Re: PROBLEM: Linux kernel 2.6.31 IPv4 TCP fails to open huge amount of outgoing connections (unable to bind ... )

[Eric Dumazet <eric.dumazet@gmail.com>]

Le mercredi 21 avril 2010 à 22:58 +0400, Evgeniy Polyakov a écrit :

> Damn it, I tried multiple times :)
> You are right of course!
> 

Here is a formal patch then :)

[PATCH] tcp: bind() fix when many ports are bound

Port autoselection done by kernel only works when number of bound
sockets is under a threshold (typically 30000).

When this threshold is over, we must check if there is a conflict before
exiting first loop in inet_csk_get_port()

Change inet_csk_bind_conflict() to forbid two reuse-enabled sockets to
bind on same (address,port) tuple (with a non ANY address)

Same change for inet6_csk_bind_conflict()

Reported-by: Gaspar Chilingarov <gasparch@gmail.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
---
 net/ipv4/inet_connection_sock.c  |   16 +++++++++++-----
 net/ipv6/inet6_connection_sock.c |   15 ++++++++++-----
 2 files changed, 21 insertions(+), 10 deletions(-)

diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index e0a3e35..78cbc39 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -70,13 +70,17 @@ 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)) {
+			const __be32 sk2_rcv_saddr = inet_rcv_saddr(sk2);
+
 			if (!reuse || !sk2->sk_reuse ||
 			    sk2->sk_state == TCP_LISTEN) {
-				const __be32 sk2_rcv_saddr = inet_rcv_saddr(sk2);
 				if (!sk2_rcv_saddr || !sk_rcv_saddr ||
 				    sk2_rcv_saddr == sk_rcv_saddr)
 					break;
-			}
+			} else if (reuse && sk2->sk_reuse &&
+				   sk2_rcv_saddr &&
+				   sk2_rcv_saddr == sk_rcv_saddr)
+				break;
 		}
 	}
 	return node != NULL;
@@ -120,9 +124,11 @@ again:
 						smallest_size = tb->num_owners;
 						smallest_rover = rover;
 						if (atomic_read(&hashinfo->bsockets) > (high - low) + 1) {
-							spin_unlock(&head->lock);
-							snum = smallest_rover;
-							goto have_snum;
+							if (!inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb)) {
+								spin_unlock(&head->lock);
+								snum = smallest_rover;
+								goto have_snum;
+							}
 						}
 					}
 					goto next;
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index 0c5e3c3..fb6959c 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -42,11 +42,16 @@ int inet6_csk_bind_conflict(const struct sock *sk,
 		if (sk != sk2 &&
 		    (!sk->sk_bound_dev_if ||
 		     !sk2->sk_bound_dev_if ||
-		     sk->sk_bound_dev_if == sk2->sk_bound_dev_if) &&
-		    (!sk->sk_reuse || !sk2->sk_reuse ||
-		     sk2->sk_state == TCP_LISTEN) &&
-		     ipv6_rcv_saddr_equal(sk, sk2))
-			break;
+		     sk->sk_bound_dev_if == sk2->sk_bound_dev_if)) {
+			if ((!sk->sk_reuse || !sk2->sk_reuse ||
+			     sk2->sk_state == TCP_LISTEN) &&
+			     ipv6_rcv_saddr_equal(sk, sk2))
+				break;
+			else if (sk->sk_reuse && sk2->sk_reuse &&
+				!ipv6_addr_any(inet6_rcv_saddr(sk2)) &&
+				ipv6_rcv_saddr_equal(sk, sk2))
+				break;
+		}
 	}
 
 	return node != NULL;