use __cxxabiv1::__cxa_thread_atexit instead of __cxa_thread_atexit_impl

Author: jiayifeng

multipy/runtime/loader.cpp

@@ -50,6 +50,7 @@
 #include <climits>
 #include <cstdint>
 #include <cstring>
+#include <cxxabi.h>
 #include <functional>
 #include <iostream>
 #include <sstream>
@@ -244,9 +245,6 @@ struct EH_Frame_HDR {
 // with the module_id and offset.
 extern "C" void* __tls_get_addr(void*);
 
-extern "C" int
-__cxa_thread_atexit_impl(void (*dtor)(void*), void* obj, void* dso_symbol);
-
 // This object performs TLS emulation for modules not loaded by dlopen.
 // Normally modules have a module_id that is used as a key in libc for the
 // thread local data for that module. However, there is no public API for
@@ -987,7 +985,7 @@ struct __attribute__((visibility("hidden"))) CustomLibraryImpl
         return (Elf64_Addr)local__tls_get_addr;
       }
       if (strcmp(sym_name, "__cxa_thread_atexit") == 0) {
-        return (Elf64_Addr)__cxa_thread_atexit_impl;
+        return (Elf64_Addr)__cxxabiv1::__cxa_thread_atexit;
       }
     }
 
@@ -1242,7 +1240,7 @@ struct __attribute__((visibility("hidden"))) CustomLibraryImpl
     void* start = pthread_getspecific(tls_key_);
     if (!start) {
       start = malloc(tls_mem_size_);
-      __cxa_thread_atexit_impl(free, start, &__dso_handle);
+      __cxxabiv1::__cxa_thread_atexit(free, start, &__dso_handle);
       memcpy(start, tls_initalization_image_, tls_file_size_);
       memset(
           (void*)((const char*)start + tls_file_size_),