[PATCH] net/hns3: fix Rx packet truncation when KEEP CRC enabled

Ferruh Yigit ferruh.yigit at amd.com
Wed Feb 7 15:15:05 CET 2024


On 2/6/2024 1:10 AM, Jie Hai wrote:
> From: Dengdui Huang <huangdengdui at huawei.com>
> 
> When KEEP_CRC offload is enabled, some packets will be truncated and
> the CRC is still be stripped in following cases:
> 1. For HIP08 hardware, the packet type is TCP and the length
>    is less than or equal to 60B.
> 2. For other hardwares, the packet type is IP and the length
>    is less than or equal to 60B.
> 

If a device doesn't support the offload by some packets, it can be
option to disable offload for that device, instead of calculating it in
software and append it.
Unless you have a specific usecase, or requirement to support the offload.

<...>

> @@ -2492,10 +2544,16 @@ hns3_recv_pkts_simple(void *rx_queue,
>  			goto pkt_err;
>  
>  		rxm->packet_type = hns3_rx_calc_ptype(rxq, l234_info, ol_info);
> -
>  		if (rxm->packet_type == RTE_PTYPE_L2_ETHER_TIMESYNC)
>  			rxm->ol_flags |= RTE_MBUF_F_RX_IEEE1588_PTP;
>  
> +		if (unlikely(rxq->crc_len > 0)) {
> +			if (hns3_need_recalculate_crc(rxq, rxm))
> +				hns3_recalculate_crc(rxq, rxm);
> +			rxm->pkt_len -= rxq->crc_len;
> +			rxm->data_len -= rxq->crc_len;
>

Removing 'crc_len' from 'mbuf->pkt_len' & 'mbuf->data_len' is
practically same as stripping CRC.

We don't count CRC length in the statistics, but it should be accessible
in the payload by the user.



More information about the dev mailing list