Merge tag 'perf-core-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

 - UAPI fixes, from David Howels

 - Separate perf tests into multiple objects, one per test, from Jiri Olsa.

 - Fixes to /proc/pid/maps parsing, preparatory to supporting data maps,
   from Namhyung Kim

 - Fix compile error for non-NEWT builds, from Namhyung Kim

 - Implement ui_progress for GTK, from Namhyung Kim

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

52 files changed, 2050 insertions, 1785 deletions

diff --git a/Makefile b/Makefile
index 14c93b39b929..08a31d8b7e39 100644
--- a/Makefile
+++ b/Makefile
@@ -1321,10 +1321,12 @@ kernelversion:
 
 # Clear a bunch of variables before executing the submake
 tools/: FORCE
-	$(Q)$(MAKE) LDFLAGS= MAKEFLAGS= -C $(src)/tools/
+	$(Q)mkdir -p $(objtree)/tools
+	$(Q)$(MAKE) LDFLAGS= MAKEFLAGS= O=$(objtree) subdir=tools -C $(src)/tools/
 
 tools/%: FORCE
-	$(Q)$(MAKE) LDFLAGS= MAKEFLAGS= -C $(src)/tools/ $*
+	$(Q)mkdir -p $(objtree)/tools
+	$(Q)$(MAKE) LDFLAGS= MAKEFLAGS= O=$(objtree) subdir=tools -C $(src)/tools/ $*
 
 # Single targets
 # ---------------------------------------------------------------------------
diff --git a/tools/Makefile b/tools/Makefile
index 3ae43947a171..1f9a529fe544 100644
--- a/tools/Makefile
+++ b/tools/Makefile
@@ -31,44 +31,44 @@ help:
 	@echo '  clean: a summary clean target to clean _all_ folders'
 
 cpupower: FORCE
-	$(QUIET_SUBDIR0)power/$@/ $(QUIET_SUBDIR1)
+	$(call descend,power/$@)
 
 firewire lguest perf usb virtio vm: FORCE
-	$(QUIET_SUBDIR0)$@/ $(QUIET_SUBDIR1)
+	$(call descend,$@)
 
 selftests: FORCE
-	$(QUIET_SUBDIR0)testing/$@/ $(QUIET_SUBDIR1)
+	$(call descend,testing/$@)
 
 turbostat x86_energy_perf_policy: FORCE
-	$(QUIET_SUBDIR0)power/x86/$@/ $(QUIET_SUBDIR1)
+	$(call descend,power/x86/$@)
 
 cpupower_install:
-	$(QUIET_SUBDIR0)power/$(@:_install=)/ $(QUIET_SUBDIR1) install
+	$(call descend,power/$(@:_install=),install)
 
 firewire_install lguest_install perf_install usb_install virtio_install vm_install:
-	$(QUIET_SUBDIR0)$(@:_install=)/ $(QUIET_SUBDIR1) install
+	$(call descend,$(@:_install=),install)
 
 selftests_install:
-	$(QUIET_SUBDIR0)testing/$(@:_clean=)/ $(QUIET_SUBDIR1) install
+	$(call descend,testing/$(@:_clean=),install)
 
 turbostat_install x86_energy_perf_policy_install:
-	$(QUIET_SUBDIR0)power/x86/$(@:_install=)/ $(QUIET_SUBDIR1) install
+	$(call descend,power/x86/$(@:_install=),install)
 
 install: cpupower_install firewire_install lguest_install perf_install \
 		selftests_install turbostat_install usb_install virtio_install \
 		vm_install x86_energy_perf_policy_install
 
 cpupower_clean:
-	$(QUIET_SUBDIR0)power/cpupower/ $(QUIET_SUBDIR1) clean
+	$(call descend,power/cpupower,clean)
 
 firewire_clean lguest_clean perf_clean usb_clean virtio_clean vm_clean:
-	$(QUIET_SUBDIR0)$(@:_clean=)/ $(QUIET_SUBDIR1) clean
+	$(call descend,$(@:_clean=),clean)
 
 selftests_clean:
-	$(QUIET_SUBDIR0)testing/$(@:_clean=)/ $(QUIET_SUBDIR1) clean
+	$(call descend,testing/$(@:_clean=),clean)
 
 turbostat_clean x86_energy_perf_policy_clean:
-	$(QUIET_SUBDIR0)power/x86/$(@:_clean=)/ $(QUIET_SUBDIR1) clean
+	$(call descend,power/x86/$(@:_clean=),clean)
 
 clean: cpupower_clean firewire_clean lguest_clean perf_clean selftests_clean \
 		turbostat_clean usb_clean virtio_clean vm_clean \
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index cca5bb8334ad..a7c6aa8d4a8b 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -422,7 +422,9 @@ LIB_OBJS += $(OUTPUT)util/intlist.o
 LIB_OBJS += $(OUTPUT)util/vdso.o
 LIB_OBJS += $(OUTPUT)util/stat.o
 
+LIB_OBJS += $(OUTPUT)ui/setup.o
 LIB_OBJS += $(OUTPUT)ui/helpline.o
+LIB_OBJS += $(OUTPUT)ui/progress.o
 LIB_OBJS += $(OUTPUT)ui/hist.o
 LIB_OBJS += $(OUTPUT)ui/stdio/hist.o
 
@@ -431,6 +433,17 @@ LIB_OBJS += $(OUTPUT)arch/common.o
 LIB_OBJS += $(OUTPUT)tests/parse-events.o
 LIB_OBJS += $(OUTPUT)tests/dso-data.o
 LIB_OBJS += $(OUTPUT)tests/attr.o
+LIB_OBJS += $(OUTPUT)tests/vmlinux-kallsyms.o
+LIB_OBJS += $(OUTPUT)tests/open-syscall.o
+LIB_OBJS += $(OUTPUT)tests/open-syscall-all-cpus.o
+LIB_OBJS += $(OUTPUT)tests/open-syscall-tp-fields.o
+LIB_OBJS += $(OUTPUT)tests/mmap-basic.o
+LIB_OBJS += $(OUTPUT)tests/perf-record.o
+LIB_OBJS += $(OUTPUT)tests/rdpmc.o
+LIB_OBJS += $(OUTPUT)tests/evsel-roundtrip-name.o
+LIB_OBJS += $(OUTPUT)tests/evsel-tp-sched.o
+LIB_OBJS += $(OUTPUT)tests/pmu.o
+LIB_OBJS += $(OUTPUT)tests/util.o
 
 BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o
 BUILTIN_OBJS += $(OUTPUT)builtin-bench.o
@@ -600,17 +613,16 @@ ifndef NO_NEWT
 		BASIC_CFLAGS += -I/usr/include/slang
 		BASIC_CFLAGS += -DNEWT_SUPPORT
 		EXTLIBS += -lnewt -lslang
-		LIB_OBJS += $(OUTPUT)ui/setup.o
 		LIB_OBJS += $(OUTPUT)ui/browser.o
 		LIB_OBJS += $(OUTPUT)ui/browsers/annotate.o
 		LIB_OBJS += $(OUTPUT)ui/browsers/hists.o
 		LIB_OBJS += $(OUTPUT)ui/browsers/map.o
 		LIB_OBJS += $(OUTPUT)ui/browsers/scripts.o
-		LIB_OBJS += $(OUTPUT)ui/progress.o
 		LIB_OBJS += $(OUTPUT)ui/util.o
 		LIB_OBJS += $(OUTPUT)ui/tui/setup.o
 		LIB_OBJS += $(OUTPUT)ui/tui/util.o
 		LIB_OBJS += $(OUTPUT)ui/tui/helpline.o
+		LIB_OBJS += $(OUTPUT)ui/tui/progress.o
 		LIB_H += ui/browser.h
 		LIB_H += ui/browsers/map.h
 		LIB_H += ui/keysyms.h
@@ -636,9 +648,9 @@ ifndef NO_GTK2
 		LIB_OBJS += $(OUTPUT)ui/gtk/setup.o
 		LIB_OBJS += $(OUTPUT)ui/gtk/util.o
 		LIB_OBJS += $(OUTPUT)ui/gtk/helpline.o
+		LIB_OBJS += $(OUTPUT)ui/gtk/progress.o
 		# Make sure that it'd be included only once.
 		ifeq ($(findstring -DNEWT_SUPPORT,$(BASIC_CFLAGS)),)
-			LIB_OBJS += $(OUTPUT)ui/setup.o
 			LIB_OBJS += $(OUTPUT)ui/util.o
 		endif
 	endif
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 5783c3225116..f3151d3c70ce 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -230,11 +230,15 @@ static int perf_record__open(struct perf_record *rec)
 	struct perf_record_opts *opts = &rec->opts;
 	int rc = 0;
 
-	perf_evlist__config_attrs(evlist, opts);
-
+	/*
+	 * Set the evsel leader links before we configure attributes,
+	 * since some might depend on this info.
+	 */
 	if (opts->group)
 		perf_evlist__set_leader(evlist);
 
+	perf_evlist__config_attrs(evlist, opts);
+
 	list_for_each_entry(pos, &evlist->entries, node) {
 		struct perf_event_attr *attr = &pos->attr;
 		/*
@@ -498,6 +502,7 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
 	struct perf_evlist *evsel_list = rec->evlist;
 	const char *output_name = rec->output_name;
 	struct perf_session *session;
+	bool disabled = false;
 
 	rec->progname = argv[0];
 
@@ -697,7 +702,13 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
 		}
 	}
 
-	perf_evlist__enable(evsel_list);
+	/*
+	 * When perf is starting the traced process, all the events
+	 * (apart from group members) have enable_on_exec=1 set,
+	 * so don't spoil it by prematurely enabling them.
+	 */
+	if (!perf_target__none(&opts->target))
+		perf_evlist__enable(evsel_list);
 
 	/*
 	 * Let the child rip
@@ -720,8 +731,15 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
 			waking++;
 		}
 
-		if (done)
+		/*
+		 * When perf is starting the traced process, at the end events
+		 * die with the process and we wait for that. Thus no need to
+		 * disable events in this case.
+		 */
+		if (done && !disabled && !perf_target__none(&opts->target)) {
 			perf_evlist__disable(evsel_list);
+			disabled = true;
+		}
 	}
 
 	if (quiet || signr == SIGUSR1)
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 6888960ef8b8..c247faca7127 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -129,8 +129,7 @@ static struct stats runtime_itlb_cache_stats[MAX_NR_CPUS];
 static struct stats runtime_dtlb_cache_stats[MAX_NR_CPUS];
 static struct stats walltime_nsecs_stats;
 
