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);
-	}