diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 289d13cad638cf17f72ee41e0f87361332373de9..d7c4255e9d5db2448bdb0da23180b6db281472ba 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -225,51 +225,35 @@ xprt_rdma_free_addresses(struct rpc_xprt *xprt) } } -void -rpcrdma_conn_func(struct rpcrdma_ep *ep) -{ - schedule_delayed_work(&ep->rep_connect_worker, 0); -} - -void -rpcrdma_connect_worker(struct work_struct *work) +/** + * xprt_rdma_connect_worker - establish connection in the background + * @work: worker thread context + * + * Requester holds the xprt's send lock to prevent activity on this + * transport while a fresh connection is being established. RPC tasks + * sleep on the xprt's pending queue waiting for connect to complete. + */ +static void +xprt_rdma_connect_worker(struct work_struct *work) { - struct rpcrdma_ep *ep = - container_of(work, struct rpcrdma_ep, rep_connect_worker.work); - struct rpcrdma_xprt *r_xprt = - container_of(ep, struct rpcrdma_xprt, rx_ep); + struct rpcrdma_xprt *r_xprt = container_of(work, struct rpcrdma_xprt, + rx_connect_worker.work); struct rpc_xprt *xprt = &r_xprt->rx_xprt; + int rc; - spin_lock_bh(&xprt->transport_lock); - if (ep->rep_connected > 0) { + rc = rpcrdma_ep_connect(&r_xprt->rx_ep, &r_xprt->rx_ia); + xprt_clear_connecting(xprt); + if (r_xprt->rx_ep.rep_connected > 0) { if (!xprt_test_and_set_connected(xprt)) { xprt->stat.connect_count++; xprt->stat.connect_time += (long)jiffies - xprt->stat.connect_start; - xprt_wake_pending_tasks(xprt, 0); + xprt_wake_pending_tasks(xprt, -EAGAIN); } } else { if (xprt_test_and_clear_connected(xprt)) - xprt_wake_pending_tasks(xprt, -ENOTCONN); + xprt_wake_pending_tasks(xprt, rc); } - spin_unlock_bh(&xprt->transport_lock); -} - -static void -xprt_rdma_connect_worker(struct work_struct *work) -{ - struct rpcrdma_xprt *r_xprt = container_of(work, struct rpcrdma_xprt, - rx_connect_worker.work); - struct rpc_xprt *xprt = &r_xprt->rx_xprt; - int rc = 0; - - xprt_clear_connected(xprt); - - rc = rpcrdma_ep_connect(&r_xprt->rx_ep, &r_xprt->rx_ia); - if (rc) - xprt_wake_pending_tasks(xprt, rc); - - xprt_clear_connecting(xprt); } static void @@ -302,8 +286,6 @@ xprt_rdma_destroy(struct rpc_xprt *xprt) cancel_delayed_work_sync(&r_xprt->rx_connect_worker); - xprt_clear_connected(xprt); - rpcrdma_ep_destroy(&r_xprt->rx_ep, &r_xprt->rx_ia); rpcrdma_buffer_destroy(&r_xprt->rx_buf); rpcrdma_ia_close(&r_xprt->rx_ia); diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index c60172f88a0d64f70f307f892b57a27895404683..abbd3cdc259af157a891b104e67e8de7ee8b99de 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -108,6 +108,25 @@ rpcrdma_destroy_wq(void) } } +/** + * rpcrdma_disconnect_worker - Force a disconnect + * @work: endpoint to be disconnected + * + * Provider callbacks can possibly run in an IRQ context. This function + * is invoked in a worker thread to guarantee that disconnect wake-up + * calls are always done in process context. + */ +static void +rpcrdma_disconnect_worker(struct work_struct *work) +{ + struct rpcrdma_ep *ep = container_of(work, struct rpcrdma_ep, + rep_disconnect_worker.work); + struct rpcrdma_xprt *r_xprt = + container_of(ep, struct rpcrdma_xprt, rx_ep); + + xprt_force_disconnect(&r_xprt->rx_xprt); +} + static void rpcrdma_qp_async_error_upcall(struct ib_event *event, void *context) { @@ -121,7 +140,7 @@ rpcrdma_qp_async_error_upcall(struct ib_event *event, void *context) if (ep->rep_connected == 1) { ep->rep_connected = -EIO; - rpcrdma_conn_func(ep); + schedule_delayed_work(&ep->rep_disconnect_worker, 0); wake_up_all(&ep->rep_connect_wait); } } @@ -271,13 +290,14 @@ rpcrdma_cm_event_handler(struct