[PATCH] IB/mthca: fix posting of first work request

Fix posting first WQE for mem-free HCAs: we need to link to previous
WQE even in that case.  While we're at it, simplify code for
Tavor-mode HCAs.  We don't really need the conditional test there
either; we can similarly always link to the previous WQE.

Based on Michael S. Tsirkin's analogous fix for userspace libmthca.
Signed-off-by: Roland Dreier <rolandd@cisco.com>

drivers/infiniband/hw/mthca/mthca_qp.c

@@ -227,7 +227,6 @@ static void mthca_wq_init(struct mthca_wq *wq)
 	wq->last_comp = wq->max - 1;
 	wq->head      = 0;
 	wq->tail      = 0;
-	wq->last      = NULL;
 }
 
 void mthca_qp_event(struct mthca_dev *dev, u32 qpn,
@@ -1103,6 +1102,9 @@ static int mthca_alloc_qp_common(struct mthca_dev *dev,
 		}
 	}
 
+	qp->sq.last = get_send_wqe(qp, qp->sq.max - 1);
+	qp->rq.last = get_recv_wqe(qp, qp->rq.max - 1);
+
 	return 0;
 }
 
@@ -1583,15 +1585,13 @@ int mthca_tavor_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 			goto out;
 		}
 
-		if (prev_wqe) {
-			((struct mthca_next_seg *) prev_wqe)->nda_op =
-				cpu_to_be32(((ind << qp->sq.wqe_shift) +
-					     qp->send_wqe_offset) |
-					    mthca_opcode[wr->opcode]);
-			wmb();
-			((struct mthca_next_seg *) prev_wqe)->ee_nds =
-				cpu_to_be32((size0 ? 0 : MTHCA_NEXT_DBD) | size);
-		}
+		((struct mthca_next_seg *) prev_wqe)->nda_op =
+			cpu_to_be32(((ind << qp->sq.wqe_shift) +
+				     qp->send_wqe_offset) |
+				    mthca_opcode[wr->opcode]);
+		wmb();
+		((struct mthca_next_seg *) prev_wqe)->ee_nds =
+			cpu_to_be32((size0 ? 0 : MTHCA_NEXT_DBD) | size);
 
 		if (!size0) {
 			size0 = size;
@@ -1688,13 +1688,11 @@ int mthca_tavor_post_receive(struct ib_qp *ibqp, struct ib_recv_wr *wr,
 
 		qp->wrid[ind] = wr->wr_id;
 
-		if (likely(prev_wqe)) {
-			((struct mthca_next_seg *) prev_wqe)->nda_op =
-				cpu_to_be32((ind << qp->rq.wqe_shift) | 1);
-			wmb();
-			((struct mthca_next_seg *) prev_wqe)->ee_nds =
-				cpu_to_be32(MTHCA_NEXT_DBD | size);
-		}
+		((struct mthca_next_seg *) prev_wqe)->nda_op =
+			cpu_to_be32((ind << qp->rq.wqe_shift) | 1);
+		wmb();
+		((struct mthca_next_seg *) prev_wqe)->ee_nds =
+			cpu_to_be32(MTHCA_NEXT_DBD | size);
 
 		if (!size0)
 			size0 = size;
@@ -1905,15 +1903,13 @@ int mthca_arbel_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 			goto out;
 		}
 
-		if (likely(prev_wqe)) {
-			((struct mthca_next_seg *) prev_wqe)->nda_op =
-				cpu_to_be32(((ind << qp->sq.wqe_shift) +
-					     qp->send_wqe_offset) |
-					    mthca_opcode[wr->opcode]);
-			wmb();
-			((struct mthca_next_seg *) prev_wqe)->ee_nds =
-				cpu_to_be32(MTHCA_NEXT_DBD | size);
-		}
+		((struct mthca_next_seg *) prev_wqe)->nda_op =
+			cpu_to_be32(((ind << qp->sq.wqe_shift) +
+				     qp->send_wqe_offset) |
+				    mthca_opcode[wr->opcode]);
+		wmb();
+		((struct mthca_next_seg *) prev_wqe)->ee_nds =
+			cpu_to_be32(MTHCA_NEXT_DBD | size);
 
 		if (!size0) {
 			size0 = size;

drivers/infiniband/hw/mthca/mthca_srq.c

@@ -189,7 +189,6 @@ int mthca_alloc_srq(struct mthca_dev *dev, struct mthca_pd *pd,
 
 	srq->max      = attr->max_wr;
 	srq->max_gs   = attr->max_sge;
-	srq->last     = NULL;
 	srq->counter  = 0;
 
 	if (mthca_is_memfree(dev))
@@ -264,6 +263,7 @@ int mthca_alloc_srq(struct mthca_dev *dev, struct mthca_pd *pd,
 
 	srq->first_free = 0;
 	srq->last_free  = srq->max - 1;
+	srq->last	= get_wqe(srq, srq->max - 1);
 
 	return 0;
 
@@ -446,13 +446,11 @@ int mthca_tavor_post_srq_recv(struct ib_srq *ibsrq, struct ib_recv_wr *wr,
 			((struct mthca_data_seg *) wqe)->addr = 0;
 		}
 
-		if (likely(prev_wqe)) {
-			((struct mthca_next_seg *) prev_wqe)->nda_op =
-				cpu_to_be32((ind << srq->wqe_shift) | 1);
-			wmb();
-			((struct mthca_next_seg *) prev_wqe)->ee_nds =
-				cpu_to_be32(MTHCA_NEXT_DBD);
-		}
+		((struct mthca_next_seg *) prev_wqe)->nda_op =
+			cpu_to_be32((ind << srq->wqe_shift) | 1);
+		wmb();
+		((struct mthca_next_seg *) prev_wqe)->ee_nds =
+			cpu_to_be32(MTHCA_NEXT_DBD);
 
 		srq->wrid[ind]  = wr->wr_id;
 		srq->first_free = next_ind;