Merge tag 'v3.14-rc1' into patchwork

Linus 3.14-rc1

* tag 'v3.14-rc1': (11781 commits)
  Linus 3.14-rc1
  hpfs: optimize quad buffer loading
  hpfs: remember free space
  parisc: add flexible mmap memory layout support
  parisc: Make EWOULDBLOCK be equal to EAGAIN on parisc
  parisc: convert uapi/asm/stat.h to use native types only
  parisc: wire up sched_setattr and sched_getattr
  parisc: fix cache-flushing
  parisc/sti_console: prefer Linux fonts over built-in ROM fonts
  hwmon: Fix SENSORS_TMP102 dependencies to eliminate build errors
  hwmon: Fix SENSORS_LM75 dependencies to eliminate build errors
  tools/power turbostat: introduce -s to dump counters
  tools/power turbostat: remove unused command line option
  afs: proc cells and rootcell are writeable
  tile: remove compat_sys_lookup_dcookie declaration to fix compile error
  Revert "PCI: Remove from bus_list and release resources in pci_release_dev()"
  ARM: multi_v7_defconfig: remove redundant entries and re-enable TI_EDMA
  ARM: multi_v7_defconfig: add mvebu drivers
  clocksource: kona: Add basic use of external clock
  drivers: bus: fix CCI driver kcalloc call parameters swap
  ...

141 files changed, 4067 insertions, 2174 deletions

diff --git a/tools/perf/Documentation/perf-archive.txt b/tools/perf/Documentation/perf-archive.txt
index 5032a142853e..ac6ecbb3e669 100644
--- a/tools/perf/Documentation/perf-archive.txt
+++ b/tools/perf/Documentation/perf-archive.txt
@@ -12,9 +12,9 @@ SYNOPSIS
 
 DESCRIPTION
 -----------
-This command runs runs perf-buildid-list --with-hits, and collects the files
-with the buildids found so that analysis of perf.data contents can be possible
-on another machine.
+This command runs perf-buildid-list --with-hits, and collects the files with the
+buildids found so that analysis of perf.data contents can be possible on another
+machine.
 
 
 SEE ALSO
diff --git a/tools/perf/Documentation/perf-kvm.txt b/tools/perf/Documentation/perf-kvm.txt
index 6a06cefe9642..52276a6d2b75 100644
--- a/tools/perf/Documentation/perf-kvm.txt
+++ b/tools/perf/Documentation/perf-kvm.txt
@@ -10,9 +10,9 @@ SYNOPSIS
 [verse]
 'perf kvm' [--host] [--guest] [--guestmount=<path>
         [--guestkallsyms=<path> --guestmodules=<path> | --guestvmlinux=<path>]]
-        {top|record|report|diff|buildid-list}
+        {top|record|report|diff|buildid-list} [<options>]
 'perf kvm' [--host] [--guest] [--guestkallsyms=<path> --guestmodules=<path>
-        | --guestvmlinux=<path>] {top|record|report|diff|buildid-list|stat}
+        | --guestvmlinux=<path>] {top|record|report|diff|buildid-list|stat} [<options>]
 'perf kvm stat [record|report|live] [<options>]
 
 DESCRIPTION
@@ -24,10 +24,17 @@ There are a couple of variants of perf kvm:
   of an arbitrary workload.
 
   'perf kvm record <command>' to record the performance counter profile
-  of an arbitrary workload and save it into a perf data file. If both
-  --host and --guest are input, the perf data file name is perf.data.kvm.
-  If there is  no --host but --guest, the file name is perf.data.guest.
-  If there is no --guest but --host, the file name is perf.data.host.
+  of an arbitrary workload and save it into a perf data file. We set the
+  default behavior of perf kvm as --guest, so if neither --host nor --guest
+  is input, the perf data file name is perf.data.guest. If --host is input,
+  the perf data file name is perf.data.kvm. If you want to record data into
+  perf.data.host, please input --host --no-guest. The behaviors are shown as
+  following:
+    Default('')         ->  perf.data.guest
+    --host              ->  perf.data.kvm
+    --guest             ->  perf.data.guest
+    --host --guest      ->  perf.data.kvm
+    --host --no-guest   ->  perf.data.host
 
   'perf kvm report' to display the performance counter profile information
   recorded via perf kvm record.
@@ -37,7 +44,9 @@ There are a couple of variants of perf kvm:
 
   'perf kvm buildid-list' to  display the buildids found in a perf data file,
   so that other tools can be used to fetch packages with matching symbol tables
-  for use by perf report.
+  for use by perf report. As buildid is read from /sys/kernel/notes in os, then
+  if you want to list the buildid for guest, please make sure your perf data file
+  was captured with --guestmount in perf kvm record.
 
   'perf kvm stat <command>' to run a command and gather performance counter
   statistics.
@@ -58,14 +67,14 @@ There are a couple of variants of perf kvm:
 OPTIONS
 -------
 -i::
---input=::
+--input=<path>::
         Input file name.
 -o::
---output::
+--output=<path>::
         Output file name.
---host=::
+--host::
         Collect host side performance profile.
---guest=::
+--guest::
         Collect guest side performance profile.
 --guestmount=<path>::
         Guest os root file system mount directory. Users mounts guest os
@@ -84,6 +93,9 @@ OPTIONS
         kernel module information. Users copy it out from guest os.
 --guestvmlinux=<path>::
         Guest os kernel vmlinux.
+-v::
+--verbose::
+        Be more verbose (show counter open errors, etc).
 
 STAT REPORT OPTIONS
 -------------------
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 43b42c4f4a91..c71b0f36d9e8 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -57,6 +57,8 @@ OPTIONS
 -t::
 --tid=::
         Record events on existing thread ID (comma separated list).
+        This option also disables inheritance by default.  Enable it by adding
+        --inherit.
 
 -u::
 --uid=::
@@ -66,8 +68,7 @@ OPTIONS
 --realtime=::
         Collect data with this RT SCHED_FIFO priority.
 
--D::
---no-delay::
+--no-buffering::
         Collect data without buffering.
 
 -c::
@@ -201,11 +202,16 @@ abort events and some memory events in precise mode on modern Intel CPUs.
 --transaction::
 Record transaction flags for transaction related events.
 
---force-per-cpu::
-Force the use of per-cpu mmaps.  By default, when tasks are specified (i.e. -p,
--t or -u options) per-thread mmaps are created.  This option overrides that and
-forces per-cpu mmaps.  A side-effect of that is that inheritance is
-automatically enabled.  Add the -i option also to disable inheritance.
+--per-thread::
+Use per-thread mmaps.  By default per-cpu mmaps are created.  This option
+overrides that and uses per-thread mmaps.  A side-effect of that is that
+inheritance is automatically disabled.  --per-thread is ignored with a warning
+if combined with -a or -C options.
+
+-D::
+--delay=::
+After starting the program, wait msecs before measuring. This is useful to
+filter out the startup phase of the program, which is often very different.
 
 SEE ALSO
 --------
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 10a279871251..8eab8a4bdeb8 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -237,6 +237,15 @@ OPTIONS
         Do not show entries which have an overhead under that percent.
         (Default: 0).
 
+--header::
+        Show header information in the perf.data file.  This includes
+        various information like hostname, OS and perf version, cpu/mem
+        info, perf command line, event list and so on.  Currently only
+        --stdio output supports this feature.
+
+--header-only::
+        Show only perf.data header (forces --stdio).
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-annotate[1]
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index e9cbfcddfa3f..05f9a0a6784c 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -115,7 +115,7 @@ OPTIONS
 -f::
 --fields::
         Comma separated list of fields to print. Options are:
-        comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff.
+        comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff, srcline.
         Field list can be prepended with the type, trace, sw or hw,
         to indicate to which event type the field list applies.
         e.g., -f sw:comm,tid,time,ip,sym  and -f trace:time,cpu,trace
@@ -203,6 +203,18 @@ OPTIONS
 --show-kernel-path::
         Try to resolve the path of [kernel.kallsyms]
 
+--show-task-events
+        Display task related events (e.g. FORK, COMM, EXIT).
+
+--show-mmap-events
+        Display mmap related events (e.g. MMAP, MMAP2).
+
+--header
+        Show perf.data header.
+
+--header-only
+        Show only perf.data header.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-script-perl[1],
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 80c7da6732f2..29ee857c09c6 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -133,7 +133,7 @@ use --per-core in addition to -a. (system-wide).  The output includes the
 core number and the number of online logical processors on that physical processor.
 
 -D msecs::
---initial-delay msecs::
+--delay msecs::
 After starting the program, wait msecs before measuring. This is useful to
 filter out the startup phase of the program, which is often very different.
 
diff --git a/tools/perf/Documentation/perf-timechart.txt b/tools/perf/Documentation/perf-timechart.txt
index 3ff8bd4f0b4d..bc5990c33dc0 100644
--- a/tools/perf/Documentation/perf-timechart.txt
+++ b/tools/perf/Documentation/perf-timechart.txt
@@ -8,8 +8,7 @@ perf-timechart - Tool to visualize total system behavior during a workload
 SYNOPSIS
 --------
 [verse]
-'perf timechart' record <command>
-'perf timechart' [<options>]
+'perf timechart' [<timechart options>] {record} [<record options>]
 
 DESCRIPTION
 -----------
@@ -21,8 +20,8 @@ There are two variants of perf timechart:
   'perf timechart' to turn a trace into a Scalable Vector Graphics file,
   that can be viewed with popular SVG viewers such as 'Inkscape'.
 
-OPTIONS
--------
+TIMECHART OPTIONS
+-----------------
 -o::
 --output=::
         Select the output file (default: output.svg)
@@ -35,6 +34,9 @@ OPTIONS
 -P::
 --power-only::
         Only output the CPU power section of the diagram
+-T::
+--tasks-only::
+        Don't output processor state transitions
 -p::
 --process::
         Select the processes to display, by name or PID
@@ -54,6 +56,38 @@ $ perf timechart
 
   Written 10.2 seconds of trace to output.svg.
 
+Record system-wide timechart:
+
+  $ perf timechart record
+
+  then generate timechart and highlight 'gcc' tasks:
+
+  $ perf timechart --highlight gcc
+
+-n::
+--proc-num::
+        Print task info for at least given number of tasks.
+-t::
+--topology::
+        Sort CPUs according to topology.
+--highlight=<duration_nsecs|task_name>::
+        Highlight tasks (using different color) that run more than given
+        duration or tasks with given name. If number is given it's interpreted
+        as number of nanoseconds. If non-numeric string is given it's
+        interpreted as task name.
+
+RECORD OPTIONS
+--------------
+-P::
+--power-only::
+        Record only power-related events
+-T::
+--tasks-only::
+        Record only tasks-related events
+-g::
+--callchain::
+        Do call-graph (stack chain/backtrace) recording
+
 SEE ALSO
 --------
 linkperf:perf-record[1]
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 7de01dd79688..cdd8d4946dba 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -50,7 +50,6 @@ Default is to monitor all CPUS.
 --count-filter=<count>::
         Only display functions with more events than this.
 
--g::
 --group::
         Put the counters into a counter group.
 
@@ -143,12 +142,12 @@ Default is to monitor all CPUS.
 --asm-raw::
         Show raw instruction encoding of assembly instructions.
 
--G::
+-g::
         Enables call-graph (stack chain/backtrace) recording.
 
 --call-graph::
         Setup and enable call-graph (stack chain/backtrace) recording,
-        implies -G.
+        implies -g.
 
 --max-stack::
         Set the stack depth limit when parsing the callchain, anything
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 025de796067c..f41572d0dd76 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -1,7 +1,11 @@
 tools/perf
 tools/scripts
 tools/lib/traceevent
-tools/lib/lk
+tools/lib/api
+tools/lib/symbol/kallsyms.c
+tools/lib/symbol/kallsyms.h
+tools/include/asm/bug.h
+tools/include/linux/compiler.h
 include/linux/const.h
 include/linux/perf_event.h
 include/linux/rbtree.h
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 4835618a5608..cb2e5868c8e8 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -60,8 +60,11 @@ endef
 
 #
 # Needed if no target specified:
+# (Except for tags and TAGS targets. The reason is that the
+# Makefile does not treat tags/TAGS as targets but as files
+# and thus won't rebuilt them once they are in place.)
 #
-all:
+all tags TAGS:
         $(print_msg)
         $(make)
 
@@ -72,8 +75,16 @@ clean:
         $(make)
 
 #
+# The build-test target is not really parallel, don't print the jobs info:
+#
+build-test:
+        @$(MAKE) -f tests/make --no-print-directory
+
+#
 # All other targets get passed through:
 #
 %:
         $(print_msg)
         $(make)
+
+.PHONY: tags TAGS
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 7fc8f179cae7..7257e7e9e38a 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -76,6 +76,7 @@ $(OUTPUT)PERF-VERSION-FILE: ../../.git/HEAD
 
 CC = $(CROSS_COMPILE)gcc
 AR = $(CROSS_COMPILE)ar
+PKG_CONFIG = $(CROSS_COMPILE)pkg-config
 
 RM      = rm -f
 LN      = ln -f
@@ -86,7 +87,7 @@ FLEX    = flex
 BISON   = bison
 STRIP   = strip
 
-LK_DIR          = $(srctree)/tools/lib/lk/
+LIB_DIR          = $(srctree)/tools/lib/api/
 TRACE_EVENT_DIR = $(srctree)/tools/lib/traceevent/
 
 # include config/Makefile by default and rule out
@@ -105,7 +106,7 @@ ifeq ($(config),1)
 include config/Makefile
 endif
 
-export prefix bindir sharedir sysconfdir
+export prefix bindir sharedir sysconfdir DESTDIR
 
 # sparse is architecture-neutral, which means that we need to tell it
 # explicitly what architecture to check for. Fix this up for yours..
@@ -127,20 +128,20 @@ strip-libs = $(filter-out -l%,$(1))
 ifneq ($(OUTPUT),)
   TE_PATH=$(OUTPUT)
 ifneq ($(subdir),)
-  LK_PATH=$(OUTPUT)/../lib/lk/
+  LIB_PATH=$(OUTPUT)/../lib/api/
 else
-  LK_PATH=$(OUTPUT)
+  LIB_PATH=$(OUTPUT)
 endif
 else
   TE_PATH=$(TRACE_EVENT_DIR)
-  LK_PATH=$(LK_DIR)
+  LIB_PATH=$(LIB_DIR)
 endif
 
 LIBTRACEEVENT = $(TE_PATH)libtraceevent.a
 export LIBTRACEEVENT
 
-LIBLK = $(LK_PATH)liblk.a
-export LIBLK
+LIBAPIKFS = $(LIB_PATH)libapikfs.a
+export LIBAPIKFS
 
 # python extension build directories
 PYTHON_EXTBUILD     := $(OUTPUT)python_ext_build/
@@ -151,7 +152,7 @@ export PYTHON_EXTBUILD_LIB PYTHON_EXTBUILD_TMP
 python-clean := $(call QUIET_CLEAN, python) $(RM) -r $(PYTHON_EXTBUILD) $(OUTPUT)python/perf.so
 
 PYTHON_EXT_SRCS := $(shell grep -v ^\# util/python-ext-sources)
-PYTHON_EXT_DEPS := util/python-ext-sources util/setup.py $(LIBTRACEEVENT) $(LIBLK)
+PYTHON_EXT_DEPS := util/python-ext-sources util/setup.py $(LIBTRACEEVENT) $(LIBAPIKFS)
 
 $(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS)
         $(QUIET_GEN)CFLAGS='$(CFLAGS)' $(PYTHON_WORD) util/setup.py \
@@ -202,6 +203,7 @@ $(OUTPUT)util/pmu.o: $(OUTPUT)util/pmu-flex.c $(OUTPUT)util/pmu-bison.c
 
 LIB_FILE=$(OUTPUT)libperf.a
 
+LIB_H += ../lib/symbol/kallsyms.h
 LIB_H += ../../include/uapi/linux/perf_event.h
 LIB_H += ../../include/linux/rbtree.h
 LIB_H += ../../include/linux/list.h
@@ -210,7 +212,7 @@ LIB_H += ../../include/linux/hash.h
 LIB_H += ../../include/linux/stringify.h
 LIB_H += util/include/linux/bitmap.h
 LIB_H += util/include/linux/bitops.h
-LIB_H += util/include/linux/compiler.h
+LIB_H += ../include/linux/compiler.h
 LIB_H += util/include/linux/const.h
 LIB_H += util/include/linux/ctype.h
 LIB_H += util/include/linux/kernel.h
@@ -225,7 +227,7 @@ LIB_H += util/include/linux/string.h
 LIB_H += util/include/linux/types.h
 LIB_H += util/include/linux/linkage.h
 LIB_H += util/include/asm/asm-offsets.h
-LIB_H += util/include/asm/bug.h
+LIB_H += ../include/asm/bug.h
 LIB_H += util/include/asm/byteorder.h
 LIB_H += util/include/asm/hweight.h
 LIB_H += util/include/asm/swab.h
@@ -312,6 +314,7 @@ LIB_OBJS += $(OUTPUT)util/evlist.o
 LIB_OBJS += $(OUTPUT)util/evsel.o
 LIB_OBJS += $(OUTPUT)util/exec_cmd.o
 LIB_OBJS += $(OUTPUT)util/help.o
+LIB_OBJS += $(OUTPUT)util/kallsyms.o
 LIB_OBJS += $(OUTPUT)util/levenshtein.o
 LIB_OBJS += $(OUTPUT)util/parse-options.o
 LIB_OBJS += $(OUTPUT)util/parse-events.o
@@ -353,6 +356,7 @@ LIB_OBJS += $(OUTPUT)util/pmu-bison.o
 LIB_OBJS += $(OUTPUT)util/trace-event-read.o
 LIB_OBJS += $(OUTPUT)util/trace-event-info.o
 LIB_OBJS += $(OUTPUT)util/trace-event-scripting.o
+LIB_OBJS += $(OUTPUT)util/trace-event.o
 LIB_OBJS += $(OUTPUT)util/svghelper.o
 LIB_OBJS += $(OUTPUT)util/sort.o
 LIB_OBJS += $(OUTPUT)util/hist.o
@@ -438,7 +442,7 @@ BUILTIN_OBJS += $(OUTPUT)builtin-inject.o
 BUILTIN_OBJS += $(OUTPUT)tests/builtin-test.o
 BUILTIN_OBJS += $(OUTPUT)builtin-mem.o
 
-PERFLIBS = $(LIB_FILE) $(LIBLK) $(LIBTRACEEVENT)
+PERFLIBS = $(LIB_FILE) $(LIBAPIKFS) $(LIBTRACEEVENT)
 
 # We choose to avoid "if .. else if .. else .. endif endif"
 # because maintaining the nesting to match is a pain.  If
@@ -486,6 +490,7 @@ ifndef NO_SLANG
   LIB_OBJS += $(OUTPUT)ui/browsers/hists.o
   LIB_OBJS += $(OUTPUT)ui/browsers/map.o
   LIB_OBJS += $(OUTPUT)ui/browsers/scripts.o
+  LIB_OBJS += $(OUTPUT)ui/browsers/header.o
   LIB_OBJS += $(OUTPUT)ui/tui/setup.o
   LIB_OBJS += $(OUTPUT)ui/tui/util.o
   LIB_OBJS += $(OUTPUT)ui/tui/helpline.o
@@ -671,6 +676,9 @@ $(OUTPUT)ui/browsers/map.o: ui/browsers/map.c $(OUTPUT)PERF-CFLAGS
 $(OUTPUT)ui/browsers/scripts.o: ui/browsers/scripts.c $(OUTPUT)PERF-CFLAGS
         $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DENABLE_SLFUTURE_CONST $<
 
+$(OUTPUT)util/kallsyms.o: ../lib/symbol/kallsyms.c $(OUTPUT)PERF-CFLAGS
+        $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $<
+
 $(OUTPUT)util/rbtree.o: ../../lib/rbtree.c $(OUTPUT)PERF-CFLAGS
         $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-unused-parameter -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
 
@@ -710,26 +718,33 @@ $(LIB_FILE): $(LIB_OBJS)
 # libtraceevent.a
 TE_SOURCES = $(wildcard $(TRACE_EVENT_DIR)*.[ch])
 
-$(LIBTRACEEVENT): $(TE_SOURCES)
-        $(QUIET_SUBDIR0)$(TRACE_EVENT_DIR) $(QUIET_SUBDIR1) O=$(OUTPUT) CFLAGS="-g -Wall $(EXTRA_CFLAGS)" libtraceevent.a
+LIBTRACEEVENT_FLAGS  = $(QUIET_SUBDIR1) O=$(OUTPUT)
+LIBTRACEEVENT_FLAGS += CFLAGS="-g -Wall $(EXTRA_CFLAGS)"
+LIBTRACEEVENT_FLAGS += plugin_dir=$(plugindir_SQ)
+
+$(LIBTRACEEVENT): $(TE_SOURCES) $(OUTPUT)PERF-CFLAGS
+        $(QUIET_SUBDIR0)$(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) libtraceevent.a plugins
 
 $(LIBTRACEEVENT)-clean:
         $(call QUIET_CLEAN, libtraceevent)
         @$(MAKE) -C $(TRACE_EVENT_DIR) O=$(OUTPUT) clean >/dev/null
 
-LIBLK_SOURCES = $(wildcard $(LK_PATH)*.[ch])
+install-traceevent-plugins: $(LIBTRACEEVENT)
+        $(QUIET_SUBDIR0)$(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) install_plugins
+
+LIBAPIKFS_SOURCES = $(wildcard $(LIB_PATH)fs/*.[ch])
 
 # if subdir is set, we've been called from above so target has been built
 # already
-$(LIBLK): $(LIBLK_SOURCES)
+$(LIBAPIKFS): $(LIBAPIKFS_SOURCES)
 ifeq ($(subdir),)
-        $(QUIET_SUBDIR0)$(LK_DIR) $(QUIET_SUBDIR1) O=$(OUTPUT) liblk.a
+        $(QUIET_SUBDIR0)$(LIB_DIR) $(QUIET_SUBDIR1) O=$(OUTPUT) libapikfs.a
 endif
 
-$(LIBLK)-clean:
+$(LIBAPIKFS)-clean:
 ifeq ($(subdir),)
-        $(call QUIET_CLEAN, liblk)
-        @$(MAKE) -C $(LK_DIR) O=$(OUTPUT) clean >/dev/null
+        $(call QUIET_CLEAN, libapikfs)
+        @$(MAKE) -C $(LIB_DIR) O=$(OUTPUT) clean >/dev/null
 endif
 
 help:
@@ -785,7 +800,7 @@ cscope:
 
 ### Detect prefix changes
 TRACK_CFLAGS = $(subst ','\'',$(CFLAGS)):\
-             $(bindir_SQ):$(perfexecdir_SQ):$(template_dir_SQ):$(prefix_SQ)
+             $(bindir_SQ):$(perfexecdir_SQ):$(template_dir_SQ):$(prefix_SQ):$(plugindir_SQ)
 
 $(OUTPUT)PERF-CFLAGS: .FORCE-PERF-CFLAGS
         @FLAGS='$(TRACK_CFLAGS)'; \
@@ -840,16 +855,16 @@ ifndef NO_LIBPYTHON
                 $(INSTALL) scripts/python/*.py -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python'; \
                 $(INSTALL) scripts/python/bin/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/bin'
 endif
-        $(call QUIET_INSTALL, bash_completion-script) \
+        $(call QUIET_INSTALL, perf_completion-script) \
                 $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d'; \
-                $(INSTALL) bash_completion '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d/perf'
+                $(INSTALL) perf-completion.sh '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d/perf'
         $(call QUIET_INSTALL, tests) \
                 $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \
                 $(INSTALL) tests/attr.py '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \
                 $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'; \
                 $(INSTALL) tests/attr/* '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'
 
-install: install-bin try-install-man
+install: install-bin try-install-man install-traceevent-plugins
 
 install-python_ext:
         $(PYTHON_WORD) util/setup.py --quiet install --root='/$(DESTDIR_SQ)'
@@ -868,12 +883,11 @@ config-clean:
         $(call QUIET_CLEAN, config)
         @$(MAKE) -C config/feature-checks clean >/dev/null
 
-clean: $(LIBTRACEEVENT)-clean $(LIBLK)-clean config-clean
+clean: $(LIBTRACEEVENT)-clean $(LIBAPIKFS)-clean config-clean
         $(call QUIET_CLEAN, core-objs)  $(RM) $(LIB_OBJS) $(BUILTIN_OBJS) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf.o $(LANG_BINDINGS) $(GTK_OBJS)
         $(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf
         $(call QUIET_CLEAN, core-gen)   $(RM)  *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)PERF-CFLAGS $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex*
-        $(call QUIET_CLEAN, Documentation)
-        @$(MAKE) -C Documentation O=$(OUTPUT) clean >/dev/null
+        $(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean
         $(python-clean)
 
 #
diff --git a/tools/perf/arch/common.c b/tools/perf/arch/common.c
index aacef07ebf31..42faf369211c 100644
--- a/tools/perf/arch/common.c
+++ b/tools/perf/arch/common.c
@@ -154,8 +154,7 @@ static int perf_session_env__lookup_binutils_path(struct perf_session_env *env,
                 }
                 if (lookup_path(buf))
                         goto out;
-                free(buf);
-                buf = NULL;
+                zfree(&buf);
         }
 
         if (!strcmp(arch, "arm"))
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 4087ab19823c..0da603b79b61 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -69,15 +69,7 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel,
         if (he == NULL)
                 return -ENOMEM;
 
-        ret = 0;
-        if (he->ms.sym != NULL) {
-                struct annotation *notes = symbol__annotation(he->ms.sym);
-                if (notes->src == NULL && symbol__alloc_hist(he->ms.sym) < 0)
-                        return -ENOMEM;
-
-                ret = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
-        }
-
+        ret = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
         evsel->hists.stats.total_period += sample->period;
         hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
         return ret;
@@ -188,8 +180,7 @@ find_next:
                          * symbol, free he->ms.sym->src to signal we already
                          * processed this symbol.
                          */
-                        free(notes->src);
-                        notes->src = NULL;
+                        zfree(&notes->src);
                 }
         }
 }
@@ -241,7 +232,7 @@ static int __cmd_annotate(struct perf_annotate *ann)
                 perf_session__fprintf_dsos(session, stdout);
 
         total_nr_samples = 0;
-        list_for_each_entry(pos, &session->evlist->entries, node) {
+        evlist__for_each(session->evlist, pos) {
                 struct hists *hists = &pos->hists;
                 u32 nr_samples = hists->stats.nr_events[PERF_RECORD_SAMPLE];
 
@@ -373,7 +364,7 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
 
         if (argc) {
                 /*
-                 * Special case: if there's an argument left then assume tha
+                 * Special case: if there's an argument left then assume that
                  * it's a symbol filter:
                  */
                 if (argc > 1)
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 3b67ea2444bd..a77e31246c00 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -356,9 +356,10 @@ static struct perf_evsel *evsel_match(struct perf_evsel *evsel,
 {
         struct perf_evsel *e;
 
-        list_for_each_entry(e, &evlist->entries, node)
+        evlist__for_each(evlist, e) {
                 if (perf_evsel__match2(evsel, e))
                         return e;
+        }
 
         return NULL;
 }
@@ -367,7 +368,7 @@ static void perf_evlist__collapse_resort(struct perf_evlist *evlist)
 {
         struct perf_evsel *evsel;
 
-        list_for_each_entry(evsel, &evlist->entries, node) {
+        evlist__for_each(evlist, evsel) {
                 struct hists *hists = &evsel->hists;
 
                 hists__collapse_resort(hists, NULL);
@@ -614,7 +615,7 @@ static void data_process(void)
         struct perf_evsel *evsel_base;
         bool first = true;
 
-        list_for_each_entry(evsel_base, &evlist_base->entries, node) {
+        evlist__for_each(evlist_base, evsel_base) {
                 struct data__file *d;
                 int i;
 
@@ -654,7 +655,7 @@ static void data__free(struct data__file *d)
         for (col = 0; col < PERF_HPP_DIFF__MAX_INDEX; col++) {
                 struct diff_hpp_fmt *fmt = &d->fmt[col];
 
-                free(fmt->header);
+                zfree(&fmt->header);
         }
 }
 
@@ -769,6 +770,81 @@ static int hpp__entry_baseline(struct hist_entry *he, char *buf, size_t size)
         return ret;
 }
 
+static int __hpp__color_compare(struct perf_hpp_fmt *fmt,
+                                struct perf_hpp *hpp, struct hist_entry *he,
+                                int comparison_method)
+{
+        struct diff_hpp_fmt *dfmt =
+                container_of(fmt, struct diff_hpp_fmt, fmt);
+        struct hist_entry *pair = get_pair_fmt(he, dfmt);
+        double diff;
+        s64 wdiff;
+        char pfmt[20] = " ";
+
+        if (!pair)
+                goto dummy_print;
+
+        switch (comparison_method) {
+        case COMPUTE_DELTA:
+                if (pair->diff.computed)
+                        diff = pair->diff.period_ratio_delta;
+                else
+                        diff = compute_delta(he, pair);
+
+                if (fabs(diff) < 0.01)
+                        goto dummy_print;
+                scnprintf(pfmt, 20, "%%%+d.2f%%%%", dfmt->header_width - 1);
+                return percent_color_snprintf(hpp->buf, hpp->size,
+                                        pfmt, diff);
+        case COMPUTE_RATIO:
+                if (he->dummy)
+                        goto dummy_print;
+                if (pair->diff.computed)
+                        diff = pair->diff.period_ratio;
+                else
+                        diff = compute_ratio(he, pair);
+
+                scnprintf(pfmt, 20, "%%%d.6f", dfmt->header_width);
+                return value_color_snprintf(hpp->buf, hpp->size,
+                                        pfmt, diff);
+        case COMPUTE_WEIGHTED_DIFF:
+                if (he->dummy)
+                        goto dummy_print;
+                if (pair->diff.computed)
+                        wdiff = pair->diff.wdiff;
+                else
+                        wdiff = compute_wdiff(he, pair);
+
+                scnprintf(pfmt, 20, "%%14ld", dfmt->header_width);
+                return color_snprintf(hpp->buf, hpp->size,
+                                get_percent_color(wdiff),
+                                pfmt, wdiff);
+        default:
+                BUG_ON(1);
+        }
+dummy_print:
+        return scnprintf(hpp->buf, hpp->size, "%*s",
+                        dfmt->header_width, pfmt);
+}
+
+static int hpp__color_delta(struct perf_hpp_fmt *fmt,
+                        struct perf_hpp *hpp, struct hist_entry *he)
+{
+        return __hpp__color_compare(fmt, hpp, he, COMPUTE_DELTA);
+}
+
+static int hpp__color_ratio(struct perf_hpp_fmt *fmt,
+                        struct perf_hpp *hpp, struct hist_entry *he)
+{
+        return __hpp__color_compare(fmt, hpp, he, COMPUTE_RATIO);
+}
+
+static int hpp__color_wdiff(struct perf_hpp_fmt *fmt,
+                        struct perf_hpp *hpp, struct hist_entry *he)
+{
+        return __hpp__color_compare(fmt, hpp, he, COMPUTE_WEIGHTED_DIFF);
+}
+
 static void
 hpp__entry_unpair(struct hist_entry *he, int idx, char *buf, size_t size)
 {
@@ -940,8 +1016,22 @@ static void data__hpp_register(struct data__file *d, int idx)
         fmt->entry  = hpp__entry_global;
 
         /* TODO more colors */
-        if (idx == PERF_HPP_DIFF__BASELINE)
+        switch (idx) {
+        case PERF_HPP_DIFF__BASELINE:
                 fmt->color = hpp__color_baseline;
+                break;
+        case PERF_HPP_DIFF__DELTA:
+                fmt->color = hpp__color_delta;
+                break;
+        case PERF_HPP_DIFF__RATIO:
+                fmt->color = hpp__color_ratio;
+                break;
+        case PERF_HPP_DIFF__WEIGHTED_DIFF:
+                fmt->color = hpp__color_wdiff;
+                break;
+        default:
+                break;
+        }
 
         init_header(d, dfmt);
         perf_hpp__column_register(fmt);
@@ -1000,8 +1090,7 @@ static int data_init(int argc, const char **argv)
                         data__files_cnt = argc;
                         use_default = false;
                 }
-        } else if (symbol_conf.default_guest_vmlinux_name ||
-                   symbol_conf.default_guest_kallsyms) {
+        } else if (perf_guest) {
                 defaults[0] = "perf.data.host";
                 defaults[1] = "perf.data.guest";
         }
diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c
index 20b0f12763b0..c99e0de7e54a 100644
--- a/tools/perf/builtin-evlist.c
+++ b/tools/perf/builtin-evlist.c
@@ -29,7 +29,7 @@ static int __cmd_evlist(const char *file_name, struct perf_attr_details *details
         if (session == NULL)
                 return -ENOMEM;
 
-        list_for_each_entry(pos, &session->evlist->entries, node)
+        evlist__for_each(session->evlist, pos)
                 perf_evsel__fprintf(pos, details, stdout);
 
         perf_session__delete(session);
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 6a2508589460..b3466018bbd7 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -22,14 +22,13 @@
 #include <linux/list.h>
 
 struct perf_inject {
-        struct perf_tool tool;
-        bool             build_ids;
-        bool             sched_stat;
-        const char       *input_name;
-        int              pipe_output,
-                         output;
-        u64              bytes_written;
-        struct list_head samples;
+        struct perf_tool        tool;
+        bool                    build_ids;
+        bool                    sched_stat;
+        const char              *input_name;
+        struct perf_data_file   output;
+        u64                     bytes_written;
+        struct list_head        samples;
 };
 
 struct event_entry {
@@ -42,21 +41,14 @@ static int perf_event__repipe_synth(struct perf_tool *tool,
                                     union perf_event *event)
 {
         struct perf_inject *inject = container_of(tool, struct perf_inject, tool);
-        uint32_t size;
-        void *buf = event;
+        ssize_t size;
 
-        size = event->header.size;
-
-        while (size) {
-                int ret = write(inject->output, buf, size);
-                if (ret < 0)
-                        return -errno;
-
-                size -= ret;
-                buf += ret;
-                inject->bytes_written += ret;
-        }
+        size = perf_data_file__write(&inject->output, event,
+                                     event->header.size);
+        if (size < 0)
+                return -errno;
 
+        inject->bytes_written += size;
         return 0;
 }
 
@@ -80,7 +72,7 @@ static int perf_event__repipe_attr(struct perf_tool *tool,
         if (ret)
                 return ret;
 
-        if (!inject->pipe_output)
+        if (&inject->output.is_pipe)
                 return 0;
 
         return perf_event__repipe_synth(tool, event);
@@ -355,6 +347,7 @@ static int __cmd_inject(struct perf_inject *inject)
                 .path = inject->input_name,
                 .mode = PERF_DATA_MODE_READ,
         };
+        struct perf_data_file *file_out = &inject->output;
 
         signal(SIGINT, sig_handler);
 
@@ -376,7 +369,7 @@ static int __cmd_inject(struct perf_inject *inject)
 
                 inject->tool.ordered_samples = true;
 
-                list_for_each_entry(evsel, &session->evlist->entries, node) {
+                evlist__for_each(session->evlist, evsel) {
                         const char *name = perf_evsel__name(evsel);
 
                         if (!strcmp(name, "sched:sched_switch")) {
@@ -391,14 +384,14 @@ static int __cmd_inject(struct perf_inject *inject)
                 }
         }
 
-        if (!inject->pipe_output)
-                lseek(inject->output, session->header.data_offset, SEEK_SET);
+        if (!file_out->is_pipe)
+                lseek(file_out->fd, session->header.data_offset, SEEK_SET);
 
         ret = perf_session__process_events(session, &inject->tool);
 
-        if (!inject->pipe_output) {
+        if (!file_out->is_pipe) {
                 session->header.data_size = inject->bytes_written;
-                perf_session__write_header(session, session->evlist, inject->output, true);
+                perf_session__write_header(session, session->evlist, file_out->fd, true);
         }
 
         perf_session__delete(session);
@@ -427,14 +420,17 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
                 },
                 .input_name  = "-",
                 .samples = LIST_HEAD_INIT(inject.samples),
+                .output = {
+                        .path = "-",
+                        .mode = PERF_DATA_MODE_WRITE,
+                },
         };
-        const char *output_name = "-";
         const struct option options[] = {
                 OPT_BOOLEAN('b', "build-ids", &inject.build_ids,
                             "Inject build-ids into the output stream"),
                 OPT_STRING('i', "input", &inject.input_name, "file",
                            "input file name"),
-                OPT_STRING('o', "output", &output_name, "file",
+                OPT_STRING('o', "output", &inject.output.path, "file",
                            "output file name"),
                 OPT_BOOLEAN('s', "sched-stat", &inject.sched_stat,
                             "Merge sched-stat and sched-switch for getting events "
@@ -456,16 +452,9 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
         if (argc)
                 usage_with_options(inject_usage, options);
 
-        if (!strcmp(output_name, "-")) {
-                inject.pipe_output = 1;
-                inject.output = STDOUT_FILENO;
-        } else {
-                inject.output = open(output_name, O_CREAT | O_WRONLY | O_TRUNC,
-                                                  S_IRUSR | S_IWUSR);
-                if (inject.output < 0) {
-                        perror("failed to create output file");
-                        return -1;
-                }
+        if (perf_data_file__open(&inject.output)) {
+                perror("failed to create output file");
+                return -1;
         }
 
         if (symbol__init() < 0)
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index f8bf5f244d77..a7350519c63f 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -13,7 +13,7 @@
 #include "util/parse-options.h"
 #include "util/trace-event.h"
 #include "util/debug.h"
-#include <lk/debugfs.h>
+#include <api/fs/debugfs.h>
 #include "util/tool.h"
 #include "util/stat.h"
 #include "util/top.h"
@@ -89,7 +89,7 @@ struct exit_reasons_table {
 
 struct perf_kvm_stat {
         struct perf_tool    tool;
-        struct perf_record_opts opts;
+        struct record_opts  opts;
         struct perf_evlist  *evlist;
         struct perf_session *session;
 
@@ -1158,9 +1158,7 @@ out:
         if (kvm->timerfd >= 0)
                 close(kvm->timerfd);
 
-        if (pollfds)
-                free(pollfds);
-
+        free(pollfds);
         return err;
 }
 
@@ -1176,7 +1174,7 @@ static int kvm_live_open_events(struct perf_kvm_stat *kvm)
          * Note: exclude_{guest,host} do not apply here.
          *       This command processes KVM tracepoints from host only
          */
-        list_for_each_entry(pos, &evlist->entries, node) {
+        evlist__for_each(evlist, pos) {
                 struct perf_event_attr *attr = &pos->attr;
 
                 /* make sure these *are* set */
@@ -1232,7 +1230,7 @@ static int read_events(struct perf_kvm_stat *kvm)
                 .ordered_samples        = true,
         };
         struct perf_data_file file = {
-                .path = input_name,
+                .path = kvm->file_name,
                 .mode = PERF_DATA_MODE_READ,
         };
 
@@ -1558,10 +1556,8 @@ out:
         if (kvm->session)
                 perf_session__delete(kvm->session);
         kvm->session = NULL;
-        if (kvm->evlist) {
-                perf_evlist__delete_maps(kvm->evlist);
+        if (kvm->evlist)
                 perf_evlist__delete(kvm->evlist);
-        }
 
         return err;
 }
@@ -1690,6 +1686,8 @@ int cmd_kvm(int argc, const char **argv, const char *prefix __maybe_unused)
                            "file", "file saving guest os /proc/kallsyms"),
                 OPT_STRING(0, "guestmodules", &symbol_conf.default_guest_modules,
                            "file", "file saving guest os /proc/modules"),
+                OPT_INCR('v', "verbose", &verbose,
+                            "be more verbose (show counter open errors, etc)"),
                 OPT_END()
         };
 
@@ -1711,12 +1709,7 @@ int cmd_kvm(int argc, const char **argv, const char *prefix __maybe_unused)
                 perf_guest = 1;
 
         if (!file_name) {
-                if (perf_host && !perf_guest)
-                        file_name = strdup("perf.data.host");
-                else if (!perf_host && perf_guest)
-                        file_name = strdup("perf.data.guest");
-                else
-                        file_name = strdup("perf.data.kvm");
+                file_name = get_filename_for_perf_kvm();
 
                 if (!file_name) {
                         pr_err("Failed to allocate memory for filename\n");
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index 31c00f186da1..2e3ade69a58e 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -62,7 +62,6 @@ static int
 dump_raw_samples(struct perf_tool *tool,
                  union perf_event *event,
                  struct perf_sample *sample,
-                 struct perf_evsel *evsel __maybe_unused,
                  struct machine *machine)
 {
         struct perf_mem *mem = container_of(tool, struct perf_mem, tool);
@@ -112,10 +111,10 @@ dump_raw_samples(struct perf_tool *tool,
 static int process_sample_event(struct perf_tool *tool,
                                 union perf_event *event,
                                 struct perf_sample *sample,
-                                struct perf_evsel *evsel,
+                                struct perf_evsel *evsel __maybe_unused,
                                 struct machine *machine)
 {
-        return dump_raw_samples(tool, event, sample, evsel, machine);
+        return dump_raw_samples(tool, event, sample, machine);
 }
 
 static int report_raw_events(struct perf_mem *mem)
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index 6ea9e85bdc00..78948882e3de 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 <lk/debugfs.h>
+#include <api/fs/debugfs.h>
 #include "util/parse-options.h"
 #include "util/probe-finder.h"
 #include "util/probe-event.h"
@@ -59,7 +59,7 @@ static struct {
         struct perf_probe_event events[MAX_PROBES];
         struct strlist *dellist;
         struct line_range line_range;
-        const char *target;
+        char *target;
         int max_probe_points;
         struct strfilter *filter;
 } params;
@@ -98,7 +98,10 @@ static int set_target(const char *ptr)
          * short module name.
          */
         if (!params.target && ptr && *ptr == '/') {
-                params.target = ptr;
+                params.target = strdup(ptr);
+                if (!params.target)
+                        return -ENOMEM;
+
                 found = 1;
                 buf = ptr + (strlen(ptr) - 3);
 
@@ -116,6 +119,9 @@ static int parse_probe_event_argv(int argc, const char **argv)
         char *buf;
 
         found_target = set_target(argv[0]);
+        if (found_target < 0)
+                return found_target;
+
         if (found_target && argc == 1)
                 return 0;
 
@@ -169,6 +175,7 @@ static int opt_set_target(const struct option *opt, const char *str,
                         int unset __maybe_unused)
 {
         int ret = -ENOENT;
+        char *tmp;
 
         if  (str && !params.target) {
                 if (!strcmp(opt->long_name, "exec"))
@@ -180,7 +187,19 @@ static int opt_set_target(const struct option *opt, const char *str,
                 else
                         return ret;
 
-                params.target = str;
+                /* Expand given path to absolute path, except for modulename */
+                if (params.uprobes || strchr(str, '/')) {
+                        tmp = realpath(str, NULL);
+                        if (!tmp) {
+                                pr_warning("Failed to get the absolute path of %s: %m\n", str);
+                                return ret;
+                        }
+                } else {
+                        tmp = strdup(str);
+                        if (!tmp)
+                                return -ENOMEM;
+                }
+                params.target = tmp;
                 ret = 0;
         }
 
@@ -204,7 +223,6 @@ static int opt_show_lines(const struct option *opt __maybe_unused,
 
         params.show_lines = true;
         ret = parse_line_range_desc(str, &params.line_range);
-        INIT_LIST_HEAD(&params.line_range.line_list);
 
         return ret;
 }
@@ -250,7 +268,28 @@ static int opt_set_filter(const struct option *opt __maybe_unused,
         return 0;
 }
 
-int cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
+static void init_params(void)
+{
+        line_range__init(&params.line_range);
+}
+
+static void cleanup_params(void)
+{
+        int i;
+
+        for (i = 0; i < params.nevents; i++)
+                clear_perf_probe_event(params.events + i);
+        if (params.dellist)
+                strlist__delete(params.dellist);
+        line_range__clear(&params.line_range);
+        free(params.target);
+        if (params.filter)
+                strfilter__delete(params.filter);
+        memset(&params, 0, sizeof(params));
+}
+
+static int
+__cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 {
         const char * const probe_usage[] = {
                 "perf probe [<options>] 'PROBEDEF' ['PROBEDEF' ...]",
@@ -404,6 +443,7 @@ int cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
                 ret = show_available_funcs(params.target, params.filter,
                                         params.uprobes);
                 strfilter__delete(params.filter);
+                params.filter = NULL;
                 if (ret < 0)
                         pr_err("  Error: Failed to show functions."
                                " (%d)\n", ret);
@@ -411,7 +451,7 @@ int cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
         }
 
 #ifdef HAVE_DWARF_SUPPORT
-        if (params.show_lines && !params.uprobes) {
+        if (params.show_lines) {
                 if (params.mod_events) {
                         pr_err("  Error: Don't use --line with"
                                " --add/--del.\n");
@@ -443,6 +483,7 @@ int cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
                                           params.filter,
                                           params.show_ext_vars);
                 strfilter__delete(params.filter);
+                params.filter = NULL;
                 if (ret < 0)
                         pr_err("  Error: Failed to show vars. (%d)\n", ret);
                 return ret;
@@ -451,7 +492,6 @@ int cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 
         if (params.dellist) {
                 ret = del_perf_probe_events(params.dellist);
-                strlist__delete(params.dellist);
                 if (ret < 0) {
                         pr_err("  Error: Failed to delete events. (%d)\n", ret);
                         return ret;
@@ -470,3 +510,14 @@ int cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
         }
         return 0;
 }
+
+int cmd_probe(int argc, const char **argv, const char *prefix)
+{
+        int ret;
+
+        init_params();
+        ret = __cmd_probe(argc, argv, prefix);
+        cleanup_params();
+
+        return ret;
+}
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 7c8020a32784..3c394bf16fa8 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -62,9 +62,9 @@ static void __handle_on_exit_funcs(void)
 }
 #endif
 
-struct perf_record {
+struct record {
         struct perf_tool        tool;
-        struct perf_record_opts opts;
+        struct record_opts      opts;
         u64                     bytes_written;
         struct perf_data_file   file;
         struct perf_evlist      *evlist;
@@ -76,46 +76,27 @@ struct perf_record {
         long                    samples;
 };
 
-static int do_write_output(struct perf_record *rec, void *buf, size_t size)
+static int record__write(struct record *rec, void *bf, size_t size)
 {
-        struct perf_data_file *file = &rec->file;
-
-        while (size) {
-                ssize_t ret = write(file->fd, buf, size);
-
-                if (ret < 0) {
-                        pr_err("failed to write perf data, error: %m\n");
-                        return -1;
-                }
-
-                size -= ret;
-                buf += ret;
-
-                rec->bytes_written += ret;
+        if (perf_data_file__write(rec->session->file, bf, size) < 0) {
+                pr_err("failed to write perf data, error: %m\n");
+                return -1;
         }
 
+        rec->bytes_written += size;
         return 0;
 }
 
-static int write_output(struct perf_record *rec, void *buf, size_t size)
-{
-        return do_write_output(rec, buf, size);
-}
-
 static int process_synthesized_event(struct perf_tool *tool,
                                      union perf_event *event,
                                      struct perf_sample *sample __maybe_unused,
                                      struct machine *machine __maybe_unused)
 {
-        struct perf_record *rec = container_of(tool, struct perf_record, tool);
-        if (write_output(rec, event, event->header.size) < 0)
-                return -1;
-
-        return 0;
+        struct record *rec = container_of(tool, struct record, tool);
+        return record__write(rec, event, event->header.size);
 }
 
-static int perf_record__mmap_read(struct perf_record *rec,
-                                   struct perf_mmap *md)
+static int record__mmap_read(struct record *rec, struct perf_mmap *md)
 {
         unsigned int head = perf_mmap__read_head(md);
         unsigned int old = md->prev;
@@ -136,7 +117,7 @@ static int perf_record__mmap_read(struct perf_record *rec,
                 size = md->mask + 1 - (old & md->mask);
                 old += size;
 
-                if (write_output(rec, buf, size) < 0) {
+                if (record__write(rec, buf, size) < 0) {
                         rc = -1;
                         goto out;
                 }
@@ -146,7 +127,7 @@ static int perf_record__mmap_read(struct perf_record *rec,
         size = head - old;
         old += size;
 
-        if (write_output(rec, buf, size) < 0) {
+        if (record__write(rec, buf, size) < 0) {
                 rc = -1;
                 goto out;
         }
@@ -171,9 +152,9 @@ static void sig_handler(int sig)
         signr = sig;
 }
 
-static void perf_record__sig_exit(int exit_status __maybe_unused, void *arg)
+static void record__sig_exit(int exit_status __maybe_unused, void *arg)
 {
-        struct perf_record *rec = arg;
+        struct record *rec = arg;
         int status;
 
         if (rec->evlist->workload.pid > 0) {
@@ -191,18 +172,18 @@ static void perf_record__sig_exit(int exit_status __maybe_unused, void *arg)
         signal(signr, SIG_DFL);
 }
 
-static int perf_record__open(struct perf_record *rec)
+static int record__open(struct record *rec)
 {
         char msg[512];
         struct perf_evsel *pos;
         struct perf_evlist *evlist = rec->evlist;
         struct perf_session *session = rec->session;
-        struct perf_record_opts *opts = &rec->opts;
+        struct record_opts *opts = &rec->opts;
         int rc = 0;
 
         perf_evlist__config(evlist, opts);
 
-        list_for_each_entry(pos, &evlist->entries, node) {
+        evlist__for_each(evlist, pos) {
 try_again:
                 if (perf_evsel__open(pos, evlist->cpus, evlist->threads) < 0) {
                         if (perf_evsel__fallback(pos, errno, msg, sizeof(msg))) {
@@ -232,7 +213,7 @@ try_again:
                                "Consider increasing "
                                "/proc/sys/kernel/perf_event_mlock_kb,\n"
                                "or try again with a smaller value of -m/--mmap_pages.\n"
-                               "(current value: %d)\n", opts->mmap_pages);
+                               "(current value: %u)\n", opts->mmap_pages);
                         rc = -errno;
                 } else {
                         pr_err("failed to mmap with %d (%s)\n", errno, strerror(errno));
@@ -247,7 +228,7 @@ out:
         return rc;
 }
 
-static int process_buildids(struct perf_record *rec)
+static int process_buildids(struct record *rec)
 {
         struct perf_data_file *file  = &rec->file;
         struct perf_session *session = rec->session;
@@ -262,9 +243,9 @@ static int process_buildids(struct perf_record *rec)
                                               size, &build_id__mark_dso_hit_ops);
 }
 
-static void perf_record__exit(int status, void *arg)
+static void record__exit(int status, void *arg)
 {
-        struct perf_record *rec = arg;
+        struct record *rec = arg;
         struct perf_data_file *file = &rec->file;
 
         if (status != 0)
@@ -320,14 +301,14 @@ static struct perf_event_header finished_round_event = {
         .type = PERF_RECORD_FINISHED_ROUND,
 };
 
-static int perf_record__mmap_read_all(struct perf_record *rec)
+static int record__mmap_read_all(struct record *rec)
 {
         int i;
         int rc = 0;
 
         for (i = 0; i < rec->evlist->nr_mmaps; i++) {
                 if (rec->evlist->mmap[i].base) {
-                        if (perf_record__mmap_read(rec, &rec->evlist->mmap[i]) != 0) {
+                        if (record__mmap_read(rec, &rec->evlist->mmap[i]) != 0) {
                                 rc = -1;
                                 goto out;
                         }
@@ -335,16 +316,14 @@ static int perf_record__mmap_read_all(struct perf_record *rec)
         }
 
         if (perf_header__has_feat(&rec->session->header, HEADER_TRACING_DATA))
-                rc = write_output(rec, &finished_round_event,
-                                  sizeof(finished_round_event));
+                rc = record__write(rec, &finished_round_event, sizeof(finished_round_event));
 
 out:
         return rc;
 }
 
-static void perf_record__init_features(struct perf_record *rec)
+static void record__init_features(struct record *rec)
 {
-        struct perf_evlist *evsel_list = rec->evlist;
         struct perf_session *session = rec->session;
         int feat;
 
@@ -354,32 +333,46 @@ static void perf_record__init_features(struct perf_record *rec)
         if (rec->no_buildid)
                 perf_header__clear_feat(&session->header, HEADER_BUILD_ID);
 
-        if (!have_tracepoints(&evsel_list->entries))
+        if (!have_tracepoints(&rec->evlist->entries))
                 perf_header__clear_feat(&session->header, HEADER_TRACING_DATA);
 
         if (!rec->opts.branch_stack)
                 perf_header__clear_feat(&session->header, HEADER_BRANCH_STACK);
 }
 
-static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
+static volatile int workload_exec_errno;
+
+/*
+ * perf_evlist__prepare_workload will send a SIGUSR1
+ * if the fork fails, since we asked by setting its
+ * want_signal to true.
+ */
+static void workload_exec_failed_signal(int signo, siginfo_t *info,
+                                        void *ucontext __maybe_unused)
+{
+        workload_exec_errno = info->si_value.sival_int;
+        done = 1;
+        signr = signo;
+        child_finished = 1;
+}
+
+static int __cmd_record(struct record *rec, int argc, const char **argv)
 {
         int err;
         unsigned long waking = 0;
         const bool forks = argc > 0;
         struct machine *machine;
         struct perf_tool *tool = &rec->tool;
-        struct perf_record_opts *opts = &rec->opts;
-        struct perf_evlist *evsel_list = rec->evlist;
+        struct record_opts *opts = &rec->opts;
         struct perf_data_file *file = &rec->file;
         struct perf_session *session;
         bool disabled = false;
 
         rec->progname = argv[0];
 
-        on_exit(perf_record__sig_exit, rec);
+        on_exit(record__sig_exit, rec);
         signal(SIGCHLD, sig_handler);
         signal(SIGINT, sig_handler);
-        signal(SIGUSR1, sig_handler);
         signal(SIGTERM, sig_handler);
 
         session = perf_session__new(file, false, NULL);
@@ -390,37 +383,37 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
 
         rec->session = session;
 
-        perf_record__init_features(rec);
+        record__init_features(rec);
 
         if (forks) {
-                err = perf_evlist__prepare_workload(evsel_list, &opts->target,
+                err = perf_evlist__prepare_workload(rec->evlist, &opts->target,
                                                     argv, file->is_pipe,
-                                                    true);
+                                                    workload_exec_failed_signal);
                 if (err < 0) {
                         pr_err("Couldn't run the workload!\n");
                         goto out_delete_session;
                 }
         }
 
-        if (perf_record__open(rec) != 0) {
+        if (record__open(rec) != 0) {
                 err = -1;
                 goto out_delete_session;
         }
 
-        if (!evsel_list->nr_groups)
+        if (!rec->evlist->nr_groups)
                 perf_header__clear_feat(&session->header, HEADER_GROUP_DESC);
 
         /*
-         * perf_session__delete(session) will be called at perf_record__exit()
+         * perf_session__delete(session) will be called at record__exit()
          */
-        on_exit(perf_record__exit, rec);
+        on_exit(record__exit, rec);
 
         if (file->is_pipe) {
                 err = perf_header__write_pipe(file->fd);
                 if (err < 0)
                         goto out_delete_session;
         } else {
-                err = perf_session__write_header(session, evsel_list,
+                err = perf_session__write_header(session, rec->evlist,
                                                  file->fd, false);
                 if (err < 0)
                         goto out_delete_session;
@@ -444,7 +437,7 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
                         goto out_delete_session;
                 }
 
-                if (have_tracepoints(&evsel_list->entries)) {
+                if (have_tracepoints(&rec->evlist->entries)) {
                         /*
                          * FIXME err <= 0 here actually means that
                          * there were no tracepoints so its not really
@@ -453,7 +446,7 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
                          * return this more properly and also
                          * propagate errors that now are calling die()
                          */
-                        err = perf_event__synthesize_tracing_data(tool, file->fd, evsel_list,
+                        err = perf_event__synthesize_tracing_data(tool, file->fd, rec->evlist,
                                                                   process_synthesized_event);
                         if (err <= 0) {
                                 pr_err("Couldn't record tracing data.\n");
@@ -485,7 +478,7 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
                                          perf_event__synthesize_guest_os, tool);
         }
 
-        err = __machine__synthesize_threads(machine, tool, &opts->target, evsel_list->threads,
+        err = __machine__synthesize_threads(machine, tool, &opts->target, rec->evlist->threads,
                                             process_synthesized_event, opts->sample_address);
         if (err != 0)
                 goto out_delete_session;
@@ -506,19 +499,24 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
          * (apart from group members) have enable_on_exec=1 set,
          * so don't spoil it by prematurely enabling them.
          */
-        if (!target__none(&opts->target))
-                perf_evlist__enable(evsel_list);
+        if (!target__none(&opts->target) && !opts->initial_delay)
+                perf_evlist__enable(rec->evlist);
 
         /*
          * Let the child rip
          */
         if (forks)
-                perf_evlist__start_workload(evsel_list);
+                perf_evlist__start_workload(rec->evlist);
+
+        if (opts->initial_delay) {
+                usleep(opts->initial_delay * 1000);
+                perf_evlist__enable(rec->evlist);
+        }
 
         for (;;) {
                 int hits = rec->samples;
 
-                if (perf_record__mmap_read_all(rec) < 0) {
+                if (record__mmap_read_all(rec) < 0) {
                         err = -1;
                         goto out_delete_session;
                 }
@@ -526,7 +524,7 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
                 if (hits == rec->samples) {
                         if (done)
                                 break;
-                        err = poll(evsel_list->pollfd, evsel_list->nr_fds, -1);
+                        err = poll(rec->evlist->pollfd, rec->evlist->nr_fds, -1);
                         waking++;
                 }
 
@@ -536,11 +534,19 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
                  * disable events in this case.
                  */
                 if (done && !disabled && !target__none(&opts->target)) {
-                        perf_evlist__disable(evsel_list);
+                        perf_evlist__disable(rec->evlist);
                         disabled = true;
                 }
         }
 
+        if (forks && workload_exec_errno) {
+                char msg[512];
+                const char *emsg = strerror_r(workload_exec_errno, msg, sizeof(msg));
+                pr_err("Workload failed: %s\n", emsg);
+                err = -1;
+                goto out_delete_session;
+        }
+
         if (quiet || signr == SIGUSR1)
                 return 0;
 
