Resize arrays in `rb_ary_freeze` and use it for freezing arrays

While working on a separate issue we found that in some cases `ary_heap_realloc` was being called on frozen arrays. To fix this, this change does the following: 1) Updates `rb_ary_freeze` to assert the type is an array, return if already frozen, and shrink the capacity if it is not embedded, shared or a shared root. 2) Replaces `rb_obj_freeze` with `rb_ary_freeze` when the object is always an array. 3) In `ary_heap_realloc`, ensure the new capa is set with `ARY_SET_CAPA`. Previously the change in capa was not set. 4) Adds an assertion to `ary_heap_realloc` that the array is not frozen. Some of this work was originally done in https://github.com/ruby/ruby/pull/2640, referencing this issue https://bugs.ruby-lang.org/issues/16291. There didn't appear to be any objections to this PR, it appears to have simply lost traction. The original PR made changes to arrays and strings at the same time, this PR only does arrays. Also it was old enough that rather than revive that branch I've made a new one. I added Lourens as co-author in addtion to Aaron who helped me with this patch. The original PR made this change for performance reasons, and while that's still true for this PR, the goal of this PR is to avoid calling `ary_heap_realloc` on frozen arrays. The capacity should be shrunk _before_ the array is frozen, not after. Co-authored-by: Aaron Patterson <[email protected]> Co-Authored-By: methodmissing <[email protected]>
author: eileencodes <[email protected]> 2024-06-18 14:52:18 -0400
committer: Aaron Patterson <[email protected]> 2024-07-02 10:34:23 -0700
commit: d25b74b32cbce4fcaed503f124fa8e7d721f18bf (patch)
tree: f83f20a0a5b0f55aa6e8bc7e9d471114f45cce9d
parent: cee62c6738c42ce774e96e180cf2d46afb8e9cbe (diff)
8 files changed, 29 insertions, 16 deletions
diff --git a/array.c b/array.c
index dab933776f..6dd46ca685 100644
--- a/array.c
+++ b/array.c
@@ -370,6 +370,7 @@ ary_heap_free(VALUE ary)
 static size_t
 ary_heap_realloc(VALUE ary, size_t new_capa)
 {
+    RUBY_ASSERT(!OBJ_FROZEN(ary));
     SIZED_REALLOC_N(RARRAY(ary)->as.heap.ptr, VALUE, new_capa, ARY_HEAP_CAPA(ary));
     ary_verify(ary);
 
@@ -441,7 +442,10 @@ ary_shrink_capa(VALUE ary)
     long old_capa = ARY_HEAP_CAPA(ary);
     RUBY_ASSERT(!ARY_SHARED_P(ary));
     RUBY_ASSERT(old_capa >= capacity);
-    if (old_capa > capacity) ary_heap_realloc(ary, capacity);
+    if (old_capa > capacity) {
+        size_t new_capa = ary_heap_realloc(ary, capacity);
+        ARY_SET_CAPA(ary, new_capa);
+    }
 
     ary_verify(ary);
 }
@@ -639,6 +643,14 @@ ary_ensure_room_for_push(VALUE ary, long add_len)
 VALUE
 rb_ary_freeze(VALUE ary)
 {
+    RUBY_ASSERT(RB_TYPE_P(ary, T_ARRAY));
+
+    if (OBJ_FROZEN(ary)) return ary;
+
+    if (!ARY_EMBED_P(ary) && !ARY_SHARED_P(ary) && !ARY_SHARED_ROOT_P(ary)) {
+        ary_shrink_capa(ary);
+    }
+
     return rb_obj_freeze(ary);
 }
 
@@ -889,7 +901,7 @@ rb_setup_fake_ary(struct RArray *fake_ary, const VALUE *list, long len, bool fre
     ARY_SET_PTR(ary, list);
     ARY_SET_HEAP_LEN(ary, len);
     ARY_SET_CAPA(ary, len);
-    if (freeze) OBJ_FREEZE(ary);
+    if (freeze) rb_ary_freeze(ary);
     return ary;
 }
 
@@ -6458,7 +6470,7 @@ rb_ary_flatten_bang(int argc, VALUE *argv, VALUE ary)
     if (result == ary) {
         return Qnil;
     }
-    if (!(mod = ARY_EMBED_P(result))) rb_obj_freeze(result);
+    if (!(mod = ARY_EMBED_P(result))) rb_ary_freeze(result);
     rb_ary_replace(ary, result);
     if (mod) ARY_SET_EMBED_LEN(result, 0);
 
