userland/arch/aarch64/inline_asm/reg_var.c: use 64 bit variables

32-bit ones likely copy paste error from coming from arm v7.

Also create userland/arch/aarch64/inline_asm/int_32.c:

Also create aarch64_ldaxr_stlxr.cpp and start documenting LDAXR and STLXR.

userland/arch/aarch64/inline_asm/inc_32.c

@@ -0,0 +1,15 @@
+/* https://cirosantilli.com/linux-kernel-module-cheat#gcc-inline-assembly */
+
+#include <assert.h>
+#include <inttypes.h>
+
+int main(void) {
+    uint32_t io = 1;
+    __asm__ (
+        "add %w[io], %w[io], 1;"
+        : [io] "+r" (io)
+        :
+        :
+    );
+    assert(io == 2);
+}

userland/arch/aarch64/inline_asm/reg_var.c

@@ -4,10 +4,10 @@
 #include <inttypes.h>
 
 int main(void) {
-    register uint32_t x0 __asm__ ("x0");
-    register uint32_t x1 __asm__ ("x1");
-    uint32_t new_x0;
-    uint32_t new_x1;
+    register uint64_t x0 __asm__ ("x0");
+    register uint64_t x1 __asm__ ("x1");
+    uint64_t new_x0;
+    uint64_t new_x1;
     {
         x0 = 1;
         x1 = 2;

userland/cpp/atomic/aarch64_ldaxr_stlxr.cpp

@@ -0,0 +1,2 @@
+#define LKMC_USERLAND_ATOMIC_LDAXR_STLXR 1
+#include "main.hpp"

userland/cpp/atomic/main.hpp

@@ -51,11 +51,28 @@ void threadMain() {
             :
             :
         );
+#elif LKMC_USERLAND_ATOMIC_LDAXR_STLXR
+        // Was used by std::atomic before LDADD was added
+        uint64_t scratch64;
+        uint64_t scratch32;
+        __asm__ __volatile__ (
+            "1:"
+            "ldaxr %[scratch64], [%[addr]];"
+            "add   %[scratch64], %[scratch64], 1;"
+            "stlxr %w[scratch32], %[scratch64], [%[addr]];"
+            "cbnz  %w[scratch32], 1b;"
+            : "=m" (global), // indicate that global is modified
+              "+g" (i), // to prevent loop unrolling
+              [scratch64] "=&r" (scratch64),
+              [scratch32] "=&r" (scratch32)
+            : [addr] "r" (&global)
+            :
+        );
 #elif LKMC_USERLAND_ATOMIC_AARCH64_LDADD
         // https://cirosantilli.com/linux-kernel-module-cheat#arm-lse
         __asm__ __volatile__ (
             "ldadd %[inc], xzr, [%[addr]];"
-            : "=m" (global),
+            : "=m" (global), // indicate that global is modified
               "+g" (i) // to prevent loop unrolling
             : [inc] "r" (1),
               [addr] "r" (&global)