diff mbox series

[net-next,v3,1/4] eth: mlx4: create a page pool for Rx

Message ID 20250213010635.1354034-2-kuba@kernel.org (mailing list archive)
State Accepted
Delegated to: Netdev Maintainers
Headers show
Series eth: mlx4: use the page pool for Rx buffers | expand

Checks

Context Check Description
netdev/series_format success Posting correctly formatted
netdev/tree_selection success Clearly marked for net-next
netdev/ynl success Generated files up to date; no warnings/errors; no diff in generated;
netdev/fixes_present success Fixes tag not required for -next series
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 0 this patch: 0
netdev/build_tools success No tools touched, skip
netdev/cc_maintainers warning 5 maintainers not CCed: ast@kernel.org daniel@iogearbox.net john.fastabend@gmail.com linux-rdma@vger.kernel.org bpf@vger.kernel.org
netdev/build_clang success Errors and warnings before: 12 this patch: 12
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/deprecated_api success None detected
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 0 this patch: 0
netdev/checkpatch success total: 0 errors, 0 warnings, 0 checks, 68 lines checked
netdev/build_clang_rust success No Rust files in patch. Skipping build
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0
netdev/contest success net-next-2025-02-15--03-00 (tests: 891)

Commit Message

Jakub Kicinski Feb. 13, 2025, 1:06 a.m. UTC 
Create a pool per rx queue. Subsequent patches will make use of it.

Move fcs_del to a hole to make space for the pointer.

Per common "wisdom" base the page pool size on the ring size.
Note that the page pool cache size is in full pages, so just
round up the effective buffer size to pages.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
v3:
 - use priv->rx_skb_size for effective buffer size
 - use priv->dma_dir for DMA mapping direction, instead of always BIDIR
v2: https://lore.kernel.org/20250211192141.619024-2-kuba@kernel.org
 - update pp.pool_size
v1: https://lore.kernel.org/20250205031213.358973-2-kuba@kernel.org
---
 drivers/net/ethernet/mellanox/mlx4/mlx4_en.h |  3 ++-
 drivers/net/ethernet/mellanox/mlx4/en_rx.c   | 24 +++++++++++++++++++-
 2 files changed, 25 insertions(+), 2 deletions(-)

Comments

Tariq Toukan Feb. 18, 2025, 12:10 p.m. UTC | #1 
On 13/02/2025 3:06, Jakub Kicinski wrote:
> Create a pool per rx queue. Subsequent patches will make use of it.
> 
> Move fcs_del to a hole to make space for the pointer.
> 
> Per common "wisdom" base the page pool size on the ring size.
> Note that the page pool cache size is in full pages, so just
> round up the effective buffer size to pages.
> 
> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
> ---
> v3:
>   - use priv->rx_skb_size for effective buffer size
>   - use priv->dma_dir for DMA mapping direction, instead of always BIDIR
> v2: https://lore.kernel.org/20250211192141.619024-2-kuba@kernel.org
>   - update pp.pool_size
> v1: https://lore.kernel.org/20250205031213.358973-2-kuba@kernel.org
> ---
>   drivers/net/ethernet/mellanox/mlx4/mlx4_en.h |  3 ++-
>   drivers/net/ethernet/mellanox/mlx4/en_rx.c   | 24 +++++++++++++++++++-
>   2 files changed, 25 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
> index 28b70dcc652e..29f48e63081b 100644
> --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
> +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
> @@ -335,10 +335,11 @@ struct mlx4_en_rx_ring {
>   	u16 stride;
>   	u16 log_stride;
>   	u16 cqn;	/* index of port CQ associated with this ring */
> +	u8  fcs_del;
>   	u32 prod;
>   	u32 cons;
>   	u32 buf_size;
> -	u8  fcs_del;
> +	struct page_pool *pp;
>   	void *buf;
>   	void *rx_info;
>   	struct bpf_prog __rcu *xdp_prog;
> diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
> index 15c57e9517e9..a8c0cf5d0d08 100644
> --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
> +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
> @@ -48,6 +48,7 @@
>   #if IS_ENABLED(CONFIG_IPV6)
>   #include <net/ip6_checksum.h>
>   #endif
> +#include <net/page_pool/helpers.h>
>   
>   #include "mlx4_en.h"
>   
> @@ -268,6 +269,7 @@ int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv,
>   			   u32 size, u16 stride, int node, int queue_index)
>   {
>   	struct mlx4_en_dev *mdev = priv->mdev;
> +	struct page_pool_params pp = {};
>   	struct mlx4_en_rx_ring *ring;
>   	int err = -ENOMEM;
>   	int tmp;
> @@ -286,9 +288,26 @@ int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv,
>   	ring->log_stride = ffs(ring->stride) - 1;
>   	ring->buf_size = ring->size * ring->stride + TXBB_SIZE;
>   
> -	if (xdp_rxq_info_reg(&ring->xdp_rxq, priv->dev, queue_index, 0) < 0)
> +	pp.flags = PP_FLAG_DMA_MAP;
> +	pp.pool_size = size * DIV_ROUND_UP(priv->rx_skb_size, PAGE_SIZE);
> +	pp.nid = node;
> +	pp.napi = &priv->rx_cq[queue_index]->napi;
> +	pp.netdev = priv->dev;
> +	pp.dev = &mdev->dev->persist->pdev->dev;
> +	pp.dma_dir = priv->dma_dir;
> +
> +	ring->pp = page_pool_create(&pp);
> +	if (!ring->pp)
>   		goto err_ring;
>   
> +	if (xdp_rxq_info_reg(&ring->xdp_rxq, priv->dev, queue_index, 0) < 0)
> +		goto err_pp;
> +
> +	err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, MEM_TYPE_PAGE_POOL,
> +					 ring->pp);
> +	if (err)
> +		goto err_xdp_info;
> +
>   	tmp = size * roundup_pow_of_two(MLX4_EN_MAX_RX_FRAGS *
>   					sizeof(struct mlx4_en_rx_alloc));
>   	ring->rx_info = kvzalloc_node(tmp, GFP_KERNEL, node);
> @@ -319,6 +338,8 @@ int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv,
>   	ring->rx_info = NULL;
>   err_xdp_info:
>   	xdp_rxq_info_unreg(&ring->xdp_rxq);
> +err_pp:
> +	page_pool_destroy(ring->pp);
>   err_ring:
>   	kfree(ring);
>   	*pring = NULL;
> @@ -445,6 +466,7 @@ void mlx4_en_destroy_rx_ring(struct mlx4_en_priv *priv,
>   	xdp_rxq_info_unreg(&ring->xdp_rxq);
>   	mlx4_free_hwq_res(mdev->dev, &ring->wqres, size * stride + TXBB_SIZE);
>   	kvfree(ring->rx_info);
> +	page_pool_destroy(ring->pp);
>   	ring->rx_info = NULL;
>   	kfree(ring);
>   	*pring = NULL;

