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

Conflicts:
	tools/Makefile

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

. Honor parallel jobs, fix from Borislav Petkov

. Introduce tools/lib/lk library, initially just removing duplication
  among tools/perf and tools/vm. from Borislav Petkov

. Fix build on non-glibc systems due to libio.h absence, from Cody P Schafer.

. Remove some perf_session and tracing dead code, from David Ahern.

. Introduce perf stat --repeat forever, from Frederik Deweerdt.

. Add perf test entries for checking --cpu in record and stat, from Jiri Olsa.

. Add perf test entries for checking breakpoint overflow signal handler issues,
  from Jiri Olsa.

. Add perf test entry for for checking number of EXIT events, from Namhyung Kim.

. Simplify some perf_evlist methods and to allow 'stat' to share code with
  'record' and 'trace'.

. Remove dead code in related to libtraceevent integration, from Namhyung Kim.

. Event group view for 'annotate' in --stdio, --tui and --gtk, from Namhyung Kim.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
[ resolved the trivial merge conflict with upstream ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>

75 files changed, 1432 insertions, 788 deletions

diff --git a/Makefile b/Makefile
index a05ea42c5f18..6b39246c2c67 100644
--- a/Makefile
+++ b/Makefile
@@ -1331,11 +1331,11 @@ kernelversion:
 # Clear a bunch of variables before executing the submake
 tools/: FORCE
 	$(Q)mkdir -p $(objtree)/tools
-	$(Q)$(MAKE) LDFLAGS= MAKEFLAGS= O=$(objtree) subdir=tools -C $(src)/tools/
+	$(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(filter --j% -j,$(MAKEFLAGS))" O=$(objtree) subdir=tools -C $(src)/tools/
 
 tools/%: FORCE
 	$(Q)mkdir -p $(objtree)/tools
-	$(Q)$(MAKE) LDFLAGS= MAKEFLAGS= O=$(objtree) subdir=tools -C $(src)/tools/ $*
+	$(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(filter --j% -j,$(MAKEFLAGS))" O=$(objtree) subdir=tools -C $(src)/tools/ $*
 
 # Single targets
 # ---------------------------------------------------------------------------
diff --git a/tools/Makefile b/tools/Makefile
index fa36565b209d..6aaeb6cd867d 100644
--- a/tools/Makefile
+++ b/tools/Makefile
@@ -34,7 +34,13 @@ help:
 cpupower: FORCE
 	$(call descend,power/$@)
 
-cgroup firewire lguest perf usb virtio vm: FORCE
+cgroup firewire guest usb virtio vm: FORCE
+	$(call descend,$@)
+
+liblk: FORCE
+	$(call descend,lib/lk)
+
+perf: liblk FORCE
 	$(call descend,$@)
 
 selftests: FORCE
@@ -62,7 +68,13 @@ install: cgroup_install cpupower_install firewire_install lguest_install \
 cpupower_clean:
 	$(call descend,power/cpupower,clean)
 
-cgroup_clean firewire_clean lguest_clean perf_clean usb_clean virtio_clean vm_clean:
+cgroup_clean firewire_clean lguest_clean usb_clean virtio_clean vm_clean:
+	$(call descend,$(@:_clean=),clean)
+
+liblk_clean:
+	$(call descend,lib/lk,clean)
+
+perf_clean: liblk_clean
 	$(call descend,$(@:_clean=),clean)
 
 selftests_clean:
diff --git a/tools/lib/lk/Makefile b/tools/lib/lk/Makefile
new file mode 100644
index 000000000000..926cbf3efc7f
--- /dev/null
+++ b/tools/lib/lk/Makefile
@@ -0,0 +1,35 @@
+include ../../scripts/Makefile.include
+
+# guard against environment variables
+LIB_H=
+LIB_OBJS=
+
+LIB_H += debugfs.h
+
+LIB_OBJS += $(OUTPUT)debugfs.o
+
+LIBFILE = liblk.a
+
+CFLAGS = -ggdb3 -Wall -Wextra -std=gnu99 -Werror -O6 -D_FORTIFY_SOURCE=2 $(EXTRA_WARNINGS) $(EXTRA_CFLAGS) -fPIC
+EXTLIBS = -lpthread -lrt -lelf -lm
+ALL_CFLAGS = $(CFLAGS) $(BASIC_CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64
+ALL_LDFLAGS = $(LDFLAGS)
+
+RM = rm -f
+
+$(LIBFILE): $(LIB_OBJS)
+	$(QUIET_AR)$(RM) $@ && $(AR) rcs $(OUTPUT)$@ $(LIB_OBJS)
+
+$(LIB_OBJS): $(LIB_H)
+
+$(OUTPUT)%.o: %.c
+	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $<
+$(OUTPUT)%.s: %.c
+	$(QUIET_CC)$(CC) -S $(ALL_CFLAGS) $<
+$(OUTPUT)%.o: %.S
+	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $<
+
+clean:
+	$(RM) $(LIB_OBJS) $(LIBFILE)
+
+.PHONY: clean
diff --git a/tools/perf/util/debugfs.c b/tools/lib/lk/debugfs.c
index dd8b19319c03..099e7cd022e4 100644
--- a/tools/perf/util/debugfs.c
+++ b/tools/lib/lk/debugfs.c
@@ -1,36 +1,39 @@
-#include "util.h"
-#include "debugfs.h"
-#include "cache.h"
-
-#include <linux/kernel.h>
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <stdbool.h>
+#include <sys/vfs.h>
 #include <sys/mount.h>
+#include <linux/magic.h>
+#include <linux/kernel.h>
+
+#include "debugfs.h"
 
-static int debugfs_premounted;
 char debugfs_mountpoint[PATH_MAX + 1] = "/sys/kernel/debug";
-char tracing_events_path[PATH_MAX + 1] = "/sys/kernel/debug/tracing/events";
 
-static const char *debugfs_known_mountpoints[] = {
+static const char * const debugfs_known_mountpoints[] = {
 	"/sys/kernel/debug/",
 	"/debug/",
 	0,
 };
 
-static int debugfs_found;
+static bool debugfs_found;
 
 /* find the path to the mounted debugfs */
 const char *debugfs_find_mountpoint(void)
 {
-	const char **ptr;
+	const char * const *ptr;
 	char type[100];
 	FILE *fp;
 
 	if (debugfs_found)
-		return (const char *) debugfs_mountpoint;
+		return (const char *)debugfs_mountpoint;
 
 	ptr = debugfs_known_mountpoints;
 	while (*ptr) {
 		if (debugfs_valid_mountpoint(*ptr) == 0) {
-			debugfs_found = 1;
+			debugfs_found = true;
 			strcpy(debugfs_mountpoint, *ptr);
 			return debugfs_mountpoint;
 		}
@@ -52,7 +55,7 @@ const char *debugfs_find_mountpoint(void)
 	if (strcmp(type, "debugfs") != 0)
 		return NULL;
 
-	debugfs_found = 1;
+	debugfs_found = true;
 
 	return debugfs_mountpoint;
 }
@@ -71,21 +74,12 @@ int debugfs_valid_mountpoint(const char *debugfs)
 	return 0;
 }
 
-static void debugfs_set_tracing_events_path(const char *mountpoint)
-{
-	snprintf(tracing_events_path, sizeof(tracing_events_path), "%s/%s",
-		 mountpoint, "tracing/events");
-}
-
 /* mount the debugfs somewhere if it's not mounted */
-
 char *debugfs_mount(const char *mountpoint)
 {
 	/* see if it's already mounted */
-	if (debugfs_find_mountpoint()) {
-		debugfs_premounted = 1;
+	if (debugfs_find_mountpoint())
 		goto out;
-	}
 
 	/* if not mounted and no argument */
 	if (mountpoint == NULL) {
@@ -100,15 +94,8 @@ char *debugfs_mount(const char *mountpoint)
 		return NULL;
 
 	/* save the mountpoint */
-	debugfs_found = 1;
+	debugfs_found = true;
 	strncpy(debugfs_mountpoint, mountpoint, sizeof(debugfs_mountpoint));
 out:
-	debugfs_set_tracing_events_path(debugfs_mountpoint);
 	return debugfs_mountpoint;
 }
-
-void debugfs_set_path(const char *mountpoint)
-{
-	snprintf(debugfs_mountpoint, sizeof(debugfs_mountpoint), "%s", mountpoint);
-	debugfs_set_tracing_events_path(mountpoint);
-}
diff --git a/tools/lib/lk/debugfs.h b/tools/lib/lk/debugfs.h
new file mode 100644
index 000000000000..935c59bdb442
--- /dev/null
+++ b/tools/lib/lk/debugfs.h
@@ -0,0 +1,29 @@
+#ifndef __LK_DEBUGFS_H__
+#define __LK_DEBUGFS_H__
+
+#define _STR(x) #x
+#define STR(x) _STR(x)
+
+/*
+ * On most systems <limits.h> would have given us this, but  not on some systems
+ * (e.g. GNU/Hurd).
+ */
+#ifndef PATH_MAX
+#define PATH_MAX 4096
+#endif
+
+#ifndef DEBUGFS_MAGIC
+#define DEBUGFS_MAGIC          0x64626720
+#endif
+
+#ifndef PERF_DEBUGFS_ENVIRONMENT
+#define PERF_DEBUGFS_ENVIRONMENT "PERF_DEBUGFS_DIR"
+#endif
+
+const char *debugfs_find_mountpoint(void);
+int debugfs_valid_mountpoint(const char *debugfs);
+char *debugfs_mount(const char *mountpoint);
+
+extern char debugfs_mountpoint[];
+
+#endif /* __LK_DEBUGFS_H__ */
diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt
index 5ad07ef417f0..e9cd39a92dc2 100644
--- a/tools/perf/Documentation/perf-annotate.txt
+++ b/tools/perf/Documentation/perf-annotate.txt
@@ -93,6 +93,9 @@ OPTIONS
 --skip-missing::
 	Skip symbols that cannot be annotated.
 
+--group::
+	Show event group information together
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-report[1]
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index faf4f4feebcc..23e587ad549e 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -52,7 +52,7 @@ OPTIONS
 
 -r::
 --repeat=<n>::
-	repeat command and print average + stddev (max: 100)
+	repeat command and print average + stddev (max: 100). 0 means forever.
 
 -B::
 --big-num::
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 39d41068484f..025de796067c 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -1,6 +1,7 @@
 tools/perf
 tools/scripts
 tools/lib/traceevent
+tools/lib/lk
 include/linux/const.h
 include/linux/perf_event.h
 include/linux/rbtree.h
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index bb74c79cd16e..0230b75ed7f9 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -215,6 +215,7 @@ BASIC_CFLAGS = \
 	-Iutil \
 	-I. \
 	-I$(TRACE_EVENT_DIR) \
+	-I../lib/ \
 	-D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
 
 BASIC_LDFLAGS =
@@ -240,19 +241,28 @@ SCRIPT_SH += perf-archive.sh
 grep-libs = $(filter -l%,$(1))
 strip-libs = $(filter-out -l%,$(1))
 
+LK_DIR = ../lib/lk/
 TRACE_EVENT_DIR = ../lib/traceevent/
 
+LK_PATH=$(LK_DIR)
+
 ifneq ($(OUTPUT),)
 	TE_PATH=$(OUTPUT)
+ifneq ($(subdir),)
+	LK_PATH=$(OUTPUT)$(LK_DIR)
+else
+	LK_PATH=$(OUTPUT)
+endif
 else
 	TE_PATH=$(TRACE_EVENT_DIR)
 endif
 
 LIBTRACEEVENT = $(TE_PATH)libtraceevent.a
-TE_LIB := -L$(TE_PATH) -ltraceevent
-
 export LIBTRACEEVENT
 
+LIBLK = $(LK_PATH)liblk.a
+export LIBLK
+
 # python extension build directories
 PYTHON_EXTBUILD     := $(OUTPUT)python_ext_build/
 PYTHON_EXTBUILD_LIB := $(PYTHON_EXTBUILD)lib/
@@ -355,7 +365,6 @@ LIB_H += util/cache.h
 LIB_H += util/callchain.h
 LIB_H += util/build-id.h
 LIB_H += util/debug.h
-LIB_H += util/debugfs.h
 LIB_H += util/sysfs.h
 LIB_H += util/pmu.h
 LIB_H += util/event.h
@@ -416,7 +425,6 @@ LIB_OBJS += $(OUTPUT)util/annotate.o
 LIB_OBJS += $(OUTPUT)util/build-id.o
 LIB_OBJS += $(OUTPUT)util/config.o
 LIB_OBJS += $(OUTPUT)util/ctype.o
-LIB_OBJS += $(OUTPUT)util/debugfs.o
 LIB_OBJS += $(OUTPUT)util/sysfs.o
 LIB_OBJS += $(OUTPUT)util/pmu.o
 LIB_OBJS += $(OUTPUT)util/environment.o
@@ -503,6 +511,10 @@ LIB_OBJS += $(OUTPUT)tests/evsel-tp-sched.o
 LIB_OBJS += $(OUTPUT)tests/pmu.o
 LIB_OBJS += $(OUTPUT)tests/hists_link.o
 LIB_OBJS += $(OUTPUT)tests/python-use.o
+LIB_OBJS += $(OUTPUT)tests/bp_signal.o
+LIB_OBJS += $(OUTPUT)tests/bp_signal_overflow.o
+LIB_OBJS += $(OUTPUT)tests/task-exit.o
+LIB_OBJS += $(OUTPUT)tests/sw-clock.o
 
 BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o
 BUILTIN_OBJS += $(OUTPUT)builtin-bench.o
@@ -536,7 +548,7 @@ BUILTIN_OBJS += $(OUTPUT)builtin-kvm.o
 BUILTIN_OBJS += $(OUTPUT)builtin-inject.o
 BUILTIN_OBJS += $(OUTPUT)tests/builtin-test.o
 
-PERFLIBS = $(LIB_FILE) $(LIBTRACEEVENT)
+PERFLIBS = $(LIB_FILE) $(LIBLK) $(LIBTRACEEVENT)
 
 #
 # Platform specific tweaks
@@ -1051,6 +1063,18 @@ $(LIBTRACEEVENT):
 $(LIBTRACEEVENT)-clean:
 	$(QUIET_SUBDIR0)$(TRACE_EVENT_DIR) $(QUIET_SUBDIR1) O=$(OUTPUT) clean
 
+# if subdir is set, we've been called from above so target has been built
+# already
+$(LIBLK):
+ifeq ($(subdir),)
+	$(QUIET_SUBDIR0)$(LK_DIR) $(QUIET_SUBDIR1) O=$(OUTPUT) liblk.a
+endif
+
+$(LIBLK)-clean:
+ifeq ($(subdir),)
+	$(QUIET_SUBDIR0)$(LK_DIR) $(QUIET_SUBDIR1) O=$(OUTPUT) clean
+endif
+
 help:
 	@echo 'Perf make targets:'
 	@echo '  doc		- make *all* documentation (see below)'
@@ -1171,7 +1195,7 @@ $(INSTALL_DOC_TARGETS):
 
 ### Cleaning rules
 
-clean: $(LIBTRACEEVENT)-clean
+clean: $(LIBTRACEEVENT)-clean $(LIBLK)-clean
 	$(RM) $(LIB_OBJS) $(BUILTIN_OBJS) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf.o $(LANG_BINDINGS)
 	$(RM) $(ALL_PROGRAMS) perf
 	$(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope*
@@ -1181,6 +1205,6 @@ clean: $(LIBTRACEEVENT)-clean
 	$(RM) $(OUTPUT)util/*-flex*
 	$(python-clean)
 
-.PHONY: all install clean strip $(LIBTRACEEVENT)
+.PHONY: all install clean strip $(LIBTRACEEVENT) $(LIBLK)
 .PHONY: shell_compatibility_test please_set_SHELL_PATH_to_a_more_modern_shell
 .PHONY: .FORCE-PERF-VERSION-FILE TAGS tags cscope .FORCE-PERF-CFLAGS
diff --git a/tools/perf/arch/arm/util/dwarf-regs.c b/tools/perf/arch/arm/util/dwarf-regs.c
index e8d5c551c69c..33ec5b339da8 100644
--- a/tools/perf/arch/arm/util/dwarf-regs.c
+++ b/tools/perf/arch/arm/util/dwarf-regs.c
@@ -8,10 +8,7 @@
  * published by the Free Software Foundation.
  */
 
-#include <stdlib.h>
-#ifndef __UCLIBC__
-#include <libio.h>
-#endif
+#include <stddef.h>
 #include <dwarf-regs.h>
 
 struct pt_regs_dwarfnum {
diff --git a/tools/perf/arch/powerpc/util/dwarf-regs.c b/tools/perf/arch/powerpc/util/dwarf-regs.c
index 7cdd61d0e27c..733151cdf46e 100644
--- a/tools/perf/arch/powerpc/util/dwarf-regs.c
+++ b/tools/perf/arch/powerpc/util/dwarf-regs.c
@@ -9,10 +9,7 @@
  * 2 of the License, or (at your option) any later version.
  */
 
-#include <stdlib.h>
-#ifndef __UCLIBC__
-#include <libio.h>
-#endif
+#include <stddef.h>
 #include <dwarf-regs.h>
 
 
diff --git a/tools/perf/arch/s390/util/dwarf-regs.c b/tools/perf/arch/s390/util/dwarf-regs.c
index e19653e025fa..0469df02ee62 100644
--- a/tools/perf/arch/s390/util/dwarf-regs.c
+++ b/tools/perf/arch/s390/util/dwarf-regs.c
@@ -6,7 +6,7 @@
  *
  */
 
-#include <libio.h>
+#include <stddef.h>
 #include <dwarf-regs.h>
 
 #define NUM_GPRS 16
diff --git a/tools/perf/arch/sh/util/dwarf-regs.c b/tools/perf/arch/sh/util/dwarf-regs.c
index a11edb007a6c..0d0897f57a10 100644
--- a/tools/perf/arch/sh/util/dwarf-regs.c
+++ b/tools/perf/arch/sh/util/dwarf-regs.c
@@ -19,7 +19,7 @@
  *
  */
 
-#include <libio.h>
+#include <stddef.h>
 #include <dwarf-regs.h>
 
 /*
diff --git a/tools/perf/arch/sparc/util/dwarf-regs.c b/tools/perf/arch/sparc/util/dwarf-regs.c
index 0ab88483720c..92eda412fed3 100644
--- a/tools/perf/arch/sparc/util/dwarf-regs.c
+++ b/tools/perf/arch/sparc/util/dwarf-regs.c
@@ -9,7 +9,7 @@
  * 2 of the License, or (at your option) any later version.
  */
 
