netdev - [RFC 09/15] net/rds: Kick-start TCP receiver after accept

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20251022191715.157755-10-achender@kernel.org>
Date: Wed, 22 Oct 2025 12:17:09 -0700
From: Allison Henderson <achender@...nel.org>
To: netdev@...r.kernel.org
Subject: [RFC 09/15] net/rds: Kick-start TCP receiver after accept

From: Gerd Rausch <gerd.rausch@...cle.com>

In cases where the server (the node with the higher IP-address)
in an RDS/TCP connection is overwhelmed it is possible that the
socket that was just accepted is chock-full of messages, up to
the limit of what the socket receive buffer permits.

Subsequently, "rds_tcp_data_ready" won't be called anymore,
because there is no more space to receive additional messages.

Nor was it called prior to the point of calling "rds_tcp_set_callbacks",
because the "sk_data_ready" pointer didn't even point to
"rds_tcp_data_ready" yet.

We fix this by simply kick-starting the receive-worker
for all cases where the socket state is neither
"TCP_CLOSE_WAIT" nor "TCP_CLOSE".

Signed-off-by: Gerd Rausch <gerd.rausch@...cle.com>
Signed-off-by: Allison Henderson <allison.henderson@...cle.com>
---
 net/rds/tcp_listen.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c
index b8a4ec424085..3da259f3a556 100644
--- a/net/rds/tcp_listen.c
+++ b/net/rds/tcp_listen.c
@@ -291,6 +291,8 @@ int rds_tcp_accept_one(struct rds_tcp_net *rtn)
 	    new_sock->sk->sk_state == TCP_LAST_ACK ||
 	    new_sock->sk->sk_state == TCP_CLOSE)
 		rds_conn_path_drop(cp, 0);
+	else
+		queue_delayed_work(cp->cp_wq, &cp->cp_recv_w, 0);

 	new_sock = NULL;
 	ret = 0;
-- 
2.43.0