Linux-libre 4.6.2-gnu

90 files changed, 6419 insertions, 1248 deletions

diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 5eec53a3f..da48fd843 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -1,4 +1,3 @@
-libperf-y += abspath.o
 libperf-y += alias.o
 libperf-y += annotate.o
 libperf-y += build-id.o
@@ -82,6 +81,7 @@ libperf-y += parse-branch-options.o
 libperf-y += parse-regs-options.o
 libperf-y += term.o
 libperf-y += help-unknown-cmd.o
+libperf-y += mem-events.o
 
 libperf-$(CONFIG_LIBBPF) += bpf-loader.o
 libperf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o
@@ -105,8 +105,17 @@ libperf-y += scripting-engines/
 
 libperf-$(CONFIG_ZLIB) += zlib.o
 libperf-$(CONFIG_LZMA) += lzma.o
+libperf-y += demangle-java.o
+
+ifdef CONFIG_JITDUMP
+libperf-$(CONFIG_LIBELF) += jitdump.o
+libperf-$(CONFIG_LIBELF) += genelf.o
+libperf-$(CONFIG_LIBELF) += genelf_debug.o
+endif
 
 CFLAGS_config.o   += -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
+# avoid compiler warnings in 32-bit mode
+CFLAGS_genelf_debug.o  += -Wno-packed
 
 $(OUTPUT)util/parse-events-flex.c: util/parse-events.l $(OUTPUT)util/parse-events-bison.c
 	$(call rule_mkdir)
diff --git a/tools/perf/util/abspath.c b/tools/perf/util/abspath.c
deleted file mode 100644
index 0e76affe9..000000000
--- a/tools/perf/util/abspath.c
+++ /dev/null
@@ -1,37 +0,0 @@
-#include "cache.h"
-
-static const char *get_pwd_cwd(void)
-{
-	static char cwd[PATH_MAX + 1];
-	char *pwd;
-	struct stat cwd_stat, pwd_stat;
-	if (getcwd(cwd, PATH_MAX) == NULL)
-		return NULL;
-	pwd = getenv("PWD");
-	if (pwd && strcmp(pwd, cwd)) {
-		stat(cwd, &cwd_stat);
-		if (!stat(pwd, &pwd_stat) &&
-		    pwd_stat.st_dev == cwd_stat.st_dev &&
-		    pwd_stat.st_ino == cwd_stat.st_ino) {
-			strlcpy(cwd, pwd, PATH_MAX);
-		}
-	}
-	return cwd;
-}
-
-const char *make_nonrelative_path(const char *path)
-{
-	static char buf[PATH_MAX + 1];
-
-	if (is_absolute_path(path)) {
-		if (strlcpy(buf, path, PATH_MAX) >= PATH_MAX)
-			die("Too long path: %.*s", 60, path);
-	} else {
-		const char *cwd = get_pwd_cwd();
-		if (!cwd)
-			die("Cannot determine the current working directory");
-		if (snprintf(buf, PATH_MAX, "%s/%s", cwd, path) >= PATH_MAX)
-			die("Too long path: %.*s", 60, path);
-	}
-	return buf;
-}
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index cea323d9e..9241f8c2b 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -158,7 +158,7 @@ int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize);
 
 int hist_entry__annotate(struct hist_entry *he, size_t privsize);
 
-int symbol__annotate_init(struct map *map __maybe_unused, struct symbol *sym);
+int symbol__annotate_init(struct map *map, struct symbol *sym);
 int symbol__annotate_printf(struct symbol *sym, struct map *map,
 			    struct perf_evsel *evsel, bool full_paths,
 			    int min_pcnt, int max_lines, int context);
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 360fda01f..ec164fe70 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -478,10 +478,11 @@ void auxtrace_heap__pop(struct auxtrace_heap *heap)
 			 heap_array[last].ordinal);
 }
 
-size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr)
+size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr,
+				       struct perf_evlist *evlist)
 {
 	if (itr)
-		return itr->info_priv_size(itr);
+		return itr->info_priv_size(itr, evlist);
 	return 0;
 }
 
@@ -852,7 +853,7 @@ int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr,
 	int err;
 
 	pr_debug2("Synthesizing auxtrace information\n");
-	priv_size = auxtrace_record__info_priv_size(itr);
+	priv_size = auxtrace_record__info_priv_size(itr, session->evlist);
 	ev = zalloc(sizeof(struct auxtrace_info_event) + priv_size);
 	if (!ev)
 		return -ENOMEM;
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index b86f90db1..57ff31ecb 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -293,7 +293,8 @@ struct auxtrace_record {
 	int (*recording_options)(struct auxtrace_record *itr,
 				 struct perf_evlist *evlist,
 				 struct record_opts *opts);
-	size_t (*info_priv_size)(struct auxtrace_record *itr);
+	size_t (*info_priv_size)(struct auxtrace_record *itr,
+				 struct perf_evlist *evlist);
 	int (*info_fill)(struct auxtrace_record *itr,
 			 struct perf_session *session,
 			 struct auxtrace_info_event *auxtrace_info,
@@ -429,7 +430,8 @@ int auxtrace_parse_snapshot_options(struct auxtrace_record *itr,
 int auxtrace_record__options(struct auxtrace_record *itr,
 			     struct perf_evlist *evlist,
 			     struct record_opts *opts);
-size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr);
+size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr,
+				       struct perf_evlist *evlist);
 int auxtrace_record__info_fill(struct auxtrace_record *itr,
 			       struct perf_session *session,
 			       struct auxtrace_info_event *auxtrace_info,
@@ -515,7 +517,7 @@ static inline void auxtrace__free(struct perf_session *session)
 
 static inline struct auxtrace_record *
 auxtrace_record__init(struct perf_evlist *evlist __maybe_unused,
-		      int *err __maybe_unused)
+		      int *err)
 {
 	*err = 0;
 	return NULL;
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 540a7efa6..0967ce601 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -7,6 +7,7 @@
 
 #include <linux/bpf.h>
 #include <bpf/libbpf.h>
+#include <bpf/bpf.h>
 #include <linux/err.h>
 #include <linux/string.h>
 #include "perf.h"
@@ -16,6 +17,7 @@
 #include "llvm-utils.h"
 #include "probe-event.h"
 #include "probe-finder.h" // for MAX_PROBES
+#include "parse-events.h"
 #include "llvm-utils.h"
 
 #define DEFINE_PRINT_FN(name, level) \
@@ -108,8 +110,8 @@ void bpf__clear(void)
 }
 
 static void
-bpf_prog_priv__clear(struct bpf_program *prog __maybe_unused,
-		     void *_priv)
+clear_prog_priv(struct bpf_program *prog __maybe_unused,
+		void *_priv)
 {
 	struct bpf_prog_priv *priv = _priv;
 
@@ -337,7 +339,7 @@ config_bpf_program(struct bpf_program *prog)
 	}
 	pr_debug("bpf: config '%s' is ok\n", config_str);
 
-	err = bpf_program__set_private(prog, priv, bpf_prog_priv__clear);
+	err = bpf_program__set_private(prog, priv, clear_prog_priv);
 	if (err) {
 		pr_debug("Failed to set priv for program '%s'\n", config_str);
 		goto errout;
@@ -739,6 +741,682 @@ int bpf__foreach_tev(struct bpf_object *obj,
 	return 0;
 }
 
+enum bpf_map_op_type {
+	BPF_MAP_OP_SET_VALUE,
+	BPF_MAP_OP_SET_EVSEL,
+};
+
+enum bpf_map_key_type {
+	BPF_MAP_KEY_ALL,
+	BPF_MAP_KEY_RANGES,
+};
+
+struct bpf_map_op {
+	struct list_head list;
+	enum bpf_map_op_type op_type;
+	enum bpf_map_key_type key_type;
+	union {
+		struct parse_events_array array;
+	} k;
+	union {
+		u64 value;
+		struct perf_evsel *evsel;
+	} v;
+};
+
+struct bpf_map_priv {
+	struct list_head ops_list;
+};
+
+static void
+bpf_map_op__delete(struct bpf_map_op *op)
+{
+	if (!list_empty(&op->list))
+		list_del(&op->list);
+	if (op->key_type == BPF_MAP_KEY_RANGES)
+		parse_events__clear_array(&op->k.array);
+	free(op);
+}
+
+static void
+bpf_map_priv__purge(struct bpf_map_priv *priv)
+{
+	struct bpf_map_op *pos, *n;
+
+	list_for_each_entry_safe(pos, n, &priv->ops_list, list) {
+		list_del_init(&pos->list);
+		bpf_map_op__delete(pos);
+	}
+}
+
+static void
+bpf_map_priv__clear(struct bpf_map *map __maybe_unused,
+		    void *_priv)
+{
+	struct bpf_map_priv *priv = _priv;
+
+	bpf_map_priv__purge(priv);
+	free(priv);
+}
+
+static int
+bpf_map_op_setkey(struct bpf_map_op *op, struct parse_events_term *term)
+{
+	op->key_type = BPF_MAP_KEY_ALL;
+	if (!term)
+		return 0;
+
+	if (term->array.nr_ranges) {
+		size_t memsz = term->array.nr_ranges *
+				sizeof(op->k.array.ranges[0]);
+
+		op->k.array.ranges = memdup(term->array.ranges, memsz);
+		if (!op->k.array.ranges) {
+			pr_debug("No enough memory to alloc indices for map\n");
+			return -ENOMEM;
+		}
+		op->key_type = BPF_MAP_KEY_RANGES;
+		op->k.array.nr_ranges = term->array.nr_ranges;
+	}
+	return 0;
+}
+
+static struct bpf_map_op *
+bpf_map_op__new(struct parse_events_term *term)
+{
+	struct bpf_map_op *op;
+	int err;
+
+	op = zalloc(sizeof(*op));
+	if (!op) {
+		pr_debug("Failed to alloc bpf_map_op\n");
+		return ERR_PTR(-ENOMEM);
+	}
+	INIT_LIST_HEAD(&op->list);
+
+	err = bpf_map_op_setkey(op, term);
+	if (err) {
+		free(op);
+		return ERR_PTR(err);
+	}
+	return op;
+}
+
+static int
+bpf_map__add_op(struct bpf_map *map, struct bpf_map_op *op)
+{
+	struct bpf_map_priv *priv;
+	const char *map_name;
+	int err;
+
+	map_name = bpf_map__get_name(map);
+	err = bpf_map__get_private(map, (void **)&priv);
+	if (err) {
+		pr_debug("Failed to get private from map %s\n", map_name);
+		return err;
+	}
+
+	if (!priv) {
+		priv = zalloc(sizeof(*priv));
+		if (!priv) {
+			pr_debug("No enough memory to alloc map private\n");
+			return -ENOMEM;
+		}
+		INIT_LIST_HEAD(&priv->ops_list);
+
+		if (bpf_map__set_private(map, priv, bpf_map_priv__clear)) {
+			free(priv);
+			return -BPF_LOADER_ERRNO__INTERNAL;
+		}
+	}
+
+	list_add_tail(&op->list, &priv->ops_list);
+	return 0;
+}
+
+static struct bpf_map_op *
+bpf_map__add_newop(struct bpf_map *map, struct parse_events_term *term)
+{
+	struct bpf_map_op *op;
+	int err;
+
+	op = bpf_map_op__new(term);
+	if (IS_ERR(op))
+		return op;
+
+	err = bpf_map__add_op(map, op);
+	if (err) {
+		bpf_map_op__delete(op);
+		return ERR_PTR(err);
+	}
+	return op;
+}
+
+static int
+__bpf_map__config_value(struct bpf_map *map,
+			struct parse_events_term *term)
+{
+	struct bpf_map_def def;
+	struct bpf_map_op *op;
+	const char *map_name;
+	int err;
+
+	map_name = bpf_map__get_name(map);
+
+	err = bpf_map__get_def(map, &def);
+	if (err) {
+		pr_debug("Unable to get map definition from '%s'\n",
+			 map_name);
+		return -BPF_LOADER_ERRNO__INTERNAL;
+	}
+
+	if (def.type != BPF_MAP_TYPE_ARRAY) {
+		pr_debug("Map %s type is not BPF_MAP_TYPE_ARRAY\n",
+			 map_name);
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE;
+	}
+	if (def.key_size < sizeof(unsigned int)) {
+		pr_debug("Map %s has incorrect key size\n", map_name);
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_KEYSIZE;
+	}
+	switch (def.value_size) {
+	case 1:
+	case 2:
+	case 4:
+	case 8:
+		break;
+	default:
+		pr_debug("Map %s has incorrect value size\n", map_name);
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUESIZE;
+	}
+
+	op = bpf_map__add_newop(map, term);
+	if (IS_ERR(op))
+		return PTR_ERR(op);
+	op->op_type = BPF_MAP_OP_SET_VALUE;
+	op->v.value = term->val.num;
+	return 0;
+}
+
+static int
+bpf_map__config_value(struct bpf_map *map,
+		      struct parse_events_term *term,
+		      struct perf_evlist *evlist __maybe_unused)
+{
+	if (!term->err_val) {
+		pr_debug("Config value not set\n");
+		return -BPF_LOADER_ERRNO__OBJCONF_CONF;
+	}
+
+	if (term->type_val != PARSE_EVENTS__TERM_TYPE_NUM) {
+		pr_debug("ERROR: wrong value type for 'value'\n");
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE;
+	}
+
+	return __bpf_map__config_value(map, term);
+}
+
+static int
+__bpf_map__config_event(struct bpf_map *map,
+			struct parse_events_term *term,
+			struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+	struct bpf_map_def def;
+	struct bpf_map_op *op;
+	const char *map_name;
+	int err;
+
+	map_name = bpf_map__get_name(map);
+	evsel = perf_evlist__find_evsel_by_str(evlist, term->val.str);
+	if (!evsel) {
+		pr_debug("Event (for '%s') '%s' doesn't exist\n",
+			 map_name, term->val.str);
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_NOEVT;
+	}
+
+	err = bpf_map__get_def(map, &def);
+	if (err) {
+		pr_debug("Unable to get map definition from '%s'\n",
+			 map_name);
+		return err;
+	}
+
+	/*
+	 * No need to check key_size and value_size:
+	 * kernel has already checked them.
+	 */
+	if (def.type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) {
+		pr_debug("Map %s type is not BPF_MAP_TYPE_PERF_EVENT_ARRAY\n",
+			 map_name);
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE;
+	}
+
+	op = bpf_map__add_newop(map, term);
+	if (IS_ERR(op))
+		return PTR_ERR(op);
+	op->op_type = BPF_MAP_OP_SET_EVSEL;
+	op->v.evsel = evsel;
+	return 0;
+}
+
+static int
+bpf_map__config_event(struct bpf_map *map,
+		      struct parse_events_term *term,
+		      struct perf_evlist *evlist)
+{
+	if (!term->err_val) {
+		pr_debug("Config value not set\n");
+		return -BPF_LOADER_ERRNO__OBJCONF_CONF;
+	}
+
+	if (term->type_val != PARSE_EVENTS__TERM_TYPE_STR) {
+		pr_debug("ERROR: wrong value type for 'event'\n");
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE;
+	}
+
+	return __bpf_map__config_event(map, term, evlist);
+}
+
+struct bpf_obj_config__map_func {
+	const char *config_opt;
+	int (*config_func)(struct bpf_map *, struct parse_events_term *,
+			   struct perf_evlist *);
+};
+
+struct bpf_obj_config__map_func bpf_obj_config__map_funcs[] = {
+	{"value", bpf_map__config_value},
+	{"event", bpf_map__config_event},
+};
+
+static int
+config_map_indices_range_check(struct parse_events_term *term,
+			       struct bpf_map *map,
+			       const char *map_name)
+{
+	struct parse_events_array *array = &term->array;
+	struct bpf_map_def def;
+	unsigned int i;
+	int err;
+
+	if (!array->nr_ranges)
+		return 0;
+	if (!array->ranges) {
+		pr_debug("ERROR: map %s: array->nr_ranges is %d but range array is NULL\n",
+			 map_name, (int)array->nr_ranges);
+		return -BPF_LOADER_ERRNO__INTERNAL;
+	}
+
+	err = bpf_map__get_def(map, &def);
+	if (err) {
+		pr_debug("ERROR: Unable to get map definition from '%s'\n",
+			 map_name);
+		return -BPF_LOADER_ERRNO__INTERNAL;
+	}
+
+	for (i = 0; i < array->nr_ranges; i++) {
+		unsigned int start = array->ranges[i].start;
+		size_t length = array->ranges[i].length;
+		unsigned int idx = start + length - 1;
+
+		if (idx >= def.max_entries) {
+			pr_debug("ERROR: index %d too large\n", idx);
+			return -BPF_LOADER_ERRNO__OBJCONF_MAP_IDX2BIG;
+		}
+	}
+	return 0;
+}
+
+static int
+bpf__obj_config_map(struct bpf_object *obj,
+		    struct parse_events_term *term,
+		    struct perf_evlist *evlist,
+		    int *key_scan_pos)
+{
+	/* key is "map:<mapname>.<config opt>" */
+	char *map_name = strdup(term->config + sizeof("map:") - 1);
+	struct bpf_map *map;
+	int err = -BPF_LOADER_ERRNO__OBJCONF_OPT;
+	char *map_opt;
+	size_t i;
+
+	if (!map_name)
+		return -ENOMEM;
+
+	map_opt = strchr(map_name, '.');
+	if (!map_opt) {
+		pr_debug("ERROR: Invalid map config: %s\n", map_name);
+		goto out;
+	}
+
+	*map_opt++ = '\0';
+	if (*map_opt == '\0') {
+		pr_debug("ERROR: Invalid map option: %s\n", term->config);
+		goto out;
+	}
+
+	map = bpf_object__get_map_by_name(obj, map_name);
+	if (!map) {
+		pr_debug("ERROR: Map %s doesn't exist\n", map_name);
+		err = -BPF_LOADER_ERRNO__OBJCONF_MAP_NOTEXIST;
+		goto out;
+	}
+
+	*key_scan_pos += strlen(map_opt);
+	err = config_map_indices_range_check(term, map, map_name);
+	if (err)
+		goto out;
+	*key_scan_pos -= strlen(map_opt);
+
+	for (i = 0; i < ARRAY_SIZE(bpf_obj_config__map_funcs); i++) {
+		struct bpf_obj_config__map_func *func =
+				&bpf_obj_config__map_funcs[i];
+
+		if (strcmp(map_opt, func->config_opt) == 0) {
+			err = func->config_func(map, term, evlist);
+			goto out;
+		}
+	}
+
+	pr_debug("ERROR: Invalid map config option '%s'\n", map_opt);
+	err = -BPF_LOADER_ERRNO__OBJCONF_MAP_OPT;
+out:
+	free(map_name);
+	if (!err)
+		key_scan_pos += strlen(map_opt);
+	return err;
+}
+
+int bpf__config_obj(struct bpf_object *obj,
+		    struct parse_events_term *term,
+		    struct perf_evlist *evlist,
+		    int *error_pos)
+{
+	int key_scan_pos = 0;
+	int err;
+
+	if (!obj || !term || !term->config)
+		return -EINVAL;
+
+	if (!prefixcmp(term->config, "map:")) {
+		key_scan_pos = sizeof("map:") - 1;
+		err = bpf__obj_config_map(obj, term, evlist, &key_scan_pos);
+		goto out;
+	}
+	err = -BPF_LOADER_ERRNO__OBJCONF_OPT;
+out:
+	if (error_pos)
+		*error_pos = key_scan_pos;
+	return err;
+
+}
+
+typedef int (*map_config_func_t)(const char *name, int map_fd,
+				 struct bpf_map_def *pdef,
+				 struct bpf_map_op *op,
+				 void *pkey, void *arg);
+
+static int
+foreach_key_array_all(map_config_func_t func,
+		      void *arg, const char *name,
+		      int map_fd, struct bpf_map_def *pdef,
+		      struct bpf_map_op *op)
+{
+	unsigned int i;
+	int err;
+
+	for (i = 0; i < pdef->max_entries; i++) {
+		err = func(name, map_fd, pdef, op, &i, arg);
+		if (err) {
+			pr_debug("ERROR: failed to insert value to %s[%u]\n",
+				 name, i);
+			return err;
+		}
+	}
+	return 0;
+}
+
+static int
+foreach_key_array_ranges(map_config_func_t func, void *arg,
+			 const char *name, int map_fd,
+			 struct bpf_map_def *pdef,
+			 struct bpf_map_op *op)
+{
+	unsigned int i, j;
+	int err;
+
+	for (i = 0; i < op->k.array.nr_ranges; i++) {
+		unsigned int start = op->k.array.ranges[i].start;
+		size_t length = op->k.array.ranges[i].length;
+
+		for (j = 0; j < length; j++) {
+			unsigned int idx = start + j;
+
+			err = func(name, map_fd, pdef, op, &idx, arg);
+			if (err) {
+				pr_debug("ERROR: failed to insert value to %s[%u]\n",
+					 name, idx);
+				return err;
+			}
+		}
+	}
+	return 0;
+}
+
+static int
+bpf_map_config_foreach_key(struct bpf_map *map,
+			   map_config_func_t func,
+			   void *arg)
+{
+	int err, map_fd;
+	const char *name;
+	struct bpf_map_op *op;
+	struct bpf_map_def def;
+	struct bpf_map_priv *priv;
+
+	name = bpf_map__get_name(map);
+
+	err = bpf_map__get_private(map, (void **)&priv);
+	if (err) {
+		pr_debug("ERROR: failed to get private from map %s\n", name);
+		return -BPF_LOADER_ERRNO__INTERNAL;
+	}
+	if (!priv || list_empty(&priv->ops_list)) {
+		pr_debug("INFO: nothing to config for map %s\n", name);
+		return 0;
+	}
+
+	err = bpf_map__get_def(map, &def);
+	if (err) {
+		pr_debug("ERROR: failed to get definition from map %s\n", name);
+		return -BPF_LOADER_ERRNO__INTERNAL;
+	}
+	map_fd = bpf_map__get_fd(map);
+	if (map_fd < 0) {
+		pr_debug("ERROR: failed to get fd from map %s\n", name);
+		return map_fd;
+	}
+
+	list_for_each_entry(op, &priv->ops_list, list) {
+		switch (def.type) {
+		case BPF_MAP_TYPE_ARRAY:
+		case BPF_MAP_TYPE_PERF_EVENT_ARRAY:
+			switch (op->key_type) {
+			case BPF_MAP_KEY_ALL:
+				err = foreach_key_array_all(func, arg, name,
+							    map_fd, &def, op);
+				break;
+			case BPF_MAP_KEY_RANGES:
+				err = foreach_key_array_ranges(func, arg, name,
+							       map_fd, &def,
+							       op);
+				break;
+			default:
+				pr_debug("ERROR: keytype for map '%s' invalid\n",
+					 name);
+				return -BPF_LOADER_ERRNO__INTERNAL;
+			}
+			if (err)
+				return err;
+			break;
+		default:
+			pr_debug("ERROR: type of '%s' incorrect\n", name);
+			return -BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE;
+		}
+	}
+
+	return 0;
+}
+
+static int
+apply_config_value_for_key(int map_fd, void *pkey,
+			   size_t val_size, u64 val)
+{
+	int err = 0;
+
+	switch (val_size) {
+	case 1: {
+		u8 _val = (u8)(val);
+		err = bpf_map_update_elem(map_fd, pkey, &_val, BPF_ANY);
+		break;
+	}
+	case 2: {
+		u16 _val = (u16)(val);
+		err = bpf_map_update_elem(map_fd, pkey, &_val, BPF_ANY);
+		break;
+	}
+	case 4: {
+		u32 _val = (u32)(val);
+		err = bpf_map_update_elem(map_fd, pkey, &_val, BPF_ANY);
+		break;
+	}
+	case 8: {
+		err = bpf_map_update_elem(map_fd, pkey, &val, BPF_ANY);
+		break;
+	}
+	default:
+		pr_debug("ERROR: invalid value size\n");
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUESIZE;
+	}
+	if (err && errno)
+		err = -errno;
+	return err;
+}
+
+static int
+apply_config_evsel_for_key(const char *name, int map_fd, void *pkey,
+			   struct perf_evsel *evsel)
+{
+	struct xyarray *xy = evsel->fd;
+	struct perf_event_attr *attr;
+	unsigned int key, events;
+	bool check_pass = false;
+	int *evt_fd;
+	int err;
+
+	if (!xy) {
+		pr_debug("ERROR: evsel not ready for map %s\n", name);
+		return -BPF_LOADER_ERRNO__INTERNAL;
+	}
+
+	if (xy->row_size / xy->entry_size != 1) {
+		pr_debug("ERROR: Dimension of target event is incorrect for map %s\n",
+			 name);
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_EVTDIM;
+	}
+
+	attr = &evsel->attr;
+	if (attr->inherit) {
+		pr_debug("ERROR: Can't put inherit event into map %s\n", name);
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_EVTINH;
+	}
+
+	if (perf_evsel__is_bpf_output(evsel))
+		check_pass = true;
+	if (attr->type == PERF_TYPE_RAW)
+		check_pass = true;
+	if (attr->type == PERF_TYPE_HARDWARE)
+		check_pass = true;
+	if (!check_pass) {
+		pr_debug("ERROR: Event type is wrong for map %s\n", name);
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_EVTTYPE;
+	}
+
+	events = xy->entries / (xy->row_size / xy->entry_size);
+	key = *((unsigned int *)pkey);
+	if (key >= events) {
+		pr_debug("ERROR: there is no event %d for map %s\n",
+			 key, name);
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_MAPSIZE;
+	}
+	evt_fd = xyarray__entry(xy, key, 0);
+	err = bpf_map_update_elem(map_fd, pkey, evt_fd, BPF_ANY);
+	if (err && errno)
+		err = -errno;
+	return err;
+}
+
+static int
+apply_obj_config_map_for_key(const char *name, int map_fd,
+			     struct bpf_map_def *pdef __maybe_unused,
+			     struct bpf_map_op *op,
+			     void *pkey, void *arg __maybe_unused)
+{
+	int err;
+
+	switch (op->op_type) {
+	case BPF_MAP_OP_SET_VALUE:
+		err = apply_config_value_for_key(map_fd, pkey,
+						 pdef->value_size,
+						 op->v.value);
+		break;
+	case BPF_MAP_OP_SET_EVSEL:
+		err = apply_config_evsel_for_key(name, map_fd, pkey,
+						 op->v.evsel);
+		break;
+	default:
+		pr_debug("ERROR: unknown value type for '%s'\n", name);
+		err = -BPF_LOADER_ERRNO__INTERNAL;
+	}
+	return err;
+}
+
+static int
+apply_obj_config_map(struct bpf_map *map)
+{
+	return bpf_map_config_foreach_key(map,
+					  apply_obj_config_map_for_key,
+					  NULL);
+}
+
+static int
+apply_obj_config_object(struct bpf_object *obj)
+{
+	struct bpf_map *map;
+	int err;
+
+	bpf_map__for_each(map, obj) {
+		err = apply_obj_config_map(map);
+		if (err)
+			return err;
+	}
+	return 0;
+}
+
+int bpf__apply_obj_config(void)
+{
+	struct bpf_object *obj, *tmp;
+	int err;
+
+	bpf_object__for_each_safe(obj, tmp) {
+		err = apply_obj_config_object(obj);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
 #define ERRNO_OFFSET(e)		((e) - __BPF_LOADER_ERRNO__START)
 #define ERRCODE_OFFSET(c)	ERRNO_OFFSET(BPF_LOADER_ERRNO__##c)
 #define NR_ERRNO	(__BPF_LOADER_ERRNO__END - __BPF_LOADER_ERRNO__START)
@@ -753,6 +1431,20 @@ static const char *bpf_loader_strerror_table[NR_ERRNO] = {
 	[ERRCODE_OFFSET(PROLOGUE)]	= "Failed to generate prologue",
 	[ERRCODE_OFFSET(PROLOGUE2BIG)]	= "Prologue too big for program",
 	[ERRCODE_OFFSET(PROLOGUEOOB)]	= "Offset out of bound for prologue",
+	[ERRCODE_OFFSET(OBJCONF_OPT)]	= "Invalid object config option",
+	[ERRCODE_OFFSET(OBJCONF_CONF)]	= "Config value not set (missing '=')",
+	[ERRCODE_OFFSET(OBJCONF_MAP_OPT)]	= "Invalid object map config option",
+	[ERRCODE_OFFSET(OBJCONF_MAP_NOTEXIST)]	= "Target map doesn't exist",
+	[ERRCODE_OFFSET(OBJCONF_MAP_VALUE)]	= "Incorrect value type for map",
+	[ERRCODE_OFFSET(OBJCONF_MAP_TYPE)]	= "Incorrect map type",
+	[ERRCODE_OFFSET(OBJCONF_MAP_KEYSIZE)]	= "Incorrect map key size",
+	[ERRCODE_OFFSET(OBJCONF_MAP_VALUESIZE)]	= "Incorrect map value size",
+	[ERRCODE_OFFSET(OBJCONF_MAP_NOEVT)]	= "Event not found for map setting",
+	[ERRCODE_OFFSET(OBJCONF_MAP_MAPSIZE)]	= "Invalid map size for event setting",
+	[ERRCODE_OFFSET(OBJCONF_MAP_EVTDIM)]	= "Event dimension too large",
+	[ERRCODE_OFFSET(OBJCONF_MAP_EVTINH)]	= "Doesn't support inherit event",
+	[ERRCODE_OFFSET(OBJCONF_MAP_EVTTYPE)]	= "Wrong event type for map",
+	[ERRCODE_OFFSET(OBJCONF_MAP_IDX2BIG)]	= "Index too large",
 };
 
 static int
@@ -872,3 +1564,29 @@ int bpf__strerror_load(struct bpf_object *obj,
 	bpf__strerror_end(buf, size);
 	return 0;
 }
+
+int bpf__strerror_config_obj(struct bpf_object *obj __maybe_unused,
+			     struct parse_events_term *term __maybe_unused,
+			     struct perf_evlist *evlist __maybe_unused,
+			     int *error_pos __maybe_unused, int err,
+			     char *buf, size_t size)
+{
+	bpf__strerror_head(err, buf, size);
+	bpf__strerror_entry(BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE,
+			    "Can't use this config term with this map type");
+	bpf__strerror_end(buf, size);
+	return 0;
+}
+
+int bpf__strerror_apply_obj_config(int err, char *buf, size_t size)
+{
+	bpf__strerror_head(err, buf, size);
+	bpf__strerror_entry(BPF_LOADER_ERRNO__OBJCONF_MAP_EVTDIM,
+			    "Cannot set event to BPF map in multi-thread tracing");
+	bpf__strerror_entry(BPF_LOADER_ERRNO__OBJCONF_MAP_EVTINH,
+			    "%s (Hint: use -i to turn off inherit)", emsg);
+	bpf__strerror_entry(BPF_LOADER_ERRNO__OBJCONF_MAP_EVTTYPE,
+			    "Can only put raw, hardware and BPF output event into a BPF map");
+	bpf__strerror_end(buf, size);
+	return 0;
+}
diff --git a/tools/perf/util/bpf-loader.h b/tools/perf/util/bpf-loader.h
index 6fdc0457e..be4311944 100644
--- a/tools/perf/util/bpf-loader.h
+++ b/tools/perf/util/bpf-loader.h
@@ -10,6 +10,7 @@
 #include <string.h>
 #include <bpf/libbpf.h>
 #include "probe-event.h"
+#include "evlist.h"
 #include "debug.h"
 
 enum bpf_loader_errno {
@@ -24,10 +25,25 @@ enum bpf_loader_errno {
 	BPF_LOADER_ERRNO__PROLOGUE,	/* Failed to generate prologue */
 	BPF_LOADER_ERRNO__PROLOGUE2BIG,	/* Prologue too big for program */
 	BPF_LOADER_ERRNO__PROLOGUEOOB,	/* Offset out of bound for prologue */
+	BPF_LOADER_ERRNO__OBJCONF_OPT,	/* Invalid object config option */
+	BPF_LOADER_ERRNO__OBJCONF_CONF,	/* Config value not set (lost '=')) */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_OPT,	/* Invalid object map config option */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_NOTEXIST,	/* Target map not exist */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE,	/* Incorrect value type for map */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE,	/* Incorrect map type */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_KEYSIZE,	/* Incorrect map key size */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_VALUESIZE,/* Incorrect map value size */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_NOEVT,	/* Event not found for map setting */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_MAPSIZE,	/* Invalid map size for event setting */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_EVTDIM,	/* Event dimension too large */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_EVTINH,	/* Doesn't support inherit event */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_EVTTYPE,	/* Wrong event type for map */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_IDX2BIG,	/* Index too large */
 	__BPF_LOADER_ERRNO__END,
 };
 
 struct bpf_object;
+struct parse_events_term;
 #define PERF_BPF_PROBE_GROUP "perf_bpf_probe"
 
 typedef int (*bpf_prog_iter_callback_t)(struct probe_trace_event *tev,
@@ -53,6 +69,16 @@ int bpf__strerror_load(struct bpf_object *obj, int err,
 		       char *buf, size_t size);
 int bpf__foreach_tev(struct bpf_object *obj,
 		     bpf_prog_iter_callback_t func, void *arg);
+
+int bpf__config_obj(struct bpf_object *obj, struct parse_events_term *term,
+		    struct perf_evlist *evlist, int *error_pos);
+int bpf__strerror_config_obj(struct bpf_object *obj,
+			     struct parse_events_term *term,
+			     struct perf_evlist *evlist,
+			     int *error_pos, int err, char *buf,
+			     size_t size);
+int bpf__apply_obj_config(void);
+int bpf__strerror_apply_obj_config(int err, char *buf, size_t size);
 #else
 static inline struct bpf_object *
 bpf__prepare_load(const char *filename __maybe_unused,
@@ -84,6 +110,21 @@ bpf__foreach_tev(struct bpf_object *obj __maybe_unused,
 }
 
 static inline int
+bpf__config_obj(struct bpf_object *obj __maybe_unused,
+		struct parse_events_term *term __maybe_unused,
+		struct perf_evlist *evlist __maybe_unused,
+		int *error_pos __maybe_unused)
+{
+	return 0;
+}
+
+static inline int
+bpf__apply_obj_config(void)
+{
+	return 0;
+}
+
+static inline int
 __bpf_strerror(char *buf, size_t size)
 {
 	if (!size)
@@ -118,5 +159,23 @@ static inline int bpf__strerror_load(struct bpf_object *obj __maybe_unused,
 {
 	return __bpf_strerror(buf, size);
 }
+
+static inline int
+bpf__strerror_config_obj(struct bpf_object *obj __maybe_unused,
+			 struct parse_events_term *term __maybe_unused,
+			 struct perf_evlist *evlist __maybe_unused,
+			 int *error_pos __maybe_unused,
+			 int err __maybe_unused,
+			 char *buf, size_t size)
+{
+	return __bpf_strerror(buf, size);
+}
+
+static inline int
+bpf__strerror_apply_obj_config(int err __maybe_unused,
+			       char *buf, size_t size)
+{
+	return __bpf_strerror(buf, size);
+}
 #endif
 #endif
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 6a7e273a5..0573c2ec8 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -28,7 +28,6 @@ int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused,
 			   struct machine *machine)
 {
 	struct addr_location al;
-	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 	struct thread *thread = machine__findnew_thread(machine, sample->pid,
 							sample->tid);
 
@@ -38,7 +37,7 @@ int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused,
 		return -1;
 	}
 
-	thread__find_addr_map(thread, cpumode, MAP__FUNCTION, sample->ip, &al);
+	thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, sample->ip, &al);
 
 	if (al.map != NULL)
 		al.map->dso->hit = 1;
@@ -166,6 +165,50 @@ char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size)
 	return build_id__filename(build_id_hex, bf, size);
 }
 
+bool dso__build_id_is_kmod(const struct dso *dso, char *bf, size_t size)
+{
+	char *id_name, *ch;
+	struct stat sb;
+
+	id_name = dso__build_id_filename(dso, bf, size);
+	if (!id_name)
+		goto err;
+	if (access(id_name, F_OK))
+		goto err;
+	if (lstat(id_name, &sb) == -1)
+		goto err;
+	if ((size_t)sb.st_size > size - 1)
+		goto err;
+	if (readlink(id_name, bf, size - 1) < 0)
+		goto err;
+
+	bf[sb.st_size] = '\0';
+
+	/*
+	 * link should be:
+	 * ../../lib/modules/4.4.0-rc4/kernel/net/ipv4/netfilter/nf_nat_ipv4.ko/a09fe3eb3147dafa4e3b31dbd6257e4d696bdc92
+	 */
+	ch = strrchr(bf, '/');
+	if (!ch)
+		goto err;
+	if (ch - 3 < bf)
+		goto err;
+
+	return strncmp(".ko", ch - 3, 3) == 0;
+err:
+	/*
+	 * If dso__build_id_filename work, get id_name again,
+	 * because id_name points to bf and is broken.
+	 */
+	if (id_name)
+		id_name = dso__build_id_filename(dso, bf, size);
+	pr_err("Invalid build id: %s\n", id_name ? :
+					 dso->long_name ? :
+					 dso->short_name ? :
+					 "[unknown]");
+	return false;
+}
+
 #define dsos__for_each_with_build_id(pos, head)	\
 	list_for_each_entry(pos, head, node)	\
 		if (!pos->has_build_id)		\
@@ -211,6 +254,7 @@ static int machine__write_buildid_table(struct machine *machine, int fd)
 	dsos__for_each_with_build_id(pos, &machine->dsos.head) {
 		const char *name;
 		size_t name_len;
+		bool in_kernel = false;
 
 		if (!pos->hit)
 			continue;
@@ -227,8 +271,11 @@ static int machine__write_buildid_table(struct machine *machine, int fd)
 			name_len = pos->long_name_len + 1;
 		}
 
+		in_kernel = pos->kernel ||
+				is_kernel_module(name,
+					PERF_RECORD_MISC_CPUMODE_UNKNOWN);
 		err = write_buildid(name, name_len, pos->build_id, machine->pid,
-				    pos->kernel ? kmisc : umisc, fd);
+				    in_kernel ? kmisc : umisc, fd);
 		if (err)
 			break;
 	}
diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h
index 27a14a8a9..64af3e206 100644
--- a/tools/perf/util/build-id.h
+++ b/tools/perf/util/build-id.h
@@ -16,6 +16,7 @@ int sysfs__sprintf_build_id(const char *root_dir, char *sbuild_id);
 int filename__sprintf_build_id(const char *pathname, char *sbuild_id);
 
 char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size);
+bool dso__build_id_is_kmod(const struct dso *dso, char *bf, size_t size);
 
 int build_id__mark_dso_hit(struct perf_tool *tool, union perf_event *event,
 			   struct perf_sample *sample, struct perf_evsel *evsel,
diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h
index 07b5d6394..1f5a93c2c 100644
--- a/tools/perf/util/cache.h
+++ b/tools/perf/util/cache.h
@@ -23,14 +23,17 @@
 #define PERF_TRACEFS_ENVIRONMENT "PERF_TRACEFS_DIR"
 #define PERF_PAGER_ENVIRONMENT "PERF_PAGER"
 
+extern const char *config_exclusive_filename;
+
 typedef int (*config_fn_t)(const char *, const char *, void *);
-extern int perf_default_config(const char *, const char *, void *);
-extern int perf_config(config_fn_t fn, void *);
-extern int perf_config_int(const char *, const char *);
-extern u64 perf_config_u64(const char *, const char *);
-extern int perf_config_bool(const char *, const char *);
-extern int config_error_nonbool(const char *);
-extern const char *perf_config_dirname(const char *, const char *);
+int perf_default_config(const char *, const char *, void *);
+int perf_config(config_fn_t fn, void *);
+int perf_config_int(const char *, const char *);
+u64 perf_config_u64(const char *, const char *);
+int perf_config_bool(const char *, const char *);
+int config_error_nonbool(const char *);
+const char *perf_config_dirname(const char *, const char *);
+const char *perf_etc_perfconfig(void);
 
 char *alias_lookup(const char *alias);
 int split_cmdline(char *cmdline, const char ***argv);
@@ -61,13 +64,9 @@ static inline int is_absolute_path(const char *path)
 	return path[0] == '/';
 }
 
-const char *make_nonrelative_path(const char *path);
 char *strip_path_suffix(const char *path, const char *suffix);
 
-extern char *mkpath(const char *fmt, ...) __attribute__((format (printf, 1, 2)));
-extern char *perf_path(const char *fmt, ...) __attribute__((format (printf, 1, 2)));
-
-extern char *perf_pathdup(const char *fmt, ...)
-	__attribute__((format (printf, 1, 2)));
+char *mkpath(const char *fmt, ...) __attribute__((format (printf, 1, 2)));
+char *perf_path(const char *fmt, ...) __attribute__((format (printf, 1, 2)));
 
 #endif /* __PERF_CACHE_H */
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 53c43eb94..24b4bd0d7 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -416,7 +416,7 @@ create_child(struct callchain_node *parent, bool inherit_children)
 /*
  * Fill the node with callchain values
  */
-static void
+static int
 fill_node(struct callchain_node *node, struct callchain_cursor *cursor)
 {
 	struct callchain_cursor_node *cursor_node;
@@ -433,7 +433,7 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor)
 		call = zalloc(sizeof(*call));
 		if (!call) {
 			perror("not enough memory for the code path tree");
-			return;
+			return -1;
 		}
 		call->ip = cursor_node->ip;
 		call->ms.sym = cursor_node->sym;
@@ -443,6 +443,7 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor)
 		callchain_cursor_advance(cursor);
 		cursor_node = callchain_cursor_current(cursor);
 	}
+	return 0;
 }
 
 static struct callchain_node *
@@ -453,7 +454,19 @@ add_child(struct callchain_node *parent,
 	struct callchain_node *new;
 
 	new = create_child(parent, false);
-	fill_node(new, cursor);
+	if (new == NULL)
+		return NULL;
+
+	if (fill_node(new, cursor) < 0) {
+		struct callchain_list *call, *tmp;
+
+		list_for_each_entry_safe(call, tmp, &new->val, list) {
+			list_del(&call->list);
+			free(call);
+		}
+		free(new);
+		return NULL;
+	}
 
 	new->children_hit = 0;
 	new->hit = period;
@@ -462,16 +475,32 @@ add_child(struct callchain_node *parent,
 	return new;
 }
 
-static s64 match_chain(struct callchain_cursor_node *node,
-		      struct callchain_list *cnode)
+enum match_result {
+	MATCH_ERROR  = -1,
+	MATCH_EQ,
+	MATCH_LT,
+	MATCH_GT,
+};
+
+static enum match_result match_chain(struct callchain_cursor_node *node,
+				     struct callchain_list *cnode)
 {
 	struct symbol *sym = node->sym;
+	u64 left, right;
 
 	if (cnode->ms.sym && sym &&
-	    callchain_param.key == CCKEY_FUNCTION)
-		return cnode->ms.sym->start - sym->start;
-	else
-		return cnode->ip - node->ip;
+	    callchain_param.key == CCKEY_FUNCTION) {
+		left = cnode->ms.sym->start;
+		right = sym->start;
+	} else {
+		left = cnode->ip;
+		right = node->ip;
+	}
+
+	if (left == right)
+		return MATCH_EQ;
+
+	return left > right ? MATCH_GT : MATCH_LT;
 }
 
 /*
@@ -479,7 +508,7 @@ static s64 match_chain(struct callchain_cursor_node *node,
  * give a part of its callchain to the created child.
  * Then create another child to host the given callchain of new branch
  */
-static void
+static int
 split_add_child(struct callchain_node *parent,
 		struct callchain_cursor *cursor,
 		struct callchain_list *to_split,
@@ -491,6 +520,8 @@ split_add_child(struct callchain_node *parent,
 
 	/* split */
 	new = create_child(parent, true);
+	if (new == NULL)
+		return -1;
 
 	/* split the callchain and move a part to the new child */
 	old_tail = parent->val.prev;
@@ -524,6 +555,8 @@ split_add_child(struct callchain_node *parent,
 
 		node = callchain_cursor_current(cursor);
 		new = add_child(parent, cursor, period);
+		if (new == NULL)
+			return -1;
 
 		/*
 		 * This is second child since we moved parent's children
@@ -534,7 +567,7 @@ split_add_child(struct callchain_node *parent,
 		cnode = list_first_entry(&first->val, struct callchain_list,
 					 list);
 
-		if (match_chain(node, cnode) < 0)
+		if (match_chain(node, cnode) == MATCH_LT)
 			pp = &p->rb_left;
 		else
 			pp = &p->rb_right;
@@ -545,14 +578,15 @@ split_add_child(struct callchain_node *parent,
 		parent->hit = period;
 		parent->count = 1;
 	}
+	return 0;
 }
 
-static int
+static enum match_result
 append_chain(struct callchain_node *root,
 	     struct callchain_cursor *cursor,
 	     u64 period);
 
-static void
+static int
 append_chain_children(struct callchain_node *root,
 		      struct callchain_cursor *cursor,
 		      u64 period)
@@ -564,36 +598,42 @@ append_chain_children(struct callchain_node *root,
 
 	node = callchain_cursor_current(cursor);
 	if (!node)
-		return;
+		return -1;
 
 	/* lookup in childrens */
 	while (*p) {
-		s64 ret;
+		enum match_result ret;
 
 		parent = *p;
 		rnode = rb_entry(parent, struct callchain_node, rb_node_in);
 
 		/* If at least first entry matches, rely to children */
 		ret = append_chain(rnode, cursor, period);
-		if (ret == 0)
+		if (ret == MATCH_EQ)
 			goto inc_children_hit;
+		if (ret == MATCH_ERROR)
+			return -1;
 
-		if (ret < 0)
+		if (ret == MATCH_LT)
 			p = &parent->rb_left;
 		else
 			p = &parent->rb_right;
 	}
 	/* nothing in children, add to the current node */
 	rnode = add_child(root, cursor, period);
+	if (rnode == NULL)
+		return -1;
+
 	rb_link_node(&rnode->rb_node_in, parent, p);
 	rb_insert_color(&rnode->rb_node_in, &root->rb_root_in);
 
 inc_children_hit:
 	root->children_hit += period;
 	root->children_count++;
+	return 0;
 }
 
-static int
+static enum match_result
 append_chain(struct callchain_node *root,
 	     struct callchain_cursor *cursor,
 	     u64 period)
@@ -602,7 +642,7 @@ append_chain(struct callchain_node *root,
 	u64 start = cursor->pos;
 	bool found = false;
 	u64 matches;
-	int cmp = 0;
+	enum match_result cmp = MATCH_ERROR;
 
 	/*
 	 * Lookup in the current node
@@ -618,7 +658,7 @@ append_chain(struct callchain_node *root,
 			break;
 
 		cmp = match_chain(node, cnode);
-		if (cmp)
+		if (cmp != MATCH_EQ)
 			break;
 
 		found = true;
@@ -628,7 +668,7 @@ append_chain(struct callchain_node *root,
 
 	/* matches not, relay no the parent */
 	if (!found) {
-		WARN_ONCE(!cmp, "Chain comparison error\n");
+		WARN_ONCE(cmp == MATCH_ERROR, "Chain comparison error\n");
 		return cmp;
 	}
 
@@ -636,21 +676,25 @@ append_chain(struct callchain_node *root,
 
 	/* we match only a part of the node. Split it and add the new chain */
 	if (matches < root->val_nr) {
-		split_add_child(root, cursor, cnode, start, matches, period);
-		return 0;
+		if (split_add_child(root, cursor, cnode, start, matches,
+				    period) < 0)
+			return MATCH_ERROR;
+
+		return MATCH_EQ;
 	}
 
 	/* we match 100% of the path, increment the hit */
 	if (matches == root->val_nr && cursor->pos == cursor->nr) {
 		root->hit += period;
 		root->count++;
-		return 0;
+		return MATCH_EQ;
 	}
 
 	/* We match the node and still have a part remaining */
-	append_chain_children(root, cursor, period);
+	if (append_chain_children(root, cursor, period) < 0)
+		return MATCH_ERROR;
 
-	return 0;
+	return MATCH_EQ;
 }
 
 int callchain_append(struct callchain_root *root,
@@ -662,7 +706,8 @@ int callchain_append(struct callchain_root *root,
 
 	callchain_cursor_commit(cursor);
 
-	append_chain_children(&root->node, cursor, period);
+	if (append_chain_children(&root->node, cursor, period) < 0)
+		return -1;
 
 	if (cursor->nr > root->max_depth)
 		root->max_depth = cursor->nr;
@@ -690,7 +735,8 @@ merge_chain_branch(struct callchain_cursor *cursor,
 
 	if (src->hit) {
 		callchain_cursor_commit(cursor);
-		append_chain_children(dst, cursor, src->hit);
+		if (append_chain_children(dst, cursor, src->hit) < 0)
+			return -1;
 	}
 
 	n = rb_first(&src->rb_root_in);
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 18dd22269..d2a9e6948 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -220,7 +220,7 @@ int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node *
 			bool hide_unresolved);
 
 extern const char record_callchain_help[];
-extern int parse_callchain_record(const char *arg, struct callchain_param *param);
+int parse_callchain_record(const char *arg, struct callchain_param *param);
 int parse_callchain_record_opt(const char *arg, struct callchain_param *param);
 int parse_callchain_report_opt(const char *arg);
 int parse_callchain_top_opt(const char *arg);
@@ -236,7 +236,7 @@ static inline void callchain_cursor_snapshot(struct callchain_cursor *dest,
 }
 