@@ -677,7 +683,7 @@ static int get_stack_size(char *str, unsigned long *_size)
 }
 #endif /* HAVE_LIBUNWIND_SUPPORT */
 
-int record_parse_callchain(const char *arg, struct perf_record_opts *opts)
+int record_parse_callchain(const char *arg, struct record_opts *opts)
 {
         char *tok, *name, *saveptr = NULL;
         char *buf;
@@ -733,7 +739,7 @@ int record_parse_callchain(const char *arg, struct perf_record_opts *opts)
         return ret;
 }
 
-static void callchain_debug(struct perf_record_opts *opts)
+static void callchain_debug(struct record_opts *opts)
 {
         pr_debug("callchain: type %d\n", opts->call_graph);
 
@@ -746,7 +752,7 @@ int record_parse_callchain_opt(const struct option *opt,
                                const char *arg,
                                int unset)
 {
-        struct perf_record_opts *opts = opt->value;
+        struct record_opts *opts = opt->value;
         int ret;
 
         /* --no-call-graph */
@@ -767,7 +773,7 @@ int record_callchain_opt(const struct option *opt,
                          const char *arg __maybe_unused,
                          int unset __maybe_unused)
 {
-        struct perf_record_opts *opts = opt->value;
+        struct record_opts *opts = opt->value;
 
         if (opts->call_graph == CALLCHAIN_NONE)
                 opts->call_graph = CALLCHAIN_FP;
@@ -783,8 +789,8 @@ static const char * const record_usage[] = {
 };
 
 /*
- * XXX Ideally would be local to cmd_record() and passed to a perf_record__new
- * because we need to have access to it in perf_record__exit, that is called
+ * XXX Ideally would be local to cmd_record() and passed to a record__new
+ * because we need to have access to it in record__exit, that is called
  * after cmd_record() exits, but since record_options need to be accessible to
  * builtin-script, leave it here.
  *
@@ -792,7 +798,7 @@ static const char * const record_usage[] = {
  *
  * Just say no to tons of global variables, sigh.
  */
-static struct perf_record record = {
+static struct record record = {
         .opts = {
                 .mmap_pages          = UINT_MAX,
                 .user_freq           = UINT_MAX,
@@ -800,6 +806,7 @@ static struct perf_record record = {
                 .freq                = 4000,
                 .target              = {
                         .uses_mmap   = true,
+                        .default_per_cpu = true,
                 },
         },
 };
@@ -815,7 +822,7 @@ const char record_callchain_help[] = CALLCHAIN_HELP "fp";
 /*
  * XXX Will stay a global variable till we fix builtin-script.c to stop messing
  * with it and switch to use the library functions in perf_evlist that came
- * from builtin-record.c, i.e. use perf_record_opts,
+ * from builtin-record.c, i.e. use record_opts,
  * perf_evlist__prepare_workload, etc instead of fork+exec'in 'perf record',
  * using pipes, etc.
  */
@@ -831,7 +838,7 @@ const struct option record_options[] = {
                     "record events on existing thread id"),
         OPT_INTEGER('r', "realtime", &record.realtime_prio,
                     "collect data with this RT SCHED_FIFO priority"),
-        OPT_BOOLEAN('D', "no-delay", &record.opts.no_delay,
+        OPT_BOOLEAN(0, "no-buffering", &record.opts.no_buffering,
                     "collect data without buffering"),
         OPT_BOOLEAN('R', "raw-samples", &record.opts.raw_samples,
                     "collect raw sample records from all opened counters"),
@@ -842,8 +849,9 @@ const struct option record_options[] = {
         OPT_U64('c', "count", &record.opts.user_interval, "event period to sample"),
         OPT_STRING('o', "output", &record.file.path, "file",
                     "output file name"),
-        OPT_BOOLEAN('i', "no-inherit", &record.opts.no_inherit,
-                    "child tasks do not inherit counters"),
+        OPT_BOOLEAN_SET('i', "no-inherit", &record.opts.no_inherit,
+                        &record.opts.no_inherit_set,
+                        "child tasks do not inherit counters"),
         OPT_UINTEGER('F', "freq", &record.opts.user_freq, "profile at this frequency"),
         OPT_CALLBACK('m', "mmap-pages", &record.opts.mmap_pages, "pages",
                      "number of mmap data pages",
@@ -874,6 +882,8 @@ const struct option record_options[] = {
         OPT_CALLBACK('G', "cgroup", &record.evlist, "name",
                      "monitor event in cgroup name only",
                      parse_cgroups),
+        OPT_UINTEGER('D', "delay", &record.opts.initial_delay,
+                  "ms to wait before starting measurement after program start"),
         OPT_STRING('u', "uid", &record.opts.target.uid_str, "user",
                    "user to profile"),
 
@@ -888,24 +898,21 @@ const struct option record_options[] = {
                     "sample by weight (on special events only)"),
         OPT_BOOLEAN(0, "transaction", &record.opts.sample_transaction,
                     "sample transaction flags (special events only)"),
-        OPT_BOOLEAN(0, "force-per-cpu", &record.opts.target.force_per_cpu,
-                    "force the use of per-cpu mmaps"),
+        OPT_BOOLEAN(0, "per-thread", &record.opts.target.per_thread,
+                    "use per-thread mmaps"),
         OPT_END()
 };
 
 int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 {
         int err = -ENOMEM;
-        struct perf_evlist *evsel_list;
-        struct perf_record *rec = &record;
+        struct record *rec = &record;
         char errbuf[BUFSIZ];
 
-        evsel_list = perf_evlist__new();
-        if (evsel_list == NULL)
+        rec->evlist = perf_evlist__new();
+        if (rec->evlist == NULL)
                 return -ENOMEM;
 
-        rec->evlist = evsel_list;
-
         argc = parse_options(argc, argv, record_options, record_usage,
                             PARSE_OPT_STOP_AT_NON_OPTION);
         if (!argc && target__none(&rec->opts.target))
@@ -932,12 +939,15 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
         if (rec->no_buildid_cache || rec->no_buildid)
                 disable_buildid_cache();
 
-        if (evsel_list->nr_entries == 0 &&
-            perf_evlist__add_default(evsel_list) < 0) {
+        if (rec->evlist->nr_entries == 0 &&
+            perf_evlist__add_default(rec->evlist) < 0) {
                 pr_err("Not enough memory for event selector list\n");
                 goto out_symbol_exit;
         }
 
+        if (rec->opts.target.tid && !rec->opts.no_inherit_set)
+                rec->opts.no_inherit = true;
+
         err = target__validate(&rec->opts.target);
         if (err) {
                 target__strerror(&rec->opts.target, err, errbuf, BUFSIZ);
@@ -956,20 +966,15 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
         }
 
         err = -ENOMEM;
-        if (perf_evlist__create_maps(evsel_list, &rec->opts.target) < 0)
+        if (perf_evlist__create_maps(rec->evlist, &rec->opts.target) < 0)
                 usage_with_options(record_usage, record_options);
 
-        if (perf_record_opts__config(&rec->opts)) {
+        if (record_opts__config(&rec->opts)) {
                 err = -EINVAL;
-                goto out_free_fd;
+                goto out_symbol_exit;
         }
 
         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:
         symbol__exit();
         return err;
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 8cf8e66ba594..3c53ec268fbc 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -39,7 +39,7 @@
 #include <dlfcn.h>
 #include <linux/bitmap.h>
 
-struct perf_report {
+struct report {
         struct perf_tool        tool;
         struct perf_session     *session;
         bool                    force, use_tui, use_gtk, use_stdio;
@@ -49,6 +49,8 @@ struct perf_report {
         bool                    show_threads;
         bool                    inverted_callchain;
         bool                    mem_mode;
+        bool                    header;
+        bool                    header_only;
         int                     max_stack;
         struct perf_read_values show_threads_values;
         const char              *pretty_printing_style;
@@ -58,14 +60,14 @@ struct perf_report {
         DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 };
 
-static int perf_report_config(const char *var, const char *value, void *cb)
+static int report__config(const char *var, const char *value, void *cb)
 {
         if (!strcmp(var, "report.group")) {
                 symbol_conf.event_group = perf_config_bool(var, value);
                 return 0;
         }
         if (!strcmp(var, "report.percent-limit")) {
-                struct perf_report *rep = cb;
+                struct report *rep = cb;
                 rep->min_percent = strtof(value, NULL);
                 return 0;
         }
@@ -73,31 +75,22 @@ static int perf_report_config(const char *var, const char *value, void *cb)
         return perf_default_config(var, value, cb);
 }
 
-static int perf_report__add_mem_hist_entry(struct perf_tool *tool,
-                                           struct addr_location *al,
-                                           struct perf_sample *sample,
-                                           struct perf_evsel *evsel,
-                                           struct machine *machine,
-                                           union perf_event *event)
+static int report__add_mem_hist_entry(struct perf_tool *tool, struct addr_location *al,
+                                      struct perf_sample *sample, struct perf_evsel *evsel,
+                                      union perf_event *event)
 {
-        struct perf_report *rep = container_of(tool, struct perf_report, tool);
+        struct report *rep = container_of(tool, struct report, tool);
         struct symbol *parent = NULL;
         u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
-        int err = 0;
         struct hist_entry *he;
         struct mem_info *mi, *mx;
         uint64_t cost;
+        int err = sample__resolve_callchain(sample, &parent, evsel, al, rep->max_stack);
 
-        if ((sort__has_parent || symbol_conf.use_callchain) &&
-            sample->callchain) {
-                err = machine__resolve_callchain(machine, evsel, al->thread,
-                                                 sample, &parent, al,
-                                                 rep->max_stack);
-                if (err)
-                        return err;
-        }
+        if (err)
+                return err;
 
-        mi = machine__resolve_mem(machine, al->thread, sample, cpumode);
+        mi = machine__resolve_mem(al->machine, al->thread, sample, cpumode);
         if (!mi)
                 return -ENOMEM;
 
@@ -120,77 +113,36 @@ static int perf_report__add_mem_hist_entry(struct perf_tool *tool,
         if (!he)
                 return -ENOMEM;
 
-        /*
-         * In the TUI browser, we are doing integrated annotation,
-         * so we don't allocate the extra space needed because the stdio
-         * code will not use it.
-         */
-        if (sort__has_sym && he->ms.sym && use_browser > 0) {
-                struct annotation *notes = symbol__annotation(he->ms.sym);
-
-                assert(evsel != NULL);
-
-                if (notes->src == NULL && symbol__alloc_hist(he->ms.sym) < 0)
-                        goto out;
-
-                err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
-                if (err)
-                        goto out;
-        }
+        err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
+        if (err)
+                goto out;
 
-        if (sort__has_sym && he->mem_info->daddr.sym && use_browser > 0) {
-                struct annotation *notes;
-
-                mx = he->mem_info;
-
-                notes = symbol__annotation(mx->daddr.sym);
-                if (notes->src == NULL && symbol__alloc_hist(mx->daddr.sym) < 0)
-                        goto out;
-
-                err = symbol__inc_addr_samples(mx->daddr.sym,
-                                               mx->daddr.map,
-                                               evsel->idx,
-                                               mx->daddr.al_addr);
-                if (err)
-                        goto out;
-        }
+        mx = he->mem_info;
+        err = addr_map_symbol__inc_samples(&mx->daddr, evsel->idx);
+        if (err)
+                goto out;
 
         evsel->hists.stats.total_period += cost;
         hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
-        err = 0;
-
-        if (symbol_conf.use_callchain) {
-                err = callchain_append(he->callchain,
-                                       &callchain_cursor,
-                                       sample->period);
-        }
+        err = hist_entry__append_callchain(he, sample);
 out:
         return err;
 }
 
-static int perf_report__add_branch_hist_entry(struct perf_tool *tool,
-                                        struct addr_location *al,
-                                        struct perf_sample *sample,
-                                        struct perf_evsel *evsel,
-                                      struct machine *machine)
+static int report__add_branch_hist_entry(struct perf_tool *tool, struct addr_location *al,
+                                         struct perf_sample *sample, struct perf_evsel *evsel)
 {
-        struct perf_report *rep = container_of(tool, struct perf_report, tool);
+        struct report *rep = container_of(tool, struct report, tool);
         struct symbol *parent = NULL;
-        int err = 0;
         unsigned i;
         struct hist_entry *he;
         struct branch_info *bi, *bx;
+        int err = sample__resolve_callchain(sample, &parent, evsel, al, rep->max_stack);
 
-        if ((sort__has_parent || symbol_conf.use_callchain)
-            && sample->callchain) {
-                err = machine__resolve_callchain(machine, evsel, al->thread,
-                                                 sample, &parent, al,
-                                                 rep->max_stack);
-                if (err)
-                        return err;
-        }
+        if (err)
+                return err;
 
-        bi = machine__resolve_bstack(machine, al->thread,
+        bi = machine__resolve_bstack(al->machine, al->thread,
                                      sample->branch_stack);
         if (!bi)
                 return -ENOMEM;
@@ -212,35 +164,15 @@ static int perf_report__add_branch_hist_entry(struct perf_tool *tool,
                 he = __hists__add_entry(&evsel->hists, al, parent, &bi[i], NULL,
                                         1, 1, 0);
                 if (he) {
-                        struct annotation *notes;
                         bx = he->branch_info;
-                        if (bx->from.sym && use_browser == 1 && sort__has_sym) {
-                                notes = symbol__annotation(bx->from.sym);
-                                if (!notes->src
-                                    && symbol__alloc_hist(bx->from.sym) < 0)
-                                        goto out;
-
-                                err = symbol__inc_addr_samples(bx->from.sym,
-                                                               bx->from.map,
-                                                               evsel->idx,
-                                                               bx->from.al_addr);
-                                if (err)
-                                        goto out;
-                        }
+                        err = addr_map_symbol__inc_samples(&bx->from, evsel->idx);
+                        if (err)
+                                goto out;
+
+                        err = addr_map_symbol__inc_samples(&bx->to, evsel->idx);
+                        if (err)
+                                goto out;
 
-                        if (bx->to.sym && use_browser == 1 && sort__has_sym) {
-                                notes = symbol__annotation(bx->to.sym);
-                                if (!notes->src
-                                    && symbol__alloc_hist(bx->to.sym) < 0)
-                                        goto out;
-
-                                err = symbol__inc_addr_samples(bx->to.sym,
-                                                               bx->to.map,
-                                                               evsel->idx,
-                                                               bx->to.al_addr);
-                                if (err)
-                                        goto out;
-                        }
                         evsel->hists.stats.total_period += 1;
                         hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
                 } else
@@ -252,24 +184,16 @@ out:
         return err;
 }
 
-static int perf_evsel__add_hist_entry(struct perf_tool *tool,
-                                      struct perf_evsel *evsel,
-                                      struct addr_location *al,
-                                      struct perf_sample *sample,
-                                      struct machine *machine)
+static int report__add_hist_entry(struct perf_tool *tool, struct perf_evsel *evsel,
+                                  struct addr_location *al, struct perf_sample *sample)
 {
-        struct perf_report *rep = container_of(tool, struct perf_report, tool);
+        struct report *rep = container_of(tool, struct report, tool);
         struct symbol *parent = NULL;
-        int err = 0;
         struct hist_entry *he;
+        int err = sample__resolve_callchain(sample, &parent, evsel, al, rep->max_stack);
 
-        if ((sort__has_parent || symbol_conf.use_callchain) && sample->callchain) {
-                err = machine__resolve_callchain(machine, evsel, al->thread,
-                                                 sample, &parent, al,
-                                                 rep->max_stack);
-                if (err)
-                        return err;
-        }
+        if (err)
+                return err;
 
         he = __hists__add_entry(&evsel->hists, al, parent, NULL, NULL,
                                 sample->period, sample->weight,
@@ -277,30 +201,11 @@ static int perf_evsel__add_hist_entry(struct perf_tool *tool,
         if (he == NULL)
                 return -ENOMEM;
 
-        if (symbol_conf.use_callchain) {
-                err = callchain_append(he->callchain,
-                                       &callchain_cursor,
-                                       sample->period);
-                if (err)
-                        return err;
-        }
-        /*
-         * Only in the TUI browser we are doing integrated annotation,
-         * so we don't allocated the extra space needed because the stdio
-         * code will not use it.
-         */
-        if (he->ms.sym != NULL && use_browser == 1 && sort__has_sym) {
-                struct annotation *notes = symbol__annotation(he->ms.sym);
-
-                assert(evsel != NULL);
-
-                err = -ENOMEM;
-                if (notes->src == NULL && symbol__alloc_hist(he->ms.sym) < 0)
-                        goto out;
-
-                err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
-        }
+        err = hist_entry__append_callchain(he, sample);
+        if (err)
+                goto out;
 
+        err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
         evsel->hists.stats.total_period += sample->period;
         hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
 out:
@@ -314,13 +219,13 @@ static int process_sample_event(struct perf_tool *tool,
                                 struct perf_evsel *evsel,
                                 struct machine *machine)
 {
-        struct perf_report *rep = container_of(tool, struct perf_report, tool);
+        struct report *rep = container_of(tool, struct report, tool);
         struct addr_location al;
         int ret;
 
         if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
-                fprintf(stderr, "problem processing %d event, skipping it.\n",
-                        event->header.type);
+                pr_debug("problem processing %d event, skipping it.\n",
+                         event->header.type);
                 return -1;
         }
 
@@ -331,21 +236,18 @@ static int process_sample_event(struct perf_tool *tool,
                 return 0;
 
         if (sort__mode == SORT_MODE__BRANCH) {
-                ret = perf_report__add_branch_hist_entry(tool, &al, sample,
-                                                         evsel, machine);
+                ret = report__add_branch_hist_entry(tool, &al, sample, evsel);
                 if (ret < 0)
                         pr_debug("problem adding lbr entry, skipping event\n");
         } else if (rep->mem_mode == 1) {
-                ret = perf_report__add_mem_hist_entry(tool, &al, sample,
-                                                      evsel, machine, event);
+                ret = report__add_mem_hist_entry(tool, &al, sample, evsel, event);
                 if (ret < 0)
                         pr_debug("problem adding mem entry, skipping event\n");
         } else {
                 if (al.map != NULL)
                         al.map->dso->hit = 1;
 
-                ret = perf_evsel__add_hist_entry(tool, evsel, &al, sample,
-                                                 machine);
+                ret = report__add_hist_entry(tool, evsel, &al, sample);
                 if (ret < 0)
                         pr_debug("problem incrementing symbol period, skipping event\n");
         }
@@ -358,7 +260,7 @@ static int process_read_event(struct perf_tool *tool,
                               struct perf_evsel *evsel,
                               struct machine *machine __maybe_unused)
 {
-        struct perf_report *rep = container_of(tool, struct perf_report, tool);
+        struct report *rep = container_of(tool, struct report, tool);
 
         if (rep->show_threads) {
                 const char *name = evsel ? perf_evsel__name(evsel) : "unknown";
@@ -377,7 +279,7 @@ static int process_read_event(struct perf_tool *tool,
 }
 
 /* For pipe mode, sample_type is not currently set */
-static int perf_report__setup_sample_type(struct perf_report *rep)
+static int report__setup_sample_type(struct report *rep)
 {
         struct perf_session *session = rep->session;
         u64 sample_type = perf_evlist__combined_sample_type(session->evlist);
@@ -422,8 +324,7 @@ static void sig_handler(int sig __maybe_unused)
         session_done = 1;
 }
 
-static size_t hists__fprintf_nr_sample_events(struct perf_report *rep,
-                                              struct hists *hists,
+static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report *rep,
                                               const char *evname, FILE *fp)
 {
         size_t ret;
@@ -460,12 +361,12 @@ static size_t hists__fprintf_nr_sample_events(struct perf_report *rep,
 }
 
 static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
-                                         struct perf_report *rep,
+                                         struct report *rep,
                                          const char *help)
 {
         struct perf_evsel *pos;
 
-        list_for_each_entry(pos, &evlist->entries, node) {
+        evlist__for_each(evlist, pos) {
                 struct hists *hists = &pos->hists;
                 const char *evname = perf_evsel__name(pos);
 
@@ -473,7 +374,7 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
                     !perf_evsel__is_group_leader(pos))
                         continue;
 
-                hists__fprintf_nr_sample_events(rep, hists, evname, stdout);
+                hists__fprintf_nr_sample_events(hists, rep, evname, stdout);
                 hists__fprintf(hists, true, 0, 0, rep->min_percent, stdout);
                 fprintf(stdout, "\n\n");
         }
@@ -493,43 +394,11 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
         return 0;
 }
 
-static int __cmd_report(struct perf_report *rep)
+static void report__warn_kptr_restrict(const struct report *rep)
 {
-        int ret = -EINVAL;
-        u64 nr_samples;
-        struct perf_session *session = rep->session;
-        struct perf_evsel *pos;
-        struct map *kernel_map;
-        struct kmap *kernel_kmap;
-        const char *help = "For a higher level overview, try: perf report --sort comm,dso";
-        struct ui_progress prog;
-        struct perf_data_file *file = session->file;
-
-        signal(SIGINT, sig_handler);
+        struct map *kernel_map = rep->session->machines.host.vmlinux_maps[MAP__FUNCTION];
+        struct kmap *kernel_kmap = map__kmap(kernel_map);
 
-        if (rep->cpu_list) {
-                ret = perf_session__cpu_bitmap(session, rep->cpu_list,
-                                               rep->cpu_bitmap);
-                if (ret)
-                        return ret;
-        }
-
-        if (use_browser <= 0)
-                perf_session__fprintf_info(session, stdout, rep->show_full_info);
-
-        if (rep->show_threads)
-                perf_read_values_init(&rep->show_threads_values);
-
-        ret = perf_report__setup_sample_type(rep);
-        if (ret)
-                return ret;
-
-        ret = perf_session__process_events(session, &rep->tool);
-        if (ret)
-                return ret;
-
-        kernel_map = session->machines.host.vmlinux_maps[MAP__FUNCTION];
-        kernel_kmap = map__kmap(kernel_map);
         if (kernel_map == NULL ||
             (kernel_map->dso->hit &&
              (kernel_kmap->ref_reloc_sym == NULL ||
@@ -552,26 +421,73 @@ static int __cmd_report(struct perf_report *rep)
 "Samples in kernel modules can't be resolved as well.\n\n",
                 desc);
         }
+}
 
-        if (verbose > 3)
-                perf_session__fprintf(session, stdout);
+static int report__gtk_browse_hists(struct report *rep, const char *help)
+{
+        int (*hist_browser)(struct perf_evlist *evlist, const char *help,
+                            struct hist_browser_timer *timer, float min_pcnt);
 
-        if (verbose > 2)
-                perf_session__fprintf_dsos(session, stdout);
+        hist_browser = dlsym(perf_gtk_handle, "perf_evlist__gtk_browse_hists");
 
-        if (dump_trace) {
-                perf_session__fprintf_nr_events(session, stdout);
-                return 0;
+        if (hist_browser == NULL) {
+                ui__error("GTK browser not found!\n");
+                return -1;
         }
 
-        nr_samples = 0;
-        list_for_each_entry(pos, &session->evlist->entries, node)
+        return hist_browser(rep->session->evlist, help, NULL, rep->min_percent);
+}
+
+static int report__browse_hists(struct report *rep)
+{
+        int ret;
+        struct perf_session *session = rep->session;
+        struct perf_evlist *evlist = session->evlist;
+        const char *help = "For a higher level overview, try: perf report --sort comm,dso";
+
+        switch (use_browser) {
+        case 1:
+                ret = perf_evlist__tui_browse_hists(evlist, help, NULL,
+                                                    rep->min_percent,
+                                                    &session->header.env);
+                /*
+                 * Usually "ret" is the last pressed key, and we only
+                 * care if the key notifies us to switch data file.
+                 */
+                if (ret != K_SWITCH_INPUT_DATA)
+                        ret = 0;
+                break;
+        case 2:
+                ret = report__gtk_browse_hists(rep, help);
+                break;
+        default:
+                ret = perf_evlist__tty_browse_hists(evlist, rep, help);
+                break;
+        }
+
+        return ret;
+}
+
+static u64 report__collapse_hists(struct report *rep)
+{
+        struct ui_progress prog;
+        struct perf_evsel *pos;
+        u64 nr_samples = 0;
+        /*
+         * Count number of histogram entries to use when showing progress,
+         * reusing nr_samples variable.
+         */
+        evlist__for_each(rep->session->evlist, pos)
                 nr_samples += pos->hists.nr_entries;
 
         ui_progress__init(&prog, nr_samples, "Merging related events...");
-
+        /*
+         * Count total number of samples, will be used to check if this
+         * session had any.
+         */
         nr_samples = 0;
-        list_for_each_entry(pos, &session->evlist->entries, node) {
+
+        evlist__for_each(rep->session->evlist, pos) {
                 struct hists *hists = &pos->hists;
 
                 if (pos->idx == 0)
@@ -589,8 +505,57 @@ static int __cmd_report(struct perf_report *rep)
                         hists__link(leader_hists, hists);
                 }
         }
+
         ui_progress__finish();
 
+        return nr_samples;
+}
+
+static int __cmd_report(struct report *rep)
+{
+        int ret;
+        u64 nr_samples;
+        struct perf_session *session = rep->session;
+        struct perf_evsel *pos;
+        struct perf_data_file *file = session->file;
+
+        signal(SIGINT, sig_handler);
+
+        if (rep->cpu_list) {
+                ret = perf_session__cpu_bitmap(session, rep->cpu_list,
+                                               rep->cpu_bitmap);
+                if (ret)
+                        return ret;
+        }
+
+        if (rep->show_threads)
+                perf_read_values_init(&rep->show_threads_values);
+
+        ret = report__setup_sample_type(rep);
+        if (ret)
+                return ret;
+
+        ret = perf_session__process_events(session, &rep->tool);
+        if (ret)
+                return ret;
+
+        report__warn_kptr_restrict(rep);
+
+        if (use_browser == 0) {
+                if (verbose > 3)
+                        perf_session__fprintf(session, stdout);
+
+                if (verbose > 2)
+                        perf_session__fprintf_dsos(session, stdout);
+
+                if (dump_trace) {
+                        perf_session__fprintf_nr_events(session, stdout);
+                        return 0;
+                }
+        }
+
+        nr_samples = report__collapse_hists(rep);
+
         if (session_done())
                 return 0;
 
@@ -599,47 +564,16 @@ static int __cmd_report(struct perf_report *rep)
                 return 0;
         }
 
-        list_for_each_entry(pos, &session->evlist->entries, node)
+        evlist__for_each(session->evlist, pos)
                 hists__output_resort(&pos->hists);
 
-        if (use_browser > 0) {
-                if (use_browser == 1) {
-                        ret = perf_evlist__tui_browse_hists(session->evlist,
-                                                        help, NULL,
-                                                        rep->min_percent,
-                                                        &session->header.env);
-                        /*
-                         * Usually "ret" is the last pressed key, and we only
-                         * care if the key notifies us to switch data file.
-                         */
-                        if (ret != K_SWITCH_INPUT_DATA)
-                                ret = 0;
-
-                } else if (use_browser == 2) {
-                        int (*hist_browser)(struct perf_evlist *,
-                                            const char *,
-                                            struct hist_browser_timer *,
-                                            float min_pcnt);
-
-                        hist_browser = dlsym(perf_gtk_handle,
-                                             "perf_evlist__gtk_browse_hists");
-                        if (hist_browser == NULL) {
-                                ui__error("GTK browser not found!\n");
-                                return ret;
-                        }
-                        hist_browser(session->evlist, help, NULL,
-                                     rep->min_percent);
-                }
-        } else
-                perf_evlist__tty_browse_hists(session->evlist, rep, help);
-
-        return ret;
+        return report__browse_hists(rep);
 }
 
 static int
 parse_callchain_opt(const struct option *opt, const char *arg, int unset)
 {
-        struct perf_report *rep = (struct perf_report *)opt->value;
+        struct report *rep = (struct report *)opt->value;
         char *tok, *tok2;
         char *endptr;
 
@@ -721,7 +655,7 @@ parse_callchain_opt(const struct option *opt, const char *arg, int unset)
                 return -1;
 setup:
         if (callchain_register_param(&callchain_param) < 0) {
-                fprintf(stderr, "Can't register callchain params\n");
+                pr_err("Can't register callchain params\n");
                 return -1;
         }
         return 0;
@@ -759,7 +693,7 @@ static int
 parse_percent_limit(const struct option *opt, const char *str,
                     int unset __maybe_unused)
 {
-        struct perf_report *rep = opt->value;
+        struct report *rep = opt->value;
 
         rep->min_percent = strtof(str, NULL);
         return 0;
@@ -777,7 +711,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
                 "perf report [<options>]",
                 NULL
         };
-        struct perf_report report = {
+        struct report report = {
                 .tool = {
                         .sample          = process_sample_event,
                         .mmap            = perf_event__process_mmap,
@@ -820,6 +754,9 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
         OPT_BOOLEAN(0, "gtk", &report.use_gtk, "Use the GTK2 interface"),
         OPT_BOOLEAN(0, "stdio", &report.use_stdio,
                     "Use the stdio interface"),
+        OPT_BOOLEAN(0, "header", &report.header, "Show data header."),
+        OPT_BOOLEAN(0, "header-only", &report.header_only,
+                    "Show only data header."),
         OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
                    "sort by key(s): pid, comm, dso, symbol, parent, cpu, srcline,"
                    " dso_to, dso_from, symbol_to, symbol_from, mispredict,"
@@ -890,7 +827,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
                 .mode  = PERF_DATA_MODE_READ,
         };
 
-        perf_config(perf_report_config, &report);
+        perf_config(report__config, &report);
 
         argc = parse_options(argc, argv, options, report_usage, 0);
 
@@ -940,7 +877,7 @@ repeat:
         }
         if (report.mem_mode) {
                 if (sort__mode == SORT_MODE__BRANCH) {
-                        fprintf(stderr, "branch and mem mode incompatible\n");
+                        pr_err("branch and mem mode incompatible\n");
                         goto error;
                 }
                 sort__mode = SORT_MODE__MEMORY;
@@ -963,6 +900,10 @@ repeat:
                         goto error;
         }
 
+        /* Force tty output for header output. */
+        if (report.header || report.header_only)
+                use_browser = 0;
+
         if (strcmp(input_name, "-") != 0)
                 setup_browser(true);
         else {
@@ -970,6 +911,16 @@ repeat:
                 perf_hpp__init();
         }
 
+        if (report.header || report.header_only) {
+                perf_session__fprintf_info(session, stdout,
+                                           report.show_full_info);
+                if (report.header_only)
+                        return 0;
+        } else if (use_browser == 0) {
+                fputs("# To display the perf.data header info, please use --header/--header-only options.\n#\n",
+                      stdout);
+        }
+
         /*
          * Only in the TUI browser we are doing integrated annotation,
          * so don't allocate extra space that won't be used in the stdio
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 0f3c65518a2c..6a76a07b6789 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -469,7 +469,7 @@ static void *thread_func(void *ctx)
         char comm2[22];
         int fd;
 
-        free(parms);
+        zfree(&parms);
 
         sprintf(comm2, ":%s", this_task->comm);
         prctl(PR_SET_NAME, comm2);
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index baf17989a216..9e9c91f5b7fa 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -43,6 +43,7 @@ enum perf_output_field {
         PERF_OUTPUT_DSO             = 1U << 9,
         PERF_OUTPUT_ADDR            = 1U << 10,
         PERF_OUTPUT_SYMOFFSET       = 1U << 11,
+        PERF_OUTPUT_SRCLINE         = 1U << 12,
 };
 
 struct output_option {
@@ -61,6 +62,7 @@ struct output_option {
         {.str = "dso",   .field = PERF_OUTPUT_DSO},
         {.str = "addr",  .field = PERF_OUTPUT_ADDR},
         {.str = "symoff", .field = PERF_OUTPUT_SYMOFFSET},
+        {.str = "srcline", .field = PERF_OUTPUT_SRCLINE},
 };
 
 /* default set to maintain compatibility with current format */
@@ -210,6 +212,11 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
                        "to DSO.\n");
                 return -EINVAL;
         }
+        if (PRINT_FIELD(SRCLINE) && !PRINT_FIELD(IP)) {
+                pr_err("Display of source line number requested but sample IP is not\n"
+                       "selected. Hence, no address to lookup the source line number.\n");
+                return -EINVAL;
+        }
 
         if ((PRINT_FIELD(PID) || PRINT_FIELD(TID)) &&
                 perf_evsel__check_stype(evsel, PERF_SAMPLE_TID, "TID",
@@ -245,6 +252,9 @@ static void set_print_ip_opts(struct perf_event_attr *attr)
 
         if (PRINT_FIELD(SYMOFFSET))
                 output[type].print_ip_opts |= PRINT_IP_OPT_SYMOFFSET;
+
+        if (PRINT_FIELD(SRCLINE))
+                output[type].print_ip_opts |= PRINT_IP_OPT_SRCLINE;
 }
 
 /*
@@ -280,6 +290,30 @@ static int perf_session__check_output_opt(struct perf_session *session)
                 set_print_ip_opts(&evsel->attr);
         }
 
+        /*
+         * set default for tracepoints to print symbols only
+         * if callchains are present
+         */
+        if (symbol_conf.use_callchain &&
+            !output[PERF_TYPE_TRACEPOINT].user_set) {
+                struct perf_event_attr *attr;
+
+                j = PERF_TYPE_TRACEPOINT;
+                evsel = perf_session__find_first_evtype(session, j);
+                if (evsel == NULL)
+                        goto out;
+
+                attr = &evsel->attr;
+
+                if (attr->sample_type & PERF_SAMPLE_CALLCHAIN) {
+                        output[j].fields |= PERF_OUTPUT_IP;
+                        output[j].fields |= PERF_OUTPUT_SYM;
+                        output[j].fields |= PERF_OUTPUT_DSO;
+                        set_print_ip_opts(attr);
+                }
+        }
+
+out:
         return 0;
 }
 
@@ -288,7 +322,6 @@ static void print_sample_start(struct perf_sample *sample,
                                struct perf_evsel *evsel)
 {
         struct perf_event_attr *attr = &evsel->attr;
-        const char *evname = NULL;
         unsigned long secs;
         unsigned long usecs;
         unsigned long long nsecs;
@@ -323,11 +356,6 @@ static void print_sample_start(struct perf_sample *sample,
                 usecs = nsecs / NSECS_PER_USEC;
                 printf("%5lu.%06lu: ", secs, usecs);
         }
-
-        if (PRINT_FIELD(EVNAME)) {
-                evname = perf_evsel__name(evsel);
-                printf("%s: ", evname ? evname : "[unknown]");
-        }
 }
 
 static bool is_bts_event(struct perf_event_attr *attr)
@@ -395,8 +423,8 @@ static void print_sample_addr(union perf_event *event,
 static void print_sample_bts(union perf_event *event,
                              struct perf_sample *sample,
                              struct perf_evsel *evsel,
-                             struct machine *machine,
-                             struct thread *thread)
+                             struct thread *thread,
+                             struct addr_location *al)
 {
         struct perf_event_attr *attr = &evsel->attr;
 
@@ -406,7 +434,7 @@ static void print_sample_bts(union perf_event *event,
                         printf(" ");
                 else
                         printf("\n");
-                perf_evsel__print_ip(evsel, event, sample, machine,
+                perf_evsel__print_ip(evsel, sample, al,
                                      output[attr->type].print_ip_opts,
                                      PERF_MAX_STACK_DEPTH);
         }
@@ -417,15 +445,14 @@ static void print_sample_bts(union perf_event *event,
         if (PRINT_FIELD(ADDR) ||
             ((evsel->attr.sample_type & PERF_SAMPLE_ADDR) &&
              !output[attr->type].user_set))
-                print_sample_addr(event, sample, machine, thread, attr);
+                print_sample_addr(event, sample, al->machine, thread, attr);
 
         printf("\n");
 }
 
 static void process_event(union perf_event *event, struct perf_sample *sample,
-                          struct perf_evsel *evsel, struct machine *machine,
-                          struct thread *thread,
-                          struct addr_location *al __maybe_unused)
+                          struct perf_evsel *evsel, struct thread *thread,
+                          struct addr_location *al)
 {
         struct perf_event_attr *attr = &evsel->attr;
 
@@ -434,8 +461,13 @@ static void process_event(union perf_event *event, struct perf_sample *sample,
 
         print_sample_start(sample, thread, evsel);
 
+        if (PRINT_FIELD(EVNAME)) {
+                const char *evname = perf_evsel__name(evsel);
+                printf("%s: ", evname ? evname : "[unknown]");
+        }
+
         if (is_bts_event(attr)) {
-                print_sample_bts(event, sample, evsel, machine, thread);
+                print_sample_bts(event, sample, evsel, thread, al);
                 return;
         }
 
@@ -443,7 +475,7 @@ static void process_event(union perf_event *event, struct perf_sample *sample,
                 event_format__print(evsel->tp_format, sample->cpu,
                                     sample->raw_data, sample->raw_size);
         if (PRINT_FIELD(ADDR))
-                print_sample_addr(event, sample, machine, thread, attr);
+                print_sample_addr(event, sample, al->machine, thread, attr);
 
         if (PRINT_FIELD(IP)) {
                 if (!symbol_conf.use_callchain)
@@ -451,7 +483,7 @@ static void process_event(union perf_event *event, struct perf_sample *sample,
                 else
                         printf("\n");
 
-                perf_evsel__print_ip(evsel, event, sample, machine,
+                perf_evsel__print_ip(evsel, sample, al,
                                      output[attr->type].print_ip_opts,
                                      PERF_MAX_STACK_DEPTH);
         }
@@ -540,7 +572,7 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
         if (cpu_list && !test_bit(sample->cpu, cpu_bitmap))
                 return 0;
 
-        scripting_ops->process_event(event, sample, evsel, machine, thread, &al);
+        scripting_ops->process_event(event, sample, evsel, thread, &al);
 
         evsel->hists.stats.total_period += sample->period;
         return 0;
@@ -549,6 +581,8 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 struct perf_script {
         struct perf_tool        tool;
         struct perf_session     *session;
+        bool                    show_task_events;
+        bool                    show_mmap_events;
 };
 
 static int process_attr(struct perf_tool *tool, union perf_event *event,
@@ -569,7 +603,7 @@ static int process_attr(struct perf_tool *tool, union perf_event *event,
         if (evsel->attr.type >= PERF_TYPE_MAX)
                 return 0;
 
-        list_for_each_entry(pos, &evlist->entries, node) {
+        evlist__for_each(evlist, pos) {
                 if (pos->attr.type == evsel->attr.type && pos != evsel)
                         return 0;
         }
@@ -579,6 +613,163 @@ static int process_attr(struct perf_tool *tool, union perf_event *event,
         return perf_evsel__check_attr(evsel, scr->session);
 }
 
+static int process_comm_event(struct perf_tool *tool,
+                              union perf_event *event,
+                              struct perf_sample *sample,
+                              struct machine *machine)
+{
+        struct thread *thread;
+        struct perf_script *script = container_of(tool, struct perf_script, tool);
+        struct perf_session *session = script->session;
+        struct perf_evsel *evsel = perf_evlist__first(session->evlist);
+        int ret = -1;
+
+        thread = machine__findnew_thread(machine, event->comm.pid, event->comm.tid);
+        if (thread == NULL) {
+                pr_debug("problem processing COMM event, skipping it.\n");
+                return -1;
+        }
+
+        if (perf_event__process_comm(tool, event, sample, machine) < 0)
+                goto out;
+
+        if (!evsel->attr.sample_id_all) {
+                sample->cpu = 0;
+                sample->time = 0;
+                sample->tid = event->comm.tid;
+                sample->pid = event->comm.pid;
+        }
+        print_sample_start(sample, thread, evsel);
+        perf_event__fprintf(event, stdout);
+        ret = 0;
+
+out:
+        return ret;
+}
+
+static int process_fork_event(struct perf_tool *tool,
+                              union perf_event *event,
+                              struct perf_sample *sample,
+                              struct machine *machine)
+{
+        struct thread *thread;
+        struct perf_script *script = container_of(tool, struct perf_script, tool);
+        struct perf_session *session = script->session;
+        struct perf_evsel *evsel = perf_evlist__first(session->evlist);
+
+        if (perf_event__process_fork(tool, event, sample, machine) < 0)
+                return -1;
+
+        thread = machine__findnew_thread(machine, event->fork.pid, event->fork.tid);
+        if (thread == NULL) {
+                pr_debug("problem processing FORK event, skipping it.\n");
+                return -1;
+        }
+
+        if (!evsel->attr.sample_id_all) {
+                sample->cpu = 0;
+                sample->time = event->fork.time;
+                sample->tid = event->fork.tid;
+                sample->pid = event->fork.pid;
+        }
+        print_sample_start(sample, thread, evsel);
+        perf_event__fprintf(event, stdout);
+
+        return 0;
+}
+static int process_exit_event(struct perf_tool *tool,
+                              union perf_event *event,
+                              struct perf_sample *sample,
+                              struct machine *machine)
+{
+        struct thread *thread;
+        struct perf_script *script = container_of(tool, struct perf_script, tool);
+        struct perf_session *session = script->session;
+        struct perf_evsel *evsel = perf_evlist__first(session->evlist);
+
+        thread = machine__findnew_thread(machine, event->fork.pid, event->fork.tid);
+        if (thread == NULL) {
+                pr_debug("problem processing EXIT event, skipping it.\n");
+                return -1;
+        }
+
+        if (!evsel->attr.sample_id_all) {
+                sample->cpu = 0;
+                sample->time = 0;
+                sample->tid = event->comm.tid;
+                sample->pid = event->comm.pid;
+        }
+        print_sample_start(sample, thread, evsel);
+        perf_event__fprintf(event, stdout);
+
+        if (perf_event__process_exit(tool, event, sample, machine) < 0)
+                return -1;
+
+        return 0;
+}
+
+static int process_mmap_event(struct perf_tool *tool,
+                              union perf_event *event,
+                              struct perf_sample *sample,
+                              struct machine *machine)
+{
+        struct thread *thread;
+        struct perf_script *script = container_of(tool, struct perf_script, tool);
+        struct perf_session *session = script->session;
+        struct perf_evsel *evsel = perf_evlist__first(session->evlist);
+
+        if (perf_event__process_mmap(tool, event, sample, machine) < 0)
+                return -1;
+
+        thread = machine__findnew_thread(machine, event->mmap.pid, event->mmap.tid);
+        if (thread == NULL) {
+                pr_debug("problem processing MMAP event, skipping it.\n");
+                return -1;
+        }
+
+        if (!evsel->attr.sample_id_all) {
+                sample->cpu = 0;
+                sample->time = 0;
+                sample->tid = event->mmap.tid;
+                sample->pid = event->mmap.pid;
+        }
+        print_sample_start(sample, thread, evsel);
+        perf_event__fprintf(event, stdout);
+
+        return 0;
+}
+
+static int process_mmap2_event(struct perf_tool *tool,
+                              union perf_event *event,
+                              struct perf_sample *sample,
+                              struct machine *machine)
+{
+        struct thread *thread;
+        struct perf_script *script = container_of(tool, struct perf_script, tool);
+        struct perf_session *session = script->session;
+        struct perf_evsel *evsel = perf_evlist__first(session->evlist);
+
+        if (perf_event__process_mmap2(tool, event, sample, machine) < 0)
+                return -1;
+
+        thread = machine__findnew_thread(machine, event->mmap2.pid, event->mmap2.tid);
+        if (thread == NULL) {
+                pr_debug("problem processing MMAP2 event, skipping it.\n");
+                return -1;
+        }
+
+        if (!evsel->attr.sample_id_all) {
+                sample->cpu = 0;
+                sample->time = 0;
+                sample->tid = event->mmap2.tid;
+                sample->pid = event->mmap2.pid;
+        }
+        print_sample_start(sample, thread, evsel);
+        perf_event__fprintf(event, stdout);
+
+        return 0;
+}
+
 static void sig_handler(int sig __maybe_unused)
 {
         session_done = 1;
@@ -590,6 +781,17 @@ static int __cmd_script(struct perf_script *script)
 
         signal(SIGINT, sig_handler);
 
+        /* override event processing functions */
+        if (script->show_task_events) {
+                script->tool.comm = process_comm_event;
+                script->tool.fork = process_fork_event;
+                script->tool.exit = process_exit_event;
+        }
+        if (script->show_mmap_events) {
+                script->tool.mmap = process_mmap_event;
+                script->tool.mmap2 = process_mmap2_event;
+        }
+
         ret = perf_session__process_events(script->session, &script->tool);
 
         if (debug_mode)
@@ -900,9 +1102,9 @@ static struct script_desc *script_desc__new(const char *name)
 
 static void script_desc__delete(struct script_desc *s)
 {
-        free(s->name);
-        free(s->half_liner);
-        free(s->args);
+        zfree(&s->name);
+        zfree(&s->half_liner);
+        zfree(&s->args);
         free(s);
 }
 
@@ -1107,8 +1309,7 @@ static int check_ev_match(char *dir_name, char *scriptname,
                         snprintf(evname, len + 1, "%s", p);
 
                         match = 0;
-                        list_for_each_entry(pos,
-                                        &session->evlist->entries, node) {
+                        evlist__for_each(session->evlist, pos) {
                                 if (!strcmp(perf_evsel__name(pos), evname)) {
                                         match = 1;
                                         break;
@@ -1290,6 +1491,8 @@ static int have_cmd(int argc, const char **argv)
 int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 {
         bool show_full_info = false;
+        bool header = false;
+        bool header_only = false;
         char *rec_script_path = NULL;
         char *rep_script_path = NULL;
         struct perf_session *session;
@@ -1328,6 +1531,8 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
         OPT_STRING('i', "input", &input_name, "file", "input file name"),
         OPT_BOOLEAN('d', "debug-mode", &debug_mode,
                    "do various checks like samples ordering and lost events"),
+        OPT_BOOLEAN(0, "header", &header, "Show data header."),
+        OPT_BOOLEAN(0, "header-only", &header_only, "Show only data header."),
         OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
                    "file", "vmlinux pathname"),
         OPT_STRING(0, "kallsyms", &symbol_conf.kallsyms_name,
@@ -1352,6 +1557,10 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
                     "display extended information from perf.data file"),
         OPT_BOOLEAN('\0', "show-kernel-path", &symbol_conf.show_kernel_path,
                     "Show the path of [kernel.kallsyms]"),
+        OPT_BOOLEAN('\0', "show-task-events", &script.show_task_events,
+                    "Show the fork/comm/exit events"),
+        OPT_BOOLEAN('\0', "show-mmap-events", &script.show_mmap_events,
+                    "Show the mmap events"),
         OPT_END()
         };
         const char * const script_usage[] = {
@@ -1540,6 +1749,12 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
         if (session == NULL)
                 return -ENOMEM;
 
+        if (header || header_only) {
+                perf_session__fprintf_info(session, stdout, show_full_info);
+                if (header_only)
+                        return 0;
+        }
+
         script.session = session;
 
         if (cpu_list) {
@@ -1547,9 +1762,6 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
                         return -1;
         }
 
-        if (!script_name && !generate_script_lang)
-                perf_session__fprintf_info(session, stdout, show_full_info);
-
         if (!no_callchain)
                 symbol_conf.use_callchain = true;
         else
@@ -1588,7 +1800,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
                         return -1;
                 }
 
-                err = scripting_ops->generate_script(session->pevent,
+                err = scripting_ops->generate_script(session->tevent.pevent,
                                                      "perf-script");
                 goto out;
         }
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index ee0d565f83e3..8b0e1c9234d9 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -138,6 +138,7 @@ static const char		*post_cmd			= NULL;
 static bool                     sync_run                        = false;
 static unsigned int             interval                        = 0;
 static unsigned int             initial_delay                   = 0;
+static unsigned int             unit_width                      = 4; /* strlen("unit") */
 static bool                     forever                         = false;
 static struct timespec          ref_time;
 static struct cpu_map           *aggr_map;
@@ -184,8 +185,7 @@ static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
 
 static void perf_evsel__free_stat_priv(struct perf_evsel *evsel)
 {
-        free(evsel->priv);
-        evsel->priv = NULL;
+        zfree(&evsel->priv);
 }
 
 static int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel)
@@ -207,15 +207,14 @@ static int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel)
 
 static void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel)
 {
-        free(evsel->prev_raw_counts);
-        evsel->prev_raw_counts = NULL;
+        zfree(&evsel->prev_raw_counts);
 }
 
 static void perf_evlist__free_stats(struct perf_evlist *evlist)
 {
         struct perf_evsel *evsel;
 
-        list_for_each_entry(evsel, &evlist->entries, node) {
+        evlist__for_each(evlist, evsel) {
                 perf_evsel__free_stat_priv(evsel);
                 perf_evsel__free_counts(evsel);
                 perf_evsel__free_prev_raw_counts(evsel);
@@ -226,7 +225,7 @@ 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) {
+        evlist__for_each(evlist, evsel) {
                 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))
@@ -260,7 +259,7 @@ static void perf_stat__reset_stats(struct perf_evlist *evlist)
 {
         struct perf_evsel *evsel;
 
-        list_for_each_entry(evsel, &evlist->entries, node) {
+        evlist__for_each(evlist, evsel) {
                 perf_evsel__reset_stat_priv(evsel);
                 perf_evsel__reset_counts(evsel, perf_evsel__nr_cpus(evsel));
         }
@@ -327,13 +326,13 @@ static struct perf_evsel *nth_evsel(int n)
 
         /* Assumes this only called when evsel_list does not change anymore. */
         if (!array) {
-                list_for_each_entry(ev, &evsel_list->entries, node)
+                evlist__for_each(evsel_list, ev)
                         array_len++;
                 array = malloc(array_len * sizeof(void *));
                 if (!array)
                         exit(ENOMEM);
                 j = 0;
-                list_for_each_entry(ev, &evsel_list->entries, node)
+                evlist__for_each(evsel_list, ev)
                         array[j++] = ev;
         }
         if (n < array_len)
@@ -441,13 +440,13 @@ static void print_interval(void)
         char prefix[64];
 
         if (aggr_mode == AGGR_GLOBAL) {
-                list_for_each_entry(counter, &evsel_list->entries, node) {
+                evlist__for_each(evsel_list, counter) {
                         ps = counter->priv;
                         memset(ps->res_stats, 0, sizeof(ps->res_stats));
                         read_counter_aggr(counter);
                 }
         } else  {
-                list_for_each_entry(counter, &evsel_list->entries, node) {
+                evlist__for_each(evsel_list, counter) {
                         ps = counter->priv;
                         memset(ps->res_stats, 0, sizeof(ps->res_stats));
                         read_counter(counter);
@@ -461,17 +460,17 @@ static void print_interval(void)
         if (num_print_interval == 0 && !csv_output) {
                 switch (aggr_mode) {
                 case AGGR_SOCKET:
-                        fprintf(output, "#           time socket cpus             counts events\n");
+                        fprintf(output, "#           time socket cpus             counts %*s events\n", unit_width, "unit");
                         break;
                 case AGGR_CORE:
-                        fprintf(output, "#           time core         cpus             counts events\n");
+                        fprintf(output, "#           time core         cpus             counts %*s events\n", unit_width, "unit");
                         break;
                 case AGGR_NONE:
-                        fprintf(output, "#           time CPU                 counts events\n");
+                        fprintf(output, "#           time CPU                counts %*s events\n", unit_width, "unit");
                         break;
                 case AGGR_GLOBAL:
                 default:
-                        fprintf(output, "#           time             counts events\n");
+                        fprintf(output, "#           time             counts %*s events\n", unit_width, "unit");
                 }
         }
 
@@ -484,12 +483,12 @@ static void print_interval(void)
                 print_aggr(prefix);
                 break;
         case AGGR_NONE:
-                list_for_each_entry(counter, &evsel_list->entries, node)
+                evlist__for_each(evsel_list, counter)
                         print_counter(counter, prefix);
                 break;
         case AGGR_GLOBAL:
         default:
-                list_for_each_entry(counter, &evsel_list->entries, node)
+                evlist__for_each(evsel_list, counter)
                         print_counter_aggr(counter, prefix);
         }
 
@@ -505,17 +504,31 @@ static void handle_initial_delay(void)
                         nthreads = thread_map__nr(evsel_list->threads);
 
                 usleep(initial_delay * 1000);
-                list_for_each_entry(counter, &evsel_list->entries, node)
+                evlist__for_each(evsel_list, counter)
                         perf_evsel__enable(counter, ncpus, nthreads);
         }
 }
 
+static volatile int workload_exec_errno;
+
+/*
+ * perf_evlist__prepare_workload will send a SIGUSR1
+ * if the fork fails, since we asked by setting its
+ * want_signal to true.
+ */
+static void workload_exec_failed_signal(int signo __maybe_unused, siginfo_t *info,
+                                        void *ucontext __maybe_unused)
+{
+        workload_exec_errno = info->si_value.sival_int;
+}
+
 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;
+        size_t l;
         int status = 0;
         const bool forks = (argc > 0);
 
@@ -528,8 +541,8 @@ static int __run_perf_stat(int argc, const char **argv)
         }
 
         if (forks) {
-                if (perf_evlist__prepare_workload(evsel_list, &target, argv,
-                                                  false, false) < 0) {
+                if (perf_evlist__prepare_workload(evsel_list, &target, argv, false,
+                                                  workload_exec_failed_signal) < 0) {
                         perror("failed to prepare workload");
                         return -1;
                 }
@@ -539,7 +552,7 @@ static int __run_perf_stat(int argc, const char **argv)
         if (group)
                 perf_evlist__set_leader(evsel_list);
 
-        list_for_each_entry(counter, &evsel_list->entries, node) {
+        evlist__for_each(evsel_list, counter) {
                 if (create_perf_stat_counter(counter) < 0) {
                         /*
                          * PPC returns ENXIO for HW counters until 2.6.37
@@ -565,6 +578,10 @@ static int __run_perf_stat(int argc, const char **argv)
                         return -1;
                 }
                 counter->supported = true;
+
+                l = strlen(counter->unit);
+                if (l > unit_width)
+                        unit_width = l;
         }
 
         if (perf_evlist__apply_filters(evsel_list)) {
@@ -590,6 +607,13 @@ static int __run_perf_stat(int argc, const char **argv)
                         }
                 }
                 wait(&status);
+
+                if (workload_exec_errno) {
+                        const char *emsg = strerror_r(workload_exec_errno, msg, sizeof(msg));
+                        pr_err("Workload failed: %s\n", emsg);
+                        return -1;
+                }
+
                 if (WIFSIGNALED(status))
                         psignal(WTERMSIG(status), argv[0]);
         } else {
@@ -606,13 +630,13 @@ static int __run_perf_stat(int argc, const char **argv)
         update_stats(&walltime_nsecs_stats, t1 - t0);
 
         if (aggr_mode == AGGR_GLOBAL) {
-                list_for_each_entry(counter, &evsel_list->entries, node) {
+                evlist__for_each(evsel_list, counter) {
                         read_counter_aggr(counter);
                         perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter),
                                              thread_map__nr(evsel_list->threads));
                 }
         } else {
-                list_for_each_entry(counter, &evsel_list->entries, node) {
+                evlist__for_each(evsel_list, counter) {
                         read_counter(counter);
                         perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter), 1);
                 }
@@ -621,7 +645,7 @@ static int __run_perf_stat(int argc, const char **argv)
         return WEXITSTATUS(status);
 }
 
-static int run_perf_stat(int argc __maybe_unused, const char **argv)
+static int run_perf_stat(int argc, const char **argv)
 {
         int ret;
 
@@ -704,14 +728,25 @@ static void aggr_printout(struct perf_evsel *evsel, int id, int nr)
 static void nsec_printout(int cpu, int nr, struct perf_evsel *evsel, double avg)
 {
         double msecs = avg / 1e6;
-        const char *fmt = csv_output ? "%.6f%s%s" : "%18.6f%s%-25s";
+        const char *fmt_v, *fmt_n;
         char name[25];
 
+        fmt_v = csv_output ? "%.6f%s" : "%18.6f%s";
+        fmt_n = csv_output ? "%s" : "%-25s";
+
         aggr_printout(evsel, cpu, nr);
 
         scnprintf(name, sizeof(name), "%s%s",
                   perf_evsel__name(evsel), csv_output ? "" : " (msec)");
-        fprintf(output, fmt, msecs, csv_sep, name);
+
+        fprintf(output, fmt_v, msecs, csv_sep);
+
+        if (csv_output)
+                fprintf(output, "%s%s", evsel->unit, csv_sep);
+        else
+                fprintf(output, "%-*s%s", unit_width, evsel->unit, csv_sep);
+
+        fprintf(output, fmt_n, name);
 
         if (evsel->cgrp)
                 fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
@@ -908,21 +943,31 @@ static void print_ll_cache_misses(int cpu,
 static void abs_printout(int cpu, int nr, struct perf_evsel *evsel, double avg)
 {
         double total, ratio = 0.0, total2;
+        double sc =  evsel->scale;
         const char *fmt;
 
-        if (csv_output)
-                fmt = "%.0f%s%s";
-        else if (big_num)
-                fmt = "%'18.0f%s%-25s";
-        else
-                fmt = "%18.0f%s%-25s";
+        if (csv_output) {
+                fmt = sc != 1.0 ?  "%.2f%s" : "%.0f%s";
+        } else {
+                if (big_num)
+                        fmt = sc != 1.0 ? "%'18.2f%s" : "%'18.0f%s";
+                else
+                        fmt = sc != 1.0 ? "%18.2f%s" : "%18.0f%s";
+        }
 
         aggr_printout(evsel, cpu, nr);
 
         if (aggr_mode == AGGR_GLOBAL)
                 cpu = 0;
 
-        fprintf(output, fmt, avg, csv_sep, perf_evsel__name(evsel));
+        fprintf(output, fmt, avg, csv_sep);
+
+        if (evsel->unit)
+                fprintf(output, "%-*s%s",
+                        csv_output ? 0 : unit_width,
+                        evsel->unit, csv_sep);
+
+        fprintf(output, "%-*s", csv_output ? 0 : 25, perf_evsel__name(evsel));
 
         if (evsel->cgrp)
                 fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
@@ -941,7 +986,10 @@ static void abs_printout(int cpu, int nr, struct perf_evsel *evsel, double avg)
 
                 if (total && avg) {
                         ratio = total / avg;
-                        fprintf(output, "\n                                             #   %5.2f  stalled cycles per insn", ratio);
+                        fprintf(output, "\n");
+                        if (aggr_mode == AGGR_NONE)
+                                fprintf(output, "        ");
+                        fprintf(output, "                                                  #   %5.2f  stalled cycles per insn", ratio);
                 }
 
