udp_tunnel: create a fastpath GRO lookup.

Most UDP tunnels bind a socket to a local port, with ANY address, no
peer and no interface index specified.
Additionally it's quite common to have a single tunnel device per
namespace.

Track in each namespace the UDP tunnel socket respecting the above.
When only a single one is present, store a reference in the netns.

When such reference is not NULL, UDP tunnel GRO lookup just need to
match the incoming packet destination port vs the socket local port.

The tunnel socket never sets the reuse[port] flag[s]. When bound to no
address and interface, no other socket can exist in the same netns
matching the specified local port.

Matching packets with non-local destination addresses will be
aggregated, and eventually segmented as needed - no behavior changes
intended.

Note that the UDP tunnel socket reference is stored into struct
netns_ipv4 for both IPv4 and IPv6 tunnels. That is intentional to keep
all the fastpath-related netns fields in the same struct and allow
cacheline-based optimization. Currently both the IPv4 and IPv6 socket
pointer share the same cacheline as the `udp_table` field.

Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/4d5c319c4471161829f50cb8436841de81a5edae.1741718157.git.pabeni@redhat.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

3 files changed, 30 insertions, 0 deletions

diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 650b2dc9199f..6373e3f17da8 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -47,6 +47,11 @@ struct sysctl_fib_multipath_hash_seed {
 };
 #endif
 
+struct udp_tunnel_gro {
+	struct sock __rcu *sk;
+	struct hlist_head list;
+};
+
 struct netns_ipv4 {
 	/* Cacheline organization can be found documented in
 	 * Documentation/networking/net_cachelines/netns_ipv4_sysctl.rst.
@@ -85,6 +90,11 @@ struct netns_ipv4 {
 	struct inet_timewait_death_row tcp_death_row;
 	struct udp_table *udp_table;
 
+#if IS_ENABLED(CONFIG_NET_UDP_TUNNEL)
+	/* Not in a pernet subsys because need to be available at GRO stage */
+	struct udp_tunnel_gro udp_tunnel_gro[2];
+#endif
+
 #ifdef CONFIG_SYSCTL
 	struct ctl_table_header	*forw_hdr;
 	struct ctl_table_header	*frags_hdr;
@@ -277,4 +287,5 @@ struct netns_ipv4 {
 	struct hlist_head	*inet_addr_lst;
 	struct delayed_work	addr_chk_work;
 };
+
 #endif
diff --git a/include/net/udp.h b/include/net/udp.h
index 6e89520e100d..a772510b2aa5 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -290,6 +290,7 @@ static inline void udp_lib_init_sock(struct sock *sk)
 	struct udp_sock *up = udp_sk(sk);
 
 	skb_queue_head_init(&up->reader_queue);
+	INIT_HLIST_NODE(&up->tunnel_list);
 	up->forward_threshold = sk->sk_rcvbuf >> 2;
 	set_bit(SOCK_CUSTOM_SOCKOPT, &sk->sk_socket->flags);
 }
diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h
index a93dc51f6323..eda0f3e2f65f 100644
--- a/include/net/udp_tunnel.h
+++ b/include/net/udp_tunnel.h
@@ -203,6 +203,24 @@ static inline void udp_tunnel_encap_enable(struct sock *sk)
 	udp_encap_enable();
 }
 
+#if IS_ENABLED(CONFIG_NET_UDP_TUNNEL)
+void udp_tunnel_update_gro_lookup(struct net *net, struct sock *sk, bool add);
+#else
+static inline void udp_tunnel_update_gro_lookup(struct net *net,
+						struct sock *sk, bool add) {}
+#endif
+
+static inline void udp_tunnel_cleanup_gro(struct sock *sk)
+{
+	struct udp_sock *up = udp_sk(sk);
+	struct net *net = sock_net(sk);
+
+	if (!up->tunnel_list.pprev)
+		return;
+
+	udp_tunnel_update_gro_lookup(net, sk, false);
+}
+
 #define UDP_TUNNEL_NIC_MAX_TABLES	4
 
 enum udp_tunnel_nic_info_flags {