On Thu, Jul 11, 2024 at 08:48:10AM -0700, Andrea Bolognani wrote:
> IIUC having devices associated to the "correct" SMMU is only a
> requirement for optimal performance, not pure functionality, right?
> In other words, getting the association wrong will make things slower
> but they will keep work
On Tue, Jul 09, 2024 at 10:59:30AM GMT, Nicolin Chen wrote:
> On Tue, Jul 09, 2024 at 03:26:58PM +0200, Eric Auger wrote:
> > > +/* Build PCI Expander Bridge + Root Port from the top of PCI_BUS_MAX
> > > */
> > > +if (vms->num_nested_smmus) {
> > > +/* VIRT_NESTED_SMMU must hold al
On Tue, Jul 09, 2024 at 03:26:58PM +0200, Eric Auger wrote:
> > @@ -1580,12 +1647,33 @@ static void create_pcie(VirtMachineState *vms)
> > qemu_fdt_setprop_cell(ms->fdt, nodename, "#interrupt-cells", 1);
> > create_pcie_irq_map(ms, vms->gic_phandle, irq, nodename);
> >
> > -if (vms->
Hi Nicolin,
On 6/26/24 02:28, Nicolin Chen wrote:
> VIRT_SMMU can be used as an emulated SMMU, i.e. iommu=smmuv3. However, the
> MMIO space for VIRT_SMMU isn't large enough to accommodate multiple nested
> SMMUv3 instances. Add a new VIRT_NESTED_SMMU to separate MMIO space.
>
> Meanwhile, a nested
VIRT_SMMU can be used as an emulated SMMU, i.e. iommu=smmuv3. However, the
MMIO space for VIRT_SMMU isn't large enough to accommodate multiple nested
SMMUv3 instances. Add a new VIRT_NESTED_SMMU to separate MMIO space.
Meanwhile, a nested SMMUv3 could only work with a vfio-pci device that is
physi