 #ifdef HAVE_SKIP_CALLCHAIN_IDX
-extern int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain);
+int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain);
 #else
 static inline int arch_skip_callchain_idx(struct thread *thread __maybe_unused,
 			struct ip_callchain *chain __maybe_unused)
diff --git a/tools/perf/util/cgroup.h b/tools/perf/util/cgroup.h
index b4b8cb42f..31f8dcdbd 100644
--- a/tools/perf/util/cgroup.h
+++ b/tools/perf/util/cgroup.h
@@ -13,7 +13,7 @@ struct cgroup_sel {
 
 
 extern int nr_cgroups; /* number of explicit cgroups defined */
-extern void close_cgroup(struct cgroup_sel *cgrp);
-extern int parse_cgroups(const struct option *opt, const char *str, int unset);
+void close_cgroup(struct cgroup_sel *cgrp);
+int parse_cgroups(const struct option *opt, const char *str, int unset);
 
 #endif /* __CGROUP_H__ */
diff --git a/tools/perf/util/cloexec.h b/tools/perf/util/cloexec.h
index 3bee6773d..d0d465953 100644
--- a/tools/perf/util/cloexec.h
+++ b/tools/perf/util/cloexec.h
@@ -5,7 +5,7 @@ unsigned long perf_event_open_cloexec_flag(void);
 
 #ifdef __GLIBC_PREREQ
 #if !__GLIBC_PREREQ(2, 6) && !defined(__UCLIBC__)
-extern int sched_getcpu(void) __THROW;
+int sched_getcpu(void) __THROW;
 #endif
 #endif
 
diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c
index e5fb88bab..43e84aa27 100644
--- a/tools/perf/util/color.c
+++ b/tools/perf/util/color.c
@@ -32,14 +32,15 @@ int perf_config_colorbool(const char *var, const char *value, int stdout_is_tty)
 	return 0;
 }
 
-int perf_color_default_config(const char *var, const char *value, void *cb)
+int perf_color_default_config(const char *var, const char *value,
+			      void *cb __maybe_unused)
 {
 	if (!strcmp(var, "color.ui")) {
 		perf_use_color_default = perf_config_colorbool(var, value, -1);
 		return 0;
 	}
 
-	return perf_default_config(var, value, cb);
+	return 0;
 }
 
 static int __color_vsnprintf(char *bf, size_t size, const char *color,
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index d3e12e30e..4e7276354 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -26,7 +26,7 @@ static const char *config_file_name;
 static int config_linenr;
 static int config_file_eof;
 
-static const char *config_exclusive_filename;
+const char *config_exclusive_filename;
 
 static int get_next_char(void)
 {
@@ -434,7 +434,7 @@ static int perf_config_from_file(config_fn_t fn, const char *filename, void *dat
 	return ret;
 }
 
-static const char *perf_etc_perfconfig(void)
+const char *perf_etc_perfconfig(void)
 {
 	static const char *system_wide;
 	if (!system_wide)
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index fa935093a..9bcf2bed3 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -8,6 +8,10 @@
 #include <linux/bitmap.h>
 #include "asm/bug.h"
 
+static int max_cpu_num;
+static int max_node_num;
+static int *cpunode_map;
+
 static struct cpu_map *cpu_map__default_new(void)
 {
 	struct cpu_map *cpus;
@@ -486,6 +490,32 @@ out:
 		pr_err("Failed to read max nodes, using default of %d\n", max_node_num);
 }
 
+int cpu__max_node(void)
+{
+	if (unlikely(!max_node_num))
+		set_max_node_num();
+
+	return max_node_num;
+}
+
+int cpu__max_cpu(void)
+{
+	if (unlikely(!max_cpu_num))
+		set_max_cpu_num();
+
+	return max_cpu_num;
+}
+
+int cpu__get_node(int cpu)
+{
+	if (unlikely(cpunode_map == NULL)) {
+		pr_debug("cpu_map not initialized\n");
+		return -1;
+	}
+
+	return cpunode_map[cpu];
+}
+
 static int init_cpunode_map(void)
 {
 	int i;
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index 71c41b9ef..81a2562aa 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -57,37 +57,11 @@ static inline bool cpu_map__empty(const struct cpu_map *map)
 	return map ? map->map[0] == -1 : true;
 }
 
-int max_cpu_num;
-int max_node_num;
-int *cpunode_map;
-
 int cpu__setup_cpunode_map(void);
 
-static inline int cpu__max_node(void)
-{
-	if (unlikely(!max_node_num))
-		pr_debug("cpu_map not initialized\n");
-
-	return max_node_num;
-}
-
-static inline int cpu__max_cpu(void)
-{
-	if (unlikely(!max_cpu_num))
-		pr_debug("cpu_map not initialized\n");
-
-	return max_cpu_num;
-}
-
-static inline int cpu__get_node(int cpu)
-{
-	if (unlikely(cpunode_map == NULL)) {
-		pr_debug("cpu_map not initialized\n");
-		return -1;
-	}
-
-	return cpunode_map[cpu];
-}
+int cpu__max_node(void);
+int cpu__max_cpu(void);
+int cpu__get_node(int cpu);
 
 int cpu_map__build_map(struct cpu_map *cpus, struct cpu_map **res,
 		       int (*f)(struct cpu_map *map, int cpu, void *data),
diff --git a/tools/perf/util/ctype.c b/tools/perf/util/ctype.c
index aada3ac5e..d4a5a21c2 100644
--- a/tools/perf/util/ctype.c
+++ b/tools/perf/util/ctype.c
@@ -32,8 +32,17 @@ unsigned char sane_ctype[256] = {
 
 const char *graph_line =
 	"_____________________________________________________________________"
+	"_____________________________________________________________________"
 	"_____________________________________________________________________";
 const char *graph_dotted_line =
 	"---------------------------------------------------------------------"
 	"---------------------------------------------------------------------"
 	"---------------------------------------------------------------------";
+const char *spaces =
+	"                                                                     "
+	"                                                                     "
+	"                                                                     ";
+const char *dots =
+	"....................................................................."
+	"....................................................................."
+	".....................................................................";
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index 34cd1e403..bbf69d248 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -352,6 +352,84 @@ static int add_tracepoint_values(struct ctf_writer *cw,
 	return ret;
 }
 
+static int
+add_bpf_output_values(struct bt_ctf_event_class *event_class,
+		      struct bt_ctf_event *event,
+		      struct perf_sample *sample)
+{
+	struct bt_ctf_field_type *len_type, *seq_type;
+	struct bt_ctf_field *len_field, *seq_field;
+	unsigned int raw_size = sample->raw_size;
+	unsigned int nr_elements = raw_size / sizeof(u32);
+	unsigned int i;
+	int ret;
+
+	if (nr_elements * sizeof(u32) != raw_size)
+		pr_warning("Incorrect raw_size (%u) in bpf output event, skip %lu bytes\n",
+			   raw_size, nr_elements * sizeof(u32) - raw_size);
+
+	len_type = bt_ctf_event_class_get_field_by_name(event_class, "raw_len");
+	len_field = bt_ctf_field_create(len_type);
+	if (!len_field) {
+		pr_err("failed to create 'raw_len' for bpf output event\n");
+		ret = -1;
+		goto put_len_type;
+	}
+
+	ret = bt_ctf_field_unsigned_integer_set_value(len_field, nr_elements);
+	if (ret) {
+		pr_err("failed to set field value for raw_len\n");
+		goto put_len_field;
+	}
+	ret = bt_ctf_event_set_payload(event, "raw_len", len_field);
+	if (ret) {
+		pr_err("failed to set payload to raw_len\n");
+		goto put_len_field;
+	}
+
+	seq_type = bt_ctf_event_class_get_field_by_name(event_class, "raw_data");
+	seq_field = bt_ctf_field_create(seq_type);
+	if (!seq_field) {
+		pr_err("failed to create 'raw_data' for bpf output event\n");
+		ret = -1;
+		goto put_seq_type;
+	}
+
+	ret = bt_ctf_field_sequence_set_length(seq_field, len_field);
+	if (ret) {
+		pr_err("failed to set length of 'raw_data'\n");
+		goto put_seq_field;
+	}
+
+	for (i = 0; i < nr_elements; i++) {
+		struct bt_ctf_field *elem_field =
+			bt_ctf_field_sequence_get_field(seq_field, i);
+
+		ret = bt_ctf_field_unsigned_integer_set_value(elem_field,
+				((u32 *)(sample->raw_data))[i]);
+
+		bt_ctf_field_put(elem_field);
+		if (ret) {
+			pr_err("failed to set raw_data[%d]\n", i);
+			goto put_seq_field;
+		}
+	}
+
+	ret = bt_ctf_event_set_payload(event, "raw_data", seq_field);
+	if (ret)
+		pr_err("failed to set payload for raw_data\n");
+
+put_seq_field:
+	bt_ctf_field_put(seq_field);
+put_seq_type:
+	bt_ctf_field_type_put(seq_type);
+put_len_field:
+	bt_ctf_field_put(len_field);
+put_len_type:
+	bt_ctf_field_type_put(len_type);
+	return ret;
+}
+
 static int add_generic_values(struct ctf_writer *cw,
 			      struct bt_ctf_event *event,
 			      struct perf_evsel *evsel,
@@ -554,7 +632,7 @@ static bool is_flush_needed(struct ctf_stream *cs)
 }
 
 static int process_sample_event(struct perf_tool *tool,
-				union perf_event *_event __maybe_unused,
+				union perf_event *_event,
 				struct perf_sample *sample,
 				struct perf_evsel *evsel,
 				struct machine *machine __maybe_unused)
@@ -597,6 +675,12 @@ static int process_sample_event(struct perf_tool *tool,
 			return -1;
 	}
 
+	if (perf_evsel__is_bpf_output(evsel)) {
+		ret = add_bpf_output_values(event_class, event, sample);
+		if (ret)
+			return -1;
+	}
+
 	cs = ctf_stream(cw, get_sample_cpu(cw, sample, evsel));
 	if (cs) {
 		if (is_flush_needed(cs))
@@ -744,6 +828,25 @@ static int add_tracepoint_types(struct ctf_writer *cw,
 	return ret;
 }
 
+static int add_bpf_output_types(struct ctf_writer *cw,
+				struct bt_ctf_event_class *class)
+{
+	struct bt_ctf_field_type *len_type = cw->data.u32;
+	struct bt_ctf_field_type *seq_base_type = cw->data.u32_hex;
+	struct bt_ctf_field_type *seq_type;
+	int ret;
+
+	ret = bt_ctf_event_class_add_field(class, len_type, "raw_len");
+	if (ret)
+		return ret;
+
+	seq_type = bt_ctf_field_type_sequence_create(seq_base_type, "raw_len");
+	if (!seq_type)
+		return -1;
+
+	return bt_ctf_event_class_add_field(class, seq_type, "raw_data");
+}
+
 static int add_generic_types(struct ctf_writer *cw, struct perf_evsel *evsel,
 			     struct bt_ctf_event_class *event_class)
 {
@@ -755,7 +858,8 @@ static int add_generic_types(struct ctf_writer *cw, struct perf_evsel *evsel,
 	 *                              ctf event header
 	 *   PERF_SAMPLE_READ         - TODO
 	 *   PERF_SAMPLE_CALLCHAIN    - TODO
-	 *   PERF_SAMPLE_RAW          - tracepoint fields are handled separately
+	 *   PERF_SAMPLE_RAW          - tracepoint fields and BPF output
+	 *                              are handled separately
 	 *   PERF_SAMPLE_BRANCH_STACK - TODO
 	 *   PERF_SAMPLE_REGS_USER    - TODO
 	 *   PERF_SAMPLE_STACK_USER   - TODO
@@ -824,6 +928,12 @@ static int add_event(struct ctf_writer *cw, struct perf_evsel *evsel)
 			goto err;
 	}
 
+	if (perf_evsel__is_bpf_output(evsel)) {
+		ret = add_bpf_output_types(cw, event_class);
+		if (ret)
+			goto err;
+	}
+
 	ret = bt_ctf_stream_class_add_event_class(cw->stream_class, event_class);
 	if (ret) {
 		pr("Failed to add event class into stream.\n");
@@ -858,6 +968,23 @@ static int setup_events(struct ctf_writer *cw, struct perf_session *session)
 	return 0;
 }
 
+static void cleanup_events(struct perf_session *session)
+{
+	struct perf_evlist *evlist = session->evlist;
+	struct perf_evsel *evsel;
+
+	evlist__for_each(evlist, evsel) {
+		struct evsel_priv *priv;
+
+		priv = evsel->priv;
+		bt_ctf_event_class_put(priv->event_class);
+		zfree(&evsel->priv);
+	}
+
+	perf_evlist__delete(evlist);
+	session->evlist = NULL;
+}
+
 static int setup_streams(struct ctf_writer *cw, struct perf_session *session)
 {
 	struct ctf_stream **stream;
@@ -953,6 +1080,12 @@ static struct bt_ctf_field_type *create_int_type(int size, bool sign, bool hex)
 	    bt_ctf_field_type_integer_set_base(type, BT_CTF_INTEGER_BASE_HEXADECIMAL))
 		goto err;
 
+#if __BYTE_ORDER == __BIG_ENDIAN
+	bt_ctf_field_type_set_byte_order(type, BT_CTF_BYTE_ORDER_BIG_ENDIAN);
+#else
+	bt_ctf_field_type_set_byte_order(type, BT_CTF_BYTE_ORDER_LITTLE_ENDIAN);
+#endif
+
 	pr2("Created type: INTEGER %d-bit %ssigned %s\n",
 	    size, sign ? "un" : "", hex ? "hex" : "");
 	return type;
@@ -1100,7 +1233,7 @@ static int convert__config(const char *var, const char *value, void *cb)
 		return 0;
 	}
 
-	return perf_default_config(var, value, cb);
+	return 0;
 }
 
 int bt_convert__perf2ctf(const char *input, const char *path, bool force)
@@ -1171,6 +1304,7 @@ int bt_convert__perf2ctf(const char *input, const char *path, bool force)
 		(double) c.events_size / 1024.0 / 1024.0,
 		c.events_count);
 
+	cleanup_events(session);
 	perf_session__delete(session);
 	ctf_writer__cleanup(cw);
 
diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c
index 1c9689e4c..049438d51 100644
--- a/tools/perf/util/db-export.c
+++ b/tools/perf/util/db-export.c
@@ -333,7 +333,7 @@ int db_export__sample(struct db_export *dbe, union perf_event *event,
 	    sample_addr_correlates_sym(&evsel->attr)) {
 		struct addr_location addr_al;
 
-		perf_event__preprocess_sample_addr(event, sample, thread, &addr_al);
+		thread__resolve(thread, &addr_al, sample);
 		err = db_ids_from_al(dbe, &addr_al, &es.addr_dso_db_id,
 				     &es.addr_sym_db_id, &es.addr_offset);
 		if (err)
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index 86d9c7302..8c4212abd 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -5,6 +5,7 @@
 #include <string.h>
 #include <stdarg.h>
 #include <stdio.h>
+#include <api/debug.h>
 
 #include "cache.h"
 #include "color.h"
@@ -22,7 +23,7 @@ int debug_ordered_events;
 static int redirect_to_stderr;
 int debug_data_convert;
 
-static int _eprintf(int level, int var, const char *fmt, va_list args)
+int veprintf(int level, int var, const char *fmt, va_list args)
 {
 	int ret = 0;
 
@@ -36,24 +37,19 @@ static int _eprintf(int level, int var, const char *fmt, va_list args)
 	return ret;
 }
 
-int veprintf(int level, int var, const char *fmt, va_list args)
-{
-	return _eprintf(level, var, fmt, args);
-}
-
 int eprintf(int level, int var, const char *fmt, ...)
 {
 	va_list args;
 	int ret;
 
 	va_start(args, fmt);
-	ret = _eprintf(level, var, fmt, args);
+	ret = veprintf(level, var, fmt, args);
 	va_end(args);
 
 	return ret;
 }
 
-static int __eprintf_time(u64 t, const char *fmt, va_list args)
+static int veprintf_time(u64 t, const char *fmt, va_list args)
 {
 	int ret = 0;
 	u64 secs, usecs, nsecs = t;
@@ -75,7 +71,7 @@ int eprintf_time(int level, int var, u64 t, const char *fmt, ...)
 
 	if (var >= level) {
 		va_start(args, fmt);
-		ret = __eprintf_time(t, fmt, args);
+		ret = veprintf_time(t, fmt, args);
 		va_end(args);
 	}
 
@@ -91,7 +87,7 @@ void pr_stat(const char *fmt, ...)
 	va_list args;
 
 	va_start(args, fmt);
-	_eprintf(1, verbose, fmt, args);
+	veprintf(1, verbose, fmt, args);
 	va_end(args);
 	eprintf(1, verbose, "\n");
 }
@@ -110,40 +106,61 @@ int dump_printf(const char *fmt, ...)
 	return ret;
 }
 
+static void trace_event_printer(enum binary_printer_ops op,
+				unsigned int val, void *extra)
+{
+	const char *color = PERF_COLOR_BLUE;
+	union perf_event *event = (union perf_event *)extra;
+	unsigned char ch = (unsigned char)val;
+
+	switch (op) {
+	case BINARY_PRINT_DATA_BEGIN:
+		printf(".");
+		color_fprintf(stdout, color, "\n. ... raw event: size %d bytes\n",
+				event->header.size);
+		break;
+	case BINARY_PRINT_LINE_BEGIN:
+		printf(".");
+		break;
+	case BINARY_PRINT_ADDR:
+		color_fprintf(stdout, color, "  %04x: ", val);
+		break;
+	case BINARY_PRINT_NUM_DATA:
+		color_fprintf(stdout, color, " %02x", val);
+		break;
+	case BINARY_PRINT_NUM_PAD:
+		color_fprintf(stdout, color, "   ");
+		break;
+	case BINARY_PRINT_SEP:
+		color_fprintf(stdout, color, "  ");
+		break;
+	case BINARY_PRINT_CHAR_DATA:
+		color_fprintf(stdout, color, "%c",
+			      isprint(ch) ? ch : '.');
+		break;
+	case BINARY_PRINT_CHAR_PAD:
+		color_fprintf(stdout, color, " ");
+		break;
+	case BINARY_PRINT_LINE_END:
+		color_fprintf(stdout, color, "\n");
+		break;
+	case BINARY_PRINT_DATA_END:
+		printf("\n");
+		break;
+	default:
+		break;
+	}
+}
+
 void trace_event(union perf_event *event)
 {
 	unsigned char *raw_event = (void *)event;
-	const char *color = PERF_COLOR_BLUE;
-	int i, j;
 
 	if (!dump_trace)
 		return;
 
-	printf(".");
-	color_fprintf(stdout, color, "\n. ... raw event: size %d bytes\n",
-		      event->header.size);
-
-	for (i = 0; i < event->header.size; i++) {
-		if ((i & 15) == 0) {
-			printf(".");
-			color_fprintf(stdout, color, "  %04x: ", i);
-		}
-
-		color_fprintf(stdout, color, " %02x", raw_event[i]);
-
-		if (((i & 15) == 15) || i == event->header.size-1) {
-			color_fprintf(stdout, color, "  ");
-			for (j = 0; j < 15-(i & 15); j++)
-				color_fprintf(stdout, color, "   ");
-			for (j = i & ~15; j <= i; j++) {
-				color_fprintf(stdout, color, "%c",
-					      isprint(raw_event[j]) ?
-					      raw_event[j] : '.');
-			}
-			color_fprintf(stdout, color, "\n");
-		}
-	}
-	printf(".\n");
+	print_binary(raw_event, event->header.size, 16,
+		     trace_event_printer, event);
 }
 
 static struct debug_variable {
@@ -192,3 +209,23 @@ int perf_debug_option(const char *str)
 	free(s);
 	return 0;
 }
+
+#define DEBUG_WRAPPER(__n, __l)				\
+static int pr_ ## __n ## _wrapper(const char *fmt, ...)	\
+{							\
+	va_list args;					\
+	int ret;					\
+							\
+	va_start(args, fmt);				\
+	ret = veprintf(__l, verbose, fmt, args);	\
+	va_end(args);					\
+	return ret;					\
+}
+
+DEBUG_WRAPPER(warning, 0);
+DEBUG_WRAPPER(debug, 1);
+
+void perf_debug_setup(void)
+{
+	libapi_set_print(pr_warning_wrapper, pr_warning_wrapper, pr_debug_wrapper);
+}
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index 8b9a088c3..14bafda79 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -53,5 +53,6 @@ int eprintf_time(int level, int var, u64 t, const char *fmt, ...) __attribute__(
 int veprintf(int level, int var, const char *fmt, va_list args);
 
 int perf_debug_option(const char *str);
+void perf_debug_setup(void);
 
 #endif	/* __PERF_DEBUG_H */
diff --git a/tools/perf/util/demangle-java.c b/tools/perf/util/demangle-java.c
new file mode 100644
index 000000000..3e6062ab2
--- /dev/null
+++ b/tools/perf/util/demangle-java.c
@@ -0,0 +1,199 @@
+#include <sys/types.h>
+#include <stdio.h>
+#include <string.h>
+#include "util.h"
+#include "debug.h"
+#include "symbol.h"
+
+#include "demangle-java.h"
+
+enum {
+	MODE_PREFIX = 0,
+	MODE_CLASS  = 1,
+	MODE_FUNC   = 2,
+	MODE_TYPE   = 3,
+	MODE_CTYPE  = 3, /* class arg */
+};
+
+#define BASE_ENT(c, n)	[c - 'A']=n
+static const char *base_types['Z' - 'A' + 1] = {
+	BASE_ENT('B', "byte" ),
+	BASE_ENT('C', "char" ),
+	BASE_ENT('D', "double" ),
+	BASE_ENT('F', "float" ),
+	BASE_ENT('I', "int" ),
+	BASE_ENT('J', "long" ),
+	BASE_ENT('S', "short" ),
+	BASE_ENT('Z', "bool" ),
+};
+
+/*
+ * demangle Java symbol between str and end positions and stores
+ * up to maxlen characters into buf. The parser starts in mode.
+ *
+ * Use MODE_PREFIX to process entire prototype till end position
+ * Use MODE_TYPE to process return type if str starts on return type char
+ *
+ *  Return:
+ *	success: buf
+ *	error  : NULL
+ */
+static char *
+__demangle_java_sym(const char *str, const char *end, char *buf, int maxlen, int mode)
+{
+	int rlen = 0;
+	int array = 0;
+	int narg = 0;
+	const char *q;
+
+	if (!end)
+		end = str + strlen(str);
+
+	for (q = str; q != end; q++) {
+
+		if (rlen == (maxlen - 1))
+			break;
+
+		switch (*q) {
+		case 'L':
+			if (mode == MODE_PREFIX || mode == MODE_CTYPE) {
+				if (mode == MODE_CTYPE) {
+					if (narg)
+						rlen += scnprintf(buf + rlen, maxlen - rlen, ", ");
+					narg++;
+				}
+				rlen += scnprintf(buf + rlen, maxlen - rlen, "class ");
+				if (mode == MODE_PREFIX)
+					mode = MODE_CLASS;
+			} else
+				buf[rlen++] = *q;
+			break;
+		case 'B':
+		case 'C':
+		case 'D':
+		case 'F':
+		case 'I':
+		case 'J':
+		case 'S':
+		case 'Z':
+			if (mode == MODE_TYPE) {
+				if (narg)
+					rlen += scnprintf(buf + rlen, maxlen - rlen, ", ");
+				rlen += scnprintf(buf + rlen, maxlen - rlen, "%s", base_types[*q - 'A']);
+				while (array--)
+					rlen += scnprintf(buf + rlen, maxlen - rlen, "[]");
+				array = 0;
+				narg++;
+			} else
+				buf[rlen++] = *q;
+			break;
+		case 'V':
+			if (mode == MODE_TYPE) {
+				rlen += scnprintf(buf + rlen, maxlen - rlen, "void");
+				while (array--)
+					rlen += scnprintf(buf + rlen, maxlen - rlen, "[]");
+				array = 0;
+			} else
+				buf[rlen++] = *q;
+			break;
+		case '[':
+			if (mode != MODE_TYPE)
+				goto error;
+			array++;
+			break;
+		case '(':
+			if (mode != MODE_FUNC)
+				goto error;
+			buf[rlen++] = *q;
+			mode = MODE_TYPE;
+			break;
+		case ')':
+			if (mode != MODE_TYPE)
+				goto error;
+			buf[rlen++] = *q;
+			narg = 0;
+			break;
+		case ';':
+			if (mode != MODE_CLASS && mode != MODE_CTYPE)
+				goto error;
+			/* safe because at least one other char to process */
+			if (isalpha(*(q + 1)))
+				rlen += scnprintf(buf + rlen, maxlen - rlen, ".");
+			if (mode == MODE_CLASS)
+				mode = MODE_FUNC;
+			else if (mode == MODE_CTYPE)
+				mode = MODE_TYPE;
+			break;
+		case '/':
+			if (mode != MODE_CLASS && mode != MODE_CTYPE)
+				goto error;
+			rlen += scnprintf(buf + rlen, maxlen - rlen, ".");
+			break;
+		default :
+			buf[rlen++] = *q;
+		}
+	}
+	buf[rlen] = '\0';
+	return buf;
+error:
+	return NULL;
+}
+
+/*
+ * Demangle Java function signature (openJDK, not GCJ)
+ * input:
+ * 	str: string to parse. String is not modified
+ *    flags: comobination of JAVA_DEMANGLE_* flags to modify demangling
+ * return:
+ *	if input can be demangled, then a newly allocated string is returned.
+ *	if input cannot be demangled, then NULL is returned
+ *
+ * Note: caller is responsible for freeing demangled string
+ */
+char *
+java_demangle_sym(const char *str, int flags)
+{
+	char *buf, *ptr;
+	char *p;
+	size_t len, l1 = 0;
+
+	if (!str)
+		return NULL;
+
+	/* find start of retunr type */
+	p = strrchr(str, ')');
+	if (!p)
+		return NULL;
+
+	/*
+	 * expansion factor estimated to 3x
+	 */
+	len = strlen(str) * 3 + 1;
+	buf = malloc(len);
+	if (!buf)
+		return NULL;
+
+	buf[0] = '\0';
+	if (!(flags & JAVA_DEMANGLE_NORET)) {
+		/*
+		 * get return type first
+		 */
+		ptr = __demangle_java_sym(p + 1, NULL, buf, len, MODE_TYPE);
+		if (!ptr)
+			goto error;
+
+		/* add space between return type and function prototype */
+		l1 = strlen(buf);
+		buf[l1++] = ' ';
+	}
+
+	/* process function up to return type */
+	ptr = __demangle_java_sym(str, p + 1, buf + l1, len - l1, MODE_PREFIX);
+	if (!ptr)
+		goto error;
+
+	return buf;
+error:
+	free(buf);
+	return NULL;
+}
diff --git a/tools/perf/util/demangle-java.h b/tools/perf/util/demangle-java.h
new file mode 100644
index 000000000..a981c1f96
--- /dev/null
+++ b/tools/perf/util/demangle-java.h
@@ -0,0 +1,10 @@
+#ifndef __PERF_DEMANGLE_JAVA
+#define __PERF_DEMANGLE_JAVA 1
+/*
+ * demangle function flags
+ */
+#define JAVA_DEMANGLE_NORET	0x1 /* do not process return type */
+
+char * java_demangle_sym(const char *str, int flags);
+
+#endif /* __PERF_DEMANGLE_JAVA */
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index e8e9a9dbf..8e6395439 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -52,6 +52,11 @@ int dso__read_binary_type_filename(const struct dso *dso,
 			debuglink--;
 		if (*debuglink == '/')
 			debuglink++;
+
+		ret = -1;
+		if (!is_regular_file(filename))
+			break;
+
 		ret = filename__read_debuglink(filename, debuglink,
 					       size - (debuglink - filename));
 		}
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index 45ec4d0a5..095328062 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -162,6 +162,7 @@ struct dso {
 	u8		 loaded;
 	u8		 rel;
 	u8		 build_id[BUILD_ID_SIZE];
+	u64		 text_offset;
 	const char	 *short_name;
 	const char	 *long_name;
 	u16		 long_name_len;
@@ -301,7 +302,7 @@ int __kmod_path__parse(struct kmod_path *m, const char *path,
  * TODO
 */
 int dso__data_get_fd(struct dso *dso, struct machine *machine);
-void dso__data_put_fd(struct dso *dso __maybe_unused);
+void dso__data_put_fd(struct dso *dso);
 void dso__data_close(struct dso *dso);
 
 off_t dso__data_size(struct dso *dso, struct machine *machine);
diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index a509aa843..aea189b41 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -915,7 +915,7 @@ int die_get_typename(Dwarf_Die *vr_die, struct strbuf *buf)
 		tmp = "*";
 	else if (tag == DW_TAG_subroutine_type) {
 		/* Function pointer */
-		strbuf_addf(buf, "(function_type)");
+		strbuf_add(buf, "(function_type)", 15);
 		return 0;
 	} else {
 		if (!dwarf_diename(&type))
@@ -932,7 +932,7 @@ int die_get_typename(Dwarf_Die *vr_die, struct strbuf *buf)
 	}
 	ret = die_get_typename(&type, buf);
 	if (ret == 0)
-		strbuf_addf(buf, "%s", tmp);
+		strbuf_addstr(buf, tmp);
 
 	return ret;
 }
@@ -951,7 +951,7 @@ int die_get_varname(Dwarf_Die *vr_die, struct strbuf *buf)
 	ret = die_get_typename(vr_die, buf);
 	if (ret < 0) {
 		pr_debug("Failed to get type, make it unknown.\n");
-		strbuf_addf(buf, "(unknown_type)");
+		strbuf_add(buf, " (unknown_type)", 14);
 	}
 
 	strbuf_addf(buf, "\t%s", dwarf_diename(vr_die));
@@ -959,6 +959,7 @@ int die_get_varname(Dwarf_Die *vr_die, struct strbuf *buf)
 	return 0;
 }
 
+#ifdef HAVE_DWARF_GETLOCATIONS
 /**
  * die_get_var_innermost_scope - Get innermost scope range of given variable DIE
  * @sp_die: a subprogram DIE
@@ -1013,7 +1014,7 @@ static int die_get_var_innermost_scope(Dwarf_Die *sp_die, Dwarf_Die *vr_die,
 	}
 
 	if (!first)
-		strbuf_addf(buf, "]>");
+		strbuf_add(buf, "]>", 2);
 
 out:
 	free(scopes);
@@ -1076,7 +1077,15 @@ int die_get_var_range(Dwarf_Die *sp_die, Dwarf_Die *vr_die, struct strbuf *buf)
 	}
 
 	if (!first)
-		strbuf_addf(buf, "]>");
+		strbuf_add(buf, "]>", 2);
 
 	return ret;
 }
+#else
+int die_get_var_range(Dwarf_Die *sp_die __maybe_unused,
+		      Dwarf_Die *vr_die __maybe_unused,
+		      struct strbuf *buf __maybe_unused)
+{
+	return -ENOTSUP;
+}
+#endif
diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h
index c42ec366f..dc0ce1adb 100644
--- a/tools/perf/util/dwarf-aux.h
+++ b/tools/perf/util/dwarf-aux.h
@@ -25,48 +25,48 @@
 #include <elfutils/version.h>
 
 /* Find the realpath of the target file */
-extern const char *cu_find_realpath(Dwarf_Die *cu_die, const char *fname);
+const char *cu_find_realpath(Dwarf_Die *cu_die, const char *fname);
 
 /* Get DW_AT_comp_dir (should be NULL with older gcc) */
-extern const char *cu_get_comp_dir(Dwarf_Die *cu_die);
+const char *cu_get_comp_dir(Dwarf_Die *cu_die);
 
 /* Get a line number and file name for given address */
-extern int cu_find_lineinfo(Dwarf_Die *cudie, unsigned long addr,
-			    const char **fname, int *lineno);
+int cu_find_lineinfo(Dwarf_Die *cudie, unsigned long addr,
+		     const char **fname, int *lineno);
 
 /* Walk on funcitons at given address */
-extern int cu_walk_functions_at(Dwarf_Die *cu_die, Dwarf_Addr addr,
-			int (*callback)(Dwarf_Die *, void *), void *data);
+int cu_walk_functions_at(Dwarf_Die *cu_die, Dwarf_Addr addr,
+			 int (*callback)(Dwarf_Die *, void *), void *data);
 
 /* Ensure that this DIE is a subprogram and definition (not declaration) */
-extern bool die_is_func_def(Dwarf_Die *dw_die);
+bool die_is_func_def(Dwarf_Die *dw_die);
 
 /* Ensure that this DIE is an instance of a subprogram */
-extern bool die_is_func_instance(Dwarf_Die *dw_die);
+bool die_is_func_instance(Dwarf_Die *dw_die);
 
 /* Compare diename and tname */
-extern bool die_compare_name(Dwarf_Die *dw_die, const char *tname);
+bool die_compare_name(Dwarf_Die *dw_die, const char *tname);
 
 /* Matching diename with glob pattern */
-extern bool die_match_name(Dwarf_Die *dw_die, const char *glob);
+bool die_match_name(Dwarf_Die *dw_die, const char *glob);
 
 /* Get callsite line number of inline-function instance */
-extern int die_get_call_lineno(Dwarf_Die *in_die);
+int die_get_call_lineno(Dwarf_Die *in_die);
 
 /* Get callsite file name of inlined function instance */
-extern const char *die_get_call_file(Dwarf_Die *in_die);
+const char *die_get_call_file(Dwarf_Die *in_die);
 
 /* Get type die */
-extern Dwarf_Die *die_get_type(Dwarf_Die *vr_die, Dwarf_Die *die_mem);
+Dwarf_Die *die_get_type(Dwarf_Die *vr_die, Dwarf_Die *die_mem);
 
 /* Get a type die, but skip qualifiers and typedef */
-extern Dwarf_Die *die_get_real_type(Dwarf_Die *vr_die, Dwarf_Die *die_mem);
+Dwarf_Die *die_get_real_type(Dwarf_Die *vr_die, Dwarf_Die *die_mem);
 
 /* Check whether the DIE is signed or not */
-extern bool die_is_signed_type(Dwarf_Die *tp_die);
+bool die_is_signed_type(Dwarf_Die *tp_die);
 
 /* Get data_member_location offset */
-extern int die_get_data_member_location(Dwarf_Die *mb_die, Dwarf_Word *offs);
+int die_get_data_member_location(Dwarf_Die *mb_die, Dwarf_Word *offs);
 
 /* Return values for die_find_child() callbacks */
 enum {
@@ -77,29 +77,29 @@ enum {
 };
 
 /* Search child DIEs */
-extern Dwarf_Die *die_find_child(Dwarf_Die *rt_die,
-				 int (*callback)(Dwarf_Die *, void *),
-				 void *data, Dwarf_Die *die_mem);
+Dwarf_Die *die_find_child(Dwarf_Die *rt_die,
+			 int (*callback)(Dwarf_Die *, void *),
+			 void *data, Dwarf_Die *die_mem);
 
 /* Search a non-inlined function including given address */
-extern Dwarf_Die *die_find_realfunc(Dwarf_Die *cu_die, Dwarf_Addr addr,
-				    Dwarf_Die *die_mem);
+Dwarf_Die *die_find_realfunc(Dwarf_Die *cu_die, Dwarf_Addr addr,
+			     Dwarf_Die *die_mem);
 
 /* Search a non-inlined function with tail call at given address */
 Dwarf_Die *die_find_tailfunc(Dwarf_Die *cu_die, Dwarf_Addr addr,
 				    Dwarf_Die *die_mem);
 
 /* Search the top inlined function including given address */
-extern Dwarf_Die *die_find_top_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
-					  Dwarf_Die *die_mem);
+Dwarf_Die *die_find_top_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
+				   Dwarf_Die *die_mem);
 
 /* Search the deepest inlined function including given address */
-extern Dwarf_Die *die_find_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
-				      Dwarf_Die *die_mem);
+Dwarf_Die *die_find_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
+			       Dwarf_Die *die_mem);
 
 /* Walk on the instances of given DIE */
-extern int die_walk_instances(Dwarf_Die *in_die,
-			      int (*callback)(Dwarf_Die *, void *), void *data);
+int die_walk_instances(Dwarf_Die *in_die,
+		       int (*callback)(Dwarf_Die *, void *), void *data);
 
 /* Walker on lines (Note: line number will not be sorted) */
 typedef int (* line_walk_callback_t) (const char *fname, int lineno,
@@ -109,22 +109,20 @@ typedef int (* line_walk_callback_t) (const char *fname, int lineno,
  * Walk on lines inside given DIE. If the DIE is a subprogram, walk only on
  * the lines inside the subprogram, otherwise the DIE must be a CU DIE.
  */
-extern int die_walk_lines(Dwarf_Die *rt_die, line_walk_callback_t callback,
-			  void *data);
+int die_walk_lines(Dwarf_Die *rt_die, line_walk_callback_t callback, void *data);
 
 /* Find a variable called 'name' at given address */
-extern Dwarf_Die *die_find_variable_at(Dwarf_Die *sp_die, const char *name,
-				       Dwarf_Addr addr, Dwarf_Die *die_mem);
+Dwarf_Die *die_find_variable_at(Dwarf_Die *sp_die, const char *name,
+				Dwarf_Addr addr, Dwarf_Die *die_mem);
 
 /* Find a member called 'name' */
-extern Dwarf_Die *die_find_member(Dwarf_Die *st_die, const char *name,
-				  Dwarf_Die *die_mem);
+Dwarf_Die *die_find_member(Dwarf_Die *st_die, const char *name,
+			   Dwarf_Die *die_mem);
 
 /* Get the name of given variable DIE */
-extern int die_get_typename(Dwarf_Die *vr_die, struct strbuf *buf);
+int die_get_typename(Dwarf_Die *vr_die, struct strbuf *buf);
 
 /* Get the name and type of given variable DIE, stored as "type\tname" */
-extern int die_get_varname(Dwarf_Die *vr_die, struct strbuf *buf);
-extern int die_get_var_range(Dwarf_Die *sp_die, Dwarf_Die *vr_die,
-			struct strbuf *buf);
+int die_get_varname(Dwarf_Die *vr_die, struct strbuf *buf);
+int die_get_var_range(Dwarf_Die *sp_die, Dwarf_Die *vr_die, struct strbuf *buf);
 #endif
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index 7dd5939de..49a11d9d8 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -6,6 +6,8 @@ struct perf_env perf_env;
 
 void perf_env__exit(struct perf_env *env)
 {
+	int i;
+
 	zfree(&env->hostname);
 	zfree(&env->os_release);
 	zfree(&env->version);
@@ -19,6 +21,10 @@ void perf_env__exit(struct perf_env *env)
 	zfree(&env->numa_nodes);
 	zfree(&env->pmu_mappings);
 	zfree(&env->cpu);
+
+	for (i = 0; i < env->caches_cnt; i++)
+		cpu_cache_level__free(&env->caches[i]);
+	zfree(&env->caches);
 }
 
 int perf_env__set_cmdline(struct perf_env *env, int argc, const char *argv[])
@@ -75,3 +81,10 @@ int perf_env__read_cpu_topology_map(struct perf_env *env)
 	env->nr_cpus_avail = nr_cpus;
 	return 0;
 }
+
+void cpu_cache_level__free(struct cpu_cache_level *cache)
+{
+	free(cache->type);
+	free(cache->map);
+	free(cache->size);
+}
diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
index 0132b9557..56cffb60a 100644
--- a/tools/perf/util/env.h
+++ b/tools/perf/util/env.h
@@ -1,11 +1,23 @@
 #ifndef __PERF_ENV_H
 #define __PERF_ENV_H
 
+#include <linux/types.h>
+
 struct cpu_topology_map {
 	int	socket_id;
 	int	core_id;
 };
 
+struct cpu_cache_level {
+	u32	level;
+	u32	line_size;
+	u32	sets;
+	u32	ways;
+	char	*type;
+	char	*size;
+	char	*map;
+};
+
 struct perf_env {
 	char			*hostname;
 	char			*os_release;
@@ -31,6 +43,8 @@ struct perf_env {
 	char			*numa_nodes;
 	char			*pmu_mappings;
 	struct cpu_topology_map	*cpu;
+	struct cpu_cache_level	*caches;
+	int			 caches_cnt;
 };
 
 extern struct perf_env perf_env;
@@ -41,4 +55,5 @@ int perf_env__set_cmdline(struct perf_env *env, int argc, const char *argv[]);
 
 int perf_env__read_cpu_topology_map(struct perf_env *env);
 
+void cpu_cache_level__free(struct cpu_cache_level *cache);
 #endif /* __PERF_ENV_H */
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 7bad5c3fa..edcf4ed4e 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -56,13 +56,22 @@ const char *perf_event__name(unsigned int id)
 	return perf_event__names[id];
 }
 
-static struct perf_sample synth_sample = {
+static int perf_tool__process_synth_event(struct perf_tool *tool,
+					  union perf_event *event,
+					  struct machine *machine,
+					  perf_event__handler_t process)
+{
+	struct perf_sample synth_sample = {
 	.pid	   = -1,
 	.tid	   = -1,
 	.time	   = -1,
 	.stream_id = -1,
 	.cpu	   = -1,
 	.period	   = 1,
+	.cpumode   = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK,
+	};
+
+	return process(tool, event, &synth_sample, machine);
 };
 
 /*
@@ -186,7 +195,7 @@ pid_t perf_event__synthesize_comm(struct perf_tool *tool,
 	if (perf_event__prepare_comm(event, pid, machine, &tgid, &ppid) != 0)
 		return -1;
 
-	if (process(tool, event, &synth_sample, machine) != 0)
+	if (perf_tool__process_synth_event(tool, event, machine, process) != 0)
 		return -1;
 
 	return tgid;
@@ -218,7 +227,7 @@ static int perf_event__synthesize_fork(struct perf_tool *tool,
 
 	event->fork.header.size = (sizeof(event->fork) + machine->id_hdr_size);
 
-	if (process(tool, event, &synth_sample, machine) != 0)
+	if (perf_tool__process_synth_event(tool, event, machine, process) != 0)
 		return -1;
 
 	return 0;
@@ -344,7 +353,7 @@ out:
 		event->mmap2.pid = tgid;
 		event->mmap2.tid = pid;
 
-		if (process(tool, event, &synth_sample, machine) != 0) {
+		if (perf_tool__process_synth_event(tool, event, machine, process) != 0) {
 			rc = -1;
 			break;
 		}
@@ -402,7 +411,7 @@ int perf_event__synthesize_modules(struct perf_tool *tool,
 
 		memcpy(event->mmap.filename, pos->dso->long_name,
 		       pos->dso->long_name_len + 1);
-		if (process(tool, event, &synth_sample, machine) != 0) {
+		if (perf_tool__process_synth_event(tool, event, machine, process) != 0) {
 			rc = -1;
 			break;
 		}
@@ -424,7 +433,7 @@ static int __event__synthesize_thread(union perf_event *comm_event,
 {
 	char filename[PATH_MAX];
 	DIR *tasks;
-	struct dirent dirent, *next;
+	struct dirent *dirent;
 	pid_t tgid, ppid;
 	int rc = 0;
 
@@ -453,11 +462,11 @@ static int __event__synthesize_thread(union perf_event *comm_event,
 		return 0;
 	}
 
-	while (!readdir_r(tasks, &dirent, &next) && next) {
+	while ((dirent = readdir(tasks)) != NULL) {
 		char *end;
 		pid_t _pid;
 
-		_pid = strtol(dirent.d_name, &end, 10);
+		_pid = strtol(dirent->d_name, &end, 10);
 		if (*end)
 			continue;
 
@@ -472,7 +481,7 @@ static int __event__synthesize_thread(union perf_event *comm_event,
 		/*
 		 * Send the prepared comm event
 		 */
-		if (process(tool, comm_event, &synth_sample, machine) != 0)
+		if (perf_tool__process_synth_event(tool, comm_event, machine, process) != 0)
 			break;
 
 		rc = 0;
@@ -566,7 +575,7 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
 {
 	DIR *proc;
 	char proc_path[PATH_MAX];
-	struct dirent dirent, *next;
+	struct dirent *dirent;
 	union perf_event *comm_event, *mmap_event, *fork_event;
 	int err = -1;
 
@@ -591,9 +600,9 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
 	if (proc == NULL)
 		goto out_free_fork;
 
-	while (!readdir_r(proc, &dirent, &next) && next) {
+	while ((dirent = readdir(proc)) != NULL) {
 		char *end;
-		pid_t pid = strtol(dirent.d_name, &end, 10);
+		pid_t pid = strtol(dirent->d_name, &end, 10);
 
 		if (*end) /* only interested in proper numerical dirents */
 			continue;
@@ -701,7 +710,7 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
 	event->mmap.len   = map->end - event->mmap.start;
 	event->mmap.pid   = machine->pid;
 
-	err = process(tool, event, &synth_sample, machine);
+	err = perf_tool__process_synth_event(tool, event, machine, process);
 	free(event);
 
 	return err;
@@ -1295,12 +1304,9 @@ void thread__find_addr_location(struct thread *thread,
  * Callers need to drop the reference to al->thread, obtained in
  * machine__findnew_thread()
  */
-int perf_event__preprocess_sample(const union perf_event *event,
-				  struct machine *machine,
-				  struct addr_location *al,
-				  struct perf_sample *sample)
+int machine__resolve(struct machine *machine, struct addr_location *al,
+		     struct perf_sample *sample)
 {
-	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 	struct thread *thread = machine__findnew_thread(machine, sample->pid,
 							sample->tid);
 
@@ -1315,11 +1321,11 @@ int perf_event__preprocess_sample(const union perf_event *event,
 	 * events, but for older perf.data files there was no such thing, so do
 	 * it now.
 	 */
-	if (cpumode == PERF_RECORD_MISC_KERNEL &&
+	if (sample->cpumode == PERF_RECORD_MISC_KERNEL &&
 	    machine__kernel_map(machine) == NULL)
 		machine__create_kernel_maps(machine);
 
-	thread__find_addr_map(thread, cpumode, MAP__FUNCTION, sample->ip, al);
+	thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, sample->ip, al);
 	dump_printf(" ...... dso: %s\n",
 		    al->map ? al->map->dso->long_name :
 			al->level == 'H' ? "[hypervisor]" : "<not found>");
@@ -1395,16 +1401,12 @@ bool sample_addr_correlates_sym(struct perf_event_attr *attr)
 	return false;
 }
 
-void perf_event__preprocess_sample_addr(union perf_event *event,
-					struct perf_sample *sample,
-					struct thread *thread,
-					struct addr_location *al)
+void thread__resolve(struct thread *thread, struct addr_location *al,
+		     struct perf_sample *sample)
 {
-	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
-
-	thread__find_addr_map(thread, cpumode, MAP__FUNCTION, sample->addr, al);
+	thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, sample->addr, al);
 	if (!al->map)
-		thread__find_addr_map(thread, cpumode, MAP__VARIABLE,
+		thread__find_addr_map(thread, sample->cpumode, MAP__VARIABLE,
 				      sample->addr, al);
 
 	al->cpu = sample->cpu;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index b7ffb7ee9..6bb1c9283 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -192,6 +192,7 @@ struct perf_sample {
 	u64 data_src;
 	u32 flags;
 	u16 insn_len;
+	u8  cpumode;
 	void *raw_data;
 	struct ip_callchain *callchain;
 	struct branch_stack *branch_stack;
@@ -597,10 +598,8 @@ int perf_event__process(struct perf_tool *tool,
 
 struct addr_location;
 
-int perf_event__preprocess_sample(const union perf_event *event,
-				  struct machine *machine,
-				  struct addr_location *al,
-				  struct perf_sample *sample);
+int machine__resolve(struct machine *machine, struct addr_location *al,
+		     struct perf_sample *sample);
 
 void addr_location__put(struct addr_location *al);
 
@@ -608,10 +607,8 @@ struct thread;
 
 bool is_bts_event(struct perf_event_attr *attr);
 bool sample_addr_correlates_sym(struct perf_event_attr *attr);
-void perf_event__preprocess_sample_addr(union perf_event *event,
-					struct perf_sample *sample,
-					struct thread *thread,
-					struct addr_location *al);
+void thread__resolve(struct thread *thread, struct addr_location *al,
+		     struct perf_sample *sample);
 
 const char *perf_event__name(unsigned int id);
 
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index a7eb0eae9..86a03836a 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1223,6 +1223,9 @@ int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter)
 	int err = 0;
 
 	evlist__for_each(evlist, evsel) {
+		if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
+			continue;
+
 		err = perf_evsel__set_filter(evsel, filter);
 		if (err)
 			break;
@@ -1624,7 +1627,7 @@ size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp)
 	return printed + fprintf(fp, "\n");
 }
 
