[builtins] emutls cleanup: determine header size using sizeof

[rprichard]

Summary

Also add a few post-#else/#endif comments

[echristo]

LGTM.

lib/builtins/emutls.c

 static __inline void emutls_setspecific(emutls_address_array *value) {
     pthread_setspecific(emutls_pthread_key, (void*) value);
 }
 
 static __inline emutls_address_array* emutls_getspecific() {
     return (emutls_address_array*) pthread_getspecific(emutls_pthread_key);
 }
 
-#else
+#else /* _WIN32 */
 
 #include <windows.h>
 #include <malloc.h>
 #include <stdio.h>
 #include <assert.h>
 
 static LPCRITICAL_SECTION emutls_mutex;
 static DWORD emutls_tls_index = TLS_OUT_OF_INDEXES;

 #endif
 }
 
 static __inline void __atomic_store_n(void *ptr, uintptr_t val, unsigned type) {
     assert(type == __ATOMIC_RELEASE);
     InterlockedExchangePointer((void *volatile *)ptr, (void *)val);
 }
 
-#endif
+#endif /* __ATOMIC_RELEASE */
 
 #pragma warning (pop)
 
-#endif
+#endif /* _WIN32 */
 
 static size_t emutls_num_object = 0;  /* number of allocated TLS objects */
 
 /* Free the allocated TLS data
  */
 static void emutls_shutdown(emutls_address_array *array) {
     if (array) {
         uintptr_t i;
static __inline void emutls_check_array_set_size(emutls_address_array *array,
     array->size = size;
     emutls_setspecific(array);
 }
 
 /* Returns the new 'data' array size, number of elements,
  * which must be no smaller than the given index.
  */
 static __inline uintptr_t emutls_new_data_array_size(uintptr_t index) {
-   /* Need to allocate emutls_address_array with one extra slot
-    * to store the data array size.
+   /* Need to allocate emutls_address_array with extra slots
+    * to store the header.
     * Round up the emutls_address_array size to multiple of 16.
     */
-    return ((index + 1 + 15) & ~((uintptr_t)15)) - 1;
+    uintptr_t header_words = sizeof(emutls_address_array) / sizeof(void *);
+    return ((index + header_words + 15) & ~((uintptr_t)15)) - header_words;
 }
 
 /* Returns the size in bytes required for an emutls_address_array with
  * N number of elements for data field.
  */
 static __inline uintptr_t emutls_asize(uintptr_t N) {
     return N * sizeof(void *) + sizeof(emutls_address_array);
 }