fix @invokelatest performance regression

base/reflection.jl

@@ -1269,16 +1269,17 @@ macro invoke(ex)
     return esc(out)
 end
 
-apply_gr(gr::GlobalRef, @nospecialize args...) = getglobal(gr.mod, gr.name)(args...)
-apply_gr_kw(@nospecialize(kwargs::NamedTuple), gr::GlobalRef, @nospecialize args...) = Core.kwcall(kwargs, getglobal(gr.mod, gr.name), args...)
+getglobalref(gr::GlobalRef, world::UInt) = ccall(:jl_eval_globalref, Any, (Any, UInt), gr, world)
 
-function invokelatest_gr(gr::GlobalRef, @nospecialize args...; kwargs...)
+function invokelatest_gr(gr::GlobalRef, args...; kwargs...)
     @inline
     kwargs = merge(NamedTuple(), kwargs)
+    world = get_world_counter()
+    f = getglobalref(gr, world)
     if isempty(kwargs)
-        return invokelatest(apply_gr, gr, args...)
+        return invoke_in_world(world, f, args...)
     end
-    return invokelatest(apply_gr_kw, kwargs, gr, args...)
+    return invoke_in_world(world, Core.kwcall, kwargs, f, args...)
 end
 
 """

src/ast.c

@@ -1328,7 +1328,7 @@ JL_DLLEXPORT jl_value_t *jl_lower(jl_value_t *expr, jl_module_t *inmodule,
 {
     jl_value_t *core_lower = NULL;
     if (jl_core_module)
-        core_lower = jl_get_global_value(jl_core_module, jl_symbol("_lower"));
+        core_lower = jl_get_global_value(jl_core_module, jl_symbol("_lower"), jl_current_task->world_age);
     if (!core_lower || core_lower == jl_nothing) {
         return jl_fl_lower(expr, inmodule, filename, line, world, warn);
     }

src/builtins.c

@@ -1340,7 +1340,7 @@ JL_CALLABLE(jl_f_getglobal)
         jl_atomic_error("getglobal: module binding cannot be read non-atomically");
     else if (order >= jl_memory_order_seq_cst)
         jl_fence();
-    jl_value_t *v = jl_eval_global_var(mod, sym); // relaxed load
+    jl_value_t *v = jl_eval_global_var(mod, sym, jl_current_task->world_age); // relaxed load
     if (order >= jl_memory_order_acquire)
         jl_fence();
     return v;

src/gf.c

@@ -512,13 +512,13 @@ JL_DLLEXPORT jl_code_info_t *jl_gdbcodetyped1(jl_method_instance_t *mi, size_t w
     ct->world_age = jl_typeinf_world;
     jl_value_t **fargs;
     JL_GC_PUSHARGS(fargs, 4);
-    jl_module_t *CC = (jl_module_t*)jl_get_global_value(jl_core_module, jl_symbol("Compiler"));
+    jl_module_t *CC = (jl_module_t*)jl_get_global_value(jl_core_module, jl_symbol("Compiler"), ct->world_age);
     if (CC != NULL && jl_is_module(CC)) {
         JL_GC_PROMISE_ROOTED(CC);
-        fargs[0] = jl_get_global_value(CC, jl_symbol("NativeInterpreter"));;
+        fargs[0] = jl_get_global_value(CC, jl_symbol("NativeInterpreter"), ct->world_age);
         fargs[1] = jl_box_ulong(world);
         fargs[1] = jl_apply(fargs, 2);
-        fargs[0] = jl_get_global_value(CC, jl_symbol("typeinf_code"));
+        fargs[0] = jl_get_global_value(CC, jl_symbol("typeinf_code"), ct->world_age);
         fargs[2] = (jl_value_t*)mi;
         fargs[3] = jl_true;
         ci = (jl_code_info_t*)jl_apply(fargs, 4);

