diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index be5939418425..e7417fe97a97 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -51,6 +51,7 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel,
 				  struct addr_location *al,
 				  struct perf_annotate *ann)
 {
+	struct hists *hists = evsel__hists(evsel);
 	struct hist_entry *he;
 	int ret;
 
@@ -66,13 +67,12 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel,
 		return 0;
 	}
 
-	he = __hists__add_entry(&evsel->hists, al, NULL, NULL, NULL, 1, 1, 0,
-				true);
+	he = __hists__add_entry(hists, al, NULL, NULL, NULL, 1, 1, 0, true);
 	if (he == NULL)
 		return -ENOMEM;
 
 	ret = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
-	hists__inc_nr_samples(&evsel->hists, true);
+	hists__inc_nr_samples(hists, true);
 	return ret;
 }
 
@@ -214,6 +214,7 @@ static int __cmd_annotate(struct perf_annotate *ann)
 
 	if (dump_trace) {
 		perf_session__fprintf_nr_events(session, stdout);
+		perf_evlist__fprintf_nr_events(session->evlist, stdout);
 		goto out;
 	}
 
@@ -225,7 +226,7 @@ static int __cmd_annotate(struct perf_annotate *ann)
 
 	total_nr_samples = 0;
 	evlist__for_each(session->evlist, pos) {
-		struct hists *hists = &pos->hists;
+		struct hists *hists = evsel__hists(pos);
 		u32 nr_samples = hists->stats.nr_events[PERF_RECORD_SAMPLE];
 
 		if (nr_samples > 0) {
@@ -325,7 +326,10 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
 		    "Show event group information together"),
 	OPT_END()
 	};
-	int ret;
+	int ret = hists__init();
+
+	if (ret < 0)
+		return ret;
 
 	argc = parse_options(argc, argv, options, annotate_usage, 0);
 
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index a3ce19f7aebd..8c5c11ca8c53 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -327,6 +327,7 @@ static int diff__process_sample_event(struct perf_tool *tool __maybe_unused,
 				      struct machine *machine)
 {
 	struct addr_location al;
+	struct hists *hists = evsel__hists(evsel);
 
 	if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
 		pr_warning("problem processing %d event, skipping it.\n",
@@ -334,7 +335,7 @@ static int diff__process_sample_event(struct perf_tool *tool __maybe_unused,
 		return -1;
 	}
 
-	if (hists__add_entry(&evsel->hists, &al, sample->period,
+	if (hists__add_entry(hists, &al, sample->period,
 			     sample->weight, sample->transaction)) {
 		pr_warning("problem incrementing symbol period, skipping event\n");
 		return -1;
@@ -346,9 +347,9 @@ static int diff__process_sample_event(struct perf_tool *tool __maybe_unused,
 	 * hists__output_resort() and precompute needs the total
 	 * period in order to sort entries by percentage delta.
 	 */
-	evsel->hists.stats.total_period += sample->period;
+	hists->stats.total_period += sample->period;
 	if (!al.filtered)
-		evsel->hists.stats.total_non_filtered_period += sample->period;
+		hists->stats.total_non_filtered_period += sample->period;
 
 	return 0;
 }
@@ -382,7 +383,7 @@ static void perf_evlist__collapse_resort(struct perf_evlist *evlist)
 	struct perf_evsel *evsel;
 
 	evlist__for_each(evlist, evsel) {
-		struct hists *hists = &evsel->hists;
+		struct hists *hists = evsel__hists(evsel);
 
 		hists__collapse_resort(hists, NULL);
 	}
@@ -631,24 +632,26 @@ static void data_process(void)
 	bool first = true;
 
 	evlist__for_each(evlist_base, evsel_base) {
+		struct hists *hists_base = evsel__hists(evsel_base);
 		struct data__file *d;
 		int i;
 
 		data__for_each_file_new(i, d) {
 			struct perf_evlist *evlist = d->session->evlist;
 			struct perf_evsel *evsel;
+			struct hists *hists;
 
 			evsel = evsel_match(evsel_base, evlist);
 			if (!evsel)
 				continue;
 
-			d->hists = &evsel->hists;
+			hists = evsel__hists(evsel);
+			d->hists = hists;
 
-			hists__match(&evsel_base->hists, &evsel->hists);
+			hists__match(hists_base, hists);
 
 			if (!show_baseline_only)
-				hists__link(&evsel_base->hists,
-					    &evsel->hists);
+				hists__link(hists_base, hists);
 		}
 
 		fprintf(stdout, "%s# Event '%s'\n#\n", first ? "" : "\n",
@@ -659,7 +662,7 @@ static void data_process(void)
 		if (verbose || data__files_cnt > 2)
 			data__fprintf();
 
-		hists__process(&evsel_base->hists);
+		hists__process(hists_base);
 	}
 }
 
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index d8bf2271f4ea..460a4ce9c044 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -896,8 +896,7 @@ static int perf_kvm__handle_stdin(void)
 
 static int kvm_events_live_report(struct perf_kvm_stat *kvm)
 {
-	struct pollfd *pollfds = NULL;
-	int nr_fds, nr_stdin, ret, err = -EINVAL;
+	int nr_stdin, ret, err = -EINVAL;
 	struct termios save;
 
 	/* live flag must be set first */
@@ -919,34 +918,27 @@ static int kvm_events_live_report(struct perf_kvm_stat *kvm)
 	signal(SIGINT, sig_handler);
 	signal(SIGTERM, sig_handler);
 
-	/* use pollfds -- need to add timerfd and stdin */
-	nr_fds = kvm->evlist->pollfd.nr;
-
 	/* add timer fd */
 	if (perf_kvm__timerfd_create(kvm) < 0) {
 		err = -1;
 		goto out;
 	}
 
-	if (perf_evlist__add_pollfd(kvm->evlist, kvm->timerfd))
+	if (perf_evlist__add_pollfd(kvm->evlist, kvm->timerfd) < 0)
 		goto out;
 
-	nr_fds++;
-
-	if (perf_evlist__add_pollfd(kvm->evlist, fileno(stdin)))
+	nr_stdin = perf_evlist__add_pollfd(kvm->evlist, fileno(stdin));
+	if (nr_stdin < 0)
 		goto out;
 
-	nr_stdin = nr_fds;
-	nr_fds++;
 	if (fd_set_nonblock(fileno(stdin)) != 0)
 		goto out;
 
-	pollfds	 = kvm->evlist->pollfd.entries;
-
 	/* everything is good - enable the events and process */
 	perf_evlist__enable(kvm->evlist);
 
 	while (!done) {
+		struct fdarray *fda = &kvm->evlist->pollfd;
 		int rc;
 
 		rc = perf_kvm__mmap_read(kvm);
@@ -957,11 +949,11 @@ static int kvm_events_live_report(struct perf_kvm_stat *kvm)
 		if (err)
 			goto out;
 
-		if (pollfds[nr_stdin].revents & POLLIN)
+		if (fda->entries[nr_stdin].revents & POLLIN)
 			done = perf_kvm__handle_stdin();
 
 		if (!rc && !done)
-			err = poll(pollfds, nr_fds, 100);
+			err = fdarray__poll(fda, 100);
 	}
 
 	perf_evlist__disable(kvm->evlist);
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 44c6f3d55ce7..a6b2132c666f 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -14,6 +14,7 @@
 #include "util/parse-options.h"
 #include "util/parse-events.h"
 
