Rubyのbuiltinを複数のファイルでサポートできるようにした

結論

builtinで複数のRubyコードを使うことができるようになる話。ようはRubyでRubyを高速化するのがよりやりやすくなる話。

以前書いたこの記事をもっと深堀りしたものなので、もっとソフトな話を読みたい方はこちらを読んでいただければと思います。

gamelinks007.hatenablog.com

前提

RubyでRubyのメソッドを実装することが最近のCRubyではできます。
で、いくつかのメソッドはRubyで実装を書くことで高速化を図ることができるケースがあります。

詳しくはこちらの記事を読んで頂ければと思います。

gamelinks007.hatenablog.com

ただ、RubyでRubyを実装する際には複数のRubyコードを使用することは現状できません。

複数のRubyコードを使って実装する場合、こんな感じでCのコードなどを部分的に使用することがあります。

class TrueClass
  #  Document-class: TrueClass
  #
  #  The global value <code>true</code> is the only instance of class
  #  TrueClass and represents a logically true value in
  #  boolean expressions. The class provides operators allowing
  #  <code>true</code> to be used in logical expressions.
  # 
  #
  # call-seq:
  #   true.to_s   ->  "true"
  #
  # The string representation of <code>true</code> is "true".
  #
  def to_s
    Primitive.attr! 'inline'
    Primitive.cexpr! 'rb_cTrueClass_to_s'
  end

  def inspect
    Primitive.attr! 'inline'
    Primitive.cexpr! 'rb_cTrueClass_to_s'
  end

  #
  #  call-seq:
  #     true & obj    -> true or false
  #
  #  And---Returns <code>false</code> if <i>obj</i> is
  #  <code>nil</code> or <code>false</code>, <code>true</code> otherwise.
  #
  def &(obj)
    obj ? true : false
  end

  #
  #  call-seq:
  #     true ^ obj   -> !obj
  #
  #  Exclusive Or---Returns <code>true</code> if <i>obj</i> is
  #  <code>nil</code> or <code>false</code>, <code>false</code>
  #  otherwise.
  #
  def ^(obj)
    obj ? false : true
  end

  #
  #  call-seq:
  #     true | obj   -> true
  #
  #  Or---Returns <code>true</code>. As <i>obj</i> is an argument to
  #  a method call, it is always evaluated; there is no short-circuit
  #  evaluation in this case.
  #
  #     true |  puts("or")
  #     true || puts("logical or")
  #
  #  <em>produces:</em>
  #
  #     or
  #
  def |(bool)
    true
  end
end

module Kernel
  #
  #  call-seq:
  #     obj.class    -> class
  #
  #  Returns the class of <i>obj</i>. This method must always be called
  #  with an explicit receiver, as #class is also a reserved word in
  #  Ruby.
  #
  #     1.class      #=> Integer
  #     self.class   #=> Object
  #--
  # Equivalent to \c Object\#class in Ruby.
  #
  # Returns the class of \c obj, skipping singleton classes or module inclusions.
  #++
  #
  def class
    Primitive.attr! 'inline'
    Primitive.cexpr! 'rb_obj_class(self)'
  end

  #
  #  call-seq:
  #     obj.clone(freeze: nil) -> an_object
  #
  #  Produces a shallow copy of <i>obj</i>---the instance variables of
  #  <i>obj</i> are copied, but not the objects they reference.
  #  #clone copies the frozen value state of <i>obj</i>, unless the
  #  +:freeze+ keyword argument is given with a false or true value.
  #  See also the discussion under Object#dup.
  #
  #     class Klass
  #        attr_accessor :str
  #     end
  #     s1 = Klass.new      #=> #<Klass:0x401b3a38>
  #     s1.str = "Hello"    #=> "Hello"
  #     s2 = s1.clone       #=> #<Klass:0x401b3998 @str="Hello">
  #     s2.str[1,4] = "i"   #=> "i"
  #     s1.inspect          #=> "#<Klass:0x401b3a38 @str=\"Hi\">"
  #     s2.inspect          #=> "#<Klass:0x401b3998 @str=\"Hi\">"
  #
  #  This method may have class-specific behavior.  If so, that
  #  behavior will be documented under the #+initialize_copy+ method of
  #  the class.
  #
  def clone(freeze: nil)
    Primitive.rb_obj_clone2(freeze)
  end

  #
  #  call-seq:
  #     obj.frozen?    -> true or false
  #
  #  Returns the freeze status of <i>obj</i>.
  #
  #     a = [ "a", "b", "c" ]
  #     a.freeze    #=> ["a", "b", "c"]
  #     a.frozen?   #=> true
  #--
  # Determines if the object is frozen. Equivalent to \c Object\#frozen? in Ruby.
  # \param[in] obj  the object to be determines
  # \retval Qtrue if frozen
  # \retval Qfalse if not frozen
  #++
  #
  def frozen?
    Primitive.attr! 'inline'
    Primitive.cexpr! 'rb_obj_frozen_p(self)'
  end

