Prevent Clang from emitting atomic libcalls

Clang expects 8-byte alignment for some 64-bit atomic operations
in some 32-bit targets. Native instruction lock cmpxchg8b (for x86)
should only require 4-byte alignment.

This patch tries to add 8-byte alignents to data needing atomic ops
which helps clang to not generate the libatomic calls but emit
builtins directly.

Upstream-Status: Submitted[https://jira.mariadb.org/browse/MDEV-28162]
Signed-off-by: Khem Raj <raj.khem@gmail.com>

--- a/include/my_atomic.h
+++ b/include/my_atomic.h
@@ -115,6 +115,16 @@
 #include "atomic/gcc_builtins.h"
 #endif
 
+#include <stdint.h>
+
+# ifdef __GNUC__
+typedef __attribute__((__aligned__(8))) int64 ATOMIC_I64;
+typedef __attribute__((__aligned__(8))) uint64 ATOMIC_U64;
+# else
+typedef int64 ATOMIC_I64;
+typedef uint64 ATOMIC_U64;
+# endif
+
 #if SIZEOF_LONG == 4
 #define my_atomic_addlong(A,B) my_atomic_add32((int32*) (A), (B))
 #define my_atomic_loadlong(A) my_atomic_load32((int32*) (A))
@@ -123,12 +133,12 @@
 #define my_atomic_faslong(A,B) my_atomic_fas32((int32*) (A), (B))
 #define my_atomic_caslong(A,B,C) my_atomic_cas32((int32*) (A), (int32*) (B), (C))
 #else
-#define my_atomic_addlong(A,B) my_atomic_add64((int64*) (A), (B))
-#define my_atomic_loadlong(A) my_atomic_load64((int64*) (A))
-#define my_atomic_loadlong_explicit(A,O) my_atomic_load64_explicit((int64*) (A), (O))
-#define my_atomic_storelong(A,B) my_atomic_store64((int64*) (A), (B))
-#define my_atomic_faslong(A,B) my_atomic_fas64((int64*) (A), (B))
-#define my_atomic_caslong(A,B,C) my_atomic_cas64((int64*) (A), (int64*) (B), (C))
+#define my_atomic_addlong(A,B) my_atomic_add64((ATOMIC_I64*) (A), (B))
+#define my_atomic_loadlong(A) my_atomic_load64((ATOMIC_I64*) (A))
+#define my_atomic_loadlong_explicit(A,O) my_atomic_load64_explicit((ATOMIC_I64*) (A), (O))
+#define my_atomic_storelong(A,B) my_atomic_store64((ATOMIC_I64*) (A), (B))
+#define my_atomic_faslong(A,B) my_atomic_fas64((ATOMIC_I64*) (A), (B))
+#define my_atomic_caslong(A,B,C) my_atomic_cas64((ATOMIC_I64*) (A), (ATOMIC_I64*) (B), (C))
 #endif
 
 #ifndef MY_MEMORY_ORDER_SEQ_CST
--- a/storage/perfschema/pfs_atomic.h
+++ b/storage/perfschema/pfs_atomic.h
@@ -41,7 +41,7 @@ public:
   }
 
   /** Atomic load. */
-  static inline int64 load_64(int64 *ptr)
+  static inline int64 load_64(ATOMIC_I64 *ptr)
   {
     return my_atomic_load64(ptr);
   }
@@ -53,9 +53,9 @@ public:
   }
 
   /** Atomic load. */
-  static inline uint64 load_u64(uint64 *ptr)
+  static inline uint64 load_u64(ATOMIC_U64 *ptr)
   {
-    return (uint64) my_atomic_load64((int64*) ptr);
+    return (uint64) my_atomic_load64((ATOMIC_I64*) ptr);
   }
 
   /** Atomic store. */
@@ -65,7 +65,7 @@ public:
   }
 
   /** Atomic store. */
-  static inline void store_64(int64 *ptr, int64 value)
+  static inline void store_64(ATOMIC_I64 *ptr, int64 value)
   {
     my_atomic_store64(ptr, value);
   }
@@ -77,9 +77,9 @@ public:
   }
 