-#include <libio.h>
+#include <stddef.h>
 #include <dwarf-regs.h>
 
 #define SPARC_MAX_REGS	96
diff --git a/tools/perf/arch/x86/util/dwarf-regs.c b/tools/perf/arch/x86/util/dwarf-regs.c
index a794d3081928..be22dd463232 100644
--- a/tools/perf/arch/x86/util/dwarf-regs.c
+++ b/tools/perf/arch/x86/util/dwarf-regs.c
@@ -20,7 +20,7 @@
  *
  */
 
-#include <libio.h>
+#include <stddef.h>
 #include <dwarf-regs.h>
 
 /*
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 2e6961ea3184..ae36f3cb5410 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -109,14 +109,16 @@ static int process_sample_event(struct perf_tool *tool,
 	return 0;
 }
 
-static int hist_entry__tty_annotate(struct hist_entry *he, int evidx,
+static int hist_entry__tty_annotate(struct hist_entry *he,
+				    struct perf_evsel *evsel,
 				    struct perf_annotate *ann)
 {
-	return symbol__tty_annotate(he->ms.sym, he->ms.map, evidx,
+	return symbol__tty_annotate(he->ms.sym, he->ms.map, evsel,
 				    ann->print_line, ann->full_paths, 0, 0);
 }
 
-static void hists__find_annotations(struct hists *self, int evidx,
+static void hists__find_annotations(struct hists *self,
+				    struct perf_evsel *evsel,
 				    struct perf_annotate *ann)
 {
 	struct rb_node *nd = rb_first(&self->entries), *next;
@@ -142,14 +144,14 @@ find_next:
 		if (use_browser == 2) {
 			int ret;
 
-			ret = hist_entry__gtk_annotate(he, evidx, NULL);
+			ret = hist_entry__gtk_annotate(he, evsel, NULL);
 			if (!ret || !ann->skip_missing)
 				return;
 
 			/* skip missing symbols */
 			nd = rb_next(nd);
 		} else if (use_browser == 1) {
-			key = hist_entry__tui_annotate(he, evidx, NULL);
+			key = hist_entry__tui_annotate(he, evsel, NULL);
 			switch (key) {
 			case -1:
 				if (!ann->skip_missing)
@@ -168,7 +170,7 @@ find_next:
 			if (next != NULL)
 				nd = next;
 		} else {
-			hist_entry__tty_annotate(he, evidx, ann);
+			hist_entry__tty_annotate(he, evsel, ann);
 			nd = rb_next(nd);
 			/*
 			 * Since we have a hist_entry per IP for the same
@@ -230,7 +232,12 @@ static int __cmd_annotate(struct perf_annotate *ann)
 			total_nr_samples += nr_samples;
 			hists__collapse_resort(hists);
 			hists__output_resort(hists);
-			hists__find_annotations(hists, pos->idx, ann);
+
+			if (symbol_conf.event_group &&
+			    !perf_evsel__is_group_leader(pos))
+				continue;
+
+			hists__find_annotations(hists, pos, ann);
 		}
 	}
 
@@ -312,6 +319,8 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
 		   "Specify disassembler style (e.g. -M intel for intel syntax)"),
 	OPT_STRING(0, "objdump", &objdump_path, "path",
 		   "objdump binary to use for disassembly and annotations"),
+	OPT_BOOLEAN(0, "group", &symbol_conf.event_group,
+		    "Show event group information together"),
 	OPT_END()
 	};
 
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 37a769d7f9fe..533501e2b07c 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -12,7 +12,7 @@
 #include "util/parse-options.h"
 #include "util/trace-event.h"
 #include "util/debug.h"
-#include "util/debugfs.h"
+#include <lk/debugfs.h>
 #include "util/tool.h"
 #include "util/stat.h"
 
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index de38a034b129..e8a66f9a6715 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -37,7 +37,7 @@
 #include "util/strfilter.h"
 #include "util/symbol.h"
 #include "util/debug.h"
-#include "util/debugfs.h"
+#include <lk/debugfs.h>
 #include "util/parse-options.h"
 #include "util/probe-finder.h"
 #include "util/probe-event.h"
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index f1a939ebc19c..9f2344a2c506 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -474,7 +474,9 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
 	}
 
 	if (forks) {
-		err = perf_evlist__prepare_workload(evsel_list, opts, argv);
+		err = perf_evlist__prepare_workload(evsel_list, &opts->target,
+						    argv, opts->pipe_output,
+						    true);
 		if (err < 0) {
 			pr_err("Couldn't run the workload!\n");
 			goto out_delete_session;
@@ -964,7 +966,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 	struct perf_record *rec = &record;
 	char errbuf[BUFSIZ];
 
-	evsel_list = perf_evlist__new(NULL, NULL);
+	evsel_list = perf_evlist__new();
 	if (evsel_list == NULL)
 		return -ENOMEM;
 
@@ -1026,7 +1028,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 		ui__error("%s", errbuf);
 
 		err = -saved_errno;
-		goto out_free_fd;
+		goto out_symbol_exit;
 	}
 
 	err = -ENOMEM;
@@ -1057,6 +1059,9 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 	}
 
 	err = __cmd_record(&record, argc, argv);
+
+	perf_evlist__munmap(evsel_list);
+	perf_evlist__close(evsel_list);
 out_free_fd:
 	perf_evlist__delete_maps(evsel_list);
 out_symbol_exit:
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 96b5a7fee4bb..296bd219977a 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -13,7 +13,6 @@
 #include "util/annotate.h"
 #include "util/color.h"
 #include <linux/list.h>
-#include "util/cache.h"
 #include <linux/rbtree.h>
 #include "util/symbol.h"
 #include "util/callchain.h"
@@ -314,7 +313,7 @@ static size_t hists__fprintf_nr_sample_events(struct hists *self,
 	char buf[512];
 	size_t size = sizeof(buf);
 
-	if (symbol_conf.event_group && evsel->nr_members > 1) {
+	if (perf_evsel__is_group_event(evsel)) {
 		struct perf_evsel *pos;
 
 		perf_evsel__group_desc(evsel, buf, size);
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 99848761f573..ba0bdd87c279 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -94,6 +94,7 @@ static const char		*pre_cmd			= NULL;
 static const char		*post_cmd			= NULL;
 static bool			sync_run			= false;
 static unsigned int		interval			= 0;
+static bool			forever				= false;
 static struct timespec		ref_time;
 static struct cpu_map		*sock_map;
 
@@ -125,6 +126,11 @@ static inline int perf_evsel__nr_cpus(struct perf_evsel *evsel)
 	return perf_evsel__cpus(evsel)->nr;
 }
 
+static void perf_evsel__reset_stat_priv(struct perf_evsel *evsel)
+{
+	memset(evsel->priv, 0, sizeof(struct perf_stat));
+}
+
 static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
 {
 	evsel->priv = zalloc(sizeof(struct perf_stat));
@@ -160,6 +166,35 @@ static void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel)
 	evsel->prev_raw_counts = NULL;
 }
 
+static void perf_evlist__free_stats(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+
+	list_for_each_entry(evsel, &evlist->entries, node) {
+		perf_evsel__free_stat_priv(evsel);
+		perf_evsel__free_counts(evsel);
+		perf_evsel__free_prev_raw_counts(evsel);
+	}
+}
+
+static int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw)
+{
+	struct perf_evsel *evsel;
+
+	list_for_each_entry(evsel, &evlist->entries, node) {
+		if (perf_evsel__alloc_stat_priv(evsel) < 0 ||
+		    perf_evsel__alloc_counts(evsel, perf_evsel__nr_cpus(evsel)) < 0 ||
+		    (alloc_raw && perf_evsel__alloc_prev_raw_counts(evsel) < 0))
+			goto out_free;
+	}
+
+	return 0;
+
+out_free:
+	perf_evlist__free_stats(evlist);
+	return -1;
+}
+
 static struct stats runtime_nsecs_stats[MAX_NR_CPUS];
 static struct stats runtime_cycles_stats[MAX_NR_CPUS];
 static struct stats runtime_stalled_cycles_front_stats[MAX_NR_CPUS];
@@ -173,6 +208,29 @@ 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 void perf_stat__reset_stats(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+
+	list_for_each_entry(evsel, &evlist->entries, node) {
+		perf_evsel__reset_stat_priv(evsel);
+		perf_evsel__reset_counts(evsel, perf_evsel__nr_cpus(evsel));
+	}
+
+	memset(runtime_nsecs_stats, 0, sizeof(runtime_nsecs_stats));
+	memset(runtime_cycles_stats, 0, sizeof(runtime_cycles_stats));
+	memset(runtime_stalled_cycles_front_stats, 0, sizeof(runtime_stalled_cycles_front_stats));
+	memset(runtime_stalled_cycles_back_stats, 0, sizeof(runtime_stalled_cycles_back_stats));
+	memset(runtime_branches_stats, 0, sizeof(runtime_branches_stats));
+	memset(runtime_cacherefs_stats, 0, sizeof(runtime_cacherefs_stats));
+	memset(runtime_l1_dcache_stats, 0, sizeof(runtime_l1_dcache_stats));
+	memset(runtime_l1_icache_stats, 0, sizeof(runtime_l1_icache_stats));
+	memset(runtime_ll_cache_stats, 0, sizeof(runtime_ll_cache_stats));
+	memset(runtime_itlb_cache_stats, 0, sizeof(runtime_itlb_cache_stats));
+	memset(runtime_dtlb_cache_stats, 0, sizeof(runtime_dtlb_cache_stats));
+	memset(&walltime_nsecs_stats, 0, sizeof(walltime_nsecs_stats));
+}
+
 static int create_perf_stat_counter(struct perf_evsel *evsel)
 {
 	struct perf_event_attr *attr = &evsel->attr;
@@ -249,7 +307,7 @@ static int read_counter_aggr(struct perf_evsel *counter)
 	int i;
 
 	if (__perf_evsel__read(counter, perf_evsel__nr_cpus(counter),
-			       evsel_list->threads->nr, scale) < 0)
+			       thread_map__nr(evsel_list->threads), scale) < 0)
 		return -1;
 
 	for (i = 0; i < 3; i++)
@@ -337,16 +395,14 @@ static void print_interval(void)
 	}
 }
 
-static int __run_perf_stat(int argc __maybe_unused, const char **argv)
+static int __run_perf_stat(int argc, const char **argv)
 {
 	char msg[512];
 	unsigned long long t0, t1;
 	struct perf_evsel *counter;
 	struct timespec ts;
 	int status = 0;
-	int child_ready_pipe[2], go_pipe[2];
 	const bool forks = (argc > 0);
-	char buf;
 
 	if (interval) {
 		ts.tv_sec  = interval / 1000;
@@ -362,55 +418,12 @@ static int __run_perf_stat(int argc __maybe_unused, const char **argv)
 		return -1;
 	}
 
-	if (forks && (pipe(child_ready_pipe) < 0 || pipe(go_pipe) < 0)) {
-		perror("failed to create pipes");
-		return -1;
-	}
-
 	if (forks) {
-		if ((child_pid = fork()) < 0)
-			perror("failed to fork");
-
-		if (!child_pid) {
-			close(child_ready_pipe[0]);
-			close(go_pipe[1]);
-			fcntl(go_pipe[0], F_SETFD, FD_CLOEXEC);
-
-			/*
-			 * Do a dummy execvp to get the PLT entry resolved,
-			 * so we avoid the resolver overhead on the real
-			 * execvp call.
-			 */
-			execvp("", (char **)argv);
-
-			/*
-			 * Tell the parent we're ready to go
-			 */
-			close(child_ready_pipe[1]);
-
-			/*
-			 * Wait until the parent tells us to go.
-			 */
-			if (read(go_pipe[0], &buf, 1) == -1)
-				perror("unable to read pipe");
-
-			execvp(argv[0], (char **)argv);
-
-			perror(argv[0]);
-			exit(-1);
+		if (perf_evlist__prepare_workload(evsel_list, &target, argv,
+						  false, false) < 0) {
+			perror("failed to prepare workload");
+			return -1;
 		}
-
-		if (perf_target__none(&target))
-			evsel_list->threads->map[0] = child_pid;
-
-		/*
-		 * Wait for the child to be ready to exec.
-		 */
-		close(child_ready_pipe[1]);
-		close(go_pipe[0]);
-		if (read(child_ready_pipe[0], &buf, 1) == -1)
-			perror("unable to read pipe");
-		close(child_ready_pipe[0]);
 	}
 
 	if (group)
@@ -457,7 +470,8 @@ static int __run_perf_stat(int argc __maybe_unused, const char **argv)
 	clock_gettime(CLOCK_MONOTONIC, &ref_time);
 
 	if (forks) {
-		close(go_pipe[1]);
+		perf_evlist__start_workload(evsel_list);
+
 		if (interval) {
 			while (!waitpid(child_pid, &status, WNOHANG)) {
 				nanosleep(&ts, NULL);
@@ -488,7 +502,7 @@ static int __run_perf_stat(int argc __maybe_unused, const char **argv)
 		list_for_each_entry(counter, &evsel_list->entries, node) {
 			read_counter_aggr(counter);
 			perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter),
-					     evsel_list->threads->nr);
+					     thread_map__nr(evsel_list->threads));
 		}
 	}
 
@@ -1296,7 +1310,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose (show counter open errors, etc)"),
 	OPT_INTEGER('r', "repeat", &run_count,
-		    "repeat command and print average + stddev (max: 100)"),
+		    "repeat command and print average + stddev (max: 100, forever: 0)"),
 	OPT_BOOLEAN('n', "null", &null_run,
 		    "null run - dont start any counters"),
 	OPT_INCR('d', "detailed", &detailed_run,
@@ -1330,13 +1344,12 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 		"perf stat [<options>] [<command>]",
 		NULL
 	};
-	struct perf_evsel *pos;
 	int status = -ENOMEM, run_idx;
 	const char *mode;
 
 	setlocale(LC_ALL, "");
 
-	evsel_list = perf_evlist__new(NULL, NULL);
+	evsel_list = perf_evlist__new();
 	if (evsel_list == NULL)
 		return -ENOMEM;
 
@@ -1399,8 +1412,12 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	if (!argc && !perf_target__has_task(&target))
 		usage_with_options(stat_usage, options);
-	if (run_count <= 0)
+	if (run_count < 0) {
 		usage_with_options(stat_usage, options);
+	} else if (run_count == 0) {
+		forever = true;
+		run_count = 1;
+	}
 
 	/* no_aggr, cgroup are for system-wide only */
 	if ((no_aggr || nr_cgroups) && !perf_target__has_cpu(&target)) {
@@ -1438,17 +1455,8 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 		return -1;
 	}
 
-	list_for_each_entry(pos, &evsel_list->entries, node) {
-		if (perf_evsel__alloc_stat_priv(pos) < 0 ||
-		    perf_evsel__alloc_counts(pos, perf_evsel__nr_cpus(pos)) < 0)
-			goto out_free_fd;
-	}
-	if (interval) {
-		list_for_each_entry(pos, &evsel_list->entries, node) {
-			if (perf_evsel__alloc_prev_raw_counts(pos) < 0)
-				goto out_free_fd;
-		}
-	}
+	if (perf_evlist__alloc_stats(evsel_list, interval))
+		goto out_free_maps;
 
 	/*
 	 * We dont want to block the signals - that would cause
@@ -1457,28 +1465,30 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 	 * task, but being ignored by perf stat itself:
 	 */
 	atexit(sig_atexit);
-	signal(SIGINT,  skip_signal);
+	if (!forever)
+		signal(SIGINT,  skip_signal);
 	signal(SIGCHLD, skip_signal);
 	signal(SIGALRM, skip_signal);
 	signal(SIGABRT, skip_signal);
 
 	status = 0;
-	for (run_idx = 0; run_idx < run_count; run_idx++) {
+	for (run_idx = 0; forever || run_idx < run_count; run_idx++) {
 		if (run_count != 1 && verbose)
 			fprintf(output, "[ perf stat: executing run #%d ... ]\n",
 				run_idx + 1);
 
 		status = run_perf_stat(argc, argv);
+		if (forever && status != -1) {
+			print_stat(argc, argv);
+			perf_stat__reset_stats(evsel_list);
+		}
 	}
 
-	if (status != -1 && !interval)
+	if (!forever && status != -1 && !interval)
 		print_stat(argc, argv);
-out_free_fd:
-	list_for_each_entry(pos, &evsel_list->entries, node) {
-		perf_evsel__free_stat_priv(pos);
-		perf_evsel__free_counts(pos);
-		perf_evsel__free_prev_raw_counts(pos);
-	}
+
+	perf_evlist__free_stats(evsel_list);
+out_free_maps:
 	perf_evlist__delete_maps(evsel_list);
 out:
 	perf_evlist__delete(evsel_list);
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 72f6eb7b4173..b5520ad0dbb8 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -231,7 +231,7 @@ static void perf_top__show_details(struct perf_top *top)
 	printf("Showing %s for %s\n", perf_evsel__name(top->sym_evsel), symbol->name);
 	printf("  Events  Pcnt (>=%d%%)\n", top->sym_pcnt_filter);
 
-	more = symbol__annotate_printf(symbol, he->ms.map, top->sym_evsel->idx,
+	more = symbol__annotate_printf(symbol, he->ms.map, top->sym_evsel,
 				       0, top->sym_pcnt_filter, top->print_entries, 4);
 	if (top->zero)
 		symbol__annotate_zero_histogram(symbol, top->sym_evsel->idx);
@@ -1116,7 +1116,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 		NULL
 	};
 
-	top.evlist = perf_evlist__new(NULL, NULL);
+	top.evlist = perf_evlist__new();
 	if (top.evlist == NULL)
 		return -ENOMEM;
 
