I'm writing a Lua API binding and I have a problem regarding the interaction with the garbage collector. The situation is rather canonical: a particular C data type, the Lua state, is used as argument in all the C functions of the API. A pointer to a lua_State is wrapped inside an OCaml custom block, in the very same way presented in the official documentation (in the ncurses example). Like the WINDOW* example, the lua_State is allocated via caml_stat_alloc and the resulting pointer is wrapped in a value obtained by caml_alloc_custom using a macro:

#define lua_State_val(L) (*((lua_State **) Data_custom_val(L))) /* also l-value */
... ... ...
lua_State *L = lua_newstate(custom_alloc, NULL); // the actual allocation made by caml_stat_resize
... ... ...
v_L = caml_alloc_custom(&lua_State_ops, sizeof(lua_State *), 1, 10);
lua_State_val(v_L) = L;
CAMLreturn(v_L);

So far so good.

The problem is that, for several good reasons, I need a copy, or a reference, to the OCaml value representing the lua_State (v_L in the code above) inside the Lua state (I mean the C data structure). This is possible because the Lua API provides for a way to bind a user data inside the state. So I wrote:

typedef struct ocaml_data
{
value state_value;
value panic_callback;
} ocaml_data;

CAMLprim
value luaL_newstate__stub (value unit)
{
   CAMLparam1(unit);
   CAMLlocal1(v_L);

   value *default_panic_v = caml_named_value("default_panic");

   /* create a fresh new Lua state */
   lua_State *L = lua_newstate(custom_alloc, NULL);
   lua_atpanic(L, &default_panic);

   /* alloc space for the register entry */
   ocaml_data *data = (ocaml_data*)caml_stat_alloc(sizeof(ocaml_data));
   caml_register_global_root(&(data->panic_callback));
   data->panic_callback = *default_panic_v;

   /* create a new Lua table for binding informations */
   set_ocaml_data(L, data); // puts "data" inside L

   /* wrap the lua_State* in a custom object */
   v_L = caml_alloc_custom(&lua_State_ops, sizeof(lua_State *), 1, 10);
   lua_State_val(v_L) = L;
   data->state_value = v_L; // also v_L inside L but BIG PROBLEM HERE!!!

   /* return the lua_State value */
   CAMLreturn(v_L);
}

The problem here is that I'm storing an OCaml value (v_L) inside a malloc-ed area. Result: segfault.

Is there a safe way to store a reference to a value outside the heap?

As a temporary workaround I removed the "value state_value" field from the ocaml_data struct, replacing it with a reference counter:

typedef struct ocaml_data
{
   value panic_callback;
   int ref_counter;
} ocaml_data;

and the previous "luaL_newstate__stub" function sets the counter to 1:

... ... ...
   /* alloc space for the register entry */
   ocaml_data *data = (ocaml_data*)caml_stat_alloc(sizeof(ocaml_data));
   caml_register_global_root(&(data->panic_callback));
   data->panic_callback = *default_panic_v;
   data->ref_counter = 1;
... ... ...

In other parts of the code, where I have the original lua_State pointer, but I need the corresponding OCaml value, and where I previously used the retrieve it from the lua_State, now I create *another* OCaml value with the same lua_State, incrementing the reference counter, for example:

static int panic_wrapper(lua_State *L)
{
   CAMLlocal1(v_L);
   ocaml_data *data = get_ocaml_data(L);

   /* wrap the lua_State* in a custom object */
   v_L = caml_alloc_custom(&lua_State_ops, sizeof(lua_State *), 1, 10);
   lua_State_val(v_L) = L;
   data->ref_counter++;

   return Int_val(caml_callback(data->panic_callback, v_L));
}

In the finalization function I free() the C data structures only if ref_counter reaches 0:

static void finalize_lua_State(value L)
{
   lua_State *state = lua_State_val(L);
   ocaml_data *data = get_ocaml_data(state);

   if (data->ref_counter == 1)
   {
   caml_remove_global_root(&(data->panic_callback));
   caml_stat_free(data);
   lua_close(state); // this calls free()
   }
   else
   {
   data->ref_counter--;
   }
}

What I don't like here is that several OCaml values, representing the same C data structure, are simultaneously present in the program, and the reference counting is not exactly the best way to collect memory garbage.

Any ideas or suggestions?

--
Paolo