[Intel-gfx] [PATCH v3 2/8] drm/i915: Adds graphic address space ballooning logic

[Tian, Kevin]

> From: Tvrtko Ursulin
> Sent: Friday, December 12, 2014 9:00 PM
> > @@ -1683,6 +1684,16 @@ int i915_gem_setup_global_gtt(struct
> drm_device *dev,
> >
> >   	/* Subtract the guard page ... */
> >   	drm_mm_init(&ggtt_vm->mm, start, end - start - PAGE_SIZE);
> > +
> > +	dev_priv->gtt.base.start = start;
> > +	dev_priv->gtt.base.total = end - start;
> > +
> > +	if (intel_vgpu_active(dev)) {
> > +		ret = intel_vgt_balloon(dev);
> > +		if (ret)
> > +			return ret;
> > +	}
> > +
> 
> Out of curiosity, what will be the mechanism to prevent a vGPU instance
> from ignoring the ballooning data? Must be something in the hypervisor
> blocking pass-through access to such domains?
> 
> And probably GPU reset should also be disallowed for vGPU instances?
> 

GPU reset is allowed and the host side needs to emulate the vGPU reset
behavior. A simple example is that we need remove this vGPU from the
scheduling queue, upon a vGPU reset request.

Thanks
Kevin