[PATCH v7 01/23] net: Introduce direct data placement tcp offload

[Aurelien Aptel]

Jakub Kicinski kuba at kernel.org writes:
> Sounds good. Just to be clear - I was suggesting:
>
>         net_device_ops->ddp_ulp_ops->set_ulp_caps()
>
> so an extra indirection, but if you're worried about the overhead
> an ndo is fine, too.

Sure, thanks.

>> We add ETHTOOL messages to get and set ULP caps:
>>
>> - ETHTOOL_MSG_ULP_CAPS_GET: get device ulp capabilities
>> - ETHTOOL_MSG_ULP_CAPS_SET: set device up capabilities
>
> ULP or DDP? Are you planning to plumb TLS thru the same ops?
> Otherwise ULP on its own may be a little too generic of a name.

TLS is not in our scope. It was originally used as a reference.
We will use the term "ULP_DDP".

>
>> The GET reply code can use ethnl_put_bitset32() which does the job of
>> sending bits + their names as strings.
>>
>> The SET code would apply the changes to netdev->ulp_ddp_caps.caps_active.
>>
>> # Statistics
>>
>> If the ETHTOOL_MSG_ULP_CAPS_GET message requests statistics (by
>
> Would it make sense to drop the _CAPS from the name, then?
> Or replace by something more general, like INFO?

Ok, we will drop the _CAPS.

>>    # query ULP stats of $dev
>>    ethtool -u|--ulp-get --include-statistics <dev>
>
> -I|--include-statistics ?

Could you please elaborate what is the comment?

>>    # set $cap to $val on device $dev
>>    -U|--ulp-set <dev> <cap> [on|off]
>
> Sounds good!

Since -u is taken we are going with -J/-j and --ulp-ddp to keep it
consistent with the netlink flags.

> Thanks for describing the options! I definitely prefer ethtool/netlink.

Great, we will add it in v8.

Thanks