Initial import

77 files changed, 11310 insertions, 0 deletions

diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
new file mode 100644
index 000000000..6a8801b32
--- /dev/null
+++ b/tools/perf/tests/Build
@@ -0,0 +1,43 @@
+perf-y += builtin-test.o
+perf-y += parse-events.o
+perf-y += dso-data.o
+perf-y += attr.o
+perf-y += vmlinux-kallsyms.o
+perf-y += open-syscall.o
+perf-y += open-syscall-all-cpus.o
+perf-y += open-syscall-tp-fields.o
+perf-y += mmap-basic.o
+perf-y += perf-record.o
+perf-y += rdpmc.o
+perf-y += evsel-roundtrip-name.o
+perf-y += evsel-tp-sched.o
+perf-y += fdarray.o
+perf-y += pmu.o
+perf-y += hists_common.o
+perf-y += hists_link.o
+perf-y += hists_filter.o
+perf-y += hists_output.o
+perf-y += hists_cumulate.o
+perf-y += python-use.o
+perf-y += bp_signal.o
+perf-y += bp_signal_overflow.o
+perf-y += task-exit.o
+perf-y += sw-clock.o
+perf-y += mmap-thread-lookup.o
+perf-y += thread-mg-share.o
+perf-y += switch-tracking.o
+perf-y += keep-tracking.o
+perf-y += code-reading.o
+perf-y += sample-parsing.o
+perf-y += parse-no-sample-id-all.o
+perf-y += kmod-path.o
+
+perf-$(CONFIG_X86) += perf-time-to-tsc.o
+
+ifeq ($(ARCH),$(filter $(ARCH),x86 arm))
+perf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o
+endif
+
+CFLAGS_attr.o         += -DBINDIR="BUILD_STR($(bindir_SQ))" -DPYTHON="BUILD_STR($(PYTHON_WORD))"
+CFLAGS_python-use.o   += -DPYTHONPATH="BUILD_STR($(OUTPUT)python)" -DPYTHON="BUILD_STR($(PYTHON_WORD))"
+CFLAGS_dwarf-unwind.o += -fno-optimize-sibling-calls
diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c
new file mode 100644
index 000000000..2dfc9ad0e
--- /dev/null
+++ b/tools/perf/tests/attr.c
@@ -0,0 +1,176 @@
+/*
+ * The struct perf_event_attr test support.
+ *
+ * This test is embedded inside into perf directly and is governed
+ * by the PERF_TEST_ATTR environment variable and hook inside
+ * sys_perf_event_open function.
+ *
+ * The general idea is to store 'struct perf_event_attr' details for
+ * each event created within single perf command. Each event details
+ * are stored into separate text file. Once perf command is finished
+ * these files can be checked for values we expect for command.
+ *
+ * Besides 'struct perf_event_attr' values we also store 'fd' and
+ * 'group_fd' values to allow checking for groups created.
+ *
+ * This all is triggered by setting PERF_TEST_ATTR environment variable.
+ * It must contain name of existing directory with access and write
+ * permissions. All the event text files are stored there.
+ */
+
+#include <stdlib.h>
+#include <stdio.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include "../perf.h"
+#include "util.h"
+#include "exec_cmd.h"
+#include "tests.h"
+
+#define ENV "PERF_TEST_ATTR"
+
+extern int verbose;
+
+static char *dir;
+
+void test_attr__init(void)
+{
+	dir = getenv(ENV);
+	test_attr__enabled = (dir != NULL);
+}
+
+#define BUFSIZE 1024
+
+#define __WRITE_ASS(str, fmt, data)					\
+do {									\
+	char buf[BUFSIZE];						\
+	size_t size;							\
+									\
+	size = snprintf(buf, BUFSIZE, #str "=%"fmt "\n", data);		\
+	if (1 != fwrite(buf, size, 1, file)) {				\
+		perror("test attr - failed to write event file");	\
+		fclose(file);						\
+		return -1;						\
+	}								\
+									\
+} while (0)
+
+#define WRITE_ASS(field, fmt) __WRITE_ASS(field, fmt, attr->field)
+
+static int store_event(struct perf_event_attr *attr, pid_t pid, int cpu,
+		       int fd, int group_fd, unsigned long flags)
+{
+	FILE *file;
+	char path[PATH_MAX];
+
+	snprintf(path, PATH_MAX, "%s/event-%d-%llu-%d", dir,
+		 attr->type, attr->config, fd);
+
+	file = fopen(path, "w+");
+	if (!file) {
+		perror("test attr - failed to open event file");
+		return -1;
+	}
+
+	if (fprintf(file, "[event-%d-%llu-%d]\n",
+		    attr->type, attr->config, fd) < 0) {
+		perror("test attr - failed to write event file");
+		fclose(file);
+		return -1;
+	}
+
+	/* syscall arguments */
+	__WRITE_ASS(fd,       "d", fd);
+	__WRITE_ASS(group_fd, "d", group_fd);
+	__WRITE_ASS(cpu,      "d", cpu);
+	__WRITE_ASS(pid,      "d", pid);
+	__WRITE_ASS(flags,   "lu", flags);
+
+	/* struct perf_event_attr */
+	WRITE_ASS(type,   PRIu32);
+	WRITE_ASS(size,   PRIu32);
+	WRITE_ASS(config,  "llu");
+	WRITE_ASS(sample_period, "llu");
+	WRITE_ASS(sample_type,   "llu");
+	WRITE_ASS(read_format,   "llu");
+	WRITE_ASS(disabled,       "d");
+	WRITE_ASS(inherit,        "d");
+	WRITE_ASS(pinned,         "d");
+	WRITE_ASS(exclusive,      "d");
+	WRITE_ASS(exclude_user,   "d");
+	WRITE_ASS(exclude_kernel, "d");
+	WRITE_ASS(exclude_hv,     "d");
+	WRITE_ASS(exclude_idle,   "d");
+	WRITE_ASS(mmap,           "d");
+	WRITE_ASS(comm,           "d");
+	WRITE_ASS(freq,           "d");
+	WRITE_ASS(inherit_stat,   "d");
+	WRITE_ASS(enable_on_exec, "d");
+	WRITE_ASS(task,           "d");
+	WRITE_ASS(watermark,      "d");
+	WRITE_ASS(precise_ip,     "d");
+	WRITE_ASS(mmap_data,      "d");
+	WRITE_ASS(sample_id_all,  "d");
+	WRITE_ASS(exclude_host,   "d");
+	WRITE_ASS(exclude_guest,  "d");
+	WRITE_ASS(exclude_callchain_kernel, "d");
+	WRITE_ASS(exclude_callchain_user, "d");
+	WRITE_ASS(wakeup_events, PRIu32);
+	WRITE_ASS(bp_type, PRIu32);
+	WRITE_ASS(config1, "llu");
+	WRITE_ASS(config2, "llu");
+	WRITE_ASS(branch_sample_type, "llu");
+	WRITE_ASS(sample_regs_user,   "llu");
+	WRITE_ASS(sample_stack_user,  PRIu32);
+
+	fclose(file);
+	return 0;
+}
+
+void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu,
+		     int fd, int group_fd, unsigned long flags)
+{
+	int errno_saved = errno;
+
+	if (store_event(attr, pid, cpu, fd, group_fd, flags))
+		die("test attr FAILED");
+
+	errno = errno_saved;
+}
+
+static int run_dir(const char *d, const char *perf)
+{
+	char v[] = "-vvvvv";
+	int vcnt = min(verbose, (int) sizeof(v) - 1);
+	char cmd[3*PATH_MAX];
+
+	if (verbose)
+		vcnt++;
+
+	snprintf(cmd, 3*PATH_MAX, PYTHON " %s/attr.py -d %s/attr/ -p %s %.*s",
+		 d, d, perf, vcnt, v);
+
+	return system(cmd);
+}
+
+int test__attr(void)
+{
+	struct stat st;
+	char path_perf[PATH_MAX];
+	char path_dir[PATH_MAX];
+
+	/* First try developement tree tests. */
+	if (!lstat("./tests", &st))
+		return run_dir("./tests", "./perf");
+
+	/* Then installed path. */
+	snprintf(path_dir,  PATH_MAX, "%s/tests", perf_exec_path());
+	snprintf(path_perf, PATH_MAX, "%s/perf", BINDIR);
+
+	if (!lstat(path_dir, &st) &&
+	    !lstat(path_perf, &st))
+		return run_dir(path_dir, path_perf);
+
+	fprintf(stderr, " (omitted)");
+	return 0;
+}
diff --git a/tools/perf/tests/attr.py b/tools/perf/tests/attr.py
new file mode 100644
index 000000000..1091bd47a
--- /dev/null
+++ b/tools/perf/tests/attr.py
@@ -0,0 +1,331 @@
+#! /usr/bin/python
+
+import os
+import sys
+import glob
+import optparse
+import tempfile
+import logging
+import shutil
+import ConfigParser
+
+class Fail(Exception):
+    def __init__(self, test, msg):
+        self.msg = msg
+        self.test = test
+    def getMsg(self):
+        return '\'%s\' - %s' % (self.test.path, self.msg)
+
+class Unsup(Exception):
+    def __init__(self, test):
+        self.test = test
+    def getMsg(self):
+        return '\'%s\'' % self.test.path
+
+class Event(dict):
+    terms = [
+        'cpu',
+        'flags',
+        'type',
+        'size',
+        'config',
+        'sample_period',
+        'sample_type',
+        'read_format',
+        'disabled',
+        'inherit',
+        'pinned',
+        'exclusive',
+        'exclude_user',
+        'exclude_kernel',
+        'exclude_hv',
+        'exclude_idle',
+        'mmap',
+        'comm',
+        'freq',
+        'inherit_stat',
+        'enable_on_exec',
+        'task',
+        'watermark',
+        'precise_ip',
+        'mmap_data',
+        'sample_id_all',
+        'exclude_host',
+        'exclude_guest',
+        'exclude_callchain_kernel',
+        'exclude_callchain_user',
+        'wakeup_events',
+        'bp_type',
+        'config1',
+        'config2',
+        'branch_sample_type',
+        'sample_regs_user',
+        'sample_stack_user',
+    ]
+
+    def add(self, data):
+        for key, val in data:
+            log.debug("      %s = %s" % (key, val))
+            self[key] = val
+
+    def __init__(self, name, data, base):
+        log.debug("    Event %s" % name);
+        self.name  = name;
+        self.group = ''
+        self.add(base)
+        self.add(data)
+
+    def compare_data(self, a, b):
+        # Allow multiple values in assignment separated by '|'
+        a_list = a.split('|')
+        b_list = b.split('|')
+
+        for a_item in a_list:
+            for b_item in b_list:
+                if (a_item == b_item):
+                    return True
+                elif (a_item == '*') or (b_item == '*'):
+                    return True
+
+        return False
+
+    def equal(self, other):
+        for t in Event.terms:
+            log.debug("      [%s] %s %s" % (t, self[t], other[t]));
+            if not self.has_key(t) or not other.has_key(t):
+                return False
+            if not self.compare_data(self[t], other[t]):
+                return False
+        return True
+
+    def diff(self, other):
+        for t in Event.terms:
+            if not self.has_key(t) or not other.has_key(t):
+                continue
+            if not self.compare_data(self[t], other[t]):
+		log.warning("expected %s=%s, got %s" % (t, self[t], other[t]))
+
+# Test file description needs to have following sections:
+# [config]
+#   - just single instance in file
+#   - needs to specify:
+#     'command' - perf command name
+#     'args'    - special command arguments
+#     'ret'     - expected command return value (0 by default)
+#
+# [eventX:base]
+#   - one or multiple instances in file
+#   - expected values assignments
+class Test(object):
+    def __init__(self, path, options):
+        parser = ConfigParser.SafeConfigParser()
+        parser.read(path)
+
+        log.warning("running '%s'" % path)
+
+        self.path     = path
+        self.test_dir = options.test_dir
+        self.perf     = options.perf
+        self.command  = parser.get('config', 'command')
+        self.args     = parser.get('config', 'args')
+
+        try:
+            self.ret  = parser.get('config', 'ret')
+        except:
+            self.ret  = 0
+
+        self.expect   = {}
+        self.result   = {}
+        log.debug("  loading expected events");
+        self.load_events(path, self.expect)
+
+    def is_event(self, name):
+        if name.find("event") == -1:
+            return False
+        else:
+            return True
+
+    def load_events(self, path, events):
+        parser_event = ConfigParser.SafeConfigParser()
+        parser_event.read(path)
+
+        # The event record section header contains 'event' word,
+        # optionaly followed by ':' allowing to load 'parent
+        # event' first as a base
+        for section in filter(self.is_event, parser_event.sections()):
+
+            parser_items = parser_event.items(section);
+            base_items   = {}
+
+            # Read parent event if there's any
+            if (':' in section):
+                base = section[section.index(':') + 1:]
+                parser_base = ConfigParser.SafeConfigParser()
+                parser_base.read(self.test_dir + '/' + base)
+                base_items = parser_base.items('event')
+
+            e = Event(section, parser_items, base_items)
+            events[section] = e
+
+    def run_cmd(self, tempdir):
+        cmd = "PERF_TEST_ATTR=%s %s %s -o %s/perf.data %s" % (tempdir,
+              self.perf, self.command, tempdir, self.args)
+        ret = os.WEXITSTATUS(os.system(cmd))
+
+        log.info("  '%s' ret %d " % (cmd, ret))
+
+        if ret != int(self.ret):
+            raise Unsup(self)
+
+    def compare(self, expect, result):
+        match = {}
+
+        log.debug("  compare");
+
+        # For each expected event find all matching
+        # events in result. Fail if there's not any.
+        for exp_name, exp_event in expect.items():
+            exp_list = []
+            log.debug("    matching [%s]" % exp_name)
+            for res_name, res_event in result.items():
+                log.debug("      to [%s]" % res_name)
+                if (exp_event.equal(res_event)):
+                    exp_list.append(res_name)
+                    log.debug("    ->OK")
+                else:
+                    log.debug("    ->FAIL");
+
+            log.debug("    match: [%s] matches %s" % (exp_name, str(exp_list)))
+
+            # we did not any matching event - fail
+            if (not exp_list):
+		exp_event.diff(res_event)
+                raise Fail(self, 'match failure');
+
+            match[exp_name] = exp_list
+
+        # For each defined group in the expected events
+        # check we match the same group in the result.
+        for exp_name, exp_event in expect.items():
+            group = exp_event.group
+
+            if (group == ''):
+                continue
+
+            for res_name in match[exp_name]:
+                res_group = result[res_name].group
+                if res_group not in match[group]:
+                    raise Fail(self, 'group failure')
+
+                log.debug("    group: [%s] matches group leader %s" %
+                         (exp_name, str(match[group])))
+
+        log.debug("  matched")
+
+    def resolve_groups(self, events):
+        for name, event in events.items():
+            group_fd = event['group_fd'];
+            if group_fd == '-1':
+                continue;
+
+            for iname, ievent in events.items():
+                if (ievent['fd'] == group_fd):
+                    event.group = iname
+                    log.debug('[%s] has group leader [%s]' % (name, iname))
+                    break;
+
+    def run(self):
+        tempdir = tempfile.mkdtemp();
+
+        try:
+            # run the test script
+            self.run_cmd(tempdir);
+
+            # load events expectation for the test
+            log.debug("  loading result events");
+            for f in glob.glob(tempdir + '/event*'):
+                self.load_events(f, self.result);
+
+            # resolve group_fd to event names
+            self.resolve_groups(self.expect);
+            self.resolve_groups(self.result);
+
+            # do the expectation - results matching - both ways
+            self.compare(self.expect, self.result)
+            self.compare(self.result, self.expect)
+
+        finally:
+            # cleanup
+            shutil.rmtree(tempdir)
+
+
+def run_tests(options):
+    for f in glob.glob(options.test_dir + '/' + options.test):
+        try:
+            Test(f, options).run()
+        except Unsup, obj:
+            log.warning("unsupp  %s" % obj.getMsg())
+
+def setup_log(verbose):
+    global log
+    level = logging.CRITICAL
+
+    if verbose == 1:
+        level = logging.WARNING
+    if verbose == 2:
+        level = logging.INFO
+    if verbose >= 3:
+        level = logging.DEBUG
+
+    log = logging.getLogger('test')
+    log.setLevel(level)
+    ch  = logging.StreamHandler()
+    ch.setLevel(level)
+    formatter = logging.Formatter('%(message)s')
+    ch.setFormatter(formatter)
+    log.addHandler(ch)
+
+USAGE = '''%s [OPTIONS]
+  -d dir  # tests dir
+  -p path # perf binary
+  -t test # single test
+  -v      # verbose level
+''' % sys.argv[0]
+
+def main():
+    parser = optparse.OptionParser(usage=USAGE)
+
+    parser.add_option("-t", "--test",
+                      action="store", type="string", dest="test")
+    parser.add_option("-d", "--test-dir",
+                      action="store", type="string", dest="test_dir")
+    parser.add_option("-p", "--perf",
+                      action="store", type="string", dest="perf")
+    parser.add_option("-v", "--verbose",
+                      action="count", dest="verbose")
+
+    options, args = parser.parse_args()
+    if args:
+        parser.error('FAILED wrong arguments %s' %  ' '.join(args))
+        return -1
+
+    setup_log(options.verbose)
+
+    if not options.test_dir:
+        print 'FAILED no -d option specified'
+        sys.exit(-1)
+
+    if not options.test:
+        options.test = 'test*'
+
+    try:
+        run_tests(options)
+
+    except Fail, obj:
+        print "FAILED %s" % obj.getMsg();
+        sys.exit(-1)
+
+    sys.exit(0)
+
+if __name__ == '__main__':
+    main()
diff --git a/tools/perf/tests/attr/README b/tools/perf/tests/attr/README
new file mode 100644
index 000000000..430024f61
--- /dev/null
+++ b/tools/perf/tests/attr/README
@@ -0,0 +1,64 @@
+The struct perf_event_attr test (attr tests) support
+====================================================
+This testing support is embedded into perf directly and is governed
+by the PERF_TEST_ATTR environment variable and hook inside the
+sys_perf_event_open function.
+
+The general idea is to store 'struct perf_event_attr' details for
+each event created within single perf command. Each event details
+are stored into separate text file. Once perf command is finished
+these files are checked for values we expect for command.
+
+The attr tests consist of following parts:
+
+tests/attr.c
+------------
+This is the sys_perf_event_open hook implementation. The hook
+is triggered when the PERF_TEST_ATTR environment variable is
+defined. It must contain name of existing directory with access
+and write permissions.
+
+For each sys_perf_event_open call event details are stored in
+separate file. Besides 'struct perf_event_attr' values we also
+store 'fd' and 'group_fd' values to allow checking for groups.
+
+tests/attr.py
+-------------
+This is the python script that does all the hard work. It reads
+the test definition, executes it and checks results.
+
+tests/attr/
+-----------
+Directory containing all attr test definitions.
+Following tests are defined (with perf commands):
+
+  perf record kill                              (test-record-basic)
+  perf record -b kill                           (test-record-branch-any)
+  perf record -j any kill                       (test-record-branch-filter-any)
+  perf record -j any_call kill                  (test-record-branch-filter-any_call)
+  perf record -j any_ret kill                   (test-record-branch-filter-any_ret)
+  perf record -j hv kill                        (test-record-branch-filter-hv)
+  perf record -j ind_call kill                  (test-record-branch-filter-ind_call)
+  perf record -j k kill                         (test-record-branch-filter-k)
+  perf record -j u kill                         (test-record-branch-filter-u)
+  perf record -c 123 kill                       (test-record-count)
+  perf record -d kill                           (test-record-data)
+  perf record -F 100 kill                       (test-record-freq)
+  perf record -g kill                           (test-record-graph-default)
+  perf record --call-graph dwarf kill		(test-record-graph-dwarf)
+  perf record --call-graph fp kill              (test-record-graph-fp)
+  perf record --group -e cycles,instructions kill (test-record-group)
+  perf record -e '{cycles,instructions}' kill   (test-record-group1)
+  perf record -D kill                           (test-record-no-delay)
+  perf record -i kill                           (test-record-no-inherit)
+  perf record -n kill                           (test-record-no-samples)
+  perf record -c 100 -P kill                    (test-record-period)
+  perf record -R kill                           (test-record-raw)
+  perf stat -e cycles kill                      (test-stat-basic)
+  perf stat kill                                (test-stat-default)
+  perf stat -d kill                             (test-stat-detailed-1)
+  perf stat -dd kill                            (test-stat-detailed-2)
+  perf stat -ddd kill                           (test-stat-detailed-3)
+  perf stat --group -e cycles,instructions kill (test-stat-group)
+  perf stat -e '{cycles,instructions}' kill     (test-stat-group1)
+  perf stat -i -e cycles kill                   (test-stat-no-inherit)
diff --git a/tools/perf/tests/attr/base-record b/tools/perf/tests/attr/base-record
new file mode 100644
index 000000000..7e6d74946
--- /dev/null
+++ b/tools/perf/tests/attr/base-record
@@ -0,0 +1,41 @@
+[event]
+fd=1
+group_fd=-1
+# 0 or PERF_FLAG_FD_CLOEXEC flag
+flags=0|8
+cpu=*
+type=0|1
+size=112
+config=0
+sample_period=4000
+sample_type=263
+read_format=0
+disabled=1
+inherit=1
+pinned=0
+exclusive=0
+exclude_user=0
+exclude_kernel=0
+exclude_hv=0
+exclude_idle=0
+mmap=1
+comm=1
+freq=1
+inherit_stat=0
+enable_on_exec=1
+task=0
+watermark=0
+precise_ip=0
+mmap_data=0
+sample_id_all=1
+exclude_host=0|1
+exclude_guest=0|1
+exclude_callchain_kernel=0
+exclude_callchain_user=0
+wakeup_events=0
+bp_type=0
+config1=0
+config2=0
+branch_sample_type=0
+sample_regs_user=0
+sample_stack_user=0
diff --git a/tools/perf/tests/attr/base-stat b/tools/perf/tests/attr/base-stat
new file mode 100644
index 000000000..f4cf148f1
--- /dev/null
+++ b/tools/perf/tests/attr/base-stat
@@ -0,0 +1,41 @@
+[event]
+fd=1
+group_fd=-1
+# 0 or PERF_FLAG_FD_CLOEXEC flag
+flags=0|8
+cpu=*
+type=0
+size=112
+config=0
+sample_period=0
+sample_type=0
+read_format=3
+disabled=1
+inherit=1
+pinned=0
+exclusive=0
+exclude_user=0
+exclude_kernel=0
+exclude_hv=0
+exclude_idle=0
+mmap=0
+comm=0
+freq=0
+inherit_stat=0
+enable_on_exec=1
+task=0
+watermark=0
+precise_ip=0
+mmap_data=0
+sample_id_all=0
+exclude_host=0|1
+exclude_guest=0|1
+exclude_callchain_kernel=0
+exclude_callchain_user=0
+wakeup_events=0
+bp_type=0
+config1=0
+config2=0
+branch_sample_type=0
+sample_regs_user=0
+sample_stack_user=0
diff --git a/tools/perf/tests/attr/test-record-C0 b/tools/perf/tests/attr/test-record-C0
new file mode 100644
index 000000000..d6a7e43f6
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-C0
@@ -0,0 +1,13 @@
+[config]
+command = record
+args    = -C 0 kill >/dev/null 2>&1
+
+[event:base-record]
+cpu=0
+
+# no enable on exec for CPU attached
+enable_on_exec=0
+
+# PERF_SAMPLE_IP | PERF_SAMPLE_TID PERF_SAMPLE_TIME | # PERF_SAMPLE_PERIOD
+# + PERF_SAMPLE_CPU added by -C 0
+sample_type=391
diff --git a/tools/perf/tests/attr/test-record-basic b/tools/perf/tests/attr/test-record-basic
new file mode 100644
index 000000000..55c042837
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-basic
@@ -0,0 +1,5 @@
+[config]
+command = record
+args    = kill >/dev/null 2>&1
+
+[event:base-record]
diff --git a/tools/perf/tests/attr/test-record-branch-any b/tools/perf/tests/attr/test-record-branch-any
new file mode 100644
index 000000000..1421960ed
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-branch-any
@@ -0,0 +1,8 @@
+[config]
+command = record
+args    = -b kill >/dev/null 2>&1
+
+[event:base-record]
+sample_period=4000
+sample_type=2311
+branch_sample_type=8
diff --git a/tools/perf/tests/attr/test-record-branch-filter-any b/tools/perf/tests/attr/test-record-branch-filter-any
new file mode 100644
index 000000000..915c4df0e
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-branch-filter-any
@@ -0,0 +1,8 @@
+[config]
+command = record
+args    = -j any kill >/dev/null 2>&1
+
+[event:base-record]
+sample_period=4000
+sample_type=2311
+branch_sample_type=8
diff --git a/tools/perf/tests/attr/test-record-branch-filter-any_call b/tools/perf/tests/attr/test-record-branch-filter-any_call
new file mode 100644
index 000000000..8708dbd4f
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-branch-filter-any_call
@@ -0,0 +1,8 @@
+[config]
+command = record
+args    = -j any_call kill >/dev/null 2>&1
+
+[event:base-record]
+sample_period=4000
+sample_type=2311
+branch_sample_type=16
diff --git a/tools/perf/tests/attr/test-record-branch-filter-any_ret b/tools/perf/tests/attr/test-record-branch-filter-any_ret
new file mode 100644
index 000000000..0d3607a6d
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-branch-filter-any_ret
@@ -0,0 +1,8 @@
+[config]
+command = record
+args    = -j any_ret kill >/dev/null 2>&1
+
+[event:base-record]
+sample_period=4000
+sample_type=2311
+branch_sample_type=32
diff --git a/tools/perf/tests/attr/test-record-branch-filter-hv b/tools/perf/tests/attr/test-record-branch-filter-hv
new file mode 100644
index 000000000..f25526740
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-branch-filter-hv
@@ -0,0 +1,8 @@
+[config]
+command = record
+args    = -j hv kill >/dev/null 2>&1
+
+[event:base-record]
+sample_period=4000
+sample_type=2311
+branch_sample_type=8
diff --git a/tools/perf/tests/attr/test-record-branch-filter-ind_call b/tools/perf/tests/attr/test-record-branch-filter-ind_call
new file mode 100644
index 000000000..e862dd179
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-branch-filter-ind_call
@@ -0,0 +1,8 @@
+[config]
+command = record
+args    = -j ind_call kill >/dev/null 2>&1
+
+[event:base-record]
+sample_period=4000
+sample_type=2311
+branch_sample_type=64
diff --git a/tools/perf/tests/attr/test-record-branch-filter-k b/tools/perf/tests/attr/test-record-branch-filter-k
new file mode 100644
index 000000000..182971e89
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-branch-filter-k
@@ -0,0 +1,8 @@
+[config]
+command = record
+args    = -j k kill >/dev/null 2>&1
+
+[event:base-record]
+sample_period=4000
+sample_type=2311
+branch_sample_type=8
diff --git a/tools/perf/tests/attr/test-record-branch-filter-u b/tools/perf/tests/attr/test-record-branch-filter-u
new file mode 100644
index 000000000..83449ef9e
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-branch-filter-u
@@ -0,0 +1,8 @@
+[config]
+command = record
+args    = -j u kill >/dev/null 2>&1
+
+[event:base-record]
+sample_period=4000
+sample_type=2311
+branch_sample_type=8
diff --git a/tools/perf/tests/attr/test-record-count b/tools/perf/tests/attr/test-record-count
new file mode 100644
index 000000000..2f841de56
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-count
@@ -0,0 +1,8 @@
+[config]
+command = record
+args    = -c 123 kill >/dev/null 2>&1
+
+[event:base-record]
+sample_period=123
+sample_type=7
+freq=0
diff --git a/tools/perf/tests/attr/test-record-data b/tools/perf/tests/attr/test-record-data
new file mode 100644
index 000000000..716e143b5
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-data
@@ -0,0 +1,11 @@
+[config]
+command = record
+args    = -d kill >/dev/null 2>&1
+
+[event:base-record]
+sample_period=4000
+
+# sample_type = PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_TIME |
+# PERF_SAMPLE_ADDR | PERF_SAMPLE_PERIOD | PERF_SAMPLE_DATA_SRC
+sample_type=33039
+mmap_data=1
diff --git a/tools/perf/tests/attr/test-record-freq b/tools/perf/tests/attr/test-record-freq
new file mode 100644
index 000000000..600d0f8f2
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-freq
@@ -0,0 +1,6 @@
+[config]
+command = record
+args    = -F 100 kill >/dev/null 2>&1
+
+[event:base-record]
+sample_period=100
diff --git a/tools/perf/tests/attr/test-record-graph-default b/tools/perf/tests/attr/test-record-graph-default
new file mode 100644
index 000000000..853597a9a
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-graph-default
@@ -0,0 +1,6 @@
+[config]
+command = record
+args    = -g kill >/dev/null 2>&1
+
+[event:base-record]
+sample_type=295
diff --git a/tools/perf/tests/attr/test-record-graph-dwarf b/tools/perf/tests/attr/test-record-graph-dwarf
new file mode 100644
index 000000000..d6f324ea5
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-graph-dwarf
@@ -0,0 +1,10 @@
+[config]
+command = record
+args    = --call-graph dwarf -- kill >/dev/null 2>&1
+
+[event:base-record]
+sample_type=12583
+exclude_callchain_user=1
+sample_stack_user=8192
+# TODO different for each arch, no support for that now
+sample_regs_user=*
diff --git a/tools/perf/tests/attr/test-record-graph-fp b/tools/perf/tests/attr/test-record-graph-fp
new file mode 100644
index 000000000..055e3bee7
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-graph-fp
@@ -0,0 +1,6 @@
+[config]
+command = record
+args    = --call-graph fp kill >/dev/null 2>&1
+
+[event:base-record]
+sample_type=295
diff --git a/tools/perf/tests/attr/test-record-group b/tools/perf/tests/attr/test-record-group
new file mode 100644
index 000000000..57739cacd
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-group
@@ -0,0 +1,20 @@
+[config]
+command = record
+args    = --group -e cycles,instructions kill >/dev/null 2>&1
+
+[event-1:base-record]
+fd=1
+group_fd=-1
+sample_type=327
+read_format=4
+
+[event-2:base-record]
+fd=2
+group_fd=1
+config=1
+sample_type=327
+read_format=4
+mmap=0
+comm=0
+enable_on_exec=0
+disabled=0
diff --git a/tools/perf/tests/attr/test-record-group-sampling b/tools/perf/tests/attr/test-record-group-sampling
new file mode 100644
index 000000000..658f5d60c
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-group-sampling
@@ -0,0 +1,36 @@
+[config]
+command = record
+args    = -e '{cycles,cache-misses}:S' kill >/dev/null 2>&1
+
+[event-1:base-record]
+fd=1
+group_fd=-1
+sample_type=343
+read_format=12
+inherit=0
+
+[event-2:base-record]
+fd=2
+group_fd=1
+
+# cache-misses
+type=0
+config=3
+
+# default | PERF_SAMPLE_READ
+sample_type=343
+
+# PERF_FORMAT_ID | PERF_FORMAT_GROUP
+read_format=12
+
+mmap=0
+comm=0
+enable_on_exec=0
+disabled=0
+
+# inherit is disabled for group sampling
+inherit=0
+
+# sampling disabled
+sample_freq=0
+sample_period=0
diff --git a/tools/perf/tests/attr/test-record-group1 b/tools/perf/tests/attr/test-record-group1
new file mode 100644
index 000000000..c5548d054
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-group1
@@ -0,0 +1,21 @@
+[config]
+command = record
+args    = -e '{cycles,instructions}' kill >/dev/null 2>&1
+
+[event-1:base-record]
+fd=1
+group_fd=-1
+sample_type=327
+read_format=4
+
+[event-2:base-record]
+fd=2
+group_fd=1
+type=0
+config=1
+sample_type=327
+read_format=4
+mmap=0
+comm=0
+enable_on_exec=0
+disabled=0
diff --git a/tools/perf/tests/attr/test-record-no-delay b/tools/perf/tests/attr/test-record-no-delay
new file mode 100644
index 000000000..f253b78cd
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-no-delay
@@ -0,0 +1,9 @@
+[config]
+command = record
+args    = -D kill >/dev/null 2>&1
+
+[event:base-record]
+sample_period=4000
+sample_type=263
+watermark=0
+wakeup_events=1
diff --git a/tools/perf/tests/attr/test-record-no-inherit b/tools/perf/tests/attr/test-record-no-inherit
new file mode 100644
index 000000000..44edcb2ed
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-no-inherit
@@ -0,0 +1,7 @@
+[config]
+command = record
+args    = -i kill >/dev/null 2>&1
+
+[event:base-record]
+sample_type=263
+inherit=0
diff --git a/tools/perf/tests/attr/test-record-no-samples b/tools/perf/tests/attr/test-record-no-samples
new file mode 100644
index 000000000..d0141b241
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-no-samples
@@ -0,0 +1,6 @@
+[config]
+command = record
+args    = -n kill >/dev/null 2>&1
+
+[event:base-record]
+sample_period=0
diff --git a/tools/perf/tests/attr/test-record-period b/tools/perf/tests/attr/test-record-period
new file mode 100644
index 000000000..8abc5314f
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-period
@@ -0,0 +1,7 @@
+[config]
+command = record
+args    = -c 100 -P kill >/dev/null 2>&1
+
+[event:base-record]
+sample_period=100
+freq=0
diff --git a/tools/perf/tests/attr/test-record-raw b/tools/perf/tests/attr/test-record-raw
new file mode 100644
index 000000000..4a8ef25b5
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-raw
@@ -0,0 +1,7 @@
+[config]
+command = record
+args    = -R kill >/dev/null 2>&1
+
+[event:base-record]
+sample_period=4000
+sample_type=1415
diff --git a/tools/perf/tests/attr/test-stat-C0 b/tools/perf/tests/attr/test-stat-C0
new file mode 100644
index 000000000..aa8359507
--- /dev/null
+++ b/tools/perf/tests/attr/test-stat-C0
@@ -0,0 +1,9 @@
+[config]
+command = stat
+args    = -e cycles -C 0 kill >/dev/null 2>&1
+ret     = 1
+
+[event:base-stat]
+# events are enabled by default when attached to cpu
+disabled=0
+enable_on_exec=0
diff --git a/tools/perf/tests/attr/test-stat-basic b/tools/perf/tests/attr/test-stat-basic
new file mode 100644
index 000000000..74e17881f
--- /dev/null
+++ b/tools/perf/tests/attr/test-stat-basic
@@ -0,0 +1,6 @@
+[config]
+command = stat
+args    = -e cycles kill >/dev/null 2>&1
+ret     = 1
+
+[event:base-stat]
diff --git a/tools/perf/tests/attr/test-stat-default b/tools/perf/tests/attr/test-stat-default
new file mode 100644
index 000000000..19270f54c
--- /dev/null
+++ b/tools/perf/tests/attr/test-stat-default
@@ -0,0 +1,64 @@
+[config]
+command = stat
+args    = kill >/dev/null 2>&1
+ret     = 1
+
+# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_TASK_CLOCK
+[event1:base-stat]
+fd=1
+type=1
+config=1
+
+# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_CONTEXT_SWITCHES
+[event2:base-stat]
+fd=2
+type=1
+config=3
+
+# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_CPU_MIGRATIONS
+[event3:base-stat]
+fd=3
+type=1
+config=4
+
+# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_PAGE_FAULTS
+[event4:base-stat]
+fd=4
+type=1
+config=2
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_CPU_CYCLES
+[event5:base-stat]
+fd=5
+type=0
+config=0
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_FRONTEND
+[event6:base-stat]
+fd=6
+type=0
+config=7
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_BACKEND
+[event7:base-stat]
+fd=7
+type=0
+config=8
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_INSTRUCTIONS
+[event8:base-stat]
+fd=8
+type=0
+config=1
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_INSTRUCTIONS
+[event9:base-stat]
+fd=9
+type=0
+config=4
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_MISSES
+[event10:base-stat]
+fd=10
+type=0
+config=5
diff --git a/tools/perf/tests/attr/test-stat-detailed-1 b/tools/perf/tests/attr/test-stat-detailed-1
new file mode 100644
index 000000000..51426b871
--- /dev/null
+++ b/tools/perf/tests/attr/test-stat-detailed-1
@@ -0,0 +1,101 @@
+[config]
+command = stat
+args    = -d kill >/dev/null 2>&1
+ret     = 1
+
+
+# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_TASK_CLOCK
+[event1:base-stat]
+fd=1
+type=1
+config=1
+
+# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_CONTEXT_SWITCHES
+[event2:base-stat]
+fd=2
+type=1
+config=3
+
+# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_CPU_MIGRATIONS
+[event3:base-stat]
+fd=3
+type=1
+config=4
+
+# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_PAGE_FAULTS
+[event4:base-stat]
+fd=4
+type=1
+config=2
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_CPU_CYCLES
+[event5:base-stat]
+fd=5
+type=0
+config=0
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_FRONTEND
+[event6:base-stat]
+fd=6
+type=0
+config=7
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_BACKEND
+[event7:base-stat]
+fd=7
+type=0
+config=8
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_INSTRUCTIONS
+[event8:base-stat]
+fd=8
+type=0
+config=1
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_INSTRUCTIONS
+[event9:base-stat]
+fd=9
+type=0
+config=4
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_MISSES
+[event10:base-stat]
+fd=10
+type=0
+config=5
+
+# PERF_TYPE_HW_CACHE /
+#  PERF_COUNT_HW_CACHE_L1D                <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
+[event11:base-stat]
+fd=11
+type=3
+config=0
+
+# PERF_TYPE_HW_CACHE /
+#  PERF_COUNT_HW_CACHE_L1D                <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
+[event12:base-stat]
+fd=12
+type=3
+config=65536
+
+# PERF_TYPE_HW_CACHE /
+#  PERF_COUNT_HW_CACHE_LL                 <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
+[event13:base-stat]
+fd=13
+type=3
+config=2
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_LL                 <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
+[event14:base-stat]
+fd=14
+type=3
+config=65538
diff --git a/tools/perf/tests/attr/test-stat-detailed-2 b/tools/perf/tests/attr/test-stat-detailed-2
new file mode 100644
index 000000000..8de5acc31
--- /dev/null
+++ b/tools/perf/tests/attr/test-stat-detailed-2
@@ -0,0 +1,155 @@
+[config]
+command = stat
+args    = -dd kill >/dev/null 2>&1
+ret     = 1
+
+
+# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_TASK_CLOCK
+[event1:base-stat]
+fd=1
+type=1
+config=1
+
+# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_CONTEXT_SWITCHES
+[event2:base-stat]
+fd=2
+type=1
+config=3
+
+# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_CPU_MIGRATIONS
+[event3:base-stat]
+fd=3
+type=1
+config=4
+
+# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_PAGE_FAULTS
+[event4:base-stat]
+fd=4
+type=1
+config=2
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_CPU_CYCLES
+[event5:base-stat]
+fd=5
+type=0
+config=0
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_FRONTEND
+[event6:base-stat]
+fd=6
+type=0
+config=7
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_BACKEND
+[event7:base-stat]
+fd=7
+type=0
+config=8
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_INSTRUCTIONS
+[event8:base-stat]
+fd=8
+type=0
+config=1
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_INSTRUCTIONS
+[event9:base-stat]
+fd=9
+type=0
+config=4
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_MISSES
+[event10:base-stat]
+fd=10
+type=0
+config=5
+
+# PERF_TYPE_HW_CACHE /
+#  PERF_COUNT_HW_CACHE_L1D                <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
+[event11:base-stat]
+fd=11
+type=3
+config=0
+
+# PERF_TYPE_HW_CACHE /
+#  PERF_COUNT_HW_CACHE_L1D                <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
+[event12:base-stat]
+fd=12
+type=3
+config=65536
+
+# PERF_TYPE_HW_CACHE /
+#  PERF_COUNT_HW_CACHE_LL                 <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
+[event13:base-stat]
+fd=13
+type=3
+config=2
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_LL                 <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
+[event14:base-stat]
+fd=14
+type=3
+config=65538
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_L1I                <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
+[event15:base-stat]
+fd=15
+type=3
+config=1
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_L1I                <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
+[event16:base-stat]
+fd=16
+type=3
+config=65537
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_DTLB               <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
+[event17:base-stat]
+fd=17
+type=3
+config=3
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_DTLB               <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
+[event18:base-stat]
+fd=18
+type=3
+config=65539
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_ITLB               <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
+[event19:base-stat]
+fd=19
+type=3
+config=4
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_ITLB               <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
+[event20:base-stat]
+fd=20
+type=3
+config=65540
diff --git a/tools/perf/tests/attr/test-stat-detailed-3 b/tools/perf/tests/attr/test-stat-detailed-3
new file mode 100644
index 000000000..0a1f45bf7
--- /dev/null
+++ b/tools/perf/tests/attr/test-stat-detailed-3
@@ -0,0 +1,173 @@
+[config]
+command = stat
+args    = -ddd kill >/dev/null 2>&1
+ret     = 1
+
+
+# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_TASK_CLOCK
+[event1:base-stat]
+fd=1
+type=1
+config=1
+
+# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_CONTEXT_SWITCHES
+[event2:base-stat]
+fd=2
+type=1
+config=3
+
+# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_CPU_MIGRATIONS
+[event3:base-stat]
+fd=3
+type=1
+config=4
+
+# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_PAGE_FAULTS
+[event4:base-stat]
+fd=4
+type=1
+config=2
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_CPU_CYCLES
+[event5:base-stat]
+fd=5
+type=0
+config=0
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_FRONTEND
+[event6:base-stat]
+fd=6
+type=0
+config=7
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_BACKEND
+[event7:base-stat]
+fd=7
+type=0
+config=8
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_INSTRUCTIONS
+[event8:base-stat]
+fd=8
+type=0
+config=1
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_INSTRUCTIONS
+[event9:base-stat]
+fd=9
+type=0
+config=4
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_MISSES
+[event10:base-stat]
+fd=10
+type=0
+config=5
+
+# PERF_TYPE_HW_CACHE /
+#  PERF_COUNT_HW_CACHE_L1D                <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
+[event11:base-stat]
+fd=11
+type=3
+config=0
+
+# PERF_TYPE_HW_CACHE /
+#  PERF_COUNT_HW_CACHE_L1D                <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
+[event12:base-stat]
+fd=12
+type=3
+config=65536
+
+# PERF_TYPE_HW_CACHE /
+#  PERF_COUNT_HW_CACHE_LL                 <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
+[event13:base-stat]
+fd=13
+type=3
+config=2
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_LL                 <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
+[event14:base-stat]
+fd=14
+type=3
+config=65538
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_L1I                <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
+[event15:base-stat]
+fd=15
+type=3
+config=1
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_L1I                <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
+[event16:base-stat]
+fd=16
+type=3
+config=65537
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_DTLB               <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
+[event17:base-stat]
+fd=17
+type=3
+config=3
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_DTLB               <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
+[event18:base-stat]
+fd=18
+type=3
+config=65539
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_ITLB               <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
+[event19:base-stat]
+fd=19
+type=3
+config=4
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_ITLB               <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
+[event20:base-stat]
+fd=20
+type=3
+config=65540
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_L1D                <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_PREFETCH        <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
+[event21:base-stat]
+fd=21
+type=3
+config=512
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_L1D                <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_PREFETCH        <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
+[event22:base-stat]
+fd=22
+type=3
+config=66048
diff --git a/tools/perf/tests/attr/test-stat-group b/tools/perf/tests/attr/test-stat-group
new file mode 100644
index 000000000..fdc1596a8
--- /dev/null
+++ b/tools/perf/tests/attr/test-stat-group
@@ -0,0 +1,15 @@
+[config]
+command = stat
+args    = --group -e cycles,instructions kill >/dev/null 2>&1
+ret     = 1
+
+[event-1:base-stat]
+fd=1
+group_fd=-1
+
+[event-2:base-stat]
+fd=2
+group_fd=1
+config=1
+disabled=0
+enable_on_exec=0
diff --git a/tools/perf/tests/attr/test-stat-group1 b/tools/perf/tests/attr/test-stat-group1
new file mode 100644
index 000000000..2a1f86e4a
--- /dev/null
+++ b/tools/perf/tests/attr/test-stat-group1
@@ -0,0 +1,15 @@
+[config]
+command = stat
+args    = -e '{cycles,instructions}' kill >/dev/null 2>&1
+ret     = 1
+
+[event-1:base-stat]
+fd=1
+group_fd=-1
+
+[event-2:base-stat]
+fd=2
+group_fd=1
+config=1
+disabled=0
+enable_on_exec=0
diff --git a/tools/perf/tests/attr/test-stat-no-inherit b/tools/perf/tests/attr/test-stat-no-inherit
new file mode 100644
index 000000000..d54b2a1e3
--- /dev/null
+++ b/tools/perf/tests/attr/test-stat-no-inherit
@@ -0,0 +1,7 @@
+[config]
+command = stat
+args    = -i -e cycles kill >/dev/null 2>&1
+ret     = 1
+
+[event:base-stat]
+inherit=0
diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c
new file mode 100644
index 000000000..a02b035fd
--- /dev/null
+++ b/tools/perf/tests/bp_signal.c
@@ -0,0 +1,194 @@
+/*
+ * Inspired by breakpoint overflow test done by
+ * Vince Weaver <vincent.weaver@maine.edu> for perf_event_tests
+ * (git://github.com/deater/perf_event_tests)
+ */
+
+/*
+ * 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 <unistd.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <time.h>
+#include <fcntl.h>
+#include <signal.h>
+#include <sys/mman.h>
+#include <linux/compiler.h>
+#include <linux/hw_breakpoint.h>
+
+#include "tests.h"
+#include "debug.h"
+#include "perf.h"
+#include "cloexec.h"
+
+static int fd1;
+static int fd2;
+static int overflows;
+
+__attribute__ ((noinline))
+static int test_function(void)
+{
+	return time(NULL);
+}
+
+static void sig_handler(int signum __maybe_unused,
+			siginfo_t *oh __maybe_unused,
+			void *uc __maybe_unused)
+{
+	overflows++;
+
+	if (overflows > 10) {
+		/*
+		 * This should be executed only once during
+		 * this test, if we are here for the 10th
+		 * time, consider this the recursive issue.