         } else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES) &&
@@ -1061,6 +1109,7 @@ static void print_aggr(char *prefix)
 {
         struct perf_evsel *counter;
         int cpu, cpu2, s, s2, id, nr;
+        double uval;
         u64 ena, run, val;
 
         if (!(aggr_map || aggr_get_id))
@@ -1068,7 +1117,7 @@ static void print_aggr(char *prefix)
 
         for (s = 0; s < aggr_map->nr; s++) {
                 id = aggr_map->map[s];
-                list_for_each_entry(counter, &evsel_list->entries, node) {
+                evlist__for_each(evsel_list, counter) {
                         val = ena = run = 0;
                         nr = 0;
                         for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
@@ -1087,11 +1136,17 @@ static void print_aggr(char *prefix)
                         if (run == 0 || ena == 0) {
                                 aggr_printout(counter, id, nr);
 
-                                fprintf(output, "%*s%s%*s",
+                                fprintf(output, "%*s%s",
                                         csv_output ? 0 : 18,
                                         counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
-                                        csv_sep,
-                                        csv_output ? 0 : -24,
+                                        csv_sep);
+
+                                fprintf(output, "%-*s%s",
+                                        csv_output ? 0 : unit_width,
+                                        counter->unit, csv_sep);
+
+                                fprintf(output, "%*s",
+                                        csv_output ? 0 : -25,
                                         perf_evsel__name(counter));
 
                                 if (counter->cgrp)
@@ -1101,11 +1156,12 @@ static void print_aggr(char *prefix)
                                 fputc('\n', output);
                                 continue;
                         }
+                        uval = val * counter->scale;
 
                         if (nsec_counter(counter))
-                                nsec_printout(id, nr, counter, val);
+                                nsec_printout(id, nr, counter, uval);
                         else
-                                abs_printout(id, nr, counter, val);
+                                abs_printout(id, nr, counter, uval);
 
                         if (!csv_output) {
                                 print_noise(counter, 1.0);
@@ -1128,16 +1184,21 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
         struct perf_stat *ps = counter->priv;
         double avg = avg_stats(&ps->res_stats[0]);
         int scaled = counter->counts->scaled;
+        double uval;
 
         if (prefix)
                 fprintf(output, "%s", prefix);
 
         if (scaled == -1) {
-                fprintf(output, "%*s%s%*s",
+                fprintf(output, "%*s%s",
                         csv_output ? 0 : 18,
                         counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
-                        csv_sep,
-                        csv_output ? 0 : -24,
+                        csv_sep);
+                fprintf(output, "%-*s%s",
+                        csv_output ? 0 : unit_width,
+                        counter->unit, csv_sep);
+                fprintf(output, "%*s",
+                        csv_output ? 0 : -25,
                         perf_evsel__name(counter));
 
                 if (counter->cgrp)
@@ -1147,10 +1208,12 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
                 return;
         }
 
+        uval = avg * counter->scale;
+
         if (nsec_counter(counter))
-                nsec_printout(-1, 0, counter, avg);
+                nsec_printout(-1, 0, counter, uval);
         else
-                abs_printout(-1, 0, counter, avg);
+                abs_printout(-1, 0, counter, uval);
 
         print_noise(counter, avg);
 
@@ -1177,6 +1240,7 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
 static void print_counter(struct perf_evsel *counter, char *prefix)
 {
         u64 ena, run, val;
+        double uval;
         int cpu;
 
         for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
@@ -1188,14 +1252,20 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
                         fprintf(output, "%s", prefix);
 
                 if (run == 0 || ena == 0) {
-                        fprintf(output, "CPU%*d%s%*s%s%*s",
+                        fprintf(output, "CPU%*d%s%*s%s",
                                 csv_output ? 0 : -4,
                                 perf_evsel__cpus(counter)->map[cpu], csv_sep,
                                 csv_output ? 0 : 18,
                                 counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
-                                csv_sep,
-                                csv_output ? 0 : -24,
-                                perf_evsel__name(counter));
+                                csv_sep);
+
+                                fprintf(output, "%-*s%s",
+                                        csv_output ? 0 : unit_width,
+                                        counter->unit, csv_sep);
+
+                                fprintf(output, "%*s",
+                                        csv_output ? 0 : -25,
+                                        perf_evsel__name(counter));
 
                         if (counter->cgrp)
                                 fprintf(output, "%s%s",
@@ -1205,10 +1275,12 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
                         continue;
                 }
 
+                uval = val * counter->scale;
+
                 if (nsec_counter(counter))
-                        nsec_printout(cpu, 0, counter, val);
+                        nsec_printout(cpu, 0, counter, uval);
                 else
-                        abs_printout(cpu, 0, counter, val);
+                        abs_printout(cpu, 0, counter, uval);
 
                 if (!csv_output) {
                         print_noise(counter, 1.0);
@@ -1256,11 +1328,11 @@ static void print_stat(int argc, const char **argv)
                 print_aggr(NULL);
                 break;
         case AGGR_GLOBAL:
-                list_for_each_entry(counter, &evsel_list->entries, node)
+                evlist__for_each(evsel_list, counter)
                         print_counter_aggr(counter, NULL);
                 break;
         case AGGR_NONE:
-                list_for_each_entry(counter, &evsel_list->entries, node)
+                evlist__for_each(evsel_list, counter)
                         print_counter(counter, NULL);
                 break;
         default:
@@ -1710,14 +1782,14 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
         if (interval && interval < 100) {
                 pr_err("print interval must be >= 100ms\n");
                 parse_options_usage(stat_usage, options, "I", 1);
-                goto out_free_maps;
+                goto out;
         }
 
         if (perf_evlist__alloc_stats(evsel_list, interval))
-                goto out_free_maps;
+                goto out;
 
         if (perf_stat_init_aggr_mode())
-                goto out_free_maps;
+                goto out;
 
         /*
          * We dont want to block the signals - that would cause
@@ -1749,8 +1821,6 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
                 print_stat(argc, argv);
 
         perf_evlist__free_stats(evsel_list);
-out_free_maps:
-        perf_evlist__delete_maps(evsel_list);
 out:
         perf_evlist__delete(evsel_list);
         return status;
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 41c9bde2fb67..25526d6eae59 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -41,25 +41,29 @@
 #define SUPPORT_OLD_POWER_EVENTS 1
 #define PWR_EVENT_EXIT -1
 
-
-static unsigned int     numcpus;
-static u64              min_freq;       /* Lowest CPU frequency seen */
-static u64              max_freq;       /* Highest CPU frequency seen */
-static u64              turbo_frequency;
-
-static u64              first_time, last_time;
-
-static bool             power_only;
-
-
 struct per_pid;
-struct per_pidcomm;
-
-struct cpu_sample;
 struct power_event;
 struct wake_event;
 
-struct sample_wrapper;
+struct timechart {
+        struct perf_tool        tool;
+        struct per_pid          *all_data;
+        struct power_event      *power_events;
+        struct wake_event       *wake_events;
+        int                     proc_num;
+        unsigned int            numcpus;
+        u64                     min_freq,       /* Lowest CPU frequency seen */
+                                max_freq,       /* Highest CPU frequency seen */
+                                turbo_frequency,
+                                first_time, last_time;
+        bool                    power_only,
+                                tasks_only,
+                                with_backtrace,
+                                topology;
+};
+
+struct per_pidcomm;
+struct cpu_sample;
 
 /*
  * Datastructure layout:
@@ -124,10 +128,9 @@ struct cpu_sample {
         u64 end_time;
         int type;
         int cpu;
+        const char *backtrace;
 };
 
-static struct per_pid *all_data;
-
 #define CSTATE 1
 #define PSTATE 2
 
@@ -145,12 +148,9 @@ struct wake_event {
         int waker;
         int wakee;
         u64 time;
+        const char *backtrace;
 };
 
-static struct power_event    *power_events;
-static struct wake_event     *wake_events;
-
-struct process_filter;
 struct process_filter {
         char                    *name;
         int                     pid;
@@ -160,9 +160,9 @@ struct process_filter {
 static struct process_filter *process_filter;
 
 
-static struct per_pid *find_create_pid(int pid)
+static struct per_pid *find_create_pid(struct timechart *tchart, int pid)
 {
-        struct per_pid *cursor = all_data;
+        struct per_pid *cursor = tchart->all_data;
 
         while (cursor) {
                 if (cursor->pid == pid)
@@ -172,16 +172,16 @@ static struct per_pid *find_create_pid(int pid)
         cursor = zalloc(sizeof(*cursor));
         assert(cursor != NULL);
         cursor->pid = pid;
-        cursor->next = all_data;
-        all_data = cursor;
+        cursor->next = tchart->all_data;
+        tchart->all_data = cursor;
         return cursor;
 }
 
-static void pid_set_comm(int pid, char *comm)
+static void pid_set_comm(struct timechart *tchart, int pid, char *comm)
 {
         struct per_pid *p;
         struct per_pidcomm *c;
-        p = find_create_pid(pid);
+        p = find_create_pid(tchart, pid);
         c = p->all;
         while (c) {
                 if (c->comm && strcmp(c->comm, comm) == 0) {
@@ -203,14 +203,14 @@ static void pid_set_comm(int pid, char *comm)
         p->all = c;
 }
 
-static void pid_fork(int pid, int ppid, u64 timestamp)
+static void pid_fork(struct timechart *tchart, int pid, int ppid, u64 timestamp)
 {
         struct per_pid *p, *pp;
-        p = find_create_pid(pid);
-        pp = find_create_pid(ppid);
+        p = find_create_pid(tchart, pid);
+        pp = find_create_pid(tchart, ppid);
         p->ppid = ppid;
         if (pp->current && pp->current->comm && !p->current)
-                pid_set_comm(pid, pp->current->comm);
+                pid_set_comm(tchart, pid, pp->current->comm);
 
         p->start_time = timestamp;
         if (p->current) {
@@ -219,23 +219,24 @@ static void pid_fork(int pid, int ppid, u64 timestamp)
         }
 }
 
-static void pid_exit(int pid, u64 timestamp)
+static void pid_exit(struct timechart *tchart, int pid, u64 timestamp)
 {
         struct per_pid *p;
-        p = find_create_pid(pid);
+        p = find_create_pid(tchart, pid);
         p->end_time = timestamp;
         if (p->current)
                 p->current->end_time = timestamp;
 }
 
-static void
-pid_put_sample(int pid, int type, unsigned int cpu, u64 start, u64 end)
+static void pid_put_sample(struct timechart *tchart, int pid, int type,
+                           unsigned int cpu, u64 start, u64 end,
+                           const char *backtrace)
 {
         struct per_pid *p;
         struct per_pidcomm *c;
         struct cpu_sample *sample;
 
-        p = find_create_pid(pid);
+        p = find_create_pid(tchart, pid);
         c = p->current;
         if (!c) {
                 c = zalloc(sizeof(*c));
@@ -252,6 +253,7 @@ pid_put_sample(int pid, int type, unsigned int cpu, u64 start, u64 end)
         sample->type = type;
         sample->next = c->samples;
         sample->cpu = cpu;
+        sample->backtrace = backtrace;
         c->samples = sample;
 
         if (sample->type == TYPE_RUNNING && end > start && start > 0) {
@@ -272,84 +274,47 @@ static int cpus_cstate_state[MAX_CPUS];
 static u64 cpus_pstate_start_times[MAX_CPUS];
 static u64 cpus_pstate_state[MAX_CPUS];
 
-static int process_comm_event(struct perf_tool *tool __maybe_unused,
+static int process_comm_event(struct perf_tool *tool,
                               union perf_event *event,
                               struct perf_sample *sample __maybe_unused,
                               struct machine *machine __maybe_unused)
 {
-        pid_set_comm(event->comm.tid, event->comm.comm);
+        struct timechart *tchart = container_of(tool, struct timechart, tool);
+        pid_set_comm(tchart, event->comm.tid, event->comm.comm);
         return 0;
 }
 
-static int process_fork_event(struct perf_tool *tool __maybe_unused,
+static int process_fork_event(struct perf_tool *tool,
                               union perf_event *event,
                               struct perf_sample *sample __maybe_unused,
                               struct machine *machine __maybe_unused)
 {
-        pid_fork(event->fork.pid, event->fork.ppid, event->fork.time);
+        struct timechart *tchart = container_of(tool, struct timechart, tool);
+        pid_fork(tchart, event->fork.pid, event->fork.ppid, event->fork.time);
         return 0;
 }
 
-static int process_exit_event(struct perf_tool *tool __maybe_unused,
+static int process_exit_event(struct perf_tool *tool,
                               union perf_event *event,
                               struct perf_sample *sample __maybe_unused,
                               struct machine *machine __maybe_unused)
 {
-        pid_exit(event->fork.pid, event->fork.time);
+        struct timechart *tchart = container_of(tool, struct timechart, tool);
+        pid_exit(tchart, event->fork.pid, event->fork.time);
         return 0;
 }
 
-struct trace_entry {
-        unsigned short          type;
-        unsigned char           flags;
-        unsigned char           preempt_count;
-        int                     pid;
-        int                     lock_depth;
-};
-
 #ifdef SUPPORT_OLD_POWER_EVENTS
 static int use_old_power_events;
-struct power_entry_old {
-        struct trace_entry te;
-        u64     type;
-        u64     value;
-        u64     cpu_id;
-};
 #endif
 
-struct power_processor_entry {
-        struct trace_entry te;
-        u32     state;
-        u32     cpu_id;
-};
-
-#define TASK_COMM_LEN 16
-struct wakeup_entry {
-        struct trace_entry te;
-        char comm[TASK_COMM_LEN];
-        int   pid;
-        int   prio;
-        int   success;
-};
-
-struct sched_switch {
-        struct trace_entry te;
-        char prev_comm[TASK_COMM_LEN];
-        int  prev_pid;
-        int  prev_prio;
-        long prev_state; /* Arjan weeps. */
-        char next_comm[TASK_COMM_LEN];
-        int  next_pid;
-        int  next_prio;
-};
-
 static void c_state_start(int cpu, u64 timestamp, int state)
 {
         cpus_cstate_start_times[cpu] = timestamp;
         cpus_cstate_state[cpu] = state;
 }
 
-static void c_state_end(int cpu, u64 timestamp)
+static void c_state_end(struct timechart *tchart, int cpu, u64 timestamp)
 {
         struct power_event *pwr = zalloc(sizeof(*pwr));
 
@@ -361,12 +326,12 @@ static void c_state_end(int cpu, u64 timestamp)
         pwr->end_time = timestamp;
         pwr->cpu = cpu;
         pwr->type = CSTATE;
-        pwr->next = power_events;
+        pwr->next = tchart->power_events;
 
-        power_events = pwr;
+        tchart->power_events = pwr;
 }
 
-static void p_state_change(int cpu, u64 timestamp, u64 new_freq)
+static void p_state_change(struct timechart *tchart, int cpu, u64 timestamp, u64 new_freq)
 {
         struct power_event *pwr;
 
@@ -382,73 +347,78 @@ static void p_state_change(int cpu, u64 timestamp, u64 new_freq)
         pwr->end_time = timestamp;
         pwr->cpu = cpu;
         pwr->type = PSTATE;
-        pwr->next = power_events;
+        pwr->next = tchart->power_events;
 
         if (!pwr->start_time)
-                pwr->start_time = first_time;
+                pwr->start_time = tchart->first_time;
 
-        power_events = pwr;
+        tchart->power_events = pwr;
 
         cpus_pstate_state[cpu] = new_freq;
         cpus_pstate_start_times[cpu] = timestamp;
 
-        if ((u64)new_freq > max_freq)
-                max_freq = new_freq;
+        if ((u64)new_freq > tchart->max_freq)
+                tchart->max_freq = new_freq;
 
-        if (new_freq < min_freq || min_freq == 0)
-                min_freq = new_freq;
+        if (new_freq < tchart->min_freq || tchart->min_freq == 0)
+                tchart->min_freq = new_freq;
 
-        if (new_freq == max_freq - 1000)
-                        turbo_frequency = max_freq;
+        if (new_freq == tchart->max_freq - 1000)
+                tchart->turbo_frequency = tchart->max_freq;
 }
 
-static void
-sched_wakeup(int cpu, u64 timestamp, int pid, struct trace_entry *te)
+static void sched_wakeup(struct timechart *tchart, int cpu, u64 timestamp,
+                         int waker, int wakee, u8 flags, const char *backtrace)
 {
         struct per_pid *p;
-        struct wakeup_entry *wake = (void *)te;
         struct wake_event *we = zalloc(sizeof(*we));
 
         if (!we)
                 return;
 
         we->time = timestamp;
-        we->waker = pid;
+        we->waker = waker;
+        we->backtrace = backtrace;
 
-        if ((te->flags & TRACE_FLAG_HARDIRQ) || (te->flags & TRACE_FLAG_SOFTIRQ))
+        if ((flags & TRACE_FLAG_HARDIRQ) || (flags & TRACE_FLAG_SOFTIRQ))
                 we->waker = -1;
 
-        we->wakee = wake->pid;
-        we->next = wake_events;
-        wake_events = we;
-        p = find_create_pid(we->wakee);
+        we->wakee = wakee;
+        we->next = tchart->wake_events;
+        tchart->wake_events = we;
+        p = find_create_pid(tchart, we->wakee);
 
         if (p && p->current && p->current->state == TYPE_NONE) {
                 p->current->state_since = timestamp;
                 p->current->state = TYPE_WAITING;
         }
         if (p && p->current && p->current->state == TYPE_BLOCKED) {
-                pid_put_sample(p->pid, p->current->state, cpu, p->current->state_since, timestamp);
+                pid_put_sample(tchart, p->pid, p->current->state, cpu,
+                               p->current->state_since, timestamp, NULL);
                 p->current->state_since = timestamp;
                 p->current->state = TYPE_WAITING;
         }
 }
 
-static void sched_switch(int cpu, u64 timestamp, struct trace_entry *te)
+static void sched_switch(struct timechart *tchart, int cpu, u64 timestamp,
+                         int prev_pid, int next_pid, u64 prev_state,
+                         const char *backtrace)
 {
         struct per_pid *p = NULL, *prev_p;
-        struct sched_switch *sw = (void *)te;
 
+        prev_p = find_create_pid(tchart, prev_pid);
 
-        prev_p = find_create_pid(sw->prev_pid);
-
-        p = find_create_pid(sw->next_pid);
+        p = find_create_pid(tchart, next_pid);
 
         if (prev_p->current && prev_p->current->state != TYPE_NONE)
-                pid_put_sample(sw->prev_pid, TYPE_RUNNING, cpu, prev_p->current->state_since, timestamp);
+                pid_put_sample(tchart, prev_pid, TYPE_RUNNING, cpu,
+                               prev_p->current->state_since, timestamp,
+                               backtrace);
         if (p && p->current) {
                 if (p->current->state != TYPE_NONE)
-                        pid_put_sample(sw->next_pid, p->current->state, cpu, p->current->state_since, timestamp);
+                        pid_put_sample(tchart, next_pid, p->current->state, cpu,
+                                       p->current->state_since, timestamp,
+                                       backtrace);
 
                 p->current->state_since = timestamp;
                 p->current->state = TYPE_RUNNING;
@@ -457,109 +427,211 @@ static void sched_switch(int cpu, u64 timestamp, struct trace_entry *te)
         if (prev_p->current) {
                 prev_p->current->state = TYPE_NONE;
                 prev_p->current->state_since = timestamp;
-                if (sw->prev_state & 2)
+                if (prev_state & 2)
                         prev_p->current->state = TYPE_BLOCKED;
-                if (sw->prev_state == 0)
+                if (prev_state == 0)
                         prev_p->current->state = TYPE_WAITING;
         }
 }
 
-typedef int (*tracepoint_handler)(struct perf_evsel *evsel,
-                                  struct perf_sample *sample);
+static const char *cat_backtrace(union perf_event *event,
+                                 struct perf_sample *sample,
+                                 struct machine *machine)
+{
+        struct addr_location al;
+        unsigned int i;
+        char *p = NULL;
+        size_t p_len;
+        u8 cpumode = PERF_RECORD_MISC_USER;
+        struct addr_location tal;
+        struct ip_callchain *chain = sample->callchain;
+        FILE *f = open_memstream(&p, &p_len);
+
+        if (!f) {
+                perror("open_memstream error");
+                return NULL;
+        }
+
+        if (!chain)
+                goto exit;
+
+        if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
+                fprintf(stderr, "problem processing %d event, skipping it.\n",
+                        event->header.type);
+                goto exit;
+        }
+
+        for (i = 0; i < chain->nr; i++) {
+                u64 ip;
+
+                if (callchain_param.order == ORDER_CALLEE)
+                        ip = chain->ips[i];
+                else
+                        ip = chain->ips[chain->nr - i - 1];
+
+                if (ip >= PERF_CONTEXT_MAX) {
+                        switch (ip) {
+                        case PERF_CONTEXT_HV:
+                                cpumode = PERF_RECORD_MISC_HYPERVISOR;
+                                break;
+                        case PERF_CONTEXT_KERNEL:
+                                cpumode = PERF_RECORD_MISC_KERNEL;
+                                break;
+                        case PERF_CONTEXT_USER:
+                                cpumode = PERF_RECORD_MISC_USER;
+                                break;
+                        default:
+                                pr_debug("invalid callchain context: "
+                                         "%"PRId64"\n", (s64) ip);
+
+                                /*
+                                 * It seems the callchain is corrupted.
+                                 * Discard all.
+                                 */
+                                zfree(&p);
+                                goto exit;
+                        }
+                        continue;
+                }
+
+                tal.filtered = false;
+                thread__find_addr_location(al.thread, machine, cpumode,
+                                           MAP__FUNCTION, ip, &tal);
+
+                if (tal.sym)
+                        fprintf(f, "..... %016" PRIx64 " %s\n", ip,
+                                tal.sym->name);
+                else
+                        fprintf(f, "..... %016" PRIx64 "\n", ip);
+        }
+
+exit:
+        fclose(f);
+
+        return p;
+}
+
+typedef int (*tracepoint_handler)(struct timechart *tchart,
+                                  struct perf_evsel *evsel,
+                                  struct perf_sample *sample,
+                                  const char *backtrace);
 
-static int process_sample_event(struct perf_tool *tool __maybe_unused,
-                                union perf_event *event __maybe_unused,
+static int process_sample_event(struct perf_tool *tool,
+                                union perf_event *event,
                                 struct perf_sample *sample,
                                 struct perf_evsel *evsel,
-                                struct machine *machine __maybe_unused)
+                                struct machine *machine)
 {
+        struct timechart *tchart = container_of(tool, struct timechart, tool);
+
         if (evsel->attr.sample_type & PERF_SAMPLE_TIME) {
-                if (!first_time || first_time > sample->time)
-                        first_time = sample->time;
-                if (last_time < sample->time)
-                        last_time = sample->time;
+                if (!tchart->first_time || tchart->first_time > sample->time)
+                        tchart->first_time = sample->time;
+                if (tchart->last_time < sample->time)
+                        tchart->last_time = sample->time;
         }
 
-        if (sample->cpu > numcpus)
-                numcpus = sample->cpu;
-
         if (evsel->handler != NULL) {
                 tracepoint_handler f = evsel->handler;
-                return f(evsel, sample);
+                return f(tchart, evsel, sample,
+                         cat_backtrace(event, sample, machine));
         }
 
         return 0;
 }
 
 static int
-process_sample_cpu_idle(struct perf_evsel *evsel __maybe_unused,
-                        struct perf_sample *sample)
+process_sample_cpu_idle(struct timechart *tchart __maybe_unused,
+                        struct perf_evsel *evsel,
+                        struct perf_sample *sample,
+                        const char *backtrace __maybe_unused)
 {
-        struct power_processor_entry *ppe = sample->raw_data;
+        u32 state = perf_evsel__intval(evsel, sample, "state");
+        u32 cpu_id = perf_evsel__intval(evsel, sample, "cpu_id");
 
-        if (ppe->state == (u32) PWR_EVENT_EXIT)
-                c_state_end(ppe->cpu_id, sample->time);
+        if (state == (u32)PWR_EVENT_EXIT)
+                c_state_end(tchart, cpu_id, sample->time);
         else
-                c_state_start(ppe->cpu_id, sample->time, ppe->state);
+                c_state_start(cpu_id, sample->time, state);
         return 0;
 }
 
 static int
-process_sample_cpu_frequency(struct perf_evsel *evsel __maybe_unused,
-                             struct perf_sample *sample)
+process_sample_cpu_frequency(struct timechart *tchart,
+                             struct perf_evsel *evsel,
+                             struct perf_sample *sample,
+                             const char *backtrace __maybe_unused)
 {
-        struct power_processor_entry *ppe = sample->raw_data;
+        u32 state = perf_evsel__intval(evsel, sample, "state");
+        u32 cpu_id = perf_evsel__intval(evsel, sample, "cpu_id");
 
-        p_state_change(ppe->cpu_id, sample->time, ppe->state);
+        p_state_change(tchart, cpu_id, sample->time, state);
         return 0;
 }
 
 static int
-process_sample_sched_wakeup(struct perf_evsel *evsel __maybe_unused,
-                            struct perf_sample *sample)
+process_sample_sched_wakeup(struct timechart *tchart,
+                            struct perf_evsel *evsel,
+                            struct perf_sample *sample,
+                            const char *backtrace)
 {
-        struct trace_entry *te = sample->raw_data;
+        u8 flags = perf_evsel__intval(evsel, sample, "common_flags");
+        int waker = perf_evsel__intval(evsel, sample, "common_pid");
+        int wakee = perf_evsel__intval(evsel, sample, "pid");
 
-        sched_wakeup(sample->cpu, sample->time, sample->pid, te);
+        sched_wakeup(tchart, sample->cpu, sample->time, waker, wakee, flags, backtrace);
         return 0;
 }
 
 static int
-process_sample_sched_switch(struct perf_evsel *evsel __maybe_unused,
-                            struct perf_sample *sample)
+process_sample_sched_switch(struct timechart *tchart,
+                            struct perf_evsel *evsel,
+                            struct perf_sample *sample,
+                            const char *backtrace)
 {
-        struct trace_entry *te = sample->raw_data;
+        int prev_pid = perf_evsel__intval(evsel, sample, "prev_pid");
+        int next_pid = perf_evsel__intval(evsel, sample, "next_pid");
+        u64 prev_state = perf_evsel__intval(evsel, sample, "prev_state");
 
-        sched_switch(sample->cpu, sample->time, te);
+        sched_switch(tchart, sample->cpu, sample->time, prev_pid, next_pid,
+                     prev_state, backtrace);
         return 0;
 }
 
 #ifdef SUPPORT_OLD_POWER_EVENTS
 static int
-process_sample_power_start(struct perf_evsel *evsel __maybe_unused,
-                           struct perf_sample *sample)
+process_sample_power_start(struct timechart *tchart __maybe_unused,
+                           struct perf_evsel *evsel,
+                           struct perf_sample *sample,
+                           const char *backtrace __maybe_unused)
 {
-        struct power_entry_old *peo = sample->raw_data;
+        u64 cpu_id = perf_evsel__intval(evsel, sample, "cpu_id");
+        u64 value = perf_evsel__intval(evsel, sample, "value");
 
-        c_state_start(peo->cpu_id, sample->time, peo->value);
+        c_state_start(cpu_id, sample->time, value);
         return 0;
 }
 
 static int
-process_sample_power_end(struct perf_evsel *evsel __maybe_unused,
-                         struct perf_sample *sample)
+process_sample_power_end(struct timechart *tchart,
+                         struct perf_evsel *evsel __maybe_unused,
+                         struct perf_sample *sample,
+                         const char *backtrace __maybe_unused)
 {
-        c_state_end(sample->cpu, sample->time);
+        c_state_end(tchart, sample->cpu, sample->time);
         return 0;
 }
 
 static int
-process_sample_power_frequency(struct perf_evsel *evsel __maybe_unused,
-                               struct perf_sample *sample)
+process_sample_power_frequency(struct timechart *tchart,
+                               struct perf_evsel *evsel,
+                               struct perf_sample *sample,
+                               const char *backtrace __maybe_unused)
 {
-        struct power_entry_old *peo = sample->raw_data;
+        u64 cpu_id = perf_evsel__intval(evsel, sample, "cpu_id");
+        u64 value = perf_evsel__intval(evsel, sample, "value");
 
-        p_state_change(peo->cpu_id, sample->time, peo->value);
+        p_state_change(tchart, cpu_id, sample->time, value);
         return 0;
 }
 #endif /* SUPPORT_OLD_POWER_EVENTS */
@@ -568,12 +640,12 @@ process_sample_power_frequency(struct perf_evsel *evsel __maybe_unused,
  * After the last sample we need to wrap up the current C/P state
  * and close out each CPU for these.
  */
-static void end_sample_processing(void)
+static void end_sample_processing(struct timechart *tchart)
 {
         u64 cpu;
         struct power_event *pwr;
 
-        for (cpu = 0; cpu <= numcpus; cpu++) {
+        for (cpu = 0; cpu <= tchart->numcpus; cpu++) {
                 /* C state */
 #if 0
                 pwr = zalloc(sizeof(*pwr));
@@ -582,12 +654,12 @@ static void end_sample_processing(void)
 
                 pwr->state = cpus_cstate_state[cpu];
                 pwr->start_time = cpus_cstate_start_times[cpu];
-                pwr->end_time = last_time;
+                pwr->end_time = tchart->last_time;
                 pwr->cpu = cpu;
                 pwr->type = CSTATE;
-                pwr->next = power_events;
+                pwr->next = tchart->power_events;
 
-                power_events = pwr;
+                tchart->power_events = pwr;
 #endif
                 /* P state */
 
@@ -597,32 +669,32 @@ static void end_sample_processing(void)
 
                 pwr->state = cpus_pstate_state[cpu];
                 pwr->start_time = cpus_pstate_start_times[cpu];
-                pwr->end_time = last_time;
+                pwr->end_time = tchart->last_time;
                 pwr->cpu = cpu;
                 pwr->type = PSTATE;
-                pwr->next = power_events;
+                pwr->next = tchart->power_events;
 
                 if (!pwr->start_time)
-                        pwr->start_time = first_time;
+                        pwr->start_time = tchart->first_time;
                 if (!pwr->state)
-                        pwr->state = min_freq;
-                power_events = pwr;
+                        pwr->state = tchart->min_freq;
+                tchart->power_events = pwr;
         }
 }
 
 /*
  * Sort the pid datastructure
  */
-static void sort_pids(void)
+static void sort_pids(struct timechart *tchart)
 {
         struct per_pid *new_list, *p, *cursor, *prev;
         /* sort by ppid first, then by pid, lowest to highest */
 
         new_list = NULL;
 
-        while (all_data) {
-                p = all_data;
-                all_data = p->next;
+        while (tchart->all_data) {
+                p = tchart->all_data;
+                tchart->all_data = p->next;
                 p->next = NULL;
 
                 if (new_list == NULL) {
@@ -655,14 +727,14 @@ static void sort_pids(void)
                                 prev->next = p;
                 }
         }
-        all_data = new_list;
+        tchart->all_data = new_list;
 }
 
 
-static void draw_c_p_states(void)
+static void draw_c_p_states(struct timechart *tchart)
 {
         struct power_event *pwr;
-        pwr = power_events;
+        pwr = tchart->power_events;
 
         /*
          * two pass drawing so that the P state bars are on top of the C state blocks
@@ -673,30 +745,30 @@ static void draw_c_p_states(void)
                 pwr = pwr->next;
         }
 
-        pwr = power_events;
+        pwr = tchart->power_events;
         while (pwr) {
                 if (pwr->type == PSTATE) {
                         if (!pwr->state)
-                                pwr->state = min_freq;
+                                pwr->state = tchart->min_freq;
                         svg_pstate(pwr->cpu, pwr->start_time, pwr->end_time, pwr->state);
                 }
                 pwr = pwr->next;
         }
 }
 
-static void draw_wakeups(void)
+static void draw_wakeups(struct timechart *tchart)
 {
         struct wake_event *we;
         struct per_pid *p;
         struct per_pidcomm *c;
 
-        we = wake_events;
+        we = tchart->wake_events;
         while (we) {
                 int from = 0, to = 0;
                 char *task_from = NULL, *task_to = NULL;
 
                 /* locate the column of the waker and wakee */
-                p = all_data;
+                p = tchart->all_data;
                 while (p) {
                         if (p->pid == we->waker || p->pid == we->wakee) {
                                 c = p->all;
@@ -739,11 +811,12 @@ static void draw_wakeups(void)
                 }
 
                 if (we->waker == -1)
-                        svg_interrupt(we->time, to);
+                        svg_interrupt(we->time, to, we->backtrace);
                 else if (from && to && abs(from - to) == 1)
-                        svg_wakeline(we->time, from, to);
+                        svg_wakeline(we->time, from, to, we->backtrace);
                 else
-                        svg_partial_wakeline(we->time, from, task_from, to, task_to);
+                        svg_partial_wakeline(we->time, from, task_from, to,
+                                             task_to, we->backtrace);
                 we = we->next;
 
                 free(task_from);
@@ -751,19 +824,25 @@ static void draw_wakeups(void)
         }
 }
 
-static void draw_cpu_usage(void)
+static void draw_cpu_usage(struct timechart *tchart)
 {
         struct per_pid *p;
         struct per_pidcomm *c;
         struct cpu_sample *sample;
-        p = all_data;
+        p = tchart->all_data;
         while (p) {
                 c = p->all;
                 while (c) {
                         sample = c->samples;
                         while (sample) {
-                                if (sample->type == TYPE_RUNNING)
-                                        svg_process(sample->cpu, sample->start_time, sample->end_time, "sample", c->comm);
+                                if (sample->type == TYPE_RUNNING) {
+                                        svg_process(sample->cpu,
+                                                    sample->start_time,
+                                                    sample->end_time,
+                                                    p->pid,
+                                                    c->comm,
+                                                    sample->backtrace);
+                                }
 
                                 sample = sample->next;
                         }
@@ -773,16 +852,16 @@ static void draw_cpu_usage(void)
         }
 }
 
-static void draw_process_bars(void)
+static void draw_process_bars(struct timechart *tchart)
 {
         struct per_pid *p;
         struct per_pidcomm *c;
         struct cpu_sample *sample;
         int Y = 0;
 
-        Y = 2 * numcpus + 2;
+        Y = 2 * tchart->numcpus + 2;
 
-        p = all_data;
+        p = tchart->all_data;
         while (p) {
                 c = p->all;
                 while (c) {
@@ -796,11 +875,20 @@ static void draw_process_bars(void)
                         sample = c->samples;
                         while (sample) {
                                 if (sample->type == TYPE_RUNNING)
-                                        svg_sample(Y, sample->cpu, sample->start_time, sample->end_time);
+                                        svg_running(Y, sample->cpu,
+                                                    sample->start_time,
+                                                    sample->end_time,
+                                                    sample->backtrace);
                                 if (sample->type == TYPE_BLOCKED)
-                                        svg_box(Y, sample->start_time, sample->end_time, "blocked");
+                                        svg_blocked(Y, sample->cpu,
+                                                    sample->start_time,
+                                                    sample->end_time,
+                                                    sample->backtrace);
                                 if (sample->type == TYPE_WAITING)
-                                        svg_waiting(Y, sample->start_time, sample->end_time);
+                                        svg_waiting(Y, sample->cpu,
+                                                    sample->start_time,
+                                                    sample->end_time,
+                                                    sample->backtrace);
                                 sample = sample->next;
                         }
 
@@ -853,21 +941,21 @@ static int passes_filter(struct per_pid *p, struct per_pidcomm *c)
         return 0;
 }
 
-static int determine_display_tasks_filtered(void)
+static int determine_display_tasks_filtered(struct timechart *tchart)
 {
         struct per_pid *p;
         struct per_pidcomm *c;
         int count = 0;
 
-        p = all_data;
+        p = tchart->all_data;
         while (p) {
                 p->display = 0;
                 if (p->start_time == 1)
-                        p->start_time = first_time;
+                        p->start_time = tchart->first_time;
 
                 /* no exit marker, task kept running to the end */
                 if (p->end_time == 0)
-                        p->end_time = last_time;
+                        p->end_time = tchart->last_time;
 
                 c = p->all;
 
@@ -875,7 +963,7 @@ static int determine_display_tasks_filtered(void)
                         c->display = 0;
 
                         if (c->start_time == 1)
-                                c->start_time = first_time;
+                                c->start_time = tchart->first_time;
 
                         if (passes_filter(p, c)) {
                                 c->display = 1;
@@ -884,7 +972,7 @@ static int determine_display_tasks_filtered(void)
                         }
 
                         if (c->end_time == 0)
-                                c->end_time = last_time;
+                                c->end_time = tchart->last_time;
 
                         c = c->next;
                 }
@@ -893,25 +981,25 @@ static int determine_display_tasks_filtered(void)
         return count;
 }
 
-static int determine_display_tasks(u64 threshold)
+static int determine_display_tasks(struct timechart *tchart, u64 threshold)
 {
         struct per_pid *p;
         struct per_pidcomm *c;
         int count = 0;
 
         if (process_filter)
-                return determine_display_tasks_filtered();
+                return determine_display_tasks_filtered(tchart);
 
-        p = all_data;
+        p = tchart->all_data;
         while (p) {
                 p->display = 0;
                 if (p->start_time == 1)
-                        p->start_time = first_time;
+                        p->start_time = tchart->first_time;
 
                 /* no exit marker, task kept running to the end */
                 if (p->end_time == 0)
-                        p->end_time = last_time;
-                if (p->total_time >= threshold && !power_only)
+                        p->end_time = tchart->last_time;
+                if (p->total_time >= threshold)
                         p->display = 1;
 
                 c = p->all;
@@ -920,15 +1008,15 @@ static int determine_display_tasks(u64 threshold)
                         c->display = 0;
 
                         if (c->start_time == 1)
-                                c->start_time = first_time;
+                                c->start_time = tchart->first_time;
 
-                        if (c->total_time >= threshold && !power_only) {
+                        if (c->total_time >= threshold) {
                                 c->display = 1;
                                 count++;
                         }
 
                         if (c->end_time == 0)
-                                c->end_time = last_time;
+                                c->end_time = tchart->last_time;
 
                         c = c->next;
                 }
@@ -941,45 +1029,77 @@ static int determine_display_tasks(u64 threshold)
 
 #define TIME_THRESH 10000000
 
-static void write_svg_file(const char *filename)
+static void write_svg_file(struct timechart *tchart, const char *filename)
 {
         u64 i;
         int count;
+        int thresh = TIME_THRESH;
 
-        numcpus++;
+        if (tchart->power_only)
+                tchart->proc_num = 0;
 
+        /* We'd like to show at least proc_num tasks;
+         * be less picky if we have fewer */
+        do {
+                count = determine_display_tasks(tchart, thresh);
+                thresh /= 10;
+        } while (!process_filter && thresh && count < tchart->proc_num);
 
-        count = determine_display_tasks(TIME_THRESH);
+        if (!tchart->proc_num)
+                count = 0;
 
-        /* We'd like to show at least 15 tasks; be less picky if we have fewer */
-        if (count < 15)
-                count = determine_display_tasks(TIME_THRESH / 10);
-
-        open_svg(filename, numcpus, count, first_time, last_time);
+        open_svg(filename, tchart->numcpus, count, tchart->first_time, tchart->last_time);
 
         svg_time_grid();
         svg_legenda();
 
-        for (i = 0; i < numcpus; i++)
-                svg_cpu_box(i, max_freq, turbo_frequency);
+        for (i = 0; i < tchart->numcpus; i++)
+                svg_cpu_box(i, tchart->max_freq, tchart->turbo_frequency);
 
-        draw_cpu_usage();
-        draw_process_bars();
-        draw_c_p_states();
-        draw_wakeups();
+        draw_cpu_usage(tchart);
+        if (tchart->proc_num)
+                draw_process_bars(tchart);
+        if (!tchart->tasks_only)
+                draw_c_p_states(tchart);
+        if (tchart->proc_num)
+                draw_wakeups(tchart);
 
         svg_close();
 }
 
-static int __cmd_timechart(const char *output_name)
+static int process_header(struct perf_file_section *section __maybe_unused,
+                          struct perf_header *ph,
+                          int feat,
+                          int fd __maybe_unused,
+                          void *data)
+{
+        struct timechart *tchart = data;
+
+        switch (feat) {
+        case HEADER_NRCPUS:
+                tchart->numcpus = ph->env.nr_cpus_avail;
+                break;
+
+        case HEADER_CPU_TOPOLOGY:
+                if (!tchart->topology)
+                        break;
+
+                if (svg_build_topology_map(ph->env.sibling_cores,
+                                           ph->env.nr_sibling_cores,
+                                           ph->env.sibling_threads,
+                                           ph->env.nr_sibling_threads))
+                        fprintf(stderr, "problem building topology\n");
+                break;
+
+        default:
+                break;
+        }
+
+        return 0;
+}
+
+static int __cmd_timechart(struct timechart *tchart, const char *output_name)
 {
-        struct perf_tool perf_timechart = {
-                .comm            = process_comm_event,
-                .fork            = process_fork_event,
-                .exit            = process_exit_event,
-                .sample          = process_sample_event,
-                .ordered_samples = true,
-        };
         const struct perf_evsel_str_handler power_tracepoints[] = {
                 { "power:cpu_idle",             process_sample_cpu_idle },
                 { "power:cpu_frequency",        process_sample_cpu_frequency },
@@ -997,12 +1117,17 @@ static int __cmd_timechart(const char *output_name)
         };
 
         struct perf_session *session = perf_session__new(&file, false,
-                                                         &perf_timechart);
+                                                         &tchart->tool);
         int ret = -EINVAL;
 
         if (session == NULL)
                 return -ENOMEM;
 
+        (void)perf_header__process_sections(&session->header,
+                                            perf_data_file__fd(session->file),
+                                            tchart,
+                                            process_header);
+
         if (!perf_session__has_traces(session, "timechart record"))
                 goto out_delete;
 
@@ -1012,69 +1137,111 @@ static int __cmd_timechart(const char *output_name)
                 goto out_delete;
         }
 
-        ret = perf_session__process_events(session, &perf_timechart);
+        ret = perf_session__process_events(session, &tchart->tool);
         if (ret)
                 goto out_delete;
 
-        end_sample_processing();
+        end_sample_processing(tchart);
 
-        sort_pids();
+        sort_pids(tchart);
 
-        write_svg_file(output_name);
+        write_svg_file(tchart, output_name);
 
         pr_info("Written %2.1f seconds of trace to %s.\n",
-                (last_time - first_time) / 1000000000.0, output_name);
+                (tchart->last_time - tchart->first_time) / 1000000000.0, output_name);
 out_delete:
         perf_session__delete(session);
         return ret;
 }
 
-static int __cmd_record(int argc, const char **argv)
+static int timechart__record(struct timechart *tchart, int argc, const char **argv)
 {
-#ifdef SUPPORT_OLD_POWER_EVENTS
-        const char * const record_old_args[] = {
+        unsigned int rec_argc, i, j;
+        const char **rec_argv;
+        const char **p;
+        unsigned int record_elems;
+
+        const char * const common_args[] = {
                 "record", "-a", "-R", "-c", "1",
+        };
+        unsigned int common_args_nr = ARRAY_SIZE(common_args);
+
+        const char * const backtrace_args[] = {
+                "-g",
+        };
+        unsigned int backtrace_args_no = ARRAY_SIZE(backtrace_args);
+
+        const char * const power_args[] = {
+                "-e", "power:cpu_frequency",
+                "-e", "power:cpu_idle",
+        };
+        unsigned int power_args_nr = ARRAY_SIZE(power_args);
+
+        const char * const old_power_args[] = {
+#ifdef SUPPORT_OLD_POWER_EVENTS
                 "-e", "power:power_start",
                 "-e", "power:power_end",
                 "-e", "power:power_frequency",
-                "-e", "sched:sched_wakeup",
-                "-e", "sched:sched_switch",
-        };
 #endif
-        const char * const record_new_args[] = {
-                "record", "-a", "-R", "-c", "1",
-                "-e", "power:cpu_frequency",
-                "-e", "power:cpu_idle",
+        };
+        unsigned int old_power_args_nr = ARRAY_SIZE(old_power_args);
+
+        const char * const tasks_args[] = {
                 "-e", "sched:sched_wakeup",
                 "-e", "sched:sched_switch",
         };
-        unsigned int rec_argc, i, j;
-        const char **rec_argv;
-        const char * const *record_args = record_new_args;
-        unsigned int record_elems = ARRAY_SIZE(record_new_args);
+        unsigned int tasks_args_nr = ARRAY_SIZE(tasks_args);
 
 #ifdef SUPPORT_OLD_POWER_EVENTS
         if (!is_valid_tracepoint("power:cpu_idle") &&
             is_valid_tracepoint("power:power_start")) {
                 use_old_power_events = 1;
-                record_args = record_old_args;
-                record_elems = ARRAY_SIZE(record_old_args);
+                power_args_nr = 0;
+        } else {
+                old_power_args_nr = 0;
         }
 #endif
 
-        rec_argc = record_elems + argc - 1;
+        if (tchart->power_only)
+                tasks_args_nr = 0;
+
+        if (tchart->tasks_only) {
+                power_args_nr = 0;
+                old_power_args_nr = 0;
+        }
+
+        if (!tchart->with_backtrace)
+                backtrace_args_no = 0;
+
+        record_elems = common_args_nr + tasks_args_nr +
+                power_args_nr + old_power_args_nr + backtrace_args_no;
+
+        rec_argc = record_elems + argc;
         rec_argv = calloc(rec_argc + 1, sizeof(char *));
 
         if (rec_argv == NULL)
                 return -ENOMEM;
 
-        for (i = 0; i < record_elems; i++)
-                rec_argv[i] = strdup(record_args[i]);
+        p = rec_argv;
+        for (i = 0; i < common_args_nr; i++)
+                *p++ = strdup(common_args[i]);
+
+        for (i = 0; i < backtrace_args_no; i++)
+                *p++ = strdup(backtrace_args[i]);
+
+        for (i = 0; i < tasks_args_nr; i++)
+                *p++ = strdup(tasks_args[i]);
+
+        for (i = 0; i < power_args_nr; i++)
+                *p++ = strdup(power_args[i]);
 
-        for (j = 1; j < (unsigned int)argc; j++, i++)
-                rec_argv[i] = argv[j];
+        for (i = 0; i < old_power_args_nr; i++)
+                *p++ = strdup(old_power_args[i]);
 
-        return cmd_record(i, rec_argv, NULL);
+        for (j = 1; j < (unsigned int)argc; j++)
+                *p++ = argv[j];
+
+        return cmd_record(rec_argc, rec_argv, NULL);
 }
 
 static int
@@ -1086,20 +1253,56 @@ parse_process(const struct option *opt __maybe_unused, const char *arg,
         return 0;
 }
 
+static int
+parse_highlight(const struct option *opt __maybe_unused, const char *arg,
+                int __maybe_unused unset)
+{
+        unsigned long duration = strtoul(arg, NULL, 0);
+
+        if (svg_highlight || svg_highlight_name)
+                return -1;
+
+        if (duration)
+                svg_highlight = duration;
+        else
+                svg_highlight_name = strdup(arg);
+
+        return 0;
+}
+
 int cmd_timechart(int argc, const char **argv,
                   const char *prefix __maybe_unused)
 {
+        struct timechart tchart = {
+                .tool = {
+                        .comm            = process_comm_event,
+                        .fork            = process_fork_event,
+                        .exit            = process_exit_event,
+                        .sample          = process_sample_event,
+                        .ordered_samples = true,
+                },
+                .proc_num = 15,
+        };
         const char *output_name = "output.svg";
-        const struct option options[] = {
+        const struct option timechart_options[] = {
         OPT_STRING('i', "input", &input_name, "file", "input file name"),
         OPT_STRING('o', "output", &output_name, "file", "output file name"),
         OPT_INTEGER('w', "width", &svg_page_width, "page width"),
-        OPT_BOOLEAN('P', "power-only", &power_only, "output power data only"),
+        OPT_CALLBACK(0, "highlight", NULL, "duration or task name",
+                      "highlight tasks. Pass duration in ns or process name.",
+                       parse_highlight),
+        OPT_BOOLEAN('P', "power-only", &tchart.power_only, "output power data only"),
+        OPT_BOOLEAN('T', "tasks-only", &tchart.tasks_only,
+                    "output processes data only"),
         OPT_CALLBACK('p', "process", NULL, "process",
                       "process selector. Pass a pid or process name.",
                        parse_process),
         OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
                     "Look for files with symbols relative to this directory"),
+        OPT_INTEGER('n', "proc-num", &tchart.proc_num,
+                    "min. number of tasks to print"),
+        OPT_BOOLEAN('t', "topology", &tchart.topology,
+                    "sort CPUs according to topology"),
         OPT_END()
         };
         const char * const timechart_usage[] = {
@@ -1107,17 +1310,41 @@ int cmd_timechart(int argc, const char **argv,
                 NULL
         };
 
-        argc = parse_options(argc, argv, options, timechart_usage,
+        const struct option record_options[] = {
+        OPT_BOOLEAN('P', "power-only", &tchart.power_only, "output power data only"),
+        OPT_BOOLEAN('T', "tasks-only", &tchart.tasks_only,
+                    "output processes data only"),
+        OPT_BOOLEAN('g', "callchain", &tchart.with_backtrace, "record callchain"),
+        OPT_END()
+        };
+        const char * const record_usage[] = {
+                "perf timechart record [<options>]",
+                NULL
+        };
+        argc = parse_options(argc, argv, timechart_options, timechart_usage,
                         PARSE_OPT_STOP_AT_NON_OPTION);
 
+        if (tchart.power_only && tchart.tasks_only) {
+                pr_err("-P and -T options cannot be used at the same time.\n");
+                return -1;
+        }
+
         symbol__init();
 
-        if (argc && !strncmp(argv[0], "rec", 3))
-                return __cmd_record(argc, argv);
-        else if (argc)
-                usage_with_options(timechart_usage, options);
+        if (argc && !strncmp(argv[0], "rec", 3)) {
+                argc = parse_options(argc, argv, record_options, record_usage,
+                                     PARSE_OPT_STOP_AT_NON_OPTION);
+
+                if (tchart.power_only && tchart.tasks_only) {
+                        pr_err("-P and -T options cannot be used at the same time.\n");
+                        return -1;
+                }
+
+                return timechart__record(&tchart, argc, argv);
+        } else if (argc)
+                usage_with_options(timechart_usage, timechart_options);
 
         setup_pager();
 
-        return __cmd_timechart(output_name);
+        return __cmd_timechart(&tchart, output_name);
 }
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 71e6402729a8..76cd510d34d0 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -189,21 +189,18 @@ static void perf_top__record_precise_ip(struct perf_top *top,
         if (pthread_mutex_trylock(&notes->lock))
                 return;
 
-        if (notes->src == NULL && symbol__alloc_hist(sym) < 0) {
-                pthread_mutex_unlock(&notes->lock);
-                pr_err("Not enough memory for annotating '%s' symbol!\n",
-                       sym->name);
-                sleep(1);
-                return;
-        }
-
         ip = he->ms.map->map_ip(he->ms.map, ip);
-        err = symbol__inc_addr_samples(sym, he->ms.map, counter, ip);
+        err = hist_entry__inc_addr_samples(he, counter, ip);
 
         pthread_mutex_unlock(&notes->lock);
 
         if (err == -ERANGE && !he->ms.map->erange_warned)
                 ui__warn_map_erange(he->ms.map, sym, ip);
+        else if (err == -ENOMEM) {
+                pr_err("Not enough memory for annotating '%s' symbol!\n",
+                       sym->name);
+                sleep(1);
+        }
 }
 
 static void perf_top__show_details(struct perf_top *top)
@@ -485,7 +482,7 @@ static bool perf_top__handle_keypress(struct perf_top *top, int c)
 
                                 fprintf(stderr, "\nAvailable events:");
 
-                                list_for_each_entry(top->sym_evsel, &top->evlist->entries, node)
+                                evlist__for_each(top->evlist, top->sym_evsel)
                                         fprintf(stderr, "\n\t%d %s", top->sym_evsel->idx, perf_evsel__name(top->sym_evsel));
 
                                 prompt_integer(&counter, "Enter details event counter");
@@ -496,7 +493,7 @@ static bool perf_top__handle_keypress(struct perf_top *top, int c)
                                         sleep(1);
                                         break;
                                 }
-                                list_for_each_entry(top->sym_evsel, &top->evlist->entries, node)
+                                evlist__for_each(top->evlist, top->sym_evsel)
                                         if (top->sym_evsel->idx == counter)
                                                 break;
                         } else
@@ -578,7 +575,7 @@ static void *display_thread_tui(void *arg)
          * Zooming in/out UIDs. For now juse use whatever the user passed
          * via --uid.
          */
-        list_for_each_entry(pos, &top->evlist->entries, node)
+        evlist__for_each(top->evlist, pos)
                 pos->hists.uid_filter_str = top->record_opts.target.uid_str;
 
         perf_evlist__tui_browse_hists(top->evlist, help, &hbt, top->min_percent,
@@ -634,26 +631,9 @@ repeat:
         return NULL;
 }
 
-/* Tag samples to be skipped. */
-static const char *skip_symbols[] = {
-        "intel_idle",
-        "default_idle",
-        "native_safe_halt",
-        "cpu_idle",
-        "enter_idle",
-        "exit_idle",
-        "mwait_idle",
-        "mwait_idle_with_hints",
-        "poll_idle",
-        "ppc64_runlatch_off",
-        "pseries_dedicated_idle_sleep",
-        NULL
-};
-
 static int symbol_filter(struct map *map __maybe_unused, struct symbol *sym)
 {
         const char *name = sym->name;
-        int i;
 
         /*
          * ppc64 uses function descriptors and appends a '.' to the
@@ -671,12 +651,8 @@ static int symbol_filter(struct map *map __maybe_unused, struct symbol *sym)
             strstr(name, "_text_end"))
                 return 1;
 
-        for (i = 0; skip_symbols[i]; i++) {
-                if (!strcmp(skip_symbols[i], name)) {
-                        sym->ignore = true;
-                        break;
-                }
-        }
+        if (symbol__is_idle(sym))
+                sym->ignore = true;
 
         return 0;
 }
@@ -767,15 +743,10 @@ static void perf_event__process_sample(struct perf_tool *tool,
         if (al.sym == NULL || !al.sym->ignore) {
                 struct hist_entry *he;
 
-                if ((sort__has_parent || symbol_conf.use_callchain) &&
-                    sample->callchain) {
-                        err = machine__resolve_callchain(machine, evsel,
-                                                         al.thread, sample,
-                                                         &parent, &al,
-                                                         top->max_stack);
-                        if (err)
-                                return;
-                }
+                err = sample__resolve_callchain(sample, &parent, evsel, &al,
+                                                top->max_stack);
+                if (err)
+                        return;
 
                 he = perf_evsel__add_hist_entry(evsel, &al, sample);
                 if (he == NULL) {
@@ -783,12 +754,9 @@ static void perf_event__process_sample(struct perf_tool *tool,
                         return;
                 }
 
-                if (symbol_conf.use_callchain) {
-                        err = callchain_append(he->callchain, &callchain_cursor,
-                                               sample->period);
-                        if (err)
-                                return;
-                }
+                err = hist_entry__append_callchain(he, sample);
+                if (err)
+                        return;
 
                 if (sort__has_sym)
                         perf_top__record_precise_ip(top, he, evsel->idx, ip);
@@ -878,11 +846,11 @@ static int perf_top__start_counters(struct perf_top *top)
         char msg[512];
         struct perf_evsel *counter;
         struct perf_evlist *evlist = top->evlist;
-        struct perf_record_opts *opts = &top->record_opts;
+        struct record_opts *opts = &top->record_opts;
 
         perf_evlist__config(evlist, opts);
 
-        list_for_each_entry(counter, &evlist->entries, node) {
+        evlist__for_each(evlist, counter) {
 try_again:
                 if (perf_evsel__open(counter, top->evlist->cpus,
                                      top->evlist->threads) < 0) {
@@ -930,7 +898,7 @@ static int perf_top__setup_sample_type(struct perf_top *top __maybe_unused)
 
 static int __cmd_top(struct perf_top *top)
 {
-        struct perf_record_opts *opts = &top->record_opts;
+        struct record_opts *opts = &top->record_opts;
         pthread_t thread;
         int ret;
 
@@ -1052,7 +1020,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
                 .max_stack           = PERF_MAX_STACK_DEPTH,
                 .sym_pcnt_filter     = 5,
         };
-        struct perf_record_opts *opts = &top.record_opts;
+        struct record_opts *opts = &top.record_opts;
         struct target *target = &opts->target;
         const struct option options[] = {
         OPT_CALLBACK('e', "event", &top.evlist, "event",
@@ -1084,7 +1052,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
                             "dump the symbol table used for profiling"),
         OPT_INTEGER('f', "count-filter", &top.count_filter,
                     "only display functions with more events than this"),
-        OPT_BOOLEAN('g', "group", &opts->group,
+        OPT_BOOLEAN(0, "group", &opts->group,
                             "put the counters into a counter group"),
         OPT_BOOLEAN('i', "no-inherit", &opts->no_inherit,
                     "child tasks do not inherit counters"),
@@ -1105,7 +1073,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
                    " abort, in_tx, transaction"),
         OPT_BOOLEAN('n', "show-nr-samples", &symbol_conf.show_nr_samples,
                     "Show a column with the number of samples"),
-        OPT_CALLBACK_NOOPT('G', NULL, &top.record_opts,
+        OPT_CALLBACK_NOOPT('g', NULL, &top.record_opts,
                            NULL, "enables call-graph recording",
                            &callchain_opt),
         OPT_CALLBACK(0, "call-graph", &top.record_opts,
@@ -1195,7 +1163,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
         if (!top.evlist->nr_entries &&
             perf_evlist__add_default(top.evlist) < 0) {
                 ui__error("Not enough memory for event selector list\n");
-                goto out_delete_maps;
+                goto out_delete_evlist;
         }
 
         symbol_conf.nr_events = top.evlist->nr_entries;
@@ -1203,9 +1171,9 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
         if (top.delay_secs < 1)
                 top.delay_secs = 1;
 
-        if (perf_record_opts__config(opts)) {
+        if (record_opts__config(opts)) {
                 status = -EINVAL;
-                goto out_delete_maps;
+                goto out_delete_evlist;
         }
 
         top.sym_evsel = perf_evlist__first(top.evlist);
@@ -1230,8 +1198,6 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 
         status = __cmd_top(&top);
 
