Merge tag 'perf-core-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

 User visible changes:

  * Add a visual cue for toggle zeroing of samples in 'perf top' (Taeung Song)

  * Fix for double free in 'perf stat' when using some specific invalid
    command line combo (Yasser Shalabi)

 Infrastructure changes:

  * Add option to copy events when queuing for sorting across cpu buffers
    and enable it for 'perf kvm stat live', to avoid having events left
    in the queue pointing to the ring buffer be rewritten in high volume
    sessions.  (Alexander Yarygin, improving work done by David Ahern):

  * Document sysfs events/ interfaces (Cody P Schafer)

  * Add support to new style format of kernel PMU event. (Kan Liang)

  * Fix typos in perf/Documentation (Masanari Iida)

  * Improve callchains when using libunwind (Namhyung Kim)

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

15 files changed, 316 insertions, 71 deletions

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index b4b54d84e9b0..3c9e77d6b4c2 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1003,6 +1003,7 @@ int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
 
 out_delete_threads:
 	thread_map__delete(evlist->threads);
+	evlist->threads = NULL;
 	return -1;
 }
 
diff --git a/tools/perf/util/include/linux/string.h b/tools/perf/util/include/linux/string.h
index 97a800738226..6f19c548ecc0 100644
--- a/tools/perf/util/include/linux/string.h
+++ b/tools/perf/util/include/linux/string.h
@@ -1,4 +1,3 @@
 #include <string.h>
 
 void *memdup(const void *src, size_t len);
-int str_append(char **s, int *len, const char *a);
diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c
index 706ce1a66169..fd4be94125fb 100644
--- a/tools/perf/util/ordered-events.c
+++ b/tools/perf/util/ordered-events.c
@@ -1,5 +1,6 @@
 #include <linux/list.h>
 #include <linux/compiler.h>
+#include <linux/string.h>
 #include "ordered-events.h"
 #include "evlist.h"
 #include "session.h"
@@ -57,11 +58,45 @@ static void queue_event(struct ordered_events *oe, struct ordered_event *new)
 	}
 }
 
+static union perf_event *__dup_event(struct ordered_events *oe,
+				     union perf_event *event)
+{
+	union perf_event *new_event = NULL;
+
+	if (oe->cur_alloc_size < oe->max_alloc_size) {
+		new_event = memdup(event, event->header.size);
+		if (new_event)
+			oe->cur_alloc_size += event->header.size;
+	}
+
+	return new_event;
+}
+
+static union perf_event *dup_event(struct ordered_events *oe,
+				   union perf_event *event)
+{
+	return oe->copy_on_queue ? __dup_event(oe, event) : event;
+}
+
+static void free_dup_event(struct ordered_events *oe, union perf_event *event)
+{
+	if (oe->copy_on_queue) {
+		oe->cur_alloc_size -= event->header.size;
+		free(event);
+	}
+}
+
 #define MAX_SAMPLE_BUFFER	(64 * 1024 / sizeof(struct ordered_event))
-static struct ordered_event *alloc_event(struct ordered_events *oe)
+static struct ordered_event *alloc_event(struct ordered_events *oe,
+					 union perf_event *event)
 {
 	struct list_head *cache = &oe->cache;
 	struct ordered_event *new = NULL;
+	union perf_event *new_event;
+
+	new_event = dup_event(oe, event);
+	if (!new_event)
+		return NULL;
 
 	if (!list_empty(cache)) {
 		new = list_entry(cache->next, struct ordered_event, list);
@@ -74,8 +109,10 @@ static struct ordered_event *alloc_event(struct ordered_events *oe)
 		size_t size = MAX_SAMPLE_BUFFER * sizeof(*new);
 
 		oe->buffer = malloc(size);
-		if (!oe->buffer)
+		if (!oe->buffer) {
+			free_dup_event(oe, new_event);
 			return NULL;
+		}
 
 		pr("alloc size %" PRIu64 "B (+%zu), max %" PRIu64 "B\n",
 		   oe->cur_alloc_size, size, oe->max_alloc_size);
@@ -90,15 +127,17 @@ static struct ordered_event *alloc_event(struct ordered_events *oe)
 		pr("allocation limit reached %" PRIu64 "B\n", oe->max_alloc_size);
 	}
 
+	new->event = new_event;
 	return new;
 }
 
 struct ordered_event *
-ordered_events__new(struct ordered_events *oe, u64 timestamp)
+ordered_events__new(struct ordered_events *oe, u64 timestamp,
+		    union perf_event *event)
 {
 	struct ordered_event *new;
 
