On Wed, Jun 12, 2019 at 3:37 AM Ondrej Mosnacek <omosnace(a)redhat.com> wrote:
On Wed, Jun 12, 2019 at 12:56 AM Paul Moore
<paul(a)paul-moore.com> wrote:
> On Tue, Jun 11, 2019 at 4:07 AM Ondrej Mosnacek <omosnace(a)redhat.com> wrote:
> > These strings may come from untrusted sources (e.g. file xattrs) so they
> > need to be properly escaped.
> >
> > Reproducer:
> > # setenforce 0
> > # touch /tmp/test
> > # setfattr -n security.selinux -v 'kuřecí řízek' /tmp/test
> > # runcon system_u:system_r:sshd_t:s0 cat /tmp/test
> > (look at the generated AVCs)
> >
> > Actual result:
> > type=AVC [...] trawcon=kuřecí řízek
> >
> > Expected result:
> > type=AVC [...] trawcon=6B75C5996563C3AD20C599C3AD7A656B
> >
> > Fixes: fede148324c3 ("selinux: log invalid contexts in AVCs")
> > Cc: stable(a)vger.kernel.org # v5.1+
> > Signed-off-by: Ondrej Mosnacek <omosnace(a)redhat.com>
> > ---
> > security/selinux/avc.c | 10 ++++++++--
> > 1 file changed, 8 insertions(+), 2 deletions(-)
>
> Thanks, the patch looks fine to me, but it is borderline -stable
> material in my opinion. I'll add it to the stable-5.2 branch, but in
> the future I would prefer if you left the stable marking off patches
> and sent a reply discussing *why* this should go to stable so we can
> discuss it. I realize Greg likes to pull a lot of stuff into stable,
> but I try to be a bit more conservative about what gets marked. Even
> the simplest fix can still break things :)
OK, I was a bit unsure whether to mark it as stable or not and
eventually inclined to do so... I'll try be more careful about it in
the future.
If it makes you feel better, it's not that big of a deal, I just felt
it was worth mentioning since we've been doing a bit of a "best
practices for submitting SELinux kernel patches" on the mailing list
lately and I felt this was worth mentioning. The basic idea is that I
think marking something for stable shouldn't be taken lightly and it
is worth a discussion, even if it is short.
--
paul moore
www.paul-moore.com