--- zzzz-none-000/linux-3.10.107/tools/perf/util/hist.c	2017-06-27 09:49:32.000000000 +0000
+++ scorpion-7490-727/linux-3.10.107/tools/perf/util/hist.c	2021-02-04 17:41:59.000000000 +0000
@@ -1,10 +1,12 @@
-#include "annotate.h"
 #include "util.h"
 #include "build-id.h"
 #include "hist.h"
 #include "session.h"
 #include "sort.h"
+#include "evlist.h"
 #include "evsel.h"
+#include "annotate.h"
+#include "ui/progress.h"
 #include <math.h>
 
 static bool hists__filter_entry_by_dso(struct hists *hists,
@@ -13,19 +15,8 @@
 					  struct hist_entry *he);
 static bool hists__filter_entry_by_symbol(struct hists *hists,
 					  struct hist_entry *he);
-
-enum hist_filter {
-	HIST_FILTER__DSO,
-	HIST_FILTER__THREAD,
-	HIST_FILTER__PARENT,
-	HIST_FILTER__SYMBOL,
-};
-
-struct callchain_param	callchain_param = {
-	.mode	= CHAIN_GRAPH_REL,
-	.min_percent = 0.5,
-	.order  = ORDER_CALLEE
-};
+static bool hists__filter_entry_by_socket(struct hists *hists,
+					  struct hist_entry *he);
 
 u16 hists__col_len(struct hists *hists, enum hist_column col)
 {
@@ -70,9 +61,17 @@
 	int symlen;
 	u16 len;
 
-	if (h->ms.sym)
-		hists__new_col_len(hists, HISTC_SYMBOL, h->ms.sym->namelen + 4);
-	else {
+	/*
+	 * +4 accounts for '[x] ' priv level info
+	 * +2 accounts for 0x prefix on raw addresses
+	 * +3 accounts for ' y ' symtab origin info
+	 */
+	if (h->ms.sym) {
+		symlen = h->ms.sym->namelen + 4;
+		if (verbose)
+			symlen += BITS_PER_LONG / 4 + 2 + 3;
+		hists__new_col_len(hists, HISTC_SYMBOL, symlen);
+	} else {
 		symlen = unresolved_col_width + 4 + 2;
 		hists__new_col_len(hists, HISTC_SYMBOL, symlen);
 		hists__set_unres_dso_col_len(hists, HISTC_DSO);
@@ -91,12 +90,10 @@
 		hists__new_col_len(hists, HISTC_PARENT, h->parent->namelen);
 
 	if (h->branch_info) {
-		/*
-		 * +4 accounts for '[x] ' priv level info
-		 * +2 account of 0x prefix on raw addresses
-		 */
 		if (h->branch_info->from.sym) {
 			symlen = (int)h->branch_info->from.sym->namelen + 4;
+			if (verbose)
+				symlen += BITS_PER_LONG / 4 + 2 + 3;
 			hists__new_col_len(hists, HISTC_SYMBOL_FROM, symlen);
 
 			symlen = dso__name_len(h->branch_info->from.map->dso);
@@ -109,6 +106,8 @@
 
 		if (h->branch_info->to.sym) {
 			symlen = (int)h->branch_info->to.sym->namelen + 4;
+			if (verbose)
+				symlen += BITS_PER_LONG / 4 + 2 + 3;
 			hists__new_col_len(hists, HISTC_SYMBOL_TO, symlen);
 
 			symlen = dso__name_len(h->branch_info->to.map->dso);
@@ -121,20 +120,30 @@
 	}
 
 	if (h->mem_info) {
-		/*
-		 * +4 accounts for '[x] ' priv level info
-		 * +2 account of 0x prefix on raw addresses
-		 */
 		if (h->mem_info->daddr.sym) {
 			symlen = (int)h->mem_info->daddr.sym->namelen + 4
 			       + unresolved_col_width + 2;
 			hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL,
 					   symlen);
+			hists__new_col_len(hists, HISTC_MEM_DCACHELINE,
+					   symlen + 1);
 		} else {
 			symlen = unresolved_col_width + 4 + 2;
 			hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL,
 					   symlen);
 		}
+
+		if (h->mem_info->iaddr.sym) {
+			symlen = (int)h->mem_info->iaddr.sym->namelen + 4
+			       + unresolved_col_width + 2;
+			hists__new_col_len(hists, HISTC_MEM_IADDR_SYMBOL,
+					   symlen);
+		} else {
+			symlen = unresolved_col_width + 4 + 2;
+			hists__new_col_len(hists, HISTC_MEM_IADDR_SYMBOL,
+					   symlen);
+		}
+
 		if (h->mem_info->daddr.map) {
 			symlen = dso__name_len(h->mem_info->daddr.map->dso);
 			hists__new_col_len(hists, HISTC_MEM_DADDR_DSO,
@@ -146,15 +155,28 @@
 	} else {
 		symlen = unresolved_col_width + 4 + 2;
 		hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL, symlen);
+		hists__new_col_len(hists, HISTC_MEM_IADDR_SYMBOL, symlen);
 		hists__set_unres_dso_col_len(hists, HISTC_MEM_DADDR_DSO);
 	}
 
