HOTtoday

[PATCH net] net/rds: size a connection's path set by the transport it ends up with

From: Allison Henderson <achender@kernel.org>
Date: 2026-09-21 21:50:29
Also in: linux-rdma
Subsystem: networking [general], rds - reliable datagram sockets, the rest · Maintainers: "David S. Miller", Eric Dumazet, Jakub Kicinski, Paolo Abeni, Allison Henderson, Linus Torvalds

__rds_conn_create() computes npaths from the caller's transport before
it decides whether a connection to one of the host's own addresses is
to be handled by the loopback transport instead.  That substitution is
what an RDS/TCP socket sending to a local address gets, and after it
the path init loop still runs for the TCP transport's RDS_MPATH_WORKERS
paths and allocates an ordered workqueue for each, while
rds_loop_conn_alloc() only ever provides transport data for path 0.

rds_conn_destroy() sizes its teardown from c_trans, by then the
loopback transport, so it visits path 0 only - and
rds_conn_path_destroy() would skip the other paths anyway, since it
returns before destroy_workqueue() for a path without transport data.
kfree(c_path) then drops the last pointers to seven workqueues.  That
repeats for every such connection, on every netns teardown or module
unload, and every distinct local destination address is a separate
connection.

Recompute npaths once the transport is final, so that creation and
destruction agree on the set of paths.  The c_path array stays sized
for the caller's transport; the unused entries are freed with it.

Fixes: 4716af3897e9 ("net/rds: Give each connection path its own workqueue")
Assisted-by: Claude-Code:claude-fable-5
Signed-off-by: Allison Henderson <achender@kernel.org>
---
 net/rds/connection.c | 6 ++++++
 1 file changed, 6 insertions(+)
diff --git a/net/rds/connection.c b/net/rds/connection.c
index b6c4beb50eaf..c752a8623cfc 100644
--- a/net/rds/connection.c
+++ b/net/rds/connection.c
@@ -276,6 +276,12 @@ static struct rds_connection *__rds_conn_create(struct net *net,
 
 	conn->c_trans = trans;
 
+	/* The transport may just have been swapped for loopback; size the
+	 * set of paths - which is also what rds_conn_destroy() tears down
+	 * again - by the transport the connection actually uses.
+	 */
+	npaths = (trans->t_mp_capable ? RDS_MPATH_WORKERS : 1);
+
 	init_waitqueue_head(&conn->c_hs_waitq);
 	for (i = 0; i < npaths; i++) {
 		__rds_conn_path_init(conn, &conn->c_path[i],
-- 
2.25.1
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help