Merge branch 'tcp-even-faster-connect-under-stress'

Eric Dumazet says:

====================
tcp: even faster connect() under stress

This is a followup on the prior series, "tcp: scale connect() under pressure"

Now spinlocks are no longer in the picture, we see a very high cost
of the inet6_ehashfn() function.

In this series (of 2), I change how lport contributes to inet6_ehashfn()
to ensure better cache locality and call inet6_ehashfn()
only once per connect() system call.

This brings an additional 229 % increase of performance
for "neper/tcp_crr -6 -T 200 -F 30000" stress test,
while greatly improving latency metrics.

Before:
  latency_min=0.014131929
  latency_max=17.895073144
  latency_mean=0.505675853
  latency_stddev=2.125164772
  num_samples=307884
  throughput=139866.80

After:
  latency_min=0.003041375
  latency_max=7.056589232
  latency_mean=0.141075048
  latency_stddev=0.526900516
  num_samples=312996
  throughput=320677.21
====================

Link: https://patch.msgid.link/20250305034550.879255-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

include/net/inet_hashtables.h

@@ -527,10 +527,12 @@ static inline void sk_rcv_saddr_set(struct sock *sk, __be32 addr)
 
 int __inet_hash_connect(struct inet_timewait_death_row *death_row,
 			struct sock *sk, u64 port_offset,
+			u32 hash_port0,
 			int (*check_established)(struct inet_timewait_death_row *,
 						 struct sock *, __u16,
 						 struct inet_timewait_sock **,
-						 bool rcu_lookup));
+						 bool rcu_lookup,
+						 u32 hash));
 
 int inet_hash_connect(struct inet_timewait_death_row *death_row,
 		      struct sock *sk);

include/net/ip.h

@@ -357,7 +357,7 @@ static inline void inet_get_local_port_range(const struct net *net, int *low, in
 bool inet_sk_get_local_port_range(const struct sock *sk, int *low, int *high);
 
 #ifdef CONFIG_SYSCTL
-static inline bool inet_is_local_reserved_port(struct net *net, unsigned short port)
+static inline bool inet_is_local_reserved_port(const struct net *net, unsigned short port)
 {
 	if (!net->ipv4.sysctl_local_reserved_ports)
 		return false;

net/ipv4/inet_hashtables.c

@@ -35,8 +35,8 @@ u32 inet_ehashfn(const struct net *net, const __be32 laddr,
 {
 	net_get_random_once(&inet_ehash_secret, sizeof(inet_ehash_secret));
 
-	return __inet_ehashfn(laddr, lport, faddr, fport,
-			      inet_ehash_secret + net_hash_mix(net));
+	return lport + __inet_ehashfn(laddr, 0, faddr, fport,
+				      inet_ehash_secret + net_hash_mix(net));
 }
 EXPORT_SYMBOL_GPL(inet_ehashfn);
 
@@ -538,7 +538,8 @@ EXPORT_SYMBOL_GPL(__inet_lookup_established);
 static int __inet_check_established(struct inet_timewait_death_row *death_row,
 				    struct sock *sk, __u16 lport,
 				    struct inet_timewait_sock **twp,
-				    bool rcu_lookup)
+				    bool rcu_lookup,
+				    u32 hash)
 {
 	struct inet_hashinfo *hinfo = death_row->hashinfo;
 	struct inet_sock *inet = inet_sk(sk);
@@ -549,8 +550,6 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row,
 	int sdif = l3mdev_master_ifindex_by_index(net, dif);
 	INET_ADDR_COOKIE(acookie, saddr, daddr);
 	const __portpair ports = INET_COMBINED_PORTS(inet->inet_dport, lport);
-	unsigned int hash = inet_ehashfn(net, daddr, lport,
-					 saddr, inet->inet_dport);
 	struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash);
 	struct inet_timewait_sock *tw = NULL;
 	const struct hlist_nulls_node *node;
@@ -1007,9 +1006,10 @@ static u32 *table_perturb;
 
 int __inet_hash_connect(struct inet_timewait_death_row *death_row,
 		struct sock *sk, u64 port_offset,
+		u32 hash_port0,
 		int (*check_established)(struct inet_timewait_death_row *,
 			struct sock *, __u16, struct inet_timewait_sock **,
-			bool rcu_lookup))
+			bool rcu_lookup, u32 hash))
 {
 	struct inet_hashinfo *hinfo = death_row->hashinfo;
 	struct inet_bind_hashbucket *head, *head2;
@@ -1027,7 +1027,8 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
 
