On Oct  7 18:23, Lukasz Maniak wrote:
> This patch implements initial support for Single Root I/O Virtualization
> on an NVMe device.
> 
> Essentially, it allows to define the maximum number of virtual functions
> supported by the NVMe controller via sriov_max_vfs parameter.
> 
> Passing a non-zero value to sriov_max_vfs triggers reporting of SR-IOV
> capability by a physical controller and ARI capability by both the
> physical and virtual function devices.
> 
> NVMe controllers created via virtual functions mirror functionally
> the physical controller, which may not entirely be the case, thus
> consideration would be needed on the way to limit the capabilities of
> the VF.
> 
> NVMe subsystem is required for the use of SR-IOV.
> 
> Signed-off-by: Lukasz Maniak <lukasz.maniak@linux.intel.com>
> ---
>  hw/nvme/ctrl.c           | 74 ++++++++++++++++++++++++++++++++++++++--
>  hw/nvme/nvme.h           |  1 +
>  include/hw/pci/pci_ids.h |  1 +
>  3 files changed, 73 insertions(+), 3 deletions(-)
> 
> diff --git a/hw/nvme/ctrl.c b/hw/nvme/ctrl.c
> index 6a571d18cf..ad79ff0c00 100644
> --- a/hw/nvme/ctrl.c
> +++ b/hw/nvme/ctrl.c
> @@ -35,6 +35,7 @@
>   *              mdts=<N[optional]>,vsl=<N[optional]>, \
>   *              zoned.zasl=<N[optional]>, \
>   *              zoned.auto_transition=<on|off[optional]>, \
> + *              sriov_max_vfs=<N[optional]> \
>   *              subsys=<subsys_id>
>   *      -device nvme-ns,drive=<drive_id>,bus=<bus_name>,nsid=<nsid>,\
>   *              zoned=<true|false[optional]>, \
> @@ -106,6 +107,12 @@
>   *   transitioned to zone state closed for resource management purposes.
>   *   Defaults to 'on'.
>   *
> + * - `sriov_max_vfs`
> + *   Indicates the maximum number of PCIe virtual functions supported
> + *   by the controller. The default value is 0. Specifying a non-zero value
> + *   enables reporting of both SR-IOV and ARI capabilities by the NVMe device.
> + *   Virtual function controllers will not report SR-IOV capability.
> + *
>   * nvme namespace device parameters
>   * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
>   * - `shared`
> @@ -160,6 +167,7 @@
>  #include "sysemu/block-backend.h"
>  #include "sysemu/hostmem.h"
>  #include "hw/pci/msix.h"
> +#include "hw/pci/pcie_sriov.h"
>  #include "migration/vmstate.h"
>  
>  #include "nvme.h"
> @@ -175,6 +183,9 @@
>  #define NVME_TEMPERATURE_CRITICAL 0x175
>  #define NVME_NUM_FW_SLOTS 1
>  #define NVME_DEFAULT_MAX_ZA_SIZE (128 * KiB)
> +#define NVME_MAX_VFS 127
> +#define NVME_VF_OFFSET 0x1
> +#define NVME_VF_STRIDE 1
>  
>  #define NVME_GUEST_ERR(trace, fmt, ...) \
>      do { \
> @@ -5583,6 +5594,10 @@ static void nvme_ctrl_reset(NvmeCtrl *n)
>          g_free(event);
>      }
>  
> +    if (!pci_is_vf(&n->parent_obj) && n->params.sriov_max_vfs) {
> +        pcie_sriov_pf_disable_vfs(&n->parent_obj);
> +    }
> +
>      n->aer_queued = 0;
>      n->outstanding_aers = 0;
>      n->qs_created = false;
> @@ -6264,6 +6279,19 @@ static void nvme_check_constraints(NvmeCtrl *n, Error **errp)
>          error_setg(errp, "vsl must be non-zero");
>          return;
>      }
> +
> +    if (params->sriov_max_vfs) {
> +        if (!n->subsys) {
> +            error_setg(errp, "subsystem is required for the use of SR-IOV");
> +            return;
> +        }
> +
> +        if (params->sriov_max_vfs > NVME_MAX_VFS) {
> +            error_setg(errp, "sriov_max_vfs must be between 0 and %d",
> +                       NVME_MAX_VFS);
> +            return;
> +        }
> +    }
>  }
>  
>  static void nvme_init_state(NvmeCtrl *n)
> @@ -6321,6 +6349,20 @@ static void nvme_init_pmr(NvmeCtrl *n, PCIDevice *pci_dev)
>      memory_region_set_enabled(&n->pmr.dev->mr, false);
>  }
>  
> +static void nvme_init_sriov(NvmeCtrl *n, PCIDevice *pci_dev, uint16_t offset,
> +                            uint64_t bar_size)
> +{
> +    uint16_t vf_dev_id = n->params.use_intel_id ?
> +                         PCI_DEVICE_ID_INTEL_NVME : PCI_DEVICE_ID_REDHAT_NVME;
> +
> +    pcie_sriov_pf_init(pci_dev, offset, "nvme", vf_dev_id,
> +                       n->params.sriov_max_vfs, n->params.sriov_max_vfs,
> +                       NVME_VF_OFFSET, NVME_VF_STRIDE, NULL);

Did you consider adding a new device for the virtual function device,
"nvmevf"?

Down the road it might help with the variations in capabilities that you
describe.