Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Michael Ellerman <mpe@ellerman.id.au>
To:     Linus Torvalds <torvalds@linux-foundation.org>,
        Uros Bizjak <ubizjak@gmail.com>,
        Catalin Marinas <catalin.marinas@arm.com>,
        Will Deacon <will@kernel.org>,
        Russell King <linux@armlinux.org.uk>,
        Thomas Bogendoerfer <tsbogend@alpha.franken.de>,
        Heiko Carstens <hca@linux.ibm.com>
Cc:     the arch/x86 maintainers <x86@kernel.org>,
        Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
        Peter Zijlstra <peterz@infradead.org>,
        Thomas Gleixner <tglx@linutronix.de>, Waiman.Long@hp.com,
        Paul McKenney <paulmck@linux.vnet.ibm.com>,
        linuxppc-dev@lists.ozlabs.org
Subject: Re: [PATCH 1/2] locking/lockref: Use try_cmpxchg64 in CMPXCHG_LOOP
 macro
In-Reply-To: <CAHk-=wh1XeaxWXG5QziGA4ds918UnW1hO924kusgVB-wGj+9Og@mail.gmail.com>
Date:   Thu, 26 May 2022 22:14:59 +1000
Message-ID: <871qwgmqws.fsf@mpe.ellerman.id.au>
MIME-Version: 1.0
Content-Type: text/plain
Precedence: bulk

Linus Torvalds <torvalds@linux-foundation.org> writes:
> On Wed, May 25, 2022 at 7:40 AM Uros Bizjak <ubizjak@gmail.com> wrote:
>>
>> Use try_cmpxchg64 instead of cmpxchg64 in CMPXCHG_LOOP macro.
>> x86 CMPXCHG instruction returns success in ZF flag, so this
>> change saves a compare after cmpxchg (and related move instruction
>> in front of cmpxchg). The main loop of lockref_get improves from:
>
> Ack on this one regardless of the 32-bit x86 question.
>
> HOWEVER.
>
> I'd like other architectures to pipe up too, because I think right now
> x86 is the only one that implements that "arch_try_cmpxchg()" family
> of operations natively, and I think the generic fallback for when it
> is missing might be kind of nasty.
>
> Maybe it ends up generating ok code, but it's also possible that it
> just didn't matter when it was only used in one place in the
> scheduler.

This patch seems to generate slightly *better* code on powerpc.

I see one register-to-register move that gets shifted slightly later, so
that it's skipped on the path that returns directly via the SUCCESS
case.

So LGTM.

> The lockref_get() case can be quite hot under some loads, it would be
> sad if this made other architectures worse.

Do you know of a benchmark that shows it up? I tried a few things but
couldn't get lockref_get() to count for more than 1-2%.

cheers