-out_delete_maps:
-        perf_evlist__delete_maps(top.evlist);
 out_delete_evlist:
         perf_evlist__delete(top.evlist);
 
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 8be17fc462ba..896f27047ed6 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -11,6 +11,8 @@
 #include "util/intlist.h"
 #include "util/thread_map.h"
 #include "util/stat.h"
+#include "trace-event.h"
+#include "util/parse-events.h"
 
 #include <libaudit.h>
 #include <stdlib.h>
@@ -144,8 +146,7 @@ static int perf_evsel__init_tp_ptr_field(struct perf_evsel *evsel,
 
 static void perf_evsel__delete_priv(struct perf_evsel *evsel)
 {
-        free(evsel->priv);
-        evsel->priv = NULL;
+        zfree(&evsel->priv);
         perf_evsel__delete(evsel);
 }
 
@@ -163,8 +164,7 @@ static int perf_evsel__init_syscall_tp(struct perf_evsel *evsel, void *handler)
         return -ENOMEM;
 
 out_delete:
-        free(evsel->priv);
-        evsel->priv = NULL;
+        zfree(&evsel->priv);
         return -ENOENT;
 }
 
@@ -172,6 +172,10 @@ static struct perf_evsel *perf_evsel__syscall_newtp(const char *direction, void
 {
         struct perf_evsel *evsel = perf_evsel__newtp("raw_syscalls", direction);
 
+        /* older kernel (e.g., RHEL6) use syscalls:{enter,exit} */
+        if (evsel == NULL)
+                evsel = perf_evsel__newtp("syscalls", direction);
+
         if (evsel) {
                 if (perf_evsel__init_syscall_tp(evsel, handler))
                         goto out_delete;
@@ -1153,29 +1157,30 @@ struct trace {
                 int             max;
                 struct syscall  *table;
         } syscalls;
-        struct perf_record_opts opts;
+        struct record_opts      opts;
         struct machine          *host;
         u64                     base_time;
-        bool                    full_time;
         FILE                    *output;
         unsigned long           nr_events;
         struct strlist          *ev_qualifier;
-        bool                    not_ev_qualifier;
-        bool                    live;
         const char              *last_vfs_getname;
         struct intlist          *tid_list;
         struct intlist          *pid_list;
+        double                  duration_filter;
+        double                  runtime_ms;
+        struct {
+                u64             vfs_getname,
+                                proc_getname;
+        } stats;
+        bool                    not_ev_qualifier;
+        bool                    live;
+        bool                    full_time;
         bool                    sched;
         bool                    multiple_threads;
         bool                    summary;
         bool                    summary_only;
         bool                    show_comm;
         bool                    show_tool_stats;
-        double                  duration_filter;
-        double                  runtime_ms;
-        struct {
-                u64             vfs_getname, proc_getname;
-        } stats;
 };
 
 static int trace__set_fd_pathname(struct thread *thread, int fd, const char *pathname)
@@ -1272,10 +1277,8 @@ static size_t syscall_arg__scnprintf_close_fd(char *bf, size_t size,
         size_t printed = syscall_arg__scnprintf_fd(bf, size, arg);
         struct thread_trace *ttrace = arg->thread->priv;
 
-        if (ttrace && fd >= 0 && fd <= ttrace->paths.max) {
-                free(ttrace->paths.table[fd]);
-                ttrace->paths.table[fd] = NULL;
-        }
+        if (ttrace && fd >= 0 && fd <= ttrace->paths.max)
+                zfree(&ttrace->paths.table[fd]);
 
         return printed;
 }
@@ -1430,11 +1433,11 @@ static int trace__read_syscall_info(struct trace *trace, int id)
         sc->fmt  = syscall_fmt__find(sc->name);
 
         snprintf(tp_name, sizeof(tp_name), "sys_enter_%s", sc->name);
-        sc->tp_format = event_format__new("syscalls", tp_name);
+        sc->tp_format = trace_event__tp_format("syscalls", tp_name);
 
         if (sc->tp_format == NULL && sc->fmt && sc->fmt->alias) {
                 snprintf(tp_name, sizeof(tp_name), "sys_enter_%s", sc->fmt->alias);
-                sc->tp_format = event_format__new("syscalls", tp_name);
+                sc->tp_format = trace_event__tp_format("syscalls", tp_name);
         }
 
         if (sc->tp_format == NULL)
@@ -1764,8 +1767,10 @@ static int trace__process_sample(struct perf_tool *tool,
         if (!trace->full_time && trace->base_time == 0)
                 trace->base_time = sample->time;
 
-        if (handler)
+        if (handler) {
+                ++trace->nr_events;
                 handler(trace, evsel, sample);
+        }
 
         return err;
 }
@@ -1800,10 +1805,11 @@ static int trace__record(int argc, const char **argv)
                 "-R",
                 "-m", "1024",
                 "-c", "1",
-                "-e", "raw_syscalls:sys_enter,raw_syscalls:sys_exit",
+                "-e",
         };
 
-        rec_argc = ARRAY_SIZE(record_args) + argc;
+        /* +1 is for the event string below */
+        rec_argc = ARRAY_SIZE(record_args) + 1 + argc;
         rec_argv = calloc(rec_argc + 1, sizeof(char *));
 
         if (rec_argv == NULL)
@@ -1812,6 +1818,17 @@ static int trace__record(int argc, const char **argv)
         for (i = 0; i < ARRAY_SIZE(record_args); i++)
                 rec_argv[i] = record_args[i];
 
+        /* event string may be different for older kernels - e.g., RHEL6 */
+        if (is_valid_tracepoint("raw_syscalls:sys_enter"))
+                rec_argv[i] = "raw_syscalls:sys_enter,raw_syscalls:sys_exit";
+        else if (is_valid_tracepoint("syscalls:sys_enter"))
+                rec_argv[i] = "syscalls:sys_enter,syscalls:sys_exit";
+        else {
+                pr_err("Neither raw_syscalls nor syscalls events exist.\n");
+                return -1;
+        }
+        i++;
+
         for (j = 0; j < (unsigned int)argc; j++, i++)
                 rec_argv[i] = argv[j];
 
@@ -1869,7 +1886,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
         err = trace__symbols_init(trace, evlist);
         if (err < 0) {
                 fprintf(trace->output, "Problems initializing symbol libraries!\n");
-                goto out_delete_maps;
+                goto out_delete_evlist;
         }
 
         perf_evlist__config(evlist, &trace->opts);
@@ -1879,10 +1896,10 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 
         if (forks) {
                 err = perf_evlist__prepare_workload(evlist, &trace->opts.target,
-                                                    argv, false, false);
+                                                    argv, false, NULL);
                 if (err < 0) {
                         fprintf(trace->output, "Couldn't run the workload!\n");
-                        goto out_delete_maps;
+                        goto out_delete_evlist;
                 }
         }
 
@@ -1890,10 +1907,10 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
         if (err < 0)
                 goto out_error_open;
 
-        err = perf_evlist__mmap(evlist, UINT_MAX, false);
+        err = perf_evlist__mmap(evlist, trace->opts.mmap_pages, false);
         if (err < 0) {
                 fprintf(trace->output, "Couldn't mmap the events: %s\n", strerror(errno));
-                goto out_close_evlist;
+                goto out_delete_evlist;
         }
 
         perf_evlist__enable(evlist);
@@ -1977,11 +1994,6 @@ out_disable:
                 }
         }
 
-        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:
@@ -2047,6 +2059,10 @@ static int trace__replay(struct trace *trace)
 
         evsel = perf_evlist__find_tracepoint_by_name(session->evlist,
                                                      "raw_syscalls:sys_enter");
+        /* older kernels have syscalls tp versus raw_syscalls */
+        if (evsel == NULL)
+                evsel = perf_evlist__find_tracepoint_by_name(session->evlist,
+                                                             "syscalls:sys_enter");
         if (evsel == NULL) {
                 pr_err("Data file does not have raw_syscalls:sys_enter event\n");
                 goto out;
@@ -2060,6 +2076,9 @@ static int trace__replay(struct trace *trace)
 
         evsel = perf_evlist__find_tracepoint_by_name(session->evlist,
                                                      "raw_syscalls:sys_exit");
+        if (evsel == NULL)
+                evsel = perf_evlist__find_tracepoint_by_name(session->evlist,
+                                                             "syscalls:sys_exit");
         if (evsel == NULL) {
                 pr_err("Data file does not have raw_syscalls:sys_exit event\n");
                 goto out;
@@ -2158,7 +2177,6 @@ static int trace__fprintf_one_thread(struct thread *thread, void *priv)
         size_t printed = data->printed;
         struct trace *trace = data->trace;
         struct thread_trace *ttrace = thread->priv;
-        const char *color;
         double ratio;
 
         if (ttrace == NULL)
@@ -2166,17 +2184,9 @@ static int trace__fprintf_one_thread(struct thread *thread, void *priv)
 
         ratio = (double)ttrace->nr_events / trace->nr_events * 100.0;
 
-        color = PERF_COLOR_NORMAL;
-        if (ratio > 50.0)
-                color = PERF_COLOR_RED;
-        else if (ratio > 25.0)
-                color = PERF_COLOR_GREEN;
-        else if (ratio > 5.0)
-                color = PERF_COLOR_YELLOW;
-
-        printed += color_fprintf(fp, color, " %s (%d), ", thread__comm_str(thread), thread->tid);
+        printed += fprintf(fp, " %s (%d), ", thread__comm_str(thread), thread->tid);
         printed += fprintf(fp, "%lu events, ", ttrace->nr_events);
-        printed += color_fprintf(fp, color, "%.1f%%", ratio);
+        printed += fprintf(fp, "%.1f%%", ratio);
         printed += fprintf(fp, ", %.3f msec\n", ttrace->runtime_ms);
         printed += thread__dump_stats(ttrace, trace, fp);
 
@@ -2248,7 +2258,7 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
                         },
                         .user_freq     = UINT_MAX,
                         .user_interval = ULLONG_MAX,
-                        .no_delay      = true,
+                        .no_buffering  = true,
                         .mmap_pages    = 1024,
                 },
                 .output = stdout,
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index f7d11a811c74..c48d44958172 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -1,28 +1,26 @@
-uname_M := $(shell uname -m 2>/dev/null || echo not)
 
-ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \
-                                  -e s/arm.*/arm/ -e s/sa110/arm/ \
-                                  -e s/s390x/s390/ -e s/parisc64/parisc/ \
-                                  -e s/ppc.*/powerpc/ -e s/mips.*/mips/ \
-                                  -e s/sh[234].*/sh/ -e s/aarch64.*/arm64/ )
-NO_PERF_REGS := 1
-CFLAGS := $(EXTRA_CFLAGS) $(EXTRA_WARNINGS)
+ifeq ($(src-perf),)
+src-perf := $(srctree)/tools/perf
+endif
 
-# Additional ARCH settings for x86
-ifeq ($(ARCH),i386)
-  override ARCH := x86
-  NO_PERF_REGS := 0
-  LIBUNWIND_LIBS = -lunwind -lunwind-x86
+ifeq ($(obj-perf),)
+obj-perf := $(OUTPUT)
 endif
 
-ifeq ($(ARCH),x86_64)
-  override ARCH := x86
-  IS_X86_64 := 0
-  ifeq (, $(findstring m32,$(CFLAGS)))
-    IS_X86_64 := $(shell echo __x86_64__ | ${CC} -E -x c - | tail -n 1)
-  endif
+ifneq ($(obj-perf),)
+obj-perf := $(abspath $(obj-perf))/
+endif
+
+LIB_INCLUDE := $(srctree)/tools/lib/
+CFLAGS := $(EXTRA_CFLAGS) $(EXTRA_WARNINGS)
+
+include $(src-perf)/config/Makefile.arch
+
+NO_PERF_REGS := 1
+
+# Additional ARCH settings for x86
+ifeq ($(ARCH),x86)
   ifeq (${IS_X86_64}, 1)
-    RAW_ARCH := x86_64
     CFLAGS += -DHAVE_ARCH_X86_64_SUPPORT
     ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memset_64.S
     LIBUNWIND_LIBS = -lunwind -lunwind-x86_64
@@ -36,24 +34,31 @@ ifeq ($(ARCH),arm)
   LIBUNWIND_LIBS = -lunwind -lunwind-arm
 endif
 
-ifeq ($(NO_PERF_REGS),0)
-  CFLAGS += -DHAVE_PERF_REGS_SUPPORT
-endif
-
-ifeq ($(src-perf),)
-src-perf := $(srctree)/tools/perf
-endif
+ifeq ($(LIBUNWIND_LIBS),)
+  NO_LIBUNWIND := 1
+else
+  #
+  # For linking with debug library, run like:
+  #
+  #   make DEBUG=1 LIBUNWIND_DIR=/opt/libunwind/
+  #
+  ifdef LIBUNWIND_DIR
+    LIBUNWIND_CFLAGS  = -I$(LIBUNWIND_DIR)/include
+    LIBUNWIND_LDFLAGS = -L$(LIBUNWIND_DIR)/lib
+  endif
+  LIBUNWIND_LDFLAGS += $(LIBUNWIND_LIBS)
 
-ifeq ($(obj-perf),)
-obj-perf := $(OUTPUT)
+  # Set per-feature check compilation flags
+  FEATURE_CHECK_CFLAGS-libunwind = $(LIBUNWIND_CFLAGS)
+  FEATURE_CHECK_LDFLAGS-libunwind = $(LIBUNWIND_LDFLAGS)
+  FEATURE_CHECK_CFLAGS-libunwind-debug-frame = $(LIBUNWIND_CFLAGS)
+  FEATURE_CHECK_LDFLAGS-libunwind-debug-frame = $(LIBUNWIND_LDFLAGS)
 endif
 
-ifneq ($(obj-perf),)
-obj-perf := $(abspath $(obj-perf))/
+ifeq ($(NO_PERF_REGS),0)
+  CFLAGS += -DHAVE_PERF_REGS_SUPPORT
 endif
 
-LIB_INCLUDE := $(srctree)/tools/lib/
-
 # include ARCH specific config
 -include $(src-perf)/arch/$(ARCH)/Makefile
 
@@ -102,7 +107,7 @@ endif
 
 feature_check = $(eval $(feature_check_code))
 define feature_check_code
-  feature-$(1) := $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) CFLAGS="$(EXTRA_CFLAGS)" LDFLAGS="$(LDFLAGS)" LIBUNWIND_LIBS="$(LIBUNWIND_LIBS)" -C config/feature-checks test-$1 >/dev/null 2>/dev/null && echo 1 || echo 0)
+  feature-$(1) := $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) CFLAGS="$(EXTRA_CFLAGS) $(FEATURE_CHECK_CFLAGS-$(1))" LDFLAGS="$(LDFLAGS) $(FEATURE_CHECK_LDFLAGS-$(1))" -C config/feature-checks test-$1.bin >/dev/null 2>/dev/null && echo 1 || echo 0)
 endef
 
 feature_set = $(eval $(feature_set_code))
@@ -141,16 +146,26 @@ CORE_FEATURE_TESTS =			\
         libslang                        \
         libunwind                       \
         on-exit                         \
-        stackprotector                  \
         stackprotector-all              \
         timerfd
 
+# Set FEATURE_CHECK_(C|LD)FLAGS-all for all CORE_FEATURE_TESTS features.
+# If in the future we need per-feature checks/flags for features not
+# mentioned in this list we need to refactor this ;-).
+set_test_all_flags = $(eval $(set_test_all_flags_code))
+define set_test_all_flags_code
+  FEATURE_CHECK_CFLAGS-all  += $(FEATURE_CHECK_CFLAGS-$(1))
+  FEATURE_CHECK_LDFLAGS-all += $(FEATURE_CHECK_LDFLAGS-$(1))
+endef
+
+$(foreach feat,$(CORE_FEATURE_TESTS),$(call set_test_all_flags,$(feat)))
+
 #
 # So here we detect whether test-all was rebuilt, to be able
 # to skip the print-out of the long features list if the file
 # existed before and after it was built:
 #
-ifeq ($(wildcard $(OUTPUT)config/feature-checks/test-all),)
+ifeq ($(wildcard $(OUTPUT)config/feature-checks/test-all.bin),)
   test-all-failed := 1
 else
   test-all-failed := 0
@@ -180,7 +195,7 @@ ifeq ($(feature-all), 1)
   #
   $(foreach feat,$(CORE_FEATURE_TESTS),$(call feature_set,$(feat)))
 else
-  $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) CFLAGS="$(EXTRA_CFLAGS)" LDFLAGS=$(LDFLAGS) -i -j -C config/feature-checks $(CORE_FEATURE_TESTS) >/dev/null 2>&1)
+  $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) CFLAGS="$(EXTRA_CFLAGS)" LDFLAGS=$(LDFLAGS) -i -j -C config/feature-checks $(addsuffix .bin,$(CORE_FEATURE_TESTS)) >/dev/null 2>&1)
   $(foreach feat,$(CORE_FEATURE_TESTS),$(call feature_check,$(feat)))
 endif
 
@@ -209,10 +224,6 @@ ifeq ($(feature-stackprotector-all), 1)
   CFLAGS += -fstack-protector-all
 endif
 
-ifeq ($(feature-stackprotector), 1)
-  CFLAGS += -Wstack-protector
-endif
-
 ifeq ($(DEBUG),0)
   ifeq ($(feature-fortify-source), 1)
     CFLAGS += -D_FORTIFY_SOURCE=2
@@ -221,6 +232,7 @@ endif
 
 CFLAGS += -I$(src-perf)/util/include
 CFLAGS += -I$(src-perf)/arch/$(ARCH)/include
+CFLAGS += -I$(srctree)/tools/include/
 CFLAGS += -I$(srctree)/arch/$(ARCH)/include/uapi
 CFLAGS += -I$(srctree)/arch/$(ARCH)/include
 CFLAGS += -I$(srctree)/include/uapi
@@ -310,21 +322,7 @@ ifndef NO_LIBELF
   endif # NO_DWARF
 endif # NO_LIBELF
 
-ifeq ($(LIBUNWIND_LIBS),)
-  NO_LIBUNWIND := 1
-endif
-
 ifndef NO_LIBUNWIND
-  #
-  # For linking with debug library, run like:
-  #
-  #   make DEBUG=1 LIBUNWIND_DIR=/opt/libunwind/
-  #
-  ifdef LIBUNWIND_DIR
-    LIBUNWIND_CFLAGS  := -I$(LIBUNWIND_DIR)/include
-    LIBUNWIND_LDFLAGS := -L$(LIBUNWIND_DIR)/lib
-  endif
-
   ifneq ($(feature-libunwind), 1)
     msg := $(warning No libunwind found, disabling post unwind support. Please install libunwind-dev[el] >= 1.1);
     NO_LIBUNWIND := 1
@@ -339,14 +337,12 @@ ifndef NO_LIBUNWIND
       # non-ARM has no dwarf_find_debug_frame() function:
       CFLAGS += -DNO_LIBUNWIND_DEBUG_FRAME
     endif
-  endif
-endif
 
-ifndef NO_LIBUNWIND
-  CFLAGS += -DHAVE_LIBUNWIND_SUPPORT
-  EXTLIBS += $(LIBUNWIND_LIBS)
-  CFLAGS += $(LIBUNWIND_CFLAGS)
-  LDFLAGS += $(LIBUNWIND_LDFLAGS)
+    CFLAGS += -DHAVE_LIBUNWIND_SUPPORT
+    EXTLIBS += $(LIBUNWIND_LIBS)
+    CFLAGS += $(LIBUNWIND_CFLAGS)
+    LDFLAGS += $(LIBUNWIND_LDFLAGS)
+  endif # ifneq ($(feature-libunwind), 1)
 endif
 
 ifndef NO_LIBAUDIT
@@ -376,7 +372,7 @@ ifndef NO_SLANG
 endif
 
 ifndef NO_GTK2
-  FLAGS_GTK2=$(CFLAGS) $(LDFLAGS) $(EXTLIBS) $(shell pkg-config --libs --cflags gtk+-2.0 2>/dev/null)
+  FLAGS_GTK2=$(CFLAGS) $(LDFLAGS) $(EXTLIBS) $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null)
   ifneq ($(feature-gtk2), 1)
     msg := $(warning GTK2 not found, disables GTK2 support. Please install gtk2-devel or libgtk2.0-dev);
     NO_GTK2 := 1
@@ -385,8 +381,8 @@ ifndef NO_GTK2
       GTK_CFLAGS := -DHAVE_GTK_INFO_BAR_SUPPORT
     endif
     CFLAGS += -DHAVE_GTK2_SUPPORT
-    GTK_CFLAGS += $(shell pkg-config --cflags gtk+-2.0 2>/dev/null)
-    GTK_LIBS := $(shell pkg-config --libs gtk+-2.0 2>/dev/null)
+    GTK_CFLAGS += $(shell $(PKG_CONFIG) --cflags gtk+-2.0 2>/dev/null)
+    GTK_LIBS := $(shell $(PKG_CONFIG) --libs gtk+-2.0 2>/dev/null)
     EXTLIBS += -ldl
   endif
 endif
@@ -533,7 +529,7 @@ endif
 
 ifndef NO_LIBNUMA
   ifeq ($(feature-libnuma), 0)
-    msg := $(warning No numa.h found, disables 'perf bench numa mem' benchmark, please install numa-libs-devel or libnuma-dev);
+    msg := $(warning No numa.h found, disables 'perf bench numa mem' benchmark, please install numactl-devel/libnuma-devel/libnuma-dev);
     NO_LIBNUMA := 1
   else
     CFLAGS += -DHAVE_LIBNUMA_SUPPORT
@@ -598,3 +594,11 @@ else
 perfexec_instdir = $(prefix)/$(perfexecdir)
 endif
 perfexec_instdir_SQ = $(subst ','\'',$(perfexec_instdir))
+
+# If we install to $(HOME) we keep the traceevent default:
+# $(HOME)/.traceevent/plugins
+# Otherwise we install plugins into the global $(libdir).
+ifdef DESTDIR
+plugindir=$(libdir)/traceevent/plugins
+plugindir_SQ= $(subst ','\'',$(plugindir))
+endif
diff --git a/tools/perf/config/Makefile.arch b/tools/perf/config/Makefile.arch
new file mode 100644
index 000000000000..fef8ae922800
--- /dev/null
+++ b/tools/perf/config/Makefile.arch
@@ -0,0 +1,22 @@
+
+uname_M := $(shell uname -m 2>/dev/null || echo not)
+
+ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \
+                                  -e s/arm.*/arm/ -e s/sa110/arm/ \
+                                  -e s/s390x/s390/ -e s/parisc64/parisc/ \
+                                  -e s/ppc.*/powerpc/ -e s/mips.*/mips/ \
+                                  -e s/sh[234].*/sh/ -e s/aarch64.*/arm64/ )
+
+# Additional ARCH settings for x86
+ifeq ($(ARCH),i386)
+  override ARCH := x86
+endif
+
+ifeq ($(ARCH),x86_64)
+  override ARCH := x86
+  IS_X86_64 := 0
+  ifeq (, $(findstring m32,$(CFLAGS)))
+    IS_X86_64 := $(shell echo __x86_64__ | ${CC} -E -x c - | tail -n 1)
+    RAW_ARCH := x86_64
+  endif
+endif
diff --git a/tools/perf/config/feature-checks/.gitignore b/tools/perf/config/feature-checks/.gitignore
new file mode 100644
index 000000000000..80f3da0c3515
--- /dev/null
+++ b/tools/perf/config/feature-checks/.gitignore
@@ -0,0 +1,2 @@
+*.d
+*.bin
diff --git a/tools/perf/config/feature-checks/Makefile b/tools/perf/config/feature-checks/Makefile
index 87e790017c69..12e551346fa6 100644
--- a/tools/perf/config/feature-checks/Makefile
+++ b/tools/perf/config/feature-checks/Makefile
@@ -1,95 +1,92 @@
 
 FILES=                                  \
-        test-all                        \
-        test-backtrace                  \
-        test-bionic                     \
-        test-dwarf                      \
-        test-fortify-source             \
-        test-glibc                      \
-        test-gtk2                       \
-        test-gtk2-infobar               \
-        test-hello                      \
-        test-libaudit                   \
-        test-libbfd                     \
-        test-liberty                    \
-        test-liberty-z                  \
-        test-cplus-demangle             \
-        test-libelf                     \
-        test-libelf-getphdrnum          \
-        test-libelf-mmap                \
-        test-libnuma                    \
-        test-libperl                    \
-        test-libpython                  \
-        test-libpython-version          \
-        test-libslang                   \
-        test-libunwind                  \
-        test-libunwind-debug-frame      \
-        test-on-exit                    \
-        test-stackprotector-all         \
-        test-stackprotector             \
-        test-timerfd
-
-CC := $(CC) -MD
+        test-all.bin                    \
+        test-backtrace.bin              \
+        test-bionic.bin                 \
+        test-dwarf.bin                  \
+        test-fortify-source.bin         \
+        test-glibc.bin                  \
+        test-gtk2.bin                   \
+        test-gtk2-infobar.bin           \
+        test-hello.bin                  \
+        test-libaudit.bin               \
+        test-libbfd.bin                 \
+        test-liberty.bin                \
+        test-liberty-z.bin              \
+        test-cplus-demangle.bin         \
+        test-libelf.bin                 \
+        test-libelf-getphdrnum.bin      \
+        test-libelf-mmap.bin            \
+        test-libnuma.bin                \
+        test-libperl.bin                \
+        test-libpython.bin              \
+        test-libpython-version.bin      \
+        test-libslang.bin               \
+        test-libunwind.bin              \
+        test-libunwind-debug-frame.bin  \
+        test-on-exit.bin                \
+        test-stackprotector-all.bin     \
+        test-timerfd.bin
+
+CC := $(CROSS_COMPILE)gcc -MD
+PKG_CONFIG := $(CROSS_COMPILE)pkg-config
 
 all: $(FILES)
 
-BUILD = $(CC) $(CFLAGS) $(LDFLAGS) -o $(OUTPUT)$@ $@.c
+BUILD = $(CC) $(CFLAGS) -o $(OUTPUT)$@ $(patsubst %.bin,%.c,$@) $(LDFLAGS)
 
 ###############################
 
-test-all:
-        $(BUILD) -Werror -fstack-protector -fstack-protector-all -O2 -Werror -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma $(LIBUNWIND_LIBS) -lelf -laudit -I/usr/include/slang -lslang $(shell pkg-config --libs --cflags gtk+-2.0 2>/dev/null) $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl
+test-all.bin:
+        $(BUILD) -Werror -fstack-protector-all -O2 -Werror -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -laudit -I/usr/include/slang -lslang $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null) $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl
 
-test-hello:
+test-hello.bin:
         $(BUILD)
 
-test-stackprotector-all:
+test-stackprotector-all.bin:
         $(BUILD) -Werror -fstack-protector-all
 
-test-stackprotector:
-        $(BUILD) -Werror -fstack-protector -Wstack-protector
-
-test-fortify-source:
+test-fortify-source.bin:
         $(BUILD) -O2 -Werror -D_FORTIFY_SOURCE=2
 
-test-bionic:
+test-bionic.bin:
         $(BUILD)
 
-test-libelf:
+test-libelf.bin:
         $(BUILD) -lelf
 
-test-glibc:
+test-glibc.bin:
         $(BUILD)
 
-test-dwarf:
+test-dwarf.bin:
         $(BUILD) -ldw
 
-test-libelf-mmap:
+test-libelf-mmap.bin:
         $(BUILD) -lelf
 
-test-libelf-getphdrnum:
+test-libelf-getphdrnum.bin:
         $(BUILD) -lelf
 
-test-libnuma:
+test-libnuma.bin:
         $(BUILD) -lnuma
 
-test-libunwind:
-        $(BUILD) $(LIBUNWIND_LIBS) -lelf
+test-libunwind.bin:
+        $(BUILD) -lelf
 
-test-libunwind-debug-frame:
-        $(BUILD) $(LIBUNWIND_LIBS) -lelf
+test-libunwind-debug-frame.bin:
+        $(BUILD) -lelf
 
-test-libaudit:
+test-libaudit.bin:
         $(BUILD) -laudit
 
-test-libslang:
+test-libslang.bin:
         $(BUILD) -I/usr/include/slang -lslang
 
-test-gtk2:
-        $(BUILD) $(shell pkg-config --libs --cflags gtk+-2.0 2>/dev/null)
+test-gtk2.bin:
+        $(BUILD) $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null)
 
-test-gtk2-infobar:
-        $(BUILD) $(shell pkg-config --libs --cflags gtk+-2.0 2>/dev/null)
+test-gtk2-infobar.bin:
+        $(BUILD) $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null)
 
 grep-libs  = $(filter -l%,$(1))
 strip-libs = $(filter-out -l%,$(1))
@@ -100,7 +97,7 @@ PERL_EMBED_LIBADD = $(call grep-libs,$(PERL_EMBED_LDOPTS))
 PERL_EMBED_CCOPTS = `perl -MExtUtils::Embed -e ccopts 2>/dev/null`
 FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS)
 
-test-libperl:
+test-libperl.bin:
         $(BUILD) $(FLAGS_PERL_EMBED)
 
 override PYTHON := python
@@ -117,31 +114,31 @@ PYTHON_EMBED_LIBADD = $(call grep-libs,$(PYTHON_EMBED_LDOPTS))
 PYTHON_EMBED_CCOPTS = $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
 FLAGS_PYTHON_EMBED = $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS)
 
-test-libpython:
+test-libpython.bin:
         $(BUILD) $(FLAGS_PYTHON_EMBED)
 
-test-libpython-version:
+test-libpython-version.bin:
         $(BUILD) $(FLAGS_PYTHON_EMBED)
 
-test-libbfd:
+test-libbfd.bin:
         $(BUILD) -DPACKAGE='"perf"' -lbfd -ldl
 
-test-liberty:
+test-liberty.bin:
         $(CC) -o $(OUTPUT)$@ test-libbfd.c -DPACKAGE='"perf"' -lbfd -ldl -liberty
 
-test-liberty-z:
+test-liberty-z.bin:
         $(CC) -o $(OUTPUT)$@ test-libbfd.c -DPACKAGE='"perf"' -lbfd -ldl -liberty -lz
 
-test-cplus-demangle:
+test-cplus-demangle.bin:
         $(BUILD) -liberty
 
-test-on-exit:
+test-on-exit.bin:
         $(BUILD)
 
-test-backtrace:
+test-backtrace.bin:
         $(BUILD)
 
-test-timerfd:
+test-timerfd.bin:
         $(BUILD)
 
 -include *.d
diff --git a/tools/perf/config/feature-checks/test-all.c b/tools/perf/config/feature-checks/test-all.c
index 59e7a705e146..9b8a544155bb 100644
--- a/tools/perf/config/feature-checks/test-all.c
+++ b/tools/perf/config/feature-checks/test-all.c
@@ -85,6 +85,10 @@
 # include "test-timerfd.c"
 #undef main
 
+#define main main_test_stackprotector_all
+# include "test-stackprotector-all.c"
+#undef main
+
 int main(int argc, char *argv[])
 {
         main_test_libpython();
@@ -106,6 +110,7 @@ int main(int argc, char *argv[])
         main_test_backtrace();
         main_test_libnuma();
         main_test_timerfd();
+        main_test_stackprotector_all();
 
         return 0;
 }
diff --git a/tools/perf/config/feature-checks/test-stackprotector.c b/tools/perf/config/feature-checks/test-stackprotector.c
deleted file mode 100644
index c9f398d87868..000000000000
--- a/tools/perf/config/feature-checks/test-stackprotector.c
+++ /dev/null
@@ -1,6 +0,0 @@
-#include <stdio.h>
-
-int main(void)
-{
-        return puts("hi");
-}
diff --git a/tools/perf/config/feature-checks/test-volatile-register-var.c b/tools/perf/config/feature-checks/test-volatile-register-var.c
deleted file mode 100644
index c9f398d87868..000000000000
--- a/tools/perf/config/feature-checks/test-volatile-register-var.c
+++ /dev/null
@@ -1,6 +0,0 @@
-#include <stdio.h>
-
-int main(void)
-{
-        return puts("hi");
-}
diff --git a/tools/perf/config/utilities.mak b/tools/perf/config/utilities.mak
index f168debc5be2..4d985e0f03f5 100644
--- a/tools/perf/config/utilities.mak
+++ b/tools/perf/config/utilities.mak
@@ -178,10 +178,3 @@ endef
 _ge_attempt = $(if $(get-executable),$(get-executable),$(_gea_warn)$(call _gea_err,$(2)))
 _gea_warn = $(warning The path '$(1)' is not executable.)
 _gea_err  = $(if $(1),$(error Please set '$(1)' appropriately))
-
-ifneq ($(findstring $(MAKEFLAGS),s),s)
-  ifneq ($(V),1)
-    QUIET_CLEAN         = @printf '  CLEAN    %s\n' $1;
-    QUIET_INSTALL       = @printf '  INSTALL  %s\n' $1;
-  endif
-endif
diff --git a/tools/perf/bash_completion b/tools/perf/perf-completion.sh
index 62e157db2e2b..496e2abb5482 100644
--- a/tools/perf/bash_completion
+++ b/tools/perf/perf-completion.sh
@@ -1,4 +1,4 @@
-# perf completion
+# perf bash and zsh completion
 
 # Taken from git.git's completion script.
 __my_reassemble_comp_words_by_ref()
@@ -89,37 +89,117 @@ __ltrim_colon_completions()
         fi
 }
 
-type perf &>/dev/null &&
-_perf()
+__perfcomp ()
 {
-        local cur words cword prev cmd
+        COMPREPLY=( $( compgen -W "$1" -- "$2" ) )
+}
 
-        COMPREPLY=()
-        _get_comp_words_by_ref -n =: cur words cword prev
+__perfcomp_colon ()
+{
+        __perfcomp "$1" "$2"
+        __ltrim_colon_completions $cur
+}
+
+__perf_main ()
+{
+        local cmd
 
         cmd=${words[0]}
+        COMPREPLY=()
 
         # List perf subcommands or long options
         if [ $cword -eq 1 ]; then
                 if [[ $cur == --* ]]; then
-                        COMPREPLY=( $( compgen -W '--help --version \
+                        __perfcomp '--help --version \
                         --exec-path --html-path --paginate --no-pager \
-                        --perf-dir --work-tree --debugfs-dir' -- "$cur" ) )
+                        --perf-dir --work-tree --debugfs-dir' -- "$cur"
                 else
                         cmds=$($cmd --list-cmds)
-                        COMPREPLY=( $( compgen -W '$cmds' -- "$cur" ) )
+                        __perfcomp "$cmds" "$cur"
                 fi
         # List possible events for -e option
         elif [[ $prev == "-e" && "${words[1]}" == @(record|stat|top) ]]; then
                 evts=$($cmd list --raw-dump)
-                COMPREPLY=( $( compgen -W '$evts' -- "$cur" ) )
-                __ltrim_colon_completions $cur
+                __perfcomp_colon "$evts" "$cur"
+        # List subcommands for 'perf kvm'
+        elif [[ $prev == "kvm" ]]; then
+                subcmds="top record report diff buildid-list stat"
+                __perfcomp_colon "$subcmds" "$cur"
         # List long option names
         elif [[ $cur == --* ]];  then
                 subcmd=${words[1]}
                 opts=$($cmd $subcmd --list-opts)
-                COMPREPLY=( $( compgen -W '$opts' -- "$cur" ) )
+                __perfcomp "$opts" "$cur"
         fi
+}
+
+if [[ -n ${ZSH_VERSION-} ]]; then
+        autoload -U +X compinit && compinit
+
+        __perfcomp ()
+        {
+                emulate -L zsh
+
+                local c IFS=$' \t\n'
+                local -a array
+
+                for c in ${=1}; do
+                        case $c in
+                        --*=*|*.) ;;
+                        *) c="$c " ;;
+                        esac
+                        array[${#array[@]}+1]="$c"
+                done
+
+                compset -P '*[=:]'
+                compadd -Q -S '' -a -- array && _ret=0
+        }
+
+        __perfcomp_colon ()
+        {
+                emulate -L zsh
+
+                local cur_="${2-$cur}"
+                local c IFS=$' \t\n'
+                local -a array
+
+                if [[ "$cur_" == *:* ]]; then
+                        local colon_word=${cur_%"${cur_##*:}"}
+                fi
+
+                for c in ${=1}; do
+                        case $c in
+                        --*=*|*.) ;;
+                        *) c="$c " ;;
+                        esac
+                        array[$#array+1]=${c#"$colon_word"}
+                done
+
+                compset -P '*[=:]'
+                compadd -Q -S '' -a -- array && _ret=0
+        }
+
+        _perf ()
+        {
+                local _ret=1 cur cword prev
+                cur=${words[CURRENT]}
+                prev=${words[CURRENT-1]}
+                let cword=CURRENT-1
+                emulate ksh -c __perf_main
+                let _ret && _default && _ret=0
+                return _ret
+        }
+
+        compdef _perf perf
+        return
+fi
+
+type perf &>/dev/null &&
+_perf()
+{
+        local cur words cword prev
+        _get_comp_words_by_ref -n =: cur words cword prev
+        __perf_main
 } &&
 
 complete -o bashdefault -o default -o nospace -F _perf perf 2>/dev/null \
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 8b38b4e80ec2..431798a4110d 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 <lk/debugfs.h>
+#include <api/fs/debugfs.h>
 #include <pthread.h>
 
 const char perf_usage_string[] =
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index b079304bd53d..7daa806d9050 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -132,6 +132,13 @@
 #define CPUINFO_PROC    "CPU"
 #endif
 
+#ifdef __xtensa__
+#define mb()            asm volatile("memw" ::: "memory")
+#define wmb()           asm volatile("memw" ::: "memory")
+#define rmb()           asm volatile("" ::: "memory")
+#define CPUINFO_PROC    "core ID"
+#endif
+
 #define barrier() asm volatile ("" ::: "memory")
 
 #ifndef cpu_relax
@@ -247,13 +254,14 @@ enum perf_call_graph_mode {
         CALLCHAIN_DWARF
 };
 
-struct perf_record_opts {
+struct record_opts {
         struct target target;
         int          call_graph;
         bool         group;
         bool         inherit_stat;
-        bool         no_delay;
+        bool         no_buffering;
         bool         no_inherit;
+        bool         no_inherit_set;
         bool         no_samples;
         bool         raw_samples;
         bool         sample_address;
@@ -268,6 +276,7 @@ struct perf_record_opts {
         u64          user_interval;
         u16          stack_dump_size;
         bool         sample_transaction;
+        unsigned     initial_delay;
 };
 
 #endif
diff --git a/tools/perf/tests/attr/test-record-no-inherit b/tools/perf/tests/attr/test-record-no-inherit
index 9079a25cd643..44edcb2edcd5 100644
--- a/tools/perf/tests/attr/test-record-no-inherit
+++ b/tools/perf/tests/attr/test-record-no-inherit
@@ -3,5 +3,5 @@ command = record
 args    = -i kill >/dev/null 2>&1
 
 [event:base-record]
-sample_type=259
+sample_type=263
 inherit=0
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 85d4919dd623..653a8fe2db95 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -391,7 +391,7 @@ static int do_test_code_reading(bool try_kcore)
         struct machines machines;
         struct machine *machine;
         struct thread *thread;
-        struct perf_record_opts opts = {
+        struct record_opts opts = {
                 .mmap_pages          = UINT_MAX,
                 .user_freq           = UINT_MAX,
                 .user_interval       = ULLONG_MAX,
@@ -540,14 +540,11 @@ static int do_test_code_reading(bool try_kcore)
                 err = TEST_CODE_READING_OK;
 out_err:
         if (evlist) {
-                perf_evlist__munmap(evlist);
-                perf_evlist__close(evlist);
                 perf_evlist__delete(evlist);
-        }
-        if (cpus)
+        } else {
                 cpu_map__delete(cpus);
-        if (threads)
                 thread_map__delete(threads);
+        }
         machines__destroy_kernel_maps(&machines);
         machine__delete_threads(machine);
         machines__exit(&machines);
diff --git a/tools/perf/tests/evsel-roundtrip-name.c b/tools/perf/tests/evsel-roundtrip-name.c
index 0197bda9c461..465cdbc345cf 100644
--- a/tools/perf/tests/evsel-roundtrip-name.c
+++ b/tools/perf/tests/evsel-roundtrip-name.c
@@ -79,7 +79,7 @@ static int __perf_evsel__name_array_test(const char *names[], int nr_names)
         }
 
         err = 0;
-        list_for_each_entry(evsel, &evlist->entries, node) {
+        evlist__for_each(evlist, evsel) {
                 if (strcmp(perf_evsel__name(evsel), names[evsel->idx])) {
                         --err;
                         pr_debug("%s != %s\n", perf_evsel__name(evsel), names[evsel->idx]);
diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c
index 173bf42cc03e..2b6519e0e36f 100644
--- a/tools/perf/tests/hists_link.c
+++ b/tools/perf/tests/hists_link.c
@@ -208,7 +208,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
          * However the second evsel also has a collapsed entry for
          * "bash [libc] malloc" so total 9 entries will be in the tree.
          */
-        list_for_each_entry(evsel, &evlist->entries, node) {
+        evlist__for_each(evlist, evsel) {
                 for (k = 0; k < ARRAY_SIZE(fake_common_samples); k++) {
                         const union perf_event event = {
                                 .header = {
@@ -466,7 +466,7 @@ int test__hists_link(void)
         if (err < 0)
                 goto out;
 
-        list_for_each_entry(evsel, &evlist->entries, node) {
+        evlist__for_each(evlist, evsel) {
                 hists__collapse_resort(&evsel->hists, NULL);
 
                 if (verbose > 2)
diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c
index 376c35608534..497957f269d8 100644
--- a/tools/perf/tests/keep-tracking.c
+++ b/tools/perf/tests/keep-tracking.c
@@ -51,7 +51,7 @@ static int find_comm(struct perf_evlist *evlist, const char *comm)
  */
 int test__keep_tracking(void)
 {
-        struct perf_record_opts opts = {
+        struct record_opts opts = {
                 .mmap_pages          = UINT_MAX,
                 .user_freq           = UINT_MAX,
                 .user_interval       = ULLONG_MAX,
@@ -142,14 +142,11 @@ int test__keep_tracking(void)
 out_err:
         if (evlist) {
                 perf_evlist__disable(evlist);
-                perf_evlist__munmap(evlist);
-                perf_evlist__close(evlist);
                 perf_evlist__delete(evlist);
-        }
-        if (cpus)
+        } else {
                 cpu_map__delete(cpus);
-        if (threads)
                 thread_map__delete(threads);
+        }
 
         return err;
 }
diff --git a/tools/perf/tests/make b/tools/perf/tests/make
index 2ca0abf1b2b6..00544b8b644b 100644
--- a/tools/perf/tests/make
+++ b/tools/perf/tests/make
@@ -1,6 +1,16 @@
 PERF := .
 MK   := Makefile
 
+include config/Makefile.arch
+
+# FIXME looks like x86 is the only arch running tests ;-)
+# we need some IS_(32/64) flag to make this generic
+ifeq ($(IS_X86_64),1)
+lib = lib64
+else
+lib = lib
+endif
+
 has = $(shell which $1 2>/dev/null)
 
 # standard single make variable specified
@@ -106,10 +116,36 @@ test_make_python_perf_so := test -f $(PERF)/python/perf.so
 test_make_perf_o     := test -f $(PERF)/perf.o
 test_make_util_map_o := test -f $(PERF)/util/map.o
 
-test_make_install       := test -x $$TMP_DEST/bin/perf
-test_make_install_O     := $(test_make_install)
-test_make_install_bin   := $(test_make_install)
-test_make_install_bin_O := $(test_make_install)
+define test_dest_files
+  for file in $(1); do                          \
+    if [ ! -x $$TMP_DEST/$$file ]; then         \
+      echo "  failed to find: $$file";          \
+    fi                                          \
+  done
+endef
+
+installed_files_bin := bin/perf
+installed_files_bin += etc/bash_completion.d/perf
+installed_files_bin += libexec/perf-core/perf-archive
+
+installed_files_plugins := $(lib)/traceevent/plugins/plugin_cfg80211.so
+installed_files_plugins += $(lib)/traceevent/plugins/plugin_scsi.so
+installed_files_plugins += $(lib)/traceevent/plugins/plugin_xen.so
+installed_files_plugins += $(lib)/traceevent/plugins/plugin_function.so
+installed_files_plugins += $(lib)/traceevent/plugins/plugin_sched_switch.so
+installed_files_plugins += $(lib)/traceevent/plugins/plugin_mac80211.so
+installed_files_plugins += $(lib)/traceevent/plugins/plugin_kvm.so
+installed_files_plugins += $(lib)/traceevent/plugins/plugin_kmem.so
+installed_files_plugins += $(lib)/traceevent/plugins/plugin_hrtimer.so
+installed_files_plugins += $(lib)/traceevent/plugins/plugin_jbd2.so
+
+installed_files_all := $(installed_files_bin)
+installed_files_all += $(installed_files_plugins)
+
+test_make_install       := $(call test_dest_files,$(installed_files_all))
+test_make_install_O     := $(call test_dest_files,$(installed_files_all))
+test_make_install_bin   := $(call test_dest_files,$(installed_files_bin))
+test_make_install_bin_O := $(call test_dest_files,$(installed_files_bin))
 
 # FIXME nothing gets installed
 test_make_install_man    := test -f $$TMP_DEST/share/man/man1/perf.1
@@ -162,7 +198,7 @@ $(run):
         cmd="cd $(PERF) && make -f $(MK) DESTDIR=$$TMP_DEST $($@)"; \
         echo "- $@: $$cmd" && echo $$cmd > $@ && \
         ( eval $$cmd ) >> $@ 2>&1; \
-        echo "  test: $(call test,$@)"; \
+        echo "  test: $(call test,$@)" >> $@ 2>&1; \
         $(call test,$@) && \
         rm -f $@ \
         rm -rf $$TMP_DEST
@@ -174,16 +210,22 @@ $(run_O):
         cmd="cd $(PERF) && make -f $(MK) O=$$TMP_O DESTDIR=$$TMP_DEST $($(patsubst %_O,%,$@))"; \
         echo "- $@: $$cmd" && echo $$cmd > $@ && \
         ( eval $$cmd ) >> $@ 2>&1 && \
-        echo "  test: $(call test_O,$@)"; \
+        echo "  test: $(call test_O,$@)" >> $@ 2>&1; \
         $(call test_O,$@) && \
         rm -f $@ && \
         rm -rf $$TMP_O \
         rm -rf $$TMP_DEST
 
-all: $(run) $(run_O)
+tarpkg:
+        @cmd="$(PERF)/tests/perf-targz-src-pkg $(PERF)"; \
+        echo "- $@: $$cmd" && echo $$cmd > $@ && \
+        ( eval $$cmd ) >> $@ 2>&1
+        
+
+all: $(run) $(run_O) tarpkg
         @echo OK
 
 out: $(run_O)
         @echo OK
 
-.PHONY: all $(run) $(run_O) clean
+.PHONY: all $(run) $(run_O) tarpkg clean
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index d64ab79c6d35..142263492f6f 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -68,7 +68,7 @@ int test__basic_mmap(void)
                 evsels[i] = perf_evsel__newtp("syscalls", name);
                 if (evsels[i] == NULL) {
                         pr_debug("perf_evsel__new\n");
-                        goto out_free_evlist;
+                        goto out_delete_evlist;
                 }
 
                 evsels[i]->attr.wakeup_events = 1;
@@ -80,7 +80,7 @@ int test__basic_mmap(void)
                         pr_debug("failed to open counter: %s, "
                                  "tweak /proc/sys/kernel/perf_event_paranoid?\n",
                                  strerror(errno));
-                        goto out_close_fd;
+                        goto out_delete_evlist;
                 }
 
                 nr_events[i] = 0;
@@ -90,7 +90,7 @@ int test__basic_mmap(void)
         if (perf_evlist__mmap(evlist, 128, true) < 0) {
                 pr_debug("failed to mmap events: %d (%s)\n", errno,
                          strerror(errno));
-                goto out_close_fd;
+                goto out_delete_evlist;
         }
 
         for (i = 0; i < nsyscalls; ++i)
@@ -105,13 +105,13 @@ int test__basic_mmap(void)
                 if (event->header.type != PERF_RECORD_SAMPLE) {
                         pr_debug("unexpected %s event\n",
                                  perf_event__name(event->header.type));
-                        goto out_munmap;
+                        goto out_delete_evlist;
                 }
 
                 err = perf_evlist__parse_sample(evlist, event, &sample);
                 if (err) {
                         pr_err("Can't parse sample, err = %d\n", err);
-                        goto out_munmap;
+                        goto out_delete_evlist;
                 }
 
                 err = -1;
@@ -119,30 +119,27 @@ int test__basic_mmap(void)
                 if (evsel == NULL) {
                         pr_debug("event with id %" PRIu64
                                  " doesn't map to an evsel\n", sample.id);
-                        goto out_munmap;
+                        goto out_delete_evlist;
                 }
                 nr_events[evsel->idx]++;
                 perf_evlist__mmap_consume(evlist, 0);
         }
 
         err = 0;
-        list_for_each_entry(evsel, &evlist->entries, node) {
+        evlist__for_each(evlist, evsel) {
                 if (nr_events[evsel->idx] != expected_nr_events[evsel->idx]) {
                         pr_debug("expected %d %s events, got %d\n",
                                  expected_nr_events[evsel->idx],
                                  perf_evsel__name(evsel), nr_events[evsel->idx]);
                         err = -1;
-                        goto out_munmap;
+                        goto out_delete_evlist;
                 }
         }
 
-out_munmap:
-        perf_evlist__munmap(evlist);
-out_close_fd:
-        for (i = 0; i < nsyscalls; ++i)
-                perf_evsel__close_fd(evsels[i], 1, threads->nr);
-out_free_evlist:
+out_delete_evlist:
         perf_evlist__delete(evlist);
+        cpus    = NULL;
+        threads = NULL;
 out_free_cpus:
         cpu_map__delete(cpus);
 out_free_threads:
diff --git a/tools/perf/tests/open-syscall-tp-fields.c b/tools/perf/tests/open-syscall-tp-fields.c
index 41cc0badb74b..c505ef2af245 100644
--- a/tools/perf/tests/open-syscall-tp-fields.c
+++ b/tools/perf/tests/open-syscall-tp-fields.c
@@ -6,15 +6,15 @@
 
 int test__syscall_open_tp_fields(void)
 {
-        struct perf_record_opts opts = {
+        struct record_opts opts = {
                 .target = {
                         .uid = UINT_MAX,
                         .uses_mmap = true,
                 },
-                .no_delay   = true,
-                .freq       = 1,
-                .mmap_pages = 256,
-                .raw_samples = true,
+                .no_buffering = true,
+                .freq         = 1,
+                .mmap_pages   = 256,
+                .raw_samples  = true,
         };
         const char *filename = "/etc/passwd";
         int flags = O_RDONLY | O_DIRECTORY;
@@ -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_maps;
+                goto out_delete_evlist;
         }
 
         err = perf_evlist__mmap(evlist, UINT_MAX, false);
         if (err < 0) {
                 pr_debug("perf_evlist__mmap: %s\n", strerror(errno));
-                goto out_close_evlist;
+                goto out_delete_evlist;
         }
 
         perf_evlist__enable(evlist);
@@ -85,7 +85,7 @@ int test__syscall_open_tp_fields(void)
                                 err = perf_evsel__parse_sample(evsel, event, &sample);
                                 if (err) {
                                         pr_err("Can't parse sample, err = %d\n", err);
-                                        goto out_munmap;
+                                        goto out_delete_evlist;
                                 }
 
                                 tp_flags = perf_evsel__intval(evsel, &sample, "flags");
@@ -93,7 +93,7 @@ int test__syscall_open_tp_fields(void)
                                 if (flags != tp_flags) {
                                         pr_debug("%s: Expected flags=%#x, got %#x\n",
                                                  __func__, flags, tp_flags);
-                                        goto out_munmap;
+                                        goto out_delete_evlist;
                                 }
 
                                 goto out_ok;
@@ -105,17 +105,11 @@ int test__syscall_open_tp_fields(void)
 
                 if (++nr_polls > 5) {
                         pr_debug("%s: no events!\n", __func__);
-                        goto out_munmap;
+                        goto out_delete_evlist;
                 }
         }
 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 3cbd10496087..4db0ae617d70 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 "fs.h"
-#include <lk/debugfs.h>
+#include <api/fs/debugfs.h>
 #include "tests.h"
 #include <linux/hw_breakpoint.h>
 
@@ -30,7 +30,7 @@ static int test__checkevent_tracepoint_multi(struct perf_evlist *evlist)
         TEST_ASSERT_VAL("wrong number of entries", evlist->nr_entries > 1);
         TEST_ASSERT_VAL("wrong number of groups", 0 == evlist->nr_groups);
 
-        list_for_each_entry(evsel, &evlist->entries, node) {
+        evlist__for_each(evlist, evsel) {
                 TEST_ASSERT_VAL("wrong type",
                         PERF_TYPE_TRACEPOINT == evsel->attr.type);
                 TEST_ASSERT_VAL("wrong sample_type",
@@ -201,7 +201,7 @@ test__checkevent_tracepoint_multi_modifier(struct perf_evlist *evlist)
 
         TEST_ASSERT_VAL("wrong number of entries", evlist->nr_entries > 1);
 
-        list_for_each_entry(evsel, &evlist->entries, node) {
+        evlist__for_each(evlist, evsel) {
                 TEST_ASSERT_VAL("wrong exclude_user",
                                 !evsel->attr.exclude_user);
                 TEST_ASSERT_VAL("wrong exclude_kernel",
@@ -1385,10 +1385,10 @@ static int test_event(struct evlist_test *e)
         if (ret) {
                 pr_debug("failed to parse event '%s', err %d\n",
                          e->name, ret);
-                return ret;
+        } else {
+                ret = e->check(evlist);
         }
-
-        ret = e->check(evlist);
+        
         perf_evlist__delete(evlist);
 
         return ret;
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index 93a62b06c3af..aca1a83dd13a 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -34,14 +34,14 @@ realloc:
 
 int test__PERF_RECORD(void)
 {
-        struct perf_record_opts opts = {
+        struct record_opts opts = {
                 .target = {
                         .uid = UINT_MAX,
                         .uses_mmap = true,
                 },
-                .no_delay   = true,
-                .freq       = 10,
-                .mmap_pages = 256,
+                .no_buffering = true,
+                .freq         = 10,
+                .mmap_pages   = 256,
         };
         cpu_set_t cpu_mask;
         size_t cpu_mask_size = sizeof(cpu_mask);
@@ -83,11 +83,10 @@ 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.target, argv,
-                                            false, false);
+        err = perf_evlist__prepare_workload(evlist, &opts.target, argv, false, NULL);
         if (err < 0) {
                 pr_debug("Couldn't run the workload!\n");
-                goto out_delete_maps;
+                goto out_delete_evlist;
         }
 
         /*
@@ -102,7 +101,7 @@ int test__PERF_RECORD(void)
         err = sched__get_first_possible_cpu(evlist->workload.pid, &cpu_mask);
         if (err < 0) {
                 pr_debug("sched__get_first_possible_cpu: %s\n", strerror(errno));
-                goto out_delete_maps;
+                goto out_delete_evlist;
         }
 
         cpu = err;
@@ -112,7 +111,7 @@ int test__PERF_RECORD(void)
          */
         if (sched_setaffinity(evlist->workload.pid, cpu_mask_size, &cpu_mask) < 0) {
                 pr_debug("sched_setaffinity: %s\n", strerror(errno));
-                goto out_delete_maps;
+                goto out_delete_evlist;
         }
 
         /*
@@ -122,7 +121,7 @@ int test__PERF_RECORD(void)
         err = perf_evlist__open(evlist);
         if (err < 0) {
                 pr_debug("perf_evlist__open: %s\n", strerror(errno));
-                goto out_delete_maps;
+                goto out_delete_evlist;
         }
 
         /*
@@ -133,7 +132,7 @@ 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_close_evlist;
+                goto out_delete_evlist;
         }
 
         /*
@@ -166,7 +165,7 @@ int test__PERF_RECORD(void)
                                         if (verbose)
                                                 perf_event__fprintf(event, stderr);
                                         pr_debug("Couldn't parse sample\n");
-                                        goto out_err;
+                                        goto out_delete_evlist;
                                 }
 
                                 if (verbose) {
@@ -303,12 +302,6 @@ found_exit:
                 pr_debug("PERF_RECORD_MMAP for %s missing!\n", "[vdso]");
                 ++errs;
         }
-out_err:
-        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/perf-targz-src-pkg b/tools/perf/tests/perf-targz-src-pkg
new file mode 100755
index 000000000000..238aa3927c71
--- /dev/null
+++ b/tools/perf/tests/perf-targz-src-pkg
@@ -0,0 +1,21 @@
+#!/bin/sh
+# Test one of the main kernel Makefile targets to generate a perf sources tarball
+# suitable for build outside the full kernel sources.
+#
+# This is to test that the tools/perf/MANIFEST file lists all the files needed to
+# be in such tarball, which sometimes gets broken when we move files around,
+# like when we made some files that were in tools/perf/ available to other tools/
+# codebases by moving it to tools/include/, etc.
+
+PERF=$1
+cd ${PERF}/../..
+make perf-targz-src-pkg > /dev/null
+TARBALL=$(ls -rt perf-*.tar.gz)
+TMP_DEST=$(mktemp -d)
+tar xf ${TARBALL} -C $TMP_DEST
+rm -f ${TARBALL}
+cd - > /dev/null
+make -C $TMP_DEST/perf*/tools/perf > /dev/null 2>&1
+RC=$?
+rm -rf ${TMP_DEST}
+exit $RC
diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c
index 4ca1b938f6a6..47146d388dbf 100644
--- a/tools/perf/tests/perf-time-to-tsc.c
+++ b/tools/perf/tests/perf-time-to-tsc.c
@@ -46,7 +46,7 @@ static u64 rdtsc(void)
  */
 int test__perf_time_to_tsc(void)
 {
-        struct perf_record_opts opts = {
+        struct record_opts opts = {
                 .mmap_pages          = UINT_MAX,
                 .user_freq           = UINT_MAX,
                 .user_interval       = ULLONG_MAX,
@@ -166,14 +166,8 @@ next_event:
 out_err:
         if (evlist) {
                 perf_evlist__disable(evlist);
-                perf_evlist__munmap(evlist);
-                perf_evlist__close(evlist);
                 perf_evlist__delete(evlist);
         }
-        if (cpus)
-                cpu_map__delete(cpus);
-        if (threads)
-                thread_map__delete(threads);
 
         return err;
 }
diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
index 6664a7cd828c..983d6b8562a8 100644
--- a/tools/perf/tests/sw-clock.c
+++ b/tools/perf/tests/sw-clock.c
@@ -45,7 +45,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
         evsel = perf_evsel__new(&attr);
         if (evsel == NULL) {
                 pr_debug("perf_evsel__new\n");
-                goto out_free_evlist;
+                goto out_delete_evlist;
         }
         perf_evlist__add(evlist, evsel);
 
