target/s390x: Fix the floating-point multiply-and-add NaN rules

Order the helper arguments to match the Principles of Operation.
Implement the "Results: MULTIPLY AND ADD" table in pickNaNMulAdd().

Reported-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Message-ID: <20241023000147.34035-2-iii@linux.ibm.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>

fpu/softfloat-specialize.c.inc

@@ -597,6 +597,25 @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls,
         float_raise(float_flag_invalid | float_flag_invalid_imz, status);
     }
     return 3; /* default NaN */
+#elif defined(TARGET_S390X)
+    if (infzero) {
+        float_raise(float_flag_invalid | float_flag_invalid_imz, status);
+        return 3;
+    }
+
+    if (is_snan(a_cls)) {
+        return 0;
+    } else if (is_snan(b_cls)) {
+        return 1;
+    } else if (is_snan(c_cls)) {
+        return 2;
+    } else if (is_qnan(a_cls)) {
+        return 0;
+    } else if (is_qnan(b_cls)) {
+        return 1;
+    } else {
+        return 2;
+    }
 #elif defined(TARGET_SPARC)
     /* For (inf,0,nan) return c. */
     if (infzero) {

target/s390x/tcg/fpu_helper.c

@@ -780,7 +780,7 @@ uint32_t HELPER(kxb)(CPUS390XState *env, Int128 a, Int128 b)
 uint64_t HELPER(maeb)(CPUS390XState *env, uint64_t f1,
                       uint64_t f2, uint64_t f3)
 {
-    float32 ret = float32_muladd(f2, f3, f1, 0, &env->fpu_status);
+    float32 ret = float32_muladd(f3, f2, f1, 0, &env->fpu_status);
     handle_exceptions(env, false, GETPC());
     return ret;
 }
@@ -789,7 +789,7 @@ uint64_t HELPER(maeb)(CPUS390XState *env, uint64_t f1,
 uint64_t HELPER(madb)(CPUS390XState *env, uint64_t f1,
                       uint64_t f2, uint64_t f3)
 {
-    float64 ret = float64_muladd(f2, f3, f1, 0, &env->fpu_status);
+    float64 ret = float64_muladd(f3, f2, f1, 0, &env->fpu_status);
     handle_exceptions(env, false, GETPC());
     return ret;
 }
@@ -798,7 +798,7 @@ uint64_t HELPER(madb)(CPUS390XState *env, uint64_t f1,
 uint64_t HELPER(mseb)(CPUS390XState *env, uint64_t f1,
                       uint64_t f2, uint64_t f3)
 {
-    float32 ret = float32_muladd(f2, f3, f1, float_muladd_negate_c,
+    float32 ret = float32_muladd(f3, f2, f1, float_muladd_negate_c,
                                  &env->fpu_status);
     handle_exceptions(env, false, GETPC());
     return ret;
@@ -808,7 +808,7 @@ uint64_t HELPER(mseb)(CPUS390XState *env, uint64_t f1,
 uint64_t HELPER(msdb)(CPUS390XState *env, uint64_t f1,
                       uint64_t f2, uint64_t f3)
 {
-    float64 ret = float64_muladd(f2, f3, f1, float_muladd_negate_c,
+    float64 ret = float64_muladd(f3, f2, f1, float_muladd_negate_c,
                                  &env->fpu_status);
     handle_exceptions(env, false, GETPC());
     return ret;

target/s390x/tcg/vec_fpu_helper.c

@@ -621,8 +621,8 @@ static void vfma32(S390Vector *v1, const S390Vector *v2, const S390Vector *v3,
     int i;
 
     for (i = 0; i < 4; i++) {
-        const float32 a = s390_vec_read_float32(v2, i);
-        const float32 b = s390_vec_read_float32(v3, i);
+        const float32 a = s390_vec_read_float32(v3, i);
+        const float32 b = s390_vec_read_float32(v2, i);
         const float32 c = s390_vec_read_float32(v4, i);
         float32 ret = float32_muladd(a, b, c, flags, &env->fpu_status);
 
@@ -645,8 +645,8 @@ static void vfma64(S390Vector *v1, const S390Vector *v2, const S390Vector *v3,
     int i;
 
     for (i = 0; i < 2; i++) {
-        const float64 a = s390_vec_read_float64(v2, i);
-        const float64 b = s390_vec_read_float64(v3, i);
+        const float64 a = s390_vec_read_float64(v3, i);
+        const float64 b = s390_vec_read_float64(v2, i);
         const float64 c = s390_vec_read_float64(v4, i);
         const float64 ret = float64_muladd(a, b, c, flags, &env->fpu_status);
 
@@ -664,8 +664,8 @@ static void vfma128(S390Vector *v1, const S390Vector *v2, const S390Vector *v3,
                     const S390Vector *v4, CPUS390XState *env, bool s, int flags,
                     uintptr_t retaddr)
 {
-    const float128 a = s390_vec_read_float128(v2);
-    const float128 b = s390_vec_read_float128(v3);
+    const float128 a = s390_vec_read_float128(v3);
+    const float128 b = s390_vec_read_float128(v2);
     const float128 c = s390_vec_read_float128(v4);
     uint8_t vxc, vec_exc = 0;
     float128 ret;