-int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused,
+int perf_evlist__strerror_open(struct perf_evlist *evlist,
 			       int err, char *buf, size_t size)
 {
 	int printed, value;
@@ -1652,7 +1655,25 @@ int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused,
 				    "Hint:\tTry: 'sudo sh -c \"echo -1 > /proc/sys/kernel/perf_event_paranoid\"'\n"
 				    "Hint:\tThe current value is %d.", value);
 		break;
+	case EINVAL: {
+		struct perf_evsel *first = perf_evlist__first(evlist);
+		int max_freq;
+
+		if (sysctl__read_int("kernel/perf_event_max_sample_rate", &max_freq) < 0)
+			goto out_default;
+
+		if (first->attr.sample_freq < (u64)max_freq)
+			goto out_default;
+
+		printed = scnprintf(buf, size,
+				    "Error:\t%s.\n"
+				    "Hint:\tCheck /proc/sys/kernel/perf_event_max_sample_rate.\n"
+				    "Hint:\tThe current value is %d and %" PRIu64 " is being requested.",
+				    emsg, max_freq, first->attr.sample_freq);
+		break;
+	}
 	default:
+out_default:
 		scnprintf(buf, size, "%s", emsg);
 		break;
 	}
@@ -1723,3 +1744,19 @@ void perf_evlist__set_tracking_event(struct perf_evlist *evlist,
 
 	tracking_evsel->tracking = true;
 }
+
+struct perf_evsel *
+perf_evlist__find_evsel_by_str(struct perf_evlist *evlist,
+			       const char *str)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each(evlist, evsel) {
+		if (!evsel->name)
+			continue;
+		if (strcmp(str, evsel->name) == 0)
+			return evsel;
+	}
+
+	return NULL;
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 7c4d9a206..a0d15221d 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -294,4 +294,7 @@ void perf_evlist__set_tracking_event(struct perf_evlist *evlist,
 				     struct perf_evsel *tracking_evsel);
 
 void perf_event_attr__set_max_precise_ip(struct perf_event_attr *attr);
+
+struct perf_evsel *
+perf_evlist__find_evsel_by_str(struct perf_evlist *evlist, const char *str);
 #endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index cdbaf9b51..645dc1828 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -225,6 +225,11 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
 	if (evsel != NULL)
 		perf_evsel__init(evsel, attr, idx);
 
+	if (perf_evsel__is_bpf_output(evsel)) {
+		evsel->attr.sample_type |= PERF_SAMPLE_RAW;
+		evsel->attr.sample_period = 1;
+	}
+
 	return evsel;
 }
 
@@ -898,6 +903,16 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 	if (evsel->precise_max)
 		perf_event_attr__set_max_precise_ip(attr);
 
+	if (opts->all_user) {
+		attr->exclude_kernel = 1;
+		attr->exclude_user   = 0;
+	}
+
+	if (opts->all_kernel) {
+		attr->exclude_kernel = 0;
+		attr->exclude_user   = 1;
+	}
+
 	/*
 	 * Apply event specific term settings,
 	 * it overloads any global configuration.
@@ -1628,6 +1643,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 	data->stream_id = data->id = data->time = -1ULL;
 	data->period = evsel->attr.sample_period;
 	data->weight = 0;
+	data->cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 
 	if (event->header.type != PERF_RECORD_SAMPLE) {
 		if (!evsel->attr.sample_id_all)
@@ -2329,6 +2345,8 @@ out:
 bool perf_evsel__fallback(struct perf_evsel *evsel, int err,
 			  char *msg, size_t msgsize)
 {
+	int paranoid;
+
 	if ((err == ENOENT || err == ENXIO || err == ENODEV) &&
 	    evsel->attr.type   == PERF_TYPE_HARDWARE &&
 	    evsel->attr.config == PERF_COUNT_HW_CPU_CYCLES) {
@@ -2348,6 +2366,22 @@ bool perf_evsel__fallback(struct perf_evsel *evsel, int err,
 
 		zfree(&evsel->name);
 		return true;
+	} else if (err == EACCES && !evsel->attr.exclude_kernel &&
+		   (paranoid = perf_event_paranoid()) > 1) {
+		const char *name = perf_evsel__name(evsel);
+		char *new_name;
+
+		if (asprintf(&new_name, "%s%su", name, strchr(name, ':') ? "" : ":") < 0)
+			return false;
+
+		if (evsel->name)
+			free(evsel->name);
+		evsel->name = new_name;
+		scnprintf(msg, msgsize,
+"kernel.perf_event_paranoid=%d, trying to fall back to excluding kernel samples", paranoid);
+		evsel->attr.exclude_kernel = 1;
+
+		return true;
 	}
 
 	return false;
@@ -2362,13 +2396,17 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
 	case EPERM:
 	case EACCES:
 		return scnprintf(msg, size,
-		 "You may not have permission to collect %sstats.\n"
-		 "Consider tweaking /proc/sys/kernel/perf_event_paranoid:\n"
-		 " -1 - Not paranoid at all\n"
-		 "  0 - Disallow raw tracepoint access for unpriv\n"
-		 "  1 - Disallow cpu events for unpriv\n"
-		 "  2 - Disallow kernel profiling for unpriv",
-				 target->system_wide ? "system-wide " : "");
+		 "You may not have permission to collect %sstats.\n\n"
+		 "Consider tweaking /proc/sys/kernel/perf_event_paranoid,\n"
+		 "which controls use of the performance events system by\n"
+		 "unprivileged users (without CAP_SYS_ADMIN).\n\n"
+		 "The current value is %d:\n\n"
+		 "  -1: Allow use of (almost) all events by all users\n"
+		 ">= 0: Disallow raw tracepoint access by users without CAP_IOC_LOCK\n"
+		 ">= 1: Disallow CPU event access by users without CAP_SYS_ADMIN\n"
+		 ">= 2: Disallow kernel profiling by users without CAP_SYS_ADMIN",
+				 target->system_wide ? "system-wide " : "",
+				 perf_event_paranoid());
 	case ENOENT:
 		return scnprintf(msg, size, "The %s event is not supported.",
 				 perf_evsel__name(evsel));
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 4d8037a3d..501ea6e56 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -362,6 +362,14 @@ static inline bool perf_evsel__is_function_event(struct perf_evsel *evsel)
 #undef FUNCTION_EVENT
 }
 
+static inline bool perf_evsel__is_bpf_output(struct perf_evsel *evsel)
+{
+	struct perf_event_attr *attr = &evsel->attr;
+
+	return (attr->config == PERF_COUNT_SW_BPF_OUTPUT) &&
+		(attr->type == PERF_TYPE_SOFTWARE);
+}
+
 struct perf_attr_details {
 	bool freq;
 	bool verbose;
diff --git a/tools/perf/util/genelf.c b/tools/perf/util/genelf.c
new file mode 100644
index 000000000..c1ef805c6
--- /dev/null
+++ b/tools/perf/util/genelf.c
@@ -0,0 +1,449 @@
+/*
+ * genelf.c
+ * Copyright (C) 2014, Google, Inc
+ *
+ * Contributed by:
+ * 	Stephane Eranian <eranian@gmail.com>
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+
+#include <sys/types.h>
+#include <stdio.h>
+#include <getopt.h>
+#include <stddef.h>
+#include <libelf.h>
+#include <string.h>
+#include <stdlib.h>
+#include <inttypes.h>
+#include <limits.h>
+#include <fcntl.h>
+#include <err.h>
+#include <dwarf.h>
+
+#include "perf.h"
+#include "genelf.h"
+#include "../util/jitdump.h"
+
+#define JVMTI
+
+#define BUILD_ID_URANDOM /* different uuid for each run */
+
+#ifdef HAVE_LIBCRYPTO
+
+#define BUILD_ID_MD5
+#undef BUILD_ID_SHA	/* does not seem to work well when linked with Java */
+#undef BUILD_ID_URANDOM /* different uuid for each run */
+
+#ifdef BUILD_ID_SHA
+#include <openssl/sha.h>
+#endif
+
+#ifdef BUILD_ID_MD5
+#include <openssl/md5.h>
+#endif
+#endif
+
+
+typedef struct {
+  unsigned int namesz;  /* Size of entry's owner string */
+  unsigned int descsz;  /* Size of the note descriptor */
+  unsigned int type;    /* Interpretation of the descriptor */
+  char         name[0]; /* Start of the name+desc data */
+} Elf_Note;
+
+struct options {
+	char *output;
+	int fd;
+};
+
+static char shd_string_table[] = {
+	0,
+	'.', 't', 'e', 'x', 't', 0,			/*  1 */
+	'.', 's', 'h', 's', 't', 'r', 't', 'a', 'b', 0, /*  7 */
+	'.', 's', 'y', 'm', 't', 'a', 'b', 0,		/* 17 */
+	'.', 's', 't', 'r', 't', 'a', 'b', 0,		/* 25 */
+	'.', 'n', 'o', 't', 'e', '.', 'g', 'n', 'u', '.', 'b', 'u', 'i', 'l', 'd', '-', 'i', 'd', 0, /* 33 */
+	'.', 'd', 'e', 'b', 'u', 'g', '_', 'l', 'i', 'n', 'e', 0, /* 52 */
+	'.', 'd', 'e', 'b', 'u', 'g', '_', 'i', 'n', 'f', 'o', 0, /* 64 */
+	'.', 'd', 'e', 'b', 'u', 'g', '_', 'a', 'b', 'b', 'r', 'e', 'v', 0, /* 76 */
+};
+
+static struct buildid_note {
+	Elf_Note desc;		/* descsz: size of build-id, must be multiple of 4 */
+	char	 name[4];	/* GNU\0 */
+	char	 build_id[20];
+} bnote;
+
+static Elf_Sym symtab[]={
+	/* symbol 0 MUST be the undefined symbol */
+	{ .st_name  = 0, /* index in sym_string table */
+	  .st_info  = ELF_ST_TYPE(STT_NOTYPE),
+	  .st_shndx = 0, /* for now */
+	  .st_value = 0x0,
+	  .st_other = ELF_ST_VIS(STV_DEFAULT),
+	  .st_size  = 0,
+	},
+	{ .st_name  = 1, /* index in sym_string table */
+	  .st_info  = ELF_ST_BIND(STB_LOCAL) | ELF_ST_TYPE(STT_FUNC),
+	  .st_shndx = 1,
+	  .st_value = 0, /* for now */
+	  .st_other = ELF_ST_VIS(STV_DEFAULT),
+	  .st_size  = 0, /* for now */
+	}
+};
+
+#ifdef BUILD_ID_URANDOM
+static void
+gen_build_id(struct buildid_note *note,
+	     unsigned long load_addr __maybe_unused,
+	     const void *code __maybe_unused,
+	     size_t csize __maybe_unused)
+{
+	int fd;
+	size_t sz = sizeof(note->build_id);
+	ssize_t sret;
+
+	fd = open("/dev/urandom", O_RDONLY);
+	if (fd == -1)
+		err(1, "cannot access /dev/urandom for builid");
+
+	sret = read(fd, note->build_id, sz);
+
+	close(fd);
+
+	if (sret != (ssize_t)sz)
+		memset(note->build_id, 0, sz);
+}
+#endif
+
+#ifdef BUILD_ID_SHA
+static void
+gen_build_id(struct buildid_note *note,
+	     unsigned long load_addr __maybe_unused,
+	     const void *code,
+	     size_t csize)
+{
+	if (sizeof(note->build_id) < SHA_DIGEST_LENGTH)
+		errx(1, "build_id too small for SHA1");
+
+	SHA1(code, csize, (unsigned char *)note->build_id);
+}
+#endif
+
+#ifdef BUILD_ID_MD5
+static void
+gen_build_id(struct buildid_note *note, unsigned long load_addr, const void *code, size_t csize)
+{
+	MD5_CTX context;
+
+	if (sizeof(note->build_id) < 16)
+		errx(1, "build_id too small for MD5");
+
+	MD5_Init(&context);
+	MD5_Update(&context, &load_addr, sizeof(load_addr));
+	MD5_Update(&context, code, csize);
+	MD5_Final((unsigned char *)note->build_id, &context);
+}
+#endif
+
+/*
+ * fd: file descriptor open for writing for the output file
+ * load_addr: code load address (could be zero, just used for buildid)
+ * sym: function name (for native code - used as the symbol)
+ * code: the native code
+ * csize: the code size in bytes
+ */
+int
+jit_write_elf(int fd, uint64_t load_addr, const char *sym,
+	      const void *code, int csize,
+	      void *debug, int nr_debug_entries)
+{
+	Elf *e;
+	Elf_Data *d;
+	Elf_Scn *scn;
+	Elf_Ehdr *ehdr;
+	Elf_Shdr *shdr;
+	char *strsym = NULL;
+	int symlen;
+	int retval = -1;
+
+	if (elf_version(EV_CURRENT) == EV_NONE) {
+		warnx("ELF initialization failed");
+		return -1;
+	}
+
+	e = elf_begin(fd, ELF_C_WRITE, NULL);
+	if (!e) {
+		warnx("elf_begin failed");
+		goto error;
+	}
+
+	/*
+	 * setup ELF header
+	 */
+	ehdr = elf_newehdr(e);
+	if (!ehdr) {
+		warnx("cannot get ehdr");
+		goto error;
+	}
+
+	ehdr->e_ident[EI_DATA] = GEN_ELF_ENDIAN;
+	ehdr->e_ident[EI_CLASS] = GEN_ELF_CLASS;
+	ehdr->e_machine = GEN_ELF_ARCH;
+	ehdr->e_type = ET_DYN;
+	ehdr->e_entry = GEN_ELF_TEXT_OFFSET;
+	ehdr->e_version = EV_CURRENT;
+	ehdr->e_shstrndx= 2; /* shdr index for section name */
+
+	/*
+	 * setup text section
+	 */
+	scn = elf_newscn(e);
+	if (!scn) {
+		warnx("cannot create section");
+		goto error;
+	}
+
+	d = elf_newdata(scn);
+	if (!d) {
+		warnx("cannot get new data");
+		goto error;
+	}
+
+	d->d_align = 16;
+	d->d_off = 0LL;
+	d->d_buf = (void *)code;
+	d->d_type = ELF_T_BYTE;
+	d->d_size = csize;
+	d->d_version = EV_CURRENT;
+
+	shdr = elf_getshdr(scn);
+	if (!shdr) {
+		warnx("cannot get section header");
+		goto error;
+	}
+
+	shdr->sh_name = 1;
+	shdr->sh_type = SHT_PROGBITS;
+	shdr->sh_addr = GEN_ELF_TEXT_OFFSET;
+	shdr->sh_flags = SHF_EXECINSTR | SHF_ALLOC;
+	shdr->sh_entsize = 0;
+
+	/*
+	 * setup section headers string table
+	 */
+	scn = elf_newscn(e);
+	if (!scn) {
+		warnx("cannot create section");
+		goto error;
+	}
+
+	d = elf_newdata(scn);
+	if (!d) {
+		warnx("cannot get new data");
+		goto error;
+	}
+
+	d->d_align = 1;
+	d->d_off = 0LL;
+	d->d_buf = shd_string_table;
+	d->d_type = ELF_T_BYTE;
+	d->d_size = sizeof(shd_string_table);
+	d->d_version = EV_CURRENT;
+
+	shdr = elf_getshdr(scn);
+	if (!shdr) {
+		warnx("cannot get section header");
+		goto error;
+	}
+
+	shdr->sh_name = 7; /* offset of '.shstrtab' in shd_string_table */
+	shdr->sh_type = SHT_STRTAB;
+	shdr->sh_flags = 0;
+	shdr->sh_entsize = 0;
+
+	/*
+	 * setup symtab section
+	 */
+	symtab[1].st_size  = csize;
+	symtab[1].st_value = GEN_ELF_TEXT_OFFSET;
+
+	scn = elf_newscn(e);
+	if (!scn) {
+		warnx("cannot create section");
+		goto error;
+	}
+
+	d = elf_newdata(scn);
+	if (!d) {
+		warnx("cannot get new data");
+		goto error;
+	}
+
+	d->d_align = 8;
+	d->d_off = 0LL;
+	d->d_buf = symtab;
+	d->d_type = ELF_T_SYM;
+	d->d_size = sizeof(symtab);
+	d->d_version = EV_CURRENT;
+
+	shdr = elf_getshdr(scn);
+	if (!shdr) {
+		warnx("cannot get section header");
+		goto error;
+	}
+
+	shdr->sh_name = 17; /* offset of '.symtab' in shd_string_table */
+	shdr->sh_type = SHT_SYMTAB;
+	shdr->sh_flags = 0;
+	shdr->sh_entsize = sizeof(Elf_Sym);
+	shdr->sh_link = 4; /* index of .strtab section */
+
+	/*
+	 * setup symbols string table
+	 * 2 = 1 for 0 in 1st entry, 1 for the 0 at end of symbol for 2nd entry
+	 */
+	symlen = 2 + strlen(sym);
+	strsym = calloc(1, symlen);
+	if (!strsym) {
+		warnx("cannot allocate strsym");
+		goto error;
+	}
+	strcpy(strsym + 1, sym);
+
+	scn = elf_newscn(e);
+	if (!scn) {
+		warnx("cannot create section");
+		goto error;
+	}
+
+	d = elf_newdata(scn);
+	if (!d) {
+		warnx("cannot get new data");
+		goto error;
+	}
+
+	d->d_align = 1;
+	d->d_off = 0LL;
+	d->d_buf = strsym;
+	d->d_type = ELF_T_BYTE;
+	d->d_size = symlen;
+	d->d_version = EV_CURRENT;
+
+	shdr = elf_getshdr(scn);
+	if (!shdr) {
+		warnx("cannot get section header");
+		goto error;
+	}
+
+	shdr->sh_name = 25; /* offset in shd_string_table */
+	shdr->sh_type = SHT_STRTAB;
+	shdr->sh_flags = 0;
+	shdr->sh_entsize = 0;
+
+	/*
+	 * setup build-id section
+	 */
+	scn = elf_newscn(e);
+	if (!scn) {
+		warnx("cannot create section");
+		goto error;
+	}
+
+	d = elf_newdata(scn);
+	if (!d) {
+		warnx("cannot get new data");
+		goto error;
+	}
+
+	/*
+	 * build-id generation
+	 */
+	gen_build_id(&bnote, load_addr, code, csize);
+	bnote.desc.namesz = sizeof(bnote.name); /* must include 0 termination */
+	bnote.desc.descsz = sizeof(bnote.build_id);
+	bnote.desc.type   = NT_GNU_BUILD_ID;
+	strcpy(bnote.name, "GNU");
+
+	d->d_align = 4;
+	d->d_off = 0LL;
+	d->d_buf = &bnote;
+	d->d_type = ELF_T_BYTE;
+	d->d_size = sizeof(bnote);
+	d->d_version = EV_CURRENT;
+
+	shdr = elf_getshdr(scn);
+	if (!shdr) {
+		warnx("cannot get section header");
+		goto error;
+	}
+
+	shdr->sh_name = 33; /* offset in shd_string_table */
+	shdr->sh_type = SHT_NOTE;
+	shdr->sh_addr = 0x0;
+	shdr->sh_flags = SHF_ALLOC;
+	shdr->sh_size = sizeof(bnote);
+	shdr->sh_entsize = 0;
+
+	if (debug && nr_debug_entries) {
+		retval = jit_add_debug_info(e, load_addr, debug, nr_debug_entries);
+		if (retval)
+			goto error;
+	} else {
+		if (elf_update(e, ELF_C_WRITE) < 0) {
+			warnx("elf_update 4 failed");
+			goto error;
+		}
+	}
+
+	retval = 0;
+error:
+	(void)elf_end(e);
+
+	free(strsym);
+
+
+	return retval;
+}
+
+#ifndef JVMTI
+
+static unsigned char x86_code[] = {
+    0xBB, 0x2A, 0x00, 0x00, 0x00, /* movl $42, %ebx */
+    0xB8, 0x01, 0x00, 0x00, 0x00, /* movl $1, %eax */
+    0xCD, 0x80            /* int $0x80 */
+};
+
+static struct options options;
+
+int main(int argc, char **argv)
+{
+	int c, fd, ret;
+
+	while ((c = getopt(argc, argv, "o:h")) != -1) {
+		switch (c) {
+		case 'o':
+			options.output = optarg;
+			break;
+		case 'h':
+			printf("Usage: genelf -o output_file [-h]\n");
+			return 0;
+		default:
+			errx(1, "unknown option");
+		}
+	}
+
+	fd = open(options.output, O_CREAT|O_TRUNC|O_RDWR, 0666);
+	if (fd == -1)
+		err(1, "cannot create file %s", options.output);
+
+	ret = jit_write_elf(fd, "main", x86_code, sizeof(x86_code));
+	close(fd);
+
+	if (ret != 0)
+		unlink(options.output);
+
+	return ret;
+}
+#endif
diff --git a/tools/perf/util/genelf.h b/tools/perf/util/genelf.h
new file mode 100644
index 000000000..2fbeb59c4
--- /dev/null
+++ b/tools/perf/util/genelf.h
@@ -0,0 +1,61 @@
+#ifndef __GENELF_H__
+#define __GENELF_H__
+
+/* genelf.c */
+int jit_write_elf(int fd, uint64_t code_addr, const char *sym,
+		  const void *code, int csize, void *debug, int nr_debug_entries);
+/* genelf_debug.c */
+int jit_add_debug_info(Elf *e, uint64_t code_addr, void *debug, int nr_debug_entries);
+
+#if   defined(__arm__)
+#define GEN_ELF_ARCH	EM_ARM
+#define GEN_ELF_CLASS	ELFCLASS32
+#elif defined(__aarch64__)
+#define GEN_ELF_ARCH	EM_AARCH64
+#define GEN_ELF_CLASS	ELFCLASS64
+#elif defined(__x86_64__)
+#define GEN_ELF_ARCH	EM_X86_64
+#define GEN_ELF_CLASS	ELFCLASS64
+#elif defined(__i386__)
+#define GEN_ELF_ARCH	EM_386
+#define GEN_ELF_CLASS	ELFCLASS32
+#elif defined(__powerpc64__)
+#define GEN_ELF_ARCH	EM_PPC64
+#define GEN_ELF_CLASS	ELFCLASS64
+#elif defined(__powerpc__)
+#define GEN_ELF_ARCH	EM_PPC
+#define GEN_ELF_CLASS	ELFCLASS32
+#else
+#error "unsupported architecture"
+#endif
+
+#if __BYTE_ORDER == __BIG_ENDIAN
+#define GEN_ELF_ENDIAN	ELFDATA2MSB
+#else
+#define GEN_ELF_ENDIAN	ELFDATA2LSB
+#endif
+
+#if GEN_ELF_CLASS == ELFCLASS64
+#define elf_newehdr	elf64_newehdr
+#define elf_getshdr	elf64_getshdr
+#define Elf_Ehdr	Elf64_Ehdr
+#define Elf_Shdr	Elf64_Shdr
+#define Elf_Sym		Elf64_Sym
+#define ELF_ST_TYPE(a)	ELF64_ST_TYPE(a)
+#define ELF_ST_BIND(a)	ELF64_ST_BIND(a)
+#define ELF_ST_VIS(a)	ELF64_ST_VISIBILITY(a)
+#else
+#define elf_newehdr	elf32_newehdr
+#define elf_getshdr	elf32_getshdr
+#define Elf_Ehdr	Elf32_Ehdr
+#define Elf_Shdr	Elf32_Shdr
+#define Elf_Sym		Elf32_Sym
+#define ELF_ST_TYPE(a)	ELF32_ST_TYPE(a)
+#define ELF_ST_BIND(a)	ELF32_ST_BIND(a)
+#define ELF_ST_VIS(a)	ELF32_ST_VISIBILITY(a)
+#endif
+
+/* The .text section is directly after the ELF header */
+#define GEN_ELF_TEXT_OFFSET sizeof(Elf_Ehdr)
+
+#endif
diff --git a/tools/perf/util/genelf_debug.c b/tools/perf/util/genelf_debug.c
new file mode 100644
index 000000000..5980f7d25
--- /dev/null
+++ b/tools/perf/util/genelf_debug.c
@@ -0,0 +1,610 @@
+/*
+ * genelf_debug.c
+ * Copyright (C) 2015, Google, Inc
+ *
+ * Contributed by:
+ * 	Stephane Eranian <eranian@google.com>
+ *
+ * Released under the GPL v2.
+ *
+ * based on GPLv2 source code from Oprofile
+ * @remark Copyright 2007 OProfile authors
+ * @author Philippe Elie
+ */
+#include <sys/types.h>
+#include <stdio.h>
+#include <getopt.h>
+#include <stddef.h>
+#include <libelf.h>
+#include <string.h>
+#include <stdlib.h>
+#include <inttypes.h>
+#include <limits.h>
+#include <fcntl.h>
+#include <err.h>
+#include <dwarf.h>
+
+#include "perf.h"
+#include "genelf.h"
+#include "../util/jitdump.h"
+
+#define BUFFER_EXT_DFL_SIZE	(4 * 1024)
+
+typedef uint32_t uword;
+typedef uint16_t uhalf;
+typedef int32_t  sword;
+typedef int16_t  shalf;
+typedef uint8_t  ubyte;
+typedef int8_t   sbyte;
+
+struct buffer_ext {
+	size_t cur_pos;
+	size_t max_sz;
+	void *data;
+};
+
+static void
+buffer_ext_dump(struct buffer_ext *be, const char *msg)
+{
+	size_t i;
+	warnx("DUMP for %s", msg);
+	for (i = 0 ; i < be->cur_pos; i++)
+		warnx("%4zu 0x%02x", i, (((char *)be->data)[i]) & 0xff);
+}
+
+static inline int
+buffer_ext_add(struct buffer_ext *be, void *addr, size_t sz)
+{
+	void *tmp;
+	size_t be_sz = be->max_sz;
+
+retry:
+	if ((be->cur_pos + sz) < be_sz) {
+		memcpy(be->data + be->cur_pos, addr, sz);
+		be->cur_pos += sz;
+		return 0;
+	}
+
+	if (!be_sz)
+		be_sz = BUFFER_EXT_DFL_SIZE;
+	else
+		be_sz <<= 1;
+
+	tmp = realloc(be->data, be_sz);
+	if (!tmp)
+		return -1;
+
+	be->data   = tmp;
+	be->max_sz = be_sz;
+
+	goto retry;
+}
+
+static void
+buffer_ext_init(struct buffer_ext *be)
+{
+	be->data = NULL;
+	be->cur_pos = 0;
+	be->max_sz = 0;
+}
+
+static inline size_t
+buffer_ext_size(struct buffer_ext *be)
+{
+	return be->cur_pos;
+}
+
+static inline void *
+buffer_ext_addr(struct buffer_ext *be)
+{
+	return be->data;
+}
+
+struct debug_line_header {
+	// Not counting this field
+	uword total_length;
+	// version number (2 currently)
+	uhalf version;
+	// relative offset from next field to
+	// program statement
+	uword prolog_length;
+	ubyte minimum_instruction_length;
+	ubyte default_is_stmt;
+	// line_base - see DWARF 2 specs
+	sbyte line_base;
+	// line_range - see DWARF 2 specs
+	ubyte line_range;
+	// number of opcode + 1
+	ubyte opcode_base;
+	/* follow the array of opcode args nr: ubytes [nr_opcode_base] */
+	/* follow the search directories index, zero terminated string
+	 * terminated by an empty string.
+	 */
+	/* follow an array of { filename, LEB128, LEB128, LEB128 }, first is
+	 * the directory index entry, 0 means current directory, then mtime
+	 * and filesize, last entry is followed by en empty string.
+	 */
+	/* follow the first program statement */
+} __attribute__((packed));
+
+/* DWARF 2 spec talk only about one possible compilation unit header while
+ * binutils can handle two flavours of dwarf 2, 32 and 64 bits, this is not
+ * related to the used arch, an ELF 32 can hold more than 4 Go of debug
+ * information. For now we handle only DWARF 2 32 bits comp unit. It'll only
+ * become a problem if we generate more than 4GB of debug information.
+ */
+struct compilation_unit_header {
+	uword total_length;
+	uhalf version;
+	uword debug_abbrev_offset;
+	ubyte pointer_size;
+} __attribute__((packed));
+
+#define DW_LNS_num_opcode (DW_LNS_set_isa + 1)
+
+/* field filled at run time are marked with -1 */
+static struct debug_line_header const default_debug_line_header = {
+	.total_length = -1,
+	.version = 2,
+	.prolog_length = -1,
+	.minimum_instruction_length = 1,	/* could be better when min instruction size != 1 */
+	.default_is_stmt = 1,	/* we don't take care about basic block */
+	.line_base = -5,	/* sensible value for line base ... */
+	.line_range = -14,     /* ... and line range are guessed statically */
+	.opcode_base = DW_LNS_num_opcode
+};
+
+static ubyte standard_opcode_length[] =
+{
+	0, 1, 1, 1, 1, 0, 0, 0, 1, 0, 0, 1
+};
+#if 0
+{
+	[DW_LNS_advance_pc]   = 1,
+	[DW_LNS_advance_line] = 1,
+	[DW_LNS_set_file] =  1,
+	[DW_LNS_set_column] = 1,
+	[DW_LNS_fixed_advance_pc] = 1,
+	[DW_LNS_set_isa] = 1,
+};
+#endif
+
+/* field filled at run time are marked with -1 */
+static struct compilation_unit_header default_comp_unit_header = {
+	.total_length = -1,
+	.version = 2,
+	.debug_abbrev_offset = 0,     /* we reuse the same abbrev entries for all comp unit */
+	.pointer_size = sizeof(void *)
+};
+
+static void emit_uword(struct buffer_ext *be, uword data)
+{
+	buffer_ext_add(be, &data, sizeof(uword));
+}
+
+static void emit_string(struct buffer_ext *be, const char *s)
+{
+	buffer_ext_add(be, (void *)s, strlen(s) + 1);
+}
+
+static void emit_unsigned_LEB128(struct buffer_ext *be,
+				 unsigned long data)
+{
+	do {
+		ubyte cur = data & 0x7F;
+		data >>= 7;
+		if (data)
+			cur |= 0x80;
+		buffer_ext_add(be, &cur, 1);
+	} while (data);
+}
+
+static void emit_signed_LEB128(struct buffer_ext *be, long data)
+{
+	int more = 1;
+	int negative = data < 0;
+	int size = sizeof(long) * CHAR_BIT;
+	while (more) {
+		ubyte cur = data & 0x7F;
+		data >>= 7;
+		if (negative)
+			data |= - (1 << (size - 7));
+		if ((data == 0 && !(cur & 0x40)) ||
+		    (data == -1l && (cur & 0x40)))
+			more = 0;
+		else
+			cur |= 0x80;
+		buffer_ext_add(be, &cur, 1);
+	}
+}
+
+static void emit_extended_opcode(struct buffer_ext *be, ubyte opcode,
+				 void *data, size_t data_len)
+{
+	buffer_ext_add(be, (char *)"", 1);
+
+	emit_unsigned_LEB128(be, data_len + 1);
+
+	buffer_ext_add(be, &opcode, 1);
+	buffer_ext_add(be, data, data_len);
+}
+
+static void emit_opcode(struct buffer_ext *be, ubyte opcode)
+{
+	buffer_ext_add(be, &opcode, 1);
+}
+
+static void emit_opcode_signed(struct buffer_ext  *be,
+			       ubyte opcode, long data)
+{
+	buffer_ext_add(be, &opcode, 1);
+	emit_signed_LEB128(be, data);
+}
+
+static void emit_opcode_unsigned(struct buffer_ext *be, ubyte opcode,
+				 unsigned long data)
+{
+	buffer_ext_add(be, &opcode, 1);
+	emit_unsigned_LEB128(be, data);
+}
+
+static void emit_advance_pc(struct buffer_ext *be, unsigned long delta_pc)
+{
+	emit_opcode_unsigned(be, DW_LNS_advance_pc, delta_pc);
+}
+
+static void emit_advance_lineno(struct buffer_ext  *be, long delta_lineno)
+{
+	emit_opcode_signed(be, DW_LNS_advance_line, delta_lineno);
+}
+
+static void emit_lne_end_of_sequence(struct buffer_ext *be)
+{
+	emit_extended_opcode(be, DW_LNE_end_sequence, NULL, 0);
+}
+
+static void emit_set_file(struct buffer_ext *be, unsigned long idx)
+{
+	emit_opcode_unsigned(be, DW_LNS_set_file, idx);
+}
+
+static void emit_lne_define_filename(struct buffer_ext *be,
+				     const char *filename)
+{
+	buffer_ext_add(be, (void *)"", 1);
+
+	/* LNE field, strlen(filename) + zero termination, 3 bytes for: the dir entry, timestamp, filesize */
+	emit_unsigned_LEB128(be, strlen(filename) + 5);
+	emit_opcode(be, DW_LNE_define_file);
+	emit_string(be, filename);
+	/* directory index 0=do not know */
+        emit_unsigned_LEB128(be, 0);
+	/* last modification date on file 0=do not know */
+        emit_unsigned_LEB128(be, 0);
+	/* filesize 0=do not know */
+        emit_unsigned_LEB128(be, 0);
+}
+
+static void emit_lne_set_address(struct buffer_ext *be,
+				 void *address)
+{
+	emit_extended_opcode(be, DW_LNE_set_address, &address, sizeof(unsigned long));
+}
+
+static ubyte get_special_opcode(struct debug_entry *ent,
+				unsigned int last_line,
+				unsigned long last_vma)
+{
+	unsigned int temp;
+	unsigned long delta_addr;
+
+	/*
+	 * delta from line_base
+	 */
+	temp = (ent->lineno - last_line) - default_debug_line_header.line_base;
+
+	if (temp >= default_debug_line_header.line_range)
+		return 0;
+
+	/*
+	 * delta of addresses
+	 */
+	delta_addr = (ent->addr - last_vma) / default_debug_line_header.minimum_instruction_length;
+
+	/* This is not sufficient to ensure opcode will be in [0-256] but
+	 * sufficient to ensure when summing with the delta lineno we will
+	 * not overflow the unsigned long opcode */
+
+	if (delta_addr <= 256 / default_debug_line_header.line_range) {
+		unsigned long opcode = temp +
+			(delta_addr * default_debug_line_header.line_range) +
+			default_debug_line_header.opcode_base;
+
+		return opcode <= 255 ? opcode : 0;
+	}
+	return 0;
+}
+
+static void emit_lineno_info(struct buffer_ext *be,
+			     struct debug_entry *ent, size_t nr_entry,
+			     unsigned long code_addr)
+{
+	size_t i;
+
+	/*
+	 * Machine state at start of a statement program
+	 * address = 0
+	 * file    = 1
+	 * line    = 1
+	 * column  = 0
+	 * is_stmt = default_is_stmt as given in the debug_line_header
+	 * basic block = 0
+	 * end sequence = 0
+	 */
+
+	/* start state of the state machine we take care of */
+	unsigned long last_vma = code_addr;
+	char const  *cur_filename = NULL;
+	unsigned long cur_file_idx = 0;
+	int last_line = 1;
+
+	emit_lne_set_address(be, (void *)code_addr);
+
+	for (i = 0; i < nr_entry; i++, ent = debug_entry_next(ent)) {
+		int need_copy = 0;
+		ubyte special_opcode;
+
+		/*
+		 * check if filename changed, if so add it
+		 */
+		if (!cur_filename || strcmp(cur_filename, ent->name)) {
+			emit_lne_define_filename(be, ent->name);
+			cur_filename = ent->name;
+			emit_set_file(be, ++cur_file_idx);
+			need_copy = 1;
+		}
+
+		special_opcode = get_special_opcode(ent, last_line, last_vma);
+		if (special_opcode != 0) {
+			last_line = ent->lineno;
+			last_vma  = ent->addr;
+			emit_opcode(be, special_opcode);
+		} else {
+			/*
+			 * lines differ, emit line delta
+			 */
+			if (last_line != ent->lineno) {
+				emit_advance_lineno(be, ent->lineno - last_line);
+				last_line = ent->lineno;
+				need_copy = 1;
+			}
+			/*
+			 * addresses differ, emit address delta
+			 */
+			if (last_vma != ent->addr) {
+				emit_advance_pc(be, ent->addr - last_vma);
+				last_vma = ent->addr;
+				need_copy = 1;
+			}
+			/*
+			 * add new row to matrix
+			 */
+			if (need_copy)
+				emit_opcode(be, DW_LNS_copy);
+		}
+	}
+}
+
+static void add_debug_line(struct buffer_ext *be,
+	struct debug_entry *ent, size_t nr_entry,
+	unsigned long code_addr)
+{
+	struct debug_line_header * dbg_header;
+	size_t old_size;
+
+	old_size = buffer_ext_size(be);
+
+	buffer_ext_add(be, (void *)&default_debug_line_header,
+		 sizeof(default_debug_line_header));
+
+	buffer_ext_add(be, &standard_opcode_length,  sizeof(standard_opcode_length));
+
+	// empty directory entry
+	buffer_ext_add(be, (void *)"", 1);
+
+	// empty filename directory
+	buffer_ext_add(be, (void *)"", 1);
+
+	dbg_header = buffer_ext_addr(be) + old_size;
+	dbg_header->prolog_length = (buffer_ext_size(be) - old_size) -
+		offsetof(struct debug_line_header, minimum_instruction_length);
+
+	emit_lineno_info(be, ent, nr_entry, code_addr);
+
+	emit_lne_end_of_sequence(be);
+
+	dbg_header = buffer_ext_addr(be) + old_size;
+	dbg_header->total_length = (buffer_ext_size(be) - old_size) -
+		offsetof(struct debug_line_header, version);
+}
+
+static void
+add_debug_abbrev(struct buffer_ext *be)
+{
+        emit_unsigned_LEB128(be, 1);
+        emit_unsigned_LEB128(be, DW_TAG_compile_unit);
+        emit_unsigned_LEB128(be, DW_CHILDREN_yes);
+        emit_unsigned_LEB128(be, DW_AT_stmt_list);
+        emit_unsigned_LEB128(be, DW_FORM_data4);
+        emit_unsigned_LEB128(be, 0);
+        emit_unsigned_LEB128(be, 0);
+        emit_unsigned_LEB128(be, 0);
+}
+
+static void
+add_compilation_unit(struct buffer_ext *be,
+		     size_t offset_debug_line)
+{
+	struct compilation_unit_header *comp_unit_header;
+	size_t old_size = buffer_ext_size(be);
+
+	buffer_ext_add(be, &default_comp_unit_header,
+		       sizeof(default_comp_unit_header));
+
+	emit_unsigned_LEB128(be, 1);
+	emit_uword(be, offset_debug_line);
+
+	comp_unit_header = buffer_ext_addr(be) + old_size;
+	comp_unit_header->total_length = (buffer_ext_size(be) - old_size) -
+		offsetof(struct compilation_unit_header, version);
+}
+
+static int
+jit_process_debug_info(uint64_t code_addr,
+		       void *debug, int nr_debug_entries,
+		       struct buffer_ext *dl,
+		       struct buffer_ext *da,
+		       struct buffer_ext *di)
+{
+	struct debug_entry *ent = debug;
+	int i;
+
+	for (i = 0; i < nr_debug_entries; i++) {
+		ent->addr = ent->addr - code_addr;
+		ent = debug_entry_next(ent);
+	}
+	add_compilation_unit(di, buffer_ext_size(dl));
+	add_debug_line(dl, debug, nr_debug_entries, 0);
+	add_debug_abbrev(da);
+	if (0) buffer_ext_dump(da, "abbrev");
+
+	return 0;
+}
+
+int
+jit_add_debug_info(Elf *e, uint64_t code_addr, void *debug, int nr_debug_entries)
+{
+	Elf_Data *d;
+	Elf_Scn *scn;
+	Elf_Shdr *shdr;
+	struct buffer_ext dl, di, da;
+	int ret;
+
+	buffer_ext_init(&dl);
+	buffer_ext_init(&di);
+	buffer_ext_init(&da);
+
+	ret = jit_process_debug_info(code_addr, debug, nr_debug_entries, &dl, &da, &di);
+	if (ret)
+		return -1;
+	/*
+	 * setup .debug_line section
+	 */
+	scn = elf_newscn(e);
+	if (!scn) {
+		warnx("cannot create section");
+		return -1;
+	}
+
+	d = elf_newdata(scn);
+	if (!d) {
+		warnx("cannot get new data");
+		return -1;
+	}
+
+	d->d_align = 1;
+	d->d_off = 0LL;
+	d->d_buf = buffer_ext_addr(&dl);
+	d->d_type = ELF_T_BYTE;
+	d->d_size = buffer_ext_size(&dl);
+	d->d_version = EV_CURRENT;
+
+	shdr = elf_getshdr(scn);
+	if (!shdr) {
+		warnx("cannot get section header");
+		return -1;
+	}
+
+	shdr->sh_name = 52; /* .debug_line */
+	shdr->sh_type = SHT_PROGBITS;
+	shdr->sh_addr = 0; /* must be zero or == sh_offset -> dynamic object */
+	shdr->sh_flags = 0;
+	shdr->sh_entsize = 0;
+
+	/*
+	 * setup .debug_info section
+	 */
+	scn = elf_newscn(e);
+	if (!scn) {
+		warnx("cannot create section");
+		return -1;
+	}
+
+	d = elf_newdata(scn);
+	if (!d) {
+		warnx("cannot get new data");
+		return -1;
+	}
+
+	d->d_align = 1;
+	d->d_off = 0LL;
+	d->d_buf = buffer_ext_addr(&di);
+	d->d_type = ELF_T_BYTE;
+	d->d_size = buffer_ext_size(&di);
+	d->d_version = EV_CURRENT;
+
+	shdr = elf_getshdr(scn);
+	if (!shdr) {
+		warnx("cannot get section header");
+		return -1;
+	}
+
+	shdr->sh_name = 64; /* .debug_info */
+	shdr->sh_type = SHT_PROGBITS;
+	shdr->sh_addr = 0; /* must be zero or == sh_offset -> dynamic object */
+	shdr->sh_flags = 0;
+	shdr->sh_entsize = 0;
+
+	/*
+	 * setup .debug_abbrev section
+	 */
+	scn = elf_newscn(e);
+	if (!scn) {
+		warnx("cannot create section");
+		return -1;
+	}
+
+	d = elf_newdata(scn);
+	if (!d) {
+		warnx("cannot get new data");
+		return -1;
+	}
+
+	d->d_align = 1;
+	d->d_off = 0LL;
+	d->d_buf = buffer_ext_addr(&da);
+	d->d_type = ELF_T_BYTE;
+	d->d_size = buffer_ext_size(&da);
+	d->d_version = EV_CURRENT;
+
+	shdr = elf_getshdr(scn);
+	if (!shdr) {
+		warnx("cannot get section header");
+		return -1;
+	}
+
+	shdr->sh_name = 76; /* .debug_info */
+	shdr->sh_type = SHT_PROGBITS;
+	shdr->sh_addr = 0; /* must be zero or == sh_offset -> dynamic object */
+	shdr->sh_flags = 0;
+	shdr->sh_entsize = 0;
+
+	/*
+	 * now we update the ELF image with all the sections
+	 */
+	if (elf_update(e, ELF_C_WRITE) < 0) {
+		warnx("elf_update debug failed");
+		return -1;
+	}
+	return 0;
+}
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index f50b7235e..90680ec9f 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -23,6 +23,8 @@
 #include "strbuf.h"
 #include "build-id.h"
 #include "data.h"
+#include <api/fs/fs.h>
+#include "asm/bug.h"
 
 /*
  * magic2 = "PERFILE2"
@@ -868,6 +870,199 @@ static int write_auxtrace(int fd, struct perf_header *h,
 	return err;
 }
 
+static int cpu_cache_level__sort(const void *a, const void *b)
+{
+	struct cpu_cache_level *cache_a = (struct cpu_cache_level *)a;
+	struct cpu_cache_level *cache_b = (struct cpu_cache_level *)b;
+
+	return cache_a->level - cache_b->level;
+}
+
+static bool cpu_cache_level__cmp(struct cpu_cache_level *a, struct cpu_cache_level *b)
+{
+	if (a->level != b->level)
+		return false;
+
+	if (a->line_size != b->line_size)
+		return false;
+
+	if (a->sets != b->sets)
+		return false;
+
+	if (a->ways != b->ways)
+		return false;
+
+	if (strcmp(a->type, b->type))
+		return false;
+
+	if (strcmp(a->size, b->size))
+		return false;
+
+	if (strcmp(a->map, b->map))
+		return false;
+
+	return true;
+}
+
+static int cpu_cache_level__read(struct cpu_cache_level *cache, u32 cpu, u16 level)
+{
+	char path[PATH_MAX], file[PATH_MAX];
+	struct stat st;
+	size_t len;
+
+	scnprintf(path, PATH_MAX, "devices/system/cpu/cpu%d/cache/index%d/", cpu, level);
+	scnprintf(file, PATH_MAX, "%s/%s", sysfs__mountpoint(), path);
+
+	if (stat(file, &st))
+		return 1;
+
+	scnprintf(file, PATH_MAX, "%s/level", path);
+	if (sysfs__read_int(file, (int *) &cache->level))
+		return -1;
+
+	scnprintf(file, PATH_MAX, "%s/coherency_line_size", path);
+	if (sysfs__read_int(file, (int *) &cache->line_size))
+		return -1;
+
+	scnprintf(file, PATH_MAX, "%s/number_of_sets", path);
+	if (sysfs__read_int(file, (int *) &cache->sets))
+		return -1;
+
+	scnprintf(file, PATH_MAX, "%s/ways_of_associativity", path);
+	if (sysfs__read_int(file, (int *) &cache->ways))
+		return -1;
+
+	scnprintf(file, PATH_MAX, "%s/type", path);
+	if (sysfs__read_str(file, &cache->type, &len))
+		return -1;
+
+	cache->type[len] = 0;
+	cache->type = rtrim(cache->type);
+
+	scnprintf(file, PATH_MAX, "%s/size", path);
+	if (sysfs__read_str(file, &cache->size, &len)) {
+		free(cache->type);
+		return -1;
+	}
+
+	cache->size[len] = 0;
+	cache->size = rtrim(cache->size);
+
+	scnprintf(file, PATH_MAX, "%s/shared_cpu_list", path);
+	if (sysfs__read_str(file, &cache->map, &len)) {
+		free(cache->map);
+		free(cache->type);
+		return -1;
+	}
+
+	cache->map[len] = 0;
+	cache->map = rtrim(cache->map);
+	return 0;
+}
+
+static void cpu_cache_level__fprintf(FILE *out, struct cpu_cache_level *c)
+{
+	fprintf(out, "L%d %-15s %8s [%s]\n", c->level, c->type, c->size, c->map);
+}
+
+static int build_caches(struct cpu_cache_level caches[], u32 size, u32 *cntp)
+{
+	u32 i, cnt = 0;
+	long ncpus;
+	u32 nr, cpu;
+	u16 level;
+
+	ncpus = sysconf(_SC_NPROCESSORS_CONF);
+	if (ncpus < 0)
+		return -1;
+
+	nr = (u32)(ncpus & UINT_MAX);
+
+	for (cpu = 0; cpu < nr; cpu++) {
+		for (level = 0; level < 10; level++) {
+			struct cpu_cache_level c;
+			int err;
+
+			err = cpu_cache_level__read(&c, cpu, level);
+			if (err < 0)
+				return err;
+
+			if (err == 1)
+				break;
+
+			for (i = 0; i < cnt; i++) {
+				if (cpu_cache_level__cmp(&c, &caches[i]))
+					break;
+			}
+
+			if (i == cnt)
+				caches[cnt++] = c;
+			else
+				cpu_cache_level__free(&c);
+
+			if (WARN_ONCE(cnt == size, "way too many cpu caches.."))
+				goto out;
+		}
+	}
+ out:
+	*cntp = cnt;
+	return 0;
+}
+
+#define MAX_CACHES 2000
+
+static int write_cache(int fd, struct perf_header *h __maybe_unused,
+			  struct perf_evlist *evlist __maybe_unused)
+{
+	struct cpu_cache_level caches[MAX_CACHES];
+	u32 cnt = 0, i, version = 1;
+	int ret;
+
+	ret = build_caches(caches, MAX_CACHES, &cnt);
+	if (ret)
+		goto out;
+
+	qsort(&caches, cnt, sizeof(struct cpu_cache_level), cpu_cache_level__sort);
+
+	ret = do_write(fd, &version, sizeof(u32));
+	if (ret < 0)
+		goto out;
+
+	ret = do_write(fd, &cnt, sizeof(u32));
+	if (ret < 0)
+		goto out;
+
+	for (i = 0; i < cnt; i++) {
+		struct cpu_cache_level *c = &caches[i];
+
+		#define _W(v)					\
+			ret = do_write(fd, &c->v, sizeof(u32));	\
+			if (ret < 0)				\
+				goto out;
+
+		_W(level)
+		_W(line_size)
+		_W(sets)
+		_W(ways)
+		#undef _W
+
+		#define _W(v)						\
+			ret = do_write_string(fd, (const char *) c->v);	\
+			if (ret < 0)					\
+				goto out;
+
+		_W(type)
+		_W(size)
+		_W(map)
+		#undef _W
+	}
+
+out:
+	for (i = 0; i < cnt; i++)
+		cpu_cache_level__free(&caches[i]);
+	return ret;
+}
+
 static int write_stat(int fd __maybe_unused,
 		      struct perf_header *h __maybe_unused,
 		      struct perf_evlist *evlist __maybe_unused)
@@ -1172,6 +1367,18 @@ static void print_stat(struct perf_header *ph __maybe_unused,
 	fprintf(fp, "# contains stat data\n");
 }
 