+#include "util/callchain.h"
 #include "util/header.h"
 #include "util/event.h"
 #include "util/evlist.h"
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index ac145fae0521..2cfc4b93991f 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -288,12 +288,14 @@ static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report
 		evname = buf;
 
 		for_each_group_member(pos, evsel) {
+			const struct hists *pos_hists = evsel__hists(pos);
+
 			if (symbol_conf.filter_relative) {
-				nr_samples += pos->hists.stats.nr_non_filtered_samples;
-				nr_events += pos->hists.stats.total_non_filtered_period;
+				nr_samples += pos_hists->stats.nr_non_filtered_samples;
+				nr_events += pos_hists->stats.total_non_filtered_period;
 			} else {
-				nr_samples += pos->hists.stats.nr_events[PERF_RECORD_SAMPLE];
-				nr_events += pos->hists.stats.total_period;
+				nr_samples += pos_hists->stats.nr_events[PERF_RECORD_SAMPLE];
+				nr_events += pos_hists->stats.total_period;
 			}
 		}
 	}
@@ -318,7 +320,7 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
 	struct perf_evsel *pos;
 
 	evlist__for_each(evlist, pos) {
-		struct hists *hists = &pos->hists;
+		struct hists *hists = evsel__hists(pos);
 		const char *evname = perf_evsel__name(pos);
 
 		if (symbol_conf.event_group &&
@@ -427,7 +429,7 @@ static void report__collapse_hists(struct report *rep)
 	ui_progress__init(&prog, rep->nr_entries, "Merging related events...");
 
 	evlist__for_each(rep->session->evlist, pos) {
-		struct hists *hists = &pos->hists;
+		struct hists *hists = evsel__hists(pos);
 
 		if (pos->idx == 0)
 			hists->symbol_filter_str = rep->symbol_filter_str;
@@ -437,7 +439,7 @@ static void report__collapse_hists(struct report *rep)
 		/* Non-group events are considered as leader */
 		if (symbol_conf.event_group &&
 		    !perf_evsel__is_group_leader(pos)) {
-			struct hists *leader_hists = &pos->leader->hists;
+			struct hists *leader_hists = evsel__hists(pos->leader);
 
 			hists__match(leader_hists, hists);
 			hists__link(leader_hists, hists);
@@ -485,6 +487,7 @@ static int __cmd_report(struct report *rep)
 
 		if (dump_trace) {
 			perf_session__fprintf_nr_events(session, stdout);
+			perf_evlist__fprintf_nr_events(session->evlist, stdout);
 			return 0;
 		}
 	}
@@ -500,7 +503,7 @@ static int __cmd_report(struct report *rep)
 	}
 
 	evlist__for_each(session->evlist, pos)
-		hists__output_resort(&pos->hists);
+		hists__output_resort(evsel__hists(pos));
 
 	return report__browse_hists(rep);
 }
@@ -565,7 +568,6 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 	struct stat st;
 	bool has_br_stack = false;
 	int branch_mode = -1;
-	int ret = -1;
 	char callchain_default_opt[] = "fractal,0.5,callee";
 	const char * const report_usage[] = {
 		"perf report [<options>]",
@@ -692,6 +694,10 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 	struct perf_data_file file = {
 		.mode  = PERF_DATA_MODE_READ,
 	};
+	int ret = hists__init();
+
+	if (ret < 0)
+		return ret;
 
 	perf_config(report__config, &report);
 
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 9c9287fbf8e9..891c3930080e 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -1431,9 +1431,6 @@ static int perf_sched__process_tracepoint_sample(struct perf_tool *tool __maybe_
 {
 	int err = 0;
 
-	evsel->hists.stats.total_period += sample->period;
-	hists__inc_nr_samples(&evsel->hists, true);
-
 	if (evsel->handler != NULL) {
 		tracepoint_handler f = evsel->handler;
 		err = f(tool, evsel, sample, machine);
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index b9b9e58a6c39..6b4925f65bf0 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -572,7 +572,6 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 
 	scripting_ops->process_event(event, sample, evsel, thread, &al);
 
-	evsel->hists.stats.total_period += sample->period;
 	return 0;
 }
 
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index fc3d55f832ac..0aa7747ff139 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -251,6 +251,7 @@ static void perf_top__print_sym_table(struct perf_top *top)
 	char bf[160];
 	int printed = 0;
 	const int win_width = top->winsize.ws_col - 1;
+	struct hists *hists = evsel__hists(top->sym_evsel);
 
 	puts(CONSOLE_CLEAR);
 
@@ -261,13 +262,13 @@ static void perf_top__print_sym_table(struct perf_top *top)
 
 	printf("%-*.*s\n", win_width, win_width, graph_dotted_line);
 
-	if (top->sym_evsel->hists.stats.nr_lost_warned !=
-	    top->sym_evsel->hists.stats.nr_events[PERF_RECORD_LOST]) {
-		top->sym_evsel->hists.stats.nr_lost_warned =
-			top->sym_evsel->hists.stats.nr_events[PERF_RECORD_LOST];
+	if (hists->stats.nr_lost_warned !=
+	    hists->stats.nr_events[PERF_RECORD_LOST]) {
+		hists->stats.nr_lost_warned =
+			      hists->stats.nr_events[PERF_RECORD_LOST];
 		color_fprintf(stdout, PERF_COLOR_RED,
 			      "WARNING: LOST %d chunks, Check IO/CPU overload",
-			      top->sym_evsel->hists.stats.nr_lost_warned);
+			      hists->stats.nr_lost_warned);
 		++printed;
 	}
 
@@ -277,21 +278,18 @@ static void perf_top__print_sym_table(struct perf_top *top)
 	}
 
 	if (top->zero) {
-		hists__delete_entries(&top->sym_evsel->hists);
+		hists__delete_entries(hists);
 	} else {
-		hists__decay_entries(&top->sym_evsel->hists,
-				     top->hide_user_symbols,
+		hists__decay_entries(hists, top->hide_user_symbols,
 				     top->hide_kernel_symbols);
 	}
 
-	hists__collapse_resort(&top->sym_evsel->hists, NULL);
-	hists__output_resort(&top->sym_evsel->hists);
+	hists__collapse_resort(hists, NULL);
+	hists__output_resort(hists);
 
-	hists__output_recalc_col_len(&top->sym_evsel->hists,
-				     top->print_entries - printed);
+	hists__output_recalc_col_len(hists, top->print_entries - printed);
 	putchar('\n');
-	hists__fprintf(&top->sym_evsel->hists, false,
-		       top->print_entries - printed, win_width,
+	hists__fprintf(hists, false, top->print_entries - printed, win_width,
 		       top->min_percent, stdout);
 }
 
@@ -334,6 +332,7 @@ static void perf_top__prompt_symbol(struct perf_top *top, const char *msg)
 {
 	char *buf = malloc(0), *p;
 	struct hist_entry *syme = top->sym_filter_entry, *n, *found = NULL;
+	struct hists *hists = evsel__hists(top->sym_evsel);
 	struct rb_node *next;
 	size_t dummy = 0;
 
@@ -351,7 +350,7 @@ static void perf_top__prompt_symbol(struct perf_top *top, const char *msg)
 	if (p)
 		*p = 0;
 
-	next = rb_first(&top->sym_evsel->hists.entries);
+	next = rb_first(&hists->entries);
 	while (next) {
 		n = rb_entry(next, struct hist_entry, rb_node);
 		if (n->ms.sym && !strcmp(buf, n->ms.sym->name)) {
@@ -538,21 +537,24 @@ static bool perf_top__handle_keypress(struct perf_top *top, int c)
 static void perf_top__sort_new_samples(void *arg)
 {
 	struct perf_top *t = arg;
+	struct hists *hists;
+
 	perf_top__reset_sample_counters(t);
 
 	if (t->evlist->selected != NULL)
 		t->sym_evsel = t->evlist->selected;
 
+	hists = evsel__hists(t->sym_evsel);
+
 	if (t->zero) {
-		hists__delete_entries(&t->sym_evsel->hists);
+		hists__delete_entries(hists);
 	} else {
-		hists__decay_entries(&t->sym_evsel->hists,
-				     t->hide_user_symbols,
+		hists__decay_entries(hists, t->hide_user_symbols,
 				     t->hide_kernel_symbols);
 	}
 
