1 files changed, 200 insertions, 75 deletions

diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 19ea045c50ed..096a085611ab 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -31,6 +31,86 @@ const char inet_csk_timer_bug_msg[] = "inet_csk BUG: unknown timer value\n";
 EXPORT_SYMBOL(inet_csk_timer_bug_msg);
 #endif
 
+#if IS_ENABLED(CONFIG_IPV6)
+/* match_wildcard == true:  IPV6_ADDR_ANY equals to any IPv6 addresses if IPv6
+ *                          only, and any IPv4 addresses if not IPv6 only
+ * match_wildcard == false: addresses must be exactly the same, i.e.
+ *                          IPV6_ADDR_ANY only equals to IPV6_ADDR_ANY,
+ *                          and 0.0.0.0 equals to 0.0.0.0 only
+ */
+static int ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6,
+				const struct in6_addr *sk2_rcv_saddr6,
+				__be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr,
+				bool sk1_ipv6only, bool sk2_ipv6only,
+				bool match_wildcard)
+{
+	int addr_type = ipv6_addr_type(sk1_rcv_saddr6);
+	int addr_type2 = sk2_rcv_saddr6 ? ipv6_addr_type(sk2_rcv_saddr6) : IPV6_ADDR_MAPPED;
+
+	/* if both are mapped, treat as IPv4 */
+	if (addr_type == IPV6_ADDR_MAPPED && addr_type2 == IPV6_ADDR_MAPPED) {
+		if (!sk2_ipv6only) {
+			if (sk1_rcv_saddr == sk2_rcv_saddr)
+				return 1;
+			if (!sk1_rcv_saddr || !sk2_rcv_saddr)
+				return match_wildcard;
+		}
+		return 0;
+	}
+
+	if (addr_type == IPV6_ADDR_ANY && addr_type2 == IPV6_ADDR_ANY)
+		return 1;
+
+	if (addr_type2 == IPV6_ADDR_ANY && match_wildcard &&
+	    !(sk2_ipv6only && addr_type == IPV6_ADDR_MAPPED))
+		return 1;
+
+	if (addr_type == IPV6_ADDR_ANY && match_wildcard &&
+	    !(sk1_ipv6only && addr_type2 == IPV6_ADDR_MAPPED))
+		return 1;
+
+	if (sk2_rcv_saddr6 &&
+	    ipv6_addr_equal(sk1_rcv_saddr6, sk2_rcv_saddr6))
+		return 1;
+
+	return 0;
+}
+#endif
+
+/* match_wildcard == true:  0.0.0.0 equals to any IPv4 addresses
+ * match_wildcard == false: addresses must be exactly the same, i.e.
+ *                          0.0.0.0 only equals to 0.0.0.0
+ */
+static int ipv4_rcv_saddr_equal(__be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr,
+				bool sk2_ipv6only, bool match_wildcard)
+{
+	if (!sk2_ipv6only) {
+		if (sk1_rcv_saddr == sk2_rcv_saddr)
+			return 1;
+		if (!sk1_rcv_saddr || !sk2_rcv_saddr)
+			return match_wildcard;
+	}
+	return 0;
+}
+
+int inet_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2,
+			 bool match_wildcard)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+	if (sk->sk_family == AF_INET6)
+		return ipv6_rcv_saddr_equal(&sk->sk_v6_rcv_saddr,
+					    &sk2->sk_v6_rcv_saddr,
+					    sk->sk_rcv_saddr,
+					    sk2->sk_rcv_saddr,
+					    ipv6_only_sock(sk),
+					    ipv6_only_sock(sk2),
+					    match_wildcard);
+#endif
+	return ipv4_rcv_saddr_equal(sk->sk_rcv_saddr, sk2->sk_rcv_saddr,
+				    ipv6_only_sock(sk2), match_wildcard);
+}
+EXPORT_SYMBOL(inet_rcv_saddr_equal);
+
 void inet_get_local_port_range(struct net *net, int *low, int *high)
 {
 	unsigned int seq;
@@ -44,9 +124,9 @@ void inet_get_local_port_range(struct net *net, int *low, int *high)
 }
 EXPORT_SYMBOL(inet_get_local_port_range);
 
