On Wed, 2012-09-05 at 15:27 +1000, Alexey Kardashevskiy wrote:
> On 05/09/12 15:17, Benjamin Herrenschmidt wrote:
> > On Tue, 2012-09-04 at 22:57 -0600, Alex Williamson wrote:
> >
> >> Do we need an extra region info field, or is it sufficient that we
> >> define a region to be mmap'able with getpa
On 05/09/12 15:17, Benjamin Herrenschmidt wrote:
On Tue, 2012-09-04 at 22:57 -0600, Alex Williamson wrote:
Do we need an extra region info field, or is it sufficient that we
define a region to be mmap'able with getpagesize() pages when the MMAP
flag is set and simply offset the region within th
On Tue, 2012-09-04 at 22:57 -0600, Alex Williamson wrote:
> Do we need an extra region info field, or is it sufficient that we
> define a region to be mmap'able with getpagesize() pages when the MMAP
> flag is set and simply offset the region within the device fd? ex.
Alexey ? You mentioned you
On Wed, 2012-09-05 at 11:16 +1000, Benjamin Herrenschmidt wrote:
> > > It's still bad in more ways that I care to explain...
> >
> > Well it is right before pci_reassigndev_resource_alignment() which is
> > common and does the same thing.
> >
> > > The main one is that you do the "fixup" in a ve
> > It's still bad in more ways that I care to explain...
>
> Well it is right before pci_reassigndev_resource_alignment() which is
> common and does the same thing.
>
> > The main one is that you do the "fixup" in a very wrong place anyway and
> > it might cause cases of overlapping BARs.
>
>
On 05/09/12 05:45, Benjamin Herrenschmidt wrote:
On Tue, 2012-09-04 at 17:36 +1000, Alexey Kardashevskiy wrote:
VFIO adds a separate memory region for every BAR and tries
to mmap() it to provide direct BAR mapping to the guest.
If it succeedes, QEMU registers this address with kvm_set_phys_mem()
On Tue, 2012-09-04 at 17:36 +1000, Alexey Kardashevskiy wrote:
> VFIO adds a separate memory region for every BAR and tries
> to mmap() it to provide direct BAR mapping to the guest.
> If it succeedes, QEMU registers this address with kvm_set_phys_mem().
> However it is not always possible because
VFIO adds a separate memory region for every BAR and tries
to mmap() it to provide direct BAR mapping to the guest.
If it succeedes, QEMU registers this address with kvm_set_phys_mem().
However it is not always possible because such a BAR should
be host page size aligned. In this case VFIO uses "sl