+		 *
+		 * We can get out of here by disable events,
+		 * so no new SIGIO is delivered.
+		 */
+		ioctl(fd1, PERF_EVENT_IOC_DISABLE, 0);
+		ioctl(fd2, PERF_EVENT_IOC_DISABLE, 0);
+	}
+}
+
+static int bp_event(void *fn, int setup_signal)
+{
+	struct perf_event_attr pe;
+	int fd;
+
+	memset(&pe, 0, sizeof(struct perf_event_attr));
+	pe.type = PERF_TYPE_BREAKPOINT;
+	pe.size = sizeof(struct perf_event_attr);
+
+	pe.config = 0;
+	pe.bp_type = HW_BREAKPOINT_X;
+	pe.bp_addr = (unsigned long) fn;
+	pe.bp_len = sizeof(long);
+
+	pe.sample_period = 1;
+	pe.sample_type = PERF_SAMPLE_IP;
+	pe.wakeup_events = 1;
+
+	pe.disabled = 1;
+	pe.exclude_kernel = 1;
+	pe.exclude_hv = 1;
+
+	fd = sys_perf_event_open(&pe, 0, -1, -1,
+				 perf_event_open_cloexec_flag());
+	if (fd < 0) {
+		pr_debug("failed opening event %llx\n", pe.config);
+		return TEST_FAIL;
+	}
+
+	if (setup_signal) {
+		fcntl(fd, F_SETFL, O_RDWR|O_NONBLOCK|O_ASYNC);
+		fcntl(fd, F_SETSIG, SIGIO);
+		fcntl(fd, F_SETOWN, getpid());
+	}
+
+	ioctl(fd, PERF_EVENT_IOC_RESET, 0);
+
+	return fd;
+}
+
+static long long bp_count(int fd)
+{
+	long long count;
+	int ret;
+
+	ret = read(fd, &count, sizeof(long long));
+	if (ret != sizeof(long long)) {
+		pr_debug("failed to read: %d\n", ret);
+		return TEST_FAIL;
+	}
+
+	return count;
+}
+
+int test__bp_signal(void)
+{
+	struct sigaction sa;
+	long long count1, count2;
+
+	/* setup SIGIO signal handler */
+	memset(&sa, 0, sizeof(struct sigaction));
+	sa.sa_sigaction = (void *) sig_handler;
+	sa.sa_flags = SA_SIGINFO;
+
+	if (sigaction(SIGIO, &sa, NULL) < 0) {
+		pr_debug("failed setting up signal handler\n");
+		return TEST_FAIL;
+	}
+
+	/*
+	 * We create following events:
+	 *
+	 * fd1 - breakpoint event on test_function with SIGIO
+	 *       signal configured. We should get signal
+	 *       notification each time the breakpoint is hit
+	 *
+	 * fd2 - breakpoint event on sig_handler without SIGIO
+	 *       configured.
+	 *
+	 * Following processing should happen:
+	 *   - execute test_function
+	 *   - fd1 event breakpoint hit -> count1 == 1
+	 *   - SIGIO is delivered       -> overflows == 1
+	 *   - fd2 event breakpoint hit -> count2 == 1
+	 *
+	 * The test case check following error conditions:
+	 * - we get stuck in signal handler because of debug
+	 *   exception being triggered receursively due to
+	 *   the wrong RF EFLAG management
+	 *
+	 * - we never trigger the sig_handler breakpoint due
+	 *   to the rong RF EFLAG management
+	 *
+	 */
+
+	fd1 = bp_event(test_function, 1);
+	fd2 = bp_event(sig_handler, 0);
+
+	ioctl(fd1, PERF_EVENT_IOC_ENABLE, 0);
+	ioctl(fd2, PERF_EVENT_IOC_ENABLE, 0);
+
+	/*
+	 * Kick off the test by trigering 'fd1'
+	 * breakpoint.
+	 */
+	test_function();
+
+	ioctl(fd1, PERF_EVENT_IOC_DISABLE, 0);
+	ioctl(fd2, PERF_EVENT_IOC_DISABLE, 0);
+
+	count1 = bp_count(fd1);
+	count2 = bp_count(fd2);
+
+	close(fd1);
+	close(fd2);
+
+	pr_debug("count1 %lld, count2 %lld, overflow %d\n",
+		 count1, count2, overflows);
+
+	if (count1 != 1) {
+		if (count1 == 11)
+			pr_debug("failed: RF EFLAG recursion issue detected\n");
+		else
+			pr_debug("failed: wrong count for bp1%lld\n", count1);
+	}
+
+	if (overflows != 1)
+		pr_debug("failed: wrong overflow hit\n");
+
+	if (count2 != 1)
+		pr_debug("failed: wrong count for bp2\n");
+
+	return count1 == 1 && overflows == 1 && count2 == 1 ?
+		TEST_OK : TEST_FAIL;
+}
diff --git a/tools/perf/tests/bp_signal_overflow.c b/tools/perf/tests/bp_signal_overflow.c
new file mode 100644
index 000000000..e76537724
--- /dev/null
+++ b/tools/perf/tests/bp_signal_overflow.c
@@ -0,0 +1,134 @@
+/*
+ * Originally done by Vince Weaver <vincent.weaver@maine.edu> for
+ * perf_event_tests (git://github.com/deater/perf_event_tests)
+ */
+
+/*
+ * 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 <unistd.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <time.h>
+#include <fcntl.h>
+#include <signal.h>
+#include <sys/mman.h>
+#include <linux/compiler.h>
+#include <linux/hw_breakpoint.h>
+
+#include "tests.h"
+#include "debug.h"
+#include "perf.h"
+#include "cloexec.h"
+
+static int overflows;
+
+__attribute__ ((noinline))
+static int test_function(void)
+{
+	return time(NULL);
+}
+
+static void sig_handler(int signum __maybe_unused,
+			siginfo_t *oh __maybe_unused,
+			void *uc __maybe_unused)
+{
+	overflows++;
+}
+
+static long long bp_count(int fd)
+{
+	long long count;
+	int ret;
+
+	ret = read(fd, &count, sizeof(long long));
+	if (ret != sizeof(long long)) {
+		pr_debug("failed to read: %d\n", ret);
+		return TEST_FAIL;
+	}
+
+	return count;
+}
+
+#define EXECUTIONS 10000
+#define THRESHOLD  100
+
+int test__bp_signal_overflow(void)
+{
+	struct perf_event_attr pe;
+	struct sigaction sa;
+	long long count;
+	int fd, i, fails = 0;
+
+	/* setup SIGIO signal handler */
+	memset(&sa, 0, sizeof(struct sigaction));
+	sa.sa_sigaction = (void *) sig_handler;
+	sa.sa_flags = SA_SIGINFO;
+
+	if (sigaction(SIGIO, &sa, NULL) < 0) {
+		pr_debug("failed setting up signal handler\n");
+		return TEST_FAIL;
+	}
+
+	memset(&pe, 0, sizeof(struct perf_event_attr));
+	pe.type = PERF_TYPE_BREAKPOINT;
+	pe.size = sizeof(struct perf_event_attr);
+
+	pe.config = 0;
+	pe.bp_type = HW_BREAKPOINT_X;
+	pe.bp_addr = (unsigned long) test_function;
+	pe.bp_len = sizeof(long);
+
+	pe.sample_period = THRESHOLD;
+	pe.sample_type = PERF_SAMPLE_IP;
+	pe.wakeup_events = 1;
+
+	pe.disabled = 1;
+	pe.exclude_kernel = 1;
+	pe.exclude_hv = 1;
+
+	fd = sys_perf_event_open(&pe, 0, -1, -1,
+				 perf_event_open_cloexec_flag());
+	if (fd < 0) {
+		pr_debug("failed opening event %llx\n", pe.config);
+		return TEST_FAIL;
+	}
+
+	fcntl(fd, F_SETFL, O_RDWR|O_NONBLOCK|O_ASYNC);
+	fcntl(fd, F_SETSIG, SIGIO);
+	fcntl(fd, F_SETOWN, getpid());
+
+	ioctl(fd, PERF_EVENT_IOC_RESET, 0);
+	ioctl(fd, PERF_EVENT_IOC_ENABLE, 0);
+
+	for (i = 0; i < EXECUTIONS; i++)
+		test_function();
+
+	ioctl(fd, PERF_EVENT_IOC_DISABLE, 0);
+
+	count = bp_count(fd);
+
+	close(fd);
+
+	pr_debug("count %lld, overflow %d\n",
+		 count, overflows);
+
+	if (count != EXECUTIONS) {
+		pr_debug("\tWrong number of executions %lld != %d\n",
+		count, EXECUTIONS);
+		fails++;
+	}
+
+	if (overflows != EXECUTIONS / THRESHOLD) {
+		pr_debug("\tWrong number of overflows %d != %d\n",
+		overflows, EXECUTIONS / THRESHOLD);
+		fails++;
+	}
+
+	return fails ? TEST_FAIL : TEST_OK;
+}
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
new file mode 100644
index 000000000..4f4098167
--- /dev/null
+++ b/tools/perf/tests/builtin-test.c
@@ -0,0 +1,331 @@
+/*
+ * builtin-test.c
+ *
+ * Builtin regression testing command: ever growing number of sanity tests
+ */
+#include <unistd.h>
+#include <string.h>
+#include "builtin.h"
+#include "hist.h"
+#include "intlist.h"
+#include "tests.h"
+#include "debug.h"
+#include "color.h"
+#include "parse-options.h"
+#include "symbol.h"
+
+static struct test {
+	const char *desc;
+	int (*func)(void);
+} tests[] = {
+	{
+		.desc = "vmlinux symtab matches kallsyms",
+		.func = test__vmlinux_matches_kallsyms,
+	},
+	{
+		.desc = "detect open syscall event",
+		.func = test__open_syscall_event,
+	},
+	{
+		.desc = "detect open syscall event on all cpus",
+		.func = test__open_syscall_event_on_all_cpus,
+	},
+	{
+		.desc = "read samples using the mmap interface",
+		.func = test__basic_mmap,
+	},
+	{
+		.desc = "parse events tests",
+		.func = test__parse_events,
+	},
+#if defined(__x86_64__) || defined(__i386__)
+	{
+		.desc = "x86 rdpmc test",
+		.func = test__rdpmc,
+	},
+#endif
+	{
+		.desc = "Validate PERF_RECORD_* events & perf_sample fields",
+		.func = test__PERF_RECORD,
+	},
+	{
+		.desc = "Test perf pmu format parsing",
+		.func = test__pmu,
+	},
+	{
+		.desc = "Test dso data read",
+		.func = test__dso_data,
+	},
+	{
+		.desc = "Test dso data cache",
+		.func = test__dso_data_cache,
+	},
+	{
+		.desc = "Test dso data reopen",
+		.func = test__dso_data_reopen,
+	},
+	{
+		.desc = "roundtrip evsel->name check",
+		.func = test__perf_evsel__roundtrip_name_test,
+	},
+	{
+		.desc = "Check parsing of sched tracepoints fields",
+		.func = test__perf_evsel__tp_sched_test,
+	},
+	{
+		.desc = "Generate and check syscalls:sys_enter_open event fields",
+		.func = test__syscall_open_tp_fields,
+	},
+	{
+		.desc = "struct perf_event_attr setup",
+		.func = test__attr,
+	},
+	{
+		.desc = "Test matching and linking multiple hists",
+		.func = test__hists_link,
+	},
+	{
+		.desc = "Try 'import perf' in python, checking link problems",
+		.func = test__python_use,
+	},
+	{
+		.desc = "Test breakpoint overflow signal handler",
+		.func = test__bp_signal,
+	},
+	{
+		.desc = "Test breakpoint overflow sampling",
+		.func = test__bp_signal_overflow,
+	},
+	{
+		.desc = "Test number of exit event of a simple workload",
+		.func = test__task_exit,
+	},
+	{
+		.desc = "Test software clock events have valid period values",
+		.func = test__sw_clock_freq,
+	},
+#if defined(__x86_64__) || defined(__i386__)
+	{
+		.desc = "Test converting perf time to TSC",
+		.func = test__perf_time_to_tsc,
+	},
+#endif
+	{
+		.desc = "Test object code reading",
+		.func = test__code_reading,
+	},
+	{
+		.desc = "Test sample parsing",
+		.func = test__sample_parsing,
+	},
+	{
+		.desc = "Test using a dummy software event to keep tracking",
+		.func = test__keep_tracking,
+	},
+	{
+		.desc = "Test parsing with no sample_id_all bit set",
+		.func = test__parse_no_sample_id_all,
+	},
+#if defined(__x86_64__) || defined(__i386__) || defined(__arm__)
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
+	{
+		.desc = "Test dwarf unwind",
+		.func = test__dwarf_unwind,
+	},
+#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,
+	},
+	{
+		.desc = "Test cumulation of child hist entries",
+		.func = test__hists_cumulate,
+	},
+	{
+		.desc = "Test tracking with sched_switch",
+		.func = test__switch_tracking,
+	},
+	{
+		.desc = "Filter fds with revents mask in a fdarray",
+		.func = test__fdarray__filter,
+	},
+	{
+		.desc = "Add fd to a fdarray, making it autogrow",
+		.func = test__fdarray__add,
+	},
+	{
+		.desc = "Test kmod_path__parse function",
+		.func = test__kmod_path__parse,
+	},
+	{
+		.func = NULL,
+	},
+};
+
+static bool perf_test__matches(int curr, int argc, const char *argv[])
+{
+	int i;
+
+	if (argc == 0)
+		return true;
+
+	for (i = 0; i < argc; ++i) {
+		char *end;
+		long nr = strtoul(argv[i], &end, 10);
+
+		if (*end == '\0') {
+			if (nr == curr + 1)
+				return true;
+			continue;
+		}
+
+		if (strstr(tests[curr].desc, argv[i]))
+			return true;
+	}
+
+	return false;
+}
+
+static int run_test(struct test *test)
+{
+	int status, err = -1, child = fork();
+	char sbuf[STRERR_BUFSIZE];
+
+	if (child < 0) {
+		pr_err("failed to fork test: %s\n",
+			strerror_r(errno, sbuf, sizeof(sbuf)));
+		return -1;
+	}
+
+	if (!child) {
+		pr_debug("test child forked, pid %d\n", getpid());
+		err = test->func();
+		exit(err);
+	}
+
+	wait(&status);
+
+	if (WIFEXITED(status)) {
+		err = WEXITSTATUS(status);
+		pr_debug("test child finished with %d\n", err);
+	} else if (WIFSIGNALED(status)) {
+		err = -1;
+		pr_debug("test child interrupted\n");
+	}
+
+	return err;
+}
+
+static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist)
+{
+	int i = 0;
+	int width = 0;
+
+	while (tests[i].func) {
+		int len = strlen(tests[i].desc);
+
+		if (width < len)
+			width = len;
+		++i;
+	}
+
+	i = 0;
+	while (tests[i].func) {
+		int curr = i++, err;
+
+		if (!perf_test__matches(curr, argc, argv))
+			continue;
+
+		pr_info("%2d: %-*s:", i, width, tests[curr].desc);
+
+		if (intlist__find(skiplist, i)) {
+			color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip (user override)\n");
+			continue;
+		}
+
+		pr_debug("\n--- start ---\n");
+		err = run_test(&tests[curr]);
+		pr_debug("---- end ----\n%s:", tests[curr].desc);
+
+		switch (err) {
+		case TEST_OK:
+			pr_info(" Ok\n");
+			break;
+		case TEST_SKIP:
+			color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip\n");
+			break;
+		case TEST_FAIL:
+		default:
+			color_fprintf(stderr, PERF_COLOR_RED, " FAILED!\n");
+			break;
+		}
+	}
+
+	return 0;
+}
+
+static int perf_test__list(int argc, const char **argv)
+{
+	int i = 0;
+
+	while (tests[i].func) {
+		int curr = i++;
+
+		if (argc > 1 && !strstr(tests[curr].desc, argv[1]))
+			continue;
+
+		pr_info("%2d: %s\n", i, tests[curr].desc);
+	}
+
+	return 0;
+}
+
+int cmd_test(int argc, const char **argv, const char *prefix __maybe_unused)
+{
+	const char *test_usage[] = {
+	"perf test [<options>] [{list <test-name-fragment>|[<test-name-fragments>|<test-numbers>]}]",
+	NULL,
+	};
+	const char *skip = NULL;
+	const struct option test_options[] = {
+	OPT_STRING('s', "skip", &skip, "tests", "tests to skip"),
+	OPT_INCR('v', "verbose", &verbose,
+		    "be more verbose (show symbol address, etc)"),
+	OPT_END()
+	};
+	const char * const test_subcommands[] = { "list", NULL };
+	struct intlist *skiplist = NULL;
+        int ret = hists__init();
+
+        if (ret < 0)
+                return ret;
+
+	argc = parse_options_subcommand(argc, argv, test_options, test_subcommands, test_usage, 0);
+	if (argc >= 1 && !strcmp(argv[0], "list"))
+		return perf_test__list(argc, argv);
+
+	symbol_conf.priv_size = sizeof(int);
+	symbol_conf.sort_by_name = true;
+	symbol_conf.try_vmlinux_path = true;
+
+	if (symbol__init(NULL) < 0)
+		return -1;
+
+	if (skip != NULL)
+		skiplist = intlist__new(skip);
+
+	return __cmd_test(argc, argv, skiplist);
+}
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
new file mode 100644
index 000000000..f671ec37a
--- /dev/null
+++ b/tools/perf/tests/code-reading.c
@@ -0,0 +1,578 @@
+#include <linux/types.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <ctype.h>
+#include <string.h>
+
+#include "parse-events.h"
+#include "evlist.h"
+#include "evsel.h"
+#include "thread_map.h"
+#include "cpumap.h"
+#include "machine.h"
+#include "event.h"
+#include "thread.h"
+
+#include "tests.h"
+
+#define BUFSZ	1024
+#define READLEN	128
+
+struct state {
+	u64 done[1024];
+	size_t done_cnt;
+};
+
+static unsigned int hex(char c)
+{
+	if (c >= '0' && c <= '9')
+		return c - '0';
+	if (c >= 'a' && c <= 'f')
+		return c - 'a' + 10;
+	return c - 'A' + 10;
+}
+
+static void read_objdump_line(const char *line, size_t line_len, void **buf,
+			      size_t *len)
+{
+	const char *p;
+	size_t i;
+
+	/* Skip to a colon */
+	p = strchr(line, ':');
+	if (!p)
+		return;
+	i = p + 1 - line;
+
+	/* Read bytes */
+	while (*len) {
+		char c1, c2;
+
+		/* Skip spaces */
+		for (; i < line_len; i++) {
+			if (!isspace(line[i]))
+				break;
+		}
+		/* Get 2 hex digits */
+		if (i >= line_len || !isxdigit(line[i]))
+			break;
+		c1 = line[i++];
+		if (i >= line_len || !isxdigit(line[i]))
+			break;
+		c2 = line[i++];
+		/* Followed by a space */
+		if (i < line_len && line[i] && !isspace(line[i]))
+			break;
+		/* Store byte */
+		*(unsigned char *)*buf = (hex(c1) << 4) | hex(c2);
+		*buf += 1;
+		*len -= 1;
+	}
+}
+
+static int read_objdump_output(FILE *f, void **buf, size_t *len)
+{
+	char *line = NULL;
+	size_t line_len;
+	ssize_t ret;
+	int err = 0;
+
+	while (1) {
+		ret = getline(&line, &line_len, f);
+		if (feof(f))
+			break;
+		if (ret < 0) {
+			pr_debug("getline failed\n");
+			err = -1;
+			break;
+		}
+		read_objdump_line(line, ret, buf, len);
+	}
+
+	free(line);
+
+	return err;
+}
+
+static int read_via_objdump(const char *filename, u64 addr, void *buf,
+			    size_t len)
+{
+	char cmd[PATH_MAX * 2];
+	const char *fmt;
+	FILE *f;
+	int ret;
+
+	fmt = "%s -d --start-address=0x%"PRIx64" --stop-address=0x%"PRIx64" %s";
+	ret = snprintf(cmd, sizeof(cmd), fmt, "objdump", addr, addr + len,
+		       filename);
+	if (ret <= 0 || (size_t)ret >= sizeof(cmd))
+		return -1;
+
+	pr_debug("Objdump command is: %s\n", cmd);
+
+	/* Ignore objdump errors */
+	strcat(cmd, " 2>/dev/null");
+
+	f = popen(cmd, "r");
+	if (!f) {
+		pr_debug("popen failed\n");
+		return -1;
+	}
+
+	ret = read_objdump_output(f, &buf, &len);
+	if (len) {
+		pr_debug("objdump read too few bytes\n");
+		if (!ret)
+			ret = len;
+	}
+
+	pclose(f);
+
+	return ret;
+}
+
+static int read_object_code(u64 addr, size_t len, u8 cpumode,
+			    struct thread *thread, struct state *state)
+{
+	struct addr_location al;
+	unsigned char buf1[BUFSZ];
+	unsigned char buf2[BUFSZ];
+	size_t ret_len;
+	u64 objdump_addr;
+	int ret;
+
+	pr_debug("Reading object code for memory address: %#"PRIx64"\n", addr);
+
+	thread__find_addr_map(thread, cpumode, MAP__FUNCTION, addr, &al);
+	if (!al.map || !al.map->dso) {
+		pr_debug("thread__find_addr_map failed\n");
+		return -1;
+	}
+
+	pr_debug("File is: %s\n", al.map->dso->long_name);
+
+	if (al.map->dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS &&
+	    !dso__is_kcore(al.map->dso)) {
+		pr_debug("Unexpected kernel address - skipping\n");
+		return 0;
+	}
+
+	pr_debug("On file address is: %#"PRIx64"\n", al.addr);
+
+	if (len > BUFSZ)
+		len = BUFSZ;
+
+	/* Do not go off the map */
+	if (addr + len > al.map->end)
+		len = al.map->end - addr;
+
+	/* Read the object code using perf */
+	ret_len = dso__data_read_offset(al.map->dso, thread->mg->machine,
+					al.addr, buf1, len);
+	if (ret_len != len) {
+		pr_debug("dso__data_read_offset failed\n");
+		return -1;
+	}
+
+	/*
+	 * Converting addresses for use by objdump requires more information.
+	 * map__load() does that.  See map__rip_2objdump() for details.
+	 */
+	if (map__load(al.map, NULL))
+		return -1;
+
+	/* objdump struggles with kcore - try each map only once */
+	if (dso__is_kcore(al.map->dso)) {
+		size_t d;
+
+		for (d = 0; d < state->done_cnt; d++) {
+			if (state->done[d] == al.map->start) {
+				pr_debug("kcore map tested already");
+				pr_debug(" - skipping\n");
+				return 0;
+			}
+		}
+		if (state->done_cnt >= ARRAY_SIZE(state->done)) {
+			pr_debug("Too many kcore maps - skipping\n");
+			return 0;
+		}
+		state->done[state->done_cnt++] = al.map->start;
+	}
+
+	/* Read the object code using objdump */
+	objdump_addr = map__rip_2objdump(al.map, al.addr);
+	ret = read_via_objdump(al.map->dso->long_name, objdump_addr, buf2, len);
+	if (ret > 0) {
+		/*
+		 * The kernel maps are inaccurate - assume objdump is right in
+		 * that case.
+		 */
+		if (cpumode == PERF_RECORD_MISC_KERNEL ||
+		    cpumode == PERF_RECORD_MISC_GUEST_KERNEL) {
+			len -= ret;
+			if (len) {
+				pr_debug("Reducing len to %zu\n", len);
+			} else if (dso__is_kcore(al.map->dso)) {
+				/*
+				 * objdump cannot handle very large segments
+				 * that may be found in kcore.