  #
  #  call-seq:
  #     obj.tap {|x| block }    -> obj
  #
  #  Yields self to the block, and then returns self.
  #  The primary purpose of this method is to "tap into" a method chain,
  #  in order to perform operations on intermediate results within the chain.
  #
  #     (1..10)                  .tap {|x| puts "original: #{x}" }
  #       .to_a                  .tap {|x| puts "array:    #{x}" }
  #       .select {|x| x.even? } .tap {|x| puts "evens:    #{x}" }
  #       .map {|x| x*x }        .tap {|x| puts "squares:  #{x}" }
  #
  #--
  # \private
  #++
  #
  def tap
    yield(self)
    self
  end

  #
  #  call-seq:
  #     obj.then {|x| block }          -> an_object
  #
  #  Yields self to the block and returns the result of the block.
  #
  #     3.next.then {|x| x**x }.to_s             #=> "256"
  #
  #  Good usage for +then+ is value piping in method chains:
  #
  #     require 'open-uri'
  #     require 'json'
  #
  #     construct_url(arguments).
  #       then {|url| open(url).read }.
  #       then {|response| JSON.parse(response) }
  #
  #  When called without block, the method returns +Enumerator+,
  #  which can be used, for example, for conditional
  #  circuit-breaking:
  #
  #     # meets condition, no-op
  #     1.then.detect(&:odd?)            # => 1
  #     # does not meet condition, drop value
  #     2.then.detect(&:odd?)            # => nil
  #
  def then
    unless Primitive.block_given_p
      return Primitive.cexpr! 'SIZED_ENUMERATOR(self, 0, 0, rb_obj_size)'
    end
    yield(self)
  end

  #
  #  call-seq:
  #     obj.yield_self {|x| block }    -> an_object
  #
  #  Yields self to the block and returns the result of the block.
  #
  #     "my string".yield_self {|s| s.upcase }   #=> "MY STRING"
  #
  #  Good usage for +then+ is value piping in method chains:
  #
  #     require 'open-uri'
  #     require 'json'
  #
  #     construct_url(arguments).
  #       then {|url| open(url).read }.
  #       then {|response| JSON.parse(response) }
  #
  def yield_self
    unless Primitive.block_given_p
      return Primitive.cexpr! 'SIZED_ENUMERATOR(self, 0, 0, rb_obj_size)'
    end
    yield(self)
  end

  module_function

  #
  #  call-seq:
  #     Float(arg, exception: true)    -> float or nil
  #
  #  Returns <i>arg</i> converted to a float. Numeric types are
  #  converted directly, and with exception to String and
  #  <code>nil</code> the rest are converted using
  #  <i>arg</i><code>.to_f</code>.  Converting a String with invalid
  #  characters will result in a ArgumentError.  Converting
  #  <code>nil</code> generates a TypeError.  Exceptions can be
  #  suppressed by passing <code>exception: false</code>.
  #
  #     Float(1)                 #=> 1.0
  #     Float("123.456")         #=> 123.456
  #     Float("123.0_badstring") #=> ArgumentError: invalid value for Float(): "123.0_badstring"
  #     Float(nil)               #=> TypeError: can't convert nil into Float
  #     Float("123.0_badstring", exception: false)  #=> nil
  #
  def Float(arg, exception: true)
    Primitive.rb_f_float(arg, exception)
  end
end

またCのコードをRubyで使用する際には、以下のように自動生成されるヘッダーを読み込む必要があります。
今回のケースだとTrueClassとKernelの二つでRubyの実装を使用するようにしているので、それらが定義されているobject.c内で以下のように自動生成されたヘッダーを読み込む必要があります。

#include "kernel.rbinc"
#include "trueclass.rbinc"

kernel.rbincなどの.rbincは、makeでビルドする際に自動生成されているヘッダーです。

で、この自動生成されているヘッダーで定義されているCの関数がネックとなっています。

CRubyではmakeする際に、Rubyコード内のCコードをチェックしてヘッダーへと自動変換する処理が行われています(つまりRubyで実装した個所をCへと変換してたりする)

具体的な処理の箇所としてはcommon.mkでは

{$(srcdir)}.rb.rbinc:
	$(ECHO) making $@
	$(Q) $(BASERUBY) $(tooldir)/mk_builtin_loader.rb $<

builtin_binary.inc: $(PREP) $(BUILTIN_RB_SRCS) $(srcdir)/template/builtin_binary.inc.tmpl
	$(Q) $(MINIRUBY) $(tooldir)/generic_erb.rb -o $@ \
		$(srcdir)/template/builtin_binary.inc.tmpl -- --cross=$(CROSS_COMPILING)

mk_builtin_loader.rbをビルドする際に実行するようにしています。

またtool/mk_builtin_loader.rb内部ではビルド時にRubyのソースコード(builtinで配置されたもの。ex: array.rbなど)を引数に受け取り、それをもとにヘッダーを自動生成しています。

