Hi Zhenzhong,
On 7/8/25 1:05 PM, Zhenzhong Duan wrote:
> pci_device_get_viommu_cap() call pci_device_get_iommu_bus_devfn()
> to get iommu_bus->iommu_ops and call get_viommu_cap() callback to
> get a bitmap with each bit represents a vIOMMU exposed capability.
Suggesting:
Introduce a new PCIIOMMUOps optional callback, get_viommu_cap() which
allows to retrieve capabilities exposed by a vIOMMU. The first planned
capability is VIOMMU_CAP_HW_NESTED that advertises the support of HW
nested stage translation scheme. pci_device_get_viommu_cap is a wrapper
that can be called on a PCI device potentially protected by a vIOMMU.
>
> Suggested-by: Yi Liu <yi.l....@intel.com>
> Signed-off-by: Zhenzhong Duan <zhenzhong.d...@intel.com>
> ---
> MAINTAINERS | 1 +
> hw/pci/pci.c | 11 +++++++++++
> include/hw/iommu.h | 16 ++++++++++++++++
> include/hw/pci/pci.h | 23 +++++++++++++++++++++++
> 4 files changed, 51 insertions(+)
> create mode 100644 include/hw/iommu.h
>
> diff --git a/MAINTAINERS b/MAINTAINERS
> index 1842c3dd83..d9fc977b81 100644
> --- a/MAINTAINERS
> +++ b/MAINTAINERS
> @@ -2302,6 +2302,7 @@ F: include/system/iommufd.h
> F: backends/host_iommu_device.c
> F: include/system/host_iommu_device.h
> F: include/qemu/chardev_open.h
> +F: include/hw/iommu.h
> F: util/chardev_open.c
> F: docs/devel/vfio-iommufd.rst
>
> diff --git a/hw/pci/pci.c b/hw/pci/pci.c
> index c70b5ceeba..df1fb615a8 100644
> --- a/hw/pci/pci.c
> +++ b/hw/pci/pci.c
> @@ -2992,6 +2992,17 @@ void pci_device_unset_iommu_device(PCIDevice *dev)
> }
> }
>
> +uint64_t pci_device_get_viommu_cap(PCIDevice *dev)
> +{
> + PCIBus *iommu_bus;
> +
> + pci_device_get_iommu_bus_devfn(dev, &iommu_bus, NULL, NULL);
> + if (iommu_bus && iommu_bus->iommu_ops->get_viommu_cap) {
> + return iommu_bus->iommu_ops->get_viommu_cap(iommu_bus->iommu_opaque);
> + }
> + return 0;
> +}
> +
> int pci_pri_request_page(PCIDevice *dev, uint32_t pasid, bool priv_req,
> bool exec_req, hwaddr addr, bool lpig,
> uint16_t prgi, bool is_read, bool is_write)
> diff --git a/include/hw/iommu.h b/include/hw/iommu.h
> new file mode 100644
> index 0000000000..e80aaf4431
> --- /dev/null
> +++ b/include/hw/iommu.h
> @@ -0,0 +1,16 @@
> +/*
> + * General vIOMMU capabilities, flags, etc
> + *
> + * Copyright (C) 2025 Intel Corporation.
> + *
> + * SPDX-License-Identifier: GPL-2.0-or-later
> + */
> +
> +#ifndef HW_IOMMU_H
> +#define HW_IOMMU_H
> +
> +enum {
> + VIOMMU_CAP_STAGE1 = BIT_ULL(0), /* stage1 page table supported */
with the enum name change,
Reviewed-by: Eric Auger <eric.au...@redhat.com>
Thanks
Eric
> +};
> +
> +#endif /* HW_IOMMU_H */
> diff --git a/include/hw/pci/pci.h b/include/hw/pci/pci.h
> index df3cc7b875..a11ab14bdc 100644
> --- a/include/hw/pci/pci.h
> +++ b/include/hw/pci/pci.h
> @@ -453,6 +453,19 @@ typedef struct PCIIOMMUOps {
> * @devfn: device and function number of the PCI device.
> */
> void (*unset_iommu_device)(PCIBus *bus, void *opaque, int devfn);
> + /**
> + * @get_viommu_cap: get vIOMMU capabilities
> + *
> + * Optional callback, if not implemented, then vIOMMU doesn't
> + * support exposing capabilities to other subsystem, e.g., VFIO.
> + * vIOMMU can choose which capabilities to expose.
> + *
> + * @opaque: the data passed to pci_setup_iommu().
> + *
> + * Returns: 64bit bitmap with each bit represents a capability emulated
> + * by VIOMMU_CAP_* in include/hw/iommu.h
> + */
> + uint64_t (*get_viommu_cap)(void *opaque);
> /**
> * @get_iotlb_info: get properties required to initialize a device IOTLB.
> *
> @@ -633,6 +646,16 @@ bool pci_device_set_iommu_device(PCIDevice *dev,
> HostIOMMUDevice *hiod,
> Error **errp);
> void pci_device_unset_iommu_device(PCIDevice *dev);
>
> +/**
> + * pci_device_get_viommu_cap: get vIOMMU capabilities.
> + *
> + * Returns a 64bit bitmap with each bit represents a vIOMMU exposed
> + * capability, 0 if vIOMMU doesn't support esposing capabilities.
> + *
> + * @dev: PCI device pointer.
> + */
> +uint64_t pci_device_get_viommu_cap(PCIDevice *dev);
> +
> /**
> * pci_iommu_get_iotlb_info: get properties required to initialize a
> * device IOTLB.
