RDMA/rxe: Don't schedule rxe_completer from rxe_requester

Now that rxe_completer() is always called serially after rxe_requester()
there is no reason to schedule rxe_completer() from rxe_requester().

Link: https://lore.kernel.org/r/20240329145513.35381-9-rpearsonhpe@gmail.comSigned-off-by: Bob Pearson <rpearsonhpe@gmail.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

drivers/infiniband/sw/rxe/rxe_net.c

@@ -440,12 +440,6 @@ int rxe_xmit_packet(struct rxe_qp *qp, struct rxe_pkt_info *pkt,
 		return err;
 	}
 
-	if ((qp_type(qp) != IB_QPT_RC) &&
-	    (pkt->mask & RXE_END_MASK)) {
-		pkt->wqe->state = wqe_state_done;
-		rxe_sched_task(&qp->send_task);
-	}
-
 	rxe_counter_inc(rxe, RXE_CNT_SENT_PKTS);
 	goto done;
 

drivers/infiniband/sw/rxe/rxe_req.c

@@ -545,6 +545,8 @@ static void update_wqe_state(struct rxe_qp *qp,
 	if (pkt->mask & RXE_END_MASK) {
 		if (qp_type(qp) == IB_QPT_RC)
 			wqe->state = wqe_state_pending;
+		else
+			wqe->state = wqe_state_done;
 	} else {
 		wqe->state = wqe_state_processing;
 	}
@@ -631,12 +633,6 @@ static int rxe_do_local_ops(struct rxe_qp *qp, struct rxe_send_wqe *wqe)
 	wqe->status = IB_WC_SUCCESS;
 	qp->req.wqe_index = queue_next_index(qp->sq.queue, qp->req.wqe_index);
 
-	/* There is no ack coming for local work requests
-	 * which can lead to a deadlock. So go ahead and complete
-	 * it now.
-	 */
-	rxe_sched_task(&qp->send_task);
-
 	return 0;
 }
 
@@ -760,7 +756,6 @@ int rxe_requester(struct rxe_qp *qp)
 						       qp->req.wqe_index);
 			wqe->state = wqe_state_done;
 			wqe->status = IB_WC_SUCCESS;
-			rxe_sched_task(&qp->send_task);
 			goto done;
 		}
 		payload = mtu;