diff options
author | Tariq Toukan <tariqt@mellanox.com> | 2017-12-20 12:56:35 +0300 |
---|---|---|
committer | Saeed Mahameed <saeedm@mellanox.com> | 2018-03-31 02:55:07 +0300 |
commit | b8a98a4cf3221d8140969e3f5bde09206a6cb623 (patch) | |
tree | 4ab167a2152d139d86ed2e28cc334df6cd2f1816 /drivers/net/ethernet/mellanox/mlx5/core/en_main.c | |
parent | 9f9e9cd50eac6ad09cb053509f2e764bddc05f18 (diff) | |
download | linux-b8a98a4cf3221d8140969e3f5bde09206a6cb623.tar.xz |
net/mlx5e: Keep single pre-initialized UMR WQE per RQ
All UMR WQEs of an RQ share many common fields. We use
pre-initialized structures to save calculations in datapath.
One field (xlt_offset) was the only reason we saved a pre-initialized
copy per WQE index.
Here we remove its initialization (move its calculation to datapath),
and reduce the number of copies to one-per-RQ.
A very small datapath calculation is added, it occurs once per a MPWQE
(i.e. once every 256KB), but reduces memory consumption and gives
better cache utilization.
Performance testing:
Tested packet rate, no degradation sensed.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Diffstat (limited to 'drivers/net/ethernet/mellanox/mlx5/core/en_main.c')
-rw-r--r-- | drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 20 |
1 files changed, 8 insertions, 12 deletions
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index b03a2327356a..0339609cfa56 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -306,13 +306,11 @@ static void mlx5e_disable_async_events(struct mlx5e_priv *priv) static inline void mlx5e_build_umr_wqe(struct mlx5e_rq *rq, struct mlx5e_icosq *sq, - struct mlx5e_umr_wqe *wqe, - u16 ix) + struct mlx5e_umr_wqe *wqe) { struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl; struct mlx5_wqe_umr_ctrl_seg *ucseg = &wqe->uctrl; u8 ds_cnt = DIV_ROUND_UP(MLX5E_UMR_WQE_INLINE_SZ, MLX5_SEND_WQE_DS); - u32 umr_wqe_mtt_offset = mlx5e_get_wqe_mtt_offset(rq, ix); cseg->qpn_ds = cpu_to_be32((sq->sqn << MLX5_WQE_CTRL_QPN_SHIFT) | ds_cnt); @@ -322,8 +320,6 @@ static inline void mlx5e_build_umr_wqe(struct mlx5e_rq *rq, ucseg->flags = MLX5_UMR_TRANSLATION_OFFSET_EN | MLX5_UMR_INLINE; ucseg->xlt_octowords = cpu_to_be16(MLX5_MTT_OCTW(MLX5_MPWRQ_PAGES_PER_WQE)); - ucseg->bsf_octowords = - cpu_to_be16(MLX5_MTT_OCTW(umr_wqe_mtt_offset)); ucseg->mkey_mask = cpu_to_be64(MLX5_MKEY_MASK_FREE); } @@ -331,18 +327,13 @@ static int mlx5e_rq_alloc_mpwqe_info(struct mlx5e_rq *rq, struct mlx5e_channel *c) { int wq_sz = mlx5_wq_ll_get_size(&rq->wq); - int i; rq->mpwqe.info = kzalloc_node(wq_sz * sizeof(*rq->mpwqe.info), GFP_KERNEL, cpu_to_node(c->cpu)); if (!rq->mpwqe.info) return -ENOMEM; - for (i = 0; i < wq_sz; i++) { - struct mlx5e_mpw_info *wi = &rq->mpwqe.info[i]; - - mlx5e_build_umr_wqe(rq, &c->icosq, &wi->umr.wqe, i); - } + mlx5e_build_umr_wqe(rq, &c->icosq, &rq->mpwqe.umr_wqe); return 0; } @@ -388,6 +379,11 @@ static int mlx5e_create_rq_umr_mkey(struct mlx5_core_dev *mdev, struct mlx5e_rq return mlx5e_create_umr_mkey(mdev, num_mtts, PAGE_SHIFT, &rq->umr_mkey); } +static inline u64 mlx5e_get_mpwqe_offset(struct mlx5e_rq *rq, u16 wqe_ix) +{ + return (wqe_ix << MLX5E_LOG_ALIGNED_MPWQE_PPW) << PAGE_SHIFT; +} + static int mlx5e_alloc_rq(struct mlx5e_channel *c, struct mlx5e_params *params, struct mlx5e_rq_param *rqp, @@ -520,7 +516,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, 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; + u64 dma_offset = mlx5e_get_mpwqe_offset(rq, i); wqe->data.addr = cpu_to_be64(dma_offset + rq->buff.headroom); } |