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 improvements:

   - watchdog driver improvements by Li Zefan
   - Power7 CPI stack events related improvements by Sukadev Bhattiprolu
   - event multiplexing via hrtimers and other improvements by Stephane
     Eranian
   - kernel stack use optimization by Andrew Hunter
   - AMD IOMMU uncore PMU support by Suravee Suthikulpanit
   - NMI handling rate-limits by Dave Hansen
   - various hw_breakpoint fixes by Oleg Nesterov
   - hw_breakpoint overflow period sampling and related signal handling
     fixes by Jiri Olsa
   - Intel Haswell PMU support by Andi Kleen

  Tooling improvements:

   - Reset SIGTERM handler in workload child process, fix from David
     Ahern.
   - Makefile reorganization, prep work for Kconfig patches, from Jiri
     Olsa.
   - Add automated make test suite, from Jiri Olsa.
   - Add --percent-limit option to 'top' and 'report', from Namhyung
     Kim.
   - Sorting improvements, from Namhyung Kim.
   - Expand definition of sysfs format attribute, from Michael Ellerman.

  Tooling fixes:

   - 'perf tests' fixes from Jiri Olsa.
   - Make Power7 CPI stack events available in sysfs, from Sukadev
     Bhattiprolu.
   - Handle death by SIGTERM in 'perf record', fix from David Ahern.
   - Fix printing of perf_event_paranoid message, from David Ahern.
   - Handle realloc failures in 'perf kvm', from David Ahern.
   - Fix divide by 0 in variance, from David Ahern.
   - Save parent pid in thread struct, from David Ahern.
   - Handle JITed code in shared memory, from Andi Kleen.
   - Fixes for 'perf diff', from Jiri Olsa.
   - Remove some unused struct members, from Jiri Olsa.
   - Add missing liblk.a dependency for python/perf.so, fix from Jiri
     Olsa.
   - Respect CROSS_COMPILE in liblk.a, from Rabin Vincent.
   - No need to do locking when adding hists in perf report, only 'top'
     needs that, from Namhyung Kim.
   - Fix alignment of symbol column in in the hists browser (top,
     report) when -v is given, from NAmhyung Kim.
   - Fix 'perf top' -E option behavior, from Namhyung Kim.
   - Fix bug in isupper() and islower(), from Sukadev Bhattiprolu.
   - Fix compile errors in bp_signal 'perf test', from Sukadev
     Bhattiprolu.

  ... and more things"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (102 commits)
  perf/x86: Disable PEBS-LL in intel_pmu_pebs_disable()
  perf/x86: Fix shared register mutual exclusion enforcement
  perf/x86/intel: Support full width counting
  x86: Add NMI duration tracepoints
  perf: Drop sample rate when sampling is too slow
  x86: Warn when NMI handlers take large amounts of time
  hw_breakpoint: Introduce "struct bp_cpuinfo"
  hw_breakpoint: Simplify *register_wide_hw_breakpoint()
  hw_breakpoint: Introduce cpumask_of_bp()
  hw_breakpoint: Simplify the "weight" usage in toggle_bp_slot() paths
  hw_breakpoint: Simplify list/idx mess in toggle_bp_slot() paths
  perf/x86/intel: Add mem-loads/stores support for Haswell
  perf/x86/intel: Support Haswell/v4 LBR format
  perf/x86/intel: Move NMI clearing to end of PMI handler
  perf/x86/intel: Add Haswell PEBS support
  perf/x86/intel: Add simple Haswell PMU support
  perf/x86/intel: Add Haswell PEBS record support
  perf/x86/intel: Fix sparse warning
  perf/x86/amd: AMD IOMMU Performance Counter PERF uncore PMU implementation
  perf/x86/amd: Add IOMMU Performance Counter resource management
  ...

38 files changed, 1164 insertions, 773 deletions

diff --git a/tools/lib/lk/Makefile b/tools/lib/lk/Makefile
index 926cbf3..2c5a197 100644
--- a/tools/lib/lk/Makefile
+++ b/tools/lib/lk/Makefile
@@ -1,5 +1,8 @@
 include ../../scripts/Makefile.include
 
+CC = $(CROSS_COMPILE)gcc
+AR = $(CROSS_COMPILE)ar
+
 # guard against environment variables
 LIB_H=
 LIB_OBJS=
diff --git a/tools/perf/Documentation/perf-archive.txt b/tools/perf/Documentation/perf-archive.txt
index fae174d..5032a14 100644
--- a/tools/perf/Documentation/perf-archive.txt
+++ b/tools/perf/Documentation/perf-archive.txt
@@ -13,7 +13,7 @@ SYNOPSIS
 DESCRIPTION
 -----------
 This command runs runs perf-buildid-list --with-hits, and collects the files
-with the buildids found so that analisys of perf.data contents can be possible
+with the buildids found so that analysis of perf.data contents can be possible
 on another machine.
 
 
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 7d5f4f3..66dab74 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -210,6 +210,10 @@ OPTIONS
 	Demangle symbol names to human readable form. It's enabled by default,
 	disable with --no-demangle.
 
+--percent-limit::
+	Do not show entries which have an overhead under that percent.
+	(Default: 0).
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-annotate[1]
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 9f1a2fe..7fdd190 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -155,6 +155,10 @@ Default is to monitor all CPUS.
 
 	Default: fractal,0.5,callee.
 
+--percent-limit::
+	Do not show entries which have an overhead under that percent.
+	(Default: 0).
+
 INTERACTIVE PROMPTING KEYS
 --------------------------
 
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index b0f164b..203cb0e 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -51,189 +51,63 @@ include config/utilities.mak
 # Define NO_BACKTRACE if you do not want stack backtrace debug feature
 #
 # Define NO_LIBNUMA if you do not want numa perf benchmark
+#
+# Define NO_LIBAUDIT if you do not want libaudit support
+#
+# Define NO_LIBBIONIC if you do not want bionic support
 
-$(OUTPUT)PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE
-	@$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT)
-
-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
-
-CC = $(CROSS_COMPILE)gcc
-AR = $(CROSS_COMPILE)ar
-
-# Additional ARCH settings for x86
-ifeq ($(ARCH),i386)
-	override ARCH := x86
-	NO_PERF_REGS := 0
-	LIBUNWIND_LIBS = -lunwind -lunwind-x86
-endif
-ifeq ($(ARCH),x86_64)
-	override ARCH := x86
-	IS_X86_64 := 0
-	ifeq (, $(findstring m32,$(EXTRA_CFLAGS)))
-		IS_X86_64 := $(shell echo __x86_64__ | ${CC} -E -x c - | tail -n 1)
-	endif
-	ifeq (${IS_X86_64}, 1)
-		RAW_ARCH := x86_64
-		ARCH_CFLAGS := -DARCH_X86_64
-		ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memset_64.S
-	endif
-	NO_PERF_REGS := 0
-	LIBUNWIND_LIBS = -lunwind -lunwind-x86_64
-endif
-
-# Treat warnings as errors unless directed not to
-ifneq ($(WERROR),0)
-	CFLAGS_WERROR := -Werror
-endif
-
-ifeq ("$(origin DEBUG)", "command line")
-  PERF_DEBUG = $(DEBUG)
-endif
-ifndef PERF_DEBUG
-  CFLAGS_OPTIMIZE = -O6
+ifeq ($(srctree),)
+srctree := $(patsubst %/,%,$(dir $(shell pwd)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+#$(info Determined 'srctree' to be $(srctree))
 endif
 
-ifdef PARSER_DEBUG
-	PARSER_DEBUG_BISON  := -t
-	PARSER_DEBUG_FLEX   := -d
-	PARSER_DEBUG_CFLAGS := -DPARSER_DEBUG
+ifneq ($(objtree),)
+#$(info Determined 'objtree' to be $(objtree))
 endif
 
-ifdef NO_NEWT
-	NO_SLANG=1
+ifneq ($(OUTPUT),)
+#$(info Determined 'OUTPUT' to be $(OUTPUT))
 endif
 
-CFLAGS = -fno-omit-frame-pointer -ggdb3 -funwind-tables -Wall -Wextra -std=gnu99 $(CFLAGS_WERROR) $(CFLAGS_OPTIMIZE) $(EXTRA_WARNINGS) $(EXTRA_CFLAGS) $(PARSER_DEBUG_CFLAGS)
-EXTLIBS = -lpthread -lrt -lelf -lm
-ALL_CFLAGS = $(CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
-ALL_LDFLAGS = $(LDFLAGS)
-STRIP ?= strip
-
-# Among the variables below, these:
-#   perfexecdir
-#   template_dir
-#   mandir
-#   infodir
-#   htmldir
-#   ETC_PERFCONFIG (but not sysconfdir)
-# can be specified as a relative path some/where/else;
-# this is interpreted as relative to $(prefix) and "perf" at
-# runtime figures out where they are based on the path to the executable.
-# This can help installing the suite in a relocatable way.
-
-# Make the path relative to DESTDIR, not to prefix
-ifndef DESTDIR
-prefix = $(HOME)
-endif
-bindir_relative = bin
-bindir = $(prefix)/$(bindir_relative)
-mandir = share/man
-infodir = share/info
-perfexecdir = libexec/perf-core
-sharedir = $(prefix)/share
-template_dir = share/perf-core/templates
-htmldir = share/doc/perf-doc
-ifeq ($(prefix),/usr)
-sysconfdir = /etc
-ETC_PERFCONFIG = $(sysconfdir)/perfconfig
-else
-sysconfdir = $(prefix)/etc
-ETC_PERFCONFIG = etc/perfconfig
-endif
-lib = lib
+$(OUTPUT)PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE
+	@$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT)
 
-export prefix bindir sharedir sysconfdir
+CC = $(CROSS_COMPILE)gcc
+AR = $(CROSS_COMPILE)ar
 
-RM = rm -f
-MKDIR = mkdir
-FIND = find
+RM      = rm -f
+MKDIR   = mkdir
+FIND    = find
 INSTALL = install
-FLEX = flex
-BISON= bison
-
-# sparse is architecture-neutral, which means that we need to tell it
-# explicitly what architecture to check for. Fix this up for yours..
-SPARSE_FLAGS = -D__BIG_ENDIAN__ -D__powerpc__
-
-ifneq ($(MAKECMDGOALS),clean)
-ifneq ($(MAKECMDGOALS),tags)
--include config/feature-tests.mak
-
-ifeq ($(call get-executable,$(FLEX)),)
-	dummy := $(error Error: $(FLEX) is missing on this system, please install it)
-endif
-
-ifeq ($(call get-executable,$(BISON)),)
-	dummy := $(error Error: $(BISON) is missing on this system, please install it)
-endif
+FLEX    = flex
+BISON   = bison
+STRIP   = strip
 
-ifeq ($(call try-cc,$(SOURCE_HELLO),$(CFLAGS) -Werror -fstack-protector-all,-fstack-protector-all),y)
-	CFLAGS := $(CFLAGS) -fstack-protector-all
-endif
+LK_DIR          = $(srctree)/tools/lib/lk/
+TRACE_EVENT_DIR = $(srctree)/tools/lib/traceevent/
 
-ifeq ($(call try-cc,$(SOURCE_HELLO),$(CFLAGS) -Werror -Wstack-protector,-Wstack-protector),y)
-       CFLAGS := $(CFLAGS) -Wstack-protector
-endif
+# include config/Makefile by default and rule out
+# non-config cases
+config := 1
 
-ifeq ($(call try-cc,$(SOURCE_HELLO),$(CFLAGS) -Werror -Wvolatile-register-var,-Wvolatile-register-var),y)
-       CFLAGS := $(CFLAGS) -Wvolatile-register-var
-endif
+NON_CONFIG_TARGETS := clean TAGS tags cscope help
 
-ifndef PERF_DEBUG
-	ifeq ($(call try-cc,$(SOURCE_HELLO),$(CFLAGS) -D_FORTIFY_SOURCE=2,-D_FORTIFY_SOURCE=2),y)
-		CFLAGS := $(CFLAGS) -D_FORTIFY_SOURCE=2
-	endif
+ifdef MAKECMDGOALS
+ifeq ($(filter-out $(NON_CONFIG_TARGETS),$(MAKECMDGOALS)),)
+  config := 0
 endif
-
-### --- END CONFIGURATION SECTION ---
-
-ifeq ($(srctree),)
-srctree := $(patsubst %/,%,$(dir $(shell pwd)))
-srctree := $(patsubst %/,%,$(dir $(srctree)))
-#$(info Determined 'srctree' to be $(srctree))
 endif
 
-ifneq ($(objtree),)
-#$(info Determined 'objtree' to be $(objtree))
+ifeq ($(config),1)
+include config/Makefile
 endif
 
-ifneq ($(OUTPUT),)
-#$(info Determined 'OUTPUT' to be $(OUTPUT))
-endif
+export prefix bindir sharedir sysconfdir
 
-BASIC_CFLAGS = \
-	-Iutil/include \
-	-Iarch/$(ARCH)/include \
-	$(if $(objtree),-I$(objtree)/arch/$(ARCH)/include/generated/uapi) \
-	-I$(srctree)/arch/$(ARCH)/include/uapi \
-	-I$(srctree)/arch/$(ARCH)/include \
-	$(if $(objtree),-I$(objtree)/include/generated/uapi) \
-	-I$(srctree)/include/uapi \
-	-I$(srctree)/include \
-	-I$(OUTPUT)util \
-	-Iutil \
-	-I. \
-	-I$(TRACE_EVENT_DIR) \
-	-I../lib/ \
-	-D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
-
-BASIC_LDFLAGS =
-
-ifeq ($(call try-cc,$(SOURCE_BIONIC),$(CFLAGS),bionic),y)
-	BIONIC := 1
-	EXTLIBS := $(filter-out -lrt,$(EXTLIBS))
-	EXTLIBS := $(filter-out -lpthread,$(EXTLIBS))
-	BASIC_CFLAGS += -I.
-endif
-endif # MAKECMDGOALS != tags
-endif # MAKECMDGOALS != clean
+# sparse is architecture-neutral, which means that we need to tell it
+# explicitly what architecture to check for. Fix this up for yours..
+SPARSE_FLAGS = -D__BIG_ENDIAN__ -D__powerpc__
 
 # Guard against environment variables
 BUILTIN_OBJS =
@@ -247,20 +121,17 @@ SCRIPT_SH += perf-archive.sh
 grep-libs = $(filter -l%,$(1))
 strip-libs = $(filter-out -l%,$(1))
 
-LK_DIR = ../lib/lk/
-TRACE_EVENT_DIR = ../lib/traceevent/
-
 LK_PATH=$(LK_DIR)
 
 ifneq ($(OUTPUT),)
-	TE_PATH=$(OUTPUT)
+  TE_PATH=$(OUTPUT)
 ifneq ($(subdir),)
-	LK_PATH=$(OUTPUT)$(LK_DIR)
+  LK_PATH=$(OUTPUT)$(LK_DIR)
 else
-	LK_PATH=$(OUTPUT)
+  LK_PATH=$(OUTPUT)
 endif
 else
-	TE_PATH=$(TRACE_EVENT_DIR)
+  TE_PATH=$(TRACE_EVENT_DIR)
 endif
 
 LIBTRACEEVENT = $(TE_PATH)libtraceevent.a
@@ -278,10 +149,10 @@ export PYTHON_EXTBUILD_LIB PYTHON_EXTBUILD_TMP
 python-clean := rm -rf $(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)
+PYTHON_EXT_DEPS := util/python-ext-sources util/setup.py $(LIBTRACEEVENT) $(LIBLK)
 
 $(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS)
-	$(QUIET_GEN)CFLAGS='$(BASIC_CFLAGS)' $(PYTHON_WORD) util/setup.py \
+	$(QUIET_GEN)CFLAGS='$(CFLAGS)' $(PYTHON_WORD) util/setup.py \
 	  --quiet build_ext; \
 	mkdir -p $(OUTPUT)python && \
 	cp $(PYTHON_EXTBUILD_LIB)perf.so $(OUTPUT)python/
@@ -296,8 +167,6 @@ SCRIPTS = $(patsubst %.sh,%,$(SCRIPT_SH))
 #
 PROGRAMS += $(OUTPUT)perf
 
-LANG_BINDINGS =
-
 # what 'all' will build and 'install' will install, in perfexecdir
 ALL_PROGRAMS = $(PROGRAMS) $(SCRIPTS)
 
@@ -306,10 +175,10 @@ OTHER_PROGRAMS = $(OUTPUT)perf
 
 # Set paths to tools early so that they can be used for version tests.
 ifndef SHELL_PATH
-	SHELL_PATH = /bin/sh
+  SHELL_PATH = /bin/sh
 endif
 ifndef PERL_PATH
-	PERL_PATH = /usr/bin/perl
+  PERL_PATH = /usr/bin/perl
 endif
 
 export PERL_PATH
@@ -557,79 +426,14 @@ BUILTIN_OBJS += $(OUTPUT)builtin-mem.o
 
 PERFLIBS = $(LIB_FILE) $(LIBLK) $(LIBTRACEEVENT)
 
-#
-# Platform specific tweaks
-#
-ifneq ($(MAKECMDGOALS),clean)
-ifneq ($(MAKECMDGOALS),tags)
-
 # We choose to avoid "if .. else if .. else .. endif endif"
 # because maintaining the nesting to match is a pain.  If
 # we had "elif" things would have been much nicer...
 