@@ -54,7 +54,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
         if (!evlist->cpus || !evlist->threads) {
                 err = -ENOMEM;
                 pr_debug("Not enough memory to create thread/cpu maps\n");
-                goto out_delete_maps;
+                goto out_delete_evlist;
         }
 
         if (perf_evlist__open(evlist)) {
@@ -63,14 +63,14 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
                 err = -errno;
                 pr_debug("Couldn't open evlist: %s\nHint: check %s, using %" PRIu64 " in this test.\n",
                          strerror(errno), knob, (u64)attr.sample_freq);
-                goto out_delete_maps;
+                goto out_delete_evlist;
         }
 
         err = perf_evlist__mmap(evlist, 128, true);
         if (err < 0) {
                 pr_debug("failed to mmap event: %d (%s)\n", errno,
                          strerror(errno));
-                goto out_close_evlist;
+                goto out_delete_evlist;
         }
 
         perf_evlist__enable(evlist);
@@ -90,7 +90,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
                 err = perf_evlist__parse_sample(evlist, event, &sample);
                 if (err < 0) {
                         pr_debug("Error during parse sample\n");
-                        goto out_unmap_evlist;
+                        goto out_delete_evlist;
                 }
 
                 total_periods += sample.period;
@@ -105,13 +105,7 @@ next_event:
                 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:
+out_delete_evlist:
         perf_evlist__delete(evlist);
         return err;
 }
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index d09ab579119e..5ff3db318f12 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -9,12 +9,21 @@
 static int exited;
 static int nr_exit;
 
-static void sig_handler(int sig)
+static void sig_handler(int sig __maybe_unused)
 {
         exited = 1;
+}
 
-        if (sig == SIGUSR1)
-                nr_exit = -1;
+/*
+ * perf_evlist__prepare_workload will send a SIGUSR1 if the fork fails, since
+ * we asked by setting its exec_error to this handler.
+ */
+static void workload_exec_failed_signal(int signo __maybe_unused,
+                                        siginfo_t *info __maybe_unused,
+                                        void *ucontext __maybe_unused)
+{
+        exited  = 1;
+        nr_exit = -1;
 }
 
 /*
@@ -35,7 +44,6 @@ int test__task_exit(void)
         const char *argv[] = { "true", NULL };
 
         signal(SIGCHLD, sig_handler);
-        signal(SIGUSR1, sig_handler);
 
         evlist = perf_evlist__new_default();
         if (evlist == NULL) {
@@ -54,13 +62,14 @@ int test__task_exit(void)
         if (!evlist->cpus || !evlist->threads) {
                 err = -ENOMEM;
                 pr_debug("Not enough memory to create thread/cpu maps\n");
-                goto out_delete_maps;
+                goto out_delete_evlist;
         }
 
-        err = perf_evlist__prepare_workload(evlist, &target, argv, false, true);
+        err = perf_evlist__prepare_workload(evlist, &target, argv, false,
+                                            workload_exec_failed_signal);
         if (err < 0) {
                 pr_debug("Couldn't run the workload!\n");
-                goto out_delete_maps;
+                goto out_delete_evlist;
         }
 
         evsel = perf_evlist__first(evlist);
@@ -74,13 +83,13 @@ int test__task_exit(void)
         err = perf_evlist__open(evlist);
         if (err < 0) {
                 pr_debug("Couldn't open the evlist: %s\n", strerror(-err));
-                goto out_delete_maps;
+                goto out_delete_evlist;
         }
 
         if (perf_evlist__mmap(evlist, 128, true) < 0) {
                 pr_debug("failed to mmap events: %d (%s)\n", errno,
                          strerror(errno));
-                goto out_close_evlist;
+                goto out_delete_evlist;
         }
 
         perf_evlist__start_workload(evlist);
@@ -103,11 +112,7 @@ retry:
                 err = -1;
         }
 
-        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);
         return err;
 }
diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c
index cbaa7af45513..d11541d4d7d7 100644
--- a/tools/perf/ui/browser.c
+++ b/tools/perf/ui/browser.c
@@ -256,8 +256,7 @@ int ui_browser__show(struct ui_browser *browser, const char *title,
         __ui_browser__show_title(browser, title);
 
         browser->title = title;
-        free(browser->helpline);
-        browser->helpline = NULL;
+        zfree(&browser->helpline);
 
         va_start(ap, helpline);
         err = vasprintf(&browser->helpline, helpline, ap);
@@ -268,12 +267,11 @@ int ui_browser__show(struct ui_browser *browser, const char *title,
         return err ? 0 : -1;
 }
 
-void ui_browser__hide(struct ui_browser *browser __maybe_unused)
+void ui_browser__hide(struct ui_browser *browser)
 {
         pthread_mutex_lock(&ui__lock);
         ui_helpline__pop();
-        free(browser->helpline);
-        browser->helpline = NULL;
+        zfree(&browser->helpline);
         pthread_mutex_unlock(&ui__lock);
 }
 
diff --git a/tools/perf/ui/browser.h b/tools/perf/ui/browser.h
index 7d45d2f53601..118cca29dd26 100644
--- a/tools/perf/ui/browser.h
+++ b/tools/perf/ui/browser.h
@@ -59,6 +59,8 @@ int ui_browser__help_window(struct ui_browser *browser, const char *text);
 bool ui_browser__dialog_yesno(struct ui_browser *browser, const char *text);
 int ui_browser__input_window(const char *title, const char *text, char *input,
                              const char *exit_msg, int delay_sec);
+struct perf_session_env;
+int tui__header_window(struct perf_session_env *env);
 
 void ui_browser__argv_seek(struct ui_browser *browser, off_t offset, int whence);
 unsigned int ui_browser__argv_refresh(struct ui_browser *browser);
diff --git a/tools/perf/ui/browsers/header.c b/tools/perf/ui/browsers/header.c
new file mode 100644
index 000000000000..89c16b988618
--- /dev/null
+++ b/tools/perf/ui/browsers/header.c
@@ -0,0 +1,127 @@
+#include "util/cache.h"
+#include "util/debug.h"
+#include "ui/browser.h"
+#include "ui/ui.h"
+#include "ui/util.h"
+#include "ui/libslang.h"
+#include "util/header.h"
+#include "util/session.h"
+
+static void ui_browser__argv_write(struct ui_browser *browser,
+                                   void *entry, int row)
+{
+        char **arg = entry;
+        char *str = *arg;
+        char empty[] = " ";
+        bool current_entry = ui_browser__is_current_entry(browser, row);
+        unsigned long offset = (unsigned long)browser->priv;
+
+        if (offset >= strlen(str))
+                str = empty;
+        else
+                str = str + offset;
+
+        ui_browser__set_color(browser, current_entry ? HE_COLORSET_SELECTED :
+                                                       HE_COLORSET_NORMAL);
+
+        slsmg_write_nstring(str, browser->width);
+}
+
+static int list_menu__run(struct ui_browser *menu)
+{
+        int key;
+        unsigned long offset;
+        const char help[] =
+        "h/?/F1        Show this window\n"
+        "UP/DOWN/PGUP\n"
+        "PGDN/SPACE\n"
+        "LEFT/RIGHT    Navigate\n"
+        "q/ESC/CTRL+C  Exit browser";
+
+        if (ui_browser__show(menu, "Header information", "Press 'q' to exit") < 0)
+                return -1;
+
+        while (1) {
+                key = ui_browser__run(menu, 0);
+
+                switch (key) {
+                case K_RIGHT:
+                        offset = (unsigned long)menu->priv;
+                        offset += 10;
+                        menu->priv = (void *)offset;
+                        continue;
+                case K_LEFT:
+                        offset = (unsigned long)menu->priv;
+                        if (offset >= 10)
+                                offset -= 10;
+                        menu->priv = (void *)offset;
+                        continue;
+                case K_F1:
+                case 'h':
+                case '?':
+                        ui_browser__help_window(menu, help);
+                        continue;
+                case K_ESC:
+                case 'q':
+                case CTRL('c'):
+                        key = -1;
+                        break;
+                default:
+                        continue;
+                }
+
+                break;
+        }
+
+        ui_browser__hide(menu);
+        return key;
+}
+
+static int ui__list_menu(int argc, char * const argv[])
+{
+        struct ui_browser menu = {
+                .entries    = (void *)argv,
+                .refresh    = ui_browser__argv_refresh,
+                .seek       = ui_browser__argv_seek,
+                .write      = ui_browser__argv_write,
+                .nr_entries = argc,
+        };
+
+        return list_menu__run(&menu);
+}
+
+int tui__header_window(struct perf_session_env *env)
+{
+        int i, argc = 0;
+        char **argv;
+        struct perf_session *session;
+        char *ptr, *pos;
+        size_t size;
+        FILE *fp = open_memstream(&ptr, &size);
+
+        session = container_of(env, struct perf_session, header.env);
+        perf_header__fprintf_info(session, fp, true);
+        fclose(fp);
+
+        for (pos = ptr, argc = 0; (pos = strchr(pos, '\n')) != NULL; pos++)
+                argc++;
+
+        argv = calloc(argc + 1, sizeof(*argv));
+        if (argv == NULL)
+                goto out;
+
+        argv[0] = pos = ptr;
+        for (i = 1; (pos = strchr(pos, '\n')) != NULL; i++) {
+                *pos++ = '\0';
+                argv[i] = pos;
+        }
+
+        BUG_ON(i != argc + 1);
+
+        ui__list_menu(argc, argv);
+
+out:
+        free(argv);
+        free(ptr);
+        return 0;
+}
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index a440e03cd8c2..b720b92eba6e 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -1267,10 +1267,8 @@ static inline void free_popup_options(char **options, int n)
 {
         int i;
 
-        for (i = 0; i < n; ++i) {
-                free(options[i]);
-                options[i] = NULL;
-        }
+        for (i = 0; i < n; ++i)
+                zfree(&options[i]);
 }
 
 /* Check whether the browser is for 'top' or 'report' */
@@ -1329,7 +1327,7 @@ static int switch_data_file(void)
 
                         abs_path[nr_options] = strdup(path);
                         if (!abs_path[nr_options]) {
-                                free(options[nr_options]);
+                                zfree(&options[nr_options]);
                                 ui__warning("Can't search all data files due to memory shortage.\n");
                                 fclose(file);
                                 break;
@@ -1400,6 +1398,36 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
         char script_opt[64];
         int delay_secs = hbt ? hbt->refresh : 0;
 
+#define HIST_BROWSER_HELP_COMMON                                        \
+        "h/?/F1        Show this window\n"                              \
+        "UP/DOWN/PGUP\n"                                                \
+        "PGDN/SPACE    Navigate\n"                                      \
+        "q/ESC/CTRL+C  Exit browser\n\n"                                \
+        "For multiple event sessions:\n\n"                              \
+        "TAB/UNTAB     Switch events\n\n"                               \
+        "For symbolic views (--sort has sym):\n\n"                      \
+        "->            Zoom into DSO/Threads & Annotate current symbol\n" \
+        "<-            Zoom out\n"                                      \
+        "a             Annotate current symbol\n"                       \
+        "C             Collapse all callchains\n"                       \
+        "d             Zoom into current DSO\n"                         \
+        "E             Expand all callchains\n"                         \
+
+        /* help messages are sorted by lexical order of the hotkey */
+        const char report_help[] = HIST_BROWSER_HELP_COMMON
+        "i             Show header information\n"
+        "P             Print histograms to perf.hist.N\n"
+        "r             Run available scripts\n"
+        "s             Switch to another data file in PWD\n"
+        "t             Zoom into current Thread\n"
+        "V             Verbose (DSO names in callchains, etc)\n"
+        "/             Filter symbol by name";
+        const char top_help[] = HIST_BROWSER_HELP_COMMON
+        "P             Print histograms to perf.hist.N\n"
+        "t             Zoom into current Thread\n"
+        "V             Verbose (DSO names in callchains, etc)\n"
+        "/             Filter symbol by name";
+
         if (browser == NULL)
                 return -1;
 
@@ -1484,29 +1512,16 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
                         if (is_report_browser(hbt))
                                 goto do_data_switch;
                         continue;
+                case 'i':
+                        /* env->arch is NULL for live-mode (i.e. perf top) */
+                        if (env->arch)
+                                tui__header_window(env);
+                        continue;
                 case K_F1:
                 case 'h':
                 case '?':
                         ui_browser__help_window(&browser->b,
-                                        "h/?/F1        Show this window\n"
-                                        "UP/DOWN/PGUP\n"
-                                        "PGDN/SPACE    Navigate\n"
-                                        "q/ESC/CTRL+C  Exit browser\n\n"
-                                        "For multiple event sessions:\n\n"
-                                        "TAB/UNTAB Switch events\n\n"
-                                        "For symbolic views (--sort has sym):\n\n"
-                                        "->            Zoom into DSO/Threads & Annotate current symbol\n"
-                                        "<-            Zoom out\n"
-                                        "a             Annotate current symbol\n"
-                                        "C             Collapse all callchains\n"
-                                        "E             Expand all callchains\n"
-                                        "d             Zoom into current DSO\n"
-                                        "t             Zoom into current Thread\n"
-                                        "r             Run available scripts('perf report' only)\n"
-                                        "s             Switch to another data file in PWD ('perf report' only)\n"
-                                        "P             Print histograms to perf.hist.N\n"
-                                        "V             Verbose (DSO names in callchains, etc)\n"
-                                        "/             Filter symbol by name");
+                                is_report_browser(hbt) ? report_help : top_help);
                         continue;
                 case K_ENTER:
                 case K_RIGHT:
@@ -1923,7 +1938,7 @@ static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist,
 
         ui_helpline__push("Press ESC to exit");
 
-        list_for_each_entry(pos, &evlist->entries, node) {
+        evlist__for_each(evlist, pos) {
                 const char *ev_name = perf_evsel__name(pos);
                 size_t line_len = strlen(ev_name) + 7;
 
@@ -1955,9 +1970,10 @@ single_entry:
                 struct perf_evsel *pos;
 
                 nr_entries = 0;
-                list_for_each_entry(pos, &evlist->entries, node)
+                evlist__for_each(evlist, pos) {
                         if (perf_evsel__is_group_leader(pos))
                                 nr_entries++;
+                }
 
                 if (nr_entries == 1)
                         goto single_entry;
diff --git a/tools/perf/ui/browsers/scripts.c b/tools/perf/ui/browsers/scripts.c
index d63c68ea02a8..402d2bd30b09 100644
--- a/tools/perf/ui/browsers/scripts.c
+++ b/tools/perf/ui/browsers/scripts.c
@@ -173,8 +173,7 @@ int script_browse(const char *script_opt)
         if (script.b.width > AVERAGE_LINE_LEN)
                 script.b.width = AVERAGE_LINE_LEN;
 
-        if (line)
-                free(line);
+        free(line);
         pclose(fp);
 
         script.nr_lines = nr_entries;
diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c
index 2ca66cc1160f..5b95c44f3435 100644
--- a/tools/perf/ui/gtk/hists.c
+++ b/tools/perf/ui/gtk/hists.c
@@ -375,7 +375,7 @@ int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist,
 
         gtk_container_add(GTK_CONTAINER(window), vbox);
 
-        list_for_each_entry(pos, &evlist->entries, node) {
+        evlist__for_each(evlist, pos) {
                 struct hists *hists = &pos->hists;
                 const char *evname = perf_evsel__name(pos);
                 GtkWidget *scrolled_window;
diff --git a/tools/perf/ui/gtk/util.c b/tools/perf/ui/gtk/util.c
index 696c1fbe4248..52e7fc48af9f 100644
--- a/tools/perf/ui/gtk/util.c
+++ b/tools/perf/ui/gtk/util.c
@@ -23,8 +23,7 @@ int perf_gtk__deactivate_context(struct perf_gtk_context **ctx)
         if (!perf_gtk__is_active_context(*ctx))
                 return -1;
 
-        free(*ctx);
-        *ctx = NULL;
+        zfree(ctx);
         return 0;
 }
 
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index c244cb524ef2..831fbb77d1ff 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -510,7 +510,7 @@ print_entries:
 
         free(line);
 out:
-        free(rem_sq_bracket);
+        zfree(&rem_sq_bracket);
 
         return ret;
 }
diff --git a/tools/perf/ui/tui/util.c b/tools/perf/ui/tui/util.c
index 092902e30cee..bf890f72fe80 100644
--- a/tools/perf/ui/tui/util.c
+++ b/tools/perf/ui/tui/util.c
@@ -92,6 +92,8 @@ int ui_browser__input_window(const char *title, const char *text, char *input,
                 t = sep + 1;
         }
 
+        pthread_mutex_lock(&ui__lock);
+
         max_len += 2;
         nr_lines += 8;
         y = SLtt_Screen_Rows / 2 - nr_lines / 2;
@@ -120,13 +122,19 @@ int ui_browser__input_window(const char *title, const char *text, char *input,
         SLsmg_write_nstring((char *)exit_msg, max_len);
         SLsmg_refresh();
 
+        pthread_mutex_unlock(&ui__lock);
+
         x += 2;
         len = 0;
         key = ui__getch(delay_secs);
         while (key != K_TIMER && key != K_ENTER && key != K_ESC) {
+                pthread_mutex_lock(&ui__lock);
+
                 if (key == K_BKSPC) {
-                        if (len == 0)
+                        if (len == 0) {
+                                pthread_mutex_unlock(&ui__lock);
                                 goto next_key;
+                        }
                         SLsmg_gotorc(y, x + --len);
                         SLsmg_write_char(' ');
                 } else {
@@ -136,6 +144,8 @@ int ui_browser__input_window(const char *title, const char *text, char *input,
                 }
                 SLsmg_refresh();
 
+                pthread_mutex_unlock(&ui__lock);
+
                 /* XXX more graceful overflow handling needed */
                 if (len == sizeof(buf) - 1) {
                         ui_helpline__push("maximum size of symbol name reached!");
@@ -174,6 +184,8 @@ int ui__question_window(const char *title, const char *text,
                 t = sep + 1;
         }
 
+        pthread_mutex_lock(&ui__lock);
+
         max_len += 2;
         nr_lines += 4;
         y = SLtt_Screen_Rows / 2 - nr_lines / 2,
@@ -195,6 +207,9 @@ int ui__question_window(const char *title, const char *text,
         SLsmg_gotorc(y + nr_lines - 1, x);
         SLsmg_write_nstring((char *)exit_msg, max_len);
         SLsmg_refresh();
+
+        pthread_mutex_unlock(&ui__lock);
+
         return ui__getch(delay_secs);
 }
 
@@ -215,9 +230,7 @@ static int __ui__warning(const char *title, const char *format, va_list args)
         if (vasprintf(&s, format, args) > 0) {
                 int key;
 
-                pthread_mutex_lock(&ui__lock);
                 key = ui__question_window(title, s, "Press any key...", 0);
-                pthread_mutex_unlock(&ui__lock);
                 free(s);
                 return key;
         }
diff --git a/tools/perf/util/alias.c b/tools/perf/util/alias.c
index e6d134773d0a..c0b43ee40d95 100644
--- a/tools/perf/util/alias.c
+++ b/tools/perf/util/alias.c
@@ -55,8 +55,7 @@ int split_cmdline(char *cmdline, const char ***argv)
                                 src++;
                                 c = cmdline[src];
                                 if (!c) {
-                                        free(*argv);
-                                        *argv = NULL;
+                                        zfree(argv);
                                         return error("cmdline ends with \\");
                                 }
                         }
@@ -68,8 +67,7 @@ int split_cmdline(char *cmdline, const char ***argv)
         cmdline[dst] = 0;
 
         if (quoted) {
-                free(*argv);
-                *argv = NULL;
+                zfree(argv);
                 return error("unclosed quote");
         }
 
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index cf6242c92ee2..469eb679fb9d 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -26,10 +26,10 @@ static int disasm_line__parse(char *line, char **namep, char **rawp);
 
 static void ins__delete(struct ins_operands *ops)
 {
-        free(ops->source.raw);
-        free(ops->source.name);
-        free(ops->target.raw);
-        free(ops->target.name);
+        zfree(&ops->source.raw);
+        zfree(&ops->source.name);
+        zfree(&ops->target.raw);
+        zfree(&ops->target.name);
 }
 
 static int ins__raw_scnprintf(struct ins *ins, char *bf, size_t size,
@@ -185,8 +185,7 @@ static int lock__parse(struct ins_operands *ops)
         return 0;
 
 out_free_ops:
-        free(ops->locked.ops);
-        ops->locked.ops = NULL;
+        zfree(&ops->locked.ops);
         return 0;
 }
 
@@ -205,9 +204,9 @@ static int lock__scnprintf(struct ins *ins, char *bf, size_t size,
 
 static void lock__delete(struct ins_operands *ops)
 {
-        free(ops->locked.ops);
-        free(ops->target.raw);
-        free(ops->target.name);
+        zfree(&ops->locked.ops);
+        zfree(&ops->target.raw);
+        zfree(&ops->target.name);
 }
 
 static struct ins_ops lock_ops = {
@@ -256,8 +255,7 @@ static int mov__parse(struct ins_operands *ops)
         return 0;
 
 out_free_source:
-        free(ops->source.raw);
-        ops->source.raw = NULL;
+        zfree(&ops->source.raw);
         return -1;
 }
 
@@ -464,17 +462,12 @@ void symbol__annotate_zero_histograms(struct symbol *sym)
         pthread_mutex_unlock(&notes->lock);
 }
 
-int symbol__inc_addr_samples(struct symbol *sym, struct map *map,
-                             int evidx, u64 addr)
+static int __symbol__inc_addr_samples(struct symbol *sym, struct map *map,
+                                      struct annotation *notes, int evidx, u64 addr)
 {
         unsigned offset;
-        struct annotation *notes;
         struct sym_hist *h;
 
-        notes = symbol__annotation(sym);
-        if (notes->src == NULL)
-                return -ENOMEM;
-
         pr_debug3("%s: addr=%#" PRIx64 "\n", __func__, map->unmap_ip(map, addr));
 
         if (addr < sym->start || addr > sym->end)
@@ -491,6 +484,33 @@ int symbol__inc_addr_samples(struct symbol *sym, struct map *map,
         return 0;
 }
 
+static int symbol__inc_addr_samples(struct symbol *sym, struct map *map,
+                                    int evidx, u64 addr)
+{
+        struct annotation *notes;
+
+        if (sym == NULL || use_browser != 1 || !sort__has_sym)
+                return 0;
+
+        notes = symbol__annotation(sym);
+        if (notes->src == NULL) {
+                if (symbol__alloc_hist(sym) < 0)
+                        return -ENOMEM;
+        }
+
+        return __symbol__inc_addr_samples(sym, map, notes, evidx, addr);
+}
+
+int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, int evidx)
+{
+        return symbol__inc_addr_samples(ams->sym, ams->map, evidx, ams->al_addr);
+}
+
+int hist_entry__inc_addr_samples(struct hist_entry *he, int evidx, u64 ip)
+{
+        return symbol__inc_addr_samples(he->ms.sym, he->ms.map, evidx, ip);
+}
+
 static void disasm_line__init_ins(struct disasm_line *dl)
 {
         dl->ins = ins__find(dl->name);
@@ -538,8 +558,7 @@ static int disasm_line__parse(char *line, char **namep, char **rawp)
         return 0;
 
 out_free_name:
-        free(*namep);
-        *namep = NULL;
+        zfree(namep);
         return -1;
 }
 
@@ -564,7 +583,7 @@ static struct disasm_line *disasm_line__new(s64 offset, char *line, size_t privs
         return dl;
 
 out_free_line:
-        free(dl->line);
+        zfree(&dl->line);
 out_delete:
         free(dl);
         return NULL;
@@ -572,8 +591,8 @@ out_delete:
 
 void disasm_line__free(struct disasm_line *dl)
 {
-        free(dl->line);
-        free(dl->name);
+        zfree(&dl->line);
+        zfree(&dl->name);
         if (dl->ins && dl->ins->ops->free)
                 dl->ins->ops->free(&dl->ops);
         else
@@ -900,7 +919,7 @@ fallback:
                  * cache, or is just a kallsyms file, well, lets hope that this
                  * DSO is the same as when 'perf record' ran.
                  */
-                filename = dso->long_name;
+                filename = (char *)dso->long_name;
                 snprintf(symfs_filename, sizeof(symfs_filename), "%s%s",
                          symbol_conf.symfs, filename);
                 free_filename = false;
@@ -1091,8 +1110,7 @@ static void symbol__free_source_line(struct symbol *sym, int len)
                 src_line = (void *)src_line + sizeof_src_line;
         }
 
-        free(notes->src->lines);
-        notes->src->lines = NULL;
+        zfree(&notes->src->lines);
 }
 
 /* Get the filename:line for the colored entries */
@@ -1376,3 +1394,8 @@ int symbol__tty_annotate(struct symbol *sym, struct map *map,
 
         return 0;
 }
+
+int hist_entry__annotate(struct hist_entry *he, size_t privsize)
+{
+        return symbol__annotate(he->ms.sym, he->ms.map, privsize);
+}
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 834b7b57b788..b2aef59d6bb2 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -132,12 +132,17 @@ static inline struct annotation *symbol__annotation(struct symbol *sym)
         return &a->annotation;
 }
 
-int symbol__inc_addr_samples(struct symbol *sym, struct map *map,
-                             int evidx, u64 addr);
+int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, int evidx);
+
+int hist_entry__inc_addr_samples(struct hist_entry *he, int evidx, u64 addr);
+
 int symbol__alloc_hist(struct symbol *sym);
 void symbol__annotate_zero_histograms(struct symbol *sym);
 
 int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize);
+
+int hist_entry__annotate(struct hist_entry *he, 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,
                             struct perf_evsel *evsel, bool full_paths,
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index a92770c98cc7..6baabe63182b 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -89,7 +89,7 @@ int build_id__sprintf(const u8 *build_id, int len, char *bf)
         return raw - build_id;
 }
 
-char *dso__build_id_filename(struct dso *dso, char *bf, size_t size)
+char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size)
 {
         char build_id_hex[BUILD_ID_SIZE * 2 + 1];
 
diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h
index 929f28a7c14d..845ef865eced 100644
--- a/tools/perf/util/build-id.h
+++ b/tools/perf/util/build-id.h
@@ -10,7 +10,7 @@ extern struct perf_tool build_id__mark_dso_hit_ops;
 struct dso;
 
 int build_id__sprintf(const u8 *build_id, int len, char *bf);
-char *dso__build_id_filename(struct dso *dso, char *bf, size_t size);
+char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size);
 
 int build_id__mark_dso_hit(struct perf_tool *tool, union perf_event *event,
                            struct perf_sample *sample, struct perf_evsel *evsel,
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index e3970e3eaacf..8d9db454f1a9 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -15,8 +15,12 @@
 #include <errno.h>
 #include <math.h>
 
+#include "asm/bug.h"
+
 #include "hist.h"
 #include "util.h"
+#include "sort.h"
+#include "machine.h"
 #include "callchain.h"
 
 __thread struct callchain_cursor callchain_cursor;
@@ -356,19 +360,14 @@ append_chain_children(struct callchain_node *root,
         /* lookup in childrens */
         while (*p) {
                 s64 ret;
-                struct callchain_list *cnode;
 
                 parent = *p;
                 rnode = rb_entry(parent, struct callchain_node, rb_node_in);
-                cnode = list_first_entry(&rnode->val, struct callchain_list,
-                                         list);
 
-                /* just check first entry */
-                ret = match_chain(node, cnode);
-                if (ret == 0) {
-                        append_chain(rnode, cursor, period);
+                /* If at least first entry matches, rely to children */
+                ret = append_chain(rnode, cursor, period);
+                if (ret == 0)
                         goto inc_children_hit;
-                }
 
                 if (ret < 0)
                         p = &parent->rb_left;
@@ -389,11 +388,11 @@ append_chain(struct callchain_node *root,
              struct callchain_cursor *cursor,
              u64 period)
 {
-        struct callchain_cursor_node *curr_snap = cursor->curr;
         struct callchain_list *cnode;
         u64 start = cursor->pos;
         bool found = false;
         u64 matches;
+        int cmp = 0;
 
         /*
          * Lookup in the current node
@@ -408,7 +407,8 @@ append_chain(struct callchain_node *root,
                 if (!node)
                         break;
 
-                if (match_chain(node, cnode) != 0)
+                cmp = match_chain(node, cnode);
+                if (cmp)
                         break;
 
                 found = true;
@@ -418,9 +418,8 @@ append_chain(struct callchain_node *root,
 
         /* matches not, relay no the parent */
         if (!found) {
-                cursor->curr = curr_snap;
-                cursor->pos = start;
-                return -1;
+                WARN_ONCE(!cmp, "Chain comparison error\n");
+                return cmp;
         }
 
         matches = cursor->pos - start;
@@ -531,3 +530,24 @@ int callchain_cursor_append(struct callchain_cursor *cursor,
 
         return 0;
 }
+
+int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent,
+                              struct perf_evsel *evsel, struct addr_location *al,
+                              int max_stack)
+{
+        if (sample->callchain == NULL)
+                return 0;
+
+        if (symbol_conf.use_callchain || sort__has_parent) {
+                return machine__resolve_callchain(al->machine, evsel, al->thread,
+                                                  sample, parent, al, max_stack);
+        }
+        return 0;
+}
+
+int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *sample)
+{
+        if (!symbol_conf.use_callchain)
+                return 0;
+        return callchain_append(he->callchain, &callchain_cursor, sample->period);
+}
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 4f7f989876ec..8ad97e9b119f 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -145,10 +145,16 @@ static inline void callchain_cursor_advance(struct callchain_cursor *cursor)
 }
 
 struct option;
+struct hist_entry;
 
-int record_parse_callchain(const char *arg, struct perf_record_opts *opts);
+int record_parse_callchain(const char *arg, struct record_opts *opts);
 int record_parse_callchain_opt(const struct option *opt, const char *arg, int unset);
 int record_callchain_opt(const struct option *opt, const char *arg, int unset);
 
+int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent,
+                              struct perf_evsel *evsel, struct addr_location *al,
+                              int max_stack);
+int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *sample);
+
 extern const char record_callchain_help[];
 #endif  /* __PERF_CALLCHAIN_H */
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index 96bbda1ddb83..88f7be399432 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -81,7 +81,7 @@ static int add_cgroup(struct perf_evlist *evlist, char *str)
         /*
          * check if cgrp is already defined, if so we reuse it
          */
-        list_for_each_entry(counter, &evlist->entries, node) {
+        evlist__for_each(evlist, counter) {
                 cgrp = counter->cgrp;
                 if (!cgrp)
                         continue;
@@ -110,7 +110,7 @@ static int add_cgroup(struct perf_evlist *evlist, char *str)
          * if add cgroup N, then need to find event N
          */
         n = 0;
-        list_for_each_entry(counter, &evlist->entries, node) {
+        evlist__for_each(evlist, counter) {
                 if (n == nr_cgroups)
                         goto found;
                 n++;
@@ -133,7 +133,7 @@ void close_cgroup(struct cgroup_sel *cgrp)
         /* XXX: not reentrant */
         if (--cgrp->refcnt == 0) {
                 close(cgrp->fd);
-                free(cgrp->name);
+                zfree(&cgrp->name);
                 free(cgrp);
         }
 }
diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c
index 66e44a5019d5..87b8672eb413 100644
--- a/tools/perf/util/color.c
+++ b/tools/perf/util/color.c
@@ -1,6 +1,7 @@
 #include <linux/kernel.h>
 #include "cache.h"
 #include "color.h"
+#include <math.h>
 
 int perf_use_color_default = -1;
 
@@ -298,10 +299,10 @@ const char *get_percent_color(double percent)
          * entries in green - and keep the low overhead places
          * normal:
          */
-        if (percent >= MIN_RED)
+        if (fabs(percent) >= MIN_RED)
                 color = PERF_COLOR_RED;
         else {
-                if (percent > MIN_GREEN)
+                if (fabs(percent) > MIN_GREEN)
                         color = PERF_COLOR_GREEN;
         }
         return color;
@@ -318,15 +319,19 @@ int percent_color_fprintf(FILE *fp, const char *fmt, double percent)
         return r;
 }
 
+int value_color_snprintf(char *bf, size_t size, const char *fmt, double value)
+{
+        const char *color = get_percent_color(value);
+        return color_snprintf(bf, size, color, fmt, value);
+}
+
 int percent_color_snprintf(char *bf, size_t size, const char *fmt, ...)
 {
         va_list args;
         double percent;
-        const char *color;
 
         va_start(args, fmt);
         percent = va_arg(args, double);
         va_end(args);
-        color = get_percent_color(percent);
-        return color_snprintf(bf, size, color, fmt, percent);
+        return value_color_snprintf(bf, size, fmt, percent);
 }
diff --git a/tools/perf/util/color.h b/tools/perf/util/color.h
index fced3840e99c..7ff30a62a132 100644
--- a/tools/perf/util/color.h
+++ b/tools/perf/util/color.h
@@ -39,6 +39,7 @@ int color_fprintf(FILE *fp, const char *color, const char *fmt, ...);
 int color_snprintf(char *bf, size_t size, const char *color, const char *fmt, ...);
 int color_fprintf_ln(FILE *fp, const char *color, const char *fmt, ...);
 int color_fwrite_lines(FILE *fp, const char *color, size_t count, const char *buf);
+int value_color_snprintf(char *bf, size_t size, const char *fmt, double value);
 int percent_color_snprintf(char *bf, size_t size, const char *fmt, ...);
 int percent_color_fprintf(FILE *fp, const char *fmt, double percent);
 const char *get_percent_color(double percent);
diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c
index ee0df0e24cdb..f9e777629e21 100644
--- a/tools/perf/util/comm.c
+++ b/tools/perf/util/comm.c
@@ -21,7 +21,7 @@ static void comm_str__put(struct comm_str *cs)
 {
         if (!--cs->ref) {
                 rb_erase(&cs->rb_node, &comm_str_root);
-                free(cs->str);
+                zfree(&cs->str);
                 free(cs);
         }
 }
@@ -94,19 +94,20 @@ struct comm *comm__new(const char *str, u64 timestamp)
         return comm;
 }
 
-void comm__override(struct comm *comm, const char *str, u64 timestamp)
+int comm__override(struct comm *comm, const char *str, u64 timestamp)
 {
-        struct comm_str *old = comm->comm_str;
+        struct comm_str *new, *old = comm->comm_str;
 
-        comm->comm_str = comm_str__findnew(str, &comm_str_root);
-        if (!comm->comm_str) {
-                comm->comm_str = old;
-                return;
-        }
+        new = comm_str__findnew(str, &comm_str_root);
+        if (!new)
+                return -ENOMEM;
 
-        comm->start = timestamp;
-        comm_str__get(comm->comm_str);
+        comm_str__get(new);
         comm_str__put(old);
+        comm->comm_str = new;
+        comm->start = timestamp;
+
+        return 0;
 }
 
 void comm__free(struct comm *comm)
diff --git a/tools/perf/util/comm.h b/tools/perf/util/comm.h
index 7a86e5656710..fac5bd51befc 100644
--- a/tools/perf/util/comm.h
+++ b/tools/perf/util/comm.h
@@ -16,6 +16,6 @@ struct comm {
 void comm__free(struct comm *comm);
 struct comm *comm__new(const char *str, u64 timestamp);
 const char *comm__str(const struct comm *comm);
-void comm__override(struct comm *comm, const char *str, u64 timestamp);
+int comm__override(struct comm *comm, const char *str, u64 timestamp);
 
 #endif  /* __PERF_COMM_H */
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index 7d09faf85cf1..1fbcd8bdc11b 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -118,3 +118,9 @@ void perf_data_file__close(struct perf_data_file *file)
 {
         close(file->fd);
 }
+
+ssize_t perf_data_file__write(struct perf_data_file *file,
+                              void *buf, size_t size)
+{
+        return writen(file->fd, buf, size);
+}
diff --git a/tools/perf/util/data.h b/tools/perf/util/data.h
index 8c2df80152a5..2b15d0c95c7f 100644
--- a/tools/perf/util/data.h
+++ b/tools/perf/util/data.h
@@ -9,12 +9,12 @@ enum perf_data_mode {
 };
 
 struct perf_data_file {
-        const char *path;
-        int fd;
-        bool is_pipe;
-        bool force;
-        unsigned long size;
-        enum perf_data_mode mode;
+        const char              *path;
+        int                      fd;
+        bool                     is_pipe;
+        bool                     force;
+        unsigned long            size;
+        enum perf_data_mode      mode;
 };
 
 static inline bool perf_data_file__is_read(struct perf_data_file *file)
@@ -44,5 +44,7 @@ static inline unsigned long perf_data_file__size(struct perf_data_file *file)
 
 int perf_data_file__open(struct perf_data_file *file);
 void perf_data_file__close(struct perf_data_file *file);
+ssize_t perf_data_file__write(struct perf_data_file *file,
+                              void *buf, size_t size);
 
 #endif /* __PERF_DATA_H */
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index 399e74c34c1a..299b55586502 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -16,23 +16,46 @@
 int verbose;
 bool dump_trace = false, quiet = false;
 
-int eprintf(int level, const char *fmt, ...)
+static int _eprintf(int level, const char *fmt, va_list args)
 {
-        va_list args;
         int ret = 0;
 
         if (verbose >= level) {
-                va_start(args, fmt);
                 if (use_browser >= 1)
                         ui_helpline__vshow(fmt, args);
                 else
                         ret = vfprintf(stderr, fmt, args);
-                va_end(args);
         }
 
         return ret;
 }
 
+int eprintf(int level, const char *fmt, ...)
+{
+        va_list args;
+        int ret;
+
+        va_start(args, fmt);
+        ret = _eprintf(level, fmt, args);
+        va_end(args);
+
+        return ret;
+}
+
+/*
+ * Overloading libtraceevent standard info print
+ * function, display with -v in perf.
+ */
+void pr_stat(const char *fmt, ...)
+{
+        va_list args;
+
+        va_start(args, fmt);
+        _eprintf(1, fmt, args);
+        va_end(args);
+        eprintf(1, "\n");
+}
+
 int dump_printf(const char *fmt, ...)
 {
         va_list args;
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index efbd98805ad0..443694c36b03 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -17,4 +17,6 @@ void trace_event(union perf_event *event);
 int ui__error(const char *format, ...) __attribute__((format(printf, 1, 2)));
 int ui__warning(const char *format, ...) __attribute__((format(printf, 1, 2)));
 
+void pr_stat(const char *fmt, ...);
+
 #endif  /* __PERF_DEBUG_H */
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index af4c687cc49b..4045d086d9d9 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -28,8 +28,9 @@ char dso__symtab_origin(const struct dso *dso)
         return origin[dso->symtab_type];
 }
 
-int dso__binary_type_file(struct dso *dso, enum dso_binary_type type,
-                          char *root_dir, char *file, size_t size)
+int dso__read_binary_type_filename(const struct dso *dso,
+                                   enum dso_binary_type type,
+                                   char *root_dir, char *filename, size_t size)
 {
         char build_id_hex[BUILD_ID_SIZE * 2 + 1];
         int ret = 0;
@@ -38,36 +39,36 @@ int dso__binary_type_file(struct dso *dso, enum dso_binary_type type,
         case DSO_BINARY_TYPE__DEBUGLINK: {
                 char *debuglink;
 
-                strncpy(file, dso->long_name, size);
-                debuglink = file + dso->long_name_len;
-                while (debuglink != file && *debuglink != '/')
+                strncpy(filename, dso->long_name, size);
+                debuglink = filename + dso->long_name_len;
+                while (debuglink != filename && *debuglink != '/')
                         debuglink--;
                 if (*debuglink == '/')
                         debuglink++;
                 filename__read_debuglink(dso->long_name, debuglink,
-                                         size - (debuglink - file));
+                                         size - (debuglink - filename));
                 }
                 break;
         case DSO_BINARY_TYPE__BUILD_ID_CACHE:
                 /* skip the locally configured cache if a symfs is given */
                 if (symbol_conf.symfs[0] ||
-                    (dso__build_id_filename(dso, file, size) == NULL))
+                    (dso__build_id_filename(dso, filename, size) == NULL))
                         ret = -1;
                 break;
 
         case DSO_BINARY_TYPE__FEDORA_DEBUGINFO:
-                snprintf(file, size, "%s/usr/lib/debug%s.debug",
+                snprintf(filename, size, "%s/usr/lib/debug%s.debug",
                          symbol_conf.symfs, dso->long_name);
                 break;
 
         case DSO_BINARY_TYPE__UBUNTU_DEBUGINFO:
-                snprintf(file, size, "%s/usr/lib/debug%s",
+                snprintf(filename, size, "%s/usr/lib/debug%s",
                          symbol_conf.symfs, dso->long_name);
                 break;
 
         case DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO:
         {
-                char *last_slash;
+                const char *last_slash;
                 size_t len;
                 size_t dir_size;
 
@@ -75,14 +76,14 @@ int dso__binary_type_file(struct dso *dso, enum dso_binary_type type,
                 while (last_slash != dso->long_name && *last_slash != '/')
                         last_slash--;
 
-                len = scnprintf(file, size, "%s", symbol_conf.symfs);
+                len = scnprintf(filename, size, "%s", symbol_conf.symfs);
                 dir_size = last_slash - dso->long_name + 2;
                 if (dir_size > (size - len)) {
                         ret = -1;
                         break;
                 }
-                len += scnprintf(file + len, dir_size, "%s",  dso->long_name);
-                len += scnprintf(file + len , size - len, ".debug%s",
+                len += scnprintf(filename + len, dir_size, "%s",  dso->long_name);
+                len += scnprintf(filename + len , size - len, ".debug%s",
                                                                 last_slash);
                 break;
         }
@@ -96,7 +97,7 @@ int dso__binary_type_file(struct dso *dso, enum dso_binary_type type,
                 build_id__sprintf(dso->build_id,
                                   sizeof(dso->build_id),
                                   build_id_hex);
-                snprintf(file, size,
+                snprintf(filename, size,
                          "%s/usr/lib/debug/.build-id/%.2s/%s.debug",
                          symbol_conf.symfs, build_id_hex, build_id_hex + 2);
                 break;
@@ -104,23 +105,23 @@ int dso__binary_type_file(struct dso *dso, enum dso_binary_type type,
         case DSO_BINARY_TYPE__VMLINUX:
         case DSO_BINARY_TYPE__GUEST_VMLINUX:
         case DSO_BINARY_TYPE__SYSTEM_PATH_DSO:
-                snprintf(file, size, "%s%s",
+                snprintf(filename, size, "%s%s",
                          symbol_conf.symfs, dso->long_name);
                 break;
 
         case DSO_BINARY_TYPE__GUEST_KMODULE:
-                snprintf(file, size, "%s%s%s", symbol_conf.symfs,
+                snprintf(filename, size, "%s%s%s", symbol_conf.symfs,
                          root_dir, dso->long_name);
                 break;
 
         case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE:
-                snprintf(file, size, "%s%s", symbol_conf.symfs,
+                snprintf(filename, size, "%s%s", symbol_conf.symfs,
                          dso->long_name);
                 break;
 
         case DSO_BINARY_TYPE__KCORE:
         case DSO_BINARY_TYPE__GUEST_KCORE:
-                snprintf(file, size, "%s", dso->long_name);
+                snprintf(filename, size, "%s", dso->long_name);
                 break;
 
         default:
@@ -137,19 +138,18 @@ int dso__binary_type_file(struct dso *dso, enum dso_binary_type type,
 
 static int open_dso(struct dso *dso, struct machine *machine)
 {
-        char *root_dir = (char *) "";
-        char *name;
         int fd;
+        char *root_dir = (char *)"";
+        char *name = malloc(PATH_MAX);
 
-        name = malloc(PATH_MAX);
         if (!name)
                 return -ENOMEM;
 
         if (machine)
                 root_dir = machine->root_dir;
 
-        if (dso__binary_type_file(dso, dso->data_type,
-                                  root_dir, name, PATH_MAX)) {
+        if (dso__read_binary_type_filename(dso, dso->binary_type,
+                                            root_dir, name, PATH_MAX)) {
                 free(name);
                 return -EINVAL;
         }
@@ -161,26 +161,26 @@ static int open_dso(struct dso *dso, struct machine *machine)
 
 int dso__data_fd(struct dso *dso, struct machine *machine)
 {
-        static enum dso_binary_type binary_type_data[] = {
+        enum dso_binary_type binary_type_data[] = {
                 DSO_BINARY_TYPE__BUILD_ID_CACHE,
                 DSO_BINARY_TYPE__SYSTEM_PATH_DSO,
                 DSO_BINARY_TYPE__NOT_FOUND,
         };
         int i = 0;
 
-        if (dso->data_type != DSO_BINARY_TYPE__NOT_FOUND)
+        if (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND)
                 return open_dso(dso, machine);
 
         do {
                 int fd;
 
-                dso->data_type = binary_type_data[i++];
+                dso->binary_type = binary_type_data[i++];
 
                 fd = open_dso(dso, machine);
                 if (fd >= 0)
                         return fd;
 
-        } while (dso->data_type != DSO_BINARY_TYPE__NOT_FOUND);
+        } while (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND);
 
         return -EINVAL;
 }
@@ -200,11 +200,10 @@ dso_cache__free(struct rb_root *root)
         }
 }
 
-static struct dso_cache*
-dso_cache__find(struct rb_root *root, u64 offset)
+static struct dso_cache *dso_cache__find(const struct rb_root *root, u64 offset)
 {
-        struct rb_node **p = &root->rb_node;
-        struct rb_node *parent = NULL;
+        struct rb_node * const *p = &root->rb_node;
+        const struct rb_node *parent = NULL;
         struct dso_cache *cache;
 
         while (*p != NULL) {
@@ -379,32 +378,63 @@ struct dso *dso__kernel_findnew(struct machine *machine, const char *name,
          * processing we had no idea this was the kernel dso.
          */
         if (dso != NULL) {
-                dso__set_short_name(dso, short_name);
+                dso__set_short_name(dso, short_name, false);
                 dso->kernel = dso_type;
         }
 
         return dso;
 }
 
-void dso__set_long_name(struct dso *dso, char *name)
+void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated)
 {
         if (name == NULL)
                 return;
-        dso->long_name = name;
-        dso->long_name_len = strlen(name);
+
+        if (dso->long_name_allocated)
+                free((char *)dso->long_name);
+
+        dso->long_name           = name;
+        dso->long_name_len       = strlen(name);
+        dso->long_name_allocated = name_allocated;
 }
 
-void dso__set_short_name(struct dso *dso, const char *name)
+void dso__set_short_name(struct dso *dso, const char *name, bool name_allocated)
 {
         if (name == NULL)
                 return;
-        dso->short_name = name;
-        dso->short_name_len = strlen(name);
+
+        if (dso->short_name_allocated)
+                free((char *)dso->short_name);
+
+        dso->short_name           = name;
+        dso->short_name_len       = strlen(name);
+        dso->short_name_allocated = name_allocated;
 }
 
 static void dso__set_basename(struct dso *dso)
 {
-        dso__set_short_name(dso, basename(dso->long_name));
+       /*
+        * basename() may modify path buffer, so we must pass
+        * a copy.
+        */
+       char *base, *lname = strdup(dso->long_name);
+
+       if (!lname)
+               return;
+
+       /*
+        * basename() may return a pointer to internal
+        * storage which is reused in subsequent calls
+        * so copy the result.
+        */
+       base = strdup(basename(lname));
+
+       free(lname);
+
+       if (!base)
+               return;
+
+       dso__set_short_name(dso, base, true);
 }
 
 int dso__name_len(const struct dso *dso)
@@ -439,18 +469,19 @@ struct dso *dso__new(const char *name)
         if (dso != NULL) {
                 int i;
                 strcpy(dso->name, name);
-                dso__set_long_name(dso, dso->name);
-                dso__set_short_name(dso, dso->name);
+                dso__set_long_name(dso, dso->name, false);
+                dso__set_short_name(dso, dso->name, false);
                 for (i = 0; i < MAP__NR_TYPES; ++i)
                         dso->symbols[i] = dso->symbol_names[i] = RB_ROOT;
                 dso->cache = RB_ROOT;
                 dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND;
-                dso->data_type   = DSO_BINARY_TYPE__NOT_FOUND;
+                dso->binary_type = DSO_BINARY_TYPE__NOT_FOUND;
                 dso->loaded = 0;
                 dso->rel = 0;
                 dso->sorted_by_name = 0;
                 dso->has_build_id = 0;
                 dso->has_srcline = 1;
+                dso->a2l_fails = 1;
                 dso->kernel = DSO_TYPE_USER;
                 dso->needs_swap = DSO_SWAP__UNSET;
                 INIT_LIST_HEAD(&dso->node);
@@ -464,11 +495,20 @@ void dso__delete(struct dso *dso)
         int i;
         for (i = 0; i < MAP__NR_TYPES; ++i)
                 symbols__delete(&dso->symbols[i]);
-        if (dso->sname_alloc)
-                free((char *)dso->short_name);
-        if (dso->lname_alloc)
-                free(dso->long_name);
+
+        if (dso->short_name_allocated) {
+                zfree((char **)&dso->short_name);
+                dso->short_name_allocated = false;
+        }
+
+        if (dso->long_name_allocated) {
+                zfree((char **)&dso->long_name);
+                dso->long_name_allocated = false;
+        }
+
         dso_cache__free(&dso->cache);
+        dso__free_a2l(dso);
+        zfree(&dso->symsrc_filename);
         free(dso);
 }
 
@@ -543,7 +583,7 @@ void dsos__add(struct list_head *head, struct dso *dso)
         list_add_tail(&dso->node, head);
 }
 
-struct dso *dsos__find(struct list_head *head, const char *name, bool cmp_short)
+struct dso *dsos__find(const struct list_head *head, const char *name, bool cmp_short)
 {
         struct dso *pos;
 
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index 9ac666abbe7e..cd7d6f078cdd 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -77,23 +77,26 @@ struct dso {
         struct rb_root   symbols[MAP__NR_TYPES];
         struct rb_root   symbol_names[MAP__NR_TYPES];
         struct rb_root   cache;
+        void             *a2l;
+        char             *symsrc_filename;
+        unsigned int     a2l_fails;
         enum dso_kernel_type    kernel;
         enum dso_swap_type      needs_swap;
         enum dso_binary_type    symtab_type;
-        enum dso_binary_type    data_type;
+        enum dso_binary_type    binary_type;
         u8               adjust_symbols:1;
         u8               has_build_id:1;
         u8               has_srcline:1;
         u8               hit:1;
         u8               annotate_warned:1;
-        u8               sname_alloc:1;
-        u8               lname_alloc:1;
+        u8               short_name_allocated:1;
+        u8               long_name_allocated:1;
         u8               sorted_by_name;
         u8               loaded;
         u8               rel;
         u8               build_id[BUILD_ID_SIZE];
         const char       *short_name;
-        char             *long_name;
+        const char       *long_name;
         u16              long_name_len;
         u16              short_name_len;
         char             name[0];
@@ -107,8 +110,8 @@ static inline void dso__set_loaded(struct dso *dso, enum map_type type)
 struct dso *dso__new(const char *name);
 void dso__delete(struct dso *dso);
 
-void dso__set_short_name(struct dso *dso, const char *name);
-void dso__set_long_name(struct dso *dso, char *name);
+void dso__set_short_name(struct dso *dso, const char *name, bool name_allocated);
+void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated);
 
 int dso__name_len(const struct dso *dso);
 
@@ -125,8 +128,8 @@ void dso__read_running_kernel_build_id(struct dso *dso,
 int dso__kernel_module_get_build_id(struct dso *dso, const char *root_dir);
 
 char dso__symtab_origin(const struct dso *dso);
-int dso__binary_type_file(struct dso *dso, enum dso_binary_type type,
-                          char *root_dir, char *file, size_t size);
+int dso__read_binary_type_filename(const struct dso *dso, enum dso_binary_type type,
+                                   char *root_dir, char *filename, size_t size);
 
 int dso__data_fd(struct dso *dso, struct machine *machine);
 ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
@@ -140,7 +143,7 @@ struct dso *dso__kernel_findnew(struct machine *machine, const char *name,
                                 const char *short_name, int dso_type);
 
 void dsos__add(struct list_head *head, struct dso *dso);
-struct dso *dsos__find(struct list_head *head, const char *name,
+struct dso *dsos__find(const struct list_head *head, const char *name,
                        bool cmp_short);
 struct dso *__dsos__findnew(struct list_head *head, const char *name);
 bool __dsos__read_build_ids(struct list_head *head, bool with_hits);
@@ -156,14 +159,16 @@ size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp);
 
 static inline bool dso__is_vmlinux(struct dso *dso)
 {
-        return dso->data_type == DSO_BINARY_TYPE__VMLINUX ||
-               dso->data_type == DSO_BINARY_TYPE__GUEST_VMLINUX;
+        return dso->binary_type == DSO_BINARY_TYPE__VMLINUX ||
+               dso->binary_type == DSO_BINARY_TYPE__GUEST_VMLINUX;
 }
 
 static inline bool dso__is_kcore(struct dso *dso)
 {
-        return dso->data_type == DSO_BINARY_TYPE__KCORE ||
-               dso->data_type == DSO_BINARY_TYPE__GUEST_KCORE;
+        return dso->binary_type == DSO_BINARY_TYPE__KCORE ||
+               dso->binary_type == DSO_BINARY_TYPE__GUEST_KCORE;
 }
 
+void dso__free_a2l(struct dso *dso);
+
 #endif /* __PERF_DSO */
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index bb788c109fe6..1fc1c2f04772 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -7,6 +7,7 @@
 #include "strlist.h"
 #include "thread.h"
 #include "thread_map.h"
+#include "symbol/kallsyms.h"
 
 static const char *perf_event__names[] = {
         [0]                                     = "TOTAL",
@@ -105,8 +106,12 @@ static pid_t perf_event__synthesize_comm(struct perf_tool *tool,
 
         memset(&event->comm, 0, sizeof(event->comm));
 
-        tgid = perf_event__get_comm_tgid(pid, event->comm.comm,
-                                         sizeof(event->comm.comm));
+        if (machine__is_host(machine))
+                tgid = perf_event__get_comm_tgid(pid, event->comm.comm,
+                                                 sizeof(event->comm.comm));
+        else
+                tgid = machine->pid;
+
         if (tgid < 0)
                 goto out;
 
@@ -128,7 +133,11 @@ static pid_t perf_event__synthesize_comm(struct perf_tool *tool,
                 goto out;
         }
 
-        snprintf(filename, sizeof(filename), "/proc/%d/task", pid);
+        if (machine__is_default_guest(machine))
+                return 0;
+
+        snprintf(filename, sizeof(filename), "%s/proc/%d/task",
+                 machine->root_dir, pid);
 
         tasks = opendir(filename);
         if (tasks == NULL) {
@@ -166,18 +175,22 @@ out:
         return tgid;
 }
 
-static int perf_event__synthesize_mmap_events(struct perf_tool *tool,
-                                              union perf_event *event,
-                                              pid_t pid, pid_t tgid,
-                                              perf_event__handler_t process,
-                                              struct machine *machine,
-                                              bool mmap_data)
+int perf_event__synthesize_mmap_events(struct perf_tool *tool,
+                                       union perf_event *event,
+                                       pid_t pid, pid_t tgid,
+                                       perf_event__handler_t process,
+                                       struct machine *machine,
+                                       bool mmap_data)
 {
         char filename[PATH_MAX];
         FILE *fp;
         int rc = 0;
 
-        snprintf(filename, sizeof(filename), "/proc/%d/maps", pid);
+        if (machine__is_default_guest(machine))
+                return 0;
+
+        snprintf(filename, sizeof(filename), "%s/proc/%d/maps",
+                 machine->root_dir, pid);
 
         fp = fopen(filename, "r");
         if (fp == NULL) {
@@ -217,7 +230,10 @@ static int perf_event__synthesize_mmap_events(struct perf_tool *tool,
                 /*
                  * Just like the kernel, see __perf_event_mmap in kernel/perf_event.c
                  */
-                event->header.misc = PERF_RECORD_MISC_USER;
+                if (machine__is_host(machine))
+                        event->header.misc = PERF_RECORD_MISC_USER;
+                else
+                        event->header.misc = PERF_RECORD_MISC_GUEST_USER;
 
                 if (prot[2] != 'x') {
                         if (!mmap_data || prot[0] != 'r')
@@ -386,6 +402,7 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
                                    struct machine *machine, bool mmap_data)
 {
         DIR *proc;
+        char proc_path[PATH_MAX];
         struct dirent dirent, *next;
         union perf_event *comm_event, *mmap_event;
         int err = -1;
@@ -398,7 +415,12 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
         if (mmap_event == NULL)
                 goto out_free_comm;
 
-        proc = opendir("/proc");
+        if (machine__is_default_guest(machine))
+                return 0;
+
+        snprintf(proc_path, sizeof(proc_path), "%s/proc", machine->root_dir);
+        proc = opendir(proc_path);
+
         if (proc == NULL)
                 goto out_free_mmap;
 
@@ -637,6 +659,7 @@ void thread__find_addr_map(struct thread *thread,
         struct map_groups *mg = &thread->mg;
         bool load_map = false;
 
+        al->machine = machine;
         al->thread = thread;
         al->addr = addr;
         al->cpumode = cpumode;
@@ -657,15 +680,10 @@ void thread__find_addr_map(struct thread *thread,
                 al->level = 'g';
                 mg = &machine->kmaps;
                 load_map = true;
+        } else if (cpumode == PERF_RECORD_MISC_GUEST_USER && perf_guest) {
+                al->level = 'u';
         } else {
-                /*
-                 * 'u' means guest os user space.
-                 * TODO: We don't support guest user space. Might support late.
-                 */
-                if (cpumode == PERF_RECORD_MISC_GUEST_USER && perf_guest)
-                        al->level = 'u';
-                else
-                        al->level = 'H';
+                al->level = 'H';
                 al->map = NULL;
 
                 if ((cpumode == PERF_RECORD_MISC_GUEST_USER ||
@@ -732,8 +750,7 @@ int perf_event__preprocess_sample(const union perf_event *event,
         if (thread == NULL)
                 return -1;
 
