Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip into next

Pull perf updates from Ingo Molnar:
 "The tooling changes maintained by Jiri Olsa until Arnaldo is on
  vacation:

  User visible changes:
   - Add -F option for specifying output fields (Namhyung Kim)
   - Propagate exit status of a command line workload for record command
     (Namhyung Kim)
   - Use tid for finding thread (Namhyung Kim)
   - Clarify the output of perf sched map plus small sched command
     fixes (Dongsheng Yang)
   - Wire up perf_regs and unwind support for ARM64 (Jean Pihet)
   - Factor hists statistics counts processing which in turn also fixes
     several bugs in TUI report command (Namhyung Kim)
   - Add --percentage option to control absolute/relative percentage
     output (Namhyung Kim)
   - Add --list-cmds to 'kmem', 'mem', 'lock' and 'sched', for use by
     completion scripts (Ramkumar Ramachandra)

  Development/infrastructure changes and fixes:
   - Android related fixes for pager and map dso resolving (Michael
     Lentine)
   - Add libdw DWARF post unwind support for ARM (Jean Pihet)
   - Consolidate types.h for ARM and ARM64 (Jean Pihet)
   - Fix possible null pointer dereference in session.c (Masanari Iida)
   - Cleanup, remove unused variables in map_switch_event() (Dongsheng
     Yang)
   - Remove nr_state_machine_bugs in perf latency (Dongsheng Yang)
   - Remove usage of trace_sched_wakeup(.success) (Peter Zijlstra)
   - Cleanups for perf.h header (Jiri Olsa)
   - Consolidate types.h and export.h within tools (Borislav Petkov)
   - Move u64_swap union to its single user's header, evsel.h (Borislav
     Petkov)
   - Fix for s390 to properly parse tracepoints plus test code
     (Alexander Yarygin)
   - Handle EINTR error for readn/writen (Namhyung Kim)
   - Add a test case for hists filtering (Namhyung Kim)
   - Share map_groups among threads of the same group (Arnaldo Carvalho
     de Melo, Jiri Olsa)
   - Making some code (cpu node map and report parse callchain callback)
     global to be usable by upcomming changes (Don Zickus)
   - Fix pmu object compilation error (Jiri Olsa)

  Kernel side changes:
   - intrusive uprobes fixes from Oleg Nesterov.  Since the interface is
     admin-only, and the bug only affects user-space ("any probed
     jmp/call can kill the application"), we queued these fixes via the
     development tree, as a special exception.
   - more fuzzer motivated race fixes and related refactoring and
     robustization.
   - allow PMU drivers to be built as modules.  (No actual module yet,
     because the x86 Intel uncore module wasn't ready in time for this)"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (114 commits)
  perf tools: Add automatic remapping of Android libraries
  perf tools: Add cat as fallback pager
  perf tests: Add a testcase for histogram output sorting
  perf tests: Factor out print_hists_*()
  perf tools: Introduce reset_output_field()
  perf tools: Get rid of obsolete hist_entry__sort_list
  perf hists: Reset width of output fields with header length
  perf tools: Skip elided sort entries
  perf top: Add --fields option to specify output fields
  perf report/tui: Fix a bug when --fields/sort is given
  perf tools: Add ->sort() member to struct sort_entry
  perf report: Add -F option to specify output fields
  perf tools: Call perf_hpp__init() before setting up GUI browsers
  perf tools: Consolidate management of default sort orders
  perf tools: Allow hpp fields to be sort keys
  perf ui: Get rid of callback from __hpp__fmt()
  perf tools: Consolidate output field handling to hpp format routines
  perf tools: Use hpp formats to sort final output
  perf tools: Support event grouping in hpp ->sort()
  perf tools: Use hpp formats to sort hist entries
  ...

20 files changed, 1617 insertions, 235 deletions

diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c
index 00218f503b2e..2dfc9ad0e6f2 100644
--- a/tools/perf/tests/attr.c
+++ b/tools/perf/tests/attr.c
@@ -1,4 +1,3 @@
-
 /*
  * The struct perf_event_attr test support.
  *
@@ -19,14 +18,8 @@
  * permissions. All the event text files are stored there.
  */
 
-/*
- * Powerpc needs __SANE_USERSPACE_TYPES__ before <linux/types.h> to select
- * 'int-ll64.h' and avoid compile warnings when printing __u64 with %llu.
- */
-#define __SANE_USERSPACE_TYPES__
 #include <stdlib.h>
 #include <stdio.h>
-#include <inttypes.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include "../perf.h"
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index b11bf8a08430..831f52cae197 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -115,7 +115,7 @@ static struct test {
 		.desc = "Test parsing with no sample_id_all bit set",
 		.func = test__parse_no_sample_id_all,
 	},
-#if defined(__x86_64__) || defined(__i386__)
+#if defined(__x86_64__) || defined(__i386__) || defined(__arm__)
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
 	{
 		.desc = "Test dwarf unwind",
@@ -124,6 +124,22 @@ static struct test {
 #endif
 #endif
 	{
+		.desc = "Test filtering hist entries",
+		.func = test__hists_filter,
+	},
+	{
+		.desc = "Test mmap thread lookup",
+		.func = test__mmap_thread_lookup,
+	},
+	{
+		.desc = "Test thread mg sharing",
+		.func = test__thread_mg_share,
+	},
+	{
+		.desc = "Test output sorting of hist entries",
+		.func = test__hists_output,
+	},
+	{
 		.func = NULL,
 	},
 };
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index bfb186900ac0..67f2d6323558 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -1,8 +1,7 @@
-#include <sys/types.h>
+#include <linux/types.h>
 #include <stdlib.h>
 #include <unistd.h>
 #include <stdio.h>
-#include <inttypes.h>
 #include <ctype.h>
 #include <string.h>
 
@@ -257,7 +256,7 @@ static int process_sample_event(struct machine *machine,
 		return -1;
 	}
 
-	thread = machine__findnew_thread(machine, sample.pid, sample.pid);
+	thread = machine__findnew_thread(machine, sample.pid, sample.tid);
 	if (!thread) {
 		pr_debug("machine__findnew_thread failed\n");
 		return -1;
diff --git a/tools/perf/tests/dso-data.c b/tools/perf/tests/dso-data.c
index 9cc81a3eb9b4..3e6cb171e3d3 100644
--- a/tools/perf/tests/dso-data.c
+++ b/tools/perf/tests/dso-data.c
@@ -1,7 +1,7 @@
 #include "util.h"
 
 #include <stdlib.h>
-#include <sys/types.h>
+#include <linux/types.h>
 #include <sys/stat.h>
 #include <fcntl.h>
 #include <string.h>
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
index c059ee81c038..108f0cd49f4e 100644
--- a/tools/perf/tests/dwarf-unwind.c
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -1,5 +1,5 @@
 #include <linux/compiler.h>
-#include <sys/types.h>
+#include <linux/types.h>
 #include <unistd.h>
 #include "tests.h"
 #include "debug.h"
diff --git a/tools/perf/tests/evsel-tp-sched.c b/tools/perf/tests/evsel-tp-sched.c
index 4774f7fbb758..35d7fdb2328d 100644
--- a/tools/perf/tests/evsel-tp-sched.c
+++ b/tools/perf/tests/evsel-tp-sched.c
@@ -74,9 +74,6 @@ int test__perf_evsel__tp_sched_test(void)
 	if (perf_evsel__test_field(evsel, "prio", 4, true))
 		ret = -1;
 
-	if (perf_evsel__test_field(evsel, "success", 4, true))
-		ret = -1;
-
 	if (perf_evsel__test_field(evsel, "target_cpu", 4, true))
 		ret = -1;
 