-ifdef NO_LIBELF
-	NO_DWARF := 1
-	NO_DEMANGLE := 1
-	NO_LIBUNWIND := 1
-else
-FLAGS_LIBELF=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS)
-ifneq ($(call try-cc,$(SOURCE_LIBELF),$(FLAGS_LIBELF),libelf),y)
-	FLAGS_GLIBC=$(ALL_CFLAGS) $(ALL_LDFLAGS)
-	ifeq ($(call try-cc,$(SOURCE_GLIBC),$(FLAGS_GLIBC),glibc),y)
-		LIBC_SUPPORT := 1
-	endif
-	ifeq ($(BIONIC),1)
-		LIBC_SUPPORT := 1
-	endif
-	ifeq ($(LIBC_SUPPORT),1)
-		msg := $(warning No libelf found, disables 'probe' tool, please install elfutils-libelf-devel/libelf-dev);
-
-		NO_LIBELF := 1
-		NO_DWARF := 1
-		NO_DEMANGLE := 1
-	else
-		msg := $(error No gnu/libc-version.h found, please install glibc-dev[el]/glibc-static);
-	endif
-else
-	# for linking with debug library, run like:
-	# make DEBUG=1 LIBDW_DIR=/opt/libdw/
-	ifdef LIBDW_DIR
-		LIBDW_CFLAGS  := -I$(LIBDW_DIR)/include
-		LIBDW_LDFLAGS := -L$(LIBDW_DIR)/lib
-	endif
-
-	FLAGS_DWARF=$(ALL_CFLAGS) $(LIBDW_CFLAGS) -ldw -lelf $(LIBDW_LDFLAGS) $(ALL_LDFLAGS) $(EXTLIBS)
-	ifneq ($(call try-cc,$(SOURCE_DWARF),$(FLAGS_DWARF),libdw),y)
-		msg := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev);
-		NO_DWARF := 1
-	endif # Dwarf support
-endif # SOURCE_LIBELF
-endif # NO_LIBELF
-
-# There's only x86 (both 32 and 64) support for CFI unwind so far
-ifneq ($(ARCH),x86)
-	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
-
-FLAGS_UNWIND=$(LIBUNWIND_CFLAGS) $(ALL_CFLAGS) $(LIBUNWIND_LDFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) $(LIBUNWIND_LIBS)
-ifneq ($(call try-cc,$(SOURCE_LIBUNWIND),$(FLAGS_UNWIND),libunwind),y)
-	msg := $(warning No libunwind found, disabling post unwind support. Please install libunwind-dev[el] >= 0.99);
-	NO_LIBUNWIND := 1
-endif # Libunwind support
-endif # NO_LIBUNWIND
-
 -include arch/$(ARCH)/Makefile
 
 ifneq ($(OUTPUT),)
-	BASIC_CFLAGS += -I$(OUTPUT)
+  CFLAGS += -I$(OUTPUT)
 endif
 
 ifdef NO_LIBELF
@@ -647,281 +451,74 @@ BUILTIN_OBJS := $(filter-out $(OUTPUT)builtin-probe.o,$(BUILTIN_OBJS))
 LIB_OBJS += $(OUTPUT)util/symbol-minimal.o
 
 else # NO_LIBELF
-BASIC_CFLAGS += -DLIBELF_SUPPORT
-
-FLAGS_LIBELF=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS)
-ifeq ($(call try-cc,$(SOURCE_ELF_MMAP),$(FLAGS_LIBELF),-DLIBELF_MMAP),y)
-	BASIC_CFLAGS += -DLIBELF_MMAP
-endif
-
 ifndef NO_DWARF
-ifeq ($(origin PERF_HAVE_DWARF_REGS), undefined)
-	msg := $(warning DWARF register mappings have not been defined for architecture $(ARCH), DWARF support disabled);
-else
-	BASIC_CFLAGS := -DDWARF_SUPPORT $(LIBDW_CFLAGS) $(BASIC_CFLAGS)
-	BASIC_LDFLAGS := $(LIBDW_LDFLAGS) $(BASIC_LDFLAGS)
-	EXTLIBS += -lelf -ldw
-	LIB_OBJS += $(OUTPUT)util/probe-finder.o
-	LIB_OBJS += $(OUTPUT)util/dwarf-aux.o
-endif # PERF_HAVE_DWARF_REGS
+  LIB_OBJS += $(OUTPUT)util/probe-finder.o
+  LIB_OBJS += $(OUTPUT)util/dwarf-aux.o
 endif # NO_DWARF
 endif # NO_LIBELF
 
 ifndef NO_LIBUNWIND
-	BASIC_CFLAGS += -DLIBUNWIND_SUPPORT
-	EXTLIBS += $(LIBUNWIND_LIBS)
-	BASIC_CFLAGS := $(LIBUNWIND_CFLAGS) $(BASIC_CFLAGS)
-	BASIC_LDFLAGS := $(LIBUNWIND_LDFLAGS) $(BASIC_LDFLAGS)
-	LIB_OBJS += $(OUTPUT)util/unwind.o
+  LIB_OBJS += $(OUTPUT)util/unwind.o
 endif
 
 ifndef NO_LIBAUDIT
-	FLAGS_LIBAUDIT = $(ALL_CFLAGS) $(ALL_LDFLAGS) -laudit
-	ifneq ($(call try-cc,$(SOURCE_LIBAUDIT),$(FLAGS_LIBAUDIT),libaudit),y)
-		msg := $(warning No libaudit.h found, disables 'trace' tool, please install audit-libs-devel or libaudit-dev);
-	else
-		BASIC_CFLAGS += -DLIBAUDIT_SUPPORT
-		BUILTIN_OBJS += $(OUTPUT)builtin-trace.o
-		EXTLIBS += -laudit
-	endif
+  BUILTIN_OBJS += $(OUTPUT)builtin-trace.o
 endif
 
 ifndef NO_SLANG
-	FLAGS_SLANG=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) -I/usr/include/slang -lslang
-	ifneq ($(call try-cc,$(SOURCE_SLANG),$(FLAGS_SLANG),libslang),y)
-		msg := $(warning slang not found, disables TUI support. Please install slang-devel or libslang-dev);
-	else
-		# Fedora has /usr/include/slang/slang.h, but ubuntu /usr/include/slang.h
-		BASIC_CFLAGS += -I/usr/include/slang
-		BASIC_CFLAGS += -DSLANG_SUPPORT
-		EXTLIBS += -lslang
-		LIB_OBJS += $(OUTPUT)ui/browser.o
-		LIB_OBJS += $(OUTPUT)ui/browsers/annotate.o
-		LIB_OBJS += $(OUTPUT)ui/browsers/hists.o
-		LIB_OBJS += $(OUTPUT)ui/browsers/map.o
-		LIB_OBJS += $(OUTPUT)ui/browsers/scripts.o
-		LIB_OBJS += $(OUTPUT)ui/tui/setup.o
-		LIB_OBJS += $(OUTPUT)ui/tui/util.o
-		LIB_OBJS += $(OUTPUT)ui/tui/helpline.o
-		LIB_OBJS += $(OUTPUT)ui/tui/progress.o
-		LIB_H += ui/browser.h
-		LIB_H += ui/browsers/map.h
-		LIB_H += ui/keysyms.h
-		LIB_H += ui/libslang.h
-	endif
+  LIB_OBJS += $(OUTPUT)ui/browser.o
+  LIB_OBJS += $(OUTPUT)ui/browsers/annotate.o
+  LIB_OBJS += $(OUTPUT)ui/browsers/hists.o
+  LIB_OBJS += $(OUTPUT)ui/browsers/map.o
+  LIB_OBJS += $(OUTPUT)ui/browsers/scripts.o
+  LIB_OBJS += $(OUTPUT)ui/tui/setup.o
+  LIB_OBJS += $(OUTPUT)ui/tui/util.o
+  LIB_OBJS += $(OUTPUT)ui/tui/helpline.o
+  LIB_OBJS += $(OUTPUT)ui/tui/progress.o
+  LIB_H += ui/browser.h
+  LIB_H += ui/browsers/map.h
+  LIB_H += ui/keysyms.h
+  LIB_H += ui/libslang.h
 endif
 
 ifndef NO_GTK2
-	FLAGS_GTK2=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) $(shell pkg-config --libs --cflags gtk+-2.0 2>/dev/null)
-	ifneq ($(call try-cc,$(SOURCE_GTK2),$(FLAGS_GTK2),gtk2),y)
-		msg := $(warning GTK2 not found, disables GTK2 support. Please install gtk2-devel or libgtk2.0-dev);
-	else
-		ifeq ($(call try-cc,$(SOURCE_GTK2_INFOBAR),$(FLAGS_GTK2),-DHAVE_GTK_INFO_BAR),y)
-			BASIC_CFLAGS += -DHAVE_GTK_INFO_BAR
-		endif
-		BASIC_CFLAGS += -DGTK2_SUPPORT
-		BASIC_CFLAGS += $(shell pkg-config --cflags gtk+-2.0 2>/dev/null)
-		EXTLIBS += $(shell pkg-config --libs gtk+-2.0 2>/dev/null)
-		LIB_OBJS += $(OUTPUT)ui/gtk/browser.o
-		LIB_OBJS += $(OUTPUT)ui/gtk/hists.o
-		LIB_OBJS += $(OUTPUT)ui/gtk/setup.o
-		LIB_OBJS += $(OUTPUT)ui/gtk/util.o
-		LIB_OBJS += $(OUTPUT)ui/gtk/helpline.o
-		LIB_OBJS += $(OUTPUT)ui/gtk/progress.o
-		LIB_OBJS += $(OUTPUT)ui/gtk/annotate.o
-	endif
+  LIB_OBJS += $(OUTPUT)ui/gtk/browser.o
+  LIB_OBJS += $(OUTPUT)ui/gtk/hists.o
+  LIB_OBJS += $(OUTPUT)ui/gtk/setup.o
+  LIB_OBJS += $(OUTPUT)ui/gtk/util.o
+  LIB_OBJS += $(OUTPUT)ui/gtk/helpline.o
+  LIB_OBJS += $(OUTPUT)ui/gtk/progress.o
+  LIB_OBJS += $(OUTPUT)ui/gtk/annotate.o
 endif
 
-ifdef NO_LIBPERL
-	BASIC_CFLAGS += -DNO_LIBPERL
-else
-       PERL_EMBED_LDOPTS = $(shell perl -MExtUtils::Embed -e ldopts 2>/dev/null)
-       PERL_EMBED_LDFLAGS = $(call strip-libs,$(PERL_EMBED_LDOPTS))
-       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) $(PERL_EMBED_LDOPTS)
-
-	ifneq ($(call try-cc,$(SOURCE_PERL_EMBED),$(FLAGS_PERL_EMBED),perl),y)
-		BASIC_CFLAGS += -DNO_LIBPERL
-	else
-               ALL_LDFLAGS += $(PERL_EMBED_LDFLAGS)
-               EXTLIBS += $(PERL_EMBED_LIBADD)
-		LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-perl.o
-		LIB_OBJS += $(OUTPUT)scripts/perl/Perf-Trace-Util/Context.o
-	endif
+ifndef NO_LIBPERL
+  LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-perl.o
+  LIB_OBJS += $(OUTPUT)scripts/perl/Perf-Trace-Util/Context.o
 endif
 
-disable-python = $(eval $(disable-python_code))
-define disable-python_code
-  BASIC_CFLAGS += -DNO_LIBPYTHON
-  $(if $(1),$(warning No $(1) was found))
-  $(warning Python support will not be built)
-endef
-
-override PYTHON := \
-  $(call get-executable-or-default,PYTHON,python)
-
-ifndef PYTHON
-  $(call disable-python,python interpreter)
-else
-
-  PYTHON_WORD := $(call shell-wordify,$(PYTHON))
-
-  ifdef NO_LIBPYTHON
-    $(call disable-python)
-  else
-
-    override PYTHON_CONFIG := \
-      $(call get-executable-or-default,PYTHON_CONFIG,$(PYTHON)-config)
-
-    ifndef PYTHON_CONFIG
-      $(call disable-python,python-config tool)
-    else
-
-      PYTHON_CONFIG_SQ := $(call shell-sq,$(PYTHON_CONFIG))
-
-      PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null)
-      PYTHON_EMBED_LDFLAGS := $(call strip-libs,$(PYTHON_EMBED_LDOPTS))
-      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) $(PYTHON_EMBED_LDOPTS)
-
-      ifneq ($(call try-cc,$(SOURCE_PYTHON_EMBED),$(FLAGS_PYTHON_EMBED),python),y)
-        $(call disable-python,Python.h (for Python 2.x))
-      else
-
-        ifneq ($(call try-cc,$(SOURCE_PYTHON_VERSION),$(FLAGS_PYTHON_EMBED),python version),y)
-          $(warning Python 3 is not yet supported; please set)
-          $(warning PYTHON and/or PYTHON_CONFIG appropriately.)
-          $(warning If you also have Python 2 installed, then)
-          $(warning try something like:)
-          $(warning $(and ,))
-          $(warning $(and ,)  make PYTHON=python2)
-          $(warning $(and ,))
-          $(warning Otherwise, disable Python support entirely:)
-          $(warning $(and ,))
-          $(warning $(and ,)  make NO_LIBPYTHON=1)
-          $(warning $(and ,))
-          $(error   $(and ,))
-        else
-          ALL_LDFLAGS += $(PYTHON_EMBED_LDFLAGS)
-          EXTLIBS += $(PYTHON_EMBED_LIBADD)
-          LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-python.o
-          LIB_OBJS += $(OUTPUT)scripts/python/Perf-Trace-Util/Context.o
-          LANG_BINDINGS += $(OUTPUT)python/perf.so
-        endif
-
-      endif
-    endif
-  endif
-endif
-
-ifdef NO_DEMANGLE
-	BASIC_CFLAGS += -DNO_DEMANGLE
-else
-        ifdef HAVE_CPLUS_DEMANGLE
-		EXTLIBS += -liberty
-		BASIC_CFLAGS += -DHAVE_CPLUS_DEMANGLE
-        else
-		FLAGS_BFD=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) -DPACKAGE='perf' -lbfd
-		has_bfd := $(call try-cc,$(SOURCE_BFD),$(FLAGS_BFD),libbfd)
-		ifeq ($(has_bfd),y)
-			EXTLIBS += -lbfd
-		else
-			FLAGS_BFD_IBERTY=$(FLAGS_BFD) -liberty
-			has_bfd_iberty := $(call try-cc,$(SOURCE_BFD),$(FLAGS_BFD_IBERTY),liberty)
-			ifeq ($(has_bfd_iberty),y)
-				EXTLIBS += -lbfd -liberty
-			else
-				FLAGS_BFD_IBERTY_Z=$(FLAGS_BFD_IBERTY) -lz
-				has_bfd_iberty_z := $(call try-cc,$(SOURCE_BFD),$(FLAGS_BFD_IBERTY_Z),libz)
-				ifeq ($(has_bfd_iberty_z),y)
-					EXTLIBS += -lbfd -liberty -lz
-				else
-					FLAGS_CPLUS_DEMANGLE=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) -liberty
-					has_cplus_demangle := $(call try-cc,$(SOURCE_CPLUS_DEMANGLE),$(FLAGS_CPLUS_DEMANGLE),demangle)
-					ifeq ($(has_cplus_demangle),y)
-						EXTLIBS += -liberty
-						BASIC_CFLAGS += -DHAVE_CPLUS_DEMANGLE
-					else
-						msg := $(warning No bfd.h/libbfd found, install binutils-dev[el]/zlib-static to gain symbol demangling)
-						BASIC_CFLAGS += -DNO_DEMANGLE
-					endif
-				endif
-			endif
-		endif
-	endif
+ifndef NO_LIBPYTHON
+  LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-python.o
+  LIB_OBJS += $(OUTPUT)scripts/python/Perf-Trace-Util/Context.o
 endif
 
 ifeq ($(NO_PERF_REGS),0)
-	ifeq ($(ARCH),x86)
-		LIB_H += arch/x86/include/perf_regs.h
-	endif
-	BASIC_CFLAGS += -DHAVE_PERF_REGS
-endif
-
-ifndef NO_STRLCPY
-	ifeq ($(call try-cc,$(SOURCE_STRLCPY),,-DHAVE_STRLCPY),y)
-		BASIC_CFLAGS += -DHAVE_STRLCPY
-	endif
-endif
-
-ifndef NO_ON_EXIT
-	ifeq ($(call try-cc,$(SOURCE_ON_EXIT),,-DHAVE_ON_EXIT),y)
-		BASIC_CFLAGS += -DHAVE_ON_EXIT
-	endif
-endif
-
-ifndef NO_BACKTRACE
-       ifeq ($(call try-cc,$(SOURCE_BACKTRACE),,-DBACKTRACE_SUPPORT),y)
-               BASIC_CFLAGS += -DBACKTRACE_SUPPORT
-       endif
+  ifeq ($(ARCH),x86)
+    LIB_H += arch/x86/include/perf_regs.h
+  endif
 endif
 
 ifndef NO_LIBNUMA
-	FLAGS_LIBNUMA = $(ALL_CFLAGS) $(ALL_LDFLAGS) -lnuma
-	ifneq ($(call try-cc,$(SOURCE_LIBNUMA),$(FLAGS_LIBNUMA),libnuma),y)
-		msg := $(warning No numa.h found, disables 'perf bench numa mem' benchmark, please install numa-libs-devel or libnuma-dev);
-	else
-		BASIC_CFLAGS += -DLIBNUMA_SUPPORT
-		BUILTIN_OBJS += $(OUTPUT)bench/numa.o
-		EXTLIBS += -lnuma
-	endif
+  BUILTIN_OBJS += $(OUTPUT)bench/numa.o
 endif
 
 ifdef ASCIIDOC8
-	export ASCIIDOC8
+  export ASCIIDOC8
 endif
 
-endif # MAKECMDGOALS != tags
-endif # MAKECMDGOALS != clean
-
-# Shell quote (do not use $(call) to accommodate ancient setups);
-
-ETC_PERFCONFIG_SQ = $(subst ','\'',$(ETC_PERFCONFIG))
-
-DESTDIR_SQ = $(subst ','\'',$(DESTDIR))
-bindir_SQ = $(subst ','\'',$(bindir))
-bindir_relative_SQ = $(subst ','\'',$(bindir_relative))
-mandir_SQ = $(subst ','\'',$(mandir))
-infodir_SQ = $(subst ','\'',$(infodir))
-perfexecdir_SQ = $(subst ','\'',$(perfexecdir))
-template_dir_SQ = $(subst ','\'',$(template_dir))
-htmldir_SQ = $(subst ','\'',$(htmldir))
-prefix_SQ = $(subst ','\'',$(prefix))
-sysconfdir_SQ = $(subst ','\'',$(sysconfdir))
-
-SHELL_PATH_SQ = $(subst ','\'',$(SHELL_PATH))
-
 LIBS = -Wl,--whole-archive $(PERFLIBS) -Wl,--no-whole-archive -Wl,--start-group $(EXTLIBS) -Wl,--end-group
 
