support builtin features with Ruby and C.

Support loading builtin features written in Ruby, which implement
with C builtin functions.
[Feature #16254]

Several features:

(1) Load .rb file at boottime with native binary.

Now, prelude.rb is loaded at boottime. However, this file is contained
into the interpreter as a text format and we need to compile it.
This patch contains a feature to load from binary format.

(2) __builtin_func() in Ruby call func() written in C.

In Ruby file, we can write `__builtin_func()` like method call.
However this is not a method call, but special syntax to call
a function `func()` written in C. C functions should be defined
in a file (same compile unit) which load this .rb file.

Functions (`func` in above example) should be defined with
  (a) 1st parameter: rb_execution_context_t *ec
  (b) rest parameters (0 to 15).
  (c) VALUE return type.
This is very similar requirements for functions used by
rb_define_method(), however `rb_execution_context_t *ec`
is new requirement.

(3) automatic C code generation from .rb files.

tool/mk_builtin_loader.rb creates a C code to load .rb files
needed by miniruby and ruby command. This script is run by
BASERUBY, so *.rb should be written in BASERUBY compatbile
syntax. This script load a .rb file and find all of __builtin_
prefix method calls, and generate a part of C code to export
functions.

tool/mk_builtin_binary.rb creates a C code which contains
binary compiled Ruby files needed by ruby command.

