udp: correct reuseport selection with connected sockets

UDP reuseport groups can hold a mix unconnected and connected sockets.
Ensure that connections only receive all traffic to their 4-tuple.

Fast reuseport returns on the first reuseport match on the assumption
that all matches are equal. Only if connections are present, return to
the previous behavior of scoring all sockets.

Record if connections are present and if so (1) treat such connected
sockets as an independent match from the group, (2) only return
2-tuple matches from reuseport and (3) do not return on the first
2-tuple reuseport match to allow for a higher scoring match later.

New field has_conns is set without locks. No other fields in the
bitmap are modified at runtime and the field is only ever set
unconditionally, so an RMW cannot miss a change.

Fixes: e32ea7e74727 ("soreuseport: fast reuseport UDP socket selection")
Link: http://lkml.kernel.org/r/[e-mail]
Signed-off-by: Willem de Bruijn <[e-mail]>
Acked-by: Paolo Abeni <[e-mail]>
Acked-by: Craig Gallek <[e-mail]>
Signed-off-by: Willem de Bruijn <[e-mail]>
Signed-off-by: David S. Miller <[e-mail]>

include/net/sock_reuseport.h

···
 	unsigned int		synq_overflow_ts;
 	/* ID stays the same even after the size of socks[] grows. */
 	unsigned int		reuseport_id;
-	bool			bind_inany;
+	unsigned int		bind_inany:1;
+	unsigned int		has_conns:1;
 	struct bpf_prog __rcu	*prog;		/* optional BPF sock selector */
 	struct sock		*socks[0];	/* array of sock pointers */
 };
···
 					  int hdr_len);
 extern int reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog);
 extern int reuseport_detach_prog(struct sock *sk);
+
+static inline bool reuseport_has_conns(struct sock *sk, bool set)
+{
+	struct sock_reuseport *reuse;
+	bool ret = false;
+
+	rcu_read_lock();
+	reuse = rcu_dereference(sk->sk_reuseport_cb);
+	if (reuse) {
+		if (set)
+			reuse->has_conns = 1;
+		ret = reuse->has_conns;
+	}
+	rcu_read_unlock();
+
+	return ret;
+}
 
 int reuseport_get_id(struct sock_reuseport *reuse);
 

net/core/sock_reuseport.c

···
 
 select_by_hash:
 		/* no bpf or invalid bpf result: fall back to hash usage */
-		if (!sk2)
-			sk2 = reuse->socks[reciprocal_scale(hash, socks)];
+		if (!sk2) {
+			int i, j;
+
+			i = j = reciprocal_scale(hash, socks);
+			while (reuse->socks[i]->sk_state == TCP_ESTABLISHED) {
+				i++;
+				if (i >= reuse->num_socks)
+					i = 0;
+				if (i == j)
+					goto out;
+			}
+			sk2 = reuse->socks[i];
+		}
 	}
 
 out:

net/ipv4/datagram.c

···
 #include <net/sock.h>
 #include <net/route.h>
 #include <net/tcp_states.h>
+#include <net/sock_reuseport.h>
 
 int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 {
···
 	}
 	inet->inet_daddr = fl4->daddr;
 	inet->inet_dport = usin->sin_port;
+	reuseport_has_conns(sk, true);
 	sk->sk_state = TCP_ESTABLISHED;
 	sk_set_txhash(sk);
 	inet->inet_id = jiffies;

net/ipv4/udp.c

···
 		score = compute_score(sk, net, saddr, sport,
 				      daddr, hnum, dif, sdif);
 		if (score > badness) {
-			if (sk->sk_reuseport) {
+			if (sk->sk_reuseport &&
+			    sk->sk_state != TCP_ESTABLISHED) {
 				hash = udp_ehashfn(net, daddr, hnum,
 						   saddr, sport);
 				result = reuseport_select_sock(sk, hash, skb,
 							sizeof(struct udphdr));
-				if (result)
+				if (result && !reuseport_has_conns(sk, false))
 					return result;
 			}
 			badness = score;

net/ipv6/datagram.c

···
 #include <net/ip6_route.h>
 #include <net/tcp_states.h>
 #include <net/dsfield.h>
+#include <net/sock_reuseport.h>
 
 #include <linux/errqueue.h>
 #include <linux/uaccess.h>
···
 		goto out;
 	}
 
+	reuseport_has_conns(sk, true);
 	sk->sk_state = TCP_ESTABLISHED;
 	sk_set_txhash(sk);
 out:

net/ipv6/udp.c

···
 		score = compute_score(sk, net, saddr, sport,
 				      daddr, hnum, dif, sdif);
 		if (score > badness) {
-			if (sk->sk_reuseport) {
+			if (sk->sk_reuseport &&
+			    sk->sk_state != TCP_ESTABLISHED) {
 				hash = udp6_ehashfn(net, daddr, hnum,
 						    saddr, sport);
 
 				result = reuseport_select_sock(sk, hash, skb,
 							sizeof(struct udphdr));
-				if (result)
+				if (result && !reuseport_has_conns(sk, false))
 					return result;
 			}
 			result = sk;