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index d222d7fc7e96..ab3ed4af1466 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -419,7 +419,7 @@ out_dump:
 
 static int trace__run(struct trace *trace, int argc, const char **argv)
 {
-	struct perf_evlist *evlist = perf_evlist__new(NULL, NULL);
+	struct perf_evlist *evlist = perf_evlist__new();
 	struct perf_evsel *evsel;
 	int err = -1, i;
 	unsigned long before;
@@ -452,7 +452,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 	err = trace__symbols_init(trace, evlist);
 	if (err < 0) {
 		printf("Problems initializing symbol libraries!\n");
-		goto out_delete_evlist;
+		goto out_delete_maps;
 	}
 
 	perf_evlist__config(evlist, &trace->opts);
@@ -461,23 +461,24 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 	signal(SIGINT, sig_handler);
 
 	if (forks) {
-		err = perf_evlist__prepare_workload(evlist, &trace->opts, argv);
+		err = perf_evlist__prepare_workload(evlist, &trace->opts.target,
+						    argv, false, false);
 		if (err < 0) {
 			printf("Couldn't run the workload!\n");
-			goto out_delete_evlist;
+			goto out_delete_maps;
 		}
 	}
 
 	err = perf_evlist__open(evlist);
 	if (err < 0) {
 		printf("Couldn't create the events: %s\n", strerror(errno));
-		goto out_delete_evlist;
+		goto out_delete_maps;
 	}
 
 	err = perf_evlist__mmap(evlist, UINT_MAX, false);
 	if (err < 0) {
 		printf("Couldn't mmap the events: %s\n", strerror(errno));
-		goto out_delete_evlist;
+		goto out_close_evlist;
 	}
 
 	perf_evlist__enable(evlist);
@@ -526,13 +527,6 @@ again:
 				continue;
 			}
 
-			if (sample.raw_data == NULL) {
-				printf("%s sample with no payload for tid: %d, cpu %d, raw_size=%d, skipping...\n",
-				       perf_evsel__name(evsel), sample.tid,
-				       sample.cpu, sample.raw_size);
-				continue;
-			}
-
 			handler = evsel->handler.func;
 			handler(trace, evsel, &sample);
 		}
@@ -540,7 +534,7 @@ again:
 
 	if (trace->nr_events == before) {
 		if (done)
-			goto out_delete_evlist;
+			goto out_unmap_evlist;
 
 		poll(evlist->pollfd, evlist->nr_fds, -1);
 	}
@@ -550,6 +544,12 @@ again:
 
 	goto again;
 
+out_unmap_evlist:
+	perf_evlist__munmap(evlist);
+out_close_evlist:
+	perf_evlist__close(evlist);
+out_delete_maps:
+	perf_evlist__delete_maps(evlist);
 out_delete_evlist:
 	perf_evlist__delete(evlist);
 out:
diff --git a/tools/perf/command-list.txt b/tools/perf/command-list.txt
index 3e86bbd8c2d5..a28e31be6cb4 100644
--- a/tools/perf/command-list.txt
+++ b/tools/perf/command-list.txt
@@ -10,17 +10,17 @@ perf-buildid-list		mainporcelain common
 perf-diff			mainporcelain common
 perf-evlist			mainporcelain common
 perf-inject			mainporcelain common
+perf-kmem			mainporcelain common
+perf-kvm			mainporcelain common
 perf-list			mainporcelain common
-perf-sched			mainporcelain common
+perf-lock			mainporcelain common
+perf-probe			mainporcelain full
 perf-record			mainporcelain common
 perf-report			mainporcelain common
+perf-sched			mainporcelain common
+perf-script			mainporcelain common
 perf-stat			mainporcelain common
+perf-test			mainporcelain common
 perf-timechart			mainporcelain common
 perf-top			mainporcelain common
 perf-trace			mainporcelain common
-perf-script			mainporcelain common
-perf-probe			mainporcelain full
-perf-kmem			mainporcelain common
-perf-lock			mainporcelain common
-perf-kvm			mainporcelain common
-perf-test			mainporcelain common
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 095b88207cd3..f6ba7b73f40e 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -13,7 +13,7 @@
 #include "util/quote.h"
 #include "util/run-command.h"
 #include "util/parse-events.h"
-#include "util/debugfs.h"
+#include <lk/debugfs.h>
 #include <pthread.h>
 
 const char perf_usage_string[] =
@@ -193,13 +193,13 @@ static int handle_options(const char ***argv, int *argc, int *envchanged)
 				fprintf(stderr, "No directory given for --debugfs-dir.\n");
 				usage(perf_usage_string);
 			}
-			debugfs_set_path((*argv)[1]);
+			perf_debugfs_set_path((*argv)[1]);
 			if (envchanged)
 				*envchanged = 1;
 			(*argv)++;
 			(*argc)--;
 		} else if (!prefixcmp(cmd, CMD_DEBUGFS_DIR)) {
-			debugfs_set_path(cmd + strlen(CMD_DEBUGFS_DIR));
+			perf_debugfs_set_path(cmd + strlen(CMD_DEBUGFS_DIR));
 			fprintf(stderr, "dir: %s\n", debugfs_mountpoint);
 			if (envchanged)
 				*envchanged = 1;
@@ -461,7 +461,7 @@ int main(int argc, const char **argv)
 	if (!cmd)
 		cmd = "perf-help";
 	/* get debugfs mount point from /proc/mounts */
-	debugfs_mount(NULL);
+	perf_debugfs_mount(NULL);
 	/*
 	 * "perf-xxxx" is the same as "perf xxxx", but we obviously:
 	 *
diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c
index bdcceb886f77..038de3ecb8cb 100644
--- a/tools/perf/tests/attr.c
+++ b/tools/perf/tests/attr.c
@@ -147,10 +147,15 @@ void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu,
 
 static int run_dir(const char *d, const char *perf)
 {
+	char v[] = "-vvvvv";
+	int vcnt = min(verbose, (int) sizeof(v) - 1);
 	char cmd[3*PATH_MAX];
 
-	snprintf(cmd, 3*PATH_MAX, PYTHON " %s/attr.py -d %s/attr/ -p %s %s",
-		 d, d, perf, verbose ? "-v" : "");
+	if (verbose)
+		vcnt++;
+
+	snprintf(cmd, 3*PATH_MAX, PYTHON " %s/attr.py -d %s/attr/ -p %s %.*s",
+		 d, d, perf, vcnt, v);
 
 	return system(cmd);
 }
diff --git a/tools/perf/tests/attr.py b/tools/perf/tests/attr.py
index 2f629ca485bc..c9b4b6269b51 100644
--- a/tools/perf/tests/attr.py
+++ b/tools/perf/tests/attr.py
@@ -24,6 +24,7 @@ class Unsup(Exception):
 
 class Event(dict):
     terms = [
+        'cpu',
         'flags',
         'type',
         'size',
@@ -121,7 +122,7 @@ class Test(object):
         parser = ConfigParser.SafeConfigParser()
         parser.read(path)
 
-        log.debug("running '%s'" % path)
+        log.warning("running '%s'" % path)
 
         self.path     = path
         self.test_dir = options.test_dir
@@ -172,7 +173,7 @@ class Test(object):
               self.perf, self.command, tempdir, self.args)
         ret = os.WEXITSTATUS(os.system(cmd))
 
-        log.warning("  running '%s' ret %d " % (cmd, ret))
+        log.info("  '%s' ret %d " % (cmd, ret))
 
         if ret != int(self.ret):
             raise Unsup(self)
diff --git a/tools/perf/tests/attr/base-record b/tools/perf/tests/attr/base-record
index 5bc3880f7be5..b4fc835de607 100644
--- a/tools/perf/tests/attr/base-record
+++ b/tools/perf/tests/attr/base-record
@@ -2,6 +2,7 @@
 fd=1
 group_fd=-1
 flags=0
+cpu=*
 type=0|1
 size=96
 config=0
diff --git a/tools/perf/tests/attr/base-stat b/tools/perf/tests/attr/base-stat
index 4bd79a82784f..748ee949a204 100644
--- a/tools/perf/tests/attr/base-stat
+++ b/tools/perf/tests/attr/base-stat
@@ -2,6 +2,7 @@
 fd=1
 group_fd=-1
 flags=0
+cpu=*
 type=0
 size=96
 config=0
diff --git a/tools/perf/tests/attr/test-record-C0 b/tools/perf/tests/attr/test-record-C0
new file mode 100644
index 000000000000..d6a7e43f61b3
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-C0
@@ -0,0 +1,13 @@
+[config]
+command = record
+args    = -C 0 kill >/dev/null 2>&1
+
+[event:base-record]
+cpu=0
+
+# no enable on exec for CPU attached
+enable_on_exec=0
+
+# PERF_SAMPLE_IP | PERF_SAMPLE_TID PERF_SAMPLE_TIME | # PERF_SAMPLE_PERIOD
+# + PERF_SAMPLE_CPU added by -C 0
+sample_type=391
diff --git a/tools/perf/tests/attr/test-stat-C0 b/tools/perf/tests/attr/test-stat-C0
new file mode 100644
index 000000000000..aa835950751f
--- /dev/null
+++ b/tools/perf/tests/attr/test-stat-C0
@@ -0,0 +1,9 @@
+[config]
+command = stat
+args    = -e cycles -C 0 kill >/dev/null 2>&1
+ret     = 1
+
+[event:base-stat]
+# events are enabled by default when attached to cpu
+disabled=0
+enable_on_exec=0
diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c
new file mode 100644
index 000000000000..68daa289e94c
--- /dev/null
+++ b/tools/perf/tests/bp_signal.c
@@ -0,0 +1,186 @@
+/*
+ * Inspired by breakpoint overflow test done by
+ * Vince Weaver <vincent.weaver@maine.edu> for perf_event_tests
+ * (git://github.com/deater/perf_event_tests)
+ */
+
+#include <stdlib.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <time.h>
+#include <fcntl.h>
+#include <signal.h>
+#include <sys/mman.h>
+#include <linux/compiler.h>
+#include <linux/hw_breakpoint.h>
+
+#include "tests.h"
+#include "debug.h"
+#include "perf.h"
+
+static int fd1;
+static int fd2;
+static int overflows;
+
+__attribute__ ((noinline))
+static int test_function(void)
+{
+	return time(NULL);
+}
+
+static void sig_handler(int signum __maybe_unused,
+			siginfo_t *oh __maybe_unused,
+			void *uc __maybe_unused)
+{
+	overflows++;
+
+	if (overflows > 10) {
+		/*
+		 * This should be executed only once during
+		 * this test, if we are here for the 10th
+		 * time, consider this the recursive issue.
+		 *
+		 * We can get out of here by disable events,
+		 * so no new SIGIO is delivered.
+		 */
+		ioctl(fd1, PERF_EVENT_IOC_DISABLE, 0);
+		ioctl(fd2, PERF_EVENT_IOC_DISABLE, 0);
+	}
+}
+
+static int bp_event(void *fn, int setup_signal)
+{
+	struct perf_event_attr pe;
+	int fd;
+
+	memset(&pe, 0, sizeof(struct perf_event_attr));
+	pe.type = PERF_TYPE_BREAKPOINT;
+	pe.size = sizeof(struct perf_event_attr);
+
+	pe.config = 0;
+	pe.bp_type = HW_BREAKPOINT_X;
+	pe.bp_addr = (unsigned long) fn;
+	pe.bp_len = sizeof(long);
+
+	pe.sample_period = 1;
+	pe.sample_type = PERF_SAMPLE_IP;
+	pe.wakeup_events = 1;
+
+	pe.disabled = 1;
+	pe.exclude_kernel = 1;
+	pe.exclude_hv = 1;
+
+	fd = sys_perf_event_open(&pe, 0, -1, -1, 0);
+	if (fd < 0) {
+		pr_debug("failed opening event %llx\n", pe.config);
+		return TEST_FAIL;
+	}
+
+	if (setup_signal) {
+		fcntl(fd, F_SETFL, O_RDWR|O_NONBLOCK|O_ASYNC);
+		fcntl(fd, F_SETSIG, SIGIO);
+		fcntl(fd, F_SETOWN, getpid());
+	}
+
+	ioctl(fd, PERF_EVENT_IOC_RESET, 0);
+
+	return fd;
+}
+
+static long long bp_count(int fd)
+{
+	long long count;
+	int ret;
+
+	ret = read(fd, &count, sizeof(long long));
+	if (ret != sizeof(long long)) {
+		pr_debug("failed to read: %d\n", ret);
+		return TEST_FAIL;
+	}
+
+	return count;
+}
+
+int test__bp_signal(void)
+{
+	struct sigaction sa;
+	long long count1, count2;
+
+	/* setup SIGIO signal handler */
+	memset(&sa, 0, sizeof(struct sigaction));
+	sa.sa_sigaction = (void *) sig_handler;
+	sa.sa_flags = SA_SIGINFO;
+
+	if (sigaction(SIGIO, &sa, NULL) < 0) {
+		pr_debug("failed setting up signal handler\n");
+		return TEST_FAIL;
+	}
+
+	/*
+	 * We create following events:
+	 *
+	 * fd1 - breakpoint event on test_function with SIGIO
+	 *       signal configured. We should get signal
+	 *       notification each time the breakpoint is hit
+	 *
+	 * fd2 - breakpoint event on sig_handler without SIGIO
+	 *       configured.
+	 *
+	 * Following processing should happen:
+	 *   - execute test_function
+	 *   - fd1 event breakpoint hit -> count1 == 1
+	 *   - SIGIO is delivered       -> overflows == 1
+	 *   - fd2 event breakpoint hit -> count2 == 1
+	 *
+	 * The test case check following error conditions:
+	 * - we get stuck in signal handler because of debug
+	 *   exception being triggered receursively due to
+	 *   the wrong RF EFLAG management
+	 *
+	 * - we never trigger the sig_handler breakpoint due
+	 *   to the rong RF EFLAG management
+	 *
+	 */
+
+	fd1 = bp_event(test_function, 1);
+	fd2 = bp_event(sig_handler, 0);
+
+	ioctl(fd1, PERF_EVENT_IOC_ENABLE, 0);
+	ioctl(fd2, PERF_EVENT_IOC_ENABLE, 0);
+
+	/*
+	 * Kick off the test by trigering 'fd1'
+	 * breakpoint.
+	 */
+	test_function();
+
+	ioctl(fd1, PERF_EVENT_IOC_DISABLE, 0);
+	ioctl(fd2, PERF_EVENT_IOC_DISABLE, 0);
+
+	count1 = bp_count(fd1);
+	count2 = bp_count(fd2);
+
+	close(fd1);
+	close(fd2);
+
+	pr_debug("count1 %lld, count2 %lld, overflow %d\n",
+		 count1, count2, overflows);
+
+	if (count1 != 1) {
+		if (count1 == 11)
+			pr_debug("failed: RF EFLAG recursion issue detected\n");
+		else
+			pr_debug("failed: wrong count for bp1%lld\n", count1);
+	}
+
+	if (overflows != 1)
+		pr_debug("failed: wrong overflow hit\n");
+
+	if (count2 != 1)
+		pr_debug("failed: wrong count for bp2\n");
+
+	return count1 == 1 && overflows == 1 && count2 == 1 ?
+		TEST_OK : TEST_FAIL;
+}
diff --git a/tools/perf/tests/bp_signal_overflow.c b/tools/perf/tests/bp_signal_overflow.c
new file mode 100644
index 000000000000..fe7ed28815f8
--- /dev/null
+++ b/tools/perf/tests/bp_signal_overflow.c
@@ -0,0 +1,126 @@
+/*
+ * Originally done by Vince Weaver <vincent.weaver@maine.edu> for
+ * perf_event_tests (git://github.com/deater/perf_event_tests)
+ */
+
+#include <stdlib.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <time.h>
+#include <fcntl.h>
+#include <signal.h>
+#include <sys/mman.h>
+#include <linux/compiler.h>
+#include <linux/hw_breakpoint.h>
+
+#include "tests.h"
+#include "debug.h"
+#include "perf.h"
+
+static int overflows;
+
+__attribute__ ((noinline))
+static int test_function(void)
+{
+	return time(NULL);
+}
+
+static void sig_handler(int signum __maybe_unused,
+			siginfo_t *oh __maybe_unused,
+			void *uc __maybe_unused)
+{
+	overflows++;
+}
+
+static long long bp_count(int fd)
+{
+	long long count;
+	int ret;
+
+	ret = read(fd, &count, sizeof(long long));
+	if (ret != sizeof(long long)) {
+		pr_debug("failed to read: %d\n", ret);
+		return TEST_FAIL;
+	}
+
+	return count;
+}
+
+#define EXECUTIONS 10000
+#define THRESHOLD  100
+
+int test__bp_signal_overflow(void)
+{
+	struct perf_event_attr pe;
+	struct sigaction sa;
+	long long count;
+	int fd, i, fails = 0;
+
+	/* setup SIGIO signal handler */
+	memset(&sa, 0, sizeof(struct sigaction));
+	sa.sa_sigaction = (void *) sig_handler;
+	sa.sa_flags = SA_SIGINFO;
+
+	if (sigaction(SIGIO, &sa, NULL) < 0) {
+		pr_debug("failed setting up signal handler\n");
+		return TEST_FAIL;
+	}
+
+	memset(&pe, 0, sizeof(struct perf_event_attr));
+	pe.type = PERF_TYPE_BREAKPOINT;
+	pe.size = sizeof(struct perf_event_attr);
+
+	pe.config = 0;
+	pe.bp_type = HW_BREAKPOINT_X;
+	pe.bp_addr = (unsigned long) test_function;
+	pe.bp_len = sizeof(long);
+
+	pe.sample_period = THRESHOLD;
+	pe.sample_type = PERF_SAMPLE_IP;
+	pe.wakeup_events = 1;
+
+	pe.disabled = 1;
+	pe.exclude_kernel = 1;
+	pe.exclude_hv = 1;
+
+	fd = sys_perf_event_open(&pe, 0, -1, -1, 0);
+	if (fd < 0) {
+		pr_debug("failed opening event %llx\n", pe.config);
+		return TEST_FAIL;
+	}
+
+	fcntl(fd, F_SETFL, O_RDWR|O_NONBLOCK|O_ASYNC);
+	fcntl(fd, F_SETSIG, SIGIO);
+	fcntl(fd, F_SETOWN, getpid());
+
+	ioctl(fd, PERF_EVENT_IOC_RESET, 0);
+	ioctl(fd, PERF_EVENT_IOC_ENABLE, 0);
+
+	for (i = 0; i < EXECUTIONS; i++)
+		test_function();
+
+	ioctl(fd, PERF_EVENT_IOC_DISABLE, 0);
+
+	count = bp_count(fd);
+
+	close(fd);
+
+	pr_debug("count %lld, overflow %d\n",
+		 count, overflows);
+
+	if (count != EXECUTIONS) {
+		pr_debug("\tWrong number of executions %lld != %d\n",
+		count, EXECUTIONS);
+		fails++;
+	}
+
+	if (overflows != EXECUTIONS / THRESHOLD) {
+		pr_debug("\tWrong number of overflows %d != %d\n",
+		overflows, EXECUTIONS / THRESHOLD);
+		fails++;
+	}
+
+	return fails ? TEST_FAIL : TEST_OK;
+}
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index acb98e0e39f2..0918ada4cc41 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -78,6 +78,22 @@ static struct test {
 		.func = test__python_use,
 	},
 	{
+		.desc = "Test breakpoint overflow signal handler",
+		.func = test__bp_signal,
+	},
+	{
+		.desc = "Test breakpoint overflow sampling",
+		.func = test__bp_signal_overflow,
+	},
+	{
+		.desc = "Test number of exit event of a simple workload",
+		.func = test__task_exit,
+	},
+	{
+		.desc = "Test software clock events have valid period values",
+		.func = test__sw_clock_freq,
+	},
+	{
 		.func = NULL,
 	},
 };
diff --git a/tools/perf/tests/evsel-roundtrip-name.c b/tools/perf/tests/evsel-roundtrip-name.c
index 0fd99a9adb91..0197bda9c461 100644
--- a/tools/perf/tests/evsel-roundtrip-name.c
+++ b/tools/perf/tests/evsel-roundtrip-name.c
@@ -8,7 +8,7 @@ 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);
+	struct perf_evlist *evlist = perf_evlist__new();
 
         if (evlist == NULL)
                 return -ENOMEM;
@@ -64,7 +64,7 @@ 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);
+	struct perf_evlist *evlist = perf_evlist__new();
 
         if (evlist == NULL)
                 return -ENOMEM;
diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c
index 1be64a6c5daf..e0c0267858a1 100644
--- a/tools/perf/tests/hists_link.c
+++ b/tools/perf/tests/hists_link.c
@@ -436,7 +436,7 @@ int test__hists_link(void)
 	struct machines machines;
 	struct machine *machine = NULL;
 	struct perf_evsel *evsel, *first;
-        struct perf_evlist *evlist = perf_evlist__new(NULL, NULL);
+	struct perf_evlist *evlist = perf_evlist__new();
 
 	if (evlist == NULL)
                 return -ENOMEM;
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index cdd50755af51..5b1b5aba722b 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -53,12 +53,14 @@ int test__basic_mmap(void)
 		goto out_free_cpus;
 	}
 