-	hists__collapse_resort(&t->sym_evsel->hists, NULL);
-	hists__output_resort(&t->sym_evsel->hists);
+	hists__collapse_resort(hists, NULL);
+	hists__output_resort(hists);
 }
 
 static void *display_thread_tui(void *arg)
@@ -573,8 +575,10 @@ static void *display_thread_tui(void *arg)
 	 * Zooming in/out UIDs. For now juse use whatever the user passed
 	 * via --uid.
 	 */
-	evlist__for_each(top->evlist, pos)
-		pos->hists.uid_filter_str = top->record_opts.target.uid_str;
+	evlist__for_each(top->evlist, pos) {
+		struct hists *hists = evsel__hists(pos);
+		hists->uid_filter_str = top->record_opts.target.uid_str;
+	}
 
 	perf_evlist__tui_browse_hists(top->evlist, help, &hbt, top->min_percent,
 				      &top->session->header.env);
@@ -768,6 +772,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
 	}
 
 	if (al.sym == NULL || !al.sym->ignore) {
+		struct hists *hists = evsel__hists(evsel);
 		struct hist_entry_iter iter = {
 			.add_entry_cb = hist_iter__top_callback,
 		};
@@ -777,14 +782,14 @@ static void perf_event__process_sample(struct perf_tool *tool,
 		else
 			iter.ops = &hist_iter_normal;
 
-		pthread_mutex_lock(&evsel->hists.lock);
+		pthread_mutex_lock(&hists->lock);
 
 		err = hist_entry_iter__add(&iter, &al, evsel, sample,
 					   top->max_stack, top);
 		if (err < 0)
 			pr_err("Problem incrementing symbol period, skipping event\n");
 
-		pthread_mutex_unlock(&evsel->hists.lock);
+		pthread_mutex_unlock(&hists->lock);
 	}
 
 	return;
@@ -849,7 +854,7 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx)
 			perf_event__process_sample(&top->tool, event, evsel,
 						   &sample, machine);
 		} else if (event->header.type < PERF_RECORD_MAX) {
-			hists__inc_nr_events(&evsel->hists, event->header.type);
+			hists__inc_nr_events(evsel__hists(evsel), event->header.type);
 			machine__process_event(machine, event, &sample);
 		} else
 			++session->stats.nr_unknown_events;
@@ -1042,7 +1047,6 @@ parse_percent_limit(const struct option *opt, const char *arg,
 
 int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 {
-	int status = -1;
 	char errbuf[BUFSIZ];
 	struct perf_top top = {
 		.count_filter	     = 5,
@@ -1160,6 +1164,10 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 		"perf top [<options>]",
 		NULL
 	};
+	int status = hists__init();
+
+	if (status < 0)
+		return status;
 
 	top.evlist = perf_evlist__new();
 	if (top.evlist == NULL)
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index ac655b0700e7..162c978f1491 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -6,6 +6,7 @@
 #include <unistd.h>
 #include <string.h>
 #include "builtin.h"
+#include "hist.h"
 #include "intlist.h"
 #include "tests.h"
 #include "debug.h"
@@ -302,6 +303,10 @@ int cmd_test(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_END()
 	};
 	struct intlist *skiplist = NULL;
+        int ret = hists__init();
+
+        if (ret < 0)
+                return ret;
 
 	argc = parse_options(argc, argv, test_options, test_usage, 0);
 	if (argc >= 1 && !strcmp(argv[0], "list"))
diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c
index 0ac240db2e24..614d5c4978ab 100644
--- a/tools/perf/tests/hists_cumulate.c
+++ b/tools/perf/tests/hists_cumulate.c
@@ -245,7 +245,7 @@ static int do_test(struct hists *hists, struct result *expected, size_t nr_expec
 static int test1(struct perf_evsel *evsel, struct machine *machine)
 {
 	int err;
-	struct hists *hists = &evsel->hists;
+	struct hists *hists = evsel__hists(evsel);
 	/*
 	 * expected output:
 	 *
@@ -295,7 +295,7 @@ out:
 static int test2(struct perf_evsel *evsel, struct machine *machine)
 {
 	int err;
-	struct hists *hists = &evsel->hists;
+	struct hists *hists = evsel__hists(evsel);
 	/*
 	 * expected output:
 	 *
@@ -442,7 +442,7 @@ out:
 static int test3(struct perf_evsel *evsel, struct machine *machine)
 {
 	int err;
-	struct hists *hists = &evsel->hists;
+	struct hists *hists = evsel__hists(evsel);
 	/*
 	 * expected output:
 	 *
@@ -498,7 +498,7 @@ out:
 static int test4(struct perf_evsel *evsel, struct machine *machine)
 {
 	int err;
-	struct hists *hists = &evsel->hists;
+	struct hists *hists = evsel__hists(evsel);
 	/*
 	 * expected output:
 	 *
diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c
index 821f581fd930..5a31787cc6b9 100644
--- a/tools/perf/tests/hists_filter.c
+++ b/tools/perf/tests/hists_filter.c
@@ -66,11 +66,12 @@ static int add_hist_entries(struct perf_evlist *evlist,
 				.ops = &hist_iter_normal,
 				.hide_unresolved = false,
 			};
+			struct hists *hists = evsel__hists(evsel);
 
 			/* make sure it has no filter at first */
-			evsel->hists.thread_filter = NULL;
-			evsel->hists.dso_filter = NULL;
-			evsel->hists.symbol_filter_str = NULL;
+			hists->thread_filter = NULL;
+			hists->dso_filter = NULL;
+			hists->symbol_filter_str = NULL;
 
 			sample.pid = fake_samples[i].pid;
 			sample.tid = fake_samples[i].pid;
@@ -134,7 +135,7 @@ int test__hists_filter(void)
 		goto out;
 
 	evlist__for_each(evlist, evsel) {
-		struct hists *hists = &evsel->hists;
+		struct hists *hists = evsel__hists(evsel);
 
 		hists__collapse_resort(hists, NULL);
 		hists__output_resort(hists);
@@ -160,7 +161,7 @@ int test__hists_filter(void)
 				hists->stats.total_non_filtered_period);
 
 		/* now applying thread filter for 'bash' */
-		evsel->hists.thread_filter = fake_samples[9].thread;
+		hists->thread_filter = fake_samples[9].thread;
 		hists__filter_by_thread(hists);
 
 		if (verbose > 2) {
@@ -185,11 +186,11 @@ int test__hists_filter(void)
 				hists->stats.total_non_filtered_period == 400);
 
 		/* remove thread filter first */
-		evsel->hists.thread_filter = NULL;
+		hists->thread_filter = NULL;
 		hists__filter_by_thread(hists);
 
 		/* now applying dso filter for 'kernel' */
-		evsel->hists.dso_filter = fake_samples[0].map->dso;
+		hists->dso_filter = fake_samples[0].map->dso;
 		hists__filter_by_dso(hists);
 
 		if (verbose > 2) {
@@ -214,7 +215,7 @@ int test__hists_filter(void)
 				hists->stats.total_non_filtered_period == 300);
 
 		/* remove dso filter first */
-		evsel->hists.dso_filter = NULL;
+		hists->dso_filter = NULL;
 		hists__filter_by_dso(hists);
 
 		/*
@@ -224,7 +225,7 @@ int test__hists_filter(void)
 		 * be counted as a separate entry but the sample count and
 		 * total period will be remained.
 		 */
-		evsel->hists.symbol_filter_str = "main";
+		hists->symbol_filter_str = "main";
 		hists__filter_by_symbol(hists);
 
 		if (verbose > 2) {
@@ -249,8 +250,8 @@ int test__hists_filter(void)
 				hists->stats.total_non_filtered_period == 300);
 
