454 files changed, 77794 insertions, 20541 deletions

diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore
index e1d60d78078..782d86e961b 100644
--- a/tools/perf/.gitignore
+++ b/tools/perf/.gitignore
@@ -1,4 +1,3 @@
-PERF-BUILD-OPTIONS
 PERF-CFLAGS
 PERF-GUI-VARS
 PERF-VERSION-FILE
@@ -14,7 +13,14 @@ perf*.html
 common-cmds.h
 perf.data
 perf.data.old
+output.svg
 perf-archive
 tags
 TAGS
 cscope*
+config.mak
+config.mak.autogen
+*-bison.*
+*-flex.*
+*.pyc
+*.pyo
diff --git a/tools/perf/Documentation/Makefile b/tools/perf/Documentation/Makefile
index bd498d49695..3ba1c0b0990 100644
--- a/tools/perf/Documentation/Makefile
+++ b/tools/perf/Documentation/Makefile
@@ -1,3 +1,6 @@
+include ../../scripts/Makefile.include
+include ../config/utilities.mak
+
 MAN1_TXT= \
 	$(filter-out $(addsuffix .txt, $(ARTICLES) $(SP_ARTICLES)), \
 		$(wildcard perf-*.txt)) \
@@ -6,10 +9,11 @@ MAN5_TXT=
 MAN7_TXT=
 
 MAN_TXT = $(MAN1_TXT) $(MAN5_TXT) $(MAN7_TXT)
-MAN_XML=$(patsubst %.txt,%.xml,$(MAN_TXT))
-MAN_HTML=$(patsubst %.txt,%.html,$(MAN_TXT))
+_MAN_XML=$(patsubst %.txt,%.xml,$(MAN_TXT))
+_MAN_HTML=$(patsubst %.txt,%.html,$(MAN_TXT))
 
-DOC_HTML=$(MAN_HTML)
+MAN_XML=$(addprefix $(OUTPUT),$(_MAN_XML))
+MAN_HTML=$(addprefix $(OUTPUT),$(_MAN_HTML))
 
 ARTICLES =
 # with their own formatting rules.
@@ -18,11 +22,17 @@ API_DOCS = $(patsubst %.txt,%,$(filter-out technical/api-index-skel.txt technica
 SP_ARTICLES += $(API_DOCS)
 SP_ARTICLES += technical/api-index
 
-DOC_HTML += $(patsubst %,%.html,$(ARTICLES) $(SP_ARTICLES))
+_DOC_HTML = $(_MAN_HTML)
+_DOC_HTML+=$(patsubst %,%.html,$(ARTICLES) $(SP_ARTICLES))
+DOC_HTML=$(addprefix $(OUTPUT),$(_DOC_HTML))
+
+_DOC_MAN1=$(patsubst %.txt,%.1,$(MAN1_TXT))
+_DOC_MAN5=$(patsubst %.txt,%.5,$(MAN5_TXT))
+_DOC_MAN7=$(patsubst %.txt,%.7,$(MAN7_TXT))
 
-DOC_MAN1=$(patsubst %.txt,%.1,$(MAN1_TXT))
-DOC_MAN5=$(patsubst %.txt,%.5,$(MAN5_TXT))
-DOC_MAN7=$(patsubst %.txt,%.7,$(MAN7_TXT))
+DOC_MAN1=$(addprefix $(OUTPUT),$(_DOC_MAN1))
+DOC_MAN5=$(addprefix $(OUTPUT),$(_DOC_MAN5))
+DOC_MAN7=$(addprefix $(OUTPUT),$(_DOC_MAN7))
 
 # Make the path relative to DESTDIR, not prefix
 ifndef DESTDIR
@@ -50,6 +60,7 @@ MAKEINFO=makeinfo
 INSTALL_INFO=install-info
 DOCBOOK2X_TEXI=docbook2x-texi
 DBLATEX=dblatex
+XMLTO=xmlto
 ifndef PERL_PATH
 	PERL_PATH = /usr/bin/perl
 endif
@@ -57,6 +68,16 @@ endif
 -include ../config.mak.autogen
 -include ../config.mak
 
+_tmp_tool_path := $(call get-executable,$(ASCIIDOC))
+ifeq ($(_tmp_tool_path),)
+	missing_tools = $(ASCIIDOC)
+endif
+
+_tmp_tool_path := $(call get-executable,$(XMLTO))
+ifeq ($(_tmp_tool_path),)
+	missing_tools += $(XMLTO)
+endif
+
 #
 # For asciidoc ...
 #	-7.1.2,	no extra settings are needed.
@@ -123,17 +144,18 @@ NO_SUBDIR = :
 endif
 
 ifneq ($(findstring $(MAKEFLAGS),s),s)
-ifndef V
-	QUIET_ASCIIDOC	= @echo '   ' ASCIIDOC $@;
-	QUIET_XMLTO	= @echo '   ' XMLTO $@;
-	QUIET_DB2TEXI	= @echo '   ' DB2TEXI $@;
-	QUIET_MAKEINFO	= @echo '   ' MAKEINFO $@;
-	QUIET_DBLATEX	= @echo '   ' DBLATEX $@;
-	QUIET_XSLTPROC	= @echo '   ' XSLTPROC $@;
-	QUIET_GEN	= @echo '   ' GEN $@;
+ifneq ($(V),1)
+	QUIET_ASCIIDOC	= @echo '  ASCIIDOC '$@;
+	QUIET_XMLTO	= @echo '  XMLTO    '$@;
+	QUIET_DB2TEXI	= @echo '  DB2TEXI  '$@;
+	QUIET_MAKEINFO	= @echo '  MAKEINFO '$@;
+	QUIET_DBLATEX	= @echo '  DBLATEX  '$@;
+	QUIET_XSLTPROC	= @echo '  XSLTPROC '$@;
+	QUIET_GEN	= @echo '  GEN      '$@;
 	QUIET_STDERR	= 2> /dev/null
 	QUIET_SUBDIR0	= +@subdir=
-	QUIET_SUBDIR1	= ;$(NO_SUBDIR) echo '   ' SUBDIR $$subdir; \
+	QUIET_SUBDIR1	= ;$(NO_SUBDIR) \
+			   echo '  SUBDIR   ' $$subdir; \
 			  $(MAKE) $(PRINT_DIR) -C $$subdir
 	export V
 endif
@@ -150,53 +172,67 @@ man1: $(DOC_MAN1)
 man5: $(DOC_MAN5)
 man7: $(DOC_MAN7)
 
-info: perf.info perfman.info
+info: $(OUTPUT)perf.info $(OUTPUT)perfman.info
 
-pdf: user-manual.pdf
+pdf: $(OUTPUT)user-manual.pdf
 
 install: install-man
 
-install-man: man
-	$(INSTALL) -d -m 755 $(DESTDIR)$(man1dir)
-#	$(INSTALL) -d -m 755 $(DESTDIR)$(man5dir)
-#	$(INSTALL) -d -m 755 $(DESTDIR)$(man7dir)
-	$(INSTALL) -m 644 $(DOC_MAN1) $(DESTDIR)$(man1dir)
-#	$(INSTALL) -m 644 $(DOC_MAN5) $(DESTDIR)$(man5dir)
-#	$(INSTALL) -m 644 $(DOC_MAN7) $(DESTDIR)$(man7dir)
+check-man-tools:
+ifdef missing_tools
+	$(error "You need to install $(missing_tools) for man pages")
+endif
+
+do-install-man: man
+	$(call QUIET_INSTALL, Documentation-man) \
+		$(INSTALL) -d -m 755 $(DESTDIR)$(man1dir); \
+#		$(INSTALL) -d -m 755 $(DESTDIR)$(man5dir); \
+#		$(INSTALL) -d -m 755 $(DESTDIR)$(man7dir); \
+		$(INSTALL) -m 644 $(DOC_MAN1) $(DESTDIR)$(man1dir); \
+#		$(INSTALL) -m 644 $(DOC_MAN5) $(DESTDIR)$(man5dir); \
+#		$(INSTALL) -m 644 $(DOC_MAN7) $(DESTDIR)$(man7dir)
+
+install-man: check-man-tools man
+
+ifdef missing_tools
+  DO_INSTALL_MAN = $(warning Please install $(missing_tools) to have the man pages installed)
+else
+  DO_INSTALL_MAN = do-install-man
+endif
+
+try-install-man: $(DO_INSTALL_MAN)
 
 install-info: info
-	$(INSTALL) -d -m 755 $(DESTDIR)$(infodir)
-	$(INSTALL) -m 644 perf.info perfman.info $(DESTDIR)$(infodir)
+	$(call QUIET_INSTALL, Documentation-info) \
+		$(INSTALL) -d -m 755 $(DESTDIR)$(infodir); \
+		$(INSTALL) -m 644 $(OUTPUT)perf.info $(OUTPUT)perfman.info $(DESTDIR)$(infodir); \
 	if test -r $(DESTDIR)$(infodir)/dir; then \
-	  $(INSTALL_INFO) --info-dir=$(DESTDIR)$(infodir) perf.info ;\
-	  $(INSTALL_INFO) --info-dir=$(DESTDIR)$(infodir) perfman.info ;\
+		$(INSTALL_INFO) --info-dir=$(DESTDIR)$(infodir) perf.info ;\
+		$(INSTALL_INFO) --info-dir=$(DESTDIR)$(infodir) perfman.info ;\
 	else \
 	  echo "No directory found in $(DESTDIR)$(infodir)" >&2 ; \
 	fi
 
 install-pdf: pdf
-	$(INSTALL) -d -m 755 $(DESTDIR)$(pdfdir)
-	$(INSTALL) -m 644 user-manual.pdf $(DESTDIR)$(pdfdir)
-
-install-html: html
-	'$(SHELL_PATH_SQ)' ./install-webdoc.sh $(DESTDIR)$(htmldir)
+	$(call QUIET_INSTALL, Documentation-pdf) \
+		$(INSTALL) -d -m 755 $(DESTDIR)$(pdfdir); \
+		$(INSTALL) -m 644 $(OUTPUT)user-manual.pdf $(DESTDIR)$(pdfdir)
 
-../PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE
-	$(QUIET_SUBDIR0)../ $(QUIET_SUBDIR1) PERF-VERSION-FILE
+#install-html: html
+#	'$(SHELL_PATH_SQ)' ./install-webdoc.sh $(DESTDIR)$(htmldir)
 
--include ../PERF-VERSION-FILE
 
 #
 # Determine "include::" file references in asciidoc files.
 #
-doc.dep : $(wildcard *.txt) build-docdep.perl
+$(OUTPUT)doc.dep : $(wildcard *.txt) build-docdep.perl
 	$(QUIET_GEN)$(RM) $@+ $@ && \
 	$(PERL_PATH) ./build-docdep.perl >$@+ $(QUIET_STDERR) && \
 	mv $@+ $@
 
--include doc.dep
+-include $(OUPTUT)doc.dep
 
-cmds_txt = cmds-ancillaryinterrogators.txt \
+_cmds_txt = cmds-ancillaryinterrogators.txt \
 	cmds-ancillarymanipulators.txt \
 	cmds-mainporcelain.txt \
 	cmds-plumbinginterrogators.txt \
@@ -205,32 +241,38 @@ cmds_txt = cmds-ancillaryinterrogators.txt \
 	cmds-synchelpers.txt \
 	cmds-purehelpers.txt \
 	cmds-foreignscminterface.txt
+cmds_txt=$(addprefix $(OUTPUT),$(_cmds_txt))
 
-$(cmds_txt): cmd-list.made
+$(cmds_txt): $(OUTPUT)cmd-list.made
 
-cmd-list.made: cmd-list.perl ../command-list.txt $(MAN1_TXT)
+$(OUTPUT)cmd-list.made: cmd-list.perl ../command-list.txt $(MAN1_TXT)
 	$(QUIET_GEN)$(RM) $@ && \
 	$(PERL_PATH) ./cmd-list.perl ../command-list.txt $(QUIET_STDERR) && \
 	date >$@
 
+CLEAN_FILES =									\
+	$(MAN_XML) $(addsuffix +,$(MAN_XML))					\
+	$(MAN_HTML) $(addsuffix +,$(MAN_HTML))					\
+	$(DOC_HTML) $(DOC_MAN1) $(DOC_MAN5) $(DOC_MAN7)				\
+	$(OUTPUT)*.texi $(OUTPUT)*.texi+ $(OUTPUT)*.texi++			\
+	$(OUTPUT)perf.info $(OUTPUT)perfman.info				\
+	$(OUTPUT)howto-index.txt $(OUTPUT)howto/*.html $(OUTPUT)doc.dep		\
+	$(OUTPUT)technical/api-*.html $(OUTPUT)technical/api-index.txt		\
+	$(cmds_txt) $(OUTPUT)*.made
 clean:
-	$(RM) *.xml *.xml+ *.html *.html+ *.1 *.5 *.7
-	$(RM) *.texi *.texi+ *.texi++ perf.info perfman.info
-	$(RM) howto-index.txt howto/*.html doc.dep
-	$(RM) technical/api-*.html technical/api-index.txt
-	$(RM) $(cmds_txt) *.made
+	$(call QUIET_CLEAN, Documentation) $(RM) $(CLEAN_FILES)
 
-$(MAN_HTML): %.html : %.txt
+$(MAN_HTML): $(OUTPUT)%.html : %.txt
 	$(QUIET_ASCIIDOC)$(RM) $@+ $@ && \
 	$(ASCIIDOC) -b xhtml11 -d manpage -f asciidoc.conf \
 		$(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) -o $@+ $< && \
 	mv $@+ $@
 
-%.1 %.5 %.7 : %.xml
+$(OUTPUT)%.1 $(OUTPUT)%.5 $(OUTPUT)%.7 : $(OUTPUT)%.xml
 	$(QUIET_XMLTO)$(RM) $@ && \
-	xmlto -m $(MANPAGE_XSL) $(XMLTO_EXTRA) man $<
+	$(XMLTO) -o $(OUTPUT). -m $(MANPAGE_XSL) $(XMLTO_EXTRA) man $<
 
-%.xml : %.txt
+$(OUTPUT)%.xml : %.txt
 	$(QUIET_ASCIIDOC)$(RM) $@+ $@ && \
 	$(ASCIIDOC) -b docbook -d manpage -f asciidoc.conf \
 		$(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) -o $@+ $< && \
@@ -239,25 +281,25 @@ $(MAN_HTML): %.html : %.txt
 XSLT = docbook.xsl
 XSLTOPTS = --xinclude --stringparam html.stylesheet docbook-xsl.css
 
-user-manual.html: user-manual.xml
+$(OUTPUT)user-manual.html: $(OUTPUT)user-manual.xml
 	$(QUIET_XSLTPROC)xsltproc $(XSLTOPTS) -o $@ $(XSLT) $<
 
-perf.info: user-manual.texi
-	$(QUIET_MAKEINFO)$(MAKEINFO) --no-split -o $@ user-manual.texi
+$(OUTPUT)perf.info: $(OUTPUT)user-manual.texi
+	$(QUIET_MAKEINFO)$(MAKEINFO) --no-split -o $@ $(OUTPUT)user-manual.texi
 
-user-manual.texi: user-manual.xml
+$(OUTPUT)user-manual.texi: $(OUTPUT)user-manual.xml
 	$(QUIET_DB2TEXI)$(RM) $@+ $@ && \
-	$(DOCBOOK2X_TEXI) user-manual.xml --encoding=UTF-8 --to-stdout >$@++ && \
+	$(DOCBOOK2X_TEXI) $(OUTPUT)user-manual.xml --encoding=UTF-8 --to-stdout >$@++ && \
 	$(PERL_PATH) fix-texi.perl <$@++ >$@+ && \
 	rm $@++ && \
 	mv $@+ $@
 
-user-manual.pdf: user-manual.xml
+$(OUTPUT)user-manual.pdf: $(OUTPUT)user-manual.xml
 	$(QUIET_DBLATEX)$(RM) $@+ $@ && \
 	$(DBLATEX) -o $@+ -p /etc/asciidoc/dblatex/asciidoc-dblatex.xsl -s /etc/asciidoc/dblatex/asciidoc-dblatex.sty $< && \
 	mv $@+ $@
 
-perfman.texi: $(MAN_XML) cat-texi.perl
+$(OUTPUT)perfman.texi: $(MAN_XML) cat-texi.perl
 	$(QUIET_DB2TEXI)$(RM) $@+ $@ && \
 	($(foreach xml,$(MAN_XML),$(DOCBOOK2X_TEXI) --encoding=UTF-8 \
 		--to-stdout $(xml) &&) true) > $@++ && \
@@ -265,7 +307,7 @@ perfman.texi: $(MAN_XML) cat-texi.perl
 	rm $@++ && \
 	mv $@+ $@
 
-perfman.info: perfman.texi
+$(OUTPUT)perfman.info: $(OUTPUT)perfman.texi
 	$(QUIET_MAKEINFO)$(MAKEINFO) --no-split --no-validate $*.texi
 
 $(patsubst %.txt,%.texi,$(MAN_TXT)): %.texi : %.xml
@@ -288,15 +330,14 @@ $(patsubst %.txt,%.html,$(wildcard howto/*.txt)): %.html : %.txt
 	sed -e '1,/^$$/d' $< | $(ASCIIDOC) -b xhtml11 - >$@+ && \
 	mv $@+ $@
 
-install-webdoc : html
-	'$(SHELL_PATH_SQ)' ./install-webdoc.sh $(WEBDOC_DEST)
-
-quick-install: quick-install-man
+# UNIMPLEMENTED
+#install-webdoc : html
+#	'$(SHELL_PATH_SQ)' ./install-webdoc.sh $(WEBDOC_DEST)
 
-quick-install-man:
-	'$(SHELL_PATH_SQ)' ./install-doc-quick.sh $(DOC_REF) $(DESTDIR)$(mandir)
+# quick-install: quick-install-man
 
-quick-install-html:
-	'$(SHELL_PATH_SQ)' ./install-doc-quick.sh $(HTML_REF) $(DESTDIR)$(htmldir)
+# quick-install-man:
+#	'$(SHELL_PATH_SQ)' ./install-doc-quick.sh $(DOC_REF) $(DESTDIR)$(mandir)
 
-.PHONY: .FORCE-PERF-VERSION-FILE
+#quick-install-html:
+#	'$(SHELL_PATH_SQ)' ./install-doc-quick.sh $(HTML_REF) $(DESTDIR)$(htmldir)
diff --git a/tools/perf/Documentation/android.txt b/tools/perf/Documentation/android.txt
new file mode 100644
index 00000000000..8484c3a04a6
--- /dev/null
+++ b/tools/perf/Documentation/android.txt
@@ -0,0 +1,78 @@
+How to compile perf for Android
+=========================================
+
+I. Set the Android NDK environment
+------------------------------------------------
+
+(a). Use the Android NDK
+------------------------------------------------
+1. You need to download and install the Android Native Development Kit (NDK).
+Set the NDK variable to point to the path where you installed the NDK:
+  export NDK=/path/to/android-ndk
+
+2. Set cross-compiling environment variables for NDK toolchain and sysroot.
+For arm:
+  export NDK_TOOLCHAIN=${NDK}/toolchains/arm-linux-androideabi-4.6/prebuilt/linux-x86/bin/arm-linux-androideabi-
+  export NDK_SYSROOT=${NDK}/platforms/android-9/arch-arm
+For x86:
+  export NDK_TOOLCHAIN=${NDK}/toolchains/x86-4.6/prebuilt/linux-x86/bin/i686-linux-android-
+  export NDK_SYSROOT=${NDK}/platforms/android-9/arch-x86
+
+This method is not working for Android NDK versions up to Revision 8b.
+perf uses some bionic enhancements that are not included in these NDK versions.
+You can use method (b) described below instead.
+
+(b). Use the Android source tree
+-----------------------------------------------
+1. Download the master branch of the Android source tree.
+Set the environment for the target you want using:
+  source build/envsetup.sh
+  lunch
+
+2. Build your own NDK sysroot to contain latest bionic changes and set the
+NDK sysroot environment variable.
+  cd ${ANDROID_BUILD_TOP}/ndk
+For arm:
+  ./build/tools/build-ndk-sysroot.sh --abi=arm
+  export NDK_SYSROOT=${ANDROID_BUILD_TOP}/ndk/build/platforms/android-3/arch-arm
+For x86:
+  ./build/tools/build-ndk-sysroot.sh --abi=x86
+  export NDK_SYSROOT=${ANDROID_BUILD_TOP}/ndk/build/platforms/android-3/arch-x86
+
+3. Set the NDK toolchain environment variable.
+For arm:
+  export NDK_TOOLCHAIN=${ANDROID_TOOLCHAIN}/arm-linux-androideabi-
+For x86:
+  export NDK_TOOLCHAIN=${ANDROID_TOOLCHAIN}/i686-linux-android-
+
+II. Compile perf for Android
+------------------------------------------------
+You need to run make with the NDK toolchain and sysroot defined above:
+For arm:
+  make ARCH=arm CROSS_COMPILE=${NDK_TOOLCHAIN} CFLAGS="--sysroot=${NDK_SYSROOT}"
+For x86:
+  make ARCH=x86 CROSS_COMPILE=${NDK_TOOLCHAIN} CFLAGS="--sysroot=${NDK_SYSROOT}"
+
+III. Install perf
+-----------------------------------------------
+You need to connect to your Android device/emulator using adb.
+Install perf using:
+  adb push perf /data/perf
+
+If you also want to use perf-archive you need busybox tools for Android.
+For installing perf-archive, you first need to replace #!/bin/bash with #!/system/bin/sh:
+  sed 's/#!\/bin\/bash/#!\/system\/bin\/sh/g' perf-archive >> /tmp/perf-archive
+  chmod +x /tmp/perf-archive
+  adb push /tmp/perf-archive /data/perf-archive
+
+IV. Environment settings for running perf
+------------------------------------------------
+Some perf features need environment variables to run properly.
+You need to set these before running perf on the target:
+  adb shell
+  # PERF_PAGER=cat
+
+IV. Run perf
+------------------------------------------------
+Run perf on your device/emulator to which you previously connected using adb:
+  # ./data/perf
diff --git a/tools/perf/Documentation/examples.txt b/tools/perf/Documentation/examples.txt
index 8eb6c489fb1..a4e39215648 100644
--- a/tools/perf/Documentation/examples.txt
+++ b/tools/perf/Documentation/examples.txt
@@ -17,8 +17,8 @@ titan:~> perf list
   kmem:kmem_cache_alloc_node               [Tracepoint event]
   kmem:kfree                               [Tracepoint event]
   kmem:kmem_cache_free                     [Tracepoint event]
-  kmem:mm_page_free_direct                 [Tracepoint event]
-  kmem:mm_pagevec_free                     [Tracepoint event]
+  kmem:mm_page_free                        [Tracepoint event]
+  kmem:mm_page_free_batched                [Tracepoint event]
   kmem:mm_page_alloc                       [Tracepoint event]
   kmem:mm_page_alloc_zone_locked           [Tracepoint event]
   kmem:mm_page_pcpu_drain                  [Tracepoint event]
@@ -29,15 +29,15 @@ measured. For example the page alloc/free properties of a 'hackbench
 run' are:
 
  titan:~> perf stat -e kmem:mm_page_pcpu_drain -e kmem:mm_page_alloc
- -e kmem:mm_pagevec_free -e kmem:mm_page_free_direct ./hackbench 10
+ -e kmem:mm_page_free_batched -e kmem:mm_page_free ./hackbench 10
  Time: 0.575
 
  Performance counter stats for './hackbench 10':
 
           13857  kmem:mm_page_pcpu_drain
           27576  kmem:mm_page_alloc
-           6025  kmem:mm_pagevec_free
-          20934  kmem:mm_page_free_direct
+           6025  kmem:mm_page_free_batched
+          20934  kmem:mm_page_free
 
     0.613972165  seconds time elapsed
 
@@ -45,8 +45,8 @@ You can observe the statistical properties as well, by using the
 'repeat the workload N times' feature of perf stat:
 
  titan:~> perf stat --repeat 5 -e kmem:mm_page_pcpu_drain -e
-   kmem:mm_page_alloc -e kmem:mm_pagevec_free -e
-   kmem:mm_page_free_direct ./hackbench 10
+   kmem:mm_page_alloc -e kmem:mm_page_free_batched -e
+   kmem:mm_page_free ./hackbench 10
  Time: 0.627
  Time: 0.644
  Time: 0.564
@@ -57,8 +57,8 @@ You can observe the statistical properties as well, by using the
 
           12920  kmem:mm_page_pcpu_drain    ( +-   3.359% )
           25035  kmem:mm_page_alloc         ( +-   3.783% )
-           6104  kmem:mm_pagevec_free       ( +-   0.934% )
-          18376  kmem:mm_page_free_direct   ( +-   4.941% )
+           6104  kmem:mm_page_free_batched  ( +-   0.934% )
+          18376  kmem:mm_page_free	    ( +-   4.941% )
 
     0.643954516  seconds time elapsed   ( +-   2.363% )
 
@@ -66,7 +66,7 @@ Furthermore, these tracepoints can be used to sample the workload as
 well. For example the page allocations done by a 'git gc' can be
 captured the following way:
 
- titan:~/git> perf record -f -e kmem:mm_page_alloc -c 1 ./git gc
+ titan:~/git> perf record -e kmem:mm_page_alloc -c 1 ./git gc
  Counting objects: 1148, done.
  Delta compression using up to 2 threads.
  Compressing objects: 100% (450/450), done.
@@ -120,7 +120,7 @@ Furthermore, call-graph sampling can be done too, of page
 allocations - to see precisely what kind of page allocations there
 are:
 
- titan:~/git> perf record -f -g -e kmem:mm_page_alloc -c 1 ./git gc
+ titan:~/git> perf record -g -e kmem:mm_page_alloc -c 1 ./git gc
  Counting objects: 1148, done.
  Delta compression using up to 2 threads.
  Compressing objects: 100% (450/450), done.
@@ -158,15 +158,15 @@ Or you can observe the whole system's page allocations for 10
 seconds:
 
 titan:~/git> perf stat -a -e kmem:mm_page_pcpu_drain -e
-kmem:mm_page_alloc -e kmem:mm_pagevec_free -e
-kmem:mm_page_free_direct sleep 10
+kmem:mm_page_alloc -e kmem:mm_page_free_batched -e
+kmem:mm_page_free sleep 10
 
  Performance counter stats for 'sleep 10':
 
          171585  kmem:mm_page_pcpu_drain
          322114  kmem:mm_page_alloc
-          73623  kmem:mm_pagevec_free
-         254115  kmem:mm_page_free_direct
+          73623  kmem:mm_page_free_batched
+         254115  kmem:mm_page_free
 
    10.000591410  seconds time elapsed
 
@@ -174,15 +174,15 @@ Or observe how fluctuating the page allocations are, via statistical
 analysis done over ten 1-second intervals:
 
  titan:~/git> perf stat --repeat 10 -a -e kmem:mm_page_pcpu_drain -e
-   kmem:mm_page_alloc -e kmem:mm_pagevec_free -e
-   kmem:mm_page_free_direct sleep 1
+   kmem:mm_page_alloc -e kmem:mm_page_free_batched -e
+   kmem:mm_page_free sleep 1
 
  Performance counter stats for 'sleep 1' (10 runs):
 
           17254  kmem:mm_page_pcpu_drain    ( +-   3.709% )
           34394  kmem:mm_page_alloc         ( +-   4.617% )
-           7509  kmem:mm_pagevec_free       ( +-   4.820% )
-          25653  kmem:mm_page_free_direct   ( +-   3.672% )
+           7509  kmem:mm_page_free_batched  ( +-   4.820% )
+          25653  kmem:mm_page_free	    ( +-   3.672% )
 
     1.058135029  seconds time elapsed   ( +-   3.089% )
 
diff --git a/tools/perf/Documentation/jit-interface.txt b/tools/perf/Documentation/jit-interface.txt
new file mode 100644
index 00000000000..a8656f56491
--- /dev/null
+++ b/tools/perf/Documentation/jit-interface.txt
@@ -0,0 +1,15 @@
+perf supports a simple JIT interface to resolve symbols for dynamic code generated
+by a JIT.
+
+The JIT has to write a /tmp/perf-%d.map  (%d = pid of process) file
+
+This is a text file.
+
+Each line has the following format, fields separated with spaces:
+
+START SIZE symbolname
+
+START and SIZE are hex numbers without 0x.
+symbolname is the rest of the line, so it could contain special characters.
+
+The ownership of the file has to match the process.
diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt
index 5164a655c39..e9cd39a92dc 100644
--- a/tools/perf/Documentation/perf-annotate.txt
+++ b/tools/perf/Documentation/perf-annotate.txt
@@ -8,7 +8,7 @@ perf-annotate - Read perf.data (created by perf record) and display annotated co
 SYNOPSIS
 --------
 [verse]
-'perf annotate' [-i <file> | --input=file] symbol_name
+'perf annotate' [-i <file> | --input=file] [symbol_name]
 
 DESCRIPTION
 -----------
@@ -22,8 +22,80 @@ OPTIONS
 -------
 -i::
 --input=::
-        Input file name. (default: perf.data)
+        Input file name. (default: perf.data unless stdin is a fifo)
+
+-d::
+--dsos=<dso[,dso...]>::
+        Only consider symbols in these dsos.
+-s::
+--symbol=<symbol>::
+        Symbol to annotate.
+
+-f::
+--force::
+        Don't complain, do it.
+
+-v::
+--verbose::
+        Be more verbose. (Show symbol address, etc)
+
+-D::
+--dump-raw-trace::
+        Dump raw trace in ASCII.
+
+-k::
+--vmlinux=<file>::
+        vmlinux pathname.
+
+-m::
+--modules::
+        Load module symbols. WARNING: use only with -k and LIVE kernel.
+
+-l::
+--print-line::
+        Print matching source lines (may be slow).
+
+-P::
+--full-paths::
+        Don't shorten the displayed pathnames.
+
+--stdio:: Use the stdio interface.
+
+--tui:: Use the TUI interface. Use of --tui requires a tty, if one is not
+	present, as when piping to other commands, the stdio interface is
+	used. This interfaces starts by centering on the line with more
+	samples, TAB/UNTAB cycles through the lines with more samples.
+
+--gtk:: Use the GTK interface.
+
+-C::
+--cpu:: Only report samples for the list of CPUs provided. Multiple CPUs can
+	be provided as a comma-separated list with no space: 0,1. Ranges of
+	CPUs are specified with -: 0-2. Default is to report samples on all
+	CPUs.
+
+--asm-raw::
+	Show raw instruction encoding of assembly instructions.
+
+--source::
+	Interleave source code with assembly code. Enabled by default,
+	disable with --no-source.
+
+--symfs=<directory>::
+        Look for files with symbols relative to this directory.
+
+-M::
+--disassembler-style=:: Set disassembler style for objdump.
+
+--objdump=<path>::
+        Path to objdump binary.
+
+--skip-missing::
+	Skip symbols that cannot be annotated.
+
+--group::
+	Show event group information together
 
 SEE ALSO
 --------
-linkperf:perf-record[1]
+linkperf:perf-record[1], linkperf:perf-report[1]
diff --git a/tools/perf/Documentation/perf-archive.txt b/tools/perf/Documentation/perf-archive.txt
index fae174dc7d0..ac6ecbb3e66 100644
--- a/tools/perf/Documentation/perf-archive.txt
+++ b/tools/perf/Documentation/perf-archive.txt
@@ -12,9 +12,9 @@ SYNOPSIS
 
 DESCRIPTION
 -----------
-This command runs runs perf-buildid-list --with-hits, and collects the files
-with the buildids found so that analisys of perf.data contents can be possible
-on another machine.
+This command runs perf-buildid-list --with-hits, and collects the files with the
+buildids found so that analysis of perf.data contents can be possible on another
+machine.
 
 
 SEE ALSO
diff --git a/tools/perf/Documentation/perf-bench.txt b/tools/perf/Documentation/perf-bench.txt
index a3dbadb26ef..4464ad770d5 100644
--- a/tools/perf/Documentation/perf-bench.txt
+++ b/tools/perf/Documentation/perf-bench.txt
@@ -12,7 +12,7 @@ SYNOPSIS
 
 DESCRIPTION
 -----------
-This 'perf bench' command is general framework for benchmark suites.
+This 'perf bench' command is a general framework for benchmark suites.
 
 COMMON OPTIONS
 --------------
@@ -45,14 +45,26 @@ SUBSYSTEM
 'sched'::
 	Scheduler and IPC mechanisms.
 
