Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf updates from Ingo Molnar:
 "Kernel side changes:

   - Add Intel RAPL energy counter support (Stephane Eranian)
   - Clean up uprobes (Oleg Nesterov)
   - Optimize ring-buffer writes (Peter Zijlstra)

  Tooling side changes, user visible:

   - 'perf diff':
     - Add column colouring improvements (Ramkumar Ramachandra)

  - 'perf kvm':
     - Add guest related improvements, including allowing to specify a
       directory with guest specific /proc information (Dongsheng Yang)
     - Add shell completion support (Ramkumar Ramachandra)
     - Add '-v' option (Dongsheng Yang)
     - Support --guestmount (Dongsheng Yang)

   - 'perf probe':
     - Support showing source code, asking for variables to be collected
       at probe time and other 'perf probe' operations that use DWARF
       information.

       This supports only binaries with debugging information at this
       time, detached debuginfo (aka debuginfo packages) support should
       come in later patches (Masami Hiramatsu)

   - 'perf record':
     - Rename --no-delay option to --no-buffering, better reflecting its
       purpose and freeing up '--delay' to take the place of
       '--initial-delay', so that 'record' and 'stat' are consistent
       (Arnaldo Carvalho de Melo)
     - Default the -t/--thread option to no inheritance (Adrian Hunter)
     - Make per-cpu mmaps the default (Adrian Hunter)

   - 'perf report':
     - Improve callchain processing performance (Frederic Weisbecker)
     - Retain bfd reference to lookup source line numbers, greatly
       optimizing, among other use cases, 'perf report -s srcline'
       (Adrian Hunter)
     - Improve callchain processing performance even more (Namhyung Kim)
     - Add a perf.data file header window in the 'perf report' TUI,
       associated with the 'i' hotkey, providing a counterpart to the
       --header option in the stdio UI (Namhyung Kim)

   - 'perf script':
     - Add an option in 'perf script' to print the source line number
       (Adrian Hunter)
     - Add --header/--header-only options to 'script' and 'report', the
       default is not tho show the header info, but as this has been the
       default for some time, leave a single line explaining how to
       obtain that information (Jiri Olsa)
     - Add options to show comm, fork, exit and mmap PERF_RECORD_ events
       (Namhyung Kim)
     - Print callchains and symbols if they exist (David Ahern)

   - 'perf timechart'
     - Add backtrace support to CPU info
     - Print pid along the name
     - Add support for CPU topology
     - Add new option --highlight'ing threads, be it by name or, if a
       numeric value is provided, that run more than given duration
       (Stanislav Fomichev)

   - 'perf top':
     - Make 'perf top -g' refer to callchains, for consistency with
       other tools (David Ahern)

   - 'perf trace':
     - Handle old kernels where the "raw_syscalls" tracepoints were
       called plain "syscalls" (David Ahern)
     - Remove thread summary coloring, by Pekka Enberg.
     - Honour -m option in 'trace', the tool was offering the option to
       set the mmap size, but wasn't using it when doing the actual mmap
       on the events file descriptors (Jiri Olsa)

   - generic:
     - Backport libtraceevent plugin support (trace-cmd repository, with
       plugins for jbd2, hrtimer, kmem, kvm, mac80211, sched_switch,
       function, xen, scsi, cfg80211 (Jiri Olsa)
     - Print session information only if --stdio is given (Namhyung Kim)

  Tooling side changes, developer visible (plumbing):

   - Improve 'perf probe' exit path, release resources (Masami
     Hiramatsu)
   - Improve libtraceevent plugins exit path, allowing the registering
     of an unregister handler to be called at exit time (Namhyung Kim)
   - Add an alias to the build test makefile (make -C tools/perf
     build-test) (Namhyung Kim)
   - Get rid of die() and friends (good riddance!) in libtraceevent
     (Namhyung Kim)
   - Fix cross build problems related to pkgconfig and CROSS_COMPILE not
     being propagated to the feature tests, leading to features being
     tested in the host and then being enabled on the target (Mark
     Rutland)
   - Improve forked workload error reporting by sending the errno in the
     signal data queueing integer field, using sigqueue and by doing the
     signal setup in the evlist methods, removing open coded equivalents
     in various tools (Arnaldo Carvalho de Melo)
   - Do more auto exit cleanup chores in the 'evlist' destructor, so
     that the tools don't have to all do that sequence (Arnaldo Carvalho
     de Melo)
   - Pack 'struct perf_session_env' and 'struct trace' (Arnaldo Carvalho
     de Melo)
   - Add test for building detached source tarballs (Arnaldo Carvalho de
     Melo)
   - Move some header files (tools/perf/ to tools/include/ to make them
     available to other tools/ dwelling codebases (Namhyung Kim)
   - Move logic to warn about kptr_restrict'ed kernels to separate
     function in 'report' (Arnaldo Carvalho de Melo)
   - Move hist browser selection code to separate function (Arnaldo
     Carvalho de Melo)
   - Move histogram entries collapsing to separate function (Arnaldo
     Carvalho de Melo)
   - Introduce evlist__for_each() & friends (Arnaldo Carvalho de Melo)
   - Automate setup of FEATURE_CHECK_(C|LD)FLAGS-all variables (Jiri
     Olsa)
   - Move arch setup into seprate Makefile (Jiri Olsa)
   - Make libtraceevent install target quieter (Jiri Olsa)
   - Make tests/make output more compact (Jiri Olsa)
   - Ignore generated files in feature-checks (Chunwei Chen)
   - Introduce pevent_filter_strerror() in libtraceevent, similar in
     purpose to libc's strerror() function (Namhyung Kim)
   - Use perf_data_file methods to write output file in 'record' and
     'inject' (Jiri Olsa)
   - Use pr_*() functions where applicable in 'report' (Namhyumg Kim)
   - Add 'machine' 'addr_location' struct to have full picture (machine,
     thread, map, symbol, addr) for a (partially) resolved address,
     reducing function signatures (Arnaldo Carvalho de Melo)
   - Reduce code duplication in the histogram entry creation/insertion
     (Arnaldo Carvalho de Melo)
   - Auto allocate annotation histogram data structures (Arnaldo
     Carvalho de Melo)
   - No need to test against NULL before calling free, also set freed
     memory in struct pointers to NULL, to help fixing use after free
     bugs (Arnaldo Carvalho de Melo)
   - Rename some struct DSO binary_type related members and methods, to
     clarify its purpose and need for differentiation (symtab_type, ie
     one is about the files .text, CFI, etc, i.e.  its binary contents,
     and the other is about where the symbol table came from (Arnaldo
     Carvalho de Melo)
   - Convert to new topic libraries, starting with an API one (sysfs,
     debugfs, etc), renaming liblk in the process (Borislav Petkov)
   - Get rid of some more panic() like error handling in libtraceevent.
     (Namhyung Kim)
   - Get rid of panic() like calls in libtraceevent (Namyung Kim)
   - Start carving out symbol parsing routines (perf, just moving
     routines to topic files in tools/lib/symbol/, tools that want to
     use it need to integrate it directly, ie no
     tools/lib/symbol/Makefile is provided (Arnaldo Carvalho de Melo)
   - Assorted refactoring patches, moving code around and adding utility
     evlist methods that will be used in the IPT patchset (Adrian
     Hunter)
   - Assorted mmap_pages handling fixes (Adrian Hunter)
   - Several man pages typo fixes (Dongsheng Yang)
   - Get rid of several die() calls in libtraceevent (Namhyung Kim)
   - Use basename() in a more robust way, to avoid problems related to
     different system library implementations for that function
     (Stephane Eranian)
   - Remove open coded management of short_name_allocated member (Adrian
     Hunter)
   - Several cleanups in the "dso" methods, constifying some parameters
     and renaming some fields to clarify its purpose (Arnaldo Carvalho
     de Melo)
   - Add per-feature check flags, fixing libunwind related build
     problems on some architectures (Jean Pihet)
   - Do not disable source line lookup just because of one failure.
     (Adrian Hunter)
   - Several 'perf kvm' man page corrections (Dongsheng Yang)
   - Correct the message in feature-libnuma checking, swowing the right
     devel package names for various distros (Dongsheng Yang)
   - Polish 'readn()' function and introduce its counterpart,
     'writen()' (Jiri Olsa)
   - Start moving timechart state from global variables to a 'perf_tool'
     derived 'timechart' struct (Arnaldo Carvalho de Melo)

  ... and lots of fixes and improvements I forgot to list"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (282 commits)
  perf tools: Remove unnecessary callchain cursor state restore on unmatch
  perf callchain: Spare double comparison of callchain first entry
  perf tools: Do proper comm override error handling
  perf symbols: Export elf_section_by_name and reuse
  perf probe: Release all dynamically allocated parameters
  perf probe: Release allocated probe_trace_event if failed
  perf tools: Add 'build-test' make target
  tools lib traceevent: Unregister handler when xen plugin is unloaded
  tools lib traceevent: Unregister handler when scsi plugin is unloaded
  tools lib traceevent: Unregister handler when jbd2 plugin is is unloaded
  tools lib traceevent: Unregister handler when cfg80211 plugin is unloaded
  tools lib traceevent: Unregister handler when mac80211 plugin is unloaded
  tools lib traceevent: Unregister handler when sched_switch plugin is unloaded
  tools lib traceevent: Unregister handler when kvm plugin is unloaded
  tools lib traceevent: Unregister handler when kmem plugin is unloaded
  tools lib traceevent: Unregister handler when hrtimer plugin is unloaded
  tools lib traceevent: Unregister handler when function plugin is unloaded
  tools lib traceevent: Add pevent_unregister_print_function()
  tools lib traceevent: Add pevent_unregister_event_handler()
  tools lib traceevent: fix pointer-integer size mismatch
  ...

168 files changed, 6924 insertions, 2626 deletions

diff --git a/tools/Makefile b/tools/Makefile
index a9b02008443..927cd46d36d 100644
--- a/tools/Makefile
+++ b/tools/Makefile
@@ -39,10 +39,10 @@ cpupower: FORCE
 cgroup firewire guest usb virtio vm net: FORCE
 	$(call descend,$@)
 
-liblk: FORCE
-	$(call descend,lib/lk)
+libapikfs: FORCE
+	$(call descend,lib/api)
 
-perf: liblk FORCE
+perf: libapikfs FORCE
 	$(call descend,$@)
 
 selftests: FORCE
@@ -80,10 +80,10 @@ cpupower_clean:
 cgroup_clean firewire_clean lguest_clean usb_clean virtio_clean vm_clean net_clean:
 	$(call descend,$(@:_clean=),clean)
 
-liblk_clean:
-	$(call descend,lib/lk,clean)
+libapikfs_clean:
+	$(call descend,lib/api,clean)
 
-perf_clean: liblk_clean
+perf_clean: libapikfs_clean
 	$(call descend,$(@:_clean=),clean)
 
 selftests_clean:
diff --git a/tools/perf/util/include/asm/bug.h b/tools/include/asm/bug.h
index 7fcc6810adc..9e5f4846967 100644
--- a/tools/perf/util/include/asm/bug.h
+++ b/tools/include/asm/bug.h
@@ -1,5 +1,7 @@
-#ifndef _PERF_ASM_GENERIC_BUG_H
-#define _PERF_ASM_GENERIC_BUG_H
+#ifndef _TOOLS_ASM_BUG_H
+#define _TOOLS_ASM_BUG_H
+
+#include <linux/compiler.h>
 
 #define __WARN_printf(arg...)	do { fprintf(stderr, arg); } while (0)
 
@@ -19,4 +21,5 @@
 			__warned = 1;		\
 	unlikely(__ret_warn_once);		\
 })
-#endif
+
+#endif /* _TOOLS_ASM_BUG_H */
diff --git a/tools/perf/util/include/linux/compiler.h b/tools/include/linux/compiler.h
index b003ad7200b..fbc6665c6d5 100644
--- a/tools/perf/util/include/linux/compiler.h
+++ b/tools/include/linux/compiler.h
@@ -1,5 +1,5 @@
-#ifndef _PERF_LINUX_COMPILER_H_
-#define _PERF_LINUX_COMPILER_H_
+#ifndef _TOOLS_LINUX_COMPILER_H_
+#define _TOOLS_LINUX_COMPILER_H_
 
 #ifndef __always_inline
 # define __always_inline	inline __attribute__((always_inline))
@@ -27,4 +27,12 @@
 # define __weak			__attribute__((weak))
 #endif
 
+#ifndef likely
+# define likely(x)		__builtin_expect(!!(x), 1)
 #endif
+
+#ifndef unlikely
+# define unlikely(x)		__builtin_expect(!!(x), 0)
+#endif
+
+#endif /* _TOOLS_LINUX_COMPILER_H */
diff --git a/tools/lib/lk/Makefile b/tools/lib/api/Makefile
index 3dba0a4aebb..ed2f51e11b8 100644
--- a/tools/lib/lk/Makefile
+++ b/tools/lib/api/Makefile
@@ -1,4 +1,5 @@
 include ../../scripts/Makefile.include
+include ../../perf/config/utilities.mak		# QUIET_CLEAN
 
 CC = $(CROSS_COMPILE)gcc
 AR = $(CROSS_COMPILE)ar
@@ -7,11 +8,11 @@ AR = $(CROSS_COMPILE)ar
 LIB_H=
 LIB_OBJS=
 
-LIB_H += debugfs.h
+LIB_H += fs/debugfs.h
 
-LIB_OBJS += $(OUTPUT)debugfs.o
+LIB_OBJS += $(OUTPUT)fs/debugfs.o
 
-LIBFILE = liblk.a
+LIBFILE = libapikfs.a
 
 CFLAGS = -ggdb3 -Wall -Wextra -std=gnu99 -Werror -O6 -D_FORTIFY_SOURCE=2 $(EXTRA_WARNINGS) $(EXTRA_CFLAGS) -fPIC
 EXTLIBS = -lelf -lpthread -lrt -lm
@@ -25,14 +26,17 @@ $(LIBFILE): $(LIB_OBJS)
 
 $(LIB_OBJS): $(LIB_H)
 
-$(OUTPUT)%.o: %.c
+libapi_dirs:
+	$(QUIET_MKDIR)mkdir -p $(OUTPUT)fs/
+
+$(OUTPUT)%.o: %.c libapi_dirs
 	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $<
-$(OUTPUT)%.s: %.c
+$(OUTPUT)%.s: %.c libapi_dirs
 	$(QUIET_CC)$(CC) -S $(ALL_CFLAGS) $<
-$(OUTPUT)%.o: %.S
+$(OUTPUT)%.o: %.S libapi_dirs
 	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $<
 
 clean:
-	$(RM) $(LIB_OBJS) $(LIBFILE)
+	$(call QUIET_CLEAN, libapi) $(RM) $(LIB_OBJS) $(LIBFILE)
 
 .PHONY: clean
diff --git a/tools/lib/lk/debugfs.c b/tools/lib/api/fs/debugfs.c
index 7c434796235..7c434796235 100644
--- a/tools/lib/lk/debugfs.c
+++ b/tools/lib/api/fs/debugfs.c
diff --git a/tools/lib/lk/debugfs.h b/tools/lib/api/fs/debugfs.h
index 935c59bdb44..f19d3df9609 100644
--- a/tools/lib/lk/debugfs.h
+++ b/tools/lib/api/fs/debugfs.h
@@ -1,5 +1,5 @@
-#ifndef __LK_DEBUGFS_H__
-#define __LK_DEBUGFS_H__
+#ifndef __API_DEBUGFS_H__
+#define __API_DEBUGFS_H__
 
 #define _STR(x) #x
 #define STR(x) _STR(x)
@@ -26,4 +26,4 @@ char *debugfs_mount(const char *mountpoint);
 
 extern char debugfs_mountpoint[];
 
-#endif /* __LK_DEBUGFS_H__ */
+#endif /* __API_DEBUGFS_H__ */
diff --git a/tools/lib/symbol/kallsyms.c b/tools/lib/symbol/kallsyms.c
new file mode 100644
index 00000000000..18bc271a4bb
--- /dev/null
+++ b/tools/lib/symbol/kallsyms.c
@@ -0,0 +1,58 @@
+#include "symbol/kallsyms.h"
+#include <stdio.h>
+#include <stdlib.h>
+
+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;
+}
diff --git a/tools/lib/symbol/kallsyms.h b/tools/lib/symbol/kallsyms.h
new file mode 100644
index 00000000000..6084f5e18b3
--- /dev/null
+++ b/tools/lib/symbol/kallsyms.h
@@ -0,0 +1,24 @@
+#ifndef __TOOLS_KALLSYMS_H_
+#define __TOOLS_KALLSYMS_H_ 1
+
+#include <elf.h>
+#include <linux/ctype.h>
+#include <linux/types.h>
+
+#ifndef KSYM_NAME_LEN
+#define KSYM_NAME_LEN 256
+#endif
+
+static inline u8 kallsyms2elf_type(char type)
+{
+	if (type == 'W')
+		return STB_WEAK;
+
+	return isupper(type) ? STB_GLOBAL : STB_LOCAL;
+}
+
+int kallsyms__parse(const char *filename, void *arg,
+		    int (*process_symbol)(void *arg, const char *name,
+					  char type, u64 start));
+
+#endif /* __TOOLS_KALLSYMS_H_ */
diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index fc150209859..56d52a33a3d 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -43,6 +43,32 @@ man_dir_SQ = '$(subst ','\'',$(man_dir))'
 export man_dir man_dir_SQ INSTALL
 export DESTDIR DESTDIR_SQ
 
+set_plugin_dir := 1
+
+# Set plugin_dir to preffered global plugin location
+# If we install under $HOME directory we go under
+# $(HOME)/.traceevent/plugins
+#
+# We dont set PLUGIN_DIR in case we install under $HOME
+# directory, because by default the code looks under:
+# $(HOME)/.traceevent/plugins by default.
+#
+ifeq ($(plugin_dir),)
+ifeq ($(prefix),$(HOME))
+override plugin_dir = $(HOME)/.traceevent/plugins
+set_plugin_dir := 0
+else
+override plugin_dir = $(prefix)/lib/traceevent/plugins
+endif
+endif
+
+ifeq ($(set_plugin_dir),1)
+PLUGIN_DIR = -DPLUGIN_DIR="$(DESTDIR)/$(plugin_dir)"
+PLUGIN_DIR_SQ = '$(subst ','\'',$(PLUGIN_DIR))'
+endif
+
+include $(if $(BUILD_SRC),$(BUILD_SRC)/)../../scripts/Makefile.include
+
 # copy a bit from Linux kbuild
 
 ifeq ("$(origin V)", "command line")
@@ -57,18 +83,13 @@ ifeq ("$(origin O)", "command line")
 endif
 
 ifeq ($(BUILD_SRC),)
-ifneq ($(BUILD_OUTPUT),)
+ifneq ($(OUTPUT),)
 
 define build_output
-	$(if $(VERBOSE:1=),@)+$(MAKE) -C $(BUILD_OUTPUT) 	\
-	BUILD_SRC=$(CURDIR) -f $(CURDIR)/Makefile $1
+  $(if $(VERBOSE:1=),@)+$(MAKE) -C $(OUTPUT) \
+  BUILD_SRC=$(CURDIR)/ -f $(CURDIR)/Makefile $1
 endef
 
-saved-output := $(BUILD_OUTPUT)
-BUILD_OUTPUT := $(shell cd $(BUILD_OUTPUT) && /bin/pwd)
-$(if $(BUILD_OUTPUT),, \
-     $(error output directory "$(saved-output)" does not exist))
-
 all: sub-make
 
 $(MAKECMDGOALS): sub-make
@@ -80,7 +101,7 @@ sub-make: force
 # Leave processing to above invocation of make
 skip-makefile := 1
 
-endif # BUILD_OUTPUT
+endif # OUTPUT
 endif # BUILD_SRC
 
 # We process the rest of the Makefile if this is the final invocation of make
@@ -96,6 +117,7 @@ export prefix bindir src obj
 # Shell quotes
 bindir_SQ = $(subst ','\'',$(bindir))
 bindir_relative_SQ = $(subst ','\'',$(bindir_relative))
+plugin_dir_SQ = $(subst ','\'',$(plugin_dir))
 
 LIB_FILE = libtraceevent.a libtraceevent.so
 
@@ -114,7 +136,7 @@ export Q VERBOSE
 
 EVENT_PARSE_VERSION = $(EP_VERSION).$(EP_PATCHLEVEL).$(EP_EXTRAVERSION)
 
-INCLUDES = -I. $(CONFIG_INCLUDES)
+INCLUDES = -I. -I $(srctree)/../../include $(CONFIG_INCLUDES)
 
 # Set compile option CFLAGS if not set elsewhere
 CFLAGS ?= -g -Wall
@@ -125,41 +147,14 @@ override CFLAGS += $(udis86-flags) -D_GNU_SOURCE
 
 ifeq ($(VERBOSE),1)
   Q =
-  print_compile =
-  print_app_build =
-  print_fpic_compile =
-  print_shared_lib_compile =
-  print_plugin_obj_compile =
-  print_plugin_build =
-  print_install =
 else
   Q = @
-  print_compile =		echo '  CC       '$(OBJ);
-  print_app_build =		echo '  BUILD    '$(OBJ);
-  print_fpic_compile =		echo '  CC FPIC  '$(OBJ);
-  print_shared_lib_compile =	echo '  BUILD    SHARED LIB '$(OBJ);
-  print_plugin_obj_compile =	echo '  BUILD    PLUGIN OBJ '$(OBJ);
-  print_plugin_build =		echo '  BUILD    PLUGIN     '$(OBJ);
-  print_static_lib_build =	echo '  BUILD    STATIC LIB '$(OBJ);
-  print_install =		echo '  INSTALL  '$1'	to	$(DESTDIR_SQ)$2';
 endif
 
-do_fpic_compile =					\
-	($(print_fpic_compile)				\
-	$(CC) -c $(CFLAGS) $(EXT) -fPIC $< -o $@)
-
-do_app_build =						\
-	($(print_app_build)				\
-	$(CC) $^ -rdynamic -o $@ $(CONFIG_LIBS) $(LIBS))
-
 do_compile_shared_library =			\
 	($(print_shared_lib_compile)		\
 	$(CC) --shared $^ -o $@)
 
-do_compile_plugin_obj =				\
-	($(print_plugin_obj_compile)		\
-	$(CC) -c $(CFLAGS) -fPIC -o $@ $<)
-
 do_plugin_build =				\
 	($(print_plugin_build)			\
 	$(CC) $(CFLAGS) -shared -nostartfiles -o $@ $<)
@@ -169,23 +164,37 @@ do_build_static_lib =				\
 	$(RM) $@;  $(AR) rcs $@ $^)
 
 
-define do_compile
-	$(print_compile)						\
-	$(CC) -c $(CFLAGS) $(EXT) $< -o $(obj)/$@;
-endef
+do_compile = $(QUIET_CC)$(CC) -c $(CFLAGS) $(EXT) $< -o $(obj)/$@;
 
 $(obj)/%.o: $(src)/%.c
-	$(Q)$(call do_compile)
+	$(call do_compile)
 
 %.o: $(src)/%.c
-	$(Q)$(call do_compile)
+	$(call do_compile)
 
-PEVENT_LIB_OBJS = event-parse.o trace-seq.o parse-filter.o parse-utils.o
+PEVENT_LIB_OBJS  = event-parse.o
+PEVENT_LIB_OBJS += event-plugin.o
+PEVENT_LIB_OBJS += trace-seq.o
+PEVENT_LIB_OBJS += parse-filter.o
+PEVENT_LIB_OBJS += parse-utils.o
 PEVENT_LIB_OBJS += kbuffer-parse.o
 