+	hists__new_col_len(hists, HISTC_CPU, 3);
+	hists__new_col_len(hists, HISTC_SOCKET, 6);
 	hists__new_col_len(hists, HISTC_MEM_LOCKED, 6);
 	hists__new_col_len(hists, HISTC_MEM_TLB, 22);
 	hists__new_col_len(hists, HISTC_MEM_SNOOP, 12);
 	hists__new_col_len(hists, HISTC_MEM_LVL, 21 + 3);
 	hists__new_col_len(hists, HISTC_LOCAL_WEIGHT, 12);
 	hists__new_col_len(hists, HISTC_GLOBAL_WEIGHT, 12);
+
+	if (h->srcline)
+		hists__new_col_len(hists, HISTC_SRCLINE, strlen(h->srcline));
+
+	if (h->srcfile)
+		hists__new_col_len(hists, HISTC_SRCFILE, strlen(h->srcfile));
+
+	if (h->transaction)
+		hists__new_col_len(hists, HISTC_TRANSACTION,
+				   hist_entry__transaction_len());
 }
 
 void hists__output_recalc_col_len(struct hists *hists, int max_rows)
@@ -173,21 +195,21 @@
 	}
 }
 
-static void hist_entry__add_cpumode_period(struct hist_entry *he,
-					   unsigned int cpumode, u64 period)
+static void he_stat__add_cpumode_period(struct he_stat *he_stat,
+					unsigned int cpumode, u64 period)
 {
 	switch (cpumode) {
 	case PERF_RECORD_MISC_KERNEL:
-		he->stat.period_sys += period;
+		he_stat->period_sys += period;
 		break;
 	case PERF_RECORD_MISC_USER:
-		he->stat.period_us += period;
+		he_stat->period_us += period;
 		break;
 	case PERF_RECORD_MISC_GUEST_KERNEL:
-		he->stat.period_guest_sys += period;
+		he_stat->period_guest_sys += period;
 		break;
 	case PERF_RECORD_MISC_GUEST_USER:
-		he->stat.period_guest_us += period;
+		he_stat->period_guest_us += period;
 		break;
 	default:
 		break;
@@ -214,30 +236,49 @@
 	dest->weight		+= src->weight;
 }
 
-static void hist_entry__decay(struct hist_entry *he)
+static void he_stat__decay(struct he_stat *he_stat)
 {
-	he->stat.period = (he->stat.period * 7) / 8;
-	he->stat.nr_events = (he->stat.nr_events * 7) / 8;
+	he_stat->period = (he_stat->period * 7) / 8;
+	he_stat->nr_events = (he_stat->nr_events * 7) / 8;
 	/* XXX need decay for weight too? */
 }
 
 static bool hists__decay_entry(struct hists *hists, struct hist_entry *he)
 {
 	u64 prev_period = he->stat.period;
+	u64 diff;
 
 	if (prev_period == 0)
 		return true;
 
-	hist_entry__decay(he);
+	he_stat__decay(&he->stat);
+	if (symbol_conf.cumulate_callchain)
+		he_stat__decay(he->stat_acc);
 
+	diff = prev_period - he->stat.period;
+
+	hists->stats.total_period -= diff;
 	if (!he->filtered)
-		hists->stats.total_period -= prev_period - he->stat.period;
+		hists->stats.total_non_filtered_period -= diff;
 
 	return he->stat.period == 0;
 }
 
-static void __hists__decay_entries(struct hists *hists, bool zap_user,
-				   bool zap_kernel, bool threaded)
+static void hists__delete_entry(struct hists *hists, struct hist_entry *he)
+{
+	rb_erase(&he->rb_node, &hists->entries);
+
+	if (sort__need_collapse)
+		rb_erase(&he->rb_node_in, &hists->entries_collapsed);
+
+	--hists->nr_entries;
+	if (!he->filtered)
+		--hists->nr_non_filtered_entries;
+
+	hist_entry__delete(he);
+}
+
+void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel)
 {
 	struct rb_node *next = rb_first(&hists->entries);
 	struct hist_entry *n;
@@ -245,84 +286,94 @@
 	while (next) {
 		n = rb_entry(next, struct hist_entry, rb_node);
 		next = rb_next(&n->rb_node);
-		/*
-		 * We may be annotating this, for instance, so keep it here in
-		 * case some it gets new samples, we'll eventually free it when
-		 * the user stops browsing and it agains gets fully decayed.
-		 */
 		if (((zap_user && n->level == '.') ||
 		     (zap_kernel && n->level != '.') ||
-		     hists__decay_entry(hists, n)) &&
-		    !n->used) {
-			rb_erase(&n->rb_node, &hists->entries);
-
-			if (sort__need_collapse || threaded)
-				rb_erase(&n->rb_node_in, &hists->entries_collapsed);
-
-			hist_entry__free(n);
-			--hists->nr_entries;
+		     hists__decay_entry(hists, n))) {
+			hists__delete_entry(hists, n);
 		}
 	}
 }
 
-void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel)
+void hists__delete_entries(struct hists *hists)
 {
-	return __hists__decay_entries(hists, zap_user, zap_kernel, false);
-}
+	struct rb_node *next = rb_first(&hists->entries);
+	struct hist_entry *n;
 
-void hists__decay_entries_threaded(struct hists *hists,
-				   bool zap_user, bool zap_kernel)
-{
-	return __hists__decay_entries(hists, zap_user, zap_kernel, true);
+	while (next) {
+		n = rb_entry(next, struct hist_entry, rb_node);
+		next = rb_next(&n->rb_node);
+
+		hists__delete_entry(hists, n);
+	}
 }
 