+static void print_cache(struct perf_header *ph __maybe_unused,
+			int fd __maybe_unused, FILE *fp __maybe_unused)
+{
+	int i;
+
+	fprintf(fp, "# CPU cache info:\n");
+	for (i = 0; i < ph->env.caches_cnt; i++) {
+		fprintf(fp, "#  ");
+		cpu_cache_level__fprintf(fp, &ph->env.caches[i]);
+	}
+}
+
 static void print_pmu_mappings(struct perf_header *ph, int fd __maybe_unused,
 			       FILE *fp)
 {
@@ -1665,11 +1872,6 @@ static int process_cpu_topology(struct perf_file_section *section,
 		if (ph->needs_swap)
 			nr = bswap_32(nr);
 
-		if (nr > (u32)cpu_nr) {
-			pr_debug("core_id number is too big."
-				 "You may need to upgrade the perf tool.\n");
-			goto free_cpu;
-		}
 		ph->env.cpu[i].core_id = nr;
 
 		ret = readn(fd, &nr, sizeof(nr));
@@ -1920,6 +2122,68 @@ static int process_auxtrace(struct perf_file_section *section,
 	return err;
 }
 
+static int process_cache(struct perf_file_section *section __maybe_unused,
+			 struct perf_header *ph __maybe_unused, int fd __maybe_unused,
+			 void *data __maybe_unused)
+{
+	struct cpu_cache_level *caches;
+	u32 cnt, i, version;
+
+	if (readn(fd, &version, sizeof(version)) != sizeof(version))
+		return -1;
+
+	if (ph->needs_swap)
+		version = bswap_32(version);
+
+	if (version != 1)
+		return -1;
+
+	if (readn(fd, &cnt, sizeof(cnt)) != sizeof(cnt))
+		return -1;
+
+	if (ph->needs_swap)
+		cnt = bswap_32(cnt);
+
+	caches = zalloc(sizeof(*caches) * cnt);
+	if (!caches)
+		return -1;
+
+	for (i = 0; i < cnt; i++) {
+		struct cpu_cache_level c;
+
+		#define _R(v)						\
+			if (readn(fd, &c.v, sizeof(u32)) != sizeof(u32))\
+				goto out_free_caches;			\
+			if (ph->needs_swap)				\
+				c.v = bswap_32(c.v);			\
+
+		_R(level)
+		_R(line_size)
+		_R(sets)
+		_R(ways)
+		#undef _R
+
+		#define _R(v)				\
+			c.v = do_read_string(fd, ph);	\
+			if (!c.v)			\
+				goto out_free_caches;
+
+		_R(type)
+		_R(size)
+		_R(map)
+		#undef _R
+
+		caches[i] = c;
+	}
+
+	ph->env.caches = caches;
+	ph->env.caches_cnt = cnt;
+	return 0;
+out_free_caches:
+	free(caches);
+	return -1;
+}
+
 struct feature_ops {
 	int (*write)(int fd, struct perf_header *h, struct perf_evlist *evlist);
 	void (*print)(struct perf_header *h, int fd, FILE *fp);
@@ -1962,6 +2226,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
 	FEAT_OPP(HEADER_GROUP_DESC,	group_desc),
 	FEAT_OPP(HEADER_AUXTRACE,	auxtrace),
 	FEAT_OPA(HEADER_STAT,		stat),
+	FEAT_OPF(HEADER_CACHE,		cache),
 };
 
 struct header_print_data {
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index cff989245..d306ca118 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -32,6 +32,7 @@ enum {
 	HEADER_GROUP_DESC,
 	HEADER_AUXTRACE,
 	HEADER_STAT,
+	HEADER_CACHE,
 	HEADER_LAST_FEATURE,
 	HEADER_FEAT_BITS	= 256,
 };
@@ -120,7 +121,7 @@ int perf_event__synthesize_event_update_cpus(struct perf_tool *tool,
 					     perf_event__handler_t process);
 int perf_event__process_attr(struct perf_tool *tool, union perf_event *event,
 			     struct perf_evlist **pevlist);
-int perf_event__process_event_update(struct perf_tool *tool __maybe_unused,
+int perf_event__process_event_update(struct perf_tool *tool,
 				     union perf_event *event,
 				     struct perf_evlist **pevlist);
 size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp);
diff --git a/tools/perf/util/help-unknown-cmd.c b/tools/perf/util/help-unknown-cmd.c
index dc1e41c9b..43a98a4dc 100644
--- a/tools/perf/util/help-unknown-cmd.c
+++ b/tools/perf/util/help-unknown-cmd.c
@@ -6,7 +6,8 @@
 static int autocorrect;
 static struct cmdnames aliases;
 
-static int perf_unknown_cmd_config(const char *var, const char *value, void *cb)
+static int perf_unknown_cmd_config(const char *var, const char *value,
+				   void *cb __maybe_unused)
 {
 	if (!strcmp(var, "help.autocorrect"))
 		autocorrect = perf_config_int(var,value);
@@ -14,7 +15,7 @@ static int perf_unknown_cmd_config(const char *var, const char *value, void *cb)
 	if (!prefixcmp(var, "alias."))
 		add_cmdname(&aliases, var + 6, strlen(var + 6));
 
-	return perf_default_config(var, value, cb);
+	return 0;
 }
 
 static int levenshtein_compare(const void *p1, const void *p2)
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 68a761201..31c4641fe 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -179,6 +179,9 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 	if (h->transaction)
 		hists__new_col_len(hists, HISTC_TRANSACTION,
 				   hist_entry__transaction_len());
+
+	if (h->trace_output)
+		hists__new_col_len(hists, HISTC_TRACE, strlen(h->trace_output));
 }
 
 void hists__output_recalc_col_len(struct hists *hists, int max_rows)
@@ -245,6 +248,8 @@ static void he_stat__decay(struct he_stat *he_stat)
 	/* XXX need decay for weight too? */
 }
 
+static void hists__delete_entry(struct hists *hists, struct hist_entry *he);
+
 static bool hists__decay_entry(struct hists *hists, struct hist_entry *he)
 {
 	u64 prev_period = he->stat.period;
@@ -260,21 +265,45 @@ static bool hists__decay_entry(struct hists *hists, struct hist_entry *he)
 
 	diff = prev_period - he->stat.period;
 
-	hists->stats.total_period -= diff;
-	if (!he->filtered)
-		hists->stats.total_non_filtered_period -= diff;
+	if (!he->depth) {
+		hists->stats.total_period -= diff;
+		if (!he->filtered)
+			hists->stats.total_non_filtered_period -= diff;
+	}
+
+	if (!he->leaf) {
+		struct hist_entry *child;
+		struct rb_node *node = rb_first(&he->hroot_out);
+		while (node) {
+			child = rb_entry(node, struct hist_entry, rb_node);
+			node = rb_next(node);
+
+			if (hists__decay_entry(hists, child))
+				hists__delete_entry(hists, child);
+		}
+	}
 
 	return he->stat.period == 0;
 }
 
 static void hists__delete_entry(struct hists *hists, struct hist_entry *he)
 {
-	rb_erase(&he->rb_node, &hists->entries);
+	struct rb_root *root_in;
+	struct rb_root *root_out;
 
-	if (sort__need_collapse)
-		rb_erase(&he->rb_node_in, &hists->entries_collapsed);
-	else
-		rb_erase(&he->rb_node_in, hists->entries_in);
+	if (he->parent_he) {
+		root_in  = &he->parent_he->hroot_in;
+		root_out = &he->parent_he->hroot_out;
+	} else {
+		if (sort__need_collapse)
+			root_in = &hists->entries_collapsed;
+		else
+			root_in = hists->entries_in;
+		root_out = &hists->entries;
+	}
+
+	rb_erase(&he->rb_node_in, root_in);
+	rb_erase(&he->rb_node, root_out);
 
 	--hists->nr_entries;
 	if (!he->filtered)
@@ -393,6 +422,9 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template,
 		}
 		INIT_LIST_HEAD(&he->pairs.node);
 		thread__get(he->thread);
+
+		if (!symbol_conf.report_hierarchy)
+			he->leaf = true;
 	}
 
 	return he;
@@ -405,6 +437,16 @@ static u8 symbol__parent_filter(const struct symbol *parent)
 	return 0;
 }
 
+static void hist_entry__add_callchain_period(struct hist_entry *he, u64 period)
+{
+	if (!symbol_conf.use_callchain)
+		return;
+
+	he->hists->callchain_period += period;
+	if (!he->filtered)
+		he->hists->callchain_non_filtered_period += period;
+}
+
 static struct hist_entry *hists__findnew_entry(struct hists *hists,
 					       struct hist_entry *entry,
 					       struct addr_location *al,
@@ -432,8 +474,10 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists,
 		cmp = hist_entry__cmp(he, entry);
 
 		if (!cmp) {
-			if (sample_self)
+			if (sample_self) {
 				he_stat__add_period(&he->stat, period, weight);
+				hist_entry__add_callchain_period(he, period);
+			}
 			if (symbol_conf.cumulate_callchain)
 				he_stat__add_period(he->stat_acc, period, weight);
 
@@ -466,6 +510,8 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists,
 	if (!he)
 		return NULL;
 
+	if (sample_self)
+		hist_entry__add_callchain_period(he, period);
 	hists->nr_entries++;
 
 	rb_link_node(&he->rb_node_in, parent, p);
@@ -624,7 +670,7 @@ iter_prepare_branch_entry(struct hist_entry_iter *iter, struct addr_location *al
 }
 
 static int
-iter_add_single_branch_entry(struct hist_entry_iter *iter __maybe_unused,
+iter_add_single_branch_entry(struct hist_entry_iter *iter,
 			     struct addr_location *al __maybe_unused)
 {
 	/* to avoid calling callback function */
@@ -951,10 +997,15 @@ out:
 int64_t
 hist_entry__cmp(struct hist_entry *left, struct hist_entry *right)
 {
+	struct hists *hists = left->hists;
 	struct perf_hpp_fmt *fmt;
 	int64_t cmp = 0;
 
-	perf_hpp__for_each_sort_list(fmt) {
+	hists__for_each_sort_list(hists, fmt) {
+		if (perf_hpp__is_dynamic_entry(fmt) &&
+		    !perf_hpp__defined_dynamic_entry(fmt, hists))
+			continue;
+
 		cmp = fmt->cmp(fmt, left, right);
 		if (cmp)
 			break;
@@ -966,10 +1017,15 @@ hist_entry__cmp(struct hist_entry *left, struct hist_entry *right)
 int64_t
 hist_entry__collapse(struct hist_entry *left, struct hist_entry *right)
 {
+	struct hists *hists = left->hists;
 	struct perf_hpp_fmt *fmt;
 	int64_t cmp = 0;
 
-	perf_hpp__for_each_sort_list(fmt) {
+	hists__for_each_sort_list(hists, fmt) {
+		if (perf_hpp__is_dynamic_entry(fmt) &&
+		    !perf_hpp__defined_dynamic_entry(fmt, hists))
+			continue;
+
 		cmp = fmt->collapse(fmt, left, right);
 		if (cmp)
 			break;
@@ -1006,17 +1062,250 @@ void hist_entry__delete(struct hist_entry *he)
 }
 
 /*
+ * If this is not the last column, then we need to pad it according to the
+ * pre-calculated max lenght for this column, otherwise don't bother adding
+ * spaces because that would break viewing this with, for instance, 'less',
+ * that would show tons of trailing spaces when a long C++ demangled method
+ * names is sampled.
+*/
+int hist_entry__snprintf_alignment(struct hist_entry *he, struct perf_hpp *hpp,
+				   struct perf_hpp_fmt *fmt, int printed)
+{
+	if (!list_is_last(&fmt->list, &he->hists->hpp_list->fields)) {
+		const int width = fmt->width(fmt, hpp, hists_to_evsel(he->hists));
+		if (printed < width) {
+			advance_hpp(hpp, printed);
+			printed = scnprintf(hpp->buf, hpp->size, "%-*s", width - printed, " ");
+		}
+	}
+
+	return printed;
+}
+
+/*
  * collapse the histogram
  */
 
-bool hists__collapse_insert_entry(struct hists *hists __maybe_unused,
-				  struct rb_root *root, struct hist_entry *he)
+static void hists__apply_filters(struct hists *hists, struct hist_entry *he);
+static void hists__remove_entry_filter(struct hists *hists, struct hist_entry *he,
+				       enum hist_filter type);
+
+typedef bool (*fmt_chk_fn)(struct perf_hpp_fmt *fmt);
+
+static bool check_thread_entry(struct perf_hpp_fmt *fmt)
+{
+	return perf_hpp__is_thread_entry(fmt) || perf_hpp__is_comm_entry(fmt);
+}
+
+static void hist_entry__check_and_remove_filter(struct hist_entry *he,
+						enum hist_filter type,
+						fmt_chk_fn check)
+{
+	struct perf_hpp_fmt *fmt;
+	bool type_match = false;
+	struct hist_entry *parent = he->parent_he;
+
+	switch (type) {
+	case HIST_FILTER__THREAD:
+		if (symbol_conf.comm_list == NULL &&
+		    symbol_conf.pid_list == NULL &&
+		    symbol_conf.tid_list == NULL)
+			return;
+		break;
+	case HIST_FILTER__DSO:
+		if (symbol_conf.dso_list == NULL)
+			return;
+		break;
+	case HIST_FILTER__SYMBOL:
+		if (symbol_conf.sym_list == NULL)
+			return;
+		break;
+	case HIST_FILTER__PARENT:
+	case HIST_FILTER__GUEST:
+	case HIST_FILTER__HOST:
+	case HIST_FILTER__SOCKET:
+	default:
+		return;
+	}
+
+	/* if it's filtered by own fmt, it has to have filter bits */
+	perf_hpp_list__for_each_format(he->hpp_list, fmt) {
+		if (check(fmt)) {
+			type_match = true;
+			break;
+		}
+	}
+
+	if (type_match) {
+		/*
+		 * If the filter is for current level entry, propagate
+		 * filter marker to parents.  The marker bit was
+		 * already set by default so it only needs to clear
+		 * non-filtered entries.
+		 */
+		if (!(he->filtered & (1 << type))) {
+			while (parent) {
+				parent->filtered &= ~(1 << type);
+				parent = parent->parent_he;
+			}
+		}
+	} else {
+		/*
+		 * If current entry doesn't have matching formats, set
+		 * filter marker for upper level entries.  it will be
+		 * cleared if its lower level entries is not filtered.
+		 *
+		 * For lower-level entries, it inherits parent's
+		 * filter bit so that lower level entries of a
+		 * non-filtered entry won't set the filter marker.
+		 */
+		if (parent == NULL)
+			he->filtered |= (1 << type);
+		else
+			he->filtered |= (parent->filtered & (1 << type));
+	}
+}
+
+static void hist_entry__apply_hierarchy_filters(struct hist_entry *he)
+{
+	hist_entry__check_and_remove_filter(he, HIST_FILTER__THREAD,
+					    check_thread_entry);
+
+	hist_entry__check_and_remove_filter(he, HIST_FILTER__DSO,
+					    perf_hpp__is_dso_entry);
+
+	hist_entry__check_and_remove_filter(he, HIST_FILTER__SYMBOL,
+					    perf_hpp__is_sym_entry);
+
+	hists__apply_filters(he->hists, he);
+}
+
+static struct hist_entry *hierarchy_insert_entry(struct hists *hists,
+						 struct rb_root *root,
+						 struct hist_entry *he,
+						 struct hist_entry *parent_he,
+						 struct perf_hpp_list *hpp_list)
+{
+	struct rb_node **p = &root->rb_node;
+	struct rb_node *parent = NULL;
+	struct hist_entry *iter, *new;
+	struct perf_hpp_fmt *fmt;
+	int64_t cmp;
+
+	while (*p != NULL) {
+		parent = *p;
+		iter = rb_entry(parent, struct hist_entry, rb_node_in);
+
+		cmp = 0;
+		perf_hpp_list__for_each_sort_list(hpp_list, fmt) {
+			cmp = fmt->collapse(fmt, iter, he);
+			if (cmp)
+				break;
+		}
+
+		if (!cmp) {
+			he_stat__add_stat(&iter->stat, &he->stat);
+			return iter;
+		}
+
+		if (cmp < 0)
+			p = &parent->rb_left;
+		else
+			p = &parent->rb_right;
+	}
+
+	new = hist_entry__new(he, true);
+	if (new == NULL)
+		return NULL;
+
+	hists->nr_entries++;
+
+	/* save related format list for output */
+	new->hpp_list = hpp_list;
+	new->parent_he = parent_he;
+
+	hist_entry__apply_hierarchy_filters(new);
+
+	/* some fields are now passed to 'new' */
+	perf_hpp_list__for_each_sort_list(hpp_list, fmt) {
+		if (perf_hpp__is_trace_entry(fmt) || perf_hpp__is_dynamic_entry(fmt))
+			he->trace_output = NULL;
+		else
+			new->trace_output = NULL;
+
+		if (perf_hpp__is_srcline_entry(fmt))
+			he->srcline = NULL;
+		else
+			new->srcline = NULL;
+
+		if (perf_hpp__is_srcfile_entry(fmt))
+			he->srcfile = NULL;
+		else
+			new->srcfile = NULL;
+	}
+
+	rb_link_node(&new->rb_node_in, parent, p);
+	rb_insert_color(&new->rb_node_in, root);
+	return new;
+}
+
+static int hists__hierarchy_insert_entry(struct hists *hists,
+					 struct rb_root *root,
+					 struct hist_entry *he)
+{
+	struct perf_hpp_list_node *node;
+	struct hist_entry *new_he = NULL;
+	struct hist_entry *parent = NULL;
+	int depth = 0;
+	int ret = 0;
+
+	list_for_each_entry(node, &hists->hpp_formats, list) {
+		/* skip period (overhead) and elided columns */
+		if (node->level == 0 || node->skip)
+			continue;
+
+		/* insert copy of 'he' for each fmt into the hierarchy */
+		new_he = hierarchy_insert_entry(hists, root, he, parent, &node->hpp);
+		if (new_he == NULL) {
+			ret = -1;
+			break;
+		}
+
+		root = &new_he->hroot_in;
+		new_he->depth = depth++;
+		parent = new_he;
+	}
+
+	if (new_he) {
+		new_he->leaf = true;
+
+		if (symbol_conf.use_callchain) {
+			callchain_cursor_reset(&callchain_cursor);
+			if (callchain_merge(&callchain_cursor,
+					    new_he->callchain,
+					    he->callchain) < 0)
+				ret = -1;
+		}
+	}
+
+	/* 'he' is no longer used */
+	hist_entry__delete(he);
+
+	/* return 0 (or -1) since it already applied filters */
+	return ret;
+}
+
+int hists__collapse_insert_entry(struct hists *hists, struct rb_root *root,
+				 struct hist_entry *he)
 {
 	struct rb_node **p = &root->rb_node;
 	struct rb_node *parent = NULL;
 	struct hist_entry *iter;
 	int64_t cmp;
 
+	if (symbol_conf.report_hierarchy)
+		return hists__hierarchy_insert_entry(hists, root, he);
+
 	while (*p != NULL) {
 		parent = *p;
 		iter = rb_entry(parent, struct hist_entry, rb_node_in);
@@ -1024,18 +1313,21 @@ bool hists__collapse_insert_entry(struct hists *hists __maybe_unused,
 		cmp = hist_entry__collapse(iter, he);
 
 		if (!cmp) {
+			int ret = 0;
+
 			he_stat__add_stat(&iter->stat, &he->stat);
 			if (symbol_conf.cumulate_callchain)
 				he_stat__add_stat(iter->stat_acc, he->stat_acc);
 
 			if (symbol_conf.use_callchain) {
 				callchain_cursor_reset(&callchain_cursor);
-				callchain_merge(&callchain_cursor,
-						iter->callchain,
-						he->callchain);
+				if (callchain_merge(&callchain_cursor,
+						    iter->callchain,
+						    he->callchain) < 0)
+					ret = -1;
 			}
 			hist_entry__delete(he);
-			return false;
+			return ret;
 		}
 
 		if (cmp < 0)
@@ -1047,7 +1339,7 @@ bool hists__collapse_insert_entry(struct hists *hists __maybe_unused,
 
 	rb_link_node(&he->rb_node_in, parent, p);
 	rb_insert_color(&he->rb_node_in, root);
-	return true;
+	return 1;
 }
 
 struct rb_root *hists__get_rotate_entries_in(struct hists *hists)
@@ -1073,14 +1365,15 @@ static void hists__apply_filters(struct hists *hists, struct hist_entry *he)
 	hists__filter_entry_by_socket(hists, he);
 }
 
-void hists__collapse_resort(struct hists *hists, struct ui_progress *prog)
+int hists__collapse_resort(struct hists *hists, struct ui_progress *prog)
 {
 	struct rb_root *root;
 	struct rb_node *next;
 	struct hist_entry *n;
+	int ret;
 
 	if (!sort__need_collapse)
-		return;
+		return 0;
 
 	hists->nr_entries = 0;
 
@@ -1095,7 +1388,11 @@ void hists__collapse_resort(struct hists *hists, struct ui_progress *prog)
 		next = rb_next(&n->rb_node_in);
 
 		rb_erase(&n->rb_node_in, root);
-		if (hists__collapse_insert_entry(hists, &hists->entries_collapsed, n)) {
+		ret = hists__collapse_insert_entry(hists, &hists->entries_collapsed, n);
+		if (ret < 0)
+			return -1;
+
+		if (ret) {
 			/*
 			 * If it wasn't combined with one of the entries already
 			 * collapsed, we need to apply the filters that may have
@@ -1106,14 +1403,16 @@ void hists__collapse_resort(struct hists *hists, struct ui_progress *prog)
 		if (prog)
 			ui_progress__update(prog, 1);
 	}
+	return 0;
 }
 
 static int hist_entry__sort(struct hist_entry *a, struct hist_entry *b)
 {
+	struct hists *hists = a->hists;
 	struct perf_hpp_fmt *fmt;
 	int64_t cmp = 0;
 
-	perf_hpp__for_each_sort_list(fmt) {
+	hists__for_each_sort_list(hists, fmt) {
 		if (perf_hpp__should_skip(fmt, a->hists))
 			continue;
 
@@ -1154,6 +1453,113 @@ void hists__inc_stats(struct hists *hists, struct hist_entry *h)
 	hists->stats.total_period += h->stat.period;
 }
 
+static void hierarchy_recalc_total_periods(struct hists *hists)
+{
+	struct rb_node *node;
+	struct hist_entry *he;
+
+	node = rb_first(&hists->entries);
+
+	hists->stats.total_period = 0;
+	hists->stats.total_non_filtered_period = 0;
+
+	/*
+	 * recalculate total period using top-level entries only
+	 * since lower level entries only see non-filtered entries
+	 * but upper level entries have sum of both entries.
+	 */
+	while (node) {
+		he = rb_entry(node, struct hist_entry, rb_node);
+		node = rb_next(node);
+
+		hists->stats.total_period += he->stat.period;
+		if (!he->filtered)
+			hists->stats.total_non_filtered_period += he->stat.period;
+	}
+}
+
+static void hierarchy_insert_output_entry(struct rb_root *root,
+					  struct hist_entry *he)
+{
+	struct rb_node **p = &root->rb_node;
+	struct rb_node *parent = NULL;
+	struct hist_entry *iter;
+	struct perf_hpp_fmt *fmt;
+
+	while (*p != NULL) {
+		parent = *p;
+		iter = rb_entry(parent, struct hist_entry, rb_node);
+
+		if (hist_entry__sort(he, iter) > 0)
+			p = &parent->rb_left;
+		else
+			p = &parent->rb_right;
+	}
+
+	rb_link_node(&he->rb_node, parent, p);
+	rb_insert_color(&he->rb_node, root);
+
+	/* update column width of dynamic entry */
+	perf_hpp_list__for_each_sort_list(he->hpp_list, fmt) {
+		if (perf_hpp__is_dynamic_entry(fmt))
+			fmt->sort(fmt, he, NULL);
+	}
+}
+
+static void hists__hierarchy_output_resort(struct hists *hists,
+					   struct ui_progress *prog,
+					   struct rb_root *root_in,
+					   struct rb_root *root_out,
+					   u64 min_callchain_hits,
+					   bool use_callchain)
+{
+	struct rb_node *node;
+	struct hist_entry *he;
+
+	*root_out = RB_ROOT;
+	node = rb_first(root_in);
+
+	while (node) {
+		he = rb_entry(node, struct hist_entry, rb_node_in);
+		node = rb_next(node);
+
+		hierarchy_insert_output_entry(root_out, he);
+
+		if (prog)
+			ui_progress__update(prog, 1);
+
+		if (!he->leaf) {
+			hists__hierarchy_output_resort(hists, prog,
+						       &he->hroot_in,
+						       &he->hroot_out,
+						       min_callchain_hits,
+						       use_callchain);
+			hists->nr_entries++;
+			if (!he->filtered) {
+				hists->nr_non_filtered_entries++;
+				hists__calc_col_len(hists, he);
+			}
+
+			continue;
+		}
+
+		if (!use_callchain)
+			continue;
+
+		if (callchain_param.mode == CHAIN_GRAPH_REL) {
+			u64 total = he->stat.period;
+
+			if (symbol_conf.cumulate_callchain)
+				total = he->stat_acc->period;
+
+			min_callchain_hits = total * (callchain_param.min_percent / 100);
+		}
+
+		callchain_param.sort(&he->sorted_chain, he->callchain,
+				     min_callchain_hits, &callchain_param);
+	}
+}
+
 static void __hists__insert_output_entry(struct rb_root *entries,
 					 struct hist_entry *he,
 					 u64 min_callchain_hits,
@@ -1162,10 +1568,20 @@ static void __hists__insert_output_entry(struct rb_root *entries,
 	struct rb_node **p = &entries->rb_node;
 	struct rb_node *parent = NULL;
 	struct hist_entry *iter;
+	struct perf_hpp_fmt *fmt;
+
+	if (use_callchain) {
+		if (callchain_param.mode == CHAIN_GRAPH_REL) {
+			u64 total = he->stat.period;
+
+			if (symbol_conf.cumulate_callchain)
+				total = he->stat_acc->period;
 
-	if (use_callchain)
+			min_callchain_hits = total * (callchain_param.min_percent / 100);
+		}
 		callchain_param.sort(&he->sorted_chain, he->callchain,
 				      min_callchain_hits, &callchain_param);
+	}
 
 	while (*p != NULL) {
 		parent = *p;
@@ -1179,23 +1595,41 @@ static void __hists__insert_output_entry(struct rb_root *entries,
 
 	rb_link_node(&he->rb_node, parent, p);
 	rb_insert_color(&he->rb_node, entries);
+
+	perf_hpp_list__for_each_sort_list(&perf_hpp_list, fmt) {
+		if (perf_hpp__is_dynamic_entry(fmt) &&
+		    perf_hpp__defined_dynamic_entry(fmt, he->hists))
+			fmt->sort(fmt, he, NULL);  /* update column width */
+	}
 }
 
-void hists__output_resort(struct hists *hists, struct ui_progress *prog)
+static void output_resort(struct hists *hists, struct ui_progress *prog,
+			  bool use_callchain)
 {
 	struct rb_root *root;
 	struct rb_node *next;
 	struct hist_entry *n;
+	u64 callchain_total;
 	u64 min_callchain_hits;
-	struct perf_evsel *evsel = hists_to_evsel(hists);
-	bool use_callchain;
 
-	if (evsel && symbol_conf.use_callchain && !symbol_conf.show_ref_callgraph)
-		use_callchain = evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN;
-	else
-		use_callchain = symbol_conf.use_callchain;
+	callchain_total = hists->callchain_period;
+	if (symbol_conf.filter_relative)
+		callchain_total = hists->callchain_non_filtered_period;
 
-	min_callchain_hits = hists->stats.total_period * (callchain_param.min_percent / 100);
+	min_callchain_hits = callchain_total * (callchain_param.min_percent / 100);
+
+	hists__reset_stats(hists);
+	hists__reset_col_len(hists);
+
+	if (symbol_conf.report_hierarchy) {
+		hists__hierarchy_output_resort(hists, prog,
+					       &hists->entries_collapsed,
+					       &hists->entries,
+					       min_callchain_hits,
+					       use_callchain);
+		hierarchy_recalc_total_periods(hists);
+		return;
+	}
 
 	if (sort__need_collapse)
 		root = &hists->entries_collapsed;
@@ -1205,9 +1639,6 @@ void hists__output_resort(struct hists *hists, struct ui_progress *prog)
 	next = rb_first(root);
 	hists->entries = RB_ROOT;
 
-	hists__reset_stats(hists);
-	hists__reset_col_len(hists);
-
 	while (next) {
 		n = rb_entry(next, struct hist_entry, rb_node_in);
 		next = rb_next(&n->rb_node_in);
@@ -1223,15 +1654,136 @@ void hists__output_resort(struct hists *hists, struct ui_progress *prog)
 	}
 }
 
+void perf_evsel__output_resort(struct perf_evsel *evsel, struct ui_progress *prog)
+{
+	bool use_callchain;
+
+	if (evsel && symbol_conf.use_callchain && !symbol_conf.show_ref_callgraph)
+		use_callchain = evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN;
+	else
+		use_callchain = symbol_conf.use_callchain;
+
+	output_resort(evsel__hists(evsel), prog, use_callchain);
+}
+
+void hists__output_resort(struct hists *hists, struct ui_progress *prog)
+{
+	output_resort(hists, prog, symbol_conf.use_callchain);
+}
+
+static bool can_goto_child(struct hist_entry *he, enum hierarchy_move_dir hmd)
+{
+	if (he->leaf || hmd == HMD_FORCE_SIBLING)
+		return false;
+
+	if (he->unfolded || hmd == HMD_FORCE_CHILD)
+		return true;
+
+	return false;
+}
+
+struct rb_node *rb_hierarchy_last(struct rb_node *node)
+{
+	struct hist_entry *he = rb_entry(node, struct hist_entry, rb_node);
+
+	while (can_goto_child(he, HMD_NORMAL)) {
+		node = rb_last(&he->hroot_out);
+		he = rb_entry(node, struct hist_entry, rb_node);
+	}
+	return node;
+}
+
+struct rb_node *__rb_hierarchy_next(struct rb_node *node, enum hierarchy_move_dir hmd)
+{
+	struct hist_entry *he = rb_entry(node, struct hist_entry, rb_node);
+
+	if (can_goto_child(he, hmd))
+		node = rb_first(&he->hroot_out);
+	else
+		node = rb_next(node);
+
+	while (node == NULL) {
+		he = he->parent_he;
+		if (he == NULL)
+			break;
+
+		node = rb_next(&he->rb_node);
+	}
+	return node;
+}
+
+struct rb_node *rb_hierarchy_prev(struct rb_node *node)
+{
+	struct hist_entry *he = rb_entry(node, struct hist_entry, rb_node);
+
+	node = rb_prev(node);
+	if (node)
+		return rb_hierarchy_last(node);
+
+	he = he->parent_he;
+	if (he == NULL)
+		return NULL;
+
+	return &he->rb_node;
+}
+
+bool hist_entry__has_hierarchy_children(struct hist_entry *he, float limit)
+{
+	struct rb_node *node;
+	struct hist_entry *child;
+	float percent;
+
+	if (he->leaf)
+		return false;
+
+	node = rb_first(&he->hroot_out);
+	child = rb_entry(node, struct hist_entry, rb_node);
+
+	while (node && child->filtered) {
+		node = rb_next(node);
+		child = rb_entry(node, struct hist_entry, rb_node);
+	}
+
+	if (node)
+		percent = hist_entry__get_percent_limit(child);
+	else
+		percent = 0;
+
+	return node && percent >= limit;
+}
+
 static void hists__remove_entry_filter(struct hists *hists, struct hist_entry *h,
 				       enum hist_filter filter)
 {
 	h->filtered &= ~(1 << filter);
+
+	if (symbol_conf.report_hierarchy) {
+		struct hist_entry *parent = h->parent_he;
+
+		while (parent) {
+			he_stat__add_stat(&parent->stat, &h->stat);
+
+			parent->filtered &= ~(1 << filter);
+
+			if (parent->filtered)
+				goto next;
+
+			/* force fold unfiltered entry for simplicity */
+			parent->unfolded = false;
+			parent->has_no_entry = false;
+			parent->row_offset = 0;
+			parent->nr_rows = 0;
+next:
+			parent = parent->parent_he;
+		}
+	}
+
 	if (h->filtered)
 		return;
 
 	/* force fold unfiltered entry for simplicity */
 	h->unfolded = false;
+	h->has_no_entry = false;
 	h->row_offset = 0;
 	h->nr_rows = 0;
 
@@ -1254,28 +1806,6 @@ static bool hists__filter_entry_by_dso(struct hists *hists,
 	return false;
 }
 
-void hists__filter_by_dso(struct hists *hists)
-{
-	struct rb_node *nd;
-
-	hists->stats.nr_non_filtered_samples = 0;
-
-	hists__reset_filter_stats(hists);
-	hists__reset_col_len(hists);
-
-	for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
-		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
-
-		if (symbol_conf.exclude_other && !h->parent)
-			continue;
-
-		if (hists__filter_entry_by_dso(hists, h))
-			continue;
-
-		hists__remove_entry_filter(hists, h, HIST_FILTER__DSO);
-	}
-}
-
 static bool hists__filter_entry_by_thread(struct hists *hists,
 					  struct hist_entry *he)
 {
@@ -1288,25 +1818,6 @@ static bool hists__filter_entry_by_thread(struct hists *hists,
 	return false;
 }
 
-void hists__filter_by_thread(struct hists *hists)
-{
-	struct rb_node *nd;
-
-	hists->stats.nr_non_filtered_samples = 0;
-
-	hists__reset_filter_stats(hists);
-	hists__reset_col_len(hists);
-
-	for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
-		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
-
-		if (hists__filter_entry_by_thread(hists, h))
-			continue;
-
-		hists__remove_entry_filter(hists, h, HIST_FILTER__THREAD);
-	}
-}
-
 static bool hists__filter_entry_by_symbol(struct hists *hists,
 					  struct hist_entry *he)
 {
@@ -1320,7 +1831,21 @@ static bool hists__filter_entry_by_symbol(struct hists *hists,
 	return false;
 }
 
-void hists__filter_by_symbol(struct hists *hists)
+static bool hists__filter_entry_by_socket(struct hists *hists,
+					  struct hist_entry *he)
+{
+	if ((hists->socket_filter > -1) &&
+	    (he->socket != hists->socket_filter)) {
+		he->filtered |= (1 << HIST_FILTER__SOCKET);
+		return true;
+	}
+
+	return false;
+}
+
+typedef bool (*filter_fn_t)(struct hists *hists, struct hist_entry *he);
+
+static void hists__filter_by_type(struct hists *hists, int type, filter_fn_t filter)
 {
 	struct rb_node *nd;
 
@@ -1332,42 +1857,155 @@ void hists__filter_by_symbol(struct hists *hists)
 	for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
 
-		if (hists__filter_entry_by_symbol(hists, h))
+		if (filter(hists, h))
 			continue;
 
-		hists__remove_entry_filter(hists, h, HIST_FILTER__SYMBOL);
+		hists__remove_entry_filter(hists, h, type);
 	}
 }
 
-static bool hists__filter_entry_by_socket(struct hists *hists,
-					  struct hist_entry *he)
+static void resort_filtered_entry(struct rb_root *root, struct hist_entry *he)
 {
-	if ((hists->socket_filter > -1) &&
-	    (he->socket != hists->socket_filter)) {
-		he->filtered |= (1 << HIST_FILTER__SOCKET);
-		return true;
+	struct rb_node **p = &root->rb_node;
+	struct rb_node *parent = NULL;
+	struct hist_entry *iter;
+	struct rb_root new_root = RB_ROOT;
+	struct rb_node *nd;
+
+	while (*p != NULL) {
+		parent = *p;
+		iter = rb_entry(parent, struct hist_entry, rb_node);
+
+		if (hist_entry__sort(he, iter) > 0)
+			p = &(*p)->rb_left;
+		else
+			p = &(*p)->rb_right;
 	}
 
-	return false;
+	rb_link_node(&he->rb_node, parent, p);
+	rb_insert_color(&he->rb_node, root);
+
+	if (he->leaf || he->filtered)
+		return;
+
+	nd = rb_first(&he->hroot_out);
+	while (nd) {
+		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
+
+		nd = rb_next(nd);
+		rb_erase(&h->rb_node, &he->hroot_out);
+
+		resort_filtered_entry(&new_root, h);
+	}
+
+	he->hroot_out = new_root;
 }
 
-void hists__filter_by_socket(struct hists *hists)
+static void hists__filter_hierarchy(struct hists *hists, int type, const void *arg)
 {
 	struct rb_node *nd;
+	struct rb_root new_root = RB_ROOT;
 
 	hists->stats.nr_non_filtered_samples = 0;
 
 	hists__reset_filter_stats(hists);
 	hists__reset_col_len(hists);
 
-	for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
+	nd = rb_first(&hists->entries);
+	while (nd) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
+		int ret;
 
-		if (hists__filter_entry_by_socket(hists, h))
-			continue;
+		ret = hist_entry__filter(h, type, arg);
 
-		hists__remove_entry_filter(hists, h, HIST_FILTER__SOCKET);
+		/*
+		 * case 1. non-matching type
+		 * zero out the period, set filter marker and move to child
+		 */
+		if (ret < 0) {
+			memset(&h->stat, 0, sizeof(h->stat));
+			h->filtered |= (1 << type);
+
+			nd = __rb_hierarchy_next(&h->rb_node, HMD_FORCE_CHILD);
+		}
+		/*
+		 * case 2. matched type (filter out)
+		 * set filter marker and move to next
+		 */
+		else if (ret == 1) {
+			h->filtered |= (1 << type);
+
+			nd = __rb_hierarchy_next(&h->rb_node, HMD_FORCE_SIBLING);
+		}
+		/*
+		 * case 3. ok (not filtered)
+		 * add period to hists and parents, erase the filter marker
+		 * and move to next sibling
+		 */
+		else {
+			hists__remove_entry_filter(hists, h, type);
+
+			nd = __rb_hierarchy_next(&h->rb_node, HMD_FORCE_SIBLING);
+		}
+	}
+
+	hierarchy_recalc_total_periods(hists);
+
+	/*
+	 * resort output after applying a new filter since filter in a lower
+	 * hierarchy can change periods in a upper hierarchy.
+	 */
+	nd = rb_first(&hists->entries);
+	while (nd) {
+		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
+
+		nd = rb_next(nd);
+		rb_erase(&h->rb_node, &hists->entries);
+
+		resort_filtered_entry(&new_root, h);
 	}
+
+	hists->entries = new_root;
+}
+
+void hists__filter_by_thread(struct hists *hists)
+{
+	if (symbol_conf.report_hierarchy)
+		hists__filter_hierarchy(hists, HIST_FILTER__THREAD,
+					hists->thread_filter);
+	else
+		hists__filter_by_type(hists, HIST_FILTER__THREAD,
+				      hists__filter_entry_by_thread);
+}
+
+void hists__filter_by_dso(struct hists *hists)
+{
+	if (symbol_conf.report_hierarchy)
+		hists__filter_hierarchy(hists, HIST_FILTER__DSO,
+					hists->dso_filter);
+	else
+		hists__filter_by_type(hists, HIST_FILTER__DSO,
+				      hists__filter_entry_by_dso);
+}
+
+void hists__filter_by_symbol(struct hists *hists)
+{
+	if (symbol_conf.report_hierarchy)
+		hists__filter_hierarchy(hists, HIST_FILTER__SYMBOL,
+					hists->symbol_filter_str);
+	else
+		hists__filter_by_type(hists, HIST_FILTER__SYMBOL,
+				      hists__filter_entry_by_symbol);
+}
+
+void hists__filter_by_socket(struct hists *hists)
+{
+	if (symbol_conf.report_hierarchy)
+		hists__filter_hierarchy(hists, HIST_FILTER__SOCKET,
+					&hists->socket_filter);
+	else
+		hists__filter_by_type(hists, HIST_FILTER__SOCKET,
+				      hists__filter_entry_by_socket);
 }
 
 void events_stats__inc(struct events_stats *stats, u32 type)
@@ -1585,7 +2223,7 @@ int perf_hist_config(const char *var, const char *value)
 	return 0;
 }
 
-int __hists__init(struct hists *hists)
+int __hists__init(struct hists *hists, struct perf_hpp_list *hpp_list)
 {
 	memset(hists, 0, sizeof(*hists));
 	hists->entries_in_array[0] = hists->entries_in_array[1] = RB_ROOT;
@@ -1594,6 +2232,8 @@ int __hists__init(struct hists *hists)
 	hists->entries = RB_ROOT;
 	pthread_mutex_init(&hists->lock, NULL);
 	hists->socket_filter = -1;
+	hists->hpp_list = hpp_list;
+	INIT_LIST_HEAD(&hists->hpp_formats);
 	return 0;
 }
 
@@ -1622,15 +2262,26 @@ static void hists__delete_all_entries(struct hists *hists)
 static void hists_evsel__exit(struct perf_evsel *evsel)
 {
 	struct hists *hists = evsel__hists(evsel);
+	struct perf_hpp_fmt *fmt, *pos;
+	struct perf_hpp_list_node *node, *tmp;
 
 	hists__delete_all_entries(hists);
+
+	list_for_each_entry_safe(node, tmp, &hists->hpp_formats, list) {
+		perf_hpp_list__for_each_format_safe(&node->hpp, fmt, pos) {
+			list_del(&fmt->list);
+			free(fmt);
+		}
+		list_del(&node->list);
+		free(node);
+	}
 }
 
 static int hists_evsel__init(struct perf_evsel *evsel)
 {
 	struct hists *hists = evsel__hists(evsel);
 
-	__hists__init(hists);
+	__hists__init(hists, &perf_hpp_list);
 	return 0;
 }
 
@@ -1649,3 +2300,9 @@ int hists__init(void)
 
 	return err;
 }
+
+void perf_hpp_list__init(struct perf_hpp_list *list)
+{
+	INIT_LIST_HEAD(&list->fields);
+	INIT_LIST_HEAD(&list->sorts);
+}
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index d4ec4822a..bec0cd660 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -66,6 +66,8 @@ struct hists {
 	struct rb_root		entries_collapsed;
 	u64			nr_entries;
 	u64			nr_non_filtered_entries;
+	u64			callchain_period;
+	u64			callchain_non_filtered_period;
 	struct thread		*thread_filter;
 	const struct dso	*dso_filter;
 	const char		*uid_filter_str;
@@ -75,6 +77,9 @@ struct hists {
 	u64			event_stream;
 	u16			col_len[HISTC_NR_COLS];
 	int			socket_filter;
+	struct perf_hpp_list	*hpp_list;
+	struct list_head	hpp_formats;
+	int			nr_hpp_node;
 };
 
 struct hist_entry_iter;
@@ -121,15 +126,21 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
 int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
 			 int max_stack_depth, void *arg);
 
+struct perf_hpp;
+struct perf_hpp_fmt;
+
 int64_t hist_entry__cmp(struct hist_entry *left, struct hist_entry *right);
 int64_t hist_entry__collapse(struct hist_entry *left, struct hist_entry *right);
 int hist_entry__transaction_len(void);
 int hist_entry__sort_snprintf(struct hist_entry *he, char *bf, size_t size,
 			      struct hists *hists);
+int hist_entry__snprintf_alignment(struct hist_entry *he, struct perf_hpp *hpp,
+				   struct perf_hpp_fmt *fmt, int printed);
 void hist_entry__delete(struct hist_entry *he);
 
+void perf_evsel__output_resort(struct perf_evsel *evsel, struct ui_progress *prog);
 void hists__output_resort(struct hists *hists, struct ui_progress *prog);
-void hists__collapse_resort(struct hists *hists, struct ui_progress *prog);
+int hists__collapse_resort(struct hists *hists, struct ui_progress *prog);
 
 void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel);
 void hists__delete_entries(struct hists *hists);
@@ -185,10 +196,10 @@ static inline struct hists *evsel__hists(struct perf_evsel *evsel)
 }
 
 int hists__init(void);
-int __hists__init(struct hists *hists);
+int __hists__init(struct hists *hists, struct perf_hpp_list *hpp_list);
 
 struct rb_root *hists__get_rotate_entries_in(struct hists *hists);
-bool hists__collapse_insert_entry(struct hists *hists __maybe_unused,
+int hists__collapse_insert_entry(struct hists *hists,
 				  struct rb_root *root, struct hist_entry *he);
 
 struct perf_hpp {
@@ -214,28 +225,64 @@ struct perf_hpp_fmt {
 			    struct hist_entry *a, struct hist_entry *b);
 	int64_t (*sort)(struct perf_hpp_fmt *fmt,
 			struct hist_entry *a, struct hist_entry *b);
+	bool (*equal)(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b);
+	void (*free)(struct perf_hpp_fmt *fmt);
 
 	struct list_head list;
 	struct list_head sort_list;
 	bool elide;
 	int len;
 	int user_len;
+	int idx;
+	int level;
+};
+
+struct perf_hpp_list {
+	struct list_head fields;
+	struct list_head sorts;
 };
 
-extern struct list_head perf_hpp__list;
-extern struct list_head perf_hpp__sort_list;
+extern struct perf_hpp_list perf_hpp_list;
+
+struct perf_hpp_list_node {
+	struct list_head	list;
+	struct perf_hpp_list	hpp;
+	int			level;
+	bool			skip;
+};
+
+void perf_hpp_list__column_register(struct perf_hpp_list *list,
+				    struct perf_hpp_fmt *format);
+void perf_hpp_list__register_sort_field(struct perf_hpp_list *list,
+					struct perf_hpp_fmt *format);
+
+static inline void perf_hpp__column_register(struct perf_hpp_fmt *format)
+{
+	perf_hpp_list__column_register(&perf_hpp_list, format);
+}
+
+static inline void perf_hpp__register_sort_field(struct perf_hpp_fmt *format)
+{
+	perf_hpp_list__register_sort_field(&perf_hpp_list, format);
+}
+
+#define perf_hpp_list__for_each_format(_list, format) \
+	list_for_each_entry(format, &(_list)->fields, list)
 
-#define perf_hpp__for_each_format(format) \
-	list_for_each_entry(format, &perf_hpp__list, list)
+#define perf_hpp_list__for_each_format_safe(_list, format, tmp)	\
+	list_for_each_entry_safe(format, tmp, &(_list)->fields, list)
 
-#define perf_hpp__for_each_format_safe(format, tmp)	\
-	list_for_each_entry_safe(format, tmp, &perf_hpp__list, list)
+#define perf_hpp_list__for_each_sort_list(_list, format) \
+	list_for_each_entry(format, &(_list)->sorts, sort_list)
 
-#define perf_hpp__for_each_sort_list(format) \
-	list_for_each_entry(format, &perf_hpp__sort_list, sort_list)
+#define perf_hpp_list__for_each_sort_list_safe(_list, format, tmp)	\
+	list_for_each_entry_safe(format, tmp, &(_list)->sorts, sort_list)
 
-#define perf_hpp__for_each_sort_list_safe(format, tmp)	\
-	list_for_each_entry_safe(format, tmp, &perf_hpp__sort_list, sort_list)
+#define hists__for_each_format(hists, format) \
+	perf_hpp_list__for_each_format((hists)->hpp_list, fmt)
+
+#define hists__for_each_sort_list(hists, format) \
+	perf_hpp_list__for_each_sort_list((hists)->hpp_list, fmt)
 
 extern struct perf_hpp_fmt perf_hpp__format[];
 
@@ -254,21 +301,29 @@ enum {
 };
 
 void perf_hpp__init(void);
-void perf_hpp__column_register(struct perf_hpp_fmt *format);
 void perf_hpp__column_unregister(struct perf_hpp_fmt *format);
-void perf_hpp__column_enable(unsigned col);
-void perf_hpp__column_disable(unsigned col);
 void perf_hpp__cancel_cumulate(void);
+void perf_hpp__setup_output_field(struct perf_hpp_list *list);
+void perf_hpp__reset_output_field(struct perf_hpp_list *list);
+void perf_hpp__append_sort_keys(struct perf_hpp_list *list);
+int perf_hpp__setup_hists_formats(struct perf_hpp_list *list,
+				  struct perf_evlist *evlist);
 
