net: udp: 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, 19 insertions, 57 deletions

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index aff2a8e99e01..3fb0ed5e4789 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -380,15 +380,12 @@ static int compute_score(struct sock *sk, struct net *net,
 	    ipv6_only_sock(sk))
 		return -1;
 
-	score = (sk->sk_family == PF_INET) ? 2 : 1;
-	inet = inet_sk(sk);
+	if (sk->sk_rcv_saddr != daddr)
+		return -1;
 
-	if (inet->inet_rcv_saddr) {
-		if (inet->inet_rcv_saddr != daddr)
-			return -1;
-		score += 4;
-	}
+	score = (sk->sk_family == PF_INET) ? 2 : 1;
 
+	inet = inet_sk(sk);
 	if (inet->inet_daddr) {
 		if (inet->inet_daddr != saddr)
 			return -1;
@@ -464,65 +461,30 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr,
 		__be16 sport, __be32 daddr, __be16 dport, int dif,
 		int sdif, struct udp_table *udptable, struct sk_buff *skb)
 {
-	struct sock *sk, *result;
+	struct sock *result;
 	unsigned short hnum = ntohs(dport);
-	unsigned int hash2, slot2, slot = udp_hashfn(net, hnum, udptable->mask);
-	struct udp_hslot *hslot2, *hslot = &udptable->hash[slot];
+	unsigned int hash2, slot2;
+	struct udp_hslot *hslot2;
 	bool exact_dif = udp_lib_exact_dif_match(net, skb);
-	int score, badness;
-	u32 hash = 0;
 
-	if (hslot->count > 10) {
-		hash2 = ipv4_portaddr_hash(net, daddr, hnum);
+	hash2 = ipv4_portaddr_hash(net, daddr, hnum);
+	slot2 = hash2 & udptable->mask;
+	hslot2 = &udptable->hash2[slot2];
+
+	result = udp4_lib_lookup2(net, saddr, sport,
+				  daddr, hnum, dif, sdif,
+				  exact_dif, hslot2, skb);
+	if (!result) {
+		hash2 = ipv4_portaddr_hash(net, htonl(INADDR_ANY), hnum);
 		slot2 = hash2 & udptable->mask;
 		hslot2 = &udptable->hash2[slot2];
-		if (hslot->count < hslot2->count)
-			goto begin;
 
 		result = udp4_lib_lookup2(net, saddr, sport,
-					  daddr, hnum, dif, sdif,
+					  htonl(INADDR_ANY), hnum, dif, sdif,
 					  exact_dif, hslot2, skb);
-		if (!result) {
-			unsigned int old_slot2 = slot2;
-			hash2 = ipv4_portaddr_hash(net, htonl(INADDR_ANY), hnum);
-			slot2 = hash2 & udptable->mask;
-			/* avoid searching the same slot again. */
-			if (unlikely(slot2 == old_slot2))
-				return result;
-
-			hslot2 = &udptable->hash2[slot2];
-			if (hslot->count < hslot2->count)
-				goto begin;
-
-			result = udp4_lib_lookup2(net, saddr, sport,
-						  daddr, hnum, dif, sdif,
-						  exact_dif, hslot2, skb);
-		}
-		if (unlikely(IS_ERR(result)))
-			return NULL;
-		return result;
-	}
-begin:
-	result = NULL;
-	badness = 0;
-	sk_for_each_rcu(sk, &hslot->head) {
-		score = compute_score(sk, net, saddr, sport,
-				      daddr, hnum, dif, sdif, exact_dif);
-		if (score > badness) {
-			if (sk->sk_reuseport) {
-				hash = udp_ehashfn(net, daddr, hnum,
-						   saddr, sport);
-				result = reuseport_select_sock(sk, hash, skb,
-							sizeof(struct udphdr));
-				if (unlikely(IS_ERR(result)))
-					return NULL;
-				if (result)
-					return result;
-			}
-			result = sk;
-			badness = score;
-		}
 	}
+	if (unlikely(IS_ERR(result)))
+		return NULL;
 	return result;
 }
 EXPORT_SYMBOL_GPL(__udp4_lib_lookup);