-	new = alloc_event(oe);
+	new = alloc_event(oe, event);
 	if (new) {
 		new->timestamp = timestamp;
 		queue_event(oe, new);
@@ -111,6 +150,7 @@ void ordered_events__delete(struct ordered_events *oe, struct ordered_event *eve
 {
 	list_move(&event->list, &oe->cache);
 	oe->nr_events--;
+	free_dup_event(oe, event->event);
 }
 
 static int __ordered_events__flush(struct perf_session *s,
@@ -240,6 +280,7 @@ void ordered_events__free(struct ordered_events *oe)
 
 		event = list_entry(oe->to_free.next, struct ordered_event, list);
 		list_del(&event->list);
+		free_dup_event(oe, event->event);
 		free(event);
 	}
 }
diff --git a/tools/perf/util/ordered-events.h b/tools/perf/util/ordered-events.h
index 3b2f20542a01..7b8f9b011f38 100644
--- a/tools/perf/util/ordered-events.h
+++ b/tools/perf/util/ordered-events.h
@@ -34,9 +34,11 @@ struct ordered_events {
 	int			buffer_idx;
 	unsigned int		nr_events;
 	enum oe_flush		last_flush_type;
+	bool                    copy_on_queue;
 };
 
-struct ordered_event *ordered_events__new(struct ordered_events *oe, u64 timestamp);
+struct ordered_event *ordered_events__new(struct ordered_events *oe, u64 timestamp,
+					  union perf_event *event);
 void ordered_events__delete(struct ordered_events *oe, struct ordered_event *event);
 int ordered_events__flush(struct perf_session *s, struct perf_tool *tool,
 			  enum oe_flush how);
@@ -48,4 +50,10 @@ void ordered_events__set_alloc_size(struct ordered_events *oe, u64 size)
 {
 	oe->max_alloc_size = size;
 }
+
+static inline
+void ordered_events__set_copy_on_queue(struct ordered_events *oe, bool copy)
+{
+	oe->copy_on_queue = copy;
+}
 #endif /* __ORDERED_EVENTS_H */
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index d76aa30cb1fb..c659a3ca1283 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -6,7 +6,7 @@
 #include "parse-options.h"
 #include "parse-events.h"
 #include "exec_cmd.h"
-#include "linux/string.h"
+#include "string.h"
 #include "symbol.h"
 #include "cache.h"
 #include "header.h"
@@ -30,6 +30,15 @@ extern int parse_events_debug;
 #endif
 int parse_events_parse(void *data, void *scanner);
 
+static struct perf_pmu_event_symbol *perf_pmu_events_list;
+/*
+ * The variable indicates the number of supported pmu event symbols.
+ * 0 means not initialized and ready to init
+ * -1 means failed to init, don't try anymore
+ * >0 is the number of supported pmu event symbols
+ */
+static int perf_pmu_events_list_num;
+
 static struct event_symbol event_symbols_hw[PERF_COUNT_HW_MAX] = {
 	[PERF_COUNT_HW_CPU_CYCLES] = {
 		.symbol = "cpu-cycles",
@@ -863,30 +872,111 @@ int parse_events_name(struct list_head *list, char *name)
 	return 0;
 }
 
-static int parse_events__scanner(const char *str, void *data, int start_token);
+static int
+comp_pmu(const void *p1, const void *p2)
+{
+	struct perf_pmu_event_symbol *pmu1 = (struct perf_pmu_event_symbol *) p1;
+	struct perf_pmu_event_symbol *pmu2 = (struct perf_pmu_event_symbol *) p2;
 
-static int parse_events_fixup(int ret, const char *str, void *data,
-			      int start_token)
+	return strcmp(pmu1->symbol, pmu2->symbol);
+}
+
+static void perf_pmu__parse_cleanup(void)
 {
-	char *o = strdup(str);
-	char *s = NULL;
-	char *t = o;
-	char *p;
+	if (perf_pmu_events_list_num > 0) {
+		struct perf_pmu_event_symbol *p;
+		int i;
+
+		for (i = 0; i < perf_pmu_events_list_num; i++) {
+			p = perf_pmu_events_list + i;
+			free(p->symbol);
+		}
+		free(perf_pmu_events_list);
+		perf_pmu_events_list = NULL;
+		perf_pmu_events_list_num = 0;
+	}
+}
+
+#define SET_SYMBOL(str, stype)		\
+do {					\
+	p->symbol = str;		\
+	if (!p->symbol)			\
+		goto err;		\
+	p->type = stype;		\
+} while (0)
+
+/*
+ * Read the pmu events list from sysfs
+ * Save it into perf_pmu_events_list
+ */
+static void perf_pmu__parse_init(void)
+{
+
+	struct perf_pmu *pmu = NULL;
+	struct perf_pmu_alias *alias;
 	int len = 0;
 