diff --git a/tools/perf/tests/hists_common.c b/tools/perf/tests/hists_common.c
new file mode 100644
index 000000000000..e4e01aadc3be
--- /dev/null
+++ b/tools/perf/tests/hists_common.c
@@ -0,0 +1,205 @@
+#include "perf.h"
+#include "util/debug.h"
+#include "util/symbol.h"
+#include "util/sort.h"
+#include "util/evsel.h"
+#include "util/evlist.h"
+#include "util/machine.h"
+#include "util/thread.h"
+#include "tests/hists_common.h"
+
+static struct {
+	u32 pid;
+	const char *comm;
+} fake_threads[] = {
+	{ 100, "perf" },
+	{ 200, "perf" },
+	{ 300, "bash" },
+};
+
+static struct {
+	u32 pid;
+	u64 start;
+	const char *filename;
+} fake_mmap_info[] = {
+	{ 100, 0x40000, "perf" },
+	{ 100, 0x50000, "libc" },
+	{ 100, 0xf0000, "[kernel]" },
+	{ 200, 0x40000, "perf" },
+	{ 200, 0x50000, "libc" },
+	{ 200, 0xf0000, "[kernel]" },
+	{ 300, 0x40000, "bash" },
+	{ 300, 0x50000, "libc" },
+	{ 300, 0xf0000, "[kernel]" },
+};
+
+struct fake_sym {
+	u64 start;
+	u64 length;
+	const char *name;
+};
+
+static struct fake_sym perf_syms[] = {
+	{ 700, 100, "main" },
+	{ 800, 100, "run_command" },
+	{ 900, 100, "cmd_record" },
+};
+
+static struct fake_sym bash_syms[] = {
+	{ 700, 100, "main" },
+	{ 800, 100, "xmalloc" },
+	{ 900, 100, "xfree" },
+};
+
+static struct fake_sym libc_syms[] = {
+	{ 700, 100, "malloc" },
+	{ 800, 100, "free" },
+	{ 900, 100, "realloc" },
+};
+
+static struct fake_sym kernel_syms[] = {
+	{ 700, 100, "schedule" },
+	{ 800, 100, "page_fault" },
+	{ 900, 100, "sys_perf_event_open" },
+};
+
+static struct {
+	const char *dso_name;
+	struct fake_sym *syms;
+	size_t nr_syms;
+} fake_symbols[] = {
+	{ "perf", perf_syms, ARRAY_SIZE(perf_syms) },
+	{ "bash", bash_syms, ARRAY_SIZE(bash_syms) },
+	{ "libc", libc_syms, ARRAY_SIZE(libc_syms) },
+	{ "[kernel]", kernel_syms, ARRAY_SIZE(kernel_syms) },
+};
+
+struct machine *setup_fake_machine(struct machines *machines)
+{
+	struct machine *machine = machines__find(machines, HOST_KERNEL_ID);
+	size_t i;
+
+	if (machine == NULL) {
+		pr_debug("Not enough memory for machine setup\n");
+		return NULL;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(fake_threads); i++) {
+		struct thread *thread;
+
+		thread = machine__findnew_thread(machine, fake_threads[i].pid,
+						 fake_threads[i].pid);
+		if (thread == NULL)
+			goto out;
+
+		thread__set_comm(thread, fake_threads[i].comm, 0);
+	}
+
+	for (i = 0; i < ARRAY_SIZE(fake_mmap_info); i++) {
+		union perf_event fake_mmap_event = {
+			.mmap = {
+				.header = { .misc = PERF_RECORD_MISC_USER, },
+				.pid = fake_mmap_info[i].pid,
+				.tid = fake_mmap_info[i].pid,
+				.start = fake_mmap_info[i].start,
+				.len = 0x1000ULL,
+				.pgoff = 0ULL,
+			},
+		};
+
+		strcpy(fake_mmap_event.mmap.filename,
+		       fake_mmap_info[i].filename);
+
+		machine__process_mmap_event(machine, &fake_mmap_event, NULL);
+	}
+
+	for (i = 0; i < ARRAY_SIZE(fake_symbols); i++) {
+		size_t k;
+		struct dso *dso;
+
+		dso = __dsos__findnew(&machine->user_dsos,
+				      fake_symbols[i].dso_name);
+		if (dso == NULL)
+			goto out;
+
+		/* emulate dso__load() */
+		dso__set_loaded(dso, MAP__FUNCTION);
+
+		for (k = 0; k < fake_symbols[i].nr_syms; k++) {
+			struct symbol *sym;
+			struct fake_sym *fsym = &fake_symbols[i].syms[k];
+
+			sym = symbol__new(fsym->start, fsym->length,
+					  STB_GLOBAL, fsym->name);
+			if (sym == NULL)
+				goto out;
+
+			symbols__insert(&dso->symbols[MAP__FUNCTION], sym);
+		}
+	}
+
+	return machine;
+
+out:
+	pr_debug("Not enough memory for machine setup\n");
+	machine__delete_threads(machine);
+	machine__delete(machine);
+	return NULL;
+}
+
+void print_hists_in(struct hists *hists)
+{
+	int i = 0;
+	struct rb_root *root;
+	struct rb_node *node;
+
+	if (sort__need_collapse)
+		root = &hists->entries_collapsed;
+	else
+		root = hists->entries_in;
+
+	pr_info("----- %s --------\n", __func__);
+	node = rb_first(root);
+	while (node) {
+		struct hist_entry *he;
+
+		he = rb_entry(node, struct hist_entry, rb_node_in);
+
+		if (!he->filtered) {
+			pr_info("%2d: entry: %-8s [%-8s] %20s: period = %"PRIu64"\n",
+				i, thread__comm_str(he->thread),
+				he->ms.map->dso->short_name,
+				he->ms.sym->name, he->stat.period);
+		}
+
+		i++;
+		node = rb_next(node);
+	}
+}
+
+void print_hists_out(struct hists *hists)
+{
+	int i = 0;
+	struct rb_root *root;
+	struct rb_node *node;
+
+	root = &hists->entries;
+
+	pr_info("----- %s --------\n", __func__);
+	node = rb_first(root);
+	while (node) {
+		struct hist_entry *he;
+
+		he = rb_entry(node, struct hist_entry, rb_node);
+
+		if (!he->filtered) {
+			pr_info("%2d: entry: %8s:%5d [%-8s] %20s: period = %"PRIu64"\n",
+				i, thread__comm_str(he->thread), he->thread->tid,
+				he->ms.map->dso->short_name,
+				he->ms.sym->name, he->stat.period);
+		}
+
+		i++;
+		node = rb_next(node);
+	}
+}
diff --git a/tools/perf/tests/hists_common.h b/tools/perf/tests/hists_common.h
new file mode 100644
index 000000000000..1415ae69d7b6
--- /dev/null
+++ b/tools/perf/tests/hists_common.h
@@ -0,0 +1,47 @@
+#ifndef __PERF_TESTS__HISTS_COMMON_H__
+#define __PERF_TESTS__HISTS_COMMON_H__
+
+struct machine;
+struct machines;
+
+/*
+ * The setup_fake_machine() provides a test environment which consists
+ * of 3 processes that have 3 mappings and in turn, have 3 symbols
+ * respectively.  See below table:
+ *
+ * Command:  Pid  Shared Object               Symbol
+ * .............  .............  ...................
+ *    perf:  100           perf  main
+ *    perf:  100           perf  run_command
+ *    perf:  100           perf  comd_record
+ *    perf:  100           libc  malloc
+ *    perf:  100           libc  free
+ *    perf:  100           libc  realloc
+ *    perf:  100       [kernel]  schedule
+ *    perf:  100       [kernel]  page_fault
+ *    perf:  100       [kernel]  sys_perf_event_open
+ *    perf:  200           perf  main
+ *    perf:  200           perf  run_command
+ *    perf:  200           perf  comd_record
+ *    perf:  200           libc  malloc
+ *    perf:  200           libc  free
+ *    perf:  200           libc  realloc
+ *    perf:  200       [kernel]  schedule
+ *    perf:  200       [kernel]  page_fault
+ *    perf:  200       [kernel]  sys_perf_event_open
+ *    bash:  300           bash  main
+ *    bash:  300           bash  xmalloc
+ *    bash:  300           bash  xfree
+ *    bash:  300           libc  malloc
+ *    bash:  300           libc  free
+ *    bash:  300           libc  realloc
+ *    bash:  300       [kernel]  schedule
+ *    bash:  300       [kernel]  page_fault
+ *    bash:  300       [kernel]  sys_perf_event_open
+ */
+struct machine *setup_fake_machine(struct machines *machines);
+
+void print_hists_in(struct hists *hists);
+void print_hists_out(struct hists *hists);
+
+#endif /* __PERF_TESTS__HISTS_COMMON_H__ */
diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c
new file mode 100644
index 000000000000..c5ba924a3581
--- /dev/null
+++ b/tools/perf/tests/hists_filter.c
@@ -0,0 +1,290 @@
+#include "perf.h"
+#include "util/debug.h"
+#include "util/symbol.h"
+#include "util/sort.h"
+#include "util/evsel.h"
+#include "util/evlist.h"
+#include "util/machine.h"
+#include "util/thread.h"
+#include "util/parse-events.h"
+#include "tests/tests.h"
+#include "tests/hists_common.h"
+
+struct sample {
+	u32 pid;
+	u64 ip;
+	struct thread *thread;
+	struct map *map;
+	struct symbol *sym;
+};
+
+/* For the numbers, see hists_common.c */
+static struct sample fake_samples[] = {
+	/* perf [kernel] schedule() */
+	{ .pid = 100, .ip = 0xf0000 + 700, },
+	/* perf [perf]   main() */
+	{ .pid = 100, .ip = 0x40000 + 700, },
+	/* perf [libc]   malloc() */
+	{ .pid = 100, .ip = 0x50000 + 700, },
+	/* perf [perf]   main() */
+	{ .pid = 200, .ip = 0x40000 + 700, }, /* will be merged */
+	/* perf [perf]   cmd_record() */
+	{ .pid = 200, .ip = 0x40000 + 900, },
+	/* perf [kernel] page_fault() */
+	{ .pid = 200, .ip = 0xf0000 + 800, },
+	/* bash [bash]   main() */
+	{ .pid = 300, .ip = 0x40000 + 700, },
+	/* bash [bash]   xmalloc() */
+	{ .pid = 300, .ip = 0x40000 + 800, },
+	/* bash [libc]   malloc() */
+	{ .pid = 300, .ip = 0x50000 + 700, },
+	/* bash [kernel] page_fault() */
+	{ .pid = 300, .ip = 0xf0000 + 800, },
+};
+
+static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
+{
+	struct perf_evsel *evsel;
+	struct addr_location al;
+	struct hist_entry *he;
+	struct perf_sample sample = { .cpu = 0, };
+	size_t i;
+
+	/*
+	 * each evsel will have 10 samples but the 4th sample
+	 * (perf [perf] main) will be collapsed to an existing entry
+	 * so total 9 entries will be in the tree.
+	 */
+	evlist__for_each(evlist, evsel) {
+		for (i = 0; i < ARRAY_SIZE(fake_samples); i++) {
+			const union perf_event event = {
+				.header = {
+					.misc = PERF_RECORD_MISC_USER,
+				},
+			};
+
+			/* make sure it has no filter at first */
+			evsel->hists.thread_filter = NULL;
+			evsel->hists.dso_filter = NULL;
+			evsel->hists.symbol_filter_str = NULL;
+
+			sample.pid = fake_samples[i].pid;
+			sample.tid = fake_samples[i].pid;
+			sample.ip = fake_samples[i].ip;
+
+			if (perf_event__preprocess_sample(&event, machine, &al,
+							  &sample) < 0)
+				goto out;
+
+			he = __hists__add_entry(&evsel->hists, &al, NULL,
+						NULL, NULL, 100, 1, 0);
+			if (he == NULL)
+				goto out;
+
+			fake_samples[i].thread = al.thread;
+			fake_samples[i].map = al.map;
+			fake_samples[i].sym = al.sym;