1 files changed, 186 insertions, 0 deletions

diff --git a/vm_insnhelper.c b/vm_insnhelper.c
index f8be5f6f33..89bc94cd8e 100644
--- a/vm_insnhelper.c
+++ b/vm_insnhelper.c
@@ -4725,3 +4725,189 @@ vm_canary_is_found_dead(enum ruby_vminsn_type i, VALUE c)
 #else
 void Init_vm_stack_canary(void) { /* nothing to do */ }
 #endif
+
+
+/* a part of the following code is generated by this ruby script:
+
+16.times{|i|
+  typedef_args = (0...i).map{|j| "VALUE v#{j+1}"}.join(", ")
+  typedef_args.prepend(", ") if i != 0
+  call_args = (0...i).map{|j| "argv[#{j}]"}.join(", ")
+  call_args.prepend(", ") if i != 0
+  puts %Q{
+static VALUE
+builtin_invoker#{i}(rb_execution_context_t *ec, VALUE self, const VALUE *argv, rb_insn_func_t funcptr)
+{
+    typedef VALUE (*rb_invoke_funcptr#{i}_t)(rb_execution_context_t *ec, VALUE self#{typedef_args});
+    return (*(rb_invoke_funcptr#{i}_t)funcptr)(ec, self#{call_args});
+}}
+}
+
+puts
+puts "static VALUE (* const cfunc_invokers[])(rb_execution_context_t *ec, VALUE self, const VALUE *argv, rb_insn_func_t funcptr) = {"
+16.times{|i|
+  puts "    builtin_invoker#{i},"
+}
+puts "};"
+*/
+
+static VALUE
+builtin_invoker0(rb_execution_context_t *ec, VALUE self, const VALUE *argv, rb_insn_func_t funcptr)
+{
+    typedef VALUE (*rb_invoke_funcptr0_t)(rb_execution_context_t *ec, VALUE self);
+    return (*(rb_invoke_funcptr0_t)funcptr)(ec, self);
+}
+
+static VALUE
+builtin_invoker1(rb_execution_context_t *ec, VALUE self, const VALUE *argv, rb_insn_func_t funcptr)
+{
+    typedef VALUE (*rb_invoke_funcptr1_t)(rb_execution_context_t *ec, VALUE self, VALUE v1);
+    return (*(rb_invoke_funcptr1_t)funcptr)(ec, self, argv[0]);
+}
+
+static VALUE
+builtin_invoker2(rb_execution_context_t *ec, VALUE self, const VALUE *argv, rb_insn_func_t funcptr)
+{
+    typedef VALUE (*rb_invoke_funcptr2_t)(rb_execution_context_t *ec, VALUE self, VALUE v1, VALUE v2);
+    return (*(rb_invoke_funcptr2_t)funcptr)(ec, self, argv[0], argv[1]);
+}
+
+static VALUE
+builtin_invoker3(rb_execution_context_t *ec, VALUE self, const VALUE *argv, rb_insn_func_t funcptr)
+{
+    typedef VALUE (*rb_invoke_funcptr3_t)(rb_execution_context_t *ec, VALUE self, VALUE v1, VALUE v2, VALUE v3);
+    return (*(rb_invoke_funcptr3_t)funcptr)(ec, self, argv[0], argv[1], argv[2]);
+}
+
+static VALUE
+builtin_invoker4(rb_execution_context_t *ec, VALUE self, const VALUE *argv, rb_insn_func_t funcptr)
+{
+    typedef VALUE (*rb_invoke_funcptr4_t)(rb_execution_context_t *ec, VALUE self, VALUE v1, VALUE v2, VALUE v3, VALUE v4);
+    return (*(rb_invoke_funcptr4_t)funcptr)(ec, self, argv[0], argv[1], argv[2], argv[3]);
+}
+
+static VALUE
+builtin_invoker5(rb_execution_context_t *ec, VALUE self, const VALUE *argv, rb_insn_func_t funcptr)
+{
+    typedef VALUE (*rb_invoke_funcptr5_t)(rb_execution_context_t *ec, VALUE self, VALUE v1, VALUE v2, VALUE v3, VALUE v4, VALUE v5);
+    return (*(rb_invoke_funcptr5_t)funcptr)(ec, self, argv[0], argv[1], argv[2], argv[3], argv[4]);
+}
+
+static VALUE
+builtin_invoker6(rb_execution_context_t *ec, VALUE self, const VALUE *argv, rb_insn_func_t funcptr)
+{
+    typedef VALUE (*rb_invoke_funcptr6_t)(rb_execution_context_t *ec, VALUE self, VALUE v1, VALUE v2, VALUE v3, VALUE v4, VALUE v5, VALUE v6);
+    return (*(rb_invoke_funcptr6_t)funcptr)(ec, self, argv[0], argv[1], argv[2], argv[3], argv[4], argv[5]);
+}
+
+static VALUE
+builtin_invoker7(rb_execution_context_t *ec, VALUE self, const VALUE *argv, rb_insn_func_t funcptr)
+{
+    typedef VALUE (*rb_invoke_funcptr7_t)(rb_execution_context_t *ec, VALUE self, VALUE v1, VALUE v2, VALUE v3, VALUE v4, VALUE v5, VALUE v6, VALUE v7);
+    return (*(rb_invoke_funcptr7_t)funcptr)(ec, self, argv[0], argv[1], argv[2], argv[3], argv[4], argv[5], argv[6]);
+}
+
+static VALUE
+builtin_invoker8(rb_execution_context_t *ec, VALUE self, const VALUE *argv, rb_insn_func_t funcptr)
+{
+    typedef VALUE (*rb_invoke_funcptr8_t)(rb_execution_context_t *ec, VALUE self, VALUE v1, VALUE v2, VALUE v3, VALUE v4, VALUE v5, VALUE v6, VALUE v7, VALUE v8);
+    return (*(rb_invoke_funcptr8_t)funcptr)(ec, self, argv[0], argv[1], argv[2], argv[3], argv[4], argv[5], argv[6], argv[7]);
+}
+
+static VALUE
+builtin_invoker9(rb_execution_context_t *ec, VALUE self, const VALUE *argv, rb_insn_func_t funcptr)
+{
+    typedef VALUE (*rb_invoke_funcptr9_t)(rb_execution_context_t *ec, VALUE self, VALUE v1, VALUE v2, VALUE v3, VALUE v4, VALUE v5, VALUE v6, VALUE v7, VALUE v8, VALUE v9);
+    return (*(rb_invoke_funcptr9_t)funcptr)(ec, self, argv[0], argv[1], argv[2], argv[3], argv[4], argv[5], argv[6], argv[7], argv[8]);
+}
+
