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 <bigeasy@linutronix.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1322649814-544-1-git-send-email-bigeasy@linutronix.de
Signed-off-by: Ingo Molnar <mingo@elte.hu>

arch/x86/include/asm/div64.h

@@ -4,6 +4,7 @@
 #ifdef CONFIG_X86_32
 
 #include <linux/types.h>
+#include <linux/log2.h>
 
 /*
  * 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;							\
 })