Re: [PATCH v2 1/2] x86/asm/bitops: ffs: use __builtin_ffs to evaluate constant expressions

From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
To: Vincent Mailhol <mailhol.vincent@wanadoo.fr>,
	Nick Desaulniers <ndesaulniers@google.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>,
	x86@kernel.org, "H . Peter Anvin" <hpa@zytor.com>,
	Nathan Chancellor <nathan@kernel.org>, Tom Rix <trix@redhat.com>,
	linux-kernel@vger.kernel.org, llvm@lists.linux.dev,
	David Howells <dhowells@redhat.com>,
	Jan Beulich <JBeulich@suse.com>
Subject: Re: [PATCH v2 1/2] x86/asm/bitops: ffs: use __builtin_ffs to evaluate constant expressions
Date: Wed, 11 May 2022 22:56:15 +0200	[thread overview]
Message-ID: <324f245e-15e2-a1f2-bc8a-46255a1a859f@wanadoo.fr> (raw)
In-Reply-To: <20220511160319.1045812-2-mailhol.vincent@wanadoo.fr>

Le 11/05/2022 à 18:03, Vincent Mailhol a écrit :
> For x86_64, the current ffs() implementation does not produce
> optimized code when called with a constant expression. On the
> contrary, the __builtin_ffs() function of both GCC and clang is able
> to simplify the expression into a single instruction.
> 

[...]

> 
> ** Statistics **
> 
> On a allyesconfig, before applying this patch...:
> 
> | $ objdump -d vmlinux.o | grep bsf | wc -l
> | 3607
> 
> ...and after:
> 
> | $ objdump -d vmlinux.o | grep bsf | wc -l
> | 792
> 
> So, roughly 26.7% of the call to ffs() were using constant expression
> and were optimized out.
> 
> 
nitpicking: numbers look odd.
    3607 is the exact same number as in patch 2/2. (ok, could be)
    26.7% is surprising with these numbers. (I guess it is (total_before 
- remaining) / total_before x 100 = (3607-792)/36.07 = 78.0%)

(but patch looks great to me :)

CJ