1 files changed, 83 insertions, 63 deletions

diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index dd9d295813c..be8bbd5d65e 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -254,9 +254,10 @@ struct sock_xprt {
 	/*
 	 * Saved socket callback addresses
 	 */
-	void			(*old_data_ready)(struct sock *, int);
+	void			(*old_data_ready)(struct sock *);
 	void			(*old_state_change)(struct sock *);
 	void			(*old_write_space)(struct sock *);
+	void			(*old_error_report)(struct sock *);
 };
 
 /*
@@ -274,6 +275,11 @@ struct sock_xprt {
  */
 #define TCP_RPC_REPLY		(1UL << 6)
 
+static inline struct rpc_xprt *xprt_from_sock(struct sock *sk)
+{
+	return (struct rpc_xprt *) sk->sk_user_data;
+}
+
 static inline struct sockaddr *xs_addr(struct rpc_xprt *xprt)
 {
 	return (struct sockaddr *) &xprt->addr;
@@ -504,6 +510,7 @@ static int xs_nospace(struct rpc_task *task)
 	struct rpc_rqst *req = task->tk_rqstp;
 	struct rpc_xprt *xprt = req->rq_xprt;
 	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
+	struct sock *sk = transport->inet;
 	int ret = -EAGAIN;
 
 	dprintk("RPC: %5u xmit incomplete (%u left of %u)\n",
@@ -521,7 +528,7 @@ static int xs_nospace(struct rpc_task *task)
 			 * window size
 			 */
 			set_bit(SOCK_NOSPACE, &transport->sock->flags);
-			transport->inet->sk_write_pending++;
+			sk->sk_write_pending++;
 			/* ...and wait for more buffer space */
 			xprt_wait_for_buffer_space(task, xs_nospace_callback);
 		}
@@ -531,6 +538,9 @@ static int xs_nospace(struct rpc_task *task)
 	}
 
 	spin_unlock_bh(&xprt->transport_lock);
+
+	/* Race breaker in case memory is freed before above code is called */
+	sk->sk_write_space(sk);
 	return ret;
 }
 
@@ -799,6 +809,7 @@ static void xs_save_old_callbacks(struct sock_xprt *transport, struct sock *sk)
 	transport->old_data_ready = sk->sk_data_ready;
 	transport->old_state_change = sk->sk_state_change;
 	transport->old_write_space = sk->sk_write_space;
+	transport->old_error_report = sk->sk_error_report;
 }
 
 static void xs_restore_old_callbacks(struct sock_xprt *transport, struct sock *sk)
@@ -806,6 +817,34 @@ static void xs_restore_old_callbacks(struct sock_xprt *transport, struct sock *s
 	sk->sk_data_ready = transport->old_data_ready;
 	sk->sk_state_change = transport->old_state_change;
 	sk->sk_write_space = transport->old_write_space;
+	sk->sk_error_report = transport->old_error_report;
+}
+
+/**
+ * xs_error_report - callback to handle TCP socket state errors
+ * @sk: socket
+ *
+ * Note: we don't call sock_error() since there may be a rpc_task
+ * using the socket, and so we don't want to clear sk->sk_err.
+ */
+static void xs_error_report(struct sock *sk)
+{
+	struct rpc_xprt *xprt;
+	int err;
+
+	read_lock_bh(&sk->sk_callback_lock);
+	if (!(xprt = xprt_from_sock(sk)))
+		goto out;
+
+	err = -sk->sk_err;
+	if (err == 0)
+		goto out;
+	dprintk("RPC:       xs_error_report client %p, error=%d...\n",
+			xprt, -err);
+	trace_rpc_socket_error(xprt, sk->sk_socket, err);
+	xprt_wake_pending_tasks(xprt, err);
+ out:
+	read_unlock_bh(&sk->sk_callback_lock);
 }
 
 static void xs_reset_transport(struct sock_xprt *transport)
@@ -827,8 +866,6 @@ static void xs_reset_transport(struct sock_xprt *transport)
 	xs_restore_old_callbacks(transport, sk);
 	write_unlock_bh(&sk->sk_callback_lock);
 