-ALL_OBJS = $(PEVENT_LIB_OBJS)
+PLUGIN_OBJS  = plugin_jbd2.o
+PLUGIN_OBJS += plugin_hrtimer.o
+PLUGIN_OBJS += plugin_kmem.o
+PLUGIN_OBJS += plugin_kvm.o
+PLUGIN_OBJS += plugin_mac80211.o
+PLUGIN_OBJS += plugin_sched_switch.o
+PLUGIN_OBJS += plugin_function.o
+PLUGIN_OBJS += plugin_xen.o
+PLUGIN_OBJS += plugin_scsi.o
+PLUGIN_OBJS += plugin_cfg80211.o
+
+PLUGINS := $(PLUGIN_OBJS:.o=.so)
+
+ALL_OBJS = $(PEVENT_LIB_OBJS) $(PLUGIN_OBJS)
 
-CMD_TARGETS = $(LIB_FILE)
+CMD_TARGETS = $(LIB_FILE) $(PLUGINS)
 
 TARGETS = $(CMD_TARGETS)
 
@@ -195,32 +204,40 @@ all: all_cmd
 all_cmd: $(CMD_TARGETS)
 
 libtraceevent.so: $(PEVENT_LIB_OBJS)
-	$(Q)$(do_compile_shared_library)
+	$(QUIET_LINK)$(CC) --shared $^ -o $@
 
 libtraceevent.a: $(PEVENT_LIB_OBJS)
-	$(Q)$(do_build_static_lib)
+	$(QUIET_LINK)$(RM) $@; $(AR) rcs $@ $^
+
+plugins: $(PLUGINS)
 
 $(PEVENT_LIB_OBJS): %.o: $(src)/%.c TRACEEVENT-CFLAGS
-	$(Q)$(do_fpic_compile)
+	$(QUIET_CC_FPIC)$(CC) -c $(CFLAGS) $(EXT) -fPIC $< -o $@
+
+$(PLUGIN_OBJS): %.o : $(src)/%.c
+	$(QUIET_CC_FPIC)$(CC) -c $(CFLAGS) -fPIC -o $@ $<
+
+$(PLUGINS): %.so: %.o
+	$(QUIET_LINK)$(CC) $(CFLAGS) -shared -nostartfiles -o $@ $<
 
 define make_version.h
-	(echo '/* This file is automatically generated. Do not modify. */';		\
-	echo \#define VERSION_CODE $(shell						\
-	expr $(VERSION) \* 256 + $(PATCHLEVEL));					\
-	echo '#define EXTRAVERSION ' $(EXTRAVERSION);					\
-	echo '#define VERSION_STRING "'$(VERSION).$(PATCHLEVEL).$(EXTRAVERSION)'"';	\
-	echo '#define FILE_VERSION '$(FILE_VERSION);					\
-	) > $1
+  (echo '/* This file is automatically generated. Do not modify. */';		\
+   echo \#define VERSION_CODE $(shell						\
+   expr $(VERSION) \* 256 + $(PATCHLEVEL));					\
+   echo '#define EXTRAVERSION ' $(EXTRAVERSION);				\
+   echo '#define VERSION_STRING "'$(VERSION).$(PATCHLEVEL).$(EXTRAVERSION)'"';	\
+   echo '#define FILE_VERSION '$(FILE_VERSION);					\
+  ) > $1
 endef
 
 define update_version.h
-	($(call make_version.h, $@.tmp);		\
-	if [ -r $@ ] && cmp -s $@ $@.tmp; then		\
-		rm -f $@.tmp;				\
-	else						\
-		echo '  UPDATE                 $@';	\
-		mv -f $@.tmp $@;			\
-	fi);
+  ($(call make_version.h, $@.tmp);		\
+    if [ -r $@ ] && cmp -s $@ $@.tmp; then	\
+      rm -f $@.tmp;				\
+    else					\
+      echo '  UPDATE                 $@';	\
+      mv -f $@.tmp $@;				\
+    fi);
 endef
 
 ep_version.h: force
@@ -229,13 +246,13 @@ ep_version.h: force
 VERSION_FILES = ep_version.h
 
 define update_dir
-	(echo $1 > $@.tmp;	\
-	if [ -r $@ ] && cmp -s $@ $@.tmp; then		\
-		rm -f $@.tmp;				\
-	else						\
-		echo '  UPDATE                 $@';	\
-		mv -f $@.tmp $@;			\
-	fi);
+  (echo $1 > $@.tmp;				\
+   if [ -r $@ ] && cmp -s $@ $@.tmp; then	\
+     rm -f $@.tmp;				\
+   else						\
+     echo '  UPDATE                 $@';	\
+     mv -f $@.tmp $@;				\
+   fi);
 endef
 
 ## make deps
@@ -245,10 +262,10 @@ all_deps := $(all_objs:%.o=.%.d)
 
 # let .d file also depends on the source and header files
 define check_deps
-		@set -e; $(RM) $@; \
-		$(CC) -MM $(CFLAGS) $< > $@.$$$$; \
-		sed 's,\($*\)\.o[ :]*,\1.o $@ : ,g' < $@.$$$$ > $@; \
-		$(RM) $@.$$$$
+  @set -e; $(RM) $@; \
+  $(CC) -MM $(CFLAGS) $< > $@.$$$$; \
+  sed 's,\($*\)\.o[ :]*,\1.o $@ : ,g' < $@.$$$$ > $@; \
+  $(RM) $@.$$$$
 endef
 
 $(all_deps): .%.d: $(src)/%.c
@@ -283,27 +300,41 @@ TAGS:	force
 	--regex='/_PE(\([^,)]*\).*/PEVENT_ERRNO__\1/'
 
 define do_install
-	$(print_install)				\
 	if [ ! -d '$(DESTDIR_SQ)$2' ]; then		\
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$2';	\
 	fi;						\
 	$(INSTALL) $1 '$(DESTDIR_SQ)$2'
 endef
 
-install_lib: all_cmd
-	$(Q)$(call do_install,$(LIB_FILE),$(bindir_SQ))
+define do_install_plugins
+	for plugin in $1; do				\
+	  $(call do_install,$$plugin,$(plugin_dir_SQ));	\
+	done
+endef
+
+install_lib: all_cmd install_plugins
+	$(call QUIET_INSTALL, $(LIB_FILE)) \
+		$(call do_install,$(LIB_FILE),$(bindir_SQ))
+
+install_plugins: $(PLUGINS)
+	$(call QUIET_INSTALL, trace_plugins) \
+		$(call do_install_plugins, $(PLUGINS))
 
 install: install_lib
 
 clean:
-	$(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES) .*.d
-	$(RM) TRACEEVENT-CFLAGS tags TAGS
+	$(call QUIET_CLEAN, libtraceevent) \
+		$(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES) .*.d \
+		$(RM) TRACEEVENT-CFLAGS tags TAGS
 
 endif # skip-makefile
 
-PHONY += force
+PHONY += force plugins
 force:
 
+plugins:
+	@echo > /dev/null
+
 # Declare the contents of the .PHONY variable as phony.  We keep that
 # information in a variable so we can use it in if_changed and friends.
 .PHONY: $(PHONY)
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 217c82ee366..1587ea392ad 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -2710,7 +2710,6 @@ process_func_handler(struct event_format *event, struct pevent_function_handler
 	struct print_arg *farg;
 	enum event_type type;
 	char *token;
-	const char *test;
 	int i;
 
 	arg->type = PRINT_FUNC;
@@ -2727,15 +2726,19 @@ process_func_handler(struct event_format *event, struct pevent_function_handler
 		}
 
 		type = process_arg(event, farg, &token);
-		if (i < (func->nr_args - 1))
-			test = ",";
-		else
-			test = ")";
-
-		if (test_type_token(type, token, EVENT_DELIM, test)) {
-			free_arg(farg);
-			free_token(token);
-			return EVENT_ERROR;
+		if (i < (func->nr_args - 1)) {
+			if (type != EVENT_DELIM || strcmp(token, ",") != 0) {
+				warning("Error: function '%s()' expects %d arguments but event %s only uses %d",
+					func->name, func->nr_args,
+					event->name, i + 1);
+				goto err;
+			}
+		} else {
+			if (type != EVENT_DELIM || strcmp(token, ")") != 0) {
+				warning("Error: function '%s()' only expects %d arguments but event %s has more",
+					func->name, func->nr_args, event->name);
+				goto err;
+			}
 		}
 
 		*next_arg = farg;
@@ -2747,6 +2750,11 @@ process_func_handler(struct event_format *event, struct pevent_function_handler
 	*tok = token;
 
 	return type;
+
+err:
+	free_arg(farg);
+	free_token(token);
+	return EVENT_ERROR;
 }
 
 static enum event_type
@@ -4099,6 +4107,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event
 	unsigned long long val;
 	struct func_map *func;
 	const char *saveptr;
+	struct trace_seq p;
 	char *bprint_fmt = NULL;
 	char format[32];
 	int show_func;
@@ -4306,8 +4315,12 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event
 				format[len] = 0;
 				if (!len_as_arg)
 					len_arg = -1;
-				print_str_arg(s, data, size, event,
+				/* Use helper trace_seq */
+				trace_seq_init(&p);
+				print_str_arg(&p, data, size, event,
 					      format, len_arg, arg);
+				trace_seq_terminate(&p);
+				trace_seq_puts(s, p.buffer);
 				arg = arg->next;
 				break;
 			default:
@@ -5116,8 +5129,38 @@ enum pevent_errno __pevent_parse_format(struct event_format **eventp,
 	return ret;
 }
 
+static enum pevent_errno
+__pevent_parse_event(struct pevent *pevent,
+		     struct event_format **eventp,
+		     const char *buf, unsigned long size,
+		     const char *sys)
+{
+	int ret = __pevent_parse_format(eventp, pevent, buf, size, sys);
+	struct event_format *event = *eventp;
+
+	if (event == NULL)
+		return ret;
+
+	if (pevent && add_event(pevent, event)) {
+		ret = PEVENT_ERRNO__MEM_ALLOC_FAILED;
+		goto event_add_failed;
+	}
+
+#define PRINT_ARGS 0
+	if (PRINT_ARGS && event->print_fmt.args)
+		print_args(event->print_fmt.args);
+
+	return 0;
+
+event_add_failed:
+	pevent_free_format(event);
+	return ret;
+}
+
 /**
  * pevent_parse_format - parse the event format
+ * @pevent: the handle to the pevent
+ * @eventp: returned format
  * @buf: the buffer storing the event format string
  * @size: the size of @buf
  * @sys: the system the event belongs to
@@ -5129,10 +5172,12 @@ enum pevent_errno __pevent_parse_format(struct event_format **eventp,
  *
  * /sys/kernel/debug/tracing/events/.../.../format
  */
-enum pevent_errno pevent_parse_format(struct event_format **eventp, const char *buf,
+enum pevent_errno pevent_parse_format(struct pevent *pevent,
+				      struct event_format **eventp,
+				      const char *buf,
 				      unsigned long size, const char *sys)
 {
-	return __pevent_parse_format(eventp, NULL, buf, size, sys);
+	return __pevent_parse_event(pevent, eventp, buf, size, sys);
 }
 
 /**
@@ -5153,25 +5198,7 @@ enum pevent_errno pevent_parse_event(struct pevent *pevent, const char *buf,
 				     unsigned long size, const char *sys)
 {
 	struct event_format *event = NULL;
-	int ret = __pevent_parse_format(&event, pevent, buf, size, sys);
-
-	if (event == NULL)
-		return ret;
-
-	if (add_event(pevent, event)) {
-		ret = PEVENT_ERRNO__MEM_ALLOC_FAILED;
-		goto event_add_failed;
-	}
-
-#define PRINT_ARGS 0
-	if (PRINT_ARGS && event->print_fmt.args)
-		print_args(event->print_fmt.args);
-
-	return 0;
-
-event_add_failed:
-	pevent_free_format(event);
-	return ret;
+	return __pevent_parse_event(pevent, &event, buf, size, sys);
 }
 
 #undef _PE
@@ -5203,22 +5230,7 @@ int pevent_strerror(struct pevent *pevent __maybe_unused,
 
 	idx = errnum - __PEVENT_ERRNO__START - 1;
 	msg = pevent_error_str[idx];
-
-	switch (errnum) {
-	case PEVENT_ERRNO__MEM_ALLOC_FAILED:
-	case PEVENT_ERRNO__PARSE_EVENT_FAILED:
-	case PEVENT_ERRNO__READ_ID_FAILED:
-	case PEVENT_ERRNO__READ_FORMAT_FAILED:
-	case PEVENT_ERRNO__READ_PRINT_FAILED:
-	case PEVENT_ERRNO__OLD_FTRACE_ARG_FAILED:
-	case PEVENT_ERRNO__INVALID_ARG_TYPE:
-		snprintf(buf, buflen, "%s", msg);
-		break;
-
-	default:
-		/* cannot reach here */
-		break;
-	}
+	snprintf(buf, buflen, "%s", msg);
 
 	return 0;
 }
@@ -5549,6 +5561,52 @@ int pevent_register_print_function(struct pevent *pevent,
 }
 
 /**
+ * pevent_unregister_print_function - unregister a helper function
+ * @pevent: the handle to the pevent
+ * @func: the function to process the helper function
+ * @name: the name of the helper function
+ *
+ * This function removes existing print handler for function @name.
+ *
+ * Returns 0 if the handler was removed successully, -1 otherwise.
+ */
+int pevent_unregister_print_function(struct pevent *pevent,
+				     pevent_func_handler func, char *name)
+{
+	struct pevent_function_handler *func_handle;
+
+	func_handle = find_func_handler(pevent, name);
+	if (func_handle && func_handle->func == func) {
+		remove_func_handler(pevent, name);
+		return 0;
+	}
+	return -1;
+}
+
+static struct event_format *pevent_search_event(struct pevent *pevent, int id,
+						const char *sys_name,
+						const char *event_name)
+{
+	struct event_format *event;
+
+	if (id >= 0) {
+		/* search by id */
+		event = pevent_find_event(pevent, id);
+		if (!event)
+			return NULL;
+		if (event_name && (strcmp(event_name, event->name) != 0))
+			return NULL;
+		if (sys_name && (strcmp(sys_name, event->system) != 0))
+			return NULL;
+	} else {
+		event = pevent_find_event_by_name(pevent, sys_name, event_name);
+		if (!event)
+			return NULL;
+	}
+	return event;
+}
+
+/**
  * pevent_register_event_handler - register a way to parse an event
  * @pevent: the handle to the pevent
  * @id: the id of the event to register
@@ -5572,20 +5630,9 @@ int pevent_register_event_handler(struct pevent *pevent, int id,
 	struct event_format *event;
 	struct event_handler *handle;
 
-	if (id >= 0) {
-		/* search by id */
-		event = pevent_find_event(pevent, id);
-		if (!event)
-			goto not_found;
-		if (event_name && (strcmp(event_name, event->name) != 0))
-			goto not_found;
-		if (sys_name && (strcmp(sys_name, event->system) != 0))
-			goto not_found;
-	} else {
-		event = pevent_find_event_by_name(pevent, sys_name, event_name);
-		if (!event)
-			goto not_found;
-	}
+	event = pevent_search_event(pevent, id, sys_name, event_name);
+	if (event == NULL)
+		goto not_found;
 
 	pr_stat("overriding event (%d) %s:%s with new print handler",
 		event->id, event->system, event->name);
@@ -5625,6 +5672,79 @@ int pevent_register_event_handler(struct pevent *pevent, int id,
 	return -1;
 }
 
+static int handle_matches(struct event_handler *handler, int id,
+			  const char *sys_name, const char *event_name,
+			  pevent_event_handler_func func, void *context)
+{
+	if (id >= 0 && id != handler->id)
+		return 0;
+
+	if (event_name && (strcmp(event_name, handler->event_name) != 0))
+		return 0;
+
+	if (sys_name && (strcmp(sys_name, handler->sys_name) != 0))
+		return 0;
+
+	if (func != handler->func || context != handler->context)
+		return 0;
+
+	return 1;
+}
+
+/**
+ * pevent_unregister_event_handler - unregister an existing event handler
+ * @pevent: the handle to the pevent
+ * @id: the id of the event to unregister
+ * @sys_name: the system name the handler belongs to
+ * @event_name: the name of the event handler
+ * @func: the function to call to parse the event information
+ * @context: the data to be passed to @func
+ *
+ * This function removes existing event handler (parser).
+ *
+ * If @id is >= 0, then it is used to find the event.
+ * else @sys_name and @event_name are used.
+ *
+ * Returns 0 if handler was removed successfully, -1 if event was not found.
+ */
+int pevent_unregister_event_handler(struct pevent *pevent, int id,
+				    const char *sys_name, const char *event_name,
+				    pevent_event_handler_func func, void *context)
+{
+	struct event_format *event;
+	struct event_handler *handle;
+	struct event_handler **next;
+
+	event = pevent_search_event(pevent, id, sys_name, event_name);
+	if (event == NULL)
+		goto not_found;
+
+	if (event->handler == func && event->context == context) {
+		pr_stat("removing override handler for event (%d) %s:%s. Going back to default handler.",
+			event->id, event->system, event->name);
+
+		event->handler = NULL;
+		event->context = NULL;
+		return 0;
+	}
+
+not_found:
+	for (next = &pevent->handlers; *next; next = &(*next)->next) {
+		handle = *next;
+		if (handle_matches(handle, id, sys_name, event_name,
+				   func, context))
+			break;
+	}
+
+	if (!(*next))
+		return -1;
+
+	*next = handle->next;
+	free_handler(handle);
+
+	return 0;
+}
+
 /**
  * pevent_alloc - create a pevent handle
  */
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index 8d73d2594f6..791c539374c 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -23,6 +23,7 @@
 #include <stdbool.h>
 #include <stdarg.h>
 #include <regex.h>
+#include <string.h>
 
 #ifndef __maybe_unused
 #define __maybe_unused __attribute__((unused))
@@ -57,6 +58,12 @@ struct pevent_record {
 #endif
 };
 
+enum trace_seq_fail {
+	TRACE_SEQ__GOOD,
+	TRACE_SEQ__BUFFER_POISONED,
+	TRACE_SEQ__MEM_ALLOC_FAILED,
+};
+
 /*
  * Trace sequences are used to allow a function to call several other functions
  * to create a string of data to use (up to a max of PAGE_SIZE).
@@ -67,6 +74,7 @@ struct trace_seq {
 	unsigned int		buffer_size;
 	unsigned int		len;
 	unsigned int		readpos;
+	enum trace_seq_fail	state;
 };
 
 void trace_seq_init(struct trace_seq *s);
@@ -97,7 +105,7 @@ typedef int (*pevent_event_handler_func)(struct trace_seq *s,
 					 void *context);
 
 typedef int (*pevent_plugin_load_func)(struct pevent *pevent);
-typedef int (*pevent_plugin_unload_func)(void);
+typedef int (*pevent_plugin_unload_func)(struct pevent *pevent);
 
 struct plugin_option {
 	struct plugin_option		*next;
@@ -122,7 +130,7 @@ struct plugin_option {
  * PEVENT_PLUGIN_UNLOADER:  (optional)
  *   The function called just before unloading
  *
- *   int PEVENT_PLUGIN_UNLOADER(void)
+ *   int PEVENT_PLUGIN_UNLOADER(struct pevent *pevent)
  *
  * PEVENT_PLUGIN_OPTIONS:  (optional)
  *   Plugin options that can be set before loading
@@ -355,12 +363,35 @@ enum pevent_flag {
 	_PE(READ_FORMAT_FAILED,	"failed to read event format"),		      \
 	_PE(READ_PRINT_FAILED,	"failed to read event print fmt"), 	      \
 	_PE(OLD_FTRACE_ARG_FAILED,"failed to allocate field name for ftrace"),\
-	_PE(INVALID_ARG_TYPE,	"invalid argument type")
+	_PE(INVALID_ARG_TYPE,	"invalid argument type"),		      \
+	_PE(INVALID_EXP_TYPE,	"invalid expression type"),		      \
+	_PE(INVALID_OP_TYPE,	"invalid operator type"),		      \
+	_PE(INVALID_EVENT_NAME,	"invalid event name"),			      \
+	_PE(EVENT_NOT_FOUND,	"no event found"),			      \
+	_PE(SYNTAX_ERROR,	"syntax error"),			      \
+	_PE(ILLEGAL_RVALUE,	"illegal rvalue"),			      \
+	_PE(ILLEGAL_LVALUE,	"illegal lvalue for string comparison"),      \
+	_PE(INVALID_REGEX,	"regex did not compute"),		      \
+	_PE(ILLEGAL_STRING_CMP,	"illegal comparison for string"), 	      \
+	_PE(ILLEGAL_INTEGER_CMP,"illegal comparison for integer"), 	      \
+	_PE(REPARENT_NOT_OP,	"cannot reparent other than OP"),	      \
+	_PE(REPARENT_FAILED,	"failed to reparent filter OP"),	      \
+	_PE(BAD_FILTER_ARG,	"bad arg in filter tree"),		      \
+	_PE(UNEXPECTED_TYPE,	"unexpected type (not a value)"),	      \
+	_PE(ILLEGAL_TOKEN,	"illegal token"),			      \
+	_PE(INVALID_PAREN,	"open parenthesis cannot come here"), 	      \
+	_PE(UNBALANCED_PAREN,	"unbalanced number of parenthesis"),	      \
+	_PE(UNKNOWN_TOKEN,	"unknown token"),			      \
+	_PE(FILTER_NOT_FOUND,	"no filter found"),			      \
+	_PE(NOT_A_NUMBER,	"must have number field"),		      \
+	_PE(NO_FILTER,		"no filters exists"),			      \
+	_PE(FILTER_MISS,	"record does not match to filter")
 
 #undef _PE
 #define _PE(__code, __str) PEVENT_ERRNO__ ## __code
 enum pevent_errno {
 	PEVENT_ERRNO__SUCCESS			= 0,
+	PEVENT_ERRNO__FILTER_MATCH		= PEVENT_ERRNO__SUCCESS,
 
 	/*
 	 * Choose an arbitrary negative big number not to clash with standard
@@ -377,6 +408,12 @@ enum pevent_errno {
 };
 #undef _PE
 
+struct plugin_list;
+
+struct plugin_list *traceevent_load_plugins(struct pevent *pevent);
+void traceevent_unload_plugins(struct plugin_list *plugin_list,
+			       struct pevent *pevent);
+
 struct cmdline;
 struct cmdline_list;
 struct func_map;
@@ -522,6 +559,15 @@ __data2host8(struct pevent *pevent, unsigned long long data)
 	__data2host8(pevent, __val);				\
 })
 
+static inline int traceevent_host_bigendian(void)
+{
+	unsigned char str[] = { 0x1, 0x2, 0x3, 0x4 };
+	unsigned int val;
+
+	memcpy(&val, str, 4);
+	return val == 0x01020304;
+}
+
 /* taken from kernel/trace/trace.h */
 enum trace_flag_type {
 	TRACE_FLAG_IRQS_OFF		= 0x01,
@@ -547,7 +593,9 @@ int pevent_parse_header_page(struct pevent *pevent, char *buf, unsigned long siz
 
 enum pevent_errno pevent_parse_event(struct pevent *pevent, const char *buf,
 				     unsigned long size, const char *sys);
-enum pevent_errno pevent_parse_format(struct event_format **eventp, const char *buf,
+enum pevent_errno pevent_parse_format(struct pevent *pevent,
+				      struct event_format **eventp,
+				      const char *buf,
 				      unsigned long size, const char *sys);
 void pevent_free_format(struct event_format *event);
 
@@ -576,10 +624,15 @@ int pevent_print_func_field(struct trace_seq *s, const char *fmt,
 int pevent_register_event_handler(struct pevent *pevent, int id,
 				  const char *sys_name, const char *event_name,
 				  pevent_event_handler_func func, void *context);
+int pevent_unregister_event_handler(struct pevent *pevent, int id,
+				    const char *sys_name, const char *event_name,
+				    pevent_event_handler_func func, void *context);
 int pevent_register_print_function(struct pevent *pevent,
 				   pevent_func_handler func,
 				   enum pevent_func_arg_type ret_type,
 				   char *name, ...);
+int pevent_unregister_print_function(struct pevent *pevent,
+				     pevent_func_handler func, char *name);
 
 struct format_field *pevent_find_common_field(struct event_format *event, const char *name);
 struct format_field *pevent_find_field(struct event_format *event, const char *name);
@@ -811,18 +864,22 @@ struct filter_type {
 	struct filter_arg	*filter;
 };
 
