ruby--ruby/ext/objspace/object_tracing.c

/**********************************************************************

  object_tracing.c - Object Tracing mechanism/ObjectSpace extender for MRI.

  $Author$
  created at: Mon May 27 16:27:44 2013

  NOTE: This extension library is not expected to exist except C Ruby.
  NOTE: This feature is an example usage of internal event tracing APIs.

  All the files in this distribution are covered under the Ruby's
  license (see the file COPYING).

**********************************************************************/

#include "ruby/ruby.h"
#include "ruby/debug.h"

size_t rb_gc_count(void); /* from gc.c */

struct traceobj_arg {
    int running;
    VALUE newobj_trace;
    VALUE freeobj_trace;
    st_table *object_table; /* obj (VALUE) -> allocation_info */
    st_table *str_table;    /* cstr -> refcount */
    struct traceobj_arg *prev_traceobj_arg;
};

/* all of information don't need marking. */
struct allocation_info {
    const char *path;
    unsigned long line;
    const char *class_path;
    VALUE mid;
    size_t generation;
};

static const char *
make_unique_str(st_table *tbl, const char *str, long len)
{
    if (!str) {
	return NULL;
    }
    else {
	st_data_t n;
	char *result;

	if (st_lookup(tbl, (st_data_t)str, &n)) {
	    st_insert(tbl, (st_data_t)str, n+1);
	    st_get_key(tbl, (st_data_t)str, (st_data_t *)&result);
	}
	else {
	    result = (char *)ruby_xmalloc(len+1);
	    strncpy(result, str, len);
	    result[len] = 0;
	    st_add_direct(tbl, (st_data_t)result, 1);
	}
	return result;
    }
}

static void
delete_unique_str(st_table *tbl, const char *str)
{
    if (str) {
	st_data_t n;

	st_lookup(tbl, (st_data_t)str, &n);
	if (n == 1) {
	    st_delete(tbl, (st_data_t *)&str, 0);
	    ruby_xfree((char *)str);
	}
	else {
	    st_insert(tbl, (st_data_t)str, n-1);
	}
    }
}

static void
newobj_i(VALUE tpval, void *data)
{
    struct traceobj_arg *arg = (struct traceobj_arg *)data;
    rb_trace_arg_t *tparg = rb_tracearg_from_tracepoint(tpval);
    VALUE obj = rb_tracearg_object(tparg);
    VALUE path = rb_tracearg_path(tparg);
    VALUE line = rb_tracearg_lineno(tparg);
    VALUE mid = rb_tracearg_method_id(tparg);
    VALUE klass = rb_tracearg_defined_class(tparg);
    struct allocation_info *info = (struct allocation_info *)ruby_xmalloc(sizeof(struct allocation_info));
    const char *path_cstr = RTEST(path) ? make_unique_str(arg->str_table, RSTRING_PTR(path), RSTRING_LEN(path)) : 0;
    VALUE class_path = RTEST(klass) ? rb_class_path(klass) : Qnil;
    const char *class_path_cstr = RTEST(class_path) ? make_unique_str(arg->str_table, RSTRING_PTR(class_path), RSTRING_LEN(class_path)) : 0;

    info->path = path_cstr;
    info->line = NUM2INT(line);
    info->mid = mid;
    info->class_path = class_path_cstr;
    info->generation = rb_gc_count();
    st_insert(arg->object_table, (st_data_t)obj, (st_data_t)info);
}

static void
freeobj_i(VALUE tpval, void *data)
{
    struct traceobj_arg *arg = (struct traceobj_arg *)data;
    rb_trace_arg_t *tparg = rb_tracearg_from_tracepoint(tpval);
    VALUE obj = rb_tracearg_object(tparg);
    struct allocation_info *info;

    if (st_delete(arg->object_table, (st_data_t *)&obj, (st_data_t *)&info)) {
	delete_unique_str(arg->str_table, info->path);
	delete_unique_str(arg->str_table, info->class_path);
	ruby_xfree(info);
    }
}

static int
free_keys_i(st_data_t key, st_data_t value, void *data)
{
    ruby_xfree((void *)key);
    return ST_CONTINUE;
}