+				 */
+				pr_debug("objdump failed for kcore");
+				pr_debug(" - skipping\n");
+				return 0;
+			} else {
+				return -1;
+			}
+		}
+	}
+	if (ret < 0) {
+		pr_debug("read_via_objdump failed\n");
+		return -1;
+	}
+
+	/* The results should be identical */
+	if (memcmp(buf1, buf2, len)) {
+		pr_debug("Bytes read differ from those read by objdump\n");
+		return -1;
+	}
+	pr_debug("Bytes read match those read by objdump\n");
+
+	return 0;
+}
+
+static int process_sample_event(struct machine *machine,
+				struct perf_evlist *evlist,
+				union perf_event *event, struct state *state)
+{
+	struct perf_sample sample;
+	struct thread *thread;
+	u8 cpumode;
+
+	if (perf_evlist__parse_sample(evlist, event, &sample)) {
+		pr_debug("perf_evlist__parse_sample failed\n");
+		return -1;
+	}
+
+	thread = machine__findnew_thread(machine, sample.pid, sample.tid);
+	if (!thread) {
+		pr_debug("machine__findnew_thread failed\n");
+		return -1;
+	}
+
+	cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+
+	return read_object_code(sample.ip, READLEN, cpumode, thread, state);
+}
+
+static int process_event(struct machine *machine, struct perf_evlist *evlist,
+			 union perf_event *event, struct state *state)
+{
+	if (event->header.type == PERF_RECORD_SAMPLE)
+		return process_sample_event(machine, evlist, event, state);
+
+	if (event->header.type == PERF_RECORD_THROTTLE ||
+	    event->header.type == PERF_RECORD_UNTHROTTLE)
+		return 0;
+
+	if (event->header.type < PERF_RECORD_MAX) {
+		int ret;
+
+		ret = machine__process_event(machine, event, NULL);
+		if (ret < 0)
+			pr_debug("machine__process_event failed, event type %u\n",
+				 event->header.type);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int process_events(struct machine *machine, struct perf_evlist *evlist,
+			  struct state *state)
+{
+	union perf_event *event;
+	int i, ret;
+
+	for (i = 0; i < evlist->nr_mmaps; i++) {
+		while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
+			ret = process_event(machine, evlist, event, state);
+			perf_evlist__mmap_consume(evlist, i);
+			if (ret < 0)
+				return ret;
+		}
+	}
+	return 0;
+}
+
+static int comp(const void *a, const void *b)
+{
+	return *(int *)a - *(int *)b;
+}
+
+static void do_sort_something(void)
+{
+	int buf[40960], i;
+
+	for (i = 0; i < (int)ARRAY_SIZE(buf); i++)
+		buf[i] = ARRAY_SIZE(buf) - i - 1;
+
+	qsort(buf, ARRAY_SIZE(buf), sizeof(int), comp);
+
+	for (i = 0; i < (int)ARRAY_SIZE(buf); i++) {
+		if (buf[i] != i) {
+			pr_debug("qsort failed\n");
+			break;
+		}
+	}
+}
+
+static void sort_something(void)
+{
+	int i;
+
+	for (i = 0; i < 10; i++)
+		do_sort_something();
+}
+
+static void syscall_something(void)
+{
+	int pipefd[2];
+	int i;
+
+	for (i = 0; i < 1000; i++) {
+		if (pipe(pipefd) < 0) {
+			pr_debug("pipe failed\n");
+			break;
+		}
+		close(pipefd[1]);
+		close(pipefd[0]);
+	}
+}
+
+static void fs_something(void)
+{
+	const char *test_file_name = "temp-perf-code-reading-test-file--";
+	FILE *f;
+	int i;
+
+	for (i = 0; i < 1000; i++) {
+		f = fopen(test_file_name, "w+");
+		if (f) {
+			fclose(f);
+			unlink(test_file_name);
+		}
+	}
+}
+
+static void do_something(void)
+{
+	fs_something();
+
+	sort_something();
+
+	syscall_something();
+}
+
+enum {
+	TEST_CODE_READING_OK,
+	TEST_CODE_READING_NO_VMLINUX,
+	TEST_CODE_READING_NO_KCORE,
+	TEST_CODE_READING_NO_ACCESS,
+	TEST_CODE_READING_NO_KERNEL_OBJ,
+};
+
+static int do_test_code_reading(bool try_kcore)
+{
+	struct machines machines;
+	struct machine *machine;
+	struct thread *thread;
+	struct record_opts opts = {
+		.mmap_pages	     = UINT_MAX,
+		.user_freq	     = UINT_MAX,
+		.user_interval	     = ULLONG_MAX,
+		.freq		     = 4000,
+		.target		     = {
+			.uses_mmap   = true,
+		},
+	};
+	struct state state = {
+		.done_cnt = 0,
+	};
+	struct thread_map *threads = NULL;
+	struct cpu_map *cpus = NULL;
+	struct perf_evlist *evlist = NULL;
+	struct perf_evsel *evsel = NULL;
+	int err = -1, ret;
+	pid_t pid;
+	struct map *map;
+	bool have_vmlinux, have_kcore, excl_kernel = false;
+
+	pid = getpid();
+
+	machines__init(&machines);
+	machine = &machines.host;
+
+	ret = machine__create_kernel_maps(machine);
+	if (ret < 0) {
+		pr_debug("machine__create_kernel_maps failed\n");
+		goto out_err;
+	}
+
+	/* Force the use of kallsyms instead of vmlinux to try kcore */
+	if (try_kcore)
+		symbol_conf.kallsyms_name = "/proc/kallsyms";
+
+	/* Load kernel map */
+	map = machine->vmlinux_maps[MAP__FUNCTION];
+	ret = map__load(map, NULL);
+	if (ret < 0) {
+		pr_debug("map__load failed\n");
+		goto out_err;
+	}
+	have_vmlinux = dso__is_vmlinux(map->dso);
+	have_kcore = dso__is_kcore(map->dso);
+
+	/* 2nd time through we just try kcore */
+	if (try_kcore && !have_kcore)
+		return TEST_CODE_READING_NO_KCORE;
+
+	/* No point getting kernel events if there is no kernel object */
+	if (!have_vmlinux && !have_kcore)
+		excl_kernel = true;
+
+	threads = thread_map__new_by_tid(pid);
+	if (!threads) {
+		pr_debug("thread_map__new_by_tid failed\n");
+		goto out_err;
+	}
+
+	ret = perf_event__synthesize_thread_map(NULL, threads,
+						perf_event__process, machine, false);
+	if (ret < 0) {
+		pr_debug("perf_event__synthesize_thread_map failed\n");
+		goto out_err;
+	}
+
+	thread = machine__findnew_thread(machine, pid, pid);
+	if (!thread) {
+		pr_debug("machine__findnew_thread failed\n");
+		goto out_err;
+	}
+
+	cpus = cpu_map__new(NULL);
+	if (!cpus) {
+		pr_debug("cpu_map__new failed\n");
+		goto out_err;
+	}
+
+	while (1) {
+		const char *str;
+
+		evlist = perf_evlist__new();
+		if (!evlist) {
+			pr_debug("perf_evlist__new failed\n");
+			goto out_err;
+		}
+
+		perf_evlist__set_maps(evlist, cpus, threads);
+
+		if (excl_kernel)
+			str = "cycles:u";
+		else
+			str = "cycles";
+		pr_debug("Parsing event '%s'\n", str);
+		ret = parse_events(evlist, str);
+		if (ret < 0) {
+			pr_debug("parse_events failed\n");
+			goto out_err;
+		}
+
+		perf_evlist__config(evlist, &opts);
+
+		evsel = perf_evlist__first(evlist);
+
+		evsel->attr.comm = 1;
+		evsel->attr.disabled = 1;
+		evsel->attr.enable_on_exec = 0;
+
+		ret = perf_evlist__open(evlist);
+		if (ret < 0) {
+			if (!excl_kernel) {
+				excl_kernel = true;
+				perf_evlist__set_maps(evlist, NULL, NULL);
+				perf_evlist__delete(evlist);
+				evlist = NULL;
+				continue;
+			}
+			pr_debug("perf_evlist__open failed\n");
+			goto out_err;
+		}
+		break;
+	}
+
+	ret = perf_evlist__mmap(evlist, UINT_MAX, false);
+	if (ret < 0) {
+		pr_debug("perf_evlist__mmap failed\n");
+		goto out_err;
+	}
+
+	perf_evlist__enable(evlist);
+
+	do_something();
+
+	perf_evlist__disable(evlist);
+
+	ret = process_events(machine, evlist, &state);
+	if (ret < 0)
+		goto out_err;
+
+	if (!have_vmlinux && !have_kcore && !try_kcore)
+		err = TEST_CODE_READING_NO_KERNEL_OBJ;
+	else if (!have_vmlinux && !try_kcore)
+		err = TEST_CODE_READING_NO_VMLINUX;
+	else if (excl_kernel)
+		err = TEST_CODE_READING_NO_ACCESS;
+	else
+		err = TEST_CODE_READING_OK;
+out_err:
+	if (evlist) {
+		perf_evlist__delete(evlist);
+	} else {
+		cpu_map__delete(cpus);
+		thread_map__delete(threads);
+	}
+	machines__destroy_kernel_maps(&machines);
+	machine__delete_threads(machine);
+	machines__exit(&machines);
+
+	return err;
+}
+
+int test__code_reading(void)
+{
+	int ret;
+
+	ret = do_test_code_reading(false);
+	if (!ret)
+		ret = do_test_code_reading(true);
+
+	switch (ret) {
+	case TEST_CODE_READING_OK:
+		return 0;
+	case TEST_CODE_READING_NO_VMLINUX:
+		fprintf(stderr, " (no vmlinux)");
+		return 0;
+	case TEST_CODE_READING_NO_KCORE:
+		fprintf(stderr, " (no kcore)");
+		return 0;
+	case TEST_CODE_READING_NO_ACCESS:
+		fprintf(stderr, " (no access)");
+		return 0;
+	case TEST_CODE_READING_NO_KERNEL_OBJ:
+		fprintf(stderr, " (no kernel obj)");
+		return 0;
+	default:
+		return -1;
+	};
+}
diff --git a/tools/perf/tests/dso-data.c b/tools/perf/tests/dso-data.c
new file mode 100644
index 000000000..513e5febb
--- /dev/null
+++ b/tools/perf/tests/dso-data.c
@@ -0,0 +1,365 @@
+#include <stdlib.h>
+#include <linux/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <string.h>
+#include <sys/time.h>
+#include <sys/resource.h>
+#include <api/fs/fs.h>
+#include "util.h"
+#include "machine.h"
+#include "symbol.h"
+#include "tests.h"
+#include "debug.h"
+
+static char *test_file(int size)
+{
+#define TEMPL "/tmp/perf-test-XXXXXX"
+	static char buf_templ[sizeof(TEMPL)];
+	char *templ = buf_templ;
+	int fd, i;
+	unsigned char *buf;
+
+	strcpy(buf_templ, TEMPL);
+#undef TEMPL
+
+	fd = mkstemp(templ);
+	if (fd < 0) {
+		perror("mkstemp failed");
+		return NULL;
+	}
+
+	buf = malloc(size);
+	if (!buf) {
+		close(fd);
+		return NULL;
+	}
+
+	for (i = 0; i < size; i++)
+		buf[i] = (unsigned char) ((int) i % 10);
+
+	if (size != write(fd, buf, size))
+		templ = NULL;
+
+	free(buf);
+	close(fd);
+	return templ;
+}
+
+#define TEST_FILE_SIZE (DSO__DATA_CACHE_SIZE * 20)
+
+struct test_data_offset {
+	off_t offset;
+	u8 data[10];
+	int size;
+};
+
+struct test_data_offset offsets[] = {
+	/* Fill first cache page. */
+	{
+		.offset = 10,
+		.data   = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 },
+		.size   = 10,
+	},
+	/* Read first cache page. */
+	{
+		.offset = 10,
+		.data   = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 },
+		.size   = 10,
+	},
+	/* Fill cache boundary pages. */
+	{
+		.offset = DSO__DATA_CACHE_SIZE - DSO__DATA_CACHE_SIZE % 10,
+		.data   = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 },
+		.size   = 10,
+	},
+	/* Read cache boundary pages. */
+	{
+		.offset = DSO__DATA_CACHE_SIZE - DSO__DATA_CACHE_SIZE % 10,
+		.data   = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 },
+		.size   = 10,
+	},
+	/* Fill final cache page. */
+	{
+		.offset = TEST_FILE_SIZE - 10,
+		.data   = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 },
+		.size   = 10,
+	},
+	/* Read final cache page. */
+	{
+		.offset = TEST_FILE_SIZE - 10,
+		.data   = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 },
+		.size   = 10,
+	},
+	/* Read final cache page. */
+	{
+		.offset = TEST_FILE_SIZE - 3,
+		.data   = { 7, 8, 9, 0, 0, 0, 0, 0, 0, 0 },
+		.size   = 3,
+	},
+};
+
+int test__dso_data(void)
+{
+	struct machine machine;
+	struct dso *dso;
+	char *file = test_file(TEST_FILE_SIZE);
+	size_t i;
+
+	TEST_ASSERT_VAL("No test file", file);
+
+	memset(&machine, 0, sizeof(machine));
+
+	dso = dso__new((const char *)file);
+
+	TEST_ASSERT_VAL("Failed to access to dso",
+			dso__data_fd(dso, &machine) >= 0);
+
+	/* Basic 10 bytes tests. */
+	for (i = 0; i < ARRAY_SIZE(offsets); i++) {
+		struct test_data_offset *data = &offsets[i];
+		ssize_t size;
+		u8 buf[10];
+
+		memset(buf, 0, 10);
+		size = dso__data_read_offset(dso, &machine, data->offset,
+				     buf, 10);
+
+		TEST_ASSERT_VAL("Wrong size", size == data->size);
+		TEST_ASSERT_VAL("Wrong data", !memcmp(buf, data->data, 10));
+	}
+
+	/* Read cross multiple cache pages. */
+	{
+		ssize_t size;
+		int c;
+		u8 *buf;
+
+		buf = malloc(TEST_FILE_SIZE);
+		TEST_ASSERT_VAL("ENOMEM\n", buf);
+
+		/* First iteration to fill caches, second one to read them. */
+		for (c = 0; c < 2; c++) {
+			memset(buf, 0, TEST_FILE_SIZE);
+			size = dso__data_read_offset(dso, &machine, 10,
+						     buf, TEST_FILE_SIZE);
+
+			TEST_ASSERT_VAL("Wrong size",
+				size == (TEST_FILE_SIZE - 10));
+
+			for (i = 0; i < (size_t)size; i++)
+				TEST_ASSERT_VAL("Wrong data",
+					buf[i] == (i % 10));
+		}
+
+		free(buf);
+	}
+
+	dso__delete(dso);
+	unlink(file);
+	return 0;
+}
+
+static long open_files_cnt(void)
+{
+	char path[PATH_MAX];
+	struct dirent *dent;
+	DIR *dir;
+	long nr = 0;
+
+	scnprintf(path, PATH_MAX, "%s/self/fd", procfs__mountpoint());
+	pr_debug("fd path: %s\n", path);
+
+	dir = opendir(path);
+	TEST_ASSERT_VAL("failed to open fd directory", dir);
+
+	while ((dent = readdir(dir)) != NULL) {
+		if (!strcmp(dent->d_name, ".") ||
+		    !strcmp(dent->d_name, ".."))
+			continue;
+
+		nr++;
+	}
+
+	closedir(dir);
+	return nr - 1;
+}
+
+static struct dso **dsos;
+
+static int dsos__create(int cnt, int size)
+{
+	int i;
+
+	dsos = malloc(sizeof(dsos) * cnt);
+	TEST_ASSERT_VAL("failed to alloc dsos array", dsos);
+
+	for (i = 0; i < cnt; i++) {
+		char *file;
+
+		file = test_file(size);
+		TEST_ASSERT_VAL("failed to get dso file", file);
+
+		dsos[i] = dso__new(file);
+		TEST_ASSERT_VAL("failed to get dso", dsos[i]);
+	}
+
+	return 0;
+}
+
+static void dsos__delete(int cnt)
+{
+	int i;
+
+	for (i = 0; i < cnt; i++) {
+		struct dso *dso = dsos[i];
+
+		unlink(dso->name);
+		dso__delete(dso);
+	}
+
+	free(dsos);
+}
+
+static int set_fd_limit(int n)
+{
+	struct rlimit rlim;
+
+	if (getrlimit(RLIMIT_NOFILE, &rlim))
+		return -1;
+
+	pr_debug("file limit %ld, new %d\n", (long) rlim.rlim_cur, n);
+
+	rlim.rlim_cur = n;
+	return setrlimit(RLIMIT_NOFILE, &rlim);
+}
+
+int test__dso_data_cache(void)
+{
+	struct machine machine;
+	long nr_end, nr = open_files_cnt();
+	int dso_cnt, limit, i, fd;
+
+	memset(&machine, 0, sizeof(machine));
+
+	/* set as system limit */
+	limit = nr * 4;
+	TEST_ASSERT_VAL("failed to set file limit", !set_fd_limit(limit));
+
+	/* and this is now our dso open FDs limit */
+	dso_cnt = limit / 2;
+	TEST_ASSERT_VAL("failed to create dsos\n",
+		!dsos__create(dso_cnt, TEST_FILE_SIZE));
+
+	for (i = 0; i < (dso_cnt - 1); i++) {
+		struct dso *dso = dsos[i];
+
+		/*
+		 * Open dsos via dso__data_fd(), it opens the data
+		 * file and keep it open (unless open file limit).
+		 */
+		fd = dso__data_fd(dso, &machine);
+		TEST_ASSERT_VAL("failed to get fd", fd > 0);
+
+		if (i % 2) {
+			#define BUFSIZE 10
+			u8 buf[BUFSIZE];
+			ssize_t n;
+
+			n = dso__data_read_offset(dso, &machine, 0, buf, BUFSIZE);
+			TEST_ASSERT_VAL("failed to read dso", n == BUFSIZE);
+		}
+	}
+
+	/* verify the first one is already open */
+	TEST_ASSERT_VAL("dsos[0] is not open", dsos[0]->data.fd != -1);
+
+	/* open +1 dso to reach the allowed limit */
+	fd = dso__data_fd(dsos[i], &machine);
+	TEST_ASSERT_VAL("failed to get fd", fd > 0);
+
+	/* should force the first one to be closed */
+	TEST_ASSERT_VAL("failed to close dsos[0]", dsos[0]->data.fd == -1);
+
+	/* cleanup everything */
+	dsos__delete(dso_cnt);
+
+	/* Make sure we did not leak any file descriptor. */
+	nr_end = open_files_cnt();
+	pr_debug("nr start %ld, nr stop %ld\n", nr, nr_end);
+	TEST_ASSERT_VAL("failed leadking files", nr == nr_end);
+	return 0;
+}
+
+int test__dso_data_reopen(void)
+{
+	struct machine machine;
+	long nr_end, nr = open_files_cnt();
+	int fd, fd_extra;
+
+#define dso_0 (dsos[0])
+#define dso_1 (dsos[1])
+#define dso_2 (dsos[2])
+
+	memset(&machine, 0, sizeof(machine));
+
+	/*
+	 * Test scenario:
+	 * - create 3 dso objects
+	 * - set process file descriptor limit to current
+	 *   files count + 3
+	 * - test that the first dso gets closed when we
+	 *   reach the files count limit
+	 */
+
+	/* Make sure we are able to open 3 fds anyway */
+	TEST_ASSERT_VAL("failed to set file limit",
+			!set_fd_limit((nr + 3)));
+
+	TEST_ASSERT_VAL("failed to create dsos\n", !dsos__create(3, TEST_FILE_SIZE));
+
+	/* open dso_0 */
+	fd = dso__data_fd(dso_0, &machine);
+	TEST_ASSERT_VAL("failed to get fd", fd > 0);
+
+	/* open dso_1 */
+	fd = dso__data_fd(dso_1, &machine);
+	TEST_ASSERT_VAL("failed to get fd", fd > 0);
+
+	/*
+	 * open extra file descriptor and we just
+	 * reached the files count limit
+	 */
+	fd_extra = open("/dev/null", O_RDONLY);
+	TEST_ASSERT_VAL("failed to open extra fd", fd_extra > 0);
+
+	/* open dso_2 */
+	fd = dso__data_fd(dso_2, &machine);
+	TEST_ASSERT_VAL("failed to get fd", fd > 0);
+
+	/*
+	 * dso_0 should get closed, because we reached
+	 * the file descriptor limit
+	 */
+	TEST_ASSERT_VAL("failed to close dso_0", dso_0->data.fd == -1);
+
+	/* open dso_0 */
+	fd = dso__data_fd(dso_0, &machine);
+	TEST_ASSERT_VAL("failed to get fd", fd > 0);
+
+	/*
+	 * dso_1 should get closed, because we reached
+	 * the file descriptor limit
+	 */
+	TEST_ASSERT_VAL("failed to close dso_1", dso_1->data.fd == -1);
+
+	/* cleanup everything */
+	close(fd_extra);
+	dsos__delete(3);
+
+	/* Make sure we did not leak any file descriptor. */
+	nr_end = open_files_cnt();
+	pr_debug("nr start %ld, nr stop %ld\n", nr, nr_end);
+	TEST_ASSERT_VAL("failed leadking files", nr == nr_end);
+	return 0;
+}
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
new file mode 100644
index 000000000..0bf06bec6
--- /dev/null
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -0,0 +1,179 @@
+#include <linux/compiler.h>
+#include <linux/types.h>
+#include <unistd.h>
+#include "tests.h"
+#include "debug.h"
+#include "machine.h"
+#include "event.h"
+#include "unwind.h"
+#include "perf_regs.h"
+#include "map.h"
+#include "thread.h"
+#include "callchain.h"
+
+/* For bsearch. We try to unwind functions in shared object. */
+#include <stdlib.h>
+
+static int mmap_handler(struct perf_tool *tool __maybe_unused,
+			union perf_event *event,
+			struct perf_sample *sample __maybe_unused,
+			struct machine *machine)
+{
+	return machine__process_mmap2_event(machine, event, NULL);
+}
+
+static int init_live_machine(struct machine *machine)
+{
+	union perf_event event;
+	pid_t pid = getpid();
+
+	return perf_event__synthesize_mmap_events(NULL, &event, pid, pid,
+						  mmap_handler, machine, true);
+}
+
+#define MAX_STACK 8
+
+static int unwind_entry(struct unwind_entry *entry, void *arg)
+{
+	unsigned long *cnt = (unsigned long *) arg;
+	char *symbol = entry->sym ? entry->sym->name : NULL;
+	static const char *funcs[MAX_STACK] = {
+		"test__arch_unwind_sample",
+		"unwind_thread",
+		"compare",
+		"bsearch",
+		"krava_3",
+		"krava_2",
+		"krava_1",
+		"test__dwarf_unwind"
+	};
+
+	if (*cnt >= MAX_STACK) {
+		pr_debug("failed: crossed the max stack value %d\n", MAX_STACK);
+		return -1;
+	}
+
+	if (!symbol) {
+		pr_debug("failed: got unresolved address 0x%" PRIx64 "\n",
+			 entry->ip);
+		return -1;
+	}
+
+	pr_debug("got: %s 0x%" PRIx64 "\n", symbol, entry->ip);
+	return strcmp((const char *) symbol, funcs[(*cnt)++]);
+}
+
+__attribute__ ((noinline))
+static int unwind_thread(struct thread *thread)
+{
+	struct perf_sample sample;
+	unsigned long cnt = 0;
+	int err = -1;
+
+	memset(&sample, 0, sizeof(sample));
+
+	if (test__arch_unwind_sample(&sample, thread)) {
+		pr_debug("failed to get unwind sample\n");
+		goto out;
+	}
+
+	err = unwind__get_entries(unwind_entry, &cnt, thread,
+				  &sample, MAX_STACK);
+	if (err)
+		pr_debug("unwind failed\n");
+	else if (cnt != MAX_STACK) {
+		pr_debug("got wrong number of stack entries %lu != %d\n",
+			 cnt, MAX_STACK);
+		err = -1;
+	}
+
+ out:
+	free(sample.user_stack.data);
+	free(sample.user_regs.regs);
+	return err;
+}
+
+static int global_unwind_retval = -INT_MAX;
+
+__attribute__ ((noinline))
+static int compare(void *p1, void *p2)
+{
+	/* Any possible value should be 'thread' */
+	struct thread *thread = *(struct thread **)p1;
+
+	if (global_unwind_retval == -INT_MAX)
+		global_unwind_retval = unwind_thread(thread);
+
+	return p1 - p2;
+}
+
+__attribute__ ((noinline))
+static int krava_3(struct thread *thread)
+{
+	struct thread *array[2] = {thread, thread};
+	void *fp = &bsearch;
+	/*
+	 * make _bsearch a volatile function pointer to
+	 * prevent potential optimization, which may expand
+	 * bsearch and call compare directly from this function,
+	 * instead of libc shared object.
+	 */
+	void *(*volatile _bsearch)(void *, void *, size_t,
+			size_t, int (*)(void *, void *));
+
+	_bsearch = fp;
+	_bsearch(array, &thread, 2, sizeof(struct thread **), compare);
+	return global_unwind_retval;
+}
+
+__attribute__ ((noinline))
+static int krava_2(struct thread *thread)
+{
+	return krava_3(thread);
+}
+
+__attribute__ ((noinline))
+static int krava_1(struct thread *thread)
+{
+	return krava_2(thread);
+}
+
+int test__dwarf_unwind(void)
+{
+	struct machines machines;
+	struct machine *machine;
+	struct thread *thread;
+	int err = -1;
+
+	machines__init(&machines);
+
+	machine = machines__find(&machines, HOST_KERNEL_ID);
+	if (!machine) {
+		pr_err("Could not get machine\n");
+		return -1;
+	}
+
+	callchain_param.record_mode = CALLCHAIN_DWARF;
+
+	if (init_live_machine(machine)) {
+		pr_err("Could not init machine\n");
+		goto out;
+	}
+
+	if (verbose > 1)
+		machine__fprintf(machine, stderr);
+
+	thread = machine__find_thread(machine, getpid(), getpid());
+	if (!thread) {
+		pr_err("Could not get thread\n");
+		goto out;
+	}
+
+	err = krava_1(thread);
+
+ out:
+	machine__delete_threads(machine);
+	machine__exit(machine);
+	machines__exit(&machines);
+	return err;
+}
diff --git a/tools/perf/tests/evsel-roundtrip-name.c b/tools/perf/tests/evsel-roundtrip-name.c
new file mode 100644
index 000000000..b8d8341b3
--- /dev/null
+++ b/tools/perf/tests/evsel-roundtrip-name.c
@@ -0,0 +1,115 @@
+#include "evlist.h"
+#include "evsel.h"
+#include "parse-events.h"
+#include "tests.h"
+#include "debug.h"
+
+static int perf_evsel__roundtrip_cache_name_test(void)
+{
+	char name[128];
+	int type, op, err = 0, ret = 0, i, idx;
+	struct perf_evsel *evsel;
+	struct perf_evlist *evlist = perf_evlist__new();
+
+        if (evlist == NULL)
+                return -ENOMEM;
+
+	for (type = 0; type < PERF_COUNT_HW_CACHE_MAX; type++) {
+		for (op = 0; op < PERF_COUNT_HW_CACHE_OP_MAX; op++) {
+			/* skip invalid cache type */
+			if (!perf_evsel__is_cache_op_valid(type, op))
+				continue;
+
+			for (i = 0; i < PERF_COUNT_HW_CACHE_RESULT_MAX; i++) {
+				__perf_evsel__hw_cache_type_op_res_name(type, op, i,
+									name, sizeof(name));
+				err = parse_events(evlist, name);
+				if (err)
+					ret = err;
+			}
+		}
+	}
+
+	idx = 0;
+	evsel = perf_evlist__first(evlist);
+
+	for (type = 0; type < PERF_COUNT_HW_CACHE_MAX; type++) {
+		for (op = 0; op < PERF_COUNT_HW_CACHE_OP_MAX; op++) {
+			/* skip invalid cache type */
+			if (!perf_evsel__is_cache_op_valid(type, op))
+				continue;
+
+			for (i = 0; i < PERF_COUNT_HW_CACHE_RESULT_MAX; i++) {
+				__perf_evsel__hw_cache_type_op_res_name(type, op, i,
+									name, sizeof(name));
+				if (evsel->idx != idx)
+					continue;
+
+				++idx;
+
+				if (strcmp(perf_evsel__name(evsel), name)) {
+					pr_debug("%s != %s\n", perf_evsel__name(evsel), name);
+					ret = -1;
+				}
+
+				evsel = perf_evsel__next(evsel);
+			}
+		}
+	}
+
+	perf_evlist__delete(evlist);
+	return ret;
+}
+
+static int __perf_evsel__name_array_test(const char *names[], int nr_names)
+{
+	int i, err;
+	struct perf_evsel *evsel;
+	struct perf_evlist *evlist = perf_evlist__new();
+
+        if (evlist == NULL)
+                return -ENOMEM;
+
+	for (i = 0; i < nr_names; ++i) {
+		err = parse_events(evlist, names[i]);
+		if (err) {
+			pr_debug("failed to parse event '%s', err %d\n",
+				 names[i], err);
+			goto out_delete_evlist;
+		}
+	}
+
+	err = 0;
+	evlist__for_each(evlist, evsel) {
+		if (strcmp(perf_evsel__name(evsel), names[evsel->idx])) {
+			--err;
+			pr_debug("%s != %s\n", perf_evsel__name(evsel), names[evsel->idx]);
+		}
+	}
+
+out_delete_evlist:
+	perf_evlist__delete(evlist);
+	return err;
+}
+
+#define perf_evsel__name_array_test(names) \
+	__perf_evsel__name_array_test(names, ARRAY_SIZE(names))
+
+int test__perf_evsel__roundtrip_name_test(void)
+{
+	int err = 0, ret = 0;
+
+	err = perf_evsel__name_array_test(perf_evsel__hw_names);
+	if (err)
+		ret = err;
+
+	err = perf_evsel__name_array_test(perf_evsel__sw_names);
+	if (err)
+		ret = err;
+
+	err = perf_evsel__roundtrip_cache_name_test();
+	if (err)
+		ret = err;
+
+	return ret;
+}
diff --git a/tools/perf/tests/evsel-tp-sched.c b/tools/perf/tests/evsel-tp-sched.c
new file mode 100644
index 000000000..52162425c
--- /dev/null
+++ b/tools/perf/tests/evsel-tp-sched.c
@@ -0,0 +1,82 @@
+#include <traceevent/event-parse.h>
+#include "evsel.h"
+#include "tests.h"
+#include "debug.h"
+
+static int perf_evsel__test_field(struct perf_evsel *evsel, const char *name,
+				  int size, bool should_be_signed)
+{
+	struct format_field *field = perf_evsel__field(evsel, name);
+	int is_signed;
+	int ret = 0;
+
+	if (field == NULL) {
+		pr_debug("%s: \"%s\" field not found!\n", evsel->name, name);
+		return -1;
+	}
+
+	is_signed = !!(field->flags | FIELD_IS_SIGNED);
+	if (should_be_signed && !is_signed) {
+		pr_debug("%s: \"%s\" signedness(%d) is wrong, should be %d\n",
+			 evsel->name, name, is_signed, should_be_signed);
+		ret = -1;
+	}
+
+	if (field->size != size) {
+		pr_debug("%s: \"%s\" size (%d) should be %d!\n",
+			 evsel->name, name, field->size, size);
+		ret = -1;
+	}
+
+	return ret;
+}
+
+int test__perf_evsel__tp_sched_test(void)
+{
+	struct perf_evsel *evsel = perf_evsel__newtp("sched", "sched_switch");
+	int ret = 0;
+
+	if (evsel == NULL) {
+		pr_debug("perf_evsel__new\n");
+		return -1;
+	}
+
+	if (perf_evsel__test_field(evsel, "prev_comm", 16, true))
+		ret = -1;
+
+	if (perf_evsel__test_field(evsel, "prev_pid", 4, true))
+		ret = -1;
+
+	if (perf_evsel__test_field(evsel, "prev_prio", 4, true))
+		ret = -1;
+
+	if (perf_evsel__test_field(evsel, "prev_state", sizeof(long), true))
+		ret = -1;
+
+	if (perf_evsel__test_field(evsel, "next_comm", 16, true))
+		ret = -1;
+
+	if (perf_evsel__test_field(evsel, "next_pid", 4, true))
+		ret = -1;
+
+	if (perf_evsel__test_field(evsel, "next_prio", 4, true))
+		ret = -1;
+
+	perf_evsel__delete(evsel);
+
+	evsel = perf_evsel__newtp("sched", "sched_wakeup");
+
+	if (perf_evsel__test_field(evsel, "comm", 16, true))
+		ret = -1;
+
+	if (perf_evsel__test_field(evsel, "pid", 4, true))
+		ret = -1;
+
+	if (perf_evsel__test_field(evsel, "prio", 4, true))
+		ret = -1;
+
+	if (perf_evsel__test_field(evsel, "target_cpu", 4, true))
+		ret = -1;
+
+	return ret;
+}
diff --git a/tools/perf/tests/fdarray.c b/tools/perf/tests/fdarray.c
new file mode 100644
index 000000000..d24b83795
--- /dev/null
+++ b/tools/perf/tests/fdarray.c
@@ -0,0 +1,174 @@
+#include <api/fd/array.h>
+#include "util/debug.h"
+#include "tests/tests.h"
+
+static void fdarray__init_revents(struct fdarray *fda, short revents)
+{
+	int fd;
+
+	fda->nr = fda->nr_alloc;
+
+	for (fd = 0; fd < fda->nr; ++fd) {
+		fda->entries[fd].fd	 = fda->nr - fd;
+		fda->entries[fd].revents = revents;
+	}
+}
+
+static int fdarray__fprintf_prefix(struct fdarray *fda, const char *prefix, FILE *fp)
+{
+	int printed = 0;
+
+	if (!verbose)
+		return 0;
+
+	printed += fprintf(fp, "\n%s: ", prefix);
+	return printed + fdarray__fprintf(fda, fp);
+}
+
+int test__fdarray__filter(void)
+{
+	int nr_fds, expected_fd[2], fd, err = TEST_FAIL;
+	struct fdarray *fda = fdarray__new(5, 5);
+
+	if (fda == NULL) {
+		pr_debug("\nfdarray__new() failed!");
+		goto out;
+	}
+
+	fdarray__init_revents(fda, POLLIN);
+	nr_fds = fdarray__filter(fda, POLLHUP, NULL);
+	if (nr_fds != fda->nr_alloc) {
+		pr_debug("\nfdarray__filter()=%d != %d shouldn't have filtered anything",
+			 nr_fds, fda->nr_alloc);
+		goto out_delete;
+	}
+
+	fdarray__init_revents(fda, POLLHUP);
+	nr_fds = fdarray__filter(fda, POLLHUP, NULL);
+	if (nr_fds != 0) {
+		pr_debug("\nfdarray__filter()=%d != %d, should have filtered all fds",
+			 nr_fds, fda->nr_alloc);
+		goto out_delete;
+	}
+
+	fdarray__init_revents(fda, POLLHUP);
+	fda->entries[2].revents = POLLIN;
+	expected_fd[0] = fda->entries[2].fd;
+
+	pr_debug("\nfiltering all but fda->entries[2]:");
+	fdarray__fprintf_prefix(fda, "before", stderr);
+	nr_fds = fdarray__filter(fda, POLLHUP, NULL);
+	fdarray__fprintf_prefix(fda, " after", stderr);
+	if (nr_fds != 1) {
+		pr_debug("\nfdarray__filter()=%d != 1, should have left just one event", nr_fds);
+		goto out_delete;
+	}
+
+	if (fda->entries[0].fd != expected_fd[0]) {
+		pr_debug("\nfda->entries[0].fd=%d != %d\n",
+			 fda->entries[0].fd, expected_fd[0]);
+		goto out_delete;
+	}
+
+	fdarray__init_revents(fda, POLLHUP);
+	fda->entries[0].revents = POLLIN;
+	expected_fd[0] = fda->entries[0].fd;
+	fda->entries[3].revents = POLLIN;
+	expected_fd[1] = fda->entries[3].fd;
+
+	pr_debug("\nfiltering all but (fda->entries[0], fda->entries[3]):");
+	fdarray__fprintf_prefix(fda, "before", stderr);
+	nr_fds = fdarray__filter(fda, POLLHUP, NULL);
+	fdarray__fprintf_prefix(fda, " after", stderr);
+	if (nr_fds != 2) {
+		pr_debug("\nfdarray__filter()=%d != 2, should have left just two events",
+			 nr_fds);
+		goto out_delete;
+	}
+
+	for (fd = 0; fd < 2; ++fd) {
+		if (fda->entries[fd].fd != expected_fd[fd]) {
+			pr_debug("\nfda->entries[%d].fd=%d != %d\n", fd,
+				 fda->entries[fd].fd, expected_fd[fd]);
+			goto out_delete;
+		}
+	}
+
+	pr_debug("\n");
+
+	err = 0;
+out_delete:
+	fdarray__delete(fda);
+out:
+	return err;
+}
+
+int test__fdarray__add(void)
+{
+	int err = TEST_FAIL;
+	struct fdarray *fda = fdarray__new(2, 2);
+
+	if (fda == NULL) {
+		pr_debug("\nfdarray__new() failed!");
+		goto out;
+	}
+
+#define FDA_CHECK(_idx, _fd, _revents)					   \
+	if (fda->entries[_idx].fd != _fd) {				   \
+		pr_debug("\n%d: fda->entries[%d](%d) != %d!",		   \
+			 __LINE__, _idx, fda->entries[1].fd, _fd);	   \
+		goto out_delete;					   \
+	}								   \
+	if (fda->entries[_idx].events != (_revents)) {			   \
+		pr_debug("\n%d: fda->entries[%d].revents(%d) != %d!",	   \
+			 __LINE__, _idx, fda->entries[_idx].fd, _revents); \
+		goto out_delete;					   \
+	}
+
+#define FDA_ADD(_idx, _fd, _revents, _nr)				   \
+	if (fdarray__add(fda, _fd, _revents) < 0) {			   \
+		pr_debug("\n%d: fdarray__add(fda, %d, %d) failed!",	   \
+			 __LINE__,_fd, _revents);			   \
+		goto out_delete;					   \
+	}								   \
+	if (fda->nr != _nr) {						   \
+		pr_debug("\n%d: fdarray__add(fda, %d, %d)=%d != %d",	   \
+			 __LINE__,_fd, _revents, fda->nr, _nr);		   \
+		goto out_delete;					   \
+	}								   \
+	FDA_CHECK(_idx, _fd, _revents)
+
+	FDA_ADD(0, 1, POLLIN, 1);
+	FDA_ADD(1, 2, POLLERR, 2);
+
+	fdarray__fprintf_prefix(fda, "before growing array", stderr);
+
+	FDA_ADD(2, 35, POLLHUP, 3);
+
+	if (fda->entries == NULL) {
+		pr_debug("\nfdarray__add(fda, 35, POLLHUP) should have allocated fda->pollfd!");
+		goto out_delete;
+	}
+
+	fdarray__fprintf_prefix(fda, "after 3rd add", stderr);
+
+	FDA_ADD(3, 88, POLLIN | POLLOUT, 4);
+
+	fdarray__fprintf_prefix(fda, "after 4th add", stderr);
+
+	FDA_CHECK(0, 1, POLLIN);
+	FDA_CHECK(1, 2, POLLERR);
+	FDA_CHECK(2, 35, POLLHUP);
+	FDA_CHECK(3, 88, POLLIN | POLLOUT);
+
+#undef FDA_ADD
+#undef FDA_CHECK
+
+	pr_debug("\n");
+
+	err = 0;
+out_delete:
+	fdarray__delete(fda);
+out:
+	return err;
+}
diff --git a/tools/perf/tests/hists_common.c b/tools/perf/tests/hists_common.c
new file mode 100644
index 000000000..a62c09134
--- /dev/null
+++ b/tools/perf/tests/hists_common.c
@@ -0,0 +1,209 @@
+#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[] = {
+	{ FAKE_PID_PERF1, "perf" },
+	{ FAKE_PID_PERF2, "perf" },
+	{ FAKE_PID_BASH,  "bash" },
+};
+
+static struct {
+	u32 pid;
+	u64 start;
+	const char *filename;
+} fake_mmap_info[] = {
+	{ FAKE_PID_PERF1, FAKE_MAP_PERF,   "perf" },
+	{ FAKE_PID_PERF1, FAKE_MAP_LIBC,   "libc" },
+	{ FAKE_PID_PERF1, FAKE_MAP_KERNEL, "[kernel]" },
+	{ FAKE_PID_PERF2, FAKE_MAP_PERF,   "perf" },
+	{ FAKE_PID_PERF2, FAKE_MAP_LIBC,   "libc" },
+	{ FAKE_PID_PERF2, FAKE_MAP_KERNEL, "[kernel]" },
+	{ FAKE_PID_BASH,  FAKE_MAP_BASH,   "bash" },
+	{ FAKE_PID_BASH,  FAKE_MAP_LIBC,   "libc" },
+	{ FAKE_PID_BASH,  FAKE_MAP_KERNEL, "[kernel]" },
+};
+
+struct fake_sym {
+	u64 start;
+	u64 length;
+	const char *name;
+};
+
+static struct fake_sym perf_syms[] = {
+	{ FAKE_SYM_OFFSET1, FAKE_SYM_LENGTH, "main" },
+	{ FAKE_SYM_OFFSET2, FAKE_SYM_LENGTH, "run_command" },
+	{ FAKE_SYM_OFFSET3, FAKE_SYM_LENGTH, "cmd_record" },
+};
+
+static struct fake_sym bash_syms[] = {
+	{ FAKE_SYM_OFFSET1, FAKE_SYM_LENGTH, "main" },
+	{ FAKE_SYM_OFFSET2, FAKE_SYM_LENGTH, "xmalloc" },
+	{ FAKE_SYM_OFFSET3, FAKE_SYM_LENGTH, "xfree" },
+};
+
+static struct fake_sym libc_syms[] = {
+	{ 700, 100, "malloc" },
+	{ 800, 100, "free" },
+	{ 900, 100, "realloc" },
+	{ FAKE_SYM_OFFSET1, FAKE_SYM_LENGTH, "malloc" },
+	{ FAKE_SYM_OFFSET2, FAKE_SYM_LENGTH, "free" },
+	{ FAKE_SYM_OFFSET3, FAKE_SYM_LENGTH, "realloc" },
+};
+
+static struct fake_sym kernel_syms[] = {
+	{ FAKE_SYM_OFFSET1, FAKE_SYM_LENGTH, "schedule" },
+	{ FAKE_SYM_OFFSET2, FAKE_SYM_LENGTH, "page_fault" },
+	{ FAKE_SYM_OFFSET3, FAKE_SYM_LENGTH, "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 = FAKE_MAP_LENGTH,
+				.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"/%"PRIu64"\n",
+				i, thread__comm_str(he->thread), he->thread->tid,
+				he->ms.map->dso->short_name,
+				he->ms.sym->name, he->stat.period,
+				he->stat_acc ? he->stat_acc->period : 0);
+		}
+
+		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 000000000..888254e86
--- /dev/null
+++ b/tools/perf/tests/hists_common.h
@@ -0,0 +1,75 @@
+#ifndef __PERF_TESTS__HISTS_COMMON_H__
+#define __PERF_TESTS__HISTS_COMMON_H__
+
+struct machine;
+struct machines;
+
+#define FAKE_PID_PERF1  100
+#define FAKE_PID_PERF2  200
+#define FAKE_PID_BASH   300
+
+#define FAKE_MAP_PERF    0x400000
+#define FAKE_MAP_BASH    0x400000
+#define FAKE_MAP_LIBC    0x500000
+#define FAKE_MAP_KERNEL  0xf00000
+#define FAKE_MAP_LENGTH  0x100000
+
+#define FAKE_SYM_OFFSET1  700
+#define FAKE_SYM_OFFSET2  800
+#define FAKE_SYM_OFFSET3  900
+#define FAKE_SYM_LENGTH   100
+
+#define FAKE_IP_PERF_MAIN  FAKE_MAP_PERF + FAKE_SYM_OFFSET1
+#define FAKE_IP_PERF_RUN_COMMAND  FAKE_MAP_PERF + FAKE_SYM_OFFSET2
+#define FAKE_IP_PERF_CMD_RECORD  FAKE_MAP_PERF + FAKE_SYM_OFFSET3
+#define FAKE_IP_BASH_MAIN  FAKE_MAP_BASH + FAKE_SYM_OFFSET1
+#define FAKE_IP_BASH_XMALLOC  FAKE_MAP_BASH + FAKE_SYM_OFFSET2
+#define FAKE_IP_BASH_XFREE  FAKE_MAP_BASH + FAKE_SYM_OFFSET3
+#define FAKE_IP_LIBC_MALLOC  FAKE_MAP_LIBC + FAKE_SYM_OFFSET1
+#define FAKE_IP_LIBC_FREE  FAKE_MAP_LIBC + FAKE_SYM_OFFSET2
+#define FAKE_IP_LIBC_REALLOC  FAKE_MAP_LIBC + FAKE_SYM_OFFSET3
+#define FAKE_IP_KERNEL_SCHEDULE  FAKE_MAP_KERNEL + FAKE_SYM_OFFSET1
+#define FAKE_IP_KERNEL_PAGE_FAULT  FAKE_MAP_KERNEL + FAKE_SYM_OFFSET2
+#define FAKE_IP_KERNEL_SYS_PERF_EVENT_OPEN  FAKE_MAP_KERNEL + FAKE_SYM_OFFSET3
+
+/*
+ * 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  cmd_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  cmd_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_cumulate.c b/tools/perf/tests/hists_cumulate.c
new file mode 100644
index 000000000..186199664
--- /dev/null
+++ b/tools/perf/tests/hists_cumulate.c
@@ -0,0 +1,726 @@
+#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 = FAKE_PID_PERF1, .ip = FAKE_IP_KERNEL_SCHEDULE, },
+	/* perf [perf]   main() */
+	{ .pid = FAKE_PID_PERF1, .ip = FAKE_IP_PERF_MAIN, },
+	/* perf [perf]   cmd_record() */
+	{ .pid = FAKE_PID_PERF1, .ip = FAKE_IP_PERF_CMD_RECORD, },
+	/* perf [libc]   malloc() */
+	{ .pid = FAKE_PID_PERF1, .ip = FAKE_IP_LIBC_MALLOC, },
+	/* perf [libc]   free() */
+	{ .pid = FAKE_PID_PERF1, .ip = FAKE_IP_LIBC_FREE, },
+	/* perf [perf]   main() */
+	{ .pid = FAKE_PID_PERF2, .ip = FAKE_IP_PERF_MAIN, },
+	/* perf [kernel] page_fault() */
+	{ .pid = FAKE_PID_PERF2, .ip = FAKE_IP_KERNEL_PAGE_FAULT, },
+	/* bash [bash]   main() */
+	{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_BASH_MAIN, },
+	/* bash [bash]   xmalloc() */
+	{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_BASH_XMALLOC, },
+	/* bash [kernel] page_fault() */
+	{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_KERNEL_PAGE_FAULT, },
+};
+
+/*
+ * Will be casted to struct ip_callchain which has all 64 bit entries
+ * of nr and ips[].