 		/* now applying all filters at once. */
-		evsel->hists.thread_filter = fake_samples[1].thread;
-		evsel->hists.dso_filter = fake_samples[1].map->dso;
+		hists->thread_filter = fake_samples[1].thread;
+		hists->dso_filter = fake_samples[1].map->dso;
 		hists__filter_by_thread(hists);
 		hists__filter_by_dso(hists);
 
diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c
index d4b34b0f50a2..278ba8344c23 100644
--- a/tools/perf/tests/hists_link.c
+++ b/tools/perf/tests/hists_link.c
@@ -73,6 +73,8 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 	 * "bash [libc] malloc" so total 9 entries will be in the tree.
 	 */
 	evlist__for_each(evlist, evsel) {
+		struct hists *hists = evsel__hists(evsel);
+
 		for (k = 0; k < ARRAY_SIZE(fake_common_samples); k++) {
 			const union perf_event event = {
 				.header = {
@@ -87,7 +89,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 							  &sample) < 0)
 				goto out;
 
-			he = __hists__add_entry(&evsel->hists, &al, NULL,
+			he = __hists__add_entry(hists, &al, NULL,
 						NULL, NULL, 1, 1, 0, true);
 			if (he == NULL)
 				goto out;
@@ -111,7 +113,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 							  &sample) < 0)
 				goto out;
 
-			he = __hists__add_entry(&evsel->hists, &al, NULL,
+			he = __hists__add_entry(hists, &al, NULL,
 						NULL, NULL, 1, 1, 0, true);
 			if (he == NULL)
 				goto out;
@@ -271,6 +273,7 @@ static int validate_link(struct hists *leader, struct hists *other)
 int test__hists_link(void)
 {
 	int err = -1;
+	struct hists *hists, *first_hists;
 	struct machines machines;
 	struct machine *machine = NULL;
 	struct perf_evsel *evsel, *first;
@@ -306,24 +309,28 @@ int test__hists_link(void)
 		goto out;
 
 	evlist__for_each(evlist, evsel) {
-		hists__collapse_resort(&evsel->hists, NULL);
+		hists = evsel__hists(evsel);
+		hists__collapse_resort(hists, NULL);
 
 		if (verbose > 2)
-			print_hists_in(&evsel->hists);
+			print_hists_in(hists);
 	}
 
 	first = perf_evlist__first(evlist);
 	evsel = perf_evlist__last(evlist);
 
+	first_hists = evsel__hists(first);
+	hists = evsel__hists(evsel);
+
 	/* match common entries */
-	hists__match(&first->hists, &evsel->hists);
-	err = validate_match(&first->hists, &evsel->hists);
+	hists__match(first_hists, hists);
+	err = validate_match(first_hists, hists);
 	if (err)
 		goto out;
 
 	/* link common and/or dummy entries */
-	hists__link(&first->hists, &evsel->hists);
-	err = validate_link(&first->hists, &evsel->hists);
+	hists__link(first_hists, hists);
+	err = validate_link(first_hists, hists);
 	if (err)
 		goto out;
 
diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c
index e3bbd6c54c1b..a748f2be1222 100644
--- a/tools/perf/tests/hists_output.c
+++ b/tools/perf/tests/hists_output.c
@@ -122,7 +122,7 @@ typedef int (*test_fn_t)(struct perf_evsel *, struct machine *);
 static int test1(struct perf_evsel *evsel, struct machine *machine)
 {
 	int err;
-	struct hists *hists = &evsel->hists;
+	struct hists *hists = evsel__hists(evsel);
 	struct hist_entry *he;
 	struct rb_root *root;
 	struct rb_node *node;
@@ -159,7 +159,7 @@ static int test1(struct perf_evsel *evsel, struct machine *machine)
 		print_hists_out(hists);
 	}
 
-	root = &evsel->hists.entries;
+	root = &hists->entries;
 	node = rb_first(root);
 	he = rb_entry(node, struct hist_entry, rb_node);
 	TEST_ASSERT_VAL("Invalid hist entry",
@@ -224,7 +224,7 @@ out:
 static int test2(struct perf_evsel *evsel, struct machine *machine)
 {
 	int err;
-	struct hists *hists = &evsel->hists;
+	struct hists *hists = evsel__hists(evsel);
 	struct hist_entry *he;
 	struct rb_root *root;
 	struct rb_node *node;
@@ -259,7 +259,7 @@ static int test2(struct perf_evsel *evsel, struct machine *machine)
 		print_hists_out(hists);
 	}
 
-	root = &evsel->hists.entries;
+	root = &hists->entries;
 	node = rb_first(root);
 	he = rb_entry(node, struct hist_entry, rb_node);
 	TEST_ASSERT_VAL("Invalid hist entry",
@@ -280,7 +280,7 @@ out:
 static int test3(struct perf_evsel *evsel, struct machine *machine)
 {
 	int err;
-	struct hists *hists = &evsel->hists;
+	struct hists *hists = evsel__hists(evsel);
 	struct hist_entry *he;
 	struct rb_root *root;
 	struct rb_node *node;
@@ -313,7 +313,7 @@ static int test3(struct perf_evsel *evsel, struct machine *machine)
 		print_hists_out(hists);
 	}
 
-	root = &evsel->hists.entries;
+	root = &hists->entries;
 	node = rb_first(root);
 	he = rb_entry(node, struct hist_entry, rb_node);
 	TEST_ASSERT_VAL("Invalid hist entry",
@@ -354,7 +354,7 @@ out:
 static int test4(struct perf_evsel *evsel, struct machine *machine)
 {
 	int err;
-	struct hists *hists = &evsel->hists;
+	struct hists *hists = evsel__hists(evsel);
 	struct hist_entry *he;
 	struct rb_root *root;
 	struct rb_node *node;
@@ -391,7 +391,7 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
 		print_hists_out(hists);
 	}
 
-	root = &evsel->hists.entries;
+	root = &hists->entries;
 	node = rb_first(root);
 	he = rb_entry(node, struct hist_entry, rb_node);
 	TEST_ASSERT_VAL("Invalid hist entry",
@@ -456,7 +456,7 @@ out:
 static int test5(struct perf_evsel *evsel, struct machine *machine)
 {
 	int err;
-	struct hists *hists = &evsel->hists;
+	struct hists *hists = evsel__hists(evsel);
 	struct hist_entry *he;
 	struct rb_root *root;
 	struct rb_node *node;
@@ -494,7 +494,7 @@ static int test5(struct perf_evsel *evsel, struct machine *machine)
 		print_hists_out(hists);
 	}
 