-	if (!o)
-		return ret;
-	while ((p = strsep(&t, ",")) != NULL) {
-		if (s)
-			str_append(&s, &len, ",");
-		str_append(&s, &len, "cpu/");
-		str_append(&s, &len, p);
-		str_append(&s, &len, "/");
+	pmu = perf_pmu__find("cpu");
+	if ((pmu == NULL) || list_empty(&pmu->aliases)) {
+		perf_pmu_events_list_num = -1;
+		return;
 	}
-	free(o);
-	if (!s)
-		return -ENOMEM;
-	return parse_events__scanner(s, data, start_token);
+	list_for_each_entry(alias, &pmu->aliases, list) {
+		if (strchr(alias->name, '-'))
+			len++;
+		len++;
+	}
+	perf_pmu_events_list = malloc(sizeof(struct perf_pmu_event_symbol) * len);
+	if (!perf_pmu_events_list)
+		return;
+	perf_pmu_events_list_num = len;
+
+	len = 0;
+	list_for_each_entry(alias, &pmu->aliases, list) {
+		struct perf_pmu_event_symbol *p = perf_pmu_events_list + len;
+		char *tmp = strchr(alias->name, '-');
+
+		if (tmp != NULL) {
+			SET_SYMBOL(strndup(alias->name, tmp - alias->name),
+					PMU_EVENT_SYMBOL_PREFIX);
+			p++;
+			SET_SYMBOL(strdup(++tmp), PMU_EVENT_SYMBOL_SUFFIX);
+			len += 2;
+		} else {
+			SET_SYMBOL(strdup(alias->name), PMU_EVENT_SYMBOL);
+			len++;
+		}
+	}
+	qsort(perf_pmu_events_list, len,
+		sizeof(struct perf_pmu_event_symbol), comp_pmu);
+
+	return;
+err:
+	perf_pmu__parse_cleanup();
+}
+
+enum perf_pmu_event_symbol_type
+perf_pmu__parse_check(const char *name)
+{
+	struct perf_pmu_event_symbol p, *r;
+
+	/* scan kernel pmu events from sysfs if needed */
+	if (perf_pmu_events_list_num == 0)
+		perf_pmu__parse_init();
+	/*
+	 * name "cpu" could be prefix of cpu-cycles or cpu// events.
+	 * cpu-cycles has been handled by hardcode.
+	 * So it must be cpu// events, not kernel pmu event.
+	 */
+	if ((perf_pmu_events_list_num <= 0) || !strcmp(name, "cpu"))
+		return PMU_EVENT_SYMBOL_ERR;
+
+	p.symbol = strdup(name);
+	r = bsearch(&p, perf_pmu_events_list,
+			(size_t) perf_pmu_events_list_num,
+			sizeof(struct perf_pmu_event_symbol), comp_pmu);
+	free(p.symbol);
+	return r ? r->type : PMU_EVENT_SYMBOL_ERR;
 }
 
 static int parse_events__scanner(const char *str, void *data, int start_token)
@@ -909,8 +999,6 @@ static int parse_events__scanner(const char *str, void *data, int start_token)
 	parse_events__flush_buffer(buffer, scanner);
 	parse_events__delete_buffer(buffer, scanner);
 	parse_events_lex_destroy(scanner);
-	if (ret && !strchr(str, '/'))
-		ret = parse_events_fixup(ret, str, data, start_token);
 	return ret;
 }
 
@@ -945,6 +1033,7 @@ int parse_events(struct perf_evlist *evlist, const char *str)
 	int ret;
 
 	ret = parse_events__scanner(str, &data, PE_START_EVENTS);
+	perf_pmu__parse_cleanup();
 	if (!ret) {
 		int entries = data.idx - evlist->nr_entries;
 		perf_evlist__splice_list_tail(evlist, &data.list, entries);
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index df094b4ed5ed..db2cf78ff0f3 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -35,6 +35,18 @@ extern int parse_filter(const struct option *opt, const char *str, int unset);
 
