[PATCH V3] nvme-pci: add sgl support

[Christoph Hellwig]

On Tue, Aug 01, 2017 at 04:48:04AM -0400, Keith Busch wrote:
> On Tue, Aug 01, 2017 at 08:29:00AM +0000, Chaitanya Kulkarni wrote:
> > [CK] Yes, I've observed approximately %5 better
> > performance for IO sizes larger than 32k (for sgl_threshold = 32k).
> 
> Is that a physically contiguous 32k, or does each 4k require a different
> SG element? Could you try to force both conditions and see how each
> scenario compares with PRP?

How do we find out the segment alignment without walking the list of
biovecs, which would be rather annoying.