@@ -8754,6 +8766,7 @@ Init_Array(void)
     rb_define_method(rb_cArray, "one?", rb_ary_one_p, -1);
     rb_define_method(rb_cArray, "dig", rb_ary_dig, -1);
     rb_define_method(rb_cArray, "sum", rb_ary_sum, -1);
+    rb_define_method(rb_cArray, "freeze", rb_ary_freeze, 0);
 
     rb_define_method(rb_cArray, "deconstruct", rb_ary_deconstruct, 0);
 }
diff --git a/ast.c b/ast.c
index 12b3996f94..cc4bca1a1a 100644
--- a/ast.c
+++ b/ast.c
@@ -769,7 +769,7 @@ ast_node_all_tokens(rb_execution_context_t *ec, VALUE self)
         token = rb_ary_new_from_args(4, INT2FIX(parser_token->id), ID2SYM(rb_intern(parser_token->type_name)), str, loc);
         rb_ary_push(all_tokens, token);
     }
-    rb_obj_freeze(all_tokens);
+    rb_ary_freeze(all_tokens);
 
     return all_tokens;
 }
diff --git a/compile.c b/compile.c
index a9fe5ce114..ce2f7473fd 100644
--- a/compile.c
+++ b/compile.c
@@ -4840,7 +4840,7 @@ static_literal_value(const NODE *node, rb_iseq_t *iseq)
         if (ISEQ_COMPILE_DATA(iseq)->option->debug_frozen_string_literal || RTEST(ruby_debug)) {
             VALUE debug_info = rb_ary_new_from_args(2, rb_iseq_path(iseq), INT2FIX((int)nd_line(node)));
             VALUE lit = rb_str_dup(get_string_value(node));
-            rb_ivar_set(lit, id_debug_created_info, rb_obj_freeze(debug_info));
+            rb_ivar_set(lit, id_debug_created_info, rb_ary_freeze(debug_info));
             return rb_str_freeze(lit);
         }
         else {
@@ -10752,7 +10752,7 @@ iseq_compile_each0(rb_iseq_t *iseq, LINK_ANCHOR *const ret, const NODE *const no
                 if (ISEQ_COMPILE_DATA(iseq)->option->debug_frozen_string_literal || RTEST(ruby_debug)) {
                     VALUE debug_info = rb_ary_new_from_args(2, rb_iseq_path(iseq), INT2FIX(line));
                     lit = rb_str_dup(lit);
-                    rb_ivar_set(lit, id_debug_created_info, rb_obj_freeze(debug_info));
+                    rb_ivar_set(lit, id_debug_created_info, rb_ary_freeze(debug_info));
                     lit = rb_str_freeze(lit);
                 }
                 ADD_INSN1(ret, node, putobject, lit);
@@ -11321,7 +11321,7 @@ rb_insns_name_array(void)
     for (i = 0; i < VM_INSTRUCTION_SIZE; i++) {
         rb_ary_push(ary, rb_fstring_cstr(insn_name(i)));
     }
-    return rb_obj_freeze(ary);
+    return rb_ary_freeze(ary);
 }
 
 static LABEL *
@@ -13709,7 +13709,7 @@ ibf_load_object_array(const struct ibf_load *load, const struct ibf_object_heade
         rb_ary_push(ary, ibf_load_object(load, index));
     }
 
-    if (header->frozen) rb_obj_freeze(ary);
+    if (header->frozen) rb_ary_freeze(ary);
 
     return ary;
 }
diff --git a/enumerator.c b/enumerator.c
index 193a865dbc..b8ca6bddd2 100644
--- a/enumerator.c
+++ b/enumerator.c
@@ -3181,7 +3181,7 @@ enum_chain_initialize(VALUE obj, VALUE enums)
 
     if (!ptr) rb_raise(rb_eArgError, "unallocated chain");
 
-    ptr->enums = rb_obj_freeze(enums);
+    ptr->enums = rb_ary_freeze(enums);
     ptr->pos = -1;
 
     return obj;
@@ -3509,7 +3509,7 @@ enum_product_initialize(int argc, VALUE *argv, VALUE obj)
 
     if (!ptr) rb_raise(rb_eArgError, "unallocated product");
 
