diff --git a/tools/perf/Build b/tools/perf/Build
index 72237455b400..2c7aaf2ba119 100644
--- a/tools/perf/Build
+++ b/tools/perf/Build
@@ -1,5 +1,6 @@
 perf-y += builtin-bench.o
 perf-y += builtin-annotate.o
+perf-y += builtin-config.o
 perf-y += builtin-diff.o
 perf-y += builtin-evlist.o
 perf-y += builtin-help.o
diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt
new file mode 100644
index 000000000000..b9ca1e304158
--- /dev/null
+++ b/tools/perf/Documentation/perf-config.txt
@@ -0,0 +1,103 @@
+perf-config(1)
+==============
+
+NAME
+----
+perf-config - Get and set variables in a configuration file.
+
+SYNOPSIS
+--------
+[verse]
+'perf config' -l | --list
+
+DESCRIPTION
+-----------
+You can manage variables in a configuration file with this command.
+
+OPTIONS
+-------
+
+-l::
+--list::
+	Show current config variables, name and value, for all sections.
+
+CONFIGURATION FILE
+------------------
+
+The perf configuration file contains many variables to change various
+aspects of each of its tools, including output, disk usage, etc.
+The '$HOME/.perfconfig' file is used to store a per-user configuration.
+The file '$(sysconfdir)/perfconfig' can be used to
+store a system-wide default configuration.
+
+Syntax
+~~~~~~
+
+The file consist of sections. A section starts with its name
+surrounded by square brackets and continues till the next section
+begins. Each variable must be in a section, and have the form
+'name = value', for example:
+
+	[section]
+		name1 = value1
+		name2 = value2
+
+Section names are case sensitive and can contain any characters except
+newline (double quote `"` and backslash have to be escaped as `\"` and `\\`,
+respectively). Section headers can't span multiple lines.
+
+Example
+~~~~~~~
+
+Given a $HOME/.perfconfig like this:
+
+#
+# This is the config file, and
+# a '#' and ';' character indicates a comment
+#
+
+	[colors]
+		# Color variables
+		top = red, default
+		medium = green, default
+		normal = lightgray, default
+		selected = white, lightgray
+		code = blue, default
+		addr = magenta, default
+		root = white, blue
+
+	[tui]
+		# Defaults if linked with libslang
+		report = on
+		annotate = on
+		top = on
+
+	[buildid]
+		# Default, disable using /dev/null
+		dir = ~/.debug
+
+	[annotate]
+		# Defaults
+		hide_src_code = false
+		use_offset = true
+		jump_arrows = true
+		show_nr_jumps = false
+
+	[help]
+		# Format can be man, info, web or html
+		format = man
+		autocorrect = 0
+
+	[ui]
+		show-headers = true
+
+	[call-graph]
+		# fp (framepointer), dwarf
+		record-mode = fp
+		print-type = graph
+		order = caller
+		sort-key = function
+
+SEE ALSO
+--------
+linkperf:perf[1]
diff --git a/tools/perf/builtin-config.c b/tools/perf/builtin-config.c
new file mode 100644
index 000000000000..427ea7a705b8
--- /dev/null
+++ b/tools/perf/builtin-config.c
@@ -0,0 +1,66 @@
+/*
+ * builtin-config.c
+ *
+ * Copyright (C) 2015, Taeung Song <treeze.taeung@gmail.com>
+ *
+ */
+#include "builtin.h"
+
+#include "perf.h"
+
+#include "util/cache.h"
+#include "util/parse-options.h"
+#include "util/util.h"
+#include "util/debug.h"
+
+static const char * const config_usage[] = {
+	"perf config [options]",
