Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
MIME-Version: 1.0
References: <20190729202542.205309-1-ndesaulniers@google.com>
 <20190729203246.GA117371@archlinux-threadripper> <CAKwvOdm7GRBWYhPy4Ni2jbsXJp8gDF-AqaAxeLbZ03+LvHxADQ@mail.gmail.com>
 <20190729204755.GA118622@archlinux-threadripper>
In-Reply-To: <20190729204755.GA118622@archlinux-threadripper>
From:   Nick Desaulniers <ndesaulniers@google.com>
Date:   Mon, 29 Jul 2019 13:49:11 -0700
Message-ID: <CAKwvOdk13rU=Fyb0BUFCL4ZYATxTNS3YG52ziPcqixfg4r7=gQ@mail.gmail.com>
Subject: Re: [PATCH] powerpc: workaround clang codegen bug in dcbz
To:     Nathan Chancellor <natechancellor@gmail.com>
Cc:     Michael Ellerman <mpe@ellerman.id.au>,
        Christophe Leroy <christophe.leroy@c-s.fr>,
        Segher Boessenkool <segher@kernel.crashing.org>,
        Arnd Bergmann <arnd@arndb.de>,
        kbuild test robot <lkp@intel.com>,
        Benjamin Herrenschmidt <benh@kernel.crashing.org>,
        Paul Mackerras <paulus@samba.org>,
        linuxppc-dev@lists.ozlabs.org, LKML <linux-kernel@vger.kernel.org>,
        clang-built-linux <clang-built-linux@googlegroups.com>
Content-Type: text/plain; charset="UTF-8"
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Mon, Jul 29, 2019 at 1:47 PM Nathan Chancellor
<natechancellor@gmail.com> wrote:
>
> On Mon, Jul 29, 2019 at 01:45:35PM -0700, Nick Desaulniers wrote:
> > On Mon, Jul 29, 2019 at 1:32 PM Nathan Chancellor
> > <natechancellor@gmail.com> wrote:
> > >
> > > On Mon, Jul 29, 2019 at 01:25:41PM -0700, Nick Desaulniers wrote:
> > > > But I'm not sure how the inlined code generated would be affected.
> > >
> > > For the record:
> > >
> > > https://godbolt.org/z/z57VU7
> > >
> > > This seems consistent with what Michael found so I don't think a revert
> > > is entirely unreasonable.
> >
> > Thanks for debugging/reporting/testing and the Godbolt link which
> > clearly shows that the codegen for out of line versions is no
> > different.  The case I can't comment on is what happens when those
> > `static inline` functions get inlined (maybe the original patch
> > improves those cases?).
> > --
> > Thanks,
> > ~Nick Desaulniers
>
> I'll try to build with various versions of GCC and compare the
> disassembly of the one problematic location that I found and see
> what it looks like.

Also, guess I should have included the tag:
Fixes: 6c5875843b87 ("powerpc: slightly improve cache helpers")
-- 
Thanks,
~Nick Desaulniers