-	root = &evsel->hists.entries;
+	root = &hists->entries;
 	node = rb_first(root);
 	he = rb_entry(node, struct hist_entry, rb_node);
 
diff --git a/tools/perf/ui/browsers/header.c b/tools/perf/ui/browsers/header.c
index 89c16b988618..e8278c558d4a 100644
--- a/tools/perf/ui/browsers/header.c
+++ b/tools/perf/ui/browsers/header.c
@@ -1,6 +1,7 @@
 #include "util/cache.h"
 #include "util/debug.h"
 #include "ui/browser.h"
+#include "ui/keysyms.h"
 #include "ui/ui.h"
 #include "ui/util.h"
 #include "ui/libslang.h"
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 8f60a970404f..68eab9ea1634 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -1229,12 +1229,14 @@ static int hists__browser_title(struct hists *hists, char *bf, size_t size)
 		ev_name = buf;
 
 		for_each_group_member(pos, evsel) {
+			struct hists *pos_hists = evsel__hists(pos);
+
 			if (symbol_conf.filter_relative) {
-				nr_samples += pos->hists.stats.nr_non_filtered_samples;
-				nr_events += pos->hists.stats.total_non_filtered_period;
+				nr_samples += pos_hists->stats.nr_non_filtered_samples;
+				nr_events += pos_hists->stats.total_non_filtered_period;
 			} else {
-				nr_samples += pos->hists.stats.nr_events[PERF_RECORD_SAMPLE];
-				nr_events += pos->hists.stats.total_period;
+				nr_samples += pos_hists->stats.nr_events[PERF_RECORD_SAMPLE];
+				nr_events += pos_hists->stats.total_period;
 			}
 		}
 	}
@@ -1387,7 +1389,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 				    float min_pcnt,
 				    struct perf_session_env *env)
 {
-	struct hists *hists = &evsel->hists;
+	struct hists *hists = evsel__hists(evsel);
 	struct hist_browser *browser = hist_browser__new(hists);
 	struct branch_info *bi;
 	struct pstack *fstack;
@@ -1802,8 +1804,9 @@ static void perf_evsel_menu__write(struct ui_browser *browser,
 	struct perf_evsel_menu *menu = container_of(browser,
 						    struct perf_evsel_menu, b);
 	struct perf_evsel *evsel = list_entry(entry, struct perf_evsel, node);
+	struct hists *hists = evsel__hists(evsel);
 	bool current_entry = ui_browser__is_current_entry(browser, row);
-	unsigned long nr_events = evsel->hists.stats.nr_events[PERF_RECORD_SAMPLE];
+	unsigned long nr_events = hists->stats.nr_events[PERF_RECORD_SAMPLE];
 	const char *ev_name = perf_evsel__name(evsel);
 	char bf[256], unit;
 	const char *warn = " ";
@@ -1818,7 +1821,8 @@ static void perf_evsel_menu__write(struct ui_browser *browser,
 		ev_name = perf_evsel__group_name(evsel);
 
 		for_each_group_member(pos, evsel) {
-			nr_events += pos->hists.stats.nr_events[PERF_RECORD_SAMPLE];
+			struct hists *pos_hists = evsel__hists(pos);
+			nr_events += pos_hists->stats.nr_events[PERF_RECORD_SAMPLE];
 		}
 	}
 
@@ -1827,7 +1831,7 @@ static void perf_evsel_menu__write(struct ui_browser *browser,
 			   unit, unit == ' ' ? "" : " ", ev_name);
 	slsmg_printf("%s", bf);
 
-	nr_events = evsel->hists.stats.nr_events[PERF_RECORD_LOST];
+	nr_events = hists->stats.nr_events[PERF_RECORD_LOST];
 	if (nr_events != 0) {
 		menu->lost_events = true;
 		if (!current_entry)
diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c
index f3fa4258b256..fc654fb77ace 100644
--- a/tools/perf/ui/gtk/hists.c
+++ b/tools/perf/ui/gtk/hists.c
@@ -319,7 +319,7 @@ int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist,
 	gtk_container_add(GTK_CONTAINER(window), vbox);
 
 	evlist__for_each(evlist, pos) {
-		struct hists *hists = &pos->hists;
+		struct hists *hists = evsel__hists(pos);
 		const char *evname = perf_evsel__name(pos);
 		GtkWidget *scrolled_window;
 		GtkWidget *tab_label;
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 36437527dbb3..7dabde14ea54 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -478,7 +478,7 @@ static int __symbol__inc_addr_samples(struct symbol *sym, struct map *map,
 
 	pr_debug3("%s: addr=%#" PRIx64 "\n", __func__, map->unmap_ip(map, addr));
 
-	if (addr < sym->start || addr > sym->end)
+	if (addr < sym->start || addr >= sym->end)
 		return -ERANGE;
 
 	offset = addr - sym->start;
@@ -836,7 +836,7 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map,
 		    end = map__rip_2objdump(map, sym->end);
 
 		offset = line_ip - start;
-		if ((u64)line_ip < start || (u64)line_ip > end)
+		if ((u64)line_ip < start || (u64)line_ip >= end)
 			offset = -1;
 		else
 			parsed_line = tmp2 + 1;
@@ -966,7 +966,7 @@ fallback:
 		kce.kcore_filename = symfs_filename;
 		kce.addr = map__rip_2objdump(map, sym->start);
 		kce.offs = sym->start;
-		kce.len = sym->end + 1 - sym->start;
+		kce.len = sym->end - sym->start;
 		if (!kcore_extract__create(&kce)) {
 			delete_extract = true;
 			strlcpy(symfs_filename, kce.extract_filename,
@@ -987,7 +987,7 @@ fallback:
 		 disassembler_style ? "-M " : "",
 		 disassembler_style ? disassembler_style : "",
 		 map__rip_2objdump(map, sym->start),
-		 map__rip_2objdump(map, sym->end+1),
+		 map__rip_2objdump(map, sym->end),
 		 symbol_conf.annotate_asm_raw ? "" : "--no-show-raw",
 		 symbol_conf.annotate_src ? "-S" : "",
 		 symfs_filename, filename);
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 2a1f5a46543a..94cfefddf4db 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -65,6 +65,8 @@ struct callchain_param {
 	enum chain_key		key;
 };
 
+extern struct callchain_param callchain_param;
+
 struct callchain_list {
 	u64			ip;
 	struct map_symbol	ms;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 7eb7107731ec..5699e7e2a790 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -190,6 +190,32 @@ enum perf_user_event_type { /* above any possible kernel type */
 	PERF_RECORD_HEADER_MAX
 };
 
+/*
+ * The kernel collects the number of events it couldn't send in a stretch and
+ * when possible sends this number in a PERF_RECORD_LOST event. The number of
+ * such "chunks" of lost events is stored in .nr_events[PERF_EVENT_LOST] while
+ * total_lost tells exactly how many events the kernel in fact lost, i.e. it is
+ * the sum of all struct lost_event.lost fields reported.
+ *
+ * The total_period is needed because by default auto-freq is used, so
+ * multipling nr_events[PERF_EVENT_SAMPLE] by a frequency isn't possible to get
+ * the total number of low level events, it is necessary to to sum all struct
+ * sample_event.period and stash the result in total_period.
+ */
+struct events_stats {
+	u64 total_period;
+	u64 total_non_filtered_period;
+	u64 total_lost;
+	u64 total_invalid_chains;
+	u32 nr_events[PERF_RECORD_HEADER_MAX];
+	u32 nr_non_filtered_samples;
+	u32 nr_lost_warned;
+	u32 nr_unknown_events;
+	u32 nr_invalid_chains;
+	u32 nr_unknown_id;
+	u32 nr_unprocessable_samples;
+};
+
 struct attr_event {
 	struct perf_event_header header;
 	struct perf_event_attr attr;
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 3cebc9a8d52e..b4b54d84e9b0 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1175,11 +1175,51 @@ void perf_evlist__close(struct perf_evlist *evlist)
 	}
 }
 
+static int perf_evlist__create_syswide_maps(struct perf_evlist *evlist)
+{
+	int err = -ENOMEM;
+
+	/*
+	 * Try reading /sys/devices/system/cpu/online to get
+	 * an all cpus map.
+	 *
+	 * FIXME: -ENOMEM is the best we can do here, the cpu_map
+	 * code needs an overhaul to properly forward the
+	 * error, and we may not want to do that fallback to a
+	 * default cpu identity map :-\
+	 */
+	evlist->cpus = cpu_map__new(NULL);
+	if (evlist->cpus == NULL)
+		goto out;
+
+	evlist->threads = thread_map__new_dummy();
+	if (evlist->threads == NULL)
+		goto out_free_cpus;
+
+	err = 0;
+out:
+	return err;
+out_free_cpus:
+	cpu_map__delete(evlist->cpus);
+	evlist->cpus = NULL;
+	goto out;
+}
+
 int perf_evlist__open(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel;
 	int err;
 