+#define PEVENT_FILTER_ERROR_BUFSZ  1024
+
 struct event_filter {
 	struct pevent		*pevent;
 	int			filters;
 	struct filter_type	*event_filters;
+	char			error_buffer[PEVENT_FILTER_ERROR_BUFSZ];
 };
 
 struct event_filter *pevent_filter_alloc(struct pevent *pevent);
 
-#define FILTER_NONE		-2
-#define FILTER_NOEXIST		-1
-#define FILTER_MISS		0
-#define FILTER_MATCH		1
+/* for backward compatibility */
+#define FILTER_NONE		PEVENT_ERRNO__FILTER_NOT_FOUND
+#define FILTER_NOEXIST		PEVENT_ERRNO__NO_FILTER
+#define FILTER_MISS		PEVENT_ERRNO__FILTER_MISS
+#define FILTER_MATCH		PEVENT_ERRNO__FILTER_MATCH
 
 enum filter_trivial_type {
 	FILTER_TRIVIAL_FALSE,
@@ -830,20 +887,21 @@ enum filter_trivial_type {
 	FILTER_TRIVIAL_BOTH,
 };
 
-int pevent_filter_add_filter_str(struct event_filter *filter,
-				 const char *filter_str,
-				 char **error_str);
+enum pevent_errno pevent_filter_add_filter_str(struct event_filter *filter,
+					       const char *filter_str);
 
+enum pevent_errno pevent_filter_match(struct event_filter *filter,
+				      struct pevent_record *record);
 
-int pevent_filter_match(struct event_filter *filter,
-			struct pevent_record *record);
+int pevent_filter_strerror(struct event_filter *filter, enum pevent_errno err,
+			   char *buf, size_t buflen);
 
 int pevent_event_filtered(struct event_filter *filter,
 			  int event_id);
 
 void pevent_filter_reset(struct event_filter *filter);
 
-void pevent_filter_clear_trivial(struct event_filter *filter,
+int pevent_filter_clear_trivial(struct event_filter *filter,
 				 enum filter_trivial_type type);
 
 void pevent_filter_free(struct event_filter *filter);
diff --git a/tools/lib/traceevent/event-plugin.c b/tools/lib/traceevent/event-plugin.c
new file mode 100644
index 00000000000..0c8bf6780e4
--- /dev/null
+++ b/tools/lib/traceevent/event-plugin.c
@@ -0,0 +1,215 @@
+/*
+ * Copyright (C) 2009, 2010 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation;
+ * version 2.1 of the License (not later!)
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this program; if not,  see <http://www.gnu.org/licenses>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+
+#include <string.h>
+#include <dlfcn.h>
+#include <stdlib.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+#include <dirent.h>
+#include "event-parse.h"
+#include "event-utils.h"
+
+#define LOCAL_PLUGIN_DIR ".traceevent/plugins"
+
+struct plugin_list {
+	struct plugin_list	*next;
+	char			*name;
+	void			*handle;
+};
+
+static void
+load_plugin(struct pevent *pevent, const char *path,
+	    const char *file, void *data)
+{
+	struct plugin_list **plugin_list = data;
+	pevent_plugin_load_func func;
+	struct plugin_list *list;
+	const char *alias;
+	char *plugin;
+	void *handle;
+
+	plugin = malloc(strlen(path) + strlen(file) + 2);
+	if (!plugin) {
+		warning("could not allocate plugin memory\n");
+		return;
+	}
+
+	strcpy(plugin, path);
+	strcat(plugin, "/");
+	strcat(plugin, file);
+
+	handle = dlopen(plugin, RTLD_NOW | RTLD_GLOBAL);
+	if (!handle) {
+		warning("could not load plugin '%s'\n%s\n",
+			plugin, dlerror());
+		goto out_free;
+	}
+
+	alias = dlsym(handle, PEVENT_PLUGIN_ALIAS_NAME);
+	if (!alias)
+		alias = file;
+
+	func = dlsym(handle, PEVENT_PLUGIN_LOADER_NAME);
+	if (!func) {
+		warning("could not find func '%s' in plugin '%s'\n%s\n",
+			PEVENT_PLUGIN_LOADER_NAME, plugin, dlerror());
+		goto out_free;
+	}
+
+	list = malloc(sizeof(*list));
+	if (!list) {
+		warning("could not allocate plugin memory\n");
+		goto out_free;
+	}
+
+	list->next = *plugin_list;
+	list->handle = handle;
+	list->name = plugin;
+	*plugin_list = list;
+
+	pr_stat("registering plugin: %s", plugin);
+	func(pevent);
+	return;
+
+ out_free:
+	free(plugin);
+}
+
+static void
+load_plugins_dir(struct pevent *pevent, const char *suffix,
+		 const char *path,
+		 void (*load_plugin)(struct pevent *pevent,
+				     const char *path,
+				     const char *name,
+				     void *data),
+		 void *data)
+{
+	struct dirent *dent;
+	struct stat st;
+	DIR *dir;
+	int ret;
+
+	ret = stat(path, &st);
+	if (ret < 0)
+		return;
+
+	if (!S_ISDIR(st.st_mode))
+		return;
+
+	dir = opendir(path);
+	if (!dir)
+		return;
+
+	while ((dent = readdir(dir))) {
+		const char *name = dent->d_name;
+
+		if (strcmp(name, ".") == 0 ||
+		    strcmp(name, "..") == 0)
+			continue;
+
+		/* Only load plugins that end in suffix */
+		if (strcmp(name + (strlen(name) - strlen(suffix)), suffix) != 0)
+			continue;
+
+		load_plugin(pevent, path, name, data);
+	}
+
+	closedir(dir);
+}
+
+static void
+load_plugins(struct pevent *pevent, const char *suffix,
+	     void (*load_plugin)(struct pevent *pevent,
+				 const char *path,
+				 const char *name,
+				 void *data),
+	     void *data)
+{
+	char *home;
+	char *path;
+	char *envdir;
+
+	/*
+	 * If a system plugin directory was defined,
+	 * check that first.
+	 */
+#ifdef PLUGIN_DIR
+	load_plugins_dir(pevent, suffix, PLUGIN_DIR, load_plugin, data);
+#endif
+
+	/*
+	 * Next let the environment-set plugin directory
+	 * override the system defaults.
+	 */
+	envdir = getenv("TRACEEVENT_PLUGIN_DIR");
+	if (envdir)
+		load_plugins_dir(pevent, suffix, envdir, load_plugin, data);
+
+	/*
+	 * Now let the home directory override the environment
+	 * or system defaults.
+	 */
+	home = getenv("HOME");
+	if (!home)
+		return;
+
+	path = malloc(strlen(home) + strlen(LOCAL_PLUGIN_DIR) + 2);
+	if (!path) {
+		warning("could not allocate plugin memory\n");
+		return;
+	}
+
+	strcpy(path, home);
+	strcat(path, "/");
+	strcat(path, LOCAL_PLUGIN_DIR);
+
+	load_plugins_dir(pevent, suffix, path, load_plugin, data);
+
+	free(path);
+}
+
+struct plugin_list*
+traceevent_load_plugins(struct pevent *pevent)
+{
+	struct plugin_list *list = NULL;
+
+	load_plugins(pevent, ".so", load_plugin, &list);
+	return list;
+}
+
+void
+traceevent_unload_plugins(struct plugin_list *plugin_list, struct pevent *pevent)
+{
+	pevent_plugin_unload_func func;
+	struct plugin_list *list;
+
+	while (plugin_list) {
+		list = plugin_list;
+		plugin_list = list->next;
+		func = dlsym(list->handle, PEVENT_PLUGIN_UNLOADER_NAME);
+		if (func)
+			func(pevent);
+		dlclose(list->handle);
+		free(list->name);
+		free(list);
+	}
+}
diff --git a/tools/lib/traceevent/event-utils.h b/tools/lib/traceevent/event-utils.h
index e76c9acb92c..d1dc2170e40 100644
--- a/tools/lib/traceevent/event-utils.h
+++ b/tools/lib/traceevent/event-utils.h
@@ -23,18 +23,14 @@
 #include <ctype.h>
 
 /* Can be overridden */
-void die(const char *fmt, ...);
-void *malloc_or_die(unsigned int size);
 void warning(const char *fmt, ...);
 void pr_stat(const char *fmt, ...);
 void vpr_stat(const char *fmt, va_list ap);
 
 /* Always available */
-void __die(const char *fmt, ...);
 void __warning(const char *fmt, ...);
 void __pr_stat(const char *fmt, ...);
 
-void __vdie(const char *fmt, ...);
 void __vwarning(const char *fmt, ...);
 void __vpr_stat(const char *fmt, ...);
 
diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index 2500e75583f..b50234402fc 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -38,41 +38,31 @@ struct event_list {
 	struct event_format	*event;
 };
 
-#define MAX_ERR_STR_SIZE 256
-
-static void show_error(char **error_str, const char *fmt, ...)
+static void show_error(char *error_buf, const char *fmt, ...)
 {
 	unsigned long long index;
 	const char *input;
-	char *error;
 	va_list ap;
 	int len;
 	int i;
 
-	if (!error_str)
-		return;
-
 	input = pevent_get_input_buf();
 	index = pevent_get_input_buf_ptr();
 	len = input ? strlen(input) : 0;
 
-	error = malloc_or_die(MAX_ERR_STR_SIZE + (len*2) + 3);
-
 	if (len) {
-		strcpy(error, input);
-		error[len] = '\n';
+		strcpy(error_buf, input);
+		error_buf[len] = '\n';
 		for (i = 1; i < len && i < index; i++)
-			error[len+i] = ' ';
-		error[len + i] = '^';
-		error[len + i + 1] = '\n';
+			error_buf[len+i] = ' ';
+		error_buf[len + i] = '^';
+		error_buf[len + i + 1] = '\n';
 		len += i+2;
 	}
 
 	va_start(ap, fmt);
-	vsnprintf(error + len, MAX_ERR_STR_SIZE, fmt, ap);
+	vsnprintf(error_buf + len, PEVENT_FILTER_ERROR_BUFSZ - len, fmt, ap);
 	va_end(ap);
-
-	*error_str = error;
 }
 
 static void free_token(char *token)
@@ -95,7 +85,11 @@ static enum event_type read_token(char **tok)
 	    (strcmp(token, "=") == 0 || strcmp(token, "!") == 0) &&
 	    pevent_peek_char() == '~') {
 		/* append it */
-		*tok = malloc_or_die(3);
+		*tok = malloc(3);
+		if (*tok == NULL) {
+			free_token(token);
+			return EVENT_ERROR;
+		}
 		sprintf(*tok, "%c%c", *token, '~');
 		free_token(token);
 		/* Now remove the '~' from the buffer */
@@ -147,11 +141,13 @@ add_filter_type(struct event_filter *filter, int id)
 	if (filter_type)
 		return filter_type;
 
-	filter->event_filters =	realloc(filter->event_filters,
-					sizeof(*filter->event_filters) *
-					(filter->filters + 1));
-	if (!filter->event_filters)
-		die("Could not allocate filter");
+	filter_type = realloc(filter->event_filters,
+			      sizeof(*filter->event_filters) *
+			      (filter->filters + 1));
+	if (!filter_type)
+		return NULL;
+
+	filter->event_filters = filter_type;
 
 	for (i = 0; i < filter->filters; i++) {
 		if (filter->event_filters[i].event_id > id)
@@ -182,7 +178,10 @@ struct event_filter *pevent_filter_alloc(struct pevent *pevent)
 {
 	struct event_filter *filter;
 
-	filter = malloc_or_die(sizeof(*filter));
+	filter = malloc(sizeof(*filter));
+	if (filter == NULL)
+		return NULL;
+
 	memset(filter, 0, sizeof(*filter));
 	filter->pevent = pevent;
 	pevent_ref(pevent);
@@ -192,12 +191,7 @@ struct event_filter *pevent_filter_alloc(struct pevent *pevent)
 
 static struct filter_arg *allocate_arg(void)
 {
-	struct filter_arg *arg;
-
-	arg = malloc_or_die(sizeof(*arg));
-	memset(arg, 0, sizeof(*arg));
-
-	return arg;
+	return calloc(1, sizeof(struct filter_arg));
 }
 
 static void free_arg(struct filter_arg *arg)
@@ -242,15 +236,19 @@ static void free_arg(struct filter_arg *arg)
 	free(arg);
 }
 
-static void add_event(struct event_list **events,
+static int add_event(struct event_list **events,
 		      struct event_format *event)
 {
 	struct event_list *list;
 
-	list = malloc_or_die(sizeof(*list));
+	list = malloc(sizeof(*list));
+	if (list == NULL)
+		return -1;
+
 	list->next = *events;
 	*events = list;
 	list->event = event;
+	return 0;
 }
 
 static int event_match(struct event_format *event,
@@ -265,7 +263,7 @@ static int event_match(struct event_format *event,
 		!regexec(ereg, event->name, 0, NULL, 0);
 }
 
-static int
+static enum pevent_errno
 find_event(struct pevent *pevent, struct event_list **events,
 	   char *sys_name, char *event_name)
 {
@@ -273,6 +271,7 @@ find_event(struct pevent *pevent, struct event_list **events,
 	regex_t ereg;
 	regex_t sreg;
 	int match = 0;
+	int fail = 0;
 	char *reg;
 	int ret;
 	int i;
@@ -283,23 +282,31 @@ find_event(struct pevent *pevent, struct event_list **events,
 		sys_name = NULL;
 	}
 
-	reg = malloc_or_die(strlen(event_name) + 3);
+	reg = malloc(strlen(event_name) + 3);
+	if (reg == NULL)
+		return PEVENT_ERRNO__MEM_ALLOC_FAILED;
+
 	sprintf(reg, "^%s$", event_name);
 
 	ret = regcomp(&ereg, reg, REG_ICASE|REG_NOSUB);
 	free(reg);
 
 	if (ret)
-		return -1;
+		return PEVENT_ERRNO__INVALID_EVENT_NAME;
 
 	if (sys_name) {
-		reg = malloc_or_die(strlen(sys_name) + 3);
+		reg = malloc(strlen(sys_name) + 3);
+		if (reg == NULL) {
+			regfree(&ereg);
+			return PEVENT_ERRNO__MEM_ALLOC_FAILED;
+		}
+
 		sprintf(reg, "^%s$", sys_name);
 		ret = regcomp(&sreg, reg, REG_ICASE|REG_NOSUB);
 		free(reg);
 		if (ret) {
 			regfree(&ereg);
-			return -1;
+			return PEVENT_ERRNO__INVALID_EVENT_NAME;
 		}
 	}
 
@@ -307,7 +314,10 @@ find_event(struct pevent *pevent, struct event_list **events,
 		event = pevent->events[i];
 		if (event_match(event, sys_name ? &sreg : NULL, &ereg)) {
 			match = 1;
-			add_event(events, event);
+			if (add_event(events, event) < 0) {
+				fail = 1;
+				break;
+			}
 		}
 	}
 
@@ -316,7 +326,9 @@ find_event(struct pevent *pevent, struct event_list **events,
 		regfree(&sreg);
 
 	if (!match)
-		return -1;
+		return PEVENT_ERRNO__EVENT_NOT_FOUND;
+	if (fail)
+		return PEVENT_ERRNO__MEM_ALLOC_FAILED;
 
 	return 0;
 }
@@ -332,14 +344,18 @@ static void free_events(struct event_list *events)
 	}
 }
 
-static struct filter_arg *
+static enum pevent_errno
 create_arg_item(struct event_format *event, const char *token,
-		enum event_type type, char **error_str)
+		enum event_type type, struct filter_arg **parg, char *error_str)
 {
 	struct format_field *field;
 	struct filter_arg *arg;
 
 	arg = allocate_arg();
+	if (arg == NULL) {
+		show_error(error_str, "failed to allocate filter arg");
+		return PEVENT_ERRNO__MEM_ALLOC_FAILED;
+	}
 
 	switch (type) {
 
@@ -349,8 +365,11 @@ create_arg_item(struct event_format *event, const char *token,
 		arg->value.type =
 			type == EVENT_DQUOTE ? FILTER_STRING : FILTER_CHAR;
 		arg->value.str = strdup(token);
-		if (!arg->value.str)
-			die("malloc string");
+		if (!arg->value.str) {
+			free_arg(arg);
+			show_error(error_str, "failed to allocate string filter arg");
+			return PEVENT_ERRNO__MEM_ALLOC_FAILED;
+		}
 		break;
 	case EVENT_ITEM:
 		/* if it is a number, then convert it */
@@ -377,11 +396,11 @@ create_arg_item(struct event_format *event, const char *token,
 		break;
 	default:
 		free_arg(arg);
-		show_error(error_str, "expected a value but found %s",
-			   token);
-		return NULL;
+		show_error(error_str, "expected a value but found %s", token);
+		return PEVENT_ERRNO__UNEXPECTED_TYPE;
 	}
-	return arg;
+	*parg = arg;
+	return 0;
 }
 
 static struct filter_arg *
@@ -390,6 +409,9 @@ create_arg_op(enum filter_op_type btype)
 	struct filter_arg *arg;
 
 	arg = allocate_arg();
+	if (!arg)
+		return NULL;
+
 	arg->type = FILTER_ARG_OP;
 	arg->op.type = btype;
 
@@ -402,6 +424,9 @@ create_arg_exp(enum filter_exp_type etype)
 	struct filter_arg *arg;
 
 	arg = allocate_arg();
+	if (!arg)
+		return NULL;
+
 	arg->type = FILTER_ARG_EXP;
 	arg->op.type = etype;
 
@@ -414,6 +439,9 @@ create_arg_cmp(enum filter_exp_type etype)
 	struct filter_arg *arg;
 
 	arg = allocate_arg();
+	if (!arg)
+		return NULL;
+
 	/* Use NUM and change if necessary */
 	arg->type = FILTER_ARG_NUM;
 	arg->op.type = etype;
@@ -421,8 +449,8 @@ create_arg_cmp(enum filter_exp_type etype)
 	return arg;
 }
 
-static int add_right(struct filter_arg *op, struct filter_arg *arg,
-		     char **error_str)
+static enum pevent_errno
+add_right(struct filter_arg *op, struct filter_arg *arg, char *error_str)
 {
 	struct filter_arg *left;
 	char *str;
@@ -453,9 +481,8 @@ static int add_right(struct filter_arg *op, struct filter_arg *arg,
 		case FILTER_ARG_FIELD:
 			break;
 		default:
-			show_error(error_str,
-				   "Illegal rvalue");
-			return -1;
+			show_error(error_str, "Illegal rvalue");
+			return PEVENT_ERRNO__ILLEGAL_RVALUE;
 		}
 
 		/*
@@ -502,7 +529,7 @@ static int add_right(struct filter_arg *op, struct filter_arg *arg,
 			if (left->type != FILTER_ARG_FIELD) {
 				show_error(error_str,
 					   "Illegal lvalue for string comparison");
-				return -1;
+				return PEVENT_ERRNO__ILLEGAL_LVALUE;
 			}
 
 			/* Make sure this is a valid string compare */
@@ -521,25 +548,31 @@ static int add_right(struct filter_arg *op, struct filter_arg *arg,
 					show_error(error_str,
 						   "RegEx '%s' did not compute",
 						   str);
-					return -1;
+					return PEVENT_ERRNO__INVALID_REGEX;
 				}
 				break;
 			default:
 				show_error(error_str,
 					   "Illegal comparison for string");
-				return -1;
+				return PEVENT_ERRNO__ILLEGAL_STRING_CMP;
 			}
 
 			op->type = FILTER_ARG_STR;
 			op->str.type = op_type;
 			op->str.field = left->field.field;
 			op->str.val = strdup(str);
-			if (!op->str.val)
-				die("malloc string");
+			if (!op->str.val) {
+				show_error(error_str, "Failed to allocate string filter");
+				return PEVENT_ERRNO__MEM_ALLOC_FAILED;
+			}
 			/*
 			 * Need a buffer to copy data for tests
 			 */
-			op->str.buffer = malloc_or_die(op->str.field->size + 1);
+			op->str.buffer = malloc(op->str.field->size + 1);
+			if (!op->str.buffer) {
+				show_error(error_str, "Failed to allocate string filter");
+				return PEVENT_ERRNO__MEM_ALLOC_FAILED;
+			}
 			/* Null terminate this buffer */
 			op->str.buffer[op->str.field->size] = 0;
 
@@ -557,7 +590,7 @@ static int add_right(struct filter_arg *op, struct filter_arg *arg,
 			case FILTER_CMP_NOT_REGEX:
 				show_error(error_str,
 					   "Op not allowed with integers");
-				return -1;
+				return PEVENT_ERRNO__ILLEGAL_INTEGER_CMP;
 
 			default:
 				break;
@@ -577,9 +610,8 @@ static int add_right(struct filter_arg *op, struct filter_arg *arg,
 	return 0;
 
  out_fail:
-	show_error(error_str,
-		   "Syntax error");
-	return -1;
+	show_error(error_str, "Syntax error");
+	return PEVENT_ERRNO__SYNTAX_ERROR;
 }
 
 static struct filter_arg *
@@ -592,7 +624,7 @@ rotate_op_right(struct filter_arg *a, struct filter_arg *b)
 	return arg;
 }
 
-static int add_left(struct filter_arg *op, struct filter_arg *arg)
+static enum pevent_errno add_left(struct filter_arg *op, struct filter_arg *arg)
 {
 	switch (op->type) {
 	case FILTER_ARG_EXP:
@@ -611,11 +643,11 @@ static int add_left(struct filter_arg *op, struct filter_arg *arg)
 		/* left arg of compares must be a field */
 		if (arg->type != FILTER_ARG_FIELD &&
 		    arg->type != FILTER_ARG_BOOLEAN)
-			return -1;
+			return PEVENT_ERRNO__INVALID_ARG_TYPE;
 		op->num.left = arg;
 		break;
 	default:
-		return -1;
+		return PEVENT_ERRNO__INVALID_ARG_TYPE;
 	}
 	return 0;
 }
@@ -728,15 +760,18 @@ enum filter_vals {
 	FILTER_VAL_TRUE,
 };
 
-void reparent_op_arg(struct filter_arg *parent, struct filter_arg *old_child,
-		  struct filter_arg *arg)
+static enum pevent_errno
+reparent_op_arg(struct filter_arg *parent, struct filter_arg *old_child,
+		struct filter_arg *arg, char *error_str)
 {
 	struct filter_arg *other_child;
 	struct filter_arg **ptr;
 
 	if (parent->type != FILTER_ARG_OP &&
-	    arg->type != FILTER_ARG_OP)
-		die("can not reparent other than OP");
+	    arg->type != FILTER_ARG_OP) {
+		show_error(error_str, "can not reparent other than OP");
+		return PEVENT_ERRNO__REPARENT_NOT_OP;
+	}
 
 	/* Get the sibling */
 	if (old_child->op.right == arg) {
@@ -745,8 +780,10 @@ void reparent_op_arg(struct filter_arg *parent, struct filter_arg *old_child,
 	} else if (old_child->op.left == arg) {
 		ptr = &old_child->op.left;
 		other_child = old_child->op.right;
-	} else
-		die("Error in reparent op, find other child");
+	} else {
+		show_error(error_str, "Error in reparent op, find other child");
+		return PEVENT_ERRNO__REPARENT_FAILED;
+	}
 
