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, 8 insertions, 9 deletions

diff --git a/vm_method.c b/vm_method.c
index 221f184267..a65c676cfc 100644
--- a/vm_method.c
+++ b/vm_method.c
@@ -307,19 +307,19 @@ rb_clear_method_cache(VALUE klass_or_module, ID mid)
 void rb_cc_table_free(VALUE klass);
 
 static int
-invalidate_all_cc(void *vstart, void *vend, size_t stride, void *data)
+invalidate_all_refinement_cc(void *vstart, void *vend, size_t stride, void *data)
 {
     VALUE v = (VALUE)vstart;
     for (; v != (VALUE)vend; v += stride) {
         void *ptr = asan_poisoned_object_p(v);
         asan_unpoison_object(v, false);
+
         if (RBASIC(v)->flags) { // liveness check
-            if (RB_TYPE_P(v, T_CLASS) ||
-                RB_TYPE_P(v, T_ICLASS)) {
-                if (RCLASS_CC_TBL(v)) {
-                    rb_cc_table_free(v);
+            if (imemo_type_p(v, imemo_callcache)) {
+                const struct rb_callcache *cc = (const struct rb_callcache *)v;
+                if (vm_cc_refinement_p(cc) && cc->klass) {
+                    vm_cc_invalidate(cc);
                 }
-                RCLASS_CC_TBL(v) = NULL;
             }
         }
 
@@ -331,10 +331,9 @@ invalidate_all_cc(void *vstart, void *vend, size_t stride, void *data)
 }
 
 void
-rb_clear_method_cache_all(void)
+rb_clear_all_refinement_method_cache(void)
 {
-    rb_objspace_each_objects(invalidate_all_cc, NULL);
-
+    rb_objspace_each_objects(invalidate_all_refinement_cc, NULL);
     rb_yjit_invalidate_all_method_lookup_assumptions();
 }