+'mem'::
+	Memory access performance.
+
+'numa'::
+	NUMA scheduling and MM benchmarks.
+
+'futex'::
+	Futex stressing benchmarks.
+
+'all'::
+	All benchmark subsystems.
+
 SUITES FOR 'sched'
 ~~~~~~~~~~~~~~~~~~
 *messaging*::
 Suite for evaluating performance of scheduler and IPC mechanisms.
 Based on hackbench by Rusty Russell.
 
-Options of *pipe*
-^^^^^^^^^^^^^^^^^
+Options of *messaging*
+^^^^^^^^^^^^^^^^^^^^^^
 -p::
 --pipe::
 Use pipe() instead of socketpair()
@@ -115,6 +127,88 @@ Example of *pipe*
                 59004 ops/sec
 ---------------------
 
+SUITES FOR 'mem'
+~~~~~~~~~~~~~~~~
+*memcpy*::
+Suite for evaluating performance of simple memory copy in various ways.
+
+Options of *memcpy*
+^^^^^^^^^^^^^^^^^^^
+-l::
+--length::
+Specify length of memory to copy (default: 1MB).
+Available units are B, KB, MB, GB and TB (case insensitive).
+
+-r::
+--routine::
+Specify routine to copy (default: default).
+Available routines are depend on the architecture.
+On x86-64, x86-64-unrolled, x86-64-movsq and x86-64-movsb are supported.
+
+-i::
+--iterations::
+Repeat memcpy invocation this number of times.
+
+-c::
+--cycle::
+Use perf's cpu-cycles event instead of gettimeofday syscall.
+
+-o::
+--only-prefault::
+Show only the result with page faults before memcpy.
+
+-n::
+--no-prefault::
+Show only the result without page faults before memcpy.
+
+*memset*::
+Suite for evaluating performance of simple memory set in various ways.
+
+Options of *memset*
+^^^^^^^^^^^^^^^^^^^
+-l::
+--length::
+Specify length of memory to set (default: 1MB).
+Available units are B, KB, MB, GB and TB (case insensitive).
+
+-r::
+--routine::
+Specify routine to set (default: default).
+Available routines are depend on the architecture.
+On x86-64, x86-64-unrolled, x86-64-stosq and x86-64-stosb are supported.
+
+-i::
+--iterations::
+Repeat memset invocation this number of times.
+
+-c::
+--cycle::
+Use perf's cpu-cycles event instead of gettimeofday syscall.
+
+-o::
+--only-prefault::
+Show only the result with page faults before memset.
+
+-n::
+--no-prefault::
+Show only the result without page faults before memset.
+
+SUITES FOR 'numa'
+~~~~~~~~~~~~~~~~~
+*mem*::
+Suite for evaluating NUMA workloads.
+
+SUITES FOR 'futex'
+~~~~~~~~~~~~~~~~~~
+*hash*::
+Suite for evaluating hash tables.
+
+*wake*::
+Suite for evaluating wake calls.
+
+*requeue*::
+Suite for evaluating requeue calls.
+
 SEE ALSO
 --------
 linkperf:perf[1]
diff --git a/tools/perf/Documentation/perf-buildid-cache.txt b/tools/perf/Documentation/perf-buildid-cache.txt
index 5d1a9500277..fd77d81ea74 100644
--- a/tools/perf/Documentation/perf-buildid-cache.txt
+++ b/tools/perf/Documentation/perf-buildid-cache.txt
@@ -12,18 +12,38 @@ SYNOPSIS
 
 DESCRIPTION
 -----------
-This command manages the build-id cache. It can add and remove files to the
-cache. In the future it should as well purge older entries, set upper limits
-for the space used by the cache, etc.
+This command manages the build-id cache. It can add and remove files to/from
+the cache. In the future it should as well purge older entries, set upper
+limits for the space used by the cache, etc.
 
 OPTIONS
 -------
 -a::
 --add=::
         Add specified file to the cache.
+-k::
+--kcore::
+        Add specified kcore file to the cache. For the current host that is
+        /proc/kcore which requires root permissions to read. Be aware that
+        running 'perf buildid-cache' as root may update root's build-id cache
+        not the user's. Use the -v option to see where the file is created.
+        Note that the copied file contains only code sections not the whole core
+        image. Note also that files "kallsyms" and "modules" must also be in the
+        same directory and are also copied.  All 3 files are created with read
+        permissions for root only. kcore will not be added if there is already a
+        kcore in the cache (with the same build-id) that has the same modules at
+        the same addresses. Use the -v option to see if a copy of kcore is
+        actually made.
 -r::
 --remove=::
-        Remove specified file to the cache.
+        Remove specified file from the cache.
+-M::
+--missing=:: 
+	List missing build ids in the cache for the specified file.
+-u::
+--update::
+	Update specified file of the cache. It can be used to update kallsyms
+	kernel dso to vmlinux in order to support annotation.
 -v::
 --verbose::
 	Be more verbose.
diff --git a/tools/perf/Documentation/perf-buildid-list.txt b/tools/perf/Documentation/perf-buildid-list.txt
index 01b642c0bf8..25c52efcc7f 100644
--- a/tools/perf/Documentation/perf-buildid-list.txt
+++ b/tools/perf/Documentation/perf-buildid-list.txt
@@ -16,14 +16,23 @@ This command displays the buildids found in a perf.data file, so that other
 tools can be used to fetch packages with matching symbol tables for use by
 perf report.
 
+It can also be used to show the build id of the running kernel or in an ELF
+file using -i/--input.
+
 OPTIONS
 -------
+-H::
+--with-hits::
+        Show only DSOs with hits.
 -i::
 --input=::
-        Input file name. (default: perf.data)
+        Input file name. (default: perf.data unless stdin is a fifo)
 -f::
 --force::
 	Don't do ownership validation.
+-k::
+--kernel::
+	Show running kernel build id.
 -v::
 --verbose::
 	Be more verbose.
diff --git a/tools/perf/Documentation/perf-diff.txt b/tools/perf/Documentation/perf-diff.txt
index 20d97d84ea1..b3b8abae62b 100644
--- a/tools/perf/Documentation/perf-diff.txt
+++ b/tools/perf/Documentation/perf-diff.txt
@@ -3,46 +3,61 @@ perf-diff(1)
 
 NAME
 ----
-perf-diff - Read two perf.data files and display the differential profile
+perf-diff - Read perf.data files and display the differential profile
 
 SYNOPSIS
 --------
 [verse]
-'perf diff' [oldfile] [newfile]
+'perf diff' [baseline file] [data file1] [[data file2] ... ]
 
 DESCRIPTION
 -----------
-This command displays the performance difference amongst two perf.data files
-captured via perf record.
+This command displays the performance difference amongst two or more perf.data
+files captured via perf record.
 
 If no parameters are passed it will assume perf.data.old and perf.data.
 
+The differential profile is displayed only for events matching both
+specified perf.data files.
+
 OPTIONS
 -------
+-D::
+--dump-raw-trace::
+        Dump raw trace in ASCII.
+
+-m::
+--modules::
+        Load module symbols. WARNING: use only with -k and LIVE kernel
+
 -d::
 --dsos=::
 	Only consider symbols in these dsos. CSV that understands
-	file://filename entries.
+	file://filename entries.  This option will affect the percentage
+	of the Baseline/Delta column.  See --percentage for more info.
 
 -C::
 --comms=::
 	Only consider symbols in these comms. CSV that understands
-	file://filename entries.
+	file://filename entries.  This option will affect the percentage
+	of the Baseline/Delta column.  See --percentage for more info.
 
 -S::
 --symbols=::
 	Only consider these symbols. CSV that understands
-	file://filename entries.
+	file://filename entries.  This option will affect the percentage
+	of the Baseline/Delta column.  See --percentage for more info.
 
 -s::
 --sort=::
-	Sort by key(s): pid, comm, dso, symbol.
+	Sort by key(s): pid, comm, dso, symbol, cpu, parent, srcline.
+	Please see description of --sort in the perf-report man page.
 
 -t::
 --field-separator=::
 
 	Use a special separator character and don't pad with spaces, replacing
-	all occurances of this separator in symbol names (and other output)
+	all occurrences of this separator in symbol names (and other output)
 	with a '.' character, that thus it's the only non valid separator.
 
 -v::
@@ -50,6 +65,142 @@ OPTIONS
 	Be verbose, for instance, show the raw counts in addition to the
 	diff.
 
+-f::
+--force::
+       Don't complain, do it.
+
+--symfs=<directory>::
+        Look for files with symbols relative to this directory.
+
+-b::
+--baseline-only::
+        Show only items with match in baseline.
+
+-c::
+--compute::
+        Differential computation selection - delta,ratio,wdiff (default is delta).
+        See COMPARISON METHODS section for more info.
+
+-p::
+--period::
+        Show period values for both compared hist entries.
+
+-F::
+--formula::
+        Show formula for given computation.
+
+-o::
+--order::
+       Specify compute sorting column number.
+
+--percentage::
+	Determine how to display the overhead percentage of filtered entries.
+	Filters can be applied by --comms, --dsos and/or --symbols options.
+
+	"relative" means it's relative to filtered entries only so that the
+	sum of shown entries will be always 100%.  "absolute" means it retains
+	the original value before and after the filter is applied.
+
+COMPARISON
+----------
+The comparison is governed by the baseline file. The baseline perf.data
+file is iterated for samples. All other perf.data files specified on
+the command line are searched for the baseline sample pair. If the pair
+is found, specified computation is made and result is displayed.
+
+All samples from non-baseline perf.data files, that do not match any
+baseline entry, are displayed with empty space within baseline column
+and possible computation results (delta) in their related column.
+
+Example files samples:
+- file A with samples f1, f2, f3, f4,    f6
+- file B with samples     f2,     f4, f5
+- file C with samples f1, f2,         f5
+
+Example output:
+  x - computation takes place for pair
+  b - baseline sample percentage
+
+- perf diff A B C
+
+  baseline/A compute/B compute/C  samples
+  ---------------------------------------
+  b                    x          f1
+  b          x         x          f2
+  b                               f3
+  b          x                    f4
+  b                               f6
+             x         x          f5
+
+- perf diff B A C
+
+  baseline/B compute/A compute/C  samples
+  ---------------------------------------
+  b          x         x          f2
+  b          x                    f4
+  b                    x          f5
+             x         x          f1
+             x                    f3
+             x                    f6
+
+- perf diff C B A
+
+  baseline/C compute/B compute/A  samples
+  ---------------------------------------
+  b                    x          f1
+  b          x         x          f2
+  b          x                    f5
+                       x          f3
+             x         x          f4
+                       x          f6
+
+COMPARISON METHODS
+------------------
+delta
+~~~~~
+If specified the 'Delta' column is displayed with value 'd' computed as:
+
+  d = A->period_percent - B->period_percent
+
+with:
+  - A/B being matching hist entry from data/baseline file specified
+    (or perf.data/perf.data.old) respectively.
+
+  - period_percent being the % of the hist entry period value within
+    single data file
+
+  - with filtering by -C, -d and/or -S, period_percent might be changed
+    relative to how entries are filtered.  Use --percentage=absolute to
+    prevent such fluctuation.
+
+ratio
+~~~~~
+If specified the 'Ratio' column is displayed with value 'r' computed as:
+
+  r = A->period / B->period
+
+with:
+  - A/B being matching hist entry from data/baseline file specified
+    (or perf.data/perf.data.old) respectively.
+
+  - period being the hist entry period value
+
+wdiff:WEIGHT-B,WEIGHT-A
+~~~~~~~~~~~~~~~~~~~~~~~
+If specified the 'Weighted diff' column is displayed with value 'd' computed as:
+
+   d = B->period * WEIGHT-A - A->period * WEIGHT-B
+
+  - A/B being matching hist entry from data/baseline file specified
+    (or perf.data/perf.data.old) respectively.
+
+  - period being the hist entry period value
+
+  - WEIGHT-A/WEIGHT-B being user suplied weights in the the '-c' option
+    behind ':' separator like '-c wdiff:1,2'.
+    - WIEGHT-A being the weight of the data file
+    - WIEGHT-B being the weight of the baseline data file
+
 SEE ALSO
 --------
-linkperf:perf-record[1]
+linkperf:perf-record[1], linkperf:perf-report[1]
diff --git a/tools/perf/Documentation/perf-evlist.txt b/tools/perf/Documentation/perf-evlist.txt
new file mode 100644
index 00000000000..1ceb3700ffb
--- /dev/null
+++ b/tools/perf/Documentation/perf-evlist.txt
@@ -0,0 +1,38 @@
+perf-evlist(1)
+==============
+
+NAME
+----
+perf-evlist - List the event names in a perf.data file
+
+SYNOPSIS
+--------
+[verse]
+'perf evlist <options>'
+
+DESCRIPTION
+-----------
+This command displays the names of events sampled in a perf.data file.
+
+OPTIONS
+-------
+-i::
+--input=::
+        Input file name. (default: perf.data unless stdin is a fifo)
+
+-F::
+--freq=::
+	Show just the sample frequency used for each event.
+
+-v::
+--verbose=::
+	Show all fields.
+
+-g::
+--group::
+	Show event group information.
+
+SEE ALSO
+--------
+linkperf:perf-record[1], linkperf:perf-list[1],
+linkperf:perf-report[1]
diff --git a/tools/perf/Documentation/perf-inject.txt b/tools/perf/Documentation/perf-inject.txt
index 025630d43cd..a00a34276c5 100644
--- a/tools/perf/Documentation/perf-inject.txt
+++ b/tools/perf/Documentation/perf-inject.txt
@@ -29,6 +29,17 @@ OPTIONS
 -v::
 --verbose::
 	Be more verbose.
+-i::
+--input=::
+	Input file name. (default: stdin)
+-o::
+--output=::
+	Output file name. (default: stdout)
+-s::
+--sched-stat::
+	Merge sched_stat and sched_switch for getting events where and how long
+	tasks slept. sched_switch contains a callchain where a task slept and
+	sched_stat contains a timeslice how long a task slept.
 
 SEE ALSO
 --------
diff --git a/tools/perf/Documentation/perf-kmem.txt b/tools/perf/Documentation/perf-kmem.txt
index a52fcde894c..7c8fbbf3f61 100644
--- a/tools/perf/Documentation/perf-kmem.txt
+++ b/tools/perf/Documentation/perf-kmem.txt
@@ -23,7 +23,7 @@ OPTIONS
 -------
 -i <file>::
 --input=<file>::
-	Select the input file (default: perf.data)
+	Select the input file (default: perf.data unless stdin is a fifo)
 
 --caller::
 	Show per-callsite statistics
diff --git a/tools/perf/Documentation/perf-kvm.txt b/tools/perf/Documentation/perf-kvm.txt
index d004e19fe6d..52276a6d2b7 100644
--- a/tools/perf/Documentation/perf-kvm.txt
+++ b/tools/perf/Documentation/perf-kvm.txt
@@ -10,9 +10,10 @@ SYNOPSIS
 [verse]
 'perf kvm' [--host] [--guest] [--guestmount=<path>
 	[--guestkallsyms=<path> --guestmodules=<path> | --guestvmlinux=<path>]]
-	{top|record|report|diff|buildid-list}
+	{top|record|report|diff|buildid-list} [<options>]
 'perf kvm' [--host] [--guest] [--guestkallsyms=<path> --guestmodules=<path>
-	| --guestvmlinux=<path>] {top|record|report|diff|buildid-list}
+	| --guestvmlinux=<path>] {top|record|report|diff|buildid-list|stat} [<options>]
+'perf kvm stat [record|report|live] [<options>]
 
 DESCRIPTION
 -----------
@@ -22,11 +23,18 @@ There are a couple of variants of perf kvm:
   a performance counter profile of guest os in realtime
   of an arbitrary workload.
 
-  'perf kvm record <command>' to record the performance couinter profile
-  of an arbitrary workload and save it into a perf data file. If both
-  --host and --guest are input, the perf data file name is perf.data.kvm.
-  If there is  no --host but --guest, the file name is perf.data.guest.
-  If there is no --guest but --host, the file name is perf.data.host.
+  'perf kvm record <command>' to record the performance counter profile
+  of an arbitrary workload and save it into a perf data file. We set the
+  default behavior of perf kvm as --guest, so if neither --host nor --guest
+  is input, the perf data file name is perf.data.guest. If --host is input,
+  the perf data file name is perf.data.kvm. If you want to record data into
+  perf.data.host, please input --host --no-guest. The behaviors are shown as
+  following:
+    Default('')         ->  perf.data.guest
+    --host              ->  perf.data.kvm
+    --guest             ->  perf.data.guest
+    --host --guest      ->  perf.data.kvm
+    --host --no-guest   ->  perf.data.host
 
   'perf kvm report' to display the performance counter profile information
   recorded via perf kvm record.
@@ -36,13 +44,37 @@ There are a couple of variants of perf kvm:
 
   'perf kvm buildid-list' to  display the buildids found in a perf data file,
   so that other tools can be used to fetch packages with matching symbol tables
-  for use by perf report.
+  for use by perf report. As buildid is read from /sys/kernel/notes in os, then
+  if you want to list the buildid for guest, please make sure your perf data file
+  was captured with --guestmount in perf kvm record.
+
+  'perf kvm stat <command>' to run a command and gather performance counter
+  statistics.
+  Especially, perf 'kvm stat record/report' generates a statistical analysis
+  of KVM events. Currently, vmexit, mmio and ioport events are supported.
+  'perf kvm stat record <command>' records kvm events and the events between
+  start and end <command>.
+  And this command produces a file which contains tracing results of kvm
+  events.
+
+  'perf kvm stat report' reports statistical data which includes events
+  handled time, samples, and so on.
+
+  'perf kvm stat live' reports statistical data in a live mode (similar to
+  record + report but with statistical data updated live at a given display
+  rate).
 
 OPTIONS
 -------
---host=::
+-i::
+--input=<path>::
+        Input file name.
+-o::
+--output=<path>::
+        Output file name.
+--host::
         Collect host side performance profile.
---guest=::
+--guest::
         Collect guest side performance profile.
 --guestmount=<path>::
 	Guest os root file system mount directory. Users mounts guest os
@@ -61,8 +93,64 @@ OPTIONS
 	kernel module information. Users copy it out from guest os.
 --guestvmlinux=<path>::
 	Guest os kernel vmlinux.
+-v::
+--verbose::
+	Be more verbose (show counter open errors, etc).
+
+STAT REPORT OPTIONS
+-------------------
+--vcpu=<value>::
+       analyze events which occures on this vcpu. (default: all vcpus)
+
+--event=<value>::
+       event to be analyzed. Possible values: vmexit, mmio, ioport.
+       (default: vmexit)
+-k::
+--key=<value>::
+       Sorting key. Possible values: sample (default, sort by samples
+       number), time (sort by average time).
+-p::
+--pid=::
+    Analyze events only for given process ID(s) (comma separated list).
+
+STAT LIVE OPTIONS
+-----------------
+-d::
+--display::
+        Time in seconds between display updates
+
+-m::
+--mmap-pages=::
+    Number of mmap data pages (must be a power of two) or size
+    specification with appended unit character - B/K/M/G. The
+    size is rounded up to have nearest pages power of two value.
+
+-a::
+--all-cpus::
+        System-wide collection from all CPUs.
+
+-p::
+--pid=::
+    Analyze events only for given process ID(s) (comma separated list).
+
+--vcpu=<value>::
+       analyze events which occures on this vcpu. (default: all vcpus)
+
+
+--event=<value>::
+       event to be analyzed. Possible values: vmexit, mmio, ioport.
+       (default: vmexit)
+
+-k::
+--key=<value>::
+       Sorting key. Possible values: sample (default, sort by samples
+       number), time (sort by average time).
+
+--duration=<value>::
+       Show events other than HLT that take longer than duration usecs.
 
 SEE ALSO
 --------
 linkperf:perf-top[1], linkperf:perf-record[1], linkperf:perf-report[1],
-linkperf:perf-diff[1], linkperf:perf-buildid-list[1]
+linkperf:perf-diff[1], linkperf:perf-buildid-list[1],
+linkperf:perf-stat[1]
diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index 43e3dd284b9..6fce6a62220 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -8,13 +8,53 @@ perf-list - List all symbolic event types
 SYNOPSIS
 --------
 [verse]
-'perf list'
+'perf list' [hw|sw|cache|tracepoint|pmu|event_glob]
 
 DESCRIPTION
 -----------
 This command displays the symbolic event types which can be selected in the
 various perf commands with the -e option.
 
+[[EVENT_MODIFIERS]]
+EVENT MODIFIERS
+---------------
+
+Events can optionally have a modifer by appending a colon and one or
+more modifiers. Modifiers allow the user to restrict the events to be
+counted. The following modifiers exist:
+
+ u - user-space counting
+ k - kernel counting
+ h - hypervisor counting
+ G - guest counting (in KVM guests)
+ H - host counting (not in KVM guests)
+ p - precise level
+ S - read sample value (PERF_SAMPLE_READ)
+ D - pin the event to the PMU
+
+The 'p' modifier can be used for specifying how precise the instruction
+address should be. The 'p' modifier can be specified multiple times:
+
+ 0 - SAMPLE_IP can have arbitrary skid
+ 1 - SAMPLE_IP must have constant skid
+ 2 - SAMPLE_IP requested to have 0 skid
+ 3 - SAMPLE_IP must have 0 skid
+
+For Intel systems precise event sampling is implemented with PEBS
+which supports up to precise-level 2.
+
+On AMD systems it is implemented using IBS (up to precise-level 2).
+The precise modifier works with event types 0x76 (cpu-cycles, CPU
+clocks not halted) and 0xC1 (micro-ops retired). Both events map to
+IBS execution sampling (IBS op) with the IBS Op Counter Control bit
+(IbsOpCntCtl) set respectively (see AMD64 Architecture Programmer’s
+Manual Volume 2: System Programming, 13.3 Instruction-Based
+Sampling). Examples to use IBS:
+
+ perf record -a -e cpu-cycles:p ...    # use ibs op counting cycles
+ perf record -a -e r076:p ...          # same as -e cpu-cycles:p
+ perf record -a -e r0C1:p ...          # use ibs op counting micro-ops
+
 RAW HARDWARE EVENT DESCRIPTOR
 -----------------------------
 Even when an event is not available in a symbolic form within perf right now,
@@ -25,6 +65,11 @@ layout of IA32_PERFEVTSELx MSRs (see [Intel® 64 and IA-32 Architectures Softwar
 of IA32_PERFEVTSELx MSRs) or AMD's PerfEvtSeln (see [AMD64 Architecture Programmer’s Manual Volume 2: System Programming], Page 344,
 Figure 13-7 Performance Event-Select Register (PerfEvtSeln)).
 
+Note: Only the following bit fields can be set in x86 counter
+registers: event, umask, edge, inv, cmask. Esp. guest/host only and
+OS/user mode flags must be setup using <<EVENT_MODIFIERS, EVENT
+MODIFIERS>>.
+
 Example:
 
 If the Intel docs for a QM720 Core i7 describe an event as:
@@ -46,11 +91,32 @@ details. Some of them are referenced in the SEE ALSO section below.
 
 OPTIONS
 -------
-None
+
+Without options all known events will be listed.
+
+To limit the list use:
+
+. 'hw' or 'hardware' to list hardware events such as cache-misses, etc.
+
+. 'sw' or 'software' to list software events such as context switches, etc.
+
+. 'cache' or 'hwcache' to list hardware cache events such as L1-dcache-loads, etc.
+
+. 'tracepoint' to list all tracepoint events, alternatively use
+  'subsys_glob:event_glob' to filter by tracepoint subsystems such as sched,
+  block, etc.
+
+. 'pmu' to print the kernel supplied PMU events.
+
+. If none of the above is matched, it will apply the supplied glob to all
+  events, printing the ones that match.
+
+One or more types can be used at the same time, listing the events for the
+types specified.
 
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-top[1],
 linkperf:perf-record[1],
 http://www.intel.com/Assets/PDF/manual/253669.pdf[Intel® 64 and IA-32 Architectures Software Developer's Manual Volume 3B: System Programming Guide],
-http://support.amd.com/us/Processor_TechDocs/24593.pdf[AMD64 Architecture Programmer’s Manual Volume 2: System Programming]
+http://support.amd.com/us/Processor_TechDocs/24593_APM_v2.pdf[AMD64 Architecture Programmer’s Manual Volume 2: System Programming]
diff --git a/tools/perf/Documentation/perf-lock.txt b/tools/perf/Documentation/perf-lock.txt
index b317102138c..ab25be28c9d 100644
--- a/tools/perf/Documentation/perf-lock.txt
+++ b/tools/perf/Documentation/perf-lock.txt
@@ -8,7 +8,7 @@ perf-lock - Analyze lock events
 SYNOPSIS
 --------
 [verse]
-'perf lock' {record|report|trace}
+'perf lock' {record|report|script|info}
 
 DESCRIPTION
 -----------
@@ -20,10 +20,47 @@ and statistics with this 'perf lock' command.
   produces the file "perf.data" which contains tracing
   results of lock events.
 
-  'perf lock trace' shows raw lock events.
-
   'perf lock report' reports statistical data.
 
+  'perf lock script' shows raw lock events.
+
+  'perf lock info' shows metadata like threads or addresses
+  of lock instances.
+
+COMMON OPTIONS
+--------------
+
+-i::
+--input=<file>::
+        Input file name. (default: perf.data unless stdin is a fifo)
+
+-v::
+--verbose::
+        Be more verbose (show symbol address, etc).
+
+-D::
+--dump-raw-trace::
+        Dump raw trace in ASCII.
+
+REPORT OPTIONS
+--------------
+
+-k::
+--key=<value>::
+        Sorting key. Possible values: acquired (default), contended,
+	avg_wait, wait_total, wait_max, wait_min.
+
+INFO OPTIONS
+------------
+
+-t::
+--threads::
+	dump thread list in perf.data
+
+-m::
+--map::
+	dump map of lock instances (address:name table)
+
 SEE ALSO
 --------
 linkperf:perf[1]
diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt
new file mode 100644
index 00000000000..1d78a4064da
--- /dev/null
+++ b/tools/perf/Documentation/perf-mem.txt
@@ -0,0 +1,52 @@
+perf-mem(1)
+===========
+
+NAME
+----
+perf-mem - Profile memory accesses
+
+SYNOPSIS
+--------
+[verse]
+'perf mem' [<options>] (record [<command>] | report)
+
+DESCRIPTION
+-----------
+"perf mem -t <TYPE> record" runs a command and gathers memory operation data
+from it, into perf.data. Perf record options are accepted and are passed through.
+
+"perf mem -t <TYPE> report" displays the result. It invokes perf report with the
+right set of options to display a memory access profile.
+
+Note that on Intel systems the memory latency reported is the use-latency,
+not the pure load (or store latency). Use latency includes any pipeline
+queueing delays in addition to the memory subsystem latency.
+
+OPTIONS
+-------
+<command>...::
+	Any command you can specify in a shell.
+
+-t::
+--type=::
+	Select the memory operation type: load or store (default: load)
+
+-D::
+--dump-raw-samples=::
+	Dump the raw decoded samples on the screen in a format that is easy to parse with
+	one sample per line.
+
+-x::
+--field-separator::
+	Specify the field separator used when dump raw samples (-D option). By default,
+	The separator is the space character.
+
+-C::
+--cpu-list::
+	Restrict dump of raw samples to those provided via this option. Note that the same
+	option can be passed in record mode. It will be interpreted the same way as perf
+	record.
+
+SEE ALSO
+--------
+linkperf:perf-record[1], linkperf:perf-report[1]
diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt
index 94a258c96a4..1513935c399 100644
--- a/tools/perf/Documentation/perf-probe.txt
+++ b/tools/perf/Documentation/perf-probe.txt
@@ -16,7 +16,9 @@ or
 or
 'perf probe' --list
 or
-'perf probe' --line='FUNC[:RLN[+NUM|:RLN2]]|SRC:ALN[+NUM|:ALN2]'
+'perf probe' [options] --line='LINE'
+or
+'perf probe' [options] --vars='PROBEPOINT'
 
 DESCRIPTION
 -----------
@@ -31,6 +33,17 @@ OPTIONS
 --vmlinux=PATH::
 	Specify vmlinux path which has debuginfo (Dwarf binary).
 
+-m::
+--module=MODNAME|PATH::
+	Specify module name in which perf-probe searches probe points
+	or lines. If a path of module file is passed, perf-probe
+	treat it as an offline module (this means you can add a probe on
+        a module which has not been loaded yet).
+
+-s::
+--source=PATH::
+	Specify path to kernel source.
+
 -v::
 --verbose::
         Be more verbose (show parsed arguments, etc).
@@ -53,6 +66,27 @@ OPTIONS
 	Show source code lines which can be probed. This needs an argument
 	which specifies a range of the source code. (see LINE SYNTAX for detail)
 
+-V::
+--vars=::
+	Show available local variables at given probe point. The argument
+	syntax is same as PROBE SYNTAX, but NO ARGs.
+
+--externs::
+	(Only for --vars) Show external defined variables in addition to local
+	variables.
+
+-F::
+--funcs::
+	Show available functions in given module or kernel. With -x/--exec,
+	can also list functions in a user space executable / shared library.
+
+--filter=FILTER::
+	(Only for --vars and --funcs) Set filter. FILTER is a combination of glob
+	pattern, see FILTER PATTERN for detail.
+	Default FILTER is "!__k???tab_* & !__crc_*" for --vars, and "!_*"
+	for --funcs.
+	If several filters are specified, only the last filter is used.
+
 -f::
 --force::
 	Forcibly add events with existing name.
@@ -65,6 +99,15 @@ OPTIONS
 --max-probes::
 	Set the maximum number of probe points for an event. Default is 128.
 
+-x::
+--exec=PATH::
+	Specify path to the executable or shared library file for user
+	space tracing. Can also be used with --funcs option.
+
+In absence of -m/-x options, perf probe checks if the first argument after
+the options is an absolute path name. If its an absolute path, perf probe
+uses it as a target module/target user space binary to probe.
+
 PROBE SYNTAX
 ------------
 Probe points are defined by following syntax.
@@ -90,20 +133,23 @@ Each probe argument follows below syntax.
 
  [NAME=]LOCALVAR|$retval|%REG|@SYMBOL[:TYPE]
 
-'NAME' specifies the name of this argument (optional). You can use the name of local variable, local data structure member (e.g. var->field, var.field2), or kprobe-tracer argument format (e.g. $retval, %ax, etc). Note that the name of this argument will be set as the last member name if you specify a local data structure member (e.g. field2 for 'var->field1.field2'.)
-'TYPE' casts the type of this argument (optional). If omitted, perf probe automatically set the type based on debuginfo.
+'NAME' specifies the name of this argument (optional). You can use the name of local variable, local data structure member (e.g. var->field, var.field2), local array with fixed index (e.g. array[1], var->array[0], var->pointer[2]), or kprobe-tracer argument format (e.g. $retval, %ax, etc). Note that the name of this argument will be set as the last member name if you specify a local data structure member (e.g. field2 for 'var->field1.field2'.)
+'TYPE' casts the type of this argument (optional). If omitted, perf probe automatically set the type based on debuginfo. You can specify 'string' type only for the local variable or structure member which is an array of or a pointer to 'char' or 'unsigned char' type.
+
+On x86 systems %REG is always the short form of the register: for example %AX. %RAX or %EAX is not valid.
 
 LINE SYNTAX
 -----------
-Line range is descripted by following syntax.
+Line range is described by following syntax.
 
- "FUNC[:RLN[+NUM|-RLN2]]|SRC:ALN[+NUM|-ALN2]"
+ "FUNC[@SRC][:RLN[+NUM|-RLN2]]|SRC[:ALN[+NUM|-ALN2]]"
 
 FUNC specifies the function name of showing lines. 'RLN' is the start line
 number from function entry line, and 'RLN2' is the end line number. As same as
 probe syntax, 'SRC' means the source file path, 'ALN' is start line number,
 and 'ALN2' is end line number in the file. It is also possible to specify how
-many lines to show by using 'NUM'.
+many lines to show by using 'NUM'. Moreover, 'FUNC@SRC' combination is good
+for searching a specific function when several functions share same name.
 So, "source.c:100-120" shows lines between 100th to l20th in source.c file. And "func:10+20" shows 20 lines from 10th line of func function.
 
 LAZY MATCHING
@@ -115,6 +161,14 @@ e.g.
 
 This provides some sort of flexibility and robustness to probe point definitions against minor code changes. For example, actual 10th line of schedule() can be moved easily by modifying schedule(), but the same line matching 'rq=cpu_rq*' may still exist in the function.)
 
+FILTER PATTERN
+--------------
+ The filter pattern is a glob matching pattern(s) to filter variables.
+ In addition, you can use "!" for specifying filter-out rule. You also can give several rules combined with "&" or "|", and fold those rules as one rule by using "(" ")".
+
+e.g.
+ With --filter "foo* | bar*", perf probe -V shows variables which start with "foo" or "bar".
+ With --filter "!foo* & *bar", perf probe -V shows variables which don't start with "foo" and end with "bar", like "fizzbar". But "foobar" is filtered out.
 
 EXAMPLES
 --------
@@ -140,6 +194,13 @@ Delete all probes on schedule().
 
  ./perf probe --del='schedule*'
 
+Add probes at zfree() function on /bin/zsh
+
+ ./perf probe -x /bin/zsh zfree or ./perf probe /bin/zsh zfree
+
+Add probes at malloc() function on libc
+
+ ./perf probe -x /lib/libc.so.6 malloc or ./perf probe /lib/libc.so.6 malloc
 
 SEE ALSO
 --------
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 34e255fc3e2..d460049cae8 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -39,26 +39,37 @@ OPTIONS
           be passed as follows: '\mem:addr[:[r][w][x]]'.
           If you want to profile read-write accesses in 0x1000, just set
           'mem:0x1000:rw'.
+
+--filter=<filter>::
+        Event filter.
+
 -a::
-        System-wide collection.
+--all-cpus::
+        System-wide collection from all CPUs.
 
 -l::
         Scale counter values.
 
 -p::
 --pid=::
-	Record events on existing pid.
+	Record events on existing process ID (comma separated list).
+
+-t::
+--tid=::
+        Record events on existing thread ID (comma separated list).
+        This option also disables inheritance by default.  Enable it by adding
+        --inherit.
+
+-u::
+--uid=::
+        Record events in threads owned by uid. Name or number.
 
 -r::
 --realtime=::
 	Collect data with this RT SCHED_FIFO priority.
--A::
---append::
-	Append to the output file to do incremental profiling.
 
--f::
---force::
-	Overwrite existing data file. (deprecated)
+--no-buffering::
+	Collect data without buffering.
 
 -c::
 --count=::
@@ -77,11 +88,29 @@ OPTIONS
 
 -m::
 --mmap-pages=::
-	Number of mmap data pages.
+	Number of mmap data pages (must be a power of two) or size
+	specification with appended unit character - B/K/M/G. The
+	size is rounded up to have nearest pages power of two value.
 
 -g::
+	Enables call-graph (stack chain/backtrace) recording.
+
 --call-graph::
-	Do call-graph (stack chain/backtrace) recording.
+	Setup and enable call-graph (stack chain/backtrace) recording,
+	implies -g.
+
+	Allows specifying "fp" (frame pointer) or "dwarf"
+	(DWARF's CFI - Call Frame Information) as the method to collect
+	the information used to show the call graphs.
+
+	In some systems, where binaries are build with gcc
+	--fomit-frame-pointer, using the "fp" method will produce bogus
+	call graphs, using "dwarf", if available (perf tools linked to
+	the libunwind library) should be used instead.
+
+-q::
+--quiet::
+	Don't print any message, useful for scripting.
 
 -v::
 --verbose::
@@ -95,6 +124,11 @@ OPTIONS
 --data::
 	Sample addresses.
 
+-T::
+--timestamp::
+	Sample timestamps. Use it with 'perf report -D' to see the timestamps,
+	for instance.
+
 -n::
 --no-samples::
 	Don't sample.
@@ -103,6 +137,83 @@ OPTIONS
 --raw-samples::
 Collect raw sample records from all opened counters (default for tracepoint counters).
 
+-C::
+--cpu::
+Collect samples only on the list of CPUs provided. Multiple CPUs can be provided as a
+comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2.
+In per-thread mode with inheritance mode on (default), samples are captured only when
+the thread executes on the designated CPUs. Default is to monitor all CPUs.
+
+-N::
+--no-buildid-cache::
+Do not update the builid cache. This saves some overhead in situations
+where the information in the perf.data file (which includes buildids)
+is sufficient.
+
+-G name,...::
+--cgroup name,...::
+monitor only in the container (cgroup) called "name". This option is available only
+in per-cpu mode. The cgroup filesystem must be mounted. All threads belonging to
+container "name" are monitored when they run on the monitored CPUs. Multiple cgroups
+can be provided. Each cgroup is applied to the corresponding event, i.e., first cgroup
+to first event, second cgroup to second event and so on. It is possible to provide
+an empty cgroup (monitor all the time) using, e.g., -G foo,,bar. Cgroups must have
+corresponding events, i.e., they always refer to events defined earlier on the command
+line.
+
+-b::
+--branch-any::
+Enable taken branch stack sampling. Any type of taken branch may be sampled.
+This is a shortcut for --branch-filter any. See --branch-filter for more infos.
+
+-j::
+--branch-filter::
+Enable taken branch stack sampling. Each sample captures a series of consecutive
+taken branches. The number of branches captured with each sample depends on the
+underlying hardware, the type of branches of interest, and the executed code.
+It is possible to select the types of branches captured by enabling filters. The
+following filters are defined:
+
+        - any:  any type of branches
+        - any_call: any function call or system call
+        - any_ret: any function return or system call return
+        - ind_call: any indirect branch
+        - u:  only when the branch target is at the user level
+        - k: only when the branch target is in the kernel
+        - hv: only when the target is at the hypervisor level
+	- in_tx: only when the target is in a hardware transaction
+	- no_tx: only when the target is not in a hardware transaction
+	- abort_tx: only when the target is a hardware transaction abort
+	- cond: conditional branches
+
++
+The option requires at least one branch type among any, any_call, any_ret, ind_call, cond.
+The privilege levels may be omitted, in which case, the privilege levels of the associated
+event are applied to the branch filter. Both kernel (k) and hypervisor (hv) privilege
+levels are subject to permissions.  When sampling on multiple events, branch stack sampling
+is enabled for all the sampling events. The sampled branch type is the same for all events.
+The various filters must be specified as a comma separated list: --branch-filter any_ret,u,k
+Note that this feature may not be available on all processors.
+
+--weight::
+Enable weightened sampling. An additional weight is recorded per sample and can be
+displayed with the weight and local_weight sort keys.  This currently works for TSX
+abort events and some memory events in precise mode on modern Intel CPUs.
+
+--transaction::
+Record transaction flags for transaction related events.
+
+--per-thread::
+Use per-thread mmaps.  By default per-cpu mmaps are created.  This option
+overrides that and uses per-thread mmaps.  A side-effect of that is that
+inheritance is automatically disabled.  --per-thread is ignored with a warning
+if combined with -a or -C options.
+
+-D::
+--delay=::
+After starting the program, wait msecs before measuring. This is useful to
+filter out the startup phase of the program, which is often very different.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-list[1]
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index abfabe9147a..d2b59af62bc 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -19,52 +19,292 @@ OPTIONS
 -------
 -i::
 --input=::
-        Input file name. (default: perf.data)
--d::
---dsos=::
-	Only consider symbols in these dsos. CSV that understands
-	file://filename entries.
+        Input file name. (default: perf.data unless stdin is a fifo)
+
+-v::
+--verbose::
+        Be more verbose. (show symbol address, etc)
+
 -n::
 --show-nr-samples::
 	Show the number of samples for each symbol
+
+--showcpuutilization::
+        Show sample percentage for different cpu modes.
+
 -T::
 --threads::
 	Show per-thread event counters
--C::
+-c::
 --comms=::
 	Only consider symbols in these comms. CSV that understands
-	file://filename entries.
+	file://filename entries.  This option will affect the percentage of
+	the overhead column.  See --percentage for more info.
+-d::
+--dsos=::
+	Only consider symbols in these dsos. CSV that understands
+	file://filename entries.  This option will affect the percentage of
+	the overhead column.  See --percentage for more info.
 -S::
 --symbols=::
 	Only consider these symbols. CSV that understands
-	file://filename entries.
+	file://filename entries.  This option will affect the percentage of
+	the overhead column.  See --percentage for more info.
+
+--symbol-filter=::
+	Only show symbols that match (partially) with this filter.
+
+-U::
+--hide-unresolved::
+        Only display entries resolved to a symbol.
 
 -s::
 --sort=::
-	Sort by key(s): pid, comm, dso, symbol, parent.
+	Sort histogram entries by given key(s) - multiple keys can be specified
+	in CSV format.  Following sort keys are available:
+	pid, comm, dso, symbol, parent, cpu, srcline, weight, local_weight.
+
+	Each key has following meaning:
+
+	- comm: command (name) of the task which can be read via /proc/<pid>/comm
+	- pid: command and tid of the task
+	- dso: name of library or module executed at the time of sample
+	- symbol: name of function executed at the time of sample
+	- parent: name of function matched to the parent regex filter. Unmatched
+	entries are displayed as "[other]".
+	- cpu: cpu number the task ran at the time of sample
+	- srcline: filename and line number executed at the time of sample.  The
+	DWARF debugging info must be provided.
+	- weight: Event specific weight, e.g. memory latency or transaction
+	abort cost. This is the global weight.
+	- local_weight: Local weight version of the weight above.
+	- transaction: Transaction abort flags.
+	- overhead: Overhead percentage of sample
+	- overhead_sys: Overhead percentage of sample running in system mode
+	- overhead_us: Overhead percentage of sample running in user mode
+	- overhead_guest_sys: Overhead percentage of sample running in system mode
+	on guest machine
+	- overhead_guest_us: Overhead percentage of sample running in user mode on
+	guest machine
+	- sample: Number of sample
+	- period: Raw number of event count of sample
+
+	By default, comm, dso and symbol keys are used.
+	(i.e. --sort comm,dso,symbol)
+
+	If --branch-stack option is used, following sort keys are also
+	available:
+	dso_from, dso_to, symbol_from, symbol_to, mispredict.
+
+	- dso_from: name of library or module branched from
+	- dso_to: name of library or module branched to
+	- symbol_from: name of function branched from
+	- symbol_to: name of function branched to
+	- mispredict: "N" for predicted branch, "Y" for mispredicted branch
+	- in_tx: branch in TSX transaction
+	- abort: TSX transaction abort.
+
+	And default sort keys are changed to comm, dso_from, symbol_from, dso_to
+	and symbol_to, see '--branch-stack'.
+
+-F::
+--fields=::
+	Specify output field - multiple keys can be specified in CSV format.
+	Following fields are available:
+	overhead, overhead_sys, overhead_us, overhead_children, sample and period.
+	Also it can contain any sort key(s).
+
+	By default, every sort keys not specified in -F will be appended
+	automatically.
+
+	If --mem-mode option is used, following sort keys are also available
+	(incompatible with --branch-stack):
+	symbol_daddr, dso_daddr, locked, tlb, mem, snoop, dcacheline.
+
+	- symbol_daddr: name of data symbol being executed on at the time of sample
+	- dso_daddr: name of library or module containing the data being executed
+	on at the time of sample
+	- locked: whether the bus was locked at the time of sample
+	- tlb: type of tlb access for the data at the time of sample
+	- mem: type of memory access for the data at the time of sample
+	- snoop: type of snoop (if any) for the data at the time of sample
+	- dcacheline: the cacheline the data address is on at the time of sample
+
+	And default sort keys are changed to local_weight, mem, sym, dso,
+	symbol_daddr, dso_daddr, snoop, tlb, locked, see '--mem-mode'.
+
+-p::
+--parent=<regex>::
+        A regex filter to identify parent. The parent is a caller of this
+	function and searched through the callchain, thus it requires callchain
+	information recorded. The pattern is in the exteneded regex format and
+	defaults to "\^sys_|^do_page_fault", see '--sort parent'.
+
+-x::
+--exclude-other::
+        Only display entries with parent-match.
 
 -w::
---field-width=::
+--column-widths=<width[,width...]>::
 	Force each column width to the provided list, for large terminal
 	readability.
 
 -t::
 --field-separator=::
-
 	Use a special separator character and don't pad with spaces, replacing
-	all occurances of this separator in symbol names (and other output)
+	all occurrences of this separator in symbol names (and other output)
 	with a '.' character, that thus it's the only non valid separator.
 
--g [type,min]::
+-D::
+--dump-raw-trace::
+        Dump raw trace in ASCII.
+
+-g [type,min[,limit],order[,key]]::
 --call-graph::
-        Display callchains using type and min percent threshold.
+        Display call chains using type, min percent threshold, optional print
+	limit and order.
 	type can be either:
-	- flat: single column, linear exposure of callchains.
+	- flat: single column, linear exposure of call chains.
 	- graph: use a graph tree, displaying absolute overhead rates.
 	- fractal: like graph, but displays relative rates. Each branch of
 		 the tree is considered as a new profiled object. +
-	Default: fractal,0.5.
+
+	order can be either:
+	- callee: callee based call graph.
+	- caller: inverted caller based call graph.
+
+	key can be:
+	- function: compare on functions
+	- address: compare on individual code addresses
+
+	Default: fractal,0.5,callee,function.
+
+--children::
+	Accumulate callchain of children to parent entry so that then can
+	show up in the output.  The output will have a new "Children" column
+	and will be sorted on the data.  It requires callchains are recorded.
+
+--max-stack::
+	Set the stack depth limit when parsing the callchain, anything
+	beyond the specified depth will be ignored. This is a trade-off
+	between information loss and faster processing especially for
+	workloads that can have a very long callchain stack.
+
+	Default: 127
+
+-G::
+--inverted::
+        alias for inverted caller based call graph.
+
+--ignore-callees=<regex>::
+        Ignore callees of the function(s) matching the given regex.
+        This has the effect of collecting the callers of each such
+        function into one place in the call-graph tree.
+
+--pretty=<key>::
+        Pretty printing style.  key: normal, raw
+
+--stdio:: Use the stdio interface.
+
+--tui:: Use the TUI interface, that is integrated with annotate and allows
+        zooming into DSOs or threads, among other features. Use of --tui
+	requires a tty, if one is not present, as when piping to other
+	commands, the stdio interface is used.
+
+--gtk:: Use the GTK2 interface.
+
+-k::
+--vmlinux=<file>::
+        vmlinux pathname
+
+--kallsyms=<file>::
+        kallsyms pathname
+
+-m::
+--modules::
+        Load module symbols. WARNING: This should only be used with -k and
+        a LIVE kernel.
+
+-f::
+--force::
+        Don't complain, do it.
+
+--symfs=<directory>::
+        Look for files with symbols relative to this directory.
+
+-C::
+--cpu:: Only report samples for the list of CPUs provided. Multiple CPUs can
+	be provided as a comma-separated list with no space: 0,1. Ranges of
+	CPUs are specified with -: 0-2. Default is to report samples on all
+	CPUs.
+
+-M::
+--disassembler-style=:: Set disassembler style for objdump.
+
+--source::
+	Interleave source code with assembly code. Enabled by default,
+	disable with --no-source.
+
+--asm-raw::
+	Show raw instruction encoding of assembly instructions.
+
+--show-total-period:: Show a column with the sum of periods.
+
+-I::
+--show-info::
+	Display extended information about the perf.data file. This adds
+	information which may be very large and thus may clutter the display.
+	It currently includes: cpu and numa topology of the host system.
+
+-b::
+--branch-stack::
+	Use the addresses of sampled taken branches instead of the instruction
+	address to build the histograms. To generate meaningful output, the
+	perf.data file must have been obtained using perf record -b or
+	perf record --branch-filter xxx where xxx is a branch filter option.
+	perf report is able to auto-detect whether a perf.data file contains
+	branch stacks and it will automatically switch to the branch view mode,
+	unless --no-branch-stack is used.
+
+--objdump=<path>::
+        Path to objdump binary.
+
+--group::
+	Show event group information together.
+
+--demangle::
+	Demangle symbol names to human readable form. It's enabled by default,
+	disable with --no-demangle.
+
+--mem-mode::
+	Use the data addresses of samples in addition to instruction addresses
+	to build the histograms.  To generate meaningful output, the perf.data
+	file must have been obtained using perf record -d -W and using a
+	special event -e cpu/mem-loads/ or -e cpu/mem-stores/. See
+	'perf mem' for simpler access.
+
+--percent-limit::
+	Do not show entries which have an overhead under that percent.
+	(Default: 0).
+
+--percentage::
+	Determine how to display the overhead percentage of filtered entries.
+	Filters can be applied by --comms, --dsos and/or --symbols options and
+	Zoom operations on the TUI (thread, dso, etc).
+
+	"relative" means it's relative to filtered entries only so that the
+	sum of shown entries will be always 100%.  "absolute" means it retains
+	the original value before and after the filter is applied.
+
+--header::
+	Show header information in the perf.data file.  This includes
+	various information like hostname, OS and perf version, cpu/mem
+	info, perf command line, event list and so on.  Currently only
+	--stdio output supports this feature.
+
+--header-only::
+	Show only perf.data header (forces --stdio).
 
 SEE ALSO
 --------
-linkperf:perf-stat[1]
+linkperf:perf-stat[1], linkperf:perf-annotate[1]
diff --git a/tools/perf/Documentation/perf-sched.txt b/tools/perf/Documentation/perf-sched.txt
index 8417644a616..8ff4df95695 100644
--- a/tools/perf/Documentation/perf-sched.txt
+++ b/tools/perf/Documentation/perf-sched.txt
@@ -8,11 +8,11 @@ perf-sched - Tool to trace/measure scheduler properties (latencies)
 SYNOPSIS
 --------
 [verse]
-'perf sched' {record|latency|replay|trace}
+'perf sched' {record|latency|map|replay|script}
 
 DESCRIPTION
 -----------
-There are four variants of perf sched:
+There are five variants of perf sched:
 
   'perf sched record <command>' to record the scheduling events
   of an arbitrary workload.
@@ -20,8 +20,8 @@ There are four variants of perf sched:
   'perf sched latency' to report the per task scheduling latencies
   and other scheduling properties of the workload.
 
-  'perf sched trace' to see a detailed trace of the workload that
-  was recorded.
+  'perf sched script' to see a detailed trace of the workload that
+   was recorded (aliased to 'perf script' for now).
 
   'perf sched replay' to simulate the workload that was recorded
   via perf sched record. (this is done by starting up mockup threads
@@ -30,8 +30,22 @@ There are four variants of perf sched:
   of the workload as it occurred when it was recorded - and can repeat
   it a number of times, measuring its performance.)
 
+  'perf sched map' to print a textual context-switching outline of
+  workload captured via perf sched record.  Columns stand for
+  individual CPUs, and the two-letter shortcuts stand for tasks that
+  are running on a CPU. A '*' denotes the CPU that had the event, and
+  a dot signals an idle CPU.
+
 OPTIONS
 -------
+-i::
+--input=<file>::
+        Input file name. (default: perf.data unless stdin is a fifo)
+
+-v::
+--verbose::
+        Be more verbose. (show symbol address, etc)
+
 -D::
 --dump-raw-trace=::
         Display verbose dump of the sched data.
diff --git a/tools/perf/Documentation/perf-trace-perl.txt b/tools/perf/Documentation/perf-script-perl.txt
index ee6525ee6d6..d00bef23134 100644
--- a/tools/perf/Documentation/perf-trace-perl.txt
+++ b/tools/perf/Documentation/perf-script-perl.txt
@@ -1,19 +1,19 @@
-perf-trace-perl(1)
+perf-script-perl(1)
 ==================
 
 NAME
 ----
-perf-trace-perl - Process trace data with a Perl script
+perf-script-perl - Process trace data with a Perl script
 
 SYNOPSIS
 --------
 [verse]
-'perf trace' [-s [Perl]:script[.pl] ]
+'perf script' [-s [Perl]:script[.pl] ]
 
 DESCRIPTION
 -----------
 
-This perf trace option is used to process perf trace data using perf's
+This perf script option is used to process perf script data using perf's
 built-in Perl interpreter.  It reads and processes the input file and
 displays the results of the trace analysis implemented in the given
 Perl script, if any.
@@ -21,7 +21,7 @@ Perl script, if any.
 STARTER SCRIPTS
 ---------------
 
-You can avoid reading the rest of this document by running 'perf trace
+You can avoid reading the rest of this document by running 'perf script
 -g perl' in the same directory as an existing perf.data trace file.
 That will generate a starter script containing a handler for each of
 the event types in the trace file; it simply prints every available
@@ -30,13 +30,13 @@ field for each event in the trace file.
 You can also look at the existing scripts in
 ~/libexec/perf-core/scripts/perl for typical examples showing how to
 do basic things like aggregate event data, print results, etc.  Also,
-the check-perf-trace.pl script, while not interesting for its results,
+the check-perf-script.pl script, while not interesting for its results,
 attempts to exercise all of the main scripting features.
 
 EVENT HANDLERS
 --------------
 
-When perf trace is invoked using a trace script, a user-defined
+When perf script is invoked using a trace script, a user-defined
 'handler function' is called for each event in the trace.  If there's
 no handler function defined for a given event type, the event is
 ignored (or passed to a 'trace_handled' function, see below) and the
@@ -63,7 +63,6 @@ The format file for the sched_wakep event defines the following fields
         field:unsigned char common_flags;
         field:unsigned char common_preempt_count;
         field:int common_pid;
-        field:int common_lock_depth;
 
         field:char comm[TASK_COMM_LEN];
         field:pid_t pid;
@@ -112,7 +111,7 @@ write a useful trace script.  The sections below cover the rest.
 SCRIPT LAYOUT
 -------------
 
-Every perf trace Perl script should start by setting up a Perl module
+Every perf script Perl script should start by setting up a Perl module
 search path and 'use'ing a few support modules (see module
 descriptions below):
 
@@ -162,7 +161,7 @@ sub trace_unhandled
 ----
 
 The remaining sections provide descriptions of each of the available
-built-in perf trace Perl modules and their associated functions.
+built-in perf script Perl modules and their associated functions.
 
 AVAILABLE MODULES AND FUNCTIONS
 -------------------------------
@@ -170,7 +169,7 @@ AVAILABLE MODULES AND FUNCTIONS
 The following sections describe the functions and variables available
 via the various Perf::Trace::* Perl modules.  To use the functions and
 variables from the given module, add the corresponding 'use
-Perf::Trace::XXX' line to your perf trace script.
+Perf::Trace::XXX' line to your perf script script.
 
 Perf::Trace::Core Module
 ~~~~~~~~~~~~~~~~~~~~~~~~
@@ -204,7 +203,7 @@ argument.
 Perf::Trace::Util Module
 ~~~~~~~~~~~~~~~~~~~~~~~~
 
-Various utility functions for use with perf trace:
+Various utility functions for use with perf script:
 
   nsecs($secs, $nsecs) - returns total nsecs given secs/nsecs pair
   nsecs_secs($nsecs) - returns whole secs portion given nsecs
@@ -214,4 +213,4 @@ Various utility functions for use with perf trace:
 
 SEE ALSO
 --------
-linkperf:perf-trace[1]
+linkperf:perf-script[1]
diff --git a/tools/perf/Documentation/perf-trace-python.txt b/tools/perf/Documentation/perf-script-python.txt
index 693be804dd3..9f1f054b843 100644
--- a/tools/perf/Documentation/perf-trace-python.txt
+++ b/tools/perf/Documentation/perf-script-python.txt
@@ -1,19 +1,19 @@
-perf-trace-python(1)
+perf-script-python(1)
 ====================
 
 NAME
 ----
-perf-trace-python - Process trace data with a Python script
+perf-script-python - Process trace data with a Python script
 
 SYNOPSIS
 --------
 [verse]
-'perf trace' [-s [Python]:script[.py] ]
+'perf script' [-s [Python]:script[.py] ]
 
 DESCRIPTION
 -----------
 
-This perf trace option is used to process perf trace data using perf's
+This perf script option is used to process perf script data using perf's
 built-in Python interpreter.  It reads and processes the input file and
 displays the results of the trace analysis implemented in the given
 Python script, if any.
@@ -23,15 +23,15 @@ A QUICK EXAMPLE
 
 This section shows the process, start to finish, of creating a working
 Python script that aggregates and extracts useful information from a
-raw perf trace stream.  You can avoid reading the rest of this
+raw perf script stream.  You can avoid reading the rest of this
 document if an example is enough for you; the rest of the document
 provides more details on each step and lists the library functions
 available to script writers.
 
 This example actually details the steps that were used to create the
-'syscall-counts' script you see when you list the available perf trace
-scripts via 'perf trace -l'.  As such, this script also shows how to
-integrate your script into the list of general-purpose 'perf trace'
+'syscall-counts' script you see when you list the available perf script
+scripts via 'perf script -l'.  As such, this script also shows how to
+integrate your script into the list of general-purpose 'perf script'
 scripts listed by that command.
 
 The syscall-counts script is a simple script, but demonstrates all the
@@ -105,25 +105,25 @@ That single stream will be recorded in a file in the current directory
 called perf.data.
 
 Once we have a perf.data file containing our data, we can use the -g
-'perf trace' option to generate a Python script that will contain a
+'perf script' option to generate a Python script that will contain a
 callback handler for each event type found in the perf.data trace
 stream (for more details, see the STARTER SCRIPTS section).
 
 ----
-# perf trace -g python
-generated Python script: perf-trace.py
+# perf script -g python
+generated Python script: perf-script.py
 
 The output file created also in the current directory is named
-perf-trace.py.  Here's the file in its entirety:
+perf-script.py.  Here's the file in its entirety:
 
-# perf trace event handlers, generated by perf trace -g python
+# perf script event handlers, generated by perf script -g python
 # Licensed under the terms of the GNU GPL License version 2
 
 # The common_* event handler fields are the most useful fields common to
 # all events.  They don't necessarily correspond to the 'common_*' fields
 # in the format files.  Those fields not available as handler params can
 # be retrieved using Python functions of the form common_*(context).
-# See the perf-trace-python Documentation for the list of available functions.
+# See the perf-script-python Documentation for the list of available functions.
 
 import os
 import sys
@@ -160,7 +160,7 @@ def print_header(event_name, cpu, secs, nsecs, pid, comm):
 ----
 
 At the top is a comment block followed by some import statements and a
-path append which every perf trace script should include.
+path append which every perf script script should include.
 
 Following that are a couple generated functions, trace_begin() and
 trace_end(), which are called at the beginning and the end of the
@@ -189,8 +189,8 @@ simply a utility function used for that purpose.  Let's rename the
 script and run it to see the default output:
 
 ----
-# mv perf-trace.py syscall-counts.py
-# perf trace -s syscall-counts.py
+# mv perf-script.py syscall-counts.py
+# perf script -s syscall-counts.py
 
 raw_syscalls__sys_enter     1 00840.847582083     7506 perf                  id=1, args=
 raw_syscalls__sys_enter     1 00840.847595764     7506 perf                  id=1, args=
@@ -315,7 +315,7 @@ def print_syscall_totals():
 
 The script can be run just as before:
 
-  # perf trace -s syscall-counts.py
+  # perf script -s syscall-counts.py
 
 So those are the essential steps in writing and running a script.  The
 process can be generalized to any tracepoint or set of tracepoints
@@ -324,19 +324,18 @@ interested in by looking at the list of available events shown by
 'perf list' and/or look in /sys/kernel/debug/tracing events for
 detailed event and field info, record the corresponding trace data
 using 'perf record', passing it the list of interesting events,
-generate a skeleton script using 'perf trace -g python' and modify the
+generate a skeleton script using 'perf script -g python' and modify the
 code to aggregate and display it for your particular needs.
 
 After you've done that you may end up with a general-purpose script
 that you want to keep around and have available for future use.  By
 writing a couple of very simple shell scripts and putting them in the
 right place, you can have your script listed alongside the other
-scripts listed by the 'perf trace -l' command e.g.:
+scripts listed by the 'perf script -l' command e.g.:
 
 ----
-root@tropicana:~# perf trace -l
+root@tropicana:~# perf script -l
 List of available trace scripts:
-  workqueue-stats                      workqueue stats (ins/exe/create/destroy)
   wakeup-latency                       system-wide min/max/avg wakeup latency
   rw-by-file <comm>                    r/w activity for a program, by file
   rw-by-pid                            system-wide r/w activity
@@ -365,14 +364,14 @@ perf record -a -e raw_syscalls:sys_enter
 The 'report' script is also a shell script with the same base name as
 your script, but with -report appended.  It should also be located in
 the perf/scripts/python/bin directory.  In that script, you write the
-'perf trace -s' command-line needed for running your script:
+'perf script -s' command-line needed for running your script:
 
 ----
 # cat kernel-source/tools/perf/scripts/python/bin/syscall-counts-report
 
 #!/bin/bash
 # description: system-wide syscall counts
-perf trace -s ~/libexec/perf-core/scripts/python/syscall-counts.py
+perf script -s ~/libexec/perf-core/scripts/python/syscall-counts.py
 ----
 
 Note that the location of the Python script given in the shell script
@@ -390,38 +389,37 @@ total 32
 drwxr-xr-x 4 trz trz 4096 2010-01-26 22:30 .
 drwxr-xr-x 4 trz trz 4096 2010-01-26 22:29 ..
 drwxr-xr-x 2 trz trz 4096 2010-01-26 22:29 bin
--rw-r--r-- 1 trz trz 2548 2010-01-26 22:29 check-perf-trace.py
+-rw-r--r-- 1 trz trz 2548 2010-01-26 22:29 check-perf-script.py
 drwxr-xr-x 3 trz trz 4096 2010-01-26 22:49 Perf-Trace-Util
 -rw-r--r-- 1 trz trz 1462 2010-01-26 22:30 syscall-counts.py
 ----
 
 Once you've done that (don't forget to do a new 'make install',
-otherwise your script won't show up at run-time), 'perf trace -l'
+otherwise your script won't show up at run-time), 'perf script -l'
 should show a new entry for your script:
 
 ----
-root@tropicana:~# perf trace -l
+root@tropicana:~# perf script -l
 List of available trace scripts:
-  workqueue-stats                      workqueue stats (ins/exe/create/destroy)
   wakeup-latency                       system-wide min/max/avg wakeup latency
   rw-by-file <comm>                    r/w activity for a program, by file
   rw-by-pid                            system-wide r/w activity
   syscall-counts                       system-wide syscall counts
 ----
 
-You can now perform the record step via 'perf trace record':
+You can now perform the record step via 'perf script record':
 
-  # perf trace record syscall-counts
+  # perf script record syscall-counts
 
-and display the output using 'perf trace report':
+and display the output using 'perf script report':
 
-  # perf trace report syscall-counts
+  # perf script report syscall-counts
 
 STARTER SCRIPTS
 ---------------
 
 You can quickly get started writing a script for a particular set of
-trace data by generating a skeleton script using 'perf trace -g
+trace data by generating a skeleton script using 'perf script -g
 python' in the same directory as an existing perf.data trace file.
 That will generate a starter script containing a handler for each of
 the event types in the trace file; it simply prints every available
@@ -430,13 +428,13 @@ field for each event in the trace file.
 You can also look at the existing scripts in
 ~/libexec/perf-core/scripts/python for typical examples showing how to
 do basic things like aggregate event data, print results, etc.  Also,
-the check-perf-trace.py script, while not interesting for its results,
+the check-perf-script.py script, while not interesting for its results,
 attempts to exercise all of the main scripting features.
 
 EVENT HANDLERS
 --------------
 
-When perf trace is invoked using a trace script, a user-defined
+When perf script is invoked using a trace script, a user-defined
 'handler function' is called for each event in the trace.  If there's
 no handler function defined for a given event type, the event is
 ignored (or passed to a 'trace_handled' function, see below) and the
@@ -463,7 +461,6 @@ The format file for the sched_wakep event defines the following fields
         field:unsigned char common_flags;
         field:unsigned char common_preempt_count;
         field:int common_pid;
-        field:int common_lock_depth;
 
         field:char comm[TASK_COMM_LEN];
         field:pid_t pid;
@@ -510,7 +507,7 @@ write a useful trace script.  The sections below cover the rest.
 SCRIPT LAYOUT
 -------------
 
-Every perf trace Python script should start by setting up a Python
+Every perf script Python script should start by setting up a Python
 module search path and 'import'ing a few support modules (see module
 descriptions below):
 
@@ -559,15 +556,15 @@ def trace_unhandled(event_name, context, common_cpu, common_secs,
 ----
 
 The remaining sections provide descriptions of each of the available
-built-in perf trace Python modules and their associated functions.
+built-in perf script Python modules and their associated functions.
 
 AVAILABLE MODULES AND FUNCTIONS
 -------------------------------
 
 The following sections describe the functions and variables available
-via the various perf trace Python modules.  To use the functions and
+via the various perf script Python modules.  To use the functions and
 variables from the given module, add the corresponding 'from XXXX
-import' line to your perf trace script.
+import' line to your perf script script.
 
 Core.py Module
 ~~~~~~~~~~~~~~
@@ -610,7 +607,7 @@ argument.
 Util.py Module
 ~~~~~~~~~~~~~~
 
-Various utility functions for use with perf trace:
+Various utility functions for use with perf script:
 
   nsecs(secs, nsecs) - returns total nsecs given secs/nsecs pair
   nsecs_secs(nsecs) - returns whole secs portion given nsecs
@@ -620,4 +617,4 @@ Various utility functions for use with perf trace:
 
 SEE ALSO
 --------
-linkperf:perf-trace[1]
+linkperf:perf-script[1]
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
new file mode 100644
index 00000000000..05f9a0a6784
--- /dev/null
+++ b/tools/perf/Documentation/perf-script.txt
@@ -0,0 +1,221 @@
+perf-script(1)
+=============
+
+NAME
+----
+perf-script - Read perf.data (created by perf record) and display trace output
+
+SYNOPSIS
+--------
+[verse]
+'perf script' [<options>]
+'perf script' [<options>] record <script> [<record-options>] <command>
+'perf script' [<options>] report <script> [script-args]
+'perf script' [<options>] <script> <required-script-args> [<record-options>] <command>
+'perf script' [<options>] <top-script> [script-args]
+
+DESCRIPTION
+-----------
+This command reads the input file and displays the trace recorded.
+
+There are several variants of perf script:
+
+  'perf script' to see a detailed trace of the workload that was
+  recorded.
+
+  You can also run a set of pre-canned scripts that aggregate and
+  summarize the raw trace data in various ways (the list of scripts is
+  available via 'perf script -l').  The following variants allow you to
+  record and run those scripts:
+
+  'perf script record <script> <command>' to record the events required
+  for 'perf script report'.  <script> is the name displayed in the
+  output of 'perf script --list' i.e. the actual script name minus any
+  language extension.  If <command> is not specified, the events are
+  recorded using the -a (system-wide) 'perf record' option.
+
+  'perf script report <script> [args]' to run and display the results
+  of <script>.  <script> is the name displayed in the output of 'perf
+  trace --list' i.e. the actual script name minus any language
+  extension.  The perf.data output from a previous run of 'perf script
+  record <script>' is used and should be present for this command to
+  succeed.  [args] refers to the (mainly optional) args expected by
+  the script.
+
+  'perf script <script> <required-script-args> <command>' to both
+  record the events required for <script> and to run the <script>
+  using 'live-mode' i.e. without writing anything to disk.  <script>
+  is the name displayed in the output of 'perf script --list' i.e. the
+  actual script name minus any language extension.  If <command> is
+  not specified, the events are recorded using the -a (system-wide)
+  'perf record' option.  If <script> has any required args, they
+  should be specified before <command>.  This mode doesn't allow for
+  optional script args to be specified; if optional script args are
+  desired, they can be specified using separate 'perf script record'
+  and 'perf script report' commands, with the stdout of the record step
+  piped to the stdin of the report script, using the '-o -' and '-i -'
+  options of the corresponding commands.
+
+  'perf script <top-script>' to both record the events required for
+  <top-script> and to run the <top-script> using 'live-mode'
+  i.e. without writing anything to disk.  <top-script> is the name
+  displayed in the output of 'perf script --list' i.e. the actual
+  script name minus any language extension; a <top-script> is defined
+  as any script name ending with the string 'top'.
+
+  [<record-options>] can be passed to the record steps of 'perf script
+  record' and 'live-mode' variants; this isn't possible however for
+  <top-script> 'live-mode' or 'perf script report' variants.
+
+  See the 'SEE ALSO' section for links to language-specific
+  information on how to write and run your own trace scripts.
+
+OPTIONS
+-------
+<command>...::
+	Any command you can specify in a shell.
+
+-D::
+--dump-raw-script=::
+        Display verbose dump of the trace data.
+
+-L::
+--Latency=::
+        Show latency attributes (irqs/preemption disabled, etc).
+
+-l::
+--list=::
+        Display a list of available trace scripts.
+
+-s ['lang']::
+--script=::
+        Process trace data with the given script ([lang]:script[.ext]).
+	If the string 'lang' is specified in place of a script name, a
+        list of supported languages will be displayed instead.
+
+-g::
+--gen-script=::
+        Generate perf-script.[ext] starter script for given language,
+        using current perf.data.
+
+-a::
+        Force system-wide collection.  Scripts run without a <command>
+        normally use -a by default, while scripts run with a <command>
+        normally don't - this option allows the latter to be run in
+        system-wide mode.
+
+-i::
+--input=::
+        Input file name. (default: perf.data unless stdin is a fifo)
+
+-d::
+--debug-mode::
+        Do various checks like samples ordering and lost events.
+
+-f::
+--fields::
+        Comma separated list of fields to print. Options are:
+        comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff, srcline.
+        Field list can be prepended with the type, trace, sw or hw,
+        to indicate to which event type the field list applies.
+        e.g., -f sw:comm,tid,time,ip,sym  and -f trace:time,cpu,trace
+
+		perf script -f <fields>
+
+	is equivalent to:
+
+		perf script -f trace:<fields> -f sw:<fields> -f hw:<fields>
+    
+	i.e., the specified fields apply to all event types if the type string
+	is not given.
+    
+	The arguments are processed in the order received. A later usage can
+	reset a prior request. e.g.:
+    
+		-f trace: -f comm,tid,time,ip,sym
+    
+	The first -f suppresses trace events (field list is ""), but then the
+	second invocation sets the fields to comm,tid,time,ip,sym. In this case a
+	warning is given to the user:
+    
+		"Overriding previous field request for all events."
+    
+	Alternativey, consider the order:
+    
+		-f comm,tid,time,ip,sym -f trace:
+    
+	The first -f sets the fields for all events and the second -f
+	suppresses trace events. The user is given a warning message about
+	the override, and the result of the above is that only S/W and H/W
+	events are displayed with the given fields.
+    
+	For the 'wildcard' option if a user selected field is invalid for an
+	event type, a message is displayed to the user that the option is
+	ignored for that type. For example:
+    
+		$ perf script -f comm,tid,trace
+		'trace' not valid for hardware events. Ignoring.
+		'trace' not valid for software events. Ignoring.
+    
+	Alternatively, if the type is given an invalid field is specified it
+	is an error. For example:
+    
+        perf script -v -f sw:comm,tid,trace
+        'trace' not valid for software events.
+    
+	At this point usage is displayed, and perf-script exits.
+    
+	Finally, a user may not set fields to none for all event types.
+	i.e., -f "" is not allowed.
+
+-k::
+--vmlinux=<file>::
+        vmlinux pathname
+
+--kallsyms=<file>::
+        kallsyms pathname
+
+--symfs=<directory>::
+        Look for files with symbols relative to this directory.
+
+-G::
+--hide-call-graph::
+        When printing symbols do not display call chain.
+
+-C::
+--cpu:: Only report samples for the list of CPUs provided. Multiple CPUs can
+	be provided as a comma-separated list with no space: 0,1. Ranges of
+	CPUs are specified with -: 0-2. Default is to report samples on all
+	CPUs.
+
+-c::
+--comms=::
+	Only display events for these comms. CSV that understands
+	file://filename entries.
+
+-I::
+--show-info::
+	Display extended information about the perf.data file. This adds
+	information which may be very large and thus may clutter the display.
+	It currently includes: cpu and numa topology of the host system.
+	It can only be used with the perf script report mode.
+
+--show-kernel-path::
+	Try to resolve the path of [kernel.kallsyms]
+
+--show-task-events
+	Display task related events (e.g. FORK, COMM, EXIT).
+
+--show-mmap-events
+	Display mmap related events (e.g. MMAP, MMAP2).
+
+--header
+	Show perf.data header.
+
+--header-only
+	Show only perf.data header.
+
+SEE ALSO
+--------
+linkperf:perf-record[1], linkperf:perf-script-perl[1],
+linkperf:perf-script-python[1]
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 909fa766fa1..29ee857c09c 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -8,8 +8,8 @@ perf-stat - Run a command and gather performance counter statistics
 SYNOPSIS
 --------
 [verse]
-'perf stat' [-e <EVENT> | --event=EVENT] [-S] [-a] <command>
-'perf stat' [-e <EVENT> | --event=EVENT] [-S] [-a] -- <command> [<options>]
+'perf stat' [-e <EVENT> | --event=EVENT] [-a] <command>
+'perf stat' [-e <EVENT> | --event=EVENT] [-a] -- <command> [<options>]
 
 DESCRIPTION
 -----------
@@ -35,17 +35,113 @@ OPTIONS
         child tasks do not inherit counters
 -p::
 --pid=<pid>::
-        stat events on existing pid
+        stat events on existing process id (comma separated list)
+
+-t::
+--tid=<tid>::
+        stat events on existing thread id (comma separated list)
+
 
 -a::
-        system-wide collection
+--all-cpus::
+        system-wide collection from all CPUs
 
 -c::
-        scale counter values
+--scale::
+	scale/normalize counter values
+
+-r::
+--repeat=<n>::
+	repeat command and print average + stddev (max: 100). 0 means forever.
 
 -B::
+--big-num::
         print large numbers with thousands' separators according to locale
 
+-C::
+--cpu=::
+Count only on the list of CPUs provided. Multiple CPUs can be provided as a
+comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2.
+In per-thread mode, this option is ignored. The -a option is still necessary
+to activate system-wide monitoring. Default is to count on all CPUs.
+
+-A::
+--no-aggr::
+Do not aggregate counts across all monitored CPUs in system-wide mode (-a).
+This option is only valid in system-wide mode.
+
+-n::
+--null::
+        null run - don't start any counters
+
+-v::
+--verbose::
+        be more verbose (show counter open errors, etc)
+
+-x SEP::
+--field-separator SEP::
+print counts using a CSV-style output to make it easy to import directly into
+spreadsheets. Columns are separated by the string specified in SEP.
+
+-G name::
+--cgroup name::
+monitor only in the container (cgroup) called "name". This option is available only
+in per-cpu mode. The cgroup filesystem must be mounted. All threads belonging to
+container "name" are monitored when they run on the monitored CPUs. Multiple cgroups
+can be provided. Each cgroup is applied to the corresponding event, i.e., first cgroup
+to first event, second cgroup to second event and so on. It is possible to provide
+an empty cgroup (monitor all the time) using, e.g., -G foo,,bar. Cgroups must have
+corresponding events, i.e., they always refer to events defined earlier on the command
+line.
+
+-o file::
+--output file::
+Print the output into the designated file.
+
+--append::
+Append to the output file designated with the -o option. Ignored if -o is not specified.
+
+--log-fd::
+
+Log output to fd, instead of stderr.  Complementary to --output, and mutually exclusive
+with it.  --append may be used here.  Examples:
+     3>results  perf stat --log-fd 3          -- $cmd
+     3>>results perf stat --log-fd 3 --append -- $cmd
+
+--pre::
+--post::
+	Pre and post measurement hooks, e.g.:
+
+perf stat --repeat 10 --null --sync --pre 'make -s O=defconfig-build/clean' -- make -s -j64 O=defconfig-build/ bzImage
+
+-I msecs::
+--interval-print msecs::
+	Print count deltas every N milliseconds (minimum: 100ms)
+	example: perf stat -I 1000 -e cycles -a sleep 5
+
+--per-socket::
+Aggregate counts per processor socket for system-wide mode measurements.  This
+is a useful mode to detect imbalance between sockets.  To enable this mode,
+use --per-socket in addition to -a. (system-wide).  The output includes the
+socket number and the number of online processors on that socket. This is
+useful to gauge the amount of aggregation.
+
+--per-core::
+Aggregate counts per physical processor for system-wide mode measurements.  This
+is a useful mode to detect imbalance between physical cores.  To enable this mode,
+use --per-core in addition to -a. (system-wide).  The output includes the
+core number and the number of online logical processors on that physical processor.
+
+-D msecs::
+--delay msecs::
+After starting the program, wait msecs before measuring. This is useful to
+filter out the startup phase of the program, which is often very different.
+
+-T::
+--transaction::
+
+Print statistics of transactional execution if supported.
+
 EXAMPLES
 --------
 
diff --git a/tools/perf/Documentation/perf-test.txt b/tools/perf/Documentation/perf-test.txt
index 1c4b5f5b7f7..d1d3e5121f8 100644
--- a/tools/perf/Documentation/perf-test.txt
+++ b/tools/perf/Documentation/perf-test.txt
@@ -8,15 +8,25 @@ perf-test - Runs sanity tests.
 SYNOPSIS
 --------
 [verse]
-'perf test <options>'
+'perf test [<options>] [{list <test-name-fragment>|[<test-name-fragments>|<test-numbers>]}]'
 
 DESCRIPTION
 -----------
-This command does assorted sanity tests, initially thru linked routines but
+This command does assorted sanity tests, initially through linked routines but
 also will look for a directory with more tests in the form of scripts.
 
+To get a list of available tests use 'perf test list', specifying a test name
+fragment will show all tests that have it.
+
+To run just specific tests, inform test name fragments or the numbers obtained
+from 'perf test list'.
+
 OPTIONS
 -------
+-s::
+--skip::
+	Tests to skip (comma separater numeric list).
+
 -v::
 --verbose::
 	Be more verbose.
diff --git a/tools/perf/Documentation/perf-timechart.txt b/tools/perf/Documentation/perf-timechart.txt
index 4b1788355ec..5e0f986dff3 100644
--- a/tools/perf/Documentation/perf-timechart.txt
+++ b/tools/perf/Documentation/perf-timechart.txt
@@ -8,7 +8,7 @@ perf-timechart - Tool to visualize total system behavior during a workload
 SYNOPSIS
 --------
 [verse]
-'perf timechart' {record}
+'perf timechart' [<timechart options>] {record} [<record options>]
 
 DESCRIPTION
 -----------
@@ -20,24 +20,72 @@ There are two variants of perf timechart:
   'perf timechart' to turn a trace into a Scalable Vector Graphics file,
   that can be viewed with popular SVG viewers such as 'Inkscape'.
 
-OPTIONS
--------
+TIMECHART OPTIONS
+-----------------
 -o::
 --output=::
         Select the output file (default: output.svg)
 -i::
 --input=::
-        Select the input file (default: perf.data)
+        Select the input file (default: perf.data unless stdin is a fifo)
 -w::
 --width=::
         Select the width of the SVG file (default: 1000)
 -P::
 --power-only::
         Only output the CPU power section of the diagram
+-T::
+--tasks-only::
+        Don't output processor state transitions
 -p::
 --process::
         Select the processes to display, by name or PID
 
+--symfs=<directory>::
+        Look for files with symbols relative to this directory.
+-n::
+--proc-num::
+        Print task info for at least given number of tasks.
+-t::
+--topology::
+        Sort CPUs according to topology.
+--highlight=<duration_nsecs|task_name>::
+	Highlight tasks (using different color) that run more than given
+	duration or tasks with given name. If number is given it's interpreted
+	as number of nanoseconds. If non-numeric string is given it's
+	interpreted as task name.
+
+RECORD OPTIONS
+--------------
+-P::
+--power-only::
+        Record only power-related events
+-T::
+--tasks-only::
+        Record only tasks-related events
+-g::
+--callchain::
+        Do call-graph (stack chain/backtrace) recording
+
+EXAMPLES
+--------
+
+$ perf timechart record git pull
+
+  [ perf record: Woken up 13 times to write data ]
+  [ perf record: Captured and wrote 4.253 MB perf.data (~185801 samples) ]
+
+$ perf timechart
+
+  Written 10.2 seconds of trace to output.svg.
+
+Record system-wide timechart:
+
+  $ perf timechart record
+
+  then generate timechart and highlight 'gcc' tasks:
+
+  $ perf timechart --highlight gcc
 
 SEE ALSO
 --------
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 785b9fc32a4..180ae02137a 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -12,7 +12,7 @@ SYNOPSIS
 
 DESCRIPTION
 -----------
-This command generates and displays a performance counter profile in realtime.
+This command generates and displays a performance counter profile in real time.
 
 
 OPTIONS
@@ -25,9 +25,11 @@ OPTIONS
 --count=<count>::
 	Event period to sample.
 
--C <cpu>::
---CPU=<cpu>::
-	CPU to profile.
+-C <cpu-list>::
+--cpu=<cpu>::
+Monitor only on the list of CPUs provided. Multiple CPUs can be provided as a
+comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2.
+Default is to monitor all CPUS.
 
 -d <seconds>::
 --delay=<seconds>::
@@ -48,13 +50,16 @@ OPTIONS
 --count-filter=<count>::
 	Only display functions with more events than this.
 
+--group::
+        Put the counters into a counter group.
+
 -F <freq>::
 --freq=<freq>::
 	Profile at this frequency.
 
 -i::
 --inherit::
-	Child tasks inherit counters, only makes sens with -p option.
+	Child tasks do not inherit counters.
 
 -k <path>::
 --vmlinux=<path>::
@@ -62,20 +67,41 @@ OPTIONS
 
 -m <pages>::
 --mmap-pages=<pages>::
-	Number of mmapped data pages.
+	Number of mmap data pages (must be a power of two) or size
+	specification with appended unit character - B/K/M/G. The
+	size is rounded up to have nearest pages power of two value.
 
 -p <pid>::
 --pid=<pid>::
-	Profile events on existing pid.
+	Profile events on existing Process ID (comma separated list).
+
+-t <tid>::
+--tid=<tid>::
+        Profile events on existing thread ID (comma separated list).
+
+-u::
+--uid=::
+        Record events in threads owned by uid. Name or number.
 
 -r <priority>::
 --realtime=<priority>::
 	Collect data with this RT SCHED_FIFO priority.
 
--s <symbol>::
 --sym-annotate=<symbol>::
         Annotate this symbol.
 
+-K::
+--hide_kernel_symbols::
+        Hide kernel symbols.
+
+-U::
+--hide_user_symbols::
+        Hide user symbols.
+
+-D::
+--dump-symtab::
+        Dump the symbol table used for profiling.
+
 -v::
 --verbose::
 	Be more verbose (show counter open errors, etc).
@@ -84,6 +110,89 @@ OPTIONS
 --zero::
 	Zero history across display updates.
 
+-s::
+--sort::
+	Sort by key(s): pid, comm, dso, symbol, parent, srcline, weight,
+	local_weight, abort, in_tx, transaction, overhead, sample, period.
+	Please see description of --sort in the perf-report man page.
+
+--fields=::
+	Specify output field - multiple keys can be specified in CSV format.
+	Following fields are available:
+	overhead, overhead_sys, overhead_us, overhead_children, sample and period.
+	Also it can contain any sort key(s).
+
+	By default, every sort keys not specified in --field will be appended
+	automatically.
+
+-n::
+--show-nr-samples::
+	Show a column with the number of samples.
+
+--show-total-period::
+	Show a column with the sum of periods.
+
+--dsos::
+	Only consider symbols in these dsos.  This option will affect the
+	percentage of the overhead column.  See --percentage for more info.
+
+--comms::
+	Only consider symbols in these comms.  This option will affect the
+	percentage of the overhead column.  See --percentage for more info.
+
+--symbols::
+	Only consider these symbols.  This option will affect the
+	percentage of the overhead column.  See --percentage for more info.
+
+-M::
+--disassembler-style=:: Set disassembler style for objdump.
+
+--source::
+	Interleave source code with assembly code. Enabled by default,
+	disable with --no-source.
+
+--asm-raw::
+	Show raw instruction encoding of assembly instructions.
+
+-g::
+	Enables call-graph (stack chain/backtrace) recording.
+
+--call-graph::
+	Setup and enable call-graph (stack chain/backtrace) recording,
+	implies -g.
+
+--children::
+	Accumulate callchain of children to parent entry so that then can
+	show up in the output.  The output will have a new "Children" column
+	and will be sorted on the data.  It requires -g/--call-graph option
+	enabled.
+
+--max-stack::
+	Set the stack depth limit when parsing the callchain, anything
+	beyond the specified depth will be ignored. This is a trade-off
+	between information loss and faster processing especially for
+	workloads that can have a very long callchain stack.
+
+	Default: 127
+
+--ignore-callees=<regex>::
+        Ignore callees of the function(s) matching the given regex.
+        This has the effect of collecting the callers of each such
+        function into one place in the call-graph tree.
+
+--percent-limit::
+	Do not show entries which have an overhead under that percent.
+	(Default: 0).
+
+--percentage::
+	Determine how to display the overhead percentage of filtered entries.
+	Filters can be applied by --comms, --dsos and/or --symbols options and
+	Zoom operations on the TUI (thread, dso, etc).
+
+	"relative" means it's relative to filtered entries only so that the
+	sum of shown entries will be always 100%. "absolute" means it retains
+	the original value before and after the filter is applied.
+
 INTERACTIVE PROMPTING KEYS
 --------------------------
 
@@ -108,9 +217,6 @@ INTERACTIVE PROMPTING KEYS
 [S]::
 	Stop annotation, return to full profile display.
 
-[w]::
-	Toggle between weighted sum and individual count[E]r profile.
-
 [z]::
 	Toggle event count zeroing across display updates.
 
@@ -122,4 +228,4 @@ Pressing any unmapped key displays a menu, and prompts for input.
 
 SEE ALSO
 --------
-linkperf:perf-stat[1], linkperf:perf-list[1]
+linkperf:perf-stat[1], linkperf:perf-list[1], linkperf:perf-report[1]
diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index 122ec9dc485..fae38d9a44a 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -3,68 +3,110 @@ perf-trace(1)
 
 NAME
 ----
-perf-trace - Read perf.data (created by perf record) and display trace output
+perf-trace - strace inspired tool
 
 SYNOPSIS
 --------
 [verse]
-'perf trace' {record <script> | report <script> [args] }
+'perf trace'
+'perf trace record'
 
 DESCRIPTION
 -----------
-This command reads the input file and displays the trace recorded.
+This command will show the events associated with the target, initially
+syscalls, but other system events like pagefaults, task lifetime events,
+scheduling events, etc.
 
-There are several variants of perf trace:
+This is a live mode tool in addition to working with perf.data files like
+the other perf tools. Files can be generated using the 'perf record' command
+but the session needs to include the raw_syscalls events (-e 'raw_syscalls:*').
+Alernatively, the 'perf trace record' can be used as a shortcut to
+automatically include the raw_syscalls events when writing events to a file.
 
-  'perf trace' to see a detailed trace of the workload that was
-  recorded.
+The following options apply to perf trace; options to perf trace record are
+found in the perf record man page.
 
-  You can also run a set of pre-canned scripts that aggregate and
-  summarize the raw trace data in various ways (the list of scripts is
-  available via 'perf trace -l').  The following variants allow you to
-  record and run those scripts:
+OPTIONS
+-------
 
-  'perf trace record <script>' to record the events required for 'perf
-  trace report'.  <script> is the name displayed in the output of
-  'perf trace --list' i.e. the actual script name minus any language
-  extension.
+-a::
+--all-cpus::
+        System-wide collection from all CPUs.
 
-  'perf trace report <script>' to run and display the results of
-  <script>.  <script> is the name displayed in the output of 'perf
-  trace --list' i.e. the actual script name minus any language
-  extension.  The perf.data output from a previous run of 'perf trace
-  record <script>' is used and should be present for this command to
-  succeed.
+-e::
+--expr::
+	List of events to show, currently only syscall names.
+	Prefixing with ! shows all syscalls but the ones specified.  You may
+	need to escape it.
 
-  See the 'SEE ALSO' section for links to language-specific
-  information on how to write and run your own trace scripts.
+-o::
+--output=::
+	Output file name.
 
-OPTIONS
--------
--D::
---dump-raw-trace=::
-        Display verbose dump of the trace data.
+-p::
+--pid=::
+	Record events on existing process ID (comma separated list).
+
+-t::
+--tid=::
+        Record events on existing thread ID (comma separated list).
+
+-u::
+--uid=::
+        Record events in threads owned by uid. Name or number.
+
+-v::
+--verbose=::
+        Verbosity level.
+
+-i::
+--no-inherit::
+	Child tasks do not inherit counters.
+
+-m::
+--mmap-pages=::
+	Number of mmap data pages (must be a power of two) or size
+	specification with appended unit character - B/K/M/G. The
+	size is rounded up to have nearest pages power of two value.
+
+-C::
+--cpu::
+Collect samples only on the list of CPUs provided. Multiple CPUs can be provided as a
+comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2.
+In per-thread mode with inheritance mode on (default), Events are captured only when
+the thread executes on the designated CPUs. Default is to monitor all CPUs.
+
+--duration:
+	Show only events that had a duration greater than N.M ms.
+
+--sched:
+	Accrue thread runtime and provide a summary at the end of the session.
+
+-i
+--input
+	Process events from a given perf data file.
+
+-T
+--time
+	Print full timestamp rather time relative to first sample.
 
--L::
---Latency=::
-        Show latency attributes (irqs/preemption disabled, etc).
+--comm::
+        Show process COMM right beside its ID, on by default, disable with --no-comm.
 
--l::
---list=::
-        Display a list of available trace scripts.
+-s::
+--summary::
+	Show only a summary of syscalls by thread with min, max, and average times
+    (in msec) and relative stddev.
 
--s ['lang']::
---script=::
-        Process trace data with the given script ([lang]:script[.ext]).
-	If the string 'lang' is specified in place of a script name, a
-        list of supported languages will be displayed instead.
+-S::
+--with-summary::
+	Show all syscalls followed by a summary by thread with min, max, and
+    average times (in msec) and relative stddev.
 
--g::
---gen-script=::
-        Generate perf-trace.[ext] starter script for given language,
-        using current perf.data.
+--tool_stats::
+	Show tool stats such as number of times fd->pathname was discovered thru
+	hooking the open syscall return + vfs_getname or via reading /proc/pid/fd, etc.
 
 SEE ALSO
 --------
-linkperf:perf-record[1], linkperf:perf-trace-perl[1],
-linkperf:perf-trace-python[1]
+linkperf:perf-record[1], linkperf:perf-script[1]
diff --git a/tools/perf/Documentation/perfconfig.example b/tools/perf/Documentation/perfconfig.example
new file mode 100644
index 00000000000..767ea2436e1
--- /dev/null
+++ b/tools/perf/Documentation/perfconfig.example
@@ -0,0 +1,29 @@
+[colors]
+
+	# These were the old defaults
+	top = red, lightgray
+	medium = green, lightgray
+	normal = black, lightgray
+	selected = lightgray, magenta
+	code = blue, lightgray
+	addr = magenta, lightgray
+
+[tui]
+
+	# Defaults if linked with libslang
+	report = on
+	annotate = on
+	top = on
+
+[buildid]
+
+	# Default, disable using /dev/null
+	dir = /root/.debug
+
+[annotate]
+
+	# Defaults
+	hide_src_code = false
+	use_offset = true
+	jump_arrows = true
+	show_nr_jumps = false
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
new file mode 100644
index 00000000000..45da209b6ed
--- /dev/null
+++ b/tools/perf/MANIFEST
@@ -0,0 +1,39 @@
+tools/perf
+tools/scripts
+tools/lib/traceevent
+tools/lib/api
+tools/lib/symbol/kallsyms.c
+tools/lib/symbol/kallsyms.h
+tools/include/asm/bug.h
+tools/include/linux/compiler.h
+tools/include/linux/hash.h
+tools/include/linux/export.h
+tools/include/linux/types.h
+include/linux/const.h
+include/linux/perf_event.h
+include/linux/rbtree.h
+include/linux/list.h
+include/linux/hash.h
+include/linux/stringify.h
+lib/rbtree.c
+include/linux/swab.h
+arch/*/include/asm/unistd*.h
+arch/*/include/asm/perf_regs.h
+arch/*/include/uapi/asm/unistd*.h
+arch/*/include/uapi/asm/perf_regs.h
+arch/*/lib/memcpy*.S
+arch/*/lib/memset*.S
+include/linux/poison.h
+include/linux/magic.h
+include/linux/hw_breakpoint.h
+include/linux/rbtree_augmented.h
+include/uapi/linux/perf_event.h
+include/uapi/linux/const.h
+include/uapi/linux/swab.h
+include/uapi/linux/hw_breakpoint.h
+arch/x86/include/asm/svm.h
+arch/x86/include/asm/vmx.h
+arch/x86/include/asm/kvm_host.h
+arch/x86/include/uapi/asm/svm.h
+arch/x86/include/uapi/asm/vmx.h
+arch/x86/include/uapi/asm/kvm.h
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 3d8f31ed771..cb2e5868c8e 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -1,1233 +1,90 @@
-ifeq ("$(origin O)", "command line")
-	OUTPUT := $(O)/
-endif
-
-# The default target of this Makefile is...
-all::
-
-# Define V=1 to have a more verbose compile.
-# Define V=2 to have an even more verbose compile.
-#
-# Define SNPRINTF_RETURNS_BOGUS if your are on a system which snprintf()
-# or vsnprintf() return -1 instead of number of characters which would
-# have been written to the final string if enough space had been available.
-#
-# Define FREAD_READS_DIRECTORIES if your are on a system which succeeds
-# when attempting to read from an fopen'ed directory.
-#
-# Define NO_OPENSSL environment variable if you do not have OpenSSL.
-# This also implies MOZILLA_SHA1.
-#
-# Define CURLDIR=/foo/bar if your curl header and library files are in
-# /foo/bar/include and /foo/bar/lib directories.
-#
-# Define EXPATDIR=/foo/bar if your expat header and library files are in
-# /foo/bar/include and /foo/bar/lib directories.
-#
-# Define NO_D_INO_IN_DIRENT if you don't have d_ino in your struct dirent.
-#
-# Define NO_D_TYPE_IN_DIRENT if your platform defines DT_UNKNOWN but lacks
-# d_type in struct dirent (latest Cygwin -- will be fixed soonish).
-#
-# Define NO_C99_FORMAT if your formatted IO functions (printf/scanf et.al.)
-# do not support the 'size specifiers' introduced by C99, namely ll, hh,
-# j, z, t. (representing long long int, char, intmax_t, size_t, ptrdiff_t).
-# some C compilers supported these specifiers prior to C99 as an extension.
-#
-# Define NO_STRCASESTR if you don't have strcasestr.
-#
-# Define NO_MEMMEM if you don't have memmem.
-#
-# Define NO_STRTOUMAX if you don't have strtoumax in the C library.
-# If your compiler also does not support long long or does not have
-# strtoull, define NO_STRTOULL.
-#
-# Define NO_SETENV if you don't have setenv in the C library.
-#
-# Define NO_UNSETENV if you don't have unsetenv in the C library.
-#
-# Define NO_MKDTEMP if you don't have mkdtemp in the C library.
-#
-# Define NO_SYS_SELECT_H if you don't have sys/select.h.
-#
-# Define NO_SYMLINK_HEAD if you never want .perf/HEAD to be a symbolic link.
-# Enable it on Windows.  By default, symrefs are still used.
-#
-# Define NO_SVN_TESTS if you want to skip time-consuming SVN interoperability
-# tests.  These tests take up a significant amount of the total test time
-# but are not needed unless you plan to talk to SVN repos.
-#
-# Define NO_FINK if you are building on Darwin/Mac OS X, have Fink
-# installed in /sw, but don't want PERF to link against any libraries
-# installed there.  If defined you may specify your own (or Fink's)
-# include directories and library directories by defining CFLAGS
-# and LDFLAGS appropriately.
-#
-# Define NO_DARWIN_PORTS if you are building on Darwin/Mac OS X,
-# have DarwinPorts installed in /opt/local, but don't want PERF to
-# link against any libraries installed there.  If defined you may
-# specify your own (or DarwinPort's) include directories and
-# library directories by defining CFLAGS and LDFLAGS appropriately.
-#
-# Define PPC_SHA1 environment variable when running make to make use of
-# a bundled SHA1 routine optimized for PowerPC.
-#
-# Define ARM_SHA1 environment variable when running make to make use of
-# a bundled SHA1 routine optimized for ARM.
-#
-# Define MOZILLA_SHA1 environment variable when running make to make use of
-# a bundled SHA1 routine coming from Mozilla. It is GPL'd and should be fast
-# on non-x86 architectures (e.g. PowerPC), while the OpenSSL version (default
-# choice) has very fast version optimized for i586.
-#
-# Define NEEDS_SSL_WITH_CRYPTO if you need -lcrypto with -lssl (Darwin).
-#
-# Define NEEDS_LIBICONV if linking with libc is not enough (Darwin).
-#
-# Define NEEDS_SOCKET if linking with libc is not enough (SunOS,
-# Patrick Mauritz).
-#
-# Define NO_MMAP if you want to avoid mmap.
-#
-# Define NO_PTHREADS if you do not have or do not want to use Pthreads.
-#
-# Define NO_PREAD if you have a problem with pread() system call (e.g.
-# cygwin.dll before v1.5.22).
-#
-# Define NO_FAST_WORKING_DIRECTORY if accessing objects in pack files is
-# generally faster on your platform than accessing the working directory.
-#
-# Define NO_TRUSTABLE_FILEMODE if your filesystem may claim to support
-# the executable mode bit, but doesn't really do so.
-#
-# Define NO_IPV6 if you lack IPv6 support and getaddrinfo().
-#
-# Define NO_SOCKADDR_STORAGE if your platform does not have struct
-# sockaddr_storage.
-#
-# Define NO_ICONV if your libc does not properly support iconv.
-#
-# Define OLD_ICONV if your library has an old iconv(), where the second
-# (input buffer pointer) parameter is declared with type (const char **).
 #
-# Define NO_DEFLATE_BOUND if your zlib does not have deflateBound.
+# This is a simple wrapper Makefile that calls the main Makefile.perf
+# with a -j option to do parallel builds
 #
-# Define NO_R_TO_GCC_LINKER if your gcc does not like "-R/path/lib"
-# that tells runtime paths to dynamic libraries;
-# "-Wl,-rpath=/path/lib" is used instead.
+# If you want to invoke the perf build in some non-standard way then
+# you can use the 'make -f Makefile.perf' method to invoke it.
 #
-# Define USE_NSEC below if you want perf to care about sub-second file mtimes
-# and ctimes. Note that you need recent glibc (at least 2.2.4) for this, and
-# it will BREAK YOUR LOCAL DIFFS! show-diff and anything using it will likely
-# randomly break unless your underlying filesystem supports those sub-second
-# times (my ext3 doesn't).
-#
-# Define USE_ST_TIMESPEC if your "struct stat" uses "st_ctimespec" instead of
-# "st_ctim"
-#
-# Define NO_NSEC if your "struct stat" does not have "st_ctim.tv_nsec"
-# available.  This automatically turns USE_NSEC off.
-#
-# Define USE_STDEV below if you want perf to care about the underlying device
-# change being considered an inode change from the update-index perspective.
-#
-# Define NO_ST_BLOCKS_IN_STRUCT_STAT if your platform does not have st_blocks
-# field that counts the on-disk footprint in 512-byte blocks.
-#
-# Define ASCIIDOC8 if you want to format documentation with AsciiDoc 8
-#
-# Define DOCBOOK_XSL_172 if you want to format man pages with DocBook XSL v1.72.
-#
-# Define NO_PERL_MAKEMAKER if you cannot use Makefiles generated by perl's
-# MakeMaker (e.g. using ActiveState under Cygwin).
-#
-# Define NO_PERL if you do not want Perl scripts or libraries at all.
-#
-# Define INTERNAL_QSORT to use Git's implementation of qsort(), which
-# is a simplified version of the merge sort used in glibc. This is
-# recommended if Git triggers O(n^2) behavior in your platform's qsort().
-#
-# Define NO_EXTERNAL_GREP if you don't want "perf grep" to ever call
-# your external grep (e.g., if your system lacks grep, if its grep is
-# broken, or spawning external process is slower than built-in grep perf has).
-#
-# Define LDFLAGS=-static to build a static binary.
-#
-# Define EXTRA_CFLAGS=-m64 or EXTRA_CFLAGS=-m32 as appropriate for cross-builds.
-#
-# Define NO_DWARF if you do not want debug-info analysis feature at all.
-
-$(shell sh -c 'mkdir -p $(OUTPUT)scripts/python/Perf-Trace-Util/' 2> /dev/null)
-$(shell sh -c 'mkdir -p $(OUTPUT)scripts/perl/Perf-Trace-Util/' 2> /dev/null)
-$(shell sh -c 'mkdir -p $(OUTPUT)util/scripting-engines/' 2> /dev/null)
-$(shell sh -c 'mkdir $(OUTPUT)bench' 2> /dev/null)
-
-$(OUTPUT)PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE
-	@$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT)
--include $(OUTPUT)PERF-VERSION-FILE
-
-uname_S := $(shell sh -c 'uname -s 2>/dev/null || echo not')
-uname_M := $(shell sh -c 'uname -m 2>/dev/null || echo not')
-uname_O := $(shell sh -c 'uname -o 2>/dev/null || echo not')
-uname_R := $(shell sh -c 'uname -r 2>/dev/null || echo not')
-uname_P := $(shell sh -c 'uname -p 2>/dev/null || echo not')
-uname_V := $(shell sh -c 'uname -v 2>/dev/null || echo not')
-
-ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \
-				  -e s/arm.*/arm/ -e s/sa110/arm/ \
-				  -e s/s390x/s390/ -e s/parisc64/parisc/ \
-				  -e s/ppc.*/powerpc/ -e s/mips.*/mips/ \
-				  -e s/sh[234].*/sh/ )
-
-# Additional ARCH settings for x86
-ifeq ($(ARCH),i386)
-        ARCH := x86
-endif
-ifeq ($(ARCH),x86_64)
-        ARCH := x86
-endif
-
-$(shell sh -c 'mkdir -p $(OUTPUT)arch/$(ARCH)/util/' 2> /dev/null)
-
-# CFLAGS and LDFLAGS are for the users to override from the command line.
 
 #
-# Include saner warnings here, which can catch bugs:
+# Clear out the built-in rules GNU make defines by default (such as .o targets),
+# so that we pass through all targets to Makefile.perf:
 #
-
-EXTRA_WARNINGS := -Wformat
-EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wformat-security
-EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wformat-y2k
-EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wshadow
-EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Winit-self
-EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wpacked
-EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wredundant-decls
-EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wstack-protector
-EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wstrict-aliasing=3
-EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wswitch-default
-EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wswitch-enum
-EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wno-system-headers
-EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wundef
-EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wvolatile-register-var
-EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wwrite-strings
-EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wbad-function-cast
-EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wmissing-declarations
-EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wmissing-prototypes
-EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wnested-externs
-EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wold-style-definition
-EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wstrict-prototypes
-EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wdeclaration-after-statement
-
-ifeq ("$(origin DEBUG)", "command line")
-  PERF_DEBUG = $(DEBUG)
-endif
-ifndef PERF_DEBUG
-  CFLAGS_OPTIMIZE = -O6
-endif
-
-CFLAGS = -ggdb3 -Wall -Wextra -std=gnu99 -Werror $(CFLAGS_OPTIMIZE) -D_FORTIFY_SOURCE=2 $(EXTRA_WARNINGS) $(EXTRA_CFLAGS)
-EXTLIBS = -lpthread -lrt -lelf -lm
-ALL_CFLAGS = $(CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64
-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
-
-export prefix bindir sharedir sysconfdir
-
-CC = $(CROSS_COMPILE)gcc
-AR = $(CROSS_COMPILE)ar
-RM = rm -f
-TAR = tar
-FIND = find
-INSTALL = install
-RPMBUILD = rpmbuild
-PTHREAD_LIBS = -lpthread
-
-# sparse is architecture-neutral, which means that we need to tell it
-# explicitly what architecture to check for. Fix this up for yours..
-SPARSE_FLAGS = -D__BIG_ENDIAN__ -D__powerpc__
-
-ifeq ($(V), 2)
-	QUIET_STDERR = ">/dev/null"
-else
-	QUIET_STDERR = ">/dev/null 2>&1"
-endif
-
-BITBUCKET = "/dev/null"
-
-ifneq ($(shell sh -c "(echo '\#include <stdio.h>'; echo 'int main(void) { return puts(\"hi\"); }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) "$(QUIET_STDERR)" && echo y"), y)
-	BITBUCKET = .perf.dev.null
-endif
-
-ifeq ($(shell sh -c "echo 'int foo(void) {char X[2]; return 3;}' | $(CC) -x c -c -Werror -fstack-protector-all - -o $(BITBUCKET) "$(QUIET_STDERR)" && echo y"), y)
-  CFLAGS := $(CFLAGS) -fstack-protector-all
-endif
-
-
-### --- END CONFIGURATION SECTION ---
-
-# Those must not be GNU-specific; they are shared with perl/ which may
-# be built by a different compiler. (Note that this is an artifact now
-# but it still might be nice to keep that distinction.)
-BASIC_CFLAGS = -Iutil/include -Iarch/$(ARCH)/include
-BASIC_LDFLAGS =
-
-# Guard against environment variables
-BUILTIN_OBJS =
-BUILT_INS =
-COMPAT_CFLAGS =
-COMPAT_OBJS =
-LIB_H =
-LIB_OBJS =
-SCRIPT_PERL =
-SCRIPT_SH =
-TEST_PROGRAMS =
-
-SCRIPT_SH += perf-archive.sh
+.SUFFIXES:
 
 #
-# No Perl scripts right now:
+# We don't want to pass along options like -j:
 #
-
-# SCRIPT_PERL += perf-add--interactive.perl
-
-SCRIPTS = $(patsubst %.sh,%,$(SCRIPT_SH)) \
-	  $(patsubst %.perl,%,$(SCRIPT_PERL))
-
-# Empty...
-EXTRA_PROGRAMS =
-
-# ... and all the rest that could be moved out of bindir to perfexecdir
-PROGRAMS += $(EXTRA_PROGRAMS)
+unexport MAKEFLAGS
 
 #
-# Single 'perf' binary right now:
+# Do a parallel build with multiple jobs, based on the number of CPUs online
+# in this system: 'make -j8' on a 8-CPU system, etc.
 #
-PROGRAMS += $(OUTPUT)perf
-
-# List built-in command $C whose implementation cmd_$C() is not in
-# builtin-$C.o but is linked in as part of some other command.
+# (To override it, run 'make JOBS=1' and similar.)
 #
-
-# what 'all' will build and 'install' will install, in perfexecdir
-ALL_PROGRAMS = $(PROGRAMS) $(SCRIPTS)
-
-# what 'all' will build but not install in perfexecdir
-OTHER_PROGRAMS = $(OUTPUT)perf$X
-
-# Set paths to tools early so that they can be used for version tests.
-ifndef SHELL_PATH
-	SHELL_PATH = /bin/sh
-endif
-ifndef PERL_PATH
-	PERL_PATH = /usr/bin/perl
+ifeq ($(JOBS),)
+  JOBS := $(shell grep -c ^processor /proc/cpuinfo 2>/dev/null)
+  ifeq ($(JOBS),)
+    JOBS := 1
+  endif
 endif
 
-export PERL_PATH
-
-LIB_FILE=$(OUTPUT)libperf.a
-
-LIB_H += ../../include/linux/perf_event.h
-LIB_H += ../../include/linux/rbtree.h
-LIB_H += ../../include/linux/list.h
-LIB_H += ../../include/linux/hash.h
-LIB_H += ../../include/linux/stringify.h
-LIB_H += util/include/linux/bitmap.h
-LIB_H += util/include/linux/bitops.h
-LIB_H += util/include/linux/compiler.h
-LIB_H += util/include/linux/ctype.h
-LIB_H += util/include/linux/kernel.h
-LIB_H += util/include/linux/list.h
-LIB_H += util/include/linux/module.h
-LIB_H += util/include/linux/poison.h
-LIB_H += util/include/linux/prefetch.h
-LIB_H += util/include/linux/rbtree.h
-LIB_H += util/include/linux/string.h
-LIB_H += util/include/linux/types.h
-LIB_H += util/include/asm/asm-offsets.h
-LIB_H += util/include/asm/bug.h
-LIB_H += util/include/asm/byteorder.h
-LIB_H += util/include/asm/hweight.h
-LIB_H += util/include/asm/swab.h
-LIB_H += util/include/asm/system.h
-LIB_H += util/include/asm/uaccess.h
-LIB_H += util/include/dwarf-regs.h
-LIB_H += perf.h
-LIB_H += util/cache.h
-LIB_H += util/callchain.h
-LIB_H += util/build-id.h
-LIB_H += util/debug.h
-LIB_H += util/debugfs.h
-LIB_H += util/event.h
-LIB_H += util/exec_cmd.h
-LIB_H += util/types.h
-LIB_H += util/levenshtein.h
-LIB_H += util/map.h
-LIB_H += util/parse-options.h
-LIB_H += util/parse-events.h
-LIB_H += util/quote.h
-LIB_H += util/util.h
-LIB_H += util/header.h
-LIB_H += util/help.h
-LIB_H += util/session.h
-LIB_H += util/strbuf.h
-LIB_H += util/strlist.h
-LIB_H += util/svghelper.h
-LIB_H += util/run-command.h
-LIB_H += util/sigchain.h
-LIB_H += util/symbol.h
-LIB_H += util/color.h
-LIB_H += util/values.h
-LIB_H += util/sort.h
-LIB_H += util/hist.h
-LIB_H += util/thread.h
-LIB_H += util/trace-event.h
-LIB_H += util/probe-finder.h
-LIB_H += util/probe-event.h
-LIB_H += util/pstack.h
-LIB_H += util/cpumap.h
-
-LIB_OBJS += $(OUTPUT)util/abspath.o
-LIB_OBJS += $(OUTPUT)util/alias.o
-LIB_OBJS += $(OUTPUT)util/build-id.o
-LIB_OBJS += $(OUTPUT)util/config.o
-LIB_OBJS += $(OUTPUT)util/ctype.o
-LIB_OBJS += $(OUTPUT)util/debugfs.o
-LIB_OBJS += $(OUTPUT)util/environment.o
-LIB_OBJS += $(OUTPUT)util/event.o
-LIB_OBJS += $(OUTPUT)util/exec_cmd.o
-LIB_OBJS += $(OUTPUT)util/help.o
-LIB_OBJS += $(OUTPUT)util/levenshtein.o
-LIB_OBJS += $(OUTPUT)util/parse-options.o
-LIB_OBJS += $(OUTPUT)util/parse-events.o
-LIB_OBJS += $(OUTPUT)util/path.o
-LIB_OBJS += $(OUTPUT)util/rbtree.o
-LIB_OBJS += $(OUTPUT)util/bitmap.o
-LIB_OBJS += $(OUTPUT)util/hweight.o
-LIB_OBJS += $(OUTPUT)util/run-command.o
-LIB_OBJS += $(OUTPUT)util/quote.o
-LIB_OBJS += $(OUTPUT)util/strbuf.o
-LIB_OBJS += $(OUTPUT)util/string.o
-LIB_OBJS += $(OUTPUT)util/strlist.o
-LIB_OBJS += $(OUTPUT)util/usage.o
-LIB_OBJS += $(OUTPUT)util/wrapper.o
-LIB_OBJS += $(OUTPUT)util/sigchain.o
-LIB_OBJS += $(OUTPUT)util/symbol.o
-LIB_OBJS += $(OUTPUT)util/color.o
-LIB_OBJS += $(OUTPUT)util/pager.o
-LIB_OBJS += $(OUTPUT)util/header.o
-LIB_OBJS += $(OUTPUT)util/callchain.o
-LIB_OBJS += $(OUTPUT)util/values.o
-LIB_OBJS += $(OUTPUT)util/debug.o
-LIB_OBJS += $(OUTPUT)util/map.o
-LIB_OBJS += $(OUTPUT)util/pstack.o
-LIB_OBJS += $(OUTPUT)util/session.o
-LIB_OBJS += $(OUTPUT)util/thread.o
-LIB_OBJS += $(OUTPUT)util/trace-event-parse.o
-LIB_OBJS += $(OUTPUT)util/trace-event-read.o
-LIB_OBJS += $(OUTPUT)util/trace-event-info.o
-LIB_OBJS += $(OUTPUT)util/trace-event-scripting.o
-LIB_OBJS += $(OUTPUT)util/svghelper.o
-LIB_OBJS += $(OUTPUT)util/sort.o
-LIB_OBJS += $(OUTPUT)util/hist.o
-LIB_OBJS += $(OUTPUT)util/probe-event.o
-LIB_OBJS += $(OUTPUT)util/util.o
-LIB_OBJS += $(OUTPUT)util/cpumap.o
-
-BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o
-
-BUILTIN_OBJS += $(OUTPUT)builtin-bench.o
-
-# Benchmark modules
-BUILTIN_OBJS += $(OUTPUT)bench/sched-messaging.o
-BUILTIN_OBJS += $(OUTPUT)bench/sched-pipe.o
-BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy.o
-
-BUILTIN_OBJS += $(OUTPUT)builtin-diff.o
-BUILTIN_OBJS += $(OUTPUT)builtin-help.o
-BUILTIN_OBJS += $(OUTPUT)builtin-sched.o
-BUILTIN_OBJS += $(OUTPUT)builtin-buildid-list.o
-BUILTIN_OBJS += $(OUTPUT)builtin-buildid-cache.o
-BUILTIN_OBJS += $(OUTPUT)builtin-list.o
-BUILTIN_OBJS += $(OUTPUT)builtin-record.o
-BUILTIN_OBJS += $(OUTPUT)builtin-report.o
-BUILTIN_OBJS += $(OUTPUT)builtin-stat.o
-BUILTIN_OBJS += $(OUTPUT)builtin-timechart.o
-BUILTIN_OBJS += $(OUTPUT)builtin-top.o
-BUILTIN_OBJS += $(OUTPUT)builtin-trace.o
-BUILTIN_OBJS += $(OUTPUT)builtin-probe.o
-BUILTIN_OBJS += $(OUTPUT)builtin-kmem.o
-BUILTIN_OBJS += $(OUTPUT)builtin-lock.o
-BUILTIN_OBJS += $(OUTPUT)builtin-kvm.o
-BUILTIN_OBJS += $(OUTPUT)builtin-test.o
-BUILTIN_OBJS += $(OUTPUT)builtin-inject.o
-
-PERFLIBS = $(LIB_FILE)
-
 #
-# Platform specific tweaks
+# Only pass canonical directory names as the output directory:
 #
-
-# We choose to avoid "if .. else if .. else .. endif endif"
-# because maintaining the nesting to match is a pain.  If
-# we had "elif" things would have been much nicer...
-
--include config.mak.autogen
--include config.mak
-
-ifndef NO_DWARF
-ifneq ($(shell sh -c "(echo '\#include <dwarf.h>'; echo '\#include <libdw.h>'; echo '\#include <version.h>'; echo '\#ifndef _ELFUTILS_PREREQ'; echo '\#error'; echo '\#endif'; echo 'int main(void) { Dwarf *dbg; dbg = dwarf_begin(0, DWARF_C_READ); return (long)dbg; }') | $(CC) -x c - $(ALL_CFLAGS) -I/usr/include/elfutils -ldw -lelf -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y)
-	msg := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev);
-	NO_DWARF := 1
-endif # Dwarf support
-endif # NO_DWARF
-
--include arch/$(ARCH)/Makefile
-
-ifeq ($(uname_S),Darwin)
-	ifndef NO_FINK
-		ifeq ($(shell test -d /sw/lib && echo y),y)
-			BASIC_CFLAGS += -I/sw/include
-			BASIC_LDFLAGS += -L/sw/lib
-		endif
-	endif
-	ifndef NO_DARWIN_PORTS
-		ifeq ($(shell test -d /opt/local/lib && echo y),y)
-			BASIC_CFLAGS += -I/opt/local/include
-			BASIC_LDFLAGS += -L/opt/local/lib
-		endif
-	endif
-	PTHREAD_LIBS =
+ifneq ($(O),)
+  FULL_O := $(shell readlink -f $(O) || echo $(O))
 endif
 
-ifneq ($(OUTPUT),)
-	BASIC_CFLAGS += -I$(OUTPUT)
-endif
-
-ifeq ($(shell sh -c "(echo '\#include <libelf.h>'; echo 'int main(void) { Elf * elf = elf_begin(0, ELF_C_READ, 0); return (long)elf; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y)
-ifneq ($(shell sh -c "(echo '\#include <gnu/libc-version.h>'; echo 'int main(void) { const char * version = gnu_get_libc_version(); return (long)version; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y)
-	msg := $(error No gnu/libc-version.h found, please install glibc-dev[el]/glibc-static);
-endif
-
-	ifneq ($(shell sh -c "(echo '\#include <libelf.h>'; echo 'int main(void) { Elf * elf = elf_begin(0, ELF_C_READ_MMAP, 0); return (long)elf; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y)
-		BASIC_CFLAGS += -DLIBELF_NO_MMAP
-	endif
-else
-	msg := $(error No libelf.h/libelf found, please install libelf-dev/elfutils-libelf-devel and glibc-dev[el]);
-endif
-
-ifndef NO_DWARF
-ifeq ($(origin PERF_HAVE_DWARF_REGS), undefined)
-	msg := $(warning DWARF register mappings have not been defined for architecture $(ARCH), DWARF support disabled);
-else
-	BASIC_CFLAGS += -I/usr/include/elfutils -DDWARF_SUPPORT
-	EXTLIBS += -lelf -ldw
-	LIB_OBJS += $(OUTPUT)util/probe-finder.o
-endif # PERF_HAVE_DWARF_REGS
-endif # NO_DWARF
-
-ifdef NO_NEWT
-	BASIC_CFLAGS += -DNO_NEWT_SUPPORT
-else
-ifneq ($(shell sh -c "(echo '\#include <newt.h>'; echo 'int main(void) { newtInit(); newtCls(); return newtFinished(); }') | $(CC) -x c - $(ALL_CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -lnewt -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y)
-	msg := $(warning newt not found, disables TUI support. Please install newt-devel or libnewt-dev);
-	BASIC_CFLAGS += -DNO_NEWT_SUPPORT
-else
-	# Fedora has /usr/include/slang/slang.h, but ubuntu /usr/include/slang.h
-	BASIC_CFLAGS += -I/usr/include/slang
-	EXTLIBS += -lnewt -lslang
-	LIB_OBJS += $(OUTPUT)util/newt.o
-endif
-endif # NO_NEWT
-
-ifndef NO_LIBPERL
-PERL_EMBED_LDOPTS = `perl -MExtUtils::Embed -e ldopts 2>/dev/null`
-PERL_EMBED_CCOPTS = `perl -MExtUtils::Embed -e ccopts 2>/dev/null`
-endif
-
-ifneq ($(shell sh -c "(echo '\#include <EXTERN.h>'; echo '\#include <perl.h>'; echo 'int main(void) { perl_alloc(); return 0; }') | $(CC) -x c - $(PERL_EMBED_CCOPTS) -o $(BITBUCKET) $(PERL_EMBED_LDOPTS) > /dev/null 2>&1 && echo y"), y)
-	BASIC_CFLAGS += -DNO_LIBPERL
-else
-	ALL_LDFLAGS += $(PERL_EMBED_LDOPTS)
-	LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-perl.o
-	LIB_OBJS += $(OUTPUT)scripts/perl/Perf-Trace-Util/Context.o
-endif
-
-ifndef NO_LIBPYTHON
-PYTHON_EMBED_LDOPTS = `python-config --ldflags 2>/dev/null`
-PYTHON_EMBED_CCOPTS = `python-config --cflags 2>/dev/null`
-endif
-
-ifneq ($(shell sh -c "(echo '\#include <Python.h>'; echo 'int main(void) { Py_Initialize(); return 0; }') | $(CC) -x c - $(PYTHON_EMBED_CCOPTS) -o $(BITBUCKET) $(PYTHON_EMBED_LDOPTS) > /dev/null 2>&1 && echo y"), y)
-	BASIC_CFLAGS += -DNO_LIBPYTHON
-else
-	ALL_LDFLAGS += $(PYTHON_EMBED_LDOPTS)
-	LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-python.o
-	LIB_OBJS += $(OUTPUT)scripts/python/Perf-Trace-Util/Context.o
-endif
-
-ifdef NO_DEMANGLE
-	BASIC_CFLAGS += -DNO_DEMANGLE
-else ifdef HAVE_CPLUS_DEMANGLE
-	EXTLIBS += -liberty
-	BASIC_CFLAGS += -DHAVE_CPLUS_DEMANGLE
-else
-	has_bfd := $(shell sh -c "(echo '\#include <bfd.h>'; echo 'int main(void) { bfd_demangle(0, 0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) -lbfd "$(QUIET_STDERR)" && echo y")
-
-	ifeq ($(has_bfd),y)
-		EXTLIBS += -lbfd
-	else
-		has_bfd_iberty := $(shell sh -c "(echo '\#include <bfd.h>'; echo 'int main(void) { bfd_demangle(0, 0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) -lbfd -liberty "$(QUIET_STDERR)" && echo y")
-		ifeq ($(has_bfd_iberty),y)
-			EXTLIBS += -lbfd -liberty
-		else
-			has_bfd_iberty_z := $(shell sh -c "(echo '\#include <bfd.h>'; echo 'int main(void) { bfd_demangle(0, 0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) -lbfd -liberty -lz "$(QUIET_STDERR)" && echo y")
-			ifeq ($(has_bfd_iberty_z),y)
-				EXTLIBS += -lbfd -liberty -lz
-			else
-				has_cplus_demangle := $(shell sh -c "(echo 'extern char *cplus_demangle(const char *, int);'; echo 'int main(void) { cplus_demangle(0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) -liberty "$(QUIET_STDERR)" && echo y")
-				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 CC_LD_DYNPATH
-	ifdef NO_R_TO_GCC_LINKER
-		# Some gcc does not accept and pass -R to the linker to specify
-		# the runtime dynamic library path.
-		CC_LD_DYNPATH = -Wl,-rpath,
-	else
-		CC_LD_DYNPATH = -R
-	endif
-endif
-
-ifdef NEEDS_SOCKET
-	EXTLIBS += -lsocket
-endif
-ifdef NEEDS_NSL
-	EXTLIBS += -lnsl
-endif
-ifdef NO_D_TYPE_IN_DIRENT
-	BASIC_CFLAGS += -DNO_D_TYPE_IN_DIRENT
-endif
-ifdef NO_D_INO_IN_DIRENT
-	BASIC_CFLAGS += -DNO_D_INO_IN_DIRENT
-endif
-ifdef NO_ST_BLOCKS_IN_STRUCT_STAT
-	BASIC_CFLAGS += -DNO_ST_BLOCKS_IN_STRUCT_STAT
-endif
-ifdef USE_NSEC
-	BASIC_CFLAGS += -DUSE_NSEC
-endif
-ifdef USE_ST_TIMESPEC
-	BASIC_CFLAGS += -DUSE_ST_TIMESPEC
-endif
-ifdef NO_NSEC
-	BASIC_CFLAGS += -DNO_NSEC
-endif
-ifdef NO_C99_FORMAT
-	BASIC_CFLAGS += -DNO_C99_FORMAT
-endif
-ifdef SNPRINTF_RETURNS_BOGUS
-	COMPAT_CFLAGS += -DSNPRINTF_RETURNS_BOGUS
-	COMPAT_OBJS += $(OUTPUT)compat/snprintf.o
-endif
-ifdef FREAD_READS_DIRECTORIES
-	COMPAT_CFLAGS += -DFREAD_READS_DIRECTORIES
-	COMPAT_OBJS += $(OUTPUT)compat/fopen.o
-endif
-ifdef NO_SYMLINK_HEAD
-	BASIC_CFLAGS += -DNO_SYMLINK_HEAD
-endif
-ifdef NO_STRCASESTR
-	COMPAT_CFLAGS += -DNO_STRCASESTR
-	COMPAT_OBJS += $(OUTPUT)compat/strcasestr.o
-endif
-ifdef NO_STRTOUMAX
-	COMPAT_CFLAGS += -DNO_STRTOUMAX
-	COMPAT_OBJS += $(OUTPUT)compat/strtoumax.o
-endif
-ifdef NO_STRTOULL
-	COMPAT_CFLAGS += -DNO_STRTOULL
-endif
-ifdef NO_SETENV
-	COMPAT_CFLAGS += -DNO_SETENV
-	COMPAT_OBJS += $(OUTPUT)compat/setenv.o
-endif
-ifdef NO_MKDTEMP
-	COMPAT_CFLAGS += -DNO_MKDTEMP
-	COMPAT_OBJS += $(OUTPUT)compat/mkdtemp.o
-endif
-ifdef NO_UNSETENV
-	COMPAT_CFLAGS += -DNO_UNSETENV
-	COMPAT_OBJS += $(OUTPUT)compat/unsetenv.o
-endif
-ifdef NO_SYS_SELECT_H
-	BASIC_CFLAGS += -DNO_SYS_SELECT_H
-endif
-ifdef NO_MMAP
-	COMPAT_CFLAGS += -DNO_MMAP
-	COMPAT_OBJS += $(OUTPUT)compat/mmap.o
-else
-	ifdef USE_WIN32_MMAP
-		COMPAT_CFLAGS += -DUSE_WIN32_MMAP
-		COMPAT_OBJS += $(OUTPUT)compat/win32mmap.o
-	endif
-endif
-ifdef NO_PREAD
-	COMPAT_CFLAGS += -DNO_PREAD
-	COMPAT_OBJS += $(OUTPUT)compat/pread.o
-endif
-ifdef NO_FAST_WORKING_DIRECTORY
-	BASIC_CFLAGS += -DNO_FAST_WORKING_DIRECTORY
-endif
-ifdef NO_TRUSTABLE_FILEMODE
-	BASIC_CFLAGS += -DNO_TRUSTABLE_FILEMODE
-endif
-ifdef NO_IPV6
-	BASIC_CFLAGS += -DNO_IPV6
-endif
-ifdef NO_UINTMAX_T
-	BASIC_CFLAGS += -Duintmax_t=uint32_t
-endif
-ifdef NO_SOCKADDR_STORAGE
-ifdef NO_IPV6
-	BASIC_CFLAGS += -Dsockaddr_storage=sockaddr_in
-else
-	BASIC_CFLAGS += -Dsockaddr_storage=sockaddr_in6
-endif
-endif
-ifdef NO_INET_NTOP
-	LIB_OBJS += $(OUTPUT)compat/inet_ntop.o
-endif
-ifdef NO_INET_PTON
-	LIB_OBJS += $(OUTPUT)compat/inet_pton.o
-endif
-
-ifdef NO_ICONV
-	BASIC_CFLAGS += -DNO_ICONV
-endif
-
-ifdef OLD_ICONV
-	BASIC_CFLAGS += -DOLD_ICONV
-endif
-
-ifdef NO_DEFLATE_BOUND
-	BASIC_CFLAGS += -DNO_DEFLATE_BOUND
-endif
-
-ifdef PPC_SHA1
-	SHA1_HEADER = "ppc/sha1.h"
-	LIB_OBJS += $(OUTPUT)ppc/sha1.o ppc/sha1ppc.o
-else
-ifdef ARM_SHA1
-	SHA1_HEADER = "arm/sha1.h"
-	LIB_OBJS += $(OUTPUT)arm/sha1.o $(OUTPUT)arm/sha1_arm.o
-else
-ifdef MOZILLA_SHA1
-	SHA1_HEADER = "mozilla-sha1/sha1.h"
-	LIB_OBJS += $(OUTPUT)mozilla-sha1/sha1.o
-else
-	SHA1_HEADER = <openssl/sha.h>
-	EXTLIBS += $(LIB_4_CRYPTO)
-endif
-endif
-endif
-ifdef NO_PERL_MAKEMAKER
-	export NO_PERL_MAKEMAKER
-endif
-ifdef NO_HSTRERROR
-	COMPAT_CFLAGS += -DNO_HSTRERROR
-	COMPAT_OBJS += $(OUTPUT)compat/hstrerror.o
-endif
-ifdef NO_MEMMEM
-	COMPAT_CFLAGS += -DNO_MEMMEM
-	COMPAT_OBJS += $(OUTPUT)compat/memmem.o
-endif
-ifdef INTERNAL_QSORT
-	COMPAT_CFLAGS += -DINTERNAL_QSORT
-	COMPAT_OBJS += $(OUTPUT)compat/qsort.o
-endif
-ifdef RUNTIME_PREFIX
-	COMPAT_CFLAGS += -DRUNTIME_PREFIX
-endif
-
-ifdef DIR_HAS_BSD_GROUP_SEMANTICS
-	COMPAT_CFLAGS += -DDIR_HAS_BSD_GROUP_SEMANTICS
-endif
-ifdef NO_EXTERNAL_GREP
-	BASIC_CFLAGS += -DNO_EXTERNAL_GREP
-endif
-
-ifeq ($(PERL_PATH),)
-NO_PERL=NoThanks
-endif
-
-QUIET_SUBDIR0  = +$(MAKE) -C # space to separate -C and subdir
-QUIET_SUBDIR1  =
-
-ifneq ($(findstring $(MAKEFLAGS),w),w)
-PRINT_DIR = --no-print-directory
-else # "make -w"
-NO_SUBDIR = :
-endif
-
-ifneq ($(findstring $(MAKEFLAGS),s),s)
-ifndef V
-	QUIET_CC       = @echo '   ' CC $@;
-	QUIET_AR       = @echo '   ' AR $@;
-	QUIET_LINK     = @echo '   ' LINK $@;
-	QUIET_BUILT_IN = @echo '   ' BUILTIN $@;
-	QUIET_GEN      = @echo '   ' GEN $@;
-	QUIET_SUBDIR0  = +@subdir=
-	QUIET_SUBDIR1  = ;$(NO_SUBDIR) echo '   ' SUBDIR $$subdir; \
-			 $(MAKE) $(PRINT_DIR) -C $$subdir
-	export V
-	export QUIET_GEN
-	export QUIET_BUILT_IN
-endif
-endif
-
-ifdef ASCIIDOC8
-	export ASCIIDOC8
-endif
-
-# Shell quote (do not use $(call) to accommodate ancient setups);
-
-SHA1_HEADER_SQ = $(subst ','\'',$(SHA1_HEADER))
-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))
-
-SHELL_PATH_SQ = $(subst ','\'',$(SHELL_PATH))
-PERL_PATH_SQ = $(subst ','\'',$(PERL_PATH))
-
-LIBS = $(PERFLIBS) $(EXTLIBS)
-
-BASIC_CFLAGS += -DSHA1_HEADER='$(SHA1_HEADER_SQ)' \
-	$(COMPAT_CFLAGS)
-LIB_OBJS += $(COMPAT_OBJS)
-
-ALL_CFLAGS += $(BASIC_CFLAGS)
-ALL_LDFLAGS += $(BASIC_LDFLAGS)
-
-export TAR INSTALL DESTDIR SHELL_PATH
-
-
-### Build rules
-
-SHELL = $(SHELL_PATH)
-
-all:: .perf.dev.null shell_compatibility_test $(ALL_PROGRAMS) $(BUILT_INS) $(OTHER_PROGRAMS) $(OUTPUT)PERF-BUILD-OPTIONS
-ifneq (,$X)
-	$(foreach p,$(patsubst %$X,%,$(filter %$X,$(ALL_PROGRAMS) $(BUILT_INS) perf$X)), test '$p' -ef '$p$X' || $(RM) '$p';)
-endif
-
-all::
-
-please_set_SHELL_PATH_to_a_more_modern_shell:
-	@$$(:)
-
-shell_compatibility_test: please_set_SHELL_PATH_to_a_more_modern_shell
-
-strip: $(PROGRAMS) $(OUTPUT)perf$X
-	$(STRIP) $(STRIP_OPTS) $(PROGRAMS) $(OUTPUT)perf$X
-
-$(OUTPUT)perf.o: perf.c $(OUTPUT)common-cmds.h $(OUTPUT)PERF-CFLAGS
-	$(QUIET_CC)$(CC) -DPERF_VERSION='"$(PERF_VERSION)"' \
-		'-DPERF_HTML_PATH="$(htmldir_SQ)"' \
-		$(ALL_CFLAGS) -c $(filter %.c,$^) -o $@
-
-$(OUTPUT)perf$X: $(OUTPUT)perf.o $(BUILTIN_OBJS) $(PERFLIBS)
-	$(QUIET_LINK)$(CC) $(ALL_CFLAGS) -o $@ $(OUTPUT)perf.o \
-		$(BUILTIN_OBJS) $(ALL_LDFLAGS) $(LIBS)
-
-$(OUTPUT)builtin-help.o: builtin-help.c $(OUTPUT)common-cmds.h $(OUTPUT)PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o $@ -c $(ALL_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) \
-		'-DPERF_HTML_PATH="$(htmldir_SQ)"' \
-		'-DPERF_MAN_PATH="$(mandir_SQ)"' \
-		'-DPERF_INFO_PATH="$(infodir_SQ)"' $<
-
-$(BUILT_INS): $(OUTPUT)perf$X
-	$(QUIET_BUILT_IN)$(RM) $@ && \
-	ln perf$X $@ 2>/dev/null || \
-	ln -s perf$X $@ 2>/dev/null || \
-	cp perf$X $@
-
-$(OUTPUT)common-cmds.h: util/generate-cmdlist.sh command-list.txt
-
-$(OUTPUT)common-cmds.h: $(wildcard Documentation/perf-*.txt)
-	$(QUIET_GEN). util/generate-cmdlist.sh > $@+ && mv $@+ $@
-
-$(patsubst %.sh,%,$(SCRIPT_SH)) : % : %.sh
-	$(QUIET_GEN)$(RM) $@ $@+ && \
-	sed -e '1s|#!.*/sh|#!$(SHELL_PATH_SQ)|' \
-	    -e 's|@SHELL_PATH@|$(SHELL_PATH_SQ)|' \
-	    -e 's|@@PERL@@|$(PERL_PATH_SQ)|g' \
-	    -e 's/@@PERF_VERSION@@/$(PERF_VERSION)/g' \
-	    -e 's/@@NO_CURL@@/$(NO_CURL)/g' \
-	    $@.sh >$@+ && \
-	chmod +x $@+ && \
-	mv $@+ $(OUTPUT)$@
-
-configure: configure.ac
-	$(QUIET_GEN)$(RM) $@ $<+ && \
-	sed -e 's/@@PERF_VERSION@@/$(PERF_VERSION)/g' \
-	    $< > $<+ && \
-	autoconf -o $@ $<+ && \
-	$(RM) $<+
-
-# These can record PERF_VERSION
-$(OUTPUT)perf.o perf.spec \
-	$(patsubst %.sh,%,$(SCRIPT_SH)) \
-	$(patsubst %.perl,%,$(SCRIPT_PERL)) \
-	: $(OUTPUT)PERF-VERSION-FILE
-
-$(OUTPUT)%.o: %.c $(OUTPUT)PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $<
-$(OUTPUT)%.s: %.c $(OUTPUT)PERF-CFLAGS
-	$(QUIET_CC)$(CC) -S $(ALL_CFLAGS) $<
-$(OUTPUT)%.o: %.S
-	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $<
-
-$(OUTPUT)util/exec_cmd.o: util/exec_cmd.c $(OUTPUT)PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) \
-		'-DPERF_EXEC_PATH="$(perfexecdir_SQ)"' \
-		'-DBINDIR="$(bindir_relative_SQ)"' \
-		'-DPREFIX="$(prefix_SQ)"' \
-		$<
-
-$(OUTPUT)builtin-init-db.o: builtin-init-db.c $(OUTPUT)PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DDEFAULT_PERF_TEMPLATE_DIR='"$(template_dir_SQ)"' $<
-
-$(OUTPUT)util/config.o: util/config.c $(OUTPUT)PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
-
-$(OUTPUT)util/newt.o: util/newt.c $(OUTPUT)PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DENABLE_SLFUTURE_CONST $<
-
-$(OUTPUT)util/rbtree.o: ../../lib/rbtree.c $(OUTPUT)PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
-
-$(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 $<
-
-$(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 $<
-
-$(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 $<
-
-$(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 $<
-
-$(OUTPUT)perf-%$X: %.o $(PERFLIBS)
-	$(QUIET_LINK)$(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) $(LIBS)
-
-$(LIB_OBJS) $(BUILTIN_OBJS): $(LIB_H)
-$(patsubst perf-%$X,%.o,$(PROGRAMS)): $(LIB_H) $(wildcard */*.h)
-builtin-revert.o wt-status.o: wt-status.h
-
-$(LIB_FILE): $(LIB_OBJS)
-	$(QUIET_AR)$(RM) $@ && $(AR) rcs $@ $(LIB_OBJS)
-
-doc:
-	$(MAKE) -C Documentation all
-
-man:
-	$(MAKE) -C Documentation man
-
-html:
-	$(MAKE) -C Documentation html
-
-info:
-	$(MAKE) -C Documentation info
-
-pdf:
-	$(MAKE) -C Documentation pdf
-
-TAGS:
-	$(RM) TAGS
-	$(FIND) . -name '*.[hcS]' -print | xargs etags -a
-
-tags:
-	$(RM) tags
-	$(FIND) . -name '*.[hcS]' -print | xargs ctags -a
-
-cscope:
-	$(RM) cscope*
-	$(FIND) . -name '*.[hcS]' -print | xargs cscope -b
-
-### Detect prefix changes
-TRACK_CFLAGS = $(subst ','\'',$(ALL_CFLAGS)):\
-             $(bindir_SQ):$(perfexecdir_SQ):$(template_dir_SQ):$(prefix_SQ)
-
-$(OUTPUT)PERF-CFLAGS: .FORCE-PERF-CFLAGS
-	@FLAGS='$(TRACK_CFLAGS)'; \
-	    if test x"$$FLAGS" != x"`cat $(OUTPUT)PERF-CFLAGS 2>/dev/null`" ; then \
-		echo 1>&2 "    * new build flags or prefix"; \
-		echo "$$FLAGS" >$(OUTPUT)PERF-CFLAGS; \
-            fi
-
-# We need to apply sq twice, once to protect from the shell
-# that runs $(OUTPUT)PERF-BUILD-OPTIONS, and then again to protect it
-# and the first level quoting from the shell that runs "echo".
-$(OUTPUT)PERF-BUILD-OPTIONS: .FORCE-PERF-BUILD-OPTIONS
-	@echo SHELL_PATH=\''$(subst ','\'',$(SHELL_PATH_SQ))'\' >$@
-	@echo TAR=\''$(subst ','\'',$(subst ','\'',$(TAR)))'\' >>$@
-	@echo NO_CURL=\''$(subst ','\'',$(subst ','\'',$(NO_CURL)))'\' >>$@
-	@echo NO_PERL=\''$(subst ','\'',$(subst ','\'',$(NO_PERL)))'\' >>$@
-
-### Testing rules
-
 #
-# None right now:
+# Only accept the 'DEBUG' variable from the command line:
 #
-# TEST_PROGRAMS += test-something$X
-
-all:: $(TEST_PROGRAMS)
-
-# GNU make supports exporting all variables by "export" without parameters.
-# However, the environment gets quite big, and some programs have problems
-# with that.
-
-export NO_SVN_TESTS
-
-check: $(OUTPUT)common-cmds.h
-	if sparse; \
-	then \
-		for i in *.c */*.c; \
-		do \
-			sparse $(ALL_CFLAGS) $(SPARSE_FLAGS) $$i || exit; \
-		done; \
-	else \
-		echo 2>&1 "Did you mean 'make test'?"; \
-		exit 1; \
-	fi
-
-remove-dashes:
-	./fixup-builtins $(BUILT_INS) $(PROGRAMS) $(SCRIPTS)
-
-### Installation rules
-
-ifneq ($(filter /%,$(firstword $(template_dir))),)
-template_instdir = $(template_dir)
-else
-template_instdir = $(prefix)/$(template_dir)
-endif
-export template_instdir
-
-ifneq ($(filter /%,$(firstword $(perfexecdir))),)
-perfexec_instdir = $(perfexecdir)
+ifeq ("$(origin DEBUG)", "command line")
+  ifeq ($(DEBUG),)
+    override DEBUG = 0
+  else
+    SET_DEBUG = "DEBUG=$(DEBUG)"
+  endif
 else
-perfexec_instdir = $(prefix)/$(perfexecdir)
+  override DEBUG = 0
 endif
-perfexec_instdir_SQ = $(subst ','\'',$(perfexec_instdir))
-export perfexec_instdir
-
-install: all
-	$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(bindir_SQ)'
-	$(INSTALL) $(OUTPUT)perf$X '$(DESTDIR_SQ)$(bindir_SQ)'
-	$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace'
-	$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/bin'
-	$(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
-	$(INSTALL) scripts/perl/Perf-Trace-Util/lib/Perf/Trace/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace'
-	$(INSTALL) scripts/perl/*.pl -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl'
-	$(INSTALL) scripts/perl/bin/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/bin'
-	$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/Perf-Trace-Util/lib/Perf/Trace'
-	$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/bin'
-	$(INSTALL) scripts/python/Perf-Trace-Util/lib/Perf/Trace/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/Perf-Trace-Util/lib/Perf/Trace'
-	$(INSTALL) scripts/python/*.py -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python'
-	$(INSTALL) scripts/python/bin/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/bin'
-
-ifdef BUILT_INS
-	$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
-	$(INSTALL) $(BUILT_INS) '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
-ifneq (,$X)
-	$(foreach p,$(patsubst %$X,%,$(filter %$X,$(ALL_PROGRAMS) $(BUILT_INS) $(OUTPUT)perf$X)), $(RM) '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/$p';)
-endif
-endif
-
-install-doc:
-	$(MAKE) -C Documentation install
-
-install-man:
-	$(MAKE) -C Documentation install-man
-
-install-html:
-	$(MAKE) -C Documentation install-html
-
-install-info:
-	$(MAKE) -C Documentation install-info
-
-install-pdf:
-	$(MAKE) -C Documentation install-pdf
 
-quick-install-doc:
-	$(MAKE) -C Documentation quick-install
+define print_msg
+  @printf '  BUILD:   Doing '\''make \033[33m-j'$(JOBS)'\033[m'\'' parallel build\n'
+endef
 
-quick-install-man:
-	$(MAKE) -C Documentation quick-install-man
+define make
+  @$(MAKE) -f Makefile.perf --no-print-directory -j$(JOBS) O=$(FULL_O) $(SET_DEBUG) $@
+endef
 
-quick-install-html:
-	$(MAKE) -C Documentation quick-install-html
-
-
-### Maintainer's dist rules
-#
-# None right now
 #
+# Needed if no target specified:
+# (Except for tags and TAGS targets. The reason is that the
+# Makefile does not treat tags/TAGS as targets but as files
+# and thus won't rebuilt them once they are in place.)
 #
-# perf.spec: perf.spec.in
-#	sed -e 's/@@VERSION@@/$(PERF_VERSION)/g' < $< > $@+
-#	mv $@+ $@
-#
-# PERF_TARNAME=perf-$(PERF_VERSION)
-# dist: perf.spec perf-archive$(X) configure
-#	./perf-archive --format=tar \
-#		--prefix=$(PERF_TARNAME)/ HEAD^{tree} > $(PERF_TARNAME).tar
-#	@mkdir -p $(PERF_TARNAME)
-#	@cp perf.spec configure $(PERF_TARNAME)
-#	@echo $(PERF_VERSION) > $(PERF_TARNAME)/version
-#	$(TAR) rf $(PERF_TARNAME).tar \
-#		$(PERF_TARNAME)/perf.spec \
-#		$(PERF_TARNAME)/configure \
-#		$(PERF_TARNAME)/version
-#	@$(RM) -r $(PERF_TARNAME)
-#	gzip -f -9 $(PERF_TARNAME).tar
+all tags TAGS:
+	$(print_msg)
+	$(make)
+
 #
-# htmldocs = perf-htmldocs-$(PERF_VERSION)
-# manpages = perf-manpages-$(PERF_VERSION)
-# dist-doc:
-#	$(RM) -r .doc-tmp-dir
-#	mkdir .doc-tmp-dir
-#	$(MAKE) -C Documentation WEBDOC_DEST=../.doc-tmp-dir install-webdoc
-#	cd .doc-tmp-dir && $(TAR) cf ../$(htmldocs).tar .
-#	gzip -n -9 -f $(htmldocs).tar
-#	:
-#	$(RM) -r .doc-tmp-dir
-#	mkdir -p .doc-tmp-dir/man1 .doc-tmp-dir/man5 .doc-tmp-dir/man7
-#	$(MAKE) -C Documentation DESTDIR=./ \
-#		man1dir=../.doc-tmp-dir/man1 \
-#		man5dir=../.doc-tmp-dir/man5 \
-#		man7dir=../.doc-tmp-dir/man7 \
-#		install
-#	cd .doc-tmp-dir && $(TAR) cf ../$(manpages).tar .
-#	gzip -n -9 -f $(manpages).tar
-#	$(RM) -r .doc-tmp-dir
+# The clean target is not really parallel, don't print the jobs info:
 #
-# rpm: dist
-#	$(RPMBUILD) -ta $(PERF_TARNAME).tar.gz
-
-### Cleaning rules
-
-distclean: clean
-#	$(RM) configure
-
 clean:
-	$(RM) *.o */*.o */*/*.o */*/*/*.o $(LIB_FILE)
-	$(RM) $(ALL_PROGRAMS) $(BUILT_INS) perf$X
-	$(RM) $(TEST_PROGRAMS)
-	$(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope*
-	$(RM) -r autom4te.cache
-	$(RM) config.log config.mak.autogen config.mak.append config.status config.cache
-	$(RM) -r $(PERF_TARNAME) .doc-tmp-dir
-	$(RM) $(PERF_TARNAME).tar.gz perf-core_$(PERF_VERSION)-*.tar.gz
-	$(RM) $(htmldocs).tar.gz $(manpages).tar.gz
-	$(MAKE) -C Documentation/ clean
-	$(RM) $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)PERF-CFLAGS $(OUTPUT)PERF-BUILD-OPTIONS
-
-.PHONY: all install clean strip
-.PHONY: shell_compatibility_test please_set_SHELL_PATH_to_a_more_modern_shell
-.PHONY: .FORCE-PERF-VERSION-FILE TAGS tags cscope .FORCE-PERF-CFLAGS
-.PHONY: .FORCE-PERF-BUILD-OPTIONS
+	$(make)
 
-.perf.dev.null:
-		touch .perf.dev.null
-
-.INTERMEDIATE:	.perf.dev.null
-
-### Make sure built-ins do not have dups and listed in perf.c
-#
-check-builtins::
-	./check-builtins.sh
-
-### Test suite coverage testing
-#
-# None right now
 #
-# .PHONY: coverage coverage-clean coverage-build coverage-report
+# The build-test target is not really parallel, don't print the jobs info:
 #
-# coverage:
-#	$(MAKE) coverage-build
-#	$(MAKE) coverage-report
-#
-# coverage-clean:
-#	rm -f *.gcda *.gcno
-#
-# COVERAGE_CFLAGS = $(CFLAGS) -O0 -ftest-coverage -fprofile-arcs
-# COVERAGE_LDFLAGS = $(CFLAGS)  -O0 -lgcov
+build-test:
+	@$(MAKE) -f tests/make --no-print-directory
+
 #
-# coverage-build: coverage-clean
-#	$(MAKE) CFLAGS="$(COVERAGE_CFLAGS)" LDFLAGS="$(COVERAGE_LDFLAGS)" all
-#	$(MAKE) CFLAGS="$(COVERAGE_CFLAGS)" LDFLAGS="$(COVERAGE_LDFLAGS)" \
-#		-j1 test
+# All other targets get passed through:
 #
-# coverage-report:
-#	gcov -b *.c */*.c
-#	grep '^function.*called 0 ' *.c.gcov */*.c.gcov \
-#		| sed -e 's/\([^:]*\)\.gcov: *function \([^ ]*\) called.*/\1: \2/' \
-#		| tee coverage-untested-functions
+%:
+	$(print_msg)
+	$(make)
+
+.PHONY: tags TAGS
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
new file mode 100644
index 00000000000..9670a16fa57
--- /dev/null
+++ b/tools/perf/Makefile.perf
@@ -0,0 +1,938 @@
+include ../scripts/Makefile.include
+
+# The default target of this Makefile is...
+all:
+
+include config/utilities.mak
+
+# Define V to have a more verbose compile.
+#
+# Define VF to have a more verbose feature check output.
+#
+# Define O to save output files in a separate directory.
+#
+# Define ARCH as name of target architecture if you want cross-builds.
+#
+# Define CROSS_COMPILE as prefix name of compiler if you want cross-builds.
+#
+# Define NO_LIBPERL to disable perl script extension.
+#
+# Define NO_LIBPYTHON to disable python script extension.
+#
+# Define PYTHON to point to the python binary if the default
+# `python' is not correct; for example: PYTHON=python2
+#
+# Define PYTHON_CONFIG to point to the python-config binary if
+# the default `$(PYTHON)-config' is not correct.
+#
+# Define ASCIIDOC8 if you want to format documentation with AsciiDoc 8
+#
+# Define DOCBOOK_XSL_172 if you want to format man pages with DocBook XSL v1.72.
+#
+# Define LDFLAGS=-static to build a static binary.
+#
+# Define EXTRA_CFLAGS=-m64 or EXTRA_CFLAGS=-m32 as appropriate for cross-builds.
+#
+# Define NO_DWARF if you do not want debug-info analysis feature at all.
+#
+# Define WERROR=0 to disable treating any warnings as errors.
+#
+# Define NO_NEWT if you do not want TUI support. (deprecated)
+#
+# Define NO_SLANG if you do not want TUI support.
+#
+# Define NO_GTK2 if you do not want GTK+ GUI support.
+#
+# Define NO_DEMANGLE if you do not want C++ symbol demangling.
+#
+# Define NO_LIBELF if you do not want libelf dependency (e.g. cross-builds)
+#
+# Define NO_LIBUNWIND if you do not want libunwind dependency for dwarf
+# backtrace post unwind.
+#
+# 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
+#
+# Define NO_LIBDW_DWARF_UNWIND if you do not want libdw support
+# for dwarf backtrace post unwind.
+
+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 $(objtree))
+endif
+
+ifneq ($(OUTPUT),)
+#$(info Determined 'OUTPUT' to be $(OUTPUT))
+endif
+
+$(OUTPUT)PERF-VERSION-FILE: ../../.git/HEAD
+	@$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT)
+	@touch $(OUTPUT)PERF-VERSION-FILE
+
+CC = $(CROSS_COMPILE)gcc
+AR = $(CROSS_COMPILE)ar
+PKG_CONFIG = $(CROSS_COMPILE)pkg-config
+
+RM      = rm -f
+LN      = ln -f
+MKDIR   = mkdir
+FIND    = find
+INSTALL = install
+FLEX    = flex
+BISON   = bison
+STRIP   = strip
+
+LIB_DIR          = $(srctree)/tools/lib/api/
+TRACE_EVENT_DIR = $(srctree)/tools/lib/traceevent/
+
+# include config/Makefile by default and rule out
+# non-config cases
+config := 1
+
+NON_CONFIG_TARGETS := clean TAGS tags cscope help
+
+ifdef MAKECMDGOALS
+ifeq ($(filter-out $(NON_CONFIG_TARGETS),$(MAKECMDGOALS)),)
+  config := 0
+endif
+endif
+
+ifeq ($(config),1)
+include config/Makefile
+endif
+
+export prefix bindir sharedir sysconfdir DESTDIR
+
+# sparse is architecture-neutral, which means that we need to tell it
+# explicitly what architecture to check for. Fix this up for yours..
+SPARSE_FLAGS = -D__BIG_ENDIAN__ -D__powerpc__
+
+# Guard against environment variables
+BUILTIN_OBJS =
+LIB_H =
+LIB_OBJS =
+GTK_OBJS =
+PYRF_OBJS =
+SCRIPT_SH =
+
+SCRIPT_SH += perf-archive.sh
+
+grep-libs = $(filter -l%,$(1))
+strip-libs = $(filter-out -l%,$(1))
+
+ifneq ($(OUTPUT),)
+  TE_PATH=$(OUTPUT)
+ifneq ($(subdir),)
+  LIB_PATH=$(OUTPUT)/../lib/api/
+else
+  LIB_PATH=$(OUTPUT)
+endif
+else
+  TE_PATH=$(TRACE_EVENT_DIR)
+  LIB_PATH=$(LIB_DIR)
+endif
+
+LIBTRACEEVENT = $(TE_PATH)libtraceevent.a
+export LIBTRACEEVENT
+
+LIBAPIKFS = $(LIB_PATH)libapikfs.a
+export LIBAPIKFS
+
+# python extension build directories
+PYTHON_EXTBUILD     := $(OUTPUT)python_ext_build/
+PYTHON_EXTBUILD_LIB := $(PYTHON_EXTBUILD)lib/
+PYTHON_EXTBUILD_TMP := $(PYTHON_EXTBUILD)tmp/
+export PYTHON_EXTBUILD_LIB PYTHON_EXTBUILD_TMP
+
+python-clean := $(call QUIET_CLEAN, python) $(RM) -r $(PYTHON_EXTBUILD) $(OUTPUT)python/perf.so
+
+PYTHON_EXT_SRCS := $(shell grep -v ^\# util/python-ext-sources)
+PYTHON_EXT_DEPS := util/python-ext-sources util/setup.py $(LIBTRACEEVENT) $(LIBAPIKFS)
+
+$(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS)
+	$(QUIET_GEN)CFLAGS='$(CFLAGS)' $(PYTHON_WORD) util/setup.py \
+	  --quiet build_ext; \
+	mkdir -p $(OUTPUT)python && \
+	cp $(PYTHON_EXTBUILD_LIB)perf.so $(OUTPUT)python/
+#
+# No Perl scripts right now:
+#
+
+SCRIPTS = $(patsubst %.sh,%,$(SCRIPT_SH))
+
+#
+# Single 'perf' binary right now:
+#
+PROGRAMS += $(OUTPUT)perf
+
+# what 'all' will build and 'install' will install, in perfexecdir
+ALL_PROGRAMS = $(PROGRAMS) $(SCRIPTS)
+
+# what 'all' will build but not install in perfexecdir
+OTHER_PROGRAMS = $(OUTPUT)perf
+
+# Set paths to tools early so that they can be used for version tests.
+ifndef SHELL_PATH
+  SHELL_PATH = /bin/sh
+endif
+ifndef PERL_PATH
+  PERL_PATH = /usr/bin/perl
+endif
+
+export PERL_PATH
+
+$(OUTPUT)util/parse-events-flex.c: util/parse-events.l $(OUTPUT)util/parse-events-bison.c
+	$(QUIET_FLEX)$(FLEX) -o $@ --header-file=$(OUTPUT)util/parse-events-flex.h $(PARSER_DEBUG_FLEX) util/parse-events.l
+
+$(OUTPUT)util/parse-events-bison.c: util/parse-events.y
+	$(QUIET_BISON)$(BISON) -v util/parse-events.y -d $(PARSER_DEBUG_BISON) -o $(OUTPUT)util/parse-events-bison.c -p parse_events_
+
+$(OUTPUT)util/pmu-flex.c: util/pmu.l $(OUTPUT)util/pmu-bison.c
+	$(QUIET_FLEX)$(FLEX) -o $@ --header-file=$(OUTPUT)util/pmu-flex.h util/pmu.l
+
+$(OUTPUT)util/pmu-bison.c: util/pmu.y
+	$(QUIET_BISON)$(BISON) -v util/pmu.y -d -o $(OUTPUT)util/pmu-bison.c -p perf_pmu_
+
+$(OUTPUT)util/parse-events.o: $(OUTPUT)util/parse-events-flex.c $(OUTPUT)util/parse-events-bison.c
+$(OUTPUT)util/pmu.o: $(OUTPUT)util/pmu-flex.c $(OUTPUT)util/pmu-bison.c
+
+LIB_FILE=$(OUTPUT)libperf.a
+
+LIB_H += ../lib/symbol/kallsyms.h
+LIB_H += ../../include/uapi/linux/perf_event.h
+LIB_H += ../../include/linux/rbtree.h
+LIB_H += ../../include/linux/list.h
+LIB_H += ../../include/uapi/linux/const.h
+LIB_H += ../include/linux/hash.h
+LIB_H += ../../include/linux/stringify.h
+LIB_H += util/include/linux/bitmap.h
+LIB_H += util/include/linux/bitops.h
+LIB_H += ../include/linux/compiler.h
+LIB_H += util/include/linux/const.h
+LIB_H += util/include/linux/ctype.h
+LIB_H += util/include/linux/kernel.h
+LIB_H += util/include/linux/list.h
+LIB_H += ../include/linux/export.h
+LIB_H += util/include/linux/poison.h
+LIB_H += util/include/linux/rbtree.h
+LIB_H += util/include/linux/rbtree_augmented.h
+LIB_H += util/include/linux/string.h
+LIB_H += ../include/linux/types.h
+LIB_H += util/include/linux/linkage.h
+LIB_H += util/include/asm/asm-offsets.h
+LIB_H += ../include/asm/bug.h
+LIB_H += util/include/asm/byteorder.h
+LIB_H += util/include/asm/hweight.h
+LIB_H += util/include/asm/swab.h
+LIB_H += util/include/asm/system.h
+LIB_H += util/include/asm/uaccess.h
+LIB_H += util/include/dwarf-regs.h
+LIB_H += util/include/asm/dwarf2.h
+LIB_H += util/include/asm/cpufeature.h
+LIB_H += util/include/asm/unistd_32.h
+LIB_H += util/include/asm/unistd_64.h
+LIB_H += perf.h
+LIB_H += util/annotate.h
+LIB_H += util/cache.h
+LIB_H += util/callchain.h
+LIB_H += util/build-id.h
+LIB_H += util/debug.h
+LIB_H += util/pmu.h
+LIB_H += util/event.h
+LIB_H += util/evsel.h
+LIB_H += util/evlist.h
+LIB_H += util/exec_cmd.h
+LIB_H += util/levenshtein.h
+LIB_H += util/machine.h
+LIB_H += util/map.h
+LIB_H += util/parse-options.h
+LIB_H += util/parse-events.h
+LIB_H += util/quote.h
+LIB_H += util/util.h
+LIB_H += util/xyarray.h
+LIB_H += util/header.h
+LIB_H += util/help.h
+LIB_H += util/session.h
+LIB_H += util/strbuf.h
+LIB_H += util/strlist.h
+LIB_H += util/strfilter.h
+LIB_H += util/svghelper.h
+LIB_H += util/tool.h
+LIB_H += util/run-command.h
+LIB_H += util/sigchain.h
+LIB_H += util/dso.h
+LIB_H += util/symbol.h
+LIB_H += util/color.h
+LIB_H += util/values.h
+LIB_H += util/sort.h
+LIB_H += util/hist.h
+LIB_H += util/comm.h
+LIB_H += util/thread.h
+LIB_H += util/thread_map.h
+LIB_H += util/trace-event.h
+LIB_H += util/probe-finder.h
+LIB_H += util/dwarf-aux.h
+LIB_H += util/probe-event.h
+LIB_H += util/pstack.h
+LIB_H += util/cpumap.h
+LIB_H += util/top.h
+LIB_H += $(ARCH_INCLUDE)
+LIB_H += util/cgroup.h
+LIB_H += $(LIB_INCLUDE)traceevent/event-parse.h
+LIB_H += util/target.h
+LIB_H += util/rblist.h
+LIB_H += util/intlist.h
+LIB_H += util/perf_regs.h
+LIB_H += util/unwind.h
+LIB_H += util/vdso.h
+LIB_H += ui/helpline.h
+LIB_H += ui/progress.h
+LIB_H += ui/util.h
+LIB_H += ui/ui.h
+LIB_H += util/data.h
+
+LIB_OBJS += $(OUTPUT)util/abspath.o
+LIB_OBJS += $(OUTPUT)util/alias.o
+LIB_OBJS += $(OUTPUT)util/annotate.o
+LIB_OBJS += $(OUTPUT)util/build-id.o
+LIB_OBJS += $(OUTPUT)util/config.o
+LIB_OBJS += $(OUTPUT)util/ctype.o
+LIB_OBJS += $(OUTPUT)util/pmu.o
+LIB_OBJS += $(OUTPUT)util/environment.o
+LIB_OBJS += $(OUTPUT)util/event.o
+LIB_OBJS += $(OUTPUT)util/evlist.o
+LIB_OBJS += $(OUTPUT)util/evsel.o
+LIB_OBJS += $(OUTPUT)util/exec_cmd.o
+LIB_OBJS += $(OUTPUT)util/help.o
+LIB_OBJS += $(OUTPUT)util/kallsyms.o
+LIB_OBJS += $(OUTPUT)util/levenshtein.o
+LIB_OBJS += $(OUTPUT)util/parse-options.o
+LIB_OBJS += $(OUTPUT)util/parse-events.o
+LIB_OBJS += $(OUTPUT)util/path.o
+LIB_OBJS += $(OUTPUT)util/rbtree.o
+LIB_OBJS += $(OUTPUT)util/bitmap.o
+LIB_OBJS += $(OUTPUT)util/hweight.o
+LIB_OBJS += $(OUTPUT)util/run-command.o
+LIB_OBJS += $(OUTPUT)util/quote.o
+LIB_OBJS += $(OUTPUT)util/strbuf.o
+LIB_OBJS += $(OUTPUT)util/string.o
+LIB_OBJS += $(OUTPUT)util/strlist.o
+LIB_OBJS += $(OUTPUT)util/strfilter.o
+LIB_OBJS += $(OUTPUT)util/top.o
+LIB_OBJS += $(OUTPUT)util/usage.o
+LIB_OBJS += $(OUTPUT)util/wrapper.o
+LIB_OBJS += $(OUTPUT)util/sigchain.o
+LIB_OBJS += $(OUTPUT)util/dso.o
+LIB_OBJS += $(OUTPUT)util/symbol.o
+LIB_OBJS += $(OUTPUT)util/symbol-elf.o
+LIB_OBJS += $(OUTPUT)util/color.o
+LIB_OBJS += $(OUTPUT)util/pager.o
+LIB_OBJS += $(OUTPUT)util/header.o
+LIB_OBJS += $(OUTPUT)util/callchain.o
+LIB_OBJS += $(OUTPUT)util/values.o
+LIB_OBJS += $(OUTPUT)util/debug.o
+LIB_OBJS += $(OUTPUT)util/machine.o
+LIB_OBJS += $(OUTPUT)util/map.o
+LIB_OBJS += $(OUTPUT)util/pstack.o
+LIB_OBJS += $(OUTPUT)util/session.o
+LIB_OBJS += $(OUTPUT)util/comm.o
+LIB_OBJS += $(OUTPUT)util/thread.o
+LIB_OBJS += $(OUTPUT)util/thread_map.o
+LIB_OBJS += $(OUTPUT)util/trace-event-parse.o
+LIB_OBJS += $(OUTPUT)util/parse-events-flex.o
+LIB_OBJS += $(OUTPUT)util/parse-events-bison.o
+LIB_OBJS += $(OUTPUT)util/pmu-flex.o
+LIB_OBJS += $(OUTPUT)util/pmu-bison.o
+LIB_OBJS += $(OUTPUT)util/trace-event-read.o
+LIB_OBJS += $(OUTPUT)util/trace-event-info.o
+LIB_OBJS += $(OUTPUT)util/trace-event-scripting.o
+LIB_OBJS += $(OUTPUT)util/trace-event.o
+LIB_OBJS += $(OUTPUT)util/svghelper.o
+LIB_OBJS += $(OUTPUT)util/sort.o
+LIB_OBJS += $(OUTPUT)util/hist.o
+LIB_OBJS += $(OUTPUT)util/probe-event.o
+LIB_OBJS += $(OUTPUT)util/util.o
+LIB_OBJS += $(OUTPUT)util/xyarray.o
+LIB_OBJS += $(OUTPUT)util/cpumap.o
+LIB_OBJS += $(OUTPUT)util/cgroup.o
+LIB_OBJS += $(OUTPUT)util/target.o
+LIB_OBJS += $(OUTPUT)util/rblist.o
+LIB_OBJS += $(OUTPUT)util/intlist.o
+LIB_OBJS += $(OUTPUT)util/vdso.o
+LIB_OBJS += $(OUTPUT)util/stat.o
+LIB_OBJS += $(OUTPUT)util/record.o
+LIB_OBJS += $(OUTPUT)util/srcline.o
+LIB_OBJS += $(OUTPUT)util/data.o
+
+LIB_OBJS += $(OUTPUT)ui/setup.o
+LIB_OBJS += $(OUTPUT)ui/helpline.o
+LIB_OBJS += $(OUTPUT)ui/progress.o
+LIB_OBJS += $(OUTPUT)ui/util.o
+LIB_OBJS += $(OUTPUT)ui/hist.o
+LIB_OBJS += $(OUTPUT)ui/stdio/hist.o
+
+LIB_OBJS += $(OUTPUT)arch/common.o
+
+LIB_OBJS += $(OUTPUT)tests/parse-events.o
+LIB_OBJS += $(OUTPUT)tests/dso-data.o
+LIB_OBJS += $(OUTPUT)tests/attr.o
+LIB_OBJS += $(OUTPUT)tests/vmlinux-kallsyms.o
+LIB_OBJS += $(OUTPUT)tests/open-syscall.o
+LIB_OBJS += $(OUTPUT)tests/open-syscall-all-cpus.o
+LIB_OBJS += $(OUTPUT)tests/open-syscall-tp-fields.o
+LIB_OBJS += $(OUTPUT)tests/mmap-basic.o
+LIB_OBJS += $(OUTPUT)tests/perf-record.o
+LIB_OBJS += $(OUTPUT)tests/rdpmc.o
+LIB_OBJS += $(OUTPUT)tests/evsel-roundtrip-name.o
+LIB_OBJS += $(OUTPUT)tests/evsel-tp-sched.o
+LIB_OBJS += $(OUTPUT)tests/pmu.o
+LIB_OBJS += $(OUTPUT)tests/hists_common.o
+LIB_OBJS += $(OUTPUT)tests/hists_link.o
+LIB_OBJS += $(OUTPUT)tests/hists_filter.o
+LIB_OBJS += $(OUTPUT)tests/hists_output.o
+LIB_OBJS += $(OUTPUT)tests/hists_cumulate.o
+LIB_OBJS += $(OUTPUT)tests/python-use.o
+LIB_OBJS += $(OUTPUT)tests/bp_signal.o
+LIB_OBJS += $(OUTPUT)tests/bp_signal_overflow.o
+LIB_OBJS += $(OUTPUT)tests/task-exit.o
+LIB_OBJS += $(OUTPUT)tests/sw-clock.o
+ifeq ($(ARCH),x86)
+LIB_OBJS += $(OUTPUT)tests/perf-time-to-tsc.o
+endif
+LIB_OBJS += $(OUTPUT)tests/code-reading.o
+LIB_OBJS += $(OUTPUT)tests/sample-parsing.o
+LIB_OBJS += $(OUTPUT)tests/parse-no-sample-id-all.o
+ifndef NO_DWARF_UNWIND
+ifeq ($(ARCH),$(filter $(ARCH),x86 arm))
+LIB_OBJS += $(OUTPUT)tests/dwarf-unwind.o
+endif
+endif
+LIB_OBJS += $(OUTPUT)tests/mmap-thread-lookup.o
+LIB_OBJS += $(OUTPUT)tests/thread-mg-share.o
+
+BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o
+BUILTIN_OBJS += $(OUTPUT)builtin-bench.o
+# Benchmark modules
+BUILTIN_OBJS += $(OUTPUT)bench/sched-messaging.o
+BUILTIN_OBJS += $(OUTPUT)bench/sched-pipe.o
+ifeq ($(RAW_ARCH),x86_64)
+BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy-x86-64-asm.o
+BUILTIN_OBJS += $(OUTPUT)bench/mem-memset-x86-64-asm.o
+endif
+BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy.o
+BUILTIN_OBJS += $(OUTPUT)bench/mem-memset.o
+BUILTIN_OBJS += $(OUTPUT)bench/futex-hash.o
+BUILTIN_OBJS += $(OUTPUT)bench/futex-wake.o
+BUILTIN_OBJS += $(OUTPUT)bench/futex-requeue.o
+
+BUILTIN_OBJS += $(OUTPUT)builtin-diff.o
+BUILTIN_OBJS += $(OUTPUT)builtin-evlist.o
+BUILTIN_OBJS += $(OUTPUT)builtin-help.o
+BUILTIN_OBJS += $(OUTPUT)builtin-sched.o
+BUILTIN_OBJS += $(OUTPUT)builtin-buildid-list.o
+BUILTIN_OBJS += $(OUTPUT)builtin-buildid-cache.o
+BUILTIN_OBJS += $(OUTPUT)builtin-list.o
+BUILTIN_OBJS += $(OUTPUT)builtin-record.o
+BUILTIN_OBJS += $(OUTPUT)builtin-report.o
+BUILTIN_OBJS += $(OUTPUT)builtin-stat.o
+BUILTIN_OBJS += $(OUTPUT)builtin-timechart.o
+BUILTIN_OBJS += $(OUTPUT)builtin-top.o
+BUILTIN_OBJS += $(OUTPUT)builtin-script.o
+BUILTIN_OBJS += $(OUTPUT)builtin-probe.o
+BUILTIN_OBJS += $(OUTPUT)builtin-kmem.o
+BUILTIN_OBJS += $(OUTPUT)builtin-lock.o
+BUILTIN_OBJS += $(OUTPUT)builtin-kvm.o
+BUILTIN_OBJS += $(OUTPUT)builtin-inject.o
+BUILTIN_OBJS += $(OUTPUT)tests/builtin-test.o
+BUILTIN_OBJS += $(OUTPUT)builtin-mem.o
+
+PERFLIBS = $(LIB_FILE) $(LIBAPIKFS) $(LIBTRACEEVENT)
+
+# We choose to avoid "if .. else if .. else .. endif endif"
+# because maintaining the nesting to match is a pain.  If
+# we had "elif" things would have been much nicer...
+
+-include arch/$(ARCH)/Makefile
+
+ifneq ($(OUTPUT),)
+  CFLAGS += -I$(OUTPUT)
+endif
+
+ifdef NO_LIBELF
+EXTLIBS := $(filter-out -lelf,$(EXTLIBS))
+
+# Remove ELF/DWARF dependent codes
+LIB_OBJS := $(filter-out $(OUTPUT)util/symbol-elf.o,$(LIB_OBJS))
+LIB_OBJS := $(filter-out $(OUTPUT)util/dwarf-aux.o,$(LIB_OBJS))
+LIB_OBJS := $(filter-out $(OUTPUT)util/probe-event.o,$(LIB_OBJS))
+LIB_OBJS := $(filter-out $(OUTPUT)util/probe-finder.o,$(LIB_OBJS))
+
+BUILTIN_OBJS := $(filter-out $(OUTPUT)builtin-probe.o,$(BUILTIN_OBJS))
+
+# Use minimal symbol handling
+LIB_OBJS += $(OUTPUT)util/symbol-minimal.o
+
+else # NO_LIBELF
+ifndef NO_DWARF
+  LIB_OBJS += $(OUTPUT)util/probe-finder.o
+  LIB_OBJS += $(OUTPUT)util/dwarf-aux.o
+endif # NO_DWARF
+endif # NO_LIBELF
+
+ifndef NO_LIBDW_DWARF_UNWIND
+  LIB_OBJS += $(OUTPUT)util/unwind-libdw.o
+  LIB_H += util/unwind-libdw.h
+endif
+
+ifndef NO_LIBUNWIND
+  LIB_OBJS += $(OUTPUT)util/unwind-libunwind.o
+endif
+LIB_OBJS += $(OUTPUT)tests/keep-tracking.o
+
+ifndef NO_LIBAUDIT
+  BUILTIN_OBJS += $(OUTPUT)builtin-trace.o
+endif
+
+ifndef NO_SLANG
+  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/browsers/header.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/tui/tui.h
+  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
+  ALL_PROGRAMS += $(OUTPUT)libperf-gtk.so
+
+  GTK_OBJS += $(OUTPUT)ui/gtk/browser.o
+  GTK_OBJS += $(OUTPUT)ui/gtk/hists.o
+  GTK_OBJS += $(OUTPUT)ui/gtk/setup.o
+  GTK_OBJS += $(OUTPUT)ui/gtk/util.o
+  GTK_OBJS += $(OUTPUT)ui/gtk/helpline.o
+  GTK_OBJS += $(OUTPUT)ui/gtk/progress.o
+  GTK_OBJS += $(OUTPUT)ui/gtk/annotate.o
+
+install-gtk: $(OUTPUT)libperf-gtk.so
+	$(call QUIET_INSTALL, 'GTK UI') \
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(libdir_SQ)'; \
+		$(INSTALL) $(OUTPUT)libperf-gtk.so '$(DESTDIR_SQ)$(libdir_SQ)'
+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
+
+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
+  LIB_OBJS += $(OUTPUT)util/perf_regs.o
+endif
+
+ifndef NO_LIBNUMA
+  BUILTIN_OBJS += $(OUTPUT)bench/numa.o
+endif
+
+ifdef ASCIIDOC8
+  export ASCIIDOC8
+endif
+
+LIBS = -Wl,--whole-archive $(PERFLIBS) -Wl,--no-whole-archive -Wl,--start-group $(EXTLIBS) -Wl,--end-group
+
+export INSTALL SHELL_PATH
+
+### Build rules
+
+SHELL = $(SHELL_PATH)
+
+all: shell_compatibility_test $(ALL_PROGRAMS) $(LANG_BINDINGS) $(OTHER_PROGRAMS)
+
+please_set_SHELL_PATH_to_a_more_modern_shell:
+	@$$(:)
+
+shell_compatibility_test: please_set_SHELL_PATH_to_a_more_modern_shell
+
+strip: $(PROGRAMS) $(OUTPUT)perf
+	$(STRIP) $(STRIP_OPTS) $(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)"' \
+		$(CFLAGS) -c $(filter %.c,$^) -o $@
+
+$(OUTPUT)perf: $(OUTPUT)perf.o $(BUILTIN_OBJS) $(PERFLIBS)
+	$(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $(OUTPUT)perf.o \
+               $(BUILTIN_OBJS) $(LIBS) -o $@
+
+$(GTK_OBJS): $(OUTPUT)%.o: %.c $(LIB_H)
+	$(QUIET_CC)$(CC) -o $@ -c -fPIC $(CFLAGS) $(GTK_CFLAGS) $<
+
+$(OUTPUT)libperf-gtk.so: $(GTK_OBJS) $(PERFLIBS)
+	$(QUIET_LINK)$(CC) -o $@ -shared $(LDFLAGS) $(filter %.o,$^) $(GTK_LIBS)
+
+$(OUTPUT)builtin-help.o: builtin-help.c $(OUTPUT)common-cmds.h $(OUTPUT)PERF-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 $(CFLAGS) \
+		'-DPERF_HTML_PATH="$(htmldir_SQ)"' \
+		'-DPERF_MAN_PATH="$(mandir_SQ)"' \
+		'-DPERF_INFO_PATH="$(infodir_SQ)"' $<
+
+$(OUTPUT)common-cmds.h: util/generate-cmdlist.sh command-list.txt
+
+$(OUTPUT)common-cmds.h: $(wildcard Documentation/perf-*.txt)
+	$(QUIET_GEN). util/generate-cmdlist.sh > $@+ && mv $@+ $@
+
+$(SCRIPTS) : % : %.sh
+	$(QUIET_GEN)$(INSTALL) '$@.sh' '$(OUTPUT)$@'
+
+# These can record PERF_VERSION
+$(OUTPUT)perf.o perf.spec \
+	$(SCRIPTS) \
+	: $(OUTPUT)PERF-VERSION-FILE
+
+.SUFFIXES:
+
+#
+# If a target does not match any of the later rules then prefix it by $(OUTPUT)
+# This makes targets like 'make O=/tmp/perf perf.o' work in a natural way.
+#
+ifneq ($(OUTPUT),)
+%.o: $(OUTPUT)%.o
+	@echo "    # Redirected target $@ => $(OUTPUT)$@"
+util/%.o: $(OUTPUT)util/%.o
+	@echo "    # Redirected target $@ => $(OUTPUT)$@"
+bench/%.o: $(OUTPUT)bench/%.o
+	@echo "    # Redirected target $@ => $(OUTPUT)$@"
+tests/%.o: $(OUTPUT)tests/%.o
+	@echo "    # Redirected target $@ => $(OUTPUT)$@"
+endif
+
+# These two need to be here so that when O= is not used they take precedence
+# over the general rule for .o
+
+$(OUTPUT)util/%-flex.o: $(OUTPUT)util/%-flex.c $(OUTPUT)PERF-CFLAGS
+	$(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/ $(CFLAGS) -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w $<
+
+$(OUTPUT)%.o: %.c $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $<
+$(OUTPUT)%.i: %.c $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -E $(CFLAGS) $<
+$(OUTPUT)%.s: %.c $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -S $(CFLAGS) $<
+$(OUTPUT)%.o: %.S
+	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $<
+$(OUTPUT)%.s: %.S
+	$(QUIET_CC)$(CC) -o $@ -E $(CFLAGS) $<
+
+$(OUTPUT)util/exec_cmd.o: util/exec_cmd.c $(OUTPUT)PERF-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 $(CFLAGS) \
+		'-DBINDIR="$(bindir_SQ)"' -DPYTHON='"$(PYTHON_WORD)"' \
+		$<
+
+$(OUTPUT)tests/python-use.o: tests/python-use.c $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) \
+		-DPYTHONPATH='"$(OUTPUT)python"' \
+		-DPYTHON='"$(PYTHON_WORD)"' \
+		$<
+
+$(OUTPUT)tests/dwarf-unwind.o: tests/dwarf-unwind.c
+	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -fno-optimize-sibling-calls $<
+
+$(OUTPUT)util/config.o: util/config.c $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
+
+$(OUTPUT)ui/setup.o: ui/setup.c $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DLIBDIR='"$(libdir_SQ)"' $<
+
+$(OUTPUT)ui/browser.o: ui/browser.c $(OUTPUT)PERF-CFLAGS
+	$(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 $(CFLAGS) -DENABLE_SLFUTURE_CONST $<
+
+$(OUTPUT)ui/browsers/hists.o: ui/browsers/hists.c $(OUTPUT)PERF-CFLAGS
+	$(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 $(CFLAGS) -DENABLE_SLFUTURE_CONST $<
+
+$(OUTPUT)ui/browsers/scripts.o: ui/browsers/scripts.c $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DENABLE_SLFUTURE_CONST $<
+
+$(OUTPUT)util/kallsyms.o: ../lib/symbol/kallsyms.c $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $<
+
+$(OUTPUT)util/rbtree.o: ../../lib/rbtree.c $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-unused-parameter -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
+
+$(OUTPUT)util/parse-events.o: util/parse-events.c $(OUTPUT)PERF-CFLAGS
+	$(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 $(CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-undef -Wno-switch-default $<
+
+$(OUTPUT)scripts/perl/Perf-Trace-Util/Context.o: scripts/perl/Perf-Trace-Util/Context.c $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs -Wno-undef -Wno-switch-default $<
+
+$(OUTPUT)util/scripting-engines/trace-event-python.o: util/scripting-engines/trace-event-python.c $(OUTPUT)PERF-CFLAGS
+	$(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 $(CFLAGS) $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs $<
+
+$(OUTPUT)perf-%: %.o $(PERFLIBS)
+	$(QUIET_LINK)$(CC) $(CFLAGS) -o $@ $(LDFLAGS) $(filter %.o,$^) $(LIBS)
+
+$(LIB_OBJS) $(BUILTIN_OBJS): $(LIB_H)
+$(patsubst perf-%,%.o,$(PROGRAMS)): $(LIB_H) $(wildcard */*.h)
+
+# we compile into subdirectories. if the target directory is not the source directory, they might not exists. So
+# we depend the various files onto their directories.
+DIRECTORY_DEPS = $(LIB_OBJS) $(BUILTIN_OBJS) $(GTK_OBJS)
+DIRECTORY_DEPS += $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h
+# no need to add flex objects, because they depend on bison ones
+DIRECTORY_DEPS += $(OUTPUT)util/parse-events-bison.c
+DIRECTORY_DEPS += $(OUTPUT)util/pmu-bison.c
+
+OUTPUT_DIRECTORIES := $(sort $(dir $(DIRECTORY_DEPS)))
+
+$(DIRECTORY_DEPS): | $(OUTPUT_DIRECTORIES)
+# In the second step, we make a rule to actually create these directories
+$(OUTPUT_DIRECTORIES):
+	$(QUIET_MKDIR)$(MKDIR) -p $@ 2>/dev/null
+
+$(LIB_FILE): $(LIB_OBJS)
+	$(QUIET_AR)$(RM) $@ && $(AR) rcs $@ $(LIB_OBJS)
+
+# libtraceevent.a
+TE_SOURCES = $(wildcard $(TRACE_EVENT_DIR)*.[ch])
+
+LIBTRACEEVENT_FLAGS  = $(QUIET_SUBDIR1) O=$(OUTPUT)
+LIBTRACEEVENT_FLAGS += CFLAGS="-g -Wall $(EXTRA_CFLAGS)"
+LIBTRACEEVENT_FLAGS += plugin_dir=$(plugindir_SQ)
+
+$(LIBTRACEEVENT): $(TE_SOURCES) $(OUTPUT)PERF-CFLAGS
+	$(QUIET_SUBDIR0)$(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) libtraceevent.a plugins
+
+$(LIBTRACEEVENT)-clean:
+	$(call QUIET_CLEAN, libtraceevent)
+	@$(MAKE) -C $(TRACE_EVENT_DIR) O=$(OUTPUT) clean >/dev/null
+
+install-traceevent-plugins: $(LIBTRACEEVENT)
+	$(QUIET_SUBDIR0)$(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) install_plugins
+
+LIBAPIKFS_SOURCES = $(wildcard $(LIB_PATH)fs/*.[ch])
+
+# if subdir is set, we've been called from above so target has been built
+# already
+$(LIBAPIKFS): $(LIBAPIKFS_SOURCES)
+ifeq ($(subdir),)
+	$(QUIET_SUBDIR0)$(LIB_DIR) $(QUIET_SUBDIR1) O=$(OUTPUT) libapikfs.a
+endif
+
+$(LIBAPIKFS)-clean:
+ifeq ($(subdir),)
+	$(call QUIET_CLEAN, libapikfs)
+	@$(MAKE) -C $(LIB_DIR) O=$(OUTPUT) clean >/dev/null
+endif
+
+help:
+	@echo 'Perf make targets:'
+	@echo '  doc		- make *all* documentation (see below)'
+	@echo '  man		- make manpage documentation (access with man <foo>)'
+	@echo '  html		- make html documentation'
+	@echo '  info		- make GNU info documentation (access with info <foo>)'
+	@echo '  pdf		- make pdf documentation'
+	@echo '  TAGS		- use etags to make tag information for source browsing'
+	@echo '  tags		- use ctags to make tag information for source browsing'
+	@echo '  cscope	- use cscope to make interactive browsing database'
+	@echo ''
+	@echo 'Perf install targets:'
+	@echo '  NOTE: documentation build requires asciidoc, xmlto packages to be installed'
+	@echo '  HINT: use "prefix" or "DESTDIR" to install to a particular'
+	@echo '        path like "make prefix=/usr/local install install-doc"'
+	@echo '  install	- install compiled binaries'
+	@echo '  install-doc	- install *all* documentation'
+	@echo '  install-man	- install manpage documentation'
+	@echo '  install-html	- install html documentation'
+	@echo '  install-info	- install GNU info documentation'
+	@echo '  install-pdf	- install pdf documentation'
+	@echo ''
+	@echo '  quick-install-doc	- alias for quick-install-man'
+	@echo '  quick-install-man	- install the documentation quickly'
+	@echo '  quick-install-html	- install the html documentation quickly'
+	@echo ''
+	@echo 'Perf maintainer targets:'
+	@echo '  clean			- clean all binary objects and build output'
+
+
+DOC_TARGETS := doc man html info pdf
+
+INSTALL_DOC_TARGETS := $(patsubst %,install-%,$(DOC_TARGETS)) try-install-man
+INSTALL_DOC_TARGETS += quick-install-doc quick-install-man quick-install-html
+
+# 'make doc' should call 'make -C Documentation all'
+$(DOC_TARGETS):
+	$(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) $(@:doc=all)
+
+TAG_FOLDERS= . ../lib/traceevent ../lib/api ../lib/symbol
+TAG_FILES= ../../include/uapi/linux/perf_event.h
+
+TAGS:
+	$(QUIET_GEN)$(RM) TAGS; \
+	$(FIND) $(TAG_FOLDERS) -name '*.[hcS]' -print | xargs etags -a $(TAG_FILES)
+
+tags:
+	$(QUIET_GEN)$(RM) tags; \
+	$(FIND) $(TAG_FOLDERS) -name '*.[hcS]' -print | xargs ctags -a $(TAG_FILES)
+
+cscope:
+	$(QUIET_GEN)$(RM) cscope*; \
+	$(FIND) $(TAG_FOLDERS) -name '*.[hcS]' -print | xargs cscope -b $(TAG_FILES)
+
+### Detect prefix changes
+TRACK_CFLAGS = $(subst ','\'',$(CFLAGS)):\
+             $(bindir_SQ):$(perfexecdir_SQ):$(template_dir_SQ):$(prefix_SQ):$(plugindir_SQ)
+
+$(OUTPUT)PERF-CFLAGS: .FORCE-PERF-CFLAGS
+	@FLAGS='$(TRACK_CFLAGS)'; \
+	    if test x"$$FLAGS" != x"`cat $(OUTPUT)PERF-CFLAGS 2>/dev/null`" ; then \
+		echo 1>&2 "  FLAGS:   * new build flags or prefix"; \
+		echo "$$FLAGS" >$(OUTPUT)PERF-CFLAGS; \
+            fi
+
+### Testing rules
+
+# GNU make supports exporting all variables by "export" without parameters.
+# However, the environment gets quite big, and some programs have problems
+# with that.
+
+check: $(OUTPUT)common-cmds.h
+	if sparse; \
+	then \
+		for i in *.c */*.c; \
+		do \
+			sparse $(CFLAGS) $(SPARSE_FLAGS) $$i || exit; \
+		done; \
+	else \
+		exit 1; \
+	fi
+
+### Installation rules
+
+install-gtk:
+
+install-bin: all install-gtk
+	$(call QUIET_INSTALL, binaries) \
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(bindir_SQ)'; \
+		$(INSTALL) $(OUTPUT)perf '$(DESTDIR_SQ)$(bindir_SQ)'; \
+		$(LN) '$(DESTDIR_SQ)$(bindir_SQ)/perf' '$(DESTDIR_SQ)$(bindir_SQ)/trace'
+	$(call QUIET_INSTALL, libexec) \
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
+	$(call QUIET_INSTALL, perf-archive) \
+		$(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
+ifndef NO_LIBPERL
+	$(call QUIET_INSTALL, perl-scripts) \
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace'; \
+		$(INSTALL) scripts/perl/Perf-Trace-Util/lib/Perf/Trace/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace'; \
+		$(INSTALL) scripts/perl/*.pl -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl'; \
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/bin'; \
+		$(INSTALL) scripts/perl/bin/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/bin'
+endif
+ifndef NO_LIBPYTHON
+	$(call QUIET_INSTALL, python-scripts) \
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/Perf-Trace-Util/lib/Perf/Trace'; \
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/bin'; \
+		$(INSTALL) scripts/python/Perf-Trace-Util/lib/Perf/Trace/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/Perf-Trace-Util/lib/Perf/Trace'; \
+		$(INSTALL) scripts/python/*.py -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python'; \
+		$(INSTALL) scripts/python/bin/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/bin'
+endif
+	$(call QUIET_INSTALL, perf_completion-script) \
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d'; \
+		$(INSTALL) perf-completion.sh '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d/perf'
+	$(call QUIET_INSTALL, tests) \
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \
+		$(INSTALL) tests/attr.py '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'; \
+		$(INSTALL) tests/attr/* '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'
+
+install: install-bin try-install-man install-traceevent-plugins
+
+install-python_ext:
+	$(PYTHON_WORD) util/setup.py --quiet install --root='/$(DESTDIR_SQ)'
+
+# 'make install-doc' should call 'make -C Documentation install'
+$(INSTALL_DOC_TARGETS):
+	$(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) $(@:-doc=)
+
+### Cleaning rules
+
+#
+# This is here, not in config/Makefile, because config/Makefile does
+# not get included for the clean target:
+#
+config-clean:
+	$(call QUIET_CLEAN, config)
+	@$(MAKE) -C config/feature-checks clean >/dev/null
+
+clean: $(LIBTRACEEVENT)-clean $(LIBAPIKFS)-clean config-clean
+	$(call QUIET_CLEAN, core-objs)  $(RM) $(LIB_OBJS) $(BUILTIN_OBJS) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf.o $(LANG_BINDINGS) $(GTK_OBJS)
+	$(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf
+	$(call QUIET_CLEAN, core-gen)   $(RM)  *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)PERF-CFLAGS $(OUTPUT)PERF-FEATURES $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex*
+	$(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean
+	$(python-clean)
+
+#
+# Trick: if ../../.git does not exist - we are building out of tree for example,
+# then force version regeneration:
+#
+ifeq ($(wildcard ../../.git/HEAD),)
+    GIT-HEAD-PHONY = ../../.git/HEAD
+else
+    GIT-HEAD-PHONY =
+endif
+
+.PHONY: all install clean config-clean strip install-gtk
+.PHONY: shell_compatibility_test please_set_SHELL_PATH_to_a_more_modern_shell
+.PHONY: $(GIT-HEAD-PHONY) TAGS tags cscope .FORCE-PERF-CFLAGS
+
diff --git a/tools/perf/arch/arm/Makefile b/tools/perf/arch/arm/Makefile
new file mode 100644
index 00000000000..09d62153d38
--- /dev/null
+++ b/tools/perf/arch/arm/Makefile
@@ -0,0 +1,14 @@
+ifndef NO_DWARF
+PERF_HAVE_DWARF_REGS := 1
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o
+endif
+ifndef NO_LIBUNWIND
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind-libunwind.o
+endif
+ifndef NO_LIBDW_DWARF_UNWIND
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind-libdw.o
+endif
+ifndef NO_DWARF_UNWIND
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/tests/regs_load.o
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/tests/dwarf-unwind.o
+endif
diff --git a/tools/perf/arch/arm/include/perf_regs.h b/tools/perf/arch/arm/include/perf_regs.h
new file mode 100644
index 00000000000..f619c9c5a4b
--- /dev/null
+++ b/tools/perf/arch/arm/include/perf_regs.h
@@ -0,0 +1,59 @@
+#ifndef ARCH_PERF_REGS_H
+#define ARCH_PERF_REGS_H
+
+#include <stdlib.h>
+#include <linux/types.h>
+#include <asm/perf_regs.h>
+
+void perf_regs_load(u64 *regs);
+
+#define PERF_REGS_MASK	((1ULL << PERF_REG_ARM_MAX) - 1)
+#define PERF_REGS_MAX	PERF_REG_ARM_MAX
+#define PERF_SAMPLE_REGS_ABI	PERF_SAMPLE_REGS_ABI_32
+
+#define PERF_REG_IP	PERF_REG_ARM_PC
+#define PERF_REG_SP	PERF_REG_ARM_SP
+
+static inline const char *perf_reg_name(int id)
+{
+	switch (id) {
+	case PERF_REG_ARM_R0:
+		return "r0";
+	case PERF_REG_ARM_R1:
+		return "r1";
+	case PERF_REG_ARM_R2:
+		return "r2";
+	case PERF_REG_ARM_R3:
+		return "r3";
+	case PERF_REG_ARM_R4:
+		return "r4";
+	case PERF_REG_ARM_R5:
+		return "r5";
+	case PERF_REG_ARM_R6:
+		return "r6";
+	case PERF_REG_ARM_R7:
+		return "r7";
+	case PERF_REG_ARM_R8:
+		return "r8";
+	case PERF_REG_ARM_R9:
+		return "r9";
+	case PERF_REG_ARM_R10:
+		return "r10";
+	case PERF_REG_ARM_FP:
+		return "fp";
+	case PERF_REG_ARM_IP:
+		return "ip";
+	case PERF_REG_ARM_SP:
+		return "sp";
+	case PERF_REG_ARM_LR:
+		return "lr";
+	case PERF_REG_ARM_PC:
+		return "pc";
+	default:
+		return NULL;
+	}
+
+	return NULL;
+}
+
+#endif /* ARCH_PERF_REGS_H */
diff --git a/tools/perf/arch/arm/tests/dwarf-unwind.c b/tools/perf/arch/arm/tests/dwarf-unwind.c
new file mode 100644
index 00000000000..9f870d27cb3
--- /dev/null
+++ b/tools/perf/arch/arm/tests/dwarf-unwind.c
@@ -0,0 +1,60 @@
+#include <string.h>
+#include "perf_regs.h"
+#include "thread.h"
+#include "map.h"
+#include "event.h"
+#include "tests/tests.h"
+
+#define STACK_SIZE 8192
+
+static int sample_ustack(struct perf_sample *sample,
+			 struct thread *thread, u64 *regs)
+{
+	struct stack_dump *stack = &sample->user_stack;
+	struct map *map;
+	unsigned long sp;
+	u64 stack_size, *buf;
+
+	buf = malloc(STACK_SIZE);
+	if (!buf) {
+		pr_debug("failed to allocate sample uregs data\n");
+		return -1;
+	}
+
+	sp = (unsigned long) regs[PERF_REG_ARM_SP];
+
+	map = map_groups__find(thread->mg, MAP__VARIABLE, (u64) sp);
+	if (!map) {
+		pr_debug("failed to get stack map\n");
+		free(buf);
+		return -1;
+	}
+
+	stack_size = map->end - sp;
+	stack_size = stack_size > STACK_SIZE ? STACK_SIZE : stack_size;
+
+	memcpy(buf, (void *) sp, stack_size);
+	stack->data = (char *) buf;
+	stack->size = stack_size;
+	return 0;
+}
+
+int test__arch_unwind_sample(struct perf_sample *sample,
+			     struct thread *thread)
+{
+	struct regs_dump *regs = &sample->user_regs;
+	u64 *buf;
+
+	buf = calloc(1, sizeof(u64) * PERF_REGS_MAX);
+	if (!buf) {
+		pr_debug("failed to allocate sample uregs data\n");
+		return -1;
+	}
+
+	perf_regs_load(buf);
+	regs->abi  = PERF_SAMPLE_REGS_ABI;
+	regs->regs = buf;
+	regs->mask = PERF_REGS_MASK;
+
+	return sample_ustack(sample, thread, buf);
+}
diff --git a/tools/perf/arch/arm/tests/regs_load.S b/tools/perf/arch/arm/tests/regs_load.S
new file mode 100644
index 00000000000..e09e983946f
--- /dev/null
+++ b/tools/perf/arch/arm/tests/regs_load.S
@@ -0,0 +1,58 @@
+#include <linux/linkage.h>
+
+#define R0 0x00
+#define R1 0x08
+#define R2 0x10
+#define R3 0x18
+#define R4 0x20
+#define R5 0x28
+#define R6 0x30
+#define R7 0x38
+#define R8 0x40
+#define R9 0x48
+#define SL 0x50
+#define FP 0x58
+#define IP 0x60
+#define SP 0x68
+#define LR 0x70
+#define PC 0x78
+
+/*
+ * Implementation of void perf_regs_load(u64 *regs);
+ *
+ * This functions fills in the 'regs' buffer from the actual registers values,
+ * in the way the perf built-in unwinding test expects them:
+ * - the PC at the time at the call to this function. Since this function
+ *   is called using a bl instruction, the PC value is taken from LR.
+ * The built-in unwinding test then unwinds the call stack from the dwarf
+ * information in unwind__get_entries.
+ *
+ * Notes:
+ * - the 8 bytes stride in the registers offsets comes from the fact
+ * that the registers are stored in an u64 array (u64 *regs),
+ * - the regs buffer needs to be zeroed before the call to this function,
+ * in this case using a calloc in dwarf-unwind.c.
+ */
+
+.text
+.type perf_regs_load,%function
+ENTRY(perf_regs_load)
+	str r0, [r0, #R0]
+	str r1, [r0, #R1]
+	str r2, [r0, #R2]
+	str r3, [r0, #R3]
+	str r4, [r0, #R4]
+	str r5, [r0, #R5]
+	str r6, [r0, #R6]
+	str r7, [r0, #R7]
+	str r8, [r0, #R8]
+	str r9, [r0, #R9]
+	str sl, [r0, #SL]
+	str fp, [r0, #FP]
+	str ip, [r0, #IP]
+	str sp, [r0, #SP]
+	str lr, [r0, #LR]
+	str lr, [r0, #PC]	// store pc as lr in order to skip the call
+	                        //  to this function
+	mov pc, lr
+ENDPROC(perf_regs_load)
diff --git a/tools/perf/arch/arm/util/dwarf-regs.c b/tools/perf/arch/arm/util/dwarf-regs.c
new file mode 100644
index 00000000000..33ec5b339da
--- /dev/null
+++ b/tools/perf/arch/arm/util/dwarf-regs.c
@@ -0,0 +1,64 @@
+/*
+ * Mapping of DWARF debug register numbers into register names.
+ *
+ * Copyright (C) 2010 Will Deacon, ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <stddef.h>
+#include <dwarf-regs.h>
+
+struct pt_regs_dwarfnum {
+	const char *name;
+	unsigned int dwarfnum;
+};
+
+#define STR(s) #s
+#define REG_DWARFNUM_NAME(r, num) {.name = r, .dwarfnum = num}
+#define GPR_DWARFNUM_NAME(num) \
+	{.name = STR(%r##num), .dwarfnum = num}
+#define REG_DWARFNUM_END {.name = NULL, .dwarfnum = 0}
+
+/*
+ * Reference:
+ * http://infocenter.arm.com/help/topic/com.arm.doc.ihi0040a/IHI0040A_aadwarf.pdf
+ */
+static const struct pt_regs_dwarfnum regdwarfnum_table[] = {
+	GPR_DWARFNUM_NAME(0),
+	GPR_DWARFNUM_NAME(1),
+	GPR_DWARFNUM_NAME(2),
+	GPR_DWARFNUM_NAME(3),
+	GPR_DWARFNUM_NAME(4),
+	GPR_DWARFNUM_NAME(5),
+	GPR_DWARFNUM_NAME(6),
+	GPR_DWARFNUM_NAME(7),
+	GPR_DWARFNUM_NAME(8),
+	GPR_DWARFNUM_NAME(9),
+	GPR_DWARFNUM_NAME(10),
+	REG_DWARFNUM_NAME("%fp", 11),
+	REG_DWARFNUM_NAME("%ip", 12),
+	REG_DWARFNUM_NAME("%sp", 13),
+	REG_DWARFNUM_NAME("%lr", 14),
+	REG_DWARFNUM_NAME("%pc", 15),
+	REG_DWARFNUM_END,
+};
+
+/**
+ * get_arch_regstr() - lookup register name from it's DWARF register number
+ * @n:	the DWARF register number
+ *
+ * get_arch_regstr() returns the name of the register in struct
+ * regdwarfnum_table from it's DWARF register number. If the register is not
+ * found in the table, this returns NULL;
+ */
+const char *get_arch_regstr(unsigned int n)
+{
+	const struct pt_regs_dwarfnum *roff;
+	for (roff = regdwarfnum_table; roff->name != NULL; roff++)
+		if (roff->dwarfnum == n)
+			return roff->name;
+	return NULL;
+}
diff --git a/tools/perf/arch/arm/util/unwind-libdw.c b/tools/perf/arch/arm/util/unwind-libdw.c
new file mode 100644
index 00000000000..b4176c60117
--- /dev/null
+++ b/tools/perf/arch/arm/util/unwind-libdw.c
@@ -0,0 +1,36 @@
+#include <elfutils/libdwfl.h>
+#include "../../util/unwind-libdw.h"
+#include "../../util/perf_regs.h"
+
+bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg)
+{
+	struct unwind_info *ui = arg;
+	struct regs_dump *user_regs = &ui->sample->user_regs;
+	Dwarf_Word dwarf_regs[PERF_REG_ARM_MAX];
+
+#define REG(r) ({						\
+	Dwarf_Word val = 0;					\
+	perf_reg_value(&val, user_regs, PERF_REG_ARM_##r);	\
+	val;							\
+})
+
+	dwarf_regs[0]  = REG(R0);
+	dwarf_regs[1]  = REG(R1);
+	dwarf_regs[2]  = REG(R2);
+	dwarf_regs[3]  = REG(R3);
+	dwarf_regs[4]  = REG(R4);
+	dwarf_regs[5]  = REG(R5);
+	dwarf_regs[6]  = REG(R6);
+	dwarf_regs[7]  = REG(R7);
+	dwarf_regs[8]  = REG(R8);
+	dwarf_regs[9]  = REG(R9);
+	dwarf_regs[10] = REG(R10);
+	dwarf_regs[11] = REG(FP);
+	dwarf_regs[12] = REG(IP);
+	dwarf_regs[13] = REG(SP);
+	dwarf_regs[14] = REG(LR);
+	dwarf_regs[15] = REG(PC);
+
+	return dwfl_thread_state_registers(thread, 0, PERF_REG_ARM_MAX,
+					   dwarf_regs);
+}
diff --git a/tools/perf/arch/arm/util/unwind-libunwind.c b/tools/perf/arch/arm/util/unwind-libunwind.c
new file mode 100644
index 00000000000..729ed69a666
--- /dev/null
+++ b/tools/perf/arch/arm/util/unwind-libunwind.c
@@ -0,0 +1,48 @@
+
+#include <errno.h>
+#include <libunwind.h>
+#include "perf_regs.h"
+#include "../../util/unwind.h"
+
+int libunwind__arch_reg_id(int regnum)
+{
+	switch (regnum) {
+	case UNW_ARM_R0:
+		return PERF_REG_ARM_R0;
+	case UNW_ARM_R1:
+		return PERF_REG_ARM_R1;
+	case UNW_ARM_R2:
+		return PERF_REG_ARM_R2;
+	case UNW_ARM_R3:
+		return PERF_REG_ARM_R3;
+	case UNW_ARM_R4:
+		return PERF_REG_ARM_R4;
+	case UNW_ARM_R5:
+		return PERF_REG_ARM_R5;
+	case UNW_ARM_R6:
+		return PERF_REG_ARM_R6;
+	case UNW_ARM_R7:
+		return PERF_REG_ARM_R7;
+	case UNW_ARM_R8:
+		return PERF_REG_ARM_R8;
+	case UNW_ARM_R9:
+		return PERF_REG_ARM_R9;
+	case UNW_ARM_R10:
+		return PERF_REG_ARM_R10;
+	case UNW_ARM_R11:
+		return PERF_REG_ARM_FP;
+	case UNW_ARM_R12:
+		return PERF_REG_ARM_IP;
+	case UNW_ARM_R13:
+		return PERF_REG_ARM_SP;
+	case UNW_ARM_R14:
+		return PERF_REG_ARM_LR;
+	case UNW_ARM_R15:
+		return PERF_REG_ARM_PC;
+	default:
+		pr_err("unwind: invalid reg id %d\n", regnum);
+		return -EINVAL;
+	}
+
+	return -EINVAL;
+}
diff --git a/tools/perf/arch/arm64/Makefile b/tools/perf/arch/arm64/Makefile
new file mode 100644
index 00000000000..67e9b3d38e8
--- /dev/null
+++ b/tools/perf/arch/arm64/Makefile
@@ -0,0 +1,7 @@
+ifndef NO_DWARF
+PERF_HAVE_DWARF_REGS := 1
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o
+endif
+ifndef NO_LIBUNWIND
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind-libunwind.o
+endif
diff --git a/tools/perf/arch/arm64/include/perf_regs.h b/tools/perf/arch/arm64/include/perf_regs.h
new file mode 100644
index 00000000000..e9441b9e2a3
--- /dev/null
+++ b/tools/perf/arch/arm64/include/perf_regs.h
@@ -0,0 +1,88 @@
+#ifndef ARCH_PERF_REGS_H
+#define ARCH_PERF_REGS_H
+
+#include <stdlib.h>
+#include <linux/types.h>
+#include <asm/perf_regs.h>
+
+#define PERF_REGS_MASK	((1ULL << PERF_REG_ARM64_MAX) - 1)
+#define PERF_REG_IP	PERF_REG_ARM64_PC
+#define PERF_REG_SP	PERF_REG_ARM64_SP
+
+static inline const char *perf_reg_name(int id)
+{
+	switch (id) {
+	case PERF_REG_ARM64_X0:
+		return "x0";
+	case PERF_REG_ARM64_X1:
+		return "x1";
+	case PERF_REG_ARM64_X2:
+		return "x2";
+	case PERF_REG_ARM64_X3:
+		return "x3";
+	case PERF_REG_ARM64_X4:
+		return "x4";
+	case PERF_REG_ARM64_X5:
+		return "x5";
+	case PERF_REG_ARM64_X6:
+		return "x6";
+	case PERF_REG_ARM64_X7:
+		return "x7";
+	case PERF_REG_ARM64_X8:
+		return "x8";
+	case PERF_REG_ARM64_X9:
+		return "x9";
+	case PERF_REG_ARM64_X10:
+		return "x10";
+	case PERF_REG_ARM64_X11:
+		return "x11";
+	case PERF_REG_ARM64_X12:
+		return "x12";
+	case PERF_REG_ARM64_X13:
+		return "x13";
+	case PERF_REG_ARM64_X14:
+		return "x14";
+	case PERF_REG_ARM64_X15:
+		return "x15";
+	case PERF_REG_ARM64_X16:
+		return "x16";
+	case PERF_REG_ARM64_X17:
+		return "x17";
+	case PERF_REG_ARM64_X18:
+		return "x18";
+	case PERF_REG_ARM64_X19:
+		return "x19";
+	case PERF_REG_ARM64_X20:
+		return "x20";
+	case PERF_REG_ARM64_X21:
+		return "x21";
+	case PERF_REG_ARM64_X22:
+		return "x22";
+	case PERF_REG_ARM64_X23:
+		return "x23";
+	case PERF_REG_ARM64_X24:
+		return "x24";
+	case PERF_REG_ARM64_X25:
+		return "x25";
+	case PERF_REG_ARM64_X26:
+		return "x26";
+	case PERF_REG_ARM64_X27:
+		return "x27";
+	case PERF_REG_ARM64_X28:
+		return "x28";
+	case PERF_REG_ARM64_X29:
+		return "x29";
+	case PERF_REG_ARM64_SP:
+		return "sp";
+	case PERF_REG_ARM64_LR:
+		return "lr";
+	case PERF_REG_ARM64_PC:
+		return "pc";
+	default:
+		return NULL;
+	}
+
+	return NULL;
+}
+
+#endif /* ARCH_PERF_REGS_H */
diff --git a/tools/perf/arch/arm64/util/dwarf-regs.c b/tools/perf/arch/arm64/util/dwarf-regs.c
new file mode 100644
index 00000000000..d49efeb8172
--- /dev/null
+++ b/tools/perf/arch/arm64/util/dwarf-regs.c
@@ -0,0 +1,80 @@
+/*
+ * Mapping of DWARF debug register numbers into register names.
+ *
+ * Copyright (C) 2010 Will Deacon, ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <stddef.h>
+#include <dwarf-regs.h>
+
+struct pt_regs_dwarfnum {
+	const char *name;
+	unsigned int dwarfnum;
+};
+
+#define STR(s) #s
+#define REG_DWARFNUM_NAME(r, num) {.name = r, .dwarfnum = num}
+#define GPR_DWARFNUM_NAME(num) \
+	{.name = STR(%x##num), .dwarfnum = num}
+#define REG_DWARFNUM_END {.name = NULL, .dwarfnum = 0}
+
+/*
+ * Reference:
+ * http://infocenter.arm.com/help/topic/com.arm.doc.ihi0057b/IHI0057B_aadwarf64.pdf
+ */
+static const struct pt_regs_dwarfnum regdwarfnum_table[] = {
+	GPR_DWARFNUM_NAME(0),
+	GPR_DWARFNUM_NAME(1),
+	GPR_DWARFNUM_NAME(2),
+	GPR_DWARFNUM_NAME(3),
+	GPR_DWARFNUM_NAME(4),
+	GPR_DWARFNUM_NAME(5),
+	GPR_DWARFNUM_NAME(6),
+	GPR_DWARFNUM_NAME(7),
+	GPR_DWARFNUM_NAME(8),
+	GPR_DWARFNUM_NAME(9),
+	GPR_DWARFNUM_NAME(10),
+	GPR_DWARFNUM_NAME(11),
+	GPR_DWARFNUM_NAME(12),
+	GPR_DWARFNUM_NAME(13),
+	GPR_DWARFNUM_NAME(14),
+	GPR_DWARFNUM_NAME(15),
+	GPR_DWARFNUM_NAME(16),
+	GPR_DWARFNUM_NAME(17),
+	GPR_DWARFNUM_NAME(18),
+	GPR_DWARFNUM_NAME(19),
+	GPR_DWARFNUM_NAME(20),
+	GPR_DWARFNUM_NAME(21),
+	GPR_DWARFNUM_NAME(22),
+	GPR_DWARFNUM_NAME(23),
+	GPR_DWARFNUM_NAME(24),
+	GPR_DWARFNUM_NAME(25),
+	GPR_DWARFNUM_NAME(26),
+	GPR_DWARFNUM_NAME(27),
+	GPR_DWARFNUM_NAME(28),
+	GPR_DWARFNUM_NAME(29),
+	REG_DWARFNUM_NAME("%lr", 30),
+	REG_DWARFNUM_NAME("%sp", 31),
+	REG_DWARFNUM_END,
+};
+
+/**
+ * get_arch_regstr() - lookup register name from it's DWARF register number
+ * @n:	the DWARF register number
+ *
+ * get_arch_regstr() returns the name of the register in struct
+ * regdwarfnum_table from it's DWARF register number. If the register is not
+ * found in the table, this returns NULL;
+ */
+const char *get_arch_regstr(unsigned int n)
+{
+	const struct pt_regs_dwarfnum *roff;
+	for (roff = regdwarfnum_table; roff->name != NULL; roff++)
+		if (roff->dwarfnum == n)
+			return roff->name;
+	return NULL;
+}
diff --git a/tools/perf/arch/arm64/util/unwind-libunwind.c b/tools/perf/arch/arm64/util/unwind-libunwind.c
new file mode 100644
index 00000000000..436ee43859d
--- /dev/null
+++ b/tools/perf/arch/arm64/util/unwind-libunwind.c
@@ -0,0 +1,82 @@
+
+#include <errno.h>
+#include <libunwind.h>
+#include "perf_regs.h"
+#include "../../util/unwind.h"
+
+int libunwind__arch_reg_id(int regnum)
+{
+	switch (regnum) {
+	case UNW_AARCH64_X0:
+		return PERF_REG_ARM64_X0;
+	case UNW_AARCH64_X1:
+		return PERF_REG_ARM64_X1;
+	case UNW_AARCH64_X2:
+		return PERF_REG_ARM64_X2;
+	case UNW_AARCH64_X3:
+		return PERF_REG_ARM64_X3;
+	case UNW_AARCH64_X4:
+		return PERF_REG_ARM64_X4;
+	case UNW_AARCH64_X5:
+		return PERF_REG_ARM64_X5;
+	case UNW_AARCH64_X6:
+		return PERF_REG_ARM64_X6;
+	case UNW_AARCH64_X7:
+		return PERF_REG_ARM64_X7;
+	case UNW_AARCH64_X8:
+		return PERF_REG_ARM64_X8;
+	case UNW_AARCH64_X9:
+		return PERF_REG_ARM64_X9;
+	case UNW_AARCH64_X10:
+		return PERF_REG_ARM64_X10;
+	case UNW_AARCH64_X11:
+		return PERF_REG_ARM64_X11;
+	case UNW_AARCH64_X12:
+		return PERF_REG_ARM64_X12;
+	case UNW_AARCH64_X13:
+		return PERF_REG_ARM64_X13;
+	case UNW_AARCH64_X14:
+		return PERF_REG_ARM64_X14;
+	case UNW_AARCH64_X15:
+		return PERF_REG_ARM64_X15;
+	case UNW_AARCH64_X16:
+		return PERF_REG_ARM64_X16;
+	case UNW_AARCH64_X17:
+		return PERF_REG_ARM64_X17;
+	case UNW_AARCH64_X18:
+		return PERF_REG_ARM64_X18;
+	case UNW_AARCH64_X19:
+		return PERF_REG_ARM64_X19;
+	case UNW_AARCH64_X20:
+		return PERF_REG_ARM64_X20;
+	case UNW_AARCH64_X21:
+		return PERF_REG_ARM64_X21;
+	case UNW_AARCH64_X22:
+		return PERF_REG_ARM64_X22;
+	case UNW_AARCH64_X23:
+		return PERF_REG_ARM64_X23;
+	case UNW_AARCH64_X24:
+		return PERF_REG_ARM64_X24;
+	case UNW_AARCH64_X25:
+		return PERF_REG_ARM64_X25;
+	case UNW_AARCH64_X26:
+		return PERF_REG_ARM64_X26;
+	case UNW_AARCH64_X27:
+		return PERF_REG_ARM64_X27;
+	case UNW_AARCH64_X28:
+		return PERF_REG_ARM64_X28;
+	case UNW_AARCH64_X29:
+		return PERF_REG_ARM64_X29;
+	case UNW_AARCH64_X30:
+		return PERF_REG_ARM64_LR;
+	case UNW_AARCH64_SP:
+		return PERF_REG_ARM64_SP;
+	case UNW_AARCH64_PC:
+		return PERF_REG_ARM64_PC;
+	default:
+		pr_err("unwind: invalid reg id %d\n", regnum);
+		return -EINVAL;
+	}
+
+	return -EINVAL;
+}
diff --git a/tools/perf/arch/common.c b/tools/perf/arch/common.c
new file mode 100644
index 00000000000..42faf369211
--- /dev/null
+++ b/tools/perf/arch/common.c
@@ -0,0 +1,211 @@
+#include <stdio.h>
+#include <sys/utsname.h>
+#include "common.h"
+#include "../util/debug.h"
+
+const char *const arm_triplets[] = {
+	"arm-eabi-",
+	"arm-linux-androideabi-",
+	"arm-unknown-linux-",
+	"arm-unknown-linux-gnu-",
+	"arm-unknown-linux-gnueabi-",
+	NULL
+};
+
+const char *const powerpc_triplets[] = {
+	"powerpc-unknown-linux-gnu-",
+	"powerpc64-unknown-linux-gnu-",
+	NULL
+};
+
+const char *const s390_triplets[] = {
+	"s390-ibm-linux-",
+	NULL
+};
+
+const char *const sh_triplets[] = {
+	"sh-unknown-linux-gnu-",
+	"sh64-unknown-linux-gnu-",
+	NULL
+};
+
+const char *const sparc_triplets[] = {
+	"sparc-unknown-linux-gnu-",
+	"sparc64-unknown-linux-gnu-",
+	NULL
+};
+
+const char *const x86_triplets[] = {
+	"x86_64-pc-linux-gnu-",
+	"x86_64-unknown-linux-gnu-",
+	"i686-pc-linux-gnu-",
+	"i586-pc-linux-gnu-",
+	"i486-pc-linux-gnu-",
+	"i386-pc-linux-gnu-",
+	"i686-linux-android-",
+	"i686-android-linux-",
+	NULL
+};
+
+const char *const mips_triplets[] = {
+	"mips-unknown-linux-gnu-",
+	"mipsel-linux-android-",
+	NULL
+};
+
+static bool lookup_path(char *name)
+{
+	bool found = false;
+	char *path, *tmp;
+	char buf[PATH_MAX];
+	char *env = getenv("PATH");
+
+	if (!env)
+		return false;
+
+	env = strdup(env);
+	if (!env)
+		return false;
+
+	path = strtok_r(env, ":", &tmp);
+	while (path) {
+		scnprintf(buf, sizeof(buf), "%s/%s", path, name);
+		if (access(buf, F_OK) == 0) {
+			found = true;
+			break;
+		}
+		path = strtok_r(NULL, ":", &tmp);
+	}
+	free(env);
+	return found;
+}
+
+static int lookup_triplets(const char *const *triplets, const char *name)
+{
+	int i;
+	char buf[PATH_MAX];
+
+	for (i = 0; triplets[i] != NULL; i++) {
+		scnprintf(buf, sizeof(buf), "%s%s", triplets[i], name);
+		if (lookup_path(buf))
+			return i;
+	}
+	return -1;
+}
+
+/*
+ * Return architecture name in a normalized form.
+ * The conversion logic comes from the Makefile.
+ */
+static const char *normalize_arch(char *arch)
+{
+	if (!strcmp(arch, "x86_64"))
+		return "x86";
+	if (arch[0] == 'i' && arch[2] == '8' && arch[3] == '6')
+		return "x86";
+	if (!strcmp(arch, "sun4u") || !strncmp(arch, "sparc", 5))
+		return "sparc";
+	if (!strncmp(arch, "arm", 3) || !strcmp(arch, "sa110"))
+		return "arm";
+	if (!strncmp(arch, "s390", 4))
+		return "s390";
+	if (!strncmp(arch, "parisc", 6))
+		return "parisc";
+	if (!strncmp(arch, "powerpc", 7) || !strncmp(arch, "ppc", 3))
+		return "powerpc";
+	if (!strncmp(arch, "mips", 4))
+		return "mips";
+	if (!strncmp(arch, "sh", 2) && isdigit(arch[2]))
+		return "sh";
+
+	return arch;
+}
+
+static int perf_session_env__lookup_binutils_path(struct perf_session_env *env,
+						  const char *name,
+						  const char **path)
+{
+	int idx;
+	const char *arch, *cross_env;
+	struct utsname uts;
+	const char *const *path_list;
+	char *buf = NULL;
+
+	arch = normalize_arch(env->arch);
+
+	if (uname(&uts) < 0)
+		goto out;
+
+	/*
+	 * We don't need to try to find objdump path for native system.
+	 * Just use default binutils path (e.g.: "objdump").
+	 */
+	if (!strcmp(normalize_arch(uts.machine), arch))
+		goto out;
+
+	cross_env = getenv("CROSS_COMPILE");
+	if (cross_env) {
+		if (asprintf(&buf, "%s%s", cross_env, name) < 0)
+			goto out_error;
+		if (buf[0] == '/') {
+			if (access(buf, F_OK) == 0)
+				goto out;
+			goto out_error;
+		}
+		if (lookup_path(buf))
+			goto out;
+		zfree(&buf);
+	}
+
+	if (!strcmp(arch, "arm"))
+		path_list = arm_triplets;
+	else if (!strcmp(arch, "powerpc"))
+		path_list = powerpc_triplets;
+	else if (!strcmp(arch, "sh"))
+		path_list = sh_triplets;
+	else if (!strcmp(arch, "s390"))
+		path_list = s390_triplets;
+	else if (!strcmp(arch, "sparc"))
+		path_list = sparc_triplets;
+	else if (!strcmp(arch, "x86"))
+		path_list = x86_triplets;
+	else if (!strcmp(arch, "mips"))
+		path_list = mips_triplets;
+	else {
+		ui__error("binutils for %s not supported.\n", arch);
+		goto out_error;
+	}
+
+	idx = lookup_triplets(path_list, name);
+	if (idx < 0) {
+		ui__error("Please install %s for %s.\n"
+			  "You can add it to PATH, set CROSS_COMPILE or "
+			  "override the default using --%s.\n",
+			  name, arch, name);
+		goto out_error;
+	}
+
+	if (asprintf(&buf, "%s%s", path_list[idx], name) < 0)
+		goto out_error;
+
+out:
+	*path = buf;
+	return 0;
+out_error:
+	free(buf);
+	*path = NULL;
+	return -1;
+}
+
+int perf_session_env__lookup_objdump(struct perf_session_env *env)
+{
+	/*
+	 * For live mode, env->arch will be NULL and we can use
+	 * the native objdump tool.
+	 */
+	if (env->arch == NULL)
+		return 0;
+
+	return perf_session_env__lookup_binutils_path(env, "objdump",
+						      &objdump_path);
+}
diff --git a/tools/perf/arch/common.h b/tools/perf/arch/common.h
new file mode 100644
index 00000000000..ede246eda9b
--- /dev/null
+++ b/tools/perf/arch/common.h
@@ -0,0 +1,10 @@
+#ifndef ARCH_PERF_COMMON_H
+#define ARCH_PERF_COMMON_H
+
+#include "../util/session.h"
+
+extern const char *objdump_path;
+
+int perf_session_env__lookup_objdump(struct perf_session_env *env);
+
+#endif /* ARCH_PERF_COMMON_H */
diff --git a/tools/perf/arch/powerpc/Makefile b/tools/perf/arch/powerpc/Makefile
index 15130b50dfe..744e629797b 100644
--- a/tools/perf/arch/powerpc/Makefile
+++ b/tools/perf/arch/powerpc/Makefile
@@ -2,3 +2,4 @@ ifndef NO_DWARF
 PERF_HAVE_DWARF_REGS := 1
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o
 endif
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/header.o
diff --git a/tools/perf/arch/powerpc/util/dwarf-regs.c b/tools/perf/arch/powerpc/util/dwarf-regs.c
index 48ae0c5e3f7..733151cdf46 100644
--- a/tools/perf/arch/powerpc/util/dwarf-regs.c
+++ b/tools/perf/arch/powerpc/util/dwarf-regs.c
@@ -9,7 +9,7 @@
  * 2 of the License, or (at your option) any later version.
  */
 
-#include <libio.h>
+#include <stddef.h>
 #include <dwarf-regs.h>
 
 
diff --git a/tools/perf/arch/powerpc/util/header.c b/tools/perf/arch/powerpc/util/header.c
new file mode 100644
index 00000000000..2f7073d107f
--- /dev/null
+++ b/tools/perf/arch/powerpc/util/header.c
@@ -0,0 +1,36 @@
+#include <sys/types.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include "../../util/header.h"
+
+#define __stringify_1(x)        #x
+#define __stringify(x)          __stringify_1(x)
+
+#define mfspr(rn)       ({unsigned long rval; \
+			 asm volatile("mfspr %0," __stringify(rn) \
+				      : "=r" (rval)); rval; })
+
+#define SPRN_PVR        0x11F	/* Processor Version Register */
+#define PVR_VER(pvr)    (((pvr) >>  16) & 0xFFFF) /* Version field */
+#define PVR_REV(pvr)    (((pvr) >>   0) & 0xFFFF) /* Revison field */
+
+int
+get_cpuid(char *buffer, size_t sz)
+{
+	unsigned long pvr;
+	int nb;
+
+	pvr = mfspr(SPRN_PVR);
+
+	nb = scnprintf(buffer, sz, "%lu,%lu$", PVR_VER(pvr), PVR_REV(pvr));
+
+	/* look for end marker to ensure the entire data fit */
+	if (strchr(buffer, '$')) {
+		buffer[nb-1] = '\0';
+		return 0;
+	}
+	return -1;
+}
diff --git a/tools/perf/arch/s390/Makefile b/tools/perf/arch/s390/Makefile
new file mode 100644
index 00000000000..15130b50dfe
--- /dev/null
+++ b/tools/perf/arch/s390/Makefile
@@ -0,0 +1,4 @@
+ifndef NO_DWARF
+PERF_HAVE_DWARF_REGS := 1
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o
+endif
diff --git a/tools/perf/arch/s390/util/dwarf-regs.c b/tools/perf/arch/s390/util/dwarf-regs.c
new file mode 100644
index 00000000000..0469df02ee6
--- /dev/null
+++ b/tools/perf/arch/s390/util/dwarf-regs.c
@@ -0,0 +1,22 @@
+/*
+ * Mapping of DWARF debug register numbers into register names.
+ *
+ *    Copyright IBM Corp. 2010
+ *    Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>,
+ *
+ */
+
+#include <stddef.h>
+#include <dwarf-regs.h>
+
+#define NUM_GPRS 16
+
+static const char *gpr_names[NUM_GPRS] = {
+	"%r0", "%r1",  "%r2",  "%r3",  "%r4",  "%r5",  "%r6",  "%r7",
+	"%r8", "%r9", "%r10", "%r11", "%r12", "%r13", "%r14", "%r15",
+};
+
+const char *get_arch_regstr(unsigned int n)
+{
+	return (n >= NUM_GPRS) ? NULL : gpr_names[n];
+}
diff --git a/tools/perf/arch/sh/Makefile b/tools/perf/arch/sh/Makefile
new file mode 100644
index 00000000000..15130b50dfe
--- /dev/null
+++ b/tools/perf/arch/sh/Makefile
@@ -0,0 +1,4 @@
+ifndef NO_DWARF
+PERF_HAVE_DWARF_REGS := 1
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o
+endif
diff --git a/tools/perf/arch/sh/util/dwarf-regs.c b/tools/perf/arch/sh/util/dwarf-regs.c
new file mode 100644
index 00000000000..0d0897f57a1
--- /dev/null
+++ b/tools/perf/arch/sh/util/dwarf-regs.c
@@ -0,0 +1,55 @@
+/*
+ * Mapping of DWARF debug register numbers into register names.
+ *
+ * Copyright (C) 2010 Matt Fleming <matt@console-pimps.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ */
+
+#include <stddef.h>
+#include <dwarf-regs.h>
+
+/*
+ * Generic dwarf analysis helpers
+ */
+
+#define SH_MAX_REGS 18
+const char *sh_regs_table[SH_MAX_REGS] = {
+	"r0",
+	"r1",
+	"r2",
+	"r3",
+	"r4",
+	"r5",
+	"r6",
+	"r7",
+	"r8",
+	"r9",
+	"r10",
+	"r11",
+	"r12",
+	"r13",
+	"r14",
+	"r15",
+	"pc",
+	"pr",
+};
+
+/* Return architecture dependent register string (for kprobe-tracer) */
+const char *get_arch_regstr(unsigned int n)
+{
+	return (n <= SH_MAX_REGS) ? sh_regs_table[n] : NULL;
+}
diff --git a/tools/perf/arch/sparc/Makefile b/tools/perf/arch/sparc/Makefile
new file mode 100644
index 00000000000..15130b50dfe
--- /dev/null
+++ b/tools/perf/arch/sparc/Makefile
@@ -0,0 +1,4 @@
+ifndef NO_DWARF
+PERF_HAVE_DWARF_REGS := 1
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o
+endif
diff --git a/tools/perf/arch/sparc/util/dwarf-regs.c b/tools/perf/arch/sparc/util/dwarf-regs.c
new file mode 100644
index 00000000000..92eda412fed
--- /dev/null
+++ b/tools/perf/arch/sparc/util/dwarf-regs.c
@@ -0,0 +1,43 @@
+/*
+ * Mapping of DWARF debug register numbers into register names.
+ *
+ * Copyright (C) 2010 David S. Miller <davem@davemloft.net>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <stddef.h>
+#include <dwarf-regs.h>
+
+#define SPARC_MAX_REGS	96
+
+const char *sparc_regs_table[SPARC_MAX_REGS] = {
+	"%g0", "%g1", "%g2", "%g3", "%g4", "%g5", "%g6", "%g7",
+	"%o0", "%o1", "%o2", "%o3", "%o4", "%o5", "%sp", "%o7",
+	"%l0", "%l1", "%l2", "%l3", "%l4", "%l5", "%l6", "%l7",
+	"%i0", "%i1", "%i2", "%i3", "%i4", "%i5", "%fp", "%i7",
+	"%f0", "%f1", "%f2", "%f3", "%f4", "%f5", "%f6", "%f7",
+	"%f8", "%f9", "%f10", "%f11", "%f12", "%f13", "%f14", "%f15",
+	"%f16", "%f17", "%f18", "%f19", "%f20", "%f21", "%f22", "%f23",
+	"%f24", "%f25", "%f26", "%f27", "%f28", "%f29", "%f30", "%f31",
+	"%f32", "%f33", "%f34", "%f35", "%f36", "%f37", "%f38", "%f39",
+	"%f40", "%f41", "%f42", "%f43", "%f44", "%f45", "%f46", "%f47",
+	"%f48", "%f49", "%f50", "%f51", "%f52", "%f53", "%f54", "%f55",
+	"%f56", "%f57", "%f58", "%f59", "%f60", "%f61", "%f62", "%f63",
+};
+
+/**
+ * get_arch_regstr() - lookup register name from it's DWARF register number
+ * @n:	the DWARF register number
+ *
+ * get_arch_regstr() returns the name of the register in struct
+ * regdwarfnum_table from it's DWARF register number. If the register is not
+ * found in the table, this returns NULL;
+ */
+const char *get_arch_regstr(unsigned int n)
+{
+	return (n <= SPARC_MAX_REGS) ? sparc_regs_table[n] : NULL;
+}
diff --git a/tools/perf/arch/x86/Makefile b/tools/perf/arch/x86/Makefile
index 15130b50dfe..1641542e363 100644
--- a/tools/perf/arch/x86/Makefile
+++ b/tools/perf/arch/x86/Makefile
@@ -2,3 +2,16 @@ ifndef NO_DWARF
 PERF_HAVE_DWARF_REGS := 1
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o
 endif
+ifndef NO_LIBUNWIND
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind-libunwind.o
+endif
+ifndef NO_LIBDW_DWARF_UNWIND
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind-libdw.o
+endif
+ifndef NO_DWARF_UNWIND
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/tests/regs_load.o
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/tests/dwarf-unwind.o
+endif
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/header.o
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/tsc.o
+LIB_H += arch/$(ARCH)/util/tsc.h
diff --git a/tools/perf/arch/x86/include/perf_regs.h b/tools/perf/arch/x86/include/perf_regs.h
new file mode 100644
index 00000000000..7df517acfef
--- /dev/null
+++ b/tools/perf/arch/x86/include/perf_regs.h
@@ -0,0 +1,86 @@
+#ifndef ARCH_PERF_REGS_H
+#define ARCH_PERF_REGS_H
+
+#include <stdlib.h>
+#include <linux/types.h>
+#include <asm/perf_regs.h>
+
+void perf_regs_load(u64 *regs);
+
+#ifndef HAVE_ARCH_X86_64_SUPPORT
+#define PERF_REGS_MASK ((1ULL << PERF_REG_X86_32_MAX) - 1)
+#define PERF_REGS_MAX PERF_REG_X86_32_MAX
+#define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_32
+#else
+#define REG_NOSUPPORT ((1ULL << PERF_REG_X86_DS) | \
+		       (1ULL << PERF_REG_X86_ES) | \
+		       (1ULL << PERF_REG_X86_FS) | \
+		       (1ULL << PERF_REG_X86_GS))
+#define PERF_REGS_MASK (((1ULL << PERF_REG_X86_64_MAX) - 1) & ~REG_NOSUPPORT)
+#define PERF_REGS_MAX PERF_REG_X86_64_MAX
+#define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_64
+#endif
+#define PERF_REG_IP PERF_REG_X86_IP
+#define PERF_REG_SP PERF_REG_X86_SP
+
+static inline const char *perf_reg_name(int id)
+{
+	switch (id) {
+	case PERF_REG_X86_AX:
+		return "AX";
+	case PERF_REG_X86_BX:
+		return "BX";
+	case PERF_REG_X86_CX:
+		return "CX";
+	case PERF_REG_X86_DX:
+		return "DX";
+	case PERF_REG_X86_SI:
+		return "SI";
+	case PERF_REG_X86_DI:
+		return "DI";
+	case PERF_REG_X86_BP:
+		return "BP";
+	case PERF_REG_X86_SP:
+		return "SP";
+	case PERF_REG_X86_IP:
+		return "IP";
+	case PERF_REG_X86_FLAGS:
+		return "FLAGS";
+	case PERF_REG_X86_CS:
+		return "CS";
+	case PERF_REG_X86_SS:
+		return "SS";
+	case PERF_REG_X86_DS:
+		return "DS";
+	case PERF_REG_X86_ES:
+		return "ES";
+	case PERF_REG_X86_FS:
+		return "FS";
+	case PERF_REG_X86_GS:
+		return "GS";
+#ifdef HAVE_ARCH_X86_64_SUPPORT
+	case PERF_REG_X86_R8:
+		return "R8";
+	case PERF_REG_X86_R9:
+		return "R9";
+	case PERF_REG_X86_R10:
+		return "R10";
+	case PERF_REG_X86_R11:
+		return "R11";
+	case PERF_REG_X86_R12:
+		return "R12";
+	case PERF_REG_X86_R13:
+		return "R13";
+	case PERF_REG_X86_R14:
+		return "R14";
+	case PERF_REG_X86_R15:
+		return "R15";
+#endif /* HAVE_ARCH_X86_64_SUPPORT */
+	default:
+		return NULL;
+	}
+
+	return NULL;
+}
+
+#endif /* ARCH_PERF_REGS_H */
diff --git a/tools/perf/arch/x86/tests/dwarf-unwind.c b/tools/perf/arch/x86/tests/dwarf-unwind.c
new file mode 100644
index 00000000000..9f89f899ccc
--- /dev/null
+++ b/tools/perf/arch/x86/tests/dwarf-unwind.c
@@ -0,0 +1,60 @@
+#include <string.h>
+#include "perf_regs.h"
+#include "thread.h"
+#include "map.h"
+#include "event.h"
+#include "tests/tests.h"
+
+#define STACK_SIZE 8192
+
+static int sample_ustack(struct perf_sample *sample,
+			 struct thread *thread, u64 *regs)
+{
+	struct stack_dump *stack = &sample->user_stack;
+	struct map *map;
+	unsigned long sp;
+	u64 stack_size, *buf;
+
+	buf = malloc(STACK_SIZE);
+	if (!buf) {
+		pr_debug("failed to allocate sample uregs data\n");
+		return -1;
+	}
+
+	sp = (unsigned long) regs[PERF_REG_X86_SP];
+
+	map = map_groups__find(thread->mg, MAP__VARIABLE, (u64) sp);
+	if (!map) {
+		pr_debug("failed to get stack map\n");
+		free(buf);
+		return -1;
+	}
+
+	stack_size = map->end - sp;
+	stack_size = stack_size > STACK_SIZE ? STACK_SIZE : stack_size;
+
+	memcpy(buf, (void *) sp, stack_size);
+	stack->data = (char *) buf;
+	stack->size = stack_size;
+	return 0;
+}
+
+int test__arch_unwind_sample(struct perf_sample *sample,
+			     struct thread *thread)
+{
+	struct regs_dump *regs = &sample->user_regs;
+	u64 *buf;
+
+	buf = malloc(sizeof(u64) * PERF_REGS_MAX);
+	if (!buf) {
+		pr_debug("failed to allocate sample uregs data\n");
+		return -1;
+	}
+
+	perf_regs_load(buf);
+	regs->abi  = PERF_SAMPLE_REGS_ABI;
+	regs->regs = buf;
+	regs->mask = PERF_REGS_MASK;
+
+	return sample_ustack(sample, thread, buf);
+}
diff --git a/tools/perf/arch/x86/tests/regs_load.S b/tools/perf/arch/x86/tests/regs_load.S
new file mode 100644
index 00000000000..60875d5c556
--- /dev/null
+++ b/tools/perf/arch/x86/tests/regs_load.S
@@ -0,0 +1,98 @@
+#include <linux/linkage.h>
+
+#define AX	 0
+#define BX	 1 * 8
+#define CX	 2 * 8
+#define DX	 3 * 8
+#define SI	 4 * 8
+#define DI	 5 * 8
+#define BP	 6 * 8
+#define SP	 7 * 8
+#define IP	 8 * 8
+#define FLAGS	 9 * 8
+#define CS	10 * 8
+#define SS	11 * 8
+#define DS	12 * 8
+#define ES	13 * 8
+#define FS	14 * 8
+#define GS	15 * 8
+#define R8	16 * 8
+#define R9	17 * 8
+#define R10	18 * 8
+#define R11	19 * 8
+#define R12	20 * 8
+#define R13	21 * 8
+#define R14	22 * 8
+#define R15	23 * 8
+
+.text
+#ifdef HAVE_ARCH_X86_64_SUPPORT
+ENTRY(perf_regs_load)
+	movq %rax, AX(%rdi)
+	movq %rbx, BX(%rdi)
+	movq %rcx, CX(%rdi)
+	movq %rdx, DX(%rdi)
+	movq %rsi, SI(%rdi)
+	movq %rdi, DI(%rdi)
+	movq %rbp, BP(%rdi)
+
+	leaq 8(%rsp), %rax /* exclude this call.  */
+	movq %rax, SP(%rdi)
+
+	movq 0(%rsp), %rax
+	movq %rax, IP(%rdi)
+
+	movq $0, FLAGS(%rdi)
+	movq $0, CS(%rdi)
+	movq $0, SS(%rdi)
+	movq $0, DS(%rdi)
+	movq $0, ES(%rdi)
+	movq $0, FS(%rdi)
+	movq $0, GS(%rdi)
+
+	movq %r8,  R8(%rdi)
+	movq %r9,  R9(%rdi)
+	movq %r10, R10(%rdi)
+	movq %r11, R11(%rdi)
+	movq %r12, R12(%rdi)
+	movq %r13, R13(%rdi)
+	movq %r14, R14(%rdi)
+	movq %r15, R15(%rdi)
+	ret
+ENDPROC(perf_regs_load)
+#else
+ENTRY(perf_regs_load)
+	push %edi
+	movl 8(%esp), %edi
+	movl %eax, AX(%edi)
+	movl %ebx, BX(%edi)
+	movl %ecx, CX(%edi)
+	movl %edx, DX(%edi)
+	movl %esi, SI(%edi)
+	pop %eax
+	movl %eax, DI(%edi)
+	movl %ebp, BP(%edi)
+
+	leal 4(%esp), %eax /* exclude this call.  */
+	movl %eax, SP(%edi)
+
+	movl 0(%esp), %eax
+	movl %eax, IP(%edi)
+
+	movl $0, FLAGS(%edi)
+	movl $0, CS(%edi)
+	movl $0, SS(%edi)
+	movl $0, DS(%edi)
+	movl $0, ES(%edi)
+	movl $0, FS(%edi)
+	movl $0, GS(%edi)
+	ret
+ENDPROC(perf_regs_load)
+#endif
+
+/*
+ * We need to provide note.GNU-stack section, saying that we want
+ * NOT executable stack. Otherwise the final linking will assume that
+ * the ELF stack should not be restricted at all and set it RWX.
+ */
+.section .note.GNU-stack,"",@progbits
diff --git a/tools/perf/arch/x86/util/dwarf-regs.c b/tools/perf/arch/x86/util/dwarf-regs.c
index a794d308192..be22dd46323 100644
--- a/tools/perf/arch/x86/util/dwarf-regs.c
+++ b/tools/perf/arch/x86/util/dwarf-regs.c
@@ -20,7 +20,7 @@
  *
  */
 
-#include <libio.h>
+#include <stddef.h>
 #include <dwarf-regs.h>
 
 /*
diff --git a/tools/perf/arch/x86/util/header.c b/tools/perf/arch/x86/util/header.c
new file mode 100644
index 00000000000..146d12a1cec
--- /dev/null
+++ b/tools/perf/arch/x86/util/header.c
@@ -0,0 +1,59 @@
+#include <sys/types.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include "../../util/header.h"
+
+static inline void
+cpuid(unsigned int op, unsigned int *a, unsigned int *b, unsigned int *c,
+      unsigned int *d)
+{
+	__asm__ __volatile__ (".byte 0x53\n\tcpuid\n\t"
+			      "movl %%ebx, %%esi\n\t.byte 0x5b"
+			: "=a" (*a),
+			"=S" (*b),
+			"=c" (*c),
+			"=d" (*d)
+			: "a" (op));
+}
+
+int
+get_cpuid(char *buffer, size_t sz)
+{
+	unsigned int a, b, c, d, lvl;
+	int family = -1, model = -1, step = -1;
+	int nb;
+	char vendor[16];
+
+	cpuid(0, &lvl, &b, &c, &d);
+	strncpy(&vendor[0], (char *)(&b), 4);
+	strncpy(&vendor[4], (char *)(&d), 4);
+	strncpy(&vendor[8], (char *)(&c), 4);
+	vendor[12] = '\0';
+
+	if (lvl >= 1) {
+		cpuid(1, &a, &b, &c, &d);
+
+		family = (a >> 8) & 0xf;  /* bits 11 - 8 */
+		model  = (a >> 4) & 0xf;  /* Bits  7 - 4 */
+		step   = a & 0xf;
+
+		/* extended family */
+		if (family == 0xf)
+			family += (a >> 20) & 0xff;
+
+		/* extended model */
+		if (family >= 0x6)
+			model += ((a >> 16) & 0xf) << 4;
+	}
+	nb = scnprintf(buffer, sz, "%s,%u,%u,%u$", vendor, family, model, step);
+
+	/* look for end marker to ensure the entire data fit */
+	if (strchr(buffer, '$')) {
+		buffer[nb-1] = '\0';
+		return 0;
+	}
+	return -1;
+}
diff --git a/tools/perf/arch/x86/util/tsc.c b/tools/perf/arch/x86/util/tsc.c
new file mode 100644
index 00000000000..40021fa3129
--- /dev/null
+++ b/tools/perf/arch/x86/util/tsc.c
@@ -0,0 +1,59 @@
+#include <stdbool.h>
+#include <errno.h>
+
+#include <linux/perf_event.h>
+
+#include "../../perf.h"
+#include <linux/types.h>
+#include "../../util/debug.h"
+#include "tsc.h"
+
+u64 perf_time_to_tsc(u64 ns, struct perf_tsc_conversion *tc)
+{
+	u64 t, quot, rem;
+
+	t = ns - tc->time_zero;
+	quot = t / tc->time_mult;
+	rem  = t % tc->time_mult;
+	return (quot << tc->time_shift) +
+	       (rem << tc->time_shift) / tc->time_mult;
+}
+
+u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc)
+{
+	u64 quot, rem;
+
+	quot = cyc >> tc->time_shift;
+	rem  = cyc & ((1 << tc->time_shift) - 1);
+	return tc->time_zero + quot * tc->time_mult +
+	       ((rem * tc->time_mult) >> tc->time_shift);
+}
+
+int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc,
+			     struct perf_tsc_conversion *tc)
+{
+	bool cap_user_time_zero;
+	u32 seq;
+	int i = 0;
+
+	while (1) {
+		seq = pc->lock;
+		rmb();
+		tc->time_mult = pc->time_mult;
+		tc->time_shift = pc->time_shift;
+		tc->time_zero = pc->time_zero;
+		cap_user_time_zero = pc->cap_user_time_zero;
+		rmb();
+		if (pc->lock == seq && !(seq & 1))
+			break;
+		if (++i > 10000) {
+			pr_debug("failed to get perf_event_mmap_page lock\n");
+			return -EINVAL;
+		}
+	}
+
+	if (!cap_user_time_zero)
+		return -EOPNOTSUPP;
+
+	return 0;
+}
diff --git a/tools/perf/arch/x86/util/tsc.h b/tools/perf/arch/x86/util/tsc.h
new file mode 100644
index 00000000000..2affe0366b5
--- /dev/null
+++ b/tools/perf/arch/x86/util/tsc.h
@@ -0,0 +1,20 @@
+#ifndef TOOLS_PERF_ARCH_X86_UTIL_TSC_H__
+#define TOOLS_PERF_ARCH_X86_UTIL_TSC_H__
+
+#include <linux/types.h>
+
+struct perf_tsc_conversion {
+	u16 time_shift;
+	u32 time_mult;
+	u64 time_zero;
+};
+
+struct perf_event_mmap_page;
+
+int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc,
+			     struct perf_tsc_conversion *tc);
+
+u64 perf_time_to_tsc(u64 ns, struct perf_tsc_conversion *tc);
+u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc);
+
+#endif /* TOOLS_PERF_ARCH_X86_UTIL_TSC_H__ */
diff --git a/tools/perf/arch/x86/util/unwind-libdw.c b/tools/perf/arch/x86/util/unwind-libdw.c
new file mode 100644
index 00000000000..c4b72176ca8
--- /dev/null
+++ b/tools/perf/arch/x86/util/unwind-libdw.c
@@ -0,0 +1,51 @@
+#include <elfutils/libdwfl.h>
+#include "../../util/unwind-libdw.h"
+#include "../../util/perf_regs.h"
+
+bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg)
+{
+	struct unwind_info *ui = arg;
+	struct regs_dump *user_regs = &ui->sample->user_regs;
+	Dwarf_Word dwarf_regs[17];
+	unsigned nregs;
+
+#define REG(r) ({						\
+	Dwarf_Word val = 0;					\
+	perf_reg_value(&val, user_regs, PERF_REG_X86_##r);	\
+	val;							\
+})
+
+	if (user_regs->abi == PERF_SAMPLE_REGS_ABI_32) {
+		dwarf_regs[0] = REG(AX);
+		dwarf_regs[1] = REG(CX);
+		dwarf_regs[2] = REG(DX);
+		dwarf_regs[3] = REG(BX);
+		dwarf_regs[4] = REG(SP);
+		dwarf_regs[5] = REG(BP);
+		dwarf_regs[6] = REG(SI);
+		dwarf_regs[7] = REG(DI);
+		dwarf_regs[8] = REG(IP);
+		nregs = 9;
+	} else {
+		dwarf_regs[0]  = REG(AX);
+		dwarf_regs[1]  = REG(DX);
+		dwarf_regs[2]  = REG(CX);
+		dwarf_regs[3]  = REG(BX);
+		dwarf_regs[4]  = REG(SI);
+		dwarf_regs[5]  = REG(DI);
+		dwarf_regs[6]  = REG(BP);
+		dwarf_regs[7]  = REG(SP);
+		dwarf_regs[8]  = REG(R8);
+		dwarf_regs[9]  = REG(R9);
+		dwarf_regs[10] = REG(R10);
+		dwarf_regs[11] = REG(R11);
+		dwarf_regs[12] = REG(R12);
+		dwarf_regs[13] = REG(R13);
+		dwarf_regs[14] = REG(R14);
+		dwarf_regs[15] = REG(R15);
+		dwarf_regs[16] = REG(IP);
+		nregs = 17;
+	}
+
+	return dwfl_thread_state_registers(thread, 0, nregs, dwarf_regs);
+}
diff --git a/tools/perf/arch/x86/util/unwind-libunwind.c b/tools/perf/arch/x86/util/unwind-libunwind.c
new file mode 100644
index 00000000000..3261f68c6a7
--- /dev/null
+++ b/tools/perf/arch/x86/util/unwind-libunwind.c
@@ -0,0 +1,111 @@
+
+#include <errno.h>
+#include <libunwind.h>
+#include "perf_regs.h"
+#include "../../util/unwind.h"
+
+#ifdef HAVE_ARCH_X86_64_SUPPORT
+int libunwind__arch_reg_id(int regnum)
+{
+	int id;
+
+	switch (regnum) {
+	case UNW_X86_64_RAX:
+		id = PERF_REG_X86_AX;
+		break;
+	case UNW_X86_64_RDX:
+		id = PERF_REG_X86_DX;
+		break;
+	case UNW_X86_64_RCX:
+		id = PERF_REG_X86_CX;
+		break;
+	case UNW_X86_64_RBX:
+		id = PERF_REG_X86_BX;
+		break;
+	case UNW_X86_64_RSI:
+		id = PERF_REG_X86_SI;
+		break;
+	case UNW_X86_64_RDI:
+		id = PERF_REG_X86_DI;
+		break;
+	case UNW_X86_64_RBP:
+		id = PERF_REG_X86_BP;
+		break;
+	case UNW_X86_64_RSP:
+		id = PERF_REG_X86_SP;
+		break;
+	case UNW_X86_64_R8:
+		id = PERF_REG_X86_R8;
+		break;
+	case UNW_X86_64_R9:
+		id = PERF_REG_X86_R9;
+		break;
+	case UNW_X86_64_R10:
+		id = PERF_REG_X86_R10;
+		break;
+	case UNW_X86_64_R11:
+		id = PERF_REG_X86_R11;
+		break;
+	case UNW_X86_64_R12:
+		id = PERF_REG_X86_R12;
+		break;
+	case UNW_X86_64_R13:
+		id = PERF_REG_X86_R13;
+		break;
+	case UNW_X86_64_R14:
+		id = PERF_REG_X86_R14;
+		break;
+	case UNW_X86_64_R15:
+		id = PERF_REG_X86_R15;
+		break;
+	case UNW_X86_64_RIP:
+		id = PERF_REG_X86_IP;
+		break;
+	default:
+		pr_err("unwind: invalid reg id %d\n", regnum);
+		return -EINVAL;
+	}
+
+	return id;
+}
+#else
+int libunwind__arch_reg_id(int regnum)
+{
+	int id;
+
+	switch (regnum) {
+	case UNW_X86_EAX:
+		id = PERF_REG_X86_AX;
+		break;
+	case UNW_X86_EDX:
+		id = PERF_REG_X86_DX;
+		break;
+	case UNW_X86_ECX:
+		id = PERF_REG_X86_CX;
+		break;
+	case UNW_X86_EBX:
+		id = PERF_REG_X86_BX;
+		break;
+	case UNW_X86_ESI:
+		id = PERF_REG_X86_SI;
+		break;
+	case UNW_X86_EDI:
+		id = PERF_REG_X86_DI;
+		break;
+	case UNW_X86_EBP:
+		id = PERF_REG_X86_BP;
+		break;
+	case UNW_X86_ESP:
+		id = PERF_REG_X86_SP;
+		break;
+	case UNW_X86_EIP:
+		id = PERF_REG_X86_IP;
+		break;
+	default:
+		pr_err("unwind: invalid reg id %d\n", regnum);
+		return -EINVAL;
+	}
+
+	return id;
+}
+#endif /* HAVE_ARCH_X86_64_SUPPORT */
diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h
index f7781c6267c..eba46709b27 100644
--- a/tools/perf/bench/bench.h
+++ b/tools/perf/bench/bench.h
@@ -1,9 +1,39 @@
 #ifndef BENCH_H
 #define BENCH_H
 
+/*
+ * The madvise transparent hugepage constants were added in glibc
+ * 2.13. For compatibility with older versions of glibc, define these
+ * tokens if they are not already defined.
+ *
+ * PA-RISC uses different madvise values from other architectures and
+ * needs to be special-cased.
+ */
+#ifdef __hppa__
+# ifndef MADV_HUGEPAGE
+#  define MADV_HUGEPAGE		67
+# endif
+# ifndef MADV_NOHUGEPAGE
+#  define MADV_NOHUGEPAGE	68
+# endif
+#else
+# ifndef MADV_HUGEPAGE
+#  define MADV_HUGEPAGE		14
+# endif
+# ifndef MADV_NOHUGEPAGE
+#  define MADV_NOHUGEPAGE	15
+# endif
+#endif
+
+extern int bench_numa(int argc, const char **argv, const char *prefix);
 extern int bench_sched_messaging(int argc, const char **argv, const char *prefix);
 extern int bench_sched_pipe(int argc, const char **argv, const char *prefix);
-extern int bench_mem_memcpy(int argc, const char **argv, const char *prefix __used);
+extern int bench_mem_memcpy(int argc, const char **argv,
+			    const char *prefix __maybe_unused);
+extern int bench_mem_memset(int argc, const char **argv, const char *prefix);
+extern int bench_futex_hash(int argc, const char **argv, const char *prefix);
+extern int bench_futex_wake(int argc, const char **argv, const char *prefix);
+extern int bench_futex_requeue(int argc, const char **argv, const char *prefix);
 
 #define BENCH_FORMAT_DEFAULT_STR	"default"
 #define BENCH_FORMAT_DEFAULT		0
diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c
new file mode 100644
index 00000000000..a84206e9c4a
--- /dev/null
+++ b/tools/perf/bench/futex-hash.c
@@ -0,0 +1,212 @@
+/*
+ * Copyright (C) 2013  Davidlohr Bueso <davidlohr@hp.com>
+ *
+ * futex-hash: Stress the hell out of the Linux kernel futex uaddr hashing.
+ *
+ * This program is particularly useful for measuring the kernel's futex hash
+ * table/function implementation. In order for it to make sense, use with as
+ * many threads and futexes as possible.
+ */
+
+#include "../perf.h"
+#include "../util/util.h"
+#include "../util/stat.h"
+#include "../util/parse-options.h"
+#include "../util/header.h"
+#include "bench.h"
+#include "futex.h"
+
+#include <err.h>
+#include <stdlib.h>
+#include <sys/time.h>
+#include <pthread.h>
+
+static unsigned int nthreads = 0;
+static unsigned int nsecs    = 10;
+/* amount of futexes per thread */
+static unsigned int nfutexes = 1024;
+static bool fshared = false, done = false, silent = false;
+
+struct timeval start, end, runtime;
+static pthread_mutex_t thread_lock;
+static unsigned int threads_starting;
+static struct stats throughput_stats;
+static pthread_cond_t thread_parent, thread_worker;
+
+struct worker {
+	int tid;
+	u_int32_t *futex;
+	pthread_t thread;
+	unsigned long ops;
+};
+
+static const struct option options[] = {
+	OPT_UINTEGER('t', "threads", &nthreads, "Specify amount of threads"),
+	OPT_UINTEGER('r', "runtime", &nsecs,    "Specify runtime (in seconds)"),
+	OPT_UINTEGER('f', "futexes", &nfutexes, "Specify amount of futexes per threads"),
+	OPT_BOOLEAN( 's', "silent",  &silent,   "Silent mode: do not display data/details"),
+	OPT_BOOLEAN( 'S', "shared",  &fshared,  "Use shared futexes instead of private ones"),
+	OPT_END()
+};
+
+static const char * const bench_futex_hash_usage[] = {
+	"perf bench futex hash <options>",
+	NULL
+};
+
+static void *workerfn(void *arg)
+{
+	int ret;
+	unsigned int i;
+	struct worker *w = (struct worker *) arg;
+
+	pthread_mutex_lock(&thread_lock);
+	threads_starting--;
+	if (!threads_starting)
+		pthread_cond_signal(&thread_parent);
+	pthread_cond_wait(&thread_worker, &thread_lock);
+	pthread_mutex_unlock(&thread_lock);
+
+	do {
+		for (i = 0; i < nfutexes; i++, w->ops++) {
+			/*
+			 * We want the futex calls to fail in order to stress
+			 * the hashing of uaddr and not measure other steps,
+			 * such as internal waitqueue handling, thus enlarging
+			 * the critical region protected by hb->lock.
+			 */
+			ret = futex_wait(&w->futex[i], 1234, NULL,
+					 fshared ? 0 : FUTEX_PRIVATE_FLAG);
+			if (!silent &&
+			    (!ret || errno != EAGAIN || errno != EWOULDBLOCK))
+				warn("Non-expected futex return call");
+		}
+	}  while (!done);
+
+	return NULL;
+}
+
+static void toggle_done(int sig __maybe_unused,
+			siginfo_t *info __maybe_unused,
+			void *uc __maybe_unused)
+{
+	/* inform all threads that we're done for the day */
+	done = true;
+	gettimeofday(&end, NULL);
+	timersub(&end, &start, &runtime);
+}
+
+static void print_summary(void)
+{
+	unsigned long avg = avg_stats(&throughput_stats);
+	double stddev = stddev_stats(&throughput_stats);
+
+	printf("%sAveraged %ld operations/sec (+- %.2f%%), total secs = %d\n",
+	       !silent ? "\n" : "", avg, rel_stddev_stats(stddev, avg),
+	       (int) runtime.tv_sec);
+}
+
+int bench_futex_hash(int argc, const char **argv,
+		     const char *prefix __maybe_unused)
+{
+	int ret = 0;
+	cpu_set_t cpu;
+	struct sigaction act;
+	unsigned int i, ncpus;
+	pthread_attr_t thread_attr;
+	struct worker *worker = NULL;
+
+	argc = parse_options(argc, argv, options, bench_futex_hash_usage, 0);
+	if (argc) {
+		usage_with_options(bench_futex_hash_usage, options);
+		exit(EXIT_FAILURE);
+	}
+
+	ncpus = sysconf(_SC_NPROCESSORS_ONLN);
+
+	sigfillset(&act.sa_mask);
+	act.sa_sigaction = toggle_done;
+	sigaction(SIGINT, &act, NULL);
+
+	if (!nthreads) /* default to the number of CPUs */
+		nthreads = ncpus;
+
+	worker = calloc(nthreads, sizeof(*worker));
+	if (!worker)
+		goto errmem;
+
+	printf("Run summary [PID %d]: %d threads, each operating on %d [%s] futexes for %d secs.\n\n",
+	       getpid(), nthreads, nfutexes, fshared ? "shared":"private", nsecs);
+
+	init_stats(&throughput_stats);
+	pthread_mutex_init(&thread_lock, NULL);
+	pthread_cond_init(&thread_parent, NULL);
+	pthread_cond_init(&thread_worker, NULL);
+
+	threads_starting = nthreads;
+	pthread_attr_init(&thread_attr);
+	gettimeofday(&start, NULL);
+	for (i = 0; i < nthreads; i++) {
+		worker[i].tid = i;
+		worker[i].futex = calloc(nfutexes, sizeof(*worker[i].futex));
+		if (!worker[i].futex)
+			goto errmem;
+
+		CPU_ZERO(&cpu);
+		CPU_SET(i % ncpus, &cpu);
+
+		ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpu);
+		if (ret)
+			err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
+
+		ret = pthread_create(&worker[i].thread, &thread_attr, workerfn,
+				     (void *)(struct worker *) &worker[i]);
+		if (ret)
+			err(EXIT_FAILURE, "pthread_create");
+
+	}
+	pthread_attr_destroy(&thread_attr);
+
+	pthread_mutex_lock(&thread_lock);
+	while (threads_starting)
+		pthread_cond_wait(&thread_parent, &thread_lock);
+	pthread_cond_broadcast(&thread_worker);
+	pthread_mutex_unlock(&thread_lock);
+
+	sleep(nsecs);
+	toggle_done(0, NULL, NULL);
+
+	for (i = 0; i < nthreads; i++) {
+		ret = pthread_join(worker[i].thread, NULL);
+		if (ret)
+			err(EXIT_FAILURE, "pthread_join");
+	}
+
+	/* cleanup & report results */
+	pthread_cond_destroy(&thread_parent);
+	pthread_cond_destroy(&thread_worker);
+	pthread_mutex_destroy(&thread_lock);
+
+	for (i = 0; i < nthreads; i++) {
+		unsigned long t = worker[i].ops/runtime.tv_sec;
+		update_stats(&throughput_stats, t);
+		if (!silent) {
+			if (nfutexes == 1)
+				printf("[thread %2d] futex: %p [ %ld ops/sec ]\n",
+				       worker[i].tid, &worker[i].futex[0], t);
+			else
+				printf("[thread %2d] futexes: %p ... %p [ %ld ops/sec ]\n",
+				       worker[i].tid, &worker[i].futex[0],
+				       &worker[i].futex[nfutexes-1], t);
+		}
+
+		free(worker[i].futex);
+	}
+
+	print_summary();
+
+	free(worker);
+	return ret;
+errmem:
+	err(EXIT_FAILURE, "calloc");
+}
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
new file mode 100644
index 00000000000..a16255876f1
--- /dev/null
+++ b/tools/perf/bench/futex-requeue.c
@@ -0,0 +1,211 @@
+/*
+ * Copyright (C) 2013  Davidlohr Bueso <davidlohr@hp.com>
+ *
+ * futex-requeue: Block a bunch of threads on futex1 and requeue them
+ *                on futex2, N at a time.
+ *
+ * This program is particularly useful to measure the latency of nthread
+ * requeues without waking up any tasks -- thus mimicking a regular futex_wait.
+ */
+
+#include "../perf.h"
+#include "../util/util.h"
+#include "../util/stat.h"
+#include "../util/parse-options.h"
+#include "../util/header.h"
+#include "bench.h"
+#include "futex.h"
+
+#include <err.h>
+#include <stdlib.h>
+#include <sys/time.h>
+#include <pthread.h>
+
+static u_int32_t futex1 = 0, futex2 = 0;
+
+/*
+ * How many tasks to requeue at a time.
+ * Default to 1 in order to make the kernel work more.
+ */
+static unsigned int nrequeue = 1;
+
+/*
+ * There can be significant variance from run to run,
+ * the more repeats, the more exact the overall avg and
+ * the better idea of the futex latency.
+ */
+static unsigned int repeat = 10;
+
+static pthread_t *worker;
+static bool done = 0, silent = 0;
+static pthread_mutex_t thread_lock;
+static pthread_cond_t thread_parent, thread_worker;
+static struct stats requeuetime_stats, requeued_stats;
+static unsigned int ncpus, threads_starting, nthreads = 0;
+
+static const struct option options[] = {
+	OPT_UINTEGER('t', "threads",  &nthreads, "Specify amount of threads"),
+	OPT_UINTEGER('q', "nrequeue", &nrequeue, "Specify amount of threads to requeue at once"),
+	OPT_UINTEGER('r', "repeat",   &repeat,   "Specify amount of times to repeat the run"),
+	OPT_BOOLEAN( 's', "silent",   &silent,   "Silent mode: do not display data/details"),
+	OPT_END()
+};
+
+static const char * const bench_futex_requeue_usage[] = {
+	"perf bench futex requeue <options>",
+	NULL
+};
+
+static void print_summary(void)
+{
+	double requeuetime_avg = avg_stats(&requeuetime_stats);
+	double requeuetime_stddev = stddev_stats(&requeuetime_stats);
+	unsigned int requeued_avg = avg_stats(&requeued_stats);
+
+	printf("Requeued %d of %d threads in %.4f ms (+-%.2f%%)\n",
+	       requeued_avg,
+	       nthreads,
+	       requeuetime_avg/1e3,
+	       rel_stddev_stats(requeuetime_stddev, requeuetime_avg));
+}
+
+static void *workerfn(void *arg __maybe_unused)
+{
+	pthread_mutex_lock(&thread_lock);
+	threads_starting--;
+	if (!threads_starting)
+		pthread_cond_signal(&thread_parent);
+	pthread_cond_wait(&thread_worker, &thread_lock);
+	pthread_mutex_unlock(&thread_lock);
+
+	futex_wait(&futex1, 0, NULL, FUTEX_PRIVATE_FLAG);
+	return NULL;
+}
+
+static void block_threads(pthread_t *w,
+			  pthread_attr_t thread_attr)
+{
+	cpu_set_t cpu;
+	unsigned int i;
+
+	threads_starting = nthreads;
+
+	/* create and block all threads */
+	for (i = 0; i < nthreads; i++) {
+		CPU_ZERO(&cpu);
+		CPU_SET(i % ncpus, &cpu);
+
+		if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpu))
+			err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
+
+		if (pthread_create(&w[i], &thread_attr, workerfn, NULL))
+			err(EXIT_FAILURE, "pthread_create");
+	}
+}
+
+static void toggle_done(int sig __maybe_unused,
+			siginfo_t *info __maybe_unused,
+			void *uc __maybe_unused)
+{
+	done = true;
+}
+
+int bench_futex_requeue(int argc, const char **argv,
+			const char *prefix __maybe_unused)
+{
+	int ret = 0;
+	unsigned int i, j;
+	struct sigaction act;
+	pthread_attr_t thread_attr;
+
+	argc = parse_options(argc, argv, options, bench_futex_requeue_usage, 0);
+	if (argc)
+		goto err;
+
+	ncpus = sysconf(_SC_NPROCESSORS_ONLN);
+
+	sigfillset(&act.sa_mask);
+	act.sa_sigaction = toggle_done;
+	sigaction(SIGINT, &act, NULL);
+
+	if (!nthreads)
+		nthreads = ncpus;
+
+	worker = calloc(nthreads, sizeof(*worker));
+	if (!worker)
+		err(EXIT_FAILURE, "calloc");
+
+	printf("Run summary [PID %d]: Requeuing %d threads (from %p to %p), "
+	       "%d at a time.\n\n",
+	       getpid(), nthreads, &futex1, &futex2, nrequeue);
+
+	init_stats(&requeued_stats);
+	init_stats(&requeuetime_stats);
+	pthread_attr_init(&thread_attr);
+	pthread_mutex_init(&thread_lock, NULL);
+	pthread_cond_init(&thread_parent, NULL);
+	pthread_cond_init(&thread_worker, NULL);
+
+	for (j = 0; j < repeat && !done; j++) {
+		unsigned int nrequeued = 0;
+		struct timeval start, end, runtime;
+
+		/* create, launch & block all threads */
+		block_threads(worker, thread_attr);
+
+		/* make sure all threads are already blocked */
+		pthread_mutex_lock(&thread_lock);
+		while (threads_starting)
+			pthread_cond_wait(&thread_parent, &thread_lock);
+		pthread_cond_broadcast(&thread_worker);
+		pthread_mutex_unlock(&thread_lock);
+
+		usleep(100000);
+
+		/* Ok, all threads are patiently blocked, start requeueing */
+		gettimeofday(&start, NULL);
+		for (nrequeued = 0; nrequeued < nthreads; nrequeued += nrequeue)
+			/*
+			 * Do not wakeup any tasks blocked on futex1, allowing
+			 * us to really measure futex_wait functionality.
+			 */
+			futex_cmp_requeue(&futex1, 0, &futex2, 0, nrequeue,
+					  FUTEX_PRIVATE_FLAG);
+		gettimeofday(&end, NULL);
+		timersub(&end, &start, &runtime);
+
+		update_stats(&requeued_stats, nrequeued);
+		update_stats(&requeuetime_stats, runtime.tv_usec);
+
+		if (!silent) {
+			printf("[Run %d]: Requeued %d of %d threads in %.4f ms\n",
+			       j + 1, nrequeued, nthreads, runtime.tv_usec/1e3);
+		}
+
+		/* everybody should be blocked on futex2, wake'em up */
+		nrequeued = futex_wake(&futex2, nthreads, FUTEX_PRIVATE_FLAG);
+		if (nthreads != nrequeued)
+			warnx("couldn't wakeup all tasks (%d/%d)", nrequeued, nthreads);
+
+		for (i = 0; i < nthreads; i++) {
+			ret = pthread_join(worker[i], NULL);
+			if (ret)
+				err(EXIT_FAILURE, "pthread_join");
+		}
+
+	}
+
+	/* cleanup & report results */
+	pthread_cond_destroy(&thread_parent);
+	pthread_cond_destroy(&thread_worker);
+	pthread_mutex_destroy(&thread_lock);
+	pthread_attr_destroy(&thread_attr);
+
+	print_summary();
+
+	free(worker);
+	return ret;
+err:
+	usage_with_options(bench_futex_requeue_usage, options);
+	exit(EXIT_FAILURE);
+}
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
new file mode 100644
index 00000000000..d096169b161
--- /dev/null
+++ b/tools/perf/bench/futex-wake.c
@@ -0,0 +1,201 @@
+/*
+ * Copyright (C) 2013  Davidlohr Bueso <davidlohr@hp.com>
+ *
+ * futex-wake: Block a bunch of threads on a futex and wake'em up, N at a time.
+ *
+ * This program is particularly useful to measure the latency of nthread wakeups
+ * in non-error situations:  all waiters are queued and all wake calls wakeup
+ * one or more tasks, and thus the waitqueue is never empty.
+ */
+
+#include "../perf.h"
+#include "../util/util.h"
+#include "../util/stat.h"
+#include "../util/parse-options.h"
+#include "../util/header.h"
+#include "bench.h"
+#include "futex.h"
+
+#include <err.h>
+#include <stdlib.h>
+#include <sys/time.h>
+#include <pthread.h>
+
+/* all threads will block on the same futex */
+static u_int32_t futex1 = 0;
+
+/*
+ * How many wakeups to do at a time.
+ * Default to 1 in order to make the kernel work more.
+ */
+static unsigned int nwakes = 1;
+
+/*
+ * There can be significant variance from run to run,
+ * the more repeats, the more exact the overall avg and
+ * the better idea of the futex latency.
+ */
+static unsigned int repeat = 10;
+
+pthread_t *worker;
+static bool done = 0, silent = 0;
+static pthread_mutex_t thread_lock;
+static pthread_cond_t thread_parent, thread_worker;
+static struct stats waketime_stats, wakeup_stats;
+static unsigned int ncpus, threads_starting, nthreads = 0;
+
+static const struct option options[] = {
+	OPT_UINTEGER('t', "threads", &nthreads, "Specify amount of threads"),
+	OPT_UINTEGER('w', "nwakes",  &nwakes,   "Specify amount of threads to wake at once"),
+	OPT_UINTEGER('r', "repeat",  &repeat,   "Specify amount of times to repeat the run"),
+	OPT_BOOLEAN( 's', "silent",  &silent,   "Silent mode: do not display data/details"),
+	OPT_END()
+};
+
+static const char * const bench_futex_wake_usage[] = {
+	"perf bench futex wake <options>",
+	NULL
+};
+
+static void *workerfn(void *arg __maybe_unused)
+{
+	pthread_mutex_lock(&thread_lock);
+	threads_starting--;
+	if (!threads_starting)
+		pthread_cond_signal(&thread_parent);
+	pthread_cond_wait(&thread_worker, &thread_lock);
+	pthread_mutex_unlock(&thread_lock);
+
+	futex_wait(&futex1, 0, NULL, FUTEX_PRIVATE_FLAG);
+	return NULL;
+}
+
+static void print_summary(void)
+{
+	double waketime_avg = avg_stats(&waketime_stats);
+	double waketime_stddev = stddev_stats(&waketime_stats);
+	unsigned int wakeup_avg = avg_stats(&wakeup_stats);
+
+	printf("Wokeup %d of %d threads in %.4f ms (+-%.2f%%)\n",
+	       wakeup_avg,
+	       nthreads,
+	       waketime_avg/1e3,
+	       rel_stddev_stats(waketime_stddev, waketime_avg));
+}
+
+static void block_threads(pthread_t *w,
+			  pthread_attr_t thread_attr)
+{
+	cpu_set_t cpu;
+	unsigned int i;
+
+	threads_starting = nthreads;
+
+	/* create and block all threads */
+	for (i = 0; i < nthreads; i++) {
+		CPU_ZERO(&cpu);
+		CPU_SET(i % ncpus, &cpu);
+
+		if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpu))
+			err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
+
+		if (pthread_create(&w[i], &thread_attr, workerfn, NULL))
+			err(EXIT_FAILURE, "pthread_create");
+	}
+}
+
+static void toggle_done(int sig __maybe_unused,
+			siginfo_t *info __maybe_unused,
+			void *uc __maybe_unused)
+{
+	done = true;
+}
+
+int bench_futex_wake(int argc, const char **argv,
+		     const char *prefix __maybe_unused)
+{
+	int ret = 0;
+	unsigned int i, j;
+	struct sigaction act;
+	pthread_attr_t thread_attr;
+
+	argc = parse_options(argc, argv, options, bench_futex_wake_usage, 0);
+	if (argc) {
+		usage_with_options(bench_futex_wake_usage, options);
+		exit(EXIT_FAILURE);
+	}
+
+	ncpus = sysconf(_SC_NPROCESSORS_ONLN);
+
+	sigfillset(&act.sa_mask);
+	act.sa_sigaction = toggle_done;
+	sigaction(SIGINT, &act, NULL);
+
+	if (!nthreads)
+		nthreads = ncpus;
+
+	worker = calloc(nthreads, sizeof(*worker));
+	if (!worker)
+		err(EXIT_FAILURE, "calloc");
+
+	printf("Run summary [PID %d]: blocking on %d threads (at futex %p), "
+	       "waking up %d at a time.\n\n",
+	       getpid(), nthreads, &futex1, nwakes);
+
+	init_stats(&wakeup_stats);
+	init_stats(&waketime_stats);
+	pthread_attr_init(&thread_attr);
+	pthread_mutex_init(&thread_lock, NULL);
+	pthread_cond_init(&thread_parent, NULL);
+	pthread_cond_init(&thread_worker, NULL);
+
+	for (j = 0; j < repeat && !done; j++) {
+		unsigned int nwoken = 0;
+		struct timeval start, end, runtime;
+
+		/* create, launch & block all threads */
+		block_threads(worker, thread_attr);
+
+		/* make sure all threads are already blocked */
+		pthread_mutex_lock(&thread_lock);
+		while (threads_starting)
+			pthread_cond_wait(&thread_parent, &thread_lock);
+		pthread_cond_broadcast(&thread_worker);
+		pthread_mutex_unlock(&thread_lock);
+
+		usleep(100000);
+
+		/* Ok, all threads are patiently blocked, start waking folks up */
+		gettimeofday(&start, NULL);
+		while (nwoken != nthreads)
+			nwoken += futex_wake(&futex1, nwakes, FUTEX_PRIVATE_FLAG);
+		gettimeofday(&end, NULL);
+		timersub(&end, &start, &runtime);
+
+		update_stats(&wakeup_stats, nwoken);
+		update_stats(&waketime_stats, runtime.tv_usec);
+
+		if (!silent) {
+			printf("[Run %d]: Wokeup %d of %d threads in %.4f ms\n",
+			       j + 1, nwoken, nthreads, runtime.tv_usec/1e3);
+		}
+
+		for (i = 0; i < nthreads; i++) {
+			ret = pthread_join(worker[i], NULL);
+			if (ret)
+				err(EXIT_FAILURE, "pthread_join");
+		}
+
+	}
+
+	/* cleanup & report results */
+	pthread_cond_destroy(&thread_parent);
+	pthread_cond_destroy(&thread_worker);
+	pthread_mutex_destroy(&thread_lock);
+	pthread_attr_destroy(&thread_attr);
+
+	print_summary();
+
+	free(worker);
+	return ret;
+}
diff --git a/tools/perf/bench/futex.h b/tools/perf/bench/futex.h
new file mode 100644
index 00000000000..71f2844cf97
--- /dev/null
+++ b/tools/perf/bench/futex.h
@@ -0,0 +1,71 @@
+/*
+ * Glibc independent futex library for testing kernel functionality.
+ * Shamelessly stolen from Darren Hart <dvhltc@us.ibm.com>
+ *    http://git.kernel.org/cgit/linux/kernel/git/dvhart/futextest.git/
+ */
+
+#ifndef _FUTEX_H
+#define _FUTEX_H
+
+#include <unistd.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <linux/futex.h>
+
+/**
+ * futex() - SYS_futex syscall wrapper
+ * @uaddr:	address of first futex
+ * @op:		futex op code
+ * @val:	typically expected value of uaddr, but varies by op
+ * @timeout:	typically an absolute struct timespec (except where noted
+ *		otherwise). Overloaded by some ops
+ * @uaddr2:	address of second futex for some ops\
+ * @val3:	varies by op
+ * @opflags:	flags to be bitwise OR'd with op, such as FUTEX_PRIVATE_FLAG
+ *
+ * futex() is used by all the following futex op wrappers. It can also be
+ * used for misuse and abuse testing. Generally, the specific op wrappers
+ * should be used instead. It is a macro instead of an static inline function as
+ * some of the types over overloaded (timeout is used for nr_requeue for
+ * example).
+ *
+ * These argument descriptions are the defaults for all
+ * like-named arguments in the following wrappers except where noted below.
+ */
+#define futex(uaddr, op, val, timeout, uaddr2, val3, opflags) \
+	syscall(SYS_futex, uaddr, op | opflags, val, timeout, uaddr2, val3)
+
+/**
+ * futex_wait() - block on uaddr with optional timeout
+ * @timeout:	relative timeout
+ */
+static inline int
+futex_wait(u_int32_t *uaddr, u_int32_t val, struct timespec *timeout, int opflags)
+{
+	return futex(uaddr, FUTEX_WAIT, val, timeout, NULL, 0, opflags);
+}
+
+/**
+ * futex_wake() - wake one or more tasks blocked on uaddr
+ * @nr_wake:	wake up to this many tasks
+ */
+static inline int
+futex_wake(u_int32_t *uaddr, int nr_wake, int opflags)
+{
+	return futex(uaddr, FUTEX_WAKE, nr_wake, NULL, NULL, 0, opflags);
+}
+
+/**
+* futex_cmp_requeue() - requeue tasks from uaddr to uaddr2
+* @nr_wake:        wake up to this many tasks
+* @nr_requeue:        requeue up to this many tasks
+*/
+static inline int
+futex_cmp_requeue(u_int32_t *uaddr, u_int32_t val, u_int32_t *uaddr2, int nr_wake,
+		 int nr_requeue, int opflags)
+{
+	return futex(uaddr, FUTEX_CMP_REQUEUE, nr_wake, nr_requeue, uaddr2,
+		 val, opflags);
+}
+
+#endif /* _FUTEX_H */
diff --git a/tools/perf/bench/mem-memcpy-arch.h b/tools/perf/bench/mem-memcpy-arch.h
new file mode 100644
index 00000000000..57b4ed87145
--- /dev/null
+++ b/tools/perf/bench/mem-memcpy-arch.h
@@ -0,0 +1,12 @@
+
+#ifdef HAVE_ARCH_X86_64_SUPPORT
+
+#define MEMCPY_FN(fn, name, desc)		\
+	extern void *fn(void *, const void *, size_t);
+
+#include "mem-memcpy-x86-64-asm-def.h"
+
+#undef MEMCPY_FN
+
+#endif
+
diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm-def.h b/tools/perf/bench/mem-memcpy-x86-64-asm-def.h
new file mode 100644
index 00000000000..d66ab799b35
--- /dev/null
+++ b/tools/perf/bench/mem-memcpy-x86-64-asm-def.h
@@ -0,0 +1,12 @@
+
+MEMCPY_FN(__memcpy,
+	"x86-64-unrolled",
+	"unrolled memcpy() in arch/x86/lib/memcpy_64.S")
+
+MEMCPY_FN(memcpy_c,
+	"x86-64-movsq",
+	"movsq-based memcpy() in arch/x86/lib/memcpy_64.S")
+
+MEMCPY_FN(memcpy_c_e,
+	"x86-64-movsb",
+	"movsb-based memcpy() in arch/x86/lib/memcpy_64.S")
diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S
new file mode 100644
index 00000000000..fcd9cf00600
--- /dev/null
+++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S
@@ -0,0 +1,12 @@
+#define memcpy MEMCPY /* don't hide glibc's memcpy() */
+#define altinstr_replacement text
+#define globl p2align 4; .globl
+#define Lmemcpy_c globl memcpy_c; memcpy_c
+#define Lmemcpy_c_e globl memcpy_c_e; memcpy_c_e
+#include "../../../arch/x86/lib/memcpy_64.S"
+/*
+ * We need to provide note.GNU-stack section, saying that we want
+ * NOT executable stack. Otherwise the final linking will assume that
+ * the ELF stack should not be restricted at all and set it RWX.
+ */
+.section .note.GNU-stack,"",@progbits
diff --git a/tools/perf/bench/mem-memcpy.c b/tools/perf/bench/mem-memcpy.c
index 38dae746514..5ce71d3b72c 100644
--- a/tools/perf/bench/mem-memcpy.c
+++ b/tools/perf/bench/mem-memcpy.c
@@ -5,13 +5,13 @@
  *
  * Written by Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp>
  */
-#include <ctype.h>
 
 #include "../perf.h"
 #include "../util/util.h"
 #include "../util/parse-options.h"
 #include "../util/header.h"
 #include "bench.h"
+#include "mem-memcpy-arch.h"
 
 #include <stdio.h>
 #include <stdlib.h>
@@ -23,30 +23,49 @@
 
 static const char	*length_str	= "1MB";
 static const char	*routine	= "default";
-static bool		use_clock	= false;
-static int		clock_fd;
+static int		iterations	= 1;
+static bool		use_cycle;
+static int		cycle_fd;
+static bool		only_prefault;
+static bool		no_prefault;
 
 static const struct option options[] = {
 	OPT_STRING('l', "length", &length_str, "1MB",
 		    "Specify length of memory to copy. "
-		    "available unit: B, MB, GB (upper and lower)"),
+		    "Available units: B, KB, MB, GB and TB (upper and lower)"),
 	OPT_STRING('r', "routine", &routine, "default",
 		    "Specify routine to copy"),
-	OPT_BOOLEAN('c', "clock", &use_clock,
-		    "Use CPU clock for measuring"),
+	OPT_INTEGER('i', "iterations", &iterations,
+		    "repeat memcpy() invocation this number of times"),
+	OPT_BOOLEAN('c', "cycle", &use_cycle,
+		    "Use cycles event instead of gettimeofday() for measuring"),
+	OPT_BOOLEAN('o', "only-prefault", &only_prefault,
+		    "Show only the result with page faults before memcpy()"),
+	OPT_BOOLEAN('n', "no-prefault", &no_prefault,
+		    "Show only the result without page faults before memcpy()"),
 	OPT_END()
 };
 
+typedef void *(*memcpy_t)(void *, const void *, size_t);
+
 struct routine {
 	const char *name;
 	const char *desc;
-	void * (*fn)(void *dst, const void *src, size_t len);
+	memcpy_t fn;
 };
 
 struct routine routines[] = {
 	{ "default",
 	  "Default memcpy() provided by glibc",
 	  memcpy },
+#ifdef HAVE_ARCH_X86_64_SUPPORT
+
+#define MEMCPY_FN(fn, name, desc) { name, desc, fn },
+#include "mem-memcpy-x86-64-asm-def.h"
+#undef MEMCPY_FN
+
+#endif
+
 	{ NULL,
 	  NULL,
 	  NULL   }
@@ -57,27 +76,27 @@ static const char * const bench_mem_memcpy_usage[] = {
 	NULL
 };
 
-static struct perf_event_attr clock_attr = {
+static struct perf_event_attr cycle_attr = {
 	.type		= PERF_TYPE_HARDWARE,
 	.config		= PERF_COUNT_HW_CPU_CYCLES
 };
 
-static void init_clock(void)
+static void init_cycle(void)
 {
-	clock_fd = sys_perf_event_open(&clock_attr, getpid(), -1, -1, 0);
+	cycle_fd = sys_perf_event_open(&cycle_attr, getpid(), -1, -1, 0);
 
-	if (clock_fd < 0 && errno == ENOSYS)
+	if (cycle_fd < 0 && errno == ENOSYS)
 		die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
 	else
-		BUG_ON(clock_fd < 0);
+		BUG_ON(cycle_fd < 0);
 }
 
-static u64 get_clock(void)
+static u64 get_cycle(void)
 {
 	int ret;
 	u64 clk;
 
-	ret = read(clock_fd, &clk, sizeof(u64));
+	ret = read(cycle_fd, &clk, sizeof(u64));
 	BUG_ON(ret != sizeof(u64));
 
 	return clk;
@@ -89,29 +108,104 @@ static double timeval2double(struct timeval *ts)
 		(double)ts->tv_usec / (double)1000000;
 }
 
-int bench_mem_memcpy(int argc, const char **argv,
-		     const char *prefix __used)
+static void alloc_mem(void **dst, void **src, size_t length)
+{
+	*dst = zalloc(length);
+	if (!*dst)
+		die("memory allocation failed - maybe length is too large?\n");
+
+	*src = zalloc(length);
+	if (!*src)
+		die("memory allocation failed - maybe length is too large?\n");
+	/* Make sure to always replace the zero pages even if MMAP_THRESH is crossed */
+	memset(*src, 0, length);
+}
+
+static u64 do_memcpy_cycle(memcpy_t fn, size_t len, bool prefault)
 {
+	u64 cycle_start = 0ULL, cycle_end = 0ULL;
+	void *src = NULL, *dst = NULL;
 	int i;
-	void *dst, *src;
-	size_t length;
-	double bps = 0.0;
+
+	alloc_mem(&src, &dst, len);
+
+	if (prefault)
+		fn(dst, src, len);
+
+	cycle_start = get_cycle();
+	for (i = 0; i < iterations; ++i)
+		fn(dst, src, len);
+	cycle_end = get_cycle();
+
+	free(src);
+	free(dst);
+	return cycle_end - cycle_start;
+}
+
+static double do_memcpy_gettimeofday(memcpy_t fn, size_t len, bool prefault)
+{
 	struct timeval tv_start, tv_end, tv_diff;
-	u64 clock_start, clock_end, clock_diff;
+	void *src = NULL, *dst = NULL;
+	int i;
+
+	alloc_mem(&src, &dst, len);
+
+	if (prefault)
+		fn(dst, src, len);
+
+	BUG_ON(gettimeofday(&tv_start, NULL));
+	for (i = 0; i < iterations; ++i)
+		fn(dst, src, len);
+	BUG_ON(gettimeofday(&tv_end, NULL));
+
+	timersub(&tv_end, &tv_start, &tv_diff);
+
+	free(src);
+	free(dst);
+	return (double)((double)len / timeval2double(&tv_diff));
+}
+
+#define pf (no_prefault ? 0 : 1)
+
+#define print_bps(x) do {					\
+		if (x < K)					\
+			printf(" %14lf B/Sec", x);		\
+		else if (x < K * K)				\
+			printf(" %14lfd KB/Sec", x / K);	\
+		else if (x < K * K * K)				\
+			printf(" %14lf MB/Sec", x / K / K);	\
+		else						\
+			printf(" %14lf GB/Sec", x / K / K / K); \
+	} while (0)
+
+int bench_mem_memcpy(int argc, const char **argv,
+		     const char *prefix __maybe_unused)
+{
+	int i;
+	size_t len;
+	double result_bps[2];
+	u64 result_cycle[2];
 
-	clock_start = clock_end = clock_diff = 0ULL;
 	argc = parse_options(argc, argv, options,
 			     bench_mem_memcpy_usage, 0);
 
-	tv_diff.tv_sec = 0;
-	tv_diff.tv_usec = 0;
-	length = (size_t)perf_atoll((char *)length_str);
+	if (use_cycle)
+		init_cycle();
 
-	if ((s64)length <= 0) {
+	len = (size_t)perf_atoll((char *)length_str);
+
+	result_cycle[0] = result_cycle[1] = 0ULL;
+	result_bps[0] = result_bps[1] = 0.0;
+
+	if ((s64)len <= 0) {
 		fprintf(stderr, "Invalid length:%s\n", length_str);
 		return 1;
 	}
 
+	/* same to without specifying either of prefault and no-prefault */
+	if (only_prefault && no_prefault)
+		only_prefault = no_prefault = false;
+
 	for (i = 0; routines[i].name; i++) {
 		if (!strcmp(routines[i].name, routine))
 			break;
@@ -126,61 +220,80 @@ int bench_mem_memcpy(int argc, const char **argv,
 		return 1;
 	}
 
-	dst = zalloc(length);
-	if (!dst)
-		die("memory allocation failed - maybe length is too large?\n");
-
-	src = zalloc(length);
-	if (!src)
-		die("memory allocation failed - maybe length is too large?\n");
-
-	if (bench_format == BENCH_FORMAT_DEFAULT) {
-		printf("# Copying %s Bytes from %p to %p ...\n\n",
-		       length_str, src, dst);
-	}
-
-	if (use_clock) {
-		init_clock();
-		clock_start = get_clock();
-	} else {
-		BUG_ON(gettimeofday(&tv_start, NULL));
-	}
+	if (bench_format == BENCH_FORMAT_DEFAULT)
+		printf("# Copying %s Bytes ...\n\n", length_str);
 
-	routines[i].fn(dst, src, length);
-
-	if (use_clock) {
-		clock_end = get_clock();
-		clock_diff = clock_end - clock_start;
+	if (!only_prefault && !no_prefault) {
+		/* show both of results */
+		if (use_cycle) {
+			result_cycle[0] =
+				do_memcpy_cycle(routines[i].fn, len, false);
+			result_cycle[1] =
+				do_memcpy_cycle(routines[i].fn, len, true);
+		} else {
+			result_bps[0] =
+				do_memcpy_gettimeofday(routines[i].fn,
+						len, false);
+			result_bps[1] =
+				do_memcpy_gettimeofday(routines[i].fn,
+						len, true);
+		}
 	} else {
-		BUG_ON(gettimeofday(&tv_end, NULL));
-		timersub(&tv_end, &tv_start, &tv_diff);
-		bps = (double)((double)length / timeval2double(&tv_diff));
+		if (use_cycle) {
+			result_cycle[pf] =
+				do_memcpy_cycle(routines[i].fn,
+						len, only_prefault);
+		} else {
+			result_bps[pf] =
+				do_memcpy_gettimeofday(routines[i].fn,
+						len, only_prefault);
+		}
 	}
 
 	switch (bench_format) {
 	case BENCH_FORMAT_DEFAULT:
-		if (use_clock) {
-			printf(" %14lf Clock/Byte\n",
-			       (double)clock_diff / (double)length);
-		} else {
-			if (bps < K)
-				printf(" %14lf B/Sec\n", bps);
-			else if (bps < K * K)
-				printf(" %14lfd KB/Sec\n", bps / 1024);
-			else if (bps < K * K * K)
-				printf(" %14lf MB/Sec\n", bps / 1024 / 1024);
-			else {
-				printf(" %14lf GB/Sec\n",
-				       bps / 1024 / 1024 / 1024);
+		if (!only_prefault && !no_prefault) {
+			if (use_cycle) {
+				printf(" %14lf Cycle/Byte\n",
+					(double)result_cycle[0]
+					/ (double)len);
+				printf(" %14lf Cycle/Byte (with prefault)\n",
+					(double)result_cycle[1]
+					/ (double)len);
+			} else {
+				print_bps(result_bps[0]);
+				printf("\n");
+				print_bps(result_bps[1]);
+				printf(" (with prefault)\n");
 			}
+		} else {
+			if (use_cycle) {
+				printf(" %14lf Cycle/Byte",
+					(double)result_cycle[pf]
+					/ (double)len);
+			} else
+				print_bps(result_bps[pf]);
+
+			printf("%s\n", only_prefault ? " (with prefault)" : "");
 		}
 		break;
 	case BENCH_FORMAT_SIMPLE:
-		if (use_clock) {
-			printf("%14lf\n",
-			       (double)clock_diff / (double)length);
-		} else
-			printf("%lf\n", bps);
+		if (!only_prefault && !no_prefault) {
+			if (use_cycle) {
+				printf("%lf %lf\n",
+					(double)result_cycle[0] / (double)len,
+					(double)result_cycle[1] / (double)len);
+			} else {
+				printf("%lf %lf\n",
+					result_bps[0], result_bps[1]);
+			}
+		} else {
+			if (use_cycle) {
+				printf("%lf\n", (double)result_cycle[pf]
+					/ (double)len);
+			} else
+				printf("%lf\n", result_bps[pf]);
+		}
 		break;
 	default:
 		/* reaching this means there's some disaster: */
diff --git a/tools/perf/bench/mem-memset-arch.h b/tools/perf/bench/mem-memset-arch.h
new file mode 100644
index 00000000000..633800cb0dc
--- /dev/null
+++ b/tools/perf/bench/mem-memset-arch.h
@@ -0,0 +1,12 @@
+
+#ifdef HAVE_ARCH_X86_64_SUPPORT
+
+#define MEMSET_FN(fn, name, desc)		\
+	extern void *fn(void *, int, size_t);
+
+#include "mem-memset-x86-64-asm-def.h"
+
+#undef MEMSET_FN
+
+#endif
+
diff --git a/tools/perf/bench/mem-memset-x86-64-asm-def.h b/tools/perf/bench/mem-memset-x86-64-asm-def.h
new file mode 100644
index 00000000000..a71dff97c1f
--- /dev/null
+++ b/tools/perf/bench/mem-memset-x86-64-asm-def.h
@@ -0,0 +1,12 @@
+
+MEMSET_FN(__memset,
+	"x86-64-unrolled",
+	"unrolled memset() in arch/x86/lib/memset_64.S")
+
+MEMSET_FN(memset_c,
+	"x86-64-stosq",
+	"movsq-based memset() in arch/x86/lib/memset_64.S")
+
+MEMSET_FN(memset_c_e,
+	"x86-64-stosb",
+	"movsb-based memset() in arch/x86/lib/memset_64.S")
diff --git a/tools/perf/bench/mem-memset-x86-64-asm.S b/tools/perf/bench/mem-memset-x86-64-asm.S
new file mode 100644
index 00000000000..9e5af89ed13
--- /dev/null
+++ b/tools/perf/bench/mem-memset-x86-64-asm.S
@@ -0,0 +1,13 @@
+#define memset MEMSET /* don't hide glibc's memset() */
+#define altinstr_replacement text
+#define globl p2align 4; .globl
+#define Lmemset_c globl memset_c; memset_c
+#define Lmemset_c_e globl memset_c_e; memset_c_e
+#include "../../../arch/x86/lib/memset_64.S"
+
+/*
+ * We need to provide note.GNU-stack section, saying that we want
+ * NOT executable stack. Otherwise the final linking will assume that
+ * the ELF stack should not be restricted at all and set it RWX.
+ */
+.section .note.GNU-stack,"",@progbits
diff --git a/tools/perf/bench/mem-memset.c b/tools/perf/bench/mem-memset.c
new file mode 100644
index 00000000000..9af79d2b18e
--- /dev/null
+++ b/tools/perf/bench/mem-memset.c
@@ -0,0 +1,297 @@
+/*
+ * mem-memset.c
+ *
+ * memset: Simple memory set in various ways
+ *
+ * Trivial clone of mem-memcpy.c.
+ */
+
+#include "../perf.h"
+#include "../util/util.h"
+#include "../util/parse-options.h"
+#include "../util/header.h"
+#include "bench.h"
+#include "mem-memset-arch.h"
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/time.h>
+#include <errno.h>
+
+#define K 1024
+
+static const char	*length_str	= "1MB";
+static const char	*routine	= "default";
+static int		iterations	= 1;
+static bool		use_cycle;
+static int		cycle_fd;
+static bool		only_prefault;
+static bool		no_prefault;
+
+static const struct option options[] = {
+	OPT_STRING('l', "length", &length_str, "1MB",
+		    "Specify length of memory to set. "
+		    "Available units: B, KB, MB, GB and TB (upper and lower)"),
+	OPT_STRING('r', "routine", &routine, "default",
+		    "Specify routine to set"),
+	OPT_INTEGER('i', "iterations", &iterations,
+		    "repeat memset() invocation this number of times"),
+	OPT_BOOLEAN('c', "cycle", &use_cycle,
+		    "Use cycles event instead of gettimeofday() for measuring"),
+	OPT_BOOLEAN('o', "only-prefault", &only_prefault,
+		    "Show only the result with page faults before memset()"),
+	OPT_BOOLEAN('n', "no-prefault", &no_prefault,
+		    "Show only the result without page faults before memset()"),
+	OPT_END()
+};
+
+typedef void *(*memset_t)(void *, int, size_t);
+
+struct routine {
+	const char *name;
+	const char *desc;
+	memset_t fn;
+};
+
+static const struct routine routines[] = {
+	{ "default",
+	  "Default memset() provided by glibc",
+	  memset },
+#ifdef HAVE_ARCH_X86_64_SUPPORT
+
+#define MEMSET_FN(fn, name, desc) { name, desc, fn },
+#include "mem-memset-x86-64-asm-def.h"
+#undef MEMSET_FN
+
+#endif
+
+	{ NULL,
+	  NULL,
+	  NULL   }
+};
+
+static const char * const bench_mem_memset_usage[] = {
+	"perf bench mem memset <options>",
+	NULL
+};
+
+static struct perf_event_attr cycle_attr = {
+	.type		= PERF_TYPE_HARDWARE,
+	.config		= PERF_COUNT_HW_CPU_CYCLES
+};
+
+static void init_cycle(void)
+{
+	cycle_fd = sys_perf_event_open(&cycle_attr, getpid(), -1, -1, 0);
+
+	if (cycle_fd < 0 && errno == ENOSYS)
+		die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
+	else
+		BUG_ON(cycle_fd < 0);
+}
+
+static u64 get_cycle(void)
+{
+	int ret;
+	u64 clk;
+
+	ret = read(cycle_fd, &clk, sizeof(u64));
+	BUG_ON(ret != sizeof(u64));
+
+	return clk;
+}
+
+static double timeval2double(struct timeval *ts)
+{
+	return (double)ts->tv_sec +
+		(double)ts->tv_usec / (double)1000000;
+}
+
+static void alloc_mem(void **dst, size_t length)
+{
+	*dst = zalloc(length);
+	if (!*dst)
+		die("memory allocation failed - maybe length is too large?\n");
+}
+
+static u64 do_memset_cycle(memset_t fn, size_t len, bool prefault)
+{
+	u64 cycle_start = 0ULL, cycle_end = 0ULL;
+	void *dst = NULL;
+	int i;
+
+	alloc_mem(&dst, len);
+
+	if (prefault)
+		fn(dst, -1, len);
+
+	cycle_start = get_cycle();
+	for (i = 0; i < iterations; ++i)
+		fn(dst, i, len);
+	cycle_end = get_cycle();
+
+	free(dst);
+	return cycle_end - cycle_start;
+}
+
+static double do_memset_gettimeofday(memset_t fn, size_t len, bool prefault)
+{
+	struct timeval tv_start, tv_end, tv_diff;
+	void *dst = NULL;
+	int i;
+
+	alloc_mem(&dst, len);
+
+	if (prefault)
+		fn(dst, -1, len);
+
+	BUG_ON(gettimeofday(&tv_start, NULL));
+	for (i = 0; i < iterations; ++i)
+		fn(dst, i, len);
+	BUG_ON(gettimeofday(&tv_end, NULL));
+
+	timersub(&tv_end, &tv_start, &tv_diff);
+
+	free(dst);
+	return (double)((double)len / timeval2double(&tv_diff));
+}
+
+#define pf (no_prefault ? 0 : 1)
+
+#define print_bps(x) do {					\
+		if (x < K)					\
+			printf(" %14lf B/Sec", x);		\
+		else if (x < K * K)				\
+			printf(" %14lfd KB/Sec", x / K);	\
+		else if (x < K * K * K)				\
+			printf(" %14lf MB/Sec", x / K / K);	\
+		else						\
+			printf(" %14lf GB/Sec", x / K / K / K); \
+	} while (0)
+
+int bench_mem_memset(int argc, const char **argv,
+		     const char *prefix __maybe_unused)
+{
+	int i;
+	size_t len;
+	double result_bps[2];
+	u64 result_cycle[2];
+
+	argc = parse_options(argc, argv, options,
+			     bench_mem_memset_usage, 0);
+
+	if (use_cycle)
+		init_cycle();
+
+	len = (size_t)perf_atoll((char *)length_str);
+
+	result_cycle[0] = result_cycle[1] = 0ULL;
+	result_bps[0] = result_bps[1] = 0.0;
+
+	if ((s64)len <= 0) {
+		fprintf(stderr, "Invalid length:%s\n", length_str);
+		return 1;
+	}
+
+	/* same to without specifying either of prefault and no-prefault */
+	if (only_prefault && no_prefault)
+		only_prefault = no_prefault = false;
+
+	for (i = 0; routines[i].name; i++) {
+		if (!strcmp(routines[i].name, routine))
+			break;
+	}
+	if (!routines[i].name) {
+		printf("Unknown routine:%s\n", routine);
+		printf("Available routines...\n");
+		for (i = 0; routines[i].name; i++) {
+			printf("\t%s ... %s\n",
+			       routines[i].name, routines[i].desc);
+		}
+		return 1;
+	}
+
+	if (bench_format == BENCH_FORMAT_DEFAULT)
+		printf("# Copying %s Bytes ...\n\n", length_str);
+
+	if (!only_prefault && !no_prefault) {
+		/* show both of results */
+		if (use_cycle) {
+			result_cycle[0] =
+				do_memset_cycle(routines[i].fn, len, false);
+			result_cycle[1] =
+				do_memset_cycle(routines[i].fn, len, true);
+		} else {
+			result_bps[0] =
+				do_memset_gettimeofday(routines[i].fn,
+						len, false);
+			result_bps[1] =
+				do_memset_gettimeofday(routines[i].fn,
+						len, true);
+		}
+	} else {
+		if (use_cycle) {
+			result_cycle[pf] =
+				do_memset_cycle(routines[i].fn,
+						len, only_prefault);
+		} else {
+			result_bps[pf] =
+				do_memset_gettimeofday(routines[i].fn,
+						len, only_prefault);
+		}
+	}
+
+	switch (bench_format) {
+	case BENCH_FORMAT_DEFAULT:
+		if (!only_prefault && !no_prefault) {
+			if (use_cycle) {
+				printf(" %14lf Cycle/Byte\n",
+					(double)result_cycle[0]
+					/ (double)len);
+				printf(" %14lf Cycle/Byte (with prefault)\n ",
+					(double)result_cycle[1]
+					/ (double)len);
+			} else {
+				print_bps(result_bps[0]);
+				printf("\n");
+				print_bps(result_bps[1]);
+				printf(" (with prefault)\n");
+			}
+		} else {
+			if (use_cycle) {
+				printf(" %14lf Cycle/Byte",
+					(double)result_cycle[pf]
+					/ (double)len);
+			} else
+				print_bps(result_bps[pf]);
+
+			printf("%s\n", only_prefault ? " (with prefault)" : "");
+		}
+		break;
+	case BENCH_FORMAT_SIMPLE:
+		if (!only_prefault && !no_prefault) {
+			if (use_cycle) {
+				printf("%lf %lf\n",
+					(double)result_cycle[0] / (double)len,
+					(double)result_cycle[1] / (double)len);
+			} else {
+				printf("%lf %lf\n",
+					result_bps[0], result_bps[1]);
+			}
+		} else {
+			if (use_cycle) {
+				printf("%lf\n", (double)result_cycle[pf]
+					/ (double)len);
+			} else
+				printf("%lf\n", result_bps[pf]);
+		}
+		break;
+	default:
+		/* reaching this means there's some disaster: */
+		die("unknown format: %d\n", bench_format);
+		break;
+	}
+
+	return 0;
+}
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
new file mode 100644
index 00000000000..ebfa163b80b
--- /dev/null
+++ b/tools/perf/bench/numa.c
@@ -0,0 +1,1744 @@
+/*
+ * numa.c
+ *
+ * numa: Simulate NUMA-sensitive workload and measure their NUMA performance
+ */
+
+#include "../perf.h"
+#include "../builtin.h"
+#include "../util/util.h"
+#include "../util/parse-options.h"
+
+#include "bench.h"
+
+#include <errno.h>
+#include <sched.h>
+#include <stdio.h>
+#include <assert.h>
+#include <malloc.h>
+#include <signal.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <pthread.h>
+#include <sys/mman.h>
+#include <sys/time.h>
+#include <sys/wait.h>
+#include <sys/prctl.h>
+#include <sys/types.h>
+
+#include <numa.h>
+#include <numaif.h>
+
+/*
+ * Regular printout to the terminal, supressed if -q is specified:
+ */
+#define tprintf(x...) do { if (g && g->p.show_details >= 0) printf(x); } while (0)
+
+/*
+ * Debug printf:
+ */
+#define dprintf(x...) do { if (g && g->p.show_details >= 1) printf(x); } while (0)
+
+struct thread_data {
+	int			curr_cpu;
+	cpu_set_t		bind_cpumask;
+	int			bind_node;
+	u8			*process_data;
+	int			process_nr;
+	int			thread_nr;
+	int			task_nr;
+	unsigned int		loops_done;
+	u64			val;
+	u64			runtime_ns;
+	pthread_mutex_t		*process_lock;
+};
+
+/* Parameters set by options: */
+
+struct params {
+	/* Startup synchronization: */
+	bool			serialize_startup;
+
+	/* Task hierarchy: */
+	int			nr_proc;
+	int			nr_threads;
+
+	/* Working set sizes: */
+	const char		*mb_global_str;
+	const char		*mb_proc_str;
+	const char		*mb_proc_locked_str;
+	const char		*mb_thread_str;
+
+	double			mb_global;
+	double			mb_proc;
+	double			mb_proc_locked;
+	double			mb_thread;
+
+	/* Access patterns to the working set: */
+	bool			data_reads;
+	bool			data_writes;
+	bool			data_backwards;
+	bool			data_zero_memset;
+	bool			data_rand_walk;
+	u32			nr_loops;
+	u32			nr_secs;
+	u32			sleep_usecs;
+
+	/* Working set initialization: */
+	bool			init_zero;
+	bool			init_random;
+	bool			init_cpu0;
+
+	/* Misc options: */
+	int			show_details;
+	int			run_all;
+	int			thp;
+
+	long			bytes_global;
+	long			bytes_process;
+	long			bytes_process_locked;
+	long			bytes_thread;
+
+	int			nr_tasks;
+	bool			show_quiet;
+
+	bool			show_convergence;
+	bool			measure_convergence;
+
+	int			perturb_secs;
+	int			nr_cpus;
+	int			nr_nodes;
+
+	/* Affinity options -C and -N: */
+	char			*cpu_list_str;
+	char			*node_list_str;
+};
+
+
+/* Global, read-writable area, accessible to all processes and threads: */
+
+struct global_info {
+	u8			*data;
+
+	pthread_mutex_t		startup_mutex;
+	int			nr_tasks_started;
+
+	pthread_mutex_t		startup_done_mutex;
+
+	pthread_mutex_t		start_work_mutex;
+	int			nr_tasks_working;
+
+	pthread_mutex_t		stop_work_mutex;
+	u64			bytes_done;
+
+	struct thread_data	*threads;
+
+	/* Convergence latency measurement: */
+	bool			all_converged;
+	bool			stop_work;
+
+	int			print_once;
+
+	struct params		p;
+};
+
+static struct global_info	*g = NULL;
+
+static int parse_cpus_opt(const struct option *opt, const char *arg, int unset);
+static int parse_nodes_opt(const struct option *opt, const char *arg, int unset);
+
+struct params p0;
+
+static const struct option options[] = {
+	OPT_INTEGER('p', "nr_proc"	, &p0.nr_proc,		"number of processes"),
+	OPT_INTEGER('t', "nr_threads"	, &p0.nr_threads,	"number of threads per process"),
+
+	OPT_STRING('G', "mb_global"	, &p0.mb_global_str,	"MB", "global  memory (MBs)"),
+	OPT_STRING('P', "mb_proc"	, &p0.mb_proc_str,	"MB", "process memory (MBs)"),
+	OPT_STRING('L', "mb_proc_locked", &p0.mb_proc_locked_str,"MB", "process serialized/locked memory access (MBs), <= process_memory"),
+	OPT_STRING('T', "mb_thread"	, &p0.mb_thread_str,	"MB", "thread  memory (MBs)"),
+
+	OPT_UINTEGER('l', "nr_loops"	, &p0.nr_loops,		"max number of loops to run"),
+	OPT_UINTEGER('s', "nr_secs"	, &p0.nr_secs,		"max number of seconds to run"),
+	OPT_UINTEGER('u', "usleep"	, &p0.sleep_usecs,	"usecs to sleep per loop iteration"),
+
+	OPT_BOOLEAN('R', "data_reads"	, &p0.data_reads,	"access the data via writes (can be mixed with -W)"),
+	OPT_BOOLEAN('W', "data_writes"	, &p0.data_writes,	"access the data via writes (can be mixed with -R)"),
+	OPT_BOOLEAN('B', "data_backwards", &p0.data_backwards,	"access the data backwards as well"),
+	OPT_BOOLEAN('Z', "data_zero_memset", &p0.data_zero_memset,"access the data via glibc bzero only"),
+	OPT_BOOLEAN('r', "data_rand_walk", &p0.data_rand_walk,	"access the data with random (32bit LFSR) walk"),
+
+
+	OPT_BOOLEAN('z', "init_zero"	, &p0.init_zero,	"bzero the initial allocations"),
+	OPT_BOOLEAN('I', "init_random"	, &p0.init_random,	"randomize the contents of the initial allocations"),
+	OPT_BOOLEAN('0', "init_cpu0"	, &p0.init_cpu0,	"do the initial allocations on CPU#0"),
+	OPT_INTEGER('x', "perturb_secs", &p0.perturb_secs,	"perturb thread 0/0 every X secs, to test convergence stability"),
+
+	OPT_INCR   ('d', "show_details"	, &p0.show_details,	"Show details"),
+	OPT_INCR   ('a', "all"		, &p0.run_all,		"Run all tests in the suite"),
+	OPT_INTEGER('H', "thp"		, &p0.thp,		"MADV_NOHUGEPAGE < 0 < MADV_HUGEPAGE"),
+	OPT_BOOLEAN('c', "show_convergence", &p0.show_convergence, "show convergence details"),
+	OPT_BOOLEAN('m', "measure_convergence",	&p0.measure_convergence, "measure convergence latency"),
+	OPT_BOOLEAN('q', "quiet"	, &p0.show_quiet,	"bzero the initial allocations"),
+	OPT_BOOLEAN('S', "serialize-startup", &p0.serialize_startup,"serialize thread startup"),
+
+	/* Special option string parsing callbacks: */
+        OPT_CALLBACK('C', "cpus", NULL, "cpu[,cpu2,...cpuN]",
+			"bind the first N tasks to these specific cpus (the rest is unbound)",
+			parse_cpus_opt),
+        OPT_CALLBACK('M', "memnodes", NULL, "node[,node2,...nodeN]",
+			"bind the first N tasks to these specific memory nodes (the rest is unbound)",
+			parse_nodes_opt),
+	OPT_END()
+};
+
+static const char * const bench_numa_usage[] = {
+	"perf bench numa <options>",
+	NULL
+};
+
+static const char * const numa_usage[] = {
+	"perf bench numa mem [<options>]",
+	NULL
+};
+
+static cpu_set_t bind_to_cpu(int target_cpu)
+{
+	cpu_set_t orig_mask, mask;
+	int ret;
+
+	ret = sched_getaffinity(0, sizeof(orig_mask), &orig_mask);
+	BUG_ON(ret);
+
+	CPU_ZERO(&mask);
+
+	if (target_cpu == -1) {
+		int cpu;
+
+		for (cpu = 0; cpu < g->p.nr_cpus; cpu++)
+			CPU_SET(cpu, &mask);
+	} else {
+		BUG_ON(target_cpu < 0 || target_cpu >= g->p.nr_cpus);
+		CPU_SET(target_cpu, &mask);
+	}
+
+	ret = sched_setaffinity(0, sizeof(mask), &mask);
+	BUG_ON(ret);
+
+	return orig_mask;
+}
+
+static cpu_set_t bind_to_node(int target_node)
+{
+	int cpus_per_node = g->p.nr_cpus/g->p.nr_nodes;
+	cpu_set_t orig_mask, mask;
+	int cpu;
+	int ret;
+
+	BUG_ON(cpus_per_node*g->p.nr_nodes != g->p.nr_cpus);
+	BUG_ON(!cpus_per_node);
+
+	ret = sched_getaffinity(0, sizeof(orig_mask), &orig_mask);
+	BUG_ON(ret);
+
+	CPU_ZERO(&mask);
+
+	if (target_node == -1) {
+		for (cpu = 0; cpu < g->p.nr_cpus; cpu++)
+			CPU_SET(cpu, &mask);
+	} else {
+		int cpu_start = (target_node + 0) * cpus_per_node;
+		int cpu_stop  = (target_node + 1) * cpus_per_node;
+
+		BUG_ON(cpu_stop > g->p.nr_cpus);
+
+		for (cpu = cpu_start; cpu < cpu_stop; cpu++)
+			CPU_SET(cpu, &mask);
+	}
+
+	ret = sched_setaffinity(0, sizeof(mask), &mask);
+	BUG_ON(ret);
+
+	return orig_mask;
+}
+
+static void bind_to_cpumask(cpu_set_t mask)
+{
+	int ret;
+
+	ret = sched_setaffinity(0, sizeof(mask), &mask);
+	BUG_ON(ret);
+}
+
+static void mempol_restore(void)
+{
+	int ret;
+
+	ret = set_mempolicy(MPOL_DEFAULT, NULL, g->p.nr_nodes-1);
+
+	BUG_ON(ret);
+}
+
+static void bind_to_memnode(int node)
+{
+	unsigned long nodemask;
+	int ret;
+
+	if (node == -1)
+		return;
+
+	BUG_ON(g->p.nr_nodes > (int)sizeof(nodemask));
+	nodemask = 1L << node;
+
+	ret = set_mempolicy(MPOL_BIND, &nodemask, sizeof(nodemask)*8);
+	dprintf("binding to node %d, mask: %016lx => %d\n", node, nodemask, ret);
+
+	BUG_ON(ret);
+}
+
+#define HPSIZE (2*1024*1024)
+
+#define set_taskname(fmt...)				\
+do {							\
+	char name[20];					\
+							\
+	snprintf(name, 20, fmt);			\
+	prctl(PR_SET_NAME, name);			\
+} while (0)
+
+static u8 *alloc_data(ssize_t bytes0, int map_flags,
+		      int init_zero, int init_cpu0, int thp, int init_random)
+{
+	cpu_set_t orig_mask;
+	ssize_t bytes;
+	u8 *buf;
+	int ret;
+
+	if (!bytes0)
+		return NULL;
+
+	/* Allocate and initialize all memory on CPU#0: */
+	if (init_cpu0) {
+		orig_mask = bind_to_node(0);
+		bind_to_memnode(0);
+	}
+
+	bytes = bytes0 + HPSIZE;
+
+	buf = (void *)mmap(0, bytes, PROT_READ|PROT_WRITE, MAP_ANON|map_flags, -1, 0);
+	BUG_ON(buf == (void *)-1);
+
+	if (map_flags == MAP_PRIVATE) {
+		if (thp > 0) {
+			ret = madvise(buf, bytes, MADV_HUGEPAGE);
+			if (ret && !g->print_once) {
+				g->print_once = 1;
+				printf("WARNING: Could not enable THP - do: 'echo madvise > /sys/kernel/mm/transparent_hugepage/enabled'\n");
+			}
+		}
+		if (thp < 0) {
+			ret = madvise(buf, bytes, MADV_NOHUGEPAGE);
+			if (ret && !g->print_once) {
+				g->print_once = 1;
+				printf("WARNING: Could not disable THP: run a CONFIG_TRANSPARENT_HUGEPAGE kernel?\n");
+			}
+		}
+	}
+
+	if (init_zero) {
+		bzero(buf, bytes);
+	} else {
+		/* Initialize random contents, different in each word: */
+		if (init_random) {
+			u64 *wbuf = (void *)buf;
+			long off = rand();
+			long i;
+
+			for (i = 0; i < bytes/8; i++)
+				wbuf[i] = i + off;
+		}
+	}
+
+	/* Align to 2MB boundary: */
+	buf = (void *)(((unsigned long)buf + HPSIZE-1) & ~(HPSIZE-1));
+
+	/* Restore affinity: */
+	if (init_cpu0) {
+		bind_to_cpumask(orig_mask);
+		mempol_restore();
+	}
+
+	return buf;
+}
+
+static void free_data(void *data, ssize_t bytes)
+{
+	int ret;
+
+	if (!data)
+		return;
+
+	ret = munmap(data, bytes);
+	BUG_ON(ret);
+}
+
+/*
+ * Create a shared memory buffer that can be shared between processes, zeroed:
+ */
+static void * zalloc_shared_data(ssize_t bytes)
+{
+	return alloc_data(bytes, MAP_SHARED, 1, g->p.init_cpu0,  g->p.thp, g->p.init_random);
+}
+
+/*
+ * Create a shared memory buffer that can be shared between processes:
+ */
+static void * setup_shared_data(ssize_t bytes)
+{
+	return alloc_data(bytes, MAP_SHARED, 0, g->p.init_cpu0,  g->p.thp, g->p.init_random);
+}
+
+/*
+ * Allocate process-local memory - this will either be shared between
+ * threads of this process, or only be accessed by this thread:
+ */
+static void * setup_private_data(ssize_t bytes)
+{
+	return alloc_data(bytes, MAP_PRIVATE, 0, g->p.init_cpu0,  g->p.thp, g->p.init_random);
+}
+
+/*
+ * Return a process-shared (global) mutex:
+ */
+static void init_global_mutex(pthread_mutex_t *mutex)
+{
+	pthread_mutexattr_t attr;
+
+	pthread_mutexattr_init(&attr);
+	pthread_mutexattr_setpshared(&attr, PTHREAD_PROCESS_SHARED);
+	pthread_mutex_init(mutex, &attr);
+}
+
+static int parse_cpu_list(const char *arg)
+{
+	p0.cpu_list_str = strdup(arg);
+
+	dprintf("got CPU list: {%s}\n", p0.cpu_list_str);
+
+	return 0;
+}
+
+static int parse_setup_cpu_list(void)
+{
+	struct thread_data *td;
+	char *str0, *str;
+	int t;
+
+	if (!g->p.cpu_list_str)
+		return 0;
+
+	dprintf("g->p.nr_tasks: %d\n", g->p.nr_tasks);
+
+	str0 = str = strdup(g->p.cpu_list_str);
+	t = 0;
+
+	BUG_ON(!str);
+
+	tprintf("# binding tasks to CPUs:\n");
+	tprintf("#  ");
+
+	while (true) {
+		int bind_cpu, bind_cpu_0, bind_cpu_1;
+		char *tok, *tok_end, *tok_step, *tok_len, *tok_mul;
+		int bind_len;
+		int step;
+		int mul;
+
+		tok = strsep(&str, ",");
+		if (!tok)
+			break;
+
+		tok_end = strstr(tok, "-");
+
+		dprintf("\ntoken: {%s}, end: {%s}\n", tok, tok_end);
+		if (!tok_end) {
+			/* Single CPU specified: */
+			bind_cpu_0 = bind_cpu_1 = atol(tok);
+		} else {
+			/* CPU range specified (for example: "5-11"): */
+			bind_cpu_0 = atol(tok);
+			bind_cpu_1 = atol(tok_end + 1);
+		}
+
+		step = 1;
+		tok_step = strstr(tok, "#");
+		if (tok_step) {
+			step = atol(tok_step + 1);
+			BUG_ON(step <= 0 || step >= g->p.nr_cpus);
+		}
+
+		/*
+		 * Mask length.
+		 * Eg: "--cpus 8_4-16#4" means: '--cpus 8_4,12_4,16_4',
+		 * where the _4 means the next 4 CPUs are allowed.
+		 */
+		bind_len = 1;
+		tok_len = strstr(tok, "_");
+		if (tok_len) {
+			bind_len = atol(tok_len + 1);
+			BUG_ON(bind_len <= 0 || bind_len > g->p.nr_cpus);
+		}
+
+		/* Multiplicator shortcut, "0x8" is a shortcut for: "0,0,0,0,0,0,0,0" */
+		mul = 1;
+		tok_mul = strstr(tok, "x");
+		if (tok_mul) {
+			mul = atol(tok_mul + 1);
+			BUG_ON(mul <= 0);
+		}
+
+		dprintf("CPUs: %d_%d-%d#%dx%d\n", bind_cpu_0, bind_len, bind_cpu_1, step, mul);
+
+		if (bind_cpu_0 >= g->p.nr_cpus || bind_cpu_1 >= g->p.nr_cpus) {
+			printf("\nTest not applicable, system has only %d CPUs.\n", g->p.nr_cpus);
+			return -1;
+		}
+
+		BUG_ON(bind_cpu_0 < 0 || bind_cpu_1 < 0);
+		BUG_ON(bind_cpu_0 > bind_cpu_1);
+
+		for (bind_cpu = bind_cpu_0; bind_cpu <= bind_cpu_1; bind_cpu += step) {
+			int i;
+
+			for (i = 0; i < mul; i++) {
+				int cpu;
+
+				if (t >= g->p.nr_tasks) {
+					printf("\n# NOTE: ignoring bind CPUs starting at CPU#%d\n #", bind_cpu);
+					goto out;
+				}
+				td = g->threads + t;
+
+				if (t)
+					tprintf(",");
+				if (bind_len > 1) {
+					tprintf("%2d/%d", bind_cpu, bind_len);
+				} else {
+					tprintf("%2d", bind_cpu);
+				}
+
+				CPU_ZERO(&td->bind_cpumask);
+				for (cpu = bind_cpu; cpu < bind_cpu+bind_len; cpu++) {
+					BUG_ON(cpu < 0 || cpu >= g->p.nr_cpus);
+					CPU_SET(cpu, &td->bind_cpumask);
+				}
+				t++;
+			}
+		}
+	}
+out:
+
+	tprintf("\n");
+
+	if (t < g->p.nr_tasks)
+		printf("# NOTE: %d tasks bound, %d tasks unbound\n", t, g->p.nr_tasks - t);
+
+	free(str0);
+	return 0;
+}
+
+static int parse_cpus_opt(const struct option *opt __maybe_unused,
+			  const char *arg, int unset __maybe_unused)
+{
+	if (!arg)
+		return -1;
+
+	return parse_cpu_list(arg);
+}
+
+static int parse_node_list(const char *arg)
+{
+	p0.node_list_str = strdup(arg);
+
+	dprintf("got NODE list: {%s}\n", p0.node_list_str);
+
+	return 0;
+}
+
+static int parse_setup_node_list(void)
+{
+	struct thread_data *td;
+	char *str0, *str;
+	int t;
+
+	if (!g->p.node_list_str)
+		return 0;
+
+	dprintf("g->p.nr_tasks: %d\n", g->p.nr_tasks);
+
+	str0 = str = strdup(g->p.node_list_str);
+	t = 0;
+
+	BUG_ON(!str);
+
+	tprintf("# binding tasks to NODEs:\n");
+	tprintf("# ");
+
+	while (true) {
+		int bind_node, bind_node_0, bind_node_1;
+		char *tok, *tok_end, *tok_step, *tok_mul;
+		int step;
+		int mul;
+
+		tok = strsep(&str, ",");
+		if (!tok)
+			break;
+
+		tok_end = strstr(tok, "-");
+
+		dprintf("\ntoken: {%s}, end: {%s}\n", tok, tok_end);
+		if (!tok_end) {
+			/* Single NODE specified: */
+			bind_node_0 = bind_node_1 = atol(tok);
+		} else {
+			/* NODE range specified (for example: "5-11"): */
+			bind_node_0 = atol(tok);
+			bind_node_1 = atol(tok_end + 1);
+		}
+
+		step = 1;
+		tok_step = strstr(tok, "#");
+		if (tok_step) {
+			step = atol(tok_step + 1);
+			BUG_ON(step <= 0 || step >= g->p.nr_nodes);
+		}
+
+		/* Multiplicator shortcut, "0x8" is a shortcut for: "0,0,0,0,0,0,0,0" */
+		mul = 1;
+		tok_mul = strstr(tok, "x");
+		if (tok_mul) {
+			mul = atol(tok_mul + 1);
+			BUG_ON(mul <= 0);
+		}
+
+		dprintf("NODEs: %d-%d #%d\n", bind_node_0, bind_node_1, step);
+
+		if (bind_node_0 >= g->p.nr_nodes || bind_node_1 >= g->p.nr_nodes) {
+			printf("\nTest not applicable, system has only %d nodes.\n", g->p.nr_nodes);
+			return -1;
+		}
+
+		BUG_ON(bind_node_0 < 0 || bind_node_1 < 0);
+		BUG_ON(bind_node_0 > bind_node_1);
+
+		for (bind_node = bind_node_0; bind_node <= bind_node_1; bind_node += step) {
+			int i;
+
+			for (i = 0; i < mul; i++) {
+				if (t >= g->p.nr_tasks) {
+					printf("\n# NOTE: ignoring bind NODEs starting at NODE#%d\n", bind_node);
+					goto out;
+				}
+				td = g->threads + t;
+
+				if (!t)
+					tprintf(" %2d", bind_node);
+				else
+					tprintf(",%2d", bind_node);
+
+				td->bind_node = bind_node;
+				t++;
+			}
+		}
+	}
+out:
+
+	tprintf("\n");
+
+	if (t < g->p.nr_tasks)
+		printf("# NOTE: %d tasks mem-bound, %d tasks unbound\n", t, g->p.nr_tasks - t);
+
+	free(str0);
+	return 0;
+}
+
+static int parse_nodes_opt(const struct option *opt __maybe_unused,
+			  const char *arg, int unset __maybe_unused)
+{
+	if (!arg)
+		return -1;
+
+	return parse_node_list(arg);
+
+	return 0;
+}
+
+#define BIT(x) (1ul << x)
+
+static inline uint32_t lfsr_32(uint32_t lfsr)
+{
+	const uint32_t taps = BIT(1) | BIT(5) | BIT(6) | BIT(31);
+	return (lfsr>>1) ^ ((0x0u - (lfsr & 0x1u)) & taps);
+}
+
+/*
+ * Make sure there's real data dependency to RAM (when read
+ * accesses are enabled), so the compiler, the CPU and the
+ * kernel (KSM, zero page, etc.) cannot optimize away RAM
+ * accesses:
+ */
+static inline u64 access_data(u64 *data __attribute__((unused)), u64 val)
+{
+	if (g->p.data_reads)
+		val += *data;
+	if (g->p.data_writes)
+		*data = val + 1;
+	return val;
+}
+
+/*
+ * The worker process does two types of work, a forwards going
+ * loop and a backwards going loop.
+ *
+ * We do this so that on multiprocessor systems we do not create
+ * a 'train' of processing, with highly synchronized processes,
+ * skewing the whole benchmark.
+ */
+static u64 do_work(u8 *__data, long bytes, int nr, int nr_max, int loop, u64 val)
+{
+	long words = bytes/sizeof(u64);
+	u64 *data = (void *)__data;
+	long chunk_0, chunk_1;
+	u64 *d0, *d, *d1;
+	long off;
+	long i;
+
+	BUG_ON(!data && words);
+	BUG_ON(data && !words);
+
+	if (!data)
+		return val;
+
+	/* Very simple memset() work variant: */
+	if (g->p.data_zero_memset && !g->p.data_rand_walk) {
+		bzero(data, bytes);
+		return val;
+	}
+
+	/* Spread out by PID/TID nr and by loop nr: */
+	chunk_0 = words/nr_max;
+	chunk_1 = words/g->p.nr_loops;
+	off = nr*chunk_0 + loop*chunk_1;
+
+	while (off >= words)
+		off -= words;
+
+	if (g->p.data_rand_walk) {
+		u32 lfsr = nr + loop + val;
+		int j;
+
+		for (i = 0; i < words/1024; i++) {
+			long start, end;
+
+			lfsr = lfsr_32(lfsr);
+
+			start = lfsr % words;
+			end = min(start + 1024, words-1);
+
+			if (g->p.data_zero_memset) {
+				bzero(data + start, (end-start) * sizeof(u64));
+			} else {
+				for (j = start; j < end; j++)
+					val = access_data(data + j, val);
+			}
+		}
+	} else if (!g->p.data_backwards || (nr + loop) & 1) {
+
+		d0 = data + off;
+		d  = data + off + 1;
+		d1 = data + words;
+
+		/* Process data forwards: */
+		for (;;) {
+			if (unlikely(d >= d1))
+				d = data;
+			if (unlikely(d == d0))
+				break;
+
+			val = access_data(d, val);
+
+			d++;
+		}
+	} else {
+		/* Process data backwards: */
+
+		d0 = data + off;
+		d  = data + off - 1;
+		d1 = data + words;
+
+		/* Process data forwards: */
+		for (;;) {
+			if (unlikely(d < data))
+				d = data + words-1;
+			if (unlikely(d == d0))
+				break;
+
+			val = access_data(d, val);
+
+			d--;
+		}
+	}
+
+	return val;
+}
+
+static void update_curr_cpu(int task_nr, unsigned long bytes_worked)
+{
+	unsigned int cpu;
+
+	cpu = sched_getcpu();
+
+	g->threads[task_nr].curr_cpu = cpu;
+	prctl(0, bytes_worked);
+}
+
+#define MAX_NR_NODES	64
+
+/*
+ * Count the number of nodes a process's threads
+ * are spread out on.
+ *
+ * A count of 1 means that the process is compressed
+ * to a single node. A count of g->p.nr_nodes means it's
+ * spread out on the whole system.
+ */
+static int count_process_nodes(int process_nr)
+{
+	char node_present[MAX_NR_NODES] = { 0, };
+	int nodes;
+	int n, t;
+
+	for (t = 0; t < g->p.nr_threads; t++) {
+		struct thread_data *td;
+		int task_nr;
+		int node;
+
+		task_nr = process_nr*g->p.nr_threads + t;
+		td = g->threads + task_nr;
+
+		node = numa_node_of_cpu(td->curr_cpu);
+		node_present[node] = 1;
+	}
+
+	nodes = 0;
+
+	for (n = 0; n < MAX_NR_NODES; n++)
+		nodes += node_present[n];
+
+	return nodes;
+}
+
+/*
+ * Count the number of distinct process-threads a node contains.
+ *
+ * A count of 1 means that the node contains only a single
+ * process. If all nodes on the system contain at most one
+ * process then we are well-converged.
+ */
+static int count_node_processes(int node)
+{
+	int processes = 0;
+	int t, p;
+
+	for (p = 0; p < g->p.nr_proc; p++) {
+		for (t = 0; t < g->p.nr_threads; t++) {
+			struct thread_data *td;
+			int task_nr;
+			int n;
+
+			task_nr = p*g->p.nr_threads + t;
+			td = g->threads + task_nr;
+
+			n = numa_node_of_cpu(td->curr_cpu);
+			if (n == node) {
+				processes++;
+				break;
+			}
+		}
+	}
+
+	return processes;
+}
+
+static void calc_convergence_compression(int *strong)
+{
+	unsigned int nodes_min, nodes_max;
+	int p;
+
+	nodes_min = -1;
+	nodes_max =  0;
+
+	for (p = 0; p < g->p.nr_proc; p++) {
+		unsigned int nodes = count_process_nodes(p);
+
+		nodes_min = min(nodes, nodes_min);
+		nodes_max = max(nodes, nodes_max);
+	}
+
+	/* Strong convergence: all threads compress on a single node: */
+	if (nodes_min == 1 && nodes_max == 1) {
+		*strong = 1;
+	} else {
+		*strong = 0;
+		tprintf(" {%d-%d}", nodes_min, nodes_max);
+	}
+}
+
+static void calc_convergence(double runtime_ns_max, double *convergence)
+{
+	unsigned int loops_done_min, loops_done_max;
+	int process_groups;
+	int nodes[MAX_NR_NODES];
+	int distance;
+	int nr_min;
+	int nr_max;
+	int strong;
+	int sum;
+	int nr;
+	int node;
+	int cpu;
+	int t;
+
+	if (!g->p.show_convergence && !g->p.measure_convergence)
+		return;
+
+	for (node = 0; node < g->p.nr_nodes; node++)
+		nodes[node] = 0;
+
+	loops_done_min = -1;
+	loops_done_max = 0;
+
+	for (t = 0; t < g->p.nr_tasks; t++) {
+		struct thread_data *td = g->threads + t;
+		unsigned int loops_done;
+
+		cpu = td->curr_cpu;
+
+		/* Not all threads have written it yet: */
+		if (cpu < 0)
+			continue;
+
+		node = numa_node_of_cpu(cpu);
+
+		nodes[node]++;
+
+		loops_done = td->loops_done;
+		loops_done_min = min(loops_done, loops_done_min);
+		loops_done_max = max(loops_done, loops_done_max);
+	}
+
+	nr_max = 0;
+	nr_min = g->p.nr_tasks;
+	sum = 0;
+
+	for (node = 0; node < g->p.nr_nodes; node++) {
+		nr = nodes[node];
+		nr_min = min(nr, nr_min);
+		nr_max = max(nr, nr_max);
+		sum += nr;
+	}
+	BUG_ON(nr_min > nr_max);
+
+	BUG_ON(sum > g->p.nr_tasks);
+
+	if (0 && (sum < g->p.nr_tasks))
+		return;
+
+	/*
+	 * Count the number of distinct process groups present
+	 * on nodes - when we are converged this will decrease
+	 * to g->p.nr_proc:
+	 */
+	process_groups = 0;
+
+	for (node = 0; node < g->p.nr_nodes; node++) {
+		int processes = count_node_processes(node);
+
+		nr = nodes[node];
+		tprintf(" %2d/%-2d", nr, processes);
+
+		process_groups += processes;
+	}
+
+	distance = nr_max - nr_min;
+
+	tprintf(" [%2d/%-2d]", distance, process_groups);
+
+	tprintf(" l:%3d-%-3d (%3d)",
+		loops_done_min, loops_done_max, loops_done_max-loops_done_min);
+
+	if (loops_done_min && loops_done_max) {
+		double skew = 1.0 - (double)loops_done_min/loops_done_max;
+
+		tprintf(" [%4.1f%%]", skew * 100.0);
+	}
+
+	calc_convergence_compression(&strong);
+
+	if (strong && process_groups == g->p.nr_proc) {
+		if (!*convergence) {
+			*convergence = runtime_ns_max;
+			tprintf(" (%6.1fs converged)\n", *convergence/1e9);
+			if (g->p.measure_convergence) {
+				g->all_converged = true;
+				g->stop_work = true;
+			}
+		}
+	} else {
+		if (*convergence) {
+			tprintf(" (%6.1fs de-converged)", runtime_ns_max/1e9);
+			*convergence = 0;
+		}
+		tprintf("\n");
+	}
+}
+
+static void show_summary(double runtime_ns_max, int l, double *convergence)
+{
+	tprintf("\r #  %5.1f%%  [%.1f mins]",
+		(double)(l+1)/g->p.nr_loops*100.0, runtime_ns_max/1e9 / 60.0);
+
+	calc_convergence(runtime_ns_max, convergence);
+
+	if (g->p.show_details >= 0)
+		fflush(stdout);
+}
+
+static void *worker_thread(void *__tdata)
+{
+	struct thread_data *td = __tdata;
+	struct timeval start0, start, stop, diff;
+	int process_nr = td->process_nr;
+	int thread_nr = td->thread_nr;
+	unsigned long last_perturbance;
+	int task_nr = td->task_nr;
+	int details = g->p.show_details;
+	int first_task, last_task;
+	double convergence = 0;
+	u64 val = td->val;
+	double runtime_ns_max;
+	u8 *global_data;
+	u8 *process_data;
+	u8 *thread_data;
+	u64 bytes_done;
+	long work_done;
+	u32 l;
+
+	bind_to_cpumask(td->bind_cpumask);
+	bind_to_memnode(td->bind_node);
+
+	set_taskname("thread %d/%d", process_nr, thread_nr);
+
+	global_data = g->data;
+	process_data = td->process_data;
+	thread_data = setup_private_data(g->p.bytes_thread);
+
+	bytes_done = 0;
+
+	last_task = 0;
+	if (process_nr == g->p.nr_proc-1 && thread_nr == g->p.nr_threads-1)
+		last_task = 1;
+
+	first_task = 0;
+	if (process_nr == 0 && thread_nr == 0)
+		first_task = 1;
+
+	if (details >= 2) {
+		printf("#  thread %2d / %2d global mem: %p, process mem: %p, thread mem: %p\n",
+			process_nr, thread_nr, global_data, process_data, thread_data);
+	}
+
+	if (g->p.serialize_startup) {
+		pthread_mutex_lock(&g->startup_mutex);
+		g->nr_tasks_started++;
+		pthread_mutex_unlock(&g->startup_mutex);
+
+		/* Here we will wait for the main process to start us all at once: */
+		pthread_mutex_lock(&g->start_work_mutex);
+		g->nr_tasks_working++;
+
+		/* Last one wake the main process: */
+		if (g->nr_tasks_working == g->p.nr_tasks)
+			pthread_mutex_unlock(&g->startup_done_mutex);
+
+		pthread_mutex_unlock(&g->start_work_mutex);
+	}
+
+	gettimeofday(&start0, NULL);
+
+	start = stop = start0;
+	last_perturbance = start.tv_sec;
+
+	for (l = 0; l < g->p.nr_loops; l++) {
+		start = stop;
+
+		if (g->stop_work)
+			break;
+
+		val += do_work(global_data,  g->p.bytes_global,  process_nr, g->p.nr_proc,	l, val);
+		val += do_work(process_data, g->p.bytes_process, thread_nr,  g->p.nr_threads,	l, val);
+		val += do_work(thread_data,  g->p.bytes_thread,  0,          1,		l, val);
+
+		if (g->p.sleep_usecs) {
+			pthread_mutex_lock(td->process_lock);
+			usleep(g->p.sleep_usecs);
+			pthread_mutex_unlock(td->process_lock);
+		}
+		/*
+		 * Amount of work to be done under a process-global lock:
+		 */
+		if (g->p.bytes_process_locked) {
+			pthread_mutex_lock(td->process_lock);
+			val += do_work(process_data, g->p.bytes_process_locked, thread_nr,  g->p.nr_threads,	l, val);
+			pthread_mutex_unlock(td->process_lock);
+		}
+
+		work_done = g->p.bytes_global + g->p.bytes_process +
+			    g->p.bytes_process_locked + g->p.bytes_thread;
+
+		update_curr_cpu(task_nr, work_done);
+		bytes_done += work_done;
+
+		if (details < 0 && !g->p.perturb_secs && !g->p.measure_convergence && !g->p.nr_secs)
+			continue;
+
+		td->loops_done = l;
+
+		gettimeofday(&stop, NULL);
+
+		/* Check whether our max runtime timed out: */
+		if (g->p.nr_secs) {
+			timersub(&stop, &start0, &diff);
+			if ((u32)diff.tv_sec >= g->p.nr_secs) {
+				g->stop_work = true;
+				break;
+			}
+		}
+
+		/* Update the summary at most once per second: */
+		if (start.tv_sec == stop.tv_sec)
+			continue;
+
+		/*
+		 * Perturb the first task's equilibrium every g->p.perturb_secs seconds,
+		 * by migrating to CPU#0:
+		 */
+		if (first_task && g->p.perturb_secs && (int)(stop.tv_sec - last_perturbance) >= g->p.perturb_secs) {
+			cpu_set_t orig_mask;
+			int target_cpu;
+			int this_cpu;
+
+			last_perturbance = stop.tv_sec;
+
+			/*
+			 * Depending on where we are running, move into
+			 * the other half of the system, to create some
+			 * real disturbance:
+			 */
+			this_cpu = g->threads[task_nr].curr_cpu;
+			if (this_cpu < g->p.nr_cpus/2)
+				target_cpu = g->p.nr_cpus-1;
+			else
+				target_cpu = 0;
+
+			orig_mask = bind_to_cpu(target_cpu);
+
+			/* Here we are running on the target CPU already */
+			if (details >= 1)
+				printf(" (injecting perturbalance, moved to CPU#%d)\n", target_cpu);
+
+			bind_to_cpumask(orig_mask);
+		}
+
+		if (details >= 3) {
+			timersub(&stop, &start, &diff);
+			runtime_ns_max = diff.tv_sec * 1000000000;
+			runtime_ns_max += diff.tv_usec * 1000;
+
+			if (details >= 0) {
+				printf(" #%2d / %2d: %14.2lf nsecs/op [val: %016"PRIx64"]\n",
+					process_nr, thread_nr, runtime_ns_max / bytes_done, val);
+			}
+			fflush(stdout);
+		}
+		if (!last_task)
+			continue;
+
+		timersub(&stop, &start0, &diff);
+		runtime_ns_max = diff.tv_sec * 1000000000ULL;
+		runtime_ns_max += diff.tv_usec * 1000ULL;
+
+		show_summary(runtime_ns_max, l, &convergence);
+	}
+
+	gettimeofday(&stop, NULL);
+	timersub(&stop, &start0, &diff);
+	td->runtime_ns = diff.tv_sec * 1000000000ULL;
+	td->runtime_ns += diff.tv_usec * 1000ULL;
+
+	free_data(thread_data, g->p.bytes_thread);
+
+	pthread_mutex_lock(&g->stop_work_mutex);
+	g->bytes_done += bytes_done;
+	pthread_mutex_unlock(&g->stop_work_mutex);
+
+	return NULL;
+}
+
+/*
+ * A worker process starts a couple of threads:
+ */
+static void worker_process(int process_nr)
+{
+	pthread_mutex_t process_lock;
+	struct thread_data *td;
+	pthread_t *pthreads;
+	u8 *process_data;
+	int task_nr;
+	int ret;
+	int t;
+
+	pthread_mutex_init(&process_lock, NULL);
+	set_taskname("process %d", process_nr);
+
+	/*
+	 * Pick up the memory policy and the CPU binding of our first thread,
+	 * so that we initialize memory accordingly:
+	 */
+	task_nr = process_nr*g->p.nr_threads;
+	td = g->threads + task_nr;
+
+	bind_to_memnode(td->bind_node);
+	bind_to_cpumask(td->bind_cpumask);
+
+	pthreads = zalloc(g->p.nr_threads * sizeof(pthread_t));
+	process_data = setup_private_data(g->p.bytes_process);
+
+	if (g->p.show_details >= 3) {
+		printf(" # process %2d global mem: %p, process mem: %p\n",
+			process_nr, g->data, process_data);
+	}
+
+	for (t = 0; t < g->p.nr_threads; t++) {
+		task_nr = process_nr*g->p.nr_threads + t;
+		td = g->threads + task_nr;
+
+		td->process_data = process_data;
+		td->process_nr   = process_nr;
+		td->thread_nr    = t;
+		td->task_nr	 = task_nr;
+		td->val          = rand();
+		td->curr_cpu	 = -1;
+		td->process_lock = &process_lock;
+
+		ret = pthread_create(pthreads + t, NULL, worker_thread, td);
+		BUG_ON(ret);
+	}
+
+	for (t = 0; t < g->p.nr_threads; t++) {
+                ret = pthread_join(pthreads[t], NULL);
+		BUG_ON(ret);
+	}
+
+	free_data(process_data, g->p.bytes_process);
+	free(pthreads);
+}
+
+static void print_summary(void)
+{
+	if (g->p.show_details < 0)
+		return;
+
+	printf("\n ###\n");
+	printf(" # %d %s will execute (on %d nodes, %d CPUs):\n",
+		g->p.nr_tasks, g->p.nr_tasks == 1 ? "task" : "tasks", g->p.nr_nodes, g->p.nr_cpus);
+	printf(" #      %5dx %5ldMB global  shared mem operations\n",
+			g->p.nr_loops, g->p.bytes_global/1024/1024);
+	printf(" #      %5dx %5ldMB process shared mem operations\n",
+			g->p.nr_loops, g->p.bytes_process/1024/1024);
+	printf(" #      %5dx %5ldMB thread  local  mem operations\n",
+			g->p.nr_loops, g->p.bytes_thread/1024/1024);
+
+	printf(" ###\n");
+
+	printf("\n ###\n"); fflush(stdout);
+}
+
+static void init_thread_data(void)
+{
+	ssize_t size = sizeof(*g->threads)*g->p.nr_tasks;
+	int t;
+
+	g->threads = zalloc_shared_data(size);
+
+	for (t = 0; t < g->p.nr_tasks; t++) {
+		struct thread_data *td = g->threads + t;
+		int cpu;
+
+		/* Allow all nodes by default: */
+		td->bind_node = -1;
+
+		/* Allow all CPUs by default: */
+		CPU_ZERO(&td->bind_cpumask);
+		for (cpu = 0; cpu < g->p.nr_cpus; cpu++)
+			CPU_SET(cpu, &td->bind_cpumask);
+	}
+}
+
+static void deinit_thread_data(void)
+{
+	ssize_t size = sizeof(*g->threads)*g->p.nr_tasks;
+
+	free_data(g->threads, size);
+}
+
+static int init(void)
+{
+	g = (void *)alloc_data(sizeof(*g), MAP_SHARED, 1, 0, 0 /* THP */, 0);
+
+	/* Copy over options: */
+	g->p = p0;
+
+	g->p.nr_cpus = numa_num_configured_cpus();
+
+	g->p.nr_nodes = numa_max_node() + 1;
+
+	/* char array in count_process_nodes(): */
+	BUG_ON(g->p.nr_nodes > MAX_NR_NODES || g->p.nr_nodes < 0);
+
+	if (g->p.show_quiet && !g->p.show_details)
+		g->p.show_details = -1;
+
+	/* Some memory should be specified: */
+	if (!g->p.mb_global_str && !g->p.mb_proc_str && !g->p.mb_thread_str)
+		return -1;
+
+	if (g->p.mb_global_str) {
+		g->p.mb_global = atof(g->p.mb_global_str);
+		BUG_ON(g->p.mb_global < 0);
+	}
+
+	if (g->p.mb_proc_str) {
+		g->p.mb_proc = atof(g->p.mb_proc_str);
+		BUG_ON(g->p.mb_proc < 0);
+	}
+
+	if (g->p.mb_proc_locked_str) {
+		g->p.mb_proc_locked = atof(g->p.mb_proc_locked_str);
+		BUG_ON(g->p.mb_proc_locked < 0);
+		BUG_ON(g->p.mb_proc_locked > g->p.mb_proc);
+	}
+
+	if (g->p.mb_thread_str) {
+		g->p.mb_thread = atof(g->p.mb_thread_str);
+		BUG_ON(g->p.mb_thread < 0);
+	}
+
+	BUG_ON(g->p.nr_threads <= 0);
+	BUG_ON(g->p.nr_proc <= 0);
+
+	g->p.nr_tasks = g->p.nr_proc*g->p.nr_threads;
+
+	g->p.bytes_global		= g->p.mb_global	*1024L*1024L;
+	g->p.bytes_process		= g->p.mb_proc		*1024L*1024L;
+	g->p.bytes_process_locked	= g->p.mb_proc_locked	*1024L*1024L;
+	g->p.bytes_thread		= g->p.mb_thread	*1024L*1024L;
+
+	g->data = setup_shared_data(g->p.bytes_global);
+
+	/* Startup serialization: */
+	init_global_mutex(&g->start_work_mutex);
+	init_global_mutex(&g->startup_mutex);
+	init_global_mutex(&g->startup_done_mutex);
+	init_global_mutex(&g->stop_work_mutex);
+
+	init_thread_data();
+
+	tprintf("#\n");
+	if (parse_setup_cpu_list() || parse_setup_node_list())
+		return -1;
+	tprintf("#\n");
+
+	print_summary();
+
+	return 0;
+}
+
+static void deinit(void)
+{
+	free_data(g->data, g->p.bytes_global);
+	g->data = NULL;
+
+	deinit_thread_data();
+
+	free_data(g, sizeof(*g));
+	g = NULL;
+}
+
+/*
+ * Print a short or long result, depending on the verbosity setting:
+ */
+static void print_res(const char *name, double val,
+		      const char *txt_unit, const char *txt_short, const char *txt_long)
+{
+	if (!name)
+		name = "main,";
+
+	if (g->p.show_quiet)
+		printf(" %-30s %15.3f, %-15s %s\n", name, val, txt_unit, txt_short);
+	else
+		printf(" %14.3f %s\n", val, txt_long);
+}
+
+static int __bench_numa(const char *name)
+{
+	struct timeval start, stop, diff;
+	u64 runtime_ns_min, runtime_ns_sum;
+	pid_t *pids, pid, wpid;
+	double delta_runtime;
+	double runtime_avg;
+	double runtime_sec_max;
+	double runtime_sec_min;
+	int wait_stat;
+	double bytes;
+	int i, t;
+
+	if (init())
+		return -1;
+
+	pids = zalloc(g->p.nr_proc * sizeof(*pids));
+	pid = -1;
+
+	/* All threads try to acquire it, this way we can wait for them to start up: */
+	pthread_mutex_lock(&g->start_work_mutex);
+
+	if (g->p.serialize_startup) {
+		tprintf(" #\n");
+		tprintf(" # Startup synchronization: ..."); fflush(stdout);
+	}
+
+	gettimeofday(&start, NULL);
+
+	for (i = 0; i < g->p.nr_proc; i++) {
+		pid = fork();
+		dprintf(" # process %2d: PID %d\n", i, pid);
+
+		BUG_ON(pid < 0);
+		if (!pid) {
+			/* Child process: */
+			worker_process(i);
+
+			exit(0);
+		}
+		pids[i] = pid;
+
+	}
+	/* Wait for all the threads to start up: */
+	while (g->nr_tasks_started != g->p.nr_tasks)
+		usleep(1000);
+
+	BUG_ON(g->nr_tasks_started != g->p.nr_tasks);
+
+	if (g->p.serialize_startup) {
+		double startup_sec;
+
+		pthread_mutex_lock(&g->startup_done_mutex);
+
+		/* This will start all threads: */
+		pthread_mutex_unlock(&g->start_work_mutex);
+
+		/* This mutex is locked - the last started thread will wake us: */
+		pthread_mutex_lock(&g->startup_done_mutex);
+
+		gettimeofday(&stop, NULL);
+
+		timersub(&stop, &start, &diff);
+
+		startup_sec = diff.tv_sec * 1000000000.0;
+		startup_sec += diff.tv_usec * 1000.0;
+		startup_sec /= 1e9;
+
+		tprintf(" threads initialized in %.6f seconds.\n", startup_sec);
+		tprintf(" #\n");
+
+		start = stop;
+		pthread_mutex_unlock(&g->startup_done_mutex);
+	} else {
+		gettimeofday(&start, NULL);
+	}
+
+	/* Parent process: */
+
+
+	for (i = 0; i < g->p.nr_proc; i++) {
+		wpid = waitpid(pids[i], &wait_stat, 0);
+		BUG_ON(wpid < 0);
+		BUG_ON(!WIFEXITED(wait_stat));
+
+	}
+
+	runtime_ns_sum = 0;
+	runtime_ns_min = -1LL;
+
+	for (t = 0; t < g->p.nr_tasks; t++) {
+		u64 thread_runtime_ns = g->threads[t].runtime_ns;
+
+		runtime_ns_sum += thread_runtime_ns;
+		runtime_ns_min = min(thread_runtime_ns, runtime_ns_min);
+	}
+
+	gettimeofday(&stop, NULL);
+	timersub(&stop, &start, &diff);
+
+	BUG_ON(bench_format != BENCH_FORMAT_DEFAULT);
+
+	tprintf("\n ###\n");
+	tprintf("\n");
+
+	runtime_sec_max = diff.tv_sec * 1000000000.0;
+	runtime_sec_max += diff.tv_usec * 1000.0;
+	runtime_sec_max /= 1e9;
+
+	runtime_sec_min = runtime_ns_min/1e9;
+
+	bytes = g->bytes_done;
+	runtime_avg = (double)runtime_ns_sum / g->p.nr_tasks / 1e9;
+
+	if (g->p.measure_convergence) {
+		print_res(name, runtime_sec_max,
+			"secs,", "NUMA-convergence-latency", "secs latency to NUMA-converge");
+	}
+
+	print_res(name, runtime_sec_max,
+		"secs,", "runtime-max/thread",	"secs slowest (max) thread-runtime");
+
+	print_res(name, runtime_sec_min,
+		"secs,", "runtime-min/thread",	"secs fastest (min) thread-runtime");
+
+	print_res(name, runtime_avg,
+		"secs,", "runtime-avg/thread",	"secs average thread-runtime");
+
+	delta_runtime = (runtime_sec_max - runtime_sec_min)/2.0;
+	print_res(name, delta_runtime / runtime_sec_max * 100.0,
+		"%,", "spread-runtime/thread",	"% difference between max/avg runtime");
+
+	print_res(name, bytes / g->p.nr_tasks / 1e9,
+		"GB,", "data/thread",		"GB data processed, per thread");
+
+	print_res(name, bytes / 1e9,
+		"GB,", "data-total",		"GB data processed, total");
+
+	print_res(name, runtime_sec_max * 1e9 / (bytes / g->p.nr_tasks),
+		"nsecs,", "runtime/byte/thread","nsecs/byte/thread runtime");
+
+	print_res(name, bytes / g->p.nr_tasks / 1e9 / runtime_sec_max,
+		"GB/sec,", "thread-speed",	"GB/sec/thread speed");
+
+	print_res(name, bytes / runtime_sec_max / 1e9,
+		"GB/sec,", "total-speed",	"GB/sec total speed");
+
+	free(pids);
+
+	deinit();
+
+	return 0;
+}
+
+#define MAX_ARGS 50
+
+static int command_size(const char **argv)
+{
+	int size = 0;
+
+	while (*argv) {
+		size++;
+		argv++;
+	}
+
+	BUG_ON(size >= MAX_ARGS);
+
+	return size;
+}
+
+static void init_params(struct params *p, const char *name, int argc, const char **argv)
+{
+	int i;
+
+	printf("\n # Running %s \"perf bench numa", name);
+
+	for (i = 0; i < argc; i++)
+		printf(" %s", argv[i]);
+
+	printf("\"\n");
+
+	memset(p, 0, sizeof(*p));
+
+	/* Initialize nonzero defaults: */
+
+	p->serialize_startup		= 1;
+	p->data_reads			= true;
+	p->data_writes			= true;
+	p->data_backwards		= true;
+	p->data_rand_walk		= true;
+	p->nr_loops			= -1;
+	p->init_random			= true;
+	p->mb_global_str		= "1";
+	p->nr_proc			= 1;
+	p->nr_threads			= 1;
+	p->nr_secs			= 5;
+	p->run_all			= argc == 1;
+}
+
+static int run_bench_numa(const char *name, const char **argv)
+{
+	int argc = command_size(argv);
+
+	init_params(&p0, name, argc, argv);
+	argc = parse_options(argc, argv, options, bench_numa_usage, 0);
+	if (argc)
+		goto err;
+
+	if (__bench_numa(name))
+		goto err;
+
+	return 0;
+
+err:
+	return -1;
+}
+
+#define OPT_BW_RAM		"-s",  "20", "-zZq",    "--thp", " 1", "--no-data_rand_walk"
+#define OPT_BW_RAM_NOTHP	OPT_BW_RAM,		"--thp", "-1"
+
+#define OPT_CONV		"-s", "100", "-zZ0qcm", "--thp", " 1"
+#define OPT_CONV_NOTHP		OPT_CONV,		"--thp", "-1"
+
+#define OPT_BW			"-s",  "20", "-zZ0q",   "--thp", " 1"
+#define OPT_BW_NOTHP		OPT_BW,			"--thp", "-1"
+
+/*
+ * The built-in test-suite executed by "perf bench numa -a".
+ *
+ * (A minimum of 4 nodes and 16 GB of RAM is recommended.)
+ */
+static const char *tests[][MAX_ARGS] = {
+   /* Basic single-stream NUMA bandwidth measurements: */
+   { "RAM-bw-local,",	  "mem",  "-p",  "1",  "-t",  "1", "-P", "1024",
+			  "-C" ,   "0", "-M",   "0", OPT_BW_RAM },
+   { "RAM-bw-local-NOTHP,",
+			  "mem",  "-p",  "1",  "-t",  "1", "-P", "1024",
+			  "-C" ,   "0", "-M",   "0", OPT_BW_RAM_NOTHP },
+   { "RAM-bw-remote,",	  "mem",  "-p",  "1",  "-t",  "1", "-P", "1024",
+			  "-C" ,   "0", "-M",   "1", OPT_BW_RAM },
+
+   /* 2-stream NUMA bandwidth measurements: */
+   { "RAM-bw-local-2x,",  "mem",  "-p",  "2",  "-t",  "1", "-P", "1024",
+			   "-C", "0,2", "-M", "0x2", OPT_BW_RAM },
+   { "RAM-bw-remote-2x,", "mem",  "-p",  "2",  "-t",  "1", "-P", "1024",
+		 	   "-C", "0,2", "-M", "1x2", OPT_BW_RAM },
+
+   /* Cross-stream NUMA bandwidth measurement: */
+   { "RAM-bw-cross,",     "mem",  "-p",  "2",  "-t",  "1", "-P", "1024",
+		 	   "-C", "0,8", "-M", "1,0", OPT_BW_RAM },
+
+   /* Convergence latency measurements: */
+   { " 1x3-convergence,", "mem",  "-p",  "1", "-t",  "3", "-P",  "512", OPT_CONV },
+   { " 1x4-convergence,", "mem",  "-p",  "1", "-t",  "4", "-P",  "512", OPT_CONV },
+   { " 1x6-convergence,", "mem",  "-p",  "1", "-t",  "6", "-P", "1020", OPT_CONV },
+   { " 2x3-convergence,", "mem",  "-p",  "3", "-t",  "3", "-P", "1020", OPT_CONV },
+   { " 3x3-convergence,", "mem",  "-p",  "3", "-t",  "3", "-P", "1020", OPT_CONV },
+   { " 4x4-convergence,", "mem",  "-p",  "4", "-t",  "4", "-P",  "512", OPT_CONV },
+   { " 4x4-convergence-NOTHP,",
+			  "mem",  "-p",  "4", "-t",  "4", "-P",  "512", OPT_CONV_NOTHP },
+   { " 4x6-convergence,", "mem",  "-p",  "4", "-t",  "6", "-P", "1020", OPT_CONV },
+   { " 4x8-convergence,", "mem",  "-p",  "4", "-t",  "8", "-P",  "512", OPT_CONV },
+   { " 8x4-convergence,", "mem",  "-p",  "8", "-t",  "4", "-P",  "512", OPT_CONV },
+   { " 8x4-convergence-NOTHP,",
+			  "mem",  "-p",  "8", "-t",  "4", "-P",  "512", OPT_CONV_NOTHP },
+   { " 3x1-convergence,", "mem",  "-p",  "3", "-t",  "1", "-P",  "512", OPT_CONV },
+   { " 4x1-convergence,", "mem",  "-p",  "4", "-t",  "1", "-P",  "512", OPT_CONV },
+   { " 8x1-convergence,", "mem",  "-p",  "8", "-t",  "1", "-P",  "512", OPT_CONV },
+   { "16x1-convergence,", "mem",  "-p", "16", "-t",  "1", "-P",  "256", OPT_CONV },
+   { "32x1-convergence,", "mem",  "-p", "32", "-t",  "1", "-P",  "128", OPT_CONV },
+
+   /* Various NUMA process/thread layout bandwidth measurements: */
+   { " 2x1-bw-process,",  "mem",  "-p",  "2", "-t",  "1", "-P", "1024", OPT_BW },
+   { " 3x1-bw-process,",  "mem",  "-p",  "3", "-t",  "1", "-P", "1024", OPT_BW },
+   { " 4x1-bw-process,",  "mem",  "-p",  "4", "-t",  "1", "-P", "1024", OPT_BW },
+   { " 8x1-bw-process,",  "mem",  "-p",  "8", "-t",  "1", "-P", " 512", OPT_BW },
+   { " 8x1-bw-process-NOTHP,",
+			  "mem",  "-p",  "8", "-t",  "1", "-P", " 512", OPT_BW_NOTHP },
+   { "16x1-bw-process,",  "mem",  "-p", "16", "-t",  "1", "-P",  "256", OPT_BW },
+
+   { " 4x1-bw-thread,",	  "mem",  "-p",  "1", "-t",  "4", "-T",  "256", OPT_BW },
+   { " 8x1-bw-thread,",	  "mem",  "-p",  "1", "-t",  "8", "-T",  "256", OPT_BW },
+   { "16x1-bw-thread,",   "mem",  "-p",  "1", "-t", "16", "-T",  "128", OPT_BW },
+   { "32x1-bw-thread,",   "mem",  "-p",  "1", "-t", "32", "-T",   "64", OPT_BW },
+
+   { " 2x3-bw-thread,",	  "mem",  "-p",  "2", "-t",  "3", "-P",  "512", OPT_BW },
+   { " 4x4-bw-thread,",	  "mem",  "-p",  "4", "-t",  "4", "-P",  "512", OPT_BW },
+   { " 4x6-bw-thread,",	  "mem",  "-p",  "4", "-t",  "6", "-P",  "512", OPT_BW },
+   { " 4x8-bw-thread,",	  "mem",  "-p",  "4", "-t",  "8", "-P",  "512", OPT_BW },
+   { " 4x8-bw-thread-NOTHP,",
+			  "mem",  "-p",  "4", "-t",  "8", "-P",  "512", OPT_BW_NOTHP },
+   { " 3x3-bw-thread,",	  "mem",  "-p",  "3", "-t",  "3", "-P",  "512", OPT_BW },
+   { " 5x5-bw-thread,",	  "mem",  "-p",  "5", "-t",  "5", "-P",  "512", OPT_BW },
+
+   { "2x16-bw-thread,",   "mem",  "-p",  "2", "-t", "16", "-P",  "512", OPT_BW },
+   { "1x32-bw-thread,",   "mem",  "-p",  "1", "-t", "32", "-P", "2048", OPT_BW },
+
+   { "numa02-bw,",	  "mem",  "-p",  "1", "-t", "32", "-T",   "32", OPT_BW },
+   { "numa02-bw-NOTHP,",  "mem",  "-p",  "1", "-t", "32", "-T",   "32", OPT_BW_NOTHP },
+   { "numa01-bw-thread,", "mem",  "-p",  "2", "-t", "16", "-T",  "192", OPT_BW },
+   { "numa01-bw-thread-NOTHP,",
+			  "mem",  "-p",  "2", "-t", "16", "-T",  "192", OPT_BW_NOTHP },
+};
+
+static int bench_all(void)
+{
+	int nr = ARRAY_SIZE(tests);
+	int ret;
+	int i;
+
+	ret = system("echo ' #'; echo ' # Running test on: '$(uname -a); echo ' #'");
+	BUG_ON(ret < 0);
+
+	for (i = 0; i < nr; i++) {
+		run_bench_numa(tests[i][0], tests[i] + 1);
+	}
+
+	printf("\n");
+
+	return 0;
+}
+
+int bench_numa(int argc, const char **argv, const char *prefix __maybe_unused)
+{
+	init_params(&p0, "main,", argc, argv);
+	argc = parse_options(argc, argv, options, bench_numa_usage, 0);
+	if (argc)
+		goto err;
+
+	if (p0.run_all)
+		return bench_all();
+
+	if (__bench_numa(NULL))
+		goto err;
+
+	return 0;
+
+err:
+	usage_with_options(numa_usage, options);
+	return -1;
+}
diff --git a/tools/perf/bench/sched-messaging.c b/tools/perf/bench/sched-messaging.c
index d1d1b30f99c..cc1190a0849 100644
--- a/tools/perf/bench/sched-messaging.c
+++ b/tools/perf/bench/sched-messaging.c
@@ -267,7 +267,7 @@ static const char * const bench_sched_message_usage[] = {
 };
 
 int bench_sched_messaging(int argc, const char **argv,
-		    const char *prefix __used)
+		    const char *prefix __maybe_unused)
 {
 	unsigned int i, total_children;
 	struct timeval start, stop, diff;
diff --git a/tools/perf/bench/sched-pipe.c b/tools/perf/bench/sched-pipe.c
index d9ab3ce446a..07a8d7646a1 100644
--- a/tools/perf/bench/sched-pipe.c
+++ b/tools/perf/bench/sched-pipe.c
@@ -7,9 +7,7 @@
  * Based on pipe-test-1m.c by Ingo Molnar <mingo@redhat.com>
  *  http://people.redhat.com/mingo/cfs-scheduler/tools/pipe-test-1m.c
  * Ported to perf by Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp>
- *
  */
-
 #include "../perf.h"
 #include "../util/util.h"
 #include "../util/parse-options.h"
@@ -28,12 +26,24 @@
 #include <sys/time.h>
 #include <sys/types.h>
 
+#include <pthread.h>
+
+struct thread_data {
+	int			nr;
+	int			pipe_read;
+	int			pipe_write;
+	pthread_t		pthread;
+};
+
 #define LOOPS_DEFAULT 1000000
-static int loops = LOOPS_DEFAULT;
+static	int			loops = LOOPS_DEFAULT;
+
+/* Use processes by default: */
+static bool			threaded;
 
 static const struct option options[] = {
-	OPT_INTEGER('l', "loop", &loops,
-		    "Specify number of loops"),
+	OPT_INTEGER('l', "loop",	&loops,		"Specify number of loops"),
+	OPT_BOOLEAN('T', "threaded",	&threaded,	"Specify threads/process based task setup"),
 	OPT_END()
 };
 
