[openib-general] [RFC] IB address translation using ARP

[Sean Hefty]

Hal Rosenstock wrote:
>>>(We should be able to pull that from ib_at.)
>>
>>or sdp_link which has the more temporal netdev references currently :-)

I will look at both.  Thanks.

>>>The API is similar to the route
>>>portion of ib_at, but corrects issues with canceling requests.
>>
>>What are you referring to here ?

It looks like the user can get a callback after cancel returns.  This is a 
similar problem that we discussed wrt canceling MADs many moons ago.  The return 
code can be misleading.

>>>The intent is that the CMA will use this service to locate the
>>>proper RDMA device GUID
>>
>>This is the outgoing device, right ?

correct

>>> and port to use in establishing a connection.
>>>Hopefully, this makes it clearer how I envision address translation wrt
>>>the CMA.
>>
>>When/if there are multiple paths, how is the selection performed ?
>>
>>Also, on the passive side, would a rdma_resolve_route also be done or
>>something else or wouldn't just a path lookup suffice here ? If it is
>>the latter, is that hidden under the rdma_accept or handled otherwise ?

On the passive side, the source/destination IP addresses are carried in the CM 
REQ.  The CM provides path records as part of the REQ callback.

> What happens if the destination IP address is a local one ? I think
> there is some missing code here.

I think there's code in at.c to handle that case that could be re-used.

> Also, shouldn't non subnet local destination IP addresses be handled ?

How does that map to the IB subnet?  Would it require global routing, or are 
non-subnet local addresses a valid configuration on a local IB subnet?

- Sean