From 668b44846606185a9bed5a5357bc2cb132e00dd7 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 30 Nov 2011 11:43:34 +0100 Subject: [PATCH] x86/div64: Add a micro-optimization shortcut if base is power of two In the target code I have a do_div(x, PAGE_SIZE). The x86-64 version of it was doing a shift and a mask which is clever. The 32bit version of it had a div operation in it which made me think. After digging I noticed that x86 has an optimized version of it. This patch adds this shift and mask optimization if base is constant so we don't have any runtime "checking" overhead since most users use a power of ten. Signed-off-by: Sebastian Andrzej Siewior Cc: Linus Torvalds Link: http://lkml.kernel.org/r/1322649814-544-1-git-send-email-bigeasy@linutronix.de Signed-off-by: Ingo Molnar --- arch/x86/include/asm/div64.h | 22 ++++++++++++++-------- 1 file changed, 14 insertions(+), 8 deletions(-) diff --git a/arch/x86/include/asm/div64.h b/arch/x86/include/asm/div64.h index 9a2d644c08ef..ced283ac79df 100644 --- a/arch/x86/include/asm/div64.h +++ b/arch/x86/include/asm/div64.h @@ -4,6 +4,7 @@ #ifdef CONFIG_X86_32 #include +#include /* * do_div() is NOT a C function. It wants to return @@ -21,15 +22,20 @@ ({ \ unsigned long __upper, __low, __high, __mod, __base; \ __base = (base); \ - asm("":"=a" (__low), "=d" (__high) : "A" (n)); \ - __upper = __high; \ - if (__high) { \ - __upper = __high % (__base); \ - __high = __high / (__base); \ + if (__builtin_constant_p(__base) && is_power_of_2(__base)) { \ + __mod = n & (__base - 1); \ + n >>= ilog2(__base); \ + } else { \ + asm("" : "=a" (__low), "=d" (__high) : "A" (n));\ + __upper = __high; \ + if (__high) { \ + __upper = __high % (__base); \ + __high = __high / (__base); \ + } \ + asm("divl %2" : "=a" (__low), "=d" (__mod) \ + : "rm" (__base), "0" (__low), "1" (__upper)); \ + asm("" : "=A" (n) : "a" (__low), "d" (__high)); \ } \ - asm("divl %2":"=a" (__low), "=d" (__mod) \ - : "rm" (__base), "0" (__low), "1" (__upper)); \ - asm("":"=A" (n) : "a" (__low), "d" (__high)); \ __mod; \ }) -- 2.39.5