@@ -42,59 +52,106 @@ static const char * const bench_sched_pipe_usage[] = {
 	NULL
 };
 
-int bench_sched_pipe(int argc, const char **argv,
-		     const char *prefix __used)
+static void *worker_thread(void *__tdata)
 {
-	int pipe_1[2], pipe_2[2];
+	struct thread_data *td = __tdata;
 	int m = 0, i;
+	int ret;
+
+	for (i = 0; i < loops; i++) {
+		if (!td->nr) {
+			ret = read(td->pipe_read, &m, sizeof(int));
+			BUG_ON(ret != sizeof(int));
+			ret = write(td->pipe_write, &m, sizeof(int));
+			BUG_ON(ret != sizeof(int));
+		} else {
+			ret = write(td->pipe_write, &m, sizeof(int));
+			BUG_ON(ret != sizeof(int));
+			ret = read(td->pipe_read, &m, sizeof(int));
+			BUG_ON(ret != sizeof(int));
+		}
+	}
+
+	return NULL;
+}
+
+int bench_sched_pipe(int argc, const char **argv, const char *prefix __maybe_unused)
+{
+	struct thread_data threads[2], *td;
+	int pipe_1[2], pipe_2[2];
 	struct timeval start, stop, diff;
 	unsigned long long result_usec = 0;
+	int nr_threads = 2;
+	int t;
 
 	/*
 	 * why does "ret" exist?
 	 * discarding returned value of read(), write()
 	 * causes error in building environment for perf
 	 */
-	int ret, wait_stat;
-	pid_t pid, retpid;
+	int __maybe_unused ret, wait_stat;
+	pid_t pid, retpid __maybe_unused;
 
-	argc = parse_options(argc, argv, options,
-			     bench_sched_pipe_usage, 0);
+	argc = parse_options(argc, argv, options, bench_sched_pipe_usage, 0);
 
-	assert(!pipe(pipe_1));
-	assert(!pipe(pipe_2));
-
-	pid = fork();
-	assert(pid >= 0);
+	BUG_ON(pipe(pipe_1));
+	BUG_ON(pipe(pipe_2));
 
 	gettimeofday(&start, NULL);
 
-	if (!pid) {
-		for (i = 0; i < loops; i++) {
-			ret = read(pipe_1[0], &m, sizeof(int));
-			ret = write(pipe_2[1], &m, sizeof(int));
-		}
-	} else {
-		for (i = 0; i < loops; i++) {
-			ret = write(pipe_1[1], &m, sizeof(int));
-			ret = read(pipe_2[0], &m, sizeof(int));
+	for (t = 0; t < nr_threads; t++) {
+		td = threads + t;
+
+		td->nr = t;
+
+		if (t == 0) {
+			td->pipe_read = pipe_1[0];
+			td->pipe_write = pipe_2[1];
+		} else {
+			td->pipe_write = pipe_1[1];
+			td->pipe_read = pipe_2[0];
 		}
 	}
 
-	gettimeofday(&stop, NULL);
-	timersub(&stop, &start, &diff);
 
-	if (pid) {
+	if (threaded) {
+
+		for (t = 0; t < nr_threads; t++) {
+			td = threads + t;
+
+			ret = pthread_create(&td->pthread, NULL, worker_thread, td);
+			BUG_ON(ret);
+		}
+
+		for (t = 0; t < nr_threads; t++) {
+			td = threads + t;
+
+			ret = pthread_join(td->pthread, NULL);
+			BUG_ON(ret);
+		}
+
+	} else {
+		pid = fork();
+		assert(pid >= 0);
+
+		if (!pid) {
+			worker_thread(threads + 0);
+			exit(0);
+		} else {
+			worker_thread(threads + 1);
+		}
+
 		retpid = waitpid(pid, &wait_stat, 0);
 		assert((retpid == pid) && WIFEXITED(wait_stat));
-	} else {
-		exit(0);
 	}
 
+	gettimeofday(&stop, NULL);
+	timersub(&stop, &start, &diff);
+
 	switch (bench_format) {
 	case BENCH_FORMAT_DEFAULT:
-		printf("# Executed %d pipe operations between two tasks\n\n",
-			loops);
+		printf("# Executed %d pipe operations between two %s\n\n",
+			loops, threaded ? "threads" : "processes");
 
 		result_usec = diff.tv_sec * 1000000;
 		result_usec += diff.tv_usec;
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 96db5248e99..1ec429fef2b 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -8,7 +8,6 @@
 #include "builtin.h"
 
 #include "util/util.h"
-
 #include "util/color.h"
 #include <linux/list.h>
 #include "util/cache.h"
@@ -18,6 +17,9 @@
 #include "perf.h"
 #include "util/debug.h"
 
+#include "util/evlist.h"
+#include "util/evsel.h"
+#include "util/annotate.h"
 #include "util/event.h"
 #include "util/parse-options.h"
 #include "util/parse-events.h"
@@ -25,23 +27,35 @@
 #include "util/sort.h"
 #include "util/hist.h"
 #include "util/session.h"
+#include "util/tool.h"
+#include "util/data.h"
+#include "arch/common.h"
+
+#include <dlfcn.h>
+#include <linux/bitmap.h>
+
+struct perf_annotate {
+	struct perf_tool tool;
+	bool	   force, use_tui, use_stdio, use_gtk;
+	bool	   full_paths;
+	bool	   print_line;
+	bool	   skip_missing;
+	const char *sym_hist_filter;
+	const char *cpu_list;
+	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
+};
 
-static char		const *input_name = "perf.data";
-
-static bool		force;
-
-static bool		full_paths;
-
-static bool		print_line;
-
-static const char *sym_hist_filter;
-
-static int hists__add_entry(struct hists *self, struct addr_location *al)
+static int perf_evsel__add_sample(struct perf_evsel *evsel,
+				  struct perf_sample *sample __maybe_unused,
+				  struct addr_location *al,
+				  struct perf_annotate *ann)
 {
 	struct hist_entry *he;
+	int ret;
 
-	if (sym_hist_filter != NULL &&
-	    (al->sym == NULL || strcmp(sym_hist_filter, al->sym->name) != 0)) {
+	if (ann->sym_hist_filter != NULL &&
+	    (al->sym == NULL ||
+	     strcmp(ann->sym_hist_filter, al->sym->name) != 0)) {
 		/* We're only interested in a symbol named sym_hist_filter */
 		if (al->sym != NULL) {
 			rb_erase(&al->sym->rb_node,
@@ -51,27 +65,35 @@ static int hists__add_entry(struct hists *self, struct addr_location *al)
 		return 0;
 	}
 
-	he = __hists__add_entry(self, al, NULL, 1);
+	he = __hists__add_entry(&evsel->hists, al, NULL, NULL, NULL, 1, 1, 0,
+				true);
 	if (he == NULL)
 		return -ENOMEM;
 
-	return hist_entry__inc_addr_samples(he, al->addr);
+	ret = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
+	hists__inc_nr_samples(&evsel->hists, true);
+	return ret;
 }
 
-static int process_sample_event(event_t *event, struct perf_session *session)
+static int process_sample_event(struct perf_tool *tool,
+				union perf_event *event,
+				struct perf_sample *sample,
+				struct perf_evsel *evsel,
+				struct machine *machine)
 {
+	struct perf_annotate *ann = container_of(tool, struct perf_annotate, tool);
 	struct addr_location al;
 
-	dump_printf("(IP, %d): %d: %#Lx\n", event->header.misc,
-		    event->ip.pid, event->ip.ip);
-
-	if (event__preprocess_sample(event, session, &al, NULL) < 0) {
+	if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
 		pr_warning("problem processing %d event, skipping it.\n",
 			   event->header.type);
 		return -1;
 	}
 
-	if (!al.filtered && hists__add_entry(&session->hists, &al)) {
+	if (ann->cpu_list && !test_bit(sample->cpu, ann->cpu_bitmap))
+		return 0;
+
+	if (!al.filtered && perf_evsel__add_sample(evsel, sample, &al, ann)) {
 		pr_warning("problem incrementing symbol count, "
 			   "skipping event\n");
 		return -1;
@@ -80,316 +102,121 @@ static int process_sample_event(event_t *event, struct perf_session *session)
 	return 0;
 }
 
-static int objdump_line__print(struct objdump_line *self,
-			       struct list_head *head,
-			       struct hist_entry *he, u64 len)
-{
-	struct symbol *sym = he->ms.sym;
-	static const char *prev_line;
-	static const char *prev_color;
-
-	if (self->offset != -1) {
-		const char *path = NULL;
-		unsigned int hits = 0;
-		double percent = 0.0;
-		const char *color;
-		struct sym_priv *priv = symbol__priv(sym);
-		struct sym_ext *sym_ext = priv->ext;
-		struct sym_hist *h = priv->hist;
-		s64 offset = self->offset;
-		struct objdump_line *next = objdump__get_next_ip_line(head, self);
-
-		while (offset < (s64)len &&
-		       (next == NULL || offset < next->offset)) {
-			if (sym_ext) {
-				if (path == NULL)
-					path = sym_ext[offset].path;
-				percent += sym_ext[offset].percent;
-			} else
-				hits += h->ip[offset];
-
-			++offset;
-		}
-
-		if (sym_ext == NULL && h->sum)
-			percent = 100.0 * hits / h->sum;
-
-		color = get_percent_color(percent);
-
-		/*
-		 * Also color the filename and line if needed, with
-		 * the same color than the percentage. Don't print it
-		 * twice for close colored ip with the same filename:line
-		 */
-		if (path) {
-			if (!prev_line || strcmp(prev_line, path)
-				       || color != prev_color) {
-				color_fprintf(stdout, color, " %s", path);
-				prev_line = path;
-				prev_color = color;
-			}
-		}
-
-		color_fprintf(stdout, color, " %7.2f", percent);
-		printf(" :	");
-		color_fprintf(stdout, PERF_COLOR_BLUE, "%s\n", self->line);
-	} else {
-		if (!*self->line)
-			printf("         :\n");
-		else
-			printf("         :	%s\n", self->line);
-	}
-
-	return 0;
-}
-
-static struct rb_root root_sym_ext;
-
-static void insert_source_line(struct sym_ext *sym_ext)
-{
-	struct sym_ext *iter;
-	struct rb_node **p = &root_sym_ext.rb_node;
-	struct rb_node *parent = NULL;
-
-	while (*p != NULL) {
-		parent = *p;
-		iter = rb_entry(parent, struct sym_ext, node);
-
-		if (sym_ext->percent > iter->percent)
-			p = &(*p)->rb_left;
-		else
-			p = &(*p)->rb_right;
-	}
-
-	rb_link_node(&sym_ext->node, parent, p);
-	rb_insert_color(&sym_ext->node, &root_sym_ext);
-}
-
-static void free_source_line(struct hist_entry *he, int len)
-{
-	struct sym_priv *priv = symbol__priv(he->ms.sym);
-	struct sym_ext *sym_ext = priv->ext;
-	int i;
-
-	if (!sym_ext)
-		return;
-
-	for (i = 0; i < len; i++)
-		free(sym_ext[i].path);
-	free(sym_ext);
-
-	priv->ext = NULL;
-	root_sym_ext = RB_ROOT;
-}
-
-/* Get the filename:line for the colored entries */
-static void
-get_source_line(struct hist_entry *he, int len, const char *filename)
-{
-	struct symbol *sym = he->ms.sym;
-	u64 start;
-	int i;
-	char cmd[PATH_MAX * 2];
-	struct sym_ext *sym_ext;
-	struct sym_priv *priv = symbol__priv(sym);
-	struct sym_hist *h = priv->hist;
-
-	if (!h->sum)
-		return;
-
-	sym_ext = priv->ext = calloc(len, sizeof(struct sym_ext));
-	if (!priv->ext)
-		return;
-
-	start = he->ms.map->unmap_ip(he->ms.map, sym->start);
-
-	for (i = 0; i < len; i++) {
-		char *path = NULL;
-		size_t line_len;
-		u64 offset;
-		FILE *fp;
-
-		sym_ext[i].percent = 100.0 * h->ip[i] / h->sum;
-		if (sym_ext[i].percent <= 0.5)
-			continue;
-
-		offset = start + i;
-		sprintf(cmd, "addr2line -e %s %016llx", filename, offset);
-		fp = popen(cmd, "r");
-		if (!fp)
-			continue;
-
-		if (getline(&path, &line_len, fp) < 0 || !line_len)
-			goto next;
-
-		sym_ext[i].path = malloc(sizeof(char) * line_len + 1);
-		if (!sym_ext[i].path)
-			goto next;
-
-		strcpy(sym_ext[i].path, path);
-		insert_source_line(&sym_ext[i]);
-
-	next:
-		pclose(fp);
-	}
-}
-
-static void print_summary(const char *filename)
-{
-	struct sym_ext *sym_ext;
-	struct rb_node *node;
-
-	printf("\nSorted summary for file %s\n", filename);
-	printf("----------------------------------------------\n\n");
-
-	if (RB_EMPTY_ROOT(&root_sym_ext)) {
-		printf(" Nothing higher than %1.1f%%\n", MIN_GREEN);
-		return;
-	}
-
-	node = rb_first(&root_sym_ext);
-	while (node) {
-		double percent;
-		const char *color;
-		char *path;
-
-		sym_ext = rb_entry(node, struct sym_ext, node);
-		percent = sym_ext->percent;
-		color = get_percent_color(percent);
-		path = sym_ext->path;
-
-		color_fprintf(stdout, color, " %7.2f %s", percent, path);
-		node = rb_next(node);
-	}
-}
-
-static void hist_entry__print_hits(struct hist_entry *self)
+static int hist_entry__tty_annotate(struct hist_entry *he,
+				    struct perf_evsel *evsel,
+				    struct perf_annotate *ann)
 {
-	struct symbol *sym = self->ms.sym;
-	struct sym_priv *priv = symbol__priv(sym);
-	struct sym_hist *h = priv->hist;
-	u64 len = sym->end - sym->start, offset;
-
-	for (offset = 0; offset < len; ++offset)
-		if (h->ip[offset] != 0)
-			printf("%*Lx: %Lu\n", BITS_PER_LONG / 2,
-			       sym->start + offset, h->ip[offset]);
-	printf("%*s: %Lu\n", BITS_PER_LONG / 2, "h->sum", h->sum);
+	return symbol__tty_annotate(he->ms.sym, he->ms.map, evsel,
+				    ann->print_line, ann->full_paths, 0, 0);
 }
 
-static int hist_entry__tty_annotate(struct hist_entry *he)
+static void hists__find_annotations(struct hists *hists,
+				    struct perf_evsel *evsel,
+				    struct perf_annotate *ann)
 {
-	struct map *map = he->ms.map;
-	struct dso *dso = map->dso;
-	struct symbol *sym = he->ms.sym;
-	const char *filename = dso->long_name, *d_filename;
-	u64 len;
-	LIST_HEAD(head);
-	struct objdump_line *pos, *n;
-
-	if (hist_entry__annotate(he, &head) < 0)
-		return -1;
-
-	if (full_paths)
-		d_filename = filename;
-	else
-		d_filename = basename(filename);
-
-	len = sym->end - sym->start;
-
-	if (print_line) {
-		get_source_line(he, len, filename);
-		print_summary(filename);
-	}
-
-	printf("\n\n------------------------------------------------\n");
-	printf(" Percent |	Source code & Disassembly of %s\n", d_filename);
-	printf("------------------------------------------------\n");
-
-	if (verbose)
-		hist_entry__print_hits(he);
-
-	list_for_each_entry_safe(pos, n, &head, node) {
-		objdump_line__print(pos, &head, he, len);
-		list_del(&pos->node);
-		objdump_line__free(pos);
-	}
-
-	if (print_line)
-		free_source_line(he, len);
-
-	return 0;
-}
-
-static void hists__find_annotations(struct hists *self)
-{
-	struct rb_node *first = rb_first(&self->entries), *nd = first;
-	int key = KEY_RIGHT;
+	struct rb_node *nd = rb_first(&hists->entries), *next;
+	int key = K_RIGHT;
 
 	while (nd) {
 		struct hist_entry *he = rb_entry(nd, struct hist_entry, rb_node);
-		struct sym_priv *priv;
+		struct annotation *notes;
 
 		if (he->ms.sym == NULL || he->ms.map->dso->annotate_warned)
 			goto find_next;
 
-		priv = symbol__priv(he->ms.sym);
-		if (priv->hist == NULL) {
+		notes = symbol__annotation(he->ms.sym);
+		if (notes->src == NULL) {
 find_next:
-			if (key == KEY_LEFT)
+			if (key == K_LEFT)
 				nd = rb_prev(nd);
 			else
 				nd = rb_next(nd);
 			continue;
 		}
 
-		if (use_browser > 0) {
-			key = hist_entry__tui_annotate(he);
-			if (is_exit_key(key))
-				break;
+		if (use_browser == 2) {
+			int ret;
+			int (*annotate)(struct hist_entry *he,
+					struct perf_evsel *evsel,
+					struct hist_browser_timer *hbt);
+
+			annotate = dlsym(perf_gtk_handle,
+					 "hist_entry__gtk_annotate");
+			if (annotate == NULL) {
+				ui__error("GTK browser not found!\n");
+				return;
+			}
+
+			ret = annotate(he, evsel, NULL);
+			if (!ret || !ann->skip_missing)
+				return;
+
+			/* skip missing symbols */
+			nd = rb_next(nd);
+		} else if (use_browser == 1) {
+			key = hist_entry__tui_annotate(he, evsel, NULL);
 			switch (key) {
-			case KEY_RIGHT:
-			case '\t':
-				nd = rb_next(nd);
+			case -1:
+				if (!ann->skip_missing)
+					return;
+				/* fall through */
+			case K_RIGHT:
+				next = rb_next(nd);
 				break;
-			case KEY_LEFT:
-				if (nd == first)
-					continue;
-				nd = rb_prev(nd);
-			default:
+			case K_LEFT:
+				next = rb_prev(nd);
 				break;
+			default:
+				return;
 			}
+
+			if (next != NULL)
+				nd = next;
 		} else {
-			hist_entry__tty_annotate(he);
+			hist_entry__tty_annotate(he, evsel, ann);
 			nd = rb_next(nd);
 			/*
 			 * Since we have a hist_entry per IP for the same
-			 * symbol, free he->ms.sym->hist to signal we already
+			 * symbol, free he->ms.sym->src to signal we already
 			 * processed this symbol.
 			 */
-			free(priv->hist);
-			priv->hist = NULL;
+			zfree(&notes->src);
 		}
 	}
 }
 
-static struct perf_event_ops event_ops = {
-	.sample	= process_sample_event,
-	.mmap	= event__process_mmap,
-	.comm	= event__process_comm,
-	.fork	= event__process_task,
-};
-
-static int __cmd_annotate(void)
+static int __cmd_annotate(struct perf_annotate *ann)
 {
 	int ret;
 	struct perf_session *session;
-
-	session = perf_session__new(input_name, O_RDONLY, force, false);
+	struct perf_evsel *pos;
+	u64 total_nr_samples;
+	struct perf_data_file file = {
+		.path  = input_name,
+		.mode  = PERF_DATA_MODE_READ,
+		.force = ann->force,
+	};
+
+	session = perf_session__new(&file, false, &ann->tool);
 	if (session == NULL)
 		return -ENOMEM;
 
-	ret = perf_session__process_events(session, &event_ops);
+	machines__set_symbol_filter(&session->machines, symbol__annotate_init);
+
+	if (ann->cpu_list) {
+		ret = perf_session__cpu_bitmap(session, ann->cpu_list,
+					       ann->cpu_bitmap);
+		if (ret)
+			goto out_delete;
+	}
+
+	if (!objdump_path) {
+		ret = perf_session_env__lookup_objdump(&session->header.env);
+		if (ret)
+			goto out_delete;
+	}
+
+	ret = perf_session__process_events(session, &ann->tool);
 	if (ret)
 		goto out_delete;
 
@@ -404,72 +231,147 @@ static int __cmd_annotate(void)
 	if (verbose > 2)
 		perf_session__fprintf_dsos(session, stdout);
 
-	hists__collapse_resort(&session->hists);
-	hists__output_resort(&session->hists);
-	hists__find_annotations(&session->hists);
-out_delete:
-	perf_session__delete(session);
+	total_nr_samples = 0;
+	evlist__for_each(session->evlist, pos) {
+		struct hists *hists = &pos->hists;
+		u32 nr_samples = hists->stats.nr_events[PERF_RECORD_SAMPLE];
+
+		if (nr_samples > 0) {
+			total_nr_samples += nr_samples;
+			hists__collapse_resort(hists, NULL);
+			hists__output_resort(hists);
+
+			if (symbol_conf.event_group &&
+			    !perf_evsel__is_group_leader(pos))
+				continue;
+
+			hists__find_annotations(hists, pos, ann);
+		}
+	}
+
+	if (total_nr_samples == 0) {
+		ui__error("The %s file has no samples!\n", file.path);
+		goto out_delete;
+	}
 
+	if (use_browser == 2) {
+		void (*show_annotations)(void);
+
+		show_annotations = dlsym(perf_gtk_handle,
+					 "perf_gtk__show_annotations");
+		if (show_annotations == NULL) {
+			ui__error("GTK browser not found!\n");
+			goto out_delete;
+		}
+		show_annotations();
+	}
+
+out_delete:
+	/*
+	 * Speed up the exit process, for large files this can
+	 * take quite a while.
+	 *
+	 * XXX Enable this when using valgrind or if we ever
+	 * librarize this command.
+	 *
+	 * Also experiment with obstacks to see how much speed
+	 * up we'll get here.
+	 *
+	 * perf_session__delete(session);
+	 */
 	return ret;
 }
 
 static const char * const annotate_usage[] = {
-	"perf annotate [<options>] <command>",
+	"perf annotate [<options>]",
 	NULL
 };
 
-static const struct option options[] = {
+int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
+{
+	struct perf_annotate annotate = {
+		.tool = {
+			.sample	= process_sample_event,
+			.mmap	= perf_event__process_mmap,
+			.mmap2	= perf_event__process_mmap2,
+			.comm	= perf_event__process_comm,
+			.exit	= perf_event__process_exit,
+			.fork	= perf_event__process_fork,
+			.ordered_samples = true,
+			.ordering_requires_timestamps = true,
+		},
+	};
+	const struct option options[] = {
 	OPT_STRING('i', "input", &input_name, "file",
 		    "input file name"),
 	OPT_STRING('d', "dsos", &symbol_conf.dso_list_str, "dso[,dso...]",
 		   "only consider symbols in these dsos"),
-	OPT_STRING('s', "symbol", &sym_hist_filter, "symbol",
+	OPT_STRING('s', "symbol", &annotate.sym_hist_filter, "symbol",
 		    "symbol to annotate"),
-	OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
+	OPT_BOOLEAN('f', "force", &annotate.force, "don't complain, do it"),
 	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose (show symbol address, etc)"),
 	OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
 		    "dump raw trace in ASCII"),
+	OPT_BOOLEAN(0, "gtk", &annotate.use_gtk, "Use the GTK interface"),
+	OPT_BOOLEAN(0, "tui", &annotate.use_tui, "Use the TUI interface"),
+	OPT_BOOLEAN(0, "stdio", &annotate.use_stdio, "Use the stdio interface"),
 	OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
 		   "file", "vmlinux pathname"),
 	OPT_BOOLEAN('m', "modules", &symbol_conf.use_modules,
 		    "load module symbols - WARNING: use only with -k and LIVE kernel"),
-	OPT_BOOLEAN('l', "print-line", &print_line,
+	OPT_BOOLEAN('l', "print-line", &annotate.print_line,
 		    "print matching source lines (may be slow)"),
-	OPT_BOOLEAN('P', "full-paths", &full_paths,
+	OPT_BOOLEAN('P', "full-paths", &annotate.full_paths,
 		    "Don't shorten the displayed pathnames"),
+	OPT_BOOLEAN(0, "skip-missing", &annotate.skip_missing,
+		    "Skip symbols that cannot be annotated"),
+	OPT_STRING('C', "cpu", &annotate.cpu_list, "cpu", "list of cpus to profile"),
+	OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
+		   "Look for files with symbols relative to this directory"),
+	OPT_BOOLEAN(0, "source", &symbol_conf.annotate_src,
+		    "Interleave source code with assembly code (default)"),
+	OPT_BOOLEAN(0, "asm-raw", &symbol_conf.annotate_asm_raw,
+		    "Display raw encoding of assembly instructions (default)"),
+	OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style",
+		   "Specify disassembler style (e.g. -M intel for intel syntax)"),
+	OPT_STRING(0, "objdump", &objdump_path, "path",
+		   "objdump binary to use for disassembly and annotations"),
+	OPT_BOOLEAN(0, "group", &symbol_conf.event_group,
+		    "Show event group information together"),
 	OPT_END()
-};
+	};
 
-int cmd_annotate(int argc, const char **argv, const char *prefix __used)
-{
 	argc = parse_options(argc, argv, options, annotate_usage, 0);
 
-	setup_browser();
+	if (annotate.use_stdio)
+		use_browser = 0;
+	else if (annotate.use_tui)
+		use_browser = 1;
+	else if (annotate.use_gtk)
+		use_browser = 2;
+
+	setup_browser(true);
 
-	symbol_conf.priv_size = sizeof(struct sym_priv);
+	symbol_conf.priv_size = sizeof(struct annotation);
 	symbol_conf.try_vmlinux_path = true;
 
 	if (symbol__init() < 0)
 		return -1;
 
-	setup_sorting(annotate_usage, options);
+	if (setup_sorting() < 0)
+		usage_with_options(annotate_usage, options);
 
 	if (argc) {
 		/*
-		 * Special case: if there's an argument left then assume tha
+		 * Special case: if there's an argument left then assume that
 		 * it's a symbol filter:
 		 */
 		if (argc > 1)
 			usage_with_options(annotate_usage, options);
 
-		sym_hist_filter = argv[0];
-	}
-
-	if (field_sep && *field_sep == '.') {
-		pr_err("'.' is the only non valid --field-separator argument\n");
-		return -1;
+		annotate.sym_hist_filter = argv[0];
 	}
 
-	return __cmd_annotate();
+	return __cmd_annotate(&annotate);
 }
diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c
index fcb96269852..1e6e7771054 100644
--- a/tools/perf/builtin-bench.c
+++ b/tools/perf/builtin-bench.c
@@ -1,21 +1,19 @@
 /*
- *
  * builtin-bench.c
  *
- * General benchmarking subsystem provided by perf
+ * General benchmarking collections provided by perf
  *
  * Copyright (C) 2009, Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp>
- *
  */
 
 /*
+ * Available benchmark collection list:
  *
- * Available subsystem list:
- *  sched ... scheduler and IPC mechanism
+ *  sched ... scheduler and IPC performance
  *  mem   ... memory access performance
- *
+ *  numa  ... NUMA scheduling and MM performance
+ *  futex ... Futex performance
  */
-
 #include "perf.h"
 #include "util/util.h"
 #include "util/parse-options.h"
@@ -25,92 +23,101 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
+#include <sys/prctl.h>
+
+typedef int (*bench_fn_t)(int argc, const char **argv, const char *prefix);
+
+struct bench {
+	const char	*name;
+	const char	*summary;
+	bench_fn_t	fn;
+};
+
+#ifdef HAVE_LIBNUMA_SUPPORT
+static struct bench numa_benchmarks[] = {
+	{ "mem",	"Benchmark for NUMA workloads",			bench_numa		},
+	{ "all",	"Test all NUMA benchmarks",			NULL			},
+	{ NULL,		NULL,						NULL			}
+};
+#endif
 
-struct bench_suite {
-	const char *name;
-	const char *summary;
-	int (*fn)(int, const char **, const char *);
+static struct bench sched_benchmarks[] = {
+	{ "messaging",	"Benchmark for scheduling and IPC",		bench_sched_messaging	},
+	{ "pipe",	"Benchmark for pipe() between two processes",	bench_sched_pipe	},
+	{ "all",	"Test all scheduler benchmarks",		NULL			},
+	{ NULL,		NULL,						NULL			}
 };
-						\
-/* sentinel: easy for help */
-#define suite_all { "all", "test all suite (pseudo suite)", NULL }
-
-static struct bench_suite sched_suites[] = {
-	{ "messaging",
-	  "Benchmark for scheduler and IPC mechanisms",
-	  bench_sched_messaging },
-	{ "pipe",
-	  "Flood of communication over pipe() between two processes",
-	  bench_sched_pipe      },
-	suite_all,
-	{ NULL,
-	  NULL,
-	  NULL                  }
+
+static struct bench mem_benchmarks[] = {
+	{ "memcpy",	"Benchmark for memcpy()",			bench_mem_memcpy	},
+	{ "memset",	"Benchmark for memset() tests",			bench_mem_memset	},
+	{ "all",	"Test all memory benchmarks",			NULL			},
+	{ NULL,		NULL,						NULL			}
 };
 
-static struct bench_suite mem_suites[] = {
-	{ "memcpy",
-	  "Simple memory copy in various ways",
-	  bench_mem_memcpy },
-	suite_all,
-	{ NULL,
-	  NULL,
-	  NULL             }
+static struct bench futex_benchmarks[] = {
+	{ "hash",	"Benchmark for futex hash table",               bench_futex_hash	},
+	{ "wake",	"Benchmark for futex wake calls",               bench_futex_wake	},
+	{ "requeue",	"Benchmark for futex requeue calls",            bench_futex_requeue	},
+	{ "all",	"Test all futex benchmarks",			NULL			},
+	{ NULL,		NULL,						NULL			}
 };
 
-struct bench_subsys {
-	const char *name;
-	const char *summary;
-	struct bench_suite *suites;
+struct collection {
+	const char	*name;
+	const char	*summary;
+	struct bench	*benchmarks;
 };
 
-static struct bench_subsys subsystems[] = {
-	{ "sched",
-	  "scheduler and IPC mechanism",
-	  sched_suites },
-	{ "mem",
-	  "memory access performance",
-	  mem_suites },
-	{ "all",		/* sentinel: easy for help */
-	  "test all subsystem (pseudo subsystem)",
-	  NULL },
-	{ NULL,
-	  NULL,
-	  NULL       }
+static struct collection collections[] = {
+	{ "sched",	"Scheduler and IPC benchmarks",			sched_benchmarks	},
+	{ "mem",	"Memory access benchmarks",			mem_benchmarks		},
+#ifdef HAVE_LIBNUMA_SUPPORT
+	{ "numa",	"NUMA scheduling and MM benchmarks",		numa_benchmarks		},
+#endif
+	{"futex",       "Futex stressing benchmarks",                   futex_benchmarks        },
+	{ "all",	"All benchmarks",				NULL			},
+	{ NULL,		NULL,						NULL			}
 };
 
-static void dump_suites(int subsys_index)
+/* Iterate over all benchmark collections: */
+#define for_each_collection(coll) \
+	for (coll = collections; coll->name; coll++)
+
+/* Iterate over all benchmarks within a collection: */
+#define for_each_bench(coll, bench) \
+	for (bench = coll->benchmarks; bench && bench->name; bench++)
+
+static void dump_benchmarks(struct collection *coll)
 {
-	int i;
+	struct bench *bench;
 
-	printf("# List of available suites for %s...\n\n",
-	       subsystems[subsys_index].name);
+	printf("\n        # List of available benchmarks for collection '%s':\n\n", coll->name);
 
-	for (i = 0; subsystems[subsys_index].suites[i].name; i++)
-		printf("%14s: %s\n",
-		       subsystems[subsys_index].suites[i].name,
-		       subsystems[subsys_index].suites[i].summary);
+	for_each_bench(coll, bench)
+		printf("%14s: %s\n", bench->name, bench->summary);
 
 	printf("\n");
-	return;
 }
 
 static const char *bench_format_str;
+
+/* Output/formatting style, exported to benchmark modules: */
 int bench_format = BENCH_FORMAT_DEFAULT;
 
 static const struct option bench_options[] = {
-	OPT_STRING('f', "format", &bench_format_str, "default",
-		    "Specify format style"),
+	OPT_STRING('f', "format", &bench_format_str, "default", "Specify format style"),
 	OPT_END()
 };
 
 static const char * const bench_usage[] = {
-	"perf bench [<common options>] <subsystem> <suite> [<options>]",
+	"perf bench [<common options>] <collection> <benchmark> [<options>]",
 	NULL
 };
 
 static void print_usage(void)
 {
+	struct collection *coll;
 	int i;
 
 	printf("Usage: \n");
@@ -118,11 +125,10 @@ static void print_usage(void)
 		printf("\t%s\n", bench_usage[i]);
 	printf("\n");
 
-	printf("# List of available subsystems...\n\n");
+	printf("        # List of all available benchmark collections:\n\n");
 
-	for (i = 0; subsystems[i].name; i++)
-		printf("%14s: %s\n",
-		       subsystems[i].name, subsystems[i].summary);
+	for_each_collection(coll)
+		printf("%14s: %s\n", coll->name, coll->summary);
 	printf("\n");
 }
 
@@ -139,43 +145,74 @@ static int bench_str2int(const char *str)
 	return BENCH_FORMAT_UNKNOWN;
 }
 
-static void all_suite(struct bench_subsys *subsys)	  /* FROM HERE */
+/*
+ * Run a specific benchmark but first rename the running task's ->comm[]
+ * to something meaningful:
+ */
+static int run_bench(const char *coll_name, const char *bench_name, bench_fn_t fn,
+		     int argc, const char **argv, const char *prefix)
 {
-	int i;
+	int size;
+	char *name;
+	int ret;
+
+	size = strlen(coll_name) + 1 + strlen(bench_name) + 1;
+
+	name = zalloc(size);
+	BUG_ON(!name);
+
+	scnprintf(name, size, "%s-%s", coll_name, bench_name);
+
+	prctl(PR_SET_NAME, name);
+	argv[0] = name;
+
+	ret = fn(argc, argv, prefix);
+
+	free(name);
+
+	return ret;
+}
+
+static void run_collection(struct collection *coll)
+{
+	struct bench *bench;
 	const char *argv[2];
-	struct bench_suite *suites = subsys->suites;
 
 	argv[1] = NULL;
 	/*
 	 * TODO:
-	 * preparing preset parameters for
+	 *
+	 * Preparing preset parameters for
 	 * embedded, ordinary PC, HPC, etc...
-	 * will be helpful
+	 * would be helpful.
 	 */
-	for (i = 0; suites[i].fn; i++) {
-		printf("# Running %s/%s benchmark...\n",
-		       subsys->name,
-		       suites[i].name);
-
-		argv[1] = suites[i].name;
-		suites[i].fn(1, argv, NULL);
+	for_each_bench(coll, bench) {
+		if (!bench->fn)
+			break;
+		printf("# Running %s/%s benchmark...\n", coll->name, bench->name);
+		fflush(stdout);
+
+		argv[1] = bench->name;
+		run_bench(coll->name, bench->name, bench->fn, 1, argv, NULL);
 		printf("\n");
 	}
 }
 
-static void all_subsystem(void)
+static void run_all_collections(void)
 {
-	int i;
-	for (i = 0; subsystems[i].suites; i++)
-		all_suite(&subsystems[i]);
+	struct collection *coll;
+
+	for_each_collection(coll)
+		run_collection(coll);
 }
 
-int cmd_bench(int argc, const char **argv, const char *prefix __used)
+int cmd_bench(int argc, const char **argv, const char *prefix __maybe_unused)
 {
-	int i, j, status = 0;
+	struct collection *coll;
+	int ret = 0;
 
 	if (argc < 2) {
-		/* No subsystem specified. */
+		/* No collection specified. */
 		print_usage();
 		goto end;
 	}
@@ -185,7 +222,7 @@ int cmd_bench(int argc, const char **argv, const char *prefix __used)
 
 	bench_format = bench_str2int(bench_format_str);
 	if (bench_format == BENCH_FORMAT_UNKNOWN) {
-		printf("Unknown format descriptor:%s\n", bench_format_str);
+		printf("Unknown format descriptor: '%s'\n", bench_format_str);
 		goto end;
 	}
 
@@ -195,51 +232,51 @@ int cmd_bench(int argc, const char **argv, const char *prefix __used)
 	}
 
 	if (!strcmp(argv[0], "all")) {
-		all_subsystem();
+		run_all_collections();
 		goto end;
 	}
 
-	for (i = 0; subsystems[i].name; i++) {
-		if (strcmp(subsystems[i].name, argv[0]))
+	for_each_collection(coll) {
+		struct bench *bench;
+
+		if (strcmp(coll->name, argv[0]))
 			continue;
 
 		if (argc < 2) {
-			/* No suite specified. */
-			dump_suites(i);
+			/* No bench specified. */
+			dump_benchmarks(coll);
 			goto end;
 		}
 
 		if (!strcmp(argv[1], "all")) {
-			all_suite(&subsystems[i]);
+			run_collection(coll);
 			goto end;
 		}
 
-		for (j = 0; subsystems[i].suites[j].name; j++) {
-			if (strcmp(subsystems[i].suites[j].name, argv[1]))
+		for_each_bench(coll, bench) {
+			if (strcmp(bench->name, argv[1]))
 				continue;
 
 			if (bench_format == BENCH_FORMAT_DEFAULT)
-				printf("# Running %s/%s benchmark...\n",
-				       subsystems[i].name,
-				       subsystems[i].suites[j].name);
-			status = subsystems[i].suites[j].fn(argc - 1,
-							    argv + 1, prefix);
+				printf("# Running '%s/%s' benchmark:\n", coll->name, bench->name);
+			fflush(stdout);
+			ret = run_bench(coll->name, bench->name, bench->fn, argc-1, argv+1, prefix);
 			goto end;
 		}
 
 		if (!strcmp(argv[1], "-h") || !strcmp(argv[1], "--help")) {
-			dump_suites(i);
+			dump_benchmarks(coll);
 			goto end;
 		}
 
-		printf("Unknown suite:%s for %s\n", argv[1], argv[0]);
-		status = 1;
+		printf("Unknown benchmark: '%s' for collection '%s'\n", argv[1], argv[0]);
+		ret = 1;
 		goto end;
 	}
 
-	printf("Unknown subsystem:%s\n", argv[0]);
-	status = 1;
+	printf("Unknown collection: '%s'\n", argv[0]);
+	ret = 1;
 
 end:
-	return status;
+	return ret;
 }
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index f8e3d185202..b22dbb16f87 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -6,6 +6,11 @@
  * Copyright (C) 2010, Red Hat Inc.
  * Copyright (C) 2010, Arnaldo Carvalho de Melo <acme@redhat.com>
  */
+#include <sys/types.h>
+#include <sys/time.h>
+#include <time.h>
+#include <dirent.h>
+#include <unistd.h>
 #include "builtin.h"
 #include "perf.h"
 #include "util/cache.h"
@@ -13,23 +18,168 @@
 #include "util/header.h"
 #include "util/parse-options.h"
 #include "util/strlist.h"
+#include "util/build-id.h"
+#include "util/session.h"
 #include "util/symbol.h"
 
-static char const *add_name_list_str, *remove_name_list_str;
+static int build_id_cache__kcore_buildid(const char *proc_dir, char *sbuildid)
+{
+	char root_dir[PATH_MAX];
+	char notes[PATH_MAX];
+	u8 build_id[BUILD_ID_SIZE];
+	char *p;
 
-static const char * const buildid_cache_usage[] = {
-	"perf buildid-cache [<options>]",
-	NULL
-};
+	strlcpy(root_dir, proc_dir, sizeof(root_dir));
 
-static const struct option buildid_cache_options[] = {
-	OPT_STRING('a', "add", &add_name_list_str,
-		   "file list", "file(s) to add"),
-	OPT_STRING('r', "remove", &remove_name_list_str, "file list",
-		    "file(s) to remove"),
-	OPT_INCR('v', "verbose", &verbose, "be more verbose"),
-	OPT_END()
-};
+	p = strrchr(root_dir, '/');
+	if (!p)
+		return -1;
+	*p = '\0';
+
+	scnprintf(notes, sizeof(notes), "%s/sys/kernel/notes", root_dir);
+
+	if (sysfs__read_build_id(notes, build_id, sizeof(build_id)))
+		return -1;
+
+	build_id__sprintf(build_id, sizeof(build_id), sbuildid);
+
+	return 0;
+}
+
+static int build_id_cache__kcore_dir(char *dir, size_t sz)
+{
+	struct timeval tv;
+	struct tm tm;
+	char dt[32];
+
+	if (gettimeofday(&tv, NULL) || !localtime_r(&tv.tv_sec, &tm))
+		return -1;
+
+	if (!strftime(dt, sizeof(dt), "%Y%m%d%H%M%S", &tm))
+		return -1;
+
+	scnprintf(dir, sz, "%s%02u", dt, (unsigned)tv.tv_usec / 10000);
+
+	return 0;
+}
+
+static bool same_kallsyms_reloc(const char *from_dir, char *to_dir)
+{
+	char from[PATH_MAX];
+	char to[PATH_MAX];
+	const char *name;
+	u64 addr1 = 0, addr2 = 0;
+	int i;
+
+	scnprintf(from, sizeof(from), "%s/kallsyms", from_dir);
+	scnprintf(to, sizeof(to), "%s/kallsyms", to_dir);
+
+	for (i = 0; (name = ref_reloc_sym_names[i]) != NULL; i++) {
+		addr1 = kallsyms__get_function_start(from, name);
+		if (addr1)
+			break;
+	}
+
+	if (name)
+		addr2 = kallsyms__get_function_start(to, name);
+
+	return addr1 == addr2;
+}
+
+static int build_id_cache__kcore_existing(const char *from_dir, char *to_dir,
+					  size_t to_dir_sz)
+{
+	char from[PATH_MAX];
+	char to[PATH_MAX];
+	char to_subdir[PATH_MAX];
+	struct dirent *dent;
+	int ret = -1;
+	DIR *d;
+
+	d = opendir(to_dir);
+	if (!d)
+		return -1;
+
+	scnprintf(from, sizeof(from), "%s/modules", from_dir);
+
+	while (1) {
+		dent = readdir(d);
+		if (!dent)
+			break;
+		if (dent->d_type != DT_DIR)
+			continue;
+		scnprintf(to, sizeof(to), "%s/%s/modules", to_dir,
+			  dent->d_name);
+		scnprintf(to_subdir, sizeof(to_subdir), "%s/%s",
+			  to_dir, dent->d_name);
+		if (!compare_proc_modules(from, to) &&
+		    same_kallsyms_reloc(from_dir, to_subdir)) {
+			strlcpy(to_dir, to_subdir, to_dir_sz);
+			ret = 0;
+			break;
+		}
+	}
+
+	closedir(d);
+
+	return ret;
+}
+
+static int build_id_cache__add_kcore(const char *filename, const char *debugdir)
+{
+	char dir[32], sbuildid[BUILD_ID_SIZE * 2 + 1];
+	char from_dir[PATH_MAX], to_dir[PATH_MAX];
+	char *p;
+
+	strlcpy(from_dir, filename, sizeof(from_dir));
+
+	p = strrchr(from_dir, '/');
+	if (!p || strcmp(p + 1, "kcore"))
+		return -1;
+	*p = '\0';
+
+	if (build_id_cache__kcore_buildid(from_dir, sbuildid))
+		return -1;
+
+	scnprintf(to_dir, sizeof(to_dir), "%s/[kernel.kcore]/%s",
+		  debugdir, sbuildid);
+
+	if (!build_id_cache__kcore_existing(from_dir, to_dir, sizeof(to_dir))) {
+		pr_debug("same kcore found in %s\n", to_dir);
+		return 0;
+	}
+
+	if (build_id_cache__kcore_dir(dir, sizeof(dir)))
+		return -1;
+
+	scnprintf(to_dir, sizeof(to_dir), "%s/[kernel.kcore]/%s/%s",
+		  debugdir, sbuildid, dir);
+
+	if (mkdir_p(to_dir, 0755))
+		return -1;
+
+	if (kcore_copy(from_dir, to_dir)) {
+		/* Remove YYYYmmddHHMMSShh directory */
+		if (!rmdir(to_dir)) {
+			p = strrchr(to_dir, '/');
+			if (p)
+				*p = '\0';
+			/* Try to remove buildid directory */
+			if (!rmdir(to_dir)) {
+				p = strrchr(to_dir, '/');
+				if (p)
+					*p = '\0';
+				/* Try to remove [kernel.kcore] directory */
+				rmdir(to_dir);
+			}
+		}
+		return -1;
+	}
+
+	pr_debug("kcore added to build-id cache directory %s\n", to_dir);
+
+	return 0;
+}
 
 static int build_id_cache__add_file(const char *filename, const char *debugdir)
 {
@@ -43,15 +193,16 @@ static int build_id_cache__add_file(const char *filename, const char *debugdir)
 	}
 
 	build_id__sprintf(build_id, sizeof(build_id), sbuild_id);
-	err = build_id_cache__add_s(sbuild_id, debugdir, filename, false);
+	err = build_id_cache__add_s(sbuild_id, debugdir, filename,
+				    false, false);
 	if (verbose)
 		pr_info("Adding %s %s: %s\n", sbuild_id, filename,
 			err ? "FAIL" : "Ok");
 	return err;
 }
 
-static int build_id_cache__remove_file(const char *filename __used,
-				       const char *debugdir __used)
+static int build_id_cache__remove_file(const char *filename,
+				       const char *debugdir)
 {
 	u8 build_id[BUILD_ID_SIZE];
 	char sbuild_id[BUILD_ID_SIZE * 2 + 1];
@@ -72,14 +223,113 @@ static int build_id_cache__remove_file(const char *filename __used,
 	return err;
 }
 
-static int __cmd_buildid_cache(void)
+static bool dso__missing_buildid_cache(struct dso *dso, int parm __maybe_unused)
+{
+	char filename[PATH_MAX];
+	u8 build_id[BUILD_ID_SIZE];
+
+	if (dso__build_id_filename(dso, filename, sizeof(filename)) &&
+	    filename__read_build_id(filename, build_id,
+				    sizeof(build_id)) != sizeof(build_id)) {
+		if (errno == ENOENT)
+			return false;
+
+		pr_warning("Problems with %s file, consider removing it from the cache\n", 
+			   filename);
+	} else if (memcmp(dso->build_id, build_id, sizeof(dso->build_id))) {
+		pr_warning("Problems with %s file, consider removing it from the cache\n", 
+			   filename);
+	}
+
+	return true;
+}
+
+static int build_id_cache__fprintf_missing(const char *filename, bool force, FILE *fp)
+{
+	struct perf_data_file file = {
+		.path  = filename,
+		.mode  = PERF_DATA_MODE_READ,
+		.force = force,
+	};
+	struct perf_session *session = perf_session__new(&file, false, NULL);
+	if (session == NULL)
+		return -1;
+
+	perf_session__fprintf_dsos_buildid(session, fp, dso__missing_buildid_cache, 0);
+	perf_session__delete(session);
+
+	return 0;
+}
+
+static int build_id_cache__update_file(const char *filename,
+				       const char *debugdir)
+{
+	u8 build_id[BUILD_ID_SIZE];
+	char sbuild_id[BUILD_ID_SIZE * 2 + 1];
+
+	int err;
+
+	if (filename__read_build_id(filename, &build_id, sizeof(build_id)) < 0) {
+		pr_debug("Couldn't read a build-id in %s\n", filename);
+		return -1;
+	}
+
+	build_id__sprintf(build_id, sizeof(build_id), sbuild_id);
+	err = build_id_cache__remove_s(sbuild_id, debugdir);
+	if (!err) {
+		err = build_id_cache__add_s(sbuild_id, debugdir, filename,
+					    false, false);
+	}
+	if (verbose)
+		pr_info("Updating %s %s: %s\n", sbuild_id, filename,
+			err ? "FAIL" : "Ok");
+
+	return err;
+}
+
+int cmd_buildid_cache(int argc, const char **argv,
+		      const char *prefix __maybe_unused)
 {
 	struct strlist *list;
 	struct str_node *pos;
+	int ret = 0;
+	bool force = false;
 	char debugdir[PATH_MAX];
+	char const *add_name_list_str = NULL,
+		   *remove_name_list_str = NULL,
+		   *missing_filename = NULL,
+		   *update_name_list_str = NULL,
+		   *kcore_filename;
 
-	snprintf(debugdir, sizeof(debugdir), "%s/%s", getenv("HOME"),
-		 DEBUG_CACHE_DIR);
+	const struct option buildid_cache_options[] = {
+	OPT_STRING('a', "add", &add_name_list_str,
+		   "file list", "file(s) to add"),
+	OPT_STRING('k', "kcore", &kcore_filename,
+		   "file", "kcore file to add"),
+	OPT_STRING('r', "remove", &remove_name_list_str, "file list",
+		    "file(s) to remove"),
+	OPT_STRING('M', "missing", &missing_filename, "file",
+		   "to find missing build ids in the cache"),
+	OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
+	OPT_STRING('u', "update", &update_name_list_str, "file list",
+		    "file(s) to update"),
+	OPT_INCR('v', "verbose", &verbose, "be more verbose"),
+	OPT_END()
+	};
+	const char * const buildid_cache_usage[] = {
+		"perf buildid-cache [<options>]",
+		NULL
+	};
+
+	argc = parse_options(argc, argv, buildid_cache_options,
+			     buildid_cache_usage, 0);
+
+	if (symbol__init() < 0)
+		return -1;
+
+	setup_pager();
+
+	snprintf(debugdir, sizeof(debugdir), "%s", buildid_dir);
 
 	if (add_name_list_str) {
 		list = strlist__new(true, add_name_list_str);
@@ -117,17 +367,30 @@ static int __cmd_buildid_cache(void)
 		}
 	}
 
-	return 0;
-}
+	if (missing_filename)
+		ret = build_id_cache__fprintf_missing(missing_filename, force, stdout);
 
-int cmd_buildid_cache(int argc, const char **argv, const char *prefix __used)
-{
-	argc = parse_options(argc, argv, buildid_cache_options,
-			     buildid_cache_usage, 0);
+	if (update_name_list_str) {
+		list = strlist__new(true, update_name_list_str);
+		if (list) {
+			strlist__for_each(pos, list)
+				if (build_id_cache__update_file(pos->s, debugdir)) {
+					if (errno == ENOENT) {
+						pr_debug("%s wasn't in the cache\n",
+							 pos->s);
+						continue;
+					}
+					pr_warning("Couldn't update %s: %s\n",
+						   pos->s, strerror(errno));
+				}
 
-	if (symbol__init() < 0)
-		return -1;
+			strlist__delete(list);
+		}
+	}
 
-	setup_pager();
-	return __cmd_buildid_cache();
+	if (kcore_filename &&
+	    build_id_cache__add_kcore(kcore_filename, debugdir))
+		pr_warning("Couldn't add %s\n", kcore_filename);
+
+	return ret;
 }
diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c
index 99890728409..ed3873b3e23 100644
--- a/tools/perf/builtin-buildid-list.c
+++ b/tools/perf/builtin-buildid-list.c
@@ -1,7 +1,8 @@
 /*
  * builtin-buildid-list.c
  *
- * Builtin buildid-list command: list buildids in perf.data
+ * Builtin buildid-list command: list buildids in perf.data, in the running
+ * kernel and in ELF files.
  *
  * Copyright (C) 2009, Red Hat Inc.
  * Copyright (C) 2009, Arnaldo Carvalho de Melo <acme@redhat.com>
@@ -14,49 +15,97 @@
 #include "util/parse-options.h"
 #include "util/session.h"
 #include "util/symbol.h"
+#include "util/data.h"
 
-static char const *input_name = "perf.data";
-static bool force;
-static bool with_hits;
+static int sysfs__fprintf_build_id(FILE *fp)
+{
+	u8 kallsyms_build_id[BUILD_ID_SIZE];
+	char sbuild_id[BUILD_ID_SIZE * 2 + 1];
 
-static const char * const buildid_list_usage[] = {
-	"perf buildid-list [<options>]",
-	NULL
-};
+	if (sysfs__read_build_id("/sys/kernel/notes", kallsyms_build_id,
+				 sizeof(kallsyms_build_id)) != 0)
+		return -1;
 
-static const struct option options[] = {
-	OPT_BOOLEAN('H', "with-hits", &with_hits, "Show only DSOs with hits"),
-	OPT_STRING('i', "input", &input_name, "file",
-		    "input file name"),
-	OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
-	OPT_INCR('v', "verbose", &verbose,
-		    "be more verbose"),
-	OPT_END()
-};
+	build_id__sprintf(kallsyms_build_id, sizeof(kallsyms_build_id),
+			  sbuild_id);
+	fprintf(fp, "%s\n", sbuild_id);
+	return 0;
+}
 
-static int __cmd_buildid_list(void)
+static int filename__fprintf_build_id(const char *name, FILE *fp)
+{
+	u8 build_id[BUILD_ID_SIZE];
+	char sbuild_id[BUILD_ID_SIZE * 2 + 1];
+
+	if (filename__read_build_id(name, build_id,
+				    sizeof(build_id)) != sizeof(build_id))
+		return 0;
+
+	build_id__sprintf(build_id, sizeof(build_id), sbuild_id);
+	return fprintf(fp, "%s\n", sbuild_id);
+}
+
+static bool dso__skip_buildid(struct dso *dso, int with_hits)
+{
+	return with_hits && !dso->hit;
+}
+
+static int perf_session__list_build_ids(bool force, bool with_hits)
 {
-	int err = -1;
 	struct perf_session *session;
+	struct perf_data_file file = {
+		.path  = input_name,
+		.mode  = PERF_DATA_MODE_READ,
+		.force = force,
+	};
+
+	symbol__elf_init();
+	/*
+	 * See if this is an ELF file first:
+	 */
+	if (filename__fprintf_build_id(input_name, stdout))
+		goto out;
 
-	session = perf_session__new(input_name, O_RDONLY, force, false);
+	session = perf_session__new(&file, false, &build_id__mark_dso_hit_ops);
 	if (session == NULL)
 		return -1;
-
-	if (with_hits) {
-		symbol_conf.full_paths = true;
+	/*
+	 * in pipe-mode, the only way to get the buildids is to parse
+	 * the record stream. Buildids are stored as RECORD_HEADER_BUILD_ID
+	 */
+	if (with_hits || perf_data_file__is_pipe(&file))
 		perf_session__process_events(session, &build_id__mark_dso_hit_ops);
-	}
-
-	perf_session__fprintf_dsos_buildid(session, stdout, with_hits);
 
+	perf_session__fprintf_dsos_buildid(session, stdout, dso__skip_buildid, with_hits);
 	perf_session__delete(session);
-	return err;
+out:
+	return 0;
 }
 
-int cmd_buildid_list(int argc, const char **argv, const char *prefix __used)
+int cmd_buildid_list(int argc, const char **argv,
+		     const char *prefix __maybe_unused)
 {
+	bool show_kernel = false;
+	bool with_hits = false;
+	bool force = false;
+	const struct option options[] = {
+	OPT_BOOLEAN('H', "with-hits", &with_hits, "Show only DSOs with hits"),
+	OPT_STRING('i', "input", &input_name, "file", "input file name"),
+	OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
+	OPT_BOOLEAN('k', "kernel", &show_kernel, "Show current kernel build id"),
+	OPT_INCR('v', "verbose", &verbose, "be more verbose"),
+	OPT_END()
+	};
+	const char * const buildid_list_usage[] = {
+		"perf buildid-list [<options>]",
+		NULL
+	};
+
 	argc = parse_options(argc, argv, options, buildid_list_usage, 0);
 	setup_pager();
-	return __cmd_buildid_list();
+
+	if (show_kernel)
+		return sysfs__fprintf_build_id(stdout);
+
+	return perf_session__list_build_ids(force, with_hits);
 }
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index a6e2fdc7a04..9a5a035cb42 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -9,66 +9,543 @@
 #include "util/debug.h"
 #include "util/event.h"
 #include "util/hist.h"
+#include "util/evsel.h"
+#include "util/evlist.h"
 #include "util/session.h"
+#include "util/tool.h"
 #include "util/sort.h"
 #include "util/symbol.h"
 #include "util/util.h"
+#include "util/data.h"
 
 #include <stdlib.h>
+#include <math.h>
 
-static char const *input_old = "perf.data.old",
-		  *input_new = "perf.data";
-static char	  diff__default_sort_order[] = "dso,symbol";
-static bool  force;
-static bool show_displacement;
+/* Diff command specific HPP columns. */
+enum {
+	PERF_HPP_DIFF__BASELINE,
+	PERF_HPP_DIFF__PERIOD,
+	PERF_HPP_DIFF__PERIOD_BASELINE,
+	PERF_HPP_DIFF__DELTA,
+	PERF_HPP_DIFF__RATIO,
+	PERF_HPP_DIFF__WEIGHTED_DIFF,
+	PERF_HPP_DIFF__FORMULA,
 
-static int hists__add_entry(struct hists *self,
-			    struct addr_location *al, u64 period)
+	PERF_HPP_DIFF__MAX_INDEX
+};
+
+struct diff_hpp_fmt {
+	struct perf_hpp_fmt	 fmt;
+	int			 idx;
+	char			*header;
+	int			 header_width;
+};
+
+struct data__file {
+	struct perf_session	*session;
+	struct perf_data_file	file;
+	int			 idx;
+	struct hists		*hists;
+	struct diff_hpp_fmt	 fmt[PERF_HPP_DIFF__MAX_INDEX];
+};
+
+static struct data__file *data__files;
+static int data__files_cnt;
+
+#define data__for_each_file_start(i, d, s)	\
+	for (i = s, d = &data__files[s];	\
+	     i < data__files_cnt;		\
+	     i++, d = &data__files[i])
+
+#define data__for_each_file(i, d) data__for_each_file_start(i, d, 0)
+#define data__for_each_file_new(i, d) data__for_each_file_start(i, d, 1)
+
+static bool force;
+static bool show_period;
+static bool show_formula;
+static bool show_baseline_only;
+static unsigned int sort_compute;
+
+static s64 compute_wdiff_w1;
+static s64 compute_wdiff_w2;
+
+enum {
+	COMPUTE_DELTA,
+	COMPUTE_RATIO,
+	COMPUTE_WEIGHTED_DIFF,
+	COMPUTE_MAX,
+};
+
+const char *compute_names[COMPUTE_MAX] = {
+	[COMPUTE_DELTA] = "delta",
+	[COMPUTE_RATIO] = "ratio",
+	[COMPUTE_WEIGHTED_DIFF] = "wdiff",
+};
+
+static int compute;
+
+static int compute_2_hpp[COMPUTE_MAX] = {
+	[COMPUTE_DELTA]		= PERF_HPP_DIFF__DELTA,
+	[COMPUTE_RATIO]		= PERF_HPP_DIFF__RATIO,
+	[COMPUTE_WEIGHTED_DIFF]	= PERF_HPP_DIFF__WEIGHTED_DIFF,
+};
+
+#define MAX_COL_WIDTH 70
+
+static struct header_column {
+	const char *name;
+	int width;
+} columns[PERF_HPP_DIFF__MAX_INDEX] = {
+	[PERF_HPP_DIFF__BASELINE] = {
+		.name  = "Baseline",
+	},
+	[PERF_HPP_DIFF__PERIOD] = {
+		.name  = "Period",
+		.width = 14,
+	},
+	[PERF_HPP_DIFF__PERIOD_BASELINE] = {
+		.name  = "Base period",
+		.width = 14,
+	},
+	[PERF_HPP_DIFF__DELTA] = {
+		.name  = "Delta",
+		.width = 7,
+	},
+	[PERF_HPP_DIFF__RATIO] = {
+		.name  = "Ratio",
+		.width = 14,
+	},
+	[PERF_HPP_DIFF__WEIGHTED_DIFF] = {
+		.name  = "Weighted diff",
+		.width = 14,
+	},
+	[PERF_HPP_DIFF__FORMULA] = {
+		.name  = "Formula",
+		.width = MAX_COL_WIDTH,
+	}
+};
+
+static int setup_compute_opt_wdiff(char *opt)
+{
+	char *w1_str = opt;
+	char *w2_str;
+
+	int ret = -EINVAL;
+
+	if (!opt)
+		goto out;
+
+	w2_str = strchr(opt, ',');
+	if (!w2_str)
+		goto out;
+
+	*w2_str++ = 0x0;
+	if (!*w2_str)
+		goto out;
+
+	compute_wdiff_w1 = strtol(w1_str, NULL, 10);
+	compute_wdiff_w2 = strtol(w2_str, NULL, 10);
+
+	if (!compute_wdiff_w1 || !compute_wdiff_w2)
+		goto out;
+
+	pr_debug("compute wdiff w1(%" PRId64 ") w2(%" PRId64 ")\n",
+		  compute_wdiff_w1, compute_wdiff_w2);
+
+	ret = 0;
+
+ out:
+	if (ret)
+		pr_err("Failed: wrong weight data, use 'wdiff:w1,w2'\n");
+
+	return ret;
+}
+
+static int setup_compute_opt(char *opt)
 {
-	if (__hists__add_entry(self, al, NULL, period) != NULL)
+	if (compute == COMPUTE_WEIGHTED_DIFF)
+		return setup_compute_opt_wdiff(opt);
+
+	if (opt) {
+		pr_err("Failed: extra option specified '%s'", opt);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int setup_compute(const struct option *opt, const char *str,
+			 int unset __maybe_unused)
+{
+	int *cp = (int *) opt->value;
+	char *cstr = (char *) str;
+	char buf[50];
+	unsigned i;
+	char *option;
+
+	if (!str) {
+		*cp = COMPUTE_DELTA;
+		return 0;
+	}
+
+	option = strchr(str, ':');
+	if (option) {
+		unsigned len = option++ - str;
+
+		/*
+		 * The str data are not writeable, so we need
+		 * to use another buffer.
+		 */
+
+		/* No option value is longer. */
+		if (len >= sizeof(buf))
+			return -EINVAL;
+
+		strncpy(buf, str, len);
+		buf[len] = 0x0;
+		cstr = buf;
+	}
+
+	for (i = 0; i < COMPUTE_MAX; i++)
+		if (!strcmp(cstr, compute_names[i])) {
+			*cp = i;
+			return setup_compute_opt(option);
+		}
+
+	pr_err("Failed: '%s' is not computation method "
+	       "(use 'delta','ratio' or 'wdiff')\n", str);
+	return -EINVAL;
+}
+
+static double period_percent(struct hist_entry *he, u64 period)
+{
+	u64 total = hists__total_period(he->hists);
+
+	return (period * 100.0) / total;
+}
+
+static double compute_delta(struct hist_entry *he, struct hist_entry *pair)
+{
+	double old_percent = period_percent(he, he->stat.period);
+	double new_percent = period_percent(pair, pair->stat.period);
+
+	pair->diff.period_ratio_delta = new_percent - old_percent;
+	pair->diff.computed = true;
+	return pair->diff.period_ratio_delta;
+}
+
+static double compute_ratio(struct hist_entry *he, struct hist_entry *pair)
+{
+	double old_period = he->stat.period ?: 1;
+	double new_period = pair->stat.period;
+
+	pair->diff.computed = true;
+	pair->diff.period_ratio = new_period / old_period;
+	return pair->diff.period_ratio;
+}
+
+static s64 compute_wdiff(struct hist_entry *he, struct hist_entry *pair)
+{
+	u64 old_period = he->stat.period;
+	u64 new_period = pair->stat.period;
+
+	pair->diff.computed = true;
+	pair->diff.wdiff = new_period * compute_wdiff_w2 -
+			   old_period * compute_wdiff_w1;
+
+	return pair->diff.wdiff;
+}
+
+static int formula_delta(struct hist_entry *he, struct hist_entry *pair,
+			 char *buf, size_t size)
+{
+	u64 he_total = he->hists->stats.total_period;
+	u64 pair_total = pair->hists->stats.total_period;
+
+	if (symbol_conf.filter_relative) {
+		he_total = he->hists->stats.total_non_filtered_period;
+		pair_total = pair->hists->stats.total_non_filtered_period;
+	}
+	return scnprintf(buf, size,
+			 "(%" PRIu64 " * 100 / %" PRIu64 ") - "
+			 "(%" PRIu64 " * 100 / %" PRIu64 ")",
+			 pair->stat.period, pair_total,
+			 he->stat.period, he_total);
+}
+
+static int formula_ratio(struct hist_entry *he, struct hist_entry *pair,
+			 char *buf, size_t size)
+{
+	double old_period = he->stat.period;
+	double new_period = pair->stat.period;
+
+	return scnprintf(buf, size, "%.0F / %.0F", new_period, old_period);
+}
+
+static int formula_wdiff(struct hist_entry *he, struct hist_entry *pair,
+			 char *buf, size_t size)
+{
+	u64 old_period = he->stat.period;
+	u64 new_period = pair->stat.period;
+
+	return scnprintf(buf, size,
+		  "(%" PRIu64 " * " "%" PRId64 ") - (%" PRIu64 " * " "%" PRId64 ")",
+		  new_period, compute_wdiff_w2, old_period, compute_wdiff_w1);
+}
+
+static int formula_fprintf(struct hist_entry *he, struct hist_entry *pair,
+			   char *buf, size_t size)
+{
+	switch (compute) {
+	case COMPUTE_DELTA:
+		return formula_delta(he, pair, buf, size);
+	case COMPUTE_RATIO:
+		return formula_ratio(he, pair, buf, size);
+	case COMPUTE_WEIGHTED_DIFF:
+		return formula_wdiff(he, pair, buf, size);
+	default:
+		BUG_ON(1);
+	}
+
+	return -1;
+}
+
+static int hists__add_entry(struct hists *hists,
+			    struct addr_location *al, u64 period,
+			    u64 weight, u64 transaction)
+{
+	if (__hists__add_entry(hists, al, NULL, NULL, NULL, period, weight,
+			       transaction, true) != NULL)
 		return 0;
 	return -ENOMEM;
 }
 
-static int diff__process_sample_event(event_t *event, struct perf_session *session)
+static int diff__process_sample_event(struct perf_tool *tool __maybe_unused,
+				      union perf_event *event,
+				      struct perf_sample *sample,
+				      struct perf_evsel *evsel,
+				      struct machine *machine)
 {
 	struct addr_location al;
-	struct sample_data data = { .period = 1, };
 
-	dump_printf("(IP, %d): %d: %#Lx\n", event->header.misc,
-		    event->ip.pid, event->ip.ip);
-
-	if (event__preprocess_sample(event, session, &al, NULL) < 0) {
+	if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
 		pr_warning("problem processing %d event, skipping it.\n",
 			   event->header.type);
 		return -1;
 	}
 
-	if (al.filtered || al.sym == NULL)
-		return 0;
-
-	event__parse_sample(event, session->sample_type, &data);
-
-	if (hists__add_entry(&session->hists, &al, data.period)) {
+	if (hists__add_entry(&evsel->hists, &al, sample->period,
+			     sample->weight, sample->transaction)) {
 		pr_warning("problem incrementing symbol period, skipping event\n");
 		return -1;
 	}
 
-	session->hists.stats.total_period += data.period;
+	/*
+	 * The total_period is updated here before going to the output
+	 * tree since normally only the baseline hists will call
+	 * hists__output_resort() and precompute needs the total
+	 * period in order to sort entries by percentage delta.
+	 */
+	evsel->hists.stats.total_period += sample->period;
+	if (!al.filtered)
+		evsel->hists.stats.total_non_filtered_period += sample->period;
+
 	return 0;
 }
 
-static struct perf_event_ops event_ops = {
+static struct perf_tool tool = {
 	.sample	= diff__process_sample_event,
-	.mmap	= event__process_mmap,
-	.comm	= event__process_comm,
-	.exit	= event__process_task,
-	.fork	= event__process_task,
-	.lost	= event__process_lost,
+	.mmap	= perf_event__process_mmap,
+	.comm	= perf_event__process_comm,
+	.exit	= perf_event__process_exit,
+	.fork	= perf_event__process_fork,
+	.lost	= perf_event__process_lost,
+	.ordered_samples = true,
+	.ordering_requires_timestamps = true,
 };
 
-static void perf_session__insert_hist_entry_by_name(struct rb_root *root,
-						    struct hist_entry *he)
+static struct perf_evsel *evsel_match(struct perf_evsel *evsel,
+				      struct perf_evlist *evlist)
+{
+	struct perf_evsel *e;
+
+	evlist__for_each(evlist, e) {
+		if (perf_evsel__match2(evsel, e))
+			return e;
+	}
+
+	return NULL;
+}
+
+static void perf_evlist__collapse_resort(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each(evlist, evsel) {
+		struct hists *hists = &evsel->hists;
+
+		hists__collapse_resort(hists, NULL);
+	}
+}
+
+static struct hist_entry*
+get_pair_data(struct hist_entry *he, struct data__file *d)
+{
+	if (hist_entry__has_pairs(he)) {
+		struct hist_entry *pair;
+
+		list_for_each_entry(pair, &he->pairs.head, pairs.node)
+			if (pair->hists == d->hists)
+				return pair;
+	}
+
+	return NULL;
+}
+
+static struct hist_entry*
+get_pair_fmt(struct hist_entry *he, struct diff_hpp_fmt *dfmt)
+{
+	void *ptr = dfmt - dfmt->idx;
+	struct data__file *d = container_of(ptr, struct data__file, fmt);
+
+	return get_pair_data(he, d);
+}
+
+static void hists__baseline_only(struct hists *hists)
+{
+	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_in);
+
+		next = rb_next(&he->rb_node_in);
+		if (!hist_entry__next_pair(he)) {
+			rb_erase(&he->rb_node_in, root);
+			hist_entry__free(he);
+		}
+	}
+}
+
+static void hists__precompute(struct hists *hists)
+{
+	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, *pair;
+
+		he   = rb_entry(next, struct hist_entry, rb_node_in);
+		next = rb_next(&he->rb_node_in);
+
+		pair = get_pair_data(he, &data__files[sort_compute]);
+		if (!pair)
+			continue;
+
+		switch (compute) {
+		case COMPUTE_DELTA:
+			compute_delta(he, pair);
+			break;
+		case COMPUTE_RATIO:
+			compute_ratio(he, pair);
+			break;
+		case COMPUTE_WEIGHTED_DIFF:
+			compute_wdiff(he, pair);
+			break;
+		default:
+			BUG_ON(1);
+		}
+	}
+}
+
+static int64_t cmp_doubles(double l, double r)
+{
+	if (l > r)
+		return -1;
+	else if (l < r)
+		return 1;
+	else
+		return 0;
+}
+
+static int64_t
+__hist_entry__cmp_compute(struct hist_entry *left, struct hist_entry *right,
+			int c)
+{
+	switch (c) {
+	case COMPUTE_DELTA:
+	{
+		double l = left->diff.period_ratio_delta;
+		double r = right->diff.period_ratio_delta;
+
+		return cmp_doubles(l, r);
+	}
+	case COMPUTE_RATIO:
+	{
+		double l = left->diff.period_ratio;
+		double r = right->diff.period_ratio;
+
+		return cmp_doubles(l, r);
+	}
+	case COMPUTE_WEIGHTED_DIFF:
+	{
+		s64 l = left->diff.wdiff;
+		s64 r = right->diff.wdiff;
+
+		return r - l;
+	}
+	default:
+		BUG_ON(1);
+	}
+
+	return 0;
+}
+
+static int64_t
+hist_entry__cmp_compute(struct hist_entry *left, struct hist_entry *right,
+			int c)
+{
+	bool pairs_left  = hist_entry__has_pairs(left);
+	bool pairs_right = hist_entry__has_pairs(right);
+	struct hist_entry *p_right, *p_left;
+
+	if (!pairs_left && !pairs_right)
+		return 0;
+
+	if (!pairs_left || !pairs_right)
+		return pairs_left ? -1 : 1;
+
+	p_left  = get_pair_data(left,  &data__files[sort_compute]);
+	p_right = get_pair_data(right, &data__files[sort_compute]);
+
+	if (!p_left && !p_right)
+		return 0;
+
+	if (!p_left || !p_right)
+		return p_left ? -1 : 1;
+
+	/*
+	 * We have 2 entries of same kind, let's
+	 * make the data comparison.
+	 */
+	return __hist_entry__cmp_compute(p_left, p_right, c);
+}
+
+static void insert_hist_entry_by_compute(struct rb_root *root,
+					 struct hist_entry *he,
+					 int c)
 {
 	struct rb_node **p = &root->rb_node;
 	struct rb_node *parent = NULL;
@@ -77,7 +554,7 @@ static void perf_session__insert_hist_entry_by_name(struct rb_root *root,
 	while (*p != NULL) {
 		parent = *p;
 		iter = rb_entry(parent, struct hist_entry, rb_node);
-		if (hist_entry__cmp(he, iter) < 0)
+		if (hist_entry__cmp_compute(he, iter, c) < 0)
 			p = &(*p)->rb_left;
 		else
 			p = &(*p)->rb_right;
@@ -87,86 +564,149 @@ static void perf_session__insert_hist_entry_by_name(struct rb_root *root,
 	rb_insert_color(&he->rb_node, root);
 }
 
-static void hists__resort_entries(struct hists *self)
+static void hists__compute_resort(struct hists *hists)
 {
-	unsigned long position = 1;
-	struct rb_root tmp = RB_ROOT;
-	struct rb_node *next = rb_first(&self->entries);
+	struct rb_root *root;
+	struct rb_node *next;
+
+	if (sort__need_collapse)
+		root = &hists->entries_collapsed;
+	else
+		root = hists->entries_in;
+
+	hists->entries = RB_ROOT;
+	next = rb_first(root);
+
+	hists__reset_stats(hists);
+	hists__reset_col_len(hists);
 
 	while (next != NULL) {
-		struct hist_entry *n = rb_entry(next, struct hist_entry, rb_node);
+		struct hist_entry *he;
+
+		he = rb_entry(next, struct hist_entry, rb_node_in);
+		next = rb_next(&he->rb_node_in);
 
-		next = rb_next(&n->rb_node);
-		rb_erase(&n->rb_node, &self->entries);
-		n->position = position++;
-		perf_session__insert_hist_entry_by_name(&tmp, n);
+		insert_hist_entry_by_compute(&hists->entries, he, compute);
+		hists__inc_stats(hists, he);
+
+		if (!he->filtered)
+			hists__calc_col_len(hists, he);
 	}
+}
 
-	self->entries = tmp;
+static void hists__process(struct hists *hists)
+{
+	if (show_baseline_only)
+		hists__baseline_only(hists);
+
+	if (sort_compute) {
+		hists__precompute(hists);
+		hists__compute_resort(hists);
+	} else {
+		hists__output_resort(hists);
+	}
+
+	hists__fprintf(hists, true, 0, 0, 0, stdout);
 }
 
-static void hists__set_positions(struct hists *self)
+static void data__fprintf(void)
 {
-	hists__output_resort(self);
-	hists__resort_entries(self);
+	struct data__file *d;
+	int i;
+
+	fprintf(stdout, "# Data files:\n");
+
+	data__for_each_file(i, d)
+		fprintf(stdout, "#  [%d] %s %s\n",
+			d->idx, d->file.path,
+			!d->idx ? "(Baseline)" : "");
+
+	fprintf(stdout, "#\n");
 }
 
-static struct hist_entry *hists__find_entry(struct hists *self,
-					    struct hist_entry *he)
+static void data_process(void)
 {
-	struct rb_node *n = self->entries.rb_node;
+	struct perf_evlist *evlist_base = data__files[0].session->evlist;
+	struct perf_evsel *evsel_base;
+	bool first = true;
 
-	while (n) {
-		struct hist_entry *iter = rb_entry(n, struct hist_entry, rb_node);
-		int64_t cmp = hist_entry__cmp(he, iter);
+	evlist__for_each(evlist_base, evsel_base) {
+		struct data__file *d;
+		int i;
 
-		if (cmp < 0)
-			n = n->rb_left;
-		else if (cmp > 0)
-			n = n->rb_right;
-		else 
-			return iter;
-	}
+		data__for_each_file_new(i, d) {
+			struct perf_evlist *evlist = d->session->evlist;
+			struct perf_evsel *evsel;
 
-	return NULL;
+			evsel = evsel_match(evsel_base, evlist);
+			if (!evsel)
+				continue;
+
+			d->hists = &evsel->hists;
+
+			hists__match(&evsel_base->hists, &evsel->hists);
+
+			if (!show_baseline_only)
+				hists__link(&evsel_base->hists,
+					    &evsel->hists);
+		}
+
+		fprintf(stdout, "%s# Event '%s'\n#\n", first ? "" : "\n",
+			perf_evsel__name(evsel_base));
+
+		first = false;
+
+		if (verbose || data__files_cnt > 2)
+			data__fprintf();
+
+		hists__process(&evsel_base->hists);
+	}
 }
 
-static void hists__match(struct hists *older, struct hists *newer)
+static void data__free(struct data__file *d)
 {
-	struct rb_node *nd;
+	int col;
+
+	for (col = 0; col < PERF_HPP_DIFF__MAX_INDEX; col++) {
+		struct diff_hpp_fmt *fmt = &d->fmt[col];
 
-	for (nd = rb_first(&newer->entries); nd; nd = rb_next(nd)) {
-		struct hist_entry *pos = rb_entry(nd, struct hist_entry, rb_node);
-		pos->pair = hists__find_entry(older, pos);
+		zfree(&fmt->header);
 	}
 }
 
 static int __cmd_diff(void)
 {
-	int ret, i;
-	struct perf_session *session[2];
+	struct data__file *d;
+	int ret = -EINVAL, i;
 
-	session[0] = perf_session__new(input_old, O_RDONLY, force, false);
-	session[1] = perf_session__new(input_new, O_RDONLY, force, false);
-	if (session[0] == NULL || session[1] == NULL)
-		return -ENOMEM;
+	data__for_each_file(i, d) {
+		d->session = perf_session__new(&d->file, false, &tool);
+		if (!d->session) {
+			pr_err("Failed to open %s\n", d->file.path);
+			ret = -ENOMEM;
+			goto out_delete;
+		}
 
-	for (i = 0; i < 2; ++i) {
-		ret = perf_session__process_events(session[i], &event_ops);
-		if (ret)
+		ret = perf_session__process_events(d->session, &tool);
+		if (ret) {
+			pr_err("Failed to process %s\n", d->file.path);
 			goto out_delete;
+		}
+
+		perf_evlist__collapse_resort(d->session->evlist);
 	}
 
-	hists__output_resort(&session[1]->hists);
-	if (show_displacement)
-		hists__set_positions(&session[0]->hists);
+	data_process();
+
+ out_delete:
+	data__for_each_file(i, d) {
+		if (d->session)
+			perf_session__delete(d->session);
 
-	hists__match(&session[0]->hists, &session[1]->hists);
-	hists__fprintf(&session[1]->hists, &session[0]->hists,
-		       show_displacement, stdout);
-out_delete:
-	for (i = 0; i < 2; ++i)
-		perf_session__delete(session[i]);
+		data__free(d);
+	}
+
+	free(data__files);
 	return ret;
 }
 
@@ -178,15 +718,21 @@ static const char * const diff_usage[] = {
 static const struct option options[] = {
 	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose (show symbol address, etc)"),
-	OPT_BOOLEAN('m', "displacement", &show_displacement,
-		    "Show position displacement relative to baseline"),
+	OPT_BOOLEAN('b', "baseline-only", &show_baseline_only,
+		    "Show only items with match in baseline"),
+	OPT_CALLBACK('c', "compute", &compute,
+		     "delta,ratio,wdiff:w1,w2 (default delta)",
+		     "Entries differential computation selection",
+		     setup_compute),
+	OPT_BOOLEAN('p', "period", &show_period,
+		    "Show period values."),
+	OPT_BOOLEAN('F', "formula", &show_formula,
+		    "Show formula."),
 	OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
 		    "dump raw trace in ASCII"),
 	OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
 	OPT_BOOLEAN('m', "modules", &symbol_conf.use_modules,
 		    "load module symbols - WARNING: use only with -k and LIVE kernel"),
-	OPT_BOOLEAN('P', "full-paths", &symbol_conf.full_paths,
-		    "Don't shorten the pathnames taking into account the cwd"),
 	OPT_STRING('d', "dsos", &symbol_conf.dso_list_str, "dso[,dso...]",
 		   "only consider symbols in these dsos"),
 	OPT_STRING('C', "comms", &symbol_conf.comm_list_str, "comm[,comm...]",
@@ -194,41 +740,425 @@ static const struct option options[] = {
 	OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]",
 		   "only consider these symbols"),
 	OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
-		   "sort by key(s): pid, comm, dso, symbol, parent"),
+		   "sort by key(s): pid, comm, dso, symbol, parent, cpu, srcline, ..."
+		   " Please refer the man page for the complete list."),
 	OPT_STRING('t', "field-separator", &symbol_conf.field_sep, "separator",
 		   "separator for columns, no spaces will be added between "
 		   "columns '.' is reserved."),
+	OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
+		    "Look for files with symbols relative to this directory"),
+	OPT_UINTEGER('o', "order", &sort_compute, "Specify compute sorting."),
+	OPT_CALLBACK(0, "percentage", NULL, "relative|absolute",
+		     "How to display percentage of filtered entries", parse_filter_percentage),
 	OPT_END()
 };
 
-int cmd_diff(int argc, const char **argv, const char *prefix __used)
+static double baseline_percent(struct hist_entry *he)
 {
-	sort_order = diff__default_sort_order;
-	argc = parse_options(argc, argv, options, diff_usage, 0);
+	u64 total = hists__total_period(he->hists);
+
+	return 100.0 * he->stat.period / total;
+}
+
+static int hpp__color_baseline(struct perf_hpp_fmt *fmt,
+			       struct perf_hpp *hpp, struct hist_entry *he)
+{
+	struct diff_hpp_fmt *dfmt =
+		container_of(fmt, struct diff_hpp_fmt, fmt);
+	double percent = baseline_percent(he);
+	char pfmt[20] = " ";
+
+	if (!he->dummy) {
+		scnprintf(pfmt, 20, "%%%d.2f%%%%", dfmt->header_width - 1);
+		return percent_color_snprintf(hpp->buf, hpp->size,
+					      pfmt, percent);
+	} else
+		return scnprintf(hpp->buf, hpp->size, "%*s",
+				 dfmt->header_width, pfmt);
+}
+
+static int hpp__entry_baseline(struct hist_entry *he, char *buf, size_t size)
+{
+	double percent = baseline_percent(he);
+	const char *fmt = symbol_conf.field_sep ? "%.2f" : "%6.2f%%";
+	int ret = 0;
+
+	if (!he->dummy)
+		ret = scnprintf(buf, size, fmt, percent);
+
+	return ret;
+}
+
+static int __hpp__color_compare(struct perf_hpp_fmt *fmt,
+				struct perf_hpp *hpp, struct hist_entry *he,
+				int comparison_method)
+{
+	struct diff_hpp_fmt *dfmt =
+		container_of(fmt, struct diff_hpp_fmt, fmt);
+	struct hist_entry *pair = get_pair_fmt(he, dfmt);
+	double diff;
+	s64 wdiff;
+	char pfmt[20] = " ";
+
+	if (!pair)
+		goto dummy_print;
+
+	switch (comparison_method) {
+	case COMPUTE_DELTA:
+		if (pair->diff.computed)
+			diff = pair->diff.period_ratio_delta;
+		else
+			diff = compute_delta(he, pair);
+
+		if (fabs(diff) < 0.01)
+			goto dummy_print;
+		scnprintf(pfmt, 20, "%%%+d.2f%%%%", dfmt->header_width - 1);
+		return percent_color_snprintf(hpp->buf, hpp->size,
+					pfmt, diff);
+	case COMPUTE_RATIO:
+		if (he->dummy)
+			goto dummy_print;
+		if (pair->diff.computed)
+			diff = pair->diff.period_ratio;
+		else
+			diff = compute_ratio(he, pair);
+
+		scnprintf(pfmt, 20, "%%%d.6f", dfmt->header_width);
+		return value_color_snprintf(hpp->buf, hpp->size,
+					pfmt, diff);
+	case COMPUTE_WEIGHTED_DIFF:
+		if (he->dummy)
+			goto dummy_print;
+		if (pair->diff.computed)
+			wdiff = pair->diff.wdiff;
+		else
+			wdiff = compute_wdiff(he, pair);
+
+		scnprintf(pfmt, 20, "%%14ld", dfmt->header_width);
+		return color_snprintf(hpp->buf, hpp->size,
+				get_percent_color(wdiff),
+				pfmt, wdiff);
+	default:
+		BUG_ON(1);
+	}
+dummy_print:
+	return scnprintf(hpp->buf, hpp->size, "%*s",
+			dfmt->header_width, pfmt);
+}
+
+static int hpp__color_delta(struct perf_hpp_fmt *fmt,
+			struct perf_hpp *hpp, struct hist_entry *he)
+{
+	return __hpp__color_compare(fmt, hpp, he, COMPUTE_DELTA);
+}
+
+static int hpp__color_ratio(struct perf_hpp_fmt *fmt,
+			struct perf_hpp *hpp, struct hist_entry *he)
+{
+	return __hpp__color_compare(fmt, hpp, he, COMPUTE_RATIO);
+}
+
+static int hpp__color_wdiff(struct perf_hpp_fmt *fmt,
+			struct perf_hpp *hpp, struct hist_entry *he)
+{
+	return __hpp__color_compare(fmt, hpp, he, COMPUTE_WEIGHTED_DIFF);
+}
+
+static void
+hpp__entry_unpair(struct hist_entry *he, int idx, char *buf, size_t size)
+{
+	switch (idx) {
+	case PERF_HPP_DIFF__PERIOD_BASELINE:
+		scnprintf(buf, size, "%" PRIu64, he->stat.period);
+		break;
+
+	default:
+		break;
+	}
+}
+
+static void
+hpp__entry_pair(struct hist_entry *he, struct hist_entry *pair,
+		int idx, char *buf, size_t size)
+{
+	double diff;
+	double ratio;
+	s64 wdiff;
+
+	switch (idx) {
+	case PERF_HPP_DIFF__DELTA:
+		if (pair->diff.computed)
+			diff = pair->diff.period_ratio_delta;
+		else
+			diff = compute_delta(he, pair);
+
+		if (fabs(diff) >= 0.01)
+			scnprintf(buf, size, "%+4.2F%%", diff);
+		break;
+
+	case PERF_HPP_DIFF__RATIO:
+		/* No point for ratio number if we are dummy.. */
+		if (he->dummy)
+			break;
+
+		if (pair->diff.computed)
+			ratio = pair->diff.period_ratio;
+		else
+			ratio = compute_ratio(he, pair);
+
+		if (ratio > 0.0)
+			scnprintf(buf, size, "%14.6F", ratio);
+		break;
+
+	case PERF_HPP_DIFF__WEIGHTED_DIFF:
+		/* No point for wdiff number if we are dummy.. */
+		if (he->dummy)
+			break;
+
+		if (pair->diff.computed)
+			wdiff = pair->diff.wdiff;
+		else
+			wdiff = compute_wdiff(he, pair);
+
+		if (wdiff != 0)
+			scnprintf(buf, size, "%14ld", wdiff);
+		break;
+
+	case PERF_HPP_DIFF__FORMULA:
+		formula_fprintf(he, pair, buf, size);
+		break;
+
+	case PERF_HPP_DIFF__PERIOD:
+		scnprintf(buf, size, "%" PRIu64, pair->stat.period);
+		break;
+
+	default:
+		BUG_ON(1);
+	};
+}
+
+static void
+__hpp__entry_global(struct hist_entry *he, struct diff_hpp_fmt *dfmt,
+		    char *buf, size_t size)
+{
+	struct hist_entry *pair = get_pair_fmt(he, dfmt);
+	int idx = dfmt->idx;
+
+	/* baseline is special */
+	if (idx == PERF_HPP_DIFF__BASELINE)
+		hpp__entry_baseline(he, buf, size);
+	else {
+		if (pair)
+			hpp__entry_pair(he, pair, idx, buf, size);
+		else
+			hpp__entry_unpair(he, idx, buf, size);
+	}
+}
+
+static int hpp__entry_global(struct perf_hpp_fmt *_fmt, struct perf_hpp *hpp,
+			     struct hist_entry *he)
+{
+	struct diff_hpp_fmt *dfmt =
+		container_of(_fmt, struct diff_hpp_fmt, fmt);
+	char buf[MAX_COL_WIDTH] = " ";
+
+	__hpp__entry_global(he, dfmt, buf, MAX_COL_WIDTH);
+
+	if (symbol_conf.field_sep)
+		return scnprintf(hpp->buf, hpp->size, "%s", buf);
+	else
+		return scnprintf(hpp->buf, hpp->size, "%*s",
+				 dfmt->header_width, buf);
+}
+
+static int hpp__header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+		       struct perf_evsel *evsel __maybe_unused)
+{
+	struct diff_hpp_fmt *dfmt =
+		container_of(fmt, struct diff_hpp_fmt, fmt);
+
+	BUG_ON(!dfmt->header);
+	return scnprintf(hpp->buf, hpp->size, dfmt->header);
+}
+
+static int hpp__width(struct perf_hpp_fmt *fmt,
+		      struct perf_hpp *hpp __maybe_unused,
+		      struct perf_evsel *evsel __maybe_unused)
+{
+	struct diff_hpp_fmt *dfmt =
+		container_of(fmt, struct diff_hpp_fmt, fmt);
+
+	BUG_ON(dfmt->header_width <= 0);
+	return dfmt->header_width;
+}
+
+static void init_header(struct data__file *d, struct diff_hpp_fmt *dfmt)
+{
+#define MAX_HEADER_NAME 100
+	char buf_indent[MAX_HEADER_NAME];
+	char buf[MAX_HEADER_NAME];
+	const char *header = NULL;
+	int width = 0;
+
+	BUG_ON(dfmt->idx >= PERF_HPP_DIFF__MAX_INDEX);
+	header = columns[dfmt->idx].name;
+	width  = columns[dfmt->idx].width;
+
+	/* Only our defined HPP fmts should appear here. */
+	BUG_ON(!header);
+
+	if (data__files_cnt > 2)
+		scnprintf(buf, MAX_HEADER_NAME, "%s/%d", header, d->idx);
+
+#define NAME (data__files_cnt > 2 ? buf : header)
+	dfmt->header_width = width;
+	width = (int) strlen(NAME);
+	if (dfmt->header_width < width)
+		dfmt->header_width = width;
+
+	scnprintf(buf_indent, MAX_HEADER_NAME, "%*s",
+		  dfmt->header_width, NAME);
+
+	dfmt->header = strdup(buf_indent);
+#undef MAX_HEADER_NAME
+#undef NAME
+}
+
+static void data__hpp_register(struct data__file *d, int idx)
+{
+	struct diff_hpp_fmt *dfmt = &d->fmt[idx];
+	struct perf_hpp_fmt *fmt = &dfmt->fmt;
+
+	dfmt->idx = idx;
+
+	fmt->header = hpp__header;
+	fmt->width  = hpp__width;
+	fmt->entry  = hpp__entry_global;
+
+	/* TODO more colors */
+	switch (idx) {
+	case PERF_HPP_DIFF__BASELINE:
+		fmt->color = hpp__color_baseline;
+		break;
+	case PERF_HPP_DIFF__DELTA:
+		fmt->color = hpp__color_delta;
+		break;
+	case PERF_HPP_DIFF__RATIO:
+		fmt->color = hpp__color_ratio;
+		break;
+	case PERF_HPP_DIFF__WEIGHTED_DIFF:
+		fmt->color = hpp__color_wdiff;
+		break;
+	default:
+		break;
+	}
+
+	init_header(d, dfmt);
+	perf_hpp__column_register(fmt);
+}
+
+static void ui_init(void)
+{
+	struct data__file *d;
+	int i;
+
+	data__for_each_file(i, d) {
+
+		/*
+		 * Baseline or compute realted columns:
+		 *
+		 *   PERF_HPP_DIFF__BASELINE
+		 *   PERF_HPP_DIFF__DELTA
+		 *   PERF_HPP_DIFF__RATIO
+		 *   PERF_HPP_DIFF__WEIGHTED_DIFF
+		 */
+		data__hpp_register(d, i ? compute_2_hpp[compute] :
+					  PERF_HPP_DIFF__BASELINE);
+
+		/*
+		 * And the rest:
+		 *
+		 * PERF_HPP_DIFF__FORMULA
+		 * PERF_HPP_DIFF__PERIOD
+		 * PERF_HPP_DIFF__PERIOD_BASELINE
+		 */
+		if (show_formula && i)
+			data__hpp_register(d, PERF_HPP_DIFF__FORMULA);
+
+		if (show_period)
+			data__hpp_register(d, i ? PERF_HPP_DIFF__PERIOD :
+						  PERF_HPP_DIFF__PERIOD_BASELINE);
+	}
+}
+
+static int data_init(int argc, const char **argv)
+{
+	struct data__file *d;
+	static const char *defaults[] = {
+		"perf.data.old",
+		"perf.data",
+	};
+	bool use_default = true;
+	int i;
+
+	data__files_cnt = 2;
+
 	if (argc) {
-		if (argc > 2)
-			usage_with_options(diff_usage, options);
-		if (argc == 2) {
-			input_old = argv[0];
-			input_new = argv[1];
-		} else
-			input_new = argv[0];
-	} else if (symbol_conf.default_guest_vmlinux_name ||
-		   symbol_conf.default_guest_kallsyms) {
-		input_old = "perf.data.host";
-		input_new = "perf.data.guest";
-	}
-
-	symbol_conf.exclude_other = false;
+		if (argc == 1)
+			defaults[1] = argv[0];
+		else {
+			data__files_cnt = argc;
+			use_default = false;
+		}
+	} else if (perf_guest) {
+		defaults[0] = "perf.data.host";
+		defaults[1] = "perf.data.guest";
+	}
+
+	if (sort_compute >= (unsigned int) data__files_cnt) {
+		pr_err("Order option out of limit.\n");
+		return -EINVAL;
+	}
+
+	data__files = zalloc(sizeof(*data__files) * data__files_cnt);
+	if (!data__files)
+		return -ENOMEM;
+
+	data__for_each_file(i, d) {
+		struct perf_data_file *file = &d->file;
+
+		file->path  = use_default ? defaults[i] : argv[i];
+		file->mode  = PERF_DATA_MODE_READ,
+		file->force = force,
+
+		d->idx  = i;
+	}
+
+	return 0;
+}
+
+int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused)
+{
+	perf_config(perf_default_config, NULL);
+
+	argc = parse_options(argc, argv, options, diff_usage, 0);
+
 	if (symbol__init() < 0)
 		return -1;
 
-	setup_sorting(diff_usage, options);
+	if (data_init(argc, argv) < 0)
+		return -1;
+
+	ui_init();
+
+	sort__mode = SORT_MODE__DIFF;
+
+	if (setup_sorting() < 0)
+		usage_with_options(diff_usage, options);
+
 	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-evlist.c b/tools/perf/builtin-evlist.c
new file mode 100644
index 00000000000..c99e0de7e54
--- /dev/null
+++ b/tools/perf/builtin-evlist.c
@@ -0,0 +1,66 @@
+/*
+ * Builtin evlist command: Show the list of event selectors present
+ * in a perf.data file.
+ */
+#include "builtin.h"
+
+#include "util/util.h"
+
+#include <linux/list.h>
+
+#include "perf.h"
+#include "util/evlist.h"
+#include "util/evsel.h"
+#include "util/parse-events.h"
+#include "util/parse-options.h"
+#include "util/session.h"
+#include "util/data.h"
+
+static int __cmd_evlist(const char *file_name, struct perf_attr_details *details)
+{
+	struct perf_session *session;
+	struct perf_evsel *pos;
+	struct perf_data_file file = {
+		.path = file_name,
+		.mode = PERF_DATA_MODE_READ,
+	};
+
+	session = perf_session__new(&file, 0, NULL);
+	if (session == NULL)
+		return -ENOMEM;
+
+	evlist__for_each(session->evlist, pos)
+		perf_evsel__fprintf(pos, details, stdout);
+
+	perf_session__delete(session);
+	return 0;
+}
+
+int cmd_evlist(int argc, const char **argv, const char *prefix __maybe_unused)
+{
+	struct perf_attr_details details = { .verbose = false, };
+	const struct option options[] = {
+	OPT_STRING('i', "input", &input_name, "file", "Input file name"),
+	OPT_BOOLEAN('F', "freq", &details.freq, "Show the sample frequency"),
+	OPT_BOOLEAN('v', "verbose", &details.verbose,
+		    "Show all event attr details"),
+	OPT_BOOLEAN('g', "group", &details.event_group,
+		    "Show event group information"),
+	OPT_END()
+	};
+	const char * const evlist_usage[] = {
+		"perf evlist [<options>]",
+		NULL
+	};
+
+	argc = parse_options(argc, argv, options, evlist_usage, 0);
+	if (argc)
+		usage_with_options(evlist_usage, options);
+
+	if (details.event_group && (details.verbose || details.freq)) {
+		pr_err("--group option is not compatible with other options\n");
+		usage_with_options(evlist_usage, options);
+	}
+
+	return __cmd_evlist(input_name, &details);
+}
diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c
index 6d5a8a7faf4..178b88ae3d2 100644
--- a/tools/perf/builtin-help.c
+++ b/tools/perf/builtin-help.c
@@ -24,28 +24,12 @@ static struct man_viewer_info_list {
 } *man_viewer_info_list;
 
 enum help_format {
+	HELP_FORMAT_NONE,
 	HELP_FORMAT_MAN,
 	HELP_FORMAT_INFO,
 	HELP_FORMAT_WEB,
 };
 
-static bool show_all = false;
-static enum help_format help_format = HELP_FORMAT_MAN;
-static struct option builtin_help_options[] = {
-	OPT_BOOLEAN('a', "all", &show_all, "print all available commands"),
-	OPT_SET_UINT('m', "man", &help_format, "show man page", HELP_FORMAT_MAN),
-	OPT_SET_UINT('w', "web", &help_format, "show manual in web browser",
-			HELP_FORMAT_WEB),
-	OPT_SET_UINT('i', "info", &help_format, "show info page",
-			HELP_FORMAT_INFO),
-	OPT_END(),
-};
-
-static const char * const builtin_help_usage[] = {
-	"perf help [--all] [--man|--web|--info] [command]",
-	NULL
-};
-
 static enum help_format parse_help_format(const char *format)
 {
 	if (!strcmp(format, "man"))
@@ -54,7 +38,9 @@ static enum help_format parse_help_format(const char *format)
 		return HELP_FORMAT_INFO;
 	if (!strcmp(format, "web") || !strcmp(format, "html"))
 		return HELP_FORMAT_WEB;
-	die("unrecognized help format '%s'", format);
+
+	pr_err("unrecognized help format '%s'", format);
+	return HELP_FORMAT_NONE;
 }
 
 static const char *get_man_viewer_info(const char *name)
@@ -255,10 +241,14 @@ static int add_man_viewer_info(const char *var, const char *value)
 
 static int perf_help_config(const char *var, const char *value, void *cb)
 {
+	enum help_format *help_formatp = cb;
+
 	if (!strcmp(var, "help.format")) {
 		if (!value)
 			return config_error_nonbool(var);
-		help_format = parse_help_format(value);
+		*help_formatp = parse_help_format(value);
+		if (*help_formatp == HELP_FORMAT_NONE)
+			return -1;
 		return 0;
 	}
 	if (!strcmp(var, "man.viewer")) {
@@ -352,7 +342,7 @@ static void exec_viewer(const char *name, const char *page)
 		warning("'%s': unknown man viewer.", name);
 }
 
-static void show_man_page(const char *perf_cmd)
+static int show_man_page(const char *perf_cmd)
 {
 	struct man_viewer_list *viewer;
 	const char *page = cmd_to_page(perf_cmd);
@@ -365,28 +355,35 @@ static void show_man_page(const char *perf_cmd)
 	if (fallback)
 		exec_viewer(fallback, page);
 	exec_viewer("man", page);
-	die("no man viewer handled the request");
+
+	pr_err("no man viewer handled the request");
+	return -1;
 }
 
-static void show_info_page(const char *perf_cmd)
+static int show_info_page(const char *perf_cmd)
 {
 	const char *page = cmd_to_page(perf_cmd);
 	setenv("INFOPATH", system_path(PERF_INFO_PATH), 1);
 	execlp("info", "info", "perfman", page, NULL);
+	return -1;
 }
 
-static void get_html_page_path(struct strbuf *page_path, const char *page)
+static int get_html_page_path(struct strbuf *page_path, const char *page)
 {
 	struct stat st;
 	const char *html_path = system_path(PERF_HTML_PATH);
 
 	/* Check that we have a perf documentation directory. */
 	if (stat(mkpath("%s/perf.html", html_path), &st)
-	    || !S_ISREG(st.st_mode))
-		die("'%s': not a documentation directory.", html_path);
+	    || !S_ISREG(st.st_mode)) {
+		pr_err("'%s': not a documentation directory.", html_path);
+		return -1;
+	}
 
 	strbuf_init(page_path, 0);
 	strbuf_addf(page_path, "%s/%s.html", html_path, page);
+
+	return 0;
 }
 
 /*
@@ -401,23 +398,42 @@ static void open_html(const char *path)
 }
 #endif
 
-static void show_html_page(const char *perf_cmd)
+static int show_html_page(const char *perf_cmd)
 {
 	const char *page = cmd_to_page(perf_cmd);
 	struct strbuf page_path; /* it leaks but we exec bellow */
 
-	get_html_page_path(&page_path, page);
+	if (get_html_page_path(&page_path, page) != 0)
+		return -1;
 
 	open_html(page_path.buf);
+
+	return 0;
 }
 
-int cmd_help(int argc, const char **argv, const char *prefix __used)
+int cmd_help(int argc, const char **argv, const char *prefix __maybe_unused)
 {
+	bool show_all = false;
+	enum help_format help_format = HELP_FORMAT_MAN;
+	struct option builtin_help_options[] = {
+	OPT_BOOLEAN('a', "all", &show_all, "print all available commands"),
+	OPT_SET_UINT('m', "man", &help_format, "show man page", HELP_FORMAT_MAN),
+	OPT_SET_UINT('w', "web", &help_format, "show manual in web browser",
+			HELP_FORMAT_WEB),
+	OPT_SET_UINT('i', "info", &help_format, "show info page",
+			HELP_FORMAT_INFO),
+	OPT_END(),
+	};
+	const char * const builtin_help_usage[] = {
+		"perf help [--all] [--man|--web|--info] [command]",
+		NULL
+	};
 	const char *alias;
+	int rc = 0;
 
 	load_command_list("perf-", &main_cmds, &other_cmds);
 
-	perf_config(perf_help_config, NULL);
+	perf_config(perf_help_config, &help_format);
 
 	argc = parse_options(argc, argv, builtin_help_options,
 			builtin_help_usage, 0);
@@ -444,16 +460,20 @@ int cmd_help(int argc, const char **argv, const char *prefix __used)
 
 	switch (help_format) {
 	case HELP_FORMAT_MAN:
-		show_man_page(argv[0]);
+		rc = show_man_page(argv[0]);
 		break;
 	case HELP_FORMAT_INFO:
-		show_info_page(argv[0]);
+		rc = show_info_page(argv[0]);
 		break;
 	case HELP_FORMAT_WEB:
-		show_html_page(argv[0]);
+		rc = show_html_page(argv[0]);
+		break;
+	case HELP_FORMAT_NONE:
+		/* fall-through */
 	default:
+		rc = -1;
 		break;
 	}
 
-	return 0;
+	return rc;
 }
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 8e3e47b064c..16c7c11ad06 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -8,110 +8,200 @@
 #include "builtin.h"
 
 #include "perf.h"
+#include "util/color.h"
+#include "util/evlist.h"
+#include "util/evsel.h"
 #include "util/session.h"
+#include "util/tool.h"
 #include "util/debug.h"
+#include "util/build-id.h"
+#include "util/data.h"
 
 #include "util/parse-options.h"
 
-static char		const *input_name = "-";
-static bool		inject_build_ids;
+#include <linux/list.h>
 
-static int event__repipe(event_t *event __used,
-			 struct perf_session *session __used)
+struct perf_inject {
+	struct perf_tool	tool;
+	bool			build_ids;
+	bool			sched_stat;
+	const char		*input_name;
+	struct perf_data_file	output;
+	u64			bytes_written;
+	struct list_head	samples;
+};
+
+struct event_entry {
+	struct list_head node;
+	u32		 tid;
+	union perf_event event[0];
+};
+
+static int perf_event__repipe_synth(struct perf_tool *tool,
+				    union perf_event *event)
+{
+	struct perf_inject *inject = container_of(tool, struct perf_inject, tool);
+	ssize_t size;
+
+	size = perf_data_file__write(&inject->output, event,
+				     event->header.size);
+	if (size < 0)
+		return -errno;
+
+	inject->bytes_written += size;
+	return 0;
+}
+
+static int perf_event__repipe_op2_synth(struct perf_tool *tool,
+					union perf_event *event,
+					struct perf_session *session
+					__maybe_unused)
 {
-	uint32_t size;
-	void *buf = event;
+	return perf_event__repipe_synth(tool, event);
+}
+
+static int perf_event__repipe_attr(struct perf_tool *tool,
+				   union perf_event *event,
+				   struct perf_evlist **pevlist)
+{
+	struct perf_inject *inject = container_of(tool, struct perf_inject,
+						  tool);
+	int ret;
+
+	ret = perf_event__process_attr(tool, event, pevlist);
+	if (ret)
+		return ret;
+
+	if (!inject->output.is_pipe)
+		return 0;
 
-	size = event->header.size;
+	return perf_event__repipe_synth(tool, event);
+}
 
-	while (size) {
-		int ret = write(STDOUT_FILENO, buf, size);
-		if (ret < 0)
-			return -errno;
+static int perf_event__repipe(struct perf_tool *tool,
+			      union perf_event *event,
+			      struct perf_sample *sample __maybe_unused,
+			      struct machine *machine __maybe_unused)
+{
+	return perf_event__repipe_synth(tool, event);
+}
 
-		size -= ret;
-		buf += ret;
+typedef int (*inject_handler)(struct perf_tool *tool,
+			      union perf_event *event,
+			      struct perf_sample *sample,
+			      struct perf_evsel *evsel,
+			      struct machine *machine);
+
+static int perf_event__repipe_sample(struct perf_tool *tool,
+				     union perf_event *event,
+				     struct perf_sample *sample,
+				     struct perf_evsel *evsel,
+				     struct machine *machine)
+{
+	if (evsel->handler) {
+		inject_handler f = evsel->handler;
+		return f(tool, event, sample, evsel, machine);
 	}
 
-	return 0;
+	build_id__mark_dso_hit(tool, event, sample, evsel, machine);
+
+	return perf_event__repipe_synth(tool, event);
+}
+
+static int perf_event__repipe_mmap(struct perf_tool *tool,
+				   union perf_event *event,
+				   struct perf_sample *sample,
+				   struct machine *machine)
+{
+	int err;
+
+	err = perf_event__process_mmap(tool, event, sample, machine);
+	perf_event__repipe(tool, event, sample, machine);
+
+	return err;
 }
 
-static int event__repipe_mmap(event_t *self, struct perf_session *session)
+static int perf_event__repipe_mmap2(struct perf_tool *tool,
+				   union perf_event *event,
+				   struct perf_sample *sample,
+				   struct machine *machine)
 {
 	int err;
 
-	err = event__process_mmap(self, session);
-	event__repipe(self, session);
+	err = perf_event__process_mmap2(tool, event, sample, machine);
+	perf_event__repipe(tool, event, sample, machine);
 
 	return err;
 }
 
-static int event__repipe_task(event_t *self, struct perf_session *session)
+static int perf_event__repipe_fork(struct perf_tool *tool,
+				   union perf_event *event,
+				   struct perf_sample *sample,
+				   struct machine *machine)
 {
 	int err;
 
-	err = event__process_task(self, session);
-	event__repipe(self, session);
+	err = perf_event__process_fork(tool, event, sample, machine);
+	perf_event__repipe(tool, event, sample, machine);
 
 	return err;
 }
 
-static int event__repipe_tracing_data(event_t *self,
-				      struct perf_session *session)
+static int perf_event__repipe_tracing_data(struct perf_tool *tool,
+					   union perf_event *event,
+					   struct perf_session *session)
 {
 	int err;
 
-	event__repipe(self, session);
-	err = event__process_tracing_data(self, session);
+	perf_event__repipe_synth(tool, event);
+	err = perf_event__process_tracing_data(tool, event, session);
 
 	return err;
 }
 
-static int dso__read_build_id(struct dso *self)
+static int dso__read_build_id(struct dso *dso)
 {
-	if (self->has_build_id)
+	if (dso->has_build_id)
 		return 0;
 
-	if (filename__read_build_id(self->long_name, self->build_id,
-				    sizeof(self->build_id)) > 0) {
-		self->has_build_id = true;
+	if (filename__read_build_id(dso->long_name, dso->build_id,
+				    sizeof(dso->build_id)) > 0) {
+		dso->has_build_id = true;
 		return 0;
 	}
 
 	return -1;
 }
 
-static int dso__inject_build_id(struct dso *self, struct perf_session *session)
+static int dso__inject_build_id(struct dso *dso, struct perf_tool *tool,
+				struct machine *machine)
 {
 	u16 misc = PERF_RECORD_MISC_USER;
-	struct machine *machine;
 	int err;
 
-	if (dso__read_build_id(self) < 0) {
-		pr_debug("no build_id found for %s\n", self->long_name);
+	if (dso__read_build_id(dso) < 0) {
+		pr_debug("no build_id found for %s\n", dso->long_name);
 		return -1;
 	}
 
-	machine = perf_session__find_host_machine(session);
-	if (machine == NULL) {
-		pr_err("Can't find machine for session\n");
-		return -1;
-	}
-
-	if (self->kernel)
+	if (dso->kernel)
 		misc = PERF_RECORD_MISC_KERNEL;
 
-	err = event__synthesize_build_id(self, misc, event__repipe,
-					 machine, session);
+	err = perf_event__synthesize_build_id(tool, dso, misc, perf_event__repipe,
+					      machine);
 	if (err) {
-		pr_err("Can't synthesize build_id event for %s\n", self->long_name);
+		pr_err("Can't synthesize build_id event for %s\n", dso->long_name);
 		return -1;
 	}
 
 	return 0;
 }
 
-static int event__inject_buildid(event_t *event, struct perf_session *session)
+static int perf_event__inject_buildid(struct perf_tool *tool,
+				      union perf_event *event,
+				      struct perf_sample *sample,
+				      struct perf_evsel *evsel __maybe_unused,
+				      struct machine *machine)
 {
 	struct addr_location al;
 	struct thread *thread;
@@ -119,110 +209,255 @@ static int event__inject_buildid(event_t *event, struct perf_session *session)
 
 	cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 
-	thread = perf_session__findnew(session, event->ip.pid);
+	thread = machine__findnew_thread(machine, sample->pid, sample->tid);
 	if (thread == NULL) {
 		pr_err("problem processing %d event, skipping it.\n",
 		       event->header.type);
 		goto repipe;
 	}
 
-	thread__find_addr_map(thread, session, cpumode, MAP__FUNCTION,
-			      event->ip.pid, event->ip.ip, &al);
+	thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION,
+			      sample->ip, &al);
 
 	if (al.map != NULL) {
 		if (!al.map->dso->hit) {
 			al.map->dso->hit = 1;
 			if (map__load(al.map, NULL) >= 0) {
-				dso__inject_build_id(al.map->dso, session);
+				dso__inject_build_id(al.map->dso, tool, machine);
 				/*
 				 * If this fails, too bad, let the other side
 				 * account this as unresolved.
 				 */
-			} else
+			} else {
+#ifdef HAVE_LIBELF_SUPPORT
 				pr_warning("no symbols found in %s, maybe "
 					   "install a debug package?\n",
 					   al.map->dso->long_name);
+#endif
+			}
 		}
 	}
 
 repipe:
-	event__repipe(event, session);
+	perf_event__repipe(tool, event, sample, machine);
 	return 0;
 }
 
-struct perf_event_ops inject_ops = {
-	.sample		= event__repipe,
-	.mmap		= event__repipe,
-	.comm		= event__repipe,
-	.fork		= event__repipe,
-	.exit		= event__repipe,
-	.lost		= event__repipe,
-	.read		= event__repipe,
-	.throttle	= event__repipe,
-	.unthrottle	= event__repipe,
-	.attr		= event__repipe,
-	.event_type 	= event__repipe,
-	.tracing_data 	= event__repipe,
-	.build_id 	= event__repipe,
-};
+static int perf_inject__sched_process_exit(struct perf_tool *tool,
+					   union perf_event *event __maybe_unused,
+					   struct perf_sample *sample,
+					   struct perf_evsel *evsel __maybe_unused,
+					   struct machine *machine __maybe_unused)
+{
+	struct perf_inject *inject = container_of(tool, struct perf_inject, tool);
+	struct event_entry *ent;
+
+	list_for_each_entry(ent, &inject->samples, node) {
+		if (sample->tid == ent->tid) {
+			list_del_init(&ent->node);
+			free(ent);
+			break;
+		}
+	}
 
-extern volatile int session_done;
+	return 0;
+}
 
-static void sig_handler(int sig __attribute__((__unused__)))
+static int perf_inject__sched_switch(struct perf_tool *tool,
+				     union perf_event *event,
+				     struct perf_sample *sample,
+				     struct perf_evsel *evsel,
+				     struct machine *machine)
+{
+	struct perf_inject *inject = container_of(tool, struct perf_inject, tool);
+	struct event_entry *ent;
+
+	perf_inject__sched_process_exit(tool, event, sample, evsel, machine);
+
+	ent = malloc(event->header.size + sizeof(struct event_entry));
+	if (ent == NULL) {
+		color_fprintf(stderr, PERF_COLOR_RED,
+			     "Not enough memory to process sched switch event!");
+		return -1;
+	}
+
+	ent->tid = sample->tid;
+	memcpy(&ent->event, event, event->header.size);
+	list_add(&ent->node, &inject->samples);
+	return 0;
+}
+
+static int perf_inject__sched_stat(struct perf_tool *tool,
+				   union perf_event *event __maybe_unused,
+				   struct perf_sample *sample,
+				   struct perf_evsel *evsel,
+				   struct machine *machine)
+{
+	struct event_entry *ent;
+	union perf_event *event_sw;
+	struct perf_sample sample_sw;
+	struct perf_inject *inject = container_of(tool, struct perf_inject, tool);
+	u32 pid = perf_evsel__intval(evsel, sample, "pid");
+
+	list_for_each_entry(ent, &inject->samples, node) {
+		if (pid == ent->tid)
+			goto found;
+	}
+
+	return 0;
+found:
+	event_sw = &ent->event[0];
+	perf_evsel__parse_sample(evsel, event_sw, &sample_sw);
+
+	sample_sw.period = sample->period;
+	sample_sw.time	 = sample->time;
+	perf_event__synthesize_sample(event_sw, evsel->attr.sample_type,
+				      evsel->attr.read_format, &sample_sw,
+				      false);
+	build_id__mark_dso_hit(tool, event_sw, &sample_sw, evsel, machine);
+	return perf_event__repipe(tool, event_sw, &sample_sw, machine);
+}
+
+static void sig_handler(int sig __maybe_unused)
 {
 	session_done = 1;
 }
 
-static int __cmd_inject(void)
+static int perf_evsel__check_stype(struct perf_evsel *evsel,
+				   u64 sample_type, const char *sample_msg)
+{
+	struct perf_event_attr *attr = &evsel->attr;
+	const char *name = perf_evsel__name(evsel);
+
+	if (!(attr->sample_type & sample_type)) {
+		pr_err("Samples for %s event do not have %s attribute set.",
+			name, sample_msg);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int __cmd_inject(struct perf_inject *inject)
 {
 	struct perf_session *session;
 	int ret = -EINVAL;
+	struct perf_data_file file = {
+		.path = inject->input_name,
+		.mode = PERF_DATA_MODE_READ,
+	};
+	struct perf_data_file *file_out = &inject->output;
 
 	signal(SIGINT, sig_handler);
 
-	if (inject_build_ids) {
-		inject_ops.sample	= event__inject_buildid;
-		inject_ops.mmap		= event__repipe_mmap;
-		inject_ops.fork		= event__repipe_task;
-		inject_ops.tracing_data	= event__repipe_tracing_data;
+	if (inject->build_ids || inject->sched_stat) {
+		inject->tool.mmap	  = perf_event__repipe_mmap;
+		inject->tool.mmap2	  = perf_event__repipe_mmap2;
+		inject->tool.fork	  = perf_event__repipe_fork;
+		inject->tool.tracing_data = perf_event__repipe_tracing_data;
 	}
 
-	session = perf_session__new(input_name, O_RDONLY, false, true);
+	session = perf_session__new(&file, true, &inject->tool);
 	if (session == NULL)
 		return -ENOMEM;
 
-	ret = perf_session__process_events(session, &inject_ops);
+	if (inject->build_ids) {
+		inject->tool.sample = perf_event__inject_buildid;
+	} else if (inject->sched_stat) {
+		struct perf_evsel *evsel;
+
+		inject->tool.ordered_samples = true;
+
+		evlist__for_each(session->evlist, evsel) {
+			const char *name = perf_evsel__name(evsel);
+
+			if (!strcmp(name, "sched:sched_switch")) {
+				if (perf_evsel__check_stype(evsel, PERF_SAMPLE_TID, "TID"))
+					return -EINVAL;
+
+				evsel->handler = perf_inject__sched_switch;
+			} else if (!strcmp(name, "sched:sched_process_exit"))
+				evsel->handler = perf_inject__sched_process_exit;
+			else if (!strncmp(name, "sched:sched_stat_", 17))
+				evsel->handler = perf_inject__sched_stat;
+		}
+	}
+
+	if (!file_out->is_pipe)
+		lseek(file_out->fd, session->header.data_offset, SEEK_SET);
+
+	ret = perf_session__process_events(session, &inject->tool);
+
+	if (!file_out->is_pipe) {
+		session->header.data_size = inject->bytes_written;
+		perf_session__write_header(session, session->evlist, file_out->fd, true);
+	}
 
 	perf_session__delete(session);
 
 	return ret;
 }
 
-static const char * const report_usage[] = {
-	"perf inject [<options>]",
-	NULL
-};
-
-static const struct option options[] = {
-	OPT_BOOLEAN('b', "build-ids", &inject_build_ids,
-		    "Inject build-ids into the output stream"),
-	OPT_INCR('v', "verbose", &verbose,
-		 "be more verbose (show build ids, etc)"),
-	OPT_END()
-};
-
-int cmd_inject(int argc, const char **argv, const char *prefix __used)
+int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
 {
-	argc = parse_options(argc, argv, options, report_usage, 0);
+	struct perf_inject inject = {
+		.tool = {
+			.sample		= perf_event__repipe_sample,
+			.mmap		= perf_event__repipe,
+			.mmap2		= perf_event__repipe,
+			.comm		= perf_event__repipe,
+			.fork		= perf_event__repipe,
+			.exit		= perf_event__repipe,
+			.lost		= perf_event__repipe,
+			.read		= perf_event__repipe_sample,
+			.throttle	= perf_event__repipe,
+			.unthrottle	= perf_event__repipe,
+			.attr		= perf_event__repipe_attr,
+			.tracing_data	= perf_event__repipe_op2_synth,
+			.finished_round	= perf_event__repipe_op2_synth,
+			.build_id	= perf_event__repipe_op2_synth,
+		},
+		.input_name  = "-",
+		.samples = LIST_HEAD_INIT(inject.samples),
+		.output = {
+			.path = "-",
+			.mode = PERF_DATA_MODE_WRITE,
+		},
+	};
+	const struct option options[] = {
+		OPT_BOOLEAN('b', "build-ids", &inject.build_ids,
+			    "Inject build-ids into the output stream"),
+		OPT_STRING('i', "input", &inject.input_name, "file",
+			   "input file name"),
+		OPT_STRING('o', "output", &inject.output.path, "file",
+			   "output file name"),
+		OPT_BOOLEAN('s', "sched-stat", &inject.sched_stat,
+			    "Merge sched-stat and sched-switch for getting events "
+			    "where and how long tasks slept"),
+		OPT_INCR('v', "verbose", &verbose,
+			 "be more verbose (show build ids, etc)"),
+		OPT_END()
+	};
+	const char * const inject_usage[] = {
+		"perf inject [<options>]",
+		NULL
+	};
+
+	argc = parse_options(argc, argv, options, inject_usage, 0);
 
 	/*
 	 * Any (unrecognized) arguments left?
 	 */
 	if (argc)
-		usage_with_options(report_usage, options);
+		usage_with_options(inject_usage, options);
+
+	if (perf_data_file__open(&inject.output)) {
+		perror("failed to create output file");
+		return -1;
+	}
 
 	if (symbol__init() < 0)
 		return -1;
 
-	return __cmd_inject();
+	return __cmd_inject(&inject);
 }
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 31f60a2535e..bef3376bfaf 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -1,25 +1,29 @@
 #include "builtin.h"
 #include "perf.h"
 
+#include "util/evlist.h"
+#include "util/evsel.h"
 #include "util/util.h"
 #include "util/cache.h"
 #include "util/symbol.h"
 #include "util/thread.h"
 #include "util/header.h"
 #include "util/session.h"
+#include "util/tool.h"
 
 #include "util/parse-options.h"
 #include "util/trace-event.h"
+#include "util/data.h"
+#include "util/cpumap.h"
 
 #include "util/debug.h"
 
 #include <linux/rbtree.h>
+#include <linux/string.h>
 
 struct alloc_stat;
 typedef int (*sort_fn_t)(struct alloc_stat *, struct alloc_stat *);
 
-static char const		*input_name = "perf.data";
-
 static int			alloc_flag;
 static int			caller_flag;
 
@@ -28,11 +32,6 @@ static int			caller_lines = -1;
 
 static bool			raw_ip;
 
-static char			default_sort_order[] = "frag,hit,bytes";
-
-static int			*cpunode_map;
-static int			max_cpu_num;
-
 struct alloc_stat {
 	u64	call_site;
 	u64	ptr;
@@ -54,64 +53,8 @@ static struct rb_root root_caller_sorted;
 static unsigned long total_requested, total_allocated;
 static unsigned long nr_allocs, nr_cross_allocs;
 
-#define PATH_SYS_NODE	"/sys/devices/system/node"
-
-static void init_cpunode_map(void)
-{
-	FILE *fp;
-	int i;
-
-	fp = fopen("/sys/devices/system/cpu/kernel_max", "r");
-	if (!fp) {
-		max_cpu_num = 4096;
-		return;
-	}
-
-	if (fscanf(fp, "%d", &max_cpu_num) < 1)
-		die("Failed to read 'kernel_max' from sysfs");
-	max_cpu_num++;
-
-	cpunode_map = calloc(max_cpu_num, sizeof(int));
-	if (!cpunode_map)
-		die("calloc");
-	for (i = 0; i < max_cpu_num; i++)
-		cpunode_map[i] = -1;
-	fclose(fp);
-}
-
-static void setup_cpunode_map(void)
-{
-	struct dirent *dent1, *dent2;
-	DIR *dir1, *dir2;
-	unsigned int cpu, mem;
-	char buf[PATH_MAX];
-
-	init_cpunode_map();
-
-	dir1 = opendir(PATH_SYS_NODE);
-	if (!dir1)
-		return;
-
-	while ((dent1 = readdir(dir1)) != NULL) {
-		if (dent1->d_type != DT_DIR ||
-		    sscanf(dent1->d_name, "node%u", &mem) < 1)
-			continue;
-
-		snprintf(buf, PATH_MAX, "%s/%s", PATH_SYS_NODE, dent1->d_name);
-		dir2 = opendir(buf);
-		if (!dir2)
-			continue;
-		while ((dent2 = readdir(dir2)) != NULL) {
-			if (dent2->d_type != DT_LNK ||
-			    sscanf(dent2->d_name, "cpu%u", &cpu) < 1)
-				continue;
-			cpunode_map[cpu] = mem;
-		}
-	}
-}
-
-static void insert_alloc_stat(unsigned long call_site, unsigned long ptr,
-			      int bytes_req, int bytes_alloc, int cpu)
+static int insert_alloc_stat(unsigned long call_site, unsigned long ptr,
+			     int bytes_req, int bytes_alloc, int cpu)
 {
 	struct rb_node **node = &root_alloc_stat.rb_node;
 	struct rb_node *parent = NULL;
@@ -135,8 +78,10 @@ static void insert_alloc_stat(unsigned long call_site, unsigned long ptr,
 		data->bytes_alloc += bytes_alloc;
 	} else {
 		data = malloc(sizeof(*data));
-		if (!data)
-			die("malloc");
+		if (!data) {
+			pr_err("%s: malloc failed\n", __func__);
+			return -1;
+		}
 		data->ptr = ptr;
 		data->pingpong = 0;
 		data->hit = 1;
@@ -148,9 +93,10 @@ static void insert_alloc_stat(unsigned long call_site, unsigned long ptr,
 	}
 	data->call_site = call_site;
 	data->alloc_cpu = cpu;
+	return 0;
 }
 
-static void insert_caller_stat(unsigned long call_site,
+static int insert_caller_stat(unsigned long call_site,
 			      int bytes_req, int bytes_alloc)
 {
 	struct rb_node **node = &root_caller_stat.rb_node;
@@ -175,8 +121,10 @@ static void insert_caller_stat(unsigned long call_site,
 		data->bytes_alloc += bytes_alloc;
 	} else {
 		data = malloc(sizeof(*data));
-		if (!data)
-			die("malloc");
+		if (!data) {
+			pr_err("%s: malloc failed\n", __func__);
+			return -1;
+		}
 		data->call_site = call_site;
 		data->pingpong = 0;
 		data->hit = 1;
@@ -186,39 +134,43 @@ static void insert_caller_stat(unsigned long call_site,
 		rb_link_node(&data->node, parent, node);
 		rb_insert_color(&data->node, &root_caller_stat);
 	}
+
+	return 0;
 }
 
-static void process_alloc_event(void *data,
-				struct event *event,
-				int cpu,
-				u64 timestamp __used,
-				struct thread *thread __used,
-				int node)
+static int perf_evsel__process_alloc_event(struct perf_evsel *evsel,
+					   struct perf_sample *sample)
 {
-	unsigned long call_site;
-	unsigned long ptr;
-	int bytes_req;
-	int bytes_alloc;
-	int node1, node2;
-
-	ptr = raw_field_value(event, "ptr", data);
-	call_site = raw_field_value(event, "call_site", data);
-	bytes_req = raw_field_value(event, "bytes_req", data);
-	bytes_alloc = raw_field_value(event, "bytes_alloc", data);
+	unsigned long ptr = perf_evsel__intval(evsel, sample, "ptr"),
+		      call_site = perf_evsel__intval(evsel, sample, "call_site");
+	int bytes_req = perf_evsel__intval(evsel, sample, "bytes_req"),
+	    bytes_alloc = perf_evsel__intval(evsel, sample, "bytes_alloc");
 
-	insert_alloc_stat(call_site, ptr, bytes_req, bytes_alloc, cpu);
-	insert_caller_stat(call_site, bytes_req, bytes_alloc);
+	if (insert_alloc_stat(call_site, ptr, bytes_req, bytes_alloc, sample->cpu) ||
+	    insert_caller_stat(call_site, bytes_req, bytes_alloc))
+		return -1;
 
 	total_requested += bytes_req;
 	total_allocated += bytes_alloc;
 
-	if (node) {
-		node1 = cpunode_map[cpu];
-		node2 = raw_field_value(event, "node", data);
+	nr_allocs++;
+	return 0;
+}
+
+static int perf_evsel__process_alloc_node_event(struct perf_evsel *evsel,
+						struct perf_sample *sample)
+{
+	int ret = perf_evsel__process_alloc_event(evsel, sample);
+
+	if (!ret) {
+		int node1 = cpu__get_node(sample->cpu),
+		    node2 = perf_evsel__intval(evsel, sample, "node");
+
 		if (node1 != node2)
 			nr_cross_allocs++;
 	}
-	nr_allocs++;
+
+	return ret;
 }
 
 static int ptr_cmp(struct alloc_stat *, struct alloc_stat *);
@@ -249,95 +201,62 @@ static struct alloc_stat *search_alloc_stat(unsigned long ptr,
 	return NULL;
 }
 
-static void process_free_event(void *data,
-			       struct event *event,
-			       int cpu,
-			       u64 timestamp __used,
-			       struct thread *thread __used)
+static int perf_evsel__process_free_event(struct perf_evsel *evsel,
+					  struct perf_sample *sample)
 {
-	unsigned long ptr;
+	unsigned long ptr = perf_evsel__intval(evsel, sample, "ptr");
 	struct alloc_stat *s_alloc, *s_caller;
 
-	ptr = raw_field_value(event, "ptr", data);
-
 	s_alloc = search_alloc_stat(ptr, 0, &root_alloc_stat, ptr_cmp);
 	if (!s_alloc)
-		return;
+		return 0;
 
-	if (cpu != s_alloc->alloc_cpu) {
+	if ((short)sample->cpu != s_alloc->alloc_cpu) {
 		s_alloc->pingpong++;
 
 		s_caller = search_alloc_stat(0, s_alloc->call_site,
 					     &root_caller_stat, callsite_cmp);
-		assert(s_caller);
+		if (!s_caller)
+			return -1;
 		s_caller->pingpong++;
 	}
 	s_alloc->alloc_cpu = -1;
-}
-
-static void
-process_raw_event(event_t *raw_event __used, void *data,
-		  int cpu, u64 timestamp, struct thread *thread)
-{
-	struct event *event;
-	int type;
-
-	type = trace_parse_common_type(data);
-	event = trace_find_event(type);
-
-	if (!strcmp(event->name, "kmalloc") ||
-	    !strcmp(event->name, "kmem_cache_alloc")) {
-		process_alloc_event(data, event, cpu, timestamp, thread, 0);
-		return;
-	}
 
-	if (!strcmp(event->name, "kmalloc_node") ||
-	    !strcmp(event->name, "kmem_cache_alloc_node")) {
-		process_alloc_event(data, event, cpu, timestamp, thread, 1);
-		return;
-	}
-
-	if (!strcmp(event->name, "kfree") ||
-	    !strcmp(event->name, "kmem_cache_free")) {
-		process_free_event(data, event, cpu, timestamp, thread);
-		return;
-	}
+	return 0;
 }
 
-static int process_sample_event(event_t *event, struct perf_session *session)
-{
-	struct sample_data data;
-	struct thread *thread;
-
-	memset(&data, 0, sizeof(data));
-	data.time = -1;
-	data.cpu = -1;
-	data.period = 1;
+typedef int (*tracepoint_handler)(struct perf_evsel *evsel,
+				  struct perf_sample *sample);
 
-	event__parse_sample(event, session->sample_type, &data);
-
-	dump_printf("(IP, %d): %d/%d: %#Lx period: %Ld\n", event->header.misc,
-		    data.pid, data.tid, data.ip, data.period);
+static int process_sample_event(struct perf_tool *tool __maybe_unused,
+				union perf_event *event,
+				struct perf_sample *sample,
+				struct perf_evsel *evsel,
+				struct machine *machine)
+{
+	struct thread *thread = machine__findnew_thread(machine, sample->pid,
+							sample->tid);
 
-	thread = perf_session__findnew(session, event->ip.pid);
 	if (thread == NULL) {
 		pr_debug("problem processing %d event, skipping it.\n",
 			 event->header.type);
 		return -1;
 	}
 
-	dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid);
+	dump_printf(" ... thread: %s:%d\n", thread__comm_str(thread), thread->tid);
 
-	process_raw_event(event, data.raw_data, data.cpu,
-			  data.time, thread);
+	if (evsel->handler != NULL) {
+		tracepoint_handler f = evsel->handler;
+		return f(evsel, sample);
+	}
 
 	return 0;
 }
 
-static struct perf_event_ops event_ops = {
-	.sample			= process_sample_event,
-	.comm			= event__process_comm,
-	.ordered_samples	= true,
+static struct perf_tool perf_kmem = {
+	.sample		 = process_sample_event,
+	.comm		 = perf_event__process_comm,
+	.ordered_samples = true,
 };
 
 static double fragmentation(unsigned long n_req, unsigned long n_alloc)
@@ -352,7 +271,7 @@ static void __print_result(struct rb_root *root, struct perf_session *session,
 			   int n_lines, int is_caller)
 {
 	struct rb_node *next;
-	struct machine *machine;
+	struct machine *machine = &session->machines.host;
 
 	printf("%.102s\n", graph_dotted_line);
 	printf(" %-34s |",  is_caller ? "Callsite": "Alloc Ptr");
@@ -361,11 +280,6 @@ static void __print_result(struct rb_root *root, struct perf_session *session,
 
 	next = rb_first(root);
 
-	machine = perf_session__find_host_machine(session);
-	if (!machine) {
-		pr_err("__print_result: couldn't find kernel information\n");
-		return;
-	}
 	while (next && n_lines--) {
 		struct alloc_stat *data = rb_entry(next, struct alloc_stat,
 						   node);
@@ -382,10 +296,10 @@ static void __print_result(struct rb_root *root, struct perf_session *session,
 			addr = data->ptr;
 
 		if (sym != NULL)
-			snprintf(buf, sizeof(buf), "%s+%Lx", sym->name,
+			snprintf(buf, sizeof(buf), "%s+%" PRIx64 "", sym->name,
 				 addr - map->unmap_ip(map, sym->start));
 		else
-			snprintf(buf, sizeof(buf), "%#Lx", addr);
+			snprintf(buf, sizeof(buf), "%#" PRIx64 "", addr);
 		printf(" %-34s |", buf);
 
 		printf(" %9llu/%-5lu | %9llu/%-5lu | %8lu | %8lu | %6.3f%%\n",
@@ -492,7 +406,21 @@ static void sort_result(void)
 static int __cmd_kmem(void)
 {
 	int err = -EINVAL;
-	struct perf_session *session = perf_session__new(input_name, O_RDONLY, 0, false);
+	struct perf_session *session;
+	const struct perf_evsel_str_handler kmem_tracepoints[] = {
+		{ "kmem:kmalloc",		perf_evsel__process_alloc_event, },
+    		{ "kmem:kmem_cache_alloc",	perf_evsel__process_alloc_event, },
+		{ "kmem:kmalloc_node",		perf_evsel__process_alloc_node_event, },
+    		{ "kmem:kmem_cache_alloc_node", perf_evsel__process_alloc_node_event, },
+		{ "kmem:kfree",			perf_evsel__process_free_event, },
+    		{ "kmem:kmem_cache_free",	perf_evsel__process_free_event, },
+	};
+	struct perf_data_file file = {
+		.path = input_name,
+		.mode = PERF_DATA_MODE_READ,
+	};
+
+	session = perf_session__new(&file, false, &perf_kmem);
 	if (session == NULL)
 		return -ENOMEM;
 
@@ -502,8 +430,13 @@ static int __cmd_kmem(void)
 	if (!perf_session__has_traces(session, "kmem record"))
 		goto out_delete;
 
+	if (perf_session__set_tracepoints_handlers(session, kmem_tracepoints)) {
+		pr_err("Initializing perf session tracepoint handlers failed\n");
+		return -1;
+	}
+
 	setup_pager();
-	err = perf_session__process_events(session, &event_ops);
+	err = perf_session__process_events(session, &perf_kmem);
 	if (err != 0)
 		goto out_delete;
 	sort_result();
@@ -513,11 +446,6 @@ out_delete:
 	return err;
 }
 
-static const char * const kmem_usage[] = {
-	"perf kmem [<options>] {record|stat}",
-	NULL
-};
-
 static int ptr_cmp(struct alloc_stat *l, struct alloc_stat *r)
 {
 	if (l->ptr < r->ptr)
@@ -616,8 +544,7 @@ static struct sort_dimension *avail_sorts[] = {
 	&pingpong_sort_dimension,
 };
 
-#define NUM_AVAIL_SORTS	\
-	(int)(sizeof(avail_sorts) / sizeof(struct sort_dimension *))
+#define NUM_AVAIL_SORTS	((int)ARRAY_SIZE(avail_sorts))
 
 static int sort_dimension__add(const char *tok, struct list_head *list)
 {
@@ -626,10 +553,11 @@ static int sort_dimension__add(const char *tok, struct list_head *list)
 
 	for (i = 0; i < NUM_AVAIL_SORTS; i++) {
 		if (!strcmp(avail_sorts[i]->name, tok)) {
-			sort = malloc(sizeof(*sort));
-			if (!sort)
-				die("malloc");
-			memcpy(sort, avail_sorts[i], sizeof(*sort));
+			sort = memdup(avail_sorts[i], sizeof(*avail_sorts[i]));
+			if (!sort) {
+				pr_err("%s: memdup failed\n", __func__);
+				return -1;
+			}
 			list_add_tail(&sort->list, list);
 			return 0;
 		}
@@ -643,8 +571,10 @@ static int setup_sorting(struct list_head *sort_list, const char *arg)
 	char *tok;
 	char *str = strdup(arg);
 
-	if (!str)
-		die("strdup");
+	if (!str) {
+		pr_err("%s: strdup failed\n", __func__);
+		return -1;
+	}
 
 	while (true) {
 		tok = strsep(&str, ",");
@@ -652,6 +582,7 @@ static int setup_sorting(struct list_head *sort_list, const char *arg)
 			break;
 		if (sort_dimension__add(tok, sort_list) < 0) {
 			error("Unknown --sort key: '%s'", tok);
+			free(str);
 			return -1;
 		}
 	}
@@ -660,8 +591,8 @@ static int setup_sorting(struct list_head *sort_list, const char *arg)
 	return 0;
 }
 
-static int parse_sort_opt(const struct option *opt __used,
-			  const char *arg, int unset __used)
+static int parse_sort_opt(const struct option *opt __maybe_unused,
+			  const char *arg, int unset __maybe_unused)
 {
 	if (!arg)
 		return -1;
@@ -674,22 +605,24 @@ static int parse_sort_opt(const struct option *opt __used,
 	return 0;
 }
 
-static int parse_caller_opt(const struct option *opt __used,
-			  const char *arg __used, int unset __used)
+static int parse_caller_opt(const struct option *opt __maybe_unused,
+			    const char *arg __maybe_unused,
+			    int unset __maybe_unused)
 {
 	caller_flag = (alloc_flag + 1);
 	return 0;
 }
 
-static int parse_alloc_opt(const struct option *opt __used,
-			  const char *arg __used, int unset __used)
+static int parse_alloc_opt(const struct option *opt __maybe_unused,
+			   const char *arg __maybe_unused,
+			   int unset __maybe_unused)
 {
 	alloc_flag = (caller_flag + 1);
 	return 0;
 }
 
-static int parse_line_opt(const struct option *opt __used,
-			  const char *arg, int unset __used)
+static int parse_line_opt(const struct option *opt __maybe_unused,
+			  const char *arg, int unset __maybe_unused)
 {
 	int lines;
 
@@ -706,47 +639,26 @@ static int parse_line_opt(const struct option *opt __used,
 	return 0;
 }
 
-static const struct option kmem_options[] = {
-	OPT_STRING('i', "input", &input_name, "file",
-		   "input file name"),
-	OPT_CALLBACK_NOOPT(0, "caller", NULL, NULL,
-			   "show per-callsite statistics",
-			   parse_caller_opt),
-	OPT_CALLBACK_NOOPT(0, "alloc", NULL, NULL,
-			   "show per-allocation statistics",
-			   parse_alloc_opt),
-	OPT_CALLBACK('s', "sort", NULL, "key[,key2...]",
-		     "sort by keys: ptr, call_site, bytes, hit, pingpong, frag",
-		     parse_sort_opt),
-	OPT_CALLBACK('l', "line", NULL, "num",
-		     "show n lines",
-		     parse_line_opt),
-	OPT_BOOLEAN(0, "raw-ip", &raw_ip, "show raw ip instead of symbol"),
-	OPT_END()
-};
-
-static const char *record_args[] = {
-	"record",
-	"-a",
-	"-R",
-	"-f",
-	"-c", "1",
+static int __cmd_record(int argc, const char **argv)
+{
+	const char * const record_args[] = {
+	"record", "-a", "-R", "-c", "1",
 	"-e", "kmem:kmalloc",
 	"-e", "kmem:kmalloc_node",
 	"-e", "kmem:kfree",
 	"-e", "kmem:kmem_cache_alloc",
 	"-e", "kmem:kmem_cache_alloc_node",
 	"-e", "kmem:kmem_cache_free",
-};
-
-static int __cmd_record(int argc, const char **argv)
-{
+	};
 	unsigned int rec_argc, i, j;
 	const char **rec_argv;
 
 	rec_argc = ARRAY_SIZE(record_args) + argc - 1;
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
 
+	if (rec_argv == NULL)
+		return -ENOMEM;
+
 	for (i = 0; i < ARRAY_SIZE(record_args); i++)
 		rec_argv[i] = strdup(record_args[i]);
 
@@ -756,9 +668,29 @@ static int __cmd_record(int argc, const char **argv)
 	return cmd_record(i, rec_argv, NULL);
 }
 
-int cmd_kmem(int argc, const char **argv, const char *prefix __used)
+int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
 {
-	argc = parse_options(argc, argv, kmem_options, kmem_usage, 0);
+	const char * const default_sort_order = "frag,hit,bytes";
+	const struct option kmem_options[] = {
+	OPT_STRING('i', "input", &input_name, "file", "input file name"),
+	OPT_CALLBACK_NOOPT(0, "caller", NULL, NULL,
+			   "show per-callsite statistics", parse_caller_opt),
+	OPT_CALLBACK_NOOPT(0, "alloc", NULL, NULL,
+			   "show per-allocation statistics", parse_alloc_opt),
+	OPT_CALLBACK('s', "sort", NULL, "key[,key2...]",
+		     "sort by keys: ptr, call_site, bytes, hit, pingpong, frag",
+		     parse_sort_opt),
+	OPT_CALLBACK('l', "line", NULL, "num", "show n lines", parse_line_opt),
+	OPT_BOOLEAN(0, "raw-ip", &raw_ip, "show raw ip instead of symbol"),
+	OPT_END()
+	};
+	const char *const kmem_subcommands[] = { "record", "stat", NULL };
+	const char *kmem_usage[] = {
+		NULL,
+		NULL
+	};
+	argc = parse_options_subcommand(argc, argv, kmem_options,
+					kmem_subcommands, kmem_usage, 0);
 
 	if (!argc)
 		usage_with_options(kmem_usage, kmem_options);
@@ -768,7 +700,8 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __used)
 	if (!strncmp(argv[0], "rec", 3)) {
 		return __cmd_record(argc, argv);
 	} else if (!strcmp(argv[0], "stat")) {
-		setup_cpunode_map();
+		if (cpu__setup_cpunode_map())
+			return -1;
 
 		if (list_empty(&caller_sort))
 			setup_sorting(&caller_sort, default_sort_order);
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 34d1e853829..0f1e5a2f6ad 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -1,57 +1,1617 @@
 #include "builtin.h"
 #include "perf.h"
 
+#include "util/evsel.h"
+#include "util/evlist.h"
 #include "util/util.h"
 #include "util/cache.h"
 #include "util/symbol.h"
 #include "util/thread.h"
 #include "util/header.h"
 #include "util/session.h"
-
+#include "util/intlist.h"
 #include "util/parse-options.h"
 #include "util/trace-event.h"
-
 #include "util/debug.h"
+#include <api/fs/debugfs.h>
+#include "util/tool.h"
+#include "util/stat.h"
+#include "util/top.h"
+#include "util/data.h"
 
 #include <sys/prctl.h>
+#ifdef HAVE_TIMERFD_SUPPORT
+#include <sys/timerfd.h>
+#endif
 
+#include <termios.h>
 #include <semaphore.h>
 #include <pthread.h>
 #include <math.h>
 
-static const char		*file_name;
-static char			name_buffer[256];
+#if defined(__i386__) || defined(__x86_64__)
+#include <asm/svm.h>
+#include <asm/vmx.h>
+#include <asm/kvm.h>
+
+struct event_key {
+	#define INVALID_KEY     (~0ULL)
+	u64 key;
+	int info;
+};
+
+struct kvm_event_stats {
+	u64 time;
+	struct stats stats;
+};
+
+struct kvm_event {
+	struct list_head hash_entry;
+	struct rb_node rb;
+
+	struct event_key key;
+
+	struct kvm_event_stats total;
+
+	#define DEFAULT_VCPU_NUM 8
+	int max_vcpu;
+	struct kvm_event_stats *vcpu;
+};
+
+typedef int (*key_cmp_fun)(struct kvm_event*, struct kvm_event*, int);
+
+struct kvm_event_key {
+	const char *name;
+	key_cmp_fun key;
+};
+
+
+struct perf_kvm_stat;
+
+struct kvm_events_ops {
+	bool (*is_begin_event)(struct perf_evsel *evsel,
+			       struct perf_sample *sample,
+			       struct event_key *key);
+	bool (*is_end_event)(struct perf_evsel *evsel,
+			     struct perf_sample *sample, struct event_key *key);
+	void (*decode_key)(struct perf_kvm_stat *kvm, struct event_key *key,
+			   char decode[20]);
+	const char *name;
+};
+
+struct exit_reasons_table {
+	unsigned long exit_code;
+	const char *reason;
+};
+
+#define EVENTS_BITS		12
+#define EVENTS_CACHE_SIZE	(1UL << EVENTS_BITS)
+
+struct perf_kvm_stat {
+	struct perf_tool    tool;
+	struct record_opts  opts;
+	struct perf_evlist  *evlist;
+	struct perf_session *session;
+
+	const char *file_name;
+	const char *report_event;
+	const char *sort_key;
+	int trace_vcpu;
+
+	struct exit_reasons_table *exit_reasons;
+	int exit_reasons_size;
+	const char *exit_reasons_isa;
+
+	struct kvm_events_ops *events_ops;
+	key_cmp_fun compare;
+	struct list_head kvm_events_cache[EVENTS_CACHE_SIZE];
+
+	u64 total_time;
+	u64 total_count;
+	u64 lost_events;
+	u64 duration;
+
+	const char *pid_str;
+	struct intlist *pid_list;
+
+	struct rb_root result;
+
+	int timerfd;
+	unsigned int display_time;
+	bool live;
+};
+
+
+static void exit_event_get_key(struct perf_evsel *evsel,
+			       struct perf_sample *sample,
+			       struct event_key *key)
+{
+	key->info = 0;
+	key->key = perf_evsel__intval(evsel, sample, "exit_reason");
+}
+
+static bool kvm_exit_event(struct perf_evsel *evsel)
+{
+	return !strcmp(evsel->name, "kvm:kvm_exit");
+}
+
+static bool exit_event_begin(struct perf_evsel *evsel,
+			     struct perf_sample *sample, struct event_key *key)
+{
+	if (kvm_exit_event(evsel)) {
+		exit_event_get_key(evsel, sample, key);
+		return true;
+	}
+
+	return false;
+}
+
+static bool kvm_entry_event(struct perf_evsel *evsel)
+{
+	return !strcmp(evsel->name, "kvm:kvm_entry");
+}
+
+static bool exit_event_end(struct perf_evsel *evsel,
+			   struct perf_sample *sample __maybe_unused,
+			   struct event_key *key __maybe_unused)
+{
+	return kvm_entry_event(evsel);
+}
+
+static struct exit_reasons_table vmx_exit_reasons[] = {
+	VMX_EXIT_REASONS
+};
+
+static struct exit_reasons_table svm_exit_reasons[] = {
+	SVM_EXIT_REASONS
+};
+
+static const char *get_exit_reason(struct perf_kvm_stat *kvm, u64 exit_code)
+{
+	int i = kvm->exit_reasons_size;
+	struct exit_reasons_table *tbl = kvm->exit_reasons;
+
+	while (i--) {
+		if (tbl->exit_code == exit_code)
+			return tbl->reason;
+		tbl++;
+	}
+
+	pr_err("unknown kvm exit code:%lld on %s\n",
+		(unsigned long long)exit_code, kvm->exit_reasons_isa);
+	return "UNKNOWN";
+}
+
+static void exit_event_decode_key(struct perf_kvm_stat *kvm,
+				  struct event_key *key,
+				  char decode[20])
+{
+	const char *exit_reason = get_exit_reason(kvm, key->key);
+
+	scnprintf(decode, 20, "%s", exit_reason);
+}
+
+static struct kvm_events_ops exit_events = {
+	.is_begin_event = exit_event_begin,
+	.is_end_event = exit_event_end,
+	.decode_key = exit_event_decode_key,
+	.name = "VM-EXIT"
+};
+
+/*
+ * For the mmio events, we treat:
+ * the time of MMIO write: kvm_mmio(KVM_TRACE_MMIO_WRITE...) -> kvm_entry
+ * the time of MMIO read: kvm_exit -> kvm_mmio(KVM_TRACE_MMIO_READ...).
+ */
+static void mmio_event_get_key(struct perf_evsel *evsel, struct perf_sample *sample,
+			       struct event_key *key)
+{
+	key->key  = perf_evsel__intval(evsel, sample, "gpa");
+	key->info = perf_evsel__intval(evsel, sample, "type");
+}
+
+#define KVM_TRACE_MMIO_READ_UNSATISFIED 0
+#define KVM_TRACE_MMIO_READ 1
+#define KVM_TRACE_MMIO_WRITE 2
+
+static bool mmio_event_begin(struct perf_evsel *evsel,
+			     struct perf_sample *sample, struct event_key *key)
+{
+	/* MMIO read begin event in kernel. */
+	if (kvm_exit_event(evsel))
+		return true;
+
+	/* MMIO write begin event in kernel. */
+	if (!strcmp(evsel->name, "kvm:kvm_mmio") &&
+	    perf_evsel__intval(evsel, sample, "type") == KVM_TRACE_MMIO_WRITE) {
+		mmio_event_get_key(evsel, sample, key);
+		return true;
+	}
+
+	return false;
+}
+
+static bool mmio_event_end(struct perf_evsel *evsel, struct perf_sample *sample,
+			   struct event_key *key)
+{
+	/* MMIO write end event in kernel. */
+	if (kvm_entry_event(evsel))
+		return true;
+
+	/* MMIO read end event in kernel.*/
+	if (!strcmp(evsel->name, "kvm:kvm_mmio") &&
+	    perf_evsel__intval(evsel, sample, "type") == KVM_TRACE_MMIO_READ) {
+		mmio_event_get_key(evsel, sample, key);
+		return true;
+	}
+
+	return false;
+}
+
+static void mmio_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused,
+				  struct event_key *key,
+				  char decode[20])
+{
+	scnprintf(decode, 20, "%#lx:%s", (unsigned long)key->key,
+				key->info == KVM_TRACE_MMIO_WRITE ? "W" : "R");
+}
+
+static struct kvm_events_ops mmio_events = {
+	.is_begin_event = mmio_event_begin,
+	.is_end_event = mmio_event_end,
+	.decode_key = mmio_event_decode_key,
+	.name = "MMIO Access"
+};
+
+ /* The time of emulation pio access is from kvm_pio to kvm_entry. */
+static void ioport_event_get_key(struct perf_evsel *evsel,
+				 struct perf_sample *sample,
+				 struct event_key *key)
+{
+	key->key  = perf_evsel__intval(evsel, sample, "port");
+	key->info = perf_evsel__intval(evsel, sample, "rw");
+}
+
+static bool ioport_event_begin(struct perf_evsel *evsel,
+			       struct perf_sample *sample,
+			       struct event_key *key)
+{
+	if (!strcmp(evsel->name, "kvm:kvm_pio")) {
+		ioport_event_get_key(evsel, sample, key);
+		return true;
+	}
+
+	return false;
+}
+
+static bool ioport_event_end(struct perf_evsel *evsel,
+			     struct perf_sample *sample __maybe_unused,
+			     struct event_key *key __maybe_unused)
+{
+	return kvm_entry_event(evsel);
+}
+
+static void ioport_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused,
+				    struct event_key *key,
+				    char decode[20])
+{
+	scnprintf(decode, 20, "%#llx:%s", (unsigned long long)key->key,
+				key->info ? "POUT" : "PIN");
+}
+
+static struct kvm_events_ops ioport_events = {
+	.is_begin_event = ioport_event_begin,
+	.is_end_event = ioport_event_end,
+	.decode_key = ioport_event_decode_key,
+	.name = "IO Port Access"
+};
+
+static bool register_kvm_events_ops(struct perf_kvm_stat *kvm)
+{
+	bool ret = true;
+
+	if (!strcmp(kvm->report_event, "vmexit"))
+		kvm->events_ops = &exit_events;
+	else if (!strcmp(kvm->report_event, "mmio"))
+		kvm->events_ops = &mmio_events;
+	else if (!strcmp(kvm->report_event, "ioport"))
+		kvm->events_ops = &ioport_events;
+	else {
+		pr_err("Unknown report event:%s\n", kvm->report_event);
+		ret = false;
+	}
 
-bool				perf_host = 1;
-bool				perf_guest;
+	return ret;
+}
 
-static const char * const kvm_usage[] = {
-	"perf kvm [<options>] {top|record|report|diff|buildid-list}",
-	NULL
+struct vcpu_event_record {
+	int vcpu_id;
+	u64 start_time;
+	struct kvm_event *last_event;
 };
 
-static const struct option kvm_options[] = {
-	OPT_STRING('i', "input", &file_name, "file",
-		   "Input file name"),
-	OPT_STRING('o', "output", &file_name, "file",
-		   "Output file name"),
-	OPT_BOOLEAN(0, "guest", &perf_guest,
-		    "Collect guest os data"),
-	OPT_BOOLEAN(0, "host", &perf_host,
-		    "Collect guest os data"),
-	OPT_STRING(0, "guestmount", &symbol_conf.guestmount, "directory",
-		   "guest mount directory under which every guest os"
-		   " instance has a subdir"),
-	OPT_STRING(0, "guestvmlinux", &symbol_conf.default_guest_vmlinux_name,
-		   "file", "file saving guest os vmlinux"),
-	OPT_STRING(0, "guestkallsyms", &symbol_conf.default_guest_kallsyms,
-		   "file", "file saving guest os /proc/kallsyms"),
-	OPT_STRING(0, "guestmodules", &symbol_conf.default_guest_modules,
-		   "file", "file saving guest os /proc/modules"),
-	OPT_END()
+
+static void init_kvm_event_record(struct perf_kvm_stat *kvm)
+{
+	unsigned int i;
+
+	for (i = 0; i < EVENTS_CACHE_SIZE; i++)
+		INIT_LIST_HEAD(&kvm->kvm_events_cache[i]);
+}
+
+#ifdef HAVE_TIMERFD_SUPPORT
+static void clear_events_cache_stats(struct list_head *kvm_events_cache)
+{
+	struct list_head *head;
+	struct kvm_event *event;
+	unsigned int i;
+	int j;
+
+	for (i = 0; i < EVENTS_CACHE_SIZE; i++) {
+		head = &kvm_events_cache[i];
+		list_for_each_entry(event, head, hash_entry) {
+			/* reset stats for event */
+			event->total.time = 0;
+			init_stats(&event->total.stats);
+
+			for (j = 0; j < event->max_vcpu; ++j) {
+				event->vcpu[j].time = 0;
+				init_stats(&event->vcpu[j].stats);
+			}
+		}
+	}
+}
+#endif
+
+static int kvm_events_hash_fn(u64 key)
+{
+	return key & (EVENTS_CACHE_SIZE - 1);
+}
+
+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;
+
+	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;
+	}
+
+	memset(event->vcpu + old_max_vcpu, 0,
+	       (event->max_vcpu - old_max_vcpu) * sizeof(*event->vcpu));
+	return true;
+}
+
+static struct kvm_event *kvm_alloc_init_event(struct event_key *key)
+{
+	struct kvm_event *event;
+
+	event = zalloc(sizeof(*event));
+	if (!event) {
+		pr_err("Not enough memory\n");
+		return NULL;
+	}
+
+	event->key = *key;
+	init_stats(&event->total.stats);
+	return event;
+}
+
+static struct kvm_event *find_create_kvm_event(struct perf_kvm_stat *kvm,
+					       struct event_key *key)
+{
+	struct kvm_event *event;
+	struct list_head *head;
+
+	BUG_ON(key->key == INVALID_KEY);
+
+	head = &kvm->kvm_events_cache[kvm_events_hash_fn(key->key)];
+	list_for_each_entry(event, head, hash_entry) {
+		if (event->key.key == key->key && event->key.info == key->info)
+			return event;
+	}
+
+	event = kvm_alloc_init_event(key);
+	if (!event)
+		return NULL;
+
+	list_add(&event->hash_entry, head);
+	return event;
+}
+
+static bool handle_begin_event(struct perf_kvm_stat *kvm,
+			       struct vcpu_event_record *vcpu_record,
+			       struct event_key *key, u64 timestamp)
+{
+	struct kvm_event *event = NULL;
+
+	if (key->key != INVALID_KEY)
+		event = find_create_kvm_event(kvm, key);
+
+	vcpu_record->last_event = event;
+	vcpu_record->start_time = timestamp;
+	return true;
+}
+
+static void
+kvm_update_event_stats(struct kvm_event_stats *kvm_stats, u64 time_diff)
+{
+	kvm_stats->time += time_diff;
+	update_stats(&kvm_stats->stats, time_diff);
+}
+
+static double kvm_event_rel_stddev(int vcpu_id, struct kvm_event *event)
+{
+	struct kvm_event_stats *kvm_stats = &event->total;
+
+	if (vcpu_id != -1)
+		kvm_stats = &event->vcpu[vcpu_id];
+
+	return rel_stddev_stats(stddev_stats(&kvm_stats->stats),
+				avg_stats(&kvm_stats->stats));
+}
+
+static bool update_kvm_event(struct kvm_event *event, int vcpu_id,
+			     u64 time_diff)
+{
+	if (vcpu_id == -1) {
+		kvm_update_event_stats(&event->total, time_diff);
+		return true;
+	}
+
+	if (!kvm_event_expand(event, vcpu_id))
+		return false;
+
+	kvm_update_event_stats(&event->vcpu[vcpu_id], time_diff);
+	return true;
+}
+
+static bool handle_end_event(struct perf_kvm_stat *kvm,
+			     struct vcpu_event_record *vcpu_record,
+			     struct event_key *key,
+			     struct perf_sample *sample)
+{
+	struct kvm_event *event;
+	u64 time_begin, time_diff;
+	int vcpu;
+
+	if (kvm->trace_vcpu == -1)
+		vcpu = -1;
+	else
+		vcpu = vcpu_record->vcpu_id;
+
+	event = vcpu_record->last_event;
+	time_begin = vcpu_record->start_time;
+
+	/* The begin event is not caught. */
+	if (!time_begin)
+		return true;
+
+	/*
+	 * In some case, the 'begin event' only records the start timestamp,
+	 * the actual event is recognized in the 'end event' (e.g. mmio-event).
+	 */
+
+	/* Both begin and end events did not get the key. */
+	if (!event && key->key == INVALID_KEY)
+		return true;
+
+	if (!event)
+		event = find_create_kvm_event(kvm, key);
+
+	if (!event)
+		return false;
+
+	vcpu_record->last_event = NULL;
+	vcpu_record->start_time = 0;
+
+	/* seems to happen once in a while during live mode */
+	if (sample->time < time_begin) {
+		pr_debug("End time before begin time; skipping event.\n");
+		return true;
+	}
+
+	time_diff = sample->time - time_begin;
+
+	if (kvm->duration && time_diff > kvm->duration) {
+		char decode[32];
+
+		kvm->events_ops->decode_key(kvm, &event->key, decode);
+		if (strcmp(decode, "HLT")) {
+			pr_info("%" PRIu64 " VM %d, vcpu %d: %s event took %" PRIu64 "usec\n",
+				 sample->time, sample->pid, vcpu_record->vcpu_id,
+				 decode, time_diff/1000);
+		}
+	}
+
+	return update_kvm_event(event, vcpu, time_diff);
+}
+
+static
+struct vcpu_event_record *per_vcpu_record(struct thread *thread,
+					  struct perf_evsel *evsel,
+					  struct perf_sample *sample)
+{
+	/* Only kvm_entry records vcpu id. */
+	if (!thread->priv && kvm_entry_event(evsel)) {
+		struct vcpu_event_record *vcpu_record;
+
+		vcpu_record = zalloc(sizeof(*vcpu_record));
+		if (!vcpu_record) {
+			pr_err("%s: Not enough memory\n", __func__);
+			return NULL;
+		}
+
+		vcpu_record->vcpu_id = perf_evsel__intval(evsel, sample, "vcpu_id");
+		thread->priv = vcpu_record;
+	}
+
+	return thread->priv;
+}
+
+static bool handle_kvm_event(struct perf_kvm_stat *kvm,
+			     struct thread *thread,
+			     struct perf_evsel *evsel,
+			     struct perf_sample *sample)
+{
+	struct vcpu_event_record *vcpu_record;
+	struct event_key key = {.key = INVALID_KEY};
+
+	vcpu_record = per_vcpu_record(thread, evsel, sample);
+	if (!vcpu_record)
+		return true;
+
+	/* only process events for vcpus user cares about */
+	if ((kvm->trace_vcpu != -1) &&
+	    (kvm->trace_vcpu != vcpu_record->vcpu_id))
+		return true;
+
+	if (kvm->events_ops->is_begin_event(evsel, sample, &key))
+		return handle_begin_event(kvm, vcpu_record, &key, sample->time);
+
+	if (kvm->events_ops->is_end_event(evsel, sample, &key))
+		return handle_end_event(kvm, vcpu_record, &key, sample);
+
+	return true;
+}
+
+#define GET_EVENT_KEY(func, field)					\
+static u64 get_event_ ##func(struct kvm_event *event, int vcpu)		\
+{									\
+	if (vcpu == -1)							\
+		return event->total.field;				\
+									\
+	if (vcpu >= event->max_vcpu)					\
+		return 0;						\
+									\
+	return event->vcpu[vcpu].field;					\
+}
+
+#define COMPARE_EVENT_KEY(func, field)					\
+GET_EVENT_KEY(func, field)						\
+static int compare_kvm_event_ ## func(struct kvm_event *one,		\
+					struct kvm_event *two, int vcpu)\
+{									\
+	return get_event_ ##func(one, vcpu) >				\
+				get_event_ ##func(two, vcpu);		\
+}
+
+GET_EVENT_KEY(time, time);
+COMPARE_EVENT_KEY(count, stats.n);
+COMPARE_EVENT_KEY(mean, stats.mean);
+GET_EVENT_KEY(max, stats.max);
+GET_EVENT_KEY(min, stats.min);
+
+#define DEF_SORT_NAME_KEY(name, compare_key)				\
+	{ #name, compare_kvm_event_ ## compare_key }
+
+static struct kvm_event_key keys[] = {
+	DEF_SORT_NAME_KEY(sample, count),
+	DEF_SORT_NAME_KEY(time, mean),
+	{ NULL, NULL }
 };
 
-static int __cmd_record(int argc, const char **argv)
+static bool select_key(struct perf_kvm_stat *kvm)
+{
+	int i;
+
+	for (i = 0; keys[i].name; i++) {
+		if (!strcmp(keys[i].name, kvm->sort_key)) {
+			kvm->compare = keys[i].key;
+			return true;
+		}
+	}
+
+	pr_err("Unknown compare key:%s\n", kvm->sort_key);
+	return false;
+}
+
+static void insert_to_result(struct rb_root *result, struct kvm_event *event,
+			     key_cmp_fun bigger, int vcpu)
+{
+	struct rb_node **rb = &result->rb_node;
+	struct rb_node *parent = NULL;
+	struct kvm_event *p;
+
+	while (*rb) {
+		p = container_of(*rb, struct kvm_event, rb);
+		parent = *rb;
+
+		if (bigger(event, p, vcpu))
+			rb = &(*rb)->rb_left;
+		else
+			rb = &(*rb)->rb_right;
+	}
+
+	rb_link_node(&event->rb, parent, rb);
+	rb_insert_color(&event->rb, result);
+}
+
+static void
+update_total_count(struct perf_kvm_stat *kvm, struct kvm_event *event)
+{
+	int vcpu = kvm->trace_vcpu;
+
+	kvm->total_count += get_event_count(event, vcpu);
+	kvm->total_time += get_event_time(event, vcpu);
+}
+
+static bool event_is_valid(struct kvm_event *event, int vcpu)
+{
+	return !!get_event_count(event, vcpu);
+}
+
+static void sort_result(struct perf_kvm_stat *kvm)
+{
+	unsigned int i;
+	int vcpu = kvm->trace_vcpu;
+	struct kvm_event *event;
+
+	for (i = 0; i < EVENTS_CACHE_SIZE; i++) {
+		list_for_each_entry(event, &kvm->kvm_events_cache[i], hash_entry) {
+			if (event_is_valid(event, vcpu)) {
+				update_total_count(kvm, event);
+				insert_to_result(&kvm->result, event,
+						 kvm->compare, vcpu);
+			}
+		}
+	}
+}
+
+/* returns left most element of result, and erase it */
+static struct kvm_event *pop_from_result(struct rb_root *result)
+{
+	struct rb_node *node = rb_first(result);
+
+	if (!node)
+		return NULL;
+
+	rb_erase(node, result);
+	return container_of(node, struct kvm_event, rb);
+}
+
+static void print_vcpu_info(struct perf_kvm_stat *kvm)
+{
+	int vcpu = kvm->trace_vcpu;
+
+	pr_info("Analyze events for ");
+
+	if (kvm->live) {
+		if (kvm->opts.target.system_wide)
+			pr_info("all VMs, ");
+		else if (kvm->opts.target.pid)
+			pr_info("pid(s) %s, ", kvm->opts.target.pid);
+		else
+			pr_info("dazed and confused on what is monitored, ");
+	}
+
+	if (vcpu == -1)
+		pr_info("all VCPUs:\n\n");
+	else
+		pr_info("VCPU %d:\n\n", vcpu);
+}
+
+static void show_timeofday(void)
+{
+	char date[64];
+	struct timeval tv;
+	struct tm ltime;
+
+	gettimeofday(&tv, NULL);
+	if (localtime_r(&tv.tv_sec, &ltime)) {
+		strftime(date, sizeof(date), "%H:%M:%S", &ltime);
+		pr_info("%s.%06ld", date, tv.tv_usec);
+	} else
+		pr_info("00:00:00.000000");
+
+	return;
+}
+
+static void print_result(struct perf_kvm_stat *kvm)
+{
+	char decode[20];
+	struct kvm_event *event;
+	int vcpu = kvm->trace_vcpu;
+
+	if (kvm->live) {
+		puts(CONSOLE_CLEAR);
+		show_timeofday();
+	}
+
+	pr_info("\n\n");
+	print_vcpu_info(kvm);
+	pr_info("%20s ", kvm->events_ops->name);
+	pr_info("%10s ", "Samples");
+	pr_info("%9s ", "Samples%");
+
+	pr_info("%9s ", "Time%");
+	pr_info("%10s ", "Min Time");
+	pr_info("%10s ", "Max Time");
+	pr_info("%16s ", "Avg time");
+	pr_info("\n\n");
+
+	while ((event = pop_from_result(&kvm->result))) {
+		u64 ecount, etime, max, min;
+
+		ecount = get_event_count(event, vcpu);
+		etime = get_event_time(event, vcpu);
+		max = get_event_max(event, vcpu);
+		min = get_event_min(event, vcpu);
+
+		kvm->events_ops->decode_key(kvm, &event->key, decode);
+		pr_info("%20s ", decode);
+		pr_info("%10llu ", (unsigned long long)ecount);
+		pr_info("%8.2f%% ", (double)ecount / kvm->total_count * 100);
+		pr_info("%8.2f%% ", (double)etime / kvm->total_time * 100);
+		pr_info("%8" PRIu64 "us ", min / 1000);
+		pr_info("%8" PRIu64 "us ", max / 1000);
+		pr_info("%9.2fus ( +-%7.2f%% )", (double)etime / ecount/1e3,
+			kvm_event_rel_stddev(vcpu, event));
+		pr_info("\n");
+	}
+
+	pr_info("\nTotal Samples:%" PRIu64 ", Total events handled time:%.2fus.\n\n",
+		kvm->total_count, kvm->total_time / 1e3);
+
+	if (kvm->lost_events)
+		pr_info("\nLost events: %" PRIu64 "\n\n", kvm->lost_events);
+}
+
+#ifdef HAVE_TIMERFD_SUPPORT
+static int process_lost_event(struct perf_tool *tool,
+			      union perf_event *event __maybe_unused,
+			      struct perf_sample *sample __maybe_unused,
+			      struct machine *machine __maybe_unused)
+{
+	struct perf_kvm_stat *kvm = container_of(tool, struct perf_kvm_stat, tool);
+
+	kvm->lost_events++;
+	return 0;
+}
+#endif
+
+static bool skip_sample(struct perf_kvm_stat *kvm,
+			struct perf_sample *sample)
+{
+	if (kvm->pid_list && intlist__find(kvm->pid_list, sample->pid) == NULL)
+		return true;
+
+	return false;
+}
+
+static int process_sample_event(struct perf_tool *tool,
+				union perf_event *event,
+				struct perf_sample *sample,
+				struct perf_evsel *evsel,
+				struct machine *machine)
+{
+	struct thread *thread;
+	struct perf_kvm_stat *kvm = container_of(tool, struct perf_kvm_stat,
+						 tool);
+
+	if (skip_sample(kvm, sample))
+		return 0;
+
+	thread = machine__findnew_thread(machine, sample->pid, sample->tid);
+	if (thread == NULL) {
+		pr_debug("problem processing %d event, skipping it.\n",
+			event->header.type);
+		return -1;
+	}
+
+	if (!handle_kvm_event(kvm, thread, evsel, sample))
+		return -1;
+
+	return 0;
+}
+
+static int cpu_isa_config(struct perf_kvm_stat *kvm)
+{
+	char buf[64], *cpuid;
+	int err, isa;
+
+	if (kvm->live) {
+		err = get_cpuid(buf, sizeof(buf));
+		if (err != 0) {
+			pr_err("Failed to look up CPU type (Intel or AMD)\n");
+			return err;
+		}
+		cpuid = buf;
+	} else
+		cpuid = kvm->session->header.env.cpuid;
+
+	if (strstr(cpuid, "Intel"))
+		isa = 1;
+	else if (strstr(cpuid, "AMD"))
+		isa = 0;
+	else {
+		pr_err("CPU %s is not supported.\n", cpuid);
+		return -ENOTSUP;
+	}
+
+	if (isa == 1) {
+		kvm->exit_reasons = vmx_exit_reasons;
+		kvm->exit_reasons_size = ARRAY_SIZE(vmx_exit_reasons);
+		kvm->exit_reasons_isa = "VMX";
+	}
+
+	return 0;
+}
+
+static bool verify_vcpu(int vcpu)
+{
+	if (vcpu != -1 && vcpu < 0) {
+		pr_err("Invalid vcpu:%d.\n", vcpu);
+		return false;
+	}
+
+	return true;
+}
+
+#ifdef HAVE_TIMERFD_SUPPORT
+/* keeping the max events to a modest level to keep
+ * the processing of samples per mmap smooth.
+ */
+#define PERF_KVM__MAX_EVENTS_PER_MMAP  25
+
+static s64 perf_kvm__mmap_read_idx(struct perf_kvm_stat *kvm, int idx,
+				   u64 *mmap_time)
+{
+	union perf_event *event;
+	struct perf_sample sample;
+	s64 n = 0;
+	int err;
+
+	*mmap_time = ULLONG_MAX;
+	while ((event = perf_evlist__mmap_read(kvm->evlist, idx)) != NULL) {
+		err = perf_evlist__parse_sample(kvm->evlist, event, &sample);
+		if (err) {
+			perf_evlist__mmap_consume(kvm->evlist, idx);
+			pr_err("Failed to parse sample\n");
+			return -1;
+		}
+
+		err = perf_session_queue_event(kvm->session, event, &sample, 0);
+		/*
+		 * FIXME: Here we can't consume the event, as perf_session_queue_event will
+		 *        point to it, and it'll get possibly overwritten by the kernel.
+		 */
+		perf_evlist__mmap_consume(kvm->evlist, idx);
+
+		if (err) {
+			pr_err("Failed to enqueue sample: %d\n", err);
+			return -1;
+		}
+
+		/* save time stamp of our first sample for this mmap */
+		if (n == 0)
+			*mmap_time = sample.time;
+
+		/* limit events per mmap handled all at once */
+		n++;
+		if (n == PERF_KVM__MAX_EVENTS_PER_MMAP)
+			break;
+	}
+
+	return n;
+}
+
+static int perf_kvm__mmap_read(struct perf_kvm_stat *kvm)
+{
+	int i, err, throttled = 0;
+	s64 n, ntotal = 0;
+	u64 flush_time = ULLONG_MAX, mmap_time;
+
+	for (i = 0; i < kvm->evlist->nr_mmaps; i++) {
+		n = perf_kvm__mmap_read_idx(kvm, i, &mmap_time);
+		if (n < 0)
+			return -1;
+
+		/* flush time is going to be the minimum of all the individual
+		 * mmap times. Essentially, we flush all the samples queued up
+		 * from the last pass under our minimal start time -- that leaves
+		 * a very small race for samples to come in with a lower timestamp.
+		 * The ioctl to return the perf_clock timestamp should close the
+		 * race entirely.
+		 */
+		if (mmap_time < flush_time)
+			flush_time = mmap_time;
+
+		ntotal += n;
+		if (n == PERF_KVM__MAX_EVENTS_PER_MMAP)
+			throttled = 1;
+	}
+
+	/* flush queue after each round in which we processed events */
+	if (ntotal) {
+		kvm->session->ordered_samples.next_flush = flush_time;
+		err = kvm->tool.finished_round(&kvm->tool, NULL, kvm->session);
+		if (err) {
+			if (kvm->lost_events)
+				pr_info("\nLost events: %" PRIu64 "\n\n",
+					kvm->lost_events);
+			return err;
+		}
+	}
+
+	return throttled;
+}
+
+static volatile int done;
+
+static void sig_handler(int sig __maybe_unused)
+{
+	done = 1;
+}
+
+static int perf_kvm__timerfd_create(struct perf_kvm_stat *kvm)
+{
+	struct itimerspec new_value;
+	int rc = -1;
+
+	kvm->timerfd = timerfd_create(CLOCK_MONOTONIC, TFD_NONBLOCK);
+	if (kvm->timerfd < 0) {
+		pr_err("timerfd_create failed\n");
+		goto out;
+	}
+
+	new_value.it_value.tv_sec = kvm->display_time;
+	new_value.it_value.tv_nsec = 0;
+	new_value.it_interval.tv_sec = kvm->display_time;
+	new_value.it_interval.tv_nsec = 0;
+
+	if (timerfd_settime(kvm->timerfd, 0, &new_value, NULL) != 0) {
+		pr_err("timerfd_settime failed: %d\n", errno);
+		close(kvm->timerfd);
+		goto out;
+	}
+
+	rc = 0;
+out:
+	return rc;
+}
+
+static int perf_kvm__handle_timerfd(struct perf_kvm_stat *kvm)
+{
+	uint64_t c;
+	int rc;
+
+	rc = read(kvm->timerfd, &c, sizeof(uint64_t));
+	if (rc < 0) {
+		if (errno == EAGAIN)
+			return 0;
+
+		pr_err("Failed to read timer fd: %d\n", errno);
+		return -1;
+	}
+
+	if (rc != sizeof(uint64_t)) {
+		pr_err("Error reading timer fd - invalid size returned\n");
+		return -1;
+	}
+
+	if (c != 1)
+		pr_debug("Missed timer beats: %" PRIu64 "\n", c-1);
+
+	/* update display */
+	sort_result(kvm);
+	print_result(kvm);
+
+	/* reset counts */
+	clear_events_cache_stats(kvm->kvm_events_cache);
+	kvm->total_count = 0;
+	kvm->total_time = 0;
+	kvm->lost_events = 0;
+
+	return 0;
+}
+
+static int fd_set_nonblock(int fd)
+{
+	long arg = 0;
+
+	arg = fcntl(fd, F_GETFL);
+	if (arg < 0) {
+		pr_err("Failed to get current flags for fd %d\n", fd);
+		return -1;
+	}
+
+	if (fcntl(fd, F_SETFL, arg | O_NONBLOCK) < 0) {
+		pr_err("Failed to set non-block option on fd %d\n", fd);
+		return -1;
+	}
+
+	return 0;
+}
+
+static
+int perf_kvm__handle_stdin(struct termios *tc_now, struct termios *tc_save)
+{
+	int c;
+
+	tcsetattr(0, TCSANOW, tc_now);
+	c = getc(stdin);
+	tcsetattr(0, TCSAFLUSH, tc_save);
+
+	if (c == 'q')
+		return 1;
+
+	return 0;
+}
+
+static int kvm_events_live_report(struct perf_kvm_stat *kvm)
+{
+	struct pollfd *pollfds = NULL;
+	int nr_fds, nr_stdin, ret, err = -EINVAL;
+	struct termios tc, save;
+
+	/* live flag must be set first */
+	kvm->live = true;
+
+	ret = cpu_isa_config(kvm);
+	if (ret < 0)
+		return ret;
+
+	if (!verify_vcpu(kvm->trace_vcpu) ||
+	    !select_key(kvm) ||
+	    !register_kvm_events_ops(kvm)) {
+		goto out;
+	}
+
+	init_kvm_event_record(kvm);
+
+	tcgetattr(0, &save);
+	tc = save;
+	tc.c_lflag &= ~(ICANON | ECHO);
+	tc.c_cc[VMIN] = 0;
+	tc.c_cc[VTIME] = 0;
+
+	signal(SIGINT, sig_handler);
+	signal(SIGTERM, sig_handler);
+
+	/* copy pollfds -- need to add timerfd and stdin */
+	nr_fds = kvm->evlist->nr_fds;
+	pollfds = zalloc(sizeof(struct pollfd) * (nr_fds + 2));
+	if (!pollfds) {
+		err = -ENOMEM;
+		goto out;
+	}
+	memcpy(pollfds, kvm->evlist->pollfd,
+		sizeof(struct pollfd) * kvm->evlist->nr_fds);
+
+	/* add timer fd */
+	if (perf_kvm__timerfd_create(kvm) < 0) {
+		err = -1;
+		goto out;
+	}
+
+	pollfds[nr_fds].fd = kvm->timerfd;
+	pollfds[nr_fds].events = POLLIN;
+	nr_fds++;
+
+	pollfds[nr_fds].fd = fileno(stdin);
+	pollfds[nr_fds].events = POLLIN;
+	nr_stdin = nr_fds;
+	nr_fds++;
+	if (fd_set_nonblock(fileno(stdin)) != 0)
+		goto out;
+
+	/* everything is good - enable the events and process */
+	perf_evlist__enable(kvm->evlist);
+
+	while (!done) {
+		int rc;
+
+		rc = perf_kvm__mmap_read(kvm);
+		if (rc < 0)
+			break;
+
+		err = perf_kvm__handle_timerfd(kvm);
+		if (err)
+			goto out;
+
+		if (pollfds[nr_stdin].revents & POLLIN)
+			done = perf_kvm__handle_stdin(&tc, &save);
+
+		if (!rc && !done)
+			err = poll(pollfds, nr_fds, 100);
+	}
+
+	perf_evlist__disable(kvm->evlist);
+
+	if (err == 0) {
+		sort_result(kvm);
+		print_result(kvm);
+	}
+
+out:
+	if (kvm->timerfd >= 0)
+		close(kvm->timerfd);
+
+	free(pollfds);
+	return err;
+}
+
+static int kvm_live_open_events(struct perf_kvm_stat *kvm)
+{
+	int err, rc = -1;
+	struct perf_evsel *pos;
+	struct perf_evlist *evlist = kvm->evlist;
+
+	perf_evlist__config(evlist, &kvm->opts);
+
+	/*
+	 * Note: exclude_{guest,host} do not apply here.
+	 *       This command processes KVM tracepoints from host only
+	 */
+	evlist__for_each(evlist, pos) {
+		struct perf_event_attr *attr = &pos->attr;
+
+		/* make sure these *are* set */
+		perf_evsel__set_sample_bit(pos, TID);
+		perf_evsel__set_sample_bit(pos, TIME);
+		perf_evsel__set_sample_bit(pos, CPU);
+		perf_evsel__set_sample_bit(pos, RAW);
+		/* make sure these are *not*; want as small a sample as possible */
+		perf_evsel__reset_sample_bit(pos, PERIOD);
+		perf_evsel__reset_sample_bit(pos, IP);
+		perf_evsel__reset_sample_bit(pos, CALLCHAIN);
+		perf_evsel__reset_sample_bit(pos, ADDR);
+		perf_evsel__reset_sample_bit(pos, READ);
+		attr->mmap = 0;
+		attr->comm = 0;
+		attr->task = 0;
+
+		attr->sample_period = 1;
+
+		attr->watermark = 0;
+		attr->wakeup_events = 1000;
+
+		/* will enable all once we are ready */
+		attr->disabled = 1;
+	}
+
+	err = perf_evlist__open(evlist);
+	if (err < 0) {
+		printf("Couldn't create the events: %s\n", strerror(errno));
+		goto out;
+	}
+
+	if (perf_evlist__mmap(evlist, kvm->opts.mmap_pages, false) < 0) {
+		ui__error("Failed to mmap the events: %s\n", strerror(errno));
+		perf_evlist__close(evlist);
+		goto out;
+	}
+
+	rc = 0;
+
+out:
+	return rc;
+}
+#endif
+
+static int read_events(struct perf_kvm_stat *kvm)
+{
+	int ret;
+
+	struct perf_tool eops = {
+		.sample			= process_sample_event,
+		.comm			= perf_event__process_comm,
+		.ordered_samples	= true,
+	};
+	struct perf_data_file file = {
+		.path = kvm->file_name,
+		.mode = PERF_DATA_MODE_READ,
+	};
+
+	kvm->tool = eops;
+	kvm->session = perf_session__new(&file, false, &kvm->tool);
+	if (!kvm->session) {
+		pr_err("Initializing perf session failed\n");
+		return -EINVAL;
+	}
+
+	if (!perf_session__has_traces(kvm->session, "kvm record"))
+		return -EINVAL;
+
+	/*
+	 * Do not use 'isa' recorded in kvm_exit tracepoint since it is not
+	 * traced in the old kernel.
+	 */
+	ret = cpu_isa_config(kvm);
+	if (ret < 0)
+		return ret;
+
+	return perf_session__process_events(kvm->session, &kvm->tool);
+}
+
+static int parse_target_str(struct perf_kvm_stat *kvm)
+{
+	if (kvm->pid_str) {
+		kvm->pid_list = intlist__new(kvm->pid_str);
+		if (kvm->pid_list == NULL) {
+			pr_err("Error parsing process id string\n");
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static int kvm_events_report_vcpu(struct perf_kvm_stat *kvm)
+{
+	int ret = -EINVAL;
+	int vcpu = kvm->trace_vcpu;
+
+	if (parse_target_str(kvm) != 0)
+		goto exit;
+
+	if (!verify_vcpu(vcpu))
+		goto exit;
+
+	if (!select_key(kvm))
+		goto exit;
+
+	if (!register_kvm_events_ops(kvm))
+		goto exit;
+
+	init_kvm_event_record(kvm);
+	setup_pager();
+
+	ret = read_events(kvm);
+	if (ret)
+		goto exit;
+
+	sort_result(kvm);
+	print_result(kvm);
+
+exit:
+	return ret;
+}
+
+static const char * const kvm_events_tp[] = {
+	"kvm:kvm_entry",
+	"kvm:kvm_exit",
+	"kvm:kvm_mmio",
+	"kvm:kvm_pio",
+};
+
+#define STRDUP_FAIL_EXIT(s)		\
+	({	char *_p;		\
+	_p = strdup(s);		\
+		if (!_p)		\
+			return -ENOMEM;	\
+		_p;			\
+	})
+
+static int
+kvm_events_record(struct perf_kvm_stat *kvm, int argc, const char **argv)
+{
+	unsigned int rec_argc, i, j;
+	const char **rec_argv;
+	const char * const record_args[] = {
+		"record",
+		"-R",
+		"-m", "1024",
+		"-c", "1",
+	};
+
+	rec_argc = ARRAY_SIZE(record_args) + argc + 2 +
+		   2 * ARRAY_SIZE(kvm_events_tp);
+	rec_argv = calloc(rec_argc + 1, sizeof(char *));
+
+	if (rec_argv == NULL)
+		return -ENOMEM;
+
+	for (i = 0; i < ARRAY_SIZE(record_args); i++)
+		rec_argv[i] = STRDUP_FAIL_EXIT(record_args[i]);
+
+	for (j = 0; j < ARRAY_SIZE(kvm_events_tp); j++) {
+		rec_argv[i++] = "-e";
+		rec_argv[i++] = STRDUP_FAIL_EXIT(kvm_events_tp[j]);
+	}
+
+	rec_argv[i++] = STRDUP_FAIL_EXIT("-o");
+	rec_argv[i++] = STRDUP_FAIL_EXIT(kvm->file_name);
+
+	for (j = 1; j < (unsigned int)argc; j++, i++)
+		rec_argv[i] = argv[j];
+
+	return cmd_record(i, rec_argv, NULL);
+}
+
+static int
+kvm_events_report(struct perf_kvm_stat *kvm, int argc, const char **argv)
+{
+	const struct option kvm_events_report_options[] = {
+		OPT_STRING(0, "event", &kvm->report_event, "report event",
+			    "event for reporting: vmexit, mmio, ioport"),
+		OPT_INTEGER(0, "vcpu", &kvm->trace_vcpu,
+			    "vcpu id to report"),
+		OPT_STRING('k', "key", &kvm->sort_key, "sort-key",
+			    "key for sorting: sample(sort by samples number)"
+			    " time (sort by avg time)"),
+		OPT_STRING('p', "pid", &kvm->pid_str, "pid",
+			   "analyze events only for given process id(s)"),
+		OPT_END()
+	};
+
+	const char * const kvm_events_report_usage[] = {
+		"perf kvm stat report [<options>]",
+		NULL
+	};
+
+	symbol__init();
+
+	if (argc) {
+		argc = parse_options(argc, argv,
+				     kvm_events_report_options,
+				     kvm_events_report_usage, 0);
+		if (argc)
+			usage_with_options(kvm_events_report_usage,
+					   kvm_events_report_options);
+	}
+
+	return kvm_events_report_vcpu(kvm);
+}
+
+#ifdef HAVE_TIMERFD_SUPPORT
+static struct perf_evlist *kvm_live_event_list(void)
+{
+	struct perf_evlist *evlist;
+	char *tp, *name, *sys;
+	unsigned int j;
+	int err = -1;
+
+	evlist = perf_evlist__new();
+	if (evlist == NULL)
+		return NULL;
+
+	for (j = 0; j < ARRAY_SIZE(kvm_events_tp); j++) {
+
+		tp = strdup(kvm_events_tp[j]);
+		if (tp == NULL)
+			goto out;
+
+		/* split tracepoint into subsystem and name */
+		sys = tp;
+		name = strchr(tp, ':');
+		if (name == NULL) {
+			pr_err("Error parsing %s tracepoint: subsystem delimiter not found\n",
+				kvm_events_tp[j]);
+			free(tp);
+			goto out;
+		}
+		*name = '\0';
+		name++;
+
+		if (perf_evlist__add_newtp(evlist, sys, name, NULL)) {
+			pr_err("Failed to add %s tracepoint to the list\n", kvm_events_tp[j]);
+			free(tp);
+			goto out;
+		}
+
+		free(tp);
+	}
+
+	err = 0;
+
+out:
+	if (err) {
+		perf_evlist__delete(evlist);
+		evlist = NULL;
+	}
+
+	return evlist;
+}
+
+static int kvm_events_live(struct perf_kvm_stat *kvm,
+			   int argc, const char **argv)
+{
+	char errbuf[BUFSIZ];
+	int err;
+
+	const struct option live_options[] = {
+		OPT_STRING('p', "pid", &kvm->opts.target.pid, "pid",
+			"record events on existing process id"),
+		OPT_CALLBACK('m', "mmap-pages", &kvm->opts.mmap_pages, "pages",
+			"number of mmap data pages",
+			perf_evlist__parse_mmap_pages),
+		OPT_INCR('v', "verbose", &verbose,
+			"be more verbose (show counter open errors, etc)"),
+		OPT_BOOLEAN('a', "all-cpus", &kvm->opts.target.system_wide,
+			"system-wide collection from all CPUs"),
+		OPT_UINTEGER('d', "display", &kvm->display_time,
+			"time in seconds between display updates"),
+		OPT_STRING(0, "event", &kvm->report_event, "report event",
+			"event for reporting: vmexit, mmio, ioport"),
+		OPT_INTEGER(0, "vcpu", &kvm->trace_vcpu,
+			"vcpu id to report"),
+		OPT_STRING('k', "key", &kvm->sort_key, "sort-key",
+			"key for sorting: sample(sort by samples number)"
+			" time (sort by avg time)"),
+		OPT_U64(0, "duration", &kvm->duration,
+		    "show events other than HALT that take longer than duration usecs"),
+		OPT_END()
+	};
+	const char * const live_usage[] = {
+		"perf kvm stat live [<options>]",
+		NULL
+	};
+	struct perf_data_file file = {
+		.mode = PERF_DATA_MODE_WRITE,
+	};
+
+
+	/* event handling */
+	kvm->tool.sample = process_sample_event;
+	kvm->tool.comm   = perf_event__process_comm;
+	kvm->tool.exit   = perf_event__process_exit;
+	kvm->tool.fork   = perf_event__process_fork;
+	kvm->tool.lost   = process_lost_event;
+	kvm->tool.ordered_samples = true;
+	perf_tool__fill_defaults(&kvm->tool);
+
+	/* set defaults */
+	kvm->display_time = 1;
+	kvm->opts.user_interval = 1;
+	kvm->opts.mmap_pages = 512;
+	kvm->opts.target.uses_mmap = false;
+	kvm->opts.target.uid_str = NULL;
+	kvm->opts.target.uid = UINT_MAX;
+
+	symbol__init();
+	disable_buildid_cache();
+
+	use_browser = 0;
+	setup_browser(false);
+
+	if (argc) {
+		argc = parse_options(argc, argv, live_options,
+				     live_usage, 0);
+		if (argc)
+			usage_with_options(live_usage, live_options);
+	}
+
+	kvm->duration *= NSEC_PER_USEC;   /* convert usec to nsec */
+
+	/*
+	 * target related setups
+	 */
+	err = target__validate(&kvm->opts.target);
+	if (err) {
+		target__strerror(&kvm->opts.target, err, errbuf, BUFSIZ);
+		ui__warning("%s", errbuf);
+	}
+
+	if (target__none(&kvm->opts.target))
+		kvm->opts.target.system_wide = true;
+
+
+	/*
+	 * generate the event list
+	 */
+	kvm->evlist = kvm_live_event_list();
+	if (kvm->evlist == NULL) {
+		err = -1;
+		goto out;
+	}
+
+	symbol_conf.nr_events = kvm->evlist->nr_entries;
+
+	if (perf_evlist__create_maps(kvm->evlist, &kvm->opts.target) < 0)
+		usage_with_options(live_usage, live_options);
+
+	/*
+	 * perf session
+	 */
+	kvm->session = perf_session__new(&file, false, &kvm->tool);
+	if (kvm->session == NULL) {
+		err = -ENOMEM;
+		goto out;
+	}
+	kvm->session->evlist = kvm->evlist;
+	perf_session__set_id_hdr_size(kvm->session);
+	machine__synthesize_threads(&kvm->session->machines.host, &kvm->opts.target,
+				    kvm->evlist->threads, false);
+	err = kvm_live_open_events(kvm);
+	if (err)
+		goto out;
+
+	err = kvm_events_live_report(kvm);
+
+out:
+	exit_browser(0);
+
+	if (kvm->session)
+		perf_session__delete(kvm->session);
+	kvm->session = NULL;
+	if (kvm->evlist)
+		perf_evlist__delete(kvm->evlist);
+
+	return err;
+}
+#endif
+
+static void print_kvm_stat_usage(void)
+{
+	printf("Usage: perf kvm stat <command>\n\n");
+
+	printf("# Available commands:\n");
+	printf("\trecord: record kvm events\n");
+	printf("\treport: report statistical data of kvm events\n");
+	printf("\tlive:   live reporting of statistical data of kvm events\n");
+
+	printf("\nOtherwise, it is the alias of 'perf stat':\n");
+}
+
+static int kvm_cmd_stat(const char *file_name, int argc, const char **argv)
+{
+	struct perf_kvm_stat kvm = {
+		.file_name = file_name,
+
+		.trace_vcpu	= -1,
+		.report_event	= "vmexit",
+		.sort_key	= "sample",
+
+		.exit_reasons = svm_exit_reasons,
+		.exit_reasons_size = ARRAY_SIZE(svm_exit_reasons),
+		.exit_reasons_isa = "SVM",
+	};
+
+	if (argc == 1) {
+		print_kvm_stat_usage();
+		goto perf_stat;
+	}
+
+	if (!strncmp(argv[1], "rec", 3))
+		return kvm_events_record(&kvm, argc - 1, argv + 1);
+
+	if (!strncmp(argv[1], "rep", 3))
+		return kvm_events_report(&kvm, argc - 1 , argv + 1);
+
+#ifdef HAVE_TIMERFD_SUPPORT
+	if (!strncmp(argv[1], "live", 4))
+		return kvm_events_live(&kvm, argc - 1 , argv + 1);
+#endif
+
+perf_stat:
+	return cmd_stat(argc, argv, NULL);
+}
+#endif
+
+static int __cmd_record(const char *file_name, int argc, const char **argv)
 {
 	int rec_argc, i = 0, j;
 	const char **rec_argv;
@@ -69,7 +1629,7 @@ static int __cmd_record(int argc, const char **argv)
 	return cmd_record(i, rec_argv, NULL);
 }
 
-static int __cmd_report(int argc, const char **argv)
+static int __cmd_report(const char *file_name, int argc, const char **argv)
 {
 	int rec_argc, i = 0, j;
 	const char **rec_argv;
@@ -87,7 +1647,8 @@ static int __cmd_report(int argc, const char **argv)
 	return cmd_report(i, rec_argv, NULL);
 }
 
-static int __cmd_buildid_list(int argc, const char **argv)
+static int
+__cmd_buildid_list(const char *file_name, int argc, const char **argv)
 {
 	int rec_argc, i = 0, j;
 	const char **rec_argv;
@@ -105,12 +1666,41 @@ static int __cmd_buildid_list(int argc, const char **argv)
 	return cmd_buildid_list(i, rec_argv, NULL);
 }
 
-int cmd_kvm(int argc, const char **argv, const char *prefix __used)
+int cmd_kvm(int argc, const char **argv, const char *prefix __maybe_unused)
 {
-	perf_host = perf_guest = 0;
+	const char *file_name = NULL;
+	const struct option kvm_options[] = {
+		OPT_STRING('i', "input", &file_name, "file",
+			   "Input file name"),
+		OPT_STRING('o', "output", &file_name, "file",
+			   "Output file name"),
+		OPT_BOOLEAN(0, "guest", &perf_guest,
+			    "Collect guest os data"),
+		OPT_BOOLEAN(0, "host", &perf_host,
+			    "Collect host os data"),
+		OPT_STRING(0, "guestmount", &symbol_conf.guestmount, "directory",
+			   "guest mount directory under which every guest os"
+			   " instance has a subdir"),
+		OPT_STRING(0, "guestvmlinux", &symbol_conf.default_guest_vmlinux_name,
+			   "file", "file saving guest os vmlinux"),
+		OPT_STRING(0, "guestkallsyms", &symbol_conf.default_guest_kallsyms,
+			   "file", "file saving guest os /proc/kallsyms"),
+		OPT_STRING(0, "guestmodules", &symbol_conf.default_guest_modules,
+			   "file", "file saving guest os /proc/modules"),
+		OPT_INCR('v', "verbose", &verbose,
+			    "be more verbose (show counter open errors, etc)"),
+		OPT_END()
+	};
+
+	const char *const kvm_subcommands[] = { "top", "record", "report", "diff",
+						"buildid-list", "stat", NULL };
+	const char *kvm_usage[] = { NULL, NULL };
 
-	argc = parse_options(argc, argv, kvm_options, kvm_usage,
-			PARSE_OPT_STOP_AT_NON_OPTION);
+	perf_host  = 0;
+	perf_guest = 1;
+
+	argc = parse_options_subcommand(argc, argv, kvm_options, kvm_subcommands, kvm_usage,
+					PARSE_OPT_STOP_AT_NON_OPTION);
 	if (!argc)
 		usage_with_options(kvm_usage, kvm_options);
 
@@ -118,25 +1708,28 @@ int cmd_kvm(int argc, const char **argv, const char *prefix __used)
 		perf_guest = 1;
 
 	if (!file_name) {
-		if (perf_host && !perf_guest)
-			sprintf(name_buffer, "perf.data.host");
-		else if (!perf_host && perf_guest)
-			sprintf(name_buffer, "perf.data.guest");
-		else
-			sprintf(name_buffer, "perf.data.kvm");
-		file_name = name_buffer;
+		file_name = get_filename_for_perf_kvm();
+
+		if (!file_name) {
+			pr_err("Failed to allocate memory for filename\n");
+			return -ENOMEM;
+		}
 	}
 
 	if (!strncmp(argv[0], "rec", 3))
-		return __cmd_record(argc, argv);
+		return __cmd_record(file_name, argc, argv);
 	else if (!strncmp(argv[0], "rep", 3))
-		return __cmd_report(argc, argv);
+		return __cmd_report(file_name, argc, argv);
 	else if (!strncmp(argv[0], "diff", 4))
 		return cmd_diff(argc, argv, NULL);
 	else if (!strncmp(argv[0], "top", 3))
 		return cmd_top(argc, argv, NULL);
 	else if (!strncmp(argv[0], "buildid-list", 12))
-		return __cmd_buildid_list(argc, argv);
+		return __cmd_buildid_list(file_name, argc, argv);
+#if defined(__i386__) || defined(__x86_64__)
+	else if (!strncmp(argv[0], "stat", 4))
+		return kvm_cmd_stat(file_name, argc, argv);
+#endif
 	else
 		usage_with_options(kvm_usage, kvm_options);
 
diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
index d88c6961274..011195e38f2 100644
--- a/tools/perf/builtin-list.c
+++ b/tools/perf/builtin-list.c
@@ -5,6 +5,7 @@
  *
  * Copyright (C) 2009, Thomas Gleixner <tglx@linutronix.de>
  * Copyright (C) 2008-2009, Red Hat Inc, Ingo Molnar <mingo@redhat.com>
+ * Copyright (C) 2011, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
  */
 #include "builtin.h"
 
@@ -12,10 +13,65 @@
 
 #include "util/parse-events.h"
 #include "util/cache.h"
+#include "util/pmu.h"
+#include "util/parse-options.h"
 
-int cmd_list(int argc __used, const char **argv __used, const char *prefix __used)
+int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
 {
+	int i;
+	const struct option list_options[] = {
+		OPT_END()
+	};
+	const char * const list_usage[] = {
+		"perf list [hw|sw|cache|tracepoint|pmu|event_glob]",
+		NULL
+	};
+
+	argc = parse_options(argc, argv, list_options, list_usage,
+			     PARSE_OPT_STOP_AT_NON_OPTION);
+
 	setup_pager();
-	print_events();
+
+	if (argc == 0) {
+		print_events(NULL, false);
+		return 0;
+	}
+
+	for (i = 0; i < argc; ++i) {
+		if (i)
+			putchar('\n');
+		if (strncmp(argv[i], "tracepoint", 10) == 0)
+			print_tracepoint_events(NULL, NULL, false);
+		else if (strcmp(argv[i], "hw") == 0 ||
+			 strcmp(argv[i], "hardware") == 0)
+			print_events_type(PERF_TYPE_HARDWARE);
+		else if (strcmp(argv[i], "sw") == 0 ||
+			 strcmp(argv[i], "software") == 0)
+			print_events_type(PERF_TYPE_SOFTWARE);
+		else if (strcmp(argv[i], "cache") == 0 ||
+			 strcmp(argv[i], "hwcache") == 0)
+			print_hwcache_events(NULL, false);
+		else if (strcmp(argv[i], "pmu") == 0)
+			print_pmu_events(NULL, false);
+		else if (strcmp(argv[i], "--raw-dump") == 0)
+			print_events(NULL, true);
+		else {
+			char *sep = strchr(argv[i], ':'), *s;
+			int sep_idx;
+
+			if (sep == NULL) {
+				print_events(argv[i], false);
+				continue;
+			}
+			sep_idx = sep - argv[i];
+			s = strdup(argv[i]);
+			if (s == NULL)
+				return -1;
+
+			s[sep_idx] = '\0';
+			print_tracepoint_events(s, s + sep_idx + 1, false);
+			free(s);
+		}
+	}
 	return 0;
 }
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index 821c1586a22..6148afc995c 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -1,6 +1,8 @@
 #include "builtin.h"
 #include "perf.h"
 
+#include "util/evlist.h"
+#include "util/evsel.h"
 #include "util/util.h"
 #include "util/cache.h"
 #include "util/symbol.h"
@@ -12,6 +14,8 @@
 
 #include "util/debug.h"
 #include "util/session.h"
+#include "util/tool.h"
+#include "util/data.h"
 
 #include <sys/types.h>
 #include <sys/prctl.h>
@@ -39,7 +43,7 @@ struct lock_stat {
 	struct rb_node		rb;		/* used for sorting */
 
 	/*
-	 * FIXME: raw_field_value() returns unsigned long long,
+	 * FIXME: perf_evsel__intval() returns u64,
 	 * so address of lockdep_map should be dealed as 64bit.
 	 * Is there more better solution?
 	 */
@@ -53,7 +57,9 @@ struct lock_stat {
 
 	unsigned int		nr_readlock;
 	unsigned int		nr_trylock;
+
 	/* these times are in nano sec. */
+	u64                     avg_wait_time;
 	u64			wait_time_total;
 	u64			wait_time_min;
 	u64			wait_time_max;
@@ -159,8 +165,10 @@ static struct thread_stat *thread_stat_findnew_after_first(u32 tid)
 		return st;
 
 	st = zalloc(sizeof(struct thread_stat));
-	if (!st)
-		die("memory allocation failed\n");
+	if (!st) {
+		pr_err("memory allocation failed\n");
+		return NULL;
+	}
 
 	st->tid = tid;
 	INIT_LIST_HEAD(&st->seq_list);
@@ -179,8 +187,10 @@ static struct thread_stat *thread_stat_findnew_first(u32 tid)
 	struct thread_stat *st;
 
 	st = zalloc(sizeof(struct thread_stat));
-	if (!st)
-		die("memory allocation failed\n");
+	if (!st) {
+		pr_err("memory allocation failed\n");
+		return NULL;
+	}
 	st->tid = tid;
 	INIT_LIST_HEAD(&st->seq_list);
 
@@ -201,10 +211,22 @@ static struct thread_stat *thread_stat_findnew_first(u32 tid)
 
 SINGLE_KEY(nr_acquired)
 SINGLE_KEY(nr_contended)
+SINGLE_KEY(avg_wait_time)
 SINGLE_KEY(wait_time_total)
-SINGLE_KEY(wait_time_min)
 SINGLE_KEY(wait_time_max)
 
+static int lock_stat_key_wait_time_min(struct lock_stat *one,
+					struct lock_stat *two)
+{
+	u64 s1 = one->wait_time_min;
+	u64 s2 = two->wait_time_min;
+	if (s1 == ULLONG_MAX)
+		s1 = 0;
+	if (s2 == ULLONG_MAX)
+		s2 = 0;
+	return s1 > s2;
+}
+
 struct lock_key {
 	/*
 	 * name: the value for specify by user
@@ -226,6 +248,7 @@ static struct rb_root		result;	/* place to store sorted data */
 struct lock_key keys[] = {
 	DEF_KEY_LOCK(acquired, nr_acquired),
 	DEF_KEY_LOCK(contended, nr_contended),
+	DEF_KEY_LOCK(avg_wait, avg_wait_time),
 	DEF_KEY_LOCK(wait_total, wait_time_total),
 	DEF_KEY_LOCK(wait_min, wait_time_min),
 	DEF_KEY_LOCK(wait_max, wait_time_max),
@@ -235,18 +258,20 @@ struct lock_key keys[] = {
 	{ NULL, NULL }
 };
 
-static void select_key(void)
+static int select_key(void)
 {
 	int i;
 
 	for (i = 0; keys[i].name; i++) {
 		if (!strcmp(keys[i].name, sort_key)) {
 			compare = keys[i].key;
-			return;
+			return 0;
 		}
 	}
 
-	die("Unknown compare key:%s\n", sort_key);
+	pr_err("Unknown compare key: %s\n", sort_key);
+
+	return -1;
 }
 
 static void insert_to_result(struct lock_stat *st,
@@ -301,71 +326,34 @@ static struct lock_stat *lock_stat_findnew(void *addr, const char *name)
 
 	new->addr = addr;
 	new->name = zalloc(sizeof(char) * strlen(name) + 1);
-	if (!new->name)
+	if (!new->name) {
+		free(new);
 		goto alloc_failed;
-	strcpy(new->name, name);
+	}
 
+	strcpy(new->name, name);
 	new->wait_time_min = ULLONG_MAX;
 
 	list_add(&new->hash_entry, entry);
 	return new;
 
 alloc_failed:
-	die("memory allocation failed\n");
+	pr_err("memory allocation failed\n");
+	return NULL;
 }
 
-static char			const *input_name = "perf.data";
-
-struct raw_event_sample {
-	u32			size;
-	char			data[0];
-};
-
-struct trace_acquire_event {
-	void			*addr;
-	const char		*name;
-	int			flag;
-};
-
-struct trace_acquired_event {
-	void			*addr;
-	const char		*name;
-};
+struct trace_lock_handler {
+	int (*acquire_event)(struct perf_evsel *evsel,
+			     struct perf_sample *sample);
 
-struct trace_contended_event {
-	void			*addr;
-	const char		*name;
-};
+	int (*acquired_event)(struct perf_evsel *evsel,
+			      struct perf_sample *sample);
 
-struct trace_release_event {
-	void			*addr;
-	const char		*name;
-};
+	int (*contended_event)(struct perf_evsel *evsel,
+			       struct perf_sample *sample);
 
-struct trace_lock_handler {
-	void (*acquire_event)(struct trace_acquire_event *,
-			      struct event *,
-			      int cpu,
-			      u64 timestamp,
-			      struct thread *thread);
-
-	void (*acquired_event)(struct trace_acquired_event *,
-			       struct event *,
-			       int cpu,
-			       u64 timestamp,
-			       struct thread *thread);
-
-	void (*contended_event)(struct trace_contended_event *,
-				struct event *,
-				int cpu,
-				u64 timestamp,
-				struct thread *thread);
-
-	void (*release_event)(struct trace_release_event *,
-			      struct event *,
-			      int cpu,
-			      u64 timestamp,
-			      struct thread *thread);
+	int (*release_event)(struct perf_evsel *evsel,
+			     struct perf_sample *sample);
 };
 
 static struct lock_seq_stat *get_seq(struct thread_stat *ts, void *addr)
@@ -378,8 +366,10 @@ static struct lock_seq_stat *get_seq(struct thread_stat *ts, void *addr)
 	}
 
 	seq = zalloc(sizeof(struct lock_seq_stat));
-	if (!seq)
-		die("Not enough memory\n");
+	if (!seq) {
+		pr_err("memory allocation failed\n");
+		return NULL;
+	}
 	seq->state = SEQ_STATE_UNINITIALIZED;
 	seq->addr = addr;
 
@@ -402,33 +392,42 @@ enum acquire_flags {
 	READ_LOCK = 2,
 };
 
-static void
-report_lock_acquire_event(struct trace_acquire_event *acquire_event,
-			struct event *__event __used,
-			int cpu __used,
-			u64 timestamp __used,
-			struct thread *thread __used)
+static int report_lock_acquire_event(struct perf_evsel *evsel,
+				     struct perf_sample *sample)
 {
+	void *addr;
 	struct lock_stat *ls;
 	struct thread_stat *ts;
 	struct lock_seq_stat *seq;
+	const char *name = perf_evsel__strval(evsel, sample, "name");
+	u64 tmp = perf_evsel__intval(evsel, sample, "lockdep_addr");
+	int flag = perf_evsel__intval(evsel, sample, "flag");
 
-	ls = lock_stat_findnew(acquire_event->addr, acquire_event->name);
+	memcpy(&addr, &tmp, sizeof(void *));
+
+	ls = lock_stat_findnew(addr, name);
+	if (!ls)
+		return -ENOMEM;
 	if (ls->discard)
-		return;
+		return 0;
+
+	ts = thread_stat_findnew(sample->tid);
+	if (!ts)
+		return -ENOMEM;
 
-	ts = thread_stat_findnew(thread->pid);
-	seq = get_seq(ts, acquire_event->addr);
+	seq = get_seq(ts, addr);
+	if (!seq)
+		return -ENOMEM;
 
 	switch (seq->state) {
 	case SEQ_STATE_UNINITIALIZED:
 	case SEQ_STATE_RELEASED:
-		if (!acquire_event->flag) {
+		if (!flag) {
 			seq->state = SEQ_STATE_ACQUIRING;
 		} else {
-			if (acquire_event->flag & TRY_LOCK)
+			if (flag & TRY_LOCK)
 				ls->nr_trylock++;
-			if (acquire_event->flag & READ_LOCK)
+			if (flag & READ_LOCK)
 				ls->nr_readlock++;
 			seq->state = SEQ_STATE_READ_ACQUIRED;
 			seq->read_count = 1;
@@ -436,7 +435,7 @@ report_lock_acquire_event(struct trace_acquire_event *acquire_event,
 		}
 		break;
 	case SEQ_STATE_READ_ACQUIRED:
-		if (acquire_event->flag & READ_LOCK) {
+		if (flag & READ_LOCK) {
 			seq->read_count++;
 			ls->nr_acquired++;
 			goto end;
@@ -454,45 +453,52 @@ broken:
 		list_del(&seq->list);
 		free(seq);
 		goto end;
-		break;
 	default:
 		BUG_ON("Unknown state of lock sequence found!\n");
 		break;
 	}
 
 	ls->nr_acquire++;
-	seq->prev_event_time = timestamp;
+	seq->prev_event_time = sample->time;
 end:
-	return;
+	return 0;
 }
 
-static void
-report_lock_acquired_event(struct trace_acquired_event *acquired_event,
-			 struct event *__event __used,
-			 int cpu __used,
-			 u64 timestamp __used,
-			 struct thread *thread __used)
+static int report_lock_acquired_event(struct perf_evsel *evsel,
+				      struct perf_sample *sample)
 {
+	void *addr;
 	struct lock_stat *ls;
 	struct thread_stat *ts;
 	struct lock_seq_stat *seq;
 	u64 contended_term;
+	const char *name = perf_evsel__strval(evsel, sample, "name");
+	u64 tmp = perf_evsel__intval(evsel, sample, "lockdep_addr");
+
+	memcpy(&addr, &tmp, sizeof(void *));
 
-	ls = lock_stat_findnew(acquired_event->addr, acquired_event->name);
+	ls = lock_stat_findnew(addr, name);
+	if (!ls)
+		return -ENOMEM;
 	if (ls->discard)
-		return;
+		return 0;
 
-	ts = thread_stat_findnew(thread->pid);
-	seq = get_seq(ts, acquired_event->addr);
+	ts = thread_stat_findnew(sample->tid);
+	if (!ts)
+		return -ENOMEM;
+
+	seq = get_seq(ts, addr);
+	if (!seq)
+		return -ENOMEM;
 
 	switch (seq->state) {
 	case SEQ_STATE_UNINITIALIZED:
 		/* orphan event, do nothing */
-		return;
+		return 0;
 	case SEQ_STATE_ACQUIRING:
 		break;
 	case SEQ_STATE_CONTENDED:
-		contended_term = timestamp - seq->prev_event_time;
+		contended_term = sample->time - seq->prev_event_time;
 		ls->wait_time_total += contended_term;
 		if (contended_term < ls->wait_time_min)
 			ls->wait_time_min = contended_term;
@@ -508,8 +514,6 @@ report_lock_acquired_event(struct trace_acquired_event *acquired_event,
 		list_del(&seq->list);
 		free(seq);
 		goto end;
-		break;
-
 	default:
 		BUG_ON("Unknown state of lock sequence found!\n");
 		break;
@@ -517,33 +521,42 @@ report_lock_acquired_event(struct trace_acquired_event *acquired_event,
 
 	seq->state = SEQ_STATE_ACQUIRED;
 	ls->nr_acquired++;
-	seq->prev_event_time = timestamp;
+	ls->avg_wait_time = ls->nr_contended ? ls->wait_time_total/ls->nr_contended : 0;
+	seq->prev_event_time = sample->time;
 end:
-	return;
+	return 0;
 }
 
-static void
-report_lock_contended_event(struct trace_contended_event *contended_event,
-			  struct event *__event __used,
-			  int cpu __used,
-			  u64 timestamp __used,
-			  struct thread *thread __used)
+static int report_lock_contended_event(struct perf_evsel *evsel,
+				       struct perf_sample *sample)
 {
+	void *addr;
 	struct lock_stat *ls;
 	struct thread_stat *ts;
 	struct lock_seq_stat *seq;
+	const char *name = perf_evsel__strval(evsel, sample, "name");
+	u64 tmp = perf_evsel__intval(evsel, sample, "lockdep_addr");
 
-	ls = lock_stat_findnew(contended_event->addr, contended_event->name);
+	memcpy(&addr, &tmp, sizeof(void *));
+
+	ls = lock_stat_findnew(addr, name);
+	if (!ls)
+		return -ENOMEM;
 	if (ls->discard)
-		return;
+		return 0;
 
-	ts = thread_stat_findnew(thread->pid);
-	seq = get_seq(ts, contended_event->addr);
+	ts = thread_stat_findnew(sample->tid);
+	if (!ts)
+		return -ENOMEM;
+
+	seq = get_seq(ts, addr);
+	if (!seq)
+		return -ENOMEM;
 
 	switch (seq->state) {
 	case SEQ_STATE_UNINITIALIZED:
 		/* orphan event, do nothing */
-		return;
+		return 0;
 	case SEQ_STATE_ACQUIRING:
 		break;
 	case SEQ_STATE_RELEASED:
@@ -556,7 +569,6 @@ report_lock_contended_event(struct trace_contended_event *contended_event,
 		list_del(&seq->list);
 		free(seq);
 		goto end;
-		break;
 	default:
 		BUG_ON("Unknown state of lock sequence found!\n");
 		break;
@@ -564,33 +576,41 @@ report_lock_contended_event(struct trace_contended_event *contended_event,
 
 	seq->state = SEQ_STATE_CONTENDED;
 	ls->nr_contended++;
-	seq->prev_event_time = timestamp;
+	ls->avg_wait_time = ls->wait_time_total/ls->nr_contended;
+	seq->prev_event_time = sample->time;
 end:
-	return;
+	return 0;
 }
 
-static void
-report_lock_release_event(struct trace_release_event *release_event,
-			struct event *__event __used,
-			int cpu __used,
-			u64 timestamp __used,
-			struct thread *thread __used)
+static int report_lock_release_event(struct perf_evsel *evsel,
+				     struct perf_sample *sample)
 {
+	void *addr;
 	struct lock_stat *ls;
 	struct thread_stat *ts;
 	struct lock_seq_stat *seq;
+	const char *name = perf_evsel__strval(evsel, sample, "name");
+	u64 tmp = perf_evsel__intval(evsel, sample, "lockdep_addr");
+
+	memcpy(&addr, &tmp, sizeof(void *));
 
-	ls = lock_stat_findnew(release_event->addr, release_event->name);
+	ls = lock_stat_findnew(addr, name);
+	if (!ls)
+		return -ENOMEM;
 	if (ls->discard)
-		return;
+		return 0;
 
-	ts = thread_stat_findnew(thread->pid);
-	seq = get_seq(ts, release_event->addr);
+	ts = thread_stat_findnew(sample->tid);
+	if (!ts)
+		return -ENOMEM;
+
+	seq = get_seq(ts, addr);
+	if (!seq)
+		return -ENOMEM;
 
 	switch (seq->state) {
 	case SEQ_STATE_UNINITIALIZED:
 		goto end;
-		break;
 	case SEQ_STATE_ACQUIRED:
 		break;
 	case SEQ_STATE_READ_ACQUIRED:
@@ -608,7 +628,6 @@ report_lock_release_event(struct trace_release_event *release_event,
 		ls->discard = 1;
 		bad_hist[BROKEN_RELEASE]++;
 		goto free_seq;
-		break;
 	default:
 		BUG_ON("Unknown state of lock sequence found!\n");
 		break;
@@ -619,7 +638,7 @@ free_seq:
 	list_del(&seq->list);
 	free(seq);
 end:
-	return;
+	return 0;
 }
 
 /* lock oriented handlers */
@@ -633,96 +652,36 @@ static struct trace_lock_handler report_lock_ops  = {
 
 static struct trace_lock_handler *trace_handler;
 
-static void
-process_lock_acquire_event(void *data,
-			   struct event *event __used,
-			   int cpu __used,
-			   u64 timestamp __used,
-			   struct thread *thread __used)
+static int perf_evsel__process_lock_acquire(struct perf_evsel *evsel,
+					     struct perf_sample *sample)
 {
-	struct trace_acquire_event acquire_event;
-	u64 tmp;		/* this is required for casting... */
-
-	tmp = raw_field_value(event, "lockdep_addr", data);
-	memcpy(&acquire_event.addr, &tmp, sizeof(void *));
-	acquire_event.name = (char *)raw_field_ptr(event, "name", data);
-	acquire_event.flag = (int)raw_field_value(event, "flag", data);
-
-	if (trace_handler->acquire_event)
-		trace_handler->acquire_event(&acquire_event, event, cpu, timestamp, thread);
-}
-
-static void
-process_lock_acquired_event(void *data,
-			    struct event *event __used,
-			    int cpu __used,
-			    u64 timestamp __used,
-			    struct thread *thread __used)
-{
-	struct trace_acquired_event acquired_event;
-	u64 tmp;		/* this is required for casting... */
-
-	tmp = raw_field_value(event, "lockdep_addr", data);
-	memcpy(&acquired_event.addr, &tmp, sizeof(void *));
-	acquired_event.name = (char *)raw_field_ptr(event, "name", data);
-
 	if (trace_handler->acquire_event)
-		trace_handler->acquired_event(&acquired_event, event, cpu, timestamp, thread);
+		return trace_handler->acquire_event(evsel, sample);
+	return 0;
 }
 
-static void
-process_lock_contended_event(void *data,
-			     struct event *event __used,
-			     int cpu __used,
-			     u64 timestamp __used,
-			     struct thread *thread __used)
+static int perf_evsel__process_lock_acquired(struct perf_evsel *evsel,
+					      struct perf_sample *sample)
 {
-	struct trace_contended_event contended_event;
-	u64 tmp;		/* this is required for casting... */
-
-	tmp = raw_field_value(event, "lockdep_addr", data);
-	memcpy(&contended_event.addr, &tmp, sizeof(void *));
-	contended_event.name = (char *)raw_field_ptr(event, "name", data);
-
-	if (trace_handler->acquire_event)
-		trace_handler->contended_event(&contended_event, event, cpu, timestamp, thread);
+	if (trace_handler->acquired_event)
+		return trace_handler->acquired_event(evsel, sample);
+	return 0;
 }
 
-static void
-process_lock_release_event(void *data,
-			   struct event *event __used,
-			   int cpu __used,
-			   u64 timestamp __used,
-			   struct thread *thread __used)
+static int perf_evsel__process_lock_contended(struct perf_evsel *evsel,
+					      struct perf_sample *sample)
 {
-	struct trace_release_event release_event;
-	u64 tmp;		/* this is required for casting... */
-
-	tmp = raw_field_value(event, "lockdep_addr", data);
-	memcpy(&release_event.addr, &tmp, sizeof(void *));
-	release_event.name = (char *)raw_field_ptr(event, "name", data);
-
-	if (trace_handler->acquire_event)
-		trace_handler->release_event(&release_event, event, cpu, timestamp, thread);
+	if (trace_handler->contended_event)
+		return trace_handler->contended_event(evsel, sample);
+	return 0;
 }
 
-static void
-process_raw_event(void *data, int cpu, u64 timestamp, struct thread *thread)
+static int perf_evsel__process_lock_release(struct perf_evsel *evsel,
+					    struct perf_sample *sample)
 {
-	struct event *event;
-	int type;
-
-	type = trace_parse_common_type(data);
-	event = trace_find_event(type);
-
-	if (!strcmp(event->name, "lock_acquire"))
-		process_lock_acquire_event(data, event, cpu, timestamp, thread);
-	if (!strcmp(event->name, "lock_acquired"))
-		process_lock_acquired_event(data, event, cpu, timestamp, thread);
-	if (!strcmp(event->name, "lock_contended"))
-		process_lock_contended_event(data, event, cpu, timestamp, thread);
-	if (!strcmp(event->name, "lock_release"))
-		process_lock_release_event(data, event, cpu, timestamp, thread);
+	if (trace_handler->release_event)
+		return trace_handler->release_event(evsel, sample);
+	return 0;
 }
 
 static void print_bad_events(int bad, int total)
@@ -734,7 +693,7 @@ static void print_bad_events(int bad, int total)
 
 	pr_info("\n=== output for debug===\n\n");
 	pr_info("bad: %d, total: %d\n", bad, total);
-	pr_info("bad rate: %f %%\n", (double)bad / (double)total * 100);
+	pr_info("bad rate: %.2f %%\n", (double)bad / (double)total * 100);
 	pr_info("histogram of events caused bad sequence\n");
 	for (i = 0; i < BROKEN_MAX; i++)
 		pr_info(" %10s: %d\n", name[i], bad_hist[i]);
@@ -751,6 +710,7 @@ static void print_result(void)
 	pr_info("%10s ", "acquired");
 	pr_info("%10s ", "contended");
 
+	pr_info("%15s ", "avg wait (ns)");
 	pr_info("%15s ", "total wait (ns)");
 	pr_info("%15s ", "max wait (ns)");
 	pr_info("%15s ", "min wait (ns)");
@@ -782,9 +742,10 @@ static void print_result(void)
 		pr_info("%10u ", st->nr_acquired);
 		pr_info("%10u ", st->nr_contended);
 
-		pr_info("%15llu ", st->wait_time_total);
-		pr_info("%15llu ", st->wait_time_max);
-		pr_info("%15llu ", st->wait_time_min == ULLONG_MAX ?
+		pr_info("%15" PRIu64 " ", st->avg_wait_time);
+		pr_info("%15" PRIu64 " ", st->wait_time_total);
+		pr_info("%15" PRIu64 " ", st->wait_time_max);
+		pr_info("%15" PRIu64 " ", st->wait_time_min == ULLONG_MAX ?
 		       0 : st->wait_time_min);
 		pr_info("\n");
 	}
@@ -806,7 +767,7 @@ static void dump_threads(void)
 	while (node) {
 		st = container_of(node, struct thread_stat, rb);
 		t = perf_session__findnew(session, st->tid);
-		pr_info("%10d: %s\n", st->tid, t->comm);
+		pr_info("%10d: %s\n", st->tid, thread__comm_str(t));
 		node = rb_next(node);
 	};
 }
@@ -824,51 +785,48 @@ static void dump_map(void)
 	}
 }
 
-static void dump_info(void)
+static int dump_info(void)
 {
+	int rc = 0;
+
 	if (info_threads)
 		dump_threads();
 	else if (info_map)
 		dump_map();
-	else
-		die("Unknown type of information\n");
+	else {
+		rc = -1;
+		pr_err("Unknown type of information\n");
+	}
+
+	return rc;
 }
 
-static int process_sample_event(event_t *self, struct perf_session *s)
-{
-	struct sample_data data;
-	struct thread *thread;
+typedef int (*tracepoint_handler)(struct perf_evsel *evsel,
+				  struct perf_sample *sample);
 
-	bzero(&data, sizeof(data));
-	event__parse_sample(self, s->sample_type, &data);
+static int process_sample_event(struct perf_tool *tool __maybe_unused,
+				union perf_event *event,
+				struct perf_sample *sample,
+				struct perf_evsel *evsel,
+				struct machine *machine)
+{
+	struct thread *thread = machine__findnew_thread(machine, sample->pid,
+							sample->tid);
 
-	thread = perf_session__findnew(s, data.tid);
 	if (thread == NULL) {
 		pr_debug("problem processing %d event, skipping it.\n",
-			self->header.type);
+			event->header.type);
 		return -1;
 	}
 
-	process_raw_event(data.raw_data, data.cpu, data.time, thread);
+	if (evsel->handler != NULL) {
+		tracepoint_handler f = evsel->handler;
+		return f(evsel, sample);
+	}
 
 	return 0;
 }
 
-static struct perf_event_ops eops = {
-	.sample			= process_sample_event,
-	.comm			= event__process_comm,
-	.ordered_samples	= true,
-};
-
-static int read_events(void)
-{
-	session = perf_session__new(input_name, O_RDONLY, 0, false);
-	if (!session)
-		die("Initializing perf session failed\n");
-
-	return perf_session__process_events(session, &eops);
-}
-
 static void sort_result(void)
 {
 	unsigned int i;
@@ -881,93 +839,147 @@ static void sort_result(void)
 	}
 }
 
-static void __cmd_report(void)
+static const struct perf_evsel_str_handler lock_tracepoints[] = {
+	{ "lock:lock_acquire",	 perf_evsel__process_lock_acquire,   }, /* CONFIG_LOCKDEP */
+	{ "lock:lock_acquired",	 perf_evsel__process_lock_acquired,  }, /* CONFIG_LOCKDEP, CONFIG_LOCK_STAT */
+	{ "lock:lock_contended", perf_evsel__process_lock_contended, }, /* CONFIG_LOCKDEP, CONFIG_LOCK_STAT */
+	{ "lock:lock_release",	 perf_evsel__process_lock_release,   }, /* CONFIG_LOCKDEP */
+};
+
+static int __cmd_report(bool display_info)
 {
-	setup_pager();
-	select_key();
-	read_events();
-	sort_result();
-	print_result();
-}
+	int err = -EINVAL;
+	struct perf_tool eops = {
+		.sample		 = process_sample_event,
+		.comm		 = perf_event__process_comm,
+		.ordered_samples = true,
+	};
+	struct perf_data_file file = {
+		.path = input_name,
+		.mode = PERF_DATA_MODE_READ,
+	};
 
-static const char * const report_usage[] = {
-	"perf lock report [<options>]",
-	NULL
-};
+	session = perf_session__new(&file, false, &eops);
+	if (!session) {
+		pr_err("Initializing perf session failed\n");
+		return -ENOMEM;
+	}
 
-static const struct option report_options[] = {
-	OPT_STRING('k', "key", &sort_key, "acquired",
-		    "key for sorting"),
-	/* TODO: type */
-	OPT_END()
-};
+	if (!perf_session__has_traces(session, "lock record"))
+		goto out_delete;
 
-static const char * const info_usage[] = {
-	"perf lock info [<options>]",
-	NULL
-};
+	if (perf_session__set_tracepoints_handlers(session, lock_tracepoints)) {
+		pr_err("Initializing perf session tracepoint handlers failed\n");
+		goto out_delete;
+	}
 
-static const struct option info_options[] = {
-	OPT_BOOLEAN('t', "threads", &info_threads,
-		    "dump thread list in perf.data"),
-	OPT_BOOLEAN('m', "map", &info_map,
-		    "map of lock instances (name:address table)"),
-	OPT_END()
-};
+	if (select_key())
+		goto out_delete;
 
-static const char * const lock_usage[] = {
-	"perf lock [<options>] {record|trace|report}",
-	NULL
-};
+	err = perf_session__process_events(session, &eops);
+	if (err)
+		goto out_delete;
 
-static const struct option lock_options[] = {
-	OPT_STRING('i', "input", &input_name, "file", "input file name"),
-	OPT_INCR('v', "verbose", &verbose, "be more verbose (show symbol address, etc)"),
-	OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, "dump raw trace in ASCII"),
-	OPT_END()
-};
+	setup_pager();
+	if (display_info) /* used for info subcommand */
+		err = dump_info();
+	else {
+		sort_result();
+		print_result();
+	}
 
-static const char *record_args[] = {
-	"record",
-	"-R",
-	"-f",
-	"-m", "1024",
-	"-c", "1",
-	"-e", "lock:lock_acquire:r",
-	"-e", "lock:lock_acquired:r",
-	"-e", "lock:lock_contended:r",
-	"-e", "lock:lock_release:r",
-};
+out_delete:
+	perf_session__delete(session);
+	return err;
+}
 
 static int __cmd_record(int argc, const char **argv)
 {
-	unsigned int rec_argc, i, j;
+	const char *record_args[] = {
+		"record", "-R", "-m", "1024", "-c", "1",
+	};
+	unsigned int rec_argc, i, j, ret;
 	const char **rec_argv;
 
+	for (i = 0; i < ARRAY_SIZE(lock_tracepoints); i++) {
+		if (!is_valid_tracepoint(lock_tracepoints[i].name)) {
+				pr_err("tracepoint %s is not enabled. "
+				       "Are CONFIG_LOCKDEP and CONFIG_LOCK_STAT enabled?\n",
+				       lock_tracepoints[i].name);
+				return 1;
+		}
+	}
+
 	rec_argc = ARRAY_SIZE(record_args) + argc - 1;
+	/* factor of 2 is for -e in front of each tracepoint */
+	rec_argc += 2 * ARRAY_SIZE(lock_tracepoints);
+
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
+	if (!rec_argv)
+		return -ENOMEM;
 
 	for (i = 0; i < ARRAY_SIZE(record_args); i++)
 		rec_argv[i] = strdup(record_args[i]);
 
+	for (j = 0; j < ARRAY_SIZE(lock_tracepoints); j++) {
+		rec_argv[i++] = "-e";
+		rec_argv[i++] = strdup(lock_tracepoints[j].name);
+	}
+
 	for (j = 1; j < (unsigned int)argc; j++, i++)
 		rec_argv[i] = argv[j];
 
 	BUG_ON(i != rec_argc);
 
-	return cmd_record(i, rec_argv, NULL);
+	ret = cmd_record(i, rec_argv, NULL);
+	free(rec_argv);
+	return ret;
 }
 
-int cmd_lock(int argc, const char **argv, const char *prefix __used)
+int cmd_lock(int argc, const char **argv, const char *prefix __maybe_unused)
 {
+	const struct option info_options[] = {
+	OPT_BOOLEAN('t', "threads", &info_threads,
+		    "dump thread list in perf.data"),
+	OPT_BOOLEAN('m', "map", &info_map,
+		    "map of lock instances (address:name table)"),
+	OPT_END()
+	};
+	const struct option lock_options[] = {
+	OPT_STRING('i', "input", &input_name, "file", "input file name"),
+	OPT_INCR('v', "verbose", &verbose, "be more verbose (show symbol address, etc)"),
+	OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, "dump raw trace in ASCII"),
+	OPT_END()
+	};
+	const struct option report_options[] = {
+	OPT_STRING('k', "key", &sort_key, "acquired",
+		    "key for sorting (acquired / contended / avg_wait / wait_total / wait_max / wait_min)"),
+	/* TODO: type */
+	OPT_END()
+	};
+	const char * const info_usage[] = {
+		"perf lock info [<options>]",
+		NULL
+	};
+	const char *const lock_subcommands[] = { "record", "report", "script",
+						 "info", NULL };
+	const char *lock_usage[] = {
+		NULL,
+		NULL
+	};
+	const char * const report_usage[] = {
+		"perf lock report [<options>]",
+		NULL
+	};
 	unsigned int i;
+	int rc = 0;
 
 	symbol__init();
 	for (i = 0; i < LOCKHASH_SIZE; i++)
 		INIT_LIST_HEAD(lockhash_table + i);
 
-	argc = parse_options(argc, argv, lock_options, lock_usage,
-			     PARSE_OPT_STOP_AT_NON_OPTION);
+	argc = parse_options_subcommand(argc, argv, lock_options, lock_subcommands,
+					lock_usage, PARSE_OPT_STOP_AT_NON_OPTION);
 	if (!argc)
 		usage_with_options(lock_usage, lock_options);
 
@@ -981,10 +993,10 @@ int cmd_lock(int argc, const char **argv, const char *prefix __used)
 			if (argc)
 				usage_with_options(report_usage, report_options);
 		}
-		__cmd_report();
-	} else if (!strcmp(argv[0], "trace")) {
-		/* Aliased to 'perf trace' */
-		return cmd_trace(argc, argv, prefix);
+		rc = __cmd_report(false);
+	} else if (!strcmp(argv[0], "script")) {
+		/* Aliased to 'perf script' */
+		return cmd_script(argc, argv, prefix);
 	} else if (!strcmp(argv[0], "info")) {
 		if (argc) {
 			argc = parse_options(argc, argv,
@@ -994,12 +1006,10 @@ int cmd_lock(int argc, const char **argv, const char *prefix __used)
 		}
 		/* recycling report_lock_ops */
 		trace_handler = &report_lock_ops;
-		setup_pager();
-		read_events();
-		dump_info();
+		rc = __cmd_report(true);
 	} else {
 		usage_with_options(lock_usage, lock_options);
 	}
 
-	return 0;
+	return rc;
 }
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
new file mode 100644
index 00000000000..4a1a6c94a5e
--- /dev/null
+++ b/tools/perf/builtin-mem.c
@@ -0,0 +1,246 @@
+#include "builtin.h"
+#include "perf.h"
+
+#include "util/parse-options.h"
+#include "util/trace-event.h"
+#include "util/tool.h"
+#include "util/session.h"
+#include "util/data.h"
+
+#define MEM_OPERATION_LOAD	"load"
+#define MEM_OPERATION_STORE	"store"
+
+static const char	*mem_operation		= MEM_OPERATION_LOAD;
+
+struct perf_mem {
+	struct perf_tool	tool;
+	char const		*input_name;
+	bool			hide_unresolved;
+	bool			dump_raw;
+	const char		*cpu_list;
+	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
+};
+
+static int __cmd_record(int argc, const char **argv)
+{
+	int rec_argc, i = 0, j;
+	const char **rec_argv;
+	char event[64];
+	int ret;
+
+	rec_argc = argc + 4;
+	rec_argv = calloc(rec_argc + 1, sizeof(char *));
+	if (!rec_argv)
+		return -1;
+
+	rec_argv[i++] = strdup("record");
+	if (!strcmp(mem_operation, MEM_OPERATION_LOAD))
+		rec_argv[i++] = strdup("-W");
+	rec_argv[i++] = strdup("-d");
+	rec_argv[i++] = strdup("-e");
+
+	if (strcmp(mem_operation, MEM_OPERATION_LOAD))
+		sprintf(event, "cpu/mem-stores/pp");
+	else
+		sprintf(event, "cpu/mem-loads/pp");
+
+	rec_argv[i++] = strdup(event);
+	for (j = 1; j < argc; j++, i++)
+		rec_argv[i] = argv[j];
+
+	ret = cmd_record(i, rec_argv, NULL);
+	free(rec_argv);
+	return ret;
+}
+
+static int
+dump_raw_samples(struct perf_tool *tool,
+		 union perf_event *event,
+		 struct perf_sample *sample,
+		 struct machine *machine)
+{
+	struct perf_mem *mem = container_of(tool, struct perf_mem, tool);
+	struct addr_location al;
+	const char *fmt;
+
+	if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
+		fprintf(stderr, "problem processing %d event, skipping it.\n",
+				event->header.type);
+		return -1;
+	}
+
+	if (al.filtered || (mem->hide_unresolved && al.sym == NULL))
+		return 0;
+
+	if (al.map != NULL)
+		al.map->dso->hit = 1;
+
+	if (symbol_conf.field_sep) {
+		fmt = "%d%s%d%s0x%"PRIx64"%s0x%"PRIx64"%s%"PRIu64
+		      "%s0x%"PRIx64"%s%s:%s\n";
+	} else {
+		fmt = "%5d%s%5d%s0x%016"PRIx64"%s0x016%"PRIx64
+		      "%s%5"PRIu64"%s0x%06"PRIx64"%s%s:%s\n";
+		symbol_conf.field_sep = " ";
+	}
+
+	printf(fmt,
+		sample->pid,
+		symbol_conf.field_sep,
+		sample->tid,
+		symbol_conf.field_sep,
+		sample->ip,
+		symbol_conf.field_sep,
+		sample->addr,
+		symbol_conf.field_sep,
+		sample->weight,
+		symbol_conf.field_sep,
+		sample->data_src,
+		symbol_conf.field_sep,
+		al.map ? (al.map->dso ? al.map->dso->long_name : "???") : "???",
+		al.sym ? al.sym->name : "???");
+
+	return 0;
+}
+
+static int process_sample_event(struct perf_tool *tool,
+				union perf_event *event,
+				struct perf_sample *sample,
+				struct perf_evsel *evsel __maybe_unused,
+				struct machine *machine)
+{
+	return dump_raw_samples(tool, event, sample, machine);
+}
+
+static int report_raw_events(struct perf_mem *mem)
+{
+	struct perf_data_file file = {
+		.path = input_name,
+		.mode = PERF_DATA_MODE_READ,
+	};
+	int err = -EINVAL;
+	int ret;
+	struct perf_session *session = perf_session__new(&file, false,
+							 &mem->tool);
+
+	if (session == NULL)
+		return -ENOMEM;
+
+	if (mem->cpu_list) {
+		ret = perf_session__cpu_bitmap(session, mem->cpu_list,
+					       mem->cpu_bitmap);
+		if (ret)
+			goto out_delete;
+	}
+
+	if (symbol__init() < 0)
+		return -1;
+
+	printf("# PID, TID, IP, ADDR, LOCAL WEIGHT, DSRC, SYMBOL\n");
+
+	err = perf_session__process_events(session, &mem->tool);
+	if (err)
+		return err;
+
+	return 0;
+
+out_delete:
+	perf_session__delete(session);
+	return err;
+}
+
+static int report_events(int argc, const char **argv, struct perf_mem *mem)
+{
+	const char **rep_argv;
+	int ret, i = 0, j, rep_argc;
+
+	if (mem->dump_raw)
+		return report_raw_events(mem);
+
+	rep_argc = argc + 3;
+	rep_argv = calloc(rep_argc + 1, sizeof(char *));
+	if (!rep_argv)
+		return -1;
+
+	rep_argv[i++] = strdup("report");
+	rep_argv[i++] = strdup("--mem-mode");
+	rep_argv[i++] = strdup("-n"); /* display number of samples */
+
+	/*
+	 * there is no weight (cost) associated with stores, so don't print
+	 * the column
+	 */
+	if (strcmp(mem_operation, MEM_OPERATION_LOAD))
+		rep_argv[i++] = strdup("--sort=mem,sym,dso,symbol_daddr,"
+				       "dso_daddr,tlb,locked");
+
+	for (j = 1; j < argc; j++, i++)
+		rep_argv[i] = argv[j];
+
+	ret = cmd_report(i, rep_argv, NULL);
+	free(rep_argv);
+	return ret;
+}
+
+int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused)
+{
+	struct stat st;
+	struct perf_mem mem = {
+		.tool = {
+			.sample		= process_sample_event,
+			.mmap		= perf_event__process_mmap,
+			.mmap2		= perf_event__process_mmap2,
+			.comm		= perf_event__process_comm,
+			.lost		= perf_event__process_lost,
+			.fork		= perf_event__process_fork,
+			.build_id	= perf_event__process_build_id,
+			.ordered_samples = true,
+		},
+		.input_name		 = "perf.data",
+	};
+	const struct option mem_options[] = {
+	OPT_STRING('t', "type", &mem_operation,
+		   "type", "memory operations(load/store)"),
+	OPT_BOOLEAN('D', "dump-raw-samples", &mem.dump_raw,
+		    "dump raw samples in ASCII"),
+	OPT_BOOLEAN('U', "hide-unresolved", &mem.hide_unresolved,
+		    "Only display entries resolved to a symbol"),
+	OPT_STRING('i', "input", &input_name, "file",
+		   "input file name"),
+	OPT_STRING('C', "cpu", &mem.cpu_list, "cpu",
+		   "list of cpus to profile"),
+	OPT_STRING('x', "field-separator", &symbol_conf.field_sep,
+		   "separator",
+		   "separator for columns, no spaces will be added"
+		   " between columns '.' is reserved."),
+	OPT_END()
+	};
+	const char *const mem_subcommands[] = { "record", "report", NULL };
+	const char *mem_usage[] = {
+		NULL,
+		NULL
+	};
+
+
+	argc = parse_options_subcommand(argc, argv, mem_options, mem_subcommands,
+					mem_usage, PARSE_OPT_STOP_AT_NON_OPTION);
+
+	if (!argc || !(strncmp(argv[0], "rec", 3) || mem_operation))
+		usage_with_options(mem_usage, mem_options);
+
+	if (!mem.input_name || !strlen(mem.input_name)) {
+		if (!fstat(STDIN_FILENO, &st) && S_ISFIFO(st.st_mode))
+			mem.input_name = "-";
+		else
+			mem.input_name = "perf.data";
+	}
+
+	if (!strncmp(argv[0], "rec", 3))
+		return __cmd_record(argc, argv);
+	else if (!strncmp(argv[0], "rep", 3))
+		return report_events(argc, argv, &mem);
+	else
+		usage_with_options(mem_usage, mem_options);
+
+	return 0;
+}
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index e4a4da32a56..c63fa292507 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -20,7 +20,6 @@
  * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
  *
  */
-#define _GNU_SOURCE
 #include <sys/utsname.h>
 #include <sys/types.h>
 #include <sys/stat.h>
@@ -31,33 +30,40 @@
 #include <stdlib.h>
 #include <string.h>
 
-#undef _GNU_SOURCE
 #include "perf.h"
 #include "builtin.h"
 #include "util/util.h"
 #include "util/strlist.h"
+#include "util/strfilter.h"
 #include "util/symbol.h"
 #include "util/debug.h"
-#include "util/debugfs.h"
+#include <api/fs/debugfs.h>
 #include "util/parse-options.h"
 #include "util/probe-finder.h"
 #include "util/probe-event.h"
 
-#define MAX_PATH_LEN 256
+#define DEFAULT_VAR_FILTER "!__k???tab_* & !__crc_*"
+#define DEFAULT_FUNC_FILTER "!_*"
 
 /* Session management structure */
 static struct {
 	bool list_events;
 	bool force_add;
 	bool show_lines;
+	bool show_vars;
+	bool show_ext_vars;
+	bool show_funcs;
+	bool mod_events;
+	bool uprobes;
 	int nevents;
 	struct perf_probe_event events[MAX_PROBES];
 	struct strlist *dellist;
 	struct line_range line_range;
+	char *target;
 	int max_probe_points;
+	struct strfilter *filter;
 } params;
 
-
 /* Parse an event definition. Note that any error must die. */
 static int parse_probe_event(const char *str)
 {
@@ -70,6 +76,8 @@ static int parse_probe_event(const char *str)
 		return -1;
 	}
 
+	pev->uprobes = params.uprobes;
+
 	/* Parse a perf-probe command into event */
 	ret = parse_perf_probe_command(str, pev);
 	pr_debug("%d arguments\n", pev->nargs);
@@ -77,39 +85,85 @@ static int parse_probe_event(const char *str)
 	return ret;
 }
 
+static int set_target(const char *ptr)
+{
+	int found = 0;
+	const char *buf;
+
+	/*
+	 * The first argument after options can be an absolute path
+	 * to an executable / library or kernel module.
+	 *
+	 * TODO: Support relative path, and $PATH, $LD_LIBRARY_PATH,
+	 * short module name.
+	 */
+	if (!params.target && ptr && *ptr == '/') {
+		params.target = strdup(ptr);
+		if (!params.target)
+			return -ENOMEM;
+
+		found = 1;
+		buf = ptr + (strlen(ptr) - 3);
+
+		if (strcmp(buf, ".ko"))
+			params.uprobes = true;
+
+	}
+
+	return found;
+}
+
 static int parse_probe_event_argv(int argc, const char **argv)
 {
-	int i, len, ret;
+	int i, len, ret, found_target;
 	char *buf;
 
+	found_target = set_target(argv[0]);
+	if (found_target < 0)
+		return found_target;
+
+	if (found_target && argc == 1)
+		return 0;
+
 	/* Bind up rest arguments */
 	len = 0;
-	for (i = 0; i < argc; i++)
+	for (i = 0; i < argc; i++) {
+		if (i == 0 && found_target)
+			continue;
+
 		len += strlen(argv[i]) + 1;
+	}
 	buf = zalloc(len + 1);
 	if (buf == NULL)
 		return -ENOMEM;
 	len = 0;
-	for (i = 0; i < argc; i++)
+	for (i = 0; i < argc; i++) {
+		if (i == 0 && found_target)
+			continue;
+
 		len += sprintf(&buf[len], "%s ", argv[i]);
+	}
+	params.mod_events = true;
 	ret = parse_probe_event(buf);
 	free(buf);
 	return ret;
 }
 
-static int opt_add_probe_event(const struct option *opt __used,
-			      const char *str, int unset __used)
+static int opt_add_probe_event(const struct option *opt __maybe_unused,
+			      const char *str, int unset __maybe_unused)
 {
-	if (str)
+	if (str) {
+		params.mod_events = true;
 		return parse_probe_event(str);
-	else
+	} else
 		return 0;
 }
 
-static int opt_del_probe_event(const struct option *opt __used,
-			       const char *str, int unset __used)
+static int opt_del_probe_event(const struct option *opt __maybe_unused,
+			       const char *str, int unset __maybe_unused)
 {
 	if (str) {
+		params.mod_events = true;
 		if (!params.dellist)
 			params.dellist = strlist__new(true, NULL);
 		strlist__add(params.dellist, str);
@@ -117,33 +171,145 @@ static int opt_del_probe_event(const struct option *opt __used,
 	return 0;
 }
 
-#ifdef DWARF_SUPPORT
-static int opt_show_lines(const struct option *opt __used,
-			  const char *str, int unset __used)
+static int opt_set_target(const struct option *opt, const char *str,
+			int unset __maybe_unused)
+{
+	int ret = -ENOENT;
+	char *tmp;
+
+	if  (str && !params.target) {
+		if (!strcmp(opt->long_name, "exec"))
+			params.uprobes = true;
+#ifdef HAVE_DWARF_SUPPORT
+		else if (!strcmp(opt->long_name, "module"))
+			params.uprobes = false;
+#endif
+		else
+			return ret;
+
+		/* Expand given path to absolute path, except for modulename */
+		if (params.uprobes || strchr(str, '/')) {
+			tmp = realpath(str, NULL);
+			if (!tmp) {
+				pr_warning("Failed to get the absolute path of %s: %m\n", str);
+				return ret;
+			}
+		} else {
+			tmp = strdup(str);
+			if (!tmp)
+				return -ENOMEM;
+		}
+		params.target = tmp;
+		ret = 0;
+	}
+
+	return ret;
+}
+
+#ifdef HAVE_DWARF_SUPPORT
+static int opt_show_lines(const struct option *opt __maybe_unused,
+			  const char *str, int unset __maybe_unused)
 {
 	int ret = 0;
 
-	if (str)
-		ret = parse_line_range_desc(str, &params.line_range);
-	INIT_LIST_HEAD(&params.line_range.line_list);
+	if (!str)
+		return 0;
+
+	if (params.show_lines) {
+		pr_warning("Warning: more than one --line options are"
+			   " detected. Only the first one is valid.\n");
+		return 0;
+	}
+
 	params.show_lines = true;
+	ret = parse_line_range_desc(str, &params.line_range);
+
+	return ret;
+}
+
+static int opt_show_vars(const struct option *opt __maybe_unused,
+			 const char *str, int unset __maybe_unused)
+{
+	struct perf_probe_event *pev = &params.events[params.nevents];
+	int ret;
+
+	if (!str)
+		return 0;
+
+	ret = parse_probe_event(str);
+	if (!ret && pev->nargs != 0) {
+		pr_err("  Error: '--vars' doesn't accept arguments.\n");
+		return -EINVAL;
+	}
+	params.show_vars = true;
 
 	return ret;
 }
 #endif
 
-static const char * const probe_usage[] = {
-	"perf probe [<options>] 'PROBEDEF' ['PROBEDEF' ...]",
-	"perf probe [<options>] --add 'PROBEDEF' [--add 'PROBEDEF' ...]",
-	"perf probe [<options>] --del '[GROUP:]EVENT' ...",
-	"perf probe --list",
-#ifdef DWARF_SUPPORT
-	"perf probe --line 'LINEDESC'",
+static int opt_set_filter(const struct option *opt __maybe_unused,
+			  const char *str, int unset __maybe_unused)
+{
+	const char *err;
+
+	if (str) {
+		pr_debug2("Set filter: %s\n", str);
+		if (params.filter)
+			strfilter__delete(params.filter);
+		params.filter = strfilter__new(str, &err);
+		if (!params.filter) {
+			pr_err("Filter parse error at %td.\n", err - str + 1);
+			pr_err("Source: \"%s\"\n", str);
+			pr_err("         %*c\n", (int)(err - str + 1), '^');
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static int init_params(void)
+{
+	return line_range__init(&params.line_range);
+}
+
+static void cleanup_params(void)
+{
+	int i;
+
+	for (i = 0; i < params.nevents; i++)
+		clear_perf_probe_event(params.events + i);
+	if (params.dellist)
+		strlist__delete(params.dellist);
+	line_range__clear(&params.line_range);
+	free(params.target);
+	if (params.filter)
+		strfilter__delete(params.filter);
+	memset(&params, 0, sizeof(params));
+}
+
+static void pr_err_with_code(const char *msg, int err)
+{
+	pr_err("%s", msg);
+	pr_debug(" Reason: %s (Code: %d)", strerror(-err), err);
+	pr_err("\n");
+}
+
+static int
+__cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
+{
+	const char * const probe_usage[] = {
+		"perf probe [<options>] 'PROBEDEF' ['PROBEDEF' ...]",
+		"perf probe [<options>] --add 'PROBEDEF' [--add 'PROBEDEF' ...]",
+		"perf probe [<options>] --del '[GROUP:]EVENT' ...",
+		"perf probe --list",
+#ifdef HAVE_DWARF_SUPPORT
+		"perf probe [<options>] --line 'LINEDESC'",
+		"perf probe [<options>] --vars 'PROBEPOINT'",
 #endif
-	NULL
+		NULL
 };
-
-static const struct option options[] = {
+	const struct option options[] = {
 	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose (show parsed arguments, etc)"),
 	OPT_BOOLEAN('l', "list", &params.list_events,
@@ -151,7 +317,7 @@ static const struct option options[] = {
 	OPT_CALLBACK('d', "del", NULL, "[GROUP:]EVENT", "delete a probe event.",
 		opt_del_probe_event),
 	OPT_CALLBACK('a', "add", NULL,
-#ifdef DWARF_SUPPORT
+#ifdef HAVE_DWARF_SUPPORT
 		"[EVENT=]FUNC[@SRC][+OFF|%return|:RL|;PT]|SRC:AL|SRC;PT"
 		" [[NAME=]ARG ...]",
 #else
@@ -163,7 +329,7 @@ static const struct option options[] = {
 		"\t\tFUNC:\tFunction name\n"
 		"\t\tOFF:\tOffset from function entry (in byte)\n"
 		"\t\t%return:\tPut the probe at function return\n"
-#ifdef DWARF_SUPPORT
+#ifdef HAVE_DWARF_SUPPORT
 		"\t\tSRC:\tSource code path\n"
 		"\t\tRL:\tRelative line number from function entry.\n"
 		"\t\tAL:\tAbsolute line number in file.\n"
@@ -176,21 +342,39 @@ static const struct option options[] = {
 		opt_add_probe_event),
 	OPT_BOOLEAN('f', "force", &params.force_add, "forcibly add events"
 		    " with existing name"),
-#ifdef DWARF_SUPPORT
+#ifdef HAVE_DWARF_SUPPORT
 	OPT_CALLBACK('L', "line", NULL,
 		     "FUNC[:RLN[+NUM|-RLN2]]|SRC:ALN[+NUM|-ALN2]",
 		     "Show source code lines.", opt_show_lines),
+	OPT_CALLBACK('V', "vars", NULL,
+		     "FUNC[@SRC][+OFF|%return|:RL|;PT]|SRC:AL|SRC;PT",
+		     "Show accessible variables on PROBEDEF", opt_show_vars),
+	OPT_BOOLEAN('\0', "externs", &params.show_ext_vars,
+		    "Show external variables too (with --vars only)"),
 	OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
 		   "file", "vmlinux pathname"),
+	OPT_STRING('s', "source", &symbol_conf.source_prefix,
+		   "directory", "path to kernel source"),
+	OPT_CALLBACK('m', "module", NULL, "modname|path",
+		"target module name (for online) or path (for offline)",
+		opt_set_target),
 #endif
 	OPT__DRY_RUN(&probe_event_dry_run),
 	OPT_INTEGER('\0', "max-probes", &params.max_probe_points,
 		 "Set how many probe points can be found for a probe."),
+	OPT_BOOLEAN('F', "funcs", &params.show_funcs,
+		    "Show potential probe-able functions."),
+	OPT_CALLBACK('\0', "filter", NULL,
+		     "[!]FILTER", "Set a filter (with --vars/funcs only)\n"
+		     "\t\t\t(default: \"" DEFAULT_VAR_FILTER "\" for --vars,\n"
+		     "\t\t\t \"" DEFAULT_FUNC_FILTER "\" for --funcs)",
+		     opt_set_filter),
+	OPT_CALLBACK('x', "exec", NULL, "executable|path",
+			"target executable name or path", opt_set_target),
+	OPT_BOOLEAN(0, "demangle", &symbol_conf.demangle,
+		    "Disable symbol demangling"),
 	OPT_END()
-};
-
-int cmd_probe(int argc, const char **argv, const char *prefix __used)
-{
+	};
 	int ret;
 
 	argc = parse_options(argc, argv, options, probe_usage,
@@ -202,7 +386,7 @@ int cmd_probe(int argc, const char **argv, const char *prefix __used)
 		}
 		ret = parse_probe_event_argv(argc, argv);
 		if (ret < 0) {
-			pr_err("  Error: Parse Error.  (%d)\n", ret);
+			pr_err_with_code("  Error: Command Parse Error.", ret);
 			return ret;
 		}
 	}
@@ -211,11 +395,16 @@ int cmd_probe(int argc, const char **argv, const char *prefix __used)
 		params.max_probe_points = MAX_PROBES;
 
 	if ((!params.nevents && !params.dellist && !params.list_events &&
-	     !params.show_lines))
+	     !params.show_lines && !params.show_funcs))
 		usage_with_options(probe_usage, options);
 
+	/*
+	 * Only consider the user's kernel image path if given.
+	 */
+	symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);
+
 	if (params.list_events) {
-		if (params.nevents != 0 || params.dellist) {
+		if (params.mod_events) {
 			pr_err("  Error: Don't use --list with --add/--del.\n");
 			usage_with_options(probe_usage, options);
 		}
@@ -223,46 +412,119 @@ int cmd_probe(int argc, const char **argv, const char *prefix __used)
 			pr_err("  Error: Don't use --list with --line.\n");
 			usage_with_options(probe_usage, options);
 		}
+		if (params.show_vars) {
+			pr_err(" Error: Don't use --list with --vars.\n");
+			usage_with_options(probe_usage, options);
+		}
+		if (params.show_funcs) {
+			pr_err("  Error: Don't use --list with --funcs.\n");
+			usage_with_options(probe_usage, options);
+		}
+		if (params.uprobes) {
+			pr_warning("  Error: Don't use --list with --exec.\n");
+			usage_with_options(probe_usage, options);
+		}
 		ret = show_perf_probe_events();
 		if (ret < 0)
-			pr_err("  Error: Failed to show event list. (%d)\n",
-			       ret);
+			pr_err_with_code("  Error: Failed to show event list.", ret);
+		return ret;
+	}
+	if (params.show_funcs) {
+		if (params.nevents != 0 || params.dellist) {
+			pr_err("  Error: Don't use --funcs with"
+			       " --add/--del.\n");
+			usage_with_options(probe_usage, options);
+		}
+		if (params.show_lines) {
+			pr_err("  Error: Don't use --funcs with --line.\n");
+			usage_with_options(probe_usage, options);
+		}
+		if (params.show_vars) {
+			pr_err("  Error: Don't use --funcs with --vars.\n");
+			usage_with_options(probe_usage, options);
+		}
+		if (!params.filter)
+			params.filter = strfilter__new(DEFAULT_FUNC_FILTER,
+						       NULL);
+		ret = show_available_funcs(params.target, params.filter,
+					params.uprobes);
+		strfilter__delete(params.filter);
+		params.filter = NULL;
+		if (ret < 0)
+			pr_err_with_code("  Error: Failed to show functions.", ret);
 		return ret;
 	}
 
-#ifdef DWARF_SUPPORT
+#ifdef HAVE_DWARF_SUPPORT
 	if (params.show_lines) {
-		if (params.nevents != 0 || params.dellist) {
-			pr_warning("  Error: Don't use --line with"
-				   " --add/--del.\n");
+		if (params.mod_events) {
+			pr_err("  Error: Don't use --line with"
+			       " --add/--del.\n");
+			usage_with_options(probe_usage, options);
+		}
+		if (params.show_vars) {
+			pr_err(" Error: Don't use --line with --vars.\n");
 			usage_with_options(probe_usage, options);
 		}
 
-		ret = show_line_range(&params.line_range);
+		ret = show_line_range(&params.line_range, params.target);
 		if (ret < 0)
-			pr_err("  Error: Failed to show lines. (%d)\n", ret);
+			pr_err_with_code("  Error: Failed to show lines.", ret);
+		return ret;
+	}
+	if (params.show_vars) {
+		if (params.mod_events) {
+			pr_err("  Error: Don't use --vars with"
+			       " --add/--del.\n");
+			usage_with_options(probe_usage, options);
+		}
+		if (!params.filter)
+			params.filter = strfilter__new(DEFAULT_VAR_FILTER,
+						       NULL);
+
+		ret = show_available_vars(params.events, params.nevents,
+					  params.max_probe_points,
+					  params.target,
+					  params.filter,
+					  params.show_ext_vars);
+		strfilter__delete(params.filter);
+		params.filter = NULL;
+		if (ret < 0)
+			pr_err_with_code("  Error: Failed to show vars.", ret);
 		return ret;
 	}
 #endif
 
 	if (params.dellist) {
 		ret = del_perf_probe_events(params.dellist);
-		strlist__delete(params.dellist);
 		if (ret < 0) {
-			pr_err("  Error: Failed to delete events. (%d)\n", ret);
+			pr_err_with_code("  Error: Failed to delete events.", ret);
 			return ret;
 		}
 	}
 
 	if (params.nevents) {
 		ret = add_perf_probe_events(params.events, params.nevents,
-					    params.force_add,
-					    params.max_probe_points);
+					    params.max_probe_points,
+					    params.target,
+					    params.force_add);
 		if (ret < 0) {
-			pr_err("  Error: Failed to add events. (%d)\n", ret);
+			pr_err_with_code("  Error: Failed to add events.", ret);
 			return ret;
 		}
 	}
 	return 0;
 }
 
+int cmd_probe(int argc, const char **argv, const char *prefix)
+{
+	int ret;
+
+	ret = init_params();
+	if (!ret) {
+		ret = __cmd_probe(argc, argv, prefix);
+		cleanup_params();
+	}
+
+	return ret;
+}
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 711745f56bb..378b85b731a 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -5,8 +5,6 @@
  * (or a CPU, or a PID) into the perf.data output file - for
  * later analysis via perf report.
  */
-#define _FILE_OFFSET_BITS 64
-
 #include "builtin.h"
 
 #include "perf.h"
@@ -18,149 +16,68 @@
 
 #include "util/header.h"
 #include "util/event.h"
+#include "util/evlist.h"
+#include "util/evsel.h"
 #include "util/debug.h"
 #include "util/session.h"
+#include "util/tool.h"
 #include "util/symbol.h"
 #include "util/cpumap.h"
+#include "util/thread_map.h"
+#include "util/data.h"
 
 #include <unistd.h>
 #include <sched.h>
 #include <sys/mman.h>
 
-enum write_mode_t {
-	WRITE_FORCE,
-	WRITE_APPEND
-};
 
-static int			*fd[MAX_NR_CPUS][MAX_COUNTERS];
-
-static u64			user_interval			= ULLONG_MAX;
-static u64			default_interval		=      0;
-
-static int			nr_cpus				=      0;
-static unsigned int		page_size;
-static unsigned int		mmap_pages			=    128;
-static unsigned int		user_freq 			= UINT_MAX;
-static int			freq				=   1000;
-static int			output;
-static int			pipe_output			=      0;
-static const char		*output_name			= "perf.data";
-static int			group				=      0;
-static int			realtime_prio			=      0;
-static bool			raw_samples			=  false;
-static bool			system_wide			=  false;
-static int			profile_cpu			=     -1;
-static pid_t			target_pid			=     -1;
-static pid_t			target_tid			=     -1;
-static pid_t			*all_tids			=      NULL;
-static int			thread_num			=      0;
-static pid_t			child_pid			=     -1;
-static bool			no_inherit			=  false;
-static enum write_mode_t	write_mode			= WRITE_FORCE;
-static bool			call_graph			=  false;
-static bool			inherit_stat			=  false;
-static bool			no_samples			=  false;
-static bool			sample_address			=  false;
-
-static long			samples				=      0;
-static u64			bytes_written			=      0;
-
-static struct pollfd		*event_array;
-
-static int			nr_poll				=      0;
-static int			nr_cpu				=      0;
-
-static int			file_new			=      1;
-static off_t			post_processing_offset;
-
-static struct perf_session	*session;
-
-struct mmap_data {
-	int			counter;
-	void			*base;
-	unsigned int		mask;
-	unsigned int		prev;
+struct record {
+	struct perf_tool	tool;
+	struct record_opts	opts;
+	u64			bytes_written;
+	struct perf_data_file	file;
+	struct perf_evlist	*evlist;
+	struct perf_session	*session;
+	const char		*progname;
+	int			realtime_prio;
+	bool			no_buildid;
+	bool			no_buildid_cache;
+	long			samples;
 };
 
-static struct mmap_data		mmap_array[MAX_NR_CPUS];
-
-static unsigned long mmap_read_head(struct mmap_data *md)
-{
-	struct perf_event_mmap_page *pc = md->base;
-	long head;
-
-	head = pc->data_head;
-	rmb();
-
-	return head;
-}
-
-static void mmap_write_tail(struct mmap_data *md, unsigned long tail)
-{
-	struct perf_event_mmap_page *pc = md->base;
-
-	/*
-	 * ensure all reads are done before we write the tail out.
-	 */
-	/* mb(); */
-	pc->data_tail = tail;
-}
-
-static void advance_output(size_t size)
+static int record__write(struct record *rec, void *bf, size_t size)
 {
-	bytes_written += size;
-}
-
-static void write_output(void *buf, size_t size)
-{
-	while (size) {
-		int ret = write(output, buf, size);
-
-		if (ret < 0)
-			die("failed to write");
-
-		size -= ret;
-		buf += ret;
-
-		bytes_written += ret;
+	if (perf_data_file__write(rec->session->file, bf, size) < 0) {
+		pr_err("failed to write perf data, error: %m\n");
+		return -1;
 	}
+
+	rec->bytes_written += size;
+	return 0;
 }
 
-static int process_synthesized_event(event_t *event,
-				     struct perf_session *self __used)
+static int process_synthesized_event(struct perf_tool *tool,
+				     union perf_event *event,
+				     struct perf_sample *sample __maybe_unused,
+				     struct machine *machine __maybe_unused)
 {
-	write_output(event, event->header.size);
-	return 0;
+	struct record *rec = container_of(tool, struct record, tool);
+	return record__write(rec, event, event->header.size);
 }
 
-static void mmap_read(struct mmap_data *md)
+static int record__mmap_read(struct record *rec, struct perf_mmap *md)
 {
-	unsigned int head = mmap_read_head(md);
+	unsigned int head = perf_mmap__read_head(md);
 	unsigned int old = md->prev;
 	unsigned char *data = md->base + page_size;
 	unsigned long size;
 	void *buf;
-	int diff;
+	int rc = 0;
 
-	/*
-	 * If we're further behind than half the buffer, there's a chance
-	 * the writer will bite our tail and mess up the samples under us.
-	 *
-	 * If we somehow ended up ahead of the head, we got messed up.
-	 *
-	 * In either case, truncate and restart at head.
-	 */
-	diff = head - old;
-	if (diff < 0) {
-		fprintf(stderr, "WARNING: failed to keep up with mmap data\n");
-		/*
-		 * head points to a known good entry, start there.
-		 */
-		old = head;
-	}
+	if (old == head)
+		return 0;
 
-	if (old != head)
-		samples++;
+	rec->samples++;
 
 	size = head - old;
 
@@ -169,283 +86,126 @@ static void mmap_read(struct mmap_data *md)
 		size = md->mask + 1 - (old & md->mask);
 		old += size;
 
-		write_output(buf, size);
+		if (record__write(rec, buf, size) < 0) {
+			rc = -1;
+			goto out;
+		}
 	}
 
 	buf = &data[old & md->mask];
 	size = head - old;
 	old += size;
 
-	write_output(buf, size);
+	if (record__write(rec, buf, size) < 0) {
+		rc = -1;
+		goto out;
+	}
 
 	md->prev = old;
-	mmap_write_tail(md, old);
+	perf_mmap__write_tail(md, old);
+
+out:
+	return rc;
 }
 
 static volatile int done = 0;
 static volatile int signr = -1;
+static volatile int child_finished = 0;
 
 static void sig_handler(int sig)
 {
+	if (sig == SIGCHLD)
+		child_finished = 1;
+	else
+		signr = sig;
+
 	done = 1;
-	signr = sig;
 }
 
-static void sig_atexit(void)
+static void record__sig_exit(void)
 {
-	if (child_pid > 0)
-		kill(child_pid, SIGTERM);
-
 	if (signr == -1)
 		return;
 
 	signal(signr, SIG_DFL);
-	kill(getpid(), signr);
+	raise(signr);
 }
 
-static int group_fd;
-
-static struct perf_header_attr *get_header_attr(struct perf_event_attr *a, int nr)
-{
-	struct perf_header_attr *h_attr;
-
-	if (nr < session->header.attrs) {
-		h_attr = session->header.attr[nr];
-	} else {
-		h_attr = perf_header_attr__new(a);
-		if (h_attr != NULL)
-			if (perf_header__add_attr(&session->header, h_attr) < 0) {
-				perf_header_attr__delete(h_attr);
-				h_attr = NULL;
-			}
-	}
-
-	return h_attr;
-}
-
-static void create_counter(int counter, int cpu)
+static int record__open(struct record *rec)
 {
-	char *filter = filters[counter];
-	struct perf_event_attr *attr = attrs + counter;
-	struct perf_header_attr *h_attr;
-	int track = !counter; /* only the first counter needs these */
-	int thread_index;
-	int ret;
-	struct {
-		u64 count;
-		u64 time_enabled;
-		u64 time_running;
-		u64 id;
-	} read_data;
-
-	attr->read_format	= PERF_FORMAT_TOTAL_TIME_ENABLED |
-				  PERF_FORMAT_TOTAL_TIME_RUNNING |
-				  PERF_FORMAT_ID;
-
-	attr->sample_type	|= PERF_SAMPLE_IP | PERF_SAMPLE_TID;
+	char msg[512];
+	struct perf_evsel *pos;
+	struct perf_evlist *evlist = rec->evlist;
+	struct perf_session *session = rec->session;
+	struct record_opts *opts = &rec->opts;
+	int rc = 0;
 
-	if (nr_counters > 1)
-		attr->sample_type |= PERF_SAMPLE_ID;
-
-	/*
-	 * We default some events to a 1 default interval. But keep
-	 * it a weak assumption overridable by the user.
-	 */
-	if (!attr->sample_period || (user_freq != UINT_MAX &&
-				     user_interval != ULLONG_MAX)) {
-		if (freq) {
-			attr->sample_type	|= PERF_SAMPLE_PERIOD;
-			attr->freq		= 1;
-			attr->sample_freq	= freq;
-		} else {
-			attr->sample_period = default_interval;
-		}
-	}
+	perf_evlist__config(evlist, opts);
 
-	if (no_samples)
-		attr->sample_freq = 0;
-
-	if (inherit_stat)
-		attr->inherit_stat = 1;
-
-	if (sample_address)
-		attr->sample_type	|= PERF_SAMPLE_ADDR;
-
-	if (call_graph)
-		attr->sample_type	|= PERF_SAMPLE_CALLCHAIN;
-
-	if (raw_samples) {
-		attr->sample_type	|= PERF_SAMPLE_TIME;
-		attr->sample_type	|= PERF_SAMPLE_RAW;
-		attr->sample_type	|= PERF_SAMPLE_CPU;
-	}
-
-	attr->mmap		= track;
-	attr->comm		= track;
-	attr->inherit		= !no_inherit;
-	if (target_pid == -1 && target_tid == -1 && !system_wide) {
-		attr->disabled = 1;
-		attr->enable_on_exec = 1;
-	}
-
-	for (thread_index = 0; thread_index < thread_num; thread_index++) {
+	evlist__for_each(evlist, pos) {
 try_again:
-		fd[nr_cpu][counter][thread_index] = sys_perf_event_open(attr,
-				all_tids[thread_index], cpu, group_fd, 0);
-
-		if (fd[nr_cpu][counter][thread_index] < 0) {
-			int err = errno;
-
-			if (err == EPERM || err == EACCES)
-				die("Permission error - are you root?\n"
-					"\t Consider tweaking"
-					" /proc/sys/kernel/perf_event_paranoid.\n");
-			else if (err ==  ENODEV && profile_cpu != -1) {
-				die("No such device - did you specify"
-					" an out-of-range profile CPU?\n");
-			}
-
-			/*
-			 * If it's cycles then fall back to hrtimer
-			 * based cpu-clock-tick sw counter, which
-			 * is always available even if no PMU support:
-			 */
-			if (attr->type == PERF_TYPE_HARDWARE
-					&& attr->config == PERF_COUNT_HW_CPU_CYCLES) {
-
+		if (perf_evsel__open(pos, evlist->cpus, evlist->threads) < 0) {
+			if (perf_evsel__fallback(pos, errno, msg, sizeof(msg))) {
 				if (verbose)
-					warning(" ... trying to fall back to cpu-clock-ticks\n");
-				attr->type = PERF_TYPE_SOFTWARE;
-				attr->config = PERF_COUNT_SW_CPU_CLOCK;
+					ui__warning("%s\n", msg);
 				goto try_again;
 			}
-			printf("\n");
-			error("perfcounter syscall returned with %d (%s)\n",
-					fd[nr_cpu][counter][thread_index], strerror(err));
-
-#if defined(__i386__) || defined(__x86_64__)
-			if (attr->type == PERF_TYPE_HARDWARE && err == EOPNOTSUPP)
-				die("No hardware sampling interrupt available."
-				    " No APIC? If so then you can boot the kernel"
-				    " with the \"lapic\" boot parameter to"
-				    " force-enable it.\n");
-#endif
-
-			die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
-			exit(-1);
-		}
-
-		h_attr = get_header_attr(attr, counter);
-		if (h_attr == NULL)
-			die("nomem\n");
-
-		if (!file_new) {
-			if (memcmp(&h_attr->attr, attr, sizeof(*attr))) {
-				fprintf(stderr, "incompatible append\n");
-				exit(-1);
-			}
-		}
-
-		if (read(fd[nr_cpu][counter][thread_index], &read_data, sizeof(read_data)) == -1) {
-			perror("Unable to read perf file descriptor\n");
-			exit(-1);
-		}
 
-		if (perf_header_attr__add_id(h_attr, read_data.id) < 0) {
-			pr_warning("Not enough memory to add id\n");
-			exit(-1);
+			rc = -errno;
+			perf_evsel__open_strerror(pos, &opts->target,
+						  errno, msg, sizeof(msg));
+			ui__error("%s\n", msg);
+			goto out;
 		}
+	}
 
-		assert(fd[nr_cpu][counter][thread_index] >= 0);
-		fcntl(fd[nr_cpu][counter][thread_index], F_SETFL, O_NONBLOCK);
+	if (perf_evlist__apply_filters(evlist)) {
+		error("failed to set filter with %d (%s)\n", errno,
+			strerror(errno));
+		rc = -1;
+		goto out;
+	}
 
-		/*
-		 * First counter acts as the group leader:
-		 */
-		if (group && group_fd == -1)
-			group_fd = fd[nr_cpu][counter][thread_index];
-
-		if (counter || thread_index) {
-			ret = ioctl(fd[nr_cpu][counter][thread_index],
-					PERF_EVENT_IOC_SET_OUTPUT,
-					fd[nr_cpu][0][0]);
-			if (ret) {
-				error("failed to set output: %d (%s)\n", errno,
-						strerror(errno));
-				exit(-1);
-			}
+	if (perf_evlist__mmap(evlist, opts->mmap_pages, false) < 0) {
+		if (errno == EPERM) {
+			pr_err("Permission error mapping pages.\n"
+			       "Consider increasing "
+			       "/proc/sys/kernel/perf_event_mlock_kb,\n"
+			       "or try again with a smaller value of -m/--mmap_pages.\n"
+			       "(current value: %u)\n", opts->mmap_pages);
+			rc = -errno;
 		} else {
-			mmap_array[nr_cpu].counter = counter;
-			mmap_array[nr_cpu].prev = 0;
-			mmap_array[nr_cpu].mask = mmap_pages*page_size - 1;
-			mmap_array[nr_cpu].base = mmap(NULL, (mmap_pages+1)*page_size,
-				PROT_READ|PROT_WRITE, MAP_SHARED, fd[nr_cpu][counter][thread_index], 0);
-			if (mmap_array[nr_cpu].base == MAP_FAILED) {
-				error("failed to mmap with %d (%s)\n", errno, strerror(errno));
-				exit(-1);
-			}
-
-			event_array[nr_poll].fd = fd[nr_cpu][counter][thread_index];
-			event_array[nr_poll].events = POLLIN;
-			nr_poll++;
-		}
-
-		if (filter != NULL) {
-			ret = ioctl(fd[nr_cpu][counter][thread_index],
-					PERF_EVENT_IOC_SET_FILTER, filter);
-			if (ret) {
-				error("failed to set filter with %d (%s)\n", errno,
-						strerror(errno));
-				exit(-1);
-			}
+			pr_err("failed to mmap with %d (%s)\n", errno, strerror(errno));
+			rc = -errno;
 		}
+		goto out;
 	}
-}
-
-static void open_counters(int cpu)
-{
-	int counter;
 
-	group_fd = -1;
-	for (counter = 0; counter < nr_counters; counter++)
-		create_counter(counter, cpu);
-
-	nr_cpu++;
+	session->evlist = evlist;
+	perf_session__set_id_hdr_size(session);
+out:
+	return rc;
 }
 
-static int process_buildids(void)
+static int process_buildids(struct record *rec)
 {
-	u64 size = lseek(output, 0, SEEK_CUR);
+	struct perf_data_file *file  = &rec->file;
+	struct perf_session *session = rec->session;
+	u64 start = session->header.data_offset;
 
+	u64 size = lseek(file->fd, 0, SEEK_CUR);
 	if (size == 0)
 		return 0;
 
-	session->fd = output;
-	return __perf_session__process_events(session, post_processing_offset,
-					      size - post_processing_offset,
+	return __perf_session__process_events(session, start,
+					      size - start,
 					      size, &build_id__mark_dso_hit_ops);
 }
 
-static void atexit_header(void)
-{
-	if (!pipe_output) {
-		session->header.data_size += bytes_written;
-
-		process_buildids();
-		perf_header__write(&session->header, output, true);
-	}
-}
-
-static void event__synthesize_guest_os(struct machine *machine, void *data)
+static void perf_event__synthesize_guest_os(struct machine *machine, void *data)
 {
 	int err;
-	char *guest_kallsyms;
-	char path[PATH_MAX];
-	struct perf_session *psession = data;
-
-	if (machine__is_host(machine))
-		return;
-
+	struct perf_tool *tool = data;
 	/*
 	 *As for guest kernel when processing subcommand record&report,
 	 *we arrange module mmap prior to guest kernel mmap and trigger
@@ -454,28 +214,18 @@ static void event__synthesize_guest_os(struct machine *machine, void *data)
 	 *method is used to avoid symbol missing when the first addr is
 	 *in module instead of in guest kernel.
 	 */
-	err = event__synthesize_modules(process_synthesized_event,
-					psession, machine);
+	err = perf_event__synthesize_modules(tool, process_synthesized_event,
+					     machine);
 	if (err < 0)
 		pr_err("Couldn't record guest kernel [%d]'s reference"
 		       " relocation symbol.\n", machine->pid);
 
-	if (machine__is_default_guest(machine))
-		guest_kallsyms = (char *) symbol_conf.default_guest_kallsyms;
-	else {
-		sprintf(path, "%s/proc/kallsyms", machine->root_dir);
-		guest_kallsyms = path;
-	}
-
 	/*
 	 * We use _stext for guest kernel because guest kernel's /proc/kallsyms
 	 * have no _text sometimes.
 	 */
-	err = event__synthesize_kernel_mmap(process_synthesized_event,
-					    psession, machine, "_text");
-	if (err < 0)
-		err = event__synthesize_kernel_mmap(process_synthesized_event,
-						    psession, machine, "_stext");
+	err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
+						 machine);
 	if (err < 0)
 		pr_err("Couldn't record guest kernel [%d]'s reference"
 		       " relocation symbol.\n", machine->pid);
@@ -486,179 +236,140 @@ static struct perf_event_header finished_round_event = {
 	.type = PERF_RECORD_FINISHED_ROUND,
 };
 
-static void mmap_read_all(void)
+static int record__mmap_read_all(struct record *rec)
 {
 	int i;
+	int rc = 0;
 
-	for (i = 0; i < nr_cpu; i++) {
-		if (mmap_array[i].base)
-			mmap_read(&mmap_array[i]);
+	for (i = 0; i < rec->evlist->nr_mmaps; i++) {
+		if (rec->evlist->mmap[i].base) {
+			if (record__mmap_read(rec, &rec->evlist->mmap[i]) != 0) {
+				rc = -1;
+				goto out;
+			}
+		}
 	}
 
-	if (perf_header__has_feat(&session->header, HEADER_TRACE_INFO))
-		write_output(&finished_round_event, sizeof(finished_round_event));
+	if (perf_header__has_feat(&rec->session->header, HEADER_TRACING_DATA))
+		rc = record__write(rec, &finished_round_event, sizeof(finished_round_event));
+
+out:
+	return rc;
 }
 
-static int __cmd_record(int argc, const char **argv)
+static void record__init_features(struct record *rec)
+{
+	struct perf_session *session = rec->session;
+	int feat;
+
+	for (feat = HEADER_FIRST_FEATURE; feat < HEADER_LAST_FEATURE; feat++)
+		perf_header__set_feat(&session->header, feat);
+
+	if (rec->no_buildid)
+		perf_header__clear_feat(&session->header, HEADER_BUILD_ID);
+
+	if (!have_tracepoints(&rec->evlist->entries))
+		perf_header__clear_feat(&session->header, HEADER_TRACING_DATA);
+
+	if (!rec->opts.branch_stack)
+		perf_header__clear_feat(&session->header, HEADER_BRANCH_STACK);
+}
+
+static volatile int workload_exec_errno;
+
+/*
+ * perf_evlist__prepare_workload will send a SIGUSR1
+ * if the fork fails, since we asked by setting its
+ * want_signal to true.
+ */
+static void workload_exec_failed_signal(int signo __maybe_unused,
+					siginfo_t *info,
+					void *ucontext __maybe_unused)
+{
+	workload_exec_errno = info->si_value.sival_int;
+	done = 1;
+	child_finished = 1;
+}
+
+static int __cmd_record(struct record *rec, int argc, const char **argv)
 {
-	int i, counter;
-	struct stat st;
-	int flags;
 	int err;
+	int status = 0;
 	unsigned long waking = 0;
-	int child_ready_pipe[2], go_pipe[2];
 	const bool forks = argc > 0;
-	char buf;
 	struct machine *machine;
+	struct perf_tool *tool = &rec->tool;
+	struct record_opts *opts = &rec->opts;
+	struct perf_data_file *file = &rec->file;
+	struct perf_session *session;
+	bool disabled = false;
 
-	page_size = sysconf(_SC_PAGE_SIZE);
+	rec->progname = argv[0];
 
-	atexit(sig_atexit);
+	atexit(record__sig_exit);
 	signal(SIGCHLD, sig_handler);
 	signal(SIGINT, sig_handler);
+	signal(SIGTERM, sig_handler);
 
-	if (forks && (pipe(child_ready_pipe) < 0 || pipe(go_pipe) < 0)) {
-		perror("failed to create pipes");
-		exit(-1);
-	}
-
-	if (!strcmp(output_name, "-"))
-		pipe_output = 1;
-	else if (!stat(output_name, &st) && st.st_size) {
-		if (write_mode == WRITE_FORCE) {
-			char oldname[PATH_MAX];
-			snprintf(oldname, sizeof(oldname), "%s.old",
-				 output_name);
-			unlink(oldname);
-			rename(output_name, oldname);
-		}
-	} else if (write_mode == WRITE_APPEND) {
-		write_mode = WRITE_FORCE;
-	}
-
-	flags = O_CREAT|O_RDWR;
-	if (write_mode == WRITE_APPEND)
-		file_new = 0;
-	else
-		flags |= O_TRUNC;
-
-	if (pipe_output)
-		output = STDOUT_FILENO;
-	else
-		output = open(output_name, flags, S_IRUSR | S_IWUSR);
-	if (output < 0) {
-		perror("failed to create output file");
-		exit(-1);
-	}
-
-	session = perf_session__new(output_name, O_WRONLY,
-				    write_mode == WRITE_FORCE, false);
+	session = perf_session__new(file, false, NULL);
 	if (session == NULL) {
-		pr_err("Not enough memory for reading perf file header\n");
+		pr_err("Perf session creation failed.\n");
 		return -1;
 	}
 
-	if (!file_new) {
-		err = perf_header__read(session, output);
-		if (err < 0)
-			return err;
-	}
+	rec->session = session;
 
-	if (have_tracepoints(attrs, nr_counters))
-		perf_header__set_feat(&session->header, HEADER_TRACE_INFO);
-
-	atexit(atexit_header);
+	record__init_features(rec);
 
 	if (forks) {
-		child_pid = fork();
-		if (child_pid < 0) {
-			perror("failed to fork");
-			exit(-1);
-		}
-
-		if (!child_pid) {
-			if (pipe_output)
-				dup2(2, 1);
-			close(child_ready_pipe[0]);
-			close(go_pipe[1]);
-			fcntl(go_pipe[0], F_SETFD, FD_CLOEXEC);
-
-			/*
-			 * Do a dummy execvp to get the PLT entry resolved,
-			 * so we avoid the resolver overhead on the real
-			 * execvp call.
-			 */
-			execvp("", (char **)argv);
-
-			/*
-			 * Tell the parent we're ready to go
-			 */
-			close(child_ready_pipe[1]);
-
-			/*
-			 * Wait until the parent tells us to go.
-			 */
-			if (read(go_pipe[0], &buf, 1) == -1)
-				perror("unable to read pipe");
-
-			execvp(argv[0], (char **)argv);
-
-			perror(argv[0]);
-			exit(-1);
-		}
-
-		if (!system_wide && target_tid == -1 && target_pid == -1)
-			all_tids[0] = child_pid;
-
-		close(child_ready_pipe[1]);
-		close(go_pipe[0]);
-		/*
-		 * wait for child to settle
-		 */
-		if (read(child_ready_pipe[0], &buf, 1) == -1) {
-			perror("unable to read pipe");
-			exit(-1);
+		err = perf_evlist__prepare_workload(rec->evlist, &opts->target,
+						    argv, file->is_pipe,
+						    workload_exec_failed_signal);
+		if (err < 0) {
+			pr_err("Couldn't run the workload!\n");
+			status = err;
+			goto out_delete_session;
 		}
-		close(child_ready_pipe[0]);
 	}
 
-	if ((!system_wide && no_inherit) || profile_cpu != -1) {
-		open_counters(profile_cpu);
-	} else {
-		nr_cpus = read_cpu_map();
-		for (i = 0; i < nr_cpus; i++)
-			open_counters(cpumap[i]);
+	if (record__open(rec) != 0) {
+		err = -1;
+		goto out_child;
 	}
 
-	if (pipe_output) {
-		err = perf_header__write_pipe(output);
+	if (!rec->evlist->nr_groups)
+		perf_header__clear_feat(&session->header, HEADER_GROUP_DESC);
+
+	if (file->is_pipe) {
+		err = perf_header__write_pipe(file->fd);
 		if (err < 0)
-			return err;
-	} else if (file_new) {
-		err = perf_header__write(&session->header, output, false);
+			goto out_child;
+	} else {
+		err = perf_session__write_header(session, rec->evlist,
+						 file->fd, false);
 		if (err < 0)
-			return err;
+			goto out_child;
 	}
 
-	post_processing_offset = lseek(output, 0, SEEK_CUR);
+	if (!rec->no_buildid
+	    && !perf_header__has_feat(&session->header, HEADER_BUILD_ID)) {
+		pr_err("Couldn't generate buildids. "
+		       "Use --no-buildid to profile anyway.\n");
+		err = -1;
+		goto out_child;
+	}
 
-	if (pipe_output) {
-		err = event__synthesize_attrs(&session->header,
-					      process_synthesized_event,
-					      session);
-		if (err < 0) {
-			pr_err("Couldn't synthesize attrs.\n");
-			return err;
-		}
+	machine = &session->machines.host;
 
-		err = event__synthesize_event_types(process_synthesized_event,
-						    session);
+	if (file->is_pipe) {
+		err = perf_event__synthesize_attrs(tool, session,
+						   process_synthesized_event);
 		if (err < 0) {
-			pr_err("Couldn't synthesize event_types.\n");
-			return err;
+			pr_err("Couldn't synthesize attrs.\n");
+			goto out_child;
 		}
 
-		if (have_tracepoints(attrs, nr_counters)) {
+		if (have_tracepoints(&rec->evlist->entries)) {
 			/*
 			 * FIXME err <= 0 here actually means that
 			 * there were no tracepoints so its not really
@@ -667,230 +378,583 @@ static int __cmd_record(int argc, const char **argv)
 			 * return this more properly and also
 			 * propagate errors that now are calling die()
 			 */
-			err = event__synthesize_tracing_data(output, attrs,
-							     nr_counters,
-							     process_synthesized_event,
-							     session);
+			err = perf_event__synthesize_tracing_data(tool, file->fd, rec->evlist,
+								  process_synthesized_event);
 			if (err <= 0) {
 				pr_err("Couldn't record tracing data.\n");
-				return err;
+				goto out_child;
 			}
-			advance_output(err);
+			rec->bytes_written += err;
 		}
 	}
 
-	machine = perf_session__find_host_machine(session);
-	if (!machine) {
-		pr_err("Couldn't find native kernel information.\n");
-		return -1;
-	}
+	err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
+						 machine);
+	if (err < 0)
+		pr_err("Couldn't record kernel reference relocation symbol\n"
+		       "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
+		       "Check /proc/kallsyms permission or run as root.\n");
 
-	err = event__synthesize_kernel_mmap(process_synthesized_event,
-					    session, machine, "_text");
+	err = perf_event__synthesize_modules(tool, process_synthesized_event,
+					     machine);
 	if (err < 0)
-		err = event__synthesize_kernel_mmap(process_synthesized_event,
-						    session, machine, "_stext");
-	if (err < 0) {
-		pr_err("Couldn't record kernel reference relocation symbol.\n");
-		return err;
-	}
+		pr_err("Couldn't record kernel module information.\n"
+		       "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
+		       "Check /proc/modules permission or run as root.\n");
 
-	err = event__synthesize_modules(process_synthesized_event,
-					session, machine);
-	if (err < 0) {
-		pr_err("Couldn't record kernel reference relocation symbol.\n");
-		return err;
+	if (perf_guest) {
+		machines__process_guests(&session->machines,
+					 perf_event__synthesize_guest_os, tool);
 	}
-	if (perf_guest)
-		perf_session__process_machines(session, event__synthesize_guest_os);
 
-	if (!system_wide && profile_cpu == -1)
-		event__synthesize_thread(target_tid, process_synthesized_event,
-					 session);
-	else
-		event__synthesize_threads(process_synthesized_event, session);
+	err = __machine__synthesize_threads(machine, tool, &opts->target, rec->evlist->threads,
+					    process_synthesized_event, opts->sample_address);
+	if (err != 0)
+		goto out_child;
 
-	if (realtime_prio) {
+	if (rec->realtime_prio) {
 		struct sched_param param;
 
-		param.sched_priority = realtime_prio;
+		param.sched_priority = rec->realtime_prio;
 		if (sched_setscheduler(0, SCHED_FIFO, &param)) {
 			pr_err("Could not set realtime priority.\n");
-			exit(-1);
+			err = -1;
+			goto out_child;
 		}
 	}
 
 	/*
+	 * When perf is starting the traced process, all the events
+	 * (apart from group members) have enable_on_exec=1 set,
+	 * so don't spoil it by prematurely enabling them.
+	 */
+	if (!target__none(&opts->target) && !opts->initial_delay)
+		perf_evlist__enable(rec->evlist);
+
+	/*
 	 * Let the child rip
 	 */
 	if (forks)
-		close(go_pipe[1]);
+		perf_evlist__start_workload(rec->evlist);
+
+	if (opts->initial_delay) {
+		usleep(opts->initial_delay * 1000);
+		perf_evlist__enable(rec->evlist);
+	}
 
 	for (;;) {
-		int hits = samples;
-		int thread;
+		int hits = rec->samples;
 
-		mmap_read_all();
+		if (record__mmap_read_all(rec) < 0) {
+			err = -1;
+			goto out_child;
+		}
 
-		if (hits == samples) {
+		if (hits == rec->samples) {
 			if (done)
 				break;
-			err = poll(event_array, nr_poll, -1);
+			err = poll(rec->evlist->pollfd, rec->evlist->nr_fds, -1);
+			/*
+			 * Propagate error, only if there's any. Ignore positive
+			 * number of returned events and interrupt error.
+			 */
+			if (err > 0 || (err < 0 && errno == EINTR))
+				err = 0;
 			waking++;
 		}
 
-		if (done) {
-			for (i = 0; i < nr_cpu; i++) {
-				for (counter = 0;
-					counter < nr_counters;
-					counter++) {
-					for (thread = 0;
-						thread < thread_num;
-						thread++)
-						ioctl(fd[i][counter][thread],
-							PERF_EVENT_IOC_DISABLE);
-				}
-			}
+		/*
+		 * When perf is starting the traced process, at the end events
+		 * die with the process and we wait for that. Thus no need to
+		 * disable events in this case.
+		 */
+		if (done && !disabled && !target__none(&opts->target)) {
+			perf_evlist__disable(rec->evlist);
+			disabled = true;
 		}
 	}
 
-	fprintf(stderr, "[ perf record: Woken up %ld times to write data ]\n", waking);
+	if (forks && workload_exec_errno) {
+		char msg[512];
+		const char *emsg = strerror_r(workload_exec_errno, msg, sizeof(msg));
+		pr_err("Workload failed: %s\n", emsg);
+		err = -1;
+		goto out_child;
+	}
+
+	if (!quiet) {
+		fprintf(stderr, "[ perf record: Woken up %ld times to write data ]\n", waking);
+
+		/*
+		 * Approximate RIP event size: 24 bytes.
+		 */
+		fprintf(stderr,
+			"[ perf record: Captured and wrote %.3f MB %s (~%" PRIu64 " samples) ]\n",
+			(double)rec->bytes_written / 1024.0 / 1024.0,
+			file->path,
+			rec->bytes_written / 24);
+	}
+
+out_child:
+	if (forks) {
+		int exit_status;
+
+		if (!child_finished)
+			kill(rec->evlist->workload.pid, SIGTERM);
+
+		wait(&exit_status);
+
+		if (err < 0)
+			status = err;
+		else if (WIFEXITED(exit_status))
+			status = WEXITSTATUS(exit_status);
+		else if (WIFSIGNALED(exit_status))
+			signr = WTERMSIG(exit_status);
+	} else
+		status = err;
+
+	if (!err && !file->is_pipe) {
+		rec->session->header.data_size += rec->bytes_written;
+
+		if (!rec->no_buildid)
+			process_buildids(rec);
+		perf_session__write_header(rec->session, rec->evlist,
+					   file->fd, true);
+	}
+
+out_delete_session:
+	perf_session__delete(session);
+	return status;
+}
+
+#define BRANCH_OPT(n, m) \
+	{ .name = n, .mode = (m) }
+
+#define BRANCH_END { .name = NULL }
+
+struct branch_mode {
+	const char *name;
+	int mode;
+};
+
+static const struct branch_mode branch_modes[] = {
+	BRANCH_OPT("u", PERF_SAMPLE_BRANCH_USER),
+	BRANCH_OPT("k", PERF_SAMPLE_BRANCH_KERNEL),
+	BRANCH_OPT("hv", PERF_SAMPLE_BRANCH_HV),
+	BRANCH_OPT("any", PERF_SAMPLE_BRANCH_ANY),
+	BRANCH_OPT("any_call", PERF_SAMPLE_BRANCH_ANY_CALL),
+	BRANCH_OPT("any_ret", PERF_SAMPLE_BRANCH_ANY_RETURN),
+	BRANCH_OPT("ind_call", PERF_SAMPLE_BRANCH_IND_CALL),
+	BRANCH_OPT("abort_tx", PERF_SAMPLE_BRANCH_ABORT_TX),
+	BRANCH_OPT("in_tx", PERF_SAMPLE_BRANCH_IN_TX),
+	BRANCH_OPT("no_tx", PERF_SAMPLE_BRANCH_NO_TX),
+	BRANCH_OPT("cond", PERF_SAMPLE_BRANCH_COND),
+	BRANCH_END
+};
+
+static int
+parse_branch_stack(const struct option *opt, const char *str, int unset)
+{
+#define ONLY_PLM \
+	(PERF_SAMPLE_BRANCH_USER	|\
+	 PERF_SAMPLE_BRANCH_KERNEL	|\
+	 PERF_SAMPLE_BRANCH_HV)
+
+	uint64_t *mode = (uint64_t *)opt->value;
+	const struct branch_mode *br;
+	char *s, *os = NULL, *p;
+	int ret = -1;
+
+	if (unset)
+		return 0;
 
 	/*
-	 * Approximate RIP event size: 24 bytes.
+	 * cannot set it twice, -b + --branch-filter for instance
 	 */
-	fprintf(stderr,
-		"[ perf record: Captured and wrote %.3f MB %s (~%lld samples) ]\n",
-		(double)bytes_written / 1024.0 / 1024.0,
-		output_name,
-		bytes_written / 24);
+	if (*mode)
+		return -1;
+
+	/* str may be NULL in case no arg is passed to -b */
+	if (str) {
+		/* because str is read-only */
+		s = os = strdup(str);
+		if (!s)
+			return -1;
+
+		for (;;) {
+			p = strchr(s, ',');
+			if (p)
+				*p = '\0';
+
+			for (br = branch_modes; br->name; br++) {
+				if (!strcasecmp(s, br->name))
+					break;
+			}
+			if (!br->name) {
+				ui__warning("unknown branch filter %s,"
+					    " check man page\n", s);
+				goto error;
+			}
+
+			*mode |= br->mode;
+
+			if (!p)
+				break;
+
+			s = p + 1;
+		}
+	}
+	ret = 0;
+
+	/* default to any branch */
+	if ((*mode & ~ONLY_PLM) == 0) {
+		*mode = PERF_SAMPLE_BRANCH_ANY;
+	}
+error:
+	free(os);
+	return ret;
+}
 
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
+static int get_stack_size(char *str, unsigned long *_size)
+{
+	char *endptr;
+	unsigned long size;
+	unsigned long max_size = round_down(USHRT_MAX, sizeof(u64));
+
+	size = strtoul(str, &endptr, 0);
+
+	do {
+		if (*endptr)
+			break;
+
+		size = round_up(size, sizeof(u64));
+		if (!size || size > max_size)
+			break;
+
+		*_size = size;
+		return 0;
+
+	} while (0);
+
+	pr_err("callchain: Incorrect stack dump size (max %ld): %s\n",
+	       max_size, str);
+	return -1;
+}
+#endif /* HAVE_DWARF_UNWIND_SUPPORT */
+
+int record_parse_callchain(const char *arg, struct record_opts *opts)
+{
+	char *tok, *name, *saveptr = NULL;
+	char *buf;
+	int ret = -1;
+
+	/* We need buffer that we know we can write to. */
+	buf = malloc(strlen(arg) + 1);
+	if (!buf)
+		return -ENOMEM;
+
+	strcpy(buf, arg);
+
+	tok = strtok_r((char *)buf, ",", &saveptr);
+	name = tok ? : (char *)buf;
+
+	do {
+		/* Framepointer style */
+		if (!strncmp(name, "fp", sizeof("fp"))) {
+			if (!strtok_r(NULL, ",", &saveptr)) {
+				opts->call_graph = CALLCHAIN_FP;
+				ret = 0;
+			} else
+				pr_err("callchain: No more arguments "
+				       "needed for -g fp\n");
+			break;
+
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
+		/* Dwarf style */
+		} else if (!strncmp(name, "dwarf", sizeof("dwarf"))) {
+			const unsigned long default_stack_dump_size = 8192;
+
+			ret = 0;
+			opts->call_graph = CALLCHAIN_DWARF;
+			opts->stack_dump_size = default_stack_dump_size;
+
+			tok = strtok_r(NULL, ",", &saveptr);
+			if (tok) {
+				unsigned long size = 0;
+
+				ret = get_stack_size(tok, &size);
+				opts->stack_dump_size = size;
+			}
+#endif /* HAVE_DWARF_UNWIND_SUPPORT */
+		} else {
+			pr_err("callchain: Unknown --call-graph option "
+			       "value: %s\n", arg);
+			break;
+		}
+
+	} while (0);
+
+	free(buf);
+	return ret;
+}
+
+static void callchain_debug(struct record_opts *opts)
+{
+	static const char *str[CALLCHAIN_MAX] = { "NONE", "FP", "DWARF" };
+
+	pr_debug("callchain: type %s\n", str[opts->call_graph]);
+
+	if (opts->call_graph == CALLCHAIN_DWARF)
+		pr_debug("callchain: stack dump size %d\n",
+			 opts->stack_dump_size);
+}
+
+int record_parse_callchain_opt(const struct option *opt,
+			       const char *arg,
+			       int unset)
+{
+	struct record_opts *opts = opt->value;
+	int ret;
+
+	opts->call_graph_enabled = !unset;
+
+	/* --no-call-graph */
+	if (unset) {
+		opts->call_graph = CALLCHAIN_NONE;
+		pr_debug("callchain: disabled\n");
+		return 0;
+	}
+
+	ret = record_parse_callchain(arg, opts);
+	if (!ret)
+		callchain_debug(opts);
+
+	return ret;
+}
+
+int record_callchain_opt(const struct option *opt,
+			 const char *arg __maybe_unused,
+			 int unset __maybe_unused)
+{
+	struct record_opts *opts = opt->value;
+
+	opts->call_graph_enabled = !unset;
+
+	if (opts->call_graph == CALLCHAIN_NONE)
+		opts->call_graph = CALLCHAIN_FP;
+
+	callchain_debug(opts);
 	return 0;
 }
 
+static int perf_record_config(const char *var, const char *value, void *cb)
+{
+	struct record *rec = cb;
+
+	if (!strcmp(var, "record.call-graph"))
+		return record_parse_callchain(value, &rec->opts);
+
+	return perf_default_config(var, value, cb);
+}
+
 static const char * const record_usage[] = {
 	"perf record [<options>] [<command>]",
 	"perf record [<options>] -- <command> [<options>]",
 	NULL
 };
 
-static bool force, append_file;
+/*
+ * XXX Ideally would be local to cmd_record() and passed to a record__new
+ * because we need to have access to it in record__exit, that is called
+ * after cmd_record() exits, but since record_options need to be accessible to
+ * builtin-script, leave it here.
+ *
+ * At least we don't ouch it in all the other functions here directly.
+ *
+ * Just say no to tons of global variables, sigh.
+ */
+static struct record record = {
+	.opts = {
+		.mmap_pages	     = UINT_MAX,
+		.user_freq	     = UINT_MAX,
+		.user_interval	     = ULLONG_MAX,
+		.freq		     = 4000,
+		.target		     = {
+			.uses_mmap   = true,
+			.default_per_cpu = true,
+		},
+	},
+};
 
-static const struct option options[] = {
-	OPT_CALLBACK('e', "event", NULL, "event",
+#define CALLCHAIN_HELP "setup and enables call-graph (stack chain/backtrace) recording: "
+
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
+const char record_callchain_help[] = CALLCHAIN_HELP "fp dwarf";
+#else
+const char record_callchain_help[] = CALLCHAIN_HELP "fp";
+#endif
+
+/*
+ * XXX Will stay a global variable till we fix builtin-script.c to stop messing
+ * with it and switch to use the library functions in perf_evlist that came
+ * from builtin-record.c, i.e. use record_opts,
+ * perf_evlist__prepare_workload, etc instead of fork+exec'in 'perf record',
+ * using pipes, etc.
+ */
+const struct option record_options[] = {
+	OPT_CALLBACK('e', "event", &record.evlist, "event",
 		     "event selector. use 'perf list' to list available events",
-		     parse_events),
-	OPT_CALLBACK(0, "filter", NULL, "filter",
+		     parse_events_option),
+	OPT_CALLBACK(0, "filter", &record.evlist, "filter",
 		     "event filter", parse_filter),
-	OPT_INTEGER('p', "pid", &target_pid,
+	OPT_STRING('p', "pid", &record.opts.target.pid, "pid",
 		    "record events on existing process id"),
-	OPT_INTEGER('t', "tid", &target_tid,
+	OPT_STRING('t', "tid", &record.opts.target.tid, "tid",
 		    "record events on existing thread id"),
-	OPT_INTEGER('r', "realtime", &realtime_prio,
+	OPT_INTEGER('r', "realtime", &record.realtime_prio,
 		    "collect data with this RT SCHED_FIFO priority"),
-	OPT_BOOLEAN('R', "raw-samples", &raw_samples,
+	OPT_BOOLEAN(0, "no-buffering", &record.opts.no_buffering,
+		    "collect data without buffering"),
+	OPT_BOOLEAN('R', "raw-samples", &record.opts.raw_samples,
 		    "collect raw sample records from all opened counters"),
-	OPT_BOOLEAN('a', "all-cpus", &system_wide,
+	OPT_BOOLEAN('a', "all-cpus", &record.opts.target.system_wide,
 			    "system-wide collection from all CPUs"),
-	OPT_BOOLEAN('A', "append", &append_file,
-			    "append to the output file to do incremental profiling"),
-	OPT_INTEGER('C', "profile_cpu", &profile_cpu,
-			    "CPU to profile on"),
-	OPT_BOOLEAN('f', "force", &force,
-			"overwrite existing data file (deprecated)"),
-	OPT_U64('c', "count", &user_interval, "event period to sample"),
-	OPT_STRING('o', "output", &output_name, "file",
+	OPT_STRING('C', "cpu", &record.opts.target.cpu_list, "cpu",
+		    "list of cpus to monitor"),
+	OPT_U64('c', "count", &record.opts.user_interval, "event period to sample"),
+	OPT_STRING('o', "output", &record.file.path, "file",
 		    "output file name"),
-	OPT_BOOLEAN('i', "no-inherit", &no_inherit,
-		    "child tasks do not inherit counters"),
-	OPT_UINTEGER('F', "freq", &user_freq, "profile at this frequency"),
-	OPT_UINTEGER('m', "mmap-pages", &mmap_pages, "number of mmap data pages"),
-	OPT_BOOLEAN('g', "call-graph", &call_graph,
-		    "do call-graph (stack chain/backtrace) recording"),
+	OPT_BOOLEAN_SET('i', "no-inherit", &record.opts.no_inherit,
+			&record.opts.no_inherit_set,
+			"child tasks do not inherit counters"),
+	OPT_UINTEGER('F', "freq", &record.opts.user_freq, "profile at this frequency"),
+	OPT_CALLBACK('m', "mmap-pages", &record.opts.mmap_pages, "pages",
+		     "number of mmap data pages",
+		     perf_evlist__parse_mmap_pages),
+	OPT_BOOLEAN(0, "group", &record.opts.group,
+		    "put the counters into a counter group"),
+	OPT_CALLBACK_NOOPT('g', NULL, &record.opts,
+			   NULL, "enables call-graph recording" ,
+			   &record_callchain_opt),
+	OPT_CALLBACK(0, "call-graph", &record.opts,
+		     "mode[,dump_size]", record_callchain_help,
+		     &record_parse_callchain_opt),
 	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose (show counter open errors, etc)"),
-	OPT_BOOLEAN('s', "stat", &inherit_stat,
+	OPT_BOOLEAN('q', "quiet", &quiet, "don't print any message"),
+	OPT_BOOLEAN('s', "stat", &record.opts.inherit_stat,
 		    "per thread counts"),
-	OPT_BOOLEAN('d', "data", &sample_address,
+	OPT_BOOLEAN('d', "data", &record.opts.sample_address,
 		    "Sample addresses"),
-	OPT_BOOLEAN('n', "no-samples", &no_samples,
+	OPT_BOOLEAN('T', "timestamp", &record.opts.sample_time, "Sample timestamps"),
+	OPT_BOOLEAN('P', "period", &record.opts.period, "Sample period"),
+	OPT_BOOLEAN('n', "no-samples", &record.opts.no_samples,
 		    "don't sample"),
+	OPT_BOOLEAN('N', "no-buildid-cache", &record.no_buildid_cache,
+		    "do not update the buildid cache"),
+	OPT_BOOLEAN('B', "no-buildid", &record.no_buildid,
+		    "do not collect buildids in perf.data"),
+	OPT_CALLBACK('G', "cgroup", &record.evlist, "name",
+		     "monitor event in cgroup name only",
+		     parse_cgroups),
+	OPT_UINTEGER('D', "delay", &record.opts.initial_delay,
+		  "ms to wait before starting measurement after program start"),
+	OPT_STRING('u', "uid", &record.opts.target.uid_str, "user",
+		   "user to profile"),
+
+	OPT_CALLBACK_NOOPT('b', "branch-any", &record.opts.branch_stack,
+		     "branch any", "sample any taken branches",
+		     parse_branch_stack),
+
+	OPT_CALLBACK('j', "branch-filter", &record.opts.branch_stack,
+		     "branch filter mask", "branch stack filter modes",
+		     parse_branch_stack),
+	OPT_BOOLEAN('W', "weight", &record.opts.sample_weight,
+		    "sample by weight (on special events only)"),
+	OPT_BOOLEAN(0, "transaction", &record.opts.sample_transaction,
+		    "sample transaction flags (special events only)"),
+	OPT_BOOLEAN(0, "per-thread", &record.opts.target.per_thread,
+		    "use per-thread mmaps"),
 	OPT_END()
 };
 
-int cmd_record(int argc, const char **argv, const char *prefix __used)
+int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 {
-	int i,j;
+	int err = -ENOMEM;
+	struct record *rec = &record;
+	char errbuf[BUFSIZ];
+
+	rec->evlist = perf_evlist__new();
+	if (rec->evlist == NULL)
+		return -ENOMEM;
 
-	argc = parse_options(argc, argv, options, record_usage,
+	perf_config(perf_record_config, rec);
+
+	argc = parse_options(argc, argv, record_options, record_usage,
 			    PARSE_OPT_STOP_AT_NON_OPTION);
-	if (!argc && target_pid == -1 && target_tid == -1 &&
-		!system_wide && profile_cpu == -1)
-		usage_with_options(record_usage, options);
-
-	if (force && append_file) {
-		fprintf(stderr, "Can't overwrite and append at the same time."
-				" You need to choose between -f and -A");
-		usage_with_options(record_usage, options);
-	} else if (append_file) {
-		write_mode = WRITE_APPEND;
-	} else {
-		write_mode = WRITE_FORCE;
+	if (!argc && target__none(&rec->opts.target))
+		usage_with_options(record_usage, record_options);
+
+	if (nr_cgroups && !rec->opts.target.system_wide) {
+		ui__error("cgroup monitoring only available in"
+			  " system-wide mode\n");
+		usage_with_options(record_usage, record_options);
 	}
 
 	symbol__init();
 
-	if (!nr_counters) {
-		nr_counters	= 1;
-		attrs[0].type	= PERF_TYPE_HARDWARE;
-		attrs[0].config = PERF_COUNT_HW_CPU_CYCLES;
+	if (symbol_conf.kptr_restrict)
+		pr_warning(
+"WARNING: Kernel address maps (/proc/{kallsyms,modules}) are restricted,\n"
+"check /proc/sys/kernel/kptr_restrict.\n\n"
+"Samples in kernel functions may not be resolved if a suitable vmlinux\n"
+"file is not found in the buildid cache or in the vmlinux path.\n\n"
+"Samples in kernel modules won't be resolved at all.\n\n"
+"If some relocation was applied (e.g. kexec) symbols may be misresolved\n"
+"even with a suitable vmlinux or kallsyms file.\n\n");
+
+	if (rec->no_buildid_cache || rec->no_buildid)
+		disable_buildid_cache();
+
+	if (rec->evlist->nr_entries == 0 &&
+	    perf_evlist__add_default(rec->evlist) < 0) {
+		pr_err("Not enough memory for event selector list\n");
+		goto out_symbol_exit;
 	}
 
-	if (target_pid != -1) {
-		target_tid = target_pid;
-		thread_num = find_all_tid(target_pid, &all_tids);
-		if (thread_num <= 0) {
-			fprintf(stderr, "Can't find all threads of pid %d\n",
-					target_pid);
-			usage_with_options(record_usage, options);
-		}
-	} else {
-		all_tids=malloc(sizeof(pid_t));
-		if (!all_tids)
-			return -ENOMEM;
+	if (rec->opts.target.tid && !rec->opts.no_inherit_set)
+		rec->opts.no_inherit = true;
 
-		all_tids[0] = target_tid;
-		thread_num = 1;
+	err = target__validate(&rec->opts.target);
+	if (err) {
+		target__strerror(&rec->opts.target, err, errbuf, BUFSIZ);
+		ui__warning("%s", errbuf);
 	}
 
-	for (i = 0; i < MAX_NR_CPUS; i++) {
-		for (j = 0; j < MAX_COUNTERS; j++) {
-			fd[i][j] = malloc(sizeof(int)*thread_num);
-			if (!fd[i][j])
-				return -ENOMEM;
-		}
+	err = target__parse_uid(&rec->opts.target);
+	if (err) {
+		int saved_errno = errno;
+
+		target__strerror(&rec->opts.target, err, errbuf, BUFSIZ);
+		ui__error("%s", errbuf);
+
+		err = -saved_errno;
+		goto out_symbol_exit;
 	}
-	event_array = malloc(
-		sizeof(struct pollfd)*MAX_NR_CPUS*MAX_COUNTERS*thread_num);
-	if (!event_array)
-		return -ENOMEM;
 
-	if (user_interval != ULLONG_MAX)
-		default_interval = user_interval;
-	if (user_freq != UINT_MAX)
-		freq = user_freq;
+	err = -ENOMEM;
+	if (perf_evlist__create_maps(rec->evlist, &rec->opts.target) < 0)
+		usage_with_options(record_usage, record_options);
 
-	/*
-	 * User specified count overrides default frequency.
-	 */
-	if (default_interval)
-		freq = 0;
-	else if (freq) {
-		default_interval = freq;
-	} else {
-		fprintf(stderr, "frequency and count are zero, aborting\n");
-		exit(EXIT_FAILURE);
+	if (record_opts__config(&rec->opts)) {
+		err = -EINVAL;
+		goto out_symbol_exit;
 	}
 
-	return __cmd_record(argc, argv);
+	err = __cmd_record(&record, argc, argv);
+out_symbol_exit:
+	perf_evlist__delete(rec->evlist);
+	symbol__exit();
+	return err;
 }
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 35920578296..21d830bafff 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -8,10 +8,11 @@
 #include "builtin.h"
 
 #include "util/util.h"
+#include "util/cache.h"
 
+#include "util/annotate.h"
 #include "util/color.h"
 #include <linux/list.h>
-#include "util/cache.h"
 #include <linux/rbtree.h>
 #include "util/symbol.h"
 #include "util/callchain.h"
@@ -20,8 +21,11 @@
 
 #include "perf.h"
 #include "util/debug.h"
+#include "util/evlist.h"
+#include "util/evsel.h"
 #include "util/header.h"
 #include "util/session.h"
+#include "util/tool.h"
 
 #include "util/parse-options.h"
 #include "util/parse-events.h"
@@ -29,422 +33,558 @@
 #include "util/thread.h"
 #include "util/sort.h"
 #include "util/hist.h"
+#include "util/data.h"
+#include "arch/common.h"
+
+#include <dlfcn.h>
+#include <linux/bitmap.h>
+
+struct report {
+	struct perf_tool	tool;
+	struct perf_session	*session;
+	bool			force, use_tui, use_gtk, use_stdio;
+	bool			hide_unresolved;
+	bool			dont_use_callchains;
+	bool			show_full_info;
+	bool			show_threads;
+	bool			inverted_callchain;
+	bool			mem_mode;
+	bool			header;
+	bool			header_only;
+	int			max_stack;
+	struct perf_read_values	show_threads_values;
+	const char		*pretty_printing_style;
+	const char		*cpu_list;
+	const char		*symbol_filter_str;
+	float			min_percent;
+	u64			nr_entries;
+	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
+};
 
-static char		const *input_name = "perf.data";
-
-static bool		force;
-static bool		hide_unresolved;
-static bool		dont_use_callchains;
-
-static bool		show_threads;
-static struct perf_read_values	show_threads_values;
-
-static const char	default_pretty_printing_style[] = "normal";
-static const char	*pretty_printing_style = default_pretty_printing_style;
-
-static char		callchain_default_opt[] = "fractal,0.5";
-
-static struct hists *perf_session__hists_findnew(struct perf_session *self,
-						 u64 event_stream, u32 type,
-						 u64 config)
+static int report__config(const char *var, const char *value, void *cb)
 {
-	struct rb_node **p = &self->hists_tree.rb_node;
-	struct rb_node *parent = NULL;
-	struct hists *iter, *new;
-
-	while (*p != NULL) {
-		parent = *p;
-		iter = rb_entry(parent, struct hists, rb_node);
-		if (iter->config == config)
-			return iter;
-
-
-		if (config > iter->config)
-			p = &(*p)->rb_right;
-		else
-			p = &(*p)->rb_left;
+	if (!strcmp(var, "report.group")) {
+		symbol_conf.event_group = perf_config_bool(var, value);
+		return 0;
 	}
-
-	new = malloc(sizeof(struct hists));
-	if (new == NULL)
-		return NULL;
-	memset(new, 0, sizeof(struct hists));
-	new->event_stream = event_stream;
-	new->config = config;
-	new->type = type;
-	rb_link_node(&new->rb_node, parent, p);
-	rb_insert_color(&new->rb_node, &self->hists_tree);
-	return new;
-}
-
-static int perf_session__add_hist_entry(struct perf_session *self,
-					struct addr_location *al,
-					struct sample_data *data)
-{
-	struct map_symbol *syms = NULL;
-	struct symbol *parent = NULL;
-	int err = -ENOMEM;
-	struct hist_entry *he;
-	struct hists *hists;
-	struct perf_event_attr *attr;
-
-	if ((sort__has_parent || symbol_conf.use_callchain) && data->callchain) {
-		syms = perf_session__resolve_callchain(self, al->thread,
-						       data->callchain, &parent);
-		if (syms == NULL)
-			return -ENOMEM;
+	if (!strcmp(var, "report.percent-limit")) {
+		struct report *rep = cb;
+		rep->min_percent = strtof(value, NULL);
+		return 0;
 	}
-
-	attr = perf_header__find_attr(data->id, &self->header);
-	if (attr)
-		hists = perf_session__hists_findnew(self, data->id, attr->type, attr->config);
-	else
-		hists = perf_session__hists_findnew(self, data->id, 0, 0);
-	if (hists == NULL)
-		goto out_free_syms;
-	he = __hists__add_entry(hists, al, parent, data->period);
-	if (he == NULL)
-		goto out_free_syms;
-	err = 0;
-	if (symbol_conf.use_callchain) {
-		err = append_chain(he->callchain, data->callchain, syms);
-		if (err)
-			goto out_free_syms;
+	if (!strcmp(var, "report.children")) {
+		symbol_conf.cumulate_callchain = perf_config_bool(var, value);
+		return 0;
 	}
-	/*
-	 * Only in the newt browser we are doing integrated annotation,
-	 * so we don't allocated the extra space needed because the stdio
-	 * code will not use it.
-	 */
-	if (use_browser > 0)
-		err = hist_entry__inc_addr_samples(he, al->addr);
-out_free_syms:
-	free(syms);
-	return err;
+
+	return perf_default_config(var, value, cb);
 }
 
-static int add_event_total(struct perf_session *session,
-			   struct sample_data *data,
-			   struct perf_event_attr *attr)
+static void report__inc_stats(struct report *rep, struct hist_entry *he)
 {
-	struct hists *hists;
-
-	if (attr)
-		hists = perf_session__hists_findnew(session, data->id,
-						    attr->type, attr->config);
-	else
-		hists = perf_session__hists_findnew(session, data->id, 0, 0);
-
-	if (!hists)
-		return -ENOMEM;
-
-	hists->stats.total_period += data->period;
 	/*
-	 * FIXME: add_event_total should be moved from here to
-	 * perf_session__process_event so that the proper hist is passed to
-	 * the event_op methods.
+	 * The @he is either of a newly created one or an existing one
+	 * merging current sample.  We only want to count a new one so
+	 * checking ->nr_events being 1.
 	 */
-	hists__inc_nr_events(hists, PERF_RECORD_SAMPLE);
-	session->hists.stats.total_period += data->period;
-	return 0;
+	if (he->stat.nr_events == 1)
+		rep->nr_entries++;
 }
 
-static int process_sample_event(event_t *event, struct perf_session *session)
+static int hist_iter__report_callback(struct hist_entry_iter *iter,
+				      struct addr_location *al, bool single,
+				      void *arg)
 {
-	struct sample_data data = { .period = 1, };
-	struct addr_location al;
-	struct perf_event_attr *attr;
+	int err = 0;
+	struct report *rep = arg;
+	struct hist_entry *he = iter->he;
+	struct perf_evsel *evsel = iter->evsel;
+	struct mem_info *mi;
+	struct branch_info *bi;
 
-	event__parse_sample(event, session->sample_type, &data);
+	report__inc_stats(rep, he);
 
-	dump_printf("(IP, %d): %d/%d: %#Lx period: %Ld\n", event->header.misc,
-		    data.pid, data.tid, data.ip, data.period);
+	if (!ui__has_annotation())
+		return 0;
 
-	if (session->sample_type & PERF_SAMPLE_CALLCHAIN) {
-		unsigned int i;
+	if (sort__mode == SORT_MODE__BRANCH) {
+		bi = he->branch_info;
+		err = addr_map_symbol__inc_samples(&bi->from, evsel->idx);
+		if (err)
+			goto out;
 
-		dump_printf("... chain: nr:%Lu\n", data.callchain->nr);
+		err = addr_map_symbol__inc_samples(&bi->to, evsel->idx);
 
-		if (!ip_callchain__valid(data.callchain, event)) {
-			pr_debug("call-chain problem with event, "
-				 "skipping it.\n");
-			return 0;
-		}
+	} else if (rep->mem_mode) {
+		mi = he->mem_info;
+		err = addr_map_symbol__inc_samples(&mi->daddr, evsel->idx);
+		if (err)
+			goto out;
 
-		if (dump_trace) {
-			for (i = 0; i < data.callchain->nr; i++)
-				dump_printf("..... %2d: %016Lx\n",
-					    i, data.callchain->ips[i]);
-		}
+		err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
+
+	} else if (symbol_conf.cumulate_callchain) {
+		if (single)
+			err = hist_entry__inc_addr_samples(he, evsel->idx,
+							   al->addr);
+	} else {
+		err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
 	}
 
-	if (event__preprocess_sample(event, session, &al, NULL) < 0) {
-		fprintf(stderr, "problem processing %d event, skipping it.\n",
-			event->header.type);
+out:
+	return err;
+}
+
+static int process_sample_event(struct perf_tool *tool,
+				union perf_event *event,
+				struct perf_sample *sample,
+				struct perf_evsel *evsel,
+				struct machine *machine)
+{
+	struct report *rep = container_of(tool, struct report, tool);
+	struct addr_location al;
+	struct hist_entry_iter iter = {
+		.hide_unresolved = rep->hide_unresolved,
+		.add_entry_cb = hist_iter__report_callback,
+	};
+	int ret;
+
+	if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
+		pr_debug("problem processing %d event, skipping it.\n",
+			 event->header.type);
 		return -1;
 	}
 
-	if (al.filtered || (hide_unresolved && al.sym == NULL))
+	if (rep->hide_unresolved && al.sym == NULL)
 		return 0;
 
-	if (perf_session__add_hist_entry(session, &al, &data)) {
-		pr_debug("problem incrementing symbol period, skipping event\n");
-		return -1;
-	}
+	if (rep->cpu_list && !test_bit(sample->cpu, rep->cpu_bitmap))
+		return 0;
 
-	attr = perf_header__find_attr(data.id, &session->header);
+	if (sort__mode == SORT_MODE__BRANCH)
+		iter.ops = &hist_iter_branch;
+	else if (rep->mem_mode)
+		iter.ops = &hist_iter_mem;
+	else if (symbol_conf.cumulate_callchain)
+		iter.ops = &hist_iter_cumulative;
+	else
+		iter.ops = &hist_iter_normal;
 
-	if (add_event_total(session, &data, attr)) {
-		pr_debug("problem adding event period\n");
-		return -1;
-	}
+	if (al.map != NULL)
+		al.map->dso->hit = 1;
 
-	return 0;
+	ret = hist_entry_iter__add(&iter, &al, evsel, sample, rep->max_stack,
+				   rep);
+	if (ret < 0)
+		pr_debug("problem adding hist entry, skipping event\n");
+
+	return ret;
 }
 
-static int process_read_event(event_t *event, struct perf_session *session __used)
+static int process_read_event(struct perf_tool *tool,
+			      union perf_event *event,
+			      struct perf_sample *sample __maybe_unused,
+			      struct perf_evsel *evsel,
+			      struct machine *machine __maybe_unused)
 {
-	struct perf_event_attr *attr;
-
-	attr = perf_header__find_attr(event->read.id, &session->header);
+	struct report *rep = container_of(tool, struct report, tool);
 
-	if (show_threads) {
-		const char *name = attr ? __event_name(attr->type, attr->config)
-				   : "unknown";
-		perf_read_values_add_value(&show_threads_values,
+	if (rep->show_threads) {
+		const char *name = evsel ? perf_evsel__name(evsel) : "unknown";
+		perf_read_values_add_value(&rep->show_threads_values,
 					   event->read.pid, event->read.tid,
 					   event->read.id,
 					   name,
 					   event->read.value);
 	}
 
-	dump_printf(": %d %d %s %Lu\n", event->read.pid, event->read.tid,
-		    attr ? __event_name(attr->type, attr->config) : "FAIL",
+	dump_printf(": %d %d %s %" PRIu64 "\n", event->read.pid, event->read.tid,
+		    evsel ? perf_evsel__name(evsel) : "FAIL",
 		    event->read.value);
 
 	return 0;
 }
 
-static int perf_session__setup_sample_type(struct perf_session *self)
+/* For pipe mode, sample_type is not currently set */
+static int report__setup_sample_type(struct report *rep)
 {
-	if (!(self->sample_type & PERF_SAMPLE_CALLCHAIN)) {
+	struct perf_session *session = rep->session;
+	u64 sample_type = perf_evlist__combined_sample_type(session->evlist);
+	bool is_pipe = perf_data_file__is_pipe(session->file);
+
+	if (!is_pipe && !(sample_type & PERF_SAMPLE_CALLCHAIN)) {
 		if (sort__has_parent) {
-			fprintf(stderr, "selected --sort parent, but no"
-					" callchain data. Did you call"
-					" perf record without -g?\n");
+			ui__error("Selected --sort parent, but no "
+				    "callchain data. Did you call "
+				    "'perf record' without -g?\n");
 			return -EINVAL;
 		}
 		if (symbol_conf.use_callchain) {
-			fprintf(stderr, "selected -g but no callchain data."
-					" Did you call perf record without"
-					" -g?\n");
+			ui__error("Selected -g but no callchain data. Did "
+				    "you call 'perf record' without -g?\n");
 			return -1;
 		}
-	} else if (!dont_use_callchains && callchain_param.mode != CHAIN_NONE &&
+	} else if (!rep->dont_use_callchains &&
+		   callchain_param.mode != CHAIN_NONE &&
 		   !symbol_conf.use_callchain) {
 			symbol_conf.use_callchain = true;
-			if (register_callchain_param(&callchain_param) < 0) {
-				fprintf(stderr, "Can't register callchain"
-						" params\n");
+			if (callchain_register_param(&callchain_param) < 0) {
+				ui__error("Can't register callchain params.\n");
 				return -EINVAL;
 			}
 	}
 
-	return 0;
-}
+	if (symbol_conf.cumulate_callchain) {
+		/* Silently ignore if callchain is missing */
+		if (!(sample_type & PERF_SAMPLE_CALLCHAIN)) {
+			symbol_conf.cumulate_callchain = false;
+			perf_hpp__cancel_cumulate();
+		}
+	}
 
-static struct perf_event_ops event_ops = {
-	.sample	= process_sample_event,
-	.mmap	= event__process_mmap,
-	.comm	= event__process_comm,
-	.exit	= event__process_task,
-	.fork	= event__process_task,
-	.lost	= event__process_lost,
-	.read	= process_read_event,
-	.attr	= event__process_attr,
-	.event_type = event__process_event_type,
-	.tracing_data = event__process_tracing_data,
-	.build_id = event__process_build_id,
-};
+	if (sort__mode == SORT_MODE__BRANCH) {
+		if (!is_pipe &&
+		    !(sample_type & PERF_SAMPLE_BRANCH_STACK)) {
+			ui__error("Selected -b but no branch data. "
+				  "Did you call perf record without -b?\n");
+			return -1;
+		}
+	}
 
-extern volatile int session_done;
+	return 0;
+}
 
-static void sig_handler(int sig __used)
+static void sig_handler(int sig __maybe_unused)
 {
 	session_done = 1;
 }
 
-static size_t hists__fprintf_nr_sample_events(struct hists *self,
+static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report *rep,
 					      const char *evname, FILE *fp)
 {
 	size_t ret;
 	char unit;
-	unsigned long nr_events = self->stats.nr_events[PERF_RECORD_SAMPLE];
+	unsigned long nr_samples = hists->stats.nr_events[PERF_RECORD_SAMPLE];
+	u64 nr_events = hists->stats.total_period;
+	struct perf_evsel *evsel = hists_to_evsel(hists);
+	char buf[512];
+	size_t size = sizeof(buf);
+
+	if (symbol_conf.filter_relative) {
+		nr_samples = hists->stats.nr_non_filtered_samples;
+		nr_events = hists->stats.total_non_filtered_period;
+	}
+
+	if (perf_evsel__is_group_event(evsel)) {
+		struct perf_evsel *pos;
+
+		perf_evsel__group_desc(evsel, buf, size);
+		evname = buf;
+
+		for_each_group_member(pos, evsel) {
+			if (symbol_conf.filter_relative) {
+				nr_samples += pos->hists.stats.nr_non_filtered_samples;
+				nr_events += pos->hists.stats.total_non_filtered_period;
+			} else {
+				nr_samples += pos->hists.stats.nr_events[PERF_RECORD_SAMPLE];
+				nr_events += pos->hists.stats.total_period;
+			}
+		}
+	}
 
-	nr_events = convert_unit(nr_events, &unit);
-	ret = fprintf(fp, "# Events: %lu%c", nr_events, unit);
+	nr_samples = convert_unit(nr_samples, &unit);
+	ret = fprintf(fp, "# Samples: %lu%c", nr_samples, unit);
 	if (evname != NULL)
-		ret += fprintf(fp, " %s", evname);
+		ret += fprintf(fp, " of event '%s'", evname);
+
+	if (rep->mem_mode) {
+		ret += fprintf(fp, "\n# Total weight : %" PRIu64, nr_events);
+		ret += fprintf(fp, "\n# Sort order   : %s", sort_order);
+	} else
+		ret += fprintf(fp, "\n# Event count (approx.): %" PRIu64, nr_events);
 	return ret + fprintf(fp, "\n#\n");
 }
 
-static int hists__tty_browse_tree(struct rb_root *tree, const char *help)
+static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
+					 struct report *rep,
+					 const char *help)
 {
-	struct rb_node *next = rb_first(tree);
+	struct perf_evsel *pos;
 
-	while (next) {
-		struct hists *hists = rb_entry(next, struct hists, rb_node);
-		const char *evname = NULL;
+	evlist__for_each(evlist, pos) {
+		struct hists *hists = &pos->hists;
+		const char *evname = perf_evsel__name(pos);
 
-		if (rb_first(&hists->entries) != rb_last(&hists->entries))
-			evname = __event_name(hists->type, hists->config);
+		if (symbol_conf.event_group &&
+		    !perf_evsel__is_group_leader(pos))
+			continue;
 
-		hists__fprintf_nr_sample_events(hists, evname, stdout);
-		hists__fprintf(hists, NULL, false, stdout);
+		hists__fprintf_nr_sample_events(hists, rep, evname, stdout);
+		hists__fprintf(hists, true, 0, 0, rep->min_percent, stdout);
 		fprintf(stdout, "\n\n");
-		next = rb_next(&hists->rb_node);
 	}
 
 	if (sort_order == default_sort_order &&
 	    parent_pattern == default_parent_pattern) {
 		fprintf(stdout, "#\n# (%s)\n#\n", help);
 
-		if (show_threads) {
-			bool style = !strcmp(pretty_printing_style, "raw");
-			perf_read_values_display(stdout, &show_threads_values,
+		if (rep->show_threads) {
+			bool style = !strcmp(rep->pretty_printing_style, "raw");
+			perf_read_values_display(stdout, &rep->show_threads_values,
 						 style);
-			perf_read_values_destroy(&show_threads_values);
+			perf_read_values_destroy(&rep->show_threads_values);
 		}
 	}
 
 	return 0;
 }
 
-static int __cmd_report(void)
+static void report__warn_kptr_restrict(const struct report *rep)
 {
-	int ret = -EINVAL;
-	struct perf_session *session;
-	struct rb_node *next;
+	struct map *kernel_map = rep->session->machines.host.vmlinux_maps[MAP__FUNCTION];
+	struct kmap *kernel_kmap = map__kmap(kernel_map);
+
+	if (kernel_map == NULL ||
+	    (kernel_map->dso->hit &&
+	     (kernel_kmap->ref_reloc_sym == NULL ||
+	      kernel_kmap->ref_reloc_sym->addr == 0))) {
+		const char *desc =
+		    "As no suitable kallsyms nor vmlinux was found, kernel samples\n"
+		    "can't be resolved.";
+
+		if (kernel_map) {
+			const struct dso *kdso = kernel_map->dso;
+			if (!RB_EMPTY_ROOT(&kdso->symbols[MAP__FUNCTION])) {
+				desc = "If some relocation was applied (e.g. "
+				       "kexec) symbols may be misresolved.";
+			}
+		}
+
+		ui__warning(
+"Kernel address maps (/proc/{kallsyms,modules}) were restricted.\n\n"
+"Check /proc/sys/kernel/kptr_restrict before running 'perf record'.\n\n%s\n\n"
+"Samples in kernel modules can't be resolved as well.\n\n",
+		desc);
+	}
+}
+
+static int report__gtk_browse_hists(struct report *rep, const char *help)
+{
+	int (*hist_browser)(struct perf_evlist *evlist, const char *help,
+			    struct hist_browser_timer *timer, float min_pcnt);
+
+	hist_browser = dlsym(perf_gtk_handle, "perf_evlist__gtk_browse_hists");
+
+	if (hist_browser == NULL) {
+		ui__error("GTK browser not found!\n");
+		return -1;
+	}
+
+	return hist_browser(rep->session->evlist, help, NULL, rep->min_percent);
+}
+
+static int report__browse_hists(struct report *rep)
+{
+	int ret;
+	struct perf_session *session = rep->session;
+	struct perf_evlist *evlist = session->evlist;
 	const char *help = "For a higher level overview, try: perf report --sort comm,dso";
 
+	switch (use_browser) {
+	case 1:
+		ret = perf_evlist__tui_browse_hists(evlist, help, NULL,
+						    rep->min_percent,
+						    &session->header.env);
+		/*
+		 * Usually "ret" is the last pressed key, and we only
+		 * care if the key notifies us to switch data file.
+		 */
+		if (ret != K_SWITCH_INPUT_DATA)
+			ret = 0;
+		break;
+	case 2:
+		ret = report__gtk_browse_hists(rep, help);
+		break;
+	default:
+		ret = perf_evlist__tty_browse_hists(evlist, rep, help);
+		break;
+	}
+
+	return ret;
+}
+
+static void report__collapse_hists(struct report *rep)
+{
+	struct ui_progress prog;
+	struct perf_evsel *pos;
+
+	ui_progress__init(&prog, rep->nr_entries, "Merging related events...");
+
+	evlist__for_each(rep->session->evlist, pos) {
+		struct hists *hists = &pos->hists;
+
+		if (pos->idx == 0)
+			hists->symbol_filter_str = rep->symbol_filter_str;
+
+		hists__collapse_resort(hists, &prog);
+
+		/* Non-group events are considered as leader */
+		if (symbol_conf.event_group &&
+		    !perf_evsel__is_group_leader(pos)) {
+			struct hists *leader_hists = &pos->leader->hists;
+
+			hists__match(leader_hists, hists);
+			hists__link(leader_hists, hists);
+		}
+	}
+
+	ui_progress__finish();
+}
+
+static int __cmd_report(struct report *rep)
+{
+	int ret;
+	struct perf_session *session = rep->session;
+	struct perf_evsel *pos;
+	struct perf_data_file *file = session->file;
+
 	signal(SIGINT, sig_handler);
 
-	session = perf_session__new(input_name, O_RDONLY, force, false);
-	if (session == NULL)
-		return -ENOMEM;
+	if (rep->cpu_list) {
+		ret = perf_session__cpu_bitmap(session, rep->cpu_list,
+					       rep->cpu_bitmap);
+		if (ret)
+			return ret;
+	}
 
-	if (show_threads)
-		perf_read_values_init(&show_threads_values);
+	if (rep->show_threads)
+		perf_read_values_init(&rep->show_threads_values);
 
-	ret = perf_session__setup_sample_type(session);
+	ret = report__setup_sample_type(rep);
 	if (ret)
-		goto out_delete;
+		return ret;
 
-	ret = perf_session__process_events(session, &event_ops);
+	ret = perf_session__process_events(session, &rep->tool);
 	if (ret)
-		goto out_delete;
+		return ret;
 
-	if (dump_trace) {
-		perf_session__fprintf_nr_events(session, stdout);
-		goto out_delete;
-	}
+	report__warn_kptr_restrict(rep);
+
+	if (use_browser == 0) {
+		if (verbose > 3)
+			perf_session__fprintf(session, stdout);
+
+		if (verbose > 2)
+			perf_session__fprintf_dsos(session, stdout);
 
-	if (verbose > 3)
-		perf_session__fprintf(session, stdout);
+		if (dump_trace) {
+			perf_session__fprintf_nr_events(session, stdout);
+			return 0;
+		}
+	}
 
-	if (verbose > 2)
-		perf_session__fprintf_dsos(session, stdout);
+	report__collapse_hists(rep);
 
-	next = rb_first(&session->hists_tree);
-	while (next) {
-		struct hists *hists;
+	if (session_done())
+		return 0;
 
-		hists = rb_entry(next, struct hists, rb_node);
-		hists__collapse_resort(hists);
-		hists__output_resort(hists);
-		next = rb_next(&hists->rb_node);
+	if (rep->nr_entries == 0) {
+		ui__error("The %s file has no samples!\n", file->path);
+		return 0;
 	}
 
-	if (use_browser > 0)
-		hists__tui_browse_tree(&session->hists_tree, help);
-	else
-		hists__tty_browse_tree(&session->hists_tree, help);
+	evlist__for_each(session->evlist, pos)
+		hists__output_resort(&pos->hists);
 
-out_delete:
-	perf_session__delete(session);
-	return ret;
+	return report__browse_hists(rep);
 }
 
 static int
-parse_callchain_opt(const struct option *opt __used, const char *arg,
-		    int unset)
+report_parse_callchain_opt(const struct option *opt, const char *arg, int unset)
 {
-	char *tok, *tok2;
-	char *endptr;
+	struct report *rep = (struct report *)opt->value;
 
 	/*
 	 * --no-call-graph
 	 */
 	if (unset) {
-		dont_use_callchains = true;
+		rep->dont_use_callchains = true;
 		return 0;
 	}
 
-	symbol_conf.use_callchain = true;
-
-	if (!arg)
-		return 0;
-
-	tok = strtok((char *)arg, ",");
-	if (!tok)
-		return -1;
-
-	/* get the output mode */
-	if (!strncmp(tok, "graph", strlen(arg)))
-		callchain_param.mode = CHAIN_GRAPH_ABS;
-
-	else if (!strncmp(tok, "flat", strlen(arg)))
-		callchain_param.mode = CHAIN_FLAT;
-
-	else if (!strncmp(tok, "fractal", strlen(arg)))
-		callchain_param.mode = CHAIN_GRAPH_REL;
-
-	else if (!strncmp(tok, "none", strlen(arg))) {
-		callchain_param.mode = CHAIN_NONE;
-		symbol_conf.use_callchain = false;
+	return parse_callchain_report_opt(arg);
+}
 
-		return 0;
+int
+report_parse_ignore_callees_opt(const struct option *opt __maybe_unused,
+				const char *arg, int unset __maybe_unused)
+{
+	if (arg) {
+		int err = regcomp(&ignore_callees_regex, arg, REG_EXTENDED);
+		if (err) {
+			char buf[BUFSIZ];
+			regerror(err, &ignore_callees_regex, buf, sizeof(buf));
+			pr_err("Invalid --ignore-callees regex: %s\n%s", arg, buf);
+			return -1;
+		}
+		have_ignore_callees = 1;
 	}
 
-	else
-		return -1;
-
-	/* get the min percentage */
-	tok = strtok(NULL, ",");
-	if (!tok)
-		goto setup;
+	return 0;
+}
 
-	tok2 = strtok(NULL, ",");
-	callchain_param.min_percent = strtod(tok, &endptr);
-	if (tok == endptr)
-		return -1;
+static int
+parse_branch_mode(const struct option *opt __maybe_unused,
+		  const char *str __maybe_unused, int unset)
+{
+	int *branch_mode = opt->value;
 
-	if (tok2)
-		callchain_param.print_limit = strtod(tok2, &endptr);
-setup:
-	if (register_callchain_param(&callchain_param) < 0) {
-		fprintf(stderr, "Can't register callchain params\n");
-		return -1;
-	}
+	*branch_mode = !unset;
 	return 0;
 }
 
-static const char * const report_usage[] = {
-	"perf report [<options>] <command>",
-	NULL
-};
+static int
+parse_percent_limit(const struct option *opt, const char *str,
+		    int unset __maybe_unused)
+{
+	struct report *rep = opt->value;
+
+	rep->min_percent = strtof(str, NULL);
+	return 0;
+}
 
-static const struct option options[] = {
+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[] = {
+		"perf report [<options>]",
+		NULL
+	};
+	struct report report = {
+		.tool = {
+			.sample		 = process_sample_event,
+			.mmap		 = perf_event__process_mmap,
+			.mmap2		 = perf_event__process_mmap2,
+			.comm		 = perf_event__process_comm,
+			.exit		 = perf_event__process_exit,
+			.fork		 = perf_event__process_fork,
+			.lost		 = perf_event__process_lost,
+			.read		 = process_read_event,
+			.attr		 = perf_event__process_attr,
+			.tracing_data	 = perf_event__process_tracing_data,
+			.build_id	 = perf_event__process_build_id,
+			.ordered_samples = true,
+			.ordering_requires_timestamps = true,
+		},
+		.max_stack		 = PERF_MAX_STACK_DEPTH,
+		.pretty_printing_style	 = "normal",
+	};
+	const struct option options[] = {
 	OPT_STRING('i', "input", &input_name, "file",
 		    "input file name"),
 	OPT_INCR('v', "verbose", &verbose,
@@ -453,80 +593,224 @@ static const struct option options[] = {
 		    "dump raw trace in ASCII"),
 	OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
 		   "file", "vmlinux pathname"),
-	OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
+	OPT_STRING(0, "kallsyms", &symbol_conf.kallsyms_name,
+		   "file", "kallsyms pathname"),
+	OPT_BOOLEAN('f', "force", &report.force, "don't complain, do it"),
 	OPT_BOOLEAN('m', "modules", &symbol_conf.use_modules,
 		    "load module symbols - WARNING: use only with -k and LIVE kernel"),
 	OPT_BOOLEAN('n', "show-nr-samples", &symbol_conf.show_nr_samples,
 		    "Show a column with the number of samples"),
-	OPT_BOOLEAN('T', "threads", &show_threads,
+	OPT_BOOLEAN('T', "threads", &report.show_threads,
 		    "Show per-thread event counters"),
-	OPT_STRING(0, "pretty", &pretty_printing_style, "key",
+	OPT_STRING(0, "pretty", &report.pretty_printing_style, "key",
 		   "pretty printing style key: normal raw"),
+	OPT_BOOLEAN(0, "tui", &report.use_tui, "Use the TUI interface"),
+	OPT_BOOLEAN(0, "gtk", &report.use_gtk, "Use the GTK2 interface"),
+	OPT_BOOLEAN(0, "stdio", &report.use_stdio,
+		    "Use the stdio interface"),
+	OPT_BOOLEAN(0, "header", &report.header, "Show data header."),
+	OPT_BOOLEAN(0, "header-only", &report.header_only,
+		    "Show only data header."),
 	OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
-		   "sort by key(s): pid, comm, dso, symbol, parent"),
-	OPT_BOOLEAN('P', "full-paths", &symbol_conf.full_paths,
-		    "Don't shorten the pathnames taking into account the cwd"),
+		   "sort by key(s): pid, comm, dso, symbol, parent, cpu, srcline, ..."
+		   " Please refer the man page for the complete list."),
+	OPT_STRING('F', "fields", &field_order, "key[,keys...]",
+		   "output field(s): overhead, period, sample plus all of sort keys"),
 	OPT_BOOLEAN(0, "showcpuutilization", &symbol_conf.show_cpu_utilization,
 		    "Show sample percentage for different cpu modes"),
 	OPT_STRING('p', "parent", &parent_pattern, "regex",
 		   "regex filter to identify parent, see: '--sort parent'"),
 	OPT_BOOLEAN('x', "exclude-other", &symbol_conf.exclude_other,
 		    "Only display entries with parent-match"),
-	OPT_CALLBACK_DEFAULT('g', "call-graph", NULL, "output_type,min_percent",
-		     "Display callchains using output_type (graph, flat, fractal, or none) and min percent threshold. "
-		     "Default: fractal,0.5", &parse_callchain_opt, callchain_default_opt),
+	OPT_CALLBACK_DEFAULT('g', "call-graph", &report, "output_type,min_percent[,print_limit],call_order",
+		     "Display callchains using output_type (graph, flat, fractal, or none) , min percent threshold, optional print limit, callchain order, key (function or address). "
+		     "Default: fractal,0.5,callee,function", &report_parse_callchain_opt, callchain_default_opt),
+	OPT_BOOLEAN(0, "children", &symbol_conf.cumulate_callchain,
+		    "Accumulate callchains of children and show total overhead as well"),
+	OPT_INTEGER(0, "max-stack", &report.max_stack,
+		    "Set the maximum stack depth when parsing the callchain, "
+		    "anything beyond the specified depth will be ignored. "
+		    "Default: " __stringify(PERF_MAX_STACK_DEPTH)),
+	OPT_BOOLEAN('G', "inverted", &report.inverted_callchain,
+		    "alias for inverted call graph"),
+	OPT_CALLBACK(0, "ignore-callees", NULL, "regex",
+		   "ignore callees of these functions in call graphs",
+		   report_parse_ignore_callees_opt),
 	OPT_STRING('d', "dsos", &symbol_conf.dso_list_str, "dso[,dso...]",
 		   "only consider symbols in these dsos"),
-	OPT_STRING('C', "comms", &symbol_conf.comm_list_str, "comm[,comm...]",
+	OPT_STRING('c', "comms", &symbol_conf.comm_list_str, "comm[,comm...]",
 		   "only consider symbols in these comms"),
 	OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]",
 		   "only consider these symbols"),
+	OPT_STRING(0, "symbol-filter", &report.symbol_filter_str, "filter",
+		   "only show symbols that (partially) match with this filter"),
 	OPT_STRING('w', "column-widths", &symbol_conf.col_width_list_str,
 		   "width[,width...]",
 		   "don't try to adjust column width, use these fixed values"),
 	OPT_STRING('t', "field-separator", &symbol_conf.field_sep, "separator",
 		   "separator for columns, no spaces will be added between "
 		   "columns '.' is reserved."),
-	OPT_BOOLEAN('U', "hide-unresolved", &hide_unresolved,
+	OPT_BOOLEAN('U', "hide-unresolved", &report.hide_unresolved,
 		    "Only display entries resolved to a symbol"),
+	OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
+		    "Look for files with symbols relative to this directory"),
+	OPT_STRING('C', "cpu", &report.cpu_list, "cpu",
+		   "list of cpus to profile"),
+	OPT_BOOLEAN('I', "show-info", &report.show_full_info,
+		    "Display extended information about perf.data file"),
+	OPT_BOOLEAN(0, "source", &symbol_conf.annotate_src,
+		    "Interleave source code with assembly code (default)"),
+	OPT_BOOLEAN(0, "asm-raw", &symbol_conf.annotate_asm_raw,
+		    "Display raw encoding of assembly instructions (default)"),
+	OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style",
+		   "Specify disassembler style (e.g. -M intel for intel syntax)"),
+	OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period,
+		    "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", &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_CALLBACK(0, "percentage", NULL, "relative|absolute",
+		     "how to display percentage of filtered entries", parse_filter_percentage),
 	OPT_END()
-};
+	};
+	struct perf_data_file file = {
+		.mode  = PERF_DATA_MODE_READ,
+	};
+
+	perf_config(report__config, &report);
 
-int cmd_report(int argc, const char **argv, const char *prefix __used)
-{
 	argc = parse_options(argc, argv, options, report_usage, 0);
 
+	if (report.use_stdio)
+		use_browser = 0;
+	else if (report.use_tui)
+		use_browser = 1;
+	else if (report.use_gtk)
+		use_browser = 2;
+
+	if (report.inverted_callchain)
+		callchain_param.order = ORDER_CALLER;
+
+	if (!input_name || !strlen(input_name)) {
+		if (!fstat(STDIN_FILENO, &st) && S_ISFIFO(st.st_mode))
+			input_name = "-";
+		else
+			input_name = "perf.data";
+	}
+
+	file.path  = input_name;
+	file.force = report.force;
+
+repeat:
+	session = perf_session__new(&file, false, &report.tool);
+	if (session == NULL)
+		return -ENOMEM;
+
+	report.session = session;
+
+	has_br_stack = perf_header__has_feat(&session->header,
+					     HEADER_BRANCH_STACK);
+
+	if (branch_mode == -1 && has_br_stack) {
+		sort__mode = SORT_MODE__BRANCH;
+		symbol_conf.cumulate_callchain = false;
+	}
+
+	if (report.mem_mode) {
+		if (sort__mode == SORT_MODE__BRANCH) {
+			pr_err("branch and mem mode incompatible\n");
+			goto error;
+		}
+		sort__mode = SORT_MODE__MEMORY;
+		symbol_conf.cumulate_callchain = false;
+	}
+
+	if (setup_sorting() < 0) {
+		if (sort_order)
+			parse_options_usage(report_usage, options, "s", 1);
+		if (field_order)
+			parse_options_usage(sort_order ? NULL : report_usage,
+					    options, "F", 1);
+		goto error;
+	}
+
+	/* Force tty output for header output. */
+	if (report.header || report.header_only)
+		use_browser = 0;
+
 	if (strcmp(input_name, "-") != 0)
-		setup_browser();
+		setup_browser(true);
+	else
+		use_browser = 0;
+
+	if (report.header || report.header_only) {
+		perf_session__fprintf_info(session, stdout,
+					   report.show_full_info);
+		if (report.header_only)
+			return 0;
+	} else if (use_browser == 0) {
+		fputs("# To display the perf.data header info, please use --header/--header-only options.\n#\n",
+		      stdout);
+	}
+
 	/*
-	 * Only in the newt browser we are doing integrated annotation,
+	 * Only in the TUI browser we are doing integrated annotation,
 	 * so don't allocate extra space that won't be used in the stdio
 	 * implementation.
 	 */
-	if (use_browser > 0)
-		symbol_conf.priv_size = sizeof(struct sym_priv);
+	if (ui__has_annotation()) {
+		symbol_conf.priv_size = sizeof(struct annotation);
+		machines__set_symbol_filter(&session->machines,
+					    symbol__annotate_init);
+		/*
+ 		 * For searching by name on the "Browse map details".
+ 		 * providing it only in verbose mode not to bloat too
+ 		 * much struct symbol.
+ 		 */
+		if (verbose) {
+			/*
+			 * XXX: Need to provide a less kludgy way to ask for
+			 * more space per symbol, the u32 is for the index on
+			 * the ui browser.
+			 * See symbol__browser_index.
+			 */
+			symbol_conf.priv_size += sizeof(u32);
+			symbol_conf.sort_by_name = true;
+		}
+	}
 
 	if (symbol__init() < 0)
-		return -1;
+		goto error;
 
-	setup_sorting(report_usage, options);
+	if (argc) {
+		/*
+		 * Special case: if there's an argument left then assume that
+		 * it's a symbol filter:
+		 */
+		if (argc > 1)
+			usage_with_options(report_usage, options);
 
-	if (parent_pattern != default_parent_pattern) {
-		if (sort_dimension__add("parent") < 0)
-			return -1;
-		sort_parent.elide = 1;
-	} else
-		symbol_conf.exclude_other = false;
+		report.symbol_filter_str = argv[0];
+	}
 
-	/*
-	 * Any (unrecognized) arguments left?
-	 */
-	if (argc)
-		usage_with_options(report_usage, options);
+	sort__setup_elide(stdout);
 
-	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);
+	ret = __cmd_report(&report);
+	if (ret == K_SWITCH_INPUT_DATA) {
+		perf_session__delete(session);
+		goto repeat;
+	} else
+		ret = 0;
 
-	return __cmd_report();
+error:
+	perf_session__delete(session);
+	return ret;
 }
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 55f3b5dcc73..c38d06c0477 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -2,11 +2,14 @@
 #include "perf.h"
 
 #include "util/util.h"
+#include "util/evlist.h"
 #include "util/cache.h"
+#include "util/evsel.h"
 #include "util/symbol.h"
 #include "util/thread.h"
 #include "util/header.h"
 #include "util/session.h"
+#include "util/tool.h"
 
 #include "util/parse-options.h"
 #include "util/trace-event.h"
@@ -14,31 +17,18 @@
 #include "util/debug.h"
 
 #include <sys/prctl.h>
+#include <sys/resource.h>
 
 #include <semaphore.h>
 #include <pthread.h>
 #include <math.h>
 
-static char			const *input_name = "perf.data";
-
-static char			default_sort_order[] = "avg, max, switch, runtime";
-static const char		*sort_order = default_sort_order;
-
-static int			profile_cpu = -1;
-
 #define PR_SET_NAME		15               /* Set process name */
 #define MAX_CPUS		4096
-
-static u64			run_measurement_overhead;
-static u64			sleep_measurement_overhead;
-
 #define COMM_LEN		20
 #define SYM_LEN			129
-
 #define MAX_PID			65536
 
-static unsigned long		nr_tasks;
-
 struct sched_atom;
 
 struct task_desc {
@@ -76,45 +66,7 @@ struct sched_atom {
 	struct task_desc	*wakee;
 };
 
-static struct task_desc		*pid_to_task[MAX_PID];
-
-static struct task_desc		**tasks;
-
-static pthread_mutex_t		start_work_mutex = PTHREAD_MUTEX_INITIALIZER;
-static u64			start_time;
-
-static pthread_mutex_t		work_done_wait_mutex = PTHREAD_MUTEX_INITIALIZER;
-
-static unsigned long		nr_run_events;
-static unsigned long		nr_sleep_events;
-static unsigned long		nr_wakeup_events;
-
-static unsigned long		nr_sleep_corrections;
-static unsigned long		nr_run_events_optimized;
-
-static unsigned long		targetless_wakeups;
-static unsigned long		multitarget_wakeups;
-
-static u64			cpu_usage;
-static u64			runavg_cpu_usage;
-static u64			parent_cpu_usage;
-static u64			runavg_parent_cpu_usage;
-
-static unsigned long		nr_runs;
-static u64			sum_runtime;
-static u64			sum_fluct;
-static u64			run_avg;
-
-static unsigned int		replay_repeat = 10;
-static unsigned long		nr_timestamps;
-static unsigned long		nr_unordered_timestamps;
-static unsigned long		nr_state_machine_bugs;
-static unsigned long		nr_context_switch_bugs;
-static unsigned long		nr_events;
-static unsigned long		nr_lost_chunks;
-static unsigned long		nr_lost_events;
-
-#define TASK_STATE_TO_CHAR_STR "RSDTtZX"
+#define TASK_STATE_TO_CHAR_STR "RSDTtZXxKWP"
 
 enum thread_state {
 	THREAD_SLEEPING = 0,
@@ -145,11 +97,78 @@ struct work_atoms {
 
 typedef int (*sort_fn_t)(struct work_atoms *, struct work_atoms *);
 
-static struct rb_root		atom_root, sorted_atom_root;
+struct perf_sched;
+
+struct trace_sched_handler {
+	int (*switch_event)(struct perf_sched *sched, struct perf_evsel *evsel,
+			    struct perf_sample *sample, struct machine *machine);
+
+	int (*runtime_event)(struct perf_sched *sched, struct perf_evsel *evsel,
+			     struct perf_sample *sample, struct machine *machine);
+
+	int (*wakeup_event)(struct perf_sched *sched, struct perf_evsel *evsel,
+			    struct perf_sample *sample, struct machine *machine);
 
-static u64			all_runtime;
-static u64			all_count;
+	/* PERF_RECORD_FORK event, not sched_process_fork tracepoint */
+	int (*fork_event)(struct perf_sched *sched, union perf_event *event,
+			  struct machine *machine);
+
+	int (*migrate_task_event)(struct perf_sched *sched,
+				  struct perf_evsel *evsel,
+				  struct perf_sample *sample,
+				  struct machine *machine);
+};
 
+struct perf_sched {
+	struct perf_tool tool;
+	const char	 *sort_order;
+	unsigned long	 nr_tasks;
+	struct task_desc *pid_to_task[MAX_PID];
+	struct task_desc **tasks;
+	const struct trace_sched_handler *tp_handler;
+	pthread_mutex_t	 start_work_mutex;
+	pthread_mutex_t	 work_done_wait_mutex;
+	int		 profile_cpu;
+/*
+ * Track the current task - that way we can know whether there's any
+ * weird events, such as a task being switched away that is not current.
+ */
+	int		 max_cpu;
+	u32		 curr_pid[MAX_CPUS];
+	struct thread	 *curr_thread[MAX_CPUS];
+	char		 next_shortname1;
+	char		 next_shortname2;
+	unsigned int	 replay_repeat;
+	unsigned long	 nr_run_events;
+	unsigned long	 nr_sleep_events;
+	unsigned long	 nr_wakeup_events;
+	unsigned long	 nr_sleep_corrections;
+	unsigned long	 nr_run_events_optimized;
+	unsigned long	 targetless_wakeups;
+	unsigned long	 multitarget_wakeups;
+	unsigned long	 nr_runs;
+	unsigned long	 nr_timestamps;
+	unsigned long	 nr_unordered_timestamps;
+	unsigned long	 nr_context_switch_bugs;
+	unsigned long	 nr_events;
+	unsigned long	 nr_lost_chunks;
+	unsigned long	 nr_lost_events;
+	u64		 run_measurement_overhead;
+	u64		 sleep_measurement_overhead;
+	u64		 start_time;
+	u64		 cpu_usage;
+	u64		 runavg_cpu_usage;
+	u64		 parent_cpu_usage;
+	u64		 runavg_parent_cpu_usage;
+	u64		 sum_runtime;
+	u64		 sum_fluct;
+	u64		 run_avg;
+	u64		 all_runtime;
+	u64		 all_count;
+	u64		 cpu_last_switched[MAX_CPUS];
+	struct rb_root	 atom_root, sorted_atom_root;
+	struct list_head sort_list, cmp_pid;
+};
 
 static u64 get_nsecs(void)
 {
@@ -160,13 +179,13 @@ static u64 get_nsecs(void)
 	return ts.tv_sec * 1000000000ULL + ts.tv_nsec;
 }
 
-static void burn_nsecs(u64 nsecs)
+static void burn_nsecs(struct perf_sched *sched, u64 nsecs)
 {
 	u64 T0 = get_nsecs(), T1;
 
 	do {
 		T1 = get_nsecs();
-	} while (T1 + run_measurement_overhead < T0 + nsecs);
+	} while (T1 + sched->run_measurement_overhead < T0 + nsecs);
 }
 
 static void sleep_nsecs(u64 nsecs)
@@ -179,24 +198,24 @@ static void sleep_nsecs(u64 nsecs)
 	nanosleep(&ts, NULL);
 }
 
-static void calibrate_run_measurement_overhead(void)
+static void calibrate_run_measurement_overhead(struct perf_sched *sched)
 {
 	u64 T0, T1, delta, min_delta = 1000000000ULL;
 	int i;
 
 	for (i = 0; i < 10; i++) {
 		T0 = get_nsecs();
-		burn_nsecs(0);
+		burn_nsecs(sched, 0);
 		T1 = get_nsecs();
 		delta = T1-T0;
 		min_delta = min(min_delta, delta);
 	}
-	run_measurement_overhead = min_delta;
+	sched->run_measurement_overhead = min_delta;
 
-	printf("run measurement overhead: %Ld nsecs\n", min_delta);
+	printf("run measurement overhead: %" PRIu64 " nsecs\n", min_delta);
 }
 
-static void calibrate_sleep_measurement_overhead(void)
+static void calibrate_sleep_measurement_overhead(struct perf_sched *sched)
 {
 	u64 T0, T1, delta, min_delta = 1000000000ULL;
 	int i;
@@ -209,9 +228,9 @@ static void calibrate_sleep_measurement_overhead(void)
 		min_delta = min(min_delta, delta);
 	}
 	min_delta -= 10000;
-	sleep_measurement_overhead = min_delta;
+	sched->sleep_measurement_overhead = min_delta;
 
-	printf("sleep measurement overhead: %Ld nsecs\n", min_delta);
+	printf("sleep measurement overhead: %" PRIu64 " nsecs\n", min_delta);
 }
 
 static struct sched_atom *
@@ -242,8 +261,8 @@ static struct sched_atom *last_event(struct task_desc *task)
 	return task->atoms[task->nr_events - 1];
 }
 
-static void
-add_sched_event_run(struct task_desc *task, u64 timestamp, u64 duration)
+static void add_sched_event_run(struct perf_sched *sched, struct task_desc *task,
+				u64 timestamp, u64 duration)
 {
 	struct sched_atom *event, *curr_event = last_event(task);
 
@@ -252,7 +271,7 @@ add_sched_event_run(struct task_desc *task, u64 timestamp, u64 duration)
 	 * to it:
 	 */
 	if (curr_event && curr_event->type == SCHED_EVENT_RUN) {
-		nr_run_events_optimized++;
+		sched->nr_run_events_optimized++;
 		curr_event->duration += duration;
 		return;
 	}
@@ -262,12 +281,11 @@ add_sched_event_run(struct task_desc *task, u64 timestamp, u64 duration)
 	event->type = SCHED_EVENT_RUN;
 	event->duration = duration;
 
-	nr_run_events++;
+	sched->nr_run_events++;
 }
 
-static void
-add_sched_event_wakeup(struct task_desc *task, u64 timestamp,
-		       struct task_desc *wakee)
+static void add_sched_event_wakeup(struct perf_sched *sched, struct task_desc *task,
+				   u64 timestamp, struct task_desc *wakee)
