rb_vm_insn_addr2insn: use st to perform addr2insn mapping

The current VM_INSTRUCTION_SIZE is 198, so the linear search
painful during a major GC phase.

I noticed rb_vm_insn_addr2insn2 showing up at the top of some
profiles while working on some malloc-related stuff, so I
decided to attack it.

Most notably, the benchmark/bm_vm3_gc.rb improves by over 40%:

  https://80x24.org/spew/20180602220554.GA9991@whir/raw

[ruby-core:87361] [Feature #14814]

git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@63594 b2dd03c8-39d4-4d8f-98ff-823fe69b080e

compile.c

@@ -11,6 +11,7 @@
 
 #include "ruby/encoding.h"
 #include "ruby/re.h"
+#include "ruby/util.h"
 #include "internal.h"
 #include "encindex.h"
 #include <math.h>
@@ -755,20 +756,33 @@ rb_iseq_translate_threaded_code(rb_iseq_t *iseq)
 }
 
 #if OPT_DIRECT_THREADED_CODE || OPT_CALL_THREADED_CODE
-int
+static st_table *addr2insn;
-rb_vm_insn_addr2insn(const void *addr) /* cold path */
-{
-    int insn;
-    const void * const *table = rb_vm_get_insns_address_table();
 
+void
+rb_addr2insn_init(void)
+{
+    const void * const *table = rb_vm_get_insns_address_table();
+    st_data_t insn;
+
+    addr2insn = st_init_numtable_with_size(VM_INSTRUCTION_SIZE);
     for (insn = 0; insn < VM_INSTRUCTION_SIZE; insn++) {
-	if (table[insn] == addr) {
+        st_add_direct(addr2insn, (st_data_t)table[insn], insn);
-	    return insn;
     }
 }
+
+int
+rb_vm_insn_addr2insn(const void *addr)
+{
+    st_data_t key = (st_data_t)addr;
+    st_data_t val;
+
+    if (st_lookup(addr2insn, key, &val)) {
+        return (int)val;
+    }
+
     rb_bug("rb_vm_insn_addr2insn: invalid insn address: %p", addr);
 }
-#endif
+#endif /* OPT_DIRECT_THREADED_CODE || OPT_CALL_THREADED_CODE */
 
 VALUE *
 rb_iseq_original_iseq(const rb_iseq_t *iseq) /* cold path */

eval.c

@@ -66,6 +66,7 @@ ruby_setup(void)
 #endif
     Init_BareVM();
     Init_heap();
+    rb_addr2insn_init();
     Init_vm_objects();
 
     EC_PUSH_TAG(GET_EC());

iseq.c

@@ -118,15 +118,7 @@ rb_iseq_free(const rb_iseq_t *iseq)
 static VALUE
 rb_vm_insn_addr2insn2(const void *addr)
 {
-    VALUE insn;
+    return (VALUE)rb_vm_insn_addr2insn(addr);
-    const void * const *table = rb_vm_get_insns_address_table();
-
-    for (insn = 0; insn < VM_INSTRUCTION_SIZE; insn++) {
-	if (table[insn] == addr) {
-	    return insn;
-	}
-    }
-    rb_bug("rb_vm_insn_addr2insn: invalid insn address: %p", addr);
 }
 #endif
 

vm_core.h

@@ -144,6 +144,11 @@ void *rb_register_sigaltstack(void);
 #endif /* OPT_STACK_CACHING */
 #endif /* OPT_CALL_THREADED_CODE */
 
+#if OPT_DIRECT_THREADED_CODE || OPT_CALL_THREADED_CODE
+void rb_addr2insn_init(void);
+#else
+static inline void rb_addr2insn_init(void) { }
+#endif
 typedef unsigned long rb_num_t;
 typedef   signed long rb_snum_t;