-ALL_CFLAGS += $(BASIC_CFLAGS)
-ALL_CFLAGS += $(ARCH_CFLAGS)
-ALL_LDFLAGS += $(BASIC_LDFLAGS)
-
 export INSTALL SHELL_PATH
 
-
 ### Build rules
 
 SHELL = $(SHELL_PATH)
@@ -939,20 +536,20 @@ strip: $(PROGRAMS) $(OUTPUT)perf
 $(OUTPUT)perf.o: perf.c $(OUTPUT)common-cmds.h $(OUTPUT)PERF-CFLAGS
 	$(QUIET_CC)$(CC) -include $(OUTPUT)PERF-VERSION-FILE \
 		'-DPERF_HTML_PATH="$(htmldir_SQ)"' \
-		$(ALL_CFLAGS) -c $(filter %.c,$^) -o $@
+		$(CFLAGS) -c $(filter %.c,$^) -o $@
 
 $(OUTPUT)perf: $(OUTPUT)perf.o $(BUILTIN_OBJS) $(PERFLIBS)
-	$(QUIET_LINK)$(CC) $(ALL_CFLAGS) $(ALL_LDFLAGS) $(OUTPUT)perf.o \
+	$(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $(OUTPUT)perf.o \
                $(BUILTIN_OBJS) $(LIBS) -o $@
 
 $(OUTPUT)builtin-help.o: builtin-help.c $(OUTPUT)common-cmds.h $(OUTPUT)PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) \
+	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) \
 		'-DPERF_HTML_PATH="$(htmldir_SQ)"' \
 		'-DPERF_MAN_PATH="$(mandir_SQ)"' \
 		'-DPERF_INFO_PATH="$(infodir_SQ)"' $<
 
 $(OUTPUT)builtin-timechart.o: builtin-timechart.c $(OUTPUT)common-cmds.h $(OUTPUT)PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) \
+	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) \
 		'-DPERF_HTML_PATH="$(htmldir_SQ)"' \
 		'-DPERF_MAN_PATH="$(mandir_SQ)"' \
 		'-DPERF_INFO_PATH="$(infodir_SQ)"' $<
@@ -977,77 +574,77 @@ $(OUTPUT)perf.o perf.spec \
 # over the general rule for .o
 
 $(OUTPUT)util/%-flex.o: $(OUTPUT)util/%-flex.c $(OUTPUT)PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o $@ -c -Iutil/ $(ALL_CFLAGS) -w $<
+	$(QUIET_CC)$(CC) -o $@ -c -Iutil/ $(CFLAGS) -w $<
 
 $(OUTPUT)util/%-bison.o: $(OUTPUT)util/%-bison.c $(OUTPUT)PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o $@ -c -Iutil/ $(ALL_CFLAGS) -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w $<
+	$(QUIET_CC)$(CC) -o $@ -c -Iutil/ $(CFLAGS) -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w $<
 
 $(OUTPUT)%.o: %.c $(OUTPUT)PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $<
+	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $<
 $(OUTPUT)%.i: %.c $(OUTPUT)PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o $@ -E $(ALL_CFLAGS) $<
+	$(QUIET_CC)$(CC) -o $@ -E $(CFLAGS) $<
 $(OUTPUT)%.s: %.c $(OUTPUT)PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o $@ -S $(ALL_CFLAGS) $<
+	$(QUIET_CC)$(CC) -o $@ -S $(CFLAGS) $<
 $(OUTPUT)%.o: %.S
-	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $<
+	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $<
 $(OUTPUT)%.s: %.S
-	$(QUIET_CC)$(CC) -o $@ -E $(ALL_CFLAGS) $<
+	$(QUIET_CC)$(CC) -o $@ -E $(CFLAGS) $<
 
 $(OUTPUT)util/exec_cmd.o: util/exec_cmd.c $(OUTPUT)PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) \
+	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) \
 		'-DPERF_EXEC_PATH="$(perfexecdir_SQ)"' \
 		'-DPREFIX="$(prefix_SQ)"' \
 		$<
 
 $(OUTPUT)tests/attr.o: tests/attr.c $(OUTPUT)PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) \
+	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) \
 		'-DBINDIR="$(bindir_SQ)"' -DPYTHON='"$(PYTHON_WORD)"' \
 		$<
 
 $(OUTPUT)tests/python-use.o: tests/python-use.c $(OUTPUT)PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) \
+	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) \
 		-DPYTHONPATH='"$(OUTPUT)python"' \
 		-DPYTHON='"$(PYTHON_WORD)"' \
 		$<
 
 $(OUTPUT)util/config.o: util/config.c $(OUTPUT)PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
+	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
 
 $(OUTPUT)ui/browser.o: ui/browser.c $(OUTPUT)PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DENABLE_SLFUTURE_CONST $<
+	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DENABLE_SLFUTURE_CONST $<
 
 $(OUTPUT)ui/browsers/annotate.o: ui/browsers/annotate.c $(OUTPUT)PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DENABLE_SLFUTURE_CONST $<
+	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DENABLE_SLFUTURE_CONST $<
 
 $(OUTPUT)ui/browsers/hists.o: ui/browsers/hists.c $(OUTPUT)PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DENABLE_SLFUTURE_CONST $<
+	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DENABLE_SLFUTURE_CONST $<
 
 $(OUTPUT)ui/browsers/map.o: ui/browsers/map.c $(OUTPUT)PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DENABLE_SLFUTURE_CONST $<
+	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DENABLE_SLFUTURE_CONST $<
 
 $(OUTPUT)ui/browsers/scripts.o: ui/browsers/scripts.c $(OUTPUT)PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DENABLE_SLFUTURE_CONST $<
+	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DENABLE_SLFUTURE_CONST $<
 
 $(OUTPUT)util/rbtree.o: ../../lib/rbtree.c $(OUTPUT)PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -Wno-unused-parameter -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
+	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-unused-parameter -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
 
 $(OUTPUT)util/parse-events.o: util/parse-events.c $(OUTPUT)PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -Wno-redundant-decls $<
+	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-redundant-decls $<
 
 $(OUTPUT)util/scripting-engines/trace-event-perl.o: util/scripting-engines/trace-event-perl.c $(OUTPUT)PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow $<
+	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow $<
 
 $(OUTPUT)scripts/perl/Perf-Trace-Util/Context.o: scripts/perl/Perf-Trace-Util/Context.c $(OUTPUT)PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs $<
+	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs $<
 
 $(OUTPUT)util/scripting-engines/trace-event-python.o: util/scripting-engines/trace-event-python.c $(OUTPUT)PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow $<
+	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow $<
 
 $(OUTPUT)scripts/python/Perf-Trace-Util/Context.o: scripts/python/Perf-Trace-Util/Context.c $(OUTPUT)PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs $<
+	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs $<
 
 $(OUTPUT)perf-%: %.o $(PERFLIBS)
-	$(QUIET_LINK)$(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) $(LIBS)
+	$(QUIET_LINK)$(CC) $(CFLAGS) -o $@ $(LDFLAGS) $(filter %.o,$^) $(LIBS)
 
 $(LIB_OBJS) $(BUILTIN_OBJS): $(LIB_H)
 $(patsubst perf-%,%.o,$(PROGRAMS)): $(LIB_H) $(wildcard */*.h)
@@ -1134,7 +731,7 @@ cscope:
 	$(FIND) . -name '*.[hcS]' -print | xargs cscope -b
 
 ### Detect prefix changes
-TRACK_CFLAGS = $(subst ','\'',$(ALL_CFLAGS)):\
+TRACK_CFLAGS = $(subst ','\'',$(CFLAGS)):\
              $(bindir_SQ):$(perfexecdir_SQ):$(template_dir_SQ):$(prefix_SQ)
 
 $(OUTPUT)PERF-CFLAGS: .FORCE-PERF-CFLAGS
@@ -1155,7 +752,7 @@ check: $(OUTPUT)common-cmds.h
 	then \
 		for i in *.c */*.c; \
 		do \
-			sparse $(ALL_CFLAGS) $(SPARSE_FLAGS) $$i || exit; \
+			sparse $(CFLAGS) $(SPARSE_FLAGS) $$i || exit; \
 		done; \
 	else \
 		exit 1; \
@@ -1163,13 +760,6 @@ check: $(OUTPUT)common-cmds.h
 
 ### Installation rules
 
-ifneq ($(filter /%,$(firstword $(perfexecdir))),)
-perfexec_instdir = $(perfexecdir)
-else
-perfexec_instdir = $(prefix)/$(perfexecdir)
-endif
-perfexec_instdir_SQ = $(subst ','\'',$(perfexec_instdir))
-
 install-bin: all
 	$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(bindir_SQ)'
 	$(INSTALL) $(OUTPUT)perf '$(DESTDIR_SQ)$(bindir_SQ)'
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 2d0462d..da8f8eb 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -323,13 +323,20 @@ static void hists__baseline_only(struct hists *hists)
 
 static void hists__precompute(struct hists *hists)
 {
-	struct rb_node *next = rb_first(&hists->entries);
+	struct rb_root *root;
+	struct rb_node *next;
+
+	if (sort__need_collapse)
+		root = &hists->entries_collapsed;
+	else
+		root = hists->entries_in;
 
+	next = rb_first(root);
 	while (next != NULL) {
-		struct hist_entry *he = rb_entry(next, struct hist_entry, rb_node);
+		struct hist_entry *he = rb_entry(next, struct hist_entry, rb_node_in);
 		struct hist_entry *pair = hist_entry__next_pair(he);
 
-		next = rb_next(&he->rb_node);
+		next = rb_next(&he->rb_node_in);
 		if (!pair)
 			continue;
 
@@ -457,7 +464,7 @@ static void hists__process(struct hists *old, struct hists *new)
 		hists__output_resort(new);
 	}
 
-	hists__fprintf(new, true, 0, 0, stdout);
+	hists__fprintf(new, true, 0, 0, 0, stdout);
 }
 
 static int __cmd_diff(void)
@@ -611,9 +618,7 @@ int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	setup_pager();
 
-	sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "dso", NULL);
-	sort_entry__setup_elide(&sort_comm, symbol_conf.comm_list, "comm", NULL);
-	sort_entry__setup_elide(&sort_sym, symbol_conf.sym_list, "symbol", NULL);
+	sort__setup_elide(NULL);
 
 	return __cmd_diff();
 }
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 533501e..24b78ae 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -328,6 +328,7 @@ static int kvm_events_hash_fn(u64 key)
 static bool kvm_event_expand(struct kvm_event *event, int vcpu_id)
 {
 	int old_max_vcpu = event->max_vcpu;
+	void *prev;
 
 	if (vcpu_id < event->max_vcpu)
 		return true;
@@ -335,9 +336,11 @@ static bool kvm_event_expand(struct kvm_event *event, int vcpu_id)
 	while (event->max_vcpu <= vcpu_id)
 		event->max_vcpu += DEFAULT_VCPU_NUM;
 
+	prev = event->vcpu;
 	event->vcpu = realloc(event->vcpu,
 			      event->max_vcpu * sizeof(*event->vcpu));
 	if (!event->vcpu) {
+		free(prev);
 		pr_err("Not enough memory\n");
 		return false;
 	}
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index cdf58ec..fff985c 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -198,7 +198,6 @@ static void perf_record__sig_exit(int exit_status __maybe_unused, void *arg)
 		return;
 
 	signal(signr, SIG_DFL);
-	kill(getpid(), signr);
 }
 
 static bool perf_evlist__equal(struct perf_evlist *evlist,
@@ -404,6 +403,7 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
 	signal(SIGCHLD, sig_handler);
 	signal(SIGINT, sig_handler);
 	signal(SIGUSR1, sig_handler);
+	signal(SIGTERM, sig_handler);
 
 	if (!output_name) {
 		if (!fstat(STDOUT_FILENO, &st) && S_ISFIFO(st.st_mode))
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index bd0ca81..ca98d34 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -52,6 +52,7 @@ struct perf_report {
 	symbol_filter_t		annotate_init;
 	const char		*cpu_list;
 	const char		*symbol_filter_str;
+	float			min_percent;
 	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 };
 
@@ -61,6 +62,11 @@ static int perf_report_config(const char *var, const char *value, void *cb)
 		symbol_conf.event_group = perf_config_bool(var, value);
 		return 0;
 	}
+	if (!strcmp(var, "report.percent-limit")) {
+		struct perf_report *rep = cb;
+		rep->min_percent = strtof(value, NULL);
+		return 0;
+	}
 
 	return perf_default_config(var, value, cb);
 }
@@ -187,6 +193,9 @@ static int perf_report__add_branch_hist_entry(struct perf_tool *tool,
 	for (i = 0; i < sample->branch_stack->nr; i++) {
 		if (rep->hide_unresolved && !(bi[i].from.sym && bi[i].to.sym))
 			continue;
+
+		err = -ENOMEM;
+
 		/*
 		 * The report shows the percentage of total branches captured
 		 * and not events sampled. Thus we use a pseudo period of 1.
@@ -195,7 +204,6 @@ static int perf_report__add_branch_hist_entry(struct perf_tool *tool,
 				&bi[i], 1, 1);
 		if (he) {
 			struct annotation *notes;
-			err = -ENOMEM;
 			bx = he->branch_info;
 			if (bx->from.sym && use_browser == 1 && sort__has_sym) {
 				notes = symbol__annotation(bx->from.sym);
@@ -226,11 +234,12 @@ static int perf_report__add_branch_hist_entry(struct perf_tool *tool,
 			}
 			evsel->hists.stats.total_period += 1;
 			hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
-			err = 0;
 		} else
-			return -ENOMEM;
+			goto out;
 	}
+	err = 0;
 out:
+	free(bi);
 	return err;
 }
 
@@ -294,6 +303,7 @@ static int process_sample_event(struct perf_tool *tool,
 {
 	struct perf_report *rep = container_of(tool, struct perf_report, tool);
 	struct addr_location al;
+	int ret;
 
 	if (perf_event__preprocess_sample(event, machine, &al, sample,
 					  rep->annotate_init) < 0) {
@@ -308,28 +318,25 @@ static int process_sample_event(struct perf_tool *tool,
 	if (rep->cpu_list && !test_bit(sample->cpu, rep->cpu_bitmap))
 		return 0;
 
-	if (sort__branch_mode == 1) {
-		if (perf_report__add_branch_hist_entry(tool, &al, sample,
-						       evsel, machine)) {
+	if (sort__mode == SORT_MODE__BRANCH) {
+		ret = perf_report__add_branch_hist_entry(tool, &al, sample,
+							 evsel, machine);
+		if (ret < 0)
 			pr_debug("problem adding lbr entry, skipping event\n");
-			return -1;
-		}
 	} else if (rep->mem_mode == 1) {
-		if (perf_report__add_mem_hist_entry(tool, &al, sample,
-						    evsel, machine, event)) {
+		ret = perf_report__add_mem_hist_entry(tool, &al, sample,
+						      evsel, machine, event);
+		if (ret < 0)
 			pr_debug("problem adding mem entry, skipping event\n");
-			return -1;
-		}
 	} else {
 		if (al.map != NULL)
 			al.map->dso->hit = 1;
 