-	sk->sk_no_check = 0;
-
 	trace_rpc_socket_close(&transport->xprt, sock);
 	sock_release(sock);
 }
@@ -854,11 +891,11 @@ static void xs_close(struct rpc_xprt *xprt)
 	xs_reset_transport(transport);
 	xprt->reestablish_timeout = 0;
 
-	smp_mb__before_clear_bit();
+	smp_mb__before_atomic();
 	clear_bit(XPRT_CONNECTION_ABORT, &xprt->state);
 	clear_bit(XPRT_CLOSE_WAIT, &xprt->state);
 	clear_bit(XPRT_CLOSING, &xprt->state);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 	xprt_disconnect_done(xprt);
 }
 
@@ -870,6 +907,12 @@ static void xs_tcp_close(struct rpc_xprt *xprt)
 		xs_tcp_shutdown(xprt);
 }
 
+static void xs_xprt_free(struct rpc_xprt *xprt)
+{
+	xs_free_peer_addresses(xprt);
+	xprt_free(xprt);
+}
+
 /**
  * xs_destroy - prepare to shutdown a transport
  * @xprt: doomed transport
@@ -880,16 +923,10 @@ static void xs_destroy(struct rpc_xprt *xprt)
 	dprintk("RPC:       xs_destroy xprt %p\n", xprt);
 
 	xs_close(xprt);
-	xs_free_peer_addresses(xprt);
-	xprt_free(xprt);
+	xs_xprt_free(xprt);
 	module_put(THIS_MODULE);
 }
 
-static inline struct rpc_xprt *xprt_from_sock(struct sock *sk)
-{
-	return (struct rpc_xprt *) sk->sk_user_data;
-}
-
 static int xs_local_copy_to_xdr(struct xdr_buf *xdr, struct sk_buff *skb)
 {
 	struct xdr_skb_reader desc = {
@@ -912,7 +949,7 @@ static int xs_local_copy_to_xdr(struct xdr_buf *xdr, struct sk_buff *skb)
  *
  * Currently this assumes we can read the whole reply in a single gulp.
  */
-static void xs_local_data_ready(struct sock *sk, int len)
+static void xs_local_data_ready(struct sock *sk)
 {
 	struct rpc_task *task;
 	struct rpc_xprt *xprt;
@@ -975,7 +1012,7 @@ static void xs_local_data_ready(struct sock *sk, int len)
  * @len: how much data to read
  *
  */
-static void xs_udp_data_ready(struct sock *sk, int len)
+static void xs_udp_data_ready(struct sock *sk)
 {
 	struct rpc_task *task;
 	struct rpc_xprt *xprt;
@@ -1272,41 +1309,29 @@ static inline int xs_tcp_read_reply(struct rpc_xprt *xprt,
  * If we're unable to obtain the rpc_rqst we schedule the closing of the
  * connection and return -1.
  */
-static inline int xs_tcp_read_callback(struct rpc_xprt *xprt,
+static int xs_tcp_read_callback(struct rpc_xprt *xprt,
 				       struct xdr_skb_reader *desc)
 {
 	struct sock_xprt *transport =
 				container_of(xprt, struct sock_xprt, xprt);
 	struct rpc_rqst *req;
 
-	req = xprt_alloc_bc_request(xprt);
+	/* Look up and lock the request corresponding to the given XID */
+	spin_lock(&xprt->transport_lock);
+	req = xprt_lookup_bc_request(xprt, transport->tcp_xid);
 	if (req == NULL) {
+		spin_unlock(&xprt->transport_lock);
 		printk(KERN_WARNING "Callback slot table overflowed\n");
 		xprt_force_disconnect(xprt);
 		return -1;
 	}
 
-	req->rq_xid = transport->tcp_xid;
 	dprintk("RPC:       read callback  XID %08x\n", ntohl(req->rq_xid));
 	xs_tcp_read_common(xprt, desc, req);
 