 	/* Detach arg from old_child */
 	*ptr = NULL;
@@ -757,23 +794,29 @@ void reparent_op_arg(struct filter_arg *parent, struct filter_arg *old_child,
 		*parent = *arg;
 		/* Free arg without recussion */
 		free(arg);
-		return;
+		return 0;
 	}
 
 	if (parent->op.right == old_child)
 		ptr = &parent->op.right;
 	else if (parent->op.left == old_child)
 		ptr = &parent->op.left;
-	else
-		die("Error in reparent op");
+	else {
+		show_error(error_str, "Error in reparent op");
+		return PEVENT_ERRNO__REPARENT_FAILED;
+	}
+
 	*ptr = arg;
 
 	free_arg(old_child);
+	return 0;
 }
 
-enum filter_vals test_arg(struct filter_arg *parent, struct filter_arg *arg)
+/* Returns either filter_vals (success) or pevent_errno (failfure) */
+static int test_arg(struct filter_arg *parent, struct filter_arg *arg,
+		    char *error_str)
 {
-	enum filter_vals lval, rval;
+	int lval, rval;
 
 	switch (arg->type) {
 
@@ -788,63 +831,68 @@ enum filter_vals test_arg(struct filter_arg *parent, struct filter_arg *arg)
 		return FILTER_VAL_NORM;
 
 	case FILTER_ARG_EXP:
-		lval = test_arg(arg, arg->exp.left);
+		lval = test_arg(arg, arg->exp.left, error_str);
 		if (lval != FILTER_VAL_NORM)
 			return lval;
-		rval = test_arg(arg, arg->exp.right);
+		rval = test_arg(arg, arg->exp.right, error_str);
 		if (rval != FILTER_VAL_NORM)
 			return rval;
 		return FILTER_VAL_NORM;
 
 	case FILTER_ARG_NUM:
-		lval = test_arg(arg, arg->num.left);
+		lval = test_arg(arg, arg->num.left, error_str);
 		if (lval != FILTER_VAL_NORM)
 			return lval;
-		rval = test_arg(arg, arg->num.right);
+		rval = test_arg(arg, arg->num.right, error_str);
 		if (rval != FILTER_VAL_NORM)
 			return rval;
 		return FILTER_VAL_NORM;
 
 	case FILTER_ARG_OP:
 		if (arg->op.type != FILTER_OP_NOT) {
-			lval = test_arg(arg, arg->op.left);
+			lval = test_arg(arg, arg->op.left, error_str);
 			switch (lval) {
 			case FILTER_VAL_NORM:
 				break;
 			case FILTER_VAL_TRUE:
 				if (arg->op.type == FILTER_OP_OR)
 					return FILTER_VAL_TRUE;
-				rval = test_arg(arg, arg->op.right);
+				rval = test_arg(arg, arg->op.right, error_str);
 				if (rval != FILTER_VAL_NORM)
 					return rval;
 
-				reparent_op_arg(parent, arg, arg->op.right);
-				return FILTER_VAL_NORM;
+				return reparent_op_arg(parent, arg, arg->op.right,
+						       error_str);
 
 			case FILTER_VAL_FALSE:
 				if (arg->op.type == FILTER_OP_AND)
 					return FILTER_VAL_FALSE;
-				rval = test_arg(arg, arg->op.right);
+				rval = test_arg(arg, arg->op.right, error_str);
 				if (rval != FILTER_VAL_NORM)
 					return rval;
 
-				reparent_op_arg(parent, arg, arg->op.right);
-				return FILTER_VAL_NORM;
+				return reparent_op_arg(parent, arg, arg->op.right,
+						       error_str);
+
+			default:
+				return lval;
 			}
 		}
 
-		rval = test_arg(arg, arg->op.right);
+		rval = test_arg(arg, arg->op.right, error_str);
 		switch (rval) {
 		case FILTER_VAL_NORM:
+		default:
 			break;
+
 		case FILTER_VAL_TRUE:
 			if (arg->op.type == FILTER_OP_OR)
 				return FILTER_VAL_TRUE;
 			if (arg->op.type == FILTER_OP_NOT)
 				return FILTER_VAL_FALSE;
 
-			reparent_op_arg(parent, arg, arg->op.left);
-			return FILTER_VAL_NORM;
+			return reparent_op_arg(parent, arg, arg->op.left,
+					       error_str);
 
 		case FILTER_VAL_FALSE:
 			if (arg->op.type == FILTER_OP_AND)
@@ -852,41 +900,56 @@ enum filter_vals test_arg(struct filter_arg *parent, struct filter_arg *arg)
 			if (arg->op.type == FILTER_OP_NOT)
 				return FILTER_VAL_TRUE;
 
-			reparent_op_arg(parent, arg, arg->op.left);
-			return FILTER_VAL_NORM;
+			return reparent_op_arg(parent, arg, arg->op.left,
+					       error_str);
 		}
 
-		return FILTER_VAL_NORM;
+		return rval;
 	default:
-		die("bad arg in filter tree");
+		show_error(error_str, "bad arg in filter tree");
+		return PEVENT_ERRNO__BAD_FILTER_ARG;
 	}
 	return FILTER_VAL_NORM;
 }
 
 /* Remove any unknown event fields */
-static struct filter_arg *collapse_tree(struct filter_arg *arg)
+static int collapse_tree(struct filter_arg *arg,
+			 struct filter_arg **arg_collapsed, char *error_str)
 {
-	enum filter_vals ret;
+	int ret;
 
-	ret = test_arg(arg, arg);
+	ret = test_arg(arg, arg, error_str);
 	switch (ret) {
 	case FILTER_VAL_NORM:
-		return arg;
+		break;
 
 	case FILTER_VAL_TRUE:
 	case FILTER_VAL_FALSE:
 		free_arg(arg);
 		arg = allocate_arg();
-		arg->type = FILTER_ARG_BOOLEAN;
-		arg->boolean.value = ret == FILTER_VAL_TRUE;
+		if (arg) {
+			arg->type = FILTER_ARG_BOOLEAN;
+			arg->boolean.value = ret == FILTER_VAL_TRUE;
+		} else {
+			show_error(error_str, "Failed to allocate filter arg");
+			ret = PEVENT_ERRNO__MEM_ALLOC_FAILED;
+		}
+		break;
+
+	default:
+		/* test_arg() already set the error_str */
+		free_arg(arg);
+		arg = NULL;
+		break;
 	}
 
-	return arg;
+	*arg_collapsed = arg;
+	return ret;
 }
 
-static int
+static enum pevent_errno
 process_filter(struct event_format *event, struct filter_arg **parg,
-	       char **error_str, int not)
+	       char *error_str, int not)
 {
 	enum event_type type;
 	char *token = NULL;
@@ -898,7 +961,7 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 	enum filter_op_type btype;
 	enum filter_exp_type etype;
 	enum filter_cmp_type ctype;
-	int ret;
+	enum pevent_errno ret;
 
 	*parg = NULL;
 
@@ -909,8 +972,8 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 		case EVENT_SQUOTE:
 		case EVENT_DQUOTE:
 		case EVENT_ITEM:
-			arg = create_arg_item(event, token, type, error_str);
-			if (!arg)
+			ret = create_arg_item(event, token, type, &arg, error_str);
+			if (ret < 0)
 				goto fail;
 			if (!left_item)
 				left_item = arg;
@@ -923,20 +986,20 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 				if (not) {
 					arg = NULL;
 					if (current_op)
-						goto fail_print;
+						goto fail_syntax;
 					free(token);
 					*parg = current_exp;
 					return 0;
 				}
 			} else
-				goto fail_print;
+				goto fail_syntax;
 			arg = NULL;
 			break;
 
 		case EVENT_DELIM:
 			if (*token == ',') {
-				show_error(error_str,
-					   "Illegal token ','");
+				show_error(error_str, "Illegal token ','");
+				ret = PEVENT_ERRNO__ILLEGAL_TOKEN;
 				goto fail;
 			}
 
@@ -944,19 +1007,23 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 				if (left_item) {
 					show_error(error_str,
 						   "Open paren can not come after item");
+					ret = PEVENT_ERRNO__INVALID_PAREN;
 					goto fail;
 				}
 				if (current_exp) {
 					show_error(error_str,
 						   "Open paren can not come after expression");
+					ret = PEVENT_ERRNO__INVALID_PAREN;
 					goto fail;
 				}
 
 				ret = process_filter(event, &arg, error_str, 0);
-				if (ret != 1) {
-					if (ret == 0)
+				if (ret != PEVENT_ERRNO__UNBALANCED_PAREN) {
+					if (ret == 0) {
 						show_error(error_str,
 							   "Unbalanced number of '('");
+						ret = PEVENT_ERRNO__UNBALANCED_PAREN;
+					}
 					goto fail;
 				}
 				ret = 0;
@@ -964,7 +1031,7 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 				/* A not wants just one expression */
 				if (not) {
 					if (current_op)
-						goto fail_print;
+						goto fail_syntax;
 					*parg = arg;
 					return 0;
 				}
@@ -979,19 +1046,19 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 
 			} else { /* ')' */
 				if (!current_op && !current_exp)
-					goto fail_print;
+					goto fail_syntax;
 
 				/* Make sure everything is finished at this level */
 				if (current_exp && !check_op_done(current_exp))
-					goto fail_print;
+					goto fail_syntax;
 				if (current_op && !check_op_done(current_op))
-					goto fail_print;
+					goto fail_syntax;
 
 				if (current_op)
 					*parg = current_op;
 				else
 					*parg = current_exp;
-				return 1;
+				return PEVENT_ERRNO__UNBALANCED_PAREN;
 			}
 			break;
 
@@ -1003,21 +1070,22 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 			case OP_BOOL:
 				/* Logic ops need a left expression */
 				if (!current_exp && !current_op)
-					goto fail_print;
+					goto fail_syntax;
 				/* fall through */
 			case OP_NOT:
 				/* logic only processes ops and exp */
 				if (left_item)
-					goto fail_print;
+					goto fail_syntax;
 				break;
 			case OP_EXP:
 			case OP_CMP:
 				if (!left_item)
-					goto fail_print;
+					goto fail_syntax;
 				break;
 			case OP_NONE:
 				show_error(error_str,
 					   "Unknown op token %s", token);
+				ret = PEVENT_ERRNO__UNKNOWN_TOKEN;
 				goto fail;
 			}
 
@@ -1025,6 +1093,8 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 			switch (op_type) {
 			case OP_BOOL:
 				arg = create_arg_op(btype);
+				if (arg == NULL)
+					goto fail_alloc;
 				if (current_op)
 					ret = add_left(arg, current_op);
 				else
@@ -1035,6 +1105,8 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 
 			case OP_NOT:
 				arg = create_arg_op(btype);
+				if (arg == NULL)
+					goto fail_alloc;
 				if (current_op)
 					ret = add_right(current_op, arg, error_str);
 				if (ret < 0)
@@ -1054,6 +1126,8 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 					arg = create_arg_exp(etype);
 				else
 					arg = create_arg_cmp(ctype);
+				if (arg == NULL)
+					goto fail_alloc;
 
 				if (current_op)
 					ret = add_right(current_op, arg, error_str);
@@ -1062,7 +1136,7 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 				ret = add_left(arg, left_item);
 				if (ret < 0) {
 					arg = NULL;
-					goto fail_print;
+					goto fail_syntax;
 				}
 				current_exp = arg;
 				break;
@@ -1071,57 +1145,64 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 			}
 			arg = NULL;
 			if (ret < 0)
-				goto fail_print;
+				goto fail_syntax;
 			break;
 		case EVENT_NONE:
 			break;
+		case EVENT_ERROR:
+			goto fail_alloc;
 		default:
-			goto fail_print;
+			goto fail_syntax;
 		}
 	} while (type != EVENT_NONE);
 
 	if (!current_op && !current_exp)
-		goto fail_print;
+		goto fail_syntax;
 
 	if (!current_op)
 		current_op = current_exp;
 
-	current_op = collapse_tree(current_op);
+	ret = collapse_tree(current_op, parg, error_str);
+	if (ret < 0)
+		goto fail;
 
 	*parg = current_op;
 
 	return 0;
 
- fail_print:
+ fail_alloc:
+	show_error(error_str, "failed to allocate filter arg");
+	ret = PEVENT_ERRNO__MEM_ALLOC_FAILED;
+	goto fail;
+ fail_syntax:
 	show_error(error_str, "Syntax error");
+	ret = PEVENT_ERRNO__SYNTAX_ERROR;
  fail:
 	free_arg(current_op);
 	free_arg(current_exp);
 	free_arg(arg);
 	free(token);
-	return -1;
+	return ret;
 }
 
-static int
+static enum pevent_errno
 process_event(struct event_format *event, const char *filter_str,
-	      struct filter_arg **parg, char **error_str)
+	      struct filter_arg **parg, char *error_str)
 {
 	int ret;
 
 	pevent_buffer_init(filter_str, strlen(filter_str));
 
 	ret = process_filter(event, parg, error_str, 0);
-	if (ret == 1) {
-		show_error(error_str,
-			   "Unbalanced number of ')'");
-		return -1;
-	}
 	if (ret < 0)
 		return ret;
 
 	/* If parg is NULL, then make it into FALSE */
 	if (!*parg) {
 		*parg = allocate_arg();
+		if (*parg == NULL)
+			return PEVENT_ERRNO__MEM_ALLOC_FAILED;
+
 		(*parg)->type = FILTER_ARG_BOOLEAN;
 		(*parg)->boolean.value = FILTER_FALSE;
 	}
@@ -1129,13 +1210,13 @@ process_event(struct event_format *event, const char *filter_str,
 	return 0;
 }
 
-static int filter_event(struct event_filter *filter,
-			struct event_format *event,
-			const char *filter_str, char **error_str)
+static enum pevent_errno
+filter_event(struct event_filter *filter, struct event_format *event,
+	     const char *filter_str, char *error_str)
 {
 	struct filter_type *filter_type;
 	struct filter_arg *arg;
-	int ret;
+	enum pevent_errno ret;
 
 	if (filter_str) {
 		ret = process_event(event, filter_str, &arg, error_str);
@@ -1145,11 +1226,17 @@ static int filter_event(struct event_filter *filter,
 	} else {
 		/* just add a TRUE arg */
 		arg = allocate_arg();
+		if (arg == NULL)
+			return PEVENT_ERRNO__MEM_ALLOC_FAILED;
+
 		arg->type = FILTER_ARG_BOOLEAN;
 		arg->boolean.value = FILTER_TRUE;
 	}
 
 	filter_type = add_filter_type(filter, event->id);
+	if (filter_type == NULL)
+		return PEVENT_ERRNO__MEM_ALLOC_FAILED;
+
 	if (filter_type->filter)
 		free_arg(filter_type->filter);
 	filter_type->filter = arg;
@@ -1157,22 +1244,24 @@ static int filter_event(struct event_filter *filter,
 	return 0;
 }
 
+static void filter_init_error_buf(struct event_filter *filter)
+{
+	/* clear buffer to reset show error */
+	pevent_buffer_init("", 0);
+	filter->error_buffer[0] = '\0';
+}
+
 /**
  * pevent_filter_add_filter_str - add a new filter
  * @filter: the event filter to add to
  * @filter_str: the filter string that contains the filter
- * @error_str: string containing reason for failed filter
- *
- * Returns 0 if the filter was successfully added
- *   -1 if there was an error.
  *
- * On error, if @error_str points to a string pointer,
- * it is set to the reason that the filter failed.
- * This string must be freed with "free".
+ * Returns 0 if the filter was successfully added or a
+ * negative error code.  Use pevent_filter_strerror() to see
+ * actual error message in case of error.
  */
-int pevent_filter_add_filter_str(struct event_filter *filter,
-				 const char *filter_str,
-				 char **error_str)
+enum pevent_errno pevent_filter_add_filter_str(struct event_filter *filter,
+					       const char *filter_str)
 {
 	struct pevent *pevent = filter->pevent;
 	struct event_list *event;
@@ -1183,15 +1272,11 @@ int pevent_filter_add_filter_str(struct event_filter *filter,
 	char *event_name = NULL;
 	char *sys_name = NULL;
 	char *sp;
-	int rtn = 0;
+	enum pevent_errno rtn = 0; /* PEVENT_ERRNO__SUCCESS */
 	int len;
 	int ret;
 
-	/* clear buffer to reset show error */
-	pevent_buffer_init("", 0);
-
-	if (error_str)
-		*error_str = NULL;
+	filter_init_error_buf(filter);
 
 	filter_start = strchr(filter_str, ':');
 	if (filter_start)
@@ -1199,7 +1284,6 @@ int pevent_filter_add_filter_str(struct event_filter *filter,
 	else
 		len = strlen(filter_str);
 
-
 	do {
 		next_event = strchr(filter_str, ',');
 		if (next_event &&
@@ -1210,7 +1294,12 @@ int pevent_filter_add_filter_str(struct event_filter *filter,
 		else
 			len = strlen(filter_str);
 
-		this_event = malloc_or_die(len + 1);
+		this_event = malloc(len + 1);
+		if (this_event == NULL) {
+			/* This can only happen when events is NULL, but still */
+			free_events(events);
+			return PEVENT_ERRNO__MEM_ALLOC_FAILED;
+		}
 		memcpy(this_event, filter_str, len);
 		this_event[len] = 0;
 
@@ -1223,27 +1312,18 @@ int pevent_filter_add_filter_str(struct event_filter *filter,
 		event_name = strtok_r(NULL, "/", &sp);
 
 		if (!sys_name) {
-			show_error(error_str, "No filter found");
 			/* This can only happen when events is NULL, but still */
 			free_events(events);
 			free(this_event);
-			return -1;
+			return PEVENT_ERRNO__FILTER_NOT_FOUND;
 		}
 
 		/* Find this event */
 		ret = find_event(pevent, &events, strim(sys_name), strim(event_name));
 		if (ret < 0) {
-			if (event_name)
-				show_error(error_str,
-					   "No event found under '%s.%s'",
-					   sys_name, event_name);
-			else
-				show_error(error_str,
-					   "No event found under '%s'",
-					   sys_name);
 			free_events(events);
 			free(this_event);
-			return -1;
+			return ret;
 		}
 		free(this_event);
 	} while (filter_str);
@@ -1255,7 +1335,7 @@ int pevent_filter_add_filter_str(struct event_filter *filter,
 	/* filter starts here */
 	for (event = events; event; event = event->next) {
 		ret = filter_event(filter, event->event, filter_start,
-				   error_str);
+				   filter->error_buffer);
 		/* Failures are returned if a parse error happened */
 		if (ret < 0)
 			rtn = ret;
@@ -1263,8 +1343,10 @@ int pevent_filter_add_filter_str(struct event_filter *filter,
 		if (ret >= 0 && pevent->test_filters) {
 			char *test;
 			test = pevent_filter_make_string(filter, event->event->id);
-			printf(" '%s: %s'\n", event->event->name, test);
-			free(test);
+			if (test) {
+				printf(" '%s: %s'\n", event->event->name, test);
+				free(test);
+			}
 		}
 	}
 
@@ -1282,6 +1364,32 @@ static void free_filter_type(struct filter_type *filter_type)
 }
 
 /**
+ * pevent_filter_strerror - fill error message in a buffer
+ * @filter: the event filter contains error
+ * @err: the error code
+ * @buf: the buffer to be filled in
+ * @buflen: the size of the buffer
+ *
+ * Returns 0 if message was filled successfully, -1 if error
+ */
+int pevent_filter_strerror(struct event_filter *filter, enum pevent_errno err,
+			   char *buf, size_t buflen)
+{
+	if (err <= __PEVENT_ERRNO__START || err >= __PEVENT_ERRNO__END)
+		return -1;
+
+	if (strlen(filter->error_buffer) > 0) {
+		size_t len = snprintf(buf, buflen, "%s", filter->error_buffer);
+
+		if (len > buflen)
+			return -1;
+		return 0;
+	}
+
+	return pevent_strerror(filter->pevent, err, buf, buflen);
+}
+
+/**
  * pevent_filter_remove_event - remove a filter for an event
  * @filter: the event filter to remove from
  * @event_id: the event to remove a filter for
@@ -1374,6 +1482,9 @@ static int copy_filter_type(struct event_filter *filter,
 	if (strcmp(str, "TRUE") == 0 || strcmp(str, "FALSE") == 0) {
 		/* Add trivial event */
 		arg = allocate_arg();
+		if (arg == NULL)
+			return -1;
+
 		arg->type = FILTER_ARG_BOOLEAN;
 		if (strcmp(str, "TRUE") == 0)
 			arg->boolean.value = 1;
@@ -1381,6 +1492,9 @@ static int copy_filter_type(struct event_filter *filter,
 			arg->boolean.value = 0;
 
 		filter_type = add_filter_type(filter, event->id);
+		if (filter_type == NULL)
+			return -1;
+
 		filter_type->filter = arg;
 
 		free(str);
@@ -1482,8 +1596,10 @@ int pevent_update_trivial(struct event_filter *dest, struct event_filter *source
  * @type: remove only true, false, or both
  *
  * Removes filters that only contain a TRUE or FALES boolean arg.
+ *
+ * Returns 0 on success and -1 if there was a problem.
  */
-void pevent_filter_clear_trivial(struct event_filter *filter,
+int pevent_filter_clear_trivial(struct event_filter *filter,
 				 enum filter_trivial_type type)
 {
 	struct filter_type *filter_type;
@@ -1492,13 +1608,15 @@ void pevent_filter_clear_trivial(struct event_filter *filter,
 	int i;
 
 	if (!filter->filters)
-		return;
+		return 0;
 
 	/*
 	 * Two steps, first get all ids with trivial filters.
 	 *  then remove those ids.
 	 */
 	for (i = 0; i < filter->filters; i++) {
+		int *new_ids;
+
 		filter_type = &filter->event_filters[i];
 		if (filter_type->filter->type != FILTER_ARG_BOOLEAN)
 			continue;
@@ -1513,19 +1631,24 @@ void pevent_filter_clear_trivial(struct event_filter *filter,
 			break;
 		}
 
-		ids = realloc(ids, sizeof(*ids) * (count + 1));
-		if (!ids)
-			die("Can't allocate ids");
+		new_ids = realloc(ids, sizeof(*ids) * (count + 1));
+		if (!new_ids) {
+			free(ids);
+			return -1;
+		}
+
+		ids = new_ids;
 		ids[count++] = filter_type->event_id;
 	}
 
 	if (!count)
-		return;
+		return 0;
 
 	for (i = 0; i < count; i++)
 		pevent_filter_remove_event(filter, ids[i]);
 
 	free(ids);
+	return 0;
 }
 
 /**
@@ -1565,8 +1688,8 @@ int pevent_filter_event_has_trivial(struct event_filter *filter,
 	}
 }
 
-static int test_filter(struct event_format *event,
-		       struct filter_arg *arg, struct pevent_record *record);
+static int test_filter(struct event_format *event, struct filter_arg *arg,
+		       struct pevent_record *record, enum pevent_errno *err);
 
 static const char *
 get_comm(struct event_format *event, struct pevent_record *record)
@@ -1612,15 +1735,24 @@ get_value(struct event_format *event,
 }
 
 static unsigned long long
-get_arg_value(struct event_format *event, struct filter_arg *arg, struct pevent_record *record);
+get_arg_value(struct event_format *event, struct filter_arg *arg,
+	      struct pevent_record *record, enum pevent_errno *err);
 
 static unsigned long long
-get_exp_value(struct event_format *event, struct filter_arg *arg, struct pevent_record *record)
+get_exp_value(struct event_format *event, struct filter_arg *arg,
+	      struct pevent_record *record, enum pevent_errno *err)
 {
 	unsigned long long lval, rval;
 
