From: Paolo Bonzini <pbonzini@redhat.com>

According to the manual, 32-bit vs 64-bit is governed by REX.W
and REX ignores the 0x66 prefix.  This can be confirmed with this
program:

    #include <stdio.h>
    int main()
    {
       int x = 0x12340000;
       int y;
       asm("popcntl %1, %0" : "=r" (y) : "r" (x)); printf("%x\n", y);
       asm("mov $-1, %0; .byte 0x66; popcntl %1, %0" : "+r" (y) : "r" (x)); printf("%x\n", y);
       asm("mov $-1, %0; .byte 0x66; popcntq %q1, %q0" : "+r" (y) : "r" (x)); printf("%x\n", y);
    }

which prints 5/ffff0000/5 on real hardware and 5/ffff0000/ffff0000
on QEMU.

Cc: qemu-stable@nongnu.org
Reviewed-by: Zhao Liu <zhao1.liu@intel.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 41c685dc59bb611096f3bb6a663cfa82e4cba97b)
Signed-off-by: Michael Tokarev <mjt@tls.msk.ru>

diff --git a/target/i386/tcg/translate.c b/target/i386/tcg/translate.c
index 2b0df7bcfa..c4016314fb 100644
--- a/target/i386/tcg/translate.c
+++ b/target/i386/tcg/translate.c
@@ -415,16 +415,6 @@ static inline MemOp mo_stacksize(DisasContext *s)
     return CODE64(s) ? MO_64 : SS32(s) ? MO_32 : MO_16;
 }
 
-/* Select only size 64 else 32.  Used for SSE operand sizes.  */
-static inline MemOp mo_64_32(MemOp ot)
-{
-#ifdef TARGET_X86_64
-    return ot == MO_64 ? MO_64 : MO_32;
-#else
-    return MO_32;
-#endif
-}
-
 /* Select size 8 if lsb of B is clear, else OT.  Used for decoding
    byte vs word opcodes.  */
 static inline MemOp mo_b_d(int b, MemOp ot)
@@ -6788,12 +6778,7 @@ static bool disas_insn(DisasContext *s, CPUState *cpu)
         modrm = x86_ldub_code(env, s);
         reg = ((modrm >> 3) & 7) | REX_R(s);
 
-        if (s->prefix & PREFIX_DATA) {
-            ot = MO_16;
-        } else {
-            ot = mo_64_32(dflag);
-        }
-
+        ot = dflag;
         gen_ldst_modrm(env, s, modrm, ot, OR_TMP0, 0);
         gen_extu(ot, s->T0);
         tcg_gen_mov_tl(cpu_cc_src, s->T0);
-- 
2.39.2