-		if (perf_evsel__add_hist_entry(evsel, &al, sample, machine)) {
+		ret = perf_evsel__add_hist_entry(evsel, &al, sample, machine);
+		if (ret < 0)
 			pr_debug("problem incrementing symbol period, skipping event\n");
-			return -1;
-		}
 	}
-	return 0;
+	return ret;
 }
 
 static int process_read_event(struct perf_tool *tool,
@@ -384,7 +391,7 @@ static int perf_report__setup_sample_type(struct perf_report *rep)
 			}
 	}
 
-	if (sort__branch_mode == 1) {
+	if (sort__mode == SORT_MODE__BRANCH) {
 		if (!self->fd_pipe &&
 		    !(sample_type & PERF_SAMPLE_BRANCH_STACK)) {
 			ui__error("Selected -b but no branch data. "
@@ -455,7 +462,7 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
 			continue;
 
 		hists__fprintf_nr_sample_events(rep, hists, evname, stdout);
-		hists__fprintf(hists, true, 0, 0, stdout);
+		hists__fprintf(hists, true, 0, 0, rep->min_percent, stdout);
 		fprintf(stdout, "\n\n");
 	}
 
@@ -574,8 +581,8 @@ static int __cmd_report(struct perf_report *rep)
 	if (use_browser > 0) {
 		if (use_browser == 1) {
 			ret = perf_evlist__tui_browse_hists(session->evlist,
-							help,
-							NULL,
+							help, NULL,
+							rep->min_percent,
 							&session->header.env);
 			/*
 			 * Usually "ret" is the last pressed key, and we only
@@ -586,7 +593,7 @@ static int __cmd_report(struct perf_report *rep)
 
 		} else if (use_browser == 2) {
 			perf_evlist__gtk_browse_hists(session->evlist, help,
-						      NULL);
+						      NULL, rep->min_percent);
 		}
 	} else
 		perf_evlist__tty_browse_hists(session->evlist, rep, help);
@@ -691,7 +698,19 @@ static int
 parse_branch_mode(const struct option *opt __maybe_unused,
 		  const char *str __maybe_unused, int unset)
 {
-	sort__branch_mode = !unset;
+	int *branch_mode = opt->value;
+
+	*branch_mode = !unset;
+	return 0;
+}
+
+static int
+parse_percent_limit(const struct option *opt, const char *str,
+		    int unset __maybe_unused)
+{
+	struct perf_report *rep = opt->value;
+
+	rep->min_percent = strtof(str, NULL);
 	return 0;
 }
 
@@ -700,6 +719,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 	struct perf_session *session;
 	struct stat st;
 	bool has_br_stack = false;
+	int branch_mode = -1;
 	int ret = -1;
 	char callchain_default_opt[] = "fractal,0.5,callee";
 	const char * const report_usage[] = {
@@ -796,17 +816,19 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 		    "Show a column with the sum of periods"),
 	OPT_BOOLEAN(0, "group", &symbol_conf.event_group,
 		    "Show event group information together"),
-	OPT_CALLBACK_NOOPT('b', "branch-stack", &sort__branch_mode, "",
+	OPT_CALLBACK_NOOPT('b', "branch-stack", &branch_mode, "",
 		    "use branch records for histogram filling", parse_branch_mode),
 	OPT_STRING(0, "objdump", &objdump_path, "path",
 		   "objdump binary to use for disassembly and annotations"),
 	OPT_BOOLEAN(0, "demangle", &symbol_conf.demangle,
 		    "Disable symbol demangling"),
 	OPT_BOOLEAN(0, "mem-mode", &report.mem_mode, "mem access profile"),
+	OPT_CALLBACK(0, "percent-limit", &report, "percent",
+		     "Don't show entries under that percent", parse_percent_limit),
 	OPT_END()
 	};
 
-	perf_config(perf_report_config, NULL);
+	perf_config(perf_report_config, &report);
 
 	argc = parse_options(argc, argv, options, report_usage, 0);
 
@@ -846,11 +868,11 @@ repeat:
 	has_br_stack = perf_header__has_feat(&session->header,
 					     HEADER_BRANCH_STACK);
 
-	if (sort__branch_mode == -1 && has_br_stack)
-		sort__branch_mode = 1;
+	if (branch_mode == -1 && has_br_stack)
+		sort__mode = SORT_MODE__BRANCH;
 
-	/* sort__branch_mode could be 0 if --no-branch-stack */
-	if (sort__branch_mode == 1) {
+	/* sort__mode could be NORMAL if --no-branch-stack */
+	if (sort__mode == SORT_MODE__BRANCH) {
 		/*
 		 * if no sort_order is provided, then specify
 		 * branch-mode specific order
@@ -861,10 +883,12 @@ repeat:
 
 	}
 	if (report.mem_mode) {
-		if (sort__branch_mode == 1) {
+		if (sort__mode == SORT_MODE__BRANCH) {
 			fprintf(stderr, "branch and mem mode incompatible\n");
 			goto error;
 		}
+		sort__mode = SORT_MODE__MEMORY;
+
 		/*
 		 * if no sort_order is provided, then specify
 		 * branch-mode specific order
@@ -929,25 +953,7 @@ repeat:
 		report.symbol_filter_str = argv[0];
 	}
 
-	sort_entry__setup_elide(&sort_comm, symbol_conf.comm_list, "comm", stdout);
-
-	if (sort__branch_mode == 1) {
-		sort_entry__setup_elide(&sort_dso_from, symbol_conf.dso_from_list, "dso_from", stdout);
-		sort_entry__setup_elide(&sort_dso_to, symbol_conf.dso_to_list, "dso_to", stdout);
-		sort_entry__setup_elide(&sort_sym_from, symbol_conf.sym_from_list, "sym_from", stdout);
-		sort_entry__setup_elide(&sort_sym_to, symbol_conf.sym_to_list, "sym_to", stdout);
-	} else {
-		if (report.mem_mode) {
-			sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "symbol_daddr", stdout);
-			sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "dso_daddr", stdout);
-			sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "mem", stdout);
-			sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "local_weight", stdout);
-			sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "tlb", stdout);
-			sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "snoop", stdout);
-		}
-		sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "dso", stdout);
-		sort_entry__setup_elide(&sort_sym, symbol_conf.sym_list, "symbol", stdout);
-	}
+	sort__setup_elide(stdout);
 
 	ret = __cmd_report(&report);
 	if (ret == K_SWITCH_INPUT_DATA) {
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 67bdb9f..f036af9b 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -70,10 +70,11 @@
 
 static volatile int done;
 
+#define HEADER_LINE_NR  5
+
 static void perf_top__update_print_entries(struct perf_top *top)
 {
-	if (top->print_entries > 9)
-		top->print_entries -= 9;
+	top->print_entries = top->winsize.ws_row - HEADER_LINE_NR;
 }
 
 static void perf_top__sig_winch(int sig __maybe_unused,
@@ -82,13 +83,6 @@ static void perf_top__sig_winch(int sig __maybe_unused,
 	struct perf_top *top = arg;
 
 	get_term_dimensions(&top->winsize);
-	if (!top->print_entries
-	    || (top->print_entries+4) > top->winsize.ws_row) {
-		top->print_entries = top->winsize.ws_row;
-	} else {
-		top->print_entries += 4;
-		top->winsize.ws_row = top->print_entries;
-	}
 	perf_top__update_print_entries(top);
 }
 
@@ -251,8 +245,11 @@ static struct hist_entry *perf_evsel__add_hist_entry(struct perf_evsel *evsel,
 {
 	struct hist_entry *he;
 
+	pthread_mutex_lock(&evsel->hists.lock);
 	he = __hists__add_entry(&evsel->hists, al, NULL, sample->period,
 				sample->weight);
+	pthread_mutex_unlock(&evsel->hists.lock);
+
 	if (he == NULL)
 		return NULL;
 
@@ -290,16 +287,17 @@ static void perf_top__print_sym_table(struct perf_top *top)
 		return;
 	}
 
-	hists__collapse_resort_threaded(&top->sym_evsel->hists);
-	hists__output_resort_threaded(&top->sym_evsel->hists);
-	hists__decay_entries_threaded(&top->sym_evsel->hists,
-				      top->hide_user_symbols,
-				      top->hide_kernel_symbols);
+	hists__collapse_resort(&top->sym_evsel->hists);
+	hists__output_resort(&top->sym_evsel->hists);
+	hists__decay_entries(&top->sym_evsel->hists,
+			     top->hide_user_symbols,
+			     top->hide_kernel_symbols);
 	hists__output_recalc_col_len(&top->sym_evsel->hists,
-				     top->winsize.ws_row - 3);
+				     top->print_entries - printed);
 	putchar('\n');
 	hists__fprintf(&top->sym_evsel->hists, false,
-		       top->winsize.ws_row - 4 - printed, win_width, stdout);
+		       top->print_entries - printed, win_width,
+		       top->min_percent, stdout);
 }
 
 static void prompt_integer(int *target, const char *msg)
@@ -477,7 +475,6 @@ static bool perf_top__handle_keypress(struct perf_top *top, int c)
 				perf_top__sig_winch(SIGWINCH, NULL, top);
 				sigaction(SIGWINCH, &act, NULL);
 			} else {
-				perf_top__sig_winch(SIGWINCH, NULL, top);
 				signal(SIGWINCH, SIG_DFL);
 			}
 			break;
@@ -556,11 +553,11 @@ static void perf_top__sort_new_samples(void *arg)
 	if (t->evlist->selected != NULL)
 		t->sym_evsel = t->evlist->selected;
 
-	hists__collapse_resort_threaded(&t->sym_evsel->hists);
-	hists__output_resort_threaded(&t->sym_evsel->hists);
-	hists__decay_entries_threaded(&t->sym_evsel->hists,
-				      t->hide_user_symbols,
-				      t->hide_kernel_symbols);
+	hists__collapse_resort(&t->sym_evsel->hists);
+	hists__output_resort(&t->sym_evsel->hists);
+	hists__decay_entries(&t->sym_evsel->hists,
+			     t->hide_user_symbols,
+			     t->hide_kernel_symbols);
 }
 
 static void *display_thread_tui(void *arg)
@@ -584,7 +581,7 @@ static void *display_thread_tui(void *arg)
 	list_for_each_entry(pos, &top->evlist->entries, node)
 		pos->hists.uid_filter_str = top->record_opts.target.uid_str;
 
-	perf_evlist__tui_browse_hists(top->evlist, help, &hbt,
+	perf_evlist__tui_browse_hists(top->evlist, help, &hbt, top->min_percent,
 				      &top->session->header.env);
 
 	done = 1;
@@ -794,7 +791,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
 				return;
 		}
 
-		if (top->sort_has_symbols)
+		if (sort__has_sym)
 			perf_top__record_precise_ip(top, he, evsel->idx, ip);
 	}
 
@@ -912,9 +909,9 @@ out_err:
 	return -1;
 }
 
-static int perf_top__setup_sample_type(struct perf_top *top)
+static int perf_top__setup_sample_type(struct perf_top *top __maybe_unused)
 {
-	if (!top->sort_has_symbols) {
+	if (!sort__has_sym) {
 		if (symbol_conf.use_callchain) {
 			ui__error("Selected -g but \"sym\" not present in --sort/-s.");
 			return -EINVAL;
@@ -1025,6 +1022,16 @@ parse_callchain_opt(const struct option *opt, const char *arg, int unset)
 	return record_parse_callchain_opt(opt, arg, unset);
 }
 
+static int
+parse_percent_limit(const struct option *opt, const char *arg,
+		    int unset __maybe_unused)
+{
+	struct perf_top *top = opt->value;
+
+	top->min_percent = strtof(arg, NULL);
+	return 0;
+}
+
 int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	int status;
@@ -1110,6 +1117,8 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style",
 		   "Specify disassembler style (e.g. -M intel for intel syntax)"),
 	OPT_STRING('u', "uid", &target->uid_str, "user", "user to profile"),
+	OPT_CALLBACK(0, "percent-limit", &top, "percent",
+		     "Don't show entries under that percent", parse_percent_limit),
 	OPT_END()
 	};
 	const char * const top_usage[] = {
@@ -1133,6 +1142,9 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (setup_sorting() < 0)
 		usage_with_options(top_usage, options);
 
+	/* display thread wants entries to be collapsed in a different tree */
+	sort__need_collapse = 1;
+
 	if (top.use_stdio)
 		use_browser = 0;
 	else if (top.use_tui)
@@ -1200,15 +1212,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (symbol__init() < 0)
 		return -1;
 
-	sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "dso", stdout);
-	sort_entry__setup_elide(&sort_comm, symbol_conf.comm_list, "comm", stdout);
-	sort_entry__setup_elide(&sort_sym, symbol_conf.sym_list, "symbol", stdout);
-
-	/*
-	 * Avoid annotation data structures overhead when symbols aren't on the
-	 * sort list.
-	 */
-	top.sort_has_symbols = sort_sym.list.next != NULL;
+	sort__setup_elide(stdout);
 
