[ofa-general] [PATCH RFC] rds: add iwarp support

[Steve Wise]

Or Gerlitz wrote:
> Steve Wise wrote:
>> Prior to the iWARP patch, the way this transport switch decision was 
>> made was to look up the local netdev based on the ipaddr(s) and if 
>> the netdev's ARP header type was INFINIBAND, then obviously the IB 
>> transport should be used. With the addition of iWARP, the decision is 
>> a little more complicated because the iWARP netdev arp type is ETHERNET.
> Olaf,
>
> Since the address provided to laddr_check() is the --source-- one 
> (please correct me if I am wrong) and this is slow path operation, how 
> about changing the transport switch to use rdma_bind_addr instead of 
> ip_dev_find()? rdma_bind_addr is a synchronous operation, works for 
> both IB and iWARP, and down the road will also support IPv6 (the API 
> is in place)
>
> Or.
>

Yes, after realizing this path is done only once when an RDS socket is 
bound, then we should probably just use rdma_bind_addr()...