# Parse built-in script and make rbinc file

require 'ripper'
require 'stringio'
require_relative 'ruby_vm/helpers/c_escape'

def string_literal(lit, str = [])
  while lit
    case lit.first
    when :string_concat, :string_embexpr, :string_content
      _, *lit = lit
      lit.each {|s| string_literal(s, str)}
      return str
    when :string_literal
      _, lit = lit
    when :@tstring_content
      str << lit[1]
      return str
    else
      raise "unexpected #{lit.first}"
    end
  end
end

def inline_text argc, arg1
  raise "argc (#{argc}) of inline! should be 1" unless argc == 1
  arg1 = string_literal(arg1)
  raise "1st argument should be string literal" unless arg1
  arg1.join("").rstrip
end

def make_cfunc_name inlines, name, lineno
  case name
  when /\[\]/
    name = '_GETTER'
  when /\[\]=/
    name = '_SETTER'
  else
    name = name.tr('!?', 'EP')
  end

  base = "builtin_inline_#{name}_#{lineno}"
  if inlines[base]
    1000.times{|i|
      name = "#{base}_#{i}"
      return name unless inlines[name]
    }
    raise "too many functions in same line..."
  else
    base
  end
end

def collect_locals tree
  type, name, (line, cols) = tree
  if locals = LOCALS_DB[[name, line]]
    locals
  else
    if false # for debugging
      pp LOCALS_DB
      raise "not found: [#{name}, #{line}]"
    end
  end
end

def collect_builtin base, tree, name, bs, inlines, locals = nil
  while tree
    call = recv = sep = mid = args = nil
    case tree.first
    when :def
      locals = collect_locals(tree[1])
      tree = tree[3]
      next
    when :defs
      locals = collect_locals(tree[3])
      tree = tree[5]
      next
    when :class
      name = 'class'
      tree = tree[3]
      next
    when :sclass, :module
      name = 'class'
      tree = tree[2]
      next
    when :method_add_arg
      _, mid, (_, (_, args)) = tree
      case mid.first
      when :call
        _, recv, sep, mid = mid
      when :fcall
        _, mid = mid
      else
        mid = nil
      end
    when :vcall
      _, mid = tree
    when :command               # FCALL
      _, mid, (_, args) = tree
    when :call, :command_call   # CALL
      _, recv, sep, mid, (_, args) = tree
    end
    if mid
      raise "unknown sexp: #{mid.inspect}" unless mid.first == :@ident
      _, mid, (lineno,) = mid
      if recv
        func_name = nil
        case recv.first
        when :var_ref
          _, recv = recv
          if recv.first == :@const and recv[1] == "Primitive"
            func_name = mid.to_s
          end
        when :vcall
          _, recv = recv
          if recv.first == :@ident and recv[1] == "__builtin"
            func_name = mid.to_s
          end
        end
        collect_builtin(base, recv, name, bs, inlines) unless func_name
      else
        func_name = mid[/\A__builtin_(.+)/, 1]
      end
      if func_name
        cfunc_name = func_name
        args.pop unless (args ||= []).last
        argc = args.size

        if /(.+)\!\z/ =~ func_name
          case $1
          when 'attr'
            text = inline_text(argc, args.first)
            if text != 'inline'
              raise "Only 'inline' is allowed to be annotated (but got: '#{text}')"
            end
            break
          when 'cstmt'
            text = inline_text argc, args.first

            func_name = "_bi#{inlines.size}"
            cfunc_name = make_cfunc_name(inlines, name, lineno)
            inlines[cfunc_name] = [lineno, text, locals, func_name]
            argc -= 1
          when 'cexpr', 'cconst'
            text = inline_text argc, args.first
            code = "return #{text};"

            func_name = "_bi#{inlines.size}"
            cfunc_name = make_cfunc_name(inlines, name, lineno)

            locals = [] if $1 == 'cconst'
            inlines[cfunc_name] = [lineno, code, locals, func_name]
            argc -= 1
          when 'cinit'
            text = inline_text argc, args.first
            func_name = nil # required
            inlines[inlines.size] = [lineno, text, nil, nil]
            argc -= 1
          end
        end

        if bs[func_name] &&
           bs[func_name] != [argc, cfunc_name]
          raise "same builtin function \"#{func_name}\", but different arity (was #{bs[func_name]} but #{argc})"
        end

        bs[func_name] = [argc, cfunc_name] if func_name
      end
      break unless tree = args
    end

    tree.each do |t|
      collect_builtin base, t, name, bs, inlines, locals if Array === t
    end
    break
  end
end