-	evlist = perf_evlist__new(cpus, threads);
+	evlist = perf_evlist__new();
 	if (evlist == NULL) {
 		pr_debug("perf_evlist__new\n");
 		goto out_free_cpus;
 	}
 
+	perf_evlist__set_maps(evlist, cpus, threads);
+
 	for (i = 0; i < nsyscalls; ++i) {
 		char name[64];
 
diff --git a/tools/perf/tests/open-syscall-tp-fields.c b/tools/perf/tests/open-syscall-tp-fields.c
index 1c52fdc1164e..fc5b9fca8b47 100644
--- a/tools/perf/tests/open-syscall-tp-fields.c
+++ b/tools/perf/tests/open-syscall-tp-fields.c
@@ -18,7 +18,7 @@ int test__syscall_open_tp_fields(void)
 	};
 	const char *filename = "/etc/passwd";
 	int flags = O_RDONLY | O_DIRECTORY;
-	struct perf_evlist *evlist = perf_evlist__new(NULL, NULL);
+	struct perf_evlist *evlist = perf_evlist__new();
 	struct perf_evsel *evsel;
 	int err = -1, i, nr_events = 0, nr_polls = 0;
 
@@ -48,13 +48,13 @@ int test__syscall_open_tp_fields(void)
 	err = perf_evlist__open(evlist);
 	if (err < 0) {
 		pr_debug("perf_evlist__open: %s\n", strerror(errno));
-		goto out_delete_evlist;
+		goto out_delete_maps;
 	}
 
 	err = perf_evlist__mmap(evlist, UINT_MAX, false);
 	if (err < 0) {
 		pr_debug("perf_evlist__mmap: %s\n", strerror(errno));
-		goto out_delete_evlist;
+		goto out_close_evlist;
 	}
 
 	perf_evlist__enable(evlist);
@@ -110,6 +110,10 @@ out_ok:
 	err = 0;
 out_munmap:
 	perf_evlist__munmap(evlist);
+out_close_evlist:
+	perf_evlist__close(evlist);
+out_delete_maps:
+	perf_evlist__delete_maps(evlist);
 out_delete_evlist:
 	perf_evlist__delete(evlist);
 out:
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index c5636f36fe31..88e2f44cb157 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -3,7 +3,7 @@
 #include "evsel.h"
 #include "evlist.h"
 #include "sysfs.h"
-#include "debugfs.h"
+#include <lk/debugfs.h>
 #include "tests.h"
 #include <linux/hw_breakpoint.h>
 
@@ -1218,7 +1218,7 @@ static int test_event(struct evlist_test *e)
 	struct perf_evlist *evlist;
 	int ret;
 
-	evlist = perf_evlist__new(NULL, NULL);
+	evlist = perf_evlist__new();
 	if (evlist == NULL)
 		return -ENOMEM;
 
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index 1e8e5128d0da..72d8881873b0 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -45,7 +45,7 @@ int test__PERF_RECORD(void)
 	};
 	cpu_set_t cpu_mask;
 	size_t cpu_mask_size = sizeof(cpu_mask);
-	struct perf_evlist *evlist = perf_evlist__new(NULL, NULL);
+	struct perf_evlist *evlist = perf_evlist__new();
 	struct perf_evsel *evsel;
 	struct perf_sample sample;
 	const char *cmd = "sleep";
@@ -93,7 +93,8 @@ int test__PERF_RECORD(void)
 	 * 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);
+	err = perf_evlist__prepare_workload(evlist, &opts.target, argv,
+					    false, false);
 	if (err < 0) {
 		pr_debug("Couldn't run the workload!\n");
 		goto out_delete_maps;
@@ -142,7 +143,7 @@ int test__PERF_RECORD(void)
 	err = perf_evlist__mmap(evlist, opts.mmap_pages, false);
 	if (err < 0) {
 		pr_debug("perf_evlist__mmap: %s\n", strerror(errno));
-		goto out_delete_maps;
+		goto out_close_evlist;
 	}
 
 	/*
@@ -305,6 +306,8 @@ found_exit:
 	}
 out_err:
 	perf_evlist__munmap(evlist);
+out_close_evlist:
+	perf_evlist__close(evlist);
 out_delete_maps:
 	perf_evlist__delete_maps(evlist);
 out_delete_evlist:
diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
new file mode 100644
index 000000000000..2e41e2d32ccc
--- /dev/null
+++ b/tools/perf/tests/sw-clock.c
@@ -0,0 +1,119 @@
+#include <unistd.h>
+#include <stdlib.h>
+#include <signal.h>
+#include <sys/mman.h>
+
+#include "tests.h"
+#include "util/evsel.h"
+#include "util/evlist.h"
+#include "util/cpumap.h"
+#include "util/thread_map.h"
+
+#define NR_LOOPS  1000000
+
+/*
+ * This test will open software clock events (cpu-clock, task-clock)
+ * then check their frequency -> period conversion has no artifact of
+ * setting period to 1 forcefully.
+ */
+static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
+{
+	int i, err = -1;
+	volatile int tmp = 0;
+	u64 total_periods = 0;
+	int nr_samples = 0;
+	union perf_event *event;
+	struct perf_evsel *evsel;
+	struct perf_evlist *evlist;
+	struct perf_event_attr attr = {
+		.type = PERF_TYPE_SOFTWARE,
+		.config = clock_id,
+		.sample_type = PERF_SAMPLE_PERIOD,
+		.exclude_kernel = 1,
+		.disabled = 1,
+		.freq = 1,
+	};
+
+	attr.sample_freq = 10000;
+
+	evlist = perf_evlist__new();
+	if (evlist == NULL) {
+		pr_debug("perf_evlist__new\n");
+		return -1;
+	}
+
+	evsel = perf_evsel__new(&attr, 0);
+	if (evsel == NULL) {
+		pr_debug("perf_evsel__new\n");
+		goto out_free_evlist;
+	}
+	perf_evlist__add(evlist, evsel);
+
+	evlist->cpus = cpu_map__dummy_new();
+	evlist->threads = thread_map__new_by_tid(getpid());
+	if (!evlist->cpus || !evlist->threads) {
+		err = -ENOMEM;
+		pr_debug("Not enough memory to create thread/cpu maps\n");
+		goto out_delete_maps;
+	}
+
+	perf_evlist__open(evlist);
+
+	err = perf_evlist__mmap(evlist, 128, true);
+	if (err < 0) {
+		pr_debug("failed to mmap event: %d (%s)\n", errno,
+			 strerror(errno));
+		goto out_close_evlist;
+	}
+
+	perf_evlist__enable(evlist);
+
+	/* collect samples */
+	for (i = 0; i < NR_LOOPS; i++)
+		tmp++;
+
+	perf_evlist__disable(evlist);
+
+	while ((event = perf_evlist__mmap_read(evlist, 0)) != NULL) {
+		struct perf_sample sample;
+
+		if (event->header.type != PERF_RECORD_SAMPLE)
+			continue;
+
+		err = perf_evlist__parse_sample(evlist, event, &sample);
+		if (err < 0) {
+			pr_debug("Error during parse sample\n");
+			goto out_unmap_evlist;
+		}
+
+		total_periods += sample.period;
+		nr_samples++;
+	}
+
+	if ((u64) nr_samples == total_periods) {
+		pr_debug("All (%d) samples have period value of 1!\n",
+			 nr_samples);
+		err = -1;
+	}
+
+out_unmap_evlist:
+	perf_evlist__munmap(evlist);
+out_close_evlist:
+	perf_evlist__close(evlist);
+out_delete_maps:
+	perf_evlist__delete_maps(evlist);
+out_free_evlist:
+	perf_evlist__delete(evlist);
+	return err;
+}
+
+int test__sw_clock_freq(void)
+{
+	int ret;
+
+	ret = __test__sw_clock_freq(PERF_COUNT_SW_CPU_CLOCK);
+	if (!ret)
+		ret = __test__sw_clock_freq(PERF_COUNT_SW_TASK_CLOCK);
+
+	return ret;
+}
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
new file mode 100644
index 000000000000..28fe5894b061
--- /dev/null
+++ b/tools/perf/tests/task-exit.c
@@ -0,0 +1,123 @@
+#include "evlist.h"
+#include "evsel.h"
+#include "thread_map.h"
+#include "cpumap.h"
+#include "tests.h"
+
+#include <signal.h>
+
+static int exited;
+static int nr_exit;
+
+static void sig_handler(int sig)
+{
+	exited = 1;
+
+	if (sig == SIGUSR1)
+		nr_exit = -1;
+}
+
+/*
+ * This test will start a workload that does nothing then it checks
+ * if the number of exit event reported by the kernel is 1 or not
+ * in order to check the kernel returns correct number of event.
+ */
+int test__task_exit(void)
+{
+	int err = -1;
+	union perf_event *event;
+	struct perf_evsel *evsel;
+	struct perf_evlist *evlist;
+	struct perf_target target = {
+		.uid		= UINT_MAX,
+		.uses_mmap	= true,
+	};
+	const char *argv[] = { "true", NULL };
+
+	signal(SIGCHLD, sig_handler);
+	signal(SIGUSR1, sig_handler);
+
+	evlist = perf_evlist__new();
+	if (evlist == NULL) {
+		pr_debug("perf_evlist__new\n");
+		return -1;
+	}
+	/*
+	 * 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_free_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.
+	 */
+	evlist->cpus = cpu_map__dummy_new();
+	evlist->threads = thread_map__new_by_tid(-1);
+	if (!evlist->cpus || !evlist->threads) {
+		err = -ENOMEM;
+		pr_debug("Not enough memory to create thread/cpu maps\n");
+		goto out_delete_maps;
+	}
+
+	err = perf_evlist__prepare_workload(evlist, &target, argv, false, true);
+	if (err < 0) {
+		pr_debug("Couldn't run the workload!\n");
+		goto out_delete_maps;
+	}
+
+	evsel = perf_evlist__first(evlist);
+	evsel->attr.task = 1;
+	evsel->attr.sample_freq = 0;
+	evsel->attr.inherit = 0;
+	evsel->attr.watermark = 0;
+	evsel->attr.wakeup_events = 1;
+	evsel->attr.exclude_kernel = 1;
+
+	err = perf_evlist__open(evlist);
+	if (err < 0) {
+		pr_debug("Couldn't open the evlist: %s\n", strerror(-err));
+		goto out_delete_maps;
+	}
+
+	if (perf_evlist__mmap(evlist, 128, true) < 0) {
+		pr_debug("failed to mmap events: %d (%s)\n", errno,
+			 strerror(errno));
+		goto out_close_evlist;
+	}
+
+	perf_evlist__start_workload(evlist);
+
+retry:
+	while ((event = perf_evlist__mmap_read(evlist, 0)) != NULL) {
+		if (event->header.type != PERF_RECORD_EXIT)
+			continue;
+
+		nr_exit++;
+	}
+
+	if (!exited || !nr_exit) {
+		poll(evlist->pollfd, evlist->nr_fds, -1);
+		goto retry;
+	}
+
+	if (nr_exit != 1) {
+		pr_debug("received %d EXIT records\n", nr_exit);
+		err = -1;
+	}
+
+	perf_evlist__munmap(evlist);
+out_close_evlist:
+	perf_evlist__close(evlist);
+out_delete_maps:
+	perf_evlist__delete_maps(evlist);
+out_free_evlist:
+	perf_evlist__delete(evlist);
+	return err;
+}
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index 5de0be1ff4b6..dd7feae2d37b 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -23,5 +23,9 @@ int test__dso_data(void);
 int test__parse_events(void);
 int test__hists_link(void);
 int test__python_use(void);
+int test__bp_signal(void);
+int test__bp_signal_overflow(void);
+int test__task_exit(void);
+int test__sw_clock_freq(void);
 
 #endif /* TESTS_H */
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index 7dca1555c610..f56247a03a22 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -8,15 +8,20 @@
 #include "../../util/hist.h"
 #include "../../util/sort.h"
 #include "../../util/symbol.h"
+#include "../../util/evsel.h"
 #include <pthread.h>
 #include <newt.h>
 
 struct browser_disasm_line {
 	struct rb_node	rb_node;
-	double		percent;
 	u32		idx;
 	int		idx_asm;
 	int		jump_sources;
+	/*
+	 * actual length of this array is saved on the nr_events field
+	 * of the struct annotate_browser
+	 */
+	double		percent[1];
 };
 
 static struct annotate_browser_opt {
@@ -33,8 +38,9 @@ struct annotate_browser {
 	struct ui_browser b;
 	struct rb_root	  entries;
 	struct rb_node	  *curr_hot;
-	struct disasm_line	  *selection;
+	struct disasm_line  *selection;
 	struct disasm_line  **offsets;
+	int		    nr_events;
 	u64		    start;
 	int		    nr_asm_entries;
 	int		    nr_entries;
@@ -94,14 +100,24 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int
 			     (!current_entry || (browser->use_navkeypressed &&
 					         !browser->navkeypressed)));
 	int width = browser->width, printed;
+	int i, pcnt_width = 7 * ab->nr_events;
+	double percent_max = 0.0;
 	char bf[256];
 
-	if (dl->offset != -1 && bdl->percent != 0.0) {
-		ui_browser__set_percent_color(browser, bdl->percent, current_entry);
-		slsmg_printf("%6.2f ", bdl->percent);
+	for (i = 0; i < ab->nr_events; i++) {
+		if (bdl->percent[i] > percent_max)
+			percent_max = bdl->percent[i];
+	}
+
+	if (dl->offset != -1 && percent_max != 0.0) {
+		for (i = 0; i < ab->nr_events; i++) {
+			ui_browser__set_percent_color(browser, bdl->percent[i],
+						      current_entry);
+			slsmg_printf("%6.2f ", bdl->percent[i]);
+		}
 	} else {
 		ui_browser__set_percent_color(browser, 0, current_entry);
-		slsmg_write_nstring(" ", 7);
+		slsmg_write_nstring(" ", pcnt_width);
 	}
 
 	SLsmg_write_char(' ');
@@ -111,12 +127,12 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int
 		width += 1;
 
 	if (!*dl->line)
-		slsmg_write_nstring(" ", width - 7);
+		slsmg_write_nstring(" ", width - pcnt_width);
 	else if (dl->offset == -1) {
 		printed = scnprintf(bf, sizeof(bf), "%*s  ",
 				    ab->addr_width, " ");
 		slsmg_write_nstring(bf, printed);
-		slsmg_write_nstring(dl->line, width - printed - 6);
+		slsmg_write_nstring(dl->line, width - printed - pcnt_width + 1);
 	} else {
 		u64 addr = dl->offset;
 		int color = -1;
@@ -175,7 +191,7 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int
 		}
 
 		disasm_line__scnprintf(dl, bf, sizeof(bf), !annotate_browser__opts.use_offset);
-		slsmg_write_nstring(bf, width - 10 - printed);
+		slsmg_write_nstring(bf, width - pcnt_width - 3 - printed);
 	}
 
 	if (current_entry)
@@ -200,6 +216,7 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser)
 	unsigned int from, to;
 	struct map_symbol *ms = ab->b.priv;
 	struct symbol *sym = ms->sym;
+	u8 pcnt_width = 7;
 
 	/* PLT symbols contain external offsets */
 	if (strstr(sym->name, "@plt"))
@@ -223,57 +240,44 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser)
 		to = (u64)btarget->idx;
 	}
 
+	pcnt_width *= ab->nr_events;
+
 	ui_browser__set_color(browser, HE_COLORSET_CODE);
-	__ui_browser__line_arrow(browser, 9 + ab->addr_width, from, to);
+	__ui_browser__line_arrow(browser, pcnt_width + 2 + ab->addr_width,
+				 from, to);
 }
 
 static unsigned int annotate_browser__refresh(struct ui_browser *browser)
 {
+	struct annotate_browser *ab = container_of(browser, struct annotate_browser, b);
 	int ret = ui_browser__list_head_refresh(browser);
+	int pcnt_width;
+
+	pcnt_width = 7 * ab->nr_events;
 
 	if (annotate_browser__opts.jump_arrows)
 		annotate_browser__draw_current_jump(browser);
 
 	ui_browser__set_color(browser, HE_COLORSET_NORMAL);
-	__ui_browser__vline(browser, 7, 0, browser->height - 1);
+	__ui_browser__vline(browser, pcnt_width, 0, browser->height - 1);
 	return ret;
 }
 
-static double disasm_line__calc_percent(struct disasm_line *dl, struct symbol *sym, int evidx)
+static int disasm__cmp(struct browser_disasm_line *a,
+		       struct browser_disasm_line *b, int nr_pcnt)
 {
-	double percent = 0.0;
-
-	if (dl->offset != -1) {
-		int len = sym->end - sym->start;
-		unsigned int hits = 0;
-		struct annotation *notes = symbol__annotation(sym);
-		struct source_line *src_line = notes->src->lines;
-		struct sym_hist *h = annotation__histogram(notes, evidx);
-		s64 offset = dl->offset;
-		struct disasm_line *next;
+	int i;
 
