include/qemu/int128: Use Int128 structure for TCI

We are about to allow passing Int128 to/from tcg helper functions,
but libffi doesn't support __int128_t, so use the structure.

In order for atomic128.h to continue working, we must provide
a mechanism to frob between real __int128_t and the structure.
Provide a new union, Int128Alias, for this.  We cannot modify
Int128 itself, as any changed alignment would also break libffi.

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

include/qemu/atomic128.h

@@ -44,13 +44,23 @@
 #if defined(CONFIG_ATOMIC128)
 static inline Int128 atomic16_cmpxchg(Int128 *ptr, Int128 cmp, Int128 new)
 {
-    return qatomic_cmpxchg__nocheck(ptr, cmp, new);
+    Int128Alias r, c, n;
+
+    c.s = cmp;
+    n.s = new;
+    r.i = qatomic_cmpxchg__nocheck((__int128_t *)ptr, c.i, n.i);
+    return r.s;
 }
 # define HAVE_CMPXCHG128 1
 #elif defined(CONFIG_CMPXCHG128)
 static inline Int128 atomic16_cmpxchg(Int128 *ptr, Int128 cmp, Int128 new)
 {
-    return __sync_val_compare_and_swap_16(ptr, cmp, new);
+    Int128Alias r, c, n;
+
+    c.s = cmp;
+    n.s = new;
+    r.i = __sync_val_compare_and_swap_16((__int128_t *)ptr, c.i, n.i);
+    return r.s;
 }
 # define HAVE_CMPXCHG128 1
 #elif defined(__aarch64__)
@@ -89,12 +99,18 @@ Int128 QEMU_ERROR("unsupported atomic")
 #if defined(CONFIG_ATOMIC128)
 static inline Int128 atomic16_read(Int128 *ptr)
 {
-    return qatomic_read__nocheck(ptr);
+    Int128Alias r;
+
+    r.i = qatomic_read__nocheck((__int128_t *)ptr);
+    return r.s;
 }
 
 static inline void atomic16_set(Int128 *ptr, Int128 val)
 {
-    qatomic_set__nocheck(ptr, val);
+    Int128Alias v;
+
+    v.s = val;
+    qatomic_set__nocheck((__int128_t *)ptr, v.i);
 }
 
 # define HAVE_ATOMIC128 1
@@ -132,7 +148,8 @@ static inline void atomic16_set(Int128 *ptr, Int128 val)
 static inline Int128 atomic16_read(Int128 *ptr)
 {
     /* Maybe replace 0 with 0, returning the old value.  */
-    return atomic16_cmpxchg(ptr, 0, 0);
+    Int128 z = int128_make64(0);
+    return atomic16_cmpxchg(ptr, z, z);
 }
 
 static inline void atomic16_set(Int128 *ptr, Int128 val)
@@ -141,7 +158,7 @@ static inline void atomic16_set(Int128 *ptr, Int128 val)
     do {
         cmp = old;
         old = atomic16_cmpxchg(ptr, cmp, val);
-    } while (old != cmp);
+    } while (int128_ne(old, cmp));
 }
 
 # define HAVE_ATOMIC128 1

include/qemu/int128.h

@@ -3,7 +3,12 @@
 
 #include "qemu/bswap.h"
 
-#ifdef CONFIG_INT128
+/*
+ * With TCI, we need to use libffi for interfacing with TCG helpers.
+ * But libffi does not support __int128_t, and therefore cannot pass
+ * or return values of this type, force use of the Int128 struct.
+ */
+#if defined(CONFIG_INT128) && !defined(CONFIG_TCG_INTERPRETER)
 typedef __int128_t Int128;
 
 static inline Int128 int128_make64(uint64_t a)
@@ -460,8 +465,7 @@ Int128 int128_divu(Int128, Int128);
 Int128 int128_remu(Int128, Int128);
 Int128 int128_divs(Int128, Int128);
 Int128 int128_rems(Int128, Int128);
-
-#endif /* CONFIG_INT128 */
+#endif /* CONFIG_INT128 && !CONFIG_TCG_INTERPRETER */
 
 static inline void bswap128s(Int128 *s)
 {
@@ -472,4 +476,19 @@ static inline void bswap128s(Int128 *s)
 #define INT128_MAX int128_make128(UINT64_MAX, INT64_MAX)
 #define INT128_MIN int128_make128(0, INT64_MIN)
 
+/*
+ * When compiler supports a 128-bit type, define a combination of
+ * a possible structure and the native types.  Ease parameter passing
+ * via use of the transparent union extension.
+ */
+#ifdef CONFIG_INT128
+typedef union {
+    Int128 s;
+    __int128_t i;
+    __uint128_t u;
+} Int128Alias __attribute__((transparent_union));
+#else
+typedef Int128 Int128Alias;
+#endif /* CONFIG_INT128 */
+
 #endif /* INT128_H */

util/int128.c

@@ -144,4 +144,46 @@ Int128 int128_rems(Int128 a, Int128 b)
     return r;
 }
 
+#elif defined(CONFIG_TCG_INTERPRETER)
+
+Int128 int128_divu(Int128 a_s, Int128 b_s)
+{
+    Int128Alias r, a, b;
+
+    a.s = a_s;
+    b.s = b_s;
+    r.u = a.u / b.u;
+    return r.s;
+}
+
+Int128 int128_remu(Int128 a_s, Int128 b_s)
+{
+    Int128Alias r, a, b;
+
+    a.s = a_s;
+    b.s = b_s;
+    r.u = a.u % b.u;
+    return r.s;
+}
+
+Int128 int128_divs(Int128 a_s, Int128 b_s)
+{
+    Int128Alias r, a, b;
+
+    a.s = a_s;
+    b.s = b_s;
+    r.i = a.i / b.i;
+    return r.s;
+}
+
+Int128 int128_rems(Int128 a_s, Int128 b_s)
+{
+    Int128Alias r, a, b;
+
+    a.s = a_s;
+    b.s = b_s;
+    r.i = a.i % b.i;
+    return r.s;
+}
+
 #endif