+	NULL
+};
+
+enum actions {
+	ACTION_LIST = 1
+} actions;
+
+static struct option config_options[] = {
+	OPT_SET_UINT('l', "list", &actions,
+		     "show current config variables", ACTION_LIST),
+	OPT_END()
+};
+
+static int show_config(const char *key, const char *value,
+		       void *cb __maybe_unused)
+{
+	if (value)
+		printf("%s=%s\n", key, value);
+	else
+		printf("%s\n", key);
+
+	return 0;
+}
+
+int cmd_config(int argc, const char **argv, const char *prefix __maybe_unused)
+{
+	int ret = 0;
+
+	argc = parse_options(argc, argv, config_options, config_usage,
+			     PARSE_OPT_STOP_AT_NON_OPTION);
+
+	switch (actions) {
+	case ACTION_LIST:
+		if (argc) {
+			pr_err("Error: takes no arguments\n");
+			parse_options_usage(config_usage, config_options, "l", 1);
+		} else {
+			ret = perf_config(show_config, NULL);
+			if (ret < 0)
+				pr_err("Nothing configured, "
+				       "please check your ~/.perfconfig file\n");
+		}
+		break;
+	default:
+		usage_with_options(config_usage, config_options);
+	}
+
+	return ret;
+}
diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h
index 3688ad29085f..3f871b54e261 100644
--- a/tools/perf/builtin.h
+++ b/tools/perf/builtin.h
@@ -17,6 +17,7 @@ extern int cmd_annotate(int argc, const char **argv, const char *prefix);
 extern int cmd_bench(int argc, const char **argv, const char *prefix);
 extern int cmd_buildid_cache(int argc, const char **argv, const char *prefix);
 extern int cmd_buildid_list(int argc, const char **argv, const char *prefix);
+extern int cmd_config(int argc, const char **argv, const char *prefix);
 extern int cmd_diff(int argc, const char **argv, const char *prefix);
 extern int cmd_evlist(int argc, const char **argv, const char *prefix);
 extern int cmd_help(int argc, const char **argv, const char *prefix);
diff --git a/tools/perf/command-list.txt b/tools/perf/command-list.txt
index 00fcaf8a5b8d..acc3ea7d90b7 100644
--- a/tools/perf/command-list.txt
+++ b/tools/perf/command-list.txt
@@ -9,6 +9,7 @@ perf-buildid-cache		mainporcelain common
 perf-buildid-list		mainporcelain common
 perf-data			mainporcelain common
 perf-diff			mainporcelain common
+perf-config			mainporcelain common
 perf-evlist			mainporcelain common
 perf-inject			mainporcelain common
 perf-kmem			mainporcelain common
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 3d4c7c09adea..4bee53c3f796 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -39,6 +39,7 @@ struct cmd_struct {
 static struct cmd_struct commands[] = {
 	{ "buildid-cache", cmd_buildid_cache, 0 },
 	{ "buildid-list", cmd_buildid_list, 0 },
+	{ "config",	cmd_config,	0 },
 	{ "diff",	cmd_diff,	0 },
 	{ "evlist",	cmd_evlist,	0 },
 	{ "help",	cmd_help,	0 },
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
index 01f0b61de53d..b2357e8115a2 100644
--- a/tools/perf/tests/dwarf-unwind.c
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -51,6 +51,12 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
 		"krava_1",
 		"test__dwarf_unwind"
 	};
+	/*
+	 * The funcs[MAX_STACK] array index, based on the
+	 * callchain order setup.
+	 */
+	int idx = callchain_param.order == ORDER_CALLER ?
+		  MAX_STACK - *cnt - 1 : *cnt;
 