-static int create_perf_stat_counter(struct perf_evsel *evsel,
-				    struct perf_evsel *first)
+static int create_perf_stat_counter(struct perf_evsel *evsel)
 {
 	struct perf_event_attr *attr = &evsel->attr;
 	bool exclude_guest_missing = false;
@@ -153,7 +152,8 @@ retry:
 		return 0;
 	}
 
-	if (!perf_target__has_task(&target) && (!group || evsel == first)) {
+	if (!perf_target__has_task(&target) &&
+	    !perf_evsel__is_group_member(evsel)) {
 		attr->disabled = 1;
 		attr->enable_on_exec = 1;
 	}
@@ -272,7 +272,7 @@ static int read_counter(struct perf_evsel *counter)
 static int __run_perf_stat(int argc __maybe_unused, const char **argv)
 {
 	unsigned long long t0, t1;
-	struct perf_evsel *counter, *first;
+	struct perf_evsel *counter;
 	int status = 0;
 	int child_ready_pipe[2], go_pipe[2];
 	const bool forks = (argc > 0);
@@ -332,10 +332,8 @@ static int __run_perf_stat(int argc __maybe_unused, const char **argv)
 	if (group)
 		perf_evlist__set_leader(evsel_list);
 
-	first = perf_evlist__first(evsel_list);
-
 	list_for_each_entry(counter, &evsel_list->entries, node) {
-		if (create_perf_stat_counter(counter, first) < 0) {
+		if (create_perf_stat_counter(counter) < 0) {
 			/*
 			 * PPC returns ENXIO for HW counters until 2.6.37
 			 * (behavior changed with commit b0a873e).
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index a0ae2902f9c9..0f661fbce6a8 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -85,21 +85,26 @@ int check_pager_config(const char *cmd)
 	return c.val;
 }
 
-static int tui_command_config(const char *var, const char *value, void *data)
+static int browser_command_config(const char *var, const char *value, void *data)
 {
 	struct pager_config *c = data;
 	if (!prefixcmp(var, "tui.") && !strcmp(var + 4, c->cmd))
 		c->val = perf_config_bool(var, value);
+	if (!prefixcmp(var, "gtk.") && !strcmp(var + 4, c->cmd))
+		c->val = perf_config_bool(var, value) ? 2 : 0;
 	return 0;
 }
 
-/* returns 0 for "no tui", 1 for "use tui", and -1 for "not specified" */
-static int check_tui_config(const char *cmd)
+/*
+ * returns 0 for "no tui", 1 for "use tui", 2 for "use gtk",
+ * and -1 for "not specified"
+ */
+static int check_browser_config(const char *cmd)
 {
 	struct pager_config c;
 	c.cmd = cmd;
 	c.val = -1;
-	perf_config(tui_command_config, &c);
+	perf_config(browser_command_config, &c);
 	return c.val;
 }
 
@@ -302,7 +307,7 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv)
 		prefix = NULL; /* setup_perf_directory(); */
 
 	if (use_browser == -1)
-		use_browser = check_tui_config(p->cmd);
+		use_browser = check_browser_config(p->cmd);
 
 	if (use_pager == -1 && p->option & RUN_SETUP)
 		use_pager = check_pager_config(p->cmd);
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 054182e41dca..f53ee0bbee88 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -26,7 +26,7 @@ void get_term_dimensions(struct winsize *ws);
 #endif
 
 #ifdef __powerpc__
-#include "../../arch/powerpc/include/asm/unistd.h"
+#include "../../arch/powerpc/include/uapi/asm/unistd.h"
 #define rmb()		asm volatile ("sync" ::: "memory")
 #define cpu_relax()	asm volatile ("" ::: "memory");
 #define CPUINFO_PROC	"cpu"
@@ -178,7 +178,6 @@ extern bool test_attr__enabled;
 void test_attr__init(void);
 void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu,
 		     int fd, int group_fd, unsigned long flags);
-int  test_attr__run(void);
 
 static inline int
 sys_perf_event_open(struct perf_event_attr *attr,
diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c
index 6e2feee8db2a..25638a986257 100644
--- a/tools/perf/tests/attr.c
+++ b/tools/perf/tests/attr.c
@@ -27,6 +27,7 @@
 #include "../perf.h"
 #include "util.h"
 #include "exec_cmd.h"
+#include "tests.h"
 
 #define ENV "PERF_TEST_ATTR"
 
@@ -151,7 +152,7 @@ static int run_dir(const char *d, const char *perf)
 	return system(cmd);
 }
 