 {
 	struct sched_atom *event, *wakee_event;
 
@@ -277,11 +295,11 @@ add_sched_event_wakeup(struct task_desc *task, u64 timestamp,
 
 	wakee_event = last_event(wakee);
 	if (!wakee_event || wakee_event->type != SCHED_EVENT_SLEEP) {
-		targetless_wakeups++;
+		sched->targetless_wakeups++;
 		return;
 	}
 	if (wakee_event->wait_sem) {
-		multitarget_wakeups++;
+		sched->multitarget_wakeups++;
 		return;
 	}
 
@@ -290,94 +308,89 @@ add_sched_event_wakeup(struct task_desc *task, u64 timestamp,
 	wakee_event->specific_wait = 1;
 	event->wait_sem = wakee_event->wait_sem;
 
-	nr_wakeup_events++;
+	sched->nr_wakeup_events++;
 }
 
-static void
-add_sched_event_sleep(struct task_desc *task, u64 timestamp,
-		      u64 task_state __used)
+static void add_sched_event_sleep(struct perf_sched *sched, struct task_desc *task,
+				  u64 timestamp, u64 task_state __maybe_unused)
 {
 	struct sched_atom *event = get_new_event(task, timestamp);
 
 	event->type = SCHED_EVENT_SLEEP;
 
-	nr_sleep_events++;
+	sched->nr_sleep_events++;
 }
 
-static struct task_desc *register_pid(unsigned long pid, const char *comm)
+static struct task_desc *register_pid(struct perf_sched *sched,
+				      unsigned long pid, const char *comm)
 {
 	struct task_desc *task;
 
 	BUG_ON(pid >= MAX_PID);
 
-	task = pid_to_task[pid];
+	task = sched->pid_to_task[pid];
 
 	if (task)
 		return task;
 
 	task = zalloc(sizeof(*task));
 	task->pid = pid;
-	task->nr = nr_tasks;
+	task->nr = sched->nr_tasks;
 	strcpy(task->comm, comm);
 	/*
 	 * every task starts in sleeping state - this gets ignored
 	 * if there's no wakeup pointing to this sleep state:
 	 */
-	add_sched_event_sleep(task, 0, 0);
+	add_sched_event_sleep(sched, task, 0, 0);
 
-	pid_to_task[pid] = task;
-	nr_tasks++;
-	tasks = realloc(tasks, nr_tasks*sizeof(struct task_task *));
-	BUG_ON(!tasks);
-	tasks[task->nr] = task;
+	sched->pid_to_task[pid] = task;
+	sched->nr_tasks++;
+	sched->tasks = realloc(sched->tasks, sched->nr_tasks * sizeof(struct task_task *));
+	BUG_ON(!sched->tasks);
+	sched->tasks[task->nr] = task;
 
 	if (verbose)
-		printf("registered task #%ld, PID %ld (%s)\n", nr_tasks, pid, comm);
+		printf("registered task #%ld, PID %ld (%s)\n", sched->nr_tasks, pid, comm);
 
 	return task;
 }
 
 
-static void print_task_traces(void)
+static void print_task_traces(struct perf_sched *sched)
 {
 	struct task_desc *task;
 	unsigned long i;
 
-	for (i = 0; i < nr_tasks; i++) {
-		task = tasks[i];
+	for (i = 0; i < sched->nr_tasks; i++) {
+		task = sched->tasks[i];
 		printf("task %6ld (%20s:%10ld), nr_events: %ld\n",
 			task->nr, task->comm, task->pid, task->nr_events);
 	}
 }
 
-static void add_cross_task_wakeups(void)
+static void add_cross_task_wakeups(struct perf_sched *sched)
 {
 	struct task_desc *task1, *task2;
 	unsigned long i, j;
 
-	for (i = 0; i < nr_tasks; i++) {
-		task1 = tasks[i];
+	for (i = 0; i < sched->nr_tasks; i++) {
+		task1 = sched->tasks[i];
 		j = i + 1;
-		if (j == nr_tasks)
+		if (j == sched->nr_tasks)
 			j = 0;
-		task2 = tasks[j];
-		add_sched_event_wakeup(task1, 0, task2);
+		task2 = sched->tasks[j];
+		add_sched_event_wakeup(sched, task1, 0, task2);
 	}
 }
 
-static void
-process_sched_event(struct task_desc *this_task __used, struct sched_atom *atom)
+static void perf_sched__process_event(struct perf_sched *sched,
+				      struct sched_atom *atom)
 {
 	int ret = 0;
-	u64 now;
-	long long delta;
-
-	now = get_nsecs();
-	delta = start_time + atom->timestamp - now;
 
 	switch (atom->type) {
 		case SCHED_EVENT_RUN:
-			burn_nsecs(atom->duration);
+			burn_nsecs(sched, atom->duration);
 			break;
 		case SCHED_EVENT_SLEEP:
 			if (atom->wait_sem)
@@ -424,8 +437,8 @@ static int self_open_counters(void)
 	fd = sys_perf_event_open(&attr, 0, -1, -1, 0);
 
 	if (fd < 0)
-		die("Error: sys_perf_event_open() syscall returned"
-		    "with %d (%s)\n", fd, strerror(errno));
+		pr_err("Error: sys_perf_event_open() syscall returned "
+		       "with %d (%s)\n", fd, strerror(errno));
 	return fd;
 }
 
@@ -440,31 +453,41 @@ static u64 get_cpu_usage_nsec_self(int fd)
 	return runtime;
 }
 
+struct sched_thread_parms {
+	struct task_desc  *task;
+	struct perf_sched *sched;
+};
+
 static void *thread_func(void *ctx)
 {
-	struct task_desc *this_task = ctx;
+	struct sched_thread_parms *parms = ctx;
+	struct task_desc *this_task = parms->task;
+	struct perf_sched *sched = parms->sched;
 	u64 cpu_usage_0, cpu_usage_1;
 	unsigned long i, ret;
 	char comm2[22];
 	int fd;
 
+	zfree(&parms);
+
 	sprintf(comm2, ":%s", this_task->comm);
 	prctl(PR_SET_NAME, comm2);
 	fd = self_open_counters();
-
+	if (fd < 0)
+		return NULL;
 again:
 	ret = sem_post(&this_task->ready_for_work);
 	BUG_ON(ret);
-	ret = pthread_mutex_lock(&start_work_mutex);
+	ret = pthread_mutex_lock(&sched->start_work_mutex);
 	BUG_ON(ret);
-	ret = pthread_mutex_unlock(&start_work_mutex);
+	ret = pthread_mutex_unlock(&sched->start_work_mutex);
 	BUG_ON(ret);
 
 	cpu_usage_0 = get_cpu_usage_nsec_self(fd);
 
 	for (i = 0; i < this_task->nr_events; i++) {
 		this_task->curr_event = i;
-		process_sched_event(this_task, this_task->atoms[i]);
+		perf_sched__process_event(sched, this_task->atoms[i]);
 	}
 
 	cpu_usage_1 = get_cpu_usage_nsec_self(fd);
@@ -472,15 +495,15 @@ again:
 	ret = sem_post(&this_task->work_done_sem);
 	BUG_ON(ret);
 
-	ret = pthread_mutex_lock(&work_done_wait_mutex);
+	ret = pthread_mutex_lock(&sched->work_done_wait_mutex);
 	BUG_ON(ret);
-	ret = pthread_mutex_unlock(&work_done_wait_mutex);
+	ret = pthread_mutex_unlock(&sched->work_done_wait_mutex);
 	BUG_ON(ret);
 
 	goto again;
 }
 
-static void create_tasks(void)
+static void create_tasks(struct perf_sched *sched)
 {
 	struct task_desc *task;
 	pthread_attr_t attr;
@@ -489,372 +512,238 @@ static void create_tasks(void)
 
 	err = pthread_attr_init(&attr);
 	BUG_ON(err);
-	err = pthread_attr_setstacksize(&attr, (size_t)(16*1024));
+	err = pthread_attr_setstacksize(&attr,
+			(size_t) max(16 * 1024, PTHREAD_STACK_MIN));
 	BUG_ON(err);
-	err = pthread_mutex_lock(&start_work_mutex);
+	err = pthread_mutex_lock(&sched->start_work_mutex);
 	BUG_ON(err);
-	err = pthread_mutex_lock(&work_done_wait_mutex);
+	err = pthread_mutex_lock(&sched->work_done_wait_mutex);
 	BUG_ON(err);
-	for (i = 0; i < nr_tasks; i++) {
-		task = tasks[i];
+	for (i = 0; i < sched->nr_tasks; i++) {
+		struct sched_thread_parms *parms = malloc(sizeof(*parms));
+		BUG_ON(parms == NULL);
+		parms->task = task = sched->tasks[i];
+		parms->sched = sched;
 		sem_init(&task->sleep_sem, 0, 0);
 		sem_init(&task->ready_for_work, 0, 0);
 		sem_init(&task->work_done_sem, 0, 0);
 		task->curr_event = 0;
-		err = pthread_create(&task->thread, &attr, thread_func, task);
+		err = pthread_create(&task->thread, &attr, thread_func, parms);
 		BUG_ON(err);
 	}
 }
 
-static void wait_for_tasks(void)
+static void wait_for_tasks(struct perf_sched *sched)
 {
 	u64 cpu_usage_0, cpu_usage_1;
 	struct task_desc *task;
 	unsigned long i, ret;
 
-	start_time = get_nsecs();
-	cpu_usage = 0;
-	pthread_mutex_unlock(&work_done_wait_mutex);
+	sched->start_time = get_nsecs();
+	sched->cpu_usage = 0;
+	pthread_mutex_unlock(&sched->work_done_wait_mutex);
 
-	for (i = 0; i < nr_tasks; i++) {
-		task = tasks[i];
+	for (i = 0; i < sched->nr_tasks; i++) {
+		task = sched->tasks[i];
 		ret = sem_wait(&task->ready_for_work);
 		BUG_ON(ret);
 		sem_init(&task->ready_for_work, 0, 0);
 	}
-	ret = pthread_mutex_lock(&work_done_wait_mutex);
+	ret = pthread_mutex_lock(&sched->work_done_wait_mutex);
 	BUG_ON(ret);
 
 	cpu_usage_0 = get_cpu_usage_nsec_parent();
 
-	pthread_mutex_unlock(&start_work_mutex);
+	pthread_mutex_unlock(&sched->start_work_mutex);
 
-	for (i = 0; i < nr_tasks; i++) {
-		task = tasks[i];
+	for (i = 0; i < sched->nr_tasks; i++) {
+		task = sched->tasks[i];
 		ret = sem_wait(&task->work_done_sem);
 		BUG_ON(ret);
 		sem_init(&task->work_done_sem, 0, 0);
-		cpu_usage += task->cpu_usage;
+		sched->cpu_usage += task->cpu_usage;
 		task->cpu_usage = 0;
 	}
 
 	cpu_usage_1 = get_cpu_usage_nsec_parent();
-	if (!runavg_cpu_usage)
-		runavg_cpu_usage = cpu_usage;
-	runavg_cpu_usage = (runavg_cpu_usage*9 + cpu_usage)/10;
+	if (!sched->runavg_cpu_usage)
+		sched->runavg_cpu_usage = sched->cpu_usage;
+	sched->runavg_cpu_usage = (sched->runavg_cpu_usage * 9 + sched->cpu_usage) / 10;
 
-	parent_cpu_usage = cpu_usage_1 - cpu_usage_0;
-	if (!runavg_parent_cpu_usage)
-		runavg_parent_cpu_usage = parent_cpu_usage;
-	runavg_parent_cpu_usage = (runavg_parent_cpu_usage*9 +
-				   parent_cpu_usage)/10;
+	sched->parent_cpu_usage = cpu_usage_1 - cpu_usage_0;
+	if (!sched->runavg_parent_cpu_usage)
+		sched->runavg_parent_cpu_usage = sched->parent_cpu_usage;
+	sched->runavg_parent_cpu_usage = (sched->runavg_parent_cpu_usage * 9 +
+					 sched->parent_cpu_usage)/10;
 
-	ret = pthread_mutex_lock(&start_work_mutex);
+	ret = pthread_mutex_lock(&sched->start_work_mutex);
 	BUG_ON(ret);
 
-	for (i = 0; i < nr_tasks; i++) {
-		task = tasks[i];
+	for (i = 0; i < sched->nr_tasks; i++) {
+		task = sched->tasks[i];
 		sem_init(&task->sleep_sem, 0, 0);
 		task->curr_event = 0;
 	}
 }
 
-static void run_one_test(void)
+static void run_one_test(struct perf_sched *sched)
 {
-	u64 T0, T1, delta, avg_delta, fluct, std_dev;
+	u64 T0, T1, delta, avg_delta, fluct;
 
 	T0 = get_nsecs();
-	wait_for_tasks();
+	wait_for_tasks(sched);
 	T1 = get_nsecs();
 
 	delta = T1 - T0;
-	sum_runtime += delta;
-	nr_runs++;
+	sched->sum_runtime += delta;
+	sched->nr_runs++;
 
-	avg_delta = sum_runtime / nr_runs;
+	avg_delta = sched->sum_runtime / sched->nr_runs;
 	if (delta < avg_delta)
 		fluct = avg_delta - delta;
 	else
 		fluct = delta - avg_delta;
-	sum_fluct += fluct;
-	std_dev = sum_fluct / nr_runs / sqrt(nr_runs);
-	if (!run_avg)
-		run_avg = delta;
-	run_avg = (run_avg*9 + delta)/10;
+	sched->sum_fluct += fluct;
+	if (!sched->run_avg)
+		sched->run_avg = delta;
+	sched->run_avg = (sched->run_avg * 9 + delta) / 10;
 
-	printf("#%-3ld: %0.3f, ",
-		nr_runs, (double)delta/1000000.0);
+	printf("#%-3ld: %0.3f, ", sched->nr_runs, (double)delta / 1000000.0);
 
-	printf("ravg: %0.2f, ",
-		(double)run_avg/1e6);
+	printf("ravg: %0.2f, ", (double)sched->run_avg / 1e6);
 
 	printf("cpu: %0.2f / %0.2f",
-		(double)cpu_usage/1e6, (double)runavg_cpu_usage/1e6);
+		(double)sched->cpu_usage / 1e6, (double)sched->runavg_cpu_usage / 1e6);
 
 #if 0
 	/*
 	 * rusage statistics done by the parent, these are less
-	 * accurate than the sum_exec_runtime based statistics:
+	 * accurate than the sched->sum_exec_runtime based statistics:
 	 */
 	printf(" [%0.2f / %0.2f]",
-		(double)parent_cpu_usage/1e6,
-		(double)runavg_parent_cpu_usage/1e6);
+		(double)sched->parent_cpu_usage/1e6,
+		(double)sched->runavg_parent_cpu_usage/1e6);
 #endif
 
 	printf("\n");
 
-	if (nr_sleep_corrections)
-		printf(" (%ld sleep corrections)\n", nr_sleep_corrections);
-	nr_sleep_corrections = 0;
+	if (sched->nr_sleep_corrections)
+		printf(" (%ld sleep corrections)\n", sched->nr_sleep_corrections);
+	sched->nr_sleep_corrections = 0;
 }
 
-static void test_calibrations(void)
+static void test_calibrations(struct perf_sched *sched)
 {
 	u64 T0, T1;
 
 	T0 = get_nsecs();
-	burn_nsecs(1e6);
+	burn_nsecs(sched, 1e6);
 	T1 = get_nsecs();
 
-	printf("the run test took %Ld nsecs\n", T1-T0);
+	printf("the run test took %" PRIu64 " nsecs\n", T1 - T0);
 
 	T0 = get_nsecs();
 	sleep_nsecs(1e6);
 	T1 = get_nsecs();
 
-	printf("the sleep test took %Ld nsecs\n", T1-T0);
+	printf("the sleep test took %" PRIu64 " nsecs\n", T1 - T0);
 }
 
-#define FILL_FIELD(ptr, field, event, data)	\
-	ptr.field = (typeof(ptr.field)) raw_field_value(event, #field, data)
-
-#define FILL_ARRAY(ptr, array, event, data)			\
-do {								\
-	void *__array = raw_field_ptr(event, #array, data);	\
-	memcpy(ptr.array, __array, sizeof(ptr.array));	\
-} while(0)
-
-#define FILL_COMMON_FIELDS(ptr, event, data)			\
-do {								\
-	FILL_FIELD(ptr, common_type, event, data);		\
-	FILL_FIELD(ptr, common_flags, event, data);		\
-	FILL_FIELD(ptr, common_preempt_count, event, data);	\
-	FILL_FIELD(ptr, common_pid, event, data);		\
-	FILL_FIELD(ptr, common_tgid, event, data);		\
-} while (0)
-
-
-
-struct trace_switch_event {
-	u32 size;
-
-	u16 common_type;
-	u8 common_flags;
-	u8 common_preempt_count;
-	u32 common_pid;
-	u32 common_tgid;
-
-	char prev_comm[16];
-	u32 prev_pid;
-	u32 prev_prio;
-	u64 prev_state;
-	char next_comm[16];
-	u32 next_pid;
-	u32 next_prio;
-};
-
-struct trace_runtime_event {
-	u32 size;
-
-	u16 common_type;
-	u8 common_flags;
-	u8 common_preempt_count;
-	u32 common_pid;
-	u32 common_tgid;
-
-	char comm[16];
-	u32 pid;
-	u64 runtime;
-	u64 vruntime;
-};
-
-struct trace_wakeup_event {
-	u32 size;
-
-	u16 common_type;
-	u8 common_flags;
-	u8 common_preempt_count;
-	u32 common_pid;
-	u32 common_tgid;
-
-	char comm[16];
-	u32 pid;
-
-	u32 prio;
-	u32 success;
-	u32 cpu;
-};
-
-struct trace_fork_event {
-	u32 size;
-
-	u16 common_type;
-	u8 common_flags;
-	u8 common_preempt_count;
-	u32 common_pid;
-	u32 common_tgid;
-
-	char parent_comm[16];
-	u32 parent_pid;
-	char child_comm[16];
-	u32 child_pid;
-};
-
-struct trace_migrate_task_event {
-	u32 size;
-
-	u16 common_type;
-	u8 common_flags;
-	u8 common_preempt_count;
-	u32 common_pid;
-	u32 common_tgid;
-
-	char comm[16];
-	u32 pid;
-
-	u32 prio;
-	u32 cpu;
-};
-
-struct trace_sched_handler {
-	void (*switch_event)(struct trace_switch_event *,
-			     struct perf_session *,
-			     struct event *,
-			     int cpu,
-			     u64 timestamp,
-			     struct thread *thread);
-
-	void (*runtime_event)(struct trace_runtime_event *,
-			      struct perf_session *,
-			      struct event *,
-			      int cpu,
-			      u64 timestamp,
-			      struct thread *thread);
-
-	void (*wakeup_event)(struct trace_wakeup_event *,
-			     struct perf_session *,
-			     struct event *,
-			     int cpu,
-			     u64 timestamp,
-			     struct thread *thread);
-
-	void (*fork_event)(struct trace_fork_event *,
-			   struct event *,
-			   int cpu,
-			   u64 timestamp,
-			   struct thread *thread);
-
-	void (*migrate_task_event)(struct trace_migrate_task_event *,
-			   struct perf_session *session,
-			   struct event *,
-			   int cpu,
-			   u64 timestamp,
-			   struct thread *thread);
-};
-
-
-static void
-replay_wakeup_event(struct trace_wakeup_event *wakeup_event,
-		    struct perf_session *session __used,
-		    struct event *event,
-		    int cpu __used,
-		    u64 timestamp __used,
-		    struct thread *thread __used)
+static int
+replay_wakeup_event(struct perf_sched *sched,
+		    struct perf_evsel *evsel, struct perf_sample *sample,
+		    struct machine *machine __maybe_unused)
 {
+	const char *comm = perf_evsel__strval(evsel, sample, "comm");
+	const u32 pid	 = perf_evsel__intval(evsel, sample, "pid");
 	struct task_desc *waker, *wakee;
 
 	if (verbose) {
-		printf("sched_wakeup event %p\n", event);
+		printf("sched_wakeup event %p\n", evsel);
 
-		printf(" ... pid %d woke up %s/%d\n",
-			wakeup_event->common_pid,
-			wakeup_event->comm,
-			wakeup_event->pid);
+		printf(" ... pid %d woke up %s/%d\n", sample->tid, comm, pid);
 	}
 
-	waker = register_pid(wakeup_event->common_pid, "<unknown>");
-	wakee = register_pid(wakeup_event->pid, wakeup_event->comm);
+	waker = register_pid(sched, sample->tid, "<unknown>");
+	wakee = register_pid(sched, pid, comm);
 
-	add_sched_event_wakeup(waker, timestamp, wakee);
+	add_sched_event_wakeup(sched, waker, sample->time, wakee);
+	return 0;
 }
 
-static u64 cpu_last_switched[MAX_CPUS];
-
-static void
-replay_switch_event(struct trace_switch_event *switch_event,
-		    struct perf_session *session __used,
-		    struct event *event,
-		    int cpu,
-		    u64 timestamp,
-		    struct thread *thread __used)
+static int replay_switch_event(struct perf_sched *sched,
+			       struct perf_evsel *evsel,
+			       struct perf_sample *sample,
+			       struct machine *machine __maybe_unused)
 {
-	struct task_desc *prev, *next;
-	u64 timestamp0;
+	const char *prev_comm  = perf_evsel__strval(evsel, sample, "prev_comm"),
+		   *next_comm  = perf_evsel__strval(evsel, sample, "next_comm");
+	const u32 prev_pid = perf_evsel__intval(evsel, sample, "prev_pid"),
+		  next_pid = perf_evsel__intval(evsel, sample, "next_pid");
+	const u64 prev_state = perf_evsel__intval(evsel, sample, "prev_state");
+	struct task_desc *prev, __maybe_unused *next;
+	u64 timestamp0, timestamp = sample->time;
+	int cpu = sample->cpu;
 	s64 delta;
 
 	if (verbose)
-		printf("sched_switch event %p\n", event);
+		printf("sched_switch event %p\n", evsel);
 
 	if (cpu >= MAX_CPUS || cpu < 0)
-		return;
+		return 0;
 
-	timestamp0 = cpu_last_switched[cpu];
+	timestamp0 = sched->cpu_last_switched[cpu];
 	if (timestamp0)
 		delta = timestamp - timestamp0;
 	else
 		delta = 0;
 
-	if (delta < 0)
-		die("hm, delta: %Ld < 0 ?\n", delta);
-
-	if (verbose) {
-		printf(" ... switch from %s/%d to %s/%d [ran %Ld nsecs]\n",
-			switch_event->prev_comm, switch_event->prev_pid,
-			switch_event->next_comm, switch_event->next_pid,
-			delta);
+	if (delta < 0) {
+		pr_err("hm, delta: %" PRIu64 " < 0 ?\n", delta);
+		return -1;
 	}
 
-	prev = register_pid(switch_event->prev_pid, switch_event->prev_comm);
-	next = register_pid(switch_event->next_pid, switch_event->next_comm);
+	pr_debug(" ... switch from %s/%d to %s/%d [ran %" PRIu64 " nsecs]\n",
+		 prev_comm, prev_pid, next_comm, next_pid, delta);
 
-	cpu_last_switched[cpu] = timestamp;
+	prev = register_pid(sched, prev_pid, prev_comm);
+	next = register_pid(sched, next_pid, next_comm);
 
-	add_sched_event_run(prev, timestamp, delta);
-	add_sched_event_sleep(prev, timestamp, switch_event->prev_state);
-}
+	sched->cpu_last_switched[cpu] = timestamp;
 
+	add_sched_event_run(sched, prev, timestamp, delta);
+	add_sched_event_sleep(sched, prev, timestamp, prev_state);
 
-static void
-replay_fork_event(struct trace_fork_event *fork_event,
-		  struct event *event,
-		  int cpu __used,
-		  u64 timestamp __used,
-		  struct thread *thread __used)
+	return 0;
+}
+
+static int replay_fork_event(struct perf_sched *sched,
+			     union perf_event *event,
+			     struct machine *machine)
 {
+	struct thread *child, *parent;
+
+	child = machine__findnew_thread(machine, event->fork.pid,
+					event->fork.tid);
+	parent = machine__findnew_thread(machine, event->fork.ppid,
+					 event->fork.ptid);
+
+	if (child == NULL || parent == NULL) {
+		pr_debug("thread does not exist on fork event: child %p, parent %p\n",
+				 child, parent);
+		return 0;
+	}
+
 	if (verbose) {
-		printf("sched_fork event %p\n", event);
-		printf("... parent: %s/%d\n", fork_event->parent_comm, fork_event->parent_pid);
-		printf("...  child: %s/%d\n", fork_event->child_comm, fork_event->child_pid);
+		printf("fork event\n");
+		printf("... parent: %s/%d\n", thread__comm_str(parent), parent->tid);
+		printf("...  child: %s/%d\n", thread__comm_str(child), child->tid);
 	}
-	register_pid(fork_event->parent_pid, fork_event->parent_comm);
-	register_pid(fork_event->child_pid, fork_event->child_comm);
-}
 
-static struct trace_sched_handler replay_ops  = {
-	.wakeup_event		= replay_wakeup_event,
-	.switch_event		= replay_switch_event,
-	.fork_event		= replay_fork_event,
-};
+	register_pid(sched, parent->tid, thread__comm_str(parent));
+	register_pid(sched, child->tid, thread__comm_str(child));
+	return 0;
+}
 
 struct sort_dimension {
 	const char		*name;
@@ -862,8 +751,6 @@ struct sort_dimension {
 	struct list_head	list;
 };
 
-static LIST_HEAD(cmp_pid);
-
 static int
 thread_lat_cmp(struct list_head *list, struct work_atoms *l, struct work_atoms *r)
 {
@@ -932,43 +819,37 @@ __thread_latency_insert(struct rb_root *root, struct work_atoms *data,
 	rb_insert_color(&data->node, root);
 }
 
-static void thread_atoms_insert(struct thread *thread)
+static int thread_atoms_insert(struct perf_sched *sched, struct thread *thread)
 {
 	struct work_atoms *atoms = zalloc(sizeof(*atoms));
-	if (!atoms)
-		die("No memory");
+	if (!atoms) {
+		pr_err("No memory at %s\n", __func__);
+		return -1;
+	}
 
 	atoms->thread = thread;
 	INIT_LIST_HEAD(&atoms->work_list);
-	__thread_latency_insert(&atom_root, atoms, &cmp_pid);
-}
-
-static void
-latency_fork_event(struct trace_fork_event *fork_event __used,
-		   struct event *event __used,
-		   int cpu __used,
-		   u64 timestamp __used,
-		   struct thread *thread __used)
-{
-	/* should insert the newcomer */
+	__thread_latency_insert(&sched->atom_root, atoms, &sched->cmp_pid);
+	return 0;
 }
 
-__used
-static char sched_out_state(struct trace_switch_event *switch_event)
+static char sched_out_state(u64 prev_state)
 {
 	const char *str = TASK_STATE_TO_CHAR_STR;
 
-	return str[switch_event->prev_state];
+	return str[prev_state];
 }
 
-static void
+static int
 add_sched_out_event(struct work_atoms *atoms,
 		    char run_state,
 		    u64 timestamp)
 {
 	struct work_atom *atom = zalloc(sizeof(*atom));
-	if (!atom)
-		die("Non memory");
+	if (!atom) {
+		pr_err("Non memory at %s", __func__);
+		return -1;
+	}
 
 	atom->sched_out_time = timestamp;
 
@@ -978,10 +859,12 @@ add_sched_out_event(struct work_atoms *atoms,
 	}
 
 	list_add_tail(&atom->list, &atoms->work_list);
+	return 0;
 }
 
 static void
-add_runtime_event(struct work_atoms *atoms, u64 delta, u64 timestamp __used)
+add_runtime_event(struct work_atoms *atoms, u64 delta,
+		  u64 timestamp __maybe_unused)
 {
 	struct work_atom *atom;
 
@@ -1024,106 +907,123 @@ add_sched_in_event(struct work_atoms *atoms, u64 timestamp)
 	atoms->nb_atoms++;
 }
 
-static void
-latency_switch_event(struct trace_switch_event *switch_event,
-		     struct perf_session *session,
-		     struct event *event __used,
-		     int cpu,
-		     u64 timestamp,
-		     struct thread *thread __used)
+static int latency_switch_event(struct perf_sched *sched,
+				struct perf_evsel *evsel,
+				struct perf_sample *sample,
+				struct machine *machine)
 {
+	const u32 prev_pid = perf_evsel__intval(evsel, sample, "prev_pid"),
+		  next_pid = perf_evsel__intval(evsel, sample, "next_pid");
+	const u64 prev_state = perf_evsel__intval(evsel, sample, "prev_state");
 	struct work_atoms *out_events, *in_events;
 	struct thread *sched_out, *sched_in;
-	u64 timestamp0;
+	u64 timestamp0, timestamp = sample->time;
+	int cpu = sample->cpu;
 	s64 delta;
 
 	BUG_ON(cpu >= MAX_CPUS || cpu < 0);
 
-	timestamp0 = cpu_last_switched[cpu];
-	cpu_last_switched[cpu] = timestamp;
+	timestamp0 = sched->cpu_last_switched[cpu];
+	sched->cpu_last_switched[cpu] = timestamp;
 	if (timestamp0)
 		delta = timestamp - timestamp0;
 	else
 		delta = 0;
 
-	if (delta < 0)
-		die("hm, delta: %Ld < 0 ?\n", delta);
-
+	if (delta < 0) {
+		pr_err("hm, delta: %" PRIu64 " < 0 ?\n", delta);
+		return -1;
+	}
 
-	sched_out = perf_session__findnew(session, switch_event->prev_pid);
-	sched_in = perf_session__findnew(session, switch_event->next_pid);
+	sched_out = machine__findnew_thread(machine, 0, prev_pid);
+	sched_in = machine__findnew_thread(machine, 0, next_pid);
 
-	out_events = thread_atoms_search(&atom_root, sched_out, &cmp_pid);
+	out_events = thread_atoms_search(&sched->atom_root, sched_out, &sched->cmp_pid);
 	if (!out_events) {
-		thread_atoms_insert(sched_out);
-		out_events = thread_atoms_search(&atom_root, sched_out, &cmp_pid);
-		if (!out_events)
-			die("out-event: Internal tree error");
+		if (thread_atoms_insert(sched, sched_out))
+			return -1;
+		out_events = thread_atoms_search(&sched->atom_root, sched_out, &sched->cmp_pid);
+		if (!out_events) {
+			pr_err("out-event: Internal tree error");
+			return -1;
+		}
 	}
-	add_sched_out_event(out_events, sched_out_state(switch_event), timestamp);
+	if (add_sched_out_event(out_events, sched_out_state(prev_state), timestamp))
+		return -1;
 
-	in_events = thread_atoms_search(&atom_root, sched_in, &cmp_pid);
+	in_events = thread_atoms_search(&sched->atom_root, sched_in, &sched->cmp_pid);
 	if (!in_events) {
-		thread_atoms_insert(sched_in);
-		in_events = thread_atoms_search(&atom_root, sched_in, &cmp_pid);
-		if (!in_events)
-			die("in-event: Internal tree error");
+		if (thread_atoms_insert(sched, sched_in))
+			return -1;
+		in_events = thread_atoms_search(&sched->atom_root, sched_in, &sched->cmp_pid);
+		if (!in_events) {
+			pr_err("in-event: Internal tree error");
+			return -1;
+		}
 		/*
 		 * Take came in we have not heard about yet,
 		 * add in an initial atom in runnable state:
 		 */
-		add_sched_out_event(in_events, 'R', timestamp);
+		if (add_sched_out_event(in_events, 'R', timestamp))
+			return -1;
 	}
 	add_sched_in_event(in_events, timestamp);
+
+	return 0;
 }
 
-static void
-latency_runtime_event(struct trace_runtime_event *runtime_event,
-		     struct perf_session *session,
-		     struct event *event __used,
-		     int cpu,
-		     u64 timestamp,
-		     struct thread *this_thread __used)
+static int latency_runtime_event(struct perf_sched *sched,
+				 struct perf_evsel *evsel,
+				 struct perf_sample *sample,
+				 struct machine *machine)
 {
-	struct thread *thread = perf_session__findnew(session, runtime_event->pid);
-	struct work_atoms *atoms = thread_atoms_search(&atom_root, thread, &cmp_pid);
+	const u32 pid	   = perf_evsel__intval(evsel, sample, "pid");
+	const u64 runtime  = perf_evsel__intval(evsel, sample, "runtime");
+	struct thread *thread = machine__findnew_thread(machine, 0, pid);
+	struct work_atoms *atoms = thread_atoms_search(&sched->atom_root, thread, &sched->cmp_pid);
+	u64 timestamp = sample->time;
+	int cpu = sample->cpu;
 
 	BUG_ON(cpu >= MAX_CPUS || cpu < 0);
 	if (!atoms) {
-		thread_atoms_insert(thread);
-		atoms = thread_atoms_search(&atom_root, thread, &cmp_pid);
-		if (!atoms)
-			die("in-event: Internal tree error");
-		add_sched_out_event(atoms, 'R', timestamp);
+		if (thread_atoms_insert(sched, thread))
+			return -1;
+		atoms = thread_atoms_search(&sched->atom_root, thread, &sched->cmp_pid);
+		if (!atoms) {
+			pr_err("in-event: Internal tree error");
+			return -1;
+		}
+		if (add_sched_out_event(atoms, 'R', timestamp))
+			return -1;
 	}
 
-	add_runtime_event(atoms, runtime_event->runtime, timestamp);
+	add_runtime_event(atoms, runtime, timestamp);
+	return 0;
 }
 
-static void
-latency_wakeup_event(struct trace_wakeup_event *wakeup_event,
-		     struct perf_session *session,
-		     struct event *__event __used,
-		     int cpu __used,
-		     u64 timestamp,
-		     struct thread *thread __used)
+static int latency_wakeup_event(struct perf_sched *sched,
+				struct perf_evsel *evsel,
+				struct perf_sample *sample,
+				struct machine *machine)
 {
+	const u32 pid	  = perf_evsel__intval(evsel, sample, "pid");
 	struct work_atoms *atoms;
 	struct work_atom *atom;
 	struct thread *wakee;
+	u64 timestamp = sample->time;
 
-	/* Note for later, it may be interesting to observe the failing cases */
-	if (!wakeup_event->success)
-		return;
-
-	wakee = perf_session__findnew(session, wakeup_event->pid);
-	atoms = thread_atoms_search(&atom_root, wakee, &cmp_pid);
+	wakee = machine__findnew_thread(machine, 0, pid);
+	atoms = thread_atoms_search(&sched->atom_root, wakee, &sched->cmp_pid);
 	if (!atoms) {
-		thread_atoms_insert(wakee);
-		atoms = thread_atoms_search(&atom_root, wakee, &cmp_pid);
-		if (!atoms)
-			die("wakeup-event: Internal tree error");
-		add_sched_out_event(atoms, 'S', timestamp);
+		if (thread_atoms_insert(sched, wakee))
+			return -1;
+		atoms = thread_atoms_search(&sched->atom_root, wakee, &sched->cmp_pid);
+		if (!atoms) {
+			pr_err("wakeup-event: Internal tree error");
+			return -1;
+		}
+		if (add_sched_out_event(atoms, 'S', timestamp))
+			return -1;
 	}
 
 	BUG_ON(list_empty(&atoms->work_list));
@@ -1131,31 +1031,37 @@ latency_wakeup_event(struct trace_wakeup_event *wakeup_event,
 	atom = list_entry(atoms->work_list.prev, struct work_atom, list);
 
 	/*
+	 * As we do not guarantee the wakeup event happens when
+	 * task is out of run queue, also may happen when task is
+	 * on run queue and wakeup only change ->state to TASK_RUNNING,
+	 * then we should not set the ->wake_up_time when wake up a
+	 * task which is on run queue.
+	 *
 	 * You WILL be missing events if you've recorded only
 	 * one CPU, or are only looking at only one, so don't
-	 * make useless noise.
+	 * skip in this case.
 	 */
-	if (profile_cpu == -1 && atom->state != THREAD_SLEEPING)
-		nr_state_machine_bugs++;
+	if (sched->profile_cpu == -1 && atom->state != THREAD_SLEEPING)
+		return 0;
 
-	nr_timestamps++;
+	sched->nr_timestamps++;
 	if (atom->sched_out_time > timestamp) {
-		nr_unordered_timestamps++;
-		return;
+		sched->nr_unordered_timestamps++;
+		return 0;
 	}
 
 	atom->state = THREAD_WAIT_CPU;
 	atom->wake_up_time = timestamp;
+	return 0;
 }
 
-static void
-latency_migrate_task_event(struct trace_migrate_task_event *migrate_task_event,
-		     struct perf_session *session,
-		     struct event *__event __used,
-		     int cpu __used,
-		     u64 timestamp,
-		     struct thread *thread __used)
+static int latency_migrate_task_event(struct perf_sched *sched,
+				      struct perf_evsel *evsel,
+				      struct perf_sample *sample,
+				      struct machine *machine)
 {
+	const u32 pid = perf_evsel__intval(evsel, sample, "pid");
+	u64 timestamp = sample->time;
 	struct work_atoms *atoms;
 	struct work_atom *atom;
 	struct thread *migrant;
@@ -1163,18 +1069,22 @@ latency_migrate_task_event(struct trace_migrate_task_event *migrate_task_event,
 	/*
 	 * Only need to worry about migration when profiling one CPU.
 	 */
-	if (profile_cpu == -1)
-		return;
+	if (sched->profile_cpu == -1)
+		return 0;
 
-	migrant = perf_session__findnew(session, migrate_task_event->pid);
-	atoms = thread_atoms_search(&atom_root, migrant, &cmp_pid);
+	migrant = machine__findnew_thread(machine, 0, pid);
+	atoms = thread_atoms_search(&sched->atom_root, migrant, &sched->cmp_pid);
 	if (!atoms) {
-		thread_atoms_insert(migrant);
-		register_pid(migrant->pid, migrant->comm);
-		atoms = thread_atoms_search(&atom_root, migrant, &cmp_pid);
-		if (!atoms)
-			die("migration-event: Internal tree error");
-		add_sched_out_event(atoms, 'R', timestamp);
+		if (thread_atoms_insert(sched, migrant))
+			return -1;
+		register_pid(sched, migrant->tid, thread__comm_str(migrant));
+		atoms = thread_atoms_search(&sched->atom_root, migrant, &sched->cmp_pid);
+		if (!atoms) {
+			pr_err("migration-event: Internal tree error");
+			return -1;
+		}
+		if (add_sched_out_event(atoms, 'R', timestamp))
+			return -1;
 	}
 
 	BUG_ON(list_empty(&atoms->work_list));
@@ -1182,21 +1092,15 @@ latency_migrate_task_event(struct trace_migrate_task_event *migrate_task_event,
 	atom = list_entry(atoms->work_list.prev, struct work_atom, list);
 	atom->sched_in_time = atom->sched_out_time = atom->wake_up_time = timestamp;
 
-	nr_timestamps++;
+	sched->nr_timestamps++;
 
 	if (atom->sched_out_time > timestamp)
-		nr_unordered_timestamps++;
-}
+		sched->nr_unordered_timestamps++;
 
-static struct trace_sched_handler lat_ops  = {
-	.wakeup_event		= latency_wakeup_event,
-	.switch_event		= latency_switch_event,
-	.runtime_event		= latency_runtime_event,
-	.fork_event		= latency_fork_event,
-	.migrate_task_event	= latency_migrate_task_event,
-};
+	return 0;
+}
 
-static void output_lat_thread(struct work_atoms *work_list)
+static void output_lat_thread(struct perf_sched *sched, struct work_atoms *work_list)
 {
 	int i;
 	int ret;
@@ -1207,20 +1111,20 @@ static void output_lat_thread(struct work_atoms *work_list)
 	/*
 	 * Ignore idle threads:
 	 */
-	if (!strcmp(work_list->thread->comm, "swapper"))
+	if (!strcmp(thread__comm_str(work_list->thread), "swapper"))
 		return;
 
-	all_runtime += work_list->total_runtime;
-	all_count += work_list->nb_atoms;
+	sched->all_runtime += work_list->total_runtime;
+	sched->all_count   += work_list->nb_atoms;
 
-	ret = printf("  %s:%d ", work_list->thread->comm, work_list->thread->pid);
+	ret = printf("  %s:%d ", thread__comm_str(work_list->thread), work_list->thread->tid);
 
 	for (i = 0; i < 24 - ret; i++)
 		printf(" ");
 
 	avg = work_list->total_lat / work_list->nb_atoms;
 
-	printf("|%11.3f ms |%9llu | avg:%9.3f ms | max:%9.3f ms | max at: %9.6f s\n",
+	printf("|%11.3f ms |%9" PRIu64 " | avg:%9.3f ms | max:%9.3f ms | max at: %13.6f s\n",
 	      (double)work_list->total_runtime / 1e6,
 		 work_list->nb_atoms, (double)avg / 1e6,
 		 (double)work_list->max_lat / 1e6,
@@ -1229,19 +1133,14 @@ static void output_lat_thread(struct work_atoms *work_list)
 
 static int pid_cmp(struct work_atoms *l, struct work_atoms *r)
 {
-	if (l->thread->pid < r->thread->pid)
+	if (l->thread->tid < r->thread->tid)
 		return -1;
-	if (l->thread->pid > r->thread->pid)
+	if (l->thread->tid > r->thread->tid)
 		return 1;
 
 	return 0;
 }
 
-static struct sort_dimension pid_sort_dimension = {
-	.name			= "pid",
-	.cmp			= pid_cmp,
-};
-
 static int avg_cmp(struct work_atoms *l, struct work_atoms *r)
 {
 	u64 avgl, avgr;
@@ -1263,11 +1162,6 @@ static int avg_cmp(struct work_atoms *l, struct work_atoms *r)
 	return 0;
 }
 
-static struct sort_dimension avg_sort_dimension = {
-	.name			= "avg",
-	.cmp			= avg_cmp,
-};
-
 static int max_cmp(struct work_atoms *l, struct work_atoms *r)
 {
 	if (l->max_lat < r->max_lat)
@@ -1278,11 +1172,6 @@ static int max_cmp(struct work_atoms *l, struct work_atoms *r)
 	return 0;
 }
 
-static struct sort_dimension max_sort_dimension = {
-	.name			= "max",
-	.cmp			= max_cmp,
-};
-
 static int switch_cmp(struct work_atoms *l, struct work_atoms *r)
 {
 	if (l->nb_atoms < r->nb_atoms)
@@ -1293,11 +1182,6 @@ static int switch_cmp(struct work_atoms *l, struct work_atoms *r)
 	return 0;
 }
 
-static struct sort_dimension switch_sort_dimension = {
-	.name			= "switch",
-	.cmp			= switch_cmp,
-};
-
 static int runtime_cmp(struct work_atoms *l, struct work_atoms *r)
 {
 	if (l->total_runtime < r->total_runtime)
@@ -1308,28 +1192,38 @@ static int runtime_cmp(struct work_atoms *l, struct work_atoms *r)
 	return 0;
 }
 
-static struct sort_dimension runtime_sort_dimension = {
-	.name			= "runtime",
-	.cmp			= runtime_cmp,
-};
-
-static struct sort_dimension *available_sorts[] = {
-	&pid_sort_dimension,
-	&avg_sort_dimension,
-	&max_sort_dimension,
-	&switch_sort_dimension,
-	&runtime_sort_dimension,
-};
-
-#define NB_AVAILABLE_SORTS	(int)(sizeof(available_sorts) / sizeof(struct sort_dimension *))
-
-static LIST_HEAD(sort_list);
-
 static int sort_dimension__add(const char *tok, struct list_head *list)
 {
-	int i;
-
-	for (i = 0; i < NB_AVAILABLE_SORTS; i++) {
+	size_t i;
+	static struct sort_dimension avg_sort_dimension = {
+		.name = "avg",
+		.cmp  = avg_cmp,
+	};
+	static struct sort_dimension max_sort_dimension = {
+		.name = "max",
+		.cmp  = max_cmp,
+	};
+	static struct sort_dimension pid_sort_dimension = {
+		.name = "pid",
+		.cmp  = pid_cmp,
+	};
+	static struct sort_dimension runtime_sort_dimension = {
+		.name = "runtime",
+		.cmp  = runtime_cmp,
+	};
+	static struct sort_dimension switch_sort_dimension = {
+		.name = "switch",
+		.cmp  = switch_cmp,
+	};
+	struct sort_dimension *available_sorts[] = {
+		&pid_sort_dimension,
+		&avg_sort_dimension,
+		&max_sort_dimension,
+		&switch_sort_dimension,
+		&runtime_sort_dimension,
+	};
+
+	for (i = 0; i < ARRAY_SIZE(available_sorts); i++) {
 		if (!strcmp(available_sorts[i]->name, tok)) {
 			list_add_tail(&available_sorts[i]->list, list);
 
@@ -1340,535 +1234,412 @@ static int sort_dimension__add(const char *tok, struct list_head *list)
 	return -1;
 }
 
-static void setup_sorting(void);
-
-static void sort_lat(void)
+static void perf_sched__sort_lat(struct perf_sched *sched)
 {
 	struct rb_node *node;
 
 	for (;;) {
 		struct work_atoms *data;
-		node = rb_first(&atom_root);
+		node = rb_first(&sched->atom_root);
 		if (!node)
 			break;
 
-		rb_erase(node, &atom_root);
+		rb_erase(node, &sched->atom_root);
 		data = rb_entry(node, struct work_atoms, node);
-		__thread_latency_insert(&sorted_atom_root, data, &sort_list);
+		__thread_latency_insert(&sched->sorted_atom_root, data, &sched->sort_list);
 	}
 }
 
-static struct trace_sched_handler *trace_handler;
-
-static void
-process_sched_wakeup_event(void *data, struct perf_session *session,
-			   struct event *event,
-			   int cpu __used,
-			   u64 timestamp __used,
-			   struct thread *thread __used)
+static int process_sched_wakeup_event(struct perf_tool *tool,
+				      struct perf_evsel *evsel,
+				      struct perf_sample *sample,
+				      struct machine *machine)
 {
-	struct trace_wakeup_event wakeup_event;
-
-	FILL_COMMON_FIELDS(wakeup_event, event, data);
+	struct perf_sched *sched = container_of(tool, struct perf_sched, tool);
 
-	FILL_ARRAY(wakeup_event, comm, event, data);
-	FILL_FIELD(wakeup_event, pid, event, data);
-	FILL_FIELD(wakeup_event, prio, event, data);
-	FILL_FIELD(wakeup_event, success, event, data);
-	FILL_FIELD(wakeup_event, cpu, event, data);
+	if (sched->tp_handler->wakeup_event)
+		return sched->tp_handler->wakeup_event(sched, evsel, sample, machine);
 
-	if (trace_handler->wakeup_event)
-		trace_handler->wakeup_event(&wakeup_event, session, event,
-					    cpu, timestamp, thread);
+	return 0;
 }
 
-/*
- * Track the current task - that way we can know whether there's any
- * weird events, such as a task being switched away that is not current.
- */
-static int max_cpu;
-
-static u32 curr_pid[MAX_CPUS] = { [0 ... MAX_CPUS-1] = -1 };
-
-static struct thread *curr_thread[MAX_CPUS];
-
-static char next_shortname1 = 'A';
-static char next_shortname2 = '0';
-
-static void
-map_switch_event(struct trace_switch_event *switch_event,
-		 struct perf_session *session,
-		 struct event *event __used,
-		 int this_cpu,
-		 u64 timestamp,
-		 struct thread *thread __used)
+static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
+			    struct perf_sample *sample, struct machine *machine)
 {
-	struct thread *sched_out, *sched_in;
+	const u32 next_pid = perf_evsel__intval(evsel, sample, "next_pid");
+	struct thread *sched_in;
 	int new_shortname;
-	u64 timestamp0;
+	u64 timestamp0, timestamp = sample->time;
 	s64 delta;
-	int cpu;
+	int cpu, this_cpu = sample->cpu;
 
 	BUG_ON(this_cpu >= MAX_CPUS || this_cpu < 0);
 
-	if (this_cpu > max_cpu)
-		max_cpu = this_cpu;
+	if (this_cpu > sched->max_cpu)
+		sched->max_cpu = this_cpu;
 
-	timestamp0 = cpu_last_switched[this_cpu];
-	cpu_last_switched[this_cpu] = timestamp;
+	timestamp0 = sched->cpu_last_switched[this_cpu];
+	sched->cpu_last_switched[this_cpu] = timestamp;
 	if (timestamp0)
 		delta = timestamp - timestamp0;
 	else
 		delta = 0;
 
-	if (delta < 0)
-		die("hm, delta: %Ld < 0 ?\n", delta);
-
+	if (delta < 0) {
+		pr_err("hm, delta: %" PRIu64 " < 0 ?\n", delta);
+		return -1;
+	}
 
-	sched_out = perf_session__findnew(session, switch_event->prev_pid);
-	sched_in = perf_session__findnew(session, switch_event->next_pid);
+	sched_in = machine__findnew_thread(machine, 0, next_pid);
 
-	curr_thread[this_cpu] = sched_in;
+	sched->curr_thread[this_cpu] = sched_in;
 
 	printf("  ");
 
 	new_shortname = 0;
 	if (!sched_in->shortname[0]) {
-		sched_in->shortname[0] = next_shortname1;
-		sched_in->shortname[1] = next_shortname2;
-
-		if (next_shortname1 < 'Z') {
-			next_shortname1++;
+		if (!strcmp(thread__comm_str(sched_in), "swapper")) {
+			/*
+			 * Don't allocate a letter-number for swapper:0
+			 * as a shortname. Instead, we use '.' for it.
+			 */
+			sched_in->shortname[0] = '.';
+			sched_in->shortname[1] = ' ';
 		} else {
-			next_shortname1='A';
-			if (next_shortname2 < '9') {
-				next_shortname2++;
+			sched_in->shortname[0] = sched->next_shortname1;
+			sched_in->shortname[1] = sched->next_shortname2;
+
+			if (sched->next_shortname1 < 'Z') {
+				sched->next_shortname1++;
 			} else {
-				next_shortname2='0';
+				sched->next_shortname1 = 'A';
+				if (sched->next_shortname2 < '9')
+					sched->next_shortname2++;
+				else
+					sched->next_shortname2 = '0';
 			}
 		}
 		new_shortname = 1;
 	}
 
-	for (cpu = 0; cpu <= max_cpu; cpu++) {
+	for (cpu = 0; cpu <= sched->max_cpu; cpu++) {
 		if (cpu != this_cpu)
 			printf(" ");
 		else
 			printf("*");
 
-		if (curr_thread[cpu]) {
-			if (curr_thread[cpu]->pid)
-				printf("%2s ", curr_thread[cpu]->shortname);
-			else
-				printf(".  ");
-		} else
+		if (sched->curr_thread[cpu])
+			printf("%2s ", sched->curr_thread[cpu]->shortname);
+		else
 			printf("   ");
 	}
 
 	printf("  %12.6f secs ", (double)timestamp/1e9);
 	if (new_shortname) {
 		printf("%s => %s:%d\n",
-			sched_in->shortname, sched_in->comm, sched_in->pid);
+		       sched_in->shortname, thread__comm_str(sched_in), sched_in->tid);
 	} else {
 		printf("\n");
 	}
-}
 
+	return 0;
+}
 
-static void
-process_sched_switch_event(void *data, struct perf_session *session,
-			   struct event *event,
-			   int this_cpu,
-			   u64 timestamp __used,
-			   struct thread *thread __used)
+static int process_sched_switch_event(struct perf_tool *tool,
+				      struct perf_evsel *evsel,
+				      struct perf_sample *sample,
+				      struct machine *machine)
 {
-	struct trace_switch_event switch_event;
-
-	FILL_COMMON_FIELDS(switch_event, event, data);
-
-	FILL_ARRAY(switch_event, prev_comm, event, data);
-	FILL_FIELD(switch_event, prev_pid, event, data);
-	FILL_FIELD(switch_event, prev_prio, event, data);
-	FILL_FIELD(switch_event, prev_state, event, data);
-	FILL_ARRAY(switch_event, next_comm, event, data);
-	FILL_FIELD(switch_event, next_pid, event, data);
-	FILL_FIELD(switch_event, next_prio, event, data);
+	struct perf_sched *sched = container_of(tool, struct perf_sched, tool);
+	int this_cpu = sample->cpu, err = 0;
+	u32 prev_pid = perf_evsel__intval(evsel, sample, "prev_pid"),
+	    next_pid = perf_evsel__intval(evsel, sample, "next_pid");
 
-	if (curr_pid[this_cpu] != (u32)-1) {
+	if (sched->curr_pid[this_cpu] != (u32)-1) {
 		/*
 		 * Are we trying to switch away a PID that is
 		 * not current?
 		 */
-		if (curr_pid[this_cpu] != switch_event.prev_pid)
-			nr_context_switch_bugs++;
+		if (sched->curr_pid[this_cpu] != prev_pid)
+			sched->nr_context_switch_bugs++;
 	}
-	if (trace_handler->switch_event)
-		trace_handler->switch_event(&switch_event, session, event,
-					    this_cpu, timestamp, thread);
 
-	curr_pid[this_cpu] = switch_event.next_pid;
+	if (sched->tp_handler->switch_event)
+		err = sched->tp_handler->switch_event(sched, evsel, sample, machine);
+
+	sched->curr_pid[this_cpu] = next_pid;
+	return err;
 }
 
-static void
-process_sched_runtime_event(void *data, struct perf_session *session,
-			   struct event *event,
-			   int cpu __used,
-			   u64 timestamp __used,
-			   struct thread *thread __used)
+static int process_sched_runtime_event(struct perf_tool *tool,
+				       struct perf_evsel *evsel,
+				       struct perf_sample *sample,
+				       struct machine *machine)
 {
-	struct trace_runtime_event runtime_event;
+	struct perf_sched *sched = container_of(tool, struct perf_sched, tool);
 
-	FILL_ARRAY(runtime_event, comm, event, data);
-	FILL_FIELD(runtime_event, pid, event, data);
-	FILL_FIELD(runtime_event, runtime, event, data);
-	FILL_FIELD(runtime_event, vruntime, event, data);
+	if (sched->tp_handler->runtime_event)
+		return sched->tp_handler->runtime_event(sched, evsel, sample, machine);
 
-	if (trace_handler->runtime_event)
-		trace_handler->runtime_event(&runtime_event, session, event, cpu, timestamp, thread);
+	return 0;
 }
 
-static void
-process_sched_fork_event(void *data,
-			 struct event *event,
-			 int cpu __used,
-			 u64 timestamp __used,
-			 struct thread *thread __used)
+static int perf_sched__process_fork_event(struct perf_tool *tool,
+					  union perf_event *event,
+					  struct perf_sample *sample,
+					  struct machine *machine)
 {
-	struct trace_fork_event fork_event;
+	struct perf_sched *sched = container_of(tool, struct perf_sched, tool);
 
-	FILL_COMMON_FIELDS(fork_event, event, data);
+	/* run the fork event through the perf machineruy */
+	perf_event__process_fork(tool, event, sample, machine);
 
-	FILL_ARRAY(fork_event, parent_comm, event, data);
-	FILL_FIELD(fork_event, parent_pid, event, data);
-	FILL_ARRAY(fork_event, child_comm, event, data);
-	FILL_FIELD(fork_event, child_pid, event, data);
+	/* and then run additional processing needed for this command */
+	if (sched->tp_handler->fork_event)
+		return sched->tp_handler->fork_event(sched, event, machine);
 
-	if (trace_handler->fork_event)
-		trace_handler->fork_event(&fork_event, event,
-					  cpu, timestamp, thread);
-}
-
-static void
-process_sched_exit_event(struct event *event,
-			 int cpu __used,
-			 u64 timestamp __used,
-			 struct thread *thread __used)
-{
-	if (verbose)
-		printf("sched_exit event %p\n", event);
+	return 0;
 }
 
-static void
-process_sched_migrate_task_event(void *data, struct perf_session *session,
-			   struct event *event,
-			   int cpu __used,
-			   u64 timestamp __used,
-			   struct thread *thread __used)
+static int process_sched_migrate_task_event(struct perf_tool *tool,
+					    struct perf_evsel *evsel,
+					    struct perf_sample *sample,
+					    struct machine *machine)
 {
-	struct trace_migrate_task_event migrate_task_event;
-
-	FILL_COMMON_FIELDS(migrate_task_event, event, data);
+	struct perf_sched *sched = container_of(tool, struct perf_sched, tool);
 
-	FILL_ARRAY(migrate_task_event, comm, event, data);
-	FILL_FIELD(migrate_task_event, pid, event, data);
-	FILL_FIELD(migrate_task_event, prio, event, data);
-	FILL_FIELD(migrate_task_event, cpu, event, data);
+	if (sched->tp_handler->migrate_task_event)
+		return sched->tp_handler->migrate_task_event(sched, evsel, sample, machine);
 
-	if (trace_handler->migrate_task_event)
-		trace_handler->migrate_task_event(&migrate_task_event, session,
-						 event, cpu, timestamp, thread);
+	return 0;
 }
 
-static void
-process_raw_event(event_t *raw_event __used, struct perf_session *session,
-		  void *data, int cpu, u64 timestamp, struct thread *thread)
-{
-	struct event *event;
-	int type;
-
-
-	type = trace_parse_common_type(data);
-	event = trace_find_event(type);
-
-	if (!strcmp(event->name, "sched_switch"))
-		process_sched_switch_event(data, session, event, cpu, timestamp, thread);
-	if (!strcmp(event->name, "sched_stat_runtime"))
-		process_sched_runtime_event(data, session, event, cpu, timestamp, thread);
-	if (!strcmp(event->name, "sched_wakeup"))
-		process_sched_wakeup_event(data, session, event, cpu, timestamp, thread);
-	if (!strcmp(event->name, "sched_wakeup_new"))
-		process_sched_wakeup_event(data, session, event, cpu, timestamp, thread);
-	if (!strcmp(event->name, "sched_process_fork"))
-		process_sched_fork_event(data, event, cpu, timestamp, thread);
-	if (!strcmp(event->name, "sched_process_exit"))
-		process_sched_exit_event(event, cpu, timestamp, thread);
-	if (!strcmp(event->name, "sched_migrate_task"))
-		process_sched_migrate_task_event(data, session, event, cpu, timestamp, thread);
-}
+typedef int (*tracepoint_handler)(struct perf_tool *tool,
+				  struct perf_evsel *evsel,
+				  struct perf_sample *sample,
+				  struct machine *machine);
 
-static int process_sample_event(event_t *event, struct perf_session *session)
+static int perf_sched__process_tracepoint_sample(struct perf_tool *tool __maybe_unused,
+						 union perf_event *event __maybe_unused,
+						 struct perf_sample *sample,
+						 struct perf_evsel *evsel,
+						 struct machine *machine)
 {
-	struct sample_data data;
-	struct thread *thread;
+	int err = 0;
 
-	if (!(session->sample_type & PERF_SAMPLE_RAW))
-		return 0;
+	evsel->hists.stats.total_period += sample->period;
+	hists__inc_nr_samples(&evsel->hists, true);
 
-	memset(&data, 0, sizeof(data));
-	data.time = -1;
-	data.cpu = -1;
-	data.period = -1;
-
-	event__parse_sample(event, session->sample_type, &data);
+	if (evsel->handler != NULL) {
+		tracepoint_handler f = evsel->handler;
+		err = f(tool, evsel, sample, machine);
+	}
 
-	dump_printf("(IP, %d): %d/%d: %#Lx period: %Ld\n", event->header.misc,
-		    data.pid, data.tid, data.ip, data.period);
+	return err;
+}
 
-	thread = perf_session__findnew(session, data.pid);
-	if (thread == NULL) {
-		pr_debug("problem processing %d event, skipping it.\n",
-			 event->header.type);
+static int perf_sched__read_events(struct perf_sched *sched,
+				   struct perf_session **psession)
+{
+	const struct perf_evsel_str_handler handlers[] = {
+		{ "sched:sched_switch",	      process_sched_switch_event, },
+		{ "sched:sched_stat_runtime", process_sched_runtime_event, },
+		{ "sched:sched_wakeup",	      process_sched_wakeup_event, },
+		{ "sched:sched_wakeup_new",   process_sched_wakeup_event, },
+		{ "sched:sched_migrate_task", process_sched_migrate_task_event, },
+	};
+	struct perf_session *session;
+	struct perf_data_file file = {
+		.path = input_name,
+		.mode = PERF_DATA_MODE_READ,
+	};
+
+	session = perf_session__new(&file, false, &sched->tool);
+	if (session == NULL) {
+		pr_debug("No Memory for session\n");
 		return -1;
 	}
 
-	dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid);
+	if (perf_session__set_tracepoints_handlers(session, handlers))
+		goto out_delete;
 
-	if (profile_cpu != -1 && profile_cpu != (int)data.cpu)
-		return 0;
-
-	process_raw_event(event, session, data.raw_data, data.cpu, data.time, thread);
-
-	return 0;
-}
+	if (perf_session__has_traces(session, "record -R")) {
+		int err = perf_session__process_events(session, &sched->tool);
+		if (err) {
+			pr_err("Failed to process events, error %d", err);
+			goto out_delete;
+		}
 
-static struct perf_event_ops event_ops = {
-	.sample			= process_sample_event,
-	.comm			= event__process_comm,
-	.lost			= event__process_lost,
-	.fork			= event__process_task,
-	.ordered_samples	= true,
-};
+		sched->nr_events      = session->stats.nr_events[0];
+		sched->nr_lost_events = session->stats.total_lost;
+		sched->nr_lost_chunks = session->stats.nr_events[PERF_RECORD_LOST];
+	}
 
-static int read_events(void)
-{
-	int err = -EINVAL;
-	struct perf_session *session = perf_session__new(input_name, O_RDONLY, 0, false);
-	if (session == NULL)
-		return -ENOMEM;
+	if (psession)
+		*psession = session;
+	else
+		perf_session__delete(session);
 
-	if (perf_session__has_traces(session, "record -R")) {
-		err = perf_session__process_events(session, &event_ops);
-		nr_events      = session->hists.stats.nr_events[0];
-		nr_lost_events = session->hists.stats.total_lost;
-		nr_lost_chunks = session->hists.stats.nr_events[PERF_RECORD_LOST];
-	}
+	return 0;
 
+out_delete:
 	perf_session__delete(session);
-	return err;
+	return -1;
 }
 
-static void print_bad_events(void)
+static void print_bad_events(struct perf_sched *sched)
 {
-	if (nr_unordered_timestamps && nr_timestamps) {
+	if (sched->nr_unordered_timestamps && sched->nr_timestamps) {
 		printf("  INFO: %.3f%% unordered timestamps (%ld out of %ld)\n",
-			(double)nr_unordered_timestamps/(double)nr_timestamps*100.0,
-			nr_unordered_timestamps, nr_timestamps);
+			(double)sched->nr_unordered_timestamps/(double)sched->nr_timestamps*100.0,
+			sched->nr_unordered_timestamps, sched->nr_timestamps);
 	}
-	if (nr_lost_events && nr_events) {
+	if (sched->nr_lost_events && sched->nr_events) {
 		printf("  INFO: %.3f%% lost events (%ld out of %ld, in %ld chunks)\n",
-			(double)nr_lost_events/(double)nr_events*100.0,
-			nr_lost_events, nr_events, nr_lost_chunks);
-	}
-	if (nr_state_machine_bugs && nr_timestamps) {
-		printf("  INFO: %.3f%% state machine bugs (%ld out of %ld)",
-			(double)nr_state_machine_bugs/(double)nr_timestamps*100.0,
-			nr_state_machine_bugs, nr_timestamps);
-		if (nr_lost_events)
-			printf(" (due to lost events?)");
-		printf("\n");
+			(double)sched->nr_lost_events/(double)sched->nr_events * 100.0,
+			sched->nr_lost_events, sched->nr_events, sched->nr_lost_chunks);
 	}
-	if (nr_context_switch_bugs && nr_timestamps) {
+	if (sched->nr_context_switch_bugs && sched->nr_timestamps) {
 		printf("  INFO: %.3f%% context switch bugs (%ld out of %ld)",
-			(double)nr_context_switch_bugs/(double)nr_timestamps*100.0,
-			nr_context_switch_bugs, nr_timestamps);
-		if (nr_lost_events)
+			(double)sched->nr_context_switch_bugs/(double)sched->nr_timestamps*100.0,
+			sched->nr_context_switch_bugs, sched->nr_timestamps);
+		if (sched->nr_lost_events)
 			printf(" (due to lost events?)");
 		printf("\n");
 	}
 }
 
-static void __cmd_lat(void)
+static int perf_sched__lat(struct perf_sched *sched)
 {
 	struct rb_node *next;
+	struct perf_session *session;
 
 	setup_pager();
-	read_events();
-	sort_lat();
 
-	printf("\n ---------------------------------------------------------------------------------------------------------------\n");
-	printf("  Task                  |   Runtime ms  | Switches | Average delay ms | Maximum delay ms | Maximum delay at     |\n");
-	printf(" ---------------------------------------------------------------------------------------------------------------\n");
+	/* save session -- references to threads are held in work_list */
+	if (perf_sched__read_events(sched, &session))
+		return -1;
+
+	perf_sched__sort_lat(sched);
+
+	printf("\n -----------------------------------------------------------------------------------------------------------------\n");
+	printf("  Task                  |   Runtime ms  | Switches | Average delay ms | Maximum delay ms | Maximum delay at       |\n");
+	printf(" -----------------------------------------------------------------------------------------------------------------\n");
 
-	next = rb_first(&sorted_atom_root);
+	next = rb_first(&sched->sorted_atom_root);
 
 	while (next) {
 		struct work_atoms *work_list;
 
 		work_list = rb_entry(next, struct work_atoms, node);
-		output_lat_thread(work_list);
+		output_lat_thread(sched, work_list);
 		next = rb_next(next);
 	}
 
-	printf(" -----------------------------------------------------------------------------------------\n");
-	printf("  TOTAL:                |%11.3f ms |%9Ld |\n",
-		(double)all_runtime/1e6, all_count);
+	printf(" -----------------------------------------------------------------------------------------------------------------\n");
+	printf("  TOTAL:                |%11.3f ms |%9" PRIu64 " |\n",
+		(double)sched->all_runtime / 1e6, sched->all_count);
 
 	printf(" ---------------------------------------------------\n");
 
-	print_bad_events();
+	print_bad_events(sched);
 	printf("\n");
 
+	perf_session__delete(session);
+	return 0;
 }
 
-static struct trace_sched_handler map_ops  = {
-	.wakeup_event		= NULL,
-	.switch_event		= map_switch_event,
-	.runtime_event		= NULL,
-	.fork_event		= NULL,
-};
-
-static void __cmd_map(void)
+static int perf_sched__map(struct perf_sched *sched)
 {
-	max_cpu = sysconf(_SC_NPROCESSORS_CONF);
+	sched->max_cpu = sysconf(_SC_NPROCESSORS_CONF);
 
 	setup_pager();
-	read_events();
-	print_bad_events();
+	if (perf_sched__read_events(sched, NULL))
+		return -1;
+	print_bad_events(sched);
+	return 0;
 }
 
-static void __cmd_replay(void)
+static int perf_sched__replay(struct perf_sched *sched)
 {
 	unsigned long i;
 
-	calibrate_run_measurement_overhead();
-	calibrate_sleep_measurement_overhead();
+	calibrate_run_measurement_overhead(sched);
+	calibrate_sleep_measurement_overhead(sched);
 
-	test_calibrations();
+	test_calibrations(sched);
 
-	read_events();
+	if (perf_sched__read_events(sched, NULL))
+		return -1;
 
-	printf("nr_run_events:        %ld\n", nr_run_events);
-	printf("nr_sleep_events:      %ld\n", nr_sleep_events);
-	printf("nr_wakeup_events:     %ld\n", nr_wakeup_events);
+	printf("nr_run_events:        %ld\n", sched->nr_run_events);
+	printf("nr_sleep_events:      %ld\n", sched->nr_sleep_events);
+	printf("nr_wakeup_events:     %ld\n", sched->nr_wakeup_events);
 
-	if (targetless_wakeups)
-		printf("target-less wakeups:  %ld\n", targetless_wakeups);
-	if (multitarget_wakeups)
-		printf("multi-target wakeups: %ld\n", multitarget_wakeups);
-	if (nr_run_events_optimized)
+	if (sched->targetless_wakeups)
+		printf("target-less wakeups:  %ld\n", sched->targetless_wakeups);
+	if (sched->multitarget_wakeups)
+		printf("multi-target wakeups: %ld\n", sched->multitarget_wakeups);
+	if (sched->nr_run_events_optimized)
 		printf("run atoms optimized: %ld\n",
-			nr_run_events_optimized);
+			sched->nr_run_events_optimized);
 
-	print_task_traces();
-	add_cross_task_wakeups();
+	print_task_traces(sched);
+	add_cross_task_wakeups(sched);
 
-	create_tasks();
+	create_tasks(sched);
 	printf("------------------------------------------------------------\n");
-	for (i = 0; i < replay_repeat; i++)
-		run_one_test();
-}
-
-
-static const char * const sched_usage[] = {
-	"perf sched [<options>] {record|latency|map|replay|trace}",
-	NULL
-};
-
-static const struct option sched_options[] = {
-	OPT_STRING('i', "input", &input_name, "file",
-		    "input file name"),
-	OPT_INCR('v', "verbose", &verbose,
-		    "be more verbose (show symbol address, etc)"),
-	OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
-		    "dump raw trace in ASCII"),
-	OPT_END()
-};
-
-static const char * const latency_usage[] = {
-	"perf sched latency [<options>]",
-	NULL
-};
-
-static const struct option latency_options[] = {
-	OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
-		   "sort by key(s): runtime, switch, avg, max"),
-	OPT_INCR('v', "verbose", &verbose,
-		    "be more verbose (show symbol address, etc)"),
-	OPT_INTEGER('C', "CPU", &profile_cpu,
-		    "CPU to profile on"),
-	OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
-		    "dump raw trace in ASCII"),
-	OPT_END()
-};
+	for (i = 0; i < sched->replay_repeat; i++)
+		run_one_test(sched);
 
-static const char * const replay_usage[] = {
-	"perf sched replay [<options>]",
-	NULL
-};
-
-static const struct option replay_options[] = {
-	OPT_UINTEGER('r', "repeat", &replay_repeat,
-		     "repeat the workload replay N times (-1: infinite)"),
-	OPT_INCR('v', "verbose", &verbose,
-		    "be more verbose (show symbol address, etc)"),
-	OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
-		    "dump raw trace in ASCII"),
-	OPT_END()
-};
+	return 0;
+}
 
-static void setup_sorting(void)
+static void setup_sorting(struct perf_sched *sched, const struct option *options,
+			  const char * const usage_msg[])
 {
-	char *tmp, *tok, *str = strdup(sort_order);
+	char *tmp, *tok, *str = strdup(sched->sort_order);
 
 	for (tok = strtok_r(str, ", ", &tmp);
 			tok; tok = strtok_r(NULL, ", ", &tmp)) {
-		if (sort_dimension__add(tok, &sort_list) < 0) {
+		if (sort_dimension__add(tok, &sched->sort_list) < 0) {
 			error("Unknown --sort key: `%s'", tok);
-			usage_with_options(latency_usage, latency_options);
+			usage_with_options(usage_msg, options);
 		}
 	}
 
 	free(str);
 
-	sort_dimension__add("pid", &cmp_pid);
+	sort_dimension__add("pid", &sched->cmp_pid);
 }
 
-static const char *record_args[] = {
-	"record",
-	"-a",
-	"-R",
-	"-f",
-	"-m", "1024",
-	"-c", "1",
-	"-e", "sched:sched_switch:r",
-	"-e", "sched:sched_stat_wait:r",
-	"-e", "sched:sched_stat_sleep:r",
-	"-e", "sched:sched_stat_iowait:r",
-	"-e", "sched:sched_stat_runtime:r",
-	"-e", "sched:sched_process_exit:r",
-	"-e", "sched:sched_process_fork:r",
-	"-e", "sched:sched_wakeup:r",
-	"-e", "sched:sched_migrate_task:r",
-};
-
 static int __cmd_record(int argc, const char **argv)
 {
 	unsigned int rec_argc, i, j;
 	const char **rec_argv;
+	const char * const record_args[] = {
+		"record",
+		"-a",
+		"-R",
+		"-m", "1024",
+		"-c", "1",
+		"-e", "sched:sched_switch",
+		"-e", "sched:sched_stat_wait",
+		"-e", "sched:sched_stat_sleep",
+		"-e", "sched:sched_stat_iowait",
+		"-e", "sched:sched_stat_runtime",
+		"-e", "sched:sched_process_fork",
+		"-e", "sched:sched_wakeup",
+		"-e", "sched:sched_wakeup_new",
+		"-e", "sched:sched_migrate_task",
+	};
 
 	rec_argc = ARRAY_SIZE(record_args) + argc - 1;
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
 
+	if (rec_argv == NULL)
+		return -ENOMEM;
+
 	for (i = 0; i < ARRAY_SIZE(record_args); i++)
 		rec_argv[i] = strdup(record_args[i]);
 
@@ -1880,43 +1651,124 @@ static int __cmd_record(int argc, const char **argv)
 	return cmd_record(i, rec_argv, NULL);
 }
 
-int cmd_sched(int argc, const char **argv, const char *prefix __used)
+int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
 {
-	argc = parse_options(argc, argv, sched_options, sched_usage,
-			     PARSE_OPT_STOP_AT_NON_OPTION);
+	const char default_sort_order[] = "avg, max, switch, runtime";
+	struct perf_sched sched = {
+		.tool = {
+			.sample		 = perf_sched__process_tracepoint_sample,
+			.comm		 = perf_event__process_comm,
+			.lost		 = perf_event__process_lost,
+			.fork		 = perf_sched__process_fork_event,
+			.ordered_samples = true,
+		},
+		.cmp_pid	      = LIST_HEAD_INIT(sched.cmp_pid),
+		.sort_list	      = LIST_HEAD_INIT(sched.sort_list),
+		.start_work_mutex     = PTHREAD_MUTEX_INITIALIZER,
+		.work_done_wait_mutex = PTHREAD_MUTEX_INITIALIZER,
+		.sort_order	      = default_sort_order,
+		.replay_repeat	      = 10,
+		.profile_cpu	      = -1,
+		.next_shortname1      = 'A',
+		.next_shortname2      = '0',
+	};
+	const struct option latency_options[] = {
+	OPT_STRING('s', "sort", &sched.sort_order, "key[,key2...]",
+		   "sort by key(s): runtime, switch, avg, max"),
+	OPT_INCR('v', "verbose", &verbose,
+		    "be more verbose (show symbol address, etc)"),
+	OPT_INTEGER('C', "CPU", &sched.profile_cpu,
+		    "CPU to profile on"),
+	OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
+		    "dump raw trace in ASCII"),
+	OPT_END()
+	};
+	const struct option replay_options[] = {
+	OPT_UINTEGER('r', "repeat", &sched.replay_repeat,
+		     "repeat the workload replay N times (-1: infinite)"),
+	OPT_INCR('v', "verbose", &verbose,
+		    "be more verbose (show symbol address, etc)"),
+	OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
+		    "dump raw trace in ASCII"),
+	OPT_END()
+	};
+	const struct option sched_options[] = {
+	OPT_STRING('i', "input", &input_name, "file",
+		    "input file name"),
+	OPT_INCR('v', "verbose", &verbose,
+		    "be more verbose (show symbol address, etc)"),
+	OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
+		    "dump raw trace in ASCII"),
+	OPT_END()
+	};
+	const char * const latency_usage[] = {
+		"perf sched latency [<options>]",
+		NULL
+	};
+	const char * const replay_usage[] = {
+		"perf sched replay [<options>]",
+		NULL
+	};
+	const char *const sched_subcommands[] = { "record", "latency", "map",
+						  "replay", "script", NULL };
+	const char *sched_usage[] = {
+		NULL,
+		NULL
+	};
+	struct trace_sched_handler lat_ops  = {
+		.wakeup_event	    = latency_wakeup_event,
+		.switch_event	    = latency_switch_event,
+		.runtime_event	    = latency_runtime_event,
+		.migrate_task_event = latency_migrate_task_event,
+	};
+	struct trace_sched_handler map_ops  = {
+		.switch_event	    = map_switch_event,
+	};
+	struct trace_sched_handler replay_ops  = {
+		.wakeup_event	    = replay_wakeup_event,
+		.switch_event	    = replay_switch_event,
+		.fork_event	    = replay_fork_event,
+	};
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(sched.curr_pid); i++)
+		sched.curr_pid[i] = -1;
+
+	argc = parse_options_subcommand(argc, argv, sched_options, sched_subcommands,
+					sched_usage, PARSE_OPT_STOP_AT_NON_OPTION);
 	if (!argc)
 		usage_with_options(sched_usage, sched_options);
 
 	/*
-	 * Aliased to 'perf trace' for now:
+	 * Aliased to 'perf script' for now:
 	 */
-	if (!strcmp(argv[0], "trace"))
-		return cmd_trace(argc, argv, prefix);
+	if (!strcmp(argv[0], "script"))
+		return cmd_script(argc, argv, prefix);
 
 	symbol__init();
 	if (!strncmp(argv[0], "rec", 3)) {
 		return __cmd_record(argc, argv);
 	} else if (!strncmp(argv[0], "lat", 3)) {
-		trace_handler = &lat_ops;
+		sched.tp_handler = &lat_ops;
 		if (argc > 1) {
 			argc = parse_options(argc, argv, latency_options, latency_usage, 0);
 			if (argc)
 				usage_with_options(latency_usage, latency_options);
 		}
-		setup_sorting();
-		__cmd_lat();
+		setup_sorting(&sched, latency_options, latency_usage);
+		return perf_sched__lat(&sched);
 	} else if (!strcmp(argv[0], "map")) {
-		trace_handler = &map_ops;
-		setup_sorting();
-		__cmd_map();
+		sched.tp_handler = &map_ops;
+		setup_sorting(&sched, latency_options, latency_usage);
+		return perf_sched__map(&sched);
 	} else if (!strncmp(argv[0], "rep", 3)) {
-		trace_handler = &replay_ops;
+		sched.tp_handler = &replay_ops;
 		if (argc) {
 			argc = parse_options(argc, argv, replay_options, replay_usage, 0);
 			if (argc)
 				usage_with_options(replay_usage, replay_options);
 		}
-		__cmd_replay();
+		return perf_sched__replay(&sched);
 	} else {
 		usage_with_options(sched_usage, sched_options);
 	}
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
new file mode 100644
index 00000000000..9e9c91f5b7f
--- /dev/null
+++ b/tools/perf/builtin-script.c
@@ -0,0 +1,1826 @@
+#include "builtin.h"
+
+#include "perf.h"
+#include "util/cache.h"
+#include "util/debug.h"
+#include "util/exec_cmd.h"
+#include "util/header.h"
+#include "util/parse-options.h"
+#include "util/session.h"
+#include "util/tool.h"
+#include "util/symbol.h"
+#include "util/thread.h"
+#include "util/trace-event.h"
+#include "util/util.h"
+#include "util/evlist.h"
+#include "util/evsel.h"
+#include "util/sort.h"
+#include "util/data.h"
+#include <linux/bitmap.h>
+
+static char const		*script_name;
+static char const		*generate_script_lang;
+static bool			debug_mode;
+static u64			last_timestamp;
+static u64			nr_unordered;
+extern const struct option	record_options[];
+static bool			no_callchain;
+static bool			latency_format;
+static bool			system_wide;
+static const char		*cpu_list;
+static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
+
+enum perf_output_field {
+	PERF_OUTPUT_COMM            = 1U << 0,
+	PERF_OUTPUT_TID             = 1U << 1,
+	PERF_OUTPUT_PID             = 1U << 2,
+	PERF_OUTPUT_TIME            = 1U << 3,
+	PERF_OUTPUT_CPU             = 1U << 4,
+	PERF_OUTPUT_EVNAME          = 1U << 5,
+	PERF_OUTPUT_TRACE           = 1U << 6,
+	PERF_OUTPUT_IP              = 1U << 7,
+	PERF_OUTPUT_SYM             = 1U << 8,
+	PERF_OUTPUT_DSO             = 1U << 9,
+	PERF_OUTPUT_ADDR            = 1U << 10,
+	PERF_OUTPUT_SYMOFFSET       = 1U << 11,
+	PERF_OUTPUT_SRCLINE         = 1U << 12,
+};
+
+struct output_option {
+	const char *str;
+	enum perf_output_field field;
+} all_output_options[] = {
+	{.str = "comm",  .field = PERF_OUTPUT_COMM},
+	{.str = "tid",   .field = PERF_OUTPUT_TID},
+	{.str = "pid",   .field = PERF_OUTPUT_PID},
+	{.str = "time",  .field = PERF_OUTPUT_TIME},
+	{.str = "cpu",   .field = PERF_OUTPUT_CPU},
+	{.str = "event", .field = PERF_OUTPUT_EVNAME},
+	{.str = "trace", .field = PERF_OUTPUT_TRACE},
+	{.str = "ip",    .field = PERF_OUTPUT_IP},
+	{.str = "sym",   .field = PERF_OUTPUT_SYM},
+	{.str = "dso",   .field = PERF_OUTPUT_DSO},
+	{.str = "addr",  .field = PERF_OUTPUT_ADDR},
+	{.str = "symoff", .field = PERF_OUTPUT_SYMOFFSET},
+	{.str = "srcline", .field = PERF_OUTPUT_SRCLINE},
+};
+
+/* default set to maintain compatibility with current format */
+static struct {
+	bool user_set;
+	bool wildcard_set;
+	unsigned int print_ip_opts;
+	u64 fields;
+	u64 invalid_fields;
+} output[PERF_TYPE_MAX] = {
+
+	[PERF_TYPE_HARDWARE] = {
+		.user_set = false,
+
+		.fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
+			      PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
+			      PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
+				  PERF_OUTPUT_SYM | PERF_OUTPUT_DSO,
+
+		.invalid_fields = PERF_OUTPUT_TRACE,
+	},
+
+	[PERF_TYPE_SOFTWARE] = {
+		.user_set = false,
+
+		.fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
+			      PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
+			      PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
+				  PERF_OUTPUT_SYM | PERF_OUTPUT_DSO,
+
+		.invalid_fields = PERF_OUTPUT_TRACE,
+	},
+
+	[PERF_TYPE_TRACEPOINT] = {
+		.user_set = false,
+
+		.fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
+				  PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
+				  PERF_OUTPUT_EVNAME | PERF_OUTPUT_TRACE,
+	},
+
+	[PERF_TYPE_RAW] = {
+		.user_set = false,
+
+		.fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
+			      PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
+			      PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
+				  PERF_OUTPUT_SYM | PERF_OUTPUT_DSO,
+
+		.invalid_fields = PERF_OUTPUT_TRACE,
+	},
+};
+
+static bool output_set_by_user(void)
+{
+	int j;
+	for (j = 0; j < PERF_TYPE_MAX; ++j) {
+		if (output[j].user_set)
+			return true;
+	}
+	return false;
+}
+
+static const char *output_field2str(enum perf_output_field field)
+{
+	int i, imax = ARRAY_SIZE(all_output_options);
+	const char *str = "";
+
+	for (i = 0; i < imax; ++i) {
+		if (all_output_options[i].field == field) {
+			str = all_output_options[i].str;
+			break;
+		}
+	}
+	return str;
+}
+
+#define PRINT_FIELD(x)  (output[attr->type].fields & PERF_OUTPUT_##x)
+
+static int perf_evsel__check_stype(struct perf_evsel *evsel,
+				   u64 sample_type, const char *sample_msg,
+				   enum perf_output_field field)
+{
+	struct perf_event_attr *attr = &evsel->attr;
+	int type = attr->type;
+	const char *evname;
+
+	if (attr->sample_type & sample_type)
+		return 0;
+
+	if (output[type].user_set) {
+		evname = perf_evsel__name(evsel);
+		pr_err("Samples for '%s' event do not have %s attribute set. "
+		       "Cannot print '%s' field.\n",
+		       evname, sample_msg, output_field2str(field));
+		return -1;
+	}
+
+	/* user did not ask for it explicitly so remove from the default list */
+	output[type].fields &= ~field;
+	evname = perf_evsel__name(evsel);
+	pr_debug("Samples for '%s' event do not have %s attribute set. "
+		 "Skipping '%s' field.\n",
+		 evname, sample_msg, output_field2str(field));
+
+	return 0;
+}
+
+static int perf_evsel__check_attr(struct perf_evsel *evsel,
+				  struct perf_session *session)
+{
+	struct perf_event_attr *attr = &evsel->attr;
+
+	if (PRINT_FIELD(TRACE) &&
+		!perf_session__has_traces(session, "record -R"))
+		return -EINVAL;
+
+	if (PRINT_FIELD(IP)) {
+		if (perf_evsel__check_stype(evsel, PERF_SAMPLE_IP, "IP",
+					    PERF_OUTPUT_IP))
+			return -EINVAL;
+
+		if (!no_callchain &&
+		    !(attr->sample_type & PERF_SAMPLE_CALLCHAIN))
+			symbol_conf.use_callchain = false;
+	}
+
+	if (PRINT_FIELD(ADDR) &&
+		perf_evsel__check_stype(evsel, PERF_SAMPLE_ADDR, "ADDR",
+					PERF_OUTPUT_ADDR))
+		return -EINVAL;
+
+	if (PRINT_FIELD(SYM) && !PRINT_FIELD(IP) && !PRINT_FIELD(ADDR)) {
+		pr_err("Display of symbols requested but neither sample IP nor "
+			   "sample address\nis selected. Hence, no addresses to convert "
+		       "to symbols.\n");
+		return -EINVAL;
+	}
+	if (PRINT_FIELD(SYMOFFSET) && !PRINT_FIELD(SYM)) {
+		pr_err("Display of offsets requested but symbol is not"
+		       "selected.\n");
+		return -EINVAL;
+	}
+	if (PRINT_FIELD(DSO) && !PRINT_FIELD(IP) && !PRINT_FIELD(ADDR)) {
+		pr_err("Display of DSO requested but neither sample IP nor "
+			   "sample address\nis selected. Hence, no addresses to convert "
+		       "to DSO.\n");
+		return -EINVAL;
+	}
+	if (PRINT_FIELD(SRCLINE) && !PRINT_FIELD(IP)) {
+		pr_err("Display of source line number requested but sample IP is not\n"
+		       "selected. Hence, no address to lookup the source line number.\n");
+		return -EINVAL;
+	}
+
+	if ((PRINT_FIELD(PID) || PRINT_FIELD(TID)) &&
+		perf_evsel__check_stype(evsel, PERF_SAMPLE_TID, "TID",
+					PERF_OUTPUT_TID|PERF_OUTPUT_PID))
+		return -EINVAL;
+
+	if (PRINT_FIELD(TIME) &&
+		perf_evsel__check_stype(evsel, PERF_SAMPLE_TIME, "TIME",
+					PERF_OUTPUT_TIME))
+		return -EINVAL;
+
+	if (PRINT_FIELD(CPU) &&
+		perf_evsel__check_stype(evsel, PERF_SAMPLE_CPU, "CPU",
+					PERF_OUTPUT_CPU))
+		return -EINVAL;
+
+	return 0;
+}
+
+static void set_print_ip_opts(struct perf_event_attr *attr)
+{
+	unsigned int type = attr->type;
+
+	output[type].print_ip_opts = 0;
+	if (PRINT_FIELD(IP))
+		output[type].print_ip_opts |= PRINT_IP_OPT_IP;
+
+	if (PRINT_FIELD(SYM))
+		output[type].print_ip_opts |= PRINT_IP_OPT_SYM;
+
+	if (PRINT_FIELD(DSO))
+		output[type].print_ip_opts |= PRINT_IP_OPT_DSO;
+
+	if (PRINT_FIELD(SYMOFFSET))
+		output[type].print_ip_opts |= PRINT_IP_OPT_SYMOFFSET;
+
+	if (PRINT_FIELD(SRCLINE))
+		output[type].print_ip_opts |= PRINT_IP_OPT_SRCLINE;
+}
+
+/*
+ * verify all user requested events exist and the samples
+ * have the expected data
+ */
+static int perf_session__check_output_opt(struct perf_session *session)
+{
+	int j;
+	struct perf_evsel *evsel;
+
+	for (j = 0; j < PERF_TYPE_MAX; ++j) {
+		evsel = perf_session__find_first_evtype(session, j);
+
+		/*
+		 * even if fields is set to 0 (ie., show nothing) event must
+		 * exist if user explicitly includes it on the command line
+		 */
+		if (!evsel && output[j].user_set && !output[j].wildcard_set) {
+			pr_err("%s events do not exist. "
+			       "Remove corresponding -f option to proceed.\n",
+			       event_type(j));
+			return -1;
+		}
+
+		if (evsel && output[j].fields &&
+			perf_evsel__check_attr(evsel, session))
+			return -1;
+
+		if (evsel == NULL)
+			continue;
+
+		set_print_ip_opts(&evsel->attr);
+	}
+
+	/*
+	 * set default for tracepoints to print symbols only
+	 * if callchains are present
+	 */
+	if (symbol_conf.use_callchain &&
+	    !output[PERF_TYPE_TRACEPOINT].user_set) {
+		struct perf_event_attr *attr;
+
+		j = PERF_TYPE_TRACEPOINT;
+		evsel = perf_session__find_first_evtype(session, j);
+		if (evsel == NULL)
+			goto out;
+
+		attr = &evsel->attr;
+
+		if (attr->sample_type & PERF_SAMPLE_CALLCHAIN) {
+			output[j].fields |= PERF_OUTPUT_IP;
+			output[j].fields |= PERF_OUTPUT_SYM;
+			output[j].fields |= PERF_OUTPUT_DSO;
+			set_print_ip_opts(attr);
+		}
+	}
+
+out:
+	return 0;
+}
+
+static void print_sample_start(struct perf_sample *sample,
+			       struct thread *thread,
+			       struct perf_evsel *evsel)
+{
+	struct perf_event_attr *attr = &evsel->attr;
+	unsigned long secs;
+	unsigned long usecs;
+	unsigned long long nsecs;
+
+	if (PRINT_FIELD(COMM)) {
+		if (latency_format)
+			printf("%8.8s ", thread__comm_str(thread));
+		else if (PRINT_FIELD(IP) && symbol_conf.use_callchain)
+			printf("%s ", thread__comm_str(thread));
+		else
+			printf("%16s ", thread__comm_str(thread));
+	}
+
+	if (PRINT_FIELD(PID) && PRINT_FIELD(TID))
+		printf("%5d/%-5d ", sample->pid, sample->tid);
+	else if (PRINT_FIELD(PID))
+		printf("%5d ", sample->pid);
+	else if (PRINT_FIELD(TID))
+		printf("%5d ", sample->tid);
+
+	if (PRINT_FIELD(CPU)) {
+		if (latency_format)
+			printf("%3d ", sample->cpu);
+		else
+			printf("[%03d] ", sample->cpu);
+	}
+
+	if (PRINT_FIELD(TIME)) {
+		nsecs = sample->time;
+		secs = nsecs / NSECS_PER_SEC;
+		nsecs -= secs * NSECS_PER_SEC;
+		usecs = nsecs / NSECS_PER_USEC;
+		printf("%5lu.%06lu: ", secs, usecs);
+	}
+}
+
+static bool is_bts_event(struct perf_event_attr *attr)
+{
+	return ((attr->type == PERF_TYPE_HARDWARE) &&
+		(attr->config & PERF_COUNT_HW_BRANCH_INSTRUCTIONS) &&
+		(attr->sample_period == 1));
+}
+
+static bool sample_addr_correlates_sym(struct perf_event_attr *attr)
+{
+	if ((attr->type == PERF_TYPE_SOFTWARE) &&
+	    ((attr->config == PERF_COUNT_SW_PAGE_FAULTS) ||
+	     (attr->config == PERF_COUNT_SW_PAGE_FAULTS_MIN) ||
+	     (attr->config == PERF_COUNT_SW_PAGE_FAULTS_MAJ)))
+		return true;
+
+	if (is_bts_event(attr))
+		return true;
+
+	return false;
+}
+
+static void print_sample_addr(union perf_event *event,
+			  struct perf_sample *sample,
+			  struct machine *machine,
+			  struct thread *thread,
+			  struct perf_event_attr *attr)
+{
+	struct addr_location al;
+	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+
+	printf("%16" PRIx64, sample->addr);
+
+	if (!sample_addr_correlates_sym(attr))
+		return;
+
+	thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION,
+			      sample->addr, &al);
+	if (!al.map)
+		thread__find_addr_map(thread, machine, cpumode, MAP__VARIABLE,
+				      sample->addr, &al);
+
+	al.cpu = sample->cpu;
+	al.sym = NULL;
+
+	if (al.map)
+		al.sym = map__find_symbol(al.map, al.addr, NULL);
+
+	if (PRINT_FIELD(SYM)) {
+		printf(" ");
+		if (PRINT_FIELD(SYMOFFSET))
+			symbol__fprintf_symname_offs(al.sym, &al, stdout);
+		else
+			symbol__fprintf_symname(al.sym, stdout);
+	}
+
+	if (PRINT_FIELD(DSO)) {
+		printf(" (");
+		map__fprintf_dsoname(al.map, stdout);
+		printf(")");
+	}
+}
+
+static void print_sample_bts(union perf_event *event,
+			     struct perf_sample *sample,
+			     struct perf_evsel *evsel,
+			     struct thread *thread,
+			     struct addr_location *al)
+{
+	struct perf_event_attr *attr = &evsel->attr;
+
+	/* print branch_from information */
+	if (PRINT_FIELD(IP)) {
+		if (!symbol_conf.use_callchain)
+			printf(" ");
+		else
+			printf("\n");
+		perf_evsel__print_ip(evsel, sample, al,
+				     output[attr->type].print_ip_opts,
+				     PERF_MAX_STACK_DEPTH);
+	}
+
+	printf(" => ");
+
+	/* print branch_to information */
+	if (PRINT_FIELD(ADDR) ||
+	    ((evsel->attr.sample_type & PERF_SAMPLE_ADDR) &&
+	     !output[attr->type].user_set))
+		print_sample_addr(event, sample, al->machine, thread, attr);
+
+	printf("\n");
+}
+
+static void process_event(union perf_event *event, struct perf_sample *sample,
+			  struct perf_evsel *evsel, struct thread *thread,
+			  struct addr_location *al)
+{
+	struct perf_event_attr *attr = &evsel->attr;
+
+	if (output[attr->type].fields == 0)
+		return;
+
+	print_sample_start(sample, thread, evsel);
+
+	if (PRINT_FIELD(EVNAME)) {
+		const char *evname = perf_evsel__name(evsel);
+		printf("%s: ", evname ? evname : "[unknown]");
+	}
+
+	if (is_bts_event(attr)) {
+		print_sample_bts(event, sample, evsel, thread, al);
+		return;
+	}
+
+	if (PRINT_FIELD(TRACE))
+		event_format__print(evsel->tp_format, sample->cpu,
+				    sample->raw_data, sample->raw_size);
+	if (PRINT_FIELD(ADDR))
+		print_sample_addr(event, sample, al->machine, thread, attr);
+
+	if (PRINT_FIELD(IP)) {
+		if (!symbol_conf.use_callchain)
+			printf(" ");
+		else
+			printf("\n");
+
+		perf_evsel__print_ip(evsel, sample, al,
+				     output[attr->type].print_ip_opts,
+				     PERF_MAX_STACK_DEPTH);
+	}
+
+	printf("\n");
+}
+
+static int default_start_script(const char *script __maybe_unused,
+				int argc __maybe_unused,
+				const char **argv __maybe_unused)
+{
+	return 0;
+}
+
+static int default_stop_script(void)
+{
+	return 0;
+}
+
+static int default_generate_script(struct pevent *pevent __maybe_unused,
+				   const char *outfile __maybe_unused)
+{
+	return 0;
+}
+
+static struct scripting_ops default_scripting_ops = {
+	.start_script		= default_start_script,
+	.stop_script		= default_stop_script,
+	.process_event		= process_event,
+	.generate_script	= default_generate_script,
+};
+
+static struct scripting_ops	*scripting_ops;
+
+static void setup_scripting(void)
+{
+	setup_perl_scripting();
+	setup_python_scripting();
+
+	scripting_ops = &default_scripting_ops;
+}
+
+static int cleanup_scripting(void)
+{
+	pr_debug("\nperf script stopped\n");
+
+	return scripting_ops->stop_script();
+}
+
+static int process_sample_event(struct perf_tool *tool __maybe_unused,
+				union perf_event *event,
+				struct perf_sample *sample,
+				struct perf_evsel *evsel,
+				struct machine *machine)
+{
+	struct addr_location al;
+	struct thread *thread = machine__findnew_thread(machine, sample->pid,
+							sample->tid);
+
+	if (thread == NULL) {
+		pr_debug("problem processing %d event, skipping it.\n",
+			 event->header.type);
+		return -1;
+	}
+
+	if (debug_mode) {
+		if (sample->time < last_timestamp) {
+			pr_err("Samples misordered, previous: %" PRIu64
+				" this: %" PRIu64 "\n", last_timestamp,
+				sample->time);
+			nr_unordered++;
+		}
+		last_timestamp = sample->time;
+		return 0;
+	}
+
+	if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
+		pr_err("problem processing %d event, skipping it.\n",
+		       event->header.type);
+		return -1;
+	}
+
+	if (al.filtered)
+		return 0;
+
+	if (cpu_list && !test_bit(sample->cpu, cpu_bitmap))
+		return 0;
+
+	scripting_ops->process_event(event, sample, evsel, thread, &al);
+
+	evsel->hists.stats.total_period += sample->period;
+	return 0;
+}
+
+struct perf_script {
+	struct perf_tool	tool;
+	struct perf_session	*session;
+	bool			show_task_events;
+	bool			show_mmap_events;
+};
+
+static int process_attr(struct perf_tool *tool, union perf_event *event,
+			struct perf_evlist **pevlist)
+{
+	struct perf_script *scr = container_of(tool, struct perf_script, tool);
+	struct perf_evlist *evlist;
+	struct perf_evsel *evsel, *pos;
+	int err;
+
+	err = perf_event__process_attr(tool, event, pevlist);
+	if (err)
+		return err;
+
+	evlist = *pevlist;
+	evsel = perf_evlist__last(*pevlist);
+
+	if (evsel->attr.type >= PERF_TYPE_MAX)
+		return 0;
+
+	evlist__for_each(evlist, pos) {
+		if (pos->attr.type == evsel->attr.type && pos != evsel)
+			return 0;
+	}
+
+	set_print_ip_opts(&evsel->attr);
+
+	return perf_evsel__check_attr(evsel, scr->session);
+}
+
+static int process_comm_event(struct perf_tool *tool,
+			      union perf_event *event,
+			      struct perf_sample *sample,
+			      struct machine *machine)
+{
+	struct thread *thread;
+	struct perf_script *script = container_of(tool, struct perf_script, tool);
+	struct perf_session *session = script->session;
+	struct perf_evsel *evsel = perf_evlist__first(session->evlist);
+	int ret = -1;
+
+	thread = machine__findnew_thread(machine, event->comm.pid, event->comm.tid);
+	if (thread == NULL) {
+		pr_debug("problem processing COMM event, skipping it.\n");
+		return -1;
+	}
+
+	if (perf_event__process_comm(tool, event, sample, machine) < 0)
+		goto out;
+
+	if (!evsel->attr.sample_id_all) {
+		sample->cpu = 0;
+		sample->time = 0;
+		sample->tid = event->comm.tid;
+		sample->pid = event->comm.pid;
+	}
+	print_sample_start(sample, thread, evsel);
+	perf_event__fprintf(event, stdout);
+	ret = 0;
+
+out:
+	return ret;
+}
+
+static int process_fork_event(struct perf_tool *tool,
+			      union perf_event *event,
+			      struct perf_sample *sample,
+			      struct machine *machine)
+{
+	struct thread *thread;
+	struct perf_script *script = container_of(tool, struct perf_script, tool);
+	struct perf_session *session = script->session;
+	struct perf_evsel *evsel = perf_evlist__first(session->evlist);
+
+	if (perf_event__process_fork(tool, event, sample, machine) < 0)
+		return -1;
+
+	thread = machine__findnew_thread(machine, event->fork.pid, event->fork.tid);
+	if (thread == NULL) {
+		pr_debug("problem processing FORK event, skipping it.\n");
+		return -1;
+	}
+
+	if (!evsel->attr.sample_id_all) {
+		sample->cpu = 0;
+		sample->time = event->fork.time;
+		sample->tid = event->fork.tid;
+		sample->pid = event->fork.pid;
+	}
+	print_sample_start(sample, thread, evsel);
+	perf_event__fprintf(event, stdout);
+
+	return 0;
+}
+static int process_exit_event(struct perf_tool *tool,
+			      union perf_event *event,
+			      struct perf_sample *sample,
+			      struct machine *machine)
+{
+	struct thread *thread;
+	struct perf_script *script = container_of(tool, struct perf_script, tool);
+	struct perf_session *session = script->session;
+	struct perf_evsel *evsel = perf_evlist__first(session->evlist);
+
+	thread = machine__findnew_thread(machine, event->fork.pid, event->fork.tid);
+	if (thread == NULL) {
+		pr_debug("problem processing EXIT event, skipping it.\n");
+		return -1;
+	}
+
+	if (!evsel->attr.sample_id_all) {
+		sample->cpu = 0;
+		sample->time = 0;
+		sample->tid = event->comm.tid;
+		sample->pid = event->comm.pid;
+	}
+	print_sample_start(sample, thread, evsel);
+	perf_event__fprintf(event, stdout);
+
+	if (perf_event__process_exit(tool, event, sample, machine) < 0)
+		return -1;
+
+	return 0;
+}
+
+static int process_mmap_event(struct perf_tool *tool,
+			      union perf_event *event,
+			      struct perf_sample *sample,
+			      struct machine *machine)
+{
+	struct thread *thread;
+	struct perf_script *script = container_of(tool, struct perf_script, tool);
+	struct perf_session *session = script->session;
+	struct perf_evsel *evsel = perf_evlist__first(session->evlist);
+
+	if (perf_event__process_mmap(tool, event, sample, machine) < 0)
+		return -1;
+
+	thread = machine__findnew_thread(machine, event->mmap.pid, event->mmap.tid);
+	if (thread == NULL) {
+		pr_debug("problem processing MMAP event, skipping it.\n");
+		return -1;
+	}
+
+	if (!evsel->attr.sample_id_all) {
+		sample->cpu = 0;
+		sample->time = 0;
+		sample->tid = event->mmap.tid;
+		sample->pid = event->mmap.pid;
+	}
+	print_sample_start(sample, thread, evsel);
+	perf_event__fprintf(event, stdout);
+
+	return 0;
+}
+
+static int process_mmap2_event(struct perf_tool *tool,
+			      union perf_event *event,
+			      struct perf_sample *sample,
+			      struct machine *machine)
+{
+	struct thread *thread;
+	struct perf_script *script = container_of(tool, struct perf_script, tool);
+	struct perf_session *session = script->session;
+	struct perf_evsel *evsel = perf_evlist__first(session->evlist);
+
+	if (perf_event__process_mmap2(tool, event, sample, machine) < 0)
+		return -1;
+
+	thread = machine__findnew_thread(machine, event->mmap2.pid, event->mmap2.tid);
+	if (thread == NULL) {
+		pr_debug("problem processing MMAP2 event, skipping it.\n");
+		return -1;
+	}
+
+	if (!evsel->attr.sample_id_all) {
+		sample->cpu = 0;
+		sample->time = 0;
+		sample->tid = event->mmap2.tid;
+		sample->pid = event->mmap2.pid;
+	}
+	print_sample_start(sample, thread, evsel);
+	perf_event__fprintf(event, stdout);
+
+	return 0;
+}
+
+static void sig_handler(int sig __maybe_unused)
+{
+	session_done = 1;
+}
+
+static int __cmd_script(struct perf_script *script)
+{
+	int ret;
+
+	signal(SIGINT, sig_handler);
+
+	/* override event processing functions */
+	if (script->show_task_events) {
+		script->tool.comm = process_comm_event;
+		script->tool.fork = process_fork_event;
+		script->tool.exit = process_exit_event;
+	}
+	if (script->show_mmap_events) {
+		script->tool.mmap = process_mmap_event;
+		script->tool.mmap2 = process_mmap2_event;
+	}
+
+	ret = perf_session__process_events(script->session, &script->tool);
+
+	if (debug_mode)
+		pr_err("Misordered timestamps: %" PRIu64 "\n", nr_unordered);
+
+	return ret;
+}
+
+struct script_spec {
+	struct list_head	node;
+	struct scripting_ops	*ops;
+	char			spec[0];
+};
+
+static LIST_HEAD(script_specs);
+
+static struct script_spec *script_spec__new(const char *spec,
+					    struct scripting_ops *ops)
+{
+	struct script_spec *s = malloc(sizeof(*s) + strlen(spec) + 1);
+
+	if (s != NULL) {
+		strcpy(s->spec, spec);
+		s->ops = ops;
+	}
+
+	return s;
+}
+
+static void script_spec__add(struct script_spec *s)
+{
+	list_add_tail(&s->node, &script_specs);
+}
+
+static struct script_spec *script_spec__find(const char *spec)
+{
+	struct script_spec *s;
+
+	list_for_each_entry(s, &script_specs, node)
+		if (strcasecmp(s->spec, spec) == 0)
+			return s;
+	return NULL;
+}
+
+static struct script_spec *script_spec__findnew(const char *spec,
+						struct scripting_ops *ops)
+{
+	struct script_spec *s = script_spec__find(spec);
+
+	if (s)
+		return s;
+
+	s = script_spec__new(spec, ops);
+	if (!s)
+		return NULL;
+
+	script_spec__add(s);
+
+	return s;
+}
+
+int script_spec_register(const char *spec, struct scripting_ops *ops)
+{
+	struct script_spec *s;
+
+	s = script_spec__find(spec);
+	if (s)
+		return -1;
+
+	s = script_spec__findnew(spec, ops);
+	if (!s)
+		return -1;
+
+	return 0;
+}
+
+static struct scripting_ops *script_spec__lookup(const char *spec)
+{
+	struct script_spec *s = script_spec__find(spec);
+	if (!s)
+		return NULL;
+
+	return s->ops;
+}
+
+static void list_available_languages(void)
+{
+	struct script_spec *s;
+
+	fprintf(stderr, "\n");
+	fprintf(stderr, "Scripting language extensions (used in "
+		"perf script -s [spec:]script.[spec]):\n\n");
+
+	list_for_each_entry(s, &script_specs, node)
+		fprintf(stderr, "  %-42s [%s]\n", s->spec, s->ops->name);
+
+	fprintf(stderr, "\n");
+}
+
+static int parse_scriptname(const struct option *opt __maybe_unused,
+			    const char *str, int unset __maybe_unused)
+{
+	char spec[PATH_MAX];
+	const char *script, *ext;
+	int len;
+
+	if (strcmp(str, "lang") == 0) {
+		list_available_languages();
+		exit(0);
+	}
+
+	script = strchr(str, ':');
+	if (script) {
+		len = script - str;
+		if (len >= PATH_MAX) {
+			fprintf(stderr, "invalid language specifier");
+			return -1;
+		}
+		strncpy(spec, str, len);
+		spec[len] = '\0';
+		scripting_ops = script_spec__lookup(spec);
+		if (!scripting_ops) {
+			fprintf(stderr, "invalid language specifier");
+			return -1;
+		}
+		script++;
+	} else {
+		script = str;
+		ext = strrchr(script, '.');
+		if (!ext) {
+			fprintf(stderr, "invalid script extension");
+			return -1;
+		}
+		scripting_ops = script_spec__lookup(++ext);
+		if (!scripting_ops) {
+			fprintf(stderr, "invalid script extension");
+			return -1;
+		}
+	}
+
+	script_name = strdup(script);
+
+	return 0;
+}
+
+static int parse_output_fields(const struct option *opt __maybe_unused,
+			    const char *arg, int unset __maybe_unused)
+{
+	char *tok;
+	int i, imax = ARRAY_SIZE(all_output_options);
+	int j;
+	int rc = 0;
+	char *str = strdup(arg);
+	int type = -1;
+
+	if (!str)
+		return -ENOMEM;
+
+	/* first word can state for which event type the user is specifying
+	 * the fields. If no type exists, the specified fields apply to all
+	 * event types found in the file minus the invalid fields for a type.
+	 */
+	tok = strchr(str, ':');
+	if (tok) {
+		*tok = '\0';
+		tok++;
+		if (!strcmp(str, "hw"))
+			type = PERF_TYPE_HARDWARE;
+		else if (!strcmp(str, "sw"))
+			type = PERF_TYPE_SOFTWARE;
+		else if (!strcmp(str, "trace"))
+			type = PERF_TYPE_TRACEPOINT;
+		else if (!strcmp(str, "raw"))
+			type = PERF_TYPE_RAW;
+		else {
+			fprintf(stderr, "Invalid event type in field string.\n");
+			rc = -EINVAL;
+			goto out;
+		}
+
+		if (output[type].user_set)
+			pr_warning("Overriding previous field request for %s events.\n",
+				   event_type(type));
+
+		output[type].fields = 0;
+		output[type].user_set = true;
+		output[type].wildcard_set = false;
+
+	} else {
+		tok = str;
+		if (strlen(str) == 0) {
+			fprintf(stderr,
+				"Cannot set fields to 'none' for all event types.\n");
+			rc = -EINVAL;
+			goto out;
+		}
+
+		if (output_set_by_user())
+			pr_warning("Overriding previous field request for all events.\n");
+
+		for (j = 0; j < PERF_TYPE_MAX; ++j) {
+			output[j].fields = 0;
+			output[j].user_set = true;
+			output[j].wildcard_set = true;
+		}
+	}
+
+	tok = strtok(tok, ",");
+	while (tok) {
+		for (i = 0; i < imax; ++i) {
+			if (strcmp(tok, all_output_options[i].str) == 0)
+				break;
+		}
+		if (i == imax) {
+			fprintf(stderr, "Invalid field requested.\n");
+			rc = -EINVAL;
+			goto out;
+		}
+
+		if (type == -1) {
+			/* add user option to all events types for
+			 * which it is valid
+			 */
+			for (j = 0; j < PERF_TYPE_MAX; ++j) {
+				if (output[j].invalid_fields & all_output_options[i].field) {
+					pr_warning("\'%s\' not valid for %s events. Ignoring.\n",
+						   all_output_options[i].str, event_type(j));
+				} else
+					output[j].fields |= all_output_options[i].field;
+			}
+		} else {
+			if (output[type].invalid_fields & all_output_options[i].field) {
+				fprintf(stderr, "\'%s\' not valid for %s events.\n",
+					 all_output_options[i].str, event_type(type));
+
+				rc = -EINVAL;
+				goto out;
+			}
+			output[type].fields |= all_output_options[i].field;
+		}
+
+		tok = strtok(NULL, ",");
+	}
+
+	if (type >= 0) {
+		if (output[type].fields == 0) {
+			pr_debug("No fields requested for %s type. "
+				 "Events will not be displayed.\n", event_type(type));
+		}
+	}
+
+out:
+	free(str);
+	return rc;
+}
+
+/* Helper function for filesystems that return a dent->d_type DT_UNKNOWN */
+static int is_directory(const char *base_path, const struct dirent *dent)
+{
+	char path[PATH_MAX];
+	struct stat st;
+
+	sprintf(path, "%s/%s", base_path, dent->d_name);
+	if (stat(path, &st))
+		return 0;
+
+	return S_ISDIR(st.st_mode);
+}
+
+#define for_each_lang(scripts_path, scripts_dir, lang_dirent, lang_next)\
+	while (!readdir_r(scripts_dir, &lang_dirent, &lang_next) &&	\
+	       lang_next)						\
+		if ((lang_dirent.d_type == DT_DIR ||			\
+		     (lang_dirent.d_type == DT_UNKNOWN &&		\
+		      is_directory(scripts_path, &lang_dirent))) &&	\
+		    (strcmp(lang_dirent.d_name, ".")) &&		\
+		    (strcmp(lang_dirent.d_name, "..")))
+
+#define for_each_script(lang_path, lang_dir, script_dirent, script_next)\
+	while (!readdir_r(lang_dir, &script_dirent, &script_next) &&	\
+	       script_next)						\
+		if (script_dirent.d_type != DT_DIR &&			\
+		    (script_dirent.d_type != DT_UNKNOWN ||		\
+		     !is_directory(lang_path, &script_dirent)))
+
+
+#define RECORD_SUFFIX			"-record"
+#define REPORT_SUFFIX			"-report"
+
+struct script_desc {
+	struct list_head	node;
+	char			*name;
+	char			*half_liner;
+	char			*args;
+};
+
+static LIST_HEAD(script_descs);
+
+static struct script_desc *script_desc__new(const char *name)
+{
+	struct script_desc *s = zalloc(sizeof(*s));
+
+	if (s != NULL && name)
+		s->name = strdup(name);
+
+	return s;
+}
+
+static void script_desc__delete(struct script_desc *s)
+{
+	zfree(&s->name);
+	zfree(&s->half_liner);
+	zfree(&s->args);
+	free(s);
+}
+
+static void script_desc__add(struct script_desc *s)
+{
+	list_add_tail(&s->node, &script_descs);
+}
+
+static struct script_desc *script_desc__find(const char *name)
+{
+	struct script_desc *s;
+
+	list_for_each_entry(s, &script_descs, node)
+		if (strcasecmp(s->name, name) == 0)
+			return s;
+	return NULL;
+}
+
+static struct script_desc *script_desc__findnew(const char *name)
+{
+	struct script_desc *s = script_desc__find(name);
+
+	if (s)
+		return s;
+
+	s = script_desc__new(name);
+	if (!s)
+		goto out_delete_desc;
+
+	script_desc__add(s);
+
+	return s;
+
+out_delete_desc:
+	script_desc__delete(s);
+
+	return NULL;
+}
+
+static const char *ends_with(const char *str, const char *suffix)
+{
+	size_t suffix_len = strlen(suffix);
+	const char *p = str;
+
+	if (strlen(str) > suffix_len) {
+		p = str + strlen(str) - suffix_len;
+		if (!strncmp(p, suffix, suffix_len))
+			return p;
+	}
+
+	return NULL;
+}
+
+static int read_script_info(struct script_desc *desc, const char *filename)
+{
+	char line[BUFSIZ], *p;
+	FILE *fp;
+
+	fp = fopen(filename, "r");
+	if (!fp)
+		return -1;
+
+	while (fgets(line, sizeof(line), fp)) {
+		p = ltrim(line);
+		if (strlen(p) == 0)
+			continue;
+		if (*p != '#')
+			continue;
+		p++;
+		if (strlen(p) && *p == '!')
+			continue;
+
+		p = ltrim(p);
+		if (strlen(p) && p[strlen(p) - 1] == '\n')
+			p[strlen(p) - 1] = '\0';
+
+		if (!strncmp(p, "description:", strlen("description:"))) {
+			p += strlen("description:");
+			desc->half_liner = strdup(ltrim(p));
+			continue;
+		}
+
+		if (!strncmp(p, "args:", strlen("args:"))) {
+			p += strlen("args:");
+			desc->args = strdup(ltrim(p));
+			continue;
+		}
+	}
+
+	fclose(fp);
+
+	return 0;
+}
+
+static char *get_script_root(struct dirent *script_dirent, const char *suffix)
+{
+	char *script_root, *str;
+
+	script_root = strdup(script_dirent->d_name);
+	if (!script_root)
+		return NULL;
+
+	str = (char *)ends_with(script_root, suffix);
+	if (!str) {
+		free(script_root);
+		return NULL;
+	}
+
+	*str = '\0';
+	return script_root;
+}
+
+static int list_available_scripts(const struct option *opt __maybe_unused,
+				  const char *s __maybe_unused,
+				  int unset __maybe_unused)
+{
+	struct dirent *script_next, *lang_next, script_dirent, lang_dirent;
+	char scripts_path[MAXPATHLEN];
+	DIR *scripts_dir, *lang_dir;
+	char script_path[MAXPATHLEN];
+	char lang_path[MAXPATHLEN];
+	struct script_desc *desc;
+	char first_half[BUFSIZ];
+	char *script_root;
+
+	snprintf(scripts_path, MAXPATHLEN, "%s/scripts", perf_exec_path());
+
+	scripts_dir = opendir(scripts_path);
+	if (!scripts_dir)
+		return -1;
+
+	for_each_lang(scripts_path, scripts_dir, lang_dirent, lang_next) {
+		snprintf(lang_path, MAXPATHLEN, "%s/%s/bin", scripts_path,
+			 lang_dirent.d_name);
+		lang_dir = opendir(lang_path);
+		if (!lang_dir)
+			continue;
+
+		for_each_script(lang_path, lang_dir, script_dirent, script_next) {
+			script_root = get_script_root(&script_dirent, REPORT_SUFFIX);
+			if (script_root) {
+				desc = script_desc__findnew(script_root);
+				snprintf(script_path, MAXPATHLEN, "%s/%s",
+					 lang_path, script_dirent.d_name);
+				read_script_info(desc, script_path);
+				free(script_root);
+			}
+		}
+	}
+
+	fprintf(stdout, "List of available trace scripts:\n");
+	list_for_each_entry(desc, &script_descs, node) {
+		sprintf(first_half, "%s %s", desc->name,
+			desc->args ? desc->args : "");
+		fprintf(stdout, "  %-36s %s\n", first_half,
+			desc->half_liner ? desc->half_liner : "");
+	}
+
+	exit(0);
+}
+
+/*
+ * Some scripts specify the required events in their "xxx-record" file,
+ * this function will check if the events in perf.data match those
+ * mentioned in the "xxx-record".
+ *
+ * Fixme: All existing "xxx-record" are all in good formats "-e event ",
+ * which is covered well now. And new parsing code should be added to
+ * cover the future complexing formats like event groups etc.
+ */
+static int check_ev_match(char *dir_name, char *scriptname,
+			struct perf_session *session)
+{
+	char filename[MAXPATHLEN], evname[128];
+	char line[BUFSIZ], *p;
+	struct perf_evsel *pos;
+	int match, len;
+	FILE *fp;
+
+	sprintf(filename, "%s/bin/%s-record", dir_name, scriptname);
+
+	fp = fopen(filename, "r");
+	if (!fp)
+		return -1;
+
+	while (fgets(line, sizeof(line), fp)) {
+		p = ltrim(line);
+		if (*p == '#')
+			continue;
+
+		while (strlen(p)) {
+			p = strstr(p, "-e");
+			if (!p)
+				break;
+
+			p += 2;
+			p = ltrim(p);
+			len = strcspn(p, " \t");
+			if (!len)
+				break;
+
+			snprintf(evname, len + 1, "%s", p);
+
+			match = 0;
+			evlist__for_each(session->evlist, pos) {
+				if (!strcmp(perf_evsel__name(pos), evname)) {
+					match = 1;
+					break;
+				}
+			}
+
+			if (!match) {
+				fclose(fp);
+				return -1;
+			}
+		}
+	}
+
+	fclose(fp);
+	return 0;
+}
+
+/*
+ * Return -1 if none is found, otherwise the actual scripts number.
+ *
+ * Currently the only user of this function is the script browser, which
+ * will list all statically runnable scripts, select one, execute it and
+ * show the output in a perf browser.
+ */
+int find_scripts(char **scripts_array, char **scripts_path_array)
+{
+	struct dirent *script_next, *lang_next, script_dirent, lang_dirent;
+	char scripts_path[MAXPATHLEN], lang_path[MAXPATHLEN];
+	DIR *scripts_dir, *lang_dir;
+	struct perf_session *session;
+	struct perf_data_file file = {
+		.path = input_name,
+		.mode = PERF_DATA_MODE_READ,
+	};
+	char *temp;
+	int i = 0;
+
+	session = perf_session__new(&file, false, NULL);
+	if (!session)
+		return -1;
+
+	snprintf(scripts_path, MAXPATHLEN, "%s/scripts", perf_exec_path());
+
+	scripts_dir = opendir(scripts_path);
+	if (!scripts_dir) {
+		perf_session__delete(session);
+		return -1;
+	}
+
+	for_each_lang(scripts_path, scripts_dir, lang_dirent, lang_next) {
+		snprintf(lang_path, MAXPATHLEN, "%s/%s", scripts_path,
+			 lang_dirent.d_name);
+#ifdef NO_LIBPERL
+		if (strstr(lang_path, "perl"))
+			continue;
+#endif
+#ifdef NO_LIBPYTHON
+		if (strstr(lang_path, "python"))
+			continue;
+#endif
+
+		lang_dir = opendir(lang_path);
+		if (!lang_dir)
+			continue;
+
+		for_each_script(lang_path, lang_dir, script_dirent, script_next) {
+			/* Skip those real time scripts: xxxtop.p[yl] */
+			if (strstr(script_dirent.d_name, "top."))
+				continue;
+			sprintf(scripts_path_array[i], "%s/%s", lang_path,
+				script_dirent.d_name);
+			temp = strchr(script_dirent.d_name, '.');
+			snprintf(scripts_array[i],
+				(temp - script_dirent.d_name) + 1,
+				"%s", script_dirent.d_name);
+
+			if (check_ev_match(lang_path,
+					scripts_array[i], session))
+				continue;
+
+			i++;
+		}
+		closedir(lang_dir);
+	}
+
+	closedir(scripts_dir);
+	perf_session__delete(session);
+	return i;
+}
+
+static char *get_script_path(const char *script_root, const char *suffix)
+{
+	struct dirent *script_next, *lang_next, script_dirent, lang_dirent;
+	char scripts_path[MAXPATHLEN];
+	char script_path[MAXPATHLEN];
+	DIR *scripts_dir, *lang_dir;
+	char lang_path[MAXPATHLEN];
+	char *__script_root;
+
+	snprintf(scripts_path, MAXPATHLEN, "%s/scripts", perf_exec_path());
+
+	scripts_dir = opendir(scripts_path);
+	if (!scripts_dir)
+		return NULL;
+
+	for_each_lang(scripts_path, scripts_dir, lang_dirent, lang_next) {
+		snprintf(lang_path, MAXPATHLEN, "%s/%s/bin", scripts_path,
+			 lang_dirent.d_name);
+		lang_dir = opendir(lang_path);
+		if (!lang_dir)
+			continue;
+
+		for_each_script(lang_path, lang_dir, script_dirent, script_next) {
+			__script_root = get_script_root(&script_dirent, suffix);
+			if (__script_root && !strcmp(script_root, __script_root)) {
+				free(__script_root);
+				closedir(lang_dir);
+				closedir(scripts_dir);
+				snprintf(script_path, MAXPATHLEN, "%s/%s",
+					 lang_path, script_dirent.d_name);
+				return strdup(script_path);
+			}
+			free(__script_root);
+		}
+		closedir(lang_dir);
+	}
+	closedir(scripts_dir);
+
+	return NULL;
+}
+
+static bool is_top_script(const char *script_path)
+{
+	return ends_with(script_path, "top") == NULL ? false : true;
+}
+
+static int has_required_arg(char *script_path)
+{
+	struct script_desc *desc;
+	int n_args = 0;
+	char *p;
+
+	desc = script_desc__new(NULL);
+
+	if (read_script_info(desc, script_path))
+		goto out;
+
+	if (!desc->args)
+		goto out;
+
+	for (p = desc->args; *p; p++)
+		if (*p == '<')
+			n_args++;
+out:
+	script_desc__delete(desc);
+
+	return n_args;
+}
+
+static int have_cmd(int argc, const char **argv)
+{
+	char **__argv = malloc(sizeof(const char *) * argc);
+
+	if (!__argv) {
+		pr_err("malloc failed\n");
+		return -1;
+	}
+
+	memcpy(__argv, argv, sizeof(const char *) * argc);
+	argc = parse_options(argc, (const char **)__argv, record_options,
+			     NULL, PARSE_OPT_STOP_AT_NON_OPTION);
+	free(__argv);
+
+	system_wide = (argc == 0);
+
+	return 0;
+}
+
+int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
+{
+	bool show_full_info = false;
+	bool header = false;
+	bool header_only = false;
+	char *rec_script_path = NULL;
+	char *rep_script_path = NULL;
+	struct perf_session *session;
+	char *script_path = NULL;
+	const char **__argv;
+	int i, j, err;
+	struct perf_script script = {
+		.tool = {
+			.sample		 = process_sample_event,
+			.mmap		 = perf_event__process_mmap,
+			.mmap2		 = perf_event__process_mmap2,
+			.comm		 = perf_event__process_comm,
+			.exit		 = perf_event__process_exit,
+			.fork		 = perf_event__process_fork,
+			.attr		 = process_attr,
+			.tracing_data	 = perf_event__process_tracing_data,
+			.build_id	 = perf_event__process_build_id,
+			.ordered_samples = true,
+			.ordering_requires_timestamps = true,
+		},
+	};
+	const struct option options[] = {
+	OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
+		    "dump raw trace in ASCII"),
+	OPT_INCR('v', "verbose", &verbose,
+		 "be more verbose (show symbol address, etc)"),
+	OPT_BOOLEAN('L', "Latency", &latency_format,
+		    "show latency attributes (irqs/preemption disabled, etc)"),
+	OPT_CALLBACK_NOOPT('l', "list", NULL, NULL, "list available scripts",
+			   list_available_scripts),
+	OPT_CALLBACK('s', "script", NULL, "name",
+		     "script file name (lang:script name, script name, or *)",
+		     parse_scriptname),
+	OPT_STRING('g', "gen-script", &generate_script_lang, "lang",
+		   "generate perf-script.xx script in specified language"),
+	OPT_STRING('i', "input", &input_name, "file", "input file name"),
+	OPT_BOOLEAN('d', "debug-mode", &debug_mode,
+		   "do various checks like samples ordering and lost events"),
+	OPT_BOOLEAN(0, "header", &header, "Show data header."),
+	OPT_BOOLEAN(0, "header-only", &header_only, "Show only data header."),
+	OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
+		   "file", "vmlinux pathname"),
+	OPT_STRING(0, "kallsyms", &symbol_conf.kallsyms_name,
+		   "file", "kallsyms pathname"),
+	OPT_BOOLEAN('G', "hide-call-graph", &no_callchain,
+		    "When printing symbols do not display call chain"),
+	OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
+		    "Look for files with symbols relative to this directory"),
+	OPT_CALLBACK('f', "fields", NULL, "str",
+		     "comma separated output fields prepend with 'type:'. "
+		     "Valid types: hw,sw,trace,raw. "
+		     "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
+		     "addr,symoff", parse_output_fields),
+	OPT_BOOLEAN('a', "all-cpus", &system_wide,
+		    "system-wide collection from all CPUs"),
+	OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]",
+		   "only consider these symbols"),
+	OPT_STRING('C', "cpu", &cpu_list, "cpu", "list of cpus to profile"),
+	OPT_STRING('c', "comms", &symbol_conf.comm_list_str, "comm[,comm...]",
+		   "only display events for these comms"),
+	OPT_BOOLEAN('I', "show-info", &show_full_info,
+		    "display extended information from perf.data file"),
+	OPT_BOOLEAN('\0', "show-kernel-path", &symbol_conf.show_kernel_path,
+		    "Show the path of [kernel.kallsyms]"),
+	OPT_BOOLEAN('\0', "show-task-events", &script.show_task_events,
+		    "Show the fork/comm/exit events"),
+	OPT_BOOLEAN('\0', "show-mmap-events", &script.show_mmap_events,
+		    "Show the mmap events"),
+	OPT_END()
+	};
+	const char * const script_usage[] = {
+		"perf script [<options>]",
+		"perf script [<options>] record <script> [<record-options>] <command>",
+		"perf script [<options>] report <script> [script-args]",
+		"perf script [<options>] <script> [<record-options>] <command>",
+		"perf script [<options>] <top-script> [script-args]",
+		NULL
+	};
+	struct perf_data_file file = {
+		.mode = PERF_DATA_MODE_READ,
+	};
+
+	setup_scripting();
+
+	argc = parse_options(argc, argv, options, script_usage,
+			     PARSE_OPT_STOP_AT_NON_OPTION);
+
+	file.path = input_name;
+
+	if (argc > 1 && !strncmp(argv[0], "rec", strlen("rec"))) {
+		rec_script_path = get_script_path(argv[1], RECORD_SUFFIX);
+		if (!rec_script_path)
+			return cmd_record(argc, argv, NULL);
+	}
+
+	if (argc > 1 && !strncmp(argv[0], "rep", strlen("rep"))) {
+		rep_script_path = get_script_path(argv[1], REPORT_SUFFIX);
+		if (!rep_script_path) {
+			fprintf(stderr,
+				"Please specify a valid report script"
+				"(see 'perf script -l' for listing)\n");
+			return -1;
+		}
+	}
+
+	/* make sure PERF_EXEC_PATH is set for scripts */
+	perf_set_argv_exec_path(perf_exec_path());
+
+	if (argc && !script_name && !rec_script_path && !rep_script_path) {
+		int live_pipe[2];
+		int rep_args;
+		pid_t pid;
+
+		rec_script_path = get_script_path(argv[0], RECORD_SUFFIX);
+		rep_script_path = get_script_path(argv[0], REPORT_SUFFIX);
+
+		if (!rec_script_path && !rep_script_path) {
+			fprintf(stderr, " Couldn't find script %s\n\n See perf"
+				" script -l for available scripts.\n", argv[0]);
+			usage_with_options(script_usage, options);
+		}
+
+		if (is_top_script(argv[0])) {
+			rep_args = argc - 1;
+		} else {
+			int rec_args;
+
+			rep_args = has_required_arg(rep_script_path);
+			rec_args = (argc - 1) - rep_args;
+			if (rec_args < 0) {
+				fprintf(stderr, " %s script requires options."
+					"\n\n See perf script -l for available "
+					"scripts and options.\n", argv[0]);
+				usage_with_options(script_usage, options);
+			}
+		}
+
+		if (pipe(live_pipe) < 0) {
+			perror("failed to create pipe");
+			return -1;
+		}
+
+		pid = fork();
+		if (pid < 0) {
+			perror("failed to fork");
+			return -1;
+		}
+
+		if (!pid) {
+			j = 0;
+
+			dup2(live_pipe[1], 1);
+			close(live_pipe[0]);
+
+			if (is_top_script(argv[0])) {
+				system_wide = true;
+			} else if (!system_wide) {
+				if (have_cmd(argc - rep_args, &argv[rep_args]) != 0) {
+					err = -1;
+					goto out;
+				}
+			}
+
+			__argv = malloc((argc + 6) * sizeof(const char *));
+			if (!__argv) {
+				pr_err("malloc failed\n");
+				err = -ENOMEM;
+				goto out;
+			}
+
+			__argv[j++] = "/bin/sh";
+			__argv[j++] = rec_script_path;
+			if (system_wide)
+				__argv[j++] = "-a";
+			__argv[j++] = "-q";
+			__argv[j++] = "-o";
+			__argv[j++] = "-";
+			for (i = rep_args + 1; i < argc; i++)
+				__argv[j++] = argv[i];
+			__argv[j++] = NULL;
+
+			execvp("/bin/sh", (char **)__argv);
+			free(__argv);
+			exit(-1);
+		}
+
+		dup2(live_pipe[0], 0);
+		close(live_pipe[1]);
+
+		__argv = malloc((argc + 4) * sizeof(const char *));
+		if (!__argv) {
+			pr_err("malloc failed\n");
+			err = -ENOMEM;
+			goto out;
+		}
+
+		j = 0;
+		__argv[j++] = "/bin/sh";
+		__argv[j++] = rep_script_path;
+		for (i = 1; i < rep_args + 1; i++)
+			__argv[j++] = argv[i];
+		__argv[j++] = "-i";
+		__argv[j++] = "-";
+		__argv[j++] = NULL;
+
+		execvp("/bin/sh", (char **)__argv);
+		free(__argv);
+		exit(-1);
+	}
+
+	if (rec_script_path)
+		script_path = rec_script_path;
+	if (rep_script_path)
+		script_path = rep_script_path;
+
+	if (script_path) {
+		j = 0;
+
+		if (!rec_script_path)
+			system_wide = false;
+		else if (!system_wide) {
+			if (have_cmd(argc - 1, &argv[1]) != 0) {
+				err = -1;
+				goto out;
+			}
+		}
+
+		__argv = malloc((argc + 2) * sizeof(const char *));
+		if (!__argv) {
+			pr_err("malloc failed\n");
+			err = -ENOMEM;
+			goto out;
+		}
+
+		__argv[j++] = "/bin/sh";
+		__argv[j++] = script_path;
+		if (system_wide)
+			__argv[j++] = "-a";
+		for (i = 2; i < argc; i++)
+			__argv[j++] = argv[i];
+		__argv[j++] = NULL;
+
+		execvp("/bin/sh", (char **)__argv);
+		free(__argv);
+		exit(-1);
+	}
+
+	if (symbol__init() < 0)
+		return -1;
+	if (!script_name)
+		setup_pager();
+
+	session = perf_session__new(&file, false, &script.tool);
+	if (session == NULL)
+		return -ENOMEM;
+
+	if (header || header_only) {
+		perf_session__fprintf_info(session, stdout, show_full_info);
+		if (header_only)
+			return 0;
+	}
+
+	script.session = session;
+
+	if (cpu_list) {
+		if (perf_session__cpu_bitmap(session, cpu_list, cpu_bitmap))
+			return -1;
+	}
+
+	if (!no_callchain)
+		symbol_conf.use_callchain = true;
+	else
+		symbol_conf.use_callchain = false;
+
+	if (generate_script_lang) {
+		struct stat perf_stat;
+		int input;
+
+		if (output_set_by_user()) {
+			fprintf(stderr,
+				"custom fields not supported for generated scripts");
+			return -1;
+		}
+
+		input = open(file.path, O_RDONLY);	/* input_name */
+		if (input < 0) {
+			perror("failed to open file");
+			return -1;
+		}
+
+		err = fstat(input, &perf_stat);
+		if (err < 0) {
+			perror("failed to stat file");
+			return -1;
+		}
+
+		if (!perf_stat.st_size) {
+			fprintf(stderr, "zero-sized file, nothing to do!\n");
+			return 0;
+		}
+
+		scripting_ops = script_spec__lookup(generate_script_lang);
+		if (!scripting_ops) {
+			fprintf(stderr, "invalid language specifier");
+			return -1;
+		}
+
+		err = scripting_ops->generate_script(session->tevent.pevent,
+						     "perf-script");
+		goto out;
+	}
+
+	if (script_name) {
+		err = scripting_ops->start_script(script_name, argc, argv);
+		if (err)
+			goto out;
+		pr_debug("perf script started with script %s\n\n", script_name);
+	}
+
+
+	err = perf_session__check_output_opt(session);
+	if (err < 0)
+		goto out;
+
+	err = __cmd_script(&script);
+
+	perf_session__delete(session);
+	cleanup_scripting();
+out:
+	return err;
+}
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 9a39ca3c3ac..65a151e3606 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -6,24 +6,28 @@
  *
  * Sample output:
 
-   $ perf stat ~/hackbench 10
-   Time: 0.104
+   $ perf stat ./hackbench 10
 
-    Performance counter stats for '/home/mingo/hackbench':
+  Time: 0.118
 
-       1255.538611  task clock ticks     #      10.143 CPU utilization factor
-             54011  context switches     #       0.043 M/sec
-               385  CPU migrations       #       0.000 M/sec
-             17755  pagefaults           #       0.014 M/sec
-        3808323185  CPU cycles           #    3033.219 M/sec
-        1575111190  instructions         #    1254.530 M/sec
-          17367895  cache references     #      13.833 M/sec
-           7674421  cache misses         #       6.112 M/sec
+  Performance counter stats for './hackbench 10':
 
-    Wall-clock time elapsed:   123.786620 msecs
+       1708.761321 task-clock                #   11.037 CPUs utilized
+            41,190 context-switches          #    0.024 M/sec
+             6,735 CPU-migrations            #    0.004 M/sec
+            17,318 page-faults               #    0.010 M/sec
+     5,205,202,243 cycles                    #    3.046 GHz
+     3,856,436,920 stalled-cycles-frontend   #   74.09% frontend cycles idle
+     1,600,790,871 stalled-cycles-backend    #   30.75% backend  cycles idle
+     2,603,501,247 instructions              #    0.50  insns per cycle
+                                             #    1.48  stalled cycles per insn
+       484,357,498 branches                  #  283.455 M/sec
+         6,388,934 branch-misses             #    1.32% of all branches
+
+        0.154822978  seconds time elapsed
 
  *
- * Copyright (C) 2008, Red Hat Inc, Ingo Molnar <mingo@redhat.com>
+ * Copyright (C) 2008-2011, Red Hat Inc, Ingo Molnar <mingo@redhat.com>
  *
  * Improvements and fixes by:
  *
@@ -42,306 +46,554 @@
 #include "util/util.h"
 #include "util/parse-options.h"
 #include "util/parse-events.h"
+#include "util/pmu.h"
 #include "util/event.h"
+#include "util/evlist.h"
+#include "util/evsel.h"
 #include "util/debug.h"
+#include "util/color.h"
+#include "util/stat.h"
 #include "util/header.h"
 #include "util/cpumap.h"
 #include "util/thread.h"
+#include "util/thread_map.h"
 
+#include <stdlib.h>
 #include <sys/prctl.h>
-#include <math.h>
 #include <locale.h>
 
-static struct perf_event_attr default_attrs[] = {
+#define DEFAULT_SEPARATOR	" "
+#define CNTR_NOT_SUPPORTED	"<not supported>"
+#define CNTR_NOT_COUNTED	"<not counted>"
+
+static void print_stat(int argc, const char **argv);
+static void print_counter_aggr(struct perf_evsel *counter, char *prefix);
+static void print_counter(struct perf_evsel *counter, char *prefix);
+static void print_aggr(char *prefix);
+
+/* Default events used for perf stat -T */
+static const char * const transaction_attrs[] = {
+	"task-clock",
+	"{"
+	"instructions,"
+	"cycles,"
+	"cpu/cycles-t/,"
+	"cpu/tx-start/,"
+	"cpu/el-start/,"
+	"cpu/cycles-ct/"
+	"}"
+};
 
-  { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_TASK_CLOCK		},
-  { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CONTEXT_SWITCHES	},
-  { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CPU_MIGRATIONS		},
-  { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_PAGE_FAULTS		},
+/* More limited version when the CPU does not have all events. */
+static const char * const transaction_limited_attrs[] = {
+	"task-clock",
+	"{"
+	"instructions,"
+	"cycles,"
+	"cpu/cycles-t/,"
+	"cpu/tx-start/"
+	"}"
+};
 
-  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES		},
-  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_INSTRUCTIONS		},
-  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_INSTRUCTIONS	},
-  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_MISSES		},
-  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CACHE_REFERENCES	},
-  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CACHE_MISSES		},
+/* must match transaction_attrs and the beginning limited_attrs */
+enum {
+	T_TASK_CLOCK,
+	T_INSTRUCTIONS,
+	T_CYCLES,
+	T_CYCLES_IN_TX,
+	T_TRANSACTION_START,
+	T_ELISION_START,
+	T_CYCLES_IN_TX_CP,
+};
+
+static struct perf_evlist	*evsel_list;
 
+static struct target target = {
+	.uid	= UINT_MAX,
 };
 
-static bool			system_wide			=  false;
-static unsigned int		nr_cpus				=  0;
-static int			run_idx				=  0;
+enum aggr_mode {
+	AGGR_NONE,
+	AGGR_GLOBAL,
+	AGGR_SOCKET,
+	AGGR_CORE,
+};
 
 static int			run_count			=  1;
 static bool			no_inherit			= false;
 static bool			scale				=  true;
-static pid_t			target_pid			= -1;
-static pid_t			target_tid			= -1;
-static pid_t			*all_tids			=  NULL;
-static int			thread_num			=  0;
-static pid_t			child_pid			= -1;
+static enum aggr_mode		aggr_mode			= AGGR_GLOBAL;
+static volatile pid_t		child_pid			= -1;
 static bool			null_run			=  false;
-static bool			big_num				=  false;
+static int			detailed_run			=  0;
+static bool			transaction_run;
+static bool			big_num				=  true;
+static int			big_num_opt			=  -1;
+static const char		*csv_sep			= NULL;
+static bool			csv_output			= false;
+static bool			group				= false;
+static FILE			*output				= NULL;
+static const char		*pre_cmd			= NULL;
+static const char		*post_cmd			= NULL;
+static bool			sync_run			= false;
+static unsigned int		interval			= 0;
+static unsigned int		initial_delay			= 0;
+static unsigned int		unit_width			= 4; /* strlen("unit") */
+static bool			forever				= false;
+static struct timespec		ref_time;
+static struct cpu_map		*aggr_map;
+static int			(*aggr_get_id)(struct cpu_map *m, int cpu);
 
+static volatile int done = 0;
 
-static int			*fd[MAX_NR_CPUS][MAX_COUNTERS];
+struct perf_stat {
+	struct stats	  res_stats[3];
+};
 
-static int			event_scaled[MAX_COUNTERS];
+static inline void diff_timespec(struct timespec *r, struct timespec *a,
+				 struct timespec *b)
+{
+	r->tv_sec = a->tv_sec - b->tv_sec;
+	if (a->tv_nsec < b->tv_nsec) {
+		r->tv_nsec = a->tv_nsec + 1000000000L - b->tv_nsec;
+		r->tv_sec--;
+	} else {
+		r->tv_nsec = a->tv_nsec - b->tv_nsec ;
+	}
+}
 
-static volatile int done = 0;
+static inline struct cpu_map *perf_evsel__cpus(struct perf_evsel *evsel)
+{
+	return (evsel->cpus && !target.cpu_list) ? evsel->cpus : evsel_list->cpus;
+}
 
-struct stats
+static inline int perf_evsel__nr_cpus(struct perf_evsel *evsel)
 {
-	double n, mean, M2;
-};
+	return perf_evsel__cpus(evsel)->nr;
+}
 
-static void update_stats(struct stats *stats, u64 val)
+static void perf_evsel__reset_stat_priv(struct perf_evsel *evsel)
 {
-	double delta;
+	int i;
+	struct perf_stat *ps = evsel->priv;
 
-	stats->n++;
-	delta = val - stats->mean;
-	stats->mean += delta / stats->n;
-	stats->M2 += delta*(val - stats->mean);
+	for (i = 0; i < 3; i++)
+		init_stats(&ps->res_stats[i]);
 }
 
-static double avg_stats(struct stats *stats)
+static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
 {
-	return stats->mean;
+	evsel->priv = zalloc(sizeof(struct perf_stat));
+	if (evsel == NULL)
+		return -ENOMEM;
+	perf_evsel__reset_stat_priv(evsel);
+	return 0;
 }
 
-/*
- * http://en.wikipedia.org/wiki/Algorithms_for_calculating_variance
- *
- *       (\Sum n_i^2) - ((\Sum n_i)^2)/n
- * s^2 = -------------------------------
- *                  n - 1
- *
- * http://en.wikipedia.org/wiki/Stddev
- *
- * The std dev of the mean is related to the std dev by:
- *
- *             s
- * s_mean = -------
- *          sqrt(n)
- *
- */
-static double stddev_stats(struct stats *stats)
+static void perf_evsel__free_stat_priv(struct perf_evsel *evsel)
+{
+	zfree(&evsel->priv);
+}
+
+static int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel)
+{
+	void *addr;
+	size_t sz;
+
+	sz = sizeof(*evsel->counts) +
+	     (perf_evsel__nr_cpus(evsel) * sizeof(struct perf_counts_values));
+
+	addr = zalloc(sz);
+	if (!addr)
+		return -ENOMEM;
+
+	evsel->prev_raw_counts =  addr;
+
+	return 0;
+}
+
+static void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel)
+{
+	zfree(&evsel->prev_raw_counts);
+}
+
+static void perf_evlist__free_stats(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each(evlist, evsel) {
+		perf_evsel__free_stat_priv(evsel);
+		perf_evsel__free_counts(evsel);
+		perf_evsel__free_prev_raw_counts(evsel);
+	}
+}
+
+static int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw)
 {
-	double variance = stats->M2 / (stats->n - 1);
-	double variance_mean = variance / stats->n;
+	struct perf_evsel *evsel;
+
+	evlist__for_each(evlist, evsel) {
+		if (perf_evsel__alloc_stat_priv(evsel) < 0 ||
+		    perf_evsel__alloc_counts(evsel, perf_evsel__nr_cpus(evsel)) < 0 ||
+		    (alloc_raw && perf_evsel__alloc_prev_raw_counts(evsel) < 0))
+			goto out_free;
+	}
 
-	return sqrt(variance_mean);
+	return 0;
+
+out_free:
+	perf_evlist__free_stats(evlist);
+	return -1;
 }
 
-struct stats			event_res_stats[MAX_COUNTERS][3];
-struct stats			runtime_nsecs_stats;
-struct stats			walltime_nsecs_stats;
-struct stats			runtime_cycles_stats;
-struct stats			runtime_branches_stats;
+static struct stats runtime_nsecs_stats[MAX_NR_CPUS];
+static struct stats runtime_cycles_stats[MAX_NR_CPUS];
+static struct stats runtime_stalled_cycles_front_stats[MAX_NR_CPUS];
+static struct stats runtime_stalled_cycles_back_stats[MAX_NR_CPUS];
+static struct stats runtime_branches_stats[MAX_NR_CPUS];
+static struct stats runtime_cacherefs_stats[MAX_NR_CPUS];
+static struct stats runtime_l1_dcache_stats[MAX_NR_CPUS];
+static struct stats runtime_l1_icache_stats[MAX_NR_CPUS];
+static struct stats runtime_ll_cache_stats[MAX_NR_CPUS];
+static struct stats runtime_itlb_cache_stats[MAX_NR_CPUS];
+static struct stats runtime_dtlb_cache_stats[MAX_NR_CPUS];
+static struct stats runtime_cycles_in_tx_stats[MAX_NR_CPUS];
+static struct stats walltime_nsecs_stats;
+static struct stats runtime_transaction_stats[MAX_NR_CPUS];
+static struct stats runtime_elision_stats[MAX_NR_CPUS];
+
+static void perf_stat__reset_stats(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
 
-#define MATCH_EVENT(t, c, counter)			\
-	(attrs[counter].type == PERF_TYPE_##t &&	\
-	 attrs[counter].config == PERF_COUNT_##c)
+	evlist__for_each(evlist, evsel) {
+		perf_evsel__reset_stat_priv(evsel);
+		perf_evsel__reset_counts(evsel, perf_evsel__nr_cpus(evsel));
+	}
 
-#define ERR_PERF_OPEN \
-"Error: counter %d, sys_perf_event_open() syscall returned with %d (%s)\n"
+	memset(runtime_nsecs_stats, 0, sizeof(runtime_nsecs_stats));
+	memset(runtime_cycles_stats, 0, sizeof(runtime_cycles_stats));
+	memset(runtime_stalled_cycles_front_stats, 0, sizeof(runtime_stalled_cycles_front_stats));
+	memset(runtime_stalled_cycles_back_stats, 0, sizeof(runtime_stalled_cycles_back_stats));
+	memset(runtime_branches_stats, 0, sizeof(runtime_branches_stats));
+	memset(runtime_cacherefs_stats, 0, sizeof(runtime_cacherefs_stats));
+	memset(runtime_l1_dcache_stats, 0, sizeof(runtime_l1_dcache_stats));
+	memset(runtime_l1_icache_stats, 0, sizeof(runtime_l1_icache_stats));
+	memset(runtime_ll_cache_stats, 0, sizeof(runtime_ll_cache_stats));
+	memset(runtime_itlb_cache_stats, 0, sizeof(runtime_itlb_cache_stats));
+	memset(runtime_dtlb_cache_stats, 0, sizeof(runtime_dtlb_cache_stats));
+	memset(runtime_cycles_in_tx_stats, 0,
+			sizeof(runtime_cycles_in_tx_stats));
+	memset(runtime_transaction_stats, 0,
+		sizeof(runtime_transaction_stats));
+	memset(runtime_elision_stats, 0, sizeof(runtime_elision_stats));
+	memset(&walltime_nsecs_stats, 0, sizeof(walltime_nsecs_stats));
+}
 
-static int create_perf_stat_counter(int counter)
+static int create_perf_stat_counter(struct perf_evsel *evsel)
 {
-	struct perf_event_attr *attr = attrs + counter;
-	int thread;
-	int ncreated = 0;
+	struct perf_event_attr *attr = &evsel->attr;
 
 	if (scale)
 		attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED |
 				    PERF_FORMAT_TOTAL_TIME_RUNNING;
 
-	if (system_wide) {
-		unsigned int cpu;
+	attr->inherit = !no_inherit;
 
-		for (cpu = 0; cpu < nr_cpus; cpu++) {
-			fd[cpu][counter][0] = sys_perf_event_open(attr,
-					-1, cpumap[cpu], -1, 0);
-			if (fd[cpu][counter][0] < 0)
-				pr_debug(ERR_PERF_OPEN, counter,
-					 fd[cpu][counter][0], strerror(errno));
-			else
-				++ncreated;
-		}
-	} else {
-		attr->inherit = !no_inherit;
-		if (target_pid == -1 && target_tid == -1) {
-			attr->disabled = 1;
+	if (target__has_cpu(&target))
+		return perf_evsel__open_per_cpu(evsel, perf_evsel__cpus(evsel));
+
+	if (!target__has_task(&target) && perf_evsel__is_group_leader(evsel)) {
+		attr->disabled = 1;
+		if (!initial_delay)
 			attr->enable_on_exec = 1;
-		}
-		for (thread = 0; thread < thread_num; thread++) {
-			fd[0][counter][thread] = sys_perf_event_open(attr,
-				all_tids[thread], -1, -1, 0);
-			if (fd[0][counter][thread] < 0)
-				pr_debug(ERR_PERF_OPEN, counter,
-					 fd[0][counter][thread],
-					 strerror(errno));
-			else
-				++ncreated;
-		}
 	}
 
-	return ncreated;
+	return perf_evsel__open_per_thread(evsel, evsel_list->threads);
 }
 
 /*
  * Does the counter have nsecs as a unit?
  */
-static inline int nsec_counter(int counter)
+static inline int nsec_counter(struct perf_evsel *evsel)
 {
-	if (MATCH_EVENT(SOFTWARE, SW_CPU_CLOCK, counter) ||
-	    MATCH_EVENT(SOFTWARE, SW_TASK_CLOCK, counter))
+	if (perf_evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK) ||
+	    perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK))
 		return 1;
 
 	return 0;
 }
 
+static struct perf_evsel *nth_evsel(int n)
+{
+	static struct perf_evsel **array;
+	static int array_len;
+	struct perf_evsel *ev;
+	int j;
+
+	/* Assumes this only called when evsel_list does not change anymore. */
+	if (!array) {
+		evlist__for_each(evsel_list, ev)
+			array_len++;
+		array = malloc(array_len * sizeof(void *));
+		if (!array)
+			exit(ENOMEM);
+		j = 0;
+		evlist__for_each(evsel_list, ev)
+			array[j++] = ev;
+	}
+	if (n < array_len)
+		return array[n];
+	return NULL;
+}
+
+/*
+ * Update various tracking values we maintain to print
+ * more semantic information such as miss/hit ratios,
+ * instruction rates, etc:
+ */
+static void update_shadow_stats(struct perf_evsel *counter, u64 *count)
+{
+	if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK))
+		update_stats(&runtime_nsecs_stats[0], count[0]);
+	else if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
+		update_stats(&runtime_cycles_stats[0], count[0]);
+	else if (transaction_run &&
+		 perf_evsel__cmp(counter, nth_evsel(T_CYCLES_IN_TX)))
+		update_stats(&runtime_cycles_in_tx_stats[0], count[0]);
+	else if (transaction_run &&
+		 perf_evsel__cmp(counter, nth_evsel(T_TRANSACTION_START)))
+		update_stats(&runtime_transaction_stats[0], count[0]);
+	else if (transaction_run &&
+		 perf_evsel__cmp(counter, nth_evsel(T_ELISION_START)))
+		update_stats(&runtime_elision_stats[0], count[0]);
+	else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND))
+		update_stats(&runtime_stalled_cycles_front_stats[0], count[0]);
+	else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND))
+		update_stats(&runtime_stalled_cycles_back_stats[0], count[0]);
+	else if (perf_evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS))
+		update_stats(&runtime_branches_stats[0], count[0]);
+	else if (perf_evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES))
+		update_stats(&runtime_cacherefs_stats[0], count[0]);
+	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1D))
+		update_stats(&runtime_l1_dcache_stats[0], count[0]);
+	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1I))
+		update_stats(&runtime_l1_icache_stats[0], count[0]);
+	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_LL))
+		update_stats(&runtime_ll_cache_stats[0], count[0]);
+	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_DTLB))
+		update_stats(&runtime_dtlb_cache_stats[0], count[0]);
+	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_ITLB))
+		update_stats(&runtime_itlb_cache_stats[0], count[0]);
+}
+
 /*
  * Read out the results of a single counter:
+ * aggregate counts across CPUs in system-wide mode
  */
-static void read_counter(int counter)
+static int read_counter_aggr(struct perf_evsel *counter)
 {
-	u64 count[3], single_count[3];
-	unsigned int cpu;
-	size_t res, nv;
-	int scaled;
-	int i, thread;
+	struct perf_stat *ps = counter->priv;
+	u64 *count = counter->counts->aggr.values;
+	int i;
 
-	count[0] = count[1] = count[2] = 0;
+	if (__perf_evsel__read(counter, perf_evsel__nr_cpus(counter),
+			       thread_map__nr(evsel_list->threads), scale) < 0)
+		return -1;
 
-	nv = scale ? 3 : 1;
-	for (cpu = 0; cpu < nr_cpus; cpu++) {
-		for (thread = 0; thread < thread_num; thread++) {
-			if (fd[cpu][counter][thread] < 0)
-				continue;
+	for (i = 0; i < 3; i++)
+		update_stats(&ps->res_stats[i], count[i]);
 
-			res = read(fd[cpu][counter][thread],
-					single_count, nv * sizeof(u64));
-			assert(res == nv * sizeof(u64));
+	if (verbose) {
+		fprintf(output, "%s: %" PRIu64 " %" PRIu64 " %" PRIu64 "\n",
+			perf_evsel__name(counter), count[0], count[1], count[2]);
+	}
 
-			close(fd[cpu][counter][thread]);
-			fd[cpu][counter][thread] = -1;
+	/*
+	 * Save the full runtime - to allow normalization during printout:
+	 */
+	update_shadow_stats(counter, count);
 
-			count[0] += single_count[0];
-			if (scale) {
-				count[1] += single_count[1];
-				count[2] += single_count[2];
-			}
-		}
+	return 0;
+}
+
+/*
+ * Read out the results of a single counter:
+ * do not aggregate counts across CPUs in system-wide mode
+ */
+static int read_counter(struct perf_evsel *counter)
+{
+	u64 *count;
+	int cpu;
+
+	for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
+		if (__perf_evsel__read_on_cpu(counter, cpu, 0, scale) < 0)
+			return -1;
+
+		count = counter->counts->cpu[cpu].values;
+
+		update_shadow_stats(counter, count);
 	}
 
-	scaled = 0;
-	if (scale) {
-		if (count[2] == 0) {
-			event_scaled[counter] = -1;
-			count[0] = 0;
-			return;
+	return 0;
+}
+
+static void print_interval(void)
+{
+	static int num_print_interval;
+	struct perf_evsel *counter;
+	struct perf_stat *ps;
+	struct timespec ts, rs;
+	char prefix[64];
+
+	if (aggr_mode == AGGR_GLOBAL) {
+		evlist__for_each(evsel_list, counter) {
+			ps = counter->priv;
+			memset(ps->res_stats, 0, sizeof(ps->res_stats));
+			read_counter_aggr(counter);
+		}
+	} else	{
+		evlist__for_each(evsel_list, counter) {
+			ps = counter->priv;
+			memset(ps->res_stats, 0, sizeof(ps->res_stats));
+			read_counter(counter);
 		}
+	}
 
-		if (count[2] < count[1]) {
-			event_scaled[counter] = 1;
-			count[0] = (unsigned long long)
-				((double)count[0] * count[1] / count[2] + 0.5);
+	clock_gettime(CLOCK_MONOTONIC, &ts);
+	diff_timespec(&rs, &ts, &ref_time);
+	sprintf(prefix, "%6lu.%09lu%s", rs.tv_sec, rs.tv_nsec, csv_sep);
+
+	if (num_print_interval == 0 && !csv_output) {
+		switch (aggr_mode) {
+		case AGGR_SOCKET:
+			fprintf(output, "#           time socket cpus             counts %*s events\n", unit_width, "unit");
+			break;
+		case AGGR_CORE:
+			fprintf(output, "#           time core         cpus             counts %*s events\n", unit_width, "unit");
+			break;
+		case AGGR_NONE:
+			fprintf(output, "#           time CPU                counts %*s events\n", unit_width, "unit");
+			break;
+		case AGGR_GLOBAL:
+		default:
+			fprintf(output, "#           time             counts %*s events\n", unit_width, "unit");
 		}
 	}
 
-	for (i = 0; i < 3; i++)
-		update_stats(&event_res_stats[counter][i], count[i]);
+	if (++num_print_interval == 25)
+		num_print_interval = 0;
+
+	switch (aggr_mode) {
+	case AGGR_CORE:
+	case AGGR_SOCKET:
+		print_aggr(prefix);
+		break;
+	case AGGR_NONE:
+		evlist__for_each(evsel_list, counter)
+			print_counter(counter, prefix);
+		break;
+	case AGGR_GLOBAL:
+	default:
+		evlist__for_each(evsel_list, counter)
+			print_counter_aggr(counter, prefix);
+	}
 
-	if (verbose) {
-		fprintf(stderr, "%s: %Ld %Ld %Ld\n", event_name(counter),
-				count[0], count[1], count[2]);
+	fflush(output);
+}
+
+static void handle_initial_delay(void)
+{
+	struct perf_evsel *counter;
+
+	if (initial_delay) {
+		const int ncpus = cpu_map__nr(evsel_list->cpus),
+			nthreads = thread_map__nr(evsel_list->threads);
+
+		usleep(initial_delay * 1000);
+		evlist__for_each(evsel_list, counter)
+			perf_evsel__enable(counter, ncpus, nthreads);
 	}
+}
 
-	/*
-	 * Save the full runtime - to allow normalization during printout:
-	 */
-	if (MATCH_EVENT(SOFTWARE, SW_TASK_CLOCK, counter))
-		update_stats(&runtime_nsecs_stats, count[0]);
-	if (MATCH_EVENT(HARDWARE, HW_CPU_CYCLES, counter))
-		update_stats(&runtime_cycles_stats, count[0]);
-	if (MATCH_EVENT(HARDWARE, HW_BRANCH_INSTRUCTIONS, counter))
-		update_stats(&runtime_branches_stats, count[0]);
+static volatile int workload_exec_errno;
+
+/*
+ * perf_evlist__prepare_workload will send a SIGUSR1
+ * if the fork fails, since we asked by setting its
+ * want_signal to true.
+ */
+static void workload_exec_failed_signal(int signo __maybe_unused, siginfo_t *info,
+					void *ucontext __maybe_unused)
+{
+	workload_exec_errno = info->si_value.sival_int;
 }
 
-static int run_perf_stat(int argc __used, const char **argv)
+static int __run_perf_stat(int argc, const char **argv)
 {
+	char msg[512];
 	unsigned long long t0, t1;
+	struct perf_evsel *counter;
+	struct timespec ts;
+	size_t l;
 	int status = 0;
-	int counter, ncreated = 0;
-	int child_ready_pipe[2], go_pipe[2];
 	const bool forks = (argc > 0);
-	char buf;
-
-	if (!system_wide)
-		nr_cpus = 1;
 
-	if (forks && (pipe(child_ready_pipe) < 0 || pipe(go_pipe) < 0)) {
-		perror("failed to create pipes");
-		exit(1);
+	if (interval) {
+		ts.tv_sec  = interval / 1000;
+		ts.tv_nsec = (interval % 1000) * 1000000;
+	} else {
+		ts.tv_sec  = 1;
+		ts.tv_nsec = 0;
 	}
 
 	if (forks) {
-		if ((child_pid = fork()) < 0)
-			perror("failed to fork");
+		if (perf_evlist__prepare_workload(evsel_list, &target, argv, false,
+						  workload_exec_failed_signal) < 0) {
+			perror("failed to prepare workload");
+			return -1;
+		}
+		child_pid = evsel_list->workload.pid;
+	}
 
-		if (!child_pid) {
-			close(child_ready_pipe[0]);
-			close(go_pipe[1]);
-			fcntl(go_pipe[0], F_SETFD, FD_CLOEXEC);
+	if (group)
+		perf_evlist__set_leader(evsel_list);
 
+	evlist__for_each(evsel_list, counter) {
+		if (create_perf_stat_counter(counter) < 0) {
 			/*
-			 * Do a dummy execvp to get the PLT entry resolved,
-			 * so we avoid the resolver overhead on the real
-			 * execvp call.
+			 * PPC returns ENXIO for HW counters until 2.6.37
+			 * (behavior changed with commit b0a873e).
 			 */
-			execvp("", (char **)argv);
+			if (errno == EINVAL || errno == ENOSYS ||
+			    errno == ENOENT || errno == EOPNOTSUPP ||
+			    errno == ENXIO) {
+				if (verbose)
+					ui__warning("%s event is not supported by the kernel.\n",
+						    perf_evsel__name(counter));
+				counter->supported = false;
+				continue;
+			}
 
-			/*
-			 * Tell the parent we're ready to go
-			 */
-			close(child_ready_pipe[1]);
+			perf_evsel__open_strerror(counter, &target,
+						  errno, msg, sizeof(msg));
+			ui__error("%s\n", msg);
 
-			/*
-			 * Wait until the parent tells us to go.
-			 */
-			if (read(go_pipe[0], &buf, 1) == -1)
-				perror("unable to read pipe");
+			if (child_pid != -1)
+				kill(child_pid, SIGTERM);
 
-			execvp(argv[0], (char **)argv);
-
-			perror(argv[0]);
-			exit(-1);
+			return -1;
 		}
+		counter->supported = true;
 
-		if (target_tid == -1 && target_pid == -1 && !system_wide)
-			all_tids[0] = child_pid;
-
-		/*
-		 * Wait for the child to be ready to exec.
-		 */
-		close(child_ready_pipe[1]);
-		close(go_pipe[0]);
-		if (read(child_ready_pipe[0], &buf, 1) == -1)
-			perror("unable to read pipe");
-		close(child_ready_pipe[0]);
+		l = strlen(counter->unit);
+		if (l > unit_width)
+			unit_width = l;
 	}
 
-	for (counter = 0; counter < nr_counters; counter++)
-		ncreated += create_perf_stat_counter(counter);
-
-	if (ncreated == 0) {
-		pr_err("No permission to collect %sstats.\n"
-		       "Consider tweaking /proc/sys/kernel/perf_event_paranoid.\n",
-		       system_wide ? "system-wide " : "");
-		if (child_pid != -1)
-			kill(child_pid, SIGTERM);
+	if (perf_evlist__apply_filters(evsel_list)) {
+		error("failed to set filter with %d (%s)\n", errno,
+			strerror(errno));
 		return -1;
 	}
 
@@ -349,165 +601,801 @@ static int run_perf_stat(int argc __used, const char **argv)
 	 * Enable counters and exec the command:
 	 */
 	t0 = rdclock();
+	clock_gettime(CLOCK_MONOTONIC, &ref_time);
 
 	if (forks) {
-		close(go_pipe[1]);
+		perf_evlist__start_workload(evsel_list);
+		handle_initial_delay();
+
+		if (interval) {
+			while (!waitpid(child_pid, &status, WNOHANG)) {
+				nanosleep(&ts, NULL);
+				print_interval();
+			}
+		}
 		wait(&status);
+
+		if (workload_exec_errno) {
+			const char *emsg = strerror_r(workload_exec_errno, msg, sizeof(msg));
+			pr_err("Workload failed: %s\n", emsg);
+			return -1;
+		}
+
+		if (WIFSIGNALED(status))
+			psignal(WTERMSIG(status), argv[0]);
 	} else {
-		while(!done) sleep(1);
+		handle_initial_delay();
+		while (!done) {
+			nanosleep(&ts, NULL);
+			if (interval)
+				print_interval();
+		}
 	}
 
 	t1 = rdclock();
 
 	update_stats(&walltime_nsecs_stats, t1 - t0);
 
-	for (counter = 0; counter < nr_counters; counter++)
-		read_counter(counter);
+	if (aggr_mode == AGGR_GLOBAL) {
+		evlist__for_each(evsel_list, counter) {
+			read_counter_aggr(counter);
+			perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter),
+					     thread_map__nr(evsel_list->threads));
+		}
+	} else {
+		evlist__for_each(evsel_list, counter) {
+			read_counter(counter);
+			perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter), 1);
+		}
+	}
 
 	return WEXITSTATUS(status);
 }
 
-static void print_noise(int counter, double avg)
+static int run_perf_stat(int argc, const char **argv)
+{
+	int ret;
+
+	if (pre_cmd) {
+		ret = system(pre_cmd);
+		if (ret)
+			return ret;
+	}
+
+	if (sync_run)
+		sync();
+
+	ret = __run_perf_stat(argc, argv);
+	if (ret)
+		return ret;
+
+	if (post_cmd) {
+		ret = system(post_cmd);
+		if (ret)
+			return ret;
+	}
+
+	return ret;
+}
+
+static void print_noise_pct(double total, double avg)
+{
+	double pct = rel_stddev_stats(total, avg);
+
+	if (csv_output)
+		fprintf(output, "%s%.2f%%", csv_sep, pct);
+	else if (pct)
+		fprintf(output, "  ( +-%6.2f%% )", pct);
+}
+
+static void print_noise(struct perf_evsel *evsel, double avg)
 {
+	struct perf_stat *ps;
+
 	if (run_count == 1)
 		return;
 
-	fprintf(stderr, "   ( +- %7.3f%% )",
-			100 * stddev_stats(&event_res_stats[counter][0]) / avg);
+	ps = evsel->priv;
+	print_noise_pct(stddev_stats(&ps->res_stats[0]), avg);
 }
 
-static void nsec_printout(int counter, double avg)
+static void aggr_printout(struct perf_evsel *evsel, int id, int nr)
+{
+	switch (aggr_mode) {
+	case AGGR_CORE:
+		fprintf(output, "S%d-C%*d%s%*d%s",
+			cpu_map__id_to_socket(id),
+			csv_output ? 0 : -8,
+			cpu_map__id_to_cpu(id),
+			csv_sep,
+			csv_output ? 0 : 4,
+			nr,
+			csv_sep);
+		break;
+	case AGGR_SOCKET:
+		fprintf(output, "S%*d%s%*d%s",
+			csv_output ? 0 : -5,
+			id,
+			csv_sep,
+			csv_output ? 0 : 4,
+			nr,
+			csv_sep);
+			break;
+	case AGGR_NONE:
+		fprintf(output, "CPU%*d%s",
+			csv_output ? 0 : -4,
+			perf_evsel__cpus(evsel)->map[id], csv_sep);
+		break;
+	case AGGR_GLOBAL:
+	default:
+		break;
+	}
+}
+
+static void nsec_printout(int cpu, int nr, struct perf_evsel *evsel, double avg)
 {
 	double msecs = avg / 1e6;
+	const char *fmt_v, *fmt_n;
+	char name[25];
 
-	fprintf(stderr, " %18.6f  %-24s", msecs, event_name(counter));
+	fmt_v = csv_output ? "%.6f%s" : "%18.6f%s";
+	fmt_n = csv_output ? "%s" : "%-25s";
 
-	if (MATCH_EVENT(SOFTWARE, SW_TASK_CLOCK, counter)) {
-		fprintf(stderr, " # %10.3f CPUs ",
-				avg / avg_stats(&walltime_nsecs_stats));
-	}
+	aggr_printout(evsel, cpu, nr);
+
+	scnprintf(name, sizeof(name), "%s%s",
+		  perf_evsel__name(evsel), csv_output ? "" : " (msec)");
+
+	fprintf(output, fmt_v, msecs, csv_sep);
+
+	if (csv_output)
+		fprintf(output, "%s%s", evsel->unit, csv_sep);
+	else
+		fprintf(output, "%-*s%s", unit_width, evsel->unit, csv_sep);
+
+	fprintf(output, fmt_n, name);
+
+	if (evsel->cgrp)
+		fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
+
+	if (csv_output || interval)
+		return;
+
+	if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK))
+		fprintf(output, " # %8.3f CPUs utilized          ",
+			avg / avg_stats(&walltime_nsecs_stats));
+	else
+		fprintf(output, "                                   ");
 }
 
-static void abs_printout(int counter, double avg)
+/* used for get_ratio_color() */
+enum grc_type {
+	GRC_STALLED_CYCLES_FE,
+	GRC_STALLED_CYCLES_BE,
+	GRC_CACHE_MISSES,
+	GRC_MAX_NR
+};
+
+static const char *get_ratio_color(enum grc_type type, double ratio)
+{
+	static const double grc_table[GRC_MAX_NR][3] = {
+		[GRC_STALLED_CYCLES_FE] = { 50.0, 30.0, 10.0 },
+		[GRC_STALLED_CYCLES_BE] = { 75.0, 50.0, 20.0 },
+		[GRC_CACHE_MISSES] 	= { 20.0, 10.0, 5.0 },
+	};
+	const char *color = PERF_COLOR_NORMAL;
+
+	if (ratio > grc_table[type][0])
+		color = PERF_COLOR_RED;
+	else if (ratio > grc_table[type][1])
+		color = PERF_COLOR_MAGENTA;
+	else if (ratio > grc_table[type][2])
+		color = PERF_COLOR_YELLOW;
+
+	return color;
+}
+
+static void print_stalled_cycles_frontend(int cpu,
+					  struct perf_evsel *evsel
+					  __maybe_unused, double avg)
 {
 	double total, ratio = 0.0;
+	const char *color;
 
-	if (big_num)
-		fprintf(stderr, " %'18.0f  %-24s", avg, event_name(counter));
-	else
-		fprintf(stderr, " %18.0f  %-24s", avg, event_name(counter));
+	total = avg_stats(&runtime_cycles_stats[cpu]);
 
-	if (MATCH_EVENT(HARDWARE, HW_INSTRUCTIONS, counter)) {
-		total = avg_stats(&runtime_cycles_stats);
+	if (total)
+		ratio = avg / total * 100.0;
 
-		if (total)
+	color = get_ratio_color(GRC_STALLED_CYCLES_FE, ratio);
+
+	fprintf(output, " #  ");
+	color_fprintf(output, color, "%6.2f%%", ratio);
+	fprintf(output, " frontend cycles idle   ");
+}
+
+static void print_stalled_cycles_backend(int cpu,
+					 struct perf_evsel *evsel
+					 __maybe_unused, double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+
+	total = avg_stats(&runtime_cycles_stats[cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = get_ratio_color(GRC_STALLED_CYCLES_BE, ratio);
+
+	fprintf(output, " #  ");
+	color_fprintf(output, color, "%6.2f%%", ratio);
+	fprintf(output, " backend  cycles idle   ");
+}
+
+static void print_branch_misses(int cpu,
+				struct perf_evsel *evsel __maybe_unused,
+				double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+
+	total = avg_stats(&runtime_branches_stats[cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
+
+	fprintf(output, " #  ");
+	color_fprintf(output, color, "%6.2f%%", ratio);
+	fprintf(output, " of all branches        ");
+}
+
+static void print_l1_dcache_misses(int cpu,
+				   struct perf_evsel *evsel __maybe_unused,
+				   double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+
+	total = avg_stats(&runtime_l1_dcache_stats[cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
+
+	fprintf(output, " #  ");
+	color_fprintf(output, color, "%6.2f%%", ratio);
+	fprintf(output, " of all L1-dcache hits  ");
+}
+
+static void print_l1_icache_misses(int cpu,
+				   struct perf_evsel *evsel __maybe_unused,
+				   double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+
+	total = avg_stats(&runtime_l1_icache_stats[cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
+
+	fprintf(output, " #  ");
+	color_fprintf(output, color, "%6.2f%%", ratio);
+	fprintf(output, " of all L1-icache hits  ");
+}
+
+static void print_dtlb_cache_misses(int cpu,
+				    struct perf_evsel *evsel __maybe_unused,
+				    double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+
+	total = avg_stats(&runtime_dtlb_cache_stats[cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
+
+	fprintf(output, " #  ");
+	color_fprintf(output, color, "%6.2f%%", ratio);
+	fprintf(output, " of all dTLB cache hits ");
+}
+
+static void print_itlb_cache_misses(int cpu,
+				    struct perf_evsel *evsel __maybe_unused,
+				    double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+
+	total = avg_stats(&runtime_itlb_cache_stats[cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
+
+	fprintf(output, " #  ");
+	color_fprintf(output, color, "%6.2f%%", ratio);
+	fprintf(output, " of all iTLB cache hits ");
+}
+
+static void print_ll_cache_misses(int cpu,
+				  struct perf_evsel *evsel __maybe_unused,
+				  double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+
+	total = avg_stats(&runtime_ll_cache_stats[cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
+
+	fprintf(output, " #  ");
+	color_fprintf(output, color, "%6.2f%%", ratio);
+	fprintf(output, " of all LL-cache hits   ");
+}
+
+static void abs_printout(int cpu, int nr, struct perf_evsel *evsel, double avg)
+{
+	double total, ratio = 0.0, total2;
+	double sc =  evsel->scale;
+	const char *fmt;
+
+	if (csv_output) {
+		fmt = sc != 1.0 ?  "%.2f%s" : "%.0f%s";
+	} else {
+		if (big_num)
+			fmt = sc != 1.0 ? "%'18.2f%s" : "%'18.0f%s";
+		else
+			fmt = sc != 1.0 ? "%18.2f%s" : "%18.0f%s";
+	}
+
+	aggr_printout(evsel, cpu, nr);
+
+	if (aggr_mode == AGGR_GLOBAL)
+		cpu = 0;
+
+	fprintf(output, fmt, avg, csv_sep);
+
+	if (evsel->unit)
+		fprintf(output, "%-*s%s",
+			csv_output ? 0 : unit_width,
+			evsel->unit, csv_sep);
+
+	fprintf(output, "%-*s", csv_output ? 0 : 25, perf_evsel__name(evsel));
+
+	if (evsel->cgrp)
+		fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
+
+	if (csv_output || interval)
+		return;
+
+	if (perf_evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) {
+		total = avg_stats(&runtime_cycles_stats[cpu]);
+		if (total) {
 			ratio = avg / total;
+			fprintf(output, " #   %5.2f  insns per cycle        ", ratio);
+		}
+		total = avg_stats(&runtime_stalled_cycles_front_stats[cpu]);
+		total = max(total, avg_stats(&runtime_stalled_cycles_back_stats[cpu]));
+
+		if (total && avg) {
+			ratio = total / avg;
+			fprintf(output, "\n");
+			if (aggr_mode == AGGR_NONE)
+				fprintf(output, "        ");
+			fprintf(output, "                                                  #   %5.2f  stalled cycles per insn", ratio);
+		}
 
-		fprintf(stderr, " # %10.3f IPC  ", ratio);
-	} else if (MATCH_EVENT(HARDWARE, HW_BRANCH_MISSES, counter) &&
-			runtime_branches_stats.n != 0) {
-		total = avg_stats(&runtime_branches_stats);
+	} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES) &&
+			runtime_branches_stats[cpu].n != 0) {
+		print_branch_misses(cpu, evsel, avg);
+	} else if (
+		evsel->attr.type == PERF_TYPE_HW_CACHE &&
+		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1D |
+					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
+					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
+			runtime_l1_dcache_stats[cpu].n != 0) {
+		print_l1_dcache_misses(cpu, evsel, avg);
+	} else if (
+		evsel->attr.type == PERF_TYPE_HW_CACHE &&
+		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1I |
+					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
+					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
+			runtime_l1_icache_stats[cpu].n != 0) {
+		print_l1_icache_misses(cpu, evsel, avg);
+	} else if (
+		evsel->attr.type == PERF_TYPE_HW_CACHE &&
+		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_DTLB |
+					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
+					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
+			runtime_dtlb_cache_stats[cpu].n != 0) {
+		print_dtlb_cache_misses(cpu, evsel, avg);
+	} else if (
+		evsel->attr.type == PERF_TYPE_HW_CACHE &&
+		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_ITLB |
+					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
+					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
+			runtime_itlb_cache_stats[cpu].n != 0) {
+		print_itlb_cache_misses(cpu, evsel, avg);
+	} else if (
+		evsel->attr.type == PERF_TYPE_HW_CACHE &&
+		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_LL |
+					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
+					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
+			runtime_ll_cache_stats[cpu].n != 0) {
+		print_ll_cache_misses(cpu, evsel, avg);
+	} else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES) &&
+			runtime_cacherefs_stats[cpu].n != 0) {
+		total = avg_stats(&runtime_cacherefs_stats[cpu]);
 
 		if (total)
 			ratio = avg * 100 / total;
 
-		fprintf(stderr, " # %10.3f %%    ", ratio);
+		fprintf(output, " # %8.3f %% of all cache refs    ", ratio);
+
+	} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) {
+		print_stalled_cycles_frontend(cpu, evsel, avg);
+	} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) {
+		print_stalled_cycles_backend(cpu, evsel, avg);
+	} else if (perf_evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) {
+		total = avg_stats(&runtime_nsecs_stats[cpu]);
+
+		if (total) {
+			ratio = avg / total;
+			fprintf(output, " # %8.3f GHz                    ", ratio);
+		}
+	} else if (transaction_run &&
+		   perf_evsel__cmp(evsel, nth_evsel(T_CYCLES_IN_TX))) {
+		total = avg_stats(&runtime_cycles_stats[cpu]);
+		if (total)
+			fprintf(output,
+				" #   %5.2f%% transactional cycles   ",
+				100.0 * (avg / total));
+	} else if (transaction_run &&
+		   perf_evsel__cmp(evsel, nth_evsel(T_CYCLES_IN_TX_CP))) {
+		total = avg_stats(&runtime_cycles_stats[cpu]);
+		total2 = avg_stats(&runtime_cycles_in_tx_stats[cpu]);
+		if (total2 < avg)
+			total2 = avg;
+		if (total)
+			fprintf(output,
+				" #   %5.2f%% aborted cycles         ",
+				100.0 * ((total2-avg) / total));
+	} else if (transaction_run &&
+		   perf_evsel__cmp(evsel, nth_evsel(T_TRANSACTION_START)) &&
+		   avg > 0 &&
+		   runtime_cycles_in_tx_stats[cpu].n != 0) {
+		total = avg_stats(&runtime_cycles_in_tx_stats[cpu]);
 
-	} else if (runtime_nsecs_stats.n != 0) {
-		total = avg_stats(&runtime_nsecs_stats);
+		if (total)
+			ratio = total / avg;
+
+		fprintf(output, " # %8.0f cycles / transaction   ", ratio);
+	} else if (transaction_run &&
+		   perf_evsel__cmp(evsel, nth_evsel(T_ELISION_START)) &&
+		   avg > 0 &&
+		   runtime_cycles_in_tx_stats[cpu].n != 0) {
+		total = avg_stats(&runtime_cycles_in_tx_stats[cpu]);
+
+		if (total)
+			ratio = total / avg;
+
+		fprintf(output, " # %8.0f cycles / elision       ", ratio);
+	} else if (runtime_nsecs_stats[cpu].n != 0) {
+		char unit = 'M';
+
+		total = avg_stats(&runtime_nsecs_stats[cpu]);
 
 		if (total)
 			ratio = 1000.0 * avg / total;
+		if (ratio < 0.001) {
+			ratio *= 1000;
+			unit = 'K';
+		}
 
-		fprintf(stderr, " # %10.3f M/sec", ratio);
+		fprintf(output, " # %8.3f %c/sec                  ", ratio, unit);
+	} else {
+		fprintf(output, "                                   ");
+	}
+}
+
+static void print_aggr(char *prefix)
+{
+	struct perf_evsel *counter;
+	int cpu, cpu2, s, s2, id, nr;
+	double uval;
+	u64 ena, run, val;
+
+	if (!(aggr_map || aggr_get_id))
+		return;
+
+	for (s = 0; s < aggr_map->nr; s++) {
+		id = aggr_map->map[s];
+		evlist__for_each(evsel_list, counter) {
+			val = ena = run = 0;
+			nr = 0;
+			for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
+				cpu2 = perf_evsel__cpus(counter)->map[cpu];
+				s2 = aggr_get_id(evsel_list->cpus, cpu2);
+				if (s2 != id)
+					continue;
+				val += counter->counts->cpu[cpu].val;
+				ena += counter->counts->cpu[cpu].ena;
+				run += counter->counts->cpu[cpu].run;
+				nr++;
+			}
+			if (prefix)
+				fprintf(output, "%s", prefix);
+
+			if (run == 0 || ena == 0) {
+				aggr_printout(counter, id, nr);
+
+				fprintf(output, "%*s%s",
+					csv_output ? 0 : 18,
+					counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
+					csv_sep);
+
+				fprintf(output, "%-*s%s",
+					csv_output ? 0 : unit_width,
+					counter->unit, csv_sep);
+
+				fprintf(output, "%*s",
+					csv_output ? 0 : -25,
+					perf_evsel__name(counter));
+
+				if (counter->cgrp)
+					fprintf(output, "%s%s",
+						csv_sep, counter->cgrp->name);
+
+				fputc('\n', output);
+				continue;
+			}
+			uval = val * counter->scale;
+
+			if (nsec_counter(counter))
+				nsec_printout(id, nr, counter, uval);
+			else
+				abs_printout(id, nr, counter, uval);
+
+			if (!csv_output) {
+				print_noise(counter, 1.0);
+
+				if (run != ena)
+					fprintf(output, "  (%.2f%%)",
+						100.0 * run / ena);
+			}
+			fputc('\n', output);
+		}
 	}
 }
 
 /*
  * Print out the results of a single counter:
+ * aggregated counts in system-wide mode
  */
-static void print_counter(int counter)
+static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
 {
-	double avg = avg_stats(&event_res_stats[counter][0]);
-	int scaled = event_scaled[counter];
+	struct perf_stat *ps = counter->priv;
+	double avg = avg_stats(&ps->res_stats[0]);
+	int scaled = counter->counts->scaled;
+	double uval;
+
+	if (prefix)
+		fprintf(output, "%s", prefix);
 
 	if (scaled == -1) {
-		fprintf(stderr, " %18s  %-24s\n",
-			"<not counted>", event_name(counter));
+		fprintf(output, "%*s%s",
+			csv_output ? 0 : 18,
+			counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
+			csv_sep);
+		fprintf(output, "%-*s%s",
+			csv_output ? 0 : unit_width,
+			counter->unit, csv_sep);
+		fprintf(output, "%*s",
+			csv_output ? 0 : -25,
+			perf_evsel__name(counter));
+
+		if (counter->cgrp)
+			fprintf(output, "%s%s", csv_sep, counter->cgrp->name);
+
+		fputc('\n', output);
 		return;
 	}
 
+	uval = avg * counter->scale;
+
 	if (nsec_counter(counter))
-		nsec_printout(counter, avg);
+		nsec_printout(-1, 0, counter, uval);
 	else
-		abs_printout(counter, avg);
+		abs_printout(-1, 0, counter, uval);
 
 	print_noise(counter, avg);
 
+	if (csv_output) {
+		fputc('\n', output);
+		return;
+	}
+
 	if (scaled) {
 		double avg_enabled, avg_running;
 
-		avg_enabled = avg_stats(&event_res_stats[counter][1]);
-		avg_running = avg_stats(&event_res_stats[counter][2]);
+		avg_enabled = avg_stats(&ps->res_stats[1]);
+		avg_running = avg_stats(&ps->res_stats[2]);
 
-		fprintf(stderr, "  (scaled from %.2f%%)",
-				100 * avg_running / avg_enabled);
+		fprintf(output, " [%5.2f%%]", 100 * avg_running / avg_enabled);
 	}
+	fprintf(output, "\n");
+}
+
+/*
+ * Print out the results of a single counter:
+ * does not use aggregated count in system-wide
+ */
+static void print_counter(struct perf_evsel *counter, char *prefix)
+{
+	u64 ena, run, val;
+	double uval;
+	int cpu;
+
+	for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
+		val = counter->counts->cpu[cpu].val;
+		ena = counter->counts->cpu[cpu].ena;
+		run = counter->counts->cpu[cpu].run;
+
+		if (prefix)
+			fprintf(output, "%s", prefix);
+
+		if (run == 0 || ena == 0) {
+			fprintf(output, "CPU%*d%s%*s%s",
+				csv_output ? 0 : -4,
+				perf_evsel__cpus(counter)->map[cpu], csv_sep,
+				csv_output ? 0 : 18,
+				counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
+				csv_sep);
+
+				fprintf(output, "%-*s%s",
+					csv_output ? 0 : unit_width,
+					counter->unit, csv_sep);
+
+				fprintf(output, "%*s",
+					csv_output ? 0 : -25,
+					perf_evsel__name(counter));
+
+			if (counter->cgrp)
+				fprintf(output, "%s%s",
+					csv_sep, counter->cgrp->name);
+
+			fputc('\n', output);
+			continue;
+		}
+
+		uval = val * counter->scale;
+
+		if (nsec_counter(counter))
+			nsec_printout(cpu, 0, counter, uval);
+		else
+			abs_printout(cpu, 0, counter, uval);
 
-	fprintf(stderr, "\n");
+		if (!csv_output) {
+			print_noise(counter, 1.0);
+
+			if (run != ena)
+				fprintf(output, "  (%.2f%%)",
+					100.0 * run / ena);
+		}
+		fputc('\n', output);
+	}
 }
 
 static void print_stat(int argc, const char **argv)
 {
-	int i, counter;
+	struct perf_evsel *counter;
+	int i;
 
 	fflush(stdout);
 
-	fprintf(stderr, "\n");
-	fprintf(stderr, " Performance counter stats for ");
-	if(target_pid == -1 && target_tid == -1) {
-		fprintf(stderr, "\'%s", argv[0]);
-		for (i = 1; i < argc; i++)
-			fprintf(stderr, " %s", argv[i]);
-	} else if (target_pid != -1)
-		fprintf(stderr, "process id \'%d", target_pid);
-	else
-		fprintf(stderr, "thread id \'%d", target_tid);
-
-	fprintf(stderr, "\'");
-	if (run_count > 1)
-		fprintf(stderr, " (%d runs)", run_count);
-	fprintf(stderr, ":\n\n");
+	if (!csv_output) {
+		fprintf(output, "\n");
+		fprintf(output, " Performance counter stats for ");
+		if (target.system_wide)
+			fprintf(output, "\'system wide");
+		else if (target.cpu_list)
+			fprintf(output, "\'CPU(s) %s", target.cpu_list);
+		else if (!target__has_task(&target)) {
+			fprintf(output, "\'%s", argv[0]);
+			for (i = 1; i < argc; i++)
+				fprintf(output, " %s", argv[i]);
+		} else if (target.pid)
+			fprintf(output, "process id \'%s", target.pid);
+		else
+			fprintf(output, "thread id \'%s", target.tid);
+
+		fprintf(output, "\'");
+		if (run_count > 1)
+			fprintf(output, " (%d runs)", run_count);
+		fprintf(output, ":\n\n");
+	}
 
-	for (counter = 0; counter < nr_counters; counter++)
-		print_counter(counter);
+	switch (aggr_mode) {
+	case AGGR_CORE:
+	case AGGR_SOCKET:
+		print_aggr(NULL);
+		break;
+	case AGGR_GLOBAL:
+		evlist__for_each(evsel_list, counter)
+			print_counter_aggr(counter, NULL);
+		break;
+	case AGGR_NONE:
+		evlist__for_each(evsel_list, counter)
+			print_counter(counter, NULL);
+		break;
+	default:
+		break;
+	}
 
-	fprintf(stderr, "\n");
-	fprintf(stderr, " %18.9f  seconds time elapsed",
-			avg_stats(&walltime_nsecs_stats)/1e9);
-	if (run_count > 1) {
-		fprintf(stderr, "   ( +- %7.3f%% )",
-				100*stddev_stats(&walltime_nsecs_stats) /
-				avg_stats(&walltime_nsecs_stats));
+	if (!csv_output) {
+		if (!null_run)
+			fprintf(output, "\n");
+		fprintf(output, " %17.9f seconds time elapsed",
+				avg_stats(&walltime_nsecs_stats)/1e9);
+		if (run_count > 1) {
+			fprintf(output, "                                        ");
+			print_noise_pct(stddev_stats(&walltime_nsecs_stats),
+					avg_stats(&walltime_nsecs_stats));
+		}
+		fprintf(output, "\n\n");
 	}
-	fprintf(stderr, "\n\n");
 }
 
 static volatile int signr = -1;
 
 static void skip_signal(int signo)
 {
-	if(child_pid == -1)
+	if ((child_pid == -1) || interval)
 		done = 1;
 
 	signr = signo;
+	/*
+	 * render child_pid harmless
+	 * won't send SIGTERM to a random
+	 * process in case of race condition
+	 * and fast PID recycling
+	 */
+	child_pid = -1;
 }
 
 static void sig_atexit(void)
 {
+	sigset_t set, oset;
+
+	/*
+	 * avoid race condition with SIGCHLD handler
+	 * in skip_signal() which is modifying child_pid
+	 * goal is to avoid send SIGTERM to a random
+	 * process
+	 */
+	sigemptyset(&set);
+	sigaddset(&set, SIGCHLD);
+	sigprocmask(SIG_BLOCK, &set, &oset);
+
 	if (child_pid != -1)
 		kill(child_pid, SIGTERM);
 
+	sigprocmask(SIG_SETMASK, &oset, NULL);
+
 	if (signr == -1)
 		return;
 
@@ -515,86 +1403,401 @@ static void sig_atexit(void)
 	kill(getpid(), signr);
 }
 
-static const char * const stat_usage[] = {
-	"perf stat [<options>] [<command>]",
-	NULL
+static int stat__set_big_num(const struct option *opt __maybe_unused,
+			     const char *s __maybe_unused, int unset)
+{
+	big_num_opt = unset ? 0 : 1;
+	return 0;
+}
+
+static int perf_stat_init_aggr_mode(void)
+{
+	switch (aggr_mode) {
+	case AGGR_SOCKET:
+		if (cpu_map__build_socket_map(evsel_list->cpus, &aggr_map)) {
+			perror("cannot build socket map");
+			return -1;
+		}
+		aggr_get_id = cpu_map__get_socket;
+		break;
+	case AGGR_CORE:
+		if (cpu_map__build_core_map(evsel_list->cpus, &aggr_map)) {
+			perror("cannot build core map");
+			return -1;
+		}
+		aggr_get_id = cpu_map__get_core;
+		break;
+	case AGGR_NONE:
+	case AGGR_GLOBAL:
+	default:
+		break;
+	}
+	return 0;
+}
+
+static int setup_events(const char * const *attrs, unsigned len)
+{
+	unsigned i;
+
+	for (i = 0; i < len; i++) {
+		if (parse_events(evsel_list, attrs[i]))
+			return -1;
+	}
+	return 0;
+}
+
+/*
+ * Add default attributes, if there were no attributes specified or
+ * if -d/--detailed, -d -d or -d -d -d is used:
+ */
+static int add_default_attributes(void)
+{
+	struct perf_event_attr default_attrs[] = {
+
+  { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_TASK_CLOCK		},
+  { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CONTEXT_SWITCHES	},
+  { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CPU_MIGRATIONS		},
+  { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_PAGE_FAULTS		},
+
+  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES		},
+  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_STALLED_CYCLES_FRONTEND	},
+  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_STALLED_CYCLES_BACKEND	},
+  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_INSTRUCTIONS		},
+  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_INSTRUCTIONS	},
+  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_MISSES		},
+
+};
+
+/*
+ * Detailed stats (-d), covering the L1 and last level data caches:
+ */
+	struct perf_event_attr detailed_attrs[] = {
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+	 PERF_COUNT_HW_CACHE_L1D		<<  0  |
+	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
+	(PERF_COUNT_HW_CACHE_RESULT_ACCESS	<< 16)				},
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+	 PERF_COUNT_HW_CACHE_L1D		<<  0  |
+	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
+	(PERF_COUNT_HW_CACHE_RESULT_MISS	<< 16)				},
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+	 PERF_COUNT_HW_CACHE_LL			<<  0  |
+	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
+	(PERF_COUNT_HW_CACHE_RESULT_ACCESS	<< 16)				},
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+	 PERF_COUNT_HW_CACHE_LL			<<  0  |
+	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
+	(PERF_COUNT_HW_CACHE_RESULT_MISS	<< 16)				},
 };
 
-static const struct option options[] = {
-	OPT_CALLBACK('e', "event", NULL, "event",
+/*
+ * Very detailed stats (-d -d), covering the instruction cache and the TLB caches:
+ */
+	struct perf_event_attr very_detailed_attrs[] = {
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+	 PERF_COUNT_HW_CACHE_L1I		<<  0  |
+	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
+	(PERF_COUNT_HW_CACHE_RESULT_ACCESS	<< 16)				},
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+	 PERF_COUNT_HW_CACHE_L1I		<<  0  |
+	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
+	(PERF_COUNT_HW_CACHE_RESULT_MISS	<< 16)				},
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+	 PERF_COUNT_HW_CACHE_DTLB		<<  0  |
+	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
+	(PERF_COUNT_HW_CACHE_RESULT_ACCESS	<< 16)				},
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+	 PERF_COUNT_HW_CACHE_DTLB		<<  0  |
+	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
+	(PERF_COUNT_HW_CACHE_RESULT_MISS	<< 16)				},
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+	 PERF_COUNT_HW_CACHE_ITLB		<<  0  |
+	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
+	(PERF_COUNT_HW_CACHE_RESULT_ACCESS	<< 16)				},
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+	 PERF_COUNT_HW_CACHE_ITLB		<<  0  |
+	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
+	(PERF_COUNT_HW_CACHE_RESULT_MISS	<< 16)				},
+
+};
+
+/*
+ * Very, very detailed stats (-d -d -d), adding prefetch events:
+ */
+	struct perf_event_attr very_very_detailed_attrs[] = {
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+	 PERF_COUNT_HW_CACHE_L1D		<<  0  |
+	(PERF_COUNT_HW_CACHE_OP_PREFETCH	<<  8) |
+	(PERF_COUNT_HW_CACHE_RESULT_ACCESS	<< 16)				},
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+	 PERF_COUNT_HW_CACHE_L1D		<<  0  |
+	(PERF_COUNT_HW_CACHE_OP_PREFETCH	<<  8) |
+	(PERF_COUNT_HW_CACHE_RESULT_MISS	<< 16)				},
+};
+
+	/* Set attrs if no event is selected and !null_run: */
+	if (null_run)
+		return 0;
+
+	if (transaction_run) {
+		int err;
+		if (pmu_have_event("cpu", "cycles-ct") &&
+		    pmu_have_event("cpu", "el-start"))
+			err = setup_events(transaction_attrs,
+					ARRAY_SIZE(transaction_attrs));
+		else
+			err = setup_events(transaction_limited_attrs,
+				 ARRAY_SIZE(transaction_limited_attrs));
+		if (err < 0) {
+			fprintf(stderr, "Cannot set up transaction events\n");
+			return -1;
+		}
+		return 0;
+	}
+
+	if (!evsel_list->nr_entries) {
+		if (perf_evlist__add_default_attrs(evsel_list, default_attrs) < 0)
+			return -1;
+	}
+
+	/* Detailed events get appended to the event list: */
+
+	if (detailed_run <  1)
+		return 0;
+
+	/* Append detailed run extra attributes: */
+	if (perf_evlist__add_default_attrs(evsel_list, detailed_attrs) < 0)
+		return -1;
+
+	if (detailed_run < 2)
+		return 0;
+
+	/* Append very detailed run extra attributes: */
+	if (perf_evlist__add_default_attrs(evsel_list, very_detailed_attrs) < 0)
+		return -1;
+
+	if (detailed_run < 3)
+		return 0;
+
+	/* Append very, very detailed run extra attributes: */
+	return perf_evlist__add_default_attrs(evsel_list, very_very_detailed_attrs);
+}
+
+int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
+{
+	bool append_file = false;
+	int output_fd = 0;
+	const char *output_name	= NULL;
+	const struct option options[] = {
+	OPT_BOOLEAN('T', "transaction", &transaction_run,
+		    "hardware transaction statistics"),
+	OPT_CALLBACK('e', "event", &evsel_list, "event",
 		     "event selector. use 'perf list' to list available events",
-		     parse_events),
+		     parse_events_option),
+	OPT_CALLBACK(0, "filter", &evsel_list, "filter",
+		     "event filter", parse_filter),
 	OPT_BOOLEAN('i', "no-inherit", &no_inherit,
 		    "child tasks do not inherit counters"),
-	OPT_INTEGER('p', "pid", &target_pid,
-		    "stat events on existing process id"),
-	OPT_INTEGER('t', "tid", &target_tid,
-		    "stat events on existing thread id"),
-	OPT_BOOLEAN('a', "all-cpus", &system_wide,
+	OPT_STRING('p', "pid", &target.pid, "pid",
+		   "stat events on existing process id"),
+	OPT_STRING('t', "tid", &target.tid, "tid",
+		   "stat events on existing thread id"),
+	OPT_BOOLEAN('a', "all-cpus", &target.system_wide,
 		    "system-wide collection from all CPUs"),
-	OPT_BOOLEAN('c', "scale", &scale,
-		    "scale/normalize counters"),
+	OPT_BOOLEAN('g', "group", &group,
+		    "put the counters into a counter group"),
+	OPT_BOOLEAN('c', "scale", &scale, "scale/normalize counters"),
 	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose (show counter open errors, etc)"),
 	OPT_INTEGER('r', "repeat", &run_count,
-		    "repeat command and print average + stddev (max: 100)"),
+		    "repeat command and print average + stddev (max: 100, forever: 0)"),
 	OPT_BOOLEAN('n', "null", &null_run,
 		    "null run - dont start any counters"),
-	OPT_BOOLEAN('B', "big-num", &big_num,
-		    "print large numbers with thousands\' separators"),
+	OPT_INCR('d', "detailed", &detailed_run,
+		    "detailed run - start a lot of events"),
+	OPT_BOOLEAN('S', "sync", &sync_run,
+		    "call sync() before starting a run"),
+	OPT_CALLBACK_NOOPT('B', "big-num", NULL, NULL, 
+			   "print large numbers with thousands\' separators",
+			   stat__set_big_num),
+	OPT_STRING('C', "cpu", &target.cpu_list, "cpu",
+		    "list of cpus to monitor in system-wide"),
+	OPT_SET_UINT('A', "no-aggr", &aggr_mode,
+		    "disable CPU count aggregation", AGGR_NONE),
+	OPT_STRING('x', "field-separator", &csv_sep, "separator",
+		   "print counts with custom separator"),
+	OPT_CALLBACK('G', "cgroup", &evsel_list, "name",
+		     "monitor event in cgroup name only", parse_cgroups),
+	OPT_STRING('o', "output", &output_name, "file", "output file name"),
+	OPT_BOOLEAN(0, "append", &append_file, "append to the output file"),
+	OPT_INTEGER(0, "log-fd", &output_fd,
+		    "log output to fd, instead of stderr"),
+	OPT_STRING(0, "pre", &pre_cmd, "command",
+			"command to run prior to the measured command"),
+	OPT_STRING(0, "post", &post_cmd, "command",
+			"command to run after to the measured command"),
+	OPT_UINTEGER('I', "interval-print", &interval,
+		    "print counts at regular interval in ms (>= 100)"),
+	OPT_SET_UINT(0, "per-socket", &aggr_mode,
+		     "aggregate counts per processor socket", AGGR_SOCKET),
+	OPT_SET_UINT(0, "per-core", &aggr_mode,
+		     "aggregate counts per physical processor core", AGGR_CORE),
+	OPT_UINTEGER('D', "delay", &initial_delay,
+		     "ms to wait before starting measurement after program start"),
 	OPT_END()
-};
-
-int cmd_stat(int argc, const char **argv, const char *prefix __used)
-{
-	int status;
-	int i,j;
+	};
+	const char * const stat_usage[] = {
+		"perf stat [<options>] [<command>]",
+		NULL
+	};
+	int status = -EINVAL, run_idx;
+	const char *mode;
 
 	setlocale(LC_ALL, "");
 
+	evsel_list = perf_evlist__new();
+	if (evsel_list == NULL)
+		return -ENOMEM;
+
 	argc = parse_options(argc, argv, options, stat_usage,
 		PARSE_OPT_STOP_AT_NON_OPTION);
-	if (!argc && target_pid == -1 && target_tid == -1)
-		usage_with_options(stat_usage, options);
-	if (run_count <= 0)
-		usage_with_options(stat_usage, options);
 
-	/* Set attrs and nr_counters if no event is selected and !null_run */
-	if (!null_run && !nr_counters) {
-		memcpy(attrs, default_attrs, sizeof(default_attrs));
-		nr_counters = ARRAY_SIZE(default_attrs);
+	output = stderr;
+	if (output_name && strcmp(output_name, "-"))
+		output = NULL;
+
+	if (output_name && output_fd) {
+		fprintf(stderr, "cannot use both --output and --log-fd\n");
+		parse_options_usage(stat_usage, options, "o", 1);
+		parse_options_usage(NULL, options, "log-fd", 0);
+		goto out;
 	}
 
-	if (system_wide)
-		nr_cpus = read_cpu_map();
-	else
-		nr_cpus = 1;
-
-	if (target_pid != -1) {
-		target_tid = target_pid;
-		thread_num = find_all_tid(target_pid, &all_tids);
-		if (thread_num <= 0) {
-			fprintf(stderr, "Can't find all threads of pid %d\n",
-					target_pid);
-			usage_with_options(stat_usage, options);
+	if (output_fd < 0) {
+		fprintf(stderr, "argument to --log-fd must be a > 0\n");
+		parse_options_usage(stat_usage, options, "log-fd", 0);
+		goto out;
+	}
+
+	if (!output) {
+		struct timespec tm;
+		mode = append_file ? "a" : "w";
+
+		output = fopen(output_name, mode);
+		if (!output) {
+			perror("failed to create output file");
+			return -1;
 		}
-	} else {
-		all_tids=malloc(sizeof(pid_t));
-		if (!all_tids)
-			return -ENOMEM;
+		clock_gettime(CLOCK_REALTIME, &tm);
+		fprintf(output, "# started on %s\n", ctime(&tm.tv_sec));
+	} else if (output_fd > 0) {
+		mode = append_file ? "a" : "w";
+		output = fdopen(output_fd, mode);
+		if (!output) {
+			perror("Failed opening logfd");
+			return -errno;
+		}
+	}
 
-		all_tids[0] = target_tid;
-		thread_num = 1;
+	if (csv_sep) {
+		csv_output = true;
+		if (!strcmp(csv_sep, "\\t"))
+			csv_sep = "\t";
+	} else
+		csv_sep = DEFAULT_SEPARATOR;
+
+	/*
+	 * let the spreadsheet do the pretty-printing
+	 */
+	if (csv_output) {
+		/* User explicitly passed -B? */
+		if (big_num_opt == 1) {
+			fprintf(stderr, "-B option not supported with -x\n");
+			parse_options_usage(stat_usage, options, "B", 1);
+			parse_options_usage(NULL, options, "x", 1);
+			goto out;
+		} else /* Nope, so disable big number formatting */
+			big_num = false;
+	} else if (big_num_opt == 0) /* User passed --no-big-num */
+		big_num = false;
+
+	if (!argc && target__none(&target))
+		usage_with_options(stat_usage, options);
+
+	if (run_count < 0) {
+		pr_err("Run count must be a positive number\n");
+		parse_options_usage(stat_usage, options, "r", 1);
+		goto out;
+	} else if (run_count == 0) {
+		forever = true;
+		run_count = 1;
+	}
+
+	/* no_aggr, cgroup are for system-wide only */
+	if ((aggr_mode != AGGR_GLOBAL || nr_cgroups) &&
+	    !target__has_cpu(&target)) {
+		fprintf(stderr, "both cgroup and no-aggregation "
+			"modes only available in system-wide mode\n");
+
+		parse_options_usage(stat_usage, options, "G", 1);
+		parse_options_usage(NULL, options, "A", 1);
+		parse_options_usage(NULL, options, "a", 1);
+		goto out;
 	}
 
-	for (i = 0; i < MAX_NR_CPUS; i++) {
-		for (j = 0; j < MAX_COUNTERS; j++) {
-			fd[i][j] = malloc(sizeof(int)*thread_num);
-			if (!fd[i][j])
-				return -ENOMEM;
+	if (add_default_attributes())
+		goto out;
+
+	target__validate(&target);
+
+	if (perf_evlist__create_maps(evsel_list, &target) < 0) {
+		if (target__has_task(&target)) {
+			pr_err("Problems finding threads of monitor\n");
+			parse_options_usage(stat_usage, options, "p", 1);
+			parse_options_usage(NULL, options, "t", 1);
+		} else if (target__has_cpu(&target)) {
+			perror("failed to parse CPUs map");
+			parse_options_usage(stat_usage, options, "C", 1);
+			parse_options_usage(NULL, options, "a", 1);
 		}
+		goto out;
+	}
+	if (interval && interval < 100) {
+		pr_err("print interval must be >= 100ms\n");
+		parse_options_usage(stat_usage, options, "I", 1);
+		goto out;
 	}
 
+	if (perf_evlist__alloc_stats(evsel_list, interval))
+		goto out;
+
+	if (perf_stat_init_aggr_mode())
+		goto out;
+
 	/*
 	 * We dont want to block the signals - that would cause
 	 * child tasks to inherit that and Ctrl-C would not work.
@@ -602,19 +1805,30 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used)
 	 * task, but being ignored by perf stat itself:
 	 */
 	atexit(sig_atexit);
-	signal(SIGINT,  skip_signal);
+	if (!forever)
+		signal(SIGINT,  skip_signal);
+	signal(SIGCHLD, skip_signal);
 	signal(SIGALRM, skip_signal);
 	signal(SIGABRT, skip_signal);
 
 	status = 0;
-	for (run_idx = 0; run_idx < run_count; run_idx++) {
+	for (run_idx = 0; forever || run_idx < run_count; run_idx++) {
 		if (run_count != 1 && verbose)
-			fprintf(stderr, "[ perf stat: executing run #%d ... ]\n", run_idx + 1);
+			fprintf(output, "[ perf stat: executing run #%d ... ]\n",
+				run_idx + 1);
+
 		status = run_perf_stat(argc, argv);
+		if (forever && status != -1) {
+			print_stat(argc, argv);
+			perf_stat__reset_stats(evsel_list);
+		}
 	}
 
-	if (status != -1)
+	if (!forever && status != -1 && !interval)
 		print_stat(argc, argv);
 
+	perf_evlist__free_stats(evsel_list);
+out:
+	perf_evlist__delete(evsel_list);
 	return status;
 }
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 5a52ed9fc10..74db2568b86 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -12,6 +12,8 @@
  * of the License.
  */
 
+#include <traceevent/event-parse.h>
+
 #include "builtin.h"
 
 #include "util/util.h"
@@ -19,6 +21,8 @@
 #include "util/color.h"
 #include <linux/list.h>
 #include "util/cache.h"
+#include "util/evlist.h"
+#include "util/evsel.h"
 #include <linux/rbtree.h>
 #include "util/symbol.h"
 #include "util/callchain.h"
@@ -31,28 +35,35 @@
 #include "util/event.h"
 #include "util/session.h"
 #include "util/svghelper.h"
+#include "util/tool.h"
+#include "util/data.h"
 
-static char		const *input_name = "perf.data";
-static char		const *output_name = "output.svg";
-
-static unsigned int	numcpus;
-static u64		min_freq;	/* Lowest CPU frequency seen */
-static u64		max_freq;	/* Highest CPU frequency seen */
-static u64		turbo_frequency;
-
-static u64		first_time, last_time;
-
-static bool		power_only;
-
+#define SUPPORT_OLD_POWER_EVENTS 1
+#define PWR_EVENT_EXIT -1
 
 struct per_pid;
-struct per_pidcomm;
-
-struct cpu_sample;
 struct power_event;
 struct wake_event;
 
-struct sample_wrapper;
+struct timechart {
+	struct perf_tool	tool;
+	struct per_pid		*all_data;
+	struct power_event	*power_events;
+	struct wake_event	*wake_events;
+	int			proc_num;
+	unsigned int		numcpus;
+	u64			min_freq,	/* Lowest CPU frequency seen */
+				max_freq,	/* Highest CPU frequency seen */
+				turbo_frequency,
+				first_time, last_time;
+	bool			power_only,
+				tasks_only,
+				with_backtrace,
+				topology;
+};
+
+struct per_pidcomm;
+struct cpu_sample;
 
 /*
  * Datastructure layout:
@@ -117,10 +128,9 @@ struct cpu_sample {
 	u64 end_time;
 	int type;
 	int cpu;
+	const char *backtrace;
 };
 
-static struct per_pid *all_data;
-
 #define CSTATE 1
 #define PSTATE 2
 
@@ -138,12 +148,9 @@ struct wake_event {
 	int waker;
 	int wakee;
 	u64 time;
+	const char *backtrace;
 };
 
-static struct power_event    *power_events;
-static struct wake_event     *wake_events;
-
-struct process_filter;
 struct process_filter {
 	char			*name;
 	int			pid;
@@ -153,29 +160,28 @@ struct process_filter {
 static struct process_filter *process_filter;
 
 
-static struct per_pid *find_create_pid(int pid)
+static struct per_pid *find_create_pid(struct timechart *tchart, int pid)
 {
-	struct per_pid *cursor = all_data;
+	struct per_pid *cursor = tchart->all_data;
 
 	while (cursor) {
 		if (cursor->pid == pid)
 			return cursor;
 		cursor = cursor->next;
 	}
-	cursor = malloc(sizeof(struct per_pid));
+	cursor = zalloc(sizeof(*cursor));
 	assert(cursor != NULL);
-	memset(cursor, 0, sizeof(struct per_pid));
 	cursor->pid = pid;
-	cursor->next = all_data;
-	all_data = cursor;
+	cursor->next = tchart->all_data;
+	tchart->all_data = cursor;
 	return cursor;
 }
 
-static void pid_set_comm(int pid, char *comm)
+static void pid_set_comm(struct timechart *tchart, int pid, char *comm)
 {
 	struct per_pid *p;
 	struct per_pidcomm *c;
-	p = find_create_pid(pid);
+	p = find_create_pid(tchart, pid);
 	c = p->all;
 	while (c) {
 		if (c->comm && strcmp(c->comm, comm) == 0) {
@@ -189,23 +195,22 @@ static void pid_set_comm(int pid, char *comm)
 		}
 		c = c->next;
 	}
-	c = malloc(sizeof(struct per_pidcomm));
+	c = zalloc(sizeof(*c));
 	assert(c != NULL);
-	memset(c, 0, sizeof(struct per_pidcomm));
 	c->comm = strdup(comm);
 	p->current = c;
 	c->next = p->all;
 	p->all = c;
 }
 
-static void pid_fork(int pid, int ppid, u64 timestamp)
+static void pid_fork(struct timechart *tchart, int pid, int ppid, u64 timestamp)
 {
 	struct per_pid *p, *pp;
-	p = find_create_pid(pid);
-	pp = find_create_pid(ppid);
+	p = find_create_pid(tchart, pid);
+	pp = find_create_pid(tchart, ppid);
 	p->ppid = ppid;
 	if (pp->current && pp->current->comm && !p->current)
-		pid_set_comm(pid, pp->current->comm);
+		pid_set_comm(tchart, pid, pp->current->comm);
 
 	p->start_time = timestamp;
 	if (p->current) {
@@ -214,41 +219,41 @@ static void pid_fork(int pid, int ppid, u64 timestamp)
 	}
 }
 
-static void pid_exit(int pid, u64 timestamp)
+static void pid_exit(struct timechart *tchart, int pid, u64 timestamp)
 {
 	struct per_pid *p;
-	p = find_create_pid(pid);
+	p = find_create_pid(tchart, pid);
 	p->end_time = timestamp;
 	if (p->current)
 		p->current->end_time = timestamp;
 }
 
-static void
-pid_put_sample(int pid, int type, unsigned int cpu, u64 start, u64 end)
+static void pid_put_sample(struct timechart *tchart, int pid, int type,
+			   unsigned int cpu, u64 start, u64 end,
+			   const char *backtrace)
 {
 	struct per_pid *p;
 	struct per_pidcomm *c;
 	struct cpu_sample *sample;
 
-	p = find_create_pid(pid);
+	p = find_create_pid(tchart, pid);
 	c = p->current;
 	if (!c) {
-		c = malloc(sizeof(struct per_pidcomm));
+		c = zalloc(sizeof(*c));
 		assert(c != NULL);
-		memset(c, 0, sizeof(struct per_pidcomm));
 		p->current = c;
 		c->next = p->all;
 		p->all = c;
 	}
 
-	sample = malloc(sizeof(struct cpu_sample));
+	sample = zalloc(sizeof(*sample));
 	assert(sample != NULL);
-	memset(sample, 0, sizeof(struct cpu_sample));
 	sample->start_time = start;
 	sample->end_time = end;
 	sample->type = type;
 	sample->next = c->samples;
 	sample->cpu = cpu;
+	sample->backtrace = backtrace;
 	c->samples = sample;
 
 	if (sample->type == TYPE_RUNNING && end > start && start > 0) {
@@ -260,9 +265,6 @@ pid_put_sample(int pid, int type, unsigned int cpu, u64 start, u64 end)
 		c->start_time = start;
 	if (p->start_time == 0 || p->start_time > start)
 		p->start_time = start;
-
-	if (cpu > numcpus)
-		numcpus = cpu;
 }
 
 #define MAX_CPUS 4096
@@ -272,76 +274,39 @@ static int cpus_cstate_state[MAX_CPUS];
 static u64 cpus_pstate_start_times[MAX_CPUS];
 static u64 cpus_pstate_state[MAX_CPUS];
 
-static int process_comm_event(event_t *event, struct perf_session *session __used)
+static int process_comm_event(struct perf_tool *tool,
+			      union perf_event *event,
+			      struct perf_sample *sample __maybe_unused,
+			      struct machine *machine __maybe_unused)
 {
-	pid_set_comm(event->comm.tid, event->comm.comm);
+	struct timechart *tchart = container_of(tool, struct timechart, tool);
+	pid_set_comm(tchart, event->comm.tid, event->comm.comm);
 	return 0;
 }
 
-static int process_fork_event(event_t *event, struct perf_session *session __used)
+static int process_fork_event(struct perf_tool *tool,
+			      union perf_event *event,
+			      struct perf_sample *sample __maybe_unused,
+			      struct machine *machine __maybe_unused)
 {
-	pid_fork(event->fork.pid, event->fork.ppid, event->fork.time);
+	struct timechart *tchart = container_of(tool, struct timechart, tool);
+	pid_fork(tchart, event->fork.pid, event->fork.ppid, event->fork.time);
 	return 0;
 }
 
-static int process_exit_event(event_t *event, struct perf_session *session __used)
+static int process_exit_event(struct perf_tool *tool,
+			      union perf_event *event,
+			      struct perf_sample *sample __maybe_unused,
+			      struct machine *machine __maybe_unused)
 {
-	pid_exit(event->fork.pid, event->fork.time);
+	struct timechart *tchart = container_of(tool, struct timechart, tool);
+	pid_exit(tchart, event->fork.pid, event->fork.time);
 	return 0;
 }
 
-struct trace_entry {
-	unsigned short		type;
-	unsigned char		flags;
-	unsigned char		preempt_count;
-	int			pid;
-	int			lock_depth;
-};
-
-struct power_entry {
-	struct trace_entry te;
-	s64	type;
-	s64	value;
-};
-
-#define TASK_COMM_LEN 16
-struct wakeup_entry {
-	struct trace_entry te;
-	char comm[TASK_COMM_LEN];
-	int   pid;
-	int   prio;
-	int   success;
-};
-
-/*
- * trace_flag_type is an enumeration that holds different
- * states when a trace occurs. These are:
- *  IRQS_OFF            - interrupts were disabled
- *  IRQS_NOSUPPORT      - arch does not support irqs_disabled_flags
- *  NEED_RESCED         - reschedule is requested
- *  HARDIRQ             - inside an interrupt handler
- *  SOFTIRQ             - inside a softirq handler
- */
-enum trace_flag_type {
-	TRACE_FLAG_IRQS_OFF		= 0x01,
-	TRACE_FLAG_IRQS_NOSUPPORT	= 0x02,
-	TRACE_FLAG_NEED_RESCHED		= 0x04,
-	TRACE_FLAG_HARDIRQ		= 0x08,
-	TRACE_FLAG_SOFTIRQ		= 0x10,
-};
-
-
-
-struct sched_switch {
-	struct trace_entry te;
-	char prev_comm[TASK_COMM_LEN];
-	int  prev_pid;
-	int  prev_prio;
-	long prev_state; /* Arjan weeps. */
-	char next_comm[TASK_COMM_LEN];
-	int  next_pid;
-	int  next_prio;
-};
+#ifdef SUPPORT_OLD_POWER_EVENTS
+static int use_old_power_events;
+#endif
 
 static void c_state_start(int cpu, u64 timestamp, int state)
 {
@@ -349,233 +314,387 @@ static void c_state_start(int cpu, u64 timestamp, int state)
 	cpus_cstate_state[cpu] = state;
 }
 
-static void c_state_end(int cpu, u64 timestamp)
+static void c_state_end(struct timechart *tchart, int cpu, u64 timestamp)
 {
-	struct power_event *pwr;
-	pwr = malloc(sizeof(struct power_event));
+	struct power_event *pwr = zalloc(sizeof(*pwr));
+
 	if (!pwr)
 		return;
-	memset(pwr, 0, sizeof(struct power_event));
 
 	pwr->state = cpus_cstate_state[cpu];
 	pwr->start_time = cpus_cstate_start_times[cpu];
 	pwr->end_time = timestamp;
 	pwr->cpu = cpu;
 	pwr->type = CSTATE;
-	pwr->next = power_events;
+	pwr->next = tchart->power_events;
 
-	power_events = pwr;
+	tchart->power_events = pwr;
 }
 
-static void p_state_change(int cpu, u64 timestamp, u64 new_freq)
+static void p_state_change(struct timechart *tchart, int cpu, u64 timestamp, u64 new_freq)
 {
 	struct power_event *pwr;
-	pwr = malloc(sizeof(struct power_event));
 
 	if (new_freq > 8000000) /* detect invalid data */
 		return;
 
+	pwr = zalloc(sizeof(*pwr));
 	if (!pwr)
 		return;
-	memset(pwr, 0, sizeof(struct power_event));
 
 	pwr->state = cpus_pstate_state[cpu];
 	pwr->start_time = cpus_pstate_start_times[cpu];
 	pwr->end_time = timestamp;
 	pwr->cpu = cpu;
 	pwr->type = PSTATE;
-	pwr->next = power_events;
+	pwr->next = tchart->power_events;
 
 	if (!pwr->start_time)
-		pwr->start_time = first_time;
+		pwr->start_time = tchart->first_time;
 
-	power_events = pwr;
+	tchart->power_events = pwr;
 
 	cpus_pstate_state[cpu] = new_freq;
 	cpus_pstate_start_times[cpu] = timestamp;
 
-	if ((u64)new_freq > max_freq)
-		max_freq = new_freq;
+	if ((u64)new_freq > tchart->max_freq)
+		tchart->max_freq = new_freq;
 
-	if (new_freq < min_freq || min_freq == 0)
-		min_freq = new_freq;
+	if (new_freq < tchart->min_freq || tchart->min_freq == 0)
+		tchart->min_freq = new_freq;
 
-	if (new_freq == max_freq - 1000)
-			turbo_frequency = max_freq;
+	if (new_freq == tchart->max_freq - 1000)
+		tchart->turbo_frequency = tchart->max_freq;
 }
 
-static void
-sched_wakeup(int cpu, u64 timestamp, int pid, struct trace_entry *te)
+static void sched_wakeup(struct timechart *tchart, int cpu, u64 timestamp,
+			 int waker, int wakee, u8 flags, const char *backtrace)
 {
-	struct wake_event *we;
 	struct per_pid *p;
-	struct wakeup_entry *wake = (void *)te;
+	struct wake_event *we = zalloc(sizeof(*we));
 
-	we = malloc(sizeof(struct wake_event));
 	if (!we)
 		return;
 
-	memset(we, 0, sizeof(struct wake_event));
 	we->time = timestamp;
-	we->waker = pid;
+	we->waker = waker;
+	we->backtrace = backtrace;
 
-	if ((te->flags & TRACE_FLAG_HARDIRQ) || (te->flags & TRACE_FLAG_SOFTIRQ))
+	if ((flags & TRACE_FLAG_HARDIRQ) || (flags & TRACE_FLAG_SOFTIRQ))
 		we->waker = -1;
 
-	we->wakee = wake->pid;
-	we->next = wake_events;
-	wake_events = we;
-	p = find_create_pid(we->wakee);
+	we->wakee = wakee;
+	we->next = tchart->wake_events;
+	tchart->wake_events = we;
+	p = find_create_pid(tchart, we->wakee);
 
 	if (p && p->current && p->current->state == TYPE_NONE) {
 		p->current->state_since = timestamp;
 		p->current->state = TYPE_WAITING;
 	}
 	if (p && p->current && p->current->state == TYPE_BLOCKED) {
-		pid_put_sample(p->pid, p->current->state, cpu, p->current->state_since, timestamp);
+		pid_put_sample(tchart, p->pid, p->current->state, cpu,
+			       p->current->state_since, timestamp, NULL);
 		p->current->state_since = timestamp;
 		p->current->state = TYPE_WAITING;
 	}
 }
 
-static void sched_switch(int cpu, u64 timestamp, struct trace_entry *te)
+static void sched_switch(struct timechart *tchart, int cpu, u64 timestamp,
+			 int prev_pid, int next_pid, u64 prev_state,
+			 const char *backtrace)
 {
 	struct per_pid *p = NULL, *prev_p;
-	struct sched_switch *sw = (void *)te;
 
+	prev_p = find_create_pid(tchart, prev_pid);
 
-	prev_p = find_create_pid(sw->prev_pid);
-
-	p = find_create_pid(sw->next_pid);
+	p = find_create_pid(tchart, next_pid);
 
 	if (prev_p->current && prev_p->current->state != TYPE_NONE)
-		pid_put_sample(sw->prev_pid, TYPE_RUNNING, cpu, prev_p->current->state_since, timestamp);
+		pid_put_sample(tchart, prev_pid, TYPE_RUNNING, cpu,
+			       prev_p->current->state_since, timestamp,
+			       backtrace);
 	if (p && p->current) {
 		if (p->current->state != TYPE_NONE)
-			pid_put_sample(sw->next_pid, p->current->state, cpu, p->current->state_since, timestamp);
+			pid_put_sample(tchart, next_pid, p->current->state, cpu,
+				       p->current->state_since, timestamp,
+				       backtrace);
 
-			p->current->state_since = timestamp;
-			p->current->state = TYPE_RUNNING;
+		p->current->state_since = timestamp;
+		p->current->state = TYPE_RUNNING;
 	}
 
 	if (prev_p->current) {
 		prev_p->current->state = TYPE_NONE;
 		prev_p->current->state_since = timestamp;
-		if (sw->prev_state & 2)
+		if (prev_state & 2)
 			prev_p->current->state = TYPE_BLOCKED;
-		if (sw->prev_state == 0)
+		if (prev_state == 0)
 			prev_p->current->state = TYPE_WAITING;
 	}
 }
 
-
-static int process_sample_event(event_t *event, struct perf_session *session)
+static const char *cat_backtrace(union perf_event *event,
+				 struct perf_sample *sample,
+				 struct machine *machine)
 {
-	struct sample_data data;
-	struct trace_entry *te;
-
-	memset(&data, 0, sizeof(data));
+	struct addr_location al;
+	unsigned int i;
+	char *p = NULL;
+	size_t p_len;
+	u8 cpumode = PERF_RECORD_MISC_USER;
+	struct addr_location tal;
+	struct ip_callchain *chain = sample->callchain;
+	FILE *f = open_memstream(&p, &p_len);
+
+	if (!f) {
+		perror("open_memstream error");
+		return NULL;
+	}
 
-	event__parse_sample(event, session->sample_type, &data);
+	if (!chain)
+		goto exit;
 
-	if (session->sample_type & PERF_SAMPLE_TIME) {
-		if (!first_time || first_time > data.time)
-			first_time = data.time;
-		if (last_time < data.time)
-			last_time = data.time;
+	if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
+		fprintf(stderr, "problem processing %d event, skipping it.\n",
+			event->header.type);
+		goto exit;
 	}
 
-	te = (void *)data.raw_data;
-	if (session->sample_type & PERF_SAMPLE_RAW && data.raw_size > 0) {
-		char *event_str;
-		struct power_entry *pe;
+	for (i = 0; i < chain->nr; i++) {
+		u64 ip;
 
-		pe = (void *)te;
+		if (callchain_param.order == ORDER_CALLEE)
+			ip = chain->ips[i];
+		else
+			ip = chain->ips[chain->nr - i - 1];
+
+		if (ip >= PERF_CONTEXT_MAX) {
+			switch (ip) {
+			case PERF_CONTEXT_HV:
+				cpumode = PERF_RECORD_MISC_HYPERVISOR;
+				break;
+			case PERF_CONTEXT_KERNEL:
+				cpumode = PERF_RECORD_MISC_KERNEL;
+				break;
+			case PERF_CONTEXT_USER:
+				cpumode = PERF_RECORD_MISC_USER;
+				break;
+			default:
+				pr_debug("invalid callchain context: "
+					 "%"PRId64"\n", (s64) ip);
+
+				/*
+				 * It seems the callchain is corrupted.
+				 * Discard all.
+				 */
+				zfree(&p);
+				goto exit;
+			}
+			continue;
+		}
 
-		event_str = perf_header__find_event(te->type);
+		tal.filtered = 0;
+		thread__find_addr_location(al.thread, machine, cpumode,
+					   MAP__FUNCTION, ip, &tal);
 
-		if (!event_str)
-			return 0;
+		if (tal.sym)
+			fprintf(f, "..... %016" PRIx64 " %s\n", ip,
+				tal.sym->name);
+		else
+			fprintf(f, "..... %016" PRIx64 "\n", ip);
+	}
 
-		if (strcmp(event_str, "power:power_start") == 0)
-			c_state_start(data.cpu, data.time, pe->value);
+exit:
+	fclose(f);
+
+	return p;
+}
 
-		if (strcmp(event_str, "power:power_end") == 0)
-			c_state_end(data.cpu, data.time);
+typedef int (*tracepoint_handler)(struct timechart *tchart,
+				  struct perf_evsel *evsel,
+				  struct perf_sample *sample,
+				  const char *backtrace);
 
-		if (strcmp(event_str, "power:power_frequency") == 0)
-			p_state_change(data.cpu, data.time, pe->value);
+static int process_sample_event(struct perf_tool *tool,
+				union perf_event *event,
+				struct perf_sample *sample,
+				struct perf_evsel *evsel,
+				struct machine *machine)
+{
+	struct timechart *tchart = container_of(tool, struct timechart, tool);
 
-		if (strcmp(event_str, "sched:sched_wakeup") == 0)
-			sched_wakeup(data.cpu, data.time, data.pid, te);
+	if (evsel->attr.sample_type & PERF_SAMPLE_TIME) {
+		if (!tchart->first_time || tchart->first_time > sample->time)
+			tchart->first_time = sample->time;
+		if (tchart->last_time < sample->time)
+			tchart->last_time = sample->time;
+	}
 
-		if (strcmp(event_str, "sched:sched_switch") == 0)
-			sched_switch(data.cpu, data.time, te);
+	if (evsel->handler != NULL) {
+		tracepoint_handler f = evsel->handler;
+		return f(tchart, evsel, sample,
+			 cat_backtrace(event, sample, machine));
 	}
+
+	return 0;
+}
+
+static int
+process_sample_cpu_idle(struct timechart *tchart __maybe_unused,
+			struct perf_evsel *evsel,
+			struct perf_sample *sample,
+			const char *backtrace __maybe_unused)
+{
+	u32 state = perf_evsel__intval(evsel, sample, "state");
+	u32 cpu_id = perf_evsel__intval(evsel, sample, "cpu_id");
+
+	if (state == (u32)PWR_EVENT_EXIT)
+		c_state_end(tchart, cpu_id, sample->time);
+	else
+		c_state_start(cpu_id, sample->time, state);
+	return 0;
+}
+
+static int
+process_sample_cpu_frequency(struct timechart *tchart,
+			     struct perf_evsel *evsel,
+			     struct perf_sample *sample,
+			     const char *backtrace __maybe_unused)
+{
+	u32 state = perf_evsel__intval(evsel, sample, "state");
+	u32 cpu_id = perf_evsel__intval(evsel, sample, "cpu_id");
+
+	p_state_change(tchart, cpu_id, sample->time, state);
+	return 0;
+}
+
+static int
+process_sample_sched_wakeup(struct timechart *tchart,
+			    struct perf_evsel *evsel,
+			    struct perf_sample *sample,
+			    const char *backtrace)
+{
+	u8 flags = perf_evsel__intval(evsel, sample, "common_flags");
+	int waker = perf_evsel__intval(evsel, sample, "common_pid");
+	int wakee = perf_evsel__intval(evsel, sample, "pid");
+
+	sched_wakeup(tchart, sample->cpu, sample->time, waker, wakee, flags, backtrace);
+	return 0;
+}
+
+static int
+process_sample_sched_switch(struct timechart *tchart,
+			    struct perf_evsel *evsel,
+			    struct perf_sample *sample,
+			    const char *backtrace)
+{
+	int prev_pid = perf_evsel__intval(evsel, sample, "prev_pid");
+	int next_pid = perf_evsel__intval(evsel, sample, "next_pid");
+	u64 prev_state = perf_evsel__intval(evsel, sample, "prev_state");
+
+	sched_switch(tchart, sample->cpu, sample->time, prev_pid, next_pid,
+		     prev_state, backtrace);
 	return 0;
 }
 
+#ifdef SUPPORT_OLD_POWER_EVENTS
+static int
+process_sample_power_start(struct timechart *tchart __maybe_unused,
+			   struct perf_evsel *evsel,
+			   struct perf_sample *sample,
+			   const char *backtrace __maybe_unused)
+{
+	u64 cpu_id = perf_evsel__intval(evsel, sample, "cpu_id");
+	u64 value = perf_evsel__intval(evsel, sample, "value");
+
+	c_state_start(cpu_id, sample->time, value);
+	return 0;
+}
+
+static int
+process_sample_power_end(struct timechart *tchart,
+			 struct perf_evsel *evsel __maybe_unused,
+			 struct perf_sample *sample,
+			 const char *backtrace __maybe_unused)
+{
+	c_state_end(tchart, sample->cpu, sample->time);
+	return 0;
+}
+
+static int
+process_sample_power_frequency(struct timechart *tchart,
+			       struct perf_evsel *evsel,
+			       struct perf_sample *sample,
+			       const char *backtrace __maybe_unused)
+{
+	u64 cpu_id = perf_evsel__intval(evsel, sample, "cpu_id");
+	u64 value = perf_evsel__intval(evsel, sample, "value");
+
+	p_state_change(tchart, cpu_id, sample->time, value);
+	return 0;
+}
+#endif /* SUPPORT_OLD_POWER_EVENTS */
+
 /*
  * After the last sample we need to wrap up the current C/P state
  * and close out each CPU for these.
  */
-static void end_sample_processing(void)
+static void end_sample_processing(struct timechart *tchart)
 {
 	u64 cpu;
 	struct power_event *pwr;
 
-	for (cpu = 0; cpu <= numcpus; cpu++) {
-		pwr = malloc(sizeof(struct power_event));
+	for (cpu = 0; cpu <= tchart->numcpus; cpu++) {
+		/* C state */
+#if 0
+		pwr = zalloc(sizeof(*pwr));
 		if (!pwr)
 			return;
-		memset(pwr, 0, sizeof(struct power_event));
 
-		/* C state */
-#if 0
 		pwr->state = cpus_cstate_state[cpu];
 		pwr->start_time = cpus_cstate_start_times[cpu];
-		pwr->end_time = last_time;
+		pwr->end_time = tchart->last_time;
 		pwr->cpu = cpu;
 		pwr->type = CSTATE;
-		pwr->next = power_events;
+		pwr->next = tchart->power_events;
 
-		power_events = pwr;
+		tchart->power_events = pwr;
 #endif
 		/* P state */
 
-		pwr = malloc(sizeof(struct power_event));
+		pwr = zalloc(sizeof(*pwr));
 		if (!pwr)
 			return;
-		memset(pwr, 0, sizeof(struct power_event));
 
 		pwr->state = cpus_pstate_state[cpu];
 		pwr->start_time = cpus_pstate_start_times[cpu];
-		pwr->end_time = last_time;
+		pwr->end_time = tchart->last_time;
 		pwr->cpu = cpu;
 		pwr->type = PSTATE;
-		pwr->next = power_events;
+		pwr->next = tchart->power_events;
 
 		if (!pwr->start_time)
-			pwr->start_time = first_time;
+			pwr->start_time = tchart->first_time;
 		if (!pwr->state)
-			pwr->state = min_freq;
-		power_events = pwr;
+			pwr->state = tchart->min_freq;
+		tchart->power_events = pwr;
 	}
 }
 
 /*
  * Sort the pid datastructure
  */
-static void sort_pids(void)
+static void sort_pids(struct timechart *tchart)
 {
 	struct per_pid *new_list, *p, *cursor, *prev;
 	/* sort by ppid first, then by pid, lowest to highest */
 
 	new_list = NULL;
 
-	while (all_data) {
-		p = all_data;
-		all_data = p->next;
+	while (tchart->all_data) {
+		p = tchart->all_data;
+		tchart->all_data = p->next;
 		p->next = NULL;
 
 		if (new_list == NULL) {
@@ -608,14 +727,14 @@ static void sort_pids(void)
 				prev->next = p;
 		}
 	}
-	all_data = new_list;
+	tchart->all_data = new_list;
 }
 
 
-static void draw_c_p_states(void)
+static void draw_c_p_states(struct timechart *tchart)
 {
 	struct power_event *pwr;
-	pwr = power_events;
+	pwr = tchart->power_events;
 
 	/*
 	 * two pass drawing so that the P state bars are on top of the C state blocks
@@ -626,30 +745,30 @@ static void draw_c_p_states(void)
 		pwr = pwr->next;
 	}
 
-	pwr = power_events;
+	pwr = tchart->power_events;
 	while (pwr) {
 		if (pwr->type == PSTATE) {
 			if (!pwr->state)
-				pwr->state = min_freq;
+				pwr->state = tchart->min_freq;
 			svg_pstate(pwr->cpu, pwr->start_time, pwr->end_time, pwr->state);
 		}
 		pwr = pwr->next;
 	}
 }
 
-static void draw_wakeups(void)
+static void draw_wakeups(struct timechart *tchart)
 {
 	struct wake_event *we;
 	struct per_pid *p;
 	struct per_pidcomm *c;
 
-	we = wake_events;
+	we = tchart->wake_events;
 	while (we) {
 		int from = 0, to = 0;
 		char *task_from = NULL, *task_to = NULL;
 
 		/* locate the column of the waker and wakee */
-		p = all_data;
+		p = tchart->all_data;
 		while (p) {
 			if (p->pid == we->waker || p->pid == we->wakee) {
 				c = p->all;
@@ -692,11 +811,12 @@ static void draw_wakeups(void)
 		}
 
 		if (we->waker == -1)
-			svg_interrupt(we->time, to);
+			svg_interrupt(we->time, to, we->backtrace);
 		else if (from && to && abs(from - to) == 1)
-			svg_wakeline(we->time, from, to);
+			svg_wakeline(we->time, from, to, we->backtrace);
 		else
-			svg_partial_wakeline(we->time, from, task_from, to, task_to);
+			svg_partial_wakeline(we->time, from, task_from, to,
+					     task_to, we->backtrace);
 		we = we->next;
 
 		free(task_from);
@@ -704,19 +824,25 @@ static void draw_wakeups(void)
 	}
 }
 
-static void draw_cpu_usage(void)
+static void draw_cpu_usage(struct timechart *tchart)
 {
 	struct per_pid *p;
 	struct per_pidcomm *c;
 	struct cpu_sample *sample;
-	p = all_data;
+	p = tchart->all_data;
 	while (p) {
 		c = p->all;
 		while (c) {
 			sample = c->samples;
 			while (sample) {
-				if (sample->type == TYPE_RUNNING)
-					svg_process(sample->cpu, sample->start_time, sample->end_time, "sample", c->comm);
+				if (sample->type == TYPE_RUNNING) {
+					svg_process(sample->cpu,
+						    sample->start_time,
+						    sample->end_time,
+						    p->pid,
+						    c->comm,
+						    sample->backtrace);
+				}
 
 				sample = sample->next;
 			}
@@ -726,16 +852,16 @@ static void draw_cpu_usage(void)
 	}
 }
 
-static void draw_process_bars(void)
+static void draw_process_bars(struct timechart *tchart)
 {
 	struct per_pid *p;
 	struct per_pidcomm *c;
 	struct cpu_sample *sample;
 	int Y = 0;
 
-	Y = 2 * numcpus + 2;
+	Y = 2 * tchart->numcpus + 2;
 
-	p = all_data;
+	p = tchart->all_data;
 	while (p) {
 		c = p->all;
 		while (c) {
@@ -749,11 +875,20 @@ static void draw_process_bars(void)
 			sample = c->samples;
 			while (sample) {
 				if (sample->type == TYPE_RUNNING)
-					svg_sample(Y, sample->cpu, sample->start_time, sample->end_time);
+					svg_running(Y, sample->cpu,
+						    sample->start_time,
+						    sample->end_time,
+						    sample->backtrace);
 				if (sample->type == TYPE_BLOCKED)
-					svg_box(Y, sample->start_time, sample->end_time, "blocked");
+					svg_blocked(Y, sample->cpu,
+						    sample->start_time,
+						    sample->end_time,
+						    sample->backtrace);
 				if (sample->type == TYPE_WAITING)
-					svg_waiting(Y, sample->start_time, sample->end_time);
+					svg_waiting(Y, sample->cpu,
+						    sample->start_time,
+						    sample->end_time,
+						    sample->backtrace);
 				sample = sample->next;
 			}
 
@@ -776,11 +911,9 @@ static void draw_process_bars(void)
 
 static void add_process_filter(const char *string)
 {
-	struct process_filter *filt;
-	int pid;
+	int pid = strtoull(string, NULL, 10);
+	struct process_filter *filt = malloc(sizeof(*filt));
 
-	pid = strtoull(string, NULL, 10);
-	filt = malloc(sizeof(struct process_filter));
 	if (!filt)
 		return;
 
@@ -808,21 +941,21 @@ static int passes_filter(struct per_pid *p, struct per_pidcomm *c)
 	return 0;
 }
 
-static int determine_display_tasks_filtered(void)
+static int determine_display_tasks_filtered(struct timechart *tchart)
 {
 	struct per_pid *p;
 	struct per_pidcomm *c;
 	int count = 0;
 
-	p = all_data;
+	p = tchart->all_data;
 	while (p) {
 		p->display = 0;
 		if (p->start_time == 1)
-			p->start_time = first_time;
+			p->start_time = tchart->first_time;
 
 		/* no exit marker, task kept running to the end */
 		if (p->end_time == 0)
-			p->end_time = last_time;
+			p->end_time = tchart->last_time;
 
 		c = p->all;
 
@@ -830,7 +963,7 @@ static int determine_display_tasks_filtered(void)
 			c->display = 0;
 
 			if (c->start_time == 1)
-				c->start_time = first_time;
+				c->start_time = tchart->first_time;
 
 			if (passes_filter(p, c)) {
 				c->display = 1;
@@ -839,7 +972,7 @@ static int determine_display_tasks_filtered(void)
 			}
 
 			if (c->end_time == 0)
-				c->end_time = last_time;
+				c->end_time = tchart->last_time;
 
 			c = c->next;
 		}
@@ -848,25 +981,25 @@ static int determine_display_tasks_filtered(void)
 	return count;
 }
 
-static int determine_display_tasks(u64 threshold)
+static int determine_display_tasks(struct timechart *tchart, u64 threshold)
 {
 	struct per_pid *p;
 	struct per_pidcomm *c;
 	int count = 0;
 
 	if (process_filter)
-		return determine_display_tasks_filtered();
+		return determine_display_tasks_filtered(tchart);
 
-	p = all_data;
+	p = tchart->all_data;
 	while (p) {
 		p->display = 0;
 		if (p->start_time == 1)
-			p->start_time = first_time;
+			p->start_time = tchart->first_time;
 
 		/* no exit marker, task kept running to the end */
 		if (p->end_time == 0)
-			p->end_time = last_time;
-		if (p->total_time >= threshold && !power_only)
+			p->end_time = tchart->last_time;
+		if (p->total_time >= threshold)
 			p->display = 1;
 
 		c = p->all;
@@ -875,15 +1008,15 @@ static int determine_display_tasks(u64 threshold)
 			c->display = 0;
 
 			if (c->start_time == 1)
-				c->start_time = first_time;
+				c->start_time = tchart->first_time;
 
-			if (c->total_time >= threshold && !power_only) {
+			if (c->total_time >= threshold) {
 				c->display = 1;
 				count++;
 			}
 
 			if (c->end_time == 0)
-				c->end_time = last_time;
+				c->end_time = tchart->last_time;
 
 			c = c->next;
 		}
@@ -896,144 +1029,322 @@ static int determine_display_tasks(u64 threshold)
 
 #define TIME_THRESH 10000000
 
-static void write_svg_file(const char *filename)
+static void write_svg_file(struct timechart *tchart, const char *filename)
 {
 	u64 i;
 	int count;
+	int thresh = TIME_THRESH;
 
-	numcpus++;
+	if (tchart->power_only)
+		tchart->proc_num = 0;
 
+	/* We'd like to show at least proc_num tasks;
+	 * be less picky if we have fewer */
+	do {
+		count = determine_display_tasks(tchart, thresh);
+		thresh /= 10;
+	} while (!process_filter && thresh && count < tchart->proc_num);
 
-	count = determine_display_tasks(TIME_THRESH);
+	if (!tchart->proc_num)
+		count = 0;
 
-	/* We'd like to show at least 15 tasks; be less picky if we have fewer */
-	if (count < 15)
-		count = determine_display_tasks(TIME_THRESH / 10);
-
-	open_svg(filename, numcpus, count, first_time, last_time);
+	open_svg(filename, tchart->numcpus, count, tchart->first_time, tchart->last_time);
 
 	svg_time_grid();
 	svg_legenda();
 
-	for (i = 0; i < numcpus; i++)
-		svg_cpu_box(i, max_freq, turbo_frequency);
+	for (i = 0; i < tchart->numcpus; i++)
+		svg_cpu_box(i, tchart->max_freq, tchart->turbo_frequency);
 
-	draw_cpu_usage();
-	draw_process_bars();
-	draw_c_p_states();
-	draw_wakeups();
+	draw_cpu_usage(tchart);
+	if (tchart->proc_num)
+		draw_process_bars(tchart);
+	if (!tchart->tasks_only)
+		draw_c_p_states(tchart);
+	if (tchart->proc_num)
+		draw_wakeups(tchart);
 
 	svg_close();
 }
 
-static struct perf_event_ops event_ops = {
-	.comm			= process_comm_event,
-	.fork			= process_fork_event,
-	.exit			= process_exit_event,
-	.sample			= process_sample_event,
-	.ordered_samples	= true,
-};
+static int process_header(struct perf_file_section *section __maybe_unused,
+			  struct perf_header *ph,
+			  int feat,
+			  int fd __maybe_unused,
+			  void *data)
+{
+	struct timechart *tchart = data;
+
+	switch (feat) {
+	case HEADER_NRCPUS:
+		tchart->numcpus = ph->env.nr_cpus_avail;
+		break;
+
+	case HEADER_CPU_TOPOLOGY:
+		if (!tchart->topology)
+			break;
+
+		if (svg_build_topology_map(ph->env.sibling_cores,
+					   ph->env.nr_sibling_cores,
+					   ph->env.sibling_threads,
+					   ph->env.nr_sibling_threads))
+			fprintf(stderr, "problem building topology\n");
+		break;
+
+	default:
+		break;
+	}
 
-static int __cmd_timechart(void)
+	return 0;
+}
+
+static int __cmd_timechart(struct timechart *tchart, const char *output_name)
 {
-	struct perf_session *session = perf_session__new(input_name, O_RDONLY, 0, false);
+	const struct perf_evsel_str_handler power_tracepoints[] = {
+		{ "power:cpu_idle",		process_sample_cpu_idle },
+		{ "power:cpu_frequency",	process_sample_cpu_frequency },
+		{ "sched:sched_wakeup",		process_sample_sched_wakeup },
+		{ "sched:sched_switch",		process_sample_sched_switch },
+#ifdef SUPPORT_OLD_POWER_EVENTS
+		{ "power:power_start",		process_sample_power_start },
+		{ "power:power_end",		process_sample_power_end },
+		{ "power:power_frequency",	process_sample_power_frequency },
+#endif
+	};
+	struct perf_data_file file = {
+		.path = input_name,
+		.mode = PERF_DATA_MODE_READ,
+	};
+
+	struct perf_session *session = perf_session__new(&file, false,
+							 &tchart->tool);
 	int ret = -EINVAL;
 
 	if (session == NULL)
 		return -ENOMEM;
 
+	(void)perf_header__process_sections(&session->header,
+					    perf_data_file__fd(session->file),
+					    tchart,
+					    process_header);
+
 	if (!perf_session__has_traces(session, "timechart record"))
 		goto out_delete;
 
-	ret = perf_session__process_events(session, &event_ops);
+	if (perf_session__set_tracepoints_handlers(session,
+						   power_tracepoints)) {
+		pr_err("Initializing session tracepoint handlers failed\n");
+		goto out_delete;
+	}
+
+	ret = perf_session__process_events(session, &tchart->tool);
 	if (ret)
 		goto out_delete;
 
-	end_sample_processing();
+	end_sample_processing(tchart);
 
-	sort_pids();
+	sort_pids(tchart);
 
-	write_svg_file(output_name);
+	write_svg_file(tchart, output_name);
 
 	pr_info("Written %2.1f seconds of trace to %s.\n",
-		(last_time - first_time) / 1000000000.0, output_name);
+		(tchart->last_time - tchart->first_time) / 1000000000.0, output_name);
 out_delete:
 	perf_session__delete(session);
 	return ret;
 }
 
-static const char * const timechart_usage[] = {
-	"perf timechart [<options>] {record}",
-	NULL
-};
-
-static const char *record_args[] = {
-	"record",
-	"-a",
-	"-R",
-	"-f",
-	"-c", "1",
-	"-e", "power:power_start",
-	"-e", "power:power_end",
-	"-e", "power:power_frequency",
-	"-e", "sched:sched_wakeup",
-	"-e", "sched:sched_switch",
-};
-
-static int __cmd_record(int argc, const char **argv)
+static int timechart__record(struct timechart *tchart, int argc, const char **argv)
 {
 	unsigned int rec_argc, i, j;
 	const char **rec_argv;
+	const char **p;
+	unsigned int record_elems;
+
+	const char * const common_args[] = {
+		"record", "-a", "-R", "-c", "1",
+	};
+	unsigned int common_args_nr = ARRAY_SIZE(common_args);
+
+	const char * const backtrace_args[] = {
+		"-g",
+	};
+	unsigned int backtrace_args_no = ARRAY_SIZE(backtrace_args);
+
+	const char * const power_args[] = {
+		"-e", "power:cpu_frequency",
+		"-e", "power:cpu_idle",
+	};
+	unsigned int power_args_nr = ARRAY_SIZE(power_args);
+
+	const char * const old_power_args[] = {
+#ifdef SUPPORT_OLD_POWER_EVENTS
+		"-e", "power:power_start",
+		"-e", "power:power_end",
+		"-e", "power:power_frequency",
+#endif
+	};
+	unsigned int old_power_args_nr = ARRAY_SIZE(old_power_args);
+
+	const char * const tasks_args[] = {
+		"-e", "sched:sched_wakeup",
+		"-e", "sched:sched_switch",
+	};
+	unsigned int tasks_args_nr = ARRAY_SIZE(tasks_args);
+
+#ifdef SUPPORT_OLD_POWER_EVENTS
+	if (!is_valid_tracepoint("power:cpu_idle") &&
+	    is_valid_tracepoint("power:power_start")) {
+		use_old_power_events = 1;
+		power_args_nr = 0;
+	} else {
+		old_power_args_nr = 0;
+	}
+#endif
+
+	if (tchart->power_only)
+		tasks_args_nr = 0;
+
+	if (tchart->tasks_only) {
+		power_args_nr = 0;
+		old_power_args_nr = 0;
+	}
 
-	rec_argc = ARRAY_SIZE(record_args) + argc - 1;
+	if (!tchart->with_backtrace)
+		backtrace_args_no = 0;
+
+	record_elems = common_args_nr + tasks_args_nr +
+		power_args_nr + old_power_args_nr + backtrace_args_no;
+
+	rec_argc = record_elems + argc;
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
 
-	for (i = 0; i < ARRAY_SIZE(record_args); i++)
-		rec_argv[i] = strdup(record_args[i]);
+	if (rec_argv == NULL)
+		return -ENOMEM;
+
+	p = rec_argv;
+	for (i = 0; i < common_args_nr; i++)
+		*p++ = strdup(common_args[i]);
+
+	for (i = 0; i < backtrace_args_no; i++)
+		*p++ = strdup(backtrace_args[i]);
 
-	for (j = 1; j < (unsigned int)argc; j++, i++)
-		rec_argv[i] = argv[j];
+	for (i = 0; i < tasks_args_nr; i++)
+		*p++ = strdup(tasks_args[i]);
 
-	return cmd_record(i, rec_argv, NULL);
+	for (i = 0; i < power_args_nr; i++)
+		*p++ = strdup(power_args[i]);
+
+	for (i = 0; i < old_power_args_nr; i++)
+		*p++ = strdup(old_power_args[i]);
+
+	for (j = 0; j < (unsigned int)argc; j++)
+		*p++ = argv[j];
+
+	return cmd_record(rec_argc, rec_argv, NULL);
 }
 
 static int
-parse_process(const struct option *opt __used, const char *arg, int __used unset)
+parse_process(const struct option *opt __maybe_unused, const char *arg,
+	      int __maybe_unused unset)
 {
 	if (arg)
 		add_process_filter(arg);
 	return 0;
 }
 
-static const struct option options[] = {
-	OPT_STRING('i', "input", &input_name, "file",
-		    "input file name"),
-	OPT_STRING('o', "output", &output_name, "file",
-		    "output file name"),
-	OPT_INTEGER('w', "width", &svg_page_width,
-		    "page width"),
-	OPT_BOOLEAN('P', "power-only", &power_only,
-		    "output power data only"),
+static int
+parse_highlight(const struct option *opt __maybe_unused, const char *arg,
+		int __maybe_unused unset)
+{
+	unsigned long duration = strtoul(arg, NULL, 0);
+
+	if (svg_highlight || svg_highlight_name)
+		return -1;
+
+	if (duration)
+		svg_highlight = duration;
+	else
+		svg_highlight_name = strdup(arg);
+
+	return 0;
+}
+
+int cmd_timechart(int argc, const char **argv,
+		  const char *prefix __maybe_unused)
+{
+	struct timechart tchart = {
+		.tool = {
+			.comm		 = process_comm_event,
+			.fork		 = process_fork_event,
+			.exit		 = process_exit_event,
+			.sample		 = process_sample_event,
+			.ordered_samples = true,
+		},
+		.proc_num = 15,
+	};
+	const char *output_name = "output.svg";
+	const struct option timechart_options[] = {
+	OPT_STRING('i', "input", &input_name, "file", "input file name"),
+	OPT_STRING('o', "output", &output_name, "file", "output file name"),
+	OPT_INTEGER('w', "width", &svg_page_width, "page width"),
+	OPT_CALLBACK(0, "highlight", NULL, "duration or task name",
+		      "highlight tasks. Pass duration in ns or process name.",
+		       parse_highlight),
+	OPT_BOOLEAN('P', "power-only", &tchart.power_only, "output power data only"),
+	OPT_BOOLEAN('T', "tasks-only", &tchart.tasks_only,
+		    "output processes data only"),
 	OPT_CALLBACK('p', "process", NULL, "process",
 		      "process selector. Pass a pid or process name.",
 		       parse_process),
+	OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
+		    "Look for files with symbols relative to this directory"),
+	OPT_INTEGER('n', "proc-num", &tchart.proc_num,
+		    "min. number of tasks to print"),
+	OPT_BOOLEAN('t', "topology", &tchart.topology,
+		    "sort CPUs according to topology"),
 	OPT_END()
-};
-
-
-int cmd_timechart(int argc, const char **argv, const char *prefix __used)
-{
-	argc = parse_options(argc, argv, options, timechart_usage,
+	};
+	const char * const timechart_usage[] = {
+		"perf timechart [<options>] {record}",
+		NULL
+	};
+
+	const struct option record_options[] = {
+	OPT_BOOLEAN('P', "power-only", &tchart.power_only, "output power data only"),
+	OPT_BOOLEAN('T', "tasks-only", &tchart.tasks_only,
+		    "output processes data only"),
+	OPT_BOOLEAN('g', "callchain", &tchart.with_backtrace, "record callchain"),
+	OPT_END()
+	};
+	const char * const record_usage[] = {
+		"perf timechart record [<options>]",
+		NULL
+	};
+	argc = parse_options(argc, argv, timechart_options, timechart_usage,
 			PARSE_OPT_STOP_AT_NON_OPTION);
 
+	if (tchart.power_only && tchart.tasks_only) {
+		pr_err("-P and -T options cannot be used at the same time.\n");
+		return -1;
+	}
+
 	symbol__init();
 
-	if (argc && !strncmp(argv[0], "rec", 3))
-		return __cmd_record(argc, argv);
-	else if (argc)
-		usage_with_options(timechart_usage, options);
+	if (argc && !strncmp(argv[0], "rec", 3)) {
+		argc = parse_options(argc, argv, record_options, record_usage,
+				     PARSE_OPT_STOP_AT_NON_OPTION);
+
+		if (tchart.power_only && tchart.tasks_only) {
+			pr_err("-P and -T options cannot be used at the same time.\n");
+			return -1;
+		}
+
+		return timechart__record(&tchart, argc, argv);
+	} else if (argc)
+		usage_with_options(timechart_usage, timechart_options);
 
 	setup_pager();
 
-	return __cmd_timechart();
+	return __cmd_timechart(&tchart, output_name);
 }
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index a66f4272b99..377971dc89a 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -5,6 +5,7 @@
  * any workload, CPU or specific PID.
  *
  * Copyright (C) 2008, Red Hat Inc, Ingo Molnar <mingo@redhat.com>
+ *		 2011, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
  *
  * Improvements and fixes by:
  *
@@ -20,29 +21,41 @@
 
 #include "perf.h"
 
+#include "util/annotate.h"
+#include "util/cache.h"
 #include "util/color.h"
+#include "util/evlist.h"
+#include "util/evsel.h"
+#include "util/machine.h"
 #include "util/session.h"
 #include "util/symbol.h"
 #include "util/thread.h"
+#include "util/thread_map.h"
+#include "util/top.h"
 #include "util/util.h"
 #include <linux/rbtree.h>
 #include "util/parse-options.h"
 #include "util/parse-events.h"
 #include "util/cpumap.h"
+#include "util/xyarray.h"
+#include "util/sort.h"
+#include "util/intlist.h"
+#include "arch/common.h"
 
 #include "util/debug.h"
 
 #include <assert.h>
+#include <elf.h>
 #include <fcntl.h>
 
 #include <stdio.h>
 #include <termios.h>
 #include <unistd.h>
+#include <inttypes.h>
 
 #include <errno.h>
 #include <time.h>
 #include <sched.h>
-#include <pthread.h>
 
 #include <sys/syscall.h>
 #include <sys/ioctl.h>
@@ -50,598 +63,230 @@
 #include <sys/prctl.h>
 #include <sys/wait.h>
 #include <sys/uio.h>
+#include <sys/utsname.h>
 #include <sys/mman.h>
 
 #include <linux/unistd.h>
 #include <linux/types.h>
 
-static int			*fd[MAX_NR_CPUS][MAX_COUNTERS];
+static volatile int done;
 
-static bool			system_wide			=  false;
+#define HEADER_LINE_NR  5
 
-static int			default_interval		=      0;
-
-static int			count_filter			=      5;
-static int			print_entries;
-
-static int			target_pid			=     -1;
-static int			target_tid			=     -1;
-static pid_t			*all_tids			=      NULL;
-static int			thread_num			=      0;
-static bool			inherit				=  false;
-static int			profile_cpu			=     -1;
-static int			nr_cpus				=      0;
-static int			realtime_prio			=      0;
-static bool			group				=  false;
-static unsigned int		page_size;
-static unsigned int		mmap_pages			=     16;
-static int			freq				=   1000; /* 1 KHz */
-
-static int			delay_secs			=      2;
-static bool			zero                            =  false;
-static bool			dump_symtab                     =  false;
-
-static bool			hide_kernel_symbols		=  false;
-static bool			hide_user_symbols		=  false;
-static struct winsize		winsize;
-
-/*
- * Source
- */
-
-struct source_line {
-	u64			eip;
-	unsigned long		count[MAX_COUNTERS];
-	char			*line;
-	struct source_line	*next;
-};
-
-static const char		*sym_filter			=   NULL;
-struct sym_entry		*sym_filter_entry		=   NULL;
-struct sym_entry		*sym_filter_entry_sched		=   NULL;
-static int			sym_pcnt_filter			=      5;
-static int			sym_counter			=      0;
-static int			display_weighted		=     -1;
-
-/*
- * Symbols
- */
-
-struct sym_entry_source {
-	struct source_line	*source;
-	struct source_line	*lines;
-	struct source_line	**lines_tail;
-	pthread_mutex_t		lock;
-};
-
-struct sym_entry {
-	struct rb_node		rb_node;
-	struct list_head	node;
-	unsigned long		snap_count;
-	double			weight;
-	int			skip;
-	u16			name_len;
-	u8			origin;
-	struct map		*map;
-	struct sym_entry_source	*src;
-	unsigned long		count[0];
-};
-
-/*
- * Source functions
- */
-
-static inline struct symbol *sym_entry__symbol(struct sym_entry *self)
+static void perf_top__update_print_entries(struct perf_top *top)
 {
-       return ((void *)self) + symbol_conf.priv_size;
-}
-
-void get_term_dimensions(struct winsize *ws)
-{
-	char *s = getenv("LINES");
-
-	if (s != NULL) {
-		ws->ws_row = atoi(s);
-		s = getenv("COLUMNS");
-		if (s != NULL) {
-			ws->ws_col = atoi(s);
-			if (ws->ws_row && ws->ws_col)
-				return;
-		}
-	}
-#ifdef TIOCGWINSZ
-	if (ioctl(1, TIOCGWINSZ, ws) == 0 &&
-	    ws->ws_row && ws->ws_col)
-		return;
-#endif
-	ws->ws_row = 25;
-	ws->ws_col = 80;
+	top->print_entries = top->winsize.ws_row - HEADER_LINE_NR;
 }
 
-static void update_print_entries(struct winsize *ws)
+static void perf_top__sig_winch(int sig __maybe_unused,
+				siginfo_t *info __maybe_unused, void *arg)
 {
-	print_entries = ws->ws_row;
-
-	if (print_entries > 9)
-		print_entries -= 9;
-}
+	struct perf_top *top = arg;
 
-static void sig_winch_handler(int sig __used)
-{
-	get_term_dimensions(&winsize);
-	update_print_entries(&winsize);
+	get_term_dimensions(&top->winsize);
+	perf_top__update_print_entries(top);
 }
 
-static int parse_source(struct sym_entry *syme)
+static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he)
 {
 	struct symbol *sym;
-	struct sym_entry_source *source;
+	struct annotation *notes;
 	struct map *map;
-	FILE *file;
-	char command[PATH_MAX*2];
-	const char *path;
-	u64 len;
+	int err = -1;
 
-	if (!syme)
+	if (!he || !he->ms.sym)
 		return -1;
 
-	sym = sym_entry__symbol(syme);
-	map = syme->map;
+	sym = he->ms.sym;
+	map = he->ms.map;
 
 	/*
 	 * We can't annotate with just /proc/kallsyms
 	 */
-	if (map->dso->origin == DSO__ORIG_KERNEL)
+	if (map->dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS &&
+	    !dso__is_kcore(map->dso)) {
+		pr_err("Can't annotate %s: No vmlinux file was found in the "
+		       "path\n", sym->name);
+		sleep(1);
 		return -1;
-
-	if (syme->src == NULL) {
-		syme->src = zalloc(sizeof(*source));
-		if (syme->src == NULL)
-			return -1;
-		pthread_mutex_init(&syme->src->lock, NULL);
 	}
 
-	source = syme->src;
-
-	if (source->lines) {
-		pthread_mutex_lock(&source->lock);
+	notes = symbol__annotation(sym);
+	if (notes->src != NULL) {
+		pthread_mutex_lock(&notes->lock);
 		goto out_assign;
 	}
-	path = map->dso->long_name;
-
-	len = sym->end - sym->start;
 
-	sprintf(command,
-		"objdump --start-address=%#0*Lx --stop-address=%#0*Lx -dS %s",
-		BITS_PER_LONG / 4, map__rip_2objdump(map, sym->start),
-		BITS_PER_LONG / 4, map__rip_2objdump(map, sym->end), path);
-
-	file = popen(command, "r");
-	if (!file)
-		return -1;
+	pthread_mutex_lock(&notes->lock);
 
-	pthread_mutex_lock(&source->lock);
-	source->lines_tail = &source->lines;
-	while (!feof(file)) {
-		struct source_line *src;
-		size_t dummy = 0;
-		char *c, *sep;
-
-		src = malloc(sizeof(struct source_line));
-		assert(src != NULL);
-		memset(src, 0, sizeof(struct source_line));
-
-		if (getline(&src->line, &dummy, file) < 0)
-			break;
-		if (!src->line)
-			break;
-
-		c = strchr(src->line, '\n');
-		if (c)
-			*c = 0;
-
-		src->next = NULL;
-		*source->lines_tail = src;
-		source->lines_tail = &src->next;
-
-		src->eip = strtoull(src->line, &sep, 16);
-		if (*sep == ':')
-			src->eip = map__objdump_2ip(map, src->eip);
-		else /* this line has no ip info (e.g. source line) */
-			src->eip = 0;
+	if (symbol__alloc_hist(sym) < 0) {
+		pthread_mutex_unlock(&notes->lock);
+		pr_err("Not enough memory for annotating '%s' symbol!\n",
+		       sym->name);
+		sleep(1);
+		return err;
 	}
-	pclose(file);
-out_assign:
-	sym_filter_entry = syme;
-	pthread_mutex_unlock(&source->lock);
-	return 0;
-}
-
-static void __zero_source_counters(struct sym_entry *syme)
-{
-	int i;
-	struct source_line *line;
 
-	line = syme->src->lines;
-	while (line) {
-		for (i = 0; i < nr_counters; i++)
-			line->count[i] = 0;
-		line = line->next;
+	err = symbol__annotate(sym, map, 0);
+	if (err == 0) {
+out_assign:
+		top->sym_filter_entry = he;
 	}
-}
 
-static void record_precise_ip(struct sym_entry *syme, int counter, u64 ip)
-{
-	struct source_line *line;
-
-	if (syme != sym_filter_entry)
-		return;
-
-	if (pthread_mutex_trylock(&syme->src->lock))
-		return;
-
-	if (syme->src == NULL || syme->src->source == NULL)
-		goto out_unlock;
-
-	for (line = syme->src->lines; line; line = line->next) {
-		/* skip lines without IP info */
-		if (line->eip == 0)
-			continue;
-		if (line->eip == ip) {
-			line->count[counter]++;
-			break;
-		}
-		if (line->eip > ip)
-			break;
-	}
-out_unlock:
-	pthread_mutex_unlock(&syme->src->lock);
+	pthread_mutex_unlock(&notes->lock);
+	return err;
 }
 
-#define PATTERN_LEN		(BITS_PER_LONG / 4 + 2)
-
-static void lookup_sym_source(struct sym_entry *syme)
+static void __zero_source_counters(struct hist_entry *he)
 {
-	struct symbol *symbol = sym_entry__symbol(syme);
-	struct source_line *line;
-	char pattern[PATTERN_LEN + 1];
-
-	sprintf(pattern, "%0*Lx <", BITS_PER_LONG / 4,
-		map__rip_2objdump(syme->map, symbol->start));
-
-	pthread_mutex_lock(&syme->src->lock);
-	for (line = syme->src->lines; line; line = line->next) {
-		if (memcmp(line->line, pattern, PATTERN_LEN) == 0) {
-			syme->src->source = line;
-			break;
-		}
-	}
-	pthread_mutex_unlock(&syme->src->lock);
+	struct symbol *sym = he->ms.sym;
+	symbol__annotate_zero_histograms(sym);
 }
 
-static void show_lines(struct source_line *queue, int count, int total)
+static void ui__warn_map_erange(struct map *map, struct symbol *sym, u64 ip)
 {
-	int i;
-	struct source_line *line;
-
-	line = queue;
-	for (i = 0; i < count; i++) {
-		float pcnt = 100.0*(float)line->count[sym_counter]/(float)total;
-
-		printf("%8li %4.1f%%\t%s\n", line->count[sym_counter], pcnt, line->line);
-		line = line->next;
-	}
+	struct utsname uts;
+	int err = uname(&uts);
+
+	ui__warning("Out of bounds address found:\n\n"
+		    "Addr:   %" PRIx64 "\n"
+		    "DSO:    %s %c\n"
+		    "Map:    %" PRIx64 "-%" PRIx64 "\n"
+		    "Symbol: %" PRIx64 "-%" PRIx64 " %c %s\n"
+		    "Arch:   %s\n"
+		    "Kernel: %s\n"
+		    "Tools:  %s\n\n"
+		    "Not all samples will be on the annotation output.\n\n"
+		    "Please report to linux-kernel@vger.kernel.org\n",
+		    ip, map->dso->long_name, dso__symtab_origin(map->dso),
+		    map->start, map->end, sym->start, sym->end,
+		    sym->binding == STB_GLOBAL ? 'g' :
+		    sym->binding == STB_LOCAL  ? 'l' : 'w', sym->name,
+		    err ? "[unknown]" : uts.machine,
+		    err ? "[unknown]" : uts.release, perf_version_string);
+	if (use_browser <= 0)
+		sleep(5);
+	
+	map->erange_warned = true;
 }
 
-#define TRACE_COUNT     3
-
-static void show_details(struct sym_entry *syme)
+static void perf_top__record_precise_ip(struct perf_top *top,
+					struct hist_entry *he,
+					int counter, u64 ip)
 {
-	struct symbol *symbol;
-	struct source_line *line;
-	struct source_line *line_queue = NULL;
-	int displayed = 0;
-	int line_queue_count = 0, total = 0, more = 0;
+	struct annotation *notes;
+	struct symbol *sym;
+	int err = 0;
 
-	if (!syme)
+	if (he == NULL || he->ms.sym == NULL ||
+	    ((top->sym_filter_entry == NULL ||
+	      top->sym_filter_entry->ms.sym != he->ms.sym) && use_browser != 1))
 		return;
 
-	if (!syme->src->source)
-		lookup_sym_source(syme);
+	sym = he->ms.sym;
+	notes = symbol__annotation(sym);
 
-	if (!syme->src->source)
+	if (pthread_mutex_trylock(&notes->lock))
 		return;
 
-	symbol = sym_entry__symbol(syme);
-	printf("Showing %s for %s\n", event_name(sym_counter), symbol->name);
-	printf("  Events  Pcnt (>=%d%%)\n", sym_pcnt_filter);
-
-	pthread_mutex_lock(&syme->src->lock);
-	line = syme->src->source;
-	while (line) {
-		total += line->count[sym_counter];
-		line = line->next;
-	}
-
-	line = syme->src->source;
-	while (line) {
-		float pcnt = 0.0;
-
-		if (!line_queue_count)
-			line_queue = line;
-		line_queue_count++;
-
-		if (line->count[sym_counter])
-			pcnt = 100.0 * line->count[sym_counter] / (float)total;
-		if (pcnt >= (float)sym_pcnt_filter) {
-			if (displayed <= print_entries)
-				show_lines(line_queue, line_queue_count, total);
-			else more++;
-			displayed += line_queue_count;
-			line_queue_count = 0;
-			line_queue = NULL;
-		} else if (line_queue_count > TRACE_COUNT) {
-			line_queue = line_queue->next;
-			line_queue_count--;
-		}
-
-		line->count[sym_counter] = zero ? 0 : line->count[sym_counter] * 7 / 8;
-		line = line->next;
-	}
-	pthread_mutex_unlock(&syme->src->lock);
-	if (more)
-		printf("%d lines not displayed, maybe increase display entries [e]\n", more);
-}
-
-/*
- * Symbols will be added here in event__process_sample and will get out
- * after decayed.
- */
-static LIST_HEAD(active_symbols);
-static pthread_mutex_t active_symbols_lock = PTHREAD_MUTEX_INITIALIZER;
+	ip = he->ms.map->map_ip(he->ms.map, ip);
 
-/*
- * Ordering weight: count-1 * count-2 * ... / count-n
- */
-static double sym_weight(const struct sym_entry *sym)
-{
-	double weight = sym->snap_count;
-	int counter;
+	if (ui__has_annotation())
+		err = hist_entry__inc_addr_samples(he, counter, ip);
 
-	if (!display_weighted)
-		return weight;
+	pthread_mutex_unlock(&notes->lock);
 
-	for (counter = 1; counter < nr_counters-1; counter++)
-		weight *= sym->count[counter];
+	/*
+	 * This function is now called with he->hists->lock held.
+	 * Release it before going to sleep.
+	 */
+	pthread_mutex_unlock(&he->hists->lock);
 
-	weight /= (sym->count[counter] + 1);
+	if (err == -ERANGE && !he->ms.map->erange_warned)
+		ui__warn_map_erange(he->ms.map, sym, ip);
+	else if (err == -ENOMEM) {
+		pr_err("Not enough memory for annotating '%s' symbol!\n",
+		       sym->name);
+		sleep(1);
+	}
 
-	return weight;
+	pthread_mutex_lock(&he->hists->lock);
 }
 
-static long			samples;
-static long			kernel_samples, us_samples;
-static long			exact_samples;
-static long			guest_us_samples, guest_kernel_samples;
-static const char		CONSOLE_CLEAR[] = "";
-
-static void __list_insert_active_sym(struct sym_entry *syme)
+static void perf_top__show_details(struct perf_top *top)
 {
-	list_add(&syme->node, &active_symbols);
-}
+	struct hist_entry *he = top->sym_filter_entry;
+	struct annotation *notes;
+	struct symbol *symbol;
+	int more;
 
-static void list_remove_active_sym(struct sym_entry *syme)
-{
-	pthread_mutex_lock(&active_symbols_lock);
-	list_del_init(&syme->node);
-	pthread_mutex_unlock(&active_symbols_lock);
-}
+	if (!he)
+		return;
 
-static void rb_insert_active_sym(struct rb_root *tree, struct sym_entry *se)
-{
-	struct rb_node **p = &tree->rb_node;
-	struct rb_node *parent = NULL;
-	struct sym_entry *iter;
+	symbol = he->ms.sym;
+	notes = symbol__annotation(symbol);
 
-	while (*p != NULL) {
-		parent = *p;
-		iter = rb_entry(parent, struct sym_entry, rb_node);
+	pthread_mutex_lock(&notes->lock);
 
-		if (se->weight > iter->weight)
-			p = &(*p)->rb_left;
-		else
-			p = &(*p)->rb_right;
-	}
+	if (notes->src == NULL)
+		goto out_unlock;
+
+	printf("Showing %s for %s\n", perf_evsel__name(top->sym_evsel), symbol->name);
+	printf("  Events  Pcnt (>=%d%%)\n", top->sym_pcnt_filter);
 
-	rb_link_node(&se->rb_node, parent, p);
-	rb_insert_color(&se->rb_node, tree);
+	more = symbol__annotate_printf(symbol, he->ms.map, top->sym_evsel,
+				       0, top->sym_pcnt_filter, top->print_entries, 4);
+	if (top->zero)
+		symbol__annotate_zero_histogram(symbol, top->sym_evsel->idx);
+	else
+		symbol__annotate_decay_histogram(symbol, top->sym_evsel->idx);
+	if (more != 0)
+		printf("%d lines not displayed, maybe increase display entries [e]\n", more);
+out_unlock:
+	pthread_mutex_unlock(&notes->lock);
 }
 
-static void print_sym_table(void)
+static void perf_top__print_sym_table(struct perf_top *top)
 {
-	int printed = 0, j;
-	int counter, snap = !display_weighted ? sym_counter : 0;
-	float samples_per_sec = samples/delay_secs;
-	float ksamples_per_sec = kernel_samples/delay_secs;
-	float us_samples_per_sec = (us_samples)/delay_secs;
-	float guest_kernel_samples_per_sec = (guest_kernel_samples)/delay_secs;
-	float guest_us_samples_per_sec = (guest_us_samples)/delay_secs;
-	float esamples_percent = (100.0*exact_samples)/samples;
-	float sum_ksamples = 0.0;
-	struct sym_entry *syme, *n;
-	struct rb_root tmp = RB_ROOT;
-	struct rb_node *nd;
-	int sym_width = 0, dso_width = 0, dso_short_width = 0;
-	const int win_width = winsize.ws_col - 1;
-
-	samples = us_samples = kernel_samples = exact_samples = 0;
-	guest_kernel_samples = guest_us_samples = 0;
-
-	/* Sort the active symbols */
-	pthread_mutex_lock(&active_symbols_lock);
-	syme = list_entry(active_symbols.next, struct sym_entry, node);
-	pthread_mutex_unlock(&active_symbols_lock);
-
-	list_for_each_entry_safe_from(syme, n, &active_symbols, node) {
-		syme->snap_count = syme->count[snap];
-		if (syme->snap_count != 0) {
-
-			if ((hide_user_symbols &&
-			     syme->origin == PERF_RECORD_MISC_USER) ||
-			    (hide_kernel_symbols &&
-			     syme->origin == PERF_RECORD_MISC_KERNEL)) {
-				list_remove_active_sym(syme);
-				continue;
-			}
-			syme->weight = sym_weight(syme);
-			rb_insert_active_sym(&tmp, syme);
-			sum_ksamples += syme->snap_count;
-
-			for (j = 0; j < nr_counters; j++)
-				syme->count[j] = zero ? 0 : syme->count[j] * 7 / 8;
-		} else
-			list_remove_active_sym(syme);
-	}
+	char bf[160];
+	int printed = 0;
+	const int win_width = top->winsize.ws_col - 1;
 
 	puts(CONSOLE_CLEAR);
 
-	printf("%-*.*s\n", win_width, win_width, graph_dotted_line);
-	if (!perf_guest) {
-		printf("   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);
-	} else {
-		printf("   PerfTop:%8.0f irqs/sec  kernel:%4.1f%% us:%4.1f%%"
-			" guest kernel:%4.1f%% guest us:%4.1f%%"
-			" exact: %4.1f%% [",
-			samples_per_sec,
-			100.0 - (100.0 * ((samples_per_sec-ksamples_per_sec) /
-					  samples_per_sec)),
-			100.0 - (100.0 * ((samples_per_sec-us_samples_per_sec) /
-					  samples_per_sec)),
-			100.0 - (100.0 * ((samples_per_sec -
-						guest_kernel_samples_per_sec) /
-					  samples_per_sec)),
-			100.0 - (100.0 * ((samples_per_sec -
-					   guest_us_samples_per_sec) /
-					  samples_per_sec)),
-			esamples_percent);
-	}
+	perf_top__header_snprintf(top, bf, sizeof(bf));
+	printf("%s\n", bf);
 
-	if (nr_counters == 1 || !display_weighted) {
-		printf("%Ld", (u64)attrs[0].sample_period);
-		if (freq)
-			printf("Hz ");
-		else
-			printf(" ");
-	}
-
-	if (!display_weighted)
-		printf("%s", event_name(sym_counter));
-	else for (counter = 0; counter < nr_counters; counter++) {
-		if (counter)
-			printf("/");
-
-		printf("%s", event_name(counter));
-	}
-
-	printf( "], ");
-
-	if (target_pid != -1)
-		printf(" (target_pid: %d", target_pid);
-	else if (target_tid != -1)
-		printf(" (target_tid: %d", target_tid);
-	else
-		printf(" (all");
-
-	if (profile_cpu != -1)
-		printf(", cpu: %d)\n", profile_cpu);
-	else {
-		if (target_tid != -1)
-			printf(")\n");
-		else
-			printf(", %d CPUs)\n", nr_cpus);
-	}
+	perf_top__reset_sample_counters(top);
 
 	printf("%-*.*s\n", win_width, win_width, graph_dotted_line);
 
-	if (sym_filter_entry) {
-		show_details(sym_filter_entry);
-		return;
+	if (top->sym_evsel->hists.stats.nr_lost_warned !=
+	    top->sym_evsel->hists.stats.nr_events[PERF_RECORD_LOST]) {
+		top->sym_evsel->hists.stats.nr_lost_warned =
+			top->sym_evsel->hists.stats.nr_events[PERF_RECORD_LOST];
+		color_fprintf(stdout, PERF_COLOR_RED,
+			      "WARNING: LOST %d chunks, Check IO/CPU overload",
+			      top->sym_evsel->hists.stats.nr_lost_warned);
+		++printed;
 	}
 
-	/*
-	 * Find the longest symbol name that will be displayed
-	 */
-	for (nd = rb_first(&tmp); nd; nd = rb_next(nd)) {
-		syme = rb_entry(nd, struct sym_entry, rb_node);
-		if (++printed > print_entries ||
-		    (int)syme->snap_count < count_filter)
-			continue;
-
-		if (syme->map->dso->long_name_len > dso_width)
-			dso_width = syme->map->dso->long_name_len;
-
-		if (syme->map->dso->short_name_len > dso_short_width)
-			dso_short_width = syme->map->dso->short_name_len;
-
-		if (syme->name_len > sym_width)
-			sym_width = syme->name_len;
+	if (top->sym_filter_entry) {
+		perf_top__show_details(top);
+		return;
 	}
 
-	printed = 0;
-
-	if (sym_width + dso_width > winsize.ws_col - 29) {
-		dso_width = dso_short_width;
-		if (sym_width + dso_width > winsize.ws_col - 29)
-			sym_width = winsize.ws_col - dso_width - 29;
-	}
+	hists__collapse_resort(&top->sym_evsel->hists, NULL);
+	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->print_entries - printed);
 	putchar('\n');
-	if (nr_counters == 1)
-		printf("             samples  pcnt");
-	else
-		printf("   weight    samples  pcnt");
-
-	if (verbose)
-		printf("         RIP       ");
-	printf(" %-*.*s DSO\n", sym_width, sym_width, "function");
-	printf("   %s    _______ _____",
-	       nr_counters == 1 ? "      " : "______");
-	if (verbose)
-		printf(" ________________");
-	printf(" %-*.*s", sym_width, sym_width, graph_line);
-	printf(" %-*.*s", dso_width, dso_width, graph_line);
-	puts("\n");
-
-	for (nd = rb_first(&tmp); nd; nd = rb_next(nd)) {
-		struct symbol *sym;
-		double pcnt;
-
-		syme = rb_entry(nd, struct sym_entry, rb_node);
-		sym = sym_entry__symbol(syme);
-		if (++printed > print_entries || (int)syme->snap_count < count_filter)
-			continue;
-
-		pcnt = 100.0 - (100.0 * ((sum_ksamples - syme->snap_count) /
-					 sum_ksamples));
-
-		if (nr_counters == 1 || !display_weighted)
-			printf("%20.2f ", syme->weight);
-		else
-			printf("%9.1f %10ld ", syme->weight, syme->snap_count);
-
-		percent_color_fprintf(stdout, "%4.1f%%", pcnt);
-		if (verbose)
-			printf(" %016llx", sym->start);
-		printf(" %-*.*s", sym_width, sym_width, sym->name);
-		printf(" %-*.*s\n", dso_width, dso_width,
-		       dso_width >= syme->map->dso->long_name_len ?
-					syme->map->dso->long_name :
-					syme->map->dso->short_name);
-	}
+	hists__fprintf(&top->sym_evsel->hists, false,
+		       top->print_entries - printed, win_width,
+		       top->min_percent, stdout);
 }
 
 static void prompt_integer(int *target, const char *msg)
@@ -679,18 +324,17 @@ static void prompt_percent(int *target, const char *msg)
 		*target = tmp;
 }
 
-static void prompt_symbol(struct sym_entry **target, const char *msg)
+static void perf_top__prompt_symbol(struct perf_top *top, const char *msg)
 {
 	char *buf = malloc(0), *p;
-	struct sym_entry *syme = *target, *n, *found = NULL;
+	struct hist_entry *syme = top->sym_filter_entry, *n, *found = NULL;
+	struct rb_node *next;
 	size_t dummy = 0;
 
 	/* zero counters of active symbol */
 	if (syme) {
-		pthread_mutex_lock(&syme->src->lock);
 		__zero_source_counters(syme);
-		*target = NULL;
-		pthread_mutex_unlock(&syme->src->lock);
+		top->sym_filter_entry = NULL;
 	}
 
 	fprintf(stdout, "\n%s: ", msg);
@@ -701,66 +345,59 @@ static void prompt_symbol(struct sym_entry **target, const char *msg)
 	if (p)
 		*p = 0;
 
-	pthread_mutex_lock(&active_symbols_lock);
-	syme = list_entry(active_symbols.next, struct sym_entry, node);
-	pthread_mutex_unlock(&active_symbols_lock);
-
-	list_for_each_entry_safe_from(syme, n, &active_symbols, node) {
-		struct symbol *sym = sym_entry__symbol(syme);
-
-		if (!strcmp(buf, sym->name)) {
-			found = syme;
+	next = rb_first(&top->sym_evsel->hists.entries);
+	while (next) {
+		n = rb_entry(next, struct hist_entry, rb_node);
+		if (n->ms.sym && !strcmp(buf, n->ms.sym->name)) {
+			found = n;
 			break;
 		}
+		next = rb_next(&n->rb_node);
 	}
 
 	if (!found) {
 		fprintf(stderr, "Sorry, %s is not active.\n", buf);
 		sleep(1);
-		return;
 	} else
-		parse_source(found);
+		perf_top__parse_source(top, found);
 
 out_free:
 	free(buf);
 }
 
-static void print_mapped_keys(void)
+static void perf_top__print_mapped_keys(struct perf_top *top)
 {
 	char *name = NULL;
 
-	if (sym_filter_entry) {
-		struct symbol *sym = sym_entry__symbol(sym_filter_entry);
+	if (top->sym_filter_entry) {
+		struct symbol *sym = top->sym_filter_entry->ms.sym;
 		name = sym->name;
 	}
 
 	fprintf(stdout, "\nMapped keys:\n");
-	fprintf(stdout, "\t[d]     display refresh delay.             \t(%d)\n", delay_secs);
-	fprintf(stdout, "\t[e]     display entries (lines).           \t(%d)\n", print_entries);
+	fprintf(stdout, "\t[d]     display refresh delay.             \t(%d)\n", top->delay_secs);
+	fprintf(stdout, "\t[e]     display entries (lines).           \t(%d)\n", top->print_entries);
 
-	if (nr_counters > 1)
-		fprintf(stdout, "\t[E]     active event counter.              \t(%s)\n", event_name(sym_counter));
+	if (top->evlist->nr_entries > 1)
+		fprintf(stdout, "\t[E]     active event counter.              \t(%s)\n", perf_evsel__name(top->sym_evsel));
 
-	fprintf(stdout, "\t[f]     profile display filter (count).    \t(%d)\n", count_filter);
+	fprintf(stdout, "\t[f]     profile display filter (count).    \t(%d)\n", top->count_filter);
 
-	fprintf(stdout, "\t[F]     annotate display filter (percent). \t(%d%%)\n", sym_pcnt_filter);
+	fprintf(stdout, "\t[F]     annotate display filter (percent). \t(%d%%)\n", top->sym_pcnt_filter);
 	fprintf(stdout, "\t[s]     annotate symbol.                   \t(%s)\n", name?: "NULL");
 	fprintf(stdout, "\t[S]     stop annotation.\n");
 
-	if (nr_counters > 1)
-		fprintf(stdout, "\t[w]     toggle display weighted/count[E]r. \t(%d)\n", display_weighted ? 1 : 0);
-
 	fprintf(stdout,
 		"\t[K]     hide kernel_symbols symbols.     \t(%s)\n",
-		hide_kernel_symbols ? "yes" : "no");
+		top->hide_kernel_symbols ? "yes" : "no");
 	fprintf(stdout,
 		"\t[U]     hide user symbols.               \t(%s)\n",
-		hide_user_symbols ? "yes" : "no");
-	fprintf(stdout, "\t[z]     toggle sample zeroing.             \t(%d)\n", zero ? 1 : 0);
+		top->hide_user_symbols ? "yes" : "no");
+	fprintf(stdout, "\t[z]     toggle sample zeroing.             \t(%d)\n", top->zero ? 1 : 0);
 	fprintf(stdout, "\t[qQ]    quit.\n");
 }
 
-static int key_mapped(int c)
+static int perf_top__key_mapped(struct perf_top *top, int c)
 {
 	switch (c) {
 		case 'd':
@@ -776,8 +413,7 @@ static int key_mapped(int c)
 		case 'S':
 			return 1;
 		case 'E':
-		case 'w':
-			return nr_counters > 1 ? 1 : 0;
+			return top->evlist->nr_entries > 1 ? 1 : 0;
 		default:
 			break;
 	}
@@ -785,13 +421,15 @@ static int key_mapped(int c)
 	return 0;
 }
 
-static void handle_keypress(struct perf_session *session, int c)
+static bool perf_top__handle_keypress(struct perf_top *top, int c)
 {
-	if (!key_mapped(c)) {
+	bool ret = true;
+
+	if (!perf_top__key_mapped(top, c)) {
 		struct pollfd stdin_poll = { .fd = 0, .events = POLLIN };
 		struct termios tc, save;
 
-		print_mapped_keys();
+		perf_top__print_mapped_keys(top);
 		fprintf(stdout, "\nEnter selection, or unmapped key to continue: ");
 		fflush(stdout);
 
@@ -806,91 +444,145 @@ static void handle_keypress(struct perf_session *session, int c)
 		c = getc(stdin);
 
 		tcsetattr(0, TCSAFLUSH, &save);
-		if (!key_mapped(c))
-			return;
+		if (!perf_top__key_mapped(top, c))
+			return ret;
 	}
 
 	switch (c) {
 		case 'd':
-			prompt_integer(&delay_secs, "Enter display delay");
-			if (delay_secs < 1)
-				delay_secs = 1;
+			prompt_integer(&top->delay_secs, "Enter display delay");
+			if (top->delay_secs < 1)
+				top->delay_secs = 1;
 			break;
 		case 'e':
-			prompt_integer(&print_entries, "Enter display entries (lines)");
-			if (print_entries == 0) {
-				sig_winch_handler(SIGWINCH);
-				signal(SIGWINCH, sig_winch_handler);
-			} else
+			prompt_integer(&top->print_entries, "Enter display entries (lines)");
+			if (top->print_entries == 0) {
+				struct sigaction act = {
+					.sa_sigaction = perf_top__sig_winch,
+					.sa_flags     = SA_SIGINFO,
+				};
+				perf_top__sig_winch(SIGWINCH, NULL, top);
+				sigaction(SIGWINCH, &act, NULL);
+			} else {
 				signal(SIGWINCH, SIG_DFL);
+			}
 			break;
 		case 'E':
-			if (nr_counters > 1) {
-				int i;
+			if (top->evlist->nr_entries > 1) {
+				/* Select 0 as the default event: */
+				int counter = 0;
 
 				fprintf(stderr, "\nAvailable events:");
-				for (i = 0; i < nr_counters; i++)
-					fprintf(stderr, "\n\t%d %s", i, event_name(i));
 
-				prompt_integer(&sym_counter, "Enter details event counter");
+				evlist__for_each(top->evlist, top->sym_evsel)
+					fprintf(stderr, "\n\t%d %s", top->sym_evsel->idx, perf_evsel__name(top->sym_evsel));
+
+				prompt_integer(&counter, "Enter details event counter");
 
-				if (sym_counter >= nr_counters) {
-					fprintf(stderr, "Sorry, no such event, using %s.\n", event_name(0));
-					sym_counter = 0;
+				if (counter >= top->evlist->nr_entries) {
+					top->sym_evsel = perf_evlist__first(top->evlist);
+					fprintf(stderr, "Sorry, no such event, using %s.\n", perf_evsel__name(top->sym_evsel));
 					sleep(1);
+					break;
 				}
-			} else sym_counter = 0;
+				evlist__for_each(top->evlist, top->sym_evsel)
+					if (top->sym_evsel->idx == counter)
+						break;
+			} else
+				top->sym_evsel = perf_evlist__first(top->evlist);
 			break;
 		case 'f':
-			prompt_integer(&count_filter, "Enter display event count filter");
+			prompt_integer(&top->count_filter, "Enter display event count filter");
 			break;
 		case 'F':
-			prompt_percent(&sym_pcnt_filter, "Enter details display event filter (percent)");
+			prompt_percent(&top->sym_pcnt_filter,
+				       "Enter details display event filter (percent)");
 			break;
 		case 'K':
-			hide_kernel_symbols = !hide_kernel_symbols;
+			top->hide_kernel_symbols = !top->hide_kernel_symbols;
 			break;
 		case 'q':
 		case 'Q':
 			printf("exiting.\n");
-			if (dump_symtab)
-				perf_session__fprintf_dsos(session, stderr);
-			exit(0);
+			if (top->dump_symtab)
+				perf_session__fprintf_dsos(top->session, stderr);
+			ret = false;
+			break;
 		case 's':
-			prompt_symbol(&sym_filter_entry, "Enter details symbol");
+			perf_top__prompt_symbol(top, "Enter details symbol");
 			break;
 		case 'S':
-			if (!sym_filter_entry)
+			if (!top->sym_filter_entry)
 				break;
 			else {
-				struct sym_entry *syme = sym_filter_entry;
+				struct hist_entry *syme = top->sym_filter_entry;
 
-				pthread_mutex_lock(&syme->src->lock);
-				sym_filter_entry = NULL;
+				top->sym_filter_entry = NULL;
 				__zero_source_counters(syme);
-				pthread_mutex_unlock(&syme->src->lock);
 			}
 			break;
 		case 'U':
-			hide_user_symbols = !hide_user_symbols;
-			break;
-		case 'w':
-			display_weighted = ~display_weighted;
+			top->hide_user_symbols = !top->hide_user_symbols;
 			break;
 		case 'z':
-			zero = !zero;
+			top->zero = !top->zero;
 			break;
 		default:
 			break;
 	}
+
+	return ret;
+}
+
+static void perf_top__sort_new_samples(void *arg)
+{
+	struct perf_top *t = arg;
+	perf_top__reset_sample_counters(t);
+
+	if (t->evlist->selected != NULL)
+		t->sym_evsel = t->evlist->selected;
+
+	hists__collapse_resort(&t->sym_evsel->hists, NULL);
+	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)
+{
+	struct perf_evsel *pos;
+	struct perf_top *top = arg;
+	const char *help = "For a higher level overview, try: perf top --sort comm,dso";
+	struct hist_browser_timer hbt = {
+		.timer		= perf_top__sort_new_samples,
+		.arg		= top,
+		.refresh	= top->delay_secs,
+	};
+
+	perf_top__sort_new_samples(top);
+
+	/*
+	 * Initialize the uid_filter_str, in the future the TUI will allow
+	 * Zooming in/out UIDs. For now juse use whatever the user passed
+	 * via --uid.
+	 */
+	evlist__for_each(top->evlist, pos)
+		pos->hists.uid_filter_str = top->record_opts.target.uid_str;
+
+	perf_evlist__tui_browse_hists(top->evlist, help, &hbt, top->min_percent,
+				      &top->session->header.env);
+
+	done = 1;
+	return NULL;
 }
 
-static void *display_thread(void *arg __used)
+static void *display_thread(void *arg)
 {
 	struct pollfd stdin_poll = { .fd = 0, .events = POLLIN };
 	struct termios tc, save;
+	struct perf_top *top = arg;
 	int delay_msecs, c;
-	struct perf_session *session = (struct perf_session *) arg;
 
 	tcgetattr(0, &save);
 	tc = save;
@@ -898,44 +590,42 @@ static void *display_thread(void *arg __used)
 	tc.c_cc[VMIN] = 0;
 	tc.c_cc[VTIME] = 0;
 
+	pthread__unblock_sigwinch();
 repeat:
-	delay_msecs = delay_secs * 1000;
+	delay_msecs = top->delay_secs * 1000;
 	tcsetattr(0, TCSANOW, &tc);
 	/* trash return*/
 	getc(stdin);
 
-	do {
-		print_sym_table();
-	} while (!poll(&stdin_poll, 1, delay_msecs) == 1);
-
-	c = getc(stdin);
-	tcsetattr(0, TCSAFLUSH, &save);
+	while (!done) {
+		perf_top__print_sym_table(top);
+		/*
+		 * Either timeout expired or we got an EINTR due to SIGWINCH,
+		 * refresh screen in both cases.
+		 */
+		switch (poll(&stdin_poll, 1, delay_msecs)) {
+		case 0:
+			continue;
+		case -1:
+			if (errno == EINTR)
+				continue;
+			/* Fall trhu */
+		default:
+			c = getc(stdin);
+			tcsetattr(0, TCSAFLUSH, &save);
 
-	handle_keypress(session, c);
-	goto repeat;
+			if (perf_top__handle_keypress(top, c))
+				goto repeat;
+			done = 1;
+		}
+	}
 
 	return NULL;
 }
 
-/* Tag samples to be skipped. */
-static const char *skip_symbols[] = {
-	"default_idle",
-	"cpu_idle",
-	"enter_idle",
-	"exit_idle",
-	"mwait_idle",
-	"mwait_idle_with_hints",
-	"poll_idle",
-	"ppc64_runlatch_off",
-	"pseries_dedicated_idle_sleep",
-	NULL
-};
-
-static int symbol_filter(struct map *map, struct symbol *sym)
+static int symbol_filter(struct map *map __maybe_unused, struct symbol *sym)
 {
-	struct sym_entry *syme;
 	const char *name = sym->name;
-	int i;
 
 	/*
 	 * ppc64 uses function descriptors and appends a '.' to the
@@ -953,82 +643,84 @@ static int symbol_filter(struct map *map, struct symbol *sym)
 	    strstr(name, "_text_end"))
 		return 1;
 
-	syme = symbol__priv(sym);
-	syme->map = map;
-	syme->src = NULL;
+	if (symbol__is_idle(sym))
+		sym->ignore = true;
 
-	if (!sym_filter_entry && sym_filter && !strcmp(name, sym_filter)) {
-		/* schedule initial sym_filter_entry setup */
-		sym_filter_entry_sched = syme;
-		sym_filter = NULL;
-	}
+	return 0;
+}
 
-	for (i = 0; skip_symbols[i]; i++) {
-		if (!strcmp(skip_symbols[i], name)) {
-			syme->skip = 1;
-			break;
-		}
-	}
+static int hist_iter__top_callback(struct hist_entry_iter *iter,
+				   struct addr_location *al, bool single,
+				   void *arg)
+{
+	struct perf_top *top = arg;
+	struct hist_entry *he = iter->he;
+	struct perf_evsel *evsel = iter->evsel;
+
+	if (sort__has_sym && single) {
+		u64 ip = al->addr;
 
-	if (!syme->skip)
-		syme->name_len = strlen(sym->name);
+		if (al->map)
+			ip = al->map->unmap_ip(al->map, ip);
+
+		perf_top__record_precise_ip(top, he, evsel->idx, ip);
+	}
 
 	return 0;
 }
 
-static void event__process_sample(const event_t *self,
-				 struct perf_session *session, int counter)
+static void perf_event__process_sample(struct perf_tool *tool,
+				       const union perf_event *event,
+				       struct perf_evsel *evsel,
+				       struct perf_sample *sample,
+				       struct machine *machine)
 {
-	u64 ip = self->ip.ip;
-	struct sym_entry *syme;
+	struct perf_top *top = container_of(tool, struct perf_top, tool);
 	struct addr_location al;
-	struct machine *machine;
-	u8 origin = self->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
-
-	++samples;
-
-	switch (origin) {
-	case PERF_RECORD_MISC_USER:
-		++us_samples;
-		if (hide_user_symbols)
-			return;
-		machine = perf_session__find_host_machine(session);
-		break;
-	case PERF_RECORD_MISC_KERNEL:
-		++kernel_samples;
-		if (hide_kernel_symbols)
-			return;
-		machine = perf_session__find_host_machine(session);
-		break;
-	case PERF_RECORD_MISC_GUEST_KERNEL:
-		++guest_kernel_samples;
-		machine = perf_session__find_machine(session, self->ip.pid);
-		break;
-	case PERF_RECORD_MISC_GUEST_USER:
-		++guest_us_samples;
-		/*
-		 * TODO: we don't process guest user from host side
-		 * except simple counting.
-		 */
-		return;
-	default:
+	int err;
+
+	if (!machine && perf_guest) {
+		static struct intlist *seen;
+
+		if (!seen)
+			seen = intlist__new(NULL);
+
+		if (!intlist__has_entry(seen, sample->pid)) {
+			pr_err("Can't find guest [%d]'s kernel information\n",
+				sample->pid);
+			intlist__add(seen, sample->pid);
+		}
 		return;
 	}
 
-	if (!machine && perf_guest) {
-		pr_err("Can't find guest [%d]'s kernel information\n",
-			self->ip.pid);
+	if (!machine) {
+		pr_err("%u unprocessable samples recorded.\r",
+		       top->session->stats.nr_unprocessable_samples++);
 		return;
 	}
 
-	if (self->header.misc & PERF_RECORD_MISC_EXACT_IP)
-		exact_samples++;
+	if (event->header.misc & PERF_RECORD_MISC_EXACT_IP)
+		top->exact_samples++;
 
-	if (event__preprocess_sample(self, session, &al, symbol_filter) < 0 ||
-	    al.filtered)
+	if (perf_event__preprocess_sample(event, machine, &al, sample) < 0)
 		return;
 
+	if (!top->kptr_restrict_warned &&
+	    symbol_conf.kptr_restrict &&
+	    al.cpumode == PERF_RECORD_MISC_KERNEL) {
+		ui__warning(
+"Kernel address maps (/proc/{kallsyms,modules}) are restricted.\n\n"
+"Check /proc/sys/kernel/kptr_restrict.\n\n"
+"Kernel%s samples will not be resolved.\n",
+			  !RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION]) ?
+			  " modules" : "");
+		if (use_browser <= 0)
+			sleep(5);
+		top->kptr_restrict_warned = true;
+	}
+
 	if (al.sym == NULL) {
+		const char *msg = "Kernel samples will not be resolved.\n";
 		/*
 		 * As we do lazy loading of symtabs we only will know if the
 		 * specified vmlinux file is invalid when we actually have a
@@ -1040,445 +732,510 @@ static void event__process_sample(const event_t *self,
 		 * --hide-kernel-symbols, even if the user specifies an
 		 * invalid --vmlinux ;-)
 		 */
-		if (al.map == machine->vmlinux_maps[MAP__FUNCTION] &&
+		if (!top->kptr_restrict_warned && !top->vmlinux_warned &&
+		    al.map == machine->vmlinux_maps[MAP__FUNCTION] &&
 		    RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION])) {
-			pr_err("The %s file can't be used\n",
-			       symbol_conf.vmlinux_name);
-			exit(1);
-		}
-
-		return;
-	}
+			if (symbol_conf.vmlinux_name) {
+				ui__warning("The %s file can't be used.\n%s",
+					    symbol_conf.vmlinux_name, msg);
+			} else {
+				ui__warning("A vmlinux file was not found.\n%s",
+					    msg);
+			}
 
-	/* let's see, whether we need to install initial sym_filter_entry */
-	if (sym_filter_entry_sched) {
-		sym_filter_entry = sym_filter_entry_sched;
-		sym_filter_entry_sched = NULL;
-		if (parse_source(sym_filter_entry) < 0) {
-			struct symbol *sym = sym_entry__symbol(sym_filter_entry);
-
-			pr_err("Can't annotate %s", sym->name);
-			if (sym_filter_entry->map->dso->origin == DSO__ORIG_KERNEL) {
-				pr_err(": No vmlinux file was found in the path:\n");
-				machine__fprintf_vmlinux_path(machine, stderr);
-			} else
-				pr_err(".\n");
-			exit(1);
+			if (use_browser <= 0)
+				sleep(5);
+			top->vmlinux_warned = true;
 		}
 	}
 
-	syme = symbol__priv(al.sym);
-	if (!syme->skip) {
-		syme->count[counter]++;
-		syme->origin = origin;
-		record_precise_ip(syme, counter, ip);
-		pthread_mutex_lock(&active_symbols_lock);
-		if (list_empty(&syme->node) || !syme->node.next)
-			__list_insert_active_sym(syme);
-		pthread_mutex_unlock(&active_symbols_lock);
-	}
-}
+	if (al.sym == NULL || !al.sym->ignore) {
+		struct hist_entry_iter iter = {
+			.add_entry_cb = hist_iter__top_callback,
+		};
 
-static int event__process(event_t *event, struct perf_session *session)
-{
-	switch (event->header.type) {
-	case PERF_RECORD_COMM:
-		event__process_comm(event, session);
-		break;
-	case PERF_RECORD_MMAP:
-		event__process_mmap(event, session);
-		break;
-	case PERF_RECORD_FORK:
-	case PERF_RECORD_EXIT:
-		event__process_task(event, session);
-		break;
-	default:
-		break;
-	}
-
-	return 0;
-}
+		if (symbol_conf.cumulate_callchain)
+			iter.ops = &hist_iter_cumulative;
+		else
+			iter.ops = &hist_iter_normal;
 
-struct mmap_data {
-	int			counter;
-	void			*base;
-	int			mask;
-	unsigned int		prev;
-};
+		pthread_mutex_lock(&evsel->hists.lock);
 
-static unsigned int mmap_read_head(struct mmap_data *md)
-{
-	struct perf_event_mmap_page *pc = md->base;
-	int head;
+		err = hist_entry_iter__add(&iter, &al, evsel, sample,
+					   top->max_stack, top);
+		if (err < 0)
+			pr_err("Problem incrementing symbol period, skipping event\n");
 
-	head = pc->data_head;
-	rmb();
+		pthread_mutex_unlock(&evsel->hists.lock);
+	}
 
-	return head;
+	return;
 }
 
-static void perf_session__mmap_read_counter(struct perf_session *self,
-					    struct mmap_data *md)
+static void perf_top__mmap_read_idx(struct perf_top *top, int idx)
 {
-	unsigned int head = mmap_read_head(md);
-	unsigned int old = md->prev;
-	unsigned char *data = md->base + page_size;
-	int diff;
-
-	/*
-	 * If we're further behind than half the buffer, there's a chance
-	 * the writer will bite our tail and mess up the samples under us.
-	 *
-	 * If we somehow ended up ahead of the head, we got messed up.
-	 *
-	 * In either case, truncate and restart at head.
-	 */
-	diff = head - old;
-	if (diff > md->mask / 2 || diff < 0) {
-		fprintf(stderr, "WARNING: failed to keep up with mmap data.\n");
-
-		/*
-		 * head points to a known good entry, start there.
-		 */
-		old = head;
-	}
+	struct perf_sample sample;
+	struct perf_evsel *evsel;
+	struct perf_session *session = top->session;
+	union perf_event *event;
+	struct machine *machine;
+	u8 origin;
+	int ret;
 
-	for (; old != head;) {
-		event_t *event = (event_t *)&data[old & md->mask];
+	while ((event = perf_evlist__mmap_read(top->evlist, idx)) != NULL) {
+		ret = perf_evlist__parse_sample(top->evlist, event, &sample);
+		if (ret) {
+			pr_err("Can't parse sample, err = %d\n", ret);
+			goto next_event;
+		}
 
-		event_t event_copy;
+		evsel = perf_evlist__id2evsel(session->evlist, sample.id);
+		assert(evsel != NULL);
 
-		size_t size = event->header.size;
+		origin = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 
-		/*
-		 * Event straddles the mmap boundary -- header should always
-		 * be inside due to u64 alignment of output.
-		 */
-		if ((old & md->mask) + size != ((old + size) & md->mask)) {
-			unsigned int offset = old;
-			unsigned int len = min(sizeof(*event), size), cpy;
-			void *dst = &event_copy;
-
-			do {
-				cpy = min(md->mask + 1 - (offset & md->mask), len);
-				memcpy(dst, &data[offset & md->mask], cpy);
-				offset += cpy;
-				dst += cpy;
-				len -= cpy;
-			} while (len);
-
-			event = &event_copy;
+		if (event->header.type == PERF_RECORD_SAMPLE)
+			++top->samples;
+
+		switch (origin) {
+		case PERF_RECORD_MISC_USER:
+			++top->us_samples;
+			if (top->hide_user_symbols)
+				goto next_event;
+			machine = &session->machines.host;
+			break;
+		case PERF_RECORD_MISC_KERNEL:
+			++top->kernel_samples;
+			if (top->hide_kernel_symbols)
+				goto next_event;
+			machine = &session->machines.host;
+			break;
+		case PERF_RECORD_MISC_GUEST_KERNEL:
+			++top->guest_kernel_samples;
+			machine = perf_session__find_machine(session,
+							     sample.pid);
+			break;
+		case PERF_RECORD_MISC_GUEST_USER:
+			++top->guest_us_samples;
+			/*
+			 * TODO: we don't process guest user from host side
+			 * except simple counting.
+			 */
+			/* Fall thru */
+		default:
+			goto next_event;
 		}
 
-		if (event->header.type == PERF_RECORD_SAMPLE)
-			event__process_sample(event, self, md->counter);
-		else
-			event__process(event, self);
-		old += size;
-	}
 
-	md->prev = old;
+		if (event->header.type == PERF_RECORD_SAMPLE) {
+			perf_event__process_sample(&top->tool, event, evsel,
+						   &sample, machine);
+		} else if (event->header.type < PERF_RECORD_MAX) {
+			hists__inc_nr_events(&evsel->hists, event->header.type);
+			machine__process_event(machine, event, &sample);
+		} else
+			++session->stats.nr_unknown_events;
+next_event:
+		perf_evlist__mmap_consume(top->evlist, idx);
+	}
 }
 
-static struct pollfd *event_array;
-static struct mmap_data *mmap_array[MAX_NR_CPUS][MAX_COUNTERS];
-
-static void perf_session__mmap_read(struct perf_session *self)
+static void perf_top__mmap_read(struct perf_top *top)
 {
-	int i, counter, thread_index;
-
-	for (i = 0; i < nr_cpus; i++) {
-		for (counter = 0; counter < nr_counters; counter++)
-			for (thread_index = 0;
-				thread_index < thread_num;
-				thread_index++) {
-				perf_session__mmap_read_counter(self,
-					&mmap_array[i][counter][thread_index]);
-			}
-	}
-}
+	int i;
 
-int nr_poll;
-int group_fd;
+	for (i = 0; i < top->evlist->nr_mmaps; i++)
+		perf_top__mmap_read_idx(top, i);
+}
 
-static void start_counter(int i, int counter)
+static int perf_top__start_counters(struct perf_top *top)
 {
-	struct perf_event_attr *attr;
-	int cpu;
-	int thread_index;
+	char msg[512];
+	struct perf_evsel *counter;
+	struct perf_evlist *evlist = top->evlist;
+	struct record_opts *opts = &top->record_opts;
 
-	cpu = profile_cpu;
-	if (target_tid == -1 && profile_cpu == -1)
-		cpu = cpumap[i];
+	perf_evlist__config(evlist, opts);
 
-	attr = attrs + counter;
-
-	attr->sample_type	= PERF_SAMPLE_IP | PERF_SAMPLE_TID;
+	evlist__for_each(evlist, counter) {
+try_again:
+		if (perf_evsel__open(counter, top->evlist->cpus,
+				     top->evlist->threads) < 0) {
+			if (perf_evsel__fallback(counter, errno, msg, sizeof(msg))) {
+				if (verbose)
+					ui__warning("%s\n", msg);
+				goto try_again;
+			}
 
-	if (freq) {
-		attr->sample_type	|= PERF_SAMPLE_PERIOD;
-		attr->freq		= 1;
-		attr->sample_freq	= freq;
+			perf_evsel__open_strerror(counter, &opts->target,
+						  errno, msg, sizeof(msg));
+			ui__error("%s\n", msg);
+			goto out_err;
+		}
 	}
 
-	attr->inherit		= (cpu < 0) && inherit;
-	attr->mmap		= 1;
-
-	for (thread_index = 0; thread_index < thread_num; thread_index++) {
-try_again:
-		fd[i][counter][thread_index] = sys_perf_event_open(attr,
-				all_tids[thread_index], cpu, group_fd, 0);
-
-		if (fd[i][counter][thread_index] < 0) {
-			int err = errno;
+	if (perf_evlist__mmap(evlist, opts->mmap_pages, false) < 0) {
+		ui__error("Failed to mmap with %d (%s)\n",
+			    errno, strerror(errno));
+		goto out_err;
+	}
 
-			if (err == EPERM || err == EACCES)
-				die("No permission - are you root?\n");
-			/*
-			 * If it's cycles then fall back to hrtimer
-			 * based cpu-clock-tick sw counter, which
-			 * is always available even if no PMU support:
-			 */
-			if (attr->type == PERF_TYPE_HARDWARE
-					&& attr->config == PERF_COUNT_HW_CPU_CYCLES) {
+	return 0;
 
-				if (verbose)
-					warning(" ... trying to fall back to cpu-clock-ticks\n");
+out_err:
+	return -1;
+}
 
-				attr->type = PERF_TYPE_SOFTWARE;
-				attr->config = PERF_COUNT_SW_CPU_CLOCK;
-				goto try_again;
-			}
-			printf("\n");
-			error("perfcounter syscall returned with %d (%s)\n",
-					fd[i][counter][thread_index], strerror(err));
-			die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
-			exit(-1);
+static int perf_top__setup_sample_type(struct perf_top *top __maybe_unused)
+{
+	if (!sort__has_sym) {
+		if (symbol_conf.use_callchain) {
+			ui__error("Selected -g but \"sym\" not present in --sort/-s.");
+			return -EINVAL;
+		}
+	} else if (callchain_param.mode != CHAIN_NONE) {
+		if (callchain_register_param(&callchain_param) < 0) {
+			ui__error("Can't register callchain params.\n");
+			return -EINVAL;
 		}
-		assert(fd[i][counter][thread_index] >= 0);
-		fcntl(fd[i][counter][thread_index], F_SETFL, O_NONBLOCK);
-
-		/*
-		 * First counter acts as the group leader:
-		 */
-		if (group && group_fd == -1)
-			group_fd = fd[i][counter][thread_index];
-
-		event_array[nr_poll].fd = fd[i][counter][thread_index];
-		event_array[nr_poll].events = POLLIN;
-		nr_poll++;
-
-		mmap_array[i][counter][thread_index].counter = counter;
-		mmap_array[i][counter][thread_index].prev = 0;
-		mmap_array[i][counter][thread_index].mask = mmap_pages*page_size - 1;
-		mmap_array[i][counter][thread_index].base = mmap(NULL, (mmap_pages+1)*page_size,
-				PROT_READ, MAP_SHARED, fd[i][counter][thread_index], 0);
-		if (mmap_array[i][counter][thread_index].base == MAP_FAILED)
-			die("failed to mmap with %d (%s)\n", errno, strerror(errno));
 	}
+
+	return 0;
 }
 
-static int __cmd_top(void)
+static int __cmd_top(struct perf_top *top)
 {
+	struct record_opts *opts = &top->record_opts;
 	pthread_t thread;
-	int i, counter;
 	int ret;
-	/*
-	 * FIXME: perf_session__new should allow passing a O_MMAP, so that all this
-	 * mmap reading, etc is encapsulated in it. Use O_WRONLY for now.
-	 */
-	struct perf_session *session = perf_session__new(NULL, O_WRONLY, false, false);
-	if (session == NULL)
+
+	top->session = perf_session__new(NULL, false, NULL);
+	if (top->session == NULL)
 		return -ENOMEM;
 
-	if (target_tid != -1)
-		event__synthesize_thread(target_tid, event__process, session);
-	else
-		event__synthesize_threads(event__process, session);
+	machines__set_symbol_filter(&top->session->machines, symbol_filter);
 
-	for (i = 0; i < nr_cpus; i++) {
-		group_fd = -1;
-		for (counter = 0; counter < nr_counters; counter++)
-			start_counter(i, counter);
+	if (!objdump_path) {
+		ret = perf_session_env__lookup_objdump(&top->session->header.env);
+		if (ret)
+			goto out_delete;
 	}
 
+	ret = perf_top__setup_sample_type(top);
+	if (ret)
+		goto out_delete;
+
+	machine__synthesize_threads(&top->session->machines.host, &opts->target,
+				    top->evlist->threads, false);
+	ret = perf_top__start_counters(top);
+	if (ret)
+		goto out_delete;
+
+	top->session->evlist = top->evlist;
+	perf_session__set_id_hdr_size(top->session);
+
+	/*
+	 * When perf is starting the traced process, all the events (apart from
+	 * group members) have enable_on_exec=1 set, so don't spoil it by
+	 * prematurely enabling them.
+	 *
+	 * XXX 'top' still doesn't start workloads like record, trace, but should,
+	 * so leave the check here.
+	 */
+        if (!target__none(&opts->target))
+                perf_evlist__enable(top->evlist);
+
 	/* Wait for a minimal set of events before starting the snapshot */
-	poll(&event_array[0], nr_poll, 100);
+	poll(top->evlist->pollfd, top->evlist->nr_fds, 100);
 
-	perf_session__mmap_read(session);
+	perf_top__mmap_read(top);
 
-	if (pthread_create(&thread, NULL, display_thread, session)) {
-		printf("Could not create display thread.\n");
-		exit(-1);
+	ret = -1;
+	if (pthread_create(&thread, NULL, (use_browser > 0 ? display_thread_tui :
+							    display_thread), top)) {
+		ui__error("Could not create display thread.\n");
+		goto out_delete;
 	}
 
-	if (realtime_prio) {
+	if (top->realtime_prio) {
 		struct sched_param param;
 
-		param.sched_priority = realtime_prio;
+		param.sched_priority = top->realtime_prio;
 		if (sched_setscheduler(0, SCHED_FIFO, &param)) {
-			printf("Could not set realtime priority.\n");
-			exit(-1);
+			ui__error("Could not set realtime priority.\n");
+			goto out_delete;
 		}
 	}
 
-	while (1) {
-		int hits = samples;
+	while (!done) {
+		u64 hits = top->samples;
 
-		perf_session__mmap_read(session);
+		perf_top__mmap_read(top);
 
-		if (hits == samples)
-			ret = poll(event_array, nr_poll, 100);
+		if (hits == top->samples)
+			ret = poll(top->evlist->pollfd, top->evlist->nr_fds, 100);
 	}
 
-	return 0;
+	ret = 0;
+out_delete:
+	perf_session__delete(top->session);
+	top->session = NULL;
+
+	return ret;
+}
+
+static int
+callchain_opt(const struct option *opt, const char *arg, int unset)
+{
+	symbol_conf.use_callchain = true;
+	return record_callchain_opt(opt, arg, unset);
 }
 
-static const char * const top_usage[] = {
-	"perf top [<options>]",
-	NULL
-};
+static int
+parse_callchain_opt(const struct option *opt, const char *arg, int unset)
+{
+	symbol_conf.use_callchain = true;
+	return record_parse_callchain_opt(opt, arg, unset);
+}
+
+static int perf_top_config(const char *var, const char *value, void *cb)
+{
+	struct perf_top *top = cb;
 
-static const struct option options[] = {
-	OPT_CALLBACK('e', "event", NULL, "event",
+	if (!strcmp(var, "top.call-graph"))
+		return record_parse_callchain(value, &top->record_opts);
+	if (!strcmp(var, "top.children")) {
+		symbol_conf.cumulate_callchain = perf_config_bool(var, value);
+		return 0;
+	}
+
+	return perf_default_config(var, value, cb);
+}
+
+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 = -1;
+	char errbuf[BUFSIZ];
+	struct perf_top top = {
+		.count_filter	     = 5,
+		.delay_secs	     = 2,
+		.record_opts = {
+			.mmap_pages	= UINT_MAX,
+			.user_freq	= UINT_MAX,
+			.user_interval	= ULLONG_MAX,
+			.freq		= 4000, /* 4 KHz */
+			.target		= {
+				.uses_mmap   = true,
+			},
+		},
+		.max_stack	     = PERF_MAX_STACK_DEPTH,
+		.sym_pcnt_filter     = 5,
+	};
+	struct record_opts *opts = &top.record_opts;
+	struct target *target = &opts->target;
+	const struct option options[] = {
+	OPT_CALLBACK('e', "event", &top.evlist, "event",
 		     "event selector. use 'perf list' to list available events",
-		     parse_events),
-	OPT_INTEGER('c', "count", &default_interval,
-		    "event period to sample"),
-	OPT_INTEGER('p', "pid", &target_pid,
+		     parse_events_option),
+	OPT_U64('c', "count", &opts->user_interval, "event period to sample"),
+	OPT_STRING('p', "pid", &target->pid, "pid",
 		    "profile events on existing process id"),
-	OPT_INTEGER('t', "tid", &target_tid,
+	OPT_STRING('t', "tid", &target->tid, "tid",
 		    "profile events on existing thread id"),
-	OPT_BOOLEAN('a', "all-cpus", &system_wide,
+	OPT_BOOLEAN('a', "all-cpus", &target->system_wide,
 			    "system-wide collection from all CPUs"),
-	OPT_INTEGER('C', "CPU", &profile_cpu,
-		    "CPU to profile on"),
+	OPT_STRING('C', "cpu", &target->cpu_list, "cpu",
+		    "list of cpus to monitor"),
 	OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
 		   "file", "vmlinux pathname"),
-	OPT_BOOLEAN('K', "hide_kernel_symbols", &hide_kernel_symbols,
+	OPT_BOOLEAN(0, "ignore-vmlinux", &symbol_conf.ignore_vmlinux,
+		    "don't load vmlinux even if found"),
+	OPT_BOOLEAN('K', "hide_kernel_symbols", &top.hide_kernel_symbols,
 		    "hide kernel symbols"),
-	OPT_UINTEGER('m', "mmap-pages", &mmap_pages, "number of mmap data pages"),
-	OPT_INTEGER('r', "realtime", &realtime_prio,
+	OPT_CALLBACK('m', "mmap-pages", &opts->mmap_pages, "pages",
+		     "number of mmap data pages",
+		     perf_evlist__parse_mmap_pages),
+	OPT_INTEGER('r', "realtime", &top.realtime_prio,
 		    "collect data with this RT SCHED_FIFO priority"),
-	OPT_INTEGER('d', "delay", &delay_secs,
+	OPT_INTEGER('d', "delay", &top.delay_secs,
 		    "number of seconds to delay between refreshes"),
-	OPT_BOOLEAN('D', "dump-symtab", &dump_symtab,
+	OPT_BOOLEAN('D', "dump-symtab", &top.dump_symtab,
 			    "dump the symbol table used for profiling"),
-	OPT_INTEGER('f', "count-filter", &count_filter,
+	OPT_INTEGER('f', "count-filter", &top.count_filter,
 		    "only display functions with more events than this"),
-	OPT_BOOLEAN('g', "group", &group,
+	OPT_BOOLEAN(0, "group", &opts->group,
 			    "put the counters into a counter group"),
-	OPT_BOOLEAN('i', "inherit", &inherit,
-		    "child tasks inherit counters"),
-	OPT_STRING('s', "sym-annotate", &sym_filter, "symbol name",
+	OPT_BOOLEAN('i', "no-inherit", &opts->no_inherit,
+		    "child tasks do not inherit counters"),
+	OPT_STRING(0, "sym-annotate", &top.sym_filter, "symbol name",
 		    "symbol to annotate"),
-	OPT_BOOLEAN('z', "zero", &zero,
-		    "zero history across updates"),
-	OPT_INTEGER('F', "freq", &freq,
-		    "profile at this frequency"),
-	OPT_INTEGER('E', "entries", &print_entries,
+	OPT_BOOLEAN('z', "zero", &top.zero, "zero history across updates"),
+	OPT_UINTEGER('F', "freq", &opts->user_freq, "profile at this frequency"),
+	OPT_INTEGER('E', "entries", &top.print_entries,
 		    "display this many functions"),
-	OPT_BOOLEAN('U', "hide_user_symbols", &hide_user_symbols,
+	OPT_BOOLEAN('U', "hide_user_symbols", &top.hide_user_symbols,
 		    "hide user symbols"),
+	OPT_BOOLEAN(0, "tui", &top.use_tui, "Use the TUI interface"),
+	OPT_BOOLEAN(0, "stdio", &top.use_stdio, "Use the stdio interface"),
 	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose (show counter open errors, etc)"),
+	OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
+		   "sort by key(s): pid, comm, dso, symbol, parent, cpu, srcline, ..."
+		   " Please refer the man page for the complete list."),
+	OPT_STRING(0, "fields", &field_order, "key[,keys...]",
+		   "output field(s): overhead, period, sample plus all of sort keys"),
+	OPT_BOOLEAN('n', "show-nr-samples", &symbol_conf.show_nr_samples,
+		    "Show a column with the number of samples"),
+	OPT_CALLBACK_NOOPT('g', NULL, &top.record_opts,
+			   NULL, "enables call-graph recording",
+			   &callchain_opt),
+	OPT_CALLBACK(0, "call-graph", &top.record_opts,
+		     "mode[,dump_size]", record_callchain_help,
+		     &parse_callchain_opt),
+	OPT_BOOLEAN(0, "children", &symbol_conf.cumulate_callchain,
+		    "Accumulate callchains of children and show total overhead as well"),
+	OPT_INTEGER(0, "max-stack", &top.max_stack,
+		    "Set the maximum stack depth when parsing the callchain. "
+		    "Default: " __stringify(PERF_MAX_STACK_DEPTH)),
+	OPT_CALLBACK(0, "ignore-callees", NULL, "regex",
+		   "ignore callees of these functions in call graphs",
+		   report_parse_ignore_callees_opt),
+	OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period,
+		    "Show a column with the sum of periods"),
+	OPT_STRING(0, "dsos", &symbol_conf.dso_list_str, "dso[,dso...]",
+		   "only consider symbols in these dsos"),
+	OPT_STRING(0, "comms", &symbol_conf.comm_list_str, "comm[,comm...]",
+		   "only consider symbols in these comms"),
+	OPT_STRING(0, "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]",
+		   "only consider these symbols"),
+	OPT_BOOLEAN(0, "source", &symbol_conf.annotate_src,
+		    "Interleave source code with assembly code (default)"),
+	OPT_BOOLEAN(0, "asm-raw", &symbol_conf.annotate_asm_raw,
+		    "Display raw encoding of assembly instructions (default)"),
+	OPT_STRING(0, "objdump", &objdump_path, "path",
+		    "objdump binary to use for disassembly and annotations"),
+	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_CALLBACK(0, "percentage", NULL, "relative|absolute",
+		     "How to display percentage of filtered entries", parse_filter_percentage),
 	OPT_END()
-};
-
-int cmd_top(int argc, const char **argv, const char *prefix __used)
-{
-	int counter;
-	int i,j;
+	};
+	const char * const top_usage[] = {
+		"perf top [<options>]",
+		NULL
+	};
+
+	top.evlist = perf_evlist__new();
+	if (top.evlist == NULL)
+		return -ENOMEM;
 
-	page_size = sysconf(_SC_PAGE_SIZE);
+	perf_config(perf_top_config, &top);
 
 	argc = parse_options(argc, argv, options, top_usage, 0);
 	if (argc)
 		usage_with_options(top_usage, options);
 
-	if (target_pid != -1) {
-		target_tid = target_pid;
-		thread_num = find_all_tid(target_pid, &all_tids);
-		if (thread_num <= 0) {
-			fprintf(stderr, "Can't find all threads of pid %d\n",
-				target_pid);
-			usage_with_options(top_usage, options);
-		}
-	} else {
-		all_tids=malloc(sizeof(pid_t));
-		if (!all_tids)
-			return -ENOMEM;
-
-		all_tids[0] = target_tid;
-		thread_num = 1;
+	sort__mode = SORT_MODE__TOP;
+	/* display thread wants entries to be collapsed in a different tree */
+	sort__need_collapse = 1;
+
+	if (setup_sorting() < 0) {
+		if (sort_order)
+			parse_options_usage(top_usage, options, "s", 1);
+		if (field_order)
+			parse_options_usage(sort_order ? NULL : top_usage,
+					    options, "fields", 0);
+		goto out_delete_evlist;
 	}
 
-	for (i = 0; i < MAX_NR_CPUS; i++) {
-		for (j = 0; j < MAX_COUNTERS; j++) {
-			fd[i][j] = malloc(sizeof(int)*thread_num);
-			mmap_array[i][j] = zalloc(
-				sizeof(struct mmap_data)*thread_num);
-			if (!fd[i][j] || !mmap_array[i][j])
-				return -ENOMEM;
-		}
+	if (top.use_stdio)
+		use_browser = 0;
+	else if (top.use_tui)
+		use_browser = 1;
+
+	setup_browser(false);
+
+	status = target__validate(target);
+	if (status) {
+		target__strerror(target, status, errbuf, BUFSIZ);
+		ui__warning("%s\n", errbuf);
 	}
-	event_array = malloc(
-		sizeof(struct pollfd)*MAX_NR_CPUS*MAX_COUNTERS*thread_num);
-	if (!event_array)
-		return -ENOMEM;
 
-	/* CPU and PID are mutually exclusive */
-	if (target_tid > 0 && profile_cpu != -1) {
-		printf("WARNING: PID switch overriding CPU\n");
-		sleep(1);
-		profile_cpu = -1;
+	status = target__parse_uid(target);
+	if (status) {
+		int saved_errno = errno;
+
+		target__strerror(target, status, errbuf, BUFSIZ);
+		ui__error("%s\n", errbuf);
+
+		status = -saved_errno;
+		goto out_delete_evlist;
 	}
 
-	if (!nr_counters)
-		nr_counters = 1;
+	if (target__none(target))
+		target->system_wide = true;
 
-	symbol_conf.priv_size = (sizeof(struct sym_entry) +
-				 (nr_counters + 1) * sizeof(unsigned long));
+	if (perf_evlist__create_maps(top.evlist, target) < 0)
+		usage_with_options(top_usage, options);
 
-	symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);
-	if (symbol__init() < 0)
-		return -1;
+	if (!top.evlist->nr_entries &&
+	    perf_evlist__add_default(top.evlist) < 0) {
+		ui__error("Not enough memory for event selector list\n");
+		goto out_delete_evlist;
+	}
 
-	if (delay_secs < 1)
-		delay_secs = 1;
+	symbol_conf.nr_events = top.evlist->nr_entries;
 
-	/*
-	 * User specified count overrides default frequency.
-	 */
-	if (default_interval)
-		freq = 0;
-	else if (freq) {
-		default_interval = freq;
-	} else {
-		fprintf(stderr, "frequency and count are zero, aborting\n");
-		exit(EXIT_FAILURE);
+	if (top.delay_secs < 1)
+		top.delay_secs = 1;
+
+	if (record_opts__config(opts)) {
+		status = -EINVAL;
+		goto out_delete_evlist;
 	}
 
-	/*
-	 * Fill in the ones not specifically initialized via -c:
-	 */
-	for (counter = 0; counter < nr_counters; counter++) {
-		if (attrs[counter].sample_period)
-			continue;
+	top.sym_evsel = perf_evlist__first(top.evlist);
 
-		attrs[counter].sample_period = default_interval;
+	if (!symbol_conf.use_callchain) {
+		symbol_conf.cumulate_callchain = false;
+		perf_hpp__cancel_cumulate();
 	}
 
-	if (target_tid != -1 || profile_cpu != -1)
-		nr_cpus = 1;
-	else
-		nr_cpus = read_cpu_map();
+	symbol_conf.priv_size = sizeof(struct annotation);
+
+	symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);
+	if (symbol__init() < 0)
+		return -1;
+
+	sort__setup_elide(stdout);
 
-	get_term_dimensions(&winsize);
-	if (print_entries == 0) {
-		update_print_entries(&winsize);
-		signal(SIGWINCH, sig_winch_handler);
+	get_term_dimensions(&top.winsize);
+	if (top.print_entries == 0) {
+		struct sigaction act = {
+			.sa_sigaction = perf_top__sig_winch,
+			.sa_flags     = SA_SIGINFO,
+		};
+		perf_top__update_print_entries(&top);
+		sigaction(SIGWINCH, &act, NULL);
 	}
 
-	return __cmd_top();
+	status = __cmd_top(&top);
+
+out_delete_evlist:
+	perf_evlist__delete(top.evlist);
+
+	return status;
 }
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index dddf3f01b5a..f954c26de23 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1,717 +1,2397 @@
+#include <traceevent/event-parse.h>
 #include "builtin.h"
-
-#include "util/util.h"
-#include "util/cache.h"
-#include "util/symbol.h"
-#include "util/thread.h"
-#include "util/header.h"
-#include "util/exec_cmd.h"
-#include "util/trace-event.h"
+#include "util/color.h"
+#include "util/debug.h"
+#include "util/evlist.h"
+#include "util/machine.h"
 #include "util/session.h"
+#include "util/thread.h"
+#include "util/parse-options.h"
+#include "util/strlist.h"
+#include "util/intlist.h"
+#include "util/thread_map.h"
+#include "util/stat.h"
+#include "trace-event.h"
+#include "util/parse-events.h"
+
+#include <libaudit.h>
+#include <stdlib.h>
+#include <sys/eventfd.h>
+#include <sys/mman.h>
+#include <linux/futex.h>
+
+/* For older distros: */
+#ifndef MAP_STACK
+# define MAP_STACK		0x20000
+#endif
+
+#ifndef MADV_HWPOISON
+# define MADV_HWPOISON		100
+#endif
+
+#ifndef MADV_MERGEABLE
+# define MADV_MERGEABLE		12
+#endif
+
+#ifndef MADV_UNMERGEABLE
+# define MADV_UNMERGEABLE	13
+#endif
+
+#ifndef EFD_SEMAPHORE
+# define EFD_SEMAPHORE		1
+#endif
+
+struct tp_field {
+	int offset;
+	union {
+		u64 (*integer)(struct tp_field *field, struct perf_sample *sample);
+		void *(*pointer)(struct tp_field *field, struct perf_sample *sample);
+	};
+};
+
+#define TP_UINT_FIELD(bits) \
+static u64 tp_field__u##bits(struct tp_field *field, struct perf_sample *sample) \
+{ \
+	return *(u##bits *)(sample->raw_data + field->offset); \
+}
 
-static char const		*script_name;
-static char const		*generate_script_lang;
-static bool			debug_ordering;
-static u64			last_timestamp;
+TP_UINT_FIELD(8);
+TP_UINT_FIELD(16);
+TP_UINT_FIELD(32);
+TP_UINT_FIELD(64);
 
-static int default_start_script(const char *script __unused,
-				int argc __unused,
-				const char **argv __unused)
+#define TP_UINT_FIELD__SWAPPED(bits) \
+static u64 tp_field__swapped_u##bits(struct tp_field *field, struct perf_sample *sample) \
+{ \
+	u##bits value = *(u##bits *)(sample->raw_data + field->offset); \
+	return bswap_##bits(value);\
+}
+
+TP_UINT_FIELD__SWAPPED(16);
+TP_UINT_FIELD__SWAPPED(32);
+TP_UINT_FIELD__SWAPPED(64);
+
+static int tp_field__init_uint(struct tp_field *field,
+			       struct format_field *format_field,
+			       bool needs_swap)
 {
+	field->offset = format_field->offset;
+
+	switch (format_field->size) {
+	case 1:
+		field->integer = tp_field__u8;
+		break;
+	case 2:
+		field->integer = needs_swap ? tp_field__swapped_u16 : tp_field__u16;
+		break;
+	case 4:
+		field->integer = needs_swap ? tp_field__swapped_u32 : tp_field__u32;
+		break;
+	case 8:
+		field->integer = needs_swap ? tp_field__swapped_u64 : tp_field__u64;
+		break;
+	default:
+		return -1;
+	}
+
 	return 0;
 }
 
-static int default_stop_script(void)
+static void *tp_field__ptr(struct tp_field *field, struct perf_sample *sample)
 {
-	return 0;
+	return sample->raw_data + field->offset;
 }
 
-static int default_generate_script(const char *outfile __unused)
+static int tp_field__init_ptr(struct tp_field *field, struct format_field *format_field)
 {
+	field->offset = format_field->offset;
+	field->pointer = tp_field__ptr;
 	return 0;
 }
 
-static struct scripting_ops default_scripting_ops = {
-	.start_script		= default_start_script,
-	.stop_script		= default_stop_script,
-	.process_event		= print_event,
-	.generate_script	= default_generate_script,
+struct syscall_tp {
+	struct tp_field id;
+	union {
+		struct tp_field args, ret;
+	};
 };
 
-static struct scripting_ops	*scripting_ops;
+static int perf_evsel__init_tp_uint_field(struct perf_evsel *evsel,
+					  struct tp_field *field,
+					  const char *name)
+{
+	struct format_field *format_field = perf_evsel__field(evsel, name);
 
-static void setup_scripting(void)
+	if (format_field == NULL)
+		return -1;
+
+	return tp_field__init_uint(field, format_field, evsel->needs_swap);
+}
+
+#define perf_evsel__init_sc_tp_uint_field(evsel, name) \
+	({ struct syscall_tp *sc = evsel->priv;\
+	   perf_evsel__init_tp_uint_field(evsel, &sc->name, #name); })
+
+static int perf_evsel__init_tp_ptr_field(struct perf_evsel *evsel,
+					 struct tp_field *field,
+					 const char *name)
 {
-	/* make sure PERF_EXEC_PATH is set for scripts */
-	perf_set_argv_exec_path(perf_exec_path());
+	struct format_field *format_field = perf_evsel__field(evsel, name);
 
-	setup_perl_scripting();
-	setup_python_scripting();
+	if (format_field == NULL)
+		return -1;
 
-	scripting_ops = &default_scripting_ops;
+	return tp_field__init_ptr(field, format_field);
 }
 
-static int cleanup_scripting(void)
+#define perf_evsel__init_sc_tp_ptr_field(evsel, name) \
+	({ struct syscall_tp *sc = evsel->priv;\
+	   perf_evsel__init_tp_ptr_field(evsel, &sc->name, #name); })
+
+static void perf_evsel__delete_priv(struct perf_evsel *evsel)
 {
-	pr_debug("\nperf trace script stopped\n");
+	zfree(&evsel->priv);
+	perf_evsel__delete(evsel);
+}
 
-	return scripting_ops->stop_script();
+static int perf_evsel__init_syscall_tp(struct perf_evsel *evsel, void *handler)
+{
+	evsel->priv = malloc(sizeof(struct syscall_tp));
+	if (evsel->priv != NULL) {
+		if (perf_evsel__init_sc_tp_uint_field(evsel, id))
+			goto out_delete;
+
+		evsel->handler = handler;
+		return 0;
+	}
+
+	return -ENOMEM;
+
+out_delete:
+	zfree(&evsel->priv);
+	return -ENOENT;
 }
 
-#include "util/parse-options.h"
+static struct perf_evsel *perf_evsel__syscall_newtp(const char *direction, void *handler)
+{
+	struct perf_evsel *evsel = perf_evsel__newtp("raw_syscalls", direction);
 
-#include "perf.h"
-#include "util/debug.h"
+	/* older kernel (e.g., RHEL6) use syscalls:{enter,exit} */
+	if (evsel == NULL)
+		evsel = perf_evsel__newtp("syscalls", direction);
+
+	if (evsel) {
+		if (perf_evsel__init_syscall_tp(evsel, handler))
+			goto out_delete;
+	}
+
+	return evsel;
 
-#include "util/trace-event.h"
-#include "util/exec_cmd.h"
+out_delete:
+	perf_evsel__delete_priv(evsel);
+	return NULL;
+}
 
-static char const		*input_name = "perf.data";
+#define perf_evsel__sc_tp_uint(evsel, name, sample) \
+	({ struct syscall_tp *fields = evsel->priv; \
+	   fields->name.integer(&fields->name, sample); })
 
-static int process_sample_event(event_t *event, struct perf_session *session)
+#define perf_evsel__sc_tp_ptr(evsel, name, sample) \
+	({ struct syscall_tp *fields = evsel->priv; \
+	   fields->name.pointer(&fields->name, sample); })
+
+static int perf_evlist__add_syscall_newtp(struct perf_evlist *evlist,
+					  void *sys_enter_handler,
+					  void *sys_exit_handler)
 {
-	struct sample_data data;
+	int ret = -1;
+	struct perf_evsel *sys_enter, *sys_exit;
+
+	sys_enter = perf_evsel__syscall_newtp("sys_enter", sys_enter_handler);
+	if (sys_enter == NULL)
+		goto out;
+
+	if (perf_evsel__init_sc_tp_ptr_field(sys_enter, args))
+		goto out_delete_sys_enter;
+
+	sys_exit = perf_evsel__syscall_newtp("sys_exit", sys_exit_handler);
+	if (sys_exit == NULL)
+		goto out_delete_sys_enter;
+
+	if (perf_evsel__init_sc_tp_uint_field(sys_exit, ret))
+		goto out_delete_sys_exit;
+
+	perf_evlist__add(evlist, sys_enter);
+	perf_evlist__add(evlist, sys_exit);
+
+	ret = 0;
+out:
+	return ret;
+
+out_delete_sys_exit:
+	perf_evsel__delete_priv(sys_exit);
+out_delete_sys_enter:
+	perf_evsel__delete_priv(sys_enter);
+	goto out;
+}
+
+
+struct syscall_arg {
+	unsigned long val;
 	struct thread *thread;
+	struct trace  *trace;
+	void	      *parm;
+	u8	      idx;
+	u8	      mask;
+};
 
-	memset(&data, 0, sizeof(data));
-	data.time = -1;
-	data.cpu = -1;
-	data.period = 1;
+struct strarray {
+	int	    offset;
+	int	    nr_entries;
+	const char **entries;
+};
 
-	event__parse_sample(event, session->sample_type, &data);
+#define DEFINE_STRARRAY(array) struct strarray strarray__##array = { \
+	.nr_entries = ARRAY_SIZE(array), \
+	.entries = array, \
+}
 
-	dump_printf("(IP, %d): %d/%d: %#Lx period: %Ld\n", event->header.misc,
-		    data.pid, data.tid, data.ip, data.period);
+#define DEFINE_STRARRAY_OFFSET(array, off) struct strarray strarray__##array = { \
+	.offset	    = off, \
+	.nr_entries = ARRAY_SIZE(array), \
+	.entries = array, \
+}
 
-	thread = perf_session__findnew(session, event->ip.pid);
-	if (thread == NULL) {
-		pr_debug("problem processing %d event, skipping it.\n",
-			 event->header.type);
-		return -1;
+static size_t __syscall_arg__scnprintf_strarray(char *bf, size_t size,
+						const char *intfmt,
+					        struct syscall_arg *arg)
+{
+	struct strarray *sa = arg->parm;
+	int idx = arg->val - sa->offset;
+
+	if (idx < 0 || idx >= sa->nr_entries)
+		return scnprintf(bf, size, intfmt, arg->val);
+
+	return scnprintf(bf, size, "%s", sa->entries[idx]);
+}
+
+static size_t syscall_arg__scnprintf_strarray(char *bf, size_t size,
+					      struct syscall_arg *arg)
+{
+	return __syscall_arg__scnprintf_strarray(bf, size, "%d", arg);
+}
+
+#define SCA_STRARRAY syscall_arg__scnprintf_strarray
+
+#if defined(__i386__) || defined(__x86_64__)
+/*
+ * FIXME: Make this available to all arches as soon as the ioctl beautifier
+ * 	  gets rewritten to support all arches.
+ */
+static size_t syscall_arg__scnprintf_strhexarray(char *bf, size_t size,
+						 struct syscall_arg *arg)
+{
+	return __syscall_arg__scnprintf_strarray(bf, size, "%#x", arg);
+}
+
+#define SCA_STRHEXARRAY syscall_arg__scnprintf_strhexarray
+#endif /* defined(__i386__) || defined(__x86_64__) */
+
+static size_t syscall_arg__scnprintf_fd(char *bf, size_t size,
+					struct syscall_arg *arg);
+
+#define SCA_FD syscall_arg__scnprintf_fd
+
+static size_t syscall_arg__scnprintf_fd_at(char *bf, size_t size,
+					   struct syscall_arg *arg)
+{
+	int fd = arg->val;
+
+	if (fd == AT_FDCWD)
+		return scnprintf(bf, size, "CWD");
+
+	return syscall_arg__scnprintf_fd(bf, size, arg);
+}
+
+#define SCA_FDAT syscall_arg__scnprintf_fd_at
+
+static size_t syscall_arg__scnprintf_close_fd(char *bf, size_t size,
+					      struct syscall_arg *arg);
+
+#define SCA_CLOSE_FD syscall_arg__scnprintf_close_fd
+
+static size_t syscall_arg__scnprintf_hex(char *bf, size_t size,
+					 struct syscall_arg *arg)
+{
+	return scnprintf(bf, size, "%#lx", arg->val);
+}
+
+#define SCA_HEX syscall_arg__scnprintf_hex
+
+static size_t syscall_arg__scnprintf_mmap_prot(char *bf, size_t size,
+					       struct syscall_arg *arg)
+{
+	int printed = 0, prot = arg->val;
+
+	if (prot == PROT_NONE)
+		return scnprintf(bf, size, "NONE");
+#define	P_MMAP_PROT(n) \
+	if (prot & PROT_##n) { \
+		printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
+		prot &= ~PROT_##n; \
 	}
 
-	if (session->sample_type & PERF_SAMPLE_RAW) {
-		if (debug_ordering) {
-			if (data.time < last_timestamp) {
-				pr_err("Samples misordered, previous: %llu "
-					"this: %llu\n", last_timestamp,
-					data.time);
-			}
-			last_timestamp = data.time;
-		}
-		/*
-		 * FIXME: better resolve from pid from the struct trace_entry
-		 * field, although it should be the same than this perf
-		 * event pid
-		 */
-		scripting_ops->process_event(data.cpu, data.raw_data,
-					     data.raw_size,
-					     data.time, thread->comm);
+	P_MMAP_PROT(EXEC);
+	P_MMAP_PROT(READ);
+	P_MMAP_PROT(WRITE);
+#ifdef PROT_SEM
+	P_MMAP_PROT(SEM);
+#endif
+	P_MMAP_PROT(GROWSDOWN);
+	P_MMAP_PROT(GROWSUP);
+#undef P_MMAP_PROT
+
+	if (prot)
+		printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", prot);
+
+	return printed;
+}
+
+#define SCA_MMAP_PROT syscall_arg__scnprintf_mmap_prot
+
+static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size,
+						struct syscall_arg *arg)
+{
+	int printed = 0, flags = arg->val;
+
+#define	P_MMAP_FLAG(n) \
+	if (flags & MAP_##n) { \
+		printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
+		flags &= ~MAP_##n; \
 	}
 
-	session->hists.stats.total_period += data.period;
-	return 0;
+	P_MMAP_FLAG(SHARED);
+	P_MMAP_FLAG(PRIVATE);
+#ifdef MAP_32BIT
+	P_MMAP_FLAG(32BIT);
+#endif
+	P_MMAP_FLAG(ANONYMOUS);
+	P_MMAP_FLAG(DENYWRITE);
+	P_MMAP_FLAG(EXECUTABLE);
+	P_MMAP_FLAG(FILE);
+	P_MMAP_FLAG(FIXED);
+	P_MMAP_FLAG(GROWSDOWN);
+#ifdef MAP_HUGETLB
+	P_MMAP_FLAG(HUGETLB);
+#endif
+	P_MMAP_FLAG(LOCKED);
+	P_MMAP_FLAG(NONBLOCK);
+	P_MMAP_FLAG(NORESERVE);
+	P_MMAP_FLAG(POPULATE);
+	P_MMAP_FLAG(STACK);
+#ifdef MAP_UNINITIALIZED
+	P_MMAP_FLAG(UNINITIALIZED);
+#endif
+#undef P_MMAP_FLAG
+
+	if (flags)
+		printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
+
+	return printed;
 }
 
-static struct perf_event_ops event_ops = {
-	.sample	= process_sample_event,
-	.comm	= event__process_comm,
-	.attr	= event__process_attr,
-	.event_type = event__process_event_type,
-	.tracing_data = event__process_tracing_data,
-	.build_id = event__process_build_id,
-	.ordered_samples = true,
-};
+#define SCA_MMAP_FLAGS syscall_arg__scnprintf_mmap_flags
+
+static size_t syscall_arg__scnprintf_madvise_behavior(char *bf, size_t size,
+						      struct syscall_arg *arg)
+{
+	int behavior = arg->val;
+
+	switch (behavior) {
+#define	P_MADV_BHV(n) case MADV_##n: return scnprintf(bf, size, #n)
+	P_MADV_BHV(NORMAL);
+	P_MADV_BHV(RANDOM);
+	P_MADV_BHV(SEQUENTIAL);
+	P_MADV_BHV(WILLNEED);
+	P_MADV_BHV(DONTNEED);
+	P_MADV_BHV(REMOVE);
+	P_MADV_BHV(DONTFORK);
+	P_MADV_BHV(DOFORK);
+	P_MADV_BHV(HWPOISON);
+#ifdef MADV_SOFT_OFFLINE
+	P_MADV_BHV(SOFT_OFFLINE);
+#endif
+	P_MADV_BHV(MERGEABLE);
+	P_MADV_BHV(UNMERGEABLE);
+#ifdef MADV_HUGEPAGE
+	P_MADV_BHV(HUGEPAGE);
+#endif
+#ifdef MADV_NOHUGEPAGE
+	P_MADV_BHV(NOHUGEPAGE);
+#endif
+#ifdef MADV_DONTDUMP
+	P_MADV_BHV(DONTDUMP);
+#endif
+#ifdef MADV_DODUMP
+	P_MADV_BHV(DODUMP);
+#endif
+#undef P_MADV_PHV
+	default: break;
+	}
+
+	return scnprintf(bf, size, "%#x", behavior);
+}
 
-extern volatile int session_done;
+#define SCA_MADV_BHV syscall_arg__scnprintf_madvise_behavior
 
-static void sig_handler(int sig __unused)
+static size_t syscall_arg__scnprintf_flock(char *bf, size_t size,
+					   struct syscall_arg *arg)
 {
-	session_done = 1;
+	int printed = 0, op = arg->val;
+
+	if (op == 0)
+		return scnprintf(bf, size, "NONE");
+#define	P_CMD(cmd) \
+	if ((op & LOCK_##cmd) == LOCK_##cmd) { \
+		printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #cmd); \
+		op &= ~LOCK_##cmd; \
+	}
+
+	P_CMD(SH);
+	P_CMD(EX);
+	P_CMD(NB);
+	P_CMD(UN);
+	P_CMD(MAND);
+	P_CMD(RW);
+	P_CMD(READ);
+	P_CMD(WRITE);
+#undef P_OP
+
+	if (op)
+		printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", op);
+
+	return printed;
 }
 
-static int __cmd_trace(struct perf_session *session)
+#define SCA_FLOCK syscall_arg__scnprintf_flock
+
+static size_t syscall_arg__scnprintf_futex_op(char *bf, size_t size, struct syscall_arg *arg)
 {
-	signal(SIGINT, sig_handler);
+	enum syscall_futex_args {
+		SCF_UADDR   = (1 << 0),
+		SCF_OP	    = (1 << 1),
+		SCF_VAL	    = (1 << 2),
+		SCF_TIMEOUT = (1 << 3),
+		SCF_UADDR2  = (1 << 4),
+		SCF_VAL3    = (1 << 5),
+	};
+	int op = arg->val;
+	int cmd = op & FUTEX_CMD_MASK;
+	size_t printed = 0;
+
+	switch (cmd) {
+#define	P_FUTEX_OP(n) case FUTEX_##n: printed = scnprintf(bf, size, #n);
+	P_FUTEX_OP(WAIT);	    arg->mask |= SCF_VAL3|SCF_UADDR2;		  break;
+	P_FUTEX_OP(WAKE);	    arg->mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break;
+	P_FUTEX_OP(FD);		    arg->mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break;
+	P_FUTEX_OP(REQUEUE);	    arg->mask |= SCF_VAL3|SCF_TIMEOUT;	          break;
+	P_FUTEX_OP(CMP_REQUEUE);    arg->mask |= SCF_TIMEOUT;			  break;
+	P_FUTEX_OP(CMP_REQUEUE_PI); arg->mask |= SCF_TIMEOUT;			  break;
+	P_FUTEX_OP(WAKE_OP);							  break;
+	P_FUTEX_OP(LOCK_PI);	    arg->mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break;
+	P_FUTEX_OP(UNLOCK_PI);	    arg->mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break;
+	P_FUTEX_OP(TRYLOCK_PI);	    arg->mask |= SCF_VAL3|SCF_UADDR2;		  break;
+	P_FUTEX_OP(WAIT_BITSET);    arg->mask |= SCF_UADDR2;			  break;
+	P_FUTEX_OP(WAKE_BITSET);    arg->mask |= SCF_UADDR2;			  break;
+	P_FUTEX_OP(WAIT_REQUEUE_PI);						  break;
+	default: printed = scnprintf(bf, size, "%#x", cmd);			  break;
+	}
 
-	return perf_session__process_events(session, &event_ops);
+	if (op & FUTEX_PRIVATE_FLAG)
+		printed += scnprintf(bf + printed, size - printed, "|PRIV");
+
+	if (op & FUTEX_CLOCK_REALTIME)
+		printed += scnprintf(bf + printed, size - printed, "|CLKRT");
+
+	return printed;
 }
 
-struct script_spec {
-	struct list_head	node;
-	struct scripting_ops	*ops;
-	char			spec[0];
+#define SCA_FUTEX_OP  syscall_arg__scnprintf_futex_op
+
+static const char *epoll_ctl_ops[] = { "ADD", "DEL", "MOD", };
+static DEFINE_STRARRAY_OFFSET(epoll_ctl_ops, 1);
+
+static const char *itimers[] = { "REAL", "VIRTUAL", "PROF", };
+static DEFINE_STRARRAY(itimers);
+
+static const char *whences[] = { "SET", "CUR", "END",
+#ifdef SEEK_DATA
+"DATA",
+#endif
+#ifdef SEEK_HOLE
+"HOLE",
+#endif
+};
+static DEFINE_STRARRAY(whences);
+
+static const char *fcntl_cmds[] = {
+	"DUPFD", "GETFD", "SETFD", "GETFL", "SETFL", "GETLK", "SETLK",
+	"SETLKW", "SETOWN", "GETOWN", "SETSIG", "GETSIG", "F_GETLK64",
+	"F_SETLK64", "F_SETLKW64", "F_SETOWN_EX", "F_GETOWN_EX",
+	"F_GETOWNER_UIDS",
 };
+static DEFINE_STRARRAY(fcntl_cmds);
 
-LIST_HEAD(script_specs);
+static const char *rlimit_resources[] = {
+	"CPU", "FSIZE", "DATA", "STACK", "CORE", "RSS", "NPROC", "NOFILE",
+	"MEMLOCK", "AS", "LOCKS", "SIGPENDING", "MSGQUEUE", "NICE", "RTPRIO",
+	"RTTIME",
+};
+static DEFINE_STRARRAY(rlimit_resources);
 
-static struct script_spec *script_spec__new(const char *spec,
-					    struct scripting_ops *ops)
+static const char *sighow[] = { "BLOCK", "UNBLOCK", "SETMASK", };
+static DEFINE_STRARRAY(sighow);
+
+static const char *clockid[] = {
+	"REALTIME", "MONOTONIC", "PROCESS_CPUTIME_ID", "THREAD_CPUTIME_ID",
+	"MONOTONIC_RAW", "REALTIME_COARSE", "MONOTONIC_COARSE",
+};
+static DEFINE_STRARRAY(clockid);
+
+static const char *socket_families[] = {
+	"UNSPEC", "LOCAL", "INET", "AX25", "IPX", "APPLETALK", "NETROM",
+	"BRIDGE", "ATMPVC", "X25", "INET6", "ROSE", "DECnet", "NETBEUI",
+	"SECURITY", "KEY", "NETLINK", "PACKET", "ASH", "ECONET", "ATMSVC",
+	"RDS", "SNA", "IRDA", "PPPOX", "WANPIPE", "LLC", "IB", "CAN", "TIPC",
+	"BLUETOOTH", "IUCV", "RXRPC", "ISDN", "PHONET", "IEEE802154", "CAIF",
+	"ALG", "NFC", "VSOCK",
+};
+static DEFINE_STRARRAY(socket_families);
+
+#ifndef SOCK_TYPE_MASK
+#define SOCK_TYPE_MASK 0xf
+#endif
+
+static size_t syscall_arg__scnprintf_socket_type(char *bf, size_t size,
+						      struct syscall_arg *arg)
 {
-	struct script_spec *s = malloc(sizeof(*s) + strlen(spec) + 1);
+	size_t printed;
+	int type = arg->val,
+	    flags = type & ~SOCK_TYPE_MASK;
+
+	type &= SOCK_TYPE_MASK;
+	/*
+ 	 * Can't use a strarray, MIPS may override for ABI reasons.
+ 	 */
+	switch (type) {
+#define	P_SK_TYPE(n) case SOCK_##n: printed = scnprintf(bf, size, #n); break;
+	P_SK_TYPE(STREAM);
+	P_SK_TYPE(DGRAM);
+	P_SK_TYPE(RAW);
+	P_SK_TYPE(RDM);
+	P_SK_TYPE(SEQPACKET);
+	P_SK_TYPE(DCCP);
+	P_SK_TYPE(PACKET);
+#undef P_SK_TYPE
+	default:
+		printed = scnprintf(bf, size, "%#x", type);
+	}
 
-	if (s != NULL) {
-		strcpy(s->spec, spec);
-		s->ops = ops;
+#define	P_SK_FLAG(n) \
+	if (flags & SOCK_##n) { \
+		printed += scnprintf(bf + printed, size - printed, "|%s", #n); \
+		flags &= ~SOCK_##n; \
 	}
 
-	return s;
+	P_SK_FLAG(CLOEXEC);
+	P_SK_FLAG(NONBLOCK);
+#undef P_SK_FLAG
+
+	if (flags)
+		printed += scnprintf(bf + printed, size - printed, "|%#x", flags);
+
+	return printed;
 }
 
-static void script_spec__delete(struct script_spec *s)
+#define SCA_SK_TYPE syscall_arg__scnprintf_socket_type
+
+#ifndef MSG_PROBE
+#define MSG_PROBE	     0x10
+#endif
+#ifndef MSG_WAITFORONE
+#define MSG_WAITFORONE	0x10000
+#endif
+#ifndef MSG_SENDPAGE_NOTLAST
+#define MSG_SENDPAGE_NOTLAST 0x20000
+#endif
+#ifndef MSG_FASTOPEN
+#define MSG_FASTOPEN	     0x20000000
+#endif
+
+static size_t syscall_arg__scnprintf_msg_flags(char *bf, size_t size,
+					       struct syscall_arg *arg)
 {
-	free(s->spec);
-	free(s);
+	int printed = 0, flags = arg->val;
+
+	if (flags == 0)
+		return scnprintf(bf, size, "NONE");
+#define	P_MSG_FLAG(n) \
+	if (flags & MSG_##n) { \
+		printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
+		flags &= ~MSG_##n; \
+	}
+
+	P_MSG_FLAG(OOB);
+	P_MSG_FLAG(PEEK);
+	P_MSG_FLAG(DONTROUTE);
+	P_MSG_FLAG(TRYHARD);
+	P_MSG_FLAG(CTRUNC);
+	P_MSG_FLAG(PROBE);
+	P_MSG_FLAG(TRUNC);
+	P_MSG_FLAG(DONTWAIT);
+	P_MSG_FLAG(EOR);
+	P_MSG_FLAG(WAITALL);
+	P_MSG_FLAG(FIN);
+	P_MSG_FLAG(SYN);
+	P_MSG_FLAG(CONFIRM);
+	P_MSG_FLAG(RST);
+	P_MSG_FLAG(ERRQUEUE);
+	P_MSG_FLAG(NOSIGNAL);
+	P_MSG_FLAG(MORE);
+	P_MSG_FLAG(WAITFORONE);
+	P_MSG_FLAG(SENDPAGE_NOTLAST);
+	P_MSG_FLAG(FASTOPEN);
+	P_MSG_FLAG(CMSG_CLOEXEC);
+#undef P_MSG_FLAG
+
+	if (flags)
+		printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
+
+	return printed;
 }
 
-static void script_spec__add(struct script_spec *s)
+#define SCA_MSG_FLAGS syscall_arg__scnprintf_msg_flags
+
+static size_t syscall_arg__scnprintf_access_mode(char *bf, size_t size,
+						 struct syscall_arg *arg)
 {
-	list_add_tail(&s->node, &script_specs);
+	size_t printed = 0;
+	int mode = arg->val;
+
+	if (mode == F_OK) /* 0 */
+		return scnprintf(bf, size, "F");
+#define	P_MODE(n) \
+	if (mode & n##_OK) { \
+		printed += scnprintf(bf + printed, size - printed, "%s", #n); \
+		mode &= ~n##_OK; \
+	}
+
+	P_MODE(R);
+	P_MODE(W);
+	P_MODE(X);
+#undef P_MODE
+
+	if (mode)
+		printed += scnprintf(bf + printed, size - printed, "|%#x", mode);
+
+	return printed;
 }
 
-static struct script_spec *script_spec__find(const char *spec)
+#define SCA_ACCMODE syscall_arg__scnprintf_access_mode
+
+static size_t syscall_arg__scnprintf_open_flags(char *bf, size_t size,
+					       struct syscall_arg *arg)
 {
-	struct script_spec *s;
+	int printed = 0, flags = arg->val;
 
-	list_for_each_entry(s, &script_specs, node)
-		if (strcasecmp(s->spec, spec) == 0)
-			return s;
-	return NULL;
+	if (!(flags & O_CREAT))
+		arg->mask |= 1 << (arg->idx + 1); /* Mask the mode parm */
+
+	if (flags == 0)
+		return scnprintf(bf, size, "RDONLY");
+#define	P_FLAG(n) \
+	if (flags & O_##n) { \
+		printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
+		flags &= ~O_##n; \
+	}
+
+	P_FLAG(APPEND);
+	P_FLAG(ASYNC);
+	P_FLAG(CLOEXEC);
+	P_FLAG(CREAT);
+	P_FLAG(DIRECT);
+	P_FLAG(DIRECTORY);
+	P_FLAG(EXCL);
+	P_FLAG(LARGEFILE);
+	P_FLAG(NOATIME);
+	P_FLAG(NOCTTY);
+#ifdef O_NONBLOCK
+	P_FLAG(NONBLOCK);
+#elif O_NDELAY
+	P_FLAG(NDELAY);
+#endif
+#ifdef O_PATH
+	P_FLAG(PATH);
+#endif
+	P_FLAG(RDWR);
+#ifdef O_DSYNC
+	if ((flags & O_SYNC) == O_SYNC)
+		printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", "SYNC");
+	else {
+		P_FLAG(DSYNC);
+	}
+#else
+	P_FLAG(SYNC);
+#endif
+	P_FLAG(TRUNC);
+	P_FLAG(WRONLY);
+#undef P_FLAG
+
+	if (flags)
