sunrpc: xprtsock: annotate shared socket callbacks with READ_ONCE/WRITE_ONCE

xprtsock replaces and restores sk->sk_data_ready and
sk->sk_write_space on live sockets with plain stores, and
xs_udp_do_set_buffer_size() invokes sk->sk_write_space via a plain
load. These callback pointers are shared with generic socket and
protocol paths that may read or invoke them concurrently, so xprtsock
needs the same READ_ONCE()/WRITE_ONCE() callback visibility contract
that the validated 4022 family applied elsewhere.

When SUNRPC takes over an AF_LOCAL, UDP, or TCP socket and later
restores the lower-socket callbacks during teardown, another CPU may
still hold an earlier callback snapshot. The plain replace/restore
pattern leaves the same visibility hole as the validated 4022 family,
so a stale snapshot can still invoke xs_data_ready() or
xs_udp_write_space() after the live callback fields have already been
restored to the lower-socket handlers.

Use WRITE_ONCE() for the shared sk_data_ready and sk_write_space
stores in xs_local_finish_connecting(), xs_udp_finish_connecting(),
xs_tcp_finish_connecting(), and xs_restore_old_callbacks(). Use
READ_ONCE() for the direct sk_write_space invocation in
xs_udp_do_set_buffer_size(). This matches the required callback
visibility contract while leaving adjacent sk_state_change and
sk_error_report handling unchanged.

Fixes: a246b0105bbd ("[PATCH] RPC: introduce client-side transport switch")
Signed-off-by: Runyu Xiao <runyu.xiao@seu.edu.cn>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>

1 files changed, 11 insertions, 9 deletions

diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 359407aae03e..d735e6ec7e37 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -1202,9 +1202,9 @@ static void xs_save_old_callbacks(struct sock_xprt *transport, struct sock *sk)
 
 static void xs_restore_old_callbacks(struct sock_xprt *transport, struct sock *sk)
 {
-	sk->sk_data_ready = transport->old_data_ready;
+	WRITE_ONCE(sk->sk_data_ready, transport->old_data_ready);
 	sk->sk_state_change = transport->old_state_change;
-	sk->sk_write_space = transport->old_write_space;
+	WRITE_ONCE(sk->sk_write_space, transport->old_write_space);
 	sk->sk_error_report = transport->old_error_report;
 }
 
@@ -1664,6 +1664,7 @@ static void xs_udp_do_set_buffer_size(struct rpc_xprt *xprt)
 {
 	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
 	struct sock *sk = transport->inet;
+	void (*write_space)(struct sock *sock);
 
 	if (transport->rcvsize) {
 		sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
@@ -1672,7 +1673,8 @@ static void xs_udp_do_set_buffer_size(struct rpc_xprt *xprt)
 	if (transport->sndsize) {
 		sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
 		sk->sk_sndbuf = transport->sndsize * xprt->max_reqs * 2;
-		sk->sk_write_space(sk);
+		write_space = READ_ONCE(sk->sk_write_space);
+		write_space(sk);
 	}
 }
 
@@ -1988,8 +1990,8 @@ static int xs_local_finish_connecting(struct rpc_xprt *xprt,
 		xs_save_old_callbacks(transport, sk);
 
 		sk->sk_user_data = xprt;
-		sk->sk_data_ready = xs_data_ready;
-		sk->sk_write_space = xs_udp_write_space;
+		WRITE_ONCE(sk->sk_data_ready, xs_data_ready);
+		WRITE_ONCE(sk->sk_write_space, xs_udp_write_space);
 		sk->sk_state_change = xs_local_state_change;
 		sk->sk_error_report = xs_error_report;
 		sk->sk_use_task_frag = false;
@@ -2191,8 +2193,8 @@ static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
 		xs_save_old_callbacks(transport, sk);
 
 		sk->sk_user_data = xprt;
-		sk->sk_data_ready = xs_data_ready;
-		sk->sk_write_space = xs_udp_write_space;
+		WRITE_ONCE(sk->sk_data_ready, xs_data_ready);
+		WRITE_ONCE(sk->sk_write_space, xs_udp_write_space);
 		sk->sk_use_task_frag = false;
 
 		xprt_set_connected(xprt);
@@ -2378,9 +2380,9 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
 		xs_save_old_callbacks(transport, sk);
 
 		sk->sk_user_data = xprt;
-		sk->sk_data_ready = xs_data_ready;
+		WRITE_ONCE(sk->sk_data_ready, xs_data_ready);
 		sk->sk_state_change = xs_tcp_state_change;
-		sk->sk_write_space = xs_tcp_write_space;
+		WRITE_ONCE(sk->sk_write_space, xs_tcp_write_space);
 		sk->sk_error_report = xs_error_report;
 		sk->sk_use_task_frag = false;