-int test_attr__run(void)
+int test__attr(void)
 {
 	struct stat st;
 	char path_perf[PATH_MAX];
diff --git a/tools/perf/tests/attr/test-record-group b/tools/perf/tests/attr/test-record-group
index b945f770dc9e..a6599e9a19d3 100644
--- a/tools/perf/tests/attr/test-record-group
+++ b/tools/perf/tests/attr/test-record-group
@@ -15,3 +15,4 @@ sample_type=327
 mmap=0
 comm=0
 enable_on_exec=0
+disabled=0
diff --git a/tools/perf/tests/attr/test-record-group1 b/tools/perf/tests/attr/test-record-group1
index 39bf8609538c..5a8359da38af 100644
--- a/tools/perf/tests/attr/test-record-group1
+++ b/tools/perf/tests/attr/test-record-group1
@@ -15,6 +15,5 @@ config=1
 sample_type=327
 mmap=0
 comm=0
-# TODO this is disabled for --group option, enabled otherwise
-#      check why..
-enable_on_exec=1
+enable_on_exec=0
+disabled=0
diff --git a/tools/perf/tests/attr/test-stat-group1 b/tools/perf/tests/attr/test-stat-group1
index 5ae2718de864..2a1f86e4a904 100644
--- a/tools/perf/tests/attr/test-stat-group1
+++ b/tools/perf/tests/attr/test-stat-group1
@@ -11,7 +11,5 @@ group_fd=-1
 fd=2
 group_fd=1
 config=1
-# TODO both disabled and enable_on_exec are disabled for --group option,
-#      enabled otherwise, check why..
-disabled=1
-enable_on_exec=1
+disabled=0
+enable_on_exec=0
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 5d4354e24457..186f67535494 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -4,1388 +4,11 @@
  * Builtin regression testing command: ever growing number of sanity tests
  */
 #include "builtin.h"
-
-#include "util/cache.h"
-#include "util/color.h"
-#include "util/debug.h"
-#include "util/debugfs.h"
-#include "util/evlist.h"
-#include "util/machine.h"
-#include "util/parse-options.h"
-#include "util/parse-events.h"
-#include "util/symbol.h"
-#include "util/thread_map.h"
-#include "util/pmu.h"
-#include "event-parse.h"
-#include "../../include/linux/hw_breakpoint.h"
-
-#include <sys/mman.h>
-
-static int vmlinux_matches_kallsyms_filter(struct map *map __maybe_unused,
-					   struct symbol *sym)
-{
-	bool *visited = symbol__priv(sym);
-	*visited = true;
-	return 0;
-}
-
-static 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;
-	struct ref_reloc_sym ref_reloc_sym = { .name = "_stext", };
-
-	/*
-	 * 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 ");
-		return -1;
-	}
-
-	/*
-	 * 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);
-
-	sym = map__find_symbol_by_name(kallsyms_map, ref_reloc_sym.name, NULL);
-	if (sym == NULL) {
-		pr_debug("dso__find_symbol_by_name ");
-		goto out;
-	}
-
-	ref_reloc_sym.addr = sym->start;
-
-	/*
-	 * 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);
-	map__kmap(vmlinux_map)->ref_reloc_sym = &ref_reloc_sym;
-
-	/*
-	 * 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("machine__load_vmlinux_path ");
-		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;
-
-		first_pair = machine__find_kernel_symbol(&kallsyms, type, sym->start, NULL, NULL);
-		pair = first_pair;
-
-		if (pair && pair->start == sym->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 = sym->end - pair->end;
-				if (llabs(skew) < page_size)
-					continue;
-
-				pr_debug("%#" PRIx64 ": diff end addr for %s v: %#" PRIx64 " k: %#" PRIx64 "\n",
-					 sym->start, sym->name, sym->end, pair->end);
-			} 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 (next->start == sym->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",
-					 sym->start, sym->name, pair->name);
-			}
-		} else
-			pr_debug("%#" PRIx64 ": %s not on kallsyms\n", sym->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;
-
-		pair = map_groups__find(&kallsyms.kmaps, type, pos->start);
-		if (pair == NULL || pair->priv)
-			continue;
-
-		if (pair->start == pos->start) {
-			pair->priv = 1;
-			pr_info(" %" PRIx64 "-%" PRIx64 " %" PRIx64 " %s in kallsyms as",
-				pos->start, pos->end, pos->pgoff, pos->dso->name);
-			if (pos->pgoff != pair->pgoff || pos->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:
-	return err;
-}
-
-#include "util/cpumap.h"
-#include "util/evsel.h"
-#include <sys/types.h>
-
-static int trace_event__id(const char *evname)
-{
-	char *filename;
-	int err = -1, fd;
-
-	if (asprintf(&filename,
-		     "%s/syscalls/%s/id",
-		     tracing_events_path, evname) < 0)
-		return -1;
-
-	fd = open(filename, O_RDONLY);
-	if (fd >= 0) {
-		char id[16];
-		if (read(fd, id, sizeof(id)) > 0)
-			err = atoi(id);
-		close(fd);
-	}
-
-	free(filename);
-	return err;
-}
-
-static int test__open_syscall_event(void)
-{
-	int err = -1, fd;
-	struct thread_map *threads;
-	struct perf_evsel *evsel;
-	struct perf_event_attr attr;
-	unsigned int nr_open_calls = 111, i;
-	int id = trace_event__id("sys_enter_open");
-
-	if (id < 0) {
-		pr_debug("is debugfs mounted on /sys/kernel/debug?\n");
-		return -1;
-	}
-
-	threads = thread_map__new(-1, getpid(), UINT_MAX);
-	if (threads == NULL) {
-		pr_debug("thread_map__new\n");
-		return -1;
-	}
-
-	memset(&attr, 0, sizeof(attr));
-	attr.type = PERF_TYPE_TRACEPOINT;
-	attr.config = id;
-	evsel = perf_evsel__new(&attr, 0);
-	if (evsel == NULL) {
-		pr_debug("perf_evsel__new\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(errno));
-		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;
-}
-
-#include <sched.h>
-
-static int test__open_syscall_event_on_all_cpus(void)
-{
-	int err = -1, fd, cpu;
-	struct thread_map *threads;
-	struct cpu_map *cpus;
-	struct perf_evsel *evsel;
-	struct perf_event_attr attr;
-	unsigned int nr_open_calls = 111, i;
-	cpu_set_t cpu_set;
-	int id = trace_event__id("sys_enter_open");
-
-	if (id < 0) {
-		pr_debug("is debugfs mounted on /sys/kernel/debug?\n");
-		return -1;
-	}
-
-	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_thread_map_delete;
-	}
-
-
-	CPU_ZERO(&cpu_set);
-
-	memset(&attr, 0, sizeof(attr));
-	attr.type = PERF_TYPE_TRACEPOINT;
-	attr.config = id;
-	evsel = perf_evsel__new(&attr, 0);
-	if (evsel == NULL) {
-		pr_debug("perf_evsel__new\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(errno));
-		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(errno));
-			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;
-		}
-	}
-
-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;
-}
-
-/*
- * 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.
- */
-static int test__basic_mmap(void)
-{
-	int err = -1;
-	union perf_event *event;
-	struct thread_map *threads;
-	struct cpu_map *cpus;
-	struct perf_evlist *evlist;
-	struct perf_event_attr attr = {
-		.type		= PERF_TYPE_TRACEPOINT,
-		.read_format	= PERF_FORMAT_ID,
-		.sample_type	= PERF_SAMPLE_ID,
-		.watermark	= 0,
-	};
-	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)
-	int ids[nsyscalls];
-	unsigned int nr_events[nsyscalls],
-		     expected_nr_events[nsyscalls], i, j;
-	struct perf_evsel *evsels[nsyscalls], *evsel;
-
-	for (i = 0; i < nsyscalls; ++i) {
-		char name[64];
-
-		snprintf(name, sizeof(name), "sys_enter_%s", syscall_names[i]);
-		ids[i] = trace_event__id(name);
-		if (ids[i] < 0) {
-			pr_debug("Is debugfs mounted on /sys/kernel/debug?\n");
-			return -1;
-		}
-		nr_events[i] = 0;
-		expected_nr_events[i] = random() % 257;
-	}
-
-	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(errno));
-		goto out_free_cpus;
-	}
-
-	evlist = perf_evlist__new(cpus, threads);
-	if (evlist == NULL) {
-		pr_debug("perf_evlist__new\n");
-		goto out_free_cpus;
-	}
-
-	/* anonymous union fields, can't be initialized above */
-	attr.wakeup_events = 1;
-	attr.sample_period = 1;
-
-	for (i = 0; i < nsyscalls; ++i) {
-		attr.config = ids[i];
-		evsels[i] = perf_evsel__new(&attr, i);
-		if (evsels[i] == NULL) {
-			pr_debug("perf_evsel__new\n");
-			goto out_free_evlist;
-		}
-
-		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(errno));
-			goto out_close_fd;
-		}
-	}
-
-	if (perf_evlist__mmap(evlist, 128, true) < 0) {
-		pr_debug("failed to mmap events: %d (%s)\n", errno,
-			 strerror(errno));
-		goto out_close_fd;
-	}
-
-	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_munmap;
-		}
-
-		err = perf_evlist__parse_sample(evlist, event, &sample);
-		if (err) {
-			pr_err("Can't parse sample, err = %d\n", err);
-			goto out_munmap;
-		}
-
-		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_munmap;
-		}
-		nr_events[evsel->idx]++;
-	}
-
-	list_for_each_entry(evsel, &evlist->entries, node) {
-		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]);
-			goto out_munmap;
-		}
-	}
-
-	err = 0;
-out_munmap:
-	perf_evlist__munmap(evlist);
-out_close_fd:
-	for (i = 0; i < nsyscalls; ++i)
-		perf_evsel__close_fd(evsels[i], 1, threads->nr);
-out_free_evlist:
-	perf_evlist__delete(evlist);
-out_free_cpus:
-	cpu_map__delete(cpus);
-out_free_threads:
-	thread_map__delete(threads);
-	return err;
-#undef nsyscalls
-}
-
-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;
-}
-
-static int test__PERF_RECORD(void)
-{
-	struct perf_record_opts opts = {
-		.target = {
-			.uid = UINT_MAX,
-			.uses_mmap = true,
-		},
-		.no_delay   = 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(NULL, NULL);
-	struct perf_evsel *evsel;
-	struct perf_sample sample;
-	const char *cmd = "sleep";
-	const char *argv[] = { cmd, "1", NULL, };
-	char *bname;
-	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, };
-
-	if (evlist == NULL || argv == NULL) {
-		pr_debug("Not enough memory to create evlist\n");
-		goto out;
-	}
-
-	/*
-	 * We need at least one evsel in the evlist, use the default
-	 * one: "cycles".
-	 */
-	err = perf_evlist__add_default(evlist);
-	if (err < 0) {
-		pr_debug("Not enough memory to create evsel\n");
-		goto out_delete_evlist;
-	}
-
-	/*
-	 * 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, argv);
-	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);
-	evsel->attr.sample_type |= PERF_SAMPLE_CPU;
-	evsel->attr.sample_type |= PERF_SAMPLE_TID;
-	evsel->attr.sample_type |= PERF_SAMPLE_TIME;
-	perf_evlist__config_attrs(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(errno));
-		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(errno));
-		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(errno));
-		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(errno));
-		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_err;
-				}
-
-				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_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) &&
-				     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:
-					bname = strrchr(event->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(event->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;
-				}
-			}
-		}
-
-		/*
-		 * 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)
-			poll(evlist->pollfd, evlist->nr_fds, -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_err:
-	perf_evlist__munmap(evlist);
-out_delete_evlist:
-	perf_evlist__delete(evlist);
-out:
-	return (err < 0 || errs > 0) ? -1 : 0;
-}
-
-
-#if defined(__x86_64__) || defined(__i386__)
-
-#define barrier() asm volatile("" ::: "memory")
-
-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;
-
-	sigfillset(&sa.sa_mask);
-	sa.sa_sigaction = segfault_handler;
-	sigaction(SIGSEGV, &sa, NULL);
-
-	fd = sys_perf_event_open(&attr, 0, -1, -1, 0);
-	if (fd < 0) {
-		pr_err("Error: sys_perf_event_open() syscall returned "
-		       "with %d (%s)\n", fd, strerror(errno));
-		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(errno));
-		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;
-}
-
-static 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
-
-static int test__perf_pmu(void)
-{
-	return perf_pmu__test();
-}
-
-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(NULL, NULL);
-
-        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, 0);
-				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(NULL, NULL);
-
-        if (evlist == NULL)
-                return -ENOMEM;
-
-	for (i = 0; i < nr_names; ++i) {
-		err = parse_events(evlist, names[i], 0);
-		if (err) {
-			pr_debug("failed to parse event '%s', err %d\n",
-				 names[i], err);
-			goto out_delete_evlist;
-		}
-	}
-
-	err = 0;
-	list_for_each_entry(evsel, &evlist->entries, node) {
-		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))
-
-static int 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;
-}
-
-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;
-}
-
-static int perf_evsel__tp_sched_test(void)
-{
-	struct perf_evsel *evsel = perf_evsel__newtp("sched", "sched_switch", 0);
-	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", 8, 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", 0);
-
-	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, "success", 4, true))
-		ret = -1;
-
-	if (perf_evsel__test_field(evsel, "target_cpu", 4, true))
-		ret = -1;
-
-	return ret;
-}
-
-static int test__syscall_open_tp_fields(void)
-{
-	struct perf_record_opts opts = {
-		.target = {
-			.uid = UINT_MAX,
-			.uses_mmap = true,
-		},
-		.no_delay   = 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(NULL, NULL);
-	struct perf_evsel *evsel;
-	int err = -1, i, nr_events = 0, nr_polls = 0;
-
-	if (evlist == NULL) {
-		pr_debug("%s: perf_evlist__new\n", __func__);
-		goto out;
-	}
-
-	evsel = perf_evsel__newtp("syscalls", "sys_enter_open", 0);
-	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, evsel);
-
-	evlist->threads->map[0] = getpid();
-
-	err = perf_evlist__open(evlist);
-	if (err < 0) {
-		pr_debug("perf_evlist__open: %s\n", strerror(errno));
-		goto out_delete_evlist;
-	}
-
-	err = perf_evlist__mmap(evlist, UINT_MAX, false);
-	if (err < 0) {
-		pr_debug("perf_evlist__mmap: %s\n", strerror(errno));
-		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)
-					continue;
-
-				err = perf_evsel__parse_sample(evsel, event, &sample);
-				if (err) {
-					pr_err("Can't parse sample, err = %d\n", err);
-					goto out_munmap;
-				}
-
-				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_munmap;
-				}
-
-				goto out_ok;
-			}
-		}
-
-		if (nr_events == before)
-			poll(evlist->pollfd, evlist->nr_fds, 10);
-
-		if (++nr_polls > 5) {
-			pr_debug("%s: no events!\n", __func__);
-			goto out_munmap;
-		}
-	}
-out_ok:
-	err = 0;
-out_munmap:
-	perf_evlist__munmap(evlist);
-out_delete_evlist:
-	perf_evlist__delete(evlist);
-out:
-	return err;
-}
+#include "tests.h"
+#include "debug.h"
+#include "color.h"
+#include "parse-options.h"
+#include "symbol.h"
 
 static struct test {
 	const char *desc;
@@ -1409,7 +32,7 @@ static struct test {
 	},
 	{
 		.desc = "parse events tests",
-		.func = parse_events__test,
+		.func = test__parse_events,
 	},
 #if defined(__x86_64__) || defined(__i386__)
 	{
@@ -1423,19 +46,19 @@ static struct test {
 	},
 	{
 		.desc = "Test perf pmu format parsing",
-		.func = test__perf_pmu,
+		.func = test__pmu,
 	},
 	{
 		.desc = "Test dso data interface",
-		.func = dso__test_data,
+		.func = test__dso_data,
 	},
 	{
 		.desc = "roundtrip evsel->name check",
-		.func = perf_evsel__roundtrip_name_test,
+		.func = test__perf_evsel__roundtrip_name_test,
 	},
 	{
 		.desc = "Check parsing of sched tracepoints fields",
-		.func = perf_evsel__tp_sched_test,
+		.func = test__perf_evsel__tp_sched_test,
 	},
 	{
 		.desc = "Generate and check syscalls:sys_enter_open event fields",
@@ -1443,7 +66,7 @@ static struct test {
 	},
 	{
 		.desc = "struct perf_event_attr setup",
-		.func = test_attr__run,
+		.func = test__attr,
 	},
 	{
 		.func = NULL,
diff --git a/tools/perf/tests/dso-data.c b/tools/perf/tests/dso-data.c
index 0cd42fc9bc13..5eaffa2de9c5 100644
--- a/tools/perf/tests/dso-data.c
+++ b/tools/perf/tests/dso-data.c
@@ -8,6 +8,7 @@
 
