[PATCH net-next 1/3] net/mlx5e: Move RX MPWQE slowpath fields into a separate struct
From: Tariq Toukan <tariqt@nvidia.com>
Date: 2026-03-19 07:44:29
Also in:
linux-rdma, lkml
Subsystem:
mellanox ethernet driver (mlx5e), mellanox mlx5 core vpi driver, networking drivers, the rest · Maintainers:
Saeed Mahameed, Tariq Toukan, Mark Bloch, Leon Romanovsky, Andrew Lunn, "David S. Miller", Eric Dumazet, Jakub Kicinski, Paolo Abeni, Linus Torvalds
Move fields that are not read/written in fast path to a different struct / cacheline in the RQ structure. Signed-off-by: Tariq Toukan <tariqt@nvidia.com> Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com> --- drivers/net/ethernet/mellanox/mlx5/core/en.h | 4 +++- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 12 +++++++----- 2 files changed, 10 insertions(+), 6 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index c7ac6ebe8290..d90be82a9019 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h@@ -676,7 +676,6 @@ struct mlx5e_rq { struct mlx5e_umr_wqe_hdr 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;
@@ -745,6 +744,9 @@ struct mlx5e_rq { struct mlx5_core_dev *mdev; struct mlx5e_channel *channel; struct mlx5e_dma_info wqe_overflow; + struct { + __be32 umr_mkey_be; + } mpwqe_sp; /* XDP read-mostly */ struct xdp_rxq_info xdp_rxq;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index f7009da94f0b..20c24d829ee2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c@@ -332,7 +332,7 @@ static inline void mlx5e_build_umr_wqe(struct mlx5e_rq *rq, cseg->qpn_ds = cpu_to_be32((sq->sqn << MLX5_WQE_CTRL_QPN_SHIFT) | ds_cnt); - cseg->umr_mkey = rq->mpwqe.umr_mkey_be; + cseg->umr_mkey = rq->mpwqe_sp.umr_mkey_be; ucseg->flags = MLX5_UMR_TRANSLATION_OFFSET_EN | MLX5_UMR_INLINE; octowords = mlx5e_mpwrq_umr_octowords(rq->mpwqe.pages_per_wqe, rq->mpwqe.umr_mode);
@@ -513,7 +513,7 @@ static int mlx5e_create_rq_umr_mkey(struct mlx5_core_dev *mdev, struct mlx5e_rq err = mlx5e_create_umr_mkey(mdev, num_entries, rq->mpwqe.page_shift, &umr_mkey, rq->wqe_overflow.addr, rq->mpwqe.umr_mode, xsk_chunk_size); - rq->mpwqe.umr_mkey_be = cpu_to_be32(umr_mkey); + rq->mpwqe_sp.umr_mkey_be = cpu_to_be32(umr_mkey); return err; }
@@ -1024,7 +1024,7 @@ static int mlx5e_alloc_rq(struct mlx5e_params *params, 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->mpwqe.umr_mkey_be; + wqe->data[0].lkey = rq->mpwqe_sp.umr_mkey_be; } else { struct mlx5e_rx_wqe_cyc *wqe = mlx5_wq_cyc_get_wqe(&rq->wqe.wq, i);
@@ -1057,7 +1057,8 @@ static int mlx5e_alloc_rq(struct mlx5e_params *params, err_free_mpwqe_info: kvfree(rq->mpwqe.info); err_rq_mkey: - mlx5_core_destroy_mkey(mdev, be32_to_cpu(rq->mpwqe.umr_mkey_be)); + mlx5_core_destroy_mkey(mdev, + be32_to_cpu(rq->mpwqe_sp.umr_mkey_be)); err_rq_drop_page: mlx5e_free_mpwqe_rq_drop_page(rq); break;
@@ -1082,7 +1083,8 @@ static void mlx5e_free_rq(struct mlx5e_rq *rq) case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ: mlx5e_rq_free_shampo(rq); kvfree(rq->mpwqe.info); - mlx5_core_destroy_mkey(rq->mdev, be32_to_cpu(rq->mpwqe.umr_mkey_be)); + mlx5_core_destroy_mkey(rq->mdev, + be32_to_cpu(rq->mpwqe_sp.umr_mkey_be)); mlx5e_free_mpwqe_rq_drop_page(rq); break; default: /* MLX5_WQ_TYPE_CYCLIC */
--
2.44.0