[PULL 13/35] target/sh4: Fix mac.w with saturation enabled

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

From: Zack Buhman <zack@buhman.org>

The saturation arithmetic logic in helper_macw is not correct.
I tested and verified this behavior on a SH7091.

Reviewd-by: Yoshinori Sato <ysato@users.sourceforge.jp>
Signed-off-by: Zack Buhman <zack@buhman.org>
Message-Id: <20240405233802.29128-3-zack@buhman.org>
[rth: Reformat helper_macw, add a test case.]
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
---
 target/sh4/helper.h           |  2 +-
 target/sh4/op_helper.c        | 28 +++++++++-------
 tests/tcg/sh4/test-macw.c     | 61 +++++++++++++++++++++++++++++++++++
 tests/tcg/sh4/Makefile.target |  3 ++
 4 files changed, 82 insertions(+), 12 deletions(-)
 create mode 100644 tests/tcg/sh4/test-macw.c

diff --git a/target/sh4/helper.h b/target/sh4/helper.h
index 64056e4a39..29011d3dbb 100644
--- a/target/sh4/helper.h
+++ b/target/sh4/helper.h
@@ -12,7 +12,7 @@ DEF_HELPER_1(discard_movcal_backup, void, env)
 DEF_HELPER_2(ocbi, void, env, i32)
 
 DEF_HELPER_3(macl, void, env, s32, s32)
-DEF_HELPER_3(macw, void, env, i32, i32)
+DEF_HELPER_3(macw, void, env, s32, s32)
 
 DEF_HELPER_2(ld_fpscr, void, env, i32)
 
diff --git a/target/sh4/op_helper.c b/target/sh4/op_helper.c
index d0bae0cc00..99394b714c 100644
--- a/target/sh4/op_helper.c
+++ b/target/sh4/op_helper.c
@@ -177,22 +177,28 @@ void helper_macl(CPUSH4State *env, int32_t arg0, int32_t arg1)
     env->mac = res;
 }
 
-void helper_macw(CPUSH4State *env, uint32_t arg0, uint32_t arg1)
+void helper_macw(CPUSH4State *env, int32_t arg0, int32_t arg1)
 {
-    int64_t res;
+    /* Inputs are already sign-extended from 16 bits. */
+    int32_t mul = arg0 * arg1;
 
-    res = ((uint64_t) env->mach << 32) | env->macl;
-    res += (int64_t) (int16_t) arg0 *(int64_t) (int16_t) arg1;
-    env->mach = (res >> 32) & 0xffffffff;
-    env->macl = res & 0xffffffff;
     if (env->sr & (1u << SR_S)) {
-        if (res < -0x80000000) {
+        /*
+         * In saturation arithmetic mode, the accumulator is 32-bit
+         * with carry. MACH is not considered during the addition
+         * operation nor the 32-bit saturation logic.
+         */
+        int32_t res, macl = env->macl;
+
+        if (sadd32_overflow(macl, mul, &res)) {
+            res = macl < 0 ? INT32_MIN : INT32_MAX;
+            /* If overflow occurs, the MACH register is set to 1. */
             env->mach = 1;
-            env->macl = 0x80000000;
-        } else if (res > 0x000000007fffffff) {
-            env->mach = 1;
-            env->macl = 0x7fffffff;
         }
+        env->macl = res;
+    } else {
+        /* In non-saturation arithmetic mode, the accumulator is 64-bit */
+        env->mac += mul;
     }
 }
 
diff --git a/tests/tcg/sh4/test-macw.c b/tests/tcg/sh4/test-macw.c
new file mode 100644
index 0000000000..4eceec8634
--- /dev/null
+++ b/tests/tcg/sh4/test-macw.c
@@ -0,0 +1,61 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+
+#include <stdint.h>
+#include <stdlib.h>
+#include <stdio.h>
+
+int64_t mac_w(int64_t mac, const int16_t *a, const int16_t *b)
+{
+    register uint32_t macl __asm__("macl") = mac;
+    register uint32_t mach __asm__("mach") = mac >> 32;
+
+    asm volatile("mac.w @%0+,@%1+"
+                 : "+r"(a), "+r"(b), "+x"(macl), "+x"(mach));
+
+    return ((uint64_t)mach << 32) | macl;
+}
+
+typedef struct {
+    int64_t mac;
+    int16_t a, b;
+    int64_t res[2];
+} Test;
+
+__attribute__((noinline))
+void test(const Test *t, int sat)
+{
+    int64_t res;
+
+    if (sat) {
+        asm volatile("sets");
+    } else {
+        asm volatile("clrs");
+    }
+    res = mac_w(t->mac, &t->a, &t->b);
+
+    if (res != t->res[sat]) {
+        fprintf(stderr, "%#llx + (%#x * %#x) = %#llx -- got %#llx\n",
+                t->mac, t->a, t->b, t->res[sat], res);
+        abort();
+    }
+}
+
+int main()
+{
+    static const Test tests[] = {
+        { 0, 2, 3, { 6, 6 } },
+        { 0x123456787ffffffell, 2, -3,
+          { 0x123456787ffffff8ll, 0x123456787ffffff8ll } },
+        { 0xabcdef127ffffffall, 2, 3,
+          { 0xabcdef1280000000ll, 0x000000017fffffffll } },
+        { 0xfffffffffll, INT16_MAX, INT16_MAX,
+          { 0x103fff0000ll, 0xf3fff0000ll } },
+    };
+
+    for (int i = 0; i < sizeof(tests) / sizeof(tests[0]); ++i) {
+        for (int j = 0; j < 2; ++j) {
+            test(&tests[i], j);
+        }
+    }
+    return 0;
+}
diff --git a/tests/tcg/sh4/Makefile.target b/tests/tcg/sh4/Makefile.target
index 9a11c10924..4d09291c0c 100644
--- a/tests/tcg/sh4/Makefile.target
+++ b/tests/tcg/sh4/Makefile.target
@@ -14,3 +14,6 @@ VPATH += $(SRC_PATH)/tests/tcg/sh4
 
 test-macl: CFLAGS += -O -g
 TESTS += test-macl
+
+test-macw: CFLAGS += -O -g
+TESTS += test-macw
-- 
2.34.1