-	if (!(transport->tcp_flags & TCP_RCV_COPY_DATA)) {
-		struct svc_serv *bc_serv = xprt->bc_serv;
-
-		/*
-		 * Add callback request to callback list.  The callback
-		 * service sleeps on the sv_cb_waitq waiting for new
-		 * requests.  Wake it up after adding enqueing the
-		 * request.
-		 */
-		dprintk("RPC:       add callback request to list\n");
-		spin_lock(&bc_serv->sv_cb_lock);
-		list_add(&req->rq_bc_list, &bc_serv->sv_cb_list);
-		spin_unlock(&bc_serv->sv_cb_lock);
-		wake_up(&bc_serv->sv_cb_waitq);
-	}
-
-	req->rq_private_buf.len = transport->tcp_copied;
+	if (!(transport->tcp_flags & TCP_RCV_COPY_DATA))
+		xprt_complete_bc_request(req, transport->tcp_copied);
+	spin_unlock(&xprt->transport_lock);
 
 	return 0;
 }
@@ -1410,7 +1435,7 @@ static int xs_tcp_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb, uns
  * @bytes: how much data to read
  *
  */
-static void xs_tcp_data_ready(struct sock *sk, int bytes)
+static void xs_tcp_data_ready(struct sock *sk)
 {
 	struct rpc_xprt *xprt;
 	read_descriptor_t rd_desc;
@@ -1470,12 +1495,12 @@ static void xs_tcp_cancel_linger_timeout(struct rpc_xprt *xprt)
 
 static void xs_sock_reset_connection_flags(struct rpc_xprt *xprt)
 {
-	smp_mb__before_clear_bit();
+	smp_mb__before_atomic();
 	clear_bit(XPRT_CONNECTION_ABORT, &xprt->state);
 	clear_bit(XPRT_CONNECTION_CLOSE, &xprt->state);
 	clear_bit(XPRT_CLOSE_WAIT, &xprt->state);
 	clear_bit(XPRT_CLOSING, &xprt->state);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 }
 
 static void xs_sock_mark_closed(struct rpc_xprt *xprt)
@@ -1529,10 +1554,10 @@ static void xs_tcp_state_change(struct sock *sk)
 		xprt->connect_cookie++;
 		xprt->reestablish_timeout = 0;
 		set_bit(XPRT_CLOSING, &xprt->state);
-		smp_mb__before_clear_bit();
+		smp_mb__before_atomic();
 		clear_bit(XPRT_CONNECTED, &xprt->state);
 		clear_bit(XPRT_CLOSE_WAIT, &xprt->state);
-		smp_mb__after_clear_bit();
+		smp_mb__after_atomic();
 		xs_tcp_schedule_linger_timeout(xprt, xs_tcp_fin_timeout);
 		break;
 	case TCP_CLOSE_WAIT:
@@ -1551,9 +1576,9 @@ static void xs_tcp_state_change(struct sock *sk)
 	case TCP_LAST_ACK:
 		set_bit(XPRT_CLOSING, &xprt->state);
 		xs_tcp_schedule_linger_timeout(xprt, xs_tcp_fin_timeout);
-		smp_mb__before_clear_bit();
+		smp_mb__before_atomic();
 		clear_bit(XPRT_CONNECTED, &xprt->state);
-		smp_mb__after_clear_bit();
+		smp_mb__after_atomic();
 		break;
 	case TCP_CLOSE:
 		xs_tcp_cancel_linger_timeout(xprt);
@@ -1674,7 +1699,7 @@ static void xs_udp_timer(struct rpc_xprt *xprt, struct rpc_task *task)
 static unsigned short xs_get_random_port(void)
 {
 	unsigned short range = xprt_max_resvport - xprt_min_resvport;
-	unsigned short rand = (unsigned short) net_random() % range;
+	unsigned short rand = (unsigned short) prandom_u32() % range;
 	return rand + xprt_min_resvport;
 }
 
