diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index bf52461..1ec429f 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -65,7 +65,8 @@
 		return 0;
 	}
 
-	he = __hists__add_entry(&evsel->hists, al, NULL, NULL, NULL, 1, 1, 0);
+	he = __hists__add_entry(&evsel->hists, al, NULL, NULL, NULL, 1, 1, 0,
+				true);
 	if (he == NULL)
 		return -ENOMEM;
 
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 8bff543..9a5a035 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -315,7 +315,7 @@
 			    u64 weight, u64 transaction)
 {
 	if (__hists__add_entry(hists, al, NULL, NULL, NULL, period, weight,
-			       transaction) != NULL)
+			       transaction, true) != NULL)
 		return 0;
 	return -ENOMEM;
 }
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 5130926..12e2e12 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -247,7 +247,7 @@
 	pthread_mutex_lock(&evsel->hists.lock);
 	he = __hists__add_entry(&evsel->hists, al, NULL, NULL, NULL,
 				sample->period, sample->weight,
-				sample->transaction);
+				sample->transaction, true);
 	pthread_mutex_unlock(&evsel->hists.lock);
 	if (he == NULL)
 		return NULL;
diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c
index 5ffa2c3..ca6693b 100644
--- a/tools/perf/tests/hists_link.c
+++ b/tools/perf/tests/hists_link.c
@@ -88,7 +88,7 @@
 				goto out;
 
 			he = __hists__add_entry(&evsel->hists, &al, NULL,
-						NULL, NULL, 1, 1, 0);
+						NULL, NULL, 1, 1, 0, true);
 			if (he == NULL)
 				goto out;
 
@@ -112,7 +112,7 @@
 				goto out;
 
 			he = __hists__add_entry(&evsel->hists, &al, NULL,
-						NULL, NULL, 1, 1, 0);
+						NULL, NULL, 1, 1, 0, true);
 			if (he == NULL)
 				goto out;
 
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index dfff2ee..b9facf3 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -279,7 +279,8 @@
  * histogram, sorted on item, collects periods
  */
 
-static struct hist_entry *hist_entry__new(struct hist_entry *template)
+static struct hist_entry *hist_entry__new(struct hist_entry *template,
+					  bool sample_self)
 {
 	size_t callchain_size = 0;
 	struct hist_entry *he;
@@ -299,6 +300,8 @@
 				return NULL;
 			}
 			memcpy(he->stat_acc, &he->stat, sizeof(he->stat));
+			if (!sample_self)
+				memset(&he->stat, 0, sizeof(he->stat));
 		}
 
 		if (he->ms.map)
@@ -351,7 +354,8 @@
 
 static struct hist_entry *add_hist_entry(struct hists *hists,
 					 struct hist_entry *entry,
-					 struct addr_location *al)
+					 struct addr_location *al,
+					 bool sample_self)
 {
 	struct rb_node **p;
 	struct rb_node *parent = NULL;
@@ -375,7 +379,8 @@
 		cmp = hist_entry__cmp(he, entry);
 
 		if (!cmp) {
-			he_stat__add_period(&he->stat, period, weight);
+			if (sample_self)
+				he_stat__add_period(&he->stat, period, weight);
 			if (symbol_conf.cumulate_callchain)
 				he_stat__add_period(he->stat_acc, period, weight);
 
@@ -405,14 +410,15 @@
 			p = &(*p)->rb_right;
 	}
 
-	he = hist_entry__new(entry);
+	he = hist_entry__new(entry, sample_self);
 	if (!he)
 		return NULL;
 
 	rb_link_node(&he->rb_node_in, parent, p);
 	rb_insert_color(&he->rb_node_in, hists->entries_in);
 out:
-	he_stat__add_cpumode_period(&he->stat, al->cpumode, period);
+	if (sample_self)
+		he_stat__add_cpumode_period(&he->stat, al->cpumode, period);
 	if (symbol_conf.cumulate_callchain)
 		he_stat__add_cpumode_period(he->stat_acc, al->cpumode, period);
 	return he;
@@ -423,7 +429,8 @@
 				      struct symbol *sym_parent,
 				      struct branch_info *bi,
 				      struct mem_info *mi,
-				      u64 period, u64 weight, u64 transaction)
+				      u64 period, u64 weight, u64 transaction,
+				      bool sample_self)
 {
 	struct hist_entry entry = {
 		.thread	= al->thread,
@@ -448,7 +455,7 @@
 		.transaction = transaction,
 	};
 
-	return add_hist_entry(hists, &entry, al);
+	return add_hist_entry(hists, &entry, al, sample_self);
 }
 
 static int
@@ -501,7 +508,7 @@
 	 * and the he_stat__add_period() function.
 	 */
 	he = __hists__add_entry(&iter->evsel->hists, al, iter->parent, NULL, mi,
-				cost, cost, 0);
+				cost, cost, 0, true);
 	if (!he)
 		return -ENOMEM;
 
@@ -608,7 +615,7 @@
 	 * and not events sampled. Thus we use a pseudo period of 1.
 	 */
 	he = __hists__add_entry(&evsel->hists, al, iter->parent, &bi[i], NULL,
-				1, 1, 0);
+				1, 1, 0, true);
 	if (he == NULL)
 		return -ENOMEM;
 
@@ -657,7 +664,7 @@
 
 	he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL,
 				sample->period, sample->weight,
-				sample->transaction);
+				sample->transaction, true);
 	if (he == NULL)
 		return -ENOMEM;
 
@@ -1161,7 +1168,7 @@
 			p = &(*p)->rb_right;
 	}
 
-	he = hist_entry__new(pair);
+	he = hist_entry__new(pair, true);
 	if (he) {
 		memset(&he->stat, 0, sizeof(he->stat));
 		he->hists = hists;
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 8894f18..bedb24d 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -130,7 +130,8 @@
 				      struct symbol *parent,
 				      struct branch_info *bi,
 				      struct mem_info *mi, u64 period,
-				      u64 weight, u64 transaction);
+				      u64 weight, u64 transaction,
+				      bool sample_self);
 int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
 			 struct perf_evsel *evsel, struct perf_sample *sample,
 			 int max_stack_depth);