Merge branch 'sk_txhash'

Tom Herbert says:

====================
net: Initialize sk_hash to random value and reset for failing cnxs

This patch set implements a common function to simply set sk_txhash to
a random number instead of going through the trouble to call flow
dissector. From dst_negative_advice we now reset the sk_txhash in hopes
of finding a better ECMP path through the network. Changing sk_txhash
affects:
  - IPv6 flow label and UDP source port which affect ECMP in the network
  - Local ECMP route selection (pending changes to use sk_txhash)
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/ip.h

@@ -370,22 +370,6 @@ static inline void iph_to_flow_copy_v4addrs(struct flow_keys *flow,
 	flow->control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
 }
 
-static inline void inet_set_txhash(struct sock *sk)
-{
-	struct inet_sock *inet = inet_sk(sk);
-	struct flow_keys keys;
-
-	memset(&keys, 0, sizeof(keys));
-
-	keys.addrs.v4addrs.src = inet->inet_saddr;
-	keys.addrs.v4addrs.dst = inet->inet_daddr;
-	keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
-	keys.ports.src = inet->inet_sport;
-	keys.ports.dst = inet->inet_dport;
-
-	sk->sk_txhash = flow_hash_from_keys(&keys);
-}
-
 static inline __wsum inet_gro_compute_pseudo(struct sk_buff *skb, int proto)
 {
 	const struct iphdr *iph = skb_gro_network_header(skb);

include/net/ipv6.h

@@ -707,25 +707,6 @@ static inline void iph_to_flow_copy_v6addrs(struct flow_keys *flow,
 }
 
 #if IS_ENABLED(CONFIG_IPV6)
-static inline void ip6_set_txhash(struct sock *sk)
-{
-	struct inet_sock *inet = inet_sk(sk);
-	struct ipv6_pinfo *np = inet6_sk(sk);
-	struct flow_keys keys;
-
-	memset(&keys, 0, sizeof(keys));
-
-	memcpy(&keys.addrs.v6addrs.src, &np->saddr,
-	       sizeof(keys.addrs.v6addrs.src));
-	memcpy(&keys.addrs.v6addrs.dst, &sk->sk_v6_daddr,
-	       sizeof(keys.addrs.v6addrs.dst));
-	keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
-	keys.ports.src = inet->inet_sport;
-	keys.ports.dst = inet->inet_dport;
-
-	sk->sk_txhash = flow_hash_from_keys(&keys);
-}
-
 static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb,
 					__be32 flowlabel, bool autolabel)
 {

include/net/sock.h

@@ -1687,6 +1687,20 @@ static inline void sock_graft(struct sock *sk, struct socket *parent)
 kuid_t sock_i_uid(struct sock *sk);
 unsigned long sock_i_ino(struct sock *sk);
 
+static inline void sk_set_txhash(struct sock *sk)
+{
+	sk->sk_txhash = prandom_u32();
+
+	if (unlikely(!sk->sk_txhash))
+		sk->sk_txhash = 1;
+}
+
+static inline void sk_rethink_txhash(struct sock *sk)
+{
+	if (sk->sk_txhash)
+		sk_set_txhash(sk);
+}
+
 static inline struct dst_entry *
 __sk_dst_get(struct sock *sk)
 {
@@ -1711,6 +1725,8 @@ static inline void dst_negative_advice(struct sock *sk)
 {
 	struct dst_entry *ndst, *dst = __sk_dst_get(sk);
 
+	sk_rethink_txhash(sk);
+
 	if (dst && dst->ops->negative_advice) {
 		ndst = dst->ops->negative_advice(dst);
 

net/ipv4/datagram.c

@@ -74,7 +74,7 @@ int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len
 	inet->inet_daddr = fl4->daddr;
 	inet->inet_dport = usin->sin_port;
 	sk->sk_state = TCP_ESTABLISHED;
-	inet_set_txhash(sk);
+	sk_set_txhash(sk);
 	inet->inet_id = jiffies;
 
 	sk_dst_set(sk, &rt->dst);

net/ipv4/tcp_ipv4.c

@@ -222,7 +222,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	if (err)
 		goto failure;
 
-	inet_set_txhash(sk);
+	sk_set_txhash(sk);
 
 	rt = ip_route_newports(fl4, rt, orig_sport, orig_dport,
 			       inet->inet_sport, inet->inet_dport, sk);
@@ -1277,7 +1277,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 	newinet->mc_ttl	      = ip_hdr(skb)->ttl;
 	newinet->rcv_tos      = ip_hdr(skb)->tos;
 	inet_csk(newsk)->icsk_ext_hdr_len = 0;
-	inet_set_txhash(newsk);
+	sk_set_txhash(newsk);
 	if (inet_opt)
 		inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen;
 	newinet->inet_id = newtp->write_seq ^ jiffies;

net/ipv6/datagram.c

@@ -199,7 +199,7 @@ ipv4_connected:
 		      NULL);
 
 	sk->sk_state = TCP_ESTABLISHED;
-	ip6_set_txhash(sk);
+	sk_set_txhash(sk);
 out:
 	fl6_sock_release(flowlabel);
 	return err;

net/ipv6/tcp_ipv6.c

@@ -276,7 +276,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	if (err)
 		goto late_failure;
 
-	ip6_set_txhash(sk);
+	sk_set_txhash(sk);
 
 	if (!tp->write_seq && likely(!tp->repair))
 		tp->write_seq = secure_tcpv6_sequence_number(np->saddr.s6_addr32,
@@ -1090,7 +1090,7 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 	newsk->sk_v6_rcv_saddr = ireq->ir_v6_loc_addr;
 	newsk->sk_bound_dev_if = ireq->ir_iif;
 
-	ip6_set_txhash(newsk);
+	sk_set_txhash(newsk);
 
 	/* Now IPv6 options...