x86 & generic: change to __builtin_prefetch()

gcc 3.2+ supports __builtin_prefetch, so it's possible to use it on all
architectures. Change the generic fallback in linux/prefetch.h to use it
instead of noping it out. gcc should do the right thing when the
architecture doesn't support prefetching

Undefine the x86-64 inline assembler version and use the fallback.

Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

include/asm-x86/processor_64.h

@@ -390,12 +390,6 @@ static inline void sync_core(void)
 	asm volatile("cpuid" : "=a" (tmp) : "0" (1) : "ebx","ecx","edx","memory");
 } 
 
-#define ARCH_HAS_PREFETCH
-static inline void prefetch(void *x) 
-{ 
-	asm volatile("prefetcht0 (%0)" :: "r" (x));
-} 
-
 #define ARCH_HAS_PREFETCHW 1
 static inline void prefetchw(void *x) 
 { 

include/linux/prefetch.h

@@ -34,17 +34,12 @@
 	
 */
 
-/*
- *	These cannot be do{}while(0) macros. See the mental gymnastics in
- *	the loop macro.
- */
- 
 #ifndef ARCH_HAS_PREFETCH
-static inline void prefetch(const void *x) {;}
+#define prefetch(x) __builtin_prefetch(x)
 #endif
 
 #ifndef ARCH_HAS_PREFETCHW
-static inline void prefetchw(const void *x) {;}
+#define prefetchw(x) __builtin_prefetch(x,1)
 #endif
 
 #ifndef ARCH_HAS_SPINLOCK_PREFETCH