-	lval = get_arg_value(event, arg->exp.left, record);
-	rval = get_arg_value(event, arg->exp.right, record);
+	lval = get_arg_value(event, arg->exp.left, record, err);
+	rval = get_arg_value(event, arg->exp.right, record, err);
+
+	if (*err) {
+		/*
+		 * There was an error, no need to process anymore.
+		 */
+		return 0;
+	}
 
 	switch (arg->exp.type) {
 	case FILTER_EXP_ADD:
@@ -1655,39 +1787,51 @@ get_exp_value(struct event_format *event, struct filter_arg *arg, struct pevent_
 
 	case FILTER_EXP_NOT:
 	default:
-		die("error in exp");
+		if (!*err)
+			*err = PEVENT_ERRNO__INVALID_EXP_TYPE;
 	}
 	return 0;
 }
 
 static unsigned long long
-get_arg_value(struct event_format *event, struct filter_arg *arg, struct pevent_record *record)
+get_arg_value(struct event_format *event, struct filter_arg *arg,
+	      struct pevent_record *record, enum pevent_errno *err)
 {
 	switch (arg->type) {
 	case FILTER_ARG_FIELD:
 		return get_value(event, arg->field.field, record);
 
 	case FILTER_ARG_VALUE:
-		if (arg->value.type != FILTER_NUMBER)
-			die("must have number field!");
+		if (arg->value.type != FILTER_NUMBER) {
+			if (!*err)
+				*err = PEVENT_ERRNO__NOT_A_NUMBER;
+		}
 		return arg->value.val;
 
 	case FILTER_ARG_EXP:
-		return get_exp_value(event, arg, record);
+		return get_exp_value(event, arg, record, err);
 
 	default:
-		die("oops in filter");
+		if (!*err)
+			*err = PEVENT_ERRNO__INVALID_ARG_TYPE;
 	}
 	return 0;
 }
 
-static int test_num(struct event_format *event,
-		    struct filter_arg *arg, struct pevent_record *record)
+static int test_num(struct event_format *event, struct filter_arg *arg,
+		    struct pevent_record *record, enum pevent_errno *err)
 {
 	unsigned long long lval, rval;
 
-	lval = get_arg_value(event, arg->num.left, record);
-	rval = get_arg_value(event, arg->num.right, record);
+	lval = get_arg_value(event, arg->num.left, record, err);
+	rval = get_arg_value(event, arg->num.right, record, err);
+
+	if (*err) {
+		/*
+		 * There was an error, no need to process anymore.
+		 */
+		return 0;
+	}
 
 	switch (arg->num.type) {
 	case FILTER_CMP_EQ:
@@ -1709,7 +1853,8 @@ static int test_num(struct event_format *event,
 		return lval <= rval;
 
 	default:
-		/* ?? */
+		if (!*err)
+			*err = PEVENT_ERRNO__ILLEGAL_INTEGER_CMP;
 		return 0;
 	}
 }
@@ -1756,8 +1901,8 @@ static const char *get_field_str(struct filter_arg *arg, struct pevent_record *r
 	return val;
 }
 
-static int test_str(struct event_format *event,
-		    struct filter_arg *arg, struct pevent_record *record)
+static int test_str(struct event_format *event, struct filter_arg *arg,
+		    struct pevent_record *record, enum pevent_errno *err)
 {
 	const char *val;
 
@@ -1781,48 +1926,57 @@ static int test_str(struct event_format *event,
 		return regexec(&arg->str.reg, val, 0, NULL, 0);
 
 	default:
-		/* ?? */
+		if (!*err)
+			*err = PEVENT_ERRNO__ILLEGAL_STRING_CMP;
 		return 0;
 	}
 }
 
-static int test_op(struct event_format *event,
-		   struct filter_arg *arg, struct pevent_record *record)
+static int test_op(struct event_format *event, struct filter_arg *arg,
+		   struct pevent_record *record, enum pevent_errno *err)
 {
 	switch (arg->op.type) {
 	case FILTER_OP_AND:
-		return test_filter(event, arg->op.left, record) &&
-			test_filter(event, arg->op.right, record);
+		return test_filter(event, arg->op.left, record, err) &&
+			test_filter(event, arg->op.right, record, err);
 
 	case FILTER_OP_OR:
-		return test_filter(event, arg->op.left, record) ||
-			test_filter(event, arg->op.right, record);
+		return test_filter(event, arg->op.left, record, err) ||
+			test_filter(event, arg->op.right, record, err);
 
 	case FILTER_OP_NOT:
-		return !test_filter(event, arg->op.right, record);
+		return !test_filter(event, arg->op.right, record, err);
 
 	default:
-		/* ?? */
+		if (!*err)
+			*err = PEVENT_ERRNO__INVALID_OP_TYPE;
 		return 0;
 	}
 }
 
-static int test_filter(struct event_format *event,
-		       struct filter_arg *arg, struct pevent_record *record)
+static int test_filter(struct event_format *event, struct filter_arg *arg,
+		       struct pevent_record *record, enum pevent_errno *err)
 {
+	if (*err) {
+		/*
+		 * There was an error, no need to process anymore.
+		 */
+		return 0;
+	}
+
 	switch (arg->type) {
 	case FILTER_ARG_BOOLEAN:
 		/* easy case */
 		return arg->boolean.value;
 
 	case FILTER_ARG_OP:
-		return test_op(event, arg, record);
+		return test_op(event, arg, record, err);
 
 	case FILTER_ARG_NUM:
-		return test_num(event, arg, record);
+		return test_num(event, arg, record, err);
 
 	case FILTER_ARG_STR:
-		return test_str(event, arg, record);
+		return test_str(event, arg, record, err);
 
 	case FILTER_ARG_EXP:
 	case FILTER_ARG_VALUE:
@@ -1831,11 +1985,11 @@ static int test_filter(struct event_format *event,
 		 * Expressions, fields and values evaluate
 		 * to true if they return non zero
 		 */
-		return !!get_arg_value(event, arg, record);
+		return !!get_arg_value(event, arg, record, err);
 
 	default:
-		die("oops!");
-		/* ?? */
+		if (!*err)
+			*err = PEVENT_ERRNO__INVALID_ARG_TYPE;
 		return 0;
 	}
 }
@@ -1848,8 +2002,7 @@ static int test_filter(struct event_format *event,
  * Returns 1 if filter found for @event_id
  *   otherwise 0;
  */
-int pevent_event_filtered(struct event_filter *filter,
-			  int event_id)
+int pevent_event_filtered(struct event_filter *filter, int event_id)
 {
 	struct filter_type *filter_type;
 
@@ -1866,31 +2019,38 @@ int pevent_event_filtered(struct event_filter *filter,
  * @filter: filter struct with filter information
  * @record: the record to test against the filter
  *
- * Returns:
- *  1 - filter found for event and @record matches
- *  0 - filter found for event and @record does not match
- * -1 - no filter found for @record's event
- * -2 - if no filters exist
+ * Returns: match result or error code (prefixed with PEVENT_ERRNO__)
+ * FILTER_MATCH - filter found for event and @record matches
+ * FILTER_MISS  - filter found for event and @record does not match
+ * FILTER_NOT_FOUND - no filter found for @record's event
+ * NO_FILTER - if no filters exist
+ * otherwise - error occurred during test
  */
-int pevent_filter_match(struct event_filter *filter,
-			struct pevent_record *record)
+enum pevent_errno pevent_filter_match(struct event_filter *filter,
+				      struct pevent_record *record)
 {
 	struct pevent *pevent = filter->pevent;
 	struct filter_type *filter_type;
 	int event_id;
+	int ret;
+	enum pevent_errno err = 0;
+
+	filter_init_error_buf(filter);
 
 	if (!filter->filters)
-		return FILTER_NONE;
+		return PEVENT_ERRNO__NO_FILTER;
 
 	event_id = pevent_data_type(pevent, record);
 
 	filter_type = find_filter_type(filter, event_id);
-
 	if (!filter_type)
-		return FILTER_NOEXIST;
+		return PEVENT_ERRNO__FILTER_NOT_FOUND;
+
+	ret = test_filter(filter_type->event, filter_type->filter, record, &err);
+	if (err)
+		return err;
 
-	return test_filter(filter_type->event, filter_type->filter, record) ?
-		FILTER_MATCH : FILTER_MISS;
+	return ret ? PEVENT_ERRNO__FILTER_MATCH : PEVENT_ERRNO__FILTER_MISS;
 }
 
 static char *op_to_str(struct event_filter *filter, struct filter_arg *arg)
@@ -1902,7 +2062,6 @@ static char *op_to_str(struct event_filter *filter, struct filter_arg *arg)
 	int left_val = -1;
 	int right_val = -1;
 	int val;
-	int len;
 
 	switch (arg->op.type) {
 	case FILTER_OP_AND:
@@ -1949,11 +2108,7 @@ static char *op_to_str(struct event_filter *filter, struct filter_arg *arg)
 				default:
 					break;
 				}
-				str = malloc_or_die(6);
-				if (val)
-					strcpy(str, "TRUE");
-				else
-					strcpy(str, "FALSE");
+				asprintf(&str, val ? "TRUE" : "FALSE");
 				break;
 			}
 		}
@@ -1971,10 +2126,7 @@ static char *op_to_str(struct event_filter *filter, struct filter_arg *arg)
 			break;
 		}
 
-		len = strlen(left) + strlen(right) + strlen(op) + 10;
-		str = malloc_or_die(len);
-		snprintf(str, len, "(%s) %s (%s)",
-			 left, op, right);
+		asprintf(&str, "(%s) %s (%s)", left, op, right);
 		break;
 
 	case FILTER_OP_NOT:
@@ -1990,16 +2142,10 @@ static char *op_to_str(struct event_filter *filter, struct filter_arg *arg)
 			right_val = 0;
 		if (right_val >= 0) {
 			/* just return the opposite */
-			str = malloc_or_die(6);
-			if (right_val)
-				strcpy(str, "FALSE");
-			else
-				strcpy(str, "TRUE");
+			asprintf(&str, right_val ? "FALSE" : "TRUE");
 			break;
 		}
-		len = strlen(right) + strlen(op) + 3;
-		str = malloc_or_die(len);
-		snprintf(str, len, "%s(%s)", op, right);
+		asprintf(&str, "%s(%s)", op, right);
 		break;
 
 	default:
@@ -2013,11 +2159,9 @@ static char *op_to_str(struct event_filter *filter, struct filter_arg *arg)
 
 static char *val_to_str(struct event_filter *filter, struct filter_arg *arg)
 {
-	char *str;
-
-	str = malloc_or_die(30);
+	char *str = NULL;
 
-	snprintf(str, 30, "%lld", arg->value.val);
+	asprintf(&str, "%lld", arg->value.val);
 
 	return str;
 }
@@ -2033,7 +2177,6 @@ static char *exp_to_str(struct event_filter *filter, struct filter_arg *arg)
 	char *rstr;
 	char *op;
 	char *str = NULL;
-	int len;
 
 	lstr = arg_to_str(filter, arg->exp.left);
 	rstr = arg_to_str(filter, arg->exp.right);
@@ -2072,12 +2215,11 @@ static char *exp_to_str(struct event_filter *filter, struct filter_arg *arg)
 		op = "^";
 		break;
 	default:
-		die("oops in exp");
+		op = "[ERROR IN EXPRESSION TYPE]";
+		break;
 	}
 
-	len = strlen(op) + strlen(lstr) + strlen(rstr) + 4;
-	str = malloc_or_die(len);
-	snprintf(str, len, "%s %s %s", lstr, op, rstr);
+	asprintf(&str, "%s %s %s", lstr, op, rstr);
 out:
 	free(lstr);
 	free(rstr);
@@ -2091,7 +2233,6 @@ static char *num_to_str(struct event_filter *filter, struct filter_arg *arg)
 	char *rstr;
 	char *str = NULL;
 	char *op = NULL;
-	int len;
 
 	lstr = arg_to_str(filter, arg->num.left);
 	rstr = arg_to_str(filter, arg->num.right);
@@ -2122,10 +2263,7 @@ static char *num_to_str(struct event_filter *filter, struct filter_arg *arg)
 		if (!op)
 			op = "<=";
 
-		len = strlen(lstr) + strlen(op) + strlen(rstr) + 4;
-		str = malloc_or_die(len);
-		sprintf(str, "%s %s %s", lstr, op, rstr);
-
+		asprintf(&str, "%s %s %s", lstr, op, rstr);
 		break;
 
 	default:
@@ -2143,7 +2281,6 @@ static char *str_to_str(struct event_filter *filter, struct filter_arg *arg)
 {
 	char *str = NULL;
 	char *op = NULL;
-	int len;
 
 	switch (arg->str.type) {
 	case FILTER_CMP_MATCH:
@@ -2161,12 +2298,8 @@ static char *str_to_str(struct event_filter *filter, struct filter_arg *arg)
 		if (!op)
 			op = "!~";
 
-		len = strlen(arg->str.field->name) + strlen(op) +
-			strlen(arg->str.val) + 6;
-		str = malloc_or_die(len);
-		snprintf(str, len, "%s %s \"%s\"",
-			 arg->str.field->name,
-			 op, arg->str.val);
+		asprintf(&str, "%s %s \"%s\"",
+			 arg->str.field->name, op, arg->str.val);
 		break;
 
 	default:
@@ -2178,15 +2311,11 @@ static char *str_to_str(struct event_filter *filter, struct filter_arg *arg)
 
 static char *arg_to_str(struct event_filter *filter, struct filter_arg *arg)
 {
-	char *str;
+	char *str = NULL;
 
 	switch (arg->type) {
 	case FILTER_ARG_BOOLEAN:
-		str = malloc_or_die(6);
-		if (arg->boolean.value)
-			strcpy(str, "TRUE");
-		else
-			strcpy(str, "FALSE");
+		asprintf(&str, arg->boolean.value ? "TRUE" : "FALSE");
 		return str;
 
 	case FILTER_ARG_OP:
@@ -2221,7 +2350,7 @@ static char *arg_to_str(struct event_filter *filter, struct filter_arg *arg)
  *
  * Returns a string that displays the filter contents.
  *  This string must be freed with free(str).
- *  NULL is returned if no filter is found.
+ *  NULL is returned if no filter is found or allocation failed.
  */
 char *
 pevent_filter_make_string(struct event_filter *filter, int event_id)
diff --git a/tools/lib/traceevent/parse-utils.c b/tools/lib/traceevent/parse-utils.c
index bba701cf10e..eda07fa31dc 100644
--- a/tools/lib/traceevent/parse-utils.c
+++ b/tools/lib/traceevent/parse-utils.c
@@ -25,40 +25,6 @@
 
 #define __weak __attribute__((weak))
 
