tcp: Add TIME_WAIT sockets in bhash2.

Jiri Slaby reported regression of bind() with a simple repro. [0]

The repro creates a TIME_WAIT socket and tries to bind() a new socket
with the same local address and port.  Before commit 28044fc1d495 ("net:
Add a bhash2 table hashed by port and address"), the bind() failed with
-EADDRINUSE, but now it succeeds.

The cited commit should have put TIME_WAIT sockets into bhash2; otherwise,
inet_bhash2_conflict() misses TIME_WAIT sockets when validating bind()
requests if the address is not a wildcard one.

The straight option is to move sk_bind2_node from struct sock to struct
sock_common to add twsk to bhash2 as implemented as RFC. [1]  However, the
binary layout change in the struct sock could affect performances moving
hot fields on different cachelines.

To avoid that, we add another TIME_WAIT list in inet_bind2_bucket and check
it while validating bind().

[0]: https://lore.kernel.org/netdev/6b971a4e-c7d8-411e-1f92-fda29b5b2fb9@kernel.org/
[1]: https://lore.kernel.org/netdev/20221221151258.25748-2-kuniyu@amazon.com/

Fixes: 28044fc1d495 ("net: Add a bhash2 table hashed by port and address")
Reported-by: Jiri Slaby <jirislaby@kernel.org>
Suggested-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Acked-by: Joanne Koong <joannelkoong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 22 insertions, 4 deletions

diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index b366ab9148f2..848ffc3e0239 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -173,22 +173,40 @@ static bool inet_bind_conflict(const struct sock *sk, struct sock *sk2,
 	return false;
 }
 
+static bool __inet_bhash2_conflict(const struct sock *sk, struct sock *sk2,
+				   kuid_t sk_uid, bool relax,
+				   bool reuseport_cb_ok, bool reuseport_ok)
+{
+	if (sk->sk_family == AF_INET && ipv6_only_sock(sk2))
+		return false;
+
+	return inet_bind_conflict(sk, sk2, sk_uid, relax,
+				  reuseport_cb_ok, reuseport_ok);
+}
+
 static bool inet_bhash2_conflict(const struct sock *sk,
 				 const struct inet_bind2_bucket *tb2,
 				 kuid_t sk_uid,
 				 bool relax, bool reuseport_cb_ok,
 				 bool reuseport_ok)
 {
+	struct inet_timewait_sock *tw2;
 	struct sock *sk2;
 
 	sk_for_each_bound_bhash2(sk2, &tb2->owners) {
-		if (sk->sk_family == AF_INET && ipv6_only_sock(sk2))
-			continue;
+		if (__inet_bhash2_conflict(sk, sk2, sk_uid, relax,
+					   reuseport_cb_ok, reuseport_ok))
+			return true;
+	}
 
-		if (inet_bind_conflict(sk, sk2, sk_uid, relax,
-				       reuseport_cb_ok, reuseport_ok))
+	twsk_for_each_bound_bhash2(tw2, &tb2->deathrow) {
+		sk2 = (struct sock *)tw2;
+
+		if (__inet_bhash2_conflict(sk, sk2, sk_uid, relax,
+					   reuseport_cb_ok, reuseport_ok))
 			return true;
 	}
+
 	return false;
 }