diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 4a3b84dd4f41b7033293bc46119068d363307ca6..3201bdfa8c3f2b721390652d9afc75042e1d5d2e 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -76,163 +76,16 @@ static int report__config(const char *var, const char *value, void *cb)
 	return perf_default_config(var, value, cb);
 }
 
-static void report__inc_stats(struct report *rep, struct hist_entry *he)
+static void report__inc_stats(struct report *rep,
+			      struct hist_entry *he __maybe_unused)
 {
 	/*
-	 * The @he is either of a newly created one or an existing one
-	 * merging current sample.  We only want to count a new one so
-	 * checking ->nr_events being 1.
+	 * We cannot access @he at this time.  Just assume it's a new entry.
+	 * It'll be fixed once we have a callback mechanism in hist_iter.
 	 */
-	if (he->stat.nr_events == 1)
-		rep->nr_entries++;
-
-	/*
-	 * Only counts number of samples at this stage as it's more
-	 * natural to do it here and non-sample events are also
-	 * counted in perf_session_deliver_event().  The dump_trace
-	 * requires this info is ready before going to the output tree.
-	 */
-	hists__inc_nr_samples(he->hists, he->filtered);
-}
-
-static int report__add_mem_hist_entry(struct report *rep, struct addr_location *al,
-				      struct perf_sample *sample, struct perf_evsel *evsel)
-{
-	struct symbol *parent = NULL;
-	struct hist_entry *he;
-	struct mem_info *mi, *mx;
-	uint64_t cost;
-	int err = sample__resolve_callchain(sample, &parent, evsel, al, rep->max_stack);
-
-	if (err)
-		return err;
-
-	mi = sample__resolve_mem(sample, al);
-	if (!mi)
-		return -ENOMEM;
-
-	if (rep->hide_unresolved && !al->sym)
-		return 0;
-
-	cost = sample->weight;
-	if (!cost)
-		cost = 1;
-
-	/*
-	 * must pass period=weight in order to get the correct
-	 * sorting from hists__collapse_resort() which is solely
-	 * based on periods. We want sorting be done on nr_events * weight
-	 * and this is indirectly achieved by passing period=weight here
-	 * and the he_stat__add_period() function.
-	 */
-	he = __hists__add_entry(&evsel->hists, al, parent, NULL, mi,
-				cost, cost, 0);
-	if (!he)
-		return -ENOMEM;
-
-	if (ui__has_annotation()) {
-		err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
-		if (err)
-			goto out;
-
-		mx = he->mem_info;
-		err = addr_map_symbol__inc_samples(&mx->daddr, evsel->idx);
-		if (err)
-			goto out;
-	}
-
-	report__inc_stats(rep, he);
-
-	err = hist_entry__append_callchain(he, sample);
-out:
-	return err;
-}
-
-static int report__add_branch_hist_entry(struct report *rep, struct addr_location *al,
-					 struct perf_sample *sample, struct perf_evsel *evsel)
-{
-	struct symbol *parent = NULL;
-	unsigned i;
-	struct hist_entry *he;
-	struct branch_info *bi, *bx;
-	int err = sample__resolve_callchain(sample, &parent, evsel, al, rep->max_stack);
-
-	if (err)
-		return err;
-
-	bi = sample__resolve_bstack(sample, al);
-	if (!bi)
-		return -ENOMEM;
-
-	for (i = 0; i < sample->branch_stack->nr; i++) {
-		if (rep->hide_unresolved && !(bi[i].from.sym && bi[i].to.sym))
-			continue;
-
-		err = -ENOMEM;
-
-		/* overwrite the 'al' to branch-to info */
-		al->map = bi[i].to.map;
-		al->sym = bi[i].to.sym;
-		al->addr = bi[i].to.addr;
-		/*
-		 * The report shows the percentage of total branches captured
-		 * and not events sampled. Thus we use a pseudo period of 1.
-		 */
-		he = __hists__add_entry(&evsel->hists, al, parent, &bi[i], NULL,
-					1, 1, 0);
-		if (he) {
-			if (ui__has_annotation()) {
-				bx = he->branch_info;
-				err = addr_map_symbol__inc_samples(&bx->from,
-								   evsel->idx);
-				if (err)
-					goto out;
-
-				err = addr_map_symbol__inc_samples(&bx->to,
-								   evsel->idx);
-				if (err)
-					goto out;
-			}
-			report__inc_stats(rep, he);
-		} else
-			goto out;
-	}
-	err = 0;
-out:
-	free(bi);
-	return err;
+	rep->nr_entries++;
 }
 