# ruby mk_builtin_loader.rb TARGET_FILE.rb
# #=> generate TARGET_FILE.rbinc
#

LOCALS_DB = {} # [method_name, first_line] = locals

def collect_iseq iseq_ary
  # iseq_ary.each_with_index{|e, i| p [i, e]}
  label = iseq_ary[5]
  first_line = iseq_ary[8]
  type = iseq_ary[9]
  locals = iseq_ary[10]
  insns = iseq_ary[13]

  if type == :method
    LOCALS_DB[[label, first_line].freeze] = locals
  end

  insns.each{|insn|
    case insn
    when Integer
      # ignore
    when Array
      # p insn.shift # insn name
      insn.each{|op|
        if Array === op && op[0] == "YARVInstructionSequence/SimpleDataFormat"
          collect_iseq op
        end
      }
    end
  }
end

def generate_cexpr(ofile, lineno, line_file, body_lineno, text, locals, func_name)
  f = StringIO.new
  f.puts '{'
  lineno += 1
  locals.reverse_each.with_index{|param, i|
    next unless Symbol === param
    f.puts "MAYBE_UNUSED(const VALUE) #{param} = rb_vm_lvar(ec, #{-3 - i});"
    lineno += 1
  }
  f.puts "#line #{body_lineno} \"#{line_file}\""
  lineno += 1

  f.puts text
  lineno += text.count("\n") + 1

  f.puts "#line #{lineno + 2} \"#{ofile}\"" # TODO: restore line number.
  f.puts "}"
  f.puts
  lineno += 3

  return lineno, f.string
end

def mk_builtin_header file
  base = File.basename(file, '.rb')
  ofile = "#{file}inc"

  # bs = { func_name => argc }
  code = File.read(file)
  collect_iseq RubyVM::InstructionSequence.compile(code).to_a
  collect_builtin(base, Ripper.sexp(code), 'top', bs = {}, inlines = {})

  begin
    f = open(ofile, 'w')
  rescue Errno::EACCES
    # Fall back to the current directory
    f = open(File.basename(ofile), 'w')
  end
  begin
    if File::ALT_SEPARATOR
      file = file.tr(File::ALT_SEPARATOR, File::SEPARATOR)
      ofile = ofile.tr(File::ALT_SEPARATOR, File::SEPARATOR)
    end
    lineno = __LINE__
    f.puts "// -*- c -*-"
    f.puts "// DO NOT MODIFY THIS FILE DIRECTLY."
    f.puts "// auto-generated file"
    f.puts "//   by #{__FILE__}"
    f.puts "//   with #{file}"
    f.puts '#include "internal/compilers.h"     /* for MAYBE_UNUSED */'
    f.puts '#include "internal/warnings.h"      /* for COMPILER_WARNING_PUSH */'
    f.puts '#include "ruby/ruby.h"              /* for VALUE */'
    f.puts '#include "builtin.h"                /* for RB_BUILTIN_FUNCTION */'
    f.puts 'struct rb_execution_context_struct; /* in vm_core.h */'
    f.puts
    lineno = __LINE__ - lineno - 1
    line_file = file

    inlines.each{|cfunc_name, (body_lineno, text, locals, func_name)|
      if String === cfunc_name
        f.puts "static VALUE #{cfunc_name}(struct rb_execution_context_struct *ec, const VALUE self)"
        lineno += 1
        lineno, str = generate_cexpr(ofile, lineno, line_file, body_lineno, text, locals, func_name)
        f.write str
      else
        # cinit!
        f.puts "#line #{body_lineno} \"#{line_file}\""
        lineno += 1
        f.puts text
        lineno += text.count("\n") + 1
        f.puts "#line #{lineno + 2} \"#{ofile}\"" # TODO: restore line number.
        lineno += 1
      end
    }