 	if (*cnt >= MAX_STACK) {
 		pr_debug("failed: crossed the max stack value %d\n", MAX_STACK);
@@ -63,8 +69,10 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
 		return -1;
 	}
 
-	pr_debug("got: %s 0x%" PRIx64 "\n", symbol, entry->ip);
-	return strcmp((const char *) symbol, funcs[(*cnt)++]);
+	(*cnt)++;
+	pr_debug("got: %s 0x%" PRIx64 ", expecting %s\n",
+		 symbol, entry->ip, funcs[idx]);
+	return strcmp((const char *) symbol, funcs[idx]);
 }
 
 __attribute__ ((noinline))
@@ -105,8 +113,16 @@ static int compare(void *p1, void *p2)
 	/* Any possible value should be 'thread' */
 	struct thread *thread = *(struct thread **)p1;
 
-	if (global_unwind_retval == -INT_MAX)
+	if (global_unwind_retval == -INT_MAX) {
+		/* Call unwinder twice for both callchain orders. */
+		callchain_param.order = ORDER_CALLER;
+
 		global_unwind_retval = unwind_thread(thread);
+		if (!global_unwind_retval) {
+			callchain_param.order = ORDER_CALLEE;
+			global_unwind_retval = unwind_thread(thread);
+		}
+	}
 
 	return p1 - p2;
 }
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 6e9b5f2099e1..8ac8f043004c 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -143,6 +143,7 @@ extern __thread struct callchain_cursor callchain_cursor;
 static inline void callchain_init(struct callchain_root *root)
 {
 	INIT_LIST_HEAD(&root->node.val);
+	INIT_LIST_HEAD(&root->node.parent_val);
 
 	root->node.parent = NULL;
 	root->node.hit = 0;
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index 2dcfe9a7c8d0..db8142ba7cb9 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -11,6 +11,7 @@
 #include <linux/types.h>
 #include "event.h"
 #include "perf_regs.h"
+#include "callchain.h"
 
 static char *debuginfo_path;
 
@@ -52,25 +53,28 @@ static int report_module(u64 ip, struct unwind_info *ui)
 	return __report_module(&al, ip, ui);
 }
 
+/*
+ * Store all entries within entries array,
+ * we will process it after we finish unwind.
+ */
 static int entry(u64 ip, struct unwind_info *ui)
 
 {
-	struct unwind_entry e;
+	struct unwind_entry *e = &ui->entries[ui->idx++];
 	struct addr_location al;
 
 	if (__report_module(&al, ip, ui))
 		return -1;
 
-	e.ip  = ip;
-	e.map = al.map;
-	e.sym = al.sym;
+	e->ip  = ip;
+	e->map = al.map;
+	e->sym = al.sym;
 
 	pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n",
 		 al.sym ? al.sym->name : "''",
 		 ip,
 		 al.map ? al.map->map_ip(al.map, ip) : (u64) 0);
-
-	return ui->cb(&e, ui->arg);
+	return 0;
 }
 
 static pid_t next_thread(Dwfl *dwfl, void *arg, void **thread_argp)
@@ -168,7 +172,7 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 			struct perf_sample *data,
 			int max_stack)
 {
-	struct unwind_info ui = {
+	struct unwind_info *ui, ui_buf = {
 		.sample		= data,
 		.thread		= thread,
 		.machine	= thread->mg->machine,
@@ -177,35 +181,54 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 		.max_stack	= max_stack,
 	};
 	Dwarf_Word ip;
-	int err = -EINVAL;
+	int err = -EINVAL, i;
 
 	if (!data->user_regs.regs)
 		return -EINVAL;
 
-	ui.dwfl = dwfl_begin(&offline_callbacks);
-	if (!ui.dwfl)
+	ui = zalloc(sizeof(ui_buf) + sizeof(ui_buf.entries[0]) * max_stack);
+	if (!ui)
+		return -ENOMEM;
+
+	*ui = ui_buf;
+
+	ui->dwfl = dwfl_begin(&offline_callbacks);
+	if (!ui->dwfl)
 		goto out;
 
 	err = perf_reg_value(&ip, &data->user_regs, PERF_REG_IP);
 	if (err)
 		goto out;
 
-	err = report_module(ip, &ui);
+	err = report_module(ip, ui);
 	if (err)
 		goto out;
 
-	if (!dwfl_attach_state(ui.dwfl, EM_NONE, thread->tid, &callbacks, &ui))
+	if (!dwfl_attach_state(ui->dwfl, EM_NONE, thread->tid, &callbacks, ui))
 		goto out;
 
-	err = dwfl_getthread_frames(ui.dwfl, thread->tid, frame_callback, &ui);
+	err = dwfl_getthread_frames(ui->dwfl, thread->tid, frame_callback, ui);
 
-	if (err && !ui.max_stack)
+	if (err && !ui->max_stack)
 		err = 0;
 