+ */
+static u64 fake_callchains[][10] = {
+	/*   schedule => run_command => main */
+	{ 3, FAKE_IP_KERNEL_SCHEDULE, FAKE_IP_PERF_RUN_COMMAND, FAKE_IP_PERF_MAIN, },
+	/*   main  */
+	{ 1, FAKE_IP_PERF_MAIN, },
+	/*   cmd_record => run_command => main */
+	{ 3, FAKE_IP_PERF_CMD_RECORD, FAKE_IP_PERF_RUN_COMMAND, FAKE_IP_PERF_MAIN, },
+	/*   malloc => cmd_record => run_command => main */
+	{ 4, FAKE_IP_LIBC_MALLOC, FAKE_IP_PERF_CMD_RECORD, FAKE_IP_PERF_RUN_COMMAND,
+	     FAKE_IP_PERF_MAIN, },
+	/*   free => cmd_record => run_command => main */
+	{ 4, FAKE_IP_LIBC_FREE, FAKE_IP_PERF_CMD_RECORD, FAKE_IP_PERF_RUN_COMMAND,
+	     FAKE_IP_PERF_MAIN, },
+	/*   main */
+	{ 1, FAKE_IP_PERF_MAIN, },
+	/*   page_fault => sys_perf_event_open => run_command => main */
+	{ 4, FAKE_IP_KERNEL_PAGE_FAULT, FAKE_IP_KERNEL_SYS_PERF_EVENT_OPEN,
+	     FAKE_IP_PERF_RUN_COMMAND, FAKE_IP_PERF_MAIN, },
+	/*   main */
+	{ 1, FAKE_IP_BASH_MAIN, },
+	/*   xmalloc => malloc => xmalloc => malloc => xmalloc => main */
+	{ 6, FAKE_IP_BASH_XMALLOC, FAKE_IP_LIBC_MALLOC, FAKE_IP_BASH_XMALLOC,
+	     FAKE_IP_LIBC_MALLOC, FAKE_IP_BASH_XMALLOC, FAKE_IP_BASH_MAIN, },
+	/*   page_fault => malloc => main */
+	{ 3, FAKE_IP_KERNEL_PAGE_FAULT, FAKE_IP_LIBC_MALLOC, FAKE_IP_BASH_MAIN, },
+};
+
+static int add_hist_entries(struct hists *hists, struct machine *machine)
+{
+	struct addr_location al;
+	struct perf_evsel *evsel = hists_to_evsel(hists);
+	struct perf_sample sample = { .period = 1000, };
+	size_t i;
+
+	for (i = 0; i < ARRAY_SIZE(fake_samples); i++) {
+		const union perf_event event = {
+			.header = {
+				.misc = PERF_RECORD_MISC_USER,
+			},
+		};
+		struct hist_entry_iter iter = {
+			.hide_unresolved = false,
+		};
+
+		if (symbol_conf.cumulate_callchain)
+			iter.ops = &hist_iter_cumulative;
+		else
+			iter.ops = &hist_iter_normal;
+
+		sample.pid = fake_samples[i].pid;
+		sample.tid = fake_samples[i].pid;
+		sample.ip = fake_samples[i].ip;
+		sample.callchain = (struct ip_callchain *)fake_callchains[i];
+
+		if (perf_event__preprocess_sample(&event, machine, &al,
+						  &sample) < 0)
+			goto out;
+
+		if (hist_entry_iter__add(&iter, &al, evsel, &sample,
+					 PERF_MAX_STACK_DEPTH, NULL) < 0)
+			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__delete(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)
+#define DEPTH(he) (he->callchain->max_depth)
+#define CDSO(cl)  (cl->ms.map->dso->short_name)
+#define CSYM(cl)  (cl->ms.sym->name)
+
+struct result {
+	u64 children;
+	u64 self;
+	const char *comm;
+	const char *dso;
+	const char *sym;
+};
+
+struct callchain_result {
+	u64 nr;
+	struct {
+		const char *dso;
+		const char *sym;
+	} node[10];
+};
+
+static int do_test(struct hists *hists, struct result *expected, size_t nr_expected,
+		   struct callchain_result *expected_callchain, size_t nr_callchain)
+{
+	char buf[32];
+	size_t i, c;
+	struct hist_entry *he;
+	struct rb_root *root;
+	struct rb_node *node;
+	struct callchain_node *cnode;
+	struct callchain_list *clist;
+
+	/*
+	 * adding and deleting hist entries must be done outside of this
+	 * function since TEST_ASSERT_VAL() returns in case of failure.
+	 */
+	hists__collapse_resort(hists, NULL);
+	hists__output_resort(hists, NULL);
+
+	if (verbose > 2) {
+		pr_info("use callchain: %d, cumulate callchain: %d\n",
+			symbol_conf.use_callchain,
+			symbol_conf.cumulate_callchain);
+		print_hists_out(hists);
+	}
+
+	root = &hists->entries;
+	for (node = rb_first(root), i = 0;
+	     node && (he = rb_entry(node, struct hist_entry, rb_node));
+	     node = rb_next(node), i++) {
+		scnprintf(buf, sizeof(buf), "Invalid hist entry #%zd", i);
+
+		TEST_ASSERT_VAL("Incorrect number of hist entry",
+				i < nr_expected);
+		TEST_ASSERT_VAL(buf, he->stat.period == expected[i].self &&
+				!strcmp(COMM(he), expected[i].comm) &&
+				!strcmp(DSO(he), expected[i].dso) &&
+				!strcmp(SYM(he), expected[i].sym));
+
+		if (symbol_conf.cumulate_callchain)
+			TEST_ASSERT_VAL(buf, he->stat_acc->period == expected[i].children);
+
+		if (!symbol_conf.use_callchain)
+			continue;
+
+		/* check callchain entries */
+		root = &he->callchain->node.rb_root;
+		cnode = rb_entry(rb_first(root), struct callchain_node, rb_node);
+
+		c = 0;
+		list_for_each_entry(clist, &cnode->val, list) {
+			scnprintf(buf, sizeof(buf), "Invalid callchain entry #%zd/%zd", i, c);
+
+			TEST_ASSERT_VAL("Incorrect number of callchain entry",
+					c < expected_callchain[i].nr);
+			TEST_ASSERT_VAL(buf,
+				!strcmp(CDSO(clist), expected_callchain[i].node[c].dso) &&
+				!strcmp(CSYM(clist), expected_callchain[i].node[c].sym));
+			c++;
+		}
+		/* TODO: handle multiple child nodes properly */
+		TEST_ASSERT_VAL("Incorrect number of callchain entry",
+				c <= expected_callchain[i].nr);
+	}
+	TEST_ASSERT_VAL("Incorrect number of hist entry",
+			i == nr_expected);
+	TEST_ASSERT_VAL("Incorrect number of callchain entry",
+			!symbol_conf.use_callchain || nr_expected == nr_callchain);
+	return 0;
+}
+
+/* NO callchain + NO children */
+static int test1(struct perf_evsel *evsel, struct machine *machine)
+{
+	int err;
+	struct hists *hists = evsel__hists(evsel);
+	/*
+	 * 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
+	 */
+	struct result expected[] = {
+		{ 0, 2000, "perf", "perf",     "main" },
+		{ 0, 1000, "bash", "[kernel]", "page_fault" },
+		{ 0, 1000, "bash", "bash",     "main" },
+		{ 0, 1000, "bash", "bash",     "xmalloc" },
+		{ 0, 1000, "perf", "[kernel]", "page_fault" },
+		{ 0, 1000, "perf", "[kernel]", "schedule" },
+		{ 0, 1000, "perf", "libc",     "free" },
+		{ 0, 1000, "perf", "libc",     "malloc" },
+		{ 0, 1000, "perf", "perf",     "cmd_record" },
+	};
+
+	symbol_conf.use_callchain = false;
+	symbol_conf.cumulate_callchain = false;
+
+	setup_sorting();
+	callchain_register_param(&callchain_param);
+
+	err = add_hist_entries(hists, machine);
+	if (err < 0)
+		goto out;
+
+	err = do_test(hists, expected, ARRAY_SIZE(expected), NULL, 0);
+
+out:
+	del_hist_entries(hists);
+	reset_output_field();
+	return err;
+}
+
+/* callcain + NO children */
+static int test2(struct perf_evsel *evsel, struct machine *machine)
+{
+	int err;
+	struct hists *hists = evsel__hists(evsel);
+	/*
+	 * expected output:
+	 *
+	 * Overhead  Command  Shared Object          Symbol
+	 * ========  =======  =============  ==============
+	 *   20.00%     perf  perf           [.] main
+	 *              |
+	 *              --- main
+	 *
+	 *   10.00%     bash  [kernel]       [k] page_fault
+	 *              |
+	 *              --- page_fault
+	 *                  malloc
+	 *                  main
+	 *
+	 *   10.00%     bash  bash           [.] main
+	 *              |
+	 *              --- main
+	 *
+	 *   10.00%     bash  bash           [.] xmalloc
+	 *              |
+	 *              --- xmalloc
+	 *                  malloc
+	 *                  xmalloc     <--- NOTE: there's a cycle
+	 *                  malloc
+	 *                  xmalloc
+	 *                  main
+	 *
+	 *   10.00%     perf  [kernel]       [k] page_fault
+	 *              |
+	 *              --- page_fault
+	 *                  sys_perf_event_open
+	 *                  run_command
+	 *                  main
+	 *
+	 *   10.00%     perf  [kernel]       [k] schedule
+	 *              |
+	 *              --- schedule
+	 *                  run_command
+	 *                  main
+	 *
+	 *   10.00%     perf  libc           [.] free
+	 *              |
+	 *              --- free
+	 *                  cmd_record
+	 *                  run_command
+	 *                  main
+	 *
+	 *   10.00%     perf  libc           [.] malloc
+	 *              |
+	 *              --- malloc
+	 *                  cmd_record
+	 *                  run_command
+	 *                  main
+	 *
+	 *   10.00%     perf  perf           [.] cmd_record
+	 *              |
+	 *              --- cmd_record
+	 *                  run_command
+	 *                  main
+	 *
+	 */
+	struct result expected[] = {
+		{ 0, 2000, "perf", "perf",     "main" },
+		{ 0, 1000, "bash", "[kernel]", "page_fault" },
+		{ 0, 1000, "bash", "bash",     "main" },
+		{ 0, 1000, "bash", "bash",     "xmalloc" },
+		{ 0, 1000, "perf", "[kernel]", "page_fault" },
+		{ 0, 1000, "perf", "[kernel]", "schedule" },
+		{ 0, 1000, "perf", "libc",     "free" },
+		{ 0, 1000, "perf", "libc",     "malloc" },
+		{ 0, 1000, "perf", "perf",     "cmd_record" },
+	};
+	struct callchain_result expected_callchain[] = {
+		{
+			1, {	{ "perf",     "main" }, },
+		},
+		{
+			3, {	{ "[kernel]", "page_fault" },
+				{ "libc",     "malloc" },
+				{ "bash",     "main" }, },
+		},
+		{
+			1, {	{ "bash",     "main" }, },
+		},
+		{
+			6, {	{ "bash",     "xmalloc" },
+				{ "libc",     "malloc" },
+				{ "bash",     "xmalloc" },
+				{ "libc",     "malloc" },
+				{ "bash",     "xmalloc" },
+				{ "bash",     "main" }, },
+		},
+		{
+			4, {	{ "[kernel]", "page_fault" },
+				{ "[kernel]", "sys_perf_event_open" },
+				{ "perf",     "run_command" },
+				{ "perf",     "main" }, },
+		},
+		{
+			3, {	{ "[kernel]", "schedule" },
+				{ "perf",     "run_command" },
+				{ "perf",     "main" }, },
+		},
+		{
+			4, {	{ "libc",     "free" },
+				{ "perf",     "cmd_record" },
+				{ "perf",     "run_command" },
+				{ "perf",     "main" }, },
+		},
+		{
+			4, {	{ "libc",     "malloc" },
+				{ "perf",     "cmd_record" },
+				{ "perf",     "run_command" },
+				{ "perf",     "main" }, },
+		},
+		{
+			3, {	{ "perf",     "cmd_record" },
+				{ "perf",     "run_command" },
+				{ "perf",     "main" }, },
+		},
+	};
+
+	symbol_conf.use_callchain = true;
+	symbol_conf.cumulate_callchain = false;
+
+	setup_sorting();
+	callchain_register_param(&callchain_param);
+
+	err = add_hist_entries(hists, machine);
+	if (err < 0)
+		goto out;
+
+	err = do_test(hists, expected, ARRAY_SIZE(expected),
+		      expected_callchain, ARRAY_SIZE(expected_callchain));
+
+out:
+	del_hist_entries(hists);
+	reset_output_field();
+	return err;
+}
+
+/* NO callchain + children */
+static int test3(struct perf_evsel *evsel, struct machine *machine)
+{
+	int err;
+	struct hists *hists = evsel__hists(evsel);
+	/*
+	 * expected output:
+	 *
+	 * Children      Self  Command  Shared Object                   Symbol
+	 * ========  ========  =======  =============  =======================
+	 *   70.00%    20.00%     perf  perf           [.] main
+	 *   50.00%     0.00%     perf  perf           [.] run_command
+	 *   30.00%    10.00%     bash  bash           [.] main
+	 *   30.00%    10.00%     perf  perf           [.] cmd_record
+	 *   20.00%     0.00%     bash  libc           [.] malloc
+	 *   10.00%    10.00%     bash  [kernel]       [k] page_fault
+	 *   10.00%    10.00%     bash  bash           [.] xmalloc
+	 *   10.00%    10.00%     perf  [kernel]       [k] page_fault
+	 *   10.00%    10.00%     perf  libc           [.] malloc
+	 *   10.00%    10.00%     perf  [kernel]       [k] schedule
+	 *   10.00%    10.00%     perf  libc           [.] free
+	 *   10.00%     0.00%     perf  [kernel]       [k] sys_perf_event_open
+	 */
+	struct result expected[] = {
+		{ 7000, 2000, "perf", "perf",     "main" },
+		{ 5000,    0, "perf", "perf",     "run_command" },
+		{ 3000, 1000, "bash", "bash",     "main" },
+		{ 3000, 1000, "perf", "perf",     "cmd_record" },
+		{ 2000,    0, "bash", "libc",     "malloc" },
+		{ 1000, 1000, "bash", "[kernel]", "page_fault" },
+		{ 1000, 1000, "bash", "bash",     "xmalloc" },
+		{ 1000, 1000, "perf", "[kernel]", "page_fault" },
+		{ 1000, 1000, "perf", "[kernel]", "schedule" },
+		{ 1000, 1000, "perf", "libc",     "free" },
+		{ 1000, 1000, "perf", "libc",     "malloc" },
+		{ 1000,    0, "perf", "[kernel]", "sys_perf_event_open" },
+	};
+
+	symbol_conf.use_callchain = false;
+	symbol_conf.cumulate_callchain = true;
+
+	setup_sorting();
+	callchain_register_param(&callchain_param);
+
+	err = add_hist_entries(hists, machine);
+	if (err < 0)
+		goto out;
+
+	err = do_test(hists, expected, ARRAY_SIZE(expected), NULL, 0);
+
+out:
+	del_hist_entries(hists);
+	reset_output_field();
+	return err;
+}
+
+/* callchain + children */
+static int test4(struct perf_evsel *evsel, struct machine *machine)
+{
+	int err;
+	struct hists *hists = evsel__hists(evsel);
+	/*
+	 * expected output:
+	 *
+	 * Children      Self  Command  Shared Object                   Symbol
+	 * ========  ========  =======  =============  =======================
+	 *   70.00%    20.00%     perf  perf           [.] main
+	 *              |
+	 *              --- main
+	 *
+	 *   50.00%     0.00%     perf  perf           [.] run_command
+	 *              |
+	 *              --- run_command
+	 *                  main
+	 *
+	 *   30.00%    10.00%     bash  bash           [.] main
+	 *              |
+	 *              --- main
+	 *
+	 *   30.00%    10.00%     perf  perf           [.] cmd_record
+	 *              |
+	 *              --- cmd_record
+	 *                  run_command
+	 *                  main
+	 *
+	 *   20.00%     0.00%     bash  libc           [.] malloc
+	 *              |
+	 *              --- malloc
+	 *                 |
+	 *                 |--50.00%-- xmalloc
+	 *                 |           main
+	 *                  --50.00%-- main
+	 *
+	 *   10.00%    10.00%     bash  [kernel]       [k] page_fault
+	 *              |
+	 *              --- page_fault
+	 *                  malloc
+	 *                  main
+	 *
+	 *   10.00%    10.00%     bash  bash           [.] xmalloc
+	 *              |
+	 *              --- xmalloc
+	 *                  malloc
+	 *                  xmalloc     <--- NOTE: there's a cycle
+	 *                  malloc
+	 *                  xmalloc
+	 *                  main
+	 *
+	 *   10.00%     0.00%     perf  [kernel]       [k] sys_perf_event_open
+	 *              |
+	 *              --- sys_perf_event_open
+	 *                  run_command
+	 *                  main
+	 *
+	 *   10.00%    10.00%     perf  [kernel]       [k] page_fault
+	 *              |
+	 *              --- page_fault
+	 *                  sys_perf_event_open
+	 *                  run_command
+	 *                  main
+	 *
+	 *   10.00%    10.00%     perf  [kernel]       [k] schedule
+	 *              |
+	 *              --- schedule
+	 *                  run_command
+	 *                  main
+	 *
+	 *   10.00%    10.00%     perf  libc           [.] free
+	 *              |
+	 *              --- free
+	 *                  cmd_record
+	 *                  run_command
+	 *                  main
+	 *
+	 *   10.00%    10.00%     perf  libc           [.] malloc
+	 *              |
+	 *              --- malloc
+	 *                  cmd_record
+	 *                  run_command
+	 *                  main
+	 *
+	 */
+	struct result expected[] = {
+		{ 7000, 2000, "perf", "perf",     "main" },
+		{ 5000,    0, "perf", "perf",     "run_command" },
+		{ 3000, 1000, "bash", "bash",     "main" },
+		{ 3000, 1000, "perf", "perf",     "cmd_record" },
+		{ 2000,    0, "bash", "libc",     "malloc" },
+		{ 1000, 1000, "bash", "[kernel]", "page_fault" },
+		{ 1000, 1000, "bash", "bash",     "xmalloc" },
+		{ 1000,    0, "perf", "[kernel]", "sys_perf_event_open" },
+		{ 1000, 1000, "perf", "[kernel]", "page_fault" },
+		{ 1000, 1000, "perf", "[kernel]", "schedule" },
+		{ 1000, 1000, "perf", "libc",     "free" },
+		{ 1000, 1000, "perf", "libc",     "malloc" },
+	};
+	struct callchain_result expected_callchain[] = {
+		{
+			1, {	{ "perf",     "main" }, },
+		},
+		{
+			2, {	{ "perf",     "run_command" },
+				{ "perf",     "main" }, },
+		},
+		{
+			1, {	{ "bash",     "main" }, },
+		},
+		{
+			3, {	{ "perf",     "cmd_record" },
+				{ "perf",     "run_command" },
+				{ "perf",     "main" }, },
+		},
+		{
+			4, {	{ "libc",     "malloc" },
+				{ "bash",     "xmalloc" },
+				{ "bash",     "main" },
+				{ "bash",     "main" }, },
+		},
+		{
+			3, {	{ "[kernel]", "page_fault" },
+				{ "libc",     "malloc" },
+				{ "bash",     "main" }, },
+		},
+		{
+			6, {	{ "bash",     "xmalloc" },
+				{ "libc",     "malloc" },
+				{ "bash",     "xmalloc" },
+				{ "libc",     "malloc" },
+				{ "bash",     "xmalloc" },
+				{ "bash",     "main" }, },
+		},
+		{
+			3, {	{ "[kernel]", "sys_perf_event_open" },
+				{ "perf",     "run_command" },
+				{ "perf",     "main" }, },
+		},
+		{
+			4, {	{ "[kernel]", "page_fault" },
+				{ "[kernel]", "sys_perf_event_open" },
+				{ "perf",     "run_command" },
+				{ "perf",     "main" }, },
+		},
+		{
+			3, {	{ "[kernel]", "schedule" },
+				{ "perf",     "run_command" },
+				{ "perf",     "main" }, },
+		},
+		{
+			4, {	{ "libc",     "free" },
+				{ "perf",     "cmd_record" },
+				{ "perf",     "run_command" },
+				{ "perf",     "main" }, },
+		},
+		{
+			4, {	{ "libc",     "malloc" },
+				{ "perf",     "cmd_record" },
+				{ "perf",     "run_command" },
+				{ "perf",     "main" }, },
+		},
+	};
+
+	symbol_conf.use_callchain = true;
+	symbol_conf.cumulate_callchain = true;
+
+	setup_sorting();
+	callchain_register_param(&callchain_param);
+
+	err = add_hist_entries(hists, machine);
+	if (err < 0)
+		goto out;
+
+	err = do_test(hists, expected, ARRAY_SIZE(expected),
+		      expected_callchain, ARRAY_SIZE(expected_callchain));
+
+out:
+	del_hist_entries(hists);
+	reset_output_field();
+	return err;
+}
+
+int test__hists_cumulate(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,
+	};
+
+	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/hists_filter.c b/tools/perf/tests/hists_filter.c
new file mode 100644
index 000000000..59e53db79
--- /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 = FAKE_PID_PERF1, .ip = FAKE_IP_KERNEL_SCHEDULE, },
+	/* perf [perf]   main() */
+	{ .pid = FAKE_PID_PERF1, .ip = FAKE_IP_PERF_MAIN, },
+	/* perf [libc]   malloc() */
+	{ .pid = FAKE_PID_PERF1, .ip = FAKE_IP_LIBC_MALLOC, },
+	/* perf [perf]   main() */
+	{ .pid = FAKE_PID_PERF2, .ip = FAKE_IP_PERF_MAIN, }, /* will be merged */
+	/* perf [perf]   cmd_record() */
+	{ .pid = FAKE_PID_PERF2, .ip = FAKE_IP_PERF_CMD_RECORD, },
+	/* perf [kernel] page_fault() */
+	{ .pid = FAKE_PID_PERF2, .ip = FAKE_IP_KERNEL_PAGE_FAULT, },
+	/* bash [bash]   main() */
+	{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_BASH_MAIN, },
+	/* bash [bash]   xmalloc() */
+	{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_BASH_XMALLOC, },
+	/* bash [libc]   malloc() */
+	{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_LIBC_MALLOC, },
+	/* bash [kernel] page_fault() */
+	{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_KERNEL_PAGE_FAULT, },
+};
+
+static int add_hist_entries(struct perf_evlist *evlist,
+			    struct machine *machine)
+{
+	struct perf_evsel *evsel;
+	struct addr_location al;
+	struct perf_sample sample = { .period = 100, };
+	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,
+				},
+			};
+			struct hist_entry_iter iter = {
+				.ops = &hist_iter_normal,
+				.hide_unresolved = false,
+			};
+			struct hists *hists = evsel__hists(evsel);
+
+			/* make sure it has no filter at first */
+			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;
+			sample.ip = fake_samples[i].ip;
+
+			if (perf_event__preprocess_sample(&event, machine, &al,
+							  &sample) < 0)
+				goto out;
+
+			if (hist_entry_iter__add(&iter, &al, evsel, &sample,
+						 PERF_MAX_STACK_DEPTH, NULL) < 0)
+				goto out;
+
+			fake_samples[i].thread = al.thread;
+			fake_samples[i].map = al.map;
+			fake_samples[i].sym = al.sym;
+		}
+	}
+
+	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(evsel);
+
+		hists__collapse_resort(hists, NULL);
+		hists__output_resort(hists, NULL);
+
+		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' */
+		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 */
+		hists->thread_filter = NULL;
+		hists__filter_by_thread(hists);
+
+		/* now applying dso filter for 'kernel' */
+		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 */
+		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.
+		 */
+		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. */
+		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);
+
+		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
new file mode 100644
index 000000000..278ba8344
--- /dev/null
+++ b/tools/perf/tests/hists_link.c
@@ -0,0 +1,346 @@
+#include "perf.h"
+#include "tests.h"
+#include "debug.h"
+#include "symbol.h"
+#include "sort.h"
+#include "evsel.h"
+#include "evlist.h"
+#include "machine.h"
+#include "thread.h"
+#include "parse-events.h"
+#include "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_common_samples[] = {
+	/* perf [kernel] schedule() */
+	{ .pid = FAKE_PID_PERF1, .ip = FAKE_IP_KERNEL_SCHEDULE, },
+	/* perf [perf]   main() */
+	{ .pid = FAKE_PID_PERF2, .ip = FAKE_IP_PERF_MAIN, },
+	/* perf [perf]   cmd_record() */
+	{ .pid = FAKE_PID_PERF2, .ip = FAKE_IP_PERF_CMD_RECORD, },
+	/* bash [bash]   xmalloc() */
+	{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_BASH_XMALLOC, },
+	/* bash [libc]   malloc() */
+	{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_LIBC_MALLOC, },
+};
+
+static struct sample fake_samples[][5] = {
+	{
+		/* perf [perf]   run_command() */
+		{ .pid = FAKE_PID_PERF1, .ip = FAKE_IP_PERF_RUN_COMMAND, },
+		/* perf [libc]   malloc() */
+		{ .pid = FAKE_PID_PERF1, .ip = FAKE_IP_LIBC_MALLOC, },
+		/* perf [kernel] page_fault() */
+		{ .pid = FAKE_PID_PERF1, .ip = FAKE_IP_KERNEL_PAGE_FAULT, },
+		/* perf [kernel] sys_perf_event_open() */
+		{ .pid = FAKE_PID_PERF2, .ip = FAKE_IP_KERNEL_SYS_PERF_EVENT_OPEN, },
+		/* bash [libc]   free() */
+		{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_LIBC_FREE, },
+	},
+	{
+		/* perf [libc]   free() */
+		{ .pid = FAKE_PID_PERF2, .ip = FAKE_IP_LIBC_FREE, },
+		/* bash [libc]   malloc() */
+		{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_LIBC_MALLOC, }, /* will be merged */
+		/* bash [bash]   xfee() */
+		{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_BASH_XFREE, },
+		/* bash [libc]   realloc() */
+		{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_LIBC_REALLOC, },
+		/* bash [kernel] page_fault() */
+		{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_KERNEL_PAGE_FAULT, },
+	},
+};
+
+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 = { .period = 1, };
+	size_t i = 0, k;
+
+	/*
+	 * each evsel will have 10 samples - 5 common and 5 distinct.
+	 * However the second evsel also has a collapsed entry for
+	 * "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 = {
+					.misc = PERF_RECORD_MISC_USER,
+				},
+			};
+
+			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)
+				goto out;
+
+			he = __hists__add_entry(hists, &al, NULL,
+						NULL, NULL, 1, 1, 0, true);
+			if (he == NULL)
+				goto out;
+
+			fake_common_samples[k].thread = al.thread;
+			fake_common_samples[k].map = al.map;
+			fake_common_samples[k].sym = al.sym;
+		}
+
+		for (k = 0; k < ARRAY_SIZE(fake_samples[i]); k++) {
+			const union perf_event event = {
+				.header = {
+					.misc = PERF_RECORD_MISC_USER,
+				},
+			};
+
+			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)
+				goto out;
+
+			he = __hists__add_entry(hists, &al, NULL,
+						NULL, NULL, 1, 1, 0, true);
+			if (he == NULL)
+				goto out;
+
+			fake_samples[i][k].thread = al.thread;
+			fake_samples[i][k].map = al.map;
+			fake_samples[i][k].sym = al.sym;
+		}
+		i++;
+	}
+
+	return 0;
+
+out:
+	pr_debug("Not enough memory for adding a hist entry\n");
+	return -1;
+}
+
+static int find_sample(struct sample *samples, size_t nr_samples,
+		       struct thread *t, struct map *m, struct symbol *s)
+{
+	while (nr_samples--) {
+		if (samples->thread == t && samples->map == m &&
+		    samples->sym == s)
+			return 1;
+		samples++;
+	}
+	return 0;
+}
+
+static int __validate_match(struct hists *hists)
+{
+	size_t count = 0;
+	struct rb_root *root;
+	struct rb_node *node;
+
+	/*
+	 * Only entries from fake_common_samples should have a pair.
+	 */
+	if (sort__need_collapse)
+		root = &hists->entries_collapsed;
+	else
+		root = hists->entries_in;
+
+	node = rb_first(root);
+	while (node) {
+		struct hist_entry *he;
+
+		he = rb_entry(node, struct hist_entry, rb_node_in);
+
+		if (hist_entry__has_pairs(he)) {
+			if (find_sample(fake_common_samples,
+					ARRAY_SIZE(fake_common_samples),
+					he->thread, he->ms.map, he->ms.sym)) {
+				count++;
+			} else {
+				pr_debug("Can't find the matched entry\n");
+				return -1;
+			}
+		}
+
+		node = rb_next(node);
+	}
+
+	if (count != ARRAY_SIZE(fake_common_samples)) {
+		pr_debug("Invalid count for matched entries: %zd of %zd\n",
+			 count, ARRAY_SIZE(fake_common_samples));
+		return -1;
+	}
+
+	return 0;
+}
+
+static int validate_match(struct hists *leader, struct hists *other)
+{
+	return __validate_match(leader) || __validate_match(other);
+}
+
+static int __validate_link(struct hists *hists, int idx)
+{
+	size_t count = 0;
+	size_t count_pair = 0;
+	size_t count_dummy = 0;
+	struct rb_root *root;
+	struct rb_node *node;
+
+	/*
+	 * Leader hists (idx = 0) will have dummy entries from other,
+	 * and some entries will have no pair.  However every entry
+	 * in other hists should have (dummy) pair.
+	 */
+	if (sort__need_collapse)
+		root = &hists->entries_collapsed;
+	else
+		root = hists->entries_in;
+
+	node = rb_first(root);
+	while (node) {
+		struct hist_entry *he;
+
+		he = rb_entry(node, struct hist_entry, rb_node_in);
+
+		if (hist_entry__has_pairs(he)) {
+			if (!find_sample(fake_common_samples,
+					 ARRAY_SIZE(fake_common_samples),
+					 he->thread, he->ms.map, he->ms.sym) &&
+			    !find_sample(fake_samples[idx],
+					 ARRAY_SIZE(fake_samples[idx]),
+					 he->thread, he->ms.map, he->ms.sym)) {
+				count_dummy++;
+			}
+			count_pair++;
+		} else if (idx) {
+			pr_debug("A entry from the other hists should have pair\n");
+			return -1;
+		}
+
+		count++;
+		node = rb_next(node);
+	}
+
+	/*
+	 * Note that we have a entry collapsed in the other (idx = 1) hists.