+		printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
+
+	return printed;
 }
 
-static struct script_spec *script_spec__findnew(const char *spec,
-						struct scripting_ops *ops)
+#define SCA_OPEN_FLAGS syscall_arg__scnprintf_open_flags
+
+static size_t syscall_arg__scnprintf_eventfd_flags(char *bf, size_t size,
+						   struct syscall_arg *arg)
 {
-	struct script_spec *s = script_spec__find(spec);
+	int printed = 0, flags = arg->val;
+
+	if (flags == 0)
+		return scnprintf(bf, size, "NONE");
+#define	P_FLAG(n) \
+	if (flags & EFD_##n) { \
+		printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
+		flags &= ~EFD_##n; \
+	}
+
+	P_FLAG(SEMAPHORE);
+	P_FLAG(CLOEXEC);
+	P_FLAG(NONBLOCK);
+#undef P_FLAG
+
+	if (flags)
+		printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
 
-	if (s)
-		return s;
+	return printed;
+}
 
-	s = script_spec__new(spec, ops);
-	if (!s)
-		goto out_delete_spec;
+#define SCA_EFD_FLAGS syscall_arg__scnprintf_eventfd_flags
 
-	script_spec__add(s);
+static size_t syscall_arg__scnprintf_pipe_flags(char *bf, size_t size,
+						struct syscall_arg *arg)
+{
+	int printed = 0, flags = arg->val;
 
-	return s;
+#define	P_FLAG(n) \
+	if (flags & O_##n) { \
+		printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
+		flags &= ~O_##n; \
+	}
 
-out_delete_spec:
-	script_spec__delete(s);
+	P_FLAG(CLOEXEC);
+	P_FLAG(NONBLOCK);
+#undef P_FLAG
 
-	return NULL;
+	if (flags)
+		printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
+
+	return printed;
 }
 
-int script_spec_register(const char *spec, struct scripting_ops *ops)
+#define SCA_PIPE_FLAGS syscall_arg__scnprintf_pipe_flags
+
+static size_t syscall_arg__scnprintf_signum(char *bf, size_t size, struct syscall_arg *arg)
 {
-	struct script_spec *s;
+	int sig = arg->val;
+
+	switch (sig) {
+#define	P_SIGNUM(n) case SIG##n: return scnprintf(bf, size, #n)
+	P_SIGNUM(HUP);
+	P_SIGNUM(INT);
+	P_SIGNUM(QUIT);
+	P_SIGNUM(ILL);
+	P_SIGNUM(TRAP);
+	P_SIGNUM(ABRT);
+	P_SIGNUM(BUS);
+	P_SIGNUM(FPE);
+	P_SIGNUM(KILL);
+	P_SIGNUM(USR1);
+	P_SIGNUM(SEGV);
+	P_SIGNUM(USR2);
+	P_SIGNUM(PIPE);
+	P_SIGNUM(ALRM);
+	P_SIGNUM(TERM);
+	P_SIGNUM(CHLD);
+	P_SIGNUM(CONT);
+	P_SIGNUM(STOP);
+	P_SIGNUM(TSTP);
+	P_SIGNUM(TTIN);
+	P_SIGNUM(TTOU);
+	P_SIGNUM(URG);
+	P_SIGNUM(XCPU);
+	P_SIGNUM(XFSZ);
+	P_SIGNUM(VTALRM);
+	P_SIGNUM(PROF);
+	P_SIGNUM(WINCH);
+	P_SIGNUM(IO);
+	P_SIGNUM(PWR);
+	P_SIGNUM(SYS);
+#ifdef SIGEMT
+	P_SIGNUM(EMT);
+#endif
+#ifdef SIGSTKFLT
+	P_SIGNUM(STKFLT);
+#endif
+#ifdef SIGSWI
+	P_SIGNUM(SWI);
+#endif
+	default: break;
+	}
 
-	s = script_spec__find(spec);
-	if (s)
-		return -1;
+	return scnprintf(bf, size, "%#x", sig);
+}
 
-	s = script_spec__findnew(spec, ops);
-	if (!s)
-		return -1;
+#define SCA_SIGNUM syscall_arg__scnprintf_signum
+
+#if defined(__i386__) || defined(__x86_64__)
+/*
+ * FIXME: Make this available to all arches.
+ */
+#define TCGETS		0x5401
+
+static const char *tioctls[] = {
+	"TCGETS", "TCSETS", "TCSETSW", "TCSETSF", "TCGETA", "TCSETA", "TCSETAW",
+	"TCSETAF", "TCSBRK", "TCXONC", "TCFLSH", "TIOCEXCL", "TIOCNXCL",
+	"TIOCSCTTY", "TIOCGPGRP", "TIOCSPGRP", "TIOCOUTQ", "TIOCSTI",
+	"TIOCGWINSZ", "TIOCSWINSZ", "TIOCMGET", "TIOCMBIS", "TIOCMBIC",
+	"TIOCMSET", "TIOCGSOFTCAR", "TIOCSSOFTCAR", "FIONREAD", "TIOCLINUX",
+	"TIOCCONS", "TIOCGSERIAL", "TIOCSSERIAL", "TIOCPKT", "FIONBIO",
+	"TIOCNOTTY", "TIOCSETD", "TIOCGETD", "TCSBRKP", [0x27] = "TIOCSBRK",
+	"TIOCCBRK", "TIOCGSID", "TCGETS2", "TCSETS2", "TCSETSW2", "TCSETSF2",
+	"TIOCGRS485", "TIOCSRS485", "TIOCGPTN", "TIOCSPTLCK",
+	"TIOCGDEV||TCGETX", "TCSETX", "TCSETXF", "TCSETXW", "TIOCSIG",
+	"TIOCVHANGUP", "TIOCGPKT", "TIOCGPTLCK", "TIOCGEXCL",
+	[0x50] = "FIONCLEX", "FIOCLEX", "FIOASYNC", "TIOCSERCONFIG",
+	"TIOCSERGWILD", "TIOCSERSWILD", "TIOCGLCKTRMIOS", "TIOCSLCKTRMIOS",
+	"TIOCSERGSTRUCT", "TIOCSERGETLSR", "TIOCSERGETMULTI", "TIOCSERSETMULTI",
+	"TIOCMIWAIT", "TIOCGICOUNT", [0x60] = "FIOQSIZE",
+};
 
-	return 0;
+static DEFINE_STRARRAY_OFFSET(tioctls, 0x5401);
+#endif /* defined(__i386__) || defined(__x86_64__) */
+
+#define STRARRAY(arg, name, array) \
+	  .arg_scnprintf = { [arg] = SCA_STRARRAY, }, \
+	  .arg_parm	 = { [arg] = &strarray__##array, }
+
+static struct syscall_fmt {
+	const char *name;
+	const char *alias;
+	size_t	   (*arg_scnprintf[6])(char *bf, size_t size, struct syscall_arg *arg);
+	void	   *arg_parm[6];
+	bool	   errmsg;
+	bool	   timeout;
+	bool	   hexret;
+} syscall_fmts[] = {
+	{ .name	    = "access",	    .errmsg = true,
+	  .arg_scnprintf = { [1] = SCA_ACCMODE, /* mode */ }, },
+	{ .name	    = "arch_prctl", .errmsg = true, .alias = "prctl", },
+	{ .name	    = "brk",	    .hexret = true,
+	  .arg_scnprintf = { [0] = SCA_HEX, /* brk */ }, },
+	{ .name     = "clock_gettime",  .errmsg = true, STRARRAY(0, clk_id, clockid), },
+	{ .name	    = "close",	    .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_CLOSE_FD, /* fd */ }, }, 
+	{ .name	    = "connect",    .errmsg = true, },
+	{ .name	    = "dup",	    .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
+	{ .name	    = "dup2",	    .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
+	{ .name	    = "dup3",	    .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
+	{ .name	    = "epoll_ctl",  .errmsg = true, STRARRAY(1, op, epoll_ctl_ops), },
+	{ .name	    = "eventfd2",   .errmsg = true,
+	  .arg_scnprintf = { [1] = SCA_EFD_FLAGS, /* flags */ }, },
+	{ .name	    = "faccessat",  .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
+	{ .name	    = "fadvise64",  .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
+	{ .name	    = "fallocate",  .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
+	{ .name	    = "fchdir",	    .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
+	{ .name	    = "fchmod",	    .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
+	{ .name	    = "fchmodat",   .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, 
+	{ .name	    = "fchown",	    .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
+	{ .name	    = "fchownat",   .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, 
+	{ .name	    = "fcntl",	    .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */
+			     [1] = SCA_STRARRAY, /* cmd */ },
+	  .arg_parm	 = { [1] = &strarray__fcntl_cmds, /* cmd */ }, },
+	{ .name	    = "fdatasync",  .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
+	{ .name	    = "flock",	    .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */
+			     [1] = SCA_FLOCK, /* cmd */ }, },
+	{ .name	    = "fsetxattr",  .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
+	{ .name	    = "fstat",	    .errmsg = true, .alias = "newfstat",
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
+	{ .name	    = "fstatat",    .errmsg = true, .alias = "newfstatat",
+	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, 
+	{ .name	    = "fstatfs",    .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
+	{ .name	    = "fsync",    .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
+	{ .name	    = "ftruncate", .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
+	{ .name	    = "futex",	    .errmsg = true,
+	  .arg_scnprintf = { [1] = SCA_FUTEX_OP, /* op */ }, },
+	{ .name	    = "futimesat", .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, 
+	{ .name	    = "getdents",   .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
+	{ .name	    = "getdents64", .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
+	{ .name	    = "getitimer",  .errmsg = true, STRARRAY(0, which, itimers), },
+	{ .name	    = "getrlimit",  .errmsg = true, STRARRAY(0, resource, rlimit_resources), },
+	{ .name	    = "ioctl",	    .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ 
+#if defined(__i386__) || defined(__x86_64__)
+/*
+ * FIXME: Make this available to all arches.
+ */
+			     [1] = SCA_STRHEXARRAY, /* cmd */
+			     [2] = SCA_HEX, /* arg */ },
+	  .arg_parm	 = { [1] = &strarray__tioctls, /* cmd */ }, },
+#else
+			     [2] = SCA_HEX, /* arg */ }, },
+#endif
+	{ .name	    = "kill",	    .errmsg = true,
+	  .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, },
+	{ .name	    = "linkat",	    .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, 
+	{ .name	    = "lseek",	    .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */
+			     [2] = SCA_STRARRAY, /* whence */ },
+	  .arg_parm	 = { [2] = &strarray__whences, /* whence */ }, },
+	{ .name	    = "lstat",	    .errmsg = true, .alias = "newlstat", },
+	{ .name     = "madvise",    .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_HEX,	 /* start */
+			     [2] = SCA_MADV_BHV, /* behavior */ }, },
+	{ .name	    = "mkdirat",    .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, 
+	{ .name	    = "mknodat",    .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, 
+	{ .name	    = "mlock",	    .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
+	{ .name	    = "mlockall",   .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
+	{ .name	    = "mmap",	    .hexret = true,
+	  .arg_scnprintf = { [0] = SCA_HEX,	  /* addr */
+			     [2] = SCA_MMAP_PROT, /* prot */
+			     [3] = SCA_MMAP_FLAGS, /* flags */
+			     [4] = SCA_FD, 	  /* fd */ }, },
+	{ .name	    = "mprotect",   .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_HEX, /* start */
+			     [2] = SCA_MMAP_PROT, /* prot */ }, },
+	{ .name	    = "mremap",	    .hexret = true,
+	  .arg_scnprintf = { [0] = SCA_HEX, /* addr */
+			     [4] = SCA_HEX, /* new_addr */ }, },
+	{ .name	    = "munlock",    .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
+	{ .name	    = "munmap",	    .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
+	{ .name	    = "name_to_handle_at", .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, 
+	{ .name	    = "newfstatat", .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, 
+	{ .name	    = "open",	    .errmsg = true,
+	  .arg_scnprintf = { [1] = SCA_OPEN_FLAGS, /* flags */ }, },
+	{ .name	    = "open_by_handle_at", .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */
+			     [2] = SCA_OPEN_FLAGS, /* flags */ }, },
+	{ .name	    = "openat",	    .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */
+			     [2] = SCA_OPEN_FLAGS, /* flags */ }, },
+	{ .name	    = "pipe2",	    .errmsg = true,
+	  .arg_scnprintf = { [1] = SCA_PIPE_FLAGS, /* flags */ }, },
+	{ .name	    = "poll",	    .errmsg = true, .timeout = true, },
+	{ .name	    = "ppoll",	    .errmsg = true, .timeout = true, },
+	{ .name	    = "pread",	    .errmsg = true, .alias = "pread64",
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
+	{ .name	    = "preadv",	    .errmsg = true, .alias = "pread",
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
+	{ .name	    = "prlimit64",  .errmsg = true, STRARRAY(1, resource, rlimit_resources), },
+	{ .name	    = "pwrite",	    .errmsg = true, .alias = "pwrite64",
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
+	{ .name	    = "pwritev",    .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
+	{ .name	    = "read",	    .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
+	{ .name	    = "readlinkat", .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, 
+	{ .name	    = "readv",	    .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
+	{ .name	    = "recvfrom",   .errmsg = true,
+	  .arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, },
+	{ .name	    = "recvmmsg",   .errmsg = true,
+	  .arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, },
+	{ .name	    = "recvmsg",    .errmsg = true,
+	  .arg_scnprintf = { [2] = SCA_MSG_FLAGS, /* flags */ }, },
+	{ .name	    = "renameat",   .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, 
+	{ .name	    = "rt_sigaction", .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_SIGNUM, /* sig */ }, },
+	{ .name	    = "rt_sigprocmask",  .errmsg = true, STRARRAY(0, how, sighow), },
+	{ .name	    = "rt_sigqueueinfo", .errmsg = true,
+	  .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, },
+	{ .name	    = "rt_tgsigqueueinfo", .errmsg = true,
+	  .arg_scnprintf = { [2] = SCA_SIGNUM, /* sig */ }, },
+	{ .name	    = "select",	    .errmsg = true, .timeout = true, },
+	{ .name	    = "sendmmsg",    .errmsg = true,
+	  .arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, },
+	{ .name	    = "sendmsg",    .errmsg = true,
+	  .arg_scnprintf = { [2] = SCA_MSG_FLAGS, /* flags */ }, },
+	{ .name	    = "sendto",	    .errmsg = true,
+	  .arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, },
+	{ .name	    = "setitimer",  .errmsg = true, STRARRAY(0, which, itimers), },
+	{ .name	    = "setrlimit",  .errmsg = true, STRARRAY(0, resource, rlimit_resources), },
+	{ .name	    = "shutdown",   .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
+	{ .name	    = "socket",	    .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_STRARRAY, /* family */
+			     [1] = SCA_SK_TYPE, /* type */ },
+	  .arg_parm	 = { [0] = &strarray__socket_families, /* family */ }, },
+	{ .name	    = "socketpair", .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_STRARRAY, /* family */
+			     [1] = SCA_SK_TYPE, /* type */ },
+	  .arg_parm	 = { [0] = &strarray__socket_families, /* family */ }, },
+	{ .name	    = "stat",	    .errmsg = true, .alias = "newstat", },
+	{ .name	    = "symlinkat",  .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, 
+	{ .name	    = "tgkill",	    .errmsg = true,
+	  .arg_scnprintf = { [2] = SCA_SIGNUM, /* sig */ }, },
+	{ .name	    = "tkill",	    .errmsg = true,
+	  .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, },
+	{ .name	    = "uname",	    .errmsg = true, .alias = "newuname", },
+	{ .name	    = "unlinkat",   .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
+	{ .name	    = "utimensat",  .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_FDAT, /* dirfd */ }, },
+	{ .name	    = "write",	    .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
+	{ .name	    = "writev",	    .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
+};
+
+static int syscall_fmt__cmp(const void *name, const void *fmtp)
+{
+	const struct syscall_fmt *fmt = fmtp;
+	return strcmp(name, fmt->name);
 }
 
-static struct scripting_ops *script_spec__lookup(const char *spec)
+static struct syscall_fmt *syscall_fmt__find(const char *name)
 {
-	struct script_spec *s = script_spec__find(spec);
-	if (!s)
-		return NULL;
+	const int nmemb = ARRAY_SIZE(syscall_fmts);
+	return bsearch(name, syscall_fmts, nmemb, sizeof(struct syscall_fmt), syscall_fmt__cmp);
+}
+
+struct syscall {
+	struct event_format *tp_format;
+	const char	    *name;
+	bool		    filtered;
+	struct syscall_fmt  *fmt;
+	size_t		    (**arg_scnprintf)(char *bf, size_t size, struct syscall_arg *arg);
+	void		    **arg_parm;
+};
 
-	return s->ops;
+static size_t fprintf_duration(unsigned long t, FILE *fp)
+{
+	double duration = (double)t / NSEC_PER_MSEC;
+	size_t printed = fprintf(fp, "(");
+
+	if (duration >= 1.0)
+		printed += color_fprintf(fp, PERF_COLOR_RED, "%6.3f ms", duration);
+	else if (duration >= 0.01)
+		printed += color_fprintf(fp, PERF_COLOR_YELLOW, "%6.3f ms", duration);
+	else
+		printed += color_fprintf(fp, PERF_COLOR_NORMAL, "%6.3f ms", duration);
+	return printed + fprintf(fp, "): ");
 }
 
-static void list_available_languages(void)
+struct thread_trace {
+	u64		  entry_time;
+	u64		  exit_time;
+	bool		  entry_pending;
+	unsigned long	  nr_events;
+	char		  *entry_str;
+	double		  runtime_ms;
+	struct {
+		int	  max;
+		char	  **table;
+	} paths;
+
+	struct intlist *syscall_stats;
+};
+
+static struct thread_trace *thread_trace__new(void)
 {
-	struct script_spec *s;
+	struct thread_trace *ttrace =  zalloc(sizeof(struct thread_trace));
 
-	fprintf(stderr, "\n");
-	fprintf(stderr, "Scripting language extensions (used in "
-		"perf trace -s [spec:]script.[spec]):\n\n");
+	if (ttrace)
+		ttrace->paths.max = -1;
 
-	list_for_each_entry(s, &script_specs, node)
-		fprintf(stderr, "  %-42s [%s]\n", s->spec, s->ops->name);
+	ttrace->syscall_stats = intlist__new(NULL);
 
-	fprintf(stderr, "\n");
+	return ttrace;
 }
 
-static int parse_scriptname(const struct option *opt __used,
-			    const char *str, int unset __used)
+static struct thread_trace *thread__trace(struct thread *thread, FILE *fp)
 {
-	char spec[PATH_MAX];
-	const char *script, *ext;
-	int len;
+	struct thread_trace *ttrace;
 
-	if (strcmp(str, "lang") == 0) {
-		list_available_languages();
-		exit(0);
-	}
+	if (thread == NULL)
+		goto fail;
 
-	script = strchr(str, ':');
-	if (script) {
-		len = script - str;
-		if (len >= PATH_MAX) {
-			fprintf(stderr, "invalid language specifier");
-			return -1;
-		}
-		strncpy(spec, str, len);
-		spec[len] = '\0';
-		scripting_ops = script_spec__lookup(spec);
-		if (!scripting_ops) {
-			fprintf(stderr, "invalid language specifier");
-			return -1;
-		}
-		script++;
-	} else {
-		script = str;
-		ext = strchr(script, '.');
-		if (!ext) {
-			fprintf(stderr, "invalid script extension");
-			return -1;
-		}
-		scripting_ops = script_spec__lookup(++ext);
-		if (!scripting_ops) {
-			fprintf(stderr, "invalid script extension");
+	if (thread->priv == NULL)
+		thread->priv = thread_trace__new();
+		
+	if (thread->priv == NULL)
+		goto fail;
+
+	ttrace = thread->priv;
+	++ttrace->nr_events;
+
+	return ttrace;
+fail:
+	color_fprintf(fp, PERF_COLOR_RED,
+		      "WARNING: not enough memory, dropping samples!\n");
+	return NULL;
+}
+
+struct trace {
+	struct perf_tool	tool;
+	struct {
+		int		machine;
+		int		open_id;
+	}			audit;
+	struct {
+		int		max;
+		struct syscall  *table;
+	} syscalls;
+	struct record_opts	opts;
+	struct machine		*host;
+	u64			base_time;
+	FILE			*output;
+	unsigned long		nr_events;
+	struct strlist		*ev_qualifier;
+	const char 		*last_vfs_getname;
+	struct intlist		*tid_list;
+	struct intlist		*pid_list;
+	double			duration_filter;
+	double			runtime_ms;
+	struct {
+		u64		vfs_getname,
+				proc_getname;
+	} stats;
+	bool			not_ev_qualifier;
+	bool			live;
+	bool			full_time;
+	bool			sched;
+	bool			multiple_threads;
+	bool			summary;
+	bool			summary_only;
+	bool			show_comm;
+	bool			show_tool_stats;
+};
+
+static int trace__set_fd_pathname(struct thread *thread, int fd, const char *pathname)
+{
+	struct thread_trace *ttrace = thread->priv;
+
+	if (fd > ttrace->paths.max) {
+		char **npath = realloc(ttrace->paths.table, (fd + 1) * sizeof(char *));
+
+		if (npath == NULL)
 			return -1;
+
+		if (ttrace->paths.max != -1) {
+			memset(npath + ttrace->paths.max + 1, 0,
+			       (fd - ttrace->paths.max) * sizeof(char *));
+		} else {
+			memset(npath, 0, (fd + 1) * sizeof(char *));
 		}
+
+		ttrace->paths.table = npath;
+		ttrace->paths.max   = fd;
 	}
 
-	script_name = strdup(script);
+	ttrace->paths.table[fd] = strdup(pathname);
 
-	return 0;
+	return ttrace->paths.table[fd] != NULL ? 0 : -1;
 }
 
-#define for_each_lang(scripts_dir, lang_dirent, lang_next)		\
-	while (!readdir_r(scripts_dir, &lang_dirent, &lang_next) &&	\
-	       lang_next)						\
-		if (lang_dirent.d_type == DT_DIR &&			\
-		    (strcmp(lang_dirent.d_name, ".")) &&		\
-		    (strcmp(lang_dirent.d_name, "..")))
+static int thread__read_fd_path(struct thread *thread, int fd)
+{
+	char linkname[PATH_MAX], pathname[PATH_MAX];
+	struct stat st;
+	int ret;
 
-#define for_each_script(lang_dir, script_dirent, script_next)		\
-	while (!readdir_r(lang_dir, &script_dirent, &script_next) &&	\
-	       script_next)						\
-		if (script_dirent.d_type != DT_DIR)
+	if (thread->pid_ == thread->tid) {
+		scnprintf(linkname, sizeof(linkname),
+			  "/proc/%d/fd/%d", thread->pid_, fd);
+	} else {
+		scnprintf(linkname, sizeof(linkname),
+			  "/proc/%d/task/%d/fd/%d", thread->pid_, thread->tid, fd);
+	}
 
+	if (lstat(linkname, &st) < 0 || st.st_size + 1 > (off_t)sizeof(pathname))
+		return -1;
 
-#define RECORD_SUFFIX			"-record"
-#define REPORT_SUFFIX			"-report"
+	ret = readlink(linkname, pathname, sizeof(pathname));
 
-struct script_desc {
-	struct list_head	node;
-	char			*name;
-	char			*half_liner;
-	char			*args;
-};
+	if (ret < 0 || ret > st.st_size)
+		return -1;
+
+	pathname[ret] = '\0';
+	return trace__set_fd_pathname(thread, fd, pathname);
+}
+
+static const char *thread__fd_path(struct thread *thread, int fd,
+				   struct trace *trace)
+{
+	struct thread_trace *ttrace = thread->priv;
+
+	if (ttrace == NULL)
+		return NULL;
+
+	if (fd < 0)
+		return NULL;
+
+	if ((fd > ttrace->paths.max || ttrace->paths.table[fd] == NULL))
+		if (!trace->live)
+			return NULL;
+		++trace->stats.proc_getname;
+		if (thread__read_fd_path(thread, fd)) {
+			return NULL;
+	}
 
-LIST_HEAD(script_descs);
+	return ttrace->paths.table[fd];
+}
 
-static struct script_desc *script_desc__new(const char *name)
+static size_t syscall_arg__scnprintf_fd(char *bf, size_t size,
+					struct syscall_arg *arg)
 {
-	struct script_desc *s = zalloc(sizeof(*s));
+	int fd = arg->val;
+	size_t printed = scnprintf(bf, size, "%d", fd);
+	const char *path = thread__fd_path(arg->thread, fd, arg->trace);
 
-	if (s != NULL)
-		s->name = strdup(name);
+	if (path)
+		printed += scnprintf(bf + printed, size - printed, "<%s>", path);
 
-	return s;
+	return printed;
 }
 
-static void script_desc__delete(struct script_desc *s)
+static size_t syscall_arg__scnprintf_close_fd(char *bf, size_t size,
+					      struct syscall_arg *arg)
 {
-	free(s->name);
-	free(s);
+	int fd = arg->val;
+	size_t printed = syscall_arg__scnprintf_fd(bf, size, arg);
+	struct thread_trace *ttrace = arg->thread->priv;
+
+	if (ttrace && fd >= 0 && fd <= ttrace->paths.max)
+		zfree(&ttrace->paths.table[fd]);
+
+	return printed;
 }
 
-static void script_desc__add(struct script_desc *s)
+static bool trace__filter_duration(struct trace *trace, double t)
 {
-	list_add_tail(&s->node, &script_descs);
+	return t < (trace->duration_filter * NSEC_PER_MSEC);
 }
 
-static struct script_desc *script_desc__find(const char *name)
+static size_t trace__fprintf_tstamp(struct trace *trace, u64 tstamp, FILE *fp)
 {
-	struct script_desc *s;
+	double ts = (double)(tstamp - trace->base_time) / NSEC_PER_MSEC;
 
-	list_for_each_entry(s, &script_descs, node)
-		if (strcasecmp(s->name, name) == 0)
-			return s;
-	return NULL;
+	return fprintf(fp, "%10.3f ", ts);
 }
 
-static struct script_desc *script_desc__findnew(const char *name)
+static bool done = false;
+static bool interrupted = false;
+
+static void sig_handler(int sig)
 {
-	struct script_desc *s = script_desc__find(name);
+	done = true;
+	interrupted = sig == SIGINT;
+}
 
-	if (s)
-		return s;
+static size_t trace__fprintf_entry_head(struct trace *trace, struct thread *thread,
+					u64 duration, u64 tstamp, FILE *fp)
+{
+	size_t printed = trace__fprintf_tstamp(trace, tstamp, fp);
+	printed += fprintf_duration(duration, fp);
 
-	s = script_desc__new(name);
-	if (!s)
-		goto out_delete_desc;
+	if (trace->multiple_threads) {
+		if (trace->show_comm)
+			printed += fprintf(fp, "%.14s/", thread__comm_str(thread));
+		printed += fprintf(fp, "%d ", thread->tid);
+	}
 
-	script_desc__add(s);
+	return printed;
+}
 
-	return s;
+static int trace__process_event(struct trace *trace, struct machine *machine,
+				union perf_event *event, struct perf_sample *sample)
+{
+	int ret = 0;
+
+	switch (event->header.type) {
+	case PERF_RECORD_LOST:
+		color_fprintf(trace->output, PERF_COLOR_RED,
+			      "LOST %" PRIu64 " events!\n", event->lost.lost);
+		ret = machine__process_lost_event(machine, event, sample);
+	default:
+		ret = machine__process_event(machine, event, sample);
+		break;
+	}
 
-out_delete_desc:
-	script_desc__delete(s);
+	return ret;
+}
 
-	return NULL;
+static int trace__tool_process(struct perf_tool *tool,
+			       union perf_event *event,
+			       struct perf_sample *sample,
+			       struct machine *machine)
+{
+	struct trace *trace = container_of(tool, struct trace, tool);
+	return trace__process_event(trace, machine, event, sample);
 }
 
-static char *ends_with(char *str, const char *suffix)
+static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist)
 {
-	size_t suffix_len = strlen(suffix);
-	char *p = str;
+	int err = symbol__init();
 
-	if (strlen(str) > suffix_len) {
-		p = str + strlen(str) - suffix_len;
-		if (!strncmp(p, suffix, suffix_len))
-			return p;
-	}
+	if (err)
+		return err;
 
-	return NULL;
+	trace->host = machine__new_host();
+	if (trace->host == NULL)
+		return -ENOMEM;
+
+	err = __machine__synthesize_threads(trace->host, &trace->tool, &trace->opts.target,
+					    evlist->threads, trace__tool_process, false);
+	if (err)
+		symbol__exit();
+
+	return err;
 }
 
-static char *ltrim(char *str)
+static int syscall__set_arg_fmts(struct syscall *sc)
 {
-	int len = strlen(str);
+	struct format_field *field;
+	int idx = 0;
 
-	while (len && isspace(*str)) {
-		len--;
-		str++;
+	sc->arg_scnprintf = calloc(sc->tp_format->format.nr_fields - 1, sizeof(void *));
+	if (sc->arg_scnprintf == NULL)
+		return -1;
+
+	if (sc->fmt)
+		sc->arg_parm = sc->fmt->arg_parm;
+
+	for (field = sc->tp_format->format.fields->next; field; field = field->next) {
+		if (sc->fmt && sc->fmt->arg_scnprintf[idx])
+			sc->arg_scnprintf[idx] = sc->fmt->arg_scnprintf[idx];
+		else if (field->flags & FIELD_IS_POINTER)
+			sc->arg_scnprintf[idx] = syscall_arg__scnprintf_hex;
+		++idx;
 	}
 
-	return str;
+	return 0;
 }
 
-static int read_script_info(struct script_desc *desc, const char *filename)
+static int trace__read_syscall_info(struct trace *trace, int id)
 {
-	char line[BUFSIZ], *p;
-	FILE *fp;
+	char tp_name[128];
+	struct syscall *sc;
+	const char *name = audit_syscall_to_name(id, trace->audit.machine);
 
-	fp = fopen(filename, "r");
-	if (!fp)
+	if (name == NULL)
 		return -1;
 
-	while (fgets(line, sizeof(line), fp)) {
-		p = ltrim(line);
-		if (strlen(p) == 0)
-			continue;
-		if (*p != '#')
-			continue;
-		p++;
-		if (strlen(p) && *p == '!')
-			continue;
-
-		p = ltrim(p);
-		if (strlen(p) && p[strlen(p) - 1] == '\n')
-			p[strlen(p) - 1] = '\0';
-
-		if (!strncmp(p, "description:", strlen("description:"))) {
-			p += strlen("description:");
-			desc->half_liner = strdup(ltrim(p));
-			continue;
+	if (id > trace->syscalls.max) {
+		struct syscall *nsyscalls = realloc(trace->syscalls.table, (id + 1) * sizeof(*sc));
+
+		if (nsyscalls == NULL)
+			return -1;
+
+		if (trace->syscalls.max != -1) {
+			memset(nsyscalls + trace->syscalls.max + 1, 0,
+			       (id - trace->syscalls.max) * sizeof(*sc));
+		} else {
+			memset(nsyscalls, 0, (id + 1) * sizeof(*sc));
 		}
 
-		if (!strncmp(p, "args:", strlen("args:"))) {
-			p += strlen("args:");
-			desc->args = strdup(ltrim(p));
-			continue;
+		trace->syscalls.table = nsyscalls;
+		trace->syscalls.max   = id;
+	}
+
+	sc = trace->syscalls.table + id;
+	sc->name = name;
+
+	if (trace->ev_qualifier) {
+		bool in = strlist__find(trace->ev_qualifier, name) != NULL;
+
+		if (!(in ^ trace->not_ev_qualifier)) {
+			sc->filtered = true;
+			/*
+			 * No need to do read tracepoint information since this will be
+			 * filtered out.
+			 */
+			return 0;
 		}
 	}
 
-	fclose(fp);
+	sc->fmt  = syscall_fmt__find(sc->name);
 
-	return 0;
+	snprintf(tp_name, sizeof(tp_name), "sys_enter_%s", sc->name);
+	sc->tp_format = trace_event__tp_format("syscalls", tp_name);
+
+	if (sc->tp_format == NULL && sc->fmt && sc->fmt->alias) {
+		snprintf(tp_name, sizeof(tp_name), "sys_enter_%s", sc->fmt->alias);
+		sc->tp_format = trace_event__tp_format("syscalls", tp_name);
+	}
+
+	if (sc->tp_format == NULL)
+		return -1;
+
+	return syscall__set_arg_fmts(sc);
 }
 
-static int list_available_scripts(const struct option *opt __used,
-				  const char *s __used, int unset __used)
+static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size,
+				      unsigned long *args, struct trace *trace,
+				      struct thread *thread)
 {
-	struct dirent *script_next, *lang_next, script_dirent, lang_dirent;
-	char scripts_path[MAXPATHLEN];
-	DIR *scripts_dir, *lang_dir;
-	char script_path[MAXPATHLEN];
-	char lang_path[MAXPATHLEN];
-	struct script_desc *desc;
-	char first_half[BUFSIZ];
-	char *script_root;
-	char *str;
+	size_t printed = 0;
+
+	if (sc->tp_format != NULL) {
+		struct format_field *field;
+		u8 bit = 1;
+		struct syscall_arg arg = {
+			.idx	= 0,
+			.mask	= 0,
+			.trace  = trace,
+			.thread = thread,
+		};
+
+		for (field = sc->tp_format->format.fields->next; field;
+		     field = field->next, ++arg.idx, bit <<= 1) {
+			if (arg.mask & bit)
+				continue;
+			/*
+ 			 * Suppress this argument if its value is zero and
+ 			 * and we don't have a string associated in an
+ 			 * strarray for it.
+ 			 */
+			if (args[arg.idx] == 0 &&
+			    !(sc->arg_scnprintf &&
+			      sc->arg_scnprintf[arg.idx] == SCA_STRARRAY &&
+			      sc->arg_parm[arg.idx]))
+				continue;
+
+			printed += scnprintf(bf + printed, size - printed,
+					     "%s%s: ", printed ? ", " : "", field->name);
+			if (sc->arg_scnprintf && sc->arg_scnprintf[arg.idx]) {
+				arg.val = args[arg.idx];
+				if (sc->arg_parm)
+					arg.parm = sc->arg_parm[arg.idx];
+				printed += sc->arg_scnprintf[arg.idx](bf + printed,
+								      size - printed, &arg);
+			} else {
+				printed += scnprintf(bf + printed, size - printed,
+						     "%ld", args[arg.idx]);
+			}
+		}
+	} else {
+		int i = 0;
+
+		while (i < 6) {
+			printed += scnprintf(bf + printed, size - printed,
+					     "%sarg%d: %ld",
+					     printed ? ", " : "", i, args[i]);
+			++i;
+		}
+	}
 
-	snprintf(scripts_path, MAXPATHLEN, "%s/scripts", perf_exec_path());
+	return printed;
+}
 
-	scripts_dir = opendir(scripts_path);
-	if (!scripts_dir)
-		return -1;
+typedef int (*tracepoint_handler)(struct trace *trace, struct perf_evsel *evsel,
+				  struct perf_sample *sample);
 
-	for_each_lang(scripts_dir, lang_dirent, lang_next) {
-		snprintf(lang_path, MAXPATHLEN, "%s/%s/bin", scripts_path,
-			 lang_dirent.d_name);
-		lang_dir = opendir(lang_path);
-		if (!lang_dir)
-			continue;
-
-		for_each_script(lang_dir, script_dirent, script_next) {
-			script_root = strdup(script_dirent.d_name);
-			str = ends_with(script_root, REPORT_SUFFIX);
-			if (str) {
-				*str = '\0';
-				desc = script_desc__findnew(script_root);
-				snprintf(script_path, MAXPATHLEN, "%s/%s",
-					 lang_path, script_dirent.d_name);
-				read_script_info(desc, script_path);
-			}
-			free(script_root);
+static struct syscall *trace__syscall_info(struct trace *trace,
+					   struct perf_evsel *evsel, int id)
+{
+
+	if (id < 0) {
+
+		/*
+		 * XXX: Noticed on x86_64, reproduced as far back as 3.0.36, haven't tried
+		 * before that, leaving at a higher verbosity level till that is
+		 * explained. Reproduced with plain ftrace with:
+		 *
+		 * echo 1 > /t/events/raw_syscalls/sys_exit/enable
+		 * grep "NR -1 " /t/trace_pipe
+		 *
+		 * After generating some load on the machine.
+ 		 */
+		if (verbose > 1) {
+			static u64 n;
+			fprintf(trace->output, "Invalid syscall %d id, skipping (%s, %" PRIu64 ") ...\n",
+				id, perf_evsel__name(evsel), ++n);
 		}
+		return NULL;
 	}
 
-	fprintf(stdout, "List of available trace scripts:\n");
-	list_for_each_entry(desc, &script_descs, node) {
-		sprintf(first_half, "%s %s", desc->name,
-			desc->args ? desc->args : "");
-		fprintf(stdout, "  %-36s %s\n", first_half,
-			desc->half_liner ? desc->half_liner : "");
+	if ((id > trace->syscalls.max || trace->syscalls.table[id].name == NULL) &&
+	    trace__read_syscall_info(trace, id))
+		goto out_cant_read;
+
+	if ((id > trace->syscalls.max || trace->syscalls.table[id].name == NULL))
+		goto out_cant_read;
+
+	return &trace->syscalls.table[id];
+
+out_cant_read:
+	if (verbose) {
+		fprintf(trace->output, "Problems reading syscall %d", id);
+		if (id <= trace->syscalls.max && trace->syscalls.table[id].name != NULL)
+			fprintf(trace->output, "(%s)", trace->syscalls.table[id].name);
+		fputs(" information\n", trace->output);
 	}
+	return NULL;
+}
 
-	exit(0);
+static void thread__update_stats(struct thread_trace *ttrace,
+				 int id, struct perf_sample *sample)
+{
+	struct int_node *inode;
+	struct stats *stats;
+	u64 duration = 0;
+
+	inode = intlist__findnew(ttrace->syscall_stats, id);
+	if (inode == NULL)
+		return;
+
+	stats = inode->priv;
+	if (stats == NULL) {
+		stats = malloc(sizeof(struct stats));
+		if (stats == NULL)
+			return;
+		init_stats(stats);
+		inode->priv = stats;
+	}
+
+	if (ttrace->entry_time && sample->time > ttrace->entry_time)
+		duration = sample->time - ttrace->entry_time;
+
+	update_stats(stats, duration);
 }
 
-static char *get_script_path(const char *script_root, const char *suffix)
+static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
+			    struct perf_sample *sample)
 {
-	struct dirent *script_next, *lang_next, script_dirent, lang_dirent;
-	char scripts_path[MAXPATHLEN];
-	char script_path[MAXPATHLEN];
-	DIR *scripts_dir, *lang_dir;
-	char lang_path[MAXPATHLEN];
-	char *str, *__script_root;
-	char *path = NULL;
+	char *msg;
+	void *args;
+	size_t printed = 0;
+	struct thread *thread;
+	int id = perf_evsel__sc_tp_uint(evsel, id, sample);
+	struct syscall *sc = trace__syscall_info(trace, evsel, id);
+	struct thread_trace *ttrace;
 
-	snprintf(scripts_path, MAXPATHLEN, "%s/scripts", perf_exec_path());
+	if (sc == NULL)
+		return -1;
 
-	scripts_dir = opendir(scripts_path);
-	if (!scripts_dir)
-		return NULL;
+	if (sc->filtered)
+		return 0;
 
-	for_each_lang(scripts_dir, lang_dirent, lang_next) {
-		snprintf(lang_path, MAXPATHLEN, "%s/%s/bin", scripts_path,
-			 lang_dirent.d_name);
-		lang_dir = opendir(lang_path);
-		if (!lang_dir)
-			continue;
-
-		for_each_script(lang_dir, script_dirent, script_next) {
-			__script_root = strdup(script_dirent.d_name);
-			str = ends_with(__script_root, suffix);
-			if (str) {
-				*str = '\0';
-				if (strcmp(__script_root, script_root))
-					continue;
-				snprintf(script_path, MAXPATHLEN, "%s/%s",
-					 lang_path, script_dirent.d_name);
-				path = strdup(script_path);
-				free(__script_root);
-				break;
-			}
-			free(__script_root);
+	thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
+	ttrace = thread__trace(thread, trace->output);
+	if (ttrace == NULL)
+		return -1;
+
+	args = perf_evsel__sc_tp_ptr(evsel, args, sample);
+	ttrace = thread->priv;
+
+	if (ttrace->entry_str == NULL) {
+		ttrace->entry_str = malloc(1024);
+		if (!ttrace->entry_str)
+			return -1;
+	}
+
+	ttrace->entry_time = sample->time;
+	msg = ttrace->entry_str;
+	printed += scnprintf(msg + printed, 1024 - printed, "%s(", sc->name);
+
+	printed += syscall__scnprintf_args(sc, msg + printed, 1024 - printed,
+					   args, trace, thread);
+
+	if (!strcmp(sc->name, "exit_group") || !strcmp(sc->name, "exit")) {
+		if (!trace->duration_filter && !trace->summary_only) {
+			trace__fprintf_entry_head(trace, thread, 1, sample->time, trace->output);
+			fprintf(trace->output, "%-70s\n", ttrace->entry_str);
 		}
+	} else
+		ttrace->entry_pending = true;
+
+	return 0;
+}
+
+static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
+			   struct perf_sample *sample)
+{
+	int ret;
+	u64 duration = 0;
+	struct thread *thread;
+	int id = perf_evsel__sc_tp_uint(evsel, id, sample);
+	struct syscall *sc = trace__syscall_info(trace, evsel, id);
+	struct thread_trace *ttrace;
+
+	if (sc == NULL)
+		return -1;
+
+	if (sc->filtered)
+		return 0;
+
+	thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
+	ttrace = thread__trace(thread, trace->output);
+	if (ttrace == NULL)
+		return -1;
+
+	if (trace->summary)
+		thread__update_stats(ttrace, id, sample);
+
+	ret = perf_evsel__sc_tp_uint(evsel, ret, sample);
+
+	if (id == trace->audit.open_id && ret >= 0 && trace->last_vfs_getname) {
+		trace__set_fd_pathname(thread, ret, trace->last_vfs_getname);
+		trace->last_vfs_getname = NULL;
+		++trace->stats.vfs_getname;
+	}
+
+	ttrace = thread->priv;
+
+	ttrace->exit_time = sample->time;
+
+	if (ttrace->entry_time) {
+		duration = sample->time - ttrace->entry_time;
+		if (trace__filter_duration(trace, duration))
+			goto out;
+	} else if (trace->duration_filter)
+		goto out;
+
+	if (trace->summary_only)
+		goto out;
+
+	trace__fprintf_entry_head(trace, thread, duration, sample->time, trace->output);
+
+	if (ttrace->entry_pending) {
+		fprintf(trace->output, "%-70s", ttrace->entry_str);
+	} else {
+		fprintf(trace->output, " ... [");
+		color_fprintf(trace->output, PERF_COLOR_YELLOW, "continued");
+		fprintf(trace->output, "]: %s()", sc->name);
 	}
 
-	return path;
+	if (sc->fmt == NULL) {
+signed_print:
+		fprintf(trace->output, ") = %d", ret);
+	} else if (ret < 0 && sc->fmt->errmsg) {
+		char bf[256];
+		const char *emsg = strerror_r(-ret, bf, sizeof(bf)),
+			   *e = audit_errno_to_name(-ret);
+
+		fprintf(trace->output, ") = -1 %s %s", e, emsg);
+	} else if (ret == 0 && sc->fmt->timeout)
+		fprintf(trace->output, ") = 0 Timeout");
+	else if (sc->fmt->hexret)
+		fprintf(trace->output, ") = %#x", ret);
+	else
+		goto signed_print;
+
+	fputc('\n', trace->output);
+out:
+	ttrace->entry_pending = false;
+
+	return 0;
 }
 
-static const char * const trace_usage[] = {
-	"perf trace [<options>] <command>",
-	NULL
-};
+static int trace__vfs_getname(struct trace *trace, struct perf_evsel *evsel,
+			      struct perf_sample *sample)
+{
+	trace->last_vfs_getname = perf_evsel__rawptr(evsel, sample, "pathname");
+	return 0;
+}
 
-static const struct option options[] = {
-	OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
-		    "dump raw trace in ASCII"),
-	OPT_INCR('v', "verbose", &verbose,
-		    "be more verbose (show symbol address, etc)"),
-	OPT_BOOLEAN('L', "Latency", &latency_format,
-		    "show latency attributes (irqs/preemption disabled, etc)"),
-	OPT_CALLBACK_NOOPT('l', "list", NULL, NULL, "list available scripts",
-			   list_available_scripts),
-	OPT_CALLBACK('s', "script", NULL, "name",
-		     "script file name (lang:script name, script name, or *)",
-		     parse_scriptname),
-	OPT_STRING('g', "gen-script", &generate_script_lang, "lang",
-		   "generate perf-trace.xx script in specified language"),
-	OPT_STRING('i', "input", &input_name, "file",
-		    "input file name"),
-	OPT_BOOLEAN('d', "debug-ordering", &debug_ordering,
-		   "check that samples time ordering is monotonic"),
+static int trace__sched_stat_runtime(struct trace *trace, struct perf_evsel *evsel,
+				     struct perf_sample *sample)
+{
+        u64 runtime = perf_evsel__intval(evsel, sample, "runtime");
+	double runtime_ms = (double)runtime / NSEC_PER_MSEC;
+	struct thread *thread = machine__findnew_thread(trace->host,
+							sample->pid,
+							sample->tid);
+	struct thread_trace *ttrace = thread__trace(thread, trace->output);
+
+	if (ttrace == NULL)
+		goto out_dump;
+
+	ttrace->runtime_ms += runtime_ms;
+	trace->runtime_ms += runtime_ms;
+	return 0;
 
-	OPT_END()
-};
+out_dump:
+	fprintf(trace->output, "%s: comm=%s,pid=%u,runtime=%" PRIu64 ",vruntime=%" PRIu64 ")\n",
+	       evsel->name,
+	       perf_evsel__strval(evsel, sample, "comm"),
+	       (pid_t)perf_evsel__intval(evsel, sample, "pid"),
+	       runtime,
+	       perf_evsel__intval(evsel, sample, "vruntime"));
+	return 0;
+}
 
-int cmd_trace(int argc, const char **argv, const char *prefix __used)
+static bool skip_sample(struct trace *trace, struct perf_sample *sample)
 {
-	struct perf_session *session;
-	const char *suffix = NULL;
-	const char **__argv;
-	char *script_path;
-	int i, err;
-
-	if (argc >= 2 && strncmp(argv[1], "rec", strlen("rec")) == 0) {
-		if (argc < 3) {
-			fprintf(stderr,
-				"Please specify a record script\n");
-			return -1;
+	if ((trace->pid_list && intlist__find(trace->pid_list, sample->pid)) ||
+	    (trace->tid_list && intlist__find(trace->tid_list, sample->tid)))
+		return false;
+
+	if (trace->pid_list || trace->tid_list)
+		return true;
+
+	return false;
+}
+
+static int trace__process_sample(struct perf_tool *tool,
+				 union perf_event *event __maybe_unused,
+				 struct perf_sample *sample,
+				 struct perf_evsel *evsel,
+				 struct machine *machine __maybe_unused)
+{
+	struct trace *trace = container_of(tool, struct trace, tool);
+	int err = 0;
+
+	tracepoint_handler handler = evsel->handler;
+
+	if (skip_sample(trace, sample))
+		return 0;
+
+	if (!trace->full_time && trace->base_time == 0)
+		trace->base_time = sample->time;
+
+	if (handler) {
+		++trace->nr_events;
+		handler(trace, evsel, sample);
+	}
+
+	return err;
+}
+
+static int parse_target_str(struct trace *trace)
+{
+	if (trace->opts.target.pid) {
+		trace->pid_list = intlist__new(trace->opts.target.pid);
+		if (trace->pid_list == NULL) {
+			pr_err("Error parsing process id string\n");
+			return -EINVAL;
 		}
-		suffix = RECORD_SUFFIX;
 	}
 
-	if (argc >= 2 && strncmp(argv[1], "rep", strlen("rep")) == 0) {
-		if (argc < 3) {
-			fprintf(stderr,
-				"Please specify a report script\n");
-			return -1;
+	if (trace->opts.target.tid) {
+		trace->tid_list = intlist__new(trace->opts.target.tid);
+		if (trace->tid_list == NULL) {
+			pr_err("Error parsing thread id string\n");
+			return -EINVAL;
 		}
-		suffix = REPORT_SUFFIX;
 	}
 
-	if (!suffix && argc >= 2 && strncmp(argv[1], "-", strlen("-")) != 0) {
-		char *record_script_path, *report_script_path;
-		int live_pipe[2];
-		pid_t pid;
+	return 0;
+}
 
-		record_script_path = get_script_path(argv[1], RECORD_SUFFIX);
-		if (!record_script_path) {
-			fprintf(stderr, "record script not found\n");
-			return -1;
-		}
+static int trace__record(int argc, const char **argv)
+{
+	unsigned int rec_argc, i, j;
+	const char **rec_argv;
+	const char * const record_args[] = {
+		"record",
+		"-R",
+		"-m", "1024",
+		"-c", "1",
+		"-e",
+	};
+
+	/* +1 is for the event string below */
+	rec_argc = ARRAY_SIZE(record_args) + 1 + argc;
+	rec_argv = calloc(rec_argc + 1, sizeof(char *));
+
+	if (rec_argv == NULL)
+		return -ENOMEM;
 
-		report_script_path = get_script_path(argv[1], REPORT_SUFFIX);
-		if (!report_script_path) {
-			fprintf(stderr, "report script not found\n");
-			return -1;
-		}
+	for (i = 0; i < ARRAY_SIZE(record_args); i++)
+		rec_argv[i] = record_args[i];
 
-		if (pipe(live_pipe) < 0) {
-			perror("failed to create pipe");
-			exit(-1);
-		}
+	/* event string may be different for older kernels - e.g., RHEL6 */
+	if (is_valid_tracepoint("raw_syscalls:sys_enter"))
+		rec_argv[i] = "raw_syscalls:sys_enter,raw_syscalls:sys_exit";
+	else if (is_valid_tracepoint("syscalls:sys_enter"))
+		rec_argv[i] = "syscalls:sys_enter,syscalls:sys_exit";
+	else {
+		pr_err("Neither raw_syscalls nor syscalls events exist.\n");
+		return -1;
+	}
+	i++;
 
-		pid = fork();
-		if (pid < 0) {
-			perror("failed to fork");
-			exit(-1);
-		}
+	for (j = 0; j < (unsigned int)argc; j++, i++)
+		rec_argv[i] = argv[j];
 
-		if (!pid) {
-			dup2(live_pipe[1], 1);
-			close(live_pipe[0]);
+	return cmd_record(i, rec_argv, NULL);
+}
 
-			__argv = malloc(5 * sizeof(const char *));
-			__argv[0] = "/bin/sh";
-			__argv[1] = record_script_path;
-			__argv[2] = "-o";
-			__argv[3] = "-";
-			__argv[4] = NULL;
+static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp);
 
-			execvp("/bin/sh", (char **)__argv);
-			exit(-1);
-		}
+static void perf_evlist__add_vfs_getname(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evsel__newtp("probe", "vfs_getname");
+	if (evsel == NULL)
+		return;
+
+	if (perf_evsel__field(evsel, "pathname") == NULL) {
+		perf_evsel__delete(evsel);
+		return;
+	}
+
+	evsel->handler = trace__vfs_getname;
+	perf_evlist__add(evlist, evsel);
+}
+
+static int trace__run(struct trace *trace, int argc, const char **argv)
+{
+	struct perf_evlist *evlist = perf_evlist__new();
+	struct perf_evsel *evsel;
+	int err = -1, i;
+	unsigned long before;
+	const bool forks = argc > 0;
+
+	trace->live = true;
+
+	if (evlist == NULL) {
+		fprintf(trace->output, "Not enough memory to run!\n");
+		goto out;
+	}
+
+	if (perf_evlist__add_syscall_newtp(evlist, trace__sys_enter, trace__sys_exit))
+		goto out_error_tp;
 
-		dup2(live_pipe[0], 0);
-		close(live_pipe[1]);
+	perf_evlist__add_vfs_getname(evlist);
 
-		__argv = malloc((argc + 3) * sizeof(const char *));
-		__argv[0] = "/bin/sh";
-		__argv[1] = report_script_path;
-		for (i = 2; i < argc; i++)
-			__argv[i] = argv[i];
-		__argv[i++] = "-i";
-		__argv[i++] = "-";
-		__argv[i++] = NULL;
+	if (trace->sched &&
+		perf_evlist__add_newtp(evlist, "sched", "sched_stat_runtime",
+				trace__sched_stat_runtime))
+		goto out_error_tp;
 
-		execvp("/bin/sh", (char **)__argv);
-		exit(-1);
+	err = perf_evlist__create_maps(evlist, &trace->opts.target);
+	if (err < 0) {
+		fprintf(trace->output, "Problems parsing the target to trace, check your options!\n");
+		goto out_delete_evlist;
 	}
 
-	if (suffix) {
-		script_path = get_script_path(argv[2], suffix);
-		if (!script_path) {
-			fprintf(stderr, "script not found\n");
-			return -1;
+	err = trace__symbols_init(trace, evlist);
+	if (err < 0) {
+		fprintf(trace->output, "Problems initializing symbol libraries!\n");
+		goto out_delete_evlist;
+	}
+
+	perf_evlist__config(evlist, &trace->opts);
+
+	signal(SIGCHLD, sig_handler);
+	signal(SIGINT, sig_handler);
+
+	if (forks) {
+		err = perf_evlist__prepare_workload(evlist, &trace->opts.target,
+						    argv, false, NULL);
+		if (err < 0) {
+			fprintf(trace->output, "Couldn't run the workload!\n");
+			goto out_delete_evlist;
 		}
+	}
 
-		__argv = malloc((argc + 1) * sizeof(const char *));
-		__argv[0] = "/bin/sh";
-		__argv[1] = script_path;
-		for (i = 3; i < argc; i++)
-			__argv[i - 1] = argv[i];
-		__argv[argc - 1] = NULL;
+	err = perf_evlist__open(evlist);
+	if (err < 0)
+		goto out_error_open;
 
-		execvp("/bin/sh", (char **)__argv);
-		exit(-1);
+	err = perf_evlist__mmap(evlist, trace->opts.mmap_pages, false);
+	if (err < 0) {
+		fprintf(trace->output, "Couldn't mmap the events: %s\n", strerror(errno));
+		goto out_delete_evlist;
 	}
 
-	setup_scripting();
+	perf_evlist__enable(evlist);
+
+	if (forks)
+		perf_evlist__start_workload(evlist);
 
-	argc = parse_options(argc, argv, options, trace_usage,
-			     PARSE_OPT_STOP_AT_NON_OPTION);
+	trace->multiple_threads = evlist->threads->map[0] == -1 || evlist->threads->nr > 1;
+again:
+	before = trace->nr_events;
+
+	for (i = 0; i < evlist->nr_mmaps; i++) {
+		union perf_event *event;
+
+		while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
+			const u32 type = event->header.type;
+			tracepoint_handler handler;
+			struct perf_sample sample;
+
+			++trace->nr_events;
+
+			err = perf_evlist__parse_sample(evlist, event, &sample);
+			if (err) {
+				fprintf(trace->output, "Can't parse sample, err = %d, skipping...\n", err);
+				goto next_event;
+			}
+
+			if (!trace->full_time && trace->base_time == 0)
+				trace->base_time = sample.time;
+
+			if (type != PERF_RECORD_SAMPLE) {
+				trace__process_event(trace, trace->host, event, &sample);
+				continue;
+			}
+
+			evsel = perf_evlist__id2evsel(evlist, sample.id);
+			if (evsel == NULL) {
+				fprintf(trace->output, "Unknown tp ID %" PRIu64 ", skipping...\n", sample.id);
+				goto next_event;
+			}
+
+			if (sample.raw_data == NULL) {
+				fprintf(trace->output, "%s sample with no payload for tid: %d, cpu %d, raw_size=%d, skipping...\n",
+				       perf_evsel__name(evsel), sample.tid,
+				       sample.cpu, sample.raw_size);
+				goto next_event;
+			}
+
+			handler = evsel->handler;
+			handler(trace, evsel, &sample);
+next_event:
+			perf_evlist__mmap_consume(evlist, i);
+
+			if (interrupted)
+				goto out_disable;
+		}
+	}
+
+	if (trace->nr_events == before) {
+		int timeout = done ? 100 : -1;
+
+		if (poll(evlist->pollfd, evlist->nr_fds, timeout) > 0)
+			goto again;
+	} else {
+		goto again;
+	}
+
+out_disable:
+	perf_evlist__disable(evlist);
+
+	if (!err) {
+		if (trace->summary)
+			trace__fprintf_thread_summary(trace, trace->output);
+
+		if (trace->show_tool_stats) {
+			fprintf(trace->output, "Stats:\n "
+					       " vfs_getname : %" PRIu64 "\n"
+					       " proc_getname: %" PRIu64 "\n",
+				trace->stats.vfs_getname,
+				trace->stats.proc_getname);
+		}
+	}
+
+out_delete_evlist:
+	perf_evlist__delete(evlist);
+out:
+	trace->live = false;
+	return err;
+{
+	char errbuf[BUFSIZ];
+
+out_error_tp:
+	perf_evlist__strerror_tp(evlist, errno, errbuf, sizeof(errbuf));
+	goto out_error;
+
+out_error_open:
+	perf_evlist__strerror_open(evlist, errno, errbuf, sizeof(errbuf));
+
+out_error:
+	fprintf(trace->output, "%s\n", errbuf);
+	goto out_delete_evlist;
+}
+}
+
+static int trace__replay(struct trace *trace)
+{
+	const struct perf_evsel_str_handler handlers[] = {
+		{ "probe:vfs_getname",	     trace__vfs_getname, },
+	};
+	struct perf_data_file file = {
+		.path  = input_name,
+		.mode  = PERF_DATA_MODE_READ,
+	};
+	struct perf_session *session;
+	struct perf_evsel *evsel;
+	int err = -1;
+
+	trace->tool.sample	  = trace__process_sample;
+	trace->tool.mmap	  = perf_event__process_mmap;
+	trace->tool.mmap2	  = perf_event__process_mmap2;
+	trace->tool.comm	  = perf_event__process_comm;
+	trace->tool.exit	  = perf_event__process_exit;
+	trace->tool.fork	  = perf_event__process_fork;
+	trace->tool.attr	  = perf_event__process_attr;
+	trace->tool.tracing_data = perf_event__process_tracing_data;
+	trace->tool.build_id	  = perf_event__process_build_id;
+
+	trace->tool.ordered_samples = true;
+	trace->tool.ordering_requires_timestamps = true;
+
+	/* add tid to output */
+	trace->multiple_threads = true;
 
 	if (symbol__init() < 0)
 		return -1;
-	if (!script_name)
-		setup_pager();
 
-	session = perf_session__new(input_name, O_RDONLY, 0, false);
+	session = perf_session__new(&file, false, &trace->tool);
 	if (session == NULL)
 		return -ENOMEM;
 
-	if (strcmp(input_name, "-") &&
-	    !perf_session__has_traces(session, "record -R"))
-		return -EINVAL;
+	trace->host = &session->machines.host;
 
-	if (generate_script_lang) {
-		struct stat perf_stat;
+	err = perf_session__set_tracepoints_handlers(session, handlers);
+	if (err)
+		goto out;
 
-		int input = open(input_name, O_RDONLY);
-		if (input < 0) {
-			perror("failed to open file");
-			exit(-1);
-		}
+	evsel = perf_evlist__find_tracepoint_by_name(session->evlist,
+						     "raw_syscalls:sys_enter");
+	/* older kernels have syscalls tp versus raw_syscalls */
+	if (evsel == NULL)
+		evsel = perf_evlist__find_tracepoint_by_name(session->evlist,
+							     "syscalls:sys_enter");
+	if (evsel == NULL) {
+		pr_err("Data file does not have raw_syscalls:sys_enter event\n");
+		goto out;
+	}
 
-		err = fstat(input, &perf_stat);
-		if (err < 0) {
-			perror("failed to stat file");
-			exit(-1);
+	if (perf_evsel__init_syscall_tp(evsel, trace__sys_enter) < 0 ||
+	    perf_evsel__init_sc_tp_ptr_field(evsel, args)) {
+		pr_err("Error during initialize raw_syscalls:sys_enter event\n");
+		goto out;
+	}
+
+	evsel = perf_evlist__find_tracepoint_by_name(session->evlist,
+						     "raw_syscalls:sys_exit");
+	if (evsel == NULL)
+		evsel = perf_evlist__find_tracepoint_by_name(session->evlist,
+							     "syscalls:sys_exit");
+	if (evsel == NULL) {
+		pr_err("Data file does not have raw_syscalls:sys_exit event\n");
+		goto out;
+	}
+
+	if (perf_evsel__init_syscall_tp(evsel, trace__sys_exit) < 0 ||
+	    perf_evsel__init_sc_tp_uint_field(evsel, ret)) {
+		pr_err("Error during initialize raw_syscalls:sys_exit event\n");
+		goto out;
+	}
+
+	err = parse_target_str(trace);
+	if (err != 0)
+		goto out;
+
+	setup_pager();
+
+	err = perf_session__process_events(session, &trace->tool);
+	if (err)
+		pr_err("Failed to process events, error %d", err);
+
+	else if (trace->summary)
+		trace__fprintf_thread_summary(trace, trace->output);
+
+out:
+	perf_session__delete(session);
+
+	return err;
+}
+
+static size_t trace__fprintf_threads_header(FILE *fp)
+{
+	size_t printed;
+
+	printed  = fprintf(fp, "\n Summary of events:\n\n");
+
+	return printed;
+}
+
+static size_t thread__dump_stats(struct thread_trace *ttrace,
+				 struct trace *trace, FILE *fp)
+{
+	struct stats *stats;
+	size_t printed = 0;
+	struct syscall *sc;
+	struct int_node *inode = intlist__first(ttrace->syscall_stats);
+
+	if (inode == NULL)
+		return 0;
+
+	printed += fprintf(fp, "\n");
+
+	printed += fprintf(fp, "   syscall            calls      min       avg       max      stddev\n");
+	printed += fprintf(fp, "                               (msec)    (msec)    (msec)        (%%)\n");
+	printed += fprintf(fp, "   --------------- -------- --------- --------- ---------     ------\n");
+
+	/* each int_node is a syscall */
+	while (inode) {
+		stats = inode->priv;
+		if (stats) {
+			double min = (double)(stats->min) / NSEC_PER_MSEC;
+			double max = (double)(stats->max) / NSEC_PER_MSEC;
+			double avg = avg_stats(stats);
+			double pct;
+			u64 n = (u64) stats->n;
+
+			pct = avg ? 100.0 * stddev_stats(stats)/avg : 0.0;
+			avg /= NSEC_PER_MSEC;
+
+			sc = &trace->syscalls.table[inode->i];
+			printed += fprintf(fp, "   %-15s", sc->name);
+			printed += fprintf(fp, " %8" PRIu64 " %9.3f %9.3f",
+					   n, min, avg);
+			printed += fprintf(fp, " %9.3f %9.2f%%\n", max, pct);
 		}
 
-		if (!perf_stat.st_size) {
-			fprintf(stderr, "zero-sized file, nothing to do!\n");
-			exit(0);
+		inode = intlist__next(inode);
+	}
+
+	printed += fprintf(fp, "\n\n");
+
+	return printed;
+}
+
+/* struct used to pass data to per-thread function */
+struct summary_data {
+	FILE *fp;
+	struct trace *trace;
+	size_t printed;
+};
+
+static int trace__fprintf_one_thread(struct thread *thread, void *priv)
+{
+	struct summary_data *data = priv;
+	FILE *fp = data->fp;
+	size_t printed = data->printed;
+	struct trace *trace = data->trace;
+	struct thread_trace *ttrace = thread->priv;
+	double ratio;
+
+	if (ttrace == NULL)
+		return 0;
+
+	ratio = (double)ttrace->nr_events / trace->nr_events * 100.0;
+
+	printed += fprintf(fp, " %s (%d), ", thread__comm_str(thread), thread->tid);
+	printed += fprintf(fp, "%lu events, ", ttrace->nr_events);
+	printed += fprintf(fp, "%.1f%%", ratio);
+	printed += fprintf(fp, ", %.3f msec\n", ttrace->runtime_ms);
+	printed += thread__dump_stats(ttrace, trace, fp);
+
+	data->printed += printed;
+
+	return 0;
+}
+
+static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp)
+{
+	struct summary_data data = {
+		.fp = fp,
+		.trace = trace
+	};
+	data.printed = trace__fprintf_threads_header(fp);
+
+	machine__for_each_thread(trace->host, trace__fprintf_one_thread, &data);
+
+	return data.printed;
+}
+
+static int trace__set_duration(const struct option *opt, const char *str,
+			       int unset __maybe_unused)
+{
+	struct trace *trace = opt->value;
+
+	trace->duration_filter = atof(str);
+	return 0;
+}
+
+static int trace__open_output(struct trace *trace, const char *filename)
+{
+	struct stat st;
+
+	if (!stat(filename, &st) && st.st_size) {
+		char oldname[PATH_MAX];
+
+		scnprintf(oldname, sizeof(oldname), "%s.old", filename);
+		unlink(oldname);
+		rename(filename, oldname);
+	}
+
+	trace->output = fopen(filename, "w");
+
+	return trace->output == NULL ? -errno : 0;
+}
+
+int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
+{
+	const char * const trace_usage[] = {
+		"perf trace [<options>] [<command>]",
+		"perf trace [<options>] -- <command> [<options>]",
+		"perf trace record [<options>] [<command>]",
+		"perf trace record [<options>] -- <command> [<options>]",
+		NULL
+	};
+	struct trace trace = {
+		.audit = {
+			.machine = audit_detect_machine(),
+			.open_id = audit_name_to_syscall("open", trace.audit.machine),
+		},
+		.syscalls = {
+			. max = -1,
+		},
+		.opts = {
+			.target = {
+				.uid	   = UINT_MAX,
+				.uses_mmap = true,
+			},
+			.user_freq     = UINT_MAX,
+			.user_interval = ULLONG_MAX,
+			.no_buffering  = true,
+			.mmap_pages    = 1024,
+		},
+		.output = stdout,
+		.show_comm = true,
+	};
+	const char *output_name = NULL;
+	const char *ev_qualifier_str = NULL;
+	const struct option trace_options[] = {
+	OPT_BOOLEAN(0, "comm", &trace.show_comm,
+		    "show the thread COMM next to its id"),
+	OPT_BOOLEAN(0, "tool_stats", &trace.show_tool_stats, "show tool stats"),
+	OPT_STRING('e', "expr", &ev_qualifier_str, "expr",
+		    "list of events to trace"),
+	OPT_STRING('o', "output", &output_name, "file", "output file name"),
+	OPT_STRING('i', "input", &input_name, "file", "Analyze events in file"),
+	OPT_STRING('p', "pid", &trace.opts.target.pid, "pid",
+		    "trace events on existing process id"),
+	OPT_STRING('t', "tid", &trace.opts.target.tid, "tid",
+		    "trace events on existing thread id"),
+	OPT_BOOLEAN('a', "all-cpus", &trace.opts.target.system_wide,
+		    "system-wide collection from all CPUs"),
+	OPT_STRING('C', "cpu", &trace.opts.target.cpu_list, "cpu",
+		    "list of cpus to monitor"),
+	OPT_BOOLEAN(0, "no-inherit", &trace.opts.no_inherit,
+		    "child tasks do not inherit counters"),
+	OPT_CALLBACK('m', "mmap-pages", &trace.opts.mmap_pages, "pages",
+		     "number of mmap data pages",
+		     perf_evlist__parse_mmap_pages),
+	OPT_STRING('u', "uid", &trace.opts.target.uid_str, "user",
+		   "user to profile"),
+	OPT_CALLBACK(0, "duration", &trace, "float",
+		     "show only events with duration > N.M ms",
+		     trace__set_duration),
+	OPT_BOOLEAN(0, "sched", &trace.sched, "show blocking scheduler events"),
+	OPT_INCR('v', "verbose", &verbose, "be more verbose"),
+	OPT_BOOLEAN('T', "time", &trace.full_time,
+		    "Show full timestamp, not time relative to first start"),
+	OPT_BOOLEAN('s', "summary", &trace.summary_only,
+		    "Show only syscall summary with statistics"),
+	OPT_BOOLEAN('S', "with-summary", &trace.summary,
+		    "Show all syscalls and summary with statistics"),
+	OPT_END()
+	};
+	int err;
+	char bf[BUFSIZ];
+
+	if ((argc > 1) && (strcmp(argv[1], "record") == 0))
+		return trace__record(argc-2, &argv[2]);
+
+	argc = parse_options(argc, argv, trace_options, trace_usage, 0);
+
+	/* summary_only implies summary option, but don't overwrite summary if set */
+	if (trace.summary_only)
+		trace.summary = trace.summary_only;
+
+	if (output_name != NULL) {
+		err = trace__open_output(&trace, output_name);
+		if (err < 0) {
+			perror("failed to create output file");
+			goto out;
 		}
+	}
 
-		scripting_ops = script_spec__lookup(generate_script_lang);
-		if (!scripting_ops) {
-			fprintf(stderr, "invalid language specifier");
-			return -1;
+	if (ev_qualifier_str != NULL) {
+		const char *s = ev_qualifier_str;
+
+		trace.not_ev_qualifier = *s == '!';
+		if (trace.not_ev_qualifier)
+			++s;
+		trace.ev_qualifier = strlist__new(true, s);
+		if (trace.ev_qualifier == NULL) {
+			fputs("Not enough memory to parse event qualifier",
+			      trace.output);
+			err = -ENOMEM;
+			goto out_close;
 		}
+	}
 
-		err = scripting_ops->generate_script("perf-trace");
-		goto out;
+	err = target__validate(&trace.opts.target);
+	if (err) {
+		target__strerror(&trace.opts.target, err, bf, sizeof(bf));
+		fprintf(trace.output, "%s", bf);
+		goto out_close;
 	}
 
-	if (script_name) {
-		err = scripting_ops->start_script(script_name, argc, argv);
-		if (err)
-			goto out;
-		pr_debug("perf trace started with script %s\n\n", script_name);
+	err = target__parse_uid(&trace.opts.target);
+	if (err) {
+		target__strerror(&trace.opts.target, err, bf, sizeof(bf));
+		fprintf(trace.output, "%s", bf);
+		goto out_close;
 	}
 
-	err = __cmd_trace(session);
+	if (!argc && target__none(&trace.opts.target))
+		trace.opts.target.system_wide = true;
 
-	perf_session__delete(session);
-	cleanup_scripting();
+	if (input_name)
+		err = trace__replay(&trace);
+	else
+		err = trace__run(&trace, argc, argv);
+
+out_close:
+	if (output_name != NULL)
+		fclose(trace.output);
 out:
 	return err;
 }
diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h
index 921245b2858..b210d62907e 100644
--- a/tools/perf/builtin.h
+++ b/tools/perf/builtin.h
@@ -4,7 +4,6 @@
 #include "util/util.h"
 #include "util/strbuf.h"
 
-extern const char perf_version_string[];
 extern const char perf_usage_string[];
 extern const char perf_more_info_string[];
 
@@ -19,6 +18,7 @@ extern int cmd_bench(int argc, const char **argv, const char *prefix);
 extern int cmd_buildid_cache(int argc, const char **argv, const char *prefix);
 extern int cmd_buildid_list(int argc, const char **argv, const char *prefix);
 extern int cmd_diff(int argc, const char **argv, const char *prefix);
+extern int cmd_evlist(int argc, const char **argv, const char *prefix);
 extern int cmd_help(int argc, const char **argv, const char *prefix);
 extern int cmd_sched(int argc, const char **argv, const char *prefix);
 extern int cmd_list(int argc, const char **argv, const char *prefix);
@@ -27,13 +27,16 @@ extern int cmd_report(int argc, const char **argv, const char *prefix);
 extern int cmd_stat(int argc, const char **argv, const char *prefix);
 extern int cmd_timechart(int argc, const char **argv, const char *prefix);
 extern int cmd_top(int argc, const char **argv, const char *prefix);
-extern int cmd_trace(int argc, const char **argv, const char *prefix);
+extern int cmd_script(int argc, const char **argv, const char *prefix);
 extern int cmd_version(int argc, const char **argv, const char *prefix);
 extern int cmd_probe(int argc, const char **argv, const char *prefix);
 extern int cmd_kmem(int argc, const char **argv, const char *prefix);
 extern int cmd_lock(int argc, const char **argv, const char *prefix);
 extern int cmd_kvm(int argc, const char **argv, const char *prefix);
 extern int cmd_test(int argc, const char **argv, const char *prefix);
+extern int cmd_trace(int argc, const char **argv, const char *prefix);
 extern int cmd_inject(int argc, const char **argv, const char *prefix);
+extern int cmd_mem(int argc, const char **argv, const char *prefix);
 
+extern int find_scripts(char **scripts_array, char **scripts_path_array);
 #endif
diff --git a/tools/perf/command-list.txt b/tools/perf/command-list.txt
index 949d77fc0b9..0906fc401c5 100644
--- a/tools/perf/command-list.txt
+++ b/tools/perf/command-list.txt
@@ -8,17 +8,20 @@ perf-bench			mainporcelain common
 perf-buildid-cache		mainporcelain common
 perf-buildid-list		mainporcelain common
 perf-diff			mainporcelain common
+perf-evlist			mainporcelain common
 perf-inject			mainporcelain common
+perf-kmem			mainporcelain common
+perf-kvm			mainporcelain common
 perf-list			mainporcelain common
-perf-sched			mainporcelain common
+perf-lock			mainporcelain common
+perf-mem			mainporcelain common
+perf-probe			mainporcelain full
 perf-record			mainporcelain common
 perf-report			mainporcelain common
+perf-sched			mainporcelain common
+perf-script			mainporcelain common
 perf-stat			mainporcelain common
+perf-test			mainporcelain common
 perf-timechart			mainporcelain common
 perf-top			mainporcelain common
 perf-trace			mainporcelain common
-perf-probe			mainporcelain common
-perf-kmem			mainporcelain common
-perf-lock			mainporcelain common
-perf-kvm			mainporcelain common
-perf-test			mainporcelain common
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
new file mode 100644
index 00000000000..f30ac5e5d27
--- /dev/null
+++ b/tools/perf/config/Makefile
@@ -0,0 +1,738 @@
+
+ifeq ($(src-perf),)
+src-perf := $(srctree)/tools/perf
+endif
+
+ifeq ($(obj-perf),)
+obj-perf := $(OUTPUT)
+endif
+
+ifneq ($(obj-perf),)
+obj-perf := $(abspath $(obj-perf))/
+endif
+
+LIB_INCLUDE := $(srctree)/tools/lib/
+CFLAGS := $(EXTRA_CFLAGS) $(EXTRA_WARNINGS)
+
+include $(src-perf)/config/Makefile.arch
+
+NO_PERF_REGS := 1
+
+# Additional ARCH settings for x86
+ifeq ($(ARCH),x86)
+  ifeq (${IS_X86_64}, 1)
+    CFLAGS += -DHAVE_ARCH_X86_64_SUPPORT
+    ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memset_64.S
+    LIBUNWIND_LIBS = -lunwind -lunwind-x86_64
+  else
+    LIBUNWIND_LIBS = -lunwind -lunwind-x86
+  endif
+  NO_PERF_REGS := 0
+endif
+
+ifeq ($(ARCH),arm)
+  NO_PERF_REGS := 0
+  LIBUNWIND_LIBS = -lunwind -lunwind-arm
+endif
+
+ifeq ($(ARCH),arm64)
+  NO_PERF_REGS := 0
+  LIBUNWIND_LIBS = -lunwind -lunwind-aarch64
+endif
+
+# So far there's only x86 and arm libdw unwind support merged in perf.
+# Disable it on all other architectures in case libdw unwind
+# support is detected in system. Add supported architectures
+# to the check.
+ifneq ($(ARCH),$(filter $(ARCH),x86 arm))
+  NO_LIBDW_DWARF_UNWIND := 1
+endif
+
+ifeq ($(LIBUNWIND_LIBS),)
+  NO_LIBUNWIND := 1
+else
+  #
+  # For linking with debug library, run like:
+  #
+  #   make DEBUG=1 LIBUNWIND_DIR=/opt/libunwind/
+  #
+  ifdef LIBUNWIND_DIR
+    LIBUNWIND_CFLAGS  = -I$(LIBUNWIND_DIR)/include
+    LIBUNWIND_LDFLAGS = -L$(LIBUNWIND_DIR)/lib
+  endif
+  LIBUNWIND_LDFLAGS += $(LIBUNWIND_LIBS)
+
+  # Set per-feature check compilation flags
+  FEATURE_CHECK_CFLAGS-libunwind = $(LIBUNWIND_CFLAGS)
+  FEATURE_CHECK_LDFLAGS-libunwind = $(LIBUNWIND_LDFLAGS)
+  FEATURE_CHECK_CFLAGS-libunwind-debug-frame = $(LIBUNWIND_CFLAGS)
+  FEATURE_CHECK_LDFLAGS-libunwind-debug-frame = $(LIBUNWIND_LDFLAGS)
+endif
+
+ifeq ($(NO_PERF_REGS),0)
+  CFLAGS += -DHAVE_PERF_REGS_SUPPORT
+endif
+
+ifndef NO_LIBELF
+  # 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
+  FEATURE_CHECK_CFLAGS-libdw-dwarf-unwind := $(LIBDW_CFLAGS)
+  FEATURE_CHECK_LDFLAGS-libdw-dwarf-unwind := $(LIBDW_LDFLAGS) -ldw
+endif
+
+# include ARCH specific config
+-include $(src-perf)/arch/$(ARCH)/Makefile
+
+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
+
+ifndef DEBUG
+  DEBUG := 0
+endif
+
+ifeq ($(DEBUG),0)
+  CFLAGS += -O6
+endif
+
+ifdef PARSER_DEBUG
+  PARSER_DEBUG_BISON := -t
+  PARSER_DEBUG_FLEX  := -d
+  CFLAGS             += -DPARSER_DEBUG
+endif
+
+CFLAGS += -fno-omit-frame-pointer
+CFLAGS += -ggdb3
+CFLAGS += -funwind-tables
+CFLAGS += -Wall
+CFLAGS += -Wextra
+CFLAGS += -std=gnu99
+
+# Enforce a non-executable stack, as we may regress (again) in the future by
+# adding assembler files missing the .GNU-stack linker note.
+LDFLAGS += -Wl,-z,noexecstack
+
+EXTLIBS = -lelf -lpthread -lrt -lm -ldl
+
+ifneq ($(OUTPUT),)
+  OUTPUT_FEATURES = $(OUTPUT)config/feature-checks/
+  $(shell mkdir -p $(OUTPUT_FEATURES))
+endif
+
+feature_check = $(eval $(feature_check_code))
+define feature_check_code
+  feature-$(1) := $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) CFLAGS="$(EXTRA_CFLAGS) $(FEATURE_CHECK_CFLAGS-$(1))" LDFLAGS="$(LDFLAGS) $(FEATURE_CHECK_LDFLAGS-$(1))" -C config/feature-checks test-$1.bin >/dev/null 2>/dev/null && echo 1 || echo 0)
+endef
+
+feature_set = $(eval $(feature_set_code))
+define feature_set_code
+  feature-$(1) := 1
+endef
+
+#
+# Build the feature check binaries in parallel, ignore errors, ignore return value and suppress output:
+#
+
+#
+# Note that this is not a complete list of all feature tests, just
+# those that are typically built on a fully configured system.
+#
+# [ Feature tests not mentioned here have to be built explicitly in
+#   the rule that uses them - an example for that is the 'bionic'
+#   feature check. ]
+#
+CORE_FEATURE_TESTS =			\
+	backtrace			\
+	dwarf				\
+	fortify-source			\
+	glibc				\
+	gtk2				\
+	gtk2-infobar			\
+	libaudit			\
+	libbfd				\
+	libelf				\
+	libelf-getphdrnum		\
+	libelf-mmap			\
+	libnuma				\
+	libperl				\
+	libpython			\
+	libpython-version		\
+	libslang			\
+	libunwind			\
+	stackprotector-all		\
+	timerfd				\
+	libdw-dwarf-unwind
+
+LIB_FEATURE_TESTS =			\
+	dwarf				\
+	glibc				\
+	gtk2				\
+	libaudit			\
+	libbfd				\
+	libelf				\
+	libnuma				\
+	libperl				\
+	libpython			\
+	libslang			\
+	libunwind			\
+	libdw-dwarf-unwind
+
+VF_FEATURE_TESTS =			\
+	backtrace			\
+	fortify-source			\
+	gtk2-infobar			\
+	libelf-getphdrnum		\
+	libelf-mmap			\
+	libpython-version		\
+	stackprotector-all		\
+	timerfd				\
+	libunwind-debug-frame		\
+	bionic				\
+	liberty				\
+	liberty-z			\
+	cplus-demangle
+
+# Set FEATURE_CHECK_(C|LD)FLAGS-all for all CORE_FEATURE_TESTS features.
+# If in the future we need per-feature checks/flags for features not
+# mentioned in this list we need to refactor this ;-).
+set_test_all_flags = $(eval $(set_test_all_flags_code))
+define set_test_all_flags_code
+  FEATURE_CHECK_CFLAGS-all  += $(FEATURE_CHECK_CFLAGS-$(1))
+  FEATURE_CHECK_LDFLAGS-all += $(FEATURE_CHECK_LDFLAGS-$(1))
+endef
+
+$(foreach feat,$(CORE_FEATURE_TESTS),$(call set_test_all_flags,$(feat)))
+
+#
+# Special fast-path for the 'all features are available' case:
+#
+$(call feature_check,all,$(MSG))
+
+#
+# Just in case the build freshly failed, make sure we print the
+# feature matrix:
+#
+ifeq ($(feature-all), 1)
+  #
+  # test-all.c passed - just set all the core feature flags to 1:
+  #
+  $(foreach feat,$(CORE_FEATURE_TESTS),$(call feature_set,$(feat)))
+else
+  $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) CFLAGS="$(EXTRA_CFLAGS)" LDFLAGS=$(LDFLAGS) -i -j -C config/feature-checks $(addsuffix .bin,$(CORE_FEATURE_TESTS)) >/dev/null 2>&1)
+  $(foreach feat,$(CORE_FEATURE_TESTS),$(call feature_check,$(feat)))
+endif
+
+ifeq ($(feature-stackprotector-all), 1)
+  CFLAGS += -fstack-protector-all
+endif
+
+ifeq ($(DEBUG),0)
+  ifeq ($(feature-fortify-source), 1)
+    CFLAGS += -D_FORTIFY_SOURCE=2
+  endif
+endif
+
+CFLAGS += -I$(src-perf)/util/include
+CFLAGS += -I$(src-perf)/arch/$(ARCH)/include
+CFLAGS += -I$(srctree)/tools/include/
+CFLAGS += -I$(srctree)/arch/$(ARCH)/include/uapi
+CFLAGS += -I$(srctree)/arch/$(ARCH)/include
+CFLAGS += -I$(srctree)/include/uapi
+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$(LIB_INCLUDE)
+
+CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
+
+ifndef NO_BIONIC
+  $(call feature_check,bionic)
+  ifeq ($(feature-bionic), 1)
+    BIONIC := 1
+    EXTLIBS := $(filter-out -lrt,$(EXTLIBS))
+    EXTLIBS := $(filter-out -lpthread,$(EXTLIBS))
+  endif
+endif
+
+ifdef NO_LIBELF
+  NO_DWARF := 1
+  NO_DEMANGLE := 1
+  NO_LIBUNWIND := 1
+  NO_LIBDW_DWARF_UNWIND := 1
+else
+  ifeq ($(feature-libelf), 0)
+    ifeq ($(feature-glibc), 1)
+      LIBC_SUPPORT := 1
+    endif
+    ifeq ($(BIONIC),1)
+      LIBC_SUPPORT := 1
+    endif
+    ifeq ($(LIBC_SUPPORT),1)
+      msg := $(warning No libelf found, disables 'probe' tool, please install elfutils-libelf-devel/libelf-dev);
+
+      NO_LIBELF := 1
+      NO_DWARF := 1
+      NO_DEMANGLE := 1
+      NO_LIBUNWIND := 1
+      NO_LIBDW_DWARF_UNWIND := 1
+    else
+      ifneq ($(filter s% -static%,$(LDFLAGS),),)
+        msg := $(error No static glibc found, please install glibc-static);
+      else
+        msg := $(error No gnu/libc-version.h found, please install glibc-dev[el]);
+      endif
+    endif
+  else
+    ifndef NO_LIBDW_DWARF_UNWIND
+      ifneq ($(feature-libdw-dwarf-unwind),1)
+        NO_LIBDW_DWARF_UNWIND := 1
+        msg := $(warning No libdw DWARF unwind found, Please install elfutils-devel/libdw-dev >= 0.158 and/or set LIBDW_DIR);
+      endif
+    endif
+    ifneq ($(feature-dwarf), 1)
+      msg := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev);
+      NO_DWARF := 1
+    endif # Dwarf support
+  endif # libelf support
+endif # NO_LIBELF
+
+ifndef NO_LIBELF
+  CFLAGS += -DHAVE_LIBELF_SUPPORT
+
+  ifeq ($(feature-libelf-mmap), 1)
+    CFLAGS += -DHAVE_LIBELF_MMAP_SUPPORT
+  endif
+
+  ifeq ($(feature-libelf-getphdrnum), 1)
+    CFLAGS += -DHAVE_ELF_GETPHDRNUM_SUPPORT
+  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 += -DHAVE_DWARF_SUPPORT $(LIBDW_CFLAGS)
+      LDFLAGS += $(LIBDW_LDFLAGS)
+      EXTLIBS += -lelf -ldw
+    endif # PERF_HAVE_DWARF_REGS
+  endif # NO_DWARF
+endif # NO_LIBELF
+
+ifndef NO_LIBUNWIND
+  ifneq ($(feature-libunwind), 1)
+    msg := $(warning No libunwind found. Please install libunwind-dev[el] >= 1.1 and/or set LIBUNWIND_DIR);
+    NO_LIBUNWIND := 1
+  endif
+endif
+
+dwarf-post-unwind := 1
+dwarf-post-unwind-text := BUG
+
+# setup DWARF post unwinder
+ifdef NO_LIBUNWIND
+  ifdef NO_LIBDW_DWARF_UNWIND
+    msg := $(warning Disabling post unwind, no support found.);
+    dwarf-post-unwind := 0
+  else
+    dwarf-post-unwind-text := libdw
+  endif
+else
+  dwarf-post-unwind-text := libunwind
+  # Enable libunwind support by default.
+  ifndef NO_LIBDW_DWARF_UNWIND
+    NO_LIBDW_DWARF_UNWIND := 1
+  endif
+endif
+
+ifeq ($(dwarf-post-unwind),1)
+  CFLAGS += -DHAVE_DWARF_UNWIND_SUPPORT
+else
+  NO_DWARF_UNWIND := 1
+endif
+
+ifndef NO_LIBUNWIND
+  ifeq ($(ARCH),$(filter $(ARCH),arm arm64))
+    $(call feature_check,libunwind-debug-frame)
+    ifneq ($(feature-libunwind-debug-frame), 1)
+      msg := $(warning No debug_frame support found in libunwind);
+      CFLAGS += -DNO_LIBUNWIND_DEBUG_FRAME
+    endif
+  else
+    # non-ARM has no dwarf_find_debug_frame() function:
+    CFLAGS += -DNO_LIBUNWIND_DEBUG_FRAME
+  endif
+  CFLAGS  += -DHAVE_LIBUNWIND_SUPPORT
+  EXTLIBS += $(LIBUNWIND_LIBS)
+  CFLAGS  += $(LIBUNWIND_CFLAGS)
+  LDFLAGS += $(LIBUNWIND_LDFLAGS)
+endif
+
+ifndef NO_LIBAUDIT
+  ifneq ($(feature-libaudit), 1)
+    msg := $(warning No libaudit.h found, disables 'trace' tool, please install audit-libs-devel or libaudit-dev);
+    NO_LIBAUDIT := 1
+  else
+    CFLAGS += -DHAVE_LIBAUDIT_SUPPORT
+    EXTLIBS += -laudit
+  endif
+endif
+
+ifdef NO_NEWT
+  NO_SLANG=1
+endif
+
+ifndef NO_SLANG
+  ifneq ($(feature-libslang), 1)
+    msg := $(warning slang not found, disables TUI support. Please install slang-devel or libslang-dev);
+    NO_SLANG := 1
+  else
+    # Fedora has /usr/include/slang/slang.h, but ubuntu /usr/include/slang.h
+    CFLAGS += -I/usr/include/slang
+    CFLAGS += -DHAVE_SLANG_SUPPORT
+    EXTLIBS += -lslang
+  endif
+endif
+
+ifndef NO_GTK2
+  FLAGS_GTK2=$(CFLAGS) $(LDFLAGS) $(EXTLIBS) $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null)
+  ifneq ($(feature-gtk2), 1)
+    msg := $(warning GTK2 not found, disables GTK2 support. Please install gtk2-devel or libgtk2.0-dev);
+    NO_GTK2 := 1
+  else
+    ifeq ($(feature-gtk2-infobar), 1)
+      GTK_CFLAGS := -DHAVE_GTK_INFO_BAR_SUPPORT
+    endif
+    CFLAGS += -DHAVE_GTK2_SUPPORT
+    GTK_CFLAGS += $(shell $(PKG_CONFIG) --cflags gtk+-2.0 2>/dev/null)
+    GTK_LIBS := $(shell $(PKG_CONFIG) --libs gtk+-2.0 2>/dev/null)
+    EXTLIBS += -ldl
+  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) $(PERL_EMBED_LDOPTS)
+
+  ifneq ($(feature-libperl), 1)
+    CFLAGS += -DNO_LIBPERL
+    NO_LIBPERL := 1
+    msg := $(warning Missing perl devel files. Disabling perl scripting support, consider installing perl-ExtUtils-Embed);
+  else
+    LDFLAGS += $(PERL_EMBED_LDFLAGS)
+    EXTLIBS += $(PERL_EMBED_LIBADD)
+  endif
+endif
+
+ifeq ($(feature-timerfd), 1)
+  CFLAGS += -DHAVE_TIMERFD_SUPPORT
+else
+  msg := $(warning No timerfd support. Disables 'perf kvm stat live');
+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) $(PYTHON_EMBED_LDOPTS)
+
+      ifneq ($(feature-libpython), 1)
+        $(call disable-python,Python.h (for Python 2.x))
+      else
+
+        ifneq ($(feature-libpython-version), 1)
+          $(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 += $(obj-perf)python/perf.so
+        endif
+      endif
+    endif
+  endif
+endif
+
+ifeq ($(feature-libbfd), 1)
+  EXTLIBS += -lbfd
+
+  # call all detections now so we get correct
+  # status in VF output
+  $(call feature_check,liberty)
+  $(call feature_check,liberty-z)
+  $(call feature_check,cplus-demangle)
+
+  ifeq ($(feature-liberty), 1)
+    EXTLIBS += -liberty
+  else
+    ifeq ($(feature-liberty-z), 1)
+      EXTLIBS += -liberty -lz
+    endif
+  endif
+endif
+
+ifdef NO_DEMANGLE
+  CFLAGS += -DNO_DEMANGLE
+else
+  ifdef HAVE_CPLUS_DEMANGLE_SUPPORT
+    EXTLIBS += -liberty
+    CFLAGS += -DHAVE_CPLUS_DEMANGLE_SUPPORT
+  else
+    ifneq ($(feature-libbfd), 1)
+      ifneq ($(feature-liberty), 1)
+        ifneq ($(feature-liberty-z), 1)
+          # we dont have neither HAVE_CPLUS_DEMANGLE_SUPPORT
+          # or any of 'bfd iberty z' trinity
+          ifeq ($(feature-cplus-demangle), 1)
+            EXTLIBS += -liberty
+            CFLAGS += -DHAVE_CPLUS_DEMANGLE_SUPPORT
+          else
+            msg := $(warning No bfd.h/libbfd found, install binutils-dev[el]/zlib-static to gain symbol demangling)
+            CFLAGS += -DNO_DEMANGLE
+          endif
+        endif
+      endif
+    endif
+  endif
+endif
+
+ifneq ($(filter -lbfd,$(EXTLIBS)),)
+  CFLAGS += -DHAVE_LIBBFD_SUPPORT
+endif
+
+ifndef NO_BACKTRACE
+  ifeq ($(feature-backtrace), 1)
+    CFLAGS += -DHAVE_BACKTRACE_SUPPORT
+  endif
+endif
+
+ifndef NO_LIBNUMA
+  ifeq ($(feature-libnuma), 0)
+    msg := $(warning No numa.h found, disables 'perf bench numa mem' benchmark, please install numactl-devel/libnuma-devel/libnuma-dev);
+    NO_LIBNUMA := 1
+  else
+    CFLAGS += -DHAVE_LIBNUMA_SUPPORT
+    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 = $(prefix)/etc
+ETC_PERFCONFIG = etc/perfconfig
+endif
+ifeq ($(IS_X86_64),1)
+lib = lib64
+else
+lib = lib
+endif
+libdir = $(prefix)/$(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))
+libdir_SQ = $(subst ','\'',$(libdir))
+
+ifneq ($(filter /%,$(firstword $(perfexecdir))),)
+perfexec_instdir = $(perfexecdir)
+else
+perfexec_instdir = $(prefix)/$(perfexecdir)
+endif
+perfexec_instdir_SQ = $(subst ','\'',$(perfexec_instdir))
+
+# If we install to $(HOME) we keep the traceevent default:
+# $(HOME)/.traceevent/plugins
+# Otherwise we install plugins into the global $(libdir).
+ifdef DESTDIR
+plugindir=$(libdir)/traceevent/plugins
+plugindir_SQ= $(subst ','\'',$(plugindir))
+endif
+
+#
+# Print the result of the feature test:
+#
+feature_print_status = $(eval $(feature_print_status_code)) $(info $(MSG))
+
+define feature_print_status_code
+  ifeq ($(feature-$(1)), 1)
+    MSG = $(shell printf '...%30s: [ \033[32mon\033[m  ]' $(1))
+  else
+    MSG = $(shell printf '...%30s: [ \033[31mOFF\033[m ]' $(1))
+  endif
+endef
+
+feature_print_var = $(eval $(feature_print_var_code)) $(info $(MSG))
+define feature_print_var_code
+    MSG = $(shell printf '...%30s: %s' $(1) $($(1)))
+endef
+
+feature_print_text = $(eval $(feature_print_text_code)) $(info $(MSG))
+define feature_print_text_code
+    MSG = $(shell printf '...%30s: %s' $(1) $(2))
+endef
+
+PERF_FEATURES := $(foreach feat,$(LIB_FEATURE_TESTS),feature-$(feat)($(feature-$(feat))))
+PERF_FEATURES_FILE := $(shell touch $(OUTPUT)PERF-FEATURES; cat $(OUTPUT)PERF-FEATURES)
+
+ifeq ($(dwarf-post-unwind),1)
+  PERF_FEATURES += dwarf-post-unwind($(dwarf-post-unwind-text))
+endif
+
+# The $(display_lib) controls the default detection message
+# output. It's set if:
+# - detected features differes from stored features from
+#   last build (in PERF-FEATURES file)
+# - one of the $(LIB_FEATURE_TESTS) is not detected
+# - VF is enabled
+
+ifneq ("$(PERF_FEATURES)","$(PERF_FEATURES_FILE)")
+  $(shell echo "$(PERF_FEATURES)" > $(OUTPUT)PERF-FEATURES)
+  display_lib := 1
+endif
+
+feature_check = $(eval $(feature_check_code))
+define feature_check_code
+  ifneq ($(feature-$(1)), 1)
+    display_lib := 1
+  endif
+endef
+
+$(foreach feat,$(LIB_FEATURE_TESTS),$(call feature_check,$(feat)))
+
+ifeq ($(VF),1)
+  display_lib := 1
+  display_vf := 1
+endif
+
+ifeq ($(display_lib),1)
+  $(info )
+  $(info Auto-detecting system features:)
+  $(foreach feat,$(LIB_FEATURE_TESTS),$(call feature_print_status,$(feat),))
+
+  ifeq ($(dwarf-post-unwind),1)
+    $(call feature_print_text,"DWARF post unwind library", $(dwarf-post-unwind-text))
+  endif
+endif
+
+ifeq ($(display_vf),1)
+  $(foreach feat,$(VF_FEATURE_TESTS),$(call feature_print_status,$(feat),))
+  $(info )
+  $(call feature_print_var,prefix)
+  $(call feature_print_var,bindir)
+  $(call feature_print_var,libdir)
+  $(call feature_print_var,sysconfdir)
+  $(call feature_print_var,LIBUNWIND_DIR)
+  $(call feature_print_var,LIBDW_DIR)
+endif
+
+ifeq ($(display_lib),1)
+  $(info )
+endif
diff --git a/tools/perf/config/Makefile.arch b/tools/perf/config/Makefile.arch
new file mode 100644
index 00000000000..4b06719ee98
--- /dev/null
+++ b/tools/perf/config/Makefile.arch
@@ -0,0 +1,23 @@
+
+uname_M := $(shell uname -m 2>/dev/null || echo not)
+
+ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \
+                                  -e s/arm.*/arm/ -e s/sa110/arm/ \
+                                  -e s/s390x/s390/ -e s/parisc64/parisc/ \
+                                  -e s/ppc.*/powerpc/ -e s/mips.*/mips/ \
+                                  -e s/sh[234].*/sh/ -e s/aarch64.*/arm64/ \
+                                  -e s/tile.*/tile/ )
+
+# Additional ARCH settings for x86
+ifeq ($(ARCH),i386)
+  override ARCH := x86
+endif
+
+ifeq ($(ARCH),x86_64)
+  override ARCH := x86
+  IS_X86_64 := 0
+  ifeq (, $(findstring m32,$(CFLAGS)))
+    IS_X86_64 := $(shell echo __x86_64__ | ${CC} -E -x c - | tail -n 1)
+    RAW_ARCH := x86_64
+  endif
+endif
diff --git a/tools/perf/config/feature-checks/.gitignore b/tools/perf/config/feature-checks/.gitignore
new file mode 100644
index 00000000000..80f3da0c351
--- /dev/null
+++ b/tools/perf/config/feature-checks/.gitignore
@@ -0,0 +1,2 @@
+*.d
+*.bin
diff --git a/tools/perf/config/feature-checks/Makefile b/tools/perf/config/feature-checks/Makefile
new file mode 100644
index 00000000000..64c84e5f051
--- /dev/null
+++ b/tools/perf/config/feature-checks/Makefile
@@ -0,0 +1,149 @@
+
+FILES=					\
+	test-all.bin			\
+	test-backtrace.bin		\
+	test-bionic.bin			\
+	test-dwarf.bin			\
+	test-fortify-source.bin		\
+	test-glibc.bin			\
+	test-gtk2.bin			\
+	test-gtk2-infobar.bin		\
+	test-hello.bin			\
+	test-libaudit.bin		\
+	test-libbfd.bin			\
+	test-liberty.bin		\
+	test-liberty-z.bin		\
+	test-cplus-demangle.bin		\
+	test-libelf.bin			\
+	test-libelf-getphdrnum.bin	\
+	test-libelf-mmap.bin		\
+	test-libnuma.bin		\
+	test-libperl.bin		\
+	test-libpython.bin		\
+	test-libpython-version.bin	\
+	test-libslang.bin		\
+	test-libunwind.bin		\
+	test-libunwind-debug-frame.bin	\
+	test-stackprotector-all.bin	\
+	test-timerfd.bin		\
+	test-libdw-dwarf-unwind.bin
+
+CC := $(CROSS_COMPILE)gcc -MD
+PKG_CONFIG := $(CROSS_COMPILE)pkg-config
+
+all: $(FILES)
+
+BUILD = $(CC) $(CFLAGS) -o $(OUTPUT)$@ $(patsubst %.bin,%.c,$@) $(LDFLAGS)
+
+###############################
+
+test-all.bin:
+	$(BUILD) -Werror -fstack-protector-all -O2 -Werror -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -laudit -I/usr/include/slang -lslang $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null) $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl
+
+test-hello.bin:
+	$(BUILD)
+
+test-stackprotector-all.bin:
+	$(BUILD) -Werror -fstack-protector-all
+
+test-fortify-source.bin:
+	$(BUILD) -O2 -Werror -D_FORTIFY_SOURCE=2
+
+test-bionic.bin:
+	$(BUILD)
+
+test-libelf.bin:
+	$(BUILD) -lelf
+
+test-glibc.bin:
+	$(BUILD)
+
+test-dwarf.bin:
+	$(BUILD) -ldw
+
+test-libelf-mmap.bin:
+	$(BUILD) -lelf
+
+test-libelf-getphdrnum.bin:
+	$(BUILD) -lelf
+
+test-libnuma.bin:
+	$(BUILD) -lnuma
+
+test-libunwind.bin:
+	$(BUILD) -lelf
+
+test-libunwind-debug-frame.bin:
+	$(BUILD) -lelf
+
+test-libaudit.bin:
+	$(BUILD) -laudit
+
+test-libslang.bin:
+	$(BUILD) -I/usr/include/slang -lslang
+
+test-gtk2.bin:
+	$(BUILD) $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null)
+
+test-gtk2-infobar.bin:
+	$(BUILD) $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null)
+
+grep-libs  = $(filter -l%,$(1))
+strip-libs = $(filter-out -l%,$(1))
+
+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)
+
+test-libperl.bin:
+	$(BUILD) $(FLAGS_PERL_EMBED)
+
+override PYTHON := python
+override PYTHON_CONFIG := python-config
+
+escape-for-shell-sq =  $(subst ','\'',$(1))
+shell-sq = '$(escape-for-shell-sq)'
+
+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)
+
+test-libpython.bin:
+	$(BUILD) $(FLAGS_PYTHON_EMBED)
+
+test-libpython-version.bin:
+	$(BUILD) $(FLAGS_PYTHON_EMBED)
+
+test-libbfd.bin:
+	$(BUILD) -DPACKAGE='"perf"' -lbfd -lz -liberty -ldl
+
+test-liberty.bin:
+	$(CC) -o $(OUTPUT)$@ test-libbfd.c -DPACKAGE='"perf"' -lbfd -ldl -liberty
+
+test-liberty-z.bin:
+	$(CC) -o $(OUTPUT)$@ test-libbfd.c -DPACKAGE='"perf"' -lbfd -ldl -liberty -lz
+
+test-cplus-demangle.bin:
+	$(BUILD) -liberty
+
+test-backtrace.bin:
+	$(BUILD)
+
+test-timerfd.bin:
+	$(BUILD)
+
+test-libdw-dwarf-unwind.bin:
+	$(BUILD)
+
+-include *.d
+
+###############################
+
+clean:
+	rm -f $(FILES) *.d
diff --git a/tools/perf/config/feature-checks/test-all.c b/tools/perf/config/feature-checks/test-all.c
new file mode 100644
index 00000000000..fe5c1e5c952
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-all.c
@@ -0,0 +1,116 @@
+/*
+ * test-all.c: Try to build all the main testcases at once.
+ *
+ * A well-configured system will have all the prereqs installed, so we can speed
+ * up auto-detection on such systems.
+ */
+
+/*
+ * Quirk: Python and Perl headers cannot be in arbitrary places, so keep
+ * these 3 testcases at the top:
+ */
+#define main main_test_libpython
+# include "test-libpython.c"
+#undef main
+
+#define main main_test_libpython_version
+# include "test-libpython-version.c"
+#undef main
+
+#define main main_test_libperl
+# include "test-libperl.c"
+#undef main
+
+#define main main_test_hello
+# include "test-hello.c"
+#undef main
+
+#define main main_test_libelf
+# include "test-libelf.c"
+#undef main
+
+#define main main_test_libelf_mmap
+# include "test-libelf-mmap.c"
+#undef main
+
+#define main main_test_glibc
+# include "test-glibc.c"
+#undef main
+
+#define main main_test_dwarf
+# include "test-dwarf.c"
+#undef main
+
+#define main main_test_libelf_getphdrnum
+# include "test-libelf-getphdrnum.c"
+#undef main
+
+#define main main_test_libunwind
+# include "test-libunwind.c"
+#undef main
+
+#define main main_test_libaudit
+# include "test-libaudit.c"
+#undef main
+
+#define main main_test_libslang
+# include "test-libslang.c"
+#undef main
+
+#define main main_test_gtk2
+# include "test-gtk2.c"
+#undef main
+
+#define main main_test_gtk2_infobar
+# include "test-gtk2-infobar.c"
+#undef main
+
+#define main main_test_libbfd
+# include "test-libbfd.c"
+#undef main
+
+#define main main_test_backtrace
+# include "test-backtrace.c"
+#undef main
+
+#define main main_test_libnuma
+# include "test-libnuma.c"
+#undef main
+
+#define main main_test_timerfd
+# include "test-timerfd.c"
+#undef main
+
+#define main main_test_stackprotector_all
+# include "test-stackprotector-all.c"
+#undef main
+
+#define main main_test_libdw_dwarf_unwind
+# include "test-libdw-dwarf-unwind.c"
+#undef main
+
+int main(int argc, char *argv[])
+{
+	main_test_libpython();
+	main_test_libpython_version();
+	main_test_libperl();
+	main_test_hello();
+	main_test_libelf();
+	main_test_libelf_mmap();
+	main_test_glibc();
+	main_test_dwarf();
+	main_test_libelf_getphdrnum();
+	main_test_libunwind();
+	main_test_libaudit();
+	main_test_libslang();
+	main_test_gtk2(argc, argv);
+	main_test_gtk2_infobar(argc, argv);
+	main_test_libbfd();
+	main_test_backtrace();
+	main_test_libnuma();
+	main_test_timerfd();
+	main_test_stackprotector_all();
+	main_test_libdw_dwarf_unwind();
+
+	return 0;
+}
diff --git a/tools/perf/config/feature-checks/test-backtrace.c b/tools/perf/config/feature-checks/test-backtrace.c
new file mode 100644
index 00000000000..7124aa1dc8f
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-backtrace.c
@@ -0,0 +1,13 @@
+#include <execinfo.h>
+#include <stdio.h>
+
+int main(void)
+{
+	void *backtrace_fns[10];
+	size_t entries;
+
+	entries = backtrace(backtrace_fns, 10);
+	backtrace_symbols_fd(backtrace_fns, entries, 1);
+
+	return 0;
+}
diff --git a/tools/perf/config/feature-checks/test-bionic.c b/tools/perf/config/feature-checks/test-bionic.c
new file mode 100644
index 00000000000..eac24e9513e
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-bionic.c
@@ -0,0 +1,6 @@
+#include <android/api-level.h>
+
+int main(void)
+{
+	return __ANDROID_API__;
+}
diff --git a/tools/perf/config/feature-checks/test-cplus-demangle.c b/tools/perf/config/feature-checks/test-cplus-demangle.c
new file mode 100644
index 00000000000..610c686e000
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-cplus-demangle.c
@@ -0,0 +1,14 @@
+extern int printf(const char *format, ...);
+extern char *cplus_demangle(const char *, int);
+
+int main(void)
+{
+	char symbol[4096] = "FieldName__9ClassNameFd";
+	char *tmp;
+
+	tmp = cplus_demangle(symbol, 0);
+
+	printf("demangled symbol: {%s}\n", tmp);
+
+	return 0;
+}
diff --git a/tools/perf/config/feature-checks/test-dwarf.c b/tools/perf/config/feature-checks/test-dwarf.c
new file mode 100644
index 00000000000..3fc1801ce4a
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-dwarf.c
@@ -0,0 +1,10 @@
+#include <dwarf.h>
+#include <elfutils/libdw.h>
+#include <elfutils/version.h>
+
+int main(void)
+{
+	Dwarf *dbg = dwarf_begin(0, DWARF_C_READ);
+
+	return (long)dbg;
+}
diff --git a/tools/perf/config/feature-checks/test-fortify-source.c b/tools/perf/config/feature-checks/test-fortify-source.c
new file mode 100644
index 00000000000..c9f398d8786
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-fortify-source.c
@@ -0,0 +1,6 @@
+#include <stdio.h>
+
+int main(void)
+{
+	return puts("hi");
+}
diff --git a/tools/perf/config/feature-checks/test-glibc.c b/tools/perf/config/feature-checks/test-glibc.c
new file mode 100644
index 00000000000..b0820345cd9
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-glibc.c
@@ -0,0 +1,8 @@
+#include <gnu/libc-version.h>
+
+int main(void)
+{
+	const char *version = gnu_get_libc_version();
+
+	return (long)version;
+}
diff --git a/tools/perf/config/feature-checks/test-gtk2-infobar.c b/tools/perf/config/feature-checks/test-gtk2-infobar.c
new file mode 100644
index 00000000000..397b4646d06
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-gtk2-infobar.c
@@ -0,0 +1,11 @@
+#pragma GCC diagnostic ignored "-Wstrict-prototypes"
+#include <gtk/gtk.h>
+#pragma GCC diagnostic error "-Wstrict-prototypes"
+
+int main(int argc, char *argv[])
+{
+	gtk_init(&argc, &argv);
+	gtk_info_bar_new();
+
+	return 0;
+}
diff --git a/tools/perf/config/feature-checks/test-gtk2.c b/tools/perf/config/feature-checks/test-gtk2.c
new file mode 100644
index 00000000000..6bd80e50943
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-gtk2.c
@@ -0,0 +1,10 @@
+#pragma GCC diagnostic ignored "-Wstrict-prototypes"
+#include <gtk/gtk.h>
+#pragma GCC diagnostic error "-Wstrict-prototypes"
+
+int main(int argc, char *argv[])
+{
+	gtk_init(&argc, &argv);
+
+        return 0;
+}
diff --git a/tools/perf/config/feature-checks/test-hello.c b/tools/perf/config/feature-checks/test-hello.c
new file mode 100644
index 00000000000..c9f398d8786
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-hello.c
@@ -0,0 +1,6 @@
+#include <stdio.h>
+
+int main(void)
+{
+	return puts("hi");
+}
diff --git a/tools/perf/config/feature-checks/test-libaudit.c b/tools/perf/config/feature-checks/test-libaudit.c
new file mode 100644
index 00000000000..afc019f0864
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-libaudit.c
@@ -0,0 +1,10 @@
+#include <libaudit.h>
+
+extern int printf(const char *format, ...);
+
+int main(void)
+{
+	printf("error message: %s\n", audit_errno_to_name(0));
+
+	return audit_open();
+}
diff --git a/tools/perf/config/feature-checks/test-libbfd.c b/tools/perf/config/feature-checks/test-libbfd.c
new file mode 100644
index 00000000000..24059907e99
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-libbfd.c
@@ -0,0 +1,15 @@
+#include <bfd.h>
+
+extern int printf(const char *format, ...);
+
+int main(void)
+{
+	char symbol[4096] = "FieldName__9ClassNameFd";
+	char *tmp;
+
+	tmp = bfd_demangle(0, symbol, 0);
+
+	printf("demangled symbol: {%s}\n", tmp);
+
+	return 0;
+}
diff --git a/tools/perf/config/feature-checks/test-libdw-dwarf-unwind.c b/tools/perf/config/feature-checks/test-libdw-dwarf-unwind.c
new file mode 100644
index 00000000000..f676a3ff442
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-libdw-dwarf-unwind.c
@@ -0,0 +1,13 @@
+
+#include <elfutils/libdwfl.h>
+
+int main(void)
+{
+	/*
+	 * This function is guarded via: __nonnull_attribute__ (1, 2).
+	 * Passing '1' as arguments value. This code is never executed,
+	 * only compiled.
+	 */
+	dwfl_thread_getframes((void *) 1, (void *) 1, NULL);
+	return 0;
+}
diff --git a/tools/perf/config/feature-checks/test-libelf-getphdrnum.c b/tools/perf/config/feature-checks/test-libelf-getphdrnum.c
new file mode 100644
index 00000000000..d710459306c
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-libelf-getphdrnum.c
@@ -0,0 +1,8 @@
+#include <libelf.h>
+
+int main(void)
+{
+	size_t dst;
+
+	return elf_getphdrnum(0, &dst);
+}
diff --git a/tools/perf/config/feature-checks/test-libelf-mmap.c b/tools/perf/config/feature-checks/test-libelf-mmap.c
new file mode 100644
index 00000000000..564427d7ef1
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-libelf-mmap.c
@@ -0,0 +1,8 @@
+#include <libelf.h>
+
+int main(void)
+{
+	Elf *elf = elf_begin(0, ELF_C_READ_MMAP, 0);
+
+	return (long)elf;
+}
diff --git a/tools/perf/config/feature-checks/test-libelf.c b/tools/perf/config/feature-checks/test-libelf.c
new file mode 100644
index 00000000000..08db322d895
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-libelf.c
@@ -0,0 +1,8 @@
+#include <libelf.h>
+
+int main(void)
+{
+	Elf *elf = elf_begin(0, ELF_C_READ, 0);
+
+	return (long)elf;
+}
diff --git a/tools/perf/config/feature-checks/test-libnuma.c b/tools/perf/config/feature-checks/test-libnuma.c
new file mode 100644
index 00000000000..4763d9cd587
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-libnuma.c
@@ -0,0 +1,9 @@
+#include <numa.h>
+#include <numaif.h>
+
+int main(void)
+{
+	numa_available();
+
+	return 0;
+}
diff --git a/tools/perf/config/feature-checks/test-libperl.c b/tools/perf/config/feature-checks/test-libperl.c
new file mode 100644
index 00000000000..8871f6a0fdb
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-libperl.c
@@ -0,0 +1,9 @@
+#include <EXTERN.h>
+#include <perl.h>
+
+int main(void)
+{
+	perl_alloc();
+
+	return 0;
+}
diff --git a/tools/perf/config/feature-checks/test-libpython-version.c b/tools/perf/config/feature-checks/test-libpython-version.c
new file mode 100644
index 00000000000..facea122d81
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-libpython-version.c
@@ -0,0 +1,10 @@
+#include <Python.h>
+
+#if PY_VERSION_HEX >= 0x03000000
+	#error
+#endif
+
+int main(void)
+{
+	return 0;
+}
diff --git a/tools/perf/config/feature-checks/test-libpython.c b/tools/perf/config/feature-checks/test-libpython.c
new file mode 100644
index 00000000000..b24b28ad632
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-libpython.c
@@ -0,0 +1,8 @@
+#include <Python.h>
+
+int main(void)
+{
+	Py_Initialize();
+
+	return 0;
+}
diff --git a/tools/perf/config/feature-checks/test-libslang.c b/tools/perf/config/feature-checks/test-libslang.c
new file mode 100644
index 00000000000..22ff22ed94d
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-libslang.c
@@ -0,0 +1,6 @@
+#include <slang.h>
+
+int main(void)
+{
+	return SLsmg_init_smg();
+}
diff --git a/tools/perf/config/feature-checks/test-libunwind-debug-frame.c b/tools/perf/config/feature-checks/test-libunwind-debug-frame.c
new file mode 100644
index 00000000000..0ef8087a104
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-libunwind-debug-frame.c
@@ -0,0 +1,16 @@
+#include <libunwind.h>
+#include <stdlib.h>
+
+extern int
+UNW_OBJ(dwarf_find_debug_frame) (int found, unw_dyn_info_t *di_debug,
+				 unw_word_t ip, unw_word_t segbase,
+				 const char *obj_name, unw_word_t start,
+				 unw_word_t end);
+
+#define dwarf_find_debug_frame UNW_OBJ(dwarf_find_debug_frame)
+
+int main(void)
+{
+	dwarf_find_debug_frame(0, NULL, 0, 0, NULL, 0, 0);
+	return 0;
+}
diff --git a/tools/perf/config/feature-checks/test-libunwind.c b/tools/perf/config/feature-checks/test-libunwind.c
new file mode 100644
index 00000000000..43b9369bcab
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-libunwind.c
@@ -0,0 +1,27 @@
+#include <libunwind.h>
+#include <stdlib.h>
+
+extern int UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as,
+                                      unw_word_t ip,
+                                      unw_dyn_info_t *di,
+                                      unw_proc_info_t *pi,
+                                      int need_unwind_info, void *arg);
+
+
+#define dwarf_search_unwind_table UNW_OBJ(dwarf_search_unwind_table)
+
+static unw_accessors_t accessors;
+
+int main(void)
+{
+	unw_addr_space_t addr_space;
+
+	addr_space = unw_create_addr_space(&accessors, 0);
+	if (addr_space)
+		return 0;
+
+	unw_init_remote(NULL, addr_space, NULL);
+	dwarf_search_unwind_table(addr_space, 0, NULL, NULL, 0, NULL);
+
+	return 0;
+}
diff --git a/tools/perf/config/feature-checks/test-stackprotector-all.c b/tools/perf/config/feature-checks/test-stackprotector-all.c
new file mode 100644
index 00000000000..c9f398d8786
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-stackprotector-all.c
@@ -0,0 +1,6 @@
+#include <stdio.h>
+
+int main(void)
+{
+	return puts("hi");
+}
diff --git a/tools/perf/config/feature-checks/test-timerfd.c b/tools/perf/config/feature-checks/test-timerfd.c
new file mode 100644
index 00000000000..8c5c083b4d3
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-timerfd.c
@@ -0,0 +1,18 @@
+/*
+ * test for timerfd functions used by perf-kvm-stat-live
+ */
+#include <sys/timerfd.h>
+
+int main(void)
+{
+	struct itimerspec new_value;
+
+	int fd = timerfd_create(CLOCK_MONOTONIC, TFD_NONBLOCK);
+	if (fd < 0)
+		return 1;
+
+	if (timerfd_settime(fd, 0, &new_value, NULL) != 0)
+		return 1;
+
+	return 0;
+}
diff --git a/tools/perf/config/utilities.mak b/tools/perf/config/utilities.mak
new file mode 100644
index 00000000000..4d985e0f03f
--- /dev/null
+++ b/tools/perf/config/utilities.mak
@@ -0,0 +1,180 @@
+# This allows us to work with the newline character:
+define newline
+
+
+endef
+newline := $(newline)
+
+# nl-escape
+#
+# Usage: escape = $(call nl-escape[,escape])
+#
+# This is used as the common way to specify
+# what should replace a newline when escaping
+# newlines; the default is a bizarre string.
+#
+nl-escape = $(if $(1),$(1),m822df3020w6a44id34bt574ctac44eb9f4n)
+
+# escape-nl
+#
+# Usage: escaped-text = $(call escape-nl,text[,escape])
+#
+# GNU make's $(shell ...) function converts to a
+# single space each newline character in the output
+# produced during the expansion; this may not be
+# desirable.
+#
+# The only solution is to change each newline into
+# something that won't be converted, so that the
+# information can be recovered later with
+# $(call unescape-nl...)
+#
+escape-nl = $(subst $(newline),$(call nl-escape,$(2)),$(1))
+
+# unescape-nl
+#
+# Usage: text = $(call unescape-nl,escaped-text[,escape])
+#
+# See escape-nl.
+#
+unescape-nl = $(subst $(call nl-escape,$(2)),$(newline),$(1))
+
+# shell-escape-nl
+#
+# Usage: $(shell some-command | $(call shell-escape-nl[,escape]))
+#
+# Use this to escape newlines from within a shell call;
+# the default escape is a bizarre string.
+#
+# NOTE: The escape is used directly as a string constant
+#       in an `awk' program that is delimited by shell
+#       single-quotes, so be wary of the characters
+#       that are chosen.
+#
+define shell-escape-nl
+awk 'NR==1 {t=$$0} NR>1 {t=t "$(nl-escape)" $$0} END {printf t}'
+endef
+
+# shell-unescape-nl
+#
+# Usage: $(shell some-command | $(call shell-unescape-nl[,escape]))
+#
+# Use this to unescape newlines from within a shell call;
+# the default escape is a bizarre string.
+#
+# NOTE: The escape is used directly as an extended regular
+#       expression constant in an `awk' program that is
+#       delimited by shell single-quotes, so be wary
+#       of the characters that are chosen.
+#
+# (The bash shell has a bug where `{gsub(...),...}' is
+#  misinterpreted as a brace expansion; this can be
+#  overcome by putting a space between `{' and `gsub').
+#
+define shell-unescape-nl
+awk 'NR==1 {t=$$0} NR>1 {t=t "\n" $$0} END { gsub(/$(nl-escape)/,"\n",t); printf t }'
+endef
+
+# escape-for-shell-sq
+#
+# Usage: embeddable-text = $(call escape-for-shell-sq,text)
+#
+# This function produces text that is suitable for
+# embedding in a shell string that is delimited by
+# single-quotes.
+#
+escape-for-shell-sq =  $(subst ','\'',$(1))
+
+# shell-sq
+#
+# Usage: single-quoted-and-escaped-text = $(call shell-sq,text)
+#
+shell-sq = '$(escape-for-shell-sq)'
+
+# shell-wordify
+#
+# Usage: wordified-text = $(call shell-wordify,text)
+#
+# For instance:
+#
+#  |define text
+#  |hello
+#  |world
+#  |endef
+#  |
+#  |target:
+#  |	echo $(call shell-wordify,$(text))
+#
+# At least GNU make gets confused by expanding a newline
+# within the context of a command line of a makefile rule
+# (this is in constrast to a `$(shell ...)' function call,
+# which can handle it just fine).
+#
+# This function avoids the problem by producing a string
+# that works as a shell word, regardless of whether or
+# not it contains a newline.
+#
+# If the text to be wordified contains a newline, then
+# an intrictate shell command substitution is constructed
+# to render the text as a single line; when the shell
+# processes the resulting escaped text, it transforms
+# it into the original unescaped text.
+#
+# If the text does not contain a newline, then this function
+# produces the same results as the `$(shell-sq)' function.
+#
+shell-wordify = $(if $(findstring $(newline),$(1)),$(_sw-esc-nl),$(shell-sq))
+define _sw-esc-nl
+"$$(echo $(call escape-nl,$(shell-sq),$(2)) | $(call shell-unescape-nl,$(2)))"
+endef
+
+# is-absolute
+#
+# Usage: bool-value = $(call is-absolute,path)
+#
+is-absolute = $(shell echo $(shell-sq) | grep ^/ -q && echo y)
+
+# lookup
+#
+# Usage: absolute-executable-path-or-empty = $(call lookup,path)
+#
+# (It's necessary to use `sh -c' because GNU make messes up by
+#  trying too hard and getting things wrong).
+#
+lookup = $(call unescape-nl,$(shell sh -c $(_l-sh)))
+_l-sh = $(call shell-sq,command -v $(shell-sq) | $(call shell-escape-nl,))
+
+# is-executable
+#
+# Usage: bool-value = $(call is-executable,path)
+#
+# (It's necessary to use `sh -c' because GNU make messes up by
+#  trying too hard and getting things wrong).
+#
+is-executable = $(call _is-executable-helper,$(shell-sq))
+_is-executable-helper = $(shell sh -c $(_is-executable-sh))
+_is-executable-sh = $(call shell-sq,test -f $(1) -a -x $(1) && echo y)
+
+# get-executable
+#
+# Usage: absolute-executable-path-or-empty = $(call get-executable,path)
+#
+# The goal is to get an absolute path for an executable;
+# the `command -v' is defined by POSIX, but it's not
+# necessarily very portable, so it's only used if
+# relative path resolution is requested, as determined
+# by the presence of a leading `/'.
+#
+get-executable = $(if $(1),$(if $(is-absolute),$(_ge-abspath),$(lookup)))
+_ge-abspath = $(if $(is-executable),$(1))
+
+# get-supplied-or-default-executable
+#
+# Usage: absolute-executable-path-or-empty = $(call get-executable-or-default,variable,default)
+#
+define get-executable-or-default
+$(if $($(1)),$(call _ge_attempt,$($(1)),$(1)),$(call _ge_attempt,$(2)))
+endef
+_ge_attempt = $(if $(get-executable),$(get-executable),$(_gea_warn)$(call _gea_err,$(2)))
+_gea_warn = $(warning The path '$(1)' is not executable.)
+_gea_err  = $(if $(1),$(error Please set '$(1)' appropriately))
diff --git a/tools/perf/design.txt b/tools/perf/design.txt
index bd0bb1b1279..a28dca2582a 100644
--- a/tools/perf/design.txt
+++ b/tools/perf/design.txt
@@ -18,7 +18,7 @@ underlying hardware counters.
 Performance counters are accessed via special file descriptors.
 There's one file descriptor per virtual counter used.
 
-The special file descriptor is opened via the perf_event_open()
+The special file descriptor is opened via the sys_perf_event_open()
 system call:
 
    int sys_perf_event_open(struct perf_event_attr *hw_event_uptr,
@@ -82,7 +82,7 @@ machine-specific.
 If 'raw_type' is 0, then the 'type' field says what kind of counter
 this is, with the following encoding:
 
-enum perf_event_types {
+enum perf_type_id {
 	PERF_TYPE_HARDWARE		= 0,
 	PERF_TYPE_SOFTWARE		= 1,
 	PERF_TYPE_TRACEPOINT		= 2,
@@ -95,7 +95,7 @@ specified by 'event_id':
  * Generalized performance counter event types, used by the hw_event.event_id
  * parameter of the sys_perf_event_open() syscall:
  */
-enum hw_event_ids {
+enum perf_hw_id {
 	/*
 	 * Common hardware events, generalized by the kernel:
 	 */
@@ -129,7 +129,7 @@ software events, selected by 'event_id':
  * physical and sw events of the kernel (and allow the profiling of them as
  * well):
  */
-enum sw_event_ids {
+enum perf_sw_ids {
 	PERF_COUNT_SW_CPU_CLOCK		= 0,
 	PERF_COUNT_SW_TASK_CLOCK	= 1,
 	PERF_COUNT_SW_PAGE_FAULTS	= 2,
@@ -230,7 +230,7 @@ these events are recorded in the ring-buffer (see below).
 The 'comm' bit allows tracking of process comm data on process creation.
 This too is recorded in the ring-buffer (see below).
 
-The 'pid' parameter to the perf_event_open() system call allows the
+The 'pid' parameter to the sys_perf_event_open() system call allows the
 counter to be specific to a task:
 
  pid == 0: if the pid parameter is zero, the counter is attached to the
@@ -260,7 +260,7 @@ The 'flags' parameter is currently unused and must be zero.
 
 The 'group_fd' parameter allows counter "groups" to be set up.  A
 counter group has one counter which is the group "leader".  The leader
-is created first, with group_fd = -1 in the perf_event_open call
+is created first, with group_fd = -1 in the sys_perf_event_open call
 that creates it.  The rest of the group members are created
 subsequently, with group_fd giving the fd of the group leader.
 (A single counter on its own is created with group_fd = -1 and is
@@ -409,14 +409,15 @@ Counters can be enabled and disabled in two ways: via ioctl and via
 prctl.  When a counter is disabled, it doesn't count or generate
 events but does continue to exist and maintain its count value.
 
-An individual counter or counter group can be enabled with
+An individual counter can be enabled with
 
-	ioctl(fd, PERF_EVENT_IOC_ENABLE);
+	ioctl(fd, PERF_EVENT_IOC_ENABLE, 0);
 
 or disabled with
 
-	ioctl(fd, PERF_EVENT_IOC_DISABLE);
+	ioctl(fd, PERF_EVENT_IOC_DISABLE, 0);
 
+For a counter group, pass PERF_IOC_FLAG_GROUP as the third argument.
 Enabling or disabling the leader of a group enables or disables the
 whole group; that is, while the group leader is disabled, none of the
 counters in the group will count.  Enabling or disabling a member of a
@@ -453,7 +454,6 @@ So to start with, in order to add HAVE_PERF_EVENTS to your Kconfig, you
 will need at least this:
 	- asm/perf_event.h - a basic stub will suffice at first
 	- support for atomic64 types (and associated helper functions)
-	- set_perf_event_pending() implemented
 
 If your architecture does have hardware capabilities, you can override the
 weak stub hw_perf_event_init() to register hardware counters.
diff --git a/tools/perf/perf-archive.sh b/tools/perf/perf-archive.sh
index 2e7a4f417e2..e9193062026 100644
--- a/tools/perf/perf-archive.sh
+++ b/tools/perf/perf-archive.sh
@@ -7,29 +7,40 @@ if [ $# -ne 0 ] ; then
 	PERF_DATA=$1
 fi
 
-DEBUGDIR=~/.debug/
+#
+# PERF_BUILDID_DIR environment variable set by perf
+# path to buildid directory, default to $HOME/.debug
+#
+if [ -z $PERF_BUILDID_DIR ]; then
+	PERF_BUILDID_DIR=~/.debug/
+else
+        # append / to make substitutions work
+        PERF_BUILDID_DIR=$PERF_BUILDID_DIR/
+fi
+
 BUILDIDS=$(mktemp /tmp/perf-archive-buildids.XXXXXX)
 NOBUILDID=0000000000000000000000000000000000000000
 
 perf buildid-list -i $PERF_DATA --with-hits | grep -v "^$NOBUILDID " > $BUILDIDS
 if [ ! -s $BUILDIDS ] ; then
 	echo "perf archive: no build-ids found"
-	rm -f $BUILDIDS
+	rm $BUILDIDS || true
 	exit 1
 fi
 
 MANIFEST=$(mktemp /tmp/perf-archive-manifest.XXXXXX)
+PERF_BUILDID_LINKDIR=$(readlink -f $PERF_BUILDID_DIR)/
 
 cut -d ' ' -f 1 $BUILDIDS | \
 while read build_id ; do
-	linkname=$DEBUGDIR.build-id/${build_id:0:2}/${build_id:2}
+	linkname=$PERF_BUILDID_DIR.build-id/${build_id:0:2}/${build_id:2}
 	filename=$(readlink -f $linkname)
-	echo ${linkname#$DEBUGDIR} >> $MANIFEST
-	echo ${filename#$DEBUGDIR} >> $MANIFEST
+	echo ${linkname#$PERF_BUILDID_DIR} >> $MANIFEST
+	echo ${filename#$PERF_BUILDID_LINKDIR} >> $MANIFEST
 done
 
-tar cfj $PERF_DATA.tar.bz2 -C $DEBUGDIR -T $MANIFEST
-rm -f $MANIFEST $BUILDIDS
+tar cjf $PERF_DATA.tar.bz2 -C $PERF_BUILDID_DIR -T $MANIFEST
+rm $MANIFEST $BUILDIDS || true
 echo -e "Now please run:\n"
 echo -e "$ tar xvf $PERF_DATA.tar.bz2 -C ~/.debug\n"
 echo "wherever you need to run 'perf report' on."
diff --git a/tools/perf/perf-completion.sh b/tools/perf/perf-completion.sh
new file mode 100644
index 00000000000..33569847fdc
--- /dev/null
+++ b/tools/perf/perf-completion.sh
@@ -0,0 +1,206 @@
+# perf bash and zsh completion
+
+# Taken from git.git's completion script.
+__my_reassemble_comp_words_by_ref()
+{
+	local exclude i j first
+	# Which word separators to exclude?
+	exclude="${1//[^$COMP_WORDBREAKS]}"
+	cword_=$COMP_CWORD
+	if [ -z "$exclude" ]; then
+		words_=("${COMP_WORDS[@]}")
+		return
+	fi
+	# List of word completion separators has shrunk;
+	# re-assemble words to complete.
+	for ((i=0, j=0; i < ${#COMP_WORDS[@]}; i++, j++)); do
+		# Append each nonempty word consisting of just
+		# word separator characters to the current word.
+		first=t
+		while
+			[ $i -gt 0 ] &&
+			[ -n "${COMP_WORDS[$i]}" ] &&
+			# word consists of excluded word separators
+			[ "${COMP_WORDS[$i]//[^$exclude]}" = "${COMP_WORDS[$i]}" ]
+		do
+			# Attach to the previous token,
+			# unless the previous token is the command name.
+			if [ $j -ge 2 ] && [ -n "$first" ]; then
+				((j--))
+			fi
+			first=
+			words_[$j]=${words_[j]}${COMP_WORDS[i]}
+			if [ $i = $COMP_CWORD ]; then
+				cword_=$j
+			fi
+			if (($i < ${#COMP_WORDS[@]} - 1)); then
+				((i++))
+			else
+				# Done.
+				return
+			fi
+		done
+		words_[$j]=${words_[j]}${COMP_WORDS[i]}
+		if [ $i = $COMP_CWORD ]; then
+			cword_=$j
+		fi
+	done
+}
+
+type _get_comp_words_by_ref &>/dev/null ||
+_get_comp_words_by_ref()
+{
+	local exclude cur_ words_ cword_
+	if [ "$1" = "-n" ]; then
+		exclude=$2
+		shift 2
+	fi
+	__my_reassemble_comp_words_by_ref "$exclude"
+	cur_=${words_[cword_]}
+	while [ $# -gt 0 ]; do
+		case "$1" in
+		cur)
+			cur=$cur_
+			;;
+		prev)
+			prev=${words_[$cword_-1]}
+			;;
+		words)
+			words=("${words_[@]}")
+			;;
+		cword)
+			cword=$cword_
+			;;
+		esac
+		shift
+	done
+}
+
+type __ltrim_colon_completions &>/dev/null ||
+__ltrim_colon_completions()
+{
+	if [[ "$1" == *:* && "$COMP_WORDBREAKS" == *:* ]]; then
+		# Remove colon-word prefix from COMPREPLY items
+		local colon_word=${1%"${1##*:}"}
+		local i=${#COMPREPLY[*]}
+		while [[ $((--i)) -ge 0 ]]; do
+			COMPREPLY[$i]=${COMPREPLY[$i]#"$colon_word"}
+		done
+	fi
+}
+
+__perfcomp ()
+{
+	COMPREPLY=( $( compgen -W "$1" -- "$2" ) )
+}
+
+__perfcomp_colon ()
+{
+	__perfcomp "$1" "$2"
+	__ltrim_colon_completions $cur
+}
+
+__perf_main ()
+{
+	local cmd
+
+	cmd=${words[0]}
+	COMPREPLY=()
+
+	# List perf subcommands or long options
+	if [ $cword -eq 1 ]; then
+		if [[ $cur == --* ]]; then
+			__perfcomp '--help --version \
+			--exec-path --html-path --paginate --no-pager \
+			--perf-dir --work-tree --debugfs-dir' -- "$cur"
+		else
+			cmds=$($cmd --list-cmds)
+			__perfcomp "$cmds" "$cur"
+		fi
+	# List possible events for -e option
+	elif [[ $prev == "-e" && "${words[1]}" == @(record|stat|top) ]]; then
+		evts=$($cmd list --raw-dump)
+		__perfcomp_colon "$evts" "$cur"
+	# List subcommands for perf commands
+	elif [[ $prev == @(kvm|kmem|mem|lock|sched) ]]; then
+		subcmds=$($cmd $prev --list-cmds)
+		__perfcomp_colon "$subcmds" "$cur"
+	# List long option names
+	elif [[ $cur == --* ]];  then
+		subcmd=${words[1]}
+		opts=$($cmd $subcmd --list-opts)
+		__perfcomp "$opts" "$cur"
+	fi
+}
+
+if [[ -n ${ZSH_VERSION-} ]]; then
+	autoload -U +X compinit && compinit
+
+	__perfcomp ()
+	{
+		emulate -L zsh
+
+		local c IFS=$' \t\n'
+		local -a array
+
+		for c in ${=1}; do
+			case $c in
+			--*=*|*.) ;;
+			*) c="$c " ;;
+			esac
+			array[${#array[@]}+1]="$c"
+		done
+
+		compset -P '*[=:]'
+		compadd -Q -S '' -a -- array && _ret=0
+	}
+
+	__perfcomp_colon ()
+	{
+		emulate -L zsh
+
+		local cur_="${2-$cur}"
+		local c IFS=$' \t\n'
+		local -a array
+
+		if [[ "$cur_" == *:* ]]; then
+			local colon_word=${cur_%"${cur_##*:}"}
+		fi
+
+		for c in ${=1}; do
+			case $c in
+			--*=*|*.) ;;
+			*) c="$c " ;;
+			esac
+			array[$#array+1]=${c#"$colon_word"}
+		done
+
+		compset -P '*[=:]'
+		compadd -Q -S '' -a -- array && _ret=0
+	}
+
+	_perf ()
+	{
+		local _ret=1 cur cword prev
+		cur=${words[CURRENT]}
+		prev=${words[CURRENT-1]}
+		let cword=CURRENT-1
+		emulate ksh -c __perf_main
+		let _ret && _default && _ret=0
+		return _ret
+	}
+
+	compdef _perf perf
+	return
+fi
+
+type perf &>/dev/null &&
+_perf()
+{
+	local cur words cword prev
+	_get_comp_words_by_ref -n =: cur words cword prev
+	__perf_main
+} &&
+
+complete -o bashdefault -o default -o nospace -F _perf perf 2>/dev/null \
+	|| complete -o default -o nospace -F _perf perf
diff --git a/tools/perf/perf-sys.h b/tools/perf/perf-sys.h
new file mode 100644
index 00000000000..5268a1481d2
--- /dev/null
+++ b/tools/perf/perf-sys.h
@@ -0,0 +1,190 @@
+#ifndef _PERF_SYS_H
+#define _PERF_SYS_H
+
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/syscall.h>
+#include <linux/types.h>
+#include <linux/perf_event.h>
+#include <asm/unistd.h>
+
+#if defined(__i386__)
+#define mb()		asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
+#define wmb()		asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
+#define rmb()		asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
+#define cpu_relax()	asm volatile("rep; nop" ::: "memory");
+#define CPUINFO_PROC	"model name"
+#ifndef __NR_perf_event_open
+# define __NR_perf_event_open 336
+#endif
+#ifndef __NR_futex
+# define __NR_futex 240
+#endif
+#ifndef __NR_gettid
+# define __NR_gettid 224
+#endif
+#endif
+
+#if defined(__x86_64__)
+#define mb()		asm volatile("mfence" ::: "memory")
+#define wmb()		asm volatile("sfence" ::: "memory")
+#define rmb()		asm volatile("lfence" ::: "memory")
+#define cpu_relax()	asm volatile("rep; nop" ::: "memory");
+#define CPUINFO_PROC	"model name"
+#ifndef __NR_perf_event_open
+# define __NR_perf_event_open 298
+#endif
+#ifndef __NR_futex
+# define __NR_futex 202
+#endif
+#ifndef __NR_gettid
+# define __NR_gettid 186
+#endif
+#endif
+
+#ifdef __powerpc__
+#include "../../arch/powerpc/include/uapi/asm/unistd.h"
+#define mb()		asm volatile ("sync" ::: "memory")
+#define wmb()		asm volatile ("sync" ::: "memory")
+#define rmb()		asm volatile ("sync" ::: "memory")
+#define CPUINFO_PROC	"cpu"
+#endif
+
+#ifdef __s390__
+#define mb()		asm volatile("bcr 15,0" ::: "memory")
+#define wmb()		asm volatile("bcr 15,0" ::: "memory")
+#define rmb()		asm volatile("bcr 15,0" ::: "memory")
+#endif
+
+#ifdef __sh__
+#if defined(__SH4A__) || defined(__SH5__)
+# define mb()		asm volatile("synco" ::: "memory")
+# define wmb()		asm volatile("synco" ::: "memory")
+# define rmb()		asm volatile("synco" ::: "memory")
+#else
+# define mb()		asm volatile("" ::: "memory")
+# define wmb()		asm volatile("" ::: "memory")
+# define rmb()		asm volatile("" ::: "memory")
+#endif
+#define CPUINFO_PROC	"cpu type"
+#endif
+
+#ifdef __hppa__
+#define mb()		asm volatile("" ::: "memory")
+#define wmb()		asm volatile("" ::: "memory")
+#define rmb()		asm volatile("" ::: "memory")
+#define CPUINFO_PROC	"cpu"
+#endif
+
+#ifdef __sparc__
+#ifdef __LP64__
+#define mb()		asm volatile("ba,pt %%xcc, 1f\n"	\
+				     "membar #StoreLoad\n"	\
+				     "1:\n":::"memory")
+#else
+#define mb()		asm volatile("":::"memory")
+#endif
+#define wmb()		asm volatile("":::"memory")
+#define rmb()		asm volatile("":::"memory")
+#define CPUINFO_PROC	"cpu"
+#endif
+
+#ifdef __alpha__
+#define mb()		asm volatile("mb" ::: "memory")
+#define wmb()		asm volatile("wmb" ::: "memory")
+#define rmb()		asm volatile("mb" ::: "memory")
+#define CPUINFO_PROC	"cpu model"
+#endif
+
+#ifdef __ia64__
+#define mb()		asm volatile ("mf" ::: "memory")
+#define wmb()		asm volatile ("mf" ::: "memory")
+#define rmb()		asm volatile ("mf" ::: "memory")
+#define cpu_relax()	asm volatile ("hint @pause" ::: "memory")
+#define CPUINFO_PROC	"model name"
+#endif
+
+#ifdef __arm__
+/*
+ * Use the __kuser_memory_barrier helper in the CPU helper page. See
+ * arch/arm/kernel/entry-armv.S in the kernel source for details.
+ */
+#define mb()		((void(*)(void))0xffff0fa0)()
+#define wmb()		((void(*)(void))0xffff0fa0)()
+#define rmb()		((void(*)(void))0xffff0fa0)()
+#define CPUINFO_PROC	"Processor"
+#endif
+
+#ifdef __aarch64__
+#define mb()		asm volatile("dmb ish" ::: "memory")
+#define wmb()		asm volatile("dmb ishst" ::: "memory")
+#define rmb()		asm volatile("dmb ishld" ::: "memory")
+#define cpu_relax()	asm volatile("yield" ::: "memory")
+#endif
+
+#ifdef __mips__
+#define mb()		asm volatile(					\
+				".set	mips2\n\t"			\
+				"sync\n\t"				\
+				".set	mips0"				\
+				: /* no output */			\
+				: /* no input */			\
+				: "memory")
+#define wmb()	mb()
+#define rmb()	mb()
+#define CPUINFO_PROC	"cpu model"
+#endif
+
+#ifdef __arc__
+#define mb()		asm volatile("" ::: "memory")
+#define wmb()		asm volatile("" ::: "memory")
+#define rmb()		asm volatile("" ::: "memory")
+#define CPUINFO_PROC	"Processor"
+#endif
+
+#ifdef __metag__
+#define mb()		asm volatile("" ::: "memory")
+#define wmb()		asm volatile("" ::: "memory")
+#define rmb()		asm volatile("" ::: "memory")
+#define CPUINFO_PROC	"CPU"
+#endif
+
+#ifdef __xtensa__
+#define mb()		asm volatile("memw" ::: "memory")
+#define wmb()		asm volatile("memw" ::: "memory")
+#define rmb()		asm volatile("" ::: "memory")
+#define CPUINFO_PROC	"core ID"
+#endif
+
+#ifdef __tile__
+#define mb()		asm volatile ("mf" ::: "memory")
+#define wmb()		asm volatile ("mf" ::: "memory")
+#define rmb()		asm volatile ("mf" ::: "memory")
+#define cpu_relax()	asm volatile ("mfspr zero, PASS" ::: "memory")
+#define CPUINFO_PROC    "model name"
+#endif
+
+#define barrier() asm volatile ("" ::: "memory")
+
+#ifndef cpu_relax
+#define cpu_relax() barrier()
+#endif
+
+static inline int
+sys_perf_event_open(struct perf_event_attr *attr,
+		      pid_t pid, int cpu, int group_fd,
+		      unsigned long flags)
+{
+	int fd;
+
+	fd = syscall(__NR_perf_event_open, attr, pid, cpu,
+		     group_fd, flags);
+
+#ifdef HAVE_ATTR_TEST
+	if (unlikely(test_attr__enabled))
+		test_attr__open(attr, pid, cpu, fd, group_fd, flags);
+#endif
+	return fd;
+}
+
+#endif /* _PERF_SYS_H */
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 6e487119113..95c58fc1528 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -13,7 +13,8 @@
 #include "util/quote.h"
 #include "util/run-command.h"
 #include "util/parse-events.h"
-#include "util/debugfs.h"
+#include <api/fs/debugfs.h>
+#include <pthread.h>
 
 const char perf_usage_string[] =
 	"perf [--version] [--help] COMMAND [ARGS]";
@@ -23,14 +24,50 @@ const char perf_more_info_string[] =
 
 int use_browser = -1;
 static int use_pager = -1;
+const char *input_name;
+
+struct cmd_struct {
+	const char *cmd;
+	int (*fn)(int, const char **, const char *);
+	int option;
+};
+
+static struct cmd_struct commands[] = {
+	{ "buildid-cache", cmd_buildid_cache, 0 },
+	{ "buildid-list", cmd_buildid_list, 0 },
+	{ "diff",	cmd_diff,	0 },
+	{ "evlist",	cmd_evlist,	0 },
+	{ "help",	cmd_help,	0 },
+	{ "list",	cmd_list,	0 },
+	{ "record",	cmd_record,	0 },
+	{ "report",	cmd_report,	0 },
+	{ "bench",	cmd_bench,	0 },
+	{ "stat",	cmd_stat,	0 },
+	{ "timechart",	cmd_timechart,	0 },
+	{ "top",	cmd_top,	0 },
+	{ "annotate",	cmd_annotate,	0 },
+	{ "version",	cmd_version,	0 },
+	{ "script",	cmd_script,	0 },
+	{ "sched",	cmd_sched,	0 },
+#ifdef HAVE_LIBELF_SUPPORT
+	{ "probe",	cmd_probe,	0 },
+#endif
+	{ "kmem",	cmd_kmem,	0 },
+	{ "lock",	cmd_lock,	0 },
+	{ "kvm",	cmd_kvm,	0 },
+	{ "test",	cmd_test,	0 },
+#ifdef HAVE_LIBAUDIT_SUPPORT
+	{ "trace",	cmd_trace,	0 },
+#endif
+	{ "inject",	cmd_inject,	0 },
+	{ "mem",	cmd_mem,	0 },
+};
 
 struct pager_config {
 	const char *cmd;
 	int val;
 };
 
-static char debugfs_mntpt[MAXPATHLEN];
-
 static int pager_command_config(const char *var, const char *value, void *data)
 {
 	struct pager_config *c = data;
@@ -49,21 +86,26 @@ int check_pager_config(const char *cmd)
 	return c.val;
 }
 
-static int tui_command_config(const char *var, const char *value, void *data)
+static int browser_command_config(const char *var, const char *value, void *data)
 {
 	struct pager_config *c = data;
 	if (!prefixcmp(var, "tui.") && !strcmp(var + 4, c->cmd))
 		c->val = perf_config_bool(var, value);
+	if (!prefixcmp(var, "gtk.") && !strcmp(var + 4, c->cmd))
+		c->val = perf_config_bool(var, value) ? 2 : 0;
 	return 0;
 }
 
-/* returns 0 for "no tui", 1 for "use tui", and -1 for "not specified" */
-static int check_tui_config(const char *cmd)
+/*
+ * returns 0 for "no tui", 1 for "use tui", 2 for "use gtk",
+ * and -1 for "not specified"
+ */
+static int check_browser_config(const char *cmd)
 {
 	struct pager_config c;
 	c.cmd = cmd;
 	c.val = -1;
-	perf_config(tui_command_config, &c);
+	perf_config(browser_command_config, &c);
 	return c.val;
 }
 
@@ -81,15 +123,6 @@ static void commit_pager_choice(void)
 	}
 }
 
-static void set_debugfs_path(void)
-{
-	char *path;
-
-	path = getenv(PERF_DEBUGFS_ENVIRONMENT);
-	snprintf(debugfs_path, MAXPATHLEN, "%s/%s", path ?: debugfs_mntpt,
-		 "tracing/events");
-}
-
 static int handle_options(const char ***argv, int *argc, int *envchanged)
 {
 	int handled = 0;
@@ -161,17 +194,24 @@ static int handle_options(const char ***argv, int *argc, int *envchanged)
 				fprintf(stderr, "No directory given for --debugfs-dir.\n");
 				usage(perf_usage_string);
 			}
-			strncpy(debugfs_mntpt, (*argv)[1], MAXPATHLEN);
-			debugfs_mntpt[MAXPATHLEN - 1] = '\0';
+			perf_debugfs_set_path((*argv)[1]);
 			if (envchanged)
 				*envchanged = 1;
 			(*argv)++;
 			(*argc)--;
 		} else if (!prefixcmp(cmd, CMD_DEBUGFS_DIR)) {
-			strncpy(debugfs_mntpt, cmd + strlen(CMD_DEBUGFS_DIR), MAXPATHLEN);
-			debugfs_mntpt[MAXPATHLEN - 1] = '\0';
+			perf_debugfs_set_path(cmd + strlen(CMD_DEBUGFS_DIR));
+			fprintf(stderr, "dir: %s\n", debugfs_mountpoint);
 			if (envchanged)
 				*envchanged = 1;
+		} else if (!strcmp(cmd, "--list-cmds")) {
+			unsigned int i;
+
+			for (i = 0; i < ARRAY_SIZE(commands); i++) {
+				struct cmd_struct *p = commands+i;
+				printf("%s ", p->cmd);
+			}
+			exit(0);
 		} else {
 			fprintf(stderr, "Unknown option: %s\n", cmd);
 			usage(perf_usage_string);
@@ -257,12 +297,6 @@ const char perf_version_string[] = PERF_VERSION;
  */
 #define NEED_WORK_TREE	(1<<2)
 
-struct cmd_struct {
-	const char *cmd;
-	int (*fn)(int, const char **, const char *);
-	int option;
-};
-
 static int run_builtin(struct cmd_struct *p, int argc, const char **argv)
 {
 	int status;
@@ -274,14 +308,13 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv)
 		prefix = NULL; /* setup_perf_directory(); */
 
 	if (use_browser == -1)
-		use_browser = check_tui_config(p->cmd);
+		use_browser = check_browser_config(p->cmd);
 
 	if (use_pager == -1 && p->option & RUN_SETUP)
 		use_pager = check_pager_config(p->cmd);
 	if (use_pager == -1 && p->option & USE_PAGER)
 		use_pager = 1;
 	commit_pager_choice();
-	set_debugfs_path();
 
 	status = p->fn(argc, argv, prefix);
 	exit_browser(status);
@@ -296,42 +329,28 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv)
 	if (S_ISFIFO(st.st_mode) || S_ISSOCK(st.st_mode))
 		return 0;
 
+	status = 1;
 	/* Check for ENOSPC and EIO errors.. */
-	if (fflush(stdout))
-		die("write failure on standard output: %s", strerror(errno));
-	if (ferror(stdout))
-		die("unknown write failure on standard output");
-	if (fclose(stdout))
-		die("close failed on standard output: %s", strerror(errno));
-	return 0;
+	if (fflush(stdout)) {
+		fprintf(stderr, "write failure on standard output: %s", strerror(errno));
+		goto out;
+	}
+	if (ferror(stdout)) {
+		fprintf(stderr, "unknown write failure on standard output");
+		goto out;
+	}
+	if (fclose(stdout)) {
+		fprintf(stderr, "close failed on standard output: %s", strerror(errno));
+		goto out;
+	}
+	status = 0;
+out:
+	return status;
 }
 
 static void handle_internal_command(int argc, const char **argv)
 {
 	const char *cmd = argv[0];
-	static struct cmd_struct commands[] = {
-		{ "buildid-cache", cmd_buildid_cache, 0 },
-		{ "buildid-list", cmd_buildid_list, 0 },
-		{ "diff",	cmd_diff,	0 },
-		{ "help",	cmd_help,	0 },
-		{ "list",	cmd_list,	0 },
-		{ "record",	cmd_record,	0 },
-		{ "report",	cmd_report,	0 },
-		{ "bench",	cmd_bench,	0 },
-		{ "stat",	cmd_stat,	0 },
-		{ "timechart",	cmd_timechart,	0 },
-		{ "top",	cmd_top,	0 },
-		{ "annotate",	cmd_annotate,	0 },
-		{ "version",	cmd_version,	0 },
-		{ "trace",	cmd_trace,	0 },
-		{ "sched",	cmd_sched,	0 },
-		{ "probe",	cmd_probe,	0 },
-		{ "kmem",	cmd_kmem,	0 },
-		{ "lock",	cmd_lock,	0 },
-		{ "kvm",	cmd_kvm,	0 },
-		{ "test",	cmd_test,	0 },
-		{ "inject",	cmd_inject,	0 },
-	};
 	unsigned int i;
 	static const char ext[] = STRIP_EXTENSION;
 
@@ -415,26 +434,37 @@ static int run_argv(int *argcp, const char ***argv)
 	return done_alias;
 }
 
-/* mini /proc/mounts parser: searching for "^blah /mount/point debugfs" */
-static void get_debugfs_mntpt(void)
+static void pthread__block_sigwinch(void)
+{
+	sigset_t set;
+
+	sigemptyset(&set);
+	sigaddset(&set, SIGWINCH);
+	pthread_sigmask(SIG_BLOCK, &set, NULL);
+}
+
+void pthread__unblock_sigwinch(void)
 {
-	const char *path = debugfs_mount(NULL);
+	sigset_t set;
 
-	if (path)
-		strncpy(debugfs_mntpt, path, sizeof(debugfs_mntpt));
-	else
-		debugfs_mntpt[0] = '\0';
+	sigemptyset(&set);
+	sigaddset(&set, SIGWINCH);
+	pthread_sigmask(SIG_UNBLOCK, &set, NULL);
 }
 
 int main(int argc, const char **argv)
 {
 	const char *cmd;
 
+	/* The page_size is placed in util object. */
+	page_size = sysconf(_SC_PAGE_SIZE);
+	cacheline_size = sysconf(_SC_LEVEL1_DCACHE_LINESIZE);
+
 	cmd = perf_extract_argv0_path(argv[0]);
 	if (!cmd)
 		cmd = "perf-help";
 	/* get debugfs mount point from /proc/mounts */
-	get_debugfs_mntpt();
+	perf_debugfs_mount(NULL);
 	/*
 	 * "perf-xxxx" is the same as "perf xxxx", but we obviously:
 	 *
@@ -449,15 +479,28 @@ int main(int argc, const char **argv)
 		cmd += 5;
 		argv[0] = cmd;
 		handle_internal_command(argc, argv);
-		die("cannot handle %s internally", cmd);
+		fprintf(stderr, "cannot handle %s internally", cmd);
+		goto out;
+	}
+	if (!prefixcmp(cmd, "trace")) {
+#ifdef HAVE_LIBAUDIT_SUPPORT
+		set_buildid_dir();
+		setup_path();
+		argv[0] = "trace";
+		return cmd_trace(argc, argv, NULL);
+#else
+		fprintf(stderr,
+			"trace command not available: missing audit-libs devel package at build time.\n");
+		goto out;
+#endif
 	}
-
 	/* Look for flags.. */
 	argv++;
 	argc--;
 	handle_options(&argv, &argc, NULL);
 	commit_pager_choice();
-	set_debugfs_path();
+	set_buildid_dir();
+
 	if (argc > 0) {
 		if (!prefixcmp(argv[0], "--"))
 			argv[0] += 2;
@@ -466,10 +509,12 @@ int main(int argc, const char **argv)
 		printf("\n usage: %s\n\n", perf_usage_string);
 		list_common_cmds_help();
 		printf("\n %s\n\n", perf_more_info_string);
-		exit(1);
+		goto out;
 	}
 	cmd = argv[0];
 
+	test_attr__init();
+
 	/*
 	 * We use PATH to find perf commands, but we prepend some higher
 	 * precedence paths: the "--exec-path" option, the PERF_EXEC_PATH
@@ -477,12 +522,17 @@ int main(int argc, const char **argv)
 	 * time.
 	 */
 	setup_path();
+	/*
+	 * Block SIGWINCH notifications so that the thread that wants it can
+	 * unblock and get syscalls like select interrupted instead of waiting
+	 * forever while the signal goes to some other non interested thread.
+	 */
+	pthread__block_sigwinch();
 
 	while (1) {
 		static int done_help;
-		static int was_alias;
+		int was_alias = run_argv(&argc, &argv);
 
-		was_alias = run_argv(&argc, &argv);
 		if (errno != ENOENT)
 			break;
 
@@ -490,7 +540,7 @@ int main(int argc, const char **argv)
 			fprintf(stderr, "Expansion of alias '%s' failed; "
 				"'%s' is not a perf-command\n",
 				cmd, argv[0]);
-			exit(1);
+			goto out;
 		}
 		if (!done_help) {
 			cmd = argv[0] = help_unknown_cmd(cmd);
@@ -501,6 +551,6 @@ int main(int argc, const char **argv)
 
 	fprintf(stderr, "Failed to run command '%s': %s\n",
 		cmd, strerror(errno));
-
+out:
 	return 1;
 }
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index ef7aa0a0c52..510c65f7285 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -1,97 +1,25 @@
 #ifndef _PERF_PERF_H
 #define _PERF_PERF_H
 
-struct winsize;
-
-void get_term_dimensions(struct winsize *ws);
-
-#if defined(__i386__)
-#include "../../arch/x86/include/asm/unistd.h"
-#define rmb()		asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
-#define cpu_relax()	asm volatile("rep; nop" ::: "memory");
-#endif
-
-#if defined(__x86_64__)
-#include "../../arch/x86/include/asm/unistd.h"
-#define rmb()		asm volatile("lfence" ::: "memory")
-#define cpu_relax()	asm volatile("rep; nop" ::: "memory");
-#endif
-
-#ifdef __powerpc__
-#include "../../arch/powerpc/include/asm/unistd.h"
-#define rmb()		asm volatile ("sync" ::: "memory")
-#define cpu_relax()	asm volatile ("" ::: "memory");
-#endif
-
-#ifdef __s390__
-#include "../../arch/s390/include/asm/unistd.h"
-#define rmb()		asm volatile("bcr 15,0" ::: "memory")
-#define cpu_relax()	asm volatile("" ::: "memory");
-#endif
-
-#ifdef __sh__
-#include "../../arch/sh/include/asm/unistd.h"
-#if defined(__SH4A__) || defined(__SH5__)
-# define rmb()		asm volatile("synco" ::: "memory")
-#else
-# define rmb()		asm volatile("" ::: "memory")
-#endif
-#define cpu_relax()	asm volatile("" ::: "memory")
-#endif
-
-#ifdef __hppa__
-#include "../../arch/parisc/include/asm/unistd.h"
-#define rmb()		asm volatile("" ::: "memory")
-#define cpu_relax()	asm volatile("" ::: "memory");
-#endif
-
-#ifdef __sparc__
-#include "../../arch/sparc/include/asm/unistd.h"
-#define rmb()		asm volatile("":::"memory")
-#define cpu_relax()	asm volatile("":::"memory")
-#endif
-
-#ifdef __alpha__
-#include "../../arch/alpha/include/asm/unistd.h"
-#define rmb()		asm volatile("mb" ::: "memory")
-#define cpu_relax()	asm volatile("" ::: "memory")
-#endif
-
-#ifdef __ia64__
-#include "../../arch/ia64/include/asm/unistd.h"
-#define rmb()		asm volatile ("mf" ::: "memory")
-#define cpu_relax()	asm volatile ("hint @pause" ::: "memory")
-#endif
-
-#ifdef __arm__
-#include "../../arch/arm/include/asm/unistd.h"
-/*
- * Use the __kuser_memory_barrier helper in the CPU helper page. See
- * arch/arm/kernel/entry-armv.S in the kernel source for details.
- */
-#define rmb()		((void(*)(void))0xffff0fa0)()
-#define cpu_relax()	asm volatile("":::"memory")
-#endif
-
 #include <time.h>
-#include <unistd.h>
-#include <sys/types.h>
-#include <sys/syscall.h>
-
-#include "../../include/linux/perf_event.h"
-#include "util/types.h"
 #include <stdbool.h>
+#include <linux/types.h>
+#include <linux/perf_event.h>
 
-/*
- * prctl(PR_TASK_PERF_EVENTS_DISABLE) will (cheaply) disable all
- * counters in the current task.
- */
-#define PR_TASK_PERF_EVENTS_DISABLE   31
-#define PR_TASK_PERF_EVENTS_ENABLE    32
+extern bool test_attr__enabled;
+void test_attr__init(void);
+void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu,
+		     int fd, int group_fd, unsigned long flags);
+
+#define HAVE_ATTR_TEST
+#include "perf-sys.h"
 
 #ifndef NSEC_PER_SEC
 # define NSEC_PER_SEC			1000000000ULL
 #endif
+#ifndef NSEC_PER_USEC
+# define NSEC_PER_USEC			1000ULL
+#endif
 
 static inline unsigned long long rdclock(void)
 {
@@ -101,37 +29,40 @@ static inline unsigned long long rdclock(void)
 	return ts.tv_sec * 1000000000ULL + ts.tv_nsec;
 }
 
-/*
- * Pick up some kernel type conventions:
- */
-#define __user
-#define asmlinkage
-
-#define unlikely(x)	__builtin_expect(!!(x), 0)
-#define min(x, y) ({				\
-	typeof(x) _min1 = (x);			\
-	typeof(y) _min2 = (y);			\
-	(void) (&_min1 == &_min2);		\
-	_min1 < _min2 ? _min1 : _min2; })
-
-static inline int
-sys_perf_event_open(struct perf_event_attr *attr,
-		      pid_t pid, int cpu, int group_fd,
-		      unsigned long flags)
-{
-	attr->size = sizeof(*attr);
-	return syscall(__NR_perf_event_open, attr, pid, cpu,
-		       group_fd, flags);
-}
-
-#define MAX_COUNTERS			256
 #define MAX_NR_CPUS			256
 
-struct ip_callchain {
-	u64 nr;
-	u64 ips[0];
-};
-
+extern const char *input_name;
 extern bool perf_host, perf_guest;
+extern const char perf_version_string[];
+
+void pthread__unblock_sigwinch(void);
+
+#include "util/target.h"
+
+struct record_opts {
+	struct target target;
+	int	     call_graph;
+	bool         call_graph_enabled;
+	bool	     group;
+	bool	     inherit_stat;
+	bool	     no_buffering;
+	bool	     no_inherit;
+	bool	     no_inherit_set;
+	bool	     no_samples;
+	bool	     raw_samples;
+	bool	     sample_address;
+	bool	     sample_weight;
+	bool	     sample_time;
+	bool	     period;
+	unsigned int freq;
+	unsigned int mmap_pages;
+	unsigned int user_freq;
+	u64          branch_stack;
+	u64	     default_interval;
+	u64	     user_interval;
+	u16	     stack_dump_size;
+	bool	     sample_transaction;
+	unsigned     initial_delay;
+};
 
 #endif
diff --git a/tools/perf/python/twatch.py b/tools/perf/python/twatch.py
new file mode 100755
index 00000000000..2225162ee1f
--- /dev/null
+++ b/tools/perf/python/twatch.py
@@ -0,0 +1,41 @@
+#! /usr/bin/python
+# -*- python -*-
+# -*- coding: utf-8 -*-
+#   twatch - Experimental use of the perf python interface
+#   Copyright (C) 2011 Arnaldo Carvalho de Melo <acme@redhat.com>
+#
+#   This application is free software; you can redistribute it and/or
+#   modify it under the terms of the GNU General Public License
+#   as published by the Free Software Foundation; version 2.
+#
+#   This application is distributed in the hope that it will be useful,
+#   but WITHOUT ANY WARRANTY; without even the implied warranty of
+#   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+#   General Public License for more details.
+
+import perf
+
+def main():
+	cpus = perf.cpu_map()
+	threads = perf.thread_map()
+	evsel = perf.evsel(task = 1, comm = 1, mmap = 0,
+			   wakeup_events = 1, watermark = 1,
+			   sample_id_all = 1,
+			   sample_type = perf.SAMPLE_PERIOD | perf.SAMPLE_TID | perf.SAMPLE_CPU)
+	evsel.open(cpus = cpus, threads = threads);
+	evlist = perf.evlist(cpus, threads)
+	evlist.add(evsel)
+	evlist.mmap()
+	while True:
+		evlist.poll(timeout = -1)
+		for cpu in cpus:
+			event = evlist.read_on_cpu(cpu)
+			if not event:
+				continue
+			print "cpu: %2d, pid: %4d, tid: %4d" % (event.sample_cpu,
+								event.sample_pid,
+								event.sample_tid),
+			print event
+
+if __name__ == '__main__':
+    main()
diff --git a/tools/perf/scripts/perl/Perf-Trace-Util/Context.c b/tools/perf/scripts/perl/Perf-Trace-Util/Context.c
index 01a64ad693f..790ceba6ad3 100644
--- a/tools/perf/scripts/perl/Perf-Trace-Util/Context.c
+++ b/tools/perf/scripts/perl/Perf-Trace-Util/Context.c
@@ -8,7 +8,7 @@
 
 #line 1 "Context.xs"
 /*
- * Context.xs.  XS interfaces for perf trace.
+ * Context.xs.  XS interfaces for perf script.
  *
  * Copyright (C) 2009 Tom Zanussi <tzanussi@gmail.com>
  *
diff --git a/tools/perf/scripts/perl/Perf-Trace-Util/Context.xs b/tools/perf/scripts/perl/Perf-Trace-Util/Context.xs
index 549cf0467d3..8c7ea42444d 100644
--- a/tools/perf/scripts/perl/Perf-Trace-Util/Context.xs
+++ b/tools/perf/scripts/perl/Perf-Trace-Util/Context.xs
@@ -1,5 +1,5 @@
 /*
- * Context.xs.  XS interfaces for perf trace.
+ * Context.xs.  XS interfaces for perf script.
  *
  * Copyright (C) 2009 Tom Zanussi <tzanussi@gmail.com>
  *
diff --git a/tools/perf/scripts/perl/Perf-Trace-Util/README b/tools/perf/scripts/perl/Perf-Trace-Util/README
index 9a970763079..2f0c7f3043e 100644
--- a/tools/perf/scripts/perl/Perf-Trace-Util/README
+++ b/tools/perf/scripts/perl/Perf-Trace-Util/README
@@ -1,7 +1,7 @@
 Perf-Trace-Util version 0.01
 ============================
 
-This module contains utility functions for use with perf trace.
+This module contains utility functions for use with perf script.
 
 Core.pm and Util.pm are pure Perl modules; Core.pm contains routines
 that the core perf support for Perl calls on and should always be
@@ -33,7 +33,7 @@ After you do that:
 
 INSTALLATION
 
-Building perf with perf trace Perl scripting should install this
+Building perf with perf script Perl scripting should install this
 module in the right place.
 
 You should make sure libperl and ExtUtils/Embed.pm are installed first
diff --git a/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Context.pm b/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Context.pm
index 6c7f3659cb1..4e2f6039ac9 100644
--- a/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Context.pm
+++ b/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Context.pm
@@ -34,7 +34,7 @@ Perf::Trace::Context - Perl extension for accessing functions in perf.
 
 =head1 SEE ALSO
 
-Perf (trace) documentation
+Perf (script) documentation
 
 =head1 AUTHOR
 
diff --git a/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Core.pm b/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Core.pm
index 9df376a9f62..9158458d3ee 100644
--- a/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Core.pm
+++ b/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Core.pm
@@ -163,7 +163,7 @@ sub dump_symbolic_fields
 __END__
 =head1 NAME
 
-Perf::Trace::Core - Perl extension for perf trace
+Perf::Trace::Core - Perl extension for perf script
 
 =head1 SYNOPSIS
 
@@ -171,7 +171,7 @@ Perf::Trace::Core - Perl extension for perf trace
 
 =head1 SEE ALSO
 
-Perf (trace) documentation
+Perf (script) documentation
 
 =head1 AUTHOR
 
diff --git a/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Util.pm b/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Util.pm
index d94b40c8ac8..05350011462 100644
--- a/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Util.pm
+++ b/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Util.pm
@@ -65,7 +65,7 @@ sub clear_term
 __END__
 =head1 NAME
 
-Perf::Trace::Util - Perl extension for perf trace
+Perf::Trace::Util - Perl extension for perf script
 
 =head1 SYNOPSIS
 
@@ -73,7 +73,7 @@ Perf::Trace::Util - Perl extension for perf trace
 
 =head1 SEE ALSO
 
-Perf (trace) documentation
+Perf (script) documentation
 
 =head1 AUTHOR
 
diff --git a/tools/perf/scripts/perl/bin/failed-syscalls-record b/tools/perf/scripts/perl/bin/failed-syscalls-record
index eb5846bcb56..8104895a7b6 100644
--- a/tools/perf/scripts/perl/bin/failed-syscalls-record
+++ b/tools/perf/scripts/perl/bin/failed-syscalls-record
@@ -1,2 +1,2 @@
 #!/bin/bash
-perf record -a -e raw_syscalls:sys_exit $@
+perf record -e raw_syscalls:sys_exit $@
diff --git a/tools/perf/scripts/perl/bin/failed-syscalls-report b/tools/perf/scripts/perl/bin/failed-syscalls-report
index e3a5e55d54f..9f83cc1ad8b 100644
--- a/tools/perf/scripts/perl/bin/failed-syscalls-report
+++ b/tools/perf/scripts/perl/bin/failed-syscalls-report
@@ -7,4 +7,4 @@ if [ $# -gt 0 ] ; then
 	shift
     fi
 fi
-perf trace $@ -s ~/libexec/perf-core/scripts/perl/failed-syscalls.pl $comm
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/perl/failed-syscalls.pl $comm
diff --git a/tools/perf/scripts/perl/bin/rw-by-file-record b/tools/perf/scripts/perl/bin/rw-by-file-record
index 5bfaae5a6cb..33efc8673aa 100644
--- a/tools/perf/scripts/perl/bin/rw-by-file-record
+++ b/tools/perf/scripts/perl/bin/rw-by-file-record
@@ -1,3 +1,3 @@
 #!/bin/bash
-perf record -a -e syscalls:sys_enter_read -e syscalls:sys_enter_write $@
+perf record -e syscalls:sys_enter_read -e syscalls:sys_enter_write $@
 
diff --git a/tools/perf/scripts/perl/bin/rw-by-file-report b/tools/perf/scripts/perl/bin/rw-by-file-report
index d83070b7eeb..77200b3f310 100644
--- a/tools/perf/scripts/perl/bin/rw-by-file-report
+++ b/tools/perf/scripts/perl/bin/rw-by-file-report
@@ -7,7 +7,4 @@ if [ $# -lt 1 ] ; then
 fi
 comm=$1
 shift
-perf trace $@ -s ~/libexec/perf-core/scripts/perl/rw-by-file.pl $comm
-
-
-
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/perl/rw-by-file.pl $comm
diff --git a/tools/perf/scripts/perl/bin/rw-by-pid-record b/tools/perf/scripts/perl/bin/rw-by-pid-record
index 6e0b2f7755a..7cb9db23044 100644
--- a/tools/perf/scripts/perl/bin/rw-by-pid-record
+++ b/tools/perf/scripts/perl/bin/rw-by-pid-record
@@ -1,2 +1,2 @@
 #!/bin/bash
-perf record -a -e syscalls:sys_enter_read -e syscalls:sys_exit_read -e syscalls:sys_enter_write -e syscalls:sys_exit_write $@
+perf record -e syscalls:sys_enter_read -e syscalls:sys_exit_read -e syscalls:sys_enter_write -e syscalls:sys_exit_write $@
diff --git a/tools/perf/scripts/perl/bin/rw-by-pid-report b/tools/perf/scripts/perl/bin/rw-by-pid-report
index 7ef46983f62..a27b9f311f9 100644
--- a/tools/perf/scripts/perl/bin/rw-by-pid-report
+++ b/tools/perf/scripts/perl/bin/rw-by-pid-report
@@ -1,6 +1,3 @@
 #!/bin/bash
 # description: system-wide r/w activity
-perf trace $@ -s ~/libexec/perf-core/scripts/perl/rw-by-pid.pl
-
-
-
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/perl/rw-by-pid.pl
diff --git a/tools/perf/scripts/perl/bin/rwtop-record b/tools/perf/scripts/perl/bin/rwtop-record
index 6e0b2f7755a..7cb9db23044 100644
--- a/tools/perf/scripts/perl/bin/rwtop-record
+++ b/tools/perf/scripts/perl/bin/rwtop-record
@@ -1,2 +1,2 @@
 #!/bin/bash
-perf record -a -e syscalls:sys_enter_read -e syscalls:sys_exit_read -e syscalls:sys_enter_write -e syscalls:sys_exit_write $@
+perf record -e syscalls:sys_enter_read -e syscalls:sys_exit_read -e syscalls:sys_enter_write -e syscalls:sys_exit_write $@
diff --git a/tools/perf/scripts/perl/bin/rwtop-report b/tools/perf/scripts/perl/bin/rwtop-report
index 93e698cd3f3..83e11ec2e19 100644
--- a/tools/perf/scripts/perl/bin/rwtop-report
+++ b/tools/perf/scripts/perl/bin/rwtop-report
@@ -17,7 +17,4 @@ if [ "$n_args" -gt 0 ] ; then
     interval=$1
     shift
 fi
-perf trace $@ -s ~/libexec/perf-core/scripts/perl/rwtop.pl $interval
-
-
-
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/perl/rwtop.pl $interval
diff --git a/tools/perf/scripts/perl/bin/wakeup-latency-record b/tools/perf/scripts/perl/bin/wakeup-latency-record
index 9f2acaaae9f..464251a1bd7 100644
--- a/tools/perf/scripts/perl/bin/wakeup-latency-record
+++ b/tools/perf/scripts/perl/bin/wakeup-latency-record
@@ -1,5 +1,5 @@
 #!/bin/bash
-perf record -a -e sched:sched_switch -e sched:sched_wakeup $@
+perf record -e sched:sched_switch -e sched:sched_wakeup $@
 
 
 
diff --git a/tools/perf/scripts/perl/bin/wakeup-latency-report b/tools/perf/scripts/perl/bin/wakeup-latency-report
index a0d898f9ca1..889e8130cca 100644
--- a/tools/perf/scripts/perl/bin/wakeup-latency-report
+++ b/tools/perf/scripts/perl/bin/wakeup-latency-report
@@ -1,6 +1,3 @@
 #!/bin/bash
 # description: system-wide min/max/avg wakeup latency
-perf trace $@ -s ~/libexec/perf-core/scripts/perl/wakeup-latency.pl
-
-
-
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/perl/wakeup-latency.pl
diff --git a/tools/perf/scripts/perl/bin/workqueue-stats-record b/tools/perf/scripts/perl/bin/workqueue-stats-record
deleted file mode 100644
index 85301f2471f..00000000000
--- a/tools/perf/scripts/perl/bin/workqueue-stats-record
+++ /dev/null
@@ -1,2 +0,0 @@
-#!/bin/bash
-perf record -a -e workqueue:workqueue_creation -e workqueue:workqueue_destruction -e workqueue:workqueue_execution -e workqueue:workqueue_insertion $@
diff --git a/tools/perf/scripts/perl/bin/workqueue-stats-report b/tools/perf/scripts/perl/bin/workqueue-stats-report
deleted file mode 100644
index 35081132ef9..00000000000
--- a/tools/perf/scripts/perl/bin/workqueue-stats-report
+++ /dev/null
@@ -1,7 +0,0 @@
-#!/bin/bash
-# description: workqueue stats (ins/exe/create/destroy)
-perf trace $@ -s ~/libexec/perf-core/scripts/perl/workqueue-stats.pl
-
-
-
-
diff --git a/tools/perf/scripts/perl/check-perf-trace.pl b/tools/perf/scripts/perl/check-perf-trace.pl
index 4e7dc0a407a..4e7076c2061 100644
--- a/tools/perf/scripts/perl/check-perf-trace.pl
+++ b/tools/perf/scripts/perl/check-perf-trace.pl
@@ -1,4 +1,4 @@
-# perf trace event handlers, generated by perf trace -g perl
+# perf script event handlers, generated by perf script -g perl
 # (c) 2009, Tom Zanussi <tzanussi@gmail.com>
 # Licensed under the terms of the GNU GPL License version 2
 
diff --git a/tools/perf/scripts/perl/rw-by-file.pl b/tools/perf/scripts/perl/rw-by-file.pl
index 2a39097687b..74844ee2be3 100644
--- a/tools/perf/scripts/perl/rw-by-file.pl
+++ b/tools/perf/scripts/perl/rw-by-file.pl
@@ -18,7 +18,7 @@ use lib "./Perf-Trace-Util/lib";
 use Perf::Trace::Core;
 use Perf::Trace::Util;
 
-my $usage = "perf trace -s rw-by-file.pl <comm>\n";
+my $usage = "perf script -s rw-by-file.pl <comm>\n";
 
 my $for_comm = shift or die $usage;
 
diff --git a/tools/perf/scripts/perl/rwtop.pl b/tools/perf/scripts/perl/rwtop.pl
index 4bb3ecd3347..8b20787021c 100644
--- a/tools/perf/scripts/perl/rwtop.pl
+++ b/tools/perf/scripts/perl/rwtop.pl
@@ -17,6 +17,7 @@ use lib "$ENV{'PERF_EXEC_PATH'}/scripts/perl/Perf-Trace-Util/lib";
 use lib "./Perf-Trace-Util/lib";
 use Perf::Trace::Core;
 use Perf::Trace::Util;
+use POSIX qw/SIGALRM SA_RESTART/;
 
 my $default_interval = 3;
 my $nlines = 20;
@@ -90,7 +91,10 @@ sub syscalls::sys_enter_write
 
 sub trace_begin
 {
-    $SIG{ALRM} = \&set_print_pending;
+    my $sa = POSIX::SigAction->new(\&set_print_pending);
+    $sa->flags(SA_RESTART);
+    $sa->safe(1);
+    POSIX::sigaction(SIGALRM, $sa) or die "Can't set SIGALRM handler: $!\n";
     alarm 1;
 }
 
diff --git a/tools/perf/scripts/perl/workqueue-stats.pl b/tools/perf/scripts/perl/workqueue-stats.pl
deleted file mode 100644
index b84b12699b7..00000000000
--- a/tools/perf/scripts/perl/workqueue-stats.pl
+++ /dev/null
@@ -1,129 +0,0 @@
-#!/usr/bin/perl -w
-# (c) 2009, Tom Zanussi <tzanussi@gmail.com>
-# Licensed under the terms of the GNU GPL License version 2
-
-# Displays workqueue stats
-#
-# Usage:
-#
-#   perf record -c 1 -f -a -R -e workqueue:workqueue_creation -e
-#     workqueue:workqueue_destruction -e workqueue:workqueue_execution
-#     -e workqueue:workqueue_insertion
-#
-#   perf trace -p -s tools/perf/scripts/perl/workqueue-stats.pl
-
-use 5.010000;
-use strict;
-use warnings;
-
-use lib "$ENV{'PERF_EXEC_PATH'}/scripts/perl/Perf-Trace-Util/lib";
-use lib "./Perf-Trace-Util/lib";
-use Perf::Trace::Core;
-use Perf::Trace::Util;
-
-my @cpus;
-
-sub workqueue::workqueue_destruction
-{
-    my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
-	$common_pid, $common_comm,
-	$thread_comm, $thread_pid) = @_;
-
-    $cpus[$common_cpu]{$thread_pid}{destroyed}++;
-    $cpus[$common_cpu]{$thread_pid}{comm} = $thread_comm;
-}
-
-sub workqueue::workqueue_creation
-{
-    my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
-	$common_pid, $common_comm,
-	$thread_comm, $thread_pid, $cpu) = @_;
-
-    $cpus[$common_cpu]{$thread_pid}{created}++;
-    $cpus[$common_cpu]{$thread_pid}{comm} = $thread_comm;
-}
-
-sub workqueue::workqueue_execution
-{
-    my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
-	$common_pid, $common_comm,
-	$thread_comm, $thread_pid, $func) = @_;
-
-    $cpus[$common_cpu]{$thread_pid}{executed}++;
-    $cpus[$common_cpu]{$thread_pid}{comm} = $thread_comm;
-}
-
-sub workqueue::workqueue_insertion
-{
-    my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
-	$common_pid, $common_comm,
-	$thread_comm, $thread_pid, $func) = @_;
-
-    $cpus[$common_cpu]{$thread_pid}{inserted}++;
-    $cpus[$common_cpu]{$thread_pid}{comm} = $thread_comm;
-}
-
-sub trace_end
-{
-    print "workqueue work stats:\n\n";
-    my $cpu = 0;
-    printf("%3s %6s %6s\t%-20s\n", "cpu", "ins", "exec", "name");
-    printf("%3s %6s %6s\t%-20s\n", "---", "---", "----", "----");
-    foreach my $pidhash (@cpus) {
-	while ((my $pid, my $wqhash) = each %$pidhash) {
-	    my $ins = $$wqhash{'inserted'} || 0;
-	    my $exe = $$wqhash{'executed'} || 0;
-	    my $comm = $$wqhash{'comm'} || "";
-	    if ($ins || $exe) {
-		printf("%3u %6u %6u\t%-20s\n", $cpu, $ins, $exe, $comm);
-	    }
-	}
-	$cpu++;
-    }
-
-    $cpu = 0;
-    print "\nworkqueue lifecycle stats:\n\n";
-    printf("%3s %6s %6s\t%-20s\n", "cpu", "created", "destroyed", "name");
-    printf("%3s %6s %6s\t%-20s\n", "---", "-------", "---------", "----");
-    foreach my $pidhash (@cpus) {
-	while ((my $pid, my $wqhash) = each %$pidhash) {
-	    my $created = $$wqhash{'created'} || 0;
-	    my $destroyed = $$wqhash{'destroyed'} || 0;
-	    my $comm = $$wqhash{'comm'} || "";
-	    if ($created || $destroyed) {
-		printf("%3u %6u %6u\t%-20s\n", $cpu, $created, $destroyed,
-		       $comm);
-	    }
-	}
-	$cpu++;
-    }
-
-    print_unhandled();
-}
-
-my %unhandled;
-
-sub print_unhandled
-{
-    if ((scalar keys %unhandled) == 0) {
-	return;
-    }
-
-    print "\nunhandled events:\n\n";
-
-    printf("%-40s  %10s\n", "event", "count");
-    printf("%-40s  %10s\n", "----------------------------------------",
-	   "-----------");
-
-    foreach my $event_name (keys %unhandled) {
-	printf("%-40s  %10d\n", $event_name, $unhandled{$event_name});
-    }
-}
-
-sub trace_unhandled
-{
-    my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
-	$common_pid, $common_comm) = @_;
-
-    $unhandled{$event_name}++;
-}
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/Context.c b/tools/perf/scripts/python/Perf-Trace-Util/Context.c
index 957085dd5d8..fcd1dd66790 100644
--- a/tools/perf/scripts/python/Perf-Trace-Util/Context.c
+++ b/tools/perf/scripts/python/Perf-Trace-Util/Context.c
@@ -1,5 +1,5 @@
 /*
- * Context.c.  Python interfaces for perf trace.
+ * Context.c.  Python interfaces for perf script.
  *
  * Copyright (C) 2010 Tom Zanussi <tzanussi@gmail.com>
  *
@@ -25,7 +25,7 @@
 
 PyMODINIT_FUNC initperf_trace_context(void);
 
-static PyObject *perf_trace_context_common_pc(PyObject *self, PyObject *args)
+static PyObject *perf_trace_context_common_pc(PyObject *obj, PyObject *args)
 {
 	static struct scripting_context *scripting_context;
 	PyObject *context;
@@ -40,7 +40,7 @@ static PyObject *perf_trace_context_common_pc(PyObject *self, PyObject *args)
 	return Py_BuildValue("i", retval);
 }
 
-static PyObject *perf_trace_context_common_flags(PyObject *self,
+static PyObject *perf_trace_context_common_flags(PyObject *obj,
 						 PyObject *args)
 {
 	static struct scripting_context *scripting_context;
@@ -56,7 +56,7 @@ static PyObject *perf_trace_context_common_flags(PyObject *self,
 	return Py_BuildValue("i", retval);
 }
 
-static PyObject *perf_trace_context_common_lock_depth(PyObject *self,
+static PyObject *perf_trace_context_common_lock_depth(PyObject *obj,
 						      PyObject *args)
 {
 	static struct scripting_context *scripting_context;
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py
index 1dc464ee2ca..de7211e4fa4 100644
--- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py
+++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py
@@ -1,4 +1,4 @@
-# Core.py - Python extension for perf trace, core functions
+# Core.py - Python extension for perf script, core functions
 #
 # Copyright (C) 2010 by Tom Zanussi <tzanussi@gmail.com>
 #
@@ -89,3 +89,33 @@ def trace_flag_str(value):
 	    value &= ~idx
 
     return string
+
+
+def taskState(state):
+	states = {
+		0 : "R",
+		1 : "S",
+		2 : "D",
+		64: "DEAD"
+	}
+
+	if state not in states:
+		return "Unknown"
+
+	return states[state]
+
+
+class EventHeaders:
+	def __init__(self, common_cpu, common_secs, common_nsecs,
+		     common_pid, common_comm):
+		self.cpu = common_cpu
+		self.secs = common_secs
+		self.nsecs = common_nsecs
+		self.pid = common_pid
+		self.comm = common_comm
+
+	def ts(self):
+		return (self.secs * (10 ** 9)) + self.nsecs
+
+	def ts_format(self):
+		return "%d.%d" % (self.secs, int(self.nsecs / 1000))
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py
new file mode 100755
index 00000000000..9e0985794e2
--- /dev/null
+++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py
@@ -0,0 +1,94 @@
+# EventClass.py
+#
+# This is a library defining some events types classes, which could
+# be used by other scripts to analyzing the perf samples.
+#
+# Currently there are just a few classes defined for examples,
+# PerfEvent is the base class for all perf event sample, PebsEvent
+# is a HW base Intel x86 PEBS event, and user could add more SW/HW
+# event classes based on requirements.
+
+import struct
+
+# Event types, user could add more here
+EVTYPE_GENERIC  = 0
+EVTYPE_PEBS     = 1     # Basic PEBS event
+EVTYPE_PEBS_LL  = 2     # PEBS event with load latency info
+EVTYPE_IBS      = 3
+
+#
+# Currently we don't have good way to tell the event type, but by
+# the size of raw buffer, raw PEBS event with load latency data's
+# size is 176 bytes, while the pure PEBS event's size is 144 bytes.
+#
+def create_event(name, comm, dso, symbol, raw_buf):
+        if (len(raw_buf) == 144):
+                event = PebsEvent(name, comm, dso, symbol, raw_buf)
+        elif (len(raw_buf) == 176):
+                event = PebsNHM(name, comm, dso, symbol, raw_buf)
+        else:
+                event = PerfEvent(name, comm, dso, symbol, raw_buf)
+
+        return event
+
+class PerfEvent(object):
+        event_num = 0
+        def __init__(self, name, comm, dso, symbol, raw_buf, ev_type=EVTYPE_GENERIC):
+                self.name       = name
+                self.comm       = comm
+                self.dso        = dso
+                self.symbol     = symbol
+                self.raw_buf    = raw_buf
+                self.ev_type    = ev_type
+                PerfEvent.event_num += 1
+
+        def show(self):
+                print "PMU event: name=%12s, symbol=%24s, comm=%8s, dso=%12s" % (self.name, self.symbol, self.comm, self.dso)
+
+#
+# Basic Intel PEBS (Precise Event-based Sampling) event, whose raw buffer
+# contains the context info when that event happened: the EFLAGS and
+# linear IP info, as well as all the registers.
+#
+class PebsEvent(PerfEvent):
+        pebs_num = 0
+        def __init__(self, name, comm, dso, symbol, raw_buf, ev_type=EVTYPE_PEBS):
+                tmp_buf=raw_buf[0:80]
+                flags, ip, ax, bx, cx, dx, si, di, bp, sp = struct.unpack('QQQQQQQQQQ', tmp_buf)
+                self.flags = flags
+                self.ip    = ip
+                self.ax    = ax
+                self.bx    = bx
+                self.cx    = cx
+                self.dx    = dx
+                self.si    = si
+                self.di    = di
+                self.bp    = bp
+                self.sp    = sp
+
+                PerfEvent.__init__(self, name, comm, dso, symbol, raw_buf, ev_type)
+                PebsEvent.pebs_num += 1
+                del tmp_buf
+
+#
+# Intel Nehalem and Westmere support PEBS plus Load Latency info which lie
+# in the four 64 bit words write after the PEBS data:
+#       Status: records the IA32_PERF_GLOBAL_STATUS register value
+#       DLA:    Data Linear Address (EIP)
+#       DSE:    Data Source Encoding, where the latency happens, hit or miss
+#               in L1/L2/L3 or IO operations
+#       LAT:    the actual latency in cycles
+#
+class PebsNHM(PebsEvent):
+        pebs_nhm_num = 0
+        def __init__(self, name, comm, dso, symbol, raw_buf, ev_type=EVTYPE_PEBS_LL):
+                tmp_buf=raw_buf[144:176]
+                status, dla, dse, lat = struct.unpack('QQQQ', tmp_buf)
+                self.status = status
+                self.dla = dla
+                self.dse = dse
+                self.lat = lat
+
+                PebsEvent.__init__(self, name, comm, dso, symbol, raw_buf, ev_type)
+                PebsNHM.pebs_nhm_num += 1
+                del tmp_buf
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/SchedGui.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/SchedGui.py
new file mode 100644
index 00000000000..fdd92f69905
--- /dev/null
+++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/SchedGui.py
@@ -0,0 +1,184 @@
+# SchedGui.py - Python extension for perf script, basic GUI code for
+#		traces drawing and overview.
+#
+# Copyright (C) 2010 by Frederic Weisbecker <fweisbec@gmail.com>
+#
+# This software is distributed under the terms of the GNU General
+# Public License ("GPL") version 2 as published by the Free Software
+# Foundation.
+
+
+try:
+	import wx
+except ImportError:
+	raise ImportError, "You need to install the wxpython lib for this script"
+
+
+class RootFrame(wx.Frame):
+	Y_OFFSET = 100
+	RECT_HEIGHT = 100
+	RECT_SPACE = 50
+	EVENT_MARKING_WIDTH = 5
+
+	def __init__(self, sched_tracer, title, parent = None, id = -1):
+		wx.Frame.__init__(self, parent, id, title)
+
+		(self.screen_width, self.screen_height) = wx.GetDisplaySize()
+		self.screen_width -= 10
+		self.screen_height -= 10
+		self.zoom = 0.5
+		self.scroll_scale = 20
+		self.sched_tracer = sched_tracer
+		self.sched_tracer.set_root_win(self)
+		(self.ts_start, self.ts_end) = sched_tracer.interval()
+		self.update_width_virtual()
+		self.nr_rects = sched_tracer.nr_rectangles() + 1
+		self.height_virtual = RootFrame.Y_OFFSET + (self.nr_rects * (RootFrame.RECT_HEIGHT + RootFrame.RECT_SPACE))
+
+		# whole window panel
+		self.panel = wx.Panel(self, size=(self.screen_width, self.screen_height))
+
+		# scrollable container
+		self.scroll = wx.ScrolledWindow(self.panel)
+		self.scroll.SetScrollbars(self.scroll_scale, self.scroll_scale, self.width_virtual / self.scroll_scale, self.height_virtual / self.scroll_scale)
+		self.scroll.EnableScrolling(True, True)
+		self.scroll.SetFocus()
+
+		# scrollable drawing area
+		self.scroll_panel = wx.Panel(self.scroll, size=(self.screen_width - 15, self.screen_height / 2))
+		self.scroll_panel.Bind(wx.EVT_PAINT, self.on_paint)
+		self.scroll_panel.Bind(wx.EVT_KEY_DOWN, self.on_key_press)
+		self.scroll_panel.Bind(wx.EVT_LEFT_DOWN, self.on_mouse_down)
+		self.scroll.Bind(wx.EVT_PAINT, self.on_paint)
+		self.scroll.Bind(wx.EVT_KEY_DOWN, self.on_key_press)
+		self.scroll.Bind(wx.EVT_LEFT_DOWN, self.on_mouse_down)
+
+		self.scroll.Fit()
+		self.Fit()
+
+		self.scroll_panel.SetDimensions(-1, -1, self.width_virtual, self.height_virtual, wx.SIZE_USE_EXISTING)
+
+		self.txt = None
+
+		self.Show(True)
+
+	def us_to_px(self, val):
+		return val / (10 ** 3) * self.zoom
+
+	def px_to_us(self, val):
+		return (val / self.zoom) * (10 ** 3)
+
+	def scroll_start(self):
+		(x, y) = self.scroll.GetViewStart()
+		return (x * self.scroll_scale, y * self.scroll_scale)
+
+	def scroll_start_us(self):
+		(x, y) = self.scroll_start()
+		return self.px_to_us(x)
+
+	def paint_rectangle_zone(self, nr, color, top_color, start, end):
+		offset_px = self.us_to_px(start - self.ts_start)
+		width_px = self.us_to_px(end - self.ts_start)
+
+		offset_py = RootFrame.Y_OFFSET + (nr * (RootFrame.RECT_HEIGHT + RootFrame.RECT_SPACE))
+		width_py = RootFrame.RECT_HEIGHT
+
+		dc = self.dc
+
+		if top_color is not None:
+			(r, g, b) = top_color
+			top_color = wx.Colour(r, g, b)
+			brush = wx.Brush(top_color, wx.SOLID)
+			dc.SetBrush(brush)
+			dc.DrawRectangle(offset_px, offset_py, width_px, RootFrame.EVENT_MARKING_WIDTH)
+			width_py -= RootFrame.EVENT_MARKING_WIDTH
+			offset_py += RootFrame.EVENT_MARKING_WIDTH
+
+		(r ,g, b) = color
+		color = wx.Colour(r, g, b)
+		brush = wx.Brush(color, wx.SOLID)
+		dc.SetBrush(brush)
+		dc.DrawRectangle(offset_px, offset_py, width_px, width_py)
+
+	def update_rectangles(self, dc, start, end):
+		start += self.ts_start
+		end += self.ts_start
+		self.sched_tracer.fill_zone(start, end)
+
+	def on_paint(self, event):
+		dc = wx.PaintDC(self.scroll_panel)
+		self.dc = dc
+
+		width = min(self.width_virtual, self.screen_width)
+		(x, y) = self.scroll_start()
+		start = self.px_to_us(x)
+		end = self.px_to_us(x + width)
+		self.update_rectangles(dc, start, end)
+
+	def rect_from_ypixel(self, y):
+		y -= RootFrame.Y_OFFSET
+		rect = y / (RootFrame.RECT_HEIGHT + RootFrame.RECT_SPACE)
+		height = y % (RootFrame.RECT_HEIGHT + RootFrame.RECT_SPACE)
+
+		if rect < 0 or rect > self.nr_rects - 1 or height > RootFrame.RECT_HEIGHT:
+			return -1
+
+		return rect
+
+	def update_summary(self, txt):
+		if self.txt:
+			self.txt.Destroy()
+		self.txt = wx.StaticText(self.panel, -1, txt, (0, (self.screen_height / 2) + 50))
+
+
+	def on_mouse_down(self, event):
+		(x, y) = event.GetPositionTuple()
+		rect = self.rect_from_ypixel(y)
+		if rect == -1:
+			return
+
+		t = self.px_to_us(x) + self.ts_start
+
+		self.sched_tracer.mouse_down(rect, t)
+
+
+	def update_width_virtual(self):
+		self.width_virtual = self.us_to_px(self.ts_end - self.ts_start)
+
+	def __zoom(self, x):
+		self.update_width_virtual()
+		(xpos, ypos) = self.scroll.GetViewStart()
+		xpos = self.us_to_px(x) / self.scroll_scale
+		self.scroll.SetScrollbars(self.scroll_scale, self.scroll_scale, self.width_virtual / self.scroll_scale, self.height_virtual / self.scroll_scale, xpos, ypos)
+		self.Refresh()
+
+	def zoom_in(self):
+		x = self.scroll_start_us()
+		self.zoom *= 2
+		self.__zoom(x)
+
+	def zoom_out(self):
+		x = self.scroll_start_us()
+		self.zoom /= 2
+		self.__zoom(x)
+
+
+	def on_key_press(self, event):
+		key = event.GetRawKeyCode()
+		if key == ord("+"):
+			self.zoom_in()
+			return
+		if key == ord("-"):
+			self.zoom_out()
+			return
+
+		key = event.GetKeyCode()
+		(x, y) = self.scroll.GetViewStart()
+		if key == wx.WXK_RIGHT:
+			self.scroll.Scroll(x + 1, y)
+		elif key == wx.WXK_LEFT:
+			self.scroll.Scroll(x - 1, y)
+		elif key == wx.WXK_DOWN:
+			self.scroll.Scroll(x, y + 1)
+		elif key == wx.WXK_UP:
+			self.scroll.Scroll(x, y - 1)
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
index 9689bc0acd9..15c8400240f 100644
--- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
+++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
@@ -1,4 +1,4 @@
-# Util.py - Python extension for perf trace, miscellaneous utility code
+# Util.py - Python extension for perf script, miscellaneous utility code
 #
 # Copyright (C) 2010 by Tom Zanussi <tzanussi@gmail.com>
 #
@@ -6,6 +6,14 @@
 # Public License ("GPL") version 2 as published by the Free Software
 # Foundation.
 
+import errno, os
+
+FUTEX_WAIT = 0
+FUTEX_WAKE = 1
+FUTEX_PRIVATE_FLAG = 128
+FUTEX_CLOCK_REALTIME = 256
+FUTEX_CMD_MASK = ~(FUTEX_PRIVATE_FLAG | FUTEX_CLOCK_REALTIME)
+
 NSECS_PER_SEC    = 1000000000
 
 def avg(total, n):
@@ -24,5 +32,55 @@ def nsecs_str(nsecs):
     str = "%5u.%09u" % (nsecs_secs(nsecs), nsecs_nsecs(nsecs)),
     return str
 
+def add_stats(dict, key, value):
+	if not dict.has_key(key):
+		dict[key] = (value, value, value, 1)
+	else:
+		min, max, avg, count = dict[key]
+		if value < min:
+			min = value
+		if value > max:
+			max = value
+		avg = (avg + value) / 2
+		dict[key] = (min, max, avg, count + 1)
+
 def clear_term():
     print("\x1b[H\x1b[2J")
+
+audit_package_warned = False
+
+try:
+	import audit
+	machine_to_id = {
+		'x86_64': audit.MACH_86_64,
+		'alpha'	: audit.MACH_ALPHA,
+		'ia64'	: audit.MACH_IA64,
+		'ppc'	: audit.MACH_PPC,
+		'ppc64'	: audit.MACH_PPC64,
+		's390'	: audit.MACH_S390,
+		's390x'	: audit.MACH_S390X,
+		'i386'	: audit.MACH_X86,
+		'i586'	: audit.MACH_X86,
+		'i686'	: audit.MACH_X86,
+	}
+	try:
+		machine_to_id['armeb'] = audit.MACH_ARMEB
+	except:
+		pass
+	machine_id = machine_to_id[os.uname()[4]]
+except:
+	if not audit_package_warned:
+		audit_package_warned = True
+		print "Install the audit-libs-python package to get syscall names"
+
+def syscall_name(id):
+	try:
+		return audit.audit_syscall_to_name(id, machine_id)
+	except:
+		return str(id)
+
+def strerror(nr):
+	try:
+		return errno.errorcode[abs(nr)]
+	except:
+		return "Unknown %d errno" % nr
diff --git a/tools/perf/scripts/python/bin/event_analyzing_sample-record b/tools/perf/scripts/python/bin/event_analyzing_sample-record
new file mode 100644
index 00000000000..5ce652dabd0
--- /dev/null
+++ b/tools/perf/scripts/python/bin/event_analyzing_sample-record
@@ -0,0 +1,8 @@
+#!/bin/bash
+
+#
+# event_analyzing_sample.py can cover all type of perf samples including
+# the tracepoints, so no special record requirements, just record what
+# you want to analyze.
+#
+perf record $@
diff --git a/tools/perf/scripts/python/bin/event_analyzing_sample-report b/tools/perf/scripts/python/bin/event_analyzing_sample-report
new file mode 100644
index 00000000000..0941fc94e15
--- /dev/null
+++ b/tools/perf/scripts/python/bin/event_analyzing_sample-report
@@ -0,0 +1,3 @@
+#!/bin/bash
+# description: analyze all perf samples
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/event_analyzing_sample.py
diff --git a/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record b/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record
index eb5846bcb56..8104895a7b6 100644
--- a/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record
+++ b/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record
@@ -1,2 +1,2 @@
 #!/bin/bash
-perf record -a -e raw_syscalls:sys_exit $@
+perf record -e raw_syscalls:sys_exit $@
diff --git a/tools/perf/scripts/python/bin/failed-syscalls-by-pid-report b/tools/perf/scripts/python/bin/failed-syscalls-by-pid-report
index 30293545fcc..fda5096d0cb 100644
--- a/tools/perf/scripts/python/bin/failed-syscalls-by-pid-report
+++ b/tools/perf/scripts/python/bin/failed-syscalls-by-pid-report
@@ -7,4 +7,4 @@ if [ $# -gt 0 ] ; then
 	shift
     fi
 fi
-perf trace $@ -s ~/libexec/perf-core/scripts/python/failed-syscalls-by-pid.py $comm
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/failed-syscalls-by-pid.py $comm
diff --git a/tools/perf/scripts/python/bin/futex-contention-record b/tools/perf/scripts/python/bin/futex-contention-record
new file mode 100644
index 00000000000..b1495c9a9b2
--- /dev/null
+++ b/tools/perf/scripts/python/bin/futex-contention-record
@@ -0,0 +1,2 @@
+#!/bin/bash
+perf record -e syscalls:sys_enter_futex -e syscalls:sys_exit_futex $@
diff --git a/tools/perf/scripts/python/bin/futex-contention-report b/tools/perf/scripts/python/bin/futex-contention-report
new file mode 100644
index 00000000000..6c44271091a
--- /dev/null
+++ b/tools/perf/scripts/python/bin/futex-contention-report
@@ -0,0 +1,4 @@
+#!/bin/bash
+# description: futext contention measurement
+
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/futex-contention.py
diff --git a/tools/perf/scripts/python/bin/net_dropmonitor-record b/tools/perf/scripts/python/bin/net_dropmonitor-record
new file mode 100755
index 00000000000..423fb81dada
--- /dev/null
+++ b/tools/perf/scripts/python/bin/net_dropmonitor-record
@@ -0,0 +1,2 @@
+#!/bin/bash
+perf record -e skb:kfree_skb $@
diff --git a/tools/perf/scripts/python/bin/net_dropmonitor-report b/tools/perf/scripts/python/bin/net_dropmonitor-report
new file mode 100755
index 00000000000..8d698f5a06a
--- /dev/null
+++ b/tools/perf/scripts/python/bin/net_dropmonitor-report
@@ -0,0 +1,4 @@
+#!/bin/bash
+# description: display a table of dropped frames
+
+perf script -s "$PERF_EXEC_PATH"/scripts/python/net_dropmonitor.py $@
diff --git a/tools/perf/scripts/python/bin/netdev-times-record b/tools/perf/scripts/python/bin/netdev-times-record
new file mode 100644
index 00000000000..558754b840a
--- /dev/null
+++ b/tools/perf/scripts/python/bin/netdev-times-record
@@ -0,0 +1,8 @@
+#!/bin/bash
+perf record -e net:net_dev_xmit -e net:net_dev_queue		\
+		-e net:netif_receive_skb -e net:netif_rx		\
+		-e skb:consume_skb -e skb:kfree_skb			\
+		-e skb:skb_copy_datagram_iovec -e napi:napi_poll	\
+		-e irq:irq_handler_entry -e irq:irq_handler_exit	\
+		-e irq:softirq_entry -e irq:softirq_exit		\
+		-e irq:softirq_raise $@
diff --git a/tools/perf/scripts/python/bin/netdev-times-report b/tools/perf/scripts/python/bin/netdev-times-report
new file mode 100644
index 00000000000..8f759291da8
--- /dev/null
+++ b/tools/perf/scripts/python/bin/netdev-times-report
@@ -0,0 +1,5 @@
+#!/bin/bash
+# description: display a process of packet and processing time
+# args: [tx] [rx] [dev=] [debug]
+
+perf script -s "$PERF_EXEC_PATH"/scripts/python/netdev-times.py $@
diff --git a/tools/perf/scripts/python/bin/sched-migration-record b/tools/perf/scripts/python/bin/sched-migration-record
new file mode 100644
index 00000000000..7493fddbe99
--- /dev/null
+++ b/tools/perf/scripts/python/bin/sched-migration-record
@@ -0,0 +1,2 @@
+#!/bin/bash
+perf record -m 16384 -e sched:sched_wakeup -e sched:sched_wakeup_new -e sched:sched_switch -e sched:sched_migrate_task $@
diff --git a/tools/perf/scripts/python/bin/sched-migration-report b/tools/perf/scripts/python/bin/sched-migration-report
new file mode 100644
index 00000000000..68b037a1849
--- /dev/null
+++ b/tools/perf/scripts/python/bin/sched-migration-report
@@ -0,0 +1,3 @@
+#!/bin/bash
+# description: sched migration overview
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/sched-migration.py
diff --git a/tools/perf/scripts/python/bin/sctop-record b/tools/perf/scripts/python/bin/sctop-record
index 1fc5998b721..4efbfaa7f6a 100644
--- a/tools/perf/scripts/python/bin/sctop-record
+++ b/tools/perf/scripts/python/bin/sctop-record
@@ -1,2 +1,2 @@
 #!/bin/bash
-perf record -a -e raw_syscalls:sys_enter $@
+perf record -e raw_syscalls:sys_enter $@
diff --git a/tools/perf/scripts/python/bin/sctop-report b/tools/perf/scripts/python/bin/sctop-report
index b01c842ae7b..c32db294124 100644
--- a/tools/perf/scripts/python/bin/sctop-report
+++ b/tools/perf/scripts/python/bin/sctop-report
@@ -21,4 +21,4 @@ elif [ "$n_args" -gt 0 ] ; then
     interval=$1
     shift
 fi
-perf trace $@ -s ~/libexec/perf-core/scripts/python/sctop.py $comm $interval
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/sctop.py $comm $interval
diff --git a/tools/perf/scripts/python/bin/syscall-counts-by-pid-record b/tools/perf/scripts/python/bin/syscall-counts-by-pid-record
index 1fc5998b721..4efbfaa7f6a 100644
--- a/tools/perf/scripts/python/bin/syscall-counts-by-pid-record
+++ b/tools/perf/scripts/python/bin/syscall-counts-by-pid-record
@@ -1,2 +1,2 @@
 #!/bin/bash
-perf record -a -e raw_syscalls:sys_enter $@
+perf record -e raw_syscalls:sys_enter $@
diff --git a/tools/perf/scripts/python/bin/syscall-counts-by-pid-report b/tools/perf/scripts/python/bin/syscall-counts-by-pid-report
index 9e9d8ddd72c..16eb8d65c54 100644
--- a/tools/perf/scripts/python/bin/syscall-counts-by-pid-report
+++ b/tools/perf/scripts/python/bin/syscall-counts-by-pid-report
@@ -7,4 +7,4 @@ if [ $# -gt 0 ] ; then
 	shift
     fi
 fi
-perf trace $@ -s ~/libexec/perf-core/scripts/python/syscall-counts-by-pid.py $comm
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/syscall-counts-by-pid.py $comm
diff --git a/tools/perf/scripts/python/bin/syscall-counts-record b/tools/perf/scripts/python/bin/syscall-counts-record
index 1fc5998b721..4efbfaa7f6a 100644
--- a/tools/perf/scripts/python/bin/syscall-counts-record
+++ b/tools/perf/scripts/python/bin/syscall-counts-record
@@ -1,2 +1,2 @@
 #!/bin/bash
-perf record -a -e raw_syscalls:sys_enter $@
+perf record -e raw_syscalls:sys_enter $@
diff --git a/tools/perf/scripts/python/bin/syscall-counts-report b/tools/perf/scripts/python/bin/syscall-counts-report
index dc076b61879..0f0e9d453bb 100644
--- a/tools/perf/scripts/python/bin/syscall-counts-report
+++ b/tools/perf/scripts/python/bin/syscall-counts-report
@@ -7,4 +7,4 @@ if [ $# -gt 0 ] ; then
 	shift
     fi
 fi
-perf trace $@ -s ~/libexec/perf-core/scripts/python/syscall-counts.py $comm
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/syscall-counts.py $comm
diff --git a/tools/perf/scripts/python/check-perf-trace.py b/tools/perf/scripts/python/check-perf-trace.py
index d9f7893e315..4647a7694cf 100644
--- a/tools/perf/scripts/python/check-perf-trace.py
+++ b/tools/perf/scripts/python/check-perf-trace.py
@@ -1,4 +1,4 @@
-# perf trace event handlers, generated by perf trace -g python
+# perf script event handlers, generated by perf script -g python
 # (c) 2010, Tom Zanussi <tzanussi@gmail.com>
 # Licensed under the terms of the GNU GPL License version 2
 #
diff --git a/tools/perf/scripts/python/event_analyzing_sample.py b/tools/perf/scripts/python/event_analyzing_sample.py
new file mode 100644
index 00000000000..163c39fa12d
--- /dev/null
+++ b/tools/perf/scripts/python/event_analyzing_sample.py
@@ -0,0 +1,189 @@
+# event_analyzing_sample.py: general event handler in python
+#
+# Current perf report is already very powerful with the annotation integrated,
+# and this script is not trying to be as powerful as perf report, but
+# providing end user/developer a flexible way to analyze the events other
+# than trace points.
+#
+# The 2 database related functions in this script just show how to gather
+# the basic information, and users can modify and write their own functions
+# according to their specific requirement.
+#
+# The first function "show_general_events" just does a basic grouping for all
+# generic events with the help of sqlite, and the 2nd one "show_pebs_ll" is
+# for a x86 HW PMU event: PEBS with load latency data.
+#
+
+import os
+import sys
+import math
+import struct
+import sqlite3
+
+sys.path.append(os.environ['PERF_EXEC_PATH'] + \
+        '/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+
+from perf_trace_context import *
+from EventClass import *
+
+#
+# If the perf.data has a big number of samples, then the insert operation
+# will be very time consuming (about 10+ minutes for 10000 samples) if the
+# .db database is on disk. Move the .db file to RAM based FS to speedup
+# the handling, which will cut the time down to several seconds.
+#
+con = sqlite3.connect("/dev/shm/perf.db")
+con.isolation_level = None
+
+def trace_begin():
+	print "In trace_begin:\n"
+
+        #
+        # Will create several tables at the start, pebs_ll is for PEBS data with
+        # load latency info, while gen_events is for general event.
+        #
+        con.execute("""
+                create table if not exists gen_events (
+                        name text,
+                        symbol text,
+                        comm text,
+                        dso text
+                );""")
+        con.execute("""
+                create table if not exists pebs_ll (
+                        name text,
+                        symbol text,
+                        comm text,
+                        dso text,
+                        flags integer,
+                        ip integer,
+                        status integer,
+                        dse integer,
+                        dla integer,
+                        lat integer
+                );""")
+
+#
+# Create and insert event object to a database so that user could
+# do more analysis with simple database commands.
+#
+def process_event(param_dict):
+        event_attr = param_dict["attr"]
+        sample     = param_dict["sample"]
+        raw_buf    = param_dict["raw_buf"]
+        comm       = param_dict["comm"]
+        name       = param_dict["ev_name"]
+
+        # Symbol and dso info are not always resolved
+        if (param_dict.has_key("dso")):
+                dso = param_dict["dso"]
+        else:
+                dso = "Unknown_dso"
+
+        if (param_dict.has_key("symbol")):
+                symbol = param_dict["symbol"]
+        else:
+                symbol = "Unknown_symbol"
+
+        # Create the event object and insert it to the right table in database
+        event = create_event(name, comm, dso, symbol, raw_buf)
+        insert_db(event)
+
+def insert_db(event):
+        if event.ev_type == EVTYPE_GENERIC:
+                con.execute("insert into gen_events values(?, ?, ?, ?)",
+                                (event.name, event.symbol, event.comm, event.dso))
+        elif event.ev_type == EVTYPE_PEBS_LL:
+                event.ip &= 0x7fffffffffffffff
+                event.dla &= 0x7fffffffffffffff
+                con.execute("insert into pebs_ll values (?, ?, ?, ?, ?, ?, ?, ?, ?, ?)",
+                        (event.name, event.symbol, event.comm, event.dso, event.flags,
+                                event.ip, event.status, event.dse, event.dla, event.lat))
+
+def trace_end():
+	print "In trace_end:\n"
+        # We show the basic info for the 2 type of event classes
+        show_general_events()
+        show_pebs_ll()
+        con.close()
+
+#
+# As the event number may be very big, so we can't use linear way
+# to show the histogram in real number, but use a log2 algorithm.
+#
+
+def num2sym(num):
+        # Each number will have at least one '#'
+        snum = '#' * (int)(math.log(num, 2) + 1)
+        return snum
+
+def show_general_events():
+
+        # Check the total record number in the table
+        count = con.execute("select count(*) from gen_events")
+        for t in count:
+                print "There is %d records in gen_events table" % t[0]
+                if t[0] == 0:
+                        return
+
+        print "Statistics about the general events grouped by thread/symbol/dso: \n"
+
+         # Group by thread
+        commq = con.execute("select comm, count(comm) from gen_events group by comm order by -count(comm)")
+        print "\n%16s %8s %16s\n%s" % ("comm", "number", "histogram", "="*42)
+        for row in commq:
+             print "%16s %8d     %s" % (row[0], row[1], num2sym(row[1]))
+
+        # Group by symbol
+        print "\n%32s %8s %16s\n%s" % ("symbol", "number", "histogram", "="*58)
+        symbolq = con.execute("select symbol, count(symbol) from gen_events group by symbol order by -count(symbol)")
+        for row in symbolq:
+             print "%32s %8d     %s" % (row[0], row[1], num2sym(row[1]))
+
+        # Group by dso
+        print "\n%40s %8s %16s\n%s" % ("dso", "number", "histogram", "="*74)
+        dsoq = con.execute("select dso, count(dso) from gen_events group by dso order by -count(dso)")
+        for row in dsoq:
+             print "%40s %8d     %s" % (row[0], row[1], num2sym(row[1]))
+
+#
+# This function just shows the basic info, and we could do more with the
+# data in the tables, like checking the function parameters when some
+# big latency events happen.
+#
+def show_pebs_ll():
+
+        count = con.execute("select count(*) from pebs_ll")
+        for t in count:
+                print "There is %d records in pebs_ll table" % t[0]
+                if t[0] == 0:
+                        return
+
+        print "Statistics about the PEBS Load Latency events grouped by thread/symbol/dse/latency: \n"
+
+        # Group by thread
+        commq = con.execute("select comm, count(comm) from pebs_ll group by comm order by -count(comm)")
+        print "\n%16s %8s %16s\n%s" % ("comm", "number", "histogram", "="*42)
+        for row in commq:
+             print "%16s %8d     %s" % (row[0], row[1], num2sym(row[1]))
+
+        # Group by symbol
+        print "\n%32s %8s %16s\n%s" % ("symbol", "number", "histogram", "="*58)
+        symbolq = con.execute("select symbol, count(symbol) from pebs_ll group by symbol order by -count(symbol)")
+        for row in symbolq:
+             print "%32s %8d     %s" % (row[0], row[1], num2sym(row[1]))
+
+        # Group by dse
+        dseq = con.execute("select dse, count(dse) from pebs_ll group by dse order by -count(dse)")
+        print "\n%32s %8s %16s\n%s" % ("dse", "number", "histogram", "="*58)
+        for row in dseq:
+             print "%32s %8d     %s" % (row[0], row[1], num2sym(row[1]))
+
+        # Group by latency
+        latq = con.execute("select lat, count(lat) from pebs_ll group by lat order by lat")
+        print "\n%32s %8s %16s\n%s" % ("latency", "number", "histogram", "="*58)
+        for row in latq:
+             print "%32s %8d     %s" % (row[0], row[1], num2sym(row[1]))
+
+def trace_unhandled(event_name, context, event_fields_dict):
+		print ' '.join(['%s=%s'%(k,str(v))for k,v in sorted(event_fields_dict.items())])
diff --git a/tools/perf/scripts/python/failed-syscalls-by-pid.py b/tools/perf/scripts/python/failed-syscalls-by-pid.py
index 0ca02278fe6..85805fac411 100644
--- a/tools/perf/scripts/python/failed-syscalls-by-pid.py
+++ b/tools/perf/scripts/python/failed-syscalls-by-pid.py
@@ -13,21 +13,26 @@ sys.path.append(os.environ['PERF_EXEC_PATH'] + \
 
 from perf_trace_context import *
 from Core import *
+from Util import *
 
-usage = "perf trace -s syscall-counts-by-pid.py [comm]\n";
+usage = "perf script -s syscall-counts-by-pid.py [comm|pid]\n";
 
 for_comm = None
+for_pid = None
 
 if len(sys.argv) > 2:
 	sys.exit(usage)
 
 if len(sys.argv) > 1:
-	for_comm = sys.argv[1]
+	try:
+		for_pid = int(sys.argv[1])
+	except:
+		for_comm = sys.argv[1]
 
 syscalls = autodict()
 
 def trace_begin():
-	pass
+	print "Press control+C to stop and show the summary"
 
 def trace_end():
 	print_error_totals()
@@ -35,9 +40,9 @@ def trace_end():
 def raw_syscalls__sys_exit(event_name, context, common_cpu,
 	common_secs, common_nsecs, common_pid, common_comm,
 	id, ret):
-	if for_comm is not None:
-		if common_comm != for_comm:
-			return
+	if (for_comm and common_comm != for_comm) or \
+	   (for_pid  and common_pid  != for_pid ):
+		return
 
 	if ret < 0:
 		try:
@@ -62,7 +67,7 @@ def print_error_totals():
 		    print "\n%s [%d]\n" % (comm, pid),
 		    id_keys = syscalls[comm][pid].keys()
 		    for id in id_keys:
-			    print "  syscall: %-16d\n" % (id),
+			    print "  syscall: %-16s\n" % syscall_name(id),
 			    ret_keys = syscalls[comm][pid][id].keys()
 			    for ret, val in sorted(syscalls[comm][pid][id].iteritems(), key = lambda(k, v): (v, k),  reverse = True):
-				    print "    err = %-20d  %10d\n" % (ret, val),
+				    print "    err = %-20s  %10d\n" % (strerror(ret), val),
diff --git a/tools/perf/scripts/python/futex-contention.py b/tools/perf/scripts/python/futex-contention.py
new file mode 100644
index 00000000000..11e70a388d4
--- /dev/null
+++ b/tools/perf/scripts/python/futex-contention.py
@@ -0,0 +1,50 @@
+# futex contention
+# (c) 2010, Arnaldo Carvalho de Melo <acme@redhat.com>
+# Licensed under the terms of the GNU GPL License version 2
+#
+# Translation of:
+#
+# http://sourceware.org/systemtap/wiki/WSFutexContention
+#
+# to perf python scripting.
+#
+# Measures futex contention
+
+import os, sys
+sys.path.append(os.environ['PERF_EXEC_PATH'] + '/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+from Util import *
+
+process_names = {}
+thread_thislock = {}
+thread_blocktime = {}
+
+lock_waits = {} # long-lived stats on (tid,lock) blockage elapsed time
+process_names = {} # long-lived pid-to-execname mapping
+
+def syscalls__sys_enter_futex(event, ctxt, cpu, s, ns, tid, comm,
+			      nr, uaddr, op, val, utime, uaddr2, val3):
+	cmd = op & FUTEX_CMD_MASK
+	if cmd != FUTEX_WAIT:
+		return # we don't care about originators of WAKE events
+
+	process_names[tid] = comm
+	thread_thislock[tid] = uaddr
+	thread_blocktime[tid] = nsecs(s, ns)
+
+def syscalls__sys_exit_futex(event, ctxt, cpu, s, ns, tid, comm,
+			     nr, ret):
+	if thread_blocktime.has_key(tid):
+		elapsed = nsecs(s, ns) - thread_blocktime[tid]
+		add_stats(lock_waits, (tid, thread_thislock[tid]), elapsed)
+		del thread_blocktime[tid]
+		del thread_thislock[tid]
+
+def trace_begin():
+	print "Press control+C to stop and show the summary"
+
+def trace_end():
+	for (tid, lock) in lock_waits:
+		min, max, avg, count = lock_waits[tid, lock]
+		print "%s[%d] lock %x contended %d times, %d avg ns" % \
+		      (process_names[tid], tid, lock, count, avg)
+
diff --git a/tools/perf/scripts/python/net_dropmonitor.py b/tools/perf/scripts/python/net_dropmonitor.py
new file mode 100755
index 00000000000..b5740599aab
--- /dev/null
+++ b/tools/perf/scripts/python/net_dropmonitor.py
@@ -0,0 +1,75 @@
+# Monitor the system for dropped packets and proudce a report of drop locations and counts
+
+import os
+import sys
+
+sys.path.append(os.environ['PERF_EXEC_PATH'] + \
+		'/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+
+from perf_trace_context import *
+from Core import *
+from Util import *
+
+drop_log = {}
+kallsyms = []
+
+def get_kallsyms_table():
+	global kallsyms
+
+	try:
+		f = open("/proc/kallsyms", "r")
+	except:
+		return
+
+	for line in f:
+		loc = int(line.split()[0], 16)
+		name = line.split()[2]
+		kallsyms.append((loc, name))
+	kallsyms.sort()
+
+def get_sym(sloc):
+	loc = int(sloc)
+
+	# Invariant: kallsyms[i][0] <= loc for all 0 <= i <= start
+	#            kallsyms[i][0] > loc for all end <= i < len(kallsyms)
+	start, end = -1, len(kallsyms)
+	while end != start + 1:
+		pivot = (start + end) // 2
+		if loc < kallsyms[pivot][0]:
+			end = pivot
+		else:
+			start = pivot
+
+	# Now (start == -1 or kallsyms[start][0] <= loc)
+	# and (start == len(kallsyms) - 1 or loc < kallsyms[start + 1][0])
+	if start >= 0:
+		symloc, name = kallsyms[start]
+		return (name, loc - symloc)
+	else:
+		return (None, 0)
+
+def print_drop_table():
+	print "%25s %25s %25s" % ("LOCATION", "OFFSET", "COUNT")
+	for i in drop_log.keys():
+		(sym, off) = get_sym(i)
+		if sym == None:
+			sym = i
+		print "%25s %25s %25s" % (sym, off, drop_log[i])
+
+
+def trace_begin():
+	print "Starting trace (Ctrl-C to dump results)"
+
+def trace_end():
+	print "Gathering kallsyms data"
+	get_kallsyms_table()
+	print_drop_table()
+
+# called from perf, when it finds a correspoinding event
+def skb__kfree_skb(name, context, cpu, sec, nsec, pid, comm,
+		   skbaddr, location, protocol):
+	slocation = str(location)
+	try:
+		drop_log[slocation] = drop_log[slocation] + 1
+	except:
+		drop_log[slocation] = 1
diff --git a/tools/perf/scripts/python/netdev-times.py b/tools/perf/scripts/python/netdev-times.py
new file mode 100644
index 00000000000..9aa0a32972e
--- /dev/null
+++ b/tools/perf/scripts/python/netdev-times.py
@@ -0,0 +1,464 @@
+# Display a process of packets and processed time.
+# It helps us to investigate networking or network device.
+#
+# options
+# tx: show only tx chart
+# rx: show only rx chart
+# dev=: show only thing related to specified device
+# debug: work with debug mode. It shows buffer status.
+
+import os
+import sys
+
+sys.path.append(os.environ['PERF_EXEC_PATH'] + \
+	'/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+
+from perf_trace_context import *
+from Core import *
+from Util import *
+
+all_event_list = []; # insert all tracepoint event related with this script
+irq_dic = {}; # key is cpu and value is a list which stacks irqs
+              # which raise NET_RX softirq
+net_rx_dic = {}; # key is cpu and value include time of NET_RX softirq-entry
+		 # and a list which stacks receive
+receive_hunk_list = []; # a list which include a sequence of receive events
+rx_skb_list = []; # received packet list for matching
+		       # skb_copy_datagram_iovec
+
+buffer_budget = 65536; # the budget of rx_skb_list, tx_queue_list and
+		       # tx_xmit_list
+of_count_rx_skb_list = 0; # overflow count
+
+tx_queue_list = []; # list of packets which pass through dev_queue_xmit
+of_count_tx_queue_list = 0; # overflow count
+
+tx_xmit_list = [];  # list of packets which pass through dev_hard_start_xmit
+of_count_tx_xmit_list = 0; # overflow count
+
+tx_free_list = [];  # list of packets which is freed
+
+# options
+show_tx = 0;
+show_rx = 0;
+dev = 0; # store a name of device specified by option "dev="
+debug = 0;
+
+# indices of event_info tuple
+EINFO_IDX_NAME=   0
+EINFO_IDX_CONTEXT=1
+EINFO_IDX_CPU=    2
+EINFO_IDX_TIME=   3
+EINFO_IDX_PID=    4
+EINFO_IDX_COMM=   5
+
+# Calculate a time interval(msec) from src(nsec) to dst(nsec)
+def diff_msec(src, dst):
+	return (dst - src) / 1000000.0
+
+# Display a process of transmitting a packet
+def print_transmit(hunk):
+	if dev != 0 and hunk['dev'].find(dev) < 0:
+		return
+	print "%7s %5d %6d.%06dsec %12.3fmsec      %12.3fmsec" % \
+		(hunk['dev'], hunk['len'],
+		nsecs_secs(hunk['queue_t']),
+		nsecs_nsecs(hunk['queue_t'])/1000,
+		diff_msec(hunk['queue_t'], hunk['xmit_t']),
+		diff_msec(hunk['xmit_t'], hunk['free_t']))
+
+# Format for displaying rx packet processing
+PF_IRQ_ENTRY= "  irq_entry(+%.3fmsec irq=%d:%s)"
+PF_SOFT_ENTRY="  softirq_entry(+%.3fmsec)"
+PF_NAPI_POLL= "  napi_poll_exit(+%.3fmsec %s)"
+PF_JOINT=     "         |"
+PF_WJOINT=    "         |            |"
+PF_NET_RECV=  "         |---netif_receive_skb(+%.3fmsec skb=%x len=%d)"
+PF_NET_RX=    "         |---netif_rx(+%.3fmsec skb=%x)"
+PF_CPY_DGRAM= "         |      skb_copy_datagram_iovec(+%.3fmsec %d:%s)"
+PF_KFREE_SKB= "         |      kfree_skb(+%.3fmsec location=%x)"
+PF_CONS_SKB=  "         |      consume_skb(+%.3fmsec)"
+
+# Display a process of received packets and interrputs associated with
+# a NET_RX softirq
+def print_receive(hunk):
+	show_hunk = 0
+	irq_list = hunk['irq_list']
+	cpu = irq_list[0]['cpu']
+	base_t = irq_list[0]['irq_ent_t']
+	# check if this hunk should be showed
+	if dev != 0:
+		for i in range(len(irq_list)):
+			if irq_list[i]['name'].find(dev) >= 0:
+				show_hunk = 1
+				break
+	else:
+		show_hunk = 1
+	if show_hunk == 0:
+		return
+
+	print "%d.%06dsec cpu=%d" % \
+		(nsecs_secs(base_t), nsecs_nsecs(base_t)/1000, cpu)
+	for i in range(len(irq_list)):
+		print PF_IRQ_ENTRY % \
+			(diff_msec(base_t, irq_list[i]['irq_ent_t']),
+			irq_list[i]['irq'], irq_list[i]['name'])
+		print PF_JOINT
+		irq_event_list = irq_list[i]['event_list']
+		for j in range(len(irq_event_list)):
+			irq_event = irq_event_list[j]
+			if irq_event['event'] == 'netif_rx':
+				print PF_NET_RX % \
+					(diff_msec(base_t, irq_event['time']),
+					irq_event['skbaddr'])
+				print PF_JOINT
+	print PF_SOFT_ENTRY % \
+		diff_msec(base_t, hunk['sirq_ent_t'])
+	print PF_JOINT
+	event_list = hunk['event_list']
+	for i in range(len(event_list)):
+		event = event_list[i]
+		if event['event_name'] == 'napi_poll':
+			print PF_NAPI_POLL % \
+			    (diff_msec(base_t, event['event_t']), event['dev'])
+			if i == len(event_list) - 1:
+				print ""
+			else:
+				print PF_JOINT
+		else:
+			print PF_NET_RECV % \
+			    (diff_msec(base_t, event['event_t']), event['skbaddr'],
+				event['len'])
+			if 'comm' in event.keys():
+				print PF_WJOINT
+				print PF_CPY_DGRAM % \
+					(diff_msec(base_t, event['comm_t']),
+					event['pid'], event['comm'])
+			elif 'handle' in event.keys():
+				print PF_WJOINT
+				if event['handle'] == "kfree_skb":
+					print PF_KFREE_SKB % \
+						(diff_msec(base_t,
+						event['comm_t']),
+						event['location'])
+				elif event['handle'] == "consume_skb":
+					print PF_CONS_SKB % \
+						diff_msec(base_t,
+							event['comm_t'])
+			print PF_JOINT
+
+def trace_begin():
+	global show_tx
+	global show_rx
+	global dev
+	global debug
+
+	for i in range(len(sys.argv)):
+		if i == 0:
+			continue
+		arg = sys.argv[i]
+		if arg == 'tx':
+			show_tx = 1
+		elif arg =='rx':
+			show_rx = 1
+		elif arg.find('dev=',0, 4) >= 0:
+			dev = arg[4:]
+		elif arg == 'debug':
+			debug = 1
+	if show_tx == 0  and show_rx == 0:
+		show_tx = 1
+		show_rx = 1
+
+def trace_end():
+	# order all events in time
+	all_event_list.sort(lambda a,b :cmp(a[EINFO_IDX_TIME],
+					    b[EINFO_IDX_TIME]))
+	# process all events
+	for i in range(len(all_event_list)):
+		event_info = all_event_list[i]
+		name = event_info[EINFO_IDX_NAME]
+		if name == 'irq__softirq_exit':
+			handle_irq_softirq_exit(event_info)
+		elif name == 'irq__softirq_entry':
+			handle_irq_softirq_entry(event_info)
+		elif name == 'irq__softirq_raise':
+			handle_irq_softirq_raise(event_info)
+		elif name == 'irq__irq_handler_entry':
+			handle_irq_handler_entry(event_info)
+		elif name == 'irq__irq_handler_exit':
+			handle_irq_handler_exit(event_info)
+		elif name == 'napi__napi_poll':
+			handle_napi_poll(event_info)
+		elif name == 'net__netif_receive_skb':
+			handle_netif_receive_skb(event_info)
+		elif name == 'net__netif_rx':
+			handle_netif_rx(event_info)
+		elif name == 'skb__skb_copy_datagram_iovec':
+			handle_skb_copy_datagram_iovec(event_info)
+		elif name == 'net__net_dev_queue':
+			handle_net_dev_queue(event_info)
+		elif name == 'net__net_dev_xmit':
+			handle_net_dev_xmit(event_info)
+		elif name == 'skb__kfree_skb':
+			handle_kfree_skb(event_info)
+		elif name == 'skb__consume_skb':
+			handle_consume_skb(event_info)
+	# display receive hunks
+	if show_rx:
+		for i in range(len(receive_hunk_list)):
+			print_receive(receive_hunk_list[i])
+	# display transmit hunks
+	if show_tx:
+		print "   dev    len      Qdisc        " \
+			"       netdevice             free"
+		for i in range(len(tx_free_list)):
+			print_transmit(tx_free_list[i])
+	if debug:
+		print "debug buffer status"
+		print "----------------------------"
+		print "xmit Qdisc:remain:%d overflow:%d" % \
+			(len(tx_queue_list), of_count_tx_queue_list)
+		print "xmit netdevice:remain:%d overflow:%d" % \
+			(len(tx_xmit_list), of_count_tx_xmit_list)
+		print "receive:remain:%d overflow:%d" % \
+			(len(rx_skb_list), of_count_rx_skb_list)
+
+# called from perf, when it finds a correspoinding event
+def irq__softirq_entry(name, context, cpu, sec, nsec, pid, comm, vec):
+	if symbol_str("irq__softirq_entry", "vec", vec) != "NET_RX":
+		return
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, vec)
+	all_event_list.append(event_info)
+
+def irq__softirq_exit(name, context, cpu, sec, nsec, pid, comm, vec):
+	if symbol_str("irq__softirq_entry", "vec", vec) != "NET_RX":
+		return
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, vec)
+	all_event_list.append(event_info)
+
+def irq__softirq_raise(name, context, cpu, sec, nsec, pid, comm, vec):
+	if symbol_str("irq__softirq_entry", "vec", vec) != "NET_RX":
+		return
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, vec)
+	all_event_list.append(event_info)
+
+def irq__irq_handler_entry(name, context, cpu, sec, nsec, pid, comm,
+			irq, irq_name):
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
+			irq, irq_name)
+	all_event_list.append(event_info)
+
+def irq__irq_handler_exit(name, context, cpu, sec, nsec, pid, comm, irq, ret):
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, irq, ret)
+	all_event_list.append(event_info)
+
+def napi__napi_poll(name, context, cpu, sec, nsec, pid, comm, napi, dev_name):
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
+			napi, dev_name)
+	all_event_list.append(event_info)
+
+def net__netif_receive_skb(name, context, cpu, sec, nsec, pid, comm, skbaddr,
+			skblen, dev_name):
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
+			skbaddr, skblen, dev_name)
+	all_event_list.append(event_info)
+
+def net__netif_rx(name, context, cpu, sec, nsec, pid, comm, skbaddr,
+			skblen, dev_name):
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
+			skbaddr, skblen, dev_name)
+	all_event_list.append(event_info)
+
+def net__net_dev_queue(name, context, cpu, sec, nsec, pid, comm,
+			skbaddr, skblen, dev_name):
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
+			skbaddr, skblen, dev_name)
+	all_event_list.append(event_info)
+
+def net__net_dev_xmit(name, context, cpu, sec, nsec, pid, comm,
+			skbaddr, skblen, rc, dev_name):
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
+			skbaddr, skblen, rc ,dev_name)
+	all_event_list.append(event_info)
+
+def skb__kfree_skb(name, context, cpu, sec, nsec, pid, comm,
+			skbaddr, protocol, location):
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
+			skbaddr, protocol, location)
+	all_event_list.append(event_info)
+
+def skb__consume_skb(name, context, cpu, sec, nsec, pid, comm, skbaddr):
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
+			skbaddr)
+	all_event_list.append(event_info)
+
+def skb__skb_copy_datagram_iovec(name, context, cpu, sec, nsec, pid, comm,
+	skbaddr, skblen):
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
+			skbaddr, skblen)
+	all_event_list.append(event_info)
+
+def handle_irq_handler_entry(event_info):
+	(name, context, cpu, time, pid, comm, irq, irq_name) = event_info
+	if cpu not in irq_dic.keys():
+		irq_dic[cpu] = []
+	irq_record = {'irq':irq, 'name':irq_name, 'cpu':cpu, 'irq_ent_t':time}
+	irq_dic[cpu].append(irq_record)
+
+def handle_irq_handler_exit(event_info):
+	(name, context, cpu, time, pid, comm, irq, ret) = event_info
+	if cpu not in irq_dic.keys():
+		return
+	irq_record = irq_dic[cpu].pop()
+	if irq != irq_record['irq']:
+		return
+	irq_record.update({'irq_ext_t':time})
+	# if an irq doesn't include NET_RX softirq, drop.
+	if 'event_list' in irq_record.keys():
+		irq_dic[cpu].append(irq_record)
+
+def handle_irq_softirq_raise(event_info):
+	(name, context, cpu, time, pid, comm, vec) = event_info
+	if cpu not in irq_dic.keys() \
+	or len(irq_dic[cpu]) == 0:
+		return
+	irq_record = irq_dic[cpu].pop()
+	if 'event_list' in irq_record.keys():
+		irq_event_list = irq_record['event_list']
+	else:
+		irq_event_list = []
+	irq_event_list.append({'time':time, 'event':'sirq_raise'})
+	irq_record.update({'event_list':irq_event_list})
+	irq_dic[cpu].append(irq_record)
+
+def handle_irq_softirq_entry(event_info):
+	(name, context, cpu, time, pid, comm, vec) = event_info
+	net_rx_dic[cpu] = {'sirq_ent_t':time, 'event_list':[]}
+
+def handle_irq_softirq_exit(event_info):
+	(name, context, cpu, time, pid, comm, vec) = event_info
+	irq_list = []
+	event_list = 0
+	if cpu in irq_dic.keys():
+		irq_list = irq_dic[cpu]
+		del irq_dic[cpu]
+	if cpu in net_rx_dic.keys():
+		sirq_ent_t = net_rx_dic[cpu]['sirq_ent_t']
+		event_list = net_rx_dic[cpu]['event_list']
+		del net_rx_dic[cpu]
+	if irq_list == [] or event_list == 0:
+		return
+	rec_data = {'sirq_ent_t':sirq_ent_t, 'sirq_ext_t':time,
+		    'irq_list':irq_list, 'event_list':event_list}
+	# merge information realted to a NET_RX softirq
+	receive_hunk_list.append(rec_data)
+
+def handle_napi_poll(event_info):
+	(name, context, cpu, time, pid, comm, napi, dev_name) = event_info
+	if cpu in net_rx_dic.keys():
+		event_list = net_rx_dic[cpu]['event_list']
+		rec_data = {'event_name':'napi_poll',
+				'dev':dev_name, 'event_t':time}
+		event_list.append(rec_data)
+
+def handle_netif_rx(event_info):
+	(name, context, cpu, time, pid, comm,
+		skbaddr, skblen, dev_name) = event_info
+	if cpu not in irq_dic.keys() \
+	or len(irq_dic[cpu]) == 0:
+		return
+	irq_record = irq_dic[cpu].pop()
+	if 'event_list' in irq_record.keys():
+		irq_event_list = irq_record['event_list']
+	else:
+		irq_event_list = []
+	irq_event_list.append({'time':time, 'event':'netif_rx',
+		'skbaddr':skbaddr, 'skblen':skblen, 'dev_name':dev_name})
+	irq_record.update({'event_list':irq_event_list})
+	irq_dic[cpu].append(irq_record)
+
+def handle_netif_receive_skb(event_info):
+	global of_count_rx_skb_list
+
+	(name, context, cpu, time, pid, comm,
+		skbaddr, skblen, dev_name) = event_info
+	if cpu in net_rx_dic.keys():
+		rec_data = {'event_name':'netif_receive_skb',
+			    'event_t':time, 'skbaddr':skbaddr, 'len':skblen}
+		event_list = net_rx_dic[cpu]['event_list']
+		event_list.append(rec_data)
+		rx_skb_list.insert(0, rec_data)
+		if len(rx_skb_list) > buffer_budget:
+			rx_skb_list.pop()
+			of_count_rx_skb_list += 1
+
+def handle_net_dev_queue(event_info):
+	global of_count_tx_queue_list
+
+	(name, context, cpu, time, pid, comm,
+		skbaddr, skblen, dev_name) = event_info
+	skb = {'dev':dev_name, 'skbaddr':skbaddr, 'len':skblen, 'queue_t':time}
+	tx_queue_list.insert(0, skb)
+	if len(tx_queue_list) > buffer_budget:
+		tx_queue_list.pop()
+		of_count_tx_queue_list += 1
+
+def handle_net_dev_xmit(event_info):
+	global of_count_tx_xmit_list
+
+	(name, context, cpu, time, pid, comm,
+		skbaddr, skblen, rc, dev_name) = event_info
+	if rc == 0: # NETDEV_TX_OK
+		for i in range(len(tx_queue_list)):
+			skb = tx_queue_list[i]
+			if skb['skbaddr'] == skbaddr:
+				skb['xmit_t'] = time
+				tx_xmit_list.insert(0, skb)
+				del tx_queue_list[i]
+				if len(tx_xmit_list) > buffer_budget:
+					tx_xmit_list.pop()
+					of_count_tx_xmit_list += 1
+				return
+
+def handle_kfree_skb(event_info):
+	(name, context, cpu, time, pid, comm,
+		skbaddr, protocol, location) = event_info
+	for i in range(len(tx_queue_list)):
+		skb = tx_queue_list[i]
+		if skb['skbaddr'] == skbaddr:
+			del tx_queue_list[i]
+			return
+	for i in range(len(tx_xmit_list)):
+		skb = tx_xmit_list[i]
+		if skb['skbaddr'] == skbaddr:
+			skb['free_t'] = time
+			tx_free_list.append(skb)
+			del tx_xmit_list[i]
+			return
+	for i in range(len(rx_skb_list)):
+		rec_data = rx_skb_list[i]
+		if rec_data['skbaddr'] == skbaddr:
+			rec_data.update({'handle':"kfree_skb",
+					'comm':comm, 'pid':pid, 'comm_t':time})
+			del rx_skb_list[i]
+			return
+
+def handle_consume_skb(event_info):
+	(name, context, cpu, time, pid, comm, skbaddr) = event_info
+	for i in range(len(tx_xmit_list)):
+		skb = tx_xmit_list[i]
+		if skb['skbaddr'] == skbaddr:
+			skb['free_t'] = time
+			tx_free_list.append(skb)
+			del tx_xmit_list[i]
+			return
+
+def handle_skb_copy_datagram_iovec(event_info):
+	(name, context, cpu, time, pid, comm, skbaddr, skblen) = event_info
+	for i in range(len(rx_skb_list)):
+		rec_data = rx_skb_list[i]
+		if skbaddr == rec_data['skbaddr']:
+			rec_data.update({'handle':"skb_copy_datagram_iovec",
+					'comm':comm, 'pid':pid, 'comm_t':time})
+			del rx_skb_list[i]
+			return
diff --git a/tools/perf/scripts/python/sched-migration.py b/tools/perf/scripts/python/sched-migration.py
new file mode 100644
index 00000000000..74d55ec08ae
--- /dev/null
+++ b/tools/perf/scripts/python/sched-migration.py
@@ -0,0 +1,461 @@
+#!/usr/bin/python
+#
+# Cpu task migration overview toy
+#
+# Copyright (C) 2010 Frederic Weisbecker <fweisbec@gmail.com>
+#
+# perf script event handlers have been generated by perf script -g python
+#
+# This software is distributed under the terms of the GNU General
+# Public License ("GPL") version 2 as published by the Free Software
+# Foundation.
+
+
+import os
+import sys
+
+from collections import defaultdict
+from UserList import UserList
+
+sys.path.append(os.environ['PERF_EXEC_PATH'] + \
+	'/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+sys.path.append('scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+
+from perf_trace_context import *
+from Core import *
+from SchedGui import *
+
+
+threads = { 0 : "idle"}
+
+def thread_name(pid):
+	return "%s:%d" % (threads[pid], pid)
+
+class RunqueueEventUnknown:
+	@staticmethod
+	def color():
+		return None
+
+	def __repr__(self):
+		return "unknown"
+
+class RunqueueEventSleep:
+	@staticmethod
+	def color():
+		return (0, 0, 0xff)
+
+	def __init__(self, sleeper):
+		self.sleeper = sleeper
+
+	def __repr__(self):
+		return "%s gone to sleep" % thread_name(self.sleeper)
+
+class RunqueueEventWakeup:
+	@staticmethod
+	def color():
+		return (0xff, 0xff, 0)
+
+	def __init__(self, wakee):
+		self.wakee = wakee
+
+	def __repr__(self):
+		return "%s woke up" % thread_name(self.wakee)
+
+class RunqueueEventFork:
+	@staticmethod
+	def color():
+		return (0, 0xff, 0)
+
+	def __init__(self, child):
+		self.child = child
+
+	def __repr__(self):
+		return "new forked task %s" % thread_name(self.child)
+
+class RunqueueMigrateIn:
+	@staticmethod
+	def color():
+		return (0, 0xf0, 0xff)
+
+	def __init__(self, new):
+		self.new = new
+
+	def __repr__(self):
+		return "task migrated in %s" % thread_name(self.new)
+
+class RunqueueMigrateOut:
+	@staticmethod
+	def color():
+		return (0xff, 0, 0xff)
+
+	def __init__(self, old):
+		self.old = old
+
+	def __repr__(self):
+		return "task migrated out %s" % thread_name(self.old)
+
+class RunqueueSnapshot:
+	def __init__(self, tasks = [0], event = RunqueueEventUnknown()):
+		self.tasks = tuple(tasks)
+		self.event = event
+
+	def sched_switch(self, prev, prev_state, next):
+		event = RunqueueEventUnknown()
+
+		if taskState(prev_state) == "R" and next in self.tasks \
+			and prev in self.tasks:
+			return self
+
+		if taskState(prev_state) != "R":
+			event = RunqueueEventSleep(prev)
+
+		next_tasks = list(self.tasks[:])
+		if prev in self.tasks:
+			if taskState(prev_state) != "R":
+				next_tasks.remove(prev)
+		elif taskState(prev_state) == "R":
+			next_tasks.append(prev)
+
+		if next not in next_tasks:
+			next_tasks.append(next)
+
+		return RunqueueSnapshot(next_tasks, event)
+
+	def migrate_out(self, old):
+		if old not in self.tasks:
+			return self
+		next_tasks = [task for task in self.tasks if task != old]
+
+		return RunqueueSnapshot(next_tasks, RunqueueMigrateOut(old))
+
+	def __migrate_in(self, new, event):
+		if new in self.tasks:
+			self.event = event
+			return self
+		next_tasks = self.tasks[:] + tuple([new])
+
+		return RunqueueSnapshot(next_tasks, event)
+
+	def migrate_in(self, new):
+		return self.__migrate_in(new, RunqueueMigrateIn(new))
+
+	def wake_up(self, new):
+		return self.__migrate_in(new, RunqueueEventWakeup(new))
+
+	def wake_up_new(self, new):
+		return self.__migrate_in(new, RunqueueEventFork(new))
+
+	def load(self):
+		""" Provide the number of tasks on the runqueue.
+		    Don't count idle"""
+		return len(self.tasks) - 1
+
+	def __repr__(self):
+		ret = self.tasks.__repr__()
+		ret += self.origin_tostring()
+
+		return ret
+
+class TimeSlice:
+	def __init__(self, start, prev):
+		self.start = start
+		self.prev = prev
+		self.end = start
+		# cpus that triggered the event
+		self.event_cpus = []
+		if prev is not None:
+			self.total_load = prev.total_load
+			self.rqs = prev.rqs.copy()
+		else:
+			self.rqs = defaultdict(RunqueueSnapshot)
+			self.total_load = 0
+
+	def __update_total_load(self, old_rq, new_rq):
+		diff = new_rq.load() - old_rq.load()
+		self.total_load += diff
+
+	def sched_switch(self, ts_list, prev, prev_state, next, cpu):
+		old_rq = self.prev.rqs[cpu]
+		new_rq = old_rq.sched_switch(prev, prev_state, next)
+
+		if old_rq is new_rq:
+			return
+
+		self.rqs[cpu] = new_rq
+		self.__update_total_load(old_rq, new_rq)
+		ts_list.append(self)
+		self.event_cpus = [cpu]
+
+	def migrate(self, ts_list, new, old_cpu, new_cpu):
+		if old_cpu == new_cpu:
+			return
+		old_rq = self.prev.rqs[old_cpu]
+		out_rq = old_rq.migrate_out(new)
+		self.rqs[old_cpu] = out_rq
+		self.__update_total_load(old_rq, out_rq)
+
+		new_rq = self.prev.rqs[new_cpu]
+		in_rq = new_rq.migrate_in(new)
+		self.rqs[new_cpu] = in_rq
+		self.__update_total_load(new_rq, in_rq)
+
+		ts_list.append(self)
+
+		if old_rq is not out_rq:
+			self.event_cpus.append(old_cpu)
+		self.event_cpus.append(new_cpu)
+
+	def wake_up(self, ts_list, pid, cpu, fork):
+		old_rq = self.prev.rqs[cpu]
+		if fork:
+			new_rq = old_rq.wake_up_new(pid)
+		else:
+			new_rq = old_rq.wake_up(pid)
+
+		if new_rq is old_rq:
+			return
+		self.rqs[cpu] = new_rq
+		self.__update_total_load(old_rq, new_rq)
+		ts_list.append(self)
+		self.event_cpus = [cpu]
+
+	def next(self, t):
+		self.end = t
+		return TimeSlice(t, self)
+
+class TimeSliceList(UserList):
+	def __init__(self, arg = []):
+		self.data = arg
+
+	def get_time_slice(self, ts):
+		if len(self.data) == 0:
+			slice = TimeSlice(ts, TimeSlice(-1, None))
+		else:
+			slice = self.data[-1].next(ts)
+		return slice
+
+	def find_time_slice(self, ts):
+		start = 0
+		end = len(self.data)
+		found = -1
+		searching = True
+		while searching:
+			if start == end or start == end - 1:
+				searching = False
+
+			i = (end + start) / 2
+			if self.data[i].start <= ts and self.data[i].end >= ts:
+				found = i
+				end = i
+				continue
+
+			if self.data[i].end < ts:
+				start = i
+
+			elif self.data[i].start > ts:
+				end = i
+
+		return found
+
+	def set_root_win(self, win):
+		self.root_win = win
+
+	def mouse_down(self, cpu, t):
+		idx = self.find_time_slice(t)
+		if idx == -1:
+			return
+
+		ts = self[idx]
+		rq = ts.rqs[cpu]
+		raw = "CPU: %d\n" % cpu
+		raw += "Last event : %s\n" % rq.event.__repr__()
+		raw += "Timestamp : %d.%06d\n" % (ts.start / (10 ** 9), (ts.start % (10 ** 9)) / 1000)
+		raw += "Duration : %6d us\n" % ((ts.end - ts.start) / (10 ** 6))
+		raw += "Load = %d\n" % rq.load()
+		for t in rq.tasks:
+			raw += "%s \n" % thread_name(t)
+
+		self.root_win.update_summary(raw)
+
+	def update_rectangle_cpu(self, slice, cpu):
+		rq = slice.rqs[cpu]
+
+		if slice.total_load != 0:
+			load_rate = rq.load() / float(slice.total_load)
+		else:
+			load_rate = 0
+
+		red_power = int(0xff - (0xff * load_rate))
+		color = (0xff, red_power, red_power)
+
+		top_color = None
+
+		if cpu in slice.event_cpus:
+			top_color = rq.event.color()
+
+		self.root_win.paint_rectangle_zone(cpu, color, top_color, slice.start, slice.end)
+
+	def fill_zone(self, start, end):
+		i = self.find_time_slice(start)
+		if i == -1:
+			return
+
+		for i in xrange(i, len(self.data)):
+			timeslice = self.data[i]
+			if timeslice.start > end:
+				return
+
+			for cpu in timeslice.rqs:
+				self.update_rectangle_cpu(timeslice, cpu)
+
+	def interval(self):
+		if len(self.data) == 0:
+			return (0, 0)
+
+		return (self.data[0].start, self.data[-1].end)
+
+	def nr_rectangles(self):
+		last_ts = self.data[-1]
+		max_cpu = 0
+		for cpu in last_ts.rqs:
+			if cpu > max_cpu:
+				max_cpu = cpu
+		return max_cpu
+
+
+class SchedEventProxy:
+	def __init__(self):
+		self.current_tsk = defaultdict(lambda : -1)
+		self.timeslices = TimeSliceList()
+
+	def sched_switch(self, headers, prev_comm, prev_pid, prev_prio, prev_state,
+			 next_comm, next_pid, next_prio):
+		""" Ensure the task we sched out this cpu is really the one
+		    we logged. Otherwise we may have missed traces """
+
+		on_cpu_task = self.current_tsk[headers.cpu]
+
+		if on_cpu_task != -1 and on_cpu_task != prev_pid:
+			print "Sched switch event rejected ts: %s cpu: %d prev: %s(%d) next: %s(%d)" % \
+				(headers.ts_format(), headers.cpu, prev_comm, prev_pid, next_comm, next_pid)
+
+		threads[prev_pid] = prev_comm
+		threads[next_pid] = next_comm
+		self.current_tsk[headers.cpu] = next_pid
+
+		ts = self.timeslices.get_time_slice(headers.ts())
+		ts.sched_switch(self.timeslices, prev_pid, prev_state, next_pid, headers.cpu)
+
+	def migrate(self, headers, pid, prio, orig_cpu, dest_cpu):
+		ts = self.timeslices.get_time_slice(headers.ts())
+		ts.migrate(self.timeslices, pid, orig_cpu, dest_cpu)
+
+	def wake_up(self, headers, comm, pid, success, target_cpu, fork):
+		if success == 0:
+			return
+		ts = self.timeslices.get_time_slice(headers.ts())
+		ts.wake_up(self.timeslices, pid, target_cpu, fork)
+
+
+def trace_begin():
+	global parser
+	parser = SchedEventProxy()
+
+def trace_end():
+	app = wx.App(False)
+	timeslices = parser.timeslices
+	frame = RootFrame(timeslices, "Migration")
+	app.MainLoop()
+
+def sched__sched_stat_runtime(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm,
+	comm, pid, runtime, vruntime):
+	pass
+
+def sched__sched_stat_iowait(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm,
+	comm, pid, delay):
+	pass
+
+def sched__sched_stat_sleep(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm,
+	comm, pid, delay):
+	pass
+
+def sched__sched_stat_wait(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm,
+	comm, pid, delay):
+	pass
+
+def sched__sched_process_fork(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm,
+	parent_comm, parent_pid, child_comm, child_pid):
+	pass
+
+def sched__sched_process_wait(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm,
+	comm, pid, prio):
+	pass
+
+def sched__sched_process_exit(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm,
+	comm, pid, prio):
+	pass
+
+def sched__sched_process_free(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm,
+	comm, pid, prio):
+	pass
+
+def sched__sched_migrate_task(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm,
+	comm, pid, prio, orig_cpu,
+	dest_cpu):
+	headers = EventHeaders(common_cpu, common_secs, common_nsecs,
+				common_pid, common_comm)
+	parser.migrate(headers, pid, prio, orig_cpu, dest_cpu)
+
+def sched__sched_switch(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm,
+	prev_comm, prev_pid, prev_prio, prev_state,
+	next_comm, next_pid, next_prio):
+
+	headers = EventHeaders(common_cpu, common_secs, common_nsecs,
+				common_pid, common_comm)
+	parser.sched_switch(headers, prev_comm, prev_pid, prev_prio, prev_state,
+			 next_comm, next_pid, next_prio)
+
+def sched__sched_wakeup_new(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm,
+	comm, pid, prio, success,
+	target_cpu):
+	headers = EventHeaders(common_cpu, common_secs, common_nsecs,
+				common_pid, common_comm)
+	parser.wake_up(headers, comm, pid, success, target_cpu, 1)
+
+def sched__sched_wakeup(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm,
+	comm, pid, prio, success,
+	target_cpu):
+	headers = EventHeaders(common_cpu, common_secs, common_nsecs,
+				common_pid, common_comm)
+	parser.wake_up(headers, comm, pid, success, target_cpu, 0)
+
+def sched__sched_wait_task(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm,
+	comm, pid, prio):
+	pass
+
+def sched__sched_kthread_stop_ret(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm,
+	ret):
+	pass
+
+def sched__sched_kthread_stop(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm,
+	comm, pid):
+	pass
+
+def trace_unhandled(event_name, context, common_cpu, common_secs, common_nsecs,
+		common_pid, common_comm):
+	pass
diff --git a/tools/perf/scripts/python/sctop.py b/tools/perf/scripts/python/sctop.py
index 6cafad40c29..42c267e292f 100644
--- a/tools/perf/scripts/python/sctop.py
+++ b/tools/perf/scripts/python/sctop.py
@@ -8,10 +8,7 @@
 # will be refreshed every [interval] seconds.  The default interval is
 # 3 seconds.
 
-import thread
-import time
-import os
-import sys
+import os, sys, thread, time
 
 sys.path.append(os.environ['PERF_EXEC_PATH'] + \
 	'/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
@@ -20,7 +17,7 @@ from perf_trace_context import *
 from Core import *
 from Util import *
 
-usage = "perf trace -s syscall-counts.py [comm] [interval]\n";
+usage = "perf script -s sctop.py [comm] [interval]\n";
 
 for_comm = None
 default_interval = 3
@@ -71,7 +68,7 @@ def print_syscall_totals(interval):
 		for id, val in sorted(syscalls.iteritems(), key = lambda(k, v): (v, k), \
 					      reverse = True):
 			try:
-				print "%-40d  %10d\n" % (id, val),
+				print "%-40s  %10d\n" % (syscall_name(id), val),
 			except TypeError:
 				pass
 		syscalls.clear()
diff --git a/tools/perf/scripts/python/syscall-counts-by-pid.py b/tools/perf/scripts/python/syscall-counts-by-pid.py
index af722d6a4b3..c64d1c55d74 100644
--- a/tools/perf/scripts/python/syscall-counts-by-pid.py
+++ b/tools/perf/scripts/python/syscall-counts-by-pid.py
@@ -5,29 +5,33 @@
 # Displays system-wide system call totals, broken down by syscall.
 # If a [comm] arg is specified, only syscalls called by [comm] are displayed.
 
-import os
-import sys
+import os, sys
 
 sys.path.append(os.environ['PERF_EXEC_PATH'] + \
 	'/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
 
 from perf_trace_context import *
 from Core import *
+from Util import syscall_name
 
-usage = "perf trace -s syscall-counts-by-pid.py [comm]\n";
+usage = "perf script -s syscall-counts-by-pid.py [comm]\n";
 
 for_comm = None
+for_pid = None
 
 if len(sys.argv) > 2:
 	sys.exit(usage)
 
 if len(sys.argv) > 1:
-	for_comm = sys.argv[1]
+	try:
+		for_pid = int(sys.argv[1])
+	except:
+		for_comm = sys.argv[1]
 
 syscalls = autodict()
 
 def trace_begin():
-	pass
+	print "Press control+C to stop and show the summary"
 
 def trace_end():
 	print_syscall_totals()
@@ -35,9 +39,10 @@ def trace_end():
 def raw_syscalls__sys_enter(event_name, context, common_cpu,
 	common_secs, common_nsecs, common_pid, common_comm,
 	id, args):
-	if for_comm is not None:
-		if common_comm != for_comm:
-			return
+
+	if (for_comm and common_comm != for_comm) or \
+	   (for_pid  and common_pid  != for_pid ):
+		return
 	try:
 		syscalls[common_comm][common_pid][id] += 1
 	except TypeError:
@@ -61,4 +66,4 @@ def print_syscall_totals():
 		    id_keys = syscalls[comm][pid].keys()
 		    for id, val in sorted(syscalls[comm][pid].iteritems(), \
 				  key = lambda(k, v): (v, k),  reverse = True):
-			    print "  %-38d  %10d\n" % (id, val),
+			    print "  %-38s  %10d\n" % (syscall_name(id), val),
diff --git a/tools/perf/scripts/python/syscall-counts.py b/tools/perf/scripts/python/syscall-counts.py
index f977e85ff04..b435d3f188e 100644
--- a/tools/perf/scripts/python/syscall-counts.py
+++ b/tools/perf/scripts/python/syscall-counts.py
@@ -13,8 +13,9 @@ sys.path.append(os.environ['PERF_EXEC_PATH'] + \
 
 from perf_trace_context import *
 from Core import *
+from Util import syscall_name
 
-usage = "perf trace -s syscall-counts.py [comm]\n";
+usage = "perf script -s syscall-counts.py [comm]\n";
 
 for_comm = None
 
@@ -27,7 +28,7 @@ if len(sys.argv) > 1:
 syscalls = autodict()
 
 def trace_begin():
-	pass
+	print "Press control+C to stop and show the summary"
 
 def trace_end():
 	print_syscall_totals()
@@ -55,4 +56,4 @@ def print_syscall_totals():
 
     for id, val in sorted(syscalls.iteritems(), key = lambda(k, v): (v, k), \
 				  reverse = True):
-	    print "%-40d  %10d\n" % (id, val),
+	    print "%-40s  %10d\n" % (syscall_name(id), val),
diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c
new file mode 100644
index 00000000000..2dfc9ad0e6f
--- /dev/null
+++ b/tools/perf/tests/attr.c
@@ -0,0 +1,176 @@
+/*
+ * The struct perf_event_attr test support.
+ *
+ * This test is embedded inside into perf directly and is governed
+ * by the PERF_TEST_ATTR environment variable and hook inside
+ * sys_perf_event_open function.
+ *
+ * The general idea is to store 'struct perf_event_attr' details for
+ * each event created within single perf command. Each event details
+ * are stored into separate text file. Once perf command is finished
+ * these files can be checked for values we expect for command.
+ *
+ * Besides 'struct perf_event_attr' values we also store 'fd' and
+ * 'group_fd' values to allow checking for groups created.
+ *
+ * This all is triggered by setting PERF_TEST_ATTR environment variable.
+ * It must contain name of existing directory with access and write
+ * permissions. All the event text files are stored there.
+ */
+
+#include <stdlib.h>
+#include <stdio.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include "../perf.h"
+#include "util.h"
+#include "exec_cmd.h"
+#include "tests.h"
+
+#define ENV "PERF_TEST_ATTR"
+
+extern int verbose;
+
+static char *dir;
+
+void test_attr__init(void)
+{
+	dir = getenv(ENV);
+	test_attr__enabled = (dir != NULL);
+}
+
+#define BUFSIZE 1024
+
+#define __WRITE_ASS(str, fmt, data)					\
+do {									\
+	char buf[BUFSIZE];						\
+	size_t size;							\
+									\
+	size = snprintf(buf, BUFSIZE, #str "=%"fmt "\n", data);		\
+	if (1 != fwrite(buf, size, 1, file)) {				\
+		perror("test attr - failed to write event file");	\
+		fclose(file);						\
+		return -1;						\
+	}								\
+									\
+} while (0)
+
+#define WRITE_ASS(field, fmt) __WRITE_ASS(field, fmt, attr->field)
+
+static int store_event(struct perf_event_attr *attr, pid_t pid, int cpu,
+		       int fd, int group_fd, unsigned long flags)
+{
+	FILE *file;
+	char path[PATH_MAX];
+
+	snprintf(path, PATH_MAX, "%s/event-%d-%llu-%d", dir,
+		 attr->type, attr->config, fd);
+
+	file = fopen(path, "w+");
+	if (!file) {
+		perror("test attr - failed to open event file");
+		return -1;
+	}
+
+	if (fprintf(file, "[event-%d-%llu-%d]\n",
+		    attr->type, attr->config, fd) < 0) {
+		perror("test attr - failed to write event file");
+		fclose(file);
+		return -1;
+	}
+
+	/* syscall arguments */
+	__WRITE_ASS(fd,       "d", fd);
+	__WRITE_ASS(group_fd, "d", group_fd);
+	__WRITE_ASS(cpu,      "d", cpu);
+	__WRITE_ASS(pid,      "d", pid);
+	__WRITE_ASS(flags,   "lu", flags);
+
+	/* struct perf_event_attr */
+	WRITE_ASS(type,   PRIu32);
+	WRITE_ASS(size,   PRIu32);
+	WRITE_ASS(config,  "llu");
+	WRITE_ASS(sample_period, "llu");
+	WRITE_ASS(sample_type,   "llu");
+	WRITE_ASS(read_format,   "llu");
+	WRITE_ASS(disabled,       "d");
+	WRITE_ASS(inherit,        "d");
+	WRITE_ASS(pinned,         "d");
+	WRITE_ASS(exclusive,      "d");
+	WRITE_ASS(exclude_user,   "d");
+	WRITE_ASS(exclude_kernel, "d");
+	WRITE_ASS(exclude_hv,     "d");
+	WRITE_ASS(exclude_idle,   "d");
+	WRITE_ASS(mmap,           "d");
+	WRITE_ASS(comm,           "d");
+	WRITE_ASS(freq,           "d");
+	WRITE_ASS(inherit_stat,   "d");
+	WRITE_ASS(enable_on_exec, "d");
+	WRITE_ASS(task,           "d");
+	WRITE_ASS(watermark,      "d");
+	WRITE_ASS(precise_ip,     "d");
+	WRITE_ASS(mmap_data,      "d");
+	WRITE_ASS(sample_id_all,  "d");
+	WRITE_ASS(exclude_host,   "d");
+	WRITE_ASS(exclude_guest,  "d");
+	WRITE_ASS(exclude_callchain_kernel, "d");
+	WRITE_ASS(exclude_callchain_user, "d");
+	WRITE_ASS(wakeup_events, PRIu32);
+	WRITE_ASS(bp_type, PRIu32);
+	WRITE_ASS(config1, "llu");
+	WRITE_ASS(config2, "llu");
+	WRITE_ASS(branch_sample_type, "llu");
+	WRITE_ASS(sample_regs_user,   "llu");
+	WRITE_ASS(sample_stack_user,  PRIu32);
+
+	fclose(file);
+	return 0;
+}
+
+void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu,
+		     int fd, int group_fd, unsigned long flags)
+{
+	int errno_saved = errno;
+
+	if (store_event(attr, pid, cpu, fd, group_fd, flags))
+		die("test attr FAILED");
+
+	errno = errno_saved;
+}
+
+static int run_dir(const char *d, const char *perf)
+{
+	char v[] = "-vvvvv";
+	int vcnt = min(verbose, (int) sizeof(v) - 1);
+	char cmd[3*PATH_MAX];
+
+	if (verbose)
+		vcnt++;
+
+	snprintf(cmd, 3*PATH_MAX, PYTHON " %s/attr.py -d %s/attr/ -p %s %.*s",
+		 d, d, perf, vcnt, v);
+
+	return system(cmd);
+}
+
+int test__attr(void)
+{
+	struct stat st;
+	char path_perf[PATH_MAX];
+	char path_dir[PATH_MAX];
+
+	/* First try developement tree tests. */
+	if (!lstat("./tests", &st))
+		return run_dir("./tests", "./perf");
+
+	/* Then installed path. */
+	snprintf(path_dir,  PATH_MAX, "%s/tests", perf_exec_path());
+	snprintf(path_perf, PATH_MAX, "%s/perf", BINDIR);
+
+	if (!lstat(path_dir, &st) &&
+	    !lstat(path_perf, &st))
+		return run_dir(path_dir, path_perf);
+
+	fprintf(stderr, " (omitted)");
+	return 0;
+}
diff --git a/tools/perf/tests/attr.py b/tools/perf/tests/attr.py
new file mode 100644
index 00000000000..c9b4b6269b5
--- /dev/null
+++ b/tools/perf/tests/attr.py
@@ -0,0 +1,332 @@
+#! /usr/bin/python
+
+import os
+import sys
+import glob
+import optparse
+import tempfile
+import logging
+import shutil
+import ConfigParser
+
+class Fail(Exception):
+    def __init__(self, test, msg):
+        self.msg = msg
+        self.test = test
+    def getMsg(self):
+        return '\'%s\' - %s' % (self.test.path, self.msg)
+
+class Unsup(Exception):
+    def __init__(self, test):
+        self.test = test
+    def getMsg(self):
+        return '\'%s\'' % self.test.path
+
+class Event(dict):
+    terms = [
+        'cpu',
+        'flags',
+        'type',
+        'size',
+        'config',
+        'sample_period',
+        'sample_type',
+        'read_format',
+        'disabled',
+        'inherit',
+        'pinned',
+        'exclusive',
+        'exclude_user',
+        'exclude_kernel',
+        'exclude_hv',
+        'exclude_idle',
+        'mmap',
+        'comm',
+        'freq',
+        'inherit_stat',
+        'enable_on_exec',
+        'task',
+        'watermark',
+        'precise_ip',
+        'mmap_data',
+        'sample_id_all',
+        'exclude_host',
+        'exclude_guest',
+        'exclude_callchain_kernel',
+        'exclude_callchain_user',
+        'wakeup_events',
+        'bp_type',
+        'config1',
+        'config2',
+        'branch_sample_type',
+        'sample_regs_user',
+        'sample_stack_user',
+    ]
+
+    def add(self, data):
+        for key, val in data:
+            log.debug("      %s = %s" % (key, val))
+            self[key] = val
+
+    def __init__(self, name, data, base):
+        log.debug("    Event %s" % name);
+        self.name  = name;
+        self.group = ''
+        self.add(base)
+        self.add(data)
+
+    def compare_data(self, a, b):
+        # Allow multiple values in assignment separated by '|'
+        a_list = a.split('|')
+        b_list = b.split('|')
+
+        for a_item in a_list:
+            for b_item in b_list:
+                if (a_item == b_item):
+                    return True
+                elif (a_item == '*') or (b_item == '*'):
+                    return True
+
+        return False
+
+    def equal(self, other):
+        for t in Event.terms:
+            log.debug("      [%s] %s %s" % (t, self[t], other[t]));
+            if not self.has_key(t) or not other.has_key(t):
+                return False
+            if not self.compare_data(self[t], other[t]):
+                return False
+        return True
+
+    def diff(self, other):
+        for t in Event.terms:
+            if not self.has_key(t) or not other.has_key(t):
+                continue
+            if not self.compare_data(self[t], other[t]):
+		log.warning("expected %s=%s, got %s" % (t, self[t], other[t]))
+                
+
+# Test file description needs to have following sections:
+# [config]
+#   - just single instance in file
+#   - needs to specify:
+#     'command' - perf command name
+#     'args'    - special command arguments
+#     'ret'     - expected command return value (0 by default)
+#
+# [eventX:base]
+#   - one or multiple instances in file
+#   - expected values assignments
+class Test(object):
+    def __init__(self, path, options):
+        parser = ConfigParser.SafeConfigParser()
+        parser.read(path)
+
+        log.warning("running '%s'" % path)
+
+        self.path     = path
+        self.test_dir = options.test_dir
+        self.perf     = options.perf
+        self.command  = parser.get('config', 'command')
+        self.args     = parser.get('config', 'args')
+
+        try:
+            self.ret  = parser.get('config', 'ret')
+        except:
+            self.ret  = 0
+
+        self.expect   = {}
+        self.result   = {}
+        log.debug("  loading expected events");
+        self.load_events(path, self.expect)
+
+    def is_event(self, name):
+        if name.find("event") == -1:
+            return False
+        else:
+            return True
+
+    def load_events(self, path, events):
+        parser_event = ConfigParser.SafeConfigParser()
+        parser_event.read(path)
+
+        # The event record section header contains 'event' word,
+        # optionaly followed by ':' allowing to load 'parent
+        # event' first as a base
+        for section in filter(self.is_event, parser_event.sections()):
+
+            parser_items = parser_event.items(section);
+            base_items   = {}
+
+            # Read parent event if there's any
+            if (':' in section):
+                base = section[section.index(':') + 1:]
+                parser_base = ConfigParser.SafeConfigParser()
+                parser_base.read(self.test_dir + '/' + base)
+                base_items = parser_base.items('event')
+
+            e = Event(section, parser_items, base_items)
+            events[section] = e
+
+    def run_cmd(self, tempdir):
+        cmd = "PERF_TEST_ATTR=%s %s %s -o %s/perf.data %s" % (tempdir,
+              self.perf, self.command, tempdir, self.args)
+        ret = os.WEXITSTATUS(os.system(cmd))
+
+        log.info("  '%s' ret %d " % (cmd, ret))
+
+        if ret != int(self.ret):
+            raise Unsup(self)
+
+    def compare(self, expect, result):
+        match = {}
+
+        log.debug("  compare");
+
+        # For each expected event find all matching
+        # events in result. Fail if there's not any.
+        for exp_name, exp_event in expect.items():
+            exp_list = []
+            log.debug("    matching [%s]" % exp_name)
+            for res_name, res_event in result.items():
+                log.debug("      to [%s]" % res_name)
+                if (exp_event.equal(res_event)):
+                    exp_list.append(res_name)
+                    log.debug("    ->OK")
+                else:
+                    log.debug("    ->FAIL");
+
+            log.debug("    match: [%s] matches %s" % (exp_name, str(exp_list)))
+
+            # we did not any matching event - fail
+            if (not exp_list):
+		exp_event.diff(res_event)
+                raise Fail(self, 'match failure');
+
+            match[exp_name] = exp_list
+
+        # For each defined group in the expected events
+        # check we match the same group in the result.
+        for exp_name, exp_event in expect.items():
+            group = exp_event.group
+
+            if (group == ''):
+                continue
+
+            for res_name in match[exp_name]:
+                res_group = result[res_name].group
+                if res_group not in match[group]:
+                    raise Fail(self, 'group failure')
+
+                log.debug("    group: [%s] matches group leader %s" %
+                         (exp_name, str(match[group])))
+
+        log.debug("  matched")
+
+    def resolve_groups(self, events):
+        for name, event in events.items():
+            group_fd = event['group_fd'];
+            if group_fd == '-1':
+                continue;
+
+            for iname, ievent in events.items():
+                if (ievent['fd'] == group_fd):
+                    event.group = iname
+                    log.debug('[%s] has group leader [%s]' % (name, iname))
+                    break;
+
+    def run(self):
+        tempdir = tempfile.mkdtemp();
+
+        try:
+            # run the test script
+            self.run_cmd(tempdir);
+
+            # load events expectation for the test
+            log.debug("  loading result events");
+            for f in glob.glob(tempdir + '/event*'):
+                self.load_events(f, self.result);
+
+            # resolve group_fd to event names
+            self.resolve_groups(self.expect);
+            self.resolve_groups(self.result);
+
+            # do the expectation - results matching - both ways
+            self.compare(self.expect, self.result)
+            self.compare(self.result, self.expect)
+
+        finally:
+            # cleanup
+            shutil.rmtree(tempdir)
+
+
+def run_tests(options):
+    for f in glob.glob(options.test_dir + '/' + options.test):
+        try:
+            Test(f, options).run()
+        except Unsup, obj:
+            log.warning("unsupp  %s" % obj.getMsg())
+
+def setup_log(verbose):
+    global log
+    level = logging.CRITICAL
+
+    if verbose == 1:
+        level = logging.WARNING
+    if verbose == 2:
+        level = logging.INFO
+    if verbose >= 3:
+        level = logging.DEBUG
+
+    log = logging.getLogger('test')
+    log.setLevel(level)
+    ch  = logging.StreamHandler()
+    ch.setLevel(level)
+    formatter = logging.Formatter('%(message)s')
+    ch.setFormatter(formatter)
+    log.addHandler(ch)
+
+USAGE = '''%s [OPTIONS]
+  -d dir  # tests dir
+  -p path # perf binary
+  -t test # single test
+  -v      # verbose level
+''' % sys.argv[0]
+
+def main():
+    parser = optparse.OptionParser(usage=USAGE)
+
+    parser.add_option("-t", "--test",
+                      action="store", type="string", dest="test")
+    parser.add_option("-d", "--test-dir",
+                      action="store", type="string", dest="test_dir")
+    parser.add_option("-p", "--perf",
+                      action="store", type="string", dest="perf")
+    parser.add_option("-v", "--verbose",
+                      action="count", dest="verbose")
+
+    options, args = parser.parse_args()
+    if args:
+        parser.error('FAILED wrong arguments %s' %  ' '.join(args))
+        return -1
+
+    setup_log(options.verbose)
+
+    if not options.test_dir:
+        print 'FAILED no -d option specified'
+        sys.exit(-1)
+
+    if not options.test:
+        options.test = 'test*'
+
+    try:
+        run_tests(options)
+
+    except Fail, obj:
+        print "FAILED %s" % obj.getMsg();
+        sys.exit(-1)
+
+    sys.exit(0)
+
+if __name__ == '__main__':
+    main()
diff --git a/tools/perf/tests/attr/README b/tools/perf/tests/attr/README
new file mode 100644
index 00000000000..430024f618f
--- /dev/null
+++ b/tools/perf/tests/attr/README
@@ -0,0 +1,64 @@
+The struct perf_event_attr test (attr tests) support
+====================================================
+This testing support is embedded into perf directly and is governed
+by the PERF_TEST_ATTR environment variable and hook inside the
+sys_perf_event_open function.
+
+The general idea is to store 'struct perf_event_attr' details for
+each event created within single perf command. Each event details
+are stored into separate text file. Once perf command is finished
+these files are checked for values we expect for command.
+
+The attr tests consist of following parts:
+
+tests/attr.c
+------------
+This is the sys_perf_event_open hook implementation. The hook
+is triggered when the PERF_TEST_ATTR environment variable is
+defined. It must contain name of existing directory with access
+and write permissions.
+
+For each sys_perf_event_open call event details are stored in
+separate file. Besides 'struct perf_event_attr' values we also
+store 'fd' and 'group_fd' values to allow checking for groups.
+
+tests/attr.py
+-------------
+This is the python script that does all the hard work. It reads
+the test definition, executes it and checks results.
+
+tests/attr/
+-----------
+Directory containing all attr test definitions.
+Following tests are defined (with perf commands):
+
+  perf record kill                              (test-record-basic)
+  perf record -b kill                           (test-record-branch-any)
+  perf record -j any kill                       (test-record-branch-filter-any)
+  perf record -j any_call kill                  (test-record-branch-filter-any_call)
+  perf record -j any_ret kill                   (test-record-branch-filter-any_ret)
+  perf record -j hv kill                        (test-record-branch-filter-hv)
+  perf record -j ind_call kill                  (test-record-branch-filter-ind_call)
+  perf record -j k kill                         (test-record-branch-filter-k)
+  perf record -j u kill                         (test-record-branch-filter-u)
+  perf record -c 123 kill                       (test-record-count)
+  perf record -d kill                           (test-record-data)
+  perf record -F 100 kill                       (test-record-freq)
+  perf record -g kill                           (test-record-graph-default)
+  perf record --call-graph dwarf kill		(test-record-graph-dwarf)
+  perf record --call-graph fp kill              (test-record-graph-fp)
+  perf record --group -e cycles,instructions kill (test-record-group)
+  perf record -e '{cycles,instructions}' kill   (test-record-group1)
+  perf record -D kill                           (test-record-no-delay)
+  perf record -i kill                           (test-record-no-inherit)
+  perf record -n kill                           (test-record-no-samples)
+  perf record -c 100 -P kill                    (test-record-period)
+  perf record -R kill                           (test-record-raw)
+  perf stat -e cycles kill                      (test-stat-basic)
+  perf stat kill                                (test-stat-default)
+  perf stat -d kill                             (test-stat-detailed-1)
+  perf stat -dd kill                            (test-stat-detailed-2)
+  perf stat -ddd kill                           (test-stat-detailed-3)
+  perf stat --group -e cycles,instructions kill (test-stat-group)
+  perf stat -e '{cycles,instructions}' kill     (test-stat-group1)
+  perf stat -i -e cycles kill                   (test-stat-no-inherit)
diff --git a/tools/perf/tests/attr/base-record b/tools/perf/tests/attr/base-record
new file mode 100644
index 00000000000..e9bd6391f2a
--- /dev/null
+++ b/tools/perf/tests/attr/base-record
@@ -0,0 +1,40 @@
+[event]
+fd=1
+group_fd=-1
+flags=0
+cpu=*
+type=0|1
+size=96
+config=0
+sample_period=4000
+sample_type=263
+read_format=0
+disabled=1
+inherit=1
+pinned=0
+exclusive=0
+exclude_user=0
+exclude_kernel=0
+exclude_hv=0
+exclude_idle=0
+mmap=1
+comm=1
+freq=1
+inherit_stat=0
+enable_on_exec=1
+task=0
+watermark=0
+precise_ip=0
+mmap_data=0
+sample_id_all=1
+exclude_host=0|1
+exclude_guest=0|1
+exclude_callchain_kernel=0
+exclude_callchain_user=0
+wakeup_events=0
+bp_type=0
+config1=0
+config2=0
+branch_sample_type=0
+sample_regs_user=0
+sample_stack_user=0
diff --git a/tools/perf/tests/attr/base-stat b/tools/perf/tests/attr/base-stat
new file mode 100644
index 00000000000..91cd48b399f
--- /dev/null
+++ b/tools/perf/tests/attr/base-stat
@@ -0,0 +1,40 @@
+[event]
+fd=1
+group_fd=-1
+flags=0
+cpu=*
+type=0
+size=96
+config=0
+sample_period=0
+sample_type=0
+read_format=3
+disabled=1
+inherit=1
+pinned=0
+exclusive=0
+exclude_user=0
+exclude_kernel=0
+exclude_hv=0
+exclude_idle=0
+mmap=0
+comm=0
+freq=0
+inherit_stat=0
+enable_on_exec=1
+task=0
+watermark=0
+precise_ip=0
+mmap_data=0
+sample_id_all=0
+exclude_host=0|1
+exclude_guest=0|1
+exclude_callchain_kernel=0
+exclude_callchain_user=0
+wakeup_events=0
+bp_type=0
+config1=0
+config2=0
+branch_sample_type=0
+sample_regs_user=0
+sample_stack_user=0
diff --git a/tools/perf/tests/attr/test-record-C0 b/tools/perf/tests/attr/test-record-C0
new file mode 100644
index 00000000000..d6a7e43f61b
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-C0
@@ -0,0 +1,13 @@
+[config]
+command = record
+args    = -C 0 kill >/dev/null 2>&1
+
+[event:base-record]
+cpu=0
+
+# no enable on exec for CPU attached
+enable_on_exec=0
+
+# PERF_SAMPLE_IP | PERF_SAMPLE_TID PERF_SAMPLE_TIME | # PERF_SAMPLE_PERIOD
+# + PERF_SAMPLE_CPU added by -C 0
+sample_type=391
diff --git a/tools/perf/tests/attr/test-record-basic b/tools/perf/tests/attr/test-record-basic
new file mode 100644
index 00000000000..55c0428370c
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-basic
@@ -0,0 +1,5 @@
+[config]
+command = record
+args    = kill >/dev/null 2>&1
+
+[event:base-record]
diff --git a/tools/perf/tests/attr/test-record-branch-any b/tools/perf/tests/attr/test-record-branch-any
new file mode 100644
index 00000000000..1421960ed4e
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-branch-any
@@ -0,0 +1,8 @@
+[config]
+command = record
+args    = -b kill >/dev/null 2>&1
+
+[event:base-record]
+sample_period=4000
+sample_type=2311
+branch_sample_type=8
diff --git a/tools/perf/tests/attr/test-record-branch-filter-any b/tools/perf/tests/attr/test-record-branch-filter-any
new file mode 100644
index 00000000000..915c4df0e0c
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-branch-filter-any
@@ -0,0 +1,8 @@
+[config]
+command = record
+args    = -j any kill >/dev/null 2>&1
+
+[event:base-record]
+sample_period=4000
+sample_type=2311
+branch_sample_type=8
diff --git a/tools/perf/tests/attr/test-record-branch-filter-any_call b/tools/perf/tests/attr/test-record-branch-filter-any_call
new file mode 100644
index 00000000000..8708dbd4f37
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-branch-filter-any_call
@@ -0,0 +1,8 @@
+[config]
+command = record
+args    = -j any_call kill >/dev/null 2>&1
+
+[event:base-record]
+sample_period=4000
+sample_type=2311
+branch_sample_type=16
diff --git a/tools/perf/tests/attr/test-record-branch-filter-any_ret b/tools/perf/tests/attr/test-record-branch-filter-any_ret
new file mode 100644
index 00000000000..0d3607a6dcb
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-branch-filter-any_ret
@@ -0,0 +1,8 @@
+[config]
+command = record
+args    = -j any_ret kill >/dev/null 2>&1
+
+[event:base-record]
+sample_period=4000
+sample_type=2311
+branch_sample_type=32
diff --git a/tools/perf/tests/attr/test-record-branch-filter-hv b/tools/perf/tests/attr/test-record-branch-filter-hv
new file mode 100644
index 00000000000..f25526740ce
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-branch-filter-hv
@@ -0,0 +1,8 @@
+[config]
+command = record
+args    = -j hv kill >/dev/null 2>&1
+
+[event:base-record]
+sample_period=4000
+sample_type=2311
+branch_sample_type=8
diff --git a/tools/perf/tests/attr/test-record-branch-filter-ind_call b/tools/perf/tests/attr/test-record-branch-filter-ind_call
new file mode 100644
index 00000000000..e862dd17912
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-branch-filter-ind_call
@@ -0,0 +1,8 @@
+[config]
+command = record
+args    = -j ind_call kill >/dev/null 2>&1
+
+[event:base-record]
+sample_period=4000
+sample_type=2311
+branch_sample_type=64
diff --git a/tools/perf/tests/attr/test-record-branch-filter-k b/tools/perf/tests/attr/test-record-branch-filter-k
new file mode 100644
index 00000000000..182971e898f
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-branch-filter-k
@@ -0,0 +1,8 @@
+[config]
+command = record
+args    = -j k kill >/dev/null 2>&1
+
+[event:base-record]
+sample_period=4000
+sample_type=2311
+branch_sample_type=8
diff --git a/tools/perf/tests/attr/test-record-branch-filter-u b/tools/perf/tests/attr/test-record-branch-filter-u
new file mode 100644
index 00000000000..83449ef9e68
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-branch-filter-u
@@ -0,0 +1,8 @@
+[config]
+command = record
+args    = -j u kill >/dev/null 2>&1
+
+[event:base-record]
+sample_period=4000
+sample_type=2311
+branch_sample_type=8
diff --git a/tools/perf/tests/attr/test-record-count b/tools/perf/tests/attr/test-record-count
new file mode 100644
index 00000000000..2f841de56f6
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-count
@@ -0,0 +1,8 @@
+[config]
+command = record
+args    = -c 123 kill >/dev/null 2>&1
+
+[event:base-record]
+sample_period=123
+sample_type=7
+freq=0
diff --git a/tools/perf/tests/attr/test-record-data b/tools/perf/tests/attr/test-record-data
new file mode 100644
index 00000000000..716e143b529
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-data
@@ -0,0 +1,11 @@
+[config]
+command = record
+args    = -d kill >/dev/null 2>&1
+
+[event:base-record]
+sample_period=4000
+
+# 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/attr/test-record-freq b/tools/perf/tests/attr/test-record-freq
new file mode 100644
index 00000000000..600d0f8f258
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-freq
@@ -0,0 +1,6 @@
+[config]
+command = record
+args    = -F 100 kill >/dev/null 2>&1
+
+[event:base-record]
+sample_period=100
diff --git a/tools/perf/tests/attr/test-record-graph-default b/tools/perf/tests/attr/test-record-graph-default
new file mode 100644
index 00000000000..853597a9a8f
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-graph-default
@@ -0,0 +1,6 @@
+[config]
+command = record
+args    = -g kill >/dev/null 2>&1
+
+[event:base-record]
+sample_type=295
diff --git a/tools/perf/tests/attr/test-record-graph-dwarf b/tools/perf/tests/attr/test-record-graph-dwarf
new file mode 100644
index 00000000000..d6f324ea578
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-graph-dwarf
@@ -0,0 +1,10 @@
+[config]
+command = record
+args    = --call-graph dwarf -- kill >/dev/null 2>&1
+
+[event:base-record]
+sample_type=12583
+exclude_callchain_user=1
+sample_stack_user=8192
+# TODO different for each arch, no support for that now
+sample_regs_user=*
diff --git a/tools/perf/tests/attr/test-record-graph-fp b/tools/perf/tests/attr/test-record-graph-fp
new file mode 100644
index 00000000000..055e3bee799
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-graph-fp
@@ -0,0 +1,6 @@
+[config]
+command = record
+args    = --call-graph fp kill >/dev/null 2>&1
+
+[event:base-record]
+sample_type=295
diff --git a/tools/perf/tests/attr/test-record-group b/tools/perf/tests/attr/test-record-group
new file mode 100644
index 00000000000..57739cacdb2
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-group
@@ -0,0 +1,20 @@
+[config]
+command = record
+args    = --group -e cycles,instructions kill >/dev/null 2>&1
+
+[event-1:base-record]
+fd=1
+group_fd=-1
+sample_type=327
+read_format=4
+
+[event-2:base-record]
+fd=2
+group_fd=1
+config=1
+sample_type=327
+read_format=4
+mmap=0
+comm=0
+enable_on_exec=0
+disabled=0
diff --git a/tools/perf/tests/attr/test-record-group-sampling b/tools/perf/tests/attr/test-record-group-sampling
new file mode 100644
index 00000000000..658f5d60c87
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-group-sampling
@@ -0,0 +1,36 @@
+[config]
+command = record
+args    = -e '{cycles,cache-misses}:S' kill >/dev/null 2>&1
+
+[event-1:base-record]
+fd=1
+group_fd=-1
+sample_type=343
+read_format=12
+inherit=0
+
+[event-2:base-record]
+fd=2
+group_fd=1
+
+# cache-misses
+type=0
+config=3
+
+# default | PERF_SAMPLE_READ
+sample_type=343
+
+# PERF_FORMAT_ID | PERF_FORMAT_GROUP
+read_format=12
+
+mmap=0
+comm=0
+enable_on_exec=0
+disabled=0
+
+# inherit is disabled for group sampling
+inherit=0
+
+# sampling disabled
+sample_freq=0
+sample_period=0
diff --git a/tools/perf/tests/attr/test-record-group1 b/tools/perf/tests/attr/test-record-group1
new file mode 100644
index 00000000000..c5548d054af
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-group1
@@ -0,0 +1,21 @@
+[config]
+command = record
+args    = -e '{cycles,instructions}' kill >/dev/null 2>&1
+
+[event-1:base-record]
+fd=1
+group_fd=-1
+sample_type=327
+read_format=4
+
+[event-2:base-record]
+fd=2
+group_fd=1
+type=0
+config=1
+sample_type=327
+read_format=4
+mmap=0
+comm=0
+enable_on_exec=0
+disabled=0
diff --git a/tools/perf/tests/attr/test-record-no-delay b/tools/perf/tests/attr/test-record-no-delay
new file mode 100644
index 00000000000..f253b78cdbf
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-no-delay
@@ -0,0 +1,9 @@
+[config]
+command = record
+args    = -D kill >/dev/null 2>&1
+
+[event:base-record]
+sample_period=4000
+sample_type=263
+watermark=0
+wakeup_events=1
diff --git a/tools/perf/tests/attr/test-record-no-inherit b/tools/perf/tests/attr/test-record-no-inherit
new file mode 100644
index 00000000000..44edcb2edcd
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-no-inherit
@@ -0,0 +1,7 @@
+[config]
+command = record
+args    = -i kill >/dev/null 2>&1
+
+[event:base-record]
+sample_type=263
+inherit=0
diff --git a/tools/perf/tests/attr/test-record-no-samples b/tools/perf/tests/attr/test-record-no-samples
new file mode 100644
index 00000000000..d0141b2418b
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-no-samples
@@ -0,0 +1,6 @@
+[config]
+command = record
+args    = -n kill >/dev/null 2>&1
+
+[event:base-record]
+sample_period=0
diff --git a/tools/perf/tests/attr/test-record-period b/tools/perf/tests/attr/test-record-period
new file mode 100644
index 00000000000..8abc5314fc5
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-period
@@ -0,0 +1,7 @@
+[config]
+command = record
+args    = -c 100 -P kill >/dev/null 2>&1
+
+[event:base-record]
+sample_period=100
+freq=0
diff --git a/tools/perf/tests/attr/test-record-raw b/tools/perf/tests/attr/test-record-raw
new file mode 100644
index 00000000000..4a8ef25b5f4
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-raw
@@ -0,0 +1,7 @@
+[config]
+command = record
+args    = -R kill >/dev/null 2>&1
+
+[event:base-record]
+sample_period=4000
+sample_type=1415
diff --git a/tools/perf/tests/attr/test-stat-C0 b/tools/perf/tests/attr/test-stat-C0
new file mode 100644
index 00000000000..aa835950751
--- /dev/null
+++ b/tools/perf/tests/attr/test-stat-C0
@@ -0,0 +1,9 @@
+[config]
+command = stat
+args    = -e cycles -C 0 kill >/dev/null 2>&1
+ret     = 1
+
+[event:base-stat]
+# events are enabled by default when attached to cpu
+disabled=0
+enable_on_exec=0
diff --git a/tools/perf/tests/attr/test-stat-basic b/tools/perf/tests/attr/test-stat-basic
new file mode 100644
index 00000000000..74e17881f2b
--- /dev/null
+++ b/tools/perf/tests/attr/test-stat-basic
@@ -0,0 +1,6 @@
+[config]
+command = stat
+args    = -e cycles kill >/dev/null 2>&1
+ret     = 1
+
+[event:base-stat]
diff --git a/tools/perf/tests/attr/test-stat-default b/tools/perf/tests/attr/test-stat-default
new file mode 100644
index 00000000000..19270f54c96
--- /dev/null
+++ b/tools/perf/tests/attr/test-stat-default
@@ -0,0 +1,64 @@
+[config]
+command = stat
+args    = kill >/dev/null 2>&1
+ret     = 1
+
+# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_TASK_CLOCK
+[event1:base-stat]
+fd=1
+type=1
+config=1
+
+# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_CONTEXT_SWITCHES
+[event2:base-stat]
+fd=2
+type=1
+config=3
+
+# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_CPU_MIGRATIONS
+[event3:base-stat]
+fd=3
+type=1
+config=4
+
+# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_PAGE_FAULTS
+[event4:base-stat]
+fd=4
+type=1
+config=2
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_CPU_CYCLES
+[event5:base-stat]
+fd=5
+type=0
+config=0
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_FRONTEND
+[event6:base-stat]
+fd=6
+type=0
+config=7
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_BACKEND
+[event7:base-stat]
+fd=7
+type=0
+config=8
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_INSTRUCTIONS
+[event8:base-stat]
+fd=8
+type=0
+config=1
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_INSTRUCTIONS
+[event9:base-stat]
+fd=9
+type=0
+config=4
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_MISSES
+[event10:base-stat]
+fd=10
+type=0
+config=5
diff --git a/tools/perf/tests/attr/test-stat-detailed-1 b/tools/perf/tests/attr/test-stat-detailed-1
new file mode 100644
index 00000000000..51426b87153
--- /dev/null
+++ b/tools/perf/tests/attr/test-stat-detailed-1
@@ -0,0 +1,101 @@
+[config]
+command = stat
+args    = -d kill >/dev/null 2>&1
+ret     = 1
+
+
+# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_TASK_CLOCK
+[event1:base-stat]
+fd=1
+type=1
+config=1
+
+# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_CONTEXT_SWITCHES
+[event2:base-stat]
+fd=2
+type=1
+config=3
+
+# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_CPU_MIGRATIONS
+[event3:base-stat]
+fd=3
+type=1
+config=4
+
+# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_PAGE_FAULTS
+[event4:base-stat]
+fd=4
+type=1
+config=2
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_CPU_CYCLES
+[event5:base-stat]
+fd=5
+type=0
+config=0
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_FRONTEND
+[event6:base-stat]
+fd=6
+type=0
+config=7
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_BACKEND
+[event7:base-stat]
+fd=7
+type=0
+config=8
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_INSTRUCTIONS
+[event8:base-stat]
+fd=8
+type=0
+config=1
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_INSTRUCTIONS
+[event9:base-stat]
+fd=9
+type=0
+config=4
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_MISSES
+[event10:base-stat]
+fd=10
+type=0
+config=5
+
+# PERF_TYPE_HW_CACHE /
+#  PERF_COUNT_HW_CACHE_L1D                <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
+[event11:base-stat]
+fd=11
+type=3
+config=0
+
+# PERF_TYPE_HW_CACHE /
+#  PERF_COUNT_HW_CACHE_L1D                <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
+[event12:base-stat]
+fd=12
+type=3
+config=65536
+
+# PERF_TYPE_HW_CACHE /
+#  PERF_COUNT_HW_CACHE_LL                 <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
+[event13:base-stat]
+fd=13
+type=3
+config=2
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_LL                 <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
+[event14:base-stat]
+fd=14
+type=3
+config=65538
diff --git a/tools/perf/tests/attr/test-stat-detailed-2 b/tools/perf/tests/attr/test-stat-detailed-2
new file mode 100644
index 00000000000..8de5acc31c2
--- /dev/null
+++ b/tools/perf/tests/attr/test-stat-detailed-2
@@ -0,0 +1,155 @@
+[config]
+command = stat
+args    = -dd kill >/dev/null 2>&1
+ret     = 1
+
+
+# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_TASK_CLOCK
+[event1:base-stat]
+fd=1
+type=1
+config=1
+
+# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_CONTEXT_SWITCHES
+[event2:base-stat]
+fd=2
+type=1
+config=3
+
+# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_CPU_MIGRATIONS
+[event3:base-stat]
+fd=3
+type=1
+config=4
+
+# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_PAGE_FAULTS
+[event4:base-stat]
+fd=4
+type=1
+config=2
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_CPU_CYCLES
+[event5:base-stat]
+fd=5
+type=0
+config=0
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_FRONTEND
+[event6:base-stat]
+fd=6
+type=0
+config=7
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_BACKEND
+[event7:base-stat]
+fd=7
+type=0
+config=8
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_INSTRUCTIONS
+[event8:base-stat]
+fd=8
+type=0
+config=1
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_INSTRUCTIONS
+[event9:base-stat]
+fd=9
+type=0
+config=4
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_MISSES
+[event10:base-stat]
+fd=10
+type=0
+config=5
+
+# PERF_TYPE_HW_CACHE /
+#  PERF_COUNT_HW_CACHE_L1D                <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
+[event11:base-stat]
+fd=11
+type=3
+config=0
+
+# PERF_TYPE_HW_CACHE /
+#  PERF_COUNT_HW_CACHE_L1D                <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
+[event12:base-stat]
+fd=12
+type=3
+config=65536
+
+# PERF_TYPE_HW_CACHE /
+#  PERF_COUNT_HW_CACHE_LL                 <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
+[event13:base-stat]
+fd=13
+type=3
+config=2
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_LL                 <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
+[event14:base-stat]
+fd=14
+type=3
+config=65538
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_L1I                <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
+[event15:base-stat]
+fd=15
+type=3
+config=1
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_L1I                <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
+[event16:base-stat]
+fd=16
+type=3
+config=65537
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_DTLB               <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
+[event17:base-stat]
+fd=17
+type=3
+config=3
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_DTLB               <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
+[event18:base-stat]
+fd=18
+type=3
+config=65539
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_ITLB               <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
+[event19:base-stat]
+fd=19
+type=3
+config=4
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_ITLB               <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
+[event20:base-stat]
+fd=20
+type=3
+config=65540
diff --git a/tools/perf/tests/attr/test-stat-detailed-3 b/tools/perf/tests/attr/test-stat-detailed-3
new file mode 100644
index 00000000000..0a1f45bf7d7
--- /dev/null
+++ b/tools/perf/tests/attr/test-stat-detailed-3
@@ -0,0 +1,173 @@
+[config]
+command = stat
+args    = -ddd kill >/dev/null 2>&1
+ret     = 1
+
+
+# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_TASK_CLOCK
+[event1:base-stat]
+fd=1
+type=1
+config=1
+
+# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_CONTEXT_SWITCHES
+[event2:base-stat]
+fd=2
+type=1
+config=3
+
+# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_CPU_MIGRATIONS
+[event3:base-stat]
+fd=3
+type=1
+config=4
+
+# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_PAGE_FAULTS
+[event4:base-stat]
+fd=4
+type=1
+config=2
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_CPU_CYCLES
+[event5:base-stat]
+fd=5
+type=0
+config=0
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_FRONTEND
+[event6:base-stat]
+fd=6
+type=0
+config=7
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_BACKEND
+[event7:base-stat]
+fd=7
+type=0
+config=8
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_INSTRUCTIONS
+[event8:base-stat]
+fd=8
+type=0
+config=1
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_INSTRUCTIONS
+[event9:base-stat]
+fd=9
+type=0
+config=4
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_MISSES
+[event10:base-stat]
+fd=10
+type=0
+config=5
+
+# PERF_TYPE_HW_CACHE /
+#  PERF_COUNT_HW_CACHE_L1D                <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
+[event11:base-stat]
+fd=11
+type=3
+config=0
+
+# PERF_TYPE_HW_CACHE /
+#  PERF_COUNT_HW_CACHE_L1D                <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
+[event12:base-stat]
+fd=12
+type=3
+config=65536
+
+# PERF_TYPE_HW_CACHE /
+#  PERF_COUNT_HW_CACHE_LL                 <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
+[event13:base-stat]
+fd=13
+type=3
+config=2
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_LL                 <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
+[event14:base-stat]
+fd=14
+type=3
+config=65538
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_L1I                <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
+[event15:base-stat]
+fd=15
+type=3
+config=1
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_L1I                <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
+[event16:base-stat]
+fd=16
+type=3
+config=65537
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_DTLB               <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
+[event17:base-stat]
+fd=17
+type=3
+config=3
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_DTLB               <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
+[event18:base-stat]
+fd=18
+type=3
+config=65539
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_ITLB               <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
+[event19:base-stat]
+fd=19
+type=3
+config=4
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_ITLB               <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
+[event20:base-stat]
+fd=20
+type=3
+config=65540
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_L1D                <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_PREFETCH        <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
+[event21:base-stat]
+fd=21
+type=3
+config=512
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_L1D                <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_PREFETCH        <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
+[event22:base-stat]
+fd=22
+type=3
+config=66048
diff --git a/tools/perf/tests/attr/test-stat-group b/tools/perf/tests/attr/test-stat-group
new file mode 100644
index 00000000000..fdc1596a886
--- /dev/null
+++ b/tools/perf/tests/attr/test-stat-group
@@ -0,0 +1,15 @@
+[config]
+command = stat
+args    = --group -e cycles,instructions kill >/dev/null 2>&1
+ret     = 1
+
+[event-1:base-stat]
+fd=1
+group_fd=-1
+
+[event-2:base-stat]
+fd=2
+group_fd=1
+config=1
+disabled=0
+enable_on_exec=0
diff --git a/tools/perf/tests/attr/test-stat-group1 b/tools/perf/tests/attr/test-stat-group1
new file mode 100644
index 00000000000..2a1f86e4a90
--- /dev/null
+++ b/tools/perf/tests/attr/test-stat-group1
@@ -0,0 +1,15 @@
+[config]
+command = stat
+args    = -e '{cycles,instructions}' kill >/dev/null 2>&1
+ret     = 1
+
+[event-1:base-stat]
+fd=1
+group_fd=-1
+
+[event-2:base-stat]
+fd=2
+group_fd=1
+config=1
+disabled=0
+enable_on_exec=0
diff --git a/tools/perf/tests/attr/test-stat-no-inherit b/tools/perf/tests/attr/test-stat-no-inherit
new file mode 100644
index 00000000000..d54b2a1e3e2
--- /dev/null
+++ b/tools/perf/tests/attr/test-stat-no-inherit
@@ -0,0 +1,7 @@
+[config]
+command = stat
+args    = -i -e cycles kill >/dev/null 2>&1
+ret     = 1
+
+[event:base-stat]
+inherit=0
diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c
new file mode 100644
index 00000000000..aba09548919
--- /dev/null
+++ b/tools/perf/tests/bp_signal.c
@@ -0,0 +1,192 @@
+/*
+ * Inspired by breakpoint overflow test done by
+ * Vince Weaver <vincent.weaver@maine.edu> for 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>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <time.h>
+#include <fcntl.h>
+#include <signal.h>
+#include <sys/mman.h>
+#include <linux/compiler.h>
+#include <linux/hw_breakpoint.h>
+
+#include "tests.h"
+#include "debug.h"
+#include "perf.h"
+
+static int fd1;
+static int fd2;
+static int overflows;
+
+__attribute__ ((noinline))
+static int test_function(void)
+{
+	return time(NULL);
+}
+
+static void sig_handler(int signum __maybe_unused,
+			siginfo_t *oh __maybe_unused,
+			void *uc __maybe_unused)
+{
+	overflows++;
+
+	if (overflows > 10) {
+		/*
+		 * This should be executed only once during
+		 * this test, if we are here for the 10th
+		 * time, consider this the recursive issue.
+		 *
+		 * We can get out of here by disable events,
+		 * so no new SIGIO is delivered.
+		 */
+		ioctl(fd1, PERF_EVENT_IOC_DISABLE, 0);
+		ioctl(fd2, PERF_EVENT_IOC_DISABLE, 0);
+	}
+}
+
+static int bp_event(void *fn, int setup_signal)
+{
+	struct perf_event_attr pe;
+	int fd;
+
+	memset(&pe, 0, sizeof(struct perf_event_attr));
+	pe.type = PERF_TYPE_BREAKPOINT;
+	pe.size = sizeof(struct perf_event_attr);
+
+	pe.config = 0;
+	pe.bp_type = HW_BREAKPOINT_X;
+	pe.bp_addr = (unsigned long) fn;
+	pe.bp_len = sizeof(long);
+
+	pe.sample_period = 1;
+	pe.sample_type = PERF_SAMPLE_IP;
+	pe.wakeup_events = 1;
+
+	pe.disabled = 1;
+	pe.exclude_kernel = 1;
+	pe.exclude_hv = 1;
+
+	fd = sys_perf_event_open(&pe, 0, -1, -1, 0);
+	if (fd < 0) {
+		pr_debug("failed opening event %llx\n", pe.config);
+		return TEST_FAIL;
+	}
+
+	if (setup_signal) {
+		fcntl(fd, F_SETFL, O_RDWR|O_NONBLOCK|O_ASYNC);
+		fcntl(fd, F_SETSIG, SIGIO);
+		fcntl(fd, F_SETOWN, getpid());
+	}
+
+	ioctl(fd, PERF_EVENT_IOC_RESET, 0);
+
+	return fd;
+}
+
+static long long bp_count(int fd)
+{
+	long long count;
+	int ret;
+
+	ret = read(fd, &count, sizeof(long long));
+	if (ret != sizeof(long long)) {
+		pr_debug("failed to read: %d\n", ret);
+		return TEST_FAIL;
+	}
+
+	return count;
+}
+
+int test__bp_signal(void)
+{
+	struct sigaction sa;
+	long long count1, count2;
+
+	/* setup SIGIO signal handler */
+	memset(&sa, 0, sizeof(struct sigaction));
+	sa.sa_sigaction = (void *) sig_handler;
+	sa.sa_flags = SA_SIGINFO;
+
+	if (sigaction(SIGIO, &sa, NULL) < 0) {
+		pr_debug("failed setting up signal handler\n");
+		return TEST_FAIL;
+	}
+
+	/*
+	 * We create following events:
+	 *
+	 * fd1 - breakpoint event on test_function with SIGIO
+	 *       signal configured. We should get signal
+	 *       notification each time the breakpoint is hit
+	 *
+	 * fd2 - breakpoint event on sig_handler without SIGIO
+	 *       configured.
+	 *
+	 * Following processing should happen:
+	 *   - execute test_function
+	 *   - fd1 event breakpoint hit -> count1 == 1
+	 *   - SIGIO is delivered       -> overflows == 1
+	 *   - fd2 event breakpoint hit -> count2 == 1
+	 *
+	 * The test case check following error conditions:
+	 * - we get stuck in signal handler because of debug
+	 *   exception being triggered receursively due to
+	 *   the wrong RF EFLAG management
+	 *
+	 * - we never trigger the sig_handler breakpoint due
+	 *   to the rong RF EFLAG management
+	 *
+	 */
+
+	fd1 = bp_event(test_function, 1);
+	fd2 = bp_event(sig_handler, 0);
+
+	ioctl(fd1, PERF_EVENT_IOC_ENABLE, 0);
+	ioctl(fd2, PERF_EVENT_IOC_ENABLE, 0);
+
+	/*
+	 * Kick off the test by trigering 'fd1'
+	 * breakpoint.
+	 */
+	test_function();
+
+	ioctl(fd1, PERF_EVENT_IOC_DISABLE, 0);
+	ioctl(fd2, PERF_EVENT_IOC_DISABLE, 0);
+
+	count1 = bp_count(fd1);
+	count2 = bp_count(fd2);
+
+	close(fd1);
+	close(fd2);
+
+	pr_debug("count1 %lld, count2 %lld, overflow %d\n",
+		 count1, count2, overflows);
+
+	if (count1 != 1) {
+		if (count1 == 11)
+			pr_debug("failed: RF EFLAG recursion issue detected\n");
+		else
+			pr_debug("failed: wrong count for bp1%lld\n", count1);
+	}
+
+	if (overflows != 1)
+		pr_debug("failed: wrong overflow hit\n");
+
+	if (count2 != 1)
+		pr_debug("failed: wrong count for bp2\n");
+
+	return count1 == 1 && overflows == 1 && count2 == 1 ?
+		TEST_OK : TEST_FAIL;
+}
diff --git a/tools/perf/tests/bp_signal_overflow.c b/tools/perf/tests/bp_signal_overflow.c
new file mode 100644
index 00000000000..44ac8217970
--- /dev/null
+++ b/tools/perf/tests/bp_signal_overflow.c
@@ -0,0 +1,132 @@
+/*
+ * Originally done by Vince Weaver <vincent.weaver@maine.edu> for
+ * 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>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <time.h>
+#include <fcntl.h>
+#include <signal.h>
+#include <sys/mman.h>
+#include <linux/compiler.h>
+#include <linux/hw_breakpoint.h>
+
+#include "tests.h"
+#include "debug.h"
+#include "perf.h"
+
+static int overflows;
+
+__attribute__ ((noinline))
+static int test_function(void)
+{
+	return time(NULL);
+}
+
+static void sig_handler(int signum __maybe_unused,
+			siginfo_t *oh __maybe_unused,
+			void *uc __maybe_unused)
+{
+	overflows++;
+}
+
+static long long bp_count(int fd)
+{
+	long long count;
+	int ret;
+
+	ret = read(fd, &count, sizeof(long long));
+	if (ret != sizeof(long long)) {
+		pr_debug("failed to read: %d\n", ret);
+		return TEST_FAIL;
+	}
+
+	return count;
+}
+
+#define EXECUTIONS 10000
+#define THRESHOLD  100
+
+int test__bp_signal_overflow(void)
+{
+	struct perf_event_attr pe;
+	struct sigaction sa;
+	long long count;
+	int fd, i, fails = 0;
+
+	/* setup SIGIO signal handler */
+	memset(&sa, 0, sizeof(struct sigaction));
+	sa.sa_sigaction = (void *) sig_handler;
+	sa.sa_flags = SA_SIGINFO;
+
+	if (sigaction(SIGIO, &sa, NULL) < 0) {
+		pr_debug("failed setting up signal handler\n");
+		return TEST_FAIL;
+	}
+
+	memset(&pe, 0, sizeof(struct perf_event_attr));
+	pe.type = PERF_TYPE_BREAKPOINT;
+	pe.size = sizeof(struct perf_event_attr);
+
+	pe.config = 0;
+	pe.bp_type = HW_BREAKPOINT_X;
+	pe.bp_addr = (unsigned long) test_function;
+	pe.bp_len = sizeof(long);
+
+	pe.sample_period = THRESHOLD;
+	pe.sample_type = PERF_SAMPLE_IP;
+	pe.wakeup_events = 1;
+
+	pe.disabled = 1;
+	pe.exclude_kernel = 1;
+	pe.exclude_hv = 1;
+
+	fd = sys_perf_event_open(&pe, 0, -1, -1, 0);
+	if (fd < 0) {
+		pr_debug("failed opening event %llx\n", pe.config);
+		return TEST_FAIL;
+	}
+
+	fcntl(fd, F_SETFL, O_RDWR|O_NONBLOCK|O_ASYNC);
+	fcntl(fd, F_SETSIG, SIGIO);
+	fcntl(fd, F_SETOWN, getpid());
+
+	ioctl(fd, PERF_EVENT_IOC_RESET, 0);
+	ioctl(fd, PERF_EVENT_IOC_ENABLE, 0);
+
+	for (i = 0; i < EXECUTIONS; i++)
+		test_function();
+
+	ioctl(fd, PERF_EVENT_IOC_DISABLE, 0);
+
+	count = bp_count(fd);
+
+	close(fd);
+
+	pr_debug("count %lld, overflow %d\n",
+		 count, overflows);
+
+	if (count != EXECUTIONS) {
+		pr_debug("\tWrong number of executions %lld != %d\n",
+		count, EXECUTIONS);
+		fails++;
+	}
+
+	if (overflows != EXECUTIONS / THRESHOLD) {
+		pr_debug("\tWrong number of overflows %d != %d\n",
+		overflows, EXECUTIONS / THRESHOLD);
+		fails++;
+	}
+
+	return fails ? TEST_FAIL : TEST_OK;
+}
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
new file mode 100644
index 00000000000..6f8b01bc603
--- /dev/null
+++ b/tools/perf/tests/builtin-test.c
@@ -0,0 +1,307 @@
+/*
+ * builtin-test.c
+ *
+ * Builtin regression testing command: ever growing number of sanity tests
+ */
+#include <unistd.h>
+#include <string.h>
+#include "builtin.h"
+#include "intlist.h"
+#include "tests.h"
+#include "debug.h"
+#include "color.h"
+#include "parse-options.h"
+#include "symbol.h"
+
+static struct test {
+	const char *desc;
+	int (*func)(void);
+} tests[] = {
+	{
+		.desc = "vmlinux symtab matches kallsyms",
+		.func = test__vmlinux_matches_kallsyms,
+	},
+	{
+		.desc = "detect open syscall event",
+		.func = test__open_syscall_event,
+	},
+	{
+		.desc = "detect open syscall event on all cpus",
+		.func = test__open_syscall_event_on_all_cpus,
+	},
+	{
+		.desc = "read samples using the mmap interface",
+		.func = test__basic_mmap,
+	},
+	{
+		.desc = "parse events tests",
+		.func = test__parse_events,
+	},
+#if defined(__x86_64__) || defined(__i386__)
+	{
+		.desc = "x86 rdpmc test",
+		.func = test__rdpmc,
+	},
+#endif
+	{
+		.desc = "Validate PERF_RECORD_* events & perf_sample fields",
+		.func = test__PERF_RECORD,
+	},
+	{
+		.desc = "Test perf pmu format parsing",
+		.func = test__pmu,
+	},
+	{
+		.desc = "Test dso data read",
+		.func = test__dso_data,
+	},
+	{
+		.desc = "Test dso data cache",
+		.func = test__dso_data_cache,
+	},
+	{
+		.desc = "Test dso data reopen",
+		.func = test__dso_data_reopen,
+	},
+	{
+		.desc = "roundtrip evsel->name check",
+		.func = test__perf_evsel__roundtrip_name_test,
+	},
+	{
+		.desc = "Check parsing of sched tracepoints fields",
+		.func = test__perf_evsel__tp_sched_test,
+	},
+	{
+		.desc = "Generate and check syscalls:sys_enter_open event fields",
+		.func = test__syscall_open_tp_fields,
+	},
+	{
+		.desc = "struct perf_event_attr setup",
+		.func = test__attr,
+	},
+	{
+		.desc = "Test matching and linking multiple hists",
+		.func = test__hists_link,
+	},
+	{
+		.desc = "Try 'use perf' in python, checking link problems",
+		.func = test__python_use,
+	},
+	{
+		.desc = "Test breakpoint overflow signal handler",
+		.func = test__bp_signal,
+	},
+	{
+		.desc = "Test breakpoint overflow sampling",
+		.func = test__bp_signal_overflow,
+	},
+	{
+		.desc = "Test number of exit event of a simple workload",
+		.func = test__task_exit,
+	},
+	{
+		.desc = "Test software clock events have valid period values",
+		.func = test__sw_clock_freq,
+	},
+#if defined(__x86_64__) || defined(__i386__)
+	{
+		.desc = "Test converting perf time to TSC",
+		.func = test__perf_time_to_tsc,
+	},
+#endif
+	{
+		.desc = "Test object code reading",
+		.func = test__code_reading,
+	},
+	{
+		.desc = "Test sample parsing",
+		.func = test__sample_parsing,
+	},
+	{
+		.desc = "Test using a dummy software event to keep tracking",
+		.func = test__keep_tracking,
+	},
+	{
+		.desc = "Test parsing with no sample_id_all bit set",
+		.func = test__parse_no_sample_id_all,
+	},
+#if defined(__x86_64__) || defined(__i386__) || defined(__arm__)
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
+	{
+		.desc = "Test dwarf unwind",
+		.func = test__dwarf_unwind,
+	},
+#endif
+#endif
+	{
+		.desc = "Test filtering hist entries",
+		.func = test__hists_filter,
+	},
+	{
+		.desc = "Test mmap thread lookup",
+		.func = test__mmap_thread_lookup,
+	},
+	{
+		.desc = "Test thread mg sharing",
+		.func = test__thread_mg_share,
+	},
+	{
+		.desc = "Test output sorting of hist entries",
+		.func = test__hists_output,
+	},
+	{
+		.desc = "Test cumulation of child hist entries",
+		.func = test__hists_cumulate,
+	},
+	{
+		.func = NULL,
+	},
+};
+
+static bool perf_test__matches(int curr, int argc, const char *argv[])
+{
+	int i;
+
+	if (argc == 0)
+		return true;
+
+	for (i = 0; i < argc; ++i) {
+		char *end;
+		long nr = strtoul(argv[i], &end, 10);
+
+		if (*end == '\0') {
+			if (nr == curr + 1)
+				return true;
+			continue;
+		}
+
+		if (strstr(tests[curr].desc, argv[i]))
+			return true;
+	}
+
+	return false;
+}
+
+static int run_test(struct test *test)
+{
+	int status, err = -1, child = fork();
+
+	if (child < 0) {
+		pr_err("failed to fork test: %s\n", strerror(errno));
+		return -1;
+	}
+
+	if (!child) {
+		pr_debug("test child forked, pid %d\n", getpid());
+		err = test->func();
+		exit(err);
+	}
+
+	wait(&status);
+
+	if (WIFEXITED(status)) {
+		err = WEXITSTATUS(status);
+		pr_debug("test child finished with %d\n", err);
+	} else if (WIFSIGNALED(status)) {
+		err = -1;
+		pr_debug("test child interrupted\n");
+	}
+
+	return err;
+}
+
+static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist)
+{
+	int i = 0;
+	int width = 0;
+
+	while (tests[i].func) {
+		int len = strlen(tests[i].desc);
+
+		if (width < len)
+			width = len;
+		++i;
+	}
+
+	i = 0;
+	while (tests[i].func) {
+		int curr = i++, err;
+
+		if (!perf_test__matches(curr, argc, argv))
+			continue;
+
+		pr_info("%2d: %-*s:", i, width, tests[curr].desc);
+
+		if (intlist__find(skiplist, i)) {
+			color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip (user override)\n");
+			continue;
+		}
+
+		pr_debug("\n--- start ---\n");
+		err = run_test(&tests[curr]);
+		pr_debug("---- end ----\n%s:", tests[curr].desc);
+
+		switch (err) {
+		case TEST_OK:
+			pr_info(" Ok\n");
+			break;
+		case TEST_SKIP:
+			color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip\n");
+			break;
+		case TEST_FAIL:
+		default:
+			color_fprintf(stderr, PERF_COLOR_RED, " FAILED!\n");
+			break;
+		}
+	}
+
+	return 0;
+}
+
+static int perf_test__list(int argc, const char **argv)
+{
+	int i = 0;
+
+	while (tests[i].func) {
+		int curr = i++;
+
+		if (argc > 1 && !strstr(tests[curr].desc, argv[1]))
+			continue;
+
+		pr_info("%2d: %s\n", i, tests[curr].desc);
+	}
+
+	return 0;
+}
+
+int cmd_test(int argc, const char **argv, const char *prefix __maybe_unused)
+{
+	const char * const test_usage[] = {
+	"perf test [<options>] [{list <test-name-fragment>|[<test-name-fragments>|<test-numbers>]}]",
+	NULL,
+	};
+	const char *skip = NULL;
+	const struct option test_options[] = {
+	OPT_STRING('s', "skip", &skip, "tests", "tests to skip"),
+	OPT_INCR('v', "verbose", &verbose,
+		    "be more verbose (show symbol address, etc)"),
+	OPT_END()
+	};
+	struct intlist *skiplist = NULL;
+
+	argc = parse_options(argc, argv, test_options, test_usage, 0);
+	if (argc >= 1 && !strcmp(argv[0], "list"))
+		return perf_test__list(argc, argv);
+
+	symbol_conf.priv_size = sizeof(int);
+	symbol_conf.sort_by_name = true;
+	symbol_conf.try_vmlinux_path = true;
+
+	if (symbol__init() < 0)
+		return -1;
+
+	if (skip != NULL)
+		skiplist = intlist__new(skip);
+
+	return __cmd_test(argc, argv, skiplist);
+}
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
new file mode 100644
index 00000000000..67f2d632355
--- /dev/null
+++ b/tools/perf/tests/code-reading.c
@@ -0,0 +1,581 @@
+#include <linux/types.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <ctype.h>
+#include <string.h>
+
+#include "parse-events.h"
+#include "evlist.h"
+#include "evsel.h"
+#include "thread_map.h"
+#include "cpumap.h"
+#include "machine.h"
+#include "event.h"
+#include "thread.h"
+
+#include "tests.h"
+
+#define BUFSZ	1024
+#define READLEN	128
+
+struct state {
+	u64 done[1024];
+	size_t done_cnt;
+};
+
+static unsigned int hex(char c)
+{
+	if (c >= '0' && c <= '9')
+		return c - '0';
+	if (c >= 'a' && c <= 'f')
+		return c - 'a' + 10;
+	return c - 'A' + 10;
+}
+
+static void read_objdump_line(const char *line, size_t line_len, void **buf,
+			      size_t *len)
+{
+	const char *p;
+	size_t i;
+
+	/* Skip to a colon */
+	p = strchr(line, ':');
+	if (!p)
+		return;
+	i = p + 1 - line;
+
+	/* Read bytes */
+	while (*len) {
+		char c1, c2;
+
+		/* Skip spaces */
+		for (; i < line_len; i++) {
+			if (!isspace(line[i]))
+				break;
+		}
+		/* Get 2 hex digits */
+		if (i >= line_len || !isxdigit(line[i]))
+			break;
+		c1 = line[i++];
+		if (i >= line_len || !isxdigit(line[i]))
+			break;
+		c2 = line[i++];
+		/* Followed by a space */
+		if (i < line_len && line[i] && !isspace(line[i]))
+			break;
+		/* Store byte */
+		*(unsigned char *)*buf = (hex(c1) << 4) | hex(c2);
+		*buf += 1;
+		*len -= 1;
+	}
+}
+
+static int read_objdump_output(FILE *f, void **buf, size_t *len)
+{
+	char *line = NULL;
+	size_t line_len;
+	ssize_t ret;
+	int err = 0;
+
+	while (1) {
+		ret = getline(&line, &line_len, f);
+		if (feof(f))
+			break;
+		if (ret < 0) {
+			pr_debug("getline failed\n");
+			err = -1;
+			break;
+		}
+		read_objdump_line(line, ret, buf, len);
+	}
+
+	free(line);
+
+	return err;
+}
+
+static int read_via_objdump(const char *filename, u64 addr, void *buf,
+			    size_t len)
+{
+	char cmd[PATH_MAX * 2];
+	const char *fmt;
+	FILE *f;
+	int ret;
+
+	fmt = "%s -d --start-address=0x%"PRIx64" --stop-address=0x%"PRIx64" %s";
+	ret = snprintf(cmd, sizeof(cmd), fmt, "objdump", addr, addr + len,
+		       filename);
+	if (ret <= 0 || (size_t)ret >= sizeof(cmd))
+		return -1;
+
+	pr_debug("Objdump command is: %s\n", cmd);
+
+	/* Ignore objdump errors */
+	strcat(cmd, " 2>/dev/null");
+
+	f = popen(cmd, "r");
+	if (!f) {
+		pr_debug("popen failed\n");
+		return -1;
+	}
+
+	ret = read_objdump_output(f, &buf, &len);
+	if (len) {
+		pr_debug("objdump read too few bytes\n");
+		if (!ret)
+			ret = len;
+	}
+
+	pclose(f);
+
+	return ret;
+}
+
+static int read_object_code(u64 addr, size_t len, u8 cpumode,
+			    struct thread *thread, struct machine *machine,
+			    struct state *state)
+{
+	struct addr_location al;
+	unsigned char buf1[BUFSZ];
+	unsigned char buf2[BUFSZ];
+	size_t ret_len;
+	u64 objdump_addr;
+	int ret;
+
+	pr_debug("Reading object code for memory address: %#"PRIx64"\n", addr);
+
+	thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION, addr,
+			      &al);
+	if (!al.map || !al.map->dso) {
+		pr_debug("thread__find_addr_map failed\n");
+		return -1;
+	}
+
+	pr_debug("File is: %s\n", al.map->dso->long_name);
+
+	if (al.map->dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS &&
+	    !dso__is_kcore(al.map->dso)) {
+		pr_debug("Unexpected kernel address - skipping\n");
+		return 0;
+	}
+
+	pr_debug("On file address is: %#"PRIx64"\n", al.addr);
+
+	if (len > BUFSZ)
+		len = BUFSZ;
+
+	/* Do not go off the map */
+	if (addr + len > al.map->end)
+		len = al.map->end - addr;
+
+	/* Read the object code using perf */
+	ret_len = dso__data_read_offset(al.map->dso, machine, al.addr, buf1,
+					len);
+	if (ret_len != len) {
+		pr_debug("dso__data_read_offset failed\n");
+		return -1;
+	}
+
+	/*
+	 * Converting addresses for use by objdump requires more information.
+	 * map__load() does that.  See map__rip_2objdump() for details.
+	 */
+	if (map__load(al.map, NULL))
+		return -1;
+
+	/* objdump struggles with kcore - try each map only once */
+	if (dso__is_kcore(al.map->dso)) {
+		size_t d;
+
+		for (d = 0; d < state->done_cnt; d++) {
+			if (state->done[d] == al.map->start) {
+				pr_debug("kcore map tested already");
+				pr_debug(" - skipping\n");
+				return 0;
+			}
+		}
+		if (state->done_cnt >= ARRAY_SIZE(state->done)) {
+			pr_debug("Too many kcore maps - skipping\n");
+			return 0;
+		}
+		state->done[state->done_cnt++] = al.map->start;
+	}
+
+	/* Read the object code using objdump */
+	objdump_addr = map__rip_2objdump(al.map, al.addr);
+	ret = read_via_objdump(al.map->dso->long_name, objdump_addr, buf2, len);
+	if (ret > 0) {
+		/*
+		 * The kernel maps are inaccurate - assume objdump is right in
+		 * that case.
+		 */
+		if (cpumode == PERF_RECORD_MISC_KERNEL ||
+		    cpumode == PERF_RECORD_MISC_GUEST_KERNEL) {
+			len -= ret;
+			if (len) {
+				pr_debug("Reducing len to %zu\n", len);
+			} else if (dso__is_kcore(al.map->dso)) {
+				/*
+				 * objdump cannot handle very large segments
+				 * that may be found in kcore.
+				 */
+				pr_debug("objdump failed for kcore");
+				pr_debug(" - skipping\n");
+				return 0;
+			} else {
+				return -1;
+			}
+		}
+	}
+	if (ret < 0) {
+		pr_debug("read_via_objdump failed\n");
+		return -1;
+	}
+
+	/* The results should be identical */
+	if (memcmp(buf1, buf2, len)) {
+		pr_debug("Bytes read differ from those read by objdump\n");
+		return -1;
+	}
+	pr_debug("Bytes read match those read by objdump\n");
+
+	return 0;
+}
+
+static int process_sample_event(struct machine *machine,
+				struct perf_evlist *evlist,
+				union perf_event *event, struct state *state)
+{
+	struct perf_sample sample;
+	struct thread *thread;
+	u8 cpumode;
+
+	if (perf_evlist__parse_sample(evlist, event, &sample)) {
+		pr_debug("perf_evlist__parse_sample failed\n");
+		return -1;
+	}
+
+	thread = machine__findnew_thread(machine, sample.pid, sample.tid);
+	if (!thread) {
+		pr_debug("machine__findnew_thread failed\n");
+		return -1;
+	}
+
+	cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+
+	return read_object_code(sample.ip, READLEN, cpumode, thread, machine,
+				state);
+}
+
+static int process_event(struct machine *machine, struct perf_evlist *evlist,
+			 union perf_event *event, struct state *state)
+{
+	if (event->header.type == PERF_RECORD_SAMPLE)
+		return process_sample_event(machine, evlist, event, state);
+
+	if (event->header.type == PERF_RECORD_THROTTLE ||
+	    event->header.type == PERF_RECORD_UNTHROTTLE)
+		return 0;
+
+	if (event->header.type < PERF_RECORD_MAX) {
+		int ret;
+
+		ret = machine__process_event(machine, event, NULL);
+		if (ret < 0)
+			pr_debug("machine__process_event failed, event type %u\n",
+				 event->header.type);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int process_events(struct machine *machine, struct perf_evlist *evlist,
+			  struct state *state)
+{
+	union perf_event *event;
+	int i, ret;
+
+	for (i = 0; i < evlist->nr_mmaps; i++) {
+		while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
+			ret = process_event(machine, evlist, event, state);
+			perf_evlist__mmap_consume(evlist, i);
+			if (ret < 0)
+				return ret;
+		}
+	}
+	return 0;
+}
+
+static int comp(const void *a, const void *b)
+{
+	return *(int *)a - *(int *)b;
+}
+
+static void do_sort_something(void)
+{
+	int buf[40960], i;
+
+	for (i = 0; i < (int)ARRAY_SIZE(buf); i++)
+		buf[i] = ARRAY_SIZE(buf) - i - 1;
+
+	qsort(buf, ARRAY_SIZE(buf), sizeof(int), comp);
+
+	for (i = 0; i < (int)ARRAY_SIZE(buf); i++) {
+		if (buf[i] != i) {
+			pr_debug("qsort failed\n");
+			break;
+		}
+	}
+}
+
+static void sort_something(void)
+{
+	int i;
+
+	for (i = 0; i < 10; i++)
+		do_sort_something();
+}
+
+static void syscall_something(void)
+{
+	int pipefd[2];
+	int i;
+
+	for (i = 0; i < 1000; i++) {
+		if (pipe(pipefd) < 0) {
+			pr_debug("pipe failed\n");
+			break;
+		}
+		close(pipefd[1]);
+		close(pipefd[0]);
+	}
+}
+
+static void fs_something(void)
+{
+	const char *test_file_name = "temp-perf-code-reading-test-file--";
+	FILE *f;
+	int i;
+
+	for (i = 0; i < 1000; i++) {
+		f = fopen(test_file_name, "w+");
+		if (f) {
+			fclose(f);
+			unlink(test_file_name);
+		}
+	}
+}
+
+static void do_something(void)
+{
+	fs_something();
+
+	sort_something();
+
+	syscall_something();
+}
+
+enum {
+	TEST_CODE_READING_OK,
+	TEST_CODE_READING_NO_VMLINUX,
+	TEST_CODE_READING_NO_KCORE,
+	TEST_CODE_READING_NO_ACCESS,
+	TEST_CODE_READING_NO_KERNEL_OBJ,
+};
+
+static int do_test_code_reading(bool try_kcore)
+{
+	struct machines machines;
+	struct machine *machine;
+	struct thread *thread;
+	struct record_opts opts = {
+		.mmap_pages	     = UINT_MAX,
+		.user_freq	     = UINT_MAX,
+		.user_interval	     = ULLONG_MAX,
+		.freq		     = 4000,
+		.target		     = {
+			.uses_mmap   = true,
+		},
+	};
+	struct state state = {
+		.done_cnt = 0,
+	};
+	struct thread_map *threads = NULL;
+	struct cpu_map *cpus = NULL;
+	struct perf_evlist *evlist = NULL;
+	struct perf_evsel *evsel = NULL;
+	int err = -1, ret;
+	pid_t pid;
+	struct map *map;
+	bool have_vmlinux, have_kcore, excl_kernel = false;
+
+	pid = getpid();
+
+	machines__init(&machines);
+	machine = &machines.host;
+
+	ret = machine__create_kernel_maps(machine);
+	if (ret < 0) {
+		pr_debug("machine__create_kernel_maps failed\n");
+		goto out_err;
+	}
+
+	/* Force the use of kallsyms instead of vmlinux to try kcore */
+	if (try_kcore)
+		symbol_conf.kallsyms_name = "/proc/kallsyms";
+
+	/* Load kernel map */
+	map = machine->vmlinux_maps[MAP__FUNCTION];
+	ret = map__load(map, NULL);
+	if (ret < 0) {
+		pr_debug("map__load failed\n");
+		goto out_err;
+	}
+	have_vmlinux = dso__is_vmlinux(map->dso);
+	have_kcore = dso__is_kcore(map->dso);
+
+	/* 2nd time through we just try kcore */
+	if (try_kcore && !have_kcore)
+		return TEST_CODE_READING_NO_KCORE;
+
+	/* No point getting kernel events if there is no kernel object */
+	if (!have_vmlinux && !have_kcore)
+		excl_kernel = true;
+
+	threads = thread_map__new_by_tid(pid);
+	if (!threads) {
+		pr_debug("thread_map__new_by_tid failed\n");
+		goto out_err;
+	}
+
+	ret = perf_event__synthesize_thread_map(NULL, threads,
+						perf_event__process, machine, false);
+	if (ret < 0) {
+		pr_debug("perf_event__synthesize_thread_map failed\n");
+		goto out_err;
+	}
+
+	thread = machine__findnew_thread(machine, pid, pid);
+	if (!thread) {
+		pr_debug("machine__findnew_thread failed\n");
+		goto out_err;
+	}
+
+	cpus = cpu_map__new(NULL);
+	if (!cpus) {
+		pr_debug("cpu_map__new failed\n");
+		goto out_err;
+	}
+
+	while (1) {
+		const char *str;
+
+		evlist = perf_evlist__new();
+		if (!evlist) {
+			pr_debug("perf_evlist__new failed\n");
+			goto out_err;
+		}
+
+		perf_evlist__set_maps(evlist, cpus, threads);
+
+		if (excl_kernel)
+			str = "cycles:u";
+		else
+			str = "cycles";
+		pr_debug("Parsing event '%s'\n", str);
+		ret = parse_events(evlist, str);
+		if (ret < 0) {
+			pr_debug("parse_events failed\n");
+			goto out_err;
+		}
+
+		perf_evlist__config(evlist, &opts);
+
+		evsel = perf_evlist__first(evlist);
+
+		evsel->attr.comm = 1;
+		evsel->attr.disabled = 1;
+		evsel->attr.enable_on_exec = 0;
+
+		ret = perf_evlist__open(evlist);
+		if (ret < 0) {
+			if (!excl_kernel) {
+				excl_kernel = true;
+				perf_evlist__set_maps(evlist, NULL, NULL);
+				perf_evlist__delete(evlist);
+				evlist = NULL;
+				continue;
+			}
+			pr_debug("perf_evlist__open failed\n");
+			goto out_err;
+		}
+		break;
+	}
+
+	ret = perf_evlist__mmap(evlist, UINT_MAX, false);
+	if (ret < 0) {
+		pr_debug("perf_evlist__mmap failed\n");
+		goto out_err;
+	}
+
+	perf_evlist__enable(evlist);
+
+	do_something();
+
+	perf_evlist__disable(evlist);
+
+	ret = process_events(machine, evlist, &state);
+	if (ret < 0)
+		goto out_err;
+
+	if (!have_vmlinux && !have_kcore && !try_kcore)
+		err = TEST_CODE_READING_NO_KERNEL_OBJ;
+	else if (!have_vmlinux && !try_kcore)
+		err = TEST_CODE_READING_NO_VMLINUX;
+	else if (excl_kernel)
+		err = TEST_CODE_READING_NO_ACCESS;
+	else
+		err = TEST_CODE_READING_OK;
+out_err:
+	if (evlist) {
+		perf_evlist__delete(evlist);
+	} else {
+		cpu_map__delete(cpus);
+		thread_map__delete(threads);
+	}
+	machines__destroy_kernel_maps(&machines);
+	machine__delete_threads(machine);
+	machines__exit(&machines);
+
+	return err;
+}
+
+int test__code_reading(void)
+{
+	int ret;
+
+	ret = do_test_code_reading(false);
+	if (!ret)
+		ret = do_test_code_reading(true);
+
+	switch (ret) {
+	case TEST_CODE_READING_OK:
+		return 0;
+	case TEST_CODE_READING_NO_VMLINUX:
+		fprintf(stderr, " (no vmlinux)");
+		return 0;
+	case TEST_CODE_READING_NO_KCORE:
+		fprintf(stderr, " (no kcore)");
+		return 0;
+	case TEST_CODE_READING_NO_ACCESS:
+		fprintf(stderr, " (no access)");
+		return 0;
+	case TEST_CODE_READING_NO_KERNEL_OBJ:
+		fprintf(stderr, " (no kernel obj)");
+		return 0;
+	default:
+		return -1;
+	};
+}
diff --git a/tools/perf/tests/dso-data.c b/tools/perf/tests/dso-data.c
new file mode 100644
index 00000000000..630808cd7cc
--- /dev/null
+++ b/tools/perf/tests/dso-data.c
@@ -0,0 +1,358 @@
+#include <stdlib.h>
+#include <linux/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <string.h>
+#include <sys/time.h>
+#include <sys/resource.h>
+#include <api/fs/fs.h>
+#include "util.h"
+#include "machine.h"
+#include "symbol.h"
+#include "tests.h"
+
+static char *test_file(int size)
+{
+#define TEMPL "/tmp/perf-test-XXXXXX"
+	static char buf_templ[sizeof(TEMPL)];
+	char *templ = buf_templ;
+	int fd, i;
+	unsigned char *buf;
+
+	strcpy(buf_templ, TEMPL);
+#undef TEMPL
+
+	fd = mkstemp(templ);
+	if (fd < 0) {
+		perror("mkstemp failed");
+		return NULL;
+	}
+
+	buf = malloc(size);
+	if (!buf) {
+		close(fd);
+		return NULL;
+	}
+
+	for (i = 0; i < size; i++)
+		buf[i] = (unsigned char) ((int) i % 10);
+
+	if (size != write(fd, buf, size))
+		templ = NULL;
+
+	free(buf);
+	close(fd);
+	return templ;
+}
+
+#define TEST_FILE_SIZE (DSO__DATA_CACHE_SIZE * 20)
+
+struct test_data_offset {
+	off_t offset;
+	u8 data[10];
+	int size;
+};
+
+struct test_data_offset offsets[] = {
+	/* Fill first cache page. */
+	{
+		.offset = 10,
+		.data   = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 },
+		.size   = 10,
+	},
+	/* Read first cache page. */
+	{
+		.offset = 10,
+		.data   = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 },
+		.size   = 10,
+	},
+	/* Fill cache boundary pages. */
+	{
+		.offset = DSO__DATA_CACHE_SIZE - DSO__DATA_CACHE_SIZE % 10,
+		.data   = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 },
+		.size   = 10,
+	},
+	/* Read cache boundary pages. */
+	{
+		.offset = DSO__DATA_CACHE_SIZE - DSO__DATA_CACHE_SIZE % 10,
+		.data   = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 },
+		.size   = 10,
+	},
+	/* Fill final cache page. */
+	{
+		.offset = TEST_FILE_SIZE - 10,
+		.data   = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 },
+		.size   = 10,
+	},
+	/* Read final cache page. */
+	{
+		.offset = TEST_FILE_SIZE - 10,
+		.data   = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 },
+		.size   = 10,
+	},
+	/* Read final cache page. */
+	{
+		.offset = TEST_FILE_SIZE - 3,
+		.data   = { 7, 8, 9, 0, 0, 0, 0, 0, 0, 0 },
+		.size   = 3,
+	},
+};
+
+int test__dso_data(void)
+{
+	struct machine machine;
+	struct dso *dso;
+	char *file = test_file(TEST_FILE_SIZE);
+	size_t i;
+
+	TEST_ASSERT_VAL("No test file", file);
+
+	memset(&machine, 0, sizeof(machine));
+
+	dso = dso__new((const char *)file);
+
+	/* Basic 10 bytes tests. */
+	for (i = 0; i < ARRAY_SIZE(offsets); i++) {
+		struct test_data_offset *data = &offsets[i];
+		ssize_t size;
+		u8 buf[10];
+
+		memset(buf, 0, 10);
+		size = dso__data_read_offset(dso, &machine, data->offset,
+				     buf, 10);
+
+		TEST_ASSERT_VAL("Wrong size", size == data->size);
+		TEST_ASSERT_VAL("Wrong data", !memcmp(buf, data->data, 10));
+	}
+
+	/* Read cross multiple cache pages. */
+	{
+		ssize_t size;
+		int c;
+		u8 *buf;
+
+		buf = malloc(TEST_FILE_SIZE);
+		TEST_ASSERT_VAL("ENOMEM\n", buf);
+
+		/* First iteration to fill caches, second one to read them. */
+		for (c = 0; c < 2; c++) {
+			memset(buf, 0, TEST_FILE_SIZE);
+			size = dso__data_read_offset(dso, &machine, 10,
+						     buf, TEST_FILE_SIZE);
+
+			TEST_ASSERT_VAL("Wrong size",
+				size == (TEST_FILE_SIZE - 10));
+
+			for (i = 0; i < (size_t)size; i++)
+				TEST_ASSERT_VAL("Wrong data",
+					buf[i] == (i % 10));
+		}
+
+		free(buf);
+	}
+
+	dso__delete(dso);
+	unlink(file);
+	return 0;
+}
+
+static long open_files_cnt(void)
+{
+	char path[PATH_MAX];
+	struct dirent *dent;
+	DIR *dir;
+	long nr = 0;
+
+	scnprintf(path, PATH_MAX, "%s/self/fd", procfs__mountpoint());
+	pr_debug("fd path: %s\n", path);
+
+	dir = opendir(path);
+	TEST_ASSERT_VAL("failed to open fd directory", dir);
+
+	while ((dent = readdir(dir)) != NULL) {
+		if (!strcmp(dent->d_name, ".") ||
+		    !strcmp(dent->d_name, ".."))
+			continue;
+
+		nr++;
+	}
+
+	closedir(dir);
+	return nr - 1;
+}
+
+static struct dso **dsos;
+
+static int dsos__create(int cnt, int size)
+{
+	int i;
+
+	dsos = malloc(sizeof(dsos) * cnt);
+	TEST_ASSERT_VAL("failed to alloc dsos array", dsos);
+
+	for (i = 0; i < cnt; i++) {
+		char *file;
+
+		file = test_file(size);
+		TEST_ASSERT_VAL("failed to get dso file", file);
+
+		dsos[i] = dso__new(file);
+		TEST_ASSERT_VAL("failed to get dso", dsos[i]);
+	}
+
+	return 0;
+}
+
+static void dsos__delete(int cnt)
+{
+	int i;
+
+	for (i = 0; i < cnt; i++) {
+		struct dso *dso = dsos[i];
+
+		unlink(dso->name);
+		dso__delete(dso);
+	}
+
+	free(dsos);
+}
+
+static int set_fd_limit(int n)
+{
+	struct rlimit rlim;
+
+	if (getrlimit(RLIMIT_NOFILE, &rlim))
+		return -1;
+
+	pr_debug("file limit %ld, new %d\n", (long) rlim.rlim_cur, n);
+
+	rlim.rlim_cur = n;
+	return setrlimit(RLIMIT_NOFILE, &rlim);
+}
+
+int test__dso_data_cache(void)
+{
+	struct machine machine;
+	long nr_end, nr = open_files_cnt();
+	int dso_cnt, limit, i, fd;
+
+	memset(&machine, 0, sizeof(machine));
+
+	/* set as system limit */
+	limit = nr * 4;
+	TEST_ASSERT_VAL("failed to set file limit", !set_fd_limit(limit));
+
+	/* and this is now our dso open FDs limit + 1 extra */
+	dso_cnt = limit / 2 + 1;
+	TEST_ASSERT_VAL("failed to create dsos\n",
+		!dsos__create(dso_cnt, TEST_FILE_SIZE));
+
+	for (i = 0; i < (dso_cnt - 1); i++) {
+		struct dso *dso = dsos[i];
+
+		/*
+		 * Open dsos via dso__data_fd or dso__data_read_offset.
+		 * Both opens the data file and keep it open.
+		 */
+		if (i % 2) {
+			fd = dso__data_fd(dso, &machine);
+			TEST_ASSERT_VAL("failed to get fd", fd > 0);
+		} else {
+			#define BUFSIZE 10
+			u8 buf[BUFSIZE];
+			ssize_t n;
+
+			n = dso__data_read_offset(dso, &machine, 0, buf, BUFSIZE);
+			TEST_ASSERT_VAL("failed to read dso", n == BUFSIZE);
+		}
+	}
+
+	/* open +1 dso over the allowed limit */
+	fd = dso__data_fd(dsos[i], &machine);
+	TEST_ASSERT_VAL("failed to get fd", fd > 0);
+
+	/* should force the first one to be closed */
+	TEST_ASSERT_VAL("failed to close dsos[0]", dsos[0]->data.fd == -1);
+
+	/* cleanup everything */
+	dsos__delete(dso_cnt);
+
+	/* Make sure we did not leak any file descriptor. */
+	nr_end = open_files_cnt();
+	pr_debug("nr start %ld, nr stop %ld\n", nr, nr_end);
+	TEST_ASSERT_VAL("failed leadking files", nr == nr_end);
+	return 0;
+}
+
+int test__dso_data_reopen(void)
+{
+	struct machine machine;
+	long nr_end, nr = open_files_cnt();
+	int fd, fd_extra;
+
+#define dso_0 (dsos[0])
+#define dso_1 (dsos[1])
+#define dso_2 (dsos[2])
+
+	memset(&machine, 0, sizeof(machine));
+
+	/*
+	 * Test scenario:
+	 * - create 3 dso objects
+	 * - set process file descriptor limit to current
+	 *   files count + 3
+	 * - test that the first dso gets closed when we
+	 *   reach the files count limit
+	 */
+
+	/* Make sure we are able to open 3 fds anyway */
+	TEST_ASSERT_VAL("failed to set file limit",
+			!set_fd_limit((nr + 3)));
+
+	TEST_ASSERT_VAL("failed to create dsos\n", !dsos__create(3, TEST_FILE_SIZE));
+
+	/* open dso_0 */
+	fd = dso__data_fd(dso_0, &machine);
+	TEST_ASSERT_VAL("failed to get fd", fd > 0);
+
+	/* open dso_1 */
+	fd = dso__data_fd(dso_1, &machine);
+	TEST_ASSERT_VAL("failed to get fd", fd > 0);
+
+	/*
+	 * open extra file descriptor and we just
+	 * reached the files count limit
+	 */
+	fd_extra = open("/dev/null", O_RDONLY);
+	TEST_ASSERT_VAL("failed to open extra fd", fd_extra > 0);
+
+	/* open dso_2 */
+	fd = dso__data_fd(dso_2, &machine);
+	TEST_ASSERT_VAL("failed to get fd", fd > 0);
+
+	/*
+	 * dso_0 should get closed, because we reached
+	 * the file descriptor limit
+	 */
+	TEST_ASSERT_VAL("failed to close dso_0", dso_0->data.fd == -1);
+
+	/* open dso_0 */
+	fd = dso__data_fd(dso_0, &machine);
+	TEST_ASSERT_VAL("failed to get fd", fd > 0);
+
+	/*
+	 * dso_1 should get closed, because we reached
+	 * the file descriptor limit
+	 */
+	TEST_ASSERT_VAL("failed to close dso_1", dso_1->data.fd == -1);
+
+	/* cleanup everything */
+	close(fd_extra);
+	dsos__delete(3);
+
+	/* Make sure we did not leak any file descriptor. */
+	nr_end = open_files_cnt();
+	pr_debug("nr start %ld, nr stop %ld\n", nr, nr_end);
+	TEST_ASSERT_VAL("failed leadking files", nr == nr_end);
+	return 0;
+}
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
new file mode 100644
index 00000000000..96adb730b74
--- /dev/null
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -0,0 +1,144 @@
+#include <linux/compiler.h>
+#include <linux/types.h>
+#include <unistd.h>
+#include "tests.h"
+#include "debug.h"
+#include "machine.h"
+#include "event.h"
+#include "unwind.h"
+#include "perf_regs.h"
+#include "map.h"
+#include "thread.h"
+
+static int mmap_handler(struct perf_tool *tool __maybe_unused,
+			union perf_event *event,
+			struct perf_sample *sample __maybe_unused,
+			struct machine *machine)
+{
+	return machine__process_mmap2_event(machine, event, NULL);
+}
+
+static int init_live_machine(struct machine *machine)
+{
+	union perf_event event;
+	pid_t pid = getpid();
+
+	return perf_event__synthesize_mmap_events(NULL, &event, pid, pid,
+						  mmap_handler, machine, true);
+}
+
+#define MAX_STACK 6
+
+static int unwind_entry(struct unwind_entry *entry, void *arg)
+{
+	unsigned long *cnt = (unsigned long *) arg;
+	char *symbol = entry->sym ? entry->sym->name : NULL;
+	static const char *funcs[MAX_STACK] = {
+		"test__arch_unwind_sample",
+		"unwind_thread",
+		"krava_3",
+		"krava_2",
+		"krava_1",
+		"test__dwarf_unwind"
+	};
+
+	if (*cnt >= MAX_STACK) {
+		pr_debug("failed: crossed the max stack value %d\n", MAX_STACK);
+		return -1;
+	}
+
+	if (!symbol) {
+		pr_debug("failed: got unresolved address 0x%" PRIx64 "\n",
+			 entry->ip);
+		return -1;
+	}
+
+	pr_debug("got: %s 0x%" PRIx64 "\n", symbol, entry->ip);
+	return strcmp((const char *) symbol, funcs[(*cnt)++]);
+}
+
+__attribute__ ((noinline))
+static int unwind_thread(struct thread *thread, struct machine *machine)
+{
+	struct perf_sample sample;
+	unsigned long cnt = 0;
+	int err = -1;
+
+	memset(&sample, 0, sizeof(sample));
+
+	if (test__arch_unwind_sample(&sample, thread)) {
+		pr_debug("failed to get unwind sample\n");
+		goto out;
+	}
+
+	err = unwind__get_entries(unwind_entry, &cnt, machine, thread,
+				  &sample, MAX_STACK);
+	if (err)
+		pr_debug("unwind failed\n");
+	else if (cnt != MAX_STACK) {
+		pr_debug("got wrong number of stack entries %lu != %d\n",
+			 cnt, MAX_STACK);
+		err = -1;
+	}
+
+ out:
+	free(sample.user_stack.data);
+	free(sample.user_regs.regs);
+	return err;
+}
+
+__attribute__ ((noinline))
+static int krava_3(struct thread *thread, struct machine *machine)
+{
+	return unwind_thread(thread, machine);
+}
+
+__attribute__ ((noinline))
+static int krava_2(struct thread *thread, struct machine *machine)
+{
+	return krava_3(thread, machine);
+}
+
+__attribute__ ((noinline))
+static int krava_1(struct thread *thread, struct machine *machine)
+{
+	return krava_2(thread, machine);
+}
+
+int test__dwarf_unwind(void)
+{
+	struct machines machines;
+	struct machine *machine;
+	struct thread *thread;
+	int err = -1;
+
+	machines__init(&machines);
+
+	machine = machines__find(&machines, HOST_KERNEL_ID);
+	if (!machine) {
+		pr_err("Could not get machine\n");
+		return -1;
+	}
+
+	if (init_live_machine(machine)) {
+		pr_err("Could not init machine\n");
+		goto out;
+	}
+
+	if (verbose > 1)
+		machine__fprintf(machine, stderr);
+
+	thread = machine__find_thread(machine, getpid(), getpid());
+	if (!thread) {
+		pr_err("Could not get thread\n");
+		goto out;
+	}
+
+	err = krava_1(thread, machine);
+
+ out:
+	machine__delete_threads(machine);
+	machine__exit(machine);
+	machines__exit(&machines);
+	return err;
+}
diff --git a/tools/perf/tests/evsel-roundtrip-name.c b/tools/perf/tests/evsel-roundtrip-name.c
new file mode 100644
index 00000000000..465cdbc345c
--- /dev/null
+++ b/tools/perf/tests/evsel-roundtrip-name.c
