Re: [Qemu-devel] [RFC PATCH] vfio: VFIO Driver core framework

[Alex Williamson]

On Tue, 2011-11-29 at 13:01 +1100, Alexey Kardashevskiy wrote:
> Hi all,
> 
> Another problem I hit on POWER - MSI interrupts allocation. The existing VFIO 
> does not expect a PBH
> to support less interrupts that a device might request. In my case, PHB's 
> limit is 8 interrupts
> while my test card (10Gb ethernet CXGB3) wants 9. Below are the patches to 
> demonstrate the idea.

Seems reasonable.  I assume we'd need similar for vfio_pci_setup_msi,
though I haven't seen anything use more than a single MSI interrupt.
Thanks,

Alex

> KERNEL patch:
> 
> diff --git a/drivers/vfio/pci/vfio_pci_intrs.c 
> b/drivers/vfio/pci/vfio_pci_intrs.c
> index 7d45c6b..d44b9bf 100644
> --- a/drivers/vfio/pci/vfio_pci_intrs.c
> +++ b/drivers/vfio/pci/vfio_pci_intrs.c
> @@ -458,17 +458,32 @@ int vfio_pci_setup_msix(struct vfio_pci_device *vdev, 
> int nvec, int __user *inta
>               vdev->msix[i].entry = i;
>               vdev->ev_msix[i] = ctx;
>       }
> -     if (!ret)
> +     if (!ret) {
>               ret = pci_enable_msix(pdev, vdev->msix, nvec);
> +             /*
> +                The kernel is unable to allocate requested number of IRQs
> +                and returned the available number.
> +              */
> +             if (0 < ret) {
> +                     ret = pci_enable_msix(pdev, vdev->msix, ret);
> +             }
> +     }
>       vdev->msix_nvec = 0;
> -     for (i = 0; i < nvec && !ret; i++) {
> -             ret = request_irq(vdev->msix[i].vector, msihandler, 0,
> -                               "vfio", vdev->ev_msix[i]);
> -             if (ret)
> -                     break;
> -             vdev->msix_nvec = i+1;
> +     if (0 == ret) {
> +             vdev->msix_nvec = 0;
> +             ret = 0;
> +             for (i = 0; i < nvec && !ret; i++) {
> +                     ret = request_irq(vdev->msix[i].vector, msihandler, 0,
> +                                     "vfio", vdev->ev_msix[i]);
> +                     if (ret)
> +                             break;
> +                     vdev->msix_nvec = i+1;
> +             }
> +             if ((0 == vdev->msix_nvec) && (0 != ret))
> +                     vfio_pci_drop_msix(vdev);
> +             else
> +                     ret = vdev->msix_nvec;
>       }
> -     if (ret)
> -             vfio_pci_drop_msix(vdev);
> +
>       return ret;
>  }
> 
> === end ===
> 
> 
> QEMU patch:
> 
> diff --git a/hw/vfio_pci.c b/hw/vfio_pci.c
> index 020961a..980eec7 100644
> --- a/hw/vfio_pci.c
> +++ b/hw/vfio_pci.c
> @@ -341,7 +341,8 @@ static void vfio_enable_msi(VFIODevice *vdev, bool msix)
>          }
>      }
> 
> -    if (ioctl(vdev->fd, VFIO_DEVICE_SET_IRQ_EVENTFDS, fds)) {
> +    ret = ioctl(vdev->fd, VFIO_DEVICE_SET_IRQ_EVENTFDS, fds);
> +    if (0 > ret) {
>          fprintf(stderr, "vfio: Error: Failed to setup MSI/X fds %s\n",
>                  strerror(errno));
>          for (i = 0; i < vdev->nr_vectors; i++) {
> @@ -355,6 +356,8 @@ static void vfio_enable_msi(VFIODevice *vdev, bool msix)
>          qemu_free(vdev->msi_vectors);
>          vdev->nr_vectors = 0;
>          return;
> +    } else if (0 < ret) {
> +        vdev->nr_vectors = ret;
>      }
> 
>      vdev->interrupt = msix ? INT_MSIX : INT_MSI;
> 
> 
> === end ===