src/init.c

@@ -249,7 +249,7 @@ JL_DLLEXPORT void jl_atexit_hook(int exitcode) JL_NOTSAFEPOINT_ENTER
     if (jl_base_module) {
         size_t last_age = ct->world_age;
         ct->world_age = jl_get_world_counter();
-        jl_value_t *f = jl_get_global_value(jl_base_module, jl_symbol("_atexit"));
+        jl_value_t *f = jl_get_global_value(jl_base_module, jl_symbol("_atexit"), ct->world_age);
         if (f != NULL) {
             jl_value_t **fargs;
             JL_GC_PUSHARGS(fargs, 2);
@@ -357,7 +357,7 @@ JL_DLLEXPORT void jl_postoutput_hook(void)
         jl_task_t *ct = jl_get_current_task();
         size_t last_age = ct->world_age;
         ct->world_age = jl_get_world_counter();
-        jl_value_t *f = jl_get_global_value(jl_base_module, jl_symbol("_postoutput"));
+        jl_value_t *f = jl_get_global_value(jl_base_module, jl_symbol("_postoutput"), ct->world_age);
         if (f != NULL) {
             JL_TRY {
                 JL_GC_PUSH1(&f);

src/interpreter.c

@@ -162,18 +162,18 @@ static jl_value_t *do_invoke(jl_value_t **args, size_t nargs, interpreter_state
 }
 
 // get the global (throwing if null) in the current world
-jl_value_t *jl_eval_global_var(jl_module_t *m, jl_sym_t *e)
+jl_value_t *jl_eval_global_var(jl_module_t *m, jl_sym_t *e, size_t world)
 {
-    jl_value_t *v = jl_get_global_value(m, e);
+    jl_value_t *v = jl_get_global_value(m, e, world);
     if (v == NULL)
         jl_undefined_var_error(e, (jl_value_t*)m);
     return v;
 }
 
 // get the global (throwing if null) in the current world, optimized
-jl_value_t *jl_eval_globalref(jl_globalref_t *g)
+jl_value_t *jl_eval_globalref(jl_globalref_t *g, size_t world)
 {
-    jl_value_t *v = jl_get_globalref_value(g);
+    jl_value_t *v = jl_get_globalref_value(g, world);
     if (v == NULL)
         jl_undefined_var_error(g->name, (jl_value_t*)g->mod);
     return v;
@@ -218,10 +218,10 @@ static jl_value_t *eval_value(jl_value_t *e, interpreter_state *s)
         return jl_quotenode_value(e);
     }
     if (jl_is_globalref(e)) {
-        return jl_eval_globalref((jl_globalref_t*)e);
+        return jl_eval_globalref((jl_globalref_t*)e, jl_current_task->world_age);
     }
     if (jl_is_symbol(e)) {  // bare symbols appear in toplevel exprs not wrapped in `thunk`
-        return jl_eval_global_var(s->module, (jl_sym_t*)e);
+        return jl_eval_global_var(s->module, (jl_sym_t*)e, jl_current_task->world_age);
     }
     if (jl_is_pinode(e)) {
         jl_value_t *val = eval_value(jl_fieldref_noalloc(e, 0), s);

src/jl_uv.c

@@ -162,7 +162,8 @@ static void jl_uv_call_close_callback(jl_value_t *val)
     JL_GC_PUSHARGS(args, 2); // val is "rooted" in the finalizer list only right now
     args[0] = jl_eval_global_var(
             jl_base_relative_to(((jl_datatype_t*)jl_typeof(val))->name->module),
-            jl_symbol("_uv_hook_close")); // topmod(typeof(val))._uv_hook_close
+            jl_symbol("_uv_hook_close"),
+            jl_current_task->world_age); // topmod(typeof(val))._uv_hook_close
     args[1] = val;
     jl_apply(args, 2); // TODO: wrap in try-catch?
     JL_GC_POP();

src/jlapi.c

@@ -955,7 +955,7 @@ static NOINLINE int true_main(int argc, char *argv[])
     ct->world_age = jl_get_world_counter();
 
