Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::3:2 as permitted sender) client-ip=2620:137:e000::3:2;
MIME-Version: 1.0
References: <20231010164234.140750-1-ubizjak@gmail.com> <CAHk-=whYWhZN52SJN-Th9x2L2V-vHtAXUgiy_nSJ3+vQU6ak4Q@mail.gmail.com>
 <CAFULd4ZqH3FeG8_mjDvUAU9QiGB36wDu3MzUtadgAgoVuQ9QRg@mail.gmail.com>
 <CAHk-=wiALZxieQQmvv5sW15HYB_YwC3d_ma9sdp7Zb4Fb4uK2w@mail.gmail.com>
 <CAFULd4Y8NSArDqH=VMy8F97eNosUUGxrBMEyHH=MytjUBSCmjg@mail.gmail.com>
 <CAHk-=whMr8V_q3dq4iS0dpx4Nssu+aYWz+mA36p2ykA+OXTjXA@mail.gmail.com>
 <CAFULd4afyYK0-wAOo3oJDapX0iyu86m5+vVn9c35gk8fd6iwRQ@mail.gmail.com> <CAHk-=wiLyA0g3BvQ_nsF2PWi-FDtcNS5+4-ai1FX-xFzTBeTzg@mail.gmail.com>
In-Reply-To: <CAHk-=wiLyA0g3BvQ_nsF2PWi-FDtcNS5+4-ai1FX-xFzTBeTzg@mail.gmail.com>
From:   Uros Bizjak <ubizjak@gmail.com>
Date:   Wed, 11 Oct 2023 22:00:42 +0200
Message-ID: <CAFULd4ZSorEEkUZOobAyDzkyG+DujEoUOGiMPuiqd9V3C-a39w@mail.gmail.com>
Subject: Re: [PATCH v2 -tip] x86/percpu: Use C for arch_raw_cpu_ptr()
To:     Linus Torvalds <torvalds@linux-foundation.org>
Cc:     x86@kernel.org, linux-kernel@vger.kernel.org,
        Nadav Amit <namit@vmware.com>,
        Andy Lutomirski <luto@kernel.org>,
        Brian Gerst <brgerst@gmail.com>,
        Denys Vlasenko <dvlasenk@redhat.com>,
        "H . Peter Anvin" <hpa@zytor.com>,
        Peter Zijlstra <peterz@infradead.org>,
        Thomas Gleixner <tglx@linutronix.de>,
        Josh Poimboeuf <jpoimboe@redhat.com>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
Precedence: bulk

On Wed, Oct 11, 2023 at 9:52=E2=80=AFPM Linus Torvalds
<torvalds@linux-foundation.org> wrote:
>
> On Wed, 11 Oct 2023 at 11:42, Uros Bizjak <ubizjak@gmail.com> wrote:
> >
> > The attached patch was tested on a target with fsgsbase CPUID and
> > without it. It works!
>
> .. I should clearly read all my emails before answering some of them.
>
> Yes, that patch looks good to me, and I'm happy to hear that you
> actually tested it unlike my "maybe something like this".
>
> > The patch improves amd_pmu_enable_virt() in the same way as reported
> > in the original patch submission and also reduces the number of percpu
> > offset reads (either from this_cpu_off or with rdgsbase) from 1663 to
> > 1571.
>
> Dio y ou have any actka performance numbers? The patch looks good to
> me, and I *think* rdgsbase ends up being faster in practice due to
> avoiding a memory access, but that's very much a gut feel.

Unfortunately, I don't have any perf numbers, only those from Agner's
instruction tables. The memory access performance has so many
parameters, that gut feeling is the only thing besides real
case-by-case measurements. The rule of thumb in the compiler world is
also that memory access should be avoided.

Uros.

>
> > The only drawback is a larger binary size:
> >
> >   text    data     bss     dec     hex filename
> > 25546594        4387686  808452 30742732        1d518cc vmlinux-new.o
> > 25515256        4387814  808452 30711522        1d49ee2 vmlinux-old.o
> >
> > that increases by 31k (0.123%), probably due to 1578 rdgsbase alternati=
ves.
>
> I'm actually surprised that it increases the text size. The 'rdgsbase'
> instruction should be smaller than a 'mov %gs', so I would have
> expected the *data* size to increase due to the alternatives tables,
> but not the text size.
>
> [ Looks around ]
>
> Oh. It's because we put the altinstructions into the text section.
> That's kind of silly, but whatever.
>
> So I think that increase in text-size is not "real" - yes, it
> increases our binary size because we obviously have two instructions,
> but the actual *executable* part likely stays the same, and it's just
> that we grow the altinstruction metadata.
>
>                   Linus