From nobody Wed Apr 8 14:09:02 2026 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id AA0BAC6FA82 for ; Mon, 5 Sep 2022 00:38:25 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S232053AbiIEAiX (ORCPT ); Sun, 4 Sep 2022 20:38:23 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:44970 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S231686AbiIEAiS (ORCPT ); Sun, 4 Sep 2022 20:38:18 -0400 Received: from smtp.smtpout.orange.fr (smtp-28.smtpout.orange.fr [80.12.242.28]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id D90BD26AE3 for ; Sun, 4 Sep 2022 17:38:14 -0700 (PDT) Received: from YC20090004.ad.ts.tri-ad.global ([103.175.111.222]) by smtp.orange.fr with ESMTPA id V07SoNhIZJ83FV07qovIPN; Mon, 05 Sep 2022 02:38:12 +0200 X-ME-Helo: YC20090004.ad.ts.tri-ad.global X-ME-Auth: bWFpbGhvbC52aW5jZW50QHdhbmFkb28uZnI= X-ME-Date: Mon, 05 Sep 2022 02:38:12 +0200 X-ME-IP: 103.175.111.222 From: Vincent Mailhol To: Borislav Petkov Cc: Nick Desaulniers , Thomas Gleixner , Ingo Molnar , x86@kernel.org, Peter Zijlstra , Dave Hansen , "H . Peter Anvin" , Nathan Chancellor , Tom Rix , linux-kernel@vger.kernel.org, llvm@lists.linux.dev, David Howells , Jan Beulich , Christophe Jaillet , Joe Perches , Josh Poimboeuf , Yury Norov , Vincent Mailhol Subject: [PATCH v7 2/2] x86/asm/bitops: __ffs,ffz: use __builtin_ctzl to evaluate constant expressions Date: Mon, 5 Sep 2022 09:37:32 +0900 Message-Id: <20220905003732.752-3-mailhol.vincent@wanadoo.fr> X-Mailer: git-send-email 2.35.1 In-Reply-To: <20220905003732.752-1-mailhol.vincent@wanadoo.fr> References: <20220511160319.1045812-1-mailhol.vincent@wanadoo.fr> <20220905003732.752-1-mailhol.vincent@wanadoo.fr> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" __ffs(x) is equivalent to (unsigned long)__builtin_ctzl(x) and ffz(x) is equivalent to (unsigned long)__builtin_ctzl(~x). Because __builting_ctzl() returns an int, a cast to (unsigned long) is necessary to avoid potential warnings on implicit casts. For x86_64, the current __ffs() and ffz() implementations do not produce optimized code when called with a constant expression. On the contrary, the __builtin_ctzl() folds into a single instruction. However, for non constant expressions, the __ffs() and ffz() asm versions of the kernel remains slightly better than the code produced by GCC (it produces a useless instruction to clear eax). Use __builtin_constant_p() to select between the kernel's __ffs()/ffz() and the __builtin_ctzl() depending on whether the argument is constant or not. ** Statistics ** On a allyesconfig, before...: $ objdump -d vmlinux.o | grep tzcnt | wc -l 3607 ...and after: $ objdump -d vmlinux.o | grep tzcnt | wc -l 2600 So, roughly 27.9% of the calls to either __ffs() or ffz() were using constant expressions and could be optimized out. (tests done on linux v5.18-rc5 x86_64 using GCC 11.2.1) Note: on x86_64, the asm bsf instruction produces tzcnt when used with the ret prefix (which explain the use of `grep tzcnt' instead of `grep bsf' in above benchmark). c.f. [1] [1] commit e26a44a2d618 ("x86: Use REP BSF unconditionally") Link: http://lkml.kernel.org/r/5058741E020000780009C014@nat28.tlf.novell.com Reviewed-by: Nick Desaulniers Reviewed-by: Yury Norov Signed-off-by: Vincent Mailhol --- arch/x86/include/asm/bitops.h | 38 ++++++++++++++++++++++------------- 1 file changed, 24 insertions(+), 14 deletions(-) diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index 879238e5a6a0..08eca2938f27 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -247,13 +247,7 @@ arch_test_bit_acquire(unsigned long nr, const volatile= unsigned long *addr) variable_test_bit(nr, addr); } =20 -/** - * __ffs - find first set bit in word - * @word: The word to search - * - * Undefined if no bit exists, so code should check against 0 first. - */ -static __always_inline unsigned long __ffs(unsigned long word) +static __always_inline unsigned long variable__ffs(unsigned long word) { asm("rep; bsf %1,%0" : "=3Dr" (word) @@ -261,13 +255,18 @@ static __always_inline unsigned long __ffs(unsigned l= ong word) return word; } =20 -/** - * ffz - find first zero bit in word - * @word: The word to search - * - * Undefined if no zero exists, so code should check against ~0UL first. - */ -static __always_inline unsigned long ffz(unsigned long word) +/** + * __ffs - find first set bit in word + * @word: The word to search + * + * Undefined if no bit exists, so code should check against 0 first. + */ +#define __ffs(word) \ + (__builtin_constant_p(word) ? \ + (unsigned long)__builtin_ctzl(word) : \ + variable__ffs(word)) + +static __always_inline unsigned long variable_ffz(unsigned long word) { asm("rep; bsf %1,%0" : "=3Dr" (word) @@ -275,6 +274,17 @@ static __always_inline unsigned long ffz(unsigned long= word) return word; } =20 +/** + * ffz - find first zero bit in word + * @word: The word to search + * + * Undefined if no zero exists, so code should check against ~0UL first. + */ +#define ffz(word) \ + (__builtin_constant_p(word) ? \ + (unsigned long)__builtin_ctzl(~word) : \ + variable_ffz(word)) + /* * __fls: find last set bit in word * @word: The word to search --=20 2.35.1