-		next = disasm__get_next_ip_line(&notes->src->source, dl);
-		while (offset < (s64)len &&
-		       (next == NULL || offset < next->offset)) {
-			if (src_line) {
-				percent += src_line[offset].percent;
-			} else
-				hits += h->addr[offset];
-
-			++offset;
-		}
-		/*
- 		 * If the percentage wasn't already calculated in
- 		 * symbol__get_source_line, do it now:
- 		 */
-		if (src_line == NULL && h->sum)
-			percent = 100.0 * hits / h->sum;
+	for (i = 0; i < nr_pcnt; i++) {
+		if (a->percent[i] == b->percent[i])
+			continue;
+		return a->percent[i] < b->percent[i];
 	}
-
-	return percent;
+	return 0;
 }
 
-static void disasm_rb_tree__insert(struct rb_root *root, struct browser_disasm_line *bdl)
+static void disasm_rb_tree__insert(struct rb_root *root, struct browser_disasm_line *bdl,
+				   int nr_events)
 {
 	struct rb_node **p = &root->rb_node;
 	struct rb_node *parent = NULL;
@@ -282,7 +286,8 @@ static void disasm_rb_tree__insert(struct rb_root *root, struct browser_disasm_l
 	while (*p != NULL) {
 		parent = *p;
 		l = rb_entry(parent, struct browser_disasm_line, rb_node);
-		if (bdl->percent < l->percent)
+
+		if (disasm__cmp(bdl, l, nr_events))
 			p = &(*p)->rb_left;
 		else
 			p = &(*p)->rb_right;
@@ -331,12 +336,13 @@ static void annotate_browser__set_rb_top(struct annotate_browser *browser,
 }
 
 static void annotate_browser__calc_percent(struct annotate_browser *browser,
-					   int evidx)
+					   struct perf_evsel *evsel)
 {
 	struct map_symbol *ms = browser->b.priv;
 	struct symbol *sym = ms->sym;
 	struct annotation *notes = symbol__annotation(sym);
-	struct disasm_line *pos;
+	struct disasm_line *pos, *next;
+	s64 len = symbol__size(sym);
 
 	browser->entries = RB_ROOT;
 
@@ -344,12 +350,34 @@ static void annotate_browser__calc_percent(struct annotate_browser *browser,
 
 	list_for_each_entry(pos, &notes->src->source, node) {
 		struct browser_disasm_line *bpos = disasm_line__browser(pos);
-		bpos->percent = disasm_line__calc_percent(pos, sym, evidx);
-		if (bpos->percent < 0.01) {
+		const char *path = NULL;
+		double max_percent = 0.0;
+		int i;
+
+		if (pos->offset == -1) {
+			RB_CLEAR_NODE(&bpos->rb_node);
+			continue;
+		}
+
+		next = disasm__get_next_ip_line(&notes->src->source, pos);
+
+		for (i = 0; i < browser->nr_events; i++) {
+			bpos->percent[i] = disasm__calc_percent(notes,
+						evsel->idx + i,
+						pos->offset,
+						next ? next->offset : len,
+					        &path);
+
+			if (max_percent < bpos->percent[i])
+				max_percent = bpos->percent[i];
+		}
+
+		if (max_percent < 0.01) {
 			RB_CLEAR_NODE(&bpos->rb_node);
 			continue;
 		}
-		disasm_rb_tree__insert(&browser->entries, bpos);
+		disasm_rb_tree__insert(&browser->entries, bpos,
+				       browser->nr_events);
 	}
 	pthread_mutex_unlock(&notes->lock);
 
@@ -401,7 +429,8 @@ static void annotate_browser__init_asm_mode(struct annotate_browser *browser)
 	browser->b.nr_entries = browser->nr_asm_entries;
 }
 
-static bool annotate_browser__callq(struct annotate_browser *browser, int evidx,
+static bool annotate_browser__callq(struct annotate_browser *browser,
+				    struct perf_evsel *evsel,
 				    struct hist_browser_timer *hbt)
 {
 	struct map_symbol *ms = browser->b.priv;
@@ -432,7 +461,7 @@ static bool annotate_browser__callq(struct annotate_browser *browser, int evidx,
 	}
 
 	pthread_mutex_unlock(&notes->lock);
-	symbol__tui_annotate(target, ms->map, evidx, hbt);
+	symbol__tui_annotate(target, ms->map, evsel, hbt);
 	ui_browser__show_title(&browser->b, sym->name);
 	return true;
 }
@@ -615,7 +644,8 @@ static void annotate_browser__update_addr_width(struct annotate_browser *browser
 		browser->addr_width += browser->jumps_width + 1;
 }
 
-static int annotate_browser__run(struct annotate_browser *browser, int evidx,
+static int annotate_browser__run(struct annotate_browser *browser,
+				 struct perf_evsel *evsel,
 				 struct hist_browser_timer *hbt)
 {
 	struct rb_node *nd = NULL;
@@ -628,7 +658,7 @@ static int annotate_browser__run(struct annotate_browser *browser, int evidx,
 	if (ui_browser__show(&browser->b, sym->name, help) < 0)
 		return -1;
 
-	annotate_browser__calc_percent(browser, evidx);
+	annotate_browser__calc_percent(browser, evsel);
 
 	if (browser->curr_hot) {
 		annotate_browser__set_rb_top(browser, browser->curr_hot);
@@ -641,7 +671,7 @@ static int annotate_browser__run(struct annotate_browser *browser, int evidx,
 		key = ui_browser__run(&browser->b, delay_secs);
 
 		if (delay_secs != 0) {
-			annotate_browser__calc_percent(browser, evidx);
+			annotate_browser__calc_percent(browser, evsel);
 			/*
 			 * Current line focus got out of the list of most active
 			 * lines, NULL it so that if TAB|UNTAB is pressed, we
@@ -657,7 +687,7 @@ static int annotate_browser__run(struct annotate_browser *browser, int evidx,
 				hbt->timer(hbt->arg);
 
 			if (delay_secs != 0)
-				symbol__annotate_decay_histogram(sym, evidx);
+				symbol__annotate_decay_histogram(sym, evsel->idx);
 			continue;
 		case K_TAB:
 			if (nd != NULL) {
@@ -754,7 +784,7 @@ show_help:
 					goto show_sup_ins;
 				goto out;
 			} else if (!(annotate_browser__jump(browser) ||
-				     annotate_browser__callq(browser, evidx, hbt))) {
+				     annotate_browser__callq(browser, evsel, hbt))) {
 show_sup_ins:
 				ui_helpline__puts("Actions are only available for 'callq', 'retq' & jump instructions.");
 			}
@@ -776,10 +806,10 @@ out:
 	return key;
 }
 
-int hist_entry__tui_annotate(struct hist_entry *he, int evidx,
+int hist_entry__tui_annotate(struct hist_entry *he, struct perf_evsel *evsel,
 			     struct hist_browser_timer *hbt)
 {
-	return symbol__tui_annotate(he->ms.sym, he->ms.map, evidx, hbt);
+	return symbol__tui_annotate(he->ms.sym, he->ms.map, evsel, hbt);
 }
 
 static void annotate_browser__mark_jump_targets(struct annotate_browser *browser,
@@ -826,7 +856,8 @@ static inline int width_jumps(int n)
 	return 1;
 }
 
-int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx,
+int symbol__tui_annotate(struct symbol *sym, struct map *map,
+			 struct perf_evsel *evsel,
 			 struct hist_browser_timer *hbt)
 {
 	struct disasm_line *pos, *n;
@@ -847,6 +878,8 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx,
 		},
 	};
 	int ret = -1;
+	int nr_pcnt = 1;
+	size_t sizeof_bdl = sizeof(struct browser_disasm_line);
 
 	if (sym == NULL)
 		return -1;
@@ -862,7 +895,12 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx,
 		return -1;
 	}
 
-	if (symbol__annotate(sym, map, sizeof(struct browser_disasm_line)) < 0) {
+	if (perf_evsel__is_group_event(evsel)) {
+		nr_pcnt = evsel->nr_members;
+		sizeof_bdl += sizeof(double) * (nr_pcnt - 1);
+	}
+
+	if (symbol__annotate(sym, map, sizeof_bdl) < 0) {
 		ui__error("%s", ui_helpline__last_msg);
 		goto out_free_offsets;
 	}
@@ -900,6 +938,7 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx,
 	browser.addr_width = browser.target_width = browser.min_addr_width = hex_width(size);
 	browser.max_addr_width = hex_width(sym->end);
 	browser.jumps_width = width_jumps(browser.max_jump_sources);
+	browser.nr_events = nr_pcnt;
 	browser.b.nr_entries = browser.nr_entries;
 	browser.b.entries = &notes->src->source,
 	browser.b.width += 18; /* Percentage */
@@ -909,7 +948,7 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx,
 
 	annotate_browser__update_addr_width(&browser);
 
-	ret = annotate_browser__run(&browser, evidx, hbt);
+	ret = annotate_browser__run(&browser, evsel, hbt);
 	list_for_each_entry_safe(pos, n, &notes->src->source, node) {
 		list_del(&pos->node);
 		disasm_line__free(pos);
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index aa22704047d6..a5843fd6ab51 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -1193,7 +1193,7 @@ static int hists__browser_title(struct hists *hists, char *bf, size_t size,
 	char buf[512];
 	size_t buflen = sizeof(buf);
 
-	if (symbol_conf.event_group && evsel->nr_members > 1) {
+	if (perf_evsel__is_group_event(evsel)) {
 		struct perf_evsel *pos;
 
 		perf_evsel__group_desc(evsel, buf, buflen);
@@ -1599,7 +1599,7 @@ do_annotate:
 			 * Don't let this be freed, say, by hists__decay_entry.
 			 */
 			he->used = true;
-			err = hist_entry__tui_annotate(he, evsel->idx, hbt);
+			err = hist_entry__tui_annotate(he, evsel, hbt);
 			he->used = false;
 			/*
 			 * offer option to annotate the other branch source or target
@@ -1709,7 +1709,7 @@ static void perf_evsel_menu__write(struct ui_browser *browser,
 	ui_browser__set_color(browser, current_entry ? HE_COLORSET_SELECTED :
 						       HE_COLORSET_NORMAL);
 
-	if (symbol_conf.event_group && evsel->nr_members > 1) {
+	if (perf_evsel__is_group_event(evsel)) {
 		struct perf_evsel *pos;
 
 		ev_name = perf_evsel__group_name(evsel);
diff --git a/tools/perf/ui/gtk/annotate.c b/tools/perf/ui/gtk/annotate.c
index 7d8dc581a545..f538794615db 100644
--- a/tools/perf/ui/gtk/annotate.c
+++ b/tools/perf/ui/gtk/annotate.c
@@ -1,6 +1,7 @@
 #include "gtk.h"
 #include "util/debug.h"
 #include "util/annotate.h"
+#include "util/evsel.h"
 #include "ui/helpline.h"
 
 
@@ -32,7 +33,7 @@ static int perf_gtk__get_percent(char *buf, size_t size, struct symbol *sym,
 		return 0;
 
 	symhist = annotation__histogram(symbol__annotation(sym), evidx);
-	if (!symhist->addr[dl->offset])
+	if (!symbol_conf.event_group && !symhist->addr[dl->offset])
 		return 0;
 
 	percent = 100.0 * symhist->addr[dl->offset] / symhist->sum;
@@ -85,7 +86,7 @@ static int perf_gtk__get_line(char *buf, size_t size, struct disasm_line *dl)
 }
 
 static int perf_gtk__annotate_symbol(GtkWidget *window, struct symbol *sym,
-				struct map *map, int evidx,
+				struct map *map, struct perf_evsel *evsel,
 				struct hist_browser_timer *hbt __maybe_unused)
 {
 	struct disasm_line *pos, *n;
@@ -118,10 +119,24 @@ static int perf_gtk__annotate_symbol(GtkWidget *window, struct symbol *sym,
 
 	list_for_each_entry(pos, &notes->src->source, node) {
 		GtkTreeIter iter;
+		int ret = 0;
 
 		gtk_list_store_append(store, &iter);
 
-		if (perf_gtk__get_percent(s, sizeof(s), sym, pos, evidx))
+		if (perf_evsel__is_group_event(evsel)) {
+			for (i = 0; i < evsel->nr_members; i++) {
+				ret += perf_gtk__get_percent(s + ret,
+							     sizeof(s) - ret,
+							     sym, pos,
+							     evsel->idx + i);
+				ret += scnprintf(s + ret, sizeof(s) - ret, " ");
+			}
+		} else {
+			ret = perf_gtk__get_percent(s, sizeof(s), sym, pos,
+						    evsel->idx);
+		}
+
+		if (ret)
 			gtk_list_store_set(store, &iter, ANN_COL__PERCENT, s, -1);
 		if (perf_gtk__get_offset(s, sizeof(s), sym, map, pos))
 			gtk_list_store_set(store, &iter, ANN_COL__OFFSET, s, -1);
@@ -139,7 +154,8 @@ static int perf_gtk__annotate_symbol(GtkWidget *window, struct symbol *sym,
 	return 0;
 }
 
-int symbol__gtk_annotate(struct symbol *sym, struct map *map, int evidx,
+int symbol__gtk_annotate(struct symbol *sym, struct map *map,
+			 struct perf_evsel *evsel,
 			 struct hist_browser_timer *hbt)
 {
 	GtkWidget *window;
@@ -206,7 +222,7 @@ int symbol__gtk_annotate(struct symbol *sym, struct map *map, int evidx,
 	gtk_notebook_append_page(GTK_NOTEBOOK(notebook), scrolled_window,
 				 tab_label);
 
-	perf_gtk__annotate_symbol(scrolled_window, sym, map, evidx, hbt);
+	perf_gtk__annotate_symbol(scrolled_window, sym, map, evsel, hbt);
 	return 0;
 }
 
diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c
index 1e764a8ad259..6f259b3d14e2 100644
--- a/tools/perf/ui/gtk/hists.c
+++ b/tools/perf/ui/gtk/hists.c
@@ -32,21 +32,18 @@ static int __hpp__color_fmt(struct perf_hpp *hpp, struct hist_entry *he,
 	int ret;
 	double percent = 0.0;
 	struct hists *hists = he->hists;
+	struct perf_evsel *evsel = hists_to_evsel(hists);
 
 	if (hists->stats.total_period)
 		percent = 100.0 * get_field(he) / hists->stats.total_period;
 
 	ret = __percent_color_snprintf(hpp->buf, hpp->size, percent);
 
-	if (symbol_conf.event_group) {
+	if (perf_evsel__is_group_event(evsel)) {
 		int prev_idx, idx_delta;
-		struct perf_evsel *evsel = hists_to_evsel(hists);
 		struct hist_entry *pair;
 		int nr_members = evsel->nr_members;
 
-		if (nr_members <= 1)
-			return ret;
-
 		prev_idx = perf_evsel__group_idx(evsel);
 
 		list_for_each_entry(pair, &he->pairs.head, pairs.node) {
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index d671e63aa351..4bf91b09d62d 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -16,6 +16,7 @@ static int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
 {
 	int ret;
 	struct hists *hists = he->hists;
+	struct perf_evsel *evsel = hists_to_evsel(hists);
 
 	if (fmt_percent) {
 		double percent = 0.0;
@@ -28,15 +29,11 @@ static int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
 	} else
 		ret = print_fn(hpp->buf, hpp->size, fmt, get_field(he));
 
-	if (symbol_conf.event_group) {
+	if (perf_evsel__is_group_event(evsel)) {
 		int prev_idx, idx_delta;
-		struct perf_evsel *evsel = hists_to_evsel(hists);
 		struct hist_entry *pair;
 		int nr_members = evsel->nr_members;
 
-		if (nr_members <= 1)
-			return ret;
-
 		prev_idx = perf_evsel__group_idx(evsel);
 
 		list_for_each_entry(pair, &he->pairs.head, pairs.node) {
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index d33fe937e6f1..d102716c43a1 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -14,6 +14,7 @@
 #include "symbol.h"
 #include "debug.h"
 #include "annotate.h"
+#include "evsel.h"
 #include <pthread.h>
 #include <linux/bitops.h>
 
@@ -602,8 +603,42 @@ struct disasm_line *disasm__get_next_ip_line(struct list_head *head, struct disa
 	return NULL;
 }
 
+double disasm__calc_percent(struct annotation *notes, int evidx, s64 offset,
+			    s64 end, const char **path)
+{
+	struct source_line *src_line = notes->src->lines;
+	double percent = 0.0;
+
+	if (src_line) {
+		size_t sizeof_src_line = sizeof(*src_line) +
+				sizeof(src_line->p) * (src_line->nr_pcnt - 1);
+
+		while (offset < end) {
+			src_line = (void *)notes->src->lines +
+					(sizeof_src_line * offset);
+
+			if (*path == NULL)
+				*path = src_line->path;
+
+			percent += src_line->p[evidx].percent;
+			offset++;
+		}
+	} else {
+		struct sym_hist *h = annotation__histogram(notes, evidx);
+		unsigned int hits = 0;
+
+		while (offset < end)
+			hits += h->addr[offset++];
+
+		if (h->sum)
+			percent = 100.0 * hits / h->sum;
+	}
+
+	return percent;
+}
+
 static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 start,
-		      int evidx, u64 len, int min_pcnt, int printed,
+		      struct perf_evsel *evsel, u64 len, int min_pcnt, int printed,
 		      int max_lines, struct disasm_line *queue)
 {
 	static const char *prev_line;
@@ -611,34 +646,37 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st
 
 	if (dl->offset != -1) {
 		const char *path = NULL;
-		unsigned int hits = 0;
-		double percent = 0.0;
+		double percent, max_percent = 0.0;
+		double *ppercents = &percent;
+		int i, nr_percent = 1;
 		const char *color;
 		struct annotation *notes = symbol__annotation(sym);
-		struct source_line *src_line = notes->src->lines;
-		struct sym_hist *h = annotation__histogram(notes, evidx);
 		s64 offset = dl->offset;
 		const u64 addr = start + offset;
 		struct disasm_line *next;
 
 		next = disasm__get_next_ip_line(&notes->src->source, dl);
 
-		while (offset < (s64)len &&
-		       (next == NULL || offset < next->offset)) {
-			if (src_line) {
-				if (path == NULL)
-					path = src_line[offset].path;
-				percent += src_line[offset].percent;
-			} else
-				hits += h->addr[offset];
-
-			++offset;
+		if (perf_evsel__is_group_event(evsel)) {
+			nr_percent = evsel->nr_members;
+			ppercents = calloc(nr_percent, sizeof(double));
+			if (ppercents == NULL)
+				return -1;
 		}
 
-		if (src_line == NULL && h->sum)
-			percent = 100.0 * hits / h->sum;
+		for (i = 0; i < nr_percent; i++) {
+			percent = disasm__calc_percent(notes,
+					notes->src->lines ? i : evsel->idx + i,
+					offset,
+					next ? next->offset : (s64) len,
+					&path);
+
+			ppercents[i] = percent;
+			if (percent > max_percent)
+				max_percent = percent;
+		}
 
