[PATCH v2 03/26] s390x/tcg: Simplify vop64_3() handling

[David Hildenbrand <david@redhat.com>]

Let's simplify, reworking our handler generation, passing the whole "m5"
register content and not providing specialized handlers for "se", and
reading/writing proper float64 values using new helpers.

Suggested-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: David Hildenbrand <david@redhat.com>
---
 target/s390x/helper.h           |  4 --
 target/s390x/translate_vx.c.inc | 11 ++--
 target/s390x/vec_fpu_helper.c   | 94 +++++++++------------------------
 3 files changed, 30 insertions(+), 79 deletions(-)

diff --git a/target/s390x/helper.h b/target/s390x/helper.h
index d4e4f3388f..2344f81273 100644
--- a/target/s390x/helper.h
+++ b/target/s390x/helper.h
@@ -247,7 +247,6 @@ DEF_HELPER_6(gvec_vstrc_cc_rt32, void, ptr, cptr, cptr, cptr, env, i32)
 
 /* === Vector Floating-Point Instructions */
 DEF_HELPER_FLAGS_5(gvec_vfa64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
-DEF_HELPER_FLAGS_5(gvec_vfa64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_4(gvec_wfc64, void, cptr, cptr, env, i32)
 DEF_HELPER_4(gvec_wfk64, void, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfce64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
@@ -271,7 +270,6 @@ DEF_HELPER_FLAGS_4(gvec_vcgd64s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vclgd64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vclgd64s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfd64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
-DEF_HELPER_FLAGS_5(gvec_vfd64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vfi64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vfi64s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vfll32, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
@@ -279,7 +277,6 @@ DEF_HELPER_FLAGS_4(gvec_vfll32s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vflr64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vflr64s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfm64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
-DEF_HELPER_FLAGS_5(gvec_vfm64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_6(gvec_vfma64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_6(gvec_vfma64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_6(gvec_vfms64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
@@ -287,7 +284,6 @@ DEF_HELPER_FLAGS_6(gvec_vfms64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, en
 DEF_HELPER_FLAGS_4(gvec_vfsq64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vfsq64s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfs64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
-DEF_HELPER_FLAGS_5(gvec_vfs64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_4(gvec_vftci64, void, ptr, cptr, env, i32)
 DEF_HELPER_4(gvec_vftci64s, void, ptr, cptr, env, i32)
 
diff --git a/target/s390x/translate_vx.c.inc b/target/s390x/translate_vx.c.inc
index eb767f5288..2d3fbdfab2 100644
--- a/target/s390x/translate_vx.c.inc
+++ b/target/s390x/translate_vx.c.inc
@@ -2443,7 +2443,6 @@ static DisasJumpType op_vfa(DisasContext *s, DisasOps *o)
 {
     const uint8_t fpf = get_field(s, m4);
     const uint8_t m5 = get_field(s, m5);
-    const bool se = extract32(m5, 3, 1);
     gen_helper_gvec_3_ptr *fn;
 
     if (fpf != FPF_LONG || extract32(m5, 0, 3)) {
@@ -2453,22 +2452,22 @@ static DisasJumpType op_vfa(DisasContext *s, DisasOps *o)
 
     switch (s->fields.op2) {
     case 0xe3:
-        fn = se ? gen_helper_gvec_vfa64s : gen_helper_gvec_vfa64;
+        fn = gen_helper_gvec_vfa64;
         break;
     case 0xe5:
-        fn = se ? gen_helper_gvec_vfd64s : gen_helper_gvec_vfd64;
+        fn = gen_helper_gvec_vfd64;
         break;
     case 0xe7:
-        fn = se ? gen_helper_gvec_vfm64s : gen_helper_gvec_vfm64;
+        fn = gen_helper_gvec_vfm64;
         break;
     case 0xe2:
-        fn = se ? gen_helper_gvec_vfs64s : gen_helper_gvec_vfs64;
+        fn = gen_helper_gvec_vfs64;
         break;
     default:
         g_assert_not_reached();
     }
     gen_gvec_3_ptr(get_field(s, v1), get_field(s, v2),
-                   get_field(s, v3), cpu_env, 0, fn);
+                   get_field(s, v3), cpu_env, m5, fn);
     return DISAS_NEXT;
 }
 
diff --git a/target/s390x/vec_fpu_helper.c b/target/s390x/vec_fpu_helper.c
index d485837930..f33ee6e774 100644
--- a/target/s390x/vec_fpu_helper.c
+++ b/target/s390x/vec_fpu_helper.c
@@ -78,6 +78,16 @@ static void handle_ieee_exc(CPUS390XState *env, uint8_t vxc, uint8_t vec_exc,
     }
 }
 
+static float64 s390_vec_read_float64(const S390Vector *v, uint8_t enr)
+{
+    return make_float64(s390_vec_read_element64(v, enr));
+}
+
+static void s390_vec_write_float64(S390Vector *v, uint8_t enr, float64 data)
+{
+    return s390_vec_write_element64(v, enr, data);
+}
+
 typedef uint64_t (*vop64_2_fn)(uint64_t a, float_status *s);
 static void vop64_2(S390Vector *v1, const S390Vector *v2, CPUS390XState *env,
                     bool s, bool XxC, uint8_t erm, vop64_2_fn fn,
@@ -102,7 +112,7 @@ static void vop64_2(S390Vector *v1, const S390Vector *v2, CPUS390XState *env,
     *v1 = tmp;
 }
 