-static int report__add_hist_entry(struct report *rep, struct perf_evsel *evsel,
-				  struct addr_location *al, struct perf_sample *sample)
-{
-	struct symbol *parent = NULL;
-	struct hist_entry *he;
-	int err = sample__resolve_callchain(sample, &parent, evsel, al, rep->max_stack);
-
-	if (err)
-		return err;
-
-	he = __hists__add_entry(&evsel->hists, al, parent, NULL, NULL,
-				sample->period, sample->weight,
-				sample->transaction);
-	if (he == NULL)
-		return -ENOMEM;
-
-	err = hist_entry__append_callchain(he, sample);
-	if (err)
-		goto out;
-
-	if (ui__has_annotation())
-		err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
-
-	report__inc_stats(rep, he);
-
-out:
-	return err;
-}
-
-
 static int process_sample_event(struct perf_tool *tool,
 				union perf_event *event,
 				struct perf_sample *sample,
@@ -241,6 +94,9 @@ static int process_sample_event(struct perf_tool *tool,
 {
 	struct report *rep = container_of(tool, struct report, tool);
 	struct addr_location al;
+	struct hist_entry_iter iter = {
+		.hide_unresolved = rep->hide_unresolved,
+	};
 	int ret;
 
 	if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
@@ -255,22 +111,22 @@ static int process_sample_event(struct perf_tool *tool,
 	if (rep->cpu_list && !test_bit(sample->cpu, rep->cpu_bitmap))
 		return 0;
 
-	if (sort__mode == SORT_MODE__BRANCH) {
-		ret = report__add_branch_hist_entry(rep, &al, sample, evsel);
-		if (ret < 0)
-			pr_debug("problem adding lbr entry, skipping event\n");
-	} else if (rep->mem_mode == 1) {
-		ret = report__add_mem_hist_entry(rep, &al, sample, evsel);
-		if (ret < 0)
-			pr_debug("problem adding mem entry, skipping event\n");
-	} else {
-		if (al.map != NULL)
-			al.map->dso->hit = 1;
-
-		ret = report__add_hist_entry(rep, evsel, &al, sample);
-		if (ret < 0)
-			pr_debug("problem incrementing symbol period, skipping event\n");
-	}
+	if (sort__mode == SORT_MODE__BRANCH)
+		iter.ops = &hist_iter_branch;
+	else if (rep->mem_mode)
+		iter.ops = &hist_iter_mem;
+	else
+		iter.ops = &hist_iter_normal;
+
+	if (al.map != NULL)
+		al.map->dso->hit = 1;
+
+	report__inc_stats(rep, NULL);
+
+	ret = hist_entry_iter__add(&iter, &al, evsel, sample, rep->max_stack);
+	if (ret < 0)
+		pr_debug("problem adding hist entry, skipping event\n");
+
 	return ret;
 }
 
diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c
index 0a71ef4b91583c4c8a667d314f9a0976ac5b4fc9..76b02e1de701a5d821507b856f587f468fbd6f34 100644
--- a/tools/perf/tests/hists_filter.c
+++ b/tools/perf/tests/hists_filter.c
@@ -42,11 +42,11 @@ static struct sample fake_samples[] = {
 	{ .pid = 300, .ip = 0xf0000 + 800, },
 };
 
-static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
+static int add_hist_entries(struct perf_evlist *evlist,
+			    struct machine *machine __maybe_unused)
 {
 	struct perf_evsel *evsel;
 	struct addr_location al;
-	struct hist_entry *he;
 	struct perf_sample sample = { .cpu = 0, };
 	size_t i;
 
@@ -62,6 +62,10 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 					.misc = PERF_RECORD_MISC_USER,
 				},
 			};
+			struct hist_entry_iter iter = {
+				.ops = &hist_iter_normal,
+				.hide_unresolved = false,
+			};
 
