IB/mthca: Factor out setting WQE data segment entries

Factor code to set data segment entries out of the work request
posting functions into inline functions mthca_set_data_seg() and
mthca_set_data_seg_inval().  This makes the code more readable and
also allows the compiler to do a better job -- on x86_64:

add/remove: 0/0 grow/shrink: 0/6 up/down: 0/-69 (-69)
function                                     old     new   delta
mthca_arbel_post_srq_recv                    373     369      -4
mthca_arbel_post_receive                     570     562      -8
mthca_tavor_post_srq_recv                    520     508     -12
mthca_tavor_post_send                       1344    1330     -14
mthca_arbel_post_send                       1481    1467     -14
mthca_tavor_post_receive                     792     775     -17

Signed-off-by: Roland Dreier <rolandd@cisco.com>

drivers/infiniband/hw/mthca/mthca_qp.c

@@ -1740,13 +1740,8 @@ int mthca_tavor_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 		}
 
 		for (i = 0; i < wr->num_sge; ++i) {
-			((struct mthca_data_seg *) wqe)->byte_count =
-				cpu_to_be32(wr->sg_list[i].length);
-			((struct mthca_data_seg *) wqe)->lkey =
-				cpu_to_be32(wr->sg_list[i].lkey);
-			((struct mthca_data_seg *) wqe)->addr =
-				cpu_to_be64(wr->sg_list[i].addr);
-			wqe += sizeof (struct mthca_data_seg);
+			mthca_set_data_seg(wqe, wr->sg_list + i);
+			wqe  += sizeof (struct mthca_data_seg);
 			size += sizeof (struct mthca_data_seg) / 16;
 		}
 
@@ -1869,13 +1864,8 @@ int mthca_tavor_post_receive(struct ib_qp *ibqp, struct ib_recv_wr *wr,
 		}
 
 		for (i = 0; i < wr->num_sge; ++i) {
-			((struct mthca_data_seg *) wqe)->byte_count =
-				cpu_to_be32(wr->sg_list[i].length);
-			((struct mthca_data_seg *) wqe)->lkey =
-				cpu_to_be32(wr->sg_list[i].lkey);
-			((struct mthca_data_seg *) wqe)->addr =
-				cpu_to_be64(wr->sg_list[i].addr);
-			wqe += sizeof (struct mthca_data_seg);
+			mthca_set_data_seg(wqe, wr->sg_list + i);
+			wqe  += sizeof (struct mthca_data_seg);
 			size += sizeof (struct mthca_data_seg) / 16;
 		}
 
@@ -2125,13 +2115,8 @@ int mthca_arbel_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 		}
 
 		for (i = 0; i < wr->num_sge; ++i) {
-			((struct mthca_data_seg *) wqe)->byte_count =
-				cpu_to_be32(wr->sg_list[i].length);
-			((struct mthca_data_seg *) wqe)->lkey =
-				cpu_to_be32(wr->sg_list[i].lkey);
-			((struct mthca_data_seg *) wqe)->addr =
-				cpu_to_be64(wr->sg_list[i].addr);
-			wqe += sizeof (struct mthca_data_seg);
+			mthca_set_data_seg(wqe, wr->sg_list + i);
+			wqe  += sizeof (struct mthca_data_seg);
 			size += sizeof (struct mthca_data_seg) / 16;
 		}
 
@@ -2253,20 +2238,12 @@ int mthca_arbel_post_receive(struct ib_qp *ibqp, struct ib_recv_wr *wr,
 		}
 
 		for (i = 0; i < wr->num_sge; ++i) {
-			((struct mthca_data_seg *) wqe)->byte_count =
-				cpu_to_be32(wr->sg_list[i].length);
-			((struct mthca_data_seg *) wqe)->lkey =
-				cpu_to_be32(wr->sg_list[i].lkey);
-			((struct mthca_data_seg *) wqe)->addr =
-				cpu_to_be64(wr->sg_list[i].addr);
+			mthca_set_data_seg(wqe, wr->sg_list + i);
 			wqe += sizeof (struct mthca_data_seg);
 		}
 