rdma_cm_id *id, struct rdma_cm_event *event) ++xprt->connect_cookie; ep->rep_connected = 1; rpcrdma_update_connect_private(r_xprt, &event->param.conn); - goto connected; + wake_up_all(&ep->rep_connect_wait); + break; case RDMA_CM_EVENT_CONNECT_ERROR: ep->rep_connected = -ENOTCONN; - goto connected; + goto disconnected; case RDMA_CM_EVENT_UNREACHABLE: ep->rep_connected = -ENETUNREACH; - goto connected; + goto disconnected; case RDMA_CM_EVENT_REJECTED: dprintk("rpcrdma: connection to %s:%s rejected: %s\n", rpcrdma_addrstr(r_xprt), rpcrdma_portstr(r_xprt), @@ -285,12 +305,12 @@ rpcrdma_cm_event_handler(struct rdma_cm_id *id, struct rdma_cm_event *event) ep->rep_connected = -ECONNREFUSED; if (event->status == IB_CM_REJ_STALE_CONN) ep->rep_connected = -EAGAIN; - goto connected; + goto disconnected; case RDMA_CM_EVENT_DISCONNECTED: ++xprt->connect_cookie; ep->rep_connected = -ECONNABORTED; -connected: - rpcrdma_conn_func(ep); +disconnected: + xprt_force_disconnect(xprt); wake_up_all(&ep->rep_connect_wait); break; default: @@ -550,7 +570,8 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia, cdata->max_requests >> 2); ep->rep_send_count = ep->rep_send_batch; init_waitqueue_head(&ep->rep_connect_wait); - INIT_DELAYED_WORK(&ep->rep_connect_worker, rpcrdma_connect_worker); + INIT_DELAYED_WORK(&ep->rep_disconnect_worker, + rpcrdma_disconnect_worker); sendcq = ib_alloc_cq(ia->ri_device, NULL, ep->rep_attr.cap.max_send_wr + 1, @@ -623,7 +644,7 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia, void rpcrdma_ep_destroy(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia) { - cancel_delayed_work_sync(&ep->rep_connect_worker); + cancel_delayed_work_sync(&ep->rep_disconnect_worker); if (ia->ri_id && ia->ri_id->qp) { rpcrdma_ep_disconnect(ep, ia); @@ -736,6 +757,7 @@ rpcrdma_ep_connect(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia) { struct rpcrdma_xprt *r_xprt = container_of(ia, struct rpcrdma_xprt, rx_ia); + struct rpc_xprt *xprt = &r_xprt->rx_xprt; int rc; retry: @@ -762,6 +784,8 @@ rpcrdma_ep_connect(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia) } ep->rep_connected = 0; + xprt_clear_connected(xprt); + rpcrdma_post_recvs(r_xprt, true); rc = rdma_connect(ia->ri_id, &ep->rep_remote_cma); diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index eae21668e692200095bb382a8ed6ad0b2dbd999e..a13ccb643ce07e0a3838079f914a20ee586c417e 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -101,7 +101,7 @@ struct rpcrdma_ep { wait_queue_head_t rep_connect_wait; struct rpcrdma_connect_private rep_cm_private; struct rdma_conn_param rep_remote_cma; - struct delayed_work rep_connect_worker; + struct delayed_work rep_disconnect_worker; }; /* Pre-allocate extra Work Requests for handling backward receives @@ -556,7 +556,6 @@ int rpcrdma_ep_create(struct rpcrdma_ep *, struct rpcrdma_ia *, struct rpcrdma_create_data_internal *); void rpcrdma_ep_destroy(struct rpcrdma_ep *, struct rpcrdma_ia *); int rpcrdma_ep_connect(struct rpcrdma_ep *, struct rpcrdma_ia *); -void rpcrdma_conn_func(struct rpcrdma_ep *ep); void rpcrdma_ep_disconnect(struct rpcrdma_ep *, struct rpcrdma_ia *); int rpcrdma_ep_post(struct rpcrdma_ia *, struct rpcrdma_ep *, @@ -654,7 +653,6 @@ static inline void rpcrdma_set_xdrlen(struct xdr_buf *xdr, size_t len) extern unsigned int xprt_rdma_max_inline_read; void xprt_rdma_format_addresses(struct rpc_xprt *xprt, struct sockaddr *sap); void xprt_rdma_free_addresses(struct rpc_xprt *xprt); -void rpcrdma_connect_worker(struct work_struct *work); void xprt_rdma_print_stats(struct rpc_xprt *xprt, struct seq_file *seq); int xprt_rdma_init(void); void xprt_rdma_cleanup(void);