static int
free_values_i(st_data_t key, st_data_t value, void *data)
{
    ruby_xfree((void *)value);
    return ST_CONTINUE;
}

static struct traceobj_arg *tmp_trace_arg; /* TODO: Do not use global variables */

static struct traceobj_arg *
get_traceobj_arg(void)
{
    if (tmp_trace_arg == 0) {
	tmp_trace_arg = ALLOC_N(struct traceobj_arg, 1);
	tmp_trace_arg->running = 0;
	tmp_trace_arg->newobj_trace = 0;
	tmp_trace_arg->freeobj_trace = 0;
	tmp_trace_arg->object_table = st_init_numtable();
	tmp_trace_arg->str_table = st_init_strtable();
    }
    return tmp_trace_arg;
}

/*
 * call-seq: trace_object_allocations_start
 *
 * Starts tracing object allocations.
 *
 */
static VALUE
trace_object_allocations_start(VALUE self)
{
    struct traceobj_arg *arg = get_traceobj_arg();

    if (arg->running++ > 0) {
	/* do nothing */
    }
    else {
	if (arg->newobj_trace == 0) {
	    arg->newobj_trace = rb_tracepoint_new(0, RUBY_INTERNAL_EVENT_NEWOBJ, newobj_i, arg);
	    arg->freeobj_trace = rb_tracepoint_new(0, RUBY_INTERNAL_EVENT_FREEOBJ, freeobj_i, arg);
	}
	rb_tracepoint_enable(arg->newobj_trace);
	rb_tracepoint_enable(arg->freeobj_trace);
    }

    return Qnil;
}

/*
 * call-seq: trace_object_allocations_stop
 *
 * Stop tracing object allocations.
 *
 * Note that if ::trace_object_allocations_start is called n-times, then stop
 * tracing after calling ::trace_object_allocations_stop n-times.
 *
 */
static VALUE
trace_object_allocations_stop(VALUE self)
{
    struct traceobj_arg *arg = get_traceobj_arg();

    if (arg->running > 0) {
	arg->running--;
    }

    if (arg->running == 0) {
	rb_tracepoint_disable(arg->newobj_trace);
	rb_tracepoint_disable(arg->freeobj_trace);
	arg->newobj_trace = 0;
	arg->freeobj_trace = 0;
    }

    return Qnil;
}

/*
 * call-seq: trace_object_allocations_clear
 *
 * Clear recorded tracing information.
 *
 */
static VALUE
trace_object_allocations_clear(VALUE self)
{
    struct traceobj_arg *arg = get_traceobj_arg();

    /* clear tables */
    st_foreach(arg->object_table, free_values_i, 0);
    st_clear(arg->object_table);
    st_foreach(arg->str_table, free_keys_i, 0);
    st_clear(arg->str_table);

    /* do not touch TracePoints */

    return Qnil;
}

/*
 * call-seq: trace_object_allocations { block }
 *
 * Starts tracing object allocations from the ObjectSpace extension module.
 *
 * For example:
 *
 *	require 'objspace'
 *
 *	class C
 *	  include ObjectSpace
 *
 *	  def foo
 *	    trace_object_allocations do
 *	      obj = Object.new
 *	      p "#{allocation_sourcefile(obj)}:#{allocation_sourceline(obj)}"
 *	    end
 *	  end
 *	end
 *
 *	C.new.foo #=> "objtrace.rb:8"
 *
 * This example has included the ObjectSpace module to make it easier to read,
 * but you can also use the ::trace_object_allocations notation (recommended).
 *
 * Note that this feature introduces a huge performance decrease and huge
 * memory consumption.
 */
static VALUE
trace_object_allocations(VALUE self)
{
    trace_object_allocations_start(self);
    return rb_ensure(rb_yield, Qnil, trace_object_allocations_stop, self);
}

static struct allocation_info *
lookup_allocation_info(VALUE obj)
{
    if (tmp_trace_arg) {
	struct allocation_info *info;
	if (st_lookup(tmp_trace_arg->object_table, obj, (st_data_t *)&info)) {
	    return info;
	}
    }
    return NULL;
}