 #define EVENTS_HELP_MAX (128*1024)
 
+enum perf_pmu_event_symbol_type {
+	PMU_EVENT_SYMBOL_ERR,		/* not a PMU EVENT */
+	PMU_EVENT_SYMBOL,		/* normal style PMU event */
+	PMU_EVENT_SYMBOL_PREFIX,	/* prefix of pre-suf style event */
+	PMU_EVENT_SYMBOL_SUFFIX,	/* suffix of pre-suf style event */
+};
+
+struct perf_pmu_event_symbol {
+	char	*symbol;
+	enum perf_pmu_event_symbol_type	type;
+};
+
 enum {
 	PARSE_EVENTS__TERM_TYPE_NUM,
 	PARSE_EVENTS__TERM_TYPE_STR,
@@ -95,6 +107,8 @@ int parse_events_add_breakpoint(struct list_head *list, int *idx,
 				void *ptr, char *type);
 int parse_events_add_pmu(struct list_head *list, int *idx,
 			 char *pmu , struct list_head *head_config);
+enum perf_pmu_event_symbol_type
+perf_pmu__parse_check(const char *name);
 void parse_events__set_leader(char *name, struct list_head *list);
 void parse_events_update_lists(struct list_head *list_event,
 			       struct list_head *list_all);
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 343299575b30..906630bbf8eb 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -51,6 +51,24 @@ static int str(yyscan_t scanner, int token)
 	return token;
 }
 
+static int pmu_str_check(yyscan_t scanner)
+{
+	YYSTYPE *yylval = parse_events_get_lval(scanner);
+	char *text = parse_events_get_text(scanner);
+
+	yylval->str = strdup(text);
+	switch (perf_pmu__parse_check(text)) {
+		case PMU_EVENT_SYMBOL_PREFIX:
+			return PE_PMU_EVENT_PRE;
+		case PMU_EVENT_SYMBOL_SUFFIX:
+			return PE_PMU_EVENT_SUF;
+		case PMU_EVENT_SYMBOL:
+			return PE_KERNEL_PMU_EVENT;
+		default:
+			return PE_NAME;
+	}
+}
+
 static int sym(yyscan_t scanner, int type, int config)
 {
 	YYSTYPE *yylval = parse_events_get_lval(scanner);
@@ -178,6 +196,16 @@ alignment-faults				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_AL
 emulation-faults				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EMULATION_FAULTS); }
 dummy						{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); }
 
+	/*
+	 * We have to handle the kernel PMU event cycles-ct/cycles-t/mem-loads/mem-stores separately.
+	 * Because the prefix cycles is mixed up with cpu-cycles.
+	 * loads and stores are mixed up with cache event
+	 */
+cycles-ct					{ return str(yyscanner, PE_KERNEL_PMU_EVENT); }
+cycles-t					{ return str(yyscanner, PE_KERNEL_PMU_EVENT); }
+mem-loads					{ return str(yyscanner, PE_KERNEL_PMU_EVENT); }
+mem-stores					{ return str(yyscanner, PE_KERNEL_PMU_EVENT); }
+
 L1-dcache|l1-d|l1d|L1-data		|
 L1-icache|l1-i|l1i|L1-instruction	|
 LLC|L2					|
@@ -199,7 +227,7 @@ r{num_raw_hex}		{ return raw(yyscanner); }
 {num_hex}		{ return value(yyscanner, 16); }
 
