meson: Detect atomic128 support with optimization

There is an edge condition prior to gcc13 for which optimization
is required to generate 16-byte atomic sequences.  Detect this.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

1 files changed, 25 insertions, 4 deletions

diff --git a/accel/tcg/ldst_atomicity.c.inc b/accel/tcg/ldst_atomicity.c.inc
index ce73b32..ba5db7c 100644
--- a/accel/tcg/ldst_atomicity.c.inc
+++ b/accel/tcg/ldst_atomicity.c.inc
@@ -16,6 +16,23 @@
 #endif
 #define HAVE_al8_fast      (ATOMIC_REG_SIZE >= 8)
 
+/*
+ * If __alignof(unsigned __int128) < 16, GCC may refuse to inline atomics
+ * that are supported by the host, e.g. s390x.  We can force the pointer to
+ * have our known alignment with __builtin_assume_aligned, however prior to
+ * GCC 13 that was only reliable with optimization enabled.  See
+ *   https://gcc.gnu.org/bugzilla/show_bug.cgi?id=107389
+ */
+#if defined(CONFIG_ATOMIC128_OPT)
+# if !defined(__OPTIMIZE__)
+#  define ATTRIBUTE_ATOMIC128_OPT  __attribute__((optimize("O1")))
+# endif
+# define CONFIG_ATOMIC128
+#endif
+#ifndef ATTRIBUTE_ATOMIC128_OPT
+# define ATTRIBUTE_ATOMIC128_OPT
+#endif
+
 #if defined(CONFIG_ATOMIC128)
 # define HAVE_al16_fast    true
 #else
@@ -152,7 +169,8 @@ static inline uint64_t load_atomic8(void *pv)
  *
  * Atomically load 16 aligned bytes from @pv.
  */
-static inline Int128 load_atomic16(void *pv)
+static inline Int128 ATTRIBUTE_ATOMIC128_OPT
+load_atomic16(void *pv)
 {
 #ifdef CONFIG_ATOMIC128
     __uint128_t *p = __builtin_assume_aligned(pv, 16);
@@ -356,7 +374,8 @@ static uint64_t load_atom_extract_al16_or_exit(CPUArchState *env, uintptr_t ra,
  * cross an 16-byte boundary then the access must be 16-byte atomic,
  * otherwise the access must be 8-byte atomic.
  */
-static inline uint64_t load_atom_extract_al16_or_al8(void *pv, int s)
+static inline uint64_t ATTRIBUTE_ATOMIC128_OPT
+load_atom_extract_al16_or_al8(void *pv, int s)
 {
 #if defined(CONFIG_ATOMIC128)
     uintptr_t pi = (uintptr_t)pv;
@@ -692,7 +711,8 @@ static inline void store_atomic8(void *pv, uint64_t val)
  *
  * Atomically store 16 aligned bytes to @pv.
  */
-static inline void store_atomic16(void *pv, Int128Alias val)
+static inline void ATTRIBUTE_ATOMIC128_OPT
+store_atomic16(void *pv, Int128Alias val)
 {
 #if defined(CONFIG_ATOMIC128)
     __uint128_t *pu = __builtin_assume_aligned(pv, 16);
@@ -790,7 +810,8 @@ static void store_atom_insert_al8(uint64_t *p, uint64_t val, uint64_t msk)
  *
  * Atomically store @val to @p masked by @msk.
  */
-static void store_atom_insert_al16(Int128 *ps, Int128Alias val, Int128Alias msk)
+static void ATTRIBUTE_ATOMIC128_OPT
+store_atom_insert_al16(Int128 *ps, Int128Alias val, Int128Alias msk)
 {
 #if defined(CONFIG_ATOMIC128)
     __uint128_t *pu, old, new;