     jl_function_t *start_client = jl_base_module ?
-        (jl_function_t*)jl_get_global_value(jl_base_module, jl_symbol("_start")) : NULL;
+        (jl_function_t*)jl_get_global_value(jl_base_module, jl_symbol("_start"), ct->world_age) : NULL;
 
     if (start_client) {
         int ret = 1;

src/jltypes.c

@@ -3287,6 +3287,7 @@ void jl_init_types(void) JL_GC_DISABLED
                         jl_perm_symsvec(3, "mod", "name", "binding"),
                         jl_svec(3, jl_module_type, jl_symbol_type, jl_binding_type),
                         jl_emptysvec, 0, 0, 3);
+    jl_globalref_type->name->mayinlinealloc = 0; // not at all worthwhile, since the only constructor returns a boxed object
 
     jl_core_module = jl_new_module(jl_symbol("Core"), NULL);
 

src/julia.h

@@ -2094,9 +2094,7 @@ JL_DLLEXPORT jl_value_t *jl_get_existing_strong_gf(jl_binding_t *b JL_PROPAGATES
 JL_DLLEXPORT int jl_boundp(jl_module_t *m, jl_sym_t *var, int allow_import);
 JL_DLLEXPORT int jl_is_const(jl_module_t *m, jl_sym_t *var);
 JL_DLLEXPORT int jl_globalref_is_const(jl_globalref_t *gr);
-JL_DLLEXPORT jl_value_t *jl_get_globalref_value(jl_globalref_t *gr);
 JL_DLLEXPORT jl_value_t *jl_get_global(jl_module_t *m JL_PROPAGATES_ROOT, jl_sym_t *var);
-JL_DLLEXPORT jl_value_t *jl_get_global_value(jl_module_t *m, jl_sym_t *var);
 JL_DLLEXPORT void jl_set_global(jl_module_t *m JL_ROOTING_ARGUMENT, jl_sym_t *var, jl_value_t *val JL_ROOTED_ARGUMENT);
 JL_DLLEXPORT void jl_set_const(jl_module_t *m JL_ROOTING_ARGUMENT, jl_sym_t *var, jl_value_t *val JL_ROOTED_ARGUMENT);
 void jl_set_initial_const(jl_module_t *m JL_ROOTING_ARGUMENT, jl_sym_t *var, jl_value_t *val JL_ROOTED_ARGUMENT, int exported);

src/julia_internal.h

@@ -901,7 +901,10 @@ STATIC_INLINE size_t module_usings_max(jl_module_t *m) JL_NOTSAFEPOINT {
 
 JL_DLLEXPORT jl_sym_t *jl_module_name(jl_module_t *m) JL_NOTSAFEPOINT;
 void jl_add_scanned_method(jl_module_t *m, jl_method_t *meth);
-jl_value_t *jl_eval_global_var(jl_module_t *m JL_PROPAGATES_ROOT, jl_sym_t *e);
+jl_value_t *jl_eval_global_var(jl_module_t *m JL_PROPAGATES_ROOT, jl_sym_t *e, size_t world);
+JL_DLLEXPORT jl_value_t *jl_eval_globalref(jl_globalref_t *g, size_t world);
+jl_value_t *jl_get_globalref_value(jl_globalref_t *gr, size_t world);
+jl_value_t *jl_get_global_value(jl_module_t *m, jl_sym_t *var, size_t world);
 jl_value_t *jl_interpret_opaque_closure(jl_opaque_closure_t *clos, jl_value_t **args, size_t nargs);
 jl_value_t *jl_interpret_toplevel_thunk(jl_module_t *m, jl_code_info_t *src);
 jl_value_t *jl_interpret_toplevel_expr_in(jl_module_t *m, jl_value_t *e,

src/module.c

@@ -1540,20 +1540,20 @@ JL_DLLEXPORT jl_binding_t *jl_get_module_binding(jl_module_t *m, jl_sym_t *var,
 }
 
