On 10/02/15 16:30, Jan Beulich wrote: >>>> Boris Ostrovsky <boris.ostrov...@oracle.com> 02/10/15 4:07 PM >>> >> On 02/10/2015 09:54 AM, Andrew Cooper wrote: >>> copy_to/from_guest() is not expensive. It is a straight memcpy with an >>> extable guards for pagefaults. >> True, but still why do this inside a loop? xmalloc() of less than a page >> is not that expensive, is it? >> >> (The downside is that when we have really lots of devices we may be >> asking for more than one page. I know that we try not to do this but >> again, I think the expense would be amortised over long loops.). > And risk failing the hypercall because there isn't enough contiguous memory? > And that perhaps only on really large systems where debugging may end up > being difficult? No, please don't.
Indeed. This hypercall is not part of a fastpath. It can afford not to amortise the cost in the name of making the code more simple and less liable to fail. ~Andrew _______________________________________________ Xen-devel mailing list Xen-devel@lists.xen.org http://lists.xen.org/xen-devel