-    ptr->enums = rb_obj_freeze(enums);
+    ptr->enums = rb_ary_freeze(enums);
 
     return obj;
 }
diff --git a/ext/date/date_core.c b/ext/date/date_core.c
index ca9449f0e9..823c0bc2a5 100644
--- a/ext/date/date_core.c
+++ b/ext/date/date_core.c
@@ -57,7 +57,7 @@ static VALUE sym_hour, sym_min, sym_sec, sym_sec_fraction, sym_zone;
 #define f_add3(x,y,z) f_add(f_add(x, y), z)
 #define f_sub3(x,y,z) f_sub(f_sub(x, y), z)
 
-#define f_frozen_ary(...) rb_obj_freeze(rb_ary_new3(__VA_ARGS__))
+#define f_frozen_ary(...) rb_ary_freeze(rb_ary_new3(__VA_ARGS__))
 
 static VALUE date_initialize(int argc, VALUE *argv, VALUE self);
 static VALUE datetime_initialize(int argc, VALUE *argv, VALUE self);
@@ -9466,7 +9466,7 @@ mk_ary_of_str(long len, const char *a[])
 	}
 	rb_ary_push(o, e);
     }
-    rb_obj_freeze(o);
+    rb_ary_freeze(o);
     return o;
 }
 
diff --git a/iseq.c b/iseq.c
index 85d4cca000..ad6ed332e8 100644
--- a/iseq.c
+++ b/iseq.c
@@ -521,7 +521,7 @@ rb_iseq_pathobj_new(VALUE path, VALUE realpath)
     else {
         if (!NIL_P(realpath)) realpath = rb_fstring(realpath);
         pathobj = rb_ary_new_from_args(2, rb_fstring(path), realpath);
-        rb_obj_freeze(pathobj);
+        rb_ary_freeze(pathobj);
     }
     return pathobj;
 }
diff --git a/load.c b/load.c
index 89e9ea8f99..a1729c2ba1 100644
--- a/load.c
+++ b/load.c
@@ -104,7 +104,7 @@ rb_construct_expanded_load_path(rb_vm_t *vm, enum expand_type type, int *has_rel
         if (NIL_P(expanded_path)) expanded_path = as_str;
         rb_ary_push(ary, rb_fstring(expanded_path));
     }
-    rb_obj_freeze(ary);
+    rb_ary_freeze(ary);
     vm->expanded_load_path = ary;
     rb_ary_replace(vm->load_path_snapshot, vm->load_path);
 }
diff --git a/prism_compile.c b/prism_compile.c
index 7149ca7474..467da684f1 100644
--- a/prism_compile.c
+++ b/prism_compile.c
@@ -299,7 +299,7 @@ parse_static_literal_string(rb_iseq_t *iseq, const pm_scope_node_t *scope_node,
         int line_number = pm_node_line_number(scope_node->parser, node);
         VALUE debug_info = rb_ary_new_from_args(2, rb_iseq_path(iseq), INT2FIX(line_number));
         value = rb_str_dup(value);
-        rb_ivar_set(value, id_debug_created_info, rb_obj_freeze(debug_info));
+        rb_ivar_set(value, id_debug_created_info, rb_ary_freeze(debug_info));
         rb_str_freeze(value);
     }
 
@@ -693,7 +693,7 @@ pm_static_literal_string(rb_iseq_t *iseq, VALUE string, int line_number)
 {
     if (ISEQ_COMPILE_DATA(iseq)->option->debug_frozen_string_literal || RTEST(ruby_debug)) {
         VALUE debug_info = rb_ary_new_from_args(2, rb_iseq_path(iseq), INT2FIX(line_number));
-        rb_ivar_set(string, id_debug_created_info, rb_obj_freeze(debug_info));
+        rb_ivar_set(string, id_debug_created_info, rb_ary_freeze(debug_info));
         return rb_str_freeze(string);
     }
     else {
author	eileencodes <[email protected]>	2024-06-18 14:52:18 -0400
committer	Aaron Patterson <[email protected]>	2024-07-02 10:34:23 -0700
commit	d25b74b32cbce4fcaed503f124fa8e7d721f18bf (patch)
tree	f83f20a0a5b0f55aa6e8bc7e9d471114f45cce9d
parent	cee62c6738c42ce774e96e180cf2d46afb8e9cbe (diff)