Received-SPF: pass (google.com: domain of linux-kernel+bounces-137342-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45e3:2400::1 as permitted sender) client-ip=2604:1380:45e3:2400::1;
Precedence: bulk
MIME-Version: 1.0
References: <20240409100503.274629-1-ubizjak@gmail.com> <20240409100503.274629-3-ubizjak@gmail.com>
 <ZhUixk5I_n53dbBb@FVFF77S0Q05N> <CAFULd4bBmQ85UsPOOEA+5dj-_JOBNWeyM-jipM7Zov2V484quQ@mail.gmail.com>
 <CAFULd4Z8JTc_5p8apO680es0fYO5ke9yYPpPUfp=15XrRbKESQ@mail.gmail.com> <ZhVuG4J7aocGvd0-@FVFF77S0Q05N.cambridge.arm.com>
In-Reply-To: <ZhVuG4J7aocGvd0-@FVFF77S0Q05N.cambridge.arm.com>
From: Uros Bizjak <ubizjak@gmail.com>
Date: Tue, 9 Apr 2024 18:53:30 +0200
Message-ID: <CAFULd4YM3ukFUst5ofMP8oz2gw8Spo_9A8UrAKHw_-dSyAwS7w@mail.gmail.com>
Subject: Re: [PATCH 2/6] locking/atomic/x86: Rewrite x86_32
 arch_atomic64_{,fetch}_{and,or,xor}() functions
To: Mark Rutland <mark.rutland@arm.com>
Cc: x86@kernel.org, linux-kernel@vger.kernel.org, 
	Thomas Gleixner <tglx@linutronix.de>, Ingo Molnar <mingo@kernel.org>, Borislav Petkov <bp@alien8.de>, 
	Dave Hansen <dave.hansen@linux.intel.com>, "H. Peter Anvin" <hpa@zytor.com>, 
	Peter Zijlstra <peterz@infradead.org>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

On Tue, Apr 9, 2024 at 6:34=E2=80=AFPM Mark Rutland <mark.rutland@arm.com> =
wrote:

> > Something like this:
> >
> > --cut here--
> > /*
> >  * This function is intended to preload the value from atomic64_t
> >  * location in a non-atomic way. The read might be torn, but can
> >  * safely be consumed by the compare-and-swap loop.
> >  */
> > static __always_inline s64 arch_atomic64_read_tearable(atomic64_t *v)
> > {
> >     /*
> >      * See the comment in arch_atomic_read() on why we use
> >      * __READ_ONCE() instead of READ_ONCE_NOCHECK() here.
> >      */
> >     return __READ_ONCE(v->counter);
> > }
> > --cut here--
>
> Yeah, something of that shape.
>
> Having thought for a bit longer, it's probably better to use '_torn' rath=
er
> than '_tearable' (i.e. name this arch_atomic64_read_torn()).

How about we simply name the function

arch_atomic64_read_nonatomic()

in the sense that it reads atomic64_t variables in a non-atomic way?

Uros.