* variable.c: Make autoload thread-safe. See #921.

  What's the problem?
    autoload is thread unsafe. When we define a constant to be
    autoloaded, we expect the constant construction is invariant. But
    current autoload implementation allows other threads to access the
    constant while the first thread is loading a file.

  What's happening inside?
    The current implementation uses Qundef as a marker of autoload in
    Constant table. Once the first thread find Qundef as a value at
    constant lookup, it starts loading a defined feature. Generally a
    loaded file overrides the Qundef in Constant table by module/class
    declaration at very beginning lines of the file, so other threads
    can see the new Module/Class object before feature loading is
    finished. It breaks invariant construction.

  How to solve?
    To ensure invariant constant construction, we need to override
    Qundef with defined Object after the feature loading. For keeping
    Qundef in Constant table, I expanded autoload_data struct in
    Module to have a slot for keeping the defined object while feature
    loading. And changed Module's constant lookup/update logic a
    little so that the slot is only visible from the thread which
    invokes feature loading. (== the first thread which accessed the
    autoload constant)

  Evaluation?
    All test passes (bootstrap test, test-all and RubySpec) and added
    8 tests for threading behavior. Extra logics are executed only
    when Qundef is found, so no perf drop should happen except
    autoloading.

* variable.c (rb_autoload): Prepare new autoload_data struct.

* variable.c (rb_autoload_load): Load feature and update Constant
  table after feature loading is finished. 

* variable.c (rb_const_get_0): When the fetched constant is under
  autoloading, it returns the object only for the thread which starts
  autoloading.

* variable.c (rb_const_defined_0): Ditto.

* variable.c (rb_const_set): When the specified constant is under
  autoloading, it sets the object only for the thread which starts
  autoloading. Otherwise, simply overrides Qundef with constant
  override warning.

* vm_insnhelper.c (vm_get_ev_const): Apply same change as
  rb_const_get_0 in variable.c.

* test/ruby/test_autoload.rb: Added tests for threading behavior.


git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@33078 b2dd03c8-39d4-4d8f-98ff-823fe69b080e

1 files changed, 163 insertions, 31 deletions

diff --git a/variable.c b/variable.c
index 6ddbd71390..6b3f814a71 100644
--- a/variable.c
+++ b/variable.c
@@ -1445,12 +1445,63 @@ static const rb_data_type_t autoload_data_type = {
 #define check_autoload_table(av) \
     (struct st_table *)rb_check_typeddata((av), &autoload_data_type)
 
+static VALUE
+autoload_data(VALUE mod, ID id)
+{
+    struct st_table *tbl;
+    st_data_t val;
+
+    if (!st_lookup(RCLASS_IV_TBL(mod), autoload, &val) ||
+	    !(tbl = check_autoload_table((VALUE)val)) || !st_lookup(tbl, (st_data_t)id, &val)) {
+	return 0;
+    }
+    return (VALUE)val;
+}
+
+struct autoload_data_i {
+    VALUE feature;
+    int safe_level;
+    VALUE thread;
+    VALUE value;
+};
+
+static void
+autoload_i_mark(void *ptr)
+{
+    struct autoload_data_i *p = ptr;
+    rb_gc_mark(p->feature);
+    rb_gc_mark(p->thread);
+    rb_gc_mark(p->value);
+}
+
+static void
+autoload_i_free(void *ptr)
+{
+    struct autoload_data_i *p = ptr;
+    xfree(p);
+}
+
+static size_t
+autoload_i_memsize(const void *ptr)
+{
+    return sizeof(struct autoload_data_i);
+}
+
+static const rb_data_type_t autoload_data_i_type = {
+    "autoload_i",
+    {autoload_i_mark, autoload_i_free, autoload_i_memsize,},
+};
+
+#define check_autoload_data(av) \
+    (struct autoload_data_i *)rb_check_typeddata((av), &autoload_data_i_type)
+
 void
 rb_autoload(VALUE mod, ID id, const char *file)
 {
     st_data_t av;
-    VALUE fn;
+    VALUE ad, fn;
     struct st_table *tbl;
+    struct autoload_data_i *ele;
 
