diff mbox series

[net-next,v3,3/4] eth: mlx4: remove the local XDP fast-recycling ring

Message ID 20250213010635.1354034-4-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 2 maintainers not CCed: 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, 106 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 
It will be replaced with page pool's built-in recycling.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
v2: no change
---
 drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 11 ------
 drivers/net/ethernet/mellanox/mlx4/en_rx.c   | 40 --------------------
 drivers/net/ethernet/mellanox/mlx4/en_tx.c   | 11 +-----
 3 files changed, 2 insertions(+), 60 deletions(-)

Comments

Tariq Toukan Feb. 18, 2025, 12:12 p.m. UTC | #1 
On 13/02/2025 3:06, Jakub Kicinski wrote:
> It will be replaced with page pool's built-in recycling.
> 
> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
> ---
> v2: no change
> ---
>   drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 11 ------
>   drivers/net/ethernet/mellanox/mlx4/en_rx.c   | 40 --------------------
>   drivers/net/ethernet/mellanox/mlx4/en_tx.c   | 11 +-----
>   3 files changed, 2 insertions(+), 60 deletions(-)
> 
> diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
> index 29f48e63081b..97311c98569f 100644
> --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
> +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
> @@ -253,14 +253,6 @@ struct mlx4_en_rx_alloc {
>   
>   #define MLX4_EN_CACHE_SIZE (2 * NAPI_POLL_WEIGHT)
>   
> -struct mlx4_en_page_cache {
> -	u32 index;
> -	struct {
> -		struct page	*page;
> -		dma_addr_t	dma;
> -	} buf[MLX4_EN_CACHE_SIZE];
> -};
> -
>   enum {
>   	MLX4_EN_TX_RING_STATE_RECOVERING,
>   };
> @@ -343,7 +335,6 @@ struct mlx4_en_rx_ring {
>   	void *buf;
>   	void *rx_info;
>   	struct bpf_prog __rcu *xdp_prog;
> -	struct mlx4_en_page_cache page_cache;
>   	unsigned long bytes;
>   	unsigned long packets;
>   	unsigned long csum_ok;
> @@ -708,8 +699,6 @@ netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring,
>   			       struct mlx4_en_priv *priv, unsigned int length,
>   			       int tx_ind, bool *doorbell_pending);
>   void mlx4_en_xmit_doorbell(struct mlx4_en_tx_ring *ring);
> -bool mlx4_en_rx_recycle(struct mlx4_en_rx_ring *ring,
> -			struct mlx4_en_rx_alloc *frame);
>   
>   int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
>   			   struct mlx4_en_tx_ring **pring,
> diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
> index a8c0cf5d0d08..d2cfbf2e38d9 100644
> --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
> +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
> @@ -142,18 +142,6 @@ static int mlx4_en_prepare_rx_desc(struct mlx4_en_priv *priv,
>   		(index << ring->log_stride);
>   	struct mlx4_en_rx_alloc *frags = ring->rx_info +
>   					(index << priv->log_rx_info);
> -	if (likely(ring->page_cache.index > 0)) {
> -		/* XDP uses a single page per frame */
> -		if (!frags->page) {
> -			ring->page_cache.index--;
> -			frags->page = ring->page_cache.buf[ring->page_cache.index].page;
> -			frags->dma  = ring->page_cache.buf[ring->page_cache.index].dma;
> -		}
> -		frags->page_offset = XDP_PACKET_HEADROOM;
> -		rx_desc->data[0].addr = cpu_to_be64(frags->dma +
> -						    XDP_PACKET_HEADROOM);
> -		return 0;
> -	}
>   
>   	return mlx4_en_alloc_frags(priv, ring, rx_desc, frags, gfp);
>   }
> @@ -430,26 +418,6 @@ void mlx4_en_recover_from_oom(struct mlx4_en_priv *priv)
>   	}
>   }
>   
> -/* When the rx ring is running in page-per-packet mode, a released frame can go
> - * directly into a small cache, to avoid unmapping or touching the page
> - * allocator. In bpf prog performance scenarios, buffers are either forwarded
> - * or dropped, never converted to skbs, so every page can come directly from
> - * this cache when it is sized to be a multiple of the napi budget.
> - */
> -bool mlx4_en_rx_recycle(struct mlx4_en_rx_ring *ring,
> -			struct mlx4_en_rx_alloc *frame)
> -{
> -	struct mlx4_en_page_cache *cache = &ring->page_cache;
> -
> -	if (cache->index >= MLX4_EN_CACHE_SIZE)
> -		return false;
> -
> -	cache->buf[cache->index].page = frame->page;
> -	cache->buf[cache->index].dma = frame->dma;
> -	cache->index++;
> -	return true;
> -}
> -
>   void mlx4_en_destroy_rx_ring(struct mlx4_en_priv *priv,
>   			     struct mlx4_en_rx_ring **pring,
>   			     u32 size, u16 stride)
> @@ -475,14 +443,6 @@ void mlx4_en_destroy_rx_ring(struct mlx4_en_priv *priv,
>   void mlx4_en_deactivate_rx_ring(struct mlx4_en_priv *priv,
>   				struct mlx4_en_rx_ring *ring)
>   {
> -	int i;
> -
> -	for (i = 0; i < ring->page_cache.index; i++) {
> -		dma_unmap_page(priv->ddev, ring->page_cache.buf[i].dma,
> -			       PAGE_SIZE, priv->dma_dir);
> -		put_page(ring->page_cache.buf[i].page);
> -	}
> -	ring->page_cache.index = 0;
>   	mlx4_en_free_rx_buf(priv, ring);
>   	if (ring->stride <= TXBB_SIZE)
>   		ring->buf -= TXBB_SIZE;
> diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
> index 6e077d202827..fe1378a689a1 100644
> --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
> +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
> @@ -350,16 +350,9 @@ u32 mlx4_en_recycle_tx_desc(struct mlx4_en_priv *priv,
>   			    int napi_mode)
>   {
>   	struct mlx4_en_tx_info *tx_info = &ring->tx_info[index];
> -	struct mlx4_en_rx_alloc frame = {
> -		.page = tx_info->page,
> -		.dma = tx_info->map0_dma,
> -	};
>   
> -	if (!napi_mode || !mlx4_en_rx_recycle(ring->recycle_ring, &frame)) {
> -		dma_unmap_page(priv->ddev, tx_info->map0_dma,
> -			       PAGE_SIZE, priv->dma_dir);
> -		put_page(tx_info->page);
> -	}
> +	dma_unmap_page(priv->ddev, tx_info->map0_dma, PAGE_SIZE, priv->dma_dir);
> +	put_page(tx_info->page);
>   
>   	return tx_info->nr_txbb;
>   }

Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
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 29f48e63081b..97311c98569f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -253,14 +253,6 @@  struct mlx4_en_rx_alloc {
 
 #define MLX4_EN_CACHE_SIZE (2 * NAPI_POLL_WEIGHT)
 
-struct mlx4_en_page_cache {
-	u32 index;
-	struct {
-		struct page	*page;
-		dma_addr_t	dma;
-	} buf[MLX4_EN_CACHE_SIZE];
-};
-
 enum {
 	MLX4_EN_TX_RING_STATE_RECOVERING,
 };
@@ -343,7 +335,6 @@  struct mlx4_en_rx_ring {
 	void *buf;
 	void *rx_info;
 	struct bpf_prog __rcu *xdp_prog;
-	struct mlx4_en_page_cache page_cache;
 	unsigned long bytes;
 	unsigned long packets;
 	unsigned long csum_ok;
@@ -708,8 +699,6 @@  netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring,
 			       struct mlx4_en_priv *priv, unsigned int length,
 			       int tx_ind, bool *doorbell_pending);
 void mlx4_en_xmit_doorbell(struct mlx4_en_tx_ring *ring);
-bool mlx4_en_rx_recycle(struct mlx4_en_rx_ring *ring,
-			struct mlx4_en_rx_alloc *frame);
 
