On Thu, 27 Jul 2017 15:40:33 +0200
Halil Pasic <pa...@linux.vnet.ibm.com> wrote:
> [Re-posting my previous reply because I've accidentally
> dropped almost all addressees.]
>
> On 07/27/2017 10:01 AM, Cornelia Huck wrote:
> > On Wed, 26 Jul 2017 00:44:42 +0200
> > Halil Pasic <pa...@linux.vnet.ibm.com> wrote:
> >
> >> According to the PoP bit positions 0-3 and 8-32 of the format-1 CCW must
> >> contain zeros. Bits 0-3 are already covered by cmd_code validity
> >> checking, and bit 32 is covered by the CCW address checking.
> >>
> >> Bits 8-31 correspond to CCW1.flags and CCW1.count. Currently we only
> >> check for the absence of certain flags. Let's fix this.
> >>
> >> Signed-off-by: Halil Pasic <pa...@linux.vnet.ibm.com>
> >> ---
> >> hw/s390x/css.c | 3 ++-
> >> 1 file changed, 2 insertions(+), 1 deletion(-)
> >>
> >> diff --git a/hw/s390x/css.c b/hw/s390x/css.c
> >> index d17e21b7af..1f04ce4a1b 100644
> >> --- a/hw/s390x/css.c
> >> +++ b/hw/s390x/css.c
> >> @@ -884,7 +884,8 @@ static int css_interpret_ccw(SubchDev *sch, hwaddr
> >> ccw_addr,
> >> ret = -EINVAL;
> >> break;
> >> }
> >> - if (ccw.flags & (CCW_FLAG_CC | CCW_FLAG_DC)) {
> >> + if (ccw.flags || ccw.count) {
> >> + /* We have already sanitized these if fmt 0. */
> >
> > I'd tweak that to
> >
> > /* We have already sanitized these if converted from fmt 0. */
> >
>
> Fine with me.
>
> > Seems less confusing.
> >
> >> ret = -EINVAL;
> >> break;
> >> }
> >
> > I'm inclined to pick this as a 2.10 bugfix. Patch 1 still needs work
> > from what I've seen.
> >
>
> Hm. The commit message becomes inaccurate if this goes in before
> patch 1. We still have must be zero bits which should be handled
> by the address (ccw.cda) checking. I think I can fix patch 1 today.
>
It's probably a bit much for now.
Can you rather suggest a better commit message?
