From 4415a0319f92ea0d624fe11c917faf9114f89187 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Thu, 15 Sep 2016 16:08:38 +0300 Subject: net/mlx5e: Implement RX mapped page cache for page recycle Instead of reallocating and mapping pages for RX data-path, recycle already used pages in a per ring cache. Performance tests: The following results were measured on a freshly booted system, giving optimal baseline performance, as high-order pages are yet to be fragmented and depleted. We ran pktgen single-stream benchmarks, with iptables-raw-drop: Single stride, 64 bytes: * 4,739,057 - baseline * 4,749,550 - order0 no cache * 4,786,899 - order0 with cache 1% gain Larger packets, no page cross, 1024 bytes: * 3,982,361 - baseline * 3,845,682 - order0 no cache * 4,127,852 - order0 with cache 3.7% gain Larger packets, every 3rd packet crosses a page, 1500 bytes: * 3,731,189 - baseline * 3,579,414 - order0 no cache * 3,931,708 - order0 with cache 5.4% gain Signed-off-by: Tariq Toukan Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/en.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'drivers/net/ethernet/mellanox/mlx5/core/en.h') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 401b2f7b165f..7dd4763e726e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -287,6 +287,18 @@ struct mlx5e_rx_am { /* Adaptive Moderation */ u8 tired; }; +/* a single cache unit is capable to serve one napi call (for non-striding rq) + * or a MPWQE (for striding rq). + */ +#define MLX5E_CACHE_UNIT (MLX5_MPWRQ_PAGES_PER_WQE > NAPI_POLL_WEIGHT ? \ + MLX5_MPWRQ_PAGES_PER_WQE : NAPI_POLL_WEIGHT) +#define MLX5E_CACHE_SIZE (2 * roundup_pow_of_two(MLX5E_CACHE_UNIT)) +struct mlx5e_page_cache { + u32 head; + u32 tail; + struct mlx5e_dma_info page_cache[MLX5E_CACHE_SIZE]; +}; + struct mlx5e_rq { /* data path */ struct mlx5_wq_ll wq; @@ -301,6 +313,8 @@ struct mlx5e_rq { struct mlx5e_tstamp *tstamp; struct mlx5e_rq_stats stats; struct mlx5e_cq cq; + struct mlx5e_page_cache page_cache; + mlx5e_fp_handle_rx_cqe handle_rx_cqe; mlx5e_fp_alloc_wqe alloc_wqe; mlx5e_fp_dealloc_wqe dealloc_wqe; @@ -651,6 +665,8 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget); int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget); void mlx5e_free_tx_descs(struct mlx5e_sq *sq); +void mlx5e_page_release(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info, + bool recycle); void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe); void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe); bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq); -- cgit v1.2.3-55-g7522