-void perf_hpp__register_sort_field(struct perf_hpp_fmt *format);
-void perf_hpp__setup_output_field(void);
-void perf_hpp__reset_output_field(void);
-void perf_hpp__append_sort_keys(void);
 
 bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format);
-bool perf_hpp__same_sort_entry(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b);
 bool perf_hpp__is_dynamic_entry(struct perf_hpp_fmt *format);
 bool perf_hpp__defined_dynamic_entry(struct perf_hpp_fmt *fmt, struct hists *hists);
+bool perf_hpp__is_trace_entry(struct perf_hpp_fmt *fmt);
+bool perf_hpp__is_srcline_entry(struct perf_hpp_fmt *fmt);
+bool perf_hpp__is_srcfile_entry(struct perf_hpp_fmt *fmt);
+bool perf_hpp__is_thread_entry(struct perf_hpp_fmt *fmt);
+bool perf_hpp__is_comm_entry(struct perf_hpp_fmt *fmt);
+bool perf_hpp__is_dso_entry(struct perf_hpp_fmt *fmt);
+bool perf_hpp__is_sym_entry(struct perf_hpp_fmt *fmt);
+
+struct perf_hpp_fmt *perf_hpp_fmt__dup(struct perf_hpp_fmt *fmt);
+
+int hist_entry__filter(struct hist_entry *he, int type, const void *arg);
 
 static inline bool perf_hpp__should_skip(struct perf_hpp_fmt *format,
 					 struct hists *hists)
@@ -372,13 +427,35 @@ static inline int script_browse(const char *script_opt __maybe_unused)
 #endif
 
 unsigned int hists__sort_list_width(struct hists *hists);
+unsigned int hists__overhead_width(struct hists *hists);
 
 void hist__account_cycles(struct branch_stack *bs, struct addr_location *al,
 			  struct perf_sample *sample, bool nonany_branch_mode);
 
 struct option;
-int parse_filter_percentage(const struct option *opt __maybe_unused,
-			    const char *arg, int unset __maybe_unused);
+int parse_filter_percentage(const struct option *opt, const char *arg, int unset);
 int perf_hist_config(const char *var, const char *value);
 
+void perf_hpp_list__init(struct perf_hpp_list *list);
+
+enum hierarchy_move_dir {
+	HMD_NORMAL,
+	HMD_FORCE_SIBLING,
+	HMD_FORCE_CHILD,
+};
+
+struct rb_node *rb_hierarchy_last(struct rb_node *node);
+struct rb_node *__rb_hierarchy_next(struct rb_node *node,
+				    enum hierarchy_move_dir hmd);
+struct rb_node *rb_hierarchy_prev(struct rb_node *node);
+
+static inline struct rb_node *rb_hierarchy_next(struct rb_node *node)
+{
+	return __rb_hierarchy_next(node, HMD_NORMAL);
+}
+
+#define HIERARCHY_INDENT  3
+
+bool hist_entry__has_hierarchy_children(struct hist_entry *he, float limit);
+
 #endif	/* __PERF_HIST_H */
diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
index eb0e7f8bf..abf1366e2 100644
--- a/tools/perf/util/intel-bts.c
+++ b/tools/perf/util/intel-bts.c
@@ -279,6 +279,7 @@ static int intel_bts_synth_branch_sample(struct intel_bts_queue *btsq,
 	event.sample.header.misc = PERF_RECORD_MISC_USER;
 	event.sample.header.size = sizeof(struct perf_event_header);
 
+	sample.cpumode = PERF_RECORD_MISC_USER;
 	sample.ip = le64_to_cpu(branch->from);
 	sample.pid = btsq->pid;
 	sample.tid = btsq->tid;
@@ -678,7 +679,7 @@ static int intel_bts_process_auxtrace_event(struct perf_session *session,
 	return 0;
 }
 
-static int intel_bts_flush(struct perf_session *session __maybe_unused,
+static int intel_bts_flush(struct perf_session *session,
 			   struct perf_tool *tool __maybe_unused)
 {
 	struct intel_bts *bts = container_of(session->auxtrace, struct intel_bts,
diff --git a/tools/perf/util/intel-pt-decoder/insn.c b/tools/perf/util/intel-pt-decoder/insn.c
index 47314a643..9f26eae6c 100644
--- a/tools/perf/util/intel-pt-decoder/insn.c
+++ b/tools/perf/util/intel-pt-decoder/insn.c
@@ -374,7 +374,7 @@ void insn_get_displacement(struct insn *insn)
 		if (mod == 3)
 			goto out;
 		if (mod == 1) {
-			insn->displacement.value = get_next(char, insn);
+			insn->displacement.value = get_next(signed char, insn);
 			insn->displacement.nbytes = 1;
 		} else if (insn->addr_bytes == 2) {
 			if ((mod == 0 && rm == 6) || mod == 2) {
@@ -532,7 +532,7 @@ void insn_get_immediate(struct insn *insn)
 
 	switch (inat_immediate_size(insn->attr)) {
 	case INAT_IMM_BYTE:
-		insn->immediate.value = get_next(char, insn);
+		insn->immediate.value = get_next(signed char, insn);
 		insn->immediate.nbytes = 1;
 		break;
 	case INAT_IMM_WORD:
@@ -566,7 +566,7 @@ void insn_get_immediate(struct insn *insn)
 		goto err_out;
 	}
 	if (inat_has_second_immediate(insn->attr)) {
-		insn->immediate2.value = get_next(char, insn);
+		insn->immediate2.value = get_next(signed char, insn);
 		insn->immediate2.nbytes = 1;
 	}
 done:
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 4e1590ba8..617578440 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -979,6 +979,7 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq)
 	if (!pt->timeless_decoding)
 		sample.time = tsc_to_perf_time(ptq->timestamp, &pt->tc);
 
+	sample.cpumode = PERF_RECORD_MISC_USER;
 	sample.ip = ptq->state->from_ip;
 	sample.pid = ptq->pid;
 	sample.tid = ptq->tid;
@@ -1035,6 +1036,7 @@ static int intel_pt_synth_instruction_sample(struct intel_pt_queue *ptq)
 	if (!pt->timeless_decoding)
 		sample.time = tsc_to_perf_time(ptq->timestamp, &pt->tc);
 
+	sample.cpumode = PERF_RECORD_MISC_USER;
 	sample.ip = ptq->state->from_ip;
 	sample.pid = ptq->pid;
 	sample.tid = ptq->tid;
@@ -1092,6 +1094,7 @@ static int intel_pt_synth_transaction_sample(struct intel_pt_queue *ptq)
 	if (!pt->timeless_decoding)
 		sample.time = tsc_to_perf_time(ptq->timestamp, &pt->tc);
 
+	sample.cpumode = PERF_RECORD_MISC_USER;
 	sample.ip = ptq->state->from_ip;
 	sample.pid = ptq->pid;
 	sample.tid = ptq->tid;
diff --git a/tools/perf/util/jit.h b/tools/perf/util/jit.h
new file mode 100644
index 000000000..3f42ee4d2
--- /dev/null
+++ b/tools/perf/util/jit.h
@@ -0,0 +1,11 @@
+#ifndef __JIT_H__
+#define __JIT_H__
+
+#include <data.h>
+
+int jit_process(struct perf_session *session, struct perf_data_file *output,
+		struct machine *machine, char *filename, pid_t pid, u64 *nbytes);
+
+int jit_inject_record(const char *filename);
+
+#endif /* __JIT_H__ */
diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c
new file mode 100644
index 000000000..ad0c0bb1f
--- /dev/null
+++ b/tools/perf/util/jitdump.c
@@ -0,0 +1,699 @@
+#include <sys/types.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <fcntl.h>
+#include <unistd.h>
+#include <inttypes.h>
+#include <byteswap.h>
+#include <sys/stat.h>
+#include <sys/mman.h>
+
+#include "util.h"
+#include "event.h"
+#include "debug.h"
+#include "evlist.h"
+#include "symbol.h"
+#include "strlist.h"
+#include <elf.h>
+
+#include "session.h"
+#include "jit.h"
+#include "jitdump.h"
+#include "genelf.h"
+#include "../builtin.h"
+
+struct jit_buf_desc {
+	struct perf_data_file *output;
+	struct perf_session *session;
+	struct machine *machine;
+	union jr_entry   *entry;
+	void             *buf;
+	uint64_t	 sample_type;
+	size_t           bufsize;
+	FILE             *in;
+	bool		 needs_bswap; /* handles cross-endianess */
+	void		 *debug_data;
+	size_t		 nr_debug_entries;
+	uint32_t         code_load_count;
+	u64		 bytes_written;
+	struct rb_root   code_root;
+	char		 dir[PATH_MAX];
+};
+
+struct debug_line_info {
+	unsigned long vma;
+	unsigned int lineno;
+	/* The filename format is unspecified, absolute path, relative etc. */
+	char const filename[0];
+};
+
+struct jit_tool {
+	struct perf_tool tool;
+	struct perf_data_file	output;
+	struct perf_data_file	input;
+	u64 bytes_written;
+};
+
+#define hmax(a, b) ((a) > (b) ? (a) : (b))
+#define get_jit_tool(t) (container_of(tool, struct jit_tool, tool))
+
+static int
+jit_emit_elf(char *filename,
+	     const char *sym,
+	     uint64_t code_addr,
+	     const void *code,
+	     int csize,
+	     void *debug,
+	     int nr_debug_entries)
+{
+	int ret, fd;
+
+	if (verbose > 0)
+		fprintf(stderr, "write ELF image %s\n", filename);
+
+	fd = open(filename, O_CREAT|O_TRUNC|O_WRONLY, 0644);
+	if (fd == -1) {
+		pr_warning("cannot create jit ELF %s: %s\n", filename, strerror(errno));
+		return -1;
+	}
+
+        ret = jit_write_elf(fd, code_addr, sym, (const void *)code, csize, debug, nr_debug_entries);
+
+        close(fd);
+
+        if (ret)
+                unlink(filename);
+
+	return ret;
+}
+
+static void
+jit_close(struct jit_buf_desc *jd)
+{
+	if (!(jd && jd->in))
+		return;
+	funlockfile(jd->in);
+	fclose(jd->in);
+	jd->in = NULL;
+}
+
+static int
+jit_validate_events(struct perf_session *session)
+{
+	struct perf_evsel *evsel;
+
+	/*
+	 * check that all events use CLOCK_MONOTONIC
+	 */
+	evlist__for_each(session->evlist, evsel) {
+		if (evsel->attr.use_clockid == 0 || evsel->attr.clockid != CLOCK_MONOTONIC)
+			return -1;
+	}
+	return 0;
+}
+
+static int
+jit_open(struct jit_buf_desc *jd, const char *name)
+{
+	struct jitheader header;
+	struct jr_prefix *prefix;
+	ssize_t bs, bsz = 0;
+	void *n, *buf = NULL;
+	int ret, retval = -1;
+
+	jd->in = fopen(name, "r");
+	if (!jd->in)
+		return -1;
+
+	bsz = hmax(sizeof(header), sizeof(*prefix));
+
+	buf = malloc(bsz);
+	if (!buf)
+		goto error;
+
+	/*
+	 * protect from writer modifying the file while we are reading it
+	 */
+	flockfile(jd->in);
+
+	ret = fread(buf, sizeof(header), 1, jd->in);
+	if (ret != 1)
+		goto error;
+
+	memcpy(&header, buf, sizeof(header));
+
+	if (header.magic != JITHEADER_MAGIC) {
+		if (header.magic != JITHEADER_MAGIC_SW)
+			goto error;
+		jd->needs_bswap = true;
+	}
+
+	if (jd->needs_bswap) {
+		header.version    = bswap_32(header.version);
+		header.total_size = bswap_32(header.total_size);
+		header.pid	  = bswap_32(header.pid);
+		header.elf_mach   = bswap_32(header.elf_mach);
+		header.timestamp  = bswap_64(header.timestamp);
+		header.flags      = bswap_64(header.flags);
+	}
+
+	if (verbose > 2)
+		pr_debug("version=%u\nhdr.size=%u\nts=0x%llx\npid=%d\nelf_mach=%d\n",
+			header.version,
+			header.total_size,
+			(unsigned long long)header.timestamp,
+			header.pid,
+			header.elf_mach);
+
+	if (header.flags & JITDUMP_FLAGS_RESERVED) {
+		pr_err("jitdump file contains invalid or unsupported flags 0x%llx\n",
+		       (unsigned long long)header.flags & JITDUMP_FLAGS_RESERVED);
+		goto error;
+	}
+
+	/*
+	 * validate event is using the correct clockid
+	 */
+	if (jit_validate_events(jd->session)) {
+		pr_err("error, jitted code must be sampled with perf record -k 1\n");
+		goto error;
+	}
+
+	bs = header.total_size - sizeof(header);
+
+	if (bs > bsz) {
+		n = realloc(buf, bs);
+		if (!n)
+			goto error;
+		bsz = bs;
+		buf = n;
+		/* read extra we do not know about */
+		ret = fread(buf, bs - bsz, 1, jd->in);
+		if (ret != 1)
+			goto error;
+	}
+	/*
+	 * keep dirname for generating files and mmap records
+	 */
+	strcpy(jd->dir, name);
+	dirname(jd->dir);
+
+	return 0;
+error:
+	funlockfile(jd->in);
+	fclose(jd->in);
+	return retval;
+}
+
+static union jr_entry *
+jit_get_next_entry(struct jit_buf_desc *jd)
+{
+	struct jr_prefix *prefix;
+	union jr_entry *jr;
+	void *addr;
+	size_t bs, size;
+	int id, ret;
+
+	if (!(jd && jd->in))
+		return NULL;
+
+	if (jd->buf == NULL) {
+		size_t sz = getpagesize();
+		if (sz < sizeof(*prefix))
+			sz = sizeof(*prefix);
+
+		jd->buf = malloc(sz);
+		if (jd->buf == NULL)
+			return NULL;
+
+		jd->bufsize = sz;
+	}
+
+	prefix = jd->buf;
+
+	/*
+	 * file is still locked at this point
+	 */
+	ret = fread(prefix, sizeof(*prefix), 1, jd->in);
+	if (ret  != 1)
+		return NULL;
+
+	if (jd->needs_bswap) {
+		prefix->id   	   = bswap_32(prefix->id);
+		prefix->total_size = bswap_32(prefix->total_size);
+		prefix->timestamp  = bswap_64(prefix->timestamp);
+	}
+	id   = prefix->id;
+	size = prefix->total_size;
+
+	bs = (size_t)size;
+	if (bs < sizeof(*prefix))
+		return NULL;
+
+	if (id >= JIT_CODE_MAX) {
+		pr_warning("next_entry: unknown prefix %d, skipping\n", id);
+		return NULL;
+	}
+	if (bs > jd->bufsize) {
+		void *n;
+		n = realloc(jd->buf, bs);
+		if (!n)
+			return NULL;
+		jd->buf = n;
+		jd->bufsize = bs;
+	}
+
+	addr = ((void *)jd->buf) + sizeof(*prefix);
+
+	ret = fread(addr, bs - sizeof(*prefix), 1, jd->in);
+	if (ret != 1)
+		return NULL;
+
+	jr = (union jr_entry *)jd->buf;
+
+	switch(id) {
+	case JIT_CODE_DEBUG_INFO:
+		if (jd->needs_bswap) {
+			uint64_t n;
+			jr->info.code_addr = bswap_64(jr->info.code_addr);
+			jr->info.nr_entry  = bswap_64(jr->info.nr_entry);
+			for (n = 0 ; n < jr->info.nr_entry; n++) {
+				jr->info.entries[n].addr    = bswap_64(jr->info.entries[n].addr);
+				jr->info.entries[n].lineno  = bswap_32(jr->info.entries[n].lineno);
+				jr->info.entries[n].discrim = bswap_32(jr->info.entries[n].discrim);
+			}
+		}
+		break;
+	case JIT_CODE_CLOSE:
+		break;
+	case JIT_CODE_LOAD:
+		if (jd->needs_bswap) {
+			jr->load.pid       = bswap_32(jr->load.pid);
+			jr->load.tid       = bswap_32(jr->load.tid);
+			jr->load.vma       = bswap_64(jr->load.vma);
+			jr->load.code_addr = bswap_64(jr->load.code_addr);
+			jr->load.code_size = bswap_64(jr->load.code_size);
+			jr->load.code_index= bswap_64(jr->load.code_index);
+		}
+		jd->code_load_count++;
+		break;
+	case JIT_CODE_MOVE:
+		if (jd->needs_bswap) {
+			jr->move.pid           = bswap_32(jr->move.pid);
+			jr->move.tid           = bswap_32(jr->move.tid);
+			jr->move.vma           = bswap_64(jr->move.vma);
+			jr->move.old_code_addr = bswap_64(jr->move.old_code_addr);
+			jr->move.new_code_addr = bswap_64(jr->move.new_code_addr);
+			jr->move.code_size     = bswap_64(jr->move.code_size);
+			jr->move.code_index    = bswap_64(jr->move.code_index);
+		}
+		break;
+	case JIT_CODE_MAX:
+	default:
+		return NULL;
+	}
+	return jr;
+}
+
+static int
+jit_inject_event(struct jit_buf_desc *jd, union perf_event *event)
+{
+	ssize_t size;
+
+	size = perf_data_file__write(jd->output, event, event->header.size);
+	if (size < 0)
+		return -1;
+
+	jd->bytes_written += size;
+	return 0;
+}
+
+static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr)
+{
+	struct perf_sample sample;
+	union perf_event *event;
+	struct perf_tool *tool = jd->session->tool;
+	uint64_t code, addr;
+	uintptr_t uaddr;
+	char *filename;
+	struct stat st;
+	size_t size;
+	u16 idr_size;
+	const char *sym;
+	uint32_t count;
+	int ret, csize;
+	pid_t pid, tid;
+	struct {
+		u32 pid, tid;
+		u64 time;
+	} *id;
+
+	pid   = jr->load.pid;
+	tid   = jr->load.tid;
+	csize = jr->load.code_size;
+	addr  = jr->load.code_addr;
+	sym   = (void *)((unsigned long)jr + sizeof(jr->load));
+	code  = (unsigned long)jr + jr->load.p.total_size - csize;
+	count = jr->load.code_index;
+	idr_size = jd->machine->id_hdr_size;
+
+	event = calloc(1, sizeof(*event) + idr_size);
+	if (!event)
+		return -1;
+
+	filename = event->mmap2.filename;
+	size = snprintf(filename, PATH_MAX, "%s/jitted-%d-%u.so",
+			jd->dir,
+			pid,
+			count);
+
+	size++; /* for \0 */
+
+	size = PERF_ALIGN(size, sizeof(u64));
+	uaddr = (uintptr_t)code;
+	ret = jit_emit_elf(filename, sym, addr, (const void *)uaddr, csize, jd->debug_data, jd->nr_debug_entries);
+
+	if (jd->debug_data && jd->nr_debug_entries) {
+		free(jd->debug_data);
+		jd->debug_data = NULL;
+		jd->nr_debug_entries = 0;
+	}
+
+	if (ret) {
+		free(event);
+		return -1;
+	}
+	if (stat(filename, &st))
+		memset(&st, 0, sizeof(stat));
+
+	event->mmap2.header.type = PERF_RECORD_MMAP2;
+	event->mmap2.header.misc = PERF_RECORD_MISC_USER;
+	event->mmap2.header.size = (sizeof(event->mmap2) -
+			(sizeof(event->mmap2.filename) - size) + idr_size);
+
+	event->mmap2.pgoff = GEN_ELF_TEXT_OFFSET;
+	event->mmap2.start = addr;
+	event->mmap2.len   = csize;
+	event->mmap2.pid   = pid;
+	event->mmap2.tid   = tid;
+	event->mmap2.ino   = st.st_ino;
+	event->mmap2.maj   = major(st.st_dev);
+	event->mmap2.min   = minor(st.st_dev);
+	event->mmap2.prot  = st.st_mode;
+	event->mmap2.flags = MAP_SHARED;
+	event->mmap2.ino_generation = 1;
+
+	id = (void *)((unsigned long)event + event->mmap.header.size - idr_size);
+	if (jd->sample_type & PERF_SAMPLE_TID) {
+		id->pid  = pid;
+		id->tid  = tid;
+	}
+	if (jd->sample_type & PERF_SAMPLE_TIME)
+		id->time = jr->load.p.timestamp;
+
+	/*
+	 * create pseudo sample to induce dso hit increment
+	 * use first address as sample address
+	 */
+	memset(&sample, 0, sizeof(sample));
+	sample.cpumode = PERF_RECORD_MISC_USER;
+	sample.pid  = pid;
+	sample.tid  = tid;
+	sample.time = id->time;
+	sample.ip   = addr;
+
+	ret = perf_event__process_mmap2(tool, event, &sample, jd->machine);
+	if (ret)
+		return ret;
+
+	ret = jit_inject_event(jd, event);
+	/*
+	 * mark dso as use to generate buildid in the header
+	 */
+	if (!ret)
+		build_id__mark_dso_hit(tool, event, &sample, NULL, jd->machine);
+
+	return ret;
+}
+
+static int jit_repipe_code_move(struct jit_buf_desc *jd, union jr_entry *jr)
+{
+	struct perf_sample sample;
+	union perf_event *event;
+	struct perf_tool *tool = jd->session->tool;
+	char *filename;
+	size_t size;
+	struct stat st;
+	u16 idr_size;
+	int ret;
+	pid_t pid, tid;
+	struct {
+		u32 pid, tid;
+		u64 time;
+	} *id;
+
+	pid = jr->move.pid;
+	tid =  jr->move.tid;
+	idr_size = jd->machine->id_hdr_size;
+
+	/*
+	 * +16 to account for sample_id_all (hack)
+	 */
+	event = calloc(1, sizeof(*event) + 16);
+	if (!event)
+		return -1;
+
+	filename = event->mmap2.filename;
+	size = snprintf(filename, PATH_MAX, "%s/jitted-%d-%"PRIu64,
+	         jd->dir,
+	         pid,
+		 jr->move.code_index);
+
+	size++; /* for \0 */
+
+	if (stat(filename, &st))
+		memset(&st, 0, sizeof(stat));
+
+	size = PERF_ALIGN(size, sizeof(u64));
+
+	event->mmap2.header.type = PERF_RECORD_MMAP2;
+	event->mmap2.header.misc = PERF_RECORD_MISC_USER;
+	event->mmap2.header.size = (sizeof(event->mmap2) -
+			(sizeof(event->mmap2.filename) - size) + idr_size);
+	event->mmap2.pgoff = GEN_ELF_TEXT_OFFSET;
+	event->mmap2.start = jr->move.new_code_addr;
+	event->mmap2.len   = jr->move.code_size;
+	event->mmap2.pid   = pid;
+	event->mmap2.tid   = tid;
+	event->mmap2.ino   = st.st_ino;
+	event->mmap2.maj   = major(st.st_dev);
+	event->mmap2.min   = minor(st.st_dev);
+	event->mmap2.prot  = st.st_mode;
+	event->mmap2.flags = MAP_SHARED;
+	event->mmap2.ino_generation = 1;
+
+	id = (void *)((unsigned long)event + event->mmap.header.size - idr_size);
+	if (jd->sample_type & PERF_SAMPLE_TID) {
+		id->pid  = pid;
+		id->tid  = tid;
+	}
+	if (jd->sample_type & PERF_SAMPLE_TIME)
+		id->time = jr->load.p.timestamp;
+
+	/*
+	 * create pseudo sample to induce dso hit increment
+	 * use first address as sample address
+	 */
+	memset(&sample, 0, sizeof(sample));
+	sample.cpumode = PERF_RECORD_MISC_USER;
+	sample.pid  = pid;
+	sample.tid  = tid;
+	sample.time = id->time;
+	sample.ip   = jr->move.new_code_addr;
+
+	ret = perf_event__process_mmap2(tool, event, &sample, jd->machine);
+	if (ret)
+		return ret;
+
+	ret = jit_inject_event(jd, event);
+	if (!ret)
+		build_id__mark_dso_hit(tool, event, &sample, NULL, jd->machine);
+
+	return ret;
+}
+
+static int jit_repipe_debug_info(struct jit_buf_desc *jd, union jr_entry *jr)
+{
+	void *data;
+	size_t sz;
+
+	if (!(jd && jr))
+		return -1;
+
+	sz  = jr->prefix.total_size - sizeof(jr->info);
+	data = malloc(sz);
+	if (!data)
+		return -1;
+
+	memcpy(data, &jr->info.entries, sz);
+
+	jd->debug_data       = data;
+
+	/*
+	 * we must use nr_entry instead of size here because
+	 * we cannot distinguish actual entry from padding otherwise
+	 */
+	jd->nr_debug_entries = jr->info.nr_entry;
+
+	return 0;
+}
+
+static int
+jit_process_dump(struct jit_buf_desc *jd)
+{
+	union jr_entry *jr;
+	int ret;
+
+	while ((jr = jit_get_next_entry(jd))) {
+		switch(jr->prefix.id) {
+		case JIT_CODE_LOAD:
+			ret = jit_repipe_code_load(jd, jr);
+			break;
+		case JIT_CODE_MOVE:
+			ret = jit_repipe_code_move(jd, jr);
+			break;
+		case JIT_CODE_DEBUG_INFO:
+			ret = jit_repipe_debug_info(jd, jr);
+			break;
+		default:
+			ret = 0;
+			continue;
+		}
+	}
+	return ret;
+}
+
+static int
+jit_inject(struct jit_buf_desc *jd, char *path)
+{
+	int ret;
+
+	if (verbose > 0)
+		fprintf(stderr, "injecting: %s\n", path);
+
+	ret = jit_open(jd, path);
+	if (ret)
+		return -1;
+
+	ret = jit_process_dump(jd);
+
+	jit_close(jd);
+
+	if (verbose > 0)
+		fprintf(stderr, "injected: %s (%d)\n", path, ret);
+
+	return 0;
+}
+
+/*
+ * File must be with pattern .../jit-XXXX.dump
+ * where XXXX is the PID of the process which did the mmap()
+ * as captured in the RECORD_MMAP record
+ */
+static int
+jit_detect(char *mmap_name, pid_t pid)
+ {
+	char *p;
+	char *end = NULL;
+	pid_t pid2;
+
+	if (verbose > 2)
+		fprintf(stderr, "jit marker trying : %s\n", mmap_name);
+	/*
+	 * get file name
+	 */
+	p = strrchr(mmap_name, '/');
+	if (!p)
+		return -1;
+
+	/*
+	 * match prefix
+	 */
+	if (strncmp(p, "/jit-", 5))
+		return -1;
+
+	/*
+	 * skip prefix
+	 */
+	p += 5;
+
+	/*
+	 * must be followed by a pid
+	 */
+	if (!isdigit(*p))
+		return -1;
+
+	pid2 = (int)strtol(p, &end, 10);
+	if (!end)
+		return -1;
+
+	/*
+	 * pid does not match mmap pid
+	 * pid==0 in system-wide mode (synthesized)
+	 */
+	if (pid && pid2 != pid)
+		return -1;
+	/*
+	 * validate suffix
+	 */
+	if (strcmp(end, ".dump"))
+		return -1;
+
+	if (verbose > 0)
+		fprintf(stderr, "jit marker found: %s\n", mmap_name);
+
+	return 0;
+}
+
+int
+jit_process(struct perf_session *session,
+	    struct perf_data_file *output,
+	    struct machine *machine,
+	    char *filename,
+	    pid_t pid,
+	    u64 *nbytes)
+{
+	struct perf_evsel *first;
+	struct jit_buf_desc jd;
+	int ret;
+
+	/*
+	 * first, detect marker mmap (i.e., the jitdump mmap)
+	 */
+	if (jit_detect(filename, pid))
+		return 0;
+
+	memset(&jd, 0, sizeof(jd));
+
+	jd.session = session;
+	jd.output  = output;
+	jd.machine = machine;
+
+	/*
+	 * track sample_type to compute id_all layout
+	 * perf sets the same sample type to all events as of now
+	 */
+	first = perf_evlist__first(session->evlist);
+	jd.sample_type = first->attr.sample_type;
+
+	*nbytes = 0;
+
+	ret = jit_inject(&jd, filename);
+	if (!ret) {
+		*nbytes = jd.bytes_written;
+		ret = 1;
+	}
+
+	return ret;
+}
diff --git a/tools/perf/util/jitdump.h b/tools/perf/util/jitdump.h
new file mode 100644
index 000000000..b66c1f503
--- /dev/null
+++ b/tools/perf/util/jitdump.h
@@ -0,0 +1,124 @@
+/*
+ * jitdump.h: jitted code info encapsulation file format
+ *
+ * Adapted from OProfile GPLv2 support jidump.h:
+ * Copyright 2007 OProfile authors
+ * Jens Wilke
+ * Daniel Hansel
+ * Copyright IBM Corporation 2007
+ */
+#ifndef JITDUMP_H
+#define JITDUMP_H
+
+#include <sys/time.h>
+#include <time.h>
+#include <stdint.h>
+
+/* JiTD */
+#define JITHEADER_MAGIC		0x4A695444
+#define JITHEADER_MAGIC_SW	0x4454694A
+
+#define PADDING_8ALIGNED(x) ((((x) + 7) & 7) ^ 7)
+
+#define JITHEADER_VERSION 1
+
+enum jitdump_flags_bits {
+	JITDUMP_FLAGS_MAX_BIT,
+};
+
+#define JITDUMP_FLAGS_RESERVED (JITDUMP_FLAGS_MAX_BIT < 64 ? \
+				(~((1ULL << JITDUMP_FLAGS_MAX_BIT) - 1)) : 0)
+
+struct jitheader {
+	uint32_t magic;		/* characters "jItD" */
+	uint32_t version;	/* header version */
+	uint32_t total_size;	/* total size of header */
+	uint32_t elf_mach;	/* elf mach target */
+	uint32_t pad1;		/* reserved */
+	uint32_t pid;		/* JIT process id */
+	uint64_t timestamp;	/* timestamp */
+	uint64_t flags;		/* flags */
+};
+
+enum jit_record_type {
+	JIT_CODE_LOAD		= 0,
+        JIT_CODE_MOVE           = 1,
+	JIT_CODE_DEBUG_INFO	= 2,
+	JIT_CODE_CLOSE		= 3,
+
+	JIT_CODE_MAX,
+};
+
+/* record prefix (mandatory in each record) */
+struct jr_prefix {
+	uint32_t id;
+	uint32_t total_size;
+	uint64_t timestamp;
+};
+
+struct jr_code_load {
+	struct jr_prefix p;
+
+	uint32_t pid;
+	uint32_t tid;
+	uint64_t vma;
+	uint64_t code_addr;
+	uint64_t code_size;
+	uint64_t code_index;
+};
+
+struct jr_code_close {
+	struct jr_prefix p;
+};
+
+struct jr_code_move {
+	struct jr_prefix p;
+
+	uint32_t pid;
+	uint32_t tid;
+	uint64_t vma;
+	uint64_t old_code_addr;
+	uint64_t new_code_addr;
+	uint64_t code_size;
+	uint64_t code_index;
+};
+
+struct debug_entry {
+	uint64_t addr;
+	int lineno;	    /* source line number starting at 1 */
+	int discrim;	    /* column discriminator, 0 is default */
+	const char name[0]; /* null terminated filename, \xff\0 if same as previous entry */
+};
+
+struct jr_code_debug_info {
+	struct jr_prefix p;
+
+	uint64_t code_addr;
+	uint64_t nr_entry;
+	struct debug_entry entries[0];
+};
+
+union jr_entry {
+        struct jr_code_debug_info info;
+        struct jr_code_close close;
+        struct jr_code_load load;
+        struct jr_code_move move;
+        struct jr_prefix prefix;
+};
+
+static inline struct debug_entry *
+debug_entry_next(struct debug_entry *ent)
+{
+	void *a = ent + 1;
+	size_t l = strlen(ent->name) + 1;
+	return a + l;
+}
+
+static inline char *
+debug_entry_file(struct debug_entry *ent)
+{
+	void *a = ent + 1;
+	return a;
+}
+
+#endif /* !JITDUMP_H */
diff --git a/tools/perf/util/kvm-stat.h b/tools/perf/util/kvm-stat.h
index ae825d4ec..d01e73592 100644
--- a/tools/perf/util/kvm-stat.h
+++ b/tools/perf/util/kvm-stat.h
@@ -122,6 +122,7 @@ void exit_event_decode_key(struct perf_kvm_stat *kvm,
 
 bool kvm_exit_event(struct perf_evsel *evsel);
 bool kvm_entry_event(struct perf_evsel *evsel);
+int setup_kvm_events_tp(struct perf_kvm_stat *kvm);
 
 #define define_exit_reasons_table(name, symbols)	\
 	static struct exit_reasons_table name[] = {	\
@@ -133,8 +134,13 @@ bool kvm_entry_event(struct perf_evsel *evsel);
  */
 int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid);
 
-extern const char * const kvm_events_tp[];
+extern const char *kvm_events_tp[];
 extern struct kvm_reg_events_ops kvm_reg_events_ops[];
 extern const char * const kvm_skip_events[];
+extern const char *vcpu_id_str;
+extern const int decode_str_len;
+extern const char *kvm_exit_reason;
+extern const char *kvm_entry_trace;
+extern const char *kvm_exit_trace;
 
 #endif /* __PERF_KVM_STAT_H */
diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
index 00724d496..33071d615 100644
--- a/tools/perf/util/llvm-utils.c
+++ b/tools/perf/util/llvm-utils.c
@@ -3,11 +3,11 @@
  * Copyright (C) 2015, Huawei Inc.
  */
 
+#include <limits.h>
 #include <stdio.h>
-#include "util.h"
+#include <stdlib.h>
 #include "debug.h"
 #include "llvm-utils.h"
-#include "cache.h"
 
 #define CLANG_BPF_CMD_DEFAULT_TEMPLATE				\
 		"$CLANG_EXEC -D__KERNEL__ -D__NR_CPUS__=$NR_CPUS "\
@@ -98,11 +98,12 @@ read_from_pipe(const char *cmd, void **p_buf, size_t *p_read_sz)
 	void *buf = NULL;
 	FILE *file = NULL;
 	size_t read_sz = 0, buf_sz = 0;
+	char serr[STRERR_BUFSIZE];
 
 	file = popen(cmd, "r");
 	if (!file) {
 		pr_err("ERROR: unable to popen cmd: %s\n",
-		       strerror(errno));
+		       strerror_r(errno, serr, sizeof(serr)));
 		return -EINVAL;
 	}
 
@@ -136,7 +137,7 @@ read_from_pipe(const char *cmd, void **p_buf, size_t *p_read_sz)
 
 	if (ferror(file)) {
 		pr_err("ERROR: error occurred when reading from pipe: %s\n",
-		       strerror(errno));
+		       strerror_r(errno, serr, sizeof(serr)));
 		err = -EIO;
 		goto errout;
 	}
@@ -334,10 +335,18 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf,
 	unsigned int kernel_version;
 	char linux_version_code_str[64];
 	const char *clang_opt = llvm_param.clang_opt;
-	char clang_path[PATH_MAX], nr_cpus_avail_str[64];
+	char clang_path[PATH_MAX], abspath[PATH_MAX], nr_cpus_avail_str[64];
+	char serr[STRERR_BUFSIZE];
 	char *kbuild_dir = NULL, *kbuild_include_opts = NULL;
 	const char *template = llvm_param.clang_bpf_cmd_template;
 
+	if (path[0] != '-' && realpath(path, abspath) == NULL) {
+		err = errno;
+		pr_err("ERROR: problems with path %s: %s\n",
+		       path, strerror_r(err, serr, sizeof(serr)));
+		return -err;
+	}
+
 	if (!template)
 		template = CLANG_BPF_CMD_DEFAULT_TEMPLATE;
 
@@ -362,7 +371,7 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf,
 	if (nr_cpus_avail <= 0) {
 		pr_err(
 "WARNING:\tunable to get available CPUs in this system: %s\n"
-"        \tUse 128 instead.\n", strerror(errno));
+"        \tUse 128 instead.\n", strerror_r(errno, serr, sizeof(serr)));
 		nr_cpus_avail = 128;
 	}
 	snprintf(nr_cpus_avail_str, sizeof(nr_cpus_avail_str), "%d",
@@ -387,8 +396,7 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf,
 	 * stdin to be source file (testing).
 	 */
 	force_set_env("CLANG_SOURCE",
-		      (path[0] == '-') ? path :
-		      make_nonrelative_path(path));
+		      (path[0] == '-') ? path : abspath);
 
 	pr_debug("llvm compiling command template: %s\n", template);
 	err = read_from_pipe(template, &obj_buf, &obj_buf_sz);
diff --git a/tools/perf/util/llvm-utils.h b/tools/perf/util/llvm-utils.h
index 5b3cf1c22..23b9a743f 100644
--- a/tools/perf/util/llvm-utils.h
+++ b/tools/perf/util/llvm-utils.h
@@ -39,11 +39,10 @@ struct llvm_param {
 };
 
 extern struct llvm_param llvm_param;
-extern int perf_llvm_config(const char *var, const char *value);
+int perf_llvm_config(const char *var, const char *value);
 
-extern int llvm__compile_bpf(const char *path, void **p_obj_buf,
-			     size_t *p_obj_buf_sz);
+int llvm__compile_bpf(const char *path, void **p_obj_buf, size_t *p_obj_buf_sz);
 
 /* This function is for test__llvm() use only */
-extern int llvm__search_clang(void);
+int llvm__search_clang(void);
 #endif
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index ad79297c7..80b9b6a87 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1301,9 +1301,8 @@ out_problem:
 
 int machine__process_mmap2_event(struct machine *machine,
 				 union perf_event *event,
-				 struct perf_sample *sample __maybe_unused)
+				 struct perf_sample *sample)
 {
-	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 	struct thread *thread;
 	struct map *map;
 	enum map_type type;
@@ -1312,8 +1311,8 @@ int machine__process_mmap2_event(struct machine *machine,
 	if (dump_trace)
 		perf_event__fprintf_mmap2(event, stdout);
 
-	if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL ||
-	    cpumode == PERF_RECORD_MISC_KERNEL) {
+	if (sample->cpumode == PERF_RECORD_MISC_GUEST_KERNEL ||
+	    sample->cpumode == PERF_RECORD_MISC_KERNEL) {
 		ret = machine__process_kernel_mmap_event(machine, event);
 		if (ret < 0)
 			goto out_problem;
@@ -1355,9 +1354,8 @@ out_problem:
 }
 
 int machine__process_mmap_event(struct machine *machine, union perf_event *event,
-				struct perf_sample *sample __maybe_unused)
+				struct perf_sample *sample)
 {
-	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 	struct thread *thread;
 	struct map *map;
 	enum map_type type;
@@ -1366,8 +1364,8 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event
 	if (dump_trace)
 		perf_event__fprintf_mmap(event, stdout);
 
-	if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL ||
-	    cpumode == PERF_RECORD_MISC_KERNEL) {
+	if (sample->cpumode == PERF_RECORD_MISC_GUEST_KERNEL ||
+	    sample->cpumode == PERF_RECORD_MISC_KERNEL) {
 		ret = machine__process_kernel_mmap_event(machine, event);
 		if (ret < 0)
 			goto out_problem;
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 2c2b443df..8499db281 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -94,7 +94,7 @@ int machine__process_aux_event(struct machine *machine,
 			       union perf_event *event);
 int machine__process_itrace_start_event(struct machine *machine,
 					union perf_event *event);
-int machine__process_switch_event(struct machine *machine __maybe_unused,
+int machine__process_switch_event(struct machine *machine,
 				  union perf_event *event);
 int machine__process_mmap_event(struct machine *machine, union perf_event *event,
 				struct perf_sample *sample);
@@ -180,6 +180,16 @@ struct symbol *machine__find_kernel_symbol(struct machine *machine,
 }
 
 static inline
+struct symbol *machine__find_kernel_symbol_by_name(struct machine *machine,
+						   enum map_type type, const char *name,
+						   struct map **mapp,
+						   symbol_filter_t filter)
+{
+	return map_groups__find_symbol_by_name(&machine->kmaps, type, name,
+					       mapp, filter);
+}
+
+static inline
 struct symbol *machine__find_kernel_function(struct machine *machine, u64 addr,
 					     struct map **mapp,
 					     symbol_filter_t filter)
diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
new file mode 100644
index 000000000..75465f89a
--- /dev/null
+++ b/tools/perf/util/mem-events.c
@@ -0,0 +1,255 @@
+#include <stddef.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+#include <api/fs/fs.h>
+#include "mem-events.h"
+#include "debug.h"
+#include "symbol.h"
+
+#define E(t, n, s) { .tag = t, .name = n, .sysfs_name = s }
+
+struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = {
+	E("ldlat-loads",	"cpu/mem-loads,ldlat=30/P",	"mem-loads"),
+	E("ldlat-stores",	"cpu/mem-stores/P",		"mem-stores"),
+};
+#undef E
+
+#undef E
+
+char *perf_mem_events__name(int i)
+{
+	return (char *)perf_mem_events[i].name;
+}
+
+int perf_mem_events__parse(const char *str)
+{
+	char *tok, *saveptr = NULL;
+	bool found = false;
+	char *buf;
+	int j;
+
+	/* We need buffer that we know we can write to. */
+	buf = malloc(strlen(str) + 1);
+	if (!buf)
+		return -ENOMEM;
+
+	strcpy(buf, str);
+
+	tok = strtok_r((char *)buf, ",", &saveptr);
+
+	while (tok) {
+		for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
+			struct perf_mem_event *e = &perf_mem_events[j];
+
+			if (strstr(e->tag, tok))
+				e->record = found = true;
+		}
+
+		tok = strtok_r(NULL, ",", &saveptr);
+	}
+
+	free(buf);
+
+	if (found)
+		return 0;
+
+	pr_err("failed: event '%s' not found, use '-e list' to get list of available events\n", str);
+	return -1;
+}
+
+int perf_mem_events__init(void)
+{
+	const char *mnt = sysfs__mount();
+	bool found = false;
+	int j;
+
+	if (!mnt)
+		return -ENOENT;
+
+	for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
+		char path[PATH_MAX];
+		struct perf_mem_event *e = &perf_mem_events[j];
+		struct stat st;
+
+		scnprintf(path, PATH_MAX, "%s/devices/cpu/events/%s",
+			  mnt, e->sysfs_name);
+
+		if (!stat(path, &st))
+			e->supported = found = true;
+	}
+
+	return found ? 0 : -ENOENT;
+}
+
+static const char * const tlb_access[] = {
+	"N/A",
+	"HIT",
+	"MISS",
+	"L1",
+	"L2",
+	"Walker",
+	"Fault",
+};
+
+int perf_mem__tlb_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
+{
+	size_t l = 0, i;
+	u64 m = PERF_MEM_TLB_NA;
+	u64 hit, miss;
+
+	sz -= 1; /* -1 for null termination */
+	out[0] = '\0';
+
+	if (mem_info)
+		m = mem_info->data_src.mem_dtlb;
+
+	hit = m & PERF_MEM_TLB_HIT;
+	miss = m & PERF_MEM_TLB_MISS;
+
+	/* already taken care of */
+	m &= ~(PERF_MEM_TLB_HIT|PERF_MEM_TLB_MISS);
+
+	for (i = 0; m && i < ARRAY_SIZE(tlb_access); i++, m >>= 1) {
+		if (!(m & 0x1))
+			continue;
+		if (l) {
+			strcat(out, " or ");
+			l += 4;
+		}
+		l += scnprintf(out + l, sz - l, tlb_access[i]);
+	}
+	if (*out == '\0')
+		l += scnprintf(out, sz - l, "N/A");
+	if (hit)
+		l += scnprintf(out + l, sz - l, " hit");
+	if (miss)
+		l += scnprintf(out + l, sz - l, " miss");
+
+	return l;
+}
+
+static const char * const mem_lvl[] = {
+	"N/A",
+	"HIT",
+	"MISS",
+	"L1",
+	"LFB",
+	"L2",
+	"L3",
+	"Local RAM",
+	"Remote RAM (1 hop)",
+	"Remote RAM (2 hops)",
+	"Remote Cache (1 hop)",
+	"Remote Cache (2 hops)",
+	"I/O",
+	"Uncached",
+};
+
+int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
+{
+	size_t i, l = 0;
+	u64 m =  PERF_MEM_LVL_NA;
+	u64 hit, miss;
+
+	if (mem_info)
+		m  = mem_info->data_src.mem_lvl;
+
+	sz -= 1; /* -1 for null termination */
+	out[0] = '\0';
+
+	hit = m & PERF_MEM_LVL_HIT;
+	miss = m & PERF_MEM_LVL_MISS;
+
+	/* already taken care of */
+	m &= ~(PERF_MEM_LVL_HIT|PERF_MEM_LVL_MISS);
+
+	for (i = 0; m && i < ARRAY_SIZE(mem_lvl); i++, m >>= 1) {
+		if (!(m & 0x1))
+			continue;
+		if (l) {
+			strcat(out, " or ");
+			l += 4;
+		}
+		l += scnprintf(out + l, sz - l, mem_lvl[i]);
+	}
+	if (*out == '\0')
+		l += scnprintf(out, sz - l, "N/A");
+	if (hit)
+		l += scnprintf(out + l, sz - l, " hit");
+	if (miss)
+		l += scnprintf(out + l, sz - l, " miss");
+
+	return l;
+}
+
+static const char * const snoop_access[] = {
+	"N/A",
+	"None",
+	"Miss",
+	"Hit",
+	"HitM",
+};
+
+int perf_mem__snp_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
+{
+	size_t i, l = 0;
+	u64 m = PERF_MEM_SNOOP_NA;
+
+	sz -= 1; /* -1 for null termination */
+	out[0] = '\0';
+
+	if (mem_info)
+		m = mem_info->data_src.mem_snoop;
+
+	for (i = 0; m && i < ARRAY_SIZE(snoop_access); i++, m >>= 1) {
+		if (!(m & 0x1))
+			continue;
+		if (l) {
+			strcat(out, " or ");
+			l += 4;
+		}
+		l += scnprintf(out + l, sz - l, snoop_access[i]);
+	}
+
+	if (*out == '\0')
+		l += scnprintf(out, sz - l, "N/A");
+
+	return l;
+}
+
+int perf_mem__lck_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
+{
+	u64 mask = PERF_MEM_LOCK_NA;
+	int l;
+
+	if (mem_info)
+		mask = mem_info->data_src.mem_lock;
+
+	if (mask & PERF_MEM_LOCK_NA)
+		l = scnprintf(out, sz, "N/A");
+	else if (mask & PERF_MEM_LOCK_LOCKED)
+		l = scnprintf(out, sz, "Yes");
+	else
+		l = scnprintf(out, sz, "No");
+
+	return l;
+}
+
+int perf_script__meminfo_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
+{
+	int i = 0;
+
+	i += perf_mem__lvl_scnprintf(out, sz, mem_info);
+	i += scnprintf(out + i, sz - i, "|SNP ");
+	i += perf_mem__snp_scnprintf(out + i, sz - i, mem_info);
+	i += scnprintf(out + i, sz - i, "|TLB ");
+	i += perf_mem__tlb_scnprintf(out + i, sz - i, mem_info);
+	i += scnprintf(out + i, sz - i, "|LCK ");
+	i += perf_mem__lck_scnprintf(out + i, sz - i, mem_info);
+
+	return i;
+}
diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h
new file mode 100644
index 000000000..5d6d93066
--- /dev/null
+++ b/tools/perf/util/mem-events.h
@@ -0,0 +1,35 @@
+#ifndef __PERF_MEM_EVENTS_H
+#define __PERF_MEM_EVENTS_H
+
+#include <stdbool.h>
+
+struct perf_mem_event {
+	bool		record;
+	bool		supported;
+	const char	*tag;
+	const char	*name;
+	const char	*sysfs_name;
+};
+
+enum {
+	PERF_MEM_EVENTS__LOAD,
+	PERF_MEM_EVENTS__STORE,
+	PERF_MEM_EVENTS__MAX,
+};
+
+extern struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX];
+
+int perf_mem_events__parse(const char *str);
+int perf_mem_events__init(void);
+
+char *perf_mem_events__name(int i);
+
+struct mem_info;
+int perf_mem__tlb_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
+int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
+int perf_mem__snp_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
+int perf_mem__lck_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
+
+int perf_script__meminfo_scnprintf(char *bf, size_t size, struct mem_info *mem_info);
+
+#endif /* __PERF_MEM_EVENTS_H */
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 48a1c5e7d..bcbc983d4 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -138,11 +138,11 @@ struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = {
 #define PERF_EVENT_TYPE(config)		__PERF_EVENT_FIELD(config, TYPE)
 #define PERF_EVENT_ID(config)		__PERF_EVENT_FIELD(config, EVENT)
 
