Re: [PATCH net-next v2] bonding: move 802.3ad port state flags to uapi

[Jay Vosburgh <jay.vosburgh@canonical.com>]

Andy Gospodarek <andy@greyhouse.net> wrote:

>On Sun, Dec 15, 2019 at 08:10:15PM -0700, David Ahern wrote:
>> On 12/14/19 2:18 PM, Jakub Kicinski wrote:
>> > On Wed, 11 Dec 2019 14:30:58 -0800, Andy Roulin wrote:
>> >> The bond slave actor/partner operating state is exported as
>> >> bitfield to userspace, which lacks a way to interpret it, e.g.,
>> >> iproute2 only prints the state as a number:
>> >>
>> >> ad_actor_oper_port_state 15
>> >>
>> >> For userspace to interpret the bitfield, the bitfield definitions
>> >> should be part of the uapi. The bitfield itself is defined in the
>> >> 802.3ad standard.
>> >>
>> >> This commit moves the 802.3ad bitfield definitions to uapi.
>> >>
>> >> Related iproute2 patches, soon to be posted upstream, use the new uapi
>> >> headers to pretty-print bond slave state, e.g., with ip -d link show
>> >>
>> >> ad_actor_oper_port_state_str <active,short_timeout,aggregating,in_sync>
>> >>
>> >> Signed-off-by: Andy Roulin <aroulin@cumulusnetworks.com>
>> >> Acked-by: Roopa Prabhu <roopa@cumulusnetworks.com>
>> > 
>> > Applied, I wonder if it wouldn't be better to rename those
>> > s/AD_/BOND_3AD_/ like the prefix the stats have. 
>> > But I guess it's unlikely user space has those exact defines 
>> > set to a different value so can't cause a clash..
>> > 
>> 
>> I think that would be a better namespace now that it is in the UAPI.
>
>I agree that it would be nuch nicer.  I never really liked the 'AD'
>usage as an abbreviation for 802.3ad.

	Agreed, and, of course, the LACP standard moved to 802.1AX about
ten years ago; perhaps replace "AD" with "LACP" in the UAPI?

	-J

---
	-Jay Vosburgh, jay.vosburgh@canonical.com