-int inet_csk_bind_conflict(const struct sock *sk,
-			   const struct inet_bind_bucket *tb, bool relax,
-			   bool reuseport_ok)
+static int inet_csk_bind_conflict(const struct sock *sk,
+				  const struct inet_bind_bucket *tb,
+				  bool relax, bool reuseport_ok)
 {
 	struct sock *sk2;
 	bool reuse = sk->sk_reuse;
@@ -62,7 +142,6 @@ int inet_csk_bind_conflict(const struct sock *sk,
 
 	sk_for_each_bound(sk2, &tb->owners) {
 		if (sk != sk2 &&
-		    !inet_v6_ipv6only(sk2) &&
 		    (!sk->sk_bound_dev_if ||
 		     !sk2->sk_bound_dev_if ||
 		     sk->sk_bound_dev_if == sk2->sk_bound_dev_if)) {
@@ -72,54 +151,34 @@ int inet_csk_bind_conflict(const struct sock *sk,
 			     rcu_access_pointer(sk->sk_reuseport_cb) ||
 			     (sk2->sk_state != TCP_TIME_WAIT &&
 			     !uid_eq(uid, sock_i_uid(sk2))))) {
-
-				if (!sk2->sk_rcv_saddr || !sk->sk_rcv_saddr ||
-				    sk2->sk_rcv_saddr == sk->sk_rcv_saddr)
+				if (inet_rcv_saddr_equal(sk, sk2, true))
 					break;
 			}
 			if (!relax && reuse && sk2->sk_reuse &&
 			    sk2->sk_state != TCP_LISTEN) {
-
-				if (!sk2->sk_rcv_saddr || !sk->sk_rcv_saddr ||
-				    sk2->sk_rcv_saddr == sk->sk_rcv_saddr)
+				if (inet_rcv_saddr_equal(sk, sk2, true))
 					break;
 			}
 		}
 	}
 	return sk2 != NULL;
 }
-EXPORT_SYMBOL_GPL(inet_csk_bind_conflict);
 
-/* Obtain a reference to a local port for the given sock,
- * if snum is zero it means select any available local port.
- * We try to allocate an odd port (and leave even ports for connect())
+/*
+ * Find an open port number for the socket.  Returns with the
+ * inet_bind_hashbucket lock held.
  */
-int inet_csk_get_port(struct sock *sk, unsigned short snum)
+static struct inet_bind_hashbucket *
+inet_csk_find_open_port(struct sock *sk, struct inet_bind_bucket **tb_ret, int *port_ret)
 {
-	bool reuse = sk->sk_reuse && sk->sk_state != TCP_LISTEN;
 	struct inet_hashinfo *hinfo = sk->sk_prot->h.hashinfo;
-	int ret = 1, attempts = 5, port = snum;
-	int smallest_size = -1, smallest_port;
+	int port = 0;
 	struct inet_bind_hashbucket *head;
 	struct net *net = sock_net(sk);
 	int i, low, high, attempt_half;
 	struct inet_bind_bucket *tb;
-	kuid_t uid = sock_i_uid(sk);
 	u32 remaining, offset;
-	bool reuseport_ok = !!snum;
 