-#define for_each_subsystem(sys_dir, sys_dirent, sys_next)	       \
-	while (!readdir_r(sys_dir, &sys_dirent, &sys_next) && sys_next)	       \
-	if (sys_dirent.d_type == DT_DIR &&				       \
-	   (strcmp(sys_dirent.d_name, ".")) &&				       \
-	   (strcmp(sys_dirent.d_name, "..")))
+#define for_each_subsystem(sys_dir, sys_dirent)			\
+	while ((sys_dirent = readdir(sys_dir)) != NULL)		\
+		if (sys_dirent->d_type == DT_DIR &&		\
+		    (strcmp(sys_dirent->d_name, ".")) &&	\
+		    (strcmp(sys_dirent->d_name, "..")))
 
 static int tp_event_has_id(struct dirent *sys_dir, struct dirent *evt_dir)
 {
@@ -159,12 +159,12 @@ static int tp_event_has_id(struct dirent *sys_dir, struct dirent *evt_dir)
 	return 0;
 }
 
-#define for_each_event(sys_dirent, evt_dir, evt_dirent, evt_next)	       \
-	while (!readdir_r(evt_dir, &evt_dirent, &evt_next) && evt_next)        \
-	if (evt_dirent.d_type == DT_DIR &&				       \
-	   (strcmp(evt_dirent.d_name, ".")) &&				       \
-	   (strcmp(evt_dirent.d_name, "..")) &&				       \
-	   (!tp_event_has_id(&sys_dirent, &evt_dirent)))
+#define for_each_event(sys_dirent, evt_dir, evt_dirent)		\
+	while ((evt_dirent = readdir(evt_dir)) != NULL)		\
+		if (evt_dirent->d_type == DT_DIR &&		\
+		    (strcmp(evt_dirent->d_name, ".")) &&	\
+		    (strcmp(evt_dirent->d_name, "..")) &&	\
+		    (!tp_event_has_id(sys_dirent, evt_dirent)))
 
 #define MAX_EVENT_LENGTH 512
 
@@ -173,7 +173,7 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config)
 {
 	struct tracepoint_path *path = NULL;
 	DIR *sys_dir, *evt_dir;
-	struct dirent *sys_next, *evt_next, sys_dirent, evt_dirent;
+	struct dirent *sys_dirent, *evt_dirent;
 	char id_buf[24];
 	int fd;
 	u64 id;
@@ -184,18 +184,18 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config)
 	if (!sys_dir)
 		return NULL;
 
-	for_each_subsystem(sys_dir, sys_dirent, sys_next) {
+	for_each_subsystem(sys_dir, sys_dirent) {
 
 		snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path,
-			 sys_dirent.d_name);
+			 sys_dirent->d_name);
 		evt_dir = opendir(dir_path);
 		if (!evt_dir)
 			continue;
 
-		for_each_event(sys_dirent, evt_dir, evt_dirent, evt_next) {
+		for_each_event(sys_dirent, evt_dir, evt_dirent) {
 
 			snprintf(evt_path, MAXPATHLEN, "%s/%s/id", dir_path,
-				 evt_dirent.d_name);
+				 evt_dirent->d_name);
 			fd = open(evt_path, O_RDONLY);
 			if (fd < 0)
 				continue;
@@ -220,9 +220,9 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config)
 					free(path);
 					return NULL;
 				}
-				strncpy(path->system, sys_dirent.d_name,
+				strncpy(path->system, sys_dirent->d_name,
 					MAX_EVENT_LENGTH);
-				strncpy(path->name, evt_dirent.d_name,
+				strncpy(path->name, evt_dirent->d_name,
 					MAX_EVENT_LENGTH);
 				return path;
 			}
@@ -279,7 +279,24 @@ const char *event_type(int type)
 	return "unknown";
 }
 
+static int parse_events__is_name_term(struct parse_events_term *term)
+{
+	return term->type_term == PARSE_EVENTS__TERM_TYPE_NAME;
+}
 
+static char *get_config_name(struct list_head *head_terms)
+{
+	struct parse_events_term *term;
+
+	if (!head_terms)
+		return NULL;
+
+	list_for_each_entry(term, head_terms, list)
+		if (parse_events__is_name_term(term))
+			return term->val.str;
+
+	return NULL;
+}
 
 static struct perf_evsel *
 __add_event(struct list_head *list, int *idx,
@@ -333,11 +350,25 @@ static int parse_aliases(char *str, const char *names[][PERF_EVSEL__MAX_ALIASES]
 	return -1;
 }
 
+typedef int config_term_func_t(struct perf_event_attr *attr,
+			       struct parse_events_term *term,
+			       struct parse_events_error *err);
+static int config_term_common(struct perf_event_attr *attr,
+			      struct parse_events_term *term,
+			      struct parse_events_error *err);
+static int config_attr(struct perf_event_attr *attr,
+		       struct list_head *head,
+		       struct parse_events_error *err,
+		       config_term_func_t config_term);
+
 int parse_events_add_cache(struct list_head *list, int *idx,
-			   char *type, char *op_result1, char *op_result2)
+			   char *type, char *op_result1, char *op_result2,
+			   struct parse_events_error *err,
+			   struct list_head *head_config)
 {
 	struct perf_event_attr attr;
-	char name[MAX_NAME_LEN];
+	LIST_HEAD(config_terms);
+	char name[MAX_NAME_LEN], *config_name;
 	int cache_type = -1, cache_op = -1, cache_result = -1;
 	char *op_result[2] = { op_result1, op_result2 };
 	int i, n;
@@ -351,6 +382,7 @@ int parse_events_add_cache(struct list_head *list, int *idx,
 	if (cache_type == -1)
 		return -EINVAL;
 
+	config_name = get_config_name(head_config);
 	n = snprintf(name, MAX_NAME_LEN, "%s", type);
 
 	for (i = 0; (i < 2) && (op_result[i]); i++) {
@@ -391,7 +423,16 @@ int parse_events_add_cache(struct list_head *list, int *idx,
 	memset(&attr, 0, sizeof(attr));
 	attr.config = cache_type | (cache_op << 8) | (cache_result << 16);
 	attr.type = PERF_TYPE_HW_CACHE;
-	return add_event(list, idx, &attr, name, NULL);
+
+	if (head_config) {
+		if (config_attr(&attr, head_config, err,
+				config_term_common))
+			return -EINVAL;
+
+		if (get_config_terms(head_config, &config_terms))
+			return -ENOMEM;
+	}
+	return add_event(list, idx, &attr, config_name ? : name, &config_terms);
 }
 
 static void tracepoint_error(struct parse_events_error *e, int err,
@@ -540,6 +581,7 @@ static int add_tracepoint_multi_sys(struct list_head *list, int *idx,
 struct __add_bpf_event_param {
 	struct parse_events_evlist *data;
 	struct list_head *list;
+	struct list_head *head_config;
 };
 
 static int add_bpf_event(struct probe_trace_event *tev, int fd,
@@ -556,7 +598,8 @@ static int add_bpf_event(struct probe_trace_event *tev, int fd,
 		 tev->group, tev->event, fd);
 
 	err = parse_events_add_tracepoint(&new_evsels, &evlist->idx, tev->group,
-					  tev->event, evlist->error, NULL);
+					  tev->event, evlist->error,
+					  param->head_config);
 	if (err) {
 		struct perf_evsel *evsel, *tmp;
 
@@ -581,11 +624,12 @@ static int add_bpf_event(struct probe_trace_event *tev, int fd,
 
 int parse_events_load_bpf_obj(struct parse_events_evlist *data,
 			      struct list_head *list,
-			      struct bpf_object *obj)
+			      struct bpf_object *obj,
+			      struct list_head *head_config)
 {
 	int err;
 	char errbuf[BUFSIZ];
-	struct __add_bpf_event_param param = {data, list};
+	struct __add_bpf_event_param param = {data, list, head_config};
 	static bool registered_unprobe_atexit = false;
 
 	if (IS_ERR(obj) || !obj) {
@@ -631,17 +675,99 @@ errout:
 	return err;
 }
 
+static int
+parse_events_config_bpf(struct parse_events_evlist *data,
+			struct bpf_object *obj,
+			struct list_head *head_config)
+{
+	struct parse_events_term *term;
+	int error_pos;
+
+	if (!head_config || list_empty(head_config))
+		return 0;
+
+	list_for_each_entry(term, head_config, list) {
+		char errbuf[BUFSIZ];
+		int err;
+
+		if (term->type_term != PARSE_EVENTS__TERM_TYPE_USER) {
+			snprintf(errbuf, sizeof(errbuf),
+				 "Invalid config term for BPF object");
+			errbuf[BUFSIZ - 1] = '\0';
+
+			data->error->idx = term->err_term;
+			data->error->str = strdup(errbuf);
+			return -EINVAL;
+		}
+
+		err = bpf__config_obj(obj, term, data->evlist, &error_pos);
+		if (err) {
+			bpf__strerror_config_obj(obj, term, data->evlist,
+						 &error_pos, err, errbuf,
+						 sizeof(errbuf));
+			data->error->help = strdup(
+"Hint:\tValid config terms:\n"
+"     \tmap:[<arraymap>].value<indices>=[value]\n"
+"     \tmap:[<eventmap>].event<indices>=[event]\n"
+"\n"
+"     \twhere <indices> is something like [0,3...5] or [all]\n"
+"     \t(add -v to see detail)");
+			data->error->str = strdup(errbuf);
+			if (err == -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE)
+				data->error->idx = term->err_val;
+			else
+				data->error->idx = term->err_term + error_pos;
+			return err;
+		}
+	}
+	return 0;
+}
+
+/*
+ * Split config terms:
+ * perf record -e bpf.c/call-graph=fp,map:array.value[0]=1/ ...
+ *  'call-graph=fp' is 'evt config', should be applied to each
+ *  events in bpf.c.
+ * 'map:array.value[0]=1' is 'obj config', should be processed
+ * with parse_events_config_bpf.
+ *
+ * Move object config terms from the first list to obj_head_config.
+ */
+static void
+split_bpf_config_terms(struct list_head *evt_head_config,
+		       struct list_head *obj_head_config)
+{
+	struct parse_events_term *term, *temp;
+
+	/*
+	 * Currectly, all possible user config term
+	 * belong to bpf object. parse_events__is_hardcoded_term()
+	 * happends to be a good flag.
+	 *
+	 * See parse_events_config_bpf() and
+	 * config_term_tracepoint().
+	 */
+	list_for_each_entry_safe(term, temp, evt_head_config, list)
+		if (!parse_events__is_hardcoded_term(term))
+			list_move_tail(&term->list, obj_head_config);
+}
+
 int parse_events_load_bpf(struct parse_events_evlist *data,
 			  struct list_head *list,
 			  char *bpf_file_name,
-			  bool source)
+			  bool source,
+			  struct list_head *head_config)
 {
+	int err;
 	struct bpf_object *obj;
+	LIST_HEAD(obj_head_config);
+
+	if (head_config)
+		split_bpf_config_terms(head_config, &obj_head_config);
 
 	obj = bpf__prepare_load(bpf_file_name, source);
 	if (IS_ERR(obj)) {
 		char errbuf[BUFSIZ];
-		int err;
 
 		err = PTR_ERR(obj);
 
@@ -659,7 +785,18 @@ int parse_events_load_bpf(struct parse_events_evlist *data,
 		return err;
 	}
 
-	return parse_events_load_bpf_obj(data, list, obj);
+	err = parse_events_load_bpf_obj(data, list, obj, head_config);
+	if (err)
+		return err;
+	err = parse_events_config_bpf(data, obj, &obj_head_config);
+
+	/*
+	 * Caller doesn't know anything about obj_head_config,
+	 * so combine them together again before returnning.
+	 */
+	if (head_config)
+		list_splice_tail(&obj_head_config, head_config);
+	return err;
 }
 
 static int
@@ -746,9 +883,59 @@ static int check_type_val(struct parse_events_term *term,
 	return -EINVAL;
 }
 
-typedef int config_term_func_t(struct perf_event_attr *attr,
-			       struct parse_events_term *term,
-			       struct parse_events_error *err);
+/*
+ * Update according to parse-events.l
+ */
+static const char *config_term_names[__PARSE_EVENTS__TERM_TYPE_NR] = {
+	[PARSE_EVENTS__TERM_TYPE_USER]			= "<sysfs term>",
+	[PARSE_EVENTS__TERM_TYPE_CONFIG]		= "config",
+	[PARSE_EVENTS__TERM_TYPE_CONFIG1]		= "config1",
+	[PARSE_EVENTS__TERM_TYPE_CONFIG2]		= "config2",
+	[PARSE_EVENTS__TERM_TYPE_NAME]			= "name",
+	[PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD]		= "period",
+	[PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ]		= "freq",
+	[PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE]	= "branch_type",
+	[PARSE_EVENTS__TERM_TYPE_TIME]			= "time",
+	[PARSE_EVENTS__TERM_TYPE_CALLGRAPH]		= "call-graph",
+	[PARSE_EVENTS__TERM_TYPE_STACKSIZE]		= "stack-size",
+	[PARSE_EVENTS__TERM_TYPE_NOINHERIT]		= "no-inherit",
+	[PARSE_EVENTS__TERM_TYPE_INHERIT]		= "inherit",
+};
+
+static bool config_term_shrinked;
+
+static bool
+config_term_avail(int term_type, struct parse_events_error *err)
+{
+	if (term_type < 0 || term_type >= __PARSE_EVENTS__TERM_TYPE_NR) {
+		err->str = strdup("Invalid term_type");
+		return false;
+	}
+	if (!config_term_shrinked)
+		return true;
+
+	switch (term_type) {
+	case PARSE_EVENTS__TERM_TYPE_CONFIG:
+	case PARSE_EVENTS__TERM_TYPE_CONFIG1:
+	case PARSE_EVENTS__TERM_TYPE_CONFIG2:
+	case PARSE_EVENTS__TERM_TYPE_NAME:
+		return true;
+	default:
+		if (!err)
+			return false;
+
+		/* term_type is validated so indexing is safe */
+		if (asprintf(&err->str, "'%s' is not usable in 'perf stat'",
+			     config_term_names[term_type]) < 0)
+			err->str = NULL;
+		return false;
+	}
+}
+
+void parse_events__shrink_config_terms(void)
+{
+	config_term_shrinked = true;
+}
 
 static int config_term_common(struct perf_event_attr *attr,
 			      struct parse_events_term *term,
@@ -815,6 +1002,17 @@ do {									   \
 		return -EINVAL;
 	}
 
+	/*
+	 * Check term availbility after basic checking so
+	 * PARSE_EVENTS__TERM_TYPE_USER can be found and filtered.
+	 *
+	 * If check availbility at the entry of this function,
+	 * user will see "'<sysfs term>' is not usable in 'perf stat'"
+	 * if an invalid config term is provided for legacy events
+	 * (for example, instructions/badterm/...), which is confusing.
+	 */
+	if (!config_term_avail(term->type_term, err))
+		return -EINVAL;
 	return 0;
 #undef CHECK_TYPE_VAL
 }
@@ -961,23 +1159,8 @@ int parse_events_add_numeric(struct parse_events_evlist *data,
 			return -ENOMEM;
 	}
 
-	return add_event(list, &data->idx, &attr, NULL, &config_terms);
-}
-
-static int parse_events__is_name_term(struct parse_events_term *term)
-{
-	return term->type_term == PARSE_EVENTS__TERM_TYPE_NAME;
-}
-
-static char *pmu_event_name(struct list_head *head_terms)
-{
-	struct parse_events_term *term;
-
-	list_for_each_entry(term, head_terms, list)
-		if (parse_events__is_name_term(term))
-			return term->val.str;
-
-	return NULL;
+	return add_event(list, &data->idx, &attr,
+			 get_config_name(head_config), &config_terms);
 }
 
 int parse_events_add_pmu(struct parse_events_evlist *data,
@@ -1024,7 +1207,7 @@ int parse_events_add_pmu(struct parse_events_evlist *data,
 		return -EINVAL;
 
 	evsel = __add_event(list, &data->idx, &attr,
-			    pmu_event_name(head_config), pmu->cpus,
+			    get_config_name(head_config), pmu->cpus,
 			    &config_terms);
 	if (evsel) {
 		evsel->unit = info.unit;
@@ -1386,8 +1569,7 @@ int parse_events_terms(struct list_head *terms, const char *str)
 		return 0;
 	}
 
-	if (data.terms)
-		parse_events__free_terms(data.terms);
+	parse_events_terms__delete(data.terms);
 	return ret;
 }
 
@@ -1395,9 +1577,10 @@ int parse_events(struct perf_evlist *evlist, const char *str,
 		 struct parse_events_error *err)
 {
 	struct parse_events_evlist data = {
-		.list  = LIST_HEAD_INIT(data.list),
-		.idx   = evlist->nr_entries,
-		.error = err,
+		.list   = LIST_HEAD_INIT(data.list),
+		.idx    = evlist->nr_entries,
+		.error  = err,
+		.evlist = evlist,
 	};
 	int ret;
 
@@ -1629,7 +1812,7 @@ void print_tracepoint_events(const char *subsys_glob, const char *event_glob,
 			     bool name_only)
 {
 	DIR *sys_dir, *evt_dir;
-	struct dirent *sys_next, *evt_next, sys_dirent, evt_dirent;
+	struct dirent *sys_dirent, *evt_dirent;
 	char evt_path[MAXPATHLEN];
 	char dir_path[MAXPATHLEN];
 	char **evt_list = NULL;
@@ -1647,20 +1830,20 @@ restart:
 			goto out_close_sys_dir;
 	}
 
-	for_each_subsystem(sys_dir, sys_dirent, sys_next) {
+	for_each_subsystem(sys_dir, sys_dirent) {
 		if (subsys_glob != NULL &&
-		    !strglobmatch(sys_dirent.d_name, subsys_glob))
+		    !strglobmatch(sys_dirent->d_name, subsys_glob))
 			continue;
 
 		snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path,
-			 sys_dirent.d_name);
+			 sys_dirent->d_name);
 		evt_dir = opendir(dir_path);
 		if (!evt_dir)
 			continue;
 
-		for_each_event(sys_dirent, evt_dir, evt_dirent, evt_next) {
+		for_each_event(sys_dirent, evt_dir, evt_dirent) {
 			if (event_glob != NULL &&
-			    !strglobmatch(evt_dirent.d_name, event_glob))
+			    !strglobmatch(evt_dirent->d_name, event_glob))
 				continue;
 
 			if (!evt_num_known) {
@@ -1669,7 +1852,7 @@ restart:
 			}
 
 			snprintf(evt_path, MAXPATHLEN, "%s:%s",
-				 sys_dirent.d_name, evt_dirent.d_name);
+				 sys_dirent->d_name, evt_dirent->d_name);
 
 			evt_list[evt_i] = strdup(evt_path);
 			if (evt_list[evt_i] == NULL)
@@ -1722,7 +1905,7 @@ out_close_sys_dir:
 int is_valid_tracepoint(const char *event_string)
 {
 	DIR *sys_dir, *evt_dir;
-	struct dirent *sys_next, *evt_next, sys_dirent, evt_dirent;
+	struct dirent *sys_dirent, *evt_dirent;
 	char evt_path[MAXPATHLEN];
 	char dir_path[MAXPATHLEN];
 
@@ -1730,17 +1913,17 @@ int is_valid_tracepoint(const char *event_string)
 	if (!sys_dir)
 		return 0;
 
-	for_each_subsystem(sys_dir, sys_dirent, sys_next) {
+	for_each_subsystem(sys_dir, sys_dirent) {
 
 		snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path,
-			 sys_dirent.d_name);
+			 sys_dirent->d_name);
 		evt_dir = opendir(dir_path);
 		if (!evt_dir)
 			continue;
 
-		for_each_event(sys_dirent, evt_dir, evt_dirent, evt_next) {
+		for_each_event(sys_dirent, evt_dir, evt_dirent) {
 			snprintf(evt_path, MAXPATHLEN, "%s:%s",
-				 sys_dirent.d_name, evt_dirent.d_name);
+				 sys_dirent->d_name, evt_dirent->d_name);
 			if (!strcmp(evt_path, event_string)) {
 				closedir(evt_dir);
 				closedir(sys_dir);
@@ -2068,12 +2251,29 @@ int parse_events_term__clone(struct parse_events_term **new,
 			term->err_term, term->err_val);
 }
 
-void parse_events__free_terms(struct list_head *terms)
+void parse_events_terms__purge(struct list_head *terms)
 {
 	struct parse_events_term *term, *h;
 
-	list_for_each_entry_safe(term, h, terms, list)
+	list_for_each_entry_safe(term, h, terms, list) {
+		if (term->array.nr_ranges)
+			free(term->array.ranges);
+		list_del_init(&term->list);
 		free(term);
+	}
+}
+
+void parse_events_terms__delete(struct list_head *terms)
+{
+	if (!terms)
+		return;
+	parse_events_terms__purge(terms);
+	free(terms);
+}
+
+void parse_events__clear_array(struct parse_events_array *a)
+{
+	free(a->ranges);
 }
 
 void parse_events_evlist_error(struct parse_events_evlist *data,
@@ -2088,6 +2288,33 @@ void parse_events_evlist_error(struct parse_events_evlist *data,
 	WARN_ONCE(!err->str, "WARNING: failed to allocate error string");
 }
 
+static void config_terms_list(char *buf, size_t buf_sz)
+{
+	int i;
+	bool first = true;
+
+	buf[0] = '\0';
+	for (i = 0; i < __PARSE_EVENTS__TERM_TYPE_NR; i++) {
+		const char *name = config_term_names[i];
+
+		if (!config_term_avail(i, NULL))
+			continue;
+		if (!name)
+			continue;
+		if (name[0] == '<')
+			continue;
+
+		if (strlen(buf) + strlen(name) + 2 >= buf_sz)
+			return;
+
+		if (!first)
+			strcat(buf, ",");
+		else
+			first = false;
+		strcat(buf, name);
+	}
+}
+
 /*
  * Return string contains valid config terms of an event.
  * @additional_terms: For terms such as PMU sysfs terms.
@@ -2095,10 +2322,11 @@ void parse_events_evlist_error(struct parse_events_evlist *data,
 char *parse_events_formats_error_string(char *additional_terms)
 {
 	char *str;
-	static const char *static_terms = "config,config1,config2,name,"
-					  "period,freq,branch_type,time,"
-					  "call-graph,stack-size\n";
+	/* "branch_type" is the longest name */
+	char static_terms[__PARSE_EVENTS__TERM_TYPE_NR *
+			  (sizeof("branch_type") - 1)];
 
+	config_terms_list(static_terms, sizeof(static_terms));
 	/* valid terms */
 	if (additional_terms) {
 		if (asprintf(&str, "valid terms: %s,%s",
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index f1a6db107..d740c3ca9 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -22,19 +22,18 @@ struct tracepoint_path {
 	struct tracepoint_path *next;
 };
 
-extern struct tracepoint_path *tracepoint_id_to_path(u64 config);
-extern struct tracepoint_path *tracepoint_name_to_path(const char *name);
-extern bool have_tracepoints(struct list_head *evlist);
+struct tracepoint_path *tracepoint_id_to_path(u64 config);
+struct tracepoint_path *tracepoint_name_to_path(const char *name);
+bool have_tracepoints(struct list_head *evlist);
 
 const char *event_type(int type);
 
-extern int parse_events_option(const struct option *opt, const char *str,
-			       int unset);
-extern int parse_events(struct perf_evlist *evlist, const char *str,
-			struct parse_events_error *error);
-extern int parse_events_terms(struct list_head *terms, const char *str);
-extern int parse_filter(const struct option *opt, const char *str, int unset);
-extern int exclude_perf(const struct option *opt, const char *arg, int unset);
+int parse_events_option(const struct option *opt, const char *str, int unset);
+int parse_events(struct perf_evlist *evlist, const char *str,
+		 struct parse_events_error *error);
+int parse_events_terms(struct list_head *terms, const char *str);
+int parse_filter(const struct option *opt, const char *str, int unset);
+int exclude_perf(const struct option *opt, const char *arg, int unset);
 
 #define EVENTS_HELP_MAX (128*1024)
 
@@ -68,11 +67,21 @@ enum {
 	PARSE_EVENTS__TERM_TYPE_CALLGRAPH,
 	PARSE_EVENTS__TERM_TYPE_STACKSIZE,
 	PARSE_EVENTS__TERM_TYPE_NOINHERIT,
-	PARSE_EVENTS__TERM_TYPE_INHERIT
+	PARSE_EVENTS__TERM_TYPE_INHERIT,
+	__PARSE_EVENTS__TERM_TYPE_NR,
+};
+
+struct parse_events_array {
+	size_t nr_ranges;
+	struct {
+		unsigned int start;
+		size_t length;
+	} *ranges;
 };
 
 struct parse_events_term {
 	char *config;
+	struct parse_events_array array;
 	union {
 		char *str;
 		u64  num;
@@ -98,12 +107,14 @@ struct parse_events_evlist {
 	int			   idx;
 	int			   nr_groups;
 	struct parse_events_error *error;
+	struct perf_evlist	  *evlist;
 };
 
 struct parse_events_terms {
 	struct list_head *terms;
 };
 
+void parse_events__shrink_config_terms(void);
 int parse_events__is_hardcoded_term(struct parse_events_term *term);
 int parse_events_term__num(struct parse_events_term **term,
 			   int type_term, char *config, u64 num,
@@ -115,7 +126,9 @@ int parse_events_term__sym_hw(struct parse_events_term **term,
 			      char *config, unsigned idx);
 int parse_events_term__clone(struct parse_events_term **new,
 			     struct parse_events_term *term);
-void parse_events__free_terms(struct list_head *terms);
+void parse_events_terms__delete(struct list_head *terms);
+void parse_events_terms__purge(struct list_head *terms);
+void parse_events__clear_array(struct parse_events_array *a);
 int parse_events__modifier_event(struct list_head *list, char *str, bool add);
 int parse_events__modifier_group(struct list_head *list, char *event_mod);
 int parse_events_name(struct list_head *list, char *name);
@@ -126,18 +139,22 @@ int parse_events_add_tracepoint(struct list_head *list, int *idx,
 int parse_events_load_bpf(struct parse_events_evlist *data,
 			  struct list_head *list,
 			  char *bpf_file_name,
-			  bool source);
+			  bool source,
+			  struct list_head *head_config);
 /* Provide this function for perf test */
 struct bpf_object;
 int parse_events_load_bpf_obj(struct parse_events_evlist *data,
 			      struct list_head *list,
-			      struct bpf_object *obj);
+			      struct bpf_object *obj,
+			      struct list_head *head_config);
 int parse_events_add_numeric(struct parse_events_evlist *data,
 			     struct list_head *list,
 			     u32 type, u64 config,
 			     struct list_head *head_config);
 int parse_events_add_cache(struct list_head *list, int *idx,
-			   char *type, char *op_result1, char *op_result2);
+			   char *type, char *op_result1, char *op_result2,
+			   struct parse_events_error *error,
+			   struct list_head *head_config);
 int parse_events_add_breakpoint(struct list_head *list, int *idx,
 				void *ptr, char *type, u64 len);
 int parse_events_add_pmu(struct parse_events_evlist *data,
@@ -165,7 +182,7 @@ void print_symbol_events(const char *event_glob, unsigned type,
 void print_tracepoint_events(const char *subsys_glob, const char *event_glob,
 			     bool name_only);
 int print_hwcache_events(const char *event_glob, bool name_only);
-extern int is_valid_tracepoint(const char *event_string);
+int is_valid_tracepoint(const char *event_string);
 
 int valid_event_mount(const char *eventfs);
 char *parse_events_formats_error_string(char *additional_terms);
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 58c5831ff..1477fbc78 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -9,8 +9,8 @@
 %{
 #include <errno.h>
 #include "../perf.h"
-#include "parse-events-bison.h"
 #include "parse-events.h"
+#include "parse-events-bison.h"
 
 char *parse_events_get_text(yyscan_t yyscanner);
 YYSTYPE *parse_events_get_lval(yyscan_t yyscanner);
@@ -111,6 +111,7 @@ do {							\
 %x mem
 %s config
 %x event
+%x array
 
 group		[^,{}/]*[{][^}]*[}][^,{}/]*
 event_pmu	[^,{}/]+[/][^/]*[/][^,{}/]*
@@ -122,7 +123,7 @@ num_dec		[0-9]+
 num_hex		0x[a-fA-F0-9]+
 num_raw_hex	[a-fA-F0-9]+
 name		[a-zA-Z_*?][a-zA-Z0-9_*?.]*
-name_minus	[a-zA-Z_*?][a-zA-Z0-9\-_*?.]*
+name_minus	[a-zA-Z_*?][a-zA-Z0-9\-_*?.:]*
 /* If you add a modifier you need to update check_modifier() */
 modifier_event	[ukhpPGHSDI]+
 modifier_bp	[rwx]{1,3}
@@ -176,10 +177,17 @@ modifier_bp	[rwx]{1,3}
 
 }
 
+<array>{
+"]"			{ BEGIN(config); return ']'; }
+{num_dec}		{ return value(yyscanner, 10); }
+{num_hex}		{ return value(yyscanner, 16); }
+,			{ return ','; }
+"\.\.\."		{ return PE_ARRAY_RANGE; }
+}
+
 <config>{
 	/*
-	 * Please update parse_events_formats_error_string any time
-	 * new static term is added.
+	 * Please update config_term_names when new static term is added.
 	 */
 config			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG); }
 config1			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG1); }
@@ -196,6 +204,8 @@ no-inherit		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NOINHERIT); }
 ,			{ return ','; }
 "/"			{ BEGIN(INITIAL); return '/'; }
 {name_minus}		{ return str(yyscanner, PE_NAME); }
+\[all\]			{ return PE_ARRAY_ALL; }
+"["			{ BEGIN(array); return '['; }
 }
 
 <mem>{
@@ -238,6 +248,7 @@ cpu-migrations|migrations			{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COU
 alignment-faults				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_ALIGNMENT_FAULTS); }
 emulation-faults				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EMULATION_FAULTS); }
 dummy						{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); }
+bpf-output					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_BPF_OUTPUT); }
 
 	/*
 	 * We have to handle the kernel PMU event cycles-ct/cycles-t/mem-loads/mem-stores separately.
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index ad379968d..5be4a5f21 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -28,7 +28,7 @@ do { \
 	INIT_LIST_HEAD(list);         \
 } while (0)
 
-static inc_group_count(struct list_head *list,
+static void inc_group_count(struct list_head *list,
 		       struct parse_events_evlist *data)
 {
 	/* Count groups only have more than 1 members */
@@ -48,6 +48,7 @@ static inc_group_count(struct list_head *list,
 %token PE_PREFIX_MEM PE_PREFIX_RAW PE_PREFIX_GROUP
 %token PE_ERROR
 %token PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_KERNEL_PMU_EVENT
+%token PE_ARRAY_ALL PE_ARRAY_RANGE
 %type <num> PE_VALUE
 %type <num> PE_VALUE_SYM_HW
 %type <num> PE_VALUE_SYM_SW
@@ -64,6 +65,7 @@ static inc_group_count(struct list_head *list,
 %type <str> PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_KERNEL_PMU_EVENT
 %type <num> value_sym
 %type <head> event_config
+%type <head> opt_event_config
 %type <term> event_term
 %type <head> event_pmu
 %type <head> event_legacy_symbol
@@ -82,6 +84,9 @@ static inc_group_count(struct list_head *list,
 %type <head> group_def
 %type <head> group
 %type <head> groups
+%type <array> array
+%type <array> array_term
+%type <array> array_terms
 
 %union
 {
@@ -93,6 +98,7 @@ static inc_group_count(struct list_head *list,
 		char *sys;
 		char *event;
 	} tracepoint_name;
+	struct parse_events_array array;
 }
 %%
 
@@ -211,24 +217,14 @@ event_def: event_pmu |
 	   event_bpf_file
 
 event_pmu:
-PE_NAME '/' event_config '/'
+PE_NAME opt_event_config
 {
 	struct parse_events_evlist *data = _data;
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_pmu(data, list, $1, $3));
-	parse_events__free_terms($3);
-	$$ = list;
-}
-|
-PE_NAME '/' '/'
-{
-	struct parse_events_evlist *data = _data;
-	struct list_head *list;
-
-	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_pmu(data, list, $1, NULL));
+	ABORT_ON(parse_events_add_pmu(data, list, $1, $2));
+	parse_events_terms__delete($2);
 	$$ = list;
 }
 |
@@ -246,7 +242,7 @@ PE_KERNEL_PMU_EVENT sep_dc
 
 	ALLOC_LIST(list);
 	ABORT_ON(parse_events_add_pmu(data, list, "cpu", head));
-	parse_events__free_terms(head);
+	parse_events_terms__delete(head);
 	$$ = list;
 }
 |
@@ -266,7 +262,7 @@ PE_PMU_EVENT_PRE '-' PE_PMU_EVENT_SUF sep_dc
 
 	ALLOC_LIST(list);
 	ABORT_ON(parse_events_add_pmu(data, list, "cpu", head));
-	parse_events__free_terms(head);
+	parse_events_terms__delete(head);
 	$$ = list;
 }
 
@@ -285,7 +281,7 @@ value_sym '/' event_config '/'
 
 	ALLOC_LIST(list);
 	ABORT_ON(parse_events_add_numeric(data, list, type, config, $3));
-	parse_events__free_terms($3);
+	parse_events_terms__delete($3);
 	$$ = list;
 }
 |
@@ -302,33 +298,39 @@ value_sym sep_slash_dc
 }
 
 event_legacy_cache:
-PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT '-' PE_NAME_CACHE_OP_RESULT
+PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT '-' PE_NAME_CACHE_OP_RESULT opt_event_config
 {
 	struct parse_events_evlist *data = _data;
+	struct parse_events_error *error = data->error;
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_cache(list, &data->idx, $1, $3, $5));
+	ABORT_ON(parse_events_add_cache(list, &data->idx, $1, $3, $5, error, $6));
+	parse_events_terms__delete($6);
 	$$ = list;
 }
 |
-PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT
+PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT opt_event_config
 {
 	struct parse_events_evlist *data = _data;
+	struct parse_events_error *error = data->error;
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_cache(list, &data->idx, $1, $3, NULL));
+	ABORT_ON(parse_events_add_cache(list, &data->idx, $1, $3, NULL, error, $4));
+	parse_events_terms__delete($4);
 	$$ = list;
 }
 |
-PE_NAME_CACHE_TYPE
+PE_NAME_CACHE_TYPE opt_event_config
 {
 	struct parse_events_evlist *data = _data;
+	struct parse_events_error *error = data->error;
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_cache(list, &data->idx, $1, NULL, NULL));
+	ABORT_ON(parse_events_add_cache(list, &data->idx, $1, NULL, NULL, error, $2));
+	parse_events_terms__delete($2);
 	$$ = list;
 }
 
@@ -378,24 +380,7 @@ PE_PREFIX_MEM PE_VALUE sep_dc
 }
 
 event_legacy_tracepoint:
-tracepoint_name
-{
-	struct parse_events_evlist *data = _data;
-	struct parse_events_error *error = data->error;
-	struct list_head *list;
-
-	ALLOC_LIST(list);
-	if (error)
-		error->idx = @1.first_column;
-
-	if (parse_events_add_tracepoint(list, &data->idx, $1.sys, $1.event,
-					error, NULL))
-		return -1;
-
-	$$ = list;
-}
-|
-tracepoint_name '/' event_config '/'
+tracepoint_name opt_event_config
 {
 	struct parse_events_evlist *data = _data;
 	struct parse_events_error *error = data->error;
@@ -406,7 +391,7 @@ tracepoint_name '/' event_config '/'
 		error->idx = @1.first_column;
 
 	if (parse_events_add_tracepoint(list, &data->idx, $1.sys, $1.event,
-					error, $3))
+					error, $2))
 		return -1;
 
 	$$ = list;
@@ -433,49 +418,68 @@ PE_NAME ':' PE_NAME
 }
 
 event_legacy_numeric:
-PE_VALUE ':' PE_VALUE
+PE_VALUE ':' PE_VALUE opt_event_config
 {
 	struct parse_events_evlist *data = _data;
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_numeric(data, list, (u32)$1, $3, NULL));
+	ABORT_ON(parse_events_add_numeric(data, list, (u32)$1, $3, $4));
+	parse_events_terms__delete($4);
 	$$ = list;
 }
 
 event_legacy_raw:
-PE_RAW
+PE_RAW opt_event_config
 {
 	struct parse_events_evlist *data = _data;
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_numeric(data, list, PERF_TYPE_RAW, $1, NULL));
+	ABORT_ON(parse_events_add_numeric(data, list, PERF_TYPE_RAW, $1, $2));
+	parse_events_terms__delete($2);
 	$$ = list;
 }
 
 event_bpf_file:
-PE_BPF_OBJECT
+PE_BPF_OBJECT opt_event_config
 {
 	struct parse_events_evlist *data = _data;
 	struct parse_events_error *error = data->error;
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_load_bpf(data, list, $1, false));
+	ABORT_ON(parse_events_load_bpf(data, list, $1, false, $2));
+	parse_events_terms__delete($2);
 	$$ = list;
 }
 |
-PE_BPF_SOURCE
+PE_BPF_SOURCE opt_event_config
 {
 	struct parse_events_evlist *data = _data;
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_load_bpf(data, list, $1, true));
+	ABORT_ON(parse_events_load_bpf(data, list, $1, true, $2));
+	parse_events_terms__delete($2);
 	$$ = list;
 }
 
+opt_event_config:
+'/' event_config '/'
+{
+	$$ = $2;
+}
+|
+'/' '/'
+{
+	$$ = NULL;
+}
+|
+{
+	$$ = NULL;
+}
+
 start_terms: event_config
 {
 	struct parse_events_terms *data = _data;
@@ -573,6 +577,86 @@ PE_TERM
 	ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, 1, &@1, NULL));
 	$$ = term;
 }
+|
+PE_NAME array '=' PE_NAME
+{
+	struct parse_events_term *term;
+	int i;
+
+	ABORT_ON(parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER,
+					$1, $4, &@1, &@4));
+
+	term->array = $2;
+	$$ = term;
+}
+|
+PE_NAME array '=' PE_VALUE
+{
+	struct parse_events_term *term;
+
+	ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
+					$1, $4, &@1, &@4));
+	term->array = $2;
+	$$ = term;
+}
+
+array:
+'[' array_terms ']'
+{
+	$$ = $2;
+}
+|
+PE_ARRAY_ALL
+{
+	$$.nr_ranges = 0;
+	$$.ranges = NULL;
+}
+
+array_terms:
+array_terms ',' array_term
+{
+	struct parse_events_array new_array;
+
+	new_array.nr_ranges = $1.nr_ranges + $3.nr_ranges;
+	new_array.ranges = malloc(sizeof(new_array.ranges[0]) *
+				  new_array.nr_ranges);
+	ABORT_ON(!new_array.ranges);
+	memcpy(&new_array.ranges[0], $1.ranges,
+	       $1.nr_ranges * sizeof(new_array.ranges[0]));
+	memcpy(&new_array.ranges[$1.nr_ranges], $3.ranges,
+	       $3.nr_ranges * sizeof(new_array.ranges[0]));
+	free($1.ranges);
+	free($3.ranges);
+	$$ = new_array;
+}
+|
+array_term
+
+array_term:
+PE_VALUE
+{
+	struct parse_events_array array;
+
+	array.nr_ranges = 1;
+	array.ranges = malloc(sizeof(array.ranges[0]));
+	ABORT_ON(!array.ranges);
+	array.ranges[0].start = $1;
+	array.ranges[0].length = 1;
+	$$ = array;
+}
+|
+PE_VALUE PE_ARRAY_RANGE PE_VALUE
+{
+	struct parse_events_array array;
+
+	ABORT_ON($3 < $1);
+	array.nr_ranges = 1;
+	array.ranges = malloc(sizeof(array.ranges[0]));
+	ABORT_ON(!array.ranges);
+	array.ranges[0].start = $1;
+	array.ranges[0].length = $3 - $1 + 1;
+	$$ = array;
+}
 
 sep_dc: ':' |
 
diff --git a/tools/perf/util/path.c b/tools/perf/util/path.c
index 3654d964e..3bf6bf82f 100644
--- a/tools/perf/util/path.c
+++ b/tools/perf/util/path.c
@@ -41,36 +41,6 @@ static char *cleanup_path(char *path)
 	return path;
 }
 
-static char *perf_vsnpath(char *buf, size_t n, const char *fmt, va_list args)
-{
-	const char *perf_dir = get_perf_dir();
-	size_t len;
-
-	len = strlen(perf_dir);
-	if (n < len + 1)
-		goto bad;
-	memcpy(buf, perf_dir, len);
-	if (len && !is_dir_sep(perf_dir[len-1]))
-		buf[len++] = '/';
-	len += vsnprintf(buf + len, n - len, fmt, args);
-	if (len >= n)
-		goto bad;
-	return cleanup_path(buf);
-bad:
-	strlcpy(buf, bad_path, n);
-	return buf;
-}
-
-char *perf_pathdup(const char *fmt, ...)
-{
-	char path[PATH_MAX];
-	va_list args;
-	va_start(args, fmt);
-	(void)perf_vsnpath(path, sizeof(path), fmt, args);
-	va_end(args);
-	return xstrdup(path);
-}
-
 char *mkpath(const char *fmt, ...)
 {
 	va_list args;
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 37b4f5070..adef23b13 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -98,7 +98,7 @@ static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *
 	char scale[128];
 	int fd, ret = -1;
 	char path[PATH_MAX];
-	const char *lc;
+	char *lc;
 
 	snprintf(path, PATH_MAX, "%s/%s.scale", dir, name);
 
@@ -124,6 +124,17 @@ static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *
 	lc = setlocale(LC_NUMERIC, NULL);
 
 	/*
+	 * The lc string may be allocated in static storage,
+	 * so get a dynamic copy to make it survive setlocale
+	 * call below.
+	 */
+	lc = strdup(lc);
+	if (!lc) {
+		ret = -ENOMEM;
+		goto error;
+	}
+
+	/*
 	 * force to C locale to ensure kernel
 	 * scale string is converted correctly.
 	 * kernel uses default C locale.
@@ -135,6 +146,8 @@ static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *
 	/* restore locale */
 	setlocale(LC_NUMERIC, lc);
 
+	free(lc);
+
 	ret = 0;
 error:
 	close(fd);
@@ -153,7 +166,7 @@ static int perf_pmu__parse_unit(struct perf_pmu_alias *alias, char *dir, char *n
 	if (fd == -1)
 		return -1;
 
-		sret = read(fd, alias->unit, UNIT_MAX_LEN);
+	sret = read(fd, alias->unit, UNIT_MAX_LEN);
 	if (sret < 0)
 		goto error;
 
@@ -355,7 +368,7 @@ static int pmu_alias_terms(struct perf_pmu_alias *alias,
 	list_for_each_entry(term, &alias->terms, list) {
 		ret = parse_events_term__clone(&cloned, term);
 		if (ret) {
-			parse_events__free_terms(&list);
+			parse_events_terms__purge(&list);
 			return ret;
 		}
 		list_add_tail(&cloned->list, &list);
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 93996ec4b..8319fbb08 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -2179,7 +2179,7 @@ static int perf_probe_event__sprintf(const char *group, const char *event,
 		strbuf_addf(result, " in %s", module);
 
 	if (pev->nargs > 0) {
-		strbuf_addstr(result, " with");
+		strbuf_add(result, " with", 5);
 		for (i = 0; i < pev->nargs; i++) {
 			ret = synthesize_perf_probe_arg(&pev->args[i],
 							buf, 128);
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index ba926c30f..e54e7b011 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -114,49 +114,44 @@ int init_probe_symbol_maps(bool user_only);
 void exit_probe_symbol_maps(void);
 
 /* Command string to events */
-extern int parse_perf_probe_command(const char *cmd,
-				    struct perf_probe_event *pev);
-extern int parse_probe_trace_command(const char *cmd,
-				     struct probe_trace_event *tev);
+int parse_perf_probe_command(const char *cmd, struct perf_probe_event *pev);
+int parse_probe_trace_command(const char *cmd, struct probe_trace_event *tev);
 
 /* Events to command string */
-extern char *synthesize_perf_probe_command(struct perf_probe_event *pev);
-extern char *synthesize_probe_trace_command(struct probe_trace_event *tev);
-extern int synthesize_perf_probe_arg(struct perf_probe_arg *pa, char *buf,
-				     size_t len);
+char *synthesize_perf_probe_command(struct perf_probe_event *pev);
+char *synthesize_probe_trace_command(struct probe_trace_event *tev);
+int synthesize_perf_probe_arg(struct perf_probe_arg *pa, char *buf, size_t len);
 
 /* Check the perf_probe_event needs debuginfo */
-extern bool perf_probe_event_need_dwarf(struct perf_probe_event *pev);
+bool perf_probe_event_need_dwarf(struct perf_probe_event *pev);
 
 /* Release event contents */
-extern void clear_perf_probe_event(struct perf_probe_event *pev);
-extern void clear_probe_trace_event(struct probe_trace_event *tev);
+void clear_perf_probe_event(struct perf_probe_event *pev);
+void clear_probe_trace_event(struct probe_trace_event *tev);
 
 /* Command string to line-range */
-extern int parse_line_range_desc(const char *cmd, struct line_range *lr);
+int parse_line_range_desc(const char *cmd, struct line_range *lr);
 
 /* Release line range members */
-extern void line_range__clear(struct line_range *lr);
+void line_range__clear(struct line_range *lr);
 
 /* Initialize line range */
-extern int line_range__init(struct line_range *lr);
-
-extern int add_perf_probe_events(struct perf_probe_event *pevs, int npevs);
-extern int convert_perf_probe_events(struct perf_probe_event *pevs, int npevs);
-extern int apply_perf_probe_events(struct perf_probe_event *pevs, int npevs);
-extern void cleanup_perf_probe_events(struct perf_probe_event *pevs, int npevs);
-extern int del_perf_probe_events(struct strfilter *filter);
-
-extern int show_perf_probe_event(const char *group, const char *event,
-				 struct perf_probe_event *pev,
-				 const char *module, bool use_stdout);
-extern int show_perf_probe_events(struct strfilter *filter);
-extern int show_line_range(struct line_range *lr, const char *module,
-			   bool user);
-extern int show_available_vars(struct perf_probe_event *pevs, int npevs,
-			       struct strfilter *filter);
-extern int show_available_funcs(const char *module, struct strfilter *filter,
-				bool user);
+int line_range__init(struct line_range *lr);
+
+int add_perf_probe_events(struct perf_probe_event *pevs, int npevs);
+int convert_perf_probe_events(struct perf_probe_event *pevs, int npevs);
+int apply_perf_probe_events(struct perf_probe_event *pevs, int npevs);
+void cleanup_perf_probe_events(struct perf_probe_event *pevs, int npevs);
+int del_perf_probe_events(struct strfilter *filter);
+
+int show_perf_probe_event(const char *group, const char *event,
+			  struct perf_probe_event *pev,
+			  const char *module, bool use_stdout);
+int show_perf_probe_events(struct strfilter *filter);
+int show_line_range(struct line_range *lr, const char *module, bool user);
+int show_available_vars(struct perf_probe_event *pevs, int npevs,
+			struct strfilter *filter);
+int show_available_funcs(const char *module, struct strfilter *filter, bool user);
 bool arch__prefers_symtab(void);
 void arch__fix_tev_from_maps(struct perf_probe_event *pev,
 			     struct probe_trace_event *tev, struct map *map);
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 4ce5c5e18..b3bd0fba0 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -1314,18 +1314,18 @@ static int collect_variables_cb(Dwarf_Die *die_mem, void *data)
 			if (probe_conf.show_location_range) {
 				if (!externs) {
 					if (ret)
-						strbuf_addf(&buf, "[INV]\t");
+						strbuf_add(&buf, "[INV]\t", 6);
 					else
-						strbuf_addf(&buf, "[VAL]\t");
+						strbuf_add(&buf, "[VAL]\t", 6);
 				} else
-					strbuf_addf(&buf, "[EXT]\t");
+					strbuf_add(&buf, "[EXT]\t", 6);
 			}
 
 			ret2 = die_get_varname(die_mem, &buf);
 
 			if (!ret2 && probe_conf.show_location_range &&
 				!externs) {
-				strbuf_addf(&buf, "\t");
+				strbuf_addch(&buf, '\t');
 				ret2 = die_get_var_range(&af->pf.sp_die,
 							die_mem, &buf);
 			}
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index 0aec7704e..51137fccb 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -34,27 +34,25 @@ struct debuginfo {
 };
 
 /* This also tries to open distro debuginfo */
-extern struct debuginfo *debuginfo__new(const char *path);
-extern void debuginfo__delete(struct debuginfo *dbg);
+struct debuginfo *debuginfo__new(const char *path);
+void debuginfo__delete(struct debuginfo *dbg);
 
 /* Find probe_trace_events specified by perf_probe_event from debuginfo */
-extern int debuginfo__find_trace_events(struct debuginfo *dbg,
-					struct perf_probe_event *pev,
-					struct probe_trace_event **tevs);
+int debuginfo__find_trace_events(struct debuginfo *dbg,
+				 struct perf_probe_event *pev,
+				 struct probe_trace_event **tevs);
 