-		if (percent < min_pcnt)
+		if (max_percent < min_pcnt)
 			return -1;
 
 		if (max_lines && printed >= max_lines)
@@ -648,12 +686,12 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st
 			list_for_each_entry_from(queue, &notes->src->source, node) {
 				if (queue == dl)
 					break;
-				disasm_line__print(queue, sym, start, evidx, len,
+				disasm_line__print(queue, sym, start, evsel, len,
 						    0, 0, 1, NULL);
 			}
 		}
 
-		color = get_percent_color(percent);
+		color = get_percent_color(max_percent);
 
 		/*
 		 * Also color the filename and line if needed, with
@@ -669,25 +707,59 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st
 			}
 		}
 
-		color_fprintf(stdout, color, " %7.2f", percent);
+		for (i = 0; i < nr_percent; i++) {
+			percent = ppercents[i];
+			color = get_percent_color(percent);
+			color_fprintf(stdout, color, " %7.2f", percent);
+		}
+
 		printf(" :	");
 		color_fprintf(stdout, PERF_COLOR_MAGENTA, "  %" PRIx64 ":", addr);
 		color_fprintf(stdout, PERF_COLOR_BLUE, "%s\n", dl->line);
+
+		if (ppercents != &percent)
+			free(ppercents);
+
 	} else if (max_lines && printed >= max_lines)
 		return 1;
 	else {
+		int width = 8;
+
 		if (queue)
 			return -1;
 
+		if (perf_evsel__is_group_event(evsel))
+			width *= evsel->nr_members;
+
 		if (!*dl->line)
-			printf("         :\n");
+			printf(" %*s:\n", width, " ");
 		else
-			printf("         :	%s\n", dl->line);
+			printf(" %*s:	%s\n", width, " ", dl->line);
 	}
 
 	return 0;
 }
 
+/*
+ * symbol__parse_objdump_line() parses objdump output (with -d --no-show-raw)
+ * which looks like following
+ *
+ *  0000000000415500 <_init>:
+ *    415500:       sub    $0x8,%rsp
+ *    415504:       mov    0x2f5ad5(%rip),%rax        # 70afe0 <_DYNAMIC+0x2f8>
+ *    41550b:       test   %rax,%rax
+ *    41550e:       je     415515 <_init+0x15>
+ *    415510:       callq  416e70 <__gmon_start__@plt>
+ *    415515:       add    $0x8,%rsp
+ *    415519:       retq
+ *
+ * it will be parsed and saved into struct disasm_line as
+ *  <offset>       <name>  <ops.raw>
+ *
+ * The offset will be a relative offset from the start of the symbol and -1
+ * means that it's not a disassembly line so should be treated differently.
+ * The ops.raw part will be parsed further according to type of the instruction.
+ */
 static int symbol__parse_objdump_line(struct symbol *sym, struct map *map,
 				      FILE *file, size_t privsize)
 {
@@ -858,7 +930,7 @@ static void insert_source_line(struct rb_root *root, struct source_line *src_lin
 	struct source_line *iter;
 	struct rb_node **p = &root->rb_node;
 	struct rb_node *parent = NULL;
-	int ret;
+	int i, ret;
 
 	while (*p != NULL) {
 		parent = *p;
@@ -866,7 +938,8 @@ static void insert_source_line(struct rb_root *root, struct source_line *src_lin
 
 		ret = strcmp(iter->path, src_line->path);
 		if (ret == 0) {
-			iter->percent_sum += src_line->percent;
+			for (i = 0; i < src_line->nr_pcnt; i++)
+				iter->p[i].percent_sum += src_line->p[i].percent;
 			return;
 		}
 
@@ -876,12 +949,26 @@ static void insert_source_line(struct rb_root *root, struct source_line *src_lin
 			p = &(*p)->rb_right;
 	}
 
-	src_line->percent_sum = src_line->percent;
+	for (i = 0; i < src_line->nr_pcnt; i++)
+		src_line->p[i].percent_sum = src_line->p[i].percent;
 
 	rb_link_node(&src_line->node, parent, p);
 	rb_insert_color(&src_line->node, root);
 }
 
+static int cmp_source_line(struct source_line *a, struct source_line *b)
+{
+	int i;
+
+	for (i = 0; i < a->nr_pcnt; i++) {
+		if (a->p[i].percent_sum == b->p[i].percent_sum)
+			continue;
+		return a->p[i].percent_sum > b->p[i].percent_sum;
+	}
+
+	return 0;
+}
+
 static void __resort_source_line(struct rb_root *root, struct source_line *src_line)
 {
 	struct source_line *iter;
@@ -892,7 +979,7 @@ static void __resort_source_line(struct rb_root *root, struct source_line *src_l
 		parent = *p;
 		iter = rb_entry(parent, struct source_line, node);
 
-		if (src_line->percent_sum > iter->percent_sum)
+		if (cmp_source_line(src_line, iter))
 			p = &(*p)->rb_left;
 		else
 			p = &(*p)->rb_right;
@@ -924,32 +1011,52 @@ static void symbol__free_source_line(struct symbol *sym, int len)
 {
 	struct annotation *notes = symbol__annotation(sym);
 	struct source_line *src_line = notes->src->lines;
+	size_t sizeof_src_line;
 	int i;
 
-	for (i = 0; i < len; i++)
-		free(src_line[i].path);
+	sizeof_src_line = sizeof(*src_line) +
+			  (sizeof(src_line->p) * (src_line->nr_pcnt - 1));
+
+	for (i = 0; i < len; i++) {
+		free(src_line->path);
+		src_line = (void *)src_line + sizeof_src_line;
+	}
 
-	free(src_line);
+	free(notes->src->lines);
 	notes->src->lines = NULL;
 }
 
 /* Get the filename:line for the colored entries */
 static int symbol__get_source_line(struct symbol *sym, struct map *map,
-				   int evidx, struct rb_root *root, int len,
+				   struct perf_evsel *evsel,
+				   struct rb_root *root, int len,
 				   const char *filename)
 {
 	u64 start;
-	int i;
+	int i, k;
+	int evidx = evsel->idx;
 	char cmd[PATH_MAX * 2];
 	struct source_line *src_line;
 	struct annotation *notes = symbol__annotation(sym);
 	struct sym_hist *h = annotation__histogram(notes, evidx);
 	struct rb_root tmp_root = RB_ROOT;
+	int nr_pcnt = 1;
+	u64 h_sum = h->sum;
+	size_t sizeof_src_line = sizeof(struct source_line);
+
+	if (perf_evsel__is_group_event(evsel)) {
+		for (i = 1; i < evsel->nr_members; i++) {
+			h = annotation__histogram(notes, evidx + i);
+			h_sum += h->sum;
+		}
+		nr_pcnt = evsel->nr_members;
+		sizeof_src_line += (nr_pcnt - 1) * sizeof(src_line->p);
+	}
 
-	if (!h->sum)
+	if (!h_sum)
 		return 0;
 
-	src_line = notes->src->lines = calloc(len, sizeof(struct source_line));
+	src_line = notes->src->lines = calloc(len, sizeof_src_line);
 	if (!notes->src->lines)
 		return -1;
 
@@ -960,29 +1067,41 @@ static int symbol__get_source_line(struct symbol *sym, struct map *map,
 		size_t line_len;
 		u64 offset;
 		FILE *fp;
+		double percent_max = 0.0;
 
-		src_line[i].percent = 100.0 * h->addr[i] / h->sum;
-		if (src_line[i].percent <= 0.5)
-			continue;
+		src_line->nr_pcnt = nr_pcnt;
+
+		for (k = 0; k < nr_pcnt; k++) {
+			h = annotation__histogram(notes, evidx + k);
+			src_line->p[k].percent = 100.0 * h->addr[i] / h->sum;
+
+			if (src_line->p[k].percent > percent_max)
+				percent_max = src_line->p[k].percent;
+		}
+
+		if (percent_max <= 0.5)
+			goto next;
 
 		offset = start + i;
 		sprintf(cmd, "addr2line -e %s %016" PRIx64, filename, offset);
 		fp = popen(cmd, "r");
 		if (!fp)
-			continue;
+			goto next;
 
 		if (getline(&path, &line_len, fp) < 0 || !line_len)
-			goto next;
+			goto next_close;
 
-		src_line[i].path = malloc(sizeof(char) * line_len + 1);
-		if (!src_line[i].path)
-			goto next;
+		src_line->path = malloc(sizeof(char) * line_len + 1);
+		if (!src_line->path)
+			goto next_close;
 
-		strcpy(src_line[i].path, path);
-		insert_source_line(&tmp_root, &src_line[i]);
+		strcpy(src_line->path, path);
+		insert_source_line(&tmp_root, src_line);
 
-	next:
+	next_close:
 		pclose(fp);
+	next:
+		src_line = (void *)src_line + sizeof_src_line;
 	}
 
 	resort_source_line(root, &tmp_root);
@@ -1004,24 +1123,33 @@ static void print_summary(struct rb_root *root, const char *filename)
 
 	node = rb_first(root);
 	while (node) {
-		double percent;
+		double percent, percent_max = 0.0;
 		const char *color;
 		char *path;
+		int i;
 
 		src_line = rb_entry(node, struct source_line, node);
-		percent = src_line->percent_sum;
-		color = get_percent_color(percent);
+		for (i = 0; i < src_line->nr_pcnt; i++) {
+			percent = src_line->p[i].percent_sum;
+			color = get_percent_color(percent);
+			color_fprintf(stdout, color, " %7.2f", percent);
+
+			if (percent > percent_max)
+				percent_max = percent;
+		}
+
 		path = src_line->path;
+		color = get_percent_color(percent_max);
+		color_fprintf(stdout, color, " %s", path);
 
-		color_fprintf(stdout, color, " %7.2f %s", percent, path);
 		node = rb_next(node);
 	}
 }
 
-static void symbol__annotate_hits(struct symbol *sym, int evidx)
+static void symbol__annotate_hits(struct symbol *sym, struct perf_evsel *evsel)
 {
 	struct annotation *notes = symbol__annotation(sym);
-	struct sym_hist *h = annotation__histogram(notes, evidx);
+	struct sym_hist *h = annotation__histogram(notes, evsel->idx);
 	u64 len = symbol__size(sym), offset;
 
 	for (offset = 0; offset < len; ++offset)
@@ -1031,9 +1159,9 @@ static void symbol__annotate_hits(struct symbol *sym, int evidx)
 	printf("%*s: %" PRIu64 "\n", BITS_PER_LONG / 2, "h->sum", h->sum);
 }
 
-int symbol__annotate_printf(struct symbol *sym, struct map *map, int evidx,
-			    bool full_paths, int min_pcnt, int max_lines,
-			    int context)
+int symbol__annotate_printf(struct symbol *sym, struct map *map,
+			    struct perf_evsel *evsel, bool full_paths,
+			    int min_pcnt, int max_lines, int context)
 {
 	struct dso *dso = map->dso;
 	char *filename;
@@ -1044,6 +1172,8 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map, int evidx,
 	int printed = 2, queue_len = 0;
 	int more = 0;
 	u64 len;
+	int width = 8;
+	int namelen;
 
 	filename = strdup(dso->long_name);
 	if (!filename)
@@ -1055,12 +1185,18 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map, int evidx,
 		d_filename = basename(filename);
 
 	len = symbol__size(sym);
+	namelen = strlen(d_filename);
+
+	if (perf_evsel__is_group_event(evsel))
+		width *= evsel->nr_members;
 
-	printf(" Percent |	Source code & Disassembly of %s\n", d_filename);
-	printf("------------------------------------------------\n");
+	printf(" %-*.*s|	Source code & Disassembly of %s\n",
+	       width, width, "Percent", d_filename);
+	printf("-%-*.*s-------------------------------------\n",
+	       width+namelen, width+namelen, graph_dotted_line);
 
 	if (verbose)
-		symbol__annotate_hits(sym, evidx);
+		symbol__annotate_hits(sym, evsel);
 
 	list_for_each_entry(pos, &notes->src->source, node) {
 		if (context && queue == NULL) {
@@ -1068,7 +1204,7 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map, int evidx,
 			queue_len = 0;
 		}
 
-		switch (disasm_line__print(pos, sym, start, evidx, len,
+		switch (disasm_line__print(pos, sym, start, evsel, len,
 					    min_pcnt, printed, max_lines,
 					    queue)) {
 		case 0:
@@ -1163,9 +1299,9 @@ size_t disasm__fprintf(struct list_head *head, FILE *fp)
 	return printed;
 }
 
-int symbol__tty_annotate(struct symbol *sym, struct map *map, int evidx,
-			 bool print_lines, bool full_paths, int min_pcnt,
-			 int max_lines)
+int symbol__tty_annotate(struct symbol *sym, struct map *map,
+			 struct perf_evsel *evsel, bool print_lines,
+			 bool full_paths, int min_pcnt, int max_lines)
 {
 	struct dso *dso = map->dso;
 	const char *filename = dso->long_name;
@@ -1178,12 +1314,12 @@ int symbol__tty_annotate(struct symbol *sym, struct map *map, int evidx,
 	len = symbol__size(sym);
 
 	if (print_lines) {
-		symbol__get_source_line(sym, map, evidx, &source_line,
+		symbol__get_source_line(sym, map, evsel, &source_line,
 					len, filename);
 		print_summary(&source_line, filename);
 	}
 
-	symbol__annotate_printf(sym, map, evidx, full_paths,
+	symbol__annotate_printf(sym, map, evsel, full_paths,
 				min_pcnt, max_lines, 0);
 	if (print_lines)
 		symbol__free_source_line(sym, len);
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index c422440fe611..6f3c16f01ab4 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -50,6 +50,8 @@ bool ins__is_jump(const struct ins *ins);
 bool ins__is_call(const struct ins *ins);
 int ins__scnprintf(struct ins *ins, char *bf, size_t size, struct ins_operands *ops);
 
+struct annotation;
+
 struct disasm_line {
 	struct list_head    node;
 	s64		    offset;
@@ -68,17 +70,24 @@ void disasm_line__free(struct disasm_line *dl);
 struct disasm_line *disasm__get_next_ip_line(struct list_head *head, struct disasm_line *pos);
 int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw);
 size_t disasm__fprintf(struct list_head *head, FILE *fp);
+double disasm__calc_percent(struct annotation *notes, int evidx, s64 offset,
+			    s64 end, const char **path);
 
 struct sym_hist {
 	u64		sum;
 	u64		addr[0];
 };
 
-struct source_line {
-	struct rb_node	node;
+struct source_line_percent {
 	double		percent;
 	double		percent_sum;
+};
+
+struct source_line {
+	struct rb_node	node;
 	char		*path;
+	int		nr_pcnt;
+	struct source_line_percent p[1];
 };
 
 /** struct annotated_source - symbols with hits have this attached as in sannotation
@@ -130,47 +139,49 @@ void symbol__annotate_zero_histograms(struct symbol *sym);
 
 int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize);
 int symbol__annotate_init(struct map *map __maybe_unused, struct symbol *sym);
-int symbol__annotate_printf(struct symbol *sym, struct map *map, int evidx,
-			    bool full_paths, int min_pcnt, int max_lines,
-			    int context);
+int symbol__annotate_printf(struct symbol *sym, struct map *map,
+			    struct perf_evsel *evsel, bool full_paths,
+			    int min_pcnt, int max_lines, int context);
 void symbol__annotate_zero_histogram(struct symbol *sym, int evidx);
 void symbol__annotate_decay_histogram(struct symbol *sym, int evidx);
 void disasm__purge(struct list_head *head);
 
-int symbol__tty_annotate(struct symbol *sym, struct map *map, int evidx,
-			 bool print_lines, bool full_paths, int min_pcnt,
-			 int max_lines);
+int symbol__tty_annotate(struct symbol *sym, struct map *map,
+			 struct perf_evsel *evsel, bool print_lines,
+			 bool full_paths, int min_pcnt, int max_lines);
 
 #ifdef NEWT_SUPPORT
-int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx,
+int symbol__tui_annotate(struct symbol *sym, struct map *map,
+			 struct perf_evsel *evsel,
 			 struct hist_browser_timer *hbt);
 #else
 static inline int symbol__tui_annotate(struct symbol *sym __maybe_unused,
-				       struct map *map __maybe_unused,
-				       int evidx __maybe_unused,
-				       struct hist_browser_timer *hbt
-				       __maybe_unused)
+				struct map *map __maybe_unused,
+				struct perf_evsel *evsel  __maybe_unused,
+				struct hist_browser_timer *hbt
+				__maybe_unused)
 {
 	return 0;
 }
 #endif
 
 #ifdef GTK2_SUPPORT
-int symbol__gtk_annotate(struct symbol *sym, struct map *map, int evidx,
+int symbol__gtk_annotate(struct symbol *sym, struct map *map,
+			 struct perf_evsel *evsel,
 			 struct hist_browser_timer *hbt);
 
-static inline int hist_entry__gtk_annotate(struct hist_entry *he, int evidx,
+static inline int hist_entry__gtk_annotate(struct hist_entry *he,
+					   struct perf_evsel *evsel,
 					   struct hist_browser_timer *hbt)
 {
-	return symbol__gtk_annotate(he->ms.sym, he->ms.map, evidx, hbt);
+	return symbol__gtk_annotate(he->ms.sym, he->ms.map, evsel, hbt);
 }
 
 void perf_gtk__show_annotations(void);
 #else
 static inline int hist_entry__gtk_annotate(struct hist_entry *he __maybe_unused,
-					   int evidx __maybe_unused,
-					   struct hist_browser_timer *hbt
-					   __maybe_unused)
+				struct perf_evsel *evsel __maybe_unused,
+				struct hist_browser_timer *hbt __maybe_unused)
 {
 	return 0;
 }
diff --git a/tools/perf/util/debugfs.h b/tools/perf/util/debugfs.h
deleted file mode 100644
index 68f3e87ec57f..000000000000
--- a/tools/perf/util/debugfs.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifndef __DEBUGFS_H__
-#define __DEBUGFS_H__
-
-const char *debugfs_find_mountpoint(void);
-int debugfs_valid_mountpoint(const char *debugfs);
-char *debugfs_mount(const char *mountpoint);
-void debugfs_set_path(const char *mountpoint);
-
-extern char debugfs_mountpoint[];
-extern char tracing_events_path[];
-
-#endif /* __DEBUGFS_H__ */
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index c8be0fbc5145..f7c727801aab 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -7,7 +7,7 @@
  * Released under the GPL v2. (and only v2, not any later version)
  */
 #include "util.h"
-#include "debugfs.h"
+#include <lk/debugfs.h>
 #include <poll.h>
 #include "cpumap.h"
 #include "thread_map.h"
@@ -38,13 +38,12 @@ void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus,
 	evlist->workload.pid = -1;
 }
 
