On 10/24/25 10:43, Zhenzhong Duan wrote:
> Introduce a new PCIIOMMUOps optional callback, get_viommu_flags() which
> allows to retrieve flags exposed by a vIOMMU. The first planned vIOMMU
> device flag is VIOMMU_FLAG_WANT_NESTING_PARENT that advertises the
> support of HW nested stage translation scheme and wants other sub-system
> like VFIO's cooperation to create nesting parent HWPT.
>
> pci_device_get_viommu_flags() is a wrapper that can be called on a PCI
> device potentially protected by a vIOMMU.
>
> get_viommu_flags() is designed to return 64bit bitmap of purely vIOMMU
> flags which are only determined by user's configuration, no host
> capabilities involved. Reasons are:
>
> 1. host may has heterogeneous IOMMUs, each with different capabilities
> 2. this is migration friendly, return value is consistent between source
> and target.
>
> Note that this op will be invoked at the attach_device() stage, at which
> point host IOMMU capabilities are not yet forwarded to the vIOMMU through
> the set_iommu_device() callback that will be after the attach_device().
>
> See below sequence:
>
> vfio_device_attach():
> iommufd_cdev_attach():
> pci_device_get_viommu_flags() for HW nesting cap
> create a nesting parent HWPT
> attach device to the HWPT
> vfio_device_hiod_create_and_realize() creating hiod
> ...
> pci_device_set_iommu_device(hiod)
>
> Suggested-by: Yi Liu <yi.l.liu@intel.com>
> Signed-off-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
> Reviewed-by: Nicolin Chen <nicolinc@nvidia.com>
> Reviewed-by: Eric Auger <eric.auger@redhat.com>
> Reviewed-by: Yi Liu <yi.l.liu@intel.com>
> ---
> MAINTAINERS | 1 +
> include/hw/iommu.h | 25 +++++++++++++++++++++++++
Hmm, why not under include/hw/pci/ ? Was this discussed ?
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Thanks,
C.
> include/hw/pci/pci.h | 22 ++++++++++++++++++++++
> hw/pci/pci.c | 11 +++++++++++
> 4 files changed, 59 insertions(+)
> create mode 100644 include/hw/iommu.h
>
> diff --git a/MAINTAINERS b/MAINTAINERS
> index 36eef27b41..d94fbcbdfb 100644
> --- a/MAINTAINERS
> +++ b/MAINTAINERS
> @@ -2338,6 +2338,7 @@ 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/include/hw/iommu.h b/include/hw/iommu.h
> new file mode 100644
> index 0000000000..9b8bb94fc2
> --- /dev/null
> +++ b/include/hw/iommu.h
> @@ -0,0 +1,25 @@
> +/*
> + * General vIOMMU flags
> + *
> + * Copyright (C) 2025 Intel Corporation.
> + *
> + * SPDX-License-Identifier: GPL-2.0-or-later
> + */
> +
> +#ifndef HW_IOMMU_H
> +#define HW_IOMMU_H
> +
> +#include "qemu/bitops.h"
> +
> +/*
> + * Theoretical vIOMMU flags. Only determined by the vIOMMU device properties and
> + * independent on the actual host IOMMU capabilities they may depend on. Each
> + * flag can be an expectation or request to other sub-system or just a pure
> + * vIOMMU capability. vIOMMU can choose which flags to expose.
> + */
> +enum viommu_flags {
> + /* vIOMMU needs nesting parent HWPT to create nested HWPT */
> + VIOMMU_FLAG_WANT_NESTING_PARENT = BIT_ULL(0),
> +};
> +
> +#endif /* HW_IOMMU_H */
> diff --git a/include/hw/pci/pci.h b/include/hw/pci/pci.h
> index bde9dca8e2..cf99b5bb68 100644
> --- a/include/hw/pci/pci.h
> +++ b/include/hw/pci/pci.h
> @@ -462,6 +462,18 @@ typedef struct PCIIOMMUOps {
> * @devfn: device and function number of the PCI device.
> */
> void (*unset_iommu_device)(PCIBus *bus, void *opaque, int devfn);
> + /**
> + * @get_viommu_flags: get vIOMMU flags
> + *
> + * Optional callback, if not implemented, then vIOMMU doesn't support
> + * exposing flags to other sub-system, e.g., VFIO.
> + *
> + * @opaque: the data passed to pci_setup_iommu().
> + *
> + * Returns: bitmap with each representing a vIOMMU flag defined in
> + * enum viommu_flags.
> + */
> + uint64_t (*get_viommu_flags)(void *opaque);
> /**
> * @get_iotlb_info: get properties required to initialize a device IOTLB.
> *
> @@ -644,6 +656,16 @@ bool pci_device_set_iommu_device(PCIDevice *dev, HostIOMMUDevice *hiod,
> Error **errp);
> void pci_device_unset_iommu_device(PCIDevice *dev);
>
> +/**
> + * pci_device_get_viommu_flags: get vIOMMU flags.
> + *
> + * Returns: bitmap with each representing a vIOMMU flag defined in
> + * enum viommu_flags. Or 0 if vIOMMU doesn't report any.
> + *
> + * @dev: PCI device pointer.
> + */
> +uint64_t pci_device_get_viommu_flags(PCIDevice *dev);
> +
> /**
> * pci_iommu_get_iotlb_info: get properties required to initialize a
> * device IOTLB.
> diff --git a/hw/pci/pci.c b/hw/pci/pci.c
> index d0e81651aa..c9932c87e3 100644
> --- a/hw/pci/pci.c
> +++ b/hw/pci/pci.c
> @@ -3010,6 +3010,17 @@ void pci_device_unset_iommu_device(PCIDevice *dev)
> }
> }
>
> +uint64_t pci_device_get_viommu_flags(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_flags) {
> + return iommu_bus->iommu_ops->get_viommu_flags(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)