 #include "machine.h"
 #include "symbol.h"
+#include "tests.h"
 
 #define TEST_ASSERT_VAL(text, cond) \
 do { \
@@ -25,6 +26,10 @@ static char *test_file(int size)
 	unsigned char *buf;
 
 	fd = mkstemp(templ);
+	if (fd < 0) {
+		perror("mkstemp failed");
+		return NULL;
+	}
 
 	buf = malloc(size);
 	if (!buf) {
@@ -95,7 +100,7 @@ struct test_data_offset offsets[] = {
 	},
 };
 
-int dso__test_data(void)
+int test__dso_data(void)
 {
 	struct machine machine;
 	struct dso *dso;
diff --git a/tools/perf/tests/evsel-roundtrip-name.c b/tools/perf/tests/evsel-roundtrip-name.c
new file mode 100644
index 000000000000..e61fc828a158
--- /dev/null
+++ b/tools/perf/tests/evsel-roundtrip-name.c
@@ -0,0 +1,114 @@
+#include "evlist.h"
+#include "evsel.h"
+#include "parse-events.h"
+#include "tests.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(NULL, NULL);
+
+        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, 0);
+				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(NULL, NULL);
+
+        if (evlist == NULL)
+                return -ENOMEM;
+
+	for (i = 0; i < nr_names; ++i) {
+		err = parse_events(evlist, names[i], 0);
+		if (err) {
+			pr_debug("failed to parse event '%s', err %d\n",
+				 names[i], err);
+			goto out_delete_evlist;
+		}
+	}
+
+	err = 0;
+	list_for_each_entry(evsel, &evlist->entries, node) {
+		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 000000000000..a5d2fcc5ae35
--- /dev/null
+++ b/tools/perf/tests/evsel-tp-sched.c
@@ -0,0 +1,84 @@
+#include "evsel.h"
+#include "tests.h"
+#include "event-parse.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", 0);
+	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", 8, 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", 0);
+
+	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, "success", 4, true))
+		ret = -1;
+
+	if (perf_evsel__test_field(evsel, "target_cpu", 4, true))
+		ret = -1;
+
+	return ret;
+}
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
new file mode 100644
index 000000000000..e1746811e14b
--- /dev/null
+++ b/tools/perf/tests/mmap-basic.c
@@ -0,0 +1,162 @@
+#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;
+	struct perf_event_attr attr = {
+		.type		= PERF_TYPE_TRACEPOINT,
+		.read_format	= PERF_FORMAT_ID,
+		.sample_type	= PERF_SAMPLE_ID,
+		.watermark	= 0,
+	};
+	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)
+	int ids[nsyscalls];
+	unsigned int nr_events[nsyscalls],
+		     expected_nr_events[nsyscalls], i, j;
+	struct perf_evsel *evsels[nsyscalls], *evsel;
+
+	for (i = 0; i < nsyscalls; ++i) {
+		char name[64];
+
+		snprintf(name, sizeof(name), "sys_enter_%s", syscall_names[i]);
+		ids[i] = trace_event__id(name);
+		if (ids[i] < 0) {
+			pr_debug("Is debugfs mounted on /sys/kernel/debug?\n");
+			return -1;
+		}
+		nr_events[i] = 0;
+		expected_nr_events[i] = random() % 257;
+	}
+
+	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(errno));
+		goto out_free_cpus;
+	}
+
+	evlist = perf_evlist__new(cpus, threads);
+	if (evlist == NULL) {
+		pr_debug("perf_evlist__new\n");
+		goto out_free_cpus;
+	}
+
+	/* anonymous union fields, can't be initialized above */
+	attr.wakeup_events = 1;
+	attr.sample_period = 1;
+
+	for (i = 0; i < nsyscalls; ++i) {
+		attr.config = ids[i];
+		evsels[i] = perf_evsel__new(&attr, i);
+		if (evsels[i] == NULL) {
+			pr_debug("perf_evsel__new\n");
+			goto out_free_evlist;
+		}
+
+		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(errno));
+			goto out_close_fd;
+		}
+	}
+
+	if (perf_evlist__mmap(evlist, 128, true) < 0) {
+		pr_debug("failed to mmap events: %d (%s)\n", errno,
+			 strerror(errno));
+		goto out_close_fd;
+	}
+
+	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_munmap;
+		}
+
+		err = perf_evlist__parse_sample(evlist, event, &sample);
+		if (err) {
+			pr_err("Can't parse sample, err = %d\n", err);
+			goto out_munmap;
+		}
+
+		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_munmap;
+		}
+		nr_events[evsel->idx]++;
+	}
+
+	list_for_each_entry(evsel, &evlist->entries, node) {
+		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]);
+			goto out_munmap;
+		}
+	}
+
+	err = 0;
+out_munmap:
+	perf_evlist__munmap(evlist);
+out_close_fd:
+	for (i = 0; i < nsyscalls; ++i)
+		perf_evsel__close_fd(evsels[i], 1, threads->nr);
+out_free_evlist:
+	perf_evlist__delete(evlist);
+out_free_cpus:
+	cpu_map__delete(cpus);
+out_free_threads:
+	thread_map__delete(threads);
+	return err;
+}
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 000000000000..31072aba0d54
--- /dev/null
+++ b/tools/perf/tests/open-syscall-all-cpus.c
@@ -0,0 +1,120 @@
+#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 thread_map *threads;
+	struct cpu_map *cpus;
+	struct perf_evsel *evsel;
+	struct perf_event_attr attr;
+	unsigned int nr_open_calls = 111, i;
+	cpu_set_t cpu_set;
+	int id = trace_event__id("sys_enter_open");
+
+	if (id < 0) {
+		pr_debug("is debugfs mounted on /sys/kernel/debug?\n");
+		return -1;
+	}
+
+	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_thread_map_delete;
+	}
+
+
+	CPU_ZERO(&cpu_set);
+
+	memset(&attr, 0, sizeof(attr));
+	attr.type = PERF_TYPE_TRACEPOINT;
+	attr.config = id;
+	evsel = perf_evsel__new(&attr, 0);
+	if (evsel == NULL) {
+		pr_debug("perf_evsel__new\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(errno));
+		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(errno));
+			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;
+		}
+	}
+
+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 000000000000..1c52fdc1164e
--- /dev/null
+++ b/tools/perf/tests/open-syscall-tp-fields.c
@@ -0,0 +1,117 @@
+#include "perf.h"
+#include "evlist.h"
+#include "evsel.h"
+#include "thread_map.h"
+#include "tests.h"
+
+int test__syscall_open_tp_fields(void)
+{
+	struct perf_record_opts opts = {
+		.target = {
+			.uid = UINT_MAX,
+			.uses_mmap = true,
+		},
+		.no_delay   = 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(NULL, NULL);
+	struct perf_evsel *evsel;
+	int err = -1, i, nr_events = 0, nr_polls = 0;
+
+	if (evlist == NULL) {
+		pr_debug("%s: perf_evlist__new\n", __func__);
+		goto out;
+	}
+
+	evsel = perf_evsel__newtp("syscalls", "sys_enter_open", 0);
+	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(errno));
+		goto out_delete_evlist;
+	}
+
+	err = perf_evlist__mmap(evlist, UINT_MAX, false);
+	if (err < 0) {
+		pr_debug("perf_evlist__mmap: %s\n", strerror(errno));
+		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)
+					continue;
+
+				err = perf_evsel__parse_sample(evsel, event, &sample);
+				if (err) {
+					pr_err("Can't parse sample, err = %d\n", err);
+					goto out_munmap;
+				}
+
+				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_munmap;
+				}
+
+				goto out_ok;
+			}
+		}
+
+		if (nr_events == before)
+			poll(evlist->pollfd, evlist->nr_fds, 10);
+
+		if (++nr_polls > 5) {
+			pr_debug("%s: no events!\n", __func__);
+			goto out_munmap;
+		}
+	}
+out_ok:
+	err = 0;
+out_munmap:
+	perf_evlist__munmap(evlist);
+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 000000000000..98be8b518b4f
--- /dev/null
+++ b/tools/perf/tests/open-syscall.c
@@ -0,0 +1,66 @@
+#include "thread_map.h"
+#include "evsel.h"
+#include "debug.h"
+#include "tests.h"
+
+int test__open_syscall_event(void)
+{
+	int err = -1, fd;
+	struct thread_map *threads;
+	struct perf_evsel *evsel;
+	struct perf_event_attr attr;
+	unsigned int nr_open_calls = 111, i;
+	int id = trace_event__id("sys_enter_open");
+
+	if (id < 0) {
+		pr_debug("is debugfs mounted on /sys/kernel/debug?\n");
+		return -1;
+	}
+
+	threads = thread_map__new(-1, getpid(), UINT_MAX);
+	if (threads == NULL) {
+		pr_debug("thread_map__new\n");
+		return -1;
+	}
+
+	memset(&attr, 0, sizeof(attr));
+	attr.type = PERF_TYPE_TRACEPOINT;
+	attr.config = id;
+	evsel = perf_evsel__new(&attr, 0);
+	if (evsel == NULL) {
+		pr_debug("perf_evsel__new\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(errno));
+		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
index b49c2eebff33..42a0c8cd3cd5 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -4,6 +4,7 @@
 #include "evlist.h"
 #include "sysfs.h"
 #include "../../../include/linux/hw_breakpoint.h"
+#include "tests.h"
 
 #define TEST_ASSERT_VAL(text, cond) \
 do { \
@@ -520,7 +521,7 @@ static int test__group1(struct perf_evlist *evlist)
 	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 == NULL);
+	TEST_ASSERT_VAL("wrong leader", !perf_evsel__is_group_member(evsel));
 
 	/* cycles:upp */
 	evsel = perf_evsel__next(evsel);
@@ -556,7 +557,7 @@ static int test__group2(struct perf_evlist *evlist)
 	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 == NULL);
+	TEST_ASSERT_VAL("wrong leader", !perf_evsel__is_group_member(evsel));
 
 	/* cache-references + :u modifier */
 	evsel = perf_evsel__next(evsel);
@@ -582,7 +583,7 @@ static int test__group2(struct perf_evlist *evlist)
 	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 == NULL);
+	TEST_ASSERT_VAL("wrong leader", !perf_evsel__is_group_member(evsel));
 
 	return 0;
 }
@@ -605,7 +606,7 @@ static int test__group3(struct perf_evlist *evlist __maybe_unused)
 	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 == NULL);
+	TEST_ASSERT_VAL("wrong leader", !perf_evsel__is_group_member(evsel));
 	TEST_ASSERT_VAL("wrong group name",
 		!strcmp(leader->group_name, "group1"));
 