    bs.each_pair{|func, (argc, cfunc_name)|
      decl = ', VALUE' * argc
      argv = argc                    \
           . times                   \
           . map {|i|", argv[#{i}]"} \
           . join('')
      f.puts %'static void'
      f.puts %'mjit_compile_invokebuiltin_for_#{func}_#{cfunc_name}(FILE *f, long index, unsigned stack_size, bool inlinable_p)'
      f.puts %'{'
      f.puts %'    fprintf(f, "    VALUE self = GET_SELF();\\n");'
      f.puts %'    fprintf(f, "    typedef VALUE (*func)(rb_execution_context_t *, VALUE#{decl});\\n");'
      if inlines.has_key? cfunc_name
        body_lineno, text, locals, func_name = inlines[cfunc_name]
        lineno, str = generate_cexpr(ofile, lineno, line_file, body_lineno, text, locals, func_name)
        f.puts %'    if (inlinable_p) {'
        str.gsub(/^(?!#)/, '    ').each_line {|i|
          j = RubyVM::CEscape.rstring2cstr(i).dup
          j.sub!(/^    return\b/ , '    val =')
          f.printf(%'        fprintf(f, "%%s", %s);\n', j)
        }
        f.puts(%'        return;')
        f.puts(%'    }')
      end
      if argc > 0
        f.puts %'    if (index == -1) {'
        f.puts %'        fprintf(f, "    const VALUE *argv = &stack[%d];\\n", stack_size - #{argc});'
        f.puts %'    }'
        f.puts %'    else {'
        f.puts %'        fprintf(f, "    const unsigned int lnum = GET_ISEQ()->body->local_table_size;\\n");'
        f.puts %'        fprintf(f, "    const VALUE *argv = GET_EP() - lnum - VM_ENV_DATA_SIZE + 1 + %ld;\\n", index);'
        f.puts %'    }'
      end
      f.puts %'    fprintf(f, "    func f = (func)%"PRIdPTR"; /* == #{cfunc_name} */\\n", (intptr_t)#{cfunc_name});'
      f.puts %'    fprintf(f, "    val = f(ec, self#{argv});\\n");'
      f.puts %'}'
      f.puts
    }

    f.puts "void Init_builtin_#{base}(void)"
    f.puts "{"

    table = "#{base}_table"
    f.puts "  // table definition"
    f.puts "  static const struct rb_builtin_function #{table}[] = {"
    bs.each.with_index{|(func, (argc, cfunc_name)), i|
      f.puts "    RB_BUILTIN_FUNCTION(#{i}, #{func}, #{cfunc_name}, #{argc}, mjit_compile_invokebuiltin_for_#{func}_#{cfunc_name}),"
    }
    f.puts "    RB_BUILTIN_FUNCTION(-1, NULL, NULL, 0, 0),"
    f.puts "  };"

    f.puts
    f.puts "  // arity_check"
    f.puts "COMPILER_WARNING_PUSH"
    f.puts "#if GCC_VERSION_SINCE(5, 1, 0) || __clang__"
    f.puts "COMPILER_WARNING_ERROR(-Wincompatible-pointer-types)"
    f.puts "#endif"
    bs.each{|func, (argc, cfunc_name)|
      f.puts "  if (0) rb_builtin_function_check_arity#{argc}(#{cfunc_name});"
    }
    f.puts "COMPILER_WARNING_POP"

    f.puts
    f.puts "  // load"
    f.puts "  rb_load_with_builtin_functions(#{base.dump}, #{table});"

    f.puts "}"
  ensure
    f.close
  end
end

ARGV.each{|file|
  # feature.rb => load_feature.inc
  mk_builtin_header file
}

またこの時、Primitive.cexpr! 'rb_obj_frozen_p(self)'のようなCのコードを見つけるとcompile.cのcompile_call関数が呼び出され、関数名を自動生成してくれます(長いので関数名を自動生成している部分だけ切り抜いています)

int inline_index = GET_VM()->builtin_inline_index++;
snprintf(inline_func, 0x20, "_bi%d", inline_index); // <= ここでRubyのコード内で呼び出されたCのコードの関数名を作成している

これは、Ruby内部のCコードを実行するための関数を定義するためです。

たとえばPrimitive.cexpr! 'rb_obj_frozen_p(self)'はこんな感じでCの関数が定義されます。

static void
mjit_compile_invokebuiltin_for__bi1(FILE *f, long index, unsigned stack_size, bool inlinable_p)
{
    fprintf(f, "    VALUE self = GET_SELF();\n");
    fprintf(f, "    typedef VALUE (*func)(rb_execution_context_t *, VALUE);\n");
    if (inlinable_p) {
        fprintf(f, "%s", "    {\n");
        fprintf(f, "%s", "#line 69 \"../ruby/kernel.rb\"\n");
        fprintf(f, "%s", "    return rb_obj_frozen_p(self);\n");
        fprintf(f, "%s", "#line 50 \"../ruby/kernel.rbinc\"\n");
        fprintf(f, "%s", "    }\n");
        fprintf(f, "%s", "    \n");
        return;
    }
    fprintf(f, "    func f = (func)%"PRIdPTR"; /* == builtin_inline_class_69 */\n", (intptr_t)builtin_inline_class_69);
    fprintf(f, "    val = f(ec, self);\n");
}

ちなみに複数個所でCコードが埋め込まれている場合は、mjit_compile_invokebuiltin_for__bi1、mjit_compile_invokebuiltin_for__bi2のように連番となります。

