype
       0x8847 (MPLS traffic). The destination port of the UDP header will be set to
       6635.The device will listen on UDP port 6635 to receive traffic.

    b) ip link delete bareudp0

2) Device creation with multiple proto mode enabled

There are two ways to create a bareudp device for MPLS & IP with multiproto mode
enabled.

    a) ip link add dev  bareudp0 type bareudp dstport 6635 ethertype 0x8847 multiproto

    b) ip link add dev  bareudp0 type bareudp dstport 6635 ethertype mpls

3) Device Usage

The bareudp device could be used along with OVS or flower filter in TC.
The OVS or TC flower layer must set the tunnel information in SKB dst field before
sending packet buffer to the bareudp device for transmission. On reception the
bareudp device extracts and stores the tunnel information in SKB dst field before
passing the packet buffer to the network stack.

Why not FOU ?
------------
FOU by design does l4 encapsulation.It maps udp port to ipproto (IP protocol number for l4 protocol).
Bareudp acheives a generic l3 encapsulation.It maps udp port to l3 ethertype.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

Documentation/networking/bareudp.rst

+.. SPDX-License-Identifier: GPL-2.0
+
+========================================
+Bare UDP Tunnelling Module Documentation
+========================================
+
+There are various L3 encapsulation standards using UDP being discussed to
+leverage the UDP based load balancing capability of different networks.
+MPLSoUDP (__ https://tools.ietf.org/html/rfc7510) is one among them.
+
+The Bareudp tunnel module provides a generic L3 encapsulation tunnelling
+support for tunnelling different L3 protocols like MPLS, IP, NSH etc. inside
+a UDP tunnel.
+
+Special Handling
+----------------
+The bareudp device supports special handling for MPLS & IP as they can have
+multiple ethertypes.
+MPLS procotcol can have ethertypes ETH_P_MPLS_UC  (unicast) & ETH_P_MPLS_MC (multicast).
+IP protocol can have ethertypes ETH_P_IP (v4) & ETH_P_IPV6 (v6).
+This special handling can be enabled only for ethertypes ETH_P_IP & ETH_P_MPLS_UC
+with a flag called multiproto mode.
+
+Usage
+------
+
+1) Device creation & deletion
+
+    a) ip link add dev bareudp0 type bareudp dstport 6635 ethertype 0x8847.
+
+       This creates a bareudp tunnel device which tunnels L3 traffic with ethertype
+       0x8847 (MPLS traffic). The destination port of the UDP header will be set to
+       6635.The device will listen on UDP port 6635 to receive traffic.
+
+    b) ip link delete bareudp0
+
+2) Device creation with multiple proto mode enabled
+
+There are two ways to create a bareudp device for MPLS & IP with multiproto mode
+enabled.
+
+    a) ip link add dev  bareudp0 type bareudp dstport 6635 ethertype 0x8847 multiproto
+
+    b) ip link add dev  bareudp0 type bareudp dstport 6635 ethertype mpls
+
+3) Device Usage
+
+The bareudp device could be used along with OVS or flower filter in TC.
+The OVS or TC flower layer must set the tunnel information in SKB dst field before
+sending packet buffer to the bareudp device for transmission. On reception the
+bareudp device extracts and stores the tunnel information in SKB dst field before
+passing the packet buffer to the network stack.

Documentation/networking/index.rst

@@ -8,6 +8,7 @@ Contents:
 
    netdev-FAQ
    af_xdp
+   bareudp
    batman-adv
    can
    can_ucan_protocol

drivers/net/Kconfig

@@ -258,6 +258,19 @@ config GENEVE
 	  To compile this driver as a module, choose M here: the module
 	  will be called geneve.
 
+config BAREUDP
+       tristate "Bare UDP Encapsulation"
+       depends on INET
+       depends on IPV6 || !IPV6
+       select NET_UDP_TUNNEL
+       select GRO_CELLS
+       help
+          This adds a bare UDP tunnel module for tunnelling different
+          kinds of traffic like MPLS, IP, etc. inside a UDP tunnel.
+
+          To compile this driver as a module, choose M here: the module
+          will be called bareudp.
+
 config GTP
 	tristate "GPRS Tunneling Protocol datapath (GTP-U)"
 	depends on INET