@@ -635,7 +636,7 @@ static int test__group3(struct perf_evlist *evlist __maybe_unused)
 	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 == NULL);
+	TEST_ASSERT_VAL("wrong leader", !perf_evsel__is_group_member(evsel));
 	TEST_ASSERT_VAL("wrong group name",
 		!strcmp(leader->group_name, "group2"));
 
@@ -662,7 +663,7 @@ static int test__group3(struct perf_evlist *evlist __maybe_unused)
 	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 == NULL);
+	TEST_ASSERT_VAL("wrong leader", !perf_evsel__is_group_member(evsel));
 
 	return 0;
 }
@@ -686,7 +687,7 @@ static int test__group4(struct perf_evlist *evlist __maybe_unused)
 	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", evsel->leader == NULL);
+	TEST_ASSERT_VAL("wrong leader", !perf_evsel__is_group_member(evsel));
 
 	/* instructions:kp + p */
 	evsel = perf_evsel__next(evsel);
@@ -723,7 +724,7 @@ static int test__group5(struct perf_evlist *evlist __maybe_unused)
 	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 == NULL);
+	TEST_ASSERT_VAL("wrong leader", !perf_evsel__is_group_member(evsel));
 
 	/* instructions + G */
 	evsel = perf_evsel__next(evsel);
@@ -750,7 +751,7 @@ static int test__group5(struct perf_evlist *evlist __maybe_unused)
 	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 == NULL);
+	TEST_ASSERT_VAL("wrong leader", !perf_evsel__is_group_member(evsel));
 
 	/* instructions:G */
 	evsel = perf_evsel__next(evsel);
@@ -776,7 +777,7 @@ static int test__group5(struct perf_evlist *evlist __maybe_unused)
 	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 == NULL);
+	TEST_ASSERT_VAL("wrong leader", !perf_evsel__is_group_member(evsel));
 
 	return 0;
 }
@@ -1086,7 +1087,7 @@ static int test_pmu_events(void)
 	return ret;
 }
 
-int parse_events__test(void)
+int test__parse_events(void)
 {
 	int ret1, ret2 = 0;
 
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
new file mode 100644
index 000000000000..70e0d4421df8
--- /dev/null
+++ b/tools/perf/tests/perf-record.c
@@ -0,0 +1,312 @@
+#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 perf_record_opts opts = {
+		.target = {
+			.uid = UINT_MAX,
+			.uses_mmap = true,
+		},
+		.no_delay   = 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(NULL, NULL);
+	struct perf_evsel *evsel;
+	struct perf_sample sample;
+	const char *cmd = "sleep";
+	const char *argv[] = { cmd, "1", NULL, };
+	char *bname;
+	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, };
+
+	if (evlist == NULL || argv == NULL) {
+		pr_debug("Not enough memory to create evlist\n");
+		goto out;
+	}
+
+	/*
+	 * We need at least one evsel in the evlist, use the default
+	 * one: "cycles".
+	 */
+	err = perf_evlist__add_default(evlist);
+	if (err < 0) {
+		pr_debug("Not enough memory to create evsel\n");
+		goto out_delete_evlist;
+	}
+
+	/*
+	 * 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, argv);
+	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);
+	evsel->attr.sample_type |= PERF_SAMPLE_CPU;
+	evsel->attr.sample_type |= PERF_SAMPLE_TID;
+	evsel->attr.sample_type |= PERF_SAMPLE_TIME;
+	perf_evlist__config_attrs(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(errno));
+		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(errno));
+		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(errno));
+		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(errno));
+		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_err;
+				}
+
+				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_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) &&
+				     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:
+					bname = strrchr(event->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(event->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;
+				}
+			}
+		}
+
+		/*
+		 * 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)
+			poll(evlist->pollfd, evlist->nr_fds, -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_err:
+	perf_evlist__munmap(evlist);
+out_delete_evlist:
+	perf_evlist__delete(evlist);
+out:
+	return (err < 0 || errs > 0) ? -1 : 0;
+}
diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c
new file mode 100644
index 000000000000..a5f379863b8f
--- /dev/null
+++ b/tools/perf/tests/pmu.c
@@ -0,0 +1,178 @@
+#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", },
+};
+
+#define TEST_FORMATS_CNT (sizeof(test_formats) / sizeof(struct test_format))
+
+/* 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,
+	},
+};
+#define TERMS_CNT (sizeof(test_terms) / sizeof(struct parse_events__term))
+
+/*
+ * 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 < TEST_FORMATS_CNT; 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 < TERMS_CNT; i++)
+		list_add_tail(&test_terms[i].list, &terms);
+
+	return &terms;
+}
+
+#undef TERMS_CNT
+
+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);
+		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/rdpmc.c b/tools/perf/tests/rdpmc.c
new file mode 100644
index 000000000000..ff94886aad99
--- /dev/null
+++ b/tools/perf/tests/rdpmc.c
@@ -0,0 +1,175 @@
+#include <unistd.h>
+#include <stdlib.h>
+#include <signal.h>
+#include <sys/mman.h>
+#include "types.h"
+#include "perf.h"
+#include "debug.h"
+#include "tests.h"
+
+#if defined(__x86_64__) || defined(__i386__)
+
+#define barrier() asm volatile("" ::: "memory")
+
+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;
+
+	sigfillset(&sa.sa_mask);
+	sa.sa_sigaction = segfault_handler;
+	sigaction(SIGSEGV, &sa, NULL);
+
+	fd = sys_perf_event_open(&attr, 0, -1, -1, 0);
+	if (fd < 0) {
+		pr_err("Error: sys_perf_event_open() syscall returned "
+		       "with %d (%s)\n", fd, strerror(errno));
+		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(errno));
+		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/tests.h b/tools/perf/tests/tests.h
new file mode 100644
index 000000000000..fc121edab016
--- /dev/null
+++ b/tools/perf/tests/tests.h
@@ -0,0 +1,22 @@
+#ifndef TESTS_H
+#define TESTS_H
+
+/* 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__parse_events(void);
+
+/* Util */
+int trace_event__id(const char *evname);
+
+#endif /* TESTS_H */
diff --git a/tools/perf/tests/util.c b/tools/perf/tests/util.c
new file mode 100644
index 000000000000..748f2e8f6961
--- /dev/null
+++ b/tools/perf/tests/util.c
@@ -0,0 +1,30 @@
+#include <stdio.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include "tests.h"
+#include "debugfs.h"
+
+int trace_event__id(const char *evname)
+{
+	char *filename;
+	int err = -1, fd;
+
+	if (asprintf(&filename,
+		     "%s/syscalls/%s/id",
+		     tracing_events_path, evname) < 0)
+		return -1;
+
+	fd = open(filename, O_RDONLY);
+	if (fd >= 0) {
+		char id[16];
+		if (read(fd, id, sizeof(id)) > 0)
+			err = atoi(id);
+		close(fd);
+	}
+
+	free(filename);
+	return err;
+}
diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c
new file mode 100644
index 000000000000..0d1cdbee2f59
--- /dev/null
+++ b/tools/perf/tests/vmlinux-kallsyms.c
@@ -0,0 +1,230 @@
+#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;
+}
+
+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;
+	struct ref_reloc_sym ref_reloc_sym = { .name = "_stext", };
+
+	/*
+	 * 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 ");
+		return -1;
+	}
+
+	/*
+	 * 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);
+
+	sym = map__find_symbol_by_name(kallsyms_map, ref_reloc_sym.name, NULL);
+	if (sym == NULL) {
+		pr_debug("dso__find_symbol_by_name ");
+		goto out;
+	}
+
+	ref_reloc_sym.addr = sym->start;
+
+	/*
+	 * 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);
+	map__kmap(vmlinux_map)->ref_reloc_sym = &ref_reloc_sym;
+
+	/*
+	 * 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("machine__load_vmlinux_path ");
+		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;
+
+		first_pair = machine__find_kernel_symbol(&kallsyms, type, sym->start, NULL, NULL);
+		pair = first_pair;
+
+		if (pair && pair->start == sym->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 = sym->end - pair->end;
+				if (llabs(skew) < page_size)
+					continue;
+
+				pr_debug("%#" PRIx64 ": diff end addr for %s v: %#" PRIx64 " k: %#" PRIx64 "\n",
+					 sym->start, sym->name, sym->end, pair->end);
+			} 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 (next->start == sym->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",
+					 sym->start, sym->name, pair->name);
+			}
+		} else
+			pr_debug("%#" PRIx64 ": %s not on kallsyms\n", sym->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;
+
+		pair = map_groups__find(&kallsyms.kmaps, type, pos->start);
+		if (pair == NULL || pair->priv)
+			continue;
+
+		if (pair->start == pos->start) {
+			pair->priv = 1;
+			pr_info(" %" PRIx64 "-%" PRIx64 " %" PRIx64 " %s in kallsyms as",
+				pos->start, pos->end, pos->pgoff, pos->dso->name);
+			if (pos->pgoff != pair->pgoff || pos->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:
+	return err;
+}
diff --git a/tools/perf/ui/gtk/gtk.h b/tools/perf/ui/gtk/gtk.h
index 687af0bba187..856320e2cc05 100644
--- a/tools/perf/ui/gtk/gtk.h
+++ b/tools/perf/ui/gtk/gtk.h
@@ -30,6 +30,7 @@ struct perf_gtk_context *perf_gtk__activate_context(GtkWidget *window);
 int perf_gtk__deactivate_context(struct perf_gtk_context **ctx);
 
 void perf_gtk__init_helpline(void);
+void perf_gtk__init_progress(void);
 void perf_gtk__init_hpp(void);
 
