udp-tunnel: Add a few more UDP tunnel APIs

Added a few more UDP tunnel APIs that can be shared by UDP based
tunnel protocol implementation. The main ones are highlighted below.

setup_udp_tunnel_sock() configures UDP listener socket for
receiving UDP encapsulated packets.

udp_tunnel_xmit_skb() and upd_tunnel6_xmit_skb() transmit skb
using UDP encapsulation.

udp_tunnel_sock_release() closes the UDP tunnel listener socket.

Signed-off-by: Andy Zhou <azhou@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 151 insertions, 1 deletions

diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h
index 0b9e017c9038..a47790bcaa38 100644
--- a/include/net/udp_tunnel.h
+++ b/include/net/udp_tunnel.h
@@ -1,6 +1,14 @@
 #ifndef __NET_UDP_TUNNEL_H
 #define __NET_UDP_TUNNEL_H
 
+#include <net/ip_tunnels.h>
+#include <net/udp.h>
+
+#if IS_ENABLED(CONFIG_IPV6)
+#include <net/ipv6.h>
+#include <net/addrconf.h>
+#endif
+
 struct udp_port_cfg {
 	u8			family;
 
@@ -53,4 +61,53 @@ static inline int udp_sock_create(struct net *net,
 	return -EPFNOSUPPORT;
 }
 
+typedef int (*udp_tunnel_encap_rcv_t)(struct sock *sk, struct sk_buff *skb);
+typedef void (*udp_tunnel_encap_destroy_t)(struct sock *sk);
+
+struct udp_tunnel_sock_cfg {
+	void *sk_user_data;     /* user data used by encap_rcv call back */
+	/* Used for setting up udp_sock fields, see udp.h for details */
+	__u8  encap_type;
+	udp_tunnel_encap_rcv_t encap_rcv;
+	udp_tunnel_encap_destroy_t encap_destroy;
+};
+
+/* Setup the given (UDP) sock to receive UDP encapsulated packets */
+void setup_udp_tunnel_sock(struct net *net, struct socket *sock,
+			   struct udp_tunnel_sock_cfg *sock_cfg);
+
+/* Transmit the skb using UDP encapsulation. */
+int udp_tunnel_xmit_skb(struct socket *sock, struct rtable *rt,
+			struct sk_buff *skb, __be32 src, __be32 dst,
+			__u8 tos, __u8 ttl, __be16 df, __be16 src_port,
+			__be16 dst_port, bool xnet);
+
+#if IS_ENABLED(CONFIG_IPV6)
+int udp_tunnel6_xmit_skb(struct socket *sock, struct dst_entry *dst,
+			 struct sk_buff *skb, struct net_device *dev,
+			 struct in6_addr *saddr, struct in6_addr *daddr,
+			 __u8 prio, __u8 ttl, __be16 src_port,
+			 __be16 dst_port);
+#endif
+
+void udp_tunnel_sock_release(struct socket *sock);
+
+static inline struct sk_buff *udp_tunnel_handle_offloads(struct sk_buff *skb,
+							 bool udp_csum)
+{
+	int type = udp_csum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL;
+
+	return iptunnel_handle_offloads(skb, udp_csum, type);
+}
+
+static inline void udp_tunnel_encap_enable(struct socket *sock)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+	if (sock->sk->sk_family == PF_INET6)
+		ipv6_stub->udpv6_encap_enable();
+	else
+#endif
+		udp_encap_enable();
+}
+
 #endif
diff --git a/net/ipv4/udp_tunnel.c b/net/ipv4/udp_tunnel.c
index 7fccf6c3417a..1671263e5fa0 100644
--- a/net/ipv4/udp_tunnel.c
+++ b/net/ipv4/udp_tunnel.c
@@ -11,7 +11,7 @@
 int udp_sock_create4(struct net *net, struct udp_port_cfg *cfg,
 		     struct socket **sockp)
 {
-	int err = -EINVAL;
+	int err;
 	struct socket *sock = NULL;
 	struct sockaddr_in udp_addr;
 
@@ -54,4 +54,55 @@ error:
 }
 EXPORT_SYMBOL(udp_sock_create4);
 