@@ -0,0 +1,114 @@
+#include "evlist.h"
+#include "evsel.h"
+#include "parse-events.h"
+#include "tests.h"
+
+static int perf_evsel__roundtrip_cache_name_test(void)
+{
+	char name[128];
+	int type, op, err = 0, ret = 0, i, idx;
+	struct perf_evsel *evsel;
+	struct perf_evlist *evlist = perf_evlist__new();
+
+        if (evlist == NULL)
+                return -ENOMEM;
+
+	for (type = 0; type < PERF_COUNT_HW_CACHE_MAX; type++) {
+		for (op = 0; op < PERF_COUNT_HW_CACHE_OP_MAX; op++) {
+			/* skip invalid cache type */
+			if (!perf_evsel__is_cache_op_valid(type, op))
+				continue;
+
+			for (i = 0; i < PERF_COUNT_HW_CACHE_RESULT_MAX; i++) {
+				__perf_evsel__hw_cache_type_op_res_name(type, op, i,
+									name, sizeof(name));
+				err = parse_events(evlist, name);
+				if (err)
+					ret = err;
+			}
+		}
+	}
+
+	idx = 0;
+	evsel = perf_evlist__first(evlist);
+
+	for (type = 0; type < PERF_COUNT_HW_CACHE_MAX; type++) {
+		for (op = 0; op < PERF_COUNT_HW_CACHE_OP_MAX; op++) {
+			/* skip invalid cache type */
+			if (!perf_evsel__is_cache_op_valid(type, op))
+				continue;
+
+			for (i = 0; i < PERF_COUNT_HW_CACHE_RESULT_MAX; i++) {
+				__perf_evsel__hw_cache_type_op_res_name(type, op, i,
+									name, sizeof(name));
+				if (evsel->idx != idx)
+					continue;
+
+				++idx;
+
+				if (strcmp(perf_evsel__name(evsel), name)) {
+					pr_debug("%s != %s\n", perf_evsel__name(evsel), name);
+					ret = -1;
+				}
+
+				evsel = perf_evsel__next(evsel);
+			}
+		}
+	}
+
+	perf_evlist__delete(evlist);
+	return ret;
+}
+
+static int __perf_evsel__name_array_test(const char *names[], int nr_names)
+{
+	int i, err;
+	struct perf_evsel *evsel;
+	struct perf_evlist *evlist = perf_evlist__new();
+
+        if (evlist == NULL)
+                return -ENOMEM;
+
+	for (i = 0; i < nr_names; ++i) {
+		err = parse_events(evlist, names[i]);
+		if (err) {
+			pr_debug("failed to parse event '%s', err %d\n",
+				 names[i], err);
+			goto out_delete_evlist;
+		}
+	}
+
+	err = 0;
+	evlist__for_each(evlist, evsel) {
+		if (strcmp(perf_evsel__name(evsel), names[evsel->idx])) {
+			--err;
+			pr_debug("%s != %s\n", perf_evsel__name(evsel), names[evsel->idx]);
+		}
+	}
+
+out_delete_evlist:
+	perf_evlist__delete(evlist);
+	return err;
+}
+
+#define perf_evsel__name_array_test(names) \
+	__perf_evsel__name_array_test(names, ARRAY_SIZE(names))
+
+int test__perf_evsel__roundtrip_name_test(void)
+{
+	int err = 0, ret = 0;
+
+	err = perf_evsel__name_array_test(perf_evsel__hw_names);
+	if (err)
+		ret = err;
+
+	err = perf_evsel__name_array_test(perf_evsel__sw_names);
+	if (err)
+		ret = err;
+
+	err = perf_evsel__roundtrip_cache_name_test();
+	if (err)
+		ret = err;
+
+	return ret;
+}
diff --git a/tools/perf/tests/evsel-tp-sched.c b/tools/perf/tests/evsel-tp-sched.c
new file mode 100644
index 00000000000..35d7fdb2328
--- /dev/null
+++ b/tools/perf/tests/evsel-tp-sched.c
@@ -0,0 +1,81 @@
+#include <traceevent/event-parse.h>
+#include "evsel.h"
+#include "tests.h"
+
+static int perf_evsel__test_field(struct perf_evsel *evsel, const char *name,
+				  int size, bool should_be_signed)
+{
+	struct format_field *field = perf_evsel__field(evsel, name);
+	int is_signed;
+	int ret = 0;
+
+	if (field == NULL) {
+		pr_debug("%s: \"%s\" field not found!\n", evsel->name, name);
+		return -1;
+	}
+
+	is_signed = !!(field->flags | FIELD_IS_SIGNED);
+	if (should_be_signed && !is_signed) {
+		pr_debug("%s: \"%s\" signedness(%d) is wrong, should be %d\n",
+			 evsel->name, name, is_signed, should_be_signed);
+		ret = -1;
+	}
+
+	if (field->size != size) {
+		pr_debug("%s: \"%s\" size (%d) should be %d!\n",
+			 evsel->name, name, field->size, size);
+		ret = -1;
+	}
+
+	return ret;
+}
+
+int test__perf_evsel__tp_sched_test(void)
+{
+	struct perf_evsel *evsel = perf_evsel__newtp("sched", "sched_switch");
+	int ret = 0;
+
+	if (evsel == NULL) {
+		pr_debug("perf_evsel__new\n");
+		return -1;
+	}
+
+	if (perf_evsel__test_field(evsel, "prev_comm", 16, true))
+		ret = -1;
+
+	if (perf_evsel__test_field(evsel, "prev_pid", 4, true))
+		ret = -1;
+
+	if (perf_evsel__test_field(evsel, "prev_prio", 4, true))
+		ret = -1;
+
+	if (perf_evsel__test_field(evsel, "prev_state", sizeof(long), true))
+		ret = -1;
+
+	if (perf_evsel__test_field(evsel, "next_comm", 16, true))
+		ret = -1;
+
+	if (perf_evsel__test_field(evsel, "next_pid", 4, true))
+		ret = -1;
+
+	if (perf_evsel__test_field(evsel, "next_prio", 4, true))
+		ret = -1;
+
+	perf_evsel__delete(evsel);
+
+	evsel = perf_evsel__newtp("sched", "sched_wakeup");
+
+	if (perf_evsel__test_field(evsel, "comm", 16, true))
+		ret = -1;
+
+	if (perf_evsel__test_field(evsel, "pid", 4, true))
+		ret = -1;
+
+	if (perf_evsel__test_field(evsel, "prio", 4, true))
+		ret = -1;
+
+	if (perf_evsel__test_field(evsel, "target_cpu", 4, true))
+		ret = -1;
+
+	return ret;
+}
diff --git a/tools/perf/tests/hists_common.c b/tools/perf/tests/hists_common.c
new file mode 100644
index 00000000000..a62c0913451
--- /dev/null
+++ b/tools/perf/tests/hists_common.c
@@ -0,0 +1,209 @@
+#include "perf.h"
+#include "util/debug.h"
+#include "util/symbol.h"
+#include "util/sort.h"
+#include "util/evsel.h"
+#include "util/evlist.h"
+#include "util/machine.h"
+#include "util/thread.h"
+#include "tests/hists_common.h"
+
+static struct {
+	u32 pid;
+	const char *comm;
+} fake_threads[] = {
+	{ FAKE_PID_PERF1, "perf" },
+	{ FAKE_PID_PERF2, "perf" },
+	{ FAKE_PID_BASH,  "bash" },
+};
+
+static struct {
+	u32 pid;
+	u64 start;
+	const char *filename;
+} fake_mmap_info[] = {
+	{ FAKE_PID_PERF1, FAKE_MAP_PERF,   "perf" },
+	{ FAKE_PID_PERF1, FAKE_MAP_LIBC,   "libc" },
+	{ FAKE_PID_PERF1, FAKE_MAP_KERNEL, "[kernel]" },
+	{ FAKE_PID_PERF2, FAKE_MAP_PERF,   "perf" },
+	{ FAKE_PID_PERF2, FAKE_MAP_LIBC,   "libc" },
+	{ FAKE_PID_PERF2, FAKE_MAP_KERNEL, "[kernel]" },
+	{ FAKE_PID_BASH,  FAKE_MAP_BASH,   "bash" },
+	{ FAKE_PID_BASH,  FAKE_MAP_LIBC,   "libc" },
+	{ FAKE_PID_BASH,  FAKE_MAP_KERNEL, "[kernel]" },
+};
+
+struct fake_sym {
+	u64 start;
+	u64 length;
+	const char *name;
+};
+
+static struct fake_sym perf_syms[] = {
+	{ FAKE_SYM_OFFSET1, FAKE_SYM_LENGTH, "main" },
+	{ FAKE_SYM_OFFSET2, FAKE_SYM_LENGTH, "run_command" },
+	{ FAKE_SYM_OFFSET3, FAKE_SYM_LENGTH, "cmd_record" },
+};
+
+static struct fake_sym bash_syms[] = {
+	{ FAKE_SYM_OFFSET1, FAKE_SYM_LENGTH, "main" },
+	{ FAKE_SYM_OFFSET2, FAKE_SYM_LENGTH, "xmalloc" },
+	{ FAKE_SYM_OFFSET3, FAKE_SYM_LENGTH, "xfree" },
+};
+
+static struct fake_sym libc_syms[] = {
+	{ 700, 100, "malloc" },
+	{ 800, 100, "free" },
+	{ 900, 100, "realloc" },
+	{ FAKE_SYM_OFFSET1, FAKE_SYM_LENGTH, "malloc" },
+	{ FAKE_SYM_OFFSET2, FAKE_SYM_LENGTH, "free" },
+	{ FAKE_SYM_OFFSET3, FAKE_SYM_LENGTH, "realloc" },
+};
+
+static struct fake_sym kernel_syms[] = {
+	{ FAKE_SYM_OFFSET1, FAKE_SYM_LENGTH, "schedule" },
+	{ FAKE_SYM_OFFSET2, FAKE_SYM_LENGTH, "page_fault" },
+	{ FAKE_SYM_OFFSET3, FAKE_SYM_LENGTH, "sys_perf_event_open" },
+};
+
+static struct {
+	const char *dso_name;
+	struct fake_sym *syms;
+	size_t nr_syms;
+} fake_symbols[] = {
+	{ "perf", perf_syms, ARRAY_SIZE(perf_syms) },
+	{ "bash", bash_syms, ARRAY_SIZE(bash_syms) },
+	{ "libc", libc_syms, ARRAY_SIZE(libc_syms) },
+	{ "[kernel]", kernel_syms, ARRAY_SIZE(kernel_syms) },
+};
+
+struct machine *setup_fake_machine(struct machines *machines)
+{
+	struct machine *machine = machines__find(machines, HOST_KERNEL_ID);
+	size_t i;
+
+	if (machine == NULL) {
+		pr_debug("Not enough memory for machine setup\n");
+		return NULL;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(fake_threads); i++) {
+		struct thread *thread;
+
+		thread = machine__findnew_thread(machine, fake_threads[i].pid,
+						 fake_threads[i].pid);
+		if (thread == NULL)
+			goto out;
+
+		thread__set_comm(thread, fake_threads[i].comm, 0);
+	}
+
+	for (i = 0; i < ARRAY_SIZE(fake_mmap_info); i++) {
+		union perf_event fake_mmap_event = {
+			.mmap = {
+				.header = { .misc = PERF_RECORD_MISC_USER, },
+				.pid = fake_mmap_info[i].pid,
+				.tid = fake_mmap_info[i].pid,
+				.start = fake_mmap_info[i].start,
+				.len = FAKE_MAP_LENGTH,
+				.pgoff = 0ULL,
+			},
+		};
+
+		strcpy(fake_mmap_event.mmap.filename,
+		       fake_mmap_info[i].filename);
+
+		machine__process_mmap_event(machine, &fake_mmap_event, NULL);
+	}
+
+	for (i = 0; i < ARRAY_SIZE(fake_symbols); i++) {
+		size_t k;
+		struct dso *dso;
+
+		dso = __dsos__findnew(&machine->user_dsos,
+				      fake_symbols[i].dso_name);
+		if (dso == NULL)
+			goto out;
+
+		/* emulate dso__load() */
+		dso__set_loaded(dso, MAP__FUNCTION);
+
+		for (k = 0; k < fake_symbols[i].nr_syms; k++) {
+			struct symbol *sym;
+			struct fake_sym *fsym = &fake_symbols[i].syms[k];
+
+			sym = symbol__new(fsym->start, fsym->length,
+					  STB_GLOBAL, fsym->name);
+			if (sym == NULL)
+				goto out;
+
+			symbols__insert(&dso->symbols[MAP__FUNCTION], sym);
+		}
+	}
+
+	return machine;
+
+out:
+	pr_debug("Not enough memory for machine setup\n");
+	machine__delete_threads(machine);
+	machine__delete(machine);
+	return NULL;
+}
+
+void print_hists_in(struct hists *hists)
+{
+	int i = 0;
+	struct rb_root *root;
+	struct rb_node *node;
+
+	if (sort__need_collapse)
+		root = &hists->entries_collapsed;
+	else
+		root = hists->entries_in;
+
+	pr_info("----- %s --------\n", __func__);
+	node = rb_first(root);
+	while (node) {
+		struct hist_entry *he;
+
+		he = rb_entry(node, struct hist_entry, rb_node_in);
+
+		if (!he->filtered) {
+			pr_info("%2d: entry: %-8s [%-8s] %20s: period = %"PRIu64"\n",
+				i, thread__comm_str(he->thread),
+				he->ms.map->dso->short_name,
+				he->ms.sym->name, he->stat.period);
+		}
+
+		i++;
+		node = rb_next(node);
+	}
+}
+
+void print_hists_out(struct hists *hists)
+{
+	int i = 0;
+	struct rb_root *root;
+	struct rb_node *node;
+
+	root = &hists->entries;
+
+	pr_info("----- %s --------\n", __func__);
+	node = rb_first(root);
+	while (node) {
+		struct hist_entry *he;
+
+		he = rb_entry(node, struct hist_entry, rb_node);
+
+		if (!he->filtered) {
+			pr_info("%2d: entry: %8s:%5d [%-8s] %20s: period = %"PRIu64"/%"PRIu64"\n",
+				i, thread__comm_str(he->thread), he->thread->tid,
+				he->ms.map->dso->short_name,
+				he->ms.sym->name, he->stat.period,
+				he->stat_acc ? he->stat_acc->period : 0);
+		}
+
+		i++;
+		node = rb_next(node);
+	}
+}
diff --git a/tools/perf/tests/hists_common.h b/tools/perf/tests/hists_common.h
new file mode 100644
index 00000000000..888254e8665
--- /dev/null
+++ b/tools/perf/tests/hists_common.h
@@ -0,0 +1,75 @@
+#ifndef __PERF_TESTS__HISTS_COMMON_H__
+#define __PERF_TESTS__HISTS_COMMON_H__
+
+struct machine;
+struct machines;
+
+#define FAKE_PID_PERF1  100
+#define FAKE_PID_PERF2  200
+#define FAKE_PID_BASH   300
+
+#define FAKE_MAP_PERF    0x400000
+#define FAKE_MAP_BASH    0x400000
+#define FAKE_MAP_LIBC    0x500000
+#define FAKE_MAP_KERNEL  0xf00000
+#define FAKE_MAP_LENGTH  0x100000
+
+#define FAKE_SYM_OFFSET1  700
+#define FAKE_SYM_OFFSET2  800
+#define FAKE_SYM_OFFSET3  900
+#define FAKE_SYM_LENGTH   100
+
+#define FAKE_IP_PERF_MAIN  FAKE_MAP_PERF + FAKE_SYM_OFFSET1
+#define FAKE_IP_PERF_RUN_COMMAND  FAKE_MAP_PERF + FAKE_SYM_OFFSET2
+#define FAKE_IP_PERF_CMD_RECORD  FAKE_MAP_PERF + FAKE_SYM_OFFSET3
+#define FAKE_IP_BASH_MAIN  FAKE_MAP_BASH + FAKE_SYM_OFFSET1
+#define FAKE_IP_BASH_XMALLOC  FAKE_MAP_BASH + FAKE_SYM_OFFSET2
+#define FAKE_IP_BASH_XFREE  FAKE_MAP_BASH + FAKE_SYM_OFFSET3
+#define FAKE_IP_LIBC_MALLOC  FAKE_MAP_LIBC + FAKE_SYM_OFFSET1
+#define FAKE_IP_LIBC_FREE  FAKE_MAP_LIBC + FAKE_SYM_OFFSET2
+#define FAKE_IP_LIBC_REALLOC  FAKE_MAP_LIBC + FAKE_SYM_OFFSET3
+#define FAKE_IP_KERNEL_SCHEDULE  FAKE_MAP_KERNEL + FAKE_SYM_OFFSET1
+#define FAKE_IP_KERNEL_PAGE_FAULT  FAKE_MAP_KERNEL + FAKE_SYM_OFFSET2
+#define FAKE_IP_KERNEL_SYS_PERF_EVENT_OPEN  FAKE_MAP_KERNEL + FAKE_SYM_OFFSET3
+
+/*
+ * The setup_fake_machine() provides a test environment which consists
+ * of 3 processes that have 3 mappings and in turn, have 3 symbols
+ * respectively.  See below table:
+ *
+ * Command:  Pid  Shared Object               Symbol
+ * .............  .............  ...................
+ *    perf:  100           perf  main
+ *    perf:  100           perf  run_command
+ *    perf:  100           perf  cmd_record
+ *    perf:  100           libc  malloc
+ *    perf:  100           libc  free
+ *    perf:  100           libc  realloc
+ *    perf:  100       [kernel]  schedule
+ *    perf:  100       [kernel]  page_fault
+ *    perf:  100       [kernel]  sys_perf_event_open
+ *    perf:  200           perf  main
+ *    perf:  200           perf  run_command
+ *    perf:  200           perf  cmd_record
+ *    perf:  200           libc  malloc
+ *    perf:  200           libc  free
+ *    perf:  200           libc  realloc
+ *    perf:  200       [kernel]  schedule
+ *    perf:  200       [kernel]  page_fault
+ *    perf:  200       [kernel]  sys_perf_event_open
+ *    bash:  300           bash  main
+ *    bash:  300           bash  xmalloc
+ *    bash:  300           bash  xfree
+ *    bash:  300           libc  malloc
+ *    bash:  300           libc  free
+ *    bash:  300           libc  realloc
+ *    bash:  300       [kernel]  schedule
+ *    bash:  300       [kernel]  page_fault
+ *    bash:  300       [kernel]  sys_perf_event_open
+ */
+struct machine *setup_fake_machine(struct machines *machines);
+
+void print_hists_in(struct hists *hists);
+void print_hists_out(struct hists *hists);
+
+#endif /* __PERF_TESTS__HISTS_COMMON_H__ */
diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c
new file mode 100644
index 00000000000..0ac240db2e2
--- /dev/null
+++ b/tools/perf/tests/hists_cumulate.c
@@ -0,0 +1,726 @@
+#include "perf.h"
+#include "util/debug.h"
+#include "util/symbol.h"
+#include "util/sort.h"
+#include "util/evsel.h"
+#include "util/evlist.h"
+#include "util/machine.h"
+#include "util/thread.h"
+#include "util/parse-events.h"
+#include "tests/tests.h"
+#include "tests/hists_common.h"
+
+struct sample {
+	u32 pid;
+	u64 ip;
+	struct thread *thread;
+	struct map *map;
+	struct symbol *sym;
+};
+
+/* For the numbers, see hists_common.c */
+static struct sample fake_samples[] = {
+	/* perf [kernel] schedule() */
+	{ .pid = FAKE_PID_PERF1, .ip = FAKE_IP_KERNEL_SCHEDULE, },
+	/* perf [perf]   main() */
+	{ .pid = FAKE_PID_PERF1, .ip = FAKE_IP_PERF_MAIN, },
+	/* perf [perf]   cmd_record() */
+	{ .pid = FAKE_PID_PERF1, .ip = FAKE_IP_PERF_CMD_RECORD, },
+	/* perf [libc]   malloc() */
+	{ .pid = FAKE_PID_PERF1, .ip = FAKE_IP_LIBC_MALLOC, },
+	/* perf [libc]   free() */
+	{ .pid = FAKE_PID_PERF1, .ip = FAKE_IP_LIBC_FREE, },
+	/* perf [perf]   main() */
+	{ .pid = FAKE_PID_PERF2, .ip = FAKE_IP_PERF_MAIN, },
+	/* perf [kernel] page_fault() */
+	{ .pid = FAKE_PID_PERF2, .ip = FAKE_IP_KERNEL_PAGE_FAULT, },
+	/* bash [bash]   main() */
+	{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_BASH_MAIN, },
+	/* bash [bash]   xmalloc() */
+	{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_BASH_XMALLOC, },
+	/* bash [kernel] page_fault() */
+	{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_KERNEL_PAGE_FAULT, },
+};
+
+/*
+ * Will be casted to struct ip_callchain which has all 64 bit entries
+ * of nr and ips[].
+ */
+static u64 fake_callchains[][10] = {
+	/*   schedule => run_command => main */
+	{ 3, FAKE_IP_KERNEL_SCHEDULE, FAKE_IP_PERF_RUN_COMMAND, FAKE_IP_PERF_MAIN, },
+	/*   main  */
+	{ 1, FAKE_IP_PERF_MAIN, },
+	/*   cmd_record => run_command => main */
+	{ 3, FAKE_IP_PERF_CMD_RECORD, FAKE_IP_PERF_RUN_COMMAND, FAKE_IP_PERF_MAIN, },
+	/*   malloc => cmd_record => run_command => main */
+	{ 4, FAKE_IP_LIBC_MALLOC, FAKE_IP_PERF_CMD_RECORD, FAKE_IP_PERF_RUN_COMMAND,
+	     FAKE_IP_PERF_MAIN, },
+	/*   free => cmd_record => run_command => main */
+	{ 4, FAKE_IP_LIBC_FREE, FAKE_IP_PERF_CMD_RECORD, FAKE_IP_PERF_RUN_COMMAND,
+	     FAKE_IP_PERF_MAIN, },
+	/*   main */
+	{ 1, FAKE_IP_PERF_MAIN, },
+	/*   page_fault => sys_perf_event_open => run_command => main */
+	{ 4, FAKE_IP_KERNEL_PAGE_FAULT, FAKE_IP_KERNEL_SYS_PERF_EVENT_OPEN,
+	     FAKE_IP_PERF_RUN_COMMAND, FAKE_IP_PERF_MAIN, },
+	/*   main */
+	{ 1, FAKE_IP_BASH_MAIN, },
+	/*   xmalloc => malloc => xmalloc => malloc => xmalloc => main */
+	{ 6, FAKE_IP_BASH_XMALLOC, FAKE_IP_LIBC_MALLOC, FAKE_IP_BASH_XMALLOC,
+	     FAKE_IP_LIBC_MALLOC, FAKE_IP_BASH_XMALLOC, FAKE_IP_BASH_MAIN, },
+	/*   page_fault => malloc => main */
+	{ 3, FAKE_IP_KERNEL_PAGE_FAULT, FAKE_IP_LIBC_MALLOC, FAKE_IP_BASH_MAIN, },
+};
+
+static int add_hist_entries(struct hists *hists, struct machine *machine)
+{
+	struct addr_location al;
+	struct perf_evsel *evsel = hists_to_evsel(hists);
+	struct perf_sample sample = { .period = 1000, };
+	size_t i;
+
+	for (i = 0; i < ARRAY_SIZE(fake_samples); i++) {
+		const union perf_event event = {
+			.header = {
+				.misc = PERF_RECORD_MISC_USER,
+			},
+		};
+		struct hist_entry_iter iter = {
+			.hide_unresolved = false,
+		};
+
+		if (symbol_conf.cumulate_callchain)
+			iter.ops = &hist_iter_cumulative;
+		else
+			iter.ops = &hist_iter_normal;
+
+		sample.pid = fake_samples[i].pid;
+		sample.tid = fake_samples[i].pid;
+		sample.ip = fake_samples[i].ip;
+		sample.callchain = (struct ip_callchain *)fake_callchains[i];
+
+		if (perf_event__preprocess_sample(&event, machine, &al,
+						  &sample) < 0)
+			goto out;
+
+		if (hist_entry_iter__add(&iter, &al, evsel, &sample,
+					 PERF_MAX_STACK_DEPTH, NULL) < 0)
+			goto out;
+
+		fake_samples[i].thread = al.thread;
+		fake_samples[i].map = al.map;
+		fake_samples[i].sym = al.sym;
+	}
+
+	return TEST_OK;
+
+out:
+	pr_debug("Not enough memory for adding a hist entry\n");
+	return TEST_FAIL;
+}
+
+static void del_hist_entries(struct hists *hists)
+{
+	struct hist_entry *he;
+	struct rb_root *root_in;
+	struct rb_root *root_out;
+	struct rb_node *node;
+
+	if (sort__need_collapse)
+		root_in = &hists->entries_collapsed;
+	else
+		root_in = hists->entries_in;
+
+	root_out = &hists->entries;
+
+	while (!RB_EMPTY_ROOT(root_out)) {
+		node = rb_first(root_out);
+
+		he = rb_entry(node, struct hist_entry, rb_node);
+		rb_erase(node, root_out);
+		rb_erase(&he->rb_node_in, root_in);
+		hist_entry__free(he);
+	}
+}
+
+typedef int (*test_fn_t)(struct perf_evsel *, struct machine *);
+
+#define COMM(he)  (thread__comm_str(he->thread))
+#define DSO(he)   (he->ms.map->dso->short_name)
+#define SYM(he)   (he->ms.sym->name)
+#define CPU(he)   (he->cpu)
+#define PID(he)   (he->thread->tid)
+#define DEPTH(he) (he->callchain->max_depth)
+#define CDSO(cl)  (cl->ms.map->dso->short_name)
+#define CSYM(cl)  (cl->ms.sym->name)
+
+struct result {
+	u64 children;
+	u64 self;
+	const char *comm;
+	const char *dso;
+	const char *sym;
+};
+
+struct callchain_result {
+	u64 nr;
+	struct {
+		const char *dso;
+		const char *sym;
+	} node[10];
+};
+
+static int do_test(struct hists *hists, struct result *expected, size_t nr_expected,
+		   struct callchain_result *expected_callchain, size_t nr_callchain)
+{
+	char buf[32];
+	size_t i, c;
+	struct hist_entry *he;
+	struct rb_root *root;
+	struct rb_node *node;
+	struct callchain_node *cnode;
+	struct callchain_list *clist;
+
+	/*
+	 * adding and deleting hist entries must be done outside of this
+	 * function since TEST_ASSERT_VAL() returns in case of failure.
+	 */
+	hists__collapse_resort(hists, NULL);
+	hists__output_resort(hists);
+
+	if (verbose > 2) {
+		pr_info("use callchain: %d, cumulate callchain: %d\n",
+			symbol_conf.use_callchain,
+			symbol_conf.cumulate_callchain);
+		print_hists_out(hists);
+	}
+
+	root = &hists->entries;
+	for (node = rb_first(root), i = 0;
+	     node && (he = rb_entry(node, struct hist_entry, rb_node));
+	     node = rb_next(node), i++) {
+		scnprintf(buf, sizeof(buf), "Invalid hist entry #%zd", i);
+
+		TEST_ASSERT_VAL("Incorrect number of hist entry",
+				i < nr_expected);
+		TEST_ASSERT_VAL(buf, he->stat.period == expected[i].self &&
+				!strcmp(COMM(he), expected[i].comm) &&
+				!strcmp(DSO(he), expected[i].dso) &&
+				!strcmp(SYM(he), expected[i].sym));
+
+		if (symbol_conf.cumulate_callchain)
+			TEST_ASSERT_VAL(buf, he->stat_acc->period == expected[i].children);
+
+		if (!symbol_conf.use_callchain)
+			continue;
+
+		/* check callchain entries */
+		root = &he->callchain->node.rb_root;
+		cnode = rb_entry(rb_first(root), struct callchain_node, rb_node);
+
+		c = 0;
+		list_for_each_entry(clist, &cnode->val, list) {
+			scnprintf(buf, sizeof(buf), "Invalid callchain entry #%zd/%zd", i, c);
+
+			TEST_ASSERT_VAL("Incorrect number of callchain entry",
+					c < expected_callchain[i].nr);
+			TEST_ASSERT_VAL(buf,
+				!strcmp(CDSO(clist), expected_callchain[i].node[c].dso) &&
+				!strcmp(CSYM(clist), expected_callchain[i].node[c].sym));
+			c++;
+		}
+		/* TODO: handle multiple child nodes properly */
+		TEST_ASSERT_VAL("Incorrect number of callchain entry",
+				c <= expected_callchain[i].nr);
+	}
+	TEST_ASSERT_VAL("Incorrect number of hist entry",
+			i == nr_expected);
+	TEST_ASSERT_VAL("Incorrect number of callchain entry",
+			!symbol_conf.use_callchain || nr_expected == nr_callchain);
+	return 0;
+}
+
+/* NO callchain + NO children */
+static int test1(struct perf_evsel *evsel, struct machine *machine)
+{
+	int err;
+	struct hists *hists = &evsel->hists;
+	/*
+	 * expected output:
+	 *
+	 * Overhead  Command  Shared Object          Symbol
+	 * ========  =======  =============  ==============
+	 *   20.00%     perf  perf           [.] main
+	 *   10.00%     bash  [kernel]       [k] page_fault
+	 *   10.00%     bash  bash           [.] main
+	 *   10.00%     bash  bash           [.] xmalloc
+	 *   10.00%     perf  [kernel]       [k] page_fault
+	 *   10.00%     perf  [kernel]       [k] schedule
+	 *   10.00%     perf  libc           [.] free
+	 *   10.00%     perf  libc           [.] malloc
+	 *   10.00%     perf  perf           [.] cmd_record
+	 */
+	struct result expected[] = {
+		{ 0, 2000, "perf", "perf",     "main" },
+		{ 0, 1000, "bash", "[kernel]", "page_fault" },
+		{ 0, 1000, "bash", "bash",     "main" },
+		{ 0, 1000, "bash", "bash",     "xmalloc" },
+		{ 0, 1000, "perf", "[kernel]", "page_fault" },
+		{ 0, 1000, "perf", "[kernel]", "schedule" },
+		{ 0, 1000, "perf", "libc",     "free" },
+		{ 0, 1000, "perf", "libc",     "malloc" },
+		{ 0, 1000, "perf", "perf",     "cmd_record" },
+	};
+
+	symbol_conf.use_callchain = false;
+	symbol_conf.cumulate_callchain = false;
+
+	setup_sorting();
+	callchain_register_param(&callchain_param);
+
+	err = add_hist_entries(hists, machine);
+	if (err < 0)
+		goto out;
+
+	err = do_test(hists, expected, ARRAY_SIZE(expected), NULL, 0);
+
+out:
+	del_hist_entries(hists);
+	reset_output_field();
+	return err;
+}
+
+/* callcain + NO children */
+static int test2(struct perf_evsel *evsel, struct machine *machine)
+{
+	int err;
+	struct hists *hists = &evsel->hists;
+	/*
+	 * expected output:
+	 *
+	 * Overhead  Command  Shared Object          Symbol
+	 * ========  =======  =============  ==============
+	 *   20.00%     perf  perf           [.] main
+	 *              |
+	 *              --- main
+	 *
+	 *   10.00%     bash  [kernel]       [k] page_fault
+	 *              |
+	 *              --- page_fault
+	 *                  malloc
+	 *                  main
+	 *
+	 *   10.00%     bash  bash           [.] main
+	 *              |
+	 *              --- main
+	 *
+	 *   10.00%     bash  bash           [.] xmalloc
+	 *              |
+	 *              --- xmalloc
+	 *                  malloc
+	 *                  xmalloc     <--- NOTE: there's a cycle
+	 *                  malloc
+	 *                  xmalloc
+	 *                  main
+	 *
+	 *   10.00%     perf  [kernel]       [k] page_fault
+	 *              |
+	 *              --- page_fault
+	 *                  sys_perf_event_open
+	 *                  run_command
+	 *                  main
+	 *
+	 *   10.00%     perf  [kernel]       [k] schedule
+	 *              |
+	 *              --- schedule
+	 *                  run_command
+	 *                  main
+	 *
+	 *   10.00%     perf  libc           [.] free
+	 *              |
+	 *              --- free
+	 *                  cmd_record
+	 *                  run_command
+	 *                  main
+	 *
+	 *   10.00%     perf  libc           [.] malloc
+	 *              |
+	 *              --- malloc
+	 *                  cmd_record
+	 *                  run_command
+	 *                  main
+	 *
+	 *   10.00%     perf  perf           [.] cmd_record
+	 *              |
+	 *              --- cmd_record
+	 *                  run_command
+	 *                  main
+	 *
+	 */
+	struct result expected[] = {
+		{ 0, 2000, "perf", "perf",     "main" },
+		{ 0, 1000, "bash", "[kernel]", "page_fault" },
+		{ 0, 1000, "bash", "bash",     "main" },
+		{ 0, 1000, "bash", "bash",     "xmalloc" },
+		{ 0, 1000, "perf", "[kernel]", "page_fault" },
+		{ 0, 1000, "perf", "[kernel]", "schedule" },
+		{ 0, 1000, "perf", "libc",     "free" },
+		{ 0, 1000, "perf", "libc",     "malloc" },
+		{ 0, 1000, "perf", "perf",     "cmd_record" },
+	};
+	struct callchain_result expected_callchain[] = {
+		{
+			1, {	{ "perf",     "main" }, },
+		},
+		{
+			3, {	{ "[kernel]", "page_fault" },
+				{ "libc",     "malloc" },
+				{ "bash",     "main" }, },
+		},
+		{
+			1, {	{ "bash",     "main" }, },
+		},
+		{
+			6, {	{ "bash",     "xmalloc" },
+				{ "libc",     "malloc" },
+				{ "bash",     "xmalloc" },
+				{ "libc",     "malloc" },
+				{ "bash",     "xmalloc" },
+				{ "bash",     "main" }, },
+		},
+		{
+			4, {	{ "[kernel]", "page_fault" },
+				{ "[kernel]", "sys_perf_event_open" },
+				{ "perf",     "run_command" },
+				{ "perf",     "main" }, },
+		},
+		{
+			3, {	{ "[kernel]", "schedule" },
+				{ "perf",     "run_command" },
+				{ "perf",     "main" }, },
+		},
+		{
+			4, {	{ "libc",     "free" },
+				{ "perf",     "cmd_record" },
+				{ "perf",     "run_command" },
+				{ "perf",     "main" }, },
+		},
+		{
+			4, {	{ "libc",     "malloc" },
+				{ "perf",     "cmd_record" },
+				{ "perf",     "run_command" },
+				{ "perf",     "main" }, },
+		},
+		{
+			3, {	{ "perf",     "cmd_record" },
+				{ "perf",     "run_command" },
+				{ "perf",     "main" }, },
+		},
+	};
+
+	symbol_conf.use_callchain = true;
+	symbol_conf.cumulate_callchain = false;
+
+	setup_sorting();
+	callchain_register_param(&callchain_param);
+
+	err = add_hist_entries(hists, machine);
+	if (err < 0)
+		goto out;
+
+	err = do_test(hists, expected, ARRAY_SIZE(expected),
+		      expected_callchain, ARRAY_SIZE(expected_callchain));
+
+out:
+	del_hist_entries(hists);
+	reset_output_field();
+	return err;
+}
+
+/* NO callchain + children */
+static int test3(struct perf_evsel *evsel, struct machine *machine)
+{
+	int err;
+	struct hists *hists = &evsel->hists;
+	/*
+	 * expected output:
+	 *
+	 * Children      Self  Command  Shared Object                   Symbol
+	 * ========  ========  =======  =============  =======================
+	 *   70.00%    20.00%     perf  perf           [.] main
+	 *   50.00%     0.00%     perf  perf           [.] run_command
+	 *   30.00%    10.00%     bash  bash           [.] main
+	 *   30.00%    10.00%     perf  perf           [.] cmd_record
+	 *   20.00%     0.00%     bash  libc           [.] malloc
+	 *   10.00%    10.00%     bash  [kernel]       [k] page_fault
+	 *   10.00%    10.00%     perf  [kernel]       [k] schedule
+	 *   10.00%     0.00%     perf  [kernel]       [k] sys_perf_event_open
+	 *   10.00%    10.00%     perf  [kernel]       [k] page_fault
+	 *   10.00%    10.00%     perf  libc           [.] free
+	 *   10.00%    10.00%     perf  libc           [.] malloc
+	 *   10.00%    10.00%     bash  bash           [.] xmalloc
+	 */
+	struct result expected[] = {
+		{ 7000, 2000, "perf", "perf",     "main" },
+		{ 5000,    0, "perf", "perf",     "run_command" },
+		{ 3000, 1000, "bash", "bash",     "main" },
+		{ 3000, 1000, "perf", "perf",     "cmd_record" },
+		{ 2000,    0, "bash", "libc",     "malloc" },
+		{ 1000, 1000, "bash", "[kernel]", "page_fault" },
+		{ 1000, 1000, "perf", "[kernel]", "schedule" },
+		{ 1000,    0, "perf", "[kernel]", "sys_perf_event_open" },
+		{ 1000, 1000, "perf", "[kernel]", "page_fault" },
+		{ 1000, 1000, "perf", "libc",     "free" },
+		{ 1000, 1000, "perf", "libc",     "malloc" },
+		{ 1000, 1000, "bash", "bash",     "xmalloc" },
+	};
+
+	symbol_conf.use_callchain = false;
+	symbol_conf.cumulate_callchain = true;
+
+	setup_sorting();
+	callchain_register_param(&callchain_param);
+
+	err = add_hist_entries(hists, machine);
+	if (err < 0)
+		goto out;
+
+	err = do_test(hists, expected, ARRAY_SIZE(expected), NULL, 0);
+
+out:
+	del_hist_entries(hists);
+	reset_output_field();
+	return err;
+}
+
+/* callchain + children */
+static int test4(struct perf_evsel *evsel, struct machine *machine)
+{
+	int err;
+	struct hists *hists = &evsel->hists;
+	/*
+	 * expected output:
+	 *
+	 * Children      Self  Command  Shared Object                   Symbol
+	 * ========  ========  =======  =============  =======================
+	 *   70.00%    20.00%     perf  perf           [.] main
+	 *              |
+	 *              --- main
+	 *
+	 *   50.00%     0.00%     perf  perf           [.] run_command
+	 *              |
+	 *              --- run_command
+	 *                  main
+	 *
+	 *   30.00%    10.00%     bash  bash           [.] main
+	 *              |
+	 *              --- main
+	 *
+	 *   30.00%    10.00%     perf  perf           [.] cmd_record
+	 *              |
+	 *              --- cmd_record
+	 *                  run_command
+	 *                  main
+	 *
+	 *   20.00%     0.00%     bash  libc           [.] malloc
+	 *              |
+	 *              --- malloc
+	 *                 |
+	 *                 |--50.00%-- xmalloc
+	 *                 |           main
+	 *                  --50.00%-- main
+	 *
+	 *   10.00%    10.00%     bash  [kernel]       [k] page_fault
+	 *              |
+	 *              --- page_fault
+	 *                  malloc
+	 *                  main
+	 *
+	 *   10.00%    10.00%     perf  [kernel]       [k] schedule
+	 *              |
+	 *              --- schedule
+	 *                  run_command
+	 *                  main
+	 *
+	 *   10.00%     0.00%     perf  [kernel]       [k] sys_perf_event_open
+	 *              |
+	 *              --- sys_perf_event_open
+	 *                  run_command
+	 *                  main
+	 *
+	 *   10.00%    10.00%     perf  [kernel]       [k] page_fault
+	 *              |
+	 *              --- page_fault
+	 *                  sys_perf_event_open
+	 *                  run_command
+	 *                  main
+	 *
+	 *   10.00%    10.00%     perf  libc           [.] free
+	 *              |
+	 *              --- free
+	 *                  cmd_record
+	 *                  run_command
+	 *                  main
+	 *
+	 *   10.00%    10.00%     perf  libc           [.] malloc
+	 *              |
+	 *              --- malloc
+	 *                  cmd_record
+	 *                  run_command
+	 *                  main
+	 *
+	 *   10.00%    10.00%     bash  bash           [.] xmalloc
+	 *              |
+	 *              --- xmalloc
+	 *                  malloc
+	 *                  xmalloc     <--- NOTE: there's a cycle
+	 *                  malloc
+	 *                  xmalloc
+	 *                  main
+	 *
+	 */
+	struct result expected[] = {
+		{ 7000, 2000, "perf", "perf",     "main" },
+		{ 5000,    0, "perf", "perf",     "run_command" },
+		{ 3000, 1000, "bash", "bash",     "main" },
+		{ 3000, 1000, "perf", "perf",     "cmd_record" },
+		{ 2000,    0, "bash", "libc",     "malloc" },
+		{ 1000, 1000, "bash", "[kernel]", "page_fault" },
+		{ 1000, 1000, "perf", "[kernel]", "schedule" },
+		{ 1000,    0, "perf", "[kernel]", "sys_perf_event_open" },
+		{ 1000, 1000, "perf", "[kernel]", "page_fault" },
+		{ 1000, 1000, "perf", "libc",     "free" },
+		{ 1000, 1000, "perf", "libc",     "malloc" },
+		{ 1000, 1000, "bash", "bash",     "xmalloc" },
+	};
+	struct callchain_result expected_callchain[] = {
+		{
+			1, {	{ "perf",     "main" }, },
+		},
+		{
+			2, {	{ "perf",     "run_command" },
+				{ "perf",     "main" }, },
+		},
+		{
+			1, {	{ "bash",     "main" }, },
+		},
+		{
+			3, {	{ "perf",     "cmd_record" },
+				{ "perf",     "run_command" },
+				{ "perf",     "main" }, },
+		},
+		{
+			4, {	{ "libc",     "malloc" },
+				{ "bash",     "xmalloc" },
+				{ "bash",     "main" },
+				{ "bash",     "main" }, },
+		},
+		{
+			3, {	{ "[kernel]", "page_fault" },
+				{ "libc",     "malloc" },
+				{ "bash",     "main" }, },
+		},
+		{
+			3, {	{ "[kernel]", "schedule" },
+				{ "perf",     "run_command" },
+				{ "perf",     "main" }, },
+		},
+		{
+			3, {	{ "[kernel]", "sys_perf_event_open" },
+				{ "perf",     "run_command" },
+				{ "perf",     "main" }, },
+		},
+		{
+			4, {	{ "[kernel]", "page_fault" },
+				{ "[kernel]", "sys_perf_event_open" },
+				{ "perf",     "run_command" },
+				{ "perf",     "main" }, },
+		},
+		{
+			4, {	{ "libc",     "free" },
+				{ "perf",     "cmd_record" },
+				{ "perf",     "run_command" },
+				{ "perf",     "main" }, },
+		},
+		{
+			4, {	{ "libc",     "malloc" },
+				{ "perf",     "cmd_record" },
+				{ "perf",     "run_command" },
+				{ "perf",     "main" }, },
+		},
+		{
+			6, {	{ "bash",     "xmalloc" },
+				{ "libc",     "malloc" },
+				{ "bash",     "xmalloc" },
+				{ "libc",     "malloc" },
+				{ "bash",     "xmalloc" },
+				{ "bash",     "main" }, },
+		},
+	};
+
+	symbol_conf.use_callchain = true;
+	symbol_conf.cumulate_callchain = true;
+
+	setup_sorting();
+	callchain_register_param(&callchain_param);
+
+	err = add_hist_entries(hists, machine);
+	if (err < 0)
+		goto out;
+
+	err = do_test(hists, expected, ARRAY_SIZE(expected),
+		      expected_callchain, ARRAY_SIZE(expected_callchain));
+
+out:
+	del_hist_entries(hists);
+	reset_output_field();
+	return err;
+}
+
+int test__hists_cumulate(void)
+{
+	int err = TEST_FAIL;
+	struct machines machines;
+	struct machine *machine;
+	struct perf_evsel *evsel;
+	struct perf_evlist *evlist = perf_evlist__new();
+	size_t i;
+	test_fn_t testcases[] = {
+		test1,
+		test2,
+		test3,
+		test4,
+	};
+
+	TEST_ASSERT_VAL("No memory", evlist);
+
+	err = parse_events(evlist, "cpu-clock");
+	if (err)
+		goto out;
+
+	machines__init(&machines);
+
+	/* setup threads/dso/map/symbols also */
+	machine = setup_fake_machine(&machines);
+	if (!machine)
+		goto out;
+
+	if (verbose > 1)
+		machine__fprintf(machine, stderr);
+
+	evsel = perf_evlist__first(evlist);
+
+	for (i = 0; i < ARRAY_SIZE(testcases); i++) {
+		err = testcases[i](evsel, machine);
+		if (err < 0)
+			break;
+	}
+
+out:
+	/* tear down everything */
+	perf_evlist__delete(evlist);
+	machines__exit(&machines);
+
+	return err;
+}
diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c
new file mode 100644
index 00000000000..821f581fd93
--- /dev/null
+++ b/tools/perf/tests/hists_filter.c
@@ -0,0 +1,289 @@
+#include "perf.h"
+#include "util/debug.h"
+#include "util/symbol.h"
+#include "util/sort.h"
+#include "util/evsel.h"
+#include "util/evlist.h"
+#include "util/machine.h"
+#include "util/thread.h"
+#include "util/parse-events.h"
+#include "tests/tests.h"
+#include "tests/hists_common.h"
+
+struct sample {
+	u32 pid;
+	u64 ip;
+	struct thread *thread;
+	struct map *map;
+	struct symbol *sym;
+};
+
+/* For the numbers, see hists_common.c */
+static struct sample fake_samples[] = {
+	/* perf [kernel] schedule() */
+	{ .pid = FAKE_PID_PERF1, .ip = FAKE_IP_KERNEL_SCHEDULE, },
+	/* perf [perf]   main() */
+	{ .pid = FAKE_PID_PERF1, .ip = FAKE_IP_PERF_MAIN, },
+	/* perf [libc]   malloc() */
+	{ .pid = FAKE_PID_PERF1, .ip = FAKE_IP_LIBC_MALLOC, },
+	/* perf [perf]   main() */
+	{ .pid = FAKE_PID_PERF2, .ip = FAKE_IP_PERF_MAIN, }, /* will be merged */
+	/* perf [perf]   cmd_record() */
+	{ .pid = FAKE_PID_PERF2, .ip = FAKE_IP_PERF_CMD_RECORD, },
+	/* perf [kernel] page_fault() */
+	{ .pid = FAKE_PID_PERF2, .ip = FAKE_IP_KERNEL_PAGE_FAULT, },
+	/* bash [bash]   main() */
+	{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_BASH_MAIN, },
+	/* bash [bash]   xmalloc() */
+	{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_BASH_XMALLOC, },
+	/* bash [libc]   malloc() */
+	{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_LIBC_MALLOC, },
+	/* bash [kernel] page_fault() */
+	{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_KERNEL_PAGE_FAULT, },
+};
+
+static int add_hist_entries(struct perf_evlist *evlist,
+			    struct machine *machine __maybe_unused)
+{
+	struct perf_evsel *evsel;
+	struct addr_location al;
+	struct perf_sample sample = { .period = 100, };
+	size_t i;
+
+	/*
+	 * each evsel will have 10 samples but the 4th sample
+	 * (perf [perf] main) will be collapsed to an existing entry
+	 * so total 9 entries will be in the tree.
+	 */
+	evlist__for_each(evlist, evsel) {
+		for (i = 0; i < ARRAY_SIZE(fake_samples); i++) {
+			const union perf_event event = {
+				.header = {
+					.misc = PERF_RECORD_MISC_USER,
+				},
+			};
+			struct hist_entry_iter iter = {
+				.ops = &hist_iter_normal,
+				.hide_unresolved = false,
+			};
+
+			/* make sure it has no filter at first */
+			evsel->hists.thread_filter = NULL;
+			evsel->hists.dso_filter = NULL;
+			evsel->hists.symbol_filter_str = NULL;
+
+			sample.pid = fake_samples[i].pid;
+			sample.tid = fake_samples[i].pid;
+			sample.ip = fake_samples[i].ip;
+
+			if (perf_event__preprocess_sample(&event, machine, &al,
+							  &sample) < 0)
+				goto out;
+
+			if (hist_entry_iter__add(&iter, &al, evsel, &sample,
+						 PERF_MAX_STACK_DEPTH, NULL) < 0)
+				goto out;
+
+			fake_samples[i].thread = al.thread;
+			fake_samples[i].map = al.map;
+			fake_samples[i].sym = al.sym;
+		}
+	}
+
+	return 0;
+
+out:
+	pr_debug("Not enough memory for adding a hist entry\n");
+	return TEST_FAIL;
+}
+
+int test__hists_filter(void)
+{
+	int err = TEST_FAIL;
+	struct machines machines;
+	struct machine *machine;
+	struct perf_evsel *evsel;
+	struct perf_evlist *evlist = perf_evlist__new();
+
+	TEST_ASSERT_VAL("No memory", evlist);
+
+	err = parse_events(evlist, "cpu-clock");
+	if (err)
+		goto out;
+	err = parse_events(evlist, "task-clock");
+	if (err)
+		goto out;
+
+	/* default sort order (comm,dso,sym) will be used */
+	if (setup_sorting() < 0)
+		goto out;
+
+	machines__init(&machines);
+
+	/* setup threads/dso/map/symbols also */
+	machine = setup_fake_machine(&machines);
+	if (!machine)
+		goto out;
+
+	if (verbose > 1)
+		machine__fprintf(machine, stderr);
+
+	/* process sample events */
+	err = add_hist_entries(evlist, machine);
+	if (err < 0)
+		goto out;
+
+	evlist__for_each(evlist, evsel) {
+		struct hists *hists = &evsel->hists;
+
+		hists__collapse_resort(hists, NULL);
+		hists__output_resort(hists);
+
+		if (verbose > 2) {
+			pr_info("Normal histogram\n");
+			print_hists_out(hists);
+		}
+
+		TEST_ASSERT_VAL("Invalid nr samples",
+				hists->stats.nr_events[PERF_RECORD_SAMPLE] == 10);
+		TEST_ASSERT_VAL("Invalid nr hist entries",
+				hists->nr_entries == 9);
+		TEST_ASSERT_VAL("Invalid total period",
+				hists->stats.total_period == 1000);
+		TEST_ASSERT_VAL("Unmatched nr samples",
+				hists->stats.nr_events[PERF_RECORD_SAMPLE] ==
+				hists->stats.nr_non_filtered_samples);
+		TEST_ASSERT_VAL("Unmatched nr hist entries",
+				hists->nr_entries == hists->nr_non_filtered_entries);
+		TEST_ASSERT_VAL("Unmatched total period",
+				hists->stats.total_period ==
+				hists->stats.total_non_filtered_period);
+
+		/* now applying thread filter for 'bash' */
+		evsel->hists.thread_filter = fake_samples[9].thread;
+		hists__filter_by_thread(hists);
+
+		if (verbose > 2) {
+			pr_info("Histogram for thread filter\n");
+			print_hists_out(hists);
+		}
+
+		/* normal stats should be invariant */
+		TEST_ASSERT_VAL("Invalid nr samples",
+				hists->stats.nr_events[PERF_RECORD_SAMPLE] == 10);
+		TEST_ASSERT_VAL("Invalid nr hist entries",
+				hists->nr_entries == 9);
+		TEST_ASSERT_VAL("Invalid total period",
+				hists->stats.total_period == 1000);
+
+		/* but filter stats are changed */
+		TEST_ASSERT_VAL("Unmatched nr samples for thread filter",
+				hists->stats.nr_non_filtered_samples == 4);
+		TEST_ASSERT_VAL("Unmatched nr hist entries for thread filter",
+				hists->nr_non_filtered_entries == 4);
+		TEST_ASSERT_VAL("Unmatched total period for thread filter",
+				hists->stats.total_non_filtered_period == 400);
+
+		/* remove thread filter first */
+		evsel->hists.thread_filter = NULL;
+		hists__filter_by_thread(hists);
+
+		/* now applying dso filter for 'kernel' */
+		evsel->hists.dso_filter = fake_samples[0].map->dso;
+		hists__filter_by_dso(hists);
+
+		if (verbose > 2) {
+			pr_info("Histogram for dso filter\n");
+			print_hists_out(hists);
+		}
+
+		/* normal stats should be invariant */
+		TEST_ASSERT_VAL("Invalid nr samples",
+				hists->stats.nr_events[PERF_RECORD_SAMPLE] == 10);
+		TEST_ASSERT_VAL("Invalid nr hist entries",
+				hists->nr_entries == 9);
+		TEST_ASSERT_VAL("Invalid total period",
+				hists->stats.total_period == 1000);
+
+		/* but filter stats are changed */
+		TEST_ASSERT_VAL("Unmatched nr samples for dso filter",
+				hists->stats.nr_non_filtered_samples == 3);
+		TEST_ASSERT_VAL("Unmatched nr hist entries for dso filter",
+				hists->nr_non_filtered_entries == 3);
+		TEST_ASSERT_VAL("Unmatched total period for dso filter",
+				hists->stats.total_non_filtered_period == 300);
+
+		/* remove dso filter first */
+		evsel->hists.dso_filter = NULL;
+		hists__filter_by_dso(hists);
+
+		/*
+		 * now applying symbol filter for 'main'.  Also note that
+		 * there's 3 samples that have 'main' symbol but the 4th
+		 * entry of fake_samples was collapsed already so it won't
+		 * be counted as a separate entry but the sample count and
+		 * total period will be remained.
+		 */
+		evsel->hists.symbol_filter_str = "main";
+		hists__filter_by_symbol(hists);
+
+		if (verbose > 2) {
+			pr_info("Histogram for symbol filter\n");
+			print_hists_out(hists);
+		}
+
+		/* normal stats should be invariant */
+		TEST_ASSERT_VAL("Invalid nr samples",
+				hists->stats.nr_events[PERF_RECORD_SAMPLE] == 10);
+		TEST_ASSERT_VAL("Invalid nr hist entries",
+				hists->nr_entries == 9);
+		TEST_ASSERT_VAL("Invalid total period",
+				hists->stats.total_period == 1000);
+
+		/* but filter stats are changed */
+		TEST_ASSERT_VAL("Unmatched nr samples for symbol filter",
+				hists->stats.nr_non_filtered_samples == 3);
+		TEST_ASSERT_VAL("Unmatched nr hist entries for symbol filter",
+				hists->nr_non_filtered_entries == 2);
+		TEST_ASSERT_VAL("Unmatched total period for symbol filter",
+				hists->stats.total_non_filtered_period == 300);
+
+		/* now applying all filters at once. */
+		evsel->hists.thread_filter = fake_samples[1].thread;
+		evsel->hists.dso_filter = fake_samples[1].map->dso;
+		hists__filter_by_thread(hists);
+		hists__filter_by_dso(hists);
+
+		if (verbose > 2) {
+			pr_info("Histogram for all filters\n");
+			print_hists_out(hists);
+		}
+
+		/* normal stats should be invariant */
+		TEST_ASSERT_VAL("Invalid nr samples",
+				hists->stats.nr_events[PERF_RECORD_SAMPLE] == 10);
+		TEST_ASSERT_VAL("Invalid nr hist entries",
+				hists->nr_entries == 9);
+		TEST_ASSERT_VAL("Invalid total period",
+				hists->stats.total_period == 1000);
+
+		/* but filter stats are changed */
+		TEST_ASSERT_VAL("Unmatched nr samples for all filter",
+				hists->stats.nr_non_filtered_samples == 2);
+		TEST_ASSERT_VAL("Unmatched nr hist entries for all filter",
+				hists->nr_non_filtered_entries == 1);
+		TEST_ASSERT_VAL("Unmatched total period for all filter",
+				hists->stats.total_non_filtered_period == 200);
+	}
+
+
+	err = TEST_OK;
+
+out:
+	/* tear down everything */
+	perf_evlist__delete(evlist);
+	reset_output_field();
+	machines__exit(&machines);
+
+	return err;
+}
diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c
new file mode 100644
index 00000000000..d4b34b0f50a
--- /dev/null
+++ b/tools/perf/tests/hists_link.c
@@ -0,0 +1,339 @@
+#include "perf.h"
+#include "tests.h"
+#include "debug.h"
+#include "symbol.h"
+#include "sort.h"
+#include "evsel.h"
+#include "evlist.h"
+#include "machine.h"
+#include "thread.h"
+#include "parse-events.h"
+#include "hists_common.h"
+
+struct sample {
+	u32 pid;
+	u64 ip;
+	struct thread *thread;
+	struct map *map;
+	struct symbol *sym;
+};
+
+/* For the numbers, see hists_common.c */
+static struct sample fake_common_samples[] = {
+	/* perf [kernel] schedule() */
+	{ .pid = FAKE_PID_PERF1, .ip = FAKE_IP_KERNEL_SCHEDULE, },
+	/* perf [perf]   main() */
+	{ .pid = FAKE_PID_PERF2, .ip = FAKE_IP_PERF_MAIN, },
+	/* perf [perf]   cmd_record() */
+	{ .pid = FAKE_PID_PERF2, .ip = FAKE_IP_PERF_CMD_RECORD, },
+	/* bash [bash]   xmalloc() */
+	{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_BASH_XMALLOC, },
+	/* bash [libc]   malloc() */
+	{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_LIBC_MALLOC, },
+};
+
+static struct sample fake_samples[][5] = {
+	{
+		/* perf [perf]   run_command() */
+		{ .pid = FAKE_PID_PERF1, .ip = FAKE_IP_PERF_RUN_COMMAND, },
+		/* perf [libc]   malloc() */
+		{ .pid = FAKE_PID_PERF1, .ip = FAKE_IP_LIBC_MALLOC, },
+		/* perf [kernel] page_fault() */
+		{ .pid = FAKE_PID_PERF1, .ip = FAKE_IP_KERNEL_PAGE_FAULT, },
+		/* perf [kernel] sys_perf_event_open() */
+		{ .pid = FAKE_PID_PERF2, .ip = FAKE_IP_KERNEL_SYS_PERF_EVENT_OPEN, },
+		/* bash [libc]   free() */
+		{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_LIBC_FREE, },
+	},
+	{
+		/* perf [libc]   free() */
+		{ .pid = FAKE_PID_PERF2, .ip = FAKE_IP_LIBC_FREE, },
+		/* bash [libc]   malloc() */
+		{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_LIBC_MALLOC, }, /* will be merged */
+		/* bash [bash]   xfee() */
+		{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_BASH_XFREE, },
+		/* bash [libc]   realloc() */
+		{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_LIBC_REALLOC, },
+		/* bash [kernel] page_fault() */
+		{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_KERNEL_PAGE_FAULT, },
+	},
+};
+
+static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
+{
+	struct perf_evsel *evsel;
+	struct addr_location al;
+	struct hist_entry *he;
+	struct perf_sample sample = { .period = 1, };
+	size_t i = 0, k;
+
+	/*
+	 * each evsel will have 10 samples - 5 common and 5 distinct.
+	 * However the second evsel also has a collapsed entry for
+	 * "bash [libc] malloc" so total 9 entries will be in the tree.
+	 */
+	evlist__for_each(evlist, evsel) {
+		for (k = 0; k < ARRAY_SIZE(fake_common_samples); k++) {
+			const union perf_event event = {
+				.header = {
+					.misc = PERF_RECORD_MISC_USER,
+				},
+			};
+
+			sample.pid = fake_common_samples[k].pid;
+			sample.tid = fake_common_samples[k].pid;
+			sample.ip = fake_common_samples[k].ip;
+			if (perf_event__preprocess_sample(&event, machine, &al,
+							  &sample) < 0)
+				goto out;
+
+			he = __hists__add_entry(&evsel->hists, &al, NULL,
+						NULL, NULL, 1, 1, 0, true);
+			if (he == NULL)
+				goto out;
+
+			fake_common_samples[k].thread = al.thread;
+			fake_common_samples[k].map = al.map;
+			fake_common_samples[k].sym = al.sym;
+		}
+
+		for (k = 0; k < ARRAY_SIZE(fake_samples[i]); k++) {
+			const union perf_event event = {
+				.header = {
+					.misc = PERF_RECORD_MISC_USER,
+				},
+			};
+
+			sample.pid = fake_samples[i][k].pid;
+			sample.tid = fake_samples[i][k].pid;
+			sample.ip = fake_samples[i][k].ip;
+			if (perf_event__preprocess_sample(&event, machine, &al,
+							  &sample) < 0)
+				goto out;
+
+			he = __hists__add_entry(&evsel->hists, &al, NULL,
+						NULL, NULL, 1, 1, 0, true);
+			if (he == NULL)
+				goto out;
+
+			fake_samples[i][k].thread = al.thread;
+			fake_samples[i][k].map = al.map;
+			fake_samples[i][k].sym = al.sym;
+		}
+		i++;
+	}
+
+	return 0;
+
+out:
+	pr_debug("Not enough memory for adding a hist entry\n");
+	return -1;
+}
+
+static int find_sample(struct sample *samples, size_t nr_samples,
+		       struct thread *t, struct map *m, struct symbol *s)
+{
+	while (nr_samples--) {
+		if (samples->thread == t && samples->map == m &&
+		    samples->sym == s)
+			return 1;
+		samples++;
+	}
+	return 0;
+}
+
+static int __validate_match(struct hists *hists)
+{
+	size_t count = 0;
+	struct rb_root *root;
+	struct rb_node *node;
+
+	/*
+	 * Only entries from fake_common_samples should have a pair.
+	 */
+	if (sort__need_collapse)
+		root = &hists->entries_collapsed;
+	else
+		root = hists->entries_in;
+
+	node = rb_first(root);
+	while (node) {
+		struct hist_entry *he;
+
+		he = rb_entry(node, struct hist_entry, rb_node_in);
+
+		if (hist_entry__has_pairs(he)) {
+			if (find_sample(fake_common_samples,
+					ARRAY_SIZE(fake_common_samples),
+					he->thread, he->ms.map, he->ms.sym)) {
+				count++;
+			} else {
+				pr_debug("Can't find the matched entry\n");
+				return -1;
+			}
+		}
+
+		node = rb_next(node);
+	}
+
+	if (count != ARRAY_SIZE(fake_common_samples)) {
+		pr_debug("Invalid count for matched entries: %zd of %zd\n",
+			 count, ARRAY_SIZE(fake_common_samples));
+		return -1;
+	}
+
+	return 0;
+}
+
+static int validate_match(struct hists *leader, struct hists *other)
+{
+	return __validate_match(leader) || __validate_match(other);
+}
+
+static int __validate_link(struct hists *hists, int idx)
+{
+	size_t count = 0;
+	size_t count_pair = 0;
+	size_t count_dummy = 0;
+	struct rb_root *root;
+	struct rb_node *node;
+
+	/*
+	 * Leader hists (idx = 0) will have dummy entries from other,
+	 * and some entries will have no pair.  However every entry
+	 * in other hists should have (dummy) pair.
+	 */
+	if (sort__need_collapse)
+		root = &hists->entries_collapsed;
+	else
+		root = hists->entries_in;
+
+	node = rb_first(root);
+	while (node) {
+		struct hist_entry *he;
+
+		he = rb_entry(node, struct hist_entry, rb_node_in);
+
+		if (hist_entry__has_pairs(he)) {
+			if (!find_sample(fake_common_samples,
+					 ARRAY_SIZE(fake_common_samples),
+					 he->thread, he->ms.map, he->ms.sym) &&
+			    !find_sample(fake_samples[idx],
+					 ARRAY_SIZE(fake_samples[idx]),
+					 he->thread, he->ms.map, he->ms.sym)) {
+				count_dummy++;
+			}
+			count_pair++;
+		} else if (idx) {
+			pr_debug("A entry from the other hists should have pair\n");
+			return -1;
+		}
+
+		count++;
+		node = rb_next(node);
+	}
+
+	/*
+	 * Note that we have a entry collapsed in the other (idx = 1) hists.
+	 */
+	if (idx == 0) {
+		if (count_dummy != ARRAY_SIZE(fake_samples[1]) - 1) {
+			pr_debug("Invalid count of dummy entries: %zd of %zd\n",
+				 count_dummy, ARRAY_SIZE(fake_samples[1]) - 1);
+			return -1;
+		}
+		if (count != count_pair + ARRAY_SIZE(fake_samples[0])) {
+			pr_debug("Invalid count of total leader entries: %zd of %zd\n",
+				 count, count_pair + ARRAY_SIZE(fake_samples[0]));
+			return -1;
+		}
+	} else {
+		if (count != count_pair) {
+			pr_debug("Invalid count of total other entries: %zd of %zd\n",
+				 count, count_pair);
+			return -1;
+		}
+		if (count_dummy > 0) {
+			pr_debug("Other hists should not have dummy entries: %zd\n",
+				 count_dummy);
+			return -1;
+		}
+	}
+
+	return 0;
+}
+
+static int validate_link(struct hists *leader, struct hists *other)
+{
+	return __validate_link(leader, 0) || __validate_link(other, 1);
+}
+
+int test__hists_link(void)
+{
+	int err = -1;
+	struct machines machines;
+	struct machine *machine = NULL;
+	struct perf_evsel *evsel, *first;
+	struct perf_evlist *evlist = perf_evlist__new();
+
+	if (evlist == NULL)
+                return -ENOMEM;
+
+	err = parse_events(evlist, "cpu-clock");
+	if (err)
+		goto out;
+	err = parse_events(evlist, "task-clock");
+	if (err)
+		goto out;
+
+	/* default sort order (comm,dso,sym) will be used */
+	if (setup_sorting() < 0)
+		goto out;
+
+	machines__init(&machines);
+
+	/* setup threads/dso/map/symbols also */
+	machine = setup_fake_machine(&machines);
+	if (!machine)
+		goto out;
+
+	if (verbose > 1)
+		machine__fprintf(machine, stderr);
+
+	/* process sample events */
+	err = add_hist_entries(evlist, machine);
+	if (err < 0)
+		goto out;
+
+	evlist__for_each(evlist, evsel) {
+		hists__collapse_resort(&evsel->hists, NULL);
+
+		if (verbose > 2)
+			print_hists_in(&evsel->hists);
+	}
+
+	first = perf_evlist__first(evlist);
+	evsel = perf_evlist__last(evlist);
+
+	/* match common entries */
+	hists__match(&first->hists, &evsel->hists);
+	err = validate_match(&first->hists, &evsel->hists);
+	if (err)
+		goto out;
+
+	/* link common and/or dummy entries */
+	hists__link(&first->hists, &evsel->hists);
+	err = validate_link(&first->hists, &evsel->hists);
+	if (err)
+		goto out;
+
+	err = 0;
+
+out:
+	/* tear down everything */
+	perf_evlist__delete(evlist);
+	reset_output_field();
+	machines__exit(&machines);
+
+	return err;
+}
diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c
new file mode 100644
index 00000000000..e3bbd6c54c1
--- /dev/null
+++ b/tools/perf/tests/hists_output.c
@@ -0,0 +1,621 @@
+#include "perf.h"
+#include "util/debug.h"
+#include "util/symbol.h"
+#include "util/sort.h"
+#include "util/evsel.h"
+#include "util/evlist.h"
+#include "util/machine.h"
+#include "util/thread.h"
+#include "util/parse-events.h"
+#include "tests/tests.h"
+#include "tests/hists_common.h"
+
+struct sample {
+	u32 cpu;
+	u32 pid;
+	u64 ip;
+	struct thread *thread;
+	struct map *map;
+	struct symbol *sym;
+};
+
+/* For the numbers, see hists_common.c */
+static struct sample fake_samples[] = {
+	/* perf [kernel] schedule() */
+	{ .cpu = 0, .pid = FAKE_PID_PERF1, .ip = FAKE_IP_KERNEL_SCHEDULE, },
+	/* perf [perf]   main() */
+	{ .cpu = 1, .pid = FAKE_PID_PERF1, .ip = FAKE_IP_PERF_MAIN, },
+	/* perf [perf]   cmd_record() */
+	{ .cpu = 1, .pid = FAKE_PID_PERF1, .ip = FAKE_IP_PERF_CMD_RECORD, },
+	/* perf [libc]   malloc() */
+	{ .cpu = 1, .pid = FAKE_PID_PERF1, .ip = FAKE_IP_LIBC_MALLOC, },
+	/* perf [libc]   free() */
+	{ .cpu = 2, .pid = FAKE_PID_PERF1, .ip = FAKE_IP_LIBC_FREE, },
+	/* perf [perf]   main() */
+	{ .cpu = 2, .pid = FAKE_PID_PERF2, .ip = FAKE_IP_PERF_MAIN, },
+	/* perf [kernel] page_fault() */
+	{ .cpu = 2, .pid = FAKE_PID_PERF2, .ip = FAKE_IP_KERNEL_PAGE_FAULT, },
+	/* bash [bash]   main() */
+	{ .cpu = 3, .pid = FAKE_PID_BASH,  .ip = FAKE_IP_BASH_MAIN, },
+	/* bash [bash]   xmalloc() */
+	{ .cpu = 0, .pid = FAKE_PID_BASH,  .ip = FAKE_IP_BASH_XMALLOC, },
+	/* bash [kernel] page_fault() */
+	{ .cpu = 1, .pid = FAKE_PID_BASH,  .ip = FAKE_IP_KERNEL_PAGE_FAULT, },
+};
+
+static int add_hist_entries(struct hists *hists, struct machine *machine)
+{
+	struct addr_location al;
+	struct perf_evsel *evsel = hists_to_evsel(hists);
+	struct perf_sample sample = { .period = 100, };
+	size_t i;
+
+	for (i = 0; i < ARRAY_SIZE(fake_samples); i++) {
+		const union perf_event event = {
+			.header = {
+				.misc = PERF_RECORD_MISC_USER,
+			},
+		};
+		struct hist_entry_iter iter = {
+			.ops = &hist_iter_normal,
+			.hide_unresolved = false,
+		};
+
+		sample.cpu = fake_samples[i].cpu;
+		sample.pid = fake_samples[i].pid;
+		sample.tid = fake_samples[i].pid;
+		sample.ip = fake_samples[i].ip;
+
+		if (perf_event__preprocess_sample(&event, machine, &al,
+						  &sample) < 0)
+			goto out;
+
+		if (hist_entry_iter__add(&iter, &al, evsel, &sample,
+					 PERF_MAX_STACK_DEPTH, NULL) < 0)
+			goto out;
+
+		fake_samples[i].thread = al.thread;
+		fake_samples[i].map = al.map;
+		fake_samples[i].sym = al.sym;
+	}
+
+	return TEST_OK;
+
+out:
+	pr_debug("Not enough memory for adding a hist entry\n");
+	return TEST_FAIL;
+}
+
+static void del_hist_entries(struct hists *hists)
+{
+	struct hist_entry *he;
+	struct rb_root *root_in;
+	struct rb_root *root_out;
+	struct rb_node *node;
+
+	if (sort__need_collapse)
+		root_in = &hists->entries_collapsed;
+	else
+		root_in = hists->entries_in;
+
+	root_out = &hists->entries;
+
+	while (!RB_EMPTY_ROOT(root_out)) {
+		node = rb_first(root_out);
+
+		he = rb_entry(node, struct hist_entry, rb_node);
+		rb_erase(node, root_out);
+		rb_erase(&he->rb_node_in, root_in);
+		hist_entry__free(he);
+	}
+}
+
+typedef int (*test_fn_t)(struct perf_evsel *, struct machine *);
+
+#define COMM(he)  (thread__comm_str(he->thread))
+#define DSO(he)   (he->ms.map->dso->short_name)
+#define SYM(he)   (he->ms.sym->name)
+#define CPU(he)   (he->cpu)
+#define PID(he)   (he->thread->tid)
+
+/* default sort keys (no field) */
+static int test1(struct perf_evsel *evsel, struct machine *machine)
+{
+	int err;
+	struct hists *hists = &evsel->hists;
+	struct hist_entry *he;
+	struct rb_root *root;
+	struct rb_node *node;
+
+	field_order = NULL;
+	sort_order = NULL; /* equivalent to sort_order = "comm,dso,sym" */
+
+	setup_sorting();
+
+	/*
+	 * expected output:
+	 *
+	 * Overhead  Command  Shared Object          Symbol
+	 * ========  =======  =============  ==============
+	 *   20.00%     perf  perf           [.] main
+	 *   10.00%     bash  [kernel]       [k] page_fault
+	 *   10.00%     bash  bash           [.] main
+	 *   10.00%     bash  bash           [.] xmalloc
+	 *   10.00%     perf  [kernel]       [k] page_fault
+	 *   10.00%     perf  [kernel]       [k] schedule
+	 *   10.00%     perf  libc           [.] free
+	 *   10.00%     perf  libc           [.] malloc
+	 *   10.00%     perf  perf           [.] cmd_record
+	 */
+	err = add_hist_entries(hists, machine);
+	if (err < 0)
+		goto out;
+
+	hists__collapse_resort(hists, NULL);
+	hists__output_resort(hists);
+
+	if (verbose > 2) {
+		pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
+		print_hists_out(hists);
+	}
+
+	root = &evsel->hists.entries;
+	node = rb_first(root);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			!strcmp(COMM(he), "perf") && !strcmp(DSO(he), "perf") &&
+			!strcmp(SYM(he), "main") && he->stat.period == 200);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			!strcmp(COMM(he), "bash") && !strcmp(DSO(he), "[kernel]") &&
+			!strcmp(SYM(he), "page_fault") && he->stat.period == 100);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			!strcmp(COMM(he), "bash") && !strcmp(DSO(he), "bash") &&
+			!strcmp(SYM(he), "main") && he->stat.period == 100);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			!strcmp(COMM(he), "bash") && !strcmp(DSO(he), "bash") &&
+			!strcmp(SYM(he), "xmalloc") && he->stat.period == 100);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			!strcmp(COMM(he), "perf") && !strcmp(DSO(he), "[kernel]") &&
+			!strcmp(SYM(he), "page_fault") && he->stat.period == 100);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			!strcmp(COMM(he), "perf") && !strcmp(DSO(he), "[kernel]") &&
+			!strcmp(SYM(he), "schedule") && he->stat.period == 100);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			!strcmp(COMM(he), "perf") && !strcmp(DSO(he), "libc") &&
+			!strcmp(SYM(he), "free") && he->stat.period == 100);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			!strcmp(COMM(he), "perf") && !strcmp(DSO(he), "libc") &&
+			!strcmp(SYM(he), "malloc") && he->stat.period == 100);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			!strcmp(COMM(he), "perf") && !strcmp(DSO(he), "perf") &&
+			!strcmp(SYM(he), "cmd_record") && he->stat.period == 100);
+
+out:
+	del_hist_entries(hists);
+	reset_output_field();
+	return err;
+}
+
+/* mixed fields and sort keys */
+static int test2(struct perf_evsel *evsel, struct machine *machine)
+{
+	int err;
+	struct hists *hists = &evsel->hists;
+	struct hist_entry *he;
+	struct rb_root *root;
+	struct rb_node *node;
+
+	field_order = "overhead,cpu";
+	sort_order = "pid";
+
+	setup_sorting();
+
+	/*
+	 * expected output:
+	 *
+	 * Overhead  CPU  Command:  Pid
+	 * ========  ===  =============
+	 *   30.00%    1  perf   :  100
+	 *   10.00%    0  perf   :  100
+	 *   10.00%    2  perf   :  100
+	 *   20.00%    2  perf   :  200
+	 *   10.00%    0  bash   :  300
+	 *   10.00%    1  bash   :  300
+	 *   10.00%    3  bash   :  300
+	 */
+	err = add_hist_entries(hists, machine);
+	if (err < 0)
+		goto out;
+
+	hists__collapse_resort(hists, NULL);
+	hists__output_resort(hists);
+
+	if (verbose > 2) {
+		pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
+		print_hists_out(hists);
+	}
+
+	root = &evsel->hists.entries;
+	node = rb_first(root);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			CPU(he) == 1 && PID(he) == 100 && he->stat.period == 300);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			CPU(he) == 0 && PID(he) == 100 && he->stat.period == 100);
+
+out:
+	del_hist_entries(hists);
+	reset_output_field();
+	return err;
+}
+
+/* fields only (no sort key) */
+static int test3(struct perf_evsel *evsel, struct machine *machine)
+{
+	int err;
+	struct hists *hists = &evsel->hists;
+	struct hist_entry *he;
+	struct rb_root *root;
+	struct rb_node *node;
+
+	field_order = "comm,overhead,dso";
+	sort_order = NULL;
+
+	setup_sorting();
+
+	/*
+	 * expected output:
+	 *
+	 * Command  Overhead  Shared Object
+	 * =======  ========  =============
+	 *    bash    20.00%  bash
+	 *    bash    10.00%  [kernel]
+	 *    perf    30.00%  perf
+	 *    perf    20.00%  [kernel]
+	 *    perf    20.00%  libc
+	 */
+	err = add_hist_entries(hists, machine);
+	if (err < 0)
+		goto out;
+
+	hists__collapse_resort(hists, NULL);
+	hists__output_resort(hists);
+
+	if (verbose > 2) {
+		pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
+		print_hists_out(hists);
+	}
+
+	root = &evsel->hists.entries;
+	node = rb_first(root);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			!strcmp(COMM(he), "bash") && !strcmp(DSO(he), "bash") &&
+			he->stat.period == 200);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			!strcmp(COMM(he), "bash") && !strcmp(DSO(he), "[kernel]") &&
+			he->stat.period == 100);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			!strcmp(COMM(he), "perf") && !strcmp(DSO(he), "perf") &&
+			he->stat.period == 300);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			!strcmp(COMM(he), "perf") && !strcmp(DSO(he), "[kernel]") &&
+			he->stat.period == 200);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			!strcmp(COMM(he), "perf") && !strcmp(DSO(he), "libc") &&
+			he->stat.period == 200);
+
+out:
+	del_hist_entries(hists);
+	reset_output_field();
+	return err;
+}
+
+/* handle duplicate 'dso' field */
+static int test4(struct perf_evsel *evsel, struct machine *machine)
+{
+	int err;
+	struct hists *hists = &evsel->hists;
+	struct hist_entry *he;
+	struct rb_root *root;
+	struct rb_node *node;
+
+	field_order = "dso,sym,comm,overhead,dso";
+	sort_order = "sym";
+
+	setup_sorting();
+
+	/*
+	 * expected output:
+	 *
+	 * Shared Object          Symbol  Command  Overhead
+	 * =============  ==============  =======  ========
+	 *          perf  [.] cmd_record     perf    10.00%
+	 *          libc  [.] free           perf    10.00%
+	 *          bash  [.] main           bash    10.00%
+	 *          perf  [.] main           perf    20.00%
+	 *          libc  [.] malloc         perf    10.00%
+	 *      [kernel]  [k] page_fault     bash    10.00%
+	 *      [kernel]  [k] page_fault     perf    10.00%
+	 *      [kernel]  [k] schedule       perf    10.00%
+	 *          bash  [.] xmalloc        bash    10.00%
+	 */
+	err = add_hist_entries(hists, machine);
+	if (err < 0)
+		goto out;
+
+	hists__collapse_resort(hists, NULL);
+	hists__output_resort(hists);
+
+	if (verbose > 2) {
+		pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
+		print_hists_out(hists);
+	}
+
+	root = &evsel->hists.entries;
+	node = rb_first(root);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			!strcmp(DSO(he), "perf") && !strcmp(SYM(he), "cmd_record") &&
+			!strcmp(COMM(he), "perf") && he->stat.period == 100);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			!strcmp(DSO(he), "libc") && !strcmp(SYM(he), "free") &&
+			!strcmp(COMM(he), "perf") && he->stat.period == 100);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			!strcmp(DSO(he), "bash") && !strcmp(SYM(he), "main") &&
+			!strcmp(COMM(he), "bash") && he->stat.period == 100);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			!strcmp(DSO(he), "perf") && !strcmp(SYM(he), "main") &&
+			!strcmp(COMM(he), "perf") && he->stat.period == 200);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			!strcmp(DSO(he), "libc") && !strcmp(SYM(he), "malloc") &&
+			!strcmp(COMM(he), "perf") && he->stat.period == 100);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			!strcmp(DSO(he), "[kernel]") && !strcmp(SYM(he), "page_fault") &&
+			!strcmp(COMM(he), "bash") && he->stat.period == 100);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			!strcmp(DSO(he), "[kernel]") && !strcmp(SYM(he), "page_fault") &&
+			!strcmp(COMM(he), "perf") && he->stat.period == 100);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			!strcmp(DSO(he), "[kernel]") && !strcmp(SYM(he), "schedule") &&
+			!strcmp(COMM(he), "perf") && he->stat.period == 100);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			!strcmp(DSO(he), "bash") && !strcmp(SYM(he), "xmalloc") &&
+			!strcmp(COMM(he), "bash") && he->stat.period == 100);
+
+out:
+	del_hist_entries(hists);
+	reset_output_field();
+	return err;
+}
+
+/* full sort keys w/o overhead field */
+static int test5(struct perf_evsel *evsel, struct machine *machine)
+{
+	int err;
+	struct hists *hists = &evsel->hists;
+	struct hist_entry *he;
+	struct rb_root *root;
+	struct rb_node *node;
+
+	field_order = "cpu,pid,comm,dso,sym";
+	sort_order = "dso,pid";
+
+	setup_sorting();
+
+	/*
+	 * expected output:
+	 *
+	 * CPU  Command:  Pid  Command  Shared Object          Symbol
+	 * ===  =============  =======  =============  ==============
+	 *   0     perf:  100     perf       [kernel]  [k] schedule
+	 *   2     perf:  200     perf       [kernel]  [k] page_fault
+	 *   1     bash:  300     bash       [kernel]  [k] page_fault
+	 *   0     bash:  300     bash           bash  [.] xmalloc
+	 *   3     bash:  300     bash           bash  [.] main
+	 *   1     perf:  100     perf           libc  [.] malloc
+	 *   2     perf:  100     perf           libc  [.] free
+	 *   1     perf:  100     perf           perf  [.] cmd_record
+	 *   1     perf:  100     perf           perf  [.] main
+	 *   2     perf:  200     perf           perf  [.] main
+	 */
+	err = add_hist_entries(hists, machine);
+	if (err < 0)
+		goto out;
+
+	hists__collapse_resort(hists, NULL);
+	hists__output_resort(hists);
+
+	if (verbose > 2) {
+		pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
+		print_hists_out(hists);
+	}
+
+	root = &evsel->hists.entries;
+	node = rb_first(root);
+	he = rb_entry(node, struct hist_entry, rb_node);
+
+	TEST_ASSERT_VAL("Invalid hist entry",
+			CPU(he) == 0 && PID(he) == 100 &&
+			!strcmp(COMM(he), "perf") && !strcmp(DSO(he), "[kernel]") &&
+			!strcmp(SYM(he), "schedule") && he->stat.period == 100);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			CPU(he) == 2 && PID(he) == 200 &&
+			!strcmp(COMM(he), "perf") && !strcmp(DSO(he), "[kernel]") &&
+			!strcmp(SYM(he), "page_fault") && he->stat.period == 100);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			CPU(he) == 1 && PID(he) == 300 &&
+			!strcmp(COMM(he), "bash") && !strcmp(DSO(he), "[kernel]") &&
+			!strcmp(SYM(he), "page_fault") && he->stat.period == 100);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			CPU(he) == 0 && PID(he) == 300 &&
+			!strcmp(COMM(he), "bash") && !strcmp(DSO(he), "bash") &&
+			!strcmp(SYM(he), "xmalloc") && he->stat.period == 100);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			CPU(he) == 3 && PID(he) == 300 &&
+			!strcmp(COMM(he), "bash") && !strcmp(DSO(he), "bash") &&
+			!strcmp(SYM(he), "main") && he->stat.period == 100);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			CPU(he) == 1 && PID(he) == 100 &&
+			!strcmp(COMM(he), "perf") && !strcmp(DSO(he), "libc") &&
+			!strcmp(SYM(he), "malloc") && he->stat.period == 100);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			CPU(he) == 2 && PID(he) == 100 &&
+			!strcmp(COMM(he), "perf") && !strcmp(DSO(he), "libc") &&
+			!strcmp(SYM(he), "free") && he->stat.period == 100);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			CPU(he) == 1 && PID(he) == 100 &&
+			!strcmp(COMM(he), "perf") && !strcmp(DSO(he), "perf") &&
+			!strcmp(SYM(he), "cmd_record") && he->stat.period == 100);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			CPU(he) == 1 && PID(he) == 100 &&
+			!strcmp(COMM(he), "perf") && !strcmp(DSO(he), "perf") &&
+			!strcmp(SYM(he), "main") && he->stat.period == 100);
+
+	node = rb_next(node);
+	he = rb_entry(node, struct hist_entry, rb_node);
+	TEST_ASSERT_VAL("Invalid hist entry",
+			CPU(he) == 2 && PID(he) == 200 &&
+			!strcmp(COMM(he), "perf") && !strcmp(DSO(he), "perf") &&
+			!strcmp(SYM(he), "main") && he->stat.period == 100);
+
+out:
+	del_hist_entries(hists);
+	reset_output_field();
+	return err;
+}
+
+int test__hists_output(void)
+{
+	int err = TEST_FAIL;
+	struct machines machines;
+	struct machine *machine;
+	struct perf_evsel *evsel;
+	struct perf_evlist *evlist = perf_evlist__new();
+	size_t i;
+	test_fn_t testcases[] = {
+		test1,
+		test2,
+		test3,
+		test4,
+		test5,
+	};
+
+	TEST_ASSERT_VAL("No memory", evlist);
+
+	err = parse_events(evlist, "cpu-clock");
+	if (err)
+		goto out;
+
+	machines__init(&machines);
+
+	/* setup threads/dso/map/symbols also */
+	machine = setup_fake_machine(&machines);
+	if (!machine)
+		goto out;
+
+	if (verbose > 1)
+		machine__fprintf(machine, stderr);
+
+	evsel = perf_evlist__first(evlist);
+
+	for (i = 0; i < ARRAY_SIZE(testcases); i++) {
+		err = testcases[i](evsel, machine);
+		if (err < 0)
+			break;
+	}
+
+out:
+	/* tear down everything */
+	perf_evlist__delete(evlist);
+	machines__exit(&machines);
+
+	return err;
+}
diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c
new file mode 100644
index 00000000000..7a5ab7b0b8f
--- /dev/null
+++ b/tools/perf/tests/keep-tracking.c
@@ -0,0 +1,152 @@
+#include <linux/types.h>
+#include <unistd.h>
+#include <sys/prctl.h>
+
+#include "parse-events.h"
+#include "evlist.h"
+#include "evsel.h"
+#include "thread_map.h"
+#include "cpumap.h"
+#include "tests.h"
+
+#define CHECK__(x) {				\
+	while ((x) < 0) {			\
+		pr_debug(#x " failed!\n");	\
+		goto out_err;			\
+	}					\
+}
+
+#define CHECK_NOT_NULL__(x) {			\
+	while ((x) == NULL) {			\
+		pr_debug(#x " failed!\n");	\
+		goto out_err;			\
+	}					\
+}
+
+static int find_comm(struct perf_evlist *evlist, const char *comm)
+{
+	union perf_event *event;
+	int i, found;
+
+	found = 0;
+	for (i = 0; i < evlist->nr_mmaps; i++) {
+		while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
+			if (event->header.type == PERF_RECORD_COMM &&
+			    (pid_t)event->comm.pid == getpid() &&
+			    (pid_t)event->comm.tid == getpid() &&
+			    strcmp(event->comm.comm, comm) == 0)
+				found += 1;
+			perf_evlist__mmap_consume(evlist, i);
+		}
+	}
+	return found;
+}
+
+/**
+ * test__keep_tracking - test using a dummy software event to keep tracking.
+ *
+ * This function implements a test that checks that tracking events continue
+ * when an event is disabled but a dummy software event is not disabled.  If the
+ * test passes %0 is returned, otherwise %-1 is returned.
+ */
+int test__keep_tracking(void)
+{
+	struct record_opts opts = {
+		.mmap_pages	     = UINT_MAX,
+		.user_freq	     = UINT_MAX,
+		.user_interval	     = ULLONG_MAX,
+		.freq		     = 4000,
+		.target		     = {
+			.uses_mmap   = true,
+		},
+	};
+	struct thread_map *threads = NULL;
+	struct cpu_map *cpus = NULL;
+	struct perf_evlist *evlist = NULL;
+	struct perf_evsel *evsel = NULL;
+	int found, err = -1;
+	const char *comm;
+
+	threads = thread_map__new(-1, getpid(), UINT_MAX);
+	CHECK_NOT_NULL__(threads);
+
+	cpus = cpu_map__new(NULL);
+	CHECK_NOT_NULL__(cpus);
+
+	evlist = perf_evlist__new();
+	CHECK_NOT_NULL__(evlist);
+
+	perf_evlist__set_maps(evlist, cpus, threads);
+
+	CHECK__(parse_events(evlist, "dummy:u"));
+	CHECK__(parse_events(evlist, "cycles:u"));
+
+	perf_evlist__config(evlist, &opts);
+
+	evsel = perf_evlist__first(evlist);
+
+	evsel->attr.comm = 1;
+	evsel->attr.disabled = 1;
+	evsel->attr.enable_on_exec = 0;
+
+	if (perf_evlist__open(evlist) < 0) {
+		fprintf(stderr, " (not supported)");
+		err = 0;
+		goto out_err;
+	}
+
+	CHECK__(perf_evlist__mmap(evlist, UINT_MAX, false));
+
+	/*
+	 * First, test that a 'comm' event can be found when the event is
+	 * enabled.
+	 */
+
+	perf_evlist__enable(evlist);
+
+	comm = "Test COMM 1";
+	CHECK__(prctl(PR_SET_NAME, (unsigned long)comm, 0, 0, 0));
+
+	perf_evlist__disable(evlist);
+
+	found = find_comm(evlist, comm);
+	if (found != 1) {
+		pr_debug("First time, failed to find tracking event.\n");
+		goto out_err;
+	}
+
+	/*
+	 * Secondly, test that a 'comm' event can be found when the event is
+	 * disabled with the dummy event still enabled.
+	 */
+
+	perf_evlist__enable(evlist);
+
+	evsel = perf_evlist__last(evlist);
+
+	CHECK__(perf_evlist__disable_event(evlist, evsel));
+
+	comm = "Test COMM 2";
+	CHECK__(prctl(PR_SET_NAME, (unsigned long)comm, 0, 0, 0));
+
+	perf_evlist__disable(evlist);
+
+	found = find_comm(evlist, comm);
+	if (found != 1) {
+		pr_debug("Seconf time, failed to find tracking event.\n");
+		goto out_err;
+	}
+
+	err = 0;
+
+out_err:
+	if (evlist) {
+		perf_evlist__disable(evlist);
+		perf_evlist__delete(evlist);
+	} else {
+		cpu_map__delete(cpus);
+		thread_map__delete(threads);
+	}
+
+	return err;
+}
diff --git a/tools/perf/tests/make b/tools/perf/tests/make
new file mode 100644
index 00000000000..69a71ff84e0
--- /dev/null
+++ b/tools/perf/tests/make
@@ -0,0 +1,233 @@
+PERF := .
+MK   := Makefile
+
+include config/Makefile.arch
+
+# FIXME looks like x86 is the only arch running tests ;-)
+# we need some IS_(32/64) flag to make this generic
+ifeq ($(IS_X86_64),1)
+lib = lib64
+else
+lib = lib
+endif
+
+has = $(shell which $1 2>/dev/null)
+
+# standard single make variable specified
+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_libdw_dwarf_unwind := NO_LIBDW_DWARF_UNWIND=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
+make_util_pmu_bison_o := util/pmu-bison.o
+make_install        := install
+make_install_bin    := install-bin
+make_install_doc    := install-doc
+make_install_man    := install-man
+make_install_html   := install-html
+make_install_info   := install-info
+make_install_pdf    := install-pdf
+make_static         := LDFLAGS=-static
+
+# 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
+make_minimal        += NO_LIBDW_DWARF_UNWIND=1
+
+# $(run) contains all available tests
+run := make_pure
+run += make_clean_all
+run += make_python_perf_so
+run += make_debug
+run += make_no_libperl
+run += make_no_libpython
+run += make_no_scripts
+run += make_no_newt
+run += make_no_slang
+run += make_no_gtk2
+run += make_no_ui
+run += make_no_demangle
+run += make_no_libelf
+run += make_no_libunwind
+run += make_no_libdw_dwarf_unwind
+run += make_no_backtrace
+run += make_no_libnuma
+run += make_no_libaudit
+run += make_no_libbionic
+run += make_help
+run += make_doc
+run += make_perf_o
+run += make_util_map_o
+run += make_util_pmu_bison_o
+run += make_install
+run += make_install_bin
+# FIXME 'install-*' commented out till they're fixed
+# run += make_install_doc
+# run += make_install_man
+# run += make_install_html
+# run += make_install_info
+# run += make_install_pdf
+run += make_minimal
+run += make_static
+
+ifneq ($(call has,ctags),)
+run += make_tags
+endif
+ifneq ($(call has,cscope),)
+run += make_cscope
+endif
+
+# $(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
+test_make_util_pmu_bison_o := test -f $(PERF)/util/pmu-bison.o
+
+define test_dest_files
+  for file in $(1); do				\
+    if [ ! -x $$TMP_DEST/$$file ]; then		\
+      echo "  failed to find: $$file";		\
+    fi						\
+  done
+endef
+
+installed_files_bin := bin/perf
+installed_files_bin += etc/bash_completion.d/perf
+installed_files_bin += libexec/perf-core/perf-archive
+
+installed_files_plugins := $(lib)/traceevent/plugins/plugin_cfg80211.so
+installed_files_plugins += $(lib)/traceevent/plugins/plugin_scsi.so
+installed_files_plugins += $(lib)/traceevent/plugins/plugin_xen.so
+installed_files_plugins += $(lib)/traceevent/plugins/plugin_function.so
+installed_files_plugins += $(lib)/traceevent/plugins/plugin_sched_switch.so
+installed_files_plugins += $(lib)/traceevent/plugins/plugin_mac80211.so
+installed_files_plugins += $(lib)/traceevent/plugins/plugin_kvm.so
+installed_files_plugins += $(lib)/traceevent/plugins/plugin_kmem.so
+installed_files_plugins += $(lib)/traceevent/plugins/plugin_hrtimer.so
+installed_files_plugins += $(lib)/traceevent/plugins/plugin_jbd2.so
+
+installed_files_all := $(installed_files_bin)
+installed_files_all += $(installed_files_plugins)
+
+test_make_install       := $(call test_dest_files,$(installed_files_all))
+test_make_install_O     := $(call test_dest_files,$(installed_files_all))
+test_make_install_bin   := $(call test_dest_files,$(installed_files_bin))
+test_make_install_bin_O := $(call test_dest_files,$(installed_files_bin))
+
+# FIXME nothing gets installed
+test_make_install_man    := test -f $$TMP_DEST/share/man/man1/perf.1
+test_make_install_man_O  := $(test_make_install_man)
+
+# FIXME nothing gets installed
+test_make_install_doc    := $(test_ok)
+test_make_install_doc_O  := $(test_ok)
+
+# FIXME nothing gets installed
+test_make_install_html   := $(test_ok)
+test_make_install_html_O := $(test_ok)
+
+# FIXME nothing gets installed
+test_make_install_info   := $(test_ok)
+test_make_install_info_O := $(test_ok)
+
+# FIXME nothing gets installed
+test_make_install_pdf    := $(test_ok)
+test_make_install_pdf_O  := $(test_ok)
+
+test_make_python_perf_so_O    := test -f $$TMP_O/python/perf.so
+test_make_perf_o_O            := test -f $$TMP_O/perf.o
+test_make_util_map_o_O        := test -f $$TMP_O/util/map.o
+test_make_util_pmu_bison_o_O := test -f $$TMP_O/util/pmu-bison.o
+
+test_default = test -x $(PERF)/perf
+test = $(if $(test_$1),$(test_$1),$(test_default))
+
+test_default_O = test -x $$TMP_O/perf
+test_O = $(if $(test_$1),$(test_$1),$(test_default_O))
+
+all:
+
+ifdef DEBUG
+d := $(info run   $(run))
+d := $(info run_O $(run_O))
+endif
+
+MAKEFLAGS := --no-print-directory
+
+clean := @(cd $(PERF); make -s -f $(MK) clean >/dev/null)
+
+$(run):
+	$(call clean)
+	@TMP_DEST=$$(mktemp -d); \
+	cmd="cd $(PERF) && make -f $(MK) DESTDIR=$$TMP_DEST $($@)"; \
+	echo "- $@: $$cmd" && echo $$cmd > $@ && \
+	( eval $$cmd ) >> $@ 2>&1; \
+	echo "  test: $(call test,$@)" >> $@ 2>&1; \
+	$(call test,$@) && \
+	rm -rf $@ $$TMP_DEST || (cat $@ ; false)
+
+$(run_O):
+	$(call clean)
+	@TMP_O=$$(mktemp -d); \
+	TMP_DEST=$$(mktemp -d); \
+	cmd="cd $(PERF) && make -f $(MK) O=$$TMP_O DESTDIR=$$TMP_DEST $($(patsubst %_O,%,$@))"; \
+	echo "- $@: $$cmd" && echo $$cmd > $@ && \
+	( eval $$cmd ) >> $@ 2>&1 && \
+	echo "  test: $(call test_O,$@)" >> $@ 2>&1; \
+	$(call test_O,$@) && \
+	rm -rf $@ $$TMP_O $$TMP_DEST || (cat $@ ; false)
+
+tarpkg:
+	@cmd="$(PERF)/tests/perf-targz-src-pkg $(PERF)"; \
+	echo "- $@: $$cmd" && echo $$cmd > $@ && \
+	( eval $$cmd ) >> $@ 2>&1
+	
+
+all: $(run) $(run_O) tarpkg
+	@echo OK
+
+out: $(run_O)
+	@echo OK
+
+.PHONY: all $(run) $(run_O) tarpkg clean
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
new file mode 100644
index 00000000000..142263492f6
--- /dev/null
+++ b/tools/perf/tests/mmap-basic.c
@@ -0,0 +1,148 @@
+#include "evlist.h"
+#include "evsel.h"
+#include "thread_map.h"
+#include "cpumap.h"
+#include "tests.h"
+
+/*
+ * This test will generate random numbers of calls to some getpid syscalls,
+ * then establish an mmap for a group of events that are created to monitor
+ * the syscalls.
+ *
+ * It will receive the events, using mmap, use its PERF_SAMPLE_ID generated
+ * sample.id field to map back to its respective perf_evsel instance.
+ *
+ * Then it checks if the number of syscalls reported as perf events by
+ * the kernel corresponds to the number of syscalls made.
+ */
+int test__basic_mmap(void)
+{
+	int err = -1;
+	union perf_event *event;
+	struct thread_map *threads;
+	struct cpu_map *cpus;
+	struct perf_evlist *evlist;
+	cpu_set_t cpu_set;
+	const char *syscall_names[] = { "getsid", "getppid", "getpgrp",
+					"getpgid", };
+	pid_t (*syscalls[])(void) = { (void *)getsid, getppid, getpgrp,
+				      (void*)getpgid };
+#define nsyscalls ARRAY_SIZE(syscall_names)
+	unsigned int nr_events[nsyscalls],
+		     expected_nr_events[nsyscalls], i, j;
+	struct perf_evsel *evsels[nsyscalls], *evsel;
+
+	threads = thread_map__new(-1, getpid(), UINT_MAX);
+	if (threads == NULL) {
+		pr_debug("thread_map__new\n");
+		return -1;
+	}
+
+	cpus = cpu_map__new(NULL);
+	if (cpus == NULL) {
+		pr_debug("cpu_map__new\n");
+		goto out_free_threads;
+	}
+
+	CPU_ZERO(&cpu_set);
+	CPU_SET(cpus->map[0], &cpu_set);
+	sched_setaffinity(0, sizeof(cpu_set), &cpu_set);
+	if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0) {
+		pr_debug("sched_setaffinity() failed on CPU %d: %s ",
+			 cpus->map[0], strerror(errno));
+		goto out_free_cpus;
+	}
+
+	evlist = perf_evlist__new();
+	if (evlist == NULL) {
+		pr_debug("perf_evlist__new\n");
+		goto out_free_cpus;
+	}
+
+	perf_evlist__set_maps(evlist, cpus, threads);
+
+	for (i = 0; i < nsyscalls; ++i) {
+		char name[64];
+
+		snprintf(name, sizeof(name), "sys_enter_%s", syscall_names[i]);
+		evsels[i] = perf_evsel__newtp("syscalls", name);
+		if (evsels[i] == NULL) {
+			pr_debug("perf_evsel__new\n");
+			goto out_delete_evlist;
+		}
+
+		evsels[i]->attr.wakeup_events = 1;
+		perf_evsel__set_sample_id(evsels[i], false);
+
+		perf_evlist__add(evlist, evsels[i]);
+
+		if (perf_evsel__open(evsels[i], cpus, threads) < 0) {
+			pr_debug("failed to open counter: %s, "
+				 "tweak /proc/sys/kernel/perf_event_paranoid?\n",
+				 strerror(errno));
+			goto out_delete_evlist;
+		}
+
+		nr_events[i] = 0;
+		expected_nr_events[i] = 1 + rand() % 127;
+	}
+
+	if (perf_evlist__mmap(evlist, 128, true) < 0) {
+		pr_debug("failed to mmap events: %d (%s)\n", errno,
+			 strerror(errno));
+		goto out_delete_evlist;
+	}
+
+	for (i = 0; i < nsyscalls; ++i)
+		for (j = 0; j < expected_nr_events[i]; ++j) {
+			int foo = syscalls[i]();
+			++foo;
+		}
+
+	while ((event = perf_evlist__mmap_read(evlist, 0)) != NULL) {
+		struct perf_sample sample;
+
+		if (event->header.type != PERF_RECORD_SAMPLE) {
+			pr_debug("unexpected %s event\n",
+				 perf_event__name(event->header.type));
+			goto out_delete_evlist;
+		}
+
+		err = perf_evlist__parse_sample(evlist, event, &sample);
+		if (err) {
+			pr_err("Can't parse sample, err = %d\n", err);
+			goto out_delete_evlist;
+		}
+
+		err = -1;
+		evsel = perf_evlist__id2evsel(evlist, sample.id);
+		if (evsel == NULL) {
+			pr_debug("event with id %" PRIu64
+				 " doesn't map to an evsel\n", sample.id);
+			goto out_delete_evlist;
+		}
+		nr_events[evsel->idx]++;
+		perf_evlist__mmap_consume(evlist, 0);
+	}
+
+	err = 0;
+	evlist__for_each(evlist, evsel) {
+		if (nr_events[evsel->idx] != expected_nr_events[evsel->idx]) {
+			pr_debug("expected %d %s events, got %d\n",
+				 expected_nr_events[evsel->idx],
+				 perf_evsel__name(evsel), nr_events[evsel->idx]);
+			err = -1;
+			goto out_delete_evlist;
+		}
+	}
+
+out_delete_evlist:
+	perf_evlist__delete(evlist);
+	cpus	= NULL;
+	threads = NULL;
+out_free_cpus:
+	cpu_map__delete(cpus);
+out_free_threads:
+	thread_map__delete(threads);
+	return err;
+}
diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c
new file mode 100644
index 00000000000..4a456fef66c
--- /dev/null
+++ b/tools/perf/tests/mmap-thread-lookup.c
@@ -0,0 +1,233 @@
+#include <unistd.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <sys/mman.h>
+#include <pthread.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include "debug.h"
+#include "tests.h"
+#include "machine.h"
+#include "thread_map.h"
+#include "symbol.h"
+#include "thread.h"
+
+#define THREADS 4
+
+static int go_away;
+
+struct thread_data {
+	pthread_t	pt;
+	pid_t		tid;
+	void		*map;
+	int		ready[2];
+};
+
+static struct thread_data threads[THREADS];
+
+static int thread_init(struct thread_data *td)
+{
+	void *map;
+
+	map = mmap(NULL, page_size,
+		   PROT_READ|PROT_WRITE|PROT_EXEC,
+		   MAP_SHARED|MAP_ANONYMOUS, -1, 0);
+
+	if (map == MAP_FAILED) {
+		perror("mmap failed");
+		return -1;
+	}
+
+	td->map = map;
+	td->tid = syscall(SYS_gettid);
+
+	pr_debug("tid = %d, map = %p\n", td->tid, map);
+	return 0;
+}
+
+static void *thread_fn(void *arg)
+{
+	struct thread_data *td = arg;
+	ssize_t ret;
+	int go;
+
+	if (thread_init(td))
+		return NULL;
+
+	/* Signal thread_create thread is initialized. */
+	ret = write(td->ready[1], &go, sizeof(int));
+	if (ret != sizeof(int)) {
+		pr_err("failed to notify\n");
+		return NULL;
+	}
+
+	while (!go_away) {
+		/* Waiting for main thread to kill us. */
+		usleep(100);
+	}
+
+	munmap(td->map, page_size);
+	return NULL;
+}
+
+static int thread_create(int i)
+{
+	struct thread_data *td = &threads[i];
+	int err, go;
+
+	if (pipe(td->ready))
+		return -1;
+
+	err = pthread_create(&td->pt, NULL, thread_fn, td);
+	if (!err) {
+		/* Wait for thread initialization. */
+		ssize_t ret = read(td->ready[0], &go, sizeof(int));
+		err = ret != sizeof(int);
+	}
+
+	close(td->ready[0]);
+	close(td->ready[1]);
+	return err;
+}
+
+static int threads_create(void)
+{
+	struct thread_data *td0 = &threads[0];
+	int i, err = 0;
+
+	go_away = 0;
+
+	/* 0 is main thread */
+	if (thread_init(td0))
+		return -1;
+
+	for (i = 1; !err && i < THREADS; i++)
+		err = thread_create(i);
+
+	return err;
+}
+
+static int threads_destroy(void)
+{
+	struct thread_data *td0 = &threads[0];
+	int i, err = 0;
+
+	/* cleanup the main thread */
+	munmap(td0->map, page_size);
+
+	go_away = 1;
+
+	for (i = 1; !err && i < THREADS; i++)
+		err = pthread_join(threads[i].pt, NULL);
+
+	return err;
+}
+
+typedef int (*synth_cb)(struct machine *machine);
+
+static int synth_all(struct machine *machine)
+{
+	return perf_event__synthesize_threads(NULL,
+					      perf_event__process,
+					      machine, 0);
+}
+
+static int synth_process(struct machine *machine)
+{
+	struct thread_map *map;
+	int err;
+
+	map = thread_map__new_by_pid(getpid());
+
+	err = perf_event__synthesize_thread_map(NULL, map,
+						perf_event__process,
+						machine, 0);
+
+	thread_map__delete(map);
+	return err;
+}
+
+static int mmap_events(synth_cb synth)
+{
+	struct machines machines;
+	struct machine *machine;
+	int err, i;
+
+	/*
+	 * The threads_create will not return before all threads
+	 * are spawned and all created memory map.
+	 *
+	 * They will loop until threads_destroy is called, so we
+	 * can safely run synthesizing function.
+	 */
+	TEST_ASSERT_VAL("failed to create threads", !threads_create());
+
+	machines__init(&machines);
+	machine = &machines.host;
+
+	dump_trace = verbose > 1 ? 1 : 0;
+
+	err = synth(machine);
+
+	dump_trace = 0;
+
+	TEST_ASSERT_VAL("failed to destroy threads", !threads_destroy());
+	TEST_ASSERT_VAL("failed to synthesize maps", !err);
+
+	/*
+	 * All data is synthesized, try to find map for each
+	 * thread object.
+	 */
+	for (i = 0; i < THREADS; i++) {
+		struct thread_data *td = &threads[i];
+		struct addr_location al;
+		struct thread *thread;
+
+		thread = machine__findnew_thread(machine, getpid(), td->tid);
+
+		pr_debug("looking for map %p\n", td->map);
+
+		thread__find_addr_map(thread, machine,
+				      PERF_RECORD_MISC_USER, MAP__FUNCTION,
+				      (unsigned long) (td->map + 1), &al);
+
+		if (!al.map) {
+			pr_debug("failed, couldn't find map\n");
+			err = -1;
+			break;
+		}
+
+		pr_debug("map %p, addr %" PRIx64 "\n", al.map, al.map->start);
+	}
+
+	machine__delete_threads(machine);
+	machines__exit(&machines);
+	return err;
+}
+
+/*
+ * This test creates 'THREADS' number of threads (including
+ * main thread) and each thread creates memory map.
+ *
+ * When threads are created, we synthesize them with both
+ * (separate tests):
+ *   perf_event__synthesize_thread_map (process based)
+ *   perf_event__synthesize_threads    (global)
+ *
+ * We test we can find all memory maps via:
+ *   thread__find_addr_map
+ *
+ * by using all thread objects.
+ */
+int test__mmap_thread_lookup(void)
+{
+	/* perf_event__synthesize_threads synthesize */
+	TEST_ASSERT_VAL("failed with sythesizing all",
+			!mmap_events(synth_all));
+
+	/* perf_event__synthesize_thread_map synthesize */
+	TEST_ASSERT_VAL("failed with sythesizing process",
+			!mmap_events(synth_process));
+
+	return 0;
+}
diff --git a/tools/perf/tests/open-syscall-all-cpus.c b/tools/perf/tests/open-syscall-all-cpus.c
new file mode 100644
index 00000000000..5fecdbd2f5f
--- /dev/null
+++ b/tools/perf/tests/open-syscall-all-cpus.c
@@ -0,0 +1,109 @@
+#include "evsel.h"
+#include "tests.h"
+#include "thread_map.h"
+#include "cpumap.h"
+#include "debug.h"
+
+int test__open_syscall_event_on_all_cpus(void)
+{
+	int err = -1, fd, cpu;
+	struct cpu_map *cpus;
+	struct perf_evsel *evsel;
+	unsigned int nr_open_calls = 111, i;
+	cpu_set_t cpu_set;
+	struct thread_map *threads = thread_map__new(-1, getpid(), UINT_MAX);
+
+	if (threads == NULL) {
+		pr_debug("thread_map__new\n");
+		return -1;
+	}
+
+	cpus = cpu_map__new(NULL);
+	if (cpus == NULL) {
+		pr_debug("cpu_map__new\n");
+		goto out_thread_map_delete;
+	}
+
+	CPU_ZERO(&cpu_set);
+
+	evsel = perf_evsel__newtp("syscalls", "sys_enter_open");
+	if (evsel == NULL) {
+		pr_debug("is debugfs mounted on /sys/kernel/debug?\n");
+		goto out_thread_map_delete;
+	}
+
+	if (perf_evsel__open(evsel, cpus, threads) < 0) {
+		pr_debug("failed to open counter: %s, "
+			 "tweak /proc/sys/kernel/perf_event_paranoid?\n",
+			 strerror(errno));
+		goto out_evsel_delete;
+	}
+
+	for (cpu = 0; cpu < cpus->nr; ++cpu) {
+		unsigned int ncalls = nr_open_calls + cpu;
+		/*
+		 * XXX eventually lift this restriction in a way that
+		 * keeps perf building on older glibc installations
+		 * without CPU_ALLOC. 1024 cpus in 2010 still seems
+		 * a reasonable upper limit tho :-)
+		 */
+		if (cpus->map[cpu] >= CPU_SETSIZE) {
+			pr_debug("Ignoring CPU %d\n", cpus->map[cpu]);
+			continue;
+		}
+
+		CPU_SET(cpus->map[cpu], &cpu_set);
+		if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0) {
+			pr_debug("sched_setaffinity() failed on CPU %d: %s ",
+				 cpus->map[cpu],
+				 strerror(errno));
+			goto out_close_fd;
+		}
+		for (i = 0; i < ncalls; ++i) {
+			fd = open("/etc/passwd", O_RDONLY);
+			close(fd);
+		}
+		CPU_CLR(cpus->map[cpu], &cpu_set);
+	}
+
+	/*
+	 * Here we need to explicitely preallocate the counts, as if
+	 * we use the auto allocation it will allocate just for 1 cpu,
+	 * as we start by cpu 0.
+	 */
+	if (perf_evsel__alloc_counts(evsel, cpus->nr) < 0) {
+		pr_debug("perf_evsel__alloc_counts(ncpus=%d)\n", cpus->nr);
+		goto out_close_fd;
+	}
+
+	err = 0;
+
+	for (cpu = 0; cpu < cpus->nr; ++cpu) {
+		unsigned int expected;
+
+		if (cpus->map[cpu] >= CPU_SETSIZE)
+			continue;
+
+		if (perf_evsel__read_on_cpu(evsel, cpu, 0) < 0) {
+			pr_debug("perf_evsel__read_on_cpu\n");
+			err = -1;
+			break;
+		}
+
+		expected = nr_open_calls + cpu;
+		if (evsel->counts->cpu[cpu].val != expected) {
+			pr_debug("perf_evsel__read_on_cpu: expected to intercept %d calls on cpu %d, got %" PRIu64 "\n",
+				 expected, cpus->map[cpu], evsel->counts->cpu[cpu].val);
+			err = -1;
+		}
+	}
+
+	perf_evsel__free_counts(evsel);
+out_close_fd:
+	perf_evsel__close_fd(evsel, 1, threads->nr);
+out_evsel_delete:
+	perf_evsel__delete(evsel);
+out_thread_map_delete:
+	thread_map__delete(threads);
+	return err;
+}
diff --git a/tools/perf/tests/open-syscall-tp-fields.c b/tools/perf/tests/open-syscall-tp-fields.c
new file mode 100644
index 00000000000..c505ef2af24
--- /dev/null
+++ b/tools/perf/tests/open-syscall-tp-fields.c
@@ -0,0 +1,117 @@
+#include "perf.h"
+#include "evlist.h"
+#include "evsel.h"
+#include "thread_map.h"
+#include "tests.h"
+
+int test__syscall_open_tp_fields(void)
+{
+	struct record_opts opts = {
+		.target = {
+			.uid = UINT_MAX,
+			.uses_mmap = true,
+		},
+		.no_buffering = true,
+		.freq	      = 1,
+		.mmap_pages   = 256,
+		.raw_samples  = true,
+	};
+	const char *filename = "/etc/passwd";
+	int flags = O_RDONLY | O_DIRECTORY;
+	struct perf_evlist *evlist = perf_evlist__new();
+	struct perf_evsel *evsel;
+	int err = -1, i, nr_events = 0, nr_polls = 0;
+
+	if (evlist == NULL) {
+		pr_debug("%s: perf_evlist__new\n", __func__);
+		goto out;
+	}
+
+	evsel = perf_evsel__newtp("syscalls", "sys_enter_open");
+	if (evsel == NULL) {
+		pr_debug("%s: perf_evsel__newtp\n", __func__);
+		goto out_delete_evlist;
+	}
+
+	perf_evlist__add(evlist, evsel);
+
+	err = perf_evlist__create_maps(evlist, &opts.target);
+	if (err < 0) {
+		pr_debug("%s: perf_evlist__create_maps\n", __func__);
+		goto out_delete_evlist;
+	}
+
+	perf_evsel__config(evsel, &opts);
+
+	evlist->threads->map[0] = getpid();
+
+	err = perf_evlist__open(evlist);
+	if (err < 0) {
+		pr_debug("perf_evlist__open: %s\n", strerror(errno));
+		goto out_delete_evlist;
+	}
+
+	err = perf_evlist__mmap(evlist, UINT_MAX, false);
+	if (err < 0) {
+		pr_debug("perf_evlist__mmap: %s\n", strerror(errno));
+		goto out_delete_evlist;
+	}
+
+	perf_evlist__enable(evlist);
+
+	/*
+	 * Generate the event:
+	 */
+	open(filename, flags);
+
+	while (1) {
+		int before = nr_events;
+
+		for (i = 0; i < evlist->nr_mmaps; i++) {
+			union perf_event *event;
+
+			while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
+				const u32 type = event->header.type;
+				int tp_flags;
+				struct perf_sample sample;
+
+				++nr_events;
+
+				if (type != PERF_RECORD_SAMPLE) {
+					perf_evlist__mmap_consume(evlist, i);
+					continue;
+				}
+
+				err = perf_evsel__parse_sample(evsel, event, &sample);
+				if (err) {
+					pr_err("Can't parse sample, err = %d\n", err);
+					goto out_delete_evlist;
+				}
+
+				tp_flags = perf_evsel__intval(evsel, &sample, "flags");
+
+				if (flags != tp_flags) {
+					pr_debug("%s: Expected flags=%#x, got %#x\n",
+						 __func__, flags, tp_flags);
+					goto out_delete_evlist;
+				}
+
+				goto out_ok;
+			}
+		}
+
+		if (nr_events == before)
+			poll(evlist->pollfd, evlist->nr_fds, 10);
+
+		if (++nr_polls > 5) {
+			pr_debug("%s: no events!\n", __func__);
+			goto out_delete_evlist;
+		}
+	}
+out_ok:
+	err = 0;
+out_delete_evlist:
+	perf_evlist__delete(evlist);
+out:
+	return err;
+}
diff --git a/tools/perf/tests/open-syscall.c b/tools/perf/tests/open-syscall.c
new file mode 100644
index 00000000000..c1dc7d25f38
--- /dev/null
+++ b/tools/perf/tests/open-syscall.c
@@ -0,0 +1,55 @@
+#include "thread_map.h"
+#include "evsel.h"
+#include "debug.h"
+#include "tests.h"
+
+int test__open_syscall_event(void)
+{
+	int err = -1, fd;
+	struct perf_evsel *evsel;
+	unsigned int nr_open_calls = 111, i;
+	struct thread_map *threads = thread_map__new(-1, getpid(), UINT_MAX);
+
+	if (threads == NULL) {
+		pr_debug("thread_map__new\n");
+		return -1;
+	}
+
+	evsel = perf_evsel__newtp("syscalls", "sys_enter_open");
+	if (evsel == NULL) {
+		pr_debug("is debugfs mounted on /sys/kernel/debug?\n");
+		goto out_thread_map_delete;
+	}
+
+	if (perf_evsel__open_per_thread(evsel, threads) < 0) {
+		pr_debug("failed to open counter: %s, "
+			 "tweak /proc/sys/kernel/perf_event_paranoid?\n",
+			 strerror(errno));
+		goto out_evsel_delete;
+	}
+
+	for (i = 0; i < nr_open_calls; ++i) {
+		fd = open("/etc/passwd", O_RDONLY);
+		close(fd);
+	}
+
+	if (perf_evsel__read_on_cpu(evsel, 0, 0) < 0) {
+		pr_debug("perf_evsel__read_on_cpu\n");
+		goto out_close_fd;
+	}
+
+	if (evsel->counts->cpu[0].val != nr_open_calls) {
+		pr_debug("perf_evsel__read_on_cpu: expected to intercept %d calls, got %" PRIu64 "\n",
+			 nr_open_calls, evsel->counts->cpu[0].val);
+		goto out_close_fd;
+	}
+
+	err = 0;
+out_close_fd:
+	perf_evsel__close_fd(evsel, 1, threads->nr);
+out_evsel_delete:
+	perf_evsel__delete(evsel);
+out_thread_map_delete:
+	thread_map__delete(threads);
+	return err;
+}
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
new file mode 100644
index 00000000000..deba66955f8
--- /dev/null
+++ b/tools/perf/tests/parse-events.c
@@ -0,0 +1,1590 @@
+
+#include "parse-events.h"
+#include "evsel.h"
+#include "evlist.h"
+#include <api/fs/fs.h>
+#include <api/fs/debugfs.h>
+#include "tests.h"
+#include <linux/hw_breakpoint.h>
+
+#define PERF_TP_SAMPLE_TYPE (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | \
+			     PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD)
+
+static int test__checkevent_tracepoint(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong number of groups", 0 == evlist->nr_groups);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_TRACEPOINT == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong sample_type",
+		PERF_TP_SAMPLE_TYPE == evsel->attr.sample_type);
+	TEST_ASSERT_VAL("wrong sample_period", 1 == evsel->attr.sample_period);
+	return 0;
+}
+
+static int test__checkevent_tracepoint_multi(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+
+	TEST_ASSERT_VAL("wrong number of entries", evlist->nr_entries > 1);
+	TEST_ASSERT_VAL("wrong number of groups", 0 == evlist->nr_groups);
+
+	evlist__for_each(evlist, evsel) {
+		TEST_ASSERT_VAL("wrong type",
+			PERF_TYPE_TRACEPOINT == evsel->attr.type);
+		TEST_ASSERT_VAL("wrong sample_type",
+			PERF_TP_SAMPLE_TYPE == evsel->attr.sample_type);
+		TEST_ASSERT_VAL("wrong sample_period",
+			1 == evsel->attr.sample_period);
+	}
+	return 0;
+}
+
+static int test__checkevent_raw(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config", 0x1a == evsel->attr.config);
+	return 0;
+}
+
+static int test__checkevent_numeric(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong type", 1 == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config", 1 == evsel->attr.config);
+	return 0;
+}
+
+static int test__checkevent_symbolic_name(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_INSTRUCTIONS == evsel->attr.config);
+	return 0;
+}
+
+static int test__checkevent_symbolic_name_config(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong period",
+			100000 == evsel->attr.sample_period);
+	TEST_ASSERT_VAL("wrong config1",
+			0 == evsel->attr.config1);
+	TEST_ASSERT_VAL("wrong config2",
+			1 == evsel->attr.config2);
+	return 0;
+}
+
+static int test__checkevent_symbolic_alias(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_SOFTWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_SW_PAGE_FAULTS == evsel->attr.config);
+	return 0;
+}
+
+static int test__checkevent_genhw(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HW_CACHE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config", (1 << 16) == evsel->attr.config);
+	return 0;
+}
+
+static int test__checkevent_breakpoint(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_BREAKPOINT == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config", 0 == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong bp_type", (HW_BREAKPOINT_R | HW_BREAKPOINT_W) ==
+					 evsel->attr.bp_type);
+	TEST_ASSERT_VAL("wrong bp_len", HW_BREAKPOINT_LEN_4 ==
+					evsel->attr.bp_len);
+	return 0;
+}
+
+static int test__checkevent_breakpoint_x(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_BREAKPOINT == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config", 0 == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong bp_type",
+			HW_BREAKPOINT_X == evsel->attr.bp_type);
+	TEST_ASSERT_VAL("wrong bp_len", sizeof(long) == evsel->attr.bp_len);
+	return 0;
+}
+
+static int test__checkevent_breakpoint_r(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong type",
+			PERF_TYPE_BREAKPOINT == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config", 0 == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong bp_type",
+			HW_BREAKPOINT_R == evsel->attr.bp_type);
+	TEST_ASSERT_VAL("wrong bp_len",
+			HW_BREAKPOINT_LEN_4 == evsel->attr.bp_len);
+	return 0;
+}
+
+static int test__checkevent_breakpoint_w(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong type",
+			PERF_TYPE_BREAKPOINT == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config", 0 == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong bp_type",
+			HW_BREAKPOINT_W == evsel->attr.bp_type);
+	TEST_ASSERT_VAL("wrong bp_len",
+			HW_BREAKPOINT_LEN_4 == evsel->attr.bp_len);
+	return 0;
+}
+
+static int test__checkevent_breakpoint_rw(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong type",
+			PERF_TYPE_BREAKPOINT == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config", 0 == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong bp_type",
+		(HW_BREAKPOINT_R|HW_BREAKPOINT_W) == evsel->attr.bp_type);
+	TEST_ASSERT_VAL("wrong bp_len",
+			HW_BREAKPOINT_LEN_4 == evsel->attr.bp_len);
+	return 0;
+}
+
+static int test__checkevent_tracepoint_modifier(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+
+	return test__checkevent_tracepoint(evlist);
+}
+
+static int
+test__checkevent_tracepoint_multi_modifier(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+
+	TEST_ASSERT_VAL("wrong number of entries", evlist->nr_entries > 1);
+
+	evlist__for_each(evlist, evsel) {
+		TEST_ASSERT_VAL("wrong exclude_user",
+				!evsel->attr.exclude_user);
+		TEST_ASSERT_VAL("wrong exclude_kernel",
+				evsel->attr.exclude_kernel);
+		TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+		TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	}
+
+	return test__checkevent_tracepoint_multi(evlist);
+}
+
+static int test__checkevent_raw_modifier(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip);
+
+	return test__checkevent_raw(evlist);
+}
+
+static int test__checkevent_numeric_modifier(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip);
+
+	return test__checkevent_numeric(evlist);
+}
+
+static int test__checkevent_symbolic_name_modifier(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+
+	return test__checkevent_symbolic_name(evlist);
+}
+
+static int test__checkevent_exclude_host_modifier(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host);
+
+	return test__checkevent_symbolic_name(evlist);
+}
+
+static int test__checkevent_exclude_guest_modifier(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+
+	return test__checkevent_symbolic_name(evlist);
+}
+
+static int test__checkevent_symbolic_alias_modifier(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+
+	return test__checkevent_symbolic_alias(evlist);
+}
+
+static int test__checkevent_genhw_modifier(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip);
+
+	return test__checkevent_genhw(evlist);
+}
+
+static int test__checkevent_breakpoint_modifier(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong name",
+			!strcmp(perf_evsel__name(evsel), "mem:0:u"));
+
+	return test__checkevent_breakpoint(evlist);
+}
+
+static int test__checkevent_breakpoint_x_modifier(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong name",
+			!strcmp(perf_evsel__name(evsel), "mem:0:x:k"));
+
+	return test__checkevent_breakpoint_x(evlist);
+}
+
+static int test__checkevent_breakpoint_r_modifier(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong name",
+			!strcmp(perf_evsel__name(evsel), "mem:0:r:hp"));
+
+	return test__checkevent_breakpoint_r(evlist);
+}
+
+static int test__checkevent_breakpoint_w_modifier(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong name",
+			!strcmp(perf_evsel__name(evsel), "mem:0:w:up"));
+
+	return test__checkevent_breakpoint_w(evlist);
+}
+
+static int test__checkevent_breakpoint_rw_modifier(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong name",
+			!strcmp(perf_evsel__name(evsel), "mem:0:rw:kp"));
+
+	return test__checkevent_breakpoint_rw(evlist);
+}
+
+static int test__checkevent_pmu(struct perf_evlist *evlist)
+{
+
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",    10 == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong config1",    1 == evsel->attr.config1);
+	TEST_ASSERT_VAL("wrong config2",    3 == evsel->attr.config2);
+	TEST_ASSERT_VAL("wrong period",  1000 == evsel->attr.sample_period);
+
+	return 0;
+}
+
+static int test__checkevent_list(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong number of entries", 3 == evlist->nr_entries);
+
+	/* r1 */
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config", 1 == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong config1", 0 == evsel->attr.config1);
+	TEST_ASSERT_VAL("wrong config2", 0 == evsel->attr.config2);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+
+	/* syscalls:sys_enter_open:k */
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_TRACEPOINT == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong sample_type",
+		PERF_TP_SAMPLE_TYPE == evsel->attr.sample_type);
+	TEST_ASSERT_VAL("wrong sample_period", 1 == evsel->attr.sample_period);
+	TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+
+	/* 1:1:hp */
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", 1 == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config", 1 == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip);
+
+	return 0;
+}
+
+static int test__checkevent_pmu_name(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	/* cpu/config=1,name=krava/u */
+	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",  1 == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong name", !strcmp(perf_evsel__name(evsel), "krava"));
+
+	/* cpu/config=2/u" */
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",  2 == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong name",
+			!strcmp(perf_evsel__name(evsel), "cpu/config=2/u"));
+
+	return 0;
+}
+
+static int test__checkevent_pmu_events(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong exclude_user",
+			!evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel",
+			evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong pinned", !evsel->attr.pinned);
+
+	return 0;
+}
+
+static int test__checkterms_simple(struct list_head *terms)
+{
+	struct parse_events_term *term;
+
+	/* config=10 */
+	term = list_entry(terms->next, struct parse_events_term, list);
+	TEST_ASSERT_VAL("wrong type term",
+			term->type_term == PARSE_EVENTS__TERM_TYPE_CONFIG);
+	TEST_ASSERT_VAL("wrong type val",
+			term->type_val == PARSE_EVENTS__TERM_TYPE_NUM);
+	TEST_ASSERT_VAL("wrong val", term->val.num == 10);
+	TEST_ASSERT_VAL("wrong config", !term->config);
+
+	/* config1 */
+	term = list_entry(term->list.next, struct parse_events_term, list);
+	TEST_ASSERT_VAL("wrong type term",
+			term->type_term == PARSE_EVENTS__TERM_TYPE_CONFIG1);
+	TEST_ASSERT_VAL("wrong type val",
+			term->type_val == PARSE_EVENTS__TERM_TYPE_NUM);
+	TEST_ASSERT_VAL("wrong val", term->val.num == 1);
+	TEST_ASSERT_VAL("wrong config", !term->config);
+
+	/* config2=3 */
+	term = list_entry(term->list.next, struct parse_events_term, list);
+	TEST_ASSERT_VAL("wrong type term",
+			term->type_term == PARSE_EVENTS__TERM_TYPE_CONFIG2);
+	TEST_ASSERT_VAL("wrong type val",
+			term->type_val == PARSE_EVENTS__TERM_TYPE_NUM);
+	TEST_ASSERT_VAL("wrong val", term->val.num == 3);
+	TEST_ASSERT_VAL("wrong config", !term->config);
+
+	/* umask=1*/
+	term = list_entry(term->list.next, struct parse_events_term, list);
+	TEST_ASSERT_VAL("wrong type term",
+			term->type_term == PARSE_EVENTS__TERM_TYPE_USER);
+	TEST_ASSERT_VAL("wrong type val",
+			term->type_val == PARSE_EVENTS__TERM_TYPE_NUM);
+	TEST_ASSERT_VAL("wrong val", term->val.num == 1);
+	TEST_ASSERT_VAL("wrong config", !strcmp(term->config, "umask"));
+
+	return 0;
+}
+
+static int test__group1(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel, *leader;
+
+	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups);
+
+	/* instructions:k */
+	evsel = leader = perf_evlist__first(evlist);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_INSTRUCTIONS == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
+	TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
+
+	/* cycles:upp */
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	/* use of precise requires exclude_guest */
+	TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip == 2);
+	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
+	TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
+
+	return 0;
+}
+
+static int test__group2(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel, *leader;
+
+	TEST_ASSERT_VAL("wrong number of entries", 3 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups);
+
+	/* faults + :ku modifier */
+	evsel = leader = perf_evlist__first(evlist);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_SOFTWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_SW_PAGE_FAULTS == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
+	TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
+
+	/* cache-references + :u modifier */
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CACHE_REFERENCES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
+	TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
+
+	/* cycles:k */
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
+
+	return 0;
+}
+
+static int test__group3(struct perf_evlist *evlist __maybe_unused)
+{
+	struct perf_evsel *evsel, *leader;
+
+	TEST_ASSERT_VAL("wrong number of entries", 5 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong number of groups", 2 == evlist->nr_groups);
+
+	/* group1 syscalls:sys_enter_open:H */
+	evsel = leader = perf_evlist__first(evlist);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_TRACEPOINT == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong sample_type",
+		PERF_TP_SAMPLE_TYPE == evsel->attr.sample_type);
+	TEST_ASSERT_VAL("wrong sample_period", 1 == evsel->attr.sample_period);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong group name",
+		!strcmp(leader->group_name, "group1"));
+	TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
+	TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
+
+	/* group1 cycles:kppp */
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	/* use of precise requires exclude_guest */
+	TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip == 3);
+	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
+	TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
+
+	/* group2 cycles + G modifier */
+	evsel = leader = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong group name",
+		!strcmp(leader->group_name, "group2"));
+	TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
+	TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
+
+	/* group2 1:3 + G modifier */
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", 1 == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config", 3 == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
+	TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
+
+	/* instructions:u */
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_INSTRUCTIONS == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
+
+	return 0;
+}
+
+static int test__group4(struct perf_evlist *evlist __maybe_unused)
+{
+	struct perf_evsel *evsel, *leader;
+
+	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups);
+
+	/* cycles:u + p */
+	evsel = leader = perf_evlist__first(evlist);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	/* use of precise requires exclude_guest */
+	TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip == 1);
+	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
+	TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
+
+	/* instructions:kp + p */
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_INSTRUCTIONS == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	/* use of precise requires exclude_guest */
+	TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip == 2);
+	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
+	TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
+
+	return 0;
+}
+
+static int test__group5(struct perf_evlist *evlist __maybe_unused)
+{
+	struct perf_evsel *evsel, *leader;
+
+	TEST_ASSERT_VAL("wrong number of entries", 5 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong number of groups", 2 == evlist->nr_groups);
+
+	/* cycles + G */
+	evsel = leader = perf_evlist__first(evlist);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
+	TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
+
+	/* instructions + G */
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_INSTRUCTIONS == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
+	TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
+
+	/* cycles:G */
+	evsel = leader = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
+	TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
+
+	/* instructions:G */
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_INSTRUCTIONS == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
+
+	/* cycles */
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+
+	return 0;
+}
+
+static int test__group_gh1(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel, *leader;
+
+	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups);
+
+	/* cycles + :H group modifier */
+	evsel = leader = perf_evlist__first(evlist);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
+
+	/* cache-misses:G + :H group modifier */
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CACHE_MISSES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
+
+	return 0;
+}
+
+static int test__group_gh2(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel, *leader;
+
+	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups);
+
+	/* cycles + :G group modifier */
+	evsel = leader = perf_evlist__first(evlist);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
+
+	/* cache-misses:H + :G group modifier */
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CACHE_MISSES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
+
+	return 0;
+}
+
+static int test__group_gh3(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel, *leader;
+
+	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups);
+
+	/* cycles:G + :u group modifier */
+	evsel = leader = perf_evlist__first(evlist);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
+
+	/* cache-misses:H + :u group modifier */
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CACHE_MISSES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
+
+	return 0;
+}
+
+static int test__group_gh4(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel, *leader;
+
+	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups);
+
+	/* cycles:G + :uG group modifier */
+	evsel = leader = perf_evlist__first(evlist);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
+
+	/* cache-misses:H + :uG group modifier */
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CACHE_MISSES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
+
+	return 0;
+}
+
+static int test__leader_sample1(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel, *leader;
+
+	TEST_ASSERT_VAL("wrong number of entries", 3 == evlist->nr_entries);
+
+	/* cycles - sampling group leader */
+	evsel = leader = perf_evlist__first(evlist);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
+	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+	TEST_ASSERT_VAL("wrong sample_read", evsel->sample_read);
+
+	/* cache-misses - not sampling */
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CACHE_MISSES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+	TEST_ASSERT_VAL("wrong sample_read", evsel->sample_read);
+
+	/* branch-misses - not sampling */
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_BRANCH_MISSES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
+	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+	TEST_ASSERT_VAL("wrong sample_read", evsel->sample_read);
+
+	return 0;
+}
+
+static int test__leader_sample2(struct perf_evlist *evlist __maybe_unused)
+{
+	struct perf_evsel *evsel, *leader;
+
+	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries);
+
+	/* instructions - sampling group leader */
+	evsel = leader = perf_evlist__first(evlist);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_INSTRUCTIONS == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
+	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+	TEST_ASSERT_VAL("wrong sample_read", evsel->sample_read);
+
+	/* branch-misses - not sampling */
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_BRANCH_MISSES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
+	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+	TEST_ASSERT_VAL("wrong sample_read", evsel->sample_read);
+
+	return 0;
+}
+
+static int test__checkevent_pinned_modifier(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong pinned", evsel->attr.pinned);
+
+	return test__checkevent_symbolic_name(evlist);
+}
+
+static int test__pinned_group(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel, *leader;
+
+	TEST_ASSERT_VAL("wrong number of entries", 3 == evlist->nr_entries);
+
+	/* cycles - group leader */
+	evsel = leader = perf_evlist__first(evlist);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
+	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+	TEST_ASSERT_VAL("wrong pinned", evsel->attr.pinned);
+
+	/* cache-misses - can not be pinned, but will go on with the leader */
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CACHE_MISSES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong pinned", !evsel->attr.pinned);
+
+	/* branch-misses - ditto */
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_BRANCH_MISSES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong pinned", !evsel->attr.pinned);
+
+	return 0;
+}
+
+static int count_tracepoints(void)
+{
+	char events_path[PATH_MAX];
+	struct dirent *events_ent;
+	DIR *events_dir;
+	int cnt = 0;
+
+	scnprintf(events_path, PATH_MAX, "%s/tracing/events",
+		  debugfs_find_mountpoint());
+
+	events_dir = opendir(events_path);
+
+	TEST_ASSERT_VAL("Can't open events dir", events_dir);
+
+	while ((events_ent = readdir(events_dir))) {
+		char sys_path[PATH_MAX];
+		struct dirent *sys_ent;
+		DIR *sys_dir;
+
+		if (!strcmp(events_ent->d_name, ".")
+		    || !strcmp(events_ent->d_name, "..")
+		    || !strcmp(events_ent->d_name, "enable")
+		    || !strcmp(events_ent->d_name, "header_event")
+		    || !strcmp(events_ent->d_name, "header_page"))
+			continue;
+
+		scnprintf(sys_path, PATH_MAX, "%s/%s",
+			  events_path, events_ent->d_name);
+
+		sys_dir = opendir(sys_path);
+		TEST_ASSERT_VAL("Can't open sys dir", sys_dir);
+
+		while ((sys_ent = readdir(sys_dir))) {
+			if (!strcmp(sys_ent->d_name, ".")
+			    || !strcmp(sys_ent->d_name, "..")
+			    || !strcmp(sys_ent->d_name, "enable")
+			    || !strcmp(sys_ent->d_name, "filter"))
+				continue;
+
+			cnt++;
+		}
+
+		closedir(sys_dir);
+	}
+
+	closedir(events_dir);
+	return cnt;
+}
+
+static int test__all_tracepoints(struct perf_evlist *evlist)
+{
+	TEST_ASSERT_VAL("wrong events count",
+			count_tracepoints() == evlist->nr_entries);
+
+	return test__checkevent_tracepoint_multi(evlist);
+}
+
+struct evlist_test {
+	const char *name;
+	__u32 type;
+	const int id;
+	int (*check)(struct perf_evlist *evlist);
+};
+
+static struct evlist_test test__events[] = {
+	{
+		.name  = "syscalls:sys_enter_open",
+		.check = test__checkevent_tracepoint,
+		.id    = 0,
+	},
+	{
+		.name  = "syscalls:*",
+		.check = test__checkevent_tracepoint_multi,
+		.id    = 1,
+	},
+	{
+		.name  = "r1a",
+		.check = test__checkevent_raw,
+		.id    = 2,
+	},
+	{
+		.name  = "1:1",
+		.check = test__checkevent_numeric,
+		.id    = 3,
+	},
+	{
+		.name  = "instructions",
+		.check = test__checkevent_symbolic_name,
+		.id    = 4,
+	},
+	{
+		.name  = "cycles/period=100000,config2/",
+		.check = test__checkevent_symbolic_name_config,
+		.id    = 5,
+	},
+	{
+		.name  = "faults",
+		.check = test__checkevent_symbolic_alias,
+		.id    = 6,
+	},
+	{
+		.name  = "L1-dcache-load-miss",
+		.check = test__checkevent_genhw,
+		.id    = 7,
+	},
+	{
+		.name  = "mem:0",
+		.check = test__checkevent_breakpoint,
+		.id    = 8,
+	},
+	{
+		.name  = "mem:0:x",
+		.check = test__checkevent_breakpoint_x,
+		.id    = 9,
+	},
+	{
+		.name  = "mem:0:r",
+		.check = test__checkevent_breakpoint_r,
+		.id    = 10,
+	},
+	{
+		.name  = "mem:0:w",
+		.check = test__checkevent_breakpoint_w,
+		.id    = 11,
+	},
+	{
+		.name  = "syscalls:sys_enter_open:k",
+		.check = test__checkevent_tracepoint_modifier,
+		.id    = 12,
+	},
+	{
+		.name  = "syscalls:*:u",
+		.check = test__checkevent_tracepoint_multi_modifier,
+		.id    = 13,
+	},
+	{
+		.name  = "r1a:kp",
+		.check = test__checkevent_raw_modifier,
+		.id    = 14,
+	},
+	{
+		.name  = "1:1:hp",
+		.check = test__checkevent_numeric_modifier,
+		.id    = 15,
+	},
+	{
+		.name  = "instructions:h",
+		.check = test__checkevent_symbolic_name_modifier,
+		.id    = 16,
+	},
+	{
+		.name  = "faults:u",
+		.check = test__checkevent_symbolic_alias_modifier,
+		.id    = 17,
+	},
+	{
+		.name  = "L1-dcache-load-miss:kp",
+		.check = test__checkevent_genhw_modifier,
+		.id    = 18,
+	},
+	{
+		.name  = "mem:0:u",
+		.check = test__checkevent_breakpoint_modifier,
+		.id    = 19,
+	},
+	{
+		.name  = "mem:0:x:k",
+		.check = test__checkevent_breakpoint_x_modifier,
+		.id    = 20,
+	},
+	{
+		.name  = "mem:0:r:hp",
+		.check = test__checkevent_breakpoint_r_modifier,
+		.id    = 21,
+	},
+	{
+		.name  = "mem:0:w:up",
+		.check = test__checkevent_breakpoint_w_modifier,
+		.id    = 22,
+	},
+	{
+		.name  = "r1,syscalls:sys_enter_open:k,1:1:hp",
+		.check = test__checkevent_list,
+		.id    = 23,
+	},
+	{
+		.name  = "instructions:G",
+		.check = test__checkevent_exclude_host_modifier,
+		.id    = 24,
+	},
+	{
+		.name  = "instructions:H",
+		.check = test__checkevent_exclude_guest_modifier,
+		.id    = 25,
+	},
+	{
+		.name  = "mem:0:rw",
+		.check = test__checkevent_breakpoint_rw,
+		.id    = 26,
+	},
+	{
+		.name  = "mem:0:rw:kp",
+		.check = test__checkevent_breakpoint_rw_modifier,
+		.id    = 27,
+	},
+	{
+		.name  = "{instructions:k,cycles:upp}",
+		.check = test__group1,
+		.id    = 28,
+	},
+	{
+		.name  = "{faults:k,cache-references}:u,cycles:k",
+		.check = test__group2,
+		.id    = 29,
+	},
+	{
+		.name  = "group1{syscalls:sys_enter_open:H,cycles:kppp},group2{cycles,1:3}:G,instructions:u",
+		.check = test__group3,
+		.id    = 30,
+	},
+	{
+		.name  = "{cycles:u,instructions:kp}:p",
+		.check = test__group4,
+		.id    = 31,
+	},
+	{
+		.name  = "{cycles,instructions}:G,{cycles:G,instructions:G},cycles",
+		.check = test__group5,
+		.id    = 32,
+	},
+	{
+		.name  = "*:*",
+		.check = test__all_tracepoints,
+		.id    = 33,
+	},
+	{
+		.name  = "{cycles,cache-misses:G}:H",
+		.check = test__group_gh1,
+		.id    = 34,
+	},
+	{
+		.name  = "{cycles,cache-misses:H}:G",
+		.check = test__group_gh2,
+		.id    = 35,
+	},
+	{
+		.name  = "{cycles:G,cache-misses:H}:u",
+		.check = test__group_gh3,
+		.id    = 36,
+	},
+	{
+		.name  = "{cycles:G,cache-misses:H}:uG",
+		.check = test__group_gh4,
+		.id    = 37,
+	},
+	{
+		.name  = "{cycles,cache-misses,branch-misses}:S",
+		.check = test__leader_sample1,
+		.id    = 38,
+	},
+	{
+		.name  = "{instructions,branch-misses}:Su",
+		.check = test__leader_sample2,
+		.id    = 39,
+	},
+	{
+		.name  = "instructions:uDp",
+		.check = test__checkevent_pinned_modifier,
+		.id    = 40,
+	},
+	{
+		.name  = "{cycles,cache-misses,branch-misses}:D",
+		.check = test__pinned_group,
+		.id    = 41,
+	},
+#if defined(__s390x__)
+	{
+		.name  = "kvm-s390:kvm_s390_create_vm",
+		.check = test__checkevent_tracepoint,
+		.id    = 100,
+	},
+#endif
+};
+
+static struct evlist_test test__events_pmu[] = {
+	{
+		.name  = "cpu/config=10,config1,config2=3,period=1000/u",
+		.check = test__checkevent_pmu,
+		.id    = 0,
+	},
+	{
+		.name  = "cpu/config=1,name=krava/u,cpu/config=2/u",
+		.check = test__checkevent_pmu_name,
+		.id    = 1,
+	},
+};
+
+struct terms_test {
+	const char *str;
+	__u32 type;
+	int (*check)(struct list_head *terms);
+};
+
+static struct terms_test test__terms[] = {
+	[0] = {
+		.str   = "config=10,config1,config2=3,umask=1",
+		.check = test__checkterms_simple,
+	},
+};
+
+static int test_event(struct evlist_test *e)
+{
+	struct perf_evlist *evlist;
+	int ret;
+
+	evlist = perf_evlist__new();
+	if (evlist == NULL)
+		return -ENOMEM;
+
+	ret = parse_events(evlist, e->name);
+	if (ret) {
+		pr_debug("failed to parse event '%s', err %d\n",
+			 e->name, ret);
+	} else {
+		ret = e->check(evlist);
+	}
+	
+	perf_evlist__delete(evlist);
+
+	return ret;
+}
+
+static int test_events(struct evlist_test *events, unsigned cnt)
+{
+	int ret1, ret2 = 0;
+	unsigned i;
+
+	for (i = 0; i < cnt; i++) {
+		struct evlist_test *e = &events[i];
+
+		pr_debug("running test %d '%s'\n", e->id, e->name);
+		ret1 = test_event(e);
+		if (ret1)
+			ret2 = ret1;
+	}
+
+	return ret2;
+}
+
+static int test_term(struct terms_test *t)
+{
+	struct list_head terms;
+	int ret;
+
+	INIT_LIST_HEAD(&terms);
+
+	ret = parse_events_terms(&terms, t->str);
+	if (ret) {
+		pr_debug("failed to parse terms '%s', err %d\n",
+			 t->str , ret);
+		return ret;
+	}
+
+	ret = t->check(&terms);
+	parse_events__free_terms(&terms);
+
+	return ret;
+}
+
+static int test_terms(struct terms_test *terms, unsigned cnt)
+{
+	int ret = 0;
+	unsigned i;
+
+	for (i = 0; i < cnt; i++) {
+		struct terms_test *t = &terms[i];
+
+		pr_debug("running test %d '%s'\n", i, t->str);
+		ret = test_term(t);
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+
+static int test_pmu(void)
+{
+	struct stat st;
+	char path[PATH_MAX];
+	int ret;
+
+	snprintf(path, PATH_MAX, "%s/bus/event_source/devices/cpu/format/",
+		 sysfs__mountpoint());
+
+	ret = stat(path, &st);
+	if (ret)
+		pr_debug("omitting PMU cpu tests\n");
+	return !ret;
+}
+
+static int test_pmu_events(void)
+{
+	struct stat st;
+	char path[PATH_MAX];
+	struct dirent *ent;
+	DIR *dir;
+	int ret;
+
+	snprintf(path, PATH_MAX, "%s/bus/event_source/devices/cpu/events/",
+		 sysfs__mountpoint());
+
+	ret = stat(path, &st);
+	if (ret) {
+		pr_debug("omitting PMU cpu events tests\n");
+		return 0;
+	}
+
+	dir = opendir(path);
+	if (!dir) {
+		pr_debug("can't open pmu event dir");
+		return -1;
+	}
+
+	while (!ret && (ent = readdir(dir))) {
+#define MAX_NAME 100
+		struct evlist_test e;
+		char name[MAX_NAME];
+
+		if (!strcmp(ent->d_name, ".") ||
+		    !strcmp(ent->d_name, ".."))
+			continue;
+
+		snprintf(name, MAX_NAME, "cpu/event=%s/u", ent->d_name);
+
+		e.name  = name;
+		e.check = test__checkevent_pmu_events;
+
+		ret = test_event(&e);
+#undef MAX_NAME
+	}
+
+	closedir(dir);
+	return ret;
+}
+
+int test__parse_events(void)
+{
+	int ret1, ret2 = 0;
+
+#define TEST_EVENTS(tests)				\
+do {							\
+	ret1 = test_events(tests, ARRAY_SIZE(tests));	\
+	if (!ret2)					\
+		ret2 = ret1;				\
+} while (0)
+
+	TEST_EVENTS(test__events);
+
+	if (test_pmu())
+		TEST_EVENTS(test__events_pmu);
+
+	if (test_pmu()) {
+		int ret = test_pmu_events();
+		if (ret)
+			return ret;
+	}
+
+	ret1 = test_terms(test__terms, ARRAY_SIZE(test__terms));
+	if (!ret2)
+		ret2 = ret1;
+
+	return ret2;
+}
diff --git a/tools/perf/tests/parse-no-sample-id-all.c b/tools/perf/tests/parse-no-sample-id-all.c
new file mode 100644
index 00000000000..905019f9b74
--- /dev/null
+++ b/tools/perf/tests/parse-no-sample-id-all.c
@@ -0,0 +1,108 @@
+#include <linux/types.h>
+#include <stddef.h>
+
+#include "tests.h"
+
+#include "event.h"
+#include "evlist.h"
+#include "header.h"
+#include "util.h"
+
+static int process_event(struct perf_evlist **pevlist, union perf_event *event)
+{
+	struct perf_sample sample;
+
+	if (event->header.type == PERF_RECORD_HEADER_ATTR) {
+		if (perf_event__process_attr(NULL, event, pevlist)) {
+			pr_debug("perf_event__process_attr failed\n");
+			return -1;
+		}
+		return 0;
+	}
+
+	if (event->header.type >= PERF_RECORD_USER_TYPE_START)
+		return -1;
+
+	if (!*pevlist)
+		return -1;
+
+	if (perf_evlist__parse_sample(*pevlist, event, &sample)) {
+		pr_debug("perf_evlist__parse_sample failed\n");
+		return -1;
+	}
+
+	return 0;
+}
+
+static int process_events(union perf_event **events, size_t count)
+{
+	struct perf_evlist *evlist = NULL;
+	int err = 0;
+	size_t i;
+
+	for (i = 0; i < count && !err; i++)
+		err = process_event(&evlist, events[i]);
+
+	if (evlist)
+		perf_evlist__delete(evlist);
+
+	return err;
+}
+
+struct test_attr_event {
+	struct attr_event attr;
+	u64 id;
+};
+
+/**
+ * test__parse_no_sample_id_all - test parsing with no sample_id_all bit set.
+ *
+ * This function tests parsing data produced on kernel's that do not support the
+ * sample_id_all bit.  Without the sample_id_all bit, non-sample events (such as
+ * mmap events) do not have an id sample appended, and consequently logic
+ * designed to determine the id will not work.  That case happens when there is
+ * more than one selected event, so this test processes three events: 2
+ * attributes representing the selected events and one mmap event.
+ *
+ * Return: %0 on success, %-1 if the test fails.
+ */
+int test__parse_no_sample_id_all(void)
+{
+	int err;
+
+	struct test_attr_event event1 = {
+		.attr = {
+			.header = {
+				.type = PERF_RECORD_HEADER_ATTR,
+				.size = sizeof(struct test_attr_event),
+			},
+		},
+		.id = 1,
+	};
+	struct test_attr_event event2 = {
+		.attr = {
+			.header = {
+				.type = PERF_RECORD_HEADER_ATTR,
+				.size = sizeof(struct test_attr_event),
+			},
+		},
+		.id = 2,
+	};
+	struct mmap_event event3 = {
+		.header = {
+			.type = PERF_RECORD_MMAP,
+			.size = sizeof(struct mmap_event),
+		},
+	};
+	union perf_event *events[] = {
+		(union perf_event *)&event1,
+		(union perf_event *)&event2,
+		(union perf_event *)&event3,
+	};
+
+	err = process_events(events, ARRAY_SIZE(events));
+	if (err)
+		return -1;
+
+	return 0;
+}
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
new file mode 100644
index 00000000000..aca1a83dd13
--- /dev/null
+++ b/tools/perf/tests/perf-record.c
@@ -0,0 +1,309 @@
+#include <sched.h>
+#include "evlist.h"
+#include "evsel.h"
+#include "perf.h"
+#include "debug.h"
+#include "tests.h"
+
+static int sched__get_first_possible_cpu(pid_t pid, cpu_set_t *maskp)
+{
+	int i, cpu = -1, nrcpus = 1024;
+realloc:
+	CPU_ZERO(maskp);
+
+	if (sched_getaffinity(pid, sizeof(*maskp), maskp) == -1) {
+		if (errno == EINVAL && nrcpus < (1024 << 8)) {
+			nrcpus = nrcpus << 2;
+			goto realloc;
+		}
+		perror("sched_getaffinity");
+			return -1;
+	}
+
+	for (i = 0; i < nrcpus; i++) {
+		if (CPU_ISSET(i, maskp)) {
+			if (cpu == -1)
+				cpu = i;
+			else
+				CPU_CLR(i, maskp);
+		}
+	}
+
+	return cpu;
+}
+
+int test__PERF_RECORD(void)
+{
+	struct record_opts opts = {
+		.target = {
+			.uid = UINT_MAX,
+			.uses_mmap = true,
+		},
+		.no_buffering = true,
+		.freq	      = 10,
+		.mmap_pages   = 256,
+	};
+	cpu_set_t cpu_mask;
+	size_t cpu_mask_size = sizeof(cpu_mask);
+	struct perf_evlist *evlist = perf_evlist__new_default();
+	struct perf_evsel *evsel;
+	struct perf_sample sample;
+	const char *cmd = "sleep";
+	const char *argv[] = { cmd, "1", NULL, };
+	char *bname, *mmap_filename;
+	u64 prev_time = 0;
+	bool found_cmd_mmap = false,
+	     found_libc_mmap = false,
+	     found_vdso_mmap = false,
+	     found_ld_mmap = false;
+	int err = -1, errs = 0, i, wakeups = 0;
+	u32 cpu;
+	int total_events = 0, nr_events[PERF_RECORD_MAX] = { 0, };
+
+	if (evlist == NULL || argv == NULL) {
+		pr_debug("Not enough memory to create evlist\n");
+		goto out;
+	}
+
+	/*
+	 * Create maps of threads and cpus to monitor. In this case
+	 * we start with all threads and cpus (-1, -1) but then in
+	 * perf_evlist__prepare_workload we'll fill in the only thread
+	 * we're monitoring, the one forked there.
+	 */
+	err = perf_evlist__create_maps(evlist, &opts.target);
+	if (err < 0) {
+		pr_debug("Not enough memory to create thread/cpu maps\n");
+		goto out_delete_evlist;
+	}
+
+	/*
+	 * Prepare the workload in argv[] to run, it'll fork it, and then wait
+	 * for perf_evlist__start_workload() to exec it. This is done this way
+	 * so that we have time to open the evlist (calling sys_perf_event_open
+	 * on all the fds) and then mmap them.
+	 */
+	err = perf_evlist__prepare_workload(evlist, &opts.target, argv, false, NULL);
+	if (err < 0) {
+		pr_debug("Couldn't run the workload!\n");
+		goto out_delete_evlist;
+	}
+
+	/*
+	 * Config the evsels, setting attr->comm on the first one, etc.
+	 */
+	evsel = perf_evlist__first(evlist);
+	perf_evsel__set_sample_bit(evsel, CPU);
+	perf_evsel__set_sample_bit(evsel, TID);
+	perf_evsel__set_sample_bit(evsel, TIME);
+	perf_evlist__config(evlist, &opts);
+
+	err = sched__get_first_possible_cpu(evlist->workload.pid, &cpu_mask);
+	if (err < 0) {
+		pr_debug("sched__get_first_possible_cpu: %s\n", strerror(errno));
+		goto out_delete_evlist;
+	}
+
+	cpu = err;
+
+	/*
+	 * So that we can check perf_sample.cpu on all the samples.
+	 */
+	if (sched_setaffinity(evlist->workload.pid, cpu_mask_size, &cpu_mask) < 0) {
+		pr_debug("sched_setaffinity: %s\n", strerror(errno));
+		goto out_delete_evlist;
+	}
+
+	/*
+	 * Call sys_perf_event_open on all the fds on all the evsels,
+	 * grouping them if asked to.
+	 */
+	err = perf_evlist__open(evlist);
+	if (err < 0) {
+		pr_debug("perf_evlist__open: %s\n", strerror(errno));
+		goto out_delete_evlist;
+	}
+
+	/*
+	 * mmap the first fd on a given CPU and ask for events for the other
+	 * fds in the same CPU to be injected in the same mmap ring buffer
+	 * (using ioctl(PERF_EVENT_IOC_SET_OUTPUT)).
+	 */
+	err = perf_evlist__mmap(evlist, opts.mmap_pages, false);
+	if (err < 0) {
+		pr_debug("perf_evlist__mmap: %s\n", strerror(errno));
+		goto out_delete_evlist;
+	}
+
+	/*
+	 * Now that all is properly set up, enable the events, they will
+	 * count just on workload.pid, which will start...
+	 */
+	perf_evlist__enable(evlist);
+
+	/*
+	 * Now!
+	 */
+	perf_evlist__start_workload(evlist);
+
+	while (1) {
+		int before = total_events;
+
+		for (i = 0; i < evlist->nr_mmaps; i++) {
+			union perf_event *event;
+
+			while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
+				const u32 type = event->header.type;
+				const char *name = perf_event__name(type);
+
+				++total_events;
+				if (type < PERF_RECORD_MAX)
+					nr_events[type]++;
+
+				err = perf_evlist__parse_sample(evlist, event, &sample);
+				if (err < 0) {
+					if (verbose)
+						perf_event__fprintf(event, stderr);
+					pr_debug("Couldn't parse sample\n");
+					goto out_delete_evlist;
+				}
+
+				if (verbose) {
+					pr_info("%" PRIu64" %d ", sample.time, sample.cpu);
+					perf_event__fprintf(event, stderr);
+				}
+
+				if (prev_time > sample.time) {
+					pr_debug("%s going backwards in time, prev=%" PRIu64 ", curr=%" PRIu64 "\n",
+						 name, prev_time, sample.time);
+					++errs;
+				}
+
+				prev_time = sample.time;
+
+				if (sample.cpu != cpu) {
+					pr_debug("%s with unexpected cpu, expected %d, got %d\n",
+						 name, cpu, sample.cpu);
+					++errs;
+				}
+
+				if ((pid_t)sample.pid != evlist->workload.pid) {
+					pr_debug("%s with unexpected pid, expected %d, got %d\n",
+						 name, evlist->workload.pid, sample.pid);
+					++errs;
+				}
+
+				if ((pid_t)sample.tid != evlist->workload.pid) {
+					pr_debug("%s with unexpected tid, expected %d, got %d\n",
+						 name, evlist->workload.pid, sample.tid);
+					++errs;
+				}
+
+				if ((type == PERF_RECORD_COMM ||
+				     type == PERF_RECORD_MMAP ||
+				     type == PERF_RECORD_MMAP2 ||
+				     type == PERF_RECORD_FORK ||
+				     type == PERF_RECORD_EXIT) &&
+				     (pid_t)event->comm.pid != evlist->workload.pid) {
+					pr_debug("%s with unexpected pid/tid\n", name);
+					++errs;
+				}
+
+				if ((type == PERF_RECORD_COMM ||
+				     type == PERF_RECORD_MMAP ||
+				     type == PERF_RECORD_MMAP2) &&
+				     event->comm.pid != event->comm.tid) {
+					pr_debug("%s with different pid/tid!\n", name);
+					++errs;
+				}
+
+				switch (type) {
+				case PERF_RECORD_COMM:
+					if (strcmp(event->comm.comm, cmd)) {
+						pr_debug("%s with unexpected comm!\n", name);
+						++errs;
+					}
+					break;
+				case PERF_RECORD_EXIT:
+					goto found_exit;
+				case PERF_RECORD_MMAP:
+					mmap_filename = event->mmap.filename;
+					goto check_bname;
+				case PERF_RECORD_MMAP2:
+					mmap_filename = event->mmap2.filename;
+				check_bname:
+					bname = strrchr(mmap_filename, '/');
+					if (bname != NULL) {
+						if (!found_cmd_mmap)
+							found_cmd_mmap = !strcmp(bname + 1, cmd);
+						if (!found_libc_mmap)
+							found_libc_mmap = !strncmp(bname + 1, "libc", 4);
+						if (!found_ld_mmap)
+							found_ld_mmap = !strncmp(bname + 1, "ld", 2);
+					} else if (!found_vdso_mmap)
+						found_vdso_mmap = !strcmp(mmap_filename, "[vdso]");
+					break;
+
+				case PERF_RECORD_SAMPLE:
+					/* Just ignore samples for now */
+					break;
+				default:
+					pr_debug("Unexpected perf_event->header.type %d!\n",
+						 type);
+					++errs;
+				}
+
+				perf_evlist__mmap_consume(evlist, i);
+			}
+		}
+
+		/*
+		 * We don't use poll here because at least at 3.1 times the
+		 * PERF_RECORD_{!SAMPLE} events don't honour
+		 * perf_event_attr.wakeup_events, just PERF_EVENT_SAMPLE does.
+		 */
+		if (total_events == before && false)
+			poll(evlist->pollfd, evlist->nr_fds, -1);
+
+		sleep(1);
+		if (++wakeups > 5) {
+			pr_debug("No PERF_RECORD_EXIT event!\n");
+			break;
+		}
+	}
+
+found_exit:
+	if (nr_events[PERF_RECORD_COMM] > 1) {
+		pr_debug("Excessive number of PERF_RECORD_COMM events!\n");
+		++errs;
+	}
+
+	if (nr_events[PERF_RECORD_COMM] == 0) {
+		pr_debug("Missing PERF_RECORD_COMM for %s!\n", cmd);
+		++errs;
+	}
+
+	if (!found_cmd_mmap) {
+		pr_debug("PERF_RECORD_MMAP for %s missing!\n", cmd);
+		++errs;
+	}
+
+	if (!found_libc_mmap) {
+		pr_debug("PERF_RECORD_MMAP for %s missing!\n", "libc");
+		++errs;
+	}
+
+	if (!found_ld_mmap) {
+		pr_debug("PERF_RECORD_MMAP for %s missing!\n", "ld");
+		++errs;
+	}
+
+	if (!found_vdso_mmap) {
+		pr_debug("PERF_RECORD_MMAP for %s missing!\n", "[vdso]");
+		++errs;
+	}
+out_delete_evlist:
+	perf_evlist__delete(evlist);
+out:
+	return (err < 0 || errs > 0) ? -1 : 0;
+}
diff --git a/tools/perf/tests/perf-targz-src-pkg b/tools/perf/tests/perf-targz-src-pkg
new file mode 100755
index 00000000000..238aa3927c7
--- /dev/null
+++ b/tools/perf/tests/perf-targz-src-pkg
@@ -0,0 +1,21 @@
+#!/bin/sh
+# Test one of the main kernel Makefile targets to generate a perf sources tarball
+# suitable for build outside the full kernel sources.
+#
+# This is to test that the tools/perf/MANIFEST file lists all the files needed to
+# be in such tarball, which sometimes gets broken when we move files around,
+# like when we made some files that were in tools/perf/ available to other tools/
+# codebases by moving it to tools/include/, etc.
+
+PERF=$1
+cd ${PERF}/../..
+make perf-targz-src-pkg > /dev/null
+TARBALL=$(ls -rt perf-*.tar.gz)
+TMP_DEST=$(mktemp -d)
+tar xf ${TARBALL} -C $TMP_DEST
+rm -f ${TARBALL}
+cd - > /dev/null
+make -C $TMP_DEST/perf*/tools/perf > /dev/null 2>&1
+RC=$?
+rm -rf ${TMP_DEST}
+exit $RC
diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c
new file mode 100644
index 00000000000..3b7cd4d32dc
--- /dev/null
+++ b/tools/perf/tests/perf-time-to-tsc.c
@@ -0,0 +1,172 @@
+#include <stdio.h>
+#include <unistd.h>
+#include <linux/types.h>
+#include <sys/prctl.h>
+
+#include "parse-events.h"
+#include "evlist.h"
+#include "evsel.h"
+#include "thread_map.h"
+#include "cpumap.h"
+#include "tests.h"
+
+#include "../arch/x86/util/tsc.h"
+
+#define CHECK__(x) {				\
+	while ((x) < 0) {			\
+		pr_debug(#x " failed!\n");	\
+		goto out_err;			\
+	}					\
+}
+
+#define CHECK_NOT_NULL__(x) {			\
+	while ((x) == NULL) {			\
+		pr_debug(#x " failed!\n");	\
+		goto out_err;			\
+	}					\
+}
+
+static u64 rdtsc(void)
+{
+	unsigned int low, high;
+
+	asm volatile("rdtsc" : "=a" (low), "=d" (high));
+
+	return low | ((u64)high) << 32;
+}
+
+/**
+ * test__perf_time_to_tsc - test converting perf time to TSC.
+ *
+ * This function implements a test that checks that the conversion of perf time
+ * to and from TSC is consistent with the order of events.  If the test passes
+ * %0 is returned, otherwise %-1 is returned.  If TSC conversion is not
+ * supported then then the test passes but " (not supported)" is printed.
+ */
+int test__perf_time_to_tsc(void)
+{
+	struct record_opts opts = {
+		.mmap_pages	     = UINT_MAX,
+		.user_freq	     = UINT_MAX,
+		.user_interval	     = ULLONG_MAX,
+		.freq		     = 4000,
+		.target		     = {
+			.uses_mmap   = true,
+		},
+		.sample_time	     = true,
+	};
+	struct thread_map *threads = NULL;
+	struct cpu_map *cpus = NULL;
+	struct perf_evlist *evlist = NULL;
+	struct perf_evsel *evsel = NULL;
+	int err = -1, ret, i;
+	const char *comm1, *comm2;
+	struct perf_tsc_conversion tc;
+	struct perf_event_mmap_page *pc;
+	union perf_event *event;
+	u64 test_tsc, comm1_tsc, comm2_tsc;
+	u64 test_time, comm1_time = 0, comm2_time = 0;
+
+	threads = thread_map__new(-1, getpid(), UINT_MAX);
+	CHECK_NOT_NULL__(threads);
+
+	cpus = cpu_map__new(NULL);
+	CHECK_NOT_NULL__(cpus);
+
+	evlist = perf_evlist__new();
+	CHECK_NOT_NULL__(evlist);
+
+	perf_evlist__set_maps(evlist, cpus, threads);
+
+	CHECK__(parse_events(evlist, "cycles:u"));
+
+	perf_evlist__config(evlist, &opts);
+
+	evsel = perf_evlist__first(evlist);
+
+	evsel->attr.comm = 1;
+	evsel->attr.disabled = 1;
+	evsel->attr.enable_on_exec = 0;
+
+	CHECK__(perf_evlist__open(evlist));
+
+	CHECK__(perf_evlist__mmap(evlist, UINT_MAX, false));
+
+	pc = evlist->mmap[0].base;
+	ret = perf_read_tsc_conversion(pc, &tc);
+	if (ret) {
+		if (ret == -EOPNOTSUPP) {
+			fprintf(stderr, " (not supported)");
+			return 0;
+		}
+		goto out_err;
+	}
+
+	perf_evlist__enable(evlist);
+
+	comm1 = "Test COMM 1";
+	CHECK__(prctl(PR_SET_NAME, (unsigned long)comm1, 0, 0, 0));
+
+	test_tsc = rdtsc();
+
+	comm2 = "Test COMM 2";
+	CHECK__(prctl(PR_SET_NAME, (unsigned long)comm2, 0, 0, 0));
+
+	perf_evlist__disable(evlist);
+
+	for (i = 0; i < evlist->nr_mmaps; i++) {
+		while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
+			struct perf_sample sample;
+
+			if (event->header.type != PERF_RECORD_COMM ||
+			    (pid_t)event->comm.pid != getpid() ||
+			    (pid_t)event->comm.tid != getpid())
+				goto next_event;
+
+			if (strcmp(event->comm.comm, comm1) == 0) {
+				CHECK__(perf_evsel__parse_sample(evsel, event,
+								 &sample));
+				comm1_time = sample.time;
+			}
+			if (strcmp(event->comm.comm, comm2) == 0) {
+				CHECK__(perf_evsel__parse_sample(evsel, event,
+								 &sample));
+				comm2_time = sample.time;
+			}
+next_event:
+			perf_evlist__mmap_consume(evlist, i);
+		}
+	}
+
+	if (!comm1_time || !comm2_time)
+		goto out_err;
+
+	test_time = tsc_to_perf_time(test_tsc, &tc);
+	comm1_tsc = perf_time_to_tsc(comm1_time, &tc);
+	comm2_tsc = perf_time_to_tsc(comm2_time, &tc);
+
+	pr_debug("1st event perf time %"PRIu64" tsc %"PRIu64"\n",
+		 comm1_time, comm1_tsc);
+	pr_debug("rdtsc          time %"PRIu64" tsc %"PRIu64"\n",
+		 test_time, test_tsc);
+	pr_debug("2nd event perf time %"PRIu64" tsc %"PRIu64"\n",
+		 comm2_time, comm2_tsc);
+
+	if (test_time <= comm1_time ||
+	    test_time >= comm2_time)
+		goto out_err;
+
+	if (test_tsc <= comm1_tsc ||
+	    test_tsc >= comm2_tsc)
+		goto out_err;
+
+	err = 0;
+
+out_err:
+	if (evlist) {
+		perf_evlist__disable(evlist);
+		perf_evlist__delete(evlist);
+	}
+
+	return err;
+}
diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c
new file mode 100644
index 00000000000..12b322fa347
--- /dev/null
+++ b/tools/perf/tests/pmu.c
@@ -0,0 +1,173 @@
+#include "parse-events.h"
+#include "pmu.h"
+#include "util.h"
+#include "tests.h"
+
+/* Simulated format definitions. */
+static struct test_format {
+	const char *name;
+	const char *value;
+} test_formats[] = {
+	{ "krava01", "config:0-1,62-63\n", },
+	{ "krava02", "config:10-17\n", },
+	{ "krava03", "config:5\n", },
+	{ "krava11", "config1:0,2,4,6,8,20-28\n", },
+	{ "krava12", "config1:63\n", },
+	{ "krava13", "config1:45-47\n", },
+	{ "krava21", "config2:0-3,10-13,20-23,30-33,40-43,50-53,60-63\n", },
+	{ "krava22", "config2:8,18,48,58\n", },
+	{ "krava23", "config2:28-29,38\n", },
+};
+
+/* Simulated users input. */
+static struct parse_events_term test_terms[] = {
+	{
+		.config    = (char *) "krava01",
+		.val.num   = 15,
+		.type_val  = PARSE_EVENTS__TERM_TYPE_NUM,
+		.type_term = PARSE_EVENTS__TERM_TYPE_USER,
+	},
+	{
+		.config    = (char *) "krava02",
+		.val.num   = 170,
+		.type_val  = PARSE_EVENTS__TERM_TYPE_NUM,
+		.type_term = PARSE_EVENTS__TERM_TYPE_USER,
+	},
+	{
+		.config    = (char *) "krava03",
+		.val.num   = 1,
+		.type_val  = PARSE_EVENTS__TERM_TYPE_NUM,
+		.type_term = PARSE_EVENTS__TERM_TYPE_USER,
+	},
+	{
+		.config    = (char *) "krava11",
+		.val.num   = 27,
+		.type_val  = PARSE_EVENTS__TERM_TYPE_NUM,
+		.type_term = PARSE_EVENTS__TERM_TYPE_USER,
+	},
+	{
+		.config    = (char *) "krava12",
+		.val.num   = 1,
+		.type_val  = PARSE_EVENTS__TERM_TYPE_NUM,
+		.type_term = PARSE_EVENTS__TERM_TYPE_USER,
+	},
+	{
+		.config    = (char *) "krava13",
+		.val.num   = 2,
+		.type_val  = PARSE_EVENTS__TERM_TYPE_NUM,
+		.type_term = PARSE_EVENTS__TERM_TYPE_USER,
+	},
+	{
+		.config    = (char *) "krava21",
+		.val.num   = 119,
+		.type_val  = PARSE_EVENTS__TERM_TYPE_NUM,
+		.type_term = PARSE_EVENTS__TERM_TYPE_USER,
+	},
+	{
+		.config    = (char *) "krava22",
+		.val.num   = 11,
+		.type_val  = PARSE_EVENTS__TERM_TYPE_NUM,
+		.type_term = PARSE_EVENTS__TERM_TYPE_USER,
+	},
+	{
+		.config    = (char *) "krava23",
+		.val.num   = 2,
+		.type_val  = PARSE_EVENTS__TERM_TYPE_NUM,
+		.type_term = PARSE_EVENTS__TERM_TYPE_USER,
+	},
+};
+
+/*
+ * Prepare format directory data, exported by kernel
+ * at /sys/bus/event_source/devices/<dev>/format.
+ */
+static char *test_format_dir_get(void)
+{
+	static char dir[PATH_MAX];
+	unsigned int i;
+
+	snprintf(dir, PATH_MAX, "/tmp/perf-pmu-test-format-XXXXXX");
+	if (!mkdtemp(dir))
+		return NULL;
+
+	for (i = 0; i < ARRAY_SIZE(test_formats); i++) {
+		static char name[PATH_MAX];
+		struct test_format *format = &test_formats[i];
+		FILE *file;
+
+		snprintf(name, PATH_MAX, "%s/%s", dir, format->name);
+
+		file = fopen(name, "w");
+		if (!file)
+			return NULL;
+
+		if (1 != fwrite(format->value, strlen(format->value), 1, file))
+			break;
+
+		fclose(file);
+	}
+
+	return dir;
+}
+
+/* Cleanup format directory. */
+static int test_format_dir_put(char *dir)
+{
+	char buf[PATH_MAX];
+	snprintf(buf, PATH_MAX, "rm -f %s/*\n", dir);
+	if (system(buf))
+		return -1;
+
+	snprintf(buf, PATH_MAX, "rmdir %s\n", dir);
+	return system(buf);
+}
+
+static struct list_head *test_terms_list(void)
+{
+	static LIST_HEAD(terms);
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(test_terms); i++)
+		list_add_tail(&test_terms[i].list, &terms);
+
+	return &terms;
+}
+
+int test__pmu(void)
+{
+	char *format = test_format_dir_get();
+	LIST_HEAD(formats);
+	struct list_head *terms = test_terms_list();
+	int ret;
+
+	if (!format)
+		return -EINVAL;
+
+	do {
+		struct perf_event_attr attr;
+
+		memset(&attr, 0, sizeof(attr));
+
+		ret = perf_pmu__format_parse(format, &formats);
+		if (ret)
+			break;
+
+		ret = perf_pmu__config_terms(&formats, &attr, terms);
+		if (ret)
+			break;
+
+		ret = -EINVAL;
+
+		if (attr.config  != 0xc00000000002a823)
+			break;
+		if (attr.config1 != 0x8000400000000145)
+			break;
+		if (attr.config2 != 0x0400000020041d07)
+			break;
+
+		ret = 0;
+	} while (0);
+
+	test_format_dir_put(format);
+	return ret;
+}
diff --git a/tools/perf/tests/python-use.c b/tools/perf/tests/python-use.c
new file mode 100644
index 00000000000..7760277c6de
--- /dev/null
+++ b/tools/perf/tests/python-use.c
@@ -0,0 +1,23 @@
+/*
+ * Just test if we can load the python binding.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include "tests.h"
+
+extern int verbose;
+
+int test__python_use(void)
+{
+	char *cmd;
+	int ret;
+
+	if (asprintf(&cmd, "echo \"import sys ; sys.path.append('%s'); import perf\" | %s %s",
+		     PYTHONPATH, PYTHON, verbose ? "" : "2> /dev/null") < 0)
+		return -1;
+
+	ret = system(cmd) ? -1 : 0;
+	free(cmd);
+	return ret;
+}
diff --git a/tools/perf/tests/rdpmc.c b/tools/perf/tests/rdpmc.c
new file mode 100644
index 00000000000..e59143fd9e7
--- /dev/null
+++ b/tools/perf/tests/rdpmc.c
@@ -0,0 +1,173 @@
+#include <unistd.h>
+#include <stdlib.h>
+#include <signal.h>
+#include <sys/mman.h>
+#include <linux/types.h>
+#include "perf.h"
+#include "debug.h"
+#include "tests.h"
+
+#if defined(__x86_64__) || defined(__i386__)
+
+static u64 rdpmc(unsigned int counter)
+{
+	unsigned int low, high;
+
+	asm volatile("rdpmc" : "=a" (low), "=d" (high) : "c" (counter));
+
+	return low | ((u64)high) << 32;
+}
+
+static u64 rdtsc(void)
+{
+	unsigned int low, high;
+
+	asm volatile("rdtsc" : "=a" (low), "=d" (high));
+
+	return low | ((u64)high) << 32;
+}
+
+static u64 mmap_read_self(void *addr)
+{
+	struct perf_event_mmap_page *pc = addr;
+	u32 seq, idx, time_mult = 0, time_shift = 0;
+	u64 count, cyc = 0, time_offset = 0, enabled, running, delta;
+
+	do {
+		seq = pc->lock;
+		barrier();
+
+		enabled = pc->time_enabled;
+		running = pc->time_running;
+
+		if (enabled != running) {
+			cyc = rdtsc();
+			time_mult = pc->time_mult;
+			time_shift = pc->time_shift;
+			time_offset = pc->time_offset;
+		}
+
+		idx = pc->index;
+		count = pc->offset;
+		if (idx)
+			count += rdpmc(idx - 1);
+
+		barrier();
+	} while (pc->lock != seq);
+
+	if (enabled != running) {
+		u64 quot, rem;
+
+		quot = (cyc >> time_shift);
+		rem = cyc & ((1 << time_shift) - 1);
+		delta = time_offset + quot * time_mult +
+			((rem * time_mult) >> time_shift);
+
+		enabled += delta;
+		if (idx)
+			running += delta;
+
+		quot = count / running;
+		rem = count % running;
+		count = quot * enabled + (rem * enabled) / running;
+	}
+
+	return count;
+}
+
+/*
+ * If the RDPMC instruction faults then signal this back to the test parent task:
+ */
+static void segfault_handler(int sig __maybe_unused,
+			     siginfo_t *info __maybe_unused,
+			     void *uc __maybe_unused)
+{
+	exit(-1);
+}
+
+static int __test__rdpmc(void)
+{
+	volatile int tmp = 0;
+	u64 i, loops = 1000;
+	int n;
+	int fd;
+	void *addr;
+	struct perf_event_attr attr = {
+		.type = PERF_TYPE_HARDWARE,
+		.config = PERF_COUNT_HW_INSTRUCTIONS,
+		.exclude_kernel = 1,
+	};
+	u64 delta_sum = 0;
+        struct sigaction sa;
+
+	sigfillset(&sa.sa_mask);
+	sa.sa_sigaction = segfault_handler;
+	sigaction(SIGSEGV, &sa, NULL);
+
+	fd = sys_perf_event_open(&attr, 0, -1, -1, 0);
+	if (fd < 0) {
+		pr_err("Error: sys_perf_event_open() syscall returned "
+		       "with %d (%s)\n", fd, strerror(errno));
+		return -1;
+	}
+
+	addr = mmap(NULL, page_size, PROT_READ, MAP_SHARED, fd, 0);
+	if (addr == (void *)(-1)) {
+		pr_err("Error: mmap() syscall returned with (%s)\n",
+		       strerror(errno));
+		goto out_close;
+	}
+
+	for (n = 0; n < 6; n++) {
+		u64 stamp, now, delta;
+
+		stamp = mmap_read_self(addr);
+
+		for (i = 0; i < loops; i++)
+			tmp++;
+
+		now = mmap_read_self(addr);
+		loops *= 10;
+
+		delta = now - stamp;
+		pr_debug("%14d: %14Lu\n", n, (long long)delta);
+
+		delta_sum += delta;
+	}
+
+	munmap(addr, page_size);
+	pr_debug("   ");
+out_close:
+	close(fd);
+
+	if (!delta_sum)
+		return -1;
+
+	return 0;
+}
+
+int test__rdpmc(void)
+{
+	int status = 0;
+	int wret = 0;
+	int ret;
+	int pid;
+
+	pid = fork();
+	if (pid < 0)
+		return -1;
+
+	if (!pid) {
+		ret = __test__rdpmc();
+
+		exit(ret);
+	}
+
+	wret = waitpid(pid, &status, 0);
+	if (wret < 0 || status)
+		return -1;
+
+	return 0;
+}
+
+#endif
diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c
new file mode 100644
index 00000000000..7ae8d17db3d
--- /dev/null
+++ b/tools/perf/tests/sample-parsing.c
@@ -0,0 +1,320 @@
+#include <stdbool.h>
+#include <linux/types.h>
+
+#include "util.h"
+#include "event.h"
+#include "evsel.h"
+
+#include "tests.h"
+
+#define COMP(m) do {					\
+	if (s1->m != s2->m) {				\
+		pr_debug("Samples differ at '"#m"'\n");	\
+		return false;				\
+	}						\
+} while (0)
+
+#define MCOMP(m) do {					\
+	if (memcmp(&s1->m, &s2->m, sizeof(s1->m))) {	\
+		pr_debug("Samples differ at '"#m"'\n");	\
+		return false;				\
+	}						\
+} while (0)
+
+static bool samples_same(const struct perf_sample *s1,
+			 const struct perf_sample *s2,
+			 u64 type, u64 read_format)
+{
+	size_t i;
+
+	if (type & PERF_SAMPLE_IDENTIFIER)
+		COMP(id);
+
+	if (type & PERF_SAMPLE_IP)
+		COMP(ip);
+
+	if (type & PERF_SAMPLE_TID) {
+		COMP(pid);
+		COMP(tid);
+	}
+
+	if (type & PERF_SAMPLE_TIME)
+		COMP(time);
+
+	if (type & PERF_SAMPLE_ADDR)
+		COMP(addr);
+
+	if (type & PERF_SAMPLE_ID)
+		COMP(id);
+
+	if (type & PERF_SAMPLE_STREAM_ID)
+		COMP(stream_id);
+
+	if (type & PERF_SAMPLE_CPU)
+		COMP(cpu);
+
+	if (type & PERF_SAMPLE_PERIOD)
+		COMP(period);
+
+	if (type & PERF_SAMPLE_READ) {
+		if (read_format & PERF_FORMAT_GROUP)
+			COMP(read.group.nr);
+		else
+			COMP(read.one.value);
+		if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+			COMP(read.time_enabled);
+		if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+			COMP(read.time_running);
+		/* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */
+		if (read_format & PERF_FORMAT_GROUP) {
+			for (i = 0; i < s1->read.group.nr; i++)
+				MCOMP(read.group.values[i]);
+		} else {
+			COMP(read.one.id);
+		}
+	}
+
+	if (type & PERF_SAMPLE_CALLCHAIN) {
+		COMP(callchain->nr);
+		for (i = 0; i < s1->callchain->nr; i++)
+			COMP(callchain->ips[i]);
+	}
+
+	if (type & PERF_SAMPLE_RAW) {
+		COMP(raw_size);
+		if (memcmp(s1->raw_data, s2->raw_data, s1->raw_size)) {
+			pr_debug("Samples differ at 'raw_data'\n");
+			return false;
+		}
+	}
+
+	if (type & PERF_SAMPLE_BRANCH_STACK) {
+		COMP(branch_stack->nr);
+		for (i = 0; i < s1->branch_stack->nr; i++)
+			MCOMP(branch_stack->entries[i]);
+	}
+
+	if (type & PERF_SAMPLE_REGS_USER) {
+		size_t sz = hweight_long(s1->user_regs.mask) * sizeof(u64);
+
+		COMP(user_regs.mask);
+		COMP(user_regs.abi);
+		if (s1->user_regs.abi &&
+		    (!s1->user_regs.regs || !s2->user_regs.regs ||
+		     memcmp(s1->user_regs.regs, s2->user_regs.regs, sz))) {
+			pr_debug("Samples differ at 'user_regs'\n");
+			return false;
+		}
+	}
+
+	if (type & PERF_SAMPLE_STACK_USER) {
+		COMP(user_stack.size);
+		if (memcmp(s1->user_stack.data, s1->user_stack.data,
+			   s1->user_stack.size)) {
+			pr_debug("Samples differ at 'user_stack'\n");
+			return false;
+		}
+	}
+
+	if (type & PERF_SAMPLE_WEIGHT)
+		COMP(weight);
+
+	if (type & PERF_SAMPLE_DATA_SRC)
+		COMP(data_src);
+
+	if (type & PERF_SAMPLE_TRANSACTION)
+		COMP(transaction);
+
+	return true;
+}
+
+static int do_test(u64 sample_type, u64 sample_regs_user, u64 read_format)
+{
+	struct perf_evsel evsel = {
+		.needs_swap = false,
+		.attr = {
+			.sample_type = sample_type,
+			.sample_regs_user = sample_regs_user,
+			.read_format = read_format,
+		},
+	};
+	union perf_event *event;
+	union {
+		struct ip_callchain callchain;
+		u64 data[64];
+	} callchain = {
+		/* 3 ips */
+		.data = {3, 201, 202, 203},
+	};
+	union {
+		struct branch_stack branch_stack;
+		u64 data[64];
+	} branch_stack = {
+		/* 1 branch_entry */
+		.data = {1, 211, 212, 213},
+	};
+	u64 user_regs[64];
+	const u64 raw_data[] = {0x123456780a0b0c0dULL, 0x1102030405060708ULL};
+	const u64 data[] = {0x2211443366558877ULL, 0, 0xaabbccddeeff4321ULL};
+	struct perf_sample sample = {
+		.ip		= 101,
+		.pid		= 102,
+		.tid		= 103,
+		.time		= 104,
+		.addr		= 105,
+		.id		= 106,
+		.stream_id	= 107,
+		.period		= 108,
+		.weight		= 109,
+		.cpu		= 110,
+		.raw_size	= sizeof(raw_data),
+		.data_src	= 111,
+		.transaction	= 112,
+		.raw_data	= (void *)raw_data,
+		.callchain	= &callchain.callchain,
+		.branch_stack	= &branch_stack.branch_stack,
+		.user_regs	= {
+			.abi	= PERF_SAMPLE_REGS_ABI_64,
+			.mask	= sample_regs_user,
+			.regs	= user_regs,
+		},
+		.user_stack	= {
+			.size	= sizeof(data),
+			.data	= (void *)data,
+		},
+		.read		= {
+			.time_enabled = 0x030a59d664fca7deULL,
+			.time_running = 0x011b6ae553eb98edULL,
+		},
+	};
+	struct sample_read_value values[] = {{1, 5}, {9, 3}, {2, 7}, {6, 4},};
+	struct perf_sample sample_out;
+	size_t i, sz, bufsz;
+	int err, ret = -1;
+
+	for (i = 0; i < sizeof(user_regs); i++)
+		*(i + (u8 *)user_regs) = i & 0xfe;
+
+	if (read_format & PERF_FORMAT_GROUP) {
+		sample.read.group.nr     = 4;
+		sample.read.group.values = values;
+	} else {
+		sample.read.one.value = 0x08789faeb786aa87ULL;
+		sample.read.one.id    = 99;
+	}
+
+	sz = perf_event__sample_event_size(&sample, sample_type, read_format);
+	bufsz = sz + 4096; /* Add a bit for overrun checking */
+	event = malloc(bufsz);
+	if (!event) {
+		pr_debug("malloc failed\n");
+		return -1;
+	}
+
+	memset(event, 0xff, bufsz);
+	event->header.type = PERF_RECORD_SAMPLE;
+	event->header.misc = 0;
+	event->header.size = sz;
+
+	err = perf_event__synthesize_sample(event, sample_type, read_format,
+					    &sample, false);
+	if (err) {
+		pr_debug("%s failed for sample_type %#"PRIx64", error %d\n",
+			 "perf_event__synthesize_sample", sample_type, err);
+		goto out_free;
+	}
+
+	/* The data does not contain 0xff so we use that to check the size */
+	for (i = bufsz; i > 0; i--) {
+		if (*(i - 1 + (u8 *)event) != 0xff)
+			break;
+	}
+	if (i != sz) {
+		pr_debug("Event size mismatch: actual %zu vs expected %zu\n",
+			 i, sz);
+		goto out_free;
+	}
+
+	evsel.sample_size = __perf_evsel__sample_size(sample_type);
+
+	err = perf_evsel__parse_sample(&evsel, event, &sample_out);
+	if (err) {
+		pr_debug("%s failed for sample_type %#"PRIx64", error %d\n",
+			 "perf_evsel__parse_sample", sample_type, err);
+		goto out_free;
+	}
+
+	if (!samples_same(&sample, &sample_out, sample_type, read_format)) {
+		pr_debug("parsing failed for sample_type %#"PRIx64"\n",
+			 sample_type);
+		goto out_free;
+	}
+
+	ret = 0;
+out_free:
+	free(event);
+	if (ret && read_format)
+		pr_debug("read_format %#"PRIx64"\n", read_format);
+	return ret;
+}
+
+/**
+ * test__sample_parsing - test sample parsing.
+ *
+ * This function implements a test that synthesizes a sample event, parses it
+ * and then checks that the parsed sample matches the original sample.  The test
+ * checks sample format bits separately and together.  If the test passes %0 is
+ * returned, otherwise %-1 is returned.
+ */
+int test__sample_parsing(void)
+{
+	const u64 rf[] = {4, 5, 6, 7, 12, 13, 14, 15};
+	u64 sample_type;
+	u64 sample_regs_user;
+	size_t i;
+	int err;
+
+	/*
+	 * Fail the test if it has not been updated when new sample format bits
+	 * were added.  Please actually update the test rather than just change
+	 * the condition below.
+	 */
+	if (PERF_SAMPLE_MAX > PERF_SAMPLE_TRANSACTION << 1) {
+		pr_debug("sample format has changed, some new PERF_SAMPLE_ bit was introduced - test needs updating\n");
+		return -1;
+	}
+
+	/* Test each sample format bit separately */
+	for (sample_type = 1; sample_type != PERF_SAMPLE_MAX;
+	     sample_type <<= 1) {
+		/* Test read_format variations */
+		if (sample_type == PERF_SAMPLE_READ) {
+			for (i = 0; i < ARRAY_SIZE(rf); i++) {
+				err = do_test(sample_type, 0, rf[i]);
+				if (err)
+					return err;
+			}
+			continue;
+		}
+
+		if (sample_type == PERF_SAMPLE_REGS_USER)
+			sample_regs_user = 0x3fff;
+		else
+			sample_regs_user = 0;
+
+		err = do_test(sample_type, sample_regs_user, 0);
+		if (err)
+			return err;
+	}
+
+	/* Test all sample format bits together */
+	sample_type = PERF_SAMPLE_MAX - 1;
+	sample_regs_user = 0x3fff;
+	for (i = 0; i < ARRAY_SIZE(rf); i++) {
+		err = do_test(sample_type, sample_regs_user, rf[i]);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
new file mode 100644
index 00000000000..983d6b8562a
--- /dev/null
+++ b/tools/perf/tests/sw-clock.c
@@ -0,0 +1,122 @@
+#include <unistd.h>
+#include <stdlib.h>
+#include <signal.h>
+#include <sys/mman.h>
+
+#include "tests.h"
+#include "util/evsel.h"
+#include "util/evlist.h"
+#include "util/cpumap.h"
+#include "util/thread_map.h"
+
+#define NR_LOOPS  10000000
+
+/*
+ * This test will open software clock events (cpu-clock, task-clock)
+ * then check their frequency -> period conversion has no artifact of
+ * setting period to 1 forcefully.
+ */
+static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
+{
+	int i, err = -1;
+	volatile int tmp = 0;
+	u64 total_periods = 0;
+	int nr_samples = 0;
+	union perf_event *event;
+	struct perf_evsel *evsel;
+	struct perf_evlist *evlist;
+	struct perf_event_attr attr = {
+		.type = PERF_TYPE_SOFTWARE,
+		.config = clock_id,
+		.sample_type = PERF_SAMPLE_PERIOD,
+		.exclude_kernel = 1,
+		.disabled = 1,
+		.freq = 1,
+	};
+
+	attr.sample_freq = 500;
+
+	evlist = perf_evlist__new();
+	if (evlist == NULL) {
+		pr_debug("perf_evlist__new\n");
+		return -1;
+	}
+
+	evsel = perf_evsel__new(&attr);
+	if (evsel == NULL) {
+		pr_debug("perf_evsel__new\n");
+		goto out_delete_evlist;
+	}
+	perf_evlist__add(evlist, evsel);
+
+	evlist->cpus = cpu_map__dummy_new();
+	evlist->threads = thread_map__new_by_tid(getpid());
+	if (!evlist->cpus || !evlist->threads) {
+		err = -ENOMEM;
+		pr_debug("Not enough memory to create thread/cpu maps\n");
+		goto out_delete_evlist;
+	}
+
+	if (perf_evlist__open(evlist)) {
+		const char *knob = "/proc/sys/kernel/perf_event_max_sample_rate";
+
+		err = -errno;
+		pr_debug("Couldn't open evlist: %s\nHint: check %s, using %" PRIu64 " in this test.\n",
+			 strerror(errno), knob, (u64)attr.sample_freq);
+		goto out_delete_evlist;
+	}
+
+	err = perf_evlist__mmap(evlist, 128, true);
+	if (err < 0) {
+		pr_debug("failed to mmap event: %d (%s)\n", errno,
+			 strerror(errno));
+		goto out_delete_evlist;
+	}
+
+	perf_evlist__enable(evlist);
+
+	/* collect samples */
+	for (i = 0; i < NR_LOOPS; i++)
+		tmp++;
+
+	perf_evlist__disable(evlist);
+
+	while ((event = perf_evlist__mmap_read(evlist, 0)) != NULL) {
+		struct perf_sample sample;
+
+		if (event->header.type != PERF_RECORD_SAMPLE)
+			goto next_event;
+
+		err = perf_evlist__parse_sample(evlist, event, &sample);
+		if (err < 0) {
+			pr_debug("Error during parse sample\n");
+			goto out_delete_evlist;
+		}
+
+		total_periods += sample.period;
+		nr_samples++;
+next_event:
+		perf_evlist__mmap_consume(evlist, 0);
+	}
+
+	if ((u64) nr_samples == total_periods) {
+		pr_debug("All (%d) samples have period value of 1!\n",
+			 nr_samples);
+		err = -1;
+	}
+
+out_delete_evlist:
+	perf_evlist__delete(evlist);
+	return err;
+}
+
+int test__sw_clock_freq(void)
+{
+	int ret;
+
+	ret = __test__sw_clock_freq(PERF_COUNT_SW_CPU_CLOCK);
+	if (!ret)
+		ret = __test__sw_clock_freq(PERF_COUNT_SW_TASK_CLOCK);
+
+	return ret;
+}
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
new file mode 100644
index 00000000000..5ff3db318f1
--- /dev/null
+++ b/tools/perf/tests/task-exit.c
@@ -0,0 +1,118 @@
+#include "evlist.h"
+#include "evsel.h"
+#include "thread_map.h"
+#include "cpumap.h"
+#include "tests.h"
+
+#include <signal.h>
+
+static int exited;
+static int nr_exit;
+
+static void sig_handler(int sig __maybe_unused)
+{
+	exited = 1;
+}
+
+/*
+ * perf_evlist__prepare_workload will send a SIGUSR1 if the fork fails, since
+ * we asked by setting its exec_error to this handler.
+ */
+static void workload_exec_failed_signal(int signo __maybe_unused,
+					siginfo_t *info __maybe_unused,
+					void *ucontext __maybe_unused)
+{
+	exited	= 1;
+	nr_exit = -1;
+}
+
+/*
+ * This test will start a workload that does nothing then it checks
+ * if the number of exit event reported by the kernel is 1 or not
+ * in order to check the kernel returns correct number of event.
+ */
+int test__task_exit(void)
+{
+	int err = -1;
+	union perf_event *event;
+	struct perf_evsel *evsel;
+	struct perf_evlist *evlist;
+	struct target target = {
+		.uid		= UINT_MAX,
+		.uses_mmap	= true,
+	};
+	const char *argv[] = { "true", NULL };
+
+	signal(SIGCHLD, sig_handler);
+
+	evlist = perf_evlist__new_default();
+	if (evlist == NULL) {
+		pr_debug("perf_evlist__new_default\n");
+		return -1;
+	}
+
+	/*
+	 * Create maps of threads and cpus to monitor. In this case
+	 * we start with all threads and cpus (-1, -1) but then in
+	 * perf_evlist__prepare_workload we'll fill in the only thread
+	 * we're monitoring, the one forked there.
+	 */
+	evlist->cpus = cpu_map__dummy_new();
+	evlist->threads = thread_map__new_by_tid(-1);
+	if (!evlist->cpus || !evlist->threads) {
+		err = -ENOMEM;
+		pr_debug("Not enough memory to create thread/cpu maps\n");
+		goto out_delete_evlist;
+	}
+
+	err = perf_evlist__prepare_workload(evlist, &target, argv, false,
+					    workload_exec_failed_signal);
+	if (err < 0) {
+		pr_debug("Couldn't run the workload!\n");
+		goto out_delete_evlist;
+	}
+
+	evsel = perf_evlist__first(evlist);
+	evsel->attr.task = 1;
+	evsel->attr.sample_freq = 0;
+	evsel->attr.inherit = 0;
+	evsel->attr.watermark = 0;
+	evsel->attr.wakeup_events = 1;
+	evsel->attr.exclude_kernel = 1;
+
+	err = perf_evlist__open(evlist);
+	if (err < 0) {
+		pr_debug("Couldn't open the evlist: %s\n", strerror(-err));
+		goto out_delete_evlist;
+	}
+
+	if (perf_evlist__mmap(evlist, 128, true) < 0) {
+		pr_debug("failed to mmap events: %d (%s)\n", errno,
+			 strerror(errno));
+		goto out_delete_evlist;
+	}
+
+	perf_evlist__start_workload(evlist);
+
+retry:
+	while ((event = perf_evlist__mmap_read(evlist, 0)) != NULL) {
+		if (event->header.type == PERF_RECORD_EXIT)
+			nr_exit++;
+
+		perf_evlist__mmap_consume(evlist, 0);
+	}
+
+	if (!exited || !nr_exit) {
+		poll(evlist->pollfd, evlist->nr_fds, -1);
+		goto retry;
+	}
+
+	if (nr_exit != 1) {
+		pr_debug("received %d EXIT records\n", nr_exit);
+		err = -1;
+	}
+
+out_delete_evlist:
+	perf_evlist__delete(evlist);
+	return err;
+}
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
new file mode 100644
index 00000000000..ed64790a395
--- /dev/null
+++ b/tools/perf/tests/tests.h
@@ -0,0 +1,60 @@
+#ifndef TESTS_H
+#define TESTS_H
+
+#define TEST_ASSERT_VAL(text, cond)					 \
+do {									 \
+	if (!(cond)) {							 \
+		pr_debug("FAILED %s:%d %s\n", __FILE__, __LINE__, text); \
+		return -1;						 \
+	}								 \
+} while (0)
+
+enum {
+	TEST_OK   =  0,
+	TEST_FAIL = -1,
+	TEST_SKIP = -2,
+};
+
+/* Tests */
+int test__vmlinux_matches_kallsyms(void);
+int test__open_syscall_event(void);
+int test__open_syscall_event_on_all_cpus(void);
+int test__basic_mmap(void);
+int test__PERF_RECORD(void);
+int test__rdpmc(void);
+int test__perf_evsel__roundtrip_name_test(void);
+int test__perf_evsel__tp_sched_test(void);
+int test__syscall_open_tp_fields(void);
+int test__pmu(void);
+int test__attr(void);
+int test__dso_data(void);
+int test__dso_data_cache(void);
+int test__dso_data_reopen(void);
+int test__parse_events(void);
+int test__hists_link(void);
+int test__python_use(void);
+int test__bp_signal(void);
+int test__bp_signal_overflow(void);
+int test__task_exit(void);
+int test__sw_clock_freq(void);
+int test__perf_time_to_tsc(void);
+int test__code_reading(void);
+int test__sample_parsing(void);
+int test__keep_tracking(void);
+int test__parse_no_sample_id_all(void);
+int test__dwarf_unwind(void);
+int test__hists_filter(void);
+int test__mmap_thread_lookup(void);
+int test__thread_mg_share(void);
+int test__hists_output(void);
+int test__hists_cumulate(void);
+
+#if defined(__x86_64__) || defined(__i386__) || defined(__arm__)
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
+struct thread;
+struct perf_sample;
+int test__arch_unwind_sample(struct perf_sample *sample,
+			     struct thread *thread);
+#endif
+#endif
+#endif /* TESTS_H */
diff --git a/tools/perf/tests/thread-mg-share.c b/tools/perf/tests/thread-mg-share.c
new file mode 100644
index 00000000000..2b2e0dbe114
--- /dev/null
+++ b/tools/perf/tests/thread-mg-share.c
@@ -0,0 +1,90 @@
+#include "tests.h"
+#include "machine.h"
+#include "thread.h"
+#include "map.h"
+
+int test__thread_mg_share(void)
+{
+	struct machines machines;
+	struct machine *machine;
+
+	/* thread group */
+	struct thread *leader;
+	struct thread *t1, *t2, *t3;
+	struct map_groups *mg;
+
+	/* other process */
+	struct thread *other, *other_leader;
+	struct map_groups *other_mg;
+
+	/*
+	 * This test create 2 processes abstractions (struct thread)
+	 * with several threads and checks they properly share and
+	 * maintain map groups info (struct map_groups).
+	 *
+	 * thread group (pid: 0, tids: 0, 1, 2, 3)
+	 * other  group (pid: 4, tids: 4, 5)
+	*/
+
+	machines__init(&machines);
+	machine = &machines.host;
+
+	/* create process with 4 threads */
+	leader = machine__findnew_thread(machine, 0, 0);
+	t1     = machine__findnew_thread(machine, 0, 1);
+	t2     = machine__findnew_thread(machine, 0, 2);
+	t3     = machine__findnew_thread(machine, 0, 3);
+
+	/* and create 1 separated process, without thread leader */
+	other  = machine__findnew_thread(machine, 4, 5);
+
+	TEST_ASSERT_VAL("failed to create threads",
+			leader && t1 && t2 && t3 && other);
+
+	mg = leader->mg;
+	TEST_ASSERT_VAL("wrong refcnt", mg->refcnt == 4);
+
+	/* test the map groups pointer is shared */
+	TEST_ASSERT_VAL("map groups don't match", mg == t1->mg);
+	TEST_ASSERT_VAL("map groups don't match", mg == t2->mg);
+	TEST_ASSERT_VAL("map groups don't match", mg == t3->mg);
+
+	/*
+	 * Verify the other leader was created by previous call.
+	 * It should have shared map groups with no change in
+	 * refcnt.
+	 */
+	other_leader = machine__find_thread(machine, 4, 4);
+	TEST_ASSERT_VAL("failed to find other leader", other_leader);
+
+	other_mg = other->mg;
+	TEST_ASSERT_VAL("wrong refcnt", other_mg->refcnt == 2);
+
+	TEST_ASSERT_VAL("map groups don't match", other_mg == other_leader->mg);
+
+	/* release thread group */
+	thread__delete(leader);
+	TEST_ASSERT_VAL("wrong refcnt", mg->refcnt == 3);
+
+	thread__delete(t1);
+	TEST_ASSERT_VAL("wrong refcnt", mg->refcnt == 2);
+
+	thread__delete(t2);
+	TEST_ASSERT_VAL("wrong refcnt", mg->refcnt == 1);
+
+	thread__delete(t3);
+
+	/* release other group  */
+	thread__delete(other_leader);
+	TEST_ASSERT_VAL("wrong refcnt", other_mg->refcnt == 1);
+
+	thread__delete(other);
+
+	/*
+	 * Cannot call machine__delete_threads(machine) now,
+	 * because we've already released all the threads.
+	 */
+
+	machines__exit(&machines);
+	return 0;
+}
diff --git a/tools/perf/builtin-test.c b/tools/perf/tests/vmlinux-kallsyms.c
index 035b9fa063a..3d9088003a5 100644
--- a/tools/perf/builtin-test.c
+++ b/tools/perf/tests/vmlinux-kallsyms.c
@@ -1,27 +1,24 @@
-/*
- * builtin-test.c
- *
- * Builtin regression testing command: ever growing number of sanity tests
- */
-#include "builtin.h"
-
-#include "util/cache.h"
-#include "util/debug.h"
-#include "util/parse-options.h"
-#include "util/session.h"
-#include "util/symbol.h"
-#include "util/thread.h"
-
-static long page_size;
-
-static int vmlinux_matches_kallsyms_filter(struct map *map __used, struct symbol *sym)
+#include <linux/compiler.h>
+#include <linux/rbtree.h>
+#include <string.h>
+#include "map.h"
+#include "symbol.h"
+#include "util.h"
+#include "tests.h"
+#include "debug.h"
+#include "machine.h"
+
+static int vmlinux_matches_kallsyms_filter(struct map *map __maybe_unused,
+					   struct symbol *sym)
 {
 	bool *visited = symbol__priv(sym);
 	*visited = true;
 	return 0;
 }
 
-static int test__vmlinux_matches_kallsyms(void)
+#define UM(x) kallsyms_map->unmap_ip(kallsyms_map, (x))
+
+int test__vmlinux_matches_kallsyms(void)
 {
 	int err = -1;
 	struct rb_node *nd;
@@ -29,7 +26,7 @@ static int test__vmlinux_matches_kallsyms(void)
 	struct map *kallsyms_map, *vmlinux_map;
 	struct machine kallsyms, vmlinux;
 	enum map_type type = MAP__FUNCTION;
-	struct ref_reloc_sym ref_reloc_sym = { .name = "_stext", };
+	u64 mem_start, mem_end;
 
 	/*
 	 * Step 1:
@@ -49,7 +46,7 @@ static int test__vmlinux_matches_kallsyms(void)
 	 */
 	if (machine__create_kernel_maps(&kallsyms) < 0) {
 		pr_debug("machine__create_kernel_maps ");
-		return -1;
+		goto out;
 	}
 
 	/*
@@ -72,14 +69,6 @@ static int test__vmlinux_matches_kallsyms(void)
 	 */
 	kallsyms_map = machine__kernel_map(&kallsyms, type);
 
-	sym = map__find_symbol_by_name(kallsyms_map, ref_reloc_sym.name, NULL);
-	if (sym == NULL) {
-		pr_debug("dso__find_symbol_by_name ");
-		goto out;
-	}
-
-	ref_reloc_sym.addr = sym->start;
-
 	/*
 	 * Step 5:
 	 *
@@ -91,7 +80,6 @@ static int test__vmlinux_matches_kallsyms(void)
 	}
 
 	vmlinux_map = machine__kernel_map(&vmlinux, type);
-	map__kmap(vmlinux_map)->ref_reloc_sym = &ref_reloc_sym;
 
 	/*
 	 * Step 6:
@@ -106,7 +94,8 @@ static int test__vmlinux_matches_kallsyms(void)
 	 */
 	if (machine__load_vmlinux_path(&vmlinux, type,
 				       vmlinux_matches_kallsyms_filter) <= 0) {
-		pr_debug("machine__load_vmlinux_path ");
+		pr_debug("Couldn't find a vmlinux that matches the kernel running on this machine, skipping test\n");
+		err = TEST_SKIP;
 		goto out;
 	}
 
@@ -119,12 +108,22 @@ static int test__vmlinux_matches_kallsyms(void)
 	 * end addresses too.
 	 */
 	for (nd = rb_first(&vmlinux_map->dso->symbols[type]); nd; nd = rb_next(nd)) {
-		struct symbol *pair;
+		struct symbol *pair, *first_pair;
+		bool backwards = true;
 
 		sym  = rb_entry(nd, struct symbol, rb_node);
-		pair = machine__find_kernel_symbol(&kallsyms, type, sym->start, NULL, NULL);
 
-		if (pair && pair->start == sym->start) {
+		if (sym->start == sym->end)
+			continue;
+
+		mem_start = vmlinux_map->unmap_ip(vmlinux_map, sym->start);
+		mem_end = vmlinux_map->unmap_ip(vmlinux_map, sym->end);
+
+		first_pair = machine__find_kernel_symbol(&kallsyms, type,
+							 mem_start, NULL, NULL);
+		pair = first_pair;
+
+		if (pair && UM(pair->start) == mem_start) {
 next_pair:
 			if (strcmp(sym->name, pair->name) == 0) {
 				/*
@@ -136,28 +135,46 @@ next_pair:
 				 * off the real size. More than that and we
 				 * _really_ have a problem.
 				 */
-				s64 skew = sym->end - pair->end;
-				if (llabs(skew) < page_size)
-					continue;
+				s64 skew = mem_end - UM(pair->end);
+				if (llabs(skew) >= page_size)
+					pr_debug("%#" PRIx64 ": diff end addr for %s v: %#" PRIx64 " k: %#" PRIx64 "\n",
+						 mem_start, sym->name, mem_end,
+						 UM(pair->end));
 
-				pr_debug("%#Lx: diff end addr for %s v: %#Lx k: %#Lx\n",
-					 sym->start, sym->name, sym->end, pair->end);
-			} else {
-				struct rb_node *nnd = rb_prev(&pair->rb_node);
+				/*
+				 * Do not count this as a failure, because we
+				 * could really find a case where it's not
+				 * possible to get proper function end from
+				 * kallsyms.
+				 */
+				continue;
 
+			} else {
+				struct rb_node *nnd;
+detour:
+				nnd = backwards ? rb_prev(&pair->rb_node) :
+						  rb_next(&pair->rb_node);
 				if (nnd) {
 					struct symbol *next = rb_entry(nnd, struct symbol, rb_node);
 
-					if (next->start == sym->start) {
+					if (UM(next->start) == mem_start) {
 						pair = next;
 						goto next_pair;
 					}
 				}
-				pr_debug("%#Lx: diff name v: %s k: %s\n",
-					 sym->start, sym->name, pair->name);
+
+				if (backwards) {
+					backwards = false;
+					pair = first_pair;
+					goto detour;
+				}
+
+				pr_debug("%#" PRIx64 ": diff name v: %s k: %s\n",
+					 mem_start, sym->name, pair->name);
 			}
 		} else
-			pr_debug("%#Lx: %s not on kallsyms\n", sym->start, sym->name);
+			pr_debug("%#" PRIx64 ": %s not on kallsyms\n",
+				 mem_start, sym->name);
 
 		err = -1;
 	}
@@ -190,16 +207,19 @@ next_pair:
 	for (nd = rb_first(&vmlinux.kmaps.maps[type]); nd; nd = rb_next(nd)) {
 		struct map *pos = rb_entry(nd, struct map, rb_node), *pair;
 
-		pair = map_groups__find(&kallsyms.kmaps, type, pos->start);
+		mem_start = vmlinux_map->unmap_ip(vmlinux_map, pos->start);
+		mem_end = vmlinux_map->unmap_ip(vmlinux_map, pos->end);
+
+		pair = map_groups__find(&kallsyms.kmaps, type, mem_start);
 		if (pair == NULL || pair->priv)
 			continue;
 
-		if (pair->start == pos->start) {
+		if (pair->start == mem_start) {
 			pair->priv = 1;
-			pr_info(" %Lx-%Lx %Lx %s in kallsyms as",
+			pr_info(" %" PRIx64 "-%" PRIx64 " %" PRIx64 " %s in kallsyms as",
 				pos->start, pos->end, pos->pgoff, pos->dso->name);
-			if (pos->pgoff != pair->pgoff || pos->end != pair->end)
-				pr_info(": \n*%Lx-%Lx %Lx",
+			if (mem_end != pair->end)
+				pr_info(":\n*%" PRIx64 "-%" PRIx64 " %" PRIx64,
 					pair->start, pair->end, pair->pgoff);
 			pr_info(" %s\n", pair->dso->name);
 			pair->priv = 1;
@@ -216,66 +236,7 @@ next_pair:
 			map__fprintf(pos, stderr);
 	}
 out:
+	machine__exit(&kallsyms);
+	machine__exit(&vmlinux);
 	return err;
 }
-
-static struct test {
-	const char *desc;
-	int (*func)(void);
-} tests[] = {
-	{
-		.desc = "vmlinux symtab matches kallsyms",
-		.func = test__vmlinux_matches_kallsyms,
-	},
-	{
-		.func = NULL,
-	},
-};
-
-static int __cmd_test(void)
-{
-	int i = 0;
-
-	page_size = sysconf(_SC_PAGE_SIZE);
-
-	while (tests[i].func) {
-		int err;
-		pr_info("%2d: %s:", i + 1, tests[i].desc);
-		pr_debug("\n--- start ---\n");
-		err = tests[i].func();
-		pr_debug("---- end ----\n%s:", tests[i].desc);
-		pr_info(" %s\n", err ? "FAILED!\n" : "Ok");
-		++i;
-	}
-
-	return 0;
-}
-
-static const char * const test_usage[] = {
-	"perf test [<options>]",
-	NULL,
-};
-
-static const struct option test_options[] = {
-	OPT_INTEGER('v', "verbose", &verbose,
-		    "be more verbose (show symbol address, etc)"),
-	OPT_END()
-};
-
-int cmd_test(int argc, const char **argv, const char *prefix __used)
-{
-	argc = parse_options(argc, argv, test_options, test_usage, 0);
-	if (argc)
-		usage_with_options(test_usage, test_options);
-
-	symbol_conf.priv_size = sizeof(int);
-	symbol_conf.sort_by_name = true;
-	symbol_conf.try_vmlinux_path = true;
-
-	if (symbol__init() < 0)
-		return -1;
-
-	setup_pager();
-
-	return __cmd_test();
-}
diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c
new file mode 100644
index 00000000000..3ccf6e14f89
--- /dev/null
+++ b/tools/perf/ui/browser.c
@@ -0,0 +1,719 @@
+#include "../util.h"
+#include "../cache.h"
+#include "../../perf.h"
+#include "libslang.h"
+#include "ui.h"
+#include "util.h"
+#include <linux/compiler.h>
+#include <linux/list.h>
+#include <linux/rbtree.h>
+#include <stdlib.h>
+#include <sys/ttydefaults.h>
+#include "browser.h"
+#include "helpline.h"
+#include "keysyms.h"
+#include "../color.h"
+
+static int ui_browser__percent_color(struct ui_browser *browser,
+				     double percent, bool current)
+{
+	if (current && (!browser->use_navkeypressed || browser->navkeypressed))
+		return HE_COLORSET_SELECTED;
+	if (percent >= MIN_RED)
+		return HE_COLORSET_TOP;
+	if (percent >= MIN_GREEN)
+		return HE_COLORSET_MEDIUM;
+	return HE_COLORSET_NORMAL;
+}
+
+int ui_browser__set_color(struct ui_browser *browser, int color)
+{
+	int ret = browser->current_color;
+	browser->current_color = color;
+	SLsmg_set_color(color);
+	return ret;
+}
+
+void ui_browser__set_percent_color(struct ui_browser *browser,
+				   double percent, bool current)
+{
+	 int color = ui_browser__percent_color(browser, percent, current);
+	 ui_browser__set_color(browser, color);
+}
+
+void ui_browser__gotorc(struct ui_browser *browser, int y, int x)
+{
+	SLsmg_gotorc(browser->y + y, browser->x + x);
+}
+
+static struct list_head *
+ui_browser__list_head_filter_entries(struct ui_browser *browser,
+				     struct list_head *pos)
+{
+	do {
+		if (!browser->filter || !browser->filter(browser, pos))
+			return pos;
+		pos = pos->next;
+	} while (pos != browser->entries);
+
+	return NULL;
+}
+
+static struct list_head *
+ui_browser__list_head_filter_prev_entries(struct ui_browser *browser,
+					  struct list_head *pos)
+{
+	do {
+		if (!browser->filter || !browser->filter(browser, pos))
+			return pos;
+		pos = pos->prev;
+	} while (pos != browser->entries);
+
+	return NULL;
+}
+
+void ui_browser__list_head_seek(struct ui_browser *browser, off_t offset, int whence)
+{
+	struct list_head *head = browser->entries;
+	struct list_head *pos;
+
+	if (browser->nr_entries == 0)
+		return;
+
+	switch (whence) {
+	case SEEK_SET:
+		pos = ui_browser__list_head_filter_entries(browser, head->next);
+		break;
+	case SEEK_CUR:
+		pos = browser->top;
+		break;
+	case SEEK_END:
+		pos = ui_browser__list_head_filter_prev_entries(browser, head->prev);
+		break;
+	default:
+		return;
+	}
+
+	assert(pos != NULL);
+
+	if (offset > 0) {
+		while (offset-- != 0)
+			pos = ui_browser__list_head_filter_entries(browser, pos->next);
+	} else {
+		while (offset++ != 0)
+			pos = ui_browser__list_head_filter_prev_entries(browser, pos->prev);
+	}
+
+	browser->top = pos;
+}
+
+void ui_browser__rb_tree_seek(struct ui_browser *browser, off_t offset, int whence)
+{
+	struct rb_root *root = browser->entries;
+	struct rb_node *nd;
+
+	switch (whence) {
+	case SEEK_SET:
+		nd = rb_first(root);
+		break;
+	case SEEK_CUR:
+		nd = browser->top;
+		break;
+	case SEEK_END:
+		nd = rb_last(root);
+		break;
+	default:
+		return;
+	}
+
+	if (offset > 0) {
+		while (offset-- != 0)
+			nd = rb_next(nd);
+	} else {
+		while (offset++ != 0)
+			nd = rb_prev(nd);
+	}
+
+	browser->top = nd;
+}
+
+unsigned int ui_browser__rb_tree_refresh(struct ui_browser *browser)
+{
+	struct rb_node *nd;
+	int row = 0;
+
+	if (browser->top == NULL)
+                browser->top = rb_first(browser->entries);
+
+	nd = browser->top;
+
+	while (nd != NULL) {
+		ui_browser__gotorc(browser, row, 0);
+		browser->write(browser, nd, row);
+		if (++row == browser->height)
+			break;
+		nd = rb_next(nd);
+	}
+
+	return row;
+}
+
+bool ui_browser__is_current_entry(struct ui_browser *browser, unsigned row)
+{
+	return browser->top_idx + row == browser->index;
+}
+
+void ui_browser__refresh_dimensions(struct ui_browser *browser)
+{
+	browser->width = SLtt_Screen_Cols - 1;
+	browser->height = SLtt_Screen_Rows - 2;
+	browser->y = 1;
+	browser->x = 0;
+}
+
+void ui_browser__handle_resize(struct ui_browser *browser)
+{
+	ui__refresh_dimensions(false);
+	ui_browser__show(browser, browser->title, ui_helpline__current);
+	ui_browser__refresh(browser);
+}
+
+int ui_browser__warning(struct ui_browser *browser, int timeout,
+			const char *format, ...)
+{
+	va_list args;
+	char *text;
+	int key = 0, err;
+
+	va_start(args, format);
+	err = vasprintf(&text, format, args);
+	va_end(args);
+
+	if (err < 0) {
+		va_start(args, format);
+		ui_helpline__vpush(format, args);
+		va_end(args);
+	} else {
+		while ((key = ui__question_window("Warning!", text,
+						   "Press any key...",
+						   timeout)) == K_RESIZE)
+			ui_browser__handle_resize(browser);
+		free(text);
+	}
+
+	return key;
+}
+
+int ui_browser__help_window(struct ui_browser *browser, const char *text)
+{
+	int key;
+
+	while ((key = ui__help_window(text)) == K_RESIZE)
+		ui_browser__handle_resize(browser);
+
+	return key;
+}
+
+bool ui_browser__dialog_yesno(struct ui_browser *browser, const char *text)
+{
+	int key;
+
+	while ((key = ui__dialog_yesno(text)) == K_RESIZE)
+		ui_browser__handle_resize(browser);
+
+	return key == K_ENTER || toupper(key) == 'Y';
+}
+
+void ui_browser__reset_index(struct ui_browser *browser)
+{
+	browser->index = browser->top_idx = 0;
+	browser->seek(browser, 0, SEEK_SET);
+}
+
+void __ui_browser__show_title(struct ui_browser *browser, const char *title)
+{
+	SLsmg_gotorc(0, 0);
+	ui_browser__set_color(browser, HE_COLORSET_ROOT);
+	slsmg_write_nstring(title, browser->width + 1);
+}
+
+void ui_browser__show_title(struct ui_browser *browser, const char *title)
+{
+	pthread_mutex_lock(&ui__lock);
+	__ui_browser__show_title(browser, title);
+	pthread_mutex_unlock(&ui__lock);
+}
+
+int ui_browser__show(struct ui_browser *browser, const char *title,
+		     const char *helpline, ...)
+{
+	int err;
+	va_list ap;
+
+	ui_browser__refresh_dimensions(browser);
+
+	pthread_mutex_lock(&ui__lock);
+	__ui_browser__show_title(browser, title);
+
+	browser->title = title;
+	zfree(&browser->helpline);
+
+	va_start(ap, helpline);
+	err = vasprintf(&browser->helpline, helpline, ap);
+	va_end(ap);
+	if (err > 0)
+		ui_helpline__push(browser->helpline);
+	pthread_mutex_unlock(&ui__lock);
+	return err ? 0 : -1;
+}
+
+void ui_browser__hide(struct ui_browser *browser)
+{
+	pthread_mutex_lock(&ui__lock);
+	ui_helpline__pop();
+	zfree(&browser->helpline);
+	pthread_mutex_unlock(&ui__lock);
+}
+
+static void ui_browser__scrollbar_set(struct ui_browser *browser)
+{
+	int height = browser->height, h = 0, pct = 0,
+	    col = browser->width,
+	    row = browser->y - 1;
+
+	if (browser->nr_entries > 1) {
+		pct = ((browser->index * (browser->height - 1)) /
+		       (browser->nr_entries - 1));
+	}
+
+	SLsmg_set_char_set(1);
+
+	while (h < height) {
+	        ui_browser__gotorc(browser, row++, col);
+		SLsmg_write_char(h == pct ? SLSMG_DIAMOND_CHAR : SLSMG_CKBRD_CHAR);
+		++h;
+	}
+
+	SLsmg_set_char_set(0);
+}
+
+static int __ui_browser__refresh(struct ui_browser *browser)
+{
+	int row;
+	int width = browser->width;
+
+	row = browser->refresh(browser);
+	ui_browser__set_color(browser, HE_COLORSET_NORMAL);
+
+	if (!browser->use_navkeypressed || browser->navkeypressed)
+		ui_browser__scrollbar_set(browser);
+	else
+		width += 1;
+
+	SLsmg_fill_region(browser->y + row, browser->x,
+			  browser->height - row, width, ' ');
+
+	return 0;
+}
+
+int ui_browser__refresh(struct ui_browser *browser)
+{
+	pthread_mutex_lock(&ui__lock);
+	__ui_browser__refresh(browser);
+	pthread_mutex_unlock(&ui__lock);
+
+	return 0;
+}
+
+/*
+ * Here we're updating nr_entries _after_ we started browsing, i.e.  we have to
+ * forget about any reference to any entry in the underlying data structure,
+ * that is why we do a SEEK_SET. Think about 'perf top' in the hists browser
+ * after an output_resort and hist decay.
+ */
+void ui_browser__update_nr_entries(struct ui_browser *browser, u32 nr_entries)
+{
+	off_t offset = nr_entries - browser->nr_entries;
+
+	browser->nr_entries = nr_entries;
+
+	if (offset < 0) {
+		if (browser->top_idx < (u64)-offset)
+			offset = -browser->top_idx;
+
+		browser->index += offset;
+		browser->top_idx += offset;
+	}
+
+	browser->top = NULL;
+	browser->seek(browser, browser->top_idx, SEEK_SET);
+}
+
+int ui_browser__run(struct ui_browser *browser, int delay_secs)
+{
+	int err, key;
+
+	while (1) {
+		off_t offset;
+
+		pthread_mutex_lock(&ui__lock);
+		err = __ui_browser__refresh(browser);
+		SLsmg_refresh();
+		pthread_mutex_unlock(&ui__lock);
+		if (err < 0)
+			break;
+
+		key = ui__getch(delay_secs);
+
+		if (key == K_RESIZE) {
+			ui__refresh_dimensions(false);
+			ui_browser__refresh_dimensions(browser);
+			__ui_browser__show_title(browser, browser->title);
+			ui_helpline__puts(browser->helpline);
+			continue;
+		}
+
+		if (browser->use_navkeypressed && !browser->navkeypressed) {
+			if (key == K_DOWN || key == K_UP ||
+			    key == K_PGDN || key == K_PGUP ||
+			    key == K_HOME || key == K_END ||
+			    key == ' ') {
+				browser->navkeypressed = true;
+				continue;
+			} else
+				return key;
+		}
+
+		switch (key) {
+		case K_DOWN:
+			if (browser->index == browser->nr_entries - 1)
+				break;
+			++browser->index;
+			if (browser->index == browser->top_idx + browser->height) {
+				++browser->top_idx;
+				browser->seek(browser, +1, SEEK_CUR);
+			}
+			break;
+		case K_UP:
+			if (browser->index == 0)
+				break;
+			--browser->index;
+			if (browser->index < browser->top_idx) {
+				--browser->top_idx;
+				browser->seek(browser, -1, SEEK_CUR);
+			}
+			break;
+		case K_PGDN:
+		case ' ':
+			if (browser->top_idx + browser->height > browser->nr_entries - 1)
+				break;
+
+			offset = browser->height;
+			if (browser->index + offset > browser->nr_entries - 1)
+				offset = browser->nr_entries - 1 - browser->index;
+			browser->index += offset;
+			browser->top_idx += offset;
+			browser->seek(browser, +offset, SEEK_CUR);
+			break;
+		case K_PGUP:
+			if (browser->top_idx == 0)
+				break;
+
+			if (browser->top_idx < browser->height)
+				offset = browser->top_idx;
+			else
+				offset = browser->height;
+
+			browser->index -= offset;
+			browser->top_idx -= offset;
+			browser->seek(browser, -offset, SEEK_CUR);
+			break;
+		case K_HOME:
+			ui_browser__reset_index(browser);
+			break;
+		case K_END:
+			offset = browser->height - 1;
+			if (offset >= browser->nr_entries)
+				offset = browser->nr_entries - 1;
+
+			browser->index = browser->nr_entries - 1;
+			browser->top_idx = browser->index - offset;
+			browser->seek(browser, -offset, SEEK_END);
+			break;
+		default:
+			return key;
+		}
+	}
+	return -1;
+}
+
+unsigned int ui_browser__list_head_refresh(struct ui_browser *browser)
+{
+	struct list_head *pos;
+	struct list_head *head = browser->entries;
+	int row = 0;
+
+	if (browser->top == NULL || browser->top == browser->entries)
+                browser->top = ui_browser__list_head_filter_entries(browser, head->next);
+
+	pos = browser->top;
+
+	list_for_each_from(pos, head) {
+		if (!browser->filter || !browser->filter(browser, pos)) {
+			ui_browser__gotorc(browser, row, 0);
+			browser->write(browser, pos, row);
+			if (++row == browser->height)
+				break;
+		}
+	}
+
+	return row;
+}
+
+static struct ui_browser_colorset {
+	const char *name, *fg, *bg;
+	int colorset;
+} ui_browser__colorsets[] = {
+	{
+		.colorset = HE_COLORSET_TOP,
+		.name	  = "top",
+		.fg	  = "red",
+		.bg	  = "default",
+	},
+	{
+		.colorset = HE_COLORSET_MEDIUM,
+		.name	  = "medium",
+		.fg	  = "green",
+		.bg	  = "default",
+	},
+	{
+		.colorset = HE_COLORSET_NORMAL,
+		.name	  = "normal",
+		.fg	  = "default",
+		.bg	  = "default",
+	},
+	{
+		.colorset = HE_COLORSET_SELECTED,
+		.name	  = "selected",
+		.fg	  = "black",
+		.bg	  = "lightgray",
+	},
+	{
+		.colorset = HE_COLORSET_CODE,
+		.name	  = "code",
+		.fg	  = "blue",
+		.bg	  = "default",
+	},
+	{
+		.colorset = HE_COLORSET_ADDR,
+		.name	  = "addr",
+		.fg	  = "magenta",
+		.bg	  = "default",
+	},
+	{
+		.colorset = HE_COLORSET_ROOT,
+		.name	  = "root",
+		.fg	  = "white",
+		.bg	  = "blue",
+	},
+	{
+		.name = NULL,
+	}
+};
+
+
+static int ui_browser__color_config(const char *var, const char *value,
+				    void *data __maybe_unused)
+{
+	char *fg = NULL, *bg;
+	int i;
+
+	/* same dir for all commands */
+	if (prefixcmp(var, "colors.") != 0)
+		return 0;
+
+	for (i = 0; ui_browser__colorsets[i].name != NULL; ++i) {
+		const char *name = var + 7;
+
+		if (strcmp(ui_browser__colorsets[i].name, name) != 0)
+			continue;
+
+		fg = strdup(value);
+		if (fg == NULL)
+			break;
+
+		bg = strchr(fg, ',');
+		if (bg == NULL)
+			break;
+
+		*bg = '\0';
+		while (isspace(*++bg));
+		ui_browser__colorsets[i].bg = bg;
+		ui_browser__colorsets[i].fg = fg;
+		return 0;
+	}
+
+	free(fg);
+	return -1;
+}
+
+void ui_browser__argv_seek(struct ui_browser *browser, off_t offset, int whence)
+{
+	switch (whence) {
+	case SEEK_SET:
+		browser->top = browser->entries;
+		break;
+	case SEEK_CUR:
+		browser->top = browser->top + browser->top_idx + offset;
+		break;
+	case SEEK_END:
+		browser->top = browser->top + browser->nr_entries - 1 + offset;
+		break;
+	default:
+		return;
+	}
+}
+
+unsigned int ui_browser__argv_refresh(struct ui_browser *browser)
+{
+	unsigned int row = 0, idx = browser->top_idx;
+	char **pos;
+
+	if (browser->top == NULL)
+		browser->top = browser->entries;
+
+	pos = (char **)browser->top;
+	while (idx < browser->nr_entries) {
+		if (!browser->filter || !browser->filter(browser, *pos)) {
+			ui_browser__gotorc(browser, row, 0);
+			browser->write(browser, pos, row);
+			if (++row == browser->height)
+				break;
+		}
+
+		++idx;
+		++pos;
+	}
+
+	return row;
+}
+
+void __ui_browser__vline(struct ui_browser *browser, unsigned int column,
+			 u16 start, u16 end)
+{
+	SLsmg_set_char_set(1);
+	ui_browser__gotorc(browser, start, column);
+	SLsmg_draw_vline(end - start + 1);
+	SLsmg_set_char_set(0);
+}
+
+void ui_browser__write_graph(struct ui_browser *browser __maybe_unused,
+			     int graph)
+{
+	SLsmg_set_char_set(1);
+	SLsmg_write_char(graph);
+	SLsmg_set_char_set(0);
+}
+
+static void __ui_browser__line_arrow_up(struct ui_browser *browser,
+					unsigned int column,
+					u64 start, u64 end)
+{
+	unsigned int row, end_row;
+
+	SLsmg_set_char_set(1);
+
+	if (start < browser->top_idx + browser->height) {
+		row = start - browser->top_idx;
+		ui_browser__gotorc(browser, row, column);
+		SLsmg_write_char(SLSMG_LLCORN_CHAR);
+		ui_browser__gotorc(browser, row, column + 1);
+		SLsmg_draw_hline(2);
+
+		if (row-- == 0)
+			goto out;
+	} else
+		row = browser->height - 1;
+
+	if (end > browser->top_idx)
+		end_row = end - browser->top_idx;
+	else
+		end_row = 0;
+
+	ui_browser__gotorc(browser, end_row, column);
+	SLsmg_draw_vline(row - end_row + 1);
+
+	ui_browser__gotorc(browser, end_row, column);
+	if (end >= browser->top_idx) {
+		SLsmg_write_char(SLSMG_ULCORN_CHAR);
+		ui_browser__gotorc(browser, end_row, column + 1);
+		SLsmg_write_char(SLSMG_HLINE_CHAR);
+		ui_browser__gotorc(browser, end_row, column + 2);
+		SLsmg_write_char(SLSMG_RARROW_CHAR);
+	}
+out:
+	SLsmg_set_char_set(0);
+}
+
+static void __ui_browser__line_arrow_down(struct ui_browser *browser,
+					  unsigned int column,
+					  u64 start, u64 end)
+{
+	unsigned int row, end_row;
+
+	SLsmg_set_char_set(1);
+
+	if (start >= browser->top_idx) {
+		row = start - browser->top_idx;
+		ui_browser__gotorc(browser, row, column);
+		SLsmg_write_char(SLSMG_ULCORN_CHAR);
+		ui_browser__gotorc(browser, row, column + 1);
+		SLsmg_draw_hline(2);
+
+		if (row++ == 0)
+			goto out;
+	} else
+		row = 0;
+
+	if (end >= browser->top_idx + browser->height)
+		end_row = browser->height - 1;
+	else
+		end_row = end - browser->top_idx;
+
+	ui_browser__gotorc(browser, row, column);
+	SLsmg_draw_vline(end_row - row + 1);
+
+	ui_browser__gotorc(browser, end_row, column);
+	if (end < browser->top_idx + browser->height) {
+		SLsmg_write_char(SLSMG_LLCORN_CHAR);
+		ui_browser__gotorc(browser, end_row, column + 1);
+		SLsmg_write_char(SLSMG_HLINE_CHAR);
+		ui_browser__gotorc(browser, end_row, column + 2);
+		SLsmg_write_char(SLSMG_RARROW_CHAR);
+	}
+out:
+	SLsmg_set_char_set(0);
+}
+
+void __ui_browser__line_arrow(struct ui_browser *browser, unsigned int column,
+			      u64 start, u64 end)
+{
+	if (start > end)
+		__ui_browser__line_arrow_up(browser, column, start, end);
+	else
+		__ui_browser__line_arrow_down(browser, column, start, end);
+}
+
+void ui_browser__init(void)
+{
+	int i = 0;
+
+	perf_config(ui_browser__color_config, NULL);
+
+	while (ui_browser__colorsets[i].name) {
+		struct ui_browser_colorset *c = &ui_browser__colorsets[i++];
+		sltt_set_color(c->colorset, c->name, c->fg, c->bg);
+	}
+
+	annotate_browser__init();
+}
diff --git a/tools/perf/ui/browser.h b/tools/perf/ui/browser.h
new file mode 100644
index 00000000000..03d4d6295f1
--- /dev/null
+++ b/tools/perf/ui/browser.h
@@ -0,0 +1,74 @@
+#ifndef _PERF_UI_BROWSER_H_
+#define _PERF_UI_BROWSER_H_ 1
+
+#include <linux/types.h>
+
+#define HE_COLORSET_TOP		50
+#define HE_COLORSET_MEDIUM	51
+#define HE_COLORSET_NORMAL	52
+#define HE_COLORSET_SELECTED	53
+#define HE_COLORSET_CODE	54
+#define HE_COLORSET_ADDR	55
+#define HE_COLORSET_ROOT	56
+
+struct ui_browser {
+	u64	      index, top_idx;
+	void	      *top, *entries;
+	u16	      y, x, width, height;
+	int	      current_color;
+	void	      *priv;
+	const char    *title;
+	char	      *helpline;
+	unsigned int  (*refresh)(struct ui_browser *browser);
+	void	      (*write)(struct ui_browser *browser, void *entry, int row);
+	void	      (*seek)(struct ui_browser *browser, off_t offset, int whence);
+	bool	      (*filter)(struct ui_browser *browser, void *entry);
+	u32	      nr_entries;
+	bool	      navkeypressed;
+	bool	      use_navkeypressed;
+};
+
+int  ui_browser__set_color(struct ui_browser *browser, int color);
+void ui_browser__set_percent_color(struct ui_browser *browser,
+				   double percent, bool current);
+bool ui_browser__is_current_entry(struct ui_browser *browser, unsigned row);
+void ui_browser__refresh_dimensions(struct ui_browser *browser);
+void ui_browser__reset_index(struct ui_browser *browser);
+
+void ui_browser__gotorc(struct ui_browser *browser, int y, int x);
+void ui_browser__write_graph(struct ui_browser *browser, int graph);
+void __ui_browser__line_arrow(struct ui_browser *browser, unsigned int column,
+			      u64 start, u64 end);
+void __ui_browser__show_title(struct ui_browser *browser, const char *title);
+void ui_browser__show_title(struct ui_browser *browser, const char *title);
+int ui_browser__show(struct ui_browser *browser, const char *title,
+		     const char *helpline, ...);
+void ui_browser__hide(struct ui_browser *browser);
+int ui_browser__refresh(struct ui_browser *browser);
+int ui_browser__run(struct ui_browser *browser, int delay_secs);
+void ui_browser__update_nr_entries(struct ui_browser *browser, u32 nr_entries);
+void ui_browser__handle_resize(struct ui_browser *browser);
+void __ui_browser__vline(struct ui_browser *browser, unsigned int column,
+			 u16 start, u16 end);
+
+int ui_browser__warning(struct ui_browser *browser, int timeout,
+			const char *format, ...);
+int ui_browser__help_window(struct ui_browser *browser, const char *text);
+bool ui_browser__dialog_yesno(struct ui_browser *browser, const char *text);
+int ui_browser__input_window(const char *title, const char *text, char *input,
+			     const char *exit_msg, int delay_sec);
+struct perf_session_env;
+int tui__header_window(struct perf_session_env *env);
+
+void ui_browser__argv_seek(struct ui_browser *browser, off_t offset, int whence);
+unsigned int ui_browser__argv_refresh(struct ui_browser *browser);
+
+void ui_browser__rb_tree_seek(struct ui_browser *browser, off_t offset, int whence);
+unsigned int ui_browser__rb_tree_refresh(struct ui_browser *browser);
+
+void ui_browser__list_head_seek(struct ui_browser *browser, off_t offset, int whence);
+unsigned int ui_browser__list_head_refresh(struct ui_browser *browser);
+
+void ui_browser__init(void);
+void annotate_browser__init(void);
+#endif /* _PERF_UI_BROWSER_H_ */
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
new file mode 100644
index 00000000000..f0697a3aede
--- /dev/null
+++ b/tools/perf/ui/browsers/annotate.c
@@ -0,0 +1,1023 @@
+#include "../../util/util.h"
+#include "../browser.h"
+#include "../helpline.h"
+#include "../libslang.h"
+#include "../ui.h"
+#include "../util.h"
+#include "../../util/annotate.h"
+#include "../../util/hist.h"
+#include "../../util/sort.h"
+#include "../../util/symbol.h"
+#include "../../util/evsel.h"
+#include <pthread.h>
+
+struct browser_disasm_line {
+	struct rb_node	rb_node;
+	u32		idx;
+	int		idx_asm;
+	int		jump_sources;
+	/*
+	 * actual length of this array is saved on the nr_events field
+	 * of the struct annotate_browser
+	 */
+	double		percent[1];
+};
+
+static struct annotate_browser_opt {
+	bool hide_src_code,
+	     use_offset,
+	     jump_arrows,
+	     show_nr_jumps;
+} annotate_browser__opts = {
+	.use_offset	= true,
+	.jump_arrows	= true,
+};
+
+struct annotate_browser {
+	struct ui_browser b;
+	struct rb_root	  entries;
+	struct rb_node	  *curr_hot;
+	struct disasm_line  *selection;
+	struct disasm_line  **offsets;
+	int		    nr_events;
+	u64		    start;
+	int		    nr_asm_entries;
+	int		    nr_entries;
+	int		    max_jump_sources;
+	int		    nr_jumps;
+	bool		    searching_backwards;
+	u8		    addr_width;
+	u8		    jumps_width;
+	u8		    target_width;
+	u8		    min_addr_width;
+	u8		    max_addr_width;
+	char		    search_bf[128];
+};
+
+static inline struct browser_disasm_line *disasm_line__browser(struct disasm_line *dl)
+{
+	return (struct browser_disasm_line *)(dl + 1);
+}
+
+static bool disasm_line__filter(struct ui_browser *browser __maybe_unused,
+				void *entry)
+{
+	if (annotate_browser__opts.hide_src_code) {
+		struct disasm_line *dl = list_entry(entry, struct disasm_line, node);
+		return dl->offset == -1;
+	}
+
+	return false;
+}
+
+static int annotate_browser__jumps_percent_color(struct annotate_browser *browser,
+						 int nr, bool current)
+{
+	if (current && (!browser->b.use_navkeypressed || browser->b.navkeypressed))
+		return HE_COLORSET_SELECTED;
+	if (nr == browser->max_jump_sources)
+		return HE_COLORSET_TOP;
+	if (nr > 1)
+		return HE_COLORSET_MEDIUM;
+	return HE_COLORSET_NORMAL;
+}
+
+static int annotate_browser__set_jumps_percent_color(struct annotate_browser *browser,
+						     int nr, bool current)
+{
+	 int color = annotate_browser__jumps_percent_color(browser, nr, current);
+	 return ui_browser__set_color(&browser->b, color);
+}
+
+static void annotate_browser__write(struct ui_browser *browser, void *entry, int row)
+{
+	struct annotate_browser *ab = container_of(browser, struct annotate_browser, b);
+	struct disasm_line *dl = list_entry(entry, struct disasm_line, node);
+	struct browser_disasm_line *bdl = disasm_line__browser(dl);
+	bool current_entry = ui_browser__is_current_entry(browser, row);
+	bool change_color = (!annotate_browser__opts.hide_src_code &&
+			     (!current_entry || (browser->use_navkeypressed &&
+					         !browser->navkeypressed)));
+	int width = browser->width, printed;
+	int i, pcnt_width = 7 * ab->nr_events;
+	double percent_max = 0.0;
+	char bf[256];
+
+	for (i = 0; i < ab->nr_events; i++) {
+		if (bdl->percent[i] > percent_max)
+			percent_max = bdl->percent[i];
+	}
+
+	if (dl->offset != -1 && percent_max != 0.0) {
+		for (i = 0; i < ab->nr_events; i++) {
+			ui_browser__set_percent_color(browser, bdl->percent[i],
+						      current_entry);
+			slsmg_printf("%6.2f ", bdl->percent[i]);
+		}
+	} else {
+		ui_browser__set_percent_color(browser, 0, current_entry);
+		slsmg_write_nstring(" ", pcnt_width);
+	}
+
+	SLsmg_write_char(' ');
+
+	/* The scroll bar isn't being used */
+	if (!browser->navkeypressed)
+		width += 1;
+
+	if (!*dl->line)
+		slsmg_write_nstring(" ", width - pcnt_width);
+	else if (dl->offset == -1) {
+		printed = scnprintf(bf, sizeof(bf), "%*s  ",
+				    ab->addr_width, " ");
+		slsmg_write_nstring(bf, printed);
+		slsmg_write_nstring(dl->line, width - printed - pcnt_width + 1);
+	} else {
+		u64 addr = dl->offset;
+		int color = -1;
+
+		if (!annotate_browser__opts.use_offset)
+			addr += ab->start;
+
+		if (!annotate_browser__opts.use_offset) {
+			printed = scnprintf(bf, sizeof(bf), "%" PRIx64 ": ", addr);
+		} else {
+			if (bdl->jump_sources) {
+				if (annotate_browser__opts.show_nr_jumps) {
+					int prev;
+					printed = scnprintf(bf, sizeof(bf), "%*d ",
+							    ab->jumps_width,
+							    bdl->jump_sources);
+					prev = annotate_browser__set_jumps_percent_color(ab, bdl->jump_sources,
+											 current_entry);
+					slsmg_write_nstring(bf, printed);
+					ui_browser__set_color(browser, prev);
+				}
+
+				printed = scnprintf(bf, sizeof(bf), "%*" PRIx64 ": ",
+						    ab->target_width, addr);
+			} else {
+				printed = scnprintf(bf, sizeof(bf), "%*s  ",
+						    ab->addr_width, " ");
+			}
+		}
+
+		if (change_color)
+			color = ui_browser__set_color(browser, HE_COLORSET_ADDR);
+		slsmg_write_nstring(bf, printed);
+		if (change_color)
+			ui_browser__set_color(browser, color);
+		if (dl->ins && dl->ins->ops->scnprintf) {
+			if (ins__is_jump(dl->ins)) {
+				bool fwd = dl->ops.target.offset > (u64)dl->offset;
+
+				ui_browser__write_graph(browser, fwd ? SLSMG_DARROW_CHAR :
+								    SLSMG_UARROW_CHAR);
+				SLsmg_write_char(' ');
+			} else if (ins__is_call(dl->ins)) {
+				ui_browser__write_graph(browser, SLSMG_RARROW_CHAR);
+				SLsmg_write_char(' ');
+			} else {
+				slsmg_write_nstring(" ", 2);
+			}
+		} else {
+			if (strcmp(dl->name, "retq")) {
+				slsmg_write_nstring(" ", 2);
+			} else {
+				ui_browser__write_graph(browser, SLSMG_LARROW_CHAR);
+				SLsmg_write_char(' ');
+			}
+		}
+
+		disasm_line__scnprintf(dl, bf, sizeof(bf), !annotate_browser__opts.use_offset);
+		slsmg_write_nstring(bf, width - pcnt_width - 3 - printed);
+	}
+
+	if (current_entry)
+		ab->selection = dl;
+}
+
+static bool disasm_line__is_valid_jump(struct disasm_line *dl, struct symbol *sym)
+{
+	if (!dl || !dl->ins || !ins__is_jump(dl->ins)
+	    || !disasm_line__has_offset(dl)
+	    || dl->ops.target.offset >= symbol__size(sym))
+		return false;
+
+	return true;
+}
+
+static void annotate_browser__draw_current_jump(struct ui_browser *browser)
+{
+	struct annotate_browser *ab = container_of(browser, struct annotate_browser, b);
+	struct disasm_line *cursor = ab->selection, *target;
+	struct browser_disasm_line *btarget, *bcursor;
+	unsigned int from, to;
+	struct map_symbol *ms = ab->b.priv;
+	struct symbol *sym = ms->sym;
+	u8 pcnt_width = 7;
+
+	/* PLT symbols contain external offsets */
+	if (strstr(sym->name, "@plt"))
+		return;
+
+	if (!disasm_line__is_valid_jump(cursor, sym))
+		return;
+
+	target = ab->offsets[cursor->ops.target.offset];
+	if (!target)
+		return;
+
+	bcursor = disasm_line__browser(cursor);
+	btarget = disasm_line__browser(target);
+
+	if (annotate_browser__opts.hide_src_code) {
+		from = bcursor->idx_asm;
+		to = btarget->idx_asm;
+	} else {
+		from = (u64)bcursor->idx;
+		to = (u64)btarget->idx;
+	}
+
+	pcnt_width *= ab->nr_events;
+
+	ui_browser__set_color(browser, HE_COLORSET_CODE);
+	__ui_browser__line_arrow(browser, pcnt_width + 2 + ab->addr_width,
+				 from, to);
+}
+
+static unsigned int annotate_browser__refresh(struct ui_browser *browser)
+{
+	struct annotate_browser *ab = container_of(browser, struct annotate_browser, b);
+	int ret = ui_browser__list_head_refresh(browser);
+	int pcnt_width;
+
+	pcnt_width = 7 * ab->nr_events;
+
+	if (annotate_browser__opts.jump_arrows)
+		annotate_browser__draw_current_jump(browser);
+
+	ui_browser__set_color(browser, HE_COLORSET_NORMAL);
+	__ui_browser__vline(browser, pcnt_width, 0, browser->height - 1);
+	return ret;
+}
+
+static int disasm__cmp(struct browser_disasm_line *a,
+		       struct browser_disasm_line *b, int nr_pcnt)
+{
+	int i;
+
+	for (i = 0; i < nr_pcnt; i++) {
+		if (a->percent[i] == b->percent[i])
+			continue;
+		return a->percent[i] < b->percent[i];
+	}
+	return 0;
+}
+
+static void disasm_rb_tree__insert(struct rb_root *root, struct browser_disasm_line *bdl,
+				   int nr_events)
+{
+	struct rb_node **p = &root->rb_node;
+	struct rb_node *parent = NULL;
+	struct browser_disasm_line *l;
+
+	while (*p != NULL) {
+		parent = *p;
+		l = rb_entry(parent, struct browser_disasm_line, rb_node);
+
+		if (disasm__cmp(bdl, l, nr_events))
+			p = &(*p)->rb_left;
+		else
+			p = &(*p)->rb_right;
+	}
+	rb_link_node(&bdl->rb_node, parent, p);
+	rb_insert_color(&bdl->rb_node, root);
+}
+
+static void annotate_browser__set_top(struct annotate_browser *browser,
+				      struct disasm_line *pos, u32 idx)
+{
+	unsigned back;
+
+	ui_browser__refresh_dimensions(&browser->b);
+	back = browser->b.height / 2;
+	browser->b.top_idx = browser->b.index = idx;
+
+	while (browser->b.top_idx != 0 && back != 0) {
+		pos = list_entry(pos->node.prev, struct disasm_line, node);
+
+		if (disasm_line__filter(&browser->b, &pos->node))
+			continue;
+
+		--browser->b.top_idx;
+		--back;
+	}
+
+	browser->b.top = pos;
+	browser->b.navkeypressed = true;
+}
+
+static void annotate_browser__set_rb_top(struct annotate_browser *browser,
+					 struct rb_node *nd)
+{
+	struct browser_disasm_line *bpos;
+	struct disasm_line *pos;
+	u32 idx;
+
+	bpos = rb_entry(nd, struct browser_disasm_line, rb_node);
+	pos = ((struct disasm_line *)bpos) - 1;
+	idx = bpos->idx;
+	if (annotate_browser__opts.hide_src_code)
+		idx = bpos->idx_asm;
+	annotate_browser__set_top(browser, pos, idx);
+	browser->curr_hot = nd;
+}
+
+static void annotate_browser__calc_percent(struct annotate_browser *browser,
+					   struct perf_evsel *evsel)
+{
+	struct map_symbol *ms = browser->b.priv;
+	struct symbol *sym = ms->sym;
+	struct annotation *notes = symbol__annotation(sym);
+	struct disasm_line *pos, *next;
+	s64 len = symbol__size(sym);
+
+	browser->entries = RB_ROOT;
+
+	pthread_mutex_lock(&notes->lock);
+
+	list_for_each_entry(pos, &notes->src->source, node) {
+		struct browser_disasm_line *bpos = disasm_line__browser(pos);
+		const char *path = NULL;
+		double max_percent = 0.0;
+		int i;
+
+		if (pos->offset == -1) {
+			RB_CLEAR_NODE(&bpos->rb_node);
+			continue;
+		}
+
+		next = disasm__get_next_ip_line(&notes->src->source, pos);
+
+		for (i = 0; i < browser->nr_events; i++) {
+			bpos->percent[i] = disasm__calc_percent(notes,
+						evsel->idx + i,
+						pos->offset,
+						next ? next->offset : len,
+					        &path);
+
+			if (max_percent < bpos->percent[i])
+				max_percent = bpos->percent[i];
+		}
+
+		if (max_percent < 0.01) {
+			RB_CLEAR_NODE(&bpos->rb_node);
+			continue;
+		}
+		disasm_rb_tree__insert(&browser->entries, bpos,
+				       browser->nr_events);
+	}
+	pthread_mutex_unlock(&notes->lock);
+
+	browser->curr_hot = rb_last(&browser->entries);
+}
+
+static bool annotate_browser__toggle_source(struct annotate_browser *browser)
+{
+	struct disasm_line *dl;
+	struct browser_disasm_line *bdl;
+	off_t offset = browser->b.index - browser->b.top_idx;
+
+	browser->b.seek(&browser->b, offset, SEEK_CUR);
+	dl = list_entry(browser->b.top, struct disasm_line, node);
+	bdl = disasm_line__browser(dl);
+
+	if (annotate_browser__opts.hide_src_code) {
+		if (bdl->idx_asm < offset)
+			offset = bdl->idx;
+
+		browser->b.nr_entries = browser->nr_entries;
+		annotate_browser__opts.hide_src_code = false;
+		browser->b.seek(&browser->b, -offset, SEEK_CUR);
+		browser->b.top_idx = bdl->idx - offset;
+		browser->b.index = bdl->idx;
+	} else {
+		if (bdl->idx_asm < 0) {
+			ui_helpline__puts("Only available for assembly lines.");
+			browser->b.seek(&browser->b, -offset, SEEK_CUR);
+			return false;
+		}
+
+		if (bdl->idx_asm < offset)
+			offset = bdl->idx_asm;
+
+		browser->b.nr_entries = browser->nr_asm_entries;
+		annotate_browser__opts.hide_src_code = true;
+		browser->b.seek(&browser->b, -offset, SEEK_CUR);
+		browser->b.top_idx = bdl->idx_asm - offset;
+		browser->b.index = bdl->idx_asm;
+	}
+
+	return true;
+}
+
+static void annotate_browser__init_asm_mode(struct annotate_browser *browser)
+{
+	ui_browser__reset_index(&browser->b);
+	browser->b.nr_entries = browser->nr_asm_entries;
+}
+
+#define SYM_TITLE_MAX_SIZE (PATH_MAX + 64)
+
+static int sym_title(struct symbol *sym, struct map *map, char *title,
+		     size_t sz)
+{
+	return snprintf(title, sz, "%s  %s", sym->name, map->dso->long_name);
+}
+
+static bool annotate_browser__callq(struct annotate_browser *browser,
+				    struct perf_evsel *evsel,
+				    struct hist_browser_timer *hbt)
+{
+	struct map_symbol *ms = browser->b.priv;
+	struct disasm_line *dl = browser->selection;
+	struct annotation *notes;
+	struct addr_map_symbol target = {
+		.map = ms->map,
+		.addr = map__objdump_2mem(ms->map, dl->ops.target.addr),
+	};
+	char title[SYM_TITLE_MAX_SIZE];
+
+	if (!ins__is_call(dl->ins))
+		return false;
+
+	if (map_groups__find_ams(&target, NULL) ||
+	    map__rip_2objdump(target.map, target.map->map_ip(target.map,
+							     target.addr)) !=
+	    dl->ops.target.addr) {
+		ui_helpline__puts("The called function was not found.");
+		return true;
+	}
+
+	notes = symbol__annotation(target.sym);
+	pthread_mutex_lock(&notes->lock);
+
+	if (notes->src == NULL && symbol__alloc_hist(target.sym) < 0) {
+		pthread_mutex_unlock(&notes->lock);
+		ui__warning("Not enough memory for annotating '%s' symbol!\n",
+			    target.sym->name);
+		return true;
+	}
+
+	pthread_mutex_unlock(&notes->lock);
+	symbol__tui_annotate(target.sym, target.map, evsel, hbt);
+	sym_title(ms->sym, ms->map, title, sizeof(title));
+	ui_browser__show_title(&browser->b, title);
+	return true;
+}
+
+static
+struct disasm_line *annotate_browser__find_offset(struct annotate_browser *browser,
+					  s64 offset, s64 *idx)
+{
+	struct map_symbol *ms = browser->b.priv;
+	struct symbol *sym = ms->sym;
+	struct annotation *notes = symbol__annotation(sym);
+	struct disasm_line *pos;
+
+	*idx = 0;
+	list_for_each_entry(pos, &notes->src->source, node) {
+		if (pos->offset == offset)
+			return pos;
+		if (!disasm_line__filter(&browser->b, &pos->node))
+			++*idx;
+	}
+
+	return NULL;
+}
+
+static bool annotate_browser__jump(struct annotate_browser *browser)
+{
+	struct disasm_line *dl = browser->selection;
+	s64 idx;
+
+	if (!ins__is_jump(dl->ins))
+		return false;
+
+	dl = annotate_browser__find_offset(browser, dl->ops.target.offset, &idx);
+	if (dl == NULL) {
+		ui_helpline__puts("Invalid jump offset");
+		return true;
+	}
+
+	annotate_browser__set_top(browser, dl, idx);
+	
+	return true;
+}
+
+static
+struct disasm_line *annotate_browser__find_string(struct annotate_browser *browser,
+					  char *s, s64 *idx)
+{
+	struct map_symbol *ms = browser->b.priv;
+	struct symbol *sym = ms->sym;
+	struct annotation *notes = symbol__annotation(sym);
+	struct disasm_line *pos = browser->selection;
+
+	*idx = browser->b.index;
+	list_for_each_entry_continue(pos, &notes->src->source, node) {
+		if (disasm_line__filter(&browser->b, &pos->node))
+			continue;
+
+		++*idx;
+
+		if (pos->line && strstr(pos->line, s) != NULL)
+			return pos;
+	}
+
+	return NULL;
+}
+
+static bool __annotate_browser__search(struct annotate_browser *browser)
+{
+	struct disasm_line *dl;
+	s64 idx;
+
+	dl = annotate_browser__find_string(browser, browser->search_bf, &idx);
+	if (dl == NULL) {
+		ui_helpline__puts("String not found!");
+		return false;
+	}
+
+	annotate_browser__set_top(browser, dl, idx);
+	browser->searching_backwards = false;
+	return true;
+}
+
+static
+struct disasm_line *annotate_browser__find_string_reverse(struct annotate_browser *browser,
+						  char *s, s64 *idx)
+{
+	struct map_symbol *ms = browser->b.priv;
+	struct symbol *sym = ms->sym;
+	struct annotation *notes = symbol__annotation(sym);
+	struct disasm_line *pos = browser->selection;
+
+	*idx = browser->b.index;
+	list_for_each_entry_continue_reverse(pos, &notes->src->source, node) {
+		if (disasm_line__filter(&browser->b, &pos->node))
+			continue;
+
+		--*idx;
+
+		if (pos->line && strstr(pos->line, s) != NULL)
+			return pos;
+	}
+
+	return NULL;
+}
+
+static bool __annotate_browser__search_reverse(struct annotate_browser *browser)
+{
+	struct disasm_line *dl;
+	s64 idx;
+
+	dl = annotate_browser__find_string_reverse(browser, browser->search_bf, &idx);
+	if (dl == NULL) {
+		ui_helpline__puts("String not found!");
+		return false;
+	}
+
+	annotate_browser__set_top(browser, dl, idx);
+	browser->searching_backwards = true;
+	return true;
+}
+
+static bool annotate_browser__search_window(struct annotate_browser *browser,
+					    int delay_secs)
+{
+	if (ui_browser__input_window("Search", "String: ", browser->search_bf,
+				     "ENTER: OK, ESC: Cancel",
+				     delay_secs * 2) != K_ENTER ||
+	    !*browser->search_bf)
+		return false;
+
+	return true;
+}
+
+static bool annotate_browser__search(struct annotate_browser *browser, int delay_secs)
+{
+	if (annotate_browser__search_window(browser, delay_secs))
+		return __annotate_browser__search(browser);
+
+	return false;
+}
+
+static bool annotate_browser__continue_search(struct annotate_browser *browser,
+					      int delay_secs)
+{
+	if (!*browser->search_bf)
+		return annotate_browser__search(browser, delay_secs);
+
+	return __annotate_browser__search(browser);
+}
+
+static bool annotate_browser__search_reverse(struct annotate_browser *browser,
+					   int delay_secs)
+{
+	if (annotate_browser__search_window(browser, delay_secs))
+		return __annotate_browser__search_reverse(browser);
+
+	return false;
+}
+
+static
+bool annotate_browser__continue_search_reverse(struct annotate_browser *browser,
+					       int delay_secs)
+{
+	if (!*browser->search_bf)
+		return annotate_browser__search_reverse(browser, delay_secs);
+
+	return __annotate_browser__search_reverse(browser);
+}
+
+static void annotate_browser__update_addr_width(struct annotate_browser *browser)
+{
+	if (annotate_browser__opts.use_offset)
+		browser->target_width = browser->min_addr_width;
+	else
+		browser->target_width = browser->max_addr_width;
+
+	browser->addr_width = browser->target_width;
+
+	if (annotate_browser__opts.show_nr_jumps)
+		browser->addr_width += browser->jumps_width + 1;
+}
+
+static int annotate_browser__run(struct annotate_browser *browser,
+				 struct perf_evsel *evsel,
+				 struct hist_browser_timer *hbt)
+{
+	struct rb_node *nd = NULL;
+	struct map_symbol *ms = browser->b.priv;
+	struct symbol *sym = ms->sym;
+	const char *help = "Press 'h' for help on key bindings";
+	int delay_secs = hbt ? hbt->refresh : 0;
+	int key;
+	char title[SYM_TITLE_MAX_SIZE];
+
+	sym_title(sym, ms->map, title, sizeof(title));
+	if (ui_browser__show(&browser->b, title, help) < 0)
+		return -1;
+
+	annotate_browser__calc_percent(browser, evsel);
+
+	if (browser->curr_hot) {
+		annotate_browser__set_rb_top(browser, browser->curr_hot);
+		browser->b.navkeypressed = false;
+	}
+
+	nd = browser->curr_hot;
+
+	while (1) {
+		key = ui_browser__run(&browser->b, delay_secs);
+
+		if (delay_secs != 0) {
+			annotate_browser__calc_percent(browser, evsel);
+			/*
+			 * Current line focus got out of the list of most active
+			 * lines, NULL it so that if TAB|UNTAB is pressed, we
+			 * move to curr_hot (current hottest line).
+			 */
+			if (nd != NULL && RB_EMPTY_NODE(nd))
+				nd = NULL;
+		}
+
+		switch (key) {
+		case K_TIMER:
+			if (hbt)
+				hbt->timer(hbt->arg);
+
+			if (delay_secs != 0)
+				symbol__annotate_decay_histogram(sym, evsel->idx);
+			continue;
+		case K_TAB:
+			if (nd != NULL) {
+				nd = rb_prev(nd);
+				if (nd == NULL)
+					nd = rb_last(&browser->entries);
+			} else
+				nd = browser->curr_hot;
+			break;
+		case K_UNTAB:
+			if (nd != NULL)
+				nd = rb_next(nd);
+				if (nd == NULL)
+					nd = rb_first(&browser->entries);
+			else
+				nd = browser->curr_hot;
+			break;
+		case K_F1:
+		case 'h':
+			ui_browser__help_window(&browser->b,
+		"UP/DOWN/PGUP\n"
+		"PGDN/SPACE    Navigate\n"
+		"q/ESC/CTRL+C  Exit\n\n"
+		"->            Go to target\n"
+		"<-            Exit\n"
+		"H             Cycle thru hottest instructions\n"
+		"j             Toggle showing jump to target arrows\n"
+		"J             Toggle showing number of jump sources on targets\n"
+		"n             Search next string\n"
+		"o             Toggle disassembler output/simplified view\n"
+		"s             Toggle source code view\n"
+		"/             Search string\n"
+		"r             Run available scripts\n"
+		"?             Search string backwards\n");
+			continue;
+		case 'r':
+			{
+				script_browse(NULL);
+				continue;
+			}
+		case 'H':
+			nd = browser->curr_hot;
+			break;
+		case 's':
+			if (annotate_browser__toggle_source(browser))
+				ui_helpline__puts(help);
+			continue;
+		case 'o':
+			annotate_browser__opts.use_offset = !annotate_browser__opts.use_offset;
+			annotate_browser__update_addr_width(browser);
+			continue;
+		case 'j':
+			annotate_browser__opts.jump_arrows = !annotate_browser__opts.jump_arrows;
+			continue;
+		case 'J':
+			annotate_browser__opts.show_nr_jumps = !annotate_browser__opts.show_nr_jumps;
+			annotate_browser__update_addr_width(browser);
+			continue;
+		case '/':
+			if (annotate_browser__search(browser, delay_secs)) {
+show_help:
+				ui_helpline__puts(help);
+			}
+			continue;
+		case 'n':
+			if (browser->searching_backwards ?
+			    annotate_browser__continue_search_reverse(browser, delay_secs) :
+			    annotate_browser__continue_search(browser, delay_secs))
+				goto show_help;
+			continue;
+		case '?':
+			if (annotate_browser__search_reverse(browser, delay_secs))
+				goto show_help;
+			continue;
+		case 'D': {
+			static int seq;
+			ui_helpline__pop();
+			ui_helpline__fpush("%d: nr_ent=%d, height=%d, idx=%d, top_idx=%d, nr_asm_entries=%d",
+					   seq++, browser->b.nr_entries,
+					   browser->b.height,
+					   browser->b.index,
+					   browser->b.top_idx,
+					   browser->nr_asm_entries);
+		}
+			continue;
+		case K_ENTER:
+		case K_RIGHT:
+			if (browser->selection == NULL)
+				ui_helpline__puts("Huh? No selection. Report to linux-kernel@vger.kernel.org");
+			else if (browser->selection->offset == -1)
+				ui_helpline__puts("Actions are only available for assembly lines.");
+			else if (!browser->selection->ins) {
+				if (strcmp(browser->selection->name, "retq"))
+					goto show_sup_ins;
+				goto out;
+			} else if (!(annotate_browser__jump(browser) ||
+				     annotate_browser__callq(browser, evsel, hbt))) {
+show_sup_ins:
+				ui_helpline__puts("Actions are only available for 'callq', 'retq' & jump instructions.");
+			}
+			continue;
+		case K_LEFT:
+		case K_ESC:
+		case 'q':
+		case CTRL('c'):
+			goto out;
+		default:
+			continue;
+		}
+
+		if (nd != NULL)
+			annotate_browser__set_rb_top(browser, nd);
+	}
+out:
+	ui_browser__hide(&browser->b);
+	return key;
+}
+
+int hist_entry__tui_annotate(struct hist_entry *he, struct perf_evsel *evsel,
+			     struct hist_browser_timer *hbt)
+{
+	return symbol__tui_annotate(he->ms.sym, he->ms.map, evsel, hbt);
+}
+
+static void annotate_browser__mark_jump_targets(struct annotate_browser *browser,
+						size_t size)
+{
+	u64 offset;
+	struct map_symbol *ms = browser->b.priv;
+	struct symbol *sym = ms->sym;
+
+	/* PLT symbols contain external offsets */
+	if (strstr(sym->name, "@plt"))
+		return;
+
+	for (offset = 0; offset < size; ++offset) {
+		struct disasm_line *dl = browser->offsets[offset], *dlt;
+		struct browser_disasm_line *bdlt;
+
+		if (!disasm_line__is_valid_jump(dl, sym))
+			continue;
+
+		dlt = browser->offsets[dl->ops.target.offset];
+		/*
+ 		 * FIXME: Oops, no jump target? Buggy disassembler? Or do we
+ 		 * have to adjust to the previous offset?
+ 		 */
+		if (dlt == NULL)
+			continue;
+
+		bdlt = disasm_line__browser(dlt);
+		if (++bdlt->jump_sources > browser->max_jump_sources)
+			browser->max_jump_sources = bdlt->jump_sources;
+
+		++browser->nr_jumps;
+	}
+		
+}
+
+static inline int width_jumps(int n)
+{
+	if (n >= 100)
+		return 5;
+	if (n / 10)
+		return 2;
+	return 1;
+}
+
+int symbol__tui_annotate(struct symbol *sym, struct map *map,
+			 struct perf_evsel *evsel,
+			 struct hist_browser_timer *hbt)
+{
+	struct disasm_line *pos, *n;
+	struct annotation *notes;
+	size_t size;
+	struct map_symbol ms = {
+		.map = map,
+		.sym = sym,
+	};
+	struct annotate_browser browser = {
+		.b = {
+			.refresh = annotate_browser__refresh,
+			.seek	 = ui_browser__list_head_seek,
+			.write	 = annotate_browser__write,
+			.filter  = disasm_line__filter,
+			.priv	 = &ms,
+			.use_navkeypressed = true,
+		},
+	};
+	int ret = -1;
+	int nr_pcnt = 1;
+	size_t sizeof_bdl = sizeof(struct browser_disasm_line);
+
+	if (sym == NULL)
+		return -1;
+
+	size = symbol__size(sym);
+
+	if (map->dso->annotate_warned)
+		return -1;
+
+	browser.offsets = zalloc(size * sizeof(struct disasm_line *));
+	if (browser.offsets == NULL) {
+		ui__error("Not enough memory!");
+		return -1;
+	}
+
+	if (perf_evsel__is_group_event(evsel)) {
+		nr_pcnt = evsel->nr_members;
+		sizeof_bdl += sizeof(double) * (nr_pcnt - 1);
+	}
+
+	if (symbol__annotate(sym, map, sizeof_bdl) < 0) {
+		ui__error("%s", ui_helpline__last_msg);
+		goto out_free_offsets;
+	}
+
+	ui_helpline__push("Press <- or ESC to exit");
+
+	notes = symbol__annotation(sym);
+	browser.start = map__rip_2objdump(map, sym->start);
+
+	list_for_each_entry(pos, &notes->src->source, node) {
+		struct browser_disasm_line *bpos;
+		size_t line_len = strlen(pos->line);
+
+		if (browser.b.width < line_len)
+			browser.b.width = line_len;
+		bpos = disasm_line__browser(pos);
+		bpos->idx = browser.nr_entries++;
+		if (pos->offset != -1) {
+			bpos->idx_asm = browser.nr_asm_entries++;
+			/*
+			 * FIXME: short term bandaid to cope with assembly
+			 * routines that comes with labels in the same column
+			 * as the address in objdump, sigh.
+			 *
+			 * E.g. copy_user_generic_unrolled
+ 			 */
+			if (pos->offset < (s64)size)
+				browser.offsets[pos->offset] = pos;
+		} else
+			bpos->idx_asm = -1;
+	}
+
+	annotate_browser__mark_jump_targets(&browser, size);
+
+	browser.addr_width = browser.target_width = browser.min_addr_width = hex_width(size);
+	browser.max_addr_width = hex_width(sym->end);
+	browser.jumps_width = width_jumps(browser.max_jump_sources);
+	browser.nr_events = nr_pcnt;
+	browser.b.nr_entries = browser.nr_entries;
+	browser.b.entries = &notes->src->source,
+	browser.b.width += 18; /* Percentage */
+
+	if (annotate_browser__opts.hide_src_code)
+		annotate_browser__init_asm_mode(&browser);
+
+	annotate_browser__update_addr_width(&browser);
+
+	ret = annotate_browser__run(&browser, evsel, hbt);
+	list_for_each_entry_safe(pos, n, &notes->src->source, node) {
+		list_del(&pos->node);
+		disasm_line__free(pos);
+	}
+
+out_free_offsets:
+	free(browser.offsets);
+	return ret;
+}
+
+#define ANNOTATE_CFG(n) \
+	{ .name = #n, .value = &annotate_browser__opts.n, }
+
+/*
+ * Keep the entries sorted, they are bsearch'ed
+ */
+static struct annotate_config {
+	const char *name;
+	bool *value;
+} annotate__configs[] = {
+	ANNOTATE_CFG(hide_src_code),
+	ANNOTATE_CFG(jump_arrows),
+	ANNOTATE_CFG(show_nr_jumps),
+	ANNOTATE_CFG(use_offset),
+};
+
+#undef ANNOTATE_CFG
+
+static int annotate_config__cmp(const void *name, const void *cfgp)
+{
+	const struct annotate_config *cfg = cfgp;
+
+	return strcmp(name, cfg->name);
+}
+
+static int annotate__config(const char *var, const char *value,
+			    void *data __maybe_unused)
+{
+	struct annotate_config *cfg;
+	const char *name;
+
+	if (prefixcmp(var, "annotate.") != 0)
+		return 0;
+
+	name = var + 9;
+	cfg = bsearch(name, annotate__configs, ARRAY_SIZE(annotate__configs),
+		      sizeof(struct annotate_config), annotate_config__cmp);
+
+	if (cfg == NULL)
+		return -1;
+
+	*cfg->value = perf_config_bool(name, value);
+	return 0;
+}
+
+void annotate_browser__init(void)
+{
+	perf_config(annotate__config, NULL);
+}
diff --git a/tools/perf/ui/browsers/header.c b/tools/perf/ui/browsers/header.c
new file mode 100644
index 00000000000..89c16b98861
--- /dev/null
+++ b/tools/perf/ui/browsers/header.c
@@ -0,0 +1,127 @@
+#include "util/cache.h"
+#include "util/debug.h"
+#include "ui/browser.h"
+#include "ui/ui.h"
+#include "ui/util.h"
+#include "ui/libslang.h"
+#include "util/header.h"
+#include "util/session.h"
+
+static void ui_browser__argv_write(struct ui_browser *browser,
+				   void *entry, int row)
+{
+	char **arg = entry;
+	char *str = *arg;
+	char empty[] = " ";
+	bool current_entry = ui_browser__is_current_entry(browser, row);
+	unsigned long offset = (unsigned long)browser->priv;
+
+	if (offset >= strlen(str))
+		str = empty;
+	else
+		str = str + offset;
+
+	ui_browser__set_color(browser, current_entry ? HE_COLORSET_SELECTED :
+						       HE_COLORSET_NORMAL);
+
+	slsmg_write_nstring(str, browser->width);
+}
+
+static int list_menu__run(struct ui_browser *menu)
+{
+	int key;
+	unsigned long offset;
+	const char help[] =
+	"h/?/F1        Show this window\n"
+	"UP/DOWN/PGUP\n"
+	"PGDN/SPACE\n"
+	"LEFT/RIGHT    Navigate\n"
+	"q/ESC/CTRL+C  Exit browser";
+
+	if (ui_browser__show(menu, "Header information", "Press 'q' to exit") < 0)
+		return -1;
+
+	while (1) {
+		key = ui_browser__run(menu, 0);
+
+		switch (key) {
+		case K_RIGHT:
+			offset = (unsigned long)menu->priv;
+			offset += 10;
+			menu->priv = (void *)offset;
+			continue;
+		case K_LEFT:
+			offset = (unsigned long)menu->priv;
+			if (offset >= 10)
+				offset -= 10;
+			menu->priv = (void *)offset;
+			continue;
+		case K_F1:
+		case 'h':
+		case '?':
+			ui_browser__help_window(menu, help);
+			continue;
+		case K_ESC:
+		case 'q':
+		case CTRL('c'):
+			key = -1;
+			break;
+		default:
+			continue;
+		}
+
+		break;
+	}
+
+	ui_browser__hide(menu);
+	return key;
+}
+
+static int ui__list_menu(int argc, char * const argv[])
+{
+	struct ui_browser menu = {
+		.entries    = (void *)argv,
+		.refresh    = ui_browser__argv_refresh,
+		.seek	    = ui_browser__argv_seek,
+		.write	    = ui_browser__argv_write,
+		.nr_entries = argc,
+	};
+
+	return list_menu__run(&menu);
+}
+
+int tui__header_window(struct perf_session_env *env)
+{
+	int i, argc = 0;
+	char **argv;
+	struct perf_session *session;
+	char *ptr, *pos;
+	size_t size;
+	FILE *fp = open_memstream(&ptr, &size);
+
+	session = container_of(env, struct perf_session, header.env);
+	perf_header__fprintf_info(session, fp, true);
+	fclose(fp);
+
+	for (pos = ptr, argc = 0; (pos = strchr(pos, '\n')) != NULL; pos++)
+		argc++;
+
+	argv = calloc(argc + 1, sizeof(*argv));
+	if (argv == NULL)
+		goto out;
+
+	argv[0] = pos = ptr;
+	for (i = 1; (pos = strchr(pos, '\n')) != NULL; i++) {
+		*pos++ = '\0';
+		argv[i] = pos;
+	}
+
+	BUG_ON(i != argc + 1);
+
+	ui__list_menu(argc, argv);
+
+out:
+	free(argv);
+	free(ptr);
+	return 0;
+}
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
new file mode 100644
index 00000000000..04a229aa5c0
--- /dev/null
+++ b/tools/perf/ui/browsers/hists.c
@@ -0,0 +1,2007 @@
+#include <stdio.h>
+#include "../libslang.h"
+#include <stdlib.h>
+#include <string.h>
+#include <linux/rbtree.h>
+
+#include "../../util/evsel.h"
+#include "../../util/evlist.h"
+#include "../../util/hist.h"
+#include "../../util/pstack.h"
+#include "../../util/sort.h"
+#include "../../util/util.h"
+#include "../../arch/common.h"
+
+#include "../browser.h"
+#include "../helpline.h"
+#include "../util.h"
+#include "../ui.h"
+#include "map.h"
+#include "annotate.h"
+
+struct hist_browser {
+	struct ui_browser   b;
+	struct hists	    *hists;
+	struct hist_entry   *he_selection;
+	struct map_symbol   *selection;
+	int		     print_seq;
+	bool		     show_dso;
+	float		     min_pcnt;
+	u64		     nr_non_filtered_entries;
+	u64		     nr_callchain_rows;
+};
+
+extern void hist_browser__init_hpp(void);
+
+static int hists__browser_title(struct hists *hists, char *bf, size_t size,
+				const char *ev_name);
+static void hist_browser__update_nr_entries(struct hist_browser *hb);
+
+static struct rb_node *hists__filter_entries(struct rb_node *nd,
+					     float min_pcnt);
+
+static bool hist_browser__has_filter(struct hist_browser *hb)
+{
+	return hists__has_filter(hb->hists) || hb->min_pcnt;
+}
+
+static u32 hist_browser__nr_entries(struct hist_browser *hb)
+{
+	u32 nr_entries;
+
+	if (hist_browser__has_filter(hb))
+		nr_entries = hb->nr_non_filtered_entries;
+	else
+		nr_entries = hb->hists->nr_entries;
+
+	return nr_entries + hb->nr_callchain_rows;
+}
+
+static void hist_browser__refresh_dimensions(struct hist_browser *browser)
+{
+	/* 3 == +/- toggle symbol before actual hist_entry rendering */
+	browser->b.width = 3 + (hists__sort_list_width(browser->hists) +
+			     sizeof("[k]"));
+}
+
+static void hist_browser__reset(struct hist_browser *browser)
+{
+	/*
+	 * The hists__remove_entry_filter() already folds non-filtered
+	 * entries so we can assume it has 0 callchain rows.
+	 */
+	browser->nr_callchain_rows = 0;
+
+	hist_browser__update_nr_entries(browser);
+	browser->b.nr_entries = hist_browser__nr_entries(browser);
+	hist_browser__refresh_dimensions(browser);
+	ui_browser__reset_index(&browser->b);
+}
+
+static char tree__folded_sign(bool unfolded)
+{
+	return unfolded ? '-' : '+';
+}
+
+static char map_symbol__folded(const struct map_symbol *ms)
+{
+	return ms->has_children ? tree__folded_sign(ms->unfolded) : ' ';
+}
+
+static char hist_entry__folded(const struct hist_entry *he)
+{
+	return map_symbol__folded(&he->ms);
+}
+
+static char callchain_list__folded(const struct callchain_list *cl)
+{
+	return map_symbol__folded(&cl->ms);
+}
+
+static void map_symbol__set_folding(struct map_symbol *ms, bool unfold)
+{
+	ms->unfolded = unfold ? ms->has_children : false;
+}
+
+static int callchain_node__count_rows_rb_tree(struct callchain_node *node)
+{
+	int n = 0;
+	struct rb_node *nd;
+
+	for (nd = rb_first(&node->rb_root); nd; nd = rb_next(nd)) {
+		struct callchain_node *child = rb_entry(nd, struct callchain_node, rb_node);
+		struct callchain_list *chain;
+		char folded_sign = ' '; /* No children */
+
+		list_for_each_entry(chain, &child->val, list) {
+			++n;
+			/* We need this because we may not have children */
+			folded_sign = callchain_list__folded(chain);
+			if (folded_sign == '+')
+				break;
+		}
+
+		if (folded_sign == '-') /* Have children and they're unfolded */
+			n += callchain_node__count_rows_rb_tree(child);
+	}
+
+	return n;
+}
+
+static int callchain_node__count_rows(struct callchain_node *node)
+{
+	struct callchain_list *chain;
+	bool unfolded = false;
+	int n = 0;
+
+	list_for_each_entry(chain, &node->val, list) {
+		++n;
+		unfolded = chain->ms.unfolded;
+	}
+
+	if (unfolded)
+		n += callchain_node__count_rows_rb_tree(node);
+
+	return n;
+}
+
+static int callchain__count_rows(struct rb_root *chain)
+{
+	struct rb_node *nd;
+	int n = 0;
+
+	for (nd = rb_first(chain); nd; nd = rb_next(nd)) {
+		struct callchain_node *node = rb_entry(nd, struct callchain_node, rb_node);
+		n += callchain_node__count_rows(node);
+	}
+
+	return n;
+}
+
+static bool map_symbol__toggle_fold(struct map_symbol *ms)
+{
+	if (!ms)
+		return false;
+
+	if (!ms->has_children)
+		return false;
+
+	ms->unfolded = !ms->unfolded;
+	return true;
+}
+
+static void callchain_node__init_have_children_rb_tree(struct callchain_node *node)
+{
+	struct rb_node *nd = rb_first(&node->rb_root);
+
+	for (nd = rb_first(&node->rb_root); nd; nd = rb_next(nd)) {
+		struct callchain_node *child = rb_entry(nd, struct callchain_node, rb_node);
+		struct callchain_list *chain;
+		bool first = true;
+
+		list_for_each_entry(chain, &child->val, list) {
+			if (first) {
+				first = false;
+				chain->ms.has_children = chain->list.next != &child->val ||
+							 !RB_EMPTY_ROOT(&child->rb_root);
+			} else
+				chain->ms.has_children = chain->list.next == &child->val &&
+							 !RB_EMPTY_ROOT(&child->rb_root);
+		}
+
+		callchain_node__init_have_children_rb_tree(child);
+	}
+}
+
+static void callchain_node__init_have_children(struct callchain_node *node)
+{
+	struct callchain_list *chain;
+
+	list_for_each_entry(chain, &node->val, list)
+		chain->ms.has_children = !RB_EMPTY_ROOT(&node->rb_root);
+
+	callchain_node__init_have_children_rb_tree(node);
+}
+
+static void callchain__init_have_children(struct rb_root *root)
+{
+	struct rb_node *nd;
+
+	for (nd = rb_first(root); nd; nd = rb_next(nd)) {
+		struct callchain_node *node = rb_entry(nd, struct callchain_node, rb_node);
+		callchain_node__init_have_children(node);
+	}
+}
+
+static void hist_entry__init_have_children(struct hist_entry *he)
+{
+	if (!he->init_have_children) {
+		he->ms.has_children = !RB_EMPTY_ROOT(&he->sorted_chain);
+		callchain__init_have_children(&he->sorted_chain);
+		he->init_have_children = true;
+	}
+}
+
+static bool hist_browser__toggle_fold(struct hist_browser *browser)
+{
+	if (map_symbol__toggle_fold(browser->selection)) {
+		struct hist_entry *he = browser->he_selection;
+
+		hist_entry__init_have_children(he);
+		browser->b.nr_entries -= he->nr_rows;
+		browser->nr_callchain_rows -= he->nr_rows;
+
+		if (he->ms.unfolded)
+			he->nr_rows = callchain__count_rows(&he->sorted_chain);
+		else
+			he->nr_rows = 0;
+
+		browser->b.nr_entries += he->nr_rows;
+		browser->nr_callchain_rows += he->nr_rows;
+
+		return true;
+	}
+
+	/* If it doesn't have children, no toggling performed */
+	return false;
+}
+
+static int callchain_node__set_folding_rb_tree(struct callchain_node *node, bool unfold)
+{
+	int n = 0;
+	struct rb_node *nd;
+
+	for (nd = rb_first(&node->rb_root); nd; nd = rb_next(nd)) {
+		struct callchain_node *child = rb_entry(nd, struct callchain_node, rb_node);
+		struct callchain_list *chain;
+		bool has_children = false;
+
+		list_for_each_entry(chain, &child->val, list) {
+			++n;
+			map_symbol__set_folding(&chain->ms, unfold);
+			has_children = chain->ms.has_children;
+		}
+
+		if (has_children)
+			n += callchain_node__set_folding_rb_tree(child, unfold);
+	}
+
+	return n;
+}
+
+static int callchain_node__set_folding(struct callchain_node *node, bool unfold)
+{
+	struct callchain_list *chain;
+	bool has_children = false;
+	int n = 0;
+
+	list_for_each_entry(chain, &node->val, list) {
+		++n;
+		map_symbol__set_folding(&chain->ms, unfold);
+		has_children = chain->ms.has_children;
+	}
+
+	if (has_children)
+		n += callchain_node__set_folding_rb_tree(node, unfold);
+
+	return n;
+}
+
+static int callchain__set_folding(struct rb_root *chain, bool unfold)
+{
+	struct rb_node *nd;
+	int n = 0;
+
+	for (nd = rb_first(chain); nd; nd = rb_next(nd)) {
+		struct callchain_node *node = rb_entry(nd, struct callchain_node, rb_node);
+		n += callchain_node__set_folding(node, unfold);
+	}
+
+	return n;
+}
+
+static void hist_entry__set_folding(struct hist_entry *he, bool unfold)
+{
+	hist_entry__init_have_children(he);
+	map_symbol__set_folding(&he->ms, unfold);
+
+	if (he->ms.has_children) {
+		int n = callchain__set_folding(&he->sorted_chain, unfold);
+		he->nr_rows = unfold ? n : 0;
+	} else
+		he->nr_rows = 0;
+}
+
+static void
+__hist_browser__set_folding(struct hist_browser *browser, bool unfold)
+{
+	struct rb_node *nd;
+	struct hists *hists = browser->hists;
+
+	for (nd = rb_first(&hists->entries);
+	     (nd = hists__filter_entries(nd, browser->min_pcnt)) != NULL;
+	     nd = rb_next(nd)) {
+		struct hist_entry *he = rb_entry(nd, struct hist_entry, rb_node);
+		hist_entry__set_folding(he, unfold);
+		browser->nr_callchain_rows += he->nr_rows;
+	}
+}
+
+static void hist_browser__set_folding(struct hist_browser *browser, bool unfold)
+{
+	browser->nr_callchain_rows = 0;
+	__hist_browser__set_folding(browser, unfold);
+
+	browser->b.nr_entries = hist_browser__nr_entries(browser);
+	/* Go to the start, we may be way after valid entries after a collapse */
+	ui_browser__reset_index(&browser->b);
+}
+
+static void ui_browser__warn_lost_events(struct ui_browser *browser)
+{
+	ui_browser__warning(browser, 4,
+		"Events are being lost, check IO/CPU overload!\n\n"
+		"You may want to run 'perf' using a RT scheduler policy:\n\n"
+		" perf top -r 80\n\n"
+		"Or reduce the sampling frequency.");
+}
+
+static int hist_browser__run(struct hist_browser *browser, const char *ev_name,
+			     struct hist_browser_timer *hbt)
+{
+	int key;
+	char title[160];
+	int delay_secs = hbt ? hbt->refresh : 0;
+
+	browser->b.entries = &browser->hists->entries;
+	browser->b.nr_entries = hist_browser__nr_entries(browser);
+
+	hist_browser__refresh_dimensions(browser);
+	hists__browser_title(browser->hists, title, sizeof(title), ev_name);
+
+	if (ui_browser__show(&browser->b, title,
+			     "Press '?' for help on key bindings") < 0)
+		return -1;
+
+	while (1) {
+		key = ui_browser__run(&browser->b, delay_secs);
+
+		switch (key) {
+		case K_TIMER: {
+			u64 nr_entries;
+			hbt->timer(hbt->arg);
+
+			if (hist_browser__has_filter(browser))
+				hist_browser__update_nr_entries(browser);
+
+			nr_entries = hist_browser__nr_entries(browser);
+			ui_browser__update_nr_entries(&browser->b, nr_entries);
+
+			if (browser->hists->stats.nr_lost_warned !=
+			    browser->hists->stats.nr_events[PERF_RECORD_LOST]) {
+				browser->hists->stats.nr_lost_warned =
+					browser->hists->stats.nr_events[PERF_RECORD_LOST];
+				ui_browser__warn_lost_events(&browser->b);
+			}
+
+			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,
+							struct hist_entry, rb_node);
+			ui_helpline__pop();
+			ui_helpline__fpush("%d: nr_ent=(%d,%d), height=%d, idx=%d, fve: idx=%d, row_off=%d, nrows=%d",
+					   seq++, browser->b.nr_entries,
+					   browser->hists->nr_entries,
+					   browser->b.height,
+					   browser->b.index,
+					   browser->b.top_idx,
+					   h->row_offset, h->nr_rows);
+		}
+			break;
+		case 'C':
+			/* Collapse the whole world. */
+			hist_browser__set_folding(browser, false);
+			break;
+		case 'E':
+			/* Expand the whole world. */
+			hist_browser__set_folding(browser, true);
+			break;
+		case K_ENTER:
+			if (hist_browser__toggle_fold(browser))
+				break;
+			/* fall thru */
+		default:
+			goto out;
+		}
+	}
+out:
+	ui_browser__hide(&browser->b);
+	return key;
+}
+
+static char *callchain_list__sym_name(struct callchain_list *cl,
+				      char *bf, size_t bfsize, bool show_dso)
+{
+	int printed;
+
+	if (cl->ms.sym)
+		printed = scnprintf(bf, bfsize, "%s", cl->ms.sym->name);
+	else
+		printed = scnprintf(bf, bfsize, "%#" PRIx64, cl->ip);
+
+	if (show_dso)
+		scnprintf(bf + printed, bfsize - printed, " %s",
+			  cl->ms.map ? cl->ms.map->dso->short_name : "unknown");
+
+	return bf;
+}
+
+#define LEVEL_OFFSET_STEP 3
+
+static int hist_browser__show_callchain_node_rb_tree(struct hist_browser *browser,
+						     struct callchain_node *chain_node,
+						     u64 total, int level,
+						     unsigned short row,
+						     off_t *row_offset,
+						     bool *is_current_entry)
+{
+	struct rb_node *node;
+	int first_row = row, width, offset = level * LEVEL_OFFSET_STEP;
+	u64 new_total, remaining;
+
+	if (callchain_param.mode == CHAIN_GRAPH_REL)
+		new_total = chain_node->children_hit;
+	else
+		new_total = total;
+
+	remaining = new_total;
+	node = rb_first(&chain_node->rb_root);
+	while (node) {
+		struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
+		struct rb_node *next = rb_next(node);
+		u64 cumul = callchain_cumul_hits(child);
+		struct callchain_list *chain;
+		char folded_sign = ' ';
+		int first = true;
+		int extra_offset = 0;
+
+		remaining -= cumul;
+
+		list_for_each_entry(chain, &child->val, list) {
+			char bf[1024], *alloc_str;
+			const char *str;
+			int color;
+			bool was_first = first;
+
+			if (first)
+				first = false;
+			else
+				extra_offset = LEVEL_OFFSET_STEP;
+
+			folded_sign = callchain_list__folded(chain);
+			if (*row_offset != 0) {
+				--*row_offset;
+				goto do_next;
+			}
+
+			alloc_str = NULL;
+			str = callchain_list__sym_name(chain, bf, sizeof(bf),
+						       browser->show_dso);
+			if (was_first) {
+				double percent = cumul * 100.0 / new_total;
+
+				if (asprintf(&alloc_str, "%2.2f%% %s", percent, str) < 0)
+					str = "Not enough memory!";
+				else
+					str = alloc_str;
+			}
+
+			color = HE_COLORSET_NORMAL;
+			width = browser->b.width - (offset + extra_offset + 2);
+			if (ui_browser__is_current_entry(&browser->b, row)) {
+				browser->selection = &chain->ms;
+				color = HE_COLORSET_SELECTED;
+				*is_current_entry = true;
+			}
+
+			ui_browser__set_color(&browser->b, color);
+			ui_browser__gotorc(&browser->b, row, 0);
+			slsmg_write_nstring(" ", offset + extra_offset);
+			slsmg_printf("%c ", folded_sign);
+			slsmg_write_nstring(str, width);
+			free(alloc_str);
+
+			if (++row == browser->b.height)
+				goto out;
+do_next:
+			if (folded_sign == '+')
+				break;
+		}
+
+		if (folded_sign == '-') {
+			const int new_level = level + (extra_offset ? 2 : 1);
+			row += hist_browser__show_callchain_node_rb_tree(browser, child, new_total,
+									 new_level, row, row_offset,
+									 is_current_entry);
+		}
+		if (row == browser->b.height)
+			goto out;
+		node = next;
+	}
+out:
+	return row - first_row;
+}
+
+static int hist_browser__show_callchain_node(struct hist_browser *browser,
+					     struct callchain_node *node,
+					     int level, unsigned short row,
+					     off_t *row_offset,
+					     bool *is_current_entry)
+{
+	struct callchain_list *chain;
+	int first_row = row,
+	     offset = level * LEVEL_OFFSET_STEP,
+	     width = browser->b.width - offset;
+	char folded_sign = ' ';
+
+	list_for_each_entry(chain, &node->val, list) {
+		char bf[1024], *s;
+		int color;
+
+		folded_sign = callchain_list__folded(chain);
+
+		if (*row_offset != 0) {
+			--*row_offset;
+			continue;
+		}
+
+		color = HE_COLORSET_NORMAL;
+		if (ui_browser__is_current_entry(&browser->b, row)) {
+			browser->selection = &chain->ms;
+			color = HE_COLORSET_SELECTED;
+			*is_current_entry = true;
+		}
+
+		s = callchain_list__sym_name(chain, bf, sizeof(bf),
+					     browser->show_dso);
+		ui_browser__gotorc(&browser->b, row, 0);
+		ui_browser__set_color(&browser->b, color);
+		slsmg_write_nstring(" ", offset);
+		slsmg_printf("%c ", folded_sign);
+		slsmg_write_nstring(s, width - 2);
+
+		if (++row == browser->b.height)
+			goto out;
+	}
+
+	if (folded_sign == '-')
+		row += hist_browser__show_callchain_node_rb_tree(browser, node,
+								 browser->hists->stats.total_period,
+								 level + 1, row,
+								 row_offset,
+								 is_current_entry);
+out:
+	return row - first_row;
+}
+
+static int hist_browser__show_callchain(struct hist_browser *browser,
+					struct rb_root *chain,
+					int level, unsigned short row,
+					off_t *row_offset,
+					bool *is_current_entry)
+{
+	struct rb_node *nd;
+	int first_row = row;
+
+	for (nd = rb_first(chain); nd; nd = rb_next(nd)) {
+		struct callchain_node *node = rb_entry(nd, struct callchain_node, rb_node);
+
+		row += hist_browser__show_callchain_node(browser, node, level,
+							 row, row_offset,
+							 is_current_entry);
+		if (row == browser->b.height)
+			break;
+	}
+
+	return row - first_row;
+}
+
+struct hpp_arg {
+	struct ui_browser *b;
+	char folded_sign;
+	bool current_entry;
+};
+
+static int __hpp__slsmg_color_printf(struct perf_hpp *hpp, const char *fmt, ...)
+{
+	struct hpp_arg *arg = hpp->ptr;
+	int ret;
+	va_list args;
+	double percent;
+
+	va_start(args, fmt);
+	percent = va_arg(args, double);
+	va_end(args);
+
+	ui_browser__set_percent_color(arg->b, percent, arg->current_entry);
+
+	ret = scnprintf(hpp->buf, hpp->size, fmt, percent);
+	slsmg_printf("%s", hpp->buf);
+
+	advance_hpp(hpp, ret);
+	return ret;
+}
+
+#define __HPP_COLOR_PERCENT_FN(_type, _field)				\
+static u64 __hpp_get_##_field(struct hist_entry *he)			\
+{									\
+	return he->stat._field;						\
+}									\
+									\
+static int								\
+hist_browser__hpp_color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,\
+				struct perf_hpp *hpp,			\
+				struct hist_entry *he)			\
+{									\
+	return __hpp__fmt(hpp, he, __hpp_get_##_field, " %6.2f%%",	\
+			  __hpp__slsmg_color_printf, true);		\
+}
+
+#define __HPP_COLOR_ACC_PERCENT_FN(_type, _field)			\
+static u64 __hpp_get_acc_##_field(struct hist_entry *he)		\
+{									\
+	return he->stat_acc->_field;					\
+}									\
+									\
+static int								\
+hist_browser__hpp_color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,\
+				struct perf_hpp *hpp,			\
+				struct hist_entry *he)			\
+{									\
+	if (!symbol_conf.cumulate_callchain) {				\
+		int ret = scnprintf(hpp->buf, hpp->size, "%8s", "N/A");	\
+		slsmg_printf("%s", hpp->buf);				\
+									\
+		return ret;						\
+	}								\
+	return __hpp__fmt(hpp, he, __hpp_get_acc_##_field, " %6.2f%%",	\
+			  __hpp__slsmg_color_printf, true);		\
+}
+
+__HPP_COLOR_PERCENT_FN(overhead, period)
+__HPP_COLOR_PERCENT_FN(overhead_sys, period_sys)
+__HPP_COLOR_PERCENT_FN(overhead_us, period_us)
+__HPP_COLOR_PERCENT_FN(overhead_guest_sys, period_guest_sys)
+__HPP_COLOR_PERCENT_FN(overhead_guest_us, period_guest_us)
+__HPP_COLOR_ACC_PERCENT_FN(overhead_acc, period)
+
+#undef __HPP_COLOR_PERCENT_FN
+#undef __HPP_COLOR_ACC_PERCENT_FN
+
+void hist_browser__init_hpp(void)
+{
+	perf_hpp__format[PERF_HPP__OVERHEAD].color =
+				hist_browser__hpp_color_overhead;
+	perf_hpp__format[PERF_HPP__OVERHEAD_SYS].color =
+				hist_browser__hpp_color_overhead_sys;
+	perf_hpp__format[PERF_HPP__OVERHEAD_US].color =
+				hist_browser__hpp_color_overhead_us;
+	perf_hpp__format[PERF_HPP__OVERHEAD_GUEST_SYS].color =
+				hist_browser__hpp_color_overhead_guest_sys;
+	perf_hpp__format[PERF_HPP__OVERHEAD_GUEST_US].color =
+				hist_browser__hpp_color_overhead_guest_us;
+	perf_hpp__format[PERF_HPP__OVERHEAD_ACC].color =
+				hist_browser__hpp_color_overhead_acc;
+}
+
+static int hist_browser__show_entry(struct hist_browser *browser,
+				    struct hist_entry *entry,
+				    unsigned short row)
+{
+	char s[256];
+	int printed = 0;
+	int width = browser->b.width;
+	char folded_sign = ' ';
+	bool current_entry = ui_browser__is_current_entry(&browser->b, row);
+	off_t row_offset = entry->row_offset;
+	bool first = true;
+	struct perf_hpp_fmt *fmt;
+
+	if (current_entry) {
+		browser->he_selection = entry;
+		browser->selection = &entry->ms;
+	}
+
+	if (symbol_conf.use_callchain) {
+		hist_entry__init_have_children(entry);
+		folded_sign = hist_entry__folded(entry);
+	}
+
+	if (row_offset == 0) {
+		struct hpp_arg arg = {
+			.b		= &browser->b,
+			.folded_sign	= folded_sign,
+			.current_entry	= current_entry,
+		};
+		struct perf_hpp hpp = {
+			.buf		= s,
+			.size		= sizeof(s),
+			.ptr		= &arg,
+		};
+
+		ui_browser__gotorc(&browser->b, row, 0);
+
+		perf_hpp__for_each_format(fmt) {
+			if (perf_hpp__should_skip(fmt))
+				continue;
+
+			if (current_entry && browser->b.navkeypressed) {
+				ui_browser__set_color(&browser->b,
+						      HE_COLORSET_SELECTED);
+			} else {
+				ui_browser__set_color(&browser->b,
+						      HE_COLORSET_NORMAL);
+			}
+
+			if (first) {
+				if (symbol_conf.use_callchain) {
+					slsmg_printf("%c ", folded_sign);
+					width -= 2;
+				}
+				first = false;
+			} else {
+				slsmg_printf("  ");
+				width -= 2;
+			}
+
+			if (fmt->color) {
+				width -= fmt->color(fmt, &hpp, entry);
+			} else {
+				width -= fmt->entry(fmt, &hpp, entry);
+				slsmg_printf("%s", s);
+			}
+		}
+
+		/* The scroll bar isn't being used */
+		if (!browser->b.navkeypressed)
+			width += 1;
+
+		slsmg_write_nstring("", width);
+
+		++row;
+		++printed;
+	} else
+		--row_offset;
+
+	if (folded_sign == '-' && row != browser->b.height) {
+		printed += hist_browser__show_callchain(browser, &entry->sorted_chain,
+							1, row, &row_offset,
+							&current_entry);
+		if (current_entry)
+			browser->he_selection = entry;
+	}
+
+	return printed;
+}
+
+static void ui_browser__hists_init_top(struct ui_browser *browser)
+{
+	if (browser->top == NULL) {
+		struct hist_browser *hb;
+
+		hb = container_of(browser, struct hist_browser, b);
+		browser->top = rb_first(&hb->hists->entries);
+	}
+}
+
+static unsigned int hist_browser__refresh(struct ui_browser *browser)
+{
+	unsigned row = 0;
+	struct rb_node *nd;
+	struct hist_browser *hb = container_of(browser, struct hist_browser, b);
+
+	ui_browser__hists_init_top(browser);
+
+	for (nd = browser->top; nd; nd = rb_next(nd)) {
+		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
+		float percent;
+
+		if (h->filtered)
+			continue;
+
+		percent = hist_entry__get_percent_limit(h);
+		if (percent < hb->min_pcnt)
+			continue;
+
+		row += hist_browser__show_entry(hb, h, row);
+		if (row == browser->height)
+			break;
+	}
+
+	return row;
+}
+
+static struct rb_node *hists__filter_entries(struct rb_node *nd,
+					     float min_pcnt)
+{
+	while (nd != NULL) {
+		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
+		float percent = hist_entry__get_percent_limit(h);
+
+		if (!h->filtered && percent >= min_pcnt)
+			return nd;
+
+		nd = rb_next(nd);
+	}
+
+	return NULL;
+}
+
+static struct rb_node *hists__filter_prev_entries(struct rb_node *nd,
+						  float min_pcnt)
+{
+	while (nd != NULL) {
+		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
+		float percent = hist_entry__get_percent_limit(h);
+
+		if (!h->filtered && percent >= min_pcnt)
+			return nd;
+
+		nd = rb_prev(nd);
+	}
+
+	return NULL;
+}
+
+static void ui_browser__hists_seek(struct ui_browser *browser,
+				   off_t offset, int whence)
+{
+	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;
+
+	ui_browser__hists_init_top(browser);
+
+	switch (whence) {
+	case SEEK_SET:
+		nd = hists__filter_entries(rb_first(browser->entries),
+					   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),
+						hb->min_pcnt);
+		first = false;
+		break;
+	default:
+		return;
+	}
+
+	/*
+	 * Moves not relative to the first visible entry invalidates its
+	 * row_offset:
+	 */
+	h = rb_entry(browser->top, struct hist_entry, rb_node);
+	h->row_offset = 0;
+
+	/*
+	 * Here we have to check if nd is expanded (+), if it is we can't go
+	 * the next top level hist_entry, instead we must compute an offset of
+	 * what _not_ to show and not change the first visible entry.
+	 *
+	 * This offset increments when we are going from top to bottom and
+	 * decreases when we're going from bottom to top.
+	 *
+	 * As we don't have backpointers to the top level in the callchains
+	 * structure, we need to always print the whole hist_entry callchain,
+	 * skipping the first ones that are before the first visible entry
+	 * and stop when we printed enough lines to fill the screen.
+	 */
+do_offset:
+	if (offset > 0) {
+		do {
+			h = rb_entry(nd, struct hist_entry, rb_node);
+			if (h->ms.unfolded) {
+				u16 remaining = h->nr_rows - h->row_offset;
+				if (offset > remaining) {
+					offset -= remaining;
+					h->row_offset = 0;
+				} else {
+					h->row_offset += offset;
+					offset = 0;
+					browser->top = nd;
+					break;
+				}
+			}
+			nd = hists__filter_entries(rb_next(nd), hb->min_pcnt);
+			if (nd == NULL)
+				break;
+			--offset;
+			browser->top = nd;
+		} while (offset != 0);
+	} else if (offset < 0) {
+		while (1) {
+			h = rb_entry(nd, struct hist_entry, rb_node);
+			if (h->ms.unfolded) {
+				if (first) {
+					if (-offset > h->row_offset) {
+						offset += h->row_offset;
+						h->row_offset = 0;
+					} else {
+						h->row_offset += offset;
+						offset = 0;
+						browser->top = nd;
+						break;
+					}
+				} else {
+					if (-offset > h->nr_rows) {
+						offset += h->nr_rows;
+						h->row_offset = 0;
+					} else {
+						h->row_offset = h->nr_rows + offset;
+						offset = 0;
+						browser->top = nd;
+						break;
+					}
+				}
+			}
+
+			nd = hists__filter_prev_entries(rb_prev(nd),
+							hb->min_pcnt);
+			if (nd == NULL)
+				break;
+			++offset;
+			browser->top = nd;
+			if (offset == 0) {
+				/*
+				 * Last unfiltered hist_entry, check if it is
+				 * unfolded, if it is then we should have
+				 * row_offset at its last entry.
+				 */
+				h = rb_entry(nd, struct hist_entry, rb_node);
+				if (h->ms.unfolded)
+					h->row_offset = h->nr_rows;
+				break;
+			}
+			first = false;
+		}
+	} else {
+		browser->top = nd;
+		h = rb_entry(nd, struct hist_entry, rb_node);
+		h->row_offset = 0;
+	}
+}
+
+static int hist_browser__fprintf_callchain_node_rb_tree(struct hist_browser *browser,
+							struct callchain_node *chain_node,
+							u64 total, int level,
+							FILE *fp)
+{
+	struct rb_node *node;
+	int offset = level * LEVEL_OFFSET_STEP;
+	u64 new_total, remaining;
+	int printed = 0;
+
+	if (callchain_param.mode == CHAIN_GRAPH_REL)
+		new_total = chain_node->children_hit;
+	else
+		new_total = total;
+
+	remaining = new_total;
+	node = rb_first(&chain_node->rb_root);
+	while (node) {
+		struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
+		struct rb_node *next = rb_next(node);
+		u64 cumul = callchain_cumul_hits(child);
+		struct callchain_list *chain;
+		char folded_sign = ' ';
+		int first = true;
+		int extra_offset = 0;
+
+		remaining -= cumul;
+
+		list_for_each_entry(chain, &child->val, list) {
+			char bf[1024], *alloc_str;
+			const char *str;
+			bool was_first = first;
+
+			if (first)
+				first = false;
+			else
+				extra_offset = LEVEL_OFFSET_STEP;
+
+			folded_sign = callchain_list__folded(chain);
+
+			alloc_str = NULL;
+			str = callchain_list__sym_name(chain, bf, sizeof(bf),
+						       browser->show_dso);
+			if (was_first) {
+				double percent = cumul * 100.0 / new_total;
+
+				if (asprintf(&alloc_str, "%2.2f%% %s", percent, str) < 0)
+					str = "Not enough memory!";
+				else
+					str = alloc_str;
+			}
+
+			printed += fprintf(fp, "%*s%c %s\n", offset + extra_offset, " ", folded_sign, str);
+			free(alloc_str);
+			if (folded_sign == '+')
+				break;
+		}
+
+		if (folded_sign == '-') {
+			const int new_level = level + (extra_offset ? 2 : 1);
+			printed += hist_browser__fprintf_callchain_node_rb_tree(browser, child, new_total,
+										new_level, fp);
+		}
+
+		node = next;
+	}
+
+	return printed;
+}
+
+static int hist_browser__fprintf_callchain_node(struct hist_browser *browser,
+						struct callchain_node *node,
+						int level, FILE *fp)
+{
+	struct callchain_list *chain;
+	int offset = level * LEVEL_OFFSET_STEP;
+	char folded_sign = ' ';
+	int printed = 0;
+
+	list_for_each_entry(chain, &node->val, list) {
+		char bf[1024], *s;
+
+		folded_sign = callchain_list__folded(chain);
+		s = callchain_list__sym_name(chain, bf, sizeof(bf), browser->show_dso);
+		printed += fprintf(fp, "%*s%c %s\n", offset, " ", folded_sign, s);
+	}
+
+	if (folded_sign == '-')
+		printed += hist_browser__fprintf_callchain_node_rb_tree(browser, node,
+									browser->hists->stats.total_period,
+									level + 1,  fp);
+	return printed;
+}
+
+static int hist_browser__fprintf_callchain(struct hist_browser *browser,
+					   struct rb_root *chain, int level, FILE *fp)
+{
+	struct rb_node *nd;
+	int printed = 0;
+
+	for (nd = rb_first(chain); nd; nd = rb_next(nd)) {
+		struct callchain_node *node = rb_entry(nd, struct callchain_node, rb_node);
+
+		printed += hist_browser__fprintf_callchain_node(browser, node, level, fp);
+	}
+
+	return printed;
+}
+
+static int hist_browser__fprintf_entry(struct hist_browser *browser,
+				       struct hist_entry *he, FILE *fp)
+{
+	char s[8192];
+	int printed = 0;
+	char folded_sign = ' ';
+	struct perf_hpp hpp = {
+		.buf = s,
+		.size = sizeof(s),
+	};
+	struct perf_hpp_fmt *fmt;
+	bool first = true;
+	int ret;
+
+	if (symbol_conf.use_callchain)
+		folded_sign = hist_entry__folded(he);
+
+	if (symbol_conf.use_callchain)
+		printed += fprintf(fp, "%c ", folded_sign);
+
+	perf_hpp__for_each_format(fmt) {
+		if (perf_hpp__should_skip(fmt))
+			continue;
+
+		if (!first) {
+			ret = scnprintf(hpp.buf, hpp.size, "  ");
+			advance_hpp(&hpp, ret);
+		} else
+			first = false;
+
+		ret = fmt->entry(fmt, &hpp, he);
+		advance_hpp(&hpp, ret);
+	}
+	printed += fprintf(fp, "%s\n", rtrim(s));
+
+	if (folded_sign == '-')
+		printed += hist_browser__fprintf_callchain(browser, &he->sorted_chain, 1, fp);
+
+	return printed;
+}
+
+static int hist_browser__fprintf(struct hist_browser *browser, FILE *fp)
+{
+	struct rb_node *nd = hists__filter_entries(rb_first(browser->b.entries),
+						   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), browser->min_pcnt);
+	}
+
+	return printed;
+}
+
+static int hist_browser__dump(struct hist_browser *browser)
+{
+	char filename[64];
+	FILE *fp;
+
+	while (1) {
+		scnprintf(filename, sizeof(filename), "perf.hist.%d", browser->print_seq);
+		if (access(filename, F_OK))
+			break;
+		/*
+ 		 * XXX: Just an arbitrary lazy upper limit
+ 		 */
+		if (++browser->print_seq == 8192) {
+			ui_helpline__fpush("Too many perf.hist.N files, nothing written!");
+			return -1;
+		}
+	}
+
+	fp = fopen(filename, "w");
+	if (fp == NULL) {
+		char bf[64];
+		const char *err = strerror_r(errno, bf, sizeof(bf));
+		ui_helpline__fpush("Couldn't write to %s: %s", filename, err);
+		return -1;
+	}
+
+	++browser->print_seq;
+	hist_browser__fprintf(browser, fp);
+	fclose(fp);
+	ui_helpline__fpush("%s written!", filename);
+
+	return 0;
+}
+
+static struct hist_browser *hist_browser__new(struct hists *hists)
+{
+	struct hist_browser *browser = zalloc(sizeof(*browser));
+
+	if (browser) {
+		browser->hists = hists;
+		browser->b.refresh = hist_browser__refresh;
+		browser->b.seek = ui_browser__hists_seek;
+		browser->b.use_navkeypressed = true;
+	}
+
+	return browser;
+}
+
+static void hist_browser__delete(struct hist_browser *browser)
+{
+	free(browser);
+}
+
+static struct hist_entry *hist_browser__selected_entry(struct hist_browser *browser)
+{
+	return browser->he_selection;
+}
+
+static struct thread *hist_browser__selected_thread(struct hist_browser *browser)
+{
+	return browser->he_selection->thread;
+}
+
+static int hists__browser_title(struct hists *hists, char *bf, size_t size,
+				const char *ev_name)
+{
+	char unit;
+	int printed;
+	const struct dso *dso = hists->dso_filter;
+	const struct thread *thread = hists->thread_filter;
+	unsigned long nr_samples = hists->stats.nr_events[PERF_RECORD_SAMPLE];
+	u64 nr_events = hists->stats.total_period;
+	struct perf_evsel *evsel = hists_to_evsel(hists);
+	char buf[512];
+	size_t buflen = sizeof(buf);
+
+	if (symbol_conf.filter_relative) {
+		nr_samples = hists->stats.nr_non_filtered_samples;
+		nr_events = hists->stats.total_non_filtered_period;
+	}
+
+	if (perf_evsel__is_group_event(evsel)) {
+		struct perf_evsel *pos;
+
+		perf_evsel__group_desc(evsel, buf, buflen);
+		ev_name = buf;
+
+		for_each_group_member(pos, evsel) {
+			if (symbol_conf.filter_relative) {
+				nr_samples += pos->hists.stats.nr_non_filtered_samples;
+				nr_events += pos->hists.stats.total_non_filtered_period;
+			} else {
+				nr_samples += pos->hists.stats.nr_events[PERF_RECORD_SAMPLE];
+				nr_events += pos->hists.stats.total_period;
+			}
+		}
+	}
+
+	nr_samples = convert_unit(nr_samples, &unit);
+	printed = scnprintf(bf, size,
+			   "Samples: %lu%c of event '%s', Event count (approx.): %lu",
+			   nr_samples, unit, ev_name, nr_events);
+
+
+	if (hists->uid_filter_str)
+		printed += snprintf(bf + printed, size - printed,
+				    ", UID: %s", hists->uid_filter_str);
+	if (thread)
+		printed += scnprintf(bf + printed, size - printed,
+				    ", Thread: %s(%d)",
+				     (thread->comm_set ? thread__comm_str(thread) : ""),
+				    thread->tid);
+	if (dso)
+		printed += scnprintf(bf + printed, size - printed,
+				    ", DSO: %s", dso->short_name);
+	return printed;
+}
+
+static inline void free_popup_options(char **options, int n)
+{
+	int i;
+
+	for (i = 0; i < n; ++i)
+		zfree(&options[i]);
+}
+
+/* Check whether the browser is for 'top' or 'report' */
+static inline bool is_report_browser(void *timer)
+{
+	return timer == NULL;
+}
+
+/*
+ * Only runtime switching of perf data file will make "input_name" point
+ * to a malloced buffer. So add "is_input_name_malloced" flag to decide
+ * whether we need to call free() for current "input_name" during the switch.
+ */
+static bool is_input_name_malloced = false;
+
+static int switch_data_file(void)
+{
+	char *pwd, *options[32], *abs_path[32], *tmp;
+	DIR *pwd_dir;
+	int nr_options = 0, choice = -1, ret = -1;
+	struct dirent *dent;
+
+	pwd = getenv("PWD");
+	if (!pwd)
+		return ret;
+
+	pwd_dir = opendir(pwd);
+	if (!pwd_dir)
+		return ret;
+
+	memset(options, 0, sizeof(options));
+	memset(options, 0, sizeof(abs_path));
+
+	while ((dent = readdir(pwd_dir))) {
+		char path[PATH_MAX];
+		u64 magic;
+		char *name = dent->d_name;
+		FILE *file;
+
+		if (!(dent->d_type == DT_REG))
+			continue;
+
+		snprintf(path, sizeof(path), "%s/%s", pwd, name);
+
+		file = fopen(path, "r");
+		if (!file)
+			continue;
+
+		if (fread(&magic, 1, 8, file) < 8)
+			goto close_file_and_continue;
+
+		if (is_perf_magic(magic)) {
+			options[nr_options] = strdup(name);
+			if (!options[nr_options])
+				goto close_file_and_continue;
+
+			abs_path[nr_options] = strdup(path);
+			if (!abs_path[nr_options]) {
+				zfree(&options[nr_options]);
+				ui__warning("Can't search all data files due to memory shortage.\n");
+				fclose(file);
+				break;
+			}
+
+			nr_options++;
+		}
+
+close_file_and_continue:
+		fclose(file);
+		if (nr_options >= 32) {
+			ui__warning("Too many perf data files in PWD!\n"
+				    "Only the first 32 files will be listed.\n");
+			break;
+		}
+	}
+	closedir(pwd_dir);
+
+	if (nr_options) {
+		choice = ui__popup_menu(nr_options, options);
+		if (choice < nr_options && choice >= 0) {
+			tmp = strdup(abs_path[choice]);
+			if (tmp) {
+				if (is_input_name_malloced)
+					free((void *)input_name);
+				input_name = tmp;
+				is_input_name_malloced = true;
+				ret = 0;
+			} else
+				ui__warning("Data switch failed due to memory shortage!\n");
+		}
+	}
+
+	free_popup_options(options, nr_options);
+	free_popup_options(abs_path, nr_options);
+	return ret;
+}
+
+static void hist_browser__update_nr_entries(struct hist_browser *hb)
+{
+	u64 nr_entries = 0;
+	struct rb_node *nd = rb_first(&hb->hists->entries);
+
+	if (hb->min_pcnt == 0) {
+		hb->nr_non_filtered_entries = hb->hists->nr_non_filtered_entries;
+		return;
+	}
+
+	while ((nd = hists__filter_entries(nd, hb->min_pcnt)) != NULL) {
+		nr_entries++;
+		nd = rb_next(nd);
+	}
+
+	hb->nr_non_filtered_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;
+	struct hist_browser *browser = hist_browser__new(hists);
+	struct branch_info *bi;
+	struct pstack *fstack;
+	char *options[16];
+	int nr_options = 0;
+	int key = -1;
+	char buf[64];
+	char script_opt[64];
+	int delay_secs = hbt ? hbt->refresh : 0;
+
+#define HIST_BROWSER_HELP_COMMON					\
+	"h/?/F1        Show this window\n"				\
+	"UP/DOWN/PGUP\n"						\
+	"PGDN/SPACE    Navigate\n"					\
+	"q/ESC/CTRL+C  Exit browser\n\n"				\
+	"For multiple event sessions:\n\n"				\
+	"TAB/UNTAB     Switch events\n\n"				\
+	"For symbolic views (--sort has sym):\n\n"			\
+	"->            Zoom into DSO/Threads & Annotate current symbol\n" \
+	"<-            Zoom out\n"					\
+	"a             Annotate current symbol\n"			\
+	"C             Collapse all callchains\n"			\
+	"d             Zoom into current DSO\n"				\
+	"E             Expand all callchains\n"				\
+	"F             Toggle percentage of filtered entries\n"		\
+
+	/* help messages are sorted by lexical order of the hotkey */
+	const char report_help[] = HIST_BROWSER_HELP_COMMON
+	"i             Show header information\n"
+	"P             Print histograms to perf.hist.N\n"
+	"r             Run available scripts\n"
+	"s             Switch to another data file in PWD\n"
+	"t             Zoom into current Thread\n"
+	"V             Verbose (DSO names in callchains, etc)\n"
+	"/             Filter symbol by name";
+	const char top_help[] = HIST_BROWSER_HELP_COMMON
+	"P             Print histograms to perf.hist.N\n"
+	"t             Zoom into current Thread\n"
+	"V             Verbose (DSO names in callchains, etc)\n"
+	"/             Filter symbol by name";
+
+	if (browser == NULL)
+		return -1;
+
+	if (min_pcnt) {
+		browser->min_pcnt = min_pcnt;
+		hist_browser__update_nr_entries(browser);
+	}
+
+	fstack = pstack__new(2);
+	if (fstack == NULL)
+		goto out;
+
+	ui_helpline__push(helpline);
+
+	memset(options, 0, sizeof(options));
+
+	while (1) {
+		const struct thread *thread = NULL;
+		const struct dso *dso = NULL;
+		int choice = 0,
+		    annotate = -2, zoom_dso = -2, zoom_thread = -2,
+		    annotate_f = -2, annotate_t = -2, browse_map = -2;
+		int scripts_comm = -2, scripts_symbol = -2,
+		    scripts_all = -2, switch_data = -2;
+
+		nr_options = 0;
+
+		key = hist_browser__run(browser, ev_name, hbt);
+
+		if (browser->he_selection != NULL) {
+			thread = hist_browser__selected_thread(browser);
+			dso = browser->selection->map ? browser->selection->map->dso : NULL;
+		}
+		switch (key) {
+		case K_TAB:
+		case K_UNTAB:
+			if (nr_events == 1)
+				continue;
+			/*
+			 * Exit the browser, let hists__browser_tree
+			 * go to the next or previous
+			 */
+			goto out_free_stack;
+		case 'a':
+			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.");
+				continue;
+			}
+
+			if (browser->selection == NULL ||
+			    browser->selection->sym == NULL ||
+			    browser->selection->map->dso->annotate_warned)
+				continue;
+			goto do_annotate;
+		case 'P':
+			hist_browser__dump(browser);
+			continue;
+		case 'd':
+			goto zoom_dso;
+		case 'V':
+			browser->show_dso = !browser->show_dso;
+			continue;
+		case 't':
+			goto zoom_thread;
+		case '/':
+			if (ui_browser__input_window("Symbol to show",
+					"Please enter the name of symbol you want to see",
+					buf, "ENTER: OK, ESC: Cancel",
+					delay_secs * 2) == K_ENTER) {
+				hists->symbol_filter_str = *buf ? buf : NULL;
+				hists__filter_by_symbol(hists);
+				hist_browser__reset(browser);
+			}
+			continue;
+		case 'r':
+			if (is_report_browser(hbt))
+				goto do_scripts;
+			continue;
+		case 's':
+			if (is_report_browser(hbt))
+				goto do_data_switch;
+			continue;
+		case 'i':
+			/* env->arch is NULL for live-mode (i.e. perf top) */
+			if (env->arch)
+				tui__header_window(env);
+			continue;
+		case 'F':
+			symbol_conf.filter_relative ^= 1;
+			continue;
+		case K_F1:
+		case 'h':
+		case '?':
+			ui_browser__help_window(&browser->b,
+				is_report_browser(hbt) ? report_help : top_help);
+			continue;
+		case K_ENTER:
+		case K_RIGHT:
+			/* menu */
+			break;
+		case K_LEFT: {
+			const void *top;
+
+			if (pstack__empty(fstack)) {
+				/*
+				 * Go back to the perf_evsel_menu__run or other user
+				 */
+				if (left_exits)
+					goto out_free_stack;
+				continue;
+			}
+			top = pstack__pop(fstack);
+			if (top == &browser->hists->dso_filter)
+				goto zoom_out_dso;
+			if (top == &browser->hists->thread_filter)
+				goto zoom_out_thread;
+			continue;
+		}
+		case K_ESC:
+			if (!left_exits &&
+			    !ui_browser__dialog_yesno(&browser->b,
+					       "Do you really want to exit?"))
+				continue;
+			/* Fall thru */
+		case 'q':
+		case CTRL('c'):
+			goto out_free_stack;
+		default:
+			continue;
+		}
+
+		if (!sort__has_sym)
+			goto add_exit_option;
+
+		if (sort__mode == SORT_MODE__BRANCH) {
+			bi = browser->he_selection->branch_info;
+			if (browser->selection != NULL &&
+			    bi &&
+			    bi->from.sym != NULL &&
+			    !bi->from.map->dso->annotate_warned &&
+				asprintf(&options[nr_options], "Annotate %s",
+					 bi->from.sym->name) > 0)
+				annotate_f = nr_options++;
+
+			if (browser->selection != NULL &&
+			    bi &&
+			    bi->to.sym != NULL &&
+			    !bi->to.map->dso->annotate_warned &&
+			    (bi->to.sym != bi->from.sym ||
+			     bi->to.map->dso != bi->from.map->dso) &&
+				asprintf(&options[nr_options], "Annotate %s",
+					 bi->to.sym->name) > 0)
+				annotate_t = nr_options++;
+		} else {
+			if (browser->selection != NULL &&
+			    browser->selection->sym != NULL &&
+			    !browser->selection->map->dso->annotate_warned) {
+				struct annotation *notes;
+
+				notes = symbol__annotation(browser->selection->sym);
+
+				if (notes->src &&
+				    asprintf(&options[nr_options], "Annotate %s",
+						 browser->selection->sym->name) > 0)
+					annotate = nr_options++;
+			}
+		}
+
+		if (thread != NULL &&
+		    asprintf(&options[nr_options], "Zoom %s %s(%d) thread",
+			     (browser->hists->thread_filter ? "out of" : "into"),
+			     (thread->comm_set ? thread__comm_str(thread) : ""),
+			     thread->tid) > 0)
+			zoom_thread = nr_options++;
+
+		if (dso != NULL &&
+		    asprintf(&options[nr_options], "Zoom %s %s DSO",
+			     (browser->hists->dso_filter ? "out of" : "into"),
+			     (dso->kernel ? "the Kernel" : dso->short_name)) > 0)
+			zoom_dso = nr_options++;
+
+		if (browser->selection != NULL &&
+		    browser->selection->map != NULL &&
+		    asprintf(&options[nr_options], "Browse map details") > 0)
+			browse_map = nr_options++;
+
+		/* perf script support */
+		if (browser->he_selection) {
+			struct symbol *sym;
+
+			if (asprintf(&options[nr_options], "Run scripts for samples of thread [%s]",
+				     thread__comm_str(browser->he_selection->thread)) > 0)
+				scripts_comm = nr_options++;
+
+			sym = browser->he_selection->ms.sym;
+			if (sym && sym->namelen &&
+				asprintf(&options[nr_options], "Run scripts for samples of symbol [%s]",
+						sym->name) > 0)
+				scripts_symbol = nr_options++;
+		}
+
+		if (asprintf(&options[nr_options], "Run scripts for all samples") > 0)
+			scripts_all = nr_options++;
+
+		if (is_report_browser(hbt) && asprintf(&options[nr_options],
+				"Switch to another data file in PWD") > 0)
+			switch_data = nr_options++;
+add_exit_option:
+		options[nr_options++] = (char *)"Exit";
+retry_popup_menu:
+		choice = ui__popup_menu(nr_options, options);
+
+		if (choice == nr_options - 1)
+			break;
+
+		if (choice == -1) {
+			free_popup_options(options, nr_options - 1);
+			continue;
+		}
+
+		if (choice == annotate || choice == annotate_t || choice == annotate_f) {
+			struct hist_entry *he;
+			struct annotation *notes;
+			int err;
+do_annotate:
+			if (!objdump_path && perf_session_env__lookup_objdump(env))
+				continue;
+
+			he = hist_browser__selected_entry(browser);
+			if (he == NULL)
+				continue;
+
+			/*
+			 * we stash the branch_info symbol + map into the
+			 * the ms so we don't have to rewrite all the annotation
+			 * code to use branch_info.
+			 * in branch mode, the ms struct is not used
+			 */
+			if (choice == annotate_f) {
+				he->ms.sym = he->branch_info->from.sym;
+				he->ms.map = he->branch_info->from.map;
+			}  else if (choice == annotate_t) {
+				he->ms.sym = he->branch_info->to.sym;
+				he->ms.map = he->branch_info->to.map;
+			}
+
+			notes = symbol__annotation(he->ms.sym);
+			if (!notes->src)
+				continue;
+
+			/*
+			 * Don't let this be freed, say, by hists__decay_entry.
+			 */
+			he->used = true;
+			err = hist_entry__tui_annotate(he, evsel, hbt);
+			he->used = false;
+			/*
+			 * offer option to annotate the other branch source or target
+			 * (if they exists) when returning from annotate
+			 */
+			if ((err == 'q' || err == CTRL('c'))
+			    && annotate_t != -2 && annotate_f != -2)
+				goto retry_popup_menu;
+
+			ui_browser__update_nr_entries(&browser->b, browser->hists->nr_entries);
+			if (err)
+				ui_browser__handle_resize(&browser->b);
+
+		} else if (choice == browse_map)
+			map__browse(browser->selection->map);
+		else if (choice == zoom_dso) {
+zoom_dso:
+			if (browser->hists->dso_filter) {
+				pstack__remove(fstack, &browser->hists->dso_filter);
+zoom_out_dso:
+				ui_helpline__pop();
+				browser->hists->dso_filter = NULL;
+				perf_hpp__set_elide(HISTC_DSO, false);
+			} else {
+				if (dso == NULL)
+					continue;
+				ui_helpline__fpush("To zoom out press <- or -> + \"Zoom out of %s DSO\"",
+						   dso->kernel ? "the Kernel" : dso->short_name);
+				browser->hists->dso_filter = dso;
+				perf_hpp__set_elide(HISTC_DSO, true);
+				pstack__push(fstack, &browser->hists->dso_filter);
+			}
+			hists__filter_by_dso(hists);
+			hist_browser__reset(browser);
+		} else if (choice == zoom_thread) {
+zoom_thread:
+			if (browser->hists->thread_filter) {
+				pstack__remove(fstack, &browser->hists->thread_filter);
+zoom_out_thread:
+				ui_helpline__pop();
+				browser->hists->thread_filter = NULL;
+				perf_hpp__set_elide(HISTC_THREAD, false);
+			} else {
+				ui_helpline__fpush("To zoom out press <- or -> + \"Zoom out of %s(%d) thread\"",
+						   thread->comm_set ? thread__comm_str(thread) : "",
+						   thread->tid);
+				browser->hists->thread_filter = thread;
+				perf_hpp__set_elide(HISTC_THREAD, false);
+				pstack__push(fstack, &browser->hists->thread_filter);
+			}
+			hists__filter_by_thread(hists);
+			hist_browser__reset(browser);
+		}
+		/* perf scripts support */
+		else if (choice == scripts_all || choice == scripts_comm ||
+				choice == scripts_symbol) {
+do_scripts:
+			memset(script_opt, 0, 64);
+
+			if (choice == scripts_comm)
+				sprintf(script_opt, " -c %s ", thread__comm_str(browser->he_selection->thread));
+
+			if (choice == scripts_symbol)
+				sprintf(script_opt, " -S %s ", browser->he_selection->ms.sym->name);
+
+			script_browse(script_opt);
+		}
+		/* Switch to another data file */
+		else if (choice == switch_data) {
+do_data_switch:
+			if (!switch_data_file()) {
+				key = K_SWITCH_INPUT_DATA;
+				break;
+			} else
+				ui__warning("Won't switch the data files due to\n"
+					"no valid data file get selected!\n");
+		}
+	}
+out_free_stack:
+	pstack__delete(fstack);
+out:
+	hist_browser__delete(browser);
+	free_popup_options(options, nr_options - 1);
+	return key;
+}
+
+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;
+};
+
+static void perf_evsel_menu__write(struct ui_browser *browser,
+				   void *entry, int row)
+{
+	struct perf_evsel_menu *menu = container_of(browser,
+						    struct perf_evsel_menu, b);
+	struct perf_evsel *evsel = list_entry(entry, struct perf_evsel, node);
+	bool current_entry = ui_browser__is_current_entry(browser, row);
+	unsigned long nr_events = evsel->hists.stats.nr_events[PERF_RECORD_SAMPLE];
+	const char *ev_name = perf_evsel__name(evsel);
+	char bf[256], unit;
+	const char *warn = " ";
+	size_t printed;
+
+	ui_browser__set_color(browser, current_entry ? HE_COLORSET_SELECTED :
+						       HE_COLORSET_NORMAL);
+
+	if (perf_evsel__is_group_event(evsel)) {
+		struct perf_evsel *pos;
+
+		ev_name = perf_evsel__group_name(evsel);
+
+		for_each_group_member(pos, evsel) {
+			nr_events += pos->hists.stats.nr_events[PERF_RECORD_SAMPLE];
+		}
+	}
+
+	nr_events = convert_unit(nr_events, &unit);
+	printed = scnprintf(bf, sizeof(bf), "%lu%c%s%s", nr_events,
+			   unit, unit == ' ' ? "" : " ", ev_name);
+	slsmg_printf("%s", bf);
+
+	nr_events = evsel->hists.stats.nr_events[PERF_RECORD_LOST];
+	if (nr_events != 0) {
+		menu->lost_events = true;
+		if (!current_entry)
+			ui_browser__set_color(browser, HE_COLORSET_TOP);
+		nr_events = convert_unit(nr_events, &unit);
+		printed += scnprintf(bf, sizeof(bf), ": %ld%c%schunks LOST!",
+				     nr_events, unit, unit == ' ' ? "" : " ");
+		warn = bf;
+	}
+
+	slsmg_write_nstring(warn, browser->width - printed);
+
+	if (current_entry)
+		menu->selection = evsel;
+}
+
+static int perf_evsel_menu__run(struct perf_evsel_menu *menu,
+				int nr_events, const char *help,
+				struct hist_browser_timer *hbt)
+{
+	struct perf_evlist *evlist = menu->b.priv;
+	struct perf_evsel *pos;
+	const char *ev_name, *title = "Available samples";
+	int delay_secs = hbt ? hbt->refresh : 0;
+	int key;
+
+	if (ui_browser__show(&menu->b, title,
+			     "ESC: exit, ENTER|->: Browse histograms") < 0)
+		return -1;
+
+	while (1) {
+		key = ui_browser__run(&menu->b, delay_secs);
+
+		switch (key) {
+		case K_TIMER:
+			hbt->timer(hbt->arg);
+
+			if (!menu->lost_events_warned && menu->lost_events) {
+				ui_browser__warn_lost_events(&menu->b);
+				menu->lost_events_warned = true;
+			}
+			continue;
+		case K_RIGHT:
+		case K_ENTER:
+			if (!menu->selection)
+				continue;
+			pos = menu->selection;
+browse_hists:
+			perf_evlist__set_selected(evlist, pos);
+			/*
+			 * Give the calling tool a chance to populate the non
+			 * default evsel resorted hists tree.
+			 */
+			if (hbt)
+				hbt->timer(hbt->arg);
+			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) {
+			case K_TAB:
+				if (pos->node.next == &evlist->entries)
+					pos = perf_evlist__first(evlist);
+				else
+					pos = perf_evsel__next(pos);
+				goto browse_hists;
+			case K_UNTAB:
+				if (pos->node.prev == &evlist->entries)
+					pos = perf_evlist__last(evlist);
+				else
+					pos = perf_evsel__prev(pos);
+				goto browse_hists;
+			case K_ESC:
+				if (!ui_browser__dialog_yesno(&menu->b,
+						"Do you really want to exit?"))
+					continue;
+				/* Fall thru */
+			case K_SWITCH_INPUT_DATA:
+			case 'q':
+			case CTRL('c'):
+				goto out;
+			default:
+				continue;
+			}
+		case K_LEFT:
+			continue;
+		case K_ESC:
+			if (!ui_browser__dialog_yesno(&menu->b,
+					       "Do you really want to exit?"))
+				continue;
+			/* Fall thru */
+		case 'q':
+		case CTRL('c'):
+			goto out;
+		default:
+			continue;
+		}
+	}
+
+out:
+	ui_browser__hide(&menu->b);
+	return key;
+}
+
+static bool filter_group_entries(struct ui_browser *browser __maybe_unused,
+				 void *entry)
+{
+	struct perf_evsel *evsel = list_entry(entry, struct perf_evsel, node);
+
+	if (symbol_conf.event_group && !perf_evsel__is_group_leader(evsel))
+		return true;
+
+	return false;
+}
+
+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;
+	struct perf_evsel_menu menu = {
+		.b = {
+			.entries    = &evlist->entries,
+			.refresh    = ui_browser__list_head_refresh,
+			.seek	    = ui_browser__list_head_seek,
+			.write	    = perf_evsel_menu__write,
+			.filter	    = filter_group_entries,
+			.nr_entries = nr_entries,
+			.priv	    = evlist,
+		},
+		.min_pcnt = min_pcnt,
+		.env = env,
+	};
+
+	ui_helpline__push("Press ESC to exit");
+
+	evlist__for_each(evlist, pos) {
+		const char *ev_name = perf_evsel__name(pos);
+		size_t line_len = strlen(ev_name) + 7;
+
+		if (menu.b.width < line_len)
+			menu.b.width = line_len;
+	}
+
+	return perf_evsel_menu__run(&menu, nr_entries, help, hbt);
+}
+
+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;
+
+single_entry:
+	if (nr_entries == 1) {
+		struct perf_evsel *first = perf_evlist__first(evlist);
+		const char *ev_name = perf_evsel__name(first);
+
+		return perf_evsel__hists_browse(first, nr_entries, help,
+						ev_name, false, hbt, min_pcnt,
+						env);
+	}
+
+	if (symbol_conf.event_group) {
+		struct perf_evsel *pos;
+
+		nr_entries = 0;
+		evlist__for_each(evlist, pos) {
+			if (perf_evsel__is_group_leader(pos))
+				nr_entries++;
+		}
+
+		if (nr_entries == 1)
+			goto single_entry;
+	}
+
+	return __perf_evlist__tui_browse_hists(evlist, nr_entries, help,
+					       hbt, min_pcnt, env);
+}
diff --git a/tools/perf/ui/browsers/map.c b/tools/perf/ui/browsers/map.c
new file mode 100644
index 00000000000..b11639f3368
--- /dev/null
+++ b/tools/perf/ui/browsers/map.c
@@ -0,0 +1,130 @@
+#include "../libslang.h"
+#include <elf.h>
+#include <inttypes.h>
+#include <sys/ttydefaults.h>
+#include <string.h>
+#include <linux/bitops.h>
+#include "../../util/util.h"
+#include "../../util/debug.h"
+#include "../../util/symbol.h"
+#include "../browser.h"
+#include "../helpline.h"
+#include "../keysyms.h"
+#include "map.h"
+
+struct map_browser {
+	struct ui_browser b;
+	struct map	  *map;
+	u8		  addrlen;
+};
+
+static void map_browser__write(struct ui_browser *browser, void *nd, int row)
+{
+	struct symbol *sym = rb_entry(nd, struct symbol, rb_node);
+	struct map_browser *mb = container_of(browser, struct map_browser, b);
+	bool current_entry = ui_browser__is_current_entry(browser, row);
+	int width;
+
+	ui_browser__set_percent_color(browser, 0, current_entry);
+	slsmg_printf("%*" PRIx64 " %*" PRIx64 " %c ",
+		     mb->addrlen, sym->start, mb->addrlen, sym->end,
+		     sym->binding == STB_GLOBAL ? 'g' :
+		     sym->binding == STB_LOCAL  ? 'l' : 'w');
+	width = browser->width - ((mb->addrlen * 2) + 4);
+	if (width > 0)
+		slsmg_write_nstring(sym->name, width);
+}
+
+/* FIXME uber-kludgy, see comment on cmd_report... */
+static u32 *symbol__browser_index(struct symbol *browser)
+{
+	return ((void *)browser) - sizeof(struct rb_node) - sizeof(u32);
+}
+
+static int map_browser__search(struct map_browser *browser)
+{
+	char target[512];
+	struct symbol *sym;
+	int err = ui_browser__input_window("Search by name/addr",
+					   "Prefix with 0x to search by address",
+					   target, "ENTER: OK, ESC: Cancel", 0);
+	if (err != K_ENTER)
+		return -1;
+
+	if (target[0] == '0' && tolower(target[1]) == 'x') {
+		u64 addr = strtoull(target, NULL, 16);
+		sym = map__find_symbol(browser->map, addr, NULL);
+	} else
+		sym = map__find_symbol_by_name(browser->map, target, NULL);
+
+	if (sym != NULL) {
+		u32 *idx = symbol__browser_index(sym);
+
+		browser->b.top = &sym->rb_node;
+		browser->b.index = browser->b.top_idx = *idx;
+	} else
+		ui_helpline__fpush("%s not found!", target);
+
+	return 0;
+}
+
+static int map_browser__run(struct map_browser *browser)
+{
+	int key;
+
+	if (ui_browser__show(&browser->b, browser->map->dso->long_name,
+			     "Press <- or ESC to exit, %s / to search",
+			     verbose ? "" : "restart with -v to use") < 0)
+		return -1;
+
+	while (1) {
+		key = ui_browser__run(&browser->b, 0);
+
+		switch (key) {
+		case '/':
+			if (verbose)
+				map_browser__search(browser);
+		default:
+			break;
+                case K_LEFT:
+                case K_ESC:
+                case 'q':
+                case CTRL('c'):
+                        goto out;
+		}
+	}
+out:
+	ui_browser__hide(&browser->b);
+	return key;
+}
+
+int map__browse(struct map *map)
+{
+	struct map_browser mb = {
+		.b = {
+			.entries = &map->dso->symbols[map->type],
+			.refresh = ui_browser__rb_tree_refresh,
+			.seek	 = ui_browser__rb_tree_seek,
+			.write	 = map_browser__write,
+		},
+		.map = map,
+	};
+	struct rb_node *nd;
+	char tmp[BITS_PER_LONG / 4];
+	u64 maxaddr = 0;
+
+	for (nd = rb_first(mb.b.entries); nd; nd = rb_next(nd)) {
+		struct symbol *pos = rb_entry(nd, struct symbol, rb_node);
+
+		if (maxaddr < pos->end)
+			maxaddr = pos->end;
+		if (verbose) {
+			u32 *idx = symbol__browser_index(pos);
+			*idx = mb.b.nr_entries;
+		}
+		++mb.b.nr_entries;
+	}
+
+	mb.addrlen = snprintf(tmp, sizeof(tmp), "%" PRIx64, maxaddr);
+	return map_browser__run(&mb);
+}
diff --git a/tools/perf/ui/browsers/map.h b/tools/perf/ui/browsers/map.h
new file mode 100644
index 00000000000..2d58e4b3eb6
--- /dev/null
+++ b/tools/perf/ui/browsers/map.h
@@ -0,0 +1,6 @@
+#ifndef _PERF_UI_MAP_BROWSER_H_
+#define _PERF_UI_MAP_BROWSER_H_ 1
+struct map;
+
+int map__browse(struct map *map);
+#endif /* _PERF_UI_MAP_BROWSER_H_ */
diff --git a/tools/perf/ui/browsers/scripts.c b/tools/perf/ui/browsers/scripts.c
new file mode 100644
index 00000000000..402d2bd30b0
--- /dev/null
+++ b/tools/perf/ui/browsers/scripts.c
@@ -0,0 +1,187 @@
+#include <elf.h>
+#include <inttypes.h>
+#include <sys/ttydefaults.h>
+#include <string.h>
+#include "../../util/sort.h"
+#include "../../util/util.h"
+#include "../../util/hist.h"
+#include "../../util/debug.h"
+#include "../../util/symbol.h"
+#include "../browser.h"
+#include "../helpline.h"
+#include "../libslang.h"
+
+/* 2048 lines should be enough for a script output */
+#define MAX_LINES		2048
+
+/* 160 bytes for one output line */
+#define AVERAGE_LINE_LEN	160
+
+struct script_line {
+	struct list_head node;
+	char line[AVERAGE_LINE_LEN];
+};
+
+struct perf_script_browser {
+	struct ui_browser b;
+	struct list_head entries;
+	const char *script_name;
+	int nr_lines;
+};
+
+#define SCRIPT_NAMELEN	128
+#define SCRIPT_MAX_NO	64
+/*
+ * Usually the full path for a script is:
+ *	/home/username/libexec/perf-core/scripts/python/xxx.py
+ *	/home/username/libexec/perf-core/scripts/perl/xxx.pl
+ * So 256 should be long enough to contain the full path.
+ */
+#define SCRIPT_FULLPATH_LEN	256
+
+/*
+ * When success, will copy the full path of the selected script
+ * into  the buffer pointed by script_name, and return 0.
+ * Return -1 on failure.
+ */
+static int list_scripts(char *script_name)
+{
+	char *buf, *names[SCRIPT_MAX_NO], *paths[SCRIPT_MAX_NO];
+	int i, num, choice, ret = -1;
+
+	/* Preset the script name to SCRIPT_NAMELEN */
+	buf = malloc(SCRIPT_MAX_NO * (SCRIPT_NAMELEN + SCRIPT_FULLPATH_LEN));
+	if (!buf)
+		return ret;
+
+	for (i = 0; i < SCRIPT_MAX_NO; i++) {
+		names[i] = buf + i * (SCRIPT_NAMELEN + SCRIPT_FULLPATH_LEN);
+		paths[i] = names[i] + SCRIPT_NAMELEN;
+	}
+
+	num = find_scripts(names, paths);
+	if (num > 0) {
+		choice = ui__popup_menu(num, names);
+		if (choice < num && choice >= 0) {
+			strcpy(script_name, paths[choice]);
+			ret = 0;
+		}
+	}
+
+	free(buf);
+	return ret;
+}
+
+static void script_browser__write(struct ui_browser *browser,
+				   void *entry, int row)
+{
+	struct script_line *sline = list_entry(entry, struct script_line, node);
+	bool current_entry = ui_browser__is_current_entry(browser, row);
+
+	ui_browser__set_color(browser, current_entry ? HE_COLORSET_SELECTED :
+						       HE_COLORSET_NORMAL);
+
+	slsmg_write_nstring(sline->line, browser->width);
+}
+
+static int script_browser__run(struct perf_script_browser *browser)
+{
+	int key;
+
+	if (ui_browser__show(&browser->b, browser->script_name,
+			     "Press <- or ESC to exit") < 0)
+		return -1;
+
+	while (1) {
+		key = ui_browser__run(&browser->b, 0);
+
+		/* We can add some special key handling here if needed */
+		break;
+	}
+
+	ui_browser__hide(&browser->b);
+	return key;
+}
+
+
+int script_browse(const char *script_opt)
+{
+	char cmd[SCRIPT_FULLPATH_LEN*2], script_name[SCRIPT_FULLPATH_LEN];
+	char *line = NULL;
+	size_t len = 0;
+	ssize_t retlen;
+	int ret = -1, nr_entries = 0;
+	FILE *fp;
+	void *buf;
+	struct script_line *sline;
+
+	struct perf_script_browser script = {
+		.b = {
+			.refresh    = ui_browser__list_head_refresh,
+			.seek	    = ui_browser__list_head_seek,
+			.write	    = script_browser__write,
+		},
+		.script_name = script_name,
+	};
+
+	INIT_LIST_HEAD(&script.entries);
+
+	/* Save each line of the output in one struct script_line object. */
+	buf = zalloc((sizeof(*sline)) * MAX_LINES);
+	if (!buf)
+		return -1;
+	sline = buf;
+
+	memset(script_name, 0, SCRIPT_FULLPATH_LEN);
+	if (list_scripts(script_name))
+		goto exit;
+
+	sprintf(cmd, "perf script -s %s ", script_name);
+
+	if (script_opt)
+		strcat(cmd, script_opt);
+
+	if (input_name) {
+		strcat(cmd, " -i ");
+		strcat(cmd, input_name);
+	}
+
+	strcat(cmd, " 2>&1");
+
+	fp = popen(cmd, "r");
+	if (!fp)
+		goto exit;
+
+	while ((retlen = getline(&line, &len, fp)) != -1) {
+		strncpy(sline->line, line, AVERAGE_LINE_LEN);
+
+		/* If one output line is very large, just cut it short */
+		if (retlen >= AVERAGE_LINE_LEN) {
+			sline->line[AVERAGE_LINE_LEN - 1] = '\0';
+			sline->line[AVERAGE_LINE_LEN - 2] = '\n';
+		}
+		list_add_tail(&sline->node, &script.entries);
+
+		if (script.b.width < retlen)
+			script.b.width = retlen;
+
+		if (nr_entries++ >= MAX_LINES - 1)
+			break;
+		sline++;
+	}
+
+	if (script.b.width > AVERAGE_LINE_LEN)
+		script.b.width = AVERAGE_LINE_LEN;
+
+	free(line);
+	pclose(fp);
+
+	script.nr_lines = nr_entries;
+	script.b.nr_entries = nr_entries;
+	script.b.entries = &script.entries;
+
+	ret = script_browser__run(&script);
+exit:
+	free(buf);
+	return ret;
+}
diff --git a/tools/perf/ui/gtk/annotate.c b/tools/perf/ui/gtk/annotate.c
new file mode 100644
index 00000000000..9c7ff8d31b2
--- /dev/null
+++ b/tools/perf/ui/gtk/annotate.c
@@ -0,0 +1,252 @@
+#include "gtk.h"
+#include "util/debug.h"
+#include "util/annotate.h"
+#include "util/evsel.h"
+#include "ui/helpline.h"
+
+
+enum {
+	ANN_COL__PERCENT,
+	ANN_COL__OFFSET,
+	ANN_COL__LINE,
+
+	MAX_ANN_COLS
+};
+
+static const char *const col_names[] = {
+	"Overhead",
+	"Offset",
+	"Line"
+};
+
+static int perf_gtk__get_percent(char *buf, size_t size, struct symbol *sym,
+				 struct disasm_line *dl, int evidx)
+{
+	struct sym_hist *symhist;
+	double percent = 0.0;
+	const char *markup;
+	int ret = 0;
+
+	strcpy(buf, "");
+
+	if (dl->offset == (s64) -1)
+		return 0;
+
+	symhist = annotation__histogram(symbol__annotation(sym), evidx);
+	if (!symbol_conf.event_group && !symhist->addr[dl->offset])
+		return 0;
+
+	percent = 100.0 * symhist->addr[dl->offset] / symhist->sum;
+
+	markup = perf_gtk__get_percent_color(percent);
+	if (markup)
+		ret += scnprintf(buf, size, "%s", markup);
+	ret += scnprintf(buf + ret, size - ret, "%6.2f%%", percent);
+	if (markup)
+		ret += scnprintf(buf + ret, size - ret, "</span>");
+
+	return ret;
+}
+
+static int perf_gtk__get_offset(char *buf, size_t size, struct symbol *sym,
+				struct map *map, struct disasm_line *dl)
+{
+	u64 start = map__rip_2objdump(map, sym->start);
+
+	strcpy(buf, "");
+
+	if (dl->offset == (s64) -1)
+		return 0;
+
+	return scnprintf(buf, size, "%"PRIx64, start + dl->offset);
+}
+
+static int perf_gtk__get_line(char *buf, size_t size, struct disasm_line *dl)
+{
+	int ret = 0;
+	char *line = g_markup_escape_text(dl->line, -1);
+	const char *markup = "<span fgcolor='gray'>";
+
+	strcpy(buf, "");
+
+	if (!line)
+		return 0;
+
+	if (dl->offset != (s64) -1)
+		markup = NULL;
+
+	if (markup)
+		ret += scnprintf(buf, size, "%s", markup);
+	ret += scnprintf(buf + ret, size - ret, "%s", line);
+	if (markup)
+		ret += scnprintf(buf + ret, size - ret, "</span>");
+
+	g_free(line);
+	return ret;
+}
+
+static int perf_gtk__annotate_symbol(GtkWidget *window, struct symbol *sym,
+				struct map *map, struct perf_evsel *evsel,
+				struct hist_browser_timer *hbt __maybe_unused)
+{
+	struct disasm_line *pos, *n;
+	struct annotation *notes;
+	GType col_types[MAX_ANN_COLS];
+	GtkCellRenderer *renderer;
+	GtkListStore *store;
+	GtkWidget *view;
+	int i;
+	char s[512];
+
+	notes = symbol__annotation(sym);
+
+	for (i = 0; i < MAX_ANN_COLS; i++) {
+		col_types[i] = G_TYPE_STRING;
+	}
+	store = gtk_list_store_newv(MAX_ANN_COLS, col_types);
+
+	view = gtk_tree_view_new();
+	renderer = gtk_cell_renderer_text_new();
+
+	for (i = 0; i < MAX_ANN_COLS; i++) {
+		gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view),
+					-1, col_names[i], renderer, "markup",
+					i, NULL);
+	}
+
+	gtk_tree_view_set_model(GTK_TREE_VIEW(view), GTK_TREE_MODEL(store));
+	g_object_unref(GTK_TREE_MODEL(store));
+
+	list_for_each_entry(pos, &notes->src->source, node) {
+		GtkTreeIter iter;
+		int ret = 0;
+
+		gtk_list_store_append(store, &iter);
+
+		if (perf_evsel__is_group_event(evsel)) {
+			for (i = 0; i < evsel->nr_members; i++) {
+				ret += perf_gtk__get_percent(s + ret,
+							     sizeof(s) - ret,
+							     sym, pos,
+							     evsel->idx + i);
+				ret += scnprintf(s + ret, sizeof(s) - ret, " ");
+			}
+		} else {
+			ret = perf_gtk__get_percent(s, sizeof(s), sym, pos,
+						    evsel->idx);
+		}
+
+		if (ret)
+			gtk_list_store_set(store, &iter, ANN_COL__PERCENT, s, -1);
+		if (perf_gtk__get_offset(s, sizeof(s), sym, map, pos))
+			gtk_list_store_set(store, &iter, ANN_COL__OFFSET, s, -1);
+		if (perf_gtk__get_line(s, sizeof(s), pos))
+			gtk_list_store_set(store, &iter, ANN_COL__LINE, s, -1);
+	}
+
+	gtk_container_add(GTK_CONTAINER(window), view);
+
+	list_for_each_entry_safe(pos, n, &notes->src->source, node) {
+		list_del(&pos->node);
+		disasm_line__free(pos);
+	}
+
+	return 0;
+}
+
+static int symbol__gtk_annotate(struct symbol *sym, struct map *map,
+				struct perf_evsel *evsel,
+				struct hist_browser_timer *hbt)
+{
+	GtkWidget *window;
+	GtkWidget *notebook;
+	GtkWidget *scrolled_window;
+	GtkWidget *tab_label;
+
+	if (map->dso->annotate_warned)
+		return -1;
+
+	if (symbol__annotate(sym, map, 0) < 0) {
+		ui__error("%s", ui_helpline__current);
+		return -1;
+	}
+
+	if (perf_gtk__is_active_context(pgctx)) {
+		window = pgctx->main_window;
+		notebook = pgctx->notebook;
+	} else {
+		GtkWidget *vbox;
+		GtkWidget *infobar;
+		GtkWidget *statbar;
+
+		signal(SIGSEGV, perf_gtk__signal);
+		signal(SIGFPE,  perf_gtk__signal);
+		signal(SIGINT,  perf_gtk__signal);
+		signal(SIGQUIT, perf_gtk__signal);
+		signal(SIGTERM, perf_gtk__signal);
+
+		window = gtk_window_new(GTK_WINDOW_TOPLEVEL);
+		gtk_window_set_title(GTK_WINDOW(window), "perf annotate");
+
+		g_signal_connect(window, "delete_event", gtk_main_quit, NULL);
+
+		pgctx = perf_gtk__activate_context(window);
+		if (!pgctx)
+			return -1;
+
+		vbox = gtk_vbox_new(FALSE, 0);
+		notebook = gtk_notebook_new();
+		pgctx->notebook = notebook;
+
+		gtk_box_pack_start(GTK_BOX(vbox), notebook, TRUE, TRUE, 0);
+
+		infobar = perf_gtk__setup_info_bar();
+		if (infobar) {
+			gtk_box_pack_start(GTK_BOX(vbox), infobar,
+					   FALSE, FALSE, 0);
+		}
+
+		statbar = perf_gtk__setup_statusbar();
+		gtk_box_pack_start(GTK_BOX(vbox), statbar, FALSE, FALSE, 0);
+
+		gtk_container_add(GTK_CONTAINER(window), vbox);
+	}
+
+	scrolled_window = gtk_scrolled_window_new(NULL, NULL);
+	tab_label = gtk_label_new(sym->name);
+
+	gtk_scrolled_window_set_policy(GTK_SCROLLED_WINDOW(scrolled_window),
+				       GTK_POLICY_AUTOMATIC,
+				       GTK_POLICY_AUTOMATIC);
+
+	gtk_notebook_append_page(GTK_NOTEBOOK(notebook), scrolled_window,
+				 tab_label);
+
+	perf_gtk__annotate_symbol(scrolled_window, sym, map, evsel, hbt);
+	return 0;
+}
+
+int hist_entry__gtk_annotate(struct hist_entry *he,
+			     struct perf_evsel *evsel,
+			     struct hist_browser_timer *hbt)
+{
+	return symbol__gtk_annotate(he->ms.sym, he->ms.map, evsel, hbt);
+}
+
+void perf_gtk__show_annotations(void)
+{
+	GtkWidget *window;
+
+	if (!perf_gtk__is_active_context(pgctx))
+		return;
+
+	window = pgctx->main_window;
+	gtk_widget_show_all(window);
+
+	perf_gtk__resize_window(window);
+	gtk_window_set_position(GTK_WINDOW(window), GTK_WIN_POS_CENTER);
+
+	gtk_main();
+
+	perf_gtk__deactivate_context(&pgctx);
+}
diff --git a/tools/perf/ui/gtk/browser.c b/tools/perf/ui/gtk/browser.c
new file mode 100644
index 00000000000..c24d9122129
--- /dev/null
+++ b/tools/perf/ui/gtk/browser.c
@@ -0,0 +1,87 @@
+#include "../evlist.h"
+#include "../cache.h"
+#include "../evsel.h"
+#include "../sort.h"
+#include "../hist.h"
+#include "../helpline.h"
+#include "gtk.h"
+
+#include <signal.h>
+
+void perf_gtk__signal(int sig)
+{
+	perf_gtk__exit(false);
+	psignal(sig, "perf");
+}
+
+void perf_gtk__resize_window(GtkWidget *window)
+{
+	GdkRectangle rect;
+	GdkScreen *screen;
+	int monitor;
+	int height;
+	int width;
+
+	screen = gtk_widget_get_screen(window);
+
+	monitor = gdk_screen_get_monitor_at_window(screen, window->window);
+
+	gdk_screen_get_monitor_geometry(screen, monitor, &rect);
+
+	width	= rect.width * 3 / 4;
+	height	= rect.height * 3 / 4;
+
+	gtk_window_resize(GTK_WINDOW(window), width, height);
+}
+
+const char *perf_gtk__get_percent_color(double percent)
+{
+	if (percent >= MIN_RED)
+		return "<span fgcolor='red'>";
+	if (percent >= MIN_GREEN)
+		return "<span fgcolor='dark green'>";
+	return NULL;
+}
+
+#ifdef HAVE_GTK_INFO_BAR_SUPPORT
+GtkWidget *perf_gtk__setup_info_bar(void)
+{
+	GtkWidget *info_bar;
+	GtkWidget *label;
+	GtkWidget *content_area;
+
+	info_bar = gtk_info_bar_new();
+	gtk_widget_set_no_show_all(info_bar, TRUE);
+
+	label = gtk_label_new("");
+	gtk_widget_show(label);
+
+	content_area = gtk_info_bar_get_content_area(GTK_INFO_BAR(info_bar));
+	gtk_container_add(GTK_CONTAINER(content_area), label);
+
+	gtk_info_bar_add_button(GTK_INFO_BAR(info_bar), GTK_STOCK_OK,
+				GTK_RESPONSE_OK);
+	g_signal_connect(info_bar, "response",
+			 G_CALLBACK(gtk_widget_hide), NULL);
+
+	pgctx->info_bar = info_bar;
+	pgctx->message_label = label;
+
+	return info_bar;
+}
+#endif
+
+GtkWidget *perf_gtk__setup_statusbar(void)
+{
+	GtkWidget *stbar;
+	unsigned ctxid;
+
+	stbar = gtk_statusbar_new();
+
+	ctxid = gtk_statusbar_get_context_id(GTK_STATUSBAR(stbar),
+					     "perf report");
+	pgctx->statbar = stbar;
+	pgctx->statbar_ctx_id = ctxid;
