x86: atomic64: Improve cmpxchg8b()

Rewrite cmpxchg8b() to not use %edi register but a generic "+m"
constraint, to increase compiler freedom in code generation and
possibly better code.

Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Arnd Bergmann <arnd@arndb.de>
LKML-Reference: <alpine.LFD.2.01.0907021653030.3210@localhost.localdomain>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

arch/x86/lib/atomic64_32.c

@@ -6,19 +6,14 @@
 
 static inline u64 cmpxchg8b(u64 *ptr, u64 old, u64 new)
 {
-	asm volatile(
-
-		LOCK_PREFIX "cmpxchg8b (%[ptr])\n"
-
-		     :		"=A" (old)
-
-		     : [ptr]	"D" (ptr),
-				"A" (old),
-				"b" (ll_low(new)),
-				"c" (ll_high(new))
-
-		     : "memory");
+	u32 low = new;
+	u32 high = new >> 32;
 
+	asm volatile(
+		LOCK_PREFIX "cmpxchg8b %1\n"
+		     : "+A" (old), "+m" (*ptr)
+		     :  "b" (low),  "c" (high)
+		     );
 	return old;
 }