Commit e225d9bd authored by Saeed Mahameed's avatar Saeed Mahameed Committed by Jakub Kicinski
Browse files

net/mlx5e: SHAMPO: Separate pool for headers 



Allow allocating a separate page pool for headers when SHAMPO is on.
This will be useful for adding support to zc page pool, which has to be
different from the headers page pool.
For now, the pools are the same.

Signed-off-by: default avatarSaeed Mahameed <saeedm@nvidia.com>
Reviewed-by: default avatarDragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: default avatarCosmin Ratiu <cratiu@nvidia.com>
Signed-off-by: default avatarTariq Toukan <tariqt@nvidia.com>
Signed-off-by: default avatarMark Bloch <mbloch@nvidia.com>
Link: https://patch.msgid.link/20250616141441.1243044-8-mbloch@nvidia.com


Signed-off-by: default avatarJakub Kicinski <kuba@kernel.org>
parent d2760abd

drivers/net/ethernet/mellanox/mlx5/core/en.h

+4 −0
Original line number Diff line number Diff line
@@ -716,7 +716,11 @@ struct mlx5e_rq { 
	struct bpf_prog __rcu *xdp_prog;

	struct mlx5e_xdpsq    *xdpsq;

	DECLARE_BITMAP(flags, 8);



	/* page pools */

	struct page_pool      *page_pool;

	struct page_pool      *hd_page_pool;



	struct mlx5e_xdp_buff mxbuf;



	/* AF_XDP zero-copy */

drivers/net/ethernet/mellanox/mlx5/core/en_main.c

+41 −2
Original line number Diff line number Diff line
@@ -41,6 +41,7 @@ 
#include <linux/filter.h>

#include <net/netdev_lock.h>

#include <net/netdev_queues.h>

#include <net/netdev_rx_queue.h>

#include <net/page_pool/types.h>

#include <net/pkt_sched.h>

#include <net/xdp_sock_drv.h>
@@ -746,6 +747,11 @@ static void mlx5e_rq_shampo_hd_info_free(struct mlx5e_rq *rq) 
	bitmap_free(rq->mpwqe.shampo->bitmap);

}



static bool mlx5_rq_needs_separate_hd_pool(struct mlx5e_rq *rq)

{

	return false;

}



static int mlx5_rq_shampo_alloc(struct mlx5_core_dev *mdev,

				struct mlx5e_params *params,

				struct mlx5e_rq_param *rqp,
@@ -754,6 +760,7 @@ static int mlx5_rq_shampo_alloc(struct mlx5_core_dev *mdev, 
				int node)

{

	void *wqc = MLX5_ADDR_OF(rqc, rqp->rqc, wq);

	u32 hd_pool_size;

	u16 hd_per_wq;

	int wq_size;

	int err;
@@ -781,9 +788,35 @@ static int mlx5_rq_shampo_alloc(struct mlx5_core_dev *mdev, 
	rq->mpwqe.shampo->hd_per_wqe =

		mlx5e_shampo_hd_per_wqe(mdev, params, rqp);

	wq_size = BIT(MLX5_GET(wq, wqc, log_wq_sz));

	*pool_size += (rq->mpwqe.shampo->hd_per_wqe * wq_size) /

	hd_pool_size = (rq->mpwqe.shampo->hd_per_wqe * wq_size) /

		MLX5E_SHAMPO_WQ_HEADER_PER_PAGE;



	if (mlx5_rq_needs_separate_hd_pool(rq)) {

		/* Separate page pool for shampo headers */

		struct page_pool_params pp_params = { };



		pp_params.order     = 0;

		pp_params.flags     = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV;

		pp_params.pool_size = hd_pool_size;

		pp_params.nid       = node;

		pp_params.dev       = rq->pdev;

		pp_params.napi      = rq->cq.napi;

		pp_params.netdev    = rq->netdev;

		pp_params.dma_dir   = rq->buff.map_dir;

		pp_params.max_len   = PAGE_SIZE;



		rq->hd_page_pool = page_pool_create(&pp_params);

		if (IS_ERR(rq->hd_page_pool)) {

			err = PTR_ERR(rq->hd_page_pool);

			rq->hd_page_pool = NULL;

			goto err_hds_page_pool;

		}

	} else {

		/* Common page pool, reserve space for headers. */

		*pool_size += hd_pool_size;

		rq->hd_page_pool = NULL;