+
+	return stbar;
+}
diff --git a/tools/perf/ui/gtk/gtk.h b/tools/perf/ui/gtk/gtk.h
new file mode 100644
index 00000000000..0a9173ff9a6
--- /dev/null
+++ b/tools/perf/ui/gtk/gtk.h
@@ -0,0 +1,67 @@
+#ifndef _PERF_GTK_H_
+#define _PERF_GTK_H_ 1
+
+#include <stdbool.h>
+
+#pragma GCC diagnostic ignored "-Wstrict-prototypes"
+#include <gtk/gtk.h>
+#pragma GCC diagnostic error "-Wstrict-prototypes"
+
+
+struct perf_gtk_context {
+	GtkWidget *main_window;
+	GtkWidget *notebook;
+
+#ifdef HAVE_GTK_INFO_BAR_SUPPORT
+	GtkWidget *info_bar;
+	GtkWidget *message_label;
+#endif
+	GtkWidget *statbar;
+	guint statbar_ctx_id;
+};
+
+int perf_gtk__init(void);
+void perf_gtk__exit(bool wait_for_ok);
+
+extern struct perf_gtk_context *pgctx;
+
+static inline bool perf_gtk__is_active_context(struct perf_gtk_context *ctx)
+{
+	return ctx && ctx->main_window;
+}
+
+struct perf_gtk_context *perf_gtk__activate_context(GtkWidget *window);
+int perf_gtk__deactivate_context(struct perf_gtk_context **ctx);
+
+void perf_gtk__init_helpline(void);
+void gtk_ui_progress__init(void);
+void perf_gtk__init_hpp(void);
+
+void perf_gtk__signal(int sig);
+void perf_gtk__resize_window(GtkWidget *window);
+const char *perf_gtk__get_percent_color(double percent);
+GtkWidget *perf_gtk__setup_statusbar(void);
+
+#ifdef HAVE_GTK_INFO_BAR_SUPPORT
+GtkWidget *perf_gtk__setup_info_bar(void);
+#else
+static inline GtkWidget *perf_gtk__setup_info_bar(void)
+{
+	return NULL;
+}
+#endif
+
+struct perf_evsel;
+struct perf_evlist;
+struct hist_entry;
+struct hist_browser_timer;
+
+int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist, const char *help,
+				  struct hist_browser_timer *hbt,
+				  float min_pcnt);
+int hist_entry__gtk_annotate(struct hist_entry *he,
+			     struct perf_evsel *evsel,
+			     struct hist_browser_timer *hbt);
+void perf_gtk__show_annotations(void);
+
+#endif /* _PERF_GTK_H_ */
diff --git a/tools/perf/ui/gtk/helpline.c b/tools/perf/ui/gtk/helpline.c
new file mode 100644
index 00000000000..3388cbd1218
--- /dev/null
+++ b/tools/perf/ui/gtk/helpline.c
@@ -0,0 +1,57 @@
+#include <stdio.h>
+#include <string.h>
+
+#include "gtk.h"
+#include "../ui.h"
+#include "../helpline.h"
+#include "../../util/debug.h"
+
+static void gtk_helpline_pop(void)
+{
+	if (!perf_gtk__is_active_context(pgctx))
+		return;
+
+	gtk_statusbar_pop(GTK_STATUSBAR(pgctx->statbar),
+			  pgctx->statbar_ctx_id);
+}
+
+static void gtk_helpline_push(const char *msg)
+{
+	if (!perf_gtk__is_active_context(pgctx))
+		return;
+
+	gtk_statusbar_push(GTK_STATUSBAR(pgctx->statbar),
+			   pgctx->statbar_ctx_id, msg);
+}
+
+static int gtk_helpline_show(const char *fmt, va_list ap)
+{
+	int ret;
+	char *ptr;
+	static int backlog;
+
+	ret = vscnprintf(ui_helpline__current + backlog,
+			 sizeof(ui_helpline__current) - backlog, fmt, ap);
+	backlog += ret;
+
+	/* only first line can be displayed */
+	ptr = strchr(ui_helpline__current, '\n');
+	if (ptr && (ptr - ui_helpline__current) <= backlog) {
+		*ptr = '\0';
+		ui_helpline__puts(ui_helpline__current);
+		backlog = 0;
+	}
+
+	return ret;
+}
+
+static struct ui_helpline gtk_helpline_fns = {
+	.pop	= gtk_helpline_pop,
+	.push	= gtk_helpline_push,
+	.show	= gtk_helpline_show,
+};
+
+void perf_gtk__init_helpline(void)
+{
+	helpline_fns = &gtk_helpline_fns;
+}
diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c
new file mode 100644
index 00000000000..6ca60e482cd
--- /dev/null
+++ b/tools/perf/ui/gtk/hists.c
@@ -0,0 +1,365 @@
+#include "../evlist.h"
+#include "../cache.h"
+#include "../evsel.h"
+#include "../sort.h"
+#include "../hist.h"
+#include "../helpline.h"
+#include "gtk.h"
+
+#define MAX_COLUMNS			32
+
+static int __percent_color_snprintf(struct perf_hpp *hpp, const char *fmt, ...)
+{
+	int ret = 0;
+	va_list args;
+	double percent;
+	const char *markup;
+	char *buf = hpp->buf;
+	size_t size = hpp->size;
+
+	va_start(args, fmt);
+	percent = va_arg(args, double);
+	va_end(args);
+
+	markup = perf_gtk__get_percent_color(percent);
+	if (markup)
+		ret += scnprintf(buf, size, markup);
+
+	ret += scnprintf(buf + ret, size - ret, fmt, percent);
+
+	if (markup)
+		ret += scnprintf(buf + ret, size - ret, "</span>");
+
+	return ret;
+}
+
+#define __HPP_COLOR_PERCENT_FN(_type, _field)					\
+static u64 he_get_##_field(struct hist_entry *he)				\
+{										\
+	return he->stat._field;							\
+}										\
+										\
+static int perf_gtk__hpp_color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,	\
+				       struct perf_hpp *hpp,			\
+				       struct hist_entry *he)			\
+{										\
+	return __hpp__fmt(hpp, he, he_get_##_field, " %6.2f%%",			\
+			  __percent_color_snprintf, true);			\
+}
+
+#define __HPP_COLOR_ACC_PERCENT_FN(_type, _field)				\
+static u64 he_get_acc_##_field(struct hist_entry *he)				\
+{										\
+	return he->stat_acc->_field;						\
+}										\
+										\
+static int perf_gtk__hpp_color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,	\
+				       struct perf_hpp *hpp,			\
+				       struct hist_entry *he)			\
+{										\
+	return __hpp__fmt_acc(hpp, he, he_get_acc_##_field, " %6.2f%%",		\
+			      __percent_color_snprintf, true);			\
+}
+
+__HPP_COLOR_PERCENT_FN(overhead, period)
+__HPP_COLOR_PERCENT_FN(overhead_sys, period_sys)
+__HPP_COLOR_PERCENT_FN(overhead_us, period_us)
+__HPP_COLOR_PERCENT_FN(overhead_guest_sys, period_guest_sys)
+__HPP_COLOR_PERCENT_FN(overhead_guest_us, period_guest_us)
+__HPP_COLOR_ACC_PERCENT_FN(overhead_acc, period)
+
+#undef __HPP_COLOR_PERCENT_FN
+
+
+void perf_gtk__init_hpp(void)
+{
+	perf_hpp__format[PERF_HPP__OVERHEAD].color =
+				perf_gtk__hpp_color_overhead;
+	perf_hpp__format[PERF_HPP__OVERHEAD_SYS].color =
+				perf_gtk__hpp_color_overhead_sys;
+	perf_hpp__format[PERF_HPP__OVERHEAD_US].color =
+				perf_gtk__hpp_color_overhead_us;
+	perf_hpp__format[PERF_HPP__OVERHEAD_GUEST_SYS].color =
+				perf_gtk__hpp_color_overhead_guest_sys;
+	perf_hpp__format[PERF_HPP__OVERHEAD_GUEST_US].color =
+				perf_gtk__hpp_color_overhead_guest_us;
+	perf_hpp__format[PERF_HPP__OVERHEAD_ACC].color =
+				perf_gtk__hpp_color_overhead_acc;
+}
+
+static void callchain_list__sym_name(struct callchain_list *cl,
+				     char *bf, size_t bfsize)
+{
+	if (cl->ms.sym)
+		scnprintf(bf, bfsize, "%s", cl->ms.sym->name);
+	else
+		scnprintf(bf, bfsize, "%#" PRIx64, cl->ip);
+}
+
+static void perf_gtk__add_callchain(struct rb_root *root, GtkTreeStore *store,
+				    GtkTreeIter *parent, int col, u64 total)
+{
+	struct rb_node *nd;
+	bool has_single_node = (rb_first(root) == rb_last(root));
+
+	for (nd = rb_first(root); nd; nd = rb_next(nd)) {
+		struct callchain_node *node;
+		struct callchain_list *chain;
+		GtkTreeIter iter, new_parent;
+		bool need_new_parent;
+		double percent;
+		u64 hits, child_total;
+
+		node = rb_entry(nd, struct callchain_node, rb_node);
+
+		hits = callchain_cumul_hits(node);
+		percent = 100.0 * hits / total;
+
+		new_parent = *parent;
+		need_new_parent = !has_single_node && (node->val_nr > 1);
+
+		list_for_each_entry(chain, &node->val, list) {
+			char buf[128];
+
+			gtk_tree_store_append(store, &iter, &new_parent);
+
+			scnprintf(buf, sizeof(buf), "%5.2f%%", percent);
+			gtk_tree_store_set(store, &iter, 0, buf, -1);
+
+			callchain_list__sym_name(chain, buf, sizeof(buf));
+			gtk_tree_store_set(store, &iter, col, buf, -1);
+
+			if (need_new_parent) {
+				/*
+				 * Only show the top-most symbol in a callchain
+				 * if it's not the only callchain.
+				 */
+				new_parent = iter;
+				need_new_parent = false;
+			}
+		}
+
+		if (callchain_param.mode == CHAIN_GRAPH_REL)
+			child_total = node->children_hit;
+		else
+			child_total = total;
+
+		/* Now 'iter' contains info of the last callchain_list */
+		perf_gtk__add_callchain(&node->rb_root, store, &iter, col,
+					child_total);
+	}
+}
+
+static void on_row_activated(GtkTreeView *view, GtkTreePath *path,
+			     GtkTreeViewColumn *col __maybe_unused,
+			     gpointer user_data __maybe_unused)
+{
+	bool expanded = gtk_tree_view_row_expanded(view, path);
+
+	if (expanded)
+		gtk_tree_view_collapse_row(view, path);
+	else
+		gtk_tree_view_expand_row(view, path, FALSE);
+}
+
+static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
+				 float min_pcnt)
+{
+	struct perf_hpp_fmt *fmt;
+	GType col_types[MAX_COLUMNS];
+	GtkCellRenderer *renderer;
+	GtkTreeStore *store;
+	struct rb_node *nd;
+	GtkWidget *view;
+	int col_idx;
+	int sym_col = -1;
+	int nr_cols;
+	char s[512];
+
+	struct perf_hpp hpp = {
+		.buf		= s,
+		.size		= sizeof(s),
+	};
+
+	nr_cols = 0;
+
+	perf_hpp__for_each_format(fmt)
+		col_types[nr_cols++] = G_TYPE_STRING;
+
+	store = gtk_tree_store_newv(nr_cols, col_types);
+
+	view = gtk_tree_view_new();
+
+	renderer = gtk_cell_renderer_text_new();
+
+	col_idx = 0;
+
+	perf_hpp__for_each_format(fmt) {
+		if (perf_hpp__should_skip(fmt))
+			continue;
+
+		/*
+		 * XXX no way to determine where symcol column is..
+		 *     Just use last column for now.
+		 */
+		if (perf_hpp__is_sort_entry(fmt))
+			sym_col = col_idx;
+
+		fmt->header(fmt, &hpp, hists_to_evsel(hists));
+
+		gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view),
+							    -1, ltrim(s),
+							    renderer, "markup",
+							    col_idx++, NULL);
+	}
+
+	for (col_idx = 0; col_idx < nr_cols; col_idx++) {
+		GtkTreeViewColumn *column;
+
+		column = gtk_tree_view_get_column(GTK_TREE_VIEW(view), col_idx);
+		gtk_tree_view_column_set_resizable(column, TRUE);
+
+		if (col_idx == sym_col) {
+			gtk_tree_view_set_expander_column(GTK_TREE_VIEW(view),
+							  column);
+		}
+	}
+
+	gtk_tree_view_set_model(GTK_TREE_VIEW(view), GTK_TREE_MODEL(store));
+
+	g_object_unref(GTK_TREE_MODEL(store));
+
+	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;
+		u64 total = hists__total_period(h->hists);
+		float percent;
+
+		if (h->filtered)
+			continue;
+
+		percent = hist_entry__get_percent_limit(h);
+		if (percent < min_pcnt)
+			continue;
+
+		gtk_tree_store_append(store, &iter, NULL);
+
+		col_idx = 0;
+
+		perf_hpp__for_each_format(fmt) {
+			if (perf_hpp__should_skip(fmt))
+				continue;
+
+			if (fmt->color)
+				fmt->color(fmt, &hpp, h);
+			else
+				fmt->entry(fmt, &hpp, h);
+
+			gtk_tree_store_set(store, &iter, col_idx++, s, -1);
+		}
+
+		if (symbol_conf.use_callchain && sort__has_sym) {
+			if (callchain_param.mode == CHAIN_GRAPH_REL)
+				total = symbol_conf.cumulate_callchain ?
+					h->stat_acc->period : h->stat.period;
+
+			perf_gtk__add_callchain(&h->sorted_chain, store, &iter,
+						sym_col, total);
+		}
+	}
+
+	gtk_tree_view_set_rules_hint(GTK_TREE_VIEW(view), TRUE);
+
+	g_signal_connect(view, "row-activated",
+			 G_CALLBACK(on_row_activated), NULL);
+	gtk_container_add(GTK_CONTAINER(window), view);
+}
+
+int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist,
+				  const char *help,
+				  struct hist_browser_timer *hbt __maybe_unused,
+				  float min_pcnt)
+{
+	struct perf_evsel *pos;
+	GtkWidget *vbox;
+	GtkWidget *notebook;
+	GtkWidget *info_bar;
+	GtkWidget *statbar;
+	GtkWidget *window;
+
+	signal(SIGSEGV, perf_gtk__signal);
+	signal(SIGFPE,  perf_gtk__signal);
+	signal(SIGINT,  perf_gtk__signal);
+	signal(SIGQUIT, perf_gtk__signal);
+	signal(SIGTERM, perf_gtk__signal);
+
+	window = gtk_window_new(GTK_WINDOW_TOPLEVEL);
+
+	gtk_window_set_title(GTK_WINDOW(window), "perf report");
+
+	g_signal_connect(window, "delete_event", gtk_main_quit, NULL);
+
+	pgctx = perf_gtk__activate_context(window);
+	if (!pgctx)
+		return -1;
+
+	vbox = gtk_vbox_new(FALSE, 0);
+
+	notebook = gtk_notebook_new();
+
+	gtk_box_pack_start(GTK_BOX(vbox), notebook, TRUE, TRUE, 0);
+
+	info_bar = perf_gtk__setup_info_bar();
+	if (info_bar)
+		gtk_box_pack_start(GTK_BOX(vbox), info_bar, FALSE, FALSE, 0);
+
+	statbar = perf_gtk__setup_statusbar();
+	gtk_box_pack_start(GTK_BOX(vbox), statbar, FALSE, FALSE, 0);
+
+	gtk_container_add(GTK_CONTAINER(window), vbox);
+
+	evlist__for_each(evlist, pos) {
+		struct hists *hists = &pos->hists;
+		const char *evname = perf_evsel__name(pos);
+		GtkWidget *scrolled_window;
+		GtkWidget *tab_label;
+		char buf[512];
+		size_t size = sizeof(buf);
+
+		if (symbol_conf.event_group) {
+			if (!perf_evsel__is_group_leader(pos))
+				continue;
+
+			if (pos->nr_members > 1) {
+				perf_evsel__group_desc(pos, buf, size);
+				evname = buf;
+			}
+		}
+
+		scrolled_window = gtk_scrolled_window_new(NULL, NULL);
+
+		gtk_scrolled_window_set_policy(GTK_SCROLLED_WINDOW(scrolled_window),
+							GTK_POLICY_AUTOMATIC,
+							GTK_POLICY_AUTOMATIC);
+
+		perf_gtk__show_hists(scrolled_window, hists, min_pcnt);
+
+		tab_label = gtk_label_new(evname);
+
+		gtk_notebook_append_page(GTK_NOTEBOOK(notebook), scrolled_window, tab_label);
+	}
+
+	gtk_widget_show_all(window);
+
+	perf_gtk__resize_window(window);
+
+	gtk_window_set_position(GTK_WINDOW(window), GTK_WIN_POS_CENTER);
+
+	ui_helpline__push(help);
+
+	gtk_main();
+
+	perf_gtk__deactivate_context(&pgctx);
+
+	return 0;
+}
diff --git a/tools/perf/ui/gtk/progress.c b/tools/perf/ui/gtk/progress.c
new file mode 100644
index 00000000000..b656655fbc3
--- /dev/null
+++ b/tools/perf/ui/gtk/progress.c
@@ -0,0 +1,59 @@
+#include <inttypes.h>
+
+#include "gtk.h"
+#include "../progress.h"
+#include "util.h"
+
+static GtkWidget *dialog;
+static GtkWidget *progress;
+
+static void gtk_ui_progress__update(struct ui_progress *p)
+{
+	double fraction = p->total ? 1.0 * p->curr / p->total : 0.0;
+	char buf[1024];
+
+	if (dialog == NULL) {
+		GtkWidget *vbox = gtk_vbox_new(TRUE, 5);
+		GtkWidget *label = gtk_label_new(p->title);
+
+		dialog = gtk_window_new(GTK_WINDOW_TOPLEVEL);
+		progress = gtk_progress_bar_new();
+
+		gtk_box_pack_start(GTK_BOX(vbox), label, TRUE, FALSE, 3);
+		gtk_box_pack_start(GTK_BOX(vbox), progress, TRUE, TRUE, 3);
+
+		gtk_container_add(GTK_CONTAINER(dialog), vbox);
+
+		gtk_window_set_title(GTK_WINDOW(dialog), "perf");
+		gtk_window_resize(GTK_WINDOW(dialog), 300, 80);
+		gtk_window_set_position(GTK_WINDOW(dialog), GTK_WIN_POS_CENTER);
+
+		gtk_widget_show_all(dialog);
+	}
+
+	gtk_progress_bar_set_fraction(GTK_PROGRESS_BAR(progress), fraction);
+	snprintf(buf, sizeof(buf), "%"PRIu64" / %"PRIu64, p->curr, p->total);
+	gtk_progress_bar_set_text(GTK_PROGRESS_BAR(progress), buf);
+
+	/* we didn't call gtk_main yet, so do it manually */
+	while (gtk_events_pending())
+		gtk_main_iteration();
+}
+
+static void gtk_ui_progress__finish(void)
+{
+	/* this will also destroy all of its children */
+	gtk_widget_destroy(dialog);
+
+	dialog = NULL;
+}
+
+static struct ui_progress_ops gtk_ui_progress__ops = {
+	.update		= gtk_ui_progress__update,
+	.finish		= gtk_ui_progress__finish,
+};
+
+void gtk_ui_progress__init(void)
+{
+	ui_progress__ops = &gtk_ui_progress__ops;
+}
diff --git a/tools/perf/ui/gtk/setup.c b/tools/perf/ui/gtk/setup.c
new file mode 100644
index 00000000000..1d57676f821
--- /dev/null
+++ b/tools/perf/ui/gtk/setup.c
@@ -0,0 +1,23 @@
+#include "gtk.h"
+#include "../../util/cache.h"
+#include "../../util/debug.h"
+
+extern struct perf_error_ops perf_gtk_eops;
+
+int perf_gtk__init(void)
+{
+	perf_error__register(&perf_gtk_eops);
+	perf_gtk__init_helpline();
+	gtk_ui_progress__init();
+	perf_gtk__init_hpp();
+
+	return gtk_init_check(NULL, NULL) ? 0 : -1;
+}
+
+void perf_gtk__exit(bool wait_for_ok __maybe_unused)
+{
+	if (!perf_gtk__is_active_context(pgctx))
+		return;
+	perf_error__unregister(&perf_gtk_eops);
+	gtk_main_quit();
+}
diff --git a/tools/perf/ui/gtk/util.c b/tools/perf/ui/gtk/util.c
new file mode 100644
index 00000000000..52e7fc48af9
--- /dev/null
+++ b/tools/perf/ui/gtk/util.c
@@ -0,0 +1,112 @@
+#include "../util.h"
+#include "../../util/debug.h"
+#include "gtk.h"
+
+#include <string.h>
+
+
+struct perf_gtk_context *pgctx;
+
+struct perf_gtk_context *perf_gtk__activate_context(GtkWidget *window)
+{
+	struct perf_gtk_context *ctx;
+
+	ctx = malloc(sizeof(*pgctx));
+	if (ctx)
+		ctx->main_window = window;
+
+	return ctx;
+}
+
+int perf_gtk__deactivate_context(struct perf_gtk_context **ctx)
+{
+	if (!perf_gtk__is_active_context(*ctx))
+		return -1;
+
+	zfree(ctx);
+	return 0;
+}
+
+static int perf_gtk__error(const char *format, va_list args)
+{
+	char *msg;
+	GtkWidget *dialog;
+
+	if (!perf_gtk__is_active_context(pgctx) ||
+	    vasprintf(&msg, format, args) < 0) {
+		fprintf(stderr, "Error:\n");
+		vfprintf(stderr, format, args);
+		fprintf(stderr, "\n");
+		return -1;
+	}
+
+	dialog = gtk_message_dialog_new_with_markup(GTK_WINDOW(pgctx->main_window),
+					GTK_DIALOG_DESTROY_WITH_PARENT,
+					GTK_MESSAGE_ERROR,
+					GTK_BUTTONS_CLOSE,
+					"<b>Error</b>\n\n%s", msg);
+	gtk_dialog_run(GTK_DIALOG(dialog));
+
+	gtk_widget_destroy(dialog);
+	free(msg);
+	return 0;
+}
+
+#ifdef HAVE_GTK_INFO_BAR_SUPPORT
+static int perf_gtk__warning_info_bar(const char *format, va_list args)
+{
+	char *msg;
+
+	if (!perf_gtk__is_active_context(pgctx) ||
+	    vasprintf(&msg, format, args) < 0) {
+		fprintf(stderr, "Warning:\n");
+		vfprintf(stderr, format, args);
+		fprintf(stderr, "\n");
+		return -1;
+	}
+
+	gtk_label_set_text(GTK_LABEL(pgctx->message_label), msg);
+	gtk_info_bar_set_message_type(GTK_INFO_BAR(pgctx->info_bar),
+				      GTK_MESSAGE_WARNING);
+	gtk_widget_show(pgctx->info_bar);
+
+	free(msg);
+	return 0;
+}
+#else
+static int perf_gtk__warning_statusbar(const char *format, va_list args)
+{
+	char *msg, *p;
+
+	if (!perf_gtk__is_active_context(pgctx) ||
+	    vasprintf(&msg, format, args) < 0) {
+		fprintf(stderr, "Warning:\n");
+		vfprintf(stderr, format, args);
+		fprintf(stderr, "\n");
+		return -1;
+	}
+
+	gtk_statusbar_pop(GTK_STATUSBAR(pgctx->statbar),
+			  pgctx->statbar_ctx_id);
+
+	/* Only first line can be displayed */
+	p = strchr(msg, '\n');
+	if (p)
+		*p = '\0';
+
+	gtk_statusbar_push(GTK_STATUSBAR(pgctx->statbar),
+			   pgctx->statbar_ctx_id, msg);
+
+	free(msg);
+	return 0;
+}
+#endif
+
+struct perf_error_ops perf_gtk_eops = {
+	.error		= perf_gtk__error,
+#ifdef HAVE_GTK_INFO_BAR_SUPPORT
+	.warning	= perf_gtk__warning_info_bar,
+#else
+	.warning	= perf_gtk__warning_statusbar,
+#endif
+};
diff --git a/tools/perf/ui/helpline.c b/tools/perf/ui/helpline.c
new file mode 100644
index 00000000000..700fb3cfa1c
--- /dev/null
+++ b/tools/perf/ui/helpline.c
@@ -0,0 +1,73 @@
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include "../debug.h"
+#include "helpline.h"
+#include "ui.h"
+
+char ui_helpline__current[512];
+
+static void nop_helpline__pop(void)
+{
+}
+
+static void nop_helpline__push(const char *msg __maybe_unused)
+{
+}
+
+static int nop_helpline__show(const char *fmt __maybe_unused,
+			       va_list ap __maybe_unused)
+{
+	return 0;
+}
+
+static struct ui_helpline default_helpline_fns = {
+	.pop	= nop_helpline__pop,
+	.push	= nop_helpline__push,
+	.show	= nop_helpline__show,
+};
+
+struct ui_helpline *helpline_fns = &default_helpline_fns;
+
+void ui_helpline__pop(void)
+{
+	helpline_fns->pop();
+}
+
+void ui_helpline__push(const char *msg)
+{
+	helpline_fns->push(msg);
+}
+
+void ui_helpline__vpush(const char *fmt, va_list ap)
+{
+	char *s;
+
+	if (vasprintf(&s, fmt, ap) < 0)
+		vfprintf(stderr, fmt, ap);
+	else {
+		ui_helpline__push(s);
+		free(s);
+	}
+}
+
+void ui_helpline__fpush(const char *fmt, ...)
+{
+	va_list ap;
+
+	va_start(ap, fmt);
+	ui_helpline__vpush(fmt, ap);
+	va_end(ap);
+}
+
+void ui_helpline__puts(const char *msg)
+{
+	ui_helpline__pop();
+	ui_helpline__push(msg);
+}
+
+int ui_helpline__vshow(const char *fmt, va_list ap)
+{
+	return helpline_fns->show(fmt, ap);
+}
diff --git a/tools/perf/ui/helpline.h b/tools/perf/ui/helpline.h
new file mode 100644
index 00000000000..46181f4fc07
--- /dev/null
+++ b/tools/perf/ui/helpline.h
@@ -0,0 +1,29 @@
+#ifndef _PERF_UI_HELPLINE_H_
+#define _PERF_UI_HELPLINE_H_ 1
+
+#include <stdio.h>
+#include <stdarg.h>
+
+#include "../util/cache.h"
+
+struct ui_helpline {
+	void (*pop)(void);
+	void (*push)(const char *msg);
+	int  (*show)(const char *fmt, va_list ap);
+};
+
+extern struct ui_helpline *helpline_fns;
+
+void ui_helpline__init(void);
+
+void ui_helpline__pop(void);
+void ui_helpline__push(const char *msg);
+void ui_helpline__vpush(const char *fmt, va_list ap);
+void ui_helpline__fpush(const char *fmt, ...);
+void ui_helpline__puts(const char *msg);
+int  ui_helpline__vshow(const char *fmt, va_list ap);
+
+extern char ui_helpline__current[512];
+extern char ui_helpline__last_msg[];
+
+#endif /* _PERF_UI_HELPLINE_H_ */
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
new file mode 100644
index 00000000000..498adb23c02
--- /dev/null
+++ b/tools/perf/ui/hist.c
@@ -0,0 +1,624 @@
+#include <math.h>
+#include <linux/compiler.h>
+
+#include "../util/hist.h"
+#include "../util/util.h"
+#include "../util/sort.h"
+#include "../util/evsel.h"
+
+/* hist period print (hpp) functions */
+
+#define hpp__call_print_fn(hpp, fn, fmt, ...)			\
+({								\
+	int __ret = fn(hpp, fmt, ##__VA_ARGS__);		\
+	advance_hpp(hpp, __ret);				\
+	__ret;							\
+})
+
+int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
+	       hpp_field_fn get_field, const char *fmt,
+	       hpp_snprint_fn print_fn, bool fmt_percent)
+{
+	int ret;
+	struct hists *hists = he->hists;
+	struct perf_evsel *evsel = hists_to_evsel(hists);
+	char *buf = hpp->buf;
+	size_t size = hpp->size;
+
+	if (fmt_percent) {
+		double percent = 0.0;
+		u64 total = hists__total_period(hists);
+
+		if (total)
+			percent = 100.0 * get_field(he) / total;
+
+		ret = hpp__call_print_fn(hpp, print_fn, fmt, percent);
+	} else
+		ret = hpp__call_print_fn(hpp, print_fn, fmt, get_field(he));
+
+	if (perf_evsel__is_group_event(evsel)) {
+		int prev_idx, idx_delta;
+		struct hist_entry *pair;
+		int nr_members = evsel->nr_members;
+
+		prev_idx = perf_evsel__group_idx(evsel);
+
+		list_for_each_entry(pair, &he->pairs.head, pairs.node) {
+			u64 period = get_field(pair);
+			u64 total = hists__total_period(pair->hists);
+
+			if (!total)
+				continue;
+
+			evsel = hists_to_evsel(pair->hists);
+			idx_delta = perf_evsel__group_idx(evsel) - prev_idx - 1;
+
+			while (idx_delta--) {
+				/*
+				 * zero-fill group members in the middle which
+				 * have no sample
+				 */
+				if (fmt_percent) {
+					ret += hpp__call_print_fn(hpp, print_fn,
+								  fmt, 0.0);
+				} else {
+					ret += hpp__call_print_fn(hpp, print_fn,
+								  fmt, 0ULL);
+				}
+			}
+
+			if (fmt_percent) {
+				ret += hpp__call_print_fn(hpp, print_fn, fmt,
+							  100.0 * period / total);
+			} else {
+				ret += hpp__call_print_fn(hpp, print_fn, fmt,
+							  period);
+			}
+
+			prev_idx = perf_evsel__group_idx(evsel);
+		}
+
+		idx_delta = nr_members - prev_idx - 1;
+
+		while (idx_delta--) {
+			/*
+			 * zero-fill group members at last which have no sample
+			 */
+			if (fmt_percent) {
+				ret += hpp__call_print_fn(hpp, print_fn,
+							  fmt, 0.0);
+			} else {
+				ret += hpp__call_print_fn(hpp, print_fn,
+							  fmt, 0ULL);
+			}
+		}
+	}
+
+	/*
+	 * Restore original buf and size as it's where caller expects
+	 * the result will be saved.
+	 */
+	hpp->buf = buf;
+	hpp->size = size;
+
+	return ret;
+}
+
+int __hpp__fmt_acc(struct perf_hpp *hpp, struct hist_entry *he,
+		   hpp_field_fn get_field, const char *fmt,
+		   hpp_snprint_fn print_fn, bool fmt_percent)
+{
+	if (!symbol_conf.cumulate_callchain) {
+		return snprintf(hpp->buf, hpp->size, "%*s",
+				fmt_percent ? 8 : 12, "N/A");
+	}
+
+	return __hpp__fmt(hpp, he, get_field, fmt, print_fn, fmt_percent);
+}
+
+static int field_cmp(u64 field_a, u64 field_b)
+{
+	if (field_a > field_b)
+		return 1;
+	if (field_a < field_b)
+		return -1;
+	return 0;
+}
+
+static int __hpp__sort(struct hist_entry *a, struct hist_entry *b,
+		       hpp_field_fn get_field)
+{
+	s64 ret;
+	int i, nr_members;
+	struct perf_evsel *evsel;
+	struct hist_entry *pair;
+	u64 *fields_a, *fields_b;
+
+	ret = field_cmp(get_field(a), get_field(b));
+	if (ret || !symbol_conf.event_group)
+		return ret;
+
+	evsel = hists_to_evsel(a->hists);
+	if (!perf_evsel__is_group_event(evsel))
+		return ret;
+
+	nr_members = evsel->nr_members;
+	fields_a = calloc(sizeof(*fields_a), nr_members);
+	fields_b = calloc(sizeof(*fields_b), nr_members);
+
+	if (!fields_a || !fields_b)
+		goto out;
+
+	list_for_each_entry(pair, &a->pairs.head, pairs.node) {
+		evsel = hists_to_evsel(pair->hists);
+		fields_a[perf_evsel__group_idx(evsel)] = get_field(pair);
+	}
+
+	list_for_each_entry(pair, &b->pairs.head, pairs.node) {
+		evsel = hists_to_evsel(pair->hists);
+		fields_b[perf_evsel__group_idx(evsel)] = get_field(pair);
+	}
+
+	for (i = 1; i < nr_members; i++) {
+		ret = field_cmp(fields_a[i], fields_b[i]);
+		if (ret)
+			break;
+	}
+
+out:
+	free(fields_a);
+	free(fields_b);
+
+	return ret;
+}
+
+static int __hpp__sort_acc(struct hist_entry *a, struct hist_entry *b,
+			   hpp_field_fn get_field)
+{
+	s64 ret = 0;
+
+	if (symbol_conf.cumulate_callchain) {
+		/*
+		 * Put caller above callee when they have equal period.
+		 */
+		ret = field_cmp(get_field(a), get_field(b));
+		if (ret)
+			return ret;
+
+		ret = b->callchain->max_depth - a->callchain->max_depth;
+	}
+	return ret;
+}
+
+#define __HPP_HEADER_FN(_type, _str, _min_width, _unit_width) 		\
+static int hpp__header_##_type(struct perf_hpp_fmt *fmt __maybe_unused,	\
+			       struct perf_hpp *hpp,			\
+			       struct perf_evsel *evsel)		\
+{									\
+	int len = _min_width;						\
+									\
+	if (symbol_conf.event_group)					\
+		len = max(len, evsel->nr_members * _unit_width);	\
+									\
+	return scnprintf(hpp->buf, hpp->size, "%*s", len, _str);	\
+}
+
+#define __HPP_WIDTH_FN(_type, _min_width, _unit_width) 			\
+static int hpp__width_##_type(struct perf_hpp_fmt *fmt __maybe_unused,	\
+			      struct perf_hpp *hpp __maybe_unused,	\
+			      struct perf_evsel *evsel)			\
+{									\
+	int len = _min_width;						\
+									\
+	if (symbol_conf.event_group)					\
+		len = max(len, evsel->nr_members * _unit_width);	\
+									\
+	return len;							\
+}
+
+static int hpp_color_scnprintf(struct perf_hpp *hpp, const char *fmt, ...)
+{
+	va_list args;
+	ssize_t ssize = hpp->size;
+	double percent;
+	int ret;
+
+	va_start(args, fmt);
+	percent = va_arg(args, double);
+	ret = value_color_snprintf(hpp->buf, hpp->size, fmt, percent);
+	va_end(args);
+
+	return (ret >= ssize) ? (ssize - 1) : ret;
+}
+
+static int hpp_entry_scnprintf(struct perf_hpp *hpp, const char *fmt, ...)
+{
+	va_list args;
+	ssize_t ssize = hpp->size;
+	int ret;
+
+	va_start(args, fmt);
+	ret = vsnprintf(hpp->buf, hpp->size, fmt, args);
+	va_end(args);
+
+	return (ret >= ssize) ? (ssize - 1) : ret;
+}
+
+#define __HPP_COLOR_PERCENT_FN(_type, _field)					\
+static u64 he_get_##_field(struct hist_entry *he)				\
+{										\
+	return he->stat._field;							\
+}										\
+										\
+static int hpp__color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,		\
+			      struct perf_hpp *hpp, struct hist_entry *he) 	\
+{										\
+	return __hpp__fmt(hpp, he, he_get_##_field, " %6.2f%%",			\
+			  hpp_color_scnprintf, true);				\
+}
+
+#define __HPP_ENTRY_PERCENT_FN(_type, _field)					\
+static int hpp__entry_##_type(struct perf_hpp_fmt *_fmt __maybe_unused,		\
+			      struct perf_hpp *hpp, struct hist_entry *he) 	\
+{										\
+	const char *fmt = symbol_conf.field_sep ? " %.2f" : " %6.2f%%";		\
+	return __hpp__fmt(hpp, he, he_get_##_field, fmt,			\
+			  hpp_entry_scnprintf, true);				\
+}
+
+#define __HPP_SORT_FN(_type, _field)						\
+static int64_t hpp__sort_##_type(struct hist_entry *a, struct hist_entry *b)	\
+{										\
+	return __hpp__sort(a, b, he_get_##_field);				\
+}
+
+#define __HPP_COLOR_ACC_PERCENT_FN(_type, _field)				\
+static u64 he_get_acc_##_field(struct hist_entry *he)				\
+{										\
+	return he->stat_acc->_field;						\
+}										\
+										\
+static int hpp__color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,		\
+			      struct perf_hpp *hpp, struct hist_entry *he) 	\
+{										\
+	return __hpp__fmt_acc(hpp, he, he_get_acc_##_field, " %6.2f%%",		\
+			      hpp_color_scnprintf, true);			\
+}
+
+#define __HPP_ENTRY_ACC_PERCENT_FN(_type, _field)				\
+static int hpp__entry_##_type(struct perf_hpp_fmt *_fmt __maybe_unused,		\
+			      struct perf_hpp *hpp, struct hist_entry *he) 	\
+{										\
+	const char *fmt = symbol_conf.field_sep ? " %.2f" : " %6.2f%%";		\
+	return __hpp__fmt_acc(hpp, he, he_get_acc_##_field, fmt,		\
+			      hpp_entry_scnprintf, true);			\
+}
+
+#define __HPP_SORT_ACC_FN(_type, _field)					\
+static int64_t hpp__sort_##_type(struct hist_entry *a, struct hist_entry *b)	\
+{										\
+	return __hpp__sort_acc(a, b, he_get_acc_##_field);			\
+}
+
+#define __HPP_ENTRY_RAW_FN(_type, _field)					\
+static u64 he_get_raw_##_field(struct hist_entry *he)				\
+{										\
+	return he->stat._field;							\
+}										\
+										\
+static int hpp__entry_##_type(struct perf_hpp_fmt *_fmt __maybe_unused,		\
+			      struct perf_hpp *hpp, struct hist_entry *he) 	\
+{										\
+	const char *fmt = symbol_conf.field_sep ? " %"PRIu64 : " %11"PRIu64;	\
+	return __hpp__fmt(hpp, he, he_get_raw_##_field, fmt,			\
+			  hpp_entry_scnprintf, false);				\
+}
+
+#define __HPP_SORT_RAW_FN(_type, _field)					\
+static int64_t hpp__sort_##_type(struct hist_entry *a, struct hist_entry *b)	\
+{										\
+	return __hpp__sort(a, b, he_get_raw_##_field);				\
+}
+
+
+#define HPP_PERCENT_FNS(_type, _str, _field, _min_width, _unit_width)	\
+__HPP_HEADER_FN(_type, _str, _min_width, _unit_width)			\
+__HPP_WIDTH_FN(_type, _min_width, _unit_width)				\
+__HPP_COLOR_PERCENT_FN(_type, _field)					\
+__HPP_ENTRY_PERCENT_FN(_type, _field)					\
+__HPP_SORT_FN(_type, _field)
+
+#define HPP_PERCENT_ACC_FNS(_type, _str, _field, _min_width, _unit_width)\
+__HPP_HEADER_FN(_type, _str, _min_width, _unit_width)			\
+__HPP_WIDTH_FN(_type, _min_width, _unit_width)				\
+__HPP_COLOR_ACC_PERCENT_FN(_type, _field)				\
+__HPP_ENTRY_ACC_PERCENT_FN(_type, _field)				\
+__HPP_SORT_ACC_FN(_type, _field)
+
+#define HPP_RAW_FNS(_type, _str, _field, _min_width, _unit_width)	\
+__HPP_HEADER_FN(_type, _str, _min_width, _unit_width)			\
+__HPP_WIDTH_FN(_type, _min_width, _unit_width)				\
+__HPP_ENTRY_RAW_FN(_type, _field)					\
+__HPP_SORT_RAW_FN(_type, _field)
+
+__HPP_HEADER_FN(overhead_self, "Self", 8, 8)
+
+HPP_PERCENT_FNS(overhead, "Overhead", period, 8, 8)
+HPP_PERCENT_FNS(overhead_sys, "sys", period_sys, 8, 8)
+HPP_PERCENT_FNS(overhead_us, "usr", period_us, 8, 8)
+HPP_PERCENT_FNS(overhead_guest_sys, "guest sys", period_guest_sys, 9, 8)
+HPP_PERCENT_FNS(overhead_guest_us, "guest usr", period_guest_us, 9, 8)
+HPP_PERCENT_ACC_FNS(overhead_acc, "Children", period, 8, 8)
+
+HPP_RAW_FNS(samples, "Samples", nr_events, 12, 12)
+HPP_RAW_FNS(period, "Period", period, 12, 12)
+
+static int64_t hpp__nop_cmp(struct hist_entry *a __maybe_unused,
+			    struct hist_entry *b __maybe_unused)
+{
+	return 0;
+}
+
+#define HPP__COLOR_PRINT_FNS(_name)			\
+	{						\
+		.header	= hpp__header_ ## _name,	\
+		.width	= hpp__width_ ## _name,		\
+		.color	= hpp__color_ ## _name,		\
+		.entry	= hpp__entry_ ## _name,		\
+		.cmp	= hpp__nop_cmp,			\
+		.collapse = hpp__nop_cmp,		\
+		.sort	= hpp__sort_ ## _name,		\
+	}
+
+#define HPP__COLOR_ACC_PRINT_FNS(_name)			\
+	{						\
+		.header	= hpp__header_ ## _name,	\
+		.width	= hpp__width_ ## _name,		\
+		.color	= hpp__color_ ## _name,		\
+		.entry	= hpp__entry_ ## _name,		\
+		.cmp	= hpp__nop_cmp,			\
+		.collapse = hpp__nop_cmp,		\
+		.sort	= hpp__sort_ ## _name,		\
+	}
+
+#define HPP__PRINT_FNS(_name)				\
+	{						\
+		.header	= hpp__header_ ## _name,	\
+		.width	= hpp__width_ ## _name,		\
+		.entry	= hpp__entry_ ## _name,		\
+		.cmp	= hpp__nop_cmp,			\
+		.collapse = hpp__nop_cmp,		\
+		.sort	= hpp__sort_ ## _name,		\
+	}
+
+struct perf_hpp_fmt perf_hpp__format[] = {
+	HPP__COLOR_PRINT_FNS(overhead),
+	HPP__COLOR_PRINT_FNS(overhead_sys),
+	HPP__COLOR_PRINT_FNS(overhead_us),
+	HPP__COLOR_PRINT_FNS(overhead_guest_sys),
+	HPP__COLOR_PRINT_FNS(overhead_guest_us),
+	HPP__COLOR_ACC_PRINT_FNS(overhead_acc),
+	HPP__PRINT_FNS(samples),
+	HPP__PRINT_FNS(period)
+};
+
+LIST_HEAD(perf_hpp__list);
+LIST_HEAD(perf_hpp__sort_list);
+
+
+#undef HPP__COLOR_PRINT_FNS
+#undef HPP__COLOR_ACC_PRINT_FNS
+#undef HPP__PRINT_FNS
+
+#undef HPP_PERCENT_FNS
+#undef HPP_PERCENT_ACC_FNS
+#undef HPP_RAW_FNS
+
+#undef __HPP_HEADER_FN
+#undef __HPP_WIDTH_FN
+#undef __HPP_COLOR_PERCENT_FN
+#undef __HPP_ENTRY_PERCENT_FN
+#undef __HPP_COLOR_ACC_PERCENT_FN
+#undef __HPP_ENTRY_ACC_PERCENT_FN
+#undef __HPP_ENTRY_RAW_FN
+#undef __HPP_SORT_FN
+#undef __HPP_SORT_ACC_FN
+#undef __HPP_SORT_RAW_FN
+
+
+void perf_hpp__init(void)
+{
+	struct list_head *list;
+	int i;
+
+	for (i = 0; i < PERF_HPP__MAX_INDEX; i++) {
+		struct perf_hpp_fmt *fmt = &perf_hpp__format[i];
+
+		INIT_LIST_HEAD(&fmt->list);
+
+		/* sort_list may be linked by setup_sorting() */
+		if (fmt->sort_list.next == NULL)
+			INIT_LIST_HEAD(&fmt->sort_list);
+	}
+
+	/*
+	 * If user specified field order, no need to setup default fields.
+	 */
+	if (field_order)
+		return;
+
+	if (symbol_conf.cumulate_callchain) {
+		perf_hpp__column_enable(PERF_HPP__OVERHEAD_ACC);
+
+		perf_hpp__format[PERF_HPP__OVERHEAD].header =
+						hpp__header_overhead_self;
+	}
+
+	perf_hpp__column_enable(PERF_HPP__OVERHEAD);
+
+	if (symbol_conf.show_cpu_utilization) {
+		perf_hpp__column_enable(PERF_HPP__OVERHEAD_SYS);
+		perf_hpp__column_enable(PERF_HPP__OVERHEAD_US);
+
+		if (perf_guest) {
+			perf_hpp__column_enable(PERF_HPP__OVERHEAD_GUEST_SYS);
+			perf_hpp__column_enable(PERF_HPP__OVERHEAD_GUEST_US);
+		}
+	}
+
+	if (symbol_conf.show_nr_samples)
+		perf_hpp__column_enable(PERF_HPP__SAMPLES);
+
+	if (symbol_conf.show_total_period)
+		perf_hpp__column_enable(PERF_HPP__PERIOD);
+
+	/* prepend overhead field for backward compatiblity.  */
+	list = &perf_hpp__format[PERF_HPP__OVERHEAD].sort_list;
+	if (list_empty(list))
+		list_add(list, &perf_hpp__sort_list);
+
+	if (symbol_conf.cumulate_callchain) {
+		list = &perf_hpp__format[PERF_HPP__OVERHEAD_ACC].sort_list;
+		if (list_empty(list))
+			list_add(list, &perf_hpp__sort_list);
+	}
+}
+
+void perf_hpp__column_register(struct perf_hpp_fmt *format)
+{
+	list_add_tail(&format->list, &perf_hpp__list);
+}
+
+void perf_hpp__column_unregister(struct perf_hpp_fmt *format)
+{
+	list_del(&format->list);
+}
+
+void perf_hpp__register_sort_field(struct perf_hpp_fmt *format)
+{
+	list_add_tail(&format->sort_list, &perf_hpp__sort_list);
+}
+
+void perf_hpp__column_enable(unsigned col)
+{
+	BUG_ON(col >= PERF_HPP__MAX_INDEX);
+	perf_hpp__column_register(&perf_hpp__format[col]);
+}
+
+void perf_hpp__column_disable(unsigned col)
+{
+	BUG_ON(col >= PERF_HPP__MAX_INDEX);
+	perf_hpp__column_unregister(&perf_hpp__format[col]);
+}
+
+void perf_hpp__cancel_cumulate(void)
+{
+	if (field_order)
+		return;
+
+	perf_hpp__column_disable(PERF_HPP__OVERHEAD_ACC);
+	perf_hpp__format[PERF_HPP__OVERHEAD].header = hpp__header_overhead;
+}
+
+void perf_hpp__setup_output_field(void)
+{
+	struct perf_hpp_fmt *fmt;
+
+	/* append sort keys to output field */
+	perf_hpp__for_each_sort_list(fmt) {
+		if (!list_empty(&fmt->list))
+			continue;
+
+		/*
+		 * sort entry fields are dynamically created,
+		 * so they can share a same sort key even though
+		 * the list is empty.
+		 */
+		if (perf_hpp__is_sort_entry(fmt)) {
+			struct perf_hpp_fmt *pos;
+
+			perf_hpp__for_each_format(pos) {
+				if (perf_hpp__same_sort_entry(pos, fmt))
+					goto next;
+			}
+		}
+
+		perf_hpp__column_register(fmt);
+next:
+		continue;
+	}
+}
+
+void perf_hpp__append_sort_keys(void)
+{
+	struct perf_hpp_fmt *fmt;
+
+	/* append output fields to sort keys */
+	perf_hpp__for_each_format(fmt) {
+		if (!list_empty(&fmt->sort_list))
+			continue;
+
+		/*
+		 * sort entry fields are dynamically created,
+		 * so they can share a same sort key even though
+		 * the list is empty.
+		 */
+		if (perf_hpp__is_sort_entry(fmt)) {
+			struct perf_hpp_fmt *pos;
+
+			perf_hpp__for_each_sort_list(pos) {
+				if (perf_hpp__same_sort_entry(pos, fmt))
+					goto next;
+			}
+		}
+
+		perf_hpp__register_sort_field(fmt);
+next:
+		continue;
+	}
+}
+
+void perf_hpp__reset_output_field(void)
+{
+	struct perf_hpp_fmt *fmt, *tmp;
+
+	/* reset output fields */
+	perf_hpp__for_each_format_safe(fmt, tmp) {
+		list_del_init(&fmt->list);
+		list_del_init(&fmt->sort_list);
+	}
+
+	/* reset sort keys */
+	perf_hpp__for_each_sort_list_safe(fmt, tmp) {
+		list_del_init(&fmt->list);
+		list_del_init(&fmt->sort_list);
+	}
+}
+
+/*
+ * See hists__fprintf to match the column widths
+ */
+unsigned int hists__sort_list_width(struct hists *hists)
+{
+	struct perf_hpp_fmt *fmt;
+	int ret = 0;
+	bool first = true;
+	struct perf_hpp dummy_hpp;
+
+	perf_hpp__for_each_format(fmt) {
+		if (perf_hpp__should_skip(fmt))
+			continue;
+
+		if (first)
+			first = false;
+		else
+			ret += 2;
+
+		ret += fmt->width(fmt, &dummy_hpp, hists_to_evsel(hists));
+	}
+
+	if (verbose && sort__has_sym) /* Addr + origin */
+		ret += 3 + BITS_PER_LONG / 4;
+
+	return ret;
+}
diff --git a/tools/perf/ui/keysyms.h b/tools/perf/ui/keysyms.h
new file mode 100644
index 00000000000..65092d576b4
--- /dev/null
+++ b/tools/perf/ui/keysyms.h
@@ -0,0 +1,28 @@
+#ifndef _PERF_KEYSYMS_H_
+#define _PERF_KEYSYMS_H_ 1
+
+#include "libslang.h"
+
+#define K_DOWN	SL_KEY_DOWN
+#define K_END	SL_KEY_END
+#define K_ENTER	'\r'
+#define K_ESC	033
+#define K_F1	SL_KEY_F(1)
+#define K_HOME	SL_KEY_HOME
+#define K_LEFT	SL_KEY_LEFT
+#define K_PGDN	SL_KEY_NPAGE
+#define K_PGUP	SL_KEY_PPAGE
+#define K_RIGHT	SL_KEY_RIGHT
+#define K_TAB	'\t'
+#define K_UNTAB	SL_KEY_UNTAB
+#define K_UP	SL_KEY_UP
+#define K_BKSPC 0x7f
+#define K_DEL	SL_KEY_DELETE
+
+/* Not really keys */
+#define K_TIMER	 -1
+#define K_ERROR	 -2
+#define K_RESIZE -3
+#define K_SWITCH_INPUT_DATA -4
+
+#endif /* _PERF_KEYSYMS_H_ */
diff --git a/tools/perf/ui/libslang.h b/tools/perf/ui/libslang.h
new file mode 100644
index 00000000000..4d54b6450f5
--- /dev/null
+++ b/tools/perf/ui/libslang.h
@@ -0,0 +1,29 @@
+#ifndef _PERF_UI_SLANG_H_
+#define _PERF_UI_SLANG_H_ 1
+/*
+ * slang versions <= 2.0.6 have a "#if HAVE_LONG_LONG" that breaks
+ * the build if it isn't defined. Use the equivalent one that glibc
+ * has on features.h.
+ */
+#include <features.h>
+#ifndef HAVE_LONG_LONG
+#define HAVE_LONG_LONG __GLIBC_HAVE_LONG_LONG
+#endif
+#include <slang.h>
+
+#if SLANG_VERSION < 20104
+#define slsmg_printf(msg, args...) \
+	SLsmg_printf((char *)(msg), ##args)
+#define slsmg_write_nstring(msg, len) \
+	SLsmg_write_nstring((char *)(msg), len)
+#define sltt_set_color(obj, name, fg, bg) \
+	SLtt_set_color(obj,(char *)(name), (char *)(fg), (char *)(bg))
+#else
+#define slsmg_printf SLsmg_printf
+#define slsmg_write_nstring SLsmg_write_nstring
+#define sltt_set_color SLtt_set_color
+#endif
+
+#define SL_KEY_UNTAB 0x1000
+
+#endif /* _PERF_UI_SLANG_H_ */
diff --git a/tools/perf/ui/progress.c b/tools/perf/ui/progress.c
new file mode 100644
index 00000000000..a0f24c7115c
--- /dev/null
+++ b/tools/perf/ui/progress.c
@@ -0,0 +1,38 @@
+#include "../cache.h"
+#include "progress.h"
+
+static void null_progress__update(struct ui_progress *p __maybe_unused)
+{
+}
+
+static struct ui_progress_ops null_progress__ops =
+{
+	.update = null_progress__update,
+};
+
+struct ui_progress_ops *ui_progress__ops = &null_progress__ops;
+
+void ui_progress__update(struct ui_progress *p, u64 adv)
+{
+	p->curr += adv;
+
+	if (p->curr >= p->next) {
+		p->next += p->step;
+		ui_progress__ops->update(p);
+	}
+}
+
+void ui_progress__init(struct ui_progress *p, u64 total, const char *title)
+{
+	p->curr = 0;
+	p->next = p->step = total / 16;
+	p->total = total;
+	p->title = title;
+
+}
+
+void ui_progress__finish(void)
+{
+	if (ui_progress__ops->finish)
+		ui_progress__ops->finish();
+}
diff --git a/tools/perf/ui/progress.h b/tools/perf/ui/progress.h
new file mode 100644
index 00000000000..f34f89eb607
--- /dev/null
+++ b/tools/perf/ui/progress.h
@@ -0,0 +1,23 @@
+#ifndef _PERF_UI_PROGRESS_H_
+#define _PERF_UI_PROGRESS_H_ 1
+
+#include <linux/types.h>
+
+void ui_progress__finish(void);
+ 
+struct ui_progress {
+	const char *title;
+	u64 curr, next, step, total;
+};
+ 
+void ui_progress__init(struct ui_progress *p, u64 total, const char *title);
+void ui_progress__update(struct ui_progress *p, u64 adv);
+
+struct ui_progress_ops {
+	void (*update)(struct ui_progress *p);
+	void (*finish)(void);
+};
+
+extern struct ui_progress_ops *ui_progress__ops;
+
+#endif
diff --git a/tools/perf/ui/setup.c b/tools/perf/ui/setup.c
new file mode 100644
index 00000000000..ba51fa8a117
--- /dev/null
+++ b/tools/perf/ui/setup.c
@@ -0,0 +1,107 @@
+#include <pthread.h>
+#include <dlfcn.h>
+
+#include "../util/cache.h"
+#include "../util/debug.h"
+#include "../util/hist.h"
+
+pthread_mutex_t ui__lock = PTHREAD_MUTEX_INITIALIZER;
+void *perf_gtk_handle;
+
+#ifdef HAVE_GTK2_SUPPORT
+static int setup_gtk_browser(void)
+{
+	int (*perf_ui_init)(void);
+
+	if (perf_gtk_handle)
+		return 0;
+
+	perf_gtk_handle = dlopen(PERF_GTK_DSO, RTLD_LAZY);
+	if (perf_gtk_handle == NULL) {
+		char buf[PATH_MAX];
+		scnprintf(buf, sizeof(buf), "%s/%s", LIBDIR, PERF_GTK_DSO);
+		perf_gtk_handle = dlopen(buf, RTLD_LAZY);
+	}
+	if (perf_gtk_handle == NULL)
+		return -1;
+
+	perf_ui_init = dlsym(perf_gtk_handle, "perf_gtk__init");
+	if (perf_ui_init == NULL)
+		goto out_close;
+
+	if (perf_ui_init() == 0)
+		return 0;
+
+out_close:
+	dlclose(perf_gtk_handle);
+	return -1;
+}
+
+static void exit_gtk_browser(bool wait_for_ok)
+{
+	void (*perf_ui_exit)(bool);
+
+	if (perf_gtk_handle == NULL)
+		return;
+
+	perf_ui_exit = dlsym(perf_gtk_handle, "perf_gtk__exit");
+	if (perf_ui_exit == NULL)
+		goto out_close;
+
+	perf_ui_exit(wait_for_ok);
+
+out_close:
+	dlclose(perf_gtk_handle);
+
+	perf_gtk_handle = NULL;
+}
+#else
+static inline int setup_gtk_browser(void) { return -1; }
+static inline void exit_gtk_browser(bool wait_for_ok __maybe_unused) {}
+#endif
+
+void setup_browser(bool fallback_to_pager)
+{
+	if (use_browser < 2 && (!isatty(1) || dump_trace))
+		use_browser = 0;
+
+	/* default to TUI */
+	if (use_browser < 0)
+		use_browser = 1;
+
+	switch (use_browser) {
+	case 2:
+		if (setup_gtk_browser() == 0)
+			break;
+		printf("GTK browser requested but could not find %s\n",
+		       PERF_GTK_DSO);
+		sleep(1);
+		/* fall through */
+	case 1:
+		use_browser = 1;
+		if (ui__init() == 0)
+			break;
+		/* fall through */
+	default:
+		use_browser = 0;
+		if (fallback_to_pager)
+			setup_pager();
+		break;
+	}
+}
+
+void exit_browser(bool wait_for_ok)
+{
+	switch (use_browser) {
+	case 2:
+		exit_gtk_browser(wait_for_ok);
+		break;
+
+	case 1:
+		ui__exit(wait_for_ok);
+		break;
+
+	default:
+		break;
+	}
+}
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
new file mode 100644
index 00000000000..90122abd372
--- /dev/null
+++ b/tools/perf/ui/stdio/hist.c
@@ -0,0 +1,514 @@
+#include <stdio.h>
+
+#include "../../util/util.h"
+#include "../../util/hist.h"
+#include "../../util/sort.h"
+#include "../../util/evsel.h"
+
+
+static size_t callchain__fprintf_left_margin(FILE *fp, int left_margin)
+{
+	int i;
+	int ret = fprintf(fp, "            ");
+
+	for (i = 0; i < left_margin; i++)
+		ret += fprintf(fp, " ");
+
+	return ret;
+}
+
+static size_t ipchain__fprintf_graph_line(FILE *fp, int depth, int depth_mask,
+					  int left_margin)
+{
+	int i;
+	size_t ret = callchain__fprintf_left_margin(fp, left_margin);
+
+	for (i = 0; i < depth; i++)
+		if (depth_mask & (1 << i))
+			ret += fprintf(fp, "|          ");
+		else
+			ret += fprintf(fp, "           ");
+
+	ret += fprintf(fp, "\n");
+
+	return ret;
+}
+
+static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_list *chain,
+				     int depth, int depth_mask, int period,
+				     u64 total_samples, u64 hits,
+				     int left_margin)
+{
+	int i;
+	size_t ret = 0;
+
+	ret += callchain__fprintf_left_margin(fp, left_margin);
+	for (i = 0; i < depth; i++) {
+		if (depth_mask & (1 << i))
+			ret += fprintf(fp, "|");
+		else
+			ret += fprintf(fp, " ");
+		if (!period && i == depth - 1) {
+			double percent;
+
+			percent = hits * 100.0 / total_samples;
+			ret += percent_color_fprintf(fp, "--%2.2f%%-- ", percent);
+		} else
+			ret += fprintf(fp, "%s", "          ");
+	}
+	if (chain->ms.sym)
+		ret += fprintf(fp, "%s\n", chain->ms.sym->name);
+	else
+		ret += fprintf(fp, "0x%0" PRIx64 "\n", chain->ip);
+
+	return ret;
+}
+
+static struct symbol *rem_sq_bracket;
+static struct callchain_list rem_hits;
+
+static void init_rem_hits(void)
+{
+	rem_sq_bracket = malloc(sizeof(*rem_sq_bracket) + 6);
+	if (!rem_sq_bracket) {
+		fprintf(stderr, "Not enough memory to display remaining hits\n");
+		return;
+	}
+
+	strcpy(rem_sq_bracket->name, "[...]");
+	rem_hits.ms.sym = rem_sq_bracket;
+}
+
+static size_t __callchain__fprintf_graph(FILE *fp, struct rb_root *root,
+					 u64 total_samples, int depth,
+					 int depth_mask, int left_margin)
+{
+	struct rb_node *node, *next;
+	struct callchain_node *child;
+	struct callchain_list *chain;
+	int new_depth_mask = depth_mask;
+	u64 remaining;
+	size_t ret = 0;
+	int i;
+	uint entries_printed = 0;
+
+	remaining = total_samples;
+
+	node = rb_first(root);
+	while (node) {
+		u64 new_total;
+		u64 cumul;
+
+		child = rb_entry(node, struct callchain_node, rb_node);
+		cumul = callchain_cumul_hits(child);
+		remaining -= cumul;
+
+		/*
+		 * The depth mask manages the output of pipes that show
+		 * the depth. We don't want to keep the pipes of the current
+		 * level for the last child of this depth.
+		 * Except if we have remaining filtered hits. They will
+		 * supersede the last child
+		 */
+		next = rb_next(node);
+		if (!next && (callchain_param.mode != CHAIN_GRAPH_REL || !remaining))
+			new_depth_mask &= ~(1 << (depth - 1));
+
+		/*
+		 * But we keep the older depth mask for the line separator
+		 * to keep the level link until we reach the last child
+		 */
+		ret += ipchain__fprintf_graph_line(fp, depth, depth_mask,
+						   left_margin);
+		i = 0;
+		list_for_each_entry(chain, &child->val, list) {
+			ret += ipchain__fprintf_graph(fp, chain, depth,
+						      new_depth_mask, i++,
+						      total_samples,
+						      cumul,
+						      left_margin);
+		}
+
+		if (callchain_param.mode == CHAIN_GRAPH_REL)
+			new_total = child->children_hit;
+		else
+			new_total = total_samples;
+
+		ret += __callchain__fprintf_graph(fp, &child->rb_root, new_total,
+						  depth + 1,
+						  new_depth_mask | (1 << depth),
+						  left_margin);
+		node = next;
+		if (++entries_printed == callchain_param.print_limit)
+			break;
+	}
+
+	if (callchain_param.mode == CHAIN_GRAPH_REL &&
+		remaining && remaining != total_samples) {
+
+		if (!rem_sq_bracket)
+			return ret;
+
+		new_depth_mask &= ~(1 << (depth - 1));
+		ret += ipchain__fprintf_graph(fp, &rem_hits, depth,
+					      new_depth_mask, 0, total_samples,
+					      remaining, left_margin);
+	}
+
+	return ret;
+}
+
+static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root,
+				       u64 total_samples, int left_margin)
+{
+	struct callchain_node *cnode;
+	struct callchain_list *chain;
+	u32 entries_printed = 0;
+	bool printed = false;
+	struct rb_node *node;
+	int i = 0;
+	int ret = 0;
+
+	/*
+	 * If have one single callchain root, don't bother printing
+	 * its percentage (100 % in fractal mode and the same percentage
+	 * than the hist in graph mode). This also avoid one level of column.
+	 */
+	node = rb_first(root);
+	if (node && !rb_next(node)) {
+		cnode = rb_entry(node, struct callchain_node, rb_node);
+		list_for_each_entry(chain, &cnode->val, list) {
+			/*
+			 * If we sort by symbol, the first entry is the same than
+			 * the symbol. No need to print it otherwise it appears as
+			 * displayed twice.
+			 */
+			if (!i++ && field_order == NULL &&
+			    sort_order && !prefixcmp(sort_order, "sym"))
+				continue;
+			if (!printed) {
+				ret += callchain__fprintf_left_margin(fp, left_margin);
+				ret += fprintf(fp, "|\n");
+				ret += callchain__fprintf_left_margin(fp, left_margin);
+				ret += fprintf(fp, "---");
+				left_margin += 3;
+				printed = true;
+			} else
+				ret += callchain__fprintf_left_margin(fp, left_margin);
+
+			if (chain->ms.sym)
+				ret += fprintf(fp, " %s\n", chain->ms.sym->name);
+			else
+				ret += fprintf(fp, " %p\n", (void *)(long)chain->ip);
+
+			if (++entries_printed == callchain_param.print_limit)
+				break;
+		}
+		root = &cnode->rb_root;
+	}
+
+	ret += __callchain__fprintf_graph(fp, root, total_samples,
+					  1, 1, left_margin);
+	ret += fprintf(fp, "\n");
+
+	return ret;
+}
+
+static size_t __callchain__fprintf_flat(FILE *fp, struct callchain_node *node,
+					u64 total_samples)
+{
+	struct callchain_list *chain;
+	size_t ret = 0;
+
+	if (!node)
+		return 0;
+
+	ret += __callchain__fprintf_flat(fp, node->parent, total_samples);
+
+
+	list_for_each_entry(chain, &node->val, list) {
+		if (chain->ip >= PERF_CONTEXT_MAX)
+			continue;
+		if (chain->ms.sym)
+			ret += fprintf(fp, "                %s\n", chain->ms.sym->name);
+		else
+			ret += fprintf(fp, "                %p\n",
+					(void *)(long)chain->ip);
+	}
+
+	return ret;
+}
+
+static size_t callchain__fprintf_flat(FILE *fp, struct rb_root *tree,
+				      u64 total_samples)
+{
+	size_t ret = 0;
+	u32 entries_printed = 0;
+	struct callchain_node *chain;
+	struct rb_node *rb_node = rb_first(tree);
+
+	while (rb_node) {
+		double percent;
+
+		chain = rb_entry(rb_node, struct callchain_node, rb_node);
+		percent = chain->hit * 100.0 / total_samples;
+
+		ret = percent_color_fprintf(fp, "           %6.2f%%\n", percent);
+		ret += __callchain__fprintf_flat(fp, chain, total_samples);
+		ret += fprintf(fp, "\n");
+		if (++entries_printed == callchain_param.print_limit)
+			break;
+
+		rb_node = rb_next(rb_node);
+	}
+
+	return ret;
+}
+
+static size_t hist_entry_callchain__fprintf(struct hist_entry *he,
+					    u64 total_samples, int left_margin,
+					    FILE *fp)
+{
+	switch (callchain_param.mode) {
+	case CHAIN_GRAPH_REL:
+		return callchain__fprintf_graph(fp, &he->sorted_chain,
+						symbol_conf.cumulate_callchain ?
+						he->stat_acc->period : he->stat.period,
+						left_margin);
+		break;
+	case CHAIN_GRAPH_ABS:
+		return callchain__fprintf_graph(fp, &he->sorted_chain, total_samples,
+						left_margin);
+		break;
+	case CHAIN_FLAT:
+		return callchain__fprintf_flat(fp, &he->sorted_chain, total_samples);
+		break;
+	case CHAIN_NONE:
+		break;
+	default:
+		pr_err("Bad callchain mode\n");
+	}
+
+	return 0;
+}
+
+static size_t hist_entry__callchain_fprintf(struct hist_entry *he,
+					    struct hists *hists,
+					    FILE *fp)
+{
+	int left_margin = 0;
+	u64 total_period = hists->stats.total_period;
+
+	if (field_order == NULL && (sort_order == NULL ||
+				    !prefixcmp(sort_order, "comm"))) {
+		struct perf_hpp_fmt *fmt;
+
+		perf_hpp__for_each_format(fmt) {
+			if (!perf_hpp__is_sort_entry(fmt))
+				continue;
+
+			/* must be 'comm' sort entry */
+			left_margin = fmt->width(fmt, NULL, hists_to_evsel(hists));
+			left_margin -= thread__comm_len(he->thread);
+			break;
+		}
+	}
+	return hist_entry_callchain__fprintf(he, total_period, left_margin, fp);
+}
+
+static int hist_entry__snprintf(struct hist_entry *he, struct perf_hpp *hpp)
+{
+	const char *sep = symbol_conf.field_sep;
+	struct perf_hpp_fmt *fmt;
+	char *start = hpp->buf;
+	int ret;
+	bool first = true;
+
+	if (symbol_conf.exclude_other && !he->parent)
+		return 0;
+
+	perf_hpp__for_each_format(fmt) {
+		if (perf_hpp__should_skip(fmt))
+			continue;
+
+		/*
+		 * If there's no field_sep, we still need
+		 * to display initial '  '.
+		 */
+		if (!sep || !first) {
+			ret = scnprintf(hpp->buf, hpp->size, "%s", sep ?: "  ");
+			advance_hpp(hpp, ret);
+		} else
+			first = false;
+
+		if (perf_hpp__use_color() && fmt->color)
+			ret = fmt->color(fmt, hpp, he);
+		else
+			ret = fmt->entry(fmt, hpp, he);
+
+		advance_hpp(hpp, ret);
+	}
+
+	return hpp->buf - start;
+}
+
+static int hist_entry__fprintf(struct hist_entry *he, size_t size,
+			       struct hists *hists,
+			       char *bf, size_t bfsz, FILE *fp)
+{
+	int ret;
+	struct perf_hpp hpp = {
+		.buf		= bf,
+		.size		= size,
+	};
+
+	if (size == 0 || size > bfsz)
+		size = hpp.size = bfsz;
+
+	hist_entry__snprintf(he, &hpp);
+
+	ret = fprintf(fp, "%s\n", bf);
+
+	if (symbol_conf.use_callchain)
+		ret += hist_entry__callchain_fprintf(he, hists, fp);
+
+	return ret;
+}
+
+size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
+		      int max_cols, float min_pcnt, FILE *fp)
+{
+	struct perf_hpp_fmt *fmt;
+	struct rb_node *nd;
+	size_t ret = 0;
+	unsigned int width;
+	const char *sep = symbol_conf.field_sep;
+	int nr_rows = 0;
+	char bf[96];
+	struct perf_hpp dummy_hpp = {
+		.buf	= bf,
+		.size	= sizeof(bf),
+	};
+	bool first = true;
+	size_t linesz;
+	char *line = NULL;
+
+	init_rem_hits();
+
+
+	perf_hpp__for_each_format(fmt)
+		perf_hpp__reset_width(fmt, hists);
+
+	if (!show_header)
+		goto print_entries;
+
+	fprintf(fp, "# ");
+
+	perf_hpp__for_each_format(fmt) {
+		if (perf_hpp__should_skip(fmt))
+			continue;
+
+		if (!first)
+			fprintf(fp, "%s", sep ?: "  ");
+		else
+			first = false;
+
+		fmt->header(fmt, &dummy_hpp, hists_to_evsel(hists));
+		fprintf(fp, "%s", bf);
+	}
+
+	fprintf(fp, "\n");
+	if (max_rows && ++nr_rows >= max_rows)
+		goto out;
+
+	if (sep)
+		goto print_entries;
+
+	first = true;
+
+	fprintf(fp, "# ");
+
+	perf_hpp__for_each_format(fmt) {
+		unsigned int i;
+
+		if (perf_hpp__should_skip(fmt))
+			continue;
+
+		if (!first)
+			fprintf(fp, "%s", sep ?: "  ");
+		else
+			first = false;
+
+		width = fmt->width(fmt, &dummy_hpp, hists_to_evsel(hists));
+		for (i = 0; i < width; i++)
+			fprintf(fp, ".");
+	}
+
+	fprintf(fp, "\n");
+	if (max_rows && ++nr_rows >= max_rows)
+		goto out;
+
+	fprintf(fp, "#\n");
+	if (max_rows && ++nr_rows >= max_rows)
+		goto out;
+
+print_entries:
+	linesz = hists__sort_list_width(hists) + 3 + 1;
+	linesz += perf_hpp__color_overhead();
+	line = malloc(linesz);
+	if (line == NULL) {
+		ret = -1;
+		goto out;
+	}
+
+	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;
+
+		if (h->filtered)
+			continue;
+
+		percent = hist_entry__get_percent_limit(h);
+		if (percent < min_pcnt)
+			continue;
+
+		ret += hist_entry__fprintf(h, max_cols, hists, line, linesz, fp);
+
+		if (max_rows && ++nr_rows >= max_rows)
+			break;
+
+		if (h->ms.map == NULL && verbose > 1) {
+			__map_groups__fprintf_maps(h->thread->mg,
+						   MAP__FUNCTION, verbose, fp);
+			fprintf(fp, "%.10s end\n", graph_dotted_line);
+		}
+	}
+
+	free(line);
+out:
+	zfree(&rem_sq_bracket);
+
+	return ret;
+}
+
+size_t events_stats__fprintf(struct events_stats *stats, FILE *fp)
+{
+	int i;
+	size_t ret = 0;
+
+	for (i = 0; i < PERF_RECORD_HEADER_MAX; ++i) {
+		const char *name;
+
+		if (stats->nr_events[i] == 0)
+			continue;
+
+		name = perf_event__name(i);
+		if (!strcmp(name, "UNKNOWN"))
+			continue;
+
+		ret += fprintf(fp, "%16s events: %10d\n", name,
+			       stats->nr_events[i]);
+	}
+
+	return ret;
+}
diff --git a/tools/perf/ui/tui/helpline.c b/tools/perf/ui/tui/helpline.c
new file mode 100644
index 00000000000..1c8b9afd5d6
--- /dev/null
+++ b/tools/perf/ui/tui/helpline.c
@@ -0,0 +1,58 @@
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <pthread.h>
+
+#include "../../util/debug.h"
+#include "../helpline.h"
+#include "../ui.h"
+#include "../libslang.h"
+
+char ui_helpline__last_msg[1024];
+
+static void tui_helpline__pop(void)
+{
+}
+
+static void tui_helpline__push(const char *msg)
+{
+	const size_t sz = sizeof(ui_helpline__current);
+
+	SLsmg_gotorc(SLtt_Screen_Rows - 1, 0);
+	SLsmg_set_color(0);
+	SLsmg_write_nstring((char *)msg, SLtt_Screen_Cols);
+	SLsmg_refresh();
+	strncpy(ui_helpline__current, msg, sz)[sz - 1] = '\0';
+}
+
+static int tui_helpline__show(const char *format, va_list ap)
+{
+	int ret;
+	static int backlog;
+
+	pthread_mutex_lock(&ui__lock);
+	ret = vscnprintf(ui_helpline__last_msg + backlog,
+			sizeof(ui_helpline__last_msg) - backlog, format, ap);
+	backlog += ret;
+
+	if (ui_helpline__last_msg[backlog - 1] == '\n') {
+		ui_helpline__puts(ui_helpline__last_msg);
+		SLsmg_refresh();
+		backlog = 0;
+	}
+	pthread_mutex_unlock(&ui__lock);
+
+	return ret;
+}
+
+struct ui_helpline tui_helpline_fns = {
+	.pop	= tui_helpline__pop,
+	.push	= tui_helpline__push,
+	.show	= tui_helpline__show,
+};
+
+void ui_helpline__init(void)
+{
+	helpline_fns = &tui_helpline_fns;
+	ui_helpline__puts(" ");
+}
diff --git a/tools/perf/ui/tui/progress.c b/tools/perf/ui/tui/progress.c
new file mode 100644
index 00000000000..c61d14b101e
--- /dev/null
+++ b/tools/perf/ui/tui/progress.c
@@ -0,0 +1,44 @@
+#include "../cache.h"
+#include "../progress.h"
+#include "../libslang.h"
+#include "../ui.h"
+#include "tui.h"
+#include "../browser.h"
+
+static void tui_progress__update(struct ui_progress *p)
+{
+	int bar, y;
+	/*
+	 * FIXME: We should have a per UI backend way of showing progress,
+	 * stdio will just show a percentage as NN%, etc.
+	 */
+	if (use_browser <= 0)
+		return;
+
+	if (p->total == 0)
+		return;
+
+	ui__refresh_dimensions(false);
+	pthread_mutex_lock(&ui__lock);
+	y = SLtt_Screen_Rows / 2 - 2;
+	SLsmg_set_color(0);
+	SLsmg_draw_box(y, 0, 3, SLtt_Screen_Cols);
+	SLsmg_gotorc(y++, 1);
+	SLsmg_write_string((char *)p->title);
+	SLsmg_fill_region(y, 1, 1, SLtt_Screen_Cols - 2, ' ');
+	SLsmg_set_color(HE_COLORSET_SELECTED);
+	bar = ((SLtt_Screen_Cols - 2) * p->curr) / p->total;
+	SLsmg_fill_region(y, 1, 1, bar, ' ');
+	SLsmg_refresh();
+	pthread_mutex_unlock(&ui__lock);
+}
+
+static struct ui_progress_ops tui_progress__ops =
+{
+	.update		= tui_progress__update,
+};
+
+void tui_progress__init(void)
+{
+	ui_progress__ops = &tui_progress__ops;
+}
diff --git a/tools/perf/ui/tui/setup.c b/tools/perf/ui/tui/setup.c
new file mode 100644
index 00000000000..2f612562978
--- /dev/null
+++ b/tools/perf/ui/tui/setup.c
@@ -0,0 +1,151 @@
+#include <signal.h>
+#include <stdbool.h>
+
+#include "../../util/cache.h"
+#include "../../util/debug.h"
+#include "../browser.h"
+#include "../helpline.h"
+#include "../ui.h"
+#include "../util.h"
+#include "../libslang.h"
+#include "../keysyms.h"
+#include "tui.h"
+
+static volatile int ui__need_resize;
+
+extern struct perf_error_ops perf_tui_eops;
+
+extern void hist_browser__init_hpp(void);
+
+void ui__refresh_dimensions(bool force)
+{
+	if (force || ui__need_resize) {
+		ui__need_resize = 0;
+		pthread_mutex_lock(&ui__lock);
+		SLtt_get_screen_size();
+		SLsmg_reinit_smg();
+		pthread_mutex_unlock(&ui__lock);
+	}
+}
+
+static void ui__sigwinch(int sig __maybe_unused)
+{
+	ui__need_resize = 1;
+}
+
+static void ui__setup_sigwinch(void)
+{
+	static bool done;
+
+	if (done)
+		return;
+
+	done = true;
+	pthread__unblock_sigwinch();
+	signal(SIGWINCH, ui__sigwinch);
+}
+
+int ui__getch(int delay_secs)
+{
+	struct timeval timeout, *ptimeout = delay_secs ? &timeout : NULL;
+	fd_set read_set;
+	int err, key;
+
+	ui__setup_sigwinch();
+
+	FD_ZERO(&read_set);
+	FD_SET(0, &read_set);
+
+	if (delay_secs) {
+		timeout.tv_sec = delay_secs;
+		timeout.tv_usec = 0;
+	}
+
+        err = select(1, &read_set, NULL, NULL, ptimeout);
+
+	if (err == 0)
+		return K_TIMER;
+
+	if (err == -1) {
+		if (errno == EINTR)
+			return K_RESIZE;
+		return K_ERROR;
+	}
+
+	key = SLang_getkey();
+	if (key != K_ESC)
+		return key;
+
+	FD_ZERO(&read_set);
+	FD_SET(0, &read_set);
+	timeout.tv_sec = 0;
+	timeout.tv_usec = 20;
+        err = select(1, &read_set, NULL, NULL, &timeout);
+	if (err == 0)
+		return K_ESC;
+
+	SLang_ungetkey(key);
+	return SLkp_getkey();
+}
+
+static void ui__signal(int sig)
+{
+	ui__exit(false);
+	psignal(sig, "perf");
+	exit(0);
+}
+
+int ui__init(void)
+{
+	int err;
+
+	SLutf8_enable(-1);
+	SLtt_get_terminfo();
+	SLtt_get_screen_size();
+
+	err = SLsmg_init_smg();
+	if (err < 0)
+		goto out;
+	err = SLang_init_tty(0, 0, 0);
+	if (err < 0)
+		goto out;
+
+	err = SLkp_init();
+	if (err < 0) {
+		pr_err("TUI initialization failed.\n");
+		goto out;
+	}
+
+	SLkp_define_keysym((char *)"^(kB)", SL_KEY_UNTAB);
+
+	ui_helpline__init();
+	ui_browser__init();
+	tui_progress__init();
+
+	signal(SIGSEGV, ui__signal);
+	signal(SIGFPE, ui__signal);
+	signal(SIGINT, ui__signal);
+	signal(SIGQUIT, ui__signal);
+	signal(SIGTERM, ui__signal);
+
+	perf_error__register(&perf_tui_eops);
+
+	hist_browser__init_hpp();
+out:
+	return err;
+}
+
+void ui__exit(bool wait_for_ok)
+{
+	if (wait_for_ok)
+		ui__question_window("Fatal Error",
+				    ui_helpline__last_msg,
+				    "Press any key...", 0);
+
+	SLtt_set_cursor_visibility(1);
+	SLsmg_refresh();
+	SLsmg_reset_smg();
+	SLang_reset_tty();
+
+	perf_error__unregister(&perf_tui_eops);
+}
diff --git a/tools/perf/ui/tui/tui.h b/tools/perf/ui/tui/tui.h
new file mode 100644
index 00000000000..18961c7b6ec
--- /dev/null
+++ b/tools/perf/ui/tui/tui.h
@@ -0,0 +1,6 @@
+#ifndef _PERF_TUI_H_
+#define _PERF_TUI_H_ 1
+
+void tui_progress__init(void);
+
+#endif /* _PERF_TUI_H_ */
diff --git a/tools/perf/ui/tui/util.c b/tools/perf/ui/tui/util.c
new file mode 100644
index 00000000000..bf890f72fe8
--- /dev/null
+++ b/tools/perf/ui/tui/util.c
@@ -0,0 +1,256 @@
+#include "../../util/util.h"
+#include <signal.h>
+#include <stdbool.h>
+#include <string.h>
+#include <sys/ttydefaults.h>
+
+#include "../../util/cache.h"
+#include "../../util/debug.h"
+#include "../browser.h"
+#include "../keysyms.h"
+#include "../helpline.h"
+#include "../ui.h"
+#include "../util.h"
+#include "../libslang.h"
+
+static void ui_browser__argv_write(struct ui_browser *browser,
+				   void *entry, int row)
+{
+	char **arg = entry;
+	bool current_entry = ui_browser__is_current_entry(browser, row);
+
+	ui_browser__set_color(browser, current_entry ? HE_COLORSET_SELECTED :
+						       HE_COLORSET_NORMAL);
+	slsmg_write_nstring(*arg, browser->width);
+}
+
+static int popup_menu__run(struct ui_browser *menu)
+{
+	int key;
+
+	if (ui_browser__show(menu, " ", "ESC: exit, ENTER|->: Select option") < 0)
+		return -1;
+
+	while (1) {
+		key = ui_browser__run(menu, 0);
+
+		switch (key) {
+		case K_RIGHT:
+		case K_ENTER:
+			key = menu->index;
+			break;
+		case K_LEFT:
+		case K_ESC:
+		case 'q':
+		case CTRL('c'):
+			key = -1;
+			break;
+		default:
+			continue;
+		}
+
+		break;
+	}
+
+	ui_browser__hide(menu);
+	return key;
+}
+
+int ui__popup_menu(int argc, char * const argv[])
+{
+	struct ui_browser menu = {
+		.entries    = (void *)argv,
+		.refresh    = ui_browser__argv_refresh,
+		.seek	    = ui_browser__argv_seek,
+		.write	    = ui_browser__argv_write,
+		.nr_entries = argc,
+	};
+
+	return popup_menu__run(&menu);
+}
+
+int ui_browser__input_window(const char *title, const char *text, char *input,
+			     const char *exit_msg, int delay_secs)
+{
+	int x, y, len, key;
+	int max_len = 60, nr_lines = 0;
+	static char buf[50];
+	const char *t;
+
+	t = text;
+	while (1) {
+		const char *sep = strchr(t, '\n');
+
+		if (sep == NULL)
+			sep = strchr(t, '\0');
+		len = sep - t;
+		if (max_len < len)
+			max_len = len;
+		++nr_lines;
+		if (*sep == '\0')
+			break;
+		t = sep + 1;
+	}
+
+	pthread_mutex_lock(&ui__lock);
+
+	max_len += 2;
+	nr_lines += 8;
+	y = SLtt_Screen_Rows / 2 - nr_lines / 2;
+	x = SLtt_Screen_Cols / 2 - max_len / 2;
+
+	SLsmg_set_color(0);
+	SLsmg_draw_box(y, x++, nr_lines, max_len);
+	if (title) {
+		SLsmg_gotorc(y, x + 1);
+		SLsmg_write_string((char *)title);
+	}
+	SLsmg_gotorc(++y, x);
+	nr_lines -= 7;
+	max_len -= 2;
+	SLsmg_write_wrapped_string((unsigned char *)text, y, x,
+				   nr_lines, max_len, 1);
+	y += nr_lines;
+	len = 5;
+	while (len--) {
+		SLsmg_gotorc(y + len - 1, x);
+		SLsmg_write_nstring((char *)" ", max_len);
+	}
+	SLsmg_draw_box(y++, x + 1, 3, max_len - 2);
+
+	SLsmg_gotorc(y + 3, x);
+	SLsmg_write_nstring((char *)exit_msg, max_len);
+	SLsmg_refresh();
+
+	pthread_mutex_unlock(&ui__lock);
+
+	x += 2;
+	len = 0;
+	key = ui__getch(delay_secs);
+	while (key != K_TIMER && key != K_ENTER && key != K_ESC) {
+		pthread_mutex_lock(&ui__lock);
+
+		if (key == K_BKSPC) {
+			if (len == 0) {
+				pthread_mutex_unlock(&ui__lock);
+				goto next_key;
+			}
+			SLsmg_gotorc(y, x + --len);
+			SLsmg_write_char(' ');
+		} else {
+			buf[len] = key;
+			SLsmg_gotorc(y, x + len++);
+			SLsmg_write_char(key);
+		}
+		SLsmg_refresh();
+
+		pthread_mutex_unlock(&ui__lock);
+
+		/* XXX more graceful overflow handling needed */
+		if (len == sizeof(buf) - 1) {
+			ui_helpline__push("maximum size of symbol name reached!");
+			key = K_ENTER;
+			break;
+		}
+next_key:
+		key = ui__getch(delay_secs);
+	}
+
+	buf[len] = '\0';
+	strncpy(input, buf, len+1);
+	return key;
+}
+
+int ui__question_window(const char *title, const char *text,
+			const char *exit_msg, int delay_secs)
+{
+	int x, y;
+	int max_len = 0, nr_lines = 0;
+	const char *t;
+
+	t = text;
+	while (1) {
+		const char *sep = strchr(t, '\n');
+		int len;
+
+		if (sep == NULL)
+			sep = strchr(t, '\0');
+		len = sep - t;
+		if (max_len < len)
+			max_len = len;
+		++nr_lines;
+		if (*sep == '\0')
+			break;
+		t = sep + 1;
+	}
+
+	pthread_mutex_lock(&ui__lock);
+
+	max_len += 2;
+	nr_lines += 4;
+	y = SLtt_Screen_Rows / 2 - nr_lines / 2,
+	x = SLtt_Screen_Cols / 2 - max_len / 2;
+
+	SLsmg_set_color(0);
+	SLsmg_draw_box(y, x++, nr_lines, max_len);
+	if (title) {
+		SLsmg_gotorc(y, x + 1);
+		SLsmg_write_string((char *)title);
+	}
+	SLsmg_gotorc(++y, x);
+	nr_lines -= 2;
+	max_len -= 2;
+	SLsmg_write_wrapped_string((unsigned char *)text, y, x,
+				   nr_lines, max_len, 1);
+	SLsmg_gotorc(y + nr_lines - 2, x);
+	SLsmg_write_nstring((char *)" ", max_len);
+	SLsmg_gotorc(y + nr_lines - 1, x);
+	SLsmg_write_nstring((char *)exit_msg, max_len);
+	SLsmg_refresh();
+
+	pthread_mutex_unlock(&ui__lock);
+
+	return ui__getch(delay_secs);
+}
+
+int ui__help_window(const char *text)
+{
+	return ui__question_window("Help", text, "Press any key...", 0);
+}
+
+int ui__dialog_yesno(const char *msg)
+{
+	return ui__question_window(NULL, msg, "Enter: Yes, ESC: No", 0);
+}
+
+static int __ui__warning(const char *title, const char *format, va_list args)
+{
+	char *s;
+
+	if (vasprintf(&s, format, args) > 0) {
+		int key;
+
+		key = ui__question_window(title, s, "Press any key...", 0);
+		free(s);
+		return key;
+	}
+
+	fprintf(stderr, "%s\n", title);
+	vfprintf(stderr, format, args);
+	return K_ESC;
+}
+
+static int perf_tui__error(const char *format, va_list args)
+{
+	return __ui__warning("Error:", format, args);
+}
+
+static int perf_tui__warning(const char *format, va_list args)
+{
+	return __ui__warning("Warning:", format, args);
+}
+
+struct perf_error_ops perf_tui_eops = {
+	.error		= perf_tui__error,
+	.warning	= perf_tui__warning,
+};
diff --git a/tools/perf/ui/ui.h b/tools/perf/ui/ui.h
new file mode 100644
index 00000000000..ab88383f8be
--- /dev/null
+++ b/tools/perf/ui/ui.h
@@ -0,0 +1,29 @@
+#ifndef _PERF_UI_H_
+#define _PERF_UI_H_ 1
+
+#include <pthread.h>
+#include <stdbool.h>
+#include <linux/compiler.h>
+
+extern pthread_mutex_t ui__lock;
+extern void *perf_gtk_handle;
+
+extern int use_browser;
+
+void setup_browser(bool fallback_to_pager);
+void exit_browser(bool wait_for_ok);
+
+#ifdef HAVE_SLANG_SUPPORT
+int ui__init(void);
+void ui__exit(bool wait_for_ok);
+#else
+static inline int ui__init(void)
+{
+	return -1;
+}
+static inline void ui__exit(bool wait_for_ok __maybe_unused) {}
+#endif
+
+void ui__refresh_dimensions(bool force);
+
+#endif /* _PERF_UI_H_ */
diff --git a/tools/perf/ui/util.c b/tools/perf/ui/util.c
new file mode 100644
index 00000000000..e3e0a963d03
--- /dev/null
+++ b/tools/perf/ui/util.c
@@ -0,0 +1,84 @@
+#include "util.h"
+#include "../debug.h"
+
+
+/*
+ * Default error logging functions
+ */
+static int perf_stdio__error(const char *format, va_list args)
+{
+	fprintf(stderr, "Error:\n");
+	vfprintf(stderr, format, args);
+	return 0;
+}
+
+static int perf_stdio__warning(const char *format, va_list args)
+{
+	fprintf(stderr, "Warning:\n");
+	vfprintf(stderr, format, args);
+	return 0;
+}
+
+static struct perf_error_ops default_eops =
+{
+	.error		= perf_stdio__error,
+	.warning	= perf_stdio__warning,
+};
+
+static struct perf_error_ops *perf_eops = &default_eops;
+
+
+int ui__error(const char *format, ...)
+{
+	int ret;
+	va_list args;
+
+	va_start(args, format);
+	ret = perf_eops->error(format, args);
+	va_end(args);
+
+	return ret;
+}
+
+int ui__warning(const char *format, ...)
+{
+	int ret;
+	va_list args;
+
+	va_start(args, format);
+	ret = perf_eops->warning(format, args);
+	va_end(args);
+
+	return ret;
+}
+
+/**
+ * perf_error__register - Register error logging functions
+ * @eops: The pointer to error logging function struct
+ *
+ * Register UI-specific error logging functions. Before calling this,
+ * other logging functions should be unregistered, if any.
+ */
+int perf_error__register(struct perf_error_ops *eops)
+{
+	if (perf_eops != &default_eops)
+		return -1;
+
+	perf_eops = eops;
+	return 0;
+}
+
+/**
+ * perf_error__unregister - Unregister error logging functions
+ * @eops: The pointer to error logging function struct
+ *
+ * Unregister already registered error logging functions.
+ */
+int perf_error__unregister(struct perf_error_ops *eops)
+{
+	if (perf_eops != eops)
+		return -1;
+
+	perf_eops = &default_eops;
+	return 0;
+}
diff --git a/tools/perf/ui/util.h b/tools/perf/ui/util.h
new file mode 100644
index 00000000000..361f08c52d3
--- /dev/null
+++ b/tools/perf/ui/util.h
@@ -0,0 +1,21 @@
+#ifndef _PERF_UI_UTIL_H_
+#define _PERF_UI_UTIL_H_ 1
+
+#include <stdarg.h>
+
+int ui__getch(int delay_secs);
+int ui__popup_menu(int argc, char * const argv[]);
+int ui__help_window(const char *text);
+int ui__dialog_yesno(const char *msg);
+int ui__question_window(const char *title, const char *text,
+			const char *exit_msg, int delay_secs);
+
+struct perf_error_ops {
+	int (*error)(const char *format, va_list args);
+	int (*warning)(const char *format, va_list args);
+};
+
+int perf_error__register(struct perf_error_ops *eops);
+int perf_error__unregister(struct perf_error_ops *eops);
+
+#endif /* _PERF_UI_UTIL_H_ */
diff --git a/tools/perf/util/PERF-VERSION-GEN b/tools/perf/util/PERF-VERSION-GEN
index 49ece792191..39f17507578 100755
--- a/tools/perf/util/PERF-VERSION-GEN
+++ b/tools/perf/util/PERF-VERSION-GEN
@@ -5,42 +5,46 @@ if [ $# -eq 1 ]  ; then
 fi
 
 GVF=${OUTPUT}PERF-VERSION-FILE
-DEF_VER=v0.0.2.PERF
 
 LF='
 '
 
-# First see if there is a version file (included in release tarballs),
-# then try git-describe, then default.
-if test -f version
+#
+# First check if there is a .git to get the version from git describe
+# otherwise try to get the version from the kernel Makefile
+#
+CID=
+TAG=
+if test -d ../../.git -o -f ../../.git
 then
-	VN=$(cat version) || VN="$DEF_VER"
-elif test -d .git -o -f .git &&
-	VN=$(git describe --abbrev=4 HEAD 2>/dev/null) &&
-	case "$VN" in
-	*$LF*) (exit 1) ;;
-	v[0-9]*)
-		git update-index -q --refresh
-		test -z "$(git diff-index --name-only HEAD --)" ||
-		VN="$VN-dirty" ;;
-	esac
+	TAG=$(git describe --abbrev=0 --match "v[0-9].[0-9]*" 2>/dev/null )
+	CID=$(git log -1 --abbrev=4 --pretty=format:"%h" 2>/dev/null) && CID="-g$CID"
+elif test -f ../../PERF-VERSION-FILE
 then
-	VN=$(echo "$VN" | sed -e 's/-/./g');
-else
-	VN="$DEF_VER"
+	TAG=$(cut -d' ' -f3 ../../PERF-VERSION-FILE | sed -e 's/\"//g')
+fi
+if test -z "$TAG"
+then
+	TAG=$(MAKEFLAGS= make -sC ../.. kernelversion)
+fi
+VN="$TAG$CID"
+if test -n "$CID"
+then
+	# format version string, strip trailing zero of sublevel:
+	VN=$(echo "$VN" | sed -e 's/-/./g;s/\([0-9]*[.][0-9]*\)[.]0/\1/')
 fi
 
 VN=$(expr "$VN" : v*'\(.*\)')
 
 if test -r $GVF
 then
-	VC=$(sed -e 's/^PERF_VERSION = //' <$GVF)
+	VC=$(sed -e 's/^#define PERF_VERSION "\(.*\)"/\1/' <$GVF)
 else
 	VC=unset
 fi
 test "$VN" = "$VC" || {
-	echo >&2 "PERF_VERSION = $VN"
-	echo "PERF_VERSION = $VN" >$GVF
+	echo >&2 "  PERF_VERSION = $VN"
+	echo "#define PERF_VERSION \"$VN\"" >$GVF
 }
 
 
diff --git a/tools/perf/util/alias.c b/tools/perf/util/alias.c
index b8144e80bb1..c0b43ee40d9 100644
--- a/tools/perf/util/alias.c
+++ b/tools/perf/util/alias.c
@@ -3,7 +3,8 @@
 static const char *alias_key;
 static char *alias_val;
 
-static int alias_lookup_cb(const char *k, const char *v, void *cb __used)
+static int alias_lookup_cb(const char *k, const char *v,
+			   void *cb __maybe_unused)
 {
 	if (!prefixcmp(k, "alias.") && !strcmp(k+6, alias_key)) {
 		if (!v)
@@ -54,8 +55,7 @@ int split_cmdline(char *cmdline, const char ***argv)
 				src++;
 				c = cmdline[src];
 				if (!c) {
-					free(*argv);
-					*argv = NULL;
+					zfree(argv);
 					return error("cmdline ends with \\");
 				}
 			}
@@ -67,8 +67,7 @@ int split_cmdline(char *cmdline, const char ***argv)
 	cmdline[dst] = 0;
 
 	if (quoted) {
-		free(*argv);
-		*argv = NULL;
+		zfree(argv);
 		return error("unclosed quote");
 	}
 
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
new file mode 100644
index 00000000000..809b4c50bea
--- /dev/null
+++ b/tools/perf/util/annotate.c
@@ -0,0 +1,1412 @@
+/*
+ * Copyright (C) 2011, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Parts came from builtin-annotate.c, see those files for further
+ * copyright notes.
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+
+#include "util.h"
+#include "ui/ui.h"
+#include "sort.h"
+#include "build-id.h"
+#include "color.h"
+#include "cache.h"
+#include "symbol.h"
+#include "debug.h"
+#include "annotate.h"
+#include "evsel.h"
+#include <pthread.h>
+#include <linux/bitops.h>
+
+const char 	*disassembler_style;
+const char	*objdump_path;
+
+static struct ins *ins__find(const char *name);
+static int disasm_line__parse(char *line, char **namep, char **rawp);
+
+static void ins__delete(struct ins_operands *ops)
+{
+	zfree(&ops->source.raw);
+	zfree(&ops->source.name);
+	zfree(&ops->target.raw);
+	zfree(&ops->target.name);
+}
+
+static int ins__raw_scnprintf(struct ins *ins, char *bf, size_t size,
+			      struct ins_operands *ops)
+{
+	return scnprintf(bf, size, "%-6.6s %s", ins->name, ops->raw);
+}
+
+int ins__scnprintf(struct ins *ins, char *bf, size_t size,
+		  struct ins_operands *ops)
+{
+	if (ins->ops->scnprintf)
+		return ins->ops->scnprintf(ins, bf, size, ops);
+
+	return ins__raw_scnprintf(ins, bf, size, ops);
+}
+
+static int call__parse(struct ins_operands *ops)
+{
+	char *endptr, *tok, *name;
+
+	ops->target.addr = strtoull(ops->raw, &endptr, 16);
+
+	name = strchr(endptr, '<');
+	if (name == NULL)
+		goto indirect_call;
+
+	name++;
+
+	tok = strchr(name, '>');
+	if (tok == NULL)
+		return -1;
+
+	*tok = '\0';
+	ops->target.name = strdup(name);
+	*tok = '>';
+
+	return ops->target.name == NULL ? -1 : 0;
+
+indirect_call:
+	tok = strchr(endptr, '(');
+	if (tok != NULL) {
+		ops->target.addr = 0;
+		return 0;
+	}
+
+	tok = strchr(endptr, '*');
+	if (tok == NULL)
+		return -1;
+
+	ops->target.addr = strtoull(tok + 1, NULL, 16);
+	return 0;
+}
+
+static int call__scnprintf(struct ins *ins, char *bf, size_t size,
+			   struct ins_operands *ops)
+{
+	if (ops->target.name)
+		return scnprintf(bf, size, "%-6.6s %s", ins->name, ops->target.name);
+
+	if (ops->target.addr == 0)
+		return ins__raw_scnprintf(ins, bf, size, ops);
+
+	return scnprintf(bf, size, "%-6.6s *%" PRIx64, ins->name, ops->target.addr);
+}
+
+static struct ins_ops call_ops = {
+	.parse	   = call__parse,
+	.scnprintf = call__scnprintf,
+};
+
+bool ins__is_call(const struct ins *ins)
+{
+	return ins->ops == &call_ops;
+}
+
+static int jump__parse(struct ins_operands *ops)
+{
+	const char *s = strchr(ops->raw, '+');
+
+	ops->target.addr = strtoull(ops->raw, NULL, 16);
+
+	if (s++ != NULL)
+		ops->target.offset = strtoull(s, NULL, 16);
+	else
+		ops->target.offset = UINT64_MAX;
+
+	return 0;
+}
+
+static int jump__scnprintf(struct ins *ins, char *bf, size_t size,
+			   struct ins_operands *ops)
+{
+	return scnprintf(bf, size, "%-6.6s %" PRIx64, ins->name, ops->target.offset);
+}
+
+static struct ins_ops jump_ops = {
+	.parse	   = jump__parse,
+	.scnprintf = jump__scnprintf,
+};
+
+bool ins__is_jump(const struct ins *ins)
+{
+	return ins->ops == &jump_ops;
+}
+
+static int comment__symbol(char *raw, char *comment, u64 *addrp, char **namep)
+{
+	char *endptr, *name, *t;
+
+	if (strstr(raw, "(%rip)") == NULL)
+		return 0;
+
+	*addrp = strtoull(comment, &endptr, 16);
+	name = strchr(endptr, '<');
+	if (name == NULL)
+		return -1;
+
+	name++;
+
+	t = strchr(name, '>');
+	if (t == NULL)
+		return 0;
+
+	*t = '\0';
+	*namep = strdup(name);
+	*t = '>';
+
+	return 0;
+}
+
+static int lock__parse(struct ins_operands *ops)
+{
+	char *name;
+
+	ops->locked.ops = zalloc(sizeof(*ops->locked.ops));
+	if (ops->locked.ops == NULL)
+		return 0;
+
+	if (disasm_line__parse(ops->raw, &name, &ops->locked.ops->raw) < 0)
+		goto out_free_ops;
+
+	ops->locked.ins = ins__find(name);
+	if (ops->locked.ins == NULL)
+		goto out_free_ops;
+
+	if (!ops->locked.ins->ops)
+		return 0;
+
+	if (ops->locked.ins->ops->parse)
+		ops->locked.ins->ops->parse(ops->locked.ops);
+
+	return 0;
+
+out_free_ops:
+	zfree(&ops->locked.ops);
+	return 0;
+}
+
+static int lock__scnprintf(struct ins *ins, char *bf, size_t size,
+			   struct ins_operands *ops)
+{
+	int printed;
+
+	if (ops->locked.ins == NULL)
+		return ins__raw_scnprintf(ins, bf, size, ops);
+
+	printed = scnprintf(bf, size, "%-6.6s ", ins->name);
+	return printed + ins__scnprintf(ops->locked.ins, bf + printed,
+					size - printed, ops->locked.ops);
+}
+
+static void lock__delete(struct ins_operands *ops)
+{
+	zfree(&ops->locked.ops);
+	zfree(&ops->target.raw);
+	zfree(&ops->target.name);
+}
+
+static struct ins_ops lock_ops = {
+	.free	   = lock__delete,
+	.parse	   = lock__parse,
+	.scnprintf = lock__scnprintf,
+};
+
+static int mov__parse(struct ins_operands *ops)
+{
+	char *s = strchr(ops->raw, ','), *target, *comment, prev;
+
+	if (s == NULL)
+		return -1;
+
+	*s = '\0';
+	ops->source.raw = strdup(ops->raw);
+	*s = ',';
+	
+	if (ops->source.raw == NULL)
+		return -1;
+
+	target = ++s;
+
+	while (s[0] != '\0' && !isspace(s[0]))
+		++s;
+	prev = *s;
+	*s = '\0';
+
+	ops->target.raw = strdup(target);
+	*s = prev;
+
+	if (ops->target.raw == NULL)
+		goto out_free_source;
+
+	comment = strchr(s, '#');
+	if (comment == NULL)
+		return 0;
+
+	while (comment[0] != '\0' && isspace(comment[0]))
+		++comment;
+
+	comment__symbol(ops->source.raw, comment, &ops->source.addr, &ops->source.name);
+	comment__symbol(ops->target.raw, comment, &ops->target.addr, &ops->target.name);
+
+	return 0;
+
+out_free_source:
+	zfree(&ops->source.raw);
+	return -1;
+}
+
+static int mov__scnprintf(struct ins *ins, char *bf, size_t size,
+			   struct ins_operands *ops)
+{
+	return scnprintf(bf, size, "%-6.6s %s,%s", ins->name,
+			 ops->source.name ?: ops->source.raw,
+			 ops->target.name ?: ops->target.raw);
+}
+
+static struct ins_ops mov_ops = {
+	.parse	   = mov__parse,
+	.scnprintf = mov__scnprintf,
+};
+
+static int dec__parse(struct ins_operands *ops)
+{
+	char *target, *comment, *s, prev;
+
+	target = s = ops->raw;
+
+	while (s[0] != '\0' && !isspace(s[0]))
+		++s;
+	prev = *s;
+	*s = '\0';
+
+	ops->target.raw = strdup(target);
+	*s = prev;
+
+	if (ops->target.raw == NULL)
+		return -1;
+
+	comment = strchr(s, '#');
+	if (comment == NULL)
+		return 0;
+
+	while (comment[0] != '\0' && isspace(comment[0]))
+		++comment;
+
+	comment__symbol(ops->target.raw, comment, &ops->target.addr, &ops->target.name);
+
+	return 0;
+}
+
+static int dec__scnprintf(struct ins *ins, char *bf, size_t size,
+			   struct ins_operands *ops)
+{
+	return scnprintf(bf, size, "%-6.6s %s", ins->name,
+			 ops->target.name ?: ops->target.raw);
+}
+
+static struct ins_ops dec_ops = {
+	.parse	   = dec__parse,
+	.scnprintf = dec__scnprintf,
+};
+
+static int nop__scnprintf(struct ins *ins __maybe_unused, char *bf, size_t size,
+			  struct ins_operands *ops __maybe_unused)
+{
+	return scnprintf(bf, size, "%-6.6s", "nop");
+}
+
+static struct ins_ops nop_ops = {
+	.scnprintf = nop__scnprintf,
+};
+
+/*
+ * Must be sorted by name!
+ */
+static struct ins instructions[] = {
+	{ .name = "add",   .ops  = &mov_ops, },
+	{ .name = "addl",  .ops  = &mov_ops, },
+	{ .name = "addq",  .ops  = &mov_ops, },
+	{ .name = "addw",  .ops  = &mov_ops, },
+	{ .name = "and",   .ops  = &mov_ops, },
+	{ .name = "bts",   .ops  = &mov_ops, },
+	{ .name = "call",  .ops  = &call_ops, },
+	{ .name = "callq", .ops  = &call_ops, },
+	{ .name = "cmp",   .ops  = &mov_ops, },
+	{ .name = "cmpb",  .ops  = &mov_ops, },
+	{ .name = "cmpl",  .ops  = &mov_ops, },
+	{ .name = "cmpq",  .ops  = &mov_ops, },
+	{ .name = "cmpw",  .ops  = &mov_ops, },
+	{ .name = "cmpxch", .ops  = &mov_ops, },
+	{ .name = "dec",   .ops  = &dec_ops, },
+	{ .name = "decl",  .ops  = &dec_ops, },
+	{ .name = "imul",  .ops  = &mov_ops, },
+	{ .name = "inc",   .ops  = &dec_ops, },
+	{ .name = "incl",  .ops  = &dec_ops, },
+	{ .name = "ja",	   .ops  = &jump_ops, },
+	{ .name = "jae",   .ops  = &jump_ops, },
+	{ .name = "jb",	   .ops  = &jump_ops, },
+	{ .name = "jbe",   .ops  = &jump_ops, },
+	{ .name = "jc",	   .ops  = &jump_ops, },
+	{ .name = "jcxz",  .ops  = &jump_ops, },
+	{ .name = "je",	   .ops  = &jump_ops, },
+	{ .name = "jecxz", .ops  = &jump_ops, },
+	{ .name = "jg",	   .ops  = &jump_ops, },
+	{ .name = "jge",   .ops  = &jump_ops, },
+	{ .name = "jl",    .ops  = &jump_ops, },
+	{ .name = "jle",   .ops  = &jump_ops, },
+	{ .name = "jmp",   .ops  = &jump_ops, },
+	{ .name = "jmpq",  .ops  = &jump_ops, },
+	{ .name = "jna",   .ops  = &jump_ops, },
+	{ .name = "jnae",  .ops  = &jump_ops, },
+	{ .name = "jnb",   .ops  = &jump_ops, },
+	{ .name = "jnbe",  .ops  = &jump_ops, },
+	{ .name = "jnc",   .ops  = &jump_ops, },
+	{ .name = "jne",   .ops  = &jump_ops, },
+	{ .name = "jng",   .ops  = &jump_ops, },
+	{ .name = "jnge",  .ops  = &jump_ops, },
+	{ .name = "jnl",   .ops  = &jump_ops, },
+	{ .name = "jnle",  .ops  = &jump_ops, },
+	{ .name = "jno",   .ops  = &jump_ops, },
+	{ .name = "jnp",   .ops  = &jump_ops, },
+	{ .name = "jns",   .ops  = &jump_ops, },
+	{ .name = "jnz",   .ops  = &jump_ops, },
+	{ .name = "jo",	   .ops  = &jump_ops, },
+	{ .name = "jp",	   .ops  = &jump_ops, },
+	{ .name = "jpe",   .ops  = &jump_ops, },
+	{ .name = "jpo",   .ops  = &jump_ops, },
+	{ .name = "jrcxz", .ops  = &jump_ops, },
+	{ .name = "js",	   .ops  = &jump_ops, },
+	{ .name = "jz",	   .ops  = &jump_ops, },
+	{ .name = "lea",   .ops  = &mov_ops, },
+	{ .name = "lock",  .ops  = &lock_ops, },
+	{ .name = "mov",   .ops  = &mov_ops, },
+	{ .name = "movb",  .ops  = &mov_ops, },
+	{ .name = "movdqa",.ops  = &mov_ops, },
+	{ .name = "movl",  .ops  = &mov_ops, },
+	{ .name = "movq",  .ops  = &mov_ops, },
+	{ .name = "movslq", .ops  = &mov_ops, },
+	{ .name = "movzbl", .ops  = &mov_ops, },
+	{ .name = "movzwl", .ops  = &mov_ops, },
+	{ .name = "nop",   .ops  = &nop_ops, },
+	{ .name = "nopl",  .ops  = &nop_ops, },
+	{ .name = "nopw",  .ops  = &nop_ops, },
+	{ .name = "or",    .ops  = &mov_ops, },
+	{ .name = "orl",   .ops  = &mov_ops, },
+	{ .name = "test",  .ops  = &mov_ops, },
+	{ .name = "testb", .ops  = &mov_ops, },
+	{ .name = "testl", .ops  = &mov_ops, },
+	{ .name = "xadd",  .ops  = &mov_ops, },
+	{ .name = "xbeginl", .ops  = &jump_ops, },
+	{ .name = "xbeginq", .ops  = &jump_ops, },
+};
+
+static int ins__cmp(const void *name, const void *insp)
+{
+	const struct ins *ins = insp;
+
+	return strcmp(name, ins->name);
+}
+
+static struct ins *ins__find(const char *name)
+{
+	const int nmemb = ARRAY_SIZE(instructions);
+
+	return bsearch(name, instructions, nmemb, sizeof(struct ins), ins__cmp);
+}
+
+int symbol__annotate_init(struct map *map __maybe_unused, struct symbol *sym)
+{
+	struct annotation *notes = symbol__annotation(sym);
+	pthread_mutex_init(&notes->lock, NULL);
+	return 0;
+}
+
+int symbol__alloc_hist(struct symbol *sym)
+{
+	struct annotation *notes = symbol__annotation(sym);
+	const size_t size = symbol__size(sym);
+	size_t sizeof_sym_hist;
+
+	/* Check for overflow when calculating sizeof_sym_hist */
+	if (size > (SIZE_MAX - sizeof(struct sym_hist)) / sizeof(u64))
+		return -1;
+
+	sizeof_sym_hist = (sizeof(struct sym_hist) + size * sizeof(u64));
+
+	/* Check for overflow in zalloc argument */
+	if (sizeof_sym_hist > (SIZE_MAX - sizeof(*notes->src))
+				/ symbol_conf.nr_events)
+		return -1;
+
+	notes->src = zalloc(sizeof(*notes->src) + symbol_conf.nr_events * sizeof_sym_hist);
+	if (notes->src == NULL)
+		return -1;
+	notes->src->sizeof_sym_hist = sizeof_sym_hist;
+	notes->src->nr_histograms   = symbol_conf.nr_events;
+	INIT_LIST_HEAD(&notes->src->source);
+	return 0;
+}
+
+void symbol__annotate_zero_histograms(struct symbol *sym)
+{
+	struct annotation *notes = symbol__annotation(sym);
+
+	pthread_mutex_lock(&notes->lock);
+	if (notes->src != NULL)
+		memset(notes->src->histograms, 0,
+		       notes->src->nr_histograms * notes->src->sizeof_sym_hist);
+	pthread_mutex_unlock(&notes->lock);
+}
+
+static int __symbol__inc_addr_samples(struct symbol *sym, struct map *map,
+				      struct annotation *notes, int evidx, u64 addr)
+{
+	unsigned offset;
+	struct sym_hist *h;
+
+	pr_debug3("%s: addr=%#" PRIx64 "\n", __func__, map->unmap_ip(map, addr));
+
+	if (addr < sym->start || addr > sym->end)
+		return -ERANGE;
+
+	offset = addr - sym->start;
+	h = annotation__histogram(notes, evidx);
+	h->sum++;
+	h->addr[offset]++;
+
+	pr_debug3("%#" PRIx64 " %s: period++ [addr: %#" PRIx64 ", %#" PRIx64
+		  ", evidx=%d] => %" PRIu64 "\n", sym->start, sym->name,
+		  addr, addr - sym->start, evidx, h->addr[offset]);
+	return 0;
+}
+
+static int symbol__inc_addr_samples(struct symbol *sym, struct map *map,
+				    int evidx, u64 addr)
+{
+	struct annotation *notes;
+
+	if (sym == NULL)
+		return 0;
+
+	notes = symbol__annotation(sym);
+	if (notes->src == NULL) {
+		if (symbol__alloc_hist(sym) < 0)
+			return -ENOMEM;
+	}
+
+	return __symbol__inc_addr_samples(sym, map, notes, evidx, addr);
+}
+
+int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, int evidx)
+{
+	return symbol__inc_addr_samples(ams->sym, ams->map, evidx, ams->al_addr);
+}
+
+int hist_entry__inc_addr_samples(struct hist_entry *he, int evidx, u64 ip)
+{
+	return symbol__inc_addr_samples(he->ms.sym, he->ms.map, evidx, ip);
+}
+
+static void disasm_line__init_ins(struct disasm_line *dl)
+{
+	dl->ins = ins__find(dl->name);
+
+	if (dl->ins == NULL)
+		return;
+
+	if (!dl->ins->ops)
+		return;
+
+	if (dl->ins->ops->parse)
+		dl->ins->ops->parse(&dl->ops);
+}
+
+static int disasm_line__parse(char *line, char **namep, char **rawp)
+{
+	char *name = line, tmp;
+
+	while (isspace(name[0]))
+		++name;
+
+	if (name[0] == '\0')
+		return -1;
+
+	*rawp = name + 1;
+
+	while ((*rawp)[0] != '\0' && !isspace((*rawp)[0]))
+		++*rawp;
+
+	tmp = (*rawp)[0];
+	(*rawp)[0] = '\0';
+	*namep = strdup(name);
+
+	if (*namep == NULL)
+		goto out_free_name;
+
+	(*rawp)[0] = tmp;
+
+	if ((*rawp)[0] != '\0') {
+		(*rawp)++;
+		while (isspace((*rawp)[0]))
+			++(*rawp);
+	}
+
+	return 0;
+
+out_free_name:
+	zfree(namep);
+	return -1;
+}
+
+static struct disasm_line *disasm_line__new(s64 offset, char *line, size_t privsize)
+{
+	struct disasm_line *dl = zalloc(sizeof(*dl) + privsize);
+
+	if (dl != NULL) {
+		dl->offset = offset;
+		dl->line = strdup(line);
+		if (dl->line == NULL)
+			goto out_delete;
+
+		if (offset != -1) {
+			if (disasm_line__parse(dl->line, &dl->name, &dl->ops.raw) < 0)
+				goto out_free_line;
+
+			disasm_line__init_ins(dl);
+		}
+	}
+
+	return dl;
+
+out_free_line:
+	zfree(&dl->line);
+out_delete:
+	free(dl);
+	return NULL;
+}
+
+void disasm_line__free(struct disasm_line *dl)
+{
+	zfree(&dl->line);
+	zfree(&dl->name);
+	if (dl->ins && dl->ins->ops->free)
+		dl->ins->ops->free(&dl->ops);
+	else
+		ins__delete(&dl->ops);
+	free(dl);
+}
+
+int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw)
+{
+	if (raw || !dl->ins)
+		return scnprintf(bf, size, "%-6.6s %s", dl->name, dl->ops.raw);
+
+	return ins__scnprintf(dl->ins, bf, size, &dl->ops);
+}
+
+static void disasm__add(struct list_head *head, struct disasm_line *line)
+{
+	list_add_tail(&line->node, head);
+}
+
+struct disasm_line *disasm__get_next_ip_line(struct list_head *head, struct disasm_line *pos)
+{
+	list_for_each_entry_continue(pos, head, node)
+		if (pos->offset >= 0)
+			return pos;
+
+	return NULL;
+}
+
+double disasm__calc_percent(struct annotation *notes, int evidx, s64 offset,
+			    s64 end, const char **path)
+{
+	struct source_line *src_line = notes->src->lines;
+	double percent = 0.0;
+
+	if (src_line) {
+		size_t sizeof_src_line = sizeof(*src_line) +
+				sizeof(src_line->p) * (src_line->nr_pcnt - 1);
+
+		while (offset < end) {
+			src_line = (void *)notes->src->lines +
+					(sizeof_src_line * offset);
+
+			if (*path == NULL)
+				*path = src_line->path;
+
+			percent += src_line->p[evidx].percent;
+			offset++;
+		}
+	} else {
+		struct sym_hist *h = annotation__histogram(notes, evidx);
+		unsigned int hits = 0;
+
+		while (offset < end)
+			hits += h->addr[offset++];
+
+		if (h->sum)
+			percent = 100.0 * hits / h->sum;
+	}
+
+	return percent;
+}
+
+static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 start,
+		      struct perf_evsel *evsel, u64 len, int min_pcnt, int printed,
+		      int max_lines, struct disasm_line *queue)
+{
+	static const char *prev_line;
+	static const char *prev_color;
+
+	if (dl->offset != -1) {
+		const char *path = NULL;
+		double percent, max_percent = 0.0;
+		double *ppercents = &percent;
+		int i, nr_percent = 1;
+		const char *color;
+		struct annotation *notes = symbol__annotation(sym);
+		s64 offset = dl->offset;
+		const u64 addr = start + offset;
+		struct disasm_line *next;
+
+		next = disasm__get_next_ip_line(&notes->src->source, dl);
+
+		if (perf_evsel__is_group_event(evsel)) {
+			nr_percent = evsel->nr_members;
+			ppercents = calloc(nr_percent, sizeof(double));
+			if (ppercents == NULL)
+				return -1;
+		}
+
+		for (i = 0; i < nr_percent; i++) {
+			percent = disasm__calc_percent(notes,
+					notes->src->lines ? i : evsel->idx + i,
+					offset,
+					next ? next->offset : (s64) len,
+					&path);
+
+			ppercents[i] = percent;
+			if (percent > max_percent)
+				max_percent = percent;
+		}
+
+		if (max_percent < min_pcnt)
+			return -1;
+
+		if (max_lines && printed >= max_lines)
+			return 1;
+
+		if (queue != NULL) {
+			list_for_each_entry_from(queue, &notes->src->source, node) {
+				if (queue == dl)
+					break;
+				disasm_line__print(queue, sym, start, evsel, len,
+						    0, 0, 1, NULL);
+			}
+		}
+
+		color = get_percent_color(max_percent);
+
+		/*
+		 * Also color the filename and line if needed, with
+		 * the same color than the percentage. Don't print it
+		 * twice for close colored addr with the same filename:line
+		 */
+		if (path) {
+			if (!prev_line || strcmp(prev_line, path)
+				       || color != prev_color) {
+				color_fprintf(stdout, color, " %s", path);
+				prev_line = path;
+				prev_color = color;
+			}
+		}
+
+		for (i = 0; i < nr_percent; i++) {
+			percent = ppercents[i];
+			color = get_percent_color(percent);
+			color_fprintf(stdout, color, " %7.2f", percent);
+		}
+
+		printf(" :	");
+		color_fprintf(stdout, PERF_COLOR_MAGENTA, "  %" PRIx64 ":", addr);
+		color_fprintf(stdout, PERF_COLOR_BLUE, "%s\n", dl->line);
+
+		if (ppercents != &percent)
+			free(ppercents);
+
+	} else if (max_lines && printed >= max_lines)
+		return 1;
+	else {
+		int width = 8;
+
+		if (queue)
+			return -1;
+
+		if (perf_evsel__is_group_event(evsel))
+			width *= evsel->nr_members;
+
+		if (!*dl->line)
+			printf(" %*s:\n", width, " ");
+		else
+			printf(" %*s:	%s\n", width, " ", dl->line);
+	}
+
+	return 0;
+}
+
+/*
+ * symbol__parse_objdump_line() parses objdump output (with -d --no-show-raw)
+ * which looks like following
+ *
+ *  0000000000415500 <_init>:
+ *    415500:       sub    $0x8,%rsp
+ *    415504:       mov    0x2f5ad5(%rip),%rax        # 70afe0 <_DYNAMIC+0x2f8>
+ *    41550b:       test   %rax,%rax
+ *    41550e:       je     415515 <_init+0x15>
+ *    415510:       callq  416e70 <__gmon_start__@plt>
+ *    415515:       add    $0x8,%rsp
+ *    415519:       retq
+ *
+ * it will be parsed and saved into struct disasm_line as
+ *  <offset>       <name>  <ops.raw>
+ *
+ * The offset will be a relative offset from the start of the symbol and -1
+ * means that it's not a disassembly line so should be treated differently.
+ * The ops.raw part will be parsed further according to type of the instruction.
+ */
+static int symbol__parse_objdump_line(struct symbol *sym, struct map *map,
+				      FILE *file, size_t privsize)
+{
+	struct annotation *notes = symbol__annotation(sym);
+	struct disasm_line *dl;
+	char *line = NULL, *parsed_line, *tmp, *tmp2, *c;
+	size_t line_len;
+	s64 line_ip, offset = -1;
+
+	if (getline(&line, &line_len, file) < 0)
+		return -1;
+
+	if (!line)
+		return -1;
+
+	while (line_len != 0 && isspace(line[line_len - 1]))
+		line[--line_len] = '\0';
+
+	c = strchr(line, '\n');
+	if (c)
+		*c = 0;
+
+	line_ip = -1;
+	parsed_line = line;
+
+	/*
+	 * Strip leading spaces:
+	 */
+	tmp = line;
+	while (*tmp) {
+		if (*tmp != ' ')
+			break;
+		tmp++;
+	}
+
+	if (*tmp) {
+		/*
+		 * Parse hexa addresses followed by ':'
+		 */
+		line_ip = strtoull(tmp, &tmp2, 16);
+		if (*tmp2 != ':' || tmp == tmp2 || tmp2[1] == '\0')
+			line_ip = -1;
+	}
+
+	if (line_ip != -1) {
+		u64 start = map__rip_2objdump(map, sym->start),
+		    end = map__rip_2objdump(map, sym->end);
+
+		offset = line_ip - start;
+		if ((u64)line_ip < start || (u64)line_ip > end)
+			offset = -1;
+		else
+			parsed_line = tmp2 + 1;
+	}
+
+	dl = disasm_line__new(offset, parsed_line, privsize);
+	free(line);
+
+	if (dl == NULL)
+		return -1;
+
+	if (dl->ops.target.offset == UINT64_MAX)
+		dl->ops.target.offset = dl->ops.target.addr -
+					map__rip_2objdump(map, sym->start);
+
+	/* kcore has no symbols, so add the call target name */
+	if (dl->ins && ins__is_call(dl->ins) && !dl->ops.target.name) {
+		struct addr_map_symbol target = {
+			.map = map,
+			.addr = dl->ops.target.addr,
+		};
+
+		if (!map_groups__find_ams(&target, NULL) &&
+		    target.sym->start == target.al_addr)
+			dl->ops.target.name = strdup(target.sym->name);
+	}
+
+	disasm__add(&notes->src->source, dl);
+
+	return 0;
+}
+
+static void delete_last_nop(struct symbol *sym)
+{
+	struct annotation *notes = symbol__annotation(sym);
+	struct list_head *list = &notes->src->source;
+	struct disasm_line *dl;
+
+	while (!list_empty(list)) {
+		dl = list_entry(list->prev, struct disasm_line, node);
+
+		if (dl->ins && dl->ins->ops) {
+			if (dl->ins->ops != &nop_ops)
+				return;
+		} else {
+			if (!strstr(dl->line, " nop ") &&
+			    !strstr(dl->line, " nopl ") &&
+			    !strstr(dl->line, " nopw "))
+				return;
+		}
+
+		list_del(&dl->node);
+		disasm_line__free(dl);
+	}
+}
+
+int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize)
+{
+	struct dso *dso = map->dso;
+	char *filename = dso__build_id_filename(dso, NULL, 0);
+	bool free_filename = true;
+	char command[PATH_MAX * 2];
+	FILE *file;
+	int err = 0;
+	char symfs_filename[PATH_MAX];
+	struct kcore_extract kce;
+	bool delete_extract = false;
+
+	if (filename) {
+		snprintf(symfs_filename, sizeof(symfs_filename), "%s%s",
+			 symbol_conf.symfs, filename);
+	}
+
+	if (filename == NULL) {
+		if (dso->has_build_id) {
+			pr_err("Can't annotate %s: not enough memory\n",
+			       sym->name);
+			return -ENOMEM;
+		}
+		goto fallback;
+	} else if (readlink(symfs_filename, command, sizeof(command)) < 0 ||
+		   strstr(command, "[kernel.kallsyms]") ||
+		   access(symfs_filename, R_OK)) {
+		free(filename);
+fallback:
+		/*
+		 * If we don't have build-ids or the build-id file isn't in the
+		 * cache, or is just a kallsyms file, well, lets hope that this
+		 * DSO is the same as when 'perf record' ran.
+		 */
+		filename = (char *)dso->long_name;
+		snprintf(symfs_filename, sizeof(symfs_filename), "%s%s",
+			 symbol_conf.symfs, filename);
+		free_filename = false;
+	}
+
+	if (dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS &&
+	    !dso__is_kcore(dso)) {
+		char bf[BUILD_ID_SIZE * 2 + 16] = " with build id ";
+		char *build_id_msg = NULL;
+
+		if (dso->annotate_warned)
+			goto out_free_filename;
+
+		if (dso->has_build_id) {
+			build_id__sprintf(dso->build_id,
+					  sizeof(dso->build_id), bf + 15);
+			build_id_msg = bf;
+		}
+		err = -ENOENT;
+		dso->annotate_warned = 1;
+		pr_err("Can't annotate %s:\n\n"
+		       "No vmlinux file%s\nwas found in the path.\n\n"
+		       "Please use:\n\n"
+		       "  perf buildid-cache -vu vmlinux\n\n"
+		       "or:\n\n"
+		       "  --vmlinux vmlinux\n",
+		       sym->name, build_id_msg ?: "");
+		goto out_free_filename;
+	}
+
+	pr_debug("%s: filename=%s, sym=%s, start=%#" PRIx64 ", end=%#" PRIx64 "\n", __func__,
+		 filename, sym->name, map->unmap_ip(map, sym->start),
+		 map->unmap_ip(map, sym->end));
+
+	pr_debug("annotating [%p] %30s : [%p] %30s\n",
+		 dso, dso->long_name, sym, sym->name);
+
+	if (dso__is_kcore(dso)) {
+		kce.kcore_filename = symfs_filename;
+		kce.addr = map__rip_2objdump(map, sym->start);
+		kce.offs = sym->start;
+		kce.len = sym->end + 1 - sym->start;
+		if (!kcore_extract__create(&kce)) {
+			delete_extract = true;
+			strlcpy(symfs_filename, kce.extract_filename,
+				sizeof(symfs_filename));
+			if (free_filename) {
+				free(filename);
+				free_filename = false;
+			}
+			filename = symfs_filename;
+		}
+	}
+
+	snprintf(command, sizeof(command),
+		 "%s %s%s --start-address=0x%016" PRIx64
+		 " --stop-address=0x%016" PRIx64
+		 " -d %s %s -C %s 2>/dev/null|grep -v %s|expand",
+		 objdump_path ? objdump_path : "objdump",
+		 disassembler_style ? "-M " : "",
+		 disassembler_style ? disassembler_style : "",
+		 map__rip_2objdump(map, sym->start),
+		 map__rip_2objdump(map, sym->end+1),
+		 symbol_conf.annotate_asm_raw ? "" : "--no-show-raw",
+		 symbol_conf.annotate_src ? "-S" : "",
+		 symfs_filename, filename);
+
+	pr_debug("Executing: %s\n", command);
+
+	file = popen(command, "r");
+	if (!file)
+		goto out_free_filename;
+
+	while (!feof(file))
+		if (symbol__parse_objdump_line(sym, map, file, privsize) < 0)
+			break;
+
+	/*
+	 * kallsyms does not have symbol sizes so there may a nop at the end.
+	 * Remove it.
+	 */
+	if (dso__is_kcore(dso))
+		delete_last_nop(sym);
+
+	pclose(file);
+out_free_filename:
+	if (delete_extract)
+		kcore_extract__delete(&kce);
+	if (free_filename)
+		free(filename);
+	return err;
+}
+
+static void insert_source_line(struct rb_root *root, struct source_line *src_line)
+{
+	struct source_line *iter;
+	struct rb_node **p = &root->rb_node;
+	struct rb_node *parent = NULL;
+	int i, ret;
+
+	while (*p != NULL) {
+		parent = *p;
+		iter = rb_entry(parent, struct source_line, node);
+
+		ret = strcmp(iter->path, src_line->path);
+		if (ret == 0) {
+			for (i = 0; i < src_line->nr_pcnt; i++)
+				iter->p[i].percent_sum += src_line->p[i].percent;
+			return;
+		}
+
+		if (ret < 0)
+			p = &(*p)->rb_left;
+		else
+			p = &(*p)->rb_right;
+	}
+
+	for (i = 0; i < src_line->nr_pcnt; i++)
+		src_line->p[i].percent_sum = src_line->p[i].percent;
+
+	rb_link_node(&src_line->node, parent, p);
+	rb_insert_color(&src_line->node, root);
+}
+
+static int cmp_source_line(struct source_line *a, struct source_line *b)
+{
+	int i;
+
+	for (i = 0; i < a->nr_pcnt; i++) {
+		if (a->p[i].percent_sum == b->p[i].percent_sum)
+			continue;
+		return a->p[i].percent_sum > b->p[i].percent_sum;
+	}
+
+	return 0;
+}
+
+static void __resort_source_line(struct rb_root *root, struct source_line *src_line)
+{
+	struct source_line *iter;
+	struct rb_node **p = &root->rb_node;
+	struct rb_node *parent = NULL;
+
+	while (*p != NULL) {
+		parent = *p;
+		iter = rb_entry(parent, struct source_line, node);
+
+		if (cmp_source_line(src_line, iter))
+			p = &(*p)->rb_left;
+		else
+			p = &(*p)->rb_right;
+	}
+
+	rb_link_node(&src_line->node, parent, p);
+	rb_insert_color(&src_line->node, root);
+}
+
+static void resort_source_line(struct rb_root *dest_root, struct rb_root *src_root)
+{
+	struct source_line *src_line;
+	struct rb_node *node;
+
+	node = rb_first(src_root);
+	while (node) {
+		struct rb_node *next;
+
+		src_line = rb_entry(node, struct source_line, node);
+		next = rb_next(node);
+		rb_erase(node, src_root);
+
+		__resort_source_line(dest_root, src_line);
+		node = next;
+	}
+}
+
+static void symbol__free_source_line(struct symbol *sym, int len)
+{
+	struct annotation *notes = symbol__annotation(sym);
+	struct source_line *src_line = notes->src->lines;
+	size_t sizeof_src_line;
+	int i;
+
+	sizeof_src_line = sizeof(*src_line) +
+			  (sizeof(src_line->p) * (src_line->nr_pcnt - 1));
+
+	for (i = 0; i < len; i++) {
+		free_srcline(src_line->path);
+		src_line = (void *)src_line + sizeof_src_line;
+	}
+
+	zfree(&notes->src->lines);
+}
+
+/* Get the filename:line for the colored entries */
+static int symbol__get_source_line(struct symbol *sym, struct map *map,
+				   struct perf_evsel *evsel,
+				   struct rb_root *root, int len)
+{
+	u64 start;
+	int i, k;
+	int evidx = evsel->idx;
+	struct source_line *src_line;
+	struct annotation *notes = symbol__annotation(sym);
+	struct sym_hist *h = annotation__histogram(notes, evidx);
+	struct rb_root tmp_root = RB_ROOT;
+	int nr_pcnt = 1;
+	u64 h_sum = h->sum;
+	size_t sizeof_src_line = sizeof(struct source_line);
+
+	if (perf_evsel__is_group_event(evsel)) {
+		for (i = 1; i < evsel->nr_members; i++) {
+			h = annotation__histogram(notes, evidx + i);
+			h_sum += h->sum;
+		}
+		nr_pcnt = evsel->nr_members;
+		sizeof_src_line += (nr_pcnt - 1) * sizeof(src_line->p);
+	}
+
+	if (!h_sum)
+		return 0;
+
+	src_line = notes->src->lines = calloc(len, sizeof_src_line);
+	if (!notes->src->lines)
+		return -1;
+
+	start = map__rip_2objdump(map, sym->start);
+
+	for (i = 0; i < len; i++) {
+		u64 offset;
+		double percent_max = 0.0;
+
+		src_line->nr_pcnt = nr_pcnt;
+
+		for (k = 0; k < nr_pcnt; k++) {
+			h = annotation__histogram(notes, evidx + k);
+			src_line->p[k].percent = 100.0 * h->addr[i] / h->sum;
+
+			if (src_line->p[k].percent > percent_max)
+				percent_max = src_line->p[k].percent;
+		}
+
+		if (percent_max <= 0.5)
+			goto next;
+
+		offset = start + i;
+		src_line->path = get_srcline(map->dso, offset);
+		insert_source_line(&tmp_root, src_line);
+
+	next:
+		src_line = (void *)src_line + sizeof_src_line;
+	}
+
+	resort_source_line(root, &tmp_root);
+	return 0;
+}
+
+static void print_summary(struct rb_root *root, const char *filename)
+{
+	struct source_line *src_line;
+	struct rb_node *node;
+
+	printf("\nSorted summary for file %s\n", filename);
+	printf("----------------------------------------------\n\n");
+
+	if (RB_EMPTY_ROOT(root)) {
+		printf(" Nothing higher than %1.1f%%\n", MIN_GREEN);
+		return;
+	}
+
+	node = rb_first(root);
+	while (node) {
+		double percent, percent_max = 0.0;
+		const char *color;
+		char *path;
+		int i;
+
+		src_line = rb_entry(node, struct source_line, node);
+		for (i = 0; i < src_line->nr_pcnt; i++) {
+			percent = src_line->p[i].percent_sum;
+			color = get_percent_color(percent);
+			color_fprintf(stdout, color, " %7.2f", percent);
+
+			if (percent > percent_max)
+				percent_max = percent;
+		}
+
+		path = src_line->path;
+		color = get_percent_color(percent_max);
+		color_fprintf(stdout, color, " %s\n", path);
+
+		node = rb_next(node);
+	}
+}
+
+static void symbol__annotate_hits(struct symbol *sym, struct perf_evsel *evsel)
+{
+	struct annotation *notes = symbol__annotation(sym);
+	struct sym_hist *h = annotation__histogram(notes, evsel->idx);
+	u64 len = symbol__size(sym), offset;
+
+	for (offset = 0; offset < len; ++offset)
+		if (h->addr[offset] != 0)
+			printf("%*" PRIx64 ": %" PRIu64 "\n", BITS_PER_LONG / 2,
+			       sym->start + offset, h->addr[offset]);
+	printf("%*s: %" PRIu64 "\n", BITS_PER_LONG / 2, "h->sum", h->sum);
+}
+
+int symbol__annotate_printf(struct symbol *sym, struct map *map,
+			    struct perf_evsel *evsel, bool full_paths,
+			    int min_pcnt, int max_lines, int context)
+{
+	struct dso *dso = map->dso;
+	char *filename;
+	const char *d_filename;
+	const char *evsel_name = perf_evsel__name(evsel);
+	struct annotation *notes = symbol__annotation(sym);
+	struct disasm_line *pos, *queue = NULL;
+	u64 start = map__rip_2objdump(map, sym->start);
+	int printed = 2, queue_len = 0;
+	int more = 0;
+	u64 len;
+	int width = 8;
+	int namelen, evsel_name_len, graph_dotted_len;
+
+	filename = strdup(dso->long_name);
+	if (!filename)
+		return -ENOMEM;
+
+	if (full_paths)
+		d_filename = filename;
+	else
+		d_filename = basename(filename);
+
+	len = symbol__size(sym);
+	namelen = strlen(d_filename);
+	evsel_name_len = strlen(evsel_name);
+
+	if (perf_evsel__is_group_event(evsel))
+		width *= evsel->nr_members;
+
+	printf(" %-*.*s|	Source code & Disassembly of %s for %s\n",
+	       width, width, "Percent", d_filename, evsel_name);
+
+	graph_dotted_len = width + namelen + evsel_name_len;
+	printf("-%-*.*s-----------------------------------------\n",
+	       graph_dotted_len, graph_dotted_len, graph_dotted_line);
+
+	if (verbose)
+		symbol__annotate_hits(sym, evsel);
+
+	list_for_each_entry(pos, &notes->src->source, node) {
+		if (context && queue == NULL) {
+			queue = pos;
+			queue_len = 0;
+		}
+
+		switch (disasm_line__print(pos, sym, start, evsel, len,
+					    min_pcnt, printed, max_lines,
+					    queue)) {
+		case 0:
+			++printed;
+			if (context) {
+				printed += queue_len;
+				queue = NULL;
+				queue_len = 0;
+			}
+			break;
+		case 1:
+			/* filtered by max_lines */
+			++more;
+			break;
+		case -1:
+		default:
+			/*
+			 * Filtered by min_pcnt or non IP lines when
+			 * context != 0
+			 */
+			if (!context)
+				break;
+			if (queue_len == context)
+				queue = list_entry(queue->node.next, typeof(*queue), node);
+			else
+				++queue_len;
+			break;
+		}
+	}
+
+	free(filename);
+
+	return more;
+}
+
+void symbol__annotate_zero_histogram(struct symbol *sym, int evidx)
+{
+	struct annotation *notes = symbol__annotation(sym);
+	struct sym_hist *h = annotation__histogram(notes, evidx);
+
+	memset(h, 0, notes->src->sizeof_sym_hist);
+}
+
+void symbol__annotate_decay_histogram(struct symbol *sym, int evidx)
+{
+	struct annotation *notes = symbol__annotation(sym);
+	struct sym_hist *h = annotation__histogram(notes, evidx);
+	int len = symbol__size(sym), offset;
+
+	h->sum = 0;
+	for (offset = 0; offset < len; ++offset) {
+		h->addr[offset] = h->addr[offset] * 7 / 8;
+		h->sum += h->addr[offset];
+	}
+}
+
+void disasm__purge(struct list_head *head)
+{
+	struct disasm_line *pos, *n;
+
+	list_for_each_entry_safe(pos, n, head, node) {
+		list_del(&pos->node);
+		disasm_line__free(pos);
+	}
+}
+
+static size_t disasm_line__fprintf(struct disasm_line *dl, FILE *fp)
+{
+	size_t printed;
+
+	if (dl->offset == -1)
+		return fprintf(fp, "%s\n", dl->line);
+
+	printed = fprintf(fp, "%#" PRIx64 " %s", dl->offset, dl->name);
+
+	if (dl->ops.raw[0] != '\0') {
+		printed += fprintf(fp, "%.*s %s\n", 6 - (int)printed, " ",
+				   dl->ops.raw);
+	}
+
+	return printed + fprintf(fp, "\n");
+}
+
+size_t disasm__fprintf(struct list_head *head, FILE *fp)
+{
+	struct disasm_line *pos;
+	size_t printed = 0;
+
+	list_for_each_entry(pos, head, node)
+		printed += disasm_line__fprintf(pos, fp);
+
+	return printed;
+}
+
+int symbol__tty_annotate(struct symbol *sym, struct map *map,
+			 struct perf_evsel *evsel, bool print_lines,
+			 bool full_paths, int min_pcnt, int max_lines)
+{
+	struct dso *dso = map->dso;
+	struct rb_root source_line = RB_ROOT;
+	u64 len;
+
+	if (symbol__annotate(sym, map, 0) < 0)
+		return -1;
+
+	len = symbol__size(sym);
+
+	if (print_lines) {
+		symbol__get_source_line(sym, map, evsel, &source_line, len);
+		print_summary(&source_line, dso->long_name);
+	}
+
+	symbol__annotate_printf(sym, map, evsel, full_paths,
+				min_pcnt, max_lines, 0);
+	if (print_lines)
+		symbol__free_source_line(sym, len);
+
+	disasm__purge(&symbol__annotation(sym)->src->source);
+
+	return 0;
+}
+
+int hist_entry__annotate(struct hist_entry *he, size_t privsize)
+{
+	return symbol__annotate(he->ms.sym, he->ms.map, privsize);
+}
+
+bool ui__has_annotation(void)
+{
+	return use_browser == 1 && sort__has_sym;
+}
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
new file mode 100644
index 00000000000..112d6e26815
--- /dev/null
+++ b/tools/perf/util/annotate.h
@@ -0,0 +1,177 @@
+#ifndef __PERF_ANNOTATE_H
+#define __PERF_ANNOTATE_H
+
+#include <stdbool.h>
+#include <stdint.h>
+#include <linux/types.h>
+#include "symbol.h"
+#include "hist.h"
+#include "sort.h"
+#include <linux/list.h>
+#include <linux/rbtree.h>
+#include <pthread.h>
+
+struct ins;
+
+struct ins_operands {
+	char	*raw;
+	struct {
+		char	*raw;
+		char	*name;
+		u64	addr;
+		u64	offset;
+	} target;
+	union {
+		struct {
+			char	*raw;
+			char	*name;
+			u64	addr;
+		} source;
+		struct {
+			struct ins *ins;
+			struct ins_operands *ops;
+		} locked;
+	};
+};
+
+struct ins_ops {
+	void (*free)(struct ins_operands *ops);
+	int (*parse)(struct ins_operands *ops);
+	int (*scnprintf)(struct ins *ins, char *bf, size_t size,
+			 struct ins_operands *ops);
+};
+
+struct ins {
+	const char     *name;
+	struct ins_ops *ops;
+};
+
+bool ins__is_jump(const struct ins *ins);
+bool ins__is_call(const struct ins *ins);
+int ins__scnprintf(struct ins *ins, char *bf, size_t size, struct ins_operands *ops);
+
+struct annotation;
+
+struct disasm_line {
+	struct list_head    node;
+	s64		    offset;
+	char		    *line;
+	char		    *name;
+	struct ins	    *ins;
+	struct ins_operands ops;
+};
+
+static inline bool disasm_line__has_offset(const struct disasm_line *dl)
+{
+	return dl->ops.target.offset != UINT64_MAX;
+}
+
+void disasm_line__free(struct disasm_line *dl);
+struct disasm_line *disasm__get_next_ip_line(struct list_head *head, struct disasm_line *pos);
+int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw);
+size_t disasm__fprintf(struct list_head *head, FILE *fp);
+double disasm__calc_percent(struct annotation *notes, int evidx, s64 offset,
+			    s64 end, const char **path);
+
+struct sym_hist {
+	u64		sum;
+	u64		addr[0];
+};
+
+struct source_line_percent {
+	double		percent;
+	double		percent_sum;
+};
+
+struct source_line {
+	struct rb_node	node;
+	char		*path;
+	int		nr_pcnt;
+	struct source_line_percent p[1];
+};
+
+/** struct annotated_source - symbols with hits have this attached as in sannotation
+ *
+ * @histogram: Array of addr hit histograms per event being monitored
+ * @lines: If 'print_lines' is specified, per source code line percentages
+ * @source: source parsed from a disassembler like objdump -dS
+ *
+ * lines is allocated, percentages calculated and all sorted by percentage
+ * when the annotation is about to be presented, so the percentages are for
+ * one of the entries in the histogram array, i.e. for the event/counter being
+ * presented. It is deallocated right after symbol__{tui,tty,etc}_annotate
+ * returns.
+ */
+struct annotated_source {
+	struct list_head   source;
+	struct source_line *lines;
+	int    		   nr_histograms;
+	int    		   sizeof_sym_hist;
+	struct sym_hist	   histograms[0];
+};
+
+struct annotation {
+	pthread_mutex_t		lock;
+	struct annotated_source *src;
+};
+
+struct sannotation {
+	struct annotation annotation;
+	struct symbol	  symbol;
+};
+
+static inline struct sym_hist *annotation__histogram(struct annotation *notes, int idx)
+{
+	return (((void *)&notes->src->histograms) +
+	 	(notes->src->sizeof_sym_hist * idx));
+}
+
+static inline struct annotation *symbol__annotation(struct symbol *sym)
+{
+	struct sannotation *a = container_of(sym, struct sannotation, symbol);
+	return &a->annotation;
+}
+
+int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, int evidx);
+
+int hist_entry__inc_addr_samples(struct hist_entry *he, int evidx, u64 addr);
+
+int symbol__alloc_hist(struct symbol *sym);
+void symbol__annotate_zero_histograms(struct symbol *sym);
+
+int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize);
+
+int hist_entry__annotate(struct hist_entry *he, size_t privsize);
+
+int symbol__annotate_init(struct map *map __maybe_unused, struct symbol *sym);
+int symbol__annotate_printf(struct symbol *sym, struct map *map,
+			    struct perf_evsel *evsel, bool full_paths,
+			    int min_pcnt, int max_lines, int context);
+void symbol__annotate_zero_histogram(struct symbol *sym, int evidx);
+void symbol__annotate_decay_histogram(struct symbol *sym, int evidx);
+void disasm__purge(struct list_head *head);
+
+bool ui__has_annotation(void);
+
+int symbol__tty_annotate(struct symbol *sym, struct map *map,
+			 struct perf_evsel *evsel, bool print_lines,
+			 bool full_paths, int min_pcnt, int max_lines);
+
+#ifdef HAVE_SLANG_SUPPORT
+int symbol__tui_annotate(struct symbol *sym, struct map *map,
+			 struct perf_evsel *evsel,
+			 struct hist_browser_timer *hbt);
+#else
+static inline int symbol__tui_annotate(struct symbol *sym __maybe_unused,
+				struct map *map __maybe_unused,
+				struct perf_evsel *evsel  __maybe_unused,
+				struct hist_browser_timer *hbt
+				__maybe_unused)
+{
+	return 0;
+}
+#endif
+
+extern const char	*disassembler_style;
+
+#endif	/* __PERF_ANNOTATE_H */
diff --git a/tools/perf/util/bitmap.c b/tools/perf/util/bitmap.c
index 5e230acae1e..0a1adc1111f 100644
--- a/tools/perf/util/bitmap.c
+++ b/tools/perf/util/bitmap.c
@@ -19,3 +19,13 @@ int __bitmap_weight(const unsigned long *bitmap, int bits)
 
 	return w;
 }
+
+void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
+		 const unsigned long *bitmap2, int bits)
+{
+	int k;
+	int nr = BITS_TO_LONGS(bits);
+
+	for (k = 0; k < nr; k++)
+		dst[k] = bitmap1[k] | bitmap2[k];
+}
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 70c5cf87d02..a904a4cfe7d 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -12,12 +12,20 @@
 #include "event.h"
 #include "symbol.h"
 #include <linux/kernel.h>
+#include "debug.h"
+#include "session.h"
+#include "tool.h"
 
-static int build_id__mark_dso_hit(event_t *event, struct perf_session *session)
+int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused,
+			   union perf_event *event,
+			   struct perf_sample *sample,
+			   struct perf_evsel *evsel __maybe_unused,
+			   struct machine *machine)
 {
 	struct addr_location al;
 	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
-	struct thread *thread = perf_session__findnew(session, event->ip.pid);
+	struct thread *thread = machine__findnew_thread(machine, sample->pid,
+							sample->tid);
 
 	if (thread == NULL) {
 		pr_err("problem processing %d event, skipping it.\n",
@@ -25,8 +33,8 @@ static int build_id__mark_dso_hit(event_t *event, struct perf_session *session)
 		return -1;
 	}
 
-	thread__find_addr_map(thread, session, cpumode, MAP__FUNCTION,
-			      event->ip.pid, event->ip.ip, &al);
+	thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION,
+			      sample->ip, &al);
 
 	if (al.map != NULL)
 		al.map->dso->hit = 1;
@@ -34,28 +42,67 @@ static int build_id__mark_dso_hit(event_t *event, struct perf_session *session)
 	return 0;
 }
 
-struct perf_event_ops build_id__mark_dso_hit_ops = {
+static int perf_event__exit_del_thread(struct perf_tool *tool __maybe_unused,
+				       union perf_event *event,
+				       struct perf_sample *sample
+				       __maybe_unused,
+				       struct machine *machine)
+{
+	struct thread *thread = machine__findnew_thread(machine,
+							event->fork.pid,
+							event->fork.tid);
+
+	dump_printf("(%d:%d):(%d:%d)\n", event->fork.pid, event->fork.tid,
+		    event->fork.ppid, event->fork.ptid);
+
+	if (thread) {
+		rb_erase(&thread->rb_node, &machine->threads);
+		machine->last_match = NULL;
+		thread__delete(thread);
+	}
+
+	return 0;
+}
+
+struct perf_tool build_id__mark_dso_hit_ops = {
 	.sample	= build_id__mark_dso_hit,
-	.mmap	= event__process_mmap,
-	.fork	= event__process_task,
+	.mmap	= perf_event__process_mmap,
+	.mmap2	= perf_event__process_mmap2,
+	.fork	= perf_event__process_fork,
+	.exit	= perf_event__exit_del_thread,
+	.attr		 = perf_event__process_attr,
+	.build_id	 = perf_event__process_build_id,
 };
 
-char *dso__build_id_filename(struct dso *self, char *bf, size_t size)
+int build_id__sprintf(const u8 *build_id, int len, char *bf)
+{
+	char *bid = bf;
+	const u8 *raw = build_id;
+	int i;
+
+	for (i = 0; i < len; ++i) {
+		sprintf(bid, "%02x", *raw);
+		++raw;
+		bid += 2;
+	}
+
+	return raw - build_id;
+}
+
+char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size)
 {
 	char build_id_hex[BUILD_ID_SIZE * 2 + 1];
-	const char *home;
 
-	if (!self->has_build_id)
+	if (!dso->has_build_id)
 		return NULL;
 
-	build_id__sprintf(self->build_id, sizeof(self->build_id), build_id_hex);
-	home = getenv("HOME");
+	build_id__sprintf(dso->build_id, sizeof(dso->build_id), build_id_hex);
 	if (bf == NULL) {
-		if (asprintf(&bf, "%s/%s/.build-id/%.2s/%s", home,
-			     DEBUG_CACHE_DIR, build_id_hex, build_id_hex + 2) < 0)
+		if (asprintf(&bf, "%s/.build-id/%.2s/%s", buildid_dir,
+			     build_id_hex, build_id_hex + 2) < 0)
 			return NULL;
 	} else
-		snprintf(bf, size, "%s/%s/.build-id/%.2s/%s", home,
-			 DEBUG_CACHE_DIR, build_id_hex, build_id_hex + 2);
+		snprintf(bf, size, "%s/.build-id/%.2s/%s", buildid_dir,
+			 build_id_hex, build_id_hex + 2);
 	return bf;
 }
diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h
index 5dafb00eaa0..ae392561470 100644
--- a/tools/perf/util/build-id.h
+++ b/tools/perf/util/build-id.h
@@ -1,10 +1,18 @@
 #ifndef PERF_BUILD_ID_H_
 #define PERF_BUILD_ID_H_ 1
 
-#include "session.h"
+#define BUILD_ID_SIZE 20
 
-extern struct perf_event_ops build_id__mark_dso_hit_ops;
+#include "tool.h"
+#include <linux/types.h>
 
-char *dso__build_id_filename(struct dso *self, char *bf, size_t size);
+extern struct perf_tool build_id__mark_dso_hit_ops;
+struct dso;
 
+int build_id__sprintf(const u8 *build_id, int len, char *bf);
+char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size);
+
+int build_id__mark_dso_hit(struct perf_tool *tool, union perf_event *event,
+			   struct perf_sample *sample, struct perf_evsel *evsel,
+			   struct machine *machine);
 #endif
diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h
index 65fe664fddf..7b176dd02e1 100644
--- a/tools/perf/util/cache.h
+++ b/tools/perf/util/cache.h
@@ -5,6 +5,7 @@
 #include "util.h"
 #include "strbuf.h"
 #include "../perf.h"
+#include "../ui/ui.h"
 
 #define CMD_EXEC_PATH "--exec-path"
 #define CMD_PERF_DIR "--perf-dir="
@@ -23,6 +24,7 @@ extern int perf_config(config_fn_t fn, void *);
 extern int perf_config_int(const char *, const char *);
 extern int perf_config_bool(const char *, const char *);
 extern int config_error_nonbool(const char *);
+extern const char *perf_config_dirname(const char *, const char *);
 
 /* pager.c */
 extern void setup_pager(void);
@@ -30,19 +32,6 @@ extern const char *pager_program;
 extern int pager_in_use(void);
 extern int pager_use_color;
 
-extern int use_browser;
-
-#ifdef NO_NEWT_SUPPORT
-static inline void setup_browser(void)
-{
-	setup_pager();
-}
-static inline void exit_browser(bool wait_for_ok __used) {}
-#else
-void setup_browser(void);
-void exit_browser(bool wait_for_ok);
-#endif
-
 char *alias_lookup(const char *alias);
 int split_cmdline(char *cmdline, const char ***argv);
 
@@ -81,6 +70,7 @@ extern char *perf_path(const char *fmt, ...) __attribute__((format (printf, 1, 2
 extern char *perf_pathdup(const char *fmt, ...)
 	__attribute__((format (printf, 1, 2)));
 
+/* Matches the libc/libbsd function attribute so we declare this unconditionally: */
 extern size_t strlcpy(char *dest, const char *src, size_t size);
 
 #endif /* __PERF_CACHE_H */
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 62b69ad4aa7..48b6d3f5001 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2009-2010, Frederic Weisbecker <fweisbec@gmail.com>
+ * Copyright (C) 2009-2011, Frederic Weisbecker <fweisbec@gmail.com>
  *
  * Handle the callchains from the stream in an ad-hoc radix tree and then
  * sort them in an rbtree.
@@ -15,18 +15,93 @@
 #include <errno.h>
 #include <math.h>
 
+#include "asm/bug.h"
+
+#include "hist.h"
 #include "util.h"
+#include "sort.h"
+#include "machine.h"
 #include "callchain.h"
 
-bool ip_callchain__valid(struct ip_callchain *chain, event_t *event)
+__thread struct callchain_cursor callchain_cursor;
+
+int
+parse_callchain_report_opt(const char *arg)
 {
-	unsigned int chain_size = event->header.size;
-	chain_size -= (unsigned long)&event->ip.__more_data - (unsigned long)event;
-	return chain->nr * sizeof(u64) <= chain_size;
-}
+	char *tok, *tok2;
+	char *endptr;
+
+	symbol_conf.use_callchain = true;
+
+	if (!arg)
+		return 0;
+
+	tok = strtok((char *)arg, ",");
+	if (!tok)
+		return -1;
+
+	/* get the output mode */
+	if (!strncmp(tok, "graph", strlen(arg))) {
+		callchain_param.mode = CHAIN_GRAPH_ABS;
+
+	} else if (!strncmp(tok, "flat", strlen(arg))) {
+		callchain_param.mode = CHAIN_FLAT;
+	} else if (!strncmp(tok, "fractal", strlen(arg))) {
+		callchain_param.mode = CHAIN_GRAPH_REL;
+	} else if (!strncmp(tok, "none", strlen(arg))) {
+		callchain_param.mode = CHAIN_NONE;
+		symbol_conf.use_callchain = false;
+		return 0;
+	} else {
+		return -1;
+	}
 
-#define chain_for_each_child(child, parent)	\
-	list_for_each_entry(child, &parent->children, brothers)
+	/* get the min percentage */
+	tok = strtok(NULL, ",");
+	if (!tok)
+		goto setup;
+
+	callchain_param.min_percent = strtod(tok, &endptr);
+	if (tok == endptr)
+		return -1;
+
+	/* get the print limit */
+	tok2 = strtok(NULL, ",");
+	if (!tok2)
+		goto setup;
+
+	if (tok2[0] != 'c') {
+		callchain_param.print_limit = strtoul(tok2, &endptr, 0);
+		tok2 = strtok(NULL, ",");
+		if (!tok2)
+			goto setup;
+	}
+
+	/* get the call chain order */
+	if (!strncmp(tok2, "caller", strlen("caller")))
+		callchain_param.order = ORDER_CALLER;
+	else if (!strncmp(tok2, "callee", strlen("callee")))
+		callchain_param.order = ORDER_CALLEE;
+	else
+		return -1;
+
+	/* Get the sort key */
+	tok2 = strtok(NULL, ",");
+	if (!tok2)
+		goto setup;
+	if (!strncmp(tok2, "function", strlen("function")))
+		callchain_param.key = CCKEY_FUNCTION;
+	else if (!strncmp(tok2, "address", strlen("address")))
+		callchain_param.key = CCKEY_ADDRESS;
+	else
+		return -1;
+setup:
+	if (callchain_register_param(&callchain_param) < 0) {
+		pr_err("Can't register callchain params\n");
+		return -1;
+	}
+	return 0;
+}
 
 static void
 rb_insert_callchain(struct rb_root *root, struct callchain_node *chain,
@@ -35,14 +110,14 @@ rb_insert_callchain(struct rb_root *root, struct callchain_node *chain,
 	struct rb_node **p = &root->rb_node;
 	struct rb_node *parent = NULL;
 	struct callchain_node *rnode;
-	u64 chain_cumul = cumul_hits(chain);
+	u64 chain_cumul = callchain_cumul_hits(chain);
 
 	while (*p) {
 		u64 rnode_cumul;
 
 		parent = *p;
 		rnode = rb_entry(parent, struct callchain_node, rb_node);
-		rnode_cumul = cumul_hits(rnode);
+		rnode_cumul = callchain_cumul_hits(rnode);
 
 		switch (mode) {
 		case CHAIN_FLAT:
@@ -72,10 +147,16 @@ static void
 __sort_chain_flat(struct rb_root *rb_root, struct callchain_node *node,
 		  u64 min_hit)
 {
+	struct rb_node *n;
 	struct callchain_node *child;
 
-	chain_for_each_child(child, node)
+	n = rb_first(&node->rb_root_in);
+	while (n) {
+		child = rb_entry(n, struct callchain_node, rb_node_in);
+		n = rb_next(n);
+
 		__sort_chain_flat(rb_root, child, min_hit);
+	}
 
 	if (node->hit && node->hit >= min_hit)
 		rb_insert_callchain(rb_root, node, CHAIN_FLAT);
@@ -86,61 +167,71 @@ __sort_chain_flat(struct rb_root *rb_root, struct callchain_node *node,
  * sort them by hit
  */
 static void
-sort_chain_flat(struct rb_root *rb_root, struct callchain_node *node,
-		u64 min_hit, struct callchain_param *param __used)
+sort_chain_flat(struct rb_root *rb_root, struct callchain_root *root,
+		u64 min_hit, struct callchain_param *param __maybe_unused)
 {
-	__sort_chain_flat(rb_root, node, min_hit);
+	__sort_chain_flat(rb_root, &root->node, min_hit);
 }
 
 static void __sort_chain_graph_abs(struct callchain_node *node,
 				   u64 min_hit)
 {
+	struct rb_node *n;
 	struct callchain_node *child;
 
 	node->rb_root = RB_ROOT;
+	n = rb_first(&node->rb_root_in);
+
+	while (n) {
+		child = rb_entry(n, struct callchain_node, rb_node_in);
+		n = rb_next(n);
 
-	chain_for_each_child(child, node) {
 		__sort_chain_graph_abs(child, min_hit);
-		if (cumul_hits(child) >= min_hit)
+		if (callchain_cumul_hits(child) >= min_hit)
 			rb_insert_callchain(&node->rb_root, child,
 					    CHAIN_GRAPH_ABS);
 	}
 }
 
 static void
-sort_chain_graph_abs(struct rb_root *rb_root, struct callchain_node *chain_root,
-		     u64 min_hit, struct callchain_param *param __used)
+sort_chain_graph_abs(struct rb_root *rb_root, struct callchain_root *chain_root,
+		     u64 min_hit, struct callchain_param *param __maybe_unused)
 {
-	__sort_chain_graph_abs(chain_root, min_hit);
-	rb_root->rb_node = chain_root->rb_root.rb_node;
+	__sort_chain_graph_abs(&chain_root->node, min_hit);
+	rb_root->rb_node = chain_root->node.rb_root.rb_node;
 }
 
 static void __sort_chain_graph_rel(struct callchain_node *node,
 				   double min_percent)
 {
+	struct rb_node *n;
 	struct callchain_node *child;
 	u64 min_hit;
 
 	node->rb_root = RB_ROOT;
 	min_hit = ceil(node->children_hit * min_percent);
 
-	chain_for_each_child(child, node) {
+	n = rb_first(&node->rb_root_in);
+	while (n) {
+		child = rb_entry(n, struct callchain_node, rb_node_in);
+		n = rb_next(n);
+
 		__sort_chain_graph_rel(child, min_percent);
-		if (cumul_hits(child) >= min_hit)
+		if (callchain_cumul_hits(child) >= min_hit)
 			rb_insert_callchain(&node->rb_root, child,
 					    CHAIN_GRAPH_REL);
 	}
 }
 
 static void
-sort_chain_graph_rel(struct rb_root *rb_root, struct callchain_node *chain_root,
-		     u64 min_hit __used, struct callchain_param *param)
+sort_chain_graph_rel(struct rb_root *rb_root, struct callchain_root *chain_root,
+		     u64 min_hit __maybe_unused, struct callchain_param *param)
 {
-	__sort_chain_graph_rel(chain_root, param->min_percent / 100.0);
-	rb_root->rb_node = chain_root->rb_root.rb_node;
+	__sort_chain_graph_rel(&chain_root->node, param->min_percent / 100.0);
+	rb_root->rb_node = chain_root->node.rb_root.rb_node;
 }
 
-int register_callchain_param(struct callchain_param *param)
+int callchain_register_param(struct callchain_param *param)
 {
 	switch (param->mode) {
 	case CHAIN_GRAPH_ABS:
@@ -174,44 +265,46 @@ create_child(struct callchain_node *parent, bool inherit_children)
 		return NULL;
 	}
 	new->parent = parent;
-	INIT_LIST_HEAD(&new->children);
 	INIT_LIST_HEAD(&new->val);
 
 	if (inherit_children) {
-		struct callchain_node *next;
+		struct rb_node *n;
+		struct callchain_node *child;
 
-		list_splice(&parent->children, &new->children);
-		INIT_LIST_HEAD(&parent->children);
+		new->rb_root_in = parent->rb_root_in;
+		parent->rb_root_in = RB_ROOT;
 
-		chain_for_each_child(next, new)
-			next->parent = new;
+		n = rb_first(&new->rb_root_in);
+		while (n) {
+			child = rb_entry(n, struct callchain_node, rb_node_in);
+			child->parent = new;
+			n = rb_next(n);
+		}
+
+		/* make it the first child */
+		rb_link_node(&new->rb_node_in, NULL, &parent->rb_root_in.rb_node);
+		rb_insert_color(&new->rb_node_in, &parent->rb_root_in);
 	}
-	list_add_tail(&new->brothers, &parent->children);
 
 	return new;
 }
 
 
-struct resolved_ip {
-	u64		  ip;
-	struct map_symbol ms;
-};
-
-struct resolved_chain {
-	u64			nr;
-	struct resolved_ip	ips[0];
-};
-
-
 /*
  * Fill the node with callchain values
  */
 static void
-fill_node(struct callchain_node *node, struct resolved_chain *chain, int start)
+fill_node(struct callchain_node *node, struct callchain_cursor *cursor)
 {
-	unsigned int i;
+	struct callchain_cursor_node *cursor_node;
+
+	node->val_nr = cursor->nr - cursor->pos;
+	if (!node->val_nr)
+		pr_warning("Warning: empty node in callchain tree\n");
+
+	cursor_node = callchain_cursor_current(cursor);
 
-	for (i = start; i < chain->nr; i++) {
+	while (cursor_node) {
 		struct callchain_list *call;
 
 		call = zalloc(sizeof(*call));
@@ -219,26 +312,41 @@ fill_node(struct callchain_node *node, struct resolved_chain *chain, int start)
 			perror("not enough memory for the code path tree");
 			return;
 		}
-		call->ip = chain->ips[i].ip;
-		call->ms = chain->ips[i].ms;
+		call->ip = cursor_node->ip;
+		call->ms.sym = cursor_node->sym;
+		call->ms.map = cursor_node->map;
 		list_add_tail(&call->list, &node->val);
+
+		callchain_cursor_advance(cursor);
+		cursor_node = callchain_cursor_current(cursor);
 	}
-	node->val_nr = chain->nr - start;
-	if (!node->val_nr)
-		pr_warning("Warning: empty node in callchain tree\n");
 }
 
-static void
-add_child(struct callchain_node *parent, struct resolved_chain *chain,
-	  int start)
+static struct callchain_node *
+add_child(struct callchain_node *parent,
+	  struct callchain_cursor *cursor,
+	  u64 period)
 {
 	struct callchain_node *new;
 
 	new = create_child(parent, false);
-	fill_node(new, chain, start);
+	fill_node(new, cursor);
 
 	new->children_hit = 0;
-	new->hit = 1;
+	new->hit = period;
+	return new;
+}
+
+static s64 match_chain(struct callchain_cursor_node *node,
+		      struct callchain_list *cnode)
+{
+	struct symbol *sym = node->sym;
+
+	if (cnode->ms.sym && sym &&
+	    callchain_param.key == CCKEY_FUNCTION)
+		return cnode->ms.sym->start - sym->start;
+	else
+		return cnode->ip - node->ip;
 }
 
 /*
@@ -247,8 +355,10 @@ add_child(struct callchain_node *parent, struct resolved_chain *chain,
  * Then create another child to host the given callchain of new branch
  */
 static void
-split_add_child(struct callchain_node *parent, struct resolved_chain *chain,
-		struct callchain_list *to_split, int idx_parents, int idx_local)
+split_add_child(struct callchain_node *parent,
+		struct callchain_cursor *cursor,
+		struct callchain_list *to_split,
+		u64 idx_parents, u64 idx_local, u64 period)
 {
 	struct callchain_node *new;
 	struct list_head *old_tail;
@@ -268,138 +378,297 @@ split_add_child(struct callchain_node *parent, struct resolved_chain *chain,
 	/* split the hits */
 	new->hit = parent->hit;
 	new->children_hit = parent->children_hit;
-	parent->children_hit = cumul_hits(new);
+	parent->children_hit = callchain_cumul_hits(new);
 	new->val_nr = parent->val_nr - idx_local;
 	parent->val_nr = idx_local;
 
 	/* create a new child for the new branch if any */
-	if (idx_total < chain->nr) {
+	if (idx_total < cursor->nr) {
+		struct callchain_node *first;
+		struct callchain_list *cnode;
+		struct callchain_cursor_node *node;
+		struct rb_node *p, **pp;
+
 		parent->hit = 0;
-		add_child(parent, chain, idx_total);
-		parent->children_hit++;
+		parent->children_hit += period;
+
+		node = callchain_cursor_current(cursor);
+		new = add_child(parent, cursor, period);
+
+		/*
+		 * This is second child since we moved parent's children
+		 * to new (first) child above.
+		 */
+		p = parent->rb_root_in.rb_node;
+		first = rb_entry(p, struct callchain_node, rb_node_in);
+		cnode = list_first_entry(&first->val, struct callchain_list,
+					 list);
+
+		if (match_chain(node, cnode) < 0)
+			pp = &p->rb_left;
+		else
+			pp = &p->rb_right;
+
+		rb_link_node(&new->rb_node_in, p, pp);
+		rb_insert_color(&new->rb_node_in, &parent->rb_root_in);
 	} else {
-		parent->hit = 1;
+		parent->hit = period;
 	}
 }
 
 static int
-__append_chain(struct callchain_node *root, struct resolved_chain *chain,
-	       unsigned int start);
+append_chain(struct callchain_node *root,
+	     struct callchain_cursor *cursor,
+	     u64 period);
 
 static void
-__append_chain_children(struct callchain_node *root,
-			struct resolved_chain *chain,
-			unsigned int start)
+append_chain_children(struct callchain_node *root,
+		      struct callchain_cursor *cursor,
+		      u64 period)
 {
 	struct callchain_node *rnode;
+	struct callchain_cursor_node *node;
+	struct rb_node **p = &root->rb_root_in.rb_node;
+	struct rb_node *parent = NULL;
+
+	node = callchain_cursor_current(cursor);
+	if (!node)
+		return;
 
 	/* lookup in childrens */
-	chain_for_each_child(rnode, root) {
-		unsigned int ret = __append_chain(rnode, chain, start);
+	while (*p) {
+		s64 ret;
+
+		parent = *p;
+		rnode = rb_entry(parent, struct callchain_node, rb_node_in);
 
-		if (!ret)
+		/* If at least first entry matches, rely to children */
+		ret = append_chain(rnode, cursor, period);
+		if (ret == 0)
 			goto inc_children_hit;
+
+		if (ret < 0)
+			p = &parent->rb_left;
+		else
+			p = &parent->rb_right;
 	}
 	/* nothing in children, add to the current node */
-	add_child(root, chain, start);
+	rnode = add_child(root, cursor, period);
+	rb_link_node(&rnode->rb_node_in, parent, p);
+	rb_insert_color(&rnode->rb_node_in, &root->rb_root_in);
 
 inc_children_hit:
-	root->children_hit++;
+	root->children_hit += period;
 }
 
 static int
-__append_chain(struct callchain_node *root, struct resolved_chain *chain,
-	       unsigned int start)
+append_chain(struct callchain_node *root,
+	     struct callchain_cursor *cursor,
+	     u64 period)
 {
 	struct callchain_list *cnode;
-	unsigned int i = start;
+	u64 start = cursor->pos;
 	bool found = false;
+	u64 matches;
+	int cmp = 0;
 
 	/*
 	 * Lookup in the current node
 	 * If we have a symbol, then compare the start to match
-	 * anywhere inside a function.
+	 * anywhere inside a function, unless function
+	 * mode is disabled.
 	 */
 	list_for_each_entry(cnode, &root->val, list) {
-		struct symbol *sym;
+		struct callchain_cursor_node *node;
 
-		if (i == chain->nr)
+		node = callchain_cursor_current(cursor);
+		if (!node)
 			break;
 
-		sym = chain->ips[i].ms.sym;
-
-		if (cnode->ms.sym && sym) {
-			if (cnode->ms.sym->start != sym->start)
-				break;
-		} else if (cnode->ip != chain->ips[i].ip)
+		cmp = match_chain(node, cnode);
+		if (cmp)
 			break;
 
-		if (!found)
-			found = true;
-		i++;
+		found = true;
+
+		callchain_cursor_advance(cursor);
 	}
 
-	/* matches not, relay on the parent */
-	if (!found)
-		return -1;
+	/* matches not, relay no the parent */
+	if (!found) {
+		WARN_ONCE(!cmp, "Chain comparison error\n");
+		return cmp;
+	}
+
+	matches = cursor->pos - start;
 
 	/* we match only a part of the node. Split it and add the new chain */
-	if (i - start < root->val_nr) {
-		split_add_child(root, chain, cnode, start, i - start);
+	if (matches < root->val_nr) {
+		split_add_child(root, cursor, cnode, start, matches, period);
 		return 0;
 	}
 
 	/* we match 100% of the path, increment the hit */
-	if (i - start == root->val_nr && i == chain->nr) {
-		root->hit++;
+	if (matches == root->val_nr && cursor->pos == cursor->nr) {
+		root->hit += period;
 		return 0;
 	}
 
 	/* We match the node and still have a part remaining */
-	__append_chain_children(root, chain, i);
+	append_chain_children(root, cursor, period);
+
+	return 0;
+}
+
+int callchain_append(struct callchain_root *root,
+		     struct callchain_cursor *cursor,
+		     u64 period)
+{
+	if (!cursor->nr)
+		return 0;
+
+	callchain_cursor_commit(cursor);
+
+	append_chain_children(&root->node, cursor, period);
+
+	if (cursor->nr > root->max_depth)
+		root->max_depth = cursor->nr;
 
 	return 0;
 }
 
-static void filter_context(struct ip_callchain *old, struct resolved_chain *new,
-			   struct map_symbol *syms)
+static int
+merge_chain_branch(struct callchain_cursor *cursor,
+		   struct callchain_node *dst, struct callchain_node *src)
 {
-	int i, j = 0;
+	struct callchain_cursor_node **old_last = cursor->last;
+	struct callchain_node *child;
+	struct callchain_list *list, *next_list;
+	struct rb_node *n;
+	int old_pos = cursor->nr;
+	int err = 0;
+
+	list_for_each_entry_safe(list, next_list, &src->val, list) {
+		callchain_cursor_append(cursor, list->ip,
+					list->ms.map, list->ms.sym);
+		list_del(&list->list);
+		free(list);
+	}
+
+	if (src->hit) {
+		callchain_cursor_commit(cursor);
+		append_chain_children(dst, cursor, src->hit);
+	}
 
-	for (i = 0; i < (int)old->nr; i++) {
-		if (old->ips[i] >= PERF_CONTEXT_MAX)
-			continue;
+	n = rb_first(&src->rb_root_in);
+	while (n) {
+		child = container_of(n, struct callchain_node, rb_node_in);
+		n = rb_next(n);
+		rb_erase(&child->rb_node_in, &src->rb_root_in);
 
-		new->ips[j].ip = old->ips[i];
-		new->ips[j].ms = syms[i];
-		j++;
+		err = merge_chain_branch(cursor, dst, child);
+		if (err)
+			break;
+
+		free(child);
 	}
 
-	new->nr = j;
+	cursor->nr = old_pos;
+	cursor->last = old_last;
+
+	return err;
 }
 
+int callchain_merge(struct callchain_cursor *cursor,
+		    struct callchain_root *dst, struct callchain_root *src)
+{
+	return merge_chain_branch(cursor, &dst->node, &src->node);
+}
 
-int append_chain(struct callchain_node *root, struct ip_callchain *chain,
-		 struct map_symbol *syms)
+int callchain_cursor_append(struct callchain_cursor *cursor,
+			    u64 ip, struct map *map, struct symbol *sym)
 {
-	struct resolved_chain *filtered;
+	struct callchain_cursor_node *node = *cursor->last;
 
-	if (!chain->nr)
-		return 0;
+	if (!node) {
+		node = calloc(1, sizeof(*node));
+		if (!node)
+			return -ENOMEM;
 
-	filtered = zalloc(sizeof(*filtered) +
-			  chain->nr * sizeof(struct resolved_ip));
-	if (!filtered)
-		return -ENOMEM;
+		*cursor->last = node;
+	}
 
-	filter_context(chain, filtered, syms);
+	node->ip = ip;
+	node->map = map;
+	node->sym = sym;
 
-	if (!filtered->nr)
-		goto end;
+	cursor->nr++;
 
-	__append_chain_children(root, filtered, 0);
-end:
-	free(filtered);
+	cursor->last = &node->next;
 
 	return 0;
 }
+
+int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent,
+			      struct perf_evsel *evsel, struct addr_location *al,
+			      int max_stack)
+{
+	if (sample->callchain == NULL)
+		return 0;
+
+	if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain ||
+	    sort__has_parent) {
+		return machine__resolve_callchain(al->machine, evsel, al->thread,
+						  sample, parent, al, max_stack);
+	}
+	return 0;
+}
+
+int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *sample)
+{
+	if (!symbol_conf.use_callchain)
+		return 0;
+	return callchain_append(he->callchain, &callchain_cursor, sample->period);
+}
+
+int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node *node,
+			bool hide_unresolved)
+{
+	al->map = node->map;
+	al->sym = node->sym;
+	if (node->map)
+		al->addr = node->map->map_ip(node->map, node->ip);
+	else
+		al->addr = node->ip;
+
+	if (al->sym == NULL) {
+		if (hide_unresolved)
+			return 0;
+		if (al->map == NULL)
+			goto out;
+	}
+
+	if (al->map->groups == &al->machine->kmaps) {
+		if (machine__is_host(al->machine)) {
+			al->cpumode = PERF_RECORD_MISC_KERNEL;
+			al->level = 'k';
+		} else {
+			al->cpumode = PERF_RECORD_MISC_GUEST_KERNEL;
+			al->level = 'g';
+		}
+	} else {
+		if (machine__is_host(al->machine)) {
+			al->cpumode = PERF_RECORD_MISC_USER;
+			al->level = '.';
+		} else if (perf_guest) {
+			al->cpumode = PERF_RECORD_MISC_GUEST_USER;
+			al->level = 'u';
+		} else {
+			al->cpumode = PERF_RECORD_MISC_HYPERVISOR;
+			al->level = 'H';
+		}
+	}
+
+out:
+	return 1;
+}
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 1ca73e4a272..8f84423a75d 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -7,6 +7,13 @@
 #include "event.h"
 #include "symbol.h"
 
+enum perf_call_graph_mode {
+	CALLCHAIN_NONE,
+	CALLCHAIN_FP,
+	CALLCHAIN_DWARF,
+	CALLCHAIN_MAX
+};
+
 enum chain_mode {
 	CHAIN_NONE,
 	CHAIN_FLAT,
@@ -14,28 +21,45 @@ enum chain_mode {
 	CHAIN_GRAPH_REL
 };
 
+enum chain_order {
+	ORDER_CALLER,
+	ORDER_CALLEE
+};
+
 struct callchain_node {
 	struct callchain_node	*parent;
-	struct list_head	brothers;
-	struct list_head	children;
 	struct list_head	val;
-	struct rb_node		rb_node; /* to sort nodes in an rbtree */
-	struct rb_root		rb_root; /* sorted tree of children */
+	struct rb_node		rb_node_in; /* to insert nodes in an rbtree */
+	struct rb_node		rb_node;    /* to sort nodes in an output tree */
+	struct rb_root		rb_root_in; /* input tree of children */
+	struct rb_root		rb_root;    /* sorted output tree of children */
 	unsigned int		val_nr;
 	u64			hit;
 	u64			children_hit;
 };
 
+struct callchain_root {
+	u64			max_depth;
+	struct callchain_node	node;
+};
+
 struct callchain_param;
 
-typedef void (*sort_chain_func_t)(struct rb_root *, struct callchain_node *,
+typedef void (*sort_chain_func_t)(struct rb_root *, struct callchain_root *,
 				 u64, struct callchain_param *);
 
+enum chain_key {
+	CCKEY_FUNCTION,
+	CCKEY_ADDRESS
+};
+
 struct callchain_param {
 	enum chain_mode 	mode;
 	u32			print_limit;
 	double			min_percent;
 	sort_chain_func_t	sort;
+	enum chain_order	order;
+	enum chain_key		key;
 };
 
 struct callchain_list {
@@ -44,21 +68,112 @@ struct callchain_list {
 	struct list_head	list;
 };
 
-static inline void callchain_init(struct callchain_node *node)
+/*
+ * A callchain cursor is a single linked list that
+ * let one feed a callchain progressively.
+ * It keeps persistent allocated entries to minimize
+ * allocations.
+ */
+struct callchain_cursor_node {
+	u64				ip;
+	struct map			*map;
+	struct symbol			*sym;
+	struct callchain_cursor_node	*next;
+};
+
+struct callchain_cursor {
+	u64				nr;
+	struct callchain_cursor_node	*first;
+	struct callchain_cursor_node	**last;
+	u64				pos;
+	struct callchain_cursor_node	*curr;
+};
+
+extern __thread struct callchain_cursor callchain_cursor;
+
+static inline void callchain_init(struct callchain_root *root)
 {
-	INIT_LIST_HEAD(&node->brothers);
-	INIT_LIST_HEAD(&node->children);
-	INIT_LIST_HEAD(&node->val);
+	INIT_LIST_HEAD(&root->node.val);
+
+	root->node.parent = NULL;
+	root->node.hit = 0;
+	root->node.children_hit = 0;
+	root->node.rb_root_in = RB_ROOT;
+	root->max_depth = 0;
 }
 
-static inline u64 cumul_hits(struct callchain_node *node)
+static inline u64 callchain_cumul_hits(struct callchain_node *node)
 {
 	return node->hit + node->children_hit;
 }
 
-int register_callchain_param(struct callchain_param *param);
-int append_chain(struct callchain_node *root, struct ip_callchain *chain,
-		 struct map_symbol *syms);
+int callchain_register_param(struct callchain_param *param);
+int callchain_append(struct callchain_root *root,
+		     struct callchain_cursor *cursor,
+		     u64 period);
+
+int callchain_merge(struct callchain_cursor *cursor,
+		    struct callchain_root *dst, struct callchain_root *src);
+
+/*
+ * Initialize a cursor before adding entries inside, but keep
+ * the previously allocated entries as a cache.
+ */
+static inline void callchain_cursor_reset(struct callchain_cursor *cursor)
+{
+	cursor->nr = 0;
+	cursor->last = &cursor->first;
+}
+
+int callchain_cursor_append(struct callchain_cursor *cursor, u64 ip,
+			    struct map *map, struct symbol *sym);
+
+/* Close a cursor writing session. Initialize for the reader */
+static inline void callchain_cursor_commit(struct callchain_cursor *cursor)
+{
+	cursor->curr = cursor->first;
+	cursor->pos = 0;
+}
+
+/* Cursor reading iteration helpers */
+static inline struct callchain_cursor_node *
+callchain_cursor_current(struct callchain_cursor *cursor)
+{
+	if (cursor->pos == cursor->nr)
+		return NULL;
+
+	return cursor->curr;
+}
+
+static inline void callchain_cursor_advance(struct callchain_cursor *cursor)
+{
+	cursor->curr = cursor->curr->next;
+	cursor->pos++;
+}
+
+struct option;
+struct hist_entry;
+
+int record_parse_callchain(const char *arg, struct record_opts *opts);
+int record_parse_callchain_opt(const struct option *opt, const char *arg, int unset);
+int record_callchain_opt(const struct option *opt, const char *arg, int unset);
+
+int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent,
+			      struct perf_evsel *evsel, struct addr_location *al,
+			      int max_stack);
+int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *sample);
+int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node *node,
+			bool hide_unresolved);
 
-bool ip_callchain__valid(struct ip_callchain *chain, event_t *event);
+extern const char record_callchain_help[];
+int parse_callchain_report_opt(const char *arg);
+
+static inline void callchain_cursor_snapshot(struct callchain_cursor *dest,
+					     struct callchain_cursor *src)
+{
+	*dest = *src;
+
+	dest->first = src->curr;
+	dest->nr -= src->pos;
+}
 #endif	/* __PERF_CALLCHAIN_H */
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
new file mode 100644
index 00000000000..88f7be39943
--- /dev/null
+++ b/tools/perf/util/cgroup.c
@@ -0,0 +1,177 @@
+#include "util.h"
+#include "../perf.h"
+#include "parse-options.h"
+#include "evsel.h"
+#include "cgroup.h"
+#include "evlist.h"
+
+int nr_cgroups;
+
+static int
+cgroupfs_find_mountpoint(char *buf, size_t maxlen)
+{
+	FILE *fp;
+	char mountpoint[PATH_MAX + 1], tokens[PATH_MAX + 1], type[PATH_MAX + 1];
+	char *token, *saved_ptr = NULL;
+	int found = 0;
+
+	fp = fopen("/proc/mounts", "r");
+	if (!fp)
+		return -1;
+
+	/*
+	 * in order to handle split hierarchy, we need to scan /proc/mounts
+	 * and inspect every cgroupfs mount point to find one that has
+	 * perf_event subsystem
+	 */
+	while (fscanf(fp, "%*s %"STR(PATH_MAX)"s %"STR(PATH_MAX)"s %"
+				STR(PATH_MAX)"s %*d %*d\n",
+				mountpoint, type, tokens) == 3) {
+
+		if (!strcmp(type, "cgroup")) {
+
+			token = strtok_r(tokens, ",", &saved_ptr);
+
+			while (token != NULL) {
+				if (!strcmp(token, "perf_event")) {
+					found = 1;
+					break;
+				}
+				token = strtok_r(NULL, ",", &saved_ptr);
+			}
+		}
+		if (found)
+			break;
+	}
+	fclose(fp);
+	if (!found)
+		return -1;
+
+	if (strlen(mountpoint) < maxlen) {
+		strcpy(buf, mountpoint);
+		return 0;
+	}
+	return -1;
+}
+
+static int open_cgroup(char *name)
+{
+	char path[PATH_MAX + 1];
+	char mnt[PATH_MAX + 1];
+	int fd;
+
+
+	if (cgroupfs_find_mountpoint(mnt, PATH_MAX + 1))
+		return -1;
+
+	snprintf(path, PATH_MAX, "%s/%s", mnt, name);
+
+	fd = open(path, O_RDONLY);
+	if (fd == -1)
+		fprintf(stderr, "no access to cgroup %s\n", path);
+
+	return fd;
+}
+
+static int add_cgroup(struct perf_evlist *evlist, char *str)
+{
+	struct perf_evsel *counter;
+	struct cgroup_sel *cgrp = NULL;
+	int n;
+	/*
+	 * check if cgrp is already defined, if so we reuse it
+	 */
+	evlist__for_each(evlist, counter) {
+		cgrp = counter->cgrp;
+		if (!cgrp)
+			continue;
+		if (!strcmp(cgrp->name, str))
+			break;
+
+		cgrp = NULL;
+	}
+
+	if (!cgrp) {
+		cgrp = zalloc(sizeof(*cgrp));
+		if (!cgrp)
+			return -1;
+
+		cgrp->name = str;
+
+		cgrp->fd = open_cgroup(str);
+		if (cgrp->fd == -1) {
+			free(cgrp);
+			return -1;
+		}
+	}
+
+	/*
+	 * find corresponding event
+	 * if add cgroup N, then need to find event N
+	 */
+	n = 0;
+	evlist__for_each(evlist, counter) {
+		if (n == nr_cgroups)
+			goto found;
+		n++;
+	}
+	if (cgrp->refcnt == 0)
+		free(cgrp);
+
+	return -1;
+found:
+	cgrp->refcnt++;
+	counter->cgrp = cgrp;
+	return 0;
+}
+
+void close_cgroup(struct cgroup_sel *cgrp)
+{
+	if (!cgrp)
+		return;
+
+	/* XXX: not reentrant */
+	if (--cgrp->refcnt == 0) {
+		close(cgrp->fd);
+		zfree(&cgrp->name);
+		free(cgrp);
+	}
+}
+
+int parse_cgroups(const struct option *opt __maybe_unused, const char *str,
+		  int unset __maybe_unused)
+{
+	struct perf_evlist *evlist = *(struct perf_evlist **)opt->value;
+	const char *p, *e, *eos = str + strlen(str);
+	char *s;
+	int ret;
+
+	if (list_empty(&evlist->entries)) {
+		fprintf(stderr, "must define events before cgroups\n");
+		return -1;
+	}
+
+	for (;;) {
+		p = strchr(str, ',');
+		e = p ? p : eos;
+
+		/* allow empty cgroups, i.e., skip */
+		if (e - str) {
+			/* termination added */
+			s = strndup(str, e - str);
+			if (!s)
+				return -1;
+			ret = add_cgroup(evlist, s);
+			if (ret) {
+				free(s);
+				return -1;
+			}
+		}
+		/* nr_cgroups is increased een for empty cgroups */
+		nr_cgroups++;
+		if (!p)
+			break;
+		str = p+1;
+	}
+	return 0;
+}
diff --git a/tools/perf/util/cgroup.h b/tools/perf/util/cgroup.h
new file mode 100644
index 00000000000..89acd6debdc
--- /dev/null
+++ b/tools/perf/util/cgroup.h
@@ -0,0 +1,17 @@
+#ifndef __CGROUP_H__
+#define __CGROUP_H__
+
+struct option;
+
+struct cgroup_sel {
+	char *name;
+	int fd;
+	int refcnt;
+};
+
+
+extern int nr_cgroups; /* number of explicit cgroups defined */
+extern void close_cgroup(struct cgroup_sel *cgrp);
+extern int parse_cgroups(const struct option *opt, const char *str, int unset);
+
+#endif /* __CGROUP_H__ */
diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c
index e191eb9a667..87b8672eb41 100644
--- a/tools/perf/util/color.c
+++ b/tools/perf/util/color.c
@@ -1,5 +1,7 @@
+#include <linux/kernel.h>
 #include "cache.h"
 #include "color.h"
+#include <math.h>
 
 int perf_use_color_default = -1;
 
@@ -182,12 +184,12 @@ static int __color_vsnprintf(char *bf, size_t size, const char *color,
 	}
 
 	if (perf_use_color_default && *color)
-		r += snprintf(bf, size, "%s", color);
-	r += vsnprintf(bf + r, size - r, fmt, args);
+		r += scnprintf(bf, size, "%s", color);
+	r += vscnprintf(bf + r, size - r, fmt, args);
 	if (perf_use_color_default && *color)
-		r += snprintf(bf + r, size - r, "%s", PERF_COLOR_RESET);
+		r += scnprintf(bf + r, size - r, "%s", PERF_COLOR_RESET);
 	if (trail)
-		r += snprintf(bf + r, size - r, "%s", trail);
+		r += scnprintf(bf + r, size - r, "%s", trail);
 	return r;
 }
 
@@ -200,7 +202,7 @@ static int __color_vfprintf(FILE *fp, const char *color, const char *fmt,
 	 * Auto-detect:
 	 */
 	if (perf_use_color_default < 0) {
-		if (isatty(1) || pager_in_use())
+		if (isatty(fileno(fp)) || pager_in_use())
 			perf_use_color_default = 1;
 		else
 			perf_use_color_default = 0;
@@ -297,10 +299,10 @@ const char *get_percent_color(double percent)
 	 * entries in green - and keep the low overhead places
 	 * normal:
 	 */
-	if (percent >= MIN_RED)
+	if (fabs(percent) >= MIN_RED)
 		color = PERF_COLOR_RED;
 	else {
-		if (percent > MIN_GREEN)
+		if (fabs(percent) > MIN_GREEN)
 			color = PERF_COLOR_GREEN;
 	}
 	return color;
@@ -317,8 +319,19 @@ int percent_color_fprintf(FILE *fp, const char *fmt, double percent)
 	return r;
 }
 
-int percent_color_snprintf(char *bf, size_t size, const char *fmt, double percent)
+int value_color_snprintf(char *bf, size_t size, const char *fmt, double value)
+{
+	const char *color = get_percent_color(value);
+	return color_snprintf(bf, size, color, fmt, value);
+}
+
+int percent_color_snprintf(char *bf, size_t size, const char *fmt, ...)
 {
-	const char *color = get_percent_color(percent);
-	return color_snprintf(bf, size, color, fmt, percent);
+	va_list args;
+	double percent;
+
+	va_start(args, fmt);
+	percent = va_arg(args, double);
+	va_end(args);
+	return value_color_snprintf(bf, size, fmt, percent);
 }
diff --git a/tools/perf/util/color.h b/tools/perf/util/color.h
index dea082b7960..7ff30a62a13 100644
--- a/tools/perf/util/color.h
+++ b/tools/perf/util/color.h
@@ -39,7 +39,8 @@ int color_fprintf(FILE *fp, const char *color, const char *fmt, ...);
 int color_snprintf(char *bf, size_t size, const char *color, const char *fmt, ...);
 int color_fprintf_ln(FILE *fp, const char *color, const char *fmt, ...);
 int color_fwrite_lines(FILE *fp, const char *color, size_t count, const char *buf);
-int percent_color_snprintf(char *bf, size_t size, const char *fmt, double percent);
+int value_color_snprintf(char *bf, size_t size, const char *fmt, double value);
+int percent_color_snprintf(char *bf, size_t size, const char *fmt, ...);
 int percent_color_fprintf(FILE *fp, const char *fmt, double percent);
 const char *get_percent_color(double percent);
 
diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c
new file mode 100644
index 00000000000..f9e777629e2
--- /dev/null
+++ b/tools/perf/util/comm.c
@@ -0,0 +1,122 @@
+#include "comm.h"
+#include "util.h"
+#include <stdlib.h>
+#include <stdio.h>
+
+struct comm_str {
+	char *str;
+	struct rb_node rb_node;
+	int ref;
+};
+
+/* Should perhaps be moved to struct machine */
+static struct rb_root comm_str_root;
+
+static void comm_str__get(struct comm_str *cs)
+{
+	cs->ref++;
+}
+
+static void comm_str__put(struct comm_str *cs)
+{
+	if (!--cs->ref) {
+		rb_erase(&cs->rb_node, &comm_str_root);
+		zfree(&cs->str);
+		free(cs);
+	}
+}
+
+static struct comm_str *comm_str__alloc(const char *str)
+{
+	struct comm_str *cs;
+
+	cs = zalloc(sizeof(*cs));
+	if (!cs)
+		return NULL;
+
+	cs->str = strdup(str);
+	if (!cs->str) {
+		free(cs);
+		return NULL;
+	}
+
+	return cs;
+}
+
+static struct comm_str *comm_str__findnew(const char *str, struct rb_root *root)
+{
+	struct rb_node **p = &root->rb_node;
+	struct rb_node *parent = NULL;
+	struct comm_str *iter, *new;
+	int cmp;
+
+	while (*p != NULL) {
+		parent = *p;
+		iter = rb_entry(parent, struct comm_str, rb_node);
+
+		cmp = strcmp(str, iter->str);
+		if (!cmp)
+			return iter;
+
+		if (cmp < 0)
+			p = &(*p)->rb_left;
+		else
+			p = &(*p)->rb_right;
+	}
+
+	new = comm_str__alloc(str);
+	if (!new)
+		return NULL;
+
+	rb_link_node(&new->rb_node, parent, p);
+	rb_insert_color(&new->rb_node, root);
+
+	return new;
+}
+
+struct comm *comm__new(const char *str, u64 timestamp)
+{
+	struct comm *comm = zalloc(sizeof(*comm));
+
+	if (!comm)
+		return NULL;
+
+	comm->start = timestamp;
+
+	comm->comm_str = comm_str__findnew(str, &comm_str_root);
+	if (!comm->comm_str) {
+		free(comm);
+		return NULL;
+	}
+
+	comm_str__get(comm->comm_str);
+
+	return comm;
+}
+
+int comm__override(struct comm *comm, const char *str, u64 timestamp)
+{
+	struct comm_str *new, *old = comm->comm_str;
+
+	new = comm_str__findnew(str, &comm_str_root);
+	if (!new)
+		return -ENOMEM;
+
+	comm_str__get(new);
+	comm_str__put(old);
+	comm->comm_str = new;
+	comm->start = timestamp;
+
+	return 0;
+}
+
+void comm__free(struct comm *comm)
+{
+	comm_str__put(comm->comm_str);
+	free(comm);
+}
+
+const char *comm__str(const struct comm *comm)
+{
+	return comm->comm_str->str;
+}
diff --git a/tools/perf/util/comm.h b/tools/perf/util/comm.h
new file mode 100644
index 00000000000..fac5bd51bef
--- /dev/null
+++ b/tools/perf/util/comm.h
@@ -0,0 +1,21 @@
+#ifndef __PERF_COMM_H
+#define __PERF_COMM_H
+
+#include "../perf.h"
+#include <linux/rbtree.h>
+#include <linux/list.h>
+
+struct comm_str;
+
+struct comm {
+	struct comm_str *comm_str;
+	u64 start;
+	struct list_head list;
+};
+
+void comm__free(struct comm *comm);
+struct comm *comm__new(const char *str, u64 timestamp);
+const char *comm__str(const struct comm *comm);
+int comm__override(struct comm *comm, const char *str, u64 timestamp);
+
+#endif  /* __PERF_COMM_H */
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index dabe892d0e5..24519e14ac5 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -1,5 +1,8 @@
 /*
- * GIT - The information manager from hell
+ * config.c
+ *
+ * Helper functions for parsing config items.
+ * Originally copied from GIT source.
  *
  * Copyright (C) Linus Torvalds, 2005
  * Copyright (C) Johannes Schindelin, 2005
@@ -8,9 +11,15 @@
 #include "util.h"
 #include "cache.h"
 #include "exec_cmd.h"
+#include "util/hist.h"  /* perf_hist_config */
 
 #define MAXNAME (256)
 
+#define DEBUG_CACHE_DIR ".debug"
+
+
+char buildid_dir[MAXPATHLEN]; /* root dir for buildid, binary cache */
+
 static FILE *config_file;
 static const char *config_file_name;
 static int config_linenr;
@@ -112,7 +121,7 @@ static char *parse_value(void)
 
 static inline int iskeychar(int c)
 {
-	return isalnum(c) || c == '-';
+	return isalnum(c) || c == '-' || c == '_';
 }
 
 static int get_value(config_fn_t fn, void *data, char *name, unsigned int len)
@@ -127,7 +136,7 @@ static int get_value(config_fn_t fn, void *data, char *name, unsigned int len)
 			break;
 		if (!iskeychar(c))
 			break;
-		name[len++] = tolower(c);
+		name[len++] = c;
 		if (len >= MAXNAME)
 			return -1;
 	}
@@ -327,18 +336,30 @@ int perf_config_bool(const char *name, const char *value)
 	return !!perf_config_bool_or_int(name, value, &discard);
 }
 
-static int perf_default_core_config(const char *var __used, const char *value __used)
+const char *perf_config_dirname(const char *name, const char *value)
 {
-	/* Add other config variables here and to Documentation/config.txt. */
+	if (!name)
+		return NULL;
+	return value;
+}
+
+static int perf_default_core_config(const char *var __maybe_unused,
+				    const char *value __maybe_unused)
+{
+	/* Add other config variables here. */
 	return 0;
 }
 
-int perf_default_config(const char *var, const char *value, void *dummy __used)
+int perf_default_config(const char *var, const char *value,
+			void *dummy __maybe_unused)
 {
 	if (!prefixcmp(var, "core."))
 		return perf_default_core_config(var, value);
 
-	/* Add other config variables here and to Documentation/config.txt. */
+	if (!prefixcmp(var, "hist."))
+		return perf_hist_config(var, value);
+
+	/* Add other config variables here. */
 	return 0;
 }
 
@@ -387,7 +408,6 @@ static int perf_config_global(void)
 int perf_config(config_fn_t fn, void *data)
 {
 	int ret = 0, found = 0;
-	char *repo_config = NULL;
 	const char *home = NULL;
 
 	/* Setting $PERF_CONFIG makes perf read _only_ the given config file. */
@@ -402,19 +422,32 @@ int perf_config(config_fn_t fn, void *data)
 	home = getenv("HOME");
 	if (perf_config_global() && home) {
 		char *user_config = strdup(mkpath("%s/.perfconfig", home));
-		if (!access(user_config, R_OK)) {
-			ret += perf_config_from_file(fn, user_config, data);
-			found += 1;
+		struct stat st;
+
+		if (user_config == NULL) {
+			warning("Not enough memory to process %s/.perfconfig, "
+				"ignoring it.", home);
+			goto out;
 		}
-		free(user_config);
-	}
 
-	repo_config = perf_pathdup("config");
-	if (!access(repo_config, R_OK)) {
-		ret += perf_config_from_file(fn, repo_config, data);
+		if (stat(user_config, &st) < 0)
+			goto out_free;
+
+		if (st.st_uid && (st.st_uid != geteuid())) {
+			warning("File %s not owned by current user or root, "
+				"ignoring it.", user_config);
+			goto out_free;
+		}
+
+		if (!st.st_size)
+			goto out_free;
+
+		ret += perf_config_from_file(fn, user_config, data);
 		found += 1;
+out_free:
+		free(user_config);
 	}
-	free(repo_config);
+out:
 	if (found == 0)
 		return -1;
 	return ret;
@@ -428,3 +461,53 @@ int config_error_nonbool(const char *var)
 {
 	return error("Missing value for '%s'", var);
 }
+
+struct buildid_dir_config {
+	char *dir;
+};
+
+static int buildid_dir_command_config(const char *var, const char *value,
+				      void *data)
+{
+	struct buildid_dir_config *c = data;
+	const char *v;
+
+	/* same dir for all commands */
+	if (!prefixcmp(var, "buildid.") && !strcmp(var + 8, "dir")) {
+		v = perf_config_dirname(var, value);
+		if (!v)
+			return -1;
+		strncpy(c->dir, v, MAXPATHLEN-1);
+		c->dir[MAXPATHLEN-1] = '\0';
+	}
+	return 0;
+}
+
+static void check_buildid_dir_config(void)
+{
+	struct buildid_dir_config c;
+	c.dir = buildid_dir;
+	perf_config(buildid_dir_command_config, &c);
+}
+
+void set_buildid_dir(void)
+{
+	buildid_dir[0] = '\0';
+
+	/* try config file */
+	check_buildid_dir_config();
+
+	/* default to $HOME/.debug */
+	if (buildid_dir[0] == '\0') {
+		char *v = getenv("HOME");
+		if (v) {
+			snprintf(buildid_dir, MAXPATHLEN-1, "%s/%s",
+				 v, DEBUG_CACHE_DIR);
+		} else {
+			strncpy(buildid_dir, DEBUG_CACHE_DIR, MAXPATHLEN-1);
+		}
+		buildid_dir[MAXPATHLEN-1] = '\0';
+	}
+	/* for communicating with external commands */
+	setenv("PERF_BUILDID_DIR", buildid_dir, 1);
+}
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 4e01490e51e..c4e55b71010 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -1,49 +1,83 @@
 #include "util.h"
+#include <api/fs/fs.h>
 #include "../perf.h"
 #include "cpumap.h"
 #include <assert.h>
 #include <stdio.h>
+#include <stdlib.h>
 
-int cpumap[MAX_NR_CPUS];
-
-static int default_cpu_map(void)
+static struct cpu_map *cpu_map__default_new(void)
 {
-	int nr_cpus, i;
+	struct cpu_map *cpus;
+	int nr_cpus;
 
 	nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
-	assert(nr_cpus <= MAX_NR_CPUS);
-	assert((int)nr_cpus >= 0);
+	if (nr_cpus < 0)
+		return NULL;
+
+	cpus = malloc(sizeof(*cpus) + nr_cpus * sizeof(int));
+	if (cpus != NULL) {
+		int i;
+		for (i = 0; i < nr_cpus; ++i)
+			cpus->map[i] = i;
 
-	for (i = 0; i < nr_cpus; ++i)
-		cpumap[i] = i;
+		cpus->nr = nr_cpus;
+	}
 
-	return nr_cpus;
+	return cpus;
 }
 
-int read_cpu_map(void)
+static struct cpu_map *cpu_map__trim_new(int nr_cpus, int *tmp_cpus)
 {
-	FILE *onlnf;
+	size_t payload_size = nr_cpus * sizeof(int);
+	struct cpu_map *cpus = malloc(sizeof(*cpus) + payload_size);
+
+	if (cpus != NULL) {
+		cpus->nr = nr_cpus;
+		memcpy(cpus->map, tmp_cpus, payload_size);
+	}
+
+	return cpus;
+}
+
+struct cpu_map *cpu_map__read(FILE *file)
+{
+	struct cpu_map *cpus = NULL;
 	int nr_cpus = 0;
+	int *tmp_cpus = NULL, *tmp;
+	int max_entries = 0;
 	int n, cpu, prev;
 	char sep;
 
-	onlnf = fopen("/sys/devices/system/cpu/online", "r");
-	if (!onlnf)
-		return default_cpu_map();
-
 	sep = 0;
 	prev = -1;
 	for (;;) {
-		n = fscanf(onlnf, "%u%c", &cpu, &sep);
+		n = fscanf(file, "%u%c", &cpu, &sep);
 		if (n <= 0)
 			break;
 		if (prev >= 0) {
-			assert(nr_cpus + cpu - prev - 1 < MAX_NR_CPUS);
+			int new_max = nr_cpus + cpu - prev - 1;
+
+			if (new_max >= max_entries) {
+				max_entries = new_max + MAX_NR_CPUS / 2;
+				tmp = realloc(tmp_cpus, max_entries * sizeof(int));
+				if (tmp == NULL)
+					goto out_free_tmp;
+				tmp_cpus = tmp;
+			}
+
 			while (++prev < cpu)
-				cpumap[nr_cpus++] = prev;
+				tmp_cpus[nr_cpus++] = prev;
+		}
+		if (nr_cpus == max_entries) {
+			max_entries += MAX_NR_CPUS;
+			tmp = realloc(tmp_cpus, max_entries * sizeof(int));
+			if (tmp == NULL)
+				goto out_free_tmp;
+			tmp_cpus = tmp;
 		}
-		assert (nr_cpus < MAX_NR_CPUS);
-		cpumap[nr_cpus++] = cpu;
+
+		tmp_cpus[nr_cpus++] = cpu;
 		if (n == 2 && sep == '-')
 			prev = cpu;
 		else
@@ -51,9 +85,395 @@ int read_cpu_map(void)
 		if (n == 1 || sep == '\n')
 			break;
 	}
+
+	if (nr_cpus > 0)
+		cpus = cpu_map__trim_new(nr_cpus, tmp_cpus);
+	else
+		cpus = cpu_map__default_new();
+out_free_tmp:
+	free(tmp_cpus);
+	return cpus;
+}
+
+static struct cpu_map *cpu_map__read_all_cpu_map(void)
+{
+	struct cpu_map *cpus = NULL;
+	FILE *onlnf;
+
+	onlnf = fopen("/sys/devices/system/cpu/online", "r");
+	if (!onlnf)
+		return cpu_map__default_new();
+
+	cpus = cpu_map__read(onlnf);
 	fclose(onlnf);
+	return cpus;
+}
+
+struct cpu_map *cpu_map__new(const char *cpu_list)
+{
+	struct cpu_map *cpus = NULL;
+	unsigned long start_cpu, end_cpu = 0;
+	char *p = NULL;
+	int i, nr_cpus = 0;
+	int *tmp_cpus = NULL, *tmp;
+	int max_entries = 0;
+
+	if (!cpu_list)
+		return cpu_map__read_all_cpu_map();
+
+	if (!isdigit(*cpu_list))
+		goto out;
+
+	while (isdigit(*cpu_list)) {
+		p = NULL;
+		start_cpu = strtoul(cpu_list, &p, 0);
+		if (start_cpu >= INT_MAX
+		    || (*p != '\0' && *p != ',' && *p != '-'))
+			goto invalid;
+
+		if (*p == '-') {
+			cpu_list = ++p;
+			p = NULL;
+			end_cpu = strtoul(cpu_list, &p, 0);
+
+			if (end_cpu >= INT_MAX || (*p != '\0' && *p != ','))
+				goto invalid;
+
+			if (end_cpu < start_cpu)
+				goto invalid;
+		} else {
+			end_cpu = start_cpu;
+		}
+
+		for (; start_cpu <= end_cpu; start_cpu++) {
+			/* check for duplicates */
+			for (i = 0; i < nr_cpus; i++)
+				if (tmp_cpus[i] == (int)start_cpu)
+					goto invalid;
+
+			if (nr_cpus == max_entries) {
+				max_entries += MAX_NR_CPUS;
+				tmp = realloc(tmp_cpus, max_entries * sizeof(int));
+				if (tmp == NULL)
+					goto invalid;
+				tmp_cpus = tmp;
+			}
+			tmp_cpus[nr_cpus++] = (int)start_cpu;
+		}
+		if (*p)
+			++p;
+
+		cpu_list = p;
+	}
+
 	if (nr_cpus > 0)
-		return nr_cpus;
+		cpus = cpu_map__trim_new(nr_cpus, tmp_cpus);
+	else
+		cpus = cpu_map__default_new();
+invalid:
+	free(tmp_cpus);
+out:
+	return cpus;
+}
+
+size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp)
+{
+	int i;
+	size_t printed = fprintf(fp, "%d cpu%s: ",
+				 map->nr, map->nr > 1 ? "s" : "");
+	for (i = 0; i < map->nr; ++i)
+		printed += fprintf(fp, "%s%d", i ? ", " : "", map->map[i]);
+
+	return printed + fprintf(fp, "\n");
+}
+
+struct cpu_map *cpu_map__dummy_new(void)
+{
+	struct cpu_map *cpus = malloc(sizeof(*cpus) + sizeof(int));
+
+	if (cpus != NULL) {
+		cpus->nr = 1;
+		cpus->map[0] = -1;
+	}
+
+	return cpus;
+}
 
-	return default_cpu_map();
+void cpu_map__delete(struct cpu_map *map)
+{
+	free(map);
+}
+
+int cpu_map__get_socket(struct cpu_map *map, int idx)
+{
+	FILE *fp;
+	const char *mnt;
+	char path[PATH_MAX];
+	int cpu, ret;
+
+	if (idx > map->nr)
+		return -1;
+
+	cpu = map->map[idx];
+
+	mnt = sysfs__mountpoint();
+	if (!mnt)
+		return -1;
+
+	snprintf(path, PATH_MAX,
+		"%s/devices/system/cpu/cpu%d/topology/physical_package_id",
+		mnt, cpu);
+
+	fp = fopen(path, "r");
+	if (!fp)
+		return -1;
+	ret = fscanf(fp, "%d", &cpu);
+	fclose(fp);
+	return ret == 1 ? cpu : -1;
+}
+
+static int cmp_ids(const void *a, const void *b)
+{
+	return *(int *)a - *(int *)b;
+}
+
+static int cpu_map__build_map(struct cpu_map *cpus, struct cpu_map **res,
+			      int (*f)(struct cpu_map *map, int cpu))
+{
+	struct cpu_map *c;
+	int nr = cpus->nr;
+	int cpu, s1, s2;
+
+	/* allocate as much as possible */
+	c = calloc(1, sizeof(*c) + nr * sizeof(int));
+	if (!c)
+		return -1;
+
+	for (cpu = 0; cpu < nr; cpu++) {
+		s1 = f(cpus, cpu);
+		for (s2 = 0; s2 < c->nr; s2++) {
+			if (s1 == c->map[s2])
+				break;
+		}
+		if (s2 == c->nr) {
+			c->map[c->nr] = s1;
+			c->nr++;
+		}
+	}
+	/* ensure we process id in increasing order */
+	qsort(c->map, c->nr, sizeof(int), cmp_ids);
+
+	*res = c;
+	return 0;
+}
+
+int cpu_map__get_core(struct cpu_map *map, int idx)
+{
+	FILE *fp;
+	const char *mnt;
+	char path[PATH_MAX];
+	int cpu, ret, s;
+
+	if (idx > map->nr)
+		return -1;
+
+	cpu = map->map[idx];
+
+	mnt = sysfs__mountpoint();
+	if (!mnt)
+		return -1;
+
+	snprintf(path, PATH_MAX,
+		"%s/devices/system/cpu/cpu%d/topology/core_id",
+		mnt, cpu);
+
+	fp = fopen(path, "r");
+	if (!fp)
+		return -1;
+	ret = fscanf(fp, "%d", &cpu);
+	fclose(fp);
+	if (ret != 1)
+		return -1;
+
+	s = cpu_map__get_socket(map, idx);
+	if (s == -1)
+		return -1;
+
+	/*
+	 * encode socket in upper 16 bits
+	 * core_id is relative to socket, and
+	 * we need a global id. So we combine
+	 * socket+ core id
+	 */
+	return (s << 16) | (cpu & 0xffff);
+}
+
+int cpu_map__build_socket_map(struct cpu_map *cpus, struct cpu_map **sockp)
+{
+	return cpu_map__build_map(cpus, sockp, cpu_map__get_socket);
+}
+
+int cpu_map__build_core_map(struct cpu_map *cpus, struct cpu_map **corep)
+{
+	return cpu_map__build_map(cpus, corep, cpu_map__get_core);
+}
+
+/* setup simple routines to easily access node numbers given a cpu number */
+static int get_max_num(char *path, int *max)
+{
+	size_t num;
+	char *buf;
+	int err = 0;
+
+	if (filename__read_str(path, &buf, &num))
+		return -1;
+
+	buf[num] = '\0';
+
+	/* start on the right, to find highest node num */
+	while (--num) {
+		if ((buf[num] == ',') || (buf[num] == '-')) {
+			num++;
+			break;
+		}
+	}
+	if (sscanf(&buf[num], "%d", max) < 1) {
+		err = -1;
+		goto out;
+	}
+
+	/* convert from 0-based to 1-based */
+	(*max)++;
+
+out:
+	free(buf);
+	return err;
+}
+
+/* Determine highest possible cpu in the system for sparse allocation */
+static void set_max_cpu_num(void)
+{
+	const char *mnt;
+	char path[PATH_MAX];
+	int ret = -1;
+
+	/* set up default */
+	max_cpu_num = 4096;
+
+	mnt = sysfs__mountpoint();
+	if (!mnt)
+		goto out;
+
+	/* get the highest possible cpu number for a sparse allocation */
+	ret = snprintf(path, PATH_MAX, "%s/devices/system/cpu/possible", mnt);
+	if (ret == PATH_MAX) {
+		pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX);
+		goto out;
+	}
+
+	ret = get_max_num(path, &max_cpu_num);
+
+out:
+	if (ret)
+		pr_err("Failed to read max cpus, using default of %d\n", max_cpu_num);
+}
+
+/* Determine highest possible node in the system for sparse allocation */
+static void set_max_node_num(void)
+{
+	const char *mnt;
+	char path[PATH_MAX];
+	int ret = -1;
+
+	/* set up default */
+	max_node_num = 8;
+
+	mnt = sysfs__mountpoint();
+	if (!mnt)
+		goto out;
+
+	/* get the highest possible cpu number for a sparse allocation */
+	ret = snprintf(path, PATH_MAX, "%s/devices/system/node/possible", mnt);
+	if (ret == PATH_MAX) {
+		pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX);
+		goto out;
+	}
+
+	ret = get_max_num(path, &max_node_num);
+
+out:
+	if (ret)
+		pr_err("Failed to read max nodes, using default of %d\n", max_node_num);
+}
+
+static int init_cpunode_map(void)
+{
+	int i;
+
+	set_max_cpu_num();
+	set_max_node_num();
+
+	cpunode_map = calloc(max_cpu_num, sizeof(int));
+	if (!cpunode_map) {
+		pr_err("%s: calloc failed\n", __func__);
+		return -1;
+	}
+
+	for (i = 0; i < max_cpu_num; i++)
+		cpunode_map[i] = -1;
+
+	return 0;
+}
+
+int cpu__setup_cpunode_map(void)
+{
+	struct dirent *dent1, *dent2;
+	DIR *dir1, *dir2;
+	unsigned int cpu, mem;
+	char buf[PATH_MAX];
+	char path[PATH_MAX];
+	const char *mnt;
+	int n;
+
+	/* initialize globals */
+	if (init_cpunode_map())
+		return -1;
+
+	mnt = sysfs__mountpoint();
+	if (!mnt)
+		return 0;
+
+	n = snprintf(path, PATH_MAX, "%s/devices/system/node", mnt);
+	if (n == PATH_MAX) {
+		pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX);
+		return -1;
+	}
+
+	dir1 = opendir(path);
+	if (!dir1)
+		return 0;
+
+	/* walk tree and setup map */
+	while ((dent1 = readdir(dir1)) != NULL) {
+		if (dent1->d_type != DT_DIR || sscanf(dent1->d_name, "node%u", &mem) < 1)
+			continue;
+
+		n = snprintf(buf, PATH_MAX, "%s/%s", path, dent1->d_name);
+		if (n == PATH_MAX) {
+			pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX);
+			continue;
+		}
+
+		dir2 = opendir(buf);
+		if (!dir2)
+			continue;
+		while ((dent2 = readdir(dir2)) != NULL) {
+			if (dent2->d_type != DT_LNK || sscanf(dent2->d_name, "cpu%u", &cpu) < 1)
+				continue;
+			cpunode_map[cpu] = mem;
+		}
+		closedir(dir2);
+	}
+	closedir(dir1);
+	return 0;
 }
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index 86c78bb3309..61a65484900 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -1,7 +1,84 @@
 #ifndef __PERF_CPUMAP_H
 #define __PERF_CPUMAP_H
 
-extern int read_cpu_map(void);
-extern int cpumap[];
+#include <stdio.h>
+#include <stdbool.h>
+
+#include "perf.h"
+#include "util/debug.h"
+
+struct cpu_map {
+	int nr;
+	int map[];
+};
+
+struct cpu_map *cpu_map__new(const char *cpu_list);
+struct cpu_map *cpu_map__dummy_new(void);
+void cpu_map__delete(struct cpu_map *map);
+struct cpu_map *cpu_map__read(FILE *file);
+size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp);
+int cpu_map__get_socket(struct cpu_map *map, int idx);
+int cpu_map__get_core(struct cpu_map *map, int idx);
+int cpu_map__build_socket_map(struct cpu_map *cpus, struct cpu_map **sockp);
+int cpu_map__build_core_map(struct cpu_map *cpus, struct cpu_map **corep);
+
+static inline int cpu_map__socket(struct cpu_map *sock, int s)
+{
+	if (!sock || s > sock->nr || s < 0)
+		return 0;
+	return sock->map[s];
+}
+
+static inline int cpu_map__id_to_socket(int id)
+{
+	return id >> 16;
+}
+
+static inline int cpu_map__id_to_cpu(int id)
+{
+	return id & 0xffff;
+}
+
+static inline int cpu_map__nr(const struct cpu_map *map)
+{
+	return map ? map->nr : 1;
+}
+
+static inline bool cpu_map__empty(const struct cpu_map *map)
+{
+	return map ? map->map[0] == -1 : true;
+}
+
+int max_cpu_num;
+int max_node_num;
+int *cpunode_map;
+
+int cpu__setup_cpunode_map(void);
+
+static inline int cpu__max_node(void)
+{
+	if (unlikely(!max_node_num))
+		pr_debug("cpu_map not initialized\n");
+
+	return max_node_num;
+}
+
+static inline int cpu__max_cpu(void)
+{
+	if (unlikely(!max_cpu_num))
+		pr_debug("cpu_map not initialized\n");
+
+	return max_cpu_num;
+}
+
+static inline int cpu__get_node(int cpu)
+{
+	if (unlikely(cpunode_map == NULL)) {
+		pr_debug("cpu_map not initialized\n");
+		return -1;
+	}
+
+	return cpunode_map[cpu];
+}
 
 #endif /* __PERF_CPUMAP_H */
diff --git a/tools/perf/util/ctype.c b/tools/perf/util/ctype.c
index 35073621e5d..aada3ac5e89 100644
--- a/tools/perf/util/ctype.c
+++ b/tools/perf/util/ctype.c
@@ -3,7 +3,7 @@
  *
  * No surprises, and works with signed and unsigned chars.
  */
-#include "cache.h"
+#include "util.h"
 
 enum {
 	S = GIT_SPACE,
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
new file mode 100644
index 00000000000..55de44ecebe
--- /dev/null
+++ b/tools/perf/util/data.c
@@ -0,0 +1,133 @@
+#include <linux/compiler.h>
+#include <linux/kernel.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+#include <string.h>
+
+#include "data.h"
+#include "util.h"
+
+static bool check_pipe(struct perf_data_file *file)
+{
+	struct stat st;
+	bool is_pipe = false;
+	int fd = perf_data_file__is_read(file) ?
+		 STDIN_FILENO : STDOUT_FILENO;
+
+	if (!file->path) {
+		if (!fstat(fd, &st) && S_ISFIFO(st.st_mode))
+			is_pipe = true;
+	} else {
+		if (!strcmp(file->path, "-"))
+			is_pipe = true;
+	}
+
+	if (is_pipe)
+		file->fd = fd;
+
+	return file->is_pipe = is_pipe;
+}
+
+static int check_backup(struct perf_data_file *file)
+{
+	struct stat st;
+
+	if (!stat(file->path, &st) && st.st_size) {
+		/* TODO check errors properly */
+		char oldname[PATH_MAX];
+		snprintf(oldname, sizeof(oldname), "%s.old",
+			 file->path);
+		unlink(oldname);
+		rename(file->path, oldname);
+	}
+
+	return 0;
+}
+
+static int open_file_read(struct perf_data_file *file)
+{
+	struct stat st;
+	int fd;
+
+	fd = open(file->path, O_RDONLY);
+	if (fd < 0) {
+		int err = errno;
+
+		pr_err("failed to open %s: %s", file->path, strerror(err));
+		if (err == ENOENT && !strcmp(file->path, "perf.data"))
+			pr_err("  (try 'perf record' first)");
+		pr_err("\n");
+		return -err;
+	}
+
+	if (fstat(fd, &st) < 0)
+		goto out_close;
+
+	if (!file->force && st.st_uid && (st.st_uid != geteuid())) {
+		pr_err("file %s not owned by current user or root\n",
+		       file->path);
+		goto out_close;
+	}
+
+	if (!st.st_size) {
+		pr_info("zero-sized file (%s), nothing to do!\n",
+			file->path);
+		goto out_close;
+	}
+
+	file->size = st.st_size;
+	return fd;
+
+ out_close:
+	close(fd);
+	return -1;
+}
+
+static int open_file_write(struct perf_data_file *file)
+{
+	int fd;
+
+	if (check_backup(file))
+		return -1;
+
+	fd = open(file->path, O_CREAT|O_RDWR|O_TRUNC, S_IRUSR|S_IWUSR);
+
+	if (fd < 0)
+		pr_err("failed to open %s : %s\n", file->path, strerror(errno));
+
+	return fd;
+}
+
+static int open_file(struct perf_data_file *file)
+{
+	int fd;
+
+	fd = perf_data_file__is_read(file) ?
+	     open_file_read(file) : open_file_write(file);
+
+	file->fd = fd;
+	return fd < 0 ? -1 : 0;
+}
+
+int perf_data_file__open(struct perf_data_file *file)
+{
+	if (check_pipe(file))
+		return 0;
+
+	if (!file->path)
+		file->path = "perf.data";
+
+	return open_file(file);
+}
+
+void perf_data_file__close(struct perf_data_file *file)
+{
+	close(file->fd);
+}
+
+ssize_t perf_data_file__write(struct perf_data_file *file,
+			      void *buf, size_t size)
+{
+	return writen(file->fd, buf, size);
+}
diff --git a/tools/perf/util/data.h b/tools/perf/util/data.h
new file mode 100644
index 00000000000..2b15d0c95c7
--- /dev/null
+++ b/tools/perf/util/data.h
@@ -0,0 +1,50 @@
+#ifndef __PERF_DATA_H
+#define __PERF_DATA_H
+
+#include <stdbool.h>
+
+enum perf_data_mode {
+	PERF_DATA_MODE_WRITE,
+	PERF_DATA_MODE_READ,
+};
+
+struct perf_data_file {
+	const char		*path;
+	int			 fd;
+	bool			 is_pipe;
+	bool			 force;
+	unsigned long		 size;
+	enum perf_data_mode	 mode;
+};
+
+static inline bool perf_data_file__is_read(struct perf_data_file *file)
+{
+	return file->mode == PERF_DATA_MODE_READ;
+}
+
+static inline bool perf_data_file__is_write(struct perf_data_file *file)
+{
+	return file->mode == PERF_DATA_MODE_WRITE;
+}
+
+static inline int perf_data_file__is_pipe(struct perf_data_file *file)
+{
+	return file->is_pipe;
+}
+
+static inline int perf_data_file__fd(struct perf_data_file *file)
+{
+	return file->fd;
+}
+
+static inline unsigned long perf_data_file__size(struct perf_data_file *file)
+{
+	return file->size;
+}
+
+int perf_data_file__open(struct perf_data_file *file);
+void perf_data_file__close(struct perf_data_file *file);
+ssize_t perf_data_file__write(struct perf_data_file *file,
+			      void *buf, size_t size);
+
+#endif /* __PERF_DATA_H */
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index 6cddff2bc97..299b5558650 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -11,57 +11,66 @@
 #include "event.h"
 #include "debug.h"
 #include "util.h"
+#include "target.h"
 
-int verbose = 0;
-bool dump_trace = false;
+int verbose;
+bool dump_trace = false, quiet = false;
 
-int eprintf(int level, const char *fmt, ...)
+static int _eprintf(int level, const char *fmt, va_list args)
 {
-	va_list args;
 	int ret = 0;
 
 	if (verbose >= level) {
-		va_start(args, fmt);
-		if (use_browser > 0)
-			ret = browser__show_help(fmt, args);
+		if (use_browser >= 1)
+			ui_helpline__vshow(fmt, args);
 		else
 			ret = vfprintf(stderr, fmt, args);
-		va_end(args);
 	}
 
 	return ret;
 }
 
-int dump_printf(const char *fmt, ...)
+int eprintf(int level, const char *fmt, ...)
 {
 	va_list args;
-	int ret = 0;
+	int ret;
 
-	if (dump_trace) {
-		va_start(args, fmt);
-		ret = vprintf(fmt, args);
-		va_end(args);
-	}
+	va_start(args, fmt);
+	ret = _eprintf(level, fmt, args);
+	va_end(args);
 
 	return ret;
 }
 
-static int dump_printf_color(const char *fmt, const char *color, ...)
+/*
+ * Overloading libtraceevent standard info print
+ * function, display with -v in perf.
+ */
+void pr_stat(const char *fmt, ...)
+{
+	va_list args;
+
+	va_start(args, fmt);
+	_eprintf(1, fmt, args);
+	va_end(args);
+	eprintf(1, "\n");
+}
+
+int dump_printf(const char *fmt, ...)
 {
 	va_list args;
 	int ret = 0;
 
 	if (dump_trace) {
-		va_start(args, color);
-		ret = color_vfprintf(stdout, color, fmt, args);
+		va_start(args, fmt);
+		ret = vprintf(fmt, args);
 		va_end(args);
 	}
 
 	return ret;
 }
 
-
-void trace_event(event_t *event)
+void trace_event(union perf_event *event)
 {
 	unsigned char *raw_event = (void *)event;
 	const char *color = PERF_COLOR_BLUE;
@@ -70,31 +79,29 @@ void trace_event(event_t *event)
 	if (!dump_trace)
 		return;
 
-	dump_printf(".");
-	dump_printf_color("\n. ... raw event: size %d bytes\n", color,
-			  event->header.size);
+	printf(".");
+	color_fprintf(stdout, color, "\n. ... raw event: size %d bytes\n",
+		      event->header.size);
 
 	for (i = 0; i < event->header.size; i++) {
 		if ((i & 15) == 0) {
-			dump_printf(".");
-			dump_printf_color("  %04x: ", color, i);
+			printf(".");
+			color_fprintf(stdout, color, "  %04x: ", i);
 		}
 
-		dump_printf_color(" %02x", color, raw_event[i]);
+		color_fprintf(stdout, color, " %02x", raw_event[i]);
 
 		if (((i & 15) == 15) || i == event->header.size-1) {
-			dump_printf_color("  ", color);
+			color_fprintf(stdout, color, "  ");
 			for (j = 0; j < 15-(i & 15); j++)
-				dump_printf_color("   ", color);
-			for (j = 0; j < (i & 15); j++) {
-				if (isprint(raw_event[i-15+j]))
-					dump_printf_color("%c", color,
-							  raw_event[i-15+j]);
-				else
-					dump_printf_color(".", color);
+				color_fprintf(stdout, color, "   ");
+			for (j = i & ~15; j <= i; j++) {
+				color_fprintf(stdout, color, "%c",
+					      isprint(raw_event[j]) ?
+					      raw_event[j] : '.');
 			}
-			dump_printf_color("\n", color);
+			color_fprintf(stdout, color, "\n");
 		}
 	}
-	dump_printf(".\n");
+	printf(".\n");
 }
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index 047ac3324eb..443694c36b0 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -4,36 +4,19 @@
 
 #include <stdbool.h>
 #include "event.h"
+#include "../ui/helpline.h"
+#include "../ui/progress.h"
+#include "../ui/util.h"
 
 extern int verbose;
-extern bool dump_trace;
+extern bool quiet, dump_trace;
 
 int dump_printf(const char *fmt, ...) __attribute__((format(printf, 1, 2)));
-void trace_event(event_t *event);
+void trace_event(union perf_event *event);
 
-struct ui_progress;
+int ui__error(const char *format, ...) __attribute__((format(printf, 1, 2)));
+int ui__warning(const char *format, ...) __attribute__((format(printf, 1, 2)));
 
-#ifdef NO_NEWT_SUPPORT
-static inline int browser__show_help(const char *format __used, va_list ap __used)
-{
-	return 0;
-}
-
-static inline struct ui_progress *ui_progress__new(const char *title __used,
-						   u64 total __used)
-{
-	return (struct ui_progress *)1;
-}
-
-static inline void ui_progress__update(struct ui_progress *self __used,
-				       u64 curr __used) {}
-
-static inline void ui_progress__delete(struct ui_progress *self __used) {}
-#else
-int browser__show_help(const char *format, va_list ap);
-struct ui_progress *ui_progress__new(const char *title, u64 total);
-void ui_progress__update(struct ui_progress *self, u64 curr);
-void ui_progress__delete(struct ui_progress *self);
-#endif
+void pr_stat(const char *fmt, ...);
 
 #endif	/* __PERF_DEBUG_H */
diff --git a/tools/perf/util/debugfs.c b/tools/perf/util/debugfs.c
deleted file mode 100644
index a88fefc0cc0..00000000000
--- a/tools/perf/util/debugfs.c
+++ /dev/null
@@ -1,240 +0,0 @@
-#include "util.h"
-#include "debugfs.h"
-#include "cache.h"
-
-static int debugfs_premounted;
-static char debugfs_mountpoint[MAX_PATH+1];
-
-static const char *debugfs_known_mountpoints[] = {
-	"/sys/kernel/debug/",
-	"/debug/",
-	0,
-};
-
-/* use this to force a umount */
-void debugfs_force_cleanup(void)
-{
-	debugfs_find_mountpoint();
-	debugfs_premounted = 0;
-	debugfs_umount();
-}
-
-/* construct a full path to a debugfs element */
-int debugfs_make_path(const char *element, char *buffer, int size)
-{
-	int len;
-
-	if (strlen(debugfs_mountpoint) == 0) {
-		buffer[0] = '\0';
-		return -1;
-	}
-
-	len = strlen(debugfs_mountpoint) + strlen(element) + 1;
-	if (len >= size)
-		return len+1;
-
-	snprintf(buffer, size-1, "%s/%s", debugfs_mountpoint, element);
-	return 0;
-}
-
-static int debugfs_found;
-
-/* find the path to the mounted debugfs */
-const char *debugfs_find_mountpoint(void)
-{
-	const char **ptr;
-	char type[100];
-	FILE *fp;
-
-	if (debugfs_found)
-		return (const char *) debugfs_mountpoint;
-
-	ptr = debugfs_known_mountpoints;
-	while (*ptr) {
-		if (debugfs_valid_mountpoint(*ptr) == 0) {
-			debugfs_found = 1;
-			strcpy(debugfs_mountpoint, *ptr);
-			return debugfs_mountpoint;
-		}
-		ptr++;
-	}
-
-	/* give up and parse /proc/mounts */
-	fp = fopen("/proc/mounts", "r");
-	if (fp == NULL)
-		die("Can't open /proc/mounts for read");
-
-	while (fscanf(fp, "%*s %"
-		      STR(MAX_PATH)
-		      "s %99s %*s %*d %*d\n",
-		      debugfs_mountpoint, type) == 2) {
-		if (strcmp(type, "debugfs") == 0)
-			break;
-	}
-	fclose(fp);
-
-	if (strcmp(type, "debugfs") != 0)
-		return NULL;
-
-	debugfs_found = 1;
-
-	return debugfs_mountpoint;
-}
-
-/* verify that a mountpoint is actually a debugfs instance */
-
-int debugfs_valid_mountpoint(const char *debugfs)
-{
-	struct statfs st_fs;
-
-	if (statfs(debugfs, &st_fs) < 0)
-		return -ENOENT;
-	else if (st_fs.f_type != (long) DEBUGFS_MAGIC)
-		return -ENOENT;
-
-	return 0;
-}
-
-
-int debugfs_valid_entry(const char *path)
-{
-	struct stat st;
-
-	if (stat(path, &st))
-		return -errno;
-
-	return 0;
-}
-
-/* mount the debugfs somewhere if it's not mounted */
-
-char *debugfs_mount(const char *mountpoint)
-{
-	/* see if it's already mounted */
-	if (debugfs_find_mountpoint()) {
-		debugfs_premounted = 1;
-		return debugfs_mountpoint;
-	}
-
-	/* if not mounted and no argument */
-	if (mountpoint == NULL) {
-		/* see if environment variable set */
-		mountpoint = getenv(PERF_DEBUGFS_ENVIRONMENT);
-		/* if no environment variable, use default */
-		if (mountpoint == NULL)
-			mountpoint = "/sys/kernel/debug";
-	}
-
-	if (mount(NULL, mountpoint, "debugfs", 0, NULL) < 0)
-		return NULL;
-
-	/* save the mountpoint */
-	strncpy(debugfs_mountpoint, mountpoint, sizeof(debugfs_mountpoint));
-	debugfs_found = 1;
-
-	return debugfs_mountpoint;
-}
-
-/* umount the debugfs */
-
-int debugfs_umount(void)
-{
-	char umountcmd[128];
-	int ret;
-
-	/* if it was already mounted, leave it */
-	if (debugfs_premounted)
-		return 0;
-
-	/* make sure it's a valid mount point */
-	ret = debugfs_valid_mountpoint(debugfs_mountpoint);
-	if (ret)
-		return ret;
-
-	snprintf(umountcmd, sizeof(umountcmd),
-		 "/bin/umount %s", debugfs_mountpoint);
-	return system(umountcmd);
-}
-
-int debugfs_write(const char *entry, const char *value)
-{
-	char path[MAX_PATH+1];
-	int ret, count;
-	int fd;
-
-	/* construct the path */
-	snprintf(path, sizeof(path), "%s/%s", debugfs_mountpoint, entry);
-
-	/* verify that it exists */
-	ret = debugfs_valid_entry(path);
-	if (ret)
-		return ret;
-
-	/* get how many chars we're going to write */
-	count = strlen(value);
-
-	/* open the debugfs entry */
-	fd = open(path, O_RDWR);
-	if (fd < 0)
-		return -errno;
-
-	while (count > 0) {
-		/* write it */
-		ret = write(fd, value, count);
-		if (ret <= 0) {
-			if (ret == EAGAIN)
-				continue;
-			close(fd);
-			return -errno;
-		}
-		count -= ret;
-	}
-
-	/* close it */
-	close(fd);
-
-	/* return success */
-	return 0;
-}
-
-/*
- * read a debugfs entry
- * returns the number of chars read or a negative errno
- */
-int debugfs_read(const char *entry, char *buffer, size_t size)
-{
-	char path[MAX_PATH+1];
-	int ret;
-	int fd;
-
-	/* construct the path */
-	snprintf(path, sizeof(path), "%s/%s", debugfs_mountpoint, entry);
-
-	/* verify that it exists */
-	ret = debugfs_valid_entry(path);
-	if (ret)
-		return ret;
-
-	/* open the debugfs entry */
-	fd = open(path, O_RDONLY);
-	if (fd < 0)
-		return -errno;
-
-	do {
-		/* read it */
-		ret = read(fd, buffer, size);
-		if (ret == 0) {
-			close(fd);
-			return EOF;
-		}
-	} while (ret < 0 && errno == EAGAIN);
-
-	/* close it */
-	close(fd);
-
-	/* make *sure* there's a null character at the end */
-	buffer[ret] = '\0';
-
-	/* return the number of chars read */
-	return ret;
-}
diff --git a/tools/perf/util/debugfs.h b/tools/perf/util/debugfs.h
deleted file mode 100644
index 83a02879745..00000000000
--- a/tools/perf/util/debugfs.h
+++ /dev/null
@@ -1,25 +0,0 @@
-#ifndef __DEBUGFS_H__
-#define __DEBUGFS_H__
-
-#include <sys/mount.h>
-
-#ifndef MAX_PATH
-# define MAX_PATH 256
-#endif
-
-#ifndef STR
-# define _STR(x) #x
-# define STR(x) _STR(x)
-#endif
-
-extern const char *debugfs_find_mountpoint(void);
-extern int debugfs_valid_mountpoint(const char *debugfs);
-extern int debugfs_valid_entry(const char *path);
-extern char *debugfs_mount(const char *mountpoint);
-extern int debugfs_umount(void);
-extern int debugfs_write(const char *entry, const char *value);
-extern int debugfs_read(const char *entry, char *buffer, size_t size);
-extern void debugfs_force_cleanup(void);
-extern int debugfs_make_path(const char *element, char *buffer, int size);
-
-#endif /* __DEBUGFS_H__ */
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
new file mode 100644
index 00000000000..819f10414f0
--- /dev/null
+++ b/tools/perf/util/dso.c
@@ -0,0 +1,900 @@
+#include <asm/bug.h>
+#include <sys/time.h>
+#include <sys/resource.h>
+#include "symbol.h"
+#include "dso.h"
+#include "machine.h"
+#include "util.h"
+#include "debug.h"
+
+char dso__symtab_origin(const struct dso *dso)
+{
+	static const char origin[] = {
+		[DSO_BINARY_TYPE__KALLSYMS]			= 'k',
+		[DSO_BINARY_TYPE__VMLINUX]			= 'v',
+		[DSO_BINARY_TYPE__JAVA_JIT]			= 'j',
+		[DSO_BINARY_TYPE__DEBUGLINK]			= 'l',
+		[DSO_BINARY_TYPE__BUILD_ID_CACHE]		= 'B',
+		[DSO_BINARY_TYPE__FEDORA_DEBUGINFO]		= 'f',
+		[DSO_BINARY_TYPE__UBUNTU_DEBUGINFO]		= 'u',
+		[DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO]	= 'o',
+		[DSO_BINARY_TYPE__BUILDID_DEBUGINFO]		= 'b',
+		[DSO_BINARY_TYPE__SYSTEM_PATH_DSO]		= 'd',
+		[DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE]		= 'K',
+		[DSO_BINARY_TYPE__GUEST_KALLSYMS]		= 'g',
+		[DSO_BINARY_TYPE__GUEST_KMODULE]		= 'G',
+		[DSO_BINARY_TYPE__GUEST_VMLINUX]		= 'V',
+	};
+
+	if (dso == NULL || dso->symtab_type == DSO_BINARY_TYPE__NOT_FOUND)
+		return '!';
+	return origin[dso->symtab_type];
+}
+
+int dso__read_binary_type_filename(const struct dso *dso,
+				   enum dso_binary_type type,
+				   char *root_dir, char *filename, size_t size)
+{
+	char build_id_hex[BUILD_ID_SIZE * 2 + 1];
+	int ret = 0;
+
+	switch (type) {
+	case DSO_BINARY_TYPE__DEBUGLINK: {
+		char *debuglink;
+
+		strncpy(filename, dso->long_name, size);
+		debuglink = filename + dso->long_name_len;
+		while (debuglink != filename && *debuglink != '/')
+			debuglink--;
+		if (*debuglink == '/')
+			debuglink++;
+		ret = filename__read_debuglink(dso->long_name, debuglink,
+					       size - (debuglink - filename));
+		}
+		break;
+	case DSO_BINARY_TYPE__BUILD_ID_CACHE:
+		/* skip the locally configured cache if a symfs is given */
+		if (symbol_conf.symfs[0] ||
+		    (dso__build_id_filename(dso, filename, size) == NULL))
+			ret = -1;
+		break;
+
+	case DSO_BINARY_TYPE__FEDORA_DEBUGINFO:
+		snprintf(filename, size, "%s/usr/lib/debug%s.debug",
+			 symbol_conf.symfs, dso->long_name);
+		break;
+
+	case DSO_BINARY_TYPE__UBUNTU_DEBUGINFO:
+		snprintf(filename, size, "%s/usr/lib/debug%s",
+			 symbol_conf.symfs, dso->long_name);
+		break;
+
+	case DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO:
+	{
+		const char *last_slash;
+		size_t len;
+		size_t dir_size;
+
+		last_slash = dso->long_name + dso->long_name_len;
+		while (last_slash != dso->long_name && *last_slash != '/')
+			last_slash--;
+
+		len = scnprintf(filename, size, "%s", symbol_conf.symfs);
+		dir_size = last_slash - dso->long_name + 2;
+		if (dir_size > (size - len)) {
+			ret = -1;
+			break;
+		}
+		len += scnprintf(filename + len, dir_size, "%s",  dso->long_name);
+		len += scnprintf(filename + len , size - len, ".debug%s",
+								last_slash);
+		break;
+	}
+
+	case DSO_BINARY_TYPE__BUILDID_DEBUGINFO:
+		if (!dso->has_build_id) {
+			ret = -1;
+			break;
+		}
+
+		build_id__sprintf(dso->build_id,
+				  sizeof(dso->build_id),
+				  build_id_hex);
+		snprintf(filename, size,
+			 "%s/usr/lib/debug/.build-id/%.2s/%s.debug",
+			 symbol_conf.symfs, build_id_hex, build_id_hex + 2);
+		break;
+
+	case DSO_BINARY_TYPE__VMLINUX:
+	case DSO_BINARY_TYPE__GUEST_VMLINUX:
+	case DSO_BINARY_TYPE__SYSTEM_PATH_DSO:
+		snprintf(filename, size, "%s%s",
+			 symbol_conf.symfs, dso->long_name);
+		break;
+
+	case DSO_BINARY_TYPE__GUEST_KMODULE:
+		snprintf(filename, size, "%s%s%s", symbol_conf.symfs,
+			 root_dir, dso->long_name);
+		break;
+
+	case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE:
+		snprintf(filename, size, "%s%s", symbol_conf.symfs,
+			 dso->long_name);
+		break;
+
+	case DSO_BINARY_TYPE__KCORE:
+	case DSO_BINARY_TYPE__GUEST_KCORE:
+		snprintf(filename, size, "%s", dso->long_name);
+		break;
+
+	default:
+	case DSO_BINARY_TYPE__KALLSYMS:
+	case DSO_BINARY_TYPE__GUEST_KALLSYMS:
+	case DSO_BINARY_TYPE__JAVA_JIT:
+	case DSO_BINARY_TYPE__NOT_FOUND:
+		ret = -1;
+		break;
+	}
+
+	return ret;
+}
+
+/*
+ * Global list of open DSOs and the counter.
+ */
+static LIST_HEAD(dso__data_open);
+static long dso__data_open_cnt;
+
+static void dso__list_add(struct dso *dso)
+{
+	list_add_tail(&dso->data.open_entry, &dso__data_open);
+	dso__data_open_cnt++;
+}
+
+static void dso__list_del(struct dso *dso)
+{
+	list_del(&dso->data.open_entry);
+	WARN_ONCE(dso__data_open_cnt <= 0,
+		  "DSO data fd counter out of bounds.");
+	dso__data_open_cnt--;
+}
+
+static void close_first_dso(void);
+
+static int do_open(char *name)
+{
+	int fd;
+
+	do {
+		fd = open(name, O_RDONLY);
+		if (fd >= 0)
+			return fd;
+
+		pr_debug("dso open failed, mmap: %s\n", strerror(errno));
+		if (!dso__data_open_cnt || errno != EMFILE)
+			break;
+
+		close_first_dso();
+	} while (1);
+
+	return -1;
+}
+
+static int __open_dso(struct dso *dso, struct machine *machine)
+{
+	int fd;
+	char *root_dir = (char *)"";
+	char *name = malloc(PATH_MAX);
+
+	if (!name)
+		return -ENOMEM;
+
+	if (machine)
+		root_dir = machine->root_dir;
+
+	if (dso__read_binary_type_filename(dso, dso->binary_type,
+					    root_dir, name, PATH_MAX)) {
+		free(name);
+		return -EINVAL;
+	}
+
+	fd = do_open(name);
+	free(name);
+	return fd;
+}
+
+static void check_data_close(void);
+
+/**
+ * dso_close - Open DSO data file
+ * @dso: dso object
+ *
+ * Open @dso's data file descriptor and updates
+ * list/count of open DSO objects.
+ */
+static int open_dso(struct dso *dso, struct machine *machine)
+{
+	int fd = __open_dso(dso, machine);
+
+	if (fd > 0) {
+		dso__list_add(dso);
+		/*
+		 * Check if we crossed the allowed number
+		 * of opened DSOs and close one if needed.
+		 */
+		check_data_close();
+	}
+
+	return fd;
+}
+
+static void close_data_fd(struct dso *dso)
+{
+	if (dso->data.fd >= 0) {
+		close(dso->data.fd);
+		dso->data.fd = -1;
+		dso->data.file_size = 0;
+		dso__list_del(dso);
+	}
+}
+
+/**
+ * dso_close - Close DSO data file
+ * @dso: dso object
+ *
+ * Close @dso's data file descriptor and updates
+ * list/count of open DSO objects.
+ */
+static void close_dso(struct dso *dso)
+{
+	close_data_fd(dso);
+}
+
+static void close_first_dso(void)
+{
+	struct dso *dso;
+
+	dso = list_first_entry(&dso__data_open, struct dso, data.open_entry);
+	close_dso(dso);
+}
+
+static rlim_t get_fd_limit(void)
+{
+	struct rlimit l;
+	rlim_t limit = 0;
+
+	/* Allow half of the current open fd limit. */
+	if (getrlimit(RLIMIT_NOFILE, &l) == 0) {
+		if (l.rlim_cur == RLIM_INFINITY)
+			limit = l.rlim_cur;
+		else
+			limit = l.rlim_cur / 2;
+	} else {
+		pr_err("failed to get fd limit\n");
+		limit = 1;
+	}
+
+	return limit;
+}
+
+static bool may_cache_fd(void)
+{
+	static rlim_t limit;
+
+	if (!limit)
+		limit = get_fd_limit();
+
+	if (limit == RLIM_INFINITY)
+		return true;
+
+	return limit > (rlim_t) dso__data_open_cnt;
+}
+
+/*
+ * Check and close LRU dso if we crossed allowed limit
+ * for opened dso file descriptors. The limit is half
+ * of the RLIMIT_NOFILE files opened.
+*/
+static void check_data_close(void)
+{
+	bool cache_fd = may_cache_fd();
+
+	if (!cache_fd)
+		close_first_dso();
+}
+
+/**
+ * dso__data_close - Close DSO data file
+ * @dso: dso object
+ *
+ * External interface to close @dso's data file descriptor.
+ */
+void dso__data_close(struct dso *dso)
+{
+	close_dso(dso);
+}
+
+/**
+ * dso__data_fd - Get dso's data file descriptor
+ * @dso: dso object
+ * @machine: machine object
+ *
+ * External interface to find dso's file, open it and
+ * returns file descriptor.
+ */
+int dso__data_fd(struct dso *dso, struct machine *machine)
+{
+	enum dso_binary_type binary_type_data[] = {
+		DSO_BINARY_TYPE__BUILD_ID_CACHE,
+		DSO_BINARY_TYPE__SYSTEM_PATH_DSO,
+		DSO_BINARY_TYPE__NOT_FOUND,
+	};
+	int i = 0;
+
+	if (dso->data.fd >= 0)
+		return dso->data.fd;
+
+	if (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND) {
+		dso->data.fd = open_dso(dso, machine);
+		return dso->data.fd;
+	}
+
+	do {
+		int fd;
+
+		dso->binary_type = binary_type_data[i++];
+
+		fd = open_dso(dso, machine);
+		if (fd >= 0)
+			return dso->data.fd = fd;
+
+	} while (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND);
+
+	return -EINVAL;
+}
+
+static void
+dso_cache__free(struct rb_root *root)
+{
+	struct rb_node *next = rb_first(root);
+
+	while (next) {
+		struct dso_cache *cache;
+
+		cache = rb_entry(next, struct dso_cache, rb_node);
+		next = rb_next(&cache->rb_node);
+		rb_erase(&cache->rb_node, root);
+		free(cache);
+	}
+}
+
+static struct dso_cache *dso_cache__find(const struct rb_root *root, u64 offset)
+{
+	struct rb_node * const *p = &root->rb_node;
+	const struct rb_node *parent = NULL;
+	struct dso_cache *cache;
+
+	while (*p != NULL) {
+		u64 end;
+
+		parent = *p;
+		cache = rb_entry(parent, struct dso_cache, rb_node);
+		end = cache->offset + DSO__DATA_CACHE_SIZE;
+
+		if (offset < cache->offset)
+			p = &(*p)->rb_left;
+		else if (offset >= end)
+			p = &(*p)->rb_right;
+		else
+			return cache;
+	}
+	return NULL;
+}
+
+static void
+dso_cache__insert(struct rb_root *root, struct dso_cache *new)
+{
+	struct rb_node **p = &root->rb_node;
+	struct rb_node *parent = NULL;
+	struct dso_cache *cache;
+	u64 offset = new->offset;
+
+	while (*p != NULL) {
+		u64 end;
+
+		parent = *p;
+		cache = rb_entry(parent, struct dso_cache, rb_node);
+		end = cache->offset + DSO__DATA_CACHE_SIZE;
+
+		if (offset < cache->offset)
+			p = &(*p)->rb_left;
+		else if (offset >= end)
+			p = &(*p)->rb_right;
+	}
+
+	rb_link_node(&new->rb_node, parent, p);
+	rb_insert_color(&new->rb_node, root);
+}
+
+static ssize_t
+dso_cache__memcpy(struct dso_cache *cache, u64 offset,
+		  u8 *data, u64 size)
+{
+	u64 cache_offset = offset - cache->offset;
+	u64 cache_size   = min(cache->size - cache_offset, size);
+
+	memcpy(data, cache->data + cache_offset, cache_size);
+	return cache_size;
+}
+
+static ssize_t
+dso_cache__read(struct dso *dso, u64 offset, u8 *data, ssize_t size)
+{
+	struct dso_cache *cache;
+	ssize_t ret;
+
+	do {
+		u64 cache_offset;
+
+		ret = -ENOMEM;
+
+		cache = zalloc(sizeof(*cache) + DSO__DATA_CACHE_SIZE);
+		if (!cache)
+			break;
+
+		cache_offset = offset & DSO__DATA_CACHE_MASK;
+		ret = -EINVAL;
+
+		if (-1 == lseek(dso->data.fd, cache_offset, SEEK_SET))
+			break;
+
+		ret = read(dso->data.fd, cache->data, DSO__DATA_CACHE_SIZE);
+		if (ret <= 0)
+			break;
+
+		cache->offset = cache_offset;
+		cache->size   = ret;
+		dso_cache__insert(&dso->data.cache, cache);
+
+		ret = dso_cache__memcpy(cache, offset, data, size);
+
+	} while (0);
+
+	if (ret <= 0)
+		free(cache);
+
+	return ret;
+}
+
+static ssize_t dso_cache_read(struct dso *dso, u64 offset,
+			      u8 *data, ssize_t size)
+{
+	struct dso_cache *cache;
+
+	cache = dso_cache__find(&dso->data.cache, offset);
+	if (cache)
+		return dso_cache__memcpy(cache, offset, data, size);
+	else
+		return dso_cache__read(dso, offset, data, size);
+}
+
+/*
+ * Reads and caches dso data DSO__DATA_CACHE_SIZE size chunks
+ * in the rb_tree. Any read to already cached data is served
+ * by cached data.
+ */
+static ssize_t cached_read(struct dso *dso, u64 offset, u8 *data, ssize_t size)
+{
+	ssize_t r = 0;
+	u8 *p = data;
+
+	do {
+		ssize_t ret;
+
+		ret = dso_cache_read(dso, offset, p, size);
+		if (ret < 0)
+			return ret;
+
+		/* Reached EOF, return what we have. */
+		if (!ret)
+			break;
+
+		BUG_ON(ret > size);
+
+		r      += ret;
+		p      += ret;
+		offset += ret;
+		size   -= ret;
+
+	} while (size);
+
+	return r;
+}
+
+static int data_file_size(struct dso *dso)
+{
+	struct stat st;
+
+	if (!dso->data.file_size) {
+		if (fstat(dso->data.fd, &st)) {
+			pr_err("dso mmap failed, fstat: %s\n", strerror(errno));
+			return -1;
+		}
+		dso->data.file_size = st.st_size;
+	}
+
+	return 0;
+}
+
+static ssize_t data_read_offset(struct dso *dso, u64 offset,
+				u8 *data, ssize_t size)
+{
+	if (data_file_size(dso))
+		return -1;
+
+	/* Check the offset sanity. */
+	if (offset > dso->data.file_size)
+		return -1;
+
+	if (offset + size < offset)
+		return -1;
+
+	return cached_read(dso, offset, data, size);
+}
+
+/**
+ * dso__data_read_offset - Read data from dso file offset
+ * @dso: dso object
+ * @machine: machine object
+ * @offset: file offset
+ * @data: buffer to store data
+ * @size: size of the @data buffer
+ *
+ * External interface to read data from dso file offset. Open
+ * dso data file and use cached_read to get the data.
+ */
+ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
+			      u64 offset, u8 *data, ssize_t size)
+{
+	if (dso__data_fd(dso, machine) < 0)
+		return -1;
+
+	return data_read_offset(dso, offset, data, size);
+}
+
+/**
+ * dso__data_read_addr - Read data from dso address
+ * @dso: dso object
+ * @machine: machine object
+ * @add: virtual memory address
+ * @data: buffer to store data
+ * @size: size of the @data buffer
+ *
+ * External interface to read data from dso address.
+ */
+ssize_t dso__data_read_addr(struct dso *dso, struct map *map,
+			    struct machine *machine, u64 addr,
+			    u8 *data, ssize_t size)
+{
+	u64 offset = map->map_ip(map, addr);
+	return dso__data_read_offset(dso, machine, offset, data, size);
+}
+
+struct map *dso__new_map(const char *name)
+{
+	struct map *map = NULL;
+	struct dso *dso = dso__new(name);
+
+	if (dso)
+		map = map__new2(0, dso, MAP__FUNCTION);
+
+	return map;
+}
+
+struct dso *dso__kernel_findnew(struct machine *machine, const char *name,
+		    const char *short_name, int dso_type)
+{
+	/*
+	 * The kernel dso could be created by build_id processing.
+	 */
+	struct dso *dso = __dsos__findnew(&machine->kernel_dsos, name);
+
+	/*
+	 * We need to run this in all cases, since during the build_id
+	 * processing we had no idea this was the kernel dso.
+	 */
+	if (dso != NULL) {
+		dso__set_short_name(dso, short_name, false);
+		dso->kernel = dso_type;
+	}
+
+	return dso;
+}
+
+void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated)
+{
+	if (name == NULL)
+		return;
+
+	if (dso->long_name_allocated)
+		free((char *)dso->long_name);
+
+	dso->long_name		 = name;
+	dso->long_name_len	 = strlen(name);
+	dso->long_name_allocated = name_allocated;
+}
+
+void dso__set_short_name(struct dso *dso, const char *name, bool name_allocated)
+{
+	if (name == NULL)
+		return;
+
+	if (dso->short_name_allocated)
+		free((char *)dso->short_name);
+
+	dso->short_name		  = name;
+	dso->short_name_len	  = strlen(name);
+	dso->short_name_allocated = name_allocated;
+}
+
+static void dso__set_basename(struct dso *dso)
+{
+       /*
+        * basename() may modify path buffer, so we must pass
+        * a copy.
+        */
+       char *base, *lname = strdup(dso->long_name);
+
+       if (!lname)
+               return;
+
+       /*
+        * basename() may return a pointer to internal
+        * storage which is reused in subsequent calls
+        * so copy the result.
+        */
+       base = strdup(basename(lname));
+
+       free(lname);
+
+       if (!base)
+               return;
+
+       dso__set_short_name(dso, base, true);
+}
+
+int dso__name_len(const struct dso *dso)
+{
+	if (!dso)
+		return strlen("[unknown]");
+	if (verbose)
+		return dso->long_name_len;
+
+	return dso->short_name_len;
+}
+
+bool dso__loaded(const struct dso *dso, enum map_type type)
+{
+	return dso->loaded & (1 << type);
+}
+
+bool dso__sorted_by_name(const struct dso *dso, enum map_type type)
+{
+	return dso->sorted_by_name & (1 << type);
+}
+
+void dso__set_sorted_by_name(struct dso *dso, enum map_type type)
+{
+	dso->sorted_by_name |= (1 << type);
+}
+
+struct dso *dso__new(const char *name)
+{
+	struct dso *dso = calloc(1, sizeof(*dso) + strlen(name) + 1);
+
+	if (dso != NULL) {
+		int i;
+		strcpy(dso->name, name);
+		dso__set_long_name(dso, dso->name, false);
+		dso__set_short_name(dso, dso->name, false);
+		for (i = 0; i < MAP__NR_TYPES; ++i)
+			dso->symbols[i] = dso->symbol_names[i] = RB_ROOT;
+		dso->data.cache = RB_ROOT;
+		dso->data.fd = -1;
+		dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND;
+		dso->binary_type = DSO_BINARY_TYPE__NOT_FOUND;
+		dso->loaded = 0;
+		dso->rel = 0;
+		dso->sorted_by_name = 0;
+		dso->has_build_id = 0;
+		dso->has_srcline = 1;
+		dso->a2l_fails = 1;
+		dso->kernel = DSO_TYPE_USER;
+		dso->needs_swap = DSO_SWAP__UNSET;
+		INIT_LIST_HEAD(&dso->node);
+		INIT_LIST_HEAD(&dso->data.open_entry);
+	}
+
+	return dso;
+}
+
+void dso__delete(struct dso *dso)
+{
+	int i;
+	for (i = 0; i < MAP__NR_TYPES; ++i)
+		symbols__delete(&dso->symbols[i]);
+
+	if (dso->short_name_allocated) {
+		zfree((char **)&dso->short_name);
+		dso->short_name_allocated = false;
+	}
+
+	if (dso->long_name_allocated) {
+		zfree((char **)&dso->long_name);
+		dso->long_name_allocated = false;
+	}
+
+	dso__data_close(dso);
+	dso_cache__free(&dso->data.cache);
+	dso__free_a2l(dso);
+	zfree(&dso->symsrc_filename);
+	free(dso);
+}
+
+void dso__set_build_id(struct dso *dso, void *build_id)
+{
+	memcpy(dso->build_id, build_id, sizeof(dso->build_id));
+	dso->has_build_id = 1;
+}
+
+bool dso__build_id_equal(const struct dso *dso, u8 *build_id)
+{
+	return memcmp(dso->build_id, build_id, sizeof(dso->build_id)) == 0;
+}
+
+void dso__read_running_kernel_build_id(struct dso *dso, struct machine *machine)
+{
+	char path[PATH_MAX];
+
+	if (machine__is_default_guest(machine))
+		return;
+	sprintf(path, "%s/sys/kernel/notes", machine->root_dir);
+	if (sysfs__read_build_id(path, dso->build_id,
+				 sizeof(dso->build_id)) == 0)
+		dso->has_build_id = true;
+}
+
+int dso__kernel_module_get_build_id(struct dso *dso,
+				    const char *root_dir)
+{
+	char filename[PATH_MAX];
+	/*
+	 * kernel module short names are of the form "[module]" and
+	 * we need just "module" here.
+	 */
+	const char *name = dso->short_name + 1;
+
+	snprintf(filename, sizeof(filename),
+		 "%s/sys/module/%.*s/notes/.note.gnu.build-id",
+		 root_dir, (int)strlen(name) - 1, name);
+
+	if (sysfs__read_build_id(filename, dso->build_id,
+				 sizeof(dso->build_id)) == 0)
+		dso->has_build_id = true;
+
+	return 0;
+}
+
+bool __dsos__read_build_ids(struct list_head *head, bool with_hits)
+{
+	bool have_build_id = false;
+	struct dso *pos;
+
+	list_for_each_entry(pos, head, node) {
+		if (with_hits && !pos->hit)
+			continue;
+		if (pos->has_build_id) {
+			have_build_id = true;
+			continue;
+		}
+		if (filename__read_build_id(pos->long_name, pos->build_id,
+					    sizeof(pos->build_id)) > 0) {
+			have_build_id	  = true;
+			pos->has_build_id = true;
+		}
+	}
+
+	return have_build_id;
+}
+
+void dsos__add(struct list_head *head, struct dso *dso)
+{
+	list_add_tail(&dso->node, head);
+}
+
+struct dso *dsos__find(const struct list_head *head, const char *name, bool cmp_short)
+{
+	struct dso *pos;
+
+	if (cmp_short) {
+		list_for_each_entry(pos, head, node)
+			if (strcmp(pos->short_name, name) == 0)
+				return pos;
+		return NULL;
+	}
+	list_for_each_entry(pos, head, node)
+		if (strcmp(pos->long_name, name) == 0)
+			return pos;
+	return NULL;
+}
+
+struct dso *__dsos__findnew(struct list_head *head, const char *name)
+{
+	struct dso *dso = dsos__find(head, name, false);
+
+	if (!dso) {
+		dso = dso__new(name);
+		if (dso != NULL) {
+			dsos__add(head, dso);
+			dso__set_basename(dso);
+		}
+	}
+
+	return dso;
+}
+
+size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp,
+			       bool (skip)(struct dso *dso, int parm), int parm)
+{
+	struct dso *pos;
+	size_t ret = 0;
+
+	list_for_each_entry(pos, head, node) {
+		if (skip && skip(pos, parm))
+			continue;
+		ret += dso__fprintf_buildid(pos, fp);
+		ret += fprintf(fp, " %s\n", pos->long_name);
+	}
+	return ret;
+}
+
+size_t __dsos__fprintf(struct list_head *head, FILE *fp)
+{
+	struct dso *pos;
+	size_t ret = 0;
+
+	list_for_each_entry(pos, head, node) {
+		int i;
+		for (i = 0; i < MAP__NR_TYPES; ++i)
+			ret += dso__fprintf(pos, i, fp);
+	}
+
+	return ret;
+}
+
+size_t dso__fprintf_buildid(struct dso *dso, FILE *fp)
+{
+	char sbuild_id[BUILD_ID_SIZE * 2 + 1];
+
+	build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id);
+	return fprintf(fp, "%s", sbuild_id);
+}
+
+size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp)
+{
+	struct rb_node *nd;
+	size_t ret = fprintf(fp, "dso: %s (", dso->short_name);
+
+	if (dso->short_name != dso->long_name)
+		ret += fprintf(fp, "%s, ", dso->long_name);
+	ret += fprintf(fp, "%s, %sloaded, ", map_type__name[type],
+		       dso__loaded(dso, type) ? "" : "NOT ");
+	ret += dso__fprintf_buildid(dso, fp);
+	ret += fprintf(fp, ")\n");
+	for (nd = rb_first(&dso->symbols[type]); nd; nd = rb_next(nd)) {
+		struct symbol *pos = rb_entry(nd, struct symbol, rb_node);
+		ret += symbol__fprintf(pos, fp);
+	}
+
+	return ret;
+}
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
new file mode 100644
index 00000000000..ad553ba257b
--- /dev/null
+++ b/tools/perf/util/dso.h
@@ -0,0 +1,232 @@
+#ifndef __PERF_DSO
+#define __PERF_DSO
+
+#include <linux/types.h>
+#include <linux/rbtree.h>
+#include <stdbool.h>
+#include <linux/types.h>
+#include "map.h"
+#include "build-id.h"
+
+enum dso_binary_type {
+	DSO_BINARY_TYPE__KALLSYMS = 0,
+	DSO_BINARY_TYPE__GUEST_KALLSYMS,
+	DSO_BINARY_TYPE__VMLINUX,
+	DSO_BINARY_TYPE__GUEST_VMLINUX,
+	DSO_BINARY_TYPE__JAVA_JIT,
+	DSO_BINARY_TYPE__DEBUGLINK,
+	DSO_BINARY_TYPE__BUILD_ID_CACHE,
+	DSO_BINARY_TYPE__FEDORA_DEBUGINFO,
+	DSO_BINARY_TYPE__UBUNTU_DEBUGINFO,
+	DSO_BINARY_TYPE__BUILDID_DEBUGINFO,
+	DSO_BINARY_TYPE__SYSTEM_PATH_DSO,
+	DSO_BINARY_TYPE__GUEST_KMODULE,
+	DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE,
+	DSO_BINARY_TYPE__KCORE,
+	DSO_BINARY_TYPE__GUEST_KCORE,
+	DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO,
+	DSO_BINARY_TYPE__NOT_FOUND,
+};
+
+enum dso_kernel_type {
+	DSO_TYPE_USER = 0,
+	DSO_TYPE_KERNEL,
+	DSO_TYPE_GUEST_KERNEL
+};
+
+enum dso_swap_type {
+	DSO_SWAP__UNSET,
+	DSO_SWAP__NO,
+	DSO_SWAP__YES,
+};
+
+#define DSO__SWAP(dso, type, val)			\
+({							\
+	type ____r = val;				\
+	BUG_ON(dso->needs_swap == DSO_SWAP__UNSET);	\
+	if (dso->needs_swap == DSO_SWAP__YES) {		\
+		switch (sizeof(____r)) {		\
+		case 2:					\
+			____r = bswap_16(val);		\
+			break;				\
+		case 4:					\
+			____r = bswap_32(val);		\
+			break;				\
+		case 8:					\
+			____r = bswap_64(val);		\
+			break;				\
+		default:				\
+			BUG_ON(1);			\
+		}					\
+	}						\
+	____r;						\
+})
+
+#define DSO__DATA_CACHE_SIZE 4096
+#define DSO__DATA_CACHE_MASK ~(DSO__DATA_CACHE_SIZE - 1)
+
+struct dso_cache {
+	struct rb_node	rb_node;
+	u64 offset;
+	u64 size;
+	char data[0];
+};
+
+struct dso {
+	struct list_head node;
+	struct rb_root	 symbols[MAP__NR_TYPES];
+	struct rb_root	 symbol_names[MAP__NR_TYPES];
+	void		 *a2l;
+	char		 *symsrc_filename;
+	unsigned int	 a2l_fails;
+	enum dso_kernel_type	kernel;
+	enum dso_swap_type	needs_swap;
+	enum dso_binary_type	symtab_type;
+	enum dso_binary_type	binary_type;
+	u8		 adjust_symbols:1;
+	u8		 has_build_id:1;
+	u8		 has_srcline:1;
+	u8		 hit:1;
+	u8		 annotate_warned:1;
+	u8		 short_name_allocated:1;
+	u8		 long_name_allocated:1;
+	u8		 sorted_by_name;
+	u8		 loaded;
+	u8		 rel;
+	u8		 build_id[BUILD_ID_SIZE];
+	const char	 *short_name;
+	const char	 *long_name;
+	u16		 long_name_len;
+	u16		 short_name_len;
+
+	/* dso data file */
+	struct {
+		struct rb_root	 cache;
+		int		 fd;
+		size_t		 file_size;
+		struct list_head open_entry;
+	} data;
+
+	char		 name[0];
+};
+
+/* dso__for_each_symbol - iterate over the symbols of given type
+ *
+ * @dso: the 'struct dso *' in which symbols itereated
+ * @pos: the 'struct symbol *' to use as a loop cursor
+ * @n: the 'struct rb_node *' to use as a temporary storage
+ * @type: the 'enum map_type' type of symbols
+ */
+#define dso__for_each_symbol(dso, pos, n, type)	\
+	symbols__for_each_entry(&(dso)->symbols[(type)], pos, n)
+
+static inline void dso__set_loaded(struct dso *dso, enum map_type type)
+{
+	dso->loaded |= (1 << type);
+}
+
+struct dso *dso__new(const char *name);
+void dso__delete(struct dso *dso);
+
+void dso__set_short_name(struct dso *dso, const char *name, bool name_allocated);
+void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated);
+
+int dso__name_len(const struct dso *dso);
+
+bool dso__loaded(const struct dso *dso, enum map_type type);
+
+bool dso__sorted_by_name(const struct dso *dso, enum map_type type);
+void dso__set_sorted_by_name(struct dso *dso, enum map_type type);
+void dso__sort_by_name(struct dso *dso, enum map_type type);
+
+void dso__set_build_id(struct dso *dso, void *build_id);
+bool dso__build_id_equal(const struct dso *dso, u8 *build_id);
+void dso__read_running_kernel_build_id(struct dso *dso,
+				       struct machine *machine);
+int dso__kernel_module_get_build_id(struct dso *dso, const char *root_dir);
+
+char dso__symtab_origin(const struct dso *dso);
+int dso__read_binary_type_filename(const struct dso *dso, enum dso_binary_type type,
+				   char *root_dir, char *filename, size_t size);
+
+/*
+ * The dso__data_* external interface provides following functions:
+ *   dso__data_fd
+ *   dso__data_close
+ *   dso__data_read_offset
+ *   dso__data_read_addr
+ *
+ * Please refer to the dso.c object code for each function and
+ * arguments documentation. Following text tries to explain the
+ * dso file descriptor caching.
+ *
+ * The dso__data* interface allows caching of opened file descriptors
+ * to speed up the dso data accesses. The idea is to leave the file
+ * descriptor opened ideally for the whole life of the dso object.
+ *
+ * The current usage of the dso__data_* interface is as follows:
+ *
+ * Get DSO's fd:
+ *   int fd = dso__data_fd(dso, machine);
+ *   USE 'fd' SOMEHOW
+ *
+ * Read DSO's data:
+ *   n = dso__data_read_offset(dso_0, &machine, 0, buf, BUFSIZE);
+ *   n = dso__data_read_addr(dso_0, &machine, 0, buf, BUFSIZE);
+ *
+ * Eventually close DSO's fd:
+ *   dso__data_close(dso);
+ *
+ * It is not necessary to close the DSO object data file. Each time new
+ * DSO data file is opened, the limit (RLIMIT_NOFILE/2) is checked. Once
+ * it is crossed, the oldest opened DSO object is closed.
+ *
+ * The dso__delete function calls close_dso function to ensure the
+ * data file descriptor gets closed/unmapped before the dso object
+ * is freed.
+ *
+ * TODO
+*/
+int dso__data_fd(struct dso *dso, struct machine *machine);
+void dso__data_close(struct dso *dso);
+
+ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
+			      u64 offset, u8 *data, ssize_t size);
+ssize_t dso__data_read_addr(struct dso *dso, struct map *map,
+			    struct machine *machine, u64 addr,
+			    u8 *data, ssize_t size);
+
+struct map *dso__new_map(const char *name);
+struct dso *dso__kernel_findnew(struct machine *machine, const char *name,
+				const char *short_name, int dso_type);
+
+void dsos__add(struct list_head *head, struct dso *dso);
+struct dso *dsos__find(const struct list_head *head, const char *name,
+		       bool cmp_short);
+struct dso *__dsos__findnew(struct list_head *head, const char *name);
+bool __dsos__read_build_ids(struct list_head *head, bool with_hits);
+
+size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp,
+			       bool (skip)(struct dso *dso, int parm), int parm);
+size_t __dsos__fprintf(struct list_head *head, FILE *fp);
+
+size_t dso__fprintf_buildid(struct dso *dso, FILE *fp);
+size_t dso__fprintf_symbols_by_name(struct dso *dso,
+				    enum map_type type, FILE *fp);
+size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp);
+
+static inline bool dso__is_vmlinux(struct dso *dso)
+{
+	return dso->binary_type == DSO_BINARY_TYPE__VMLINUX ||
+	       dso->binary_type == DSO_BINARY_TYPE__GUEST_VMLINUX;
+}
+
+static inline bool dso__is_kcore(struct dso *dso)
+{
+	return dso->binary_type == DSO_BINARY_TYPE__KCORE ||
+	       dso->binary_type == DSO_BINARY_TYPE__GUEST_KCORE;
+}
+
+void dso__free_a2l(struct dso *dso);
+
+#endif /* __PERF_DSO */
diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
new file mode 100644
index 00000000000..cc66c4049e0
--- /dev/null
+++ b/tools/perf/util/dwarf-aux.c
@@ -0,0 +1,884 @@
+/*
+ * dwarf-aux.c : libdw auxiliary interfaces
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ */
+
+#include <stdbool.h>
+#include "util.h"
+#include "debug.h"
+#include "dwarf-aux.h"
+
+/**
+ * cu_find_realpath - Find the realpath of the target file
+ * @cu_die: A DIE(dwarf information entry) of CU(compilation Unit)
+ * @fname:  The tail filename of the target file
+ *
+ * Find the real(long) path of @fname in @cu_die.
+ */
+const char *cu_find_realpath(Dwarf_Die *cu_die, const char *fname)
+{
+	Dwarf_Files *files;
+	size_t nfiles, i;
+	const char *src = NULL;
+	int ret;
+
+	if (!fname)
+		return NULL;
+
+	ret = dwarf_getsrcfiles(cu_die, &files, &nfiles);
+	if (ret != 0)
+		return NULL;
+
+	for (i = 0; i < nfiles; i++) {
+		src = dwarf_filesrc(files, i, NULL, NULL);
+		if (strtailcmp(src, fname) == 0)
+			break;
+	}
+	if (i == nfiles)
+		return NULL;
+	return src;
+}
+
+/**
+ * cu_get_comp_dir - Get the path of compilation directory
+ * @cu_die: a CU DIE
+ *
+ * Get the path of compilation directory of given @cu_die.
+ * Since this depends on DW_AT_comp_dir, older gcc will not
+ * embedded it. In that case, this returns NULL.
+ */
+const char *cu_get_comp_dir(Dwarf_Die *cu_die)
+{
+	Dwarf_Attribute attr;
+	if (dwarf_attr(cu_die, DW_AT_comp_dir, &attr) == NULL)
+		return NULL;
+	return dwarf_formstring(&attr);
+}
+
+/**
+ * cu_find_lineinfo - Get a line number and file name for given address
+ * @cu_die: a CU DIE
+ * @addr: An address
+ * @fname: a pointer which returns the file name string
+ * @lineno: a pointer which returns the line number
+ *
+ * Find a line number and file name for @addr in @cu_die.
+ */
+int cu_find_lineinfo(Dwarf_Die *cu_die, unsigned long addr,
+		    const char **fname, int *lineno)
+{
+	Dwarf_Line *line;
+	Dwarf_Addr laddr;
+
+	line = dwarf_getsrc_die(cu_die, (Dwarf_Addr)addr);
+	if (line && dwarf_lineaddr(line, &laddr) == 0 &&
+	    addr == (unsigned long)laddr && dwarf_lineno(line, lineno) == 0) {
+		*fname = dwarf_linesrc(line, NULL, NULL);
+		if (!*fname)
+			/* line number is useless without filename */
+			*lineno = 0;
+	}
+
+	return *lineno ?: -ENOENT;
+}
+
+static int __die_find_inline_cb(Dwarf_Die *die_mem, void *data);
+
+/**
+ * cu_walk_functions_at - Walk on function DIEs at given address
+ * @cu_die: A CU DIE
+ * @addr: An address
+ * @callback: A callback which called with found DIEs
+ * @data: A user data
+ *
+ * Walk on function DIEs at given @addr in @cu_die. Passed DIEs
+ * should be subprogram or inlined-subroutines.
+ */
+int cu_walk_functions_at(Dwarf_Die *cu_die, Dwarf_Addr addr,
+		    int (*callback)(Dwarf_Die *, void *), void *data)
+{
+	Dwarf_Die die_mem;
+	Dwarf_Die *sc_die;
+	int ret = -ENOENT;
+
+	/* Inlined function could be recursive. Trace it until fail */
+	for (sc_die = die_find_realfunc(cu_die, addr, &die_mem);
+	     sc_die != NULL;
+	     sc_die = die_find_child(sc_die, __die_find_inline_cb, &addr,
+				     &die_mem)) {
+		ret = callback(sc_die, data);
+		if (ret)
+			break;
+	}
+
+	return ret;
+
+}
+
+/**
+ * die_compare_name - Compare diename and tname
+ * @dw_die: a DIE
+ * @tname: a string of target name
+ *
+ * Compare the name of @dw_die and @tname. Return false if @dw_die has no name.
+ */
+bool die_compare_name(Dwarf_Die *dw_die, const char *tname)
+{
+	const char *name;
+	name = dwarf_diename(dw_die);
+	return name ? (strcmp(tname, name) == 0) : false;
+}
+
+/**
+ * die_get_call_lineno - Get callsite line number of inline-function instance
+ * @in_die: a DIE of an inlined function instance
+ *
+ * Get call-site line number of @in_die. This means from where the inline
+ * function is called.
+ */
+int die_get_call_lineno(Dwarf_Die *in_die)
+{
+	Dwarf_Attribute attr;
+	Dwarf_Word ret;
+
+	if (!dwarf_attr(in_die, DW_AT_call_line, &attr))
+		return -ENOENT;
+
+	dwarf_formudata(&attr, &ret);
+	return (int)ret;
+}
+
+/**
+ * die_get_type - Get type DIE
+ * @vr_die: a DIE of a variable
+ * @die_mem: where to store a type DIE
+ *
+ * Get a DIE of the type of given variable (@vr_die), and store
+ * it to die_mem. Return NULL if fails to get a type DIE.
+ */
+Dwarf_Die *die_get_type(Dwarf_Die *vr_die, Dwarf_Die *die_mem)
+{
+	Dwarf_Attribute attr;
+
+	if (dwarf_attr_integrate(vr_die, DW_AT_type, &attr) &&
+	    dwarf_formref_die(&attr, die_mem))
+		return die_mem;
+	else
+		return NULL;
+}
+
+/* Get a type die, but skip qualifiers */
+static Dwarf_Die *__die_get_real_type(Dwarf_Die *vr_die, Dwarf_Die *die_mem)
+{
+	int tag;
+
+	do {
+		vr_die = die_get_type(vr_die, die_mem);
+		if (!vr_die)
+			break;
+		tag = dwarf_tag(vr_die);
+	} while (tag == DW_TAG_const_type ||
+		 tag == DW_TAG_restrict_type ||
+		 tag == DW_TAG_volatile_type ||
+		 tag == DW_TAG_shared_type);
+
+	return vr_die;
+}
+
+/**
+ * die_get_real_type - Get a type die, but skip qualifiers and typedef
+ * @vr_die: a DIE of a variable
+ * @die_mem: where to store a type DIE
+ *
+ * Get a DIE of the type of given variable (@vr_die), and store
+ * it to die_mem. Return NULL if fails to get a type DIE.
+ * If the type is qualifiers (e.g. const) or typedef, this skips it
+ * and tries to find real type (structure or basic types, e.g. int).
+ */
+Dwarf_Die *die_get_real_type(Dwarf_Die *vr_die, Dwarf_Die *die_mem)
+{
+	do {
+		vr_die = __die_get_real_type(vr_die, die_mem);
+	} while (vr_die && dwarf_tag(vr_die) == DW_TAG_typedef);
+
+	return vr_die;
+}
+
+/* Get attribute and translate it as a udata */
+static int die_get_attr_udata(Dwarf_Die *tp_die, unsigned int attr_name,
+			      Dwarf_Word *result)
+{
+	Dwarf_Attribute attr;
+
+	if (dwarf_attr(tp_die, attr_name, &attr) == NULL ||
+	    dwarf_formudata(&attr, result) != 0)
+		return -ENOENT;
+
+	return 0;
+}
+
+/* Get attribute and translate it as a sdata */
+static int die_get_attr_sdata(Dwarf_Die *tp_die, unsigned int attr_name,
+			      Dwarf_Sword *result)
+{
+	Dwarf_Attribute attr;
+
+	if (dwarf_attr(tp_die, attr_name, &attr) == NULL ||
+	    dwarf_formsdata(&attr, result) != 0)
+		return -ENOENT;
+
+	return 0;
+}
+
+/**
+ * die_is_signed_type - Check whether a type DIE is signed or not
+ * @tp_die: a DIE of a type
+ *
+ * Get the encoding of @tp_die and return true if the encoding
+ * is signed.
+ */
+bool die_is_signed_type(Dwarf_Die *tp_die)
+{
+	Dwarf_Word ret;
+
+	if (die_get_attr_udata(tp_die, DW_AT_encoding, &ret))
+		return false;
+
+	return (ret == DW_ATE_signed_char || ret == DW_ATE_signed ||
+		ret == DW_ATE_signed_fixed);
+}
+
+/**
+ * die_is_func_def - Ensure that this DIE is a subprogram and definition
+ * @dw_die: a DIE
+ *
+ * Ensure that this DIE is a subprogram and NOT a declaration. This
+ * returns true if @dw_die is a function definition.
+ **/
+bool die_is_func_def(Dwarf_Die *dw_die)
+{
+	Dwarf_Attribute attr;
+
+	return (dwarf_tag(dw_die) == DW_TAG_subprogram &&
+		dwarf_attr(dw_die, DW_AT_declaration, &attr) == NULL);
+}
+
+/**
+ * die_get_data_member_location - Get the data-member offset
+ * @mb_die: a DIE of a member of a data structure
+ * @offs: The offset of the member in the data structure
+ *
+ * Get the offset of @mb_die in the data structure including @mb_die, and
+ * stores result offset to @offs. If any error occurs this returns errno.
+ */
+int die_get_data_member_location(Dwarf_Die *mb_die, Dwarf_Word *offs)
+{
+	Dwarf_Attribute attr;
+	Dwarf_Op *expr;
+	size_t nexpr;
+	int ret;
+
+	if (dwarf_attr(mb_die, DW_AT_data_member_location, &attr) == NULL)
+		return -ENOENT;
+
+	if (dwarf_formudata(&attr, offs) != 0) {
+		/* DW_AT_data_member_location should be DW_OP_plus_uconst */
+		ret = dwarf_getlocation(&attr, &expr, &nexpr);
+		if (ret < 0 || nexpr == 0)
+			return -ENOENT;
+
+		if (expr[0].atom != DW_OP_plus_uconst || nexpr != 1) {
+			pr_debug("Unable to get offset:Unexpected OP %x (%zd)\n",
+				 expr[0].atom, nexpr);
+			return -ENOTSUP;
+		}
+		*offs = (Dwarf_Word)expr[0].number;
+	}
+	return 0;
+}
+
+/* Get the call file index number in CU DIE */
+static int die_get_call_fileno(Dwarf_Die *in_die)
+{
+	Dwarf_Sword idx;
+
+	if (die_get_attr_sdata(in_die, DW_AT_call_file, &idx) == 0)
+		return (int)idx;
+	else
+		return -ENOENT;
+}
+
+/* Get the declared file index number in CU DIE */
+static int die_get_decl_fileno(Dwarf_Die *pdie)
+{
+	Dwarf_Sword idx;
+
+	if (die_get_attr_sdata(pdie, DW_AT_decl_file, &idx) == 0)
+		return (int)idx;
+	else
+		return -ENOENT;
+}
+
+/**
+ * die_get_call_file - Get callsite file name of inlined function instance
+ * @in_die: a DIE of an inlined function instance
+ *
+ * Get call-site file name of @in_die. This means from which file the inline
+ * function is called.
+ */
+const char *die_get_call_file(Dwarf_Die *in_die)
+{
+	Dwarf_Die cu_die;
+	Dwarf_Files *files;
+	int idx;
+
+	idx = die_get_call_fileno(in_die);
+	if (idx < 0 || !dwarf_diecu(in_die, &cu_die, NULL, NULL) ||
+	    dwarf_getsrcfiles(&cu_die, &files, NULL) != 0)
+		return NULL;
+
+	return dwarf_filesrc(files, idx, NULL, NULL);
+}
+
+
+/**
+ * die_find_child - Generic DIE search function in DIE tree
+ * @rt_die: a root DIE
+ * @callback: a callback function
+ * @data: a user data passed to the callback function
+ * @die_mem: a buffer for result DIE
+ *
+ * Trace DIE tree from @rt_die and call @callback for each child DIE.
+ * If @callback returns DIE_FIND_CB_END, this stores the DIE into
+ * @die_mem and returns it. If @callback returns DIE_FIND_CB_CONTINUE,
+ * this continues to trace the tree. Optionally, @callback can return
+ * DIE_FIND_CB_CHILD and DIE_FIND_CB_SIBLING, those means trace only
+ * the children and trace only the siblings respectively.
+ * Returns NULL if @callback can't find any appropriate DIE.
+ */
+Dwarf_Die *die_find_child(Dwarf_Die *rt_die,
+			  int (*callback)(Dwarf_Die *, void *),
+			  void *data, Dwarf_Die *die_mem)
+{
+	Dwarf_Die child_die;
+	int ret;
+
+	ret = dwarf_child(rt_die, die_mem);
+	if (ret != 0)
+		return NULL;
+
+	do {
+		ret = callback(die_mem, data);
+		if (ret == DIE_FIND_CB_END)
+			return die_mem;
+
+		if ((ret & DIE_FIND_CB_CHILD) &&
+		    die_find_child(die_mem, callback, data, &child_die)) {
+			memcpy(die_mem, &child_die, sizeof(Dwarf_Die));
+			return die_mem;
+		}
+	} while ((ret & DIE_FIND_CB_SIBLING) &&
+		 dwarf_siblingof(die_mem, die_mem) == 0);
+
+	return NULL;
+}
+
+struct __addr_die_search_param {
+	Dwarf_Addr	addr;
+	Dwarf_Die	*die_mem;
+};
+
+/* die_find callback for non-inlined function search */
+static int __die_search_func_cb(Dwarf_Die *fn_die, void *data)
+{
+	struct __addr_die_search_param *ad = data;
+
+	/*
+	 * Since a declaration entry doesn't has given pc, this always returns
+	 * function definition entry.
+	 */
+	if (dwarf_tag(fn_die) == DW_TAG_subprogram &&
+	    dwarf_haspc(fn_die, ad->addr)) {
+		memcpy(ad->die_mem, fn_die, sizeof(Dwarf_Die));
+		return DWARF_CB_ABORT;
+	}
+	return DWARF_CB_OK;
+}
+
+/**
+ * die_find_realfunc - Search a non-inlined function at given address
+ * @cu_die: a CU DIE which including @addr
+ * @addr: target address
+ * @die_mem: a buffer for result DIE
+ *
+ * Search a non-inlined function DIE which includes @addr. Stores the
+ * DIE to @die_mem and returns it if found. Returns NULL if failed.
+ */
+Dwarf_Die *die_find_realfunc(Dwarf_Die *cu_die, Dwarf_Addr addr,
+				    Dwarf_Die *die_mem)
+{
+	struct __addr_die_search_param ad;
+	ad.addr = addr;
+	ad.die_mem = die_mem;
+	/* dwarf_getscopes can't find subprogram. */
+	if (!dwarf_getfuncs(cu_die, __die_search_func_cb, &ad, 0))
+		return NULL;
+	else
+		return die_mem;
+}
+
+/* die_find callback for inline function search */
+static int __die_find_inline_cb(Dwarf_Die *die_mem, void *data)
+{
+	Dwarf_Addr *addr = data;
+
+	if (dwarf_tag(die_mem) == DW_TAG_inlined_subroutine &&
+	    dwarf_haspc(die_mem, *addr))
+		return DIE_FIND_CB_END;
+
+	return DIE_FIND_CB_CONTINUE;
+}
+
+/**
+ * die_find_top_inlinefunc - Search the top inlined function at given address
+ * @sp_die: a subprogram DIE which including @addr
+ * @addr: target address
+ * @die_mem: a buffer for result DIE
+ *
+ * Search an inlined function DIE which includes @addr. Stores the
+ * DIE to @die_mem and returns it if found. Returns NULL if failed.
+ * Even if several inlined functions are expanded recursively, this
+ * doesn't trace it down, and returns the topmost one.
+ */
+Dwarf_Die *die_find_top_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
+				   Dwarf_Die *die_mem)
+{
+	return die_find_child(sp_die, __die_find_inline_cb, &addr, die_mem);
+}
+
+/**
+ * die_find_inlinefunc - Search an inlined function at given address
+ * @sp_die: a subprogram DIE which including @addr
+ * @addr: target address
+ * @die_mem: a buffer for result DIE
+ *
+ * Search an inlined function DIE which includes @addr. Stores the
+ * DIE to @die_mem and returns it if found. Returns NULL if failed.
+ * If several inlined functions are expanded recursively, this trace
+ * it down and returns deepest one.
+ */
+Dwarf_Die *die_find_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
+			       Dwarf_Die *die_mem)
+{
+	Dwarf_Die tmp_die;
+
+	sp_die = die_find_child(sp_die, __die_find_inline_cb, &addr, &tmp_die);
+	if (!sp_die)
+		return NULL;
+
+	/* Inlined function could be recursive. Trace it until fail */
+	while (sp_die) {
+		memcpy(die_mem, sp_die, sizeof(Dwarf_Die));
+		sp_die = die_find_child(sp_die, __die_find_inline_cb, &addr,
+					&tmp_die);
+	}
+
+	return die_mem;
+}
+
+struct __instance_walk_param {
+	void    *addr;
+	int	(*callback)(Dwarf_Die *, void *);
+	void    *data;
+	int	retval;
+};
+
+static int __die_walk_instances_cb(Dwarf_Die *inst, void *data)
+{
+	struct __instance_walk_param *iwp = data;
+	Dwarf_Attribute attr_mem;
+	Dwarf_Die origin_mem;
+	Dwarf_Attribute *attr;
+	Dwarf_Die *origin;
+	int tmp;
+
+	attr = dwarf_attr(inst, DW_AT_abstract_origin, &attr_mem);
+	if (attr == NULL)
+		return DIE_FIND_CB_CONTINUE;
+
+	origin = dwarf_formref_die(attr, &origin_mem);
+	if (origin == NULL || origin->addr != iwp->addr)
+		return DIE_FIND_CB_CONTINUE;
+
+	/* Ignore redundant instances */
+	if (dwarf_tag(inst) == DW_TAG_inlined_subroutine) {
+		dwarf_decl_line(origin, &tmp);
+		if (die_get_call_lineno(inst) == tmp) {
+			tmp = die_get_decl_fileno(origin);
+			if (die_get_call_fileno(inst) == tmp)
+				return DIE_FIND_CB_CONTINUE;
+		}
+	}
+
+	iwp->retval = iwp->callback(inst, iwp->data);
+
+	return (iwp->retval) ? DIE_FIND_CB_END : DIE_FIND_CB_CONTINUE;
+}
+
+/**
+ * die_walk_instances - Walk on instances of given DIE
+ * @or_die: an abstract original DIE
+ * @callback: a callback function which is called with instance DIE
+ * @data: user data
+ *
+ * Walk on the instances of give @in_die. @in_die must be an inlined function
+ * declartion. This returns the return value of @callback if it returns
+ * non-zero value, or -ENOENT if there is no instance.
+ */
+int die_walk_instances(Dwarf_Die *or_die, int (*callback)(Dwarf_Die *, void *),
+		       void *data)
+{
+	Dwarf_Die cu_die;
+	Dwarf_Die die_mem;
+	struct __instance_walk_param iwp = {
+		.addr = or_die->addr,
+		.callback = callback,
+		.data = data,
+		.retval = -ENOENT,
+	};
+
+	if (dwarf_diecu(or_die, &cu_die, NULL, NULL) == NULL)
+		return -ENOENT;
+
+	die_find_child(&cu_die, __die_walk_instances_cb, &iwp, &die_mem);
+
+	return iwp.retval;
+}
+
+/* Line walker internal parameters */
+struct __line_walk_param {
+	bool recursive;
+	line_walk_callback_t callback;
+	void *data;
+	int retval;
+};
+
+static int __die_walk_funclines_cb(Dwarf_Die *in_die, void *data)
+{
+	struct __line_walk_param *lw = data;
+	Dwarf_Addr addr = 0;
+	const char *fname;
+	int lineno;
+
+	if (dwarf_tag(in_die) == DW_TAG_inlined_subroutine) {
+		fname = die_get_call_file(in_die);
+		lineno = die_get_call_lineno(in_die);
+		if (fname && lineno > 0 && dwarf_entrypc(in_die, &addr) == 0) {
+			lw->retval = lw->callback(fname, lineno, addr, lw->data);
+			if (lw->retval != 0)
+				return DIE_FIND_CB_END;
+		}
+	}
+	if (!lw->recursive)
+		/* Don't need to search recursively */
+		return DIE_FIND_CB_SIBLING;
+
+	if (addr) {
+		fname = dwarf_decl_file(in_die);
+		if (fname && dwarf_decl_line(in_die, &lineno) == 0) {
+			lw->retval = lw->callback(fname, lineno, addr, lw->data);
+			if (lw->retval != 0)
+				return DIE_FIND_CB_END;
+		}
+	}
+
+	/* Continue to search nested inlined function call-sites */
+	return DIE_FIND_CB_CONTINUE;
+}
+
+/* Walk on lines of blocks included in given DIE */
+static int __die_walk_funclines(Dwarf_Die *sp_die, bool recursive,
+				line_walk_callback_t callback, void *data)
+{
+	struct __line_walk_param lw = {
+		.recursive = recursive,
+		.callback = callback,
+		.data = data,
+		.retval = 0,
+	};
+	Dwarf_Die die_mem;
+	Dwarf_Addr addr;
+	const char *fname;
+	int lineno;
+
+	/* Handle function declaration line */
+	fname = dwarf_decl_file(sp_die);
+	if (fname && dwarf_decl_line(sp_die, &lineno) == 0 &&
+	    dwarf_entrypc(sp_die, &addr) == 0) {
+		lw.retval = callback(fname, lineno, addr, data);
+		if (lw.retval != 0)
+			goto done;
+	}
+	die_find_child(sp_die, __die_walk_funclines_cb, &lw, &die_mem);
+done:
+	return lw.retval;
+}
+
+static int __die_walk_culines_cb(Dwarf_Die *sp_die, void *data)
+{
+	struct __line_walk_param *lw = data;
+
+	lw->retval = __die_walk_funclines(sp_die, true, lw->callback, lw->data);
+	if (lw->retval != 0)
+		return DWARF_CB_ABORT;
+
+	return DWARF_CB_OK;
+}
+
+/**
+ * die_walk_lines - Walk on lines inside given DIE
+ * @rt_die: a root DIE (CU, subprogram or inlined_subroutine)
+ * @callback: callback routine
+ * @data: user data
+ *
+ * Walk on all lines inside given @rt_die and call @callback on each line.
+ * If the @rt_die is a function, walk only on the lines inside the function,
+ * otherwise @rt_die must be a CU DIE.
+ * Note that this walks not only dwarf line list, but also function entries
+ * and inline call-site.
+ */
+int die_walk_lines(Dwarf_Die *rt_die, line_walk_callback_t callback, void *data)
+{
+	Dwarf_Lines *lines;
+	Dwarf_Line *line;
+	Dwarf_Addr addr;
+	const char *fname;
+	int lineno, ret = 0;
+	Dwarf_Die die_mem, *cu_die;
+	size_t nlines, i;
+
+	/* Get the CU die */
+	if (dwarf_tag(rt_die) != DW_TAG_compile_unit)
+		cu_die = dwarf_diecu(rt_die, &die_mem, NULL, NULL);
+	else
+		cu_die = rt_die;
+	if (!cu_die) {
+		pr_debug2("Failed to get CU from given DIE.\n");
+		return -EINVAL;
+	}
+
+	/* Get lines list in the CU */
+	if (dwarf_getsrclines(cu_die, &lines, &nlines) != 0) {
+		pr_debug2("Failed to get source lines on this CU.\n");
+		return -ENOENT;
+	}
+	pr_debug2("Get %zd lines from this CU\n", nlines);
+
+	/* Walk on the lines on lines list */
+	for (i = 0; i < nlines; i++) {
+		line = dwarf_onesrcline(lines, i);
+		if (line == NULL ||
+		    dwarf_lineno(line, &lineno) != 0 ||
+		    dwarf_lineaddr(line, &addr) != 0) {
+			pr_debug2("Failed to get line info. "
+				  "Possible error in debuginfo.\n");
+			continue;
+		}
+		/* Filter lines based on address */
+		if (rt_die != cu_die)
+			/*
+			 * Address filtering
+			 * The line is included in given function, and
+			 * no inline block includes it.
+			 */
+			if (!dwarf_haspc(rt_die, addr) ||
+			    die_find_inlinefunc(rt_die, addr, &die_mem))
+				continue;
+		/* Get source line */
+		fname = dwarf_linesrc(line, NULL, NULL);
+
+		ret = callback(fname, lineno, addr, data);
+		if (ret != 0)
+			return ret;
+	}
+
+	/*
+	 * Dwarf lines doesn't include function declarations and inlined
+	 * subroutines. We have to check functions list or given function.
+	 */
+	if (rt_die != cu_die)
+		/*
+		 * Don't need walk functions recursively, because nested
+		 * inlined functions don't have lines of the specified DIE.
+		 */
+		ret = __die_walk_funclines(rt_die, false, callback, data);
+	else {
+		struct __line_walk_param param = {
+			.callback = callback,
+			.data = data,
+			.retval = 0,
+		};
+		dwarf_getfuncs(cu_die, __die_walk_culines_cb, &param, 0);
+		ret = param.retval;
+	}
+
+	return ret;
+}
+
+struct __find_variable_param {
+	const char *name;
+	Dwarf_Addr addr;
+};
+
+static int __die_find_variable_cb(Dwarf_Die *die_mem, void *data)
+{
+	struct __find_variable_param *fvp = data;
+	Dwarf_Attribute attr;
+	int tag;
+
+	tag = dwarf_tag(die_mem);
+	if ((tag == DW_TAG_formal_parameter ||
+	     tag == DW_TAG_variable) &&
+	    die_compare_name(die_mem, fvp->name) &&
+	/* Does the DIE have location information or external instance? */
+	    (dwarf_attr(die_mem, DW_AT_external, &attr) ||
+	     dwarf_attr(die_mem, DW_AT_location, &attr)))
+		return DIE_FIND_CB_END;
+	if (dwarf_haspc(die_mem, fvp->addr))
+		return DIE_FIND_CB_CONTINUE;
+	else
+		return DIE_FIND_CB_SIBLING;
+}
+
+/**
+ * die_find_variable_at - Find a given name variable at given address
+ * @sp_die: a function DIE
+ * @name: variable name
+ * @addr: address
+ * @die_mem: a buffer for result DIE
+ *
+ * Find a variable DIE called @name at @addr in @sp_die.
+ */
+Dwarf_Die *die_find_variable_at(Dwarf_Die *sp_die, const char *name,
+				Dwarf_Addr addr, Dwarf_Die *die_mem)
+{
+	struct __find_variable_param fvp = { .name = name, .addr = addr};
+
+	return die_find_child(sp_die, __die_find_variable_cb, (void *)&fvp,
+			      die_mem);
+}
+
+static int __die_find_member_cb(Dwarf_Die *die_mem, void *data)
+{
+	const char *name = data;
+
+	if ((dwarf_tag(die_mem) == DW_TAG_member) &&
+	    die_compare_name(die_mem, name))
+		return DIE_FIND_CB_END;
+
+	return DIE_FIND_CB_SIBLING;
+}
+
+/**
+ * die_find_member - Find a given name member in a data structure
+ * @st_die: a data structure type DIE
+ * @name: member name
+ * @die_mem: a buffer for result DIE
+ *
+ * Find a member DIE called @name in @st_die.
+ */
+Dwarf_Die *die_find_member(Dwarf_Die *st_die, const char *name,
+			   Dwarf_Die *die_mem)
+{
+	return die_find_child(st_die, __die_find_member_cb, (void *)name,
+			      die_mem);
+}
+
+/**
+ * die_get_typename - Get the name of given variable DIE
+ * @vr_die: a variable DIE
+ * @buf: a buffer for result type name
+ * @len: a max-length of @buf
+ *
+ * Get the name of @vr_die and stores it to @buf. Return the actual length
+ * of type name if succeeded. Return -E2BIG if @len is not enough long, and
+ * Return -ENOENT if failed to find type name.
+ * Note that the result will stores typedef name if possible, and stores
+ * "*(function_type)" if the type is a function pointer.
+ */
+int die_get_typename(Dwarf_Die *vr_die, char *buf, int len)
+{
+	Dwarf_Die type;
+	int tag, ret, ret2;
+	const char *tmp = "";
+
+	if (__die_get_real_type(vr_die, &type) == NULL)
+		return -ENOENT;
+
+	tag = dwarf_tag(&type);
+	if (tag == DW_TAG_array_type || tag == DW_TAG_pointer_type)
+		tmp = "*";
+	else if (tag == DW_TAG_subroutine_type) {
+		/* Function pointer */
+		ret = snprintf(buf, len, "(function_type)");
+		return (ret >= len) ? -E2BIG : ret;
+	} else {
+		if (!dwarf_diename(&type))
+			return -ENOENT;
+		if (tag == DW_TAG_union_type)
+			tmp = "union ";
+		else if (tag == DW_TAG_structure_type)
+			tmp = "struct ";
+		else if (tag == DW_TAG_enumeration_type)
+			tmp = "enum ";
+		/* Write a base name */
+		ret = snprintf(buf, len, "%s%s", tmp, dwarf_diename(&type));
+		return (ret >= len) ? -E2BIG : ret;
+	}
+	ret = die_get_typename(&type, buf, len);
+	if (ret > 0) {
+		ret2 = snprintf(buf + ret, len - ret, "%s", tmp);
+		ret = (ret2 >= len - ret) ? -E2BIG : ret2 + ret;
+	}
+	return ret;
+}
+
+/**
+ * die_get_varname - Get the name and type of given variable DIE
+ * @vr_die: a variable DIE
+ * @buf: a buffer for type and variable name
+ * @len: the max-length of @buf
+ *
+ * Get the name and type of @vr_die and stores it in @buf as "type\tname".
+ */
+int die_get_varname(Dwarf_Die *vr_die, char *buf, int len)
+{
+	int ret, ret2;
+
+	ret = die_get_typename(vr_die, buf, len);
+	if (ret < 0) {
+		pr_debug("Failed to get type, make it unknown.\n");
+		ret = snprintf(buf, len, "(unknown_type)");
+	}
+	if (ret > 0) {
+		ret2 = snprintf(buf + ret, len - ret, "\t%s",
+				dwarf_diename(vr_die));
+		ret = (ret2 >= len - ret) ? -E2BIG : ret2 + ret;
+	}
+	return ret;
+}
+
diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h
new file mode 100644
index 00000000000..b4fe90c6cb2
--- /dev/null
+++ b/tools/perf/util/dwarf-aux.h
@@ -0,0 +1,118 @@
+#ifndef _DWARF_AUX_H
+#define _DWARF_AUX_H
+/*
+ * dwarf-aux.h : libdw auxiliary interfaces
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ */
+
+#include <dwarf.h>
+#include <elfutils/libdw.h>
+#include <elfutils/libdwfl.h>
+#include <elfutils/version.h>
+
+/* Find the realpath of the target file */
+extern const char *cu_find_realpath(Dwarf_Die *cu_die, const char *fname);
+
+/* Get DW_AT_comp_dir (should be NULL with older gcc) */
+extern const char *cu_get_comp_dir(Dwarf_Die *cu_die);
+
+/* Get a line number and file name for given address */
+extern int cu_find_lineinfo(Dwarf_Die *cudie, unsigned long addr,
+			    const char **fname, int *lineno);
+
+/* Walk on funcitons at given address */
+extern int cu_walk_functions_at(Dwarf_Die *cu_die, Dwarf_Addr addr,
+			int (*callback)(Dwarf_Die *, void *), void *data);
+
+/* Ensure that this DIE is a subprogram and definition (not declaration) */
+extern bool die_is_func_def(Dwarf_Die *dw_die);
+
+/* Compare diename and tname */
+extern bool die_compare_name(Dwarf_Die *dw_die, const char *tname);
+
+/* Get callsite line number of inline-function instance */
+extern int die_get_call_lineno(Dwarf_Die *in_die);
+
+/* Get callsite file name of inlined function instance */
+extern const char *die_get_call_file(Dwarf_Die *in_die);
+
+/* Get type die */
+extern Dwarf_Die *die_get_type(Dwarf_Die *vr_die, Dwarf_Die *die_mem);
+
+/* Get a type die, but skip qualifiers and typedef */
+extern Dwarf_Die *die_get_real_type(Dwarf_Die *vr_die, Dwarf_Die *die_mem);
+
+/* Check whether the DIE is signed or not */
+extern bool die_is_signed_type(Dwarf_Die *tp_die);
+
+/* Get data_member_location offset */
+extern int die_get_data_member_location(Dwarf_Die *mb_die, Dwarf_Word *offs);
+
+/* Return values for die_find_child() callbacks */
+enum {
+	DIE_FIND_CB_END = 0,		/* End of Search */
+	DIE_FIND_CB_CHILD = 1,		/* Search only children */
+	DIE_FIND_CB_SIBLING = 2,	/* Search only siblings */
+	DIE_FIND_CB_CONTINUE = 3,	/* Search children and siblings */
+};
+
+/* Search child DIEs */
+extern Dwarf_Die *die_find_child(Dwarf_Die *rt_die,
+				 int (*callback)(Dwarf_Die *, void *),
+				 void *data, Dwarf_Die *die_mem);
+
+/* Search a non-inlined function including given address */
+extern Dwarf_Die *die_find_realfunc(Dwarf_Die *cu_die, Dwarf_Addr addr,
+				    Dwarf_Die *die_mem);
+
+/* Search the top inlined function including given address */
+extern Dwarf_Die *die_find_top_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
+					  Dwarf_Die *die_mem);
+
+/* Search the deepest inlined function including given address */
+extern Dwarf_Die *die_find_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
+				      Dwarf_Die *die_mem);
+
+/* Walk on the instances of given DIE */
+extern int die_walk_instances(Dwarf_Die *in_die,
+			      int (*callback)(Dwarf_Die *, void *), void *data);
+
+/* Walker on lines (Note: line number will not be sorted) */
+typedef int (* line_walk_callback_t) (const char *fname, int lineno,
+				      Dwarf_Addr addr, void *data);
+
+/*
+ * Walk on lines inside given DIE. If the DIE is a subprogram, walk only on
+ * the lines inside the subprogram, otherwise the DIE must be a CU DIE.
+ */
+extern int die_walk_lines(Dwarf_Die *rt_die, line_walk_callback_t callback,
+			  void *data);
+
+/* Find a variable called 'name' at given address */
+extern Dwarf_Die *die_find_variable_at(Dwarf_Die *sp_die, const char *name,
+				       Dwarf_Addr addr, Dwarf_Die *die_mem);
+
+/* Find a member called 'name' */
+extern Dwarf_Die *die_find_member(Dwarf_Die *st_die, const char *name,
+				  Dwarf_Die *die_mem);
+
+/* Get the name of given variable DIE */
+extern int die_get_typename(Dwarf_Die *vr_die, char *buf, int len);
+
+/* Get the name and type of given variable DIE, stored as "type\tname" */
+extern int die_get_varname(Dwarf_Die *vr_die, char *buf, int len);
+#endif
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 2fbf6a463c8..d0281bdfa58 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -1,119 +1,174 @@
 #include <linux/types.h>
+#include <sys/mman.h>
 #include "event.h"
 #include "debug.h"
-#include "session.h"
+#include "hist.h"
+#include "machine.h"
 #include "sort.h"
 #include "string.h"
 #include "strlist.h"
 #include "thread.h"
+#include "thread_map.h"
+#include "symbol/kallsyms.h"
+
+static const char *perf_event__names[] = {
+	[0]					= "TOTAL",
+	[PERF_RECORD_MMAP]			= "MMAP",
+	[PERF_RECORD_MMAP2]			= "MMAP2",
+	[PERF_RECORD_LOST]			= "LOST",
+	[PERF_RECORD_COMM]			= "COMM",
+	[PERF_RECORD_EXIT]			= "EXIT",
+	[PERF_RECORD_THROTTLE]			= "THROTTLE",
+	[PERF_RECORD_UNTHROTTLE]		= "UNTHROTTLE",
+	[PERF_RECORD_FORK]			= "FORK",
+	[PERF_RECORD_READ]			= "READ",
+	[PERF_RECORD_SAMPLE]			= "SAMPLE",
+	[PERF_RECORD_HEADER_ATTR]		= "ATTR",
+	[PERF_RECORD_HEADER_EVENT_TYPE]		= "EVENT_TYPE",
+	[PERF_RECORD_HEADER_TRACING_DATA]	= "TRACING_DATA",
+	[PERF_RECORD_HEADER_BUILD_ID]		= "BUILD_ID",
+	[PERF_RECORD_FINISHED_ROUND]		= "FINISHED_ROUND",
+};
+
+const char *perf_event__name(unsigned int id)
+{
+	if (id >= ARRAY_SIZE(perf_event__names))
+		return "INVALID";
+	if (!perf_event__names[id])
+		return "UNKNOWN";
+	return perf_event__names[id];
+}
 
-const char *event__name[] = {
-	[0]			 = "TOTAL",
-	[PERF_RECORD_MMAP]	 = "MMAP",
-	[PERF_RECORD_LOST]	 = "LOST",
-	[PERF_RECORD_COMM]	 = "COMM",
-	[PERF_RECORD_EXIT]	 = "EXIT",
-	[PERF_RECORD_THROTTLE]	 = "THROTTLE",
-	[PERF_RECORD_UNTHROTTLE] = "UNTHROTTLE",
-	[PERF_RECORD_FORK]	 = "FORK",
-	[PERF_RECORD_READ]	 = "READ",
-	[PERF_RECORD_SAMPLE]	 = "SAMPLE",
-	[PERF_RECORD_HEADER_ATTR]	 = "ATTR",
-	[PERF_RECORD_HEADER_EVENT_TYPE]	 = "EVENT_TYPE",
-	[PERF_RECORD_HEADER_TRACING_DATA]	 = "TRACING_DATA",
-	[PERF_RECORD_HEADER_BUILD_ID]	 = "BUILD_ID",
+static struct perf_sample synth_sample = {
+	.pid	   = -1,
+	.tid	   = -1,
+	.time	   = -1,
+	.stream_id = -1,
+	.cpu	   = -1,
+	.period	   = 1,
 };
 
-static pid_t event__synthesize_comm(pid_t pid, int full,
-				    event__handler_t process,
-				    struct perf_session *session)
+static pid_t perf_event__get_comm_tgid(pid_t pid, char *comm, size_t len)
 {
-	event_t ev;
 	char filename[PATH_MAX];
 	char bf[BUFSIZ];
 	FILE *fp;
 	size_t size = 0;
-	DIR *tasks;
-	struct dirent dirent, *next;
-	pid_t tgid = 0;
+	pid_t tgid = -1;
 
 	snprintf(filename, sizeof(filename), "/proc/%d/status", pid);
 
 	fp = fopen(filename, "r");
 	if (fp == NULL) {
-out_race:
-		/*
-		 * We raced with a task exiting - just return:
-		 */
 		pr_debug("couldn't open %s\n", filename);
 		return 0;
 	}
 
-	memset(&ev.comm, 0, sizeof(ev.comm));
-	while (!ev.comm.comm[0] || !ev.comm.pid) {
-		if (fgets(bf, sizeof(bf), fp) == NULL)
-			goto out_failure;
+	while (!comm[0] || (tgid < 0)) {
+		if (fgets(bf, sizeof(bf), fp) == NULL) {
+			pr_warning("couldn't get COMM and pgid, malformed %s\n",
+				   filename);
+			break;
+		}
 
 		if (memcmp(bf, "Name:", 5) == 0) {
 			char *name = bf + 5;
 			while (*name && isspace(*name))
 				++name;
 			size = strlen(name) - 1;
-			memcpy(ev.comm.comm, name, size++);
+			if (size >= len)
+				size = len - 1;
+			memcpy(comm, name, size);
+			comm[size] = '\0';
+
 		} else if (memcmp(bf, "Tgid:", 5) == 0) {
 			char *tgids = bf + 5;
 			while (*tgids && isspace(*tgids))
 				++tgids;
-			tgid = ev.comm.pid = atoi(tgids);
+			tgid = atoi(tgids);
 		}
 	}
 
-	ev.comm.header.type = PERF_RECORD_COMM;
-	size = ALIGN(size, sizeof(u64));
-	ev.comm.header.size = sizeof(ev.comm) - (sizeof(ev.comm.comm) - size);
+	fclose(fp);
 
-	if (!full) {
-		ev.comm.tid = pid;
+	return tgid;
+}
 
-		process(&ev, session);
-		goto out_fclose;
-	}
+static pid_t perf_event__synthesize_comm(struct perf_tool *tool,
+					 union perf_event *event, pid_t pid,
+					 perf_event__handler_t process,
+					 struct machine *machine)
+{
+	size_t size;
+	pid_t tgid;
 
-	snprintf(filename, sizeof(filename), "/proc/%d/task", pid);
+	memset(&event->comm, 0, sizeof(event->comm));
 
-	tasks = opendir(filename);
-	if (tasks == NULL)
-		goto out_race;
+	if (machine__is_host(machine))
+		tgid = perf_event__get_comm_tgid(pid, event->comm.comm,
+						 sizeof(event->comm.comm));
+	else
+		tgid = machine->pid;
 
-	while (!readdir_r(tasks, &dirent, &next) && next) {
-		char *end;
-		pid = strtol(dirent.d_name, &end, 10);
-		if (*end)
-			continue;
+	if (tgid < 0)
+		goto out;
 
-		ev.comm.tid = pid;
+	event->comm.pid = tgid;
+	event->comm.header.type = PERF_RECORD_COMM;
 
-		process(&ev, session);
-	}
-	closedir(tasks);
+	size = strlen(event->comm.comm) + 1;
+	size = PERF_ALIGN(size, sizeof(u64));
+	memset(event->comm.comm + size, 0, machine->id_hdr_size);
+	event->comm.header.size = (sizeof(event->comm) -
+				(sizeof(event->comm.comm) - size) +
+				machine->id_hdr_size);
+	event->comm.tid = pid;
 
-out_fclose:
-	fclose(fp);
+	if (process(tool, event, &synth_sample, machine) != 0)
+		return -1;
+
+out:
 	return tgid;
+}
+
+static int perf_event__synthesize_fork(struct perf_tool *tool,
+				       union perf_event *event, pid_t pid,
+				       pid_t tgid, perf_event__handler_t process,
+				       struct machine *machine)
+{
+	memset(&event->fork, 0, sizeof(event->fork) + machine->id_hdr_size);
+
+	/* this is really a clone event but we use fork to synthesize it */
+	event->fork.ppid = tgid;
+	event->fork.ptid = tgid;
+	event->fork.pid  = tgid;
+	event->fork.tid  = pid;
+	event->fork.header.type = PERF_RECORD_FORK;
 
-out_failure:
-	pr_warning("couldn't get COMM and pgid, malformed %s\n", filename);
-	return -1;
+	event->fork.header.size = (sizeof(event->fork) + machine->id_hdr_size);
+
+	if (process(tool, event, &synth_sample, machine) != 0)
+		return -1;
+
+	return 0;
 }
 
-static int event__synthesize_mmap_events(pid_t pid, pid_t tgid,
-					 event__handler_t process,
-					 struct perf_session *session)
+int perf_event__synthesize_mmap_events(struct perf_tool *tool,
+				       union perf_event *event,
+				       pid_t pid, pid_t tgid,
+				       perf_event__handler_t process,
+				       struct machine *machine,
+				       bool mmap_data)
 {
 	char filename[PATH_MAX];
 	FILE *fp;
+	int rc = 0;
 
-	snprintf(filename, sizeof(filename), "/proc/%d/maps", pid);
+	if (machine__is_default_guest(machine))
+		return 0;
+
+	snprintf(filename, sizeof(filename), "%s/proc/%d/maps",
+		 machine->root_dir, pid);
 
 	fp = fopen(filename, "r");
 	if (fp == NULL) {
@@ -124,129 +179,315 @@ static int event__synthesize_mmap_events(pid_t pid, pid_t tgid,
 		return -1;
 	}
 
+	event->header.type = PERF_RECORD_MMAP2;
+
 	while (1) {
-		char bf[BUFSIZ], *pbf = bf;
-		event_t ev = {
-			.header = {
-				.type = PERF_RECORD_MMAP,
-				/*
-				 * Just like the kernel, see __perf_event_mmap
-				 * in kernel/perf_event.c
-				 */
-				.misc = PERF_RECORD_MISC_USER,
-			 },
-		};
-		int n;
+		char bf[BUFSIZ];
+		char prot[5];
+		char execname[PATH_MAX];
+		char anonstr[] = "//anon";
+		unsigned int ino;
 		size_t size;
+		ssize_t n;
+
 		if (fgets(bf, sizeof(bf), fp) == NULL)
 			break;
 
+		/* ensure null termination since stack will be reused. */
+		strcpy(execname, "");
+
 		/* 00400000-0040c000 r-xp 00000000 fd:01 41038  /bin/cat */
-		n = hex2u64(pbf, &ev.mmap.start);
-		if (n < 0)
-			continue;
-		pbf += n + 1;
-		n = hex2u64(pbf, &ev.mmap.len);
-		if (n < 0)
+		n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %x:%x %u %s\n",
+		       &event->mmap2.start, &event->mmap2.len, prot,
+		       &event->mmap2.pgoff, &event->mmap2.maj,
+		       &event->mmap2.min,
+		       &ino, execname);
+
+		/*
+ 		 * Anon maps don't have the execname.
+ 		 */
+		if (n < 7)
 			continue;
-		pbf += n + 3;
-		if (*pbf == 'x') { /* vm_exec */
-			u64 vm_pgoff;
-			char *execname = strchr(bf, '/');
 
-			/* Catch VDSO */
-			if (execname == NULL)
-				execname = strstr(bf, "[vdso]");
+		event->mmap2.ino = (u64)ino;
+
+		/*
+		 * Just like the kernel, see __perf_event_mmap in kernel/perf_event.c
+		 */
+		if (machine__is_host(machine))
+			event->header.misc = PERF_RECORD_MISC_USER;
+		else
+			event->header.misc = PERF_RECORD_MISC_GUEST_USER;
+
+		/* map protection and flags bits */
+		event->mmap2.prot = 0;
+		event->mmap2.flags = 0;
+		if (prot[0] == 'r')
+			event->mmap2.prot |= PROT_READ;
+		if (prot[1] == 'w')
+			event->mmap2.prot |= PROT_WRITE;
+		if (prot[2] == 'x')
+			event->mmap2.prot |= PROT_EXEC;
+
+		if (prot[3] == 's')
+			event->mmap2.flags |= MAP_SHARED;
+		else
+			event->mmap2.flags |= MAP_PRIVATE;
 
-			if (execname == NULL)
+		if (prot[2] != 'x') {
+			if (!mmap_data || prot[0] != 'r')
 				continue;
 
-			pbf += 3;
-			n = hex2u64(pbf, &vm_pgoff);
-			/* pgoff is in bytes, not pages */
-			if (n >= 0)
-				ev.mmap.pgoff = vm_pgoff << getpagesize();
-			else
-				ev.mmap.pgoff = 0;
-
-			size = strlen(execname);
-			execname[size - 1] = '\0'; /* Remove \n */
-			memcpy(ev.mmap.filename, execname, size);
-			size = ALIGN(size, sizeof(u64));
-			ev.mmap.len -= ev.mmap.start;
-			ev.mmap.header.size = (sizeof(ev.mmap) -
-					       (sizeof(ev.mmap.filename) - size));
-			ev.mmap.pid = tgid;
-			ev.mmap.tid = pid;
-
-			process(&ev, session);
+			event->header.misc |= PERF_RECORD_MISC_MMAP_DATA;
+		}
+
+		if (!strcmp(execname, ""))
+			strcpy(execname, anonstr);
+
+		size = strlen(execname) + 1;
+		memcpy(event->mmap2.filename, execname, size);
+		size = PERF_ALIGN(size, sizeof(u64));
+		event->mmap2.len -= event->mmap.start;
+		event->mmap2.header.size = (sizeof(event->mmap2) -
+					(sizeof(event->mmap2.filename) - size));
+		memset(event->mmap2.filename + size, 0, machine->id_hdr_size);
+		event->mmap2.header.size += machine->id_hdr_size;
+		event->mmap2.pid = tgid;
+		event->mmap2.tid = pid;
+
+		if (process(tool, event, &synth_sample, machine) != 0) {
+			rc = -1;
+			break;
 		}
 	}
 
 	fclose(fp);
-	return 0;
+	return rc;
 }
 
-int event__synthesize_modules(event__handler_t process,
-			      struct perf_session *session,
-			      struct machine *machine)
+int perf_event__synthesize_modules(struct perf_tool *tool,
+				   perf_event__handler_t process,
+				   struct machine *machine)
 {
+	int rc = 0;
 	struct rb_node *nd;
 	struct map_groups *kmaps = &machine->kmaps;
-	u16 misc;
+	union perf_event *event = zalloc((sizeof(event->mmap) +
+					  machine->id_hdr_size));
+	if (event == NULL) {
+		pr_debug("Not enough memory synthesizing mmap event "
+			 "for kernel modules\n");
+		return -1;
+	}
+
+	event->header.type = PERF_RECORD_MMAP;
 
 	/*
 	 * kernel uses 0 for user space maps, see kernel/perf_event.c
 	 * __perf_event_mmap
 	 */
 	if (machine__is_host(machine))
-		misc = PERF_RECORD_MISC_KERNEL;
+		event->header.misc = PERF_RECORD_MISC_KERNEL;
 	else
-		misc = PERF_RECORD_MISC_GUEST_KERNEL;
+		event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
 
 	for (nd = rb_first(&kmaps->maps[MAP__FUNCTION]);
 	     nd; nd = rb_next(nd)) {
-		event_t ev;
 		size_t size;
 		struct map *pos = rb_entry(nd, struct map, rb_node);
 
 		if (pos->dso->kernel)
 			continue;
 
-		size = ALIGN(pos->dso->long_name_len + 1, sizeof(u64));
-		memset(&ev, 0, sizeof(ev));
-		ev.mmap.header.misc = misc;
-		ev.mmap.header.type = PERF_RECORD_MMAP;
-		ev.mmap.header.size = (sizeof(ev.mmap) -
-				        (sizeof(ev.mmap.filename) - size));
-		ev.mmap.start = pos->start;
-		ev.mmap.len   = pos->end - pos->start;
-		ev.mmap.pid   = machine->pid;
-
-		memcpy(ev.mmap.filename, pos->dso->long_name,
+		size = PERF_ALIGN(pos->dso->long_name_len + 1, sizeof(u64));
+		event->mmap.header.type = PERF_RECORD_MMAP;
+		event->mmap.header.size = (sizeof(event->mmap) -
+				        (sizeof(event->mmap.filename) - size));
+		memset(event->mmap.filename + size, 0, machine->id_hdr_size);
+		event->mmap.header.size += machine->id_hdr_size;
+		event->mmap.start = pos->start;
+		event->mmap.len   = pos->end - pos->start;
+		event->mmap.pid   = machine->pid;
+
+		memcpy(event->mmap.filename, pos->dso->long_name,
 		       pos->dso->long_name_len + 1);
-		process(&ev, session);
+		if (process(tool, event, &synth_sample, machine) != 0) {
+			rc = -1;
+			break;
+		}
 	}
 
+	free(event);
+	return rc;
+}
+
+static int __event__synthesize_thread(union perf_event *comm_event,
+				      union perf_event *mmap_event,
+				      union perf_event *fork_event,
+				      pid_t pid, int full,
+					  perf_event__handler_t process,
+				      struct perf_tool *tool,
+				      struct machine *machine, bool mmap_data)
+{
+	char filename[PATH_MAX];
+	DIR *tasks;
+	struct dirent dirent, *next;
+	pid_t tgid;
+
+	/* special case: only send one comm event using passed in pid */
+	if (!full) {
+		tgid = perf_event__synthesize_comm(tool, comm_event, pid,
+						   process, machine);
+
+		if (tgid == -1)
+			return -1;
+
+		return perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid,
+							  process, machine, mmap_data);
+	}
+
+	if (machine__is_default_guest(machine))
+		return 0;
+
+	snprintf(filename, sizeof(filename), "%s/proc/%d/task",
+		 machine->root_dir, pid);
+
+	tasks = opendir(filename);
+	if (tasks == NULL) {
+		pr_debug("couldn't open %s\n", filename);
+		return 0;
+	}
+
+	while (!readdir_r(tasks, &dirent, &next) && next) {
+		char *end;
+		int rc = 0;
+		pid_t _pid;
+
+		_pid = strtol(dirent.d_name, &end, 10);
+		if (*end)
+			continue;
+
+		tgid = perf_event__synthesize_comm(tool, comm_event, _pid,
+						   process, machine);
+		if (tgid == -1)
+			return -1;
+
+		if (_pid == pid) {
+			/* process the parent's maps too */
+			rc = perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid,
+						process, machine, mmap_data);
+		} else {
+			/* only fork the tid's map, to save time */
+			rc = perf_event__synthesize_fork(tool, fork_event, _pid, tgid,
+						 process, machine);
+		}
+
+		if (rc)
+			return rc;
+	}
+
+	closedir(tasks);
 	return 0;
 }
 
-int event__synthesize_thread(pid_t pid, event__handler_t process,
-			     struct perf_session *session)
+int perf_event__synthesize_thread_map(struct perf_tool *tool,
+				      struct thread_map *threads,
+				      perf_event__handler_t process,
+				      struct machine *machine,
+				      bool mmap_data)
 {
-	pid_t tgid = event__synthesize_comm(pid, 1, process, session);
-	if (tgid == -1)
-		return -1;
-	return event__synthesize_mmap_events(pid, tgid, process, session);
+	union perf_event *comm_event, *mmap_event, *fork_event;
+	int err = -1, thread, j;
+
+	comm_event = malloc(sizeof(comm_event->comm) + machine->id_hdr_size);
+	if (comm_event == NULL)
+		goto out;
+
+	mmap_event = malloc(sizeof(mmap_event->mmap) + machine->id_hdr_size);
+	if (mmap_event == NULL)
+		goto out_free_comm;
+
+	fork_event = malloc(sizeof(fork_event->fork) + machine->id_hdr_size);
+	if (fork_event == NULL)
+		goto out_free_mmap;
+
+	err = 0;
+	for (thread = 0; thread < threads->nr; ++thread) {
+		if (__event__synthesize_thread(comm_event, mmap_event,
+					       fork_event,
+					       threads->map[thread], 0,
+					       process, tool, machine,
+					       mmap_data)) {
+			err = -1;
+			break;
+		}
+
+		/*
+		 * comm.pid is set to thread group id by
+		 * perf_event__synthesize_comm
+		 */
+		if ((int) comm_event->comm.pid != threads->map[thread]) {
+			bool need_leader = true;
+
+			/* is thread group leader in thread_map? */
+			for (j = 0; j < threads->nr; ++j) {
+				if ((int) comm_event->comm.pid == threads->map[j]) {
+					need_leader = false;
+					break;
+				}
+			}
+
+			/* if not, generate events for it */
+			if (need_leader &&
+			    __event__synthesize_thread(comm_event, mmap_event,
+						       fork_event,
+						       comm_event->comm.pid, 0,
+						       process, tool, machine,
+						       mmap_data)) {
+				err = -1;
+				break;
+			}
+		}
+	}
+	free(fork_event);
+out_free_mmap:
+	free(mmap_event);
+out_free_comm:
+	free(comm_event);
+out:
+	return err;
 }
 
-void event__synthesize_threads(event__handler_t process,
-			       struct perf_session *session)
+int perf_event__synthesize_threads(struct perf_tool *tool,
+				   perf_event__handler_t process,
+				   struct machine *machine, bool mmap_data)
 {
 	DIR *proc;
+	char proc_path[PATH_MAX];
 	struct dirent dirent, *next;
+	union perf_event *comm_event, *mmap_event, *fork_event;
+	int err = -1;
+
+	if (machine__is_default_guest(machine))
+		return 0;
+
+	comm_event = malloc(sizeof(comm_event->comm) + machine->id_hdr_size);
+	if (comm_event == NULL)
+		goto out;
+
+	mmap_event = malloc(sizeof(mmap_event->mmap) + machine->id_hdr_size);
+	if (mmap_event == NULL)
+		goto out_free_comm;
+
+	fork_event = malloc(sizeof(fork_event->fork) + machine->id_hdr_size);
+	if (fork_event == NULL)
+		goto out_free_mmap;
+
+	snprintf(proc_path, sizeof(proc_path), "%s/proc", machine->root_dir);
+	proc = opendir(proc_path);
 
-	proc = opendir("/proc");
+	if (proc == NULL)
+		goto out_free_fork;
 
 	while (!readdir_r(proc, &dirent, &next) && next) {
 		char *end;
@@ -254,11 +495,24 @@ void event__synthesize_threads(event__handler_t process,
 
 		if (*end) /* only interested in proper numerical dirents */
 			continue;
-
-		event__synthesize_thread(pid, process, session);
+		/*
+ 		 * We may race with exiting thread, so don't stop just because
+ 		 * one thread couldn't be synthesized.
+ 		 */
+		__event__synthesize_thread(comm_event, mmap_event, fork_event, pid,
+					   1, process, tool, machine, mmap_data);
 	}
 
+	err = 0;
 	closedir(proc);
+out_free_fork:
+	free(fork_event);
+out_free_mmap:
+	free(mmap_event);
+out_free_comm:
+	free(comm_event);
+out:
+	return err;
 }
 
 struct process_symbol_args {
@@ -266,7 +520,8 @@ struct process_symbol_args {
 	u64	   start;
 };
 
-static int find_symbol_cb(void *arg, const char *name, char type, u64 start)
+static int find_symbol_cb(void *arg, const char *name, char type,
+			  u64 start)
 {
 	struct process_symbol_args *args = arg;
 
@@ -282,28 +537,39 @@ static int find_symbol_cb(void *arg, const char *name, char type, u64 start)
 	return 1;
 }
 
-int event__synthesize_kernel_mmap(event__handler_t process,
-				  struct perf_session *session,
-				  struct machine *machine,
-				  const char *symbol_name)
+u64 kallsyms__get_function_start(const char *kallsyms_filename,
+				 const char *symbol_name)
+{
+	struct process_symbol_args args = { .name = symbol_name, };
+
+	if (kallsyms__parse(kallsyms_filename, &args, find_symbol_cb) <= 0)
+		return 0;
+
+	return args.start;
+}
+
+int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
+				       perf_event__handler_t process,
+				       struct machine *machine)
 {
 	size_t size;
-	const char *filename, *mmap_name;
-	char path[PATH_MAX];
+	const char *mmap_name;
 	char name_buff[PATH_MAX];
 	struct map *map;
-
-	event_t ev = {
-		.header = {
-			.type = PERF_RECORD_MMAP,
-		},
-	};
+	struct kmap *kmap;
+	int err;
 	/*
 	 * We should get this from /sys/kernel/sections/.text, but till that is
 	 * available use this, and after it is use this as a fallback for older
 	 * kernels.
 	 */
-	struct process_symbol_args args = { .name = symbol_name, };
+	union perf_event *event = zalloc((sizeof(event->mmap) +
+					  machine->id_hdr_size));
+	if (event == NULL) {
+		pr_debug("Not enough memory synthesizing mmap event "
+			 "for kernel modules\n");
+		return -1;
+	}
 
 	mmap_name = machine__mmap_name(machine, name_buff, sizeof(name_buff));
 	if (machine__is_host(machine)) {
@@ -311,298 +577,191 @@ int event__synthesize_kernel_mmap(event__handler_t process,
 		 * kernel uses PERF_RECORD_MISC_USER for user space maps,
 		 * see kernel/perf_event.c __perf_event_mmap
 		 */
-		ev.header.misc = PERF_RECORD_MISC_KERNEL;
-		filename = "/proc/kallsyms";
+		event->header.misc = PERF_RECORD_MISC_KERNEL;
 	} else {
-		ev.header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
-		if (machine__is_default_guest(machine))
-			filename = (char *) symbol_conf.default_guest_kallsyms;
-		else {
-			sprintf(path, "%s/proc/kallsyms", machine->root_dir);
-			filename = path;
-		}
+		event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
 	}
 
-	if (kallsyms__parse(filename, &args, find_symbol_cb) <= 0)
-		return -ENOENT;
-
 	map = machine->vmlinux_maps[MAP__FUNCTION];
-	size = snprintf(ev.mmap.filename, sizeof(ev.mmap.filename),
-			"%s%s", mmap_name, symbol_name) + 1;
-	size = ALIGN(size, sizeof(u64));
-	ev.mmap.header.size = (sizeof(ev.mmap) -
-			(sizeof(ev.mmap.filename) - size));
-	ev.mmap.pgoff = args.start;
-	ev.mmap.start = map->start;
-	ev.mmap.len   = map->end - ev.mmap.start;
-	ev.mmap.pid   = machine->pid;
-
-	return process(&ev, session);
+	kmap = map__kmap(map);
+	size = snprintf(event->mmap.filename, sizeof(event->mmap.filename),
+			"%s%s", mmap_name, kmap->ref_reloc_sym->name) + 1;
+	size = PERF_ALIGN(size, sizeof(u64));
+	event->mmap.header.type = PERF_RECORD_MMAP;
+	event->mmap.header.size = (sizeof(event->mmap) -
+			(sizeof(event->mmap.filename) - size) + machine->id_hdr_size);
+	event->mmap.pgoff = kmap->ref_reloc_sym->addr;
+	event->mmap.start = map->start;
+	event->mmap.len   = map->end - event->mmap.start;
+	event->mmap.pid   = machine->pid;
+
+	err = process(tool, event, &synth_sample, machine);
+	free(event);
+
+	return err;
 }
 
-static void thread__comm_adjust(struct thread *self)
+size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp)
 {
-	char *comm = self->comm;
-
-	if (!symbol_conf.col_width_list_str && !symbol_conf.field_sep &&
-	    (!symbol_conf.comm_list ||
-	     strlist__has_entry(symbol_conf.comm_list, comm))) {
-		unsigned int slen = strlen(comm);
-
-		if (slen > comms__col_width) {
-			comms__col_width = slen;
-			threads__col_width = slen + 6;
-		}
-	}
+	return fprintf(fp, ": %s:%d\n", event->comm.comm, event->comm.tid);
 }
 
-static int thread__set_comm_adjust(struct thread *self, const char *comm)
+int perf_event__process_comm(struct perf_tool *tool __maybe_unused,
+			     union perf_event *event,
+			     struct perf_sample *sample,
+			     struct machine *machine)
 {
-	int ret = thread__set_comm(self, comm);
-
-	if (ret)
-		return ret;
-
-	thread__comm_adjust(self);
-
-	return 0;
+	return machine__process_comm_event(machine, event, sample);
 }
 
-int event__process_comm(event_t *self, struct perf_session *session)
+int perf_event__process_lost(struct perf_tool *tool __maybe_unused,
+			     union perf_event *event,
+			     struct perf_sample *sample,
+			     struct machine *machine)
 {
-	struct thread *thread = perf_session__findnew(session, self->comm.tid);
-
-	dump_printf(": %s:%d\n", self->comm.comm, self->comm.tid);
-
-	if (thread == NULL || thread__set_comm_adjust(thread, self->comm.comm)) {
-		dump_printf("problem processing PERF_RECORD_COMM, skipping event.\n");
-		return -1;
-	}
-
-	return 0;
+	return machine__process_lost_event(machine, event, sample);
 }
 
-int event__process_lost(event_t *self, struct perf_session *session)
+size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp)
 {
-	dump_printf(": id:%Ld: lost:%Ld\n", self->lost.id, self->lost.lost);
-	session->hists.stats.total_lost += self->lost.lost;
-	return 0;
+	return fprintf(fp, " %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64 "]: %c %s\n",
+		       event->mmap.pid, event->mmap.tid, event->mmap.start,
+		       event->mmap.len, event->mmap.pgoff,
+		       (event->header.misc & PERF_RECORD_MISC_MMAP_DATA) ? 'r' : 'x',
+		       event->mmap.filename);
 }
 
-static void event_set_kernel_mmap_len(struct map **maps, event_t *self)
+size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp)
 {
-	maps[MAP__FUNCTION]->start = self->mmap.start;
-	maps[MAP__FUNCTION]->end   = self->mmap.start + self->mmap.len;
-	/*
-	 * Be a bit paranoid here, some perf.data file came with
-	 * a zero sized synthesized MMAP event for the kernel.
-	 */
-	if (maps[MAP__FUNCTION]->end == 0)
-		maps[MAP__FUNCTION]->end = ~0UL;
+	return fprintf(fp, " %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64
+			   " %02x:%02x %"PRIu64" %"PRIu64"]: %c%c%c%c %s\n",
+		       event->mmap2.pid, event->mmap2.tid, event->mmap2.start,
+		       event->mmap2.len, event->mmap2.pgoff, event->mmap2.maj,
+		       event->mmap2.min, event->mmap2.ino,
+		       event->mmap2.ino_generation,
+		       (event->mmap2.prot & PROT_READ) ? 'r' : '-',
+		       (event->mmap2.prot & PROT_WRITE) ? 'w' : '-',
+		       (event->mmap2.prot & PROT_EXEC) ? 'x' : '-',
+		       (event->mmap2.flags & MAP_SHARED) ? 's' : 'p',
+		       event->mmap2.filename);
 }
 
-static int event__process_kernel_mmap(event_t *self,
-			struct perf_session *session)
+int perf_event__process_mmap(struct perf_tool *tool __maybe_unused,
+			     union perf_event *event,
+			     struct perf_sample *sample,
+			     struct machine *machine)
 {
-	struct map *map;
-	char kmmap_prefix[PATH_MAX];
-	struct machine *machine;
-	enum dso_kernel_type kernel_type;
-	bool is_kernel_mmap;
-
-	machine = perf_session__findnew_machine(session, self->mmap.pid);
-	if (!machine) {
-		pr_err("Can't find id %d's machine\n", self->mmap.pid);
-		goto out_problem;
-	}
-
-	machine__mmap_name(machine, kmmap_prefix, sizeof(kmmap_prefix));
-	if (machine__is_host(machine))
-		kernel_type = DSO_TYPE_KERNEL;
-	else
-		kernel_type = DSO_TYPE_GUEST_KERNEL;
-
-	is_kernel_mmap = memcmp(self->mmap.filename,
-				kmmap_prefix,
-				strlen(kmmap_prefix)) == 0;
-	if (self->mmap.filename[0] == '/' ||
-	    (!is_kernel_mmap && self->mmap.filename[0] == '[')) {
-
-		char short_module_name[1024];
-		char *name, *dot;
-
-		if (self->mmap.filename[0] == '/') {
-			name = strrchr(self->mmap.filename, '/');
-			if (name == NULL)
-				goto out_problem;
-
-			++name; /* skip / */
-			dot = strrchr(name, '.');
-			if (dot == NULL)
-				goto out_problem;
-			snprintf(short_module_name, sizeof(short_module_name),
-					"[%.*s]", (int)(dot - name), name);
-			strxfrchar(short_module_name, '-', '_');
-		} else
-			strcpy(short_module_name, self->mmap.filename);
-
-		map = machine__new_module(machine, self->mmap.start,
-					  self->mmap.filename);
-		if (map == NULL)
-			goto out_problem;
-
-		name = strdup(short_module_name);
-		if (name == NULL)
-			goto out_problem;
-
-		map->dso->short_name = name;
-		map->end = map->start + self->mmap.len;
-	} else if (is_kernel_mmap) {
-		const char *symbol_name = (self->mmap.filename +
-				strlen(kmmap_prefix));
-		/*
-		 * Should be there already, from the build-id table in
-		 * the header.
-		 */
-		struct dso *kernel = __dsos__findnew(&machine->kernel_dsos,
-						     kmmap_prefix);
-		if (kernel == NULL)
-			goto out_problem;
-
-		kernel->kernel = kernel_type;
-		if (__machine__create_kernel_maps(machine, kernel) < 0)
-			goto out_problem;
-
-		event_set_kernel_mmap_len(machine->vmlinux_maps, self);
-		perf_session__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps,
-							 symbol_name,
-							 self->mmap.pgoff);
-		if (machine__is_default_guest(machine)) {
-			/*
-			 * preload dso of guest kernel and modules
-			 */
-			dso__load(kernel, machine->vmlinux_maps[MAP__FUNCTION],
-				  NULL);
-		}
-	}
-	return 0;
-out_problem:
-	return -1;
+	return machine__process_mmap_event(machine, event, sample);
 }
 
-int event__process_mmap(event_t *self, struct perf_session *session)
+int perf_event__process_mmap2(struct perf_tool *tool __maybe_unused,
+			     union perf_event *event,
+			     struct perf_sample *sample,
+			     struct machine *machine)
 {
-	struct machine *machine;
-	struct thread *thread;
-	struct map *map;
-	u8 cpumode = self->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
-	int ret = 0;
-
-	dump_printf(" %d/%d: [%#Lx(%#Lx) @ %#Lx]: %s\n",
-			self->mmap.pid, self->mmap.tid, self->mmap.start,
-			self->mmap.len, self->mmap.pgoff, self->mmap.filename);
-
-	if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL ||
-	    cpumode == PERF_RECORD_MISC_KERNEL) {
-		ret = event__process_kernel_mmap(self, session);
-		if (ret < 0)
-			goto out_problem;
-		return 0;
-	}
-
-	machine = perf_session__find_host_machine(session);
-	if (machine == NULL)
-		goto out_problem;
-	thread = perf_session__findnew(session, self->mmap.pid);
-	map = map__new(&machine->user_dsos, self->mmap.start,
-			self->mmap.len, self->mmap.pgoff,
-			self->mmap.pid, self->mmap.filename,
-			MAP__FUNCTION, session->cwd, session->cwdlen);
-
-	if (thread == NULL || map == NULL)
-		goto out_problem;
-
-	thread__insert_map(thread, map);
-	return 0;
+	return machine__process_mmap2_event(machine, event, sample);
+}
 
-out_problem:
-	dump_printf("problem processing PERF_RECORD_MMAP, skipping event.\n");
-	return 0;
+size_t perf_event__fprintf_task(union perf_event *event, FILE *fp)
+{
+	return fprintf(fp, "(%d:%d):(%d:%d)\n",
+		       event->fork.pid, event->fork.tid,
+		       event->fork.ppid, event->fork.ptid);
 }
 
-int event__process_task(event_t *self, struct perf_session *session)
+int perf_event__process_fork(struct perf_tool *tool __maybe_unused,
+			     union perf_event *event,
+			     struct perf_sample *sample,
+			     struct machine *machine)
 {
-	struct thread *thread = perf_session__findnew(session, self->fork.tid);
-	struct thread *parent = perf_session__findnew(session, self->fork.ptid);
+	return machine__process_fork_event(machine, event, sample);
+}
 
-	dump_printf("(%d:%d):(%d:%d)\n", self->fork.pid, self->fork.tid,
-		    self->fork.ppid, self->fork.ptid);
+int perf_event__process_exit(struct perf_tool *tool __maybe_unused,
+			     union perf_event *event,
+			     struct perf_sample *sample,
+			     struct machine *machine)
+{
+	return machine__process_exit_event(machine, event, sample);
+}
 
-	if (self->header.type == PERF_RECORD_EXIT) {
-		perf_session__remove_thread(session, thread);
-		return 0;
+size_t perf_event__fprintf(union perf_event *event, FILE *fp)
+{
+	size_t ret = fprintf(fp, "PERF_RECORD_%s",
+			     perf_event__name(event->header.type));
+
+	switch (event->header.type) {
+	case PERF_RECORD_COMM:
+		ret += perf_event__fprintf_comm(event, fp);
+		break;
+	case PERF_RECORD_FORK:
+	case PERF_RECORD_EXIT:
+		ret += perf_event__fprintf_task(event, fp);
+		break;
+	case PERF_RECORD_MMAP:
+		ret += perf_event__fprintf_mmap(event, fp);
+		break;
+	case PERF_RECORD_MMAP2:
+		ret += perf_event__fprintf_mmap2(event, fp);
+		break;
+	default:
+		ret += fprintf(fp, "\n");
 	}
 
-	if (thread == NULL || parent == NULL ||
-	    thread__fork(thread, parent) < 0) {
-		dump_printf("problem processing PERF_RECORD_FORK, skipping event.\n");
-		return -1;
-	}
+	return ret;
+}
 
-	return 0;
+int perf_event__process(struct perf_tool *tool __maybe_unused,
+			union perf_event *event,
+			struct perf_sample *sample,
+			struct machine *machine)
+{
+	return machine__process_event(machine, event, sample);
 }
 
-void thread__find_addr_map(struct thread *self,
-			   struct perf_session *session, u8 cpumode,
-			   enum map_type type, pid_t pid, u64 addr,
+void thread__find_addr_map(struct thread *thread,
+			   struct machine *machine, u8 cpumode,
+			   enum map_type type, u64 addr,
 			   struct addr_location *al)
 {
-	struct map_groups *mg = &self->mg;
-	struct machine *machine = NULL;
+	struct map_groups *mg = thread->mg;
+	bool load_map = false;
 
-	al->thread = self;
+	al->machine = machine;
+	al->thread = thread;
 	al->addr = addr;
 	al->cpumode = cpumode;
-	al->filtered = false;
+	al->filtered = 0;
+
+	if (machine == NULL) {
+		al->map = NULL;
+		return;
+	}
 
 	if (cpumode == PERF_RECORD_MISC_KERNEL && perf_host) {
 		al->level = 'k';
-		machine = perf_session__find_host_machine(session);
-		if (machine == NULL) {
-			al->map = NULL;
-			return;
-		}
 		mg = &machine->kmaps;
+		load_map = true;
 	} else if (cpumode == PERF_RECORD_MISC_USER && perf_host) {
 		al->level = '.';
-		machine = perf_session__find_host_machine(session);
 	} else if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL && perf_guest) {
 		al->level = 'g';
-		machine = perf_session__find_machine(session, pid);
-		if (machine == NULL) {
-			al->map = NULL;
-			return;
-		}
 		mg = &machine->kmaps;
+		load_map = true;
+	} else if (cpumode == PERF_RECORD_MISC_GUEST_USER && perf_guest) {
+		al->level = 'u';
 	} else {
-		/*
-		 * 'u' means guest os user space.
-		 * TODO: We don't support guest user space. Might support late.
-		 */
-		if (cpumode == PERF_RECORD_MISC_GUEST_USER && perf_guest)
-			al->level = 'u';
-		else
-			al->level = 'H';
+		al->level = 'H';
 		al->map = NULL;
 
 		if ((cpumode == PERF_RECORD_MISC_GUEST_USER ||
 			cpumode == PERF_RECORD_MISC_GUEST_KERNEL) &&
 			!perf_guest)
-			al->filtered = true;
+			al->filtered |= (1 << HIST_FILTER__GUEST);
 		if ((cpumode == PERF_RECORD_MISC_USER ||
 			cpumode == PERF_RECORD_MISC_KERNEL) &&
 			!perf_host)
-			al->filtered = true;
+			al->filtered |= (1 << HIST_FILTER__HOST);
 
 		return;
 	}
@@ -619,176 +778,90 @@ try_again:
 		 * in the whole kernel symbol list.
 		 */
 		if ((long long)al->addr < 0 &&
-		    cpumode == PERF_RECORD_MISC_KERNEL &&
+		    cpumode == PERF_RECORD_MISC_USER &&
 		    machine && mg != &machine->kmaps) {
 			mg = &machine->kmaps;
 			goto try_again;
 		}
-	} else
+	} else {
+		/*
+		 * Kernel maps might be changed when loading symbols so loading
+		 * must be done prior to using kernel maps.
+		 */
+		if (load_map)
+			map__load(al->map, machine->symbol_filter);
 		al->addr = al->map->map_ip(al->map, al->addr);
+	}
 }
 
-void thread__find_addr_location(struct thread *self,
-				struct perf_session *session, u8 cpumode,
-				enum map_type type, pid_t pid, u64 addr,
-				struct addr_location *al,
-				symbol_filter_t filter)
+void thread__find_addr_location(struct thread *thread, struct machine *machine,
+				u8 cpumode, enum map_type type, u64 addr,
+				struct addr_location *al)
 {
-	thread__find_addr_map(self, session, cpumode, type, pid, addr, al);
+	thread__find_addr_map(thread, machine, cpumode, type, addr, al);
 	if (al->map != NULL)
-		al->sym = map__find_symbol(al->map, al->addr, filter);
+		al->sym = map__find_symbol(al->map, al->addr,
+					   machine->symbol_filter);
 	else
 		al->sym = NULL;
 }
 
-static void dso__calc_col_width(struct dso *self)
-{
-	if (!symbol_conf.col_width_list_str && !symbol_conf.field_sep &&
-	    (!symbol_conf.dso_list ||
-	     strlist__has_entry(symbol_conf.dso_list, self->name))) {
-		u16 slen = self->short_name_len;
-		if (verbose)
-			slen = self->long_name_len;
-		if (dsos__col_width < slen)
-			dsos__col_width = slen;
-	}
-
-	self->slen_calculated = 1;
-}
-
-int event__preprocess_sample(const event_t *self, struct perf_session *session,
-			     struct addr_location *al, symbol_filter_t filter)
+int perf_event__preprocess_sample(const union perf_event *event,
+				  struct machine *machine,
+				  struct addr_location *al,
+				  struct perf_sample *sample)
 {
-	u8 cpumode = self->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
-	struct thread *thread = perf_session__findnew(session, self->ip.pid);
+	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+	struct thread *thread = machine__findnew_thread(machine, sample->pid,
+							sample->tid);
 
 	if (thread == NULL)
 		return -1;
 
-	if (symbol_conf.comm_list &&
-	    !strlist__has_entry(symbol_conf.comm_list, thread->comm))
-		goto out_filtered;
-
-	dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid);
+	dump_printf(" ... thread: %s:%d\n", thread__comm_str(thread), thread->tid);
 	/*
-	 * Have we already created the kernel maps for the host machine?
+	 * Have we already created the kernel maps for this machine?
 	 *
 	 * This should have happened earlier, when we processed the kernel MMAP
 	 * events, but for older perf.data files there was no such thing, so do
 	 * it now.
 	 */
 	if (cpumode == PERF_RECORD_MISC_KERNEL &&
-	    session->host_machine.vmlinux_maps[MAP__FUNCTION] == NULL)
-		machine__create_kernel_maps(&session->host_machine);
+	    machine->vmlinux_maps[MAP__FUNCTION] == NULL)
+		machine__create_kernel_maps(machine);
 
-	thread__find_addr_map(thread, session, cpumode, MAP__FUNCTION,
-			      self->ip.pid, self->ip.ip, al);
+	thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION,
+			      sample->ip, al);
 	dump_printf(" ...... dso: %s\n",
 		    al->map ? al->map->dso->long_name :
 			al->level == 'H' ? "[hypervisor]" : "<not found>");
-	al->sym = NULL;
-
-	if (al->map) {
-		if (symbol_conf.dso_list &&
-		    (!al->map || !al->map->dso ||
-		     !(strlist__has_entry(symbol_conf.dso_list,
-					  al->map->dso->short_name) ||
-		       (al->map->dso->short_name != al->map->dso->long_name &&
-			strlist__has_entry(symbol_conf.dso_list,
-					   al->map->dso->long_name)))))
-			goto out_filtered;
-		/*
-		 * We have to do this here as we may have a dso with no symbol
-		 * hit that has a name longer than the ones with symbols
-		 * sampled.
-		 */
-		if (!sort_dso.elide && !al->map->dso->slen_calculated)
-			dso__calc_col_width(al->map->dso);
-
-		al->sym = map__find_symbol(al->map, al->addr, filter);
-	} else {
-		const unsigned int unresolved_col_width = BITS_PER_LONG / 4;
-
-		if (dsos__col_width < unresolved_col_width &&
-		    !symbol_conf.col_width_list_str && !symbol_conf.field_sep &&
-		    !symbol_conf.dso_list)
-			dsos__col_width = unresolved_col_width;
-	}
-
-	if (symbol_conf.sym_list && al->sym &&
-	    !strlist__has_entry(symbol_conf.sym_list, al->sym->name))
-		goto out_filtered;
-
-	return 0;
-
-out_filtered:
-	al->filtered = true;
-	return 0;
-}
-
-int event__parse_sample(event_t *event, u64 type, struct sample_data *data)
-{
-	u64 *array = event->sample.array;
-
-	if (type & PERF_SAMPLE_IP) {
-		data->ip = event->ip.ip;
-		array++;
-	}
-
-	if (type & PERF_SAMPLE_TID) {
-		u32 *p = (u32 *)array;
-		data->pid = p[0];
-		data->tid = p[1];
-		array++;
-	}
-
-	if (type & PERF_SAMPLE_TIME) {
-		data->time = *array;
-		array++;
-	}
-
-	if (type & PERF_SAMPLE_ADDR) {
-		data->addr = *array;
-		array++;
-	}
 
-	data->id = -1ULL;
-	if (type & PERF_SAMPLE_ID) {
-		data->id = *array;
-		array++;
-	}
+	if (thread__is_filtered(thread))
+		al->filtered |= (1 << HIST_FILTER__THREAD);
 
-	if (type & PERF_SAMPLE_STREAM_ID) {
-		data->stream_id = *array;
-		array++;
-	}
-
-	if (type & PERF_SAMPLE_CPU) {
-		u32 *p = (u32 *)array;
-		data->cpu = *p;
-		array++;
-	}
+	al->sym = NULL;
+	al->cpu = sample->cpu;
 
-	if (type & PERF_SAMPLE_PERIOD) {
-		data->period = *array;
-		array++;
-	}
+	if (al->map) {
+		struct dso *dso = al->map->dso;
 
-	if (type & PERF_SAMPLE_READ) {
-		pr_debug("PERF_SAMPLE_READ is unsuported for now\n");
-		return -1;
-	}
+		if (symbol_conf.dso_list &&
+		    (!dso || !(strlist__has_entry(symbol_conf.dso_list,
+						  dso->short_name) ||
+			       (dso->short_name != dso->long_name &&
+				strlist__has_entry(symbol_conf.dso_list,
+						   dso->long_name))))) {
+			al->filtered |= (1 << HIST_FILTER__DSO);
+		}
 
-	if (type & PERF_SAMPLE_CALLCHAIN) {
-		data->callchain = (struct ip_callchain *)array;
-		array += 1 + data->callchain->nr;
+		al->sym = map__find_symbol(al->map, al->addr,
+					   machine->symbol_filter);
 	}
 
-	if (type & PERF_SAMPLE_RAW) {
-		u32 *p = (u32 *)array;
-		data->raw_size = *p;
-		p++;
-		data->raw_data = p;
+	if (symbol_conf.sym_list &&
+		(!al->sym || !strlist__has_entry(symbol_conf.sym_list,
+						al->sym->name))) {
+		al->filtered |= (1 << HIST_FILTER__SYMBOL);
 	}
 
 	return 0;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 8577085db06..e5dd40addb3 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -2,26 +2,34 @@
 #define __PERF_RECORD_H
 
 #include <limits.h>
+#include <stdio.h>
 
 #include "../perf.h"
 #include "map.h"
+#include "build-id.h"
+#include "perf_regs.h"
 
-/*
- * PERF_SAMPLE_IP | PERF_SAMPLE_TID | *
- */
-struct ip_event {
+struct mmap_event {
 	struct perf_event_header header;
-	u64 ip;
 	u32 pid, tid;
-	unsigned char __more_data[];
+	u64 start;
+	u64 len;
+	u64 pgoff;
+	char filename[PATH_MAX];
 };
 
-struct mmap_event {
+struct mmap2_event {
 	struct perf_event_header header;
 	u32 pid, tid;
 	u64 start;
 	u64 len;
 	u64 pgoff;
+	u32 maj;
+	u32 min;
+	u64 ino;
+	u64 ino_generation;
+	u32 prot;
+	u32 flags;
 	char filename[PATH_MAX];
 };
 
@@ -56,12 +64,86 @@ struct read_event {
 	u64 id;
 };
 
+struct throttle_event {
+	struct perf_event_header header;
+	u64 time;
+	u64 id;
+	u64 stream_id;
+};
+
+#define PERF_SAMPLE_MASK				\
+	(PERF_SAMPLE_IP | PERF_SAMPLE_TID |		\
+	 PERF_SAMPLE_TIME | PERF_SAMPLE_ADDR |		\
+	PERF_SAMPLE_ID | PERF_SAMPLE_STREAM_ID |	\
+	 PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD |		\
+	 PERF_SAMPLE_IDENTIFIER)
+
+/* perf sample has 16 bits size limit */
+#define PERF_SAMPLE_MAX_SIZE (1 << 16)
+
 struct sample_event {
 	struct perf_event_header        header;
 	u64 array[];
 };
 
-struct sample_data {
+struct regs_dump {
+	u64 abi;
+	u64 mask;
+	u64 *regs;
+
+	/* Cached values/mask filled by first register access. */
+	u64 cache_regs[PERF_REGS_MAX];
+	u64 cache_mask;
+};
+
+struct stack_dump {
+	u16 offset;
+	u64 size;
+	char *data;
+};
+
+struct sample_read_value {
+	u64 value;
+	u64 id;
+};
+
+struct sample_read {
+	u64 time_enabled;
+	u64 time_running;
+	union {
+		struct {
+			u64 nr;
+			struct sample_read_value *values;
+		} group;
+		struct sample_read_value one;
+	};
+};
+
+struct ip_callchain {
+	u64 nr;
+	u64 ips[0];
+};
+
+struct branch_flags {
+	u64 mispred:1;
+	u64 predicted:1;
+	u64 in_tx:1;
+	u64 abort:1;
+	u64 reserved:60;
+};
+
+struct branch_entry {
+	u64			from;
+	u64			to;
+	struct branch_flags	flags;
+};
+
+struct branch_stack {
+	u64			nr;
+	struct branch_entry	entries[0];
+};
+
+struct perf_sample {
 	u64 ip;
 	u32 pid, tid;
 	u64 time;
@@ -69,24 +151,37 @@ struct sample_data {
 	u64 id;
 	u64 stream_id;
 	u64 period;
+	u64 weight;
+	u64 transaction;
 	u32 cpu;
 	u32 raw_size;
+	u64 data_src;
 	void *raw_data;
 	struct ip_callchain *callchain;
+	struct branch_stack *branch_stack;
+	struct regs_dump  user_regs;
+	struct stack_dump user_stack;
+	struct sample_read read;
 };
 
-#define BUILD_ID_SIZE 20
+#define PERF_MEM_DATA_SRC_NONE \
+	(PERF_MEM_S(OP, NA) |\
+	 PERF_MEM_S(LVL, NA) |\
+	 PERF_MEM_S(SNOOP, NA) |\
+	 PERF_MEM_S(LOCK, NA) |\
+	 PERF_MEM_S(TLB, NA))
 
 struct build_id_event {
 	struct perf_event_header header;
 	pid_t			 pid;
-	u8			 build_id[ALIGN(BUILD_ID_SIZE, sizeof(u64))];
+	u8			 build_id[PERF_ALIGN(BUILD_ID_SIZE, sizeof(u64))];
 	char			 filename[];
 };
 
 enum perf_user_event_type { /* above any possible kernel type */
+	PERF_RECORD_USER_TYPE_START		= 64,
 	PERF_RECORD_HEADER_ATTR			= 64,
-	PERF_RECORD_HEADER_EVENT_TYPE		= 65,
+	PERF_RECORD_HEADER_EVENT_TYPE		= 65, /* depreceated */
 	PERF_RECORD_HEADER_TRACING_DATA		= 66,
 	PERF_RECORD_HEADER_BUILD_ID		= 67,
 	PERF_RECORD_FINISHED_ROUND		= 68,
@@ -116,50 +211,106 @@ struct tracing_data_event {
 	u32 size;
 };
 
-typedef union event_union {
+union perf_event {
 	struct perf_event_header	header;
-	struct ip_event			ip;
 	struct mmap_event		mmap;
+	struct mmap2_event		mmap2;
 	struct comm_event		comm;
 	struct fork_event		fork;
 	struct lost_event		lost;
 	struct read_event		read;
+	struct throttle_event		throttle;
 	struct sample_event		sample;
 	struct attr_event		attr;
 	struct event_type_event		event_type;
 	struct tracing_data_event	tracing_data;
 	struct build_id_event		build_id;
-} event_t;
+};
 
-void event__print_totals(void);
+void perf_event__print_totals(void);
 
-struct perf_session;
+struct perf_tool;
+struct thread_map;
 
-typedef int (*event__handler_t)(event_t *event, struct perf_session *session);
+typedef int (*perf_event__handler_t)(struct perf_tool *tool,
+				     union perf_event *event,
+				     struct perf_sample *sample,
+				     struct machine *machine);
 
-int event__synthesize_thread(pid_t pid, event__handler_t process,
-			     struct perf_session *session);
-void event__synthesize_threads(event__handler_t process,
-			       struct perf_session *session);
-int event__synthesize_kernel_mmap(event__handler_t process,
-				struct perf_session *session,
-				struct machine *machine,
-				const char *symbol_name);
+int perf_event__synthesize_thread_map(struct perf_tool *tool,
+				      struct thread_map *threads,
+				      perf_event__handler_t process,
+				      struct machine *machine, bool mmap_data);
+int perf_event__synthesize_threads(struct perf_tool *tool,
+				   perf_event__handler_t process,
+				   struct machine *machine, bool mmap_data);
+int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
+				       perf_event__handler_t process,
+				       struct machine *machine);
 
-int event__synthesize_modules(event__handler_t process,
-			      struct perf_session *session,
-			      struct machine *machine);
+int perf_event__synthesize_modules(struct perf_tool *tool,
+				   perf_event__handler_t process,
+				   struct machine *machine);
 
-int event__process_comm(event_t *self, struct perf_session *session);
-int event__process_lost(event_t *self, struct perf_session *session);
-int event__process_mmap(event_t *self, struct perf_session *session);
-int event__process_task(event_t *self, struct perf_session *session);
+int perf_event__process_comm(struct perf_tool *tool,
+			     union perf_event *event,
+			     struct perf_sample *sample,
+			     struct machine *machine);
+int perf_event__process_lost(struct perf_tool *tool,
+			     union perf_event *event,
+			     struct perf_sample *sample,
+			     struct machine *machine);
+int perf_event__process_mmap(struct perf_tool *tool,
+			     union perf_event *event,
+			     struct perf_sample *sample,
+			     struct machine *machine);
+int perf_event__process_mmap2(struct perf_tool *tool,
+			     union perf_event *event,
+			     struct perf_sample *sample,
+			     struct machine *machine);
+int perf_event__process_fork(struct perf_tool *tool,
+			     union perf_event *event,
+			     struct perf_sample *sample,
+			     struct machine *machine);
+int perf_event__process_exit(struct perf_tool *tool,
+			     union perf_event *event,
+			     struct perf_sample *sample,
+			     struct machine *machine);
+int perf_event__process(struct perf_tool *tool,
+			union perf_event *event,
+			struct perf_sample *sample,
+			struct machine *machine);
 
 struct addr_location;
-int event__preprocess_sample(const event_t *self, struct perf_session *session,
-			     struct addr_location *al, symbol_filter_t filter);
-int event__parse_sample(event_t *event, u64 type, struct sample_data *data);
 
-extern const char *event__name[];
+int perf_event__preprocess_sample(const union perf_event *event,
+				  struct machine *machine,
+				  struct addr_location *al,
+				  struct perf_sample *sample);
+
+const char *perf_event__name(unsigned int id);
+
+size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
+				     u64 read_format);
+int perf_event__synthesize_sample(union perf_event *event, u64 type,
+				  u64 read_format,
+				  const struct perf_sample *sample,
+				  bool swapped);
+
+int perf_event__synthesize_mmap_events(struct perf_tool *tool,
+				       union perf_event *event,
+				       pid_t pid, pid_t tgid,
+				       perf_event__handler_t process,
+				       struct machine *machine,
+				       bool mmap_data);
+
+size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_task(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf(union perf_event *event, FILE *fp);
+
+u64 kallsyms__get_function_start(const char *kallsyms_filename,
+				 const char *symbol_name);
 
 #endif /* __PERF_RECORD_H */
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
new file mode 100644
index 00000000000..59ef2802fcf
--- /dev/null
+++ b/tools/perf/util/evlist.c
@@ -0,0 +1,1245 @@
+/*
+ * Copyright (C) 2011, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Parts came from builtin-{top,stat,record}.c, see those files for further
+ * copyright notes.
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+#include "util.h"
+#include <api/fs/debugfs.h>
+#include <poll.h>
+#include "cpumap.h"
+#include "thread_map.h"
+#include "target.h"
+#include "evlist.h"
+#include "evsel.h"
+#include "debug.h"
+#include <unistd.h>
+
+#include "parse-events.h"
+#include "parse-options.h"
+
+#include <sys/mman.h>
+
+#include <linux/bitops.h>
+#include <linux/hash.h>
+
+#define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
+#define SID(e, x, y) xyarray__entry(e->sample_id, x, y)
+
+void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus,
+		       struct thread_map *threads)
+{
+	int i;
+
+	for (i = 0; i < PERF_EVLIST__HLIST_SIZE; ++i)
+		INIT_HLIST_HEAD(&evlist->heads[i]);
+	INIT_LIST_HEAD(&evlist->entries);
+	perf_evlist__set_maps(evlist, cpus, threads);
+	evlist->workload.pid = -1;
+}
+
+struct perf_evlist *perf_evlist__new(void)
+{
+	struct perf_evlist *evlist = zalloc(sizeof(*evlist));
+
+	if (evlist != NULL)
+		perf_evlist__init(evlist, NULL, NULL);
+
+	return evlist;
+}
+
+struct perf_evlist *perf_evlist__new_default(void)
+{
+	struct perf_evlist *evlist = perf_evlist__new();
+
+	if (evlist && perf_evlist__add_default(evlist)) {
+		perf_evlist__delete(evlist);
+		evlist = NULL;
+	}
+
+	return evlist;
+}
+
+/**
+ * perf_evlist__set_id_pos - set the positions of event ids.
+ * @evlist: selected event list
+ *
+ * Events with compatible sample types all have the same id_pos
+ * and is_pos.  For convenience, put a copy on evlist.
+ */
+void perf_evlist__set_id_pos(struct perf_evlist *evlist)
+{
+	struct perf_evsel *first = perf_evlist__first(evlist);
+
+	evlist->id_pos = first->id_pos;
+	evlist->is_pos = first->is_pos;
+}
+
+static void perf_evlist__update_id_pos(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each(evlist, evsel)
+		perf_evsel__calc_id_pos(evsel);
+
+	perf_evlist__set_id_pos(evlist);
+}
+
+static void perf_evlist__purge(struct perf_evlist *evlist)
+{
+	struct perf_evsel *pos, *n;
+
+	evlist__for_each_safe(evlist, n, pos) {
+		list_del_init(&pos->node);
+		perf_evsel__delete(pos);
+	}
+
+	evlist->nr_entries = 0;
+}
+
+void perf_evlist__exit(struct perf_evlist *evlist)
+{
+	zfree(&evlist->mmap);
+	zfree(&evlist->pollfd);
+}
+
+void perf_evlist__delete(struct perf_evlist *evlist)
+{
+	perf_evlist__munmap(evlist);
+	perf_evlist__close(evlist);
+	cpu_map__delete(evlist->cpus);
+	thread_map__delete(evlist->threads);
+	evlist->cpus = NULL;
+	evlist->threads = NULL;
+	perf_evlist__purge(evlist);
+	perf_evlist__exit(evlist);
+	free(evlist);
+}
+
+void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry)
+{
+	list_add_tail(&entry->node, &evlist->entries);
+	entry->idx = evlist->nr_entries;
+
+	if (!evlist->nr_entries++)
+		perf_evlist__set_id_pos(evlist);
+}
+
+void perf_evlist__splice_list_tail(struct perf_evlist *evlist,
+				   struct list_head *list,
+				   int nr_entries)
+{
+	bool set_id_pos = !evlist->nr_entries;
+
+	list_splice_tail(list, &evlist->entries);
+	evlist->nr_entries += nr_entries;
+	if (set_id_pos)
+		perf_evlist__set_id_pos(evlist);
+}
+
+void __perf_evlist__set_leader(struct list_head *list)
+{
+	struct perf_evsel *evsel, *leader;
+
+	leader = list_entry(list->next, struct perf_evsel, node);
+	evsel = list_entry(list->prev, struct perf_evsel, node);
+
+	leader->nr_members = evsel->idx - leader->idx + 1;
+
+	__evlist__for_each(list, evsel) {
+		evsel->leader = leader;
+	}
+}
+
+void perf_evlist__set_leader(struct perf_evlist *evlist)
+{
+	if (evlist->nr_entries) {
+		evlist->nr_groups = evlist->nr_entries > 1 ? 1 : 0;
+		__perf_evlist__set_leader(&evlist->entries);
+	}
+}
+
+int perf_evlist__add_default(struct perf_evlist *evlist)
+{
+	struct perf_event_attr attr = {
+		.type = PERF_TYPE_HARDWARE,
+		.config = PERF_COUNT_HW_CPU_CYCLES,
+	};
+	struct perf_evsel *evsel;
+
+	event_attr_init(&attr);
+
+	evsel = perf_evsel__new(&attr);
+	if (evsel == NULL)
+		goto error;
+
+	/* use strdup() because free(evsel) assumes name is allocated */
+	evsel->name = strdup("cycles");
+	if (!evsel->name)
+		goto error_free;
+
+	perf_evlist__add(evlist, evsel);
+	return 0;
+error_free:
+	perf_evsel__delete(evsel);
+error:
+	return -ENOMEM;
+}
+
+static int perf_evlist__add_attrs(struct perf_evlist *evlist,
+				  struct perf_event_attr *attrs, size_t nr_attrs)
+{
+	struct perf_evsel *evsel, *n;
+	LIST_HEAD(head);
+	size_t i;
+
+	for (i = 0; i < nr_attrs; i++) {
+		evsel = perf_evsel__new_idx(attrs + i, evlist->nr_entries + i);
+		if (evsel == NULL)
+			goto out_delete_partial_list;
+		list_add_tail(&evsel->node, &head);
+	}
+
+	perf_evlist__splice_list_tail(evlist, &head, nr_attrs);
+
+	return 0;
+
+out_delete_partial_list:
+	__evlist__for_each_safe(&head, n, evsel)
+		perf_evsel__delete(evsel);
+	return -1;
+}
+
+int __perf_evlist__add_default_attrs(struct perf_evlist *evlist,
+				     struct perf_event_attr *attrs, size_t nr_attrs)
+{
+	size_t i;
+
+	for (i = 0; i < nr_attrs; i++)
+		event_attr_init(attrs + i);
+
+	return perf_evlist__add_attrs(evlist, attrs, nr_attrs);
+}
+
+struct perf_evsel *
+perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each(evlist, evsel) {
+		if (evsel->attr.type   == PERF_TYPE_TRACEPOINT &&
+		    (int)evsel->attr.config == id)
+			return evsel;
+	}
+
+	return NULL;
+}
+
+struct perf_evsel *
+perf_evlist__find_tracepoint_by_name(struct perf_evlist *evlist,
+				     const char *name)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each(evlist, evsel) {
+		if ((evsel->attr.type == PERF_TYPE_TRACEPOINT) &&
+		    (strcmp(evsel->name, name) == 0))
+			return evsel;
+	}
+
+	return NULL;
+}
+
+int perf_evlist__add_newtp(struct perf_evlist *evlist,
+			   const char *sys, const char *name, void *handler)
+{
+	struct perf_evsel *evsel = perf_evsel__newtp(sys, name);
+
+	if (evsel == NULL)
+		return -1;
+
+	evsel->handler = handler;
+	perf_evlist__add(evlist, evsel);
+	return 0;
+}
+
+void perf_evlist__disable(struct perf_evlist *evlist)
+{
+	int cpu, thread;
+	struct perf_evsel *pos;
+	int nr_cpus = cpu_map__nr(evlist->cpus);
+	int nr_threads = thread_map__nr(evlist->threads);
+
+	for (cpu = 0; cpu < nr_cpus; cpu++) {
+		evlist__for_each(evlist, pos) {
+			if (!perf_evsel__is_group_leader(pos) || !pos->fd)
+				continue;
+			for (thread = 0; thread < nr_threads; thread++)
+				ioctl(FD(pos, cpu, thread),
+				      PERF_EVENT_IOC_DISABLE, 0);
+		}
+	}
+}
+
+void perf_evlist__enable(struct perf_evlist *evlist)
+{
+	int cpu, thread;
+	struct perf_evsel *pos;
+	int nr_cpus = cpu_map__nr(evlist->cpus);
+	int nr_threads = thread_map__nr(evlist->threads);
+
+	for (cpu = 0; cpu < nr_cpus; cpu++) {
+		evlist__for_each(evlist, pos) {
+			if (!perf_evsel__is_group_leader(pos) || !pos->fd)
+				continue;
+			for (thread = 0; thread < nr_threads; thread++)
+				ioctl(FD(pos, cpu, thread),
+				      PERF_EVENT_IOC_ENABLE, 0);
+		}
+	}
+}
+
+int perf_evlist__disable_event(struct perf_evlist *evlist,
+			       struct perf_evsel *evsel)
+{
+	int cpu, thread, err;
+
+	if (!evsel->fd)
+		return 0;
+
