diff --git a/accel/tcg/ldst_atomicity.c.inc b/accel/tcg/ldst_atomicity.c.inc
index ba5db7c366..b89631bbef 100644
--- a/accel/tcg/ldst_atomicity.c.inc
+++ b/accel/tcg/ldst_atomicity.c.inc
@@ -16,23 +16,6 @@
 #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
diff --git a/host/include/generic/host/atomic128-cas.h b/host/include/generic/host/atomic128-cas.h
index 513622fe34..991d3da082 100644
--- a/host/include/generic/host/atomic128-cas.h
+++ b/host/include/generic/host/atomic128-cas.h
@@ -12,24 +12,28 @@
 #define HOST_ATOMIC128_CAS_H
 
 #if defined(CONFIG_ATOMIC128)
-static inline Int128 atomic16_cmpxchg(Int128 *ptr, Int128 cmp, Int128 new)
+static inline Int128 ATTRIBUTE_ATOMIC128_OPT
+atomic16_cmpxchg(Int128 *ptr, Int128 cmp, Int128 new)
 {
+    __int128_t *ptr_align = __builtin_assume_aligned(ptr, 16);
     Int128Alias r, c, n;
 
     c.s = cmp;
     n.s = new;
-    r.i = qatomic_cmpxchg__nocheck((__int128_t *)ptr, c.i, n.i);
+    r.i = qatomic_cmpxchg__nocheck(ptr_align, 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)
+static inline Int128 ATTRIBUTE_ATOMIC128_OPT
+atomic16_cmpxchg(Int128 *ptr, Int128 cmp, Int128 new)
 {
+    __int128_t *ptr_align = __builtin_assume_aligned(ptr, 16);
     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);
+    r.i = __sync_val_compare_and_swap_16(ptr_align, c.i, n.i);
     return r.s;
 }
 # define HAVE_CMPXCHG128 1
diff --git a/host/include/generic/host/atomic128-ldst.h b/host/include/generic/host/atomic128-ldst.h
index e7354a9255..46911dfb61 100644
--- a/host/include/generic/host/atomic128-ldst.h
+++ b/host/include/generic/host/atomic128-ldst.h
@@ -12,32 +12,38 @@
 #define HOST_ATOMIC128_LDST_H
 
 #if defined(CONFIG_ATOMIC128)
-static inline Int128 atomic16_read(Int128 *ptr)
+static inline Int128 ATTRIBUTE_ATOMIC128_OPT
+atomic16_read(Int128 *ptr)
 {
+    __int128_t *ptr_align = __builtin_assume_aligned(ptr, 16);
     Int128Alias r;
 
-    r.i = qatomic_read__nocheck((__int128_t *)ptr);
+    r.i = qatomic_read__nocheck(ptr_align);
     return r.s;
 }
 
-static inline void atomic16_set(Int128 *ptr, Int128 val)
+static inline void ATTRIBUTE_ATOMIC128_OPT
+atomic16_set(Int128 *ptr, Int128 val)
 {
+    __int128_t *ptr_align = __builtin_assume_aligned(ptr, 16);
     Int128Alias v;
 
     v.s = val;
-    qatomic_set__nocheck((__int128_t *)ptr, v.i);
+    qatomic_set__nocheck(ptr_align, v.i);
 }
 
 # define HAVE_ATOMIC128 1
 #elif !defined(CONFIG_USER_ONLY) && HAVE_CMPXCHG128
-static inline Int128 atomic16_read(Int128 *ptr)
+static inline Int128 ATTRIBUTE_ATOMIC128_OPT
+atomic16_read(Int128 *ptr)
 {
     /* Maybe replace 0 with 0, returning the old value.  */
     Int128 z = int128_make64(0);
     return atomic16_cmpxchg(ptr, z, z);
 }
 
-static inline void atomic16_set(Int128 *ptr, Int128 val)
+static inline void ATTRIBUTE_ATOMIC128_OPT
+atomic16_set(Int128 *ptr, Int128 val)
 {
     Int128 old = *ptr, cmp;
     do {
diff --git a/include/qemu/atomic128.h b/include/qemu/atomic128.h
index 3a8adb4d47..34554bf0ac 100644
--- a/include/qemu/atomic128.h
+++ b/include/qemu/atomic128.h
@@ -15,6 +15,23 @@
 
 #include "qemu/int128.h"
 
+/*
+ * 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
+
 /*
  * GCC is a house divided about supporting large atomic operations.
  *