drivers/net/Makefile

@@ -29,6 +29,7 @@ obj-$(CONFIG_VETH) += veth.o
 obj-$(CONFIG_VIRTIO_NET) += virtio_net.o
 obj-$(CONFIG_VXLAN) += vxlan.o
 obj-$(CONFIG_GENEVE) += geneve.o
+obj-$(CONFIG_BAREUDP) += bareudp.o
 obj-$(CONFIG_GTP) += gtp.o
 obj-$(CONFIG_NLMON) += nlmon.o
 obj-$(CONFIG_NET_VRF) += vrf.o

include/net/bareudp.h

+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __NET_BAREUDP_H
+#define __NET_BAREUDP_H
+
+#include <linux/types.h>
+#include <linux/skbuff.h>
+
+struct bareudp_conf {
+	__be16 ethertype;
+	__be16 port;
+	u16 sport_min;
+	bool multi_proto_mode;
+};
+
+struct net_device *bareudp_dev_create(struct net *net, const char *name,
+				      u8 name_assign_type,
+				      struct bareudp_conf *info);
+
+#endif

include/net/ipv6.h

@@ -1027,6 +1027,12 @@ struct dst_entry *ip6_dst_lookup_flow(struct net *net, const struct sock *sk, st
 struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
 					 const struct in6_addr *final_dst,
 					 bool connected);
+struct dst_entry *ip6_dst_lookup_tunnel(struct sk_buff *skb,
+					struct net_device *dev,
+					struct net *net, struct socket *sock,
+					struct in6_addr *saddr,
+					const struct ip_tunnel_info *info,
+					u8 protocol, bool use_cache);
 struct dst_entry *ip6_blackhole_route(struct net *net,
 				      struct dst_entry *orig_dst);
 

include/net/route.h

@@ -128,6 +128,12 @@ static inline struct rtable *__ip_route_output_key(struct net *net,
 
 struct rtable *ip_route_output_flow(struct net *, struct flowi4 *flp,
 				    const struct sock *sk);
+struct rtable *ip_route_output_tunnel(struct sk_buff *skb,
+				      struct net_device *dev,
+				      struct net *net, __be32 *saddr,
+				      const struct ip_tunnel_info *info,
+				      u8 protocol, bool use_cache);
+
 struct dst_entry *ipv4_blackhole_route(struct net *net,
 				       struct dst_entry *dst_orig);
 

include/uapi/linux/if_link.h

@@ -590,6 +590,18 @@ enum ifla_geneve_df {
 	GENEVE_DF_MAX = __GENEVE_DF_END - 1,
 };
 
+/* Bareudp section  */
+enum {
+	IFLA_BAREUDP_UNSPEC,
+	IFLA_BAREUDP_PORT,
+	IFLA_BAREUDP_ETHERTYPE,
+	IFLA_BAREUDP_SRCPORT_MIN,
+	IFLA_BAREUDP_MULTIPROTO_MODE,
+	__IFLA_BAREUDP_MAX
+};
+
+#define IFLA_BAREUDP_MAX (__IFLA_BAREUDP_MAX - 1)
+
 /* PPP section */
 enum {
 	IFLA_PPP_UNSPEC,

net/ipv4/route.c

@@ -2774,6 +2774,54 @@ struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4,
 }
 EXPORT_SYMBOL_GPL(ip_route_output_flow);
 
+struct rtable *ip_route_output_tunnel(struct sk_buff *skb,
+				      struct net_device *dev,
+				      struct net *net, __be32 *saddr,
+				      const struct ip_tunnel_info *info,
+				      u8 protocol, bool use_cache)
+{
+#ifdef CONFIG_DST_CACHE
+	struct dst_cache *dst_cache;
+#endif
+	struct rtable *rt = NULL;
+	struct flowi4 fl4;
+	__u8 tos;
+
+#ifdef CONFIG_DST_CACHE
+	dst_cache = (struct dst_cache *)&info->dst_cache;
+	if (use_cache) {
+		rt = dst_cache_get_ip4(dst_cache, saddr);
+		if (rt)
+			return rt;
+	}
+#endif
+	memset(&fl4, 0, sizeof(fl4));
+	fl4.flowi4_mark = skb->mark;
+	fl4.flowi4_proto = protocol;
+	fl4.daddr = info->key.u.ipv4.dst;
+	fl4.saddr = info->key.u.ipv4.src;
+	tos = info->key.tos;
+	fl4.flowi4_tos = RT_TOS(tos);
+
+	rt = ip_route_output_key(net, &fl4);
+	if (IS_ERR(rt)) {
+		netdev_dbg(dev, "no route to %pI4\n", &fl4.daddr);
+		return ERR_PTR(-ENETUNREACH);
+	}
+	if (rt->dst.dev == dev) { /* is this necessary? */
+		netdev_dbg(dev, "circular route to %pI4\n", &fl4.daddr);
+		ip_rt_put(rt);
+		return ERR_PTR(-ELOOP);
+	}
+#ifdef CONFIG_DST_CACHE
+	if (use_cache)
+		dst_cache_set_ip4(dst_cache, &rt->dst, fl4.saddr);
+#endif
+	*saddr = fl4.saddr;
+	return rt;
+}
+EXPORT_SYMBOL_GPL(ip_route_output_tunnel);
+
 /* called with rcu_read_lock held */
 static int rt_fill_info(struct net *net, __be32 dst, __be32 src,
 			struct rtable *rt, u32 table_id, struct flowi4 *fl4,

