[PATCH v6 25/36] target/s390x: Use a single return for helper_divs64/u64

[Richard Henderson <richard.henderson@linaro.org>]

Pack the quotient and remainder into a single Int128.
Use the divu128 primitive to remove the cpu_abort on
32-bit hosts.

Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Acked-by: Ilya Leoshkevich <iii@linux.ibm.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
v2: Extended div test case to cover these insns.
---
 target/s390x/helper.h         |  4 ++--
 target/s390x/tcg/int_helper.c | 38 +++++++++--------------------------
 target/s390x/tcg/translate.c  | 14 +++++++++----
 tests/tcg/s390x/div.c         | 35 ++++++++++++++++++++++++++++++++
 4 files changed, 56 insertions(+), 35 deletions(-)

diff --git a/target/s390x/helper.h b/target/s390x/helper.h
index bc828d976b..593f3c8bee 100644
--- a/target/s390x/helper.h
+++ b/target/s390x/helper.h
@@ -12,8 +12,8 @@ DEF_HELPER_3(clcl, i32, env, i32, i32)
 DEF_HELPER_FLAGS_4(clm, TCG_CALL_NO_WG, i32, env, i32, i32, i64)
 DEF_HELPER_FLAGS_3(divs32, TCG_CALL_NO_WG, i64, env, s64, s64)
 DEF_HELPER_FLAGS_3(divu32, TCG_CALL_NO_WG, i64, env, i64, i64)
-DEF_HELPER_FLAGS_3(divs64, TCG_CALL_NO_WG, s64, env, s64, s64)
-DEF_HELPER_FLAGS_4(divu64, TCG_CALL_NO_WG, i64, env, i64, i64, i64)
+DEF_HELPER_FLAGS_3(divs64, TCG_CALL_NO_WG, i128, env, s64, s64)
+DEF_HELPER_FLAGS_4(divu64, TCG_CALL_NO_WG, i128, env, i64, i64, i64)
 DEF_HELPER_3(srst, void, env, i32, i32)
 DEF_HELPER_3(srstu, void, env, i32, i32)
 DEF_HELPER_4(clst, i64, env, i64, i64, i64)
diff --git a/target/s390x/tcg/int_helper.c b/target/s390x/tcg/int_helper.c
index 7260583cf2..eb8e6dd1b5 100644
--- a/target/s390x/tcg/int_helper.c
+++ b/target/s390x/tcg/int_helper.c
@@ -76,46 +76,26 @@ uint64_t HELPER(divu32)(CPUS390XState *env, uint64_t a, uint64_t b64)
 }
 
 /* 64/64 -> 64 signed division */
-int64_t HELPER(divs64)(CPUS390XState *env, int64_t a, int64_t b)
+Int128 HELPER(divs64)(CPUS390XState *env, int64_t a, int64_t b)
 {
     /* Catch divide by zero, and non-representable quotient (MIN / -1).  */
     if (b == 0 || (b == -1 && a == (1ll << 63))) {
         tcg_s390_program_interrupt(env, PGM_FIXPT_DIVIDE, GETPC());
     }
-    env->retxl = a % b;
-    return a / b;
+    return int128_make128(a / b, a % b);
 }
 
