[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <Y2jSMz4GtXGJk6rS@hirez.programming.kicks-ass.net>
Date: Mon, 7 Nov 2022 10:38:59 +0100
From: Peter Zijlstra <peterz@...radead.org>
To: Vincent Mailhol <mailhol.vincent@...adoo.fr>
Cc: x86@...nel.org, Ingo Molnar <mingo@...hat.com>,
Borislav Petkov <bp@...en8.de>,
Nick Desaulniers <ndesaulniers@...gle.com>,
Thomas Gleixner <tglx@...utronix.de>,
linux-kernel@...r.kernel.org, Yury Norov <yury.norov@...il.com>,
llvm@...ts.linux.dev, Borislav Petkov <bp@...e.de>
Subject: Re: [PATCH v1 1/2] x86/asm/bitops: Replace __fls() by its generic
builtin implementation
On Sun, Nov 06, 2022 at 06:51:05PM +0900, Vincent Mailhol wrote:
> The builtin implementation is better for two reasons:
>
> 1/ it saves two instructions on clang (a push and a stack pointer
> decrement) because of a useless tentative to save rax.
I'm thinking this is the same old clang-sucks-at-"rm" constraints and
*really* should not be a reason to change things. Clang should get fixed
already.
> 2/ when used on constant expressions, the compiler is only able to
> fold the builtin version (c.f. [2]).
>
> For those two reasons, replace the assembly implementation by its
> builtin counterpart.
>
> [1] https://elixir.bootlin.com/linux/v6.0/source/include/asm-generic/bitops/builtin-__fls.h
>
> [2] commit 146034fed6ee ("x86/asm/bitops: Use __builtin_ffs() to evaluate constant expressions")
I would much prefer consistently with 146034fed6ee.
Powered by blists - more mailing lists