From: Tariq Toukan <tariqt@mellanox.com>
Date: Sun, 25 Jun 2017 16:28:46 +0300
Subject: net/mlx5e: Small enhancements for RX MPWQE allocation and free
Patch-mainline: v4.14-rc1
Git-commit: 4c2af5cc2bee32685883b55328d8b5ec80e1781f
References: bsc#1046305 FATE#322943

The dma offset of a MPWQE (Multi-Packet WQE) in memory region
is fixed for all rounds. Calculate it once on creation time,
instead of in runtime. This also obsoletes the wqe argument in
the function.

In addition, optimize dma_info iterator calculation.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Acked-by: Thomas Bogendoerfer <tbogendoerfer@suse.de>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c |    6 ++++++
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c   |   18 ++++++------------
 2 files changed, 12 insertions(+), 12 deletions(-)

--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -681,6 +681,12 @@ static int mlx5e_alloc_rq(struct mlx5e_c
 	for (i = 0; i < wq_sz; i++) {
 		struct mlx5e_rx_wqe *wqe = mlx5_wq_ll_get_wqe(&rq->wq, i);
 
+		if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
+			u64 dma_offset = (u64)mlx5e_get_wqe_mtt_offset(rq, i) << PAGE_SHIFT;
+
+			wqe->data.addr = cpu_to_be64(dma_offset);
+		}
+
 		wqe->data.byte_count = cpu_to_be32(byte_count);
 		wqe->data.lkey = rq->mkey_be;
 	}
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -374,18 +374,15 @@ static inline void mlx5e_post_umr_wqe(st
 }
 
 static int mlx5e_alloc_rx_umr_mpwqe(struct mlx5e_rq *rq,
-				    struct mlx5e_rx_wqe *wqe,
 				    u16 ix)
 {
 	struct mlx5e_mpw_info *wi = &rq->mpwqe.info[ix];
-	u64 dma_offset = (u64)mlx5e_get_wqe_mtt_offset(rq, ix) << PAGE_SHIFT;
 	int pg_strides = mlx5e_mpwqe_strides_per_page(rq);
+	struct mlx5e_dma_info *dma_info = &wi->umr.dma_info[0];
 	int err;
 	int i;
 
-	for (i = 0; i < MLX5_MPWRQ_PAGES_PER_WQE; i++) {
-		struct mlx5e_dma_info *dma_info = &wi->umr.dma_info[i];
-
+	for (i = 0; i < MLX5_MPWRQ_PAGES_PER_WQE; i++, dma_info++) {
 		err = mlx5e_page_alloc_mapped(rq, dma_info);
 		if (unlikely(err))
 			goto err_unmap;
@@ -395,14 +392,12 @@ static int mlx5e_alloc_rx_umr_mpwqe(stru
 
 	memset(wi->skbs_frags, 0, sizeof(*wi->skbs_frags) * MLX5_MPWRQ_PAGES_PER_WQE);
 	wi->consumed_strides = 0;
-	wqe->data.addr = cpu_to_be64(dma_offset);
 
 	return 0;
 
 err_unmap:
 	while (--i >= 0) {
-		struct mlx5e_dma_info *dma_info = &wi->umr.dma_info[i];
-
+		dma_info--;
 		page_ref_sub(dma_info->page, pg_strides);
 		mlx5e_page_release(rq, dma_info, true);
 	}
@@ -413,11 +408,10 @@ err_unmap:
 void mlx5e_free_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi)
 {
 	int pg_strides = mlx5e_mpwqe_strides_per_page(rq);
+	struct mlx5e_dma_info *dma_info = &wi->umr.dma_info[0];
 	int i;
 
-	for (i = 0; i < MLX5_MPWRQ_PAGES_PER_WQE; i++) {
-		struct mlx5e_dma_info *dma_info = &wi->umr.dma_info[i];
-
+	for (i = 0; i < MLX5_MPWRQ_PAGES_PER_WQE; i++, dma_info++) {
 		page_ref_sub(dma_info->page, pg_strides - wi->skbs_frags[i]);
 		mlx5e_page_release(rq, dma_info, true);
 	}
@@ -447,7 +441,7 @@ int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq
 {
 	int err;
 
-	err = mlx5e_alloc_rx_umr_mpwqe(rq, wqe, ix);
+	err = mlx5e_alloc_rx_umr_mpwqe(rq, ix);
 	if (unlikely(err))
 		return err;
 	set_bit(MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS, &rq->state);