 /* 128 -> 64/64 unsigned division */
-uint64_t HELPER(divu64)(CPUS390XState *env, uint64_t ah, uint64_t al,
-                        uint64_t b)
+Int128 HELPER(divu64)(CPUS390XState *env, uint64_t ah, uint64_t al, uint64_t b)
 {
-    uint64_t ret;
-    /* Signal divide by zero.  */
-    if (b == 0) {
-        tcg_s390_program_interrupt(env, PGM_FIXPT_DIVIDE, GETPC());
-    }
-    if (ah == 0) {
-        /* 64 -> 64/64 case */
-        env->retxl = al % b;
-        ret = al / b;
-    } else {
-        /* ??? Move i386 idivq helper to host-utils.  */
-#ifdef CONFIG_INT128
-        __uint128_t a = ((__uint128_t)ah << 64) | al;
-        __uint128_t q = a / b;
-        env->retxl = a % b;
-        ret = q;
-        if (ret != q) {
-            tcg_s390_program_interrupt(env, PGM_FIXPT_DIVIDE, GETPC());
+    if (b != 0) {
+        uint64_t r = divu128(&al, &ah, b);
+        if (ah == 0) {
+            return int128_make128(al, r);
         }
-#else
-        /* 32-bit hosts would need special wrapper functionality - just abort if
-           we encounter such a case; it's very unlikely anyways. */
-        cpu_abort(env_cpu(env), "128 -> 64/64 division not implemented\n");
-#endif
     }
-    return ret;
+    /* divide by zero or overflow */
+    tcg_s390_program_interrupt(env, PGM_FIXPT_DIVIDE, GETPC());
 }
 
 uint64_t HELPER(cvd)(int32_t reg)
diff --git a/target/s390x/tcg/translate.c b/target/s390x/tcg/translate.c
index 169f7ee1b2..6953b81de7 100644
--- a/target/s390x/tcg/translate.c
+++ b/target/s390x/tcg/translate.c
@@ -2409,15 +2409,21 @@ static DisasJumpType op_divu32(DisasContext *s, DisasOps *o)
 
 static DisasJumpType op_divs64(DisasContext *s, DisasOps *o)
 {
-    gen_helper_divs64(o->out2, cpu_env, o->in1, o->in2);
-    return_low128(o->out);
+    TCGv_i128 t = tcg_temp_new_i128();
+
+    gen_helper_divs64(t, cpu_env, o->in1, o->in2);
+    tcg_gen_extr_i128_i64(o->out2, o->out, t);
+    tcg_temp_free_i128(t);
     return DISAS_NEXT;
 }
 
 static DisasJumpType op_divu64(DisasContext *s, DisasOps *o)
 {
-    gen_helper_divu64(o->out2, cpu_env, o->out, o->out2, o->in2);
-    return_low128(o->out);
+    TCGv_i128 t = tcg_temp_new_i128();
+
+    gen_helper_divu64(t, cpu_env, o->out, o->out2, o->in2);
+    tcg_gen_extr_i128_i64(o->out2, o->out, t);
+    tcg_temp_free_i128(t);
     return DISAS_NEXT;
 }
 
diff --git a/tests/tcg/s390x/div.c b/tests/tcg/s390x/div.c
index 5807295614..6ad9900e08 100644
--- a/tests/tcg/s390x/div.c
+++ b/tests/tcg/s390x/div.c
@@ -33,8 +33,43 @@ static void test_dlr(void)
     assert(r == 1);
 }
 
+static void test_dsgr(void)
+{
+    register int64_t r0 asm("r0") = -1;
+    register int64_t r1 asm("r1") = -4241;
+    int64_t b = 101, q, r;
+
+    asm("dsgr %[r0],%[b]"
+        : [r0] "+r" (r0), [r1] "+r" (r1)
+        : [b] "r" (b)
+        : "cc");
+    q = r1;
+    r = r0;
+    assert(q == -41);
+    assert(r == -100);
+}
+
+static void test_dlgr(void)
+{
+    register uint64_t r0 asm("r0") = 0;
+    register uint64_t r1 asm("r1") = 4243;
+    uint64_t b = 101, q, r;
+
+    asm("dlgr %[r0],%[b]"
+        : [r0] "+r" (r0), [r1] "+r" (r1)
+        : [b] "r" (b)
+        : "cc");
+    q = r1;
+    r = r0;
+    assert(q == 42);
+    assert(r == 1);
+}
+
 int main(void)
 {
     test_dr();
     test_dlr();
+    test_dsgr();
+    test_dlgr();
+    return 0;
 }
-- 
2.34.1