+
+			hists__inc_nr_events(he->hists, PERF_RECORD_SAMPLE);
+			if (!he->filtered)
+				he->hists->stats.nr_non_filtered_samples++;
+		}
+	}
+
+	return 0;
+
+out:
+	pr_debug("Not enough memory for adding a hist entry\n");
+	return TEST_FAIL;
+}
+
+int test__hists_filter(void)
+{
+	int err = TEST_FAIL;
+	struct machines machines;
+	struct machine *machine;
+	struct perf_evsel *evsel;
+	struct perf_evlist *evlist = perf_evlist__new();
+
+	TEST_ASSERT_VAL("No memory", evlist);
+
+	err = parse_events(evlist, "cpu-clock");
+	if (err)
+		goto out;
+	err = parse_events(evlist, "task-clock");
+	if (err)
+		goto out;
+
+	/* default sort order (comm,dso,sym) will be used */
+	if (setup_sorting() < 0)
+		goto out;
+
+	machines__init(&machines);
+
+	/* setup threads/dso/map/symbols also */
+	machine = setup_fake_machine(&machines);
+	if (!machine)
+		goto out;
+
+	if (verbose > 1)
+		machine__fprintf(machine, stderr);
+
+	/* process sample events */
+	err = add_hist_entries(evlist, machine);
+	if (err < 0)
+		goto out;
+
+	evlist__for_each(evlist, evsel) {
+		struct hists *hists = &evsel->hists;
+
+		hists__collapse_resort(hists, NULL);
+		hists__output_resort(hists);
+
+		if (verbose > 2) {
+			pr_info("Normal histogram\n");
+			print_hists_out(hists);
+		}
+
+		TEST_ASSERT_VAL("Invalid nr samples",
+				hists->stats.nr_events[PERF_RECORD_SAMPLE] == 10);
+		TEST_ASSERT_VAL("Invalid nr hist entries",
+				hists->nr_entries == 9);
+		TEST_ASSERT_VAL("Invalid total period",
+				hists->stats.total_period == 1000);
+		TEST_ASSERT_VAL("Unmatched nr samples",
+				hists->stats.nr_events[PERF_RECORD_SAMPLE] ==
+				hists->stats.nr_non_filtered_samples);
+		TEST_ASSERT_VAL("Unmatched nr hist entries",
+				hists->nr_entries == hists->nr_non_filtered_entries);
+		TEST_ASSERT_VAL("Unmatched total period",
+				hists->stats.total_period ==
+				hists->stats.total_non_filtered_period);
+
+		/* now applying thread filter for 'bash' */
+		evsel->hists.thread_filter = fake_samples[9].thread;
+		hists__filter_by_thread(hists);
+
+		if (verbose > 2) {
+			pr_info("Histogram for thread filter\n");
+			print_hists_out(hists);
+		}
+
+		/* normal stats should be invariant */
+		TEST_ASSERT_VAL("Invalid nr samples",
+				hists->stats.nr_events[PERF_RECORD_SAMPLE] == 10);
+		TEST_ASSERT_VAL("Invalid nr hist entries",
+				hists->nr_entries == 9);
+		TEST_ASSERT_VAL("Invalid total period",
+				hists->stats.total_period == 1000);
+
+		/* but filter stats are changed */
+		TEST_ASSERT_VAL("Unmatched nr samples for thread filter",
+				hists->stats.nr_non_filtered_samples == 4);
+		TEST_ASSERT_VAL("Unmatched nr hist entries for thread filter",
+				hists->nr_non_filtered_entries == 4);
+		TEST_ASSERT_VAL("Unmatched total period for thread filter",
+				hists->stats.total_non_filtered_period == 400);
+
+		/* remove thread filter first */
+		evsel->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__filter_by_dso(hists);
+
+		if (verbose > 2) {
+			pr_info("Histogram for dso filter\n");
+			print_hists_out(hists);
+		}
+
+		/* normal stats should be invariant */
+		TEST_ASSERT_VAL("Invalid nr samples",
+				hists->stats.nr_events[PERF_RECORD_SAMPLE] == 10);
+		TEST_ASSERT_VAL("Invalid nr hist entries",
+				hists->nr_entries == 9);
+		TEST_ASSERT_VAL("Invalid total period",
+				hists->stats.total_period == 1000);
+
+		/* but filter stats are changed */
+		TEST_ASSERT_VAL("Unmatched nr samples for dso filter",
+				hists->stats.nr_non_filtered_samples == 3);
+		TEST_ASSERT_VAL("Unmatched nr hist entries for dso filter",
+				hists->nr_non_filtered_entries == 3);
+		TEST_ASSERT_VAL("Unmatched total period for dso filter",
+				hists->stats.total_non_filtered_period == 300);
+
+		/* remove dso filter first */
+		evsel->hists.dso_filter = NULL;
+		hists__filter_by_dso(hists);
+
+		/*
+		 * now applying symbol filter for 'main'.  Also note that
+		 * there's 3 samples that have 'main' symbol but the 4th
+		 * entry of fake_samples was collapsed already so it won't
+		 * be counted as a separate entry but the sample count and
+		 * total period will be remained.
+		 */
+		evsel->hists.symbol_filter_str = "main";
+		hists__filter_by_symbol(hists);
+
+		if (verbose > 2) {
+			pr_info("Histogram for symbol filter\n");
+			print_hists_out(hists);
+		}
+
+		/* normal stats should be invariant */
+		TEST_ASSERT_VAL("Invalid nr samples",
+				hists->stats.nr_events[PERF_RECORD_SAMPLE] == 10);
+		TEST_ASSERT_VAL("Invalid nr hist entries",
+				hists->nr_entries == 9);
+		TEST_ASSERT_VAL("Invalid total period",
+				hists->stats.total_period == 1000);
+
+		/* but filter stats are changed */
+		TEST_ASSERT_VAL("Unmatched nr samples for symbol filter",
+				hists->stats.nr_non_filtered_samples == 3);
+		TEST_ASSERT_VAL("Unmatched nr hist entries for symbol filter",
+				hists->nr_non_filtered_entries == 2);
+		TEST_ASSERT_VAL("Unmatched total period for symbol filter",
+				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__filter_by_thread(hists);
+		hists__filter_by_dso(hists);
+
+		if (verbose > 2) {
+			pr_info("Histogram for all filters\n");
+			print_hists_out(hists);
+		}
+
+		/* normal stats should be invariant */
+		TEST_ASSERT_VAL("Invalid nr samples",
+				hists->stats.nr_events[PERF_RECORD_SAMPLE] == 10);
+		TEST_ASSERT_VAL("Invalid nr hist entries",
+				hists->nr_entries == 9);
+		TEST_ASSERT_VAL("Invalid total period",
+				hists->stats.total_period == 1000);
+
+		/* but filter stats are changed */
+		TEST_ASSERT_VAL("Unmatched nr samples for all filter",
+				hists->stats.nr_non_filtered_samples == 2);
+		TEST_ASSERT_VAL("Unmatched nr hist entries for all filter",
+				hists->nr_non_filtered_entries == 1);
+		TEST_ASSERT_VAL("Unmatched total period for all filter",
+				hists->stats.total_non_filtered_period == 200);
+	}
+
+
+	err = TEST_OK;
+
+out:
+	/* tear down everything */
+	perf_evlist__delete(evlist);
+	reset_output_field();
+	machines__exit(&machines);
+
+	return err;
+}
diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c
index 7ccbc7b6ae77..5ffa2c3eb77d 100644
--- a/tools/perf/tests/hists_link.c
+++ b/tools/perf/tests/hists_link.c
@@ -8,145 +8,7 @@
 #include "machine.h"
 #include "thread.h"
 #include "parse-events.h"
-
-static struct {
-	u32 pid;
-	const char *comm;
-} fake_threads[] = {
-	{ 100, "perf" },
-	{ 200, "perf" },
-	{ 300, "bash" },
-};
-
-static struct {
-	u32 pid;
-	u64 start;
-	const char *filename;
-} fake_mmap_info[] = {
-	{ 100, 0x40000, "perf" },
-	{ 100, 0x50000, "libc" },
-	{ 100, 0xf0000, "[kernel]" },
-	{ 200, 0x40000, "perf" },
-	{ 200, 0x50000, "libc" },
-	{ 200, 0xf0000, "[kernel]" },
-	{ 300, 0x40000, "bash" },
-	{ 300, 0x50000, "libc" },
-	{ 300, 0xf0000, "[kernel]" },
-};
-
-struct fake_sym {
-	u64 start;
-	u64 length;
-	const char *name;
-};
-
-static struct fake_sym perf_syms[] = {
-	{ 700, 100, "main" },
-	{ 800, 100, "run_command" },
-	{ 900, 100, "cmd_record" },
-};
-
-static struct fake_sym bash_syms[] = {
-	{ 700, 100, "main" },
-	{ 800, 100, "xmalloc" },
-	{ 900, 100, "xfree" },
-};
-
-static struct fake_sym libc_syms[] = {
-	{ 700, 100, "malloc" },
-	{ 800, 100, "free" },
-	{ 900, 100, "realloc" },
-};
-
-static struct fake_sym kernel_syms[] = {
-	{ 700, 100, "schedule" },
-	{ 800, 100, "page_fault" },
-	{ 900, 100, "sys_perf_event_open" },
-};
-
-static struct {
-	const char *dso_name;
-	struct fake_sym *syms;
-	size_t nr_syms;
-} fake_symbols[] = {
-	{ "perf", perf_syms, ARRAY_SIZE(perf_syms) },
-	{ "bash", bash_syms, ARRAY_SIZE(bash_syms) },
-	{ "libc", libc_syms, ARRAY_SIZE(libc_syms) },
-	{ "[kernel]", kernel_syms, ARRAY_SIZE(kernel_syms) },
-};
-
-static struct machine *setup_fake_machine(struct machines *machines)
-{
-	struct machine *machine = machines__find(machines, HOST_KERNEL_ID);
-	size_t i;
-
-	if (machine == NULL) {
-		pr_debug("Not enough memory for machine setup\n");
-		return NULL;
-	}
-
-	for (i = 0; i < ARRAY_SIZE(fake_threads); i++) {
-		struct thread *thread;
-
-		thread = machine__findnew_thread(machine, fake_threads[i].pid,
-						 fake_threads[i].pid);
-		if (thread == NULL)
-			goto out;
-
-		thread__set_comm(thread, fake_threads[i].comm, 0);
-	}
-
-	for (i = 0; i < ARRAY_SIZE(fake_mmap_info); i++) {
-		union perf_event fake_mmap_event = {
-			.mmap = {
-				.header = { .misc = PERF_RECORD_MISC_USER, },
-				.pid = fake_mmap_info[i].pid,
-				.tid = fake_mmap_info[i].pid,
-				.start = fake_mmap_info[i].start,
-				.len = 0x1000ULL,
-				.pgoff = 0ULL,
-			},
-		};
-
-		strcpy(fake_mmap_event.mmap.filename,
-		       fake_mmap_info[i].filename);
-
-		machine__process_mmap_event(machine, &fake_mmap_event, NULL);
-	}
-
-	for (i = 0; i < ARRAY_SIZE(fake_symbols); i++) {
-		size_t k;
-		struct dso *dso;
-
-		dso = __dsos__findnew(&machine->user_dsos,
-				      fake_symbols[i].dso_name);
-		if (dso == NULL)
-			goto out;
-
-		/* emulate dso__load() */
-		dso__set_loaded(dso, MAP__FUNCTION);
-
-		for (k = 0; k < fake_symbols[i].nr_syms; k++) {
-			struct symbol *sym;
-			struct fake_sym *fsym = &fake_symbols[i].syms[k];
-
-			sym = symbol__new(fsym->start, fsym->length,
-					  STB_GLOBAL, fsym->name);
-			if (sym == NULL)
-				goto out;
-
-			symbols__insert(&dso->symbols[MAP__FUNCTION], sym);
-		}
-	}
-
-	return machine;
-
-out:
-	pr_debug("Not enough memory for machine setup\n");
-	machine__delete_threads(machine);
-	machine__delete(machine);
-	return NULL;
-}
+#include "hists_common.h"
 