-        if (symbol_conf.comm_list &&
-            !strlist__has_entry(symbol_conf.comm_list, thread__comm_str(thread)))
+        if (thread__is_filtered(thread))
                 goto out_filtered;
 
         dump_printf(" ... thread: %s:%d\n", thread__comm_str(thread), thread->tid);
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 30fec9901e44..faf6e219be21 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -266,6 +266,13 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
                                   const struct perf_sample *sample,
                                   bool swapped);
 
+int perf_event__synthesize_mmap_events(struct perf_tool *tool,
+                                       union perf_event *event,
+                                       pid_t pid, pid_t tgid,
+                                       perf_event__handler_t process,
+                                       struct machine *machine,
+                                       bool mmap_data);
+
 size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp);
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index bbc746aa5716..59ef2802fcf6 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 <lk/debugfs.h>
+#include <api/fs/debugfs.h>
 #include <poll.h>
 #include "cpumap.h"
 #include "thread_map.h"
@@ -81,7 +81,7 @@ static void perf_evlist__update_id_pos(struct perf_evlist *evlist)
 {
         struct perf_evsel *evsel;
 
-        list_for_each_entry(evsel, &evlist->entries, node)
+        evlist__for_each(evlist, evsel)
                 perf_evsel__calc_id_pos(evsel);
 
         perf_evlist__set_id_pos(evlist);
@@ -91,7 +91,7 @@ static void perf_evlist__purge(struct perf_evlist *evlist)
 {
         struct perf_evsel *pos, *n;
 
-        list_for_each_entry_safe(pos, n, &evlist->entries, node) {
+        evlist__for_each_safe(evlist, n, pos) {
                 list_del_init(&pos->node);
                 perf_evsel__delete(pos);
         }
@@ -101,14 +101,18 @@ static void perf_evlist__purge(struct perf_evlist *evlist)
 
 void perf_evlist__exit(struct perf_evlist *evlist)
 {
-        free(evlist->mmap);
-        free(evlist->pollfd);
-        evlist->mmap = NULL;
-        evlist->pollfd = NULL;
+        zfree(&evlist->mmap);
+        zfree(&evlist->pollfd);
 }
 
 void perf_evlist__delete(struct perf_evlist *evlist)
 {
+        perf_evlist__munmap(evlist);
+        perf_evlist__close(evlist);
+        cpu_map__delete(evlist->cpus);
+        thread_map__delete(evlist->threads);
+        evlist->cpus = NULL;
+        evlist->threads = NULL;
         perf_evlist__purge(evlist);
         perf_evlist__exit(evlist);
         free(evlist);
@@ -144,7 +148,7 @@ void __perf_evlist__set_leader(struct list_head *list)
 
         leader->nr_members = evsel->idx - leader->idx + 1;
 
-        list_for_each_entry(evsel, list, node) {
+        __evlist__for_each(list, evsel) {
                 evsel->leader = leader;
         }
 }
@@ -203,7 +207,7 @@ static int perf_evlist__add_attrs(struct perf_evlist *evlist,
         return 0;
 
 out_delete_partial_list:
-        list_for_each_entry_safe(evsel, n, &head, node)
+        __evlist__for_each_safe(&head, n, evsel)
                 perf_evsel__delete(evsel);
         return -1;
 }
@@ -224,7 +228,7 @@ perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id)
 {
         struct perf_evsel *evsel;
 
-        list_for_each_entry(evsel, &evlist->entries, node) {
+        evlist__for_each(evlist, evsel) {
                 if (evsel->attr.type   == PERF_TYPE_TRACEPOINT &&
                     (int)evsel->attr.config == id)
                         return evsel;
@@ -239,7 +243,7 @@ perf_evlist__find_tracepoint_by_name(struct perf_evlist *evlist,
 {
         struct perf_evsel *evsel;
 
-        list_for_each_entry(evsel, &evlist->entries, node) {
+        evlist__for_each(evlist, evsel) {
                 if ((evsel->attr.type == PERF_TYPE_TRACEPOINT) &&
                     (strcmp(evsel->name, name) == 0))
                         return evsel;
@@ -269,7 +273,7 @@ void perf_evlist__disable(struct perf_evlist *evlist)
         int nr_threads = thread_map__nr(evlist->threads);
 
         for (cpu = 0; cpu < nr_cpus; cpu++) {
-                list_for_each_entry(pos, &evlist->entries, node) {
+                evlist__for_each(evlist, pos) {
                         if (!perf_evsel__is_group_leader(pos) || !pos->fd)
                                 continue;
                         for (thread = 0; thread < nr_threads; thread++)
@@ -287,7 +291,7 @@ void perf_evlist__enable(struct perf_evlist *evlist)
         int nr_threads = thread_map__nr(evlist->threads);
 
         for (cpu = 0; cpu < nr_cpus; cpu++) {
-                list_for_each_entry(pos, &evlist->entries, node) {
+                evlist__for_each(evlist, pos) {
                         if (!perf_evsel__is_group_leader(pos) || !pos->fd)
                                 continue;
                         for (thread = 0; thread < nr_threads; thread++)
@@ -584,11 +588,13 @@ void perf_evlist__munmap(struct perf_evlist *evlist)
 {
         int i;
 
+        if (evlist->mmap == NULL)
+                return;
+
         for (i = 0; i < evlist->nr_mmaps; i++)
                 __perf_evlist__munmap(evlist, i);
 
-        free(evlist->mmap);
-        evlist->mmap = NULL;
+        zfree(&evlist->mmap);
 }
 
 static int perf_evlist__alloc_mmap(struct perf_evlist *evlist)
@@ -624,7 +630,7 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
 {
         struct perf_evsel *evsel;
 
-        list_for_each_entry(evsel, &evlist->entries, node) {
+        evlist__for_each(evlist, evsel) {
                 int fd = FD(evsel, cpu, thread);
 
                 if (*output == -1) {
@@ -732,11 +738,13 @@ static long parse_pages_arg(const char *str, unsigned long min,
                         return -EINVAL;
         }
 
-        if ((pages == 0) && (min == 0)) {
+        if (pages == 0 && min == 0) {
                 /* leave number of pages at 0 */
-        } else if (pages < (1UL << 31) && !is_power_of_2(pages)) {
+        } else if (!is_power_of_2(pages)) {
                 /* round pages up to next power of 2 */
-                pages = next_pow2(pages);
+                pages = next_pow2_l(pages);
+                if (!pages)
+                        return -EINVAL;
                 pr_info("rounding mmap pages size to %lu bytes (%lu pages)\n",
                         pages * page_size, pages);
         }
@@ -754,7 +762,7 @@ int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str,
         unsigned long max = UINT_MAX;
         long pages;
 
-        if (max < SIZE_MAX / page_size)
+        if (max > SIZE_MAX / page_size)
                 max = SIZE_MAX / page_size;
 
         pages = parse_pages_arg(str, 1, max);
@@ -798,7 +806,7 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
         pr_debug("mmap size %zuB\n", evlist->mmap_len);
         mask = evlist->mmap_len - page_size - 1;
 
-        list_for_each_entry(evsel, &evlist->entries, node) {
+        evlist__for_each(evlist, evsel) {
                 if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
                     evsel->sample_id == NULL &&
                     perf_evsel__alloc_id(evsel, cpu_map__nr(cpus), threads->nr) < 0)
@@ -819,11 +827,7 @@ int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
         if (evlist->threads == NULL)
                 return -1;
 
-        if (target->force_per_cpu)
-                evlist->cpus = cpu_map__new(target->cpu_list);
-        else if (target__has_task(target))
-                evlist->cpus = cpu_map__dummy_new();
-        else if (!target__has_cpu(target) && !target->uses_mmap)
+        if (target__uses_dummy_map(target))
                 evlist->cpus = cpu_map__dummy_new();
         else
                 evlist->cpus = cpu_map__new(target->cpu_list);
@@ -838,14 +842,6 @@ out_delete_threads:
         return -1;
 }
 
-void perf_evlist__delete_maps(struct perf_evlist *evlist)
-{
-        cpu_map__delete(evlist->cpus);
-        thread_map__delete(evlist->threads);
-        evlist->cpus    = NULL;
-        evlist->threads = NULL;
-}
-
 int perf_evlist__apply_filters(struct perf_evlist *evlist)
 {
         struct perf_evsel *evsel;
@@ -853,7 +849,7 @@ int perf_evlist__apply_filters(struct perf_evlist *evlist)
         const int ncpus = cpu_map__nr(evlist->cpus),
                   nthreads = thread_map__nr(evlist->threads);
 
-        list_for_each_entry(evsel, &evlist->entries, node) {
+        evlist__for_each(evlist, evsel) {
                 if (evsel->filter == NULL)
                         continue;
 
@@ -872,7 +868,7 @@ int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter)
         const int ncpus = cpu_map__nr(evlist->cpus),
                   nthreads = thread_map__nr(evlist->threads);
 
-        list_for_each_entry(evsel, &evlist->entries, node) {
+        evlist__for_each(evlist, evsel) {
                 err = perf_evsel__set_filter(evsel, ncpus, nthreads, filter);
                 if (err)
                         break;
@@ -891,7 +887,7 @@ bool perf_evlist__valid_sample_type(struct perf_evlist *evlist)
         if (evlist->id_pos < 0 || evlist->is_pos < 0)
                 return false;
 
-        list_for_each_entry(pos, &evlist->entries, node) {
+        evlist__for_each(evlist, pos) {
                 if (pos->id_pos != evlist->id_pos ||
                     pos->is_pos != evlist->is_pos)
                         return false;
@@ -907,7 +903,7 @@ u64 __perf_evlist__combined_sample_type(struct perf_evlist *evlist)
         if (evlist->combined_sample_type)
                 return evlist->combined_sample_type;
 
-        list_for_each_entry(evsel, &evlist->entries, node)
+        evlist__for_each(evlist, evsel)
                 evlist->combined_sample_type |= evsel->attr.sample_type;
 
         return evlist->combined_sample_type;
@@ -925,7 +921,7 @@ bool perf_evlist__valid_read_format(struct perf_evlist *evlist)
         u64 read_format = first->attr.read_format;
         u64 sample_type = first->attr.sample_type;
 
-        list_for_each_entry_continue(pos, &evlist->entries, node) {
+        evlist__for_each(evlist, pos) {
                 if (read_format != pos->attr.read_format)
                         return false;
         }
@@ -982,7 +978,7 @@ bool perf_evlist__valid_sample_id_all(struct perf_evlist *evlist)
 {
         struct perf_evsel *first = perf_evlist__first(evlist), *pos = first;
 
-        list_for_each_entry_continue(pos, &evlist->entries, node) {
+        evlist__for_each_continue(evlist, pos) {
                 if (first->attr.sample_id_all != pos->attr.sample_id_all)
                         return false;
         }
@@ -1007,9 +1003,12 @@ 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);
+        int n;
 
-        list_for_each_entry_reverse(evsel, &evlist->entries, node)
-                perf_evsel__close(evsel, ncpus, nthreads);
+        evlist__for_each_reverse(evlist, evsel) {
+                n = evsel->cpus ? evsel->cpus->nr : ncpus;
+                perf_evsel__close(evsel, n, nthreads);
+        }
 }
 
 int perf_evlist__open(struct perf_evlist *evlist)
@@ -1019,7 +1018,7 @@ int perf_evlist__open(struct perf_evlist *evlist)
 
         perf_evlist__update_id_pos(evlist);
 
-        list_for_each_entry(evsel, &evlist->entries, node) {
+        evlist__for_each(evlist, evsel) {
                 err = perf_evsel__open(evsel, evlist->cpus, evlist->threads);
                 if (err < 0)
                         goto out_err;
@@ -1034,7 +1033,7 @@ out_err:
 
 int perf_evlist__prepare_workload(struct perf_evlist *evlist, struct target *target,
                                   const char *argv[], bool pipe_output,
-                                  bool want_signal)
+                                  void (*exec_error)(int signo, siginfo_t *info, void *ucontext))
 {
         int child_ready_pipe[2], go_pipe[2];
         char bf;
@@ -1078,12 +1077,25 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist, struct target *tar
 
                 execvp(argv[0], (char **)argv);
 
-                perror(argv[0]);
-                if (want_signal)
-                        kill(getppid(), SIGUSR1);
+                if (exec_error) {
+                        union sigval val;
+
+                        val.sival_int = errno;
+                        if (sigqueue(getppid(), SIGUSR1, val))
+                                perror(argv[0]);
+                } else
+                        perror(argv[0]);
                 exit(-1);
         }
 
+        if (exec_error) {
+                struct sigaction act = {
+                        .sa_flags     = SA_SIGINFO,
+                        .sa_sigaction = exec_error,
+                };
+                sigaction(SIGUSR1, &act, NULL);
+        }
+
         if (target__none(target))
                 evlist->threads->map[0] = evlist->workload.pid;
 
@@ -1145,7 +1157,7 @@ size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp)
         struct perf_evsel *evsel;
         size_t printed = 0;
 
-        list_for_each_entry(evsel, &evlist->entries, node) {
+        evlist__for_each(evlist, evsel) {
                 printed += fprintf(fp, "%s%s", evsel->idx ? ", " : "",
                                    perf_evsel__name(evsel));
         }
@@ -1193,8 +1205,7 @@ int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused,
                                     "Error:\t%s.\n"
                                     "Hint:\tCheck /proc/sys/kernel/perf_event_paranoid setting.", emsg);
 
-                if (filename__read_int("/proc/sys/kernel/perf_event_paranoid", &value))
-                        break;
+                value = perf_event_paranoid();
 
                 printed += scnprintf(buf + printed, size - printed, "\nHint:\t");
 
@@ -1215,3 +1226,20 @@ int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused,
 
         return 0;
 }
+
+void perf_evlist__to_front(struct perf_evlist *evlist,
+                           struct perf_evsel *move_evsel)
+{
+        struct perf_evsel *evsel, *n;
+        LIST_HEAD(move);
+
+        if (move_evsel == perf_evlist__first(evlist))
+                return;
+
+        evlist__for_each_safe(evlist, n, evsel) {
+                if (evsel->leader == move_evsel->leader)
+                        list_move_tail(&evsel->node, &move);
+        }
+
+        list_splice(&move, &evlist->entries);
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 649d6ea98a84..f5173cd63693 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -12,7 +12,7 @@
 struct pollfd;
 struct thread_map;
 struct cpu_map;
-struct perf_record_opts;
+struct record_opts;
 
 #define PERF_EVLIST__HLIST_BITS 8
 #define PERF_EVLIST__HLIST_SIZE (1 << PERF_EVLIST__HLIST_BITS)
@@ -97,14 +97,14 @@ void perf_evlist__close(struct perf_evlist *evlist);
 
 void perf_evlist__set_id_pos(struct perf_evlist *evlist);
 bool perf_can_sample_identifier(void);
-void perf_evlist__config(struct perf_evlist *evlist,
-                         struct perf_record_opts *opts);
-int perf_record_opts__config(struct perf_record_opts *opts);
+void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts);
+int record_opts__config(struct record_opts *opts);
 
 int perf_evlist__prepare_workload(struct perf_evlist *evlist,
                                   struct target *target,
                                   const char *argv[], bool pipe_output,
-                                  bool want_signal);
+                                  void (*exec_error)(int signo, siginfo_t *info,
+                                                     void *ucontext));
 int perf_evlist__start_workload(struct perf_evlist *evlist);
 
 int perf_evlist__parse_mmap_pages(const struct option *opt,
@@ -135,7 +135,6 @@ static inline void perf_evlist__set_maps(struct perf_evlist *evlist,
 }
 
 int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target);
-void perf_evlist__delete_maps(struct perf_evlist *evlist);
 int perf_evlist__apply_filters(struct perf_evlist *evlist);
 
 void __perf_evlist__set_leader(struct list_head *list);
@@ -193,4 +192,74 @@ static inline void perf_mmap__write_tail(struct perf_mmap *md,
         pc->data_tail = tail;
 }
 
+bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str);
+void perf_evlist__to_front(struct perf_evlist *evlist,
+                           struct perf_evsel *move_evsel);
+
+/**
+ * __evlist__for_each - iterate thru all the evsels
+ * @list: list_head instance to iterate
+ * @evsel: struct evsel iterator
+ */
+#define __evlist__for_each(list, evsel) \
+        list_for_each_entry(evsel, list, node)
+
+/**
+ * evlist__for_each - iterate thru all the evsels
+ * @evlist: evlist instance to iterate
+ * @evsel: struct evsel iterator
+ */
+#define evlist__for_each(evlist, evsel) \
+        __evlist__for_each(&(evlist)->entries, evsel)
+
+/**
+ * __evlist__for_each_continue - continue iteration thru all the evsels
+ * @list: list_head instance to iterate
+ * @evsel: struct evsel iterator
+ */
+#define __evlist__for_each_continue(list, evsel) \
+        list_for_each_entry_continue(evsel, list, node)
+
+/**
+ * evlist__for_each_continue - continue iteration thru all the evsels
+ * @evlist: evlist instance to iterate
+ * @evsel: struct evsel iterator
+ */
+#define evlist__for_each_continue(evlist, evsel) \
+        __evlist__for_each_continue(&(evlist)->entries, evsel)
+
+/**
+ * __evlist__for_each_reverse - iterate thru all the evsels in reverse order
+ * @list: list_head instance to iterate
+ * @evsel: struct evsel iterator
+ */
+#define __evlist__for_each_reverse(list, evsel) \
+        list_for_each_entry_reverse(evsel, list, node)
+
+/**
+ * evlist__for_each_reverse - iterate thru all the evsels in reverse order
+ * @evlist: evlist instance to iterate
+ * @evsel: struct evsel iterator
+ */
+#define evlist__for_each_reverse(evlist, evsel) \
+        __evlist__for_each_reverse(&(evlist)->entries, evsel)
+
+/**
+ * __evlist__for_each_safe - safely iterate thru all the evsels
+ * @list: list_head instance to iterate
+ * @tmp: struct evsel temp iterator
+ * @evsel: struct evsel iterator
+ */
+#define __evlist__for_each_safe(list, tmp, evsel) \
+        list_for_each_entry_safe(evsel, tmp, list, node)
+
+/**
+ * evlist__for_each_safe - safely iterate thru all the evsels
+ * @evlist: evlist instance to iterate
+ * @evsel: struct evsel iterator
+ * @tmp: struct evsel temp iterator
+ */
+#define evlist__for_each_safe(evlist, tmp, evsel) \
+        __evlist__for_each_safe(&(evlist)->entries, tmp, evsel)
+
 #endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 46dd4c2a41ce..55407c594b87 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -9,7 +9,7 @@
 
 #include <byteswap.h>
 #include <linux/bitops.h>
-#include <lk/debugfs.h>
+#include <api/fs/debugfs.h>
 #include <traceevent/event-parse.h>
 #include <linux/hw_breakpoint.h>
 #include <linux/perf_event.h>
@@ -23,6 +23,7 @@
 #include "target.h"
 #include "perf_regs.h"
 #include "debug.h"
+#include "trace-event.h"
 
 static struct {
         bool sample_id_all;
@@ -162,6 +163,8 @@ void perf_evsel__init(struct perf_evsel *evsel,
         evsel->idx         = idx;
         evsel->attr        = *attr;
         evsel->leader      = evsel;
+        evsel->unit        = "";
+        evsel->scale       = 1.0;
         INIT_LIST_HEAD(&evsel->node);
         hists__init(&evsel->hists);
         evsel->sample_size = __perf_evsel__sample_size(attr->sample_type);
@@ -178,47 +181,6 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
         return evsel;
 }
 
-struct event_format *event_format__new(const char *sys, const char *name)
-{
-        int fd, n;
-        char *filename;
-        void *bf = NULL, *nbf;
-        size_t size = 0, alloc_size = 0;
-        struct event_format *format = NULL;
-
-        if (asprintf(&filename, "%s/%s/%s/format", tracing_events_path, sys, name) < 0)
-                goto out;
-
-        fd = open(filename, O_RDONLY);
-        if (fd < 0)
-                goto out_free_filename;
-
-        do {
-                if (size == alloc_size) {
-                        alloc_size += BUFSIZ;
-                        nbf = realloc(bf, alloc_size);
-                        if (nbf == NULL)
-                                goto out_free_bf;
-                        bf = nbf;
-                }
-
-                n = read(fd, bf + size, alloc_size - size);
-                if (n < 0)
-                        goto out_free_bf;
-                size += n;
-        } while (n > 0);
-
-        pevent_parse_format(&format, bf, size, sys);
-
-out_free_bf:
-        free(bf);
-        close(fd);
-out_free_filename:
-        free(filename);
-out:
-        return format;
-}
-
 struct perf_evsel *perf_evsel__newtp_idx(const char *sys, const char *name, int idx)
 {
         struct perf_evsel *evsel = zalloc(sizeof(*evsel));
@@ -233,7 +195,7 @@ struct perf_evsel *perf_evsel__newtp_idx(const char *sys, const char *name, int
                 if (asprintf(&evsel->name, "%s:%s", sys, name) < 0)
                         goto out_free;
 
-                evsel->tp_format = event_format__new(sys, name);
+                evsel->tp_format = trace_event__tp_format(sys, name);
                 if (evsel->tp_format == NULL)
                         goto out_free;
 
@@ -246,7 +208,7 @@ struct perf_evsel *perf_evsel__newtp_idx(const char *sys, const char *name, int
         return evsel;
 
 out_free:
-        free(evsel->name);
+        zfree(&evsel->name);
         free(evsel);
         return NULL;
 }
@@ -566,12 +528,12 @@ int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size)
  *     enable/disable events specifically, as there's no
  *     initial traced exec call.
  */
-void perf_evsel__config(struct perf_evsel *evsel,
-                        struct perf_record_opts *opts)
+void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 {
         struct perf_evsel *leader = evsel->leader;
         struct perf_event_attr *attr = &evsel->attr;
         int track = !evsel->idx; /* only the first counter needs these */
+        bool per_cpu = opts->target.default_per_cpu && !opts->target.per_thread;
 
         attr->sample_id_all = perf_missing_features.sample_id_all ? 0 : 1;
         attr->inherit       = !opts->no_inherit;
@@ -645,7 +607,7 @@ void perf_evsel__config(struct perf_evsel *evsel,
                 }
         }
 
-        if (target__has_cpu(&opts->target) || opts->target.force_per_cpu)
+        if (target__has_cpu(&opts->target))
                 perf_evsel__set_sample_bit(evsel, CPU);
 
         if (opts->period)
@@ -653,7 +615,7 @@ void perf_evsel__config(struct perf_evsel *evsel,
 
         if (!perf_missing_features.sample_id_all &&
             (opts->sample_time || !opts->no_inherit ||
-             target__has_cpu(&opts->target) || opts->target.force_per_cpu))
+             target__has_cpu(&opts->target) || per_cpu))
                 perf_evsel__set_sample_bit(evsel, TIME);
 
         if (opts->raw_samples) {
@@ -665,7 +627,7 @@ void perf_evsel__config(struct perf_evsel *evsel,
         if (opts->sample_address)
                 perf_evsel__set_sample_bit(evsel, DATA_SRC);
 
-        if (opts->no_delay) {
+        if (opts->no_buffering) {
                 attr->watermark = 0;
                 attr->wakeup_events = 1;
         }
@@ -696,7 +658,8 @@ void perf_evsel__config(struct perf_evsel *evsel,
          * Setting enable_on_exec for independent events and
          * group leaders for traced executed by perf.
          */
-        if (target__none(&opts->target) && perf_evsel__is_group_leader(evsel))
+        if (target__none(&opts->target) && perf_evsel__is_group_leader(evsel) &&
+                !opts->initial_delay)
                 attr->enable_on_exec = 1;
 }
 
@@ -788,8 +751,7 @@ void perf_evsel__free_id(struct perf_evsel *evsel)
 {
         xyarray__delete(evsel->sample_id);
         evsel->sample_id = NULL;
-        free(evsel->id);
-        evsel->id = NULL;
+        zfree(&evsel->id);
 }
 
 void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
@@ -805,7 +767,7 @@ void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
 
 void perf_evsel__free_counts(struct perf_evsel *evsel)
 {
-        free(evsel->counts);
+        zfree(&evsel->counts);
 }
 
 void perf_evsel__exit(struct perf_evsel *evsel)
@@ -819,10 +781,10 @@ void perf_evsel__delete(struct perf_evsel *evsel)
 {
         perf_evsel__exit(evsel);
         close_cgroup(evsel->cgrp);
-        free(evsel->group_name);
+        zfree(&evsel->group_name);
         if (evsel->tp_format)
                 pevent_free_format(evsel->tp_format);
-        free(evsel->name);
+        zfree(&evsel->name);
         free(evsel);
 }
 
@@ -1119,7 +1081,6 @@ void perf_evsel__close(struct perf_evsel *evsel, int ncpus, int nthreads)
 
         perf_evsel__close_fd(evsel, ncpus, nthreads);
         perf_evsel__free_fd(evsel);
-        evsel->fd = NULL;
 }
 
 static struct {
@@ -1998,8 +1959,7 @@ bool perf_evsel__fallback(struct perf_evsel *evsel, int err,
                 evsel->attr.type   = PERF_TYPE_SOFTWARE;
                 evsel->attr.config = PERF_COUNT_SW_CPU_CLOCK;
 
-                free(evsel->name);
-                evsel->name = NULL;
+                zfree(&evsel->name);
                 return true;
         }
 
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 1ea7c92e6e33..f1b325665aae 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -68,6 +68,8 @@ struct perf_evsel {
         u32                     ids;
         struct hists            hists;
         char                    *name;
+        double                  scale;
+        const char              *unit;
         struct event_format     *tp_format;
         union {
                 void            *priv;
@@ -94,7 +96,7 @@ struct perf_evsel {
 struct cpu_map;
 struct thread_map;
 struct perf_evlist;
-struct perf_record_opts;
+struct record_opts;
 
 struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx);
 
@@ -118,7 +120,7 @@ void perf_evsel__exit(struct perf_evsel *evsel);
 void perf_evsel__delete(struct perf_evsel *evsel);
 
 void perf_evsel__config(struct perf_evsel *evsel,
-                        struct perf_record_opts *opts);
+                        struct record_opts *opts);
 
 int __perf_evsel__sample_size(u64 sample_type);
 void perf_evsel__calc_id_pos(struct perf_evsel *evsel);
@@ -138,6 +140,7 @@ extern const char *perf_evsel__sw_names[PERF_COUNT_SW_MAX];
 int __perf_evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result,
                                             char *bf, size_t size);
 const char *perf_evsel__name(struct perf_evsel *evsel);
+
 const char *perf_evsel__group_name(struct perf_evsel *evsel);
 int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size);
 
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 369c03648f88..893f8e2df928 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -177,7 +177,7 @@ perf_header__set_cmdline(int argc, const char **argv)
                         continue;               \
                 else
 
-static int write_buildid(char *name, size_t name_len, u8 *build_id,
+static int write_buildid(const char *name, size_t name_len, u8 *build_id,
                          pid_t pid, u16 misc, int fd)
 {
         int err;
@@ -209,7 +209,7 @@ static int __dsos__write_buildid_table(struct list_head *head,
 
         dsos__for_each_with_build_id(pos, head) {
                 int err;
-                char  *name;
+                const char *name;
                 size_t name_len;
 
                 if (!pos->hit)
@@ -387,7 +387,7 @@ static int dso__cache_build_id(struct dso *dso, struct machine *machine,
 {
         bool is_kallsyms = dso->kernel && dso->long_name[0] != '/';
         bool is_vdso = is_vdso_map(dso->short_name);
-        char *name = dso->long_name;
+        const char *name = dso->long_name;
         char nm[PATH_MAX];
 
         if (dso__is_kcore(dso)) {
@@ -643,8 +643,7 @@ static int write_event_desc(int fd, struct perf_header *h __maybe_unused,
         if (ret < 0)
                 return ret;
 
-        list_for_each_entry(evsel, &evlist->entries, node) {
-
+        evlist__for_each(evlist, evsel) {
                 ret = do_write(fd, &evsel->attr, sz);
                 if (ret < 0)
                         return ret;
@@ -800,10 +799,10 @@ static void free_cpu_topo(struct cpu_topo *tp)
                 return;
 
         for (i = 0 ; i < tp->core_sib; i++)
-                free(tp->core_siblings[i]);
+                zfree(&tp->core_siblings[i]);
 
         for (i = 0 ; i < tp->thread_sib; i++)
-                free(tp->thread_siblings[i]);
+                zfree(&tp->thread_siblings[i]);
 
         free(tp);
 }
@@ -931,7 +930,7 @@ static int write_topo_node(int fd, int node)
                 /* skip over invalid lines */
                 if (!strchr(buf, ':'))
                         continue;
-                if (sscanf(buf, "%*s %*d %s %"PRIu64, field, &mem) != 2)
+                if (sscanf(buf, "%*s %*d %31s %"PRIu64, field, &mem) != 2)
                         goto done;
                 if (!strcmp(field, "MemTotal:"))
                         mem_total = mem;
@@ -1092,7 +1091,7 @@ static int write_group_desc(int fd, struct perf_header *h __maybe_unused,
         if (ret < 0)
                 return ret;
 
-        list_for_each_entry(evsel, &evlist->entries, node) {
+        evlist__for_each(evlist, evsel) {
                 if (perf_evsel__is_group_leader(evsel) &&
                     evsel->nr_members > 1) {
                         const char *name = evsel->group_name ?: "{anon_group}";
@@ -1232,10 +1231,8 @@ static void free_event_desc(struct perf_evsel *events)
                 return;
 
         for (evsel = events; evsel->attr.size; evsel++) {
-                if (evsel->name)
-                        free(evsel->name);
-                if (evsel->id)
-                        free(evsel->id);
+                zfree(&evsel->name);
+                zfree(&evsel->id);
         }
 
         free(events);
@@ -1326,8 +1323,7 @@ read_event_desc(struct perf_header *ph, int fd)
                 }
         }
 out:
-        if (buf)
-                free(buf);
+        free(buf);
         return events;
 error:
         if (events)
@@ -1490,7 +1486,7 @@ static void print_group_desc(struct perf_header *ph, int fd __maybe_unused,
 
         session = container_of(ph, struct perf_session, header);
 
-        list_for_each_entry(evsel, &session->evlist->entries, node) {
+        evlist__for_each(session->evlist, evsel) {
                 if (perf_evsel__is_group_leader(evsel) &&
                     evsel->nr_members > 1) {
                         fprintf(fp, "# group: %s{%s", evsel->group_name ?: "",
@@ -1709,7 +1705,7 @@ static int process_nrcpus(struct perf_file_section *section __maybe_unused,
                           struct perf_header *ph, int fd,
                           void *data __maybe_unused)
 {
-        size_t ret;
+        ssize_t ret;
         u32 nr;
 
         ret = readn(fd, &nr, sizeof(nr));
@@ -1753,7 +1749,7 @@ static int process_total_mem(struct perf_file_section *section __maybe_unused,
                              void *data __maybe_unused)
 {
         uint64_t mem;
-        size_t ret;
+        ssize_t ret;
 
         ret = readn(fd, &mem, sizeof(mem));
         if (ret != sizeof(mem))
@@ -1771,7 +1767,7 @@ perf_evlist__find_by_index(struct perf_evlist *evlist, int idx)
 {
         struct perf_evsel *evsel;
 
-        list_for_each_entry(evsel, &evlist->entries, node) {
+        evlist__for_each(evlist, evsel) {
                 if (evsel->idx == idx)
                         return evsel;
         }
@@ -1822,7 +1818,7 @@ static int process_cmdline(struct perf_file_section *section __maybe_unused,
                            struct perf_header *ph, int fd,
                            void *data __maybe_unused)
 {
-        size_t ret;
+        ssize_t ret;
         char *str;
         u32 nr, i;
         struct strbuf sb;
@@ -1858,7 +1854,7 @@ static int process_cpu_topology(struct perf_file_section *section __maybe_unused
                                 struct perf_header *ph, int fd,
                                 void *data __maybe_unused)
 {
-        size_t ret;
+        ssize_t ret;
         u32 nr, i;
         char *str;
         struct strbuf sb;
@@ -1914,7 +1910,7 @@ static int process_numa_topology(struct perf_file_section *section __maybe_unuse
                                  struct perf_header *ph, int fd,
                                  void *data __maybe_unused)
 {
-        size_t ret;
+        ssize_t ret;
         u32 nr, node, i;
         char *str;
         uint64_t mem_total, mem_free;
@@ -1974,7 +1970,7 @@ static int process_pmu_mappings(struct perf_file_section *section __maybe_unused
                                 struct perf_header *ph, int fd,
                                 void *data __maybe_unused)
 {
-        size_t ret;
+        ssize_t ret;
         char *name;
         u32 pmu_num;
         u32 type;
@@ -2074,12 +2070,14 @@ static int process_group_desc(struct perf_file_section *section __maybe_unused,
         session->evlist->nr_groups = nr_groups;
 
         i = nr = 0;
-        list_for_each_entry(evsel, &session->evlist->entries, node) {
+        evlist__for_each(session->evlist, evsel) {
                 if (evsel->idx == (int) desc[i].leader_idx) {
                         evsel->leader = evsel;
                         /* {anon_group} is a dummy name */
-                        if (strcmp(desc[i].name, "{anon_group}"))
+                        if (strcmp(desc[i].name, "{anon_group}")) {
                                 evsel->group_name = desc[i].name;
+                                desc[i].name = NULL;
+                        }
                         evsel->nr_members = desc[i].nr_members;
 
                         if (i >= nr_groups || nr > 0) {
@@ -2105,8 +2103,8 @@ static int process_group_desc(struct perf_file_section *section __maybe_unused,
 
         ret = 0;
 out_free:
-        while ((int) --i >= 0)
-                free(desc[i].name);
+        for (i = 0; i < nr_groups; i++)
+                zfree(&desc[i].name);
         free(desc);
 
         return ret;
@@ -2299,7 +2297,7 @@ int perf_session__write_header(struct perf_session *session,
 
         lseek(fd, sizeof(f_header), SEEK_SET);
 
-        list_for_each_entry(evsel, &evlist->entries, node) {
+        evlist__for_each(session->evlist, evsel) {
                 evsel->id_offset = lseek(fd, 0, SEEK_CUR);
                 err = do_write(fd, evsel->id, evsel->ids * sizeof(u64));
                 if (err < 0) {
@@ -2310,7 +2308,7 @@ int perf_session__write_header(struct perf_session *session,
 
         attr_offset = lseek(fd, 0, SEEK_CUR);
 
-        list_for_each_entry(evsel, &evlist->entries, node) {
+        evlist__for_each(evlist, evsel) {
                 f_attr = (struct perf_file_attr){
                         .attr = evsel->attr,
                         .ids  = {
@@ -2325,7 +2323,8 @@ int perf_session__write_header(struct perf_session *session,
                 }
         }
 
-        header->data_offset = lseek(fd, 0, SEEK_CUR);
+        if (!header->data_offset)
+                header->data_offset = lseek(fd, 0, SEEK_CUR);
         header->feat_offset = header->data_offset + header->data_size;
 
         if (at_exit) {
@@ -2532,7 +2531,7 @@ static int check_magic_endian(u64 magic, uint64_t hdr_sz,
 int perf_file_header__read(struct perf_file_header *header,
                            struct perf_header *ph, int fd)
 {
-        int ret;
+        ssize_t ret;
 
         lseek(fd, 0, SEEK_SET);
 
@@ -2626,7 +2625,7 @@ static int perf_file_header__read_pipe(struct perf_pipe_file_header *header,
                                        struct perf_header *ph, int fd,
                                        bool repipe)
 {
-        int ret;
+        ssize_t ret;
 
         ret = readn(fd, header, sizeof(*header));
         if (ret <= 0)
@@ -2667,7 +2666,7 @@ static int read_attr(int fd, struct perf_header *ph,
         struct perf_event_attr *attr = &f_attr->attr;
         size_t sz, left;
         size_t our_sz = sizeof(f_attr->attr);
-        int ret;
+        ssize_t ret;
 
         memset(f_attr, 0, sizeof(*f_attr));
 
@@ -2742,7 +2741,7 @@ static int perf_evlist__prepare_tracepoint_events(struct perf_evlist *evlist,
 {
         struct perf_evsel *pos;
 
-        list_for_each_entry(pos, &evlist->entries, node) {
+        evlist__for_each(evlist, pos) {
                 if (pos->attr.type == PERF_TYPE_TRACEPOINT &&
                     perf_evsel__prepare_tracepoint_event(pos, pevent))
                         return -1;
@@ -2832,11 +2831,11 @@ int perf_session__read_header(struct perf_session *session)
 
         symbol_conf.nr_events = nr_attrs;
 
-        perf_header__process_sections(header, fd, &session->pevent,
+        perf_header__process_sections(header, fd, &session->tevent,
                                       perf_file_section__process);
 
         if (perf_evlist__prepare_tracepoint_events(session->evlist,
-                                                   session->pevent))
+                                                   session->tevent.pevent))
                 goto out_delete_evlist;
 
         return 0;
@@ -2890,7 +2889,7 @@ int perf_event__synthesize_attrs(struct perf_tool *tool,
         struct perf_evsel *evsel;
         int err = 0;
 
-        list_for_each_entry(evsel, &session->evlist->entries, node) {
+        evlist__for_each(session->evlist, evsel) {
                 err = perf_event__synthesize_attr(tool, &evsel->attr, evsel->ids,
                                                   evsel->id, process);
                 if (err) {
@@ -3001,7 +3000,7 @@ int perf_event__process_tracing_data(struct perf_tool *tool __maybe_unused,
         lseek(fd, offset + sizeof(struct tracing_data_event),
               SEEK_SET);
 
-        size_read = trace_report(fd, &session->pevent,
+        size_read = trace_report(fd, &session->tevent,
                                  session->repipe);
         padding = PERF_ALIGN(size_read, sizeof(u64)) - size_read;
 
@@ -3023,7 +3022,7 @@ int perf_event__process_tracing_data(struct perf_tool *tool __maybe_unused,
         }
 
         perf_evlist__prepare_tracepoint_events(session->evlist,
-                                               session->pevent);
+                                               session->tevent.pevent);
 
         return size_read + padding;
 }
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 307c9aed972e..a2d047bdf4ef 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -77,16 +77,16 @@ struct perf_session_env {
         unsigned long long      total_mem;
 
         int                     nr_cmdline;
-        char                    *cmdline;
         int                     nr_sibling_cores;
-        char                    *sibling_cores;
         int                     nr_sibling_threads;
-        char                    *sibling_threads;
         int                     nr_numa_nodes;
-        char                    *numa_nodes;
         int                     nr_pmu_mappings;
-        char                    *pmu_mappings;
         int                     nr_groups;
+        char                    *cmdline;
+        char                    *sibling_cores;
+        char                    *sibling_threads;
+        char                    *numa_nodes;
+        char                    *pmu_mappings;
 };
 
 struct perf_header {
diff --git a/tools/perf/util/help.c b/tools/perf/util/help.c
index 8b1f6e891b8a..86c37c472263 100644
--- a/tools/perf/util/help.c
+++ b/tools/perf/util/help.c
@@ -22,8 +22,8 @@ static void clean_cmdnames(struct cmdnames *cmds)
         unsigned int i;
 
         for (i = 0; i < cmds->cnt; ++i)
-                free(cmds->names[i]);
-        free(cmds->names);
+                zfree(&cmds->names[i]);
+        zfree(&cmds->names);
         cmds->cnt = 0;
         cmds->alloc = 0;
 }
@@ -263,9 +263,8 @@ static void add_cmd_list(struct cmdnames *cmds, struct cmdnames *old)
 
         for (i = 0; i < old->cnt; i++)
                 cmds->names[cmds->cnt++] = old->names[i];
-        free(old->names);
+        zfree(&old->names);
         old->cnt = 0;
-        old->names = NULL;
 }
 
 const char *help_unknown_cmd(const char *cmd)
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 822903eaa201..e4e6249b87d4 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -1,4 +1,3 @@
-#include "annotate.h"
 #include "util.h"
 #include "build-id.h"
 #include "hist.h"
@@ -182,21 +181,21 @@ void hists__output_recalc_col_len(struct hists *hists, int max_rows)
         }
 }
 
-static void hist_entry__add_cpumode_period(struct hist_entry *he,
-                                           unsigned int cpumode, u64 period)
+static void he_stat__add_cpumode_period(struct he_stat *he_stat,
+                                        unsigned int cpumode, u64 period)
 {
         switch (cpumode) {
         case PERF_RECORD_MISC_KERNEL:
-                he->stat.period_sys += period;
+                he_stat->period_sys += period;
                 break;
         case PERF_RECORD_MISC_USER:
-                he->stat.period_us += period;
+                he_stat->period_us += period;
                 break;
         case PERF_RECORD_MISC_GUEST_KERNEL:
-                he->stat.period_guest_sys += period;
+                he_stat->period_guest_sys += period;
                 break;
         case PERF_RECORD_MISC_GUEST_USER:
-                he->stat.period_guest_us += period;
+                he_stat->period_guest_us += period;
                 break;
         default:
                 break;
@@ -223,10 +222,10 @@ static void he_stat__add_stat(struct he_stat *dest, struct he_stat *src)
         dest->weight            += src->weight;
 }
 
-static void hist_entry__decay(struct hist_entry *he)
+static void he_stat__decay(struct he_stat *he_stat)
 {
-        he->stat.period = (he->stat.period * 7) / 8;
-        he->stat.nr_events = (he->stat.nr_events * 7) / 8;
+        he_stat->period = (he_stat->period * 7) / 8;
+        he_stat->nr_events = (he_stat->nr_events * 7) / 8;
         /* XXX need decay for weight too? */
 }
 
@@ -237,7 +236,7 @@ static bool hists__decay_entry(struct hists *hists, struct hist_entry *he)
         if (prev_period == 0)
                 return true;
 
-        hist_entry__decay(he);
+        he_stat__decay(&he->stat);
 
         if (!he->filtered)
                 hists->stats.total_period -= prev_period - he->stat.period;
@@ -342,15 +341,15 @@ static u8 symbol__parent_filter(const struct symbol *parent)
 }
 
 static struct hist_entry *add_hist_entry(struct hists *hists,
-                                      struct hist_entry *entry,
-                                      struct addr_location *al,
-                                      u64 period,
-                                      u64 weight)
+                                         struct hist_entry *entry,
+                                         struct addr_location *al)
 {
         struct rb_node **p;
         struct rb_node *parent = NULL;
         struct hist_entry *he;
         int64_t cmp;
+        u64 period = entry->stat.period;
+        u64 weight = entry->stat.weight;
 
         p = &hists->entries_in->rb_node;
 
@@ -373,7 +372,7 @@ static struct hist_entry *add_hist_entry(struct hists *hists,
                          * This mem info was allocated from machine__resolve_mem
                          * and will not be used anymore.
                          */
-                        free(entry->mem_info);
+                        zfree(&entry->mem_info);
 
                         /* If the map of an existing hist_entry has
                          * become out-of-date due to an exec() or
@@ -403,7 +402,7 @@ static struct hist_entry *add_hist_entry(struct hists *hists,
         rb_link_node(&he->rb_node_in, parent, p);
         rb_insert_color(&he->rb_node_in, hists->entries_in);
 out:
-        hist_entry__add_cpumode_period(he, al->cpumode, period);
+        he_stat__add_cpumode_period(&he->stat, al->cpumode, period);
         return he;
 }
 
@@ -437,7 +436,7 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
                 .transaction = transaction,
         };
 
-        return add_hist_entry(hists, &entry, al, period, weight);
+        return add_hist_entry(hists, &entry, al);
 }
 
 int64_t
@@ -476,8 +475,8 @@ hist_entry__collapse(struct hist_entry *left, struct hist_entry *right)
 
 void hist_entry__free(struct hist_entry *he)
 {
-        free(he->branch_info);
-        free(he->mem_info);
+        zfree(&he->branch_info);
+        zfree(&he->mem_info);
         free_srcline(he->srcline);
         free(he);
 }
@@ -807,16 +806,6 @@ void hists__filter_by_symbol(struct hists *hists)
         }
 }
 
-int hist_entry__inc_addr_samples(struct hist_entry *he, int evidx, u64 ip)
-{
-        return symbol__inc_addr_samples(he->ms.sym, he->ms.map, evidx, ip);
-}
-
-int hist_entry__annotate(struct hist_entry *he, size_t privsize)
-{
-        return symbol__annotate(he->ms.sym, he->ms.map, privsize);
-}
-
 void events_stats__inc(struct events_stats *stats, u32 type)
 {
         ++stats->nr_events[0];
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index b621347a1585..a59743fa3ef7 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -111,9 +111,6 @@ size_t events_stats__fprintf(struct events_stats *stats, FILE *fp);
 size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
                       int max_cols, float min_pcnt, FILE *fp);
 
-int hist_entry__inc_addr_samples(struct hist_entry *he, int evidx, u64 addr);
-int hist_entry__annotate(struct hist_entry *he, size_t privsize);
-
 void hists__filter_by_dso(struct hists *hists);
 void hists__filter_by_thread(struct hists *hists);
 void hists__filter_by_symbol(struct hists *hists);
diff --git a/tools/perf/util/include/asm/bug.h b/tools/perf/util/include/asm/bug.h
deleted file mode 100644
index 7fcc6810adc2..000000000000
--- a/tools/perf/util/include/asm/bug.h
+++ /dev/null
@@ -1,22 +0,0 @@
-#ifndef _PERF_ASM_GENERIC_BUG_H
-#define _PERF_ASM_GENERIC_BUG_H
-
-#define __WARN_printf(arg...)   do { fprintf(stderr, arg); } while (0)
-
-#define WARN(condition, format...) ({           \
-        int __ret_warn_on = !!(condition);      \
-        if (unlikely(__ret_warn_on))            \
-                __WARN_printf(format);          \
-        unlikely(__ret_warn_on);                \
-})
-
-#define WARN_ONCE(condition, format...) ({      \
-        static int __warned;                    \
-        int __ret_warn_once = !!(condition);    \
-                                                \
-        if (unlikely(__ret_warn_once))          \
-                if (WARN(!__warned, format))    \
-                        __warned = 1;           \
-        unlikely(__ret_warn_once);              \
-})
-#endif
diff --git a/tools/perf/util/include/linux/compiler.h b/tools/perf/util/include/linux/compiler.h
deleted file mode 100644
index b003ad7200b2..000000000000
--- a/tools/perf/util/include/linux/compiler.h
+++ /dev/null
@@ -1,30 +0,0 @@
-#ifndef _PERF_LINUX_COMPILER_H_
-#define _PERF_LINUX_COMPILER_H_
-
-#ifndef __always_inline
-# define __always_inline        inline __attribute__((always_inline))
-#endif
-
-#define __user
-
-#ifndef __attribute_const__
-# define __attribute_const__
-#endif
-
-#ifndef __maybe_unused
-# define __maybe_unused         __attribute__((unused))
-#endif
-
-#ifndef __packed
-# define __packed               __attribute__((__packed__))
-#endif
-
-#ifndef __force
-# define __force
-#endif
-
-#ifndef __weak
-# define __weak                 __attribute__((weak))
-#endif
-
-#endif
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 84cdb072ac83..ded74590b92f 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -9,6 +9,7 @@
 #include "strlist.h"
 #include "thread.h"
 #include <stdbool.h>
+#include <symbol/kallsyms.h>
 #include "unwind.h"
 
 int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
@@ -26,6 +27,7 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
         machine->pid = pid;
 
         machine->symbol_filter = NULL;
+        machine->id_hdr_size = 0;
 
         machine->root_dir = strdup(root_dir);
         if (machine->root_dir == NULL)
@@ -101,8 +103,7 @@ void machine__exit(struct machine *machine)
         map_groups__exit(&machine->kmaps);
         dsos__delete(&machine->user_dsos);
         dsos__delete(&machine->kernel_dsos);
-        free(machine->root_dir);
-        machine->root_dir = NULL;
+        zfree(&machine->root_dir);
 }
 
 void machine__delete(struct machine *machine)
@@ -502,15 +503,11 @@ static u64 machine__get_kernel_start_addr(struct machine *machine)
         char path[PATH_MAX];
         struct process_args args;
 
-        if (machine__is_host(machine)) {
-                filename = "/proc/kallsyms";
-        } else {
-                if (machine__is_default_guest(machine))
-                        filename = (char *)symbol_conf.default_guest_kallsyms;
-                else {
-                        sprintf(path, "%s/proc/kallsyms", machine->root_dir);
-                        filename = path;
-                }
+        if (machine__is_default_guest(machine))
+                filename = (char *)symbol_conf.default_guest_kallsyms;
+        else {
+                sprintf(path, "%s/proc/kallsyms", machine->root_dir);
+                filename = path;
         }
 
         if (symbol__restricted_filename(filename, "/proc/kallsyms"))
@@ -565,11 +562,10 @@ void machine__destroy_kernel_maps(struct machine *machine)
                          * on one of them.
                          */
                         if (type == MAP__FUNCTION) {
-                                free((char *)kmap->ref_reloc_sym->name);
-                                kmap->ref_reloc_sym->name = NULL;
-                                free(kmap->ref_reloc_sym);
-                        }
-                        kmap->ref_reloc_sym = NULL;
+                                zfree((char **)&kmap->ref_reloc_sym->name);
+                                zfree(&kmap->ref_reloc_sym);
+                        } else
+                                kmap->ref_reloc_sym = NULL;
                 }
 
                 map__delete(machine->vmlinux_maps[type]);
@@ -767,8 +763,7 @@ static int map_groups__set_modules_path_dir(struct map_groups *mg,
                                 ret = -1;
                                 goto out;
                         }
-                        dso__set_long_name(map->dso, long_name);
-                        map->dso->lname_alloc = 1;
+                        dso__set_long_name(map->dso, long_name, true);
                         dso__kernel_module_get_build_id(map->dso, "");
                 }
         }
@@ -939,8 +934,7 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
                 if (name == NULL)
                         goto out_problem;
 
-                map->dso->short_name = name;
-                map->dso->sname_alloc = 1;
+                dso__set_short_name(map->dso, name, true);
                 map->end = map->start + event->mmap.len;
         } else if (is_kernel_mmap) {
                 const char *symbol_name = (event->mmap.filename +
@@ -1320,8 +1314,6 @@ static int machine__resolve_callchain_sample(struct machine *machine,
                                 *root_al = al;
                                 callchain_cursor_reset(&callchain_cursor);
                         }
-                        if (!symbol_conf.use_callchain)
-                                break;
                 }
 
                 err = callchain_cursor_append(&callchain_cursor,
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index ef5bc913ca7a..3b97513f0e77 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -11,6 +11,7 @@
 #include "strlist.h"
 #include "vdso.h"
 #include "build-id.h"
+#include "util.h"
 #include <linux/string.h>
 
 const char *map_type__name[MAP__NR_TYPES] = {
@@ -68,7 +69,7 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
                 map->ino = ino;
                 map->ino_generation = ino_gen;
 
-                if (anon) {
+                if ((anon || no_dso) && type == MAP__FUNCTION) {
                         snprintf(newfilename, sizeof(newfilename), "/tmp/perf-%d.map", pid);
                         filename = newfilename;
                 }
@@ -92,7 +93,7 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
                          * functions still return NULL, and we avoid the
                          * unnecessary map__load warning.
                          */
-                        if (no_dso)
+                        if (type != MAP__FUNCTION)
                                 dso__set_loaded(dso, map->type);
                 }
         }
@@ -252,6 +253,22 @@ size_t map__fprintf_dsoname(struct map *map, FILE *fp)
         return fprintf(fp, "%s", dsoname);
 }
 
+int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix,
+                         FILE *fp)
+{
+        char *srcline;
+        int ret = 0;
+
+        if (map && map->dso) {
+                srcline = get_srcline(map->dso,
+                                      map__rip_2objdump(map, addr));
+                if (srcline != SRCLINE_UNKNOWN)
+                        ret = fprintf(fp, "%s%s", prefix, srcline);
+                free_srcline(srcline);
+        }
+        return ret;
+}
+
 /**
  * map__rip_2objdump - convert symbol start address to objdump address.
  * @map: memory map
@@ -369,7 +386,8 @@ struct symbol *map_groups__find_symbol(struct map_groups *mg,
 {
         struct map *map = map_groups__find(mg, type, addr);
 
-        if (map != NULL) {
+        /* Ensure map is loaded before using map->map_ip */
+        if (map != NULL && map__load(map, filter) >= 0) {
                 if (mapp != NULL)
                         *mapp = map;
                 return map__find_symbol(map, map->map_ip(map, addr), filter);
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index e4e259c3ba16..18068c6b71c1 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -103,6 +103,8 @@ struct map *map__clone(struct map *map);
 int map__overlap(struct map *l, struct map *r);
 size_t map__fprintf(struct map *map, FILE *fp);
 size_t map__fprintf_dsoname(struct map *map, FILE *fp);
+int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix,
+                         FILE *fp);
 
 int map__load(struct map *map, symbol_filter_t filter);
 struct symbol *map__find_symbol(struct map *map,
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 6de6f89c2a61..d248fca6d7ed 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 <lk/debugfs.h>
+#include <api/fs/debugfs.h>
 #include "parse-events-bison.h"
 #define YY_EXTRA_TYPE int
 #include "parse-events-flex.h"
@@ -204,7 +204,7 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config)
                                 }
                                 path->name = malloc(MAX_EVENT_LENGTH);
                                 if (!path->name) {
-                                        free(path->system);
+                                        zfree(&path->system);
                                         free(path);
                                         return NULL;
                                 }
@@ -236,8 +236,8 @@ struct tracepoint_path *tracepoint_name_to_path(const char *name)
         path->name = strdup(str+1);
 
         if (path->system == NULL || path->name == NULL) {
-                free(path->system);
-                free(path->name);
+                zfree(&path->system);
+                zfree(&path->name);
                 free(path);
                 path = NULL;
         }
@@ -269,9 +269,10 @@ const char *event_type(int type)
 
 
 
-static int __add_event(struct list_head *list, int *idx,
-                       struct perf_event_attr *attr,
-                       char *name, struct cpu_map *cpus)
+static struct perf_evsel *
+__add_event(struct list_head *list, int *idx,
+            struct perf_event_attr *attr,
+            char *name, struct cpu_map *cpus)
 {
         struct perf_evsel *evsel;
 
@@ -279,19 +280,19 @@ static int __add_event(struct list_head *list, int *idx,
 
         evsel = perf_evsel__new_idx(attr, (*idx)++);
         if (!evsel)
-                return -ENOMEM;
+                return NULL;
 
         evsel->cpus = cpus;
         if (name)
                 evsel->name = strdup(name);
         list_add_tail(&evsel->node, list);
-        return 0;
+        return evsel;
 }
 
 static int add_event(struct list_head *list, int *idx,
                      struct perf_event_attr *attr, char *name)
 {
-        return __add_event(list, idx, attr, name, NULL);
+        return __add_event(list, idx, attr, name, NULL) ? 0 : -ENOMEM;
 }
 
 static int parse_aliases(char *str, const char *names[][PERF_EVSEL__MAX_ALIASES], int size)
@@ -633,6 +634,9 @@ int parse_events_add_pmu(struct list_head *list, int *idx,
 {
         struct perf_event_attr attr;
         struct perf_pmu *pmu;
+        struct perf_evsel *evsel;
+        const char *unit;
+        double scale;
 
         pmu = perf_pmu__find(name);
         if (!pmu)
@@ -640,7 +644,7 @@ int parse_events_add_pmu(struct list_head *list, int *idx,
 
         memset(&attr, 0, sizeof(attr));
 
-        if (perf_pmu__check_alias(pmu, head_config))
+        if (perf_pmu__check_alias(pmu, head_config, &unit, &scale))
                 return -EINVAL;
 
         /*
@@ -652,8 +656,14 @@ int parse_events_add_pmu(struct list_head *list, int *idx,
         if (perf_pmu__config(pmu, &attr, head_config))
                 return -EINVAL;
 
-        return __add_event(list, idx, &attr, pmu_event_name(head_config),
-                           pmu->cpus);
+        evsel = __add_event(list, idx, &attr, pmu_event_name(head_config),
+                            pmu->cpus);
+        if (evsel) {
+                evsel->unit = unit;
+                evsel->scale = scale;
+        }
+
+        return evsel ? 0 : -ENOMEM;
 }
 
 int parse_events__modifier_group(struct list_head *list,
@@ -810,8 +820,7 @@ int parse_events__modifier_event(struct list_head *list, char *str, bool add)
         if (!add && get_event_modifier(&mod, str, NULL))
                 return -EINVAL;
 
-        list_for_each_entry(evsel, list, node) {
-
+        __evlist__for_each(list, evsel) {
                 if (add && get_event_modifier(&mod, str, evsel))
                         return -EINVAL;
 
@@ -835,7 +844,7 @@ int parse_events_name(struct list_head *list, char *name)
 {
         struct perf_evsel *evsel;
 
