use inline cache for refinements

From Ruby 3.0, refined method invocations are slow because
resolved methods are not cached by inline cache because of
conservertive strategy. However, `using` clears all caches
so that it seems safe to cache resolved method entries.

This patch caches resolved method entries in inline cache
and clear all of inline method caches when `using` is called.

fix [Bug #18572]

```ruby
 # without refinements

class C
  def foo = :C
end

N = 1_000_000

obj = C.new
require 'benchmark'
Benchmark.bm{|x|
  x.report{N.times{
    obj.foo; obj.foo; obj.foo; obj.foo; obj.foo;
    obj.foo; obj.foo; obj.foo; obj.foo; obj.foo;
    obj.foo; obj.foo; obj.foo; obj.foo; obj.foo;
    obj.foo; obj.foo; obj.foo; obj.foo; obj.foo;
  }}
}

_END__
              user     system      total        real
master    0.362859   0.002544   0.365403 (  0.365424)
modified  0.357251   0.000000   0.357251 (  0.357258)
```

```ruby
 # with refinment but without using

class C
  def foo = :C
end

module R
  refine C do
    def foo = :R
  end
end

N = 1_000_000

obj = C.new
require 'benchmark'
Benchmark.bm{|x|
  x.report{N.times{
    obj.foo; obj.foo; obj.foo; obj.foo; obj.foo;
    obj.foo; obj.foo; obj.foo; obj.foo; obj.foo;
    obj.foo; obj.foo; obj.foo; obj.foo; obj.foo;
    obj.foo; obj.foo; obj.foo; obj.foo; obj.foo;
  }}
}
__END__
               user     system      total        real
master     0.957182   0.000000   0.957182 (  0.957212)
modified   0.359228   0.000000   0.359228 (  0.359238)
```

```ruby
 # with using

class C
  def foo = :C
end

module R
  refine C do
    def foo = :R
  end
end

N = 1_000_000

using R

obj = C.new
require 'benchmark'
Benchmark.bm{|x|
  x.report{N.times{
    obj.foo; obj.foo; obj.foo; obj.foo; obj.foo;
    obj.foo; obj.foo; obj.foo; obj.foo; obj.foo;
    obj.foo; obj.foo; obj.foo; obj.foo; obj.foo;
    obj.foo; obj.foo; obj.foo; obj.foo; obj.foo;
  }}
}

1 files changed, 14 insertions, 3 deletions

diff --git a/vm_callinfo.h b/vm_callinfo.h
index 914f1eafdf..91c92854d7 100644
--- a/vm_callinfo.h
+++ b/vm_callinfo.h
@@ -296,13 +296,15 @@ struct rb_callcache {
 #define VM_CALLCACHE_UNMARKABLE FL_FREEZE
 #define VM_CALLCACHE_ON_STACK   FL_EXIVAR
 
-#define VM_CALLCACHE_IVAR  IMEMO_FL_USER0
-#define VM_CALLCACHE_BF    IMEMO_FL_USER1
-#define VM_CALLCACHE_SUPER IMEMO_FL_USER2
+#define VM_CALLCACHE_IVAR       IMEMO_FL_USER0
+#define VM_CALLCACHE_BF         IMEMO_FL_USER1
+#define VM_CALLCACHE_SUPER      IMEMO_FL_USER2
+#define VM_CALLCACHE_REFINEMENT IMEMO_FL_USER3
 
 enum vm_cc_type {
     cc_type_normal, // chained from ccs
     cc_type_super,
+    cc_type_refinement,
 };
 
 extern const struct rb_callcache *rb_vm_empty_cc(void);
@@ -332,6 +334,9 @@ vm_cc_new(VALUE klass,
       case cc_type_super:
         *(VALUE *)&cc->flags |= VM_CALLCACHE_SUPER;
         break;
+      case cc_type_refinement:
+        *(VALUE *)&cc->flags |= VM_CALLCACHE_REFINEMENT;
+        break;
     }
 
     vm_cc_attr_index_initialize(cc, INVALID_SHAPE_ID);
@@ -345,6 +350,12 @@ vm_cc_super_p(const struct rb_callcache *cc)
     return (cc->flags & VM_CALLCACHE_SUPER) != 0;
 }
 
+static inline bool
+vm_cc_refinement_p(const struct rb_callcache *cc)
+{
+    return (cc->flags & VM_CALLCACHE_REFINEMENT) != 0;
+}
+
 #define VM_CC_ON_STACK(clazz, call, aux, cme) \
     (struct rb_callcache) {                   \
         .flags = T_IMEMO |                    \