From: Maxim Mikityanskiy <maximmi@nvidia.com>
Date: Thu, 29 Sep 2022 00:21:44 -0700
Subject: net/mlx5e: Keep a separate MKey for striding RQ
Patch-mainline: v6.1-rc1
Git-commit: ecc7ad2eab35f180588a60adc5c2b76262dc8d71
References: jsc#PED-1549

Currently, rq->mkey_be keeps a big-endian value of either the PA MKey
(for legacy RQ, no address translation) or MTT MKey (for striding RQ,
direct address translation). Striding RQ stores the same value in
rq->umr_mkey in the native endianness.

The next commit will make striding RQ use KSM MKey (indirect address
translation) for the unaligned mode of XSK, which will require storing
both KSM MKey and PA MKey in the RQ struct. This commit optimizes fields
of mlx5e_rq: umr_mkey is removed (it's redundant), mkey_be always points
to the PA MKey, and mpwqe.umr_mkey_be points to the MTT MKey (or to the
KSM MKey, starting from the next commit).

Signed-off-by: Maxim Mikityanskiy <maximmi@nvidia.com>
Reviewed-by: Saeed Mahameed <saeedm@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Thomas Bogendoerfer <tbogendoerfer@suse.de>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h      |    2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c |   21 ++++++++++++---------
 2 files changed, 13 insertions(+), 10 deletions(-)

--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -696,6 +696,7 @@ struct mlx5e_rq {
 			struct mlx5e_umr_wqe   umr_wqe;
 			struct mlx5e_mpw_info *info;
 			mlx5e_fp_skb_from_cqe_mpwrq skb_from_cqe_mpwrq;
+			__be32                 umr_mkey_be;
 			u16                    num_strides;
 			u16                    actual_wq_head;
 			u8                     log_stride_sz;
@@ -757,7 +758,6 @@ struct mlx5e_rq {
 	u32                    rqn;
 	struct mlx5_core_dev  *mdev;
 	struct mlx5e_channel  *channel;
-	u32  umr_mkey;
 	struct mlx5e_dma_info  wqe_overflow;
 
 	/* XDP read-mostly */
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -215,7 +215,7 @@ static inline void mlx5e_build_umr_wqe(s
 
 	cseg->qpn_ds    = cpu_to_be32((sq->sqn << MLX5_WQE_CTRL_QPN_SHIFT) |
 				      ds_cnt);
-	cseg->umr_mkey  = rq->mkey_be;
+	cseg->umr_mkey  = rq->mpwqe.umr_mkey_be;
 
 	ucseg->flags = MLX5_UMR_TRANSLATION_OFFSET_EN | MLX5_UMR_INLINE;
 	ucseg->xlt_octowords =
@@ -365,9 +365,13 @@ static int mlx5e_create_umr_klm_mkey(str
 static int mlx5e_create_rq_umr_mkey(struct mlx5_core_dev *mdev, struct mlx5e_rq *rq)
 {
 	u64 num_mtts = mlx5_wq_ll_get_size(&rq->mpwqe.wq) * rq->mpwqe.mtts_per_wqe;
+	u32 umr_mkey;
+	int err;
 
-	return mlx5e_create_umr_mtt_mkey(mdev, num_mtts, rq->mpwqe.page_shift,
-					 &rq->umr_mkey, rq->wqe_overflow.addr);
+	err = mlx5e_create_umr_mtt_mkey(mdev, num_mtts, rq->mpwqe.page_shift,
+					&umr_mkey, rq->wqe_overflow.addr);
+	rq->mpwqe.umr_mkey_be = cpu_to_be32(umr_mkey);
+	return err;
 }
 
 static int mlx5e_create_rq_hd_umr_mkey(struct mlx5_core_dev *mdev,
@@ -575,6 +579,8 @@ static int mlx5e_alloc_rq(struct mlx5e_p
 	rq->buff.headroom = mlx5e_get_rq_headroom(mdev, params, xsk);
 	pool_size = 1 << params->log_rq_mtu_frames;
 
+	rq->mkey_be = cpu_to_be32(mdev->mlx5e_res.hw_objs.mkey);
+
 	switch (rq->wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
 		err = mlx5_wq_ll_create(mdev, &rqp->wq, rqc_wq, &rq->mpwqe.wq,
@@ -611,7 +617,6 @@ static int mlx5e_alloc_rq(struct mlx5e_p
 		err = mlx5e_create_rq_umr_mkey(mdev, rq);
 		if (err)
 			goto err_rq_drop_page;
-		rq->mkey_be = cpu_to_be32(rq->umr_mkey);
 
 		err = mlx5e_rq_alloc_mpwqe_info(rq, node);
 		if (err)
@@ -647,8 +652,6 @@ static int mlx5e_alloc_rq(struct mlx5e_p
 		err = mlx5e_init_di_list(rq, wq_sz, node);
 		if (err)
 			goto err_rq_frags;
-
-		rq->mkey_be = cpu_to_be32(mdev->mlx5e_res.hw_objs.mkey);
 	}
 
 	if (xsk) {
@@ -695,7 +698,7 @@ static int mlx5e_alloc_rq(struct mlx5e_p
 
 			wqe->data[0].addr = cpu_to_be64(dma_offset + headroom);
 			wqe->data[0].byte_count = cpu_to_be32(byte_count);
-			wqe->data[0].lkey = rq->mkey_be;
+			wqe->data[0].lkey = rq->mpwqe.umr_mkey_be;
 		} else {
 			struct mlx5e_rx_wqe_cyc *wqe =
 				mlx5_wq_cyc_get_wqe(&rq->wqe.wq, i);
@@ -740,7 +743,7 @@ err_free_by_rq_type:
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
 		kvfree(rq->mpwqe.info);
 err_rq_mkey:
-		mlx5_core_destroy_mkey(mdev, rq->umr_mkey);
+		mlx5_core_destroy_mkey(mdev, be32_to_cpu(rq->mpwqe.umr_mkey_be));
 err_rq_drop_page:
 		mlx5e_free_mpwqe_rq_drop_page(rq);
 		break;
@@ -773,7 +776,7 @@ static void mlx5e_free_rq(struct mlx5e_r
 	switch (rq->wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
 		kvfree(rq->mpwqe.info);
-		mlx5_core_destroy_mkey(rq->mdev, rq->umr_mkey);
+		mlx5_core_destroy_mkey(rq->mdev, be32_to_cpu(rq->mpwqe.umr_mkey_be));
 		mlx5e_free_mpwqe_rq_drop_page(rq);
 		mlx5e_rq_free_shampo(rq);
 		break;