     if (!rb_is_const_id(id)) {
 	rb_raise(rb_eNameError, "autoload must be constant name: %s", rb_id2name(id));
@@ -1473,13 +1524,20 @@ rb_autoload(VALUE mod, ID id, const char *file)
 	st_add_direct(tbl, (st_data_t)autoload, av);
 	DATA_PTR(av) = tbl = st_init_numtable();
     }
+    ad = TypedData_Wrap_Struct(0, &autoload_data_i_type, 0);
+    st_insert(tbl, (st_data_t)id, (st_data_t)ad);
+    DATA_PTR(ad) = ele = ALLOC(struct autoload_data_i);
+
     fn = rb_str_new2(file);
     FL_UNSET(fn, FL_TAINT);
     OBJ_FREEZE(fn);
-    st_insert(tbl, (st_data_t)id, (st_data_t)rb_node_newnode(NODE_MEMO, fn, rb_safe_level(), 0));
+    ele->feature = fn;
+    ele->safe_level = rb_safe_level();
+    ele->thread = Qnil;
+    ele->value = Qundef;
 }
 
-static NODE*
+static void
 autoload_delete(VALUE mod, ID id)
 {
     st_data_t val, load = 0, n = id;
@@ -1498,8 +1556,6 @@ autoload_delete(VALUE mod, ID id)
 	    st_delete(RCLASS_IV_TBL(mod), &n, &val);
 	}
     }
-
-    return (NODE *)load;
 }
 
 static VALUE
@@ -1516,22 +1572,18 @@ reset_safe(VALUE safe)
     return safe;
 }
 
-static NODE *
-autoload_node(VALUE mod, ID id, const char **loadingpath)
+static VALUE
+check_autoload_required(VALUE mod, ID id, const char **loadingpath)
 {
-    VALUE file;
-    struct st_table *tbl;
-    st_data_t val;
-    NODE *load;
+    VALUE file, load;
+    struct autoload_data_i *ele;
     const char *loading;
     int safe;
 
-    if (!st_lookup(RCLASS_IV_TBL(mod), autoload, &val) ||
-	!(tbl = check_autoload_table((VALUE)val)) || !st_lookup(tbl, (st_data_t)id, &val)) {
+    if (!(load = autoload_data(mod, id)) || !(ele = check_autoload_data(load))) {
 	return 0;
     }
-    load = (NODE *)val;
-    file = load->nd_lit;
+    file = ele->feature;
     Check_Type(file, T_STRING);
     if (!RSTRING_PTR(file) || !*RSTRING_PTR(file)) {
 	rb_raise(rb_eArgError, "empty file name");
@@ -1550,7 +1602,7 @@ autoload_node(VALUE mod, ID id, const char **loadingpath)
 }
 
 static int
-autoload_node_id(VALUE mod, ID id)
+autoload_defined_p(VALUE mod, ID id)
 {
     struct st_table *tbl = RCLASS_CONST_TBL(mod);
     st_data_t val;
@@ -1561,42 +1613,109 @@ autoload_node_id(VALUE mod, ID id)
     return 1;
 }
 
+int
+rb_autoloading_value(VALUE mod, ID id, VALUE* value)
+{
+    VALUE load;
+    struct autoload_data_i *ele;
+
+    if (!(load = autoload_data(mod, id)) || !(ele = check_autoload_data(load))) {
+	return 0;
+    }
+    if (ele->thread == rb_thread_current()) {
+	if (ele->value != Qundef) {
+    	    if (value) {
+    		*value = ele->value;
+    	    }
+	    return 1;
+	}
+    }
+    return 0;
+}
+
+struct autoload_const_set_args {
+    VALUE mod;
+    ID id;
+    VALUE value;
+};
+
+static void
+autoload_const_set(struct autoload_const_set_args* args)
+{
+    autoload_delete(args->mod, args->id);
+    rb_const_set(args->mod, args->id, args->value);
+}
+
+static VALUE
+autoload_require(struct autoload_data_i *ele)
+{
+    return rb_require_safe(ele->feature, ele->safe_level);
+}
+
 VALUE
 rb_autoload_load(VALUE mod, ID id)
 {
-    VALUE file;
-    NODE *load;
+    VALUE load, result;
     const char *loading = 0, *src;
+    struct autoload_data_i *ele;
+    int state = 0;
 