 /*
  * 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 = symbol_conf.use_callchain ? sizeof(struct callchain_root) : 0;
-	struct hist_entry *he = zalloc(sizeof(*he) + callchain_size);
+	size_t callchain_size = 0;
+	struct hist_entry *he;
+
+	if (symbol_conf.use_callchain)
+		callchain_size = sizeof(struct callchain_root);
+
+	he = zalloc(sizeof(*he) + callchain_size);
 
 	if (he != NULL) {
 		*he = *template;
 
-		if (he->ms.map)
-			he->ms.map->referenced = true;
+		if (symbol_conf.cumulate_callchain) {
+			he->stat_acc = malloc(sizeof(he->stat));
+			if (he->stat_acc == NULL) {
+				free(he);
+				return NULL;
+			}
+			memcpy(he->stat_acc, &he->stat, sizeof(he->stat));
+			if (!sample_self)
+				memset(&he->stat, 0, sizeof(he->stat));
+		}
+
+		map__get(he->ms.map);
 
 		if (he->branch_info) {
-			if (he->branch_info->from.map)
-				he->branch_info->from.map->referenced = true;
-			if (he->branch_info->to.map)
-				he->branch_info->to.map->referenced = true;
+			/*
+			 * This branch info is (a part of) allocated from
+			 * sample__resolve_bstack() and will be freed after
+			 * adding new entries.  So we need to save a copy.
+			 */
+			he->branch_info = malloc(sizeof(*he->branch_info));
+			if (he->branch_info == NULL) {
+				map__zput(he->ms.map);
+				free(he->stat_acc);
+				free(he);
+				return NULL;
+			}
+
+			memcpy(he->branch_info, template->branch_info,
+			       sizeof(*he->branch_info));
+
+			map__get(he->branch_info->from.map);
+			map__get(he->branch_info->to.map);
 		}
 
 		if (he->mem_info) {
-			if (he->mem_info->iaddr.map)
-				he->mem_info->iaddr.map->referenced = true;
-			if (he->mem_info->daddr.map)
-				he->mem_info->daddr.map->referenced = true;
+			map__get(he->mem_info->iaddr.map);
+			map__get(he->mem_info->daddr.map);
 		}
 
 		if (symbol_conf.use_callchain)
 			callchain_init(he->callchain);
 
 		INIT_LIST_HEAD(&he->pairs.node);
+		thread__get(he->thread);
 	}
 
 	return he;
 }
 
-void hists__inc_nr_entries(struct hists *hists, struct hist_entry *h)
-{
-	if (!h->filtered) {
-		hists__calc_col_len(hists, h);
-		++hists->nr_entries;
-		hists->stats.total_period += h->stat.period;
-	}
-}
-
 static u8 symbol__parent_filter(const struct symbol *parent)
 {
 	if (symbol_conf.exclude_other && parent == NULL)
@@ -330,18 +381,17 @@
 	return 0;
 }
 
-static struct hist_entry *add_hist_entry(struct hists *hists,
-				      struct hist_entry *entry,
-				      struct addr_location *al,
-				      u64 period,
-				      u64 weight)
+static struct hist_entry *hists__findnew_entry(struct hists *hists,
+					       struct hist_entry *entry,
+					       struct addr_location *al,
+					       bool sample_self)
 {
 	struct rb_node **p;
 	struct rb_node *parent = NULL;
 	struct hist_entry *he;
-	int cmp;
-
-	pthread_mutex_lock(&hists->lock);
+	int64_t cmp;
+	u64 period = entry->stat.period;
+	u64 weight = entry->stat.weight;
 
 	p = &hists->entries_in->rb_node;
 
@@ -358,7 +408,16 @@
 		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);
+
+			/*
+			 * This mem info was allocated from sample__resolve_mem
+			 * and will not be used anymore.
+			 */
+			zfree(&entry->mem_info);
 
 			/* If the map of an existing hist_entry has
 			 * become out-of-date due to an exec() or
@@ -367,9 +426,8 @@
 			 * the history counter to increment.
 			 */
 			if (he->ms.map != entry->ms.map) {
-				he->ms.map = entry->ms.map;
-				if (he->ms.map)
-					he->ms.map->referenced = true;
+				map__put(he->ms.map);
+				he->ms.map = map__get(entry->ms.map);
 			}
 			goto out;
 		}
@@ -380,117 +438,496 @@
 			p = &(*p)->rb_right;
 	}
 
-	he = hist_entry__new(entry);
+	he = hist_entry__new(entry, sample_self);
 	if (!he)
-		goto out_unlock;
+		return NULL;
+
+	hists->nr_entries++;
 
 	rb_link_node(&he->rb_node_in, parent, p);
 	rb_insert_color(&he->rb_node_in, hists->entries_in);
 out:
-	hist_entry__add_cpumode_period(he, al->cpumode, period);
-out_unlock:
-	pthread_mutex_unlock(&hists->lock);
+	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;
 }
 
