Re: [Intel-wired-lan] [PATCH net-next v3] i40e: xsk: use xdp_build_skb_from_zc() for XDP_PASS

On 7/30/26 7:07 PM, Chenguang Zhao wrote:
> From: Chenguang Zhao <[email protected]>
> 
> Replace the driver-local i40e_construct_skb_zc() with the common
> helper xdp_build_skb_from_zc(). On failure, free the xdp buff in
> the caller.
> 
> xdp_build_skb_from_zc() already calls skb_record_rx_queue() and
> eth_type_trans(), so pull the remaining descriptor field setup into
> __i40e_process_skb_fields() and use that on the XDP_PASS path.
> 
> Signed-off-by: Chenguang Zhao <[email protected]>
> ---
> v3:
>   As suggested by Larysa:
>   - Drop eth_skb_pad() on the XDP_PASS path, along with the
>     temporary __skb_push()/__skb_pull() around it. The stack
>     handles short skbs and other vendors do not pad on Rx.
> 
> v2:
>   - https://lore.kernel.org/all/[email protected]/
> 
> v1:
>   - https://lore.kernel.org/all/[email protected]/
> ---
>   drivers/net/ethernet/intel/i40e/i40e_txrx.c   | 32 ++++++--
>   .../ethernet/intel/i40e/i40e_txrx_common.h    |  2 +
>   drivers/net/ethernet/intel/i40e/i40e_xsk.c    | 79 ++-----------------
>   3 files changed, 33 insertions(+), 80 deletions(-)
> 
> diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
> index ef5e657816f0..87553b14d34a 100644
> --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
> +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
> @@ -1833,17 +1833,17 @@ static inline void i40e_rx_hash(struct i40e_ring *ring,
>   }
>   
>   /**
> - * i40e_process_skb_fields - Populate skb header fields from Rx descriptor
> + * __i40e_process_skb_fields - Populate skb fields from Rx descriptor
>    * @rx_ring: rx descriptor ring packet is being transacted on
>    * @rx_desc: pointer to the EOP Rx descriptor
>    * @skb: pointer to current skb being populated
>    *
> - * This function checks the ring, descriptor, and packet information in
> - * order to populate the hash, checksum, VLAN, protocol, and
> - * other fields within the skb.
> + * Populate hash, checksum, PTP timestamp and VLAN from @rx_desc. Does not
> + * call skb_record_rx_queue() or eth_type_trans(); callers that already got
> + * those from xdp_build_skb_from_zc() should use this helper.
>    **/
> -void i40e_process_skb_fields(struct i40e_ring *rx_ring,
> -			     union i40e_rx_desc *rx_desc, struct sk_buff *skb)
> +void __i40e_process_skb_fields(struct i40e_ring *rx_ring,
> +			       union i40e_rx_desc *rx_desc, struct sk_buff *skb)
>   {
>   	u64 qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
>   	u32 rx_status = FIELD_GET(I40E_RXD_QW1_STATUS_MASK, qword);
> @@ -1858,14 +1858,30 @@ void i40e_process_skb_fields(struct i40e_ring *rx_ring,
>   
>   	i40e_rx_checksum(rx_ring->vsi, skb, rx_desc);
>   
> -	skb_record_rx_queue(skb, rx_ring->queue_index);
> -
>   	if (qword & BIT(I40E_RX_DESC_STATUS_L2TAG1P_SHIFT)) {
>   		__le16 vlan_tag = rx_desc->wb.qword0.lo_dword.l2tag1;
>   
>   		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
>   				       le16_to_cpu(vlan_tag));
>   	}
> +}
> +
> +/**
> + * i40e_process_skb_fields - Populate skb header fields from Rx descriptor
> + * @rx_ring: rx descriptor ring packet is being transacted on
> + * @rx_desc: pointer to the EOP Rx descriptor
> + * @skb: pointer to current skb being populated
> + *
> + * This function checks the ring, descriptor, and packet information in
> + * order to populate the hash, checksum, VLAN, protocol, and
> + * other fields within the skb.
> + **/
> +void i40e_process_skb_fields(struct i40e_ring *rx_ring,
> +			     union i40e_rx_desc *rx_desc, struct sk_buff *skb)
> +{
> +	__i40e_process_skb_fields(rx_ring, rx_desc, skb);
> +
> +	skb_record_rx_queue(skb, rx_ring->queue_index);
>   
>   	/* modifies the skb - consumes the enet header */
>   	skb->protocol = eth_type_trans(skb, rx_ring->netdev);
> diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h b/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h
> index e26807fd2123..3c52e0e60487 100644
> --- a/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h
> +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h