+	 */
+	if (idx == 0) {
+		if (count_dummy != ARRAY_SIZE(fake_samples[1]) - 1) {
+			pr_debug("Invalid count of dummy entries: %zd of %zd\n",
+				 count_dummy, ARRAY_SIZE(fake_samples[1]) - 1);
+			return -1;
+		}
+		if (count != count_pair + ARRAY_SIZE(fake_samples[0])) {
+			pr_debug("Invalid count of total leader entries: %zd of %zd\n",
+				 count, count_pair + ARRAY_SIZE(fake_samples[0]));
+			return -1;
+		}
+	} else {
+		if (count != count_pair) {
+			pr_debug("Invalid count of total other entries: %zd of %zd\n",
+				 count, count_pair);
+			return -1;
+		}
+		if (count_dummy > 0) {
+			pr_debug("Other hists should not have dummy entries: %zd\n",
+				 count_dummy);
+			return -1;
+		}
+	}
+
+	return 0;
+}
+
+static int validate_link(struct hists *leader, struct hists *other)
+{
+	return __validate_link(leader, 0) || __validate_link(other, 1);
+}
+
+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;
+	struct perf_evlist *evlist = perf_evlist__new();
+
+	if (evlist == NULL)
+                return -ENOMEM;
+
+	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) {
+		hists = evsel__hists(evsel);
+		hists__collapse_resort(hists, NULL);
+
+		if (verbose > 2)
+			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, hists);
+	err = validate_match(first_hists, hists);
+	if (err)
+		goto out;
+
+	/* link common and/or dummy entries */
+	hists__link(first_hists, hists);
+	err = validate_link(first_hists, hists);
+	if (err)
+		goto out;
+
+	err = 0;
+
+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 000000000..b52c9faea
--- /dev/null
+++ b/tools/perf/tests/hists_output.c
@@ -0,0 +1,621 @@
+#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 = FAKE_PID_PERF1, .ip = FAKE_IP_KERNEL_SCHEDULE, },
+	/* perf [perf]   main() */
+	{ .cpu = 1, .pid = FAKE_PID_PERF1, .ip = FAKE_IP_PERF_MAIN, },
+	/* perf [perf]   cmd_record() */
+	{ .cpu = 1, .pid = FAKE_PID_PERF1, .ip = FAKE_IP_PERF_CMD_RECORD, },
+	/* perf [libc]   malloc() */
+	{ .cpu = 1, .pid = FAKE_PID_PERF1, .ip = FAKE_IP_LIBC_MALLOC, },
+	/* perf [libc]   free() */
+	{ .cpu = 2, .pid = FAKE_PID_PERF1, .ip = FAKE_IP_LIBC_FREE, },
+	/* perf [perf]   main() */
+	{ .cpu = 2, .pid = FAKE_PID_PERF2, .ip = FAKE_IP_PERF_MAIN, },
+	/* perf [kernel] page_fault() */
+	{ .cpu = 2, .pid = FAKE_PID_PERF2, .ip = FAKE_IP_KERNEL_PAGE_FAULT, },
+	/* bash [bash]   main() */
+	{ .cpu = 3, .pid = FAKE_PID_BASH,  .ip = FAKE_IP_BASH_MAIN, },
+	/* bash [bash]   xmalloc() */
+	{ .cpu = 0, .pid = FAKE_PID_BASH,  .ip = FAKE_IP_BASH_XMALLOC, },
+	/* bash [kernel] page_fault() */
+	{ .cpu = 1, .pid = FAKE_PID_BASH,  .ip = FAKE_IP_KERNEL_PAGE_FAULT, },
+};
+
+static int add_hist_entries(struct hists *hists, struct machine *machine)
+{
+	struct addr_location al;
+	struct perf_evsel *evsel = hists_to_evsel(hists);
+	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,
+			},
+		};
+		struct hist_entry_iter iter = {
+			.ops = &hist_iter_normal,
+			.hide_unresolved = false,
+		};
+
+		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;
+
+		if (hist_entry_iter__add(&iter, &al, evsel, &sample,
+					 PERF_MAX_STACK_DEPTH, NULL) < 0)
+			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__delete(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(evsel);
+	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, NULL);
+
+	if (verbose > 2) {
+		pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
+		print_hists_out(hists);
+	}
+
+	root = &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(evsel);
+	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, NULL);
+
+	if (verbose > 2) {
+		pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
+		print_hists_out(hists);
+	}
+
+	root = &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(evsel);
+	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, NULL);
+
+	if (verbose > 2) {
+		pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
+		print_hists_out(hists);
+	}
+
+	root = &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(evsel);
+	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, NULL);
+
+	if (verbose > 2) {
+		pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
+		print_hists_out(hists);
+	}
+
+	root = &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(evsel);
+	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, NULL);
+
+	if (verbose > 2) {
+		pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
+		print_hists_out(hists);
+	}
+
+	root = &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
new file mode 100644
index 000000000..7a5ab7b0b
--- /dev/null
+++ b/tools/perf/tests/keep-tracking.c
@@ -0,0 +1,152 @@
+#include <linux/types.h>
+#include <unistd.h>
+#include <sys/prctl.h>
+
+#include "parse-events.h"
+#include "evlist.h"
+#include "evsel.h"
+#include "thread_map.h"
+#include "cpumap.h"
+#include "tests.h"
+
+#define CHECK__(x) {				\
+	while ((x) < 0) {			\
+		pr_debug(#x " failed!\n");	\
+		goto out_err;			\
+	}					\
+}
+
+#define CHECK_NOT_NULL__(x) {			\
+	while ((x) == NULL) {			\
+		pr_debug(#x " failed!\n");	\
+		goto out_err;			\
+	}					\
+}
+
+static int find_comm(struct perf_evlist *evlist, const char *comm)
+{
+	union perf_event *event;
+	int i, found;
+
+	found = 0;
+	for (i = 0; i < evlist->nr_mmaps; i++) {
+		while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
+			if (event->header.type == PERF_RECORD_COMM &&
+			    (pid_t)event->comm.pid == getpid() &&
+			    (pid_t)event->comm.tid == getpid() &&
+			    strcmp(event->comm.comm, comm) == 0)
+				found += 1;
+			perf_evlist__mmap_consume(evlist, i);
+		}
+	}
+	return found;
+}
+
+/**
+ * test__keep_tracking - test using a dummy software event to keep tracking.
+ *
+ * This function implements a test that checks that tracking events continue
+ * when an event is disabled but a dummy software event is not disabled.  If the
+ * test passes %0 is returned, otherwise %-1 is returned.
+ */
+int test__keep_tracking(void)
+{
+	struct record_opts opts = {
+		.mmap_pages	     = UINT_MAX,
+		.user_freq	     = UINT_MAX,
+		.user_interval	     = ULLONG_MAX,
+		.freq		     = 4000,
+		.target		     = {
+			.uses_mmap   = true,
+		},
+	};
+	struct thread_map *threads = NULL;
+	struct cpu_map *cpus = NULL;
+	struct perf_evlist *evlist = NULL;
+	struct perf_evsel *evsel = NULL;
+	int found, err = -1;
+	const char *comm;
+
+	threads = thread_map__new(-1, getpid(), UINT_MAX);
+	CHECK_NOT_NULL__(threads);
+
+	cpus = cpu_map__new(NULL);
+	CHECK_NOT_NULL__(cpus);
+
+	evlist = perf_evlist__new();
+	CHECK_NOT_NULL__(evlist);
+
+	perf_evlist__set_maps(evlist, cpus, threads);
+
+	CHECK__(parse_events(evlist, "dummy:u"));
+	CHECK__(parse_events(evlist, "cycles:u"));
+
+	perf_evlist__config(evlist, &opts);
+
+	evsel = perf_evlist__first(evlist);
+
+	evsel->attr.comm = 1;
+	evsel->attr.disabled = 1;
+	evsel->attr.enable_on_exec = 0;
+
+	if (perf_evlist__open(evlist) < 0) {
+		fprintf(stderr, " (not supported)");
+		err = 0;
+		goto out_err;
+	}
+
+	CHECK__(perf_evlist__mmap(evlist, UINT_MAX, false));
+
+	/*
+	 * First, test that a 'comm' event can be found when the event is
+	 * enabled.
+	 */
+
+	perf_evlist__enable(evlist);
+
+	comm = "Test COMM 1";
+	CHECK__(prctl(PR_SET_NAME, (unsigned long)comm, 0, 0, 0));
+
+	perf_evlist__disable(evlist);
+
+	found = find_comm(evlist, comm);
+	if (found != 1) {
+		pr_debug("First time, failed to find tracking event.\n");
+		goto out_err;
+	}
+
+	/*
+	 * Secondly, test that a 'comm' event can be found when the event is
+	 * disabled with the dummy event still enabled.
+	 */
+
+	perf_evlist__enable(evlist);
+
+	evsel = perf_evlist__last(evlist);
+
+	CHECK__(perf_evlist__disable_event(evlist, evsel));
+
+	comm = "Test COMM 2";
+	CHECK__(prctl(PR_SET_NAME, (unsigned long)comm, 0, 0, 0));
+
+	perf_evlist__disable(evlist);
+
+	found = find_comm(evlist, comm);
+	if (found != 1) {
+		pr_debug("Seconf time, failed to find tracking event.\n");
+		goto out_err;
+	}
+
+	err = 0;
+
+out_err:
+	if (evlist) {
+		perf_evlist__disable(evlist);
+		perf_evlist__delete(evlist);
+	} else {
+		cpu_map__delete(cpus);
+		thread_map__delete(threads);
+	}
+
+	return err;
+}
diff --git a/tools/perf/tests/kmod-path.c b/tools/perf/tests/kmod-path.c
new file mode 100644
index 000000000..e8d7cbb93
--- /dev/null
+++ b/tools/perf/tests/kmod-path.c
@@ -0,0 +1,73 @@
+#include <stdbool.h>
+#include "tests.h"
+#include "dso.h"
+#include "debug.h"
+
+static int test(const char *path, bool alloc_name, bool alloc_ext,
+		bool kmod, bool comp, const char *name, const char *ext)
+{
+	struct kmod_path m;
+
+	memset(&m, 0x0, sizeof(m));
+
+	TEST_ASSERT_VAL("kmod_path__parse",
+			!__kmod_path__parse(&m, path, alloc_name, alloc_ext));
+
+	pr_debug("%s - alloc name %d, alloc ext %d, kmod %d, comp %d, name '%s', ext '%s'\n",
+		 path, alloc_name, alloc_ext, m.kmod, m.comp, m.name, m.ext);
+
+	TEST_ASSERT_VAL("wrong kmod", m.kmod == kmod);
+	TEST_ASSERT_VAL("wrong comp", m.comp == comp);
+
+	if (ext)
+		TEST_ASSERT_VAL("wrong ext", m.ext && !strcmp(ext, m.ext));
+	else
+		TEST_ASSERT_VAL("wrong ext", !m.ext);
+
+	if (name)
+		TEST_ASSERT_VAL("wrong name", m.name && !strcmp(name, m.name));
+	else
+		TEST_ASSERT_VAL("wrong name", !m.name);
+
+	free(m.name);
+	free(m.ext);
+	return 0;
+}
+
+#define T(path, an, ae, k, c, n, e) \
+	TEST_ASSERT_VAL("failed", !test(path, an, ae, k, c, n, e))
+
+int test__kmod_path__parse(void)
+{
+	/* path                alloc_name  alloc_ext   kmod  comp   name     ext */
+	T("/xxxx/xxxx/x-x.ko", true      , true      , true, false, "[x_x]", NULL);
+	T("/xxxx/xxxx/x-x.ko", false     , true      , true, false, NULL   , NULL);
+	T("/xxxx/xxxx/x-x.ko", true      , false     , true, false, "[x_x]", NULL);
+	T("/xxxx/xxxx/x-x.ko", false     , false     , true, false, NULL   , NULL);
+
+	/* path                alloc_name  alloc_ext   kmod  comp  name   ext */
+	T("/xxxx/xxxx/x.ko.gz", true     , true      , true, true, "[x]", "gz");
+	T("/xxxx/xxxx/x.ko.gz", false    , true      , true, true, NULL , "gz");
+	T("/xxxx/xxxx/x.ko.gz", true     , false     , true, true, "[x]", NULL);
+	T("/xxxx/xxxx/x.ko.gz", false    , false     , true, true, NULL , NULL);
+
+	/* path              alloc_name  alloc_ext  kmod   comp  name    ext */
+	T("/xxxx/xxxx/x.gz", true      , true     , false, true, "x.gz" ,"gz");
+	T("/xxxx/xxxx/x.gz", false     , true     , false, true, NULL   ,"gz");
+	T("/xxxx/xxxx/x.gz", true      , false    , false, true, "x.gz" , NULL);
+	T("/xxxx/xxxx/x.gz", false     , false    , false, true, NULL   , NULL);
+
+	/* path   alloc_name  alloc_ext  kmod   comp  name     ext */
+	T("x.gz", true      , true     , false, true, "x.gz", "gz");
+	T("x.gz", false     , true     , false, true, NULL  , "gz");
+	T("x.gz", true      , false    , false, true, "x.gz", NULL);
+	T("x.gz", false     , false    , false, true, NULL  , NULL);
+
+	/* path      alloc_name  alloc_ext  kmod  comp  name  ext */
+	T("x.ko.gz", true      , true     , true, true, "[x]", "gz");
+	T("x.ko.gz", false     , true     , true, true, NULL , "gz");
+	T("x.ko.gz", true      , false    , true, true, "[x]", NULL);
+	T("x.ko.gz", false     , false    , true, true, NULL , NULL);
+
+	return 0;
+}
diff --git a/tools/perf/tests/make b/tools/perf/tests/make
new file mode 100644
index 000000000..bff85324f
--- /dev/null
+++ b/tools/perf/tests/make
@@ -0,0 +1,232 @@
+PERF := .
+MK   := Makefile
+
+include config/Makefile.arch
+
+# FIXME looks like x86 is the only arch running tests ;-)
+# we need some IS_(32/64) flag to make this generic
+ifeq ($(ARCH)$(IS_64_BIT), x861)
+lib = lib64
+else
+lib = lib
+endif
+
+has = $(shell which $1 2>/dev/null)
+
+# standard single make variable specified
+make_clean_all      := clean all
+make_python_perf_so := python/perf.so
+make_debug          := DEBUG=1
+make_no_libperl     := NO_LIBPERL=1
+make_no_libpython   := NO_LIBPYTHON=1
+make_no_scripts     := NO_LIBPYTHON=1 NO_LIBPERL=1
+make_no_newt        := NO_NEWT=1
+make_no_slang       := NO_SLANG=1
+make_no_gtk2        := NO_GTK2=1
+make_no_ui          := NO_NEWT=1 NO_SLANG=1 NO_GTK2=1
+make_no_demangle    := NO_DEMANGLE=1
+make_no_libelf      := NO_LIBELF=1
+make_no_libunwind   := NO_LIBUNWIND=1
+make_no_libdw_dwarf_unwind := NO_LIBDW_DWARF_UNWIND=1
+make_no_backtrace   := NO_BACKTRACE=1
+make_no_libnuma     := NO_LIBNUMA=1
+make_no_libaudit    := NO_LIBAUDIT=1
+make_no_libbionic   := NO_LIBBIONIC=1
+make_tags           := tags
+make_cscope         := cscope
+make_help           := help
+make_doc            := doc
+make_perf_o           := perf.o
+make_util_map_o       := util/map.o
+make_util_pmu_bison_o := util/pmu-bison.o
+make_install        := install
+make_install_bin    := install-bin
+make_install_doc    := install-doc
+make_install_man    := install-man
+make_install_html   := install-html
+make_install_info   := install-info
+make_install_pdf    := install-pdf
+make_static         := LDFLAGS=-static
+
+# all the NO_* variable combined
+make_minimal        := NO_LIBPERL=1 NO_LIBPYTHON=1 NO_NEWT=1 NO_GTK2=1
+make_minimal        += NO_DEMANGLE=1 NO_LIBELF=1 NO_LIBUNWIND=1 NO_BACKTRACE=1
+make_minimal        += NO_LIBNUMA=1 NO_LIBAUDIT=1 NO_LIBBIONIC=1
+make_minimal        += NO_LIBDW_DWARF_UNWIND=1
+
+# $(run) contains all available tests
+run := make_pure
+run += make_clean_all
+run += make_python_perf_so
+run += make_debug
+run += make_no_libperl
+run += make_no_libpython
+run += make_no_scripts
+run += make_no_newt
+run += make_no_slang
+run += make_no_gtk2
+run += make_no_ui
+run += make_no_demangle
+run += make_no_libelf
+run += make_no_libunwind
+run += make_no_libdw_dwarf_unwind
+run += make_no_backtrace
+run += make_no_libnuma
+run += make_no_libaudit
+run += make_no_libbionic
+run += make_help
+run += make_doc
+run += make_perf_o
+run += make_util_map_o
+run += make_util_pmu_bison_o
+run += make_install
+run += make_install_bin
+# FIXME 'install-*' commented out till they're fixed
+# run += make_install_doc
+# run += make_install_man
+# run += make_install_html
+# run += make_install_info
+# run += make_install_pdf
+run += make_minimal
+run += make_static
+
+ifneq ($(call has,ctags),)
+run += make_tags
+endif
+ifneq ($(call has,cscope),)
+run += make_cscope
+endif
+
+# $(run_O) contains same portion of $(run) tests with '_O' attached
+# to distinguish O=... tests
+run_O := $(addsuffix _O,$(run))
+
+# disable some tests for O=...
+run_O := $(filter-out make_python_perf_so_O,$(run_O))
+
+# define test for each compile as 'test_NAME' variable
+# with the test itself as a value
+test_make_tags   = test -f tags
+test_make_cscope = test -f cscope.out
+
+test_make_tags_O   := $(test_make_tags)
+test_make_cscope_O := $(test_make_cscope)
+
+test_ok          := true
+test_make_help   := $(test_ok)
+test_make_doc    := $(test_ok)
+test_make_help_O := $(test_ok)
+test_make_doc_O  := $(test_ok)
+
+test_make_python_perf_so := test -f $(PERF)/python/perf.so
+
+test_make_perf_o           := test -f $(PERF)/perf.o
+test_make_util_map_o       := test -f $(PERF)/util/map.o
+test_make_util_pmu_bison_o := test -f $(PERF)/util/pmu-bison.o
+
+define test_dest_files
+  for file in $(1); do				\
+    if [ ! -x $$TMP_DEST/$$file ]; then		\
+      echo "  failed to find: $$file";		\
+    fi						\
+  done
+endef
+
+installed_files_bin := bin/perf
+installed_files_bin += etc/bash_completion.d/perf
+installed_files_bin += libexec/perf-core/perf-archive
+
+installed_files_plugins := $(lib)/traceevent/plugins/plugin_cfg80211.so
+installed_files_plugins += $(lib)/traceevent/plugins/plugin_scsi.so
+installed_files_plugins += $(lib)/traceevent/plugins/plugin_xen.so
+installed_files_plugins += $(lib)/traceevent/plugins/plugin_function.so
+installed_files_plugins += $(lib)/traceevent/plugins/plugin_sched_switch.so
+installed_files_plugins += $(lib)/traceevent/plugins/plugin_mac80211.so
+installed_files_plugins += $(lib)/traceevent/plugins/plugin_kvm.so
+installed_files_plugins += $(lib)/traceevent/plugins/plugin_kmem.so
+installed_files_plugins += $(lib)/traceevent/plugins/plugin_hrtimer.so
+installed_files_plugins += $(lib)/traceevent/plugins/plugin_jbd2.so
+
+installed_files_all := $(installed_files_bin)
+installed_files_all += $(installed_files_plugins)
+
+test_make_install       := $(call test_dest_files,$(installed_files_all))
+test_make_install_O     := $(call test_dest_files,$(installed_files_all))
+test_make_install_bin   := $(call test_dest_files,$(installed_files_bin))
+test_make_install_bin_O := $(call test_dest_files,$(installed_files_bin))
+
+# FIXME nothing gets installed
+test_make_install_man    := test -f $$TMP_DEST/share/man/man1/perf.1
+test_make_install_man_O  := $(test_make_install_man)
+
+# FIXME nothing gets installed
+test_make_install_doc    := $(test_ok)
+test_make_install_doc_O  := $(test_ok)
+
+# FIXME nothing gets installed
+test_make_install_html   := $(test_ok)
+test_make_install_html_O := $(test_ok)
+
+# FIXME nothing gets installed
+test_make_install_info   := $(test_ok)
+test_make_install_info_O := $(test_ok)
+
+# FIXME nothing gets installed
+test_make_install_pdf    := $(test_ok)
+test_make_install_pdf_O  := $(test_ok)
+
+test_make_python_perf_so_O    := test -f $$TMP_O/python/perf.so
+test_make_perf_o_O            := test -f $$TMP_O/perf.o
+test_make_util_map_o_O        := test -f $$TMP_O/util/map.o
+test_make_util_pmu_bison_o_O := test -f $$TMP_O/util/pmu-bison.o
+
+test_default = test -x $(PERF)/perf
+test = $(if $(test_$1),$(test_$1),$(test_default))
+
+test_default_O = test -x $$TMP_O/perf
+test_O = $(if $(test_$1),$(test_$1),$(test_default_O))
+
+all:
+
+ifdef DEBUG
+d := $(info run   $(run))
+d := $(info run_O $(run_O))
+endif
+
+MAKEFLAGS := --no-print-directory
+
+clean := @(cd $(PERF); make -s -f $(MK) clean >/dev/null)
+
+$(run):
+	$(call clean)
+	@TMP_DEST=$$(mktemp -d); \
+	cmd="cd $(PERF) && make -f $(MK) DESTDIR=$$TMP_DEST $($@)"; \
+	echo "- $@: $$cmd" && echo $$cmd > $@ && \
+	( eval $$cmd ) >> $@ 2>&1; \
+	echo "  test: $(call test,$@)" >> $@ 2>&1; \
+	$(call test,$@) && \
+	rm -rf $@ $$TMP_DEST || (cat $@ ; false)
+
+$(run_O):
+	$(call clean)
+	@TMP_O=$$(mktemp -d); \
+	TMP_DEST=$$(mktemp -d); \
+	cmd="cd $(PERF) && make -f $(MK) O=$$TMP_O DESTDIR=$$TMP_DEST $($(patsubst %_O,%,$@))"; \
+	echo "- $@: $$cmd" && echo $$cmd > $@ && \
+	( eval $$cmd ) >> $@ 2>&1 && \
+	echo "  test: $(call test_O,$@)" >> $@ 2>&1; \
+	$(call test_O,$@) && \
+	rm -rf $@ $$TMP_O $$TMP_DEST || (cat $@ ; false)
+
+tarpkg:
+	@cmd="$(PERF)/tests/perf-targz-src-pkg $(PERF)"; \
+	echo "- $@: $$cmd" && echo $$cmd > $@ && \
+	( eval $$cmd ) >> $@ 2>&1
+
+all: $(run) $(run_O) tarpkg
+	@echo OK
+
+out: $(run_O)
+	@echo OK
+
+.PHONY: all $(run) $(run_O) tarpkg clean
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
new file mode 100644
index 000000000..9b9622a33
--- /dev/null
+++ b/tools/perf/tests/mmap-basic.c
@@ -0,0 +1,149 @@
+#include "evlist.h"
+#include "evsel.h"
+#include "thread_map.h"
+#include "cpumap.h"
+#include "tests.h"
+
+/*
+ * This test will generate random numbers of calls to some getpid syscalls,
+ * then establish an mmap for a group of events that are created to monitor
+ * the syscalls.
+ *
+ * It will receive the events, using mmap, use its PERF_SAMPLE_ID generated
+ * sample.id field to map back to its respective perf_evsel instance.
+ *
+ * Then it checks if the number of syscalls reported as perf events by
+ * the kernel corresponds to the number of syscalls made.
+ */
+int test__basic_mmap(void)
+{
+	int err = -1;
+	union perf_event *event;
+	struct thread_map *threads;
+	struct cpu_map *cpus;
+	struct perf_evlist *evlist;
+	cpu_set_t cpu_set;
+	const char *syscall_names[] = { "getsid", "getppid", "getpgrp",
+					"getpgid", };
+	pid_t (*syscalls[])(void) = { (void *)getsid, getppid, getpgrp,
+				      (void*)getpgid };
+#define nsyscalls ARRAY_SIZE(syscall_names)
+	unsigned int nr_events[nsyscalls],
+		     expected_nr_events[nsyscalls], i, j;
+	struct perf_evsel *evsels[nsyscalls], *evsel;
+	char sbuf[STRERR_BUFSIZE];
+
+	threads = thread_map__new(-1, getpid(), UINT_MAX);
+	if (threads == NULL) {
+		pr_debug("thread_map__new\n");
+		return -1;
+	}
+
+	cpus = cpu_map__new(NULL);
+	if (cpus == NULL) {
+		pr_debug("cpu_map__new\n");
+		goto out_free_threads;
+	}
+
+	CPU_ZERO(&cpu_set);
+	CPU_SET(cpus->map[0], &cpu_set);
+	sched_setaffinity(0, sizeof(cpu_set), &cpu_set);
+	if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0) {
+		pr_debug("sched_setaffinity() failed on CPU %d: %s ",
+			 cpus->map[0], strerror_r(errno, sbuf, sizeof(sbuf)));
+		goto out_free_cpus;
+	}
+
+	evlist = perf_evlist__new();
+	if (evlist == NULL) {
+		pr_debug("perf_evlist__new\n");
+		goto out_free_cpus;
+	}
+
+	perf_evlist__set_maps(evlist, cpus, threads);
+
+	for (i = 0; i < nsyscalls; ++i) {
+		char name[64];
+
+		snprintf(name, sizeof(name), "sys_enter_%s", syscall_names[i]);
+		evsels[i] = perf_evsel__newtp("syscalls", name);
+		if (evsels[i] == NULL) {
+			pr_debug("perf_evsel__new\n");
+			goto out_delete_evlist;
+		}
+
+		evsels[i]->attr.wakeup_events = 1;
+		perf_evsel__set_sample_id(evsels[i], false);
+
+		perf_evlist__add(evlist, evsels[i]);
+
+		if (perf_evsel__open(evsels[i], cpus, threads) < 0) {
+			pr_debug("failed to open counter: %s, "
+				 "tweak /proc/sys/kernel/perf_event_paranoid?\n",
+				 strerror_r(errno, sbuf, sizeof(sbuf)));
+			goto out_delete_evlist;
+		}
+
+		nr_events[i] = 0;
+		expected_nr_events[i] = 1 + rand() % 127;
+	}
+
+	if (perf_evlist__mmap(evlist, 128, true) < 0) {
+		pr_debug("failed to mmap events: %d (%s)\n", errno,
+			 strerror_r(errno, sbuf, sizeof(sbuf)));
+		goto out_delete_evlist;
+	}
+
+	for (i = 0; i < nsyscalls; ++i)
+		for (j = 0; j < expected_nr_events[i]; ++j) {
+			int foo = syscalls[i]();
+			++foo;
+		}
+
+	while ((event = perf_evlist__mmap_read(evlist, 0)) != NULL) {
+		struct perf_sample sample;
+
+		if (event->header.type != PERF_RECORD_SAMPLE) {
+			pr_debug("unexpected %s event\n",
+				 perf_event__name(event->header.type));
+			goto out_delete_evlist;
+		}
+
+		err = perf_evlist__parse_sample(evlist, event, &sample);
+		if (err) {
+			pr_err("Can't parse sample, err = %d\n", err);
+			goto out_delete_evlist;
+		}
+
+		err = -1;
+		evsel = perf_evlist__id2evsel(evlist, sample.id);
+		if (evsel == NULL) {
+			pr_debug("event with id %" PRIu64
+				 " doesn't map to an evsel\n", sample.id);
+			goto out_delete_evlist;
+		}
+		nr_events[evsel->idx]++;
+		perf_evlist__mmap_consume(evlist, 0);
+	}
+
+	err = 0;
+	evlist__for_each(evlist, evsel) {
+		if (nr_events[evsel->idx] != expected_nr_events[evsel->idx]) {
+			pr_debug("expected %d %s events, got %d\n",
+				 expected_nr_events[evsel->idx],
+				 perf_evsel__name(evsel), nr_events[evsel->idx]);
+			err = -1;
+			goto out_delete_evlist;
+		}
+	}
+
+out_delete_evlist:
+	perf_evlist__delete(evlist);
+	cpus	= NULL;
+	threads = NULL;
+out_free_cpus:
+	cpu_map__delete(cpus);
+out_free_threads:
+	thread_map__delete(threads);
+	return err;
+}
diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c
new file mode 100644
index 000000000..2113f1c86
--- /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,
+				      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/open-syscall-all-cpus.c b/tools/perf/tests/open-syscall-all-cpus.c
new file mode 100644
index 000000000..3ec885c48
--- /dev/null
+++ b/tools/perf/tests/open-syscall-all-cpus.c
@@ -0,0 +1,115 @@
+#include "evsel.h"
+#include "tests.h"
+#include "thread_map.h"
+#include "cpumap.h"
+#include "debug.h"
+
+int test__open_syscall_event_on_all_cpus(void)
+{
+	int err = -1, fd, cpu;
+	struct cpu_map *cpus;
+	struct perf_evsel *evsel;
+	unsigned int nr_open_calls = 111, i;
+	cpu_set_t cpu_set;
+	struct thread_map *threads = thread_map__new(-1, getpid(), UINT_MAX);
+	char sbuf[STRERR_BUFSIZE];
+
+	if (threads == NULL) {
+		pr_debug("thread_map__new\n");
+		return -1;
+	}
+
+	cpus = cpu_map__new(NULL);
+	if (cpus == NULL) {
+		pr_debug("cpu_map__new\n");
+		goto out_thread_map_delete;
+	}
+
+	CPU_ZERO(&cpu_set);
+
+	evsel = perf_evsel__newtp("syscalls", "sys_enter_open");
+	if (evsel == NULL) {
+		if (tracefs_configured())
+			pr_debug("is tracefs mounted on /sys/kernel/tracing?\n");
+		else if (debugfs_configured())
+			pr_debug("is debugfs mounted on /sys/kernel/debug?\n");
+		else
+			pr_debug("Neither tracefs or debugfs is enabled in this kernel\n");
+		goto out_thread_map_delete;
+	}
+
+	if (perf_evsel__open(evsel, cpus, threads) < 0) {
+		pr_debug("failed to open counter: %s, "
+			 "tweak /proc/sys/kernel/perf_event_paranoid?\n",
+			 strerror_r(errno, sbuf, sizeof(sbuf)));
+		goto out_evsel_delete;
+	}
+
+	for (cpu = 0; cpu < cpus->nr; ++cpu) {
+		unsigned int ncalls = nr_open_calls + cpu;
+		/*
+		 * XXX eventually lift this restriction in a way that
+		 * keeps perf building on older glibc installations
+		 * without CPU_ALLOC. 1024 cpus in 2010 still seems
+		 * a reasonable upper limit tho :-)
+		 */
+		if (cpus->map[cpu] >= CPU_SETSIZE) {
+			pr_debug("Ignoring CPU %d\n", cpus->map[cpu]);
+			continue;
+		}
+
+		CPU_SET(cpus->map[cpu], &cpu_set);
+		if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0) {
+			pr_debug("sched_setaffinity() failed on CPU %d: %s ",
+				 cpus->map[cpu],
+				 strerror_r(errno, sbuf, sizeof(sbuf)));
+			goto out_close_fd;
+		}
+		for (i = 0; i < ncalls; ++i) {
+			fd = open("/etc/passwd", O_RDONLY);
+			close(fd);
+		}
+		CPU_CLR(cpus->map[cpu], &cpu_set);
+	}
+
+	/*
+	 * Here we need to explicitely preallocate the counts, as if
+	 * we use the auto allocation it will allocate just for 1 cpu,
+	 * as we start by cpu 0.