-struct hist_entry *__hists__add_mem_entry(struct hists *self,
-					  struct addr_location *al,
-					  struct symbol *sym_parent,
-					  struct mem_info *mi,
-					  u64 period,
-					  u64 weight)
+struct hist_entry *__hists__add_entry(struct hists *hists,
+				      struct addr_location *al,
+				      struct symbol *sym_parent,
+				      struct branch_info *bi,
+				      struct mem_info *mi,
+				      u64 period, u64 weight, u64 transaction,
+				      bool sample_self)
 {
 	struct hist_entry entry = {
 		.thread	= al->thread,
+		.comm = thread__comm(al->thread),
 		.ms = {
 			.map	= al->map,
 			.sym	= al->sym,
 		},
+		.socket	 = al->socket,
+		.cpu	 = al->cpu,
+		.cpumode = al->cpumode,
+		.ip	 = al->addr,
+		.level	 = al->level,
 		.stat = {
+			.nr_events = 1,
 			.period	= period,
 			.weight = weight,
-			.nr_events = 1,
 		},
-		.cpu	= al->cpu,
-		.ip	= al->addr,
-		.level	= al->level,
 		.parent = sym_parent,
-		.filtered = symbol__parent_filter(sym_parent),
-		.hists = self,
+		.filtered = symbol__parent_filter(sym_parent) | al->filtered,
+		.hists	= hists,
+		.branch_info = bi,
 		.mem_info = mi,
-		.branch_info = NULL,
+		.transaction = transaction,
 	};
-	return add_hist_entry(self, &entry, al, period, weight);
+
+	return hists__findnew_entry(hists, &entry, al, sample_self);
 }
 
-struct hist_entry *__hists__add_branch_entry(struct hists *self,
-					     struct addr_location *al,
-					     struct symbol *sym_parent,
-					     struct branch_info *bi,
-					     u64 period,
-					     u64 weight)
+static int
+iter_next_nop_entry(struct hist_entry_iter *iter __maybe_unused,
+		    struct addr_location *al __maybe_unused)
 {
-	struct hist_entry entry = {
-		.thread	= al->thread,
-		.ms = {
-			.map	= bi->to.map,
-			.sym	= bi->to.sym,
-		},
-		.cpu	= al->cpu,
-		.ip	= bi->to.addr,
-		.level	= al->level,
-		.stat = {
-			.period	= period,
-			.nr_events = 1,
-			.weight = weight,
-		},
-		.parent = sym_parent,
-		.filtered = symbol__parent_filter(sym_parent),
-		.branch_info = bi,
-		.hists	= self,
-		.mem_info = NULL,
-	};
+	return 0;
+}
 
-	return add_hist_entry(self, &entry, al, period, weight);
+static int
+iter_add_next_nop_entry(struct hist_entry_iter *iter __maybe_unused,
+			struct addr_location *al __maybe_unused)
+{
+	return 0;
 }
 