> @@ -9,6 +9,8 @@
>   int i40e_xmit_xdp_tx_ring(struct xdp_buff *xdp, struct i40e_ring *xdp_ring);
>   void i40e_clean_programming_status(struct i40e_ring *rx_ring, u64 qword0_raw,
>   				   u64 qword1);
> +void __i40e_process_skb_fields(struct i40e_ring *rx_ring,
> +			       union i40e_rx_desc *rx_desc, struct sk_buff *skb);
>   void i40e_process_skb_fields(struct i40e_ring *rx_ring,
>   			     union i40e_rx_desc *rx_desc, struct sk_buff *skb);
>   void i40e_xdp_ring_update_tail(struct i40e_ring *xdp_ring);
> diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
> index 9f47388eaba5..dfa519c30a0d 100644
> --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
> +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
> @@ -3,6 +3,7 @@
>   
>   #include <linux/bpf_trace.h>
>   #include <linux/unroll.h>
> +#include <net/xdp.h>
>   #include <net/xdp_sock_drv.h>
>   #include "i40e_txrx_common.h"
>   #include "i40e_xsk.h"
> @@ -277,70 +278,6 @@ bool i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 count)
>   	return count == nb_buffs;
>   }
>   
> -/**
> - * i40e_construct_skb_zc - Create skbuff from zero-copy Rx buffer
> - * @rx_ring: Rx ring
> - * @xdp: xdp_buff
> - *
> - * This functions allocates a new skb from a zero-copy Rx buffer.
> - *
> - * Returns the skb, or NULL on failure.
> - **/
> -static struct sk_buff *i40e_construct_skb_zc(struct i40e_ring *rx_ring,
> -					     struct xdp_buff *xdp)
> -{
> -	unsigned int totalsize = xdp->data_end - xdp->data_meta;
> -	unsigned int metasize = xdp->data - xdp->data_meta;
> -	struct skb_shared_info *sinfo = NULL;
> -	struct sk_buff *skb;
> -	u32 nr_frags = 0;
> -
> -	if (unlikely(xdp_buff_has_frags(xdp))) {
> -		sinfo = xdp_get_shared_info_from_buff(xdp);
> -		nr_frags = sinfo->nr_frags;
> -	}
> -	net_prefetch(xdp->data_meta);
> -
> -	/* allocate a skb to store the frags */
> -	skb = napi_alloc_skb(&rx_ring->q_vector->napi, totalsize);
> -	if (unlikely(!skb))
> -		goto out;
> -
> -	memcpy(__skb_put(skb, totalsize), xdp->data_meta,
> -	       ALIGN(totalsize, sizeof(long)));
> -
> -	if (metasize) {
> -		skb_metadata_set(skb, metasize);
> -		__skb_pull(skb, metasize);
> -	}
> -
> -	if (likely(!xdp_buff_has_frags(xdp)))
> -		goto out;
> -
> -	for (int i = 0; i < nr_frags; i++) {
> -		struct skb_shared_info *skinfo = skb_shinfo(skb);
> -		skb_frag_t *frag = &sinfo->frags[i];
> -		struct page *page;
> -		void *addr;
> -
> -		page = dev_alloc_page();
> -		if (!page) {
> -			dev_kfree_skb(skb);
> -			return NULL;
> -		}
> -		addr = page_to_virt(page);
> -
> -		memcpy(addr, skb_frag_page(frag), skb_frag_size(frag));
> -
> -		__skb_fill_page_desc_noacc(skinfo, skinfo->nr_frags++,
> -					   addr, 0, skb_frag_size(frag));
> -	}
> -
> -out:
> -	xsk_buff_free(xdp);
> -	return skb;
> -}
> -
>   static void i40e_handle_xdp_result_zc(struct i40e_ring *rx_ring,
>   				      struct xdp_buff *xdp_buff,
>   				      union i40e_rx_desc *rx_desc,
> @@ -372,21 +309,19 @@ static void i40e_handle_xdp_result_zc(struct i40e_ring *rx_ring,
>   		 * BIT(I40E_RXD_QW1_ERROR_SHIFT). This is due to that
>   		 * SBP is *not* set in PRT_SBPVSI (default not set).
>   		 */
> -		skb = i40e_construct_skb_zc(rx_ring, xdp_buff);
> +		skb = xdp_build_skb_from_zc(xdp_buff);
>   		if (!skb) {
> +			xsk_buff_free(xdp_buff);
>   			rx_ring->rx_stats.alloc_buff_failed++;
>   			*rx_packets = 0;
>   			*rx_bytes = 0;
>   			return;
>   		}
>   
> -		if (eth_skb_pad(skb)) {
> -			*rx_packets = 0;
> -			*rx_bytes = 0;
> -			return;
> -		}
> -
> -		i40e_process_skb_fields(rx_ring, rx_desc, skb);
> +		/* xdp_build_skb_from_zc() already ran eth_type_trans() and
> +		 * skb_record_rx_queue().
> +		 */
> +		__i40e_process_skb_fields(rx_ring, rx_desc, skb);
>   		napi_gro_receive(&rx_ring->q_vector->napi, skb);
>   		return;
>   	}

The cleanup makes sense. I think you would also need to update kconfig. 
xdp_build_skb_from_zc() verifies page pool support and if 
CONFIG_PAGE_POOL=n, it would return NULL. In that case, we would end-up 
dropping packets in XDP_PASS.

With that addressed:
Reviewed-by: Mohsin Bashir <[email protected]>