 {modifier_event}	{ return str(yyscanner, PE_MODIFIER_EVENT); }
-{name}			{ return str(yyscanner, PE_NAME); }
+{name}			{ return pmu_str_check(yyscanner); }
 "/"			{ BEGIN(config); return '/'; }
 -			{ return '-'; }
 ,			{ BEGIN(event); return ','; }
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 55fab6ad609a..93c4c9fbc922 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -47,6 +47,7 @@ static inc_group_count(struct list_head *list,
 %token PE_NAME_CACHE_TYPE PE_NAME_CACHE_OP_RESULT
 %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
 %type <num> PE_VALUE
 %type <num> PE_VALUE_SYM_HW
 %type <num> PE_VALUE_SYM_SW
@@ -58,6 +59,7 @@ static inc_group_count(struct list_head *list,
 %type <str> PE_MODIFIER_EVENT
 %type <str> PE_MODIFIER_BP
 %type <str> PE_EVENT_NAME
+%type <str> PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_KERNEL_PMU_EVENT
 %type <num> value_sym
 %type <head> event_config
 %type <term> event_term
@@ -220,6 +222,44 @@ PE_NAME '/' '/'
 	ABORT_ON(parse_events_add_pmu(list, &data->idx, $1, NULL));
 	$$ = list;
 }
+|
+PE_KERNEL_PMU_EVENT sep_dc
+{
+	struct parse_events_evlist *data = _data;
+	struct list_head *head;
+	struct parse_events_term *term;
+	struct list_head *list;
+
+	ALLOC_LIST(head);
+	ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
+					$1, 1));
+	list_add_tail(&term->list, head);
+
+	ALLOC_LIST(list);
+	ABORT_ON(parse_events_add_pmu(list, &data->idx, "cpu", head));
+	parse_events__free_terms(head);
+	$$ = list;
+}
+|
+PE_PMU_EVENT_PRE '-' PE_PMU_EVENT_SUF sep_dc
+{
+	struct parse_events_evlist *data = _data;
+	struct list_head *head;
+	struct parse_events_term *term;
+	struct list_head *list;
+	char pmu_name[128];
+	snprintf(&pmu_name, 128, "%s-%s", $1, $3);
+
+	ALLOC_LIST(head);
+	ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
+					&pmu_name, 1));
+	list_add_tail(&term->list, head);
+
+	ALLOC_LIST(list);
+	ABORT_ON(parse_events_add_pmu(list, &data->idx, "cpu", head));
+	parse_events__free_terms(head);
+	$$ = list;
+}
 
 value_sym:
 PE_VALUE_SYM_HW
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 93a41ca96b8e..e243ad962a4d 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -12,16 +12,6 @@
 #include "parse-events.h"
 #include "cpumap.h"
 
-#define UNIT_MAX_LEN	31 /* max length for event unit name */
-
-struct perf_pmu_alias {
-	char *name;
-	struct list_head terms; /* HEAD struct parse_events_term -> list */
-	struct list_head list;  /* ELEM */
-	char unit[UNIT_MAX_LEN+1];
-	double scale;
-};
-
 struct perf_pmu_format {
 	char *name;
 	int value;
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index fe90a012c003..fe9dfbee8eed 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -30,6 +30,16 @@ struct perf_pmu_info {
 	double scale;
 };
 
+#define UNIT_MAX_LEN	31 /* max length for event unit name */
+
+struct perf_pmu_alias {
+	char *name;
+	struct list_head terms; /* HEAD struct parse_events_term -> list */
+	struct list_head list;  /* ELEM */
+	char unit[UNIT_MAX_LEN+1];
+	double scale;
+};
+
 struct perf_pmu *perf_pmu__find(const char *name);
 int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
 		     struct list_head *head_terms);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 896bac73ea08..6702ac28754b 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -532,17 +532,16 @@ int perf_session_queue_event(struct perf_session *s, union perf_event *event,
 			return -EINVAL;
 	}
 
-	new = ordered_events__new(oe, timestamp);
+	new = ordered_events__new(oe, timestamp, event);
 	if (!new) {
 		ordered_events__flush(s, tool, OE_FLUSH__HALF);
-		new = ordered_events__new(oe, timestamp);
+		new = ordered_events__new(oe, timestamp, event);
 	}
 
 	if (!new)
 		return -ENOMEM;
 
 	new->file_offset = file_offset;
-	new->event = event;
 	return 0;
 }
 
diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c
index d87767f76903..6afd6106ceb5 100644
--- a/tools/perf/util/string.c
+++ b/tools/perf/util/string.c
@@ -357,27 +357,3 @@ void *memdup(const void *src, size_t len)
 
 	return p;
 }
-
-/**
- * str_append - reallocate string and append another
- * @s: pointer to string pointer
- * @len: pointer to len (initialized)
- * @a: string to append.
- */
-int str_append(char **s, int *len, const char *a)
-{
-	int olen = *s ? strlen(*s) : 0;
-	int nlen = olen + strlen(a) + 1;
-	if (*len < nlen) {
-		*len = *len * 2;
-		if (*len < nlen)
-			*len = nlen;
-		*s = realloc(*s, *len);
-		if (!*s)
-			return -ENOMEM;
-		if (olen == 0)
-			**s = 0;
-	}
-	strcat(*s, a);
-	return 0;
-}
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index a9df7f2c6dc9..2b7b2d91c016 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -7,6 +7,7 @@
 #include "util.h"
 #include "debug.h"
 #include "comm.h"
+#include "unwind.h"
 
 int thread__init_map_groups(struct thread *thread, struct machine *machine)
 {
@@ -37,6 +38,9 @@ struct thread *thread__new(pid_t pid, pid_t tid)
 		thread->cpu = -1;
 		INIT_LIST_HEAD(&thread->comm_list);
 