+	/*
+	 * Display what we got based on the order setup.
+	 */
+	for (i = 0; i < ui->idx && !err; i++) {
+		int j = i;
+
+		if (callchain_param.order == ORDER_CALLER)
+			j = ui->idx - i - 1;
+
+		err = ui->entries[j].ip ? ui->cb(&ui->entries[j], ui->arg) : 0;
+	}
+
  out:
 	if (err)
 		pr_debug("unwind: failed with '%s'\n", dwfl_errmsg(-1));
 
-	dwfl_end(ui.dwfl);
+	dwfl_end(ui->dwfl);
+	free(ui);
 	return 0;
 }
diff --git a/tools/perf/util/unwind-libdw.h b/tools/perf/util/unwind-libdw.h
index 417a1426f3ad..58328669ed16 100644
--- a/tools/perf/util/unwind-libdw.h
+++ b/tools/perf/util/unwind-libdw.h
@@ -16,6 +16,8 @@ struct unwind_info {
 	unwind_entry_cb_t	cb;
 	void			*arg;
 	int			max_stack;
+	int			idx;
+	struct unwind_entry	entries[];
 };
 
 #endif /* __PERF_UNWIND_LIBDW_H */
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index c83832b555e5..3c258a0e4092 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -614,23 +614,48 @@ void unwind__finish_access(struct thread *thread)
 static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
 		       void *arg, int max_stack)
 {
+	u64 val;
+	unw_word_t ips[max_stack];
 	unw_addr_space_t addr_space;
 	unw_cursor_t c;
-	int ret;
+	int ret, i = 0;
 
-	addr_space = thread__priv(ui->thread);
-	if (addr_space == NULL)
-		return -1;
-
-	ret = unw_init_remote(&c, addr_space, ui);
+	ret = perf_reg_value(&val, &ui->sample->user_regs, PERF_REG_IP);
 	if (ret)
-		display_error(ret);
+		return ret;
 
-	while (!ret && (unw_step(&c) > 0) && max_stack--) {
-		unw_word_t ip;
+	ips[i++] = (unw_word_t) val;
 
-		unw_get_reg(&c, UNW_REG_IP, &ip);
-		ret = ip ? entry(ip, ui->thread, cb, arg) : 0;
+	/*
+	 * If we need more than one entry, do the DWARF
+	 * unwind itself.
+	 */
+	if (max_stack - 1 > 0) {
+		addr_space = thread__priv(ui->thread);
+		if (addr_space == NULL)
+			return -1;
+
+		ret = unw_init_remote(&c, addr_space, ui);
+		if (ret)
+			display_error(ret);
+
+		while (!ret && (unw_step(&c) > 0) && i < max_stack) {
+			unw_get_reg(&c, UNW_REG_IP, &ips[i]);
+			++i;
+		}
+
+		max_stack = i;
+	}
+
+	/*
+	 * Display what we got based on the order setup.
+	 */
+	for (i = 0; i < max_stack && !ret; i++) {
+		int j = i;
+
+		if (callchain_param.order == ORDER_CALLER)
+			j = max_stack - i - 1;
+		ret = ips[j] ? entry(ips[j], ui->thread, cb, arg) : 0;
 	}
 
 	return ret;
@@ -640,24 +665,17 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 			struct thread *thread,
 			struct perf_sample *data, int max_stack)
 {
-	u64 ip;
 	struct unwind_info ui = {
 		.sample       = data,
 		.thread       = thread,
 		.machine      = thread->mg->machine,
 	};
-	int ret;
 
 	if (!data->user_regs.regs)
 		return -EINVAL;
 
-	ret = perf_reg_value(&ip, &data->user_regs, PERF_REG_IP);
-	if (ret)
-		return ret;
+	if (max_stack <= 0)
+		return -EINVAL;
 
-	ret = entry(ip, thread, cb, arg);
-	if (ret)
-		return -ENOMEM;
-
-	return --max_stack > 0 ? get_entries(&ui, cb, arg, max_stack) : 0;
+	return get_entries(&ui, cb, arg, max_stack);
 }