On Wed, Nov 07, 2007 at 04:21:02PM +0200, Amit Shah wrote:
> @@ -1649,6 +1913,15 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
> }
>
> switch (nr) {
> + case KVM_PV_DMA_MAP:
> + ret = pv_map_hypercall(vcpu, a0, a1);
> + break;
> + case KVM_PV_DMA_UNMAP:
> + ret = pv_unmap_hypercall(vcpu, a0);
> + break;
> + case KVM_PV_PCI_DEVICE:
> + ret = pv_mapped_pci_device_hypercall(vcpu, a0);
> + break;
> default:
> ret = -KVM_ENOSYS;
> break;
How does synchronization work with that design? I don't see a hypercall
to synchronize de DMA buffers. It will only work if GART is used as the
dma_ops backend on the host side and not with SWIOTLB. But GART can be
configured away. Or do I miss something?
Joerg
--
| AMD Saxony Limited Liability Company & Co. KG
Operating | Wilschdorfer Landstr. 101, 01109 Dresden, Germany
System | Register Court Dresden: HRA 4896
Research | General Partner authorized to represent:
Center | AMD Saxony LLC (Wilmington, Delaware, US)
| General Manager of AMD Saxony LLC: Dr. Hans-R. Deppe, Thomas McCoy
On Monday 12 November 2007 21:25:22 Joerg Roedel wrote:
> On Wed, Nov 07, 2007 at 04:21:02PM +0200, Amit Shah wrote:
> > @@ -1649,6 +1913,15 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
> > }
> >
> > switch (nr) {
> > + case KVM_PV_DMA_MAP:
> > + ret = pv_map_hypercall(vcpu, a0, a1);
> > + break;
> > + case KVM_PV_DMA_UNMAP:
> > + ret = pv_unmap_hypercall(vcpu, a0);
> > + break;
> > + case KVM_PV_PCI_DEVICE:
> > + ret = pv_mapped_pci_device_hypercall(vcpu, a0);
> > + break;
> > default:
> > ret = -KVM_ENOSYS;
> > break;
>
> How does synchronization work with that design? I don't see a hypercall
> to synchronize de DMA buffers. It will only work if GART is used as the
> dma_ops backend on the host side and not with SWIOTLB. But GART can be
> configured away. Or do I miss something?
A per-VM lock is needed while mapping or unmapping. It's one of the TODOs.