-typedef uint64_t (*vop64_3_fn)(uint64_t a, uint64_t b, float_status *s);
+typedef float64 (*vop64_3_fn)(float64 a, float64 b, float_status *s);
 static void vop64_3(S390Vector *v1, const S390Vector *v2, const S390Vector *v3,
                     CPUS390XState *env, bool s, vop64_3_fn fn,
                     uintptr_t retaddr)
@@ -112,10 +122,10 @@ static void vop64_3(S390Vector *v1, const S390Vector *v2, const S390Vector *v3,
     int i;
 
     for (i = 0; i < 2; i++) {
-        const uint64_t a = s390_vec_read_element64(v2, i);
-        const uint64_t b = s390_vec_read_element64(v3, i);
+        const float64 a = s390_vec_read_float64(v2, i);
+        const float64 b = s390_vec_read_float64(v3, i);
 
-        s390_vec_write_element64(&tmp, i, fn(a, b, &env->fpu_status));
+        s390_vec_write_float64(&tmp, i, fn(a, b, &env->fpu_status));
         vxc = check_ieee_exc(env, i, false, &vec_exc);
         if (s || vxc) {
             break;
@@ -125,22 +135,19 @@ static void vop64_3(S390Vector *v1, const S390Vector *v2, const S390Vector *v3,
     *v1 = tmp;
 }
 
-static uint64_t vfa64(uint64_t a, uint64_t b, float_status *s)
-{
-    return float64_add(a, b, s);
+#define DEF_GVEC_VOP3(NAME, OP)                                                \
+void HELPER(gvec_##NAME##64)(void *v1, const void *v2, const void *v3,         \
+                             CPUS390XState *env, uint32_t desc)                \
+{                                                                              \
+    const bool se = extract32(simd_data(desc), 3, 1);                          \
+                                                                               \
+    vop64_3(v1, v2, v3, env, se, float64_##OP, GETPC());                       \
 }
 
-void HELPER(gvec_vfa64)(void *v1, const void *v2, const void *v3,
-                        CPUS390XState *env, uint32_t desc)
-{
-    vop64_3(v1, v2, v3, env, false, vfa64, GETPC());
-}
-
-void HELPER(gvec_vfa64s)(void *v1, const void *v2, const void *v3,
-                         CPUS390XState *env, uint32_t desc)
-{
-    vop64_3(v1, v2, v3, env, true, vfa64, GETPC());
-}
+DEF_GVEC_VOP3(vfa, add)
+DEF_GVEC_VOP3(vfs, sub)
+DEF_GVEC_VOP3(vfd, div)
+DEF_GVEC_VOP3(vfm, mul)
 
 static int wfc64(const S390Vector *v1, const S390Vector *v2,
                  CPUS390XState *env, bool signal, uintptr_t retaddr)
@@ -376,23 +383,6 @@ void HELPER(gvec_vclgd64s)(void *v1, const void *v2, CPUS390XState *env,
     vop64_2(v1, v2, env, true, XxC, erm, vclgd64, GETPC());
 }
 
-static uint64_t vfd64(uint64_t a, uint64_t b, float_status *s)
-{
-    return float64_div(a, b, s);
-}
-
-void HELPER(gvec_vfd64)(void *v1, const void *v2, const void *v3,
-                        CPUS390XState *env, uint32_t desc)
-{
-    vop64_3(v1, v2, v3, env, false, vfd64, GETPC());
-}
-
-void HELPER(gvec_vfd64s)(void *v1, const void *v2, const void *v3,
-                         CPUS390XState *env, uint32_t desc)
-{
-    vop64_3(v1, v2, v3, env, true, vfd64, GETPC());
-}
-
 static uint64_t vfi64(uint64_t a, float_status *s)
 {
     return float64_round_to_int(a, s);
@@ -494,23 +484,6 @@ void HELPER(gvec_vflr64s)(void *v1, const void *v2, CPUS390XState *env,
     vflr64(v1, v2, env, true, XxC, erm, GETPC());
 }
 
-static uint64_t vfm64(uint64_t a, uint64_t b, float_status *s)
-{
-    return float64_mul(a, b, s);
-}
-
-void HELPER(gvec_vfm64)(void *v1, const void *v2, const void *v3,
-                        CPUS390XState *env, uint32_t desc)
-{
-    vop64_3(v1, v2, v3, env, false, vfm64, GETPC());
-}
-
-void HELPER(gvec_vfm64s)(void *v1, const void *v2, const void *v3,
-                         CPUS390XState *env, uint32_t desc)
-{
-    vop64_3(v1, v2, v3, env, true, vfm64, GETPC());
-}
-
 static void vfma64(S390Vector *v1, const S390Vector *v2, const S390Vector *v3,
                    const S390Vector *v4, CPUS390XState *env, bool s, int flags,
                    uintptr_t retaddr)
@@ -576,23 +549,6 @@ void HELPER(gvec_vfsq64s)(void *v1, const void *v2, CPUS390XState *env,
     vop64_2(v1, v2, env, true, false, 0, vfsq64, GETPC());
 }
 
-static uint64_t vfs64(uint64_t a, uint64_t b, float_status *s)
-{
-    return float64_sub(a, b, s);
-}
-
-void HELPER(gvec_vfs64)(void *v1, const void *v2, const void *v3,
-                        CPUS390XState *env, uint32_t desc)
-{
-    vop64_3(v1, v2, v3, env, false, vfs64, GETPC());
-}
-
-void HELPER(gvec_vfs64s)(void *v1, const void *v2, const void *v3,
-                         CPUS390XState *env, uint32_t desc)
-{
-    vop64_3(v1, v2, v3, env, true, vfs64, GETPC());
-}
-
 static int vftci64(S390Vector *v1, const S390Vector *v2, CPUS390XState *env,
                    bool s, uint16_t i3)
 {
-- 
2.31.1