Hello!
> If I read this correctly, memory regions already keep track of
> ioeventfds and this patch can simply trigger them manually if that had
> not already been done?
Yes, exactly, and this is the new idea.
> Only that we don't have such a nice tracking structure that memory
> regions alrea
On Thu, 19 Nov 2015 15:17:57 +0300
Pavel Fedin wrote:
> Hello!
>
> > > Paolo, do you see anything wrong with making
> > > memory_region_add_eventfd work (slowly) without kvm ioeventfd support?
> > >
> >
> > Sure, it's even been on the todo list for a while. Stefan Hajnoczi had
> > a patch, th
On 19/11/2015 13:17, Pavel Fedin wrote:
> Ok, good. So, this has already been tested. Ok, i think i can further extend
> this patch by:
> 1. Add a flag to disable memory_region_dispatch_write_ioeventfds(), to be set
> by KVM code for example. So that with KVM we have even
> smaller performance
Hello!
> > Paolo, do you see anything wrong with making
> > memory_region_add_eventfd work (slowly) without kvm ioeventfd support?
> >
>
> Sure, it's even been on the todo list for a while. Stefan Hajnoczi had
> a patch, the only ugly thing was that it slowed down a little all
> non-ioeventfd a
On Thu, Nov 19, 2015 at 01:06:17PM +0100, Paolo Bonzini wrote:
>
>
> On 19/11/2015 13:01, Michael S. Tsirkin wrote:
> >> > You know... I took a look at this, and yes, i could simply hook up
> >> > emulation into memory region handlers. And everything that
> >> > expects KVM eventfd binding will
On 19/11/2015 13:01, Michael S. Tsirkin wrote:
>> > You know... I took a look at this, and yes, i could simply hook up
>> > emulation into memory region handlers. And everything that
>> > expects KVM eventfd binding will magically start working, probably
>> > rendering some bypass code obsolet
On Thu, Nov 19, 2015 at 03:02:12PM +0300, Pavel Fedin wrote:
> Hello!
>
> > > I think if you have motivation, you could implement userspace forwarding
> > > for ccw yourself,
> > since you know the thing and know how to
> > > do it. For MMIO it was indeed very simple.
> >
> > I'll take a peek a
Hello!
> > I think if you have motivation, you could implement userspace forwarding
> > for ccw yourself,
> since you know the thing and know how to
> > do it. For MMIO it was indeed very simple.
>
> I'll take a peek at your patch.
This is actually a note for Michael. ccw support is one more
On Thu, Nov 19, 2015 at 02:44:37PM +0300, Pavel Fedin wrote:
> Hello!
>
> > OK, that's better, thanks!
>
> Yes, indeed this was simple.
>
> > Why do we need
> > if (kvm_eventfds_enabled()) {
> > memory_region_add_eventfd(&proxy->iomem,
> > VIRTIO_MMIO_QUEUENOTIFY, 4,
> >
Hello!
> OK, that's better, thanks!
Yes, indeed this was simple.
> Why do we need
> if (kvm_eventfds_enabled()) {
> memory_region_add_eventfd(&proxy->iomem, VIRTIO_MMIO_QUEUENOTIFY,
> 4,
> true, n, notifier);
> } else if (!set_ha
On Thu, 19 Nov 2015 13:18:13 +0300
Pavel Fedin wrote:
> Hello!
>
> > Looks like this would be ok for virtio-ccw (as it does not call
> > virtio_queue_set_host_notifier_forwarding)
>
> Yes, this is the reason why i intentionally did not insert extra logic into
> virtio_queue_set_host_notifier
On Thu, Nov 19, 2015 at 12:50:49PM +0300, Pavel Fedin wrote:
> If you happen to have a kernel with ioeventfd support enabled, but
> missing support for them in KVM, and you attempt to enable vhost by
> setting vhost=on, qemu aborts with error:
>
> kvm_mem_ioeventfd_add: error adding ioeventfd: Fun
Hello!
> Looks like this would be ok for virtio-ccw (as it does not call
> virtio_queue_set_host_notifier_forwarding)
Yes, this is the reason why i intentionally did not insert extra logic into
virtio_queue_set_host_notifier_fd_handler(), but made
it into separate function. I don't know whethe
Looks like this would be ok for virtio-ccw (as it does not call
virtio_queue_set_host_notifier_forwarding)
Question is might something like this for virtio-ccw useful as well?
We cannot use memory_region, though, we would need to handle that in our
diagnose code.
Conny, FYI.
On 11/19/2015 10
If you happen to have a kernel with ioeventfd support enabled, but
missing support for them in KVM, and you attempt to enable vhost by
setting vhost=on, qemu aborts with error:
kvm_mem_ioeventfd_add: error adding ioeventfd: Function not implemented
This patch adds a mechanism which allows to emul
15 matches
Mail list logo
