From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mail-yb1-f179.google.com (mail-yb1-f179.google.com [209.85.219.179]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 063993218 for ; Wed, 11 May 2022 23:24:10 +0000 (UTC) Received: by mail-yb1-f179.google.com with SMTP id r1so6759221ybo.7 for ; Wed, 11 May 2022 16:24:10 -0700 (PDT) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=x-gm-message-state:mime-version:references:in-reply-to:from:date :message-id:subject:to:cc; bh=oy3Pm5sCLuohvb8vkD/fkUbAx0+U5niUi5E5iwOTC80=; b=JRxSBCm0nXXJHaBWqxbiMHeKZAexYeIo9T9MW7BYFLF5Fm7zGTTU8ugcnXSrY0OXlG TxkADkurVdAVqqsfJIZjzvHGuM6nX5PV53Z1h5dGekkDBYYx1fgSz4aiq/++cZHDjARR CmAO4Zl6/oVSCzGUdkuMG+it+NnwB76hAw82A39h/6KaZBNJNAoG0aEXt2M0+Ju3R2nn aoOkYZCDZYmxAxtTvK1R6fhAVAE1OhuCsai2VkbwsR/96v/8nNj0sjhdcwQ5hX92wK0X 4FsR6Xg7+MKNc9pLn7tByODyq2pzyZR5dkCBW55ooV9dvHBv05TPFzYD4rwu1h6Xd1/w WD/g== X-Gm-Message-State: AOAM530FEX2104cyXM8tJ32XhGThVSQpUFP1vA8Av7jFgFSS328msU8o ZTXG+9Vj9tYAFT0Nf3GjFdN+26TQxSZeRnx4g/A= X-Google-Smtp-Source: ABdhPJyVDRbFRlLmXJHpnwBSAwDxCMiSkisNBqSmSTztcJmphl3CHpb5Ya+K6Txjjw+vGr104VZX3qvLzgIdCyttuZ4= X-Received: by 2002:a25:cb4b:0:b0:645:d702:eb15 with SMTP id b72-20020a25cb4b000000b00645d702eb15mr24152368ybg.500.1652311449899; Wed, 11 May 2022 16:24:09 -0700 (PDT) Precedence: bulk X-Mailing-List: llvm@lists.linux.dev List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 References: <20220511160319.1045812-1-mailhol.vincent@wanadoo.fr> <20220511160319.1045812-3-mailhol.vincent@wanadoo.fr> In-Reply-To: From: Vincent MAILHOL Date: Thu, 12 May 2022 08:23:58 +0900 Message-ID: Subject: Re: [PATCH v2 2/2] x86/asm/bitops: __ffs,ffz: use __builtin_ctzl to evaluate constant expressions To: Nick Desaulniers Cc: Thomas Gleixner , Ingo Molnar , Borislav Petkov , Dave Hansen , x86@kernel.org, "H . Peter Anvin" , Nathan Chancellor , Tom Rix , linux-kernel@vger.kernel.org, llvm@lists.linux.dev, David Howells , Jan Beulich Content-Type: text/plain; charset="UTF-8" On Thu. 12 May 2022 at 07:20, Nick Desaulniers wrote: > On Wed, May 11, 2022 at 9:04 AM Vincent Mailhol > wrote: > > > > __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() gets simplified 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). > > > > This patch uses the __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 applying this patch...: > > > > | $ 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 call to either __ffs() or ffz() were using > > constant expression and were 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 is why we grep tzcnt instead of bsf in above > > benchmark). c.f. [1] > > > > [1] commit e26a44a2d618 ("x86: Use REP BSF unconditionally") > > http://lkml.kernel.org/r/5058741E020000780009C014@nat28.tlf.novell.com > > > > CC: Nick Desaulniers > > Signed-off-by: Vincent Mailhol > > Patch LGTM, though I find the location of the double unscores in the > names slightly against my taste. > > > --- > > 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 6ed979547086..7cf5374ce403 100644 > > --- a/arch/x86/include/asm/bitops.h > > +++ b/arch/x86/include/asm/bitops.h > > @@ -224,13 +224,7 @@ static __always_inline bool variable_test_bit(long nr, volatile const unsigned l > > ? constant_test_bit((nr), (addr)) \ > > : variable_test_bit((nr), (addr))) > > > > -/** > > - * __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) > > How about `variable___ffs`? Patch 1/2 used `variable_ffs` for `ffs`? On a first glance, having the triple underscores in the middle of the name seemed odd. On second thought, it is more consistent with the rest, and I finally like the idea. Will be adopted in v3. > > { > > asm("rep; bsf %1,%0" > > : "=r" (word) > > @@ -238,13 +232,18 @@ static __always_inline unsigned long __ffs(unsigned long word) > > return word; > > } > > > > -/** > > - * 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) > > `ffz` had no underscore. Regardless of `__ffs`, this should definitely > be `variable_ffz` IMO. ACK. > > { > > asm("rep; bsf %1,%0" > > : "=r" (word) > > @@ -252,6 +251,17 @@ static __always_inline unsigned long ffz(unsigned long word) > > return word; > > } > > > > +/** > > + * 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 > > -- > > 2.35.1 > > > > > -- > Thanks, > ~Nick Desaulniers