x86emul: CMPXCHG{8,16}B ignore prefixes

This removes 0F C7 from the list of two-byte opcodes treating prefixes
66, F3, and F2 as opcode extensions. We better manually handle this in
the opcode specific code:
- CMPXCHG8B ignores all these prefixes (its handling is being adjusted
  accordingly, with a respective test case added as well, to avoid
  re-introducing the subject of XSA-200),
- RDRAND/RDSEED (support to be added subsequently) honor 66, but treat
  F3 and F2 as opcode extensions (resolving to RDPID in the RDSEED
  case, which in turn ignores 66).

Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>

tools/tests/x86_emulator/test_x86_emulator.c

@@ -364,6 +364,24 @@ int main(int argc, char **argv)
         goto fail;
     printf("okay\n");
 
+    printf("%-40s", "Testing cmpxchg8b (%edi) [opsize]...");
+    instr[0] = 0x66; instr[1] = 0x0f; instr[2] = 0xc7; instr[3] = 0x0f;
+    res[0]      = 0x12345678;
+    res[1]      = 0x87654321;
+    regs.eflags = 0x200;
+    regs.eip    = (unsigned long)&instr[0];
+    regs.edi    = (unsigned long)res;
+    rc = x86_emulate(&ctxt, &emulops);
+    if ( (rc != X86EMUL_OKAY) ||
+         (res[0] != 0x12345678) ||
+         (res[1] != 0x87654321) ||
+         (regs.eax != 0x12345678) ||
+         (regs.edx != 0x87654321) ||
+         ((regs.eflags&0x240) != 0x200) ||
+         (regs.eip != (unsigned long)&instr[4]) )
+        goto fail;
+    printf("okay\n");
+
     printf("%-40s", "Testing movsxbd (%eax),%ecx...");
     instr[0] = 0x0f; instr[1] = 0xbe; instr[2] = 0x08;
     regs.eflags = 0x200;

xen/arch/x86/x86_emulate/x86_emulate.c

@@ -1964,7 +1964,7 @@ x86_decode_twobyte(
     case 0x79 ... 0x7f:
     case 0xae:
     case 0xc2:
-    case 0xc4 ... 0xc7:
+    case 0xc4 ... 0xc6:
     case 0xd0 ... 0xfe:
         ctxt->opcode |= MASK_INSR(vex.pfx, X86EMUL_OPC_PFX_MASK);
         break;
@@ -5352,8 +5352,12 @@ x86_emulate(
         generate_exception_if(ea.type != OP_MEM, EXC_UD);
         fail_if(!ops->cmpxchg);
         if ( op_bytes == 8 )
+        {
             host_and_vcpu_must_have(cx16);
-        op_bytes *= 2;
+            op_bytes = 16;
+        }
+        else
+            op_bytes = 8;
 
         /* Get actual old value. */
         if ( (rc = ops->read(ea.mem.seg, ea.mem.off, old, op_bytes,