ここまでが前提です。

起きたこと

Cのコードを連番で関数として定義しているため、複数のRubyコードでRubyを実装するとコンパイル時にエラーになる。

まあ、なんというかCの世界では想定できそうな話ではある感じです。
Cでは同じ名前の関数を定義してエラーになってしまうことがままあります(大体の場合はちょっと違う関数名つけて回避する)

int func() {
    return 42;
}

int func() {
    return 21;   
}

int main() {
    return func();
}

なので、こういうコードはコンパイルできません。

で、今回のようにTrueClassとKernelをそれぞれ別のRubyコードで実装した場合はそれぞれのソースコード毎に読み込んでtool/mk_builtin_loader.rbが実行されます。

つまり、内部にCコードの埋め込みがある場合でmjit_compile_invokebuiltin_for__bi1というコードが別々のヘッダーにそれぞれ定義されてしまうということです。

ここで思い出してほしいのですが、複数のRubyコードを読み込んでCRuby自体を実装する場合

#include "kernel.rbinc"
#include "trueclass.rbinc"

このようにそれぞれのヘッダーを読み込みます。

つまりこの部分で関数名の重複がコンパイラ側で分かり、コンパイルエラーとなるわけです。

なので、現状のCRubyでは複数のRubyコードでRubyを実装することができない状況です。

対応策

gamelinks007.hatenablog.com

この記事では文字列をハッシュ値に変換して渡すという方法を取りました。これでビルドはできるようになります。
ですが、ハッシュ値が衝突する可能性も全くないわけではないのであまり好ましい実装ではないです。

そこで、tool/mk_builtin_loader.rbでCの関数を生成している箇所を修正してみます。

# Parse built-in script and make rbinc file

require 'ripper'
require 'stringio'
require_relative 'ruby_vm/helpers/c_escape'

def string_literal(lit, str = [])
  while lit
    case lit.first
    when :string_concat, :string_embexpr, :string_content
      _, *lit = lit
      lit.each {|s| string_literal(s, str)}
      return str
    when :string_literal
      _, lit = lit
    when :@tstring_content
      str << lit[1]
      return str
    else
      raise "unexpected #{lit.first}"
    end
  end
end

def inline_text argc, arg1
  raise "argc (#{argc}) of inline! should be 1" unless argc == 1
  arg1 = string_literal(arg1)
  raise "1st argument should be string literal" unless arg1
  arg1.join("").rstrip
end

def make_cfunc_name inlines, name, lineno
  case name
  when /\[\]/
    name = '_GETTER'
  when /\[\]=/
    name = '_SETTER'
  else
    name = name.tr('!?', 'EP')
  end

  base = "builtin_inline_#{name}_#{lineno}"
  if inlines[base]
    1000.times{|i|
      name = "#{base}_#{i}"
      return name unless inlines[name]
    }
    raise "too many functions in same line..."
  else
    base
  end
end

def collect_locals tree
  type, name, (line, cols) = tree
  if locals = LOCALS_DB[[name, line]]
    locals
  else
    if false # for debugging
      pp LOCALS_DB
      raise "not found: [#{name}, #{line}]"
    end
  end
end

def collect_builtin base, tree, name, bs, inlines, locals = nil
  while tree
    call = recv = sep = mid = args = nil
    case tree.first
    when :def
      locals = collect_locals(tree[1])
      tree = tree[3]
      next
    when :defs
      locals = collect_locals(tree[3])
      tree = tree[5]
      next
    when :class
      name = 'class'
      tree = tree[3]
      next
    when :sclass, :module
      name = 'class'
      tree = tree[2]
      next
    when :method_add_arg
      _, mid, (_, (_, args)) = tree
      case mid.first
      when :call
        _, recv, sep, mid = mid
      when :fcall
        _, mid = mid
      else
        mid = nil
      end
    when :vcall
      _, mid = tree
    when :command               # FCALL
      _, mid, (_, args) = tree
    when :call, :command_call   # CALL
      _, recv, sep, mid, (_, args) = tree
    end
    if mid
      raise "unknown sexp: #{mid.inspect}" unless mid.first == :@ident
      _, mid, (lineno,) = mid
      if recv
        func_name = nil
        case recv.first
        when :var_ref
          _, recv = recv
          if recv.first == :@const and recv[1] == "Primitive"
            func_name = mid.to_s
          end
        when :vcall
          _, recv = recv
          if recv.first == :@ident and recv[1] == "__builtin"
            func_name = mid.to_s
          end
        end
        collect_builtin(base, recv, name, bs, inlines) unless func_name
      else
        func_name = mid[/\A__builtin_(.+)/, 1]
      end
      if func_name
        cfunc_name = func_name
        args.pop unless (args ||= []).last
        argc = args.size

        if /(.+)\!\z/ =~ func_name
          case $1
          when 'attr'
            text = inline_text(argc, args.first)
            if text != 'inline'
              raise "Only 'inline' is allowed to be annotated (but got: '#{text}')"
            end
            break
          when 'cstmt'
            text = inline_text argc, args.first

