staging/rdma/hfi1: Insure last cursor is updated prior to complete

This patch is a prerequisite for adding a separate lock
for post send.

The timing of updating s_last needs to be before returning
any send completion to avoid a race between a poll cq seeing
a completion and the post send checking for a full queue.
Reviewed-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: NMike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

drivers/staging/rdma/hfi1/rc.c

@@ -1123,10 +1123,18 @@ void hfi1_rc_send_complete(struct rvt_qp *qp, struct hfi1_ib_header *hdr)
 		hfi1_add_retry_timer(qp);
 
 	while (qp->s_last != qp->s_acked) {
+		u32 s_last;
+
 		wqe = rvt_get_swqe_ptr(qp, qp->s_last);
 		if (cmp_psn(wqe->lpsn, qp->s_sending_psn) >= 0 &&
 		    cmp_psn(qp->s_sending_psn, qp->s_sending_hpsn) <= 0)
 			break;
+		s_last = qp->s_last;
+		if (++s_last >= qp->s_size)
+			s_last = 0;
+		qp->s_last = s_last;
+		/* see post_send() */
+		barrier();
 		for (i = 0; i < wqe->wr.num_sge; i++) {
 			struct rvt_sge *sge = &wqe->sg_list[i];
 
@@ -1143,8 +1151,6 @@ void hfi1_rc_send_complete(struct rvt_qp *qp, struct hfi1_ib_header *hdr)
 			wc.qp = &qp->ibqp;
 			rvt_cq_enter(ibcq_to_rvtcq(qp->ibqp.send_cq), &wc, 0);
 		}
-		if (++qp->s_last >= qp->s_size)
-			qp->s_last = 0;
 	}
 	/*
 	 * If we were waiting for sends to complete before re-sending,
@@ -1184,11 +1190,19 @@ static struct rvt_swqe *do_rc_completion(struct rvt_qp *qp,
 	 */
 	if (cmp_psn(wqe->lpsn, qp->s_sending_psn) < 0 ||
 	    cmp_psn(qp->s_sending_psn, qp->s_sending_hpsn) > 0) {
+		u32 s_last;
+
 		for (i = 0; i < wqe->wr.num_sge; i++) {
 			struct rvt_sge *sge = &wqe->sg_list[i];
 
 			rvt_put_mr(sge->mr);
 		}
+		s_last = qp->s_last;
+		if (++s_last >= qp->s_size)
+			s_last = 0;
+		qp->s_last = s_last;
+		/* see post_send() */
+		barrier();
 		/* Post a send completion queue entry if requested. */
 		if (!(qp->s_flags & RVT_S_SIGNAL_REQ_WR) ||
 		    (wqe->wr.send_flags & IB_SEND_SIGNALED)) {
@@ -1200,8 +1214,6 @@ static struct rvt_swqe *do_rc_completion(struct rvt_qp *qp,
 			wc.qp = &qp->ibqp;
 			rvt_cq_enter(ibcq_to_rvtcq(qp->ibqp.send_cq), &wc, 0);
 		}
-		if (++qp->s_last >= qp->s_size)
-			qp->s_last = 0;
 	} else {
 		struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
 

drivers/staging/rdma/hfi1/ruc.c

@@ -921,6 +921,13 @@ void hfi1_send_complete(struct rvt_qp *qp, struct rvt_swqe *wqe,
 	if (!(ib_rvt_state_ops[qp->state] & RVT_PROCESS_OR_FLUSH_SEND))
 		return;
 
+	last = qp->s_last;
+	old_last = last;
+	if (++last >= qp->s_size)
+		last = 0;
+	qp->s_last = last;
+	/* See post_send() */
+	barrier();
 	for (i = 0; i < wqe->wr.num_sge; i++) {
 		struct rvt_sge *sge = &wqe->sg_list[i];
 
@@ -948,11 +955,6 @@ void hfi1_send_complete(struct rvt_qp *qp, struct rvt_swqe *wqe,
 			     status != IB_WC_SUCCESS);
 	}
 
-	last = qp->s_last;
-	old_last = last;
-	if (++last >= qp->s_size)
-		last = 0;
-	qp->s_last = last;
 	if (qp->s_acked == old_last)
 		qp->s_acked = last;
 	if (qp->s_cur == old_last)