[PATCH] x86 emulation: fix bswap

["Jan Beulich" <jbeulich@novell.com>]

REX.R needs to be decoded and since bswap on a 16-bit operand is undefined,
it is best to have hardware execute this so the emulation result matches
hardware behavior. Since it is simple to do, faster, and smaller, also let hardware
do 32- and 64-bit ones.

Signed-off-by: Jan Beulich <jbeulich@novell.com>

Index: 2007-02-07/xen/arch/x86/x86_emulate.c
===================================================================
--- 2007-02-07.orig/xen/arch/x86/x86_emulate.c	2007-02-08 08:46:39.000000000 +0100
+++ 2007-02-07/xen/arch/x86/x86_emulate.c	2007-02-08 09:32:00.000000000 +0100
@@ -2326,32 +2326,22 @@ x86_emulate(
 
     case 0xc8 ... 0xcf: /* bswap */
         dst.type  = OP_REG;
-        dst.reg   = decode_register(b & 7, &_regs, 0);
+        dst.reg   = decode_register(
+            (b & 7) | ((rex_prefix & 1) << 3), &_regs, 0);
         dst.val = *dst.reg;
         switch ( dst.bytes = op_bytes )
         {
         case 2:
-            dst.val = (((dst.val & 0x00FFUL) << 8) |
-                       ((dst.val & 0xFF00UL) >> 8));
+            __asm__("data16 bswap %k0" : "+r" (dst.val));
             break;
         case 4:
-            dst.val = (((dst.val & 0x000000FFUL) << 24) |
-                       ((dst.val & 0x0000FF00UL) <<  8) |
-                       ((dst.val & 0x00FF0000UL) >>  8) |
-                       ((dst.val & 0xFF000000UL) >> 24));
-            break;
 #ifdef __x86_64__
-        case 8:
-            dst.val = (((dst.val & 0x00000000000000FFUL) << 56) |
-                       ((dst.val & 0x000000000000FF00UL) << 40) |
-                       ((dst.val & 0x0000000000FF0000UL) << 24) |
-                       ((dst.val & 0x00000000FF000000UL) <<  8) |
-                       ((dst.val & 0x000000FF00000000UL) >>  8) |
-                       ((dst.val & 0x0000FF0000000000UL) >> 24) |
-                       ((dst.val & 0x00FF000000000000UL) >> 40) |
-                       ((dst.val & 0xFF00000000000000UL) >> 56));
+            __asm__("bswap %k0" : "+r" (dst.val));
             break;
+        case 8:
 #endif
+            __asm__("bswap %0" : "+r" (dst.val));
+            break;
         }
         break;
     }