-void __vdie(const char *fmt, va_list ap)
-{
-	int ret = errno;
-
-	if (errno)
-		perror("trace-cmd");
-	else
-		ret = -1;
-
-	fprintf(stderr, "  ");
-	vfprintf(stderr, fmt, ap);
-
-	fprintf(stderr, "\n");
-	exit(ret);
-}
-
-void __die(const char *fmt, ...)
-{
-	va_list ap;
-
-	va_start(ap, fmt);
-	__vdie(fmt, ap);
-	va_end(ap);
-}
-
-void __weak die(const char *fmt, ...)
-{
-	va_list ap;
-
-	va_start(ap, fmt);
-	__vdie(fmt, ap);
-	va_end(ap);
-}
-
 void __vwarning(const char *fmt, va_list ap)
 {
 	if (errno)
@@ -117,13 +83,3 @@ void __weak pr_stat(const char *fmt, ...)
 	__vpr_stat(fmt, ap);
 	va_end(ap);
 }
-
-void __weak *malloc_or_die(unsigned int size)
-{
-	void *data;
-
-	data = malloc(size);
-	if (!data)
-		die("malloc");
-	return data;
-}
diff --git a/tools/lib/traceevent/plugin_cfg80211.c b/tools/lib/traceevent/plugin_cfg80211.c
new file mode 100644
index 00000000000..c066b25905f
--- /dev/null
+++ b/tools/lib/traceevent/plugin_cfg80211.c
@@ -0,0 +1,30 @@
+#include <stdio.h>
+#include <string.h>
+#include <inttypes.h>
+#include <endian.h>
+#include "event-parse.h"
+
+static unsigned long long
+process___le16_to_cpup(struct trace_seq *s,
+		       unsigned long long *args)
+{
+	uint16_t *val = (uint16_t *) (unsigned long) args[0];
+	return val ? (long long) le16toh(*val) : 0;
+}
+
+int PEVENT_PLUGIN_LOADER(struct pevent *pevent)
+{
+	pevent_register_print_function(pevent,
+				       process___le16_to_cpup,
+				       PEVENT_FUNC_ARG_INT,
+				       "__le16_to_cpup",
+				       PEVENT_FUNC_ARG_PTR,
+				       PEVENT_FUNC_ARG_VOID);
+	return 0;
+}
+
+void PEVENT_PLUGIN_UNLOADER(struct pevent *pevent)
+{
+	pevent_unregister_print_function(pevent, process___le16_to_cpup,
+					 "__le16_to_cpup");
+}
diff --git a/tools/lib/traceevent/plugin_function.c b/tools/lib/traceevent/plugin_function.c
new file mode 100644
index 00000000000..80ba4ff1fe8
--- /dev/null
+++ b/tools/lib/traceevent/plugin_function.c
@@ -0,0 +1,163 @@
+/*
+ * Copyright (C) 2009, 2010 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation;
+ * version 2.1 of the License (not later!)
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this program; if not,  see <http://www.gnu.org/licenses>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include "event-parse.h"
+#include "event-utils.h"
+
+static struct func_stack {
+	int size;
+	char **stack;
+} *fstack;
+
+static int cpus = -1;
+
+#define STK_BLK 10
+
+static void add_child(struct func_stack *stack, const char *child, int pos)
+{
+	int i;
+
+	if (!child)
+		return;
+
+	if (pos < stack->size)
+		free(stack->stack[pos]);
+	else {
+		char **ptr;
+
+		ptr = realloc(stack->stack, sizeof(char *) *
+			      (stack->size + STK_BLK));
+		if (!ptr) {
+			warning("could not allocate plugin memory\n");
+			return;
+		}
+
+		stack->stack = ptr;
+
+		for (i = stack->size; i < stack->size + STK_BLK; i++)
+			stack->stack[i] = NULL;
+		stack->size += STK_BLK;
+	}
+
+	stack->stack[pos] = strdup(child);
+}
+
+static int add_and_get_index(const char *parent, const char *child, int cpu)
+{
+	int i;
+
+	if (cpu < 0)
+		return 0;
+
+	if (cpu > cpus) {
+		struct func_stack *ptr;
+
+		ptr = realloc(fstack, sizeof(*fstack) * (cpu + 1));
+		if (!ptr) {
+			warning("could not allocate plugin memory\n");
+			return 0;
+		}
+
+		fstack = ptr;
+
+		/* Account for holes in the cpu count */
+		for (i = cpus + 1; i <= cpu; i++)
+			memset(&fstack[i], 0, sizeof(fstack[i]));
+		cpus = cpu;
+	}
+
+	for (i = 0; i < fstack[cpu].size && fstack[cpu].stack[i]; i++) {
+		if (strcmp(parent, fstack[cpu].stack[i]) == 0) {
+			add_child(&fstack[cpu], child, i+1);
+			return i;
+		}
+	}
+
+	/* Not found */
+	add_child(&fstack[cpu], parent, 0);
+	add_child(&fstack[cpu], child, 1);
+	return 0;
+}
+
+static int function_handler(struct trace_seq *s, struct pevent_record *record,
+			    struct event_format *event, void *context)
+{
+	struct pevent *pevent = event->pevent;
+	unsigned long long function;
+	unsigned long long pfunction;
+	const char *func;
+	const char *parent;
+	int index;
+
+	if (pevent_get_field_val(s, event, "ip", record, &function, 1))
+		return trace_seq_putc(s, '!');
+
+	func = pevent_find_function(pevent, function);
+
+	if (pevent_get_field_val(s, event, "parent_ip", record, &pfunction, 1))
+		return trace_seq_putc(s, '!');
+
+	parent = pevent_find_function(pevent, pfunction);
+
+	index = add_and_get_index(parent, func, record->cpu);
+
+	trace_seq_printf(s, "%*s", index*3, "");
+
+	if (func)
+		trace_seq_printf(s, "%s", func);
+	else
+		trace_seq_printf(s, "0x%llx", function);
+
+	trace_seq_printf(s, " <-- ");
+	if (parent)
+		trace_seq_printf(s, "%s", parent);
+	else
+		trace_seq_printf(s, "0x%llx", pfunction);
+
+	return 0;
+}
+
+int PEVENT_PLUGIN_LOADER(struct pevent *pevent)
+{
+	pevent_register_event_handler(pevent, -1, "ftrace", "function",
+				      function_handler, NULL);
+	return 0;
+}
+
+void PEVENT_PLUGIN_UNLOADER(struct pevent *pevent)
+{
+	int i, x;
+
+	pevent_unregister_event_handler(pevent, -1, "ftrace", "function",
+					function_handler, NULL);
+
+	for (i = 0; i <= cpus; i++) {
+		for (x = 0; x < fstack[i].size && fstack[i].stack[x]; x++)
+			free(fstack[i].stack[x]);
+		free(fstack[i].stack);
+	}
+
+	free(fstack);
+	fstack = NULL;
+	cpus = -1;
+}
diff --git a/tools/lib/traceevent/plugin_hrtimer.c b/tools/lib/traceevent/plugin_hrtimer.c
new file mode 100644
index 00000000000..12bf14cc115
--- /dev/null
+++ b/tools/lib/traceevent/plugin_hrtimer.c
@@ -0,0 +1,88 @@
+/*
+ * Copyright (C) 2009 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
+ * Copyright (C) 2009 Johannes Berg <johannes@sipsolutions.net>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation;
+ * version 2.1 of the License (not later!)
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this program; if not,  see <http://www.gnu.org/licenses>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include "event-parse.h"
+
+static int timer_expire_handler(struct trace_seq *s,
+				struct pevent_record *record,
+				struct event_format *event, void *context)
+{
+	trace_seq_printf(s, "hrtimer=");
+
+	if (pevent_print_num_field(s, "0x%llx", event, "timer",
+				   record, 0) == -1)
+		pevent_print_num_field(s, "0x%llx", event, "hrtimer",
+				       record, 1);
+
+	trace_seq_printf(s, " now=");
+
+	pevent_print_num_field(s, "%llu", event, "now", record, 1);
+
+	pevent_print_func_field(s, " function=%s", event, "function",
+				record, 0);
+	return 0;
+}
+
+static int timer_start_handler(struct trace_seq *s,
+			       struct pevent_record *record,
+			       struct event_format *event, void *context)
+{
+	trace_seq_printf(s, "hrtimer=");
+
+	if (pevent_print_num_field(s, "0x%llx", event, "timer",
+				   record, 0) == -1)
+		pevent_print_num_field(s, "0x%llx", event, "hrtimer",
+				       record, 1);
+
+	pevent_print_func_field(s, " function=%s", event, "function",
+				record, 0);
+
+	trace_seq_printf(s, " expires=");
+	pevent_print_num_field(s, "%llu", event, "expires", record, 1);
+
+	trace_seq_printf(s, " softexpires=");
+	pevent_print_num_field(s, "%llu", event, "softexpires", record, 1);
+	return 0;
+}
+
+int PEVENT_PLUGIN_LOADER(struct pevent *pevent)
+{
+	pevent_register_event_handler(pevent, -1,
+				      "timer", "hrtimer_expire_entry",
+				      timer_expire_handler, NULL);
+
+	pevent_register_event_handler(pevent, -1, "timer", "hrtimer_start",
+				      timer_start_handler, NULL);
+	return 0;
+}
+
+void PEVENT_PLUGIN_UNLOADER(struct pevent *pevent)
+{
+	pevent_unregister_event_handler(pevent, -1,
+					"timer", "hrtimer_expire_entry",
+					timer_expire_handler, NULL);
+
+	pevent_unregister_event_handler(pevent, -1, "timer", "hrtimer_start",
+					timer_start_handler, NULL);
+}
diff --git a/tools/lib/traceevent/plugin_jbd2.c b/tools/lib/traceevent/plugin_jbd2.c
new file mode 100644
index 00000000000..0db714c721b
--- /dev/null
+++ b/tools/lib/traceevent/plugin_jbd2.c
@@ -0,0 +1,77 @@
+/*
+ * Copyright (C) 2010 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation;
+ * version 2.1 of the License (not later!)
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this program; if not,  see <http://www.gnu.org/licenses>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include "event-parse.h"
+
+#define MINORBITS	20
+#define MINORMASK	((1U << MINORBITS) - 1)
+
+#define MAJOR(dev)	((unsigned int) ((dev) >> MINORBITS))
+#define MINOR(dev)	((unsigned int) ((dev) & MINORMASK))
+
+static unsigned long long
+process_jbd2_dev_to_name(struct trace_seq *s,
+			 unsigned long long *args)
+{
+	unsigned int dev = args[0];
+
+	trace_seq_printf(s, "%d:%d", MAJOR(dev), MINOR(dev));
+	return 0;
+}
+
+static unsigned long long
+process_jiffies_to_msecs(struct trace_seq *s,
+			 unsigned long long *args)
+{
+	unsigned long long jiffies = args[0];
+
+	trace_seq_printf(s, "%lld", jiffies);
+	return jiffies;
+}
+
+int PEVENT_PLUGIN_LOADER(struct pevent *pevent)
+{
+	pevent_register_print_function(pevent,
+				       process_jbd2_dev_to_name,
+				       PEVENT_FUNC_ARG_STRING,
+				       "jbd2_dev_to_name",
+				       PEVENT_FUNC_ARG_INT,
+				       PEVENT_FUNC_ARG_VOID);
+
+	pevent_register_print_function(pevent,
+				       process_jiffies_to_msecs,
+				       PEVENT_FUNC_ARG_LONG,
+				       "jiffies_to_msecs",
+				       PEVENT_FUNC_ARG_LONG,
+				       PEVENT_FUNC_ARG_VOID);
+	return 0;
+}
+
+void PEVENT_PLUGIN_UNLOADER(struct pevent *pevent)
+{
+	pevent_unregister_print_function(pevent, process_jbd2_dev_to_name,
+					 "jbd2_dev_to_name");
+
+	pevent_unregister_print_function(pevent, process_jiffies_to_msecs,
+					 "jiffies_to_msecs");
+}
diff --git a/tools/lib/traceevent/plugin_kmem.c b/tools/lib/traceevent/plugin_kmem.c
new file mode 100644
index 00000000000..70650ff48d7
--- /dev/null
+++ b/tools/lib/traceevent/plugin_kmem.c
@@ -0,0 +1,94 @@
+/*
+ * Copyright (C) 2009 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation;
+ * version 2.1 of the License (not later!)
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this program; if not,  see <http://www.gnu.org/licenses>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include "event-parse.h"
+
+static int call_site_handler(struct trace_seq *s, struct pevent_record *record,
+			     struct event_format *event, void *context)
+{
+	struct format_field *field;
+	unsigned long long val, addr;
+	void *data = record->data;
+	const char *func;
+
+	field = pevent_find_field(event, "call_site");
+	if (!field)
+		return 1;
+
+	if (pevent_read_number_field(field, data, &val))
+		return 1;
+
+	func = pevent_find_function(event->pevent, val);
+	if (!func)
+		return 1;
+
+	addr = pevent_find_function_address(event->pevent, val);
+
+	trace_seq_printf(s, "(%s+0x%x) ", func, (int)(val - addr));
+	return 1;
+}
+
+int PEVENT_PLUGIN_LOADER(struct pevent *pevent)
+{
+	pevent_register_event_handler(pevent, -1, "kmem", "kfree",
+				      call_site_handler, NULL);
+
+	pevent_register_event_handler(pevent, -1, "kmem", "kmalloc",
+				      call_site_handler, NULL);
+
+	pevent_register_event_handler(pevent, -1, "kmem", "kmalloc_node",
+				      call_site_handler, NULL);
+
+	pevent_register_event_handler(pevent, -1, "kmem", "kmem_cache_alloc",
+				      call_site_handler, NULL);
+
+	pevent_register_event_handler(pevent, -1, "kmem",
+				      "kmem_cache_alloc_node",
+				      call_site_handler, NULL);
+
+	pevent_register_event_handler(pevent, -1, "kmem", "kmem_cache_free",
+				      call_site_handler, NULL);
+	return 0;
+}
+
+void PEVENT_PLUGIN_UNLOADER(struct pevent *pevent)
+{
+	pevent_unregister_event_handler(pevent, -1, "kmem", "kfree",
+					call_site_handler, NULL);
+
+	pevent_unregister_event_handler(pevent, -1, "kmem", "kmalloc",
+					call_site_handler, NULL);
+
+	pevent_unregister_event_handler(pevent, -1, "kmem", "kmalloc_node",
+					call_site_handler, NULL);
+
+	pevent_unregister_event_handler(pevent, -1, "kmem", "kmem_cache_alloc",
+					call_site_handler, NULL);
+
+	pevent_unregister_event_handler(pevent, -1, "kmem",
+					"kmem_cache_alloc_node",
+					call_site_handler, NULL);
+
+	pevent_unregister_event_handler(pevent, -1, "kmem", "kmem_cache_free",
+					call_site_handler, NULL);
+}
diff --git a/tools/lib/traceevent/plugin_kvm.c b/tools/lib/traceevent/plugin_kvm.c
new file mode 100644
index 00000000000..9e0e8c61b43
--- /dev/null
+++ b/tools/lib/traceevent/plugin_kvm.c
@@ -0,0 +1,465 @@
+/*
+ * Copyright (C) 2009 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation;
+ * version 2.1 of the License (not later!)
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this program; if not,  see <http://www.gnu.org/licenses>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <stdint.h>
+
+#include "event-parse.h"
+
+#ifdef HAVE_UDIS86
+
+#include <udis86.h>
+
+static ud_t ud;
+
+static void init_disassembler(void)
+{
+	ud_init(&ud);
+	ud_set_syntax(&ud, UD_SYN_ATT);
+}
+
+static const char *disassemble(unsigned char *insn, int len, uint64_t rip,
+			       int cr0_pe, int eflags_vm,
+			       int cs_d, int cs_l)
+{
+	int mode;
+
+	if (!cr0_pe)
+		mode = 16;
+	else if (eflags_vm)
+		mode = 16;
+	else if (cs_l)
+		mode = 64;
+	else if (cs_d)
+		mode = 32;
+	else
+		mode = 16;
+
+	ud_set_pc(&ud, rip);
+	ud_set_mode(&ud, mode);
+	ud_set_input_buffer(&ud, insn, len);
+	ud_disassemble(&ud);
+	return ud_insn_asm(&ud);
+}
+
+#else
+
+static void init_disassembler(void)
+{
+}
+
+static const char *disassemble(unsigned char *insn, int len, uint64_t rip,
+			       int cr0_pe, int eflags_vm,
+			       int cs_d, int cs_l)
+{
+	static char out[15*3+1];
+	int i;
+
+	for (i = 0; i < len; ++i)
+		sprintf(out + i * 3, "%02x ", insn[i]);
+	out[len*3-1] = '\0';
+	return out;
+}
+
+#endif
+
+
+#define VMX_EXIT_REASONS			\
+	_ER(EXCEPTION_NMI,	 0)		\
+	_ER(EXTERNAL_INTERRUPT,	 1)		\
+	_ER(TRIPLE_FAULT,	 2)		\
+	_ER(PENDING_INTERRUPT,	 7)		\
+	_ER(NMI_WINDOW,		 8)		\
+	_ER(TASK_SWITCH,	 9)		\
+	_ER(CPUID,		 10)		\
+	_ER(HLT,		 12)		\
+	_ER(INVD,		 13)		\
+	_ER(INVLPG,		 14)		\
+	_ER(RDPMC,		 15)		\
+	_ER(RDTSC,		 16)		\
+	_ER(VMCALL,		 18)		\
+	_ER(VMCLEAR,		 19)		\
+	_ER(VMLAUNCH,		 20)		\
+	_ER(VMPTRLD,		 21)		\
+	_ER(VMPTRST,		 22)		\
+	_ER(VMREAD,		 23)		\
+	_ER(VMRESUME,		 24)		\
+	_ER(VMWRITE,		 25)		\
+	_ER(VMOFF,		 26)		\
+	_ER(VMON,		 27)		\
+	_ER(CR_ACCESS,		 28)		\
+	_ER(DR_ACCESS,		 29)		\
+	_ER(IO_INSTRUCTION,	 30)		\
+	_ER(MSR_READ,		 31)		\
+	_ER(MSR_WRITE,		 32)		\
+	_ER(MWAIT_INSTRUCTION,	 36)		\
+	_ER(MONITOR_INSTRUCTION, 39)		\
+	_ER(PAUSE_INSTRUCTION,	 40)		\
+	_ER(MCE_DURING_VMENTRY,	 41)		\
+	_ER(TPR_BELOW_THRESHOLD, 43)		\
+	_ER(APIC_ACCESS,	 44)		\
+	_ER(EOI_INDUCED,	 45)		\
+	_ER(EPT_VIOLATION,	 48)		\
+	_ER(EPT_MISCONFIG,	 49)		\
+	_ER(INVEPT,		 50)		\
+	_ER(PREEMPTION_TIMER,	 52)		\
+	_ER(WBINVD,		 54)		\
+	_ER(XSETBV,		 55)		\
+	_ER(APIC_WRITE,		 56)		\
+	_ER(INVPCID,		 58)
+
+#define SVM_EXIT_REASONS \
+	_ER(EXIT_READ_CR0,	0x000)		\
+	_ER(EXIT_READ_CR3,	0x003)		\
+	_ER(EXIT_READ_CR4,	0x004)		\
+	_ER(EXIT_READ_CR8,	0x008)		\
+	_ER(EXIT_WRITE_CR0,	0x010)		\
+	_ER(EXIT_WRITE_CR3,	0x013)		\
+	_ER(EXIT_WRITE_CR4,	0x014)		\
+	_ER(EXIT_WRITE_CR8,	0x018)		\
+	_ER(EXIT_READ_DR0,	0x020)		\
+	_ER(EXIT_READ_DR1,	0x021)		\
+	_ER(EXIT_READ_DR2,	0x022)		\
+	_ER(EXIT_READ_DR3,	0x023)		\
+	_ER(EXIT_READ_DR4,	0x024)		\
+	_ER(EXIT_READ_DR5,	0x025)		\
+	_ER(EXIT_READ_DR6,	0x026)		\
+	_ER(EXIT_READ_DR7,	0x027)		\
+	_ER(EXIT_WRITE_DR0,	0x030)		\
+	_ER(EXIT_WRITE_DR1,	0x031)		\
+	_ER(EXIT_WRITE_DR2,	0x032)		\
+	_ER(EXIT_WRITE_DR3,	0x033)		\
+	_ER(EXIT_WRITE_DR4,	0x034)		\
+	_ER(EXIT_WRITE_DR5,	0x035)		\
+	_ER(EXIT_WRITE_DR6,	0x036)		\
+	_ER(EXIT_WRITE_DR7,	0x037)		\
+	_ER(EXIT_EXCP_BASE,     0x040)		\
+	_ER(EXIT_INTR,		0x060)		\
+	_ER(EXIT_NMI,		0x061)		\
+	_ER(EXIT_SMI,		0x062)		\
+	_ER(EXIT_INIT,		0x063)		\
+	_ER(EXIT_VINTR,		0x064)		\
+	_ER(EXIT_CR0_SEL_WRITE,	0x065)		\
+	_ER(EXIT_IDTR_READ,	0x066)		\
+	_ER(EXIT_GDTR_READ,	0x067)		\
+	_ER(EXIT_LDTR_READ,	0x068)		\
+	_ER(EXIT_TR_READ,	0x069)		\
+	_ER(EXIT_IDTR_WRITE,	0x06a)		\
+	_ER(EXIT_GDTR_WRITE,	0x06b)		\
+	_ER(EXIT_LDTR_WRITE,	0x06c)		\
+	_ER(EXIT_TR_WRITE,	0x06d)		\
+	_ER(EXIT_RDTSC,		0x06e)		\
+	_ER(EXIT_RDPMC,		0x06f)		\
+	_ER(EXIT_PUSHF,		0x070)		\
+	_ER(EXIT_POPF,		0x071)		\
+	_ER(EXIT_CPUID,		0x072)		\
+	_ER(EXIT_RSM,		0x073)		\
+	_ER(EXIT_IRET,		0x074)		\
+	_ER(EXIT_SWINT,		0x075)		\
+	_ER(EXIT_INVD,		0x076)		\
+	_ER(EXIT_PAUSE,		0x077)		\
+	_ER(EXIT_HLT,		0x078)		\
+	_ER(EXIT_INVLPG,	0x079)		\
+	_ER(EXIT_INVLPGA,	0x07a)		\
+	_ER(EXIT_IOIO,		0x07b)		\
+	_ER(EXIT_MSR,		0x07c)		\
+	_ER(EXIT_TASK_SWITCH,	0x07d)		\
+	_ER(EXIT_FERR_FREEZE,	0x07e)		\
+	_ER(EXIT_SHUTDOWN,	0x07f)		\
+	_ER(EXIT_VMRUN,		0x080)		\
+	_ER(EXIT_VMMCALL,	0x081)		\
+	_ER(EXIT_VMLOAD,	0x082)		\
+	_ER(EXIT_VMSAVE,	0x083)		\
+	_ER(EXIT_STGI,		0x084)		\
+	_ER(EXIT_CLGI,		0x085)		\
+	_ER(EXIT_SKINIT,	0x086)		\
+	_ER(EXIT_RDTSCP,	0x087)		\
+	_ER(EXIT_ICEBP,		0x088)		\
+	_ER(EXIT_WBINVD,	0x089)		\
+	_ER(EXIT_MONITOR,	0x08a)		\
+	_ER(EXIT_MWAIT,		0x08b)		\
+	_ER(EXIT_MWAIT_COND,	0x08c)		\
+	_ER(EXIT_NPF,		0x400)		\
+	_ER(EXIT_ERR,		-1)
+
+#define _ER(reason, val)	{ #reason, val },
+struct str_values {
+	const char	*str;
+	int		val;
+};
+
+static struct str_values vmx_exit_reasons[] = {
+	VMX_EXIT_REASONS
+	{ NULL, -1}
+};
+
+static struct str_values svm_exit_reasons[] = {
+	SVM_EXIT_REASONS
+	{ NULL, -1}
+};
+
+static struct isa_exit_reasons {
+	unsigned isa;
+	struct str_values *strings;
+} isa_exit_reasons[] = {
+	{ .isa = 1, .strings = vmx_exit_reasons },
+	{ .isa = 2, .strings = svm_exit_reasons },
+	{ }
+};
+
+static const char *find_exit_reason(unsigned isa, int val)
+{
+	struct str_values *strings = NULL;
+	int i;
+
+	for (i = 0; isa_exit_reasons[i].strings; ++i)
+		if (isa_exit_reasons[i].isa == isa) {
+			strings = isa_exit_reasons[i].strings;
+			break;
+		}
+	if (!strings)
+		return "UNKNOWN-ISA";
+	for (i = 0; strings[i].val >= 0; i++)
+		if (strings[i].val == val)
+			break;
+	if (strings[i].str)
+		return strings[i].str;
+	return "UNKNOWN";
+}
+
+static int kvm_exit_handler(struct trace_seq *s, struct pevent_record *record,
+			    struct event_format *event, void *context)
+{
+	unsigned long long isa;
+	unsigned long long val;
+	unsigned long long info1 = 0, info2 = 0;
+
+	if (pevent_get_field_val(s, event, "exit_reason", record, &val, 1) < 0)
+		return -1;
+
+	if (pevent_get_field_val(s, event, "isa", record, &isa, 0) < 0)
+		isa = 1;
+
+	trace_seq_printf(s, "reason %s", find_exit_reason(isa, val));
+
+	pevent_print_num_field(s, " rip 0x%lx", event, "guest_rip", record, 1);
+
+	if (pevent_get_field_val(s, event, "info1", record, &info1, 0) >= 0
+	    && pevent_get_field_val(s, event, "info2", record, &info2, 0) >= 0)
+		trace_seq_printf(s, " info %llx %llx", info1, info2);
+
+	return 0;
+}
+
+#define KVM_EMUL_INSN_F_CR0_PE (1 << 0)
+#define KVM_EMUL_INSN_F_EFL_VM (1 << 1)
+#define KVM_EMUL_INSN_F_CS_D   (1 << 2)
+#define KVM_EMUL_INSN_F_CS_L   (1 << 3)
+
+static int kvm_emulate_insn_handler(struct trace_seq *s,
+				    struct pevent_record *record,
+				    struct event_format *event, void *context)
+{
+	unsigned long long rip, csbase, len, flags, failed;
+	int llen;
+	uint8_t *insn;
+	const char *disasm;
+
+	if (pevent_get_field_val(s, event, "rip", record, &rip, 1) < 0)
+		return -1;
+
+	if (pevent_get_field_val(s, event, "csbase", record, &csbase, 1) < 0)
+		return -1;
+
+	if (pevent_get_field_val(s, event, "len", record, &len, 1) < 0)
+		return -1;
+
+	if (pevent_get_field_val(s, event, "flags", record, &flags, 1) < 0)
+		return -1;
+
+	if (pevent_get_field_val(s, event, "failed", record, &failed, 1) < 0)
+		return -1;
+
+	insn = pevent_get_field_raw(s, event, "insn", record, &llen, 1);
+	if (!insn)
+		return -1;
+
+	disasm = disassemble(insn, len, rip,
+			     flags & KVM_EMUL_INSN_F_CR0_PE,
+			     flags & KVM_EMUL_INSN_F_EFL_VM,
+			     flags & KVM_EMUL_INSN_F_CS_D,
+			     flags & KVM_EMUL_INSN_F_CS_L);
+
+	trace_seq_printf(s, "%llx:%llx: %s%s", csbase, rip, disasm,
+			 failed ? " FAIL" : "");
+	return 0;
+}
+
+union kvm_mmu_page_role {
+	unsigned word;
+	struct {
+		unsigned glevels:4;
+		unsigned level:4;
+		unsigned quadrant:2;
+		unsigned pad_for_nice_hex_output:6;
+		unsigned direct:1;
+		unsigned access:3;
+		unsigned invalid:1;
+		unsigned cr4_pge:1;
+		unsigned nxe:1;
+	};
+};
+
+static int kvm_mmu_print_role(struct trace_seq *s, struct pevent_record *record,
+			      struct event_format *event, void *context)
+{
+	unsigned long long val;
+	static const char *access_str[] = {
+		"---", "--x", "w--", "w-x", "-u-", "-ux", "wu-", "wux"
+	};
+	union kvm_mmu_page_role role;
+
+	if (pevent_get_field_val(s, event, "role", record, &val, 1) < 0)
+		return -1;
+
+	role.word = (int)val;
+
+	/*
+	 * We can only use the structure if file is of the same
+	 * endianess.
+	 */
+	if (pevent_is_file_bigendian(event->pevent) ==
+	    pevent_is_host_bigendian(event->pevent)) {
+
+		trace_seq_printf(s, "%u/%u q%u%s %s%s %spge %snxe",
+				 role.level,
+				 role.glevels,
+				 role.quadrant,
+				 role.direct ? " direct" : "",
+				 access_str[role.access],
+				 role.invalid ? " invalid" : "",
+				 role.cr4_pge ? "" : "!",
+				 role.nxe ? "" : "!");
+	} else
+		trace_seq_printf(s, "WORD: %08x", role.word);
+
+	pevent_print_num_field(s, " root %u ",  event,
+			       "root_count", record, 1);
+
+	if (pevent_get_field_val(s, event, "unsync", record, &val, 1) < 0)
+		return -1;
+
+	trace_seq_printf(s, "%s%c",  val ? "unsync" : "sync", 0);
+	return 0;
+}
+
+static int kvm_mmu_get_page_handler(struct trace_seq *s,
+				    struct pevent_record *record,
+				    struct event_format *event, void *context)
+{
+	unsigned long long val;
+
+	if (pevent_get_field_val(s, event, "created", record, &val, 1) < 0)
+		return -1;
+
+	trace_seq_printf(s, "%s ", val ? "new" : "existing");
+
+	if (pevent_get_field_val(s, event, "gfn", record, &val, 1) < 0)
+		return -1;
+
+	trace_seq_printf(s, "sp gfn %llx ", val);
+	return kvm_mmu_print_role(s, record, event, context);
+}
+
+#define PT_WRITABLE_SHIFT 1
+#define PT_WRITABLE_MASK (1ULL << PT_WRITABLE_SHIFT)
+
+static unsigned long long
+process_is_writable_pte(struct trace_seq *s, unsigned long long *args)
+{
+	unsigned long pte = args[0];
+	return pte & PT_WRITABLE_MASK;
+}
+
+int PEVENT_PLUGIN_LOADER(struct pevent *pevent)
+{
+	init_disassembler();
+
+	pevent_register_event_handler(pevent, -1, "kvm", "kvm_exit",
+				      kvm_exit_handler, NULL);
+
+	pevent_register_event_handler(pevent, -1, "kvm", "kvm_emulate_insn",
+				      kvm_emulate_insn_handler, NULL);
+
+	pevent_register_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_get_page",
+				      kvm_mmu_get_page_handler, NULL);
+
+	pevent_register_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_sync_page",
+				      kvm_mmu_print_role, NULL);
+
+	pevent_register_event_handler(pevent, -1,
+				      "kvmmmu", "kvm_mmu_unsync_page",
+				      kvm_mmu_print_role, NULL);
+
+	pevent_register_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_zap_page",
+				      kvm_mmu_print_role, NULL);
+
+	pevent_register_event_handler(pevent, -1, "kvmmmu",
+			"kvm_mmu_prepare_zap_page", kvm_mmu_print_role,
+			NULL);
+
+	pevent_register_print_function(pevent,
+				       process_is_writable_pte,
+				       PEVENT_FUNC_ARG_INT,
+				       "is_writable_pte",
+				       PEVENT_FUNC_ARG_LONG,
