Re: [PATCH v6 02/26] IB/Verbs: Implement raw management helpers

From: Michael Wang
Date: Mon Apr 27 2015 - 03:41:54 EST




On 04/24/2015 06:29 PM, Jason Gunthorpe wrote:
> On Fri, Apr 24, 2015 at 03:15:54PM +0000, Liran Liss wrote:
>>> From: linux-rdma-owner@xxxxxxxxxxxxxxx [mailto:linux-rdma-
>
>>> +static inline int rdma_tech_iboe(struct ib_device *device, u8 port_num)
>>> +{
>>> + return device->query_transport(device, port_num)
>>> + == RDMA_TRANSPORT_IBOE;
>>
>> Remove RDMA_TRANSPORT_IBOE.
>> In the current code, the test should be: (IB transport && Ethernet link layer).
>
> No, if this rmda_tech stuff is to reflect the specification the port
> implements, then RoCEE is a valid specification (IBA Annex A16), as it
> RoCEEv2 (A17).
>
> This patch set is trying to drop then link layer concept entirely.

I think a new enum on protocol could help solve the conflict in here, we
can still get rid of the link layer meanwhile leave the legacy
transport type alone :-)

Regards,
Michael Wang

>
> Jason
>
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/