 			/* make sure it has no filter at first */
 			evsel->hists.thread_filter = NULL;
@@ -71,21 +75,19 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 			sample.pid = fake_samples[i].pid;
 			sample.tid = fake_samples[i].pid;
 			sample.ip = fake_samples[i].ip;
+			sample.period = 100;
 
 			if (perf_event__preprocess_sample(&event, machine, &al,
 							  &sample) < 0)
 				goto out;
 
-			he = __hists__add_entry(&evsel->hists, &al, NULL,
-						NULL, NULL, 100, 1, 0);
-			if (he == NULL)
+			if (hist_entry_iter__add(&iter, &al, evsel, &sample,
+						 PERF_MAX_STACK_DEPTH) < 0)
 				goto out;
 
 			fake_samples[i].thread = al.thread;
 			fake_samples[i].map = al.map;
 			fake_samples[i].sym = al.sym;
-
-			hists__inc_nr_samples(he->hists, he->filtered);
 		}
 	}
 
diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c
index a16850551797ea13fbf5d0dfc9cb93a136c5ec7d..1308f88a916948ebbcabd858eeb61b93c1664f57 100644
--- a/tools/perf/tests/hists_output.c
+++ b/tools/perf/tests/hists_output.c
@@ -46,7 +46,7 @@ static struct sample fake_samples[] = {
 static int add_hist_entries(struct hists *hists, struct machine *machine)
 {
 	struct addr_location al;
-	struct hist_entry *he;
+	struct perf_evsel *evsel = hists_to_evsel(hists);
 	struct perf_sample sample = { .period = 100, };
 	size_t i;
 
@@ -56,6 +56,10 @@ static int add_hist_entries(struct hists *hists, struct machine *machine)
 				.misc = PERF_RECORD_MISC_USER,
 			},
 		};
+		struct hist_entry_iter iter = {
+			.ops = &hist_iter_normal,
+			.hide_unresolved = false,
+		};
 
 		sample.cpu = fake_samples[i].cpu;
 		sample.pid = fake_samples[i].pid;
@@ -66,9 +70,8 @@ static int add_hist_entries(struct hists *hists, struct machine *machine)
 						  &sample) < 0)
 			goto out;
 
-		he = __hists__add_entry(hists, &al, NULL, NULL, NULL,
-					sample.period, 1, 0);
-		if (he == NULL)
+		if (hist_entry_iter__add(&iter, &al, evsel, &sample,
+					 PERF_MAX_STACK_DEPTH) < 0)
 			goto out;
 
 		fake_samples[i].thread = al.thread;
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 5943ba60f19335ccf49b7e2916327e3613414c75..d8662356de202ea26c45ee22d90a41f0f3dd1a42 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -4,6 +4,7 @@
 #include "session.h"
 #include "sort.h"
 #include "evsel.h"
+#include "annotate.h"
 #include <math.h>
 
 static bool hists__filter_entry_by_dso(struct hists *hists,
@@ -429,6 +430,304 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
 	return add_hist_entry(hists, &entry, al);
 }
 