 
-// get the value (or null) in the current world
-JL_DLLEXPORT jl_value_t *jl_get_globalref_value(jl_globalref_t *gr)
+// get the value (or null) in the world
+jl_value_t *jl_get_globalref_value(jl_globalref_t *gr, size_t world)
 {
     jl_binding_t *b = gr->binding;
     if (!b)
         b = jl_get_module_binding(gr->mod, gr->name, 1);
-    return jl_get_binding_value_depwarn(b, jl_current_task->world_age);
+    return jl_get_binding_value_depwarn(b, world);
 }
 
-// get the value (or null) in the current world
-JL_DLLEXPORT jl_value_t *jl_get_global_value(jl_module_t *m, jl_sym_t *var)
+// get the value (or null) in the world
+jl_value_t *jl_get_global_value(jl_module_t *m, jl_sym_t *var, size_t world)
 {
     jl_binding_t *b = jl_get_module_binding(m, var, 1);
-    return jl_get_binding_value_depwarn(b, jl_current_task->world_age);
+    return jl_get_binding_value_depwarn(b, world);
 }
 
 // get the global (or null) in the latest world

src/precompile.c

@@ -45,8 +45,8 @@ void write_srctext(ios_t *f, jl_array_t *udeps, int64_t srctextpos) {
         size_t last_age = ct->world_age;
         ct->world_age = jl_atomic_load_acquire(&jl_world_counter);
         JL_GC_PUSH4(&deptuple, &depots, &replace_depot_func, &normalize_depots_func);
-        replace_depot_func = jl_eval_global_var(jl_base_module, jl_symbol("replace_depot_path"));
-        normalize_depots_func = jl_eval_global_var(jl_base_module, jl_symbol("normalize_depots_for_relocation"));
+        replace_depot_func = jl_eval_global_var(jl_base_module, jl_symbol("replace_depot_path"), jl_current_task->world_age);
+        normalize_depots_func = jl_eval_global_var(jl_base_module, jl_symbol("normalize_depots_for_relocation"), jl_current_task->world_age);
         depots = jl_apply(&normalize_depots_func, 1);
         jl_datatype_t *deptuple_p[5] = {jl_module_type, jl_string_type, jl_uint64_type, jl_uint32_type, jl_float64_type};
         jl_value_t *jl_deptuple_type = jl_apply_tuple_type_v((jl_value_t**)deptuple_p, 5);

src/rtutils.c

@@ -1596,10 +1596,11 @@ void jl_log(int level, jl_value_t *module, jl_value_t *group, jl_value_t *id,
             jl_value_t *msg)
 {
     jl_value_t *logmsg_func = NULL;
+    jl_task_t *ct = jl_current_task;
     if (jl_base_module) {
-        jl_value_t *corelogging = jl_get_global_value(jl_base_module, jl_symbol("CoreLogging"));
+        jl_value_t *corelogging = jl_get_global_value(jl_base_module, jl_symbol("CoreLogging"), ct->world_age);
         if (corelogging && jl_is_module(corelogging)) {
-            logmsg_func = jl_get_global_value((jl_module_t*)corelogging, jl_symbol("logmsg_shim"));
+            logmsg_func = jl_get_global_value((jl_module_t*)corelogging, jl_symbol("logmsg_shim"), ct->world_age);
         }
     }
     if (!logmsg_func) {

src/scheduler.c

@@ -331,7 +331,7 @@ void jl_task_wait_empty(void)
         jl_wait_empty_begin();
         size_t lastage = ct->world_age;
         ct->world_age = jl_atomic_load_acquire(&jl_world_counter);
-        jl_value_t *f = jl_get_global_value(jl_base_module, jl_symbol("wait"));
+        jl_value_t *f = jl_get_global_value(jl_base_module, jl_symbol("wait"), ct->world_age);
         wait_empty = ct;
         if (f) {
             JL_GC_PUSH1(&f);

src/staticdata_utils.c

@@ -544,21 +544,21 @@ static int64_t write_dependency_list(ios_t *s, jl_array_t* worklist, jl_array_t
     jl_value_t *get_compiletime_prefs_func = NULL;
     JL_GC_PUSH8(&depots, &prefs_list, &unique_func, &replace_depot_func, &normalize_depots_func, &toplevel, &prefs_hash_func, &get_compiletime_prefs_func);
 