net/ipv6/ip6_output.c

@@ -54,6 +54,7 @@
 #include <linux/mroute6.h>
 #include <net/l3mdev.h>
 #include <net/lwtunnel.h>
+#include <net/ip_tunnels.h>
 
 static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
@@ -1196,6 +1197,75 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
 }
 EXPORT_SYMBOL_GPL(ip6_sk_dst_lookup_flow);
 
+/**
+ *      ip6_dst_lookup_tunnel - perform route lookup on tunnel
+ *      @skb: Packet for which lookup is done
+ *      @dev: Tunnel device
+ *      @net: Network namespace of tunnel device
+ *      @sk: Socket which provides route info
+ *      @saddr: Memory to store the src ip address
+ *      @info: Tunnel information
+ *      @protocol: IP protocol
+ *      @use_cahce: Flag to enable cache usage
+ *      This function performs a route lookup on a tunnel
+ *
+ *      It returns a valid dst pointer and stores src address to be used in
+ *      tunnel in param saddr on success, else a pointer encoded error code.
+ */
+
+struct dst_entry *ip6_dst_lookup_tunnel(struct sk_buff *skb,
+					struct net_device *dev,
+					struct net *net,
+					struct socket *sock,
+					struct in6_addr *saddr,
+					const struct ip_tunnel_info *info,
+					u8 protocol,
+					bool use_cache)
+{
+	struct dst_entry *dst = NULL;
+#ifdef CONFIG_DST_CACHE
+	struct dst_cache *dst_cache;
+#endif
+	struct flowi6 fl6;
+	__u8 prio;
+
+#ifdef CONFIG_DST_CACHE
+	dst_cache = (struct dst_cache *)&info->dst_cache;
+	if (use_cache) {
+		dst = dst_cache_get_ip6(dst_cache, saddr);
+		if (dst)
+			return dst;
+	}
+#endif
+	memset(&fl6, 0, sizeof(fl6));
+	fl6.flowi6_mark = skb->mark;
+	fl6.flowi6_proto = protocol;
+	fl6.daddr = info->key.u.ipv6.dst;
+	fl6.saddr = info->key.u.ipv6.src;
+	prio = info->key.tos;
+	fl6.flowlabel = ip6_make_flowinfo(RT_TOS(prio),
+					  info->key.label);
+
+	dst = ipv6_stub->ipv6_dst_lookup_flow(net, sock->sk, &fl6,
+					      NULL);
+	if (IS_ERR(dst)) {
+		netdev_dbg(dev, "no route to %pI6\n", &fl6.daddr);
+		return ERR_PTR(-ENETUNREACH);
+	}
+	if (dst->dev == dev) { /* is this necessary? */
+		netdev_dbg(dev, "circular route to %pI6\n", &fl6.daddr);
+		dst_release(dst);
+		return ERR_PTR(-ELOOP);
+	}
+#ifdef CONFIG_DST_CACHE
+	if (use_cache)
+		dst_cache_set_ip6(dst_cache, dst, &fl6.saddr);
+#endif
+	*saddr = fl6.saddr;
+	return dst;
+}
+EXPORT_SYMBOL_GPL(ip6_dst_lookup_tunnel);
+
 static inline struct ipv6_opt_hdr *ip6_opt_dup(struct ipv6_opt_hdr *src,
 					       gfp_t gfp)
 {