+	/*
+	 * Default: one fd per CPU, all threads, aka systemwide
+	 * as sys_perf_event_open(cpu = -1, thread = -1) is EINVAL
+	 */
+	if (evlist->threads == NULL && evlist->cpus == NULL) {
+		err = perf_evlist__create_syswide_maps(evlist);
+		if (err < 0)
+			goto out_err;
+	}
+
 	perf_evlist__update_id_pos(evlist);
 
 	evlist__for_each(evlist, evsel) {
@@ -1276,8 +1316,14 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist, struct target *tar
 		sigaction(SIGUSR1, &act, NULL);
 	}
 
-	if (target__none(target))
+	if (target__none(target)) {
+		if (evlist->threads == NULL) {
+			fprintf(stderr, "FATAL: evlist->threads need to be set at this point (%s:%d).\n",
+				__func__, __LINE__);
+			goto out_close_pipes;
+		}
 		evlist->threads->map[0] = evlist->workload.pid;
+	}
 
 	close(child_ready_pipe[1]);
 	close(go_pipe[0]);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index e0868a901c4a..d1ecde0fd56c 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -15,6 +15,7 @@
 #include <linux/perf_event.h>
 #include <sys/resource.h>
 #include "asm/bug.h"
+#include "callchain.h"
 #include "evsel.h"
 #include "evlist.h"
 #include "util.h"
@@ -32,6 +33,48 @@ static struct {
 	bool cloexec;
 } perf_missing_features;
 
+static int perf_evsel__no_extra_init(struct perf_evsel *evsel __maybe_unused)
+{
+	return 0;
+}
+
+static void perf_evsel__no_extra_fini(struct perf_evsel *evsel __maybe_unused)
+{
+}
+
+static struct {
+	size_t	size;
+	int	(*init)(struct perf_evsel *evsel);
+	void	(*fini)(struct perf_evsel *evsel);
+} perf_evsel__object = {
+	.size = sizeof(struct perf_evsel),
+	.init = perf_evsel__no_extra_init,
+	.fini = perf_evsel__no_extra_fini,
+};
+
+int perf_evsel__object_config(size_t object_size,
+			      int (*init)(struct perf_evsel *evsel),
+			      void (*fini)(struct perf_evsel *evsel))
+{
+
+	if (object_size == 0)
+		goto set_methods;
+
+	if (perf_evsel__object.size > object_size)
+		return -EINVAL;
+
+	perf_evsel__object.size = object_size;
+
+set_methods:
+	if (init != NULL)
+		perf_evsel__object.init = init;
+
+	if (fini != NULL)
+		perf_evsel__object.fini = fini;
+
+	return 0;
+}
+
 #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
 
 int __perf_evsel__sample_size(u64 sample_type)
@@ -116,16 +159,6 @@ void perf_evsel__calc_id_pos(struct perf_evsel *evsel)
 	evsel->is_pos = __perf_evsel__calc_is_pos(evsel->attr.sample_type);
 }
 
-void hists__init(struct hists *hists)
-{
-	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);
-}
-
 void __perf_evsel__set_sample_bit(struct perf_evsel *evsel,
 				  enum perf_event_sample_format bit)
 {
@@ -168,14 +201,14 @@ void perf_evsel__init(struct perf_evsel *evsel,
 	evsel->unit	   = "";
 	evsel->scale	   = 1.0;
 	INIT_LIST_HEAD(&evsel->node);
-	hists__init(&evsel->hists);
+	perf_evsel__object.init(evsel);
 	evsel->sample_size = __perf_evsel__sample_size(attr->sample_type);
 	perf_evsel__calc_id_pos(evsel);
 }
 
 struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
 {
-	struct perf_evsel *evsel = zalloc(sizeof(*evsel));
+	struct perf_evsel *evsel = zalloc(perf_evsel__object.size);
 
 	if (evsel != NULL)
 		perf_evsel__init(evsel, attr, idx);
@@ -185,7 +218,7 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
 
 struct perf_evsel *perf_evsel__newtp_idx(const char *sys, const char *name, int idx)
 {
-	struct perf_evsel *evsel = zalloc(sizeof(*evsel));
+	struct perf_evsel *evsel = zalloc(perf_evsel__object.size);
 
 	if (evsel != NULL) {
 		struct perf_event_attr attr = {
@@ -692,7 +725,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 	}
 }
 
-int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
+static int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
 {
 	int cpu, thread;
 
@@ -780,13 +813,13 @@ int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus)
 	return evsel->counts != NULL ? 0 : -ENOMEM;
 }
 
-void perf_evsel__free_fd(struct perf_evsel *evsel)
+static void perf_evsel__free_fd(struct perf_evsel *evsel)
 {
 	xyarray__delete(evsel->fd);
 	evsel->fd = NULL;
 }
 
-void perf_evsel__free_id(struct perf_evsel *evsel)
+static void perf_evsel__free_id(struct perf_evsel *evsel)
 {
 	xyarray__delete(evsel->sample_id);
 	evsel->sample_id = NULL;
@@ -817,6 +850,7 @@ void perf_evsel__exit(struct perf_evsel *evsel)
 	assert(list_empty(&evsel->node));
 	perf_evsel__free_fd(evsel);
 	perf_evsel__free_id(evsel);
+	perf_evsel__object.fini(evsel);
 }
 
 void perf_evsel__delete(struct perf_evsel *evsel)
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 7bc314be6a7b..1d5c754aebc4 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -8,7 +8,6 @@
 #include <linux/types.h>
 #include "xyarray.h"
 #include "cgroup.h"
-#include "hist.h"
 #include "symbol.h"
 
 struct perf_counts_values {
@@ -66,7 +65,6 @@ struct perf_evsel {
 	struct perf_counts	*prev_raw_counts;
 	int			idx;
 	u32			ids;
-	struct hists		hists;
 	char			*name;
 	double			scale;
 	const char		*unit;
@@ -100,13 +98,16 @@ union u64_swap {
 	u32 val32[2];
 };
 
-#define hists_to_evsel(h) container_of(h, struct perf_evsel, hists)
-
 struct cpu_map;
+struct target;
 struct thread_map;
 struct perf_evlist;
 struct record_opts;
 
+int perf_evsel__object_config(size_t object_size,
+			      int (*init)(struct perf_evsel *evsel),
+			      void (*fini)(struct perf_evsel *evsel));
+
 struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx);
 
 static inline struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr)
@@ -153,12 +154,9 @@ const char *perf_evsel__name(struct perf_evsel *evsel);
 const char *perf_evsel__group_name(struct perf_evsel *evsel);
 int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size);
 
-int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
 int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads);
 int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus);
 void perf_evsel__reset_counts(struct perf_evsel *evsel, int ncpus);
-void perf_evsel__free_fd(struct perf_evsel *evsel);
-void perf_evsel__free_id(struct perf_evsel *evsel);
 void perf_evsel__free_counts(struct perf_evsel *evsel);
 void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
 
@@ -281,8 +279,6 @@ static inline int perf_evsel__read_scaled(struct perf_evsel *evsel,
 	return __perf_evsel__read(evsel, ncpus, nthreads, true);
 }
 
-void hists__init(struct hists *hists);
-
 int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 			     struct perf_sample *sample);
 
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 86569fa3651d..6e88b9e395df 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -3,6 +3,7 @@
 #include "hist.h"
 #include "session.h"
 #include "sort.h"
+#include "evlist.h"
 #include "evsel.h"
 #include "annotate.h"
 #include <math.h>
@@ -14,13 +15,6 @@ static bool hists__filter_entry_by_thread(struct hists *hists,
 static bool hists__filter_entry_by_symbol(struct hists *hists,
 					  struct hist_entry *he);
 