+				       PEVENT_FUNC_ARG_VOID);
+	return 0;
+}
+
+void PEVENT_PLUGIN_UNLOADER(struct pevent *pevent)
+{
+	pevent_unregister_event_handler(pevent, -1, "kvm", "kvm_exit",
+					kvm_exit_handler, NULL);
+
+	pevent_unregister_event_handler(pevent, -1, "kvm", "kvm_emulate_insn",
+					kvm_emulate_insn_handler, NULL);
+
+	pevent_unregister_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_get_page",
+					kvm_mmu_get_page_handler, NULL);
+
+	pevent_unregister_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_sync_page",
+					kvm_mmu_print_role, NULL);
+
+	pevent_unregister_event_handler(pevent, -1,
+					"kvmmmu", "kvm_mmu_unsync_page",
+					kvm_mmu_print_role, NULL);
+
+	pevent_unregister_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_zap_page",
+					kvm_mmu_print_role, NULL);
+
+	pevent_unregister_event_handler(pevent, -1, "kvmmmu",
+			"kvm_mmu_prepare_zap_page", kvm_mmu_print_role,
+			NULL);
+
+	pevent_unregister_print_function(pevent, process_is_writable_pte,
+					 "is_writable_pte");
+}
diff --git a/tools/lib/traceevent/plugin_mac80211.c b/tools/lib/traceevent/plugin_mac80211.c
new file mode 100644
index 00000000000..7e15a0f1c2f
--- /dev/null
+++ b/tools/lib/traceevent/plugin_mac80211.c
@@ -0,0 +1,102 @@
+/*
+ * Copyright (C) 2009 Johannes Berg <johannes@sipsolutions.net>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation;
+ * version 2.1 of the License (not later!)
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this program; if not,  see <http://www.gnu.org/licenses>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include "event-parse.h"
+
+#define INDENT 65
+
+static void print_string(struct trace_seq *s, struct event_format *event,
+			 const char *name, const void *data)
+{
+	struct format_field *f = pevent_find_field(event, name);
+	int offset;
+	int length;
+
+	if (!f) {
+		trace_seq_printf(s, "NOTFOUND:%s", name);
+		return;
+	}
+
+	offset = f->offset;
+	length = f->size;
+
+	if (!strncmp(f->type, "__data_loc", 10)) {
+		unsigned long long v;
+		if (pevent_read_number_field(f, data, &v)) {
+			trace_seq_printf(s, "invalid_data_loc");
+			return;
+		}
+		offset = v & 0xffff;
+		length = v >> 16;
+	}
+
+	trace_seq_printf(s, "%.*s", length, (char *)data + offset);
+}
+
+#define SF(fn)	pevent_print_num_field(s, fn ":%d", event, fn, record, 0)
+#define SFX(fn)	pevent_print_num_field(s, fn ":%#x", event, fn, record, 0)
+#define SP()	trace_seq_putc(s, ' ')
+
+static int drv_bss_info_changed(struct trace_seq *s,
+				struct pevent_record *record,
+				struct event_format *event, void *context)
+{
+	void *data = record->data;
+
+	print_string(s, event, "wiphy_name", data);
+	trace_seq_printf(s, " vif:");
+	print_string(s, event, "vif_name", data);
+	pevent_print_num_field(s, "(%d)", event, "vif_type", record, 1);
+
+	trace_seq_printf(s, "\n%*s", INDENT, "");
+	SF("assoc"); SP();
+	SF("aid"); SP();
+	SF("cts"); SP();
+	SF("shortpre"); SP();
+	SF("shortslot"); SP();
+	SF("dtimper"); SP();
+	trace_seq_printf(s, "\n%*s", INDENT, "");
+	SF("bcnint"); SP();
+	SFX("assoc_cap"); SP();
+	SFX("basic_rates"); SP();
+	SF("enable_beacon");
+	trace_seq_printf(s, "\n%*s", INDENT, "");
+	SF("ht_operation_mode");
+
+	return 0;
+}
+
+int PEVENT_PLUGIN_LOADER(struct pevent *pevent)
+{
+	pevent_register_event_handler(pevent, -1, "mac80211",
+				      "drv_bss_info_changed",
+				      drv_bss_info_changed, NULL);
+	return 0;
+}
+
+void PEVENT_PLUGIN_UNLOADER(struct pevent *pevent)
+{
+	pevent_unregister_event_handler(pevent, -1, "mac80211",
+					"drv_bss_info_changed",
+					drv_bss_info_changed, NULL);
+}
diff --git a/tools/lib/traceevent/plugin_sched_switch.c b/tools/lib/traceevent/plugin_sched_switch.c
new file mode 100644
index 00000000000..f1ce6006525
--- /dev/null
+++ b/tools/lib/traceevent/plugin_sched_switch.c
@@ -0,0 +1,160 @@
+/*
+ * Copyright (C) 2009, 2010 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation;
+ * version 2.1 of the License (not later!)
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this program; if not,  see <http://www.gnu.org/licenses>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include "event-parse.h"
+
+static void write_state(struct trace_seq *s, int val)
+{
+	const char states[] = "SDTtZXxW";
+	int found = 0;
+	int i;
+
+	for (i = 0; i < (sizeof(states) - 1); i++) {
+		if (!(val & (1 << i)))
+			continue;
+
+		if (found)
+			trace_seq_putc(s, '|');
+
+		found = 1;
+		trace_seq_putc(s, states[i]);
+	}
+
+	if (!found)
+		trace_seq_putc(s, 'R');
+}
+
+static void write_and_save_comm(struct format_field *field,
+				struct pevent_record *record,
+				struct trace_seq *s, int pid)
+{
+	const char *comm;
+	int len;
+
+	comm = (char *)(record->data + field->offset);
+	len = s->len;
+	trace_seq_printf(s, "%.*s",
+			 field->size, comm);
+
+	/* make sure the comm has a \0 at the end. */
+	trace_seq_terminate(s);
+	comm = &s->buffer[len];
+
+	/* Help out the comm to ids. This will handle dups */
+	pevent_register_comm(field->event->pevent, comm, pid);
+}
+
+static int sched_wakeup_handler(struct trace_seq *s,
+				struct pevent_record *record,
+				struct event_format *event, void *context)
+{
+	struct format_field *field;
+	unsigned long long val;
+
+	if (pevent_get_field_val(s, event, "pid", record, &val, 1))
+		return trace_seq_putc(s, '!');
+
+	field = pevent_find_any_field(event, "comm");
+	if (field) {
+		write_and_save_comm(field, record, s, val);
+		trace_seq_putc(s, ':');
+	}
+	trace_seq_printf(s, "%lld", val);
+
+	if (pevent_get_field_val(s, event, "prio", record, &val, 0) == 0)
+		trace_seq_printf(s, " [%lld]", val);
+
+	if (pevent_get_field_val(s, event, "success", record, &val, 1) == 0)
+		trace_seq_printf(s, " success=%lld", val);
+
+	if (pevent_get_field_val(s, event, "target_cpu", record, &val, 0) == 0)
+		trace_seq_printf(s, " CPU:%03llu", val);
+
+	return 0;
+}
+
+static int sched_switch_handler(struct trace_seq *s,
+				struct pevent_record *record,
+				struct event_format *event, void *context)
+{
+	struct format_field *field;
+	unsigned long long val;
+
+	if (pevent_get_field_val(s, event, "prev_pid", record, &val, 1))
+		return trace_seq_putc(s, '!');
+
+	field = pevent_find_any_field(event, "prev_comm");
+	if (field) {
+		write_and_save_comm(field, record, s, val);
+		trace_seq_putc(s, ':');
+	}
+	trace_seq_printf(s, "%lld ", val);
+
+	if (pevent_get_field_val(s, event, "prev_prio", record, &val, 0) == 0)
+		trace_seq_printf(s, "[%lld] ", val);
+
+	if (pevent_get_field_val(s,  event, "prev_state", record, &val, 0) == 0)
+		write_state(s, val);
+
+	trace_seq_puts(s, " ==> ");
+
+	if (pevent_get_field_val(s, event, "next_pid", record, &val, 1))
+		return trace_seq_putc(s, '!');
+
+	field = pevent_find_any_field(event, "next_comm");
+	if (field) {
+		write_and_save_comm(field, record, s, val);
+		trace_seq_putc(s, ':');
+	}
+	trace_seq_printf(s, "%lld", val);
+
+	if (pevent_get_field_val(s, event, "next_prio", record, &val, 0) == 0)
+		trace_seq_printf(s, " [%lld]", val);
+
+	return 0;
+}
+
+int PEVENT_PLUGIN_LOADER(struct pevent *pevent)
+{
+	pevent_register_event_handler(pevent, -1, "sched", "sched_switch",
+				      sched_switch_handler, NULL);
+
+	pevent_register_event_handler(pevent, -1, "sched", "sched_wakeup",
+				      sched_wakeup_handler, NULL);
+
+	pevent_register_event_handler(pevent, -1, "sched", "sched_wakeup_new",
+				      sched_wakeup_handler, NULL);
+	return 0;
+}
+
+void PEVENT_PLUGIN_UNLOADER(struct pevent *pevent)
+{
+	pevent_unregister_event_handler(pevent, -1, "sched", "sched_switch",
+					sched_switch_handler, NULL);
+
+	pevent_unregister_event_handler(pevent, -1, "sched", "sched_wakeup",
+					sched_wakeup_handler, NULL);
+
+	pevent_unregister_event_handler(pevent, -1, "sched", "sched_wakeup_new",
+					sched_wakeup_handler, NULL);
+}
diff --git a/tools/lib/traceevent/plugin_scsi.c b/tools/lib/traceevent/plugin_scsi.c
new file mode 100644
index 00000000000..eda326fc862
--- /dev/null
+++ b/tools/lib/traceevent/plugin_scsi.c
@@ -0,0 +1,429 @@
+#include <stdio.h>
+#include <string.h>
+#include <inttypes.h>
+#include "event-parse.h"
+
+typedef unsigned long sector_t;
+typedef uint64_t u64;
+typedef unsigned int u32;
+
+/*
+ *      SCSI opcodes
+ */
+#define TEST_UNIT_READY			0x00
+#define REZERO_UNIT			0x01
+#define REQUEST_SENSE			0x03
+#define FORMAT_UNIT			0x04
+#define READ_BLOCK_LIMITS		0x05
+#define REASSIGN_BLOCKS			0x07
+#define INITIALIZE_ELEMENT_STATUS	0x07
+#define READ_6				0x08
+#define WRITE_6				0x0a
+#define SEEK_6				0x0b
+#define READ_REVERSE			0x0f
+#define WRITE_FILEMARKS			0x10
+#define SPACE				0x11
+#define INQUIRY				0x12
+#define RECOVER_BUFFERED_DATA		0x14
+#define MODE_SELECT			0x15
+#define RESERVE				0x16
+#define RELEASE				0x17
+#define COPY				0x18
+#define ERASE				0x19
+#define MODE_SENSE			0x1a
+#define START_STOP			0x1b
+#define RECEIVE_DIAGNOSTIC		0x1c
+#define SEND_DIAGNOSTIC			0x1d
+#define ALLOW_MEDIUM_REMOVAL		0x1e
+
+#define READ_FORMAT_CAPACITIES		0x23
+#define SET_WINDOW			0x24
+#define READ_CAPACITY			0x25
+#define READ_10				0x28
+#define WRITE_10			0x2a
+#define SEEK_10				0x2b
+#define POSITION_TO_ELEMENT		0x2b
+#define WRITE_VERIFY			0x2e
+#define VERIFY				0x2f
+#define SEARCH_HIGH			0x30
+#define SEARCH_EQUAL			0x31
+#define SEARCH_LOW			0x32
+#define SET_LIMITS			0x33
+#define PRE_FETCH			0x34
+#define READ_POSITION			0x34
+#define SYNCHRONIZE_CACHE		0x35
+#define LOCK_UNLOCK_CACHE		0x36
+#define READ_DEFECT_DATA		0x37
+#define MEDIUM_SCAN			0x38
+#define COMPARE				0x39
+#define COPY_VERIFY			0x3a
+#define WRITE_BUFFER			0x3b
+#define READ_BUFFER			0x3c
+#define UPDATE_BLOCK			0x3d
+#define READ_LONG			0x3e
+#define WRITE_LONG			0x3f
+#define CHANGE_DEFINITION		0x40
+#define WRITE_SAME			0x41
+#define UNMAP				0x42
+#define READ_TOC			0x43
+#define READ_HEADER			0x44
+#define GET_EVENT_STATUS_NOTIFICATION	0x4a
+#define LOG_SELECT			0x4c
+#define LOG_SENSE			0x4d
+#define XDWRITEREAD_10			0x53
+#define MODE_SELECT_10			0x55
+#define RESERVE_10			0x56
+#define RELEASE_10			0x57
+#define MODE_SENSE_10			0x5a
+#define PERSISTENT_RESERVE_IN		0x5e
+#define PERSISTENT_RESERVE_OUT		0x5f
+#define VARIABLE_LENGTH_CMD		0x7f
+#define REPORT_LUNS			0xa0
+#define SECURITY_PROTOCOL_IN		0xa2
+#define MAINTENANCE_IN			0xa3
+#define MAINTENANCE_OUT			0xa4
+#define MOVE_MEDIUM			0xa5
+#define EXCHANGE_MEDIUM			0xa6
+#define READ_12				0xa8
+#define WRITE_12			0xaa
+#define READ_MEDIA_SERIAL_NUMBER	0xab
+#define WRITE_VERIFY_12			0xae
+#define VERIFY_12			0xaf
+#define SEARCH_HIGH_12			0xb0
+#define SEARCH_EQUAL_12			0xb1
+#define SEARCH_LOW_12			0xb2
+#define SECURITY_PROTOCOL_OUT		0xb5
+#define READ_ELEMENT_STATUS		0xb8
+#define SEND_VOLUME_TAG			0xb6
+#define WRITE_LONG_2			0xea
+#define EXTENDED_COPY			0x83
+#define RECEIVE_COPY_RESULTS		0x84
+#define ACCESS_CONTROL_IN		0x86
+#define ACCESS_CONTROL_OUT		0x87
+#define READ_16				0x88
+#define WRITE_16			0x8a
+#define READ_ATTRIBUTE			0x8c
+#define WRITE_ATTRIBUTE			0x8d
+#define VERIFY_16			0x8f
+#define SYNCHRONIZE_CACHE_16		0x91
+#define WRITE_SAME_16			0x93
+#define SERVICE_ACTION_IN		0x9e
+/* values for service action in */
+#define	SAI_READ_CAPACITY_16		0x10
+#define SAI_GET_LBA_STATUS		0x12
+/* values for VARIABLE_LENGTH_CMD service action codes
+ * see spc4r17 Section D.3.5, table D.7 and D.8 */
+#define VLC_SA_RECEIVE_CREDENTIAL	0x1800
+/* values for maintenance in */
+#define MI_REPORT_IDENTIFYING_INFORMATION		0x05
+#define MI_REPORT_TARGET_PGS				0x0a
+#define MI_REPORT_ALIASES				0x0b
+#define MI_REPORT_SUPPORTED_OPERATION_CODES		0x0c
+#define MI_REPORT_SUPPORTED_TASK_MANAGEMENT_FUNCTIONS	0x0d
+#define MI_REPORT_PRIORITY				0x0e
+#define MI_REPORT_TIMESTAMP				0x0f
+#define MI_MANAGEMENT_PROTOCOL_IN			0x10
+/* value for MI_REPORT_TARGET_PGS ext header */
+#define MI_EXT_HDR_PARAM_FMT		0x20
+/* values for maintenance out */
+#define MO_SET_IDENTIFYING_INFORMATION	0x06
+#define MO_SET_TARGET_PGS		0x0a
+#define MO_CHANGE_ALIASES		0x0b
+#define MO_SET_PRIORITY			0x0e
+#define MO_SET_TIMESTAMP		0x0f
+#define MO_MANAGEMENT_PROTOCOL_OUT	0x10
+/* values for variable length command */
+#define XDREAD_32			0x03
+#define XDWRITE_32			0x04
+#define XPWRITE_32			0x06
+#define XDWRITEREAD_32			0x07
+#define READ_32				0x09
+#define VERIFY_32			0x0a
+#define WRITE_32			0x0b
+#define WRITE_SAME_32			0x0d
+
+#define SERVICE_ACTION16(cdb) (cdb[1] & 0x1f)
+#define SERVICE_ACTION32(cdb) ((cdb[8] << 8) | cdb[9])
+
+static const char *
+scsi_trace_misc(struct trace_seq *, unsigned char *, int);
+
+static const char *
+scsi_trace_rw6(struct trace_seq *p, unsigned char *cdb, int len)
+{
+	const char *ret = p->buffer + p->len;
+	sector_t lba = 0, txlen = 0;
+
+	lba |= ((cdb[1] & 0x1F) << 16);
+	lba |=  (cdb[2] << 8);
+	lba |=   cdb[3];
+	txlen = cdb[4];
+
+	trace_seq_printf(p, "lba=%llu txlen=%llu",
+			 (unsigned long long)lba, (unsigned long long)txlen);
+	trace_seq_putc(p, 0);
+	return ret;
+}
+
+static const char *
+scsi_trace_rw10(struct trace_seq *p, unsigned char *cdb, int len)
+{
+	const char *ret = p->buffer + p->len;
+	sector_t lba = 0, txlen = 0;
+
+	lba |= (cdb[2] << 24);
+	lba |= (cdb[3] << 16);
+	lba |= (cdb[4] << 8);
+	lba |=  cdb[5];
+	txlen |= (cdb[7] << 8);
+	txlen |=  cdb[8];
+
+	trace_seq_printf(p, "lba=%llu txlen=%llu protect=%u",
+			 (unsigned long long)lba, (unsigned long long)txlen,
+			 cdb[1] >> 5);
+
+	if (cdb[0] == WRITE_SAME)
+		trace_seq_printf(p, " unmap=%u", cdb[1] >> 3 & 1);
+
+	trace_seq_putc(p, 0);
+	return ret;
+}
+
+static const char *
+scsi_trace_rw12(struct trace_seq *p, unsigned char *cdb, int len)
+{
+	const char *ret = p->buffer + p->len;
+	sector_t lba = 0, txlen = 0;
+
+	lba |= (cdb[2] << 24);
+	lba |= (cdb[3] << 16);
+	lba |= (cdb[4] << 8);
+	lba |=  cdb[5];
+	txlen |= (cdb[6] << 24);
+	txlen |= (cdb[7] << 16);
+	txlen |= (cdb[8] << 8);
+	txlen |=  cdb[9];
+
+	trace_seq_printf(p, "lba=%llu txlen=%llu protect=%u",
+			 (unsigned long long)lba, (unsigned long long)txlen,
+			 cdb[1] >> 5);
+	trace_seq_putc(p, 0);
+	return ret;
+}
+
+static const char *
+scsi_trace_rw16(struct trace_seq *p, unsigned char *cdb, int len)
+{
+	const char *ret = p->buffer + p->len;
+	sector_t lba = 0, txlen = 0;
+
+	lba |= ((u64)cdb[2] << 56);
+	lba |= ((u64)cdb[3] << 48);
+	lba |= ((u64)cdb[4] << 40);
+	lba |= ((u64)cdb[5] << 32);
+	lba |= (cdb[6] << 24);
+	lba |= (cdb[7] << 16);
+	lba |= (cdb[8] << 8);
+	lba |=  cdb[9];
+	txlen |= (cdb[10] << 24);
+	txlen |= (cdb[11] << 16);
+	txlen |= (cdb[12] << 8);
+	txlen |=  cdb[13];
+
+	trace_seq_printf(p, "lba=%llu txlen=%llu protect=%u",
+			 (unsigned long long)lba, (unsigned long long)txlen,
+			 cdb[1] >> 5);
+
+	if (cdb[0] == WRITE_SAME_16)
+		trace_seq_printf(p, " unmap=%u", cdb[1] >> 3 & 1);
+
+	trace_seq_putc(p, 0);
+	return ret;
+}
+
+static const char *
+scsi_trace_rw32(struct trace_seq *p, unsigned char *cdb, int len)
+{
+	const char *ret = p->buffer + p->len, *cmd;
+	sector_t lba = 0, txlen = 0;
+	u32 ei_lbrt = 0;
+
+	switch (SERVICE_ACTION32(cdb)) {
+	case READ_32:
+		cmd = "READ";
+		break;
+	case VERIFY_32:
+		cmd = "VERIFY";
+		break;
+	case WRITE_32:
+		cmd = "WRITE";
+		break;
+	case WRITE_SAME_32:
+		cmd = "WRITE_SAME";
+		break;
+	default:
+		trace_seq_printf(p, "UNKNOWN");
+		goto out;
+	}
+
+	lba |= ((u64)cdb[12] << 56);
+	lba |= ((u64)cdb[13] << 48);
+	lba |= ((u64)cdb[14] << 40);
+	lba |= ((u64)cdb[15] << 32);
+	lba |= (cdb[16] << 24);
+	lba |= (cdb[17] << 16);
+	lba |= (cdb[18] << 8);
+	lba |=  cdb[19];
+	ei_lbrt |= (cdb[20] << 24);
+	ei_lbrt |= (cdb[21] << 16);
+	ei_lbrt |= (cdb[22] << 8);
+	ei_lbrt |=  cdb[23];
+	txlen |= (cdb[28] << 24);
+	txlen |= (cdb[29] << 16);
+	txlen |= (cdb[30] << 8);
+	txlen |=  cdb[31];
+
+	trace_seq_printf(p, "%s_32 lba=%llu txlen=%llu protect=%u ei_lbrt=%u",
+			 cmd, (unsigned long long)lba,
+			 (unsigned long long)txlen, cdb[10] >> 5, ei_lbrt);
+
+	if (SERVICE_ACTION32(cdb) == WRITE_SAME_32)
+		trace_seq_printf(p, " unmap=%u", cdb[10] >> 3 & 1);
+
+out:
+	trace_seq_putc(p, 0);
+	return ret;
+}
+
+static const char *
+scsi_trace_unmap(struct trace_seq *p, unsigned char *cdb, int len)
+{
+	const char *ret = p->buffer + p->len;
+	unsigned int regions = cdb[7] << 8 | cdb[8];
+
+	trace_seq_printf(p, "regions=%u", (regions - 8) / 16);
+	trace_seq_putc(p, 0);
+	return ret;
+}
+
+static const char *
+scsi_trace_service_action_in(struct trace_seq *p, unsigned char *cdb, int len)
+{
+	const char *ret = p->buffer + p->len, *cmd;
+	sector_t lba = 0;
+	u32 alloc_len = 0;
+
+	switch (SERVICE_ACTION16(cdb)) {
+	case SAI_READ_CAPACITY_16:
+		cmd = "READ_CAPACITY_16";
+		break;
+	case SAI_GET_LBA_STATUS:
+		cmd = "GET_LBA_STATUS";
+		break;
+	default:
+		trace_seq_printf(p, "UNKNOWN");
+		goto out;
+	}
+
+	lba |= ((u64)cdb[2] << 56);
+	lba |= ((u64)cdb[3] << 48);
+	lba |= ((u64)cdb[4] << 40);
+	lba |= ((u64)cdb[5] << 32);
+	lba |= (cdb[6] << 24);
+	lba |= (cdb[7] << 16);
+	lba |= (cdb[8] << 8);
+	lba |=  cdb[9];
+	alloc_len |= (cdb[10] << 24);
+	alloc_len |= (cdb[11] << 16);
+	alloc_len |= (cdb[12] << 8);
+	alloc_len |=  cdb[13];
+
+	trace_seq_printf(p, "%s lba=%llu alloc_len=%u", cmd,
+			 (unsigned long long)lba, alloc_len);
+
+out:
+	trace_seq_putc(p, 0);
+	return ret;
+}
+
+static const char *
+scsi_trace_varlen(struct trace_seq *p, unsigned char *cdb, int len)
+{
+	switch (SERVICE_ACTION32(cdb)) {
+	case READ_32:
+	case VERIFY_32:
+	case WRITE_32:
+	case WRITE_SAME_32:
+		return scsi_trace_rw32(p, cdb, len);
+	default:
+		return scsi_trace_misc(p, cdb, len);
+	}
+}
+
+static const char *
+scsi_trace_misc(struct trace_seq *p, unsigned char *cdb, int len)
+{
+	const char *ret = p->buffer + p->len;
+
+	trace_seq_printf(p, "-");
+	trace_seq_putc(p, 0);
+	return ret;
+}
+
+const char *
+scsi_trace_parse_cdb(struct trace_seq *p, unsigned char *cdb, int len)
+{
+	switch (cdb[0]) {
+	case READ_6:
+	case WRITE_6:
+		return scsi_trace_rw6(p, cdb, len);
+	case READ_10:
+	case VERIFY:
+	case WRITE_10:
+	case WRITE_SAME:
+		return scsi_trace_rw10(p, cdb, len);
+	case READ_12:
+	case VERIFY_12:
+	case WRITE_12:
+		return scsi_trace_rw12(p, cdb, len);
+	case READ_16:
+	case VERIFY_16:
+	case WRITE_16:
+	case WRITE_SAME_16:
+		return scsi_trace_rw16(p, cdb, len);
+	case UNMAP:
+		return scsi_trace_unmap(p, cdb, len);
+	case SERVICE_ACTION_IN:
+		return scsi_trace_service_action_in(p, cdb, len);
+	case VARIABLE_LENGTH_CMD:
+		return scsi_trace_varlen(p, cdb, len);
+	default:
+		return scsi_trace_misc(p, cdb, len);
+	}
+}
+
+unsigned long long process_scsi_trace_parse_cdb(struct trace_seq *s,
+						unsigned long long *args)
+{
+	scsi_trace_parse_cdb(s, (unsigned char *) (unsigned long) args[1], args[2]);
+	return 0;
+}
+
+int PEVENT_PLUGIN_LOADER(struct pevent *pevent)
+{
+	pevent_register_print_function(pevent,
+				       process_scsi_trace_parse_cdb,
+				       PEVENT_FUNC_ARG_STRING,
+				       "scsi_trace_parse_cdb",
+				       PEVENT_FUNC_ARG_PTR,
+				       PEVENT_FUNC_ARG_PTR,
+				       PEVENT_FUNC_ARG_INT,
+				       PEVENT_FUNC_ARG_VOID);
+	return 0;
+}
+
+void PEVENT_PLUGIN_UNLOADER(struct pevent *pevent)
+{
+	pevent_unregister_print_function(pevent, process_scsi_trace_parse_cdb,
+					 "scsi_trace_parse_cdb");
+}
diff --git a/tools/lib/traceevent/plugin_xen.c b/tools/lib/traceevent/plugin_xen.c
new file mode 100644
index 00000000000..3a413eaada6
--- /dev/null
+++ b/tools/lib/traceevent/plugin_xen.c
@@ -0,0 +1,136 @@
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include "event-parse.h"
+
+#define __HYPERVISOR_set_trap_table			0
+#define __HYPERVISOR_mmu_update				1
+#define __HYPERVISOR_set_gdt				2
+#define __HYPERVISOR_stack_switch			3
+#define __HYPERVISOR_set_callbacks			4
+#define __HYPERVISOR_fpu_taskswitch			5
+#define __HYPERVISOR_sched_op_compat			6
+#define __HYPERVISOR_dom0_op				7
+#define __HYPERVISOR_set_debugreg			8
+#define __HYPERVISOR_get_debugreg			9
+#define __HYPERVISOR_update_descriptor			10
+#define __HYPERVISOR_memory_op				12
+#define __HYPERVISOR_multicall				13
+#define __HYPERVISOR_update_va_mapping			14
+#define __HYPERVISOR_set_timer_op			15
+#define __HYPERVISOR_event_channel_op_compat		16
+#define __HYPERVISOR_xen_version			17
+#define __HYPERVISOR_console_io				18
+#define __HYPERVISOR_physdev_op_compat			19
+#define __HYPERVISOR_grant_table_op			20
+#define __HYPERVISOR_vm_assist				21
+#define __HYPERVISOR_update_va_mapping_otherdomain	22
+#define __HYPERVISOR_iret				23 /* x86 only */
+#define __HYPERVISOR_vcpu_op				24
+#define __HYPERVISOR_set_segment_base			25 /* x86/64 only */
+#define __HYPERVISOR_mmuext_op				26
+#define __HYPERVISOR_acm_op				27
+#define __HYPERVISOR_nmi_op				28
+#define __HYPERVISOR_sched_op				29
+#define __HYPERVISOR_callback_op			30
+#define __HYPERVISOR_xenoprof_op			31
+#define __HYPERVISOR_event_channel_op			32
+#define __HYPERVISOR_physdev_op				33
+#define __HYPERVISOR_hvm_op				34
+#define __HYPERVISOR_tmem_op				38
+
+/* Architecture-specific hypercall definitions. */
+#define __HYPERVISOR_arch_0				48
+#define __HYPERVISOR_arch_1				49
+#define __HYPERVISOR_arch_2				50
+#define __HYPERVISOR_arch_3				51
+#define __HYPERVISOR_arch_4				52
+#define __HYPERVISOR_arch_5				53
+#define __HYPERVISOR_arch_6				54
+#define __HYPERVISOR_arch_7				55
+
+#define N(x)	[__HYPERVISOR_##x] = "("#x")"
+static const char *xen_hypercall_names[] = {
+	N(set_trap_table),
+	N(mmu_update),
+	N(set_gdt),
+	N(stack_switch),
+	N(set_callbacks),
+	N(fpu_taskswitch),
+	N(sched_op_compat),
+	N(dom0_op),
+	N(set_debugreg),
+	N(get_debugreg),
+	N(update_descriptor),
+	N(memory_op),
+	N(multicall),
+	N(update_va_mapping),
+	N(set_timer_op),
+	N(event_channel_op_compat),
+	N(xen_version),
+	N(console_io),
+	N(physdev_op_compat),
+	N(grant_table_op),
+	N(vm_assist),
+	N(update_va_mapping_otherdomain),
+	N(iret),
+	N(vcpu_op),
+	N(set_segment_base),
+	N(mmuext_op),
+	N(acm_op),
+	N(nmi_op),
+	N(sched_op),
+	N(callback_op),
+	N(xenoprof_op),
+	N(event_channel_op),
+	N(physdev_op),
+	N(hvm_op),
+
+/* Architecture-specific hypercall definitions. */
+	N(arch_0),
+	N(arch_1),
+	N(arch_2),
+	N(arch_3),
+	N(arch_4),
+	N(arch_5),
+	N(arch_6),
+	N(arch_7),
+};
+#undef N
+
+#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]))
+
+static const char *xen_hypercall_name(unsigned op)
+{
+	if (op < ARRAY_SIZE(xen_hypercall_names) &&
+	    xen_hypercall_names[op] != NULL)
+		return xen_hypercall_names[op];
+
+	return "";
+}
+
+unsigned long long process_xen_hypercall_name(struct trace_seq *s,
+					      unsigned long long *args)
+{
+	unsigned int op = args[0];
+
+	trace_seq_printf(s, "%s", xen_hypercall_name(op));
+	return 0;
+}
+
+int PEVENT_PLUGIN_LOADER(struct pevent *pevent)
+{
+	pevent_register_print_function(pevent,
+				       process_xen_hypercall_name,
+				       PEVENT_FUNC_ARG_STRING,
+				       "xen_hypercall_name",
+				       PEVENT_FUNC_ARG_INT,
+				       PEVENT_FUNC_ARG_VOID);
+	return 0;
+}
+
+void PEVENT_PLUGIN_UNLOADER(struct pevent *pevent)
+{
+	pevent_unregister_print_function(pevent, process_xen_hypercall_name,
+					 "xen_hypercall_name");
+}
diff --git a/tools/lib/traceevent/trace-seq.c b/tools/lib/traceevent/trace-seq.c
index d7f2e68bc5b..ec3bd16a548 100644
--- a/tools/lib/traceevent/trace-seq.c
+++ b/tools/lib/traceevent/trace-seq.c
@@ -22,6 +22,7 @@
 #include <string.h>
 #include <stdarg.h>
 
