From a82a24ed575c5f97b3755317f1a3bd6c9149a67e Mon Sep 17 00:00:00 2001
From: Jeremy Evans <code@jeremyevans.net>
Date: Sun, 2 Apr 2023 11:28:01 -0700
Subject: Optimize method_missing calls

CALLER_ARG_SPLAT is not necessary for method_missing.  We just need
to unshift the method name into the arguments.

This optimizes all method_missing calls:

* mm(recv) ~9%
* mm(recv, *args) ~215% for args.length == 200
* mm(recv, *args, **kw) ~55% for args.length == 200
* mm(recv, **kw) ~22%
* mm(recv, kw: 1) ~100%

Note that empty argument splats do get slower with this approach,
by about 30-40%.  Other than non-empty argument splats, other
argument splats are faster, with the speedup depending on the
number of arguments.
---
 benchmark/vm_call_method_missing.yml | 62 ++++++++++++++++++++++++++++++++++++
 vm_insnhelper.c                      | 28 ++++++----------
 2 files changed, 71 insertions(+), 19 deletions(-)
 create mode 100644 benchmark/vm_call_method_missing.yml

diff --git a/benchmark/vm_call_method_missing.yml b/benchmark/vm_call_method_missing.yml
new file mode 100644
index 0000000000..f890796f11
--- /dev/null
+++ b/benchmark/vm_call_method_missing.yml
@@ -0,0 +1,62 @@
+prelude: |
+  class A0
+    def method_missing(m); m end
+  end
+  class A1
+    def method_missing(m, a) a; end
+  end
+  class S
+    def method_missing(m, *a) a; end
+  end
+  class B
+    def method_missing(m, kw: 1) kw end
+  end
+  class SB
+    def method_missing(m, *a, kw: 1) kw end
+  end
+
+  t0 = 0.times.to_a
+  t1 = 1.times.to_a
+  t10 = 10.times.to_a
+  t200 = 200.times.to_a
+  kw = {kw: 2}
+
+  a0 = A0.new
+  a1 = A1.new
+  s = S.new
+  b = B.new
+  sb = SB.new
+benchmark:
+  method_missing_simple_0: |
+    a0.()
+  method_missing_simple_1: |
+    a1.x(1)
+  method_missing_simple_0_splat: |
+    a0.(*t0)
+  method_missing_simple_1_splat: |
+    a1.(*t1)
+  method_missing_no_splat: |
+    s.()
+  method_missing_0_splat: |
+    s.(*t0)
+  method_missing_1_splat: |
+    s.(*t1)
+  method_missing_10_splat: |
+    s.(*t10)
+  method_missing_200_splat: |
+    s.(*t200)
+  method_missing_kw: |
+    b.(kw: 1)
+  method_missing_no_kw: |
+    b.()
+  method_missing_kw_splat: |
+    b.(**kw)
+  method_missing_0_splat_kw: |
+    sb.(*t0, **kw)
+  method_missing_1_splat_kw: |
+    sb.(*t1, **kw)
+  method_missing_10_splat_kw: |
+    sb.(*t10, **kw)
+  method_missing_200_splat_kw: |
+    sb.(*t200, **kw)
+loop_count: 1000000
diff --git a/vm_insnhelper.c b/vm_insnhelper.c
index 362ac7dcb2..917333d248 100644
--- a/vm_insnhelper.c
+++ b/vm_insnhelper.c
@@ -4006,27 +4006,17 @@ vm_call_method_missing_body(rb_execution_context_t *ec, rb_control_frame_t *reg_
     VALUE *argv = STACK_ADDR_FROM_TOP(calling->argc);
     unsigned int argc, flag;
 
-    CALLER_SETUP_ARG(reg_cfp, calling, orig_ci, ALLOW_HEAP_ARGV);
-    if (UNLIKELY(calling->heap_argv)) {
-        flag = VM_CALL_ARGS_SPLAT | VM_CALL_FCALL | VM_CALL_OPT_SEND | (calling->kw_splat ? VM_CALL_KW_SPLAT : 0);
-        argc = 1;
-        rb_ary_unshift(calling->heap_argv, ID2SYM(vm_ci_mid(orig_ci)));
-    }
-    else {
-        argc = calling->argc + 1;
+    flag = VM_CALL_FCALL | VM_CALL_OPT_SEND | vm_ci_flag(orig_ci);
+    argc = ++calling->argc;
 
-        flag = VM_CALL_FCALL | VM_CALL_OPT_SEND | (calling->kw_splat ? VM_CALL_KW_SPLAT : 0);
-        calling->argc = argc;
-
-        /* shift arguments: m(a, b, c) #=> method_missing(:m, a, b, c) */
-        CHECK_VM_STACK_OVERFLOW(reg_cfp, 1);
-        vm_check_canary(ec, reg_cfp->sp);
-        if (argc > 1) {
-            MEMMOVE(argv+1, argv, VALUE, argc-1);
-        }
-        argv[0] = ID2SYM(vm_ci_mid(orig_ci));
-        INC_SP(1);
+    /* shift arguments: m(a, b, c) #=> method_missing(:m, a, b, c) */
+    CHECK_VM_STACK_OVERFLOW(reg_cfp, 1);
+    vm_check_canary(ec, reg_cfp->sp);
+    if (argc > 1) {
+        MEMMOVE(argv+1, argv, VALUE, argc-1);
     }
+    argv[0] = ID2SYM(vm_ci_mid(orig_ci));
+    INC_SP(1);
 
     ec->method_missing_reason = reason;
     calling->ci = &VM_CI_ON_STACK(idMethodMissing, flag, argc, vm_ci_kwarg(orig_ci));
-- 
cgit v1.2.1