-		if (i < qp->rq.max_gs) {
-			((struct mthca_data_seg *) wqe)->byte_count = 0;
-			((struct mthca_data_seg *) wqe)->lkey = cpu_to_be32(MTHCA_INVAL_LKEY);
-			((struct mthca_data_seg *) wqe)->addr = 0;
-		}
+		if (i < qp->rq.max_gs)
+			mthca_set_data_seg_inval(wqe);
 
 		qp->wrid[ind] = wr->wr_id;
 

drivers/infiniband/hw/mthca/mthca_srq.c

@@ -543,20 +543,12 @@ int mthca_tavor_post_srq_recv(struct ib_srq *ibsrq, struct ib_recv_wr *wr,
 		}
 
 		for (i = 0; i < wr->num_sge; ++i) {
-			((struct mthca_data_seg *) wqe)->byte_count =
-				cpu_to_be32(wr->sg_list[i].length);
-			((struct mthca_data_seg *) wqe)->lkey =
-				cpu_to_be32(wr->sg_list[i].lkey);
-			((struct mthca_data_seg *) wqe)->addr =
-				cpu_to_be64(wr->sg_list[i].addr);
+			mthca_set_data_seg(wqe, wr->sg_list + i);
 			wqe += sizeof (struct mthca_data_seg);
 		}
 
-		if (i < srq->max_gs) {
-			((struct mthca_data_seg *) wqe)->byte_count = 0;
-			((struct mthca_data_seg *) wqe)->lkey = cpu_to_be32(MTHCA_INVAL_LKEY);
-			((struct mthca_data_seg *) wqe)->addr = 0;
-		}
+		if (i < srq->max_gs)
+			mthca_set_data_seg_inval(wqe);
 
 		((struct mthca_next_seg *) prev_wqe)->nda_op =
 			cpu_to_be32((ind << srq->wqe_shift) | 1);
@@ -662,20 +654,12 @@ int mthca_arbel_post_srq_recv(struct ib_srq *ibsrq, struct ib_recv_wr *wr,
 		}
 
 		for (i = 0; i < wr->num_sge; ++i) {
-			((struct mthca_data_seg *) wqe)->byte_count =
-				cpu_to_be32(wr->sg_list[i].length);
-			((struct mthca_data_seg *) wqe)->lkey =
-				cpu_to_be32(wr->sg_list[i].lkey);
-			((struct mthca_data_seg *) wqe)->addr =
-				cpu_to_be64(wr->sg_list[i].addr);
+			mthca_set_data_seg(wqe, wr->sg_list + i);
 			wqe += sizeof (struct mthca_data_seg);
 		}
 
-		if (i < srq->max_gs) {
-			((struct mthca_data_seg *) wqe)->byte_count = 0;
-			((struct mthca_data_seg *) wqe)->lkey = cpu_to_be32(MTHCA_INVAL_LKEY);
-			((struct mthca_data_seg *) wqe)->addr = 0;
-		}
+		if (i < srq->max_gs)
+			mthca_set_data_seg_inval(wqe);
 
 		srq->wrid[ind]  = wr->wr_id;
 		srq->first_free = next_ind;

drivers/infiniband/hw/mthca/mthca_wqe.h

@@ -113,4 +113,19 @@ struct mthca_mlx_seg {
 	__be16 vcrc;
 };
 
+static __always_inline void mthca_set_data_seg(struct mthca_data_seg *dseg,
+					       struct ib_sge *sg)
+{
+	dseg->byte_count = cpu_to_be32(sg->length);
+	dseg->lkey       = cpu_to_be32(sg->lkey);
+	dseg->addr       = cpu_to_be64(sg->addr);
+}
+
+static __always_inline void mthca_set_data_seg_inval(struct mthca_data_seg *dseg)
+{
+	dseg->byte_count = 0;
+	dseg->lkey       = cpu_to_be32(MTHCA_INVAL_LKEY);
+	dseg->addr       = 0;
+}
+
 #endif /* MTHCA_WQE_H */