 	get_term_dimensions(&top.winsize);
 	if (top.print_entries == 0) {
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
new file mode 100644
index 0000000..f139dcd
--- /dev/null
+++ b/tools/perf/config/Makefile
@@ -0,0 +1,477 @@
+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) $(EXTRA_WARNINGS)
+
+# Additional ARCH settings for x86
+ifeq ($(ARCH),i386)
+  override ARCH := x86
+  NO_PERF_REGS := 0
+  LIBUNWIND_LIBS = -lunwind -lunwind-x86
+endif
+
+ifeq ($(ARCH),x86_64)
+  override ARCH := x86
+  IS_X86_64 := 0
+  ifeq (, $(findstring m32,$(CFLAGS)))
+    IS_X86_64 := $(shell echo __x86_64__ | ${CC} -E -x c - | tail -n 1)
+  endif
+  ifeq (${IS_X86_64}, 1)
+    RAW_ARCH := x86_64
+    CFLAGS += -DARCH_X86_64
+    ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memset_64.S
+  endif
+  NO_PERF_REGS := 0
+  LIBUNWIND_LIBS = -lunwind -lunwind-x86_64
+endif
+
+ifeq ($(NO_PERF_REGS),0)
+  CFLAGS += -DHAVE_PERF_REGS
+endif
+
+ifeq ($(src-perf),)
+src-perf := $(srctree)/tools/perf
+endif
+
+ifeq ($(obj-perf),)
+obj-perf := $(objtree)
+endif
+
+ifneq ($(obj-perf),)
+obj-perf := $(abspath $(obj-perf))/
+endif
+
+# include ARCH specific config
+-include $(src-perf)/arch/$(ARCH)/Makefile
+
+include $(src-perf)/config/feature-tests.mak
+include $(src-perf)/config/utilities.mak
+
+ifeq ($(call get-executable,$(FLEX)),)
+  dummy := $(error Error: $(FLEX) is missing on this system, please install it)
+endif
+
+ifeq ($(call get-executable,$(BISON)),)
+  dummy := $(error Error: $(BISON) is missing on this system, please install it)
+endif
+
+# Treat warnings as errors unless directed not to
+ifneq ($(WERROR),0)
+  CFLAGS += -Werror
+endif
+
+ifeq ("$(origin DEBUG)", "command line")
+  PERF_DEBUG = $(DEBUG)
+endif
+ifndef PERF_DEBUG
+  CFLAGS += -O6
+endif
+
+ifdef PARSER_DEBUG
+  PARSER_DEBUG_BISON := -t
+  PARSER_DEBUG_FLEX  := -d
+  CFLAGS             += -DPARSER_DEBUG
+endif
+
+CFLAGS += -fno-omit-frame-pointer
+CFLAGS += -ggdb3
+CFLAGS += -funwind-tables
+CFLAGS += -Wall
+CFLAGS += -Wextra
+CFLAGS += -std=gnu99
+
+EXTLIBS = -lpthread -lrt -lelf -lm
+
+ifeq ($(call try-cc,$(SOURCE_HELLO),$(CFLAGS) -Werror -fstack-protector-all,-fstack-protector-all),y)
+  CFLAGS += -fstack-protector-all
+endif
+
+ifeq ($(call try-cc,$(SOURCE_HELLO),$(CFLAGS) -Werror -Wstack-protector,-Wstack-protector),y)
+  CFLAGS += -Wstack-protector
+endif
+
+ifeq ($(call try-cc,$(SOURCE_HELLO),$(CFLAGS) -Werror -Wvolatile-register-var,-Wvolatile-register-var),y)
+  CFLAGS += -Wvolatile-register-var
+endif
+
+ifndef PERF_DEBUG
+  ifeq ($(call try-cc,$(SOURCE_HELLO),$(CFLAGS) -D_FORTIFY_SOURCE=2,-D_FORTIFY_SOURCE=2),y)
+    CFLAGS += -D_FORTIFY_SOURCE=2
+  endif
+endif
+
+CFLAGS += -I$(src-perf)/util/include
+CFLAGS += -I$(src-perf)/arch/$(ARCH)/include
+CFLAGS += -I$(srctree)/arch/$(ARCH)/include/uapi
+CFLAGS += -I$(srctree)/arch/$(ARCH)/include
+CFLAGS += -I$(srctree)/include/uapi
+CFLAGS += -I$(srctree)/include
+
+# $(obj-perf)      for generated common-cmds.h
+# $(obj-perf)/util for generated bison/flex headers
+ifneq ($(OUTPUT),)
+CFLAGS += -I$(obj-perf)/util
+CFLAGS += -I$(obj-perf)
+endif
+
+CFLAGS += -I$(src-perf)/util
+CFLAGS += -I$(src-perf)
+CFLAGS += -I$(TRACE_EVENT_DIR)
+CFLAGS += -I$(srctree)/tools/lib/
+
+CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
+
+ifndef NO_BIONIC
+ifeq ($(call try-cc,$(SOURCE_BIONIC),$(CFLAGS),bionic),y)
+  BIONIC := 1
+  EXTLIBS := $(filter-out -lrt,$(EXTLIBS))
+  EXTLIBS := $(filter-out -lpthread,$(EXTLIBS))
+endif
+endif # NO_BIONIC
+
+ifdef NO_LIBELF
+  NO_DWARF := 1
+  NO_DEMANGLE := 1
+  NO_LIBUNWIND := 1
+else
+FLAGS_LIBELF=$(CFLAGS) $(LDFLAGS) $(EXTLIBS)
+ifneq ($(call try-cc,$(SOURCE_LIBELF),$(FLAGS_LIBELF),libelf),y)
+  FLAGS_GLIBC=$(CFLAGS) $(LDFLAGS)
+  ifeq ($(call try-cc,$(SOURCE_GLIBC),$(FLAGS_GLIBC),glibc),y)
+    LIBC_SUPPORT := 1
+  endif
+  ifeq ($(BIONIC),1)
+    LIBC_SUPPORT := 1
+  endif
+  ifeq ($(LIBC_SUPPORT),1)
+    msg := $(warning No libelf found, disables 'probe' tool, please install elfutils-libelf-devel/libelf-dev);
+
+    NO_LIBELF := 1
+    NO_DWARF := 1
+    NO_DEMANGLE := 1
+  else
+    msg := $(error No gnu/libc-version.h found, please install glibc-dev[el]/glibc-static);
+  endif
+else
+  # for linking with debug library, run like:
+  # make DEBUG=1 LIBDW_DIR=/opt/libdw/
+  ifdef LIBDW_DIR
+    LIBDW_CFLAGS  := -I$(LIBDW_DIR)/include
+    LIBDW_LDFLAGS := -L$(LIBDW_DIR)/lib
+  endif
+
+  FLAGS_DWARF=$(CFLAGS) $(LIBDW_CFLAGS) -ldw -lelf $(LIBDW_LDFLAGS) $(LDFLAGS) $(EXTLIBS)
+  ifneq ($(call try-cc,$(SOURCE_DWARF),$(FLAGS_DWARF),libdw),y)
+    msg := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev);
+    NO_DWARF := 1
+  endif # Dwarf support
+endif # SOURCE_LIBELF
+endif # NO_LIBELF
+
+ifndef NO_LIBELF
+CFLAGS += -DLIBELF_SUPPORT
+FLAGS_LIBELF=$(CFLAGS) $(LDFLAGS) $(EXTLIBS)
+ifeq ($(call try-cc,$(SOURCE_ELF_MMAP),$(FLAGS_LIBELF),-DLIBELF_MMAP),y)
+  CFLAGS += -DLIBELF_MMAP
+endif
+
+# include ARCH specific config
+-include $(src-perf)/arch/$(ARCH)/Makefile
+
+ifndef NO_DWARF
+ifeq ($(origin PERF_HAVE_DWARF_REGS), undefined)
+  msg := $(warning DWARF register mappings have not been defined for architecture $(ARCH), DWARF support disabled);
+  NO_DWARF := 1
+else
+  CFLAGS += -DDWARF_SUPPORT $(LIBDW_CFLAGS)
+  LDFLAGS += $(LIBDW_LDFLAGS)
+  EXTLIBS += -lelf -ldw
+endif # PERF_HAVE_DWARF_REGS
+endif # NO_DWARF
+
+endif # NO_LIBELF
+
+ifndef NO_LIBELF
+CFLAGS += -DLIBELF_SUPPORT
+FLAGS_LIBELF=$(CFLAGS) $(LDFLAGS) $(EXTLIBS)
+ifeq ($(call try-cc,$(SOURCE_ELF_MMAP),$(FLAGS_LIBELF),-DLIBELF_MMAP),y)
+  CFLAGS += -DLIBELF_MMAP
+endif # try-cc
+endif # NO_LIBELF
+
+# There's only x86 (both 32 and 64) support for CFI unwind so far
+ifneq ($(ARCH),x86)
+  NO_LIBUNWIND := 1
+endif
+
+ifndef NO_LIBUNWIND
+# for linking with debug library, run like:
+# make DEBUG=1 LIBUNWIND_DIR=/opt/libunwind/
+ifdef LIBUNWIND_DIR
+  LIBUNWIND_CFLAGS  := -I$(LIBUNWIND_DIR)/include
+  LIBUNWIND_LDFLAGS := -L$(LIBUNWIND_DIR)/lib
+endif
+
+FLAGS_UNWIND=$(LIBUNWIND_CFLAGS) $(CFLAGS) $(LIBUNWIND_LDFLAGS) $(LDFLAGS) $(EXTLIBS) $(LIBUNWIND_LIBS)
+ifneq ($(call try-cc,$(SOURCE_LIBUNWIND),$(FLAGS_UNWIND),libunwind),y)
+  msg := $(warning No libunwind found, disabling post unwind support. Please install libunwind-dev[el] >= 0.99);
+  NO_LIBUNWIND := 1
+endif # Libunwind support
+endif # NO_LIBUNWIND
+
+ifndef NO_LIBUNWIND
+  CFLAGS += -DLIBUNWIND_SUPPORT
+  EXTLIBS += $(LIBUNWIND_LIBS)
+  CFLAGS += $(LIBUNWIND_CFLAGS)
+  LDFLAGS += $(LIBUNWIND_LDFLAGS)
+endif # NO_LIBUNWIND
+
+ifndef NO_LIBAUDIT
+  FLAGS_LIBAUDIT = $(CFLAGS) $(LDFLAGS) -laudit
+  ifneq ($(call try-cc,$(SOURCE_LIBAUDIT),$(FLAGS_LIBAUDIT),libaudit),y)
+    msg := $(warning No libaudit.h found, disables 'trace' tool, please install audit-libs-devel or libaudit-dev);
+    NO_LIBAUDIT := 1
+  else
+    CFLAGS += -DLIBAUDIT_SUPPORT
+    EXTLIBS += -laudit
+  endif
+endif
+
+ifdef NO_NEWT
+  NO_SLANG=1
+endif
+
+ifndef NO_SLANG
+  FLAGS_SLANG=$(CFLAGS) $(LDFLAGS) $(EXTLIBS) -I/usr/include/slang -lslang
+  ifneq ($(call try-cc,$(SOURCE_SLANG),$(FLAGS_SLANG),libslang),y)
+    msg := $(warning slang not found, disables TUI support. Please install slang-devel or libslang-dev);
+    NO_SLANG := 1
+  else
+    # Fedora has /usr/include/slang/slang.h, but ubuntu /usr/include/slang.h
+    CFLAGS += -I/usr/include/slang
+    CFLAGS += -DSLANG_SUPPORT
+    EXTLIBS += -lslang
+  endif
+endif
+
+ifndef NO_GTK2
+  FLAGS_GTK2=$(CFLAGS) $(LDFLAGS) $(EXTLIBS) $(shell pkg-config --libs --cflags gtk+-2.0 2>/dev/null)
+  ifneq ($(call try-cc,$(SOURCE_GTK2),$(FLAGS_GTK2),gtk2),y)
+    msg := $(warning GTK2 not found, disables GTK2 support. Please install gtk2-devel or libgtk2.0-dev);
+    NO_GTK2 := 1
+  else
+    ifeq ($(call try-cc,$(SOURCE_GTK2_INFOBAR),$(FLAGS_GTK2),-DHAVE_GTK_INFO_BAR),y)
+      CFLAGS += -DHAVE_GTK_INFO_BAR
+    endif
+    CFLAGS += -DGTK2_SUPPORT
+    CFLAGS += $(shell pkg-config --cflags gtk+-2.0 2>/dev/null)
+    EXTLIBS += $(shell pkg-config --libs gtk+-2.0 2>/dev/null)
+  endif
+endif
+
+grep-libs  = $(filter -l%,$(1))
+strip-libs = $(filter-out -l%,$(1))
+
+ifdef NO_LIBPERL
+  CFLAGS += -DNO_LIBPERL
+else
+  PERL_EMBED_LDOPTS = $(shell perl -MExtUtils::Embed -e ldopts 2>/dev/null)
+  PERL_EMBED_LDFLAGS = $(call strip-libs,$(PERL_EMBED_LDOPTS))
+  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) $(PERL_EMBED_LDOPTS)
+
+  ifneq ($(call try-cc,$(SOURCE_PERL_EMBED),$(FLAGS_PERL_EMBED),perl),y)
+    CFLAGS += -DNO_LIBPERL
+    NO_LIBPERL := 1
+  else
+    LDFLAGS += $(PERL_EMBED_LDFLAGS)
+    EXTLIBS += $(PERL_EMBED_LIBADD)
+  endif
+endif
+
+disable-python = $(eval $(disable-python_code))
+define disable-python_code
+  CFLAGS += -DNO_LIBPYTHON
+  $(if $(1),$(warning No $(1) was found))
+  $(warning Python support will not be built)
+  NO_LIBPYTHON := 1
+endef
+
+override PYTHON := \
+  $(call get-executable-or-default,PYTHON,python)
+
+ifndef PYTHON
+  $(call disable-python,python interpreter)
+else
+
+  PYTHON_WORD := $(call shell-wordify,$(PYTHON))
+
+  ifdef NO_LIBPYTHON
+    $(call disable-python)
+  else
+
+    override PYTHON_CONFIG := \
+      $(call get-executable-or-default,PYTHON_CONFIG,$(PYTHON)-config)
+
+    ifndef PYTHON_CONFIG
+      $(call disable-python,python-config tool)
+    else
+
+      PYTHON_CONFIG_SQ := $(call shell-sq,$(PYTHON_CONFIG))
+
+      PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null)
+      PYTHON_EMBED_LDFLAGS := $(call strip-libs,$(PYTHON_EMBED_LDOPTS))
+      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) $(PYTHON_EMBED_LDOPTS)
+
+      ifneq ($(call try-cc,$(SOURCE_PYTHON_EMBED),$(FLAGS_PYTHON_EMBED),python),y)
+        $(call disable-python,Python.h (for Python 2.x))
+      else
+
+        ifneq ($(call try-cc,$(SOURCE_PYTHON_VERSION),$(FLAGS_PYTHON_EMBED),python version),y)
+          $(warning Python 3 is not yet supported; please set)
+          $(warning PYTHON and/or PYTHON_CONFIG appropriately.)
+          $(warning If you also have Python 2 installed, then)
+          $(warning try something like:)
+          $(warning $(and ,))
+          $(warning $(and ,)  make PYTHON=python2)
+          $(warning $(and ,))
+          $(warning Otherwise, disable Python support entirely:)
+          $(warning $(and ,))
+          $(warning $(and ,)  make NO_LIBPYTHON=1)
+          $(warning $(and ,))
+          $(error   $(and ,))
+        else
+          LDFLAGS += $(PYTHON_EMBED_LDFLAGS)
+          EXTLIBS += $(PYTHON_EMBED_LIBADD)
+          LANG_BINDINGS += $(obj-perf)python/perf.so
+        endif
+      endif
+    endif
+  endif
+endif
+
+ifdef NO_DEMANGLE
+  CFLAGS += -DNO_DEMANGLE
+else
+  ifdef HAVE_CPLUS_DEMANGLE
+    EXTLIBS += -liberty
+    CFLAGS += -DHAVE_CPLUS_DEMANGLE
+  else
+    FLAGS_BFD=$(CFLAGS) $(LDFLAGS) $(EXTLIBS) -DPACKAGE='perf' -lbfd
+    has_bfd := $(call try-cc,$(SOURCE_BFD),$(FLAGS_BFD),libbfd)
+    ifeq ($(has_bfd),y)
+      EXTLIBS += -lbfd
+    else
+      FLAGS_BFD_IBERTY=$(FLAGS_BFD) -liberty
+      has_bfd_iberty := $(call try-cc,$(SOURCE_BFD),$(FLAGS_BFD_IBERTY),liberty)
+      ifeq ($(has_bfd_iberty),y)
+        EXTLIBS += -lbfd -liberty
+      else
+        FLAGS_BFD_IBERTY_Z=$(FLAGS_BFD_IBERTY) -lz
+        has_bfd_iberty_z := $(call try-cc,$(SOURCE_BFD),$(FLAGS_BFD_IBERTY_Z),libz)
+        ifeq ($(has_bfd_iberty_z),y)
+          EXTLIBS += -lbfd -liberty -lz
+        else
+          FLAGS_CPLUS_DEMANGLE=$(CFLAGS) $(LDFLAGS) $(EXTLIBS) -liberty
+          has_cplus_demangle := $(call try-cc,$(SOURCE_CPLUS_DEMANGLE),$(FLAGS_CPLUS_DEMANGLE),demangle)
+          ifeq ($(has_cplus_demangle),y)
+            EXTLIBS += -liberty
+            CFLAGS += -DHAVE_CPLUS_DEMANGLE
+          else
+            msg := $(warning No bfd.h/libbfd found, install binutils-dev[el]/zlib-static to gain symbol demangling)
+            CFLAGS += -DNO_DEMANGLE
+          endif
+        endif
+      endif
+    endif
+  endif
+endif
+
+ifndef NO_STRLCPY
+  ifeq ($(call try-cc,$(SOURCE_STRLCPY),,-DHAVE_STRLCPY),y)
+    CFLAGS += -DHAVE_STRLCPY
+  endif
+endif
+
+ifndef NO_ON_EXIT
+  ifeq ($(call try-cc,$(SOURCE_ON_EXIT),,-DHAVE_ON_EXIT),y)
+    CFLAGS += -DHAVE_ON_EXIT
+  endif
+endif
+
+ifndef NO_BACKTRACE
+  ifeq ($(call try-cc,$(SOURCE_BACKTRACE),,-DBACKTRACE_SUPPORT),y)
+    CFLAGS += -DBACKTRACE_SUPPORT
+  endif
+endif
+
+ifndef NO_LIBNUMA
+  FLAGS_LIBNUMA = $(CFLAGS) $(LDFLAGS) -lnuma
+  ifneq ($(call try-cc,$(SOURCE_LIBNUMA),$(FLAGS_LIBNUMA),libnuma),y)
+    msg := $(warning No numa.h found, disables 'perf bench numa mem' benchmark, please install numa-libs-devel or libnuma-dev);
+    NO_LIBNUMA := 1
+  else
+    CFLAGS += -DLIBNUMA_SUPPORT
+    EXTLIBS += -lnuma
+  endif
+endif
+
+# Among the variables below, these:
+#   perfexecdir
+#   template_dir
+#   mandir
+#   infodir
+#   htmldir
+#   ETC_PERFCONFIG (but not sysconfdir)
+# can be specified as a relative path some/where/else;
+# this is interpreted as relative to $(prefix) and "perf" at
+# runtime figures out where they are based on the path to the executable.
+# This can help installing the suite in a relocatable way.
+
+# Make the path relative to DESTDIR, not to prefix
+ifndef DESTDIR
+prefix = $(HOME)
+endif
+bindir_relative = bin
+bindir = $(prefix)/$(bindir_relative)
+mandir = share/man
+infodir = share/info
+perfexecdir = libexec/perf-core
+sharedir = $(prefix)/share
+template_dir = share/perf-core/templates
+htmldir = share/doc/perf-doc
+ifeq ($(prefix),/usr)
+sysconfdir = /etc
+ETC_PERFCONFIG = $(sysconfdir)/perfconfig
+else
+sysconfdir = $(prefix)/etc
+ETC_PERFCONFIG = etc/perfconfig
+endif
+lib = lib
+
+# Shell quote (do not use $(call) to accommodate ancient setups);
+ETC_PERFCONFIG_SQ = $(subst ','\'',$(ETC_PERFCONFIG))
+DESTDIR_SQ = $(subst ','\'',$(DESTDIR))
+bindir_SQ = $(subst ','\'',$(bindir))
+mandir_SQ = $(subst ','\'',$(mandir))
+infodir_SQ = $(subst ','\'',$(infodir))
+perfexecdir_SQ = $(subst ','\'',$(perfexecdir))
+template_dir_SQ = $(subst ','\'',$(template_dir))
+htmldir_SQ = $(subst ','\'',$(htmldir))
+prefix_SQ = $(subst ','\'',$(prefix))
+sysconfdir_SQ = $(subst ','\'',$(sysconfdir))
+
+ifneq ($(filter /%,$(firstword $(perfexecdir))),)
+perfexec_instdir = $(perfexecdir)
+else
+perfexec_instdir = $(prefix)/$(perfexecdir)
+endif
+perfexec_instdir_SQ = $(subst ','\'',$(perfexec_instdir))
diff --git a/tools/perf/tests/attr/base-record b/tools/perf/tests/attr/base-record
index b4fc835..e9bd639 100644
--- a/tools/perf/tests/attr/base-record
+++ b/tools/perf/tests/attr/base-record
@@ -27,8 +27,8 @@ watermark=0
 precise_ip=0
 mmap_data=0
 sample_id_all=1
-exclude_host=0
-exclude_guest=1
+exclude_host=0|1
+exclude_guest=0|1
 exclude_callchain_kernel=0
 exclude_callchain_user=0
 wakeup_events=0
diff --git a/tools/perf/tests/attr/base-stat b/tools/perf/tests/attr/base-stat
index 748ee94..91cd48b 100644
--- a/tools/perf/tests/attr/base-stat
+++ b/tools/perf/tests/attr/base-stat
@@ -27,8 +27,8 @@ watermark=0
 precise_ip=0
 mmap_data=0
 sample_id_all=0
-exclude_host=0
-exclude_guest=1
+exclude_host=0|1
+exclude_guest=0|1
 exclude_callchain_kernel=0
 exclude_callchain_user=0
 wakeup_events=0
diff --git a/tools/perf/tests/attr/test-record-data b/tools/perf/tests/attr/test-record-data
index 6627c3e..716e143 100644
--- a/tools/perf/tests/attr/test-record-data
+++ b/tools/perf/tests/attr/test-record-data
@@ -4,5 +4,8 @@ args    = -d kill >/dev/null 2>&1
 
