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.

Restrict the optimization to kernel sockets only: it covers all the
relevant use-cases, and user-space owned sockets could be disconnected
and rebound after setup_udp_tunnel_sock(), breaking the uniqueness
assumption

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.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/41d16bc8d1257d567f9344c445b4ae0b4a91ede4.1744040675.git.pabeni@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

5 files changed, 69 insertions, 1 deletions

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 2742cc7602bb..04cd3353f1d4 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2897,8 +2897,10 @@ void udp_destroy_sock(struct sock *sk)
 			if (encap_destroy)
 				encap_destroy(sk);
 		}
-		if (udp_test_bit(ENCAP_ENABLED, sk))
+		if (udp_test_bit(ENCAP_ENABLED, sk)) {
 			static_branch_dec(&udp_encap_needed_key);
+			udp_tunnel_cleanup_gro(sk);
+		}
 	}
 }
 
@@ -3810,6 +3812,15 @@ fallback:
 
 static int __net_init udp_pernet_init(struct net *net)
 {
+#if IS_ENABLED(CONFIG_NET_UDP_TUNNEL)
+	int i;
+
+	/* No tunnel is configured */
+	for (i = 0; i < ARRAY_SIZE(net->ipv4.udp_tunnel_gro); ++i) {
+		INIT_HLIST_HEAD(&net->ipv4.udp_tunnel_gro[i].list);
+		RCU_INIT_POINTER(net->ipv4.udp_tunnel_gro[i].sk, NULL);
+	}
+#endif
 	udp_sysctl_init(net);
 	udp_set_table(net);
 
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 2c0725583be3..69fc4eae8250 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -12,6 +12,38 @@
 #include <net/udp.h>
 #include <net/protocol.h>
 #include <net/inet_common.h>
+#include <net/udp_tunnel.h>
+
+#if IS_ENABLED(CONFIG_NET_UDP_TUNNEL)
+static DEFINE_SPINLOCK(udp_tunnel_gro_lock);
+
+void udp_tunnel_update_gro_lookup(struct net *net, struct sock *sk, bool add)
+{
+	bool is_ipv6 = sk->sk_family == AF_INET6;
+	struct udp_sock *tup, *up = udp_sk(sk);
+	struct udp_tunnel_gro *udp_tunnel_gro;
+
+	spin_lock(&udp_tunnel_gro_lock);
+	udp_tunnel_gro = &net->ipv4.udp_tunnel_gro[is_ipv6];
+	if (add)
+		hlist_add_head(&up->tunnel_list, &udp_tunnel_gro->list);
+	else if (up->tunnel_list.pprev)
+		hlist_del_init(&up->tunnel_list);
+
+	if (udp_tunnel_gro->list.first &&
+	    !udp_tunnel_gro->list.first->next) {
+		tup = hlist_entry(udp_tunnel_gro->list.first, struct udp_sock,
+				  tunnel_list);
+
+		rcu_assign_pointer(udp_tunnel_gro->sk, (struct sock *)tup);
+	} else {
+		RCU_INIT_POINTER(udp_tunnel_gro->sk, NULL);
+	}
+
+	spin_unlock(&udp_tunnel_gro_lock);
+}
+EXPORT_SYMBOL_GPL(udp_tunnel_update_gro_lookup);
+#endif
 
 static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
 	netdev_features_t features,
@@ -635,8 +667,13 @@ static struct sock *udp4_gro_lookup_skb(struct sk_buff *skb, __be16 sport,
 {
 	const struct iphdr *iph = skb_gro_network_header(skb);
 	struct net *net = dev_net_rcu(skb->dev);
+	struct sock *sk;
 	int iif, sdif;
 
+	sk = udp_tunnel_sk(net, false);
+	if (sk && dport == htons(sk->sk_num))
+		return sk;
+
 	inet_get_iif_sdif(skb, &iif, &sdif);
 
 	return __udp4_lib_lookup(net, iph->saddr, sport,
diff --git a/net/ipv4/udp_tunnel_core.c b/net/ipv4/udp_tunnel_core.c
index 619a53eb672d..3d1214e6df0e 100644
--- a/net/ipv4/udp_tunnel_core.c
+++ b/net/ipv4/udp_tunnel_core.c
@@ -58,6 +58,15 @@ error:
 }
 EXPORT_SYMBOL(udp_sock_create4);
 
+static bool sk_saddr_any(struct sock *sk)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+	return ipv6_addr_any(&sk->sk_v6_rcv_saddr);
+#else
+	return !sk->sk_rcv_saddr;
+#endif
+}
+
 void setup_udp_tunnel_sock(struct net *net, struct socket *sock,
 			   struct udp_tunnel_sock_cfg *cfg)
 {
@@ -80,6 +89,10 @@ void setup_udp_tunnel_sock(struct net *net, struct socket *sock,
 	udp_sk(sk)->gro_complete = cfg->gro_complete;
 
 	udp_tunnel_encap_enable(sk);
+
+	if (!sk->sk_dport && !sk->sk_bound_dev_if && sk_saddr_any(sk) &&
+	    sk->sk_kern_sock)
+		udp_tunnel_update_gro_lookup(net, sk, true);
 }
 EXPORT_SYMBOL_GPL(setup_udp_tunnel_sock);
 
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 024458ef163c..7317f8e053f1 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -46,6 +46,7 @@
 #include <net/tcp_states.h>
 #include <net/ip6_checksum.h>
 #include <net/ip6_tunnel.h>
+#include <net/udp_tunnel.h>
 #include <net/xfrm.h>
 #include <net/inet_hashtables.h>
 #include <net/inet6_hashtables.h>
@@ -1825,6 +1826,7 @@ void udpv6_destroy_sock(struct sock *sk)
 		if (udp_test_bit(ENCAP_ENABLED, sk)) {
 			static_branch_dec(&udpv6_encap_needed_key);
 			udp_encap_disable();
+			udp_tunnel_cleanup_gro(sk);
 		}
 	}
 }
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index 404212dfc99a..d8445ac1b2e4 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -118,8 +118,13 @@ static struct sock *udp6_gro_lookup_skb(struct sk_buff *skb, __be16 sport,
 {
 	const struct ipv6hdr *iph = skb_gro_network_header(skb);
 	struct net *net = dev_net_rcu(skb->dev);
+	struct sock *sk;
 	int iif, sdif;
 
+	sk = udp_tunnel_sk(net, true);
+	if (sk && dport == htons(sk->sk_num))
+		return sk;
+
 	inet6_get_iif_sdif(skb, &iif, &sdif);
 
 	return __udp6_lib_lookup(net, &iph->saddr, sport,