            func_name = "_bi#{inlines.size}"
            cfunc_name = make_cfunc_name(inlines, name, lineno)
            inlines[cfunc_name] = [lineno, text, locals, func_name]
            argc -= 1
          when 'cexpr', 'cconst'
            text = inline_text argc, args.first
            code = "return #{text};"

            func_name = "_bi#{inlines.size}"
            cfunc_name = make_cfunc_name(inlines, name, lineno)

            locals = [] if $1 == 'cconst'
            inlines[cfunc_name] = [lineno, code, locals, func_name]
            argc -= 1
          when 'cinit'
            text = inline_text argc, args.first
            func_name = nil # required
            inlines[inlines.size] = [lineno, text, nil, nil]
            argc -= 1
          end
        end

        if bs[func_name] &&
           bs[func_name] != [argc, cfunc_name]
          raise "same builtin function \"#{func_name}\", but different arity (was #{bs[func_name]} but #{argc})"
        end

        bs[func_name] = [argc, cfunc_name] if func_name
      end
      break unless tree = args
    end

    tree.each do |t|
      collect_builtin base, t, name, bs, inlines, locals if Array === t
    end
    break
  end
end

# ruby mk_builtin_loader.rb TARGET_FILE.rb
# #=> generate TARGET_FILE.rbinc
#

LOCALS_DB = {} # [method_name, first_line] = locals

def collect_iseq iseq_ary
  # iseq_ary.each_with_index{|e, i| p [i, e]}
  label = iseq_ary[5]
  first_line = iseq_ary[8]
  type = iseq_ary[9]
  locals = iseq_ary[10]
  insns = iseq_ary[13]

  if type == :method
    LOCALS_DB[[label, first_line].freeze] = locals
  end

  insns.each{|insn|
    case insn
    when Integer
      # ignore
    when Array
      # p insn.shift # insn name
      insn.each{|op|
        if Array === op && op[0] == "YARVInstructionSequence/SimpleDataFormat"
          collect_iseq op
        end
      }
    end
  }
end

def generate_cexpr(ofile, lineno, line_file, body_lineno, text, locals, func_name)
  f = StringIO.new
  f.puts '{'
  lineno += 1
  locals.reverse_each.with_index{|param, i|
    next unless Symbol === param
    f.puts "MAYBE_UNUSED(const VALUE) #{param} = rb_vm_lvar(ec, #{-3 - i});"
    lineno += 1
  }
  f.puts "#line #{body_lineno} \"#{line_file}\""
  lineno += 1

  f.puts text
  lineno += text.count("\n") + 1

  f.puts "#line #{lineno + 2} \"#{ofile}\"" # TODO: restore line number.
  f.puts "}"
  f.puts
  lineno += 3

  return lineno, f.string
end

def mk_builtin_header file
  base = File.basename(file, '.rb')
  ofile = "#{file}inc"

  # bs = { func_name => argc }
  code = File.read(file)
  collect_iseq RubyVM::InstructionSequence.compile(code).to_a
  collect_builtin(base, Ripper.sexp(code), 'top', bs = {}, inlines = {})

  begin
    f = open(ofile, 'w')
  rescue Errno::EACCES
    # Fall back to the current directory
    f = open(File.basename(ofile), 'w')
  end
  begin
    if File::ALT_SEPARATOR
      file = file.tr(File::ALT_SEPARATOR, File::SEPARATOR)
      ofile = ofile.tr(File::ALT_SEPARATOR, File::SEPARATOR)
    end
    lineno = __LINE__
    f.puts "// -*- c -*-"
    f.puts "// DO NOT MODIFY THIS FILE DIRECTLY."
    f.puts "// auto-generated file"
    f.puts "//   by #{__FILE__}"
    f.puts "//   with #{file}"
    f.puts '#include "internal/compilers.h"     /* for MAYBE_UNUSED */'
    f.puts '#include "internal/warnings.h"      /* for COMPILER_WARNING_PUSH */'
    f.puts '#include "ruby/ruby.h"              /* for VALUE */'
    f.puts '#include "builtin.h"                /* for RB_BUILTIN_FUNCTION */'
    f.puts 'struct rb_execution_context_struct; /* in vm_core.h */'
    f.puts
    lineno = __LINE__ - lineno - 1
    line_file = file

    inlines.each{|cfunc_name, (body_lineno, text, locals, func_name)|
      if String === cfunc_name
        f.puts "static VALUE #{cfunc_name}(struct rb_execution_context_struct *ec, const VALUE self)"
        lineno += 1
        lineno, str = generate_cexpr(ofile, lineno, line_file, body_lineno, text, locals, func_name)
        f.write str
      else
        # cinit!
        f.puts "#line #{body_lineno} \"#{line_file}\""
        lineno += 1
        f.puts text
        lineno += text.count("\n") + 1
        f.puts "#line #{lineno + 2} \"#{ofile}\"" # TODO: restore line number.
        lineno += 1
      end
    }