-struct perf_evlist *perf_evlist__new(struct cpu_map *cpus,
-				     struct thread_map *threads)
+struct perf_evlist *perf_evlist__new(void)
 {
 	struct perf_evlist *evlist = zalloc(sizeof(*evlist));
 
 	if (evlist != NULL)
-		perf_evlist__init(evlist, cpus, threads);
+		perf_evlist__init(evlist, NULL, NULL);
 
 	return evlist;
 }
@@ -228,12 +227,14 @@ void perf_evlist__disable(struct perf_evlist *evlist)
 {
 	int cpu, thread;
 	struct perf_evsel *pos;
+	int nr_cpus = cpu_map__nr(evlist->cpus);
+	int nr_threads = thread_map__nr(evlist->threads);
 
-	for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
+	for (cpu = 0; cpu < nr_cpus; cpu++) {
 		list_for_each_entry(pos, &evlist->entries, node) {
 			if (!perf_evsel__is_group_leader(pos))
 				continue;
-			for (thread = 0; thread < evlist->threads->nr; thread++)
+			for (thread = 0; thread < nr_threads; thread++)
 				ioctl(FD(pos, cpu, thread),
 				      PERF_EVENT_IOC_DISABLE, 0);
 		}
@@ -244,12 +245,14 @@ void perf_evlist__enable(struct perf_evlist *evlist)
 {
 	int cpu, thread;
 	struct perf_evsel *pos;
+	int nr_cpus = cpu_map__nr(evlist->cpus);
+	int nr_threads = thread_map__nr(evlist->threads);
 
-	for (cpu = 0; cpu < cpu_map__nr(evlist->cpus); cpu++) {
+	for (cpu = 0; cpu < nr_cpus; cpu++) {
 		list_for_each_entry(pos, &evlist->entries, node) {
 			if (!perf_evsel__is_group_leader(pos))
 				continue;
-			for (thread = 0; thread < evlist->threads->nr; thread++)
+			for (thread = 0; thread < nr_threads; thread++)
 				ioctl(FD(pos, cpu, thread),
 				      PERF_EVENT_IOC_ENABLE, 0);
 		}
@@ -258,7 +261,9 @@ void perf_evlist__enable(struct perf_evlist *evlist)
 
 static int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
 {
-	int nfds = cpu_map__nr(evlist->cpus) * evlist->threads->nr * evlist->nr_entries;
+	int nr_cpus = cpu_map__nr(evlist->cpus);
+	int nr_threads = thread_map__nr(evlist->threads);
+	int nfds = nr_cpus * nr_threads * evlist->nr_entries;
 	evlist->pollfd = malloc(sizeof(struct pollfd) * nfds);
 	return evlist->pollfd != NULL ? 0 : -ENOMEM;
 }
@@ -417,7 +422,7 @@ static int perf_evlist__alloc_mmap(struct perf_evlist *evlist)
 {
 	evlist->nr_mmaps = cpu_map__nr(evlist->cpus);
 	if (cpu_map__all(evlist->cpus))
-		evlist->nr_mmaps = evlist->threads->nr;
+		evlist->nr_mmaps = thread_map__nr(evlist->threads);
 	evlist->mmap = zalloc(evlist->nr_mmaps * sizeof(struct perf_mmap));
 	return evlist->mmap != NULL ? 0 : -ENOMEM;
 }
@@ -442,11 +447,13 @@ static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot, int m
 {
 	struct perf_evsel *evsel;
 	int cpu, thread;
+	int nr_cpus = cpu_map__nr(evlist->cpus);
+	int nr_threads = thread_map__nr(evlist->threads);
 
-	for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
+	for (cpu = 0; cpu < nr_cpus; cpu++) {
 		int output = -1;
 
-		for (thread = 0; thread < evlist->threads->nr; thread++) {
+		for (thread = 0; thread < nr_threads; thread++) {
 			list_for_each_entry(evsel, &evlist->entries, node) {
 				int fd = FD(evsel, cpu, thread);
 
@@ -470,7 +477,7 @@ static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot, int m
 	return 0;
 
 out_unmap:
-	for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
+	for (cpu = 0; cpu < nr_cpus; cpu++) {
 		if (evlist->mmap[cpu].base != NULL) {
 			munmap(evlist->mmap[cpu].base, evlist->mmap_len);
 			evlist->mmap[cpu].base = NULL;
@@ -483,8 +490,9 @@ static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot, in
 {
 	struct perf_evsel *evsel;
 	int thread;
+	int nr_threads = thread_map__nr(evlist->threads);
 
-	for (thread = 0; thread < evlist->threads->nr; thread++) {
+	for (thread = 0; thread < nr_threads; thread++) {
 		int output = -1;
 
 		list_for_each_entry(evsel, &evlist->entries, node) {
@@ -509,7 +517,7 @@ static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot, in
 	return 0;
 
 out_unmap:
-	for (thread = 0; thread < evlist->threads->nr; thread++) {
+	for (thread = 0; thread < nr_threads; thread++) {
 		if (evlist->mmap[thread].base != NULL) {
 			munmap(evlist->mmap[thread].base, evlist->mmap_len);
 			evlist->mmap[thread].base = NULL;
@@ -610,7 +618,7 @@ int perf_evlist__apply_filters(struct perf_evlist *evlist)
 	struct perf_evsel *evsel;
 	int err = 0;
 	const int ncpus = cpu_map__nr(evlist->cpus),
-		  nthreads = evlist->threads->nr;
+		  nthreads = thread_map__nr(evlist->threads);
 
 	list_for_each_entry(evsel, &evlist->entries, node) {
 		if (evsel->filter == NULL)
@@ -629,7 +637,7 @@ int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter)
 	struct perf_evsel *evsel;
 	int err = 0;
 	const int ncpus = cpu_map__nr(evlist->cpus),
-		  nthreads = evlist->threads->nr;
+		  nthreads = thread_map__nr(evlist->threads);
 
 	list_for_each_entry(evsel, &evlist->entries, node) {
 		err = perf_evsel__set_filter(evsel, ncpus, nthreads, filter);
@@ -712,10 +720,20 @@ void perf_evlist__set_selected(struct perf_evlist *evlist,
 	evlist->selected = evsel;
 }
 
+void perf_evlist__close(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+	int ncpus = cpu_map__nr(evlist->cpus);
+	int nthreads = thread_map__nr(evlist->threads);
+
+	list_for_each_entry_reverse(evsel, &evlist->entries, node)
+		perf_evsel__close(evsel, ncpus, nthreads);
+}
+
 int perf_evlist__open(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel;
-	int err, ncpus, nthreads;
+	int err;
 
 	list_for_each_entry(evsel, &evlist->entries, node) {
 		err = perf_evsel__open(evsel, evlist->cpus, evlist->threads);
@@ -725,19 +743,15 @@ int perf_evlist__open(struct perf_evlist *evlist)
 
 	return 0;
 out_err:
-	ncpus = evlist->cpus ? evlist->cpus->nr : 1;
-	nthreads = evlist->threads ? evlist->threads->nr : 1;
-
-	list_for_each_entry_reverse(evsel, &evlist->entries, node)
-		perf_evsel__close(evsel, ncpus, nthreads);
-
+	perf_evlist__close(evlist);
 	errno = -err;
 	return err;
 }
 
 int perf_evlist__prepare_workload(struct perf_evlist *evlist,
-				  struct perf_record_opts *opts,
-				  const char *argv[])
+				  struct perf_target *target,
+				  const char *argv[], bool pipe_output,
+				  bool want_signal)
 {
 	int child_ready_pipe[2], go_pipe[2];
 	char bf;
@@ -759,7 +773,7 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist,
 	}
 
 	if (!evlist->workload.pid) {
-		if (opts->pipe_output)
+		if (pipe_output)
 			dup2(2, 1);
 
 		close(child_ready_pipe[0]);
@@ -787,11 +801,12 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist,
 		execvp(argv[0], (char **)argv);
 
 		perror(argv[0]);
-		kill(getppid(), SIGUSR1);
+		if (want_signal)
+			kill(getppid(), SIGUSR1);
 		exit(-1);
 	}
 
-	if (perf_target__none(&opts->target))
+	if (perf_target__none(target))
 		evlist->threads->map[0] = evlist->workload.pid;
 
 	close(child_ready_pipe[1]);
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 2dd07bd60b4f..0583d36252be 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -49,8 +49,7 @@ struct perf_evsel_str_handler {
 	void	   *handler;
 };
 
-struct perf_evlist *perf_evlist__new(struct cpu_map *cpus,
-				     struct thread_map *threads);
+struct perf_evlist *perf_evlist__new(void);
 void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus,
 		       struct thread_map *threads);
 void perf_evlist__exit(struct perf_evlist *evlist);
@@ -82,13 +81,15 @@ struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id);
 union perf_event *perf_evlist__mmap_read(struct perf_evlist *self, int idx);
 
 int perf_evlist__open(struct perf_evlist *evlist);
+void perf_evlist__close(struct perf_evlist *evlist);
 
 void perf_evlist__config(struct perf_evlist *evlist,
 			 struct perf_record_opts *opts);
 
 int perf_evlist__prepare_workload(struct perf_evlist *evlist,
-				  struct perf_record_opts *opts,
-				  const char *argv[]);
+				  struct perf_target *target,
+				  const char *argv[], bool pipe_output,
+				  bool want_signal);
 int perf_evlist__start_workload(struct perf_evlist *evlist);
 
 int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 9c82f98f26de..1adb824610f0 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -10,7 +10,7 @@
 #include <byteswap.h>
 #include <linux/bitops.h>
 #include "asm/bug.h"
-#include "debugfs.h"
+#include <lk/debugfs.h>
 #include "event-parse.h"
 #include "evsel.h"
 #include "evlist.h"
@@ -633,6 +633,12 @@ int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads)
 	return 0;
 }
 
+void perf_evsel__reset_counts(struct perf_evsel *evsel, int ncpus)
+{
+	memset(evsel->counts, 0, (sizeof(*evsel->counts) +
+				 (ncpus * sizeof(struct perf_counts_values))));
+}
+
 int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus)
 {
 	evsel->counts = zalloc((sizeof(*evsel->counts) +
@@ -673,9 +679,8 @@ void perf_evsel__free_counts(struct perf_evsel *evsel)
 void perf_evsel__exit(struct perf_evsel *evsel)
 {
 	assert(list_empty(&evsel->node));
-	xyarray__delete(evsel->fd);
-	xyarray__delete(evsel->sample_id);
-	free(evsel->id);
+	perf_evsel__free_fd(evsel);
+	perf_evsel__free_id(evsel);
 }
 
 void perf_evsel__delete(struct perf_evsel *evsel)
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 52021c3087df..3f156ccc1acb 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -9,6 +9,7 @@
 #include "xyarray.h"
 #include "cgroup.h"
 #include "hist.h"
+#include "symbol.h"
  
 struct perf_counts_values {
 	union {
@@ -120,6 +121,7 @@ int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size);
 int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
 int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads);
 int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus);
+void perf_evsel__reset_counts(struct perf_evsel *evsel, int ncpus);
 void perf_evsel__free_fd(struct perf_evsel *evsel);
 void perf_evsel__free_id(struct perf_evsel *evsel);
 void perf_evsel__free_counts(struct perf_evsel *evsel);
@@ -246,11 +248,34 @@ static inline struct perf_evsel *perf_evsel__next(struct perf_evsel *evsel)
 	return list_entry(evsel->node.next, struct perf_evsel, node);
 }
 
+/**
+ * perf_evsel__is_group_leader - Return whether given evsel is a leader event
+ *
+ * @evsel - evsel selector to be tested
+ *
+ * Return %true if @evsel is a group leader or a stand-alone event
+ */
 static inline bool perf_evsel__is_group_leader(const struct perf_evsel *evsel)
 {
 	return evsel->leader == evsel;
 }
 
+/**
+ * perf_evsel__is_group_event - Return whether given evsel is a group event
+ *
+ * @evsel - evsel selector to be tested
+ *
+ * Return %true iff event group view is enabled and @evsel is a actual group
+ * leader which has other members in the group
+ */
+static inline bool perf_evsel__is_group_event(struct perf_evsel *evsel)
+{
+	if (!symbol_conf.event_group)
+		return false;
+
+	return perf_evsel__is_group_leader(evsel) && evsel->nr_members > 1;
+}
+
 struct perf_attr_details {
 	bool freq;
 	bool verbose;
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index f4bfd79ef6a7..a9b7349f7c5f 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -2789,7 +2789,7 @@ int perf_session__read_header(struct perf_session *session, int fd)
 	u64			f_id;
 	int nr_attrs, nr_ids, i, j;
 
-	session->evlist = perf_evlist__new(NULL, NULL);
+	session->evlist = perf_evlist__new();
 	if (session->evlist == NULL)
 		return -ENOMEM;
 
@@ -2940,7 +2940,7 @@ int perf_event__process_attr(union perf_event *event,
 	struct perf_evlist *evlist = *pevlist;
 
 	if (evlist == NULL) {
-		*pevlist = evlist = perf_evlist__new(NULL, NULL);
+		*pevlist = evlist = perf_evlist__new();
 		if (evlist == NULL)
 			return -ENOMEM;
 	}
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 226a4ae2f936..848331377bdb 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -177,7 +177,7 @@ struct hist_browser_timer {
 
 #ifdef NEWT_SUPPORT
 #include "../ui/keysyms.h"
-int hist_entry__tui_annotate(struct hist_entry *he, int evidx,
+int hist_entry__tui_annotate(struct hist_entry *he, struct perf_evsel *evsel,
 			     struct hist_browser_timer *hbt);
 
 int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help,
@@ -196,7 +196,8 @@ int perf_evlist__tui_browse_hists(struct perf_evlist *evlist __maybe_unused,
 
 static inline int hist_entry__tui_annotate(struct hist_entry *self
 					   __maybe_unused,
-					   int evidx __maybe_unused,
+					   struct perf_evsel *evsel
+					   __maybe_unused,
 					   struct hist_browser_timer *hbt
 					   __maybe_unused)
 {
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index efdb38e65a92..c5e3b123782b 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1003,6 +1003,17 @@ int machine__process_fork_event(struct machine *machine, union perf_event *event
 	return 0;
 }
 
+static void machine__remove_thread(struct machine *machine, struct thread *th)
+{
+	machine->last_match = NULL;
+	rb_erase(&th->rb_node, &machine->threads);
+	/*
+	 * We may have references to this thread, for instance in some hist_entry
+	 * instances, so just move them to a separate list.
+	 */
+	list_add_tail(&th->node, &machine->dead_threads);
+}
+
 int machine__process_exit_event(struct machine *machine, union perf_event *event)
 {
 	struct thread *thread = machine__find_thread(machine, event->fork.tid);
@@ -1039,17 +1050,6 @@ int machine__process_event(struct machine *machine, union perf_event *event)
 	return ret;
 }
 
-void machine__remove_thread(struct machine *machine, struct thread *th)
-{
-	machine->last_match = NULL;
-	rb_erase(&th->rb_node, &machine->threads);
-	/*
-	 * We may have references to this thread, for instance in some hist_entry
-	 * instances, so just move them to a separate list.
-	 */
-	list_add_tail(&th->node, &machine->dead_threads);
-}
-
 static bool symbol__match_parent_regex(struct symbol *sym)
 {
 	if (sym->name && !regexec(&parent_regex, sym->name, 0, NULL, 0))
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 5ac5892f2326..e0b2c00b2e75 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -97,7 +97,6 @@ static inline bool machine__is_host(struct machine *machine)
 }
 
 struct thread *machine__findnew_thread(struct machine *machine, pid_t pid);
-void machine__remove_thread(struct machine *machine, struct thread *th);
 
 size_t machine__fprintf(struct machine *machine, FILE *fp);
 
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index c84f48cf9678..6c8bb0fb189b 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -10,7 +10,7 @@
 #include "symbol.h"
 #include "cache.h"
 #include "header.h"
-#include "debugfs.h"
+#include <lk/debugfs.h>
 #include "parse-events-bison.h"
 #define YY_EXTRA_TYPE int
 #include "parse-events-flex.h"
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 49a256e6e0a2..aa04bf9c9ad7 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -40,7 +40,7 @@
 #include "color.h"
 #include "symbol.h"
 #include "thread.h"
-#include "debugfs.h"
+#include <lk/debugfs.h>
 #include "trace-event.h"	/* For __maybe_unused */
 #include "probe-event.h"
 #include "probe-finder.h"
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index 64536a993f4a..f75ae1b9900c 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -15,7 +15,6 @@ util/thread_map.c
 util/util.c
 util/xyarray.c
 util/cgroup.c
-util/debugfs.c
 util/rblist.c
 util/strlist.c
 util/sysfs.c
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index bd85280bb6e8..ab265c2cfab3 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1365,18 +1365,6 @@ size_t perf_session__fprintf(struct perf_session *session, FILE *fp)
 	return machine__fprintf(&session->machines.host, fp);
 }
 
-void perf_session__remove_thread(struct perf_session *session,
-				 struct thread *th)
-{
-	/*
-	 * FIXME: This one makes no sense, we need to remove the thread from
-	 * the machine it belongs to, perf_session can have many machines, so
-	 * doing it always on ->machines.host is wrong.  Fix when auditing all
-	 * the 'perf kvm' code.
-	 */
-	machine__remove_thread(&session->machines.host, th);
-}
-
 struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
 					      unsigned int type)
 {
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index b5c0847edfa9..6b51d47acdba 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -72,7 +72,6 @@ void perf_event__attr_swap(struct perf_event_attr *attr);
 int perf_session__create_kernel_maps(struct perf_session *self);
 
 void perf_session__set_id_hdr_size(struct perf_session *session);
-void perf_session__remove_thread(struct perf_session *self, struct thread *th);
 
 static inline
 struct machine *perf_session__find_machine(struct perf_session *self, pid_t pid)
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index 73d510269784..6b0ed322907e 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -24,6 +24,7 @@ cflags += getenv('CFLAGS', '').split()
 build_lib = getenv('PYTHON_EXTBUILD_LIB')
 build_tmp = getenv('PYTHON_EXTBUILD_TMP')
 libtraceevent = getenv('LIBTRACEEVENT')
+liblk = getenv('LIBLK')
 
 ext_sources = [f.strip() for f in file('util/python-ext-sources')
 				if len(f.strip()) > 0 and f[0] != '#']
@@ -32,7 +33,7 @@ perf = Extension('perf',
 		  sources = ext_sources,
 		  include_dirs = ['util/include'],
 		  extra_compile_args = cflags,
-		  extra_objects = [libtraceevent],
+		  extra_objects = [libtraceevent, liblk],
                  )
 
 setup(name='perf',
diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h
index f718df8a3c59..0cd8b3108084 100644
--- a/tools/perf/util/thread_map.h
+++ b/tools/perf/util/thread_map.h
@@ -21,4 +21,9 @@ void thread_map__delete(struct thread_map *threads);
 
 size_t thread_map__fprintf(struct thread_map *threads, FILE *fp);
 