-	if (port) {
-have_port:
-		head = &hinfo->bhash[inet_bhashfn(net, port,
-						  hinfo->bhash_size)];
-		spin_lock_bh(&head->lock);
-		inet_bind_bucket_for_each(tb, &head->chain)
-			if (net_eq(ib_net(tb), net) && tb->port == port)
-				goto tb_found;
-
-		goto tb_not_found;
-	}
-again:
 	attempt_half = (sk->sk_reuse == SK_CAN_REUSE) ? 1 : 0;
 other_half_scan:
 	inet_get_local_port_range(net, &low, &high);
@@ -143,8 +202,6 @@ other_half_scan:
 	 * We do the opposite to not pollute connect() users.
 	 */
 	offset |= 1U;
-	smallest_size = -1;
-	smallest_port = low; /* avoid compiler warning */
 
 other_parity_scan:
 	port = low + offset;
@@ -158,30 +215,17 @@ other_parity_scan:
 		spin_lock_bh(&head->lock);
 		inet_bind_bucket_for_each(tb, &head->chain)
 			if (net_eq(ib_net(tb), net) && tb->port == port) {
-				if (((tb->fastreuse > 0 && reuse) ||
-				     (tb->fastreuseport > 0 &&
-				      sk->sk_reuseport &&
-				      !rcu_access_pointer(sk->sk_reuseport_cb) &&
-				      uid_eq(tb->fastuid, uid))) &&
-				    (tb->num_owners < smallest_size || smallest_size == -1)) {
-					smallest_size = tb->num_owners;
-					smallest_port = port;
-				}
-				if (!inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb, false,
-									      reuseport_ok))
-					goto tb_found;
+				if (!inet_csk_bind_conflict(sk, tb, false, false))
+					goto success;
 				goto next_port;
 			}
-		goto tb_not_found;
+		tb = NULL;
+		goto success;
 next_port:
 		spin_unlock_bh(&head->lock);
 		cond_resched();
 	}
 
-	if (smallest_size != -1) {
-		port = smallest_port;
-		goto have_port;
-	}
 	offset--;
 	if (!(offset & 1))
 		goto other_parity_scan;
@@ -191,8 +235,74 @@ next_port:
 		attempt_half = 2;
 		goto other_half_scan;
 	}
-	return ret;
+	return NULL;
+success:
+	*port_ret = port;
+	*tb_ret = tb;
+	return head;
+}
 
+static inline int sk_reuseport_match(struct inet_bind_bucket *tb,
+				     struct sock *sk)
+{
+	kuid_t uid = sock_i_uid(sk);
+
+	if (tb->fastreuseport <= 0)
+		return 0;
+	if (!sk->sk_reuseport)
+		return 0;
+	if (rcu_access_pointer(sk->sk_reuseport_cb))
+		return 0;
+	if (!uid_eq(tb->fastuid, uid))
+		return 0;
+	/* We only need to check the rcv_saddr if this tb was once marked
+	 * without fastreuseport and then was reset, as we can only know that
+	 * the fast_*rcv_saddr doesn't have any conflicts with the socks on the
+	 * owners list.
+	 */
+	if (tb->fastreuseport == FASTREUSEPORT_ANY)
+		return 1;
+#if IS_ENABLED(CONFIG_IPV6)
+	if (tb->fast_sk_family == AF_INET6)
+		return ipv6_rcv_saddr_equal(&tb->fast_v6_rcv_saddr,
+					    &sk->sk_v6_rcv_saddr,
+					    tb->fast_rcv_saddr,
+					    sk->sk_rcv_saddr,
+					    tb->fast_ipv6_only,
+					    ipv6_only_sock(sk), true);
+#endif
+	return ipv4_rcv_saddr_equal(tb->fast_rcv_saddr, sk->sk_rcv_saddr,
+				    ipv6_only_sock(sk), true);
+}
+
+/* Obtain a reference to a local port for the given sock,
+ * if snum is zero it means select any available local port.
+ * We try to allocate an odd port (and leave even ports for connect())
+ */
+int inet_csk_get_port(struct sock *sk, unsigned short snum)
+{
+	bool reuse = sk->sk_reuse && sk->sk_state != TCP_LISTEN;
+	struct inet_hashinfo *hinfo = sk->sk_prot->h.hashinfo;
+	int ret = 1, port = snum;
+	struct inet_bind_hashbucket *head;
+	struct net *net = sock_net(sk);
+	struct inet_bind_bucket *tb = NULL;
+	kuid_t uid = sock_i_uid(sk);
+
+	if (!port) {
+		head = inet_csk_find_open_port(sk, &tb, &port);
+		if (!head)
+			return ret;
+		if (!tb)
+			goto tb_not_found;
+		goto success;
+	}
+	head = &hinfo->bhash[inet_bhashfn(net, port,
+					  hinfo->bhash_size)];
+	spin_lock_bh(&head->lock);
+	inet_bind_bucket_for_each(tb, &head->chain)
+		if (net_eq(ib_net(tb), net) && tb->port == port)
+			goto tb_found;
 tb_not_found:
 	tb = inet_bind_bucket_create(hinfo->bind_bucket_cachep,
 				     net, head, port);
@@ -203,39 +313,54 @@ tb_found:
 		if (sk->sk_reuse == SK_FORCE_REUSE)
 			goto success;
 
