Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: quoted-printable
From:   Andy Lutomirski <luto@amacapital.net>
Mime-Version: 1.0 (1.0)
Subject: Re: [PATCH v4 14/18] static_call: Add static_cond_call()
Date:   Wed, 6 May 2020 12:57:02 -0700
Message-Id: <88AE3649-C2E6-4965-86B5-C8FE9D226293@amacapital.net>
References: <CAHk-=wjdLY-E3m21_QcHUauakW3qAAOCe2rxzuFEm-Af_oqG0g@mail.gmail.com>
Cc:     Peter Zijlstra <peterz@infradead.org>,
        Nick Desaulniers <ndesaulniers@google.com>,
        Rasmus Villemoes <linux@rasmusvillemoes.dk>,
        "maintainer:X86 ARCHITECTURE (32-BIT AND 64-BIT)" <x86@kernel.org>,
        LKML <linux-kernel@vger.kernel.org>,
        Steven Rostedt <rostedt@goodmis.org>,
        Masami Hiramatsu <mhiramat@kernel.org>,
        Daniel Bristot de Oliveira <bristot@redhat.com>,
        Jason Baron <jbaron@akamai.com>,
        Thomas Gleixner <tglx@linutronix.de>,
        Ingo Molnar <mingo@kernel.org>, Nadav Amit <namit@vmware.com>,
        "H. Peter Anvin" <hpa@zytor.com>,
        Andy Lutomirski <luto@kernel.org>,
        Ard Biesheuvel <ard.biesheuvel@linaro.org>,
        Josh Poimboeuf <jpoimboe@redhat.com>,
        Paolo Bonzini <pbonzini@redhat.com>,
        Mathieu Desnoyers <mathieu.desnoyers@efficios.com>,
        "H.J. Lu" <hjl.tools@gmail.com>,
        clang-built-linux <clang-built-linux@googlegroups.com>
In-Reply-To: <CAHk-=wjdLY-E3m21_QcHUauakW3qAAOCe2rxzuFEm-Af_oqG0g@mail.gmail.com>
To:     Linus Torvalds <torvalds@linux-foundation.org>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk


> On May 6, 2020, at 10:23 AM, Linus Torvalds <torvalds@linux-foundation.org=
> wrote:
>=20
> =EF=BB=BFOn Wed, May 6, 2020 at 6:51 AM Peter Zijlstra <peterz@infradead.o=
rg> wrote:
>>=20
>> I was hoping for:
>>=20
>>        bar:                                    # @bar
>>                movl    %edi, .L_x$local(%rip)
>>                retq
>>        ponies:                                 # @ponies
>>                movq    .Lfoo$local(%rip), %rax
>>                testq   %rax, %rax
>>                jz      1f
>>                jmpq    *%rcx                   # TAILCALL
>>        1:
>>                retq
>=20
> If you want to just avoid the 'cmov', the best way to do that is to
> insert a barrier() on one side of the if-statement.
>=20
> That breaks the ability to turn the conditional jump into a cmov.

Having done this in the past, you can get potentially better code with asm v=
olatile (=E2=80=9C=E2=80=9D); than with a barrier and its memory clobber. I d=
on=E2=80=99t know if that will make a difference in this particular case.=