+	 */
+	if (perf_evsel__alloc_counts(evsel, cpus->nr) < 0) {
+		pr_debug("perf_evsel__alloc_counts(ncpus=%d)\n", cpus->nr);
+		goto out_close_fd;
+	}
+
+	err = 0;
+
+	for (cpu = 0; cpu < cpus->nr; ++cpu) {
+		unsigned int expected;
+
+		if (cpus->map[cpu] >= CPU_SETSIZE)
+			continue;
+
+		if (perf_evsel__read_on_cpu(evsel, cpu, 0) < 0) {
+			pr_debug("perf_evsel__read_on_cpu\n");
+			err = -1;
+			break;
+		}
+
+		expected = nr_open_calls + cpu;
+		if (evsel->counts->cpu[cpu].val != expected) {
+			pr_debug("perf_evsel__read_on_cpu: expected to intercept %d calls on cpu %d, got %" PRIu64 "\n",
+				 expected, cpus->map[cpu], evsel->counts->cpu[cpu].val);
+			err = -1;
+		}
+	}
+
+	perf_evsel__free_counts(evsel);
+out_close_fd:
+	perf_evsel__close_fd(evsel, 1, threads->nr);
+out_evsel_delete:
+	perf_evsel__delete(evsel);
+out_thread_map_delete:
+	thread_map__delete(threads);
+	return err;
+}
diff --git a/tools/perf/tests/open-syscall-tp-fields.c b/tools/perf/tests/open-syscall-tp-fields.c
new file mode 100644
index 000000000..127dcae0b
--- /dev/null
+++ b/tools/perf/tests/open-syscall-tp-fields.c
@@ -0,0 +1,121 @@
+#include "perf.h"
+#include "evlist.h"
+#include "evsel.h"
+#include "thread_map.h"
+#include "tests.h"
+#include "debug.h"
+
+int test__syscall_open_tp_fields(void)
+{
+	struct record_opts opts = {
+		.target = {
+			.uid = UINT_MAX,
+			.uses_mmap = true,
+		},
+		.no_buffering = true,
+		.freq	      = 1,
+		.mmap_pages   = 256,
+		.raw_samples  = true,
+	};
+	const char *filename = "/etc/passwd";
+	int flags = O_RDONLY | O_DIRECTORY;
+	struct perf_evlist *evlist = perf_evlist__new();
+	struct perf_evsel *evsel;
+	int err = -1, i, nr_events = 0, nr_polls = 0;
+	char sbuf[STRERR_BUFSIZE];
+
+	if (evlist == NULL) {
+		pr_debug("%s: perf_evlist__new\n", __func__);
+		goto out;
+	}
+
+	evsel = perf_evsel__newtp("syscalls", "sys_enter_open");
+	if (evsel == NULL) {
+		pr_debug("%s: perf_evsel__newtp\n", __func__);
+		goto out_delete_evlist;
+	}
+
+	perf_evlist__add(evlist, evsel);
+
+	err = perf_evlist__create_maps(evlist, &opts.target);
+	if (err < 0) {
+		pr_debug("%s: perf_evlist__create_maps\n", __func__);
+		goto out_delete_evlist;
+	}
+
+	perf_evsel__config(evsel, &opts);
+
+	evlist->threads->map[0] = getpid();
+
+	err = perf_evlist__open(evlist);
+	if (err < 0) {
+		pr_debug("perf_evlist__open: %s\n",
+			 strerror_r(errno, sbuf, sizeof(sbuf)));
+		goto out_delete_evlist;
+	}
+
+	err = perf_evlist__mmap(evlist, UINT_MAX, false);
+	if (err < 0) {
+		pr_debug("perf_evlist__mmap: %s\n",
+			 strerror_r(errno, sbuf, sizeof(sbuf)));
+		goto out_delete_evlist;
+	}
+
+	perf_evlist__enable(evlist);
+
+	/*
+	 * Generate the event:
+	 */
+	open(filename, flags);
+
+	while (1) {
+		int before = nr_events;
+
+		for (i = 0; i < evlist->nr_mmaps; i++) {
+			union perf_event *event;
+
+			while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
+				const u32 type = event->header.type;
+				int tp_flags;
+				struct perf_sample sample;
+
+				++nr_events;
+
+				if (type != PERF_RECORD_SAMPLE) {
+					perf_evlist__mmap_consume(evlist, i);
+					continue;
+				}
+
+				err = perf_evsel__parse_sample(evsel, event, &sample);
+				if (err) {
+					pr_err("Can't parse sample, err = %d\n", err);
+					goto out_delete_evlist;
+				}
+
+				tp_flags = perf_evsel__intval(evsel, &sample, "flags");
+
+				if (flags != tp_flags) {
+					pr_debug("%s: Expected flags=%#x, got %#x\n",
+						 __func__, flags, tp_flags);
+					goto out_delete_evlist;
+				}
+
+				goto out_ok;
+			}
+		}
+
+		if (nr_events == before)
+			perf_evlist__poll(evlist, 10);
+
+		if (++nr_polls > 5) {
+			pr_debug("%s: no events!\n", __func__);
+			goto out_delete_evlist;
+		}
+	}
+out_ok:
+	err = 0;
+out_delete_evlist:
+	perf_evlist__delete(evlist);
+out:
+	return err;
+}
diff --git a/tools/perf/tests/open-syscall.c b/tools/perf/tests/open-syscall.c
new file mode 100644
index 000000000..07aa319bf
--- /dev/null
+++ b/tools/perf/tests/open-syscall.c
@@ -0,0 +1,61 @@
+#include "thread_map.h"
+#include "evsel.h"
+#include "debug.h"
+#include "tests.h"
+
+int test__open_syscall_event(void)
+{
+	int err = -1, fd;
+	struct perf_evsel *evsel;
+	unsigned int nr_open_calls = 111, i;
+	struct thread_map *threads = thread_map__new(-1, getpid(), UINT_MAX);
+	char sbuf[STRERR_BUFSIZE];
+
+	if (threads == NULL) {
+		pr_debug("thread_map__new\n");
+		return -1;
+	}
+
+	evsel = perf_evsel__newtp("syscalls", "sys_enter_open");
+	if (evsel == NULL) {
+		if (tracefs_configured())
+			pr_debug("is tracefs mounted on /sys/kernel/tracing?\n");
+		else if (debugfs_configured())
+			pr_debug("is debugfs mounted on /sys/kernel/debug?\n");
+		else
+			pr_debug("Neither tracefs or debugfs is enabled in this kernel\n");
+		goto out_thread_map_delete;
+	}
+
+	if (perf_evsel__open_per_thread(evsel, threads) < 0) {
+		pr_debug("failed to open counter: %s, "
+			 "tweak /proc/sys/kernel/perf_event_paranoid?\n",
+			 strerror_r(errno, sbuf, sizeof(sbuf)));
+		goto out_evsel_delete;
+	}
+
+	for (i = 0; i < nr_open_calls; ++i) {
+		fd = open("/etc/passwd", O_RDONLY);
+		close(fd);
+	}
+
+	if (perf_evsel__read_on_cpu(evsel, 0, 0) < 0) {
+		pr_debug("perf_evsel__read_on_cpu\n");
+		goto out_close_fd;
+	}
+
+	if (evsel->counts->cpu[0].val != nr_open_calls) {
+		pr_debug("perf_evsel__read_on_cpu: expected to intercept %d calls, got %" PRIu64 "\n",
+			 nr_open_calls, evsel->counts->cpu[0].val);
+		goto out_close_fd;
+	}
+
+	err = 0;
+out_close_fd:
+	perf_evsel__close_fd(evsel, 1, threads->nr);
+out_evsel_delete:
+	perf_evsel__delete(evsel);
+out_thread_map_delete:
+	thread_map__delete(threads);
+	return err;
+}
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
new file mode 100644
index 000000000..3de744961
--- /dev/null
+++ b/tools/perf/tests/parse-events.c
@@ -0,0 +1,1734 @@
+
+#include "parse-events.h"
+#include "evsel.h"
+#include "evlist.h"
+#include <api/fs/fs.h>
+#include <api/fs/tracefs.h>
+#include <api/fs/debugfs.h>
+#include "tests.h"
+#include "debug.h"
+#include <linux/hw_breakpoint.h>
+
+#define PERF_TP_SAMPLE_TYPE (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | \
+			     PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD)
+
+static int test__checkevent_tracepoint(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong number of groups", 0 == evlist->nr_groups);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_TRACEPOINT == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong sample_type",
+		PERF_TP_SAMPLE_TYPE == evsel->attr.sample_type);
+	TEST_ASSERT_VAL("wrong sample_period", 1 == evsel->attr.sample_period);
+	return 0;
+}
+
+static int test__checkevent_tracepoint_multi(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+
+	TEST_ASSERT_VAL("wrong number of entries", evlist->nr_entries > 1);
+	TEST_ASSERT_VAL("wrong number of groups", 0 == evlist->nr_groups);
+
+	evlist__for_each(evlist, evsel) {
+		TEST_ASSERT_VAL("wrong type",
+			PERF_TYPE_TRACEPOINT == evsel->attr.type);
+		TEST_ASSERT_VAL("wrong sample_type",
+			PERF_TP_SAMPLE_TYPE == evsel->attr.sample_type);
+		TEST_ASSERT_VAL("wrong sample_period",
+			1 == evsel->attr.sample_period);
+	}
+	return 0;
+}
+
+static int test__checkevent_raw(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config", 0x1a == evsel->attr.config);
+	return 0;
+}
+
+static int test__checkevent_numeric(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong type", 1 == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config", 1 == evsel->attr.config);
+	return 0;
+}
+
+static int test__checkevent_symbolic_name(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_INSTRUCTIONS == evsel->attr.config);
+	return 0;
+}
+
+static int test__checkevent_symbolic_name_config(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong period",
+			100000 == evsel->attr.sample_period);
+	TEST_ASSERT_VAL("wrong config1",
+			0 == evsel->attr.config1);
+	TEST_ASSERT_VAL("wrong config2",
+			1 == evsel->attr.config2);
+	return 0;
+}
+
+static int test__checkevent_symbolic_alias(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_SOFTWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_SW_PAGE_FAULTS == evsel->attr.config);
+	return 0;
+}
+
+static int test__checkevent_genhw(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HW_CACHE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config", (1 << 16) == evsel->attr.config);
+	return 0;
+}
+
+static int test__checkevent_breakpoint(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_BREAKPOINT == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config", 0 == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong bp_type", (HW_BREAKPOINT_R | HW_BREAKPOINT_W) ==
+					 evsel->attr.bp_type);
+	TEST_ASSERT_VAL("wrong bp_len", HW_BREAKPOINT_LEN_4 ==
+					evsel->attr.bp_len);
+	return 0;
+}
+
+static int test__checkevent_breakpoint_x(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_BREAKPOINT == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config", 0 == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong bp_type",
+			HW_BREAKPOINT_X == evsel->attr.bp_type);
+	TEST_ASSERT_VAL("wrong bp_len", sizeof(long) == evsel->attr.bp_len);
+	return 0;
+}
+
+static int test__checkevent_breakpoint_r(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong type",
+			PERF_TYPE_BREAKPOINT == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config", 0 == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong bp_type",
+			HW_BREAKPOINT_R == evsel->attr.bp_type);
+	TEST_ASSERT_VAL("wrong bp_len",
+			HW_BREAKPOINT_LEN_4 == evsel->attr.bp_len);
+	return 0;
+}
+
+static int test__checkevent_breakpoint_w(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong type",
+			PERF_TYPE_BREAKPOINT == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config", 0 == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong bp_type",
+			HW_BREAKPOINT_W == evsel->attr.bp_type);
+	TEST_ASSERT_VAL("wrong bp_len",
+			HW_BREAKPOINT_LEN_4 == evsel->attr.bp_len);
+	return 0;
+}
+
+static int test__checkevent_breakpoint_rw(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong type",
+			PERF_TYPE_BREAKPOINT == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config", 0 == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong bp_type",
+		(HW_BREAKPOINT_R|HW_BREAKPOINT_W) == evsel->attr.bp_type);
+	TEST_ASSERT_VAL("wrong bp_len",
+			HW_BREAKPOINT_LEN_4 == evsel->attr.bp_len);
+	return 0;
+}
+
+static int test__checkevent_tracepoint_modifier(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+
+	return test__checkevent_tracepoint(evlist);
+}
+
+static int
+test__checkevent_tracepoint_multi_modifier(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+
+	TEST_ASSERT_VAL("wrong number of entries", evlist->nr_entries > 1);
+
+	evlist__for_each(evlist, evsel) {
+		TEST_ASSERT_VAL("wrong exclude_user",
+				!evsel->attr.exclude_user);
+		TEST_ASSERT_VAL("wrong exclude_kernel",
+				evsel->attr.exclude_kernel);
+		TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+		TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	}
+
+	return test__checkevent_tracepoint_multi(evlist);
+}
+
+static int test__checkevent_raw_modifier(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip);
+
+	return test__checkevent_raw(evlist);
+}
+
+static int test__checkevent_numeric_modifier(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip);
+
+	return test__checkevent_numeric(evlist);
+}
+
+static int test__checkevent_symbolic_name_modifier(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+
+	return test__checkevent_symbolic_name(evlist);
+}
+
+static int test__checkevent_exclude_host_modifier(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host);
+
+	return test__checkevent_symbolic_name(evlist);
+}
+
+static int test__checkevent_exclude_guest_modifier(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+
+	return test__checkevent_symbolic_name(evlist);
+}
+
+static int test__checkevent_symbolic_alias_modifier(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+
+	return test__checkevent_symbolic_alias(evlist);
+}
+
+static int test__checkevent_genhw_modifier(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip);
+
+	return test__checkevent_genhw(evlist);
+}
+
+static int test__checkevent_exclude_idle_modifier(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong exclude idle", evsel->attr.exclude_idle);
+	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+
+	return test__checkevent_symbolic_name(evlist);
+}
+
+static int test__checkevent_exclude_idle_modifier_1(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong exclude idle", evsel->attr.exclude_idle);
+	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+
+	return test__checkevent_symbolic_name(evlist);
+}
+
+static int test__checkevent_breakpoint_modifier(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong name",
+			!strcmp(perf_evsel__name(evsel), "mem:0:u"));
+
+	return test__checkevent_breakpoint(evlist);
+}
+
+static int test__checkevent_breakpoint_x_modifier(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong name",
+			!strcmp(perf_evsel__name(evsel), "mem:0:x:k"));
+
+	return test__checkevent_breakpoint_x(evlist);
+}
+
+static int test__checkevent_breakpoint_r_modifier(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong name",
+			!strcmp(perf_evsel__name(evsel), "mem:0:r:hp"));
+
+	return test__checkevent_breakpoint_r(evlist);
+}
+
+static int test__checkevent_breakpoint_w_modifier(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong name",
+			!strcmp(perf_evsel__name(evsel), "mem:0:w:up"));
+
+	return test__checkevent_breakpoint_w(evlist);
+}
+
+static int test__checkevent_breakpoint_rw_modifier(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong name",
+			!strcmp(perf_evsel__name(evsel), "mem:0:rw:kp"));
+
+	return test__checkevent_breakpoint_rw(evlist);
+}
+
+static int test__checkevent_pmu(struct perf_evlist *evlist)
+{
+
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",    10 == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong config1",    1 == evsel->attr.config1);
+	TEST_ASSERT_VAL("wrong config2",    3 == evsel->attr.config2);
+	TEST_ASSERT_VAL("wrong period",  1000 == evsel->attr.sample_period);
+
+	return 0;
+}
+
+static int test__checkevent_list(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong number of entries", 3 == evlist->nr_entries);
+
+	/* r1 */
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config", 1 == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong config1", 0 == evsel->attr.config1);
+	TEST_ASSERT_VAL("wrong config2", 0 == evsel->attr.config2);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+
+	/* syscalls:sys_enter_open:k */
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_TRACEPOINT == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong sample_type",
+		PERF_TP_SAMPLE_TYPE == evsel->attr.sample_type);
+	TEST_ASSERT_VAL("wrong sample_period", 1 == evsel->attr.sample_period);
+	TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+
+	/* 1:1:hp */
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", 1 == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config", 1 == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip);
+
+	return 0;
+}
+
+static int test__checkevent_pmu_name(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	/* cpu/config=1,name=krava/u */
+	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",  1 == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong name", !strcmp(perf_evsel__name(evsel), "krava"));
+
+	/* cpu/config=2/u" */
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",  2 == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong name",
+			!strcmp(perf_evsel__name(evsel), "cpu/config=2/u"));
+
+	return 0;
+}
+
+static int test__checkevent_pmu_events(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong exclude_user",
+			!evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel",
+			evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong pinned", !evsel->attr.pinned);
+
+	return 0;
+}
+
+
+static int test__checkevent_pmu_events_mix(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	/* pmu-event:u */
+	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong exclude_user",
+			!evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel",
+			evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong pinned", !evsel->attr.pinned);
+
+	/* cpu/pmu-event/u*/
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong exclude_user",
+			!evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel",
+			evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong pinned", !evsel->attr.pinned);
+
+	return 0;
+}
+
+static int test__checkterms_simple(struct list_head *terms)
+{
+	struct parse_events_term *term;
+
+	/* config=10 */
+	term = list_entry(terms->next, struct parse_events_term, list);
+	TEST_ASSERT_VAL("wrong type term",
+			term->type_term == PARSE_EVENTS__TERM_TYPE_CONFIG);
+	TEST_ASSERT_VAL("wrong type val",
+			term->type_val == PARSE_EVENTS__TERM_TYPE_NUM);
+	TEST_ASSERT_VAL("wrong val", term->val.num == 10);
+	TEST_ASSERT_VAL("wrong config", !term->config);
+
+	/* config1 */
+	term = list_entry(term->list.next, struct parse_events_term, list);
+	TEST_ASSERT_VAL("wrong type term",
+			term->type_term == PARSE_EVENTS__TERM_TYPE_CONFIG1);
+	TEST_ASSERT_VAL("wrong type val",
+			term->type_val == PARSE_EVENTS__TERM_TYPE_NUM);
+	TEST_ASSERT_VAL("wrong val", term->val.num == 1);
+	TEST_ASSERT_VAL("wrong config", !term->config);
+
+	/* config2=3 */
+	term = list_entry(term->list.next, struct parse_events_term, list);
+	TEST_ASSERT_VAL("wrong type term",
+			term->type_term == PARSE_EVENTS__TERM_TYPE_CONFIG2);
+	TEST_ASSERT_VAL("wrong type val",
+			term->type_val == PARSE_EVENTS__TERM_TYPE_NUM);
+	TEST_ASSERT_VAL("wrong val", term->val.num == 3);
+	TEST_ASSERT_VAL("wrong config", !term->config);
+
+	/* umask=1*/
+	term = list_entry(term->list.next, struct parse_events_term, list);
+	TEST_ASSERT_VAL("wrong type term",
+			term->type_term == PARSE_EVENTS__TERM_TYPE_USER);
+	TEST_ASSERT_VAL("wrong type val",
+			term->type_val == PARSE_EVENTS__TERM_TYPE_NUM);
+	TEST_ASSERT_VAL("wrong val", term->val.num == 1);
+	TEST_ASSERT_VAL("wrong config", !strcmp(term->config, "umask"));
+
+	return 0;
+}
+
+static int test__group1(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel, *leader;
+
+	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups);
+
+	/* instructions:k */
+	evsel = leader = perf_evlist__first(evlist);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_INSTRUCTIONS == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
+	TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
+
+	/* cycles:upp */
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	/* use of precise requires exclude_guest */
+	TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip == 2);
+	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
+	TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
+
+	return 0;
+}
+
+static int test__group2(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel, *leader;
+
+	TEST_ASSERT_VAL("wrong number of entries", 3 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups);
+
+	/* faults + :ku modifier */
+	evsel = leader = perf_evlist__first(evlist);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_SOFTWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_SW_PAGE_FAULTS == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
+	TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
+
+	/* cache-references + :u modifier */
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CACHE_REFERENCES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
+	TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
+
+	/* cycles:k */
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
+
+	return 0;
+}
+
+static int test__group3(struct perf_evlist *evlist __maybe_unused)
+{
+	struct perf_evsel *evsel, *leader;
+
+	TEST_ASSERT_VAL("wrong number of entries", 5 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong number of groups", 2 == evlist->nr_groups);
+
+	/* group1 syscalls:sys_enter_open:H */
+	evsel = leader = perf_evlist__first(evlist);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_TRACEPOINT == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong sample_type",
+		PERF_TP_SAMPLE_TYPE == evsel->attr.sample_type);
+	TEST_ASSERT_VAL("wrong sample_period", 1 == evsel->attr.sample_period);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong group name",
+		!strcmp(leader->group_name, "group1"));
+	TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
+	TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
+
+	/* group1 cycles:kppp */
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	/* use of precise requires exclude_guest */
+	TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip == 3);
+	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
+	TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
+
+	/* group2 cycles + G modifier */
+	evsel = leader = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong group name",
+		!strcmp(leader->group_name, "group2"));
+	TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
+	TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
+
+	/* group2 1:3 + G modifier */
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", 1 == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config", 3 == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
+	TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
+
+	/* instructions:u */
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_INSTRUCTIONS == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
+
+	return 0;
+}
+
+static int test__group4(struct perf_evlist *evlist __maybe_unused)
+{
+	struct perf_evsel *evsel, *leader;
+
+	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups);
+
+	/* cycles:u + p */
+	evsel = leader = perf_evlist__first(evlist);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	/* use of precise requires exclude_guest */
+	TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip == 1);
+	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
+	TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
+
+	/* instructions:kp + p */
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_INSTRUCTIONS == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	/* use of precise requires exclude_guest */
+	TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip == 2);
+	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
+	TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
+
+	return 0;
+}
+
+static int test__group5(struct perf_evlist *evlist __maybe_unused)
+{
+	struct perf_evsel *evsel, *leader;
+
+	TEST_ASSERT_VAL("wrong number of entries", 5 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong number of groups", 2 == evlist->nr_groups);
+
+	/* cycles + G */
+	evsel = leader = perf_evlist__first(evlist);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
+	TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
+
+	/* instructions + G */
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_INSTRUCTIONS == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
+	TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
+
+	/* cycles:G */
+	evsel = leader = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
+	TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
+
+	/* instructions:G */
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_INSTRUCTIONS == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
+
+	/* cycles */
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+
+	return 0;
+}
+
+static int test__group_gh1(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel, *leader;
+
+	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups);
+
+	/* cycles + :H group modifier */
+	evsel = leader = perf_evlist__first(evlist);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
+
+	/* cache-misses:G + :H group modifier */
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CACHE_MISSES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
+
+	return 0;
+}
+
+static int test__group_gh2(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel, *leader;
+
+	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups);
+
+	/* cycles + :G group modifier */
+	evsel = leader = perf_evlist__first(evlist);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
+
+	/* cache-misses:H + :G group modifier */
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CACHE_MISSES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
+
+	return 0;
+}
+
+static int test__group_gh3(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel, *leader;
+
+	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups);
+
+	/* cycles:G + :u group modifier */
+	evsel = leader = perf_evlist__first(evlist);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
+
+	/* cache-misses:H + :u group modifier */
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CACHE_MISSES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
+
+	return 0;
+}
+
+static int test__group_gh4(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel, *leader;
+
+	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups);
+
+	/* cycles:G + :uG group modifier */
+	evsel = leader = perf_evlist__first(evlist);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
+
+	/* cache-misses:H + :uG group modifier */
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CACHE_MISSES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
+
+	return 0;
+}
+
+static int test__leader_sample1(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel, *leader;
+
+	TEST_ASSERT_VAL("wrong number of entries", 3 == evlist->nr_entries);
+
+	/* cycles - sampling group leader */
+	evsel = leader = perf_evlist__first(evlist);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
+	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+	TEST_ASSERT_VAL("wrong sample_read", evsel->sample_read);
+
+	/* cache-misses - not sampling */
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CACHE_MISSES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+	TEST_ASSERT_VAL("wrong sample_read", evsel->sample_read);
+
+	/* branch-misses - not sampling */
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_BRANCH_MISSES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
+	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+	TEST_ASSERT_VAL("wrong sample_read", evsel->sample_read);
+
+	return 0;
+}
+
+static int test__leader_sample2(struct perf_evlist *evlist __maybe_unused)
+{
+	struct perf_evsel *evsel, *leader;
+
+	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries);
+
+	/* instructions - sampling group leader */
+	evsel = leader = perf_evlist__first(evlist);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_INSTRUCTIONS == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
+	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+	TEST_ASSERT_VAL("wrong sample_read", evsel->sample_read);
+
+	/* branch-misses - not sampling */
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_BRANCH_MISSES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
+	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+	TEST_ASSERT_VAL("wrong sample_read", evsel->sample_read);
+
+	return 0;
+}
+
+static int test__checkevent_pinned_modifier(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong pinned", evsel->attr.pinned);
+
+	return test__checkevent_symbolic_name(evlist);
+}
+
+static int test__pinned_group(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel, *leader;
+
+	TEST_ASSERT_VAL("wrong number of entries", 3 == evlist->nr_entries);
+
+	/* cycles - group leader */
+	evsel = leader = perf_evlist__first(evlist);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
+	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+	TEST_ASSERT_VAL("wrong pinned", evsel->attr.pinned);
+
+	/* cache-misses - can not be pinned, but will go on with the leader */
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CACHE_MISSES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong pinned", !evsel->attr.pinned);
+
+	/* branch-misses - ditto */
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_BRANCH_MISSES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong pinned", !evsel->attr.pinned);
+
+	return 0;
+}
+
+static int test__checkevent_breakpoint_len(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_BREAKPOINT == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config", 0 == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong bp_type", (HW_BREAKPOINT_R | HW_BREAKPOINT_W) ==
+					 evsel->attr.bp_type);
+	TEST_ASSERT_VAL("wrong bp_len", HW_BREAKPOINT_LEN_1 ==
+					evsel->attr.bp_len);
+
+	return 0;
+}
+
+static int test__checkevent_breakpoint_len_w(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_BREAKPOINT == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config", 0 == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong bp_type", HW_BREAKPOINT_W ==
+					 evsel->attr.bp_type);
+	TEST_ASSERT_VAL("wrong bp_len", HW_BREAKPOINT_LEN_2 ==
+					evsel->attr.bp_len);
+
+	return 0;
+}
+
+static int
+test__checkevent_breakpoint_len_rw_modifier(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+
+	return test__checkevent_breakpoint_rw(evlist);
+}
+
+static int count_tracepoints(void)
+{
+	char events_path[PATH_MAX];
+	struct dirent *events_ent;
+	const char *mountpoint;
+	DIR *events_dir;
+	int cnt = 0;
+
+	mountpoint = tracefs_find_mountpoint();
+	if (mountpoint) {
+		scnprintf(events_path, PATH_MAX, "%s/events",
+			  mountpoint);
+	} else {
+		mountpoint = debugfs_find_mountpoint();
+		scnprintf(events_path, PATH_MAX, "%s/tracing/events",
+			  mountpoint);
+	}
+
+	events_dir = opendir(events_path);
+
+	TEST_ASSERT_VAL("Can't open events dir", events_dir);
+
+	while ((events_ent = readdir(events_dir))) {
+		char sys_path[PATH_MAX];
+		struct dirent *sys_ent;
+		DIR *sys_dir;
+
+		if (!strcmp(events_ent->d_name, ".")
+		    || !strcmp(events_ent->d_name, "..")
+		    || !strcmp(events_ent->d_name, "enable")
+		    || !strcmp(events_ent->d_name, "header_event")
+		    || !strcmp(events_ent->d_name, "header_page"))
+			continue;
+
+		scnprintf(sys_path, PATH_MAX, "%s/%s",
+			  events_path, events_ent->d_name);
+
+		sys_dir = opendir(sys_path);
+		TEST_ASSERT_VAL("Can't open sys dir", sys_dir);
+
+		while ((sys_ent = readdir(sys_dir))) {
+			if (!strcmp(sys_ent->d_name, ".")
+			    || !strcmp(sys_ent->d_name, "..")
+			    || !strcmp(sys_ent->d_name, "enable")
+			    || !strcmp(sys_ent->d_name, "filter"))
+				continue;
+
+			cnt++;
+		}
+
+		closedir(sys_dir);
+	}
+
+	closedir(events_dir);
+	return cnt;
+}
+
+static int test__all_tracepoints(struct perf_evlist *evlist)
+{
+	TEST_ASSERT_VAL("wrong events count",
+			count_tracepoints() == evlist->nr_entries);
+
+	return test__checkevent_tracepoint_multi(evlist);
+}
+
+struct evlist_test {
+	const char *name;
+	__u32 type;
+	const int id;
+	int (*check)(struct perf_evlist *evlist);
+};
+
+static struct evlist_test test__events[] = {
+	{
+		.name  = "syscalls:sys_enter_open",
+		.check = test__checkevent_tracepoint,
+		.id    = 0,
+	},
+	{
+		.name  = "syscalls:*",
+		.check = test__checkevent_tracepoint_multi,
+		.id    = 1,
+	},
+	{
+		.name  = "r1a",
+		.check = test__checkevent_raw,
+		.id    = 2,
+	},
+	{
+		.name  = "1:1",
+		.check = test__checkevent_numeric,
+		.id    = 3,
+	},
+	{
+		.name  = "instructions",
+		.check = test__checkevent_symbolic_name,
+		.id    = 4,
+	},
+	{
+		.name  = "cycles/period=100000,config2/",
+		.check = test__checkevent_symbolic_name_config,
+		.id    = 5,
+	},
+	{
+		.name  = "faults",
+		.check = test__checkevent_symbolic_alias,
+		.id    = 6,
+	},
+	{
+		.name  = "L1-dcache-load-miss",
+		.check = test__checkevent_genhw,
+		.id    = 7,
+	},
+	{
+		.name  = "mem:0",
+		.check = test__checkevent_breakpoint,
+		.id    = 8,
+	},
+	{
+		.name  = "mem:0:x",
+		.check = test__checkevent_breakpoint_x,
+		.id    = 9,
+	},
+	{
+		.name  = "mem:0:r",
+		.check = test__checkevent_breakpoint_r,
+		.id    = 10,
+	},
+	{
+		.name  = "mem:0:w",
+		.check = test__checkevent_breakpoint_w,
+		.id    = 11,
+	},
+	{
+		.name  = "syscalls:sys_enter_open:k",
+		.check = test__checkevent_tracepoint_modifier,
+		.id    = 12,
+	},
+	{
+		.name  = "syscalls:*:u",
+		.check = test__checkevent_tracepoint_multi_modifier,
+		.id    = 13,
+	},
+	{
+		.name  = "r1a:kp",
+		.check = test__checkevent_raw_modifier,
+		.id    = 14,
+	},
+	{
+		.name  = "1:1:hp",
+		.check = test__checkevent_numeric_modifier,
+		.id    = 15,
+	},
+	{
+		.name  = "instructions:h",
+		.check = test__checkevent_symbolic_name_modifier,
+		.id    = 16,
+	},
+	{
+		.name  = "faults:u",
+		.check = test__checkevent_symbolic_alias_modifier,
+		.id    = 17,
+	},
+	{
+		.name  = "L1-dcache-load-miss:kp",
+		.check = test__checkevent_genhw_modifier,
+		.id    = 18,
+	},
+	{
+		.name  = "mem:0:u",
+		.check = test__checkevent_breakpoint_modifier,
+		.id    = 19,
+	},
+	{
+		.name  = "mem:0:x:k",
+		.check = test__checkevent_breakpoint_x_modifier,
+		.id    = 20,
+	},
+	{
+		.name  = "mem:0:r:hp",
+		.check = test__checkevent_breakpoint_r_modifier,
+		.id    = 21,
+	},
+	{
+		.name  = "mem:0:w:up",
+		.check = test__checkevent_breakpoint_w_modifier,
+		.id    = 22,
+	},
+	{
+		.name  = "r1,syscalls:sys_enter_open:k,1:1:hp",
+		.check = test__checkevent_list,
+		.id    = 23,
+	},
+	{
+		.name  = "instructions:G",
+		.check = test__checkevent_exclude_host_modifier,
+		.id    = 24,
+	},
+	{
+		.name  = "instructions:H",
+		.check = test__checkevent_exclude_guest_modifier,
+		.id    = 25,
+	},
+	{
+		.name  = "mem:0:rw",
+		.check = test__checkevent_breakpoint_rw,
+		.id    = 26,
+	},
+	{
+		.name  = "mem:0:rw:kp",
+		.check = test__checkevent_breakpoint_rw_modifier,
+		.id    = 27,
+	},
+	{
+		.name  = "{instructions:k,cycles:upp}",
+		.check = test__group1,
+		.id    = 28,
+	},
+	{
+		.name  = "{faults:k,cache-references}:u,cycles:k",
+		.check = test__group2,
+		.id    = 29,
+	},
+	{
+		.name  = "group1{syscalls:sys_enter_open:H,cycles:kppp},group2{cycles,1:3}:G,instructions:u",
+		.check = test__group3,
+		.id    = 30,
+	},
+	{
+		.name  = "{cycles:u,instructions:kp}:p",
+		.check = test__group4,
+		.id    = 31,
+	},
+	{
+		.name  = "{cycles,instructions}:G,{cycles:G,instructions:G},cycles",
+		.check = test__group5,
+		.id    = 32,
+	},
+	{
+		.name  = "*:*",
+		.check = test__all_tracepoints,
+		.id    = 33,
+	},
+	{
+		.name  = "{cycles,cache-misses:G}:H",
+		.check = test__group_gh1,
+		.id    = 34,
+	},
+	{
+		.name  = "{cycles,cache-misses:H}:G",
+		.check = test__group_gh2,
+		.id    = 35,
+	},
+	{
+		.name  = "{cycles:G,cache-misses:H}:u",
+		.check = test__group_gh3,
+		.id    = 36,
+	},
+	{
+		.name  = "{cycles:G,cache-misses:H}:uG",
+		.check = test__group_gh4,
+		.id    = 37,
+	},
+	{
+		.name  = "{cycles,cache-misses,branch-misses}:S",
+		.check = test__leader_sample1,
+		.id    = 38,
+	},
+	{
+		.name  = "{instructions,branch-misses}:Su",
+		.check = test__leader_sample2,
+		.id    = 39,
+	},
+	{
+		.name  = "instructions:uDp",
+		.check = test__checkevent_pinned_modifier,
+		.id    = 40,
+	},
+	{
+		.name  = "{cycles,cache-misses,branch-misses}:D",
+		.check = test__pinned_group,
+		.id    = 41,
+	},
+	{
+		.name  = "mem:0/1",
+		.check = test__checkevent_breakpoint_len,
+		.id    = 42,
+	},
+	{
+		.name  = "mem:0/2:w",
+		.check = test__checkevent_breakpoint_len_w,
+		.id    = 43,
+	},
+	{
+		.name  = "mem:0/4:rw:u",
+		.check = test__checkevent_breakpoint_len_rw_modifier,
+		.id    = 44
+	},
+#if defined(__s390x__)
+	{
+		.name  = "kvm-s390:kvm_s390_create_vm",
+		.check = test__checkevent_tracepoint,
+		.id    = 100,
+	},
+#endif
+	{
+		.name  = "instructions:I",
+		.check = test__checkevent_exclude_idle_modifier,
+		.id    = 45,
+	},
+	{
+		.name  = "instructions:kIG",
+		.check = test__checkevent_exclude_idle_modifier_1,
+		.id    = 46,
+	},
+};
+
+static struct evlist_test test__events_pmu[] = {
+	{
+		.name  = "cpu/config=10,config1,config2=3,period=1000/u",
+		.check = test__checkevent_pmu,
+		.id    = 0,
+	},
+	{
+		.name  = "cpu/config=1,name=krava/u,cpu/config=2/u",
+		.check = test__checkevent_pmu_name,
+		.id    = 1,
+	},
+};
+
+struct terms_test {
+	const char *str;
+	__u32 type;
+	int (*check)(struct list_head *terms);
+};
+
+static struct terms_test test__terms[] = {
+	[0] = {
+		.str   = "config=10,config1,config2=3,umask=1",
+		.check = test__checkterms_simple,
+	},
+};
+
+static int test_event(struct evlist_test *e)
+{
+	struct perf_evlist *evlist;
+	int ret;
+
+	evlist = perf_evlist__new();
+	if (evlist == NULL)
+		return -ENOMEM;
+
+	ret = parse_events(evlist, e->name);
+	if (ret) {
+		pr_debug("failed to parse event '%s', err %d\n",
+			 e->name, ret);
+	} else {
+		ret = e->check(evlist);
+	}
+
+	perf_evlist__delete(evlist);
+
+	return ret;
+}
+
+static int test_events(struct evlist_test *events, unsigned cnt)
+{
+	int ret1, ret2 = 0;
+	unsigned i;
+
+	for (i = 0; i < cnt; i++) {
+		struct evlist_test *e = &events[i];
+
+		pr_debug("running test %d '%s'\n", e->id, e->name);
+		ret1 = test_event(e);
+		if (ret1)
+			ret2 = ret1;
+	}
+
+	return ret2;
+}
+
+static int test_term(struct terms_test *t)
+{
+	struct list_head terms;
+	int ret;
+
+	INIT_LIST_HEAD(&terms);
+
+	ret = parse_events_terms(&terms, t->str);
+	if (ret) {
+		pr_debug("failed to parse terms '%s', err %d\n",
+			 t->str , ret);
+		return ret;
+	}
+
+	ret = t->check(&terms);
+	parse_events__free_terms(&terms);
+
+	return ret;
+}
+
+static int test_terms(struct terms_test *terms, unsigned cnt)
+{
+	int ret = 0;
+	unsigned i;
+
+	for (i = 0; i < cnt; i++) {
+		struct terms_test *t = &terms[i];
+
+		pr_debug("running test %d '%s'\n", i, t->str);
+		ret = test_term(t);
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+
+static int test_pmu(void)
+{
+	struct stat st;
+	char path[PATH_MAX];
+	int ret;
+
+	snprintf(path, PATH_MAX, "%s/bus/event_source/devices/cpu/format/",
+		 sysfs__mountpoint());
+
+	ret = stat(path, &st);
+	if (ret)
+		pr_debug("omitting PMU cpu tests\n");
+	return !ret;
+}
+
+static int test_pmu_events(void)
+{
+	struct stat st;
+	char path[PATH_MAX];
+	struct dirent *ent;
+	DIR *dir;
+	int ret;
+
+	snprintf(path, PATH_MAX, "%s/bus/event_source/devices/cpu/events/",
+		 sysfs__mountpoint());
+
+	ret = stat(path, &st);
+	if (ret) {
+		pr_debug("omitting PMU cpu events tests\n");
+		return 0;
+	}
+
+	dir = opendir(path);
+	if (!dir) {
+		pr_debug("can't open pmu event dir");
+		return -1;
+	}
+
+	while (!ret && (ent = readdir(dir))) {
+#define MAX_NAME 100
+		struct evlist_test e;
+		char name[MAX_NAME];
+
+		if (!strcmp(ent->d_name, ".") ||
+		    !strcmp(ent->d_name, ".."))
+			continue;
+
+		snprintf(name, MAX_NAME, "cpu/event=%s/u", ent->d_name);
+
+		e.name  = name;
+		e.check = test__checkevent_pmu_events;
+
+		ret = test_event(&e);
+		if (ret)
+			break;
+		snprintf(name, MAX_NAME, "%s:u,cpu/event=%s/u", ent->d_name, ent->d_name);
+		e.name  = name;
+		e.check = test__checkevent_pmu_events_mix;
+		ret = test_event(&e);
+#undef MAX_NAME
+	}
+
+	closedir(dir);
+	return ret;
+}
+
+int test__parse_events(void)
+{
+	int ret1, ret2 = 0;
+
+#define TEST_EVENTS(tests)				\
+do {							\
+	ret1 = test_events(tests, ARRAY_SIZE(tests));	\
+	if (!ret2)					\
+		ret2 = ret1;				\
+} while (0)
+
+	TEST_EVENTS(test__events);
+
+	if (test_pmu())
+		TEST_EVENTS(test__events_pmu);
+
+	if (test_pmu()) {
+		int ret = test_pmu_events();
+		if (ret)
+			return ret;
+	}
+
+	ret1 = test_terms(test__terms, ARRAY_SIZE(test__terms));
+	if (!ret2)
+		ret2 = ret1;
+
+	return ret2;
+}
diff --git a/tools/perf/tests/parse-no-sample-id-all.c b/tools/perf/tests/parse-no-sample-id-all.c
new file mode 100644
index 000000000..2c63ea658
--- /dev/null
+++ b/tools/perf/tests/parse-no-sample-id-all.c
@@ -0,0 +1,109 @@
+#include <linux/types.h>
+#include <stddef.h>
+
+#include "tests.h"
+
+#include "event.h"
+#include "evlist.h"
+#include "header.h"
+#include "util.h"
+#include "debug.h"
+
+static int process_event(struct perf_evlist **pevlist, union perf_event *event)
+{
+	struct perf_sample sample;
+
+	if (event->header.type == PERF_RECORD_HEADER_ATTR) {
+		if (perf_event__process_attr(NULL, event, pevlist)) {
+			pr_debug("perf_event__process_attr failed\n");
+			return -1;
+		}
+		return 0;
+	}
+
+	if (event->header.type >= PERF_RECORD_USER_TYPE_START)
+		return -1;
+
+	if (!*pevlist)
+		return -1;
+
+	if (perf_evlist__parse_sample(*pevlist, event, &sample)) {
+		pr_debug("perf_evlist__parse_sample failed\n");
+		return -1;
+	}
+
+	return 0;
+}
+
+static int process_events(union perf_event **events, size_t count)
+{
+	struct perf_evlist *evlist = NULL;
+	int err = 0;
+	size_t i;
+
+	for (i = 0; i < count && !err; i++)
+		err = process_event(&evlist, events[i]);
+
+	if (evlist)
+		perf_evlist__delete(evlist);
+
+	return err;
+}
+
+struct test_attr_event {
+	struct attr_event attr;
+	u64 id;
+};
+
+/**
+ * test__parse_no_sample_id_all - test parsing with no sample_id_all bit set.
+ *
+ * This function tests parsing data produced on kernel's that do not support the
+ * sample_id_all bit.  Without the sample_id_all bit, non-sample events (such as
+ * mmap events) do not have an id sample appended, and consequently logic
+ * designed to determine the id will not work.  That case happens when there is
+ * more than one selected event, so this test processes three events: 2
+ * attributes representing the selected events and one mmap event.
+ *
+ * Return: %0 on success, %-1 if the test fails.
+ */
+int test__parse_no_sample_id_all(void)
+{
+	int err;
+
+	struct test_attr_event event1 = {
+		.attr = {
+			.header = {
+				.type = PERF_RECORD_HEADER_ATTR,
+				.size = sizeof(struct test_attr_event),
+			},
+		},
+		.id = 1,
+	};
+	struct test_attr_event event2 = {
+		.attr = {
+			.header = {
+				.type = PERF_RECORD_HEADER_ATTR,
+				.size = sizeof(struct test_attr_event),
+			},
+		},
+		.id = 2,
+	};
+	struct mmap_event event3 = {
+		.header = {
+			.type = PERF_RECORD_MMAP,
+			.size = sizeof(struct mmap_event),
+		},
+	};
+	union perf_event *events[] = {
+		(union perf_event *)&event1,
+		(union perf_event *)&event2,
+		(union perf_event *)&event3,
+	};
+
+	err = process_events(events, ARRAY_SIZE(events));
+	if (err)
+		return -1;
+
+	return 0;
+}
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
new file mode 100644
index 000000000..7a228a2a0
--- /dev/null
+++ b/tools/perf/tests/perf-record.c
@@ -0,0 +1,314 @@
+#include <sched.h>
+#include "evlist.h"
+#include "evsel.h"
+#include "perf.h"
+#include "debug.h"
+#include "tests.h"
+
+static int sched__get_first_possible_cpu(pid_t pid, cpu_set_t *maskp)
+{
+	int i, cpu = -1, nrcpus = 1024;
+realloc:
+	CPU_ZERO(maskp);
+
+	if (sched_getaffinity(pid, sizeof(*maskp), maskp) == -1) {
+		if (errno == EINVAL && nrcpus < (1024 << 8)) {
+			nrcpus = nrcpus << 2;
+			goto realloc;
+		}
+		perror("sched_getaffinity");
+			return -1;
+	}
+
+	for (i = 0; i < nrcpus; i++) {
+		if (CPU_ISSET(i, maskp)) {
+			if (cpu == -1)
+				cpu = i;
+			else
+				CPU_CLR(i, maskp);
+		}
+	}
+
+	return cpu;
+}
+
+int test__PERF_RECORD(void)
+{
+	struct record_opts opts = {
+		.target = {
+			.uid = UINT_MAX,
+			.uses_mmap = true,
+		},
+		.no_buffering = true,
+		.freq	      = 10,
+		.mmap_pages   = 256,
+	};
+	cpu_set_t cpu_mask;
+	size_t cpu_mask_size = sizeof(cpu_mask);
+	struct perf_evlist *evlist = perf_evlist__new_default();
+	struct perf_evsel *evsel;
+	struct perf_sample sample;
+	const char *cmd = "sleep";
+	const char *argv[] = { cmd, "1", NULL, };
+	char *bname, *mmap_filename;
+	u64 prev_time = 0;
+	bool found_cmd_mmap = false,
+	     found_libc_mmap = false,
+	     found_vdso_mmap = false,
+	     found_ld_mmap = false;
+	int err = -1, errs = 0, i, wakeups = 0;
+	u32 cpu;
+	int total_events = 0, nr_events[PERF_RECORD_MAX] = { 0, };
+	char sbuf[STRERR_BUFSIZE];
+
+	if (evlist == NULL || argv == NULL) {
+		pr_debug("Not enough memory to create evlist\n");
+		goto out;
+	}
+
+	/*
+	 * Create maps of threads and cpus to monitor. In this case
+	 * we start with all threads and cpus (-1, -1) but then in
+	 * perf_evlist__prepare_workload we'll fill in the only thread
+	 * we're monitoring, the one forked there.
