On Mon, Jun 11, 2018 at 01:52:54PM +0200, Christian Ehrhardt wrote:
> The base vfio has not much functionality but to provide a custom
> container by opening this path.
> See https://www.kernel.org/doc/Documentation/vfio.txt for more.
>
> Systems with static hostdevs will get /dev/vfio/vfio by virt-aa-hotplug
> right from the beginning. But if the guest initially had no hostdev at
> all it will run into the following deny before the security module
> labelling callbacks will make the actual vfio device (like /dev/vfio/93)
> known.
>
> Access by qemu is "wr" even thou in theory it could maybe be "r":

^this sentence is not necessary for the commit message and should be dropped.

> [ 2652.756712] audit: type=1400 audit(1491303691.719:25):
>   apparmor="DENIED" operation="open"
>   profile="libvirt-17a61b87-5132-497c-b928-421ac2ee0c8a"
>   name="/dev/vfio/vfio" pid=8486 comm="qemu-system-x86"
>   requested_mask="wr" denied_mask="wr" fsuid=64055 ouid=0
>
> Bug-Ubuntu: https://bugs.launchpad.net/bugs/1678322
> Bug-Ubuntu: https://bugs.launchpad.net/bugs/1775777
>
> Signed-off-by: Christian Ehrhardt <christian.ehrhardt@canonical.com>
> Signed-off-by: Stefan Bader <stefan.bader@canonical.com>
> ---
>  examples/apparmor/libvirt-qemu | 3 +++
>  1 file changed, 3 insertions(+)
>
> diff --git a/examples/apparmor/libvirt-qemu b/examples/apparmor/libvirt-qemu
> index 2c47652250..874aca2092 100644
> --- a/examples/apparmor/libvirt-qemu
> +++ b/examples/apparmor/libvirt-qemu
> @@ -193,6 +193,9 @@
>    deny /dev/shm/lttng-ust-wait-* r,
>    deny /run/shm/lttng-ust-wait-* r,
>
> +  # for vfio hotplug on systems without static vfio (LP: #1775777)
> +  /dev/vfio/vfio rw,

Per the kernel doc you linked in the commit message I think this is fine.

Reviewed-by: Erik Skultety <eskultet@redhat.com>