Merge branch 'udp_tunnel-gro-optimizations'

Paolo Abeni says:

====================
udp_tunnel: GRO optimizations

The UDP tunnel GRO stage is source of measurable overhead for workload
based on UDP-encapsulated traffic: each incoming packets requires a full
UDP socket lookup and an indirect call.

In the most common setups a single UDP tunnel device is used. In such
case we can optimize both the lookup and the indirect call.

Patch 1 tracks per netns the active UDP tunnels and replaces the socket
lookup with a single destination port comparison when possible.

Patch 2 tracks the different types of UDP tunnels and replaces the
indirect call with a static one when there is a single UDP tunnel type
active.

I measure ~5% performance improvement in TCP over UDP tunnel stream
tests on top of this series.

v3: https://lore.kernel.org/netdev/cover.1741632298.git.pabeni@redhat.com/
v2: https://lore.kernel.org/netdev/cover.1741338765.git.pabeni@redhat.com/
v1: https://lore.kernel.org/netdev/cover.1741275846.git.pabeni@redhat.com/
====================

Link: https://patch.msgid.link/cover.1741718157.git.pabeni@redhat.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

4 files changed, 50 insertions, 0 deletions

diff --git a/include/linux/udp.h b/include/linux/udp.h
index 0807e21cfec9..895240177f4f 100644
--- a/include/linux/udp.h
+++ b/include/linux/udp.h
@@ -101,6 +101,13 @@ struct udp_sock {
 
 	/* Cache friendly copy of sk->sk_peek_off >= 0 */
 	bool		peeking_with_offset;
+
+	/*
+	 * Accounting for the tunnel GRO fastpath.
+	 * Unprotected by compilers guard, as it uses space available in
+	 * the last UDP socket cacheline.
+	 */
+	struct hlist_node	tunnel_list;
 };
 
 #define udp_test_bit(nr, sk)			\
@@ -219,4 +226,13 @@ static inline void udp_allow_gso(struct sock *sk)
 
 #define IS_UDPLITE(__sk) (__sk->sk_protocol == IPPROTO_UDPLITE)
 
+static inline struct sock *udp_tunnel_sk(const struct net *net, bool is_ipv6)
+{
+#if IS_ENABLED(CONFIG_NET_UDP_TUNNEL)
+	return rcu_dereference(net->ipv4.udp_tunnel_gro[is_ipv6].sk);
+#else
+	return NULL;
+#endif
+}
+
 #endif	/* _LINUX_UDP_H */
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..a7b230867eb1 100644
--- a/include/net/udp_tunnel.h
+++ b/include/net/udp_tunnel.h
@@ -203,6 +203,28 @@ 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);
+void udp_tunnel_update_gro_rcv(struct sock *sk, bool add);
+#else
+static inline void udp_tunnel_update_gro_lookup(struct net *net,
+						struct sock *sk, bool add) {}
+static inline void udp_tunnel_update_gro_rcv(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);
+
+	udp_tunnel_update_gro_rcv(sk, false);
+
+	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 {