 struct sample {
 	u32 pid;
@@ -156,6 +18,7 @@ struct sample {
 	struct symbol *sym;
 };
 
+/* For the numbers, see hists_common.c */
 static struct sample fake_common_samples[] = {
 	/* perf [kernel] schedule() */
 	{ .pid = 100, .ip = 0xf0000 + 700, },
@@ -218,6 +81,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 			};
 
 			sample.pid = fake_common_samples[k].pid;
+			sample.tid = fake_common_samples[k].pid;
 			sample.ip = fake_common_samples[k].ip;
 			if (perf_event__preprocess_sample(&event, machine, &al,
 							  &sample) < 0)
@@ -241,6 +105,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 			};
 
 			sample.pid = fake_samples[i][k].pid;
+			sample.tid = fake_samples[i][k].pid;
 			sample.ip = fake_samples[i][k].ip;
 			if (perf_event__preprocess_sample(&event, machine, &al,
 							  &sample) < 0)
@@ -403,33 +268,6 @@ static int validate_link(struct hists *leader, struct hists *other)
 	return __validate_link(leader, 0) || __validate_link(other, 1);
 }
 
-static void print_hists(struct hists *hists)
-{
-	int i = 0;
-	struct rb_root *root;
-	struct rb_node *node;
-
-	if (sort__need_collapse)
-		root = &hists->entries_collapsed;
-	else
-		root = hists->entries_in;
-
-	pr_info("----- %s --------\n", __func__);
-	node = rb_first(root);
-	while (node) {
-		struct hist_entry *he;
-
-		he = rb_entry(node, struct hist_entry, rb_node_in);
-
-		pr_info("%2d: entry: %-8s [%-8s] %20s: period = %"PRIu64"\n",
-			i, thread__comm_str(he->thread), he->ms.map->dso->short_name,
-			he->ms.sym->name, he->stat.period);
-
-		i++;
-		node = rb_next(node);
-	}
-}
-
 int test__hists_link(void)
 {
 	int err = -1;
@@ -471,7 +309,7 @@ int test__hists_link(void)
 		hists__collapse_resort(&evsel->hists, NULL);
 
 		if (verbose > 2)
-			print_hists(&evsel->hists);
+			print_hists_in(&evsel->hists);
 	}
 
 	first = perf_evlist__first(evlist);
@@ -494,6 +332,7 @@ int test__hists_link(void)
 out:
 	/* tear down everything */
 	perf_evlist__delete(evlist);
+	reset_output_field();
 	machines__exit(&machines);
 
