net/mlx5e: DMA-sync earlier in mlx5e_skb_from_cqe_mpwrq_nonlinear

Doing the call to dma_sync_single_for_cpu() earlier will allow us to
adjust headlen based on the actual size of the protocol headers.

Doing this earlier means that we don't need to call
mlx5e_copy_skb_header() anymore and rather can call
skb_copy_to_linear_data() directly.

Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Christoph Paasch <cpaasch@openai.com>
Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20260601061522.398044-2-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

Author: cpaasch-oai

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

@@ -1923,11 +1923,11 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 	unsigned int truesize = 0;
 	u32 pg_consumed_bytes;
 	struct bpf_prog *prog;
+	void *va, *head_addr;
 	struct sk_buff *skb;
 	u32 linear_frame_sz;
 	u16 linear_data_len;
 	u16 linear_hr;
-	void *va;
 
 	if (unlikely(cqe_bcnt > rq->hw_mtu)) {
 		u8 lro_num_seg = get_cqe_lro_num_seg(cqe);
@@ -1940,9 +1940,11 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 
 	prog = rcu_dereference(rq->xdp_prog);
 
+	head_addr = netmem_address(head_page->netmem) + head_offset;
+
 	if (prog) {
 		/* area for bpf_xdp_[store|load]_bytes */
-		net_prefetchw(netmem_address(frag_page->netmem) + frag_offset);
+		net_prefetchw(head_addr);
 
 		va = mlx5e_mpwqe_get_linear_page_frag(rq);
 		if (!va) {
@@ -1956,6 +1958,8 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 		linear_frame_sz = MLX5_SKB_FRAG_SZ(linear_hr + MLX5E_RX_MAX_HEAD);
 		linear_page = &rq->mpwqe.linear_info->frag_page;
 	} else {
+		dma_addr_t addr;
+
 		skb = napi_alloc_skb(rq->cq.napi,
 				     ALIGN(MLX5E_RX_MAX_HEAD, sizeof(long)));
 		if (unlikely(!skb)) {
@@ -1967,6 +1971,11 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 		net_prefetchw(va); /* xdp_frame data area */
 		net_prefetchw(skb->data);
 
+		addr = page_pool_get_dma_addr_netmem(head_page->netmem);
+		dma_sync_single_for_cpu(rq->pdev, addr + head_offset,
+					ALIGN(headlen, sizeof(long)),
+					rq->buff.map_dir);
+
 		frag_offset += headlen;
 		byte_cnt -= headlen;
 		linear_hr = skb_headroom(skb);
@@ -2056,8 +2065,6 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 			__pskb_pull_tail(skb, headlen);
 		}
 	} else {
-		dma_addr_t addr;
-
 		if (xdp_buff_has_frags(&mxbuf->xdp)) {
 			struct mlx5e_frag_page *pagep;
 
@@ -2071,10 +2078,11 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 				pagep->frags++;
 			while (++pagep < frag_page);
 		}
+
 		/* copy header */
-		addr = page_pool_get_dma_addr_netmem(head_page->netmem);
-		mlx5e_copy_skb_header(rq, skb, head_page->netmem, addr,
-				      head_offset, head_offset, headlen);
+		skb_copy_to_linear_data(skb, head_addr,
+					ALIGN(headlen, sizeof(long)));
+
 		/* skb linear part was allocated with headlen and aligned to long */
 		skb->tail += headlen;
 		skb->len  += headlen;