Re: [RFC/PATCH 1/1] virtio: Introduce MMIO ops

[Jan Kiszka <jan.kiszka@siemens.com>]

On 30.04.20 13:11, Srivatsa Vaddagiri wrote:
> * Will Deacon <will@kernel.org> [2020-04-30 11:41:50]:
>
> > On Thu, Apr 30, 2020 at 04:04:46PM +0530, Srivatsa Vaddagiri wrote:
> > > If CONFIG_VIRTIO_MMIO_OPS is defined, then I expect this to be unconditionally
> > > set to 'magic_qcom_ops' that uses hypervisor-supported interface for IO (for
> > > example: message_queue_send() and message_queue_recevie() hypercalls).
> >
> > Hmm, but then how would such a kernel work as a guest under all the
> > spec-compliant hypervisors out there?
>
> Ok I see your point and yes for better binary compatibility, the ops have to be
> set based on runtime detection of hypervisor capabilities.
>
> > > Ok. I guess the other option is to standardize on a new virtio transport (like
> > > ivshmem2-virtio)?
> >
> > I haven't looked at that, but I suppose it depends on what your hypervisor
> > folks are willing to accomodate.
>
> I believe ivshmem2_virtio requires hypervisor to support PCI device emulation
> (for life-cycle management of VMs), which our hypervisor may not support. A
> simple shared memory and doorbell or message-queue based transport will work for
> us.

As written in our private conversation, a mapping of the ivshmem2 device 
discovery to platform mechanism (device tree etc.) and maybe even the 
register access for doorbell and life-cycle management to something 
hypercall-like would be imaginable. What would count more from virtio 
perspective is a common mapping on a shared memory transport.

That said, I also warned about all the features that PCI already defined 
(such as message-based interrupts) which you may have to add when going 
a different way for the shared memory device.

Jan

--
Siemens AG, Corporate Technology, CT RDA IOT SES-DE
Corporate Competence Center Embedded Linux