+		if (unwind__prepare_access(thread) < 0)
+			goto err_thread;
+
 		comm_str = malloc(32);
 		if (!comm_str)
 			goto err_thread;
@@ -48,6 +52,7 @@ struct thread *thread__new(pid_t pid, pid_t tid)
 			goto err_thread;
 
 		list_add(&comm->list, &thread->comm_list);
+
 	}
 
 	return thread;
@@ -69,6 +74,7 @@ void thread__delete(struct thread *thread)
 		list_del(&comm->list);
 		comm__free(comm);
 	}
+	unwind__finish_access(thread);
 
 	free(thread);
 }
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index 92b56db52471..e060386165c5 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -24,6 +24,7 @@
 #include <linux/list.h>
 #include <libunwind.h>
 #include <libunwind-ptrace.h>
+#include "callchain.h"
 #include "thread.h"
 #include "session.h"
 #include "perf_regs.h"
@@ -525,12 +526,12 @@ static unw_accessors_t accessors = {
 	.get_proc_name		= get_proc_name,
 };
 
-static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
-		       void *arg, int max_stack)
+int unwind__prepare_access(struct thread *thread)
 {
 	unw_addr_space_t addr_space;
-	unw_cursor_t c;
-	int ret;
+
+	if (callchain_param.record_mode != CALLCHAIN_DWARF)
+		return 0;
 
 	addr_space = unw_create_addr_space(&accessors, 0);
 	if (!addr_space) {
@@ -538,6 +539,33 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
 		return -ENOMEM;
 	}
 
+	thread__set_priv(thread, addr_space);
+
+	return 0;
+}
+
+void unwind__finish_access(struct thread *thread)
+{
+	unw_addr_space_t addr_space;
+
+	if (callchain_param.record_mode != CALLCHAIN_DWARF)
+		return;
+
+	addr_space = thread__priv(thread);
+	unw_destroy_addr_space(addr_space);
+}
+
+static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
+		       void *arg, int max_stack)
+{
+	unw_addr_space_t addr_space;
+	unw_cursor_t c;
+	int ret;
+
+	addr_space = thread__priv(ui->thread);
+	if (addr_space == NULL)
+		return -1;
+
 	ret = unw_init_remote(&c, addr_space, ui);
 	if (ret)
 		display_error(ret);
@@ -549,7 +577,6 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
 		ret = ip ? entry(ip, ui->thread, ui->machine, cb, arg) : 0;
 	}
 
-	unw_destroy_addr_space(addr_space);
 	return ret;
 }
 
diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h
index f03061260b4e..c17c4855bdbc 100644
--- a/tools/perf/util/unwind.h
+++ b/tools/perf/util/unwind.h
@@ -4,6 +4,7 @@
 #include <linux/types.h>
 #include "event.h"
 #include "symbol.h"
+#include "thread.h"
 
 struct unwind_entry {
 	struct map	*map;
@@ -21,6 +22,15 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 /* libunwind specific */
 #ifdef HAVE_LIBUNWIND_SUPPORT
 int libunwind__arch_reg_id(int regnum);
+int unwind__prepare_access(struct thread *thread);
+void unwind__finish_access(struct thread *thread);
+#else
+static inline int unwind__prepare_access(struct thread *thread __maybe_unused)
+{
+	return 0;
+}
+
+static inline void unwind__finish_access(struct thread *thread __maybe_unused) {}
 #endif
 #else
 static inline int
@@ -33,5 +43,12 @@ unwind__get_entries(unwind_entry_cb_t cb __maybe_unused,
 {
 	return 0;
 }
+
+static inline int unwind__prepare_access(struct thread *thread __maybe_unused)
+{
+	return 0;
+}
+
+static inline void unwind__finish_access(struct thread *thread __maybe_unused) {}
 #endif /* HAVE_DWARF_UNWIND_SUPPORT */
 #endif /* __UNWIND_H */