    bs.each_pair{|func, (argc, cfunc_name)|
      decl = ', VALUE' * argc
      argv = argc                    \
           . times                   \
           . map {|i|", argv[#{i}]"} \
           . join('')
      f.puts %'static void'
      f.puts %'mjit_compile_invokebuiltin_for_#{base}_#{func}(FILE *f, long index, unsigned stack_size, bool inlinable_p)'
      f.puts %'{'
      f.puts %'    fprintf(f, "    VALUE self = GET_SELF();\\n");'
      f.puts %'    fprintf(f, "    typedef VALUE (*func)(rb_execution_context_t *, VALUE#{decl});\\n");'
      if inlines.has_key? cfunc_name
        body_lineno, text, locals, func_name = inlines[cfunc_name]
        lineno, str = generate_cexpr(ofile, lineno, line_file, body_lineno, text, locals, func_name)
        f.puts %'    if (inlinable_p) {'
        str.gsub(/^(?!#)/, '    ').each_line {|i|
          j = RubyVM::CEscape.rstring2cstr(i).dup
          j.sub!(/^    return\b/ , '    val =')
          f.printf(%'        fprintf(f, "%%s", %s);\n', j)
        }
        f.puts(%'        return;')
        f.puts(%'    }')
      end
      if argc > 0
        f.puts %'    if (index == -1) {'
        f.puts %'        fprintf(f, "    const VALUE *argv = &stack[%d];\\n", stack_size - #{argc});'
        f.puts %'    }'
        f.puts %'    else {'
        f.puts %'        fprintf(f, "    const unsigned int lnum = GET_ISEQ()->body->local_table_size;\\n");'
        f.puts %'        fprintf(f, "    const VALUE *argv = GET_EP() - lnum - VM_ENV_DATA_SIZE + 1 + %ld;\\n", index);'
        f.puts %'    }'
      end
      f.puts %'    fprintf(f, "    func f = (func)%"PRIdPTR"; /* == #{cfunc_name} */\\n", (intptr_t)#{cfunc_name});'
      f.puts %'    fprintf(f, "    val = f(ec, self#{argv});\\n");'
      f.puts %'}'
      f.puts
    }

    f.puts "void Init_builtin_#{base}(void)"
    f.puts "{"

    table = "#{base}_table"
    f.puts "  // table definition"
    f.puts "  static const struct rb_builtin_function #{table}[] = {"
    bs.each.with_index{|(func, (argc, cfunc_name)), i|
      f.puts "    RB_BUILTIN_FUNCTION(#{i}, #{func}, #{cfunc_name}, #{argc}, mjit_compile_invokebuiltin_for_#{base}_#{func}),"
    }
    f.puts "    RB_BUILTIN_FUNCTION(-1, NULL, NULL, 0, 0),"
    f.puts "  };"

    f.puts
    f.puts "  // arity_check"
    f.puts "COMPILER_WARNING_PUSH"
    f.puts "#if GCC_VERSION_SINCE(5, 1, 0) || __clang__"
    f.puts "COMPILER_WARNING_ERROR(-Wincompatible-pointer-types)"
    f.puts "#endif"
    bs.each{|func, (argc, cfunc_name)|
      f.puts "  if (0) rb_builtin_function_check_arity#{argc}(#{cfunc_name});"
    }
    f.puts "COMPILER_WARNING_POP"

    f.puts
    f.puts "  // load"
    f.puts "  rb_load_with_builtin_functions(#{base.dump}, #{table});"

    f.puts "}"
  ensure
    f.close
  end
end

ARGV.each{|file|
  # feature.rb => load_feature.inc
  mk_builtin_header file
}

変更した個所はに箇所です。
f.puts %'mjit_compile_invokebuiltin_for_#{func}(FILE *f, long index, unsigned stack_size, bool inlinable_p)'をf.puts %'mjit_compile_invokebuiltin_for_#{base}_#{func}(FILE *f, long index, unsigned stack_size, bool inlinable_p)'に変更し、f.puts " RB_BUILTIN_FUNCTION(#{i}, #{func}, #{cfunc_name}, #{argc}, mjit_compile_invokebuiltin_for_#{func}),"をf.puts " RB_BUILTIN_FUNCTION(#{i}, #{func}, #{cfunc_name}, #{argc}, mjit_compile_invokebuiltin_for_#{base}_#{func}),"に変更しています。

baseにはビルド時に読み込まれた各Rubyのソースコード名が入ります(ex: array.rbならarray)

これによりmjit_compile_invokebuiltin_for_kernel__bi1のように自動生成される関数名に使用するクラスやモジュール名を追加することができます。

これで複数のRubyコードを使ってCRubyを実装することができます。