/*
 * call-seq: allocation_sourcefile(object) -> string
 *
 * Returns the source file origin from the given +object+.
 *
 * See ::trace_object_allocations for more information and examples.
 */
static VALUE
allocation_sourcefile(VALUE self, VALUE obj)
{
    struct allocation_info *info = lookup_allocation_info(obj);

    if (info && info->path) {
	return rb_str_new2(info->path);
    }
    else {
	return Qnil;
    }
}

/*
 * call-seq: allocation_sourceline(object) -> string
 *
 * Returns the original line from source for from the given +object+.
 *
 * See ::trace_object_allocations for more information and examples.
 */
static VALUE
allocation_sourceline(VALUE self, VALUE obj)
{
    struct allocation_info *info = lookup_allocation_info(obj);

    if (info) {
	return INT2FIX(info->line);
    }
    else {
	return Qnil;
    }
}

/*
 * call-seq: allocation_class_path(object) -> string
 *
 * Returns the class for the given +object+.
 *
 *	class A
 *	  def foo
 *	    ObjectSpace::trace_object_allocations do
 *	      obj = Object.new
 *	      p "#{ObjectSpace::allocation_class_path(obj)}"
 *	    end
 *	  end
 *	end
 *
 *	A.new.foo #=> "Class"
 *
 * See ::trace_object_allocations for more information and examples.
 */
static VALUE
allocation_class_path(VALUE self, VALUE obj)
{
    struct allocation_info *info = lookup_allocation_info(obj);

    if (info && info->class_path) {
	return rb_str_new2(info->class_path);
    }
    else {
	return Qnil;
    }
}

/*
 * call-seq: allocation_method_id(object) -> string
 *
 * Returns the method identifier for the given +object+.
 *
 *	class A
 *	  include ObjectSpace
 *
 *	  def foo
 *	    trace_object_allocations do
 *	      obj = Object.new
 *	      p "#{allocation_class_path(obj)}##{allocation_method_id(obj)}"
 *	    end
 *	  end
 *	end
 *
 *	A.new.foo #=> "Class#new"
 *
 * See ::trace_object_allocations for more information and examples.
 */
static VALUE
allocation_method_id(VALUE self, VALUE obj)
{
    struct allocation_info *info = lookup_allocation_info(obj);
    if (info) {
	return info->mid;
    }
    else {
	return Qnil;
    }
}

/*
 * call-seq: allocation_generation(object) -> Fixnum
 *
 * Returns garbage collector generation for the given +object+.
 *
 *	class B
 *	  include ObjectSpace
 *
 *	  def foo
 *	    trace_object_allocations do
 *	      obj = Object.new
 *	      p "Generation is #{allocation_generation(obj)}"
 *	    end
 *	  end
 *	end
 *
 *	B.new.foo #=> "Generation is 3"
 *
 * See ::trace_object_allocations for more information and examples.
 */
static VALUE
allocation_generation(VALUE self, VALUE obj)
{
    struct allocation_info *info = lookup_allocation_info(obj);
    if (info) {
	return SIZET2NUM(info->generation);
    }
    else {
	return Qnil;
    }
}

void
Init_object_tracing(VALUE rb_mObjSpace)
{
#if 0
    rb_mObjSpace = rb_define_module("ObjectSpace"); /* let rdoc know */
#endif

    rb_define_module_function(rb_mObjSpace, "trace_object_allocations", trace_object_allocations, 0);
    rb_define_module_function(rb_mObjSpace, "trace_object_allocations_start", trace_object_allocations_start, 0);
    rb_define_module_function(rb_mObjSpace, "trace_object_allocations_stop", trace_object_allocations_stop, 0);
    rb_define_module_function(rb_mObjSpace, "trace_object_allocations_clear", trace_object_allocations_clear, 0);

    rb_define_module_function(rb_mObjSpace, "allocation_sourcefile", allocation_sourcefile, 1);
    rb_define_module_function(rb_mObjSpace, "allocation_sourceline", allocation_sourceline, 1);
    rb_define_module_function(rb_mObjSpace, "allocation_class_path", allocation_class_path, 1);
    rb_define_module_function(rb_mObjSpace, "allocation_method_id", allocation_method_id, 1);
    rb_define_module_function(rb_mObjSpace, "allocation_generation", allocation_generation, 1);
}