diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 4dda6f4dc61866c6470c836855da77004f7b1d6b..8b896f5eded017af417386a80e5d5b6451fa674a 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -275,43 +275,6 @@ static struct perf_tool tool = {
 	.ordering_requires_timestamps = true,
 };
 
-static void insert_hist_entry_by_name(struct rb_root *root,
-				      struct hist_entry *he)
-{
-	struct rb_node **p = &root->rb_node;
-	struct rb_node *parent = NULL;
-	struct hist_entry *iter;
-
-	while (*p != NULL) {
-		parent = *p;
-		iter = rb_entry(parent, struct hist_entry, rb_node);
-		if (hist_entry__cmp(iter, he) < 0)
-			p = &(*p)->rb_left;
-		else
-			p = &(*p)->rb_right;
-	}
-
-	rb_link_node(&he->rb_node, parent, p);
-	rb_insert_color(&he->rb_node, root);
-}
-
-static void hists__name_resort(struct hists *self)
-{
-	struct rb_root tmp = RB_ROOT;
-	struct rb_node *next = rb_first(&self->entries);
-
-	while (next != NULL) {
-		struct hist_entry *n = rb_entry(next, struct hist_entry, rb_node);
-
-		next = rb_next(&n->rb_node);
-
-		rb_erase(&n->rb_node, &self->entries);
-		insert_hist_entry_by_name(&tmp, n);
-	}
-
-	self->entries = tmp;
-}
-
 static struct perf_evsel *evsel_match(struct perf_evsel *evsel,
 				      struct perf_evlist *evlist)
 {
@@ -324,30 +287,34 @@ static struct perf_evsel *evsel_match(struct perf_evsel *evsel,
 	return NULL;
 }
 
-static void perf_evlist__resort_hists(struct perf_evlist *evlist, bool name)
+static void perf_evlist__collapse_resort(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel;
 
 	list_for_each_entry(evsel, &evlist->entries, node) {
 		struct hists *hists = &evsel->hists;
 
-		hists__output_resort(hists);
-
-		if (name)
-			hists__name_resort(hists);
+		hists__collapse_resort(hists);
 	}
 }
 
 static void hists__baseline_only(struct hists *hists)
 {
-	struct rb_node *next = rb_first(&hists->entries);
+	struct rb_root *root;
+	struct rb_node *next;
+
+	if (sort__need_collapse)
+		root = &hists->entries_collapsed;
+	else
+		root = hists->entries_in;
 
+	next = rb_first(root);
 	while (next != NULL) {
-		struct hist_entry *he = rb_entry(next, struct hist_entry, rb_node);
+		struct hist_entry *he = rb_entry(next, struct hist_entry, rb_node_in);
 
-		next = rb_next(&he->rb_node);
+		next = rb_next(&he->rb_node_in);
 		if (!hist_entry__next_pair(he)) {
-			rb_erase(&he->rb_node, &hists->entries);
+			rb_erase(&he->rb_node_in, root);
 			hist_entry__free(he);
 		}
 	}
@@ -471,6 +438,8 @@ static void hists__process(struct hists *old, struct hists *new)
 	else
 		hists__link(new, old);
 
+	hists__output_resort(new);
+
 	if (sort_compute) {
 		hists__precompute(new);
 		hists__compute_resort(new);
@@ -505,8 +474,8 @@ static int __cmd_diff(void)
 	evlist_old = older->evlist;
 	evlist_new = newer->evlist;
 
-	perf_evlist__resort_hists(evlist_old, true);
-	perf_evlist__resort_hists(evlist_new, false);
+	perf_evlist__collapse_resort(evlist_old);
+	perf_evlist__collapse_resort(evlist_new);
 
 	list_for_each_entry(evsel, &evlist_new->entries, node) {
 		struct perf_evsel *evsel_old;
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 3a9ccd09835d44380693222bb11282f7107747ac..8ff3c2f8a5dd46269a00df6e75f8899eb560b9c9 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -726,16 +726,24 @@ void hists__inc_nr_events(struct hists *hists, u32 type)
 static struct hist_entry *hists__add_dummy_entry(struct hists *hists,
 						 struct hist_entry *pair)
 {
-	struct rb_node **p = &hists->entries.rb_node;
+	struct rb_root *root;
+	struct rb_node **p;
 	struct rb_node *parent = NULL;
 	struct hist_entry *he;
 	int cmp;
 