+static VALUE
+builtin_invoker10(rb_execution_context_t *ec, VALUE self, const VALUE *argv, rb_insn_func_t funcptr)
+{
+    typedef VALUE (*rb_invoke_funcptr10_t)(rb_execution_context_t *ec, VALUE self, VALUE v1, VALUE v2, VALUE v3, VALUE v4, VALUE v5, VALUE v6, VALUE v7, VALUE v8, VALUE v9, VALUE v10);
+    return (*(rb_invoke_funcptr10_t)funcptr)(ec, self, argv[0], argv[1], argv[2], argv[3], argv[4], argv[5], argv[6], argv[7], argv[8], argv[9]);
+}
+
+static VALUE
+builtin_invoker11(rb_execution_context_t *ec, VALUE self, const VALUE *argv, rb_insn_func_t funcptr)
+{
+    typedef VALUE (*rb_invoke_funcptr11_t)(rb_execution_context_t *ec, VALUE self, VALUE v1, VALUE v2, VALUE v3, VALUE v4, VALUE v5, VALUE v6, VALUE v7, VALUE v8, VALUE v9, VALUE v10, VALUE v11);
+    return (*(rb_invoke_funcptr11_t)funcptr)(ec, self, argv[0], argv[1], argv[2], argv[3], argv[4], argv[5], argv[6], argv[7], argv[8], argv[9], argv[10]);
+}
+
+static VALUE
+builtin_invoker12(rb_execution_context_t *ec, VALUE self, const VALUE *argv, rb_insn_func_t funcptr)
+{
+    typedef VALUE (*rb_invoke_funcptr12_t)(rb_execution_context_t *ec, VALUE self, VALUE v1, VALUE v2, VALUE v3, VALUE v4, VALUE v5, VALUE v6, VALUE v7, VALUE v8, VALUE v9, VALUE v10, VALUE v11, VALUE v12);
+    return (*(rb_invoke_funcptr12_t)funcptr)(ec, self, argv[0], argv[1], argv[2], argv[3], argv[4], argv[5], argv[6], argv[7], argv[8], argv[9], argv[10], argv[11]);
+}
+
+static VALUE
+builtin_invoker13(rb_execution_context_t *ec, VALUE self, const VALUE *argv, rb_insn_func_t funcptr)
+{
+    typedef VALUE (*rb_invoke_funcptr13_t)(rb_execution_context_t *ec, VALUE self, VALUE v1, VALUE v2, VALUE v3, VALUE v4, VALUE v5, VALUE v6, VALUE v7, VALUE v8, VALUE v9, VALUE v10, VALUE v11, VALUE v12, VALUE v13);
+    return (*(rb_invoke_funcptr13_t)funcptr)(ec, self, argv[0], argv[1], argv[2], argv[3], argv[4], argv[5], argv[6], argv[7], argv[8], argv[9], argv[10], argv[11], argv[12]);
+}
+
+static VALUE
+builtin_invoker14(rb_execution_context_t *ec, VALUE self, const VALUE *argv, rb_insn_func_t funcptr)
+{
+    typedef VALUE (*rb_invoke_funcptr14_t)(rb_execution_context_t *ec, VALUE self, VALUE v1, VALUE v2, VALUE v3, VALUE v4, VALUE v5, VALUE v6, VALUE v7, VALUE v8, VALUE v9, VALUE v10, VALUE v11, VALUE v12, VALUE v13, VALUE v14);
+    return (*(rb_invoke_funcptr14_t)funcptr)(ec, self, argv[0], argv[1], argv[2], argv[3], argv[4], argv[5], argv[6], argv[7], argv[8], argv[9], argv[10], argv[11], argv[12], argv[13]);
+}
+
+static VALUE
+builtin_invoker15(rb_execution_context_t *ec, VALUE self, const VALUE *argv, rb_insn_func_t funcptr)
+{
+    typedef VALUE (*rb_invoke_funcptr15_t)(rb_execution_context_t *ec, VALUE self, VALUE v1, VALUE v2, VALUE v3, VALUE v4, VALUE v5, VALUE v6, VALUE v7, VALUE v8, VALUE v9, VALUE v10, VALUE v11, VALUE v12, VALUE v13, VALUE v14, VALUE v15);
+    return (*(rb_invoke_funcptr15_t)funcptr)(ec, self, argv[0], argv[1], argv[2], argv[3], argv[4], argv[5], argv[6], argv[7], argv[8], argv[9], argv[10], argv[11], argv[12], argv[13], argv[14]);
+}
+
+typedef VALUE (*builtin_invoker)(rb_execution_context_t *ec, VALUE self, const VALUE *argv, rb_insn_func_t funcptr);
+
+static builtin_invoker
+lookup_builtin_invoker(int argc)
+{
+    static const builtin_invoker invokers[] = {
+        builtin_invoker0,
+        builtin_invoker1,
+        builtin_invoker2,
+        builtin_invoker3,
+        builtin_invoker4,
+        builtin_invoker5,
+        builtin_invoker6,
+        builtin_invoker7,
+        builtin_invoker8,
+        builtin_invoker9,
+        builtin_invoker10,
+        builtin_invoker11,
+        builtin_invoker12,
+        builtin_invoker13,
+        builtin_invoker14,
+        builtin_invoker15,
+    };
+
+    return invokers[argc];
+}
+
+static inline VALUE
+invoke_bf(rb_execution_context_t *ec, rb_control_frame_t *cfp, const struct rb_builtin_function* bf, const VALUE *argv)
+{
+    VALUE self = cfp->self;
+    return (*lookup_builtin_invoker(bf->argc))(ec, self, argv, (rb_insn_func_t)bf->func_ptr);
+}
+
+static VALUE
+vm_invoke_builtin(rb_execution_context_t *ec, rb_control_frame_t *cfp, const struct rb_builtin_function* bf)
+{
+    const VALUE *argv = cfp->sp - bf->argc;
+    return invoke_bf(ec, cfp, bf, argv);
+}
+
+static VALUE
+vm_invoke_builtin_delegate(rb_execution_context_t *ec, rb_control_frame_t *cfp, const struct rb_builtin_function *bf)
+{
+    const VALUE *argv = cfp->ep - cfp->iseq->body->local_table_size - VM_ENV_DATA_SIZE + 1;
+    // fprintf(stderr, "%s %s(%d):%p\n", __func__, bf->name, bf->argc, bf->func_ptr);
+    return invoke_bf(ec, cfp, bf, argv);
+}