+void setup_udp_tunnel_sock(struct net *net, struct socket *sock,
+			   struct udp_tunnel_sock_cfg *cfg)
+{
+	struct sock *sk = sock->sk;
+
+	/* Disable multicast loopback */
+	inet_sk(sk)->mc_loop = 0;
+
+	/* Enable CHECKSUM_UNNECESSARY to CHECKSUM_COMPLETE conversion */
+	udp_set_convert_csum(sk, true);
+
+	rcu_assign_sk_user_data(sk, cfg->sk_user_data);
+
+	udp_sk(sk)->encap_type = cfg->encap_type;
+	udp_sk(sk)->encap_rcv = cfg->encap_rcv;
+	udp_sk(sk)->encap_destroy = cfg->encap_destroy;
+
+	udp_tunnel_encap_enable(sock);
+}
+EXPORT_SYMBOL_GPL(setup_udp_tunnel_sock);
+
+int udp_tunnel_xmit_skb(struct socket *sock, struct rtable *rt,
+			struct sk_buff *skb, __be32 src, __be32 dst,
+			__u8 tos, __u8 ttl, __be16 df, __be16 src_port,
+			__be16 dst_port, bool xnet)
+{
+	struct udphdr *uh;
+
+	__skb_push(skb, sizeof(*uh));
+	skb_reset_transport_header(skb);
+	uh = udp_hdr(skb);
+
+	uh->dest = dst_port;
+	uh->source = src_port;
+	uh->len = htons(skb->len);
+
+	udp_set_csum(sock->sk->sk_no_check_tx, skb, src, dst, skb->len);
+
+	return iptunnel_xmit(sock->sk, rt, skb, src, dst, IPPROTO_UDP,
+			     tos, ttl, df, xnet);
+}
+EXPORT_SYMBOL_GPL(udp_tunnel_xmit_skb);
+
+void udp_tunnel_sock_release(struct socket *sock)
+{
+	rcu_assign_sk_user_data(sock->sk, NULL);
+	kernel_sock_shutdown(sock, SHUT_RDWR);
+	sk_release_kernel(sock->sk);
+}
+EXPORT_SYMBOL_GPL(udp_tunnel_sock_release);
+
 MODULE_LICENSE("GPL");
diff --git a/net/ipv6/ip6_udp_tunnel.c b/net/ipv6/ip6_udp_tunnel.c
index bcfbb4b496fc..cbc990712cc1 100644
--- a/net/ipv6/ip6_udp_tunnel.c
+++ b/net/ipv6/ip6_udp_tunnel.c
@@ -61,3 +61,45 @@ error:
 	return err;
 }
 EXPORT_SYMBOL_GPL(udp_sock_create6);
+
+int udp_tunnel6_xmit_skb(struct socket *sock, struct dst_entry *dst,
+			 struct sk_buff *skb, struct net_device *dev,
+			 struct in6_addr *saddr, struct in6_addr *daddr,
+			 __u8 prio, __u8 ttl, __be16 src_port, __be16 dst_port)
+{
+	struct udphdr *uh;
+	struct ipv6hdr *ip6h;
+	struct sock *sk = sock->sk;
+
+	__skb_push(skb, sizeof(*uh));
+	skb_reset_transport_header(skb);
+	uh = udp_hdr(skb);
+
+	uh->dest = dst_port;
+	uh->source = src_port;
+
+	uh->len = htons(skb->len);
+	uh->check = 0;
+
+	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
+	IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED
+			    | IPSKB_REROUTED);
+	skb_dst_set(skb, dst);
+
+	udp6_set_csum(udp_get_no_check6_tx(sk), skb, &inet6_sk(sk)->saddr,
+		      &sk->sk_v6_daddr, skb->len);
+
+	__skb_push(skb, sizeof(*ip6h));
+	skb_reset_network_header(skb);
+	ip6h		  = ipv6_hdr(skb);
+	ip6_flow_hdr(ip6h, prio, htonl(0));
+	ip6h->payload_len = htons(skb->len);
+	ip6h->nexthdr     = IPPROTO_UDP;
+	ip6h->hop_limit   = ttl;
+	ip6h->daddr	  = *daddr;
+	ip6h->saddr	  = *saddr;
+
+	ip6tunnel_xmit(skb, dev);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(udp_tunnel6_xmit_skb);