	}



	/* gro only data structures */

	rq->hw_gro_data = kvzalloc_node(sizeof(*rq->hw_gro_data), GFP_KERNEL, node);

	if (!rq->hw_gro_data) {
@@ -794,6 +827,8 @@ static int mlx5_rq_shampo_alloc(struct mlx5_core_dev *mdev, 
	return 0;



err_hw_gro_data:

	page_pool_destroy(rq->hd_page_pool);

err_hds_page_pool:

	mlx5_core_destroy_mkey(mdev, rq->mpwqe.shampo->mkey);

err_umr_mkey:

	mlx5e_rq_shampo_hd_info_free(rq);
@@ -808,6 +843,8 @@ static void mlx5e_rq_free_shampo(struct mlx5e_rq *rq) 
		return;



	kvfree(rq->hw_gro_data);

	if (rq->hd_page_pool != rq->page_pool)

		page_pool_destroy(rq->hd_page_pool);

	mlx5e_rq_shampo_hd_info_free(rq);

	mlx5_core_destroy_mkey(rq->mdev, rq->mpwqe.shampo->mkey);

	kvfree(rq->mpwqe.shampo);
@@ -939,6 +976,8 @@ static int mlx5e_alloc_rq(struct mlx5e_params *params, 
			rq->page_pool = NULL;

			goto err_free_by_rq_type;

		}

		if (!rq->hd_page_pool)

			rq->hd_page_pool = rq->page_pool;

		if (xdp_rxq_info_is_reg(&rq->xdp_rxq))

			err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq,

							 MEM_TYPE_PAGE_POOL, rq->page_pool);

drivers/net/ethernet/mellanox/mlx5/core/en_rx.c

+24 −17
Original line number Diff line number Diff line
@@ -273,12 +273,12 @@ static inline u32 mlx5e_decompress_cqes_start(struct mlx5e_rq *rq, 


#define MLX5E_PAGECNT_BIAS_MAX (PAGE_SIZE / 64)



static int mlx5e_page_alloc_fragmented(struct mlx5e_rq *rq,

static int mlx5e_page_alloc_fragmented(struct page_pool *pool,

				       struct mlx5e_frag_page *frag_page)

{

	struct page *page;



	page = page_pool_dev_alloc_pages(rq->page_pool);

	page = page_pool_dev_alloc_pages(pool);

	if (unlikely(!page))

		return -ENOMEM;
@@ -292,14 +292,14 @@ static int mlx5e_page_alloc_fragmented(struct mlx5e_rq *rq, 
	return 0;

}



static void mlx5e_page_release_fragmented(struct mlx5e_rq *rq,

static void mlx5e_page_release_fragmented(struct page_pool *pool,

					  struct mlx5e_frag_page *frag_page)

{

	u16 drain_count = MLX5E_PAGECNT_BIAS_MAX - frag_page->frags;

	struct page *page = frag_page->page;



	if (page_pool_unref_page(page, drain_count) == 0)

		page_pool_put_unrefed_page(rq->page_pool, page, -1, true);

		page_pool_put_unrefed_page(pool, page, -1, true);

}



static inline int mlx5e_get_rx_frag(struct mlx5e_rq *rq,
@@ -313,7 +313,8 @@ static inline int mlx5e_get_rx_frag(struct mlx5e_rq *rq, 
		 * offset) should just use the new one without replenishing again

		 * by themselves.

		 */

		err = mlx5e_page_alloc_fragmented(rq, frag->frag_page);

		err = mlx5e_page_alloc_fragmented(rq->page_pool,

						  frag->frag_page);



	return err;

}
@@ -332,7 +333,7 @@ static inline void mlx5e_put_rx_frag(struct mlx5e_rq *rq, 
				     struct mlx5e_wqe_frag_info *frag)

{

	if (mlx5e_frag_can_release(frag))

		mlx5e_page_release_fragmented(rq, frag->frag_page);

		mlx5e_page_release_fragmented(rq->page_pool, frag->frag_page);

}



static inline struct mlx5e_wqe_frag_info *get_frag(struct mlx5e_rq *rq, u16 ix)
@@ -584,7 +585,8 @@ mlx5e_free_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi) 
				struct mlx5e_frag_page *frag_page;



				frag_page = &wi->alloc_units.frag_pages[i];

				mlx5e_page_release_fragmented(rq, frag_page);

				mlx5e_page_release_fragmented(rq->page_pool,

							      frag_page);