+static int
+iter_next_nop_entry(struct hist_entry_iter *iter __maybe_unused,
+		    struct addr_location *al __maybe_unused)
+{
+	return 0;
+}
+
+static int
+iter_add_next_nop_entry(struct hist_entry_iter *iter __maybe_unused,
+			struct addr_location *al __maybe_unused)
+{
+	return 0;
+}
+
+static int
+iter_prepare_mem_entry(struct hist_entry_iter *iter, struct addr_location *al)
+{
+	struct perf_sample *sample = iter->sample;
+	struct mem_info *mi;
+
+	mi = sample__resolve_mem(sample, al);
+	if (mi == NULL)
+		return -ENOMEM;
+
+	iter->priv = mi;
+	return 0;
+}
+
+static int
+iter_add_single_mem_entry(struct hist_entry_iter *iter, struct addr_location *al)
+{
+	u64 cost;
+	struct mem_info *mi = iter->priv;
+	struct hist_entry *he;
+
+	if (mi == NULL)
+		return -EINVAL;
+
+	cost = iter->sample->weight;
+	if (!cost)
+		cost = 1;
+
+	/*
+	 * must pass period=weight in order to get the correct
+	 * sorting from hists__collapse_resort() which is solely
+	 * based on periods. We want sorting be done on nr_events * weight
+	 * and this is indirectly achieved by passing period=weight here
+	 * and the he_stat__add_period() function.
+	 */
+	he = __hists__add_entry(&iter->evsel->hists, al, iter->parent, NULL, mi,
+				cost, cost, 0);
+	if (!he)
+		return -ENOMEM;
+
+	iter->he = he;
+	return 0;
+}
+
+static int
+iter_finish_mem_entry(struct hist_entry_iter *iter, struct addr_location *al)
+{
+	struct perf_evsel *evsel = iter->evsel;
+	struct hist_entry *he = iter->he;
+	struct mem_info *mx;
+	int err = -EINVAL;
+
+	if (he == NULL)
+		goto out;
+
+	if (ui__has_annotation()) {
+		err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
+		if (err)
+			goto out;
+
+		mx = he->mem_info;
+		err = addr_map_symbol__inc_samples(&mx->daddr, evsel->idx);
+		if (err)
+			goto out;
+	}
+
+	hists__inc_nr_samples(&evsel->hists, he->filtered);
+
+	err = hist_entry__append_callchain(he, iter->sample);
+
+out:
+	/*
+	 * We don't need to free iter->priv (mem_info) here since
+	 * the mem info was either already freed in add_hist_entry() or
+	 * passed to a new hist entry by hist_entry__new().
+	 */
+	iter->priv = NULL;
+
+	iter->he = NULL;
+	return err;
+}
+
+static int
+iter_prepare_branch_entry(struct hist_entry_iter *iter, struct addr_location *al)
+{
+	struct branch_info *bi;
+	struct perf_sample *sample = iter->sample;
+
+	bi = sample__resolve_bstack(sample, al);
+	if (!bi)
+		return -ENOMEM;
+
+	iter->curr = 0;
+	iter->total = sample->branch_stack->nr;
+
+	iter->priv = bi;
+	return 0;
+}
+
+static int
+iter_add_single_branch_entry(struct hist_entry_iter *iter __maybe_unused,
+			     struct addr_location *al __maybe_unused)
+{
+	return 0;
+}
+
+static int
+iter_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *al)
+{
+	struct branch_info *bi = iter->priv;
+	int i = iter->curr;
+
+	if (bi == NULL)
+		return 0;
+
+	if (iter->curr >= iter->total)
+		return 0;
+
+	al->map = bi[i].to.map;
+	al->sym = bi[i].to.sym;
+	al->addr = bi[i].to.addr;
+	return 1;
+}
+
+static int
+iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *al)
+{
+	struct branch_info *bi, *bx;
+	struct perf_evsel *evsel = iter->evsel;
+	struct hist_entry *he = NULL;
+	int i = iter->curr;
+	int err = 0;
+
+	bi = iter->priv;
+
+	if (iter->hide_unresolved && !(bi[i].from.sym && bi[i].to.sym))
+		goto out;
+
+	/*
+	 * The report shows the percentage of total branches captured
+	 * 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);
+	if (he == NULL)
+		return -ENOMEM;
+
+	if (ui__has_annotation()) {
+		bx = he->branch_info;
+		err = addr_map_symbol__inc_samples(&bx->from, evsel->idx);
+		if (err)
+			goto out;
+
+		err = addr_map_symbol__inc_samples(&bx->to, evsel->idx);
+		if (err)
+			goto out;
+	}
+
+	hists__inc_nr_samples(&evsel->hists, he->filtered);
+
+out:
+	iter->he = he;
+	iter->curr++;
+	return err;
+}
+
+static int
+iter_finish_branch_entry(struct hist_entry_iter *iter,
+			 struct addr_location *al __maybe_unused)
+{
+	zfree(&iter->priv);
+	iter->he = NULL;
+
+	return iter->curr >= iter->total ? 0 : -1;
+}
+
+static int
+iter_prepare_normal_entry(struct hist_entry_iter *iter __maybe_unused,
+			  struct addr_location *al __maybe_unused)
+{
+	return 0;
+}
+
+static int
+iter_add_single_normal_entry(struct hist_entry_iter *iter, struct addr_location *al)
+{
+	struct perf_evsel *evsel = iter->evsel;
+	struct perf_sample *sample = iter->sample;
+	struct hist_entry *he;
+
+	he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL,
+				sample->period, sample->weight,
+				sample->transaction);
+	if (he == NULL)
+		return -ENOMEM;
+
+	iter->he = he;
+	return 0;
+}
+
+static int
+iter_finish_normal_entry(struct hist_entry_iter *iter, struct addr_location *al)
+{
+	int err;
+	struct hist_entry *he = iter->he;
+	struct perf_evsel *evsel = iter->evsel;
+	struct perf_sample *sample = iter->sample;
+
+	if (he == NULL)
+		return 0;
+
+	iter->he = NULL;
+
+	if (ui__has_annotation()) {
+		err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
+		if (err)
+			return err;
+	}
+
+	hists__inc_nr_samples(&evsel->hists, he->filtered);
+
+	return hist_entry__append_callchain(he, sample);
+}
+
+const struct hist_iter_ops hist_iter_mem = {
+	.prepare_entry 		= iter_prepare_mem_entry,
+	.add_single_entry 	= iter_add_single_mem_entry,
+	.next_entry 		= iter_next_nop_entry,
+	.add_next_entry 	= iter_add_next_nop_entry,
+	.finish_entry 		= iter_finish_mem_entry,
+};
+
+const struct hist_iter_ops hist_iter_branch = {
+	.prepare_entry 		= iter_prepare_branch_entry,
+	.add_single_entry 	= iter_add_single_branch_entry,
+	.next_entry 		= iter_next_branch_entry,
+	.add_next_entry 	= iter_add_next_branch_entry,
+	.finish_entry 		= iter_finish_branch_entry,
+};
+
+const struct hist_iter_ops hist_iter_normal = {
+	.prepare_entry 		= iter_prepare_normal_entry,
+	.add_single_entry 	= iter_add_single_normal_entry,
+	.next_entry 		= iter_next_nop_entry,
+	.add_next_entry 	= iter_add_next_nop_entry,
+	.finish_entry 		= iter_finish_normal_entry,
+};
+
+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)
+{
+	int err, err2;
+
+	err = sample__resolve_callchain(sample, &iter->parent, evsel, al,
+					max_stack_depth);
+	if (err)
+		return err;
+
+	iter->evsel = evsel;
+	iter->sample = sample;
+
+	err = iter->ops->prepare_entry(iter, al);
+	if (err)
+		goto out;
+
+	err = iter->ops->add_single_entry(iter, al);
+	if (err)
+		goto out;
+
+	while (iter->ops->next_entry(iter, al)) {
+		err = iter->ops->add_next_entry(iter, al);
+		if (err)
+			break;
+	}
+
+out:
+	err2 = iter->ops->finish_entry(iter, al);
+	if (!err)
+		err = err2;
+
+	return err;
+}
+
 int64_t
 hist_entry__cmp(struct hist_entry *left, struct hist_entry *right)
 {
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 03ae1dbb1b15745da68470ad3a065a34fddeeabd..8894f184357cd89e570447121eb7822ca1aac55c 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -96,12 +96,45 @@ struct hists {
 	u16			col_len[HISTC_NR_COLS];
 };
 