 	return err;
diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c
new file mode 100644
index 000000000000..a16850551797
--- /dev/null
+++ b/tools/perf/tests/hists_output.c
@@ -0,0 +1,618 @@
+#include "perf.h"
+#include "util/debug.h"
+#include "util/symbol.h"
+#include "util/sort.h"
+#include "util/evsel.h"
+#include "util/evlist.h"
+#include "util/machine.h"
+#include "util/thread.h"
+#include "util/parse-events.h"
+#include "tests/tests.h"
+#include "tests/hists_common.h"
+
+struct sample {
+	u32 cpu;
+	u32 pid;
+	u64 ip;
+	struct thread *thread;
+	struct map *map;
+	struct symbol *sym;
+};
+
+/* For the numbers, see hists_common.c */
+static struct sample fake_samples[] = {
+	/* perf [kernel] schedule() */
+	{ .cpu = 0, .pid = 100, .ip = 0xf0000 + 700, },
+	/* perf [perf]   main() */
+	{ .cpu = 1, .pid = 100, .ip = 0x40000 + 700, },
+	/* perf [perf]   cmd_record() */
+	{ .cpu = 1, .pid = 100, .ip = 0x40000 + 900, },
+	/* perf [libc]   malloc() */
+	{ .cpu = 1, .pid = 100, .ip = 0x50000 + 700, },
+	/* perf [libc]   free() */
+	{ .cpu = 2, .pid = 100, .ip = 0x50000 + 800, },
+	/* perf [perf]   main() */
+	{ .cpu = 2, .pid = 200, .ip = 0x40000 + 700, },
+	/* perf [kernel] page_fault() */
+	{ .cpu = 2, .pid = 200, .ip = 0xf0000 + 800, },
+	/* bash [bash]   main() */
+	{ .cpu = 3, .pid = 300, .ip = 0x40000 + 700, },
+	/* bash [bash]   xmalloc() */
+	{ .cpu = 0, .pid = 300, .ip = 0x40000 + 800, },
+	/* bash [kernel] page_fault() */
+	{ .cpu = 1, .pid = 300, .ip = 0xf0000 + 800, },
+};
+
+static int add_hist_entries(struct hists *hists, struct machine *machine)
+{
+	struct addr_location al;
+	struct hist_entry *he;
+	struct perf_sample sample = { .period = 100, };
+	size_t i;
+
+	for (i = 0; i < ARRAY_SIZE(fake_samples); i++) {
+		const union perf_event event = {
+			.header = {
+				.misc = PERF_RECORD_MISC_USER,
+			},
+		};
+
+		sample.cpu = fake_samples[i].cpu;
+		sample.pid = fake_samples[i].pid;
+		sample.tid = fake_samples[i].pid;
+		sample.ip = fake_samples[i].ip;
+
+		if (perf_event__preprocess_sample(&event, machine, &al,
+						  &sample) < 0)
+			goto out;
+
+		he = __hists__add_entry(hists, &al, NULL, NULL, NULL,
+					sample.period, 1, 0);
+		if (he == NULL)
+			goto out;
+
+		fake_samples[i].thread = al.thread;
+		fake_samples[i].map = al.map;
+		fake_samples[i].sym = al.sym;
+	}
+
+	return TEST_OK;
+
+out:
+	pr_debug("Not enough memory for adding a hist entry\n");
+	return TEST_FAIL;
+}
+
+static void del_hist_entries(struct hists *hists)
+{
+	struct hist_entry *he;
+	struct rb_root *root_in;
+	struct rb_root *root_out;
+	struct rb_node *node;
+
+	if (sort__need_collapse)
+		root_in = &hists->entries_collapsed;
+	else
+		root_in = hists->entries_in;
+
+	root_out = &hists->entries;
+
+	while (!RB_EMPTY_ROOT(root_out)) {
+		node = rb_first(root_out);
+
+		he = rb_entry(node, struct hist_entry, rb_node);
+		rb_erase(node, root_out);
+		rb_erase(&he->rb_node_in, root_in);
+		hist_entry__free(he);
+	}
+}
+
+typedef int (*test_fn_t)(struct perf_evsel *, struct machine *);
+
+#define COMM(he)  (thread__comm_str(he->thread))
+#define DSO(he)   (he->ms.map->dso->short_name)
+#define SYM(he)   (he->ms.sym->name)
+#define CPU(he)   (he->cpu)
+#define PID(he)   (he->thread->tid)
+
+/* default sort keys (no field) */
+static int test1(struct perf_evsel *evsel, struct machine *machine)
+{
+	int err;
+	struct hists *hists = &evsel->hists;
+	struct hist_entry *he;
+	struct rb_root *root;
+	struct rb_node *node;
+
+	field_order = NULL;
+	sort_order = NULL; /* equivalent to sort_order = "comm,dso,sym" */
+
+	setup_sorting();
+
+	/*
+	 * expected output:
+	 *
+	 * Overhead  Command  Shared Object          Symbol
+	 * ========  =======  =============  ==============
+	 *   20.00%     perf  perf           [.] main
+	 *   10.00%     bash  [kernel]       [k] page_fault
+	 *   10.00%     bash  bash           [.] main
+	 *   10.00%     bash  bash           [.] xmalloc
+	 *   10.00%     perf  [kernel]       [k] page_fault
+	 *   10.00%     perf  [kernel]       [k] schedule
+	 *   10.00%     perf  libc           [.] free
+	 *   10.00%     perf  libc           [.] malloc
+	 *   10.00%     perf  perf           [.] cmd_record
+	 */
+	err = add_hist_entries(hists, machine);
+	if (err < 0)
+		goto out;
+
+	hists__collapse_resort(hists, NULL);
+	hists__output_resort(hists);
+
+	if (verbose > 2) {
+		pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
+		print_hists_out(hists);
+	}
+
+	root = &evsel->hists.entries;
+	node = rb_first(root);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			!strcmp(COMM(he), "perf") && !strcmp(DSO(he), "perf") &&
+			!strcmp(SYM(he), "main") && he->stat.period == 200);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			!strcmp(COMM(he), "bash") && !strcmp(DSO(he), "[kernel]") &&
+			!strcmp(SYM(he), "page_fault") && he->stat.period == 100);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			!strcmp(COMM(he), "bash") && !strcmp(DSO(he), "bash") &&
+			!strcmp(SYM(he), "main") && he->stat.period == 100);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			!strcmp(COMM(he), "bash") && !strcmp(DSO(he), "bash") &&
+			!strcmp(SYM(he), "xmalloc") && he->stat.period == 100);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			!strcmp(COMM(he), "perf") && !strcmp(DSO(he), "[kernel]") &&
+			!strcmp(SYM(he), "page_fault") && he->stat.period == 100);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			!strcmp(COMM(he), "perf") && !strcmp(DSO(he), "[kernel]") &&
+			!strcmp(SYM(he), "schedule") && he->stat.period == 100);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			!strcmp(COMM(he), "perf") && !strcmp(DSO(he), "libc") &&
+			!strcmp(SYM(he), "free") && he->stat.period == 100);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			!strcmp(COMM(he), "perf") && !strcmp(DSO(he), "libc") &&
+			!strcmp(SYM(he), "malloc") && he->stat.period == 100);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			!strcmp(COMM(he), "perf") && !strcmp(DSO(he), "perf") &&
+			!strcmp(SYM(he), "cmd_record") && he->stat.period == 100);
+
+out:
+	del_hist_entries(hists);
+	reset_output_field();
+	return err;
+}
+
+/* mixed fields and sort keys */
+static int test2(struct perf_evsel *evsel, struct machine *machine)
+{
+	int err;
+	struct hists *hists = &evsel->hists;
+	struct hist_entry *he;
+	struct rb_root *root;
+	struct rb_node *node;
+
+	field_order = "overhead,cpu";
+	sort_order = "pid";
+
+	setup_sorting();
+
+	/*
+	 * expected output:
+	 *
+	 * Overhead  CPU  Command:  Pid
+	 * ========  ===  =============
+	 *   30.00%    1  perf   :  100
+	 *   10.00%    0  perf   :  100
+	 *   10.00%    2  perf   :  100
+	 *   20.00%    2  perf   :  200
+	 *   10.00%    0  bash   :  300
+	 *   10.00%    1  bash   :  300
+	 *   10.00%    3  bash   :  300
+	 */
+	err = add_hist_entries(hists, machine);
+	if (err < 0)
+		goto out;
+
+	hists__collapse_resort(hists, NULL);
+	hists__output_resort(hists);
+
+	if (verbose > 2) {
+		pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
+		print_hists_out(hists);
+	}
+
+	root = &evsel->hists.entries;
+	node = rb_first(root);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			CPU(he) == 1 && PID(he) == 100 && he->stat.period == 300);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			CPU(he) == 0 && PID(he) == 100 && he->stat.period == 100);
+
+out:
+	del_hist_entries(hists);
+	reset_output_field();
+	return err;
+}
+
+/* fields only (no sort key) */
+static int test3(struct perf_evsel *evsel, struct machine *machine)
+{
+	int err;
+	struct hists *hists = &evsel->hists;
+	struct hist_entry *he;
+	struct rb_root *root;
+	struct rb_node *node;
+
+	field_order = "comm,overhead,dso";
+	sort_order = NULL;
+
+	setup_sorting();
+
+	/*
+	 * expected output:
+	 *
+	 * Command  Overhead  Shared Object
+	 * =======  ========  =============
+	 *    bash    20.00%  bash
+	 *    bash    10.00%  [kernel]
+	 *    perf    30.00%  perf
+	 *    perf    20.00%  [kernel]
+	 *    perf    20.00%  libc
+	 */
+	err = add_hist_entries(hists, machine);
+	if (err < 0)
+		goto out;
+
+	hists__collapse_resort(hists, NULL);
+	hists__output_resort(hists);
+
+	if (verbose > 2) {
+		pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
+		print_hists_out(hists);
+	}
+
+	root = &evsel->hists.entries;
+	node = rb_first(root);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			!strcmp(COMM(he), "bash") && !strcmp(DSO(he), "bash") &&
+			he->stat.period == 200);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			!strcmp(COMM(he), "bash") && !strcmp(DSO(he), "[kernel]") &&
+			he->stat.period == 100);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			!strcmp(COMM(he), "perf") && !strcmp(DSO(he), "perf") &&
+			he->stat.period == 300);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			!strcmp(COMM(he), "perf") && !strcmp(DSO(he), "[kernel]") &&
+			he->stat.period == 200);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			!strcmp(COMM(he), "perf") && !strcmp(DSO(he), "libc") &&
+			he->stat.period == 200);
+
+out:
+	del_hist_entries(hists);
+	reset_output_field();
+	return err;
+}
+
+/* handle duplicate 'dso' field */
+static int test4(struct perf_evsel *evsel, struct machine *machine)
+{
+	int err;
+	struct hists *hists = &evsel->hists;
+	struct hist_entry *he;
+	struct rb_root *root;
+	struct rb_node *node;
+
+	field_order = "dso,sym,comm,overhead,dso";
+	sort_order = "sym";
+
+	setup_sorting();
+
+	/*
+	 * expected output:
+	 *
+	 * Shared Object          Symbol  Command  Overhead
+	 * =============  ==============  =======  ========
+	 *          perf  [.] cmd_record     perf    10.00%
+	 *          libc  [.] free           perf    10.00%
+	 *          bash  [.] main           bash    10.00%
+	 *          perf  [.] main           perf    20.00%
+	 *          libc  [.] malloc         perf    10.00%
+	 *      [kernel]  [k] page_fault     bash    10.00%
+	 *      [kernel]  [k] page_fault     perf    10.00%
+	 *      [kernel]  [k] schedule       perf    10.00%
+	 *          bash  [.] xmalloc        bash    10.00%
+	 */
+	err = add_hist_entries(hists, machine);
+	if (err < 0)
+		goto out;
+
+	hists__collapse_resort(hists, NULL);
+	hists__output_resort(hists);
+
+	if (verbose > 2) {
+		pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
+		print_hists_out(hists);
+	}
+
+	root = &evsel->hists.entries;
+	node = rb_first(root);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			!strcmp(DSO(he), "perf") && !strcmp(SYM(he), "cmd_record") &&
+			!strcmp(COMM(he), "perf") && he->stat.period == 100);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			!strcmp(DSO(he), "libc") && !strcmp(SYM(he), "free") &&
+			!strcmp(COMM(he), "perf") && he->stat.period == 100);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			!strcmp(DSO(he), "bash") && !strcmp(SYM(he), "main") &&
+			!strcmp(COMM(he), "bash") && he->stat.period == 100);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			!strcmp(DSO(he), "perf") && !strcmp(SYM(he), "main") &&
+			!strcmp(COMM(he), "perf") && he->stat.period == 200);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			!strcmp(DSO(he), "libc") && !strcmp(SYM(he), "malloc") &&
+			!strcmp(COMM(he), "perf") && he->stat.period == 100);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			!strcmp(DSO(he), "[kernel]") && !strcmp(SYM(he), "page_fault") &&
+			!strcmp(COMM(he), "bash") && he->stat.period == 100);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			!strcmp(DSO(he), "[kernel]") && !strcmp(SYM(he), "page_fault") &&
+			!strcmp(COMM(he), "perf") && he->stat.period == 100);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			!strcmp(DSO(he), "[kernel]") && !strcmp(SYM(he), "schedule") &&
+			!strcmp(COMM(he), "perf") && he->stat.period == 100);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			!strcmp(DSO(he), "bash") && !strcmp(SYM(he), "xmalloc") &&
+			!strcmp(COMM(he), "bash") && he->stat.period == 100);
+
+out:
+	del_hist_entries(hists);
+	reset_output_field();
+	return err;
+}
+
+/* full sort keys w/o overhead field */
+static int test5(struct perf_evsel *evsel, struct machine *machine)
+{
+	int err;
+	struct hists *hists = &evsel->hists;
+	struct hist_entry *he;
+	struct rb_root *root;
+	struct rb_node *node;
+
+	field_order = "cpu,pid,comm,dso,sym";
+	sort_order = "dso,pid";
+
+	setup_sorting();
+
+	/*
+	 * expected output:
+	 *
+	 * CPU  Command:  Pid  Command  Shared Object          Symbol
+	 * ===  =============  =======  =============  ==============
+	 *   0     perf:  100     perf       [kernel]  [k] schedule
+	 *   2     perf:  200     perf       [kernel]  [k] page_fault
+	 *   1     bash:  300     bash       [kernel]  [k] page_fault
+	 *   0     bash:  300     bash           bash  [.] xmalloc
+	 *   3     bash:  300     bash           bash  [.] main
+	 *   1     perf:  100     perf           libc  [.] malloc
+	 *   2     perf:  100     perf           libc  [.] free
+	 *   1     perf:  100     perf           perf  [.] cmd_record
+	 *   1     perf:  100     perf           perf  [.] main
+	 *   2     perf:  200     perf           perf  [.] main
+	 */
+	err = add_hist_entries(hists, machine);
+	if (err < 0)
+		goto out;
+
+	hists__collapse_resort(hists, NULL);
+	hists__output_resort(hists);
+
+	if (verbose > 2) {
+		pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
+		print_hists_out(hists);
+	}
+
+	root = &evsel->hists.entries;
+	node = rb_first(root);
+	he = rb_entry(node, struct hist_entry, rb_node);
+
+	TEST_ASSERT_VAL("Invalid hist entry",
+			CPU(he) == 0 && PID(he) == 100 &&
+			!strcmp(COMM(he), "perf") && !strcmp(DSO(he), "[kernel]") &&
+			!strcmp(SYM(he), "schedule") && he->stat.period == 100);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			CPU(he) == 2 && PID(he) == 200 &&
+			!strcmp(COMM(he), "perf") && !strcmp(DSO(he), "[kernel]") &&
+			!strcmp(SYM(he), "page_fault") && he->stat.period == 100);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			CPU(he) == 1 && PID(he) == 300 &&
+			!strcmp(COMM(he), "bash") && !strcmp(DSO(he), "[kernel]") &&
+			!strcmp(SYM(he), "page_fault") && he->stat.period == 100);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			CPU(he) == 0 && PID(he) == 300 &&
+			!strcmp(COMM(he), "bash") && !strcmp(DSO(he), "bash") &&
+			!strcmp(SYM(he), "xmalloc") && he->stat.period == 100);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			CPU(he) == 3 && PID(he) == 300 &&
+			!strcmp(COMM(he), "bash") && !strcmp(DSO(he), "bash") &&
+			!strcmp(SYM(he), "main") && he->stat.period == 100);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			CPU(he) == 1 && PID(he) == 100 &&
+			!strcmp(COMM(he), "perf") && !strcmp(DSO(he), "libc") &&
+			!strcmp(SYM(he), "malloc") && he->stat.period == 100);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			CPU(he) == 2 && PID(he) == 100 &&
+			!strcmp(COMM(he), "perf") && !strcmp(DSO(he), "libc") &&
+			!strcmp(SYM(he), "free") && he->stat.period == 100);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			CPU(he) == 1 && PID(he) == 100 &&
+			!strcmp(COMM(he), "perf") && !strcmp(DSO(he), "perf") &&
+			!strcmp(SYM(he), "cmd_record") && he->stat.period == 100);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			CPU(he) == 1 && PID(he) == 100 &&
+			!strcmp(COMM(he), "perf") && !strcmp(DSO(he), "perf") &&
+			!strcmp(SYM(he), "main") && he->stat.period == 100);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			CPU(he) == 2 && PID(he) == 200 &&
+			!strcmp(COMM(he), "perf") && !strcmp(DSO(he), "perf") &&
+			!strcmp(SYM(he), "main") && he->stat.period == 100);
+
+out:
+	del_hist_entries(hists);
+	reset_output_field();
+	return err;
+}
+
+int test__hists_output(void)
+{
+	int err = TEST_FAIL;
+	struct machines machines;
+	struct machine *machine;
+	struct perf_evsel *evsel;
+	struct perf_evlist *evlist = perf_evlist__new();
+	size_t i;
+	test_fn_t testcases[] = {
+		test1,
+		test2,
+		test3,
+		test4,
+		test5,
+	};
+
+	TEST_ASSERT_VAL("No memory", evlist);
+
+	err = parse_events(evlist, "cpu-clock");
+	if (err)
+		goto out;
+
+	machines__init(&machines);
+
+	/* setup threads/dso/map/symbols also */
+	machine = setup_fake_machine(&machines);
+	if (!machine)
+		goto out;
+
+	if (verbose > 1)
+		machine__fprintf(machine, stderr);
+
+	evsel = perf_evlist__first(evlist);
+
+	for (i = 0; i < ARRAY_SIZE(testcases); i++) {
+		err = testcases[i](evsel, machine);
+		if (err < 0)
+			break;
+	}
+
+out:
+	/* tear down everything */
+	perf_evlist__delete(evlist);
+	machines__exit(&machines);
+
+	return err;
+}
diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c
index 497957f269d8..7a5ab7b0b8f6 100644
--- a/tools/perf/tests/keep-tracking.c
+++ b/tools/perf/tests/keep-tracking.c
@@ -1,4 +1,4 @@
-#include <sys/types.h>
+#include <linux/types.h>
 #include <unistd.h>
 #include <sys/prctl.h>
 
diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c
new file mode 100644
index 000000000000..4a456fef66ca
--- /dev/null
+++ b/tools/perf/tests/mmap-thread-lookup.c
@@ -0,0 +1,233 @@
+#include <unistd.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <sys/mman.h>
+#include <pthread.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include "debug.h"
+#include "tests.h"
+#include "machine.h"
+#include "thread_map.h"
+#include "symbol.h"
+#include "thread.h"
+
+#define THREADS 4
+
+static int go_away;
+
+struct thread_data {
+	pthread_t	pt;
+	pid_t		tid;
+	void		*map;
+	int		ready[2];
+};
+
+static struct thread_data threads[THREADS];
+
+static int thread_init(struct thread_data *td)
+{
+	void *map;
+
+	map = mmap(NULL, page_size,
+		   PROT_READ|PROT_WRITE|PROT_EXEC,
+		   MAP_SHARED|MAP_ANONYMOUS, -1, 0);
+
+	if (map == MAP_FAILED) {
+		perror("mmap failed");
+		return -1;
+	}
+
+	td->map = map;
+	td->tid = syscall(SYS_gettid);
+
+	pr_debug("tid = %d, map = %p\n", td->tid, map);
+	return 0;
+}
+
+static void *thread_fn(void *arg)
+{
+	struct thread_data *td = arg;
+	ssize_t ret;
+	int go;
+
+	if (thread_init(td))
+		return NULL;
+
+	/* Signal thread_create thread is initialized. */
+	ret = write(td->ready[1], &go, sizeof(int));
+	if (ret != sizeof(int)) {
+		pr_err("failed to notify\n");
+		return NULL;
+	}
+
+	while (!go_away) {
+		/* Waiting for main thread to kill us. */
+		usleep(100);
+	}
+
+	munmap(td->map, page_size);
+	return NULL;
+}
+
+static int thread_create(int i)
+{
+	struct thread_data *td = &threads[i];
+	int err, go;
+
+	if (pipe(td->ready))
+		return -1;
+
+	err = pthread_create(&td->pt, NULL, thread_fn, td);
+	if (!err) {
+		/* Wait for thread initialization. */
+		ssize_t ret = read(td->ready[0], &go, sizeof(int));
+		err = ret != sizeof(int);
+	}
+
+	close(td->ready[0]);
+	close(td->ready[1]);
+	return err;
+}
+
+static int threads_create(void)
+{
+	struct thread_data *td0 = &threads[0];
+	int i, err = 0;
+
+	go_away = 0;
+
+	/* 0 is main thread */
+	if (thread_init(td0))
+		return -1;
+
+	for (i = 1; !err && i < THREADS; i++)
+		err = thread_create(i);
+
+	return err;
+}
+
+static int threads_destroy(void)
+{
+	struct thread_data *td0 = &threads[0];
+	int i, err = 0;
+
+	/* cleanup the main thread */
+	munmap(td0->map, page_size);
+
+	go_away = 1;
+
+	for (i = 1; !err && i < THREADS; i++)
+		err = pthread_join(threads[i].pt, NULL);
+
+	return err;
+}
+
+typedef int (*synth_cb)(struct machine *machine);
+
+static int synth_all(struct machine *machine)
+{
+	return perf_event__synthesize_threads(NULL,
+					      perf_event__process,
+					      machine, 0);
+}
+
+static int synth_process(struct machine *machine)
+{
+	struct thread_map *map;
+	int err;
+
+	map = thread_map__new_by_pid(getpid());
+
+	err = perf_event__synthesize_thread_map(NULL, map,
+						perf_event__process,
+						machine, 0);
+
+	thread_map__delete(map);
+	return err;
+}
+
+static int mmap_events(synth_cb synth)
+{
+	struct machines machines;
+	struct machine *machine;
+	int err, i;
+
+	/*
+	 * The threads_create will not return before all threads
+	 * are spawned and all created memory map.
+	 *
+	 * They will loop until threads_destroy is called, so we
+	 * can safely run synthesizing function.
+	 */
+	TEST_ASSERT_VAL("failed to create threads", !threads_create());
+
+	machines__init(&machines);
+	machine = &machines.host;
+
+	dump_trace = verbose > 1 ? 1 : 0;
+
+	err = synth(machine);
+
+	dump_trace = 0;
+
+	TEST_ASSERT_VAL("failed to destroy threads", !threads_destroy());
+	TEST_ASSERT_VAL("failed to synthesize maps", !err);
+
+	/*
+	 * All data is synthesized, try to find map for each
+	 * thread object.
+	 */
+	for (i = 0; i < THREADS; i++) {
+		struct thread_data *td = &threads[i];
+		struct addr_location al;
+		struct thread *thread;
+
+		thread = machine__findnew_thread(machine, getpid(), td->tid);
+
+		pr_debug("looking for map %p\n", td->map);
+
+		thread__find_addr_map(thread, machine,
+				      PERF_RECORD_MISC_USER, MAP__FUNCTION,
+				      (unsigned long) (td->map + 1), &al);
+
+		if (!al.map) {
+			pr_debug("failed, couldn't find map\n");
+			err = -1;
+			break;
+		}
+
+		pr_debug("map %p, addr %" PRIx64 "\n", al.map, al.map->start);
+	}
+
+	machine__delete_threads(machine);
+	machines__exit(&machines);
+	return err;
+}
+
+/*
+ * This test creates 'THREADS' number of threads (including
+ * main thread) and each thread creates memory map.
+ *
+ * When threads are created, we synthesize them with both
+ * (separate tests):
+ *   perf_event__synthesize_thread_map (process based)
+ *   perf_event__synthesize_threads    (global)
+ *
+ * We test we can find all memory maps via:
+ *   thread__find_addr_map
+ *
+ * by using all thread objects.
+ */
+int test__mmap_thread_lookup(void)
+{
+	/* perf_event__synthesize_threads synthesize */
+	TEST_ASSERT_VAL("failed with sythesizing all",
+			!mmap_events(synth_all));
+
+	/* perf_event__synthesize_thread_map synthesize */
+	TEST_ASSERT_VAL("failed with sythesizing process",
+			!mmap_events(synth_process));
+
+	return 0;
+}
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 8605ff5572ae..deba66955f8c 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -1174,188 +1174,240 @@ static int test__all_tracepoints(struct perf_evlist *evlist)
 struct evlist_test {
 	const char *name;
 	__u32 type;
+	const int id;
 	int (*check)(struct perf_evlist *evlist);
 };
 