 [event:base-record]
 sample_period=4000
-sample_type=271
+
+# sample_type = PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_TIME |
+# PERF_SAMPLE_ADDR | PERF_SAMPLE_PERIOD | PERF_SAMPLE_DATA_SRC
+sample_type=33039
 mmap_data=1
diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c
index 68daa28..aba0954 100644
--- a/tools/perf/tests/bp_signal.c
+++ b/tools/perf/tests/bp_signal.c
@@ -4,6 +4,12 @@
  * (git://github.com/deater/perf_event_tests)
  */
 
+/*
+ * Powerpc needs __SANE_USERSPACE_TYPES__ before <linux/types.h> to select
+ * 'int-ll64.h' and avoid compile warnings when printing __u64 with %llu.
+ */
+#define __SANE_USERSPACE_TYPES__
+
 #include <stdlib.h>
 #include <stdio.h>
 #include <unistd.h>
diff --git a/tools/perf/tests/bp_signal_overflow.c b/tools/perf/tests/bp_signal_overflow.c
index fe7ed28..44ac821 100644
--- a/tools/perf/tests/bp_signal_overflow.c
+++ b/tools/perf/tests/bp_signal_overflow.c
@@ -3,6 +3,12 @@
  * perf_event_tests (git://github.com/deater/perf_event_tests)
  */
 
+/*
+ * Powerpc needs __SANE_USERSPACE_TYPES__ before <linux/types.h> to select
+ * 'int-ll64.h' and avoid compile warnings when printing __u64 with %llu.
+ */
+#define __SANE_USERSPACE_TYPES__
+
 #include <stdlib.h>
 #include <stdio.h>
 #include <unistd.h>
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 0918ada..35b45f1466 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -70,7 +70,7 @@ static struct test {
 		.func = test__attr,
 	},
 	{
-		.desc = "Test matching and linking mutliple hists",
+		.desc = "Test matching and linking multiple hists",
 		.func = test__hists_link,
 	},
 	{
diff --git a/tools/perf/tests/make b/tools/perf/tests/make
new file mode 100644
index 0000000..c441a28
--- /dev/null
+++ b/tools/perf/tests/make
@@ -0,0 +1,138 @@
+PERF := .
+MK   := Makefile
+
+# standard single make variable specified
+make_clean_all      := clean all
+make_python_perf_so := python/perf.so
+make_debug          := DEBUG=1
+make_no_libperl     := NO_LIBPERL=1
+make_no_libpython   := NO_LIBPYTHON=1
+make_no_scripts     := NO_LIBPYTHON=1 NO_LIBPERL=1
+make_no_newt        := NO_NEWT=1
+make_no_slang       := NO_SLANG=1
+make_no_gtk2        := NO_GTK2=1
+make_no_ui          := NO_NEWT=1 NO_SLANG=1 NO_GTK2=1
+make_no_demangle    := NO_DEMANGLE=1
+make_no_libelf      := NO_LIBELF=1
+make_no_libunwind   := NO_LIBUNWIND=1
+make_no_backtrace   := NO_BACKTRACE=1
+make_no_libnuma     := NO_LIBNUMA=1
+make_no_libaudit    := NO_LIBAUDIT=1
+make_no_libbionic   := NO_LIBBIONIC=1
+make_tags           := tags
+make_cscope         := cscope
+make_help           := help
+make_doc            := doc
+make_perf_o         := perf.o
+make_util_map_o     := util/map.o
+
+# all the NO_* variable combined
+make_minimal        := NO_LIBPERL=1 NO_LIBPYTHON=1 NO_NEWT=1 NO_GTK2=1
+make_minimal        += NO_DEMANGLE=1 NO_LIBELF=1 NO_LIBUNWIND=1 NO_BACKTRACE=1
+make_minimal        += NO_LIBNUMA=1 NO_LIBAUDIT=1 NO_LIBBIONIC=1
+
+# $(run) contains all available tests
+run := make_pure
+run += make_clean_all
+run += make_python_perf_so
+run += make_debug
+run += make_no_libperl
+run += make_no_libpython
+run += make_no_scripts
+run += make_no_newt
+run += make_no_slang
+run += make_no_gtk2
+run += make_no_ui
+run += make_no_demangle
+run += make_no_libelf
+run += make_no_libunwind
+run += make_no_backtrace
+run += make_no_libnuma
+run += make_no_libaudit
+run += make_no_libbionic
+run += make_tags
+run += make_cscope
+run += make_help
+run += make_doc
+run += make_perf_o
+run += make_util_map_o
+run += make_minimal
+
+# $(run_O) contains same portion of $(run) tests with '_O' attached
+# to distinguish O=... tests
+run_O := $(addsuffix _O,$(run))
+
+# disable some tests for O=...
+run_O := $(filter-out make_python_perf_so_O,$(run_O))
+
+# define test for each compile as 'test_NAME' variable
+# with the test itself as a value
+test_make_tags   = test -f tags
+test_make_cscope = test -f cscope.out
+
+test_make_tags_O   := $(test_make_tags)
+test_make_cscope_O := $(test_make_cscope)
+
+test_ok          := true
+test_make_help   := $(test_ok)
+test_make_doc    := $(test_ok)
+test_make_help_O := $(test_ok)
+test_make_doc_O  := $(test_ok)
+
+test_make_python_perf_so := test -f $(PERF)/python/perf.so
+
+test_make_perf_o     := test -f $(PERF)/perf.o
+test_make_util_map_o := test -f $(PERF)/util/map.o
+
+# Kbuild tests only
+#test_make_python_perf_so_O := test -f $$TMP/tools/perf/python/perf.so
+#test_make_perf_o_O         := test -f $$TMP/tools/perf/perf.o
+#test_make_util_map_o_O     := test -f $$TMP/tools/perf/util/map.o
+
+test_make_perf_o_O     := true
+test_make_util_map_o_O := true
+
+test_default = test -x $(PERF)/perf
+test = $(if $(test_$1),$(test_$1),$(test_default))
+
+test_default_O = test -x $$TMP/perf
+test_O = $(if $(test_$1),$(test_$1),$(test_default_O))
+
+all:
+
+ifdef DEBUG
+d := $(info run   $(run))
+d := $(info run_O $(run_O))
+endif
+
+MAKEFLAGS := --no-print-directory
+
+clean := @(cd $(PERF); make -s -f $(MK) clean >/dev/null)
+
+$(run):
+	$(call clean)
+	@cmd="cd $(PERF) && make -f $(MK) $($@)"; \
+	echo "- $@: $$cmd" && echo $$cmd > $@ && \
+	( eval $$cmd ) >> $@ 2>&1; \
+	echo "  test: $(call test,$@)"; \
+	$(call test,$@) && \
+	rm -f $@
+
+$(run_O):
+	$(call clean)
+	@TMP=$$(mktemp -d); \
+	cmd="cd $(PERF) && make -f $(MK) $($(patsubst %_O,%,$@)) O=$$TMP"; \
+	echo "- $@: $$cmd" && echo $$cmd > $@ && \
+	( eval $$cmd ) >> $@ 2>&1 && \
+	echo "  test: $(call test_O,$@)"; \
+	$(call test_O,$@) && \
+	rm -f $@ && \
+	rm -rf $$TMP
+
+all: $(run) $(run_O)
+	@echo OK
+
+out: $(run_O)
+	@echo OK
+
+.PHONY: all $(run) $(run_O) clean
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index d88a2d0..fc0bd38 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -25,7 +25,8 @@ struct hist_browser {
 	struct map_symbol   *selection;
 	int		     print_seq;
 	bool		     show_dso;
-	bool		     has_symbols;
+	float		     min_pcnt;
+	u64		     nr_pcnt_entries;
 };
 
 extern void hist_browser__init_hpp(void);
@@ -309,6 +310,8 @@ static void ui_browser__warn_lost_events(struct ui_browser *browser)
 		"Or reduce the sampling frequency.");
 }
 
+static void hist_browser__update_pcnt_entries(struct hist_browser *hb);
+
 static int hist_browser__run(struct hist_browser *browser, const char *ev_name,
 			     struct hist_browser_timer *hbt)
 {
@@ -318,6 +321,8 @@ static int hist_browser__run(struct hist_browser *browser, const char *ev_name,
 
 	browser->b.entries = &browser->hists->entries;
 	browser->b.nr_entries = browser->hists->nr_entries;
+	if (browser->min_pcnt)
+		browser->b.nr_entries = browser->nr_pcnt_entries;
 
 	hist_browser__refresh_dimensions(browser);
 	hists__browser_title(browser->hists, title, sizeof(title), ev_name);
@@ -330,9 +335,18 @@ static int hist_browser__run(struct hist_browser *browser, const char *ev_name,
 		key = ui_browser__run(&browser->b, delay_secs);
 
 		switch (key) {
-		case K_TIMER:
+		case K_TIMER: {
+			u64 nr_entries;
 			hbt->timer(hbt->arg);
-			ui_browser__update_nr_entries(&browser->b, browser->hists->nr_entries);
+
+			if (browser->min_pcnt) {
+				hist_browser__update_pcnt_entries(browser);
+				nr_entries = browser->nr_pcnt_entries;
+			} else {
+				nr_entries = browser->hists->nr_entries;
+			}
+
+			ui_browser__update_nr_entries(&browser->b, nr_entries);
 
 			if (browser->hists->stats.nr_lost_warned !=
 			    browser->hists->stats.nr_events[PERF_RECORD_LOST]) {
@@ -344,6 +358,7 @@ static int hist_browser__run(struct hist_browser *browser, const char *ev_name,
 			hists__browser_title(browser->hists, title, sizeof(title), ev_name);
 			ui_browser__show_title(&browser->b, title);
 			continue;
+		}
 		case 'D': { /* Debug */
 			static int seq;
 			struct hist_entry *h = rb_entry(browser->b.top,
@@ -796,10 +811,15 @@ static unsigned int hist_browser__refresh(struct ui_browser *browser)
 
 	for (nd = browser->top; nd; nd = rb_next(nd)) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
+		float percent = h->stat.period * 100.0 /
+					hb->hists->stats.total_period;
 
 		if (h->filtered)
 			continue;
 
+		if (percent < hb->min_pcnt)
+			continue;
+
 		row += hist_browser__show_entry(hb, h, row);
 		if (row == browser->height)
 			break;
@@ -808,10 +828,18 @@ static unsigned int hist_browser__refresh(struct ui_browser *browser)
 	return row;
 }
 
-static struct rb_node *hists__filter_entries(struct rb_node *nd)
+static struct rb_node *hists__filter_entries(struct rb_node *nd,
+					     struct hists *hists,
+					     float min_pcnt)
 {
 	while (nd != NULL) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
+		float percent = h->stat.period * 100.0 /
+					hists->stats.total_period;
+
+		if (percent < min_pcnt)
+			return NULL;
+
 		if (!h->filtered)
 			return nd;
 
@@ -821,11 +849,16 @@ static struct rb_node *hists__filter_entries(struct rb_node *nd)
 	return NULL;
 }
 
-static struct rb_node *hists__filter_prev_entries(struct rb_node *nd)
+static struct rb_node *hists__filter_prev_entries(struct rb_node *nd,
+						  struct hists *hists,
+						  float min_pcnt)
 {
 	while (nd != NULL) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
-		if (!h->filtered)
+		float percent = h->stat.period * 100.0 /
+					hists->stats.total_period;
+
+		if (!h->filtered && percent >= min_pcnt)
 			return nd;
 
 		nd = rb_prev(nd);
@@ -840,6 +873,9 @@ static void ui_browser__hists_seek(struct ui_browser *browser,
 	struct hist_entry *h;
 	struct rb_node *nd;
 	bool first = true;
+	struct hist_browser *hb;
+
+	hb = container_of(browser, struct hist_browser, b);
 
 	if (browser->nr_entries == 0)
 		return;
@@ -848,13 +884,15 @@ static void ui_browser__hists_seek(struct ui_browser *browser,
 
 	switch (whence) {
 	case SEEK_SET:
-		nd = hists__filter_entries(rb_first(browser->entries));
+		nd = hists__filter_entries(rb_first(browser->entries),
+					   hb->hists, hb->min_pcnt);
 		break;
 	case SEEK_CUR:
 		nd = browser->top;
 		goto do_offset;
 	case SEEK_END:
-		nd = hists__filter_prev_entries(rb_last(browser->entries));
+		nd = hists__filter_prev_entries(rb_last(browser->entries),
+						hb->hists, hb->min_pcnt);
 		first = false;
 		break;
 	default:
@@ -897,7 +935,8 @@ do_offset:
 					break;
 				}
 			}
-			nd = hists__filter_entries(rb_next(nd));
+			nd = hists__filter_entries(rb_next(nd), hb->hists,
+						   hb->min_pcnt);
 			if (nd == NULL)
 				break;
 			--offset;
@@ -930,7 +969,8 @@ do_offset:
 				}
 			}
 
-			nd = hists__filter_prev_entries(rb_prev(nd));
+			nd = hists__filter_prev_entries(rb_prev(nd), hb->hists,
+							hb->min_pcnt);
 			if (nd == NULL)
 				break;
 			++offset;
@@ -1099,14 +1139,17 @@ static int hist_browser__fprintf_entry(struct hist_browser *browser,
 
 static int hist_browser__fprintf(struct hist_browser *browser, FILE *fp)
 {
-	struct rb_node *nd = hists__filter_entries(rb_first(browser->b.entries));
+	struct rb_node *nd = hists__filter_entries(rb_first(browser->b.entries),
+						   browser->hists,
+						   browser->min_pcnt);
 	int printed = 0;
 
 	while (nd) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
 
 		printed += hist_browser__fprintf_entry(browser, h, fp);
-		nd = hists__filter_entries(rb_next(nd));
+		nd = hists__filter_entries(rb_next(nd), browser->hists,
+					   browser->min_pcnt);
 	}
 
 	return printed;
@@ -1155,10 +1198,6 @@ static struct hist_browser *hist_browser__new(struct hists *hists)
 		browser->b.refresh = hist_browser__refresh;
 		browser->b.seek = ui_browser__hists_seek;
 		browser->b.use_navkeypressed = true;
-		if (sort__branch_mode == 1)
-			browser->has_symbols = sort_sym_from.list.next != NULL;
-		else
-			browser->has_symbols = sort_sym.list.next != NULL;
 	}
 
 	return browser;
@@ -1329,11 +1368,25 @@ close_file_and_continue:
 	return ret;
 }
 
+static void hist_browser__update_pcnt_entries(struct hist_browser *hb)
+{
+	u64 nr_entries = 0;
+	struct rb_node *nd = rb_first(&hb->hists->entries);
+
+	while (nd) {
+		nr_entries++;
+		nd = hists__filter_entries(rb_next(nd), hb->hists,
+					   hb->min_pcnt);
+	}
+
+	hb->nr_pcnt_entries = nr_entries;
+}
 
 static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 				    const char *helpline, const char *ev_name,
 				    bool left_exits,
 				    struct hist_browser_timer *hbt,
+				    float min_pcnt,
 				    struct perf_session_env *env)
 {
 	struct hists *hists = &evsel->hists;
@@ -1350,6 +1403,11 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 	if (browser == NULL)
 		return -1;
 
