s390x/tcg: Implement VECTOR TEST UNDER MASK

Let's return the cc value directly via cpu_env. Unfortunately there
isn't a simple way to calculate the value lazily - one would have to
calculate and store e.g. the population count of the mask and the
result so it can be evaluated in a cc helper.

But as VTM only sets the cc, we can assume the value will be needed soon
either way.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: David Hildenbrand <david@redhat.com>

target/s390x/helper.h

@@ -209,6 +209,7 @@ DEF_HELPER_FLAGS_4(gvec_vsra, TCG_CALL_NO_RWG, void, ptr, cptr, i64, i32)
 DEF_HELPER_FLAGS_4(gvec_vsrl, TCG_CALL_NO_RWG, void, ptr, cptr, i64, i32)
 DEF_HELPER_FLAGS_4(gvec_vscbi8, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
 DEF_HELPER_FLAGS_4(gvec_vscbi16, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
+DEF_HELPER_4(gvec_vtm, void, ptr, cptr, env, i32)
 
 #ifndef CONFIG_USER_ONLY
 DEF_HELPER_3(servc, i32, env, i64, i64)

target/s390x/insn-data.def

@@ -1188,6 +1188,8 @@
     F(0xe767, VSUMQ,   VRR_c, V,   0, 0, 0, 0, vsumq, 0, IF_VEC)
 /* VECTOR SUM ACROSS WORD */
     F(0xe764, VSUM,    VRR_c, V,   0, 0, 0, 0, vsum, 0, IF_VEC)
+/* VECTOR TEST UNDER MASK */
+    F(0xe7d8, VTM,     VRR_a, V,   0, 0, 0, 0, vtm, 0, IF_VEC)
 
 #ifndef CONFIG_USER_ONLY
 /* COMPARE AND SWAP AND PURGE */

target/s390x/translate_vx.inc.c

@@ -191,6 +191,9 @@ static void get_vec_element_ptr_i64(TCGv_ptr ptr, uint8_t reg, TCGv_i64 enr,
 #define gen_gvec_2i_ool(v1, v2, c, data, fn) \
     tcg_gen_gvec_2i_ool(vec_full_reg_offset(v1), vec_full_reg_offset(v2), \
                         c, 16, 16, data, fn)
+#define gen_gvec_2_ptr(v1, v2, ptr, data, fn) \
+    tcg_gen_gvec_2_ptr(vec_full_reg_offset(v1), vec_full_reg_offset(v2), \
+                       ptr, 16, 16, data, fn)
 #define gen_gvec_3(v1, v2, v3, gen) \
     tcg_gen_gvec_3(vec_full_reg_offset(v1), vec_full_reg_offset(v2), \
                    vec_full_reg_offset(v3), 16, 16, gen)
@@ -2342,3 +2345,11 @@ static DisasJumpType op_vsum(DisasContext *s, DisasOps *o)
     tcg_temp_free_i32(tmp);
     return DISAS_NEXT;
 }
+
+static DisasJumpType op_vtm(DisasContext *s, DisasOps *o)
+{
+    gen_gvec_2_ptr(get_field(s->fields, v1), get_field(s->fields, v2),
+                   cpu_env, 0, gen_helper_gvec_vtm);
+    set_cc_static(s);
+    return DISAS_NEXT;
+}

target/s390x/vec_int_helper.c

@@ -28,6 +28,19 @@ static void s390_vec_xor(S390Vector *res, const S390Vector *a,
     res->doubleword[1] = a->doubleword[1] ^ b->doubleword[1];
 }
 
+static void s390_vec_and(S390Vector *res, const S390Vector *a,
+                         const S390Vector *b)
+{
+    res->doubleword[0] = a->doubleword[0] & b->doubleword[0];
+    res->doubleword[1] = a->doubleword[1] & b->doubleword[1];
+}
+
+static bool s390_vec_equal(const S390Vector *a, const S390Vector *b)
+{
+    return a->doubleword[0] == b->doubleword[0] &&
+           a->doubleword[1] == b->doubleword[1];
+}
+
 static void s390_vec_shl(S390Vector *d, const S390Vector *a, uint64_t count)
 {
     uint64_t tmp;
@@ -583,3 +596,21 @@ void HELPER(gvec_vscbi##BITS)(void *v1, const void *v2, const void *v3,        \
 }
 DEF_VSCBI(8)
 DEF_VSCBI(16)
+
+void HELPER(gvec_vtm)(void *v1, const void *v2, CPUS390XState *env,
+                      uint32_t desc)
+{
+    S390Vector tmp;
+
+    s390_vec_and(&tmp, v1, v2);
+    if (s390_vec_is_zero(&tmp)) {
+        /* Selected bits all zeros; or all mask bits zero */
+        env->cc_op = 0;
+    } else if (s390_vec_equal(&tmp, v2)) {
+        /* Selected bits all ones */
+        env->cc_op = 3;
+    } else {
+        /* Selected bits a mix of zeros and ones */
+        env->cc_op = 1;
+    }
+}