   /** Atomic store. */
-  static inline void store_u64(uint64 *ptr, uint64 value)
+  static inline void store_u64(ATOMIC_U64 *ptr, uint64 value)
   {
-    my_atomic_store64((int64*) ptr, (int64) value);
+    my_atomic_store64((ATOMIC_I64*) ptr, (int64) value);
   }
 
   /** Atomic add. */
@@ -89,7 +89,7 @@ public:
   }
 
   /** Atomic add. */
-  static inline int64 add_64(int64 *ptr, int64 value)
+  static inline int64 add_64(ATOMIC_I64 *ptr, int64 value)
   {
     return my_atomic_add64(ptr, value);
   }
@@ -101,9 +101,9 @@ public:
   }
 
   /** Atomic add. */
-  static inline uint64 add_u64(uint64 *ptr, uint64 value)
+  static inline uint64 add_u64(ATOMIC_U64 *ptr, uint64 value)
   {
-    return (uint64) my_atomic_add64((int64*) ptr, (int64) value);
+    return (uint64) my_atomic_add64((ATOMIC_I64*) ptr, (int64) value);
   }
 
   /** Atomic compare and swap. */
@@ -114,7 +114,7 @@ public:
   }
 
   /** Atomic compare and swap. */
-  static inline bool cas_64(int64 *ptr, int64 *old_value,
+  static inline bool cas_64(ATOMIC_I64 *ptr, ATOMIC_I64 *old_value,
                             int64 new_value)
   {
     return my_atomic_cas64(ptr, old_value, new_value);
@@ -129,10 +129,10 @@ public:
   }
 
   /** Atomic compare and swap. */
-  static inline bool cas_u64(uint64 *ptr, uint64 *old_value,
+  static inline bool cas_u64(ATOMIC_U64 *ptr, ATOMIC_U64 *old_value,
                              uint64 new_value)
   {
-    return my_atomic_cas64((int64*) ptr, (int64*) old_value,
+    return my_atomic_cas64((ATOMIC_I64*) ptr, (ATOMIC_I64*) old_value,
                             (uint64) new_value);
   }
 };
--- a/sql/sql_class.h
+++ b/sql/sql_class.h
@@ -1049,7 +1049,7 @@ static inline void update_global_memory_
                       (longlong) global_status_var.global_memory_used,
                       size));
   // workaround for gcc 4.2.4-1ubuntu4 -fPIE (from DEB_BUILD_HARDENING=1)
-  int64 volatile * volatile ptr= &global_status_var.global_memory_used;
+  ATOMIC_I64 volatile * volatile ptr= &global_status_var.global_memory_used;
   my_atomic_add64_explicit(ptr, size, MY_MEMORY_ORDER_RELAXED);
 }
 
--- a/storage/innobase/include/srv0mon.h
+++ b/storage/innobase/include/srv0mon.h
@@ -49,7 +49,7 @@ enum monitor_running_status {
 typedef enum monitor_running_status	monitor_running_t;
 
 /** Monitor counter value type */
-typedef	int64_t				mon_type_t;
+typedef	ATOMIC_I64			mon_type_t;
 
 /** Two monitor structures are defined in this file. One is
 "monitor_value_t" which contains dynamic counter values for each
@@ -568,7 +568,7 @@ Use MONITOR_INC if appropriate mutex pro
 	if (enabled) {							\
 		ib_uint64_t	value;					\
 		value  = my_atomic_add64_explicit(			\
-			(int64*) &MONITOR_VALUE(monitor), 1,		\
+			(ATOMIC_I64*) &MONITOR_VALUE(monitor), 1,	\
 			MY_MEMORY_ORDER_RELAXED) + 1;			\
 		/* Note: This is not 100% accurate because of the	\
 		inherent race, we ignore it due to performance. */	\
@@ -585,7 +585,7 @@ Use MONITOR_DEC if appropriate mutex pro
 	if (enabled) {							\
 		ib_uint64_t	value;					\
 		value = my_atomic_add64_explicit(			\
-			(int64*) &MONITOR_VALUE(monitor), -1,		\
+			(ATOMIC_I64*) &MONITOR_VALUE(monitor), -1,	\
 			MY_MEMORY_ORDER_RELAXED) - 1;			\
 		/* Note: This is not 100% accurate because of the	\
 		inherent race, we ignore it due to performance. */	\