tcp: bind() use stronger condition for bind_conflict

We must try harder to get unique (addr, port) pairs when
doing port autoselection for sockets with SO_REUSEADDR
option set.

We achieve this by adding a relaxation parameter to
inet_csk_bind_conflict. When 'relax' parameter is off
we return a conflict whenever the current searched
pair (addr, port) is not unique.

This tries to address the problems reported in patch:
	8d238b25b1ec22a73b1c2206f111df2faaff8285
	Revert "tcp: bind() fix when many ports are bound"

Tests where ran for creating and binding(0) many sockets
on 100 IPs. The results are, on average:

	* 60000 sockets, 600 ports / IP:
		* 0.210 s, 620 (IP, port) duplicates without patch
		* 0.219 s, no duplicates with patch
	* 100000 sockets, 1000 ports / IP:
		* 0.371 s, 1720 duplicates without patch
		* 0.373 s, no duplicates with patch
	* 200000 sockets, 2000 ports / IP:
		* 0.766 s, 6900 duplicates without patch
		* 0.768 s, no duplicates with patch
	* 500000 sockets, 5000 ports / IP:
		* 2.227 s, 41500 duplicates without patch
		* 2.284 s, no duplicates with patch

Signed-off-by: Alex Copot <alex.mihai.c@gmail.com>
Signed-off-by: Daniel Baluta <dbaluta@ixiacom.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 14 insertions, 4 deletions

diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index d19f32aca6c..14409f111bc 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -53,7 +53,7 @@ void inet_get_local_port_range(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)
+			   const struct inet_bind_bucket *tb, bool relax)
 {
 	struct sock *sk2;
 	struct hlist_node *node;
@@ -79,6 +79,14 @@ int inet_csk_bind_conflict(const struct sock *sk,
 				    sk2_rcv_saddr == sk_rcv_saddr(sk))
 					break;
 			}
+			if (!relax && reuse && sk2->sk_reuse &&
+			    sk2->sk_state != TCP_LISTEN) {
+				const __be32 sk2_rcv_saddr = sk_rcv_saddr(sk2);
+
+				if (!sk2_rcv_saddr || !sk_rcv_saddr(sk) ||
+				    sk2_rcv_saddr == sk_rcv_saddr(sk))
+					break;
+			}
 		}
 	}
 	return node != NULL;
@@ -122,12 +130,13 @@ again:
 					    (tb->num_owners < smallest_size || smallest_size == -1)) {
 						smallest_size = tb->num_owners;
 						smallest_rover = rover;
-						if (atomic_read(&hashinfo->bsockets) > (high - low) + 1) {
+						if (atomic_read(&hashinfo->bsockets) > (high - low) + 1 &&
+						    !inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb, false)) {
 							snum = smallest_rover;
 							goto tb_found;
 						}
 					}
-					if (!inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb)) {
+					if (!inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb, false)) {
 						snum = rover;
 						goto tb_found;
 					}
@@ -178,12 +187,13 @@ tb_found:
 			goto success;
 		} else {
 			ret = 1;
-			if (inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb)) {
+			if (inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb, true)) {
 				if (sk->sk_reuse && sk->sk_state != TCP_LISTEN &&
 				    smallest_size != -1 && --attempts >= 0) {
 					spin_unlock(&head->lock);
 					goto again;
 				}
+
 				goto fail_unlock;
 			}
 		}