			}

		}

	}
@@ -679,11 +681,10 @@ static int mlx5e_build_shampo_hd_umr(struct mlx5e_rq *rq, 
		struct mlx5e_frag_page *frag_page = mlx5e_shampo_hd_to_frag_page(rq, index);

		u64 addr;



		err = mlx5e_page_alloc_fragmented(rq, frag_page);

		err = mlx5e_page_alloc_fragmented(rq->hd_page_pool, frag_page);

		if (unlikely(err))

			goto err_unmap;





		addr = page_pool_get_dma_addr(frag_page->page);



		for (int j = 0; j < MLX5E_SHAMPO_WQ_HEADER_PER_PAGE; j++) {
@@ -715,7 +716,8 @@ static int mlx5e_build_shampo_hd_umr(struct mlx5e_rq *rq, 
		if (!header_offset) {

			struct mlx5e_frag_page *frag_page = mlx5e_shampo_hd_to_frag_page(rq, index);



			mlx5e_page_release_fragmented(rq, frag_page);

			mlx5e_page_release_fragmented(rq->hd_page_pool,

						      frag_page);

		}

	}
@@ -791,7 +793,7 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix) 
	for (i = 0; i < rq->mpwqe.pages_per_wqe; i++, frag_page++) {

		dma_addr_t addr;



		err = mlx5e_page_alloc_fragmented(rq, frag_page);

		err = mlx5e_page_alloc_fragmented(rq->page_pool, frag_page);

		if (unlikely(err))

			goto err_unmap;

		addr = page_pool_get_dma_addr(frag_page->page);
@@ -836,7 +838,7 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix) 
err_unmap:

	while (--i >= 0) {

		frag_page--;

		mlx5e_page_release_fragmented(rq, frag_page);

		mlx5e_page_release_fragmented(rq->page_pool, frag_page);

	}



	bitmap_fill(wi->skip_release_bitmap, rq->mpwqe.pages_per_wqe);
@@ -855,7 +857,7 @@ mlx5e_free_rx_shampo_hd_entry(struct mlx5e_rq *rq, u16 header_index) 
	if (((header_index + 1) & (MLX5E_SHAMPO_WQ_HEADER_PER_PAGE - 1)) == 0) {

		struct mlx5e_frag_page *frag_page = mlx5e_shampo_hd_to_frag_page(rq, header_index);



		mlx5e_page_release_fragmented(rq, frag_page);

		mlx5e_page_release_fragmented(rq->hd_page_pool, frag_page);

	}

	clear_bit(header_index, shampo->bitmap);

}
@@ -1100,6 +1102,8 @@ INDIRECT_CALLABLE_SCOPE bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq) 


	if (rq->page_pool)

		page_pool_nid_changed(rq->page_pool, numa_mem_id());

	if (rq->hd_page_pool)

		page_pool_nid_changed(rq->hd_page_pool, numa_mem_id());



	head = rq->mpwqe.actual_wq_head;

	i = missing;
@@ -2004,7 +2008,8 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w 
	if (prog) {

		/* area for bpf_xdp_[store|load]_bytes */

		net_prefetchw(page_address(frag_page->page) + frag_offset);

		if (unlikely(mlx5e_page_alloc_fragmented(rq, &wi->linear_page))) {

		if (unlikely(mlx5e_page_alloc_fragmented(rq->page_pool,

							 &wi->linear_page))) {

			rq->stats->buff_alloc_err++;

			return NULL;

		}
@@ -2068,7 +2073,8 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w 


				wi->linear_page.frags++;

			}

			mlx5e_page_release_fragmented(rq, &wi->linear_page);

			mlx5e_page_release_fragmented(rq->page_pool,

						      &wi->linear_page);

			return NULL; /* page/packet was consumed by XDP */

		}
@@ -2077,13 +2083,14 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w 
			mxbuf->xdp.data - mxbuf->xdp.data_hard_start, 0,

			mxbuf->xdp.data - mxbuf->xdp.data_meta);

		if (unlikely(!skb)) {

			mlx5e_page_release_fragmented(rq, &wi->linear_page);

			mlx5e_page_release_fragmented(rq->page_pool,

						      &wi->linear_page);

			return NULL;

		}



		skb_mark_for_recycle(skb);

		wi->linear_page.frags++;

		mlx5e_page_release_fragmented(rq, &wi->linear_page);

		mlx5e_page_release_fragmented(rq->page_pool, &wi->linear_page);



		if (xdp_buff_has_frags(&mxbuf->xdp)) {

			struct mlx5e_frag_page *pagep;