+static inline int thread_map__nr(struct thread_map *threads)
+{
+	return threads ? threads->nr : 1;
+}
+
 #endif	/* __PERF_THREAD_MAP_H */
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index a8d81c35ef66..5729f434c5b1 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -38,35 +38,14 @@
 
 #include "../perf.h"
 #include "trace-event.h"
-#include "debugfs.h"
+#include <lk/debugfs.h>
 #include "evsel.h"
 
 #define VERSION "0.5"
 
-#define TRACE_CTRL	"tracing_on"
-#define TRACE		"trace"
-#define AVAILABLE	"available_tracers"
-#define CURRENT		"current_tracer"
-#define ITER_CTRL	"trace_options"
-#define MAX_LATENCY	"tracing_max_latency"
-
-unsigned int page_size;
-
 static const char *output_file = "trace.info";
 static int output_fd;
 
-struct event_list {
-	struct event_list *next;
-	const char *event;
-};
-
-struct events {
-	struct events *sibling;
-	struct events *children;
-	struct events *next;
-	char *name;
-};
-
 
 static void *malloc_or_die(unsigned int size)
 {
@@ -80,7 +59,7 @@ static void *malloc_or_die(unsigned int size)
 
 static const char *find_debugfs(void)
 {
-	const char *path = debugfs_mount(NULL);
+	const char *path = perf_debugfs_mount(NULL);
 
 	if (!path)
 		die("Your kernel not support debugfs filesystem");
@@ -131,17 +110,10 @@ static void put_tracing_file(char *file)
 	free(file);
 }
 
-static ssize_t calc_data_size;
-
 static ssize_t write_or_die(const void *buf, size_t len)
 {
 	int ret;
 
-	if (calc_data_size) {
-		calc_data_size += len;
-		return len;
-	}
-
 	ret = write(output_fd, buf, len);
 	if (ret < 0)
 		die("writing to '%s'", output_file);
@@ -457,7 +429,6 @@ static void tracing_data_header(void)
 	write_or_die(buf, 1);
 
 	/* save page_size */
-	page_size = sysconf(_SC_PAGESIZE);
 	write_or_die(&page_size, 4);
 }
 
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index 3aabcd687cd5..4454835a9ebc 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -183,43 +183,6 @@ void event_format__print(struct event_format *event,
 	trace_seq_do_printf(&s);
 }
 
-void print_trace_event(struct pevent *pevent, int cpu, void *data, int size)
-{
-	int type = trace_parse_common_type(pevent, data);
-	struct event_format *event = pevent_find_event(pevent, type);
-
-	if (!event) {
-		warning("ug! no event found for type %d", type);
-		return;
-	}
-
-	event_format__print(event, cpu, data, size);
-}
-
-void print_event(struct pevent *pevent, int cpu, void *data, int size,
-		 unsigned long long nsecs, char *comm)
-{
-	struct pevent_record record;
-	struct trace_seq s;
-	int pid;
-
-	pevent->latency_format = latency_format;
-
-	record.ts = nsecs;
-	record.cpu = cpu;
-	record.size = size;
-	record.data = data;
-	pid = pevent_data_pid(pevent, &record);
-
-	if (!pevent_pid_is_registered(pevent, pid))
-		pevent_register_comm(pevent, comm, pid);
-
-	trace_seq_init(&s);
-	pevent_print_event(pevent, &s, &record);
-	trace_seq_do_printf(&s);
-	printf("\n");
-}
-
 void parse_proc_kallsyms(struct pevent *pevent,
 			 char *file, unsigned int size __maybe_unused)
 {
diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index 3741572696af..7cb24635adf2 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -41,8 +41,6 @@
 
 static int input_fd;
 
-static int read_page;
-
 int file_bigendian;
 int host_bigendian;
 static int long_size;
@@ -287,205 +285,6 @@ static void read_event_files(struct pevent *pevent)
 	}
 }
 
-struct cpu_data {
-	unsigned long long	offset;
-	unsigned long long	size;
-	unsigned long long	timestamp;
-	struct pevent_record	*next;
-	char			*page;
-	int			cpu;
-	int			index;
-	int			page_size;
-};
-
-static struct cpu_data *cpu_data;
-
-static void update_cpu_data_index(int cpu)
-{
-	cpu_data[cpu].offset += page_size;
-	cpu_data[cpu].size -= page_size;
-	cpu_data[cpu].index = 0;
-}
-
-static void get_next_page(int cpu)
-{
-	off_t save_seek;
-	off_t ret;
-
-	if (!cpu_data[cpu].page)
-		return;
-
-	if (read_page) {
-		if (cpu_data[cpu].size <= page_size) {
-			free(cpu_data[cpu].page);
-			cpu_data[cpu].page = NULL;
-			return;
-		}
-
-		update_cpu_data_index(cpu);
-
-		/* other parts of the code may expect the pointer to not move */
-		save_seek = lseek(input_fd, 0, SEEK_CUR);
-
-		ret = lseek(input_fd, cpu_data[cpu].offset, SEEK_SET);
-		if (ret == (off_t)-1)
-			die("failed to lseek");
-		ret = read(input_fd, cpu_data[cpu].page, page_size);
-		if (ret < 0)
-			die("failed to read page");
-
-		/* reset the file pointer back */
-		lseek(input_fd, save_seek, SEEK_SET);
-
-		return;
-	}
-
-	munmap(cpu_data[cpu].page, page_size);
-	cpu_data[cpu].page = NULL;
-
-	if (cpu_data[cpu].size <= page_size)
-		return;
-
-	update_cpu_data_index(cpu);
-
-	cpu_data[cpu].page = mmap(NULL, page_size, PROT_READ, MAP_PRIVATE,
-				  input_fd, cpu_data[cpu].offset);
-	if (cpu_data[cpu].page == MAP_FAILED)
-		die("failed to mmap cpu %d at offset 0x%llx",
-		    cpu, cpu_data[cpu].offset);
-}
-
-static unsigned int type_len4host(unsigned int type_len_ts)
-{
-	if (file_bigendian)
-		return (type_len_ts >> 27) & ((1 << 5) - 1);
-	else
-		return type_len_ts & ((1 << 5) - 1);
-}
-
-static unsigned int ts4host(unsigned int type_len_ts)
-{
-	if (file_bigendian)
-		return type_len_ts & ((1 << 27) - 1);
-	else
-		return type_len_ts >> 5;
-}
-
-static int calc_index(void *ptr, int cpu)
-{
-	return (unsigned long)ptr - (unsigned long)cpu_data[cpu].page;
-}
-
-struct pevent_record *trace_peek_data(struct pevent *pevent, int cpu)
-{
-	struct pevent_record *data;
-	void *page = cpu_data[cpu].page;
-	int idx = cpu_data[cpu].index;
-	void *ptr = page + idx;
-	unsigned long long extend;
-	unsigned int type_len_ts;
-	unsigned int type_len;
-	unsigned int delta;
-	unsigned int length = 0;
-
-	if (cpu_data[cpu].next)
-		return cpu_data[cpu].next;
-
-	if (!page)
-		return NULL;
-
-	if (!idx) {
-		/* FIXME: handle header page */
-		if (header_page_ts_size != 8)
-			die("expected a long long type for timestamp");
-		cpu_data[cpu].timestamp = data2host8(pevent, ptr);
-		ptr += 8;
-		switch (header_page_size_size) {
-		case 4:
-			cpu_data[cpu].page_size = data2host4(pevent, ptr);
-			ptr += 4;
-			break;
-		case 8:
-			cpu_data[cpu].page_size = data2host8(pevent, ptr);
-			ptr += 8;
-			break;
-		default:
-			die("bad long size");
-		}
-		ptr = cpu_data[cpu].page + header_page_data_offset;
-	}
-
-read_again:
-	idx = calc_index(ptr, cpu);
-
-	if (idx >= cpu_data[cpu].page_size) {
-		get_next_page(cpu);
-		return trace_peek_data(pevent, cpu);
-	}
-
-	type_len_ts = data2host4(pevent, ptr);
-	ptr += 4;
-
-	type_len = type_len4host(type_len_ts);
-	delta = ts4host(type_len_ts);
-
-	switch (type_len) {
-	case RINGBUF_TYPE_PADDING:
-		if (!delta)
-			die("error, hit unexpected end of page");
-		length = data2host4(pevent, ptr);
-		ptr += 4;
-		length *= 4;
-		ptr += length;
-		goto read_again;
-
-	case RINGBUF_TYPE_TIME_EXTEND:
-		extend = data2host4(pevent, ptr);
-		ptr += 4;
-		extend <<= TS_SHIFT;
-		extend += delta;
-		cpu_data[cpu].timestamp += extend;
-		goto read_again;
-
-	case RINGBUF_TYPE_TIME_STAMP:
-		ptr += 12;
-		break;
-	case 0:
-		length = data2host4(pevent, ptr);
-		ptr += 4;
-		die("here! length=%d", length);
-		break;
-	default:
-		length = type_len * 4;
-		break;
-	}
-
-	cpu_data[cpu].timestamp += delta;
-
-	data = malloc_or_die(sizeof(*data));
-	memset(data, 0, sizeof(*data));
-
-	data->ts = cpu_data[cpu].timestamp;
-	data->size = length;
-	data->data = ptr;
-	ptr += length;
-
-	cpu_data[cpu].index = calc_index(ptr, cpu);
-	cpu_data[cpu].next = data;
-
-	return data;
-}
-
-struct pevent_record *trace_read_data(struct pevent *pevent, int cpu)
-{
-	struct pevent_record *data;
-
-	data = trace_peek_data(pevent, cpu);
-	cpu_data[cpu].next = NULL;
-
-	return data;
-}
-
 ssize_t trace_report(int fd, struct pevent **ppevent, bool __repipe)
 {
 	char buf[BUFSIZ];
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index a55fd37ffea1..28ccde8ba20f 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -30,13 +30,9 @@ enum {
 int bigendian(void);
 
 struct pevent *read_trace_init(int file_bigendian, int host_bigendian);
-void print_trace_event(struct pevent *pevent, int cpu, void *data, int size);
 void event_format__print(struct event_format *event,
 			 int cpu, void *data, int size);
 
-void print_event(struct pevent *pevent, int cpu, void *data, int size,
-		 unsigned long long nsecs, char *comm);
-
 int parse_ftrace_file(struct pevent *pevent, char *buf, unsigned long size);
 int parse_event_file(struct pevent *pevent,
 		     char *buf, unsigned long size, char *sys);
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 805d1f52c5b4..59d868add275 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -17,6 +17,8 @@ bool test_attr__enabled;
 bool perf_host  = true;
 bool perf_guest = false;
 
+char tracing_events_path[PATH_MAX + 1] = "/sys/kernel/debug/tracing/events";
+
 void event_attr_init(struct perf_event_attr *attr)
 {
 	if (!perf_host)
@@ -242,3 +244,28 @@ void get_term_dimensions(struct winsize *ws)
 	ws->ws_row = 25;
 	ws->ws_col = 80;
 }
+
+static void set_tracing_events_path(const char *mountpoint)
+{
+	snprintf(tracing_events_path, sizeof(tracing_events_path), "%s/%s",
+		 mountpoint, "tracing/events");
+}
+
+const char *perf_debugfs_mount(const char *mountpoint)
+{
+	const char *mnt;
+
+	mnt = debugfs_mount(mountpoint);
+	if (!mnt)
+		return NULL;
+
+	set_tracing_events_path(mnt);
+
+	return mnt;
+}
+
+void perf_debugfs_set_path(const char *mntpt)
+{
+	snprintf(debugfs_mountpoint, strlen(debugfs_mountpoint), "%s", mntpt);
+	set_tracing_events_path(mntpt);
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 09b4c26b71aa..6a0781c3a573 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -73,10 +73,14 @@
 #include <linux/magic.h>
 #include "types.h"
 #include <sys/ttydefaults.h>
+#include <lk/debugfs.h>
 
 extern const char *graph_line;
 extern const char *graph_dotted_line;
 extern char buildid_dir[];
+extern char tracing_events_path[];
+extern void perf_debugfs_set_path(const char *mountpoint);
+const char *perf_debugfs_mount(const char *mountpoint);
 
 /* On most systems <limits.h> would have given us this, but
  * not on some systems (e.g. GNU/Hurd).
@@ -274,5 +278,4 @@ extern unsigned int page_size;
 
 struct winsize;
 void get_term_dimensions(struct winsize *ws);
-
-#endif
+#endif /* GIT_COMPAT_UTIL_H */
diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include
index 2964b96aa55f..f03e681f8891 100644
--- a/tools/scripts/Makefile.include
+++ b/tools/scripts/Makefile.include
@@ -1,3 +1,4 @@
+ifneq ($(O),)
 ifeq ($(origin O), command line)
 	dummy := $(if $(shell test -d $(O) || echo $(O)),$(error O=$(O) does not exist),)
 	ABSOLUTE_O := $(shell cd $(O) ; pwd)
@@ -7,9 +8,10 @@ ifeq ($(objtree),)
 	objtree := $(O)
 endif
 endif
+endif
 
-ifneq ($(OUTPUT),)
 # check that the output directory actually exists
+ifneq ($(OUTPUT),)
 OUTDIR := $(shell cd $(OUTPUT) && /bin/pwd)
 $(if $(OUTDIR),, $(error output directory "$(OUTPUT)" does not exist))
 endif
@@ -70,7 +72,7 @@ ifndef V
 	QUIET_BISON    = @echo '   ' BISON $@;
 
 	descend = \
-		@echo '   ' DESCEND $(1); \
+		+@echo '   ' DESCEND $(1); \
 		mkdir -p $(OUTPUT)$(1) && \
 		$(MAKE) $(COMMAND_O) subdir=$(if $(subdir),$(subdir)/$(1),$(1)) $(PRINT_DIR) -C $(1) $(2)
 endif
diff --git a/tools/vm/Makefile b/tools/vm/Makefile
index 8e30e5c40f8a..24e9ddd93fa4 100644
--- a/tools/vm/Makefile
+++ b/tools/vm/Makefile
@@ -1,11 +1,22 @@
 # Makefile for vm tools
+#
+TARGETS=page-types slabinfo
+
+LK_DIR = ../lib/lk
+LIBLK = $(LK_DIR)/liblk.a
 
 CC = $(CROSS_COMPILE)gcc
-CFLAGS = -Wall -Wextra
+CFLAGS = -Wall -Wextra -I../lib/
+LDFLAGS = $(LIBLK)
+
+$(TARGETS): liblk
+
+liblk:
+	make -C $(LK_DIR)
 
-all: page-types slabinfo
 %: %.c
-	$(CC) $(CFLAGS) -o $@ $^
+	$(CC) $(CFLAGS) -o $@ $< $(LDFLAGS)
 
 clean:
 	$(RM) page-types slabinfo
+	make -C ../lib/lk clean
diff --git a/tools/vm/page-types.c b/tools/vm/page-types.c
index b76edf2f8333..71c9c2511ee7 100644
--- a/tools/vm/page-types.c
+++ b/tools/vm/page-types.c
@@ -36,7 +36,7 @@
 #include <sys/statfs.h>
 #include "../../include/uapi/linux/magic.h"
 #include "../../include/uapi/linux/kernel-page-flags.h"
-
+#include <lk/debugfs.h>
 
 #ifndef MAX_PATH
 # define MAX_PATH 256
@@ -178,7 +178,7 @@ static int		kpageflags_fd;
 static int		opt_hwpoison;
 static int		opt_unpoison;
 
-static char		hwpoison_debug_fs[MAX_PATH+1];
+static char		*hwpoison_debug_fs;
 static int		hwpoison_inject_fd;
 static int		hwpoison_forget_fd;
 
@@ -458,81 +458,6 @@ static uint64_t kpageflags_flags(uint64_t flags)
 	return flags;
 }
 
-/* verify that a mountpoint is actually a debugfs instance */
-static int debugfs_valid_mountpoint(const char *debugfs)
-{
-	struct statfs st_fs;
-
-	if (statfs(debugfs, &st_fs) < 0)
-		return -ENOENT;
-	else if (st_fs.f_type != (long) DEBUGFS_MAGIC)
-		return -ENOENT;
-
-	return 0;
-}
-
-/* find the path to the mounted debugfs */
-static const char *debugfs_find_mountpoint(void)
-{
-	const char *const *ptr;
-	char type[100];
-	FILE *fp;
-
-	ptr = debugfs_known_mountpoints;
-	while (*ptr) {
-		if (debugfs_valid_mountpoint(*ptr) == 0) {
-			strcpy(hwpoison_debug_fs, *ptr);
-			return hwpoison_debug_fs;
-		}
-		ptr++;
-	}
-
-	/* give up and parse /proc/mounts */
-	fp = fopen("/proc/mounts", "r");
-	if (fp == NULL)
-		perror("Can't open /proc/mounts for read");
-
-	while (fscanf(fp, "%*s %"
-		      STR(MAX_PATH)
-		      "s %99s %*s %*d %*d\n",
-		      hwpoison_debug_fs, type) == 2) {
-		if (strcmp(type, "debugfs") == 0)
-			break;
-	}
-	fclose(fp);
-
-	if (strcmp(type, "debugfs") != 0)
-		return NULL;
-
-	return hwpoison_debug_fs;
-}
-
-/* mount the debugfs somewhere if it's not mounted */
-
-static void debugfs_mount(void)
-{
-	const char *const *ptr;
-
-	/* see if it's already mounted */
-	if (debugfs_find_mountpoint())
-		return;
-
-	ptr = debugfs_known_mountpoints;
-	while (*ptr) {
-		if (mount(NULL, *ptr, "debugfs", 0, NULL) == 0) {
-			/* save the mountpoint */
-			strcpy(hwpoison_debug_fs, *ptr);
-			break;
-		}
-		ptr++;
-	}
-
-	if (*ptr == NULL) {
-		perror("mount debugfs");
-		exit(EXIT_FAILURE);
-	}
-}
-
 /*
  * page actions
  */
@@ -541,7 +466,11 @@ static void prepare_hwpoison_fd(void)
 {
 	char buf[MAX_PATH + 1];
 
-	debugfs_mount();
+	hwpoison_debug_fs = debugfs_mount(NULL);
+	if (!hwpoison_debug_fs) {
+		perror("mount debugfs");
+		exit(EXIT_FAILURE);
+	}
 
 	if (opt_hwpoison && !hwpoison_inject_fd) {
 		snprintf(buf, MAX_PATH, "%s/hwpoison/corrupt-pfn",