-        list_for_each_entry(evsel, list, node) {
+        __evlist__for_each(list, evsel) {
                 if (!evsel->name)
                         evsel->name = strdup(name);
         }
@@ -907,7 +916,7 @@ int parse_events_terms(struct list_head *terms, const char *str)
         ret = parse_events__scanner(str, &data, PE_START_TERMS);
         if (!ret) {
                 list_splice(data.terms, terms);
-                free(data.terms);
+                zfree(&data.terms);
                 return 0;
         }
 
diff --git a/tools/perf/util/parse-options.c b/tools/perf/util/parse-options.c
index 31f404a032a9..d22e3f8017dc 100644
--- a/tools/perf/util/parse-options.c
+++ b/tools/perf/util/parse-options.c
@@ -78,6 +78,8 @@ static int get_value(struct parse_opt_ctx_t *p,
 
         case OPTION_BOOLEAN:
                 *(bool *)opt->value = unset ? false : true;
+                if (opt->set)
+                        *(bool *)opt->set = true;
                 return 0;
 
         case OPTION_INCR:
@@ -224,6 +226,24 @@ static int parse_long_opt(struct parse_opt_ctx_t *p, const char *arg,
                         return 0;
                 }
                 if (!rest) {
+                        if (!prefixcmp(options->long_name, "no-")) {
+                                /*
+                                 * The long name itself starts with "no-", so
+                                 * accept the option without "no-" so that users
+                                 * do not have to enter "no-no-" to get the
+                                 * negation.
+                                 */
+                                rest = skip_prefix(arg, options->long_name + 3);
+                                if (rest) {
+                                        flags |= OPT_UNSET;
+                                        goto match;
+                                }
+                                /* Abbreviated case */
+                                if (!prefixcmp(options->long_name + 3, arg)) {
+                                        flags |= OPT_UNSET;
+                                        goto is_abbreviated;
+                                }
+                        }
                         /* abbreviated? */
                         if (!strncmp(options->long_name, arg, arg_end - arg)) {
 is_abbreviated:
@@ -259,6 +279,7 @@ is_abbreviated:
                         if (!rest)
                                 continue;
                 }
+match:
                 if (*rest) {
                         if (*rest != '=')
                                 continue;
diff --git a/tools/perf/util/parse-options.h b/tools/perf/util/parse-options.h
index b0241e28eaf7..cbf0149cf221 100644
--- a/tools/perf/util/parse-options.h
+++ b/tools/perf/util/parse-options.h
@@ -82,6 +82,9 @@ typedef int parse_opt_cb(const struct option *, const char *arg, int unset);
  *   OPTION_{BIT,SET_UINT,SET_PTR} store the {mask,integer,pointer} to put in
  *   the value when met.
  *   CALLBACKS can use it like they want.
+ *
+ * `set`::
+ *   whether an option was set by the user
  */
 struct option {
         enum parse_opt_type type;
@@ -94,6 +97,7 @@ struct option {
         int flags;
         parse_opt_cb *callback;
         intptr_t defval;
+        bool *set;
 };
 
 #define check_vtype(v, type) ( BUILD_BUG_ON_ZERO(!__builtin_types_compatible_p(typeof(v), type)) + v )
@@ -103,6 +107,10 @@ struct option {
 #define OPT_GROUP(h)                { .type = OPTION_GROUP, .help = (h) }
 #define OPT_BIT(s, l, v, h, b)      { .type = OPTION_BIT, .short_name = (s), .long_name = (l), .value = check_vtype(v, int *), .help = (h), .defval = (b) }
 #define OPT_BOOLEAN(s, l, v, h)     { .type = OPTION_BOOLEAN, .short_name = (s), .long_name = (l), .value = check_vtype(v, bool *), .help = (h) }
+#define OPT_BOOLEAN_SET(s, l, v, os, h) \
+        { .type = OPTION_BOOLEAN, .short_name = (s), .long_name = (l), \
+        .value = check_vtype(v, bool *), .help = (h), \
+        .set = check_vtype(os, bool *)}
 #define OPT_INCR(s, l, v, h)        { .type = OPTION_INCR, .short_name = (s), .long_name = (l), .value = check_vtype(v, int *), .help = (h) }
 #define OPT_SET_UINT(s, l, v, h, i)  { .type = OPTION_SET_UINT, .short_name = (s), .long_name = (l), .value = check_vtype(v, unsigned int *), .help = (h), .defval = (i) }
 #define OPT_SET_PTR(s, l, v, h, p)  { .type = OPTION_SET_PTR, .short_name = (s), .long_name = (l), .value = (v), .help = (h), .defval = (p) }
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index c232d8dd410b..b752ecb40d86 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -1,19 +1,23 @@
 #include <linux/list.h>
 #include <sys/types.h>
-#include <sys/stat.h>
 #include <unistd.h>
 #include <stdio.h>
 #include <dirent.h>
 #include "fs.h"
+#include <locale.h>
 #include "util.h"
 #include "pmu.h"
 #include "parse-events.h"
 #include "cpumap.h"
 
+#define UNIT_MAX_LEN    31 /* max length for event unit name */
+
 struct perf_pmu_alias {
         char *name;
         struct list_head terms;
         struct list_head list;
+        char unit[UNIT_MAX_LEN+1];
+        double scale;
 };
 
 struct perf_pmu_format {
@@ -94,7 +98,80 @@ static int pmu_format(const char *name, struct list_head *format)
         return 0;
 }
 
-static int perf_pmu__new_alias(struct list_head *list, char *name, FILE *file)
+static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *name)
+{
+        struct stat st;
+        ssize_t sret;
+        char scale[128];
+        int fd, ret = -1;
+        char path[PATH_MAX];
+        const char *lc;
+
+        snprintf(path, PATH_MAX, "%s/%s.scale", dir, name);
+
+        fd = open(path, O_RDONLY);
+        if (fd == -1)
+                return -1;
+
+        if (fstat(fd, &st) < 0)
+                goto error;
+
+        sret = read(fd, scale, sizeof(scale)-1);
+        if (sret < 0)
+                goto error;
+
+        scale[sret] = '\0';
+        /*
+         * save current locale
+         */
+        lc = setlocale(LC_NUMERIC, NULL);
+
+        /*
+         * force to C locale to ensure kernel
+         * scale string is converted correctly.
+         * kernel uses default C locale.
+         */
+        setlocale(LC_NUMERIC, "C");
+
+        alias->scale = strtod(scale, NULL);
+
+        /* restore locale */
+        setlocale(LC_NUMERIC, lc);
+
+        ret = 0;
+error:
+        close(fd);
+        return ret;
+}
+
+static int perf_pmu__parse_unit(struct perf_pmu_alias *alias, char *dir, char *name)
+{
+        char path[PATH_MAX];
+        ssize_t sret;
+        int fd;
+
+        snprintf(path, PATH_MAX, "%s/%s.unit", dir, name);
+
+        fd = open(path, O_RDONLY);
+        if (fd == -1)
+                return -1;
+
+                sret = read(fd, alias->unit, UNIT_MAX_LEN);
+        if (sret < 0)
+                goto error;
+
+        close(fd);
+
+        alias->unit[sret] = '\0';
+
+        return 0;
+error:
+        close(fd);
+        alias->unit[0] = '\0';
+        return -1;
+}
+
+static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FILE *file)
 {
         struct perf_pmu_alias *alias;
         char buf[256];
@@ -110,6 +187,9 @@ static int perf_pmu__new_alias(struct list_head *list, char *name, FILE *file)
                 return -ENOMEM;
 
         INIT_LIST_HEAD(&alias->terms);
+        alias->scale = 1.0;
+        alias->unit[0] = '\0';
+
         ret = parse_events_terms(&alias->terms, buf);
         if (ret) {
                 free(alias);
@@ -117,7 +197,14 @@ static int perf_pmu__new_alias(struct list_head *list, char *name, FILE *file)
         }
 
         alias->name = strdup(name);
+        /*
+         * load unit name and scale if available
+         */
+        perf_pmu__parse_unit(alias, dir, name);
+        perf_pmu__parse_scale(alias, dir, name);
+
         list_add_tail(&alias->list, list);
+
         return 0;
 }
 
@@ -129,6 +216,7 @@ static int pmu_aliases_parse(char *dir, struct list_head *head)
 {
         struct dirent *evt_ent;
         DIR *event_dir;
+        size_t len;
         int ret = 0;
 
         event_dir = opendir(dir);
@@ -143,13 +231,24 @@ static int pmu_aliases_parse(char *dir, struct list_head *head)
                 if (!strcmp(name, ".") || !strcmp(name, ".."))
                         continue;
 
+                /*
+                 * skip .unit and .scale info files
+                 * parsed in perf_pmu__new_alias()
+                 */
+                len = strlen(name);
+                if (len > 5 && !strcmp(name + len - 5, ".unit"))
+                        continue;
+                if (len > 6 && !strcmp(name + len - 6, ".scale"))
+                        continue;
+
                 snprintf(path, PATH_MAX, "%s/%s", dir, name);
 
                 ret = -EINVAL;
                 file = fopen(path, "r");
                 if (!file)
                         break;
-                ret = perf_pmu__new_alias(head, name, file);
+
+                ret = perf_pmu__new_alias(head, dir, name, file);
                 fclose(file);
         }
 
@@ -406,7 +505,7 @@ static __u64 pmu_format_value(unsigned long *format, __u64 value)
 
 /*
  * Setup one of config[12] attr members based on the
- * user input data - temr parameter.
+ * user input data - term parameter.
  */
 static int pmu_config_term(struct list_head *formats,
                            struct perf_event_attr *attr,
@@ -508,16 +607,46 @@ static struct perf_pmu_alias *pmu_find_alias(struct perf_pmu *pmu,
         return NULL;
 }
 
+
+static int check_unit_scale(struct perf_pmu_alias *alias,
+                            const char **unit, double *scale)
+{
+        /*
+         * Only one term in event definition can
+         * define unit and scale, fail if there's
+         * more than one.
+         */
+        if ((*unit && alias->unit) ||
+            (*scale && alias->scale))
+                return -EINVAL;
+
+        if (alias->unit)
+                *unit = alias->unit;
+
+        if (alias->scale)
+                *scale = alias->scale;
+
+        return 0;
+}
+
 /*
  * Find alias in the terms list and replace it with the terms
  * defined for the alias
  */
-int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms)
+int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
+                          const char **unit, double *scale)
 {
         struct parse_events_term *term, *h;
         struct perf_pmu_alias *alias;
         int ret;
 
+        /*
+         * Mark unit and scale as not set
+         * (different from default values, see below)
+         */
+        *unit   = NULL;
+        *scale  = 0.0;
+
         list_for_each_entry_safe(term, h, head_terms, list) {
                 alias = pmu_find_alias(pmu, term);
                 if (!alias)
@@ -525,9 +654,26 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms)
                 ret = pmu_alias_terms(alias, &term->list);
                 if (ret)
                         return ret;
+
+                ret = check_unit_scale(alias, unit, scale);
+                if (ret)
+                        return ret;
+
                 list_del(&term->list);
                 free(term);
         }
+
+        /*
+         * if no unit or scale foundin aliases, then
+         * set defaults as for evsel
+         * unit cannot left to NULL
+         */
+        if (*unit == NULL)
+                *unit   = "";
+
+        if (*scale == 0.0)
+                *scale  = 1.0;
+
         return 0;
 }
 
@@ -625,7 +771,7 @@ void print_pmu_events(const char *event_glob, bool name_only)
                         continue;
                 }
                 printf("  %-50s [Kernel PMU event]\n", aliases[j]);
-                free(aliases[j]);
+                zfree(&aliases[j]);
                 printed++;
         }
         if (printed)
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 1179b26f244a..8b64125a9281 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -28,7 +28,8 @@ int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
 int perf_pmu__config_terms(struct list_head *formats,
                            struct perf_event_attr *attr,
                            struct list_head *head_terms);
-int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms);
+int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
+                          const char **unit, double *scale);
 struct list_head *perf_pmu__alias(struct perf_pmu *pmu,
                                   struct list_head *head_terms);
 int perf_pmu_wrap(void);
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 9c6989ca2bea..a8a9b6cd93a8 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 <lk/debugfs.h>
+#include <api/fs/debugfs.h>
 #include "trace-event.h"        /* For __maybe_unused */
 #include "probe-event.h"
 #include "probe-finder.h"
@@ -72,6 +72,7 @@ static int e_snprintf(char *str, size_t size, const char *format, ...)
 static char *synthesize_perf_probe_point(struct perf_probe_point *pp);
 static int convert_name_to_addr(struct perf_probe_event *pev,
                                 const char *exec);
+static void clear_probe_trace_event(struct probe_trace_event *tev);
 static struct machine machine;
 
 /* Initialize symbol maps and path of vmlinux/modules */
@@ -154,7 +155,7 @@ static struct dso *kernel_get_module_dso(const char *module)
 
         vmlinux_name = symbol_conf.vmlinux_name;
         if (vmlinux_name) {
-                if (dso__load_vmlinux(dso, map, vmlinux_name, NULL) <= 0)
+                if (dso__load_vmlinux(dso, map, vmlinux_name, false, NULL) <= 0)
                         return NULL;
         } else {
                 if (dso__load_vmlinux_path(dso, map, NULL) <= 0) {
@@ -186,6 +187,37 @@ static int init_user_exec(void)
         return ret;
 }
 
+static int convert_exec_to_group(const char *exec, char **result)
+{
+        char *ptr1, *ptr2, *exec_copy;
+        char buf[64];
+        int ret;
+
+        exec_copy = strdup(exec);
+        if (!exec_copy)
+                return -ENOMEM;
+
+        ptr1 = basename(exec_copy);
+        if (!ptr1) {
+                ret = -EINVAL;
+                goto out;
+        }
+
+        ptr2 = strpbrk(ptr1, "-._");
+        if (ptr2)
+                *ptr2 = '\0';
+        ret = e_snprintf(buf, 64, "%s_%s", PERFPROBE_GROUP, ptr1);
+        if (ret < 0)
+                goto out;
+
+        *result = strdup(buf);
+        ret = *result ? 0 : -ENOMEM;
+
+out:
+        free(exec_copy);
+        return ret;
+}
+
 static int convert_to_perf_probe_point(struct probe_trace_point *tp,
                                         struct perf_probe_point *pp)
 {
@@ -261,6 +293,68 @@ static int kprobe_convert_to_perf_probe(struct probe_trace_point *tp,
         return 0;
 }
 
+static int get_text_start_address(const char *exec, unsigned long *address)
+{
+        Elf *elf;
+        GElf_Ehdr ehdr;
+        GElf_Shdr shdr;
+        int fd, ret = -ENOENT;
+
+        fd = open(exec, O_RDONLY);
+        if (fd < 0)
+                return -errno;
+
+        elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
+        if (elf == NULL)
+                return -EINVAL;
+
+        if (gelf_getehdr(elf, &ehdr) == NULL)
+                goto out;
+
+        if (!elf_section_by_name(elf, &ehdr, &shdr, ".text", NULL))
+                goto out;
+
+        *address = shdr.sh_addr - shdr.sh_offset;
+        ret = 0;
+out:
+        elf_end(elf);
+        return ret;
+}
+
+static int add_exec_to_probe_trace_events(struct probe_trace_event *tevs,
+                                          int ntevs, const char *exec)
+{
+        int i, ret = 0;
+        unsigned long offset, stext = 0;
+        char buf[32];
+
+        if (!exec)
+                return 0;
+
+        ret = get_text_start_address(exec, &stext);
+        if (ret < 0)
+                return ret;
+
+        for (i = 0; i < ntevs && ret >= 0; i++) {
+                offset = tevs[i].point.address - stext;
+                offset += tevs[i].point.offset;
+                tevs[i].point.offset = 0;
+                zfree(&tevs[i].point.symbol);
+                ret = e_snprintf(buf, 32, "0x%lx", offset);
+                if (ret < 0)
+                        break;
+                tevs[i].point.module = strdup(exec);
+                tevs[i].point.symbol = strdup(buf);
+                if (!tevs[i].point.symbol || !tevs[i].point.module) {
+                        ret = -ENOMEM;
+                        break;
+                }
+                tevs[i].uprobes = true;
+        }
+
+        return ret;
+}
+
 static int add_module_to_probe_trace_events(struct probe_trace_event *tevs,
                                             int ntevs, const char *module)
 {
@@ -290,12 +384,18 @@ static int add_module_to_probe_trace_events(struct probe_trace_event *tevs,
                 }
         }
 
-        if (tmp)
-                free(tmp);
-
+        free(tmp);
         return ret;
 }
 
+static void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs)
+{
+        int i;
+
+        for (i = 0; i < ntevs; i++)
+                clear_probe_trace_event(tevs + i);
+}
+
 /* Try to find perf_probe_event with debuginfo */
 static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
                                           struct probe_trace_event **tevs,
@@ -305,15 +405,6 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
         struct debuginfo *dinfo;
         int ntevs, ret = 0;
 
-        if (pev->uprobes) {
-                if (need_dwarf) {
-                        pr_warning("Debuginfo-analysis is not yet supported"
-                                        " with -x/--exec option.\n");
-                        return -ENOSYS;
-                }
-                return convert_name_to_addr(pev, target);
-        }
-
         dinfo = open_debuginfo(target);
 
         if (!dinfo) {
@@ -332,9 +423,18 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
 
         if (ntevs > 0) {        /* Succeeded to find trace events */
                 pr_debug("find %d probe_trace_events.\n", ntevs);
-                if (target)
-                        ret = add_module_to_probe_trace_events(*tevs, ntevs,
-                                                               target);
+                if (target) {
+                        if (pev->uprobes)
+                                ret = add_exec_to_probe_trace_events(*tevs,
+                                                 ntevs, target);
+                        else
+                                ret = add_module_to_probe_trace_events(*tevs,
+                                                 ntevs, target);
+                }
+                if (ret < 0) {
+                        clear_probe_trace_events(*tevs, ntevs);
+                        zfree(tevs);
+                }
                 return ret < 0 ? ret : ntevs;
         }
 
@@ -401,15 +501,13 @@ static int get_real_path(const char *raw_path, const char *comp_dir,
                 case EFAULT:
                         raw_path = strchr(++raw_path, '/');
                         if (!raw_path) {
-                                free(*new_path);
-                                *new_path = NULL;
+                                zfree(new_path);
                                 return -ENOENT;
                         }
                         continue;
 
                 default:
-                        free(*new_path);
-                        *new_path = NULL;
+                        zfree(new_path);
                         return -errno;
                 }
         }
@@ -580,7 +678,7 @@ static int show_available_vars_at(struct debuginfo *dinfo,
                  */
                 fprintf(stdout, "\t@<%s+%lu>\n", vl->point.symbol,
                         vl->point.offset);
-                free(vl->point.symbol);
+                zfree(&vl->point.symbol);
                 nvars = 0;
                 if (vl->vars) {
                         strlist__for_each(node, vl->vars) {
@@ -647,16 +745,14 @@ static int kprobe_convert_to_perf_probe(struct probe_trace_point *tp,
 
 static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
                                 struct probe_trace_event **tevs __maybe_unused,
-                                int max_tevs __maybe_unused, const char *target)
+                                int max_tevs __maybe_unused,
+                                const char *target __maybe_unused)
 {
         if (perf_probe_event_need_dwarf(pev)) {
                 pr_warning("Debuginfo-analysis is not supported.\n");
                 return -ENOSYS;
         }
 
-        if (pev->uprobes)
-                return convert_name_to_addr(pev, target);
-
         return 0;
 }
 
@@ -678,6 +774,28 @@ int show_available_vars(struct perf_probe_event *pevs __maybe_unused,
 }
 #endif
 
+void line_range__clear(struct line_range *lr)
+{
+        struct line_node *ln;
+
+        free(lr->function);
+        free(lr->file);
+        free(lr->path);
+        free(lr->comp_dir);
+        while (!list_empty(&lr->line_list)) {
+                ln = list_first_entry(&lr->line_list, struct line_node, list);
+                list_del(&ln->list);
+                free(ln);
+        }
+        memset(lr, 0, sizeof(*lr));
+}
+
+void line_range__init(struct line_range *lr)
+{
+        memset(lr, 0, sizeof(*lr));
+        INIT_LIST_HEAD(&lr->line_list);
+}
+
 static int parse_line_num(char **ptr, int *val, const char *what)
 {
         const char *start = *ptr;
@@ -1278,8 +1396,7 @@ static char *synthesize_perf_probe_point(struct perf_probe_point *pp)
 error:
         pr_debug("Failed to synthesize perf probe point: %s\n",
                  strerror(-ret));
-        if (buf)
-                free(buf);
+        free(buf);
         return NULL;
 }
 
@@ -1480,34 +1597,25 @@ void clear_perf_probe_event(struct perf_probe_event *pev)
         struct perf_probe_arg_field *field, *next;
         int i;
 
-        if (pev->event)
-                free(pev->event);
-        if (pev->group)
-                free(pev->group);
-        if (pp->file)
-                free(pp->file);
-        if (pp->function)
-                free(pp->function);
-        if (pp->lazy_line)
-                free(pp->lazy_line);
+        free(pev->event);
+        free(pev->group);
+        free(pp->file);
+        free(pp->function);
+        free(pp->lazy_line);
+
         for (i = 0; i < pev->nargs; i++) {
-                if (pev->args[i].name)
-                        free(pev->args[i].name);
-                if (pev->args[i].var)
-                        free(pev->args[i].var);
-                if (pev->args[i].type)
-                        free(pev->args[i].type);
+                free(pev->args[i].name);
+                free(pev->args[i].var);
+                free(pev->args[i].type);
                 field = pev->args[i].field;
                 while (field) {
                         next = field->next;
-                        if (field->name)
-                                free(field->name);
+                        zfree(&field->name);
                         free(field);
                         field = next;
                 }
         }
-        if (pev->args)
-                free(pev->args);
+        free(pev->args);
         memset(pev, 0, sizeof(*pev));
 }
 
@@ -1516,21 +1624,14 @@ static void clear_probe_trace_event(struct probe_trace_event *tev)
         struct probe_trace_arg_ref *ref, *next;
         int i;
 
-        if (tev->event)
-                free(tev->event);
-        if (tev->group)
-                free(tev->group);
-        if (tev->point.symbol)
-                free(tev->point.symbol);
-        if (tev->point.module)
-                free(tev->point.module);
+        free(tev->event);
+        free(tev->group);
+        free(tev->point.symbol);
+        free(tev->point.module);
         for (i = 0; i < tev->nargs; i++) {
-                if (tev->args[i].name)
-                        free(tev->args[i].name);
-                if (tev->args[i].value)
-                        free(tev->args[i].value);
-                if (tev->args[i].type)
-                        free(tev->args[i].type);
+                free(tev->args[i].name);
+                free(tev->args[i].value);
+                free(tev->args[i].type);
                 ref = tev->args[i].ref;
                 while (ref) {
                         next = ref->next;
@@ -1538,8 +1639,7 @@ static void clear_probe_trace_event(struct probe_trace_event *tev)
                         ref = next;
                 }
         }
-        if (tev->args)
-                free(tev->args);
+        free(tev->args);
         memset(tev, 0, sizeof(*tev));
 }
 
@@ -1913,14 +2013,29 @@ static int convert_to_probe_trace_events(struct perf_probe_event *pev,
                                           int max_tevs, const char *target)
 {
         struct symbol *sym;
-        int ret = 0, i;
+        int ret, i;
         struct probe_trace_event *tev;
 
+        if (pev->uprobes && !pev->group) {
+                /* Replace group name if not given */
+                ret = convert_exec_to_group(target, &pev->group);
+                if (ret != 0) {
+                        pr_warning("Failed to make a group name.\n");
+                        return ret;
+                }
+        }
+
         /* Convert perf_probe_event with debuginfo */
         ret = try_to_find_probe_trace_events(pev, tevs, max_tevs, target);
         if (ret != 0)
                 return ret;     /* Found in debuginfo or got an error */
 
+        if (pev->uprobes) {
+                ret = convert_name_to_addr(pev, target);
+                if (ret < 0)
+                        return ret;
+        }
+
         /* Allocate trace event buffer */
         tev = *tevs = zalloc(sizeof(struct probe_trace_event));
         if (tev == NULL)
@@ -2056,7 +2171,7 @@ end:
         for (i = 0; i < npevs; i++) {
                 for (j = 0; j < pkgs[i].ntevs; j++)
                         clear_probe_trace_event(&pkgs[i].tevs[j]);
-                free(pkgs[i].tevs);
+                zfree(&pkgs[i].tevs);
         }
         free(pkgs);
 
@@ -2281,7 +2396,7 @@ static int convert_name_to_addr(struct perf_probe_event *pev, const char *exec)
         struct perf_probe_point *pp = &pev->point;
         struct symbol *sym;
         struct map *map = NULL;
-        char *function = NULL, *name = NULL;
+        char *function = NULL;
         int ret = -EINVAL;
         unsigned long long vaddr = 0;
 
@@ -2297,12 +2412,7 @@ static int convert_name_to_addr(struct perf_probe_event *pev, const char *exec)
                 goto out;
         }
 
-        name = realpath(exec, NULL);
-        if (!name) {
-                pr_warning("Cannot find realpath for %s.\n", exec);
-                goto out;
-        }
-        map = dso__new_map(name);
+        map = dso__new_map(exec);
         if (!map) {
                 pr_warning("Cannot find appropriate DSO for %s.\n", exec);
                 goto out;
@@ -2367,7 +2477,5 @@ out:
         }
         if (function)
                 free(function);
-        if (name)
-                free(name);
         return ret;
 }
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index f9f3de8b4220..fcaf7273e85a 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -12,6 +12,7 @@ struct probe_trace_point {
         char            *symbol;        /* Base symbol */
         char            *module;        /* Module name */
         unsigned long   offset;         /* Offset from symbol */
+        unsigned long   address;        /* Actual address of the trace point */
         bool            retprobe;       /* Return probe flag */
 };
 
@@ -119,6 +120,12 @@ extern void clear_perf_probe_event(struct perf_probe_event *pev);
 /* Command string to line-range */
 extern int parse_line_range_desc(const char *cmd, struct line_range *lr);
 
+/* Release line range members */
+extern void line_range__clear(struct line_range *lr);
+
+/* Initialize line range */
+extern void line_range__init(struct line_range *lr);
+
 /* Internal use: Return kernel/module path */
 extern const char *kernel_get_module_path(const char *module);
 
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index ffb657ffd327..061edb162b5b 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -226,10 +226,8 @@ struct debuginfo *debuginfo__new(const char *path)
         if (!dbg)
                 return NULL;
 
-        if (debuginfo__init_offline_dwarf(dbg, path) < 0) {
-                free(dbg);
-                dbg = NULL;
-        }
+        if (debuginfo__init_offline_dwarf(dbg, path) < 0)
+                zfree(&dbg);
 
         return dbg;
 }
@@ -241,10 +239,8 @@ struct debuginfo *debuginfo__new_online_kernel(unsigned long addr)
         if (!dbg)
                 return NULL;
 
-        if (debuginfo__init_online_kernel_dwarf(dbg, (Dwarf_Addr)addr) < 0) {
-                free(dbg);
-                dbg = NULL;
-        }
+        if (debuginfo__init_online_kernel_dwarf(dbg, (Dwarf_Addr)addr) < 0)
+                zfree(&dbg);
 
         return dbg;
 }
@@ -729,6 +725,7 @@ static int convert_to_trace_point(Dwarf_Die *sp_die, Dwfl_Module *mod,
                 return -ENOENT;
         }
         tp->offset = (unsigned long)(paddr - sym.st_value);
+        tp->address = (unsigned long)paddr;
         tp->symbol = strdup(symbol);
         if (!tp->symbol)
                 return -ENOMEM;
@@ -1301,8 +1298,7 @@ int debuginfo__find_trace_events(struct debuginfo *dbg,
 
         ret = debuginfo__find_probes(dbg, &tf.pf);
         if (ret < 0) {
-                free(*tevs);
-                *tevs = NULL;
+                zfree(tevs);
                 return ret;
         }
 
@@ -1413,13 +1409,10 @@ int debuginfo__find_available_vars_at(struct debuginfo *dbg,
         if (ret < 0) {
                 /* Free vlist for error */
                 while (af.nvls--) {
-                        if (af.vls[af.nvls].point.symbol)
-                                free(af.vls[af.nvls].point.symbol);
-                        if (af.vls[af.nvls].vars)
-                                strlist__delete(af.vls[af.nvls].vars);
+                        zfree(&af.vls[af.nvls].point.symbol);
+                        strlist__delete(af.vls[af.nvls].vars);
                 }
-                free(af.vls);
-                *vls = NULL;
+                zfree(vls);
                 return ret;
         }
 
@@ -1523,10 +1516,7 @@ post:
         if (fname) {
                 ppt->file = strdup(fname);
                 if (ppt->file == NULL) {
-                        if (ppt->function) {
-                                free(ppt->function);
-                                ppt->function = NULL;
-                        }
+                        zfree(&ppt->function);
                         ret = -ENOMEM;
                         goto end;
                 }
@@ -1580,8 +1570,7 @@ static int find_line_range_by_line(Dwarf_Die *sp_die, struct line_finder *lf)
                 else
                         ret = 0;        /* Lines are not found */
         else {
-                free(lf->lr->path);
-                lf->lr->path = NULL;
+                zfree(&lf->lr->path);
         }
         return ret;
 }
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index 239036fb2b2c..595bfc73d2ed 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -18,4 +18,5 @@ util/cgroup.c
 util/rblist.c
 util/strlist.c
 util/fs.c
+util/trace-event.c
 ../../lib/rbtree.c
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 4bf8ace7f511..122669c18ff4 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -908,9 +908,10 @@ static PyObject *pyrf_evlist__item(PyObject *obj, Py_ssize_t i)
         if (i >= pevlist->evlist.nr_entries)
                 return NULL;
 
-        list_for_each_entry(pos, &pevlist->evlist.entries, node)
+        evlist__for_each(&pevlist->evlist, pos) {
                 if (i-- == 0)
                         break;
+        }
 
         return Py_BuildValue("O", container_of(pos, struct pyrf_evsel, evsel));
 }
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index c8845b107f60..373762501dad 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -74,8 +74,7 @@ bool perf_can_sample_identifier(void)
         return perf_probe_api(perf_probe_sample_identifier);
 }
 
-void perf_evlist__config(struct perf_evlist *evlist,
-                        struct perf_record_opts *opts)
+void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts)
 {
         struct perf_evsel *evsel;
         bool use_sample_identifier = false;
@@ -90,19 +89,19 @@ void perf_evlist__config(struct perf_evlist *evlist,
         if (evlist->cpus->map[0] < 0)
                 opts->no_inherit = true;
 
-        list_for_each_entry(evsel, &evlist->entries, node)
+        evlist__for_each(evlist, evsel)
                 perf_evsel__config(evsel, opts);
 
         if (evlist->nr_entries > 1) {
                 struct perf_evsel *first = perf_evlist__first(evlist);
 
-                list_for_each_entry(evsel, &evlist->entries, node) {
+                evlist__for_each(evlist, evsel) {
                         if (evsel->attr.sample_type == first->attr.sample_type)
                                 continue;
                         use_sample_identifier = perf_can_sample_identifier();
                         break;
                 }
-                list_for_each_entry(evsel, &evlist->entries, node)
+                evlist__for_each(evlist, evsel)
                         perf_evsel__set_sample_id(evsel, use_sample_identifier);
         }
 
@@ -123,7 +122,7 @@ static int get_max_rate(unsigned int *rate)
         return filename__read_int(path, (int *) rate);
 }
 
-static int perf_record_opts__config_freq(struct perf_record_opts *opts)
+static int record_opts__config_freq(struct record_opts *opts)
 {
         bool user_freq = opts->user_freq != UINT_MAX;
         unsigned int max_rate;
@@ -173,7 +172,44 @@ static int perf_record_opts__config_freq(struct perf_record_opts *opts)
         return 0;
 }
 
-int perf_record_opts__config(struct perf_record_opts *opts)
+int record_opts__config(struct record_opts *opts)
 {
-        return perf_record_opts__config_freq(opts);
+        return record_opts__config_freq(opts);
+}
+
+bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str)
+{
+        struct perf_evlist *temp_evlist;
+        struct perf_evsel *evsel;
+        int err, fd, cpu;
+        bool ret = false;
+
+        temp_evlist = perf_evlist__new();
+        if (!temp_evlist)
+                return false;
+
+        err = parse_events(temp_evlist, str);
+        if (err)
+                goto out_delete;
+
+        evsel = perf_evlist__last(temp_evlist);
+
+        if (!evlist || cpu_map__empty(evlist->cpus)) {
+                struct cpu_map *cpus = cpu_map__new(NULL);
+
+                cpu =  cpus ? cpus->map[0] : 0;
+                cpu_map__delete(cpus);
+        } else {
+                cpu = evlist->cpus->map[0];
+        }
+
+        fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1, 0);
+        if (fd >= 0) {
+                close(fd);
+                ret = true;
+        }
+
+out_delete:
+        perf_evlist__delete(temp_evlist);
+        return ret;
 }
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index d5e5969f6fea..e108207c5de0 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -194,8 +194,7 @@ static void define_event_symbols(struct event_format *event,
                 zero_flag_atom = 0;
                 break;
         case PRINT_FIELD:
-                if (cur_field_name)
-                        free(cur_field_name);
+                free(cur_field_name);
                 cur_field_name = strdup(args->field.name);
                 break;
         case PRINT_FLAGS:
@@ -257,12 +256,9 @@ static inline struct event_format *find_cache_event(struct perf_evsel *evsel)
         return event;
 }
 
-static void perl_process_tracepoint(union perf_event *perf_event __maybe_unused,
-                                    struct perf_sample *sample,
+static void perl_process_tracepoint(struct perf_sample *sample,
                                     struct perf_evsel *evsel,
-                                    struct machine *machine __maybe_unused,
-                                    struct thread *thread,
-                                        struct addr_location *al)
+                                    struct thread *thread)
 {
         struct format_field *field;
         static char handler[256];
@@ -349,10 +345,7 @@ static void perl_process_tracepoint(union perf_event *perf_event __maybe_unused,
 
 static void perl_process_event_generic(union perf_event *event,
                                        struct perf_sample *sample,
-                                       struct perf_evsel *evsel,
-                                       struct machine *machine __maybe_unused,
-                                       struct thread *thread __maybe_unused,
-                                           struct addr_location *al __maybe_unused)
+                                       struct perf_evsel *evsel)
 {
         dSP;
 
@@ -377,12 +370,11 @@ static void perl_process_event_generic(union perf_event *event,
 static void perl_process_event(union perf_event *event,
                                struct perf_sample *sample,
                                struct perf_evsel *evsel,
-                               struct machine *machine,
                                struct thread *thread,
-                                   struct addr_location *al)
+                               struct addr_location *al __maybe_unused)
 {
-        perl_process_tracepoint(event, sample, evsel, machine, thread, al);
-        perl_process_event_generic(event, sample, evsel, machine, thread, al);
+        perl_process_tracepoint(sample, evsel, thread);
+        perl_process_event_generic(event, sample, evsel);
 }
 
 static void run_start_sub(void)
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 53c20e7fd900..cd9774df3750 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -161,8 +161,7 @@ static void define_event_symbols(struct event_format *event,
                 zero_flag_atom = 0;
                 break;
         case PRINT_FIELD:
-                if (cur_field_name)
-                        free(cur_field_name);
+                free(cur_field_name);
                 cur_field_name = strdup(args->field.name);
                 break;
         case PRINT_FLAGS:
@@ -231,13 +230,10 @@ static inline struct event_format *find_cache_event(struct perf_evsel *evsel)
         return event;
 }
 
-static void python_process_tracepoint(union perf_event *perf_event
-                                      __maybe_unused,
-                                 struct perf_sample *sample,
-                                 struct perf_evsel *evsel,
-                                 struct machine *machine __maybe_unused,
-                                 struct thread *thread,
-                                 struct addr_location *al)
+static void python_process_tracepoint(struct perf_sample *sample,
+                                      struct perf_evsel *evsel,
+                                      struct thread *thread,
+                                      struct addr_location *al)
 {
         PyObject *handler, *retval, *context, *t, *obj, *dict = NULL;
         static char handler_name[256];
@@ -351,11 +347,8 @@ static void python_process_tracepoint(union perf_event *perf_event
         Py_DECREF(t);
 }
 
-static void python_process_general_event(union perf_event *perf_event
-                                         __maybe_unused,
-                                         struct perf_sample *sample,
+static void python_process_general_event(struct perf_sample *sample,
                                          struct perf_evsel *evsel,
-                                         struct machine *machine __maybe_unused,
                                          struct thread *thread,
                                          struct addr_location *al)
 {
@@ -411,22 +404,19 @@ exit:
         Py_DECREF(t);
 }
 
-static void python_process_event(union perf_event *perf_event,
+static void python_process_event(union perf_event *event __maybe_unused,
                                  struct perf_sample *sample,
                                  struct perf_evsel *evsel,
-                                 struct machine *machine,
                                  struct thread *thread,
                                  struct addr_location *al)
 {
         switch (evsel->attr.type) {
         case PERF_TYPE_TRACEPOINT:
-                python_process_tracepoint(perf_event, sample, evsel,
-                                          machine, thread, al);
+                python_process_tracepoint(sample, evsel, thread, al);
                 break;
         /* Reserve for future process_hw/sw/raw APIs */
         default:
-                python_process_general_event(perf_event, sample, evsel,
-                                             machine, thread, al);
+                python_process_general_event(sample, evsel, thread, al);
         }
 }
 
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index f36d24a02445..0b39a48e5110 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -132,18 +132,18 @@ static void perf_session__delete_threads(struct perf_session *session)
 
 static void perf_session_env__delete(struct perf_session_env *env)
 {
-        free(env->hostname);
-        free(env->os_release);
-        free(env->version);
-        free(env->arch);
-        free(env->cpu_desc);
-        free(env->cpuid);
+        zfree(&env->hostname);
+        zfree(&env->os_release);
+        zfree(&env->version);
+        zfree(&env->arch);
+        zfree(&env->cpu_desc);
+        zfree(&env->cpuid);
 
-        free(env->cmdline);
-        free(env->sibling_cores);
-        free(env->sibling_threads);
-        free(env->numa_nodes);
-        free(env->pmu_mappings);
+        zfree(&env->cmdline);
+        zfree(&env->sibling_cores);
+        zfree(&env->sibling_threads);
+        zfree(&env->numa_nodes);
+        zfree(&env->pmu_mappings);
 }
 
 void perf_session__delete(struct perf_session *session)
@@ -247,27 +247,6 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
         }
 }
  
-void mem_bswap_32(void *src, int byte_size)
-{
-        u32 *m = src;
-        while (byte_size > 0) {
-                *m = bswap_32(*m);
-                byte_size -= sizeof(u32);
-                ++m;
-        }
-}
-
-void mem_bswap_64(void *src, int byte_size)
-{
-        u64 *m = src;
-
-        while (byte_size > 0) {
-                *m = bswap_64(*m);
-                byte_size -= sizeof(u64);
-                ++m;
-        }
-}
-
 static void swap_sample_id_all(union perf_event *event, void *data)
 {
         void *end = (void *) event + event->header.size;
@@ -851,6 +830,7 @@ static struct machine *
                                                struct perf_sample *sample)
 {
         const u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+        struct machine *machine;
 
         if (perf_guest &&
             ((cpumode == PERF_RECORD_MISC_GUEST_KERNEL) ||
@@ -863,7 +843,11 @@ static struct machine *
                 else
                         pid = sample->pid;
 
-                return perf_session__findnew_machine(session, pid);
+                machine = perf_session__find_machine(session, pid);
+                if (!machine)
+                        machine = perf_session__findnew_machine(session,
+                                                DEFAULT_GUEST_KERNEL_ID);
+                return machine;
         }
 
         return &session->machines.host;
@@ -1158,7 +1142,7 @@ static int __perf_session__process_pipe_events(struct perf_session *session,
         void *buf = NULL;
         int skip = 0;
         u64 head;
-        int err;
+        ssize_t err;
         void *p;
 
         perf_tool__fill_defaults(tool);
@@ -1400,7 +1384,7 @@ bool perf_session__has_traces(struct perf_session *session, const char *msg)
 {
         struct perf_evsel *evsel;
 
-        list_for_each_entry(evsel, &session->evlist->entries, node) {
+        evlist__for_each(session->evlist, evsel) {
                 if (evsel->attr.type == PERF_TYPE_TRACEPOINT)
                         return true;
         }
@@ -1458,7 +1442,7 @@ size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp)
 
         ret += events_stats__fprintf(&session->stats, fp);
 
-        list_for_each_entry(pos, &session->evlist->entries, node) {
+        evlist__for_each(session->evlist, pos) {
                 ret += fprintf(fp, "%s stats:\n", perf_evsel__name(pos));
                 ret += events_stats__fprintf(&pos->hists.stats, fp);
         }
@@ -1480,35 +1464,30 @@ struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
 {
         struct perf_evsel *pos;
 
-        list_for_each_entry(pos, &session->evlist->entries, node) {
+        evlist__for_each(session->evlist, pos) {
                 if (pos->attr.type == type)
                         return pos;
         }
         return NULL;
 }
 
-void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event,
-                          struct perf_sample *sample, struct machine *machine,
+void perf_evsel__print_ip(struct perf_evsel *evsel, struct perf_sample *sample,
+                          struct addr_location *al,
                           unsigned int print_opts, unsigned int stack_depth)
 {
-        struct addr_location al;
         struct callchain_cursor_node *node;
         int print_ip = print_opts & PRINT_IP_OPT_IP;
         int print_sym = print_opts & PRINT_IP_OPT_SYM;
         int print_dso = print_opts & PRINT_IP_OPT_DSO;
         int print_symoffset = print_opts & PRINT_IP_OPT_SYMOFFSET;
         int print_oneline = print_opts & PRINT_IP_OPT_ONELINE;
+        int print_srcline = print_opts & PRINT_IP_OPT_SRCLINE;
         char s = print_oneline ? ' ' : '\t';
 
-        if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
-                error("problem processing %d event, skipping it.\n",
-                        event->header.type);
-                return;
-        }
-
         if (symbol_conf.use_callchain && sample->callchain) {
+                struct addr_location node_al;
 
-                if (machine__resolve_callchain(machine, evsel, al.thread,
+                if (machine__resolve_callchain(al->machine, evsel, al->thread,
                                                sample, NULL, NULL,
                                                PERF_MAX_STACK_DEPTH) != 0) {
                         if (verbose)
@@ -1517,20 +1496,31 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event,
                 }
                 callchain_cursor_commit(&callchain_cursor);
 
+                if (print_symoffset)
+                        node_al = *al;
+
                 while (stack_depth) {
+                        u64 addr = 0;
+
                         node = callchain_cursor_current(&callchain_cursor);
                         if (!node)
                                 break;
 
+                        if (node->sym && node->sym->ignore)
+                                goto next;
+
                         if (print_ip)
                                 printf("%c%16" PRIx64, s, node->ip);
 
+                        if (node->map)
+                                addr = node->map->map_ip(node->map, node->ip);
+
                         if (print_sym) {
                                 printf(" ");
                                 if (print_symoffset) {
-                                        al.addr = node->ip;
-                                        al.map  = node->map;
-                                        symbol__fprintf_symname_offs(node->sym, &al, stdout);
+                                        node_al.addr = addr;
+                                        node_al.map  = node->map;
+                                        symbol__fprintf_symname_offs(node->sym, &node_al, stdout);
                                 } else
                                         symbol__fprintf_symname(node->sym, stdout);
                         }
@@ -1541,39 +1531,49 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event,
                                 printf(")");
                         }
 
+                        if (print_srcline)
+                                map__fprintf_srcline(node->map, addr, "\n  ",
+                                                     stdout);
+
                         if (!print_oneline)
                                 printf("\n");
 
-                        callchain_cursor_advance(&callchain_cursor);
-
                         stack_depth--;
+next:
+                        callchain_cursor_advance(&callchain_cursor);
                 }
 
         } else {
+                if (al->sym && al->sym->ignore)
+                        return;
+
                 if (print_ip)
                         printf("%16" PRIx64, sample->ip);
 
                 if (print_sym) {
                         printf(" ");
                         if (print_symoffset)
-                                symbol__fprintf_symname_offs(al.sym, &al,
+                                symbol__fprintf_symname_offs(al->sym, al,
                                                              stdout);
                         else
-                                symbol__fprintf_symname(al.sym, stdout);
+                                symbol__fprintf_symname(al->sym, stdout);
                 }
 
                 if (print_dso) {
                         printf(" (");
-                        map__fprintf_dsoname(al.map, stdout);
+                        map__fprintf_dsoname(al->map, stdout);
                         printf(")");
                 }
+
+                if (print_srcline)
+                        map__fprintf_srcline(al->map, al->addr, "\n  ", stdout);
         }
 }
 
 int perf_session__cpu_bitmap(struct perf_session *session,
                              const char *cpu_list, unsigned long *cpu_bitmap)
 {
-        int i;
+        int i, err = -1;
         struct cpu_map *map;
 
         for (i = 0; i < PERF_TYPE_MAX; ++i) {
@@ -1602,13 +1602,17 @@ int perf_session__cpu_bitmap(struct perf_session *session,
                 if (cpu >= MAX_NR_CPUS) {
                         pr_err("Requested CPU %d too large. "
                                "Consider raising MAX_NR_CPUS\n", cpu);
-                        return -1;
+                        goto out_delete_map;
                 }
 
                 set_bit(cpu, cpu_bitmap);
         }
 
-        return 0;
+        err = 0;
+
+out_delete_map:
+        cpu_map__delete(map);
+        return err;
 }
 
 void perf_session__fprintf_info(struct perf_session *session, FILE *fp,
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 50f640958f0f..3140f8ae6148 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -1,6 +1,7 @@
 #ifndef __PERF_SESSION_H
 #define __PERF_SESSION_H
 
+#include "trace-event.h"
 #include "hist.h"
 #include "event.h"
 #include "header.h"
@@ -32,7 +33,7 @@ struct perf_session {
         struct perf_header      header;
         struct machines         machines;
         struct perf_evlist      *evlist;
-        struct pevent           *pevent;
+        struct trace_event      tevent;
         struct events_stats     stats;
         bool                    repipe;
         struct ordered_samples  ordered_samples;
@@ -44,6 +45,7 @@ struct perf_session {
 #define PRINT_IP_OPT_DSO                (1<<2)
 #define PRINT_IP_OPT_SYMOFFSET  (1<<3)
 #define PRINT_IP_OPT_ONELINE    (1<<4)
+#define PRINT_IP_OPT_SRCLINE    (1<<5)
 
 struct perf_tool;
 
@@ -72,8 +74,6 @@ int perf_session__resolve_callchain(struct perf_session *session,
 
 bool perf_session__has_traces(struct perf_session *session, const char *msg);
 
-void mem_bswap_64(void *src, int byte_size);
-void mem_bswap_32(void *src, int byte_size);
 void perf_event__attr_swap(struct perf_event_attr *attr);
 
 int perf_session__create_kernel_maps(struct perf_session *session);
@@ -105,8 +105,8 @@ size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp);
 struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
                                             unsigned int type);
 
-void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event,
-                          struct perf_sample *sample, struct machine *machine,
+void perf_evsel__print_ip(struct perf_evsel *evsel, struct perf_sample *sample,
+                          struct addr_location *al,
                           unsigned int print_opts, unsigned int stack_depth);
 
 int perf_session__cpu_bitmap(struct perf_session *session,
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index 58ea5ca6c255..d0aee4b9dfd4 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -25,7 +25,7 @@ cflags += ['-fno-strict-aliasing', '-Wno-write-strings', '-Wno-unused-parameter'
 build_lib = getenv('PYTHON_EXTBUILD_LIB')
 build_tmp = getenv('PYTHON_EXTBUILD_TMP')
 libtraceevent = getenv('LIBTRACEEVENT')
-liblk = getenv('LIBLK')
+libapikfs = getenv('LIBAPIKFS')
 
 ext_sources = [f.strip() for f in file('util/python-ext-sources')
                                 if len(f.strip()) > 0 and f[0] != '#']
@@ -34,7 +34,7 @@ perf = Extension('perf',
                   sources = ext_sources,
                   include_dirs = ['util/include'],
                   extra_compile_args = cflags,
-                  extra_objects = [libtraceevent, liblk],
+                  extra_objects = [libtraceevent, libapikfs],
                  )
 
 setup(name='perf',
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 8b0bb1f4494a..635cd8f8b22e 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -13,6 +13,7 @@ int		have_ignore_callees = 0;
 int             sort__need_collapse = 0;
 int             sort__has_parent = 0;
 int             sort__has_sym = 0;
+int             sort__has_dso = 0;
 enum sort_mode  sort__mode = SORT_MODE__NORMAL;
 
 enum sort_type  sort__first_dimension;
@@ -161,6 +162,11 @@ struct sort_entry sort_dso = {
 
 /* --sort symbol */
 
+static int64_t _sort__addr_cmp(u64 left_ip, u64 right_ip)
+{
+        return (int64_t)(right_ip - left_ip);
+}
+
 static int64_t _sort__sym_cmp(struct symbol *sym_l, struct symbol *sym_r)
 {
         u64 ip_l, ip_r;
@@ -183,15 +189,17 @@ sort__sym_cmp(struct hist_entry *left, struct hist_entry *right)
         int64_t ret;
 
         if (!left->ms.sym && !right->ms.sym)
-                return right->level - left->level;
+                return _sort__addr_cmp(left->ip, right->ip);
 
         /*
          * comparing symbol address alone is not enough since it's a
          * relative address within a dso.
          */
-        ret = sort__dso_cmp(left, right);
-        if (ret != 0)
-                return ret;
+        if (!sort__has_dso) {
+                ret = sort__dso_cmp(left, right);
+                if (ret != 0)
+                        return ret;
+        }
 
         return _sort__sym_cmp(left->ms.sym, right->ms.sym);
 }
@@ -372,7 +380,7 @@ sort__sym_from_cmp(struct hist_entry *left, struct hist_entry *right)
         struct addr_map_symbol *from_r = &right->branch_info->from;
 
         if (!from_l->sym && !from_r->sym)
-                return right->level - left->level;
+                return _sort__addr_cmp(from_l->addr, from_r->addr);
 
         return _sort__sym_cmp(from_l->sym, from_r->sym);
 }
@@ -384,7 +392,7 @@ sort__sym_to_cmp(struct hist_entry *left, struct hist_entry *right)
         struct addr_map_symbol *to_r = &right->branch_info->to;
 
         if (!to_l->sym && !to_r->sym)
-                return right->level - left->level;
+                return _sort__addr_cmp(to_l->addr, to_r->addr);
 
         return _sort__sym_cmp(to_l->sym, to_r->sym);
 }
@@ -1056,6 +1064,8 @@ int sort_dimension__add(const char *tok)
                         sort__has_parent = 1;
                 } else if (sd->entry == &sort_sym) {
                         sort__has_sym = 1;
+                } else if (sd->entry == &sort_dso) {
+                        sort__has_dso = 1;
                 }
 
                 __sort_dimension__add(sd, i);
diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c
index d11aefbc4b8d..f3e4bc5fe5d2 100644
--- a/tools/perf/util/srcline.c
+++ b/tools/perf/util/srcline.c
@@ -129,7 +129,7 @@ static struct a2l_data *addr2line_init(const char *path)
 
 out:
         if (a2l) {
-                free((void *)a2l->input);
+                zfree((char **)&a2l->input);
                 free(a2l);
         }
         bfd_close(abfd);
@@ -140,24 +140,30 @@ static void addr2line_cleanup(struct a2l_data *a2l)
 {
         if (a2l->abfd)
                 bfd_close(a2l->abfd);
-        free((void *)a2l->input);
-        free(a2l->syms);
+        zfree((char **)&a2l->input);
+        zfree(&a2l->syms);
         free(a2l);
 }
 
 static int addr2line(const char *dso_name, unsigned long addr,
-                     char **file, unsigned int *line)
+                     char **file, unsigned int *line, struct dso *dso)
 {
         int ret = 0;
-        struct a2l_data *a2l;
+        struct a2l_data *a2l = dso->a2l;
+
+        if (!a2l) {
+                dso->a2l = addr2line_init(dso_name);
+                a2l = dso->a2l;
+        }
 
-        a2l = addr2line_init(dso_name);
         if (a2l == NULL) {
                 pr_warning("addr2line_init failed for %s\n", dso_name);
                 return 0;
         }
 
         a2l->addr = addr;
+        a2l->found = false;
+
         bfd_map_over_sections(a2l->abfd, find_address_in_section, a2l);
 
         if (a2l->found && a2l->filename) {
@@ -168,14 +174,26 @@ static int addr2line(const char *dso_name, unsigned long addr,
                         ret = 1;
         }
 
-        addr2line_cleanup(a2l);
         return ret;
 }
 
+void dso__free_a2l(struct dso *dso)
+{
+        struct a2l_data *a2l = dso->a2l;
+
+        if (!a2l)
+                return;
+
+        addr2line_cleanup(a2l);
+
+        dso->a2l = NULL;
+}
+
 #else /* HAVE_LIBBFD_SUPPORT */
 
 static int addr2line(const char *dso_name, unsigned long addr,
-                     char **file, unsigned int *line_nr)
+                     char **file, unsigned int *line_nr,
+                     struct dso *dso __maybe_unused)
 {
         FILE *fp;
         char cmd[PATH_MAX];
@@ -219,42 +237,58 @@ out:
         pclose(fp);
         return ret;
 }
+
+void dso__free_a2l(struct dso *dso __maybe_unused)
+{
+}
+
 #endif /* HAVE_LIBBFD_SUPPORT */
 
+/*
+ * Number of addr2line failures (without success) before disabling it for that
+ * dso.
+ */
+#define A2L_FAIL_LIMIT 123
+
 char *get_srcline(struct dso *dso, unsigned long addr)
 {
         char *file = NULL;
         unsigned line = 0;
         char *srcline;
-        char *dso_name = dso->long_name;
-        size_t size;
+        const char *dso_name;
 
         if (!dso->has_srcline)
                 return SRCLINE_UNKNOWN;
 
+        if (dso->symsrc_filename)
+                dso_name = dso->symsrc_filename;
+        else
+                dso_name = dso->long_name;
+
         if (dso_name[0] == '[')
                 goto out;
 
         if (!strncmp(dso_name, "/tmp/perf-", 10))
                 goto out;
 
-        if (!addr2line(dso_name, addr, &file, &line))
+        if (!addr2line(dso_name, addr, &file, &line, dso))
                 goto out;
 
-        /* just calculate actual length */
-        size = snprintf(NULL, 0, "%s:%u", file, line) + 1;
+        if (asprintf(&srcline, "%s:%u", file, line) < 0) {
+                free(file);
+                goto out;
+        }
 
-        srcline = malloc(size);
-        if (srcline)
-                snprintf(srcline, size, "%s:%u", file, line);
-        else
-                srcline = SRCLINE_UNKNOWN;
+        dso->a2l_fails = 0;
 
         free(file);
         return srcline;
 
 out:
-        dso->has_srcline = 0;
+        if (dso->a2l_fails && ++dso->a2l_fails > A2L_FAIL_LIMIT) {
+                dso->has_srcline = 0;
+                dso__free_a2l(dso);
+        }
         return SRCLINE_UNKNOWN;
 }
 
diff --git a/tools/perf/util/strbuf.c b/tools/perf/util/strbuf.c
index cfa906882e2c..4abe23550c73 100644
--- a/tools/perf/util/strbuf.c
+++ b/tools/perf/util/strbuf.c
@@ -28,7 +28,7 @@ void strbuf_init(struct strbuf *sb, ssize_t hint)
 void strbuf_release(struct strbuf *sb)
 {
         if (sb->alloc) {
-                free(sb->buf);
+                zfree(&sb->buf);
                 strbuf_init(sb, 0);
         }
 }
diff --git a/tools/perf/util/strfilter.c b/tools/perf/util/strfilter.c
index 3edd0538161f..79a757a2a15c 100644
--- a/tools/perf/util/strfilter.c
+++ b/tools/perf/util/strfilter.c
@@ -14,7 +14,7 @@ static void strfilter_node__delete(struct strfilter_node *node)
 {
         if (node) {
                 if (node->p && !is_operator(*node->p))
-                        free((char *)node->p);
+                        zfree((char **)&node->p);
                 strfilter_node__delete(node->l);
                 strfilter_node__delete(node->r);
                 free(node);
diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c
index f0b0c008c507..2553e5b55b89 100644
--- a/tools/perf/util/string.c
+++ b/tools/perf/util/string.c
@@ -128,7 +128,7 @@ void argv_free(char **argv)
 {
         char **p;
         for (p = argv; *p; p++)
-                free(*p);
+                zfree(p);
 
         free(argv);
 }
diff --git a/tools/perf/util/strlist.c b/tools/perf/util/strlist.c
index eabdce0a2daa..71f9d102b96f 100644
--- a/tools/perf/util/strlist.c
+++ b/tools/perf/util/strlist.c
@@ -5,6 +5,7 @@
  */
 
 #include "strlist.h"
+#include "util.h"
 #include <errno.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -38,7 +39,7 @@ out_delete:
 static void str_node__delete(struct str_node *snode, bool dupstr)
 {
         if (dupstr)
-                free((void *)snode->s);
+                zfree((char **)&snode->s);
         free(snode);
 }
 
diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c
index 96c866045d60..43262b83c541 100644
--- a/tools/perf/util/svghelper.c
+++ b/tools/perf/util/svghelper.c
@@ -17,8 +17,12 @@
 #include <stdlib.h>
 #include <unistd.h>
 #include <string.h>
+#include <linux/bitops.h>
 
+#include "perf.h"
 #include "svghelper.h"
+#include "util.h"
+#include "cpumap.h"
 
 static u64 first_time, last_time;
 static u64 turbo_frequency, max_freq;
@@ -28,6 +32,8 @@ static u64 turbo_frequency, max_freq;
 #define SLOT_HEIGHT 25.0
 
 int svg_page_width = 1000;
+u64 svg_highlight;
+const char *svg_highlight_name;
 
 #define MIN_TEXT_SIZE 0.01
 
@@ -39,9 +45,14 @@ static double cpu2slot(int cpu)
         return 2 * cpu + 1;
 }
 
+static int *topology_map;
+
 static double cpu2y(int cpu)
 {
-        return cpu2slot(cpu) * SLOT_MULT;
+        if (topology_map)
+                return cpu2slot(topology_map[cpu]) * SLOT_MULT;
+        else
+                return cpu2slot(cpu) * SLOT_MULT;
 }
 
 static double time2pixels(u64 __time)
@@ -95,6 +106,7 @@ void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end)
 
         total_height = (1 + rows + cpu2slot(cpus)) * SLOT_MULT;
         fprintf(svgfile, "<?xml version=\"1.0\" standalone=\"no\"?> \n");
+        fprintf(svgfile, "<!DOCTYPE svg SYSTEM \"http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd\">\n");
         fprintf(svgfile, "<svg width=\"%i\" height=\"%" PRIu64 "\" version=\"1.1\" xmlns=\"http://www.w3.org/2000/svg\">\n", svg_page_width, total_height);
 
         fprintf(svgfile, "<defs>\n  <style type=\"text/css\">\n    <![CDATA[\n");
@@ -103,6 +115,7 @@ void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end)
         fprintf(svgfile, "      rect.process  { fill:rgb(180,180,180); fill-opacity:0.9; stroke-width:1;   stroke:rgb(  0,  0,  0); } \n");
         fprintf(svgfile, "      rect.process2 { fill:rgb(180,180,180); fill-opacity:0.9; stroke-width:0;   stroke:rgb(  0,  0,  0); } \n");
         fprintf(svgfile, "      rect.sample   { fill:rgb(  0,  0,255); fill-opacity:0.8; stroke-width:0;   stroke:rgb(  0,  0,  0); } \n");
+        fprintf(svgfile, "      rect.sample_hi{ fill:rgb(255,128,  0); fill-opacity:0.8; stroke-width:0;   stroke:rgb(  0,  0,  0); } \n");
         fprintf(svgfile, "      rect.blocked  { fill:rgb(255,  0,  0); fill-opacity:0.5; stroke-width:0;   stroke:rgb(  0,  0,  0); } \n");
         fprintf(svgfile, "      rect.waiting  { fill:rgb(224,214,  0); fill-opacity:0.8; stroke-width:0;   stroke:rgb(  0,  0,  0); } \n");
         fprintf(svgfile, "      rect.WAITING  { fill:rgb(255,214, 48); fill-opacity:0.6; stroke-width:0;   stroke:rgb(  0,  0,  0); } \n");
@@ -128,14 +141,42 @@ void svg_box(int Yslot, u64 start, u64 end, const char *type)
                 time2pixels(start), time2pixels(end)-time2pixels(start), Yslot * SLOT_MULT, SLOT_HEIGHT, type);
 }
 