+	if (min_pcnt) {
+		browser->min_pcnt = min_pcnt;
+		hist_browser__update_pcnt_entries(browser);
+	}
+
 	fstack = pstack__new(2);
 	if (fstack == NULL)
 		goto out;
@@ -1386,7 +1444,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 			 */
 			goto out_free_stack;
 		case 'a':
-			if (!browser->has_symbols) {
+			if (!sort__has_sym) {
 				ui_browser__warning(&browser->b, delay_secs * 2,
 			"Annotation is only available for symbolic views, "
 			"include \"sym*\" in --sort to use it.");
@@ -1485,10 +1543,10 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 			continue;
 		}
 
-		if (!browser->has_symbols)
+		if (!sort__has_sym)
 			goto add_exit_option;
 
-		if (sort__branch_mode == 1) {
+		if (sort__mode == SORT_MODE__BRANCH) {
 			bi = browser->he_selection->branch_info;
 			if (browser->selection != NULL &&
 			    bi &&
@@ -1689,6 +1747,7 @@ struct perf_evsel_menu {
 	struct ui_browser b;
 	struct perf_evsel *selection;
 	bool lost_events, lost_events_warned;
+	float min_pcnt;
 	struct perf_session_env *env;
 };
 
@@ -1782,6 +1841,7 @@ browse_hists:
 			ev_name = perf_evsel__name(pos);
 			key = perf_evsel__hists_browse(pos, nr_events, help,
 						       ev_name, true, hbt,
+						       menu->min_pcnt,
 						       menu->env);
 			ui_browser__show_title(&menu->b, title);
 			switch (key) {
@@ -1843,6 +1903,7 @@ static bool filter_group_entries(struct ui_browser *self __maybe_unused,
 static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist,
 					   int nr_entries, const char *help,
 					   struct hist_browser_timer *hbt,
+					   float min_pcnt,
 					   struct perf_session_env *env)
 {
 	struct perf_evsel *pos;
@@ -1856,6 +1917,7 @@ static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist,
 			.nr_entries = nr_entries,
 			.priv	    = evlist,
 		},
+		.min_pcnt = min_pcnt,
 		.env = env,
 	};
 
@@ -1874,6 +1936,7 @@ static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist,
 
 int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help,
 				  struct hist_browser_timer *hbt,
+				  float min_pcnt,
 				  struct perf_session_env *env)
 {
 	int nr_entries = evlist->nr_entries;
@@ -1885,7 +1948,8 @@ single_entry:
 		const char *ev_name = perf_evsel__name(first);
 
 		return perf_evsel__hists_browse(first, nr_entries, help,
-						ev_name, false, hbt, env);
+						ev_name, false, hbt, min_pcnt,
+						env);
 	}
 
 	if (symbol_conf.event_group) {
@@ -1901,5 +1965,5 @@ single_entry:
 	}
 
 	return __perf_evlist__tui_browse_hists(evlist, nr_entries, help,
-					       hbt, env);
+					       hbt, min_pcnt, env);
 }
diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c
index 6f259b3..9708dd5 100644
--- a/tools/perf/ui/gtk/hists.c
+++ b/tools/perf/ui/gtk/hists.c
@@ -124,7 +124,8 @@ void perf_gtk__init_hpp(void)
 				perf_gtk__hpp_color_overhead_guest_us;
 }
 
-static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists)
+static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
+				 float min_pcnt)
 {
 	struct perf_hpp_fmt *fmt;
 	GType col_types[MAX_COLUMNS];
@@ -189,10 +190,15 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists)
 	for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
 		GtkTreeIter iter;
+		float percent = h->stat.period * 100.0 /
+					hists->stats.total_period;
 
 		if (h->filtered)
 			continue;
 
+		if (percent < min_pcnt)
+			continue;
+
 		gtk_list_store_append(store, &iter);
 
 		col_idx = 0;
@@ -222,7 +228,8 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists)
 
 int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist,
 				  const char *help,
-				  struct hist_browser_timer *hbt __maybe_unused)
+				  struct hist_browser_timer *hbt __maybe_unused,
+				  float min_pcnt)
 {
 	struct perf_evsel *pos;
 	GtkWidget *vbox;
@@ -286,7 +293,7 @@ int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist,
 							GTK_POLICY_AUTOMATIC,
 							GTK_POLICY_AUTOMATIC);
 
-		perf_gtk__show_hists(scrolled_window, hists);
+		perf_gtk__show_hists(scrolled_window, hists, min_pcnt);
 
 		tab_label = gtk_label_new(evname);
 
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index ff1f60c..ae7a754 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -334,7 +334,7 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size,
 }
 
 size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
-		      int max_cols, FILE *fp)
+		      int max_cols, float min_pcnt, FILE *fp)
 {
 	struct perf_hpp_fmt *fmt;
 	struct sort_entry *se;
@@ -440,10 +440,15 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 print_entries:
 	for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
+		float percent = h->stat.period * 100.0 /
+					hists->stats.total_period;
 
 		if (h->filtered)
 			continue;
 
+		if (percent < min_pcnt)
+			continue;
+
 		ret += hist_entry__fprintf(h, max_cols, hists, fp);
 
 		if (max_rows && ++nr_rows >= max_rows)
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index f7c7278..99b43dd 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -776,6 +776,8 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist,
 		if (pipe_output)
 			dup2(2, 1);
 
+		signal(SIGTERM, SIG_DFL);
+
 		close(child_ready_pipe[0]);
 		close(go_pipe[1]);
 		fcntl(go_pipe[0], F_SETFD, FD_CLOEXEC);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 07b1a3a..63b6f8c 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1514,7 +1514,7 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel,
 	switch (err) {
 	case EPERM:
 	case EACCES:
-		return scnprintf(msg, size, "%s",
+		return scnprintf(msg, size,
 		 "You may not have permission to collect %sstats.\n"
 		 "Consider tweaking /proc/sys/kernel/perf_event_paranoid:\n"
 		 " -1 - Not paranoid at all\n"
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 326068a..738d3b8 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -2391,7 +2391,6 @@ out_err_write:
 	}
 	lseek(fd, header->data_offset + header->data_size, SEEK_SET);
 
-	header->frozen = 1;
 	return 0;
 }
 
@@ -2871,7 +2870,6 @@ int perf_session__read_header(struct perf_session *session, int fd)
 						   session->pevent))
 		goto out_delete_evlist;
 
-	header->frozen = 1;
 	return 0;
 out_errno:
 	return -errno;
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index c9fc55c..16a3e83 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -84,7 +84,6 @@ struct perf_session_env {
 };
 
 struct perf_header {
-	int			frozen;
 	bool			needs_swap;
 	s64			attr_offset;
 	u64			data_offset;
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 6b32721..b11a6cf 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -70,9 +70,17 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 	int symlen;
 	u16 len;
 
-	if (h->ms.sym)
-		hists__new_col_len(hists, HISTC_SYMBOL, h->ms.sym->namelen + 4);
-	else {
+	/*
+	 * +4 accounts for '[x] ' priv level info
+	 * +2 accounts for 0x prefix on raw addresses
+	 * +3 accounts for ' y ' symtab origin info
+	 */
+	if (h->ms.sym) {
+		symlen = h->ms.sym->namelen + 4;
+		if (verbose)
+			symlen += BITS_PER_LONG / 4 + 2 + 3;
+		hists__new_col_len(hists, HISTC_SYMBOL, symlen);
+	} else {
 		symlen = unresolved_col_width + 4 + 2;
 		hists__new_col_len(hists, HISTC_SYMBOL, symlen);
 		hists__set_unres_dso_col_len(hists, HISTC_DSO);
@@ -91,12 +99,10 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 		hists__new_col_len(hists, HISTC_PARENT, h->parent->namelen);
 
 	if (h->branch_info) {
-		/*
-		 * +4 accounts for '[x] ' priv level info
-		 * +2 account of 0x prefix on raw addresses
-		 */
 		if (h->branch_info->from.sym) {
 			symlen = (int)h->branch_info->from.sym->namelen + 4;
+			if (verbose)
+				symlen += BITS_PER_LONG / 4 + 2 + 3;
 			hists__new_col_len(hists, HISTC_SYMBOL_FROM, symlen);
 
 			symlen = dso__name_len(h->branch_info->from.map->dso);
@@ -109,6 +115,8 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 
 		if (h->branch_info->to.sym) {
 			symlen = (int)h->branch_info->to.sym->namelen + 4;
+			if (verbose)
+				symlen += BITS_PER_LONG / 4 + 2 + 3;
 			hists__new_col_len(hists, HISTC_SYMBOL_TO, symlen);
 
 			symlen = dso__name_len(h->branch_info->to.map->dso);
@@ -121,10 +129,6 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 	}
 
 	if (h->mem_info) {
-		/*
-		 * +4 accounts for '[x] ' priv level info
-		 * +2 account of 0x prefix on raw addresses
-		 */
 		if (h->mem_info->daddr.sym) {
 			symlen = (int)h->mem_info->daddr.sym->namelen + 4
 			       + unresolved_col_width + 2;
@@ -236,8 +240,7 @@ static bool hists__decay_entry(struct hists *hists, struct hist_entry *he)
 	return he->stat.period == 0;
 }
 
-static void __hists__decay_entries(struct hists *hists, bool zap_user,
-				   bool zap_kernel, bool threaded)
+void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel)
 {
 	struct rb_node *next = rb_first(&hists->entries);
 	struct hist_entry *n;
@@ -256,7 +259,7 @@ static void __hists__decay_entries(struct hists *hists, bool zap_user,
 		    !n->used) {
 			rb_erase(&n->rb_node, &hists->entries);
 
-			if (sort__need_collapse || threaded)
+			if (sort__need_collapse)
 				rb_erase(&n->rb_node_in, &hists->entries_collapsed);
 
 			hist_entry__free(n);
@@ -265,17 +268,6 @@ static void __hists__decay_entries(struct hists *hists, bool zap_user,
 	}
 }
 
-void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel)
-{
-	return __hists__decay_entries(hists, zap_user, zap_kernel, false);
-}
-
-void hists__decay_entries_threaded(struct hists *hists,
-				   bool zap_user, bool zap_kernel)
-{
-	return __hists__decay_entries(hists, zap_user, zap_kernel, true);
-}
-
 /*
  * histogram, sorted on item, collects periods
  */
@@ -292,6 +284,20 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template)
 			he->ms.map->referenced = true;
 
 		if (he->branch_info) {
+			/*
+			 * This branch info is (a part of) allocated from
+			 * machine__resolve_bstack() and will be freed after
+			 * adding new entries.  So we need to save a copy.
+			 */
+			he->branch_info = malloc(sizeof(*he->branch_info));
+			if (he->branch_info == NULL) {
+				free(he);
+				return NULL;
+			}
+
+			memcpy(he->branch_info, template->branch_info,
+			       sizeof(*he->branch_info));
+
 			if (he->branch_info->from.map)
 				he->branch_info->from.map->referenced = true;
 			if (he->branch_info->to.map)
@@ -341,8 +347,6 @@ static struct hist_entry *add_hist_entry(struct hists *hists,
 	struct hist_entry *he;
 	int cmp;
 
-	pthread_mutex_lock(&hists->lock);
-
 	p = &hists->entries_in->rb_node;
 
 	while (*p != NULL) {
@@ -360,6 +364,12 @@ static struct hist_entry *add_hist_entry(struct hists *hists,
 		if (!cmp) {
 			he_stat__add_period(&he->stat, period, weight);
 
+			/*
+			 * This mem info was allocated from machine__resolve_mem
+			 * and will not be used anymore.
+			 */
+			free(entry->mem_info);
+
 			/* If the map of an existing hist_entry has
 			 * become out-of-date due to an exec() or
 			 * similar, update it.  Otherwise we will
@@ -382,14 +392,12 @@ static struct hist_entry *add_hist_entry(struct hists *hists,
 
 	he = hist_entry__new(entry);
 	if (!he)
-		goto out_unlock;
+		return NULL;
 
 	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);
-out_unlock:
-	pthread_mutex_unlock(&hists->lock);
 	return he;
 }
 
@@ -589,13 +597,13 @@ static void hists__apply_filters(struct hists *hists, struct hist_entry *he)
 	hists__filter_entry_by_symbol(hists, he);
 }
 
-static void __hists__collapse_resort(struct hists *hists, bool threaded)
+void hists__collapse_resort(struct hists *hists)
 {
 	struct rb_root *root;
 	struct rb_node *next;
 	struct hist_entry *n;
 
-	if (!sort__need_collapse && !threaded)
+	if (!sort__need_collapse)
 		return;
 
 	root = hists__get_rotate_entries_in(hists);
@@ -617,16 +625,6 @@ static void __hists__collapse_resort(struct hists *hists, bool threaded)
 	}
 }
 
-void hists__collapse_resort(struct hists *hists)
-{
-	return __hists__collapse_resort(hists, false);
-}
-
-void hists__collapse_resort_threaded(struct hists *hists)
-{
-	return __hists__collapse_resort(hists, true);
-}
-
 /*
  * reverse the map, sort on period.
  */
@@ -713,7 +711,7 @@ static void __hists__insert_output_entry(struct rb_root *entries,
 	rb_insert_color(&he->rb_node, entries);
 }
 
-static void __hists__output_resort(struct hists *hists, bool threaded)
+void hists__output_resort(struct hists *hists)
 {
 	struct rb_root *root;
 	struct rb_node *next;
@@ -722,7 +720,7 @@ static void __hists__output_resort(struct hists *hists, bool threaded)
 
 	min_callchain_hits = hists->stats.total_period * (callchain_param.min_percent / 100);
 
-	if (sort__need_collapse || threaded)
+	if (sort__need_collapse)
 		root = &hists->entries_collapsed;
 	else
 		root = hists->entries_in;
@@ -743,16 +741,6 @@ static void __hists__output_resort(struct hists *hists, bool threaded)
 	}
 }
 
-void hists__output_resort(struct hists *hists)
-{
-	return __hists__output_resort(hists, false);
-}
-
-void hists__output_resort_threaded(struct hists *hists)
-{
-	return __hists__output_resort(hists, true);
-}
-
 static void hists__remove_entry_filter(struct hists *hists, struct hist_entry *h,
 				       enum hist_filter filter)
 {
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 14c2fe2..2d3790f 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -43,12 +43,12 @@ enum hist_column {
 	HISTC_COMM,
 	HISTC_PARENT,
 	HISTC_CPU,
+	HISTC_SRCLINE,
 	HISTC_MISPREDICT,
 	HISTC_SYMBOL_FROM,
 	HISTC_SYMBOL_TO,
 	HISTC_DSO_FROM,
 	HISTC_DSO_TO,
-	HISTC_SRCLINE,
 	HISTC_LOCAL_WEIGHT,
 	HISTC_GLOBAL_WEIGHT,
 	HISTC_MEM_DADDR_SYMBOL,
@@ -104,13 +104,9 @@ struct hist_entry *__hists__add_mem_entry(struct hists *self,
 					  u64 weight);
 
 void hists__output_resort(struct hists *self);
-void hists__output_resort_threaded(struct hists *hists);
 void hists__collapse_resort(struct hists *self);
-void hists__collapse_resort_threaded(struct hists *hists);
 
 void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel);
-void hists__decay_entries_threaded(struct hists *hists, bool zap_user,
-				   bool zap_kernel);
 void hists__output_recalc_col_len(struct hists *hists, int max_rows);
 
 void hists__inc_nr_entries(struct hists *hists, struct hist_entry *h);
@@ -119,7 +115,7 @@ void events_stats__inc(struct events_stats *stats, u32 type);
 size_t events_stats__fprintf(struct events_stats *stats, FILE *fp);
 
 size_t hists__fprintf(struct hists *self, bool show_header, int max_rows,
-		      int max_cols, FILE *fp);
+		      int max_cols, float min_pcnt, FILE *fp);
 
 int hist_entry__inc_addr_samples(struct hist_entry *self, int evidx, u64 addr);
 int hist_entry__annotate(struct hist_entry *self, size_t privsize);
@@ -199,6 +195,7 @@ int hist_entry__tui_annotate(struct hist_entry *he, struct perf_evsel *evsel,
 
 int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help,
 				  struct hist_browser_timer *hbt,
+				  float min_pcnt,
 				  struct perf_session_env *env);
 int script_browse(const char *script_opt);
 #else
@@ -206,6 +203,7 @@ static inline
 int perf_evlist__tui_browse_hists(struct perf_evlist *evlist __maybe_unused,
 				  const char *help __maybe_unused,
 				  struct hist_browser_timer *hbt __maybe_unused,
+				  float min_pcnt __maybe_unused,
 				  struct perf_session_env *env __maybe_unused)
 {
 	return 0;
@@ -233,12 +231,14 @@ static inline int script_browse(const char *script_opt __maybe_unused)
 
