[PATCH 2/3] nvme: don't poll the CQ from the kthread

[Keith Busch]

On Wed, Feb 17, 2016 at 07:03:13PM +0100, Christoph Hellwig wrote:
> There is no reason to do unconditional polling of CQs per the NVMe
> spec.
> 
> Signed-off-by: Christoph Hellwig <hch at lst.de>

Looks good. Now we'll find out if anyone was unknowingly relying on
this. :)

The legacy IRQ used for the very first NVMe command after reset tripped
up some devices in the past, but the polling hid the breakage.

Reviewed-by: Keith Busch <keith.busch at intel.com>