target/i386: Fix BZHI instruction

We did not correctly handle N >= operand size.

Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1374
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20230114233206.3118472-1-richard.henderson@linaro.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

target/i386/tcg/emit.c.inc

@@ -1147,20 +1147,20 @@ static void gen_BLSR(DisasContext *s, CPUX86State *env, X86DecodedInsn *decode)
 static void gen_BZHI(DisasContext *s, CPUX86State *env, X86DecodedInsn *decode)
 {
     MemOp ot = decode->op[0].ot;
-    TCGv bound;
+    TCGv bound = tcg_constant_tl(ot == MO_64 ? 63 : 31);
+    TCGv zero = tcg_constant_tl(0);
+    TCGv mone = tcg_constant_tl(-1);
 
-    tcg_gen_ext8u_tl(s->T1, cpu_regs[s->vex_v]);
-    bound = tcg_constant_tl(ot == MO_64 ? 63 : 31);
+    tcg_gen_ext8u_tl(s->T1, s->T1);
 
     /*
      * Note that since we're using BMILG (in order to get O
      * cleared) we need to store the inverse into C.
      */
-    tcg_gen_setcond_tl(TCG_COND_LT, cpu_cc_src, s->T1, bound);
-    tcg_gen_movcond_tl(TCG_COND_GT, s->T1, s->T1, bound, bound, s->T1);
+    tcg_gen_setcond_tl(TCG_COND_LEU, cpu_cc_src, s->T1, bound);
 
-    tcg_gen_movi_tl(s->A0, -1);
-    tcg_gen_shl_tl(s->A0, s->A0, s->T1);
+    tcg_gen_shl_tl(s->A0, mone, s->T1);
+    tcg_gen_movcond_tl(TCG_COND_LEU, s->A0, s->T1, bound, s->A0, zero);
     tcg_gen_andc_tl(s->T0, s->T0, s->A0);
 
     gen_op_update1_cc(s);

tests/tcg/i386/test-i386-bmi2.c

@@ -123,6 +123,9 @@ int main(int argc, char *argv[]) {
     result = bzhiq(mask, 0x1f);
     assert(result == (mask & ~(-1 << 30)));
 
+    result = bzhiq(mask, 0x40);
+    assert(result == mask);
+
     result = rorxq(0x2132435465768798, 8);
     assert(result == 0x9821324354657687);