[PATCH net 2/2] net/rds: do not initialize transports after rds_init() failed

[Allison Henderson <achender@kernel.org>]

rds, rds_rdma and rds_tcp each have their own module_init().  When they
are built in, those run in link order, so rds_init() goes first, but
do_initcalls() does not stop when it fails.  The transports then
initialize against a core that has already been torn down: rds_wq has
been destroyed, yet rds_ib_dev_put(), rds_ib_unregister_client() and
rds_tcp_accept_work() still queue onto or flush it, and
rds_trans_register() hands the transports to a core whose socket
family may never have been registered.

This was seen with CONFIG_SYSCTL=n, where rds_sysctl_init() failed and
rds_ib_init()'s error path then flushed the freed rds_wq [1], but any
rds_init() failure after rds_threads_init() has the same effect.

Record whether rds_init() succeeded and have rds_rdma_init() and
rds_tcp_init() bail out with -ENODEV otherwise.  Modular builds are
unaffected: the transports need symbols exported by rds.ko, so they
cannot be loaded unless rds_init() succeeded.

[1] https://lore.kernel.org/oe-lkp/202610190310.9737b2e3-lkp@intel.com
Fixes: 55b7ed0b582f ("RDS: Common RDMA transport code")
Fixes: 70041088e3b9 ("RDS: Add TCP transport to RDS")
Suggested-by: Oleg Nesterov <oleg@redhat.com>
Assisted-by: LLM
Signed-off-by: Allison Henderson <achender@kernel.org>
---
 net/rds/af_rds.c         | 14 ++++++++++++++
 net/rds/rdma_transport.c |  3 +++
 net/rds/rds.h            |  1 +
 net/rds/tcp.c            |  3 +++
 4 files changed, 21 insertions(+)

diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c
index d5defe9172e3..840587c05178 100644
--- a/net/rds/af_rds.c
+++ b/net/rds/af_rds.c
@@ -922,8 +922,11 @@ static void rds6_sock_info(struct socket *sock, unsigned int len,
 }
 #endif
 
+static bool rds_initialized;
+
 static void rds_exit(void)
 {
+	rds_initialized = false;
 	sock_unregister(rds_family_ops.family);
 	proto_unregister(&rds_proto);
 	rds_conn_exit();
@@ -944,6 +947,16 @@ module_exit(rds_exit);
 
 u32 rds_gen_num;
 
+/* When RDS is built in, a failed rds_init() does not stop the rds_rdma
+ * and rds_tcp initcalls from running against a core that has already
+ * been torn down (rds_wq in particular).  Let them bail out early.
+ */
+bool rds_is_initialized(void)
+{
+	return rds_initialized;
+}
+EXPORT_SYMBOL_GPL(rds_is_initialized);
+
 static int __init rds_init(void)
 {
 	int ret;
@@ -980,6 +993,7 @@ static int __init rds_init(void)
 	rds_info_register_func(RDS6_INFO_SOCKETS, rds6_sock_info);
 	rds_info_register_func(RDS6_INFO_RECV_MESSAGES, rds6_sock_inc_info);
 #endif
+	rds_initialized = true;
 
 	goto out;
 
diff --git a/net/rds/rdma_transport.c b/net/rds/rdma_transport.c
index 7be38be1228e..cc6a7d29791a 100644
--- a/net/rds/rdma_transport.c
+++ b/net/rds/rdma_transport.c
@@ -325,6 +325,9 @@ static int __init rds_rdma_init(void)
 {
 	int ret;
 
+	if (!rds_is_initialized())
+		return -ENODEV;
+
 	ret = rds_ib_init();
 	if (ret)
 		goto out;
diff --git a/net/rds/rds.h b/net/rds/rds.h
index 2db49573dacd..b7ef7c8b1e03 100644
--- a/net/rds/rds.h
+++ b/net/rds/rds.h
@@ -1040,6 +1040,7 @@ extern unsigned int  rds_sysctl_trace_level;
 int rds_threads_init(void);
 void rds_threads_exit(void);
 extern struct workqueue_struct *rds_wq;
+bool rds_is_initialized(void);
 void rds_queue_reconnect(struct rds_conn_path *cp);
 void rds_connect_worker(struct work_struct *);
 void rds_shutdown_worker(struct work_struct *);
diff --git a/net/rds/tcp.c b/net/rds/tcp.c
index 34815b4f658b..c1ad37505417 100644
--- a/net/rds/tcp.c
+++ b/net/rds/tcp.c
@@ -815,6 +815,9 @@ static int __init rds_tcp_init(void)
 {
 	int ret;
 
+	if (!rds_is_initialized())
+		return -ENODEV;
+
 	rds_tcp_conn_slab = KMEM_CACHE(rds_tcp_connection, 0);
 	if (!rds_tcp_conn_slab) {
 		ret = -ENOMEM;
-- 
2.50.1