-void svg_sample(int Yslot, int cpu, u64 start, u64 end)
+static char *time_to_string(u64 duration);
+void svg_blocked(int Yslot, int cpu, u64 start, u64 end, const char *backtrace)
+{
+        if (!svgfile)
+                return;
+
+        fprintf(svgfile, "<g>\n");
+        fprintf(svgfile, "<title>#%d blocked %s</title>\n", cpu,
+                time_to_string(end - start));
+        if (backtrace)
+                fprintf(svgfile, "<desc>Blocked on:\n%s</desc>\n", backtrace);
+        svg_box(Yslot, start, end, "blocked");
+        fprintf(svgfile, "</g>\n");
+}
+
+void svg_running(int Yslot, int cpu, u64 start, u64 end, const char *backtrace)
 {
         double text_size;
+        const char *type;
+
         if (!svgfile)
                 return;
 
-        fprintf(svgfile, "<rect x=\"%4.8f\" width=\"%4.8f\" y=\"%4.1f\" height=\"%4.1f\" class=\"sample\"/>\n",
-                time2pixels(start), time2pixels(end)-time2pixels(start), Yslot * SLOT_MULT, SLOT_HEIGHT);
+        if (svg_highlight && end - start > svg_highlight)
+                type = "sample_hi";
+        else
+                type = "sample";
+        fprintf(svgfile, "<g>\n");
+
+        fprintf(svgfile, "<title>#%d running %s</title>\n",
+                cpu, time_to_string(end - start));
+        if (backtrace)
+                fprintf(svgfile, "<desc>Switched because:\n%s</desc>\n", backtrace);
+        fprintf(svgfile, "<rect x=\"%4.8f\" width=\"%4.8f\" y=\"%4.1f\" height=\"%4.1f\" class=\"%s\"/>\n",
+                time2pixels(start), time2pixels(end)-time2pixels(start), Yslot * SLOT_MULT, SLOT_HEIGHT,
+                type);
 
         text_size = (time2pixels(end)-time2pixels(start));
         if (cpu > 9)
@@ -148,6 +189,7 @@ void svg_sample(int Yslot, int cpu, u64 start, u64 end)
                 fprintf(svgfile, "<text x=\"%1.8f\" y=\"%1.8f\" font-size=\"%1.8fpt\">%i</text>\n",
                         time2pixels(start), Yslot *  SLOT_MULT + SLOT_HEIGHT - 1, text_size,  cpu + 1);
 
+        fprintf(svgfile, "</g>\n");
 }
 
 static char *time_to_string(u64 duration)
@@ -168,7 +210,7 @@ static char *time_to_string(u64 duration)
         return text;
 }
 
-void svg_waiting(int Yslot, u64 start, u64 end)
+void svg_waiting(int Yslot, int cpu, u64 start, u64 end, const char *backtrace)
 {
         char *text;
         const char *style;
@@ -192,6 +234,9 @@ void svg_waiting(int Yslot, u64 start, u64 end)
         font_size = round_text_size(font_size);
 
         fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\">\n", time2pixels(start), Yslot * SLOT_MULT);
+        fprintf(svgfile, "<title>#%d waiting %s</title>\n", cpu, time_to_string(end - start));
+        if (backtrace)
+                fprintf(svgfile, "<desc>Waiting on:\n%s</desc>\n", backtrace);
         fprintf(svgfile, "<rect x=\"0\" width=\"%4.8f\" y=\"0\" height=\"%4.1f\" class=\"%s\"/>\n",
                 time2pixels(end)-time2pixels(start), SLOT_HEIGHT, style);
         if (font_size > MIN_TEXT_SIZE)
@@ -242,28 +287,42 @@ void svg_cpu_box(int cpu, u64 __max_freq, u64 __turbo_freq)
         max_freq = __max_freq;
         turbo_frequency = __turbo_freq;
 
+        fprintf(svgfile, "<g>\n");
+
         fprintf(svgfile, "<rect x=\"%4.8f\" width=\"%4.8f\" y=\"%4.1f\" height=\"%4.1f\" class=\"cpu\"/>\n",
                 time2pixels(first_time),
                 time2pixels(last_time)-time2pixels(first_time),
                 cpu2y(cpu), SLOT_MULT+SLOT_HEIGHT);
 
-        sprintf(cpu_string, "CPU %i", (int)cpu+1);
+        sprintf(cpu_string, "CPU %i", (int)cpu);
         fprintf(svgfile, "<text x=\"%4.8f\" y=\"%4.8f\">%s</text>\n",
                 10+time2pixels(first_time), cpu2y(cpu) + SLOT_HEIGHT/2, cpu_string);
 
         fprintf(svgfile, "<text transform=\"translate(%4.8f,%4.8f)\" font-size=\"1.25pt\">%s</text>\n",
                 10+time2pixels(first_time), cpu2y(cpu) + SLOT_MULT + SLOT_HEIGHT - 4, cpu_model());
+
+        fprintf(svgfile, "</g>\n");
 }
 
-void svg_process(int cpu, u64 start, u64 end, const char *type, const char *name)
+void svg_process(int cpu, u64 start, u64 end, int pid, const char *name, const char *backtrace)
 {
         double width;
+        const char *type;
 
         if (!svgfile)
                 return;
 
+        if (svg_highlight && end - start >= svg_highlight)
+                type = "sample_hi";
+        else if (svg_highlight_name && strstr(name, svg_highlight_name))
+                type = "sample_hi";
+        else
+                type = "sample";
 
         fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\">\n", time2pixels(start), cpu2y(cpu));
+        fprintf(svgfile, "<title>%d %s running %s</title>\n", pid, name, time_to_string(end - start));
+        if (backtrace)
+                fprintf(svgfile, "<desc>Switched because:\n%s</desc>\n", backtrace);
         fprintf(svgfile, "<rect x=\"0\" width=\"%4.8f\" y=\"0\" height=\"%4.1f\" class=\"%s\"/>\n",
                 time2pixels(end)-time2pixels(start), SLOT_MULT+SLOT_HEIGHT, type);
         width = time2pixels(end)-time2pixels(start);
@@ -288,6 +347,8 @@ void svg_cstate(int cpu, u64 start, u64 end, int type)
                 return;
 
 
+        fprintf(svgfile, "<g>\n");
+
         if (type > 6)
                 type = 6;
         sprintf(style, "c%i", type);
@@ -306,6 +367,8 @@ void svg_cstate(int cpu, u64 start, u64 end, int type)
         if (width > MIN_TEXT_SIZE)
                 fprintf(svgfile, "<text x=\"%4.8f\" y=\"%4.8f\" font-size=\"%3.8fpt\">C%i</text>\n",
                         time2pixels(start), cpu2y(cpu)+width, width, type);
+
+        fprintf(svgfile, "</g>\n");
 }
 
 static char *HzToHuman(unsigned long hz)
@@ -339,6 +402,8 @@ void svg_pstate(int cpu, u64 start, u64 end, u64 freq)
         if (!svgfile)
                 return;
 
+        fprintf(svgfile, "<g>\n");
+
         if (max_freq)
                 height = freq * 1.0 / max_freq * (SLOT_HEIGHT + SLOT_MULT);
         height = 1 + cpu2y(cpu) + SLOT_MULT + SLOT_HEIGHT - height;
@@ -347,10 +412,11 @@ void svg_pstate(int cpu, u64 start, u64 end, u64 freq)
         fprintf(svgfile, "<text x=\"%4.8f\" y=\"%4.8f\" font-size=\"0.25pt\">%s</text>\n",
                 time2pixels(start), height+0.9, HzToHuman(freq));
 
+        fprintf(svgfile, "</g>\n");
 }
 
 
-void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc2)
+void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc2, const char *backtrace)
 {
         double height;
 
@@ -358,6 +424,15 @@ void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc
                 return;
 
 
+        fprintf(svgfile, "<g>\n");
+
+        fprintf(svgfile, "<title>%s wakes up %s</title>\n",
+                desc1 ? desc1 : "?",
+                desc2 ? desc2 : "?");
+
+        if (backtrace)
+                fprintf(svgfile, "<desc>%s</desc>\n", backtrace);
+
         if (row1 < row2) {
                 if (row1) {
                         fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n",
@@ -395,9 +470,11 @@ void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc
         if (row1)
                 fprintf(svgfile, "<circle  cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\"  style=\"fill:rgb(32,255,32)\"/>\n",
                         time2pixels(start), height);
+
+        fprintf(svgfile, "</g>\n");
 }
 
-void svg_wakeline(u64 start, int row1, int row2)
+void svg_wakeline(u64 start, int row1, int row2, const char *backtrace)
 {
         double height;
 
@@ -405,6 +482,11 @@ void svg_wakeline(u64 start, int row1, int row2)
                 return;
 
 
+        fprintf(svgfile, "<g>\n");
+
+        if (backtrace)
+                fprintf(svgfile, "<desc>%s</desc>\n", backtrace);
+
         if (row1 < row2)
                 fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n",
                         time2pixels(start), row1 * SLOT_MULT + SLOT_HEIGHT,  time2pixels(start), row2 * SLOT_MULT);
@@ -417,17 +499,28 @@ void svg_wakeline(u64 start, int row1, int row2)
                 height += SLOT_HEIGHT;
         fprintf(svgfile, "<circle  cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\"  style=\"fill:rgb(32,255,32)\"/>\n",
                         time2pixels(start), height);
+
+        fprintf(svgfile, "</g>\n");
 }
 
-void svg_interrupt(u64 start, int row)
+void svg_interrupt(u64 start, int row, const char *backtrace)
 {
         if (!svgfile)
                 return;
 
+        fprintf(svgfile, "<g>\n");
+
+        fprintf(svgfile, "<title>Wakeup from interrupt</title>\n");
+
+        if (backtrace)
+                fprintf(svgfile, "<desc>%s</desc>\n", backtrace);
+
         fprintf(svgfile, "<circle  cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\"  style=\"fill:rgb(255,128,128)\"/>\n",
                         time2pixels(start), row * SLOT_MULT);
         fprintf(svgfile, "<circle  cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\"  style=\"fill:rgb(255,128,128)\"/>\n",
                         time2pixels(start), row * SLOT_MULT + SLOT_HEIGHT);
+
+        fprintf(svgfile, "</g>\n");
 }
 
 void svg_text(int Yslot, u64 start, const char *text)
@@ -455,6 +548,7 @@ void svg_legenda(void)
         if (!svgfile)
                 return;
 
+        fprintf(svgfile, "<g>\n");
         svg_legenda_box(0,      "Running", "sample");
         svg_legenda_box(100,    "Idle","c1");
         svg_legenda_box(200,    "Deeper Idle", "c3");
@@ -462,6 +556,7 @@ void svg_legenda(void)
         svg_legenda_box(550,    "Sleeping", "process2");
         svg_legenda_box(650,    "Waiting for cpu", "waiting");
         svg_legenda_box(800,    "Blocked on IO", "blocked");
+        fprintf(svgfile, "</g>\n");
 }
 
 void svg_time_grid(void)
@@ -499,3 +594,123 @@ void svg_close(void)
                 svgfile = NULL;
         }
 }
+
+#define cpumask_bits(maskp) ((maskp)->bits)
+typedef struct { DECLARE_BITMAP(bits, MAX_NR_CPUS); } cpumask_t;
+
+struct topology {
+        cpumask_t *sib_core;
+        int sib_core_nr;
+        cpumask_t *sib_thr;
+        int sib_thr_nr;
+};
+
+static void scan_thread_topology(int *map, struct topology *t, int cpu, int *pos)
+{
+        int i;
+        int thr;
+
+        for (i = 0; i < t->sib_thr_nr; i++) {
+                if (!test_bit(cpu, cpumask_bits(&t->sib_thr[i])))
+                        continue;
+
+                for_each_set_bit(thr,
+                                 cpumask_bits(&t->sib_thr[i]),
+                                 MAX_NR_CPUS)
+                        if (map[thr] == -1)
+                                map[thr] = (*pos)++;
+        }
+}
+
+static void scan_core_topology(int *map, struct topology *t)
+{
+        int pos = 0;
+        int i;
+        int cpu;
+
+        for (i = 0; i < t->sib_core_nr; i++)
+                for_each_set_bit(cpu,
+                                 cpumask_bits(&t->sib_core[i]),
+                                 MAX_NR_CPUS)
+                        scan_thread_topology(map, t, cpu, &pos);
+}
+
+static int str_to_bitmap(char *s, cpumask_t *b)
+{
+        int i;
+        int ret = 0;
+        struct cpu_map *m;
+        int c;
+
+        m = cpu_map__new(s);
+        if (!m)
+                return -1;
+
+        for (i = 0; i < m->nr; i++) {
+                c = m->map[i];
+                if (c >= MAX_NR_CPUS) {
+                        ret = -1;
+                        break;
+                }
+
+                set_bit(c, cpumask_bits(b));
+        }
+
+        cpu_map__delete(m);
+
+        return ret;
+}
+
+int svg_build_topology_map(char *sib_core, int sib_core_nr,
+                           char *sib_thr, int sib_thr_nr)
+{
+        int i;
+        struct topology t;
+
+        t.sib_core_nr = sib_core_nr;
+        t.sib_thr_nr = sib_thr_nr;
+        t.sib_core = calloc(sib_core_nr, sizeof(cpumask_t));
+        t.sib_thr = calloc(sib_thr_nr, sizeof(cpumask_t));
+
+        if (!t.sib_core || !t.sib_thr) {
+                fprintf(stderr, "topology: no memory\n");
+                goto exit;
+        }
+
+        for (i = 0; i < sib_core_nr; i++) {
+                if (str_to_bitmap(sib_core, &t.sib_core[i])) {
+                        fprintf(stderr, "topology: can't parse siblings map\n");
+                        goto exit;
+                }
+
+                sib_core += strlen(sib_core) + 1;
+        }
+
+        for (i = 0; i < sib_thr_nr; i++) {
+                if (str_to_bitmap(sib_thr, &t.sib_thr[i])) {
+                        fprintf(stderr, "topology: can't parse siblings map\n");
+                        goto exit;
+                }
+
+                sib_thr += strlen(sib_thr) + 1;
+        }
+
+        topology_map = malloc(sizeof(int) * MAX_NR_CPUS);
+        if (!topology_map) {
+                fprintf(stderr, "topology: no memory\n");
+                goto exit;
+        }
+
+        for (i = 0; i < MAX_NR_CPUS; i++)
+                topology_map[i] = -1;
+
+        scan_core_topology(topology_map, &t);
+
+        return 0;
+
+exit:
+        zfree(&t.sib_core);
+        zfree(&t.sib_thr);
+
+        return -1;
+}
diff --git a/tools/perf/util/svghelper.h b/tools/perf/util/svghelper.h
index e0781989cc31..f7b4d6e699ea 100644
--- a/tools/perf/util/svghelper.h
+++ b/tools/perf/util/svghelper.h
@@ -5,24 +5,29 @@
 
 extern void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end);
 extern void svg_box(int Yslot, u64 start, u64 end, const char *type);
-extern void svg_sample(int Yslot, int cpu, u64 start, u64 end);
-extern void svg_waiting(int Yslot, u64 start, u64 end);
+extern void svg_blocked(int Yslot, int cpu, u64 start, u64 end, const char *backtrace);
+extern void svg_running(int Yslot, int cpu, u64 start, u64 end, const char *backtrace);
+extern void svg_waiting(int Yslot, int cpu, u64 start, u64 end, const char *backtrace);
 extern void svg_cpu_box(int cpu, u64 max_frequency, u64 turbo_frequency);
 
 
-extern void svg_process(int cpu, u64 start, u64 end, const char *type, const char *name);
+extern void svg_process(int cpu, u64 start, u64 end, int pid, const char *name, const char *backtrace);
 extern void svg_cstate(int cpu, u64 start, u64 end, int type);
 extern void svg_pstate(int cpu, u64 start, u64 end, u64 freq);
 
 
 extern void svg_time_grid(void);
 extern void svg_legenda(void);
-extern void svg_wakeline(u64 start, int row1, int row2);
-extern void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc2);
-extern void svg_interrupt(u64 start, int row);
+extern void svg_wakeline(u64 start, int row1, int row2, const char *backtrace);
+extern void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc2, const char *backtrace);
+extern void svg_interrupt(u64 start, int row, const char *backtrace);
 extern void svg_text(int Yslot, u64 start, const char *text);
 extern void svg_close(void);
+extern int svg_build_topology_map(char *sib_core, int sib_core_nr,
+                                  char *sib_thr, int sib_thr_nr);
 
 extern int svg_page_width;
+extern u64 svg_highlight;
+extern const char *svg_highlight_name;
 
 #endif /* __PERF_SVGHELPER_H */
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index eed0b96302af..759456728703 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -6,6 +6,7 @@
 #include <inttypes.h>
 
 #include "symbol.h"
+#include <symbol/kallsyms.h>
 #include "debug.h"
 
 #ifndef HAVE_ELF_GETPHDRNUM_SUPPORT
@@ -135,9 +136,8 @@ static size_t elf_addr_to_index(Elf *elf, GElf_Addr addr)
         return -1;
 }
 
-static Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
-                                    GElf_Shdr *shp, const char *name,
-                                    size_t *idx)
+Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
+                             GElf_Shdr *shp, const char *name, size_t *idx)
 {
         Elf_Scn *sec = NULL;
         size_t cnt = 1;
@@ -553,7 +553,7 @@ bool symsrc__has_symtab(struct symsrc *ss)
 
 void symsrc__destroy(struct symsrc *ss)
 {
-        free(ss->name);
+        zfree(&ss->name);
         elf_end(ss->elf);
         close(ss->fd);
 }
diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c
index 2d2dd0532b5a..bd15f490d04f 100644
--- a/tools/perf/util/symbol-minimal.c
+++ b/tools/perf/util/symbol-minimal.c
@@ -1,4 +1,5 @@
 #include "symbol.h"
+#include "util.h"
 
 #include <stdio.h>
 #include <fcntl.h>
@@ -253,6 +254,7 @@ int symsrc__init(struct symsrc *ss, struct dso *dso __maybe_unused,
         if (!ss->name)
                 goto out_close;
 
+        ss->fd = fd;
         ss->type = type;
 
         return 0;
@@ -274,7 +276,7 @@ bool symsrc__has_symtab(struct symsrc *ss __maybe_unused)
 
 void symsrc__destroy(struct symsrc *ss)
 {
-        free(ss->name);
+        zfree(&ss->name);
         close(ss->fd);
 }
 
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index c0c36965fff0..39ce9adbaaf0 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -18,12 +18,9 @@
 
 #include <elf.h>
 #include <limits.h>
+#include <symbol/kallsyms.h>
 #include <sys/utsname.h>
 
-#ifndef KSYM_NAME_LEN
-#define KSYM_NAME_LEN 256
-#endif
-
 static int dso__load_kernel_sym(struct dso *dso, struct map *map,
                                 symbol_filter_t filter);
 static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map,
@@ -446,62 +443,6 @@ size_t dso__fprintf_symbols_by_name(struct dso *dso,
         return ret;
 }
 
-int kallsyms__parse(const char *filename, void *arg,
-                    int (*process_symbol)(void *arg, const char *name,
-                                          char type, u64 start))
-{
-        char *line = NULL;
-        size_t n;
-        int err = -1;
-        FILE *file = fopen(filename, "r");
-
-        if (file == NULL)
-                goto out_failure;
-
-        err = 0;
-
-        while (!feof(file)) {
-                u64 start;
-                int line_len, len;
-                char symbol_type;
-                char *symbol_name;
-
-                line_len = getline(&line, &n, file);
-                if (line_len < 0 || !line)
-                        break;
-
-                line[--line_len] = '\0'; /* \n */
-
-                len = hex2u64(line, &start);
-
-                len++;
-                if (len + 2 >= line_len)
-                        continue;
-
-                symbol_type = line[len];
-                len += 2;
-                symbol_name = line + len;
-                len = line_len - len;
-
-                if (len >= KSYM_NAME_LEN) {
-                        err = -1;
-                        break;
-                }
-
-                err = process_symbol(arg, symbol_name,
-                                     symbol_type, start);
-                if (err)
-                        break;
-        }
-
-        free(line);
-        fclose(file);
-        return err;
-
-out_failure:
-        return -1;
-}
-
 int modules__parse(const char *filename, void *arg,
                    int (*process_module)(void *arg, const char *name,
                                          u64 start))
@@ -565,12 +506,34 @@ struct process_kallsyms_args {
         struct dso *dso;
 };
 
-static u8 kallsyms2elf_type(char type)
+bool symbol__is_idle(struct symbol *sym)
 {
-        if (type == 'W')
-                return STB_WEAK;
+        const char * const idle_symbols[] = {
+                "cpu_idle",
+                "intel_idle",
+                "default_idle",
+                "native_safe_halt",
+                "enter_idle",
+                "exit_idle",
+                "mwait_idle",
+                "mwait_idle_with_hints",
+                "poll_idle",
+                "ppc64_runlatch_off",
+                "pseries_dedicated_idle_sleep",
+                NULL
+        };
+
+        int i;
+
+        if (!sym)
+                return false;
+
+        for (i = 0; idle_symbols[i]; i++) {
+                if (!strcmp(idle_symbols[i], sym->name))
+                        return true;
+        }
 
-        return isupper(type) ? STB_GLOBAL : STB_LOCAL;
+        return false;
 }
 
 static int map__process_kallsym_symbol(void *arg, const char *name,
@@ -833,7 +796,7 @@ static void delete_modules(struct rb_root *modules)
                 mi = rb_entry(next, struct module_info, rb_node);
                 next = rb_next(&mi->rb_node);
                 rb_erase(&mi->rb_node, modules);
-                free(mi->name);
+                zfree(&mi->name);
                 free(mi);
         }
 }
@@ -1126,10 +1089,10 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
          * dso__data_read_addr().
          */
         if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
-                dso->data_type = DSO_BINARY_TYPE__GUEST_KCORE;
+                dso->binary_type = DSO_BINARY_TYPE__GUEST_KCORE;
         else
-                dso->data_type = DSO_BINARY_TYPE__KCORE;
-        dso__set_long_name(dso, strdup(kcore_filename));
+                dso->binary_type = DSO_BINARY_TYPE__KCORE;
+        dso__set_long_name(dso, strdup(kcore_filename), true);
 
         close(fd);
 
@@ -1295,8 +1258,8 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 
                 enum dso_binary_type symtab_type = binary_type_symtab[i];
 
-                if (dso__binary_type_file(dso, symtab_type,
-                                          root_dir, name, PATH_MAX))
+                if (dso__read_binary_type_filename(dso, symtab_type,
+                                                   root_dir, name, PATH_MAX))
                         continue;
 
                 /* Name is now the name of the next image to try */
@@ -1306,6 +1269,8 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
                 if (!syms_ss && symsrc__has_symtab(ss)) {
                         syms_ss = ss;
                         next_slot = true;
+                        if (!dso->symsrc_filename)
+                                dso->symsrc_filename = strdup(name);
                 }
 
                 if (!runtime_ss && symsrc__possibly_runtime(ss)) {
@@ -1376,7 +1341,8 @@ struct map *map_groups__find_by_name(struct map_groups *mg,
 }
 
 int dso__load_vmlinux(struct dso *dso, struct map *map,
-                      const char *vmlinux, symbol_filter_t filter)
+                      const char *vmlinux, bool vmlinux_allocated,
+                      symbol_filter_t filter)
 {
         int err = -1;
         struct symsrc ss;
@@ -1402,10 +1368,10 @@ int dso__load_vmlinux(struct dso *dso, struct map *map,
 
         if (err > 0) {
                 if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
-                        dso->data_type = DSO_BINARY_TYPE__GUEST_VMLINUX;
+                        dso->binary_type = DSO_BINARY_TYPE__GUEST_VMLINUX;
                 else
-                        dso->data_type = DSO_BINARY_TYPE__VMLINUX;
-                dso__set_long_name(dso, (char *)vmlinux);
+                        dso->binary_type = DSO_BINARY_TYPE__VMLINUX;
+                dso__set_long_name(dso, vmlinux, vmlinux_allocated);
                 dso__set_loaded(dso, map->type);
                 pr_debug("Using %s for symbols\n", symfs_vmlinux);
         }
@@ -1424,21 +1390,16 @@ int dso__load_vmlinux_path(struct dso *dso, struct map *map,
 
         filename = dso__build_id_filename(dso, NULL, 0);
         if (filename != NULL) {
-                err = dso__load_vmlinux(dso, map, filename, filter);
-                if (err > 0) {
-                        dso->lname_alloc = 1;
+                err = dso__load_vmlinux(dso, map, filename, true, filter);
+                if (err > 0)
                         goto out;
-                }
                 free(filename);
         }
 
         for (i = 0; i < vmlinux_path__nr_entries; ++i) {
-                err = dso__load_vmlinux(dso, map, vmlinux_path[i], filter);
-                if (err > 0) {
-                        dso__set_long_name(dso, strdup(vmlinux_path[i]));
-                        dso->lname_alloc = 1;
+                err = dso__load_vmlinux(dso, map, vmlinux_path[i], false, filter);
+                if (err > 0)
                         break;
-                }
         }
 out:
         return err;
@@ -1496,14 +1457,15 @@ static char *dso__find_kallsyms(struct dso *dso, struct map *map)
 
         build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id);
 
+        scnprintf(path, sizeof(path), "%s/[kernel.kcore]/%s", buildid_dir,
+                  sbuild_id);
+
         /* Use /proc/kallsyms if possible */
         if (is_host) {
                 DIR *d;
                 int fd;
 
                 /* If no cached kcore go with /proc/kallsyms */
-                scnprintf(path, sizeof(path), "%s/[kernel.kcore]/%s",
-                          buildid_dir, sbuild_id);
                 d = opendir(path);
                 if (!d)
                         goto proc_kallsyms;
@@ -1528,6 +1490,10 @@ static char *dso__find_kallsyms(struct dso *dso, struct map *map)
                 goto proc_kallsyms;
         }
 
+        /* Find kallsyms in build-id cache with kcore */
+        if (!find_matching_kcore(map, path, sizeof(path)))
+                return strdup(path);
+
         scnprintf(path, sizeof(path), "%s/[kernel.kallsyms]/%s",
                   buildid_dir, sbuild_id);
 
@@ -1570,15 +1536,8 @@ static int dso__load_kernel_sym(struct dso *dso, struct map *map,
         }
 
         if (!symbol_conf.ignore_vmlinux && symbol_conf.vmlinux_name != NULL) {
-                err = dso__load_vmlinux(dso, map,
-                                        symbol_conf.vmlinux_name, filter);
-                if (err > 0) {
-                        dso__set_long_name(dso,
-                                           strdup(symbol_conf.vmlinux_name));
-                        dso->lname_alloc = 1;
-                        return err;
-                }
-                return err;
+                return dso__load_vmlinux(dso, map, symbol_conf.vmlinux_name,
+                                         false, filter);
         }
 
         if (!symbol_conf.ignore_vmlinux && vmlinux_path != NULL) {
@@ -1604,7 +1563,7 @@ do_kallsyms:
         free(kallsyms_allocated_filename);
 
         if (err > 0 && !dso__is_kcore(dso)) {
-                dso__set_long_name(dso, strdup("[kernel.kallsyms]"));
+                dso__set_long_name(dso, "[kernel.kallsyms]", false);
                 map__fixup_start(map);
                 map__fixup_end(map);
         }
@@ -1634,7 +1593,8 @@ static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map,
                  */
                 if (symbol_conf.default_guest_vmlinux_name != NULL) {
                         err = dso__load_vmlinux(dso, map,
-                                symbol_conf.default_guest_vmlinux_name, filter);
+                                                symbol_conf.default_guest_vmlinux_name,
+                                                false, filter);
                         return err;
                 }
 
@@ -1651,7 +1611,7 @@ static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map,
                 pr_debug("Using %s for symbols\n", kallsyms_filename);
         if (err > 0 && !dso__is_kcore(dso)) {
                 machine__mmap_name(machine, path, sizeof(path));
-                dso__set_long_name(dso, strdup(path));
+                dso__set_long_name(dso, strdup(path), true);
                 map__fixup_start(map);
                 map__fixup_end(map);
         }
@@ -1661,13 +1621,10 @@ static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map,
 
 static void vmlinux_path__exit(void)
 {
-        while (--vmlinux_path__nr_entries >= 0) {
-                free(vmlinux_path[vmlinux_path__nr_entries]);
-                vmlinux_path[vmlinux_path__nr_entries] = NULL;
-        }
+        while (--vmlinux_path__nr_entries >= 0)
+                zfree(&vmlinux_path[vmlinux_path__nr_entries]);
 
-        free(vmlinux_path);
-        vmlinux_path = NULL;
+        zfree(&vmlinux_path);
 }
 
 static int vmlinux_path__init(void)
@@ -1719,7 +1676,7 @@ out_fail:
         return -1;
 }
 
-static int setup_list(struct strlist **list, const char *list_str,
+int setup_list(struct strlist **list, const char *list_str,
                       const char *list_name)
 {
         if (list_str == NULL)
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 07de8fea2f48..fffe2888a1c7 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -52,6 +52,11 @@ static inline char *bfd_demangle(void __maybe_unused *v,
 # define PERF_ELF_C_READ_MMAP ELF_C_READ
 #endif
 
+#ifdef HAVE_LIBELF_SUPPORT
+extern Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
+                                GElf_Shdr *shp, const char *name, size_t *idx);
+#endif
+
 #ifndef DMGL_PARAMS
 #define DMGL_PARAMS      (1 << 0)       /* Include function args */
 #define DMGL_ANSI        (1 << 1)       /* Include const, volatile, etc */
@@ -164,6 +169,7 @@ struct mem_info {
 };
 
 struct addr_location {
+        struct machine *machine;
         struct thread *thread;
         struct map    *map;
         struct symbol *sym;
@@ -206,7 +212,8 @@ bool symsrc__possibly_runtime(struct symsrc *ss);
 
 int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter);
 int dso__load_vmlinux(struct dso *dso, struct map *map,
-                      const char *vmlinux, symbol_filter_t filter);
+                      const char *vmlinux, bool vmlinux_allocated,
+                      symbol_filter_t filter);
 int dso__load_vmlinux_path(struct dso *dso, struct map *map,
                            symbol_filter_t filter);
 int dso__load_kallsyms(struct dso *dso, const char *filename, struct map *map,
@@ -220,9 +227,6 @@ struct symbol *dso__first_symbol(struct dso *dso, enum map_type type);
 
 int filename__read_build_id(const char *filename, void *bf, size_t size);
 int sysfs__read_build_id(const char *filename, void *bf, size_t size);
-int kallsyms__parse(const char *filename, void *arg,
-                    int (*process_symbol)(void *arg, const char *name,
-                                          char type, u64 start));
 int modules__parse(const char *filename, void *arg,
                    int (*process_module)(void *arg, const char *name,
                                          u64 start));
@@ -240,6 +244,7 @@ size_t symbol__fprintf(struct symbol *sym, FILE *fp);
 bool symbol_type__is_a(char symbol_type, enum map_type map_type);
 bool symbol__restricted_filename(const char *filename,
                                  const char *restricted_filename);
+bool symbol__is_idle(struct symbol *sym);
 
 int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
                   struct symsrc *runtime_ss, symbol_filter_t filter,
@@ -273,4 +278,7 @@ void kcore_extract__delete(struct kcore_extract *kce);
 int kcore_copy(const char *from_dir, const char *to_dir);
 int compare_proc_modules(const char *from, const char *to);
 
+int setup_list(struct strlist **list, const char *list_str,
+               const char *list_name);
+
 #endif /* __PERF_SYMBOL */
diff --git a/tools/perf/util/target.c b/tools/perf/util/target.c
index 3c778a07b7cc..e74c5963dc7a 100644
--- a/tools/perf/util/target.c
+++ b/tools/perf/util/target.c
@@ -55,6 +55,13 @@ enum target_errno target__validate(struct target *target)
                         ret = TARGET_ERRNO__UID_OVERRIDE_SYSTEM;
         }
 
+        /* THREAD and SYSTEM/CPU are mutually exclusive */
+        if (target->per_thread && (target->system_wide || target->cpu_list)) {
+                target->per_thread = false;
+                if (ret == TARGET_ERRNO__SUCCESS)
+                        ret = TARGET_ERRNO__SYSTEM_OVERRIDE_THREAD;
+        }
+
         return ret;
 }
 
@@ -100,6 +107,7 @@ static const char *target__error_str[] = {
         "UID switch overriding CPU",
         "PID/TID switch overriding SYSTEM",
         "UID switch overriding SYSTEM",
+        "SYSTEM/CPU switch overriding PER-THREAD",
         "Invalid User: %s",
         "Problems obtaining information for user %s",
 };
@@ -131,7 +139,8 @@ int target__strerror(struct target *target, int errnum,
         msg = target__error_str[idx];
 
         switch (errnum) {
-        case TARGET_ERRNO__PID_OVERRIDE_CPU ... TARGET_ERRNO__UID_OVERRIDE_SYSTEM:
+        case TARGET_ERRNO__PID_OVERRIDE_CPU ...
+             TARGET_ERRNO__SYSTEM_OVERRIDE_THREAD:
                 snprintf(buf, buflen, "%s", msg);
                 break;
 
diff --git a/tools/perf/util/target.h b/tools/perf/util/target.h
index 2d0c50690892..7381b1ca4041 100644
--- a/tools/perf/util/target.h
+++ b/tools/perf/util/target.h
@@ -12,7 +12,8 @@ struct target {
         uid_t        uid;
         bool         system_wide;
         bool         uses_mmap;
-        bool         force_per_cpu;
+        bool         default_per_cpu;
+        bool         per_thread;
 };
 
 enum target_errno {
@@ -33,6 +34,7 @@ enum target_errno {
         TARGET_ERRNO__UID_OVERRIDE_CPU,
         TARGET_ERRNO__PID_OVERRIDE_SYSTEM,
         TARGET_ERRNO__UID_OVERRIDE_SYSTEM,
+        TARGET_ERRNO__SYSTEM_OVERRIDE_THREAD,
 
         /* for target__parse_uid() */
         TARGET_ERRNO__INVALID_UID,
@@ -61,4 +63,17 @@ static inline bool target__none(struct target *target)
         return !target__has_task(target) && !target__has_cpu(target);
 }
 
+static inline bool target__uses_dummy_map(struct target *target)
+{
+        bool use_dummy = false;
+
+        if (target->default_per_cpu)
+                use_dummy = target->per_thread ? true : false;
+        else if (target__has_task(target) ||
+                 (!target__has_cpu(target) && !target->uses_mmap))
+                use_dummy = true;
+
+        return use_dummy;
+}
+
 #endif /* _PERF_TARGET_H */
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index cd8e2f592719..0358882c8910 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -66,18 +66,20 @@ struct comm *thread__comm(const struct thread *thread)
 int thread__set_comm(struct thread *thread, const char *str, u64 timestamp)
 {
         struct comm *new, *curr = thread__comm(thread);
+        int err;
 
         /* Override latest entry if it had no specific time coverage */
         if (!curr->start) {
-                comm__override(curr, str, timestamp);
-                return 0;
+                err = comm__override(curr, str, timestamp);
+                if (err)
+                        return err;
+        } else {
+                new = comm__new(str, timestamp);
+                if (!new)
+                        return -ENOMEM;
+                list_add(&new->list, &thread->comm_list);
         }
 
-        new = comm__new(str, timestamp);
-        if (!new)
-                return -ENOMEM;
-
-        list_add(&new->list, &thread->comm_list);
         thread->comm_set = true;
 
         return 0;
@@ -127,7 +129,7 @@ int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp)
                 if (!comm)
                         return -ENOMEM;
                 err = thread__set_comm(thread, comm, timestamp);
-                if (!err)
+                if (err)
                         return err;
                 thread->comm_set = true;
         }
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 897c1b2a750a..5b856bf942e1 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -6,6 +6,7 @@
 #include <unistd.h>
 #include <sys/types.h>
 #include "symbol.h"
+#include <strlist.h>
 
 struct thread {
         union {
@@ -66,4 +67,15 @@ static inline void thread__set_priv(struct thread *thread, void *p)
 {
         thread->priv = p;
 }
+
+static inline bool thread__is_filtered(struct thread *thread)
+{
+        if (symbol_conf.comm_list &&
+            !strlist__has_entry(symbol_conf.comm_list, thread__comm_str(thread))) {
+                return true;
+        }
+
+        return false;
+}
+
 #endif  /* __PERF_THREAD_H */
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index 9b5f856cc280..5d3215912105 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -9,6 +9,7 @@
 #include "strlist.h"
 #include <string.h>
 #include "thread_map.h"
+#include "util.h"
 
 /* Skip "." and ".." directories */
 static int filter(const struct dirent *dir)
@@ -40,7 +41,7 @@ struct thread_map *thread_map__new_by_pid(pid_t pid)
         }
 
         for (i=0; i<items; i++)
-                free(namelist[i]);
+                zfree(&namelist[i]);
         free(namelist);
 
         return threads;
@@ -117,7 +118,7 @@ struct thread_map *thread_map__new_by_uid(uid_t uid)
                         threads->map[threads->nr + i] = atoi(namelist[i]->d_name);
 
                 for (i = 0; i < items; i++)
-                        free(namelist[i]);
+                        zfree(&namelist[i]);
                 free(namelist);
 
                 threads->nr += items;
@@ -134,12 +135,11 @@ out_free_threads:
 
 out_free_namelist:
         for (i = 0; i < items; i++)
-                free(namelist[i]);
+                zfree(&namelist[i]);
         free(namelist);
 
 out_free_closedir:
-        free(threads);
-        threads = NULL;
+        zfree(&threads);
         goto out_closedir;
 }
 
@@ -194,7 +194,7 @@ static struct thread_map *thread_map__new_by_pid_str(const char *pid_str)
 
                 for (i = 0; i < items; i++) {
                         threads->map[j++] = atoi(namelist[i]->d_name);
-                        free(namelist[i]);
+                        zfree(&namelist[i]);
                 }
                 threads->nr = total_tasks;
                 free(namelist);
@@ -206,12 +206,11 @@ out:
 
 out_free_namelist:
         for (i = 0; i < items; i++)
-                free(namelist[i]);
+                zfree(&namelist[i]);
         free(namelist);
 
 out_free_threads:
-        free(threads);
-        threads = NULL;
+        zfree(&threads);
         goto out;
 }
 
@@ -262,8 +261,7 @@ out:
         return threads;
 
 out_free_threads:
-        free(threads);
-        threads = NULL;
+        zfree(&threads);
         goto out;
 }
 
diff --git a/tools/perf/util/top.c b/tools/perf/util/top.c
index ce793c7dd23c..8e517def925b 100644
--- a/tools/perf/util/top.c
+++ b/tools/perf/util/top.c
@@ -26,7 +26,7 @@ size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size)
         float samples_per_sec;
         float ksamples_per_sec;
         float esamples_percent;
-        struct perf_record_opts *opts = &top->record_opts;
+        struct record_opts *opts = &top->record_opts;
         struct target *target = &opts->target;
         size_t ret = 0;
 
diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h
index 88cfeaff600b..dab14d0ad3d0 100644
--- a/tools/perf/util/top.h
+++ b/tools/perf/util/top.h
@@ -14,7 +14,7 @@ struct perf_session;
 struct perf_top {
         struct perf_tool   tool;
         struct perf_evlist *evlist;
-        struct perf_record_opts record_opts;
+        struct record_opts record_opts;
         /*
          * Symbols will be added here in perf_event__process_sample and will
          * get out after decayed.
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index f3c9e551bd35..7e6fcfe8b438 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -38,7 +38,7 @@
 
 #include "../perf.h"
 #include "trace-event.h"
-#include <lk/debugfs.h>
+#include <api/fs/debugfs.h>
 #include "evsel.h"
 
 #define VERSION "0.5"
@@ -397,8 +397,8 @@ put_tracepoints_path(struct tracepoint_path *tps)
                 struct tracepoint_path *t = tps;
 
                 tps = tps->next;
-                free(t->name);
-                free(t->system);
+                zfree(&t->name);
+                zfree(&t->system);
                 free(t);
         }
 }
@@ -562,10 +562,8 @@ out:
                 output_fd = fd;
         }
 
-        if (err) {
-                free(tdata);
-                tdata = NULL;
-        }
+        if (err)
+                zfree(&tdata);
 
         put_tracepoints_path(tps);
         return tdata;
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index 6681f71f2f95..e0d6d07f6848 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -28,19 +28,6 @@
 #include "util.h"
 #include "trace-event.h"
 
-struct pevent *read_trace_init(int file_bigendian, int host_bigendian)
-{
-        struct pevent *pevent = pevent_alloc();
-
-        if (pevent != NULL) {
-                pevent_set_flag(pevent, PEVENT_NSEC_OUTPUT);
-                pevent_set_file_bigendian(pevent, file_bigendian);
-                pevent_set_host_bigendian(pevent, host_bigendian);
-        }
-
-        return pevent;
-}
-
 static int get_common_field(struct scripting_context *context,
                             int *offset, int *size, const char *type)
 {
diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index f2112270c663..e113e180c48f 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -343,7 +343,7 @@ static int read_event_files(struct pevent *pevent)
         return 0;
 }
 
-ssize_t trace_report(int fd, struct pevent **ppevent, bool __repipe)
+ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe)
 {
         char buf[BUFSIZ];
         char test[] = { 23, 8, 68 };
@@ -356,11 +356,9 @@ ssize_t trace_report(int fd, struct pevent **ppevent, bool __repipe)
         int host_bigendian;
         int file_long_size;
         int file_page_size;
-        struct pevent *pevent;
+        struct pevent *pevent = NULL;
         int err;
 
-        *ppevent = NULL;
-
         repipe = __repipe;
         input_fd = fd;
 
@@ -390,12 +388,17 @@ ssize_t trace_report(int fd, struct pevent **ppevent, bool __repipe)
         file_bigendian = buf[0];
         host_bigendian = bigendian();
 
-        pevent = read_trace_init(file_bigendian, host_bigendian);
-        if (pevent == NULL) {
-                pr_debug("read_trace_init failed");
+        if (trace_event__init(tevent)) {
+                pr_debug("trace_event__init failed");
                 goto out;
         }
 
+        pevent = tevent->pevent;
+
+        pevent_set_flag(pevent, PEVENT_NSEC_OUTPUT);
+        pevent_set_file_bigendian(pevent, file_bigendian);
+        pevent_set_host_bigendian(pevent, host_bigendian);
+
         if (do_read(buf, 1) < 0)
                 goto out;
         file_long_size = buf[0];
@@ -432,11 +435,10 @@ ssize_t trace_report(int fd, struct pevent **ppevent, bool __repipe)
                 pevent_print_printk(pevent);
         }
 
-        *ppevent = pevent;
         pevent = NULL;
 
 out:
         if (pevent)
-                pevent_free(pevent);
+                trace_event__cleanup(tevent);
         return size;
 }
diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c
index 95199e4eea97..57aaccc1692e 100644
--- a/tools/perf/util/trace-event-scripting.c
+++ b/tools/perf/util/trace-event-scripting.c
@@ -38,9 +38,8 @@ static int stop_script_unsupported(void)
 static void process_event_unsupported(union perf_event *event __maybe_unused,
                                       struct perf_sample *sample __maybe_unused,
                                       struct perf_evsel *evsel __maybe_unused,
-                                      struct machine *machine __maybe_unused,
                                       struct thread *thread __maybe_unused,
-                                          struct addr_location *al __maybe_unused)
+                                      struct addr_location *al __maybe_unused)
 {
 }
 
diff --git a/tools/perf/util/trace-event.c b/tools/perf/util/trace-event.c
new file mode 100644
index 000000000000..6322d37164c5
--- /dev/null
+++ b/tools/perf/util/trace-event.c
@@ -0,0 +1,82 @@
+
+#include <stdio.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <errno.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <linux/kernel.h>
+#include <traceevent/event-parse.h>
+#include "trace-event.h"
+#include "util.h"
+
+/*
+ * global trace_event object used by trace_event__tp_format
+ *
+ * TODO There's no cleanup call for this. Add some sort of
+ * __exit function support and call trace_event__cleanup
+ * there.
+ */
+static struct trace_event tevent;
+
+int trace_event__init(struct trace_event *t)
+{
+        struct pevent *pevent = pevent_alloc();
+
+        if (pevent) {
+                t->plugin_list = traceevent_load_plugins(pevent);
+                t->pevent  = pevent;
+        }
+
+        return pevent ? 0 : -1;
+}
+
+void trace_event__cleanup(struct trace_event *t)
+{
+        traceevent_unload_plugins(t->plugin_list, t->pevent);
+        pevent_free(t->pevent);
+}
+
+static struct event_format*
+tp_format(const char *sys, const char *name)
+{
+        struct pevent *pevent = tevent.pevent;
+        struct event_format *event = NULL;
+        char path[PATH_MAX];
+        size_t size;
+        char *data;
+
+        scnprintf(path, PATH_MAX, "%s/%s/%s/format",
+                  tracing_events_path, sys, name);
+
+        if (filename__read_str(path, &data, &size))
+                return NULL;
+
+        pevent_parse_format(pevent, &event, data, size, sys);
+
+        free(data);
+        return event;
+}
+
+struct event_format*
+trace_event__tp_format(const char *sys, const char *name)
+{
+        static bool initialized;
+
+        if (!initialized) {
+                int be = traceevent_host_bigendian();
+                struct pevent *pevent;
+
+                if (trace_event__init(&tevent))
+                        return NULL;
+
+                pevent = tevent.pevent;
+                pevent_set_flag(pevent, PEVENT_NSEC_OUTPUT);
+                pevent_set_file_bigendian(pevent, be);
+                pevent_set_host_bigendian(pevent, be);
+                initialized = true;
+        }
+
+        return tp_format(sys, name);
+}
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index 04df63114109..7b6d68688327 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -3,17 +3,26 @@
 
 #include <traceevent/event-parse.h>
 #include "parse-events.h"
-#include "session.h"
 
 struct machine;
 struct perf_sample;
 union perf_event;
 struct perf_tool;
 struct thread;
+struct plugin_list;
+
+struct trace_event {
+        struct pevent           *pevent;
+        struct plugin_list      *plugin_list;
+};
+
+int trace_event__init(struct trace_event *t);
+void trace_event__cleanup(struct trace_event *t);
+struct event_format*
+trace_event__tp_format(const char *sys, const char *name);
 
 int bigendian(void);
 
-struct pevent *read_trace_init(int file_bigendian, int host_bigendian);
 void event_format__print(struct event_format *event,
                          int cpu, void *data, int size);
 
@@ -27,7 +36,7 @@ raw_field_value(struct event_format *event, const char *name, void *data);
 void parse_proc_kallsyms(struct pevent *pevent, char *file, unsigned int size);
 void parse_ftrace_printk(struct pevent *pevent, char *file, unsigned int size);
 
-ssize_t trace_report(int fd, struct pevent **pevent, bool repipe);
+ssize_t trace_report(int fd, struct trace_event *tevent, bool repipe);
 
 struct event_format *trace_find_next_event(struct pevent *pevent,
                                            struct event_format *event);
@@ -59,7 +68,6 @@ struct scripting_ops {
         void (*process_event) (union perf_event *event,
                                struct perf_sample *sample,
                                struct perf_evsel *evsel,
-                               struct machine *machine,
                                struct thread *thread,
                                    struct addr_location *al);
         int (*generate_script) (struct pevent *pevent, const char *outfile);
diff --git a/tools/perf/util/unwind.c b/tools/perf/util/unwind.c
index 0efd5393de85..742f23bf35ff 100644
--- a/tools/perf/util/unwind.c
+++ b/tools/perf/util/unwind.c
@@ -28,6 +28,7 @@
 #include "session.h"
 #include "perf_regs.h"
 #include "unwind.h"
+#include "symbol.h"
 #include "util.h"
 
 extern int
@@ -158,23 +159,6 @@ static int __dw_read_encoded_value(u8 **p, u8 *end, u64 *val,
         __v;                                                    \
         })
 
-static Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
-                                    GElf_Shdr *shp, const char *name)
-{
-        Elf_Scn *sec = NULL;
-
-        while ((sec = elf_nextscn(elf, sec)) != NULL) {
-                char *str;
-
-                gelf_getshdr(sec, shp);
-                str = elf_strptr(elf, ep->e_shstrndx, shp->sh_name);
-                if (!strcmp(name, str))
-                        break;
-        }
-
-        return sec;
-}
-
 static u64 elf_section_offset(int fd, const char *name)
 {
         Elf *elf;
@@ -190,7 +174,7 @@ static u64 elf_section_offset(int fd, const char *name)
                 if (gelf_getehdr(elf, &ehdr) == NULL)
                         break;
 
-                if (!elf_section_by_name(elf, &ehdr, &shdr, name))
+                if (!elf_section_by_name(elf, &ehdr, &shdr, name, NULL))
                         break;
 
                 offset = shdr.sh_offset;
@@ -340,10 +324,10 @@ find_proc_info(unw_addr_space_t as, unw_word_t ip, unw_proc_info_t *pi,
         /* Check the .debug_frame section for unwinding info */
         if (!read_unwind_spec_debug_frame(map->dso, ui->machine, &segbase)) {
                 memset(&di, 0, sizeof(di));
-                dwarf_find_debug_frame(0, &di, ip, 0, map->dso->name,
-                                       map->start, map->end);
-                return dwarf_search_unwind_table(as, ip, &di, pi,
-                                                 need_unwind_info, arg);
+                if (dwarf_find_debug_frame(0, &di, ip, 0, map->dso->name,
+                                           map->start, map->end))
+                        return dwarf_search_unwind_table(as, ip, &di, pi,
+                                                         need_unwind_info, arg);
         }
 #endif
 
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 28a0a89c1f73..42ad667bb317 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -1,11 +1,17 @@
 #include "../perf.h"
 #include "util.h"
+#include "fs.h"
 #include <sys/mman.h>
 #ifdef HAVE_BACKTRACE_SUPPORT
 #include <execinfo.h>
 #endif
 #include <stdio.h>
 #include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+#include <limits.h>
+#include <byteswap.h>
+#include <linux/kernel.h>
 
 /*
  * XXX We need to find a better place for these things...
@@ -151,21 +157,40 @@ unsigned long convert_unit(unsigned long value, char *unit)
         return value;
 }
 
-int readn(int fd, void *buf, size_t n)
+static ssize_t ion(bool is_read, int fd, void *buf, size_t n)
 {
         void *buf_start = buf;
+        size_t left = n;
 
-        while (n) {
-                int ret = read(fd, buf, n);
+        while (left) {
+                ssize_t ret = is_read ? read(fd, buf, left) :
+                                        write(fd, buf, left);
 
                 if (ret <= 0)
                         return ret;
 
-                n -= ret;
-                buf += ret;
+                left -= ret;
+                buf  += ret;
         }
 
-        return buf - buf_start;
+        BUG_ON((size_t)(buf - buf_start) != n);
+        return n;
+}
+
+/*
+ * Read exactly 'n' bytes or return an error.
+ */
+ssize_t readn(int fd, void *buf, size_t n)
+{
+        return ion(true, fd, buf, n);
+}
+
+/*
+ * Write exactly 'n' bytes or return an error.
+ */
+ssize_t writen(int fd, void *buf, size_t n)
+{
+        return ion(false, fd, buf, n);
 }
 
 size_t hex_width(u64 v)
@@ -413,3 +438,102 @@ int filename__read_int(const char *filename, int *value)
         close(fd);
         return err;
 }
+
+int filename__read_str(const char *filename, char **buf, size_t *sizep)
+{
+        size_t size = 0, alloc_size = 0;
+        void *bf = NULL, *nbf;
+        int fd, n, err = 0;
+
+        fd = open(filename, O_RDONLY);
+        if (fd < 0)
+                return -errno;
+
+        do {
+                if (size == alloc_size) {
+                        alloc_size += BUFSIZ;
+                        nbf = realloc(bf, alloc_size);
+                        if (!nbf) {
+                                err = -ENOMEM;
+                                break;
+                        }
+
+                        bf = nbf;
+                }
+
+                n = read(fd, bf + size, alloc_size - size);
+                if (n < 0) {
+                        if (size) {
+                                pr_warning("read failed %d: %s\n",
+                                           errno, strerror(errno));
+                                err = 0;
+                        } else
+                                err = -errno;
+
+                        break;
+                }
+
+                size += n;
+        } while (n > 0);
+
+        if (!err) {
+                *sizep = size;
+                *buf   = bf;
+        } else
+                free(bf);
+
+        close(fd);
+        return err;
+}
+
+const char *get_filename_for_perf_kvm(void)
+{
+        const char *filename;
+
+        if (perf_host && !perf_guest)
+                filename = strdup("perf.data.host");
+        else if (!perf_host && perf_guest)
+                filename = strdup("perf.data.guest");
+        else
+                filename = strdup("perf.data.kvm");
+
+        return filename;
+}
+
+int perf_event_paranoid(void)
+{
+        char path[PATH_MAX];
+        const char *procfs = procfs__mountpoint();
+        int value;
+
+        if (!procfs)
+                return INT_MAX;
+
+        scnprintf(path, PATH_MAX, "%s/sys/kernel/perf_event_paranoid", procfs);
+
+        if (filename__read_int(path, &value))
+                return INT_MAX;
+
+        return value;
+}
+
+void mem_bswap_32(void *src, int byte_size)
+{
+        u32 *m = src;
+        while (byte_size > 0) {
+                *m = bswap_32(*m);
+                byte_size -= sizeof(u32);
+                ++m;
+        }
+}
+
+void mem_bswap_64(void *src, int byte_size)
+{
+        u64 *m = src;
+
+        while (byte_size > 0) {
+                *m = bswap_64(*m);
+                byte_size -= sizeof(u64);
+                ++m;
+        }
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index c8f362daba87..6995d66f225c 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -71,8 +71,9 @@
 #include <linux/magic.h>
 #include "types.h"
 #include <sys/ttydefaults.h>
-#include <lk/debugfs.h>
+#include <api/fs/debugfs.h>
 #include <termios.h>
+#include <linux/bitops.h>
 
 extern const char *graph_line;
 extern const char *graph_dotted_line;
@@ -185,6 +186,8 @@ static inline void *zalloc(size_t size)
         return calloc(1, size);
 }
 
+#define zfree(ptr) ({ free(*ptr); *ptr = NULL; })
+
 static inline int has_extension(const char *filename, const char *ext)
 {
         size_t len = strlen(filename);
@@ -253,7 +256,8 @@ bool strlazymatch(const char *str, const char *pat);
 int strtailcmp(const char *s1, const char *s2);
 char *strxfrchar(char *s, char from, char to);
 unsigned long convert_unit(unsigned long value, char *unit);
-int readn(int fd, void *buf, size_t size);
+ssize_t readn(int fd, void *buf, size_t n);
+ssize_t writen(int fd, void *buf, size_t n);
 
 struct perf_event_attr;
 
@@ -280,6 +284,17 @@ static inline unsigned next_pow2(unsigned x)
         return 1ULL << (32 - __builtin_clz(x - 1));
 }
 
+static inline unsigned long next_pow2_l(unsigned long x)
+{
+#if BITS_PER_LONG == 64
+        if (x <= (1UL << 31))
+                return next_pow2(x);
+        return (unsigned long)next_pow2(x >> 32) << 32;
+#else
+        return next_pow2(x);
+#endif
+}
+
 size_t hex_width(u64 v);
 int hex2u64(const char *ptr, u64 *val);
 
@@ -307,4 +322,11 @@ char *get_srcline(struct dso *dso, unsigned long addr);
 void free_srcline(char *srcline);
 
 int filename__read_int(const char *filename, int *value);
+int filename__read_str(const char *filename, char **buf, size_t *sizep);
+int perf_event_paranoid(void);
+
+void mem_bswap_64(void *src, int byte_size);
+void mem_bswap_32(void *src, int byte_size);
+
+const char *get_filename_for_perf_kvm(void);
 #endif /* GIT_COMPAT_UTIL_H */
diff --git a/tools/perf/util/values.c b/tools/perf/util/values.c
index 697c8b4e59cc..0fb3c1fcd3e6 100644
--- a/tools/perf/util/values.c
+++ b/tools/perf/util/values.c
@@ -31,14 +31,14 @@ void perf_read_values_destroy(struct perf_read_values *values)
                 return;
 
         for (i = 0; i < values->threads; i++)
-                free(values->value[i]);
-        free(values->value);
-        free(values->pid);
-        free(values->tid);
-        free(values->counterrawid);
+                zfree(&values->value[i]);
+        zfree(&values->value);
+        zfree(&values->pid);
+        zfree(&values->tid);
+        zfree(&values->counterrawid);
         for (i = 0; i < values->counters; i++)
-                free(values->countername[i]);
-        free(values->countername);
+                zfree(&values->countername[i]);
+        zfree(&values->countername);
 }
 
 static void perf_read_values__enlarge_threads(struct perf_read_values *values)
diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
index 39159822d58f..0ddb3b8a89ec 100644
--- a/tools/perf/util/vdso.c
+++ b/tools/perf/util/vdso.c
@@ -103,7 +103,7 @@ struct dso *vdso__dso_findnew(struct list_head *head)
                 dso = dso__new(VDSO__MAP_NAME);
                 if (dso != NULL) {
                         dsos__add(head, dso);
-                        dso__set_long_name(dso, file);
+                        dso__set_long_name(dso, file, false);
                 }
         }