[openib-general] Re: [PATCH] [CMA] support loopback addresses

[Michael S. Tsirkin]

Quoting r. Sean Hefty <mshefty at ichips.intel.com>:
> >>The alternative is to have the API behave one way for destination addresses that 
> >>are local, versus those that are remote, but this complicates applications that 
> >>are not aware if an address belongs to the local or a remote system.
> > 
> > So, maybe we can reuse the ib_addr wq? Having all requests complete from
> > a single thread could help applications, I think.



> I did consider pushing this down into ib_addr because it has an existing work 
> queue, and it would have been easier to implement, but ib_addr simply converts 
> an IP address into a GID/pkey.  To keep the CMA RDMA centric, rather than 
> IB-specific, it seemed better to me to map lookback addresses to an RDMA device 
> outside of IB specific code.  For example, if the mapping were moved into 
> ib_addr, then loopback addresses would not work for a system containing only 
> iWarp devices.

Does it really matter in which module doe sthe function reside?

> If there's concern about using too many work queues in the IB stack, we could 
> export a single work queue from ib_core that's accessible to multiple modules. 
> Work queues appear to be used by these modules: ib_mad, rdma_cm, ib_cm, ib_addr, 
>   sdp, and ipoib.
> 
> - Sean
> 

Sounds good, I would start with just rdma_cm ib_cm and ib_addr.

But note that exposing the wq means you must be explicit on what runs
on this queue, since otehrwise a user can flush the queue from 
inside it or other such deadlocking silliness.

Need to be careful.

-- 
MST