SUNRPC: Ensure we flush any closed sockets before xs_xprt_free()

We must ensure that all sockets are closed before we call xprt_free()
and release the reference to the net namespace. The problem is that
calling fput() will defer closing the socket until delayed_fput() gets
called.
Let's fix the situation by allowing rpciod and the transport teardown
code (which runs on the system wq) to call __fput_sync(), and directly
close the socket.

Reported-by: Felix Fu <foyjog@gmail.com>
Acked-by: Al Viro <viro@zeniv.linux.org.uk>
Fixes: a73881c96d73 ("SUNRPC: Fix an Oops in udp_poll()")
Cc: stable@vger.kernel.org # 5.1.x: 3be232f11a3c: SUNRPC: Prevent immediate close+reconnect
Cc: stable@vger.kernel.org # 5.1.x: 89f42494f92f: SUNRPC: Don't call connect() more than once on a TCP socket
Cc: stable@vger.kernel.org # 5.1.x
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>

diff --git a/fs/file_table.c b/fs/file_table.c
index 7d2e692b66a94fcfc609747802517e27489b8a0c..ada8fe814db97d118e10506382e38a02a6c9bc2b 100644 (file)
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -412,6 +412,7 @@ void __fput_sync(struct file *file)
 }
 
 EXPORT_SYMBOL(fput);
+EXPORT_SYMBOL(__fput_sync);
 
 void __init files_init(void)
 {

diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index ac33892da411ba6eab5ab3b3fb012a6cc438a36c..a4848c7bab8099f8242ece8994b17e59d1b243df 100644 (file)
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -1004,7 +1004,6 @@ DEFINE_RPC_XPRT_LIFETIME_EVENT(connect);
 DEFINE_RPC_XPRT_LIFETIME_EVENT(disconnect_auto);
 DEFINE_RPC_XPRT_LIFETIME_EVENT(disconnect_done);
 DEFINE_RPC_XPRT_LIFETIME_EVENT(disconnect_force);
-DEFINE_RPC_XPRT_LIFETIME_EVENT(disconnect_cleanup);
 DEFINE_RPC_XPRT_LIFETIME_EVENT(destroy);
 
 DECLARE_EVENT_CLASS(rpc_xprt_event,

diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 73344ffb2692fb0fe4c34d48a7c97e11133589b2..ad62eba540a4e9ecafb7ab8b568de39fcce0e369 100644 (file)
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -930,12 +930,7 @@ void xprt_connect(struct rpc_task *task)
        if (!xprt_lock_write(xprt, task))
                return;
 
-       if (test_and_clear_bit(XPRT_CLOSE_WAIT, &xprt->state)) {
-               trace_xprt_disconnect_cleanup(xprt);
-               xprt->ops->close(xprt);
-       }
-
-       if (!xprt_connected(xprt)) {
+       if (!xprt_connected(xprt) && !test_bit(XPRT_CLOSE_WAIT, &xprt->state)) {
                task->tk_rqstp->rq_connect_cookie = xprt->connect_cookie;
                rpc_sleep_on_timeout(&xprt->pending, task, NULL,
                                xprt_request_timeout(task->tk_rqstp));

diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 9b75891b3cc0322b990040434afeb5612bc65708..c6a13893e308a683edacbf657e722b65e4b6f1db 100644 (file)
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -879,7 +879,7 @@ static int xs_local_send_request(struct rpc_rqst *req)
 
        /* Close the stream if the previous transmission was incomplete */
        if (xs_send_request_was_aborted(transport, req)) {
-               xs_close(xprt);
+               xprt_force_disconnect(xprt);
                return -ENOTCONN;
        }
 
@@ -915,7 +915,7 @@ static int xs_local_send_request(struct rpc_rqst *req)
                        -status);
                fallthrough;
        case -EPIPE:
-               xs_close(xprt);
+               xprt_force_disconnect(xprt);
                status = -ENOTCONN;
        }
 
@@ -1185,6 +1185,16 @@ static void xs_reset_transport(struct sock_xprt *transport)
 
        if (sk == NULL)
                return;
+       /*
+        * Make sure we're calling this in a context from which it is safe
+        * to call __fput_sync(). In practice that means rpciod and the
+        * system workqueue.
+        */
+       if (!(current->flags & PF_WQ_WORKER)) {
+               WARN_ON_ONCE(1);
+               set_bit(XPRT_CLOSE_WAIT, &xprt->state);
+               return;
+       }
 
        if (atomic_read(&transport->xprt.swapper))
                sk_clear_memalloc(sk);
@@ -1208,7 +1218,7 @@ static void xs_reset_transport(struct sock_xprt *transport)
        mutex_unlock(&transport->recv_mutex);
 
        trace_rpc_socket_close(xprt, sock);
-       fput(filp);
+       __fput_sync(filp);
 
        xprt_disconnect_done(xprt);
 }