+#include <asm/bug.h>
 #include "event-parse.h"
 #include "event-utils.h"
 
@@ -32,10 +33,21 @@
 #define TRACE_SEQ_POISON	((void *)0xdeadbeef)
 #define TRACE_SEQ_CHECK(s)						\
 do {									\
-	if ((s)->buffer == TRACE_SEQ_POISON)			\
-		die("Usage of trace_seq after it was destroyed");	\
+	if (WARN_ONCE((s)->buffer == TRACE_SEQ_POISON,			\
+		      "Usage of trace_seq after it was destroyed"))	\
+		(s)->state = TRACE_SEQ__BUFFER_POISONED;		\
 } while (0)
 
+#define TRACE_SEQ_CHECK_RET_N(s, n)		\
+do {						\
+	TRACE_SEQ_CHECK(s);			\
+	if ((s)->state != TRACE_SEQ__GOOD)	\
+		return n; 			\
+} while (0)
+
+#define TRACE_SEQ_CHECK_RET(s)   TRACE_SEQ_CHECK_RET_N(s, )
+#define TRACE_SEQ_CHECK_RET0(s)  TRACE_SEQ_CHECK_RET_N(s, 0)
+
 /**
  * trace_seq_init - initialize the trace_seq structure
  * @s: a pointer to the trace_seq structure to initialize
@@ -45,7 +57,11 @@ void trace_seq_init(struct trace_seq *s)
 	s->len = 0;
 	s->readpos = 0;
 	s->buffer_size = TRACE_SEQ_BUF_SIZE;
-	s->buffer = malloc_or_die(s->buffer_size);
+	s->buffer = malloc(s->buffer_size);
+	if (s->buffer != NULL)
+		s->state = TRACE_SEQ__GOOD;
+	else
+		s->state = TRACE_SEQ__MEM_ALLOC_FAILED;
 }
 
 /**
@@ -71,17 +87,23 @@ void trace_seq_destroy(struct trace_seq *s)
 {
 	if (!s)
 		return;
-	TRACE_SEQ_CHECK(s);
+	TRACE_SEQ_CHECK_RET(s);
 	free(s->buffer);
 	s->buffer = TRACE_SEQ_POISON;
 }
 
 static void expand_buffer(struct trace_seq *s)
 {
+	char *buf;
+
+	buf = realloc(s->buffer, s->buffer_size + TRACE_SEQ_BUF_SIZE);
+	if (WARN_ONCE(!buf, "Can't allocate trace_seq buffer memory")) {
+		s->state = TRACE_SEQ__MEM_ALLOC_FAILED;
+		return;
+	}
+
+	s->buffer = buf;
 	s->buffer_size += TRACE_SEQ_BUF_SIZE;
-	s->buffer = realloc(s->buffer, s->buffer_size);
-	if (!s->buffer)
-		die("Can't allocate trace_seq buffer memory");
 }
 
 /**
@@ -105,9 +127,9 @@ trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
 	int len;
 	int ret;
 
-	TRACE_SEQ_CHECK(s);
-
  try_again:
+	TRACE_SEQ_CHECK_RET0(s);
+
 	len = (s->buffer_size - 1) - s->len;
 
 	va_start(ap, fmt);
@@ -141,9 +163,9 @@ trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args)
 	int len;
 	int ret;
 
-	TRACE_SEQ_CHECK(s);
-
  try_again:
+	TRACE_SEQ_CHECK_RET0(s);
+
 	len = (s->buffer_size - 1) - s->len;
 
 	ret = vsnprintf(s->buffer + s->len, len, fmt, args);
@@ -172,13 +194,15 @@ int trace_seq_puts(struct trace_seq *s, const char *str)
 {
 	int len;
 
-	TRACE_SEQ_CHECK(s);
+	TRACE_SEQ_CHECK_RET0(s);
 
 	len = strlen(str);
 
 	while (len > ((s->buffer_size - 1) - s->len))
 		expand_buffer(s);
 
+	TRACE_SEQ_CHECK_RET0(s);
+
 	memcpy(s->buffer + s->len, str, len);
 	s->len += len;
 
@@ -187,11 +211,13 @@ int trace_seq_puts(struct trace_seq *s, const char *str)
 
 int trace_seq_putc(struct trace_seq *s, unsigned char c)
 {
-	TRACE_SEQ_CHECK(s);
+	TRACE_SEQ_CHECK_RET0(s);
 
 	while (s->len >= (s->buffer_size - 1))
 		expand_buffer(s);
 
+	TRACE_SEQ_CHECK_RET0(s);
+
 	s->buffer[s->len++] = c;
 
 	return 1;
@@ -199,7 +225,7 @@ int trace_seq_putc(struct trace_seq *s, unsigned char c)
 
 void trace_seq_terminate(struct trace_seq *s)
 {
-	TRACE_SEQ_CHECK(s);
+	TRACE_SEQ_CHECK_RET(s);
 
 	/* There's always one character left on the buffer */
 	s->buffer[s->len] = 0;
@@ -208,5 +234,16 @@ void trace_seq_terminate(struct trace_seq *s)
 int trace_seq_do_printf(struct trace_seq *s)
 {
 	TRACE_SEQ_CHECK(s);
-	return printf("%.*s", s->len, s->buffer);
+
+	switch (s->state) {
+	case TRACE_SEQ__GOOD:
+		return printf("%.*s", s->len, s->buffer);
+	case TRACE_SEQ__BUFFER_POISONED:
+		puts("Usage of trace_seq after it was destroyed");
+		break;
+	case TRACE_SEQ__MEM_ALLOC_FAILED:
+		puts("Can't allocate trace_seq buffer memory");
+		break;
+	}
+	return -1;
 }
diff --git a/tools/perf/Documentation/perf-archive.txt b/tools/perf/Documentation/perf-archive.txt
index 5032a142853..ac6ecbb3e66 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 6a06cefe964..52276a6d2b7 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 43b42c4f4a9..c71b0f36d9e 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 10a27987125..8eab8a4bdeb 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 e9cbfcddfa3..05f9a0a6784 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 80c7da6732f..29ee857c09c 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 3ff8bd4f0b4..bc5990c33dc 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 7de01dd7968..cdd8d4946db 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 025de796067..f41572d0dd7 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 4835618a560..cb2e5868c8e 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 7fc8f179cae..7257e7e9e38 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 aacef07ebf3..42faf369211 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 4087ab19823..0da603b79b6 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 3b67ea2444b..a77e31246c0 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 20b0f12763b..c99e0de7e54 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 6a250858946..b3466018bbd 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 f8bf5f244d7..a7350519c63 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 31c00f186da..2e3ade69a58 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 6ea9e85bdc0..78948882e3d 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 7c8020a3278..3c394bf16fa 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 8cf8e66ba59..3c53ec268fb 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 0f3c65518a2..6a76a07b678 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 baf17989a21..9e9c91f5b7f 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 ee0d565f83e..8b0e1c9234d 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 41c9bde2fb6..652af0b66a6 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(sw->prev_pid);
+	prev_p = find_create_pid(tchart, 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;
 
-static int process_sample_event(struct perf_tool *tool __maybe_unused,
-				union perf_event *event __maybe_unused,
+	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,
+				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 +1029,74 @@ 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;
 
-	count = determine_display_tasks(TIME_THRESH);
+	/* 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);
 
-	/* 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 +1114,17 @@ 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 +1134,111 @@ 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 +1250,56 @@ 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 +1307,41 @@ 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 71e6402729a..76cd510d34d 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 8be17fc462b..896f27047ed 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 f7d11a811c7..d604e50fc16 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= $(subst ','\'',$(prefix)/$(plugindir))
+endif
diff --git a/tools/perf/config/Makefile.arch b/tools/perf/config/Makefile.arch
new file mode 100644
index 00000000000..fef8ae92280
--- /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 00000000000..80f3da0c351
--- /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 87e790017c6..12e551346fa 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 59e7a705e14..9b8a544155b 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 c9f398d8786..00000000000
--- 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 c9f398d8786..00000000000
--- 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 f168debc5be..4d985e0f03f 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 62e157db2e2..496e2abb548 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 8b38b4e80ec..431798a4110 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 b079304bd53..3c2f213e979 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -247,13 +247,14 @@ 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 +269,7 @@ 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 9079a25cd64..44edcb2edcd 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 85d4919dd62..653a8fe2db9 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 0197bda9c46..465cdbc345c 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 173bf42cc03..2b6519e0e36 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 376c3560853..497957f269d 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 2ca0abf1b2b..00544b8b644 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 d64ab79c6d3..142263492f6 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 41cc0badb74..c505ef2af24 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 3cbd1049608..4db0ae617d7 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 93a62b06c3a..aca1a83dd13 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 00000000000..238aa3927c7
--- /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 4ca1b938f6a..47146d388db 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 6664a7cd828..983d6b8562a 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 d09ab579119..5ff3db318f1 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 cbaa7af4551..d11541d4d7d 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 7d45d2f5360..118cca29dd2 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 00000000000..89c16b98861
--- /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 a440e03cd8c..b720b92eba6 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 d63c68ea02a..402d2bd30b0 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 2ca66cc1160..5b95c44f343 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 696c1fbe424..52e7fc48af9 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 c244cb524ef..831fbb77d1f 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 092902e30ce..bf890f72fe8 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 e6d134773d0..c0b43ee40d9 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 cf6242c92ee..469eb679fb9 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 834b7b57b78..b2aef59d6bb 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 a92770c98cc..6baabe63182 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 929f28a7c14..845ef865ece 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 e3970e3eaac..8d9db454f1a 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 4f7f989876e..8ad97e9b119 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 96bbda1ddb8..88f7be39943 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 66e44a5019d..87b8672eb41 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 fced3840e99..7ff30a62a13 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 ee0df0e24cd..f9e777629e2 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 7a86e565671..fac5bd51bef 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 7d09faf85cf..1fbcd8bdc11 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 8c2df80152a..2b15d0c95c7 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 399e74c34c1..299b5558650 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 efbd98805ad..443694c36b0 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 af4c687cc49..4045d086d9d 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 9ac666abbe7..cd7d6f078cd 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 bb788c109fe..1fc1c2f0477 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 30fec9901e4..faf6e219be2 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 bbc746aa571..40bd2c04df8 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;
 	}
@@ -1008,7 +1004,7 @@ void perf_evlist__close(struct perf_evlist *evlist)
 	int ncpus = cpu_map__nr(evlist->cpus);
 	int nthreads = thread_map__nr(evlist->threads);
 
-	list_for_each_entry_reverse(evsel, &evlist->entries, node)
+	evlist__for_each_reverse(evlist, evsel)
 		perf_evsel__close(evsel, ncpus, nthreads);
 }
 
@@ -1019,7 +1015,7 @@ 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 +1030,7 @@ 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 +1074,25 @@ 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 +1154,7 @@ 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 +1202,7 @@ 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 +1223,20 @@ 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 649d6ea98a8..f5173cd6369 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 46dd4c2a41c..22e18a26b7e 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);
 }
 
@@ -1998,8 +1960,7 @@ 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 1ea7c92e6e3..f1b325665aa 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 1cd03570893..bb3e0ede618 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);
 }
@@ -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;
@@ -2074,7 +2070,7 @@ 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 */
@@ -2108,7 +2104,7 @@ static int process_group_desc(struct perf_file_section *section __maybe_unused,
 	ret = 0;
 out_free:
 	for (i = 0; i < nr_groups; i++)
-		free(desc[i].name);
+		zfree(&desc[i].name);
 	free(desc);
 
 	return ret;
@@ -2301,7 +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) {
@@ -2312,7 +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  = {
@@ -2327,7 +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) {
@@ -2534,7 +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);
 
@@ -2628,7 +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)
@@ -2669,7 +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));
 
@@ -2744,7 +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;
@@ -2834,11 +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;
@@ -2892,7 +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) {
@@ -3003,7 +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;
 
@@ -3025,7 +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 307c9aed972..a2d047bdf4e 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 8b1f6e891b8..86c37c47226 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 822903eaa20..e4e6249b87d 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 b621347a158..a59743fa3ef 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/machine.c b/tools/perf/util/machine.c
index 84cdb072ac8..ded74590b92 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 ef5bc913ca7..9b9bd719aa1 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] = {
@@ -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
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index e4e259c3ba1..18068c6b71c 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 6de6f89c2a6..a7f1b6a91fd 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;
+	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 31f404a032a..d22e3f8017d 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 b0241e28eaf..cbf0149cf22 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 c232d8dd410..d9cab4d2719 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];
+	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 +607,42 @@ static struct perf_pmu_alias *pmu_find_alias(struct perf_pmu *pmu,
 	return NULL;
 }
 
+
+static int check_unit_scale(struct perf_pmu_alias *alias,
+			    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,
+			  char **unit, double *scale)
 {
 	struct parse_events_term *term, *h;
 	struct perf_pmu_alias *alias;
 	int ret;
 
+	*unit   = NULL;
+	*scale  = 0;
+
 	list_for_each_entry_safe(term, h, head_terms, list) {
 		alias = pmu_find_alias(pmu, term);
 		if (!alias)
@@ -525,6 +650,11 @@ 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);
 	}
@@ -625,7 +755,7 @@ 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 1179b26f244..9183380e203 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,
+			  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 9c6989ca2be..a8a9b6cd93a 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 f9f3de8b422..fcaf7273e85 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 ffb657ffd32..061edb162b5 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 239036fb2b2..595bfc73d2e 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 4bf8ace7f51..122669c18ff 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 c8845b107f6..373762501da 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 d5e5969f6fe..e108207c5de 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 53c20e7fd90..cd9774df375 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 f36d24a0244..7acc03e8f3b 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);
 			}
@@ -1541,32 +1531,42 @@ 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);
 	}
 }
 
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 50f640958f0..3140f8ae614 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 58ea5ca6c25..d0aee4b9dfd 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 8b0bb1f4494..635cd8f8b22 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 d11aefbc4b8..f3e4bc5fe5d 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 cfa906882e2..4abe23550c7 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 3edd0538161..79a757a2a15 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 f0b0c008c50..2553e5b55b8 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 eabdce0a2da..71f9d102b96 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 96c866045d6..43262b83c54 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 e0781989cc3..f7b4d6e699e 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 eed0b96302a..75945672870 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 2d2dd0532b5..bd15f490d04 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 c0c36965fff..39ce9adbaaf 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 07de8fea2f4..fffe2888a1c 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 3c778a07b7c..e74c5963dc7 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 2d0c5069089..7381b1ca404 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 49eaf1d7d89..0358882c891 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -66,10 +66,13 @@ 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);
+		err = comm__override(curr, str, timestamp);
+		if (err)
+			return err;
 	} else {
 		new = comm__new(str, timestamp);
 		if (!new)
@@ -126,7 +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 897c1b2a750..5b856bf942e 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 9b5f856cc28..5d321591210 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 ce793c7dd23..8e517def925 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 88cfeaff600..dab14d0ad3d 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 f3c9e551bd3..7e6fcfe8b43 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 6681f71f2f9..e0d6d07f684 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 f2112270c66..e113e180c48 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 95199e4eea9..57aaccc1692 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 00000000000..6322d37164c
--- /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 04df6311410..7b6d6868832 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 0efd5393de8..742f23bf35f 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 28a0a89c1f7..42ad667bb31 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 c8f362daba8..6995d66f225 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 697c8b4e59c..0fb3c1fcd3e 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 39159822d58..0ddb3b8a89e 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);
 		}
 	}
 
diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include
index ee76544deec..8abbef164b4 100644
--- a/tools/scripts/Makefile.include
+++ b/tools/scripts/Makefile.include
@@ -61,6 +61,7 @@ QUIET_SUBDIR1  =
 ifneq ($(findstring $(MAKEFLAGS),s),s)
   ifneq ($(V),1)
 	QUIET_CC       = @echo '  CC       '$@;
+	QUIET_CC_FPIC  = @echo '  CC FPIC  '$@;
 	QUIET_AR       = @echo '  AR       '$@;
 	QUIET_LINK     = @echo '  LINK     '$@;
 	QUIET_MKDIR    = @echo '  MKDIR    '$@;
@@ -76,5 +77,8 @@ ifneq ($(findstring $(MAKEFLAGS),s),s)
 		+@echo	       '  DESCEND  '$(1); \
 		mkdir -p $(OUTPUT)$(1) && \
 		$(MAKE) $(COMMAND_O) subdir=$(if $(subdir),$(subdir)/$(1),$(1)) $(PRINT_DIR) -C $(1) $(2)
+
+	QUIET_CLEAN    = @printf '  CLEAN    %s\n' $1;
+	QUIET_INSTALL  = @printf '  INSTALL  %s\n' $1;
   endif
 endif
diff --git a/tools/vm/Makefile b/tools/vm/Makefile
index 24e9ddd93fa..3d907dacf2a 100644
--- a/tools/vm/Makefile
+++ b/tools/vm/Makefile
@@ -2,21 +2,21 @@
 #
 TARGETS=page-types slabinfo
 
-LK_DIR = ../lib/lk
-LIBLK = $(LK_DIR)/liblk.a
+LIB_DIR = ../lib/api
+LIBS = $(LIB_DIR)/libapikfs.a
 
 CC = $(CROSS_COMPILE)gcc
 CFLAGS = -Wall -Wextra -I../lib/
-LDFLAGS = $(LIBLK)
+LDFLAGS = $(LIBS)
 
-$(TARGETS): liblk
+$(TARGETS): $(LIBS)
 
-liblk:
-	make -C $(LK_DIR)
+$(LIBS):
+	make -C $(LIB_DIR)
 
 %: %.c
 	$(CC) $(CFLAGS) -o $@ $< $(LDFLAGS)
 
 clean:
 	$(RM) page-types slabinfo
-	make -C ../lib/lk clean
+	make -C $(LIB_DIR) clean
diff --git a/tools/vm/page-types.c b/tools/vm/page-types.c
index d5e9d6d185c..f9be24d9efa 100644
--- a/tools/vm/page-types.c
+++ b/tools/vm/page-types.c
@@ -36,7 +36,7 @@
 #include <sys/statfs.h>
 #include "../../include/uapi/linux/magic.h"
 #include "../../include/uapi/linux/kernel-page-flags.h"
-#include <lk/debugfs.h>
+#include <api/fs/debugfs.h>
 
 #ifndef MAX_PATH
 # define MAX_PATH 256