Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::3:4 as permitted sender) client-ip=2620:137:e000::3:4;
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>
 <F48A9D34-3627-4372-B555-B58CBFC3F241@vmware.com> <CAHk-=wjF4gzCZKh-zN-sY0WpX1kCo+s9gYE9sOcSv0QieH1dwQ@mail.gmail.com>
 <CAFULd4bmOa7G2dXd_mu4J=_bsEs+TbxH691tYx9QQBwJPAma9w@mail.gmail.com>
In-Reply-To: <CAFULd4bmOa7G2dXd_mu4J=_bsEs+TbxH691tYx9QQBwJPAma9w@mail.gmail.com>
From:   Linus Torvalds <torvalds@linux-foundation.org>
Date:   Wed, 11 Oct 2023 14:54:45 -0700
Message-ID: <CAHk-=wj2Co_g3RQ=JkDZC7PYbRqDPq7mePQ0=eYhhtpEgqJD0w@mail.gmail.com>
Subject: Re: [PATCH v2 -tip] x86/percpu: Use C for arch_raw_cpu_ptr()
To:     Uros Bizjak <ubizjak@gmail.com>
Cc:     Nadav Amit <namit@vmware.com>,
        "the arch/x86 maintainers" <x86@kernel.org>,
        Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
        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"
Precedence: bulk

On Wed, 11 Oct 2023 at 14:33, Uros Bizjak <ubizjak@gmail.com> wrote:
>
> Reading the above, it looks to me that we don't want to play games
> with "const aliased" versions of current_task [1], as proposed by
> Nadav in his patch series.

Well, maybe I'd like it if I saw what the effect of it was, but that
patch mentions "sync_mm_rss()" which doesn't actually exist
(SPLIT_RSS_COUNTING is never defined, the split version is gone and
hasn't existed since commit f1a7941243c1 "mm: convert mm's rss stats
into percpu_counter")

I'm not sure why gcc used to get code generation wrong there, and I
don't see what could be improved in the current implementation of
'current_task', but I guess there could be things that could be done
to make gcc more likely to CSE the cases..

IOW, I don't understand why Navad's patch would improve gcc code gen.
It presumably depends on some gcc internal issue (ie "gcc just happens
to be better at optimization X").

Which is obviously a valid thing in general.

              Linus