 static struct evlist_test test__events[] = {
-	[0] = {
+	{
 		.name  = "syscalls:sys_enter_open",
 		.check = test__checkevent_tracepoint,
+		.id    = 0,
 	},
-	[1] = {
+	{
 		.name  = "syscalls:*",
 		.check = test__checkevent_tracepoint_multi,
+		.id    = 1,
 	},
-	[2] = {
+	{
 		.name  = "r1a",
 		.check = test__checkevent_raw,
+		.id    = 2,
 	},
-	[3] = {
+	{
 		.name  = "1:1",
 		.check = test__checkevent_numeric,
+		.id    = 3,
 	},
-	[4] = {
+	{
 		.name  = "instructions",
 		.check = test__checkevent_symbolic_name,
+		.id    = 4,
 	},
-	[5] = {
+	{
 		.name  = "cycles/period=100000,config2/",
 		.check = test__checkevent_symbolic_name_config,
+		.id    = 5,
 	},
-	[6] = {
+	{
 		.name  = "faults",
 		.check = test__checkevent_symbolic_alias,
+		.id    = 6,
 	},
-	[7] = {
+	{
 		.name  = "L1-dcache-load-miss",
 		.check = test__checkevent_genhw,
+		.id    = 7,
 	},
-	[8] = {
+	{
 		.name  = "mem:0",
 		.check = test__checkevent_breakpoint,
+		.id    = 8,
 	},
-	[9] = {
+	{
 		.name  = "mem:0:x",
 		.check = test__checkevent_breakpoint_x,
+		.id    = 9,
 	},
-	[10] = {
+	{
 		.name  = "mem:0:r",
 		.check = test__checkevent_breakpoint_r,
+		.id    = 10,
 	},
-	[11] = {
+	{
 		.name  = "mem:0:w",
 		.check = test__checkevent_breakpoint_w,
+		.id    = 11,
 	},
-	[12] = {
+	{
 		.name  = "syscalls:sys_enter_open:k",
 		.check = test__checkevent_tracepoint_modifier,
+		.id    = 12,
 	},
-	[13] = {
+	{
 		.name  = "syscalls:*:u",
 		.check = test__checkevent_tracepoint_multi_modifier,
+		.id    = 13,
 	},
-	[14] = {
+	{
 		.name  = "r1a:kp",
 		.check = test__checkevent_raw_modifier,
+		.id    = 14,
 	},
-	[15] = {
+	{
 		.name  = "1:1:hp",
 		.check = test__checkevent_numeric_modifier,
+		.id    = 15,
 	},
-	[16] = {
+	{
 		.name  = "instructions:h",
 		.check = test__checkevent_symbolic_name_modifier,
+		.id    = 16,
 	},
-	[17] = {
+	{
 		.name  = "faults:u",
 		.check = test__checkevent_symbolic_alias_modifier,
+		.id    = 17,
 	},
-	[18] = {
+	{
 		.name  = "L1-dcache-load-miss:kp",
 		.check = test__checkevent_genhw_modifier,
+		.id    = 18,
 	},
-	[19] = {
+	{
 		.name  = "mem:0:u",
 		.check = test__checkevent_breakpoint_modifier,
+		.id    = 19,
 	},
-	[20] = {
+	{
 		.name  = "mem:0:x:k",
 		.check = test__checkevent_breakpoint_x_modifier,
+		.id    = 20,
 	},
-	[21] = {
+	{
 		.name  = "mem:0:r:hp",
 		.check = test__checkevent_breakpoint_r_modifier,
+		.id    = 21,
 	},
-	[22] = {
+	{
 		.name  = "mem:0:w:up",
 		.check = test__checkevent_breakpoint_w_modifier,
+		.id    = 22,
 	},
-	[23] = {
+	{
 		.name  = "r1,syscalls:sys_enter_open:k,1:1:hp",
 		.check = test__checkevent_list,
+		.id    = 23,
 	},
-	[24] = {
+	{
 		.name  = "instructions:G",
 		.check = test__checkevent_exclude_host_modifier,
+		.id    = 24,
 	},
-	[25] = {
+	{
 		.name  = "instructions:H",
 		.check = test__checkevent_exclude_guest_modifier,
+		.id    = 25,
 	},
-	[26] = {
+	{
 		.name  = "mem:0:rw",
 		.check = test__checkevent_breakpoint_rw,
+		.id    = 26,
 	},
-	[27] = {
+	{
 		.name  = "mem:0:rw:kp",
 		.check = test__checkevent_breakpoint_rw_modifier,
+		.id    = 27,
 	},
-	[28] = {
+	{
 		.name  = "{instructions:k,cycles:upp}",
 		.check = test__group1,
+		.id    = 28,
 	},
-	[29] = {
+	{
 		.name  = "{faults:k,cache-references}:u,cycles:k",
 		.check = test__group2,
+		.id    = 29,
 	},
-	[30] = {
+	{
 		.name  = "group1{syscalls:sys_enter_open:H,cycles:kppp},group2{cycles,1:3}:G,instructions:u",
 		.check = test__group3,
+		.id    = 30,
 	},
-	[31] = {
+	{
 		.name  = "{cycles:u,instructions:kp}:p",
 		.check = test__group4,
+		.id    = 31,
 	},
-	[32] = {
+	{
 		.name  = "{cycles,instructions}:G,{cycles:G,instructions:G},cycles",
 		.check = test__group5,
+		.id    = 32,
 	},
-	[33] = {
+	{
 		.name  = "*:*",
 		.check = test__all_tracepoints,
+		.id    = 33,
 	},
-	[34] = {
+	{
 		.name  = "{cycles,cache-misses:G}:H",
 		.check = test__group_gh1,
+		.id    = 34,
 	},
-	[35] = {
+	{
 		.name  = "{cycles,cache-misses:H}:G",
 		.check = test__group_gh2,
+		.id    = 35,
 	},
-	[36] = {
+	{
 		.name  = "{cycles:G,cache-misses:H}:u",
 		.check = test__group_gh3,
+		.id    = 36,
 	},
-	[37] = {
+	{
 		.name  = "{cycles:G,cache-misses:H}:uG",
 		.check = test__group_gh4,
+		.id    = 37,
 	},
-	[38] = {
+	{
 		.name  = "{cycles,cache-misses,branch-misses}:S",
 		.check = test__leader_sample1,
+		.id    = 38,
 	},
-	[39] = {
+	{
 		.name  = "{instructions,branch-misses}:Su",
 		.check = test__leader_sample2,
+		.id    = 39,
 	},
-	[40] = {
+	{
 		.name  = "instructions:uDp",
 		.check = test__checkevent_pinned_modifier,
+		.id    = 40,
 	},
-	[41] = {
+	{
 		.name  = "{cycles,cache-misses,branch-misses}:D",
 		.check = test__pinned_group,
+		.id    = 41,
+	},
+#if defined(__s390x__)
+	{
+		.name  = "kvm-s390:kvm_s390_create_vm",
+		.check = test__checkevent_tracepoint,
+		.id    = 100,
 	},
+#endif
 };
 
