[PATCH 5/5] NVMe: IO queue deletion re-write

[Keith Busch]

On Sun, Jan 03, 2016 at 08:17:04AM -0800, Christoph Hellwig wrote:
> On Sun, Jan 03, 2016 at 03:43:31PM +0000, Keith Busch wrote:
> We'd get a reset for both cases, which isn't really what we what.
> I think we should be setting NVME_CTRL_RESETTING before doing a shutdown
> so that errors get reported in line.

We hold a mutex while resetting. The second reset will be stuck there.
 
> > You'll also need something to end
> > work waiting for a request when more queues exist than admin tags.
> 
> It's called the block layer.  blk_mq_alloc_request will block until
> the tag is available unless we explicitly request non-blocking behavior.

In the scenario I'm describing you _don't_ want it to succeed in getting
a request. You don't want it to wait indefinitely for one either.