+	if (sort__need_collapse)
+		root = &hists->entries_collapsed;
+	else
+		root = hists->entries_in;
+
+	p = &root->rb_node;
+
 	while (*p != NULL) {
 		parent = *p;
-		he = rb_entry(parent, struct hist_entry, rb_node);
+		he = rb_entry(parent, struct hist_entry, rb_node_in);
 
-		cmp = hist_entry__cmp(he, pair);
+		cmp = hist_entry__collapse(he, pair);
 
 		if (!cmp)
 			goto out;
@@ -750,8 +758,8 @@ static struct hist_entry *hists__add_dummy_entry(struct hists *hists,
 	if (he) {
 		memset(&he->stat, 0, sizeof(he->stat));
 		he->hists = hists;
-		rb_link_node(&he->rb_node, parent, p);
-		rb_insert_color(&he->rb_node, &hists->entries);
+		rb_link_node(&he->rb_node_in, parent, p);
+		rb_insert_color(&he->rb_node_in, root);
 		hists__inc_nr_entries(hists, he);
 	}
 out:
@@ -761,11 +769,16 @@ static struct hist_entry *hists__add_dummy_entry(struct hists *hists,
 static struct hist_entry *hists__find_entry(struct hists *hists,
 					    struct hist_entry *he)
 {
-	struct rb_node *n = hists->entries.rb_node;
+	struct rb_node *n;
+
+	if (sort__need_collapse)
+		n = hists->entries_collapsed.rb_node;
+	else
+		n = hists->entries_in->rb_node;
 
 	while (n) {
-		struct hist_entry *iter = rb_entry(n, struct hist_entry, rb_node);
-		int64_t cmp = hist_entry__cmp(iter, he);
+		struct hist_entry *iter = rb_entry(n, struct hist_entry, rb_node_in);
+		int64_t cmp = hist_entry__collapse(iter, he);
 
 		if (cmp < 0)
 			n = n->rb_left;
@@ -783,11 +796,17 @@ static struct hist_entry *hists__find_entry(struct hists *hists,
  */
 void hists__match(struct hists *leader, struct hists *other)
 {
+	struct rb_root *root;
 	struct rb_node *nd;
 	struct hist_entry *pos, *pair;
 
-	for (nd = rb_first(&leader->entries); nd; nd = rb_next(nd)) {
-		pos  = rb_entry(nd, struct hist_entry, rb_node);
+	if (sort__need_collapse)
+		root = &leader->entries_collapsed;
+	else
+		root = leader->entries_in;
+
+	for (nd = rb_first(root); nd; nd = rb_next(nd)) {
+		pos  = rb_entry(nd, struct hist_entry, rb_node_in);
 		pair = hists__find_entry(other, pos);
 
 		if (pair)
@@ -802,11 +821,17 @@ void hists__match(struct hists *leader, struct hists *other)
  */
 int hists__link(struct hists *leader, struct hists *other)
 {
+	struct rb_root *root;
 	struct rb_node *nd;
 	struct hist_entry *pos, *pair;
 
-	for (nd = rb_first(&other->entries); nd; nd = rb_next(nd)) {
-		pos = rb_entry(nd, struct hist_entry, rb_node);
+	if (sort__need_collapse)
+		root = &other->entries_collapsed;
+	else
+		root = other->entries_in;
+
+	for (nd = rb_first(root); nd; nd = rb_next(nd)) {
+		pos = rb_entry(nd, struct hist_entry, rb_node_in);
 
 		if (!hist_entry__has_pairs(pos)) {
 			pair = hists__add_dummy_entry(leader, pos);