 static struct evlist_test test__events_pmu[] = {
-	[0] = {
+	{
 		.name  = "cpu/config=10,config1,config2=3,period=1000/u",
 		.check = test__checkevent_pmu,
+		.id    = 0,
 	},
-	[1] = {
+	{
 		.name  = "cpu/config=1,name=krava/u,cpu/config=2/u",
 		.check = test__checkevent_pmu_name,
+		.id    = 1,
 	},
 };
 
@@ -1402,7 +1454,7 @@ static int test_events(struct evlist_test *events, unsigned cnt)
 	for (i = 0; i < cnt; i++) {
 		struct evlist_test *e = &events[i];
 
-		pr_debug("running test %d '%s'\n", i, e->name);
+		pr_debug("running test %d '%s'\n", e->id, e->name);
 		ret1 = test_event(e);
 		if (ret1)
 			ret2 = ret1;
diff --git a/tools/perf/tests/parse-no-sample-id-all.c b/tools/perf/tests/parse-no-sample-id-all.c
index e117b6c6a248..905019f9b740 100644
--- a/tools/perf/tests/parse-no-sample-id-all.c
+++ b/tools/perf/tests/parse-no-sample-id-all.c
@@ -1,4 +1,4 @@
-#include <sys/types.h>
+#include <linux/types.h>
 #include <stddef.h>
 
 #include "tests.h"
diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c
index 47146d388dbf..3b7cd4d32dcb 100644
--- a/tools/perf/tests/perf-time-to-tsc.c
+++ b/tools/perf/tests/perf-time-to-tsc.c
@@ -1,7 +1,6 @@
 #include <stdio.h>
-#include <sys/types.h>
 #include <unistd.h>
-#include <inttypes.h>
+#include <linux/types.h>
 #include <sys/prctl.h>
 
 #include "parse-events.h"
diff --git a/tools/perf/tests/rdpmc.c b/tools/perf/tests/rdpmc.c
index 46649c25fa5e..e59143fd9e71 100644
--- a/tools/perf/tests/rdpmc.c
+++ b/tools/perf/tests/rdpmc.c
@@ -2,7 +2,7 @@
 #include <stdlib.h>
 #include <signal.h>
 #include <sys/mman.h>
-#include "types.h"
+#include <linux/types.h>
 #include "perf.h"
 #include "debug.h"
 #include "tests.h"
diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c
index 0014d3c8c21c..7ae8d17db3d9 100644
--- a/tools/perf/tests/sample-parsing.c
+++ b/tools/perf/tests/sample-parsing.c
@@ -1,5 +1,5 @@
 #include <stdbool.h>
-#include <inttypes.h>
+#include <linux/types.h>
 
 #include "util.h"
 #include "event.h"
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index a24795ca002d..d76c0e2e6635 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -41,8 +41,12 @@ int test__sample_parsing(void);
 int test__keep_tracking(void);
 int test__parse_no_sample_id_all(void);
 int test__dwarf_unwind(void);
+int test__hists_filter(void);
+int test__mmap_thread_lookup(void);
+int test__thread_mg_share(void);
+int test__hists_output(void);
 
-#if defined(__x86_64__) || defined(__i386__)
+#if defined(__x86_64__) || defined(__i386__) || defined(__arm__)
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
 struct thread;
 struct perf_sample;
diff --git a/tools/perf/tests/thread-mg-share.c b/tools/perf/tests/thread-mg-share.c
new file mode 100644
index 000000000000..2b2e0dbe114f
--- /dev/null
+++ b/tools/perf/tests/thread-mg-share.c
@@ -0,0 +1,90 @@
+#include "tests.h"
+#include "machine.h"
+#include "thread.h"
+#include "map.h"
+
+int test__thread_mg_share(void)
+{
+	struct machines machines;
+	struct machine *machine;
+
+	/* thread group */
+	struct thread *leader;
+	struct thread *t1, *t2, *t3;
+	struct map_groups *mg;
+
+	/* other process */
+	struct thread *other, *other_leader;
+	struct map_groups *other_mg;
+
+	/*
+	 * This test create 2 processes abstractions (struct thread)
+	 * with several threads and checks they properly share and
+	 * maintain map groups info (struct map_groups).
+	 *
+	 * thread group (pid: 0, tids: 0, 1, 2, 3)
+	 * other  group (pid: 4, tids: 4, 5)
+	*/
+
+	machines__init(&machines);
+	machine = &machines.host;
+
+	/* create process with 4 threads */
+	leader = machine__findnew_thread(machine, 0, 0);
+	t1     = machine__findnew_thread(machine, 0, 1);
+	t2     = machine__findnew_thread(machine, 0, 2);
+	t3     = machine__findnew_thread(machine, 0, 3);
+
+	/* and create 1 separated process, without thread leader */
+	other  = machine__findnew_thread(machine, 4, 5);
+
+	TEST_ASSERT_VAL("failed to create threads",
+			leader && t1 && t2 && t3 && other);
+
+	mg = leader->mg;
+	TEST_ASSERT_VAL("wrong refcnt", mg->refcnt == 4);
+
+	/* test the map groups pointer is shared */
+	TEST_ASSERT_VAL("map groups don't match", mg == t1->mg);
+	TEST_ASSERT_VAL("map groups don't match", mg == t2->mg);
+	TEST_ASSERT_VAL("map groups don't match", mg == t3->mg);
+
+	/*
+	 * Verify the other leader was created by previous call.
+	 * It should have shared map groups with no change in
+	 * refcnt.
+	 */
+	other_leader = machine__find_thread(machine, 4, 4);
+	TEST_ASSERT_VAL("failed to find other leader", other_leader);
+
+	other_mg = other->mg;
+	TEST_ASSERT_VAL("wrong refcnt", other_mg->refcnt == 2);
+
+	TEST_ASSERT_VAL("map groups don't match", other_mg == other_leader->mg);
+
+	/* release thread group */
+	thread__delete(leader);
+	TEST_ASSERT_VAL("wrong refcnt", mg->refcnt == 3);
+
+	thread__delete(t1);
+	TEST_ASSERT_VAL("wrong refcnt", mg->refcnt == 2);
+
+	thread__delete(t2);
+	TEST_ASSERT_VAL("wrong refcnt", mg->refcnt == 1);
+
+	thread__delete(t3);
+
+	/* release other group  */
+	thread__delete(other_leader);
+	TEST_ASSERT_VAL("wrong refcnt", other_mg->refcnt == 1);
+
+	thread__delete(other);
+
+	/*
+	 * Cannot call machine__delete_threads(machine) now,
+	 * because we've already released all the threads.
+	 */
+
+	machines__exit(&machines);
+	return 0;
+}