 int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
 			   struct mlx4_en_tx_ring **pring,
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index a8c0cf5d0d08..d2cfbf2e38d9 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -142,18 +142,6 @@  static int mlx4_en_prepare_rx_desc(struct mlx4_en_priv *priv,
 		(index << ring->log_stride);
 	struct mlx4_en_rx_alloc *frags = ring->rx_info +
 					(index << priv->log_rx_info);
-	if (likely(ring->page_cache.index > 0)) {
-		/* XDP uses a single page per frame */
-		if (!frags->page) {
-			ring->page_cache.index--;
-			frags->page = ring->page_cache.buf[ring->page_cache.index].page;
-			frags->dma  = ring->page_cache.buf[ring->page_cache.index].dma;
-		}
-		frags->page_offset = XDP_PACKET_HEADROOM;
-		rx_desc->data[0].addr = cpu_to_be64(frags->dma +
-						    XDP_PACKET_HEADROOM);
-		return 0;
-	}
 
 	return mlx4_en_alloc_frags(priv, ring, rx_desc, frags, gfp);
 }
@@ -430,26 +418,6 @@  void mlx4_en_recover_from_oom(struct mlx4_en_priv *priv)
 	}
 }
 
-/* When the rx ring is running in page-per-packet mode, a released frame can go
- * directly into a small cache, to avoid unmapping or touching the page
- * allocator. In bpf prog performance scenarios, buffers are either forwarded
- * or dropped, never converted to skbs, so every page can come directly from
- * this cache when it is sized to be a multiple of the napi budget.
- */
-bool mlx4_en_rx_recycle(struct mlx4_en_rx_ring *ring,
-			struct mlx4_en_rx_alloc *frame)
-{
-	struct mlx4_en_page_cache *cache = &ring->page_cache;
-
-	if (cache->index >= MLX4_EN_CACHE_SIZE)
-		return false;
-
-	cache->buf[cache->index].page = frame->page;
-	cache->buf[cache->index].dma = frame->dma;
-	cache->index++;
-	return true;
-}
-
 void mlx4_en_destroy_rx_ring(struct mlx4_en_priv *priv,
 			     struct mlx4_en_rx_ring **pring,
 			     u32 size, u16 stride)
@@ -475,14 +443,6 @@  void mlx4_en_destroy_rx_ring(struct mlx4_en_priv *priv,
 void mlx4_en_deactivate_rx_ring(struct mlx4_en_priv *priv,
 				struct mlx4_en_rx_ring *ring)
 {
-	int i;
-
-	for (i = 0; i < ring->page_cache.index; i++) {
-		dma_unmap_page(priv->ddev, ring->page_cache.buf[i].dma,
-			       PAGE_SIZE, priv->dma_dir);
-		put_page(ring->page_cache.buf[i].page);
-	}
-	ring->page_cache.index = 0;
 	mlx4_en_free_rx_buf(priv, ring);
 	if (ring->stride <= TXBB_SIZE)
 		ring->buf -= TXBB_SIZE;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 6e077d202827..fe1378a689a1 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -350,16 +350,9 @@  u32 mlx4_en_recycle_tx_desc(struct mlx4_en_priv *priv,
 			    int napi_mode)
 {
 	struct mlx4_en_tx_info *tx_info = &ring->tx_info[index];
-	struct mlx4_en_rx_alloc frame = {
-		.page = tx_info->page,
-		.dma = tx_info->map0_dma,
-	};
 
-	if (!napi_mode || !mlx4_en_rx_recycle(ring->recycle_ring, &frame)) {
-		dma_unmap_page(priv->ddev, tx_info->map0_dma,
-			       PAGE_SIZE, priv->dma_dir);
-		put_page(tx_info->page);
-	}
+	dma_unmap_page(priv->ddev, tx_info->map0_dma, PAGE_SIZE, priv->dma_dir);
+	put_page(tx_info->page);
 
 	return tx_info->nr_txbb;
 }