host-utils: Use __int128_t for mul[us]64

Replace some x86_64 specific inline assembly with something that
all 64-bit hosts ought to optimize well.  At worst this becomes
a call to the gcc __multi3 routine, which is no worse than our
implementation in util/host-utils.c.

With gcc 4.7, we get identical code generation for x86_64.  We
now get native multiplication on ia64 and s390x hosts.  With minor
improvements to gcc we can get it for ppc64 as well.

Signed-off-by: Richard Henderson <rth@twiddle.net>
Signed-off-by: Blue Swirl <blauwirbel@gmail.com>
diff --git a/include/qemu/host-utils.h b/include/qemu/host-utils.h
index f0dd850..0f688c1 100644
--- a/include/qemu/host-utils.h
+++ b/include/qemu/host-utils.h
@@ -28,22 +28,21 @@
 #include "qemu/compiler.h"   /* QEMU_GNUC_PREREQ */
 #include <limits.h>
 
-#if defined(__x86_64__)
-#define __HAVE_FAST_MULU64__
+#ifdef CONFIG_INT128
 static inline void mulu64(uint64_t *plow, uint64_t *phigh,
                           uint64_t a, uint64_t b)
 {
-    __asm__ ("mul %0\n\t"
-             : "=d" (*phigh), "=a" (*plow)
-             : "a" (a), "0" (b));
+    __uint128_t r = (__uint128_t)a * b;
+    *plow = r;
+    *phigh = r >> 64;
 }
-#define __HAVE_FAST_MULS64__
+
 static inline void muls64(uint64_t *plow, uint64_t *phigh,
                           int64_t a, int64_t b)
 {
-    __asm__ ("imul %0\n\t"
-             : "=d" (*phigh), "=a" (*plow)
-             : "a" (a), "0" (b));
+    __int128_t r = (__int128_t)a * b;
+    *plow = r;
+    *phigh = r >> 64;
 }
 #else
 void muls64(uint64_t *phigh, uint64_t *plow, int64_t a, int64_t b);