+	 */
+	err = perf_evlist__create_maps(evlist, &opts.target);
+	if (err < 0) {
+		pr_debug("Not enough memory to create thread/cpu maps\n");
+		goto out_delete_evlist;
+	}
+
+	/*
+	 * Prepare the workload in argv[] to run, it'll fork it, and then wait
+	 * for perf_evlist__start_workload() to exec it. This is done this way
+	 * so that we have time to open the evlist (calling sys_perf_event_open
+	 * on all the fds) and then mmap them.
+	 */
+	err = perf_evlist__prepare_workload(evlist, &opts.target, argv, false, NULL);
+	if (err < 0) {
+		pr_debug("Couldn't run the workload!\n");
+		goto out_delete_evlist;
+	}
+
+	/*
+	 * Config the evsels, setting attr->comm on the first one, etc.
+	 */
+	evsel = perf_evlist__first(evlist);
+	perf_evsel__set_sample_bit(evsel, CPU);
+	perf_evsel__set_sample_bit(evsel, TID);
+	perf_evsel__set_sample_bit(evsel, TIME);
+	perf_evlist__config(evlist, &opts);
+
+	err = sched__get_first_possible_cpu(evlist->workload.pid, &cpu_mask);
+	if (err < 0) {
+		pr_debug("sched__get_first_possible_cpu: %s\n",
+			 strerror_r(errno, sbuf, sizeof(sbuf)));
+		goto out_delete_evlist;
+	}
+
+	cpu = err;
+
+	/*
+	 * So that we can check perf_sample.cpu on all the samples.
+	 */
+	if (sched_setaffinity(evlist->workload.pid, cpu_mask_size, &cpu_mask) < 0) {
+		pr_debug("sched_setaffinity: %s\n",
+			 strerror_r(errno, sbuf, sizeof(sbuf)));
+		goto out_delete_evlist;
+	}
+
+	/*
+	 * Call sys_perf_event_open on all the fds on all the evsels,
+	 * grouping them if asked to.
+	 */
+	err = perf_evlist__open(evlist);
+	if (err < 0) {
+		pr_debug("perf_evlist__open: %s\n",
+			 strerror_r(errno, sbuf, sizeof(sbuf)));
+		goto out_delete_evlist;
+	}
+
+	/*
+	 * mmap the first fd on a given CPU and ask for events for the other
+	 * fds in the same CPU to be injected in the same mmap ring buffer
+	 * (using ioctl(PERF_EVENT_IOC_SET_OUTPUT)).
+	 */
+	err = perf_evlist__mmap(evlist, opts.mmap_pages, false);
+	if (err < 0) {
+		pr_debug("perf_evlist__mmap: %s\n",
+			 strerror_r(errno, sbuf, sizeof(sbuf)));
+		goto out_delete_evlist;
+	}
+
+	/*
+	 * Now that all is properly set up, enable the events, they will
+	 * count just on workload.pid, which will start...
+	 */
+	perf_evlist__enable(evlist);
+
+	/*
+	 * Now!
+	 */
+	perf_evlist__start_workload(evlist);
+
+	while (1) {
+		int before = total_events;
+
+		for (i = 0; i < evlist->nr_mmaps; i++) {
+			union perf_event *event;
+
+			while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
+				const u32 type = event->header.type;
+				const char *name = perf_event__name(type);
+
+				++total_events;
+				if (type < PERF_RECORD_MAX)
+					nr_events[type]++;
+
+				err = perf_evlist__parse_sample(evlist, event, &sample);
+				if (err < 0) {
+					if (verbose)
+						perf_event__fprintf(event, stderr);
+					pr_debug("Couldn't parse sample\n");
+					goto out_delete_evlist;
+				}
+
+				if (verbose) {
+					pr_info("%" PRIu64" %d ", sample.time, sample.cpu);
+					perf_event__fprintf(event, stderr);
+				}
+
+				if (prev_time > sample.time) {
+					pr_debug("%s going backwards in time, prev=%" PRIu64 ", curr=%" PRIu64 "\n",
+						 name, prev_time, sample.time);
+					++errs;
+				}
+
+				prev_time = sample.time;
+
+				if (sample.cpu != cpu) {
+					pr_debug("%s with unexpected cpu, expected %d, got %d\n",
+						 name, cpu, sample.cpu);
+					++errs;
+				}
+
+				if ((pid_t)sample.pid != evlist->workload.pid) {
+					pr_debug("%s with unexpected pid, expected %d, got %d\n",
+						 name, evlist->workload.pid, sample.pid);
+					++errs;
+				}
+
+				if ((pid_t)sample.tid != evlist->workload.pid) {
+					pr_debug("%s with unexpected tid, expected %d, got %d\n",
+						 name, evlist->workload.pid, sample.tid);
+					++errs;
+				}
+
+				if ((type == PERF_RECORD_COMM ||
+				     type == PERF_RECORD_MMAP ||
+				     type == PERF_RECORD_MMAP2 ||
+				     type == PERF_RECORD_FORK ||
+				     type == PERF_RECORD_EXIT) &&
+				     (pid_t)event->comm.pid != evlist->workload.pid) {
+					pr_debug("%s with unexpected pid/tid\n", name);
+					++errs;
+				}
+
+				if ((type == PERF_RECORD_COMM ||
+				     type == PERF_RECORD_MMAP ||
+				     type == PERF_RECORD_MMAP2) &&
+				     event->comm.pid != event->comm.tid) {
+					pr_debug("%s with different pid/tid!\n", name);
+					++errs;
+				}
+
+				switch (type) {
+				case PERF_RECORD_COMM:
+					if (strcmp(event->comm.comm, cmd)) {
+						pr_debug("%s with unexpected comm!\n", name);
+						++errs;
+					}
+					break;
+				case PERF_RECORD_EXIT:
+					goto found_exit;
+				case PERF_RECORD_MMAP:
+					mmap_filename = event->mmap.filename;
+					goto check_bname;
+				case PERF_RECORD_MMAP2:
+					mmap_filename = event->mmap2.filename;
+				check_bname:
+					bname = strrchr(mmap_filename, '/');
+					if (bname != NULL) {
+						if (!found_cmd_mmap)
+							found_cmd_mmap = !strcmp(bname + 1, cmd);
+						if (!found_libc_mmap)
+							found_libc_mmap = !strncmp(bname + 1, "libc", 4);
+						if (!found_ld_mmap)
+							found_ld_mmap = !strncmp(bname + 1, "ld", 2);
+					} else if (!found_vdso_mmap)
+						found_vdso_mmap = !strcmp(mmap_filename, "[vdso]");
+					break;
+
+				case PERF_RECORD_SAMPLE:
+					/* Just ignore samples for now */
+					break;
+				default:
+					pr_debug("Unexpected perf_event->header.type %d!\n",
+						 type);
+					++errs;
+				}
+
+				perf_evlist__mmap_consume(evlist, i);
+			}
+		}
+
+		/*
+		 * We don't use poll here because at least at 3.1 times the
+		 * PERF_RECORD_{!SAMPLE} events don't honour
+		 * perf_event_attr.wakeup_events, just PERF_EVENT_SAMPLE does.
+		 */
+		if (total_events == before && false)
+			perf_evlist__poll(evlist, -1);
+
+		sleep(1);
+		if (++wakeups > 5) {
+			pr_debug("No PERF_RECORD_EXIT event!\n");
+			break;
+		}
+	}
+
+found_exit:
+	if (nr_events[PERF_RECORD_COMM] > 1) {
+		pr_debug("Excessive number of PERF_RECORD_COMM events!\n");
+		++errs;
+	}
+
+	if (nr_events[PERF_RECORD_COMM] == 0) {
+		pr_debug("Missing PERF_RECORD_COMM for %s!\n", cmd);
+		++errs;
+	}
+
+	if (!found_cmd_mmap) {
+		pr_debug("PERF_RECORD_MMAP for %s missing!\n", cmd);
+		++errs;
+	}
+
+	if (!found_libc_mmap) {
+		pr_debug("PERF_RECORD_MMAP for %s missing!\n", "libc");
+		++errs;
+	}
+
+	if (!found_ld_mmap) {
+		pr_debug("PERF_RECORD_MMAP for %s missing!\n", "ld");
+		++errs;
+	}
+
+	if (!found_vdso_mmap) {
+		pr_debug("PERF_RECORD_MMAP for %s missing!\n", "[vdso]");
+		++errs;
+	}
+out_delete_evlist:
+	perf_evlist__delete(evlist);
+out:
+	return (err < 0 || errs > 0) ? -1 : 0;
+}
diff --git a/tools/perf/tests/perf-targz-src-pkg b/tools/perf/tests/perf-targz-src-pkg
new file mode 100755
index 000000000..238aa3927
--- /dev/null
+++ b/tools/perf/tests/perf-targz-src-pkg
@@ -0,0 +1,21 @@
+#!/bin/sh
+# Test one of the main kernel Makefile targets to generate a perf sources tarball
+# suitable for build outside the full kernel sources.
+#
+# This is to test that the tools/perf/MANIFEST file lists all the files needed to
+# be in such tarball, which sometimes gets broken when we move files around,
+# like when we made some files that were in tools/perf/ available to other tools/
+# codebases by moving it to tools/include/, etc.
+
+PERF=$1
+cd ${PERF}/../..
+make perf-targz-src-pkg > /dev/null
+TARBALL=$(ls -rt perf-*.tar.gz)
+TMP_DEST=$(mktemp -d)
+tar xf ${TARBALL} -C $TMP_DEST
+rm -f ${TARBALL}
+cd - > /dev/null
+make -C $TMP_DEST/perf*/tools/perf > /dev/null 2>&1
+RC=$?
+rm -rf ${TMP_DEST}
+exit $RC
diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c
new file mode 100644
index 000000000..f238442b2
--- /dev/null
+++ b/tools/perf/tests/perf-time-to-tsc.c
@@ -0,0 +1,162 @@
+#include <stdio.h>
+#include <unistd.h>
+#include <linux/types.h>
+#include <sys/prctl.h>
+
+#include "parse-events.h"
+#include "evlist.h"
+#include "evsel.h"
+#include "thread_map.h"
+#include "cpumap.h"
+#include "tsc.h"
+#include "tests.h"
+
+#define CHECK__(x) {				\
+	while ((x) < 0) {			\
+		pr_debug(#x " failed!\n");	\
+		goto out_err;			\
+	}					\
+}
+
+#define CHECK_NOT_NULL__(x) {			\
+	while ((x) == NULL) {			\
+		pr_debug(#x " failed!\n");	\
+		goto out_err;			\
+	}					\
+}
+
+/**
+ * test__perf_time_to_tsc - test converting perf time to TSC.
+ *
+ * This function implements a test that checks that the conversion of perf time
+ * to and from TSC is consistent with the order of events.  If the test passes
+ * %0 is returned, otherwise %-1 is returned.  If TSC conversion is not
+ * supported then then the test passes but " (not supported)" is printed.
+ */
+int test__perf_time_to_tsc(void)
+{
+	struct record_opts opts = {
+		.mmap_pages	     = UINT_MAX,
+		.user_freq	     = UINT_MAX,
+		.user_interval	     = ULLONG_MAX,
+		.freq		     = 4000,
+		.target		     = {
+			.uses_mmap   = true,
+		},
+		.sample_time	     = true,
+	};
+	struct thread_map *threads = NULL;
+	struct cpu_map *cpus = NULL;
+	struct perf_evlist *evlist = NULL;
+	struct perf_evsel *evsel = NULL;
+	int err = -1, ret, i;
+	const char *comm1, *comm2;
+	struct perf_tsc_conversion tc;
+	struct perf_event_mmap_page *pc;
+	union perf_event *event;
+	u64 test_tsc, comm1_tsc, comm2_tsc;
+	u64 test_time, comm1_time = 0, comm2_time = 0;
+
+	threads = thread_map__new(-1, getpid(), UINT_MAX);
+	CHECK_NOT_NULL__(threads);
+
+	cpus = cpu_map__new(NULL);
+	CHECK_NOT_NULL__(cpus);
+
+	evlist = perf_evlist__new();
+	CHECK_NOT_NULL__(evlist);
+
+	perf_evlist__set_maps(evlist, cpus, threads);
+
+	CHECK__(parse_events(evlist, "cycles:u"));
+
+	perf_evlist__config(evlist, &opts);
+
+	evsel = perf_evlist__first(evlist);
+
+	evsel->attr.comm = 1;
+	evsel->attr.disabled = 1;
+	evsel->attr.enable_on_exec = 0;
+
+	CHECK__(perf_evlist__open(evlist));
+
+	CHECK__(perf_evlist__mmap(evlist, UINT_MAX, false));
+
+	pc = evlist->mmap[0].base;
+	ret = perf_read_tsc_conversion(pc, &tc);
+	if (ret) {
+		if (ret == -EOPNOTSUPP) {
+			fprintf(stderr, " (not supported)");
+			return 0;
+		}
+		goto out_err;
+	}
+
+	perf_evlist__enable(evlist);
+
+	comm1 = "Test COMM 1";
+	CHECK__(prctl(PR_SET_NAME, (unsigned long)comm1, 0, 0, 0));
+
+	test_tsc = rdtsc();
+
+	comm2 = "Test COMM 2";
+	CHECK__(prctl(PR_SET_NAME, (unsigned long)comm2, 0, 0, 0));
+
+	perf_evlist__disable(evlist);
+
+	for (i = 0; i < evlist->nr_mmaps; i++) {
+		while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
+			struct perf_sample sample;
+
+			if (event->header.type != PERF_RECORD_COMM ||
+			    (pid_t)event->comm.pid != getpid() ||
+			    (pid_t)event->comm.tid != getpid())
+				goto next_event;
+
+			if (strcmp(event->comm.comm, comm1) == 0) {
+				CHECK__(perf_evsel__parse_sample(evsel, event,
+								 &sample));
+				comm1_time = sample.time;
+			}
+			if (strcmp(event->comm.comm, comm2) == 0) {
+				CHECK__(perf_evsel__parse_sample(evsel, event,
+								 &sample));
+				comm2_time = sample.time;
+			}
+next_event:
+			perf_evlist__mmap_consume(evlist, i);
+		}
+	}
+
+	if (!comm1_time || !comm2_time)
+		goto out_err;
+
+	test_time = tsc_to_perf_time(test_tsc, &tc);
+	comm1_tsc = perf_time_to_tsc(comm1_time, &tc);
+	comm2_tsc = perf_time_to_tsc(comm2_time, &tc);
+
+	pr_debug("1st event perf time %"PRIu64" tsc %"PRIu64"\n",
+		 comm1_time, comm1_tsc);
+	pr_debug("rdtsc          time %"PRIu64" tsc %"PRIu64"\n",
+		 test_time, test_tsc);
+	pr_debug("2nd event perf time %"PRIu64" tsc %"PRIu64"\n",
+		 comm2_time, comm2_tsc);
+
+	if (test_time <= comm1_time ||
+	    test_time >= comm2_time)
+		goto out_err;
+
+	if (test_tsc <= comm1_tsc ||
+	    test_tsc >= comm2_tsc)
+		goto out_err;
+
+	err = 0;
+
+out_err:
+	if (evlist) {
+		perf_evlist__disable(evlist);
+		perf_evlist__delete(evlist);
+	}
+
+	return err;
+}
diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c
new file mode 100644
index 000000000..eeb68bb19
--- /dev/null
+++ b/tools/perf/tests/pmu.c
@@ -0,0 +1,173 @@
+#include "parse-events.h"
+#include "pmu.h"
+#include "util.h"
+#include "tests.h"
+
+/* Simulated format definitions. */
+static struct test_format {
+	const char *name;
+	const char *value;
+} test_formats[] = {
+	{ "krava01", "config:0-1,62-63\n", },
+	{ "krava02", "config:10-17\n", },
+	{ "krava03", "config:5\n", },
+	{ "krava11", "config1:0,2,4,6,8,20-28\n", },
+	{ "krava12", "config1:63\n", },
+	{ "krava13", "config1:45-47\n", },
+	{ "krava21", "config2:0-3,10-13,20-23,30-33,40-43,50-53,60-63\n", },
+	{ "krava22", "config2:8,18,48,58\n", },
+	{ "krava23", "config2:28-29,38\n", },
+};
+
+/* Simulated users input. */
+static struct parse_events_term test_terms[] = {
+	{
+		.config    = (char *) "krava01",
+		.val.num   = 15,
+		.type_val  = PARSE_EVENTS__TERM_TYPE_NUM,
+		.type_term = PARSE_EVENTS__TERM_TYPE_USER,
+	},
+	{
+		.config    = (char *) "krava02",
+		.val.num   = 170,
+		.type_val  = PARSE_EVENTS__TERM_TYPE_NUM,
+		.type_term = PARSE_EVENTS__TERM_TYPE_USER,
+	},
+	{
+		.config    = (char *) "krava03",
+		.val.num   = 1,
+		.type_val  = PARSE_EVENTS__TERM_TYPE_NUM,
+		.type_term = PARSE_EVENTS__TERM_TYPE_USER,
+	},
+	{
+		.config    = (char *) "krava11",
+		.val.num   = 27,
+		.type_val  = PARSE_EVENTS__TERM_TYPE_NUM,
+		.type_term = PARSE_EVENTS__TERM_TYPE_USER,
+	},
+	{
+		.config    = (char *) "krava12",
+		.val.num   = 1,
+		.type_val  = PARSE_EVENTS__TERM_TYPE_NUM,
+		.type_term = PARSE_EVENTS__TERM_TYPE_USER,
+	},
+	{
+		.config    = (char *) "krava13",
+		.val.num   = 2,
+		.type_val  = PARSE_EVENTS__TERM_TYPE_NUM,
+		.type_term = PARSE_EVENTS__TERM_TYPE_USER,
+	},
+	{
+		.config    = (char *) "krava21",
+		.val.num   = 119,
+		.type_val  = PARSE_EVENTS__TERM_TYPE_NUM,
+		.type_term = PARSE_EVENTS__TERM_TYPE_USER,
+	},
+	{
+		.config    = (char *) "krava22",
+		.val.num   = 11,
+		.type_val  = PARSE_EVENTS__TERM_TYPE_NUM,
+		.type_term = PARSE_EVENTS__TERM_TYPE_USER,
+	},
+	{
+		.config    = (char *) "krava23",
+		.val.num   = 2,
+		.type_val  = PARSE_EVENTS__TERM_TYPE_NUM,
+		.type_term = PARSE_EVENTS__TERM_TYPE_USER,
+	},
+};
+
+/*
+ * Prepare format directory data, exported by kernel
+ * at /sys/bus/event_source/devices/<dev>/format.
+ */
+static char *test_format_dir_get(void)
+{
+	static char dir[PATH_MAX];
+	unsigned int i;
+
+	snprintf(dir, PATH_MAX, "/tmp/perf-pmu-test-format-XXXXXX");
+	if (!mkdtemp(dir))
+		return NULL;
+
+	for (i = 0; i < ARRAY_SIZE(test_formats); i++) {
+		static char name[PATH_MAX];
+		struct test_format *format = &test_formats[i];
+		FILE *file;
+
+		snprintf(name, PATH_MAX, "%s/%s", dir, format->name);
+
+		file = fopen(name, "w");
+		if (!file)
+			return NULL;
+
+		if (1 != fwrite(format->value, strlen(format->value), 1, file))
+			break;
+
+		fclose(file);
+	}
+
+	return dir;
+}
+
+/* Cleanup format directory. */
+static int test_format_dir_put(char *dir)
+{
+	char buf[PATH_MAX];
+	snprintf(buf, PATH_MAX, "rm -f %s/*\n", dir);
+	if (system(buf))
+		return -1;
+
+	snprintf(buf, PATH_MAX, "rmdir %s\n", dir);
+	return system(buf);
+}
+
+static struct list_head *test_terms_list(void)
+{
+	static LIST_HEAD(terms);
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(test_terms); i++)
+		list_add_tail(&test_terms[i].list, &terms);
+
+	return &terms;
+}
+
+int test__pmu(void)
+{
+	char *format = test_format_dir_get();
+	LIST_HEAD(formats);
+	struct list_head *terms = test_terms_list();
+	int ret;
+
+	if (!format)
+		return -EINVAL;
+
+	do {
+		struct perf_event_attr attr;
+
+		memset(&attr, 0, sizeof(attr));
+
+		ret = perf_pmu__format_parse(format, &formats);
+		if (ret)
+			break;
+
+		ret = perf_pmu__config_terms(&formats, &attr, terms, false);
+		if (ret)
+			break;
+
+		ret = -EINVAL;
+
+		if (attr.config  != 0xc00000000002a823)
+			break;
+		if (attr.config1 != 0x8000400000000145)
+			break;
+		if (attr.config2 != 0x0400000020041d07)
+			break;
+
+		ret = 0;
+	} while (0);
+
+	test_format_dir_put(format);
+	return ret;
+}
diff --git a/tools/perf/tests/python-use.c b/tools/perf/tests/python-use.c
new file mode 100644
index 000000000..7760277c6
--- /dev/null
+++ b/tools/perf/tests/python-use.c
@@ -0,0 +1,23 @@
+/*
+ * Just test if we can load the python binding.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include "tests.h"
+
+extern int verbose;
+
+int test__python_use(void)
+{
+	char *cmd;
+	int ret;
+
+	if (asprintf(&cmd, "echo \"import sys ; sys.path.append('%s'); import perf\" | %s %s",
+		     PYTHONPATH, PYTHON, verbose ? "" : "2> /dev/null") < 0)
+		return -1;
+
+	ret = system(cmd) ? -1 : 0;
+	free(cmd);
+	return ret;
+}
diff --git a/tools/perf/tests/rdpmc.c b/tools/perf/tests/rdpmc.c
new file mode 100644
index 000000000..d31f2c4d9
--- /dev/null
+++ b/tools/perf/tests/rdpmc.c
@@ -0,0 +1,177 @@
+#include <unistd.h>
+#include <stdlib.h>
+#include <signal.h>
+#include <sys/mman.h>
+#include <linux/types.h>
+#include "perf.h"
+#include "debug.h"
+#include "tests.h"
+#include "cloexec.h"
+
+#if defined(__x86_64__) || defined(__i386__)
+
+static u64 rdpmc(unsigned int counter)
+{
+	unsigned int low, high;
+
+	asm volatile("rdpmc" : "=a" (low), "=d" (high) : "c" (counter));
+
+	return low | ((u64)high) << 32;
+}
+
+static u64 rdtsc(void)
+{
+	unsigned int low, high;
+
+	asm volatile("rdtsc" : "=a" (low), "=d" (high));
+
+	return low | ((u64)high) << 32;
+}
+
+static u64 mmap_read_self(void *addr)
+{
+	struct perf_event_mmap_page *pc = addr;
+	u32 seq, idx, time_mult = 0, time_shift = 0;
+	u64 count, cyc = 0, time_offset = 0, enabled, running, delta;
+
+	do {
+		seq = pc->lock;
+		barrier();
+
+		enabled = pc->time_enabled;
+		running = pc->time_running;
+
+		if (enabled != running) {
+			cyc = rdtsc();
+			time_mult = pc->time_mult;
+			time_shift = pc->time_shift;
+			time_offset = pc->time_offset;
+		}
+
+		idx = pc->index;
+		count = pc->offset;
+		if (idx)
+			count += rdpmc(idx - 1);
+
+		barrier();
+	} while (pc->lock != seq);
+
+	if (enabled != running) {
+		u64 quot, rem;
+
+		quot = (cyc >> time_shift);
+		rem = cyc & ((1 << time_shift) - 1);
+		delta = time_offset + quot * time_mult +
+			((rem * time_mult) >> time_shift);
+
+		enabled += delta;
+		if (idx)
+			running += delta;
+
+		quot = count / running;
+		rem = count % running;
+		count = quot * enabled + (rem * enabled) / running;
+	}
+
+	return count;
+}
+
+/*
+ * If the RDPMC instruction faults then signal this back to the test parent task:
+ */
+static void segfault_handler(int sig __maybe_unused,
+			     siginfo_t *info __maybe_unused,
+			     void *uc __maybe_unused)
+{
+	exit(-1);
+}
+
+static int __test__rdpmc(void)
+{
+	volatile int tmp = 0;
+	u64 i, loops = 1000;
+	int n;
+	int fd;
+	void *addr;
+	struct perf_event_attr attr = {
+		.type = PERF_TYPE_HARDWARE,
+		.config = PERF_COUNT_HW_INSTRUCTIONS,
+		.exclude_kernel = 1,
+	};
+	u64 delta_sum = 0;
+        struct sigaction sa;
+	char sbuf[STRERR_BUFSIZE];
+
+	sigfillset(&sa.sa_mask);
+	sa.sa_sigaction = segfault_handler;
+	sigaction(SIGSEGV, &sa, NULL);
+
+	fd = sys_perf_event_open(&attr, 0, -1, -1,
+				 perf_event_open_cloexec_flag());
+	if (fd < 0) {
+		pr_err("Error: sys_perf_event_open() syscall returned "
+		       "with %d (%s)\n", fd,
+		       strerror_r(errno, sbuf, sizeof(sbuf)));
+		return -1;
+	}
+
+	addr = mmap(NULL, page_size, PROT_READ, MAP_SHARED, fd, 0);
+	if (addr == (void *)(-1)) {
+		pr_err("Error: mmap() syscall returned with (%s)\n",
+		       strerror_r(errno, sbuf, sizeof(sbuf)));
+		goto out_close;
+	}
+
+	for (n = 0; n < 6; n++) {
+		u64 stamp, now, delta;
+
+		stamp = mmap_read_self(addr);
+
+		for (i = 0; i < loops; i++)
+			tmp++;
+
+		now = mmap_read_self(addr);
+		loops *= 10;
+
+		delta = now - stamp;
+		pr_debug("%14d: %14Lu\n", n, (long long)delta);
+
+		delta_sum += delta;
+	}
+
+	munmap(addr, page_size);
+	pr_debug("   ");
+out_close:
+	close(fd);
+
+	if (!delta_sum)
+		return -1;
+
+	return 0;
+}
+
+int test__rdpmc(void)
+{
+	int status = 0;
+	int wret = 0;
+	int ret;
+	int pid;
+
+	pid = fork();
+	if (pid < 0)
+		return -1;
+
+	if (!pid) {
+		ret = __test__rdpmc();
+
+		exit(ret);
+	}
+
+	wret = waitpid(pid, &status, 0);
+	if (wret < 0 || status)
+		return -1;
+
+	return 0;
+}
+
+#endif
diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c
new file mode 100644
index 000000000..30c02181e
--- /dev/null
+++ b/tools/perf/tests/sample-parsing.c
@@ -0,0 +1,346 @@
+#include <stdbool.h>
+#include <linux/types.h>
+
+#include "util.h"
+#include "event.h"
+#include "evsel.h"
+#include "debug.h"
+
+#include "tests.h"
+
+#define COMP(m) do {					\
+	if (s1->m != s2->m) {				\
+		pr_debug("Samples differ at '"#m"'\n");	\
+		return false;				\
+	}						\
+} while (0)
+
+#define MCOMP(m) do {					\
+	if (memcmp(&s1->m, &s2->m, sizeof(s1->m))) {	\
+		pr_debug("Samples differ at '"#m"'\n");	\
+		return false;				\
+	}						\
+} while (0)
+
+static bool samples_same(const struct perf_sample *s1,
+			 const struct perf_sample *s2,
+			 u64 type, u64 read_format)
+{
+	size_t i;
+
+	if (type & PERF_SAMPLE_IDENTIFIER)
+		COMP(id);
+
+	if (type & PERF_SAMPLE_IP)
+		COMP(ip);
+
+	if (type & PERF_SAMPLE_TID) {
+		COMP(pid);
+		COMP(tid);
+	}
+
+	if (type & PERF_SAMPLE_TIME)
+		COMP(time);
+
+	if (type & PERF_SAMPLE_ADDR)
+		COMP(addr);
+
+	if (type & PERF_SAMPLE_ID)
+		COMP(id);
+
+	if (type & PERF_SAMPLE_STREAM_ID)
+		COMP(stream_id);
+
+	if (type & PERF_SAMPLE_CPU)
+		COMP(cpu);
+
+	if (type & PERF_SAMPLE_PERIOD)
+		COMP(period);
+
+	if (type & PERF_SAMPLE_READ) {
+		if (read_format & PERF_FORMAT_GROUP)
+			COMP(read.group.nr);
+		else
+			COMP(read.one.value);
+		if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+			COMP(read.time_enabled);
+		if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+			COMP(read.time_running);
+		/* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */
+		if (read_format & PERF_FORMAT_GROUP) {
+			for (i = 0; i < s1->read.group.nr; i++)
+				MCOMP(read.group.values[i]);
+		} else {
+			COMP(read.one.id);
+		}
+	}
+
+	if (type & PERF_SAMPLE_CALLCHAIN) {
+		COMP(callchain->nr);
+		for (i = 0; i < s1->callchain->nr; i++)
+			COMP(callchain->ips[i]);
+	}
+
+	if (type & PERF_SAMPLE_RAW) {
+		COMP(raw_size);
+		if (memcmp(s1->raw_data, s2->raw_data, s1->raw_size)) {
+			pr_debug("Samples differ at 'raw_data'\n");
+			return false;
+		}
+	}
+
+	if (type & PERF_SAMPLE_BRANCH_STACK) {
+		COMP(branch_stack->nr);
+		for (i = 0; i < s1->branch_stack->nr; i++)
+			MCOMP(branch_stack->entries[i]);
+	}
+
+	if (type & PERF_SAMPLE_REGS_USER) {
+		size_t sz = hweight_long(s1->user_regs.mask) * sizeof(u64);
+
+		COMP(user_regs.mask);
+		COMP(user_regs.abi);
+		if (s1->user_regs.abi &&
+		    (!s1->user_regs.regs || !s2->user_regs.regs ||
+		     memcmp(s1->user_regs.regs, s2->user_regs.regs, sz))) {
+			pr_debug("Samples differ at 'user_regs'\n");
+			return false;
+		}
+	}
+
+	if (type & PERF_SAMPLE_STACK_USER) {
+		COMP(user_stack.size);
+		if (memcmp(s1->user_stack.data, s2->user_stack.data,
+			   s1->user_stack.size)) {
+			pr_debug("Samples differ at 'user_stack'\n");
+			return false;
+		}
+	}
+
+	if (type & PERF_SAMPLE_WEIGHT)
+		COMP(weight);
+
+	if (type & PERF_SAMPLE_DATA_SRC)
+		COMP(data_src);
+
+	if (type & PERF_SAMPLE_TRANSACTION)
+		COMP(transaction);
+
+	if (type & PERF_SAMPLE_REGS_INTR) {
+		size_t sz = hweight_long(s1->intr_regs.mask) * sizeof(u64);
+
+		COMP(intr_regs.mask);
+		COMP(intr_regs.abi);
+		if (s1->intr_regs.abi &&
+		    (!s1->intr_regs.regs || !s2->intr_regs.regs ||
+		     memcmp(s1->intr_regs.regs, s2->intr_regs.regs, sz))) {
+			pr_debug("Samples differ at 'intr_regs'\n");
+			return false;
+		}
+	}
+
+	return true;
+}
+
+static int do_test(u64 sample_type, u64 sample_regs, u64 read_format)
+{
+	struct perf_evsel evsel = {
+		.needs_swap = false,
+		.attr = {
+			.sample_type = sample_type,
+			.read_format = read_format,
+		},
+	};
+	union perf_event *event;
+	union {
+		struct ip_callchain callchain;
+		u64 data[64];
+	} callchain = {
+		/* 3 ips */
+		.data = {3, 201, 202, 203},
+	};
+	union {
+		struct branch_stack branch_stack;
+		u64 data[64];
+	} branch_stack = {
+		/* 1 branch_entry */
+		.data = {1, 211, 212, 213},
+	};
+	u64 regs[64];
+	const u64 raw_data[] = {0x123456780a0b0c0dULL, 0x1102030405060708ULL};
+	const u64 data[] = {0x2211443366558877ULL, 0, 0xaabbccddeeff4321ULL};
+	struct perf_sample sample = {
+		.ip		= 101,
+		.pid		= 102,
+		.tid		= 103,
+		.time		= 104,
+		.addr		= 105,
+		.id		= 106,
+		.stream_id	= 107,
+		.period		= 108,
+		.weight		= 109,
+		.cpu		= 110,
+		.raw_size	= sizeof(raw_data),
+		.data_src	= 111,
+		.transaction	= 112,
+		.raw_data	= (void *)raw_data,
+		.callchain	= &callchain.callchain,
+		.branch_stack	= &branch_stack.branch_stack,
+		.user_regs	= {
+			.abi	= PERF_SAMPLE_REGS_ABI_64,
+			.mask	= sample_regs,
+			.regs	= regs,
+		},
+		.user_stack	= {
+			.size	= sizeof(data),
+			.data	= (void *)data,
+		},
+		.read		= {
+			.time_enabled = 0x030a59d664fca7deULL,
+			.time_running = 0x011b6ae553eb98edULL,
+		},
+		.intr_regs	= {
+			.abi	= PERF_SAMPLE_REGS_ABI_64,
+			.mask	= sample_regs,
+			.regs	= regs,
+		},
+	};
+	struct sample_read_value values[] = {{1, 5}, {9, 3}, {2, 7}, {6, 4},};
+	struct perf_sample sample_out;
+	size_t i, sz, bufsz;
+	int err, ret = -1;
+
+	if (sample_type & PERF_SAMPLE_REGS_USER)
+		evsel.attr.sample_regs_user = sample_regs;
+
+	if (sample_type & PERF_SAMPLE_REGS_INTR)
+		evsel.attr.sample_regs_intr = sample_regs;
+
+	for (i = 0; i < sizeof(regs); i++)
+		*(i + (u8 *)regs) = i & 0xfe;
+
+	if (read_format & PERF_FORMAT_GROUP) {
+		sample.read.group.nr     = 4;
+		sample.read.group.values = values;
+	} else {
+		sample.read.one.value = 0x08789faeb786aa87ULL;
+		sample.read.one.id    = 99;
+	}
+
+	sz = perf_event__sample_event_size(&sample, sample_type, read_format);
+	bufsz = sz + 4096; /* Add a bit for overrun checking */
+	event = malloc(bufsz);
+	if (!event) {
+		pr_debug("malloc failed\n");
+		return -1;
+	}
+
+	memset(event, 0xff, bufsz);
+	event->header.type = PERF_RECORD_SAMPLE;
+	event->header.misc = 0;
+	event->header.size = sz;
+
+	err = perf_event__synthesize_sample(event, sample_type, read_format,
+					    &sample, false);
+	if (err) {
+		pr_debug("%s failed for sample_type %#"PRIx64", error %d\n",
+			 "perf_event__synthesize_sample", sample_type, err);
+		goto out_free;
+	}
+
+	/* The data does not contain 0xff so we use that to check the size */
+	for (i = bufsz; i > 0; i--) {
+		if (*(i - 1 + (u8 *)event) != 0xff)
+			break;
+	}
+	if (i != sz) {
+		pr_debug("Event size mismatch: actual %zu vs expected %zu\n",
+			 i, sz);
+		goto out_free;
+	}
+
+	evsel.sample_size = __perf_evsel__sample_size(sample_type);
+
+	err = perf_evsel__parse_sample(&evsel, event, &sample_out);
+	if (err) {
+		pr_debug("%s failed for sample_type %#"PRIx64", error %d\n",
+			 "perf_evsel__parse_sample", sample_type, err);
+		goto out_free;
+	}
+
+	if (!samples_same(&sample, &sample_out, sample_type, read_format)) {
+		pr_debug("parsing failed for sample_type %#"PRIx64"\n",
+			 sample_type);
+		goto out_free;
+	}
+
+	ret = 0;
+out_free:
+	free(event);
+	if (ret && read_format)
+		pr_debug("read_format %#"PRIx64"\n", read_format);
+	return ret;
+}
+
+/**
+ * test__sample_parsing - test sample parsing.
+ *
+ * This function implements a test that synthesizes a sample event, parses it
+ * and then checks that the parsed sample matches the original sample.  The test
+ * checks sample format bits separately and together.  If the test passes %0 is
+ * returned, otherwise %-1 is returned.
+ */
+int test__sample_parsing(void)
+{
+	const u64 rf[] = {4, 5, 6, 7, 12, 13, 14, 15};
+	u64 sample_type;
+	u64 sample_regs;
+	size_t i;
+	int err;
+
+	/*
+	 * Fail the test if it has not been updated when new sample format bits
+	 * were added.  Please actually update the test rather than just change
+	 * the condition below.
