Re: [PATCH] x86: Optimize variable_test_bit()

[Peter Zijlstra <peterz@infradead.org>]

On Fri, May 01, 2015 at 05:16:30PM +0200, Peter Zijlstra wrote:

> diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
> index cfe3b954d5e4..bcf4fa77c04f 100644
> --- a/arch/x86/include/asm/bitops.h
> +++ b/arch/x86/include/asm/bitops.h
> @@ -313,6 +313,15 @@ static __always_inline int constant_test_bit(long nr, const volatile unsigned lo
>  
>  static inline int variable_test_bit(long nr, volatile const unsigned long *addr)
>  {
> +#ifdef CC_HAVE_ASM_GOTO
> +	asm_volatile_goto ("bt %1, %0\n\t"
> +			   "jc %l[cc_label]"
> +			   : : "m" (*(unsigned long *)addr), "Ir" (nr)
> +			   : : cc_label);
> +	return 0;
> +cc_label:
> +	return 1;
> +#else

I figured I'd try both jc and jnc versions:

   text           data     bss     dec            hex   filename
12203914        1738112 1081344 15023370         e53d0a defconfig-build/vmlinux
12204228        1738112 1081344 15023684         e53e44 defconfig-build/vmlinux-jc
12203240        1738112 1081344 15022696         e53a68 defconfig-build/vmlinux-jnc

Clearly I picked the wrong one :-) It also shows there is real value in
exposing this decision to GCC.