 /* Find a perf_probe_point from debuginfo */
-extern int debuginfo__find_probe_point(struct debuginfo *dbg,
-				       unsigned long addr,
-				       struct perf_probe_point *ppt);
+int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr,
+				struct perf_probe_point *ppt);
 
 /* Find a line range */
-extern int debuginfo__find_line_range(struct debuginfo *dbg,
-				      struct line_range *lr);
+int debuginfo__find_line_range(struct debuginfo *dbg, struct line_range *lr);
 
 /* Find available variables */
-extern int debuginfo__find_available_vars_at(struct debuginfo *dbg,
-					     struct perf_probe_event *pev,
-					     struct variable_list **vls);
+int debuginfo__find_available_vars_at(struct debuginfo *dbg,
+				      struct perf_probe_event *pev,
+				      struct variable_list **vls);
 
 /* Find a src file from a DWARF tag path */
 int get_real_path(const char *raw_path, const char *comp_dir,
diff --git a/tools/perf/util/quote.h b/tools/perf/util/quote.h
index 172889ea2..3340c9c4a 100644
--- a/tools/perf/util/quote.h
+++ b/tools/perf/util/quote.h
@@ -24,6 +24,6 @@
  * sq_quote() in a real application.
  */
 
-extern void sq_quote_argv(struct strbuf *, const char **argv, size_t maxlen);
+void sq_quote_argv(struct strbuf *, const char **argv, size_t maxlen);
 
 #endif /* __PERF_QUOTE_H */
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index 544509c15..b3aabc0d4 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -187,6 +187,9 @@ static void define_event_symbols(struct event_format *event,
 				 const char *ev_name,
 				 struct print_arg *args)
 {
+	if (args == NULL)
+		return;
+
 	switch (args->type) {
 	case PRINT_NULL:
 		break;
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index d72fafc1c..fbd05242b 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -205,6 +205,9 @@ static void define_event_symbols(struct event_format *event,
 				 const char *ev_name,
 				 struct print_arg *args)
 {
+	if (args == NULL)
+		return;
+
 	switch (args->type) {
 	case PRINT_NULL:
 		break;
@@ -1091,8 +1094,6 @@ static int python_start_script(const char *script, int argc, const char **argv)
 		goto error;
 	}
 
-	free(command_line);
-
 	set_table_handlers(tables);
 
 	if (tables->db_export_mode) {
@@ -1101,6 +1102,8 @@ static int python_start_script(const char *script, int argc, const char **argv)
 			goto error;
 	}
 
+	free(command_line);
+
 	return err;
 error:
 	Py_Finalize();
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 40b7a0d09..4abd85c63 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -240,14 +240,6 @@ static int process_event_stub(struct perf_tool *tool __maybe_unused,
 	return 0;
 }
 
-static int process_build_id_stub(struct perf_tool *tool __maybe_unused,
-				 union perf_event *event __maybe_unused,
-				 struct perf_session *session __maybe_unused)
-{
-	dump_printf(": unhandled!\n");
-	return 0;
-}
-
 static int process_finished_round_stub(struct perf_tool *tool __maybe_unused,
 				       union perf_event *event __maybe_unused,
 				       struct ordered_events *oe __maybe_unused)
@@ -260,23 +252,6 @@ static int process_finished_round(struct perf_tool *tool,
 				  union perf_event *event,
 				  struct ordered_events *oe);
 
-static int process_id_index_stub(struct perf_tool *tool __maybe_unused,
-				 union perf_event *event __maybe_unused,
-				 struct perf_session *perf_session
-				 __maybe_unused)
-{
-	dump_printf(": unhandled!\n");
-	return 0;
-}
-
-static int process_event_auxtrace_info_stub(struct perf_tool *tool __maybe_unused,
-				union perf_event *event __maybe_unused,
-				struct perf_session *session __maybe_unused)
-{
-	dump_printf(": unhandled!\n");
-	return 0;
-}
-
 static int skipn(int fd, off_t n)
 {
 	char buf[4096];
@@ -303,10 +278,9 @@ static s64 process_event_auxtrace_stub(struct perf_tool *tool __maybe_unused,
 	return event->auxtrace.size;
 }
 
-static
-int process_event_auxtrace_error_stub(struct perf_tool *tool __maybe_unused,
-				      union perf_event *event __maybe_unused,
-				      struct perf_session *session __maybe_unused)
+static int process_event_op2_stub(struct perf_tool *tool __maybe_unused,
+				  union perf_event *event __maybe_unused,
+				  struct perf_session *session __maybe_unused)
 {
 	dump_printf(": unhandled!\n");
 	return 0;
@@ -410,7 +384,7 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
 	if (tool->tracing_data == NULL)
 		tool->tracing_data = process_event_synth_tracing_data_stub;
 	if (tool->build_id == NULL)
-		tool->build_id = process_build_id_stub;
+		tool->build_id = process_event_op2_stub;
 	if (tool->finished_round == NULL) {
 		if (tool->ordered_events)
 			tool->finished_round = process_finished_round;
@@ -418,13 +392,13 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
 			tool->finished_round = process_finished_round_stub;
 	}
 	if (tool->id_index == NULL)
-		tool->id_index = process_id_index_stub;
+		tool->id_index = process_event_op2_stub;
 	if (tool->auxtrace_info == NULL)
-		tool->auxtrace_info = process_event_auxtrace_info_stub;
+		tool->auxtrace_info = process_event_op2_stub;
 	if (tool->auxtrace == NULL)
 		tool->auxtrace = process_event_auxtrace_stub;
 	if (tool->auxtrace_error == NULL)
-		tool->auxtrace_error = process_event_auxtrace_error_stub;
+		tool->auxtrace_error = process_event_op2_stub;
 	if (tool->thread_map == NULL)
 		tool->thread_map = process_event_thread_map_stub;
 	if (tool->cpu_map == NULL)
@@ -1133,12 +1107,11 @@ static struct machine *machines__find_for_cpumode(struct machines *machines,
 					       union perf_event *event,
 					       struct perf_sample *sample)
 {
-	const u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 	struct machine *machine;
 
 	if (perf_guest &&
-	    ((cpumode == PERF_RECORD_MISC_GUEST_KERNEL) ||
-	     (cpumode == PERF_RECORD_MISC_GUEST_USER))) {
+	    ((sample->cpumode == PERF_RECORD_MISC_GUEST_KERNEL) ||
+	     (sample->cpumode == PERF_RECORD_MISC_GUEST_USER))) {
 		u32 pid;
 
 		if (event->header.type == PERF_RECORD_MMAP
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index ec722346e..f5ba111cd 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -6,6 +6,7 @@
 #include "evsel.h"
 #include "evlist.h"
 #include <traceevent/event-parse.h>
+#include "mem-events.h"
 
 regex_t		parent_regex;
 const char	default_parent_pattern[] = "^sys_|^do_page_fault";
@@ -25,9 +26,19 @@ int		sort__has_parent = 0;
 int		sort__has_sym = 0;
 int		sort__has_dso = 0;
 int		sort__has_socket = 0;
+int		sort__has_thread = 0;
+int		sort__has_comm = 0;
 enum sort_mode	sort__mode = SORT_MODE__NORMAL;
 
-
+/*
+ * Replaces all occurrences of a char used with the:
+ *
+ * -t, --field-separator
+ *
+ * option, that uses a special separator character and don't pad with spaces,
+ * replacing all occurances of this separator in symbol names (and other
+ * output) with a '.' character, that thus it's the only non valid separator.
+*/
 static int repsep_snprintf(char *bf, size_t size, const char *fmt, ...)
 {
 	int n;
@@ -80,10 +91,21 @@ static int hist_entry__thread_snprintf(struct hist_entry *he, char *bf,
 			       width, width, comm ?: "");
 }
 
+static int hist_entry__thread_filter(struct hist_entry *he, int type, const void *arg)
+{
+	const struct thread *th = arg;
+
+	if (type != HIST_FILTER__THREAD)
+		return -1;
+
+	return th && he->thread != th;
+}
+
 struct sort_entry sort_thread = {
 	.se_header	= "  Pid:Command",
 	.se_cmp		= sort__thread_cmp,
 	.se_snprintf	= hist_entry__thread_snprintf,
+	.se_filter	= hist_entry__thread_filter,
 	.se_width_idx	= HISTC_THREAD,
 };
 
@@ -121,6 +143,7 @@ struct sort_entry sort_comm = {
 	.se_collapse	= sort__comm_collapse,
 	.se_sort	= sort__comm_sort,
 	.se_snprintf	= hist_entry__comm_snprintf,
+	.se_filter	= hist_entry__thread_filter,
 	.se_width_idx	= HISTC_COMM,
 };
 
@@ -170,10 +193,21 @@ static int hist_entry__dso_snprintf(struct hist_entry *he, char *bf,
 	return _hist_entry__dso_snprintf(he->ms.map, bf, size, width);
 }
 
+static int hist_entry__dso_filter(struct hist_entry *he, int type, const void *arg)
+{
+	const struct dso *dso = arg;
+
+	if (type != HIST_FILTER__DSO)
+		return -1;
+
+	return dso && (!he->ms.map || he->ms.map->dso != dso);
+}
+
 struct sort_entry sort_dso = {
 	.se_header	= "Shared Object",
 	.se_cmp		= sort__dso_cmp,
 	.se_snprintf	= hist_entry__dso_snprintf,
+	.se_filter	= hist_entry__dso_filter,
 	.se_width_idx	= HISTC_DSO,
 };
 
@@ -246,10 +280,8 @@ static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym,
 			ret += repsep_snprintf(bf + ret, size - ret, "%s", sym->name);
 			ret += repsep_snprintf(bf + ret, size - ret, "+0x%llx",
 					ip - map->unmap_ip(map, sym->start));
-			ret += repsep_snprintf(bf + ret, size - ret, "%-*s",
-				       width - ret, "");
 		} else {
-			ret += repsep_snprintf(bf + ret, size - ret, "%-*s",
+			ret += repsep_snprintf(bf + ret, size - ret, "%.*s",
 					       width - ret,
 					       sym->name);
 		}
@@ -257,14 +289,9 @@ static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym,
 		size_t len = BITS_PER_LONG / 4;
 		ret += repsep_snprintf(bf + ret, size - ret, "%-#.*llx",
 				       len, ip);
-		ret += repsep_snprintf(bf + ret, size - ret, "%-*s",
-				       width - ret, "");
 	}
 
-	if (ret > width)
-		bf[width] = '\0';
-
-	return width;
+	return ret;
 }
 
 static int hist_entry__sym_snprintf(struct hist_entry *he, char *bf,
@@ -274,46 +301,56 @@ static int hist_entry__sym_snprintf(struct hist_entry *he, char *bf,
 					 he->level, bf, size, width);
 }
 
+static int hist_entry__sym_filter(struct hist_entry *he, int type, const void *arg)
+{
+	const char *sym = arg;
+
+	if (type != HIST_FILTER__SYMBOL)
+		return -1;
+
+	return sym && (!he->ms.sym || !strstr(he->ms.sym->name, sym));
+}
+
 struct sort_entry sort_sym = {
 	.se_header	= "Symbol",
 	.se_cmp		= sort__sym_cmp,
 	.se_sort	= sort__sym_sort,
 	.se_snprintf	= hist_entry__sym_snprintf,
+	.se_filter	= hist_entry__sym_filter,
 	.se_width_idx	= HISTC_SYMBOL,
 };
 
 /* --sort srcline */
 
+static char *hist_entry__get_srcline(struct hist_entry *he)
+{
+	struct map *map = he->ms.map;
+
+	if (!map)
+		return SRCLINE_UNKNOWN;
+
+	return get_srcline(map->dso, map__rip_2objdump(map, he->ip),
+			   he->ms.sym, true);
+}
+
 static int64_t
 sort__srcline_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-	if (!left->srcline) {
-		if (!left->ms.map)
-			left->srcline = SRCLINE_UNKNOWN;
-		else {
-			struct map *map = left->ms.map;
-			left->srcline = get_srcline(map->dso,
-					   map__rip_2objdump(map, left->ip),
-						    left->ms.sym, true);
-		}
-	}
-	if (!right->srcline) {
-		if (!right->ms.map)
-			right->srcline = SRCLINE_UNKNOWN;
-		else {
-			struct map *map = right->ms.map;
-			right->srcline = get_srcline(map->dso,
-					     map__rip_2objdump(map, right->ip),
-						     right->ms.sym, true);
-		}
-	}
+	if (!left->srcline)
+		left->srcline = hist_entry__get_srcline(left);
+	if (!right->srcline)
+		right->srcline = hist_entry__get_srcline(right);
+
 	return strcmp(right->srcline, left->srcline);
 }
 
 static int hist_entry__srcline_snprintf(struct hist_entry *he, char *bf,
 					size_t size, unsigned int width)
 {
-	return repsep_snprintf(bf, size, "%-*.*s", width, width, he->srcline);
+	if (!he->srcline)
+		he->srcline = hist_entry__get_srcline(he);
+
+	return repsep_snprintf(bf, size, "%-.*s", width, he->srcline);
 }
 
 struct sort_entry sort_srcline = {
@@ -327,11 +364,14 @@ struct sort_entry sort_srcline = {
 
 static char no_srcfile[1];
 
-static char *get_srcfile(struct hist_entry *e)
+static char *hist_entry__get_srcfile(struct hist_entry *e)
 {
 	char *sf, *p;
 	struct map *map = e->ms.map;
 
+	if (!map)
+		return no_srcfile;
+
 	sf = __get_srcline(map->dso, map__rip_2objdump(map, e->ip),
 			 e->ms.sym, false, true);
 	if (!strcmp(sf, SRCLINE_UNKNOWN))
@@ -348,25 +388,21 @@ static char *get_srcfile(struct hist_entry *e)
 static int64_t
 sort__srcfile_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-	if (!left->srcfile) {
-		if (!left->ms.map)
-			left->srcfile = no_srcfile;
-		else
-			left->srcfile = get_srcfile(left);
-	}
-	if (!right->srcfile) {
-		if (!right->ms.map)
-			right->srcfile = no_srcfile;
-		else
-			right->srcfile = get_srcfile(right);
-	}
+	if (!left->srcfile)
+		left->srcfile = hist_entry__get_srcfile(left);
+	if (!right->srcfile)
+		right->srcfile = hist_entry__get_srcfile(right);
+
 	return strcmp(right->srcfile, left->srcfile);
 }
 
 static int hist_entry__srcfile_snprintf(struct hist_entry *he, char *bf,
 					size_t size, unsigned int width)
 {
-	return repsep_snprintf(bf, size, "%-*.*s", width, width, he->srcfile);
+	if (!he->srcfile)
+		he->srcfile = hist_entry__get_srcfile(he);
+
+	return repsep_snprintf(bf, size, "%-.*s", width, he->srcfile);
 }
 
 struct sort_entry sort_srcfile = {
@@ -439,10 +475,21 @@ static int hist_entry__socket_snprintf(struct hist_entry *he, char *bf,
 	return repsep_snprintf(bf, size, "%*.*d", width, width-3, he->socket);
 }
 
+static int hist_entry__socket_filter(struct hist_entry *he, int type, const void *arg)
+{
+	int sk = *(const int *)arg;
+
+	if (type != HIST_FILTER__SOCKET)
+		return -1;
+
+	return sk >= 0 && he->socket != sk;
+}
+
 struct sort_entry sort_socket = {
 	.se_header      = "Socket",
 	.se_cmp	        = sort__socket_cmp,
 	.se_snprintf    = hist_entry__socket_snprintf,
+	.se_filter      = hist_entry__socket_filter,
 	.se_width_idx	= HISTC_SOCKET,
 };
 
@@ -483,9 +530,6 @@ sort__trace_cmp(struct hist_entry *left, struct hist_entry *right)
 	if (right->trace_output == NULL)
 		right->trace_output = get_trace_output(right);
 
-	hists__new_col_len(left->hists, HISTC_TRACE, strlen(left->trace_output));
-	hists__new_col_len(right->hists, HISTC_TRACE, strlen(right->trace_output));
-
 	return strcmp(right->trace_output, left->trace_output);
 }
 
@@ -496,11 +540,11 @@ static int hist_entry__trace_snprintf(struct hist_entry *he, char *bf,
 
 	evsel = hists_to_evsel(he->hists);
 	if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
-		return scnprintf(bf, size, "%-*.*s", width, width, "N/A");
+		return scnprintf(bf, size, "%-.*s", width, "N/A");
 
 	if (he->trace_output == NULL)
 		he->trace_output = get_trace_output(he);
-	return repsep_snprintf(bf, size, "%-*.*s", width, width, he->trace_output);
+	return repsep_snprintf(bf, size, "%-.*s", width, he->trace_output);
 }
 
 struct sort_entry sort_trace = {
@@ -532,6 +576,18 @@ static int hist_entry__dso_from_snprintf(struct hist_entry *he, char *bf,
 		return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A");
 }
 
+static int hist_entry__dso_from_filter(struct hist_entry *he, int type,
+				       const void *arg)
+{
+	const struct dso *dso = arg;
+
+	if (type != HIST_FILTER__DSO)
+		return -1;
+
+	return dso && (!he->branch_info || !he->branch_info->from.map ||
+		       he->branch_info->from.map->dso != dso);
+}
+
 static int64_t
 sort__dso_to_cmp(struct hist_entry *left, struct hist_entry *right)
 {
@@ -552,6 +608,18 @@ static int hist_entry__dso_to_snprintf(struct hist_entry *he, char *bf,
 		return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A");
 }
 
+static int hist_entry__dso_to_filter(struct hist_entry *he, int type,
+				     const void *arg)
+{
+	const struct dso *dso = arg;
+
+	if (type != HIST_FILTER__DSO)
+		return -1;
+
+	return dso && (!he->branch_info || !he->branch_info->to.map ||
+		       he->branch_info->to.map->dso != dso);
+}
+
 static int64_t
 sort__sym_from_cmp(struct hist_entry *left, struct hist_entry *right)
 {
@@ -613,10 +681,35 @@ static int hist_entry__sym_to_snprintf(struct hist_entry *he, char *bf,
 	return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A");
 }
 
+static int hist_entry__sym_from_filter(struct hist_entry *he, int type,
+				       const void *arg)
+{
+	const char *sym = arg;
+
+	if (type != HIST_FILTER__SYMBOL)
+		return -1;
+
+	return sym && !(he->branch_info && he->branch_info->from.sym &&
+			strstr(he->branch_info->from.sym->name, sym));
+}
+
+static int hist_entry__sym_to_filter(struct hist_entry *he, int type,
+				       const void *arg)
+{
+	const char *sym = arg;
+
+	if (type != HIST_FILTER__SYMBOL)
+		return -1;
+
+	return sym && !(he->branch_info && he->branch_info->to.sym &&
+		        strstr(he->branch_info->to.sym->name, sym));
+}
+
 struct sort_entry sort_dso_from = {
 	.se_header	= "Source Shared Object",
 	.se_cmp		= sort__dso_from_cmp,
 	.se_snprintf	= hist_entry__dso_from_snprintf,
+	.se_filter	= hist_entry__dso_from_filter,
 	.se_width_idx	= HISTC_DSO_FROM,
 };
 
@@ -624,6 +717,7 @@ struct sort_entry sort_dso_to = {
 	.se_header	= "Target Shared Object",
 	.se_cmp		= sort__dso_to_cmp,
 	.se_snprintf	= hist_entry__dso_to_snprintf,
+	.se_filter	= hist_entry__dso_to_filter,
 	.se_width_idx	= HISTC_DSO_TO,
 };
 
@@ -631,6 +725,7 @@ struct sort_entry sort_sym_from = {
 	.se_header	= "Source Symbol",
 	.se_cmp		= sort__sym_from_cmp,
 	.se_snprintf	= hist_entry__sym_from_snprintf,
+	.se_filter	= hist_entry__sym_from_filter,
 	.se_width_idx	= HISTC_SYMBOL_FROM,
 };
 
@@ -638,6 +733,7 @@ struct sort_entry sort_sym_to = {
 	.se_header	= "Target Symbol",
 	.se_cmp		= sort__sym_to_cmp,
 	.se_snprintf	= hist_entry__sym_to_snprintf,
+	.se_filter	= hist_entry__sym_to_filter,
 	.se_width_idx	= HISTC_SYMBOL_TO,
 };
 
@@ -797,20 +893,10 @@ sort__locked_cmp(struct hist_entry *left, struct hist_entry *right)
 static int hist_entry__locked_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width)
 {
-	const char *out;
-	u64 mask = PERF_MEM_LOCK_NA;
+	char out[10];
 
-	if (he->mem_info)
-		mask = he->mem_info->data_src.mem_lock;
-
-	if (mask & PERF_MEM_LOCK_NA)
-		out = "N/A";
-	else if (mask & PERF_MEM_LOCK_LOCKED)
-		out = "Yes";
-	else
-		out = "No";
-
-	return repsep_snprintf(bf, size, "%-*s", width, out);
+	perf_mem__lck_scnprintf(out, sizeof(out), he->mem_info);
+	return repsep_snprintf(bf, size, "%.*s", width, out);
 }
 
 static int64_t
@@ -832,54 +918,12 @@ sort__tlb_cmp(struct hist_entry *left, struct hist_entry *right)
 	return (int64_t)(data_src_r.mem_dtlb - data_src_l.mem_dtlb);
 }
 
-static const char * const tlb_access[] = {
-	"N/A",
-	"HIT",
-	"MISS",
-	"L1",
-	"L2",
-	"Walker",
-	"Fault",
-};
-#define NUM_TLB_ACCESS (sizeof(tlb_access)/sizeof(const char *))
-
 static int hist_entry__tlb_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width)
 {
 	char out[64];
-	size_t sz = sizeof(out) - 1; /* -1 for null termination */
-	size_t l = 0, i;
-	u64 m = PERF_MEM_TLB_NA;
-	u64 hit, miss;
-
-	out[0] = '\0';
-
-	if (he->mem_info)
-		m = he->mem_info->data_src.mem_dtlb;
-
-	hit = m & PERF_MEM_TLB_HIT;
-	miss = m & PERF_MEM_TLB_MISS;
-
-	/* already taken care of */
-	m &= ~(PERF_MEM_TLB_HIT|PERF_MEM_TLB_MISS);
-
-	for (i = 0; m && i < NUM_TLB_ACCESS; i++, m >>= 1) {
-		if (!(m & 0x1))
-			continue;
-		if (l) {
-			strcat(out, " or ");
-			l += 4;
-		}
-		strncat(out, tlb_access[i], sz - l);
-		l += strlen(tlb_access[i]);
-	}
-	if (*out == '\0')
-		strcpy(out, "N/A");
-	if (hit)
-		strncat(out, " hit", sz - l);
-	if (miss)
-		strncat(out, " miss", sz - l);
 
+	perf_mem__tlb_scnprintf(out, sizeof(out), he->mem_info);
 	return repsep_snprintf(bf, size, "%-*s", width, out);
 }
 
@@ -902,61 +946,12 @@ sort__lvl_cmp(struct hist_entry *left, struct hist_entry *right)
 	return (int64_t)(data_src_r.mem_lvl - data_src_l.mem_lvl);
 }
 
-static const char * const mem_lvl[] = {
-	"N/A",
-	"HIT",
-	"MISS",
-	"L1",
-	"LFB",
-	"L2",
-	"L3",
-	"Local RAM",
-	"Remote RAM (1 hop)",
-	"Remote RAM (2 hops)",
-	"Remote Cache (1 hop)",
-	"Remote Cache (2 hops)",
-	"I/O",
-	"Uncached",
-};
-#define NUM_MEM_LVL (sizeof(mem_lvl)/sizeof(const char *))
-
 static int hist_entry__lvl_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width)
 {
 	char out[64];
-	size_t sz = sizeof(out) - 1; /* -1 for null termination */
-	size_t i, l = 0;
-	u64 m =  PERF_MEM_LVL_NA;
-	u64 hit, miss;
-
-	if (he->mem_info)
-		m  = he->mem_info->data_src.mem_lvl;
-
-	out[0] = '\0';
-
-	hit = m & PERF_MEM_LVL_HIT;
-	miss = m & PERF_MEM_LVL_MISS;
-
-	/* already taken care of */
-	m &= ~(PERF_MEM_LVL_HIT|PERF_MEM_LVL_MISS);
-
-	for (i = 0; m && i < NUM_MEM_LVL; i++, m >>= 1) {
-		if (!(m & 0x1))
-			continue;
-		if (l) {
-			strcat(out, " or ");
-			l += 4;
-		}
-		strncat(out, mem_lvl[i], sz - l);
-		l += strlen(mem_lvl[i]);
-	}
-	if (*out == '\0')
-		strcpy(out, "N/A");
-	if (hit)
-		strncat(out, " hit", sz - l);
-	if (miss)
-		strncat(out, " miss", sz - l);
 
+	perf_mem__lvl_scnprintf(out, sizeof(out), he->mem_info);
 	return repsep_snprintf(bf, size, "%-*s", width, out);
 }
 
@@ -979,51 +974,15 @@ sort__snoop_cmp(struct hist_entry *left, struct hist_entry *right)
 	return (int64_t)(data_src_r.mem_snoop - data_src_l.mem_snoop);
 }
 
-static const char * const snoop_access[] = {
-	"N/A",
-	"None",
-	"Miss",
-	"Hit",
-	"HitM",
-};
-#define NUM_SNOOP_ACCESS (sizeof(snoop_access)/sizeof(const char *))
-
 static int hist_entry__snoop_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width)
 {
 	char out[64];
-	size_t sz = sizeof(out) - 1; /* -1 for null termination */
-	size_t i, l = 0;
-	u64 m = PERF_MEM_SNOOP_NA;
-
-	out[0] = '\0';
-
-	if (he->mem_info)
-		m = he->mem_info->data_src.mem_snoop;
-
-	for (i = 0; m && i < NUM_SNOOP_ACCESS; i++, m >>= 1) {
-		if (!(m & 0x1))
-			continue;
-		if (l) {
-			strcat(out, " or ");
-			l += 4;
-		}
-		strncat(out, snoop_access[i], sz - l);
-		l += strlen(snoop_access[i]);
-	}
-
-	if (*out == '\0')
-		strcpy(out, "N/A");
 
+	perf_mem__snp_scnprintf(out, sizeof(out), he->mem_info);
 	return repsep_snprintf(bf, size, "%-*s", width, out);
 }
 
-static inline  u64 cl_address(u64 address)
-{
-	/* return the cacheline of the address */
-	return (address & ~(cacheline_size - 1));
-}
-
 static int64_t
 sort__dcacheline_cmp(struct hist_entry *left, struct hist_entry *right)
 {
@@ -1440,20 +1399,6 @@ struct hpp_sort_entry {
 	struct sort_entry *se;
 };
 
-bool perf_hpp__same_sort_entry(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b)
-{
-	struct hpp_sort_entry *hse_a;
-	struct hpp_sort_entry *hse_b;
-
-	if (!perf_hpp__is_sort_entry(a) || !perf_hpp__is_sort_entry(b))
-		return false;
-
-	hse_a = container_of(a, struct hpp_sort_entry, hpp);
-	hse_b = container_of(b, struct hpp_sort_entry, hpp);
-
-	return hse_a->se == hse_b->se;
-}
-
 void perf_hpp__reset_sort_width(struct perf_hpp_fmt *fmt, struct hists *hists)
 {
 	struct hpp_sort_entry *hse;
@@ -1539,8 +1484,56 @@ static int64_t __sort__hpp_sort(struct perf_hpp_fmt *fmt,
 	return sort_fn(a, b);
 }
 
+bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format)
+{
+	return format->header == __sort__hpp_header;
+}
+
+#define MK_SORT_ENTRY_CHK(key)					\
+bool perf_hpp__is_ ## key ## _entry(struct perf_hpp_fmt *fmt)	\
+{								\
+	struct hpp_sort_entry *hse;				\
+								\
+	if (!perf_hpp__is_sort_entry(fmt))			\
+		return false;					\
+								\
+	hse = container_of(fmt, struct hpp_sort_entry, hpp);	\
+	return hse->se == &sort_ ## key ;			\
+}
+
+MK_SORT_ENTRY_CHK(trace)
+MK_SORT_ENTRY_CHK(srcline)
+MK_SORT_ENTRY_CHK(srcfile)
+MK_SORT_ENTRY_CHK(thread)
+MK_SORT_ENTRY_CHK(comm)
+MK_SORT_ENTRY_CHK(dso)
+MK_SORT_ENTRY_CHK(sym)
+
+
+static bool __sort__hpp_equal(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b)
+{
+	struct hpp_sort_entry *hse_a;
+	struct hpp_sort_entry *hse_b;
+
+	if (!perf_hpp__is_sort_entry(a) || !perf_hpp__is_sort_entry(b))
+		return false;
+
+	hse_a = container_of(a, struct hpp_sort_entry, hpp);
+	hse_b = container_of(b, struct hpp_sort_entry, hpp);
+
+	return hse_a->se == hse_b->se;
+}
+
+static void hse_free(struct perf_hpp_fmt *fmt)
+{
+	struct hpp_sort_entry *hse;
+
+	hse = container_of(fmt, struct hpp_sort_entry, hpp);
+	free(hse);
+}
+
 static struct hpp_sort_entry *
-__sort_dimension__alloc_hpp(struct sort_dimension *sd)
+__sort_dimension__alloc_hpp(struct sort_dimension *sd, int level)
 {
 	struct hpp_sort_entry *hse;
 
@@ -1560,40 +1553,92 @@ __sort_dimension__alloc_hpp(struct sort_dimension *sd)
 	hse->hpp.cmp = __sort__hpp_cmp;
 	hse->hpp.collapse = __sort__hpp_collapse;
 	hse->hpp.sort = __sort__hpp_sort;
+	hse->hpp.equal = __sort__hpp_equal;
+	hse->hpp.free = hse_free;
 
 	INIT_LIST_HEAD(&hse->hpp.list);
 	INIT_LIST_HEAD(&hse->hpp.sort_list);
 	hse->hpp.elide = false;
 	hse->hpp.len = 0;
 	hse->hpp.user_len = 0;
+	hse->hpp.level = level;
 
 	return hse;
 }
 
-bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format)
+static void hpp_free(struct perf_hpp_fmt *fmt)
 {
-	return format->header == __sort__hpp_header;
+	free(fmt);
+}
+
+static struct perf_hpp_fmt *__hpp_dimension__alloc_hpp(struct hpp_dimension *hd,
+						       int level)
+{
+	struct perf_hpp_fmt *fmt;
+
+	fmt = memdup(hd->fmt, sizeof(*fmt));
+	if (fmt) {
+		INIT_LIST_HEAD(&fmt->list);
+		INIT_LIST_HEAD(&fmt->sort_list);
+		fmt->free = hpp_free;
+		fmt->level = level;
+	}
+
+	return fmt;
+}
+
+int hist_entry__filter(struct hist_entry *he, int type, const void *arg)
+{
+	struct perf_hpp_fmt *fmt;
+	struct hpp_sort_entry *hse;
+	int ret = -1;
+	int r;
+
+	perf_hpp_list__for_each_format(he->hpp_list, fmt) {
+		if (!perf_hpp__is_sort_entry(fmt))
+			continue;
+
+		hse = container_of(fmt, struct hpp_sort_entry, hpp);
+		if (hse->se->se_filter == NULL)
+			continue;
+
+		/*
+		 * hist entry is filtered if any of sort key in the hpp list
+		 * is applied.  But it should skip non-matched filter types.
+		 */
+		r = hse->se->se_filter(he, type, arg);
+		if (r >= 0) {
+			if (ret < 0)
+				ret = 0;
+			ret |= r;
+		}
+	}
+
+	return ret;
 }
 
-static int __sort_dimension__add_hpp_sort(struct sort_dimension *sd)
+static int __sort_dimension__add_hpp_sort(struct sort_dimension *sd,
+					  struct perf_hpp_list *list,
+					  int level)
 {
-	struct hpp_sort_entry *hse = __sort_dimension__alloc_hpp(sd);
+	struct hpp_sort_entry *hse = __sort_dimension__alloc_hpp(sd, level);
 
 	if (hse == NULL)
 		return -1;
 
-	perf_hpp__register_sort_field(&hse->hpp);
+	perf_hpp_list__register_sort_field(list, &hse->hpp);
 	return 0;
 }
 
-static int __sort_dimension__add_hpp_output(struct sort_dimension *sd)
+static int __sort_dimension__add_hpp_output(struct sort_dimension *sd,
+					    struct perf_hpp_list *list)
 {
-	struct hpp_sort_entry *hse = __sort_dimension__alloc_hpp(sd);
+	struct hpp_sort_entry *hse = __sort_dimension__alloc_hpp(sd, 0);
 
 	if (hse == NULL)
 		return -1;
 
-	perf_hpp__column_register(&hse->hpp);
+	perf_hpp_list__column_register(list, &hse->hpp);
 	return 0;
 }
 
@@ -1727,6 +1772,9 @@ static int __sort__hde_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 	if (hde->raw_trace)
 		goto raw_field;
 
+	if (!he->trace_output)
+		he->trace_output = get_trace_output(he);
+
 	field = hde->field;
 	namelen = strlen(field->name);
 	str = he->trace_output;
@@ -1776,6 +1824,11 @@ static int64_t __sort__hde_cmp(struct perf_hpp_fmt *fmt,
 
 	hde = container_of(fmt, struct hpp_dynamic_entry, hpp);
 
+	if (b == NULL) {
+		update_dynamic_len(hde, a);
+		return 0;
+	}
+
 	field = hde->field;
 	if (field->flags & FIELD_IS_DYNAMIC) {
 		unsigned long long dyn;
@@ -1790,9 +1843,6 @@ static int64_t __sort__hde_cmp(struct perf_hpp_fmt *fmt,
 	} else {
 		offset = field->offset;
 		size = field->size;
-
-		update_dynamic_len(hde, a);
-		update_dynamic_len(hde, b);
 	}
 
 	return memcmp(a->raw_data + offset, b->raw_data + offset, size);
@@ -1803,8 +1853,31 @@ bool perf_hpp__is_dynamic_entry(struct perf_hpp_fmt *fmt)
 	return fmt->cmp == __sort__hde_cmp;
 }
 
+static bool __sort__hde_equal(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b)
+{
+	struct hpp_dynamic_entry *hde_a;
+	struct hpp_dynamic_entry *hde_b;
+
+	if (!perf_hpp__is_dynamic_entry(a) || !perf_hpp__is_dynamic_entry(b))
+		return false;
+
+	hde_a = container_of(a, struct hpp_dynamic_entry, hpp);
+	hde_b = container_of(b, struct hpp_dynamic_entry, hpp);
+
+	return hde_a->field == hde_b->field;
+}
+
+static void hde_free(struct perf_hpp_fmt *fmt)
+{
+	struct hpp_dynamic_entry *hde;
+
+	hde = container_of(fmt, struct hpp_dynamic_entry, hpp);
+	free(hde);
+}
+
 static struct hpp_dynamic_entry *
-__alloc_dynamic_entry(struct perf_evsel *evsel, struct format_field *field)
+__alloc_dynamic_entry(struct perf_evsel *evsel, struct format_field *field,
+		      int level)
 {
 	struct hpp_dynamic_entry *hde;
 
@@ -1827,16 +1900,47 @@ __alloc_dynamic_entry(struct perf_evsel *evsel, struct format_field *field)
 	hde->hpp.cmp = __sort__hde_cmp;
 	hde->hpp.collapse = __sort__hde_cmp;
 	hde->hpp.sort = __sort__hde_cmp;
+	hde->hpp.equal = __sort__hde_equal;
+	hde->hpp.free = hde_free;
 
 	INIT_LIST_HEAD(&hde->hpp.list);
 	INIT_LIST_HEAD(&hde->hpp.sort_list);
 	hde->hpp.elide = false;
 	hde->hpp.len = 0;
 	hde->hpp.user_len = 0;
+	hde->hpp.level = level;
 
 	return hde;
 }
 
+struct perf_hpp_fmt *perf_hpp_fmt__dup(struct perf_hpp_fmt *fmt)
+{
+	struct perf_hpp_fmt *new_fmt = NULL;
+
+	if (perf_hpp__is_sort_entry(fmt)) {
+		struct hpp_sort_entry *hse, *new_hse;
+
+		hse = container_of(fmt, struct hpp_sort_entry, hpp);
+		new_hse = memdup(hse, sizeof(*hse));
+		if (new_hse)
+			new_fmt = &new_hse->hpp;
+	} else if (perf_hpp__is_dynamic_entry(fmt)) {
+		struct hpp_dynamic_entry *hde, *new_hde;
+
+		hde = container_of(fmt, struct hpp_dynamic_entry, hpp);
+		new_hde = memdup(hde, sizeof(*hde));
+		if (new_hde)
+			new_fmt = &new_hde->hpp;
+	} else {
+		new_fmt = memdup(fmt, sizeof(*fmt));
+	}
+
+	INIT_LIST_HEAD(&new_fmt->list);
+	INIT_LIST_HEAD(&new_fmt->sort_list);
+
+	return new_fmt;
+}
+
 static int parse_field_name(char *str, char **event, char **field, char **opt)
 {
 	char *event_name, *field_name, *opt_name;
@@ -1908,11 +2012,11 @@ static struct perf_evsel *find_evsel(struct perf_evlist *evlist, char *event_nam
 
 static int __dynamic_dimension__add(struct perf_evsel *evsel,
 				    struct format_field *field,
-				    bool raw_trace)
+				    bool raw_trace, int level)
 {
 	struct hpp_dynamic_entry *hde;
 
-	hde = __alloc_dynamic_entry(evsel, field);
+	hde = __alloc_dynamic_entry(evsel, field, level);
 	if (hde == NULL)
 		return -ENOMEM;
 
@@ -1922,14 +2026,14 @@ static int __dynamic_dimension__add(struct perf_evsel *evsel,
 	return 0;
 }
 
-static int add_evsel_fields(struct perf_evsel *evsel, bool raw_trace)
+static int add_evsel_fields(struct perf_evsel *evsel, bool raw_trace, int level)
 {
 	int ret;
 	struct format_field *field;
 
 	field = evsel->tp_format->format.fields;
 	while (field) {
-		ret = __dynamic_dimension__add(evsel, field, raw_trace);
+		ret = __dynamic_dimension__add(evsel, field, raw_trace, level);
 		if (ret < 0)
 			return ret;
 
@@ -1938,7 +2042,8 @@ static int add_evsel_fields(struct perf_evsel *evsel, bool raw_trace)
 	return 0;
 }
 
-static int add_all_dynamic_fields(struct perf_evlist *evlist, bool raw_trace)
+static int add_all_dynamic_fields(struct perf_evlist *evlist, bool raw_trace,
+				  int level)
 {
 	int ret;
 	struct perf_evsel *evsel;
@@ -1947,7 +2052,7 @@ static int add_all_dynamic_fields(struct perf_evlist *evlist, bool raw_trace)
 		if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
 			continue;
 
-		ret = add_evsel_fields(evsel, raw_trace);
+		ret = add_evsel_fields(evsel, raw_trace, level);
 		if (ret < 0)
 			return ret;
 	}
@@ -1955,7 +2060,7 @@ static int add_all_dynamic_fields(struct perf_evlist *evlist, bool raw_trace)
 }
 
 static int add_all_matching_fields(struct perf_evlist *evlist,
-				   char *field_name, bool raw_trace)
+				   char *field_name, bool raw_trace, int level)
 {
 	int ret = -ESRCH;
 	struct perf_evsel *evsel;
@@ -1969,14 +2074,15 @@ static int add_all_matching_fields(struct perf_evlist *evlist,
 		if (field == NULL)
 			continue;
 
-		ret = __dynamic_dimension__add(evsel, field, raw_trace);
+		ret = __dynamic_dimension__add(evsel, field, raw_trace, level);
 		if (ret < 0)
 			break;
 	}
 	return ret;
 }
 
-static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok)
+static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok,
+			     int level)
 {
 	char *str, *event_name, *field_name, *opt_name;
 	struct perf_evsel *evsel;
@@ -2006,12 +2112,12 @@ static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok)
 	}
 
 	if (!strcmp(field_name, "trace_fields")) {
-		ret = add_all_dynamic_fields(evlist, raw_trace);
+		ret = add_all_dynamic_fields(evlist, raw_trace, level);
 		goto out;
 	}
 
 	if (event_name == NULL) {
-		ret = add_all_matching_fields(evlist, field_name, raw_trace);
+		ret = add_all_matching_fields(evlist, field_name, raw_trace, level);
 		goto out;
 	}
 
@@ -2029,7 +2135,7 @@ static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok)
 	}
 
 	if (!strcmp(field_name, "*")) {
-		ret = add_evsel_fields(evsel, raw_trace);
+		ret = add_evsel_fields(evsel, raw_trace, level);
 	} else {
 		field = pevent_find_any_field(evsel->tp_format, field_name);
 		if (field == NULL) {
@@ -2038,7 +2144,7 @@ static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok)
 			return -ENOENT;
 		}
 
-		ret = __dynamic_dimension__add(evsel, field, raw_trace);
+		ret = __dynamic_dimension__add(evsel, field, raw_trace, level);
 	}
 
 out:
@@ -2046,12 +2152,14 @@ out:
 	return ret;
 }
 
-static int __sort_dimension__add(struct sort_dimension *sd)
+static int __sort_dimension__add(struct sort_dimension *sd,
+				 struct perf_hpp_list *list,
+				 int level)
 {
 	if (sd->taken)
 		return 0;
 
-	if (__sort_dimension__add_hpp_sort(sd) < 0)
+	if (__sort_dimension__add_hpp_sort(sd, list, level) < 0)
 		return -1;
 
 	if (sd->entry->se_collapse)
@@ -2062,46 +2170,63 @@ static int __sort_dimension__add(struct sort_dimension *sd)
 	return 0;
 }
 
-static int __hpp_dimension__add(struct hpp_dimension *hd)
+static int __hpp_dimension__add(struct hpp_dimension *hd,
+				struct perf_hpp_list *list,
+				int level)
 {
-	if (!hd->taken) {
-		hd->taken = 1;
+	struct perf_hpp_fmt *fmt;
 
-		perf_hpp__register_sort_field(hd->fmt);
-	}
+	if (hd->taken)
+		return 0;
+
+	fmt = __hpp_dimension__alloc_hpp(hd, level);
+	if (!fmt)
+		return -1;
+
+	hd->taken = 1;
+	perf_hpp_list__register_sort_field(list, fmt);
 	return 0;
 }
 
-static int __sort_dimension__add_output(struct sort_dimension *sd)
+static int __sort_dimension__add_output(struct perf_hpp_list *list,
+					struct sort_dimension *sd)
 {
 	if (sd->taken)
 		return 0;
 
-	if (__sort_dimension__add_hpp_output(sd) < 0)
+	if (__sort_dimension__add_hpp_output(sd, list) < 0)
 		return -1;
 
 	sd->taken = 1;
 	return 0;
 }
 
-static int __hpp_dimension__add_output(struct hpp_dimension *hd)
+static int __hpp_dimension__add_output(struct perf_hpp_list *list,
+				       struct hpp_dimension *hd)
 {
-	if (!hd->taken) {
-		hd->taken = 1;
+	struct perf_hpp_fmt *fmt;
 
-		perf_hpp__column_register(hd->fmt);
-	}
+	if (hd->taken)
+		return 0;
+
+	fmt = __hpp_dimension__alloc_hpp(hd, 0);
+	if (!fmt)
+		return -1;
+
+	hd->taken = 1;
+	perf_hpp_list__column_register(list, fmt);
 	return 0;
 }
 
 int hpp_dimension__add_output(unsigned col)
 {
 	BUG_ON(col >= PERF_HPP__MAX_INDEX);
-	return __hpp_dimension__add_output(&hpp_sort_dimensions[col]);
+	return __hpp_dimension__add_output(&perf_hpp_list, &hpp_sort_dimensions[col]);
 }
 
-static int sort_dimension__add(const char *tok,
-			       struct perf_evlist *evlist __maybe_unused)
+static int sort_dimension__add(struct perf_hpp_list *list, const char *tok,
+			       struct perf_evlist *evlist,
+			       int level)
 {
 	unsigned int i;
 
@@ -2136,9 +2261,13 @@ static int sort_dimension__add(const char *tok,
 			sort__has_dso = 1;
 		} else if (sd->entry == &sort_socket) {
 			sort__has_socket = 1;
+		} else if (sd->entry == &sort_thread) {
+			sort__has_thread = 1;
+		} else if (sd->entry == &sort_comm) {
+			sort__has_comm = 1;
 		}
 
-		return __sort_dimension__add(sd);
+		return __sort_dimension__add(sd, list, level);
 	}
 
 	for (i = 0; i < ARRAY_SIZE(hpp_sort_dimensions); i++) {
@@ -2147,7 +2276,7 @@ static int sort_dimension__add(const char *tok,
 		if (strncasecmp(tok, hd->name, strlen(tok)))
 			continue;
 
-		return __hpp_dimension__add(hd);
+		return __hpp_dimension__add(hd, list, level);
 	}
 
 	for (i = 0; i < ARRAY_SIZE(bstack_sort_dimensions); i++) {
@@ -2162,7 +2291,7 @@ static int sort_dimension__add(const char *tok,
 		if (sd->entry == &sort_sym_from || sd->entry == &sort_sym_to)
 			sort__has_sym = 1;
 
-		__sort_dimension__add(sd);
+		__sort_dimension__add(sd, list, level);
 		return 0;
 	}
 
@@ -2178,16 +2307,60 @@ static int sort_dimension__add(const char *tok,
 		if (sd->entry == &sort_mem_daddr_sym)
 			sort__has_sym = 1;
 
-		__sort_dimension__add(sd);
+		__sort_dimension__add(sd, list, level);
 		return 0;
 	}
 
-	if (!add_dynamic_entry(evlist, tok))
+	if (!add_dynamic_entry(evlist, tok, level))
 		return 0;
 
 	return -ESRCH;
 }
 
+static int setup_sort_list(struct perf_hpp_list *list, char *str,
+			   struct perf_evlist *evlist)
+{
+	char *tmp, *tok;
+	int ret = 0;
+	int level = 0;
+	int next_level = 1;
+	bool in_group = false;
+
+	do {
+		tok = str;
+		tmp = strpbrk(str, "{}, ");
+		if (tmp) {
+			if (in_group)
+				next_level = level;
+			else
+				next_level = level + 1;
+
+			if (*tmp == '{')
+				in_group = true;
+			else if (*tmp == '}')
+				in_group = false;
+
+			*tmp = '\0';
+			str = tmp + 1;
+		}
+
+		if (*tok) {
+			ret = sort_dimension__add(list, tok, evlist, level);
+			if (ret == -EINVAL) {
+				error("Invalid --sort key: `%s'", tok);
+				break;
+			} else if (ret == -ESRCH) {
+				error("Unknown --sort key: `%s'", tok);
+				break;
+			}
+		}
+
+		level = next_level;
+	} while (tmp);
+
+	return ret;
+}
+
 static const char *get_default_sort_order(struct perf_evlist *evlist)
 {
 	const char *default_sort_orders[] = {
@@ -2272,6 +2445,9 @@ static char *prefix_if_not_in(const char *pre, char *str)
 
 static char *setup_overhead(char *keys)
 {
+	if (sort__mode == SORT_MODE__DIFF)
+		return keys;
+
 	keys = prefix_if_not_in("overhead", keys);
 
 	if (symbol_conf.cumulate_callchain)
@@ -2282,7 +2458,7 @@ static char *setup_overhead(char *keys)
 
 static int __setup_sorting(struct perf_evlist *evlist)
 {
-	char *tmp, *tok, *str;
+	char *str;
 	const char *sort_keys;
 	int ret = 0;
 
@@ -2320,17 +2496,7 @@ static int __setup_sorting(struct perf_evlist *evlist)
 		}
 	}
 
-	for (tok = strtok_r(str, ", ", &tmp);
-			tok; tok = strtok_r(NULL, ", ", &tmp)) {
-		ret = sort_dimension__add(tok, evlist);
-		if (ret == -EINVAL) {
-			error("Invalid --sort key: `%s'", tok);
-			break;
-		} else if (ret == -ESRCH) {
-			error("Unknown --sort key: `%s'", tok);
-			break;
-		}
-	}
+	ret = setup_sort_list(&perf_hpp_list, str, evlist);
 
 	free(str);
 	return ret;
@@ -2341,7 +2507,7 @@ void perf_hpp__set_elide(int idx, bool elide)
 	struct perf_hpp_fmt *fmt;
 	struct hpp_sort_entry *hse;
 
-	perf_hpp__for_each_format(fmt) {
+	perf_hpp_list__for_each_format(&perf_hpp_list, fmt) {
 		if (!perf_hpp__is_sort_entry(fmt))
 			continue;
 
@@ -2401,7 +2567,7 @@ void sort__setup_elide(FILE *output)
 	struct perf_hpp_fmt *fmt;
 	struct hpp_sort_entry *hse;
 
-	perf_hpp__for_each_format(fmt) {
+	perf_hpp_list__for_each_format(&perf_hpp_list, fmt) {
 		if (!perf_hpp__is_sort_entry(fmt))
 			continue;
 
