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

[Will Deacon <will@kernel.org>]

On Thu, Apr 30, 2020 at 04:04:46PM +0530, Srivatsa Vaddagiri wrote:
> * Will Deacon <will@kernel.org> [2020-04-30 11:14:32]:
> 
> > > +#ifdef CONFIG_VIRTIO_MMIO_OPS
> > >  
> > > +static struct virtio_mmio_ops *mmio_ops;
> > > +
> > > +#define virtio_readb(a)		mmio_ops->mmio_readl((a))
> > > +#define virtio_readw(a)		mmio_ops->mmio_readl((a))
> > > +#define virtio_readl(a)		mmio_ops->mmio_readl((a))
> > > +#define virtio_writeb(val, a)	mmio_ops->mmio_writeb((val), (a))
> > > +#define virtio_writew(val, a)	mmio_ops->mmio_writew((val), (a))
> > > +#define virtio_writel(val, a)	mmio_ops->mmio_writel((val), (a))
> > 
> > How exactly are these ops hooked up? I'm envisaging something like:
> > 
> > 	ops = spec_compliant_ops;
> > 	[...]
> > 	if (firmware_says_hypervisor_is_buggy())
> > 		ops = magic_qcom_ops;
> > 
> > am I wrong?
> 
> 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?

> > > +int register_virtio_mmio_ops(struct virtio_mmio_ops *ops)
> > > +{
> > > +	pr_info("Registered %s as mmio ops\n", ops->name);
> > > +	mmio_ops = ops;
> > 
> > Not looking good, and really defeats the point of standardising this stuff
> > imo.
> 
> 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.

Will