 #ifdef GTK2_SUPPORT
 int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist, const char *help,
-				  struct hist_browser_timer *hbt __maybe_unused);
+				  struct hist_browser_timer *hbt __maybe_unused,
+				  float min_pcnt);
 #else
 static inline
 int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist __maybe_unused,
 				  const char *help __maybe_unused,
-				  struct hist_browser_timer *hbt __maybe_unused)
+				  struct hist_browser_timer *hbt __maybe_unused,
+				  float min_pcnt __maybe_unused)
 {
 	return 0;
 }
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 6fcb9de..8bcdf9e 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -21,6 +21,7 @@ const char *map_type__name[MAP__NR_TYPES] = {
 static inline int is_anon_memory(const char *filename)
 {
 	return !strcmp(filename, "//anon") ||
+	       !strcmp(filename, "/dev/zero (deleted)") ||
 	       !strcmp(filename, "/anon_hugepage (deleted)");
 }
 
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 6b51d47a..f3b235e 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -37,7 +37,6 @@ struct perf_session {
 	int			fd;
 	bool			fd_pipe;
 	bool			repipe;
-	int			cwdlen;
 	char			*cwd;
 	struct ordered_samples	ordered_samples;
 	char			filename[1];
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index 6b0ed32..58ea5ca 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -18,8 +18,9 @@ class install_lib(_install_lib):
         self.build_dir = build_lib
 
 
-cflags = ['-fno-strict-aliasing', '-Wno-write-strings']
-cflags += getenv('CFLAGS', '').split()
+cflags = getenv('CFLAGS', '').split()
+# switch off several checks (need to be at the end of cflags list)
+cflags += ['-fno-strict-aliasing', '-Wno-write-strings', '-Wno-unused-parameter' ]
 
 build_lib = getenv('PYTHON_EXTBUILD_LIB')
 build_tmp = getenv('PYTHON_EXTBUILD_TMP')
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 5f52d49..313a5a7 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -1,5 +1,6 @@
 #include "sort.h"
 #include "hist.h"
+#include "symbol.h"
 
 regex_t		parent_regex;
 const char	default_parent_pattern[] = "^sys_|^do_page_fault";
@@ -9,7 +10,7 @@ const char	*sort_order = default_sort_order;
 int		sort__need_collapse = 0;
 int		sort__has_parent = 0;
 int		sort__has_sym = 0;
-int		sort__branch_mode = -1; /* -1 = means not set */
+enum sort_mode	sort__mode = SORT_MODE__NORMAL;
 
 enum sort_type	sort__first_dimension;
 
@@ -194,7 +195,7 @@ static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym,
 	if (verbose) {
 		char o = map ? dso__symtab_origin(map->dso) : '!';
 		ret += repsep_snprintf(bf, size, "%-#*llx %c ",
-				       BITS_PER_LONG / 4, ip, o);
+				       BITS_PER_LONG / 4 + 2, ip, o);
 	}
 
 	ret += repsep_snprintf(bf + ret, size - ret, "[%c] ", level);
@@ -871,14 +872,6 @@ static struct sort_dimension common_sort_dimensions[] = {
 	DIM(SORT_PARENT, "parent", sort_parent),
 	DIM(SORT_CPU, "cpu", sort_cpu),
 	DIM(SORT_SRCLINE, "srcline", sort_srcline),
-	DIM(SORT_LOCAL_WEIGHT, "local_weight", sort_local_weight),
-	DIM(SORT_GLOBAL_WEIGHT, "weight", sort_global_weight),
-	DIM(SORT_MEM_DADDR_SYMBOL, "symbol_daddr", sort_mem_daddr_sym),
-	DIM(SORT_MEM_DADDR_DSO, "dso_daddr", sort_mem_daddr_dso),
-	DIM(SORT_MEM_LOCKED, "locked", sort_mem_locked),
-	DIM(SORT_MEM_TLB, "tlb", sort_mem_tlb),
-	DIM(SORT_MEM_LVL, "mem", sort_mem_lvl),
-	DIM(SORT_MEM_SNOOP, "snoop", sort_mem_snoop),
 };
 
 #undef DIM
@@ -895,6 +888,36 @@ static struct sort_dimension bstack_sort_dimensions[] = {
 
 #undef DIM
 
+#define DIM(d, n, func) [d - __SORT_MEMORY_MODE] = { .name = n, .entry = &(func) }
+
+static struct sort_dimension memory_sort_dimensions[] = {
+	DIM(SORT_LOCAL_WEIGHT, "local_weight", sort_local_weight),
+	DIM(SORT_GLOBAL_WEIGHT, "weight", sort_global_weight),
+	DIM(SORT_MEM_DADDR_SYMBOL, "symbol_daddr", sort_mem_daddr_sym),
+	DIM(SORT_MEM_DADDR_DSO, "dso_daddr", sort_mem_daddr_dso),
+	DIM(SORT_MEM_LOCKED, "locked", sort_mem_locked),
+	DIM(SORT_MEM_TLB, "tlb", sort_mem_tlb),
+	DIM(SORT_MEM_LVL, "mem", sort_mem_lvl),
+	DIM(SORT_MEM_SNOOP, "snoop", sort_mem_snoop),
+};
+
+#undef DIM
+
+static void __sort_dimension__add(struct sort_dimension *sd, enum sort_type idx)
+{
+	if (sd->taken)
+		return;
+
+	if (sd->entry->se_collapse)
+		sort__need_collapse = 1;
+
+	if (list_empty(&hist_entry__sort_list))
+		sort__first_dimension = idx;
+
+	list_add_tail(&sd->entry->list, &hist_entry__sort_list);
+	sd->taken = 1;
+}
+
 int sort_dimension__add(const char *tok)
 {
 	unsigned int i;
@@ -915,25 +938,11 @@ int sort_dimension__add(const char *tok)
 				return -EINVAL;
 			}
 			sort__has_parent = 1;
-		} else if (sd->entry == &sort_sym ||
-			   sd->entry == &sort_sym_from ||
-			   sd->entry == &sort_sym_to ||
-			   sd->entry == &sort_mem_daddr_sym) {
+		} else if (sd->entry == &sort_sym) {
 			sort__has_sym = 1;
 		}
 
-		if (sd->taken)
-			return 0;
-
-		if (sd->entry->se_collapse)
-			sort__need_collapse = 1;
-
-		if (list_empty(&hist_entry__sort_list))
-			sort__first_dimension = i;
-
-		list_add_tail(&sd->entry->list, &hist_entry__sort_list);
-		sd->taken = 1;
-
+		__sort_dimension__add(sd, i);
 		return 0;
 	}
 
@@ -943,24 +952,29 @@ int sort_dimension__add(const char *tok)
 		if (strncasecmp(tok, sd->name, strlen(tok)))
 			continue;
 
-		if (sort__branch_mode != 1)
+		if (sort__mode != SORT_MODE__BRANCH)
 			return -EINVAL;
 
 		if (sd->entry == &sort_sym_from || sd->entry == &sort_sym_to)
 			sort__has_sym = 1;
 
-		if (sd->taken)
-			return 0;
+		__sort_dimension__add(sd, i + __SORT_BRANCH_STACK);
+		return 0;
+	}
 
-		if (sd->entry->se_collapse)
-			sort__need_collapse = 1;
+	for (i = 0; i < ARRAY_SIZE(memory_sort_dimensions); i++) {
+		struct sort_dimension *sd = &memory_sort_dimensions[i];
 
-		if (list_empty(&hist_entry__sort_list))
-			sort__first_dimension = i + __SORT_BRANCH_STACK;
+		if (strncasecmp(tok, sd->name, strlen(tok)))
+			continue;
 
-		list_add_tail(&sd->entry->list, &hist_entry__sort_list);
-		sd->taken = 1;
+		if (sort__mode != SORT_MODE__MEMORY)
+			return -EINVAL;
+
+		if (sd->entry == &sort_mem_daddr_sym)
+			sort__has_sym = 1;
 
+		__sort_dimension__add(sd, i + __SORT_MEMORY_MODE);
 		return 0;
 	}
 
@@ -993,8 +1007,9 @@ int setup_sorting(void)
 	return ret;
 }
 
-void sort_entry__setup_elide(struct sort_entry *self, struct strlist *list,
-			     const char *list_name, FILE *fp)
+static void sort_entry__setup_elide(struct sort_entry *self,
+				    struct strlist *list,
+				    const char *list_name, FILE *fp)
 {
 	if (list && strlist__nr_entries(list) == 1) {
 		if (fp != NULL)
@@ -1003,3 +1018,42 @@ void sort_entry__setup_elide(struct sort_entry *self, struct strlist *list,
 		self->elide = true;
 	}
 }
+
+void sort__setup_elide(FILE *output)
+{
+	sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list,
+				"dso", output);
+	sort_entry__setup_elide(&sort_comm, symbol_conf.comm_list,
+				"comm", output);
+	sort_entry__setup_elide(&sort_sym, symbol_conf.sym_list,
+				"symbol", output);
+
+	if (sort__mode == SORT_MODE__BRANCH) {
+		sort_entry__setup_elide(&sort_dso_from,
+					symbol_conf.dso_from_list,
+					"dso_from", output);
+		sort_entry__setup_elide(&sort_dso_to,
+					symbol_conf.dso_to_list,
+					"dso_to", output);
+		sort_entry__setup_elide(&sort_sym_from,
+					symbol_conf.sym_from_list,
+					"sym_from", output);
+		sort_entry__setup_elide(&sort_sym_to,
+					symbol_conf.sym_to_list,
+					"sym_to", output);
+	} else if (sort__mode == SORT_MODE__MEMORY) {
+		sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list,
+					"symbol_daddr", output);
+		sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list,
+					"dso_daddr", output);
+		sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list,
+					"mem", output);
+		sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list,
+					"local_weight", output);
+		sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list,
+					"tlb", output);
+		sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list,
+					"snoop", output);
+	}
+
+}
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index f24bdf6..45ac84c 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -32,7 +32,7 @@ extern const char default_sort_order[];
 extern int sort__need_collapse;
 extern int sort__has_parent;
 extern int sort__has_sym;
-extern int sort__branch_mode;
+extern enum sort_mode sort__mode;
 extern struct sort_entry sort_comm;
 extern struct sort_entry sort_dso;
 extern struct sort_entry sort_sym;
@@ -117,12 +117,18 @@ static inline struct hist_entry *hist_entry__next_pair(struct hist_entry *he)
 	return NULL;
 }
 
-static inline void hist_entry__add_pair(struct hist_entry *he,
-					struct hist_entry *pair)
+static inline void hist_entry__add_pair(struct hist_entry *pair,
+					struct hist_entry *he)
 {
-	list_add_tail(&he->pairs.head, &pair->pairs.node);
+	list_add_tail(&pair->pairs.node, &he->pairs.head);
 }
 
+enum sort_mode {
+	SORT_MODE__NORMAL,
+	SORT_MODE__BRANCH,
+	SORT_MODE__MEMORY,
+};
+
 enum sort_type {
 	/* common sort keys */
 	SORT_PID,
@@ -132,14 +138,6 @@ enum sort_type {
 	SORT_PARENT,
 	SORT_CPU,
 	SORT_SRCLINE,
-	SORT_LOCAL_WEIGHT,
-	SORT_GLOBAL_WEIGHT,
-	SORT_MEM_DADDR_SYMBOL,
-	SORT_MEM_DADDR_DSO,
-	SORT_MEM_LOCKED,
-	SORT_MEM_TLB,
-	SORT_MEM_LVL,
-	SORT_MEM_SNOOP,
 
 	/* branch stack specific sort keys */
 	__SORT_BRANCH_STACK,
@@ -148,6 +146,17 @@ enum sort_type {
 	SORT_SYM_FROM,
 	SORT_SYM_TO,
 	SORT_MISPREDICT,
+
+	/* memory mode specific sort keys */
+	__SORT_MEMORY_MODE,
+	SORT_LOCAL_WEIGHT = __SORT_MEMORY_MODE,
+	SORT_GLOBAL_WEIGHT,
+	SORT_MEM_DADDR_SYMBOL,
+	SORT_MEM_DADDR_DSO,
+	SORT_MEM_LOCKED,
+	SORT_MEM_TLB,
+	SORT_MEM_LVL,
+	SORT_MEM_SNOOP,
 };
 
 /*
@@ -172,7 +181,6 @@ extern struct list_head hist_entry__sort_list;
 
 int setup_sorting(void);
 extern int sort_dimension__add(const char *);
-void sort_entry__setup_elide(struct sort_entry *self, struct strlist *list,
-			     const char *list_name, FILE *fp);
+void sort__setup_elide(FILE *fp);
 
 #endif	/* __PERF_SORT_H */
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 2374212..7c59c28 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -37,7 +37,7 @@ double stddev_stats(struct stats *stats)
 {
 	double variance, variance_mean;
 
-	if (!stats->n)
+	if (stats->n < 2)
 		return 0.0;
 
 	variance = stats->M2 / (stats->n - 1);
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 632e40e..40399cb 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -14,6 +14,7 @@ struct thread *thread__new(pid_t pid)
 	if (self != NULL) {
 		map_groups__init(&self->mg);
 		self->pid = pid;
+		self->ppid = -1;
 		self->comm = malloc(32);
 		if (self->comm)
 			snprintf(self->comm, 32, ":%d", self->pid);
@@ -82,5 +83,8 @@ int thread__fork(struct thread *self, struct thread *parent)
 	for (i = 0; i < MAP__NR_TYPES; ++i)
 		if (map_groups__clone(&self->mg, &parent->mg, i) < 0)
 			return -ENOMEM;
+
+	self->ppid = parent->pid;
+
 	return 0;
 }
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 5ad2664..eeb7ac6 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -13,6 +13,7 @@ struct thread {
 	};
 	struct map_groups	mg;
 	pid_t			pid;
+	pid_t			ppid;
 	char			shortname[3];
 	bool			comm_set;
 	char			*comm;
diff --git a/tools/perf/util/top.c b/tools/perf/util/top.c
index 54d37a4..f857b51 100644
--- a/tools/perf/util/top.c
+++ b/tools/perf/util/top.c
@@ -23,20 +23,31 @@
 
 size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size)
 {
-	float samples_per_sec = top->samples / top->delay_secs;
-	float ksamples_per_sec = top->kernel_samples / top->delay_secs;
-	float esamples_percent = (100.0 * top->exact_samples) / top->samples;
+	float samples_per_sec;
+	float ksamples_per_sec;
+	float esamples_percent;
 	struct perf_record_opts *opts = &top->record_opts;
 	struct perf_target *target = &opts->target;
 	size_t ret = 0;
 
+	if (top->samples) {
+		samples_per_sec = top->samples / top->delay_secs;
+		ksamples_per_sec = top->kernel_samples / top->delay_secs;
+		esamples_percent = (100.0 * top->exact_samples) / top->samples;
+	} else {
+		samples_per_sec = ksamples_per_sec = esamples_percent = 0.0;
+	}
+
 	if (!perf_guest) {
+		float ksamples_percent = 0.0;
+
+		if (samples_per_sec)
+			ksamples_percent = (100.0 * ksamples_per_sec) /
+							samples_per_sec;
 		ret = SNPRINTF(bf, size,
 			       "   PerfTop:%8.0f irqs/sec  kernel:%4.1f%%"
 			       "  exact: %4.1f%% [", samples_per_sec,
-			       100.0 - (100.0 * ((samples_per_sec - ksamples_per_sec) /
-					samples_per_sec)),
-				esamples_percent);
+			       ksamples_percent, esamples_percent);
 	} else {
 		float us_samples_per_sec = top->us_samples / top->delay_secs;
 		float guest_kernel_samples_per_sec = top->guest_kernel_samples / top->delay_secs;
diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h
index 7ebf357..df46be9 100644
--- a/tools/perf/util/top.h
+++ b/tools/perf/util/top.h
@@ -26,7 +26,6 @@ struct perf_top {
 	int		   print_entries, count_filter, delay_secs;
 	bool		   hide_kernel_symbols, hide_user_symbols, zero;
 	bool		   use_tui, use_stdio;
-	bool		   sort_has_symbols;
 	bool		   kptr_restrict_warned;
 	bool		   vmlinux_warned;
 	bool		   dump_symtab;
@@ -37,6 +36,7 @@ struct perf_top {
 	int		   realtime_prio;
 	int		   sym_pcnt_filter;
 	const char	   *sym_filter;
+	float		   min_percent;
 };
 
 size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size);
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index a45710b..7a484c9 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -221,8 +221,8 @@ extern unsigned char sane_ctype[256];
 #define isalpha(x) sane_istest(x,GIT_ALPHA)
 #define isalnum(x) sane_istest(x,GIT_ALPHA | GIT_DIGIT)
 #define isprint(x) sane_istest(x,GIT_PRINT)
-#define islower(x) (sane_istest(x,GIT_ALPHA) && sane_istest(x,0x20))
-#define isupper(x) (sane_istest(x,GIT_ALPHA) && !sane_istest(x,0x20))
+#define islower(x) (sane_istest(x,GIT_ALPHA) && (x & 0x20))
+#define isupper(x) (sane_istest(x,GIT_ALPHA) && !(x & 0x20))
 #define tolower(x) sane_case((unsigned char)(x), 0x20)
 #define toupper(x) sane_case((unsigned char)(x), 0)