-		if (((tb->fastreuse > 0 && reuse) ||
-		     (tb->fastreuseport > 0 &&
-		      !rcu_access_pointer(sk->sk_reuseport_cb) &&
-		      sk->sk_reuseport && uid_eq(tb->fastuid, uid))) &&
-		    smallest_size == -1)
+		if ((tb->fastreuse > 0 && reuse) ||
+		    sk_reuseport_match(tb, sk))
 			goto success;
-		if (inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb, true,
-							     reuseport_ok)) {
-			if ((reuse ||
-			     (tb->fastreuseport > 0 &&
-			      sk->sk_reuseport &&
-			      !rcu_access_pointer(sk->sk_reuseport_cb) &&
-			      uid_eq(tb->fastuid, uid))) &&
-			    !snum && smallest_size != -1 && --attempts >= 0) {
-				spin_unlock_bh(&head->lock);
-				goto again;
-			}
+		if (inet_csk_bind_conflict(sk, tb, true, true))
 			goto fail_unlock;
+	}
+success:
+	if (!hlist_empty(&tb->owners)) {
+		tb->fastreuse = reuse;
+		if (sk->sk_reuseport) {
+			tb->fastreuseport = FASTREUSEPORT_ANY;
+			tb->fastuid = uid;
+			tb->fast_rcv_saddr = sk->sk_rcv_saddr;
+			tb->fast_ipv6_only = ipv6_only_sock(sk);
+#if IS_ENABLED(CONFIG_IPV6)
+			tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
+#endif
+		} else {
+			tb->fastreuseport = 0;
 		}
+	} else {
 		if (!reuse)
 			tb->fastreuse = 0;
-		if (!sk->sk_reuseport || !uid_eq(tb->fastuid, uid))
-			tb->fastreuseport = 0;
-	} else {
-		tb->fastreuse = reuse;
 		if (sk->sk_reuseport) {
-			tb->fastreuseport = 1;
-			tb->fastuid = uid;
+			/* We didn't match or we don't have fastreuseport set on
+			 * the tb, but we have sk_reuseport set on this socket
+			 * and we know that there are no bind conflicts with
+			 * this socket in this tb, so reset our tb's reuseport
+			 * settings so that any subsequent sockets that match
+			 * our current socket will be put on the fast path.
+			 *
+			 * If we reset we need to set FASTREUSEPORT_STRICT so we
+			 * do extra checking for all subsequent sk_reuseport
+			 * socks.
+			 */
+			if (!sk_reuseport_match(tb, sk)) {
+				tb->fastreuseport = FASTREUSEPORT_STRICT;
+				tb->fastuid = uid;
+				tb->fast_rcv_saddr = sk->sk_rcv_saddr;
+				tb->fast_ipv6_only = ipv6_only_sock(sk);
+#if IS_ENABLED(CONFIG_IPV6)
+				tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
+#endif
+			}
 		} else {
 			tb->fastreuseport = 0;
 		}
 	}
-success:
 	if (!inet_csk(sk)->icsk_bind_hash)
 		inet_bind_hash(sk, tb, port);
 	WARN_ON(inet_csk(sk)->icsk_bind_hash != tb);