@@ -1869,6 +1894,7 @@ static int xs_local_finish_connecting(struct rpc_xprt *xprt,
 		sk->sk_user_data = xprt;
 		sk->sk_data_ready = xs_local_data_ready;
 		sk->sk_write_space = xs_udp_write_space;
+		sk->sk_error_report = xs_error_report;
 		sk->sk_allocation = GFP_ATOMIC;
 
 		xprt_clear_connected(xprt);
@@ -2018,7 +2044,6 @@ static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
 		sk->sk_user_data = xprt;
 		sk->sk_data_ready = xs_udp_data_ready;
 		sk->sk_write_space = xs_udp_write_space;
-		sk->sk_no_check = UDP_CSUM_NORCV;
 		sk->sk_allocation = GFP_ATOMIC;
 
 		xprt_set_connected(xprt);
@@ -2146,6 +2171,7 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
 		sk->sk_data_ready = xs_tcp_data_ready;
 		sk->sk_state_change = xs_tcp_state_change;
 		sk->sk_write_space = xs_tcp_write_space;
+		sk->sk_error_report = xs_error_report;
 		sk->sk_allocation = GFP_ATOMIC;
 
 		/* socket options */
@@ -2508,6 +2534,10 @@ static void bc_close(struct rpc_xprt *xprt)
 
 static void bc_destroy(struct rpc_xprt *xprt)
 {
+	dprintk("RPC:       bc_destroy xprt %p\n", xprt);
+
+	xs_xprt_free(xprt);
+	module_put(THIS_MODULE);
 }
 
 static struct rpc_xprt_ops xs_local_ops = {
@@ -2708,7 +2738,7 @@ static struct rpc_xprt *xs_setup_local(struct xprt_create *args)
 		return xprt;
 	ret = ERR_PTR(-EINVAL);
 out_err:
-	xprt_free(xprt);
+	xs_xprt_free(xprt);
 	return ret;
 }
 
@@ -2786,7 +2816,7 @@ static struct rpc_xprt *xs_setup_udp(struct xprt_create *args)
 		return xprt;
 	ret = ERR_PTR(-EINVAL);
 out_err:
-	xprt_free(xprt);
+	xs_xprt_free(xprt);
 	return ret;
 }
 
@@ -2861,12 +2891,11 @@ static struct rpc_xprt *xs_setup_tcp(struct xprt_create *args)
 				xprt->address_strings[RPC_DISPLAY_ADDR],
 				xprt->address_strings[RPC_DISPLAY_PROTO]);
 
-
 	if (try_module_get(THIS_MODULE))
 		return xprt;
 	ret = ERR_PTR(-EINVAL);
 out_err:
-	xprt_free(xprt);
+	xs_xprt_free(xprt);
 	return ret;
 }
 
@@ -2883,15 +2912,6 @@ static struct rpc_xprt *xs_setup_bc_tcp(struct xprt_create *args)
 	struct svc_sock *bc_sock;
 	struct rpc_xprt *ret;
 
-	if (args->bc_xprt->xpt_bc_xprt) {
-		/*
-		 * This server connection already has a backchannel
-		 * transport; we can't create a new one, as we wouldn't
-		 * be able to match replies based on xid any more.  So,
-		 * reuse the already-existing one:
-		 */
-		 return args->bc_xprt->xpt_bc_xprt;
-	}
 	xprt = xs_setup_xprt(args, xprt_tcp_slot_table_entries,
 			xprt_tcp_slot_table_entries);
 	if (IS_ERR(xprt))
@@ -2932,10 +2952,9 @@ static struct rpc_xprt *xs_setup_bc_tcp(struct xprt_create *args)
 
 	/*
 	 * Once we've associated a backchannel xprt with a connection,
-	 * we want to keep it around as long as long as the connection
-	 * lasts, in case we need to start using it for a backchannel
-	 * again; this reference won't be dropped until bc_xprt is
-	 * destroyed.
+	 * we want to keep it around as long as the connection lasts,
+	 * in case we need to start using it for a backchannel again;
+	 * this reference won't be dropped until bc_xprt is destroyed.
 	 */
 	xprt_get(xprt);
 	args->bc_xprt->xpt_bc_xprt = xprt;
@@ -2950,13 +2969,14 @@ static struct rpc_xprt *xs_setup_bc_tcp(struct xprt_create *args)
 	 */
 	xprt_set_connected(xprt);
 
-
 	if (try_module_get(THIS_MODULE))
 		return xprt;
+
+	args->bc_xprt->xpt_bc_xprt = NULL;
 	xprt_put(xprt);
 	ret = ERR_PTR(-EINVAL);
 out_err:
-	xprt_free(xprt);
+	xs_xprt_free(xprt);
 	return ret;
 }