 #ifndef HAVE_GTK_INFO_BAR
diff --git a/tools/perf/ui/gtk/progress.c b/tools/perf/ui/gtk/progress.c
new file mode 100644
index 000000000000..482bcf3df9b7
--- /dev/null
+++ b/tools/perf/ui/gtk/progress.c
@@ -0,0 +1,59 @@
+#include <inttypes.h>
+
+#include "gtk.h"
+#include "../progress.h"
+#include "util.h"
+
+static GtkWidget *dialog;
+static GtkWidget *progress;
+
+static void gtk_progress_update(u64 curr, u64 total, const char *title)
+{
+	double fraction = total ? 1.0 * curr / total : 0.0;
+	char buf[1024];
+
+	if (dialog == NULL) {
+		GtkWidget *vbox = gtk_vbox_new(TRUE, 5);
+		GtkWidget *label = gtk_label_new(title);
+
+		dialog = gtk_window_new(GTK_WINDOW_TOPLEVEL);
+		progress = gtk_progress_bar_new();
+
+		gtk_box_pack_start(GTK_BOX(vbox), label, TRUE, FALSE, 3);
+		gtk_box_pack_start(GTK_BOX(vbox), progress, TRUE, TRUE, 3);
+
+		gtk_container_add(GTK_CONTAINER(dialog), vbox);
+
+		gtk_window_set_title(GTK_WINDOW(dialog), "perf");
+		gtk_window_resize(GTK_WINDOW(dialog), 300, 80);
+		gtk_window_set_position(GTK_WINDOW(dialog), GTK_WIN_POS_CENTER);
+
+		gtk_widget_show_all(dialog);
+	}
+
+	gtk_progress_bar_set_fraction(GTK_PROGRESS_BAR(progress), fraction);
+	snprintf(buf, sizeof(buf), "%"PRIu64" / %"PRIu64, curr, total);
+	gtk_progress_bar_set_text(GTK_PROGRESS_BAR(progress), buf);
+
+	/* we didn't call gtk_main yet, so do it manually */
+	while (gtk_events_pending())
+		gtk_main_iteration();
+}
+
+static void gtk_progress_finish(void)
+{
+	/* this will also destroy all of its children */
+	gtk_widget_destroy(dialog);
+
+	dialog = NULL;
+}
+
+static struct ui_progress gtk_progress_fns = {
+	.update		= gtk_progress_update,
+	.finish		= gtk_progress_finish,
+};
+
+void perf_gtk__init_progress(void)
+{
+	progress_fns = &gtk_progress_fns;
+}
diff --git a/tools/perf/ui/gtk/setup.c b/tools/perf/ui/gtk/setup.c
index 3c4c6ef78283..6c2dd2e423f3 100644
--- a/tools/perf/ui/gtk/setup.c
+++ b/tools/perf/ui/gtk/setup.c
@@ -8,7 +8,9 @@ int perf_gtk__init(void)
 {
 	perf_error__register(&perf_gtk_eops);
 	perf_gtk__init_helpline();
+	perf_gtk__init_progress();
 	perf_gtk__init_hpp();
+
 	return gtk_init_check(NULL, NULL) ? 0 : -1;
 }
 
diff --git a/tools/perf/ui/gtk/util.c b/tools/perf/ui/gtk/util.c
index ccb046aac98b..c06942a41c78 100644
--- a/tools/perf/ui/gtk/util.c
+++ b/tools/perf/ui/gtk/util.c
@@ -111,14 +111,3 @@ struct perf_error_ops perf_gtk_eops = {
 	.warning	= perf_gtk__warning_statusbar,
 #endif
 };
-
-/*
- * FIXME: Functions below should be implemented properly.
- *        For now, just add stubs for NO_NEWT=1 build.
- */
-#ifndef NEWT_SUPPORT
-void ui_progress__update(u64 curr __maybe_unused, u64 total __maybe_unused,
-			 const char *title __maybe_unused)
-{
-}
-#endif
diff --git a/tools/perf/ui/progress.c b/tools/perf/ui/progress.c
index 13aa64e50e11..3ec695607a4d 100644
--- a/tools/perf/ui/progress.c
+++ b/tools/perf/ui/progress.c
@@ -1,32 +1,26 @@
 #include "../cache.h"
 #include "progress.h"
-#include "libslang.h"
-#include "ui.h"
-#include "browser.h"
 
-void ui_progress__update(u64 curr, u64 total, const char *title)
+static void nop_progress_update(u64 curr __maybe_unused,
+				u64 total __maybe_unused,
+				const char *title __maybe_unused)
 {
-	int bar, y;
-	/*
-	 * FIXME: We should have a per UI backend way of showing progress,
-	 * stdio will just show a percentage as NN%, etc.
-	 */
-	if (use_browser <= 0)
-		return;
+}
 
-	if (total == 0)
-		return;
+static struct ui_progress default_progress_fns =
+{
+	.update		= nop_progress_update,
+};
 
-	ui__refresh_dimensions(true);
-	pthread_mutex_lock(&ui__lock);
-	y = SLtt_Screen_Rows / 2 - 2;
-	SLsmg_set_color(0);
-	SLsmg_draw_box(y, 0, 3, SLtt_Screen_Cols);
-	SLsmg_gotorc(y++, 1);
-	SLsmg_write_string((char *)title);
-	SLsmg_set_color(HE_COLORSET_SELECTED);
-	bar = ((SLtt_Screen_Cols - 2) * curr) / total;
-	SLsmg_fill_region(y, 1, 1, bar, ' ');
-	SLsmg_refresh();
-	pthread_mutex_unlock(&ui__lock);
+struct ui_progress *progress_fns = &default_progress_fns;
+
+void ui_progress__update(u64 curr, u64 total, const char *title)
+{
+	return progress_fns->update(curr, total, title);
+}
+
+void ui_progress__finish(void)
+{
+	if (progress_fns->finish)
+		progress_fns->finish();
 }
diff --git a/tools/perf/ui/progress.h b/tools/perf/ui/progress.h
index d9c205b59aa1..257cc224f9cf 100644
--- a/tools/perf/ui/progress.h
+++ b/tools/perf/ui/progress.h
@@ -3,6 +3,16 @@
 
 #include <../types.h>
 
+struct ui_progress {
+	void (*update)(u64, u64, const char *);
+	void (*finish)(void);
+};
+
+extern struct ui_progress *progress_fns;
+
+void ui_progress__init(void);
+
 void ui_progress__update(u64 curr, u64 total, const char *title);
+void ui_progress__finish(void);
 
 #endif
diff --git a/tools/perf/ui/tui/progress.c b/tools/perf/ui/tui/progress.c
new file mode 100644
index 000000000000..6c2184d53cbf
--- /dev/null
+++ b/tools/perf/ui/tui/progress.c
@@ -0,0 +1,42 @@
+#include "../cache.h"
+#include "../progress.h"
+#include "../libslang.h"
+#include "../ui.h"
+#include "../browser.h"
+
+static void tui_progress__update(u64 curr, u64 total, const char *title)
+{
+	int bar, y;
+	/*
+	 * FIXME: We should have a per UI backend way of showing progress,
+	 * stdio will just show a percentage as NN%, etc.
+	 */
+	if (use_browser <= 0)
+		return;
+
+	if (total == 0)
+		return;
+
+	ui__refresh_dimensions(true);
+	pthread_mutex_lock(&ui__lock);
+	y = SLtt_Screen_Rows / 2 - 2;
+	SLsmg_set_color(0);
+	SLsmg_draw_box(y, 0, 3, SLtt_Screen_Cols);
+	SLsmg_gotorc(y++, 1);
+	SLsmg_write_string((char *)title);
+	SLsmg_set_color(HE_COLORSET_SELECTED);
+	bar = ((SLtt_Screen_Cols - 2) * curr) / total;
+	SLsmg_fill_region(y, 1, 1, bar, ' ');
+	SLsmg_refresh();
+	pthread_mutex_unlock(&ui__lock);
+}
+
+static struct ui_progress tui_progress_fns =
+{
+	.update		= tui_progress__update,
+};
+
+void ui_progress__init(void)
+{
+	progress_fns = &tui_progress_fns;
+}
diff --git a/tools/perf/ui/tui/setup.c b/tools/perf/ui/tui/setup.c
index 60debb81537a..81efa192e86c 100644
--- a/tools/perf/ui/tui/setup.c
+++ b/tools/perf/ui/tui/setup.c
@@ -118,6 +118,7 @@ int ui__init(void)
 	newtSetSuspendCallback(newt_suspend, NULL);
 	ui_helpline__init();
 	ui_browser__init();
+	ui_progress__init();
 
 	signal(SIGSEGV, ui__signal);
 	signal(SIGFPE, ui__signal);
diff --git a/tools/perf/ui/ui.h b/tools/perf/ui/ui.h
index 7b67045479f6..d86359c99907 100644
--- a/tools/perf/ui/ui.h
+++ b/tools/perf/ui/ui.h
@@ -3,9 +3,37 @@
 
 #include <pthread.h>
 #include <stdbool.h>
+#include <linux/compiler.h>
 
 extern pthread_mutex_t ui__lock;
 
+extern int use_browser;
+
+void setup_browser(bool fallback_to_pager);
+void exit_browser(bool wait_for_ok);
+
+#ifdef NEWT_SUPPORT
+int ui__init(void);
+void ui__exit(bool wait_for_ok);
+#else
+static inline int ui__init(void)
+{
+	return -1;
+}
+static inline void ui__exit(bool wait_for_ok __maybe_unused) {}
+#endif
+
+#ifdef GTK2_SUPPORT
+int perf_gtk__init(void);
+void perf_gtk__exit(bool wait_for_ok);
+#else
+static inline int perf_gtk__init(void)
+{
+	return -1;
+}
+static inline void perf_gtk__exit(bool wait_for_ok __maybe_unused) {}
+#endif
+
 void ui__refresh_dimensions(bool force);
 
 #endif /* _PERF_UI_H_ */
diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h
index 2bd51370ad28..26e367239873 100644
--- a/tools/perf/util/cache.h
+++ b/tools/perf/util/cache.h
@@ -5,6 +5,7 @@
 #include "util.h"
 #include "strbuf.h"
 #include "../perf.h"
+#include "../ui/ui.h"
 
 #define CMD_EXEC_PATH "--exec-path"
 #define CMD_PERF_DIR "--perf-dir="
@@ -31,44 +32,6 @@ extern const char *pager_program;
 extern int pager_in_use(void);
 extern int pager_use_color;
 
-extern int use_browser;
-
-#if defined(NEWT_SUPPORT) || defined(GTK2_SUPPORT)
-void setup_browser(bool fallback_to_pager);
-void exit_browser(bool wait_for_ok);
-
-#ifdef NEWT_SUPPORT
-int ui__init(void);
-void ui__exit(bool wait_for_ok);
-#else
-static inline int ui__init(void)
-{
-	return -1;
-}
-static inline void ui__exit(bool wait_for_ok __maybe_unused) {}
-#endif
-
-#ifdef GTK2_SUPPORT
-int perf_gtk__init(void);
-void perf_gtk__exit(bool wait_for_ok);
-#else
-static inline int perf_gtk__init(void)
-{
-	return -1;
-}
-static inline void perf_gtk__exit(bool wait_for_ok __maybe_unused) {}
-#endif
-
-#else /* NEWT_SUPPORT || GTK2_SUPPORT */
-
-static inline void setup_browser(bool fallback_to_pager)
-{
-	if (fallback_to_pager)
-		setup_pager();
-}
-static inline void exit_browser(bool wait_for_ok __maybe_unused) {}
-#endif /* NEWT_SUPPORT || GTK2_SUPPORT */
-
 char *alias_lookup(const char *alias);
 int split_cmdline(char *cmdline, const char ***argv);
 
