soreuseport: TCP/IPv6 implementation

Motivation for soreuseport would be something like a web server
binding to port 80 running with multiple threads, where each thread
might have it's own listener socket.  This could be done as an
alternative to other models: 1) have one listener thread which
dispatches completed connections to workers. 2) accept on a single
listener socket from multiple threads.  In case #1 the listener thread
can easily become the bottleneck with high connection turn-over rate.
In case #2, the proportion of connections accepted per thread tends
to be uneven under high connection load (assuming simple event loop:
while (1) { accept(); process() }, wakeup does not promote fairness
among the sockets.  We have seen the  disproportion to be as high
as 3:1 ratio between thread accepting most connections and the one
accepting the fewest.  With so_reusport the distribution is
uniform.

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 16 insertions, 3 deletions

diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index dea17fd28e5..32b4a1675d8 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -158,25 +158,38 @@ static inline int compute_score(struct sock *sk, struct net *net,
 }
 
 struct sock *inet6_lookup_listener(struct net *net,
-		struct inet_hashinfo *hashinfo, const struct in6_addr *daddr,
+		struct inet_hashinfo *hashinfo, const struct in6_addr *saddr,
+		const __be16 sport, const struct in6_addr *daddr,
 		const unsigned short hnum, const int dif)
 {
 	struct sock *sk;
 	const struct hlist_nulls_node *node;
 	struct sock *result;
-	int score, hiscore;
+	int score, hiscore, matches = 0, reuseport = 0;
+	u32 phash = 0;
 	unsigned int hash = inet_lhashfn(net, hnum);
 	struct inet_listen_hashbucket *ilb = &hashinfo->listening_hash[hash];
 
 	rcu_read_lock();
 begin:
 	result = NULL;
-	hiscore = -1;
+	hiscore = 0;
 	sk_nulls_for_each(sk, node, &ilb->head) {
 		score = compute_score(sk, net, hnum, daddr, dif);
 		if (score > hiscore) {
 			hiscore = score;
 			result = sk;
+			reuseport = sk->sk_reuseport;
+			if (reuseport) {
+				phash = inet6_ehashfn(net, daddr, hnum,
+						      saddr, sport);
+				matches = 1;
+			}
+		} else if (score == hiscore && reuseport) {
+			matches++;
+			if (((u64)phash * matches) >> 32 == 0)
+				result = sk;
+			phash = next_pseudo_random32(phash);
 		}
 	}
 	/*