[PATCH v1] x86: Fallback {str|wcs}cmp RTM in the ncmp overflow case [BZ #28896]

[Noah Goldstein]

On Tue, Feb 15, 2022 at 12:50 PM H.J. Lu <hjl.tools@gmail.com> wrote:
>
> On Tue, Feb 15, 2022 at 9:06 AM Noah Goldstein <goldstein.w.n@gmail.com> wrote:
> >
> > On Tue, Feb 15, 2022 at 11:00 AM H.J. Lu <hjl.tools@gmail.com> wrote:
> > >
> > > On Tue, Feb 15, 2022 at 8:51 AM Noah Goldstein <goldstein.w.n@gmail.com> wrote:
> > > >
> > > > On Tue, Feb 15, 2022 at 10:30 AM H.J. Lu <hjl.tools@gmail.com> wrote:
> > > > >
> > > > > On Tue, Feb 15, 2022 at 8:28 AM Noah Goldstein <goldstein.w.n@gmail.com> wrote:
> > > > > >
> > > > > > In the overflow fallback strncmp-avx2-rtm and wcsncmp-avx2-rtm would
> > > > > > call strcmp-avx2 and wcsncmp-avx2 respectively. This would have
> > > > > > not checks around vzeroupper and would trigger spurious
> > > > > > aborts. This commit fixes that.
> > > > >
> > > > > Include a testcase?
> > > > Added test case in V2. Don't have the hardware to check it though,
> > > > can you?
> > >
> > > Yes, I can.  Please V2 on a branch in gitlab.
> >
> > https://gitlab.com/x86-glibc/glibc/-/commits/users/goldsteinn/strncmp-rtm-test
>
> I updated your branch with some fixes in the testcase and the commit log.
> I tested it on an AVX2 machine with RTM.  The testcase fails without your
> fix.
>
> Please submit the v2 patch.

It's up.

>
> Thanks.
>
> --
> H.J.