-struct hist_entry *__hists__add_entry(struct hists *self,
-				      struct addr_location *al,
-				      struct symbol *sym_parent, u64 period,
-				      u64 weight)
+static int
+iter_prepare_mem_entry(struct hist_entry_iter *iter, struct addr_location *al)
 {
-	struct hist_entry entry = {
-		.thread	= al->thread,
+	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 hists *hists = evsel__hists(iter->evsel);
+	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(hists, al, iter->parent, NULL, mi,
+				cost, cost, 0, true);
+	if (!he)
+		return -ENOMEM;
+
+	iter->he = he;
+	return 0;
+}
+
+static int
+iter_finish_mem_entry(struct hist_entry_iter *iter,
+		      struct addr_location *al __maybe_unused)
+{
+	struct perf_evsel *evsel = iter->evsel;
+	struct hists *hists = evsel__hists(evsel);
+	struct hist_entry *he = iter->he;
+	int err = -EINVAL;
+
+	if (he == NULL)
+		goto out;
+
+	hists__inc_nr_samples(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 hists__findnew_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)
+{
+	/* to avoid calling callback function */
+	iter->he = NULL;
+
+	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;
+	struct perf_evsel *evsel = iter->evsel;
+	struct hists *hists = evsel__hists(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(hists, al, iter->parent, &bi[i], NULL,
+				1, bi->flags.cycles ? bi->flags.cycles : 1,
+				0, true);
+	if (he == NULL)
+		return -ENOMEM;
+
+	hists__inc_nr_samples(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(evsel), al, iter->parent, NULL, NULL,
+				sample->period, sample->weight,
+				sample->transaction, true);
+	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 __maybe_unused)
+{
+	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;
+
+	hists__inc_nr_samples(evsel__hists(evsel), he->filtered);
+
+	return hist_entry__append_callchain(he, sample);
+}
+
+static int
+iter_prepare_cumulative_entry(struct hist_entry_iter *iter,
+			      struct addr_location *al __maybe_unused)
+{
+	struct hist_entry **he_cache;
+
+	callchain_cursor_commit(&callchain_cursor);
+
+	/*
+	 * This is for detecting cycles or recursions so that they're
+	 * cumulated only one time to prevent entries more than 100%
+	 * overhead.
+	 */
+	he_cache = malloc(sizeof(*he_cache) * (iter->max_stack + 1));
+	if (he_cache == NULL)
+		return -ENOMEM;
+
+	iter->priv = he_cache;
+	iter->curr = 0;
+
+	return 0;
+}
+
+static int
+iter_add_single_cumulative_entry(struct hist_entry_iter *iter,
+				 struct addr_location *al)
+{
+	struct perf_evsel *evsel = iter->evsel;
+	struct hists *hists = evsel__hists(evsel);
+	struct perf_sample *sample = iter->sample;
+	struct hist_entry **he_cache = iter->priv;
+	struct hist_entry *he;
+	int err = 0;
+
+	he = __hists__add_entry(hists, al, iter->parent, NULL, NULL,
+				sample->period, sample->weight,
+				sample->transaction, true);
+	if (he == NULL)
+		return -ENOMEM;
+
+	iter->he = he;
+	he_cache[iter->curr++] = he;
+
+	hist_entry__append_callchain(he, sample);
+
+	/*
+	 * We need to re-initialize the cursor since callchain_append()
+	 * advanced the cursor to the end.
+	 */
+	callchain_cursor_commit(&callchain_cursor);
+
+	hists__inc_nr_samples(hists, he->filtered);
+
+	return err;
+}
+
+static int
+iter_next_cumulative_entry(struct hist_entry_iter *iter,
+			   struct addr_location *al)
+{
+	struct callchain_cursor_node *node;
+
+	node = callchain_cursor_current(&callchain_cursor);
+	if (node == NULL)
+		return 0;
+
+	return fill_callchain_info(al, node, iter->hide_unresolved);
+}
+
+static int
+iter_add_next_cumulative_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_cache = iter->priv;
+	struct hist_entry *he;
+	struct hist_entry he_tmp = {
+		.hists = evsel__hists(evsel),
+		.cpu = al->cpu,
+		.thread = al->thread,
+		.comm = thread__comm(al->thread),
+		.ip = al->addr,
 		.ms = {
-			.map	= al->map,
-			.sym	= al->sym,
-		},
-		.cpu	= al->cpu,
-		.ip	= al->addr,
-		.level	= al->level,
-		.stat = {
-			.period	= period,
-			.nr_events = 1,
-			.weight = weight,
+			.map = al->map,
+			.sym = al->sym,
 		},
-		.parent = sym_parent,
-		.filtered = symbol__parent_filter(sym_parent),
-		.hists	= self,
-		.branch_info = NULL,
-		.mem_info = NULL,
+		.parent = iter->parent,
 	};
+	int i;
+	struct callchain_cursor cursor;
+
+	callchain_cursor_snapshot(&cursor, &callchain_cursor);
+
+	callchain_cursor_advance(&callchain_cursor);
+
+	/*
+	 * Check if there's duplicate entries in the callchain.
+	 * It's possible that it has cycles or recursive calls.
+	 */
+	for (i = 0; i < iter->curr; i++) {
+		if (hist_entry__cmp(he_cache[i], &he_tmp) == 0) {
+			/* to avoid calling callback function */
+			iter->he = NULL;
+			return 0;
+		}
+	}
+
+	he = __hists__add_entry(evsel__hists(evsel), al, iter->parent, NULL, NULL,
+				sample->period, sample->weight,
+				sample->transaction, false);
+	if (he == NULL)
+		return -ENOMEM;
+
+	iter->he = he;
+	he_cache[iter->curr++] = he;
+
+	if (symbol_conf.use_callchain)
+		callchain_append(he->callchain, &cursor, sample->period);
+	return 0;
+}
+
+static int
+iter_finish_cumulative_entry(struct hist_entry_iter *iter,
+			     struct addr_location *al __maybe_unused)
+{
+	zfree(&iter->priv);
+	iter->he = NULL;
+
+	return 0;
+}
+
+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,
+};
+
+const struct hist_iter_ops hist_iter_cumulative = {
+	.prepare_entry 		= iter_prepare_cumulative_entry,
+	.add_single_entry 	= iter_add_single_cumulative_entry,
+	.next_entry 		= iter_next_cumulative_entry,
+	.add_next_entry 	= iter_add_next_cumulative_entry,
+	.finish_entry 		= iter_finish_cumulative_entry,
+};
+
+int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
+			 int max_stack_depth, void *arg)
+{
+	int err, err2;
+
+	err = sample__resolve_callchain(iter->sample, &iter->parent,
+					iter->evsel, al, max_stack_depth);
+	if (err)
+		return err;
+
+	iter->max_stack = max_stack_depth;
+
+	err = iter->ops->prepare_entry(iter, al);
+	if (err)
+		goto out;
+
+	err = iter->ops->add_single_entry(iter, al);
+	if (err)
+		goto out;
 
-	return add_hist_entry(self, &entry, al, period, weight);
+	if (iter->he && iter->add_entry_cb) {
+		err = iter->add_entry_cb(iter, al, true, arg);
+		if (err)
+			goto out;
+	}
+
+	while (iter->ops->next_entry(iter, al)) {
+		err = iter->ops->add_next_entry(iter, al);
+		if (err)
+			break;
+
+		if (iter->he && iter->add_entry_cb) {
+			err = iter->add_entry_cb(iter, al, false, arg);
+			if (err)
+				goto out;
+		}
+	}
+
+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)
 {
-	struct sort_entry *se;
+	struct perf_hpp_fmt *fmt;
 	int64_t cmp = 0;
 
-	list_for_each_entry(se, &hist_entry__sort_list, list) {
-		cmp = se->se_cmp(left, right);
+	perf_hpp__for_each_sort_list(fmt) {
+		if (perf_hpp__should_skip(fmt))
+			continue;
+
+		cmp = fmt->cmp(fmt, left, right);
 		if (cmp)
 			break;
 	}
@@ -501,15 +938,14 @@
 int64_t
 hist_entry__collapse(struct hist_entry *left, struct hist_entry *right)
 {
-	struct sort_entry *se;
+	struct perf_hpp_fmt *fmt;
 	int64_t cmp = 0;
 