-struct callchain_param	callchain_param = {
-	.mode	= CHAIN_GRAPH_REL,
-	.min_percent = 0.5,
-	.order  = ORDER_CALLEE,
-	.key	= CCKEY_FUNCTION
-};
-
 u16 hists__col_len(struct hists *hists, enum hist_column col)
 {
 	return hists->col_len[col];
@@ -516,6 +510,7 @@ 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)
@@ -532,7 +527,7 @@ iter_add_single_mem_entry(struct hist_entry_iter *iter, struct addr_location *al
 	 * 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,
+	he = __hists__add_entry(hists, al, iter->parent, NULL, mi,
 				cost, cost, 0, true);
 	if (!he)
 		return -ENOMEM;
@@ -546,13 +541,14 @@ 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(&evsel->hists, he->filtered);
+	hists__inc_nr_samples(hists, he->filtered);
 
 	err = hist_entry__append_callchain(he, iter->sample);
 
@@ -618,6 +614,7 @@ iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *a
 {
 	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;
@@ -631,12 +628,12 @@ iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *a
 	 * 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,
+	he = __hists__add_entry(hists, al, iter->parent, &bi[i], NULL,
 				1, 1, 0, true);
 	if (he == NULL)
 		return -ENOMEM;
 
-	hists__inc_nr_samples(&evsel->hists, he->filtered);
+	hists__inc_nr_samples(hists, he->filtered);
 
 out:
 	iter->he = he;
@@ -668,7 +665,7 @@ iter_add_single_normal_entry(struct hist_entry_iter *iter, struct addr_location
 	struct perf_sample *sample = iter->sample;
 	struct hist_entry *he;
 
-	he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL,
+	he = __hists__add_entry(evsel__hists(evsel), al, iter->parent, NULL, NULL,
 				sample->period, sample->weight,
 				sample->transaction, true);
 	if (he == NULL)
@@ -691,7 +688,7 @@ iter_finish_normal_entry(struct hist_entry_iter *iter,
 
 	iter->he = NULL;
 
-	hists__inc_nr_samples(&evsel->hists, he->filtered);
+	hists__inc_nr_samples(evsel__hists(evsel), he->filtered);
 
 	return hist_entry__append_callchain(he, sample);
 }
@@ -724,12 +721,13 @@ 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(&evsel->hists, al, iter->parent, NULL, NULL,
+	he = __hists__add_entry(hists, al, iter->parent, NULL, NULL,
 				sample->period, sample->weight,
 				sample->transaction, true);
 	if (he == NULL)
@@ -746,7 +744,7 @@ iter_add_single_cumulative_entry(struct hist_entry_iter *iter,
 	 */
 	callchain_cursor_commit(&callchain_cursor);
 
-	hists__inc_nr_samples(&evsel->hists, he->filtered);
+	hists__inc_nr_samples(hists, he->filtered);
 
 	return err;
 }
@@ -802,7 +800,7 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter,
 		}
 	}
 
-	he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL,
+	he = __hists__add_entry(evsel__hists(evsel), al, iter->parent, NULL, NULL,
 				sample->period, sample->weight,
 				sample->transaction, false);
 	if (he == NULL)
@@ -1408,6 +1406,21 @@ int hists__link(struct hists *leader, struct hists *other)
 	return 0;
 }
 
+
+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 :
@@ -1434,3 +1447,31 @@ int perf_hist_config(const char *var, const char *value)
 
 	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);
+	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;
+}
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 8c9c70e18cbb..d0ef9a19a744 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -4,12 +4,11 @@
 #include <linux/types.h>
 #include <pthread.h>
 #include "callchain.h"
+#include "evsel.h"
 #include "header.h"
 #include "color.h"
 #include "ui/progress.h"
 
-extern struct callchain_param callchain_param;
-
 struct hist_entry;
 struct addr_location;
 struct symbol;
@@ -23,32 +22,6 @@ enum hist_filter {
 	HIST_FILTER__HOST,
 };
 
-/*
- * The kernel collects the number of events it couldn't send in a stretch and
- * when possible sends this number in a PERF_RECORD_LOST event. The number of
- * such "chunks" of lost events is stored in .nr_events[PERF_EVENT_LOST] while
- * total_lost tells exactly how many events the kernel in fact lost, i.e. it is
- * the sum of all struct lost_event.lost fields reported.
- *
- * The total_period is needed because by default auto-freq is used, so
- * multipling nr_events[PERF_EVENT_SAMPLE] by a frequency isn't possible to get
- * the total number of low level events, it is necessary to to sum all struct
- * sample_event.period and stash the result in total_period.
- */
-struct events_stats {
-	u64 total_period;
-	u64 total_non_filtered_period;
-	u64 total_lost;
-	u64 total_invalid_chains;
-	u32 nr_events[PERF_RECORD_HEADER_MAX];
-	u32 nr_non_filtered_samples;
-	u32 nr_lost_warned;
-	u32 nr_unknown_events;
-	u32 nr_invalid_chains;
-	u32 nr_unknown_id;
-	u32 nr_unprocessable_samples;
-};
-
 enum hist_column {
 	HISTC_SYMBOL,
 	HISTC_DSO,
@@ -165,6 +138,7 @@ size_t events_stats__fprintf(struct events_stats *stats, FILE *fp);
 
 size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 		      int max_cols, float min_pcnt, FILE *fp);
+size_t perf_evlist__fprintf_nr_events(struct perf_evlist *evlist, FILE *fp);
 
 void hists__filter_by_dso(struct hists *hists);
 void hists__filter_by_thread(struct hists *hists);
@@ -185,6 +159,25 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *he);
 void hists__match(struct hists *leader, struct hists *other);
 int hists__link(struct hists *leader, struct hists *other);
 
+struct hists_evsel {
+	struct perf_evsel evsel;
+	struct hists	  hists;
+};
+
+static inline struct perf_evsel *hists_to_evsel(struct hists *hists)
+{
+	struct hists_evsel *hevsel = container_of(hists, struct hists_evsel, hists);
+	return &hevsel->evsel;
+}
+
+static inline struct hists *evsel__hists(struct perf_evsel *evsel)
+{
+	struct hists_evsel *hevsel = (struct hists_evsel *)evsel;
+	return &hevsel->hists;
+}
+
+int hists__init(void);
+
 struct perf_hpp {
 	char *buf;
 	size_t size;
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index b7d477fbda02..34fc7c8672e4 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -13,12 +13,18 @@
 #include <symbol/kallsyms.h>
 #include "unwind.h"
 
+static void dsos__init(struct dsos *dsos)
+{
+	INIT_LIST_HEAD(&dsos->head);
+	dsos->root = RB_ROOT;
+}
+
 int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 {
 	map_groups__init(&machine->kmaps);
 	RB_CLEAR_NODE(&machine->rb_node);
-	INIT_LIST_HEAD(&machine->user_dsos.head);
-	INIT_LIST_HEAD(&machine->kernel_dsos.head);
+	dsos__init(&machine->user_dsos);
+	dsos__init(&machine->kernel_dsos);
 
 	machine->threads = RB_ROOT;
 	INIT_LIST_HEAD(&machine->dead_threads);
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index b7090596ac50..2137c4596ec7 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -556,7 +556,7 @@ struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg,
 
 int map_groups__find_ams(struct addr_map_symbol *ams, symbol_filter_t filter)
 {
-	if (ams->addr < ams->map->start || ams->addr > ams->map->end) {
+	if (ams->addr < ams->map->start || ams->addr >= ams->map->end) {
 		if (ams->map->groups == NULL)
 			return -1;
 		ams->map = map_groups__find(ams->map->groups, ams->map->type,
@@ -664,7 +664,7 @@ int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
 				goto move_map;
 			}
 
