On 21/12/2016 17:19, Fam Zheng wrote:
> It's clever! It'd be a bit more complicated than that, though. Things like
> queues etc in block/nvme.c have to be preserved, and if we already ensure
> that,
> ram blocks can be preserved similarly, but indeed bounce buffers can be
> handled
> that way.
On Wed, 12/21 16:46, Paolo Bonzini wrote:
>
>
> On 20/12/2016 17:31, Fam Zheng wrote:
> > +hbitmap_iter_init(, s->free_chunks, 1);
> > +if (contiguous) {
> > +while (true) {
> > +bool satisfy = true;
> > +next = hbitmap_iter_next();
> > +if
This is a simple helper library to be used by VFIO device drivers in
QEMU, makeing it very easy to interface with /dev/vfio and do DMA
mappings.
Especially, once initialized, this module proactively maps all guest ram
regions to IO address space (in the host IOMMU context) so that in
further I/O