+struct hist_entry_iter;
+
+struct hist_iter_ops {
+	int (*prepare_entry)(struct hist_entry_iter *, struct addr_location *);
+	int (*add_single_entry)(struct hist_entry_iter *, struct addr_location *);
+	int (*next_entry)(struct hist_entry_iter *, struct addr_location *);
+	int (*add_next_entry)(struct hist_entry_iter *, struct addr_location *);
+	int (*finish_entry)(struct hist_entry_iter *, struct addr_location *);
+};
+
+struct hist_entry_iter {
+	int total;
+	int curr;
+
+	bool hide_unresolved;
+
+	struct perf_evsel *evsel;
+	struct perf_sample *sample;
+	struct hist_entry *he;
+	struct symbol *parent;
+	void *priv;
+
+	const struct hist_iter_ops *ops;
+};
+
+extern const struct hist_iter_ops hist_iter_normal;
+extern const struct hist_iter_ops hist_iter_branch;
+extern const struct hist_iter_ops hist_iter_mem;
+
 struct hist_entry *__hists__add_entry(struct hists *hists,
 				      struct addr_location *al,
 				      struct symbol *parent,
 				      struct branch_info *bi,
 				      struct mem_info *mi, u64 period,
 				      u64 weight, u64 transaction);
+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);
+
 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);