-    jl_array_t *udeps = (jl_array_t*)jl_get_global_value(jl_base_module, jl_symbol("_require_dependencies"));
+    jl_array_t *udeps = (jl_array_t*)jl_get_global_value(jl_base_module, jl_symbol("_require_dependencies"), ct->world_age);
     *udepsp = udeps;
 
     // unique(udeps) to eliminate duplicates while preserving order:
     // we preserve order so that the topmost included .jl file comes first
     if (udeps) {
-        unique_func = jl_eval_global_var(jl_base_module, jl_symbol("unique"));
+        unique_func = jl_eval_global_var(jl_base_module, jl_symbol("unique"), ct->world_age);
         jl_value_t *uniqargs[2] = {unique_func, (jl_value_t*)udeps};
         udeps = (jl_array_t*)jl_apply(uniqargs, 2);
         *udepsp = udeps;
         JL_TYPECHK(write_dependency_list, array_any, (jl_value_t*)udeps);
     }
 
-    replace_depot_func = jl_get_global_value(jl_base_module, jl_symbol("replace_depot_path"));
-    normalize_depots_func = jl_eval_global_var(jl_base_module, jl_symbol("normalize_depots_for_relocation"));
+    replace_depot_func = jl_get_global_value(jl_base_module, jl_symbol("replace_depot_path"), ct->world_age);
+    normalize_depots_func = jl_eval_global_var(jl_base_module, jl_symbol("normalize_depots_for_relocation"), ct->world_age);
 
     depots = jl_apply(&normalize_depots_func, 1);
 
@@ -616,9 +616,9 @@ static int64_t write_dependency_list(ios_t *s, jl_array_t* worklist, jl_array_t
     // Calculate Preferences hash for current package.
     if (jl_base_module) {
         // Toplevel module is the module we're currently compiling, use it to get our preferences hash
-        toplevel = jl_get_global_value(jl_base_module, jl_symbol("__toplevel__"));
-        prefs_hash_func = jl_eval_global_var(jl_base_module, jl_symbol("get_preferences_hash"));
-        get_compiletime_prefs_func = jl_eval_global_var(jl_base_module, jl_symbol("get_compiletime_preferences"));
+        toplevel = jl_get_global_value(jl_base_module, jl_symbol("__toplevel__"), ct->world_age);
+        prefs_hash_func = jl_eval_global_var(jl_base_module, jl_symbol("get_preferences_hash"), ct->world_age);
+        get_compiletime_prefs_func = jl_eval_global_var(jl_base_module, jl_symbol("get_compiletime_preferences"), ct->world_age);
 
         if (toplevel) {
             // call get_compiletime_prefs(__toplevel__)

src/task.c

@@ -335,7 +335,7 @@ void JL_NORETURN jl_finish_task(jl_task_t *ct)
     // let the runtime know this task is dead and find a new task to run
     jl_function_t *done = jl_atomic_load_relaxed(&task_done_hook_func);
     if (done == NULL) {
-        done = (jl_function_t*)jl_get_global_value(jl_base_module, jl_symbol("task_done_hook"));
+        done = (jl_function_t*)jl_get_global_value(jl_base_module, jl_symbol("task_done_hook"), ct->world_age);
         if (done != NULL)
             jl_atomic_store_release(&task_done_hook_func, done);
     }

src/threading.c

@@ -413,7 +413,7 @@ static void jl_init_task_lock(jl_task_t *ct)
     ct->world_age = jl_get_world_counter();
     jl_function_t *done = jl_atomic_load_relaxed(&init_task_lock_func);
     if (done == NULL) {
-        done = (jl_function_t*)jl_get_global_value(jl_base_module, jl_symbol("init_task_lock"));
+        done = (jl_function_t*)jl_get_global_value(jl_base_module, jl_symbol("init_task_lock"), ct->world_age);
         if (done != NULL)
             jl_atomic_store_release(&init_task_lock_func, done);
     }