@@ -2413,7 +2579,7 @@ void sort__setup_elide(FILE *output)
 	 * It makes no sense to elide all of sort entries.
 	 * Just revert them to show up again.
 	 */
-	perf_hpp__for_each_format(fmt) {
+	perf_hpp_list__for_each_format(&perf_hpp_list, fmt) {
 		if (!perf_hpp__is_sort_entry(fmt))
 			continue;
 
@@ -2421,7 +2587,7 @@ void sort__setup_elide(FILE *output)
 			return;
 	}
 
-	perf_hpp__for_each_format(fmt) {
+	perf_hpp_list__for_each_format(&perf_hpp_list, fmt) {
 		if (!perf_hpp__is_sort_entry(fmt))
 			continue;
 
@@ -2429,7 +2595,7 @@ void sort__setup_elide(FILE *output)
 	}
 }
 
-static int output_field_add(char *tok)
+static int output_field_add(struct perf_hpp_list *list, char *tok)
 {
 	unsigned int i;
 
@@ -2439,7 +2605,7 @@ static int output_field_add(char *tok)
 		if (strncasecmp(tok, sd->name, strlen(tok)))
 			continue;
 
-		return __sort_dimension__add_output(sd);
+		return __sort_dimension__add_output(list, sd);
 	}
 
 	for (i = 0; i < ARRAY_SIZE(hpp_sort_dimensions); i++) {
@@ -2448,7 +2614,7 @@ static int output_field_add(char *tok)
 		if (strncasecmp(tok, hd->name, strlen(tok)))
 			continue;
 
-		return __hpp_dimension__add_output(hd);
+		return __hpp_dimension__add_output(list, hd);
 	}
 
 	for (i = 0; i < ARRAY_SIZE(bstack_sort_dimensions); i++) {
@@ -2457,7 +2623,7 @@ static int output_field_add(char *tok)
 		if (strncasecmp(tok, sd->name, strlen(tok)))
 			continue;
 
-		return __sort_dimension__add_output(sd);
+		return __sort_dimension__add_output(list, sd);
 	}
 
 	for (i = 0; i < ARRAY_SIZE(memory_sort_dimensions); i++) {
@@ -2466,12 +2632,32 @@ static int output_field_add(char *tok)
 		if (strncasecmp(tok, sd->name, strlen(tok)))
 			continue;
 
-		return __sort_dimension__add_output(sd);
+		return __sort_dimension__add_output(list, sd);
 	}
 
 	return -ESRCH;
 }
 
+static int setup_output_list(struct perf_hpp_list *list, char *str)
+{
+	char *tmp, *tok;
+	int ret = 0;
+
+	for (tok = strtok_r(str, ", ", &tmp);
+			tok; tok = strtok_r(NULL, ", ", &tmp)) {
+		ret = output_field_add(list, tok);
+		if (ret == -EINVAL) {
+			error("Invalid --fields key: `%s'", tok);
+			break;
+		} else if (ret == -ESRCH) {
+			error("Unknown --fields key: `%s'", tok);
+			break;
+		}
+	}
+
+	return ret;
+}
+
 static void reset_dimensions(void)
 {
 	unsigned int i;
@@ -2496,7 +2682,7 @@ bool is_strict_order(const char *order)
 
 static int __setup_output_field(void)
 {
-	char *tmp, *tok, *str, *strp;
+	char *str, *strp;
 	int ret = -EINVAL;
 
 	if (field_order == NULL)
@@ -2516,17 +2702,7 @@ static int __setup_output_field(void)
 		goto out;
 	}
 
-	for (tok = strtok_r(strp, ", ", &tmp);
-			tok; tok = strtok_r(NULL, ", ", &tmp)) {
-		ret = output_field_add(tok);
-		if (ret == -EINVAL) {
-			error("Invalid --fields key: `%s'", tok);
-			break;
-		} else if (ret == -ESRCH) {
-			error("Unknown --fields key: `%s'", tok);
-			break;
-		}
-	}
+	ret = setup_output_list(&perf_hpp_list, strp);
 
 out:
 	free(str);
@@ -2542,7 +2718,7 @@ int setup_sorting(struct perf_evlist *evlist)
 		return err;
 
 	if (parent_pattern != default_parent_pattern) {
-		err = sort_dimension__add("parent", evlist);
+		err = sort_dimension__add(&perf_hpp_list, "parent", evlist, -1);
 		if (err < 0)
 			return err;
 	}
@@ -2560,9 +2736,13 @@ int setup_sorting(struct perf_evlist *evlist)
 		return err;
 
 	/* copy sort keys to output fields */
-	perf_hpp__setup_output_field();
+	perf_hpp__setup_output_field(&perf_hpp_list);
 	/* and then copy output fields to sort keys */
-	perf_hpp__append_sort_keys();
+	perf_hpp__append_sort_keys(&perf_hpp_list);
+
+	/* setup hists-specific output fields */
+	if (perf_hpp__setup_hists_formats(&perf_hpp_list, evlist) < 0)
+		return -1;
 
 	return 0;
 }
@@ -2578,5 +2758,5 @@ void reset_output_field(void)
 	sort_order = NULL;
 
 	reset_dimensions();
-	perf_hpp__reset_output_field();
+	perf_hpp__reset_output_field(&perf_hpp_list);
 }
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 687bbb124..3f4e35998 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -32,9 +32,12 @@ extern const char default_sort_order[];
 extern regex_t ignore_callees_regex;
 extern int have_ignore_callees;
 extern int sort__need_collapse;
+extern int sort__has_dso;
 extern int sort__has_parent;
 extern int sort__has_sym;
 extern int sort__has_socket;
+extern int sort__has_thread;
+extern int sort__has_comm;
 extern enum sort_mode sort__mode;
 extern struct sort_entry sort_comm;
 extern struct sort_entry sort_dso;
@@ -94,9 +97,11 @@ struct hist_entry {
 	s32			socket;
 	s32			cpu;
 	u8			cpumode;
+	u8			depth;
 
 	/* We are added by hists__add_dummy_entry. */
 	bool			dummy;
+	bool			leaf;
 
 	char			level;
 	u8			filtered;
@@ -113,18 +118,28 @@ struct hist_entry {
 			bool	init_have_children;
 			bool	unfolded;
 			bool	has_children;
+			bool	has_no_entry;
 		};
 	};
 	char			*srcline;
 	char			*srcfile;
 	struct symbol		*parent;
-	struct rb_root		sorted_chain;
 	struct branch_info	*branch_info;
 	struct hists		*hists;
 	struct mem_info		*mem_info;
 	void			*raw_data;
 	u32			raw_size;
 	void			*trace_output;
+	struct perf_hpp_list	*hpp_list;
+	struct hist_entry	*parent_he;
+	union {
+		/* this is for hierarchical entry structure */
+		struct {
+			struct rb_root	hroot_in;
+			struct rb_root  hroot_out;
+		};				/* non-leaf entries */
+		struct rb_root	sorted_chain;	/* leaf entry has callchains */
+	};
 	struct callchain_root	callchain[0]; /* must be last member */
 };
 
@@ -160,6 +175,17 @@ static inline float hist_entry__get_percent_limit(struct hist_entry *he)
 	return period * 100.0 / total_period;
 }
 
+static inline u64 cl_address(u64 address)
+{
+	/* return the cacheline of the address */
+	return (address & ~(cacheline_size - 1));
+}
+
+static inline u64 cl_offset(u64 address)
+{
+	/* return the cacheline of the address */
+	return (address & (cacheline_size - 1));
+}
 
 enum sort_mode {
 	SORT_MODE__NORMAL,
@@ -221,6 +247,7 @@ struct sort_entry {
 	int64_t	(*se_sort)(struct hist_entry *, struct hist_entry *);
 	int	(*se_snprintf)(struct hist_entry *he, char *bf, size_t size,
 			       unsigned int width);
+	int	(*se_filter)(struct hist_entry *he, int type, const void *arg);
 	u8	se_width_idx;
 };
 
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 6ac031468..fdb719611 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -2,6 +2,7 @@
 #include "evsel.h"
 #include "stat.h"
 #include "color.h"
+#include "pmu.h"
 
 enum {
 	CTX_BIT_USER	= 1 << 0,
@@ -14,6 +15,13 @@ enum {
 
 #define NUM_CTX CTX_BIT_MAX
 
+/*
+ * AGGR_GLOBAL: Use CPU 0
+ * AGGR_SOCKET: Use first CPU of socket
+ * AGGR_CORE: Use first CPU of core
+ * AGGR_NONE: Use matching CPU
+ * AGGR_THREAD: Not supported?
+ */
 static struct stats runtime_nsecs_stats[MAX_NR_CPUS];
 static struct stats runtime_cycles_stats[NUM_CTX][MAX_NR_CPUS];
 static struct stats runtime_stalled_cycles_front_stats[NUM_CTX][MAX_NR_CPUS];
@@ -28,9 +36,15 @@ static struct stats runtime_dtlb_cache_stats[NUM_CTX][MAX_NR_CPUS];
 static struct stats runtime_cycles_in_tx_stats[NUM_CTX][MAX_NR_CPUS];
 static struct stats runtime_transaction_stats[NUM_CTX][MAX_NR_CPUS];
 static struct stats runtime_elision_stats[NUM_CTX][MAX_NR_CPUS];
+static bool have_frontend_stalled;
 
 struct stats walltime_nsecs_stats;
 
+void perf_stat__init_shadow_stats(void)
+{
+	have_frontend_stalled = pmu_have_event("cpu", "stalled-cycles-frontend");
+}
+
 static int evsel_context(struct perf_evsel *evsel)
 {
 	int ctx = 0;
@@ -137,9 +151,9 @@ static const char *get_ratio_color(enum grc_type type, double ratio)
 	return color;
 }
 
-static void print_stalled_cycles_frontend(FILE *out, int cpu,
-					  struct perf_evsel *evsel
-					  __maybe_unused, double avg)
+static void print_stalled_cycles_frontend(int cpu,
+					  struct perf_evsel *evsel, double avg,
+					  struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -152,14 +166,16 @@ static void print_stalled_cycles_frontend(FILE *out, int cpu,
 
 	color = get_ratio_color(GRC_STALLED_CYCLES_FE, ratio);
 
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " frontend cycles idle   ");
+	if (ratio)
+		out->print_metric(out->ctx, color, "%7.2f%%", "frontend cycles idle",
+				  ratio);
+	else
+		out->print_metric(out->ctx, NULL, NULL, "frontend cycles idle", 0);
 }
 
-static void print_stalled_cycles_backend(FILE *out, int cpu,
-					 struct perf_evsel *evsel
-					 __maybe_unused, double avg)
+static void print_stalled_cycles_backend(int cpu,
+					 struct perf_evsel *evsel, double avg,
+					 struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -172,14 +188,13 @@ static void print_stalled_cycles_backend(FILE *out, int cpu,
 
 	color = get_ratio_color(GRC_STALLED_CYCLES_BE, ratio);
 
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " backend  cycles idle   ");
+	out->print_metric(out->ctx, color, "%6.2f%%", "backend cycles idle", ratio);
 }
 
-static void print_branch_misses(FILE *out, int cpu,
-				struct perf_evsel *evsel __maybe_unused,
-				double avg)
+static void print_branch_misses(int cpu,
+				struct perf_evsel *evsel,
+				double avg,
+				struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -192,14 +207,13 @@ static void print_branch_misses(FILE *out, int cpu,
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
 
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " of all branches        ");
+	out->print_metric(out->ctx, color, "%7.2f%%", "of all branches", ratio);
 }
 
-static void print_l1_dcache_misses(FILE *out, int cpu,
-				   struct perf_evsel *evsel __maybe_unused,
-				   double avg)
+static void print_l1_dcache_misses(int cpu,
+				   struct perf_evsel *evsel,
+				   double avg,
+				   struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -212,14 +226,13 @@ static void print_l1_dcache_misses(FILE *out, int cpu,
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
 
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " of all L1-dcache hits  ");
+	out->print_metric(out->ctx, color, "%7.2f%%", "of all L1-dcache hits", ratio);
 }
 
-static void print_l1_icache_misses(FILE *out, int cpu,
-				   struct perf_evsel *evsel __maybe_unused,
-				   double avg)
+static void print_l1_icache_misses(int cpu,
+				   struct perf_evsel *evsel,
+				   double avg,
+				   struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -231,15 +244,13 @@ static void print_l1_icache_misses(FILE *out, int cpu,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " of all L1-icache hits  ");
+	out->print_metric(out->ctx, color, "%7.2f%%", "of all L1-icache hits", ratio);
 }
 
-static void print_dtlb_cache_misses(FILE *out, int cpu,
-				    struct perf_evsel *evsel __maybe_unused,
-				    double avg)
+static void print_dtlb_cache_misses(int cpu,
+				    struct perf_evsel *evsel,
+				    double avg,
+				    struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -251,15 +262,13 @@ static void print_dtlb_cache_misses(FILE *out, int cpu,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " of all dTLB cache hits ");
+	out->print_metric(out->ctx, color, "%7.2f%%", "of all dTLB cache hits", ratio);
 }
 
-static void print_itlb_cache_misses(FILE *out, int cpu,
-				    struct perf_evsel *evsel __maybe_unused,
-				    double avg)
+static void print_itlb_cache_misses(int cpu,
+				    struct perf_evsel *evsel,
+				    double avg,
+				    struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -271,15 +280,13 @@ static void print_itlb_cache_misses(FILE *out, int cpu,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " of all iTLB cache hits ");
+	out->print_metric(out->ctx, color, "%7.2f%%", "of all iTLB cache hits", ratio);
 }
 
-static void print_ll_cache_misses(FILE *out, int cpu,
-				  struct perf_evsel *evsel __maybe_unused,
-				  double avg)
+static void print_ll_cache_misses(int cpu,
+				  struct perf_evsel *evsel,
+				  double avg,
+				  struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -291,15 +298,15 @@ static void print_ll_cache_misses(FILE *out, int cpu,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " of all LL-cache hits   ");
+	out->print_metric(out->ctx, color, "%7.2f%%", "of all LL-cache hits", ratio);
 }
 
-void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
-				   double avg, int cpu, enum aggr_mode aggr)
+void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
+				   double avg, int cpu,
+				   struct perf_stat_output_ctx *out)
 {
+	void *ctxp = out->ctx;
+	print_metric_t print_metric = out->print_metric;
 	double total, ratio = 0.0, total2;
 	int ctx = evsel_context(evsel);
 
@@ -307,119 +314,145 @@ void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
 		total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
 		if (total) {
 			ratio = avg / total;
-			fprintf(out, " #   %5.2f  insns per cycle        ", ratio);
+			print_metric(ctxp, NULL, "%7.2f ",
+					"insn per cycle", ratio);
 		} else {
-			fprintf(out, "                                   ");
+			print_metric(ctxp, NULL, NULL, "insn per cycle", 0);
 		}
 		total = avg_stats(&runtime_stalled_cycles_front_stats[ctx][cpu]);
 		total = max(total, avg_stats(&runtime_stalled_cycles_back_stats[ctx][cpu]));
 
 		if (total && avg) {
+			out->new_line(ctxp);
 			ratio = total / avg;
-			fprintf(out, "\n");
-			if (aggr == AGGR_NONE)
-				fprintf(out, "        ");
-			fprintf(out, "                                                  #   %5.2f  stalled cycles per insn", ratio);
+			print_metric(ctxp, NULL, "%7.2f ",
+					"stalled cycles per insn",
+					ratio);
+		} else if (have_frontend_stalled) {
+			print_metric(ctxp, NULL, NULL,
+				     "stalled cycles per insn", 0);
 		}
-
-	} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES) &&
-			runtime_branches_stats[ctx][cpu].n != 0) {
-		print_branch_misses(out, cpu, evsel, avg);
+	} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) {
+		if (runtime_branches_stats[ctx][cpu].n != 0)
+			print_branch_misses(cpu, evsel, avg, out);
+		else
+			print_metric(ctxp, NULL, NULL, "of all branches", 0);
 	} else if (
 		evsel->attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1D |
 					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
-					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
-			runtime_l1_dcache_stats[ctx][cpu].n != 0) {
-		print_l1_dcache_misses(out, cpu, evsel, avg);
+					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+		if (runtime_l1_dcache_stats[ctx][cpu].n != 0)
+			print_l1_dcache_misses(cpu, evsel, avg, out);
+		else
+			print_metric(ctxp, NULL, NULL, "of all L1-dcache hits", 0);
 	} else if (
 		evsel->attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1I |
 					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
-					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
-			runtime_l1_icache_stats[ctx][cpu].n != 0) {
-		print_l1_icache_misses(out, cpu, evsel, avg);
+					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+		if (runtime_l1_icache_stats[ctx][cpu].n != 0)
+			print_l1_icache_misses(cpu, evsel, avg, out);
+		else
+			print_metric(ctxp, NULL, NULL, "of all L1-icache hits", 0);
 	} else if (
 		evsel->attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_DTLB |
 					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
-					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
-			runtime_dtlb_cache_stats[ctx][cpu].n != 0) {
-		print_dtlb_cache_misses(out, cpu, evsel, avg);
+					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+		if (runtime_dtlb_cache_stats[ctx][cpu].n != 0)
+			print_dtlb_cache_misses(cpu, evsel, avg, out);
+		else
+			print_metric(ctxp, NULL, NULL, "of all dTLB cache hits", 0);
 	} else if (
 		evsel->attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_ITLB |
 					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
-					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
-			runtime_itlb_cache_stats[ctx][cpu].n != 0) {
-		print_itlb_cache_misses(out, cpu, evsel, avg);
+					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+		if (runtime_itlb_cache_stats[ctx][cpu].n != 0)
+			print_itlb_cache_misses(cpu, evsel, avg, out);
+		else
+			print_metric(ctxp, NULL, NULL, "of all iTLB cache hits", 0);
 	} else if (
 		evsel->attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_LL |
 					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
-					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
-			runtime_ll_cache_stats[ctx][cpu].n != 0) {
-		print_ll_cache_misses(out, cpu, evsel, avg);
-	} else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES) &&
-			runtime_cacherefs_stats[ctx][cpu].n != 0) {
+					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+		if (runtime_ll_cache_stats[ctx][cpu].n != 0)
+			print_ll_cache_misses(cpu, evsel, avg, out);
+		else
+			print_metric(ctxp, NULL, NULL, "of all LL-cache hits", 0);
+	} else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES)) {
 		total = avg_stats(&runtime_cacherefs_stats[ctx][cpu]);
 
 		if (total)
 			ratio = avg * 100 / total;
 
-		fprintf(out, " # %8.3f %% of all cache refs    ", ratio);
-
+		if (runtime_cacherefs_stats[ctx][cpu].n != 0)
+			print_metric(ctxp, NULL, "%8.3f %%",
+				     "of all cache refs", ratio);
+		else
+			print_metric(ctxp, NULL, NULL, "of all cache refs", 0);
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) {
-		print_stalled_cycles_frontend(out, cpu, evsel, avg);
+		print_stalled_cycles_frontend(cpu, evsel, avg, out);
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) {
-		print_stalled_cycles_backend(out, cpu, evsel, avg);
+		print_stalled_cycles_backend(cpu, evsel, avg, out);
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) {
 		total = avg_stats(&runtime_nsecs_stats[cpu]);
 
 		if (total) {
 			ratio = avg / total;
-			fprintf(out, " # %8.3f GHz                    ", ratio);
+			print_metric(ctxp, NULL, "%8.3f", "GHz", ratio);
 		} else {
-			fprintf(out, "                                   ");
+			print_metric(ctxp, NULL, NULL, "Ghz", 0);
 		}
 	} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX)) {
 		total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
 		if (total)
-			fprintf(out,
-				" #   %5.2f%% transactional cycles   ",
-				100.0 * (avg / total));
+			print_metric(ctxp, NULL,
+					"%7.2f%%", "transactional cycles",
+					100.0 * (avg / total));
+		else
+			print_metric(ctxp, NULL, NULL, "transactional cycles",
+				     0);
 	} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX_CP)) {
 		total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
 		total2 = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
 		if (total2 < avg)
 			total2 = avg;
 		if (total)
-			fprintf(out,
-				" #   %5.2f%% aborted cycles         ",
+			print_metric(ctxp, NULL, "%7.2f%%", "aborted cycles",
 				100.0 * ((total2-avg) / total));
-	} else if (perf_stat_evsel__is(evsel, TRANSACTION_START) &&
-		   runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
+		else
+			print_metric(ctxp, NULL, NULL, "aborted cycles", 0);
+	} else if (perf_stat_evsel__is(evsel, TRANSACTION_START)) {
 		total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
 
 		if (avg)
 			ratio = total / avg;
 
-		fprintf(out, " # %8.0f cycles / transaction   ", ratio);
-	} else if (perf_stat_evsel__is(evsel, ELISION_START) &&
-		   runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
+		if (runtime_cycles_in_tx_stats[ctx][cpu].n != 0)
+			print_metric(ctxp, NULL, "%8.0f",
+				     "cycles / transaction", ratio);
+		else
+			print_metric(ctxp, NULL, NULL, "cycles / transaction",
+				     0);
+	} else if (perf_stat_evsel__is(evsel, ELISION_START)) {
 		total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
 
 		if (avg)
 			ratio = total / avg;
 
-		fprintf(out, " # %8.0f cycles / elision       ", ratio);
+		print_metric(ctxp, NULL, "%8.0f", "cycles / elision", ratio);
 	} else if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK)) {
 		if ((ratio = avg_stats(&walltime_nsecs_stats)) != 0)
-			fprintf(out, " # %8.3f CPUs utilized          ", avg / ratio);
+			print_metric(ctxp, NULL, "%8.3f", "CPUs utilized",
+				     avg / ratio);
 		else
-			fprintf(out, "                                   ");
+			print_metric(ctxp, NULL, NULL, "CPUs utilized", 0);
 	} else if (runtime_nsecs_stats[cpu].n != 0) {
 		char unit = 'M';
+		char unit_buf[10];
 
 		total = avg_stats(&runtime_nsecs_stats[cpu]);
 
@@ -429,9 +462,9 @@ void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
 			ratio *= 1000;
 			unit = 'K';
 		}
-
-		fprintf(out, " # %8.3f %c/sec                  ", ratio, unit);
+		snprintf(unit_buf, sizeof(unit_buf), "%c/sec", unit);
+		print_metric(ctxp, NULL, "%8.3f", unit_buf, ratio);
 	} else {
-		fprintf(out, "                                   ");
+		print_metric(ctxp, NULL, NULL, NULL, 0);
 	}
 }
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index afb0c45eb..4d9b481cf 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -97,7 +97,7 @@ void perf_stat_evsel_id_init(struct perf_evsel *evsel)
 	}
 }
 
-void perf_evsel__reset_stat_priv(struct perf_evsel *evsel)
+static void perf_evsel__reset_stat_priv(struct perf_evsel *evsel)
 {
 	int i;
 	struct perf_stat_evsel *ps = evsel->priv;
@@ -108,7 +108,7 @@ void perf_evsel__reset_stat_priv(struct perf_evsel *evsel)
 	perf_stat_evsel_id_init(evsel);
 }
 
-int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
+static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
 {
 	evsel->priv = zalloc(sizeof(struct perf_stat_evsel));
 	if (evsel->priv == NULL)
@@ -117,13 +117,13 @@ int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
 	return 0;
 }
 
-void perf_evsel__free_stat_priv(struct perf_evsel *evsel)
+static void perf_evsel__free_stat_priv(struct perf_evsel *evsel)
 {
 	zfree(&evsel->priv);
 }
 
-int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel,
-				      int ncpus, int nthreads)
+static int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel,
+					     int ncpus, int nthreads)
 {
 	struct perf_counts *counts;
 
@@ -134,13 +134,13 @@ int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel,
 	return counts ? 0 : -ENOMEM;
 }
 
-void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel)
+static void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel)
 {
 	perf_counts__delete(evsel->prev_raw_counts);
 	evsel->prev_raw_counts = NULL;
 }
 
-int perf_evsel__alloc_stats(struct perf_evsel *evsel, bool alloc_raw)
+static int perf_evsel__alloc_stats(struct perf_evsel *evsel, bool alloc_raw)
 {
 	int ncpus = perf_evsel__nr_cpus(evsel);
 	int nthreads = thread_map__nr(evsel->threads);
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 086f4e128..0150e786c 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -68,21 +68,23 @@ void perf_stat_evsel_id_init(struct perf_evsel *evsel);
 
 extern struct stats walltime_nsecs_stats;
 
+typedef void (*print_metric_t)(void *ctx, const char *color, const char *unit,
+			       const char *fmt, double val);
+typedef void (*new_line_t )(void *ctx);
+
+void perf_stat__init_shadow_stats(void);
 void perf_stat__reset_shadow_stats(void);
 void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
 				    int cpu);
-void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
-				   double avg, int cpu, enum aggr_mode aggr);
-
-void perf_evsel__reset_stat_priv(struct perf_evsel *evsel);
-int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel);
-void perf_evsel__free_stat_priv(struct perf_evsel *evsel);
-
-int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel,
-				      int ncpus, int nthreads);
-void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel);
+struct perf_stat_output_ctx {
+	void *ctx;
+	print_metric_t print_metric;
+	new_line_t new_line;
+};
 
-int perf_evsel__alloc_stats(struct perf_evsel *evsel, bool alloc_raw);
+void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
+				   double avg, int cpu,
+				   struct perf_stat_output_ctx *out);
 
 int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw);
 void perf_evlist__free_stats(struct perf_evlist *evlist);
diff --git a/tools/perf/util/strbuf.c b/tools/perf/util/strbuf.c
index 25671fa16..8fb73295e 100644
--- a/tools/perf/util/strbuf.c
+++ b/tools/perf/util/strbuf.c
@@ -51,28 +51,11 @@ void strbuf_grow(struct strbuf *sb, size_t extra)
 	ALLOC_GROW(sb->buf, sb->len + extra + 1, sb->alloc);
 }
 
-static void strbuf_splice(struct strbuf *sb, size_t pos, size_t len,
-				   const void *data, size_t dlen)
+void strbuf_addch(struct strbuf *sb, int c)
 {
-	if (pos + len < pos)
-		die("you want to use way too much memory");
-	if (pos > sb->len)
-		die("`pos' is too far after the end of the buffer");
-	if (pos + len > sb->len)
-		die("`pos + len' is too far after the end of the buffer");
-
-	if (dlen >= len)
-		strbuf_grow(sb, dlen - len);
-	memmove(sb->buf + pos + dlen,
-			sb->buf + pos + len,
-			sb->len - pos - len);
-	memcpy(sb->buf + pos, data, dlen);
-	strbuf_setlen(sb, sb->len + dlen - len);
-}
-
-void strbuf_remove(struct strbuf *sb, size_t pos, size_t len)
-{
-	strbuf_splice(sb, pos, len, NULL, 0);
+	strbuf_grow(sb, 1);
+	sb->buf[sb->len++] = c;
+	sb->buf[sb->len] = '\0';
 }
 
 void strbuf_add(struct strbuf *sb, const void *data, size_t len)
@@ -82,7 +65,7 @@ void strbuf_add(struct strbuf *sb, const void *data, size_t len)
 	strbuf_setlen(sb, sb->len + len);
 }
 
-void strbuf_addv(struct strbuf *sb, const char *fmt, va_list ap)
+static void strbuf_addv(struct strbuf *sb, const char *fmt, va_list ap)
 {
 	int len;
 	va_list ap_saved;
diff --git a/tools/perf/util/strbuf.h b/tools/perf/util/strbuf.h
index 529f2f035..ab9be0fbb 100644
--- a/tools/perf/util/strbuf.h
+++ b/tools/perf/util/strbuf.h
@@ -51,16 +51,16 @@ struct strbuf {
 #define STRBUF_INIT  { 0, 0, strbuf_slopbuf }
 
 /*----- strbuf life cycle -----*/
-extern void strbuf_init(struct strbuf *buf, ssize_t hint);
-extern void strbuf_release(struct strbuf *);
-extern char *strbuf_detach(struct strbuf *, size_t *);
+void strbuf_init(struct strbuf *buf, ssize_t hint);
+void strbuf_release(struct strbuf *buf);
+char *strbuf_detach(struct strbuf *buf, size_t *);
 
 /*----- strbuf size related -----*/
 static inline ssize_t strbuf_avail(const struct strbuf *sb) {
 	return sb->alloc ? sb->alloc - sb->len - 1 : 0;
 }
 
-extern void strbuf_grow(struct strbuf *, size_t);
+void strbuf_grow(struct strbuf *buf, size_t);
 
 static inline void strbuf_setlen(struct strbuf *sb, size_t len) {
 	if (!sb->alloc)
@@ -71,24 +71,17 @@ static inline void strbuf_setlen(struct strbuf *sb, size_t len) {
 }
 
 /*----- add data in your buffer -----*/
-static inline void strbuf_addch(struct strbuf *sb, int c) {
-	strbuf_grow(sb, 1);
-	sb->buf[sb->len++] = c;
-	sb->buf[sb->len] = '\0';
-}
-
-extern void strbuf_remove(struct strbuf *, size_t pos, size_t len);
+void strbuf_addch(struct strbuf *sb, int c);
 
-extern void strbuf_add(struct strbuf *, const void *, size_t);
+void strbuf_add(struct strbuf *buf, const void *, size_t);
 static inline void strbuf_addstr(struct strbuf *sb, const char *s) {
 	strbuf_add(sb, s, strlen(s));
 }
 
 __attribute__((format(printf,2,3)))
-extern void strbuf_addf(struct strbuf *sb, const char *fmt, ...);
-extern void strbuf_addv(struct strbuf *sb, const char *fmt, va_list ap);
+void strbuf_addf(struct strbuf *sb, const char *fmt, ...);
 
 /* XXX: if read fails, any partial read is undone */
-extern ssize_t strbuf_read(struct strbuf *, int fd, ssize_t hint);
+ssize_t strbuf_read(struct strbuf *, int fd, ssize_t hint);
 
 #endif /* __PERF_STRBUF_H */
diff --git a/tools/perf/util/svghelper.h b/tools/perf/util/svghelper.h
index 9292a5291..946fdf2db 100644
--- a/tools/perf/util/svghelper.h
+++ b/tools/perf/util/svghelper.h
@@ -3,32 +3,31 @@
 
 #include <linux/types.h>
 
-extern void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end);
-extern void svg_ubox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges);
-extern void svg_lbox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges);
-extern void svg_fbox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges);
-extern void svg_box(int Yslot, u64 start, u64 end, const char *type);
-extern void svg_blocked(int Yslot, int cpu, u64 start, u64 end, const char *backtrace);
-extern void svg_running(int Yslot, int cpu, u64 start, u64 end, const char *backtrace);
-extern void svg_waiting(int Yslot, int cpu, u64 start, u64 end, const char *backtrace);
-extern void svg_cpu_box(int cpu, u64 max_frequency, u64 turbo_frequency);
-
-
-extern void svg_process(int cpu, u64 start, u64 end, int pid, const char *name, const char *backtrace);
-extern void svg_cstate(int cpu, u64 start, u64 end, int type);
-extern void svg_pstate(int cpu, u64 start, u64 end, u64 freq);
-
-
-extern void svg_time_grid(double min_thickness);
-extern void svg_io_legenda(void);
-extern void svg_legenda(void);
-extern void svg_wakeline(u64 start, int row1, int row2, const char *backtrace);
-extern void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc2, const char *backtrace);
-extern void svg_interrupt(u64 start, int row, const char *backtrace);
-extern void svg_text(int Yslot, u64 start, const char *text);
-extern void svg_close(void);
-extern int svg_build_topology_map(char *sib_core, int sib_core_nr,
-				  char *sib_thr, int sib_thr_nr);
+void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end);
+void svg_ubox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges);
+void svg_lbox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges);
+void svg_fbox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges);
+void svg_box(int Yslot, u64 start, u64 end, const char *type);
+void svg_blocked(int Yslot, int cpu, u64 start, u64 end, const char *backtrace);
+void svg_running(int Yslot, int cpu, u64 start, u64 end, const char *backtrace);
+void svg_waiting(int Yslot, int cpu, u64 start, u64 end, const char *backtrace);
+void svg_cpu_box(int cpu, u64 max_frequency, u64 turbo_frequency);
+
+
+void svg_process(int cpu, u64 start, u64 end, int pid, const char *name, const char *backtrace);
+void svg_cstate(int cpu, u64 start, u64 end, int type);
+void svg_pstate(int cpu, u64 start, u64 end, u64 freq);
+
+
+void svg_time_grid(double min_thickness);
+void svg_io_legenda(void);
+void svg_legenda(void);
+void svg_wakeline(u64 start, int row1, int row2, const char *backtrace);
+void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc2, const char *backtrace);
+void svg_interrupt(u64 start, int row, const char *backtrace);
+void svg_text(int Yslot, u64 start, const char *text);
+void svg_close(void);
+int svg_build_topology_map(char *sib_core, int sib_core_nr, char *sib_thr, int sib_thr_nr);
 
 extern int svg_page_width;
 extern u64 svg_highlight;
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 562b8ebea..bc229a74c 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -6,6 +6,7 @@
 #include <inttypes.h>
 
 #include "symbol.h"
+#include "demangle-java.h"
 #include "machine.h"
 #include "vdso.h"
 #include <symbol/kallsyms.h>
@@ -792,6 +793,7 @@ int dso__load_sym(struct dso *dso, struct map *map,
 	uint32_t idx;
 	GElf_Ehdr ehdr;
 	GElf_Shdr shdr;
+	GElf_Shdr tshdr;
 	Elf_Data *syms, *opddata = NULL;
 	GElf_Sym sym;
 	Elf_Scn *sec, *sec_strndx;
@@ -831,6 +833,9 @@ int dso__load_sym(struct dso *dso, struct map *map,
 	sec = syms_ss->symtab;
 	shdr = syms_ss->symshdr;
 
+	if (elf_section_by_name(elf, &ehdr, &tshdr, ".text", NULL))
+		dso->text_offset = tshdr.sh_addr - tshdr.sh_offset;
+
 	if (runtime_ss->opdsec)
 		opddata = elf_rawdata(runtime_ss->opdsec, NULL);
 
@@ -879,12 +884,8 @@ int dso__load_sym(struct dso *dso, struct map *map,
 	 * Handle any relocation of vdso necessary because older kernels
 	 * attempted to prelink vdso to its virtual address.
 	 */
-	if (dso__is_vdso(dso)) {
-		GElf_Shdr tshdr;
-
-		if (elf_section_by_name(elf, &ehdr, &tshdr, ".text", NULL))
-			map->reloc = map->start - tshdr.sh_addr + tshdr.sh_offset;
-	}
+	if (dso__is_vdso(dso))
+		map->reloc = map->start - dso->text_offset;
 
 	dso->adjust_symbols = runtime_ss->adjust_symbols || ref_reloc(kmap);
 	/*
@@ -1077,6 +1078,8 @@ new_symbol:
 				demangle_flags = DMGL_PARAMS | DMGL_ANSI;
 
 			demangled = bfd_demangle(NULL, elf_name, demangle_flags);
+			if (demangled == NULL)
+				demangled = java_demangle_sym(elf_name, JAVA_DEMANGLE_NORET);
 			if (demangled != NULL)
 				elf_name = demangled;
 		}
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index ab02209a7..e7588dc91 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1466,7 +1466,8 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 	 * Read the build id if possible. This is required for
 	 * DSO_BINARY_TYPE__BUILDID_DEBUGINFO to work
 	 */
-	if (filename__read_build_id(dso->long_name, build_id, BUILD_ID_SIZE) > 0)
+	if (is_regular_file(name) &&
+	    filename__read_build_id(dso->long_name, build_id, BUILD_ID_SIZE) > 0)
 		dso__set_build_id(dso, build_id);
 
 	/*
@@ -1487,6 +1488,9 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 						   root_dir, name, PATH_MAX))
 			continue;
 
+		if (!is_regular_file(name))
+			continue;
+
 		/* Name is now the name of the next image to try */
 		if (symsrc__init(ss, dso, name, symtab_type) < 0)
 			continue;
@@ -1525,6 +1529,10 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 	if (!runtime_ss && syms_ss)
 		runtime_ss = syms_ss;
 
+	if (syms_ss && syms_ss->type == DSO_BINARY_TYPE__BUILD_ID_CACHE)
+		if (dso__build_id_is_kmod(dso, name, PATH_MAX))
+			kmod = true;
+
 	if (syms_ss)
 		ret = dso__load_sym(dso, map, syms_ss, runtime_ss, filter, kmod);
 	else
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index ccd1caa40..c8b7544d9 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -34,8 +34,8 @@
 #endif
 
 #ifdef HAVE_LIBELF_SUPPORT
-extern Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
-				GElf_Shdr *shp, const char *name, size_t *idx);
+Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
+			     GElf_Shdr *shp, const char *name, size_t *idx);
 #endif
 
 #ifndef DMGL_PARAMS
@@ -110,7 +110,8 @@ struct symbol_conf {
 			has_filter,
 			show_ref_callgraph,
 			hide_unresolved,
-			raw_trace;
+			raw_trace,
+			report_hierarchy;
 	const char	*vmlinux_name,
 			*kallsyms_name,
 			*source_prefix,
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index 08afc6909..267112b4e 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -94,7 +94,7 @@ struct thread_map *thread_map__new_by_uid(uid_t uid)
 	DIR *proc;
 	int max_threads = 32, items, i;
 	char path[256];
-	struct dirent dirent, *next, **namelist = NULL;
+	struct dirent *dirent, **namelist = NULL;
 	struct thread_map *threads = thread_map__alloc(max_threads);
 
 	if (threads == NULL)
@@ -107,16 +107,16 @@ struct thread_map *thread_map__new_by_uid(uid_t uid)
 	threads->nr = 0;
 	atomic_set(&threads->refcnt, 1);
 
-	while (!readdir_r(proc, &dirent, &next) && next) {
+	while ((dirent = readdir(proc)) != NULL) {
 		char *end;
 		bool grow = false;
 		struct stat st;
-		pid_t pid = strtol(dirent.d_name, &end, 10);
+		pid_t pid = strtol(dirent->d_name, &end, 10);
 
 		if (*end) /* only interested in proper numerical dirents */
 			continue;
 
-		snprintf(path, sizeof(path), "/proc/%s", dirent.d_name);
+		snprintf(path, sizeof(path), "/proc/%s", dirent->d_name);
 
 		if (stat(path, &st) != 0)
 			continue;
diff --git a/tools/perf/util/trace-event.c b/tools/perf/util/trace-event.c
index 802bb868d..8ae051e0e 100644
--- a/tools/perf/util/trace-event.c
+++ b/tools/perf/util/trace-event.c
@@ -10,6 +10,7 @@
 #include <linux/err.h>
 #include <traceevent/event-parse.h>
 #include <api/fs/tracing_path.h>
+#include <api/fs/fs.h>
 #include "trace-event.h"
 #include "machine.h"
 #include "util.h"
diff --git a/tools/perf/util/tsc.c b/tools/perf/util/tsc.c
index 4d4210d4e..1b741646e 100644
--- a/tools/perf/util/tsc.c
+++ b/tools/perf/util/tsc.c
@@ -19,7 +19,7 @@ u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc)
 	u64 quot, rem;
 
 	quot = cyc >> tc->time_shift;
-	rem  = cyc & ((1 << tc->time_shift) - 1);
+	rem  = cyc & (((u64)1 << tc->time_shift) - 1);
 	return tc->time_zero + quot * tc->time_mult +
 	       ((rem * tc->time_mult) >> tc->time_shift);
 }
diff --git a/tools/perf/util/usage.c b/tools/perf/util/usage.c
index 6adfa18cd..996046a66 100644
--- a/tools/perf/util/usage.c
+++ b/tools/perf/util/usage.c
@@ -41,15 +41,9 @@ static void warn_builtin(const char *warn, va_list params)
 /* If we are in a dlopen()ed .so write to a global variable would segfault
  * (ugh), so keep things static. */
 static void (*usage_routine)(const char *err) NORETURN = usage_builtin;
-static void (*die_routine)(const char *err, va_list params) NORETURN = die_builtin;
 static void (*error_routine)(const char *err, va_list params) = error_builtin;
 static void (*warn_routine)(const char *err, va_list params) = warn_builtin;
 
-void set_die_routine(void (*routine)(const char *err, va_list params) NORETURN)
-{
-	die_routine = routine;
-}
-
 void set_warning_routine(void (*routine)(const char *err, va_list params))
 {
 	warn_routine = routine;
@@ -65,7 +59,7 @@ void die(const char *err, ...)
 	va_list params;
 
 	va_start(params, err);
-	die_routine(err, params);
+	die_builtin(err, params);
 	va_end(params);
 }
 
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index ead950983..b7766c577 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -14,6 +14,7 @@
 #include <limits.h>
 #include <byteswap.h>
 #include <linux/kernel.h>
+#include <linux/log2.h>
 #include <unistd.h>
 #include "callchain.h"
 #include "strlist.h"
@@ -507,54 +508,6 @@ int parse_callchain_record(const char *arg, struct callchain_param *param)
 	return ret;
 }
 
-int filename__read_str(const char *filename, char **buf, size_t *sizep)
-{
-	size_t size = 0, alloc_size = 0;
-	void *bf = NULL, *nbf;
-	int fd, n, err = 0;
-	char sbuf[STRERR_BUFSIZE];
-
-	fd = open(filename, O_RDONLY);
-	if (fd < 0)
-		return -errno;
-
-	do {
-		if (size == alloc_size) {
-			alloc_size += BUFSIZ;
-			nbf = realloc(bf, alloc_size);
-			if (!nbf) {
-				err = -ENOMEM;
-				break;
-			}
-
-			bf = nbf;
-		}
-
-		n = read(fd, bf + size, alloc_size - size);
-		if (n < 0) {
-			if (size) {
-				pr_warning("read failed %d: %s\n", errno,
-					 strerror_r(errno, sbuf, sizeof(sbuf)));
-				err = 0;
-			} else
-				err = -errno;
-
-			break;
-		}
-
-		size += n;
-	} while (n > 0);
-
-	if (!err) {
-		*sizep = size;
-		*buf   = bf;
-	} else
-		free(bf);
-
-	close(fd);
-	return err;
-}
-
 const char *get_filename_for_perf_kvm(void)
 {
 	const char *filename;
@@ -691,3 +644,66 @@ out:
 
 	return tip;
 }
+
+bool is_regular_file(const char *file)
+{
+	struct stat st;
+
+	if (stat(file, &st))
+		return false;
+
+	return S_ISREG(st.st_mode);
+}
+
+int fetch_current_timestamp(char *buf, size_t sz)
+{
+	struct timeval tv;
+	struct tm tm;
+	char dt[32];
+
+	if (gettimeofday(&tv, NULL) || !localtime_r(&tv.tv_sec, &tm))
+		return -1;
+
+	if (!strftime(dt, sizeof(dt), "%Y%m%d%H%M%S", &tm))
+		return -1;
+
+	scnprintf(buf, sz, "%s%02u", dt, (unsigned)tv.tv_usec / 10000);
+
+	return 0;
+}
+
+void print_binary(unsigned char *data, size_t len,
+		  size_t bytes_per_line, print_binary_t printer,
+		  void *extra)
+{
+	size_t i, j, mask;
+
+	if (!printer)
+		return;
+
+	bytes_per_line = roundup_pow_of_two(bytes_per_line);
+	mask = bytes_per_line - 1;
+
+	printer(BINARY_PRINT_DATA_BEGIN, 0, extra);
+	for (i = 0; i < len; i++) {
+		if ((i & mask) == 0) {
+			printer(BINARY_PRINT_LINE_BEGIN, -1, extra);
+			printer(BINARY_PRINT_ADDR, i, extra);
+		}
+
+		printer(BINARY_PRINT_NUM_DATA, data[i], extra);
+
+		if (((i & mask) == mask) || i == len - 1) {
+			for (j = 0; j < mask-(i & mask); j++)
+				printer(BINARY_PRINT_NUM_PAD, -1, extra);
+
+			printer(BINARY_PRINT_SEP, i, extra);
+			for (j = i & ~mask; j <= i; j++)
+				printer(BINARY_PRINT_CHAR_DATA, data[j], extra);
+			for (j = 0; j < mask-(i & mask); j++)
+				printer(BINARY_PRINT_CHAR_PAD, i, extra);
+			printer(BINARY_PRINT_LINE_END, -1, extra);
+		}
+	}
+	printer(BINARY_PRINT_DATA_END, -1, extra);
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index fe915e616..8298d607c 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -82,6 +82,8 @@
 
 extern const char *graph_line;
 extern const char *graph_dotted_line;
+extern const char *spaces;
+extern const char *dots;
 extern char buildid_dir[];
 
 /* On most systems <limits.h> would have given us this, but
@@ -131,25 +133,15 @@ extern char buildid_dir[];
 #define PERF_GTK_DSO  "libperf-gtk.so"
 
 /* General helper functions */
-extern void usage(const char *err) NORETURN;
-extern void die(const char *err, ...) NORETURN __attribute__((format (printf, 1, 2)));
-extern int error(const char *err, ...) __attribute__((format (printf, 1, 2)));
-extern void warning(const char *err, ...) __attribute__((format (printf, 1, 2)));
+void usage(const char *err) NORETURN;
+void die(const char *err, ...) NORETURN __attribute__((format (printf, 1, 2)));
+int error(const char *err, ...) __attribute__((format (printf, 1, 2)));
+void warning(const char *err, ...) __attribute__((format (printf, 1, 2)));
 
-#include "../../../include/linux/stringify.h"
+void set_warning_routine(void (*routine)(const char *err, va_list params));
 
-#define DIE_IF(cnd)	\
-	do { if (cnd)	\
-		die(" at (" __FILE__ ":" __stringify(__LINE__) "): "	\
-		    __stringify(cnd) "\n");				\
-	} while (0)
-
-
-extern void set_die_routine(void (*routine)(const char *err, va_list params) NORETURN);
-extern void set_warning_routine(void (*routine)(const char *err, va_list params));
-
-extern int prefixcmp(const char *str, const char *prefix);
-extern void set_buildid_dir(const char *dir);
+int prefixcmp(const char *str, const char *prefix);
+void set_buildid_dir(const char *dir);
 
 #ifdef __GLIBC_PREREQ
 #if __GLIBC_PREREQ(2, 1)
@@ -170,8 +162,7 @@ static inline char *gitstrchrnul(const char *s, int c)
 /*
  * Wrappers:
  */
-extern char *xstrdup(const char *str);
-extern void *xrealloc(void *ptr, size_t size) __attribute__((weak));
+void *xrealloc(void *ptr, size_t size) __attribute__((weak));
 
 
 static inline void *zalloc(size_t size)
@@ -303,7 +294,6 @@ char *__get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
 		  bool show_sym, bool unwind_inlines);
 void free_srcline(char *srcline);
 
-int filename__read_str(const char *filename, char **buf, size_t *sizep);
 int perf_event_paranoid(void);
 
 void mem_bswap_64(void *src, int byte_size);
@@ -343,5 +333,27 @@ int fetch_kernel_version(unsigned int *puint,
 #define KVER_PARAM(x)	KVER_VERSION(x), KVER_PATCHLEVEL(x), KVER_SUBLEVEL(x)
 
 const char *perf_tip(const char *dirpath);
+bool is_regular_file(const char *file);
+int fetch_current_timestamp(char *buf, size_t sz);
+
+enum binary_printer_ops {
+	BINARY_PRINT_DATA_BEGIN,
+	BINARY_PRINT_LINE_BEGIN,
+	BINARY_PRINT_ADDR,
+	BINARY_PRINT_NUM_DATA,
+	BINARY_PRINT_NUM_PAD,
+	BINARY_PRINT_SEP,
+	BINARY_PRINT_CHAR_DATA,
+	BINARY_PRINT_CHAR_PAD,
+	BINARY_PRINT_LINE_END,
+	BINARY_PRINT_DATA_END,
+};
+
+typedef void (*print_binary_t)(enum binary_printer_ops,
+			       unsigned int val,
+			       void *extra);
 
+void print_binary(unsigned char *data, size_t len,
+		  size_t bytes_per_line, print_binary_t printer,
+		  void *extra);
 #endif /* GIT_COMPAT_UTIL_H */
diff --git a/tools/perf/util/wrapper.c b/tools/perf/util/wrapper.c
index 19f15b650..5f1a07c4b 100644
--- a/tools/perf/util/wrapper.c
+++ b/tools/perf/util/wrapper.c
@@ -12,18 +12,6 @@ static inline void release_pack_memory(size_t size __maybe_unused,
 {
 }
 
-char *xstrdup(const char *str)
-{
-	char *ret = strdup(str);
-	if (!ret) {
-		release_pack_memory(strlen(str) + 1, -1);
-		ret = strdup(str);
-		if (!ret)
-			die("Out of memory, strdup failed");
-	}
-	return ret;
-}
-
 void *xrealloc(void *ptr, size_t size)
 {
 	void *ret = realloc(ptr, size);