-	list_for_each_entry(se, &hist_entry__sort_list, list) {
-		int64_t (*f)(struct hist_entry *, struct hist_entry *);
-
-		f = se->se_collapse ?: se->se_cmp;
+	perf_hpp__for_each_sort_list(fmt) {
+		if (perf_hpp__should_skip(fmt))
+			continue;
 
-		cmp = f(left, right);
+		cmp = fmt->collapse(fmt, left, right);
 		if (cmp)
 			break;
 	}
@@ -517,10 +953,28 @@
 	return cmp;
 }
 
-void hist_entry__free(struct hist_entry *he)
+void hist_entry__delete(struct hist_entry *he)
 {
-	free(he->branch_info);
-	free(he->mem_info);
+	thread__zput(he->thread);
+	map__zput(he->ms.map);
+
+	if (he->branch_info) {
+		map__zput(he->branch_info->from.map);
+		map__zput(he->branch_info->to.map);
+		zfree(&he->branch_info);
+	}
+
+	if (he->mem_info) {
+		map__zput(he->mem_info->iaddr.map);
+		map__zput(he->mem_info->daddr.map);
+		zfree(&he->mem_info);
+	}
+
+	zfree(&he->stat_acc);
+	free_srcline(he->srcline);
+	if (he->srcfile && he->srcfile[0])
+		free(he->srcfile);
+	free_callchain(he->callchain);
 	free(he);
 }
 
@@ -545,6 +999,8 @@
 
 		if (!cmp) {
 			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);
@@ -552,7 +1008,7 @@
 						iter->callchain,
 						he->callchain);
 			}
-			hist_entry__free(he);
+			hist_entry__delete(he);
 			return false;
 		}
 
@@ -561,6 +1017,7 @@
 		else
 			p = &(*p)->rb_right;
 	}
+	hists->nr_entries++;
 
 	rb_link_node(&he->rb_node_in, parent, p);
 	rb_insert_color(&he->rb_node_in, root);
@@ -587,21 +1044,27 @@
 	hists__filter_entry_by_dso(hists, he);
 	hists__filter_entry_by_thread(hists, he);
 	hists__filter_entry_by_symbol(hists, he);
+	hists__filter_entry_by_socket(hists, he);
 }
 
-static void __hists__collapse_resort(struct hists *hists, bool threaded)
+void hists__collapse_resort(struct hists *hists, struct ui_progress *prog)
 {
 	struct rb_root *root;
 	struct rb_node *next;
 	struct hist_entry *n;
 
-	if (!sort__need_collapse && !threaded)
+	if (!sort__need_collapse)
 		return;
 
+	hists->nr_entries = 0;
+
 	root = hists__get_rotate_entries_in(hists);
+
 	next = rb_first(root);
 
 	while (next) {
+		if (session_done())
+			break;
 		n = rb_entry(next, struct hist_entry, rb_node_in);
 		next = rb_next(&n->rb_node_in);
 
@@ -614,88 +1077,67 @@
 			 */
 			hists__apply_filters(hists, n);
 		}
+		if (prog)
+			ui_progress__update(prog, 1);
 	}
 }
 
-void hists__collapse_resort(struct hists *hists)
+static int hist_entry__sort(struct hist_entry *a, struct hist_entry *b)
 {
-	return __hists__collapse_resort(hists, false);
-}
+	struct perf_hpp_fmt *fmt;
+	int64_t cmp = 0;
 
-void hists__collapse_resort_threaded(struct hists *hists)
-{
-	return __hists__collapse_resort(hists, true);
-}
+	perf_hpp__for_each_sort_list(fmt) {
+		if (perf_hpp__should_skip(fmt))
+			continue;
 
-/*
- * reverse the map, sort on period.
- */
+		cmp = fmt->sort(fmt, a, b);
+		if (cmp)
+			break;
+	}
 
-static int period_cmp(u64 period_a, u64 period_b)
-{
-	if (period_a > period_b)
-		return 1;
-	if (period_a < period_b)
-		return -1;
-	return 0;
+	return cmp;
 }
 
-static int hist_entry__sort_on_period(struct hist_entry *a,
-				      struct hist_entry *b)
+static void hists__reset_filter_stats(struct hists *hists)
 {
-	int ret;
-	int i, nr_members;
-	struct perf_evsel *evsel;
-	struct hist_entry *pair;
-	u64 *periods_a, *periods_b;
-
-	ret = period_cmp(a->stat.period, b->stat.period);
-	if (ret || !symbol_conf.event_group)
-		return ret;
-
-	evsel = hists_to_evsel(a->hists);
-	nr_members = evsel->nr_members;
-	if (nr_members <= 1)
-		return ret;
-
-	periods_a = zalloc(sizeof(periods_a) * nr_members);
-	periods_b = zalloc(sizeof(periods_b) * nr_members);
-
-	if (!periods_a || !periods_b)
-		goto out;
+	hists->nr_non_filtered_entries = 0;
+	hists->stats.total_non_filtered_period = 0;
+}
 