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index dec98750b484..83e8d234af6b 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -26,6 +26,7 @@ int ui__error(const char *format, ...) __attribute__((format(printf, 1, 2)));
 static inline void ui_progress__update(u64 curr __maybe_unused,
 				       u64 total __maybe_unused,
 				       const char *title __maybe_unused) {}
+static inline void ui_progress__finish(void) {}
 
 #define ui__error(format, arg...) ui__warning(format, ##arg)
 
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index ca9ca285406a..3cf2c3e0605f 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -193,55 +193,43 @@ static int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 	event->header.misc = PERF_RECORD_MISC_USER;
 
 	while (1) {
-		char bf[BUFSIZ], *pbf = bf;
-		int n;
+		char bf[BUFSIZ];
+		char prot[5];
+		char execname[PATH_MAX];
+		char anonstr[] = "//anon";
 		size_t size;
+
 		if (fgets(bf, sizeof(bf), fp) == NULL)
 			break;
 
+		/* ensure null termination since stack will be reused. */
+		strcpy(execname, "");
+
 		/* 00400000-0040c000 r-xp 00000000 fd:01 41038  /bin/cat */
-		n = hex2u64(pbf, &event->mmap.start);
-		if (n < 0)
-			continue;
-		pbf += n + 1;
-		n = hex2u64(pbf, &event->mmap.len);
-		if (n < 0)
+		sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %*x:%*x %*u %s\n",
+		       &event->mmap.start, &event->mmap.len, prot,
+		       &event->mmap.pgoff, execname);
+
+		if (prot[2] != 'x')
 			continue;
-		pbf += n + 3;
-		if (*pbf == 'x') { /* vm_exec */
-			char anonstr[] = "//anon\n";
-			char *execname = strchr(bf, '/');
-
-			/* Catch VDSO */
-			if (execname == NULL)
-				execname = strstr(bf, "[vdso]");
-
-			/* Catch anonymous mmaps */
-			if ((execname == NULL) && !strstr(bf, "["))
-				execname = anonstr;
-
-			if (execname == NULL)
-				continue;
-
-			pbf += 3;
-			n = hex2u64(pbf, &event->mmap.pgoff);
-
-			size = strlen(execname);
-			execname[size - 1] = '\0'; /* Remove \n */
-			memcpy(event->mmap.filename, execname, size);
-			size = PERF_ALIGN(size, sizeof(u64));
-			event->mmap.len -= event->mmap.start;
-			event->mmap.header.size = (sizeof(event->mmap) -
-					        (sizeof(event->mmap.filename) - size));
-			memset(event->mmap.filename + size, 0, machine->id_hdr_size);
-			event->mmap.header.size += machine->id_hdr_size;
-			event->mmap.pid = tgid;
-			event->mmap.tid = pid;
-
-			if (process(tool, event, &synth_sample, machine) != 0) {
-				rc = -1;
-				break;
-			}
+
+		if (!strcmp(execname, ""))
+			strcpy(execname, anonstr);
+
+		size = strlen(execname) + 1;
+		memcpy(event->mmap.filename, execname, size);
+		size = PERF_ALIGN(size, sizeof(u64));
+		event->mmap.len -= event->mmap.start;
+		event->mmap.header.size = (sizeof(event->mmap) -
+					   (sizeof(event->mmap.filename) - size));
+		memset(event->mmap.filename + size, 0, machine->id_hdr_size);
+		event->mmap.header.size += machine->id_hdr_size;
+		event->mmap.pid = tgid;
+		event->mmap.tid = pid;
+
+		if (process(tool, event, &synth_sample, machine) != 0) {
+			rc = -1;
+			break;
 		}
 	}
 
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index a41dc4a5c2de..705293489e3c 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -52,15 +52,13 @@ struct perf_evlist *perf_evlist__new(struct cpu_map *cpus,
 void perf_evlist__config_attrs(struct perf_evlist *evlist,
 			       struct perf_record_opts *opts)
 {
-	struct perf_evsel *evsel, *first;
+	struct perf_evsel *evsel;
 
 	if (evlist->cpus->map[0] < 0)
 		opts->no_inherit = true;
 
-	first = perf_evlist__first(evlist);
-
 	list_for_each_entry(evsel, &evlist->entries, node) {
-		perf_evsel__config(evsel, opts, first);
+		perf_evsel__config(evsel, opts);
 
 		if (evlist->nr_entries > 1)
 			evsel->attr.sample_type |= PERF_SAMPLE_ID;
@@ -224,6 +222,8 @@ void perf_evlist__disable(struct perf_evlist *evlist)
 
 	for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
 		list_for_each_entry(pos, &evlist->entries, node) {
+			if (perf_evsel__is_group_member(pos))
+				continue;
 			for (thread = 0; thread < evlist->threads->nr; thread++)
 				ioctl(FD(pos, cpu, thread),
 				      PERF_EVENT_IOC_DISABLE, 0);
@@ -238,6 +238,8 @@ void perf_evlist__enable(struct perf_evlist *evlist)
 
 	for (cpu = 0; cpu < cpu_map__nr(evlist->cpus); cpu++) {
 		list_for_each_entry(pos, &evlist->entries, node) {
+			if (perf_evsel__is_group_member(pos))
+				continue;
 			for (thread = 0; thread < evlist->threads->nr; thread++)
 				ioctl(FD(pos, cpu, thread),
 				      PERF_EVENT_IOC_ENABLE, 0);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 618d41140abd..1fb636c550a1 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -404,13 +404,40 @@ const char *perf_evsel__name(struct perf_evsel *evsel)
 	return evsel->name ?: "unknown";
 }
 
-void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts,
-			struct perf_evsel *first)
+/*
+ * The enable_on_exec/disabled value strategy:
+ *
+ *  1) For any type of traced program:
+ *    - all independent events and group leaders are disabled
+ *    - all group members are enabled
+ *
+ *     Group members are ruled by group leaders. They need to
+ *     be enabled, because the group scheduling relies on that.
+ *
+ *  2) For traced programs executed by perf:
+ *     - all independent events and group leaders have
+ *       enable_on_exec set
+ *     - we don't specifically enable or disable any event during
+ *       the record command
+ *
+ *     Independent events and group leaders are initially disabled
+ *     and get enabled by exec. Group members are ruled by group
+ *     leaders as stated in 1).
+ *
+ *  3) For traced programs attached by perf (pid/tid):
+ *     - we specifically enable or disable all events during
+ *       the record command
+ *
+ *     When attaching events to already running traced we
+ *     enable/disable events specifically, as there's no
+ *     initial traced exec call.
+ */
+void perf_evsel__config(struct perf_evsel *evsel,
+			struct perf_record_opts *opts)
 {
 	struct perf_event_attr *attr = &evsel->attr;
 	int track = !evsel->idx; /* only the first counter needs these */
 
-	attr->disabled = 1;
 	attr->sample_id_all = opts->sample_id_all_missing ? 0 : 1;
 	attr->inherit	    = !opts->no_inherit;
 	attr->read_format   = PERF_FORMAT_TOTAL_TIME_ENABLED |
@@ -486,10 +513,21 @@ void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts,
 	attr->mmap = track;
 	attr->comm = track;
 
-	if (perf_target__none(&opts->target) &&
-	    (!opts->group || evsel == first)) {
+	/*
+	 * XXX see the function comment above
+	 *
+	 * Disabling only independent events or group leaders,
+	 * keeping group members enabled.
+	 */
+	if (!perf_evsel__is_group_member(evsel))
+		attr->disabled = 1;
+
+	/*
+	 * Setting enable_on_exec for independent events and
+	 * group leaders for traced executed by perf.
+	 */
+	if (perf_target__none(&opts->target) && !perf_evsel__is_group_member(evsel))
 		attr->enable_on_exec = 1;
-	}
 }
 
 int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
@@ -669,7 +707,7 @@ static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread)
 	struct perf_evsel *leader = evsel->leader;
 	int fd;
 
-	if (!leader)
+	if (!perf_evsel__is_group_member(evsel))
 		return -1;
 
 	/*
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 6f94d6dea00f..a4c1dd4e149f 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -3,6 +3,7 @@
 
 #include <linux/list.h>
 #include <stdbool.h>
+#include <stddef.h>
 #include "../../../include/uapi/linux/perf_event.h"
 #include "types.h"
 #include "xyarray.h"
@@ -92,8 +93,7 @@ void perf_evsel__exit(struct perf_evsel *evsel);
 void perf_evsel__delete(struct perf_evsel *evsel);
 
 void perf_evsel__config(struct perf_evsel *evsel,
-			struct perf_record_opts *opts,
-			struct perf_evsel *first);
+			struct perf_record_opts *opts);
 
 bool perf_evsel__is_cache_op_valid(u8 type, u8 op);
 
@@ -225,4 +225,9 @@ static inline struct perf_evsel *perf_evsel__next(struct perf_evsel *evsel)
 {
 	return list_entry(evsel->node.next, struct perf_evsel, node);
 }
+
+static inline bool perf_evsel__is_group_member(const struct perf_evsel *evsel)
+{
+	return evsel->leader != NULL;
+}
 #endif /* __PERF_EVSEL_H */
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 7c6e73b1b7ea..cb17e2a8c6ed 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -742,9 +742,8 @@ static struct hist_entry *hists__add_dummy_entry(struct hists *hists,
 
 	he = hist_entry__new(pair);
 	if (he) {
-		he->stat.nr_events = 0;
-		he->stat.period    = 0;
-		he->hists	   = hists;
+		memset(&he->stat, 0, sizeof(he->stat));
+		he->hists = hists;
 		rb_link_node(&he->rb_node, parent, p);
 		rb_insert_color(&he->rb_node, &hists->entries);
 		hists__inc_nr_entries(hists, he);
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 1278c2c72a96..8b091a51e4a2 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -195,7 +195,7 @@ static inline int hist_entry__tui_annotate(struct hist_entry *self
 	return 0;
 }
 
-static inline int script_browse(const char *script_opt)
+static inline int script_browse(const char *script_opt __maybe_unused)
 {
 	return 0;
 }
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index c0b785b50849..020323af3364 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -722,6 +722,27 @@ static int get_event_modifier(struct event_modifier *mod, char *str,
 	return 0;
 }
 
+/*
+ * Basic modifier sanity check to validate it contains only one
+ * instance of any modifier (apart from 'p') present.
+ */
+static int check_modifier(char *str)
+{
+	char *p = str;
+
+	/* The sizeof includes 0 byte as well. */
+	if (strlen(str) > (sizeof("ukhGHppp") - 1))
+		return -1;
+
+	while (*p) {
+		if (*p != 'p' && strchr(p + 1, *p))
+			return -1;
+		p++;
+	}
+
+	return 0;
+}
+
 int parse_events__modifier_event(struct list_head *list, char *str, bool add)
 {
 	struct perf_evsel *evsel;
@@ -730,6 +751,9 @@ int parse_events__modifier_event(struct list_head *list, char *str, bool add)
 	if (str == NULL)
 		return 0;
 
