RE: [External] RE: [PATCH] net/cksum: compute raw cksum for several segments

[Marat Khalili <marat.khalili@huawei.com>]

[-- Attachment #1: Type: text/plain, Size: 2622 bytes --]

> -----Original Message-----
> From: Su Sai <susai.ss@bytedance.com>
> Sent: Thursday 31 July 2025 12:32
> To: Marat Khalili <marat.khalili@huawei.com>; jasvinder.singh@intel.com
> Cc: dev@dpdk.org
> Subject: Re: [External] RE: [PATCH] net/cksum: compute raw cksum for several segments
>
> Hi Marat Khalili,
>
> Thanks for your comments.
>
> We found small TCP checksum errors pkts online, then were traced to issues within the rte_raw_cksum_mbuf function.
>
> This error can be reproduced as follows:
> 1. In the client ECS with an MTU of 1500, initiate traffic using the command "iperf3 -c {dst ip} -b 1m -M 125 -t 8000".
> 2. In the destination ECS, the InCsumErrors statistic can be viewed using the command "netstat -st | grep -i csum". The erroneous packets can also be confirmed via the tcpdump command.
>
> The following is a detailed description of a captured erroneous packet. The hex stream of the packet is as follows:
> 00163e0b6bd2eeffffffffff0800450000a50d7a40004006b94bc0a8f91dc0a8f91ed5d2145146f9d990e10d6a2d8010020040a200000101080a95ac86ba091145d3ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff
>
> This is a packet in the format of eth + ipv4 + tcp + payload.
>
> The process leading to the error is as follows:
> 1. Due to the small MSS, TSO fragmentation was triggered, generating 3 mbufs.
> 2. The data_len of the first mbuf is 66 bytes, containing the Ethernet header, IPv4 header, and TCP header.
> 3. The data_len of the second mbuf is 61 bytes.
> 4. The data_len of the third mbuf is 52 bytes.
> 5. When calculating the checksum of the TCP header for such an mbuf chain using the rte_raw_cksum_mbuf function, the tmp value obtained during the calculation of the third mbuf is 0x19FFE6.
> 6. After applying rte_bswap16, tmp becomes 0xE6FF, with 0x19 discarded. This results in an incorrect final checksum.
>
> Meanwhile, we have also found that when enable jumbo frame, the payload becomes longer. In the process of rte_raw_cksum_mbuf handling an mbuf chain，due to the relatively large value of tmp, overflow will occur in the accumulated sum.

Thanks for the detailed description. I think both the bug and the fix are valid. Adding automated tests reproducing scenarios you described to app/test would help a lot, but I don’t know if you have cycles for this (I heard that AI is moderately good in generating test cases these days). I will ack your patch and let’s see what others say.

[-- Attachment #2: Type: text/html, Size: 5594 bytes --]