Merge branch 'bind_addr_zero'

Kuniyuki Iwashima says:

====================
Improve bind(addr, 0) behaviour.

Currently we fail to bind sockets to ephemeral ports when all of the ports
are exhausted even if all sockets have SO_REUSEADDR enabled. In this case,
we still have a chance to connect to the different remote hosts.

These patches add net.ipv4.ip_autobind_reuse option and fix the behaviour
to fully utilize all space of the local (addr, port) tuples.

Changes in v5:
  - Add more description to documents.
  - Fix sysctl option to use proc_dointvec_minmax.
  - Remove the Fixes: tag and squash two commits.

Changes in v4:
  - Add net.ipv4.ip_autobind_reuse option to not change the current behaviour.
  - Modify .gitignore for test.
  https://lore.kernel.org/netdev/20200308181615.90135-1-kuniyu@amazon.co.jp/

Changes in v3:
  - Change the title and write more specific description of the 3rd patch.
  - Add a test in tools/testing/selftests/net/ as the 4th patch.
  https://lore.kernel.org/netdev/20200229113554.78338-1-kuniyu@amazon.co.jp/

Changes in v2:
  - Change the description of the 2nd patch ('localhost' -> 'address').
  - Correct the description and the if statement of the 3rd patch.
  https://lore.kernel.org/netdev/20200226074631.67688-1-kuniyu@amazon.co.jp/

v1 with tests:
  https://lore.kernel.org/netdev/20200220152020.13056-1-kuniyu@amazon.co.jp/
====================

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

2 files changed, 33 insertions, 12 deletions

diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index a4db79b1b643..3b4f81790e3e 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -131,7 +131,7 @@ static int inet_csk_bind_conflict(const struct sock *sk,
 {
 	struct sock *sk2;
 	bool reuse = sk->sk_reuse;
-	bool reuseport = !!sk->sk_reuseport && reuseport_ok;
+	bool reuseport = !!sk->sk_reuseport;
 	kuid_t uid = sock_i_uid((struct sock *)sk);
 
 	/*
@@ -146,17 +146,21 @@ static int inet_csk_bind_conflict(const struct sock *sk,
 		    (!sk->sk_bound_dev_if ||
 		     !sk2->sk_bound_dev_if ||
 		     sk->sk_bound_dev_if == sk2->sk_bound_dev_if)) {
-			if ((!reuse || !sk2->sk_reuse ||
-			    sk2->sk_state == TCP_LISTEN) &&
-			    (!reuseport || !sk2->sk_reuseport ||
-			     rcu_access_pointer(sk->sk_reuseport_cb) ||
-			     (sk2->sk_state != TCP_TIME_WAIT &&
-			     !uid_eq(uid, sock_i_uid(sk2))))) {
-				if (inet_rcv_saddr_equal(sk, sk2, true))
-					break;
-			}
-			if (!relax && reuse && sk2->sk_reuse &&
+			if (reuse && sk2->sk_reuse &&
 			    sk2->sk_state != TCP_LISTEN) {
+				if ((!relax ||
+				     (!reuseport_ok &&
+				      reuseport && sk2->sk_reuseport &&
+				      !rcu_access_pointer(sk->sk_reuseport_cb) &&
+				      (sk2->sk_state == TCP_TIME_WAIT ||
+				       uid_eq(uid, sock_i_uid(sk2))))) &&
+				    inet_rcv_saddr_equal(sk, sk2, true))
+					break;
+			} else if (!reuseport_ok ||
+				   !reuseport || !sk2->sk_reuseport ||
+				   rcu_access_pointer(sk->sk_reuseport_cb) ||
+				   (sk2->sk_state != TCP_TIME_WAIT &&
+				    !uid_eq(uid, sock_i_uid(sk2)))) {
 				if (inet_rcv_saddr_equal(sk, sk2, true))
 					break;
 			}
@@ -176,12 +180,14 @@ inet_csk_find_open_port(struct sock *sk, struct inet_bind_bucket **tb_ret, int *
 	int port = 0;
 	struct inet_bind_hashbucket *head;
 	struct net *net = sock_net(sk);
+	bool relax = false;
 	int i, low, high, attempt_half;
 	struct inet_bind_bucket *tb;
 	u32 remaining, offset;
 	int l3mdev;
 
 	l3mdev = inet_sk_bound_l3mdev(sk);
+ports_exhausted:
 	attempt_half = (sk->sk_reuse == SK_CAN_REUSE) ? 1 : 0;
 other_half_scan:
 	inet_get_local_port_range(net, &low, &high);
@@ -219,7 +225,7 @@ other_parity_scan:
 		inet_bind_bucket_for_each(tb, &head->chain)
 			if (net_eq(ib_net(tb), net) && tb->l3mdev == l3mdev &&
 			    tb->port == port) {
-				if (!inet_csk_bind_conflict(sk, tb, false, false))
+				if (!inet_csk_bind_conflict(sk, tb, relax, false))
 					goto success;
 				goto next_port;
 			}
@@ -239,6 +245,12 @@ next_port:
 		attempt_half = 2;
 		goto other_half_scan;
 	}
+
+	if (net->ipv4.sysctl_ip_autobind_reuse && !relax) {
+		/* We still have a chance to connect to different destinations */
+		relax = true;
+		goto ports_exhausted;
+	}
 	return NULL;
 success:
 	*port_ret = port;
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index d9531b4b33f2..81b267e990a1 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -764,6 +764,15 @@ static struct ctl_table ipv4_net_table[] = {
 		.proc_handler	= proc_dointvec
 	},
 	{
+		.procname	= "ip_autobind_reuse",
+		.data		= &init_net.ipv4.sysctl_ip_autobind_reuse,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1         = SYSCTL_ZERO,
+		.extra2         = SYSCTL_ONE,
+	},
+	{
 		.procname	= "fwmark_reflect",
 		.data		= &init_net.ipv4.sysctl_fwmark_reflect,
 		.maxlen		= sizeof(int),