+	if (check_modifier(str))
+		return -EINVAL;
+
 	if (!add && get_event_modifier(&mod, str, NULL))
 		return -EINVAL;
 
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index ac9a6aacf2f5..f6399373d67d 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -99,7 +99,6 @@ void parse_events__set_leader(char *name, struct list_head *list);
 void parse_events_update_lists(struct list_head *list_event,
 			       struct list_head *list_all);
 void parse_events_error(void *data, void *scanner, char const *msg);
-int parse_events__test(void);
 
 void print_events(const char *event_glob, bool name_only);
 void print_events_type(u8 type);
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 66959fab6634..e9d1134c2c68 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -82,7 +82,7 @@ num_hex		0x[a-fA-F0-9]+
 num_raw_hex	[a-fA-F0-9]+
 name		[a-zA-Z_*?][a-zA-Z0-9_*?]*
 name_minus	[a-zA-Z_*?][a-zA-Z0-9\-_*?]*
-modifier_event	[ukhpGH]{1,8}
+modifier_event	[ukhpGH]+
 modifier_bp	[rwx]{1,3}
 
 %%
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 18e84801d4d1..9bdc60c6f138 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -22,7 +22,7 @@ static LIST_HEAD(pmus);
  * Parse & process all the sysfs attributes located under
  * the directory specified in 'dir' parameter.
  */
-static int pmu_format_parse(char *dir, struct list_head *head)
+int perf_pmu__format_parse(char *dir, struct list_head *head)
 {
 	struct dirent *evt_ent;
 	DIR *format_dir;
@@ -77,7 +77,7 @@ static int pmu_format(char *name, struct list_head *format)
 	if (stat(path, &st) < 0)
 		return 0;	/* no error if format does not exist */
 
-	if (pmu_format_parse(path, format))
+	if (perf_pmu__format_parse(path, format))
 		return -1;
 
 	return 0;
@@ -446,8 +446,9 @@ static int pmu_config_term(struct list_head *formats,
 	return 0;
 }
 
-static int pmu_config(struct list_head *formats, struct perf_event_attr *attr,
-		      struct list_head *head_terms)
+int perf_pmu__config_terms(struct list_head *formats,
+			   struct perf_event_attr *attr,
+			   struct list_head *head_terms)
 {
 	struct parse_events__term *term;
 
@@ -467,7 +468,7 @@ int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
 		     struct list_head *head_terms)
 {
 	attr->type = pmu->type;
-	return pmu_config(&pmu->format, attr, head_terms);
+	return perf_pmu__config_terms(&pmu->format, attr, head_terms);
 }
 
 static struct perf_pmu__alias *pmu_find_alias(struct perf_pmu *pmu,
@@ -551,177 +552,3 @@ void perf_pmu__set_format(unsigned long *bits, long from, long to)
 	for (b = from; b <= to; b++)
 		set_bit(b, bits);
 }
-
-/* 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", },
-};
-
-#define TEST_FORMATS_CNT (sizeof(test_formats) / sizeof(struct test_format))
-
-/* 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,
-	},
-};
-#define TERMS_CNT (sizeof(test_terms) / sizeof(struct parse_events__term))
-
-/*
- * 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 < TEST_FORMATS_CNT; 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 < TERMS_CNT; i++)
-		list_add_tail(&test_terms[i].list, &terms);
-
-	return &terms;
-}
-
-#undef TERMS_CNT
-
-int perf_pmu__test(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 = pmu_format_parse(format, &formats);
-		if (ret)
-			break;
-
-		ret = pmu_config(&formats, &attr, terms);
-		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/util/pmu.h b/tools/perf/util/pmu.h
index 39f3abac7744..07d553fe8d83 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -37,6 +37,9 @@ struct perf_pmu {
 struct perf_pmu *perf_pmu__find(char *name);
 int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
 		     struct list_head *head_terms);
+int perf_pmu__config_terms(struct list_head *formats,
+			   struct perf_event_attr *attr,
+			   struct list_head *head_terms);
 int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms);
 struct list_head *perf_pmu__alias(struct perf_pmu *pmu,
 				struct list_head *head_terms);
@@ -46,6 +49,7 @@ void perf_pmu_error(struct list_head *list, char *name, char const *msg);
 int perf_pmu__new_format(struct list_head *list, char *name,
 			 int config, unsigned long *bits);
 void perf_pmu__set_format(unsigned long *bits, long from, long to);
+int perf_pmu__format_parse(char *dir, struct list_head *head);
 
 struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu);
 
diff --git a/tools/perf/util/pstack.c b/tools/perf/util/pstack.c
index 13d36faf64eb..daa17aeb6c63 100644
--- a/tools/perf/util/pstack.c
+++ b/tools/perf/util/pstack.c
@@ -17,59 +17,59 @@ struct pstack {
 
 struct pstack *pstack__new(unsigned short max_nr_entries)
 {
-	struct pstack *self = zalloc((sizeof(*self) +
-				     max_nr_entries * sizeof(void *)));
-	if (self != NULL)
-		self->max_nr_entries = max_nr_entries;
-	return self;
+	struct pstack *pstack = zalloc((sizeof(*pstack) +
+				       max_nr_entries * sizeof(void *)));
+	if (pstack != NULL)
+		pstack->max_nr_entries = max_nr_entries;
+	return pstack;
 }
 
-void pstack__delete(struct pstack *self)
+void pstack__delete(struct pstack *pstack)
 {
-	free(self);
+	free(pstack);
 }
 
-bool pstack__empty(const struct pstack *self)
+bool pstack__empty(const struct pstack *pstack)
 {
-	return self->top == 0;
+	return pstack->top == 0;
 }
 
-void pstack__remove(struct pstack *self, void *key)
+void pstack__remove(struct pstack *pstack, void *key)
 {
-	unsigned short i = self->top, last_index = self->top - 1;
+	unsigned short i = pstack->top, last_index = pstack->top - 1;
 
 	while (i-- != 0) {
-		if (self->entries[i] == key) {
+		if (pstack->entries[i] == key) {
 			if (i < last_index)
-				memmove(self->entries + i,
-					self->entries + i + 1,
+				memmove(pstack->entries + i,
+					pstack->entries + i + 1,
 					(last_index - i) * sizeof(void *));
-			--self->top;
+			--pstack->top;
 			return;
 		}
 	}
 	pr_err("%s: %p not on the pstack!\n", __func__, key);
 }
 
-void pstack__push(struct pstack *self, void *key)
+void pstack__push(struct pstack *pstack, void *key)
 {
-	if (self->top == self->max_nr_entries) {
-		pr_err("%s: top=%d, overflow!\n", __func__, self->top);
+	if (pstack->top == pstack->max_nr_entries) {
+		pr_err("%s: top=%d, overflow!\n", __func__, pstack->top);
 		return;
 	}
-	self->entries[self->top++] = key;
+	pstack->entries[pstack->top++] = key;
 }
 
-void *pstack__pop(struct pstack *self)
+void *pstack__pop(struct pstack *pstack)
 {
 	void *ret;
 
-	if (self->top == 0) {
+	if (pstack->top == 0) {
 		pr_err("%s: underflow!\n", __func__);
 		return NULL;
 	}
 
-	ret = self->entries[--self->top];
-	self->entries[self->top] = NULL;
+	ret = pstack->entries[--pstack->top];
+	pstack->entries[pstack->top] = NULL;
 	return ret;
 }
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 15abe40dc702..ce6f51162386 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1458,6 +1458,7 @@ more:
 	session->ordered_samples.next_flush = ULLONG_MAX;
 	err = flush_sample_queue(session, tool);
 out_err:
+	ui_progress__finish();
 	perf_session__warn_about_errors(session, tool);
 	perf_session_free_sample_buffers(session);
 	return err;
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 04ccf2962080..de68f98b236d 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -224,7 +224,6 @@ size_t symbol__fprintf_symname(const struct symbol *sym, FILE *fp);
 size_t symbol__fprintf(struct symbol *sym, FILE *fp);
 bool symbol_type__is_a(char symbol_type, enum map_type map_type);
 
-int dso__test_data(void);
 int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 		  struct symsrc *runtime_ss, symbol_filter_t filter,
 		  int kmodule);
diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include
index 96ce80a3743b..2964b96aa55f 100644
--- a/tools/scripts/Makefile.include
+++ b/tools/scripts/Makefile.include
@@ -1,8 +1,11 @@
-ifeq ("$(origin O)", "command line")
+ifeq ($(origin O), command line)
 	dummy := $(if $(shell test -d $(O) || echo $(O)),$(error O=$(O) does not exist),)
 	ABSOLUTE_O := $(shell cd $(O) ; pwd)
-	OUTPUT := $(ABSOLUTE_O)/
+	OUTPUT := $(ABSOLUTE_O)/$(if $(subdir),$(subdir)/)
 	COMMAND_O := O=$(ABSOLUTE_O)
+ifeq ($(objtree),)
+	objtree := $(O)
+endif
 endif
 
 ifneq ($(OUTPUT),)
@@ -41,7 +44,16 @@ else
 NO_SUBDIR = :
 endif
 
-QUIET_SUBDIR0  = +$(MAKE) -C # space to separate -C and subdir
+#
+# Define a callable command for descending to a new directory
+#
+# Call by doing: $(call descend,directory[,target])
+#
+descend = \
+	+mkdir -p $(OUTPUT)$(1) && \
+	$(MAKE) $(COMMAND_O) subdir=$(if $(subdir),$(subdir)/$(1),$(1)) $(PRINT_DIR) -C $(1) $(2)
+
+QUIET_SUBDIR0  = +$(MAKE) $(COMMAND_O) -C # space to separate -C and subdir
 QUIET_SUBDIR1  =
 
 ifneq ($(findstring $(MAKEFLAGS),s),s)
@@ -56,5 +68,10 @@ ifndef V
 			 $(MAKE) $(PRINT_DIR) -C $$subdir
 	QUIET_FLEX     = @echo '   ' FLEX $@;
 	QUIET_BISON    = @echo '   ' BISON $@;
+
+	descend = \
+		@echo '   ' DESCEND $(1); \
+		mkdir -p $(OUTPUT)$(1) && \
+		$(MAKE) $(COMMAND_O) subdir=$(if $(subdir),$(subdir)/$(1),$(1)) $(PRINT_DIR) -C $(1) $(2)
 endif
 endif