Reviewed-by: Tariq Toukan <tariqt@nvidia.com>

Thanks for your patches,
Tariq
diff mbox series

Patch

diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 28b70dcc652e..29f48e63081b 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -335,10 +335,11 @@  struct mlx4_en_rx_ring {
 	u16 stride;
 	u16 log_stride;
 	u16 cqn;	/* index of port CQ associated with this ring */
+	u8  fcs_del;
 	u32 prod;
 	u32 cons;
 	u32 buf_size;
-	u8  fcs_del;
+	struct page_pool *pp;
 	void *buf;
 	void *rx_info;
 	struct bpf_prog __rcu *xdp_prog;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 15c57e9517e9..a8c0cf5d0d08 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -48,6 +48,7 @@ 
 #if IS_ENABLED(CONFIG_IPV6)
 #include <net/ip6_checksum.h>
 #endif
+#include <net/page_pool/helpers.h>
 
 #include "mlx4_en.h"
 
@@ -268,6 +269,7 @@  int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv,
 			   u32 size, u16 stride, int node, int queue_index)
 {
 	struct mlx4_en_dev *mdev = priv->mdev;
+	struct page_pool_params pp = {};
 	struct mlx4_en_rx_ring *ring;
 	int err = -ENOMEM;
 	int tmp;
@@ -286,9 +288,26 @@  int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv,
 	ring->log_stride = ffs(ring->stride) - 1;
 	ring->buf_size = ring->size * ring->stride + TXBB_SIZE;
 
-	if (xdp_rxq_info_reg(&ring->xdp_rxq, priv->dev, queue_index, 0) < 0)
+	pp.flags = PP_FLAG_DMA_MAP;
+	pp.pool_size = size * DIV_ROUND_UP(priv->rx_skb_size, PAGE_SIZE);
+	pp.nid = node;
+	pp.napi = &priv->rx_cq[queue_index]->napi;
+	pp.netdev = priv->dev;
+	pp.dev = &mdev->dev->persist->pdev->dev;
+	pp.dma_dir = priv->dma_dir;
+
+	ring->pp = page_pool_create(&pp);
+	if (!ring->pp)
 		goto err_ring;
 
+	if (xdp_rxq_info_reg(&ring->xdp_rxq, priv->dev, queue_index, 0) < 0)
+		goto err_pp;
+
+	err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, MEM_TYPE_PAGE_POOL,
+					 ring->pp);
+	if (err)
+		goto err_xdp_info;
+
 	tmp = size * roundup_pow_of_two(MLX4_EN_MAX_RX_FRAGS *
 					sizeof(struct mlx4_en_rx_alloc));
 	ring->rx_info = kvzalloc_node(tmp, GFP_KERNEL, node);
@@ -319,6 +338,8 @@  int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv,
 	ring->rx_info = NULL;
 err_xdp_info:
 	xdp_rxq_info_unreg(&ring->xdp_rxq);
+err_pp:
+	page_pool_destroy(ring->pp);
 err_ring:
 	kfree(ring);
 	*pring = NULL;
@@ -445,6 +466,7 @@  void mlx4_en_destroy_rx_ring(struct mlx4_en_priv *priv,
 	xdp_rxq_info_unreg(&ring->xdp_rxq);
 	mlx4_free_hwq_res(mdev->dev, &ring->wqres, size * stride + TXBB_SIZE);
 	kvfree(ring->rx_info);
+	page_pool_destroy(ring->pp);
 	ring->rx_info = NULL;
 	kfree(ring);
 	*pring = NULL;