[openib-general] Re: RDMA Generic Connection Management

[Michael S. Tsirkin]

Quoting r. Sean Hefty <mshefty at ichips.intel.com>:
> Subject: Re: RDMA Generic Connection Management
> 
> Michael S. Tsirkin wrote:
> >How is this different from what we have with ib_verbs now?
> 
> With ib_verbs, users receive notification of device addition/removal. 
> This interface doesn't require receiving that notification.

Wont users also activate verbs directly anyway, and so be required
to handle this notification?

> >I think that reasonable ULPs must register for hotplug events
> >in the ib layer, anyway.
> >So when they get a device removal callback, they close the qps etc.
> >
> >Makes sense?
> 
> This opens up the possibility for a user to receive a reference to a 
> device that they may not have received previous notification for. 

We seem to have that with verbs, dont we?

> Similarly, the device could have been removed before the call returned, 

I thought ULP gets a notification *before* device removal, not after
this, so it can synchronise that, addrss resolution, and verb calls.

> making the pointer invalid.

The problem probably can be solved by taking the appropriate semaphore, can it
not?

-- 
MST