net: tcp: prefer listeners bound to an address

A relatively common use case is to have several IPs configured
on a host, and have different listeners for each of them. We would
like to add a "catch all" listener on addr_any, to match incoming
connections not served by any of the listeners bound to a specific
address.

However, port-only lookups can match addr_any sockets when sockets
listening on specific addresses are present if so_reuseport flag
is set. This patch eliminates lookups into port-only hashtable,
as lookups by (addr,port) tuple are easily available.

In addition, compute_score() is tweaked to _not_ match
addr_any sockets to specific addresses, as hash collisions
could result in the unwanted behavior described above.

Tested: the patch compiles; full test in the last patch in this
patchset. Existing reuseport_* selftests also pass.

Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Peter Oskolkov <posk@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 8 insertions, 52 deletions

diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 13890d5bfc34..cd03ab42705b 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -234,24 +234,16 @@ static inline int compute_score(struct sock *sk, struct net *net,
 				const int dif, const int sdif, bool exact_dif)
 {
 	int score = -1;
-	struct inet_sock *inet = inet_sk(sk);
-	bool dev_match;
 
-	if (net_eq(sock_net(sk), net) && inet->inet_num == hnum &&
+	if (net_eq(sock_net(sk), net) && sk->sk_num == hnum &&
 			!ipv6_only_sock(sk)) {
-		__be32 rcv_saddr = inet->inet_rcv_saddr;
-		score = sk->sk_family == PF_INET ? 2 : 1;
-		if (rcv_saddr) {
-			if (rcv_saddr != daddr)
-				return -1;
-			score += 4;
-		}
-		dev_match = inet_sk_bound_dev_eq(net, sk->sk_bound_dev_if,
-						 dif, sdif);
-		if (!dev_match)
+		if (sk->sk_rcv_saddr != daddr)
+			return -1;
+
+		if (!inet_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif))
 			return -1;
-		score += 4;
 
+		score = sk->sk_family == PF_INET ? 2 : 1;
 		if (sk->sk_incoming_cpu == raw_smp_processor_id())
 			score++;
 	}
@@ -307,26 +299,12 @@ struct sock *__inet_lookup_listener(struct net *net,
 				    const __be32 daddr, const unsigned short hnum,
 				    const int dif, const int sdif)
 {
-	unsigned int hash = inet_lhashfn(net, hnum);
-	struct inet_listen_hashbucket *ilb = &hashinfo->listening_hash[hash];
-	bool exact_dif = inet_exact_dif_match(net, skb);
 	struct inet_listen_hashbucket *ilb2;
-	struct sock *sk, *result = NULL;
-	int score, hiscore = 0;
+	struct sock *result = NULL;
 	unsigned int hash2;
-	u32 phash = 0;
-
-	if (ilb->count <= 10 || !hashinfo->lhash2)
-		goto port_lookup;
-
-	/* Too many sk in the ilb bucket (which is hashed by port alone).
-	 * Try lhash2 (which is hashed by port and addr) instead.
-	 */
 
 	hash2 = ipv4_portaddr_hash(net, daddr, hnum);
 	ilb2 = inet_lhash2_bucket(hashinfo, hash2);
-	if (ilb2->count > ilb->count)
-		goto port_lookup;
 
 	result = inet_lhash2_lookup(net, ilb2, skb, doff,
 				    saddr, sport, daddr, hnum,
@@ -335,34 +313,12 @@ struct sock *__inet_lookup_listener(struct net *net,
 		goto done;
 
 	/* Lookup lhash2 with INADDR_ANY */
-
 	hash2 = ipv4_portaddr_hash(net, htonl(INADDR_ANY), hnum);
 	ilb2 = inet_lhash2_bucket(hashinfo, hash2);
-	if (ilb2->count > ilb->count)
-		goto port_lookup;
 
 	result = inet_lhash2_lookup(net, ilb2, skb, doff,
-				    saddr, sport, daddr, hnum,
+				    saddr, sport, htonl(INADDR_ANY), hnum,
 				    dif, sdif);
-	goto done;
-
-port_lookup:
-	sk_for_each_rcu(sk, &ilb->head) {
-		score = compute_score(sk, net, hnum, daddr,
-				      dif, sdif, exact_dif);
-		if (score > hiscore) {
-			if (sk->sk_reuseport) {
-				phash = inet_ehashfn(net, daddr, hnum,
-						     saddr, sport);
-				result = reuseport_select_sock(sk, phash,
-							       skb, doff);
-				if (result)
-					goto done;
-			}
-			result = sk;
-			hiscore = score;
-		}
-	}
 done:
 	if (unlikely(IS_ERR(result)))
 		return NULL;