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(a)canonical.com>
Signed-off-by: Stefan Bader <stefan.bader(a)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(a)redhat.com>