-			before->end = map->start - 1;
+			before->end = map->start;
 			map_groups__insert(mg, before);
 			if (verbose >= 2)
 				map__fprintf(before, fp);
@@ -678,7 +678,7 @@ int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
 				goto move_map;
 			}
 
-			after->start = map->end + 1;
+			after->start = map->end;
 			map_groups__insert(mg, after);
 			if (verbose >= 2)
 				map__fprintf(after, fp);
@@ -752,7 +752,7 @@ struct map *maps__find(struct rb_root *maps, u64 ip)
 		m = rb_entry(parent, struct map, rb_node);
 		if (ip < m->start)
 			p = &(*p)->rb_left;
-		else if (ip > m->end)
+		else if (ip >= m->end)
 			p = &(*p)->rb_right;
 		else
 			return m;
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 56ba07cce549..496f21cadd97 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -28,6 +28,7 @@
 
 #include "../../perf.h"
 #include "../debug.h"
+#include "../callchain.h"
 #include "../evsel.h"
 #include "../util.h"
 #include "../event.h"
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 883406f4b381..896bac73ea08 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -813,22 +813,6 @@ int perf_session__deliver_event(struct perf_session *session,
 	dump_event(session, event, file_offset, sample);
 
 	evsel = perf_evlist__id2evsel(session->evlist, sample->id);
-	if (evsel != NULL && event->header.type != PERF_RECORD_SAMPLE) {
-		/*
-		 * XXX We're leaving PERF_RECORD_SAMPLE unnacounted here
-		 * because the tools right now may apply filters, discarding
-		 * some of the samples. For consistency, in the future we
-		 * should have something like nr_filtered_samples and remove
-		 * the sample->period from total_sample_period, etc, KISS for
-		 * now tho.
-		 *
-		 * Also testing against NULL allows us to handle files without
-		 * attr.sample_id_all and/or without PERF_SAMPLE_ID. In the
-		 * future probably it'll be a good idea to restrict event
-		 * processing via perf_session to files with both set.
-		 */
-		hists__inc_nr_events(&evsel->hists, event->header.type);
-	}
 
 	machine = perf_session__find_machine_for_cpumode(session, event,
 							 sample);
@@ -1391,16 +1375,9 @@ size_t perf_session__fprintf_dsos_buildid(struct perf_session *session, FILE *fp
 
 size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp)
 {
-	struct perf_evsel *pos;
 	size_t ret = fprintf(fp, "Aggregated stats:\n");
 
 	ret += events_stats__fprintf(&session->stats, fp);
-
-	evlist__for_each(session->evlist, pos) {
-		ret += fprintf(fp, "%s stats:\n", perf_evsel__name(pos));
-		ret += events_stats__fprintf(&pos->hists.stats, fp);
-	}
-
 	return ret;
 }
 
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index ffb440462008..a4be851f1a90 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -2,7 +2,6 @@
 #define __PERF_SESSION_H
 
 #include "trace-event.h"
-#include "hist.h"
 #include "event.h"
 #include "header.h"
 #include "machine.h"
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 289df9d1e65a..4906cd81cb56 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -1218,7 +1218,7 @@ static int __sort__hpp_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 	hse = container_of(fmt, struct hpp_sort_entry, hpp);
 
 	if (!len)
-		len = hists__col_len(&evsel->hists, hse->se->se_width_idx);
+		len = hists__col_len(evsel__hists(evsel), hse->se->se_width_idx);
 
 	return scnprintf(hpp->buf, hpp->size, "%-*.*s", len, len, fmt->name);
 }
@@ -1233,7 +1233,7 @@ static int __sort__hpp_width(struct perf_hpp_fmt *fmt,
 	hse = container_of(fmt, struct hpp_sort_entry, hpp);
 
 	if (!len)
-		len = hists__col_len(&evsel->hists, hse->se->se_width_idx);
+		len = hists__col_len(evsel__hists(evsel), hse->se->se_width_idx);
 
 	return len;
 }
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index be84f7a9838b..078331140d8c 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -186,7 +186,7 @@ void symbols__fixup_end(struct rb_root *symbols)
 		curr = rb_entry(nd, struct symbol, rb_node);
 
 		if (prev->end == prev->start && prev->end != curr->start)
-			prev->end = curr->start - 1;
+			prev->end = curr->start;
 	}
 
 	/* Last entry */
@@ -207,7 +207,7 @@ void __map_groups__fixup_end(struct map_groups *mg, enum map_type type)
 	for (nd = rb_next(prevnd); nd; nd = rb_next(nd)) {
 		prev = curr;
 		curr = rb_entry(nd, struct map, rb_node);
-		prev->end = curr->start - 1;
+		prev->end = curr->start;
 	}
 
 	/*
@@ -229,7 +229,7 @@ struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name)
 		sym = ((void *)sym) + symbol_conf.priv_size;
 
 	sym->start   = start;
-	sym->end     = len ? start + len - 1 : start;
+	sym->end     = len ? start + len : start;
 	sym->binding = binding;
 	sym->namelen = namelen - 1;
 
@@ -325,7 +325,7 @@ static struct symbol *symbols__find(struct rb_root *symbols, u64 ip)
 
 		if (ip < s->start)
 			n = n->rb_left;
-		else if (ip > s->end)
+		else if (ip >= s->end)
 			n = n->rb_right;
 		else
 			return s;
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index bec4b7bd09de..eb2c19bf8d90 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -95,7 +95,7 @@ void symbols__delete(struct rb_root *symbols);
 
 static inline size_t symbol__size(const struct symbol *sym)
 {
-	return sym->end - sym->start + 1;
+	return sym->end - sym->start;
 }
 
 struct strlist;
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index 5d3215912105..f93b9734735b 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -214,6 +214,17 @@ out_free_threads:
 	goto out;
 }
 
+struct thread_map *thread_map__new_dummy(void)
+{
+	struct thread_map *threads = malloc(sizeof(*threads) + sizeof(pid_t));
+
+	if (threads != NULL) {
+		threads->map[0]	= -1;
+		threads->nr	= 1;
+	}
+	return threads;
+}
+
 static struct thread_map *thread_map__new_by_tid_str(const char *tid_str)
 {
 	struct thread_map *threads = NULL, *nt;
@@ -224,14 +235,8 @@ static struct thread_map *thread_map__new_by_tid_str(const char *tid_str)
 	struct strlist *slist;
 
 	/* perf-stat expects threads to be generated even if tid not given */
-	if (!tid_str) {
-		threads = malloc(sizeof(*threads) + sizeof(pid_t));
-		if (threads != NULL) {
-			threads->map[0] = -1;
-			threads->nr	= 1;
-		}
-		return threads;
-	}
+	if (!tid_str)
+		return thread_map__new_dummy();
 
 	slist = strlist__new(false, tid_str);
 	if (!slist)
diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h
index 0cd8b3108084..95313f43cc0f 100644
--- a/tools/perf/util/thread_map.h
+++ b/tools/perf/util/thread_map.h
@@ -9,6 +9,7 @@ struct thread_map {
 	pid_t map[];
 };
 
+struct thread_map *thread_map__new_dummy(void);
 struct thread_map *thread_map__new_by_pid(pid_t pid);
 struct thread_map *thread_map__new_by_tid(pid_t tid);
 struct thread_map *thread_map__new_by_uid(uid_t uid);
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 24e8d871b74e..d5eab3f3323f 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -14,6 +14,14 @@
 #include <byteswap.h>
 #include <linux/kernel.h>
 #include <unistd.h>
+#include "callchain.h"
+
+struct callchain_param	callchain_param = {
+	.mode	= CHAIN_GRAPH_REL,
+	.min_percent = 0.5,
+	.order  = ORDER_CALLEE,
+	.key	= CCKEY_FUNCTION
+};
 
 /*
  * XXX We need to find a better place for these things...