Re: [PATCH v3 0/5] net/zxdh: add support some new features

[Stephen Hemminger <stephen@networkplumber.org>]

On Sat, 31 Jan 2026 14:22:03 +0800
Junlong Wang <wang.junlong1@zte.com.cn> wrote:

> V3:
>   - modify some issues from AI review.
> 
> V2:
>   - add updated release note and the documentation.
>   - remove unnecessary initialization.
>   - using the compiler builtins(__rte_clz32).
>   - remove C++ style comments.
> 
> V1:
>   - support modifying queue depth.
>   - optimeze alloc queue resources.
>   - support set link speed.
>   - support primary/secondary process.
>   - support GENEVE TSO/chksum,and tunnel packets outer udp chksum.
> 
> Junlong Wang (5):
>   net/zxdh: add support for modifying queue depth
>   net/zxdh: optimize alloc queue resources
>   net/zxdh: add link speed set and autoneg get support
>   net/zxdh: add support for primary/secondary process
>   net/zxdh: add support for GENEVE TSO and Rx outer checksum
> 
>  doc/guides/rel_notes/release_26_03.rst |   7 +
>  drivers/net/zxdh/zxdh_common.c         |  75 ++------
>  drivers/net/zxdh/zxdh_common.h         |   2 +-
>  drivers/net/zxdh/zxdh_ethdev.c         | 239 +++++++++++++++++--------
>  drivers/net/zxdh/zxdh_ethdev.h         |  23 ++-
>  drivers/net/zxdh/zxdh_ethdev_ops.c     | 165 ++++++++++++++---
>  drivers/net/zxdh/zxdh_ethdev_ops.h     |  15 ++
>  drivers/net/zxdh/zxdh_msg.c            |  52 ++++++
>  drivers/net/zxdh/zxdh_msg.h            |  24 ++-
>  drivers/net/zxdh/zxdh_pci.h            |   2 +
>  drivers/net/zxdh/zxdh_queue.c          | 137 +++++++++++---
>  drivers/net/zxdh/zxdh_queue.h          |  12 +-
>  drivers/net/zxdh/zxdh_rxtx.c           | 117 +++++++++---
>  drivers/net/zxdh/zxdh_tables.h         |  12 +-
>  14 files changed, 655 insertions(+), 227 deletions(-)
> 

I put this into next-net but had to do some work:
  - the commit messages were too vague, and lower case.
    I ended up rewriting them with AI help.
  - add missing entry into features matrix for link speed.
  - fix checkpatch warning about using %lx by using PRIx64 instead.

Hope this is alright, please recheck that wording matches what you expect.