-	list_for_each_entry(pair, &a->pairs.head, pairs.node) {
-		evsel = hists_to_evsel(pair->hists);
-		periods_a[perf_evsel__group_idx(evsel)] = pair->stat.period;
-	}
+void hists__reset_stats(struct hists *hists)
+{
+	hists->nr_entries = 0;
+	hists->stats.total_period = 0;
 
-	list_for_each_entry(pair, &b->pairs.head, pairs.node) {
-		evsel = hists_to_evsel(pair->hists);
-		periods_b[perf_evsel__group_idx(evsel)] = pair->stat.period;
-	}
+	hists__reset_filter_stats(hists);
+}
 
-	for (i = 1; i < nr_members; i++) {
-		ret = period_cmp(periods_a[i], periods_b[i]);
-		if (ret)
-			break;
-	}
+static void hists__inc_filter_stats(struct hists *hists, struct hist_entry *h)
+{
+	hists->nr_non_filtered_entries++;
+	hists->stats.total_non_filtered_period += h->stat.period;
+}
 
-out:
-	free(periods_a);
-	free(periods_b);
+void hists__inc_stats(struct hists *hists, struct hist_entry *h)
+{
+	if (!h->filtered)
+		hists__inc_filter_stats(hists, h);
 
-	return ret;
+	hists->nr_entries++;
+	hists->stats.total_period += h->stat.period;
 }
 
 static void __hists__insert_output_entry(struct rb_root *entries,
 					 struct hist_entry *he,
-					 u64 min_callchain_hits)
+					 u64 min_callchain_hits,
+					 bool use_callchain)
 {
 	struct rb_node **p = &entries->rb_node;
 	struct rb_node *parent = NULL;
 	struct hist_entry *iter;
 
-	if (symbol_conf.use_callchain)
+	if (use_callchain)
 		callchain_param.sort(&he->sorted_chain, he->callchain,
 				      min_callchain_hits, &callchain_param);
 
@@ -703,7 +1145,7 @@
 		parent = *p;
 		iter = rb_entry(parent, struct hist_entry, rb_node);
 
-		if (hist_entry__sort_on_period(he, iter) > 0)
+		if (hist_entry__sort(he, iter) > 0)
 			p = &(*p)->rb_left;
 		else
 			p = &(*p)->rb_right;
@@ -713,16 +1155,23 @@
 	rb_insert_color(&he->rb_node, entries);
 }
 
-static void __hists__output_resort(struct hists *hists, bool threaded)
+void hists__output_resort(struct hists *hists, struct ui_progress *prog)
 {
 	struct rb_root *root;
 	struct rb_node *next;
 	struct hist_entry *n;
 	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;
 
 	min_callchain_hits = hists->stats.total_period * (callchain_param.min_percent / 100);
 
-	if (sort__need_collapse || threaded)
+	if (sort__need_collapse)
 		root = &hists->entries_collapsed;
 	else
 		root = hists->entries_in;
@@ -730,27 +1179,22 @@
 	next = rb_first(root);
 	hists->entries = RB_ROOT;
 
-	hists->nr_entries = 0;
-	hists->stats.total_period = 0;
+	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);
 
-		__hists__insert_output_entry(&hists->entries, n, min_callchain_hits);
-		hists__inc_nr_entries(hists, n);
-	}
-}
+		__hists__insert_output_entry(&hists->entries, n, min_callchain_hits, use_callchain);
+		hists__inc_stats(hists, n);
 
-void hists__output_resort(struct hists *hists)
-{
-	return __hists__output_resort(hists, false);
-}
+		if (!n->filtered)
+			hists__calc_col_len(hists, n);
 
-void hists__output_resort_threaded(struct hists *hists)
-{
-	return __hists__output_resort(hists, true);
+		if (prog)
+			ui_progress__update(prog, 1);
+	}
 }
 
 static void hists__remove_entry_filter(struct hists *hists, struct hist_entry *h,
@@ -760,13 +1204,14 @@
 	if (h->filtered)
 		return;
 
-	++hists->nr_entries;
-	if (h->ms.unfolded)
-		hists->nr_entries += h->nr_rows;
+	/* force fold unfiltered entry for simplicity */
+	h->unfolded = false;
 	h->row_offset = 0;
-	hists->stats.total_period += h->stat.period;
-	hists->stats.nr_events[PERF_RECORD_SAMPLE] += h->stat.nr_events;
+	h->nr_rows = 0;
+
+	hists->stats.nr_non_filtered_samples += h->stat.nr_events;
 
+	hists__inc_filter_stats(hists, h);
 	hists__calc_col_len(hists, h);
 }
 
@@ -787,8 +1232,9 @@
 {
 	struct rb_node *nd;
 
-	hists->nr_entries = hists->stats.total_period = 0;
-	hists->stats.nr_events[PERF_RECORD_SAMPLE] = 0;
+	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)) {
@@ -820,8 +1266,9 @@
 {
 	struct rb_node *nd;
 
-	hists->nr_entries = hists->stats.total_period = 0;
-	hists->stats.nr_events[PERF_RECORD_SAMPLE] = 0;
+	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)) {
@@ -851,8 +1298,9 @@
 {
 	struct rb_node *nd;
 
-	hists->nr_entries = hists->stats.total_period = 0;
-	hists->stats.nr_events[PERF_RECORD_SAMPLE] = 0;
+	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)) {
@@ -865,14 +1313,35 @@
 	}
 }
 