+	 */
+	if (PERF_SAMPLE_MAX > PERF_SAMPLE_REGS_INTR << 1) {
+		pr_debug("sample format has changed, some new PERF_SAMPLE_ bit was introduced - test needs updating\n");
+		return -1;
+	}
+
+	/* Test each sample format bit separately */
+	for (sample_type = 1; sample_type != PERF_SAMPLE_MAX;
+	     sample_type <<= 1) {
+		/* Test read_format variations */
+		if (sample_type == PERF_SAMPLE_READ) {
+			for (i = 0; i < ARRAY_SIZE(rf); i++) {
+				err = do_test(sample_type, 0, rf[i]);
+				if (err)
+					return err;
+			}
+			continue;
+		}
+		sample_regs = 0;
+
+		if (sample_type == PERF_SAMPLE_REGS_USER)
+			sample_regs = 0x3fff;
+
+		if (sample_type == PERF_SAMPLE_REGS_INTR)
+			sample_regs = 0xff0fff;
+
+		err = do_test(sample_type, sample_regs, 0);
+		if (err)
+			return err;
+	}
+
+	/* Test all sample format bits together */
+	sample_type = PERF_SAMPLE_MAX - 1;
+	sample_regs = 0x3fff; /* shared yb intr and user regs */
+	for (i = 0; i < ARRAY_SIZE(rf); i++) {
+		err = do_test(sample_type, sample_regs, rf[i]);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
new file mode 100644
index 000000000..1aa21c907
--- /dev/null
+++ b/tools/perf/tests/sw-clock.c
@@ -0,0 +1,124 @@
+#include <unistd.h>
+#include <stdlib.h>
+#include <signal.h>
+#include <sys/mman.h>
+
+#include "tests.h"
+#include "util/evsel.h"
+#include "util/evlist.h"
+#include "util/cpumap.h"
+#include "util/thread_map.h"
+
+#define NR_LOOPS  10000000
+
+/*
+ * This test will open software clock events (cpu-clock, task-clock)
+ * then check their frequency -> period conversion has no artifact of
+ * setting period to 1 forcefully.
+ */
+static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
+{
+	int i, err = -1;
+	volatile int tmp = 0;
+	u64 total_periods = 0;
+	int nr_samples = 0;
+	char sbuf[STRERR_BUFSIZE];
+	union perf_event *event;
+	struct perf_evsel *evsel;
+	struct perf_evlist *evlist;
+	struct perf_event_attr attr = {
+		.type = PERF_TYPE_SOFTWARE,
+		.config = clock_id,
+		.sample_type = PERF_SAMPLE_PERIOD,
+		.exclude_kernel = 1,
+		.disabled = 1,
+		.freq = 1,
+	};
+
+	attr.sample_freq = 500;
+
+	evlist = perf_evlist__new();
+	if (evlist == NULL) {
+		pr_debug("perf_evlist__new\n");
+		return -1;
+	}
+
+	evsel = perf_evsel__new(&attr);
+	if (evsel == NULL) {
+		pr_debug("perf_evsel__new\n");
+		goto out_delete_evlist;
+	}
+	perf_evlist__add(evlist, evsel);
+
+	evlist->cpus = cpu_map__dummy_new();
+	evlist->threads = thread_map__new_by_tid(getpid());
+	if (!evlist->cpus || !evlist->threads) {
+		err = -ENOMEM;
+		pr_debug("Not enough memory to create thread/cpu maps\n");
+		goto out_delete_evlist;
+	}
+
+	if (perf_evlist__open(evlist)) {
+		const char *knob = "/proc/sys/kernel/perf_event_max_sample_rate";
+
+		err = -errno;
+		pr_debug("Couldn't open evlist: %s\nHint: check %s, using %" PRIu64 " in this test.\n",
+			 strerror_r(errno, sbuf, sizeof(sbuf)),
+			 knob, (u64)attr.sample_freq);
+		goto out_delete_evlist;
+	}
+
+	err = perf_evlist__mmap(evlist, 128, true);
+	if (err < 0) {
+		pr_debug("failed to mmap event: %d (%s)\n", errno,
+			 strerror_r(errno, sbuf, sizeof(sbuf)));
+		goto out_delete_evlist;
+	}
+
+	perf_evlist__enable(evlist);
+
+	/* collect samples */
+	for (i = 0; i < NR_LOOPS; i++)
+		tmp++;
+
+	perf_evlist__disable(evlist);
+
+	while ((event = perf_evlist__mmap_read(evlist, 0)) != NULL) {
+		struct perf_sample sample;
+
+		if (event->header.type != PERF_RECORD_SAMPLE)
+			goto next_event;
+
+		err = perf_evlist__parse_sample(evlist, event, &sample);
+		if (err < 0) {
+			pr_debug("Error during parse sample\n");
+			goto out_delete_evlist;
+		}
+
+		total_periods += sample.period;
+		nr_samples++;
+next_event:
+		perf_evlist__mmap_consume(evlist, 0);
+	}
+
+	if ((u64) nr_samples == total_periods) {
+		pr_debug("All (%d) samples have period value of 1!\n",
+			 nr_samples);
+		err = -1;
+	}
+
+out_delete_evlist:
+	perf_evlist__delete(evlist);
+	return err;
+}
+
+int test__sw_clock_freq(void)
+{
+	int ret;
+
+	ret = __test__sw_clock_freq(PERF_COUNT_SW_CPU_CLOCK);
+	if (!ret)
+		ret = __test__sw_clock_freq(PERF_COUNT_SW_TASK_CLOCK);
+
+	return ret;
+}
diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c
new file mode 100644
index 000000000..cc68648c7
--- /dev/null
+++ b/tools/perf/tests/switch-tracking.c
@@ -0,0 +1,572 @@
+#include <sys/time.h>
+#include <sys/prctl.h>
+#include <time.h>
+#include <stdlib.h>
+
+#include "parse-events.h"
+#include "evlist.h"
+#include "evsel.h"
+#include "thread_map.h"
+#include "cpumap.h"
+#include "tests.h"
+
+static int spin_sleep(void)
+{
+	struct timeval start, now, diff, maxtime;
+	struct timespec ts;
+	int err, i;
+
+	maxtime.tv_sec = 0;
+	maxtime.tv_usec = 50000;
+
+	err = gettimeofday(&start, NULL);
+	if (err)
+		return err;
+
+	/* Spin for 50ms */
+	while (1) {
+		for (i = 0; i < 1000; i++)
+			barrier();
+
+		err = gettimeofday(&now, NULL);
+		if (err)
+			return err;
+
+		timersub(&now, &start, &diff);
+		if (timercmp(&diff, &maxtime, > /* For checkpatch */))
+			break;
+	}
+
+	ts.tv_nsec = 50 * 1000 * 1000;
+	ts.tv_sec = 0;
+
+	/* Sleep for 50ms */
+	err = nanosleep(&ts, NULL);
+	if (err == EINTR)
+		err = 0;
+
+	return err;
+}
+
+struct switch_tracking {
+	struct perf_evsel *switch_evsel;
+	struct perf_evsel *cycles_evsel;
+	pid_t *tids;
+	int nr_tids;
+	int comm_seen[4];
+	int cycles_before_comm_1;
+	int cycles_between_comm_2_and_comm_3;
+	int cycles_after_comm_4;
+};
+
+static int check_comm(struct switch_tracking *switch_tracking,
+		      union perf_event *event, const char *comm, int nr)
+{
+	if (event->header.type == PERF_RECORD_COMM &&
+	    (pid_t)event->comm.pid == getpid() &&
+	    (pid_t)event->comm.tid == getpid() &&
+	    strcmp(event->comm.comm, comm) == 0) {
+		if (switch_tracking->comm_seen[nr]) {
+			pr_debug("Duplicate comm event\n");
+			return -1;
+		}
+		switch_tracking->comm_seen[nr] = 1;
+		pr_debug3("comm event: %s nr: %d\n", event->comm.comm, nr);
+		return 1;
+	}
+	return 0;
+}
+
+static int check_cpu(struct switch_tracking *switch_tracking, int cpu)
+{
+	int i, nr = cpu + 1;
+
+	if (cpu < 0)
+		return -1;
+
+	if (!switch_tracking->tids) {
+		switch_tracking->tids = calloc(nr, sizeof(pid_t));
+		if (!switch_tracking->tids)
+			return -1;
+		for (i = 0; i < nr; i++)
+			switch_tracking->tids[i] = -1;
+		switch_tracking->nr_tids = nr;
+		return 0;
+	}
+
+	if (cpu >= switch_tracking->nr_tids) {
+		void *addr;
+
+		addr = realloc(switch_tracking->tids, nr * sizeof(pid_t));
+		if (!addr)
+			return -1;
+		switch_tracking->tids = addr;
+		for (i = switch_tracking->nr_tids; i < nr; i++)
+			switch_tracking->tids[i] = -1;
+		switch_tracking->nr_tids = nr;
+		return 0;
+	}
+
+	return 0;
+}
+
+static int process_sample_event(struct perf_evlist *evlist,
+				union perf_event *event,
+				struct switch_tracking *switch_tracking)
+{
+	struct perf_sample sample;
+	struct perf_evsel *evsel;
+	pid_t next_tid, prev_tid;
+	int cpu, err;
+
+	if (perf_evlist__parse_sample(evlist, event, &sample)) {
+		pr_debug("perf_evlist__parse_sample failed\n");
+		return -1;
+	}
+
+	evsel = perf_evlist__id2evsel(evlist, sample.id);
+	if (evsel == switch_tracking->switch_evsel) {
+		next_tid = perf_evsel__intval(evsel, &sample, "next_pid");
+		prev_tid = perf_evsel__intval(evsel, &sample, "prev_pid");
+		cpu = sample.cpu;
+		pr_debug3("sched_switch: cpu: %d prev_tid %d next_tid %d\n",
+			  cpu, prev_tid, next_tid);
+		err = check_cpu(switch_tracking, cpu);
+		if (err)
+			return err;
+		/*
+		 * Check for no missing sched_switch events i.e. that the
+		 * evsel->system_wide flag has worked.
+		 */
+		if (switch_tracking->tids[cpu] != -1 &&
+		    switch_tracking->tids[cpu] != prev_tid) {
+			pr_debug("Missing sched_switch events\n");
+			return -1;
+		}
+		switch_tracking->tids[cpu] = next_tid;
+	}
+
+	if (evsel == switch_tracking->cycles_evsel) {
+		pr_debug3("cycles event\n");
+		if (!switch_tracking->comm_seen[0])
+			switch_tracking->cycles_before_comm_1 = 1;
+		if (switch_tracking->comm_seen[1] &&
+		    !switch_tracking->comm_seen[2])
+			switch_tracking->cycles_between_comm_2_and_comm_3 = 1;
+		if (switch_tracking->comm_seen[3])
+			switch_tracking->cycles_after_comm_4 = 1;
+	}
+
+	return 0;
+}
+
+static int process_event(struct perf_evlist *evlist, union perf_event *event,
+			 struct switch_tracking *switch_tracking)
+{
+	if (event->header.type == PERF_RECORD_SAMPLE)
+		return process_sample_event(evlist, event, switch_tracking);
+
+	if (event->header.type == PERF_RECORD_COMM) {
+		int err, done = 0;
+
+		err = check_comm(switch_tracking, event, "Test COMM 1", 0);
+		if (err < 0)
+			return -1;
+		done += err;
+		err = check_comm(switch_tracking, event, "Test COMM 2", 1);
+		if (err < 0)
+			return -1;
+		done += err;
+		err = check_comm(switch_tracking, event, "Test COMM 3", 2);
+		if (err < 0)
+			return -1;
+		done += err;
+		err = check_comm(switch_tracking, event, "Test COMM 4", 3);
+		if (err < 0)
+			return -1;
+		done += err;
+		if (done != 1) {
+			pr_debug("Unexpected comm event\n");
+			return -1;
+		}
+	}
+
+	return 0;
+}
+
+struct event_node {
+	struct list_head list;
+	union perf_event *event;
+	u64 event_time;
+};
+
+static int add_event(struct perf_evlist *evlist, struct list_head *events,
+		     union perf_event *event)
+{
+	struct perf_sample sample;
+	struct event_node *node;
+
+	node = malloc(sizeof(struct event_node));
+	if (!node) {
+		pr_debug("malloc failed\n");
+		return -1;
+	}
+	node->event = event;
+	list_add(&node->list, events);
+
+	if (perf_evlist__parse_sample(evlist, event, &sample)) {
+		pr_debug("perf_evlist__parse_sample failed\n");
+		return -1;
+	}
+
+	if (!sample.time) {
+		pr_debug("event with no time\n");
+		return -1;
+	}
+
+	node->event_time = sample.time;
+
+	return 0;
+}
+
+static void free_event_nodes(struct list_head *events)
+{
+	struct event_node *node;
+
+	while (!list_empty(events)) {
+		node = list_entry(events->next, struct event_node, list);
+		list_del(&node->list);
+		free(node);
+	}
+}
+
+static int compar(const void *a, const void *b)
+{
+	const struct event_node *nodea = a;
+	const struct event_node *nodeb = b;
+	s64 cmp = nodea->event_time - nodeb->event_time;
+
+	return cmp;
+}
+
+static int process_events(struct perf_evlist *evlist,
+			  struct switch_tracking *switch_tracking)
+{
+	union perf_event *event;
+	unsigned pos, cnt = 0;
+	LIST_HEAD(events);
+	struct event_node *events_array, *node;
+	int i, ret;
+
+	for (i = 0; i < evlist->nr_mmaps; i++) {
+		while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
+			cnt += 1;
+			ret = add_event(evlist, &events, event);
+			perf_evlist__mmap_consume(evlist, i);
+			if (ret < 0)
+				goto out_free_nodes;
+		}
+	}
+
+	events_array = calloc(cnt, sizeof(struct event_node));
+	if (!events_array) {
+		pr_debug("calloc failed\n");
+		ret = -1;
+		goto out_free_nodes;
+	}
+
+	pos = 0;
+	list_for_each_entry(node, &events, list)
+		events_array[pos++] = *node;
+
+	qsort(events_array, cnt, sizeof(struct event_node), compar);
+
+	for (pos = 0; pos < cnt; pos++) {
+		ret = process_event(evlist, events_array[pos].event,
+				    switch_tracking);
+		if (ret < 0)
+			goto out_free;
+	}
+
+	ret = 0;
+out_free:
+	pr_debug("%u events recorded\n", cnt);
+	free(events_array);
+out_free_nodes:
+	free_event_nodes(&events);
+	return ret;
+}
+
+/**
+ * test__switch_tracking - test using sched_switch and tracking events.
+ *
+ * This function implements a test that checks that sched_switch events and
+ * tracking events can be recorded for a workload (current process) using the
+ * evsel->system_wide and evsel->tracking flags (respectively) with other events
+ * sometimes enabled or disabled.
+ */
+int test__switch_tracking(void)
+{
+	const char *sched_switch = "sched:sched_switch";
+	struct switch_tracking switch_tracking = { .tids = NULL, };
+	struct record_opts opts = {
+		.mmap_pages	     = UINT_MAX,
+		.user_freq	     = UINT_MAX,
+		.user_interval	     = ULLONG_MAX,
+		.freq		     = 4000,
+		.target		     = {
+			.uses_mmap   = true,
+		},
+	};
+	struct thread_map *threads = NULL;
+	struct cpu_map *cpus = NULL;
+	struct perf_evlist *evlist = NULL;
+	struct perf_evsel *evsel, *cpu_clocks_evsel, *cycles_evsel;
+	struct perf_evsel *switch_evsel, *tracking_evsel;
+	const char *comm;
+	int err = -1;
+
+	threads = thread_map__new(-1, getpid(), UINT_MAX);
+	if (!threads) {
+		pr_debug("thread_map__new failed!\n");
+		goto out_err;
+	}
+
+	cpus = cpu_map__new(NULL);
+	if (!cpus) {
+		pr_debug("cpu_map__new failed!\n");
+		goto out_err;
+	}
+
+	evlist = perf_evlist__new();
+	if (!evlist) {
+		pr_debug("perf_evlist__new failed!\n");
+		goto out_err;
+	}
+
+	perf_evlist__set_maps(evlist, cpus, threads);
+
+	/* First event */
+	err = parse_events(evlist, "cpu-clock:u");
+	if (err) {
+		pr_debug("Failed to parse event dummy:u\n");
+		goto out_err;
+	}
+
+	cpu_clocks_evsel = perf_evlist__last(evlist);
+
+	/* Second event */
+	err = parse_events(evlist, "cycles:u");
+	if (err) {
+		pr_debug("Failed to parse event cycles:u\n");
+		goto out_err;
+	}
+
+	cycles_evsel = perf_evlist__last(evlist);
+
+	/* Third event */
+	if (!perf_evlist__can_select_event(evlist, sched_switch)) {
+		fprintf(stderr, " (no sched_switch)");
+		err = 0;
+		goto out;
+	}
+
+	err = parse_events(evlist, sched_switch);
+	if (err) {
+		pr_debug("Failed to parse event %s\n", sched_switch);
+		goto out_err;
+	}
+
+	switch_evsel = perf_evlist__last(evlist);
+
+	perf_evsel__set_sample_bit(switch_evsel, CPU);
+	perf_evsel__set_sample_bit(switch_evsel, TIME);
+
+	switch_evsel->system_wide = true;
+	switch_evsel->no_aux_samples = true;
+	switch_evsel->immediate = true;
+
+	/* Test moving an event to the front */
+	if (cycles_evsel == perf_evlist__first(evlist)) {
+		pr_debug("cycles event already at front");
+		goto out_err;
+	}
+	perf_evlist__to_front(evlist, cycles_evsel);
+	if (cycles_evsel != perf_evlist__first(evlist)) {
+		pr_debug("Failed to move cycles event to front");
+		goto out_err;
+	}
+
+	perf_evsel__set_sample_bit(cycles_evsel, CPU);
+	perf_evsel__set_sample_bit(cycles_evsel, TIME);
+
+	/* Fourth event */
+	err = parse_events(evlist, "dummy:u");
+	if (err) {
+		pr_debug("Failed to parse event dummy:u\n");
+		goto out_err;
+	}
+
+	tracking_evsel = perf_evlist__last(evlist);
+
+	perf_evlist__set_tracking_event(evlist, tracking_evsel);
+
+	tracking_evsel->attr.freq = 0;
+	tracking_evsel->attr.sample_period = 1;
+
+	perf_evsel__set_sample_bit(tracking_evsel, TIME);
+
+	/* Config events */
+	perf_evlist__config(evlist, &opts);
+
+	/* Check moved event is still at the front */
+	if (cycles_evsel != perf_evlist__first(evlist)) {
+		pr_debug("Front event no longer at front");
+		goto out_err;
+	}
+
+	/* Check tracking event is tracking */
+	if (!tracking_evsel->attr.mmap || !tracking_evsel->attr.comm) {
+		pr_debug("Tracking event not tracking\n");
+		goto out_err;
+	}
+
+	/* Check non-tracking events are not tracking */
+	evlist__for_each(evlist, evsel) {
+		if (evsel != tracking_evsel) {
+			if (evsel->attr.mmap || evsel->attr.comm) {
+				pr_debug("Non-tracking event is tracking\n");
+				goto out_err;
+			}
+		}
+	}
+
+	if (perf_evlist__open(evlist) < 0) {
+		fprintf(stderr, " (not supported)");
+		err = 0;
+		goto out;
+	}
+
+	err = perf_evlist__mmap(evlist, UINT_MAX, false);
+	if (err) {
+		pr_debug("perf_evlist__mmap failed!\n");
+		goto out_err;
+	}
+
+	perf_evlist__enable(evlist);
+
+	err = perf_evlist__disable_event(evlist, cpu_clocks_evsel);
+	if (err) {
+		pr_debug("perf_evlist__disable_event failed!\n");
+		goto out_err;
+	}
+
+	err = spin_sleep();
+	if (err) {
+		pr_debug("spin_sleep failed!\n");
+		goto out_err;
+	}
+
+	comm = "Test COMM 1";
+	err = prctl(PR_SET_NAME, (unsigned long)comm, 0, 0, 0);
+	if (err) {
+		pr_debug("PR_SET_NAME failed!\n");
+		goto out_err;
+	}
+
+	err = perf_evlist__disable_event(evlist, cycles_evsel);
+	if (err) {
+		pr_debug("perf_evlist__disable_event failed!\n");
+		goto out_err;
+	}
+
+	comm = "Test COMM 2";
+	err = prctl(PR_SET_NAME, (unsigned long)comm, 0, 0, 0);
+	if (err) {
+		pr_debug("PR_SET_NAME failed!\n");
+		goto out_err;
+	}
+
+	err = spin_sleep();
+	if (err) {
+		pr_debug("spin_sleep failed!\n");
+		goto out_err;
+	}
+
+	comm = "Test COMM 3";
+	err = prctl(PR_SET_NAME, (unsigned long)comm, 0, 0, 0);
+	if (err) {
+		pr_debug("PR_SET_NAME failed!\n");
+		goto out_err;
+	}
+
+	err = perf_evlist__enable_event(evlist, cycles_evsel);
+	if (err) {
+		pr_debug("perf_evlist__disable_event failed!\n");
+		goto out_err;
+	}
+
+	comm = "Test COMM 4";
+	err = prctl(PR_SET_NAME, (unsigned long)comm, 0, 0, 0);
+	if (err) {
+		pr_debug("PR_SET_NAME failed!\n");
+		goto out_err;
+	}
+
+	err = spin_sleep();
+	if (err) {
+		pr_debug("spin_sleep failed!\n");
+		goto out_err;
+	}
+
+	perf_evlist__disable(evlist);
+
+	switch_tracking.switch_evsel = switch_evsel;
+	switch_tracking.cycles_evsel = cycles_evsel;
+
+	err = process_events(evlist, &switch_tracking);
+
+	zfree(&switch_tracking.tids);
+
+	if (err)
+		goto out_err;
+
+	/* Check all 4 comm events were seen i.e. that evsel->tracking works */
+	if (!switch_tracking.comm_seen[0] || !switch_tracking.comm_seen[1] ||
+	    !switch_tracking.comm_seen[2] || !switch_tracking.comm_seen[3]) {
+		pr_debug("Missing comm events\n");
+		goto out_err;
+	}
+
+	/* Check cycles event got enabled */
+	if (!switch_tracking.cycles_before_comm_1) {
+		pr_debug("Missing cycles events\n");
+		goto out_err;
+	}
+
+	/* Check cycles event got disabled */
+	if (switch_tracking.cycles_between_comm_2_and_comm_3) {
+		pr_debug("cycles events even though event was disabled\n");
+		goto out_err;
+	}
+
+	/* Check cycles event got enabled again */
+	if (!switch_tracking.cycles_after_comm_4) {
+		pr_debug("Missing cycles events\n");
+		goto out_err;
+	}
+out:
+	if (evlist) {
+		perf_evlist__disable(evlist);
+		perf_evlist__delete(evlist);
+	} else {
+		cpu_map__delete(cpus);
+		thread_map__delete(threads);
+	}
+
+	return err;
+
+out_err:
+	err = -1;
+	goto out;
+}
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
new file mode 100644
index 000000000..3a8fedef8
--- /dev/null
+++ b/tools/perf/tests/task-exit.c
@@ -0,0 +1,120 @@
+#include "evlist.h"
+#include "evsel.h"
+#include "thread_map.h"
+#include "cpumap.h"
+#include "tests.h"
+
+#include <signal.h>
+
+static int exited;
+static int nr_exit;
+
+static void sig_handler(int sig __maybe_unused)
+{
+	exited = 1;
+}
+
+/*
+ * perf_evlist__prepare_workload will send a SIGUSR1 if the fork fails, since
+ * we asked by setting its exec_error to this handler.
+ */
+static void workload_exec_failed_signal(int signo __maybe_unused,
+					siginfo_t *info __maybe_unused,
+					void *ucontext __maybe_unused)
+{
+	exited	= 1;
+	nr_exit = -1;
+}
+
+/*
+ * This test will start a workload that does nothing then it checks
+ * if the number of exit event reported by the kernel is 1 or not
+ * in order to check the kernel returns correct number of event.
+ */
+int test__task_exit(void)
+{
+	int err = -1;
+	union perf_event *event;
+	struct perf_evsel *evsel;
+	struct perf_evlist *evlist;
+	struct target target = {
+		.uid		= UINT_MAX,
+		.uses_mmap	= true,
+	};
+	const char *argv[] = { "true", NULL };
+	char sbuf[STRERR_BUFSIZE];
+
+	signal(SIGCHLD, sig_handler);
+
+	evlist = perf_evlist__new_default();
+	if (evlist == NULL) {
+		pr_debug("perf_evlist__new_default\n");
+		return -1;
+	}
+
+	/*
+	 * Create maps of threads and cpus to monitor. In this case
+	 * we start with all threads and cpus (-1, -1) but then in
+	 * perf_evlist__prepare_workload we'll fill in the only thread
+	 * we're monitoring, the one forked there.
+	 */
+	evlist->cpus = cpu_map__dummy_new();
+	evlist->threads = thread_map__new_by_tid(-1);
+	if (!evlist->cpus || !evlist->threads) {
+		err = -ENOMEM;
+		pr_debug("Not enough memory to create thread/cpu maps\n");
+		goto out_delete_evlist;
+	}
+
+	err = perf_evlist__prepare_workload(evlist, &target, argv, false,
+					    workload_exec_failed_signal);
+	if (err < 0) {
+		pr_debug("Couldn't run the workload!\n");
+		goto out_delete_evlist;
+	}
+
+	evsel = perf_evlist__first(evlist);
+	evsel->attr.task = 1;
+	evsel->attr.sample_freq = 0;
+	evsel->attr.inherit = 0;
+	evsel->attr.watermark = 0;
+	evsel->attr.wakeup_events = 1;
+	evsel->attr.exclude_kernel = 1;
+
+	err = perf_evlist__open(evlist);
+	if (err < 0) {
+		pr_debug("Couldn't open the evlist: %s\n",
+			 strerror_r(-err, sbuf, sizeof(sbuf)));
+		goto out_delete_evlist;
+	}
+
+	if (perf_evlist__mmap(evlist, 128, true) < 0) {
+		pr_debug("failed to mmap events: %d (%s)\n", errno,
+			 strerror_r(errno, sbuf, sizeof(sbuf)));
+		goto out_delete_evlist;
+	}
+
+	perf_evlist__start_workload(evlist);
+
+retry:
+	while ((event = perf_evlist__mmap_read(evlist, 0)) != NULL) {
+		if (event->header.type == PERF_RECORD_EXIT)
+			nr_exit++;
+
+		perf_evlist__mmap_consume(evlist, 0);
+	}
+
+	if (!exited || !nr_exit) {
+		perf_evlist__poll(evlist, -1);
+		goto retry;
+	}
+
+	if (nr_exit != 1) {
+		pr_debug("received %d EXIT records\n", nr_exit);
+		err = -1;
+	}
+
+out_delete_evlist:
+	perf_evlist__delete(evlist);
+	return err;
+}
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
new file mode 100644
index 000000000..52758a33f
--- /dev/null
+++ b/tools/perf/tests/tests.h
@@ -0,0 +1,64 @@
+#ifndef TESTS_H
+#define TESTS_H
+
+#define TEST_ASSERT_VAL(text, cond)					 \
+do {									 \
+	if (!(cond)) {							 \
+		pr_debug("FAILED %s:%d %s\n", __FILE__, __LINE__, text); \
+		return -1;						 \
+	}								 \
+} while (0)
+
+enum {
+	TEST_OK   =  0,
+	TEST_FAIL = -1,
+	TEST_SKIP = -2,
+};
+
+/* Tests */
+int test__vmlinux_matches_kallsyms(void);
+int test__open_syscall_event(void);
+int test__open_syscall_event_on_all_cpus(void);
+int test__basic_mmap(void);
+int test__PERF_RECORD(void);
+int test__rdpmc(void);
+int test__perf_evsel__roundtrip_name_test(void);
+int test__perf_evsel__tp_sched_test(void);
+int test__syscall_open_tp_fields(void);
+int test__pmu(void);
+int test__attr(void);
+int test__dso_data(void);
+int test__dso_data_cache(void);
+int test__dso_data_reopen(void);
+int test__parse_events(void);
+int test__hists_link(void);
+int test__python_use(void);
+int test__bp_signal(void);
+int test__bp_signal_overflow(void);
+int test__task_exit(void);
+int test__sw_clock_freq(void);
+int test__perf_time_to_tsc(void);
+int test__code_reading(void);
+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);
+int test__hists_cumulate(void);
+int test__switch_tracking(void);
+int test__fdarray__filter(void);
+int test__fdarray__add(void);
+int test__kmod_path__parse(void);
+
+#if defined(__x86_64__) || defined(__i386__) || defined(__arm__)
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
+struct thread;
+struct perf_sample;
+int test__arch_unwind_sample(struct perf_sample *sample,
+			     struct thread *thread);
+#endif
+#endif
+#endif /* TESTS_H */
diff --git a/tools/perf/tests/thread-mg-share.c b/tools/perf/tests/thread-mg-share.c
new file mode 100644
index 000000000..b028499dd
--- /dev/null
+++ b/tools/perf/tests/thread-mg-share.c
@@ -0,0 +1,91 @@
+#include "tests.h"
+#include "machine.h"
+#include "thread.h"
+#include "map.h"
+#include "debug.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;
+}
diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c
new file mode 100644
index 000000000..3d9088003
--- /dev/null
+++ b/tools/perf/tests/vmlinux-kallsyms.c
@@ -0,0 +1,242 @@
+#include <linux/compiler.h>
+#include <linux/rbtree.h>
+#include <string.h>
+#include "map.h"
+#include "symbol.h"
+#include "util.h"
+#include "tests.h"
+#include "debug.h"
+#include "machine.h"
+
+static int vmlinux_matches_kallsyms_filter(struct map *map __maybe_unused,
+					   struct symbol *sym)
+{
+	bool *visited = symbol__priv(sym);
+	*visited = true;
+	return 0;
+}
+
+#define UM(x) kallsyms_map->unmap_ip(kallsyms_map, (x))
+
+int test__vmlinux_matches_kallsyms(void)
+{
+	int err = -1;
+	struct rb_node *nd;
+	struct symbol *sym;
+	struct map *kallsyms_map, *vmlinux_map;
+	struct machine kallsyms, vmlinux;
+	enum map_type type = MAP__FUNCTION;
+	u64 mem_start, mem_end;
+
+	/*
+	 * Step 1:
+	 *
+	 * Init the machines that will hold kernel, modules obtained from
+	 * both vmlinux + .ko files and from /proc/kallsyms split by modules.
+	 */
+	machine__init(&kallsyms, "", HOST_KERNEL_ID);
+	machine__init(&vmlinux, "", HOST_KERNEL_ID);
+
+	/*
+	 * Step 2:
+	 *
+	 * Create the kernel maps for kallsyms and the DSO where we will then
+	 * load /proc/kallsyms. Also create the modules maps from /proc/modules
+	 * and find the .ko files that match them in /lib/modules/`uname -r`/.
+	 */
+	if (machine__create_kernel_maps(&kallsyms) < 0) {
+		pr_debug("machine__create_kernel_maps ");
+		goto out;
+	}
+
+	/*
+	 * Step 3:
+	 *
+	 * Load and split /proc/kallsyms into multiple maps, one per module.
+	 */
+	if (machine__load_kallsyms(&kallsyms, "/proc/kallsyms", type, NULL) <= 0) {
+		pr_debug("dso__load_kallsyms ");
+		goto out;
+	}
+
+	/*
+	 * Step 4:
+	 *
+	 * kallsyms will be internally on demand sorted by name so that we can
+	 * find the reference relocation * symbol, i.e. the symbol we will use
+	 * to see if the running kernel was relocated by checking if it has the
+	 * same value in the vmlinux file we load.
+	 */
+	kallsyms_map = machine__kernel_map(&kallsyms, type);
+
+	/*
+	 * Step 5:
+	 *
+	 * Now repeat step 2, this time for the vmlinux file we'll auto-locate.
+	 */
+	if (machine__create_kernel_maps(&vmlinux) < 0) {
+		pr_debug("machine__create_kernel_maps ");
+		goto out;
+	}
+
+	vmlinux_map = machine__kernel_map(&vmlinux, type);
+
+	/*
+	 * Step 6:
+	 *
+	 * Locate a vmlinux file in the vmlinux path that has a buildid that
+	 * matches the one of the running kernel.
+	 *
+	 * While doing that look if we find the ref reloc symbol, if we find it
+	 * we'll have its ref_reloc_symbol.unrelocated_addr and then
+	 * maps__reloc_vmlinux will notice and set proper ->[un]map_ip routines
+	 * to fixup the symbols.
+	 */
+	if (machine__load_vmlinux_path(&vmlinux, type,
+				       vmlinux_matches_kallsyms_filter) <= 0) {
+		pr_debug("Couldn't find a vmlinux that matches the kernel running on this machine, skipping test\n");
+		err = TEST_SKIP;
+		goto out;
+	}
+
+	err = 0;
+	/*
+	 * Step 7:
+	 *
+	 * Now look at the symbols in the vmlinux DSO and check if we find all of them
+	 * in the kallsyms dso. For the ones that are in both, check its names and
+	 * end addresses too.
+	 */
+	for (nd = rb_first(&vmlinux_map->dso->symbols[type]); nd; nd = rb_next(nd)) {
+		struct symbol *pair, *first_pair;
+		bool backwards = true;
+
+		sym  = rb_entry(nd, struct symbol, rb_node);
+
+		if (sym->start == sym->end)
+			continue;
+
+		mem_start = vmlinux_map->unmap_ip(vmlinux_map, sym->start);
+		mem_end = vmlinux_map->unmap_ip(vmlinux_map, sym->end);
+
+		first_pair = machine__find_kernel_symbol(&kallsyms, type,
+							 mem_start, NULL, NULL);
+		pair = first_pair;
+
+		if (pair && UM(pair->start) == mem_start) {
+next_pair:
+			if (strcmp(sym->name, pair->name) == 0) {
+				/*
+				 * kallsyms don't have the symbol end, so we
+				 * set that by using the next symbol start - 1,
+				 * in some cases we get this up to a page
+				 * wrong, trace_kmalloc when I was developing
+				 * this code was one such example, 2106 bytes
+				 * off the real size. More than that and we
+				 * _really_ have a problem.
+				 */
+				s64 skew = mem_end - UM(pair->end);
+				if (llabs(skew) >= page_size)
+					pr_debug("%#" PRIx64 ": diff end addr for %s v: %#" PRIx64 " k: %#" PRIx64 "\n",
+						 mem_start, sym->name, mem_end,
+						 UM(pair->end));
+
+				/*
+				 * Do not count this as a failure, because we
+				 * could really find a case where it's not
+				 * possible to get proper function end from
+				 * kallsyms.
+				 */
+				continue;
+
+			} else {
+				struct rb_node *nnd;
+detour:
+				nnd = backwards ? rb_prev(&pair->rb_node) :
+						  rb_next(&pair->rb_node);
+				if (nnd) {
+					struct symbol *next = rb_entry(nnd, struct symbol, rb_node);
+
+					if (UM(next->start) == mem_start) {
+						pair = next;
+						goto next_pair;
+					}
+				}
+
+				if (backwards) {
+					backwards = false;
+					pair = first_pair;
+					goto detour;
+				}
+
+				pr_debug("%#" PRIx64 ": diff name v: %s k: %s\n",
+					 mem_start, sym->name, pair->name);
+			}
+		} else
+			pr_debug("%#" PRIx64 ": %s not on kallsyms\n",
+				 mem_start, sym->name);
+
+		err = -1;
+	}
+
+	if (!verbose)
+		goto out;
+
+	pr_info("Maps only in vmlinux:\n");
+
+	for (nd = rb_first(&vmlinux.kmaps.maps[type]); nd; nd = rb_next(nd)) {
+		struct map *pos = rb_entry(nd, struct map, rb_node), *pair;
+		/*
+		 * If it is the kernel, kallsyms is always "[kernel.kallsyms]", while
+		 * the kernel will have the path for the vmlinux file being used,
+		 * so use the short name, less descriptive but the same ("[kernel]" in
+		 * both cases.
+		 */
+		pair = map_groups__find_by_name(&kallsyms.kmaps, type,
+						(pos->dso->kernel ?
+							pos->dso->short_name :
+							pos->dso->name));
+		if (pair)
+			pair->priv = 1;
+		else
+			map__fprintf(pos, stderr);
+	}
+
+	pr_info("Maps in vmlinux with a different name in kallsyms:\n");
+
+	for (nd = rb_first(&vmlinux.kmaps.maps[type]); nd; nd = rb_next(nd)) {
+		struct map *pos = rb_entry(nd, struct map, rb_node), *pair;
+
+		mem_start = vmlinux_map->unmap_ip(vmlinux_map, pos->start);
+		mem_end = vmlinux_map->unmap_ip(vmlinux_map, pos->end);
+
+		pair = map_groups__find(&kallsyms.kmaps, type, mem_start);
+		if (pair == NULL || pair->priv)
+			continue;
+
+		if (pair->start == mem_start) {
+			pair->priv = 1;
+			pr_info(" %" PRIx64 "-%" PRIx64 " %" PRIx64 " %s in kallsyms as",
+				pos->start, pos->end, pos->pgoff, pos->dso->name);
+			if (mem_end != pair->end)
+				pr_info(":\n*%" PRIx64 "-%" PRIx64 " %" PRIx64,
+					pair->start, pair->end, pair->pgoff);
+			pr_info(" %s\n", pair->dso->name);
+			pair->priv = 1;
+		}
+	}
+
+	pr_info("Maps only in kallsyms:\n");
+
+	for (nd = rb_first(&kallsyms.kmaps.maps[type]);
+	     nd; nd = rb_next(nd)) {
+		struct map *pos = rb_entry(nd, struct map, rb_node);
+
+		if (!pos->priv)
+			map__fprintf(pos, stderr);
+	}
+out:
+	machine__exit(&kallsyms);
+	machine__exit(&vmlinux);
+	return err;
+}