 	if (port) {
 		local_bh_disable();
-		ret = check_established(death_row, sk, port, NULL, false);
+		ret = check_established(death_row, sk, port, NULL, false,
+					hash_port0 + port);
 		local_bh_enable();
 		return ret;
 	}
@@ -1071,7 +1072,8 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
 				rcu_read_unlock();
 				goto next_port;
 			}
-			if (!check_established(death_row, sk, port, &tw, true))
+			if (!check_established(death_row, sk, port, &tw, true,
+					       hash_port0 + port))
 				break;
 			rcu_read_unlock();
 			goto next_port;
@@ -1090,7 +1092,8 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
 					goto next_port_unlock;
 				WARN_ON(hlist_empty(&tb->bhash2));
 				if (!check_established(death_row, sk,
-						       port, &tw, false))
+						       port, &tw, false,
+						       hash_port0 + port))
 					goto ok;
 				goto next_port_unlock;
 			}
@@ -1197,11 +1200,18 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
 int inet_hash_connect(struct inet_timewait_death_row *death_row,
 		      struct sock *sk)
 {
+	const struct inet_sock *inet = inet_sk(sk);
+	const struct net *net = sock_net(sk);
 	u64 port_offset = 0;
+	u32 hash_port0;
 
 	if (!inet_sk(sk)->inet_num)
 		port_offset = inet_sk_port_offset(sk);
-	return __inet_hash_connect(death_row, sk, port_offset,
+
+	hash_port0 = inet_ehashfn(net, inet->inet_rcv_saddr, 0,
+				  inet->inet_daddr, inet->inet_dport);
+
+	return __inet_hash_connect(death_row, sk, port_offset, hash_port0,
 				   __inet_check_established);
 }
 EXPORT_SYMBOL_GPL(inet_hash_connect);

net/ipv6/inet6_hashtables.c

@@ -35,8 +35,8 @@ u32 inet6_ehashfn(const struct net *net,
 	lhash = (__force u32)laddr->s6_addr32[3];
 	fhash = __ipv6_addr_jhash(faddr, tcp_ipv6_hash_secret);
 
-	return __inet6_ehashfn(lhash, lport, fhash, fport,
-			       inet6_ehash_secret + net_hash_mix(net));
+	return lport + __inet6_ehashfn(lhash, 0, fhash, fport,
+				       inet6_ehash_secret + net_hash_mix(net));
 }
 EXPORT_SYMBOL_GPL(inet6_ehashfn);
 
@@ -264,7 +264,8 @@ EXPORT_SYMBOL_GPL(inet6_lookup);
 static int __inet6_check_established(struct inet_timewait_death_row *death_row,
 				     struct sock *sk, const __u16 lport,
 				     struct inet_timewait_sock **twp,
-				     bool rcu_lookup)
+				     bool rcu_lookup,
+				     u32 hash)
 {
 	struct inet_hashinfo *hinfo = death_row->hashinfo;
 	struct inet_sock *inet = inet_sk(sk);
@@ -274,8 +275,6 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row,
 	struct net *net = sock_net(sk);
 	const int sdif = l3mdev_master_ifindex_by_index(net, dif);
 	const __portpair ports = INET_COMBINED_PORTS(inet->inet_dport, lport);
-	const unsigned int hash = inet6_ehashfn(net, daddr, lport, saddr,
-						inet->inet_dport);
 	struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash);
 	struct inet_timewait_sock *tw = NULL;
 	const struct hlist_nulls_node *node;
@@ -354,11 +353,19 @@ static u64 inet6_sk_port_offset(const struct sock *sk)
 int inet6_hash_connect(struct inet_timewait_death_row *death_row,
 		       struct sock *sk)
 {
+	const struct in6_addr *daddr = &sk->sk_v6_rcv_saddr;
+	const struct in6_addr *saddr = &sk->sk_v6_daddr;
+	const struct inet_sock *inet = inet_sk(sk);
+	const struct net *net = sock_net(sk);
 	u64 port_offset = 0;
+	u32 hash_port0;
 
 	if (!inet_sk(sk)->inet_num)
 		port_offset = inet6_sk_port_offset(sk);
-	return __inet_hash_connect(death_row, sk, port_offset,
+
+	hash_port0 = inet6_ehashfn(net, daddr, 0, saddr, inet->inet_dport);
+
+	return __inet_hash_connect(death_row, sk, port_offset, hash_port0,
 				   __inet6_check_established);
 }
 EXPORT_SYMBOL_GPL(inet6_hash_connect);