-int hist_entry__inc_addr_samples(struct hist_entry *he, int evidx, u64 ip)
+static bool hists__filter_entry_by_socket(struct hists *hists,
+					  struct hist_entry *he)
 {
-	return symbol__inc_addr_samples(he->ms.sym, he->ms.map, evidx, ip);
+	if ((hists->socket_filter > -1) &&
+	    (he->socket != hists->socket_filter)) {
+		he->filtered |= (1 << HIST_FILTER__SOCKET);
+		return true;
+	}
+
+	return false;
 }
 
-int hist_entry__annotate(struct hist_entry *he, size_t privsize)
+void hists__filter_by_socket(struct hists *hists)
 {
-	return symbol__annotate(he->ms.sym, he->ms.map, privsize);
+	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_socket(hists, h))
+			continue;
+
+		hists__remove_entry_filter(hists, h, HIST_FILTER__SOCKET);
+	}
 }
 
 void events_stats__inc(struct events_stats *stats, u32 type)
@@ -886,6 +1355,13 @@
 	events_stats__inc(&hists->stats, type);
 }
 
+void hists__inc_nr_samples(struct hists *hists, bool filtered)
+{
+	events_stats__inc(&hists->stats, PERF_RECORD_SAMPLE);
+	if (!filtered)
+		hists->stats.nr_non_filtered_samples++;
+}
+
 static struct hist_entry *hists__add_dummy_entry(struct hists *hists,
 						 struct hist_entry *pair)
 {
@@ -893,7 +1369,7 @@
 	struct rb_node **p;
 	struct rb_node *parent = NULL;
 	struct hist_entry *he;
-	int cmp;
+	int64_t cmp;
 
 	if (sort__need_collapse)
 		root = &hists->entries_collapsed;
@@ -917,13 +1393,14 @@
 			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;
 		rb_link_node(&he->rb_node_in, parent, p);
 		rb_insert_color(&he->rb_node_in, root);
-		hists__inc_nr_entries(hists, he);
+		hists__inc_stats(hists, he);
+		he->dummy = true;
 	}
 out:
 	return he;
@@ -1006,3 +1483,107 @@
 
 	return 0;
 }
+
+void hist__account_cycles(struct branch_stack *bs, struct addr_location *al,
+			  struct perf_sample *sample, bool nonany_branch_mode)
+{
+	struct branch_info *bi;
+
+	/* If we have branch cycles always annotate them. */
+	if (bs && bs->nr && bs->entries[0].flags.cycles) {
+		int i;
+
+		bi = sample__resolve_bstack(sample, al);
+		if (bi) {
+			struct addr_map_symbol *prev = NULL;
+
+			/*
+			 * Ignore errors, still want to process the
+			 * other entries.
+			 *
+			 * For non standard branch modes always
+			 * force no IPC (prev == NULL)
+			 *
+			 * Note that perf stores branches reversed from
+			 * program order!
+			 */
+			for (i = bs->nr - 1; i >= 0; i--) {
+				addr_map_symbol__account_cycles(&bi[i].from,
+					nonany_branch_mode ? NULL : prev,
+					bi[i].flags.cycles);
+				prev = &bi[i].to;
+			}
+			free(bi);
+		}
+	}
+}
+
+size_t perf_evlist__fprintf_nr_events(struct perf_evlist *evlist, FILE *fp)
+{
+	struct perf_evsel *pos;
+	size_t ret = 0;
+
+	evlist__for_each(evlist, pos) {
+		ret += fprintf(fp, "%s stats:\n", perf_evsel__name(pos));
+		ret += events_stats__fprintf(&evsel__hists(pos)->stats, fp);
+	}
+
+	return ret;
+}
+
+
+u64 hists__total_period(struct hists *hists)
+{
+	return symbol_conf.filter_relative ? hists->stats.total_non_filtered_period :
+		hists->stats.total_period;
+}
+
+int parse_filter_percentage(const struct option *opt __maybe_unused,
+			    const char *arg, int unset __maybe_unused)
+{
+	if (!strcmp(arg, "relative"))
+		symbol_conf.filter_relative = true;
+	else if (!strcmp(arg, "absolute"))
+		symbol_conf.filter_relative = false;
+	else
+		return -1;
+
+	return 0;
+}
+
+int perf_hist_config(const char *var, const char *value)
+{
+	if (!strcmp(var, "hist.percentage"))
+		return parse_filter_percentage(NULL, value, 0);
+
+	return 0;
+}
+
+static int hists_evsel__init(struct perf_evsel *evsel)
+{
+	struct hists *hists = evsel__hists(evsel);
+
+	memset(hists, 0, sizeof(*hists));
+	hists->entries_in_array[0] = hists->entries_in_array[1] = RB_ROOT;
+	hists->entries_in = &hists->entries_in_array[0];
+	hists->entries_collapsed = RB_ROOT;
+	hists->entries = RB_ROOT;
+	pthread_mutex_init(&hists->lock, NULL);
+	hists->socket_filter = -1;
+	return 0;
+}
+
+/*
+ * XXX We probably need a hists_evsel__exit() to free the hist_entries
+ * stored in the rbtree...
+ */
+
+int hists__init(void)
+{
+	int err = perf_evsel__object_config(sizeof(struct hists_evsel),
+					    hists_evsel__init, NULL);
+	if (err)
+		fputs("FATAL ERROR: Couldn't setup hists class\n", stderr);
+
+	return err;
+}