Re: [PATCH QEMU v25 11/17] vfio: Get migration capability flags for container

[Cornelia Huck <cohuck@redhat.com>]

On Sun, 21 Jun 2020 01:51:20 +0530
Kirti Wankhede <kwankhede@nvidia.com> wrote:

> Added helper functions to get IOMMU info capability chain.
> Added function to get migration capability information from that
> capability chain for IOMMU container.
> 
> Similar change was proposed earlier:
> https://lists.gnu.org/archive/html/qemu-devel/2018-05/msg03759.html
> 
> Signed-off-by: Kirti Wankhede <kwankhede@nvidia.com>
> Cc: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
> Cc: Eric Auger <eric.auger@redhat.com>
> ---
>  hw/vfio/common.c              | 91 +++++++++++++++++++++++++++++++++++++++----
>  include/hw/vfio/vfio-common.h |  3 ++
>  2 files changed, 86 insertions(+), 8 deletions(-)
> 
> diff --git a/hw/vfio/common.c b/hw/vfio/common.c
> index 90e9a854d82c..e0d3d4585a65 100644
> --- a/hw/vfio/common.c
> +++ b/hw/vfio/common.c
> @@ -1229,6 +1229,75 @@ static int vfio_init_container(VFIOContainer *container, int group_fd,
>      return 0;
>  }
>  
> +static int vfio_get_iommu_info(VFIOContainer *container,
> +                               struct vfio_iommu_type1_info **info)
> +{
> +
> +    size_t argsz = sizeof(struct vfio_iommu_type1_info);
> +
> +    *info = g_new0(struct vfio_iommu_type1_info, 1);
> +again:
> +    (*info)->argsz = argsz;
> +
> +    if (ioctl(container->fd, VFIO_IOMMU_GET_INFO, *info)) {
> +        g_free(*info);
> +        *info = NULL;
> +        return -errno;
> +    }
> +
> +    if (((*info)->argsz > argsz)) {
> +        argsz = (*info)->argsz;
> +        *info = g_realloc(*info, argsz);

Do we need to guard against getting a bogus argsz value causing a huge
allocation that might fail and crash the program?

> +        goto again;
> +    }
> +
> +    return 0;
> +}

(...)

> @@ -1314,15 +1384,20 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as,
>           * existing Type1 IOMMUs generally support any IOVA we're
>           * going to actually try in practice.
>           */
> -        info.argsz = sizeof(info);
> -        ret = ioctl(fd, VFIO_IOMMU_GET_INFO, &info);
> -        /* Ignore errors */
> -        if (ret || !(info.flags & VFIO_IOMMU_INFO_PGSIZES)) {
> +        ret = vfio_get_iommu_info(container, &info);

Previously, we ignored errors from the IOMMU_GET_INFO ioctl, now we
error out. Was that change intended?

> +        if (ret) {
> +                goto free_container_exit;
> +        }
> +
> +        if (!(info->flags & VFIO_IOMMU_INFO_PGSIZES)) {
>              /* Assume 4k IOVA page size */
> -            info.iova_pgsizes = 4096;
> +            info->iova_pgsizes = 4096;
>          }
> -        vfio_host_win_add(container, 0, (hwaddr)-1, info.iova_pgsizes);
> -        container->pgsizes = info.iova_pgsizes;
> +        vfio_host_win_add(container, 0, (hwaddr)-1, info->iova_pgsizes);
> +        container->pgsizes = info->iova_pgsizes;
> +
> +        vfio_get_iommu_info_migration(container, info);
> +        g_free(info);
>          break;
>      }
>      case VFIO_SPAPR_TCE_v2_IOMMU:
(...)