-    if (!autoload_node_id(mod, id)) return Qfalse;
-    load = autoload_node(mod, id, &loading);
+    if (!autoload_defined_p(mod, id)) return Qfalse;
+    load = check_autoload_required(mod, id, &loading);
     if (!load) return Qfalse;
     src = rb_sourcefile();
     if (src && loading && strcmp(src, loading) == 0) return Qfalse;
-    file = load->nd_lit;
-    return rb_require_safe(file, (int)load->nd_nth);
+
+    /* set ele->thread for a marker of autoloading thread */
+    if (!(ele = check_autoload_data(load))) {
+	return Qfalse;
+    }
+    if (ele->thread == Qnil) {
+	ele->thread = rb_thread_current();
+    }
+    /* autoload_data_i can be deleted by another thread while require */
+    RB_GC_GUARD(load);
+    result = rb_protect((VALUE(*)(VALUE))autoload_require, (VALUE)ele, &state);
+    if (ele->thread == rb_thread_current()) {
+	ele->thread = Qnil;
+    }
+    if (state) rb_jump_tag(state);
+
+    if (RTEST(result)) {
+	/* At the last, move a value defined in autoload to constant table */
+	if (ele->value != Qundef) {
+	    int safe_backup;
+	    struct autoload_const_set_args args;
+	    args.mod = mod;
+	    args.id = id;
+	    args.value = ele->value;
+	    safe_backup = rb_safe_level();
+	    rb_set_safe_level_force(ele->safe_level);
+	    rb_ensure((VALUE(*)(VALUE))autoload_const_set, (VALUE)&args, reset_safe, (VALUE)safe_backup);
+	}
+    }
+    return result;
 }
 
 VALUE
 rb_autoload_p(VALUE mod, ID id)
 {
-    VALUE file;
-    NODE *load;
-    const char *loading = 0;
+    VALUE load;
+    struct autoload_data_i *ele;
 
-    while (!autoload_node_id(mod, id)) {
+    while (!autoload_defined_p(mod, id)) {
 	mod = RCLASS_SUPER(mod);
 	if (!mod) return Qnil;
     }
-    load = autoload_node(mod, id, &loading);
+    load = check_autoload_required(mod, id, 0);
     if (!load) return Qnil;
-    return load && (file = load->nd_lit) ? file : Qnil;
+    return (ele = check_autoload_data(load)) ? ele->feature : Qnil;
 }
 
 static VALUE
 rb_const_get_0(VALUE klass, ID id, int exclude, int recurse, int visibility)
 {
-    VALUE value, tmp;
+    VALUE value, tmp, av;
     int mod_retry = 0;
 
     tmp = klass;
@@ -1613,6 +1732,7 @@ rb_const_get_0(VALUE klass, ID id, int exclude, int recurse, int visibility)
 	    if (value == Qundef) {
 		if (am == tmp) break;
 		am = tmp;
+		if (rb_autoloading_value(tmp, id, &av)) return av;
 		rb_autoload_load(tmp, id);
 		continue;
 	    }
@@ -1843,7 +1963,7 @@ rb_const_defined_0(VALUE klass, ID id, int exclude, int recurse, int visibility)
 	    if (visibility && ce->flag == CONST_PRIVATE) {
 		return (int)Qfalse;
 	    }
-	    if (ce->value == Qundef && !autoload_node(tmp, id, 0))
+	    if (ce->value == Qundef && !check_autoload_required(tmp, id, 0) && !rb_autoloading_value(tmp, id, 0))
 		return (int)Qfalse;
 	    return (int)Qtrue;
 	}
@@ -1922,8 +2042,20 @@ rb_const_set(VALUE klass, ID id, VALUE val)
 
 	if (st_lookup(RCLASS_CONST_TBL(klass), (st_data_t)id, &value)) {
 	    rb_const_entry_t *ce = (rb_const_entry_t*)value;
-	    if (ce->value == Qundef)
+	    if (ce->value == Qundef) {
+		VALUE load;
+		struct autoload_data_i *ele;
+
+		load = autoload_data(klass, id);
+		/* for autoloading thread, keep the defined value to autoloading storage */
+		if (load && (ele = check_autoload_data(load)) && (ele->thread == rb_thread_current())) {
+		    rb_vm_change_state();
+		    ele->value = val;
+		    return;
+		}
+		/* otherwise, allow to override */
 		autoload_delete(klass, id);
+	    }
 	    else {
 		visibility = ce->flag;
 		rb_warn("already initialized constant %s", rb_id2name(id));