+	for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
+		for (thread = 0; thread < evlist->threads->nr; thread++) {
+			err = ioctl(FD(evsel, cpu, thread),
+				    PERF_EVENT_IOC_DISABLE, 0);
+			if (err)
+				return err;
+		}
+	}
+	return 0;
+}
+
+int perf_evlist__enable_event(struct perf_evlist *evlist,
+			      struct perf_evsel *evsel)
+{
+	int cpu, thread, err;
+
+	if (!evsel->fd)
+		return -EINVAL;
+
+	for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
+		for (thread = 0; thread < evlist->threads->nr; thread++) {
+			err = ioctl(FD(evsel, cpu, thread),
+				    PERF_EVENT_IOC_ENABLE, 0);
+			if (err)
+				return err;
+		}
+	}
+	return 0;
+}
+
+static int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
+{
+	int nr_cpus = cpu_map__nr(evlist->cpus);
+	int nr_threads = thread_map__nr(evlist->threads);
+	int nfds = nr_cpus * nr_threads * evlist->nr_entries;
+	evlist->pollfd = malloc(sizeof(struct pollfd) * nfds);
+	return evlist->pollfd != NULL ? 0 : -ENOMEM;
+}
+
+void perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd)
+{
+	fcntl(fd, F_SETFL, O_NONBLOCK);
+	evlist->pollfd[evlist->nr_fds].fd = fd;
+	evlist->pollfd[evlist->nr_fds].events = POLLIN;
+	evlist->nr_fds++;
+}
+
+static void perf_evlist__id_hash(struct perf_evlist *evlist,
+				 struct perf_evsel *evsel,
+				 int cpu, int thread, u64 id)
+{
+	int hash;
+	struct perf_sample_id *sid = SID(evsel, cpu, thread);
+
+	sid->id = id;
+	sid->evsel = evsel;
+	hash = hash_64(sid->id, PERF_EVLIST__HLIST_BITS);
+	hlist_add_head(&sid->node, &evlist->heads[hash]);
+}
+
+void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel,
+			 int cpu, int thread, u64 id)
+{
+	perf_evlist__id_hash(evlist, evsel, cpu, thread, id);
+	evsel->id[evsel->ids++] = id;
+}
+
+static int perf_evlist__id_add_fd(struct perf_evlist *evlist,
+				  struct perf_evsel *evsel,
+				  int cpu, int thread, int fd)
+{
+	u64 read_data[4] = { 0, };
+	int id_idx = 1; /* The first entry is the counter value */
+	u64 id;
+	int ret;
+
+	ret = ioctl(fd, PERF_EVENT_IOC_ID, &id);
+	if (!ret)
+		goto add;
+
+	if (errno != ENOTTY)
+		return -1;
+
+	/* Legacy way to get event id.. All hail to old kernels! */
+
+	/*
+	 * This way does not work with group format read, so bail
+	 * out in that case.
+	 */
+	if (perf_evlist__read_format(evlist) & PERF_FORMAT_GROUP)
+		return -1;
+
+	if (!(evsel->attr.read_format & PERF_FORMAT_ID) ||
+	    read(fd, &read_data, sizeof(read_data)) == -1)
+		return -1;
+
+	if (evsel->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+		++id_idx;
+	if (evsel->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+		++id_idx;
+
+	id = read_data[id_idx];
+
+ add:
+	perf_evlist__id_add(evlist, evsel, cpu, thread, id);
+	return 0;
+}
+
+struct perf_sample_id *perf_evlist__id2sid(struct perf_evlist *evlist, u64 id)
+{
+	struct hlist_head *head;
+	struct perf_sample_id *sid;
+	int hash;
+
+	hash = hash_64(id, PERF_EVLIST__HLIST_BITS);
+	head = &evlist->heads[hash];
+
+	hlist_for_each_entry(sid, head, node)
+		if (sid->id == id)
+			return sid;
+
+	return NULL;
+}
+
+struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id)
+{
+	struct perf_sample_id *sid;
+
+	if (evlist->nr_entries == 1)
+		return perf_evlist__first(evlist);
+
+	sid = perf_evlist__id2sid(evlist, id);
+	if (sid)
+		return sid->evsel;
+
+	if (!perf_evlist__sample_id_all(evlist))
+		return perf_evlist__first(evlist);
+
+	return NULL;
+}
+
+static int perf_evlist__event2id(struct perf_evlist *evlist,
+				 union perf_event *event, u64 *id)
+{
+	const u64 *array = event->sample.array;
+	ssize_t n;
+
+	n = (event->header.size - sizeof(event->header)) >> 3;
+
+	if (event->header.type == PERF_RECORD_SAMPLE) {
+		if (evlist->id_pos >= n)
+			return -1;
+		*id = array[evlist->id_pos];
+	} else {
+		if (evlist->is_pos > n)
+			return -1;
+		n -= evlist->is_pos;
+		*id = array[n];
+	}
+	return 0;
+}
+
+static struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist,
+						   union perf_event *event)
+{
+	struct perf_evsel *first = perf_evlist__first(evlist);
+	struct hlist_head *head;
+	struct perf_sample_id *sid;
+	int hash;
+	u64 id;
+
+	if (evlist->nr_entries == 1)
+		return first;
+
+	if (!first->attr.sample_id_all &&
+	    event->header.type != PERF_RECORD_SAMPLE)
+		return first;
+
+	if (perf_evlist__event2id(evlist, event, &id))
+		return NULL;
+
+	/* Synthesized events have an id of zero */
+	if (!id)
+		return first;
+
+	hash = hash_64(id, PERF_EVLIST__HLIST_BITS);
+	head = &evlist->heads[hash];
+
+	hlist_for_each_entry(sid, head, node) {
+		if (sid->id == id)
+			return sid->evsel;
+	}
+	return NULL;
+}
+
+union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
+{
+	struct perf_mmap *md = &evlist->mmap[idx];
+	unsigned int head = perf_mmap__read_head(md);
+	unsigned int old = md->prev;
+	unsigned char *data = md->base + page_size;
+	union perf_event *event = NULL;
+
+	if (evlist->overwrite) {
+		/*
+		 * If we're further behind than half the buffer, there's a chance
+		 * the writer will bite our tail and mess up the samples under us.
+		 *
+		 * If we somehow ended up ahead of the head, we got messed up.
+		 *
+		 * In either case, truncate and restart at head.
+		 */
+		int diff = head - old;
+		if (diff > md->mask / 2 || diff < 0) {
+			fprintf(stderr, "WARNING: failed to keep up with mmap data.\n");
+
+			/*
+			 * head points to a known good entry, start there.
+			 */
+			old = head;
+		}
+	}
+
+	if (old != head) {
+		size_t size;
+
+		event = (union perf_event *)&data[old & md->mask];
+		size = event->header.size;
+
+		/*
+		 * Event straddles the mmap boundary -- header should always
+		 * be inside due to u64 alignment of output.
+		 */
+		if ((old & md->mask) + size != ((old + size) & md->mask)) {
+			unsigned int offset = old;
+			unsigned int len = min(sizeof(*event), size), cpy;
+			void *dst = md->event_copy;
+
+			do {
+				cpy = min(md->mask + 1 - (offset & md->mask), len);
+				memcpy(dst, &data[offset & md->mask], cpy);
+				offset += cpy;
+				dst += cpy;
+				len -= cpy;
+			} while (len);
+
+			event = (union perf_event *) md->event_copy;
+		}
+
+		old += size;
+	}
+
+	md->prev = old;
+
+	return event;
+}
+
+void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx)
+{
+	if (!evlist->overwrite) {
+		struct perf_mmap *md = &evlist->mmap[idx];
+		unsigned int old = md->prev;
+
+		perf_mmap__write_tail(md, old);
+	}
+}
+
+static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx)
+{
+	if (evlist->mmap[idx].base != NULL) {
+		munmap(evlist->mmap[idx].base, evlist->mmap_len);
+		evlist->mmap[idx].base = NULL;
+	}
+}
+
+void perf_evlist__munmap(struct perf_evlist *evlist)
+{
+	int i;
+
+	if (evlist->mmap == NULL)
+		return;
+
+	for (i = 0; i < evlist->nr_mmaps; i++)
+		__perf_evlist__munmap(evlist, i);
+
+	zfree(&evlist->mmap);
+}
+
+static int perf_evlist__alloc_mmap(struct perf_evlist *evlist)
+{
+	evlist->nr_mmaps = cpu_map__nr(evlist->cpus);
+	if (cpu_map__empty(evlist->cpus))
+		evlist->nr_mmaps = thread_map__nr(evlist->threads);
+	evlist->mmap = zalloc(evlist->nr_mmaps * sizeof(struct perf_mmap));
+	return evlist->mmap != NULL ? 0 : -ENOMEM;
+}
+
+static int __perf_evlist__mmap(struct perf_evlist *evlist,
+			       int idx, int prot, int mask, int fd)
+{
+	evlist->mmap[idx].prev = 0;
+	evlist->mmap[idx].mask = mask;
+	evlist->mmap[idx].base = mmap(NULL, evlist->mmap_len, prot,
+				      MAP_SHARED, fd, 0);
+	if (evlist->mmap[idx].base == MAP_FAILED) {
+		pr_debug2("failed to mmap perf event ring buffer, error %d\n",
+			  errno);
+		evlist->mmap[idx].base = NULL;
+		return -1;
+	}
+
+	perf_evlist__add_pollfd(evlist, fd);
+	return 0;
+}
+
+static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
+				       int prot, int mask, int cpu, int thread,
+				       int *output)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each(evlist, evsel) {
+		int fd = FD(evsel, cpu, thread);
+
+		if (*output == -1) {
+			*output = fd;
+			if (__perf_evlist__mmap(evlist, idx, prot, mask,
+						*output) < 0)
+				return -1;
+		} else {
+			if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, *output) != 0)
+				return -1;
+		}
+
+		if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
+		    perf_evlist__id_add_fd(evlist, evsel, cpu, thread, fd) < 0)
+			return -1;
+	}
+
+	return 0;
+}
+
+static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot,
+				     int mask)
+{
+	int cpu, thread;
+	int nr_cpus = cpu_map__nr(evlist->cpus);
+	int nr_threads = thread_map__nr(evlist->threads);
+
+	pr_debug2("perf event ring buffer mmapped per cpu\n");
+	for (cpu = 0; cpu < nr_cpus; cpu++) {
+		int output = -1;
+
+		for (thread = 0; thread < nr_threads; thread++) {
+			if (perf_evlist__mmap_per_evsel(evlist, cpu, prot, mask,
+							cpu, thread, &output))
+				goto out_unmap;
+		}
+	}
+
+	return 0;
+
+out_unmap:
+	for (cpu = 0; cpu < nr_cpus; cpu++)
+		__perf_evlist__munmap(evlist, cpu);
+	return -1;
+}
+
+static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot,
+					int mask)
+{
+	int thread;
+	int nr_threads = thread_map__nr(evlist->threads);
+
+	pr_debug2("perf event ring buffer mmapped per thread\n");
+	for (thread = 0; thread < nr_threads; thread++) {
+		int output = -1;
+
+		if (perf_evlist__mmap_per_evsel(evlist, thread, prot, mask, 0,
+						thread, &output))
+			goto out_unmap;
+	}
+
+	return 0;
+
+out_unmap:
+	for (thread = 0; thread < nr_threads; thread++)
+		__perf_evlist__munmap(evlist, thread);
+	return -1;
+}
+
+static size_t perf_evlist__mmap_size(unsigned long pages)
+{
+	/* 512 kiB: default amount of unprivileged mlocked memory */
+	if (pages == UINT_MAX)
+		pages = (512 * 1024) / page_size;
+	else if (!is_power_of_2(pages))
+		return 0;
+
+	return (pages + 1) * page_size;
+}
+
+static long parse_pages_arg(const char *str, unsigned long min,
+			    unsigned long max)
+{
+	unsigned long pages, val;
+	static struct parse_tag tags[] = {
+		{ .tag  = 'B', .mult = 1       },
+		{ .tag  = 'K', .mult = 1 << 10 },
+		{ .tag  = 'M', .mult = 1 << 20 },
+		{ .tag  = 'G', .mult = 1 << 30 },
+		{ .tag  = 0 },
+	};
+
+	if (str == NULL)
+		return -EINVAL;
+
+	val = parse_tag_value(str, tags);
+	if (val != (unsigned long) -1) {
+		/* we got file size value */
+		pages = PERF_ALIGN(val, page_size) / page_size;
+	} else {
+		/* we got pages count value */
+		char *eptr;
+		pages = strtoul(str, &eptr, 10);
+		if (*eptr != '\0')
+			return -EINVAL;
+	}
+
+	if (pages == 0 && min == 0) {
+		/* leave number of pages at 0 */
+	} else if (!is_power_of_2(pages)) {
+		/* round pages up to next power of 2 */
+		pages = next_pow2_l(pages);
+		if (!pages)
+			return -EINVAL;
+		pr_info("rounding mmap pages size to %lu bytes (%lu pages)\n",
+			pages * page_size, pages);
+	}
+
+	if (pages > max)
+		return -EINVAL;
+
+	return pages;
+}
+
+int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str,
+				  int unset __maybe_unused)
+{
+	unsigned int *mmap_pages = opt->value;
+	unsigned long max = UINT_MAX;
+	long pages;
+
+	if (max > SIZE_MAX / page_size)
+		max = SIZE_MAX / page_size;
+
+	pages = parse_pages_arg(str, 1, max);
+	if (pages < 0) {
+		pr_err("Invalid argument for --mmap_pages/-m\n");
+		return -1;
+	}
+
+	*mmap_pages = pages;
+	return 0;
+}
+
+/**
+ * perf_evlist__mmap - Create mmaps to receive events.
+ * @evlist: list of events
+ * @pages: map length in pages
+ * @overwrite: overwrite older events?
+ *
+ * If @overwrite is %false the user needs to signal event consumption using
+ * perf_mmap__write_tail().  Using perf_evlist__mmap_read() does this
+ * automatically.
+ *
+ * Return: %0 on success, negative error code otherwise.
+ */
+int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
+		      bool overwrite)
+{
+	struct perf_evsel *evsel;
+	const struct cpu_map *cpus = evlist->cpus;
+	const struct thread_map *threads = evlist->threads;
+	int prot = PROT_READ | (overwrite ? 0 : PROT_WRITE), mask;
+
+	if (evlist->mmap == NULL && perf_evlist__alloc_mmap(evlist) < 0)
+		return -ENOMEM;
+
+	if (evlist->pollfd == NULL && perf_evlist__alloc_pollfd(evlist) < 0)
+		return -ENOMEM;
+
+	evlist->overwrite = overwrite;
+	evlist->mmap_len = perf_evlist__mmap_size(pages);
+	pr_debug("mmap size %zuB\n", evlist->mmap_len);
+	mask = evlist->mmap_len - page_size - 1;
+
+	evlist__for_each(evlist, evsel) {
+		if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
+		    evsel->sample_id == NULL &&
+		    perf_evsel__alloc_id(evsel, cpu_map__nr(cpus), threads->nr) < 0)
+			return -ENOMEM;
+	}
+
+	if (cpu_map__empty(cpus))
+		return perf_evlist__mmap_per_thread(evlist, prot, mask);
+
+	return perf_evlist__mmap_per_cpu(evlist, prot, mask);
+}
+
+int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
+{
+	evlist->threads = thread_map__new_str(target->pid, target->tid,
+					      target->uid);
+
+	if (evlist->threads == NULL)
+		return -1;
+
+	if (target__uses_dummy_map(target))
+		evlist->cpus = cpu_map__dummy_new();
+	else
+		evlist->cpus = cpu_map__new(target->cpu_list);
+
+	if (evlist->cpus == NULL)
+		goto out_delete_threads;
+
+	return 0;
+
+out_delete_threads:
+	thread_map__delete(evlist->threads);
+	return -1;
+}
+
+int perf_evlist__apply_filters(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+	int err = 0;
+	const int ncpus = cpu_map__nr(evlist->cpus),
+		  nthreads = thread_map__nr(evlist->threads);
+
+	evlist__for_each(evlist, evsel) {
+		if (evsel->filter == NULL)
+			continue;
+
+		err = perf_evsel__set_filter(evsel, ncpus, nthreads, evsel->filter);
+		if (err)
+			break;
+	}
+
+	return err;
+}
+
+int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter)
+{
+	struct perf_evsel *evsel;
+	int err = 0;
+	const int ncpus = cpu_map__nr(evlist->cpus),
+		  nthreads = thread_map__nr(evlist->threads);
+
+	evlist__for_each(evlist, evsel) {
+		err = perf_evsel__set_filter(evsel, ncpus, nthreads, filter);
+		if (err)
+			break;
+	}
+
+	return err;
+}
+
+bool perf_evlist__valid_sample_type(struct perf_evlist *evlist)
+{
+	struct perf_evsel *pos;
+
+	if (evlist->nr_entries == 1)
+		return true;
+
+	if (evlist->id_pos < 0 || evlist->is_pos < 0)
+		return false;
+
+	evlist__for_each(evlist, pos) {
+		if (pos->id_pos != evlist->id_pos ||
+		    pos->is_pos != evlist->is_pos)
+			return false;
+	}
+
+	return true;
+}
+
+u64 __perf_evlist__combined_sample_type(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+
+	if (evlist->combined_sample_type)
+		return evlist->combined_sample_type;
+
+	evlist__for_each(evlist, evsel)
+		evlist->combined_sample_type |= evsel->attr.sample_type;
+
+	return evlist->combined_sample_type;
+}
+
+u64 perf_evlist__combined_sample_type(struct perf_evlist *evlist)
+{
+	evlist->combined_sample_type = 0;
+	return __perf_evlist__combined_sample_type(evlist);
+}
+
+bool perf_evlist__valid_read_format(struct perf_evlist *evlist)
+{
+	struct perf_evsel *first = perf_evlist__first(evlist), *pos = first;
+	u64 read_format = first->attr.read_format;
+	u64 sample_type = first->attr.sample_type;
+
+	evlist__for_each(evlist, pos) {
+		if (read_format != pos->attr.read_format)
+			return false;
+	}
+
+	/* PERF_SAMPLE_READ imples PERF_FORMAT_ID. */
+	if ((sample_type & PERF_SAMPLE_READ) &&
+	    !(read_format & PERF_FORMAT_ID)) {
+		return false;
+	}
+
+	return true;
+}
+
+u64 perf_evlist__read_format(struct perf_evlist *evlist)
+{
+	struct perf_evsel *first = perf_evlist__first(evlist);
+	return first->attr.read_format;
+}
+
+u16 perf_evlist__id_hdr_size(struct perf_evlist *evlist)
+{
+	struct perf_evsel *first = perf_evlist__first(evlist);
+	struct perf_sample *data;
+	u64 sample_type;
+	u16 size = 0;
+
+	if (!first->attr.sample_id_all)
+		goto out;
+
+	sample_type = first->attr.sample_type;
+
+	if (sample_type & PERF_SAMPLE_TID)
+		size += sizeof(data->tid) * 2;
+
+       if (sample_type & PERF_SAMPLE_TIME)
+		size += sizeof(data->time);
+
+	if (sample_type & PERF_SAMPLE_ID)
+		size += sizeof(data->id);
+
+	if (sample_type & PERF_SAMPLE_STREAM_ID)
+		size += sizeof(data->stream_id);
+
+	if (sample_type & PERF_SAMPLE_CPU)
+		size += sizeof(data->cpu) * 2;
+
+	if (sample_type & PERF_SAMPLE_IDENTIFIER)
+		size += sizeof(data->id);
+out:
+	return size;
+}
+
+bool perf_evlist__valid_sample_id_all(struct perf_evlist *evlist)
+{
+	struct perf_evsel *first = perf_evlist__first(evlist), *pos = first;
+
+	evlist__for_each_continue(evlist, pos) {
+		if (first->attr.sample_id_all != pos->attr.sample_id_all)
+			return false;
+	}
+
+	return true;
+}
+
+bool perf_evlist__sample_id_all(struct perf_evlist *evlist)
+{
+	struct perf_evsel *first = perf_evlist__first(evlist);
+	return first->attr.sample_id_all;
+}
+
+void perf_evlist__set_selected(struct perf_evlist *evlist,
+			       struct perf_evsel *evsel)
+{
+	evlist->selected = evsel;
+}
+
+void perf_evlist__close(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+	int ncpus = cpu_map__nr(evlist->cpus);
+	int nthreads = thread_map__nr(evlist->threads);
+	int n;
+
+	evlist__for_each_reverse(evlist, evsel) {
+		n = evsel->cpus ? evsel->cpus->nr : ncpus;
+		perf_evsel__close(evsel, n, nthreads);
+	}
+}
+
+int perf_evlist__open(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+	int err;
+
+	perf_evlist__update_id_pos(evlist);
+
+	evlist__for_each(evlist, evsel) {
+		err = perf_evsel__open(evsel, evlist->cpus, evlist->threads);
+		if (err < 0)
+			goto out_err;
+	}
+
+	return 0;
+out_err:
+	perf_evlist__close(evlist);
+	errno = -err;
+	return err;
+}
+
+int perf_evlist__prepare_workload(struct perf_evlist *evlist, struct target *target,
+				  const char *argv[], bool pipe_output,
+				  void (*exec_error)(int signo, siginfo_t *info, void *ucontext))
+{
+	int child_ready_pipe[2], go_pipe[2];
+	char bf;
+
+	if (pipe(child_ready_pipe) < 0) {
+		perror("failed to create 'ready' pipe");
+		return -1;
+	}
+
+	if (pipe(go_pipe) < 0) {
+		perror("failed to create 'go' pipe");
+		goto out_close_ready_pipe;
+	}
+
+	evlist->workload.pid = fork();
+	if (evlist->workload.pid < 0) {
+		perror("failed to fork");
+		goto out_close_pipes;
+	}
+
+	if (!evlist->workload.pid) {
+		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);
+
+		/*
+		 * Tell the parent we're ready to go
+		 */
+		close(child_ready_pipe[1]);
+
+		/*
+		 * Wait until the parent tells us to go.
+		 */
+		if (read(go_pipe[0], &bf, 1) == -1)
+			perror("unable to read pipe");
+
+		execvp(argv[0], (char **)argv);
+
+		if (exec_error) {
+			union sigval val;
+
+			val.sival_int = errno;
+			if (sigqueue(getppid(), SIGUSR1, val))
+				perror(argv[0]);
+		} else
+			perror(argv[0]);
+		exit(-1);
+	}
+
+	if (exec_error) {
+		struct sigaction act = {
+			.sa_flags     = SA_SIGINFO,
+			.sa_sigaction = exec_error,
+		};
+		sigaction(SIGUSR1, &act, NULL);
+	}
+
+	if (target__none(target))
+		evlist->threads->map[0] = evlist->workload.pid;
+
+	close(child_ready_pipe[1]);
+	close(go_pipe[0]);
+	/*
+	 * wait for child to settle
+	 */
+	if (read(child_ready_pipe[0], &bf, 1) == -1) {
+		perror("unable to read pipe");
+		goto out_close_pipes;
+	}
+
+	fcntl(go_pipe[1], F_SETFD, FD_CLOEXEC);
+	evlist->workload.cork_fd = go_pipe[1];
+	close(child_ready_pipe[0]);
+	return 0;
+
+out_close_pipes:
+	close(go_pipe[0]);
+	close(go_pipe[1]);
+out_close_ready_pipe:
+	close(child_ready_pipe[0]);
+	close(child_ready_pipe[1]);
+	return -1;
+}
+
+int perf_evlist__start_workload(struct perf_evlist *evlist)
+{
+	if (evlist->workload.cork_fd > 0) {
+		char bf = 0;
+		int ret;
+		/*
+		 * Remove the cork, let it rip!
+		 */
+		ret = write(evlist->workload.cork_fd, &bf, 1);
+		if (ret < 0)
+			perror("enable to write to pipe");
+
+		close(evlist->workload.cork_fd);
+		return ret;
+	}
+
+	return 0;
+}
+
+int perf_evlist__parse_sample(struct perf_evlist *evlist, union perf_event *event,
+			      struct perf_sample *sample)
+{
+	struct perf_evsel *evsel = perf_evlist__event2evsel(evlist, event);
+
+	if (!evsel)
+		return -EFAULT;
+	return perf_evsel__parse_sample(evsel, event, sample);
+}
+
+size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp)
+{
+	struct perf_evsel *evsel;
+	size_t printed = 0;
+
+	evlist__for_each(evlist, evsel) {
+		printed += fprintf(fp, "%s%s", evsel->idx ? ", " : "",
+				   perf_evsel__name(evsel));
+	}
+
+	return printed + fprintf(fp, "\n");
+}
+
+int perf_evlist__strerror_tp(struct perf_evlist *evlist __maybe_unused,
+			     int err, char *buf, size_t size)
+{
+	char sbuf[128];
+
+	switch (err) {
+	case ENOENT:
+		scnprintf(buf, size, "%s",
+			  "Error:\tUnable to find debugfs\n"
+			  "Hint:\tWas your kernel was compiled with debugfs support?\n"
+			  "Hint:\tIs the debugfs filesystem mounted?\n"
+			  "Hint:\tTry 'sudo mount -t debugfs nodev /sys/kernel/debug'");
+		break;
+	case EACCES:
+		scnprintf(buf, size,
+			  "Error:\tNo permissions to read %s/tracing/events/raw_syscalls\n"
+			  "Hint:\tTry 'sudo mount -o remount,mode=755 %s'\n",
+			  debugfs_mountpoint, debugfs_mountpoint);
+		break;
+	default:
+		scnprintf(buf, size, "%s", strerror_r(err, sbuf, sizeof(sbuf)));
+		break;
+	}
+
+	return 0;
+}
+
+int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused,
+			       int err, char *buf, size_t size)
+{
+	int printed, value;
+	char sbuf[128], *emsg = strerror_r(err, sbuf, sizeof(sbuf));
+
+	switch (err) {
+	case EACCES:
+	case EPERM:
+		printed = scnprintf(buf, size,
+				    "Error:\t%s.\n"
+				    "Hint:\tCheck /proc/sys/kernel/perf_event_paranoid setting.", emsg);
+
+		value = perf_event_paranoid();
+
+		printed += scnprintf(buf + printed, size - printed, "\nHint:\t");
+
+		if (value >= 2) {
+			printed += scnprintf(buf + printed, size - printed,
+					     "For your workloads it needs to be <= 1\nHint:\t");
+		}
+		printed += scnprintf(buf + printed, size - printed,
+				     "For system wide tracing it needs to be set to -1");
+
+		printed += scnprintf(buf + printed, size - printed,
+				    ".\nHint:\tThe current value is %d.", value);
+		break;
+	default:
+		scnprintf(buf, size, "%s", emsg);
+		break;
+	}
+
+	return 0;
+}
+
+void perf_evlist__to_front(struct perf_evlist *evlist,
+			   struct perf_evsel *move_evsel)
+{
+	struct perf_evsel *evsel, *n;
+	LIST_HEAD(move);
+
+	if (move_evsel == perf_evlist__first(evlist))
+		return;
+
+	evlist__for_each_safe(evlist, n, evsel) {
+		if (evsel->leader == move_evsel->leader)
+			list_move_tail(&evsel->node, &move);
+	}
+
+	list_splice(&move, &evlist->entries);
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
new file mode 100644
index 00000000000..f5173cd6369
--- /dev/null
+++ b/tools/perf/util/evlist.h
@@ -0,0 +1,265 @@
+#ifndef __PERF_EVLIST_H
+#define __PERF_EVLIST_H 1
+
+#include <linux/list.h>
+#include <stdio.h>
+#include "../perf.h"
+#include "event.h"
+#include "evsel.h"
+#include "util.h"
+#include <unistd.h>
+
+struct pollfd;
+struct thread_map;
+struct cpu_map;
+struct record_opts;
+
+#define PERF_EVLIST__HLIST_BITS 8
+#define PERF_EVLIST__HLIST_SIZE (1 << PERF_EVLIST__HLIST_BITS)
+
+struct perf_mmap {
+	void		 *base;
+	int		 mask;
+	unsigned int	 prev;
+	char		 event_copy[PERF_SAMPLE_MAX_SIZE];
+};
+
+struct perf_evlist {
+	struct list_head entries;
+	struct hlist_head heads[PERF_EVLIST__HLIST_SIZE];
+	int		 nr_entries;
+	int		 nr_groups;
+	int		 nr_fds;
+	int		 nr_mmaps;
+	size_t		 mmap_len;
+	int		 id_pos;
+	int		 is_pos;
+	u64		 combined_sample_type;
+	struct {
+		int	cork_fd;
+		pid_t	pid;
+	} workload;
+	bool		 overwrite;
+	struct perf_mmap *mmap;
+	struct pollfd	 *pollfd;
+	struct thread_map *threads;
+	struct cpu_map	  *cpus;
+	struct perf_evsel *selected;
+};
+
+struct perf_evsel_str_handler {
+	const char *name;
+	void	   *handler;
+};
+
+struct perf_evlist *perf_evlist__new(void);
+struct perf_evlist *perf_evlist__new_default(void);
+void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus,
+		       struct thread_map *threads);
+void perf_evlist__exit(struct perf_evlist *evlist);
+void perf_evlist__delete(struct perf_evlist *evlist);
+
+void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry);
+int perf_evlist__add_default(struct perf_evlist *evlist);
+int __perf_evlist__add_default_attrs(struct perf_evlist *evlist,
+				     struct perf_event_attr *attrs, size_t nr_attrs);
+
+#define perf_evlist__add_default_attrs(evlist, array) \
+	__perf_evlist__add_default_attrs(evlist, array, ARRAY_SIZE(array))
+
+int perf_evlist__add_newtp(struct perf_evlist *evlist,
+			   const char *sys, const char *name, void *handler);
+
+int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter);
+
+struct perf_evsel *
+perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id);
+
+struct perf_evsel *
+perf_evlist__find_tracepoint_by_name(struct perf_evlist *evlist,
+				     const char *name);
+
+void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel,
+			 int cpu, int thread, u64 id);
+
+void perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd);
+
+struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id);
+
+struct perf_sample_id *perf_evlist__id2sid(struct perf_evlist *evlist, u64 id);
+
+union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx);
+
+void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx);
+
+int perf_evlist__open(struct perf_evlist *evlist);
+void perf_evlist__close(struct perf_evlist *evlist);
+
+void perf_evlist__set_id_pos(struct perf_evlist *evlist);
+bool perf_can_sample_identifier(void);
+void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts);
+int record_opts__config(struct record_opts *opts);
+
+int perf_evlist__prepare_workload(struct perf_evlist *evlist,
+				  struct target *target,
+				  const char *argv[], bool pipe_output,
+				  void (*exec_error)(int signo, siginfo_t *info,
+						     void *ucontext));
+int perf_evlist__start_workload(struct perf_evlist *evlist);
+
+int perf_evlist__parse_mmap_pages(const struct option *opt,
+				  const char *str,
+				  int unset);
+
+int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
+		      bool overwrite);
+void perf_evlist__munmap(struct perf_evlist *evlist);
+
+void perf_evlist__disable(struct perf_evlist *evlist);
+void perf_evlist__enable(struct perf_evlist *evlist);
+
+int perf_evlist__disable_event(struct perf_evlist *evlist,
+			       struct perf_evsel *evsel);
+int perf_evlist__enable_event(struct perf_evlist *evlist,
+			      struct perf_evsel *evsel);
+
+void perf_evlist__set_selected(struct perf_evlist *evlist,
+			       struct perf_evsel *evsel);
+
+static inline void perf_evlist__set_maps(struct perf_evlist *evlist,
+					 struct cpu_map *cpus,
+					 struct thread_map *threads)
+{
+	evlist->cpus	= cpus;
+	evlist->threads	= threads;
+}
+
+int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target);
+int perf_evlist__apply_filters(struct perf_evlist *evlist);
+
+void __perf_evlist__set_leader(struct list_head *list);
+void perf_evlist__set_leader(struct perf_evlist *evlist);
+
+u64 perf_evlist__read_format(struct perf_evlist *evlist);
+u64 __perf_evlist__combined_sample_type(struct perf_evlist *evlist);
+u64 perf_evlist__combined_sample_type(struct perf_evlist *evlist);
+bool perf_evlist__sample_id_all(struct perf_evlist *evlist);
+u16 perf_evlist__id_hdr_size(struct perf_evlist *evlist);
+
+int perf_evlist__parse_sample(struct perf_evlist *evlist, union perf_event *event,
+			      struct perf_sample *sample);
+
+bool perf_evlist__valid_sample_type(struct perf_evlist *evlist);
+bool perf_evlist__valid_sample_id_all(struct perf_evlist *evlist);
+bool perf_evlist__valid_read_format(struct perf_evlist *evlist);
+
+void perf_evlist__splice_list_tail(struct perf_evlist *evlist,
+				   struct list_head *list,
+				   int nr_entries);
+
+static inline struct perf_evsel *perf_evlist__first(struct perf_evlist *evlist)
+{
+	return list_entry(evlist->entries.next, struct perf_evsel, node);
+}
+
+static inline struct perf_evsel *perf_evlist__last(struct perf_evlist *evlist)
+{
+	return list_entry(evlist->entries.prev, struct perf_evsel, node);
+}
+
+size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp);
+
+int perf_evlist__strerror_tp(struct perf_evlist *evlist, int err, char *buf, size_t size);
+int perf_evlist__strerror_open(struct perf_evlist *evlist, int err, char *buf, size_t size);
+
+static inline unsigned int perf_mmap__read_head(struct perf_mmap *mm)
+{
+	struct perf_event_mmap_page *pc = mm->base;
+	int head = ACCESS_ONCE(pc->data_head);
+	rmb();
+	return head;
+}
+
+static inline void perf_mmap__write_tail(struct perf_mmap *md,
+					 unsigned long tail)
+{
+	struct perf_event_mmap_page *pc = md->base;
+
+	/*
+	 * ensure all reads are done before we write the tail out.
+	 */
+	mb();
+	pc->data_tail = tail;
+}
+
+bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str);
+void perf_evlist__to_front(struct perf_evlist *evlist,
+			   struct perf_evsel *move_evsel);
+
+/**
+ * __evlist__for_each - iterate thru all the evsels
+ * @list: list_head instance to iterate
+ * @evsel: struct evsel iterator
+ */
+#define __evlist__for_each(list, evsel) \
+        list_for_each_entry(evsel, list, node)
+
+/**
+ * evlist__for_each - iterate thru all the evsels
+ * @evlist: evlist instance to iterate
+ * @evsel: struct evsel iterator
+ */
+#define evlist__for_each(evlist, evsel) \
+	__evlist__for_each(&(evlist)->entries, evsel)
+
+/**
+ * __evlist__for_each_continue - continue iteration thru all the evsels
+ * @list: list_head instance to iterate
+ * @evsel: struct evsel iterator
+ */
+#define __evlist__for_each_continue(list, evsel) \
+        list_for_each_entry_continue(evsel, list, node)
+
+/**
+ * evlist__for_each_continue - continue iteration thru all the evsels
+ * @evlist: evlist instance to iterate
+ * @evsel: struct evsel iterator
+ */
+#define evlist__for_each_continue(evlist, evsel) \
+	__evlist__for_each_continue(&(evlist)->entries, evsel)
+
+/**
+ * __evlist__for_each_reverse - iterate thru all the evsels in reverse order
+ * @list: list_head instance to iterate
+ * @evsel: struct evsel iterator
+ */
+#define __evlist__for_each_reverse(list, evsel) \
+        list_for_each_entry_reverse(evsel, list, node)
+
+/**
+ * evlist__for_each_reverse - iterate thru all the evsels in reverse order
+ * @evlist: evlist instance to iterate
+ * @evsel: struct evsel iterator
+ */
+#define evlist__for_each_reverse(evlist, evsel) \
+	__evlist__for_each_reverse(&(evlist)->entries, evsel)
+
+/**
+ * __evlist__for_each_safe - safely iterate thru all the evsels
+ * @list: list_head instance to iterate
+ * @tmp: struct evsel temp iterator
+ * @evsel: struct evsel iterator
+ */
+#define __evlist__for_each_safe(list, tmp, evsel) \
+        list_for_each_entry_safe(evsel, tmp, list, node)
+
+/**
+ * evlist__for_each_safe - safely iterate thru all the evsels
+ * @evlist: evlist instance to iterate
+ * @evsel: struct evsel iterator
+ * @tmp: struct evsel temp iterator
+ */
+#define evlist__for_each_safe(evlist, tmp, evsel) \
+	__evlist__for_each_safe(&(evlist)->entries, tmp, evsel)
+
+#endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
new file mode 100644
index 00000000000..8606175fe1e
--- /dev/null
+++ b/tools/perf/util/evsel.c
@@ -0,0 +1,2036 @@
+/*
+ * Copyright (C) 2011, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Parts came from builtin-{top,stat,record}.c, see those files for further
+ * copyright notes.
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+
+#include <byteswap.h>
+#include <linux/bitops.h>
+#include <api/fs/debugfs.h>
+#include <traceevent/event-parse.h>
+#include <linux/hw_breakpoint.h>
+#include <linux/perf_event.h>
+#include <sys/resource.h>
+#include "asm/bug.h"
+#include "evsel.h"
+#include "evlist.h"
+#include "util.h"
+#include "cpumap.h"
+#include "thread_map.h"
+#include "target.h"
+#include "perf_regs.h"
+#include "debug.h"
+#include "trace-event.h"
+
+static struct {
+	bool sample_id_all;
+	bool exclude_guest;
+	bool mmap2;
+} perf_missing_features;
+
+#define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
+
+int __perf_evsel__sample_size(u64 sample_type)
+{
+	u64 mask = sample_type & PERF_SAMPLE_MASK;
+	int size = 0;
+	int i;
+
+	for (i = 0; i < 64; i++) {
+		if (mask & (1ULL << i))
+			size++;
+	}
+
+	size *= sizeof(u64);
+
+	return size;
+}
+
+/**
+ * __perf_evsel__calc_id_pos - calculate id_pos.
+ * @sample_type: sample type
+ *
+ * This function returns the position of the event id (PERF_SAMPLE_ID or
+ * PERF_SAMPLE_IDENTIFIER) in a sample event i.e. in the array of struct
+ * sample_event.
+ */
+static int __perf_evsel__calc_id_pos(u64 sample_type)
+{
+	int idx = 0;
+
+	if (sample_type & PERF_SAMPLE_IDENTIFIER)
+		return 0;
+
+	if (!(sample_type & PERF_SAMPLE_ID))
+		return -1;
+
+	if (sample_type & PERF_SAMPLE_IP)
+		idx += 1;
+
+	if (sample_type & PERF_SAMPLE_TID)
+		idx += 1;
+
+	if (sample_type & PERF_SAMPLE_TIME)
+		idx += 1;
+
+	if (sample_type & PERF_SAMPLE_ADDR)
+		idx += 1;
+
+	return idx;
+}
+
+/**
+ * __perf_evsel__calc_is_pos - calculate is_pos.
+ * @sample_type: sample type
+ *
+ * This function returns the position (counting backwards) of the event id
+ * (PERF_SAMPLE_ID or PERF_SAMPLE_IDENTIFIER) in a non-sample event i.e. if
+ * sample_id_all is used there is an id sample appended to non-sample events.
+ */
+static int __perf_evsel__calc_is_pos(u64 sample_type)
+{
+	int idx = 1;
+
+	if (sample_type & PERF_SAMPLE_IDENTIFIER)
+		return 1;
+
+	if (!(sample_type & PERF_SAMPLE_ID))
+		return -1;
+
+	if (sample_type & PERF_SAMPLE_CPU)
+		idx += 1;
+
+	if (sample_type & PERF_SAMPLE_STREAM_ID)
+		idx += 1;
+
+	return idx;
+}
+
+void perf_evsel__calc_id_pos(struct perf_evsel *evsel)
+{
+	evsel->id_pos = __perf_evsel__calc_id_pos(evsel->attr.sample_type);
+	evsel->is_pos = __perf_evsel__calc_is_pos(evsel->attr.sample_type);
+}
+
+void hists__init(struct hists *hists)
+{
+	memset(hists, 0, sizeof(*hists));
+	hists->entries_in_array[0] = hists->entries_in_array[1] = RB_ROOT;
+	hists->entries_in = &hists->entries_in_array[0];
+	hists->entries_collapsed = RB_ROOT;
+	hists->entries = RB_ROOT;
+	pthread_mutex_init(&hists->lock, NULL);
+}
+
+void __perf_evsel__set_sample_bit(struct perf_evsel *evsel,
+				  enum perf_event_sample_format bit)
+{
+	if (!(evsel->attr.sample_type & bit)) {
+		evsel->attr.sample_type |= bit;
+		evsel->sample_size += sizeof(u64);
+		perf_evsel__calc_id_pos(evsel);
+	}
+}
+
+void __perf_evsel__reset_sample_bit(struct perf_evsel *evsel,
+				    enum perf_event_sample_format bit)
+{
+	if (evsel->attr.sample_type & bit) {
+		evsel->attr.sample_type &= ~bit;
+		evsel->sample_size -= sizeof(u64);
+		perf_evsel__calc_id_pos(evsel);
+	}
+}
+
+void perf_evsel__set_sample_id(struct perf_evsel *evsel,
+			       bool can_sample_identifier)
+{
+	if (can_sample_identifier) {
+		perf_evsel__reset_sample_bit(evsel, ID);
+		perf_evsel__set_sample_bit(evsel, IDENTIFIER);
+	} else {
+		perf_evsel__set_sample_bit(evsel, ID);
+	}
+	evsel->attr.read_format |= PERF_FORMAT_ID;
+}
+
+void perf_evsel__init(struct perf_evsel *evsel,
+		      struct perf_event_attr *attr, int idx)
+{
+	evsel->idx	   = idx;
+	evsel->attr	   = *attr;
+	evsel->leader	   = evsel;
+	evsel->unit	   = "";
+	evsel->scale	   = 1.0;
+	INIT_LIST_HEAD(&evsel->node);
+	hists__init(&evsel->hists);
+	evsel->sample_size = __perf_evsel__sample_size(attr->sample_type);
+	perf_evsel__calc_id_pos(evsel);
+}
+
+struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
+{
+	struct perf_evsel *evsel = zalloc(sizeof(*evsel));
+
+	if (evsel != NULL)
+		perf_evsel__init(evsel, attr, idx);
+
+	return evsel;
+}
+
+struct perf_evsel *perf_evsel__newtp_idx(const char *sys, const char *name, int idx)
+{
+	struct perf_evsel *evsel = zalloc(sizeof(*evsel));
+
+	if (evsel != NULL) {
+		struct perf_event_attr attr = {
+			.type	       = PERF_TYPE_TRACEPOINT,
+			.sample_type   = (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME |
+					  PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD),
+		};
+
+		if (asprintf(&evsel->name, "%s:%s", sys, name) < 0)
+			goto out_free;
+
+		evsel->tp_format = trace_event__tp_format(sys, name);
+		if (evsel->tp_format == NULL)
+			goto out_free;
+
+		event_attr_init(&attr);
+		attr.config = evsel->tp_format->id;
+		attr.sample_period = 1;
+		perf_evsel__init(evsel, &attr, idx);
+	}
+
+	return evsel;
+
+out_free:
+	zfree(&evsel->name);
+	free(evsel);
+	return NULL;
+}
+
+const char *perf_evsel__hw_names[PERF_COUNT_HW_MAX] = {
+	"cycles",
+	"instructions",
+	"cache-references",
+	"cache-misses",
+	"branches",
+	"branch-misses",
+	"bus-cycles",
+	"stalled-cycles-frontend",
+	"stalled-cycles-backend",
+	"ref-cycles",
+};
+
+static const char *__perf_evsel__hw_name(u64 config)
+{
+	if (config < PERF_COUNT_HW_MAX && perf_evsel__hw_names[config])
+		return perf_evsel__hw_names[config];
+
+	return "unknown-hardware";
+}
+
+static int perf_evsel__add_modifiers(struct perf_evsel *evsel, char *bf, size_t size)
+{
+	int colon = 0, r = 0;
+	struct perf_event_attr *attr = &evsel->attr;
+	bool exclude_guest_default = false;
+
+#define MOD_PRINT(context, mod)	do {					\
+		if (!attr->exclude_##context) {				\
+			if (!colon) colon = ++r;			\
+			r += scnprintf(bf + r, size - r, "%c", mod);	\
+		} } while(0)
+
+	if (attr->exclude_kernel || attr->exclude_user || attr->exclude_hv) {
+		MOD_PRINT(kernel, 'k');
+		MOD_PRINT(user, 'u');
+		MOD_PRINT(hv, 'h');
+		exclude_guest_default = true;
+	}
+
+	if (attr->precise_ip) {
+		if (!colon)
+			colon = ++r;
+		r += scnprintf(bf + r, size - r, "%.*s", attr->precise_ip, "ppp");
+		exclude_guest_default = true;
+	}
+
+	if (attr->exclude_host || attr->exclude_guest == exclude_guest_default) {
+		MOD_PRINT(host, 'H');
+		MOD_PRINT(guest, 'G');
+	}
+#undef MOD_PRINT
+	if (colon)
+		bf[colon - 1] = ':';
+	return r;
+}
+
+static int perf_evsel__hw_name(struct perf_evsel *evsel, char *bf, size_t size)
+{
+	int r = scnprintf(bf, size, "%s", __perf_evsel__hw_name(evsel->attr.config));
+	return r + perf_evsel__add_modifiers(evsel, bf + r, size - r);
+}
+
+const char *perf_evsel__sw_names[PERF_COUNT_SW_MAX] = {
+	"cpu-clock",
+	"task-clock",
+	"page-faults",
+	"context-switches",
+	"cpu-migrations",
+	"minor-faults",
+	"major-faults",
+	"alignment-faults",
+	"emulation-faults",
+	"dummy",
+};
+
+static const char *__perf_evsel__sw_name(u64 config)
+{
+	if (config < PERF_COUNT_SW_MAX && perf_evsel__sw_names[config])
+		return perf_evsel__sw_names[config];
+	return "unknown-software";
+}
+
+static int perf_evsel__sw_name(struct perf_evsel *evsel, char *bf, size_t size)
+{
+	int r = scnprintf(bf, size, "%s", __perf_evsel__sw_name(evsel->attr.config));
+	return r + perf_evsel__add_modifiers(evsel, bf + r, size - r);
+}
+
+static int __perf_evsel__bp_name(char *bf, size_t size, u64 addr, u64 type)
+{
+	int r;
+
+	r = scnprintf(bf, size, "mem:0x%" PRIx64 ":", addr);
+
+	if (type & HW_BREAKPOINT_R)
+		r += scnprintf(bf + r, size - r, "r");
+
+	if (type & HW_BREAKPOINT_W)
+		r += scnprintf(bf + r, size - r, "w");
+
+	if (type & HW_BREAKPOINT_X)
+		r += scnprintf(bf + r, size - r, "x");
+
+	return r;
+}
+
+static int perf_evsel__bp_name(struct perf_evsel *evsel, char *bf, size_t size)
+{
+	struct perf_event_attr *attr = &evsel->attr;
+	int r = __perf_evsel__bp_name(bf, size, attr->bp_addr, attr->bp_type);
+	return r + perf_evsel__add_modifiers(evsel, bf + r, size - r);
+}
+
+const char *perf_evsel__hw_cache[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_EVSEL__MAX_ALIASES] = {
+ { "L1-dcache",	"l1-d",		"l1d",		"L1-data",		},
+ { "L1-icache",	"l1-i",		"l1i",		"L1-instruction",	},
+ { "LLC",	"L2",							},
+ { "dTLB",	"d-tlb",	"Data-TLB",				},
+ { "iTLB",	"i-tlb",	"Instruction-TLB",			},
+ { "branch",	"branches",	"bpu",		"btb",		"bpc",	},
+ { "node",								},
+};
+
+const char *perf_evsel__hw_cache_op[PERF_COUNT_HW_CACHE_OP_MAX]
+				   [PERF_EVSEL__MAX_ALIASES] = {
+ { "load",	"loads",	"read",					},
+ { "store",	"stores",	"write",				},
+ { "prefetch",	"prefetches",	"speculative-read", "speculative-load",	},
+};
+
+const char *perf_evsel__hw_cache_result[PERF_COUNT_HW_CACHE_RESULT_MAX]
+				       [PERF_EVSEL__MAX_ALIASES] = {
+ { "refs",	"Reference",	"ops",		"access",		},
+ { "misses",	"miss",							},
+};
+
+#define C(x)		PERF_COUNT_HW_CACHE_##x
+#define CACHE_READ	(1 << C(OP_READ))
+#define CACHE_WRITE	(1 << C(OP_WRITE))
+#define CACHE_PREFETCH	(1 << C(OP_PREFETCH))
+#define COP(x)		(1 << x)
+
+/*
+ * cache operartion stat
+ * L1I : Read and prefetch only
+ * ITLB and BPU : Read-only
+ */
+static unsigned long perf_evsel__hw_cache_stat[C(MAX)] = {
+ [C(L1D)]	= (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH),
+ [C(L1I)]	= (CACHE_READ | CACHE_PREFETCH),
+ [C(LL)]	= (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH),
+ [C(DTLB)]	= (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH),
+ [C(ITLB)]	= (CACHE_READ),
+ [C(BPU)]	= (CACHE_READ),
+ [C(NODE)]	= (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH),
+};
+
+bool perf_evsel__is_cache_op_valid(u8 type, u8 op)
+{
+	if (perf_evsel__hw_cache_stat[type] & COP(op))
+		return true;	/* valid */
+	else
+		return false;	/* invalid */
+}
+
+int __perf_evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result,
+					    char *bf, size_t size)
+{
+	if (result) {
+		return scnprintf(bf, size, "%s-%s-%s", perf_evsel__hw_cache[type][0],
+				 perf_evsel__hw_cache_op[op][0],
+				 perf_evsel__hw_cache_result[result][0]);
+	}
+
+	return scnprintf(bf, size, "%s-%s", perf_evsel__hw_cache[type][0],
+			 perf_evsel__hw_cache_op[op][1]);
+}
+
+static int __perf_evsel__hw_cache_name(u64 config, char *bf, size_t size)
+{
+	u8 op, result, type = (config >>  0) & 0xff;
+	const char *err = "unknown-ext-hardware-cache-type";
+
+	if (type > PERF_COUNT_HW_CACHE_MAX)
+		goto out_err;
+
+	op = (config >>  8) & 0xff;
+	err = "unknown-ext-hardware-cache-op";
+	if (op > PERF_COUNT_HW_CACHE_OP_MAX)
+		goto out_err;
+
+	result = (config >> 16) & 0xff;
+	err = "unknown-ext-hardware-cache-result";
+	if (result > PERF_COUNT_HW_CACHE_RESULT_MAX)
+		goto out_err;
+
+	err = "invalid-cache";
+	if (!perf_evsel__is_cache_op_valid(type, op))
+		goto out_err;
+
+	return __perf_evsel__hw_cache_type_op_res_name(type, op, result, bf, size);
+out_err:
+	return scnprintf(bf, size, "%s", err);
+}
+
+static int perf_evsel__hw_cache_name(struct perf_evsel *evsel, char *bf, size_t size)
+{
+	int ret = __perf_evsel__hw_cache_name(evsel->attr.config, bf, size);
+	return ret + perf_evsel__add_modifiers(evsel, bf + ret, size - ret);
+}
+
+static int perf_evsel__raw_name(struct perf_evsel *evsel, char *bf, size_t size)
+{
+	int ret = scnprintf(bf, size, "raw 0x%" PRIx64, evsel->attr.config);
+	return ret + perf_evsel__add_modifiers(evsel, bf + ret, size - ret);
+}
+
+const char *perf_evsel__name(struct perf_evsel *evsel)
+{
+	char bf[128];
+
+	if (evsel->name)
+		return evsel->name;
+
+	switch (evsel->attr.type) {
+	case PERF_TYPE_RAW:
+		perf_evsel__raw_name(evsel, bf, sizeof(bf));
+		break;
+
+	case PERF_TYPE_HARDWARE:
+		perf_evsel__hw_name(evsel, bf, sizeof(bf));
+		break;
+
+	case PERF_TYPE_HW_CACHE:
+		perf_evsel__hw_cache_name(evsel, bf, sizeof(bf));
+		break;
+
+	case PERF_TYPE_SOFTWARE:
+		perf_evsel__sw_name(evsel, bf, sizeof(bf));
+		break;
+
+	case PERF_TYPE_TRACEPOINT:
+		scnprintf(bf, sizeof(bf), "%s", "unknown tracepoint");
+		break;
+
+	case PERF_TYPE_BREAKPOINT:
+		perf_evsel__bp_name(evsel, bf, sizeof(bf));
+		break;
+
+	default:
+		scnprintf(bf, sizeof(bf), "unknown attr type: %d",
+			  evsel->attr.type);
+		break;
+	}
+
+	evsel->name = strdup(bf);
+
+	return evsel->name ?: "unknown";
+}
+
+const char *perf_evsel__group_name(struct perf_evsel *evsel)
+{
+	return evsel->group_name ?: "anon group";
+}
+
+int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size)
+{
+	int ret;
+	struct perf_evsel *pos;
+	const char *group_name = perf_evsel__group_name(evsel);
+
+	ret = scnprintf(buf, size, "%s", group_name);
+
+	ret += scnprintf(buf + ret, size - ret, " { %s",
+			 perf_evsel__name(evsel));
+
+	for_each_group_member(pos, evsel)
+		ret += scnprintf(buf + ret, size - ret, ", %s",
+				 perf_evsel__name(pos));
+
+	ret += scnprintf(buf + ret, size - ret, " }");
+
+	return ret;
+}
+
+static void
+perf_evsel__config_callgraph(struct perf_evsel *evsel,
+			     struct record_opts *opts)
+{
+	bool function = perf_evsel__is_function_event(evsel);
+	struct perf_event_attr *attr = &evsel->attr;
+
+	perf_evsel__set_sample_bit(evsel, CALLCHAIN);
+
+	if (opts->call_graph == CALLCHAIN_DWARF) {
+		if (!function) {
+			perf_evsel__set_sample_bit(evsel, REGS_USER);
+			perf_evsel__set_sample_bit(evsel, STACK_USER);
+			attr->sample_regs_user = PERF_REGS_MASK;
+			attr->sample_stack_user = opts->stack_dump_size;
+			attr->exclude_callchain_user = 1;
+		} else {
+			pr_info("Cannot use DWARF unwind for function trace event,"
+				" falling back to framepointers.\n");
+		}
+	}
+
+	if (function) {
+		pr_info("Disabling user space callchains for function trace event.\n");
+		attr->exclude_callchain_user = 1;
+	}
+}
+
+/*
+ * The enable_on_exec/disabled value strategy:
+ *
+ *  1) For any type of traced program:
+ *    - all independent events and group leaders are disabled
+ *    - all group members are enabled
+ *
+ *     Group members are ruled by group leaders. They need to
+ *     be enabled, because the group scheduling relies on that.
+ *
+ *  2) For traced programs executed by perf:
+ *     - all independent events and group leaders have
+ *       enable_on_exec set
+ *     - we don't specifically enable or disable any event during
+ *       the record command
+ *
+ *     Independent events and group leaders are initially disabled
+ *     and get enabled by exec. Group members are ruled by group
+ *     leaders as stated in 1).
+ *
+ *  3) For traced programs attached by perf (pid/tid):
+ *     - we specifically enable or disable all events during
+ *       the record command
+ *
+ *     When attaching events to already running traced we
+ *     enable/disable events specifically, as there's no
+ *     initial traced exec call.
+ */
+void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
+{
+	struct perf_evsel *leader = evsel->leader;
+	struct perf_event_attr *attr = &evsel->attr;
+	int track = !evsel->idx; /* only the first counter needs these */
+	bool per_cpu = opts->target.default_per_cpu && !opts->target.per_thread;
+
+	attr->sample_id_all = perf_missing_features.sample_id_all ? 0 : 1;
+	attr->inherit	    = !opts->no_inherit;
+
+	perf_evsel__set_sample_bit(evsel, IP);
+	perf_evsel__set_sample_bit(evsel, TID);
+
+	if (evsel->sample_read) {
+		perf_evsel__set_sample_bit(evsel, READ);
+
+		/*
+		 * We need ID even in case of single event, because
+		 * PERF_SAMPLE_READ process ID specific data.
+		 */
+		perf_evsel__set_sample_id(evsel, false);
+
+		/*
+		 * Apply group format only if we belong to group
+		 * with more than one members.
+		 */
+		if (leader->nr_members > 1) {
+			attr->read_format |= PERF_FORMAT_GROUP;
+			attr->inherit = 0;
+		}
+	}
+
+	/*
+	 * We default some events to have a default interval. But keep
+	 * it a weak assumption overridable by the user.
+	 */
+	if (!attr->sample_period || (opts->user_freq != UINT_MAX ||
+				     opts->user_interval != ULLONG_MAX)) {
+		if (opts->freq) {
+			perf_evsel__set_sample_bit(evsel, PERIOD);
+			attr->freq		= 1;
+			attr->sample_freq	= opts->freq;
+		} else {
+			attr->sample_period = opts->default_interval;
+		}
+	}
+
+	/*
+	 * Disable sampling for all group members other
+	 * than leader in case leader 'leads' the sampling.
+	 */
+	if ((leader != evsel) && leader->sample_read) {
+		attr->sample_freq   = 0;
+		attr->sample_period = 0;
+	}
+
+	if (opts->no_samples)
+		attr->sample_freq = 0;
+
+	if (opts->inherit_stat)
+		attr->inherit_stat = 1;
+
+	if (opts->sample_address) {
+		perf_evsel__set_sample_bit(evsel, ADDR);
+		attr->mmap_data = track;
+	}
+
+	if (opts->call_graph_enabled)
+		perf_evsel__config_callgraph(evsel, opts);
+
+	if (target__has_cpu(&opts->target))
+		perf_evsel__set_sample_bit(evsel, CPU);
+
+	if (opts->period)
+		perf_evsel__set_sample_bit(evsel, PERIOD);
+
+	if (!perf_missing_features.sample_id_all &&
+	    (opts->sample_time || !opts->no_inherit ||
+	     target__has_cpu(&opts->target) || per_cpu))
+		perf_evsel__set_sample_bit(evsel, TIME);
+
+	if (opts->raw_samples) {
+		perf_evsel__set_sample_bit(evsel, TIME);
+		perf_evsel__set_sample_bit(evsel, RAW);
+		perf_evsel__set_sample_bit(evsel, CPU);
+	}
+
+	if (opts->sample_address)
+		perf_evsel__set_sample_bit(evsel, DATA_SRC);
+
+	if (opts->no_buffering) {
+		attr->watermark = 0;
+		attr->wakeup_events = 1;
+	}
+	if (opts->branch_stack) {
+		perf_evsel__set_sample_bit(evsel, BRANCH_STACK);
+		attr->branch_sample_type = opts->branch_stack;
+	}
+
+	if (opts->sample_weight)
+		perf_evsel__set_sample_bit(evsel, WEIGHT);
+
+	attr->mmap  = track;
+	attr->mmap2 = track && !perf_missing_features.mmap2;
+	attr->comm  = track;
+
+	if (opts->sample_transaction)
+		perf_evsel__set_sample_bit(evsel, TRANSACTION);
+
+	/*
+	 * XXX see the function comment above
+	 *
+	 * Disabling only independent events or group leaders,
+	 * keeping group members enabled.
+	 */
+	if (perf_evsel__is_group_leader(evsel))
+		attr->disabled = 1;
+
+	/*
+	 * Setting enable_on_exec for independent events and
+	 * group leaders for traced executed by perf.
+	 */
+	if (target__none(&opts->target) && perf_evsel__is_group_leader(evsel) &&
+		!opts->initial_delay)
+		attr->enable_on_exec = 1;
+}
+
+int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
+{
+	int cpu, thread;
+	evsel->fd = xyarray__new(ncpus, nthreads, sizeof(int));
+
+	if (evsel->fd) {
+		for (cpu = 0; cpu < ncpus; cpu++) {
+			for (thread = 0; thread < nthreads; thread++) {
+				FD(evsel, cpu, thread) = -1;
+			}
+		}
+	}
+
+	return evsel->fd != NULL ? 0 : -ENOMEM;
+}
+
+static int perf_evsel__run_ioctl(struct perf_evsel *evsel, int ncpus, int nthreads,
+			  int ioc,  void *arg)
+{
+	int cpu, thread;
+
+	for (cpu = 0; cpu < ncpus; cpu++) {
+		for (thread = 0; thread < nthreads; thread++) {
+			int fd = FD(evsel, cpu, thread),
+			    err = ioctl(fd, ioc, arg);
+
+			if (err)
+				return err;
+		}
+	}
+
+	return 0;
+}
+
+int perf_evsel__set_filter(struct perf_evsel *evsel, int ncpus, int nthreads,
+			   const char *filter)
+{
+	return perf_evsel__run_ioctl(evsel, ncpus, nthreads,
+				     PERF_EVENT_IOC_SET_FILTER,
+				     (void *)filter);
+}
+
+int perf_evsel__enable(struct perf_evsel *evsel, int ncpus, int nthreads)
+{
+	return perf_evsel__run_ioctl(evsel, ncpus, nthreads,
+				     PERF_EVENT_IOC_ENABLE,
+				     0);
+}
+
+int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads)
+{
+	evsel->sample_id = xyarray__new(ncpus, nthreads, sizeof(struct perf_sample_id));
+	if (evsel->sample_id == NULL)
+		return -ENOMEM;
+
+	evsel->id = zalloc(ncpus * nthreads * sizeof(u64));
+	if (evsel->id == NULL) {
+		xyarray__delete(evsel->sample_id);
+		evsel->sample_id = NULL;
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+void perf_evsel__reset_counts(struct perf_evsel *evsel, int ncpus)
+{
+	memset(evsel->counts, 0, (sizeof(*evsel->counts) +
+				 (ncpus * sizeof(struct perf_counts_values))));
+}
+
+int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus)
+{
+	evsel->counts = zalloc((sizeof(*evsel->counts) +
+				(ncpus * sizeof(struct perf_counts_values))));
+	return evsel->counts != NULL ? 0 : -ENOMEM;
+}
+
+void perf_evsel__free_fd(struct perf_evsel *evsel)
+{
+	xyarray__delete(evsel->fd);
+	evsel->fd = NULL;
+}
+
+void perf_evsel__free_id(struct perf_evsel *evsel)
+{
+	xyarray__delete(evsel->sample_id);
+	evsel->sample_id = NULL;
+	zfree(&evsel->id);
+}
+
+void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
+{
+	int cpu, thread;
+
+	for (cpu = 0; cpu < ncpus; cpu++)
+		for (thread = 0; thread < nthreads; ++thread) {
+			close(FD(evsel, cpu, thread));
+			FD(evsel, cpu, thread) = -1;
+		}
+}
+
+void perf_evsel__free_counts(struct perf_evsel *evsel)
+{
+	zfree(&evsel->counts);
+}
+
+void perf_evsel__exit(struct perf_evsel *evsel)
+{
+	assert(list_empty(&evsel->node));
+	perf_evsel__free_fd(evsel);
+	perf_evsel__free_id(evsel);
+}
+
+void perf_evsel__delete(struct perf_evsel *evsel)
+{
+	perf_evsel__exit(evsel);
+	close_cgroup(evsel->cgrp);
+	zfree(&evsel->group_name);
+	if (evsel->tp_format)
+		pevent_free_format(evsel->tp_format);
+	zfree(&evsel->name);
+	free(evsel);
+}
+
+static inline void compute_deltas(struct perf_evsel *evsel,
+				  int cpu,
+				  struct perf_counts_values *count)
+{
+	struct perf_counts_values tmp;
+
+	if (!evsel->prev_raw_counts)
+		return;
+
+	if (cpu == -1) {
+		tmp = evsel->prev_raw_counts->aggr;
+		evsel->prev_raw_counts->aggr = *count;
+	} else {
+		tmp = evsel->prev_raw_counts->cpu[cpu];
+		evsel->prev_raw_counts->cpu[cpu] = *count;
+	}
+
+	count->val = count->val - tmp.val;
+	count->ena = count->ena - tmp.ena;
+	count->run = count->run - tmp.run;
+}
+
+int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
+			      int cpu, int thread, bool scale)
+{
+	struct perf_counts_values count;
+	size_t nv = scale ? 3 : 1;
+
+	if (FD(evsel, cpu, thread) < 0)
+		return -EINVAL;
+
+	if (evsel->counts == NULL && perf_evsel__alloc_counts(evsel, cpu + 1) < 0)
+		return -ENOMEM;
+
+	if (readn(FD(evsel, cpu, thread), &count, nv * sizeof(u64)) < 0)
+		return -errno;
+
+	compute_deltas(evsel, cpu, &count);
+
+	if (scale) {
+		if (count.run == 0)
+			count.val = 0;
+		else if (count.run < count.ena)
+			count.val = (u64)((double)count.val * count.ena / count.run + 0.5);
+	} else
+		count.ena = count.run = 0;
+
+	evsel->counts->cpu[cpu] = count;
+	return 0;
+}
+
+int __perf_evsel__read(struct perf_evsel *evsel,
+		       int ncpus, int nthreads, bool scale)
+{
+	size_t nv = scale ? 3 : 1;
+	int cpu, thread;
+	struct perf_counts_values *aggr = &evsel->counts->aggr, count;
+
+	aggr->val = aggr->ena = aggr->run = 0;
+
+	for (cpu = 0; cpu < ncpus; cpu++) {
+		for (thread = 0; thread < nthreads; thread++) {
+			if (FD(evsel, cpu, thread) < 0)
+				continue;
+
+			if (readn(FD(evsel, cpu, thread),
+				  &count, nv * sizeof(u64)) < 0)
+				return -errno;
+
+			aggr->val += count.val;
+			if (scale) {
+				aggr->ena += count.ena;
+				aggr->run += count.run;
+			}
+		}
+	}
+
+	compute_deltas(evsel, -1, aggr);
+
+	evsel->counts->scaled = 0;
+	if (scale) {
+		if (aggr->run == 0) {
+			evsel->counts->scaled = -1;
+			aggr->val = 0;
+			return 0;
+		}
+
+		if (aggr->run < aggr->ena) {
+			evsel->counts->scaled = 1;
+			aggr->val = (u64)((double)aggr->val * aggr->ena / aggr->run + 0.5);
+		}
+	} else
+		aggr->ena = aggr->run = 0;
+
+	return 0;
+}
+
+static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread)
+{
+	struct perf_evsel *leader = evsel->leader;
+	int fd;
+
+	if (perf_evsel__is_group_leader(evsel))
+		return -1;
+
+	/*
+	 * Leader must be already processed/open,
+	 * if not it's a bug.
+	 */
+	BUG_ON(!leader->fd);
+
+	fd = FD(leader, cpu, thread);
+	BUG_ON(fd == -1);
+
+	return fd;
+}
+
+#define __PRINT_ATTR(fmt, cast, field)  \
+	fprintf(fp, "  %-19s "fmt"\n", #field, cast attr->field)
+
+#define PRINT_ATTR_U32(field)  __PRINT_ATTR("%u" , , field)
+#define PRINT_ATTR_X32(field)  __PRINT_ATTR("%#x", , field)
+#define PRINT_ATTR_U64(field)  __PRINT_ATTR("%" PRIu64, (uint64_t), field)
+#define PRINT_ATTR_X64(field)  __PRINT_ATTR("%#"PRIx64, (uint64_t), field)
+
+#define PRINT_ATTR2N(name1, field1, name2, field2)	\
+	fprintf(fp, "  %-19s %u    %-19s %u\n",		\
+	name1, attr->field1, name2, attr->field2)
+
+#define PRINT_ATTR2(field1, field2) \
+	PRINT_ATTR2N(#field1, field1, #field2, field2)
+
+static size_t perf_event_attr__fprintf(struct perf_event_attr *attr, FILE *fp)
+{
+	size_t ret = 0;
+
+	ret += fprintf(fp, "%.60s\n", graph_dotted_line);
+	ret += fprintf(fp, "perf_event_attr:\n");
+
+	ret += PRINT_ATTR_U32(type);
+	ret += PRINT_ATTR_U32(size);
+	ret += PRINT_ATTR_X64(config);
+	ret += PRINT_ATTR_U64(sample_period);
+	ret += PRINT_ATTR_U64(sample_freq);
+	ret += PRINT_ATTR_X64(sample_type);
+	ret += PRINT_ATTR_X64(read_format);
+
+	ret += PRINT_ATTR2(disabled, inherit);
+	ret += PRINT_ATTR2(pinned, exclusive);
+	ret += PRINT_ATTR2(exclude_user, exclude_kernel);
+	ret += PRINT_ATTR2(exclude_hv, exclude_idle);
+	ret += PRINT_ATTR2(mmap, comm);
+	ret += PRINT_ATTR2(freq, inherit_stat);
+	ret += PRINT_ATTR2(enable_on_exec, task);
+	ret += PRINT_ATTR2(watermark, precise_ip);
+	ret += PRINT_ATTR2(mmap_data, sample_id_all);
+	ret += PRINT_ATTR2(exclude_host, exclude_guest);
+	ret += PRINT_ATTR2N("excl.callchain_kern", exclude_callchain_kernel,
+			    "excl.callchain_user", exclude_callchain_user);
+	ret += PRINT_ATTR_U32(mmap2);
+
+	ret += PRINT_ATTR_U32(wakeup_events);
+	ret += PRINT_ATTR_U32(wakeup_watermark);
+	ret += PRINT_ATTR_X32(bp_type);
+	ret += PRINT_ATTR_X64(bp_addr);
+	ret += PRINT_ATTR_X64(config1);
+	ret += PRINT_ATTR_U64(bp_len);
+	ret += PRINT_ATTR_X64(config2);
+	ret += PRINT_ATTR_X64(branch_sample_type);
+	ret += PRINT_ATTR_X64(sample_regs_user);
+	ret += PRINT_ATTR_U32(sample_stack_user);
+
+	ret += fprintf(fp, "%.60s\n", graph_dotted_line);
+
+	return ret;
+}
+
+static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
+			      struct thread_map *threads)
+{
+	int cpu, thread;
+	unsigned long flags = 0;
+	int pid = -1, err;
+	enum { NO_CHANGE, SET_TO_MAX, INCREASED_MAX } set_rlimit = NO_CHANGE;
+
+	if (evsel->fd == NULL &&
+	    perf_evsel__alloc_fd(evsel, cpus->nr, threads->nr) < 0)
+		return -ENOMEM;
+
+	if (evsel->cgrp) {
+		flags = PERF_FLAG_PID_CGROUP;
+		pid = evsel->cgrp->fd;
+	}
+
+fallback_missing_features:
+	if (perf_missing_features.mmap2)
+		evsel->attr.mmap2 = 0;
+	if (perf_missing_features.exclude_guest)
+		evsel->attr.exclude_guest = evsel->attr.exclude_host = 0;
+retry_sample_id:
+	if (perf_missing_features.sample_id_all)
+		evsel->attr.sample_id_all = 0;
+
+	if (verbose >= 2)
+		perf_event_attr__fprintf(&evsel->attr, stderr);
+
+	for (cpu = 0; cpu < cpus->nr; cpu++) {
+
+		for (thread = 0; thread < threads->nr; thread++) {
+			int group_fd;
+
+			if (!evsel->cgrp)
+				pid = threads->map[thread];
+
+			group_fd = get_group_fd(evsel, cpu, thread);
+retry_open:
+			pr_debug2("sys_perf_event_open: pid %d  cpu %d  group_fd %d  flags %#lx\n",
+				  pid, cpus->map[cpu], group_fd, flags);
+
+			FD(evsel, cpu, thread) = sys_perf_event_open(&evsel->attr,
+								     pid,
+								     cpus->map[cpu],
+								     group_fd, flags);
+			if (FD(evsel, cpu, thread) < 0) {
+				err = -errno;
+				pr_debug2("sys_perf_event_open failed, error %d\n",
+					  err);
+				goto try_fallback;
+			}
+			set_rlimit = NO_CHANGE;
+		}
+	}
+
+	return 0;
+
+try_fallback:
+	/*
+	 * perf stat needs between 5 and 22 fds per CPU. When we run out
+	 * of them try to increase the limits.
+	 */
+	if (err == -EMFILE && set_rlimit < INCREASED_MAX) {
+		struct rlimit l;
+		int old_errno = errno;
+
+		if (getrlimit(RLIMIT_NOFILE, &l) == 0) {
+			if (set_rlimit == NO_CHANGE)
+				l.rlim_cur = l.rlim_max;
+			else {
+				l.rlim_cur = l.rlim_max + 1000;
+				l.rlim_max = l.rlim_cur;
+			}
+			if (setrlimit(RLIMIT_NOFILE, &l) == 0) {
+				set_rlimit++;
+				errno = old_errno;
+				goto retry_open;
+			}
+		}
+		errno = old_errno;
+	}
+
+	if (err != -EINVAL || cpu > 0 || thread > 0)
+		goto out_close;
+
+	if (!perf_missing_features.mmap2 && evsel->attr.mmap2) {
+		perf_missing_features.mmap2 = true;
+		goto fallback_missing_features;
+	} else if (!perf_missing_features.exclude_guest &&
+		   (evsel->attr.exclude_guest || evsel->attr.exclude_host)) {
+		perf_missing_features.exclude_guest = true;
+		goto fallback_missing_features;
+	} else if (!perf_missing_features.sample_id_all) {
+		perf_missing_features.sample_id_all = true;
+		goto retry_sample_id;
+	}
+
+out_close:
+	do {
+		while (--thread >= 0) {
+			close(FD(evsel, cpu, thread));
+			FD(evsel, cpu, thread) = -1;
+		}
+		thread = threads->nr;
+	} while (--cpu >= 0);
+	return err;
+}
+
+void perf_evsel__close(struct perf_evsel *evsel, int ncpus, int nthreads)
+{
+	if (evsel->fd == NULL)
+		return;
+
+	perf_evsel__close_fd(evsel, ncpus, nthreads);
+	perf_evsel__free_fd(evsel);
+}
+
+static struct {
+	struct cpu_map map;
+	int cpus[1];
+} empty_cpu_map = {
+	.map.nr	= 1,
+	.cpus	= { -1, },
+};
+
+static struct {
+	struct thread_map map;
+	int threads[1];
+} empty_thread_map = {
+	.map.nr	 = 1,
+	.threads = { -1, },
+};
+
+int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
+		     struct thread_map *threads)
+{
+	if (cpus == NULL) {
+		/* Work around old compiler warnings about strict aliasing */
+		cpus = &empty_cpu_map.map;
+	}
+
+	if (threads == NULL)
+		threads = &empty_thread_map.map;
+
+	return __perf_evsel__open(evsel, cpus, threads);
+}
+
+int perf_evsel__open_per_cpu(struct perf_evsel *evsel,
+			     struct cpu_map *cpus)
+{
+	return __perf_evsel__open(evsel, cpus, &empty_thread_map.map);
+}
+
+int perf_evsel__open_per_thread(struct perf_evsel *evsel,
+				struct thread_map *threads)
+{
+	return __perf_evsel__open(evsel, &empty_cpu_map.map, threads);
+}
+
+static int perf_evsel__parse_id_sample(const struct perf_evsel *evsel,
+				       const union perf_event *event,
+				       struct perf_sample *sample)
+{
+	u64 type = evsel->attr.sample_type;
+	const u64 *array = event->sample.array;
+	bool swapped = evsel->needs_swap;
+	union u64_swap u;
+
+	array += ((event->header.size -
+		   sizeof(event->header)) / sizeof(u64)) - 1;
+
+	if (type & PERF_SAMPLE_IDENTIFIER) {
+		sample->id = *array;
+		array--;
+	}
+
+	if (type & PERF_SAMPLE_CPU) {
+		u.val64 = *array;
+		if (swapped) {
+			/* undo swap of u64, then swap on individual u32s */
+			u.val64 = bswap_64(u.val64);
+			u.val32[0] = bswap_32(u.val32[0]);
+		}
+
+		sample->cpu = u.val32[0];
+		array--;
+	}
+
+	if (type & PERF_SAMPLE_STREAM_ID) {
+		sample->stream_id = *array;
+		array--;
+	}
+
+	if (type & PERF_SAMPLE_ID) {
+		sample->id = *array;
+		array--;
+	}
+
+	if (type & PERF_SAMPLE_TIME) {
+		sample->time = *array;
+		array--;
+	}
+
+	if (type & PERF_SAMPLE_TID) {
+		u.val64 = *array;
+		if (swapped) {
+			/* undo swap of u64, then swap on individual u32s */
+			u.val64 = bswap_64(u.val64);
+			u.val32[0] = bswap_32(u.val32[0]);
+			u.val32[1] = bswap_32(u.val32[1]);
+		}
+
+		sample->pid = u.val32[0];
+		sample->tid = u.val32[1];
+		array--;
+	}
+
+	return 0;
+}
+
+static inline bool overflow(const void *endp, u16 max_size, const void *offset,
+			    u64 size)
+{
+	return size > max_size || offset + size > endp;
+}
+
+#define OVERFLOW_CHECK(offset, size, max_size)				\
+	do {								\
+		if (overflow(endp, (max_size), (offset), (size)))	\
+			return -EFAULT;					\
+	} while (0)
+
+#define OVERFLOW_CHECK_u64(offset) \
+	OVERFLOW_CHECK(offset, sizeof(u64), sizeof(u64))
+
+int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
+			     struct perf_sample *data)
+{
+	u64 type = evsel->attr.sample_type;
+	bool swapped = evsel->needs_swap;
+	const u64 *array;
+	u16 max_size = event->header.size;
+	const void *endp = (void *)event + max_size;
+	u64 sz;
+
+	/*
+	 * used for cross-endian analysis. See git commit 65014ab3
+	 * for why this goofiness is needed.
+	 */
+	union u64_swap u;
+
+	memset(data, 0, sizeof(*data));
+	data->cpu = data->pid = data->tid = -1;
+	data->stream_id = data->id = data->time = -1ULL;
+	data->period = evsel->attr.sample_period;
+	data->weight = 0;
+
+	if (event->header.type != PERF_RECORD_SAMPLE) {
+		if (!evsel->attr.sample_id_all)
+			return 0;
+		return perf_evsel__parse_id_sample(evsel, event, data);
+	}
+
+	array = event->sample.array;
+
+	/*
+	 * The evsel's sample_size is based on PERF_SAMPLE_MASK which includes
+	 * up to PERF_SAMPLE_PERIOD.  After that overflow() must be used to
+	 * check the format does not go past the end of the event.
+	 */
+	if (evsel->sample_size + sizeof(event->header) > event->header.size)
+		return -EFAULT;
+
+	data->id = -1ULL;
+	if (type & PERF_SAMPLE_IDENTIFIER) {
+		data->id = *array;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_IP) {
+		data->ip = *array;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_TID) {
+		u.val64 = *array;
+		if (swapped) {
+			/* undo swap of u64, then swap on individual u32s */
+			u.val64 = bswap_64(u.val64);
+			u.val32[0] = bswap_32(u.val32[0]);
+			u.val32[1] = bswap_32(u.val32[1]);
+		}
+
+		data->pid = u.val32[0];
+		data->tid = u.val32[1];
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_TIME) {
+		data->time = *array;
+		array++;
+	}
+
+	data->addr = 0;
+	if (type & PERF_SAMPLE_ADDR) {
+		data->addr = *array;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_ID) {
+		data->id = *array;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_STREAM_ID) {
+		data->stream_id = *array;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_CPU) {
+
+		u.val64 = *array;
+		if (swapped) {
+			/* undo swap of u64, then swap on individual u32s */
+			u.val64 = bswap_64(u.val64);
+			u.val32[0] = bswap_32(u.val32[0]);
+		}
+
+		data->cpu = u.val32[0];
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_PERIOD) {
+		data->period = *array;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_READ) {
+		u64 read_format = evsel->attr.read_format;
+
+		OVERFLOW_CHECK_u64(array);
+		if (read_format & PERF_FORMAT_GROUP)
+			data->read.group.nr = *array;
+		else
+			data->read.one.value = *array;
+
+		array++;
+
+		if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) {
+			OVERFLOW_CHECK_u64(array);
+			data->read.time_enabled = *array;
+			array++;
+		}
+
+		if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) {
+			OVERFLOW_CHECK_u64(array);
+			data->read.time_running = *array;
+			array++;
+		}
+
+		/* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */
+		if (read_format & PERF_FORMAT_GROUP) {
+			const u64 max_group_nr = UINT64_MAX /
+					sizeof(struct sample_read_value);
+
+			if (data->read.group.nr > max_group_nr)
+				return -EFAULT;
+			sz = data->read.group.nr *
+			     sizeof(struct sample_read_value);
+			OVERFLOW_CHECK(array, sz, max_size);
+			data->read.group.values =
+					(struct sample_read_value *)array;
+			array = (void *)array + sz;
+		} else {
+			OVERFLOW_CHECK_u64(array);
+			data->read.one.id = *array;
+			array++;
+		}
+	}
+
+	if (type & PERF_SAMPLE_CALLCHAIN) {
+		const u64 max_callchain_nr = UINT64_MAX / sizeof(u64);
+
+		OVERFLOW_CHECK_u64(array);
+		data->callchain = (struct ip_callchain *)array++;
+		if (data->callchain->nr > max_callchain_nr)
+			return -EFAULT;
+		sz = data->callchain->nr * sizeof(u64);
+		OVERFLOW_CHECK(array, sz, max_size);
+		array = (void *)array + sz;
+	}
+
+	if (type & PERF_SAMPLE_RAW) {
+		OVERFLOW_CHECK_u64(array);
+		u.val64 = *array;
+		if (WARN_ONCE(swapped,
+			      "Endianness of raw data not corrected!\n")) {
+			/* undo swap of u64, then swap on individual u32s */
+			u.val64 = bswap_64(u.val64);
+			u.val32[0] = bswap_32(u.val32[0]);
+			u.val32[1] = bswap_32(u.val32[1]);
+		}
+		data->raw_size = u.val32[0];
+		array = (void *)array + sizeof(u32);
+
+		OVERFLOW_CHECK(array, data->raw_size, max_size);
+		data->raw_data = (void *)array;
+		array = (void *)array + data->raw_size;
+	}
+
+	if (type & PERF_SAMPLE_BRANCH_STACK) {
+		const u64 max_branch_nr = UINT64_MAX /
+					  sizeof(struct branch_entry);
+
+		OVERFLOW_CHECK_u64(array);
+		data->branch_stack = (struct branch_stack *)array++;
+
+		if (data->branch_stack->nr > max_branch_nr)
+			return -EFAULT;
+		sz = data->branch_stack->nr * sizeof(struct branch_entry);
+		OVERFLOW_CHECK(array, sz, max_size);
+		array = (void *)array + sz;
+	}
+
+	if (type & PERF_SAMPLE_REGS_USER) {
+		OVERFLOW_CHECK_u64(array);
+		data->user_regs.abi = *array;
+		array++;
+
+		if (data->user_regs.abi) {
+			u64 mask = evsel->attr.sample_regs_user;
+
+			sz = hweight_long(mask) * sizeof(u64);
+			OVERFLOW_CHECK(array, sz, max_size);
+			data->user_regs.mask = mask;
+			data->user_regs.regs = (u64 *)array;
+			array = (void *)array + sz;
+		}
+	}
+
+	if (type & PERF_SAMPLE_STACK_USER) {
+		OVERFLOW_CHECK_u64(array);
+		sz = *array++;
+
+		data->user_stack.offset = ((char *)(array - 1)
+					  - (char *) event);
+
+		if (!sz) {
+			data->user_stack.size = 0;
+		} else {
+			OVERFLOW_CHECK(array, sz, max_size);
+			data->user_stack.data = (char *)array;
+			array = (void *)array + sz;
+			OVERFLOW_CHECK_u64(array);
+			data->user_stack.size = *array++;
+			if (WARN_ONCE(data->user_stack.size > sz,
+				      "user stack dump failure\n"))
+				return -EFAULT;
+		}
+	}
+
+	data->weight = 0;
+	if (type & PERF_SAMPLE_WEIGHT) {
+		OVERFLOW_CHECK_u64(array);
+		data->weight = *array;
+		array++;
+	}
+
+	data->data_src = PERF_MEM_DATA_SRC_NONE;
+	if (type & PERF_SAMPLE_DATA_SRC) {
+		OVERFLOW_CHECK_u64(array);
+		data->data_src = *array;
+		array++;
+	}
+
+	data->transaction = 0;
+	if (type & PERF_SAMPLE_TRANSACTION) {
+		OVERFLOW_CHECK_u64(array);
+		data->transaction = *array;
+		array++;
+	}
+
+	return 0;
+}
+
+size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
+				     u64 read_format)
+{
+	size_t sz, result = sizeof(struct sample_event);
+
+	if (type & PERF_SAMPLE_IDENTIFIER)
+		result += sizeof(u64);
+
+	if (type & PERF_SAMPLE_IP)
+		result += sizeof(u64);
+
+	if (type & PERF_SAMPLE_TID)
+		result += sizeof(u64);
+
+	if (type & PERF_SAMPLE_TIME)
+		result += sizeof(u64);
+
+	if (type & PERF_SAMPLE_ADDR)
+		result += sizeof(u64);
+
+	if (type & PERF_SAMPLE_ID)
+		result += sizeof(u64);
+
+	if (type & PERF_SAMPLE_STREAM_ID)
+		result += sizeof(u64);
+
+	if (type & PERF_SAMPLE_CPU)
+		result += sizeof(u64);
+
+	if (type & PERF_SAMPLE_PERIOD)
+		result += sizeof(u64);
+
+	if (type & PERF_SAMPLE_READ) {
+		result += sizeof(u64);
+		if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+			result += sizeof(u64);
+		if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+			result += sizeof(u64);
+		/* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */
+		if (read_format & PERF_FORMAT_GROUP) {
+			sz = sample->read.group.nr *
+			     sizeof(struct sample_read_value);
+			result += sz;
+		} else {
+			result += sizeof(u64);
+		}
+	}
+
+	if (type & PERF_SAMPLE_CALLCHAIN) {
+		sz = (sample->callchain->nr + 1) * sizeof(u64);
+		result += sz;
+	}
+
+	if (type & PERF_SAMPLE_RAW) {
+		result += sizeof(u32);
+		result += sample->raw_size;
+	}
+
+	if (type & PERF_SAMPLE_BRANCH_STACK) {
+		sz = sample->branch_stack->nr * sizeof(struct branch_entry);
+		sz += sizeof(u64);
+		result += sz;
+	}
+
+	if (type & PERF_SAMPLE_REGS_USER) {
+		if (sample->user_regs.abi) {
+			result += sizeof(u64);
+			sz = hweight_long(sample->user_regs.mask) * sizeof(u64);
+			result += sz;
+		} else {
+			result += sizeof(u64);
+		}
+	}
+
+	if (type & PERF_SAMPLE_STACK_USER) {
+		sz = sample->user_stack.size;
+		result += sizeof(u64);
+		if (sz) {
+			result += sz;
+			result += sizeof(u64);
+		}
+	}
+
+	if (type & PERF_SAMPLE_WEIGHT)
+		result += sizeof(u64);
+
+	if (type & PERF_SAMPLE_DATA_SRC)
+		result += sizeof(u64);
+
+	if (type & PERF_SAMPLE_TRANSACTION)
+		result += sizeof(u64);
+
+	return result;
+}
+
+int perf_event__synthesize_sample(union perf_event *event, u64 type,
+				  u64 read_format,
+				  const struct perf_sample *sample,
+				  bool swapped)
+{
+	u64 *array;
+	size_t sz;
+	/*
+	 * used for cross-endian analysis. See git commit 65014ab3
+	 * for why this goofiness is needed.
+	 */
+	union u64_swap u;
+
+	array = event->sample.array;
+
+	if (type & PERF_SAMPLE_IDENTIFIER) {
+		*array = sample->id;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_IP) {
+		*array = sample->ip;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_TID) {
+		u.val32[0] = sample->pid;
+		u.val32[1] = sample->tid;
+		if (swapped) {
+			/*
+			 * Inverse of what is done in perf_evsel__parse_sample
+			 */
+			u.val32[0] = bswap_32(u.val32[0]);
+			u.val32[1] = bswap_32(u.val32[1]);
+			u.val64 = bswap_64(u.val64);
+		}
+
+		*array = u.val64;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_TIME) {
+		*array = sample->time;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_ADDR) {
+		*array = sample->addr;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_ID) {
+		*array = sample->id;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_STREAM_ID) {
+		*array = sample->stream_id;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_CPU) {
+		u.val32[0] = sample->cpu;
+		if (swapped) {
+			/*
+			 * Inverse of what is done in perf_evsel__parse_sample
+			 */
+			u.val32[0] = bswap_32(u.val32[0]);
+			u.val64 = bswap_64(u.val64);
+		}
+		*array = u.val64;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_PERIOD) {
+		*array = sample->period;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_READ) {
+		if (read_format & PERF_FORMAT_GROUP)
+			*array = sample->read.group.nr;
+		else
+			*array = sample->read.one.value;
+		array++;
+
+		if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) {
+			*array = sample->read.time_enabled;
+			array++;
+		}
+
+		if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) {
+			*array = sample->read.time_running;
+			array++;
+		}
+
+		/* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */
+		if (read_format & PERF_FORMAT_GROUP) {
+			sz = sample->read.group.nr *
+			     sizeof(struct sample_read_value);
+			memcpy(array, sample->read.group.values, sz);
+			array = (void *)array + sz;
+		} else {
+			*array = sample->read.one.id;
+			array++;
+		}
+	}
+
+	if (type & PERF_SAMPLE_CALLCHAIN) {
+		sz = (sample->callchain->nr + 1) * sizeof(u64);
+		memcpy(array, sample->callchain, sz);
+		array = (void *)array + sz;
+	}
+
+	if (type & PERF_SAMPLE_RAW) {
+		u.val32[0] = sample->raw_size;
+		if (WARN_ONCE(swapped,
+			      "Endianness of raw data not corrected!\n")) {
+			/*
+			 * Inverse of what is done in perf_evsel__parse_sample
+			 */
+			u.val32[0] = bswap_32(u.val32[0]);
+			u.val32[1] = bswap_32(u.val32[1]);
+			u.val64 = bswap_64(u.val64);
+		}
+		*array = u.val64;
+		array = (void *)array + sizeof(u32);
+
+		memcpy(array, sample->raw_data, sample->raw_size);
+		array = (void *)array + sample->raw_size;
+	}
+
+	if (type & PERF_SAMPLE_BRANCH_STACK) {
+		sz = sample->branch_stack->nr * sizeof(struct branch_entry);
+		sz += sizeof(u64);
+		memcpy(array, sample->branch_stack, sz);
+		array = (void *)array + sz;
+	}
+
+	if (type & PERF_SAMPLE_REGS_USER) {
+		if (sample->user_regs.abi) {
+			*array++ = sample->user_regs.abi;
+			sz = hweight_long(sample->user_regs.mask) * sizeof(u64);
+			memcpy(array, sample->user_regs.regs, sz);
+			array = (void *)array + sz;
+		} else {
+			*array++ = 0;
+		}
+	}
+
+	if (type & PERF_SAMPLE_STACK_USER) {
+		sz = sample->user_stack.size;
+		*array++ = sz;
+		if (sz) {
+			memcpy(array, sample->user_stack.data, sz);
+			array = (void *)array + sz;
+			*array++ = sz;
+		}
+	}
+
+	if (type & PERF_SAMPLE_WEIGHT) {
+		*array = sample->weight;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_DATA_SRC) {
+		*array = sample->data_src;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_TRANSACTION) {
+		*array = sample->transaction;
+		array++;
+	}
+
+	return 0;
+}
+
+struct format_field *perf_evsel__field(struct perf_evsel *evsel, const char *name)
+{
+	return pevent_find_field(evsel->tp_format, name);
+}
+
+void *perf_evsel__rawptr(struct perf_evsel *evsel, struct perf_sample *sample,
+			 const char *name)
+{
+	struct format_field *field = perf_evsel__field(evsel, name);
+	int offset;
+
+	if (!field)
+		return NULL;
+
+	offset = field->offset;
+
+	if (field->flags & FIELD_IS_DYNAMIC) {
+		offset = *(int *)(sample->raw_data + field->offset);
+		offset &= 0xffff;
+	}
+
+	return sample->raw_data + offset;
+}
+
+u64 perf_evsel__intval(struct perf_evsel *evsel, struct perf_sample *sample,
+		       const char *name)
+{
+	struct format_field *field = perf_evsel__field(evsel, name);
+	void *ptr;
+	u64 value;
+
+	if (!field)
+		return 0;
+
+	ptr = sample->raw_data + field->offset;
+
+	switch (field->size) {
+	case 1:
+		return *(u8 *)ptr;
+	case 2:
+		value = *(u16 *)ptr;
+		break;
+	case 4:
+		value = *(u32 *)ptr;
+		break;
+	case 8:
+		value = *(u64 *)ptr;
+		break;
+	default:
+		return 0;
+	}
+
+	if (!evsel->needs_swap)
+		return value;
+
+	switch (field->size) {
+	case 2:
+		return bswap_16(value);
+	case 4:
+		return bswap_32(value);
+	case 8:
+		return bswap_64(value);
+	default:
+		return 0;
+	}
+
+	return 0;
+}
+
+static int comma_fprintf(FILE *fp, bool *first, const char *fmt, ...)
+{
+	va_list args;
+	int ret = 0;
+
+	if (!*first) {
+		ret += fprintf(fp, ",");
+	} else {
+		ret += fprintf(fp, ":");
+		*first = false;
+	}
+
+	va_start(args, fmt);
+	ret += vfprintf(fp, fmt, args);
+	va_end(args);
+	return ret;
+}
+
+static int __if_fprintf(FILE *fp, bool *first, const char *field, u64 value)
+{
+	if (value == 0)
+		return 0;
+
+	return comma_fprintf(fp, first, " %s: %" PRIu64, field, value);
+}
+
+#define if_print(field) printed += __if_fprintf(fp, &first, #field, evsel->attr.field)
+
+struct bit_names {
+	int bit;
+	const char *name;
+};
+
+static int bits__fprintf(FILE *fp, const char *field, u64 value,
+			 struct bit_names *bits, bool *first)
+{
+	int i = 0, printed = comma_fprintf(fp, first, " %s: ", field);
+	bool first_bit = true;
+
+	do {
+		if (value & bits[i].bit) {
+			printed += fprintf(fp, "%s%s", first_bit ? "" : "|", bits[i].name);
+			first_bit = false;
+		}
+	} while (bits[++i].name != NULL);
+
+	return printed;
+}
+
+static int sample_type__fprintf(FILE *fp, bool *first, u64 value)
+{
+#define bit_name(n) { PERF_SAMPLE_##n, #n }
+	struct bit_names bits[] = {
+		bit_name(IP), bit_name(TID), bit_name(TIME), bit_name(ADDR),
+		bit_name(READ), bit_name(CALLCHAIN), bit_name(ID), bit_name(CPU),
+		bit_name(PERIOD), bit_name(STREAM_ID), bit_name(RAW),
+		bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER),
+		bit_name(IDENTIFIER),
+		{ .name = NULL, }
+	};
+#undef bit_name
+	return bits__fprintf(fp, "sample_type", value, bits, first);
+}
+
+static int read_format__fprintf(FILE *fp, bool *first, u64 value)
+{
+#define bit_name(n) { PERF_FORMAT_##n, #n }
+	struct bit_names bits[] = {
+		bit_name(TOTAL_TIME_ENABLED), bit_name(TOTAL_TIME_RUNNING),
+		bit_name(ID), bit_name(GROUP),
+		{ .name = NULL, }
+	};
+#undef bit_name
+	return bits__fprintf(fp, "read_format", value, bits, first);
+}
+
+int perf_evsel__fprintf(struct perf_evsel *evsel,
+			struct perf_attr_details *details, FILE *fp)
+{
+	bool first = true;
+	int printed = 0;
+
+	if (details->event_group) {
+		struct perf_evsel *pos;
+
+		if (!perf_evsel__is_group_leader(evsel))
+			return 0;
+
+		if (evsel->nr_members > 1)
+			printed += fprintf(fp, "%s{", evsel->group_name ?: "");
+
+		printed += fprintf(fp, "%s", perf_evsel__name(evsel));
+		for_each_group_member(pos, evsel)
+			printed += fprintf(fp, ",%s", perf_evsel__name(pos));
+
+		if (evsel->nr_members > 1)
+			printed += fprintf(fp, "}");
+		goto out;
+	}
+
+	printed += fprintf(fp, "%s", perf_evsel__name(evsel));
+
+	if (details->verbose || details->freq) {
+		printed += comma_fprintf(fp, &first, " sample_freq=%" PRIu64,
+					 (u64)evsel->attr.sample_freq);
+	}
+
+	if (details->verbose) {
+		if_print(type);
+		if_print(config);
+		if_print(config1);
+		if_print(config2);
+		if_print(size);
+		printed += sample_type__fprintf(fp, &first, evsel->attr.sample_type);
+		if (evsel->attr.read_format)
+			printed += read_format__fprintf(fp, &first, evsel->attr.read_format);
+		if_print(disabled);
+		if_print(inherit);
+		if_print(pinned);
+		if_print(exclusive);
+		if_print(exclude_user);
+		if_print(exclude_kernel);
+		if_print(exclude_hv);
+		if_print(exclude_idle);
+		if_print(mmap);
+		if_print(mmap2);
+		if_print(comm);
+		if_print(freq);
+		if_print(inherit_stat);
+		if_print(enable_on_exec);
+		if_print(task);
+		if_print(watermark);
+		if_print(precise_ip);
+		if_print(mmap_data);
+		if_print(sample_id_all);
+		if_print(exclude_host);
+		if_print(exclude_guest);
+		if_print(__reserved_1);
+		if_print(wakeup_events);
+		if_print(bp_type);
+		if_print(branch_sample_type);
+	}
+out:
+	fputc('\n', fp);
+	return ++printed;
+}
+
+bool perf_evsel__fallback(struct perf_evsel *evsel, int err,
+			  char *msg, size_t msgsize)
+{
+	if ((err == ENOENT || err == ENXIO || err == ENODEV) &&
+	    evsel->attr.type   == PERF_TYPE_HARDWARE &&
+	    evsel->attr.config == PERF_COUNT_HW_CPU_CYCLES) {
+		/*
+		 * If it's cycles then fall back to hrtimer based
+		 * cpu-clock-tick sw counter, which is always available even if
+		 * no PMU support.
+		 *
+		 * PPC returns ENXIO until 2.6.37 (behavior changed with commit
+		 * b0a873e).
+		 */
+		scnprintf(msg, msgsize, "%s",
+"The cycles event is not supported, trying to fall back to cpu-clock-ticks");
+
+		evsel->attr.type   = PERF_TYPE_SOFTWARE;
+		evsel->attr.config = PERF_COUNT_SW_CPU_CLOCK;
+
+		zfree(&evsel->name);
+		return true;
+	}
+
+	return false;
+}
+
+int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
+			      int err, char *msg, size_t size)
+{
+	switch (err) {
+	case EPERM:
+	case EACCES:
+		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"
+		 "  0 - Disallow raw tracepoint access for unpriv\n"
+		 "  1 - Disallow cpu events for unpriv\n"
+		 "  2 - Disallow kernel profiling for unpriv",
+				 target->system_wide ? "system-wide " : "");
+	case ENOENT:
+		return scnprintf(msg, size, "The %s event is not supported.",
+				 perf_evsel__name(evsel));
+	case EMFILE:
+		return scnprintf(msg, size, "%s",
+			 "Too many events are opened.\n"
+			 "Try again after reducing the number of events.");
+	case ENODEV:
+		if (target->cpu_list)
+			return scnprintf(msg, size, "%s",
+	 "No such device - did you specify an out-of-range profile CPU?\n");
+		break;
+	case EOPNOTSUPP:
+		if (evsel->attr.precise_ip)
+			return scnprintf(msg, size, "%s",
+	"\'precise\' request may not be supported. Try removing 'p' modifier.");
+#if defined(__i386__) || defined(__x86_64__)
+		if (evsel->attr.type == PERF_TYPE_HARDWARE)
+			return scnprintf(msg, size, "%s",
+	"No hardware sampling interrupt available.\n"
+	"No APIC? If so then you can boot the kernel with the \"lapic\" boot parameter to force-enable it.");
+#endif
+		break;
+	default:
+		break;
+	}
+
+	return scnprintf(msg, size,
+	"The sys_perf_event_open() syscall returned with %d (%s) for event (%s).  \n"
+	"/bin/dmesg may provide additional information.\n"
+	"No CONFIG_PERF_EVENTS=y kernel support configured?\n",
+			 err, strerror(err), perf_evsel__name(evsel));
+}
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
new file mode 100644
index 00000000000..a52e9a5bb2d
--- /dev/null
+++ b/tools/perf/util/evsel.h
@@ -0,0 +1,365 @@
+#ifndef __PERF_EVSEL_H
+#define __PERF_EVSEL_H 1
+
+#include <linux/list.h>
+#include <stdbool.h>
+#include <stddef.h>
+#include <linux/perf_event.h>
+#include <linux/types.h>
+#include "xyarray.h"
+#include "cgroup.h"
+#include "hist.h"
+#include "symbol.h"
+
+struct perf_counts_values {
+	union {
+		struct {
+			u64 val;
+			u64 ena;
+			u64 run;
+		};
+		u64 values[3];
+	};
+};
+
+struct perf_counts {
+	s8		   	  scaled;
+	struct perf_counts_values aggr;
+	struct perf_counts_values cpu[];
+};
+
+struct perf_evsel;
+
+/*
+ * Per fd, to map back from PERF_SAMPLE_ID to evsel, only used when there are
+ * more than one entry in the evlist.
+ */
+struct perf_sample_id {
+	struct hlist_node 	node;
+	u64		 	id;
+	struct perf_evsel	*evsel;
+
+	/* Holds total ID period value for PERF_SAMPLE_READ processing. */
+	u64			period;
+};
+
+/** struct perf_evsel - event selector
+ *
+ * @name - Can be set to retain the original event name passed by the user,
+ *         so that when showing results in tools such as 'perf stat', we
+ *         show the name used, not some alias.
+ * @id_pos: the position of the event id (PERF_SAMPLE_ID or
+ *          PERF_SAMPLE_IDENTIFIER) in a sample event i.e. in the array of
+ *          struct sample_event
+ * @is_pos: the position (counting backwards) of the event id (PERF_SAMPLE_ID or
+ *          PERF_SAMPLE_IDENTIFIER) in a non-sample event i.e. if sample_id_all
+ *          is used there is an id sample appended to non-sample events
+ */
+struct perf_evsel {
+	struct list_head	node;
+	struct perf_event_attr	attr;
+	char			*filter;
+	struct xyarray		*fd;
+	struct xyarray		*sample_id;
+	u64			*id;
+	struct perf_counts	*counts;
+	struct perf_counts	*prev_raw_counts;
+	int			idx;
+	u32			ids;
+	struct hists		hists;
+	char			*name;
+	double			scale;
+	const char		*unit;
+	struct event_format	*tp_format;
+	union {
+		void		*priv;
+		off_t		id_offset;
+	};
+	struct cgroup_sel	*cgrp;
+	void			*handler;
+	struct cpu_map		*cpus;
+	unsigned int		sample_size;
+	int			id_pos;
+	int			is_pos;
+	bool 			supported;
+	bool 			needs_swap;
+	/* parse modifier helper */
+	int			exclude_GH;
+	int			nr_members;
+	int			sample_read;
+	struct perf_evsel	*leader;
+	char			*group_name;
+};
+
+union u64_swap {
+	u64 val64;
+	u32 val32[2];
+};
+
+#define hists_to_evsel(h) container_of(h, struct perf_evsel, hists)
+
+struct cpu_map;
+struct thread_map;
+struct perf_evlist;
+struct record_opts;
+
+struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx);
+
+static inline struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr)
+{
+	return perf_evsel__new_idx(attr, 0);
+}
+
+struct perf_evsel *perf_evsel__newtp_idx(const char *sys, const char *name, int idx);
+
+static inline struct perf_evsel *perf_evsel__newtp(const char *sys, const char *name)
+{
+	return perf_evsel__newtp_idx(sys, name, 0);
+}
+
+struct event_format *event_format__new(const char *sys, const char *name);
+
+void perf_evsel__init(struct perf_evsel *evsel,
+		      struct perf_event_attr *attr, int idx);
+void perf_evsel__exit(struct perf_evsel *evsel);
+void perf_evsel__delete(struct perf_evsel *evsel);
+
+void perf_evsel__config(struct perf_evsel *evsel,
+			struct record_opts *opts);
+
+int __perf_evsel__sample_size(u64 sample_type);
+void perf_evsel__calc_id_pos(struct perf_evsel *evsel);
+
+bool perf_evsel__is_cache_op_valid(u8 type, u8 op);
+
+#define PERF_EVSEL__MAX_ALIASES 8
+
+extern const char *perf_evsel__hw_cache[PERF_COUNT_HW_CACHE_MAX]
+				       [PERF_EVSEL__MAX_ALIASES];
+extern const char *perf_evsel__hw_cache_op[PERF_COUNT_HW_CACHE_OP_MAX]
+					  [PERF_EVSEL__MAX_ALIASES];
+extern const char *perf_evsel__hw_cache_result[PERF_COUNT_HW_CACHE_RESULT_MAX]
+					      [PERF_EVSEL__MAX_ALIASES];
+extern const char *perf_evsel__hw_names[PERF_COUNT_HW_MAX];
+extern const char *perf_evsel__sw_names[PERF_COUNT_SW_MAX];
+int __perf_evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result,
+					    char *bf, size_t size);
+const char *perf_evsel__name(struct perf_evsel *evsel);
+
+const char *perf_evsel__group_name(struct perf_evsel *evsel);
+int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size);
+
+int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
+int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads);
+int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus);
+void perf_evsel__reset_counts(struct perf_evsel *evsel, int ncpus);
+void perf_evsel__free_fd(struct perf_evsel *evsel);
+void perf_evsel__free_id(struct perf_evsel *evsel);
+void perf_evsel__free_counts(struct perf_evsel *evsel);
+void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
+
+void __perf_evsel__set_sample_bit(struct perf_evsel *evsel,
+				  enum perf_event_sample_format bit);
+void __perf_evsel__reset_sample_bit(struct perf_evsel *evsel,
+				    enum perf_event_sample_format bit);
+
+#define perf_evsel__set_sample_bit(evsel, bit) \
+	__perf_evsel__set_sample_bit(evsel, PERF_SAMPLE_##bit)
+
+#define perf_evsel__reset_sample_bit(evsel, bit) \
+	__perf_evsel__reset_sample_bit(evsel, PERF_SAMPLE_##bit)
+
+void perf_evsel__set_sample_id(struct perf_evsel *evsel,
+			       bool use_sample_identifier);
+
+int perf_evsel__set_filter(struct perf_evsel *evsel, int ncpus, int nthreads,
+			   const char *filter);
+int perf_evsel__enable(struct perf_evsel *evsel, int ncpus, int nthreads);
+
+int perf_evsel__open_per_cpu(struct perf_evsel *evsel,
+			     struct cpu_map *cpus);
+int perf_evsel__open_per_thread(struct perf_evsel *evsel,
+				struct thread_map *threads);
+int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
+		     struct thread_map *threads);
+void perf_evsel__close(struct perf_evsel *evsel, int ncpus, int nthreads);
+
+struct perf_sample;
+
+void *perf_evsel__rawptr(struct perf_evsel *evsel, struct perf_sample *sample,
+			 const char *name);
+u64 perf_evsel__intval(struct perf_evsel *evsel, struct perf_sample *sample,
+		       const char *name);
+
+static inline char *perf_evsel__strval(struct perf_evsel *evsel,
+				       struct perf_sample *sample,
+				       const char *name)
+{
+	return perf_evsel__rawptr(evsel, sample, name);
+}
+
+struct format_field;
+
+struct format_field *perf_evsel__field(struct perf_evsel *evsel, const char *name);
+
+#define perf_evsel__match(evsel, t, c)		\
+	(evsel->attr.type == PERF_TYPE_##t &&	\
+	 evsel->attr.config == PERF_COUNT_##c)
+
+static inline bool perf_evsel__match2(struct perf_evsel *e1,
+				      struct perf_evsel *e2)
+{
+	return (e1->attr.type == e2->attr.type) &&
+	       (e1->attr.config == e2->attr.config);
+}
+
+#define perf_evsel__cmp(a, b)			\
+	((a) &&					\
+	 (b) &&					\
+	 (a)->attr.type == (b)->attr.type &&	\
+	 (a)->attr.config == (b)->attr.config)
+
+int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
+			      int cpu, int thread, bool scale);
+
+/**
+ * perf_evsel__read_on_cpu - Read out the results on a CPU and thread
+ *
+ * @evsel - event selector to read value
+ * @cpu - CPU of interest
+ * @thread - thread of interest
+ */
+static inline int perf_evsel__read_on_cpu(struct perf_evsel *evsel,
+					  int cpu, int thread)
+{
+	return __perf_evsel__read_on_cpu(evsel, cpu, thread, false);
+}
+
+/**
+ * perf_evsel__read_on_cpu_scaled - Read out the results on a CPU and thread, scaled
+ *
+ * @evsel - event selector to read value
+ * @cpu - CPU of interest
+ * @thread - thread of interest
+ */
+static inline int perf_evsel__read_on_cpu_scaled(struct perf_evsel *evsel,
+						 int cpu, int thread)
+{
+	return __perf_evsel__read_on_cpu(evsel, cpu, thread, true);
+}
+
+int __perf_evsel__read(struct perf_evsel *evsel, int ncpus, int nthreads,
+		       bool scale);
+
+/**
+ * perf_evsel__read - Read the aggregate results on all CPUs
+ *
+ * @evsel - event selector to read value
+ * @ncpus - Number of cpus affected, from zero
+ * @nthreads - Number of threads affected, from zero
+ */
+static inline int perf_evsel__read(struct perf_evsel *evsel,
+				    int ncpus, int nthreads)
+{
+	return __perf_evsel__read(evsel, ncpus, nthreads, false);
+}
+
+/**
+ * perf_evsel__read_scaled - Read the aggregate results on all CPUs, scaled
+ *
+ * @evsel - event selector to read value
+ * @ncpus - Number of cpus affected, from zero
+ * @nthreads - Number of threads affected, from zero
+ */
+static inline int perf_evsel__read_scaled(struct perf_evsel *evsel,
+					  int ncpus, int nthreads)
+{
+	return __perf_evsel__read(evsel, ncpus, nthreads, true);
+}
+
+void hists__init(struct hists *hists);
+
+int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
+			     struct perf_sample *sample);
+
+static inline struct perf_evsel *perf_evsel__next(struct perf_evsel *evsel)
+{
+	return list_entry(evsel->node.next, struct perf_evsel, node);
+}
+
+static inline struct perf_evsel *perf_evsel__prev(struct perf_evsel *evsel)
+{
+	return list_entry(evsel->node.prev, struct perf_evsel, node);
+}
+
+/**
+ * perf_evsel__is_group_leader - Return whether given evsel is a leader event
+ *
+ * @evsel - evsel selector to be tested
+ *
+ * Return %true if @evsel is a group leader or a stand-alone event
+ */
+static inline bool perf_evsel__is_group_leader(const struct perf_evsel *evsel)
+{
+	return evsel->leader == evsel;
+}
+
+/**
+ * perf_evsel__is_group_event - Return whether given evsel is a group event
+ *
+ * @evsel - evsel selector to be tested
+ *
+ * Return %true iff event group view is enabled and @evsel is a actual group
+ * leader which has other members in the group
+ */
+static inline bool perf_evsel__is_group_event(struct perf_evsel *evsel)
+{
+	if (!symbol_conf.event_group)
+		return false;
+
+	return perf_evsel__is_group_leader(evsel) && evsel->nr_members > 1;
+}
+
+/**
+ * perf_evsel__is_function_event - Return whether given evsel is a function
+ * trace event
+ *
+ * @evsel - evsel selector to be tested
+ *
+ * Return %true if event is function trace event
+ */
+static inline bool perf_evsel__is_function_event(struct perf_evsel *evsel)
+{
+#define FUNCTION_EVENT "ftrace:function"
+
+	return evsel->name &&
+	       !strncmp(FUNCTION_EVENT, evsel->name, sizeof(FUNCTION_EVENT));
+
+#undef FUNCTION_EVENT
+}
+
+struct perf_attr_details {
+	bool freq;
+	bool verbose;
+	bool event_group;
+};
+
+int perf_evsel__fprintf(struct perf_evsel *evsel,
+			struct perf_attr_details *details, FILE *fp);
+
+bool perf_evsel__fallback(struct perf_evsel *evsel, int err,
+			  char *msg, size_t msgsize);
+int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
+			      int err, char *msg, size_t size);
+
+static inline int perf_evsel__group_idx(struct perf_evsel *evsel)
+{
+	return evsel->idx - evsel->leader->idx;
+}
+
+#define for_each_group_member(_evsel, _leader) 					\
+for ((_evsel) = list_entry((_leader)->node.next, struct perf_evsel, node); 	\
+     (_evsel) && (_evsel)->leader == (_leader);					\
+     (_evsel) = list_entry((_evsel)->node.next, struct perf_evsel, node))
+
+#endif /* __PERF_EVSEL_H */
diff --git a/tools/perf/util/exec_cmd.c b/tools/perf/util/exec_cmd.c
index 67eeff57156..7adf4ad15d8 100644
--- a/tools/perf/util/exec_cmd.c
+++ b/tools/perf/util/exec_cmd.c
@@ -11,31 +11,12 @@ static const char *argv0_path;
 
 const char *system_path(const char *path)
 {
-#ifdef RUNTIME_PREFIX
-	static const char *prefix;
-#else
 	static const char *prefix = PREFIX;
-#endif
 	struct strbuf d = STRBUF_INIT;
 
 	if (is_absolute_path(path))
 		return path;
 
-#ifdef RUNTIME_PREFIX
-	assert(argv0_path);
-	assert(is_absolute_path(argv0_path));
-
-	if (!prefix &&
-	    !(prefix = strip_path_suffix(argv0_path, PERF_EXEC_PATH)) &&
-	    !(prefix = strip_path_suffix(argv0_path, BINDIR)) &&
-	    !(prefix = strip_path_suffix(argv0_path, "perf"))) {
-		prefix = PREFIX;
-		fprintf(stderr, "RUNTIME_PREFIX requested, "
-				"but prefix computation failed.  "
-				"Using static fallback '%s'.\n", prefix);
-	}
-#endif
-
 	strbuf_addf(&d, "%s/%s", prefix, path);
 	path = strbuf_detach(&d, NULL);
 	return path;
diff --git a/tools/perf/util/generate-cmdlist.sh b/tools/perf/util/generate-cmdlist.sh
index f06f6fd148f..36a885d2cd2 100755
--- a/tools/perf/util/generate-cmdlist.sh
+++ b/tools/perf/util/generate-cmdlist.sh
@@ -21,4 +21,19 @@ do
 	    p
      }' "Documentation/perf-$cmd.txt"
 done
+
+echo "#ifdef HAVE_LIBELF_SUPPORT"
+sed -n -e 's/^perf-\([^ 	]*\)[ 	].* full.*/\1/p' command-list.txt |
+sort |
+while read cmd
+do
+     sed -n '
+     /^NAME/,/perf-'"$cmd"'/H
+     ${
+            x
+            s/.*perf-'"$cmd"' - \(.*\)/  {"'"$cmd"'", "\1"},/
+	    p
+     }' "Documentation/perf-$cmd.txt"
+done
+echo "#endif /* HAVE_LIBELF_SUPPORT */"
 echo "};"
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 1f62435f96c..893f8e2df92 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1,5 +1,4 @@
-#define _FILE_OFFSET_BITS 64
-
+#include "util.h"
 #include <sys/types.h>
 #include <byteswap.h>
 #include <unistd.h>
@@ -7,181 +6,169 @@
 #include <stdlib.h>
 #include <linux/list.h>
 #include <linux/kernel.h>
+#include <linux/bitops.h>
+#include <sys/utsname.h>
 
-#include "util.h"
+#include "evlist.h"
+#include "evsel.h"
 #include "header.h"
 #include "../perf.h"
 #include "trace-event.h"
 #include "session.h"
 #include "symbol.h"
 #include "debug.h"
+#include "cpumap.h"
+#include "pmu.h"
+#include "vdso.h"
+#include "strbuf.h"
+#include "build-id.h"
+#include "data.h"
+
+static bool no_buildid_cache = false;
+
+static u32 header_argc;
+static const char **header_argv;
 
 /*
- * Create new perf.data header attribute:
+ * magic2 = "PERFILE2"
+ * must be a numerical value to let the endianness
+ * determine the memory layout. That way we are able
+ * to detect endianness when reading the perf.data file
+ * back.
+ *
+ * we check for legacy (PERFFILE) format.
  */
-struct perf_header_attr *perf_header_attr__new(struct perf_event_attr *attr)
-{
-	struct perf_header_attr *self = malloc(sizeof(*self));
-
-	if (self != NULL) {
-		self->attr = *attr;
-		self->ids  = 0;
-		self->size = 1;
-		self->id   = malloc(sizeof(u64));
-		if (self->id == NULL) {
-			free(self);
-			self = NULL;
-		}
-	}
+static const char *__perf_magic1 = "PERFFILE";
+static const u64 __perf_magic2    = 0x32454c4946524550ULL;
+static const u64 __perf_magic2_sw = 0x50455246494c4532ULL;
 
-	return self;
-}
+#define PERF_MAGIC	__perf_magic2
 
-void perf_header_attr__delete(struct perf_header_attr *self)
-{
-	free(self->id);
-	free(self);
-}
+struct perf_file_attr {
+	struct perf_event_attr	attr;
+	struct perf_file_section	ids;
+};
 
-int perf_header_attr__add_id(struct perf_header_attr *self, u64 id)
+void perf_header__set_feat(struct perf_header *header, int feat)
 {
-	int pos = self->ids;
-
-	self->ids++;
-	if (self->ids > self->size) {
-		int nsize = self->size * 2;
-		u64 *nid = realloc(self->id, nsize * sizeof(u64));
-
-		if (nid == NULL)
-			return -1;
-
-		self->size = nsize;
-		self->id = nid;
-	}
-	self->id[pos] = id;
-	return 0;
+	set_bit(feat, header->adds_features);
 }
 
-int perf_header__init(struct perf_header *self)
+void perf_header__clear_feat(struct perf_header *header, int feat)
 {
-	self->size = 1;
-	self->attr = malloc(sizeof(void *));
-	return self->attr == NULL ? -ENOMEM : 0;
+	clear_bit(feat, header->adds_features);
 }
 
-void perf_header__exit(struct perf_header *self)
+bool perf_header__has_feat(const struct perf_header *header, int feat)
 {
-	int i;
-	for (i = 0; i < self->attrs; ++i)
-                perf_header_attr__delete(self->attr[i]);
-	free(self->attr);
+	return test_bit(feat, header->adds_features);
 }
 
-int perf_header__add_attr(struct perf_header *self,
-			  struct perf_header_attr *attr)
+static int do_write(int fd, const void *buf, size_t size)
 {
-	if (self->frozen)
-		return -1;
-
-	if (self->attrs == self->size) {
-		int nsize = self->size * 2;
-		struct perf_header_attr **nattr;
+	while (size) {
+		int ret = write(fd, buf, size);
 
-		nattr = realloc(self->attr, nsize * sizeof(void *));
-		if (nattr == NULL)
-			return -1;
+		if (ret < 0)
+			return -errno;
 
-		self->size = nsize;
-		self->attr = nattr;
+		size -= ret;
+		buf += ret;
 	}
 
-	self->attr[self->attrs++] = attr;
 	return 0;
 }
 
-static int event_count;
-static struct perf_trace_event_type *events;
+#define NAME_ALIGN 64
 
-int perf_header__push_event(u64 id, const char *name)
+static int write_padded(int fd, const void *bf, size_t count,
+			size_t count_aligned)
 {
-	if (strlen(name) > MAX_EVENT_NAME)
-		pr_warning("Event %s will be truncated\n", name);
+	static const char zero_buf[NAME_ALIGN];
+	int err = do_write(fd, bf, count);
 
-	if (!events) {
-		events = malloc(sizeof(struct perf_trace_event_type));
-		if (events == NULL)
-			return -ENOMEM;
-	} else {
-		struct perf_trace_event_type *nevents;
+	if (!err)
+		err = do_write(fd, zero_buf, count_aligned - count);
 
-		nevents = realloc(events, (event_count + 1) * sizeof(*events));
-		if (nevents == NULL)
-			return -ENOMEM;
-		events = nevents;
-	}
-	memset(&events[event_count], 0, sizeof(struct perf_trace_event_type));
-	events[event_count].event_id = id;
-	strncpy(events[event_count].name, name, MAX_EVENT_NAME - 1);
-	event_count++;
-	return 0;
+	return err;
 }
 
-char *perf_header__find_event(u64 id)
+static int do_write_string(int fd, const char *str)
 {
-	int i;
-	for (i = 0 ; i < event_count; i++) {
-		if (events[i].event_id == id)
-			return events[i].name;
-	}
-	return NULL;
-}
+	u32 len, olen;
+	int ret;
 
-static const char *__perf_magic = "PERFFILE";
+	olen = strlen(str) + 1;
+	len = PERF_ALIGN(olen, NAME_ALIGN);
 
-#define PERF_MAGIC	(*(u64 *)__perf_magic)
+	/* write len, incl. \0 */
+	ret = do_write(fd, &len, sizeof(len));
+	if (ret < 0)
+		return ret;
 
-struct perf_file_attr {
-	struct perf_event_attr	attr;
-	struct perf_file_section	ids;
-};
-
-void perf_header__set_feat(struct perf_header *self, int feat)
-{
-	set_bit(feat, self->adds_features);
+	return write_padded(fd, str, olen, len);
 }
 
-bool perf_header__has_feat(const struct perf_header *self, int feat)
+static char *do_read_string(int fd, struct perf_header *ph)
 {
-	return test_bit(feat, self->adds_features);
-}
+	ssize_t sz, ret;
+	u32 len;
+	char *buf;
 
-static int do_write(int fd, const void *buf, size_t size)
-{
-	while (size) {
-		int ret = write(fd, buf, size);
+	sz = readn(fd, &len, sizeof(len));
+	if (sz < (ssize_t)sizeof(len))
+		return NULL;
 
-		if (ret < 0)
-			return -errno;
+	if (ph->needs_swap)
+		len = bswap_32(len);
 
-		size -= ret;
-		buf += ret;
+	buf = malloc(len);
+	if (!buf)
+		return NULL;
+
+	ret = readn(fd, buf, len);
+	if (ret == (ssize_t)len) {
+		/*
+		 * strings are padded by zeroes
+		 * thus the actual strlen of buf
+		 * may be less than len
+		 */
+		return buf;
 	}
 
-	return 0;
+	free(buf);
+	return NULL;
 }
 
-#define NAME_ALIGN 64
-
-static int write_padded(int fd, const void *bf, size_t count,
-			size_t count_aligned)
+int
+perf_header__set_cmdline(int argc, const char **argv)
 {
-	static const char zero_buf[NAME_ALIGN];
-	int err = do_write(fd, bf, count);
+	int i;
 
-	if (!err)
-		err = do_write(fd, zero_buf, count_aligned - count);
+	/*
+	 * If header_argv has already been set, do not override it.
+	 * This allows a command to set the cmdline, parse args and
+	 * then call another builtin function that implements a
+	 * command -- e.g, cmd_kvm calling cmd_record.
+	 */
+	if (header_argv)
+		return 0;
 
-	return err;
+	header_argc = (u32)argc;
+
+	/* do not include NULL termination */
+	header_argv = calloc(argc, sizeof(char *));
+	if (!header_argv)
+		return -ENOMEM;
+
+	/*
+	 * must copy argv contents because it gets moved
+	 * around during option parsing
+	 */
+	for (i = 0; i < argc ; i++)
+		header_argv[i] = argv[i];
+
+	return 0;
 }
 
 #define dsos__for_each_with_build_id(pos, head)	\
@@ -190,53 +177,81 @@ static int write_padded(int fd, const void *bf, size_t count,
 			continue;		\
 		else
 
-static int __dsos__write_buildid_table(struct list_head *head, pid_t pid,
-				u16 misc, int fd)
+static int write_buildid(const char *name, size_t name_len, u8 *build_id,
+			 pid_t pid, u16 misc, int fd)
 {
+	int err;
+	struct build_id_event b;
+	size_t len;
+
+	len = name_len + 1;
+	len = PERF_ALIGN(len, NAME_ALIGN);
+
+	memset(&b, 0, sizeof(b));
+	memcpy(&b.build_id, build_id, BUILD_ID_SIZE);
+	b.pid = pid;
+	b.header.misc = misc;
+	b.header.size = sizeof(b) + len;
+
+	err = do_write(fd, &b, sizeof(b));
+	if (err < 0)
+		return err;
+
+	return write_padded(fd, name, name_len + 1, len);
+}
+
+static int __dsos__write_buildid_table(struct list_head *head,
+				       struct machine *machine,
+				       pid_t pid, u16 misc, int fd)
+{
+	char nm[PATH_MAX];
 	struct dso *pos;
 
 	dsos__for_each_with_build_id(pos, head) {
 		int err;
-		struct build_id_event b;
-		size_t len;
+		const char *name;
+		size_t name_len;
 
 		if (!pos->hit)
 			continue;
-		len = pos->long_name_len + 1;
-		len = ALIGN(len, NAME_ALIGN);
-		memset(&b, 0, sizeof(b));
-		memcpy(&b.build_id, pos->build_id, sizeof(pos->build_id));
-		b.pid = pid;
-		b.header.misc = misc;
-		b.header.size = sizeof(b) + len;
-		err = do_write(fd, &b, sizeof(b));
-		if (err < 0)
-			return err;
-		err = write_padded(fd, pos->long_name,
-				   pos->long_name_len + 1, len);
-		if (err < 0)
+
+		if (is_vdso_map(pos->short_name)) {
+			name = (char *) VDSO__MAP_NAME;
+			name_len = sizeof(VDSO__MAP_NAME) + 1;
+		} else if (dso__is_kcore(pos)) {
+			machine__mmap_name(machine, nm, sizeof(nm));
+			name = nm;
+			name_len = strlen(nm) + 1;
+		} else {
+			name = pos->long_name;
+			name_len = pos->long_name_len + 1;
+		}
+
+		err = write_buildid(name, name_len, pos->build_id,
+				    pid, misc, fd);
+		if (err)
 			return err;
 	}
 
 	return 0;
 }
 
-static int machine__write_buildid_table(struct machine *self, int fd)
+static int machine__write_buildid_table(struct machine *machine, int fd)
 {
 	int err;
 	u16 kmisc = PERF_RECORD_MISC_KERNEL,
 	    umisc = PERF_RECORD_MISC_USER;
 
-	if (!machine__is_host(self)) {
+	if (!machine__is_host(machine)) {
 		kmisc = PERF_RECORD_MISC_GUEST_KERNEL;
 		umisc = PERF_RECORD_MISC_GUEST_USER;
 	}
 
-	err = __dsos__write_buildid_table(&self->kernel_dsos, self->pid,
-					  kmisc, fd);
+	err = __dsos__write_buildid_table(&machine->kernel_dsos, machine,
+					  machine->pid, kmisc, fd);
 	if (err == 0)
-		err = __dsos__write_buildid_table(&self->user_dsos,
-						  self->pid, umisc, fd);
+		err = __dsos__write_buildid_table(&machine->user_dsos, machine,
+						  machine->pid, umisc, fd);
 	return err;
 }
 
@@ -245,12 +260,12 @@ static int dsos__write_buildid_table(struct perf_header *header, int fd)
 	struct perf_session *session = container_of(header,
 			struct perf_session, header);
 	struct rb_node *nd;
-	int err = machine__write_buildid_table(&session->host_machine, fd);
+	int err = machine__write_buildid_table(&session->machines.host, fd);
 
 	if (err)
 		return err;
 
-	for (nd = rb_first(&session->machines); nd; nd = rb_next(nd)) {
+	for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
 		struct machine *pos = rb_entry(nd, struct machine, rb_node);
 		err = machine__write_buildid_table(pos, fd);
 		if (err)
@@ -260,32 +275,44 @@ static int dsos__write_buildid_table(struct perf_header *header, int fd)
 }
 
 int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
-			  const char *name, bool is_kallsyms)
+			  const char *name, bool is_kallsyms, bool is_vdso)
 {
 	const size_t size = PATH_MAX;
-	char *filename = malloc(size),
-	     *linkname = malloc(size), *targetname;
+	char *realname, *filename = zalloc(size),
+	     *linkname = zalloc(size), *targetname;
 	int len, err = -1;
+	bool slash = is_kallsyms || is_vdso;
 
-	if (filename == NULL || linkname == NULL)
+	if (is_kallsyms) {
+		if (symbol_conf.kptr_restrict) {
+			pr_debug("Not caching a kptr_restrict'ed /proc/kallsyms\n");
+			err = 0;
+			goto out_free;
+		}
+		realname = (char *) name;
+	} else
+		realname = realpath(name, NULL);
+
+	if (realname == NULL || filename == NULL || linkname == NULL)
 		goto out_free;
 
-	len = snprintf(filename, size, "%s%s%s",
-		       debugdir, is_kallsyms ? "/" : "", name);
+	len = scnprintf(filename, size, "%s%s%s",
+		       debugdir, slash ? "/" : "",
+		       is_vdso ? VDSO__MAP_NAME : realname);
 	if (mkdir_p(filename, 0755))
 		goto out_free;
 
-	snprintf(filename + len, sizeof(filename) - len, "/%s", sbuild_id);
+	snprintf(filename + len, size - len, "/%s", sbuild_id);
 
 	if (access(filename, F_OK)) {
 		if (is_kallsyms) {
 			 if (copyfile("/proc/kallsyms", filename))
 				goto out_free;
-		} else if (link(name, filename) && copyfile(name, filename))
+		} else if (link(realname, filename) && copyfile(name, filename))
 			goto out_free;
 	}
 
-	len = snprintf(linkname, size, "%s/.build-id/%.2s",
+	len = scnprintf(linkname, size, "%s/.build-id/%.2s",
 		       debugdir, sbuild_id);
 
 	if (access(linkname, X_OK) && mkdir_p(linkname, 0755))
@@ -298,6 +325,8 @@ int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
 	if (symlink(targetname, linkname) == 0)
 		err = 0;
 out_free:
+	if (!is_kallsyms)
+		free(realname);
 	free(filename);
 	free(linkname);
 	return err;
@@ -305,20 +334,21 @@ out_free:
 
 static int build_id_cache__add_b(const u8 *build_id, size_t build_id_size,
 				 const char *name, const char *debugdir,
-				 bool is_kallsyms)
+				 bool is_kallsyms, bool is_vdso)
 {
 	char sbuild_id[BUILD_ID_SIZE * 2 + 1];
 
 	build_id__sprintf(build_id, build_id_size, sbuild_id);
 
-	return build_id_cache__add_s(sbuild_id, debugdir, name, is_kallsyms);
+	return build_id_cache__add_s(sbuild_id, debugdir, name,
+				     is_kallsyms, is_vdso);
 }
 
 int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir)
 {
 	const size_t size = PATH_MAX;
-	char *filename = malloc(size),
-	     *linkname = malloc(size);
+	char *filename = zalloc(size),
+	     *linkname = zalloc(size);
 	int err = -1;
 
 	if (filename == NULL || linkname == NULL)
@@ -330,7 +360,7 @@ int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir)
 	if (access(linkname, F_OK))
 		goto out_free;
 
-	if (readlink(linkname, filename, size) < 0)
+	if (readlink(linkname, filename, size - 1) < 0)
 		goto out_free;
 
 	if (unlink(linkname))
@@ -352,67 +382,77 @@ out_free:
 	return err;
 }
 
-static int dso__cache_build_id(struct dso *self, const char *debugdir)
+static int dso__cache_build_id(struct dso *dso, struct machine *machine,
+			       const char *debugdir)
 {
-	bool is_kallsyms = self->kernel && self->long_name[0] != '/';
-
-	return build_id_cache__add_b(self->build_id, sizeof(self->build_id),
-				     self->long_name, debugdir, is_kallsyms);
+	bool is_kallsyms = dso->kernel && dso->long_name[0] != '/';
+	bool is_vdso = is_vdso_map(dso->short_name);
+	const char *name = dso->long_name;
+	char nm[PATH_MAX];
+
+	if (dso__is_kcore(dso)) {
+		is_kallsyms = true;
+		machine__mmap_name(machine, nm, sizeof(nm));
+		name = nm;
+	}
+	return build_id_cache__add_b(dso->build_id, sizeof(dso->build_id), name,
+				     debugdir, is_kallsyms, is_vdso);
 }
 
-static int __dsos__cache_build_ids(struct list_head *head, const char *debugdir)
+static int __dsos__cache_build_ids(struct list_head *head,
+				   struct machine *machine, const char *debugdir)
 {
 	struct dso *pos;
 	int err = 0;
 
 	dsos__for_each_with_build_id(pos, head)
-		if (dso__cache_build_id(pos, debugdir))
+		if (dso__cache_build_id(pos, machine, debugdir))
 			err = -1;
 
 	return err;
 }
 
-static int machine__cache_build_ids(struct machine *self, const char *debugdir)
+static int machine__cache_build_ids(struct machine *machine, const char *debugdir)
 {
-	int ret = __dsos__cache_build_ids(&self->kernel_dsos, debugdir);
-	ret |= __dsos__cache_build_ids(&self->user_dsos, debugdir);
+	int ret = __dsos__cache_build_ids(&machine->kernel_dsos, machine,
+					  debugdir);
+	ret |= __dsos__cache_build_ids(&machine->user_dsos, machine, debugdir);
 	return ret;
 }
 
-static int perf_session__cache_build_ids(struct perf_session *self)
+static int perf_session__cache_build_ids(struct perf_session *session)
 {
 	struct rb_node *nd;
 	int ret;
 	char debugdir[PATH_MAX];
 
-	snprintf(debugdir, sizeof(debugdir), "%s/%s", getenv("HOME"),
-		 DEBUG_CACHE_DIR);
+	snprintf(debugdir, sizeof(debugdir), "%s", buildid_dir);
 
 	if (mkdir(debugdir, 0755) != 0 && errno != EEXIST)
 		return -1;
 
-	ret = machine__cache_build_ids(&self->host_machine, debugdir);
+	ret = machine__cache_build_ids(&session->machines.host, debugdir);
 
-	for (nd = rb_first(&self->machines); nd; nd = rb_next(nd)) {
+	for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
 		struct machine *pos = rb_entry(nd, struct machine, rb_node);
 		ret |= machine__cache_build_ids(pos, debugdir);
 	}
 	return ret ? -1 : 0;
 }
 
-static bool machine__read_build_ids(struct machine *self, bool with_hits)
+static bool machine__read_build_ids(struct machine *machine, bool with_hits)
 {
-	bool ret = __dsos__read_build_ids(&self->kernel_dsos, with_hits);
-	ret |= __dsos__read_build_ids(&self->user_dsos, with_hits);
+	bool ret = __dsos__read_build_ids(&machine->kernel_dsos, with_hits);
+	ret |= __dsos__read_build_ids(&machine->user_dsos, with_hits);
 	return ret;
 }
 
-static bool perf_session__read_build_ids(struct perf_session *self, bool with_hits)
+static bool perf_session__read_build_ids(struct perf_session *session, bool with_hits)
 {
 	struct rb_node *nd;
-	bool ret = machine__read_build_ids(&self->host_machine, with_hits);
+	bool ret = machine__read_build_ids(&session->machines.host, with_hits);
 
-	for (nd = rb_first(&self->machines); nd; nd = rb_next(nd)) {
+	for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
 		struct machine *pos = rb_entry(nd, struct machine, rb_node);
 		ret |= machine__read_build_ids(pos, with_hits);
 	}
@@ -420,279 +460,1046 @@ static bool perf_session__read_build_ids(struct perf_session *self, bool with_hi
 	return ret;
 }
 
-static int perf_header__adds_write(struct perf_header *self, int fd)
+static int write_tracing_data(int fd, struct perf_header *h __maybe_unused,
+			    struct perf_evlist *evlist)
+{
+	return read_tracing_data(fd, &evlist->entries);
+}
+
+
+static int write_build_id(int fd, struct perf_header *h,
+			  struct perf_evlist *evlist __maybe_unused)
 {
-	int nr_sections;
 	struct perf_session *session;
-	struct perf_file_section *feat_sec;
-	int sec_size;
-	u64 sec_start;
-	int idx = 0, err;
+	int err;
 
-	session = container_of(self, struct perf_session, header);
-	if (perf_session__read_build_ids(session, true))
-		perf_header__set_feat(self, HEADER_BUILD_ID);
+	session = container_of(h, struct perf_session, header);
 
-	nr_sections = bitmap_weight(self->adds_features, HEADER_FEAT_BITS);
-	if (!nr_sections)
-		return 0;
+	if (!perf_session__read_build_ids(session, true))
+		return -1;
 
-	feat_sec = calloc(sizeof(*feat_sec), nr_sections);
-	if (feat_sec == NULL)
-		return -ENOMEM;
+	err = dsos__write_buildid_table(h, fd);
+	if (err < 0) {
+		pr_debug("failed to write buildid table\n");
+		return err;
+	}
+	if (!no_buildid_cache)
+		perf_session__cache_build_ids(session);
 
-	sec_size = sizeof(*feat_sec) * nr_sections;
+	return 0;
+}
 
-	sec_start = self->data_offset + self->data_size;
-	lseek(fd, sec_start + sec_size, SEEK_SET);
+static int write_hostname(int fd, struct perf_header *h __maybe_unused,
+			  struct perf_evlist *evlist __maybe_unused)
+{
+	struct utsname uts;
+	int ret;
 
-	if (perf_header__has_feat(self, HEADER_TRACE_INFO)) {
-		struct perf_file_section *trace_sec;
+	ret = uname(&uts);
+	if (ret < 0)
+		return -1;
 
-		trace_sec = &feat_sec[idx++];
+	return do_write_string(fd, uts.nodename);
+}
 
-		/* Write trace info */
-		trace_sec->offset = lseek(fd, 0, SEEK_CUR);
-		read_tracing_data(fd, attrs, nr_counters);
-		trace_sec->size = lseek(fd, 0, SEEK_CUR) - trace_sec->offset;
-	}
+static int write_osrelease(int fd, struct perf_header *h __maybe_unused,
+			   struct perf_evlist *evlist __maybe_unused)
+{
+	struct utsname uts;
+	int ret;
 
-	if (perf_header__has_feat(self, HEADER_BUILD_ID)) {
-		struct perf_file_section *buildid_sec;
+	ret = uname(&uts);
+	if (ret < 0)
+		return -1;
 
-		buildid_sec = &feat_sec[idx++];
+	return do_write_string(fd, uts.release);
+}
 
-		/* Write build-ids */
-		buildid_sec->offset = lseek(fd, 0, SEEK_CUR);
-		err = dsos__write_buildid_table(self, fd);
-		if (err < 0) {
-			pr_debug("failed to write buildid table\n");
-			goto out_free;
+static int write_arch(int fd, struct perf_header *h __maybe_unused,
+		      struct perf_evlist *evlist __maybe_unused)
+{
+	struct utsname uts;
+	int ret;
+
+	ret = uname(&uts);
+	if (ret < 0)
+		return -1;
+
+	return do_write_string(fd, uts.machine);
+}
+
+static int write_version(int fd, struct perf_header *h __maybe_unused,
+			 struct perf_evlist *evlist __maybe_unused)
+{
+	return do_write_string(fd, perf_version_string);
+}
+
+static int write_cpudesc(int fd, struct perf_header *h __maybe_unused,
+		       struct perf_evlist *evlist __maybe_unused)
+{
+#ifndef CPUINFO_PROC
+#define CPUINFO_PROC NULL
+#endif
+	FILE *file;
+	char *buf = NULL;
+	char *s, *p;
+	const char *search = CPUINFO_PROC;
+	size_t len = 0;
+	int ret = -1;
+
+	if (!search)
+		return -1;
+
+	file = fopen("/proc/cpuinfo", "r");
+	if (!file)
+		return -1;
+
+	while (getline(&buf, &len, file) > 0) {
+		ret = strncmp(buf, search, strlen(search));
+		if (!ret)
+			break;
+	}
+
+	if (ret)
+		goto done;
+
+	s = buf;
+
+	p = strchr(buf, ':');
+	if (p && *(p+1) == ' ' && *(p+2))
+		s = p + 2;
+	p = strchr(s, '\n');
+	if (p)
+		*p = '\0';
+
+	/* squash extra space characters (branding string) */
+	p = s;
+	while (*p) {
+		if (isspace(*p)) {
+			char *r = p + 1;
+			char *q = r;
+			*p = ' ';
+			while (*q && isspace(*q))
+				q++;
+			if (q != (p+1))
+				while ((*r++ = *q++));
 		}
-		buildid_sec->size = lseek(fd, 0, SEEK_CUR) -
-					  buildid_sec->offset;
-		perf_session__cache_build_ids(session);
+		p++;
 	}
+	ret = do_write_string(fd, s);
+done:
+	free(buf);
+	fclose(file);
+	return ret;
+}
 
-	lseek(fd, sec_start, SEEK_SET);
-	err = do_write(fd, feat_sec, sec_size);
-	if (err < 0)
-		pr_debug("failed to write feature section\n");
-out_free:
-	free(feat_sec);
-	return err;
+static int write_nrcpus(int fd, struct perf_header *h __maybe_unused,
+			struct perf_evlist *evlist __maybe_unused)
+{
+	long nr;
+	u32 nrc, nra;
+	int ret;
+
+	nr = sysconf(_SC_NPROCESSORS_CONF);
+	if (nr < 0)
+		return -1;
+
+	nrc = (u32)(nr & UINT_MAX);
+
+	nr = sysconf(_SC_NPROCESSORS_ONLN);
+	if (nr < 0)
+		return -1;
+
+	nra = (u32)(nr & UINT_MAX);
+
+	ret = do_write(fd, &nrc, sizeof(nrc));
+	if (ret < 0)
+		return ret;
+
+	return do_write(fd, &nra, sizeof(nra));
 }
 
-int perf_header__write_pipe(int fd)
+static int write_event_desc(int fd, struct perf_header *h __maybe_unused,
+			    struct perf_evlist *evlist)
 {
-	struct perf_pipe_file_header f_header;
-	int err;
+	struct perf_evsel *evsel;
+	u32 nre, nri, sz;
+	int ret;
 
-	f_header = (struct perf_pipe_file_header){
-		.magic	   = PERF_MAGIC,
-		.size	   = sizeof(f_header),
-	};
+	nre = evlist->nr_entries;
 
-	err = do_write(fd, &f_header, sizeof(f_header));
-	if (err < 0) {
-		pr_debug("failed to write perf pipe header\n");
-		return err;
+	/*
+	 * write number of events
+	 */
+	ret = do_write(fd, &nre, sizeof(nre));
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * size of perf_event_attr struct
+	 */
+	sz = (u32)sizeof(evsel->attr);
+	ret = do_write(fd, &sz, sizeof(sz));
+	if (ret < 0)
+		return ret;
+
+	evlist__for_each(evlist, evsel) {
+		ret = do_write(fd, &evsel->attr, sz);
+		if (ret < 0)
+			return ret;
+		/*
+		 * write number of unique id per event
+		 * there is one id per instance of an event
+		 *
+		 * copy into an nri to be independent of the
+		 * type of ids,
+		 */
+		nri = evsel->ids;
+		ret = do_write(fd, &nri, sizeof(nri));
+		if (ret < 0)
+			return ret;
+
+		/*
+		 * write event string as passed on cmdline
+		 */
+		ret = do_write_string(fd, perf_evsel__name(evsel));
+		if (ret < 0)
+			return ret;
+		/*
+		 * write unique ids for this event
+		 */
+		ret = do_write(fd, evsel->id, evsel->ids * sizeof(u64));
+		if (ret < 0)
+			return ret;
 	}
+	return 0;
+}
+
+static int write_cmdline(int fd, struct perf_header *h __maybe_unused,
+			 struct perf_evlist *evlist __maybe_unused)
+{
+	char buf[MAXPATHLEN];
+	char proc[32];
+	u32 i, n;
+	int ret;
 
+	/*
+	 * actual atual path to perf binary
+	 */
+	sprintf(proc, "/proc/%d/exe", getpid());
+	ret = readlink(proc, buf, sizeof(buf));
+	if (ret <= 0)
+		return -1;
+
+	/* readlink() does not add null termination */
+	buf[ret] = '\0';
+
+	/* account for binary path */
+	n = header_argc + 1;
+
+	ret = do_write(fd, &n, sizeof(n));
+	if (ret < 0)
+		return ret;
+
+	ret = do_write_string(fd, buf);
+	if (ret < 0)
+		return ret;
+
+	for (i = 0 ; i < header_argc; i++) {
+		ret = do_write_string(fd, header_argv[i]);
+		if (ret < 0)
+			return ret;
+	}
 	return 0;
 }
 
-int perf_header__write(struct perf_header *self, int fd, bool at_exit)
+#define CORE_SIB_FMT \
+	"/sys/devices/system/cpu/cpu%d/topology/core_siblings_list"
+#define THRD_SIB_FMT \
+	"/sys/devices/system/cpu/cpu%d/topology/thread_siblings_list"
+
+struct cpu_topo {
+	u32 core_sib;
+	u32 thread_sib;
+	char **core_siblings;
+	char **thread_siblings;
+};
+
+static int build_cpu_topo(struct cpu_topo *tp, int cpu)
 {
-	struct perf_file_header f_header;
-	struct perf_file_attr   f_attr;
-	struct perf_header_attr	*attr;
-	int i, err;
+	FILE *fp;
+	char filename[MAXPATHLEN];
+	char *buf = NULL, *p;
+	size_t len = 0;
+	ssize_t sret;
+	u32 i = 0;
+	int ret = -1;
+
+	sprintf(filename, CORE_SIB_FMT, cpu);
+	fp = fopen(filename, "r");
+	if (!fp)
+		goto try_threads;
+
+	sret = getline(&buf, &len, fp);
+	fclose(fp);
+	if (sret <= 0)
+		goto try_threads;
+
+	p = strchr(buf, '\n');
+	if (p)
+		*p = '\0';
+
+	for (i = 0; i < tp->core_sib; i++) {
+		if (!strcmp(buf, tp->core_siblings[i]))
+			break;
+	}
+	if (i == tp->core_sib) {
+		tp->core_siblings[i] = buf;
+		tp->core_sib++;
+		buf = NULL;
+		len = 0;
+	}
+	ret = 0;
 
-	lseek(fd, sizeof(f_header), SEEK_SET);
+try_threads:
+	sprintf(filename, THRD_SIB_FMT, cpu);
+	fp = fopen(filename, "r");
+	if (!fp)
+		goto done;
 
-	for (i = 0; i < self->attrs; i++) {
-		attr = self->attr[i];
+	if (getline(&buf, &len, fp) <= 0)
+		goto done;
 
-		attr->id_offset = lseek(fd, 0, SEEK_CUR);
-		err = do_write(fd, attr->id, attr->ids * sizeof(u64));
-		if (err < 0) {
-			pr_debug("failed to write perf header\n");
-			return err;
-		}
+	p = strchr(buf, '\n');
+	if (p)
+		*p = '\0';
+
+	for (i = 0; i < tp->thread_sib; i++) {
+		if (!strcmp(buf, tp->thread_siblings[i]))
+			break;
+	}
+	if (i == tp->thread_sib) {
+		tp->thread_siblings[i] = buf;
+		tp->thread_sib++;
+		buf = NULL;
 	}
+	ret = 0;
+done:
+	if(fp)
+		fclose(fp);
+	free(buf);
+	return ret;
+}
 
+static void free_cpu_topo(struct cpu_topo *tp)
+{
+	u32 i;
 
-	self->attr_offset = lseek(fd, 0, SEEK_CUR);
+	if (!tp)
+		return;
 
-	for (i = 0; i < self->attrs; i++) {
-		attr = self->attr[i];
+	for (i = 0 ; i < tp->core_sib; i++)
+		zfree(&tp->core_siblings[i]);
 
-		f_attr = (struct perf_file_attr){
-			.attr = attr->attr,
-			.ids  = {
-				.offset = attr->id_offset,
-				.size   = attr->ids * sizeof(u64),
-			}
-		};
-		err = do_write(fd, &f_attr, sizeof(f_attr));
-		if (err < 0) {
-			pr_debug("failed to write perf header attribute\n");
-			return err;
-		}
+	for (i = 0 ; i < tp->thread_sib; i++)
+		zfree(&tp->thread_siblings[i]);
+
+	free(tp);
+}
+
+static struct cpu_topo *build_cpu_topology(void)
+{
+	struct cpu_topo *tp;
+	void *addr;
+	u32 nr, i;
+	size_t sz;
+	long ncpus;
+	int ret = -1;
+
+	ncpus = sysconf(_SC_NPROCESSORS_CONF);
+	if (ncpus < 0)
+		return NULL;
+
+	nr = (u32)(ncpus & UINT_MAX);
+
+	sz = nr * sizeof(char *);
+
+	addr = calloc(1, sizeof(*tp) + 2 * sz);
+	if (!addr)
+		return NULL;
+
+	tp = addr;
+
+	addr += sizeof(*tp);
+	tp->core_siblings = addr;
+	addr += sz;
+	tp->thread_siblings = addr;
+
+	for (i = 0; i < nr; i++) {
+		ret = build_cpu_topo(tp, i);
+		if (ret < 0)
+			break;
+	}
+	if (ret) {
+		free_cpu_topo(tp);
+		tp = NULL;
 	}
+	return tp;
+}
 
-	self->event_offset = lseek(fd, 0, SEEK_CUR);
-	self->event_size = event_count * sizeof(struct perf_trace_event_type);
-	if (events) {
-		err = do_write(fd, events, self->event_size);
-		if (err < 0) {
-			pr_debug("failed to write perf header events\n");
-			return err;
-		}
+static int write_cpu_topology(int fd, struct perf_header *h __maybe_unused,
+			  struct perf_evlist *evlist __maybe_unused)
+{
+	struct cpu_topo *tp;
+	u32 i;
+	int ret;
+
+	tp = build_cpu_topology();
+	if (!tp)
+		return -1;
+
+	ret = do_write(fd, &tp->core_sib, sizeof(tp->core_sib));
+	if (ret < 0)
+		goto done;
+
+	for (i = 0; i < tp->core_sib; i++) {
+		ret = do_write_string(fd, tp->core_siblings[i]);
+		if (ret < 0)
+			goto done;
 	}
+	ret = do_write(fd, &tp->thread_sib, sizeof(tp->thread_sib));
+	if (ret < 0)
+		goto done;
 
-	self->data_offset = lseek(fd, 0, SEEK_CUR);
+	for (i = 0; i < tp->thread_sib; i++) {
+		ret = do_write_string(fd, tp->thread_siblings[i]);
+		if (ret < 0)
+			break;
+	}
+done:
+	free_cpu_topo(tp);
+	return ret;
+}
 
-	if (at_exit) {
-		err = perf_header__adds_write(self, fd);
-		if (err < 0)
-			return err;
+
+
+static int write_total_mem(int fd, struct perf_header *h __maybe_unused,
+			  struct perf_evlist *evlist __maybe_unused)
+{
+	char *buf = NULL;
+	FILE *fp;
+	size_t len = 0;
+	int ret = -1, n;
+	uint64_t mem;
+
+	fp = fopen("/proc/meminfo", "r");
+	if (!fp)
+		return -1;
+
+	while (getline(&buf, &len, fp) > 0) {
+		ret = strncmp(buf, "MemTotal:", 9);
+		if (!ret)
+			break;
+	}
+	if (!ret) {
+		n = sscanf(buf, "%*s %"PRIu64, &mem);
+		if (n == 1)
+			ret = do_write(fd, &mem, sizeof(mem));
 	}
+	free(buf);
+	fclose(fp);
+	return ret;
+}
 
-	f_header = (struct perf_file_header){
-		.magic	   = PERF_MAGIC,
-		.size	   = sizeof(f_header),
-		.attr_size = sizeof(f_attr),
-		.attrs = {
-			.offset = self->attr_offset,
-			.size   = self->attrs * sizeof(f_attr),
-		},
-		.data = {
-			.offset = self->data_offset,
-			.size	= self->data_size,
-		},
-		.event_types = {
-			.offset = self->event_offset,
-			.size	= self->event_size,
-		},
-	};
+static int write_topo_node(int fd, int node)
+{
+	char str[MAXPATHLEN];
+	char field[32];
+	char *buf = NULL, *p;
+	size_t len = 0;
+	FILE *fp;
+	u64 mem_total, mem_free, mem;
+	int ret = -1;
+
+	sprintf(str, "/sys/devices/system/node/node%d/meminfo", node);
+	fp = fopen(str, "r");
+	if (!fp)
+		return -1;
 
-	memcpy(&f_header.adds_features, &self->adds_features, sizeof(self->adds_features));
+	while (getline(&buf, &len, fp) > 0) {
+		/* skip over invalid lines */
+		if (!strchr(buf, ':'))
+			continue;
+		if (sscanf(buf, "%*s %*d %31s %"PRIu64, field, &mem) != 2)
+			goto done;
+		if (!strcmp(field, "MemTotal:"))
+			mem_total = mem;
+		if (!strcmp(field, "MemFree:"))
+			mem_free = mem;
+	}
 
-	lseek(fd, 0, SEEK_SET);
-	err = do_write(fd, &f_header, sizeof(f_header));
-	if (err < 0) {
-		pr_debug("failed to write perf header\n");
-		return err;
+	fclose(fp);
+	fp = NULL;
+
+	ret = do_write(fd, &mem_total, sizeof(u64));
+	if (ret)
+		goto done;
+
+	ret = do_write(fd, &mem_free, sizeof(u64));
+	if (ret)
+		goto done;
+
+	ret = -1;
+	sprintf(str, "/sys/devices/system/node/node%d/cpulist", node);
+
+	fp = fopen(str, "r");
+	if (!fp)
+		goto done;
+
+	if (getline(&buf, &len, fp) <= 0)
+		goto done;
+
+	p = strchr(buf, '\n');
+	if (p)
+		*p = '\0';
+
+	ret = do_write_string(fd, buf);
+done:
+	free(buf);
+	if (fp)
+		fclose(fp);
+	return ret;
+}
+
+static int write_numa_topology(int fd, struct perf_header *h __maybe_unused,
+			  struct perf_evlist *evlist __maybe_unused)
+{
+	char *buf = NULL;
+	size_t len = 0;
+	FILE *fp;
+	struct cpu_map *node_map = NULL;
+	char *c;
+	u32 nr, i, j;
+	int ret = -1;
+
+	fp = fopen("/sys/devices/system/node/online", "r");
+	if (!fp)
+		return -1;
+
+	if (getline(&buf, &len, fp) <= 0)
+		goto done;
+
+	c = strchr(buf, '\n');
+	if (c)
+		*c = '\0';
+
+	node_map = cpu_map__new(buf);
+	if (!node_map)
+		goto done;
+
+	nr = (u32)node_map->nr;
+
+	ret = do_write(fd, &nr, sizeof(nr));
+	if (ret < 0)
+		goto done;
+
+	for (i = 0; i < nr; i++) {
+		j = (u32)node_map->map[i];
+		ret = do_write(fd, &j, sizeof(j));
+		if (ret < 0)
+			break;
+
+		ret = write_topo_node(fd, i);
+		if (ret < 0)
+			break;
+	}
+done:
+	free(buf);
+	fclose(fp);
+	free(node_map);
+	return ret;
+}
+
+/*
+ * File format:
+ *
+ * struct pmu_mappings {
+ *	u32	pmu_num;
+ *	struct pmu_map {
+ *		u32	type;
+ *		char	name[];
+ *	}[pmu_num];
+ * };
+ */
+
+static int write_pmu_mappings(int fd, struct perf_header *h __maybe_unused,
+			      struct perf_evlist *evlist __maybe_unused)
+{
+	struct perf_pmu *pmu = NULL;
+	off_t offset = lseek(fd, 0, SEEK_CUR);
+	__u32 pmu_num = 0;
+	int ret;
+
+	/* write real pmu_num later */
+	ret = do_write(fd, &pmu_num, sizeof(pmu_num));
+	if (ret < 0)
+		return ret;
+
+	while ((pmu = perf_pmu__scan(pmu))) {
+		if (!pmu->name)
+			continue;
+		pmu_num++;
+
+		ret = do_write(fd, &pmu->type, sizeof(pmu->type));
+		if (ret < 0)
+			return ret;
+
+		ret = do_write_string(fd, pmu->name);
+		if (ret < 0)
+			return ret;
+	}
+
+	if (pwrite(fd, &pmu_num, sizeof(pmu_num), offset) != sizeof(pmu_num)) {
+		/* discard all */
+		lseek(fd, offset, SEEK_SET);
+		return -1;
 	}
-	lseek(fd, self->data_offset + self->data_size, SEEK_SET);
 
-	self->frozen = 1;
 	return 0;
 }
 
-static int perf_header__getbuffer64(struct perf_header *self,
-				    int fd, void *buf, size_t size)
+/*
+ * File format:
+ *
+ * struct group_descs {
+ *	u32	nr_groups;
+ *	struct group_desc {
+ *		char	name[];
+ *		u32	leader_idx;
+ *		u32	nr_members;
+ *	}[nr_groups];
+ * };
+ */
+static int write_group_desc(int fd, struct perf_header *h __maybe_unused,
+			    struct perf_evlist *evlist)
 {
-	if (do_read(fd, buf, size) <= 0)
-		return -1;
+	u32 nr_groups = evlist->nr_groups;
+	struct perf_evsel *evsel;
+	int ret;
 
-	if (self->needs_swap)
-		mem_bswap_64(buf, size);
+	ret = do_write(fd, &nr_groups, sizeof(nr_groups));
+	if (ret < 0)
+		return ret;
+
+	evlist__for_each(evlist, evsel) {
+		if (perf_evsel__is_group_leader(evsel) &&
+		    evsel->nr_members > 1) {
+			const char *name = evsel->group_name ?: "{anon_group}";
+			u32 leader_idx = evsel->idx;
+			u32 nr_members = evsel->nr_members;
 
+			ret = do_write_string(fd, name);
+			if (ret < 0)
+				return ret;
+
+			ret = do_write(fd, &leader_idx, sizeof(leader_idx));
+			if (ret < 0)
+				return ret;
+
+			ret = do_write(fd, &nr_members, sizeof(nr_members));
+			if (ret < 0)
+				return ret;
+		}
+	}
 	return 0;
 }
 
-int perf_header__process_sections(struct perf_header *self, int fd,
-				  int (*process)(struct perf_file_section *self,
-						 struct perf_header *ph,
-						 int feat, int fd))
+/*
+ * default get_cpuid(): nothing gets recorded
+ * actual implementation must be in arch/$(ARCH)/util/header.c
+ */
+int __attribute__ ((weak)) get_cpuid(char *buffer __maybe_unused,
+				     size_t sz __maybe_unused)
 {
-	struct perf_file_section *feat_sec;
-	int nr_sections;
-	int sec_size;
-	int idx = 0;
-	int err = -1, feat = 1;
+	return -1;
+}
 
-	nr_sections = bitmap_weight(self->adds_features, HEADER_FEAT_BITS);
-	if (!nr_sections)
-		return 0;
+static int write_cpuid(int fd, struct perf_header *h __maybe_unused,
+		       struct perf_evlist *evlist __maybe_unused)
+{
+	char buffer[64];
+	int ret;
 
-	feat_sec = calloc(sizeof(*feat_sec), nr_sections);
-	if (!feat_sec)
-		return -1;
+	ret = get_cpuid(buffer, sizeof(buffer));
+	if (!ret)
+		goto write_it;
 
-	sec_size = sizeof(*feat_sec) * nr_sections;
+	return -1;
+write_it:
+	return do_write_string(fd, buffer);
+}
 
-	lseek(fd, self->data_offset + self->data_size, SEEK_SET);
+static int write_branch_stack(int fd __maybe_unused,
+			      struct perf_header *h __maybe_unused,
+		       struct perf_evlist *evlist __maybe_unused)
+{
+	return 0;
+}
 
-	if (perf_header__getbuffer64(self, fd, feat_sec, sec_size))
-		goto out_free;
+static void print_hostname(struct perf_header *ph, int fd __maybe_unused,
+			   FILE *fp)
+{
+	fprintf(fp, "# hostname : %s\n", ph->env.hostname);
+}
 
-	err = 0;
-	while (idx < nr_sections && feat < HEADER_LAST_FEATURE) {
-		if (perf_header__has_feat(self, feat)) {
-			struct perf_file_section *sec = &feat_sec[idx++];
+static void print_osrelease(struct perf_header *ph, int fd __maybe_unused,
+			    FILE *fp)
+{
+	fprintf(fp, "# os release : %s\n", ph->env.os_release);
+}
+
+static void print_arch(struct perf_header *ph, int fd __maybe_unused, FILE *fp)
+{
+	fprintf(fp, "# arch : %s\n", ph->env.arch);
+}
 
-			err = process(sec, self, feat, fd);
-			if (err < 0)
-				break;
+static void print_cpudesc(struct perf_header *ph, int fd __maybe_unused,
+			  FILE *fp)
+{
+	fprintf(fp, "# cpudesc : %s\n", ph->env.cpu_desc);
+}
+
+static void print_nrcpus(struct perf_header *ph, int fd __maybe_unused,
+			 FILE *fp)
+{
+	fprintf(fp, "# nrcpus online : %u\n", ph->env.nr_cpus_online);
+	fprintf(fp, "# nrcpus avail : %u\n", ph->env.nr_cpus_avail);
+}
+
+static void print_version(struct perf_header *ph, int fd __maybe_unused,
+			  FILE *fp)
+{
+	fprintf(fp, "# perf version : %s\n", ph->env.version);
+}
+
+static void print_cmdline(struct perf_header *ph, int fd __maybe_unused,
+			  FILE *fp)
+{
+	int nr, i;
+	char *str;
+
+	nr = ph->env.nr_cmdline;
+	str = ph->env.cmdline;
+
+	fprintf(fp, "# cmdline : ");
+
+	for (i = 0; i < nr; i++) {
+		fprintf(fp, "%s ", str);
+		str += strlen(str) + 1;
+	}
+	fputc('\n', fp);
+}
+
+static void print_cpu_topology(struct perf_header *ph, int fd __maybe_unused,
+			       FILE *fp)
+{
+	int nr, i;
+	char *str;
+
+	nr = ph->env.nr_sibling_cores;
+	str = ph->env.sibling_cores;
+
+	for (i = 0; i < nr; i++) {
+		fprintf(fp, "# sibling cores   : %s\n", str);
+		str += strlen(str) + 1;
+	}
+
+	nr = ph->env.nr_sibling_threads;
+	str = ph->env.sibling_threads;
+
+	for (i = 0; i < nr; i++) {
+		fprintf(fp, "# sibling threads : %s\n", str);
+		str += strlen(str) + 1;
+	}
+}
+
+static void free_event_desc(struct perf_evsel *events)
+{
+	struct perf_evsel *evsel;
+
+	if (!events)
+		return;
+
+	for (evsel = events; evsel->attr.size; evsel++) {
+		zfree(&evsel->name);
+		zfree(&evsel->id);
+	}
+
+	free(events);
+}
+
+static struct perf_evsel *
+read_event_desc(struct perf_header *ph, int fd)
+{
+	struct perf_evsel *evsel, *events = NULL;
+	u64 *id;
+	void *buf = NULL;
+	u32 nre, sz, nr, i, j;
+	ssize_t ret;
+	size_t msz;
+
+	/* number of events */
+	ret = readn(fd, &nre, sizeof(nre));
+	if (ret != (ssize_t)sizeof(nre))
+		goto error;
+
+	if (ph->needs_swap)
+		nre = bswap_32(nre);
+
+	ret = readn(fd, &sz, sizeof(sz));
+	if (ret != (ssize_t)sizeof(sz))
+		goto error;
+
+	if (ph->needs_swap)
+		sz = bswap_32(sz);
+
+	/* buffer to hold on file attr struct */
+	buf = malloc(sz);
+	if (!buf)
+		goto error;
+
+	/* the last event terminates with evsel->attr.size == 0: */
+	events = calloc(nre + 1, sizeof(*events));
+	if (!events)
+		goto error;
+
+	msz = sizeof(evsel->attr);
+	if (sz < msz)
+		msz = sz;
+
+	for (i = 0, evsel = events; i < nre; evsel++, i++) {
+		evsel->idx = i;
+
+		/*
+		 * must read entire on-file attr struct to
+		 * sync up with layout.
+		 */
+		ret = readn(fd, buf, sz);
+		if (ret != (ssize_t)sz)
+			goto error;
+
+		if (ph->needs_swap)
+			perf_event__attr_swap(buf);
+
+		memcpy(&evsel->attr, buf, msz);
+
+		ret = readn(fd, &nr, sizeof(nr));
+		if (ret != (ssize_t)sizeof(nr))
+			goto error;
+
+		if (ph->needs_swap) {
+			nr = bswap_32(nr);
+			evsel->needs_swap = true;
+		}
+
+		evsel->name = do_read_string(fd, ph);
+
+		if (!nr)
+			continue;
+
+		id = calloc(nr, sizeof(*id));
+		if (!id)
+			goto error;
+		evsel->ids = nr;
+		evsel->id = id;
+
+		for (j = 0 ; j < nr; j++) {
+			ret = readn(fd, id, sizeof(*id));
+			if (ret != (ssize_t)sizeof(*id))
+				goto error;
+			if (ph->needs_swap)
+				*id = bswap_64(*id);
+			id++;
 		}
-		++feat;
 	}
-out_free:
-	free(feat_sec);
-	return err;
+out:
+	free(buf);
+	return events;
+error:
+	if (events)
+		free_event_desc(events);
+	events = NULL;
+	goto out;
 }
 
-int perf_file_header__read(struct perf_file_header *self,
-			   struct perf_header *ph, int fd)
+static void print_event_desc(struct perf_header *ph, int fd, FILE *fp)
 {
-	lseek(fd, 0, SEEK_SET);
+	struct perf_evsel *evsel, *events = read_event_desc(ph, fd);
+	u32 j;
+	u64 *id;
 
-	if (do_read(fd, self, sizeof(*self)) <= 0 ||
-	    memcmp(&self->magic, __perf_magic, sizeof(self->magic)))
-		return -1;
+	if (!events) {
+		fprintf(fp, "# event desc: not available or unable to read\n");
+		return;
+	}
 
-	if (self->attr_size != sizeof(struct perf_file_attr)) {
-		u64 attr_size = bswap_64(self->attr_size);
+	for (evsel = events; evsel->attr.size; evsel++) {
+		fprintf(fp, "# event : name = %s, ", evsel->name);
+
+		fprintf(fp, "type = %d, config = 0x%"PRIx64
+			    ", config1 = 0x%"PRIx64", config2 = 0x%"PRIx64,
+				evsel->attr.type,
+				(u64)evsel->attr.config,
+				(u64)evsel->attr.config1,
+				(u64)evsel->attr.config2);
+
+		fprintf(fp, ", excl_usr = %d, excl_kern = %d",
+				evsel->attr.exclude_user,
+				evsel->attr.exclude_kernel);
+
+		fprintf(fp, ", excl_host = %d, excl_guest = %d",
+				evsel->attr.exclude_host,
+				evsel->attr.exclude_guest);
+
+		fprintf(fp, ", precise_ip = %d", evsel->attr.precise_ip);
+
+		fprintf(fp, ", attr_mmap2 = %d", evsel->attr.mmap2);
+		fprintf(fp, ", attr_mmap  = %d", evsel->attr.mmap);
+		fprintf(fp, ", attr_mmap_data = %d", evsel->attr.mmap_data);
+		if (evsel->ids) {
+			fprintf(fp, ", id = {");
+			for (j = 0, id = evsel->id; j < evsel->ids; j++, id++) {
+				if (j)
+					fputc(',', fp);
+				fprintf(fp, " %"PRIu64, *id);
+			}
+			fprintf(fp, " }");
+		}
 
-		if (attr_size != sizeof(struct perf_file_attr))
-			return -1;
+		fputc('\n', fp);
+	}
 
-		mem_bswap_64(self, offsetof(struct perf_file_header,
-					    adds_features));
-		ph->needs_swap = true;
+	free_event_desc(events);
+}
+
+static void print_total_mem(struct perf_header *ph, int fd __maybe_unused,
+			    FILE *fp)
+{
+	fprintf(fp, "# total memory : %Lu kB\n", ph->env.total_mem);
+}
+
+static void print_numa_topology(struct perf_header *ph, int fd __maybe_unused,
+				FILE *fp)
+{
+	u32 nr, c, i;
+	char *str, *tmp;
+	uint64_t mem_total, mem_free;
+
+	/* nr nodes */
+	nr = ph->env.nr_numa_nodes;
+	str = ph->env.numa_nodes;
+
+	for (i = 0; i < nr; i++) {
+		/* node number */
+		c = strtoul(str, &tmp, 0);
+		if (*tmp != ':')
+			goto error;
+
+		str = tmp + 1;
+		mem_total = strtoull(str, &tmp, 0);
+		if (*tmp != ':')
+			goto error;
+
+		str = tmp + 1;
+		mem_free = strtoull(str, &tmp, 0);
+		if (*tmp != ':')
+			goto error;
+
+		fprintf(fp, "# node%u meminfo  : total = %"PRIu64" kB,"
+			    " free = %"PRIu64" kB\n",
+			c, mem_total, mem_free);
+
+		str = tmp + 1;
+		fprintf(fp, "# node%u cpu list : %s\n", c, str);
+
+		str += strlen(str) + 1;
 	}
+	return;
+error:
+	fprintf(fp, "# numa topology : not available\n");
+}
 
-	if (self->size != sizeof(*self)) {
-		/* Support the previous format */
-		if (self->size == offsetof(typeof(*self), adds_features))
-			bitmap_zero(self->adds_features, HEADER_FEAT_BITS);
-		else
-			return -1;
+static void print_cpuid(struct perf_header *ph, int fd __maybe_unused, FILE *fp)
+{
+	fprintf(fp, "# cpuid : %s\n", ph->env.cpuid);
+}
+
+static void print_branch_stack(struct perf_header *ph __maybe_unused,
+			       int fd __maybe_unused, FILE *fp)
+{
+	fprintf(fp, "# contains samples with branch stack\n");
+}
+
+static void print_pmu_mappings(struct perf_header *ph, int fd __maybe_unused,
+			       FILE *fp)
+{
+	const char *delimiter = "# pmu mappings: ";
+	char *str, *tmp;
+	u32 pmu_num;
+	u32 type;
+
+	pmu_num = ph->env.nr_pmu_mappings;
+	if (!pmu_num) {
+		fprintf(fp, "# pmu mappings: not available\n");
+		return;
 	}
 
-	memcpy(&ph->adds_features, &self->adds_features,
-	       sizeof(ph->adds_features));
-	/*
-	 * FIXME: hack that assumes that if we need swap the perf.data file
-	 * may be coming from an arch with a different word-size, ergo different
-	 * DEFINE_BITMAP format, investigate more later, but for now its mostly
-	 * safe to assume that we have a build-id section. Trace files probably
-	 * have several other issues in this realm anyway...
-	 */
-	if (ph->needs_swap) {
-		memset(&ph->adds_features, 0, sizeof(ph->adds_features));
-		perf_header__set_feat(ph, HEADER_BUILD_ID);
+	str = ph->env.pmu_mappings;
+
+	while (pmu_num) {
+		type = strtoul(str, &tmp, 0);
+		if (*tmp != ':')
+			goto error;
+
+		str = tmp + 1;
+		fprintf(fp, "%s%s = %" PRIu32, delimiter, str, type);
+
+		delimiter = ", ";
+		str += strlen(str) + 1;
+		pmu_num--;
 	}
 
-	ph->event_offset = self->event_types.offset;
-	ph->event_size   = self->event_types.size;
-	ph->data_offset  = self->data.offset;
-	ph->data_size	 = self->data.size;
-	return 0;
+	fprintf(fp, "\n");
+
+	if (!pmu_num)
+		return;
+error:
+	fprintf(fp, "# pmu mappings: unable to read\n");
+}
+
+static void print_group_desc(struct perf_header *ph, int fd __maybe_unused,
+			     FILE *fp)
+{
+	struct perf_session *session;
+	struct perf_evsel *evsel;
+	u32 nr = 0;
+
+	session = container_of(ph, struct perf_session, header);
+
+	evlist__for_each(session->evlist, evsel) {
+		if (perf_evsel__is_group_leader(evsel) &&
+		    evsel->nr_members > 1) {
+			fprintf(fp, "# group: %s{%s", evsel->group_name ?: "",
+				perf_evsel__name(evsel));
+
+			nr = evsel->nr_members - 1;
+		} else if (nr) {
+			fprintf(fp, ",%s", perf_evsel__name(evsel));
+
+			if (--nr == 0)
+				fprintf(fp, "}\n");
+		}
+	}
 }
 
 static int __event_process_build_id(struct build_id_event *bev,
@@ -750,28 +1557,91 @@ out:
 	return err;
 }
 
-static int perf_header__read_build_ids(struct perf_header *self,
-			int input, u64 offset, u64 size)
+static int perf_header__read_build_ids_abi_quirk(struct perf_header *header,
+						 int input, u64 offset, u64 size)
 {
-	struct perf_session *session = container_of(self,
-			struct perf_session, header);
+	struct perf_session *session = container_of(header, struct perf_session, header);
+	struct {
+		struct perf_event_header   header;
+		u8			   build_id[PERF_ALIGN(BUILD_ID_SIZE, sizeof(u64))];
+		char			   filename[0];
+	} old_bev;
 	struct build_id_event bev;
 	char filename[PATH_MAX];
 	u64 limit = offset + size;
+
+	while (offset < limit) {
+		ssize_t len;
+
+		if (readn(input, &old_bev, sizeof(old_bev)) != sizeof(old_bev))
+			return -1;
+
+		if (header->needs_swap)
+			perf_event_header__bswap(&old_bev.header);
+
+		len = old_bev.header.size - sizeof(old_bev);
+		if (readn(input, filename, len) != len)
+			return -1;
+
+		bev.header = old_bev.header;
+
+		/*
+		 * As the pid is the missing value, we need to fill
+		 * it properly. The header.misc value give us nice hint.
+		 */
+		bev.pid	= HOST_KERNEL_ID;
+		if (bev.header.misc == PERF_RECORD_MISC_GUEST_USER ||
+		    bev.header.misc == PERF_RECORD_MISC_GUEST_KERNEL)
+			bev.pid	= DEFAULT_GUEST_KERNEL_ID;
+
+		memcpy(bev.build_id, old_bev.build_id, sizeof(bev.build_id));
+		__event_process_build_id(&bev, filename, session);
+
+		offset += bev.header.size;
+	}
+
+	return 0;
+}
+
+static int perf_header__read_build_ids(struct perf_header *header,
+				       int input, u64 offset, u64 size)
+{
+	struct perf_session *session = container_of(header, struct perf_session, header);
+	struct build_id_event bev;
+	char filename[PATH_MAX];
+	u64 limit = offset + size, orig_offset = offset;
 	int err = -1;
 
 	while (offset < limit) {
 		ssize_t len;
 
-		if (read(input, &bev, sizeof(bev)) != sizeof(bev))
+		if (readn(input, &bev, sizeof(bev)) != sizeof(bev))
 			goto out;
 
-		if (self->needs_swap)
+		if (header->needs_swap)
 			perf_event_header__bswap(&bev.header);
 
 		len = bev.header.size - sizeof(bev);
-		if (read(input, filename, len) != len)
+		if (readn(input, filename, len) != len)
 			goto out;
+		/*
+		 * The a1645ce1 changeset:
+		 *
+		 * "perf: 'perf kvm' tool for monitoring guest performance from host"
+		 *
+		 * Added a field to struct build_id_event that broke the file
+		 * format.
+		 *
+		 * Since the kernel build-id is the first entry, process the
+		 * table using the old format if the well known
+		 * '[kernel.kallsyms]' string for the kernel build-id has the
+		 * first 4 characters chopped off (where the pid_t sits).
+		 */
+		if (memcmp(filename, "nel.kallsyms]", 13) == 0) {
+			if (lseek(input, orig_offset, SEEK_SET) == (off_t)-1)
+				return -1;
+			return perf_header__read_build_ids_abi_quirk(header, input, offset, size);
+		}
 
 		__event_process_build_id(&bev, filename, session);
 
@@ -782,304 +1652,1248 @@ out:
 	return err;
 }
 
-static int perf_file_section__process(struct perf_file_section *self,
-				      struct perf_header *ph,
-				      int feat, int fd)
+static int process_tracing_data(struct perf_file_section *section __maybe_unused,
+				struct perf_header *ph __maybe_unused,
+				int fd, void *data)
+{
+	ssize_t ret = trace_report(fd, data, false);
+	return ret < 0 ? -1 : 0;
+}
+
+static int process_build_id(struct perf_file_section *section,
+			    struct perf_header *ph, int fd,
+			    void *data __maybe_unused)
+{
+	if (perf_header__read_build_ids(ph, fd, section->offset, section->size))
+		pr_debug("Failed to read buildids, continuing...\n");
+	return 0;
+}
+
+static int process_hostname(struct perf_file_section *section __maybe_unused,
+			    struct perf_header *ph, int fd,
+			    void *data __maybe_unused)
+{
+	ph->env.hostname = do_read_string(fd, ph);
+	return ph->env.hostname ? 0 : -ENOMEM;
+}
+
+static int process_osrelease(struct perf_file_section *section __maybe_unused,
+			     struct perf_header *ph, int fd,
+			     void *data __maybe_unused)
+{
+	ph->env.os_release = do_read_string(fd, ph);
+	return ph->env.os_release ? 0 : -ENOMEM;
+}
+
+static int process_version(struct perf_file_section *section __maybe_unused,
+			   struct perf_header *ph, int fd,
+			   void *data __maybe_unused)
+{
+	ph->env.version = do_read_string(fd, ph);
+	return ph->env.version ? 0 : -ENOMEM;
+}
+
+static int process_arch(struct perf_file_section *section __maybe_unused,
+			struct perf_header *ph,	int fd,
+			void *data __maybe_unused)
+{
+	ph->env.arch = do_read_string(fd, ph);
+	return ph->env.arch ? 0 : -ENOMEM;
+}
+
+static int process_nrcpus(struct perf_file_section *section __maybe_unused,
+			  struct perf_header *ph, int fd,
+			  void *data __maybe_unused)
+{
+	ssize_t ret;
+	u32 nr;
+
+	ret = readn(fd, &nr, sizeof(nr));
+	if (ret != sizeof(nr))
+		return -1;
+
+	if (ph->needs_swap)
+		nr = bswap_32(nr);
+
+	ph->env.nr_cpus_online = nr;
+
+	ret = readn(fd, &nr, sizeof(nr));
+	if (ret != sizeof(nr))
+		return -1;
+
+	if (ph->needs_swap)
+		nr = bswap_32(nr);
+
+	ph->env.nr_cpus_avail = nr;
+	return 0;
+}
+
+static int process_cpudesc(struct perf_file_section *section __maybe_unused,
+			   struct perf_header *ph, int fd,
+			   void *data __maybe_unused)
+{
+	ph->env.cpu_desc = do_read_string(fd, ph);
+	return ph->env.cpu_desc ? 0 : -ENOMEM;
+}
+
+static int process_cpuid(struct perf_file_section *section __maybe_unused,
+			 struct perf_header *ph,  int fd,
+			 void *data __maybe_unused)
+{
+	ph->env.cpuid = do_read_string(fd, ph);
+	return ph->env.cpuid ? 0 : -ENOMEM;
+}
+
+static int process_total_mem(struct perf_file_section *section __maybe_unused,
+			     struct perf_header *ph, int fd,
+			     void *data __maybe_unused)
+{
+	uint64_t mem;
+	ssize_t ret;
+
+	ret = readn(fd, &mem, sizeof(mem));
+	if (ret != sizeof(mem))
+		return -1;
+
+	if (ph->needs_swap)
+		mem = bswap_64(mem);
+
+	ph->env.total_mem = mem;
+	return 0;
+}
+
+static struct perf_evsel *
+perf_evlist__find_by_index(struct perf_evlist *evlist, int idx)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each(evlist, evsel) {
+		if (evsel->idx == idx)
+			return evsel;
+	}
+
+	return NULL;
+}
+
+static void
+perf_evlist__set_event_name(struct perf_evlist *evlist,
+			    struct perf_evsel *event)
+{
+	struct perf_evsel *evsel;
+
+	if (!event->name)
+		return;
+
+	evsel = perf_evlist__find_by_index(evlist, event->idx);
+	if (!evsel)
+		return;
+
+	if (evsel->name)
+		return;
+
+	evsel->name = strdup(event->name);
+}
+
+static int
+process_event_desc(struct perf_file_section *section __maybe_unused,
+		   struct perf_header *header, int fd,
+		   void *data __maybe_unused)
 {
-	if (lseek(fd, self->offset, SEEK_SET) == (off_t)-1) {
-		pr_debug("Failed to lseek to %Ld offset for feature %d, "
-			 "continuing...\n", self->offset, feat);
+	struct perf_session *session;
+	struct perf_evsel *evsel, *events = read_event_desc(header, fd);
+
+	if (!events)
 		return 0;
+
+	session = container_of(header, struct perf_session, header);
+	for (evsel = events; evsel->attr.size; evsel++)
+		perf_evlist__set_event_name(session->evlist, evsel);
+
+	free_event_desc(events);
+
+	return 0;
+}
+
+static int process_cmdline(struct perf_file_section *section __maybe_unused,
+			   struct perf_header *ph, int fd,
+			   void *data __maybe_unused)
+{
+	ssize_t ret;
+	char *str;
+	u32 nr, i;
+	struct strbuf sb;
+
+	ret = readn(fd, &nr, sizeof(nr));
+	if (ret != sizeof(nr))
+		return -1;
+
+	if (ph->needs_swap)
+		nr = bswap_32(nr);
+
+	ph->env.nr_cmdline = nr;
+	strbuf_init(&sb, 128);
+
+	for (i = 0; i < nr; i++) {
+		str = do_read_string(fd, ph);
+		if (!str)
+			goto error;
+
+		/* include a NULL character at the end */
+		strbuf_add(&sb, str, strlen(str) + 1);
+		free(str);
 	}
+	ph->env.cmdline = strbuf_detach(&sb, NULL);
+	return 0;
 
-	switch (feat) {
-	case HEADER_TRACE_INFO:
-		trace_report(fd, false);
-		break;
+error:
+	strbuf_release(&sb);
+	return -1;
+}
 
-	case HEADER_BUILD_ID:
-		if (perf_header__read_build_ids(ph, fd, self->offset, self->size))
-			pr_debug("Failed to read buildids, continuing...\n");
-		break;
-	default:
-		pr_debug("unknown feature %d, continuing...\n", feat);
+static int process_cpu_topology(struct perf_file_section *section __maybe_unused,
+				struct perf_header *ph, int fd,
+				void *data __maybe_unused)
+{
+	ssize_t ret;
+	u32 nr, i;
+	char *str;
+	struct strbuf sb;
+
+	ret = readn(fd, &nr, sizeof(nr));
+	if (ret != sizeof(nr))
+		return -1;
+
+	if (ph->needs_swap)
+		nr = bswap_32(nr);
+
+	ph->env.nr_sibling_cores = nr;
+	strbuf_init(&sb, 128);
+
+	for (i = 0; i < nr; i++) {
+		str = do_read_string(fd, ph);
+		if (!str)
+			goto error;
+
+		/* include a NULL character at the end */
+		strbuf_add(&sb, str, strlen(str) + 1);
+		free(str);
 	}
+	ph->env.sibling_cores = strbuf_detach(&sb, NULL);
+
+	ret = readn(fd, &nr, sizeof(nr));
+	if (ret != sizeof(nr))
+		return -1;
+
+	if (ph->needs_swap)
+		nr = bswap_32(nr);
+
+	ph->env.nr_sibling_threads = nr;
 
+	for (i = 0; i < nr; i++) {
+		str = do_read_string(fd, ph);
+		if (!str)
+			goto error;
+
+		/* include a NULL character at the end */
+		strbuf_add(&sb, str, strlen(str) + 1);
+		free(str);
+	}
+	ph->env.sibling_threads = strbuf_detach(&sb, NULL);
 	return 0;
+
+error:
+	strbuf_release(&sb);
+	return -1;
 }
 
-static int perf_file_header__read_pipe(struct perf_pipe_file_header *self,
-				       struct perf_header *ph, int fd,
-				       bool repipe)
+static int process_numa_topology(struct perf_file_section *section __maybe_unused,
+				 struct perf_header *ph, int fd,
+				 void *data __maybe_unused)
 {
-	if (do_read(fd, self, sizeof(*self)) <= 0 ||
-	    memcmp(&self->magic, __perf_magic, sizeof(self->magic)))
+	ssize_t ret;
+	u32 nr, node, i;
+	char *str;
+	uint64_t mem_total, mem_free;
+	struct strbuf sb;
+
+	/* nr nodes */
+	ret = readn(fd, &nr, sizeof(nr));
+	if (ret != sizeof(nr))
+		goto error;
+
+	if (ph->needs_swap)
+		nr = bswap_32(nr);
+
+	ph->env.nr_numa_nodes = nr;
+	strbuf_init(&sb, 256);
+
+	for (i = 0; i < nr; i++) {
+		/* node number */
+		ret = readn(fd, &node, sizeof(node));
+		if (ret != sizeof(node))
+			goto error;
+
+		ret = readn(fd, &mem_total, sizeof(u64));
+		if (ret != sizeof(u64))
+			goto error;
+
+		ret = readn(fd, &mem_free, sizeof(u64));
+		if (ret != sizeof(u64))
+			goto error;
+
+		if (ph->needs_swap) {
+			node = bswap_32(node);
+			mem_total = bswap_64(mem_total);
+			mem_free = bswap_64(mem_free);
+		}
+
+		strbuf_addf(&sb, "%u:%"PRIu64":%"PRIu64":",
+			    node, mem_total, mem_free);
+
+		str = do_read_string(fd, ph);
+		if (!str)
+			goto error;
+
+		/* include a NULL character at the end */
+		strbuf_add(&sb, str, strlen(str) + 1);
+		free(str);
+	}
+	ph->env.numa_nodes = strbuf_detach(&sb, NULL);
+	return 0;
+
+error:
+	strbuf_release(&sb);
+	return -1;
+}
+
+static int process_pmu_mappings(struct perf_file_section *section __maybe_unused,
+				struct perf_header *ph, int fd,
+				void *data __maybe_unused)
+{
+	ssize_t ret;
+	char *name;
+	u32 pmu_num;
+	u32 type;
+	struct strbuf sb;
+
+	ret = readn(fd, &pmu_num, sizeof(pmu_num));
+	if (ret != sizeof(pmu_num))
 		return -1;
 
-	if (repipe && do_write(STDOUT_FILENO, self, sizeof(*self)) < 0)
+	if (ph->needs_swap)
+		pmu_num = bswap_32(pmu_num);
+
+	if (!pmu_num) {
+		pr_debug("pmu mappings not available\n");
+		return 0;
+	}
+
+	ph->env.nr_pmu_mappings = pmu_num;
+	strbuf_init(&sb, 128);
+
+	while (pmu_num) {
+		if (readn(fd, &type, sizeof(type)) != sizeof(type))
+			goto error;
+		if (ph->needs_swap)
+			type = bswap_32(type);
+
+		name = do_read_string(fd, ph);
+		if (!name)
+			goto error;
+
+		strbuf_addf(&sb, "%u:%s", type, name);
+		/* include a NULL character at the end */
+		strbuf_add(&sb, "", 1);
+
+		free(name);
+		pmu_num--;
+	}
+	ph->env.pmu_mappings = strbuf_detach(&sb, NULL);
+	return 0;
+
+error:
+	strbuf_release(&sb);
+	return -1;
+}
+
+static int process_group_desc(struct perf_file_section *section __maybe_unused,
+			      struct perf_header *ph, int fd,
+			      void *data __maybe_unused)
+{
+	size_t ret = -1;
+	u32 i, nr, nr_groups;
+	struct perf_session *session;
+	struct perf_evsel *evsel, *leader = NULL;
+	struct group_desc {
+		char *name;
+		u32 leader_idx;
+		u32 nr_members;
+	} *desc;
+
+	if (readn(fd, &nr_groups, sizeof(nr_groups)) != sizeof(nr_groups))
 		return -1;
 
-	if (self->size != sizeof(*self)) {
-		u64 size = bswap_64(self->size);
+	if (ph->needs_swap)
+		nr_groups = bswap_32(nr_groups);
 
-		if (size != sizeof(*self))
-			return -1;
+	ph->env.nr_groups = nr_groups;
+	if (!nr_groups) {
+		pr_debug("group desc not available\n");
+		return 0;
+	}
+
+	desc = calloc(nr_groups, sizeof(*desc));
+	if (!desc)
+		return -1;
+
+	for (i = 0; i < nr_groups; i++) {
+		desc[i].name = do_read_string(fd, ph);
+		if (!desc[i].name)
+			goto out_free;
+
+		if (readn(fd, &desc[i].leader_idx, sizeof(u32)) != sizeof(u32))
+			goto out_free;
+
+		if (readn(fd, &desc[i].nr_members, sizeof(u32)) != sizeof(u32))
+			goto out_free;
 
-		ph->needs_swap = true;
+		if (ph->needs_swap) {
+			desc[i].leader_idx = bswap_32(desc[i].leader_idx);
+			desc[i].nr_members = bswap_32(desc[i].nr_members);
+		}
 	}
 
-	return 0;
+	/*
+	 * Rebuild group relationship based on the group_desc
+	 */
+	session = container_of(ph, struct perf_session, header);
+	session->evlist->nr_groups = nr_groups;
+
+	i = nr = 0;
+	evlist__for_each(session->evlist, evsel) {
+		if (evsel->idx == (int) desc[i].leader_idx) {
+			evsel->leader = evsel;
+			/* {anon_group} is a dummy name */
+			if (strcmp(desc[i].name, "{anon_group}")) {
+				evsel->group_name = desc[i].name;
+				desc[i].name = NULL;
+			}
+			evsel->nr_members = desc[i].nr_members;
+
+			if (i >= nr_groups || nr > 0) {
+				pr_debug("invalid group desc\n");
+				goto out_free;
+			}
+
+			leader = evsel;
+			nr = evsel->nr_members - 1;
+			i++;
+		} else if (nr) {
+			/* This is a group member */
+			evsel->leader = leader;
+
+			nr--;
+		}
+	}
+
+	if (i != nr_groups || nr != 0) {
+		pr_debug("invalid group desc\n");
+		goto out_free;
+	}
+
+	ret = 0;
+out_free:
+	for (i = 0; i < nr_groups; i++)
+		zfree(&desc[i].name);
+	free(desc);
+
+	return ret;
 }
 
-static int perf_header__read_pipe(struct perf_session *session, int fd)
+struct feature_ops {
+	int (*write)(int fd, struct perf_header *h, struct perf_evlist *evlist);
+	void (*print)(struct perf_header *h, int fd, FILE *fp);
+	int (*process)(struct perf_file_section *section,
+		       struct perf_header *h, int fd, void *data);
+	const char *name;
+	bool full_only;
+};
+
+#define FEAT_OPA(n, func) \
+	[n] = { .name = #n, .write = write_##func, .print = print_##func }
+#define FEAT_OPP(n, func) \
+	[n] = { .name = #n, .write = write_##func, .print = print_##func, \
+		.process = process_##func }
+#define FEAT_OPF(n, func) \
+	[n] = { .name = #n, .write = write_##func, .print = print_##func, \
+		.process = process_##func, .full_only = true }
+
+/* feature_ops not implemented: */
+#define print_tracing_data	NULL
+#define print_build_id		NULL
+
+static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
+	FEAT_OPP(HEADER_TRACING_DATA,	tracing_data),
+	FEAT_OPP(HEADER_BUILD_ID,	build_id),
+	FEAT_OPP(HEADER_HOSTNAME,	hostname),
+	FEAT_OPP(HEADER_OSRELEASE,	osrelease),
+	FEAT_OPP(HEADER_VERSION,	version),
+	FEAT_OPP(HEADER_ARCH,		arch),
+	FEAT_OPP(HEADER_NRCPUS,		nrcpus),
+	FEAT_OPP(HEADER_CPUDESC,	cpudesc),
+	FEAT_OPP(HEADER_CPUID,		cpuid),
+	FEAT_OPP(HEADER_TOTAL_MEM,	total_mem),
+	FEAT_OPP(HEADER_EVENT_DESC,	event_desc),
+	FEAT_OPP(HEADER_CMDLINE,	cmdline),
+	FEAT_OPF(HEADER_CPU_TOPOLOGY,	cpu_topology),
+	FEAT_OPF(HEADER_NUMA_TOPOLOGY,	numa_topology),
+	FEAT_OPA(HEADER_BRANCH_STACK,	branch_stack),
+	FEAT_OPP(HEADER_PMU_MAPPINGS,	pmu_mappings),
+	FEAT_OPP(HEADER_GROUP_DESC,	group_desc),
+};
+
+struct header_print_data {
+	FILE *fp;
+	bool full; /* extended list of headers */
+};
+
+static int perf_file_section__fprintf_info(struct perf_file_section *section,
+					   struct perf_header *ph,
+					   int feat, int fd, void *data)
 {
-	struct perf_header *self = &session->header;
-	struct perf_pipe_file_header f_header;
+	struct header_print_data *hd = data;
 
-	if (perf_file_header__read_pipe(&f_header, self, fd,
-					session->repipe) < 0) {
-		pr_debug("incompatible file format\n");
-		return -EINVAL;
+	if (lseek(fd, section->offset, SEEK_SET) == (off_t)-1) {
+		pr_debug("Failed to lseek to %" PRIu64 " offset for feature "
+				"%d, continuing...\n", section->offset, feat);
+		return 0;
+	}
+	if (feat >= HEADER_LAST_FEATURE) {
+		pr_warning("unknown feature %d\n", feat);
+		return 0;
 	}
+	if (!feat_ops[feat].print)
+		return 0;
 
-	session->fd = fd;
+	if (!feat_ops[feat].full_only || hd->full)
+		feat_ops[feat].print(ph, fd, hd->fp);
+	else
+		fprintf(hd->fp, "# %s info available, use -I to display\n",
+			feat_ops[feat].name);
 
 	return 0;
 }
 
-int perf_header__read(struct perf_session *session, int fd)
+int perf_header__fprintf_info(struct perf_session *session, FILE *fp, bool full)
 {
-	struct perf_header *self = &session->header;
-	struct perf_file_header	f_header;
-	struct perf_file_attr	f_attr;
-	u64			f_id;
-	int nr_attrs, nr_ids, i, j;
+	struct header_print_data hd;
+	struct perf_header *header = &session->header;
+	int fd = perf_data_file__fd(session->file);
+	hd.fp = fp;
+	hd.full = full;
+
+	perf_header__process_sections(header, fd, &hd,
+				      perf_file_section__fprintf_info);
+	return 0;
+}
 
-	if (session->fd_pipe)
-		return perf_header__read_pipe(session, fd);
+static int do_write_feat(int fd, struct perf_header *h, int type,
+			 struct perf_file_section **p,
+			 struct perf_evlist *evlist)
+{
+	int err;
+	int ret = 0;
 
-	if (perf_file_header__read(&f_header, self, fd) < 0) {
-		pr_debug("incompatible file format\n");
-		return -EINVAL;
+	if (perf_header__has_feat(h, type)) {
+		if (!feat_ops[type].write)
+			return -1;
+
+		(*p)->offset = lseek(fd, 0, SEEK_CUR);
+
+		err = feat_ops[type].write(fd, h, evlist);
+		if (err < 0) {
+			pr_debug("failed to write feature %d\n", type);
+
+			/* undo anything written */
+			lseek(fd, (*p)->offset, SEEK_SET);
+
+			return -1;
+		}
+		(*p)->size = lseek(fd, 0, SEEK_CUR) - (*p)->offset;
+		(*p)++;
 	}
+	return ret;
+}
 
-	nr_attrs = f_header.attrs.size / sizeof(f_attr);
-	lseek(fd, f_header.attrs.offset, SEEK_SET);
+static int perf_header__adds_write(struct perf_header *header,
+				   struct perf_evlist *evlist, int fd)
+{
+	int nr_sections;
+	struct perf_file_section *feat_sec, *p;
+	int sec_size;
+	u64 sec_start;
+	int feat;
+	int err;
 
-	for (i = 0; i < nr_attrs; i++) {
-		struct perf_header_attr *attr;
-		off_t tmp;
+	nr_sections = bitmap_weight(header->adds_features, HEADER_FEAT_BITS);
+	if (!nr_sections)
+		return 0;
 
-		if (perf_header__getbuffer64(self, fd, &f_attr, sizeof(f_attr)))
-			goto out_errno;
+	feat_sec = p = calloc(nr_sections, sizeof(*feat_sec));
+	if (feat_sec == NULL)
+		return -ENOMEM;
 
-		tmp = lseek(fd, 0, SEEK_CUR);
+	sec_size = sizeof(*feat_sec) * nr_sections;
 
-		attr = perf_header_attr__new(&f_attr.attr);
-		if (attr == NULL)
-			 return -ENOMEM;
+	sec_start = header->feat_offset;
+	lseek(fd, sec_start + sec_size, SEEK_SET);
 
-		nr_ids = f_attr.ids.size / sizeof(u64);
-		lseek(fd, f_attr.ids.offset, SEEK_SET);
+	for_each_set_bit(feat, header->adds_features, HEADER_FEAT_BITS) {
+		if (do_write_feat(fd, header, feat, &p, evlist))
+			perf_header__clear_feat(header, feat);
+	}
 
-		for (j = 0; j < nr_ids; j++) {
-			if (perf_header__getbuffer64(self, fd, &f_id, sizeof(f_id)))
-				goto out_errno;
+	lseek(fd, sec_start, SEEK_SET);
+	/*
+	 * may write more than needed due to dropped feature, but
+	 * this is okay, reader will skip the mising entries
+	 */
+	err = do_write(fd, feat_sec, sec_size);
+	if (err < 0)
+		pr_debug("failed to write feature section\n");
+	free(feat_sec);
+	return err;
+}
 
-			if (perf_header_attr__add_id(attr, f_id) < 0) {
-				perf_header_attr__delete(attr);
-				return -ENOMEM;
-			}
+int perf_header__write_pipe(int fd)
+{
+	struct perf_pipe_file_header f_header;
+	int err;
+
+	f_header = (struct perf_pipe_file_header){
+		.magic	   = PERF_MAGIC,
+		.size	   = sizeof(f_header),
+	};
+
+	err = do_write(fd, &f_header, sizeof(f_header));
+	if (err < 0) {
+		pr_debug("failed to write perf pipe header\n");
+		return err;
+	}
+
+	return 0;
+}
+
+int perf_session__write_header(struct perf_session *session,
+			       struct perf_evlist *evlist,
+			       int fd, bool at_exit)
+{
+	struct perf_file_header f_header;
+	struct perf_file_attr   f_attr;
+	struct perf_header *header = &session->header;
+	struct perf_evsel *evsel;
+	u64 attr_offset;
+	int err;
+
+	lseek(fd, sizeof(f_header), SEEK_SET);
+
+	evlist__for_each(session->evlist, evsel) {
+		evsel->id_offset = lseek(fd, 0, SEEK_CUR);
+		err = do_write(fd, evsel->id, evsel->ids * sizeof(u64));
+		if (err < 0) {
+			pr_debug("failed to write perf header\n");
+			return err;
 		}
-		if (perf_header__add_attr(self, attr) < 0) {
-			perf_header_attr__delete(attr);
-			return -ENOMEM;
+	}
+
+	attr_offset = lseek(fd, 0, SEEK_CUR);
+
+	evlist__for_each(evlist, evsel) {
+		f_attr = (struct perf_file_attr){
+			.attr = evsel->attr,
+			.ids  = {
+				.offset = evsel->id_offset,
+				.size   = evsel->ids * sizeof(u64),
+			}
+		};
+		err = do_write(fd, &f_attr, sizeof(f_attr));
+		if (err < 0) {
+			pr_debug("failed to write perf header attribute\n");
+			return err;
 		}
+	}
 
-		lseek(fd, tmp, SEEK_SET);
+	if (!header->data_offset)
+		header->data_offset = lseek(fd, 0, SEEK_CUR);
+	header->feat_offset = header->data_offset + header->data_size;
+
+	if (at_exit) {
+		err = perf_header__adds_write(header, evlist, fd);
+		if (err < 0)
+			return err;
 	}
 
-	if (f_header.event_types.size) {
-		lseek(fd, f_header.event_types.offset, SEEK_SET);
-		events = malloc(f_header.event_types.size);
-		if (events == NULL)
-			return -ENOMEM;
-		if (perf_header__getbuffer64(self, fd, events,
-					     f_header.event_types.size))
-			goto out_errno;
-		event_count =  f_header.event_types.size / sizeof(struct perf_trace_event_type);
+	f_header = (struct perf_file_header){
+		.magic	   = PERF_MAGIC,
+		.size	   = sizeof(f_header),
+		.attr_size = sizeof(f_attr),
+		.attrs = {
+			.offset = attr_offset,
+			.size   = evlist->nr_entries * sizeof(f_attr),
+		},
+		.data = {
+			.offset = header->data_offset,
+			.size	= header->data_size,
+		},
+		/* event_types is ignored, store zeros */
+	};
+
+	memcpy(&f_header.adds_features, &header->adds_features, sizeof(header->adds_features));
+
+	lseek(fd, 0, SEEK_SET);
+	err = do_write(fd, &f_header, sizeof(f_header));
+	if (err < 0) {
+		pr_debug("failed to write perf header\n");
+		return err;
 	}
+	lseek(fd, header->data_offset + header->data_size, SEEK_SET);
 
-	perf_header__process_sections(self, fd, perf_file_section__process);
+	return 0;
+}
 
-	lseek(fd, self->data_offset, SEEK_SET);
+static int perf_header__getbuffer64(struct perf_header *header,
+				    int fd, void *buf, size_t size)
+{
+	if (readn(fd, buf, size) <= 0)
+		return -1;
+
+	if (header->needs_swap)
+		mem_bswap_64(buf, size);
 
-	self->frozen = 1;
 	return 0;
-out_errno:
-	return -errno;
 }
 
-u64 perf_header__sample_type(struct perf_header *header)
+int perf_header__process_sections(struct perf_header *header, int fd,
+				  void *data,
+				  int (*process)(struct perf_file_section *section,
+						 struct perf_header *ph,
+						 int feat, int fd, void *data))
 {
-	u64 type = 0;
-	int i;
+	struct perf_file_section *feat_sec, *sec;
+	int nr_sections;
+	int sec_size;
+	int feat;
+	int err;
 
-	for (i = 0; i < header->attrs; i++) {
-		struct perf_header_attr *attr = header->attr[i];
+	nr_sections = bitmap_weight(header->adds_features, HEADER_FEAT_BITS);
+	if (!nr_sections)
+		return 0;
 
-		if (!type)
-			type = attr->attr.sample_type;
-		else if (type != attr->attr.sample_type)
-			die("non matching sample_type");
+	feat_sec = sec = calloc(nr_sections, sizeof(*feat_sec));
+	if (!feat_sec)
+		return -1;
+
+	sec_size = sizeof(*feat_sec) * nr_sections;
+
+	lseek(fd, header->feat_offset, SEEK_SET);
+
+	err = perf_header__getbuffer64(header, fd, feat_sec, sec_size);
+	if (err < 0)
+		goto out_free;
+
+	for_each_set_bit(feat, header->adds_features, HEADER_LAST_FEATURE) {
+		err = process(sec++, header, feat, fd, data);
+		if (err < 0)
+			goto out_free;
 	}
+	err = 0;
+out_free:
+	free(feat_sec);
+	return err;
+}
+
+static const int attr_file_abi_sizes[] = {
+	[0] = PERF_ATTR_SIZE_VER0,
+	[1] = PERF_ATTR_SIZE_VER1,
+	[2] = PERF_ATTR_SIZE_VER2,
+	[3] = PERF_ATTR_SIZE_VER3,
+	0,
+};
 
-	return type;
+/*
+ * In the legacy file format, the magic number is not used to encode endianness.
+ * hdr_sz was used to encode endianness. But given that hdr_sz can vary based
+ * on ABI revisions, we need to try all combinations for all endianness to
+ * detect the endianness.
+ */
+static int try_all_file_abis(uint64_t hdr_sz, struct perf_header *ph)
+{
+	uint64_t ref_size, attr_size;
+	int i;
+
+	for (i = 0 ; attr_file_abi_sizes[i]; i++) {
+		ref_size = attr_file_abi_sizes[i]
+			 + sizeof(struct perf_file_section);
+		if (hdr_sz != ref_size) {
+			attr_size = bswap_64(hdr_sz);
+			if (attr_size != ref_size)
+				continue;
+
+			ph->needs_swap = true;
+		}
+		pr_debug("ABI%d perf.data file detected, need_swap=%d\n",
+			 i,
+			 ph->needs_swap);
+		return 0;
+	}
+	/* could not determine endianness */
+	return -1;
 }
 
-struct perf_event_attr *
-perf_header__find_attr(u64 id, struct perf_header *header)
+#define PERF_PIPE_HDR_VER0	16
+
+static const size_t attr_pipe_abi_sizes[] = {
+	[0] = PERF_PIPE_HDR_VER0,
+	0,
+};
+
+/*
+ * In the legacy pipe format, there is an implicit assumption that endiannesss
+ * between host recording the samples, and host parsing the samples is the
+ * same. This is not always the case given that the pipe output may always be
+ * redirected into a file and analyzed on a different machine with possibly a
+ * different endianness and perf_event ABI revsions in the perf tool itself.
+ */
+static int try_all_pipe_abis(uint64_t hdr_sz, struct perf_header *ph)
 {
+	u64 attr_size;
 	int i;
 
+	for (i = 0 ; attr_pipe_abi_sizes[i]; i++) {
+		if (hdr_sz != attr_pipe_abi_sizes[i]) {
+			attr_size = bswap_64(hdr_sz);
+			if (attr_size != hdr_sz)
+				continue;
+
+			ph->needs_swap = true;
+		}
+		pr_debug("Pipe ABI%d perf.data file detected\n", i);
+		return 0;
+	}
+	return -1;
+}
+
+bool is_perf_magic(u64 magic)
+{
+	if (!memcmp(&magic, __perf_magic1, sizeof(magic))
+		|| magic == __perf_magic2
+		|| magic == __perf_magic2_sw)
+		return true;
+
+	return false;
+}
+
+static int check_magic_endian(u64 magic, uint64_t hdr_sz,
+			      bool is_pipe, struct perf_header *ph)
+{
+	int ret;
+
+	/* check for legacy format */
+	ret = memcmp(&magic, __perf_magic1, sizeof(magic));
+	if (ret == 0) {
+		ph->version = PERF_HEADER_VERSION_1;
+		pr_debug("legacy perf.data format\n");
+		if (is_pipe)
+			return try_all_pipe_abis(hdr_sz, ph);
+
+		return try_all_file_abis(hdr_sz, ph);
+	}
 	/*
-	 * We set id to -1 if the data file doesn't contain sample
-	 * ids. Check for this and avoid walking through the entire
-	 * list of ids which may be large.
+	 * the new magic number serves two purposes:
+	 * - unique number to identify actual perf.data files
+	 * - encode endianness of file
 	 */
-	if (id == -1ULL)
-		return NULL;
 
-	for (i = 0; i < header->attrs; i++) {
-		struct perf_header_attr *attr = header->attr[i];
-		int j;
+	/* check magic number with one endianness */
+	if (magic == __perf_magic2)
+		return 0;
 
-		for (j = 0; j < attr->ids; j++) {
-			if (attr->id[j] == id)
-				return &attr->attr;
+	/* check magic number with opposite endianness */
+	if (magic != __perf_magic2_sw)
+		return -1;
+
+	ph->needs_swap = true;
+	ph->version = PERF_HEADER_VERSION_2;
+
+	return 0;
+}
+
+int perf_file_header__read(struct perf_file_header *header,
+			   struct perf_header *ph, int fd)
+{
+	ssize_t ret;
+
+	lseek(fd, 0, SEEK_SET);
+
+	ret = readn(fd, header, sizeof(*header));
+	if (ret <= 0)
+		return -1;
+
+	if (check_magic_endian(header->magic,
+			       header->attr_size, false, ph) < 0) {
+		pr_debug("magic/endian check failed\n");
+		return -1;
+	}
+
+	if (ph->needs_swap) {
+		mem_bswap_64(header, offsetof(struct perf_file_header,
+			     adds_features));
+	}
+
+	if (header->size != sizeof(*header)) {
+		/* Support the previous format */
+		if (header->size == offsetof(typeof(*header), adds_features))
+			bitmap_zero(header->adds_features, HEADER_FEAT_BITS);
+		else
+			return -1;
+	} else if (ph->needs_swap) {
+		/*
+		 * feature bitmap is declared as an array of unsigned longs --
+		 * not good since its size can differ between the host that
+		 * generated the data file and the host analyzing the file.
+		 *
+		 * We need to handle endianness, but we don't know the size of
+		 * the unsigned long where the file was generated. Take a best
+		 * guess at determining it: try 64-bit swap first (ie., file
+		 * created on a 64-bit host), and check if the hostname feature
+		 * bit is set (this feature bit is forced on as of fbe96f2).
+		 * If the bit is not, undo the 64-bit swap and try a 32-bit
+		 * swap. If the hostname bit is still not set (e.g., older data
+		 * file), punt and fallback to the original behavior --
+		 * clearing all feature bits and setting buildid.
+		 */
+		mem_bswap_64(&header->adds_features,
+			    BITS_TO_U64(HEADER_FEAT_BITS));
+
+		if (!test_bit(HEADER_HOSTNAME, header->adds_features)) {
+			/* unswap as u64 */
+			mem_bswap_64(&header->adds_features,
+				    BITS_TO_U64(HEADER_FEAT_BITS));
+
+			/* unswap as u32 */
+			mem_bswap_32(&header->adds_features,
+				    BITS_TO_U32(HEADER_FEAT_BITS));
+		}
+
+		if (!test_bit(HEADER_HOSTNAME, header->adds_features)) {
+			bitmap_zero(header->adds_features, HEADER_FEAT_BITS);
+			set_bit(HEADER_BUILD_ID, header->adds_features);
 		}
 	}
 
-	return NULL;
+	memcpy(&ph->adds_features, &header->adds_features,
+	       sizeof(ph->adds_features));
+
+	ph->data_offset  = header->data.offset;
+	ph->data_size	 = header->data.size;
+	ph->feat_offset  = header->data.offset + header->data.size;
+	return 0;
 }
 
-int event__synthesize_attr(struct perf_event_attr *attr, u16 ids, u64 *id,
-			   event__handler_t process,
-			   struct perf_session *session)
+static int perf_file_section__process(struct perf_file_section *section,
+				      struct perf_header *ph,
+				      int feat, int fd, void *data)
 {
-	event_t *ev;
-	size_t size;
-	int err;
+	if (lseek(fd, section->offset, SEEK_SET) == (off_t)-1) {
+		pr_debug("Failed to lseek to %" PRIu64 " offset for feature "
+			  "%d, continuing...\n", section->offset, feat);
+		return 0;
+	}
 
-	size = sizeof(struct perf_event_attr);
-	size = ALIGN(size, sizeof(u64));
-	size += sizeof(struct perf_event_header);
-	size += ids * sizeof(u64);
+	if (feat >= HEADER_LAST_FEATURE) {
+		pr_debug("unknown feature %d, continuing...\n", feat);
+		return 0;
+	}
 
-	ev = malloc(size);
+	if (!feat_ops[feat].process)
+		return 0;
 
-	ev->attr.attr = *attr;
-	memcpy(ev->attr.id, id, ids * sizeof(u64));
+	return feat_ops[feat].process(section, ph, fd, data);
+}
 
-	ev->attr.header.type = PERF_RECORD_HEADER_ATTR;
-	ev->attr.header.size = size;
+static int perf_file_header__read_pipe(struct perf_pipe_file_header *header,
+				       struct perf_header *ph, int fd,
+				       bool repipe)
+{
+	ssize_t ret;
 
-	err = process(ev, session);
+	ret = readn(fd, header, sizeof(*header));
+	if (ret <= 0)
+		return -1;
 
-	free(ev);
+	if (check_magic_endian(header->magic, header->size, true, ph) < 0) {
+		pr_debug("endian/magic failed\n");
+		return -1;
+	}
 
-	return err;
+	if (ph->needs_swap)
+		header->size = bswap_64(header->size);
+
+	if (repipe && do_write(STDOUT_FILENO, header, sizeof(*header)) < 0)
+		return -1;
+
+	return 0;
 }
 
-int event__synthesize_attrs(struct perf_header *self,
-			    event__handler_t process,
-			    struct perf_session *session)
+static int perf_header__read_pipe(struct perf_session *session)
 {
-	struct perf_header_attr	*attr;
-	int i, err = 0;
+	struct perf_header *header = &session->header;
+	struct perf_pipe_file_header f_header;
 
-	for (i = 0; i < self->attrs; i++) {
-		attr = self->attr[i];
+	if (perf_file_header__read_pipe(&f_header, header,
+					perf_data_file__fd(session->file),
+					session->repipe) < 0) {
+		pr_debug("incompatible file format\n");
+		return -EINVAL;
+	}
 
-		err = event__synthesize_attr(&attr->attr, attr->ids, attr->id,
-					     process, session);
-		if (err) {
-			pr_debug("failed to create perf header attribute\n");
-			return err;
-		}
+	return 0;
+}
+
+static int read_attr(int fd, struct perf_header *ph,
+		     struct perf_file_attr *f_attr)
+{
+	struct perf_event_attr *attr = &f_attr->attr;
+	size_t sz, left;
+	size_t our_sz = sizeof(f_attr->attr);
+	ssize_t ret;
+
+	memset(f_attr, 0, sizeof(*f_attr));
+
+	/* read minimal guaranteed structure */
+	ret = readn(fd, attr, PERF_ATTR_SIZE_VER0);
+	if (ret <= 0) {
+		pr_debug("cannot read %d bytes of header attr\n",
+			 PERF_ATTR_SIZE_VER0);
+		return -1;
 	}
 
-	return err;
+	/* on file perf_event_attr size */
+	sz = attr->size;
+
+	if (ph->needs_swap)
+		sz = bswap_32(sz);
+
+	if (sz == 0) {
+		/* assume ABI0 */
+		sz =  PERF_ATTR_SIZE_VER0;
+	} else if (sz > our_sz) {
+		pr_debug("file uses a more recent and unsupported ABI"
+			 " (%zu bytes extra)\n", sz - our_sz);
+		return -1;
+	}
+	/* what we have not yet read and that we know about */
+	left = sz - PERF_ATTR_SIZE_VER0;
+	if (left) {
+		void *ptr = attr;
+		ptr += PERF_ATTR_SIZE_VER0;
+
+		ret = readn(fd, ptr, left);
+	}
+	/* read perf_file_section, ids are read in caller */
+	ret = readn(fd, &f_attr->ids, sizeof(f_attr->ids));
+
+	return ret <= 0 ? -1 : 0;
 }
 
-int event__process_attr(event_t *self, struct perf_session *session)
+static int perf_evsel__prepare_tracepoint_event(struct perf_evsel *evsel,
+						struct pevent *pevent)
 {
-	struct perf_header_attr *attr;
-	unsigned int i, ids, n_ids;
+	struct event_format *event;
+	char bf[128];
 
-	attr = perf_header_attr__new(&self->attr.attr);
-	if (attr == NULL)
-		return -ENOMEM;
+	/* already prepared */
+	if (evsel->tp_format)
+		return 0;
 
-	ids = self->header.size;
-	ids -= (void *)&self->attr.id - (void *)self;
-	n_ids = ids / sizeof(u64);
+	if (pevent == NULL) {
+		pr_debug("broken or missing trace data\n");
+		return -1;
+	}
 
-	for (i = 0; i < n_ids; i++) {
-		if (perf_header_attr__add_id(attr, self->attr.id[i]) < 0) {
-			perf_header_attr__delete(attr);
-			return -ENOMEM;
-		}
+	event = pevent_find_event(pevent, evsel->attr.config);
+	if (event == NULL)
+		return -1;
+
+	if (!evsel->name) {
+		snprintf(bf, sizeof(bf), "%s:%s", event->system, event->name);
+		evsel->name = strdup(bf);
+		if (evsel->name == NULL)
+			return -1;
+	}
+
+	evsel->tp_format = event;
+	return 0;
+}
+
+static int perf_evlist__prepare_tracepoint_events(struct perf_evlist *evlist,
+						  struct pevent *pevent)
+{
+	struct perf_evsel *pos;
+
+	evlist__for_each(evlist, pos) {
+		if (pos->attr.type == PERF_TYPE_TRACEPOINT &&
+		    perf_evsel__prepare_tracepoint_event(pos, pevent))
+			return -1;
 	}
 
-	if (perf_header__add_attr(&session->header, attr) < 0) {
-		perf_header_attr__delete(attr);
+	return 0;
+}
+
+int perf_session__read_header(struct perf_session *session)
+{
+	struct perf_data_file *file = session->file;
+	struct perf_header *header = &session->header;
+	struct perf_file_header	f_header;
+	struct perf_file_attr	f_attr;
+	u64			f_id;
+	int nr_attrs, nr_ids, i, j;
+	int fd = perf_data_file__fd(file);
+
+	session->evlist = perf_evlist__new();
+	if (session->evlist == NULL)
 		return -ENOMEM;
+
+	if (perf_data_file__is_pipe(file))
+		return perf_header__read_pipe(session);
+
+	if (perf_file_header__read(&f_header, header, fd) < 0)
+		return -EINVAL;
+
+	/*
+	 * Sanity check that perf.data was written cleanly; data size is
+	 * initialized to 0 and updated only if the on_exit function is run.
+	 * If data size is still 0 then the file contains only partial
+	 * information.  Just warn user and process it as much as it can.
+	 */
+	if (f_header.data.size == 0) {
+		pr_warning("WARNING: The %s file's data size field is 0 which is unexpected.\n"
+			   "Was the 'perf record' command properly terminated?\n",
+			   file->path);
+	}
+
+	nr_attrs = f_header.attrs.size / f_header.attr_size;
+	lseek(fd, f_header.attrs.offset, SEEK_SET);
+
+	for (i = 0; i < nr_attrs; i++) {
+		struct perf_evsel *evsel;
+		off_t tmp;
+
+		if (read_attr(fd, header, &f_attr) < 0)
+			goto out_errno;
+
+		if (header->needs_swap)
+			perf_event__attr_swap(&f_attr.attr);
+
+		tmp = lseek(fd, 0, SEEK_CUR);
+		evsel = perf_evsel__new(&f_attr.attr);
+
+		if (evsel == NULL)
+			goto out_delete_evlist;
+
+		evsel->needs_swap = header->needs_swap;
+		/*
+		 * Do it before so that if perf_evsel__alloc_id fails, this
+		 * entry gets purged too at perf_evlist__delete().
+		 */
+		perf_evlist__add(session->evlist, evsel);
+
+		nr_ids = f_attr.ids.size / sizeof(u64);
+		/*
+		 * We don't have the cpu and thread maps on the header, so
+		 * for allocating the perf_sample_id table we fake 1 cpu and
+		 * hattr->ids threads.
+		 */
+		if (perf_evsel__alloc_id(evsel, 1, nr_ids))
+			goto out_delete_evlist;
+
+		lseek(fd, f_attr.ids.offset, SEEK_SET);
+
+		for (j = 0; j < nr_ids; j++) {
+			if (perf_header__getbuffer64(header, fd, &f_id, sizeof(f_id)))
+				goto out_errno;
+
+			perf_evlist__id_add(session->evlist, evsel, 0, j, f_id);
+		}
+
+		lseek(fd, tmp, SEEK_SET);
 	}
 
-	perf_session__update_sample_type(session);
+	symbol_conf.nr_events = nr_attrs;
+
+	perf_header__process_sections(header, fd, &session->tevent,
+				      perf_file_section__process);
+
+	if (perf_evlist__prepare_tracepoint_events(session->evlist,
+						   session->tevent.pevent))
+		goto out_delete_evlist;
 
 	return 0;
+out_errno:
+	return -errno;
+
+out_delete_evlist:
+	perf_evlist__delete(session->evlist);
+	session->evlist = NULL;
+	return -ENOMEM;
 }
 
-int event__synthesize_event_type(u64 event_id, char *name,
-				 event__handler_t process,
-				 struct perf_session *session)
+int perf_event__synthesize_attr(struct perf_tool *tool,
+				struct perf_event_attr *attr, u32 ids, u64 *id,
+				perf_event__handler_t process)
 {
-	event_t ev;
-	size_t size = 0;
-	int err = 0;
+	union perf_event *ev;
+	size_t size;
+	int err;
 
-	memset(&ev, 0, sizeof(ev));
+	size = sizeof(struct perf_event_attr);
+	size = PERF_ALIGN(size, sizeof(u64));
+	size += sizeof(struct perf_event_header);
+	size += ids * sizeof(u64);
+
+	ev = malloc(size);
+
+	if (ev == NULL)
+		return -ENOMEM;
+
+	ev->attr.attr = *attr;
+	memcpy(ev->attr.id, id, ids * sizeof(u64));
 
-	ev.event_type.event_type.event_id = event_id;
-	memset(ev.event_type.event_type.name, 0, MAX_EVENT_NAME);
-	strncpy(ev.event_type.event_type.name, name, MAX_EVENT_NAME - 1);
+	ev->attr.header.type = PERF_RECORD_HEADER_ATTR;
+	ev->attr.header.size = (u16)size;
 
-	ev.event_type.header.type = PERF_RECORD_HEADER_EVENT_TYPE;
-	size = strlen(name);
-	size = ALIGN(size, sizeof(u64));
-	ev.event_type.header.size = sizeof(ev.event_type) -
-		(sizeof(ev.event_type.event_type.name) - size);
+	if (ev->attr.header.size == size)
+		err = process(tool, ev, NULL, NULL);
+	else
+		err = -E2BIG;
 
-	err = process(&ev, session);
+	free(ev);
 
 	return err;
 }
 
-int event__synthesize_event_types(event__handler_t process,
-				  struct perf_session *session)
+int perf_event__synthesize_attrs(struct perf_tool *tool,
+				   struct perf_session *session,
+				   perf_event__handler_t process)
 {
-	struct perf_trace_event_type *type;
-	int i, err = 0;
-
-	for (i = 0; i < event_count; i++) {
-		type = &events[i];
+	struct perf_evsel *evsel;
+	int err = 0;
 
-		err = event__synthesize_event_type(type->event_id, type->name,
-						   process, session);
+	evlist__for_each(session->evlist, evsel) {
+		err = perf_event__synthesize_attr(tool, &evsel->attr, evsel->ids,
+						  evsel->id, process);
 		if (err) {
-			pr_debug("failed to create perf header event type\n");
+			pr_debug("failed to create perf header attribute\n");
 			return err;
 		}
 	}
@@ -1087,79 +2901,138 @@ int event__synthesize_event_types(event__handler_t process,
 	return err;
 }
 
-int event__process_event_type(event_t *self,
-			      struct perf_session *session __unused)
+int perf_event__process_attr(struct perf_tool *tool __maybe_unused,
+			     union perf_event *event,
+			     struct perf_evlist **pevlist)
 {
-	if (perf_header__push_event(self->event_type.event_type.event_id,
-				    self->event_type.event_type.name) < 0)
+	u32 i, ids, n_ids;
+	struct perf_evsel *evsel;
+	struct perf_evlist *evlist = *pevlist;
+
+	if (evlist == NULL) {
+		*pevlist = evlist = perf_evlist__new();
+		if (evlist == NULL)
+			return -ENOMEM;
+	}
+
+	evsel = perf_evsel__new(&event->attr.attr);
+	if (evsel == NULL)
+		return -ENOMEM;
+
+	perf_evlist__add(evlist, evsel);
+
+	ids = event->header.size;
+	ids -= (void *)&event->attr.id - (void *)event;
+	n_ids = ids / sizeof(u64);
+	/*
+	 * We don't have the cpu and thread maps on the header, so
+	 * for allocating the perf_sample_id table we fake 1 cpu and
+	 * hattr->ids threads.
+	 */
+	if (perf_evsel__alloc_id(evsel, 1, n_ids))
 		return -ENOMEM;
 
+	for (i = 0; i < n_ids; i++) {
+		perf_evlist__id_add(evlist, evsel, 0, i, event->attr.id[i]);
+	}
+
+	symbol_conf.nr_events = evlist->nr_entries;
+
 	return 0;
 }
 
-int event__synthesize_tracing_data(int fd, struct perf_event_attr *pattrs,
-				   int nb_events,
-				   event__handler_t process,
-				   struct perf_session *session __unused)
+int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd,
+					struct perf_evlist *evlist,
+					perf_event__handler_t process)
 {
-	event_t ev;
+	union perf_event ev;
+	struct tracing_data *tdata;
 	ssize_t size = 0, aligned_size = 0, padding;
-	int err = 0;
+	int err __maybe_unused = 0;
+
+	/*
+	 * We are going to store the size of the data followed
+	 * by the data contents. Since the fd descriptor is a pipe,
+	 * we cannot seek back to store the size of the data once
+	 * we know it. Instead we:
+	 *
+	 * - write the tracing data to the temp file
+	 * - get/write the data size to pipe
+	 * - write the tracing data from the temp file
+	 *   to the pipe
+	 */
+	tdata = tracing_data_get(&evlist->entries, fd, true);
+	if (!tdata)
+		return -1;
 
 	memset(&ev, 0, sizeof(ev));
 
 	ev.tracing_data.header.type = PERF_RECORD_HEADER_TRACING_DATA;
-	size = read_tracing_data_size(fd, pattrs, nb_events);
-	if (size <= 0)
-		return size;
-	aligned_size = ALIGN(size, sizeof(u64));
+	size = tdata->size;
+	aligned_size = PERF_ALIGN(size, sizeof(u64));
 	padding = aligned_size - size;
 	ev.tracing_data.header.size = sizeof(ev.tracing_data);
 	ev.tracing_data.size = aligned_size;
 
-	process(&ev, session);
+	process(tool, &ev, NULL, NULL);
+
+	/*
+	 * The put function will copy all the tracing data
+	 * stored in temp file to the pipe.
+	 */
+	tracing_data_put(tdata);
 
-	err = read_tracing_data(fd, pattrs, nb_events);
 	write_padded(fd, NULL, 0, padding);
 
 	return aligned_size;
 }
 
-int event__process_tracing_data(event_t *self,
-				struct perf_session *session)
+int perf_event__process_tracing_data(struct perf_tool *tool __maybe_unused,
+				     union perf_event *event,
+				     struct perf_session *session)
 {
-	ssize_t size_read, padding, size = self->tracing_data.size;
-	off_t offset = lseek(session->fd, 0, SEEK_CUR);
+	ssize_t size_read, padding, size = event->tracing_data.size;
+	int fd = perf_data_file__fd(session->file);
+	off_t offset = lseek(fd, 0, SEEK_CUR);
 	char buf[BUFSIZ];
 
 	/* setup for reading amidst mmap */
-	lseek(session->fd, offset + sizeof(struct tracing_data_event),
+	lseek(fd, offset + sizeof(struct tracing_data_event),
 	      SEEK_SET);
 
-	size_read = trace_report(session->fd, session->repipe);
+	size_read = trace_report(fd, &session->tevent,
+				 session->repipe);
+	padding = PERF_ALIGN(size_read, sizeof(u64)) - size_read;
 
-	padding = ALIGN(size_read, sizeof(u64)) - size_read;
-
-	if (read(session->fd, buf, padding) < 0)
-		die("reading input file");
+	if (readn(fd, buf, padding) < 0) {
+		pr_err("%s: reading input file", __func__);
+		return -1;
+	}
 	if (session->repipe) {
 		int retw = write(STDOUT_FILENO, buf, padding);
-		if (retw <= 0 || retw != padding)
-			die("repiping tracing data padding");
+		if (retw <= 0 || retw != padding) {
+			pr_err("%s: repiping tracing data padding", __func__);
+			return -1;
+		}
+	}
+
+	if (size_read + padding != size) {
+		pr_err("%s: tracing data size mismatch", __func__);
+		return -1;
 	}
 
-	if (size_read + padding != size)
-		die("tracing data size mismatch");
+	perf_evlist__prepare_tracepoint_events(session->evlist,
+					       session->tevent.pevent);
 
 	return size_read + padding;
 }
 
-int event__synthesize_build_id(struct dso *pos, u16 misc,
-			       event__handler_t process,
-			       struct machine *machine,
-			       struct perf_session *session)
+int perf_event__synthesize_build_id(struct perf_tool *tool,
+				    struct dso *pos, u16 misc,
+				    perf_event__handler_t process,
+				    struct machine *machine)
 {
-	event_t ev;
+	union perf_event ev;
 	size_t len;
 	int err = 0;
 
@@ -1169,7 +3042,7 @@ int event__synthesize_build_id(struct dso *pos, u16 misc,
 	memset(&ev, 0, sizeof(ev));
 
 	len = pos->long_name_len + 1;
-	len = ALIGN(len, NAME_ALIGN);
+	len = PERF_ALIGN(len, NAME_ALIGN);
 	memcpy(&ev.build_id.build_id, pos->build_id, sizeof(pos->build_id));
 	ev.build_id.header.type = PERF_RECORD_HEADER_BUILD_ID;
 	ev.build_id.header.misc = misc;
@@ -1177,16 +3050,22 @@ int event__synthesize_build_id(struct dso *pos, u16 misc,
 	ev.build_id.header.size = sizeof(ev.build_id) + len;
 	memcpy(&ev.build_id.filename, pos->long_name, pos->long_name_len);
 
-	err = process(&ev, session);
+	err = process(tool, &ev, NULL, machine);
 
 	return err;
 }
 
-int event__process_build_id(event_t *self,
-			    struct perf_session *session)
+int perf_event__process_build_id(struct perf_tool *tool __maybe_unused,
+				 union perf_event *event,
+				 struct perf_session *session)
 {
-	__event_process_build_id(&self->build_id,
-				 self->build_id.filename,
+	__event_process_build_id(&event->build_id,
+				 event->build_id.filename,
 				 session);
 	return 0;
 }
+
+void disable_buildid_cache(void)
+{
+	no_buildid_cache = true;
+}
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 402ac2454cf..d08cfe49940 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -1,28 +1,43 @@
 #ifndef __PERF_HEADER_H
 #define __PERF_HEADER_H
 
-#include "../../../include/linux/perf_event.h"
+#include <linux/perf_event.h>
 #include <sys/types.h>
 #include <stdbool.h>
-#include "types.h"
-#include "event.h"
-
 #include <linux/bitmap.h>
+#include <linux/types.h>
+#include "event.h"
 
-struct perf_header_attr {
-	struct perf_event_attr attr;
-	int ids, size;
-	u64 *id;
-	off_t id_offset;
-};
 
 enum {
-	HEADER_TRACE_INFO = 1,
+	HEADER_RESERVED		= 0,	/* always cleared */
+	HEADER_FIRST_FEATURE	= 1,
+	HEADER_TRACING_DATA	= 1,
 	HEADER_BUILD_ID,
+
+	HEADER_HOSTNAME,
+	HEADER_OSRELEASE,
+	HEADER_VERSION,
+	HEADER_ARCH,
+	HEADER_NRCPUS,
+	HEADER_CPUDESC,
+	HEADER_CPUID,
+	HEADER_TOTAL_MEM,
+	HEADER_CMDLINE,
+	HEADER_EVENT_DESC,
+	HEADER_CPU_TOPOLOGY,
+	HEADER_NUMA_TOPOLOGY,
+	HEADER_BRANCH_STACK,
+	HEADER_PMU_MAPPINGS,
+	HEADER_GROUP_DESC,
 	HEADER_LAST_FEATURE,
+	HEADER_FEAT_BITS	= 256,
 };
 
-#define HEADER_FEAT_BITS			256
+enum perf_header_version {
+	PERF_HEADER_VERSION_1,
+	PERF_HEADER_VERSION_2,
+};
 
 struct perf_file_section {
 	u64 offset;
@@ -35,6 +50,7 @@ struct perf_file_header {
 	u64				attr_size;
 	struct perf_file_section	attrs;
 	struct perf_file_section	data;
+	/* event_types is ignored */
 	struct perf_file_section	event_types;
 	DECLARE_BITMAP(adds_features, HEADER_FEAT_BITS);
 };
@@ -46,82 +62,98 @@ struct perf_pipe_file_header {
 
 struct perf_header;
 
-int perf_file_header__read(struct perf_file_header *self,
+int perf_file_header__read(struct perf_file_header *header,
 			   struct perf_header *ph, int fd);
 
+struct perf_session_env {
+	char			*hostname;
+	char			*os_release;
+	char			*version;
+	char			*arch;
+	int			nr_cpus_online;
+	int			nr_cpus_avail;
+	char			*cpu_desc;
+	char			*cpuid;
+	unsigned long long	total_mem;
+
+	int			nr_cmdline;
+	int			nr_sibling_cores;
+	int			nr_sibling_threads;
+	int			nr_numa_nodes;
+	int			nr_pmu_mappings;
+	int			nr_groups;
+	char			*cmdline;
+	char			*sibling_cores;
+	char			*sibling_threads;
+	char			*numa_nodes;
+	char			*pmu_mappings;
+};
+
 struct perf_header {
-	int			frozen;
-	int			attrs, size;
-	bool			needs_swap;
-	struct perf_header_attr **attr;
-	s64			attr_offset;
-	u64			data_offset;
-	u64			data_size;
-	u64			event_offset;
-	u64			event_size;
+	enum perf_header_version	version;
+	bool				needs_swap;
+	u64				data_offset;
+	u64				data_size;
+	u64				feat_offset;
 	DECLARE_BITMAP(adds_features, HEADER_FEAT_BITS);
+	struct perf_session_env 	env;
 };
 
-int perf_header__init(struct perf_header *self);
-void perf_header__exit(struct perf_header *self);
+struct perf_evlist;
+struct perf_session;
 
-int perf_header__read(struct perf_session *session, int fd);
-int perf_header__write(struct perf_header *self, int fd, bool at_exit);
+int perf_session__read_header(struct perf_session *session);
+int perf_session__write_header(struct perf_session *session,
+			       struct perf_evlist *evlist,
+			       int fd, bool at_exit);
 int perf_header__write_pipe(int fd);
 
-int perf_header__add_attr(struct perf_header *self,
-			  struct perf_header_attr *attr);
-
-int perf_header__push_event(u64 id, const char *name);
-char *perf_header__find_event(u64 id);
+void perf_header__set_feat(struct perf_header *header, int feat);
+void perf_header__clear_feat(struct perf_header *header, int feat);
+bool perf_header__has_feat(const struct perf_header *header, int feat);
 
-struct perf_header_attr *perf_header_attr__new(struct perf_event_attr *attr);
-void perf_header_attr__delete(struct perf_header_attr *self);
+int perf_header__set_cmdline(int argc, const char **argv);
 
-int perf_header_attr__add_id(struct perf_header_attr *self, u64 id);
+int perf_header__process_sections(struct perf_header *header, int fd,
+				  void *data,
+				  int (*process)(struct perf_file_section *section,
+				  struct perf_header *ph,
+				  int feat, int fd, void *data));
 
-u64 perf_header__sample_type(struct perf_header *header);
-struct perf_event_attr *
-perf_header__find_attr(u64 id, struct perf_header *header);
-void perf_header__set_feat(struct perf_header *self, int feat);
-bool perf_header__has_feat(const struct perf_header *self, int feat);
-
-int perf_header__process_sections(struct perf_header *self, int fd,
-				  int (*process)(struct perf_file_section *self,
-						 struct perf_header *ph,
-						 int feat, int fd));
+int perf_header__fprintf_info(struct perf_session *s, FILE *fp, bool full);
 
 int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
-			  const char *name, bool is_kallsyms);
+			  const char *name, bool is_kallsyms, bool is_vdso);
 int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir);
 
-int event__synthesize_attr(struct perf_event_attr *attr, u16 ids, u64 *id,
-			   event__handler_t process,
-			   struct perf_session *session);
-int event__synthesize_attrs(struct perf_header *self,
-			    event__handler_t process,
-			    struct perf_session *session);
-int event__process_attr(event_t *self, struct perf_session *session);
-
-int event__synthesize_event_type(u64 event_id, char *name,
-				 event__handler_t process,
+int perf_event__synthesize_attr(struct perf_tool *tool,
+				struct perf_event_attr *attr, u32 ids, u64 *id,
+				perf_event__handler_t process);
+int perf_event__synthesize_attrs(struct perf_tool *tool,
+				 struct perf_session *session,
+				 perf_event__handler_t process);
+int perf_event__process_attr(struct perf_tool *tool, union perf_event *event,
+			     struct perf_evlist **pevlist);
+
+int perf_event__synthesize_tracing_data(struct perf_tool *tool,
+					int fd, struct perf_evlist *evlist,
+					perf_event__handler_t process);
+int perf_event__process_tracing_data(struct perf_tool *tool,
+				     union perf_event *event,
+				     struct perf_session *session);
+
+int perf_event__synthesize_build_id(struct perf_tool *tool,
+				    struct dso *pos, u16 misc,
+				    perf_event__handler_t process,
+				    struct machine *machine);
+int perf_event__process_build_id(struct perf_tool *tool,
+				 union perf_event *event,
 				 struct perf_session *session);
-int event__synthesize_event_types(event__handler_t process,
-				  struct perf_session *session);
-int event__process_event_type(event_t *self,
-			      struct perf_session *session);
-
-int event__synthesize_tracing_data(int fd, struct perf_event_attr *pattrs,
-				   int nb_events,
-				   event__handler_t process,
-				   struct perf_session *session);
-int event__process_tracing_data(event_t *self,
-				struct perf_session *session);
-
-int event__synthesize_build_id(struct dso *pos, u16 misc,
-			       event__handler_t process,
-			       struct machine *machine,
-			       struct perf_session *session);
-int event__process_build_id(event_t *self, struct perf_session *session);
+bool is_perf_magic(u64 magic);
+
+/*
+ * arch specific callback
+ */
+int get_cpuid(char *buffer, size_t sz);
 
 #endif /* __PERF_HEADER_H */
diff --git a/tools/perf/util/help.c b/tools/perf/util/help.c
index 6f2975a0035..86c37c47226 100644
--- a/tools/perf/util/help.c
+++ b/tools/perf/util/help.c
@@ -3,6 +3,7 @@
 #include "exec_cmd.h"
 #include "levenshtein.h"
 #include "help.h"
+#include <termios.h>
 
 void add_cmdname(struct cmdnames *cmds, const char *name, size_t len)
 {
@@ -21,8 +22,8 @@ static void clean_cmdnames(struct cmdnames *cmds)
 	unsigned int i;
 
 	for (i = 0; i < cmds->cnt; ++i)
-		free(cmds->names[i]);
-	free(cmds->names);
+		zfree(&cmds->names[i]);
+	zfree(&cmds->names);
 	cmds->cnt = 0;
 	cmds->alloc = 0;
 }
@@ -262,9 +263,8 @@ static void add_cmd_list(struct cmdnames *cmds, struct cmdnames *old)
 
 	for (i = 0; i < old->cnt; i++)
 		cmds->names[cmds->cnt++] = old->names[i];
-	free(old->names);
+	zfree(&old->names);
 	old->cnt = 0;
-	old->names = NULL;
 }
 
 const char *help_unknown_cmd(const char *cmd)
@@ -331,7 +331,8 @@ const char *help_unknown_cmd(const char *cmd)
 	exit(1);
 }
 
-int cmd_version(int argc __used, const char **argv __used, const char *prefix __used)
+int cmd_version(int argc __maybe_unused, const char **argv __maybe_unused,
+		const char *prefix __maybe_unused)
 {
 	printf("perf version %s\n", perf_version_string);
 	return 0;
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 07f89b66b31..30df6187ee0 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -3,89 +3,406 @@
 #include "hist.h"
 #include "session.h"
 #include "sort.h"
+#include "evsel.h"
+#include "annotate.h"
 #include <math.h>
 
+static bool hists__filter_entry_by_dso(struct hists *hists,
+				       struct hist_entry *he);
+static bool hists__filter_entry_by_thread(struct hists *hists,
+					  struct hist_entry *he);
+static bool hists__filter_entry_by_symbol(struct hists *hists,
+					  struct hist_entry *he);
+
 struct callchain_param	callchain_param = {
 	.mode	= CHAIN_GRAPH_REL,
-	.min_percent = 0.5
+	.min_percent = 0.5,
+	.order  = ORDER_CALLEE,
+	.key	= CCKEY_FUNCTION
 };
 
-static void hist_entry__add_cpumode_period(struct hist_entry *self,
-					   unsigned int cpumode, u64 period)
+u16 hists__col_len(struct hists *hists, enum hist_column col)
+{
+	return hists->col_len[col];
+}
+
+void hists__set_col_len(struct hists *hists, enum hist_column col, u16 len)
+{
+	hists->col_len[col] = len;
+}
+
+bool hists__new_col_len(struct hists *hists, enum hist_column col, u16 len)
+{
+	if (len > hists__col_len(hists, col)) {
+		hists__set_col_len(hists, col, len);
+		return true;
+	}
+	return false;
+}
+
+void hists__reset_col_len(struct hists *hists)
+{
+	enum hist_column col;
+
+	for (col = 0; col < HISTC_NR_COLS; ++col)
+		hists__set_col_len(hists, col, 0);
+}
+
+static void hists__set_unres_dso_col_len(struct hists *hists, int dso)
+{
+	const unsigned int unresolved_col_width = BITS_PER_LONG / 4;
+
+	if (hists__col_len(hists, dso) < unresolved_col_width &&
+	    !symbol_conf.col_width_list_str && !symbol_conf.field_sep &&
+	    !symbol_conf.dso_list)
+		hists__set_col_len(hists, dso, unresolved_col_width);
+}
+
+void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
+{
+	const unsigned int unresolved_col_width = BITS_PER_LONG / 4;
+	int symlen;
+	u16 len;
+
+	/*
+	 * +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);
+	}
+
+	len = thread__comm_len(h->thread);
+	if (hists__new_col_len(hists, HISTC_COMM, len))
+		hists__set_col_len(hists, HISTC_THREAD, len + 6);
+
+	if (h->ms.map) {
+		len = dso__name_len(h->ms.map->dso);
+		hists__new_col_len(hists, HISTC_DSO, len);
+	}
+
+	if (h->parent)
+		hists__new_col_len(hists, HISTC_PARENT, h->parent->namelen);
+
+	if (h->branch_info) {
+		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);
+			hists__new_col_len(hists, HISTC_DSO_FROM, symlen);
+		} else {
+			symlen = unresolved_col_width + 4 + 2;
+			hists__new_col_len(hists, HISTC_SYMBOL_FROM, symlen);
+			hists__set_unres_dso_col_len(hists, HISTC_DSO_FROM);
+		}
+
+		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);
+			hists__new_col_len(hists, HISTC_DSO_TO, symlen);
+		} else {
+			symlen = unresolved_col_width + 4 + 2;
+			hists__new_col_len(hists, HISTC_SYMBOL_TO, symlen);
+			hists__set_unres_dso_col_len(hists, HISTC_DSO_TO);
+		}
+	}
+
+	if (h->mem_info) {
+		if (h->mem_info->daddr.sym) {
+			symlen = (int)h->mem_info->daddr.sym->namelen + 4
+			       + unresolved_col_width + 2;
+			hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL,
+					   symlen);
+			hists__new_col_len(hists, HISTC_MEM_DCACHELINE,
+					   symlen + 1);
+		} else {
+			symlen = unresolved_col_width + 4 + 2;
+			hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL,
+					   symlen);
+		}
+		if (h->mem_info->daddr.map) {
+			symlen = dso__name_len(h->mem_info->daddr.map->dso);
+			hists__new_col_len(hists, HISTC_MEM_DADDR_DSO,
+					   symlen);
+		} else {
+			symlen = unresolved_col_width + 4 + 2;
+			hists__set_unres_dso_col_len(hists, HISTC_MEM_DADDR_DSO);
+		}
+	} else {
+		symlen = unresolved_col_width + 4 + 2;
+		hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL, symlen);
+		hists__set_unres_dso_col_len(hists, HISTC_MEM_DADDR_DSO);
+	}
+
+	hists__new_col_len(hists, HISTC_MEM_LOCKED, 6);
+	hists__new_col_len(hists, HISTC_MEM_TLB, 22);
+	hists__new_col_len(hists, HISTC_MEM_SNOOP, 12);
+	hists__new_col_len(hists, HISTC_MEM_LVL, 21 + 3);
+	hists__new_col_len(hists, HISTC_LOCAL_WEIGHT, 12);
+	hists__new_col_len(hists, HISTC_GLOBAL_WEIGHT, 12);
+
+	if (h->transaction)
+		hists__new_col_len(hists, HISTC_TRANSACTION,
+				   hist_entry__transaction_len());
+}
+
+void hists__output_recalc_col_len(struct hists *hists, int max_rows)
+{
+	struct rb_node *next = rb_first(&hists->entries);
+	struct hist_entry *n;
+	int row = 0;
+
+	hists__reset_col_len(hists);
+
+	while (next && row++ < max_rows) {
+		n = rb_entry(next, struct hist_entry, rb_node);
+		if (!n->filtered)
+			hists__calc_col_len(hists, n);
+		next = rb_next(&n->rb_node);
+	}
+}
+
+static void he_stat__add_cpumode_period(struct he_stat *he_stat,
+					unsigned int cpumode, u64 period)
 {
 	switch (cpumode) {
 	case PERF_RECORD_MISC_KERNEL:
-		self->period_sys += period;
+		he_stat->period_sys += period;
 		break;
 	case PERF_RECORD_MISC_USER:
-		self->period_us += period;
+		he_stat->period_us += period;
 		break;
 	case PERF_RECORD_MISC_GUEST_KERNEL:
-		self->period_guest_sys += period;
+		he_stat->period_guest_sys += period;
 		break;
 	case PERF_RECORD_MISC_GUEST_USER:
-		self->period_guest_us += period;
+		he_stat->period_guest_us += period;
 		break;
 	default:
 		break;
 	}
 }
 
+static void he_stat__add_period(struct he_stat *he_stat, u64 period,
+				u64 weight)
+{
+
+	he_stat->period		+= period;
+	he_stat->weight		+= weight;
+	he_stat->nr_events	+= 1;
+}
+
+static void he_stat__add_stat(struct he_stat *dest, struct he_stat *src)
+{
+	dest->period		+= src->period;
+	dest->period_sys	+= src->period_sys;
+	dest->period_us		+= src->period_us;
+	dest->period_guest_sys	+= src->period_guest_sys;
+	dest->period_guest_us	+= src->period_guest_us;
+	dest->nr_events		+= src->nr_events;
+	dest->weight		+= src->weight;
+}
+
+static void he_stat__decay(struct he_stat *he_stat)
+{
+	he_stat->period = (he_stat->period * 7) / 8;
+	he_stat->nr_events = (he_stat->nr_events * 7) / 8;
+	/* XXX need decay for weight too? */
+}
+
+static bool hists__decay_entry(struct hists *hists, struct hist_entry *he)
+{
+	u64 prev_period = he->stat.period;
+	u64 diff;
+
+	if (prev_period == 0)
+		return true;
+
+	he_stat__decay(&he->stat);
+	if (symbol_conf.cumulate_callchain)
+		he_stat__decay(he->stat_acc);
+
+	diff = prev_period - he->stat.period;
+
+	hists->stats.total_period -= diff;
+	if (!he->filtered)
+		hists->stats.total_non_filtered_period -= diff;
+
+	return he->stat.period == 0;
+}
+
+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;
+
+	while (next) {
+		n = rb_entry(next, struct hist_entry, rb_node);
+		next = rb_next(&n->rb_node);
+		/*
+		 * We may be annotating this, for instance, so keep it here in
+		 * case some it gets new samples, we'll eventually free it when
+		 * the user stops browsing and it agains gets fully decayed.
+		 */
+		if (((zap_user && n->level == '.') ||
+		     (zap_kernel && n->level != '.') ||
+		     hists__decay_entry(hists, n)) &&
+		    !n->used) {
+			rb_erase(&n->rb_node, &hists->entries);
+
+			if (sort__need_collapse)
+				rb_erase(&n->rb_node_in, &hists->entries_collapsed);
+
+			--hists->nr_entries;
+			if (!n->filtered)
+				--hists->nr_non_filtered_entries;
+
+			hist_entry__free(n);
+		}
+	}
+}
+
 /*
  * histogram, sorted on item, collects periods
  */
 
-static struct hist_entry *hist_entry__new(struct hist_entry *template)
+static struct hist_entry *hist_entry__new(struct hist_entry *template,
+					  bool sample_self)
 {
-	size_t callchain_size = symbol_conf.use_callchain ? sizeof(struct callchain_node) : 0;
-	struct hist_entry *self = malloc(sizeof(*self) + callchain_size);
+	size_t callchain_size = 0;
+	struct hist_entry *he;
+
+	if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain)
+		callchain_size = sizeof(struct callchain_root);
+
+	he = zalloc(sizeof(*he) + callchain_size);
+
+	if (he != NULL) {
+		*he = *template;
+
+		if (symbol_conf.cumulate_callchain) {
+			he->stat_acc = malloc(sizeof(he->stat));
+			if (he->stat_acc == NULL) {
+				free(he);
+				return NULL;
+			}
+			memcpy(he->stat_acc, &he->stat, sizeof(he->stat));
+			if (!sample_self)
+				memset(&he->stat, 0, sizeof(he->stat));
+		}
+
+		if (he->ms.map)
+			he->ms.map->referenced = true;
+
+		if (he->branch_info) {
+			/*
+			 * This branch info is (a part of) allocated from
+			 * sample__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->stat_acc);
+				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)
+				he->branch_info->to.map->referenced = true;
+		}
+
+		if (he->mem_info) {
+			if (he->mem_info->iaddr.map)
+				he->mem_info->iaddr.map->referenced = true;
+			if (he->mem_info->daddr.map)
+				he->mem_info->daddr.map->referenced = true;
+		}
 
-	if (self != NULL) {
-		*self = *template;
-		self->nr_events = 1;
 		if (symbol_conf.use_callchain)
-			callchain_init(self->callchain);
+			callchain_init(he->callchain);
+
+		INIT_LIST_HEAD(&he->pairs.node);
 	}
 
-	return self;
+	return he;
 }
 
-static void hists__inc_nr_entries(struct hists *self, struct hist_entry *entry)
+static u8 symbol__parent_filter(const struct symbol *parent)
 {
-	if (entry->ms.sym && self->max_sym_namelen < entry->ms.sym->namelen)
-		self->max_sym_namelen = entry->ms.sym->namelen;
-	++self->nr_entries;
+	if (symbol_conf.exclude_other && parent == NULL)
+		return 1 << HIST_FILTER__PARENT;
+	return 0;
 }
 
-struct hist_entry *__hists__add_entry(struct hists *self,
-				      struct addr_location *al,
-				      struct symbol *sym_parent, u64 period)
+static struct hist_entry *add_hist_entry(struct hists *hists,
+					 struct hist_entry *entry,
+					 struct addr_location *al,
+					 bool sample_self)
 {
-	struct rb_node **p = &self->entries.rb_node;
+	struct rb_node **p;
 	struct rb_node *parent = NULL;
 	struct hist_entry *he;
-	struct hist_entry entry = {
-		.thread	= al->thread,
-		.ms = {
-			.map	= al->map,
-			.sym	= al->sym,
-		},
-		.ip	= al->addr,
-		.level	= al->level,
-		.period	= period,
-		.parent = sym_parent,
-	};
-	int cmp;
+	int64_t cmp;
+	u64 period = entry->stat.period;
+	u64 weight = entry->stat.weight;
+
+	p = &hists->entries_in->rb_node;
 
 	while (*p != NULL) {
 		parent = *p;
-		he = rb_entry(parent, struct hist_entry, rb_node);
+		he = rb_entry(parent, struct hist_entry, rb_node_in);
 
-		cmp = hist_entry__cmp(&entry, he);
+		/*
+		 * Make sure that it receives arguments in a same order as
+		 * hist_entry__collapse() so that we can use an appropriate
+		 * function when searching an entry regardless which sort
+		 * keys were used.
+		 */
+		cmp = hist_entry__cmp(he, entry);
 
 		if (!cmp) {
-			he->period += period;
-			++he->nr_events;
+			if (sample_self)
+				he_stat__add_period(&he->stat, period, weight);
+			if (symbol_conf.cumulate_callchain)
+				he_stat__add_period(he->stat_acc, period, weight);
+
+			/*
+			 * This mem info was allocated from sample__resolve_mem
+			 * and will not be used anymore.
+			 */
+			zfree(&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
+			 * mis-adjust symbol addresses when computing
+			 * the history counter to increment.
+			 */
+			if (he->ms.map != entry->ms.map) {
+				he->ms.map = entry->ms.map;
+				if (he->ms.map)
+					he->ms.map->referenced = true;
+			}
 			goto out;
 		}
 
@@ -95,987 +412,1003 @@ struct hist_entry *__hists__add_entry(struct hists *self,
 			p = &(*p)->rb_right;
 	}
 
-	he = hist_entry__new(&entry);
+	he = hist_entry__new(entry, sample_self);
 	if (!he)
 		return NULL;
-	rb_link_node(&he->rb_node, parent, p);
-	rb_insert_color(&he->rb_node, &self->entries);
-	hists__inc_nr_entries(self, he);
+
+	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);
+	if (sample_self)
+		he_stat__add_cpumode_period(&he->stat, al->cpumode, period);
+	if (symbol_conf.cumulate_callchain)
+		he_stat__add_cpumode_period(he->stat_acc, al->cpumode, period);
 	return he;
 }
 
-int64_t
-hist_entry__cmp(struct hist_entry *left, struct hist_entry *right)
+struct hist_entry *__hists__add_entry(struct hists *hists,
+				      struct addr_location *al,
+				      struct symbol *sym_parent,
+				      struct branch_info *bi,
+				      struct mem_info *mi,
+				      u64 period, u64 weight, u64 transaction,
+				      bool sample_self)
 {
-	struct sort_entry *se;
-	int64_t cmp = 0;
-
-	list_for_each_entry(se, &hist_entry__sort_list, list) {
-		cmp = se->se_cmp(left, right);
-		if (cmp)
-			break;
-	}
+	struct hist_entry entry = {
+		.thread	= al->thread,
+		.comm = thread__comm(al->thread),
+		.ms = {
+			.map	= al->map,
+			.sym	= al->sym,
+		},
+		.cpu	 = al->cpu,
+		.cpumode = al->cpumode,
+		.ip	 = al->addr,
+		.level	 = al->level,
+		.stat = {
+			.nr_events = 1,
+			.period	= period,
+			.weight = weight,
+		},
+		.parent = sym_parent,
+		.filtered = symbol__parent_filter(sym_parent) | al->filtered,
+		.hists	= hists,
+		.branch_info = bi,
+		.mem_info = mi,
+		.transaction = transaction,
+	};
 
-	return cmp;
+	return add_hist_entry(hists, &entry, al, sample_self);
 }
 
-int64_t
-hist_entry__collapse(struct hist_entry *left, struct hist_entry *right)
+static int
+iter_next_nop_entry(struct hist_entry_iter *iter __maybe_unused,
+		    struct addr_location *al __maybe_unused)
 {
-	struct sort_entry *se;
-	int64_t cmp = 0;
+	return 0;
+}
 
-	list_for_each_entry(se, &hist_entry__sort_list, list) {
-		int64_t (*f)(struct hist_entry *, struct hist_entry *);
+static int
+iter_add_next_nop_entry(struct hist_entry_iter *iter __maybe_unused,
+			struct addr_location *al __maybe_unused)
+{
+	return 0;
+}
 
-		f = se->se_collapse ?: se->se_cmp;
+static int
+iter_prepare_mem_entry(struct hist_entry_iter *iter, struct addr_location *al)
+{
+	struct perf_sample *sample = iter->sample;
+	struct mem_info *mi;
 
-		cmp = f(left, right);
-		if (cmp)
-			break;
-	}
+	mi = sample__resolve_mem(sample, al);
+	if (mi == NULL)
+		return -ENOMEM;
 
-	return cmp;
+	iter->priv = mi;
+	return 0;
 }
 
-void hist_entry__free(struct hist_entry *he)
+static int
+iter_add_single_mem_entry(struct hist_entry_iter *iter, struct addr_location *al)
 {
-	free(he);
-}
+	u64 cost;
+	struct mem_info *mi = iter->priv;
+	struct hist_entry *he;
 
-/*
- * collapse the histogram
- */
+	if (mi == NULL)
+		return -EINVAL;
+
+	cost = iter->sample->weight;
+	if (!cost)
+		cost = 1;
 
-static bool collapse__insert_entry(struct rb_root *root, struct hist_entry *he)
+	/*
+	 * must pass period=weight in order to get the correct
+	 * sorting from hists__collapse_resort() which is solely
+	 * based on periods. We want sorting be done on nr_events * weight
+	 * and this is indirectly achieved by passing period=weight here
+	 * and the he_stat__add_period() function.
+	 */
+	he = __hists__add_entry(&iter->evsel->hists, al, iter->parent, NULL, mi,
+				cost, cost, 0, true);
+	if (!he)
+		return -ENOMEM;
+
+	iter->he = he;
+	return 0;
+}
+
+static int
+iter_finish_mem_entry(struct hist_entry_iter *iter,
+		      struct addr_location *al __maybe_unused)
 {
-	struct rb_node **p = &root->rb_node;
-	struct rb_node *parent = NULL;
-	struct hist_entry *iter;
-	int64_t cmp;
+	struct perf_evsel *evsel = iter->evsel;
+	struct hist_entry *he = iter->he;
+	int err = -EINVAL;
 
-	while (*p != NULL) {
-		parent = *p;
-		iter = rb_entry(parent, struct hist_entry, rb_node);
+	if (he == NULL)
+		goto out;
 
-		cmp = hist_entry__collapse(iter, he);
+	hists__inc_nr_samples(&evsel->hists, he->filtered);
 
-		if (!cmp) {
-			iter->period += he->period;
-			hist_entry__free(he);
-			return false;
-		}
+	err = hist_entry__append_callchain(he, iter->sample);
 
-		if (cmp < 0)
-			p = &(*p)->rb_left;
-		else
-			p = &(*p)->rb_right;
-	}
+out:
+	/*
+	 * We don't need to free iter->priv (mem_info) here since
+	 * the mem info was either already freed in add_hist_entry() or
+	 * passed to a new hist entry by hist_entry__new().
+	 */
+	iter->priv = NULL;
 
-	rb_link_node(&he->rb_node, parent, p);
-	rb_insert_color(&he->rb_node, root);
-	return true;
+	iter->he = NULL;
+	return err;
 }
 
-void hists__collapse_resort(struct hists *self)
+static int
+iter_prepare_branch_entry(struct hist_entry_iter *iter, struct addr_location *al)
 {
-	struct rb_root tmp;
-	struct rb_node *next;
-	struct hist_entry *n;
+	struct branch_info *bi;
+	struct perf_sample *sample = iter->sample;
 
-	if (!sort__need_collapse)
-		return;
+	bi = sample__resolve_bstack(sample, al);
+	if (!bi)
+		return -ENOMEM;
 
-	tmp = RB_ROOT;
-	next = rb_first(&self->entries);
-	self->nr_entries = 0;
-	self->max_sym_namelen = 0;
+	iter->curr = 0;
+	iter->total = sample->branch_stack->nr;
 
-	while (next) {
-		n = rb_entry(next, struct hist_entry, rb_node);
-		next = rb_next(&n->rb_node);
+	iter->priv = bi;
+	return 0;
+}
 
-		rb_erase(&n->rb_node, &self->entries);
-		if (collapse__insert_entry(&tmp, n))
-			hists__inc_nr_entries(self, n);
-	}
+static int
+iter_add_single_branch_entry(struct hist_entry_iter *iter __maybe_unused,
+			     struct addr_location *al __maybe_unused)
+{
+	/* to avoid calling callback function */
+	iter->he = NULL;
 
-	self->entries = tmp;
+	return 0;
 }
 
-/*
- * reverse the map, sort on period.
- */
-
-static void __hists__insert_output_entry(struct rb_root *entries,
-					 struct hist_entry *he,
-					 u64 min_callchain_hits)
+static int
+iter_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *al)
 {
-	struct rb_node **p = &entries->rb_node;
-	struct rb_node *parent = NULL;
-	struct hist_entry *iter;
-
-	if (symbol_conf.use_callchain)
-		callchain_param.sort(&he->sorted_chain, he->callchain,
-				      min_callchain_hits, &callchain_param);
+	struct branch_info *bi = iter->priv;
+	int i = iter->curr;
 
-	while (*p != NULL) {
-		parent = *p;
-		iter = rb_entry(parent, struct hist_entry, rb_node);
+	if (bi == NULL)
+		return 0;
 
-		if (he->period > iter->period)
-			p = &(*p)->rb_left;
-		else
-			p = &(*p)->rb_right;
-	}
+	if (iter->curr >= iter->total)
+		return 0;
 
-	rb_link_node(&he->rb_node, parent, p);
-	rb_insert_color(&he->rb_node, entries);
+	al->map = bi[i].to.map;
+	al->sym = bi[i].to.sym;
+	al->addr = bi[i].to.addr;
+	return 1;
 }
 
-void hists__output_resort(struct hists *self)
+static int
+iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *al)
 {
-	struct rb_root tmp;
-	struct rb_node *next;
-	struct hist_entry *n;
-	u64 min_callchain_hits;
+	struct branch_info *bi;
+	struct perf_evsel *evsel = iter->evsel;
+	struct hist_entry *he = NULL;
+	int i = iter->curr;
+	int err = 0;
 
-	min_callchain_hits = self->stats.total_period * (callchain_param.min_percent / 100);
+	bi = iter->priv;
 
-	tmp = RB_ROOT;
-	next = rb_first(&self->entries);
+	if (iter->hide_unresolved && !(bi[i].from.sym && bi[i].to.sym))
+		goto out;
 
-	self->nr_entries = 0;
-	self->max_sym_namelen = 0;
+	/*
+	 * The report shows the percentage of total branches captured
+	 * and not events sampled. Thus we use a pseudo period of 1.
+	 */
+	he = __hists__add_entry(&evsel->hists, al, iter->parent, &bi[i], NULL,
+				1, 1, 0, true);
+	if (he == NULL)
+		return -ENOMEM;
 
-	while (next) {
-		n = rb_entry(next, struct hist_entry, rb_node);
-		next = rb_next(&n->rb_node);
+	hists__inc_nr_samples(&evsel->hists, he->filtered);
 
-		rb_erase(&n->rb_node, &self->entries);
-		__hists__insert_output_entry(&tmp, n, min_callchain_hits);
-		hists__inc_nr_entries(self, n);
-	}
+out:
+	iter->he = he;
+	iter->curr++;
+	return err;
+}
 
-	self->entries = tmp;
+static int
+iter_finish_branch_entry(struct hist_entry_iter *iter,
+			 struct addr_location *al __maybe_unused)
+{
+	zfree(&iter->priv);
+	iter->he = NULL;
+
+	return iter->curr >= iter->total ? 0 : -1;
 }
 
-static size_t callchain__fprintf_left_margin(FILE *fp, int left_margin)
+static int
+iter_prepare_normal_entry(struct hist_entry_iter *iter __maybe_unused,
+			  struct addr_location *al __maybe_unused)
 {
-	int i;
-	int ret = fprintf(fp, "            ");
+	return 0;
+}
 
-	for (i = 0; i < left_margin; i++)
-		ret += fprintf(fp, " ");
+static int
+iter_add_single_normal_entry(struct hist_entry_iter *iter, struct addr_location *al)
+{
+	struct perf_evsel *evsel = iter->evsel;
+	struct perf_sample *sample = iter->sample;
+	struct hist_entry *he;
 
-	return ret;
+	he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL,
+				sample->period, sample->weight,
+				sample->transaction, true);
+	if (he == NULL)
+		return -ENOMEM;
+
+	iter->he = he;
+	return 0;
 }
 
-static size_t ipchain__fprintf_graph_line(FILE *fp, int depth, int depth_mask,
-					  int left_margin)
+static int
+iter_finish_normal_entry(struct hist_entry_iter *iter,
+			 struct addr_location *al __maybe_unused)
 {
-	int i;
-	size_t ret = callchain__fprintf_left_margin(fp, left_margin);
+	struct hist_entry *he = iter->he;
+	struct perf_evsel *evsel = iter->evsel;
+	struct perf_sample *sample = iter->sample;
 
-	for (i = 0; i < depth; i++)
-		if (depth_mask & (1 << i))
-			ret += fprintf(fp, "|          ");
-		else
-			ret += fprintf(fp, "           ");
+	if (he == NULL)
+		return 0;
 
-	ret += fprintf(fp, "\n");
+	iter->he = NULL;
 
-	return ret;
+	hists__inc_nr_samples(&evsel->hists, he->filtered);
+
+	return hist_entry__append_callchain(he, sample);
 }
 
-static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_list *chain,
-				     int depth, int depth_mask, int period,
-				     u64 total_samples, int hits,
-				     int left_margin)
+static int
+iter_prepare_cumulative_entry(struct hist_entry_iter *iter __maybe_unused,
+			      struct addr_location *al __maybe_unused)
 {
-	int i;
-	size_t ret = 0;
+	struct hist_entry **he_cache;
 
-	ret += callchain__fprintf_left_margin(fp, left_margin);
-	for (i = 0; i < depth; i++) {
-		if (depth_mask & (1 << i))
-			ret += fprintf(fp, "|");
-		else
-			ret += fprintf(fp, " ");
-		if (!period && i == depth - 1) {
-			double percent;
-
-			percent = hits * 100.0 / total_samples;
-			ret += percent_color_fprintf(fp, "--%2.2f%%-- ", percent);
-		} else
-			ret += fprintf(fp, "%s", "          ");
-	}
-	if (chain->ms.sym)
-		ret += fprintf(fp, "%s\n", chain->ms.sym->name);
-	else
-		ret += fprintf(fp, "%p\n", (void *)(long)chain->ip);
+	callchain_cursor_commit(&callchain_cursor);
 
-	return ret;
-}
+	/*
+	 * This is for detecting cycles or recursions so that they're
+	 * cumulated only one time to prevent entries more than 100%
+	 * overhead.
+	 */
+	he_cache = malloc(sizeof(*he_cache) * (PERF_MAX_STACK_DEPTH + 1));
+	if (he_cache == NULL)
+		return -ENOMEM;
 
-static struct symbol *rem_sq_bracket;
-static struct callchain_list rem_hits;
+	iter->priv = he_cache;
+	iter->curr = 0;
 
-static void init_rem_hits(void)
+	return 0;
+}
+
+static int
+iter_add_single_cumulative_entry(struct hist_entry_iter *iter,
+				 struct addr_location *al)
 {
-	rem_sq_bracket = malloc(sizeof(*rem_sq_bracket) + 6);
-	if (!rem_sq_bracket) {
-		fprintf(stderr, "Not enough memory to display remaining hits\n");
-		return;
-	}
+	struct perf_evsel *evsel = iter->evsel;
+	struct perf_sample *sample = iter->sample;
+	struct hist_entry **he_cache = iter->priv;
+	struct hist_entry *he;
+	int err = 0;
+
+	he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL,
+				sample->period, sample->weight,
+				sample->transaction, true);
+	if (he == NULL)
+		return -ENOMEM;
+
+	iter->he = he;
+	he_cache[iter->curr++] = he;
 
-	strcpy(rem_sq_bracket->name, "[...]");
-	rem_hits.ms.sym = rem_sq_bracket;
+	callchain_append(he->callchain, &callchain_cursor, sample->period);
+
+	/*
+	 * We need to re-initialize the cursor since callchain_append()
+	 * advanced the cursor to the end.
+	 */
+	callchain_cursor_commit(&callchain_cursor);
+
+	hists__inc_nr_samples(&evsel->hists, he->filtered);
+
+	return err;
 }
 
-static size_t __callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
-					 u64 total_samples, int depth,
-					 int depth_mask, int left_margin)
+static int
+iter_next_cumulative_entry(struct hist_entry_iter *iter,
+			   struct addr_location *al)
 {
-	struct rb_node *node, *next;
-	struct callchain_node *child;
-	struct callchain_list *chain;
-	int new_depth_mask = depth_mask;
-	u64 new_total;
-	u64 remaining;
-	size_t ret = 0;
-	int i;
-	uint entries_printed = 0;
+	struct callchain_cursor_node *node;
 
-	if (callchain_param.mode == CHAIN_GRAPH_REL)
-		new_total = self->children_hit;
-	else
-		new_total = total_samples;
+	node = callchain_cursor_current(&callchain_cursor);
+	if (node == NULL)
+		return 0;
 
-	remaining = new_total;
+	return fill_callchain_info(al, node, iter->hide_unresolved);
+}
 
-	node = rb_first(&self->rb_root);
-	while (node) {
-		u64 cumul;
+static int
+iter_add_next_cumulative_entry(struct hist_entry_iter *iter,
+			       struct addr_location *al)
+{
+	struct perf_evsel *evsel = iter->evsel;
+	struct perf_sample *sample = iter->sample;
+	struct hist_entry **he_cache = iter->priv;
+	struct hist_entry *he;
+	struct hist_entry he_tmp = {
+		.cpu = al->cpu,
+		.thread = al->thread,
+		.comm = thread__comm(al->thread),
+		.ip = al->addr,
+		.ms = {
+			.map = al->map,
+			.sym = al->sym,
+		},
+		.parent = iter->parent,
+	};
+	int i;
+	struct callchain_cursor cursor;
 
-		child = rb_entry(node, struct callchain_node, rb_node);
-		cumul = cumul_hits(child);
-		remaining -= cumul;
+	callchain_cursor_snapshot(&cursor, &callchain_cursor);
 
-		/*
-		 * The depth mask manages the output of pipes that show
-		 * the depth. We don't want to keep the pipes of the current
-		 * level for the last child of this depth.
-		 * Except if we have remaining filtered hits. They will
-		 * supersede the last child
-		 */
-		next = rb_next(node);
-		if (!next && (callchain_param.mode != CHAIN_GRAPH_REL || !remaining))
-			new_depth_mask &= ~(1 << (depth - 1));
+	callchain_cursor_advance(&callchain_cursor);
 
-		/*
-		 * But we keep the older depth mask for the line separator
-		 * to keep the level link until we reach the last child
-		 */
-		ret += ipchain__fprintf_graph_line(fp, depth, depth_mask,
-						   left_margin);
-		i = 0;
-		list_for_each_entry(chain, &child->val, list) {
-			ret += ipchain__fprintf_graph(fp, chain, depth,
-						      new_depth_mask, i++,
-						      new_total,
-						      cumul,
-						      left_margin);
+	/*
+	 * Check if there's duplicate entries in the callchain.
+	 * It's possible that it has cycles or recursive calls.
+	 */
+	for (i = 0; i < iter->curr; i++) {
+		if (hist_entry__cmp(he_cache[i], &he_tmp) == 0) {
+			/* to avoid calling callback function */
+			iter->he = NULL;
+			return 0;
 		}
-		ret += __callchain__fprintf_graph(fp, child, new_total,
-						  depth + 1,
-						  new_depth_mask | (1 << depth),
-						  left_margin);
-		node = next;
-		if (++entries_printed == callchain_param.print_limit)
-			break;
 	}
 
-	if (callchain_param.mode == CHAIN_GRAPH_REL &&
-		remaining && remaining != new_total) {
+	he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL,
+				sample->period, sample->weight,
+				sample->transaction, false);
+	if (he == NULL)
+		return -ENOMEM;
 
-		if (!rem_sq_bracket)
-			return ret;
+	iter->he = he;
+	he_cache[iter->curr++] = he;
 
-		new_depth_mask &= ~(1 << (depth - 1));
+	callchain_append(he->callchain, &cursor, sample->period);
+	return 0;
+}
 
-		ret += ipchain__fprintf_graph(fp, &rem_hits, depth,
-					      new_depth_mask, 0, new_total,
-					      remaining, left_margin);
-	}
+static int
+iter_finish_cumulative_entry(struct hist_entry_iter *iter,
+			     struct addr_location *al __maybe_unused)
+{
+	zfree(&iter->priv);
+	iter->he = NULL;
 
-	return ret;
+	return 0;
 }
 
-static size_t callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
-				       u64 total_samples, int left_margin)
+const struct hist_iter_ops hist_iter_mem = {
+	.prepare_entry 		= iter_prepare_mem_entry,
+	.add_single_entry 	= iter_add_single_mem_entry,
+	.next_entry 		= iter_next_nop_entry,
+	.add_next_entry 	= iter_add_next_nop_entry,
+	.finish_entry 		= iter_finish_mem_entry,
+};
+
+const struct hist_iter_ops hist_iter_branch = {
+	.prepare_entry 		= iter_prepare_branch_entry,
+	.add_single_entry 	= iter_add_single_branch_entry,
+	.next_entry 		= iter_next_branch_entry,
+	.add_next_entry 	= iter_add_next_branch_entry,
+	.finish_entry 		= iter_finish_branch_entry,
+};
+
+const struct hist_iter_ops hist_iter_normal = {
+	.prepare_entry 		= iter_prepare_normal_entry,
+	.add_single_entry 	= iter_add_single_normal_entry,
+	.next_entry 		= iter_next_nop_entry,
+	.add_next_entry 	= iter_add_next_nop_entry,
+	.finish_entry 		= iter_finish_normal_entry,
+};
+
+const struct hist_iter_ops hist_iter_cumulative = {
+	.prepare_entry 		= iter_prepare_cumulative_entry,
+	.add_single_entry 	= iter_add_single_cumulative_entry,
+	.next_entry 		= iter_next_cumulative_entry,
+	.add_next_entry 	= iter_add_next_cumulative_entry,
+	.finish_entry 		= iter_finish_cumulative_entry,
+};
+
+int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
+			 struct perf_evsel *evsel, struct perf_sample *sample,
+			 int max_stack_depth, void *arg)
 {
-	struct callchain_list *chain;
-	bool printed = false;
-	int i = 0;
-	int ret = 0;
-	u32 entries_printed = 0;
+	int err, err2;
 
-	list_for_each_entry(chain, &self->val, list) {
-		if (!i++ && sort__first_dimension == SORT_SYM)
-			continue;
+	err = sample__resolve_callchain(sample, &iter->parent, evsel, al,
+					max_stack_depth);
+	if (err)
+		return err;
 
-		if (!printed) {
-			ret += callchain__fprintf_left_margin(fp, left_margin);
-			ret += fprintf(fp, "|\n");
-			ret += callchain__fprintf_left_margin(fp, left_margin);
-			ret += fprintf(fp, "---");
+	iter->evsel = evsel;
+	iter->sample = sample;
 
-			left_margin += 3;
-			printed = true;
-		} else
-			ret += callchain__fprintf_left_margin(fp, left_margin);
+	err = iter->ops->prepare_entry(iter, al);
+	if (err)
+		goto out;
 
-		if (chain->ms.sym)
-			ret += fprintf(fp, " %s\n", chain->ms.sym->name);
-		else
-			ret += fprintf(fp, " %p\n", (void *)(long)chain->ip);
+	err = iter->ops->add_single_entry(iter, al);
+	if (err)
+		goto out;
 
-		if (++entries_printed == callchain_param.print_limit)
+	if (iter->he && iter->add_entry_cb) {
+		err = iter->add_entry_cb(iter, al, true, arg);
+		if (err)
+			goto out;
+	}
+
+	while (iter->ops->next_entry(iter, al)) {
+		err = iter->ops->add_next_entry(iter, al);
+		if (err)
 			break;
+
+		if (iter->he && iter->add_entry_cb) {
+			err = iter->add_entry_cb(iter, al, false, arg);
+			if (err)
+				goto out;
+		}
 	}
 
-	ret += __callchain__fprintf_graph(fp, self, total_samples, 1, 1, left_margin);
+out:
+	err2 = iter->ops->finish_entry(iter, al);
+	if (!err)
+		err = err2;
 
-	return ret;
+	return err;
 }
 
-static size_t callchain__fprintf_flat(FILE *fp, struct callchain_node *self,
-				      u64 total_samples)
+int64_t
+hist_entry__cmp(struct hist_entry *left, struct hist_entry *right)
 {
-	struct callchain_list *chain;
-	size_t ret = 0;
-
-	if (!self)
-		return 0;
-
-	ret += callchain__fprintf_flat(fp, self->parent, total_samples);
-
+	struct perf_hpp_fmt *fmt;
+	int64_t cmp = 0;
 
-	list_for_each_entry(chain, &self->val, list) {
-		if (chain->ip >= PERF_CONTEXT_MAX)
+	perf_hpp__for_each_sort_list(fmt) {
+		if (perf_hpp__should_skip(fmt))
 			continue;
-		if (chain->ms.sym)
-			ret += fprintf(fp, "                %s\n", chain->ms.sym->name);
-		else
-			ret += fprintf(fp, "                %p\n",
-					(void *)(long)chain->ip);
+
+		cmp = fmt->cmp(left, right);
+		if (cmp)
+			break;
 	}
 
-	return ret;
+	return cmp;
 }
 
-static size_t hist_entry_callchain__fprintf(FILE *fp, struct hist_entry *self,
-					    u64 total_samples, int left_margin)
+int64_t
+hist_entry__collapse(struct hist_entry *left, struct hist_entry *right)
 {
-	struct rb_node *rb_node;
-	struct callchain_node *chain;
-	size_t ret = 0;
-	u32 entries_printed = 0;
+	struct perf_hpp_fmt *fmt;
+	int64_t cmp = 0;
 
-	rb_node = rb_first(&self->sorted_chain);
-	while (rb_node) {
-		double percent;
+	perf_hpp__for_each_sort_list(fmt) {
+		if (perf_hpp__should_skip(fmt))
+			continue;
 
-		chain = rb_entry(rb_node, struct callchain_node, rb_node);
-		percent = chain->hit * 100.0 / total_samples;
-		switch (callchain_param.mode) {
-		case CHAIN_FLAT:
-			ret += percent_color_fprintf(fp, "           %6.2f%%\n",
-						     percent);
-			ret += callchain__fprintf_flat(fp, chain, total_samples);
-			break;
-		case CHAIN_GRAPH_ABS: /* Falldown */
-		case CHAIN_GRAPH_REL:
-			ret += callchain__fprintf_graph(fp, chain, total_samples,
-							left_margin);
-		case CHAIN_NONE:
-		default:
-			break;
-		}
-		ret += fprintf(fp, "\n");
-		if (++entries_printed == callchain_param.print_limit)
+		cmp = fmt->collapse(left, right);
+		if (cmp)
 			break;
-		rb_node = rb_next(rb_node);
 	}
 
-	return ret;
+	return cmp;
+}
+
+void hist_entry__free(struct hist_entry *he)
+{
+	zfree(&he->branch_info);
+	zfree(&he->mem_info);
+	zfree(&he->stat_acc);
+	free_srcline(he->srcline);
+	free(he);
 }
 
-int hist_entry__snprintf(struct hist_entry *self, char *s, size_t size,
-			 struct hists *pair_hists, bool show_displacement,
-			 long displacement, bool color, u64 session_total)
+/*
+ * collapse the histogram
+ */
+
+static bool hists__collapse_insert_entry(struct hists *hists __maybe_unused,
+					 struct rb_root *root,
+					 struct hist_entry *he)
 {
-	struct sort_entry *se;
-	u64 period, total, period_sys, period_us, period_guest_sys, period_guest_us;
-	const char *sep = symbol_conf.field_sep;
-	int ret;
+	struct rb_node **p = &root->rb_node;
+	struct rb_node *parent = NULL;
+	struct hist_entry *iter;
+	int64_t cmp;
 
-	if (symbol_conf.exclude_other && !self->parent)
-		return 0;
+	while (*p != NULL) {
+		parent = *p;
+		iter = rb_entry(parent, struct hist_entry, rb_node_in);
 
-	if (pair_hists) {
-		period = self->pair ? self->pair->period : 0;
-		total = pair_hists->stats.total_period;
-		period_sys = self->pair ? self->pair->period_sys : 0;
-		period_us = self->pair ? self->pair->period_us : 0;
-		period_guest_sys = self->pair ? self->pair->period_guest_sys : 0;
-		period_guest_us = self->pair ? self->pair->period_guest_us : 0;
-	} else {
-		period = self->period;
-		total = session_total;
-		period_sys = self->period_sys;
-		period_us = self->period_us;
-		period_guest_sys = self->period_guest_sys;
-		period_guest_us = self->period_guest_us;
-	}
+		cmp = hist_entry__collapse(iter, he);
 
-	if (total) {
-		if (color)
-			ret = percent_color_snprintf(s, size,
-						     sep ? "%.2f" : "   %6.2f%%",
-						     (period * 100.0) / total);
-		else
-			ret = snprintf(s, size, sep ? "%.2f" : "   %6.2f%%",
-				       (period * 100.0) / total);
-		if (symbol_conf.show_cpu_utilization) {
-			ret += percent_color_snprintf(s + ret, size - ret,
-					sep ? "%.2f" : "   %6.2f%%",
-					(period_sys * 100.0) / total);
-			ret += percent_color_snprintf(s + ret, size - ret,
-					sep ? "%.2f" : "   %6.2f%%",
-					(period_us * 100.0) / total);
-			if (perf_guest) {
-				ret += percent_color_snprintf(s + ret,
-						size - ret,
-						sep ? "%.2f" : "   %6.2f%%",
-						(period_guest_sys * 100.0) /
-								total);
-				ret += percent_color_snprintf(s + ret,
-						size - ret,
-						sep ? "%.2f" : "   %6.2f%%",
-						(period_guest_us * 100.0) /
-								total);
+		if (!cmp) {
+			he_stat__add_stat(&iter->stat, &he->stat);
+			if (symbol_conf.cumulate_callchain)
+				he_stat__add_stat(iter->stat_acc, he->stat_acc);
+
+			if (symbol_conf.use_callchain) {
+				callchain_cursor_reset(&callchain_cursor);
+				callchain_merge(&callchain_cursor,
+						iter->callchain,
+						he->callchain);
 			}
+			hist_entry__free(he);
+			return false;
 		}
-	} else
-		ret = snprintf(s, size, sep ? "%lld" : "%12lld ", period);
 
-	if (symbol_conf.show_nr_samples) {
-		if (sep)
-			ret += snprintf(s + ret, size - ret, "%c%lld", *sep, period);
+		if (cmp < 0)
+			p = &(*p)->rb_left;
 		else
-			ret += snprintf(s + ret, size - ret, "%11lld", period);
+			p = &(*p)->rb_right;
 	}
 
-	if (pair_hists) {
-		char bf[32];
-		double old_percent = 0, new_percent = 0, diff;
+	rb_link_node(&he->rb_node_in, parent, p);
+	rb_insert_color(&he->rb_node_in, root);
+	return true;
+}
 
-		if (total > 0)
-			old_percent = (period * 100.0) / total;
-		if (session_total > 0)
-			new_percent = (self->period * 100.0) / session_total;
+static struct rb_root *hists__get_rotate_entries_in(struct hists *hists)
+{
+	struct rb_root *root;
 
-		diff = new_percent - old_percent;
+	pthread_mutex_lock(&hists->lock);
 
-		if (fabs(diff) >= 0.01)
-			snprintf(bf, sizeof(bf), "%+4.2F%%", diff);
-		else
-			snprintf(bf, sizeof(bf), " ");
+	root = hists->entries_in;
+	if (++hists->entries_in > &hists->entries_in_array[1])
+		hists->entries_in = &hists->entries_in_array[0];
 
-		if (sep)
-			ret += snprintf(s + ret, size - ret, "%c%s", *sep, bf);
-		else
-			ret += snprintf(s + ret, size - ret, "%11.11s", bf);
-
-		if (show_displacement) {
-			if (displacement)
-				snprintf(bf, sizeof(bf), "%+4ld", displacement);
-			else
-				snprintf(bf, sizeof(bf), " ");
-
-			if (sep)
-				ret += snprintf(s + ret, size - ret, "%c%s", *sep, bf);
-			else
-				ret += snprintf(s + ret, size - ret, "%6.6s", bf);
+	pthread_mutex_unlock(&hists->lock);
+
+	return root;
+}
+
+static void hists__apply_filters(struct hists *hists, struct hist_entry *he)
+{
+	hists__filter_entry_by_dso(hists, he);
+	hists__filter_entry_by_thread(hists, he);
+	hists__filter_entry_by_symbol(hists, he);
+}
+
+void hists__collapse_resort(struct hists *hists, struct ui_progress *prog)
+{
+	struct rb_root *root;
+	struct rb_node *next;
+	struct hist_entry *n;
+
+	if (!sort__need_collapse)
+		return;
+
+	root = hists__get_rotate_entries_in(hists);
+	next = rb_first(root);
+
+	while (next) {
+		if (session_done())
+			break;
+		n = rb_entry(next, struct hist_entry, rb_node_in);
+		next = rb_next(&n->rb_node_in);
+
+		rb_erase(&n->rb_node_in, root);
+		if (hists__collapse_insert_entry(hists, &hists->entries_collapsed, n)) {
+			/*
+			 * If it wasn't combined with one of the entries already
+			 * collapsed, we need to apply the filters that may have
+			 * been set by, say, the hist_browser.
+			 */
+			hists__apply_filters(hists, n);
 		}
+		if (prog)
+			ui_progress__update(prog, 1);
 	}
+}
 
-	list_for_each_entry(se, &hist_entry__sort_list, list) {
-		if (se->elide)
+static int hist_entry__sort(struct hist_entry *a, struct hist_entry *b)
+{
+	struct perf_hpp_fmt *fmt;
+	int64_t cmp = 0;
+
+	perf_hpp__for_each_sort_list(fmt) {
+		if (perf_hpp__should_skip(fmt))
 			continue;
 
-		ret += snprintf(s + ret, size - ret, "%s", sep ?: "  ");
-		ret += se->se_snprintf(self, s + ret, size - ret,
-				       se->se_width ? *se->se_width : 0);
+		cmp = fmt->sort(a, b);
+		if (cmp)
+			break;
 	}
 
-	return ret;
+	return cmp;
 }
 
-int hist_entry__fprintf(struct hist_entry *self, struct hists *pair_hists,
-			bool show_displacement, long displacement, FILE *fp,
-			u64 session_total)
+static void hists__reset_filter_stats(struct hists *hists)
 {
-	char bf[512];
-	hist_entry__snprintf(self, bf, sizeof(bf), pair_hists,
-			     show_displacement, displacement,
-			     true, session_total);
-	return fprintf(fp, "%s\n", bf);
+	hists->nr_non_filtered_entries = 0;
+	hists->stats.total_non_filtered_period = 0;
 }
 
-static size_t hist_entry__fprintf_callchain(struct hist_entry *self, FILE *fp,
-					    u64 session_total)
+void hists__reset_stats(struct hists *hists)
 {
-	int left_margin = 0;
+	hists->nr_entries = 0;
+	hists->stats.total_period = 0;
 
-	if (sort__first_dimension == SORT_COMM) {
-		struct sort_entry *se = list_first_entry(&hist_entry__sort_list,
-							 typeof(*se), list);
-		left_margin = se->se_width ? *se->se_width : 0;
-		left_margin -= thread__comm_len(self->thread);
-	}
+	hists__reset_filter_stats(hists);
+}
 
-	return hist_entry_callchain__fprintf(fp, self, session_total,
-					     left_margin);
+static void hists__inc_filter_stats(struct hists *hists, struct hist_entry *h)
+{
+	hists->nr_non_filtered_entries++;
+	hists->stats.total_non_filtered_period += h->stat.period;
 }
 
-size_t hists__fprintf(struct hists *self, struct hists *pair,
-		      bool show_displacement, FILE *fp)
+void hists__inc_stats(struct hists *hists, struct hist_entry *h)
 {
-	struct sort_entry *se;
-	struct rb_node *nd;
-	size_t ret = 0;
-	unsigned long position = 1;
-	long displacement = 0;
-	unsigned int width;
-	const char *sep = symbol_conf.field_sep;
-	const char *col_width = symbol_conf.col_width_list_str;
+	if (!h->filtered)
+		hists__inc_filter_stats(hists, h);
 
-	init_rem_hits();
+	hists->nr_entries++;
+	hists->stats.total_period += h->stat.period;
+}
 
-	fprintf(fp, "# %s", pair ? "Baseline" : "Overhead");
+static void __hists__insert_output_entry(struct rb_root *entries,
+					 struct hist_entry *he,
+					 u64 min_callchain_hits)
+{
+	struct rb_node **p = &entries->rb_node;
+	struct rb_node *parent = NULL;
+	struct hist_entry *iter;
 
-	if (symbol_conf.show_nr_samples) {
-		if (sep)
-			fprintf(fp, "%cSamples", *sep);
-		else
-			fputs("  Samples  ", fp);
-	}
+	if (symbol_conf.use_callchain)
+		callchain_param.sort(&he->sorted_chain, he->callchain,
+				      min_callchain_hits, &callchain_param);
 
-	if (symbol_conf.show_cpu_utilization) {
-		if (sep) {
-			ret += fprintf(fp, "%csys", *sep);
-			ret += fprintf(fp, "%cus", *sep);
-			if (perf_guest) {
-				ret += fprintf(fp, "%cguest sys", *sep);
-				ret += fprintf(fp, "%cguest us", *sep);
-			}
-		} else {
-			ret += fprintf(fp, "  sys  ");
-			ret += fprintf(fp, "  us  ");
-			if (perf_guest) {
-				ret += fprintf(fp, "  guest sys  ");
-				ret += fprintf(fp, "  guest us  ");
-			}
-		}
-	}
+	while (*p != NULL) {
+		parent = *p;
+		iter = rb_entry(parent, struct hist_entry, rb_node);
 
-	if (pair) {
-		if (sep)
-			ret += fprintf(fp, "%cDelta", *sep);
+		if (hist_entry__sort(he, iter) > 0)
+			p = &(*p)->rb_left;
 		else
-			ret += fprintf(fp, "  Delta    ");
-
-		if (show_displacement) {
-			if (sep)
-				ret += fprintf(fp, "%cDisplacement", *sep);
-			else
-				ret += fprintf(fp, " Displ");
-		}
+			p = &(*p)->rb_right;
 	}
 
-	list_for_each_entry(se, &hist_entry__sort_list, list) {
-		if (se->elide)
-			continue;
-		if (sep) {
-			fprintf(fp, "%c%s", *sep, se->se_header);
-			continue;
-		}
-		width = strlen(se->se_header);
-		if (se->se_width) {
-			if (symbol_conf.col_width_list_str) {
-				if (col_width) {
-					*se->se_width = atoi(col_width);
-					col_width = strchr(col_width, ',');
-					if (col_width)
-						++col_width;
-				}
-			}
-			width = *se->se_width = max(*se->se_width, width);
-		}
-		fprintf(fp, "  %*s", width, se->se_header);
-	}
-	fprintf(fp, "\n");
-
-	if (sep)
-		goto print_entries;
-
-	fprintf(fp, "# ........");
-	if (symbol_conf.show_nr_samples)
-		fprintf(fp, " ..........");
-	if (pair) {
-		fprintf(fp, " ..........");
-		if (show_displacement)
-			fprintf(fp, " .....");
-	}
-	list_for_each_entry(se, &hist_entry__sort_list, list) {
-		unsigned int i;
+	rb_link_node(&he->rb_node, parent, p);
+	rb_insert_color(&he->rb_node, entries);
+}
 
-		if (se->elide)
-			continue;
+void hists__output_resort(struct hists *hists)
+{
+	struct rb_root *root;
+	struct rb_node *next;
+	struct hist_entry *n;
+	u64 min_callchain_hits;
 
-		fprintf(fp, "  ");
-		if (se->se_width)
-			width = *se->se_width;
-		else
-			width = strlen(se->se_header);
-		for (i = 0; i < width; i++)
-			fprintf(fp, ".");
-	}
+	min_callchain_hits = hists->stats.total_period * (callchain_param.min_percent / 100);
 
-	fprintf(fp, "\n#\n");
+	if (sort__need_collapse)
+		root = &hists->entries_collapsed;
+	else
+		root = hists->entries_in;
 
-print_entries:
-	for (nd = rb_first(&self->entries); nd; nd = rb_next(nd)) {
-		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
+	next = rb_first(root);
+	hists->entries = RB_ROOT;
 
-		if (show_displacement) {
-			if (h->pair != NULL)
-				displacement = ((long)h->pair->position -
-					        (long)position);
-			else
-				displacement = 0;
-			++position;
-		}
-		ret += hist_entry__fprintf(h, pair, show_displacement,
-					   displacement, fp, self->stats.total_period);
+	hists__reset_stats(hists);
+	hists__reset_col_len(hists);
 
-		if (symbol_conf.use_callchain)
-			ret += hist_entry__fprintf_callchain(h, fp, self->stats.total_period);
+	while (next) {
+		n = rb_entry(next, struct hist_entry, rb_node_in);
+		next = rb_next(&n->rb_node_in);
 
-		if (h->ms.map == NULL && verbose > 1) {
-			__map_groups__fprintf_maps(&h->thread->mg,
-						   MAP__FUNCTION, verbose, fp);
-			fprintf(fp, "%.10s end\n", graph_dotted_line);
-		}
+		__hists__insert_output_entry(&hists->entries, n, min_callchain_hits);
+		hists__inc_stats(hists, n);
+
+		if (!n->filtered)
+			hists__calc_col_len(hists, n);
 	}
+}
 
-	free(rem_sq_bracket);
+static void hists__remove_entry_filter(struct hists *hists, struct hist_entry *h,
+				       enum hist_filter filter)
+{
+	h->filtered &= ~(1 << filter);
+	if (h->filtered)
+		return;
+
+	/* force fold unfiltered entry for simplicity */
+	h->ms.unfolded = false;
+	h->row_offset = 0;
 
-	return ret;
+	hists->stats.nr_non_filtered_samples += h->stat.nr_events;
+
+	hists__inc_filter_stats(hists, h);
+	hists__calc_col_len(hists, h);
 }
 
-enum hist_filter {
-	HIST_FILTER__DSO,
-	HIST_FILTER__THREAD,
-};
 
-void hists__filter_by_dso(struct hists *self, const struct dso *dso)
+static bool hists__filter_entry_by_dso(struct hists *hists,
+				       struct hist_entry *he)
+{
+	if (hists->dso_filter != NULL &&
+	    (he->ms.map == NULL || he->ms.map->dso != hists->dso_filter)) {
+		he->filtered |= (1 << HIST_FILTER__DSO);
+		return true;
+	}
+
+	return false;
+}
+
+void hists__filter_by_dso(struct hists *hists)
 {
 	struct rb_node *nd;
 
-	self->nr_entries = self->stats.total_period = 0;
-	self->stats.nr_events[PERF_RECORD_SAMPLE] = 0;
-	self->max_sym_namelen = 0;
+	hists->stats.nr_non_filtered_samples = 0;
+
+	hists__reset_filter_stats(hists);
+	hists__reset_col_len(hists);
 
-	for (nd = rb_first(&self->entries); nd; nd = rb_next(nd)) {
+	for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
 
 		if (symbol_conf.exclude_other && !h->parent)
 			continue;
 
-		if (dso != NULL && (h->ms.map == NULL || h->ms.map->dso != dso)) {
-			h->filtered |= (1 << HIST_FILTER__DSO);
+		if (hists__filter_entry_by_dso(hists, h))
 			continue;
-		}
 
-		h->filtered &= ~(1 << HIST_FILTER__DSO);
-		if (!h->filtered) {
-			++self->nr_entries;
-			self->stats.total_period += h->period;
-			self->stats.nr_events[PERF_RECORD_SAMPLE] += h->nr_events;
-			if (h->ms.sym &&
-			    self->max_sym_namelen < h->ms.sym->namelen)
-				self->max_sym_namelen = h->ms.sym->namelen;
-		}
+		hists__remove_entry_filter(hists, h, HIST_FILTER__DSO);
 	}
 }
 
-void hists__filter_by_thread(struct hists *self, const struct thread *thread)
+static bool hists__filter_entry_by_thread(struct hists *hists,
+					  struct hist_entry *he)
+{
+	if (hists->thread_filter != NULL &&
+	    he->thread != hists->thread_filter) {
+		he->filtered |= (1 << HIST_FILTER__THREAD);
+		return true;
+	}
+
+	return false;
+}
+
+void hists__filter_by_thread(struct hists *hists)
 {
 	struct rb_node *nd;
 
-	self->nr_entries = self->stats.total_period = 0;
-	self->stats.nr_events[PERF_RECORD_SAMPLE] = 0;
-	self->max_sym_namelen = 0;
+	hists->stats.nr_non_filtered_samples = 0;
 
-	for (nd = rb_first(&self->entries); nd; nd = rb_next(nd)) {
+	hists__reset_filter_stats(hists);
+	hists__reset_col_len(hists);
+
+	for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
 
-		if (thread != NULL && h->thread != thread) {
-			h->filtered |= (1 << HIST_FILTER__THREAD);
+		if (hists__filter_entry_by_thread(hists, h))
 			continue;
-		}
-		h->filtered &= ~(1 << HIST_FILTER__THREAD);
-		if (!h->filtered) {
-			++self->nr_entries;
-			self->stats.total_period += h->period;
-			self->stats.nr_events[PERF_RECORD_SAMPLE] += h->nr_events;
-			if (h->ms.sym &&
-			    self->max_sym_namelen < h->ms.sym->namelen)
-				self->max_sym_namelen = h->ms.sym->namelen;
-		}
+
+		hists__remove_entry_filter(hists, h, HIST_FILTER__THREAD);
 	}
 }
 
-static int symbol__alloc_hist(struct symbol *self)
+static bool hists__filter_entry_by_symbol(struct hists *hists,
+					  struct hist_entry *he)
 {
-	struct sym_priv *priv = symbol__priv(self);
-	const int size = (sizeof(*priv->hist) +
-			  (self->end - self->start) * sizeof(u64));
+	if (hists->symbol_filter_str != NULL &&
+	    (!he->ms.sym || strstr(he->ms.sym->name,
+				   hists->symbol_filter_str) == NULL)) {
+		he->filtered |= (1 << HIST_FILTER__SYMBOL);
+		return true;
+	}
 
-	priv->hist = zalloc(size);
-	return priv->hist == NULL ? -1 : 0;
+	return false;
 }
 
-int hist_entry__inc_addr_samples(struct hist_entry *self, u64 ip)
+void hists__filter_by_symbol(struct hists *hists)
 {
-	unsigned int sym_size, offset;
-	struct symbol *sym = self->ms.sym;
-	struct sym_priv *priv;
-	struct sym_hist *h;
-
-	if (!sym || !self->ms.map)
-		return 0;
-
-	priv = symbol__priv(sym);
-	if (priv->hist == NULL && symbol__alloc_hist(sym) < 0)
-		return -ENOMEM;
-
-	sym_size = sym->end - sym->start;
-	offset = ip - sym->start;
-
-	pr_debug3("%s: ip=%#Lx\n", __func__, self->ms.map->unmap_ip(self->ms.map, ip));
+	struct rb_node *nd;
 
-	if (offset >= sym_size)
-		return 0;
+	hists->stats.nr_non_filtered_samples = 0;
 
-	h = priv->hist;
-	h->sum++;
-	h->ip[offset]++;
+	hists__reset_filter_stats(hists);
+	hists__reset_col_len(hists);
 
-	pr_debug3("%#Lx %s: period++ [ip: %#Lx, %#Lx] => %Ld\n", self->ms.sym->start,
-		  self->ms.sym->name, ip, ip - self->ms.sym->start, h->ip[offset]);
-	return 0;
-}
+	for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
+		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
 
-static struct objdump_line *objdump_line__new(s64 offset, char *line)
-{
-	struct objdump_line *self = malloc(sizeof(*self));
+		if (hists__filter_entry_by_symbol(hists, h))
+			continue;
 
-	if (self != NULL) {
-		self->offset = offset;
-		self->line = line;
+		hists__remove_entry_filter(hists, h, HIST_FILTER__SYMBOL);
 	}
-
-	return self;
 }
 
-void objdump_line__free(struct objdump_line *self)
+void events_stats__inc(struct events_stats *stats, u32 type)
 {
-	free(self->line);
-	free(self);
+	++stats->nr_events[0];
+	++stats->nr_events[type];
 }
 
-static void objdump__add_line(struct list_head *head, struct objdump_line *line)
+void hists__inc_nr_events(struct hists *hists, u32 type)
 {
-	list_add_tail(&line->node, head);
+	events_stats__inc(&hists->stats, type);
 }
 
-struct objdump_line *objdump__get_next_ip_line(struct list_head *head,
-					       struct objdump_line *pos)
+void hists__inc_nr_samples(struct hists *hists, bool filtered)
 {
-	list_for_each_entry_continue(pos, head, node)
-		if (pos->offset >= 0)
-			return pos;
-
-	return NULL;
+	events_stats__inc(&hists->stats, PERF_RECORD_SAMPLE);
+	if (!filtered)
+		hists->stats.nr_non_filtered_samples++;
 }
 
-static int hist_entry__parse_objdump_line(struct hist_entry *self, FILE *file,
-					  struct list_head *head)
+static struct hist_entry *hists__add_dummy_entry(struct hists *hists,
+						 struct hist_entry *pair)
 {
-	struct symbol *sym = self->ms.sym;
-	struct objdump_line *objdump_line;
-	char *line = NULL, *tmp, *tmp2, *c;
-	size_t line_len;
-	s64 line_ip, offset = -1;
+	struct rb_root *root;
+	struct rb_node **p;
+	struct rb_node *parent = NULL;
+	struct hist_entry *he;
+	int64_t cmp;
 
-	if (getline(&line, &line_len, file) < 0)
-		return -1;
+	if (sort__need_collapse)
+		root = &hists->entries_collapsed;
+	else
+		root = hists->entries_in;
 
-	if (!line)
-		return -1;
+	p = &root->rb_node;
 
-	while (line_len != 0 && isspace(line[line_len - 1]))
-		line[--line_len] = '\0';
+	while (*p != NULL) {
+		parent = *p;
+		he = rb_entry(parent, struct hist_entry, rb_node_in);
 
-	c = strchr(line, '\n');
-	if (c)
-		*c = 0;
+		cmp = hist_entry__collapse(he, pair);
 
-	line_ip = -1;
+		if (!cmp)
+			goto out;
 
-	/*
-	 * Strip leading spaces:
-	 */
-	tmp = line;
-	while (*tmp) {
-		if (*tmp != ' ')
-			break;
-		tmp++;
+		if (cmp < 0)
+			p = &(*p)->rb_left;
+		else
+			p = &(*p)->rb_right;
 	}
 
-	if (*tmp) {
-		/*
-		 * Parse hexa addresses followed by ':'
-		 */
-		line_ip = strtoull(tmp, &tmp2, 16);
-		if (*tmp2 != ':' || tmp == tmp2)
-			line_ip = -1;
+	he = hist_entry__new(pair, true);
+	if (he) {
+		memset(&he->stat, 0, sizeof(he->stat));
+		he->hists = hists;
+		rb_link_node(&he->rb_node_in, parent, p);
+		rb_insert_color(&he->rb_node_in, root);
+		hists__inc_stats(hists, he);
+		he->dummy = true;
 	}
+out:
+	return he;
+}
 
-	if (line_ip != -1) {
-		u64 start = map__rip_2objdump(self->ms.map, sym->start);
-		offset = line_ip - start;
-	}
+static struct hist_entry *hists__find_entry(struct hists *hists,
+					    struct hist_entry *he)
+{
+	struct rb_node *n;
 
-	objdump_line = objdump_line__new(offset, line);
-	if (objdump_line == NULL) {
-		free(line);
-		return -1;
+	if (sort__need_collapse)
+		n = hists->entries_collapsed.rb_node;
+	else
+		n = hists->entries_in->rb_node;
+
+	while (n) {
+		struct hist_entry *iter = rb_entry(n, struct hist_entry, rb_node_in);
+		int64_t cmp = hist_entry__collapse(iter, he);
+
+		if (cmp < 0)
+			n = n->rb_left;
+		else if (cmp > 0)
+			n = n->rb_right;
+		else
+			return iter;
 	}
-	objdump__add_line(head, objdump_line);
 
-	return 0;
+	return NULL;
 }
 
-int hist_entry__annotate(struct hist_entry *self, struct list_head *head)
+/*
+ * Look for pairs to link to the leader buckets (hist_entries):
+ */
+void hists__match(struct hists *leader, struct hists *other)
 {
-	struct symbol *sym = self->ms.sym;
-	struct map *map = self->ms.map;
-	struct dso *dso = map->dso;
-	char *filename = dso__build_id_filename(dso, NULL, 0);
-	bool free_filename = true;
-	char command[PATH_MAX * 2];
-	FILE *file;
-	int err = 0;
-	u64 len;
-
-	if (filename == NULL) {
-		if (dso->has_build_id) {
-			pr_err("Can't annotate %s: not enough memory\n",
-			       sym->name);
-			return -ENOMEM;
-		}
-		goto fallback;
-	} else if (readlink(filename, command, sizeof(command)) < 0 ||
-		   strstr(command, "[kernel.kallsyms]") ||
-		   access(filename, R_OK)) {
-		free(filename);
-fallback:
-		/*
-		 * If we don't have build-ids or the build-id file isn't in the
-		 * cache, or is just a kallsyms file, well, lets hope that this
-		 * DSO is the same as when 'perf record' ran.
-		 */
-		filename = dso->long_name;
-		free_filename = false;
-	}
-
-	if (dso->origin == DSO__ORIG_KERNEL) {
-		if (dso->annotate_warned)
-			goto out_free_filename;
-		err = -ENOENT;
-		dso->annotate_warned = 1;
-		pr_err("Can't annotate %s: No vmlinux file was found in the "
-		       "path\n", sym->name);
-		goto out_free_filename;
-	}
+	struct rb_root *root;
+	struct rb_node *nd;
+	struct hist_entry *pos, *pair;
 
-	pr_debug("%s: filename=%s, sym=%s, start=%#Lx, end=%#Lx\n", __func__,
-		 filename, sym->name, map->unmap_ip(map, sym->start),
-		 map->unmap_ip(map, sym->end));
+	if (sort__need_collapse)
+		root = &leader->entries_collapsed;
+	else
+		root = leader->entries_in;
 
-	len = sym->end - sym->start;
+	for (nd = rb_first(root); nd; nd = rb_next(nd)) {
+		pos  = rb_entry(nd, struct hist_entry, rb_node_in);
+		pair = hists__find_entry(other, pos);
 
-	pr_debug("annotating [%p] %30s : [%p] %30s\n",
-		 dso, dso->long_name, sym, sym->name);
+		if (pair)
+			hist_entry__add_pair(pair, pos);
+	}
+}
 
-	snprintf(command, sizeof(command),
-		 "objdump --start-address=0x%016Lx --stop-address=0x%016Lx -dS %s|grep -v %s|expand",
-		 map__rip_2objdump(map, sym->start),
-		 map__rip_2objdump(map, sym->end),
-		 filename, filename);
+/*
+ * Look for entries in the other hists that are not present in the leader, if
+ * we find them, just add a dummy entry on the leader hists, with period=0,
+ * nr_events=0, to serve as the list header.
+ */
+int hists__link(struct hists *leader, struct hists *other)
+{
+	struct rb_root *root;
+	struct rb_node *nd;
+	struct hist_entry *pos, *pair;
 
-	pr_debug("Executing: %s\n", command);
+	if (sort__need_collapse)
+		root = &other->entries_collapsed;
+	else
+		root = other->entries_in;
 
-	file = popen(command, "r");
-	if (!file)
-		goto out_free_filename;
+	for (nd = rb_first(root); nd; nd = rb_next(nd)) {
+		pos = rb_entry(nd, struct hist_entry, rb_node_in);
 
-	while (!feof(file))
-		if (hist_entry__parse_objdump_line(self, file, head) < 0)
-			break;
+		if (!hist_entry__has_pairs(pos)) {
+			pair = hists__add_dummy_entry(leader, pos);
+			if (pair == NULL)
+				return -1;
+			hist_entry__add_pair(pos, pair);
+		}
+	}
 
-	pclose(file);
-out_free_filename:
-	if (free_filename)
-		free(filename);
-	return err;
+	return 0;
 }
 
-void hists__inc_nr_events(struct hists *self, u32 type)
+u64 hists__total_period(struct hists *hists)
 {
-	++self->stats.nr_events[0];
-	++self->stats.nr_events[type];
+	return symbol_conf.filter_relative ? hists->stats.total_non_filtered_period :
+		hists->stats.total_period;
 }
 
-size_t hists__fprintf_nr_events(struct hists *self, FILE *fp)
+int parse_filter_percentage(const struct option *opt __maybe_unused,
+			    const char *arg, int unset __maybe_unused)
 {
-	int i;
-	size_t ret = 0;
+	if (!strcmp(arg, "relative"))
+		symbol_conf.filter_relative = true;
+	else if (!strcmp(arg, "absolute"))
+		symbol_conf.filter_relative = false;
+	else
+		return -1;
 
-	for (i = 0; i < PERF_RECORD_HEADER_MAX; ++i) {
-		if (!event__name[i])
-			continue;
-		ret += fprintf(fp, "%10s events: %10d\n",
-			       event__name[i], self->stats.nr_events[i]);
-	}
+	return 0;
+}
+
+int perf_hist_config(const char *var, const char *value)
+{
+	if (!strcmp(var, "hist.percentage"))
+		return parse_filter_percentage(NULL, value, 0);
 
-	return ret;
+	return 0;
 }
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 83fa33a7b38..742f49a8572 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -2,39 +2,25 @@
 #define __PERF_HIST_H
 
 #include <linux/types.h>
+#include <pthread.h>
 #include "callchain.h"
+#include "header.h"
+#include "color.h"
+#include "ui/progress.h"
 
 extern struct callchain_param callchain_param;
 
 struct hist_entry;
 struct addr_location;
 struct symbol;
-struct rb_root;
 
-struct objdump_line {
-	struct list_head node;
-	s64		 offset;
-	char		 *line;
-};
-
-void objdump_line__free(struct objdump_line *self);
-struct objdump_line *objdump__get_next_ip_line(struct list_head *head,
-					       struct objdump_line *pos);
-
-struct sym_hist {
-	u64		sum;
-	u64		ip[0];
-};
-
-struct sym_ext {
-	struct rb_node	node;
-	double		percent;
-	char		*path;
-};
-
-struct sym_priv {
-	struct sym_hist	*hist;
-	struct sym_ext	*ext;
+enum hist_filter {
+	HIST_FILTER__DSO,
+	HIST_FILTER__THREAD,
+	HIST_FILTER__PARENT,
+	HIST_FILTER__SYMBOL,
+	HIST_FILTER__GUEST,
+	HIST_FILTER__HOST,
 };
 
 /*
@@ -51,79 +37,311 @@ struct sym_priv {
  */
 struct events_stats {
 	u64 total_period;
+	u64 total_non_filtered_period;
 	u64 total_lost;
+	u64 total_invalid_chains;
 	u32 nr_events[PERF_RECORD_HEADER_MAX];
+	u32 nr_non_filtered_samples;
+	u32 nr_lost_warned;
 	u32 nr_unknown_events;
+	u32 nr_invalid_chains;
+	u32 nr_unknown_id;
+	u32 nr_unprocessable_samples;
+};
+
+enum hist_column {
+	HISTC_SYMBOL,
+	HISTC_DSO,
+	HISTC_THREAD,
+	HISTC_COMM,
+	HISTC_PARENT,
+	HISTC_CPU,
+	HISTC_SRCLINE,
+	HISTC_MISPREDICT,
+	HISTC_IN_TX,
+	HISTC_ABORT,
+	HISTC_SYMBOL_FROM,
+	HISTC_SYMBOL_TO,
+	HISTC_DSO_FROM,
+	HISTC_DSO_TO,
+	HISTC_LOCAL_WEIGHT,
+	HISTC_GLOBAL_WEIGHT,
+	HISTC_MEM_DADDR_SYMBOL,
+	HISTC_MEM_DADDR_DSO,
+	HISTC_MEM_LOCKED,
+	HISTC_MEM_TLB,
+	HISTC_MEM_LVL,
+	HISTC_MEM_SNOOP,
+	HISTC_MEM_DCACHELINE,
+	HISTC_TRANSACTION,
+	HISTC_NR_COLS, /* Last entry */
 };
 
+struct thread;
+struct dso;
+
 struct hists {
-	struct rb_node		rb_node;
+	struct rb_root		entries_in_array[2];
+	struct rb_root		*entries_in;
 	struct rb_root		entries;
+	struct rb_root		entries_collapsed;
 	u64			nr_entries;
+	u64			nr_non_filtered_entries;
+	const struct thread	*thread_filter;
+	const struct dso	*dso_filter;
+	const char		*uid_filter_str;
+	const char		*symbol_filter_str;
+	pthread_mutex_t		lock;
 	struct events_stats	stats;
-	u64			config;
 	u64			event_stream;
-	u32			type;
-	u32			max_sym_namelen;
+	u16			col_len[HISTC_NR_COLS];
+};
+
+struct hist_entry_iter;
+
+struct hist_iter_ops {
+	int (*prepare_entry)(struct hist_entry_iter *, struct addr_location *);
+	int (*add_single_entry)(struct hist_entry_iter *, struct addr_location *);
+	int (*next_entry)(struct hist_entry_iter *, struct addr_location *);
+	int (*add_next_entry)(struct hist_entry_iter *, struct addr_location *);
+	int (*finish_entry)(struct hist_entry_iter *, struct addr_location *);
+};
+
+struct hist_entry_iter {
+	int total;
+	int curr;
+
+	bool hide_unresolved;
+
+	struct perf_evsel *evsel;
+	struct perf_sample *sample;
+	struct hist_entry *he;
+	struct symbol *parent;
+	void *priv;
+
+	const struct hist_iter_ops *ops;
+	/* user-defined callback function (optional) */
+	int (*add_entry_cb)(struct hist_entry_iter *iter,
+			    struct addr_location *al, bool single, void *arg);
 };
 
-struct hist_entry *__hists__add_entry(struct hists *self,
+extern const struct hist_iter_ops hist_iter_normal;
+extern const struct hist_iter_ops hist_iter_branch;
+extern const struct hist_iter_ops hist_iter_mem;
+extern const struct hist_iter_ops hist_iter_cumulative;
+
+struct hist_entry *__hists__add_entry(struct hists *hists,
 				      struct addr_location *al,
-				      struct symbol *parent, u64 period);
-extern int64_t hist_entry__cmp(struct hist_entry *, struct hist_entry *);
-extern int64_t hist_entry__collapse(struct hist_entry *, struct hist_entry *);
-int hist_entry__fprintf(struct hist_entry *self, struct hists *pair_hists,
-			bool show_displacement, long displacement, FILE *fp,
-			u64 total);
-int hist_entry__snprintf(struct hist_entry *self, char *bf, size_t size,
-			 struct hists *pair_hists, bool show_displacement,
-			 long displacement, bool color, u64 total);
+				      struct symbol *parent,
+				      struct branch_info *bi,
+				      struct mem_info *mi, u64 period,
+				      u64 weight, u64 transaction,
+				      bool sample_self);
+int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
+			 struct perf_evsel *evsel, struct perf_sample *sample,
+			 int max_stack_depth, void *arg);
+
+int64_t hist_entry__cmp(struct hist_entry *left, struct hist_entry *right);
+int64_t hist_entry__collapse(struct hist_entry *left, struct hist_entry *right);
+int hist_entry__transaction_len(void);
+int hist_entry__sort_snprintf(struct hist_entry *he, char *bf, size_t size,
+			      struct hists *hists);
 void hist_entry__free(struct hist_entry *);
 
-void hists__output_resort(struct hists *self);
-void hists__collapse_resort(struct hists *self);
+void hists__output_resort(struct hists *hists);
+void hists__collapse_resort(struct hists *hists, struct ui_progress *prog);
 
-void hists__inc_nr_events(struct hists *self, u32 type);
-size_t hists__fprintf_nr_events(struct hists *self, FILE *fp);
+void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel);
+void hists__output_recalc_col_len(struct hists *hists, int max_rows);
 
-size_t hists__fprintf(struct hists *self, struct hists *pair,
-		      bool show_displacement, FILE *fp);
+u64 hists__total_period(struct hists *hists);
+void hists__reset_stats(struct hists *hists);
+void hists__inc_stats(struct hists *hists, struct hist_entry *h);
+void hists__inc_nr_events(struct hists *hists, u32 type);
+void hists__inc_nr_samples(struct hists *hists, bool filtered);
+void events_stats__inc(struct events_stats *stats, u32 type);
+size_t events_stats__fprintf(struct events_stats *stats, FILE *fp);
 
-int hist_entry__inc_addr_samples(struct hist_entry *self, u64 ip);
-int hist_entry__annotate(struct hist_entry *self, struct list_head *head);
+size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
+		      int max_cols, float min_pcnt, FILE *fp);
 
-void hists__filter_by_dso(struct hists *self, const struct dso *dso);
-void hists__filter_by_thread(struct hists *self, const struct thread *thread);
+void hists__filter_by_dso(struct hists *hists);
+void hists__filter_by_thread(struct hists *hists);
+void hists__filter_by_symbol(struct hists *hists);
 
-#ifdef NO_NEWT_SUPPORT
-static inline int hists__browse(struct hists *self __used,
-				const char *helpline __used,
-				const char *ev_name __used)
+static inline bool hists__has_filter(struct hists *hists)
 {
-	return 0;
+	return hists->thread_filter || hists->dso_filter ||
+		hists->symbol_filter_str;
 }
 
-static inline int hists__tui_browse_tree(struct rb_root *self __used,
-					 const char *help __used)
+u16 hists__col_len(struct hists *hists, enum hist_column col);
+void hists__set_col_len(struct hists *hists, enum hist_column col, u16 len);
+bool hists__new_col_len(struct hists *hists, enum hist_column col, u16 len);
+void hists__reset_col_len(struct hists *hists);
+void hists__calc_col_len(struct hists *hists, struct hist_entry *he);
+
+void hists__match(struct hists *leader, struct hists *other);
+int hists__link(struct hists *leader, struct hists *other);
+
+struct perf_hpp {
+	char *buf;
+	size_t size;
+	const char *sep;
+	void *ptr;
+};
+
+struct perf_hpp_fmt {
+	int (*header)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+		      struct perf_evsel *evsel);
+	int (*width)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+		     struct perf_evsel *evsel);
+	int (*color)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+		     struct hist_entry *he);
+	int (*entry)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+		     struct hist_entry *he);
+	int64_t (*cmp)(struct hist_entry *a, struct hist_entry *b);
+	int64_t (*collapse)(struct hist_entry *a, struct hist_entry *b);
+	int64_t (*sort)(struct hist_entry *a, struct hist_entry *b);
+
+	struct list_head list;
+	struct list_head sort_list;
+	bool elide;
+};
+
+extern struct list_head perf_hpp__list;
+extern struct list_head perf_hpp__sort_list;
+
+#define perf_hpp__for_each_format(format) \
+	list_for_each_entry(format, &perf_hpp__list, list)
+
+#define perf_hpp__for_each_format_safe(format, tmp)	\
+	list_for_each_entry_safe(format, tmp, &perf_hpp__list, list)
+
+#define perf_hpp__for_each_sort_list(format) \
+	list_for_each_entry(format, &perf_hpp__sort_list, sort_list)
+
+#define perf_hpp__for_each_sort_list_safe(format, tmp)	\
+	list_for_each_entry_safe(format, tmp, &perf_hpp__sort_list, sort_list)
+
+extern struct perf_hpp_fmt perf_hpp__format[];
+
+enum {
+	/* Matches perf_hpp__format array. */
+	PERF_HPP__OVERHEAD,
+	PERF_HPP__OVERHEAD_SYS,
+	PERF_HPP__OVERHEAD_US,
+	PERF_HPP__OVERHEAD_GUEST_SYS,
+	PERF_HPP__OVERHEAD_GUEST_US,
+	PERF_HPP__OVERHEAD_ACC,
+	PERF_HPP__SAMPLES,
+	PERF_HPP__PERIOD,
+
+	PERF_HPP__MAX_INDEX
+};
+
+void perf_hpp__init(void);
+void perf_hpp__column_register(struct perf_hpp_fmt *format);
+void perf_hpp__column_unregister(struct perf_hpp_fmt *format);
+void perf_hpp__column_enable(unsigned col);
+void perf_hpp__column_disable(unsigned col);
+void perf_hpp__cancel_cumulate(void);
+
+void perf_hpp__register_sort_field(struct perf_hpp_fmt *format);
+void perf_hpp__setup_output_field(void);
+void perf_hpp__reset_output_field(void);
+void perf_hpp__append_sort_keys(void);
+
+bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format);
+bool perf_hpp__same_sort_entry(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b);
+
+static inline bool perf_hpp__should_skip(struct perf_hpp_fmt *format)
+{
+	return format->elide;
+}
+
+void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists);
+
+typedef u64 (*hpp_field_fn)(struct hist_entry *he);
+typedef int (*hpp_callback_fn)(struct perf_hpp *hpp, bool front);
+typedef int (*hpp_snprint_fn)(struct perf_hpp *hpp, const char *fmt, ...);
+
+int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
+	       hpp_field_fn get_field, const char *fmt,
+	       hpp_snprint_fn print_fn, bool fmt_percent);
+int __hpp__fmt_acc(struct perf_hpp *hpp, struct hist_entry *he,
+		   hpp_field_fn get_field, const char *fmt,
+		   hpp_snprint_fn print_fn, bool fmt_percent);
+
+static inline void advance_hpp(struct perf_hpp *hpp, int inc)
+{
+	hpp->buf  += inc;
+	hpp->size -= inc;
+}
+
+static inline size_t perf_hpp__use_color(void)
+{
+	return !symbol_conf.field_sep;
+}
+
+static inline size_t perf_hpp__color_overhead(void)
+{
+	return perf_hpp__use_color() ?
+	       (COLOR_MAXLEN + sizeof(PERF_COLOR_RESET)) * PERF_HPP__MAX_INDEX
+	       : 0;
+}
+
+struct perf_evlist;
+
+struct hist_browser_timer {
+	void (*timer)(void *arg);
+	void *arg;
+	int refresh;
+};
+
+#ifdef HAVE_SLANG_SUPPORT
+#include "../ui/keysyms.h"
+int hist_entry__tui_annotate(struct hist_entry *he, struct perf_evsel *evsel,
+			     struct hist_browser_timer *hbt);
+
+int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help,
+				  struct hist_browser_timer *hbt,
+				  float min_pcnt,
+				  struct perf_session_env *env);
+int script_browse(const char *script_opt);
+#else
+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;
 }
 
-static inline int hist_entry__tui_annotate(struct hist_entry *self __used)
+static inline int hist_entry__tui_annotate(struct hist_entry *he __maybe_unused,
+					   struct perf_evsel *evsel __maybe_unused,
+					   struct hist_browser_timer *hbt __maybe_unused)
 {
 	return 0;
 }
-#define KEY_LEFT -1
-#define KEY_RIGHT -2
-#else
-#include <newt.h>
-int hists__browse(struct hists *self, const char *helpline,
-		  const char *ev_name);
-int hist_entry__tui_annotate(struct hist_entry *self);
 
-#define KEY_LEFT NEWT_KEY_LEFT
-#define KEY_RIGHT NEWT_KEY_RIGHT
+static inline int script_browse(const char *script_opt __maybe_unused)
+{
+	return 0;
+}
 
-int hists__tui_browse_tree(struct rb_root *self, const char *help);
+#define K_LEFT  -1000
+#define K_RIGHT -2000
+#define K_SWITCH_INPUT_DATA -3000
 #endif
+
+unsigned int hists__sort_list_width(struct hists *hists);
+
+struct option;
+int parse_filter_percentage(const struct option *opt __maybe_unused,
+			    const char *arg, int unset __maybe_unused);
+int perf_hist_config(const char *var, const char *value);
+
 #endif	/* __PERF_HIST_H */
diff --git a/tools/perf/util/include/asm/alternative-asm.h b/tools/perf/util/include/asm/alternative-asm.h
new file mode 100644
index 00000000000..6789d788d49
--- /dev/null
+++ b/tools/perf/util/include/asm/alternative-asm.h
@@ -0,0 +1,8 @@
+#ifndef _PERF_ASM_ALTERNATIVE_ASM_H
+#define _PERF_ASM_ALTERNATIVE_ASM_H
+
+/* Just disable it so we can build arch/x86/lib/memcpy_64.S for perf bench: */
+
+#define altinstruction_entry #
+
+#endif
diff --git a/tools/perf/util/include/asm/bug.h b/tools/perf/util/include/asm/bug.h
deleted file mode 100644
index 7fcc6810adc..00000000000
--- a/tools/perf/util/include/asm/bug.h
+++ /dev/null
@@ -1,22 +0,0 @@
-#ifndef _PERF_ASM_GENERIC_BUG_H
-#define _PERF_ASM_GENERIC_BUG_H
-
-#define __WARN_printf(arg...)	do { fprintf(stderr, arg); } while (0)
-
-#define WARN(condition, format...) ({		\
-	int __ret_warn_on = !!(condition);	\
-	if (unlikely(__ret_warn_on))		\
-		__WARN_printf(format);		\
-	unlikely(__ret_warn_on);		\
-})
-
-#define WARN_ONCE(condition, format...)	({	\
-	static int __warned;			\
-	int __ret_warn_once = !!(condition);	\
-						\
-	if (unlikely(__ret_warn_once))		\
-		if (WARN(!__warned, format)) 	\
-			__warned = 1;		\
-	unlikely(__ret_warn_once);		\
-})
-#endif
diff --git a/tools/perf/util/include/asm/byteorder.h b/tools/perf/util/include/asm/byteorder.h
index b722abe3a62..2a9bdc06630 100644
--- a/tools/perf/util/include/asm/byteorder.h
+++ b/tools/perf/util/include/asm/byteorder.h
@@ -1,2 +1,2 @@
 #include <asm/types.h>
-#include "../../../../include/linux/swab.h"
+#include "../../../../include/uapi/linux/swab.h"
diff --git a/tools/perf/util/include/asm/cpufeature.h b/tools/perf/util/include/asm/cpufeature.h
new file mode 100644
index 00000000000..acffd5e4d1d
--- /dev/null
+++ b/tools/perf/util/include/asm/cpufeature.h
@@ -0,0 +1,9 @@
+
+#ifndef PERF_CPUFEATURE_H
+#define PERF_CPUFEATURE_H
+
+/* cpufeature.h ... dummy header file for including arch/x86/lib/memcpy_64.S */
+
+#define X86_FEATURE_REP_GOOD 0
+
+#endif	/* PERF_CPUFEATURE_H */
diff --git a/tools/perf/util/include/asm/dwarf2.h b/tools/perf/util/include/asm/dwarf2.h
new file mode 100644
index 00000000000..afe38199e92
--- /dev/null
+++ b/tools/perf/util/include/asm/dwarf2.h
@@ -0,0 +1,13 @@
+
+#ifndef PERF_DWARF2_H
+#define PERF_DWARF2_H
+
+/* dwarf2.h ... dummy header file for including arch/x86/lib/mem{cpy,set}_64.S */
+
+#define CFI_STARTPROC
+#define CFI_ENDPROC
+#define CFI_REMEMBER_STATE
+#define CFI_RESTORE_STATE
+
+#endif	/* PERF_DWARF2_H */
+
diff --git a/tools/perf/util/include/asm/hash.h b/tools/perf/util/include/asm/hash.h
new file mode 100644
index 00000000000..d82b170bb21
--- /dev/null
+++ b/tools/perf/util/include/asm/hash.h
@@ -0,0 +1,6 @@
+#ifndef __ASM_GENERIC_HASH_H
+#define __ASM_GENERIC_HASH_H
+
+/* Stub */
+
+#endif /* __ASM_GENERIC_HASH_H */
diff --git a/tools/perf/util/include/asm/unistd_32.h b/tools/perf/util/include/asm/unistd_32.h
new file mode 100644
index 00000000000..8b137891791
--- /dev/null
+++ b/tools/perf/util/include/asm/unistd_32.h
@@ -0,0 +1 @@
+
diff --git a/tools/perf/util/include/asm/unistd_64.h b/tools/perf/util/include/asm/unistd_64.h
new file mode 100644
index 00000000000..8b137891791
--- /dev/null
+++ b/tools/perf/util/include/asm/unistd_64.h
@@ -0,0 +1 @@
+
diff --git a/tools/perf/util/include/dwarf-regs.h b/tools/perf/util/include/dwarf-regs.h
index cf6727e99c4..8f149655f49 100644
--- a/tools/perf/util/include/dwarf-regs.h
+++ b/tools/perf/util/include/dwarf-regs.h
@@ -1,7 +1,7 @@
 #ifndef _PERF_DWARF_REGS_H_
 #define _PERF_DWARF_REGS_H_
 
-#ifdef DWARF_SUPPORT
+#ifdef HAVE_DWARF_SUPPORT
 const char *get_arch_regstr(unsigned int n);
 #endif
 
diff --git a/tools/perf/util/include/linux/bitmap.h b/tools/perf/util/include/linux/bitmap.h
index eda4416efa0..01ffd12dc79 100644
--- a/tools/perf/util/include/linux/bitmap.h
+++ b/tools/perf/util/include/linux/bitmap.h
@@ -4,7 +4,12 @@
 #include <string.h>
 #include <linux/bitops.h>
 
+#define DECLARE_BITMAP(name,bits) \
+	unsigned long name[BITS_TO_LONGS(bits)]
+
 int __bitmap_weight(const unsigned long *bitmap, int bits);
+void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
+		 const unsigned long *bitmap2, int bits);
 
 #define BITMAP_LAST_WORD_MASK(nbits)					\
 (									\
@@ -32,4 +37,13 @@ static inline int bitmap_weight(const unsigned long *src, int nbits)
 	return __bitmap_weight(src, nbits);
 }
 
+static inline void bitmap_or(unsigned long *dst, const unsigned long *src1,
+			     const unsigned long *src2, int nbits)
+{
+	if (small_const_nbits(nbits))
+		*dst = *src1 | *src2;
+	else
+		__bitmap_or(dst, src1, src2, nbits);
+}
+
 #endif /* _PERF_BITOPS_H */
diff --git a/tools/perf/util/include/linux/bitops.h b/tools/perf/util/include/linux/bitops.h
index bb4ac2e0538..dadfa7e5428 100644
--- a/tools/perf/util/include/linux/bitops.h
+++ b/tools/perf/util/include/linux/bitops.h
@@ -2,17 +2,41 @@
 #define _PERF_LINUX_BITOPS_H_
 
 #include <linux/kernel.h>
+#include <linux/compiler.h>
 #include <asm/hweight.h>
 
+#ifndef __WORDSIZE
+#define __WORDSIZE (__SIZEOF_LONG__ * 8)
+#endif
+
 #define BITS_PER_LONG __WORDSIZE
 #define BITS_PER_BYTE           8
 #define BITS_TO_LONGS(nr)       DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long))
+#define BITS_TO_U64(nr)         DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u64))
+#define BITS_TO_U32(nr)         DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u32))
+#define BITS_TO_BYTES(nr)       DIV_ROUND_UP(nr, BITS_PER_BYTE)
+
+#define for_each_set_bit(bit, addr, size) \
+	for ((bit) = find_first_bit((addr), (size));		\
+	     (bit) < (size);					\
+	     (bit) = find_next_bit((addr), (size), (bit) + 1))
+
+/* same as for_each_set_bit() but use bit as value to start with */
+#define for_each_set_bit_from(bit, addr, size) \
+	for ((bit) = find_next_bit((addr), (size), (bit));	\
+	     (bit) < (size);					\
+	     (bit) = find_next_bit((addr), (size), (bit) + 1))
 
 static inline void set_bit(int nr, unsigned long *addr)
 {
 	addr[nr / BITS_PER_LONG] |= 1UL << (nr % BITS_PER_LONG);
 }
 
+static inline void clear_bit(int nr, unsigned long *addr)
+{
+	addr[nr / BITS_PER_LONG] &= ~(1UL << (nr % BITS_PER_LONG));
+}
+
 static __always_inline int test_bit(unsigned int nr, const unsigned long *addr)
 {
 	return ((1UL << (nr % BITS_PER_LONG)) &
@@ -24,4 +48,113 @@ static inline unsigned long hweight_long(unsigned long w)
 	return sizeof(w) == 4 ? hweight32(w) : hweight64(w);
 }
 
+#define BITOP_WORD(nr)		((nr) / BITS_PER_LONG)
+
+/**
+ * __ffs - find first bit in word.
+ * @word: The word to search
+ *
+ * Undefined if no bit exists, so code should check against 0 first.
+ */
+static __always_inline unsigned long __ffs(unsigned long word)
+{
+	int num = 0;
+
+#if BITS_PER_LONG == 64
+	if ((word & 0xffffffff) == 0) {
+		num += 32;
+		word >>= 32;
+	}
+#endif
+	if ((word & 0xffff) == 0) {
+		num += 16;
+		word >>= 16;
+	}
+	if ((word & 0xff) == 0) {
+		num += 8;
+		word >>= 8;
+	}
+	if ((word & 0xf) == 0) {
+		num += 4;
+		word >>= 4;
+	}
+	if ((word & 0x3) == 0) {
+		num += 2;
+		word >>= 2;
+	}
+	if ((word & 0x1) == 0)
+		num += 1;
+	return num;
+}
+
+typedef const unsigned long __attribute__((__may_alias__)) long_alias_t;
+
+/*
+ * Find the first set bit in a memory region.
+ */
+static inline unsigned long
+find_first_bit(const unsigned long *addr, unsigned long size)
+{
+	long_alias_t *p = (long_alias_t *) addr;
+	unsigned long result = 0;
+	unsigned long tmp;
+
+	while (size & ~(BITS_PER_LONG-1)) {
+		if ((tmp = *(p++)))
+			goto found;
+		result += BITS_PER_LONG;
+		size -= BITS_PER_LONG;
+	}
+	if (!size)
+		return result;
+
+	tmp = (*p) & (~0UL >> (BITS_PER_LONG - size));
+	if (tmp == 0UL)		/* Are any bits set? */
+		return result + size;	/* Nope. */
+found:
+	return result + __ffs(tmp);
+}
+
+/*
+ * Find the next set bit in a memory region.
+ */
+static inline unsigned long
+find_next_bit(const unsigned long *addr, unsigned long size, unsigned long offset)
+{
+	const unsigned long *p = addr + BITOP_WORD(offset);
+	unsigned long result = offset & ~(BITS_PER_LONG-1);
+	unsigned long tmp;
+
+	if (offset >= size)
+		return size;
+	size -= result;
+	offset %= BITS_PER_LONG;
+	if (offset) {
+		tmp = *(p++);
+		tmp &= (~0UL << offset);
+		if (size < BITS_PER_LONG)
+			goto found_first;
+		if (tmp)
+			goto found_middle;
+		size -= BITS_PER_LONG;
+		result += BITS_PER_LONG;
+	}
+	while (size & ~(BITS_PER_LONG-1)) {
+		if ((tmp = *(p++)))
+			goto found_middle;
+		result += BITS_PER_LONG;
+		size -= BITS_PER_LONG;
+	}
+	if (!size)
+		return result;
+	tmp = *p;
+
+found_first:
+	tmp &= (~0UL >> (BITS_PER_LONG - size));
+	if (tmp == 0UL)		/* Are any bits set? */
+		return result + size;	/* Nope. */
+found_middle:
+	return result + __ffs(tmp);
+}
+
 #endif
diff --git a/tools/perf/util/include/linux/compiler.h b/tools/perf/util/include/linux/compiler.h
deleted file mode 100644
index 791f9dd27eb..00000000000
--- a/tools/perf/util/include/linux/compiler.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifndef _PERF_LINUX_COMPILER_H_
-#define _PERF_LINUX_COMPILER_H_
-
-#ifndef __always_inline
-#define __always_inline	inline
-#endif
-#define __user
-#define __attribute_const__
-
-#define __used		__attribute__((__unused__))
-
-#endif
diff --git a/tools/perf/util/include/linux/const.h b/tools/perf/util/include/linux/const.h
new file mode 100644
index 00000000000..c10a35e1afb
--- /dev/null
+++ b/tools/perf/util/include/linux/const.h
@@ -0,0 +1 @@
+#include "../../../../include/uapi/linux/const.h"
diff --git a/tools/perf/util/include/linux/hash.h b/tools/perf/util/include/linux/hash.h
deleted file mode 100644
index 201f5739799..00000000000
--- a/tools/perf/util/include/linux/hash.h
+++ /dev/null
@@ -1,5 +0,0 @@
-#include "../../../../include/linux/hash.h"
-
-#ifndef PERF_HASH_H
-#define PERF_HASH_H
-#endif
diff --git a/tools/perf/util/include/linux/kernel.h b/tools/perf/util/include/linux/kernel.h
index 1eb804fd3fb..9844c31b7c2 100644
--- a/tools/perf/util/include/linux/kernel.h
+++ b/tools/perf/util/include/linux/kernel.h
@@ -8,8 +8,8 @@
 
 #define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d))
 
-#define ALIGN(x,a)		__ALIGN_MASK(x,(typeof(x))(a)-1)
-#define __ALIGN_MASK(x,mask)	(((x)+(mask))&~(mask))
+#define PERF_ALIGN(x, a)	__PERF_ALIGN_MASK(x, (typeof(x))(a)-1)
+#define __PERF_ALIGN_MASK(x, mask)	(((x)+(mask))&~(mask))
 
 #ifndef offsetof
 #define offsetof(TYPE, MEMBER) ((size_t) &((TYPE *)0)->MEMBER)
@@ -46,9 +46,22 @@
 	_min1 < _min2 ? _min1 : _min2; })
 #endif
 
+#ifndef roundup
+#define roundup(x, y) (                                \
+{                                                      \
+	const typeof(y) __y = y;		       \
+	(((x) + (__y - 1)) / __y) * __y;	       \
+}                                                      \
+)
+#endif
+
 #ifndef BUG_ON
+#ifdef NDEBUG
+#define BUG_ON(cond) do { if (cond) {} } while (0)
+#else
 #define BUG_ON(cond) assert(!(cond))
 #endif
+#endif
 
 /*
  * Both need more care to handle endianness
@@ -81,12 +94,6 @@ static inline int scnprintf(char * buf, size_t size, const char * fmt, ...)
 	return (i >= ssize) ? (ssize - 1) : i;
 }
 
-static inline unsigned long
-simple_strtoul(const char *nptr, char **endptr, int base)
-{
-	return strtoul(nptr, endptr, base);
-}
-
 int eprintf(int level,
 	    const char *fmt, ...) __attribute__((format(printf, 2, 3)));
 
@@ -108,4 +115,14 @@ int eprintf(int level,
 #define pr_debug3(fmt, ...) pr_debugN(3, pr_fmt(fmt), ##__VA_ARGS__)
 #define pr_debug4(fmt, ...) pr_debugN(4, pr_fmt(fmt), ##__VA_ARGS__)
 
+/*
+ * This looks more complex than it should be. But we need to
+ * get the type for the ~ right in round_down (it needs to be
+ * as wide as the result!), and we want to evaluate the macro
+ * arguments just once each.
+ */
+#define __round_mask(x, y) ((__typeof__(x))((y)-1))
+#define round_up(x, y) ((((x)-1) | __round_mask(x, y))+1)
+#define round_down(x, y) ((x) & ~__round_mask(x, y))
+
 #endif
diff --git a/tools/perf/util/include/linux/linkage.h b/tools/perf/util/include/linux/linkage.h
new file mode 100644
index 00000000000..06387cffe12
--- /dev/null
+++ b/tools/perf/util/include/linux/linkage.h
@@ -0,0 +1,13 @@
+
+#ifndef PERF_LINUX_LINKAGE_H_
+#define PERF_LINUX_LINKAGE_H_
+
+/* linkage.h ... for including arch/x86/lib/memcpy_64.S */
+
+#define ENTRY(name)				\
+	.globl name;				\
+	name:
+
+#define ENDPROC(name)
+
+#endif	/* PERF_LINUX_LINKAGE_H_ */
diff --git a/tools/perf/util/include/linux/list.h b/tools/perf/util/include/linux/list.h
index dbe4b814382..76ddbc72634 100644
--- a/tools/perf/util/include/linux/list.h
+++ b/tools/perf/util/include/linux/list.h
@@ -1,3 +1,6 @@
+#include <linux/kernel.h>
+#include <linux/types.h>
+
 #include "../../../../include/linux/list.h"
 
 #ifndef PERF_LIST_H
@@ -15,4 +18,12 @@ static inline void list_del_range(struct list_head *begin,
 	begin->prev->next = end->next;
 	end->next->prev = begin->prev;
 }
+
+/**
+ * list_for_each_from	-	iterate over a list from one of its nodes
+ * @pos:  the &struct list_head to use as a loop cursor, from where to start
+ * @head: the head for your list.
+ */
+#define list_for_each_from(pos, head) \
+	for (; pos != (head); pos = pos->next)
 #endif
diff --git a/tools/perf/util/include/linux/module.h b/tools/perf/util/include/linux/module.h
deleted file mode 100644
index b43e2dc21e0..00000000000
--- a/tools/perf/util/include/linux/module.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef PERF_LINUX_MODULE_H
-#define PERF_LINUX_MODULE_H
-
-#define EXPORT_SYMBOL(name)
-
-#endif
diff --git a/tools/perf/util/include/linux/prefetch.h b/tools/perf/util/include/linux/prefetch.h
deleted file mode 100644
index 7841e485d8c..00000000000
--- a/tools/perf/util/include/linux/prefetch.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef PERF_LINUX_PREFETCH_H
-#define PERF_LINUX_PREFETCH_H
-
-static inline void prefetch(void *a __attribute__((unused))) { }
-
-#endif
diff --git a/tools/perf/util/include/linux/rbtree.h b/tools/perf/util/include/linux/rbtree.h
index 7a243a14303..2a030c5af3a 100644
--- a/tools/perf/util/include/linux/rbtree.h
+++ b/tools/perf/util/include/linux/rbtree.h
@@ -1 +1,2 @@
+#include <stdbool.h>
 #include "../../../../include/linux/rbtree.h"
diff --git a/tools/perf/util/include/linux/rbtree_augmented.h b/tools/perf/util/include/linux/rbtree_augmented.h
new file mode 100644
index 00000000000..9d6fcdf1788
--- /dev/null
+++ b/tools/perf/util/include/linux/rbtree_augmented.h
@@ -0,0 +1,2 @@
+#include <stdbool.h>
+#include "../../../../include/linux/rbtree_augmented.h"
diff --git a/tools/perf/util/include/linux/string.h b/tools/perf/util/include/linux/string.h
index 3b2f5900276..97a80073822 100644
--- a/tools/perf/util/include/linux/string.h
+++ b/tools/perf/util/include/linux/string.h
@@ -1 +1,4 @@
 #include <string.h>
+
+void *memdup(const void *src, size_t len);
+int str_append(char **s, int *len, const char *a);
diff --git a/tools/perf/util/include/linux/types.h b/tools/perf/util/include/linux/types.h
deleted file mode 100644
index 196862a81a2..00000000000
--- a/tools/perf/util/include/linux/types.h
+++ /dev/null
@@ -1,9 +0,0 @@
-#ifndef _PERF_LINUX_TYPES_H_
-#define _PERF_LINUX_TYPES_H_
-
-#include <asm/types.h>
-
-#define DECLARE_BITMAP(name,bits) \
-	unsigned long name[BITS_TO_LONGS(bits)]
-
-#endif
diff --git a/tools/perf/util/intlist.c b/tools/perf/util/intlist.c
new file mode 100644
index 00000000000..89715b64a31
--- /dev/null
+++ b/tools/perf/util/intlist.c
@@ -0,0 +1,146 @@
+/*
+ * Based on intlist.c by:
+ * (c) 2009 Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Licensed under the GPLv2.
+ */
+
+#include <errno.h>
+#include <stdlib.h>
+#include <linux/compiler.h>
+
+#include "intlist.h"
+
+static struct rb_node *intlist__node_new(struct rblist *rblist __maybe_unused,
+					 const void *entry)
+{
+	int i = (int)((long)entry);
+	struct rb_node *rc = NULL;
+	struct int_node *node = malloc(sizeof(*node));
+
+	if (node != NULL) {
+		node->i = i;
+		node->priv = NULL;
+		rc = &node->rb_node;
+	}
+
+	return rc;
+}
+
+static void int_node__delete(struct int_node *ilist)
+{
+	free(ilist);
+}
+
+static void intlist__node_delete(struct rblist *rblist __maybe_unused,
+				 struct rb_node *rb_node)
+{
+	struct int_node *node = container_of(rb_node, struct int_node, rb_node);
+
+	int_node__delete(node);
+}
+
+static int intlist__node_cmp(struct rb_node *rb_node, const void *entry)
+{
+	int i = (int)((long)entry);
+	struct int_node *node = container_of(rb_node, struct int_node, rb_node);
+
+	return node->i - i;
+}
+
+int intlist__add(struct intlist *ilist, int i)
+{
+	return rblist__add_node(&ilist->rblist, (void *)((long)i));
+}
+
+void intlist__remove(struct intlist *ilist, struct int_node *node)
+{
+	rblist__remove_node(&ilist->rblist, &node->rb_node);
+}
+
+static struct int_node *__intlist__findnew(struct intlist *ilist,
+					   int i, bool create)
+{
+	struct int_node *node = NULL;
+	struct rb_node *rb_node;
+
+	if (ilist == NULL)
+		return NULL;
+
+	if (create)
+		rb_node = rblist__findnew(&ilist->rblist, (void *)((long)i));
+	else
+		rb_node = rblist__find(&ilist->rblist, (void *)((long)i));
+
+	if (rb_node)
+		node = container_of(rb_node, struct int_node, rb_node);
+
+	return node;
+}
+
+struct int_node *intlist__find(struct intlist *ilist, int i)
+{
+	return __intlist__findnew(ilist, i, false);
+}
+
+struct int_node *intlist__findnew(struct intlist *ilist, int i)
+{
+	return __intlist__findnew(ilist, i, true);
+}
+
+static int intlist__parse_list(struct intlist *ilist, const char *s)
+{
+	char *sep;
+	int err;
+
+	do {
+		long value = strtol(s, &sep, 10);
+		err = -EINVAL;
+		if (*sep != ',' && *sep != '\0')
+			break;
+		err = intlist__add(ilist, value);
+		if (err)
+			break;
+		s = sep + 1;
+	} while (*sep != '\0');
+
+	return err;
+}
+
+struct intlist *intlist__new(const char *slist)
+{
+	struct intlist *ilist = malloc(sizeof(*ilist));
+
+	if (ilist != NULL) {
+		rblist__init(&ilist->rblist);
+		ilist->rblist.node_cmp    = intlist__node_cmp;
+		ilist->rblist.node_new    = intlist__node_new;
+		ilist->rblist.node_delete = intlist__node_delete;
+
+		if (slist && intlist__parse_list(ilist, slist))
+			goto out_delete;
+	}
+
+	return ilist;
+out_delete:
+	intlist__delete(ilist);
+	return NULL;
+}
+
+void intlist__delete(struct intlist *ilist)
+{
+	if (ilist != NULL)
+		rblist__delete(&ilist->rblist);
+}
+
+struct int_node *intlist__entry(const struct intlist *ilist, unsigned int idx)
+{
+	struct int_node *node = NULL;
+	struct rb_node *rb_node;
+
+	rb_node = rblist__entry(&ilist->rblist, idx);
+	if (rb_node)
+		node = container_of(rb_node, struct int_node, rb_node);
+
+	return node;
+}
diff --git a/tools/perf/util/intlist.h b/tools/perf/util/intlist.h
new file mode 100644
index 00000000000..aa6877d3685
--- /dev/null
+++ b/tools/perf/util/intlist.h
@@ -0,0 +1,77 @@
+#ifndef __PERF_INTLIST_H
+#define __PERF_INTLIST_H
+
+#include <linux/rbtree.h>
+#include <stdbool.h>
+
+#include "rblist.h"
+
+struct int_node {
+	struct rb_node rb_node;
+	int i;
+	void *priv;
+};
+
+struct intlist {
+	struct rblist rblist;
+};
+
+struct intlist *intlist__new(const char *slist);
+void intlist__delete(struct intlist *ilist);
+
+void intlist__remove(struct intlist *ilist, struct int_node *in);
+int intlist__add(struct intlist *ilist, int i);
+
+struct int_node *intlist__entry(const struct intlist *ilist, unsigned int idx);
+struct int_node *intlist__find(struct intlist *ilist, int i);
+struct int_node *intlist__findnew(struct intlist *ilist, int i);
+
+static inline bool intlist__has_entry(struct intlist *ilist, int i)
+{
+	return intlist__find(ilist, i) != NULL;
+}
+
+static inline bool intlist__empty(const struct intlist *ilist)
+{
+	return rblist__empty(&ilist->rblist);
+}
+
+static inline unsigned int intlist__nr_entries(const struct intlist *ilist)
+{
+	return rblist__nr_entries(&ilist->rblist);
+}
+
+/* For intlist iteration */
+static inline struct int_node *intlist__first(struct intlist *ilist)
+{
+	struct rb_node *rn = rb_first(&ilist->rblist.entries);
+	return rn ? rb_entry(rn, struct int_node, rb_node) : NULL;
+}
+static inline struct int_node *intlist__next(struct int_node *in)
+{
+	struct rb_node *rn;
+	if (!in)
+		return NULL;
+	rn = rb_next(&in->rb_node);
+	return rn ? rb_entry(rn, struct int_node, rb_node) : NULL;
+}
+
+/**
+ * intlist_for_each      - iterate over a intlist
+ * @pos:	the &struct int_node to use as a loop cursor.
+ * @ilist:	the &struct intlist for loop.
+ */
+#define intlist__for_each(pos, ilist)	\
+	for (pos = intlist__first(ilist); pos; pos = intlist__next(pos))
+
+/**
+ * intlist_for_each_safe - iterate over a intlist safe against removal of
+ *                         int_node
+ * @pos:	the &struct int_node to use as a loop cursor.
+ * @n:		another &struct int_node to use as temporary storage.
+ * @ilist:	the &struct intlist for loop.
+ */
+#define intlist__for_each_safe(pos, n, ilist)	\
+	for (pos = intlist__first(ilist), n = intlist__next(pos); pos;\
+	     pos = n, n = intlist__next(n))
+#endif /* __PERF_INTLIST_H */
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
new file mode 100644
index 00000000000..c73e1fc12e5
--- /dev/null
+++ b/tools/perf/util/machine.c
@@ -0,0 +1,1422 @@
+#include "callchain.h"
+#include "debug.h"
+#include "event.h"
+#include "evsel.h"
+#include "hist.h"
+#include "machine.h"
+#include "map.h"
+#include "sort.h"
+#include "strlist.h"
+#include "thread.h"
+#include <stdbool.h>
+#include <symbol/kallsyms.h>
+#include "unwind.h"
+
+int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
+{
+	map_groups__init(&machine->kmaps);
+	RB_CLEAR_NODE(&machine->rb_node);
+	INIT_LIST_HEAD(&machine->user_dsos);
+	INIT_LIST_HEAD(&machine->kernel_dsos);
+
+	machine->threads = RB_ROOT;
+	INIT_LIST_HEAD(&machine->dead_threads);
+	machine->last_match = NULL;
+
+	machine->kmaps.machine = machine;
+	machine->pid = pid;
+
+	machine->symbol_filter = NULL;
+	machine->id_hdr_size = 0;
+
+	machine->root_dir = strdup(root_dir);
+	if (machine->root_dir == NULL)
+		return -ENOMEM;
+
+	if (pid != HOST_KERNEL_ID) {
+		struct thread *thread = machine__findnew_thread(machine, 0,
+								pid);
+		char comm[64];
+
+		if (thread == NULL)
+			return -ENOMEM;
+
+		snprintf(comm, sizeof(comm), "[guest/%d]", pid);
+		thread__set_comm(thread, comm, 0);
+	}
+
+	return 0;
+}
+
+struct machine *machine__new_host(void)
+{
+	struct machine *machine = malloc(sizeof(*machine));
+
+	if (machine != NULL) {
+		machine__init(machine, "", HOST_KERNEL_ID);
+
+		if (machine__create_kernel_maps(machine) < 0)
+			goto out_delete;
+	}
+
+	return machine;
+out_delete:
+	free(machine);
+	return NULL;
+}
+
+static void dsos__delete(struct list_head *dsos)
+{
+	struct dso *pos, *n;
+
+	list_for_each_entry_safe(pos, n, dsos, node) {
+		list_del(&pos->node);
+		dso__delete(pos);
+	}
+}
+
+void machine__delete_dead_threads(struct machine *machine)
+{
+	struct thread *n, *t;
+
+	list_for_each_entry_safe(t, n, &machine->dead_threads, node) {
+		list_del(&t->node);
+		thread__delete(t);
+	}
+}
+
+void machine__delete_threads(struct machine *machine)
+{
+	struct rb_node *nd = rb_first(&machine->threads);
+
+	while (nd) {
+		struct thread *t = rb_entry(nd, struct thread, rb_node);
+
+		rb_erase(&t->rb_node, &machine->threads);
+		nd = rb_next(nd);
+		thread__delete(t);
+	}
+}
+
+void machine__exit(struct machine *machine)
+{
+	map_groups__exit(&machine->kmaps);
+	dsos__delete(&machine->user_dsos);
+	dsos__delete(&machine->kernel_dsos);
+	zfree(&machine->root_dir);
+}
+
+void machine__delete(struct machine *machine)
+{
+	machine__exit(machine);
+	free(machine);
+}
+
+void machines__init(struct machines *machines)
+{
+	machine__init(&machines->host, "", HOST_KERNEL_ID);
+	machines->guests = RB_ROOT;
+	machines->symbol_filter = NULL;
+}
+
+void machines__exit(struct machines *machines)
+{
+	machine__exit(&machines->host);
+	/* XXX exit guest */
+}
+
+struct machine *machines__add(struct machines *machines, pid_t pid,
+			      const char *root_dir)
+{
+	struct rb_node **p = &machines->guests.rb_node;
+	struct rb_node *parent = NULL;
+	struct machine *pos, *machine = malloc(sizeof(*machine));
+
+	if (machine == NULL)
+		return NULL;
+
+	if (machine__init(machine, root_dir, pid) != 0) {
+		free(machine);
+		return NULL;
+	}
+
+	machine->symbol_filter = machines->symbol_filter;
+
+	while (*p != NULL) {
+		parent = *p;
+		pos = rb_entry(parent, struct machine, rb_node);
+		if (pid < pos->pid)
+			p = &(*p)->rb_left;
+		else
+			p = &(*p)->rb_right;
+	}
+
+	rb_link_node(&machine->rb_node, parent, p);
+	rb_insert_color(&machine->rb_node, &machines->guests);
+
+	return machine;
+}
+
+void machines__set_symbol_filter(struct machines *machines,
+				 symbol_filter_t symbol_filter)
+{
+	struct rb_node *nd;
+
+	machines->symbol_filter = symbol_filter;
+	machines->host.symbol_filter = symbol_filter;
+
+	for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) {
+		struct machine *machine = rb_entry(nd, struct machine, rb_node);
+
+		machine->symbol_filter = symbol_filter;
+	}
+}
+
+struct machine *machines__find(struct machines *machines, pid_t pid)
+{
+	struct rb_node **p = &machines->guests.rb_node;
+	struct rb_node *parent = NULL;
+	struct machine *machine;
+	struct machine *default_machine = NULL;
+
+	if (pid == HOST_KERNEL_ID)
+		return &machines->host;
+
+	while (*p != NULL) {
+		parent = *p;
+		machine = rb_entry(parent, struct machine, rb_node);
+		if (pid < machine->pid)
+			p = &(*p)->rb_left;
+		else if (pid > machine->pid)
+			p = &(*p)->rb_right;
+		else
+			return machine;
+		if (!machine->pid)
+			default_machine = machine;
+	}
+
+	return default_machine;
+}
+
+struct machine *machines__findnew(struct machines *machines, pid_t pid)
+{
+	char path[PATH_MAX];
+	const char *root_dir = "";
+	struct machine *machine = machines__find(machines, pid);
+
+	if (machine && (machine->pid == pid))
+		goto out;
+
+	if ((pid != HOST_KERNEL_ID) &&
+	    (pid != DEFAULT_GUEST_KERNEL_ID) &&
+	    (symbol_conf.guestmount)) {
+		sprintf(path, "%s/%d", symbol_conf.guestmount, pid);
+		if (access(path, R_OK)) {
+			static struct strlist *seen;
+
+			if (!seen)
+				seen = strlist__new(true, NULL);
+
+			if (!strlist__has_entry(seen, path)) {
+				pr_err("Can't access file %s\n", path);
+				strlist__add(seen, path);
+			}
+			machine = NULL;
+			goto out;
+		}
+		root_dir = path;
+	}
+
+	machine = machines__add(machines, pid, root_dir);
+out:
+	return machine;
+}
+
+void machines__process_guests(struct machines *machines,
+			      machine__process_t process, void *data)
+{
+	struct rb_node *nd;
+
+	for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) {
+		struct machine *pos = rb_entry(nd, struct machine, rb_node);
+		process(pos, data);
+	}
+}
+
+char *machine__mmap_name(struct machine *machine, char *bf, size_t size)
+{
+	if (machine__is_host(machine))
+		snprintf(bf, size, "[%s]", "kernel.kallsyms");
+	else if (machine__is_default_guest(machine))
+		snprintf(bf, size, "[%s]", "guest.kernel.kallsyms");
+	else {
+		snprintf(bf, size, "[%s.%d]", "guest.kernel.kallsyms",
+			 machine->pid);
+	}
+
+	return bf;
+}
+
+void machines__set_id_hdr_size(struct machines *machines, u16 id_hdr_size)
+{
+	struct rb_node *node;
+	struct machine *machine;
+
+	machines->host.id_hdr_size = id_hdr_size;
+
+	for (node = rb_first(&machines->guests); node; node = rb_next(node)) {
+		machine = rb_entry(node, struct machine, rb_node);
+		machine->id_hdr_size = id_hdr_size;
+	}
+
+	return;
+}
+
+static struct thread *__machine__findnew_thread(struct machine *machine,
+						pid_t pid, pid_t tid,
+						bool create)
+{
+	struct rb_node **p = &machine->threads.rb_node;
+	struct rb_node *parent = NULL;
+	struct thread *th;
+
+	/*
+	 * Front-end cache - TID lookups come in blocks,
+	 * so most of the time we dont have to look up
+	 * the full rbtree:
+	 */
+	if (machine->last_match && machine->last_match->tid == tid) {
+		if (pid && pid != machine->last_match->pid_)
+			machine->last_match->pid_ = pid;
+		return machine->last_match;
+	}
+
+	while (*p != NULL) {
+		parent = *p;
+		th = rb_entry(parent, struct thread, rb_node);
+
+		if (th->tid == tid) {
+			machine->last_match = th;
+			if (pid && pid != th->pid_)
+				th->pid_ = pid;
+			return th;
+		}
+
+		if (tid < th->tid)
+			p = &(*p)->rb_left;
+		else
+			p = &(*p)->rb_right;
+	}
+
+	if (!create)
+		return NULL;
+
+	th = thread__new(pid, tid);
+	if (th != NULL) {
+		rb_link_node(&th->rb_node, parent, p);
+		rb_insert_color(&th->rb_node, &machine->threads);
+		machine->last_match = th;
+
+		/*
+		 * We have to initialize map_groups separately
+		 * after rb tree is updated.
+		 *
+		 * The reason is that we call machine__findnew_thread
+		 * within thread__init_map_groups to find the thread
+		 * leader and that would screwed the rb tree.
+		 */
+		if (thread__init_map_groups(th, machine))
+			return NULL;
+	}
+
+	return th;
+}
+
+struct thread *machine__findnew_thread(struct machine *machine, pid_t pid,
+				       pid_t tid)
+{
+	return __machine__findnew_thread(machine, pid, tid, true);
+}
+
+struct thread *machine__find_thread(struct machine *machine, pid_t pid,
+				    pid_t tid)
+{
+	return __machine__findnew_thread(machine, pid, tid, false);
+}
+
+int machine__process_comm_event(struct machine *machine, union perf_event *event,
+				struct perf_sample *sample)
+{
+	struct thread *thread = machine__findnew_thread(machine,
+							event->comm.pid,
+							event->comm.tid);
+
+	if (dump_trace)
+		perf_event__fprintf_comm(event, stdout);
+
+	if (thread == NULL || thread__set_comm(thread, event->comm.comm, sample->time)) {
+		dump_printf("problem processing PERF_RECORD_COMM, skipping event.\n");
+		return -1;
+	}
+
+	return 0;
+}
+
+int machine__process_lost_event(struct machine *machine __maybe_unused,
+				union perf_event *event, struct perf_sample *sample __maybe_unused)
+{
+	dump_printf(": id:%" PRIu64 ": lost:%" PRIu64 "\n",
+		    event->lost.id, event->lost.lost);
+	return 0;
+}
+
+struct map *machine__new_module(struct machine *machine, u64 start,
+				const char *filename)
+{
+	struct map *map;
+	struct dso *dso = __dsos__findnew(&machine->kernel_dsos, filename);
+
+	if (dso == NULL)
+		return NULL;
+
+	map = map__new2(start, dso, MAP__FUNCTION);
+	if (map == NULL)
+		return NULL;
+
+	if (machine__is_host(machine))
+		dso->symtab_type = DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE;
+	else
+		dso->symtab_type = DSO_BINARY_TYPE__GUEST_KMODULE;
+	map_groups__insert(&machine->kmaps, map);
+	return map;
+}
+
+size_t machines__fprintf_dsos(struct machines *machines, FILE *fp)
+{
+	struct rb_node *nd;
+	size_t ret = __dsos__fprintf(&machines->host.kernel_dsos, fp) +
+		     __dsos__fprintf(&machines->host.user_dsos, fp);
+
+	for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) {
+		struct machine *pos = rb_entry(nd, struct machine, rb_node);
+		ret += __dsos__fprintf(&pos->kernel_dsos, fp);
+		ret += __dsos__fprintf(&pos->user_dsos, fp);
+	}
+
+	return ret;
+}
+
+size_t machine__fprintf_dsos_buildid(struct machine *machine, FILE *fp,
+				     bool (skip)(struct dso *dso, int parm), int parm)
+{
+	return __dsos__fprintf_buildid(&machine->kernel_dsos, fp, skip, parm) +
+	       __dsos__fprintf_buildid(&machine->user_dsos, fp, skip, parm);
+}
+
+size_t machines__fprintf_dsos_buildid(struct machines *machines, FILE *fp,
+				     bool (skip)(struct dso *dso, int parm), int parm)
+{
+	struct rb_node *nd;
+	size_t ret = machine__fprintf_dsos_buildid(&machines->host, fp, skip, parm);
+
+	for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) {
+		struct machine *pos = rb_entry(nd, struct machine, rb_node);
+		ret += machine__fprintf_dsos_buildid(pos, fp, skip, parm);
+	}
+	return ret;
+}
+
+size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp)
+{
+	int i;
+	size_t printed = 0;
+	struct dso *kdso = machine->vmlinux_maps[MAP__FUNCTION]->dso;
+
+	if (kdso->has_build_id) {
+		char filename[PATH_MAX];
+		if (dso__build_id_filename(kdso, filename, sizeof(filename)))
+			printed += fprintf(fp, "[0] %s\n", filename);
+	}
+
+	for (i = 0; i < vmlinux_path__nr_entries; ++i)
+		printed += fprintf(fp, "[%d] %s\n",
+				   i + kdso->has_build_id, vmlinux_path[i]);
+
+	return printed;
+}
+
+size_t machine__fprintf(struct machine *machine, FILE *fp)
+{
+	size_t ret = 0;
+	struct rb_node *nd;
+
+	for (nd = rb_first(&machine->threads); nd; nd = rb_next(nd)) {
+		struct thread *pos = rb_entry(nd, struct thread, rb_node);
+
+		ret += thread__fprintf(pos, fp);
+	}
+
+	return ret;
+}
+
+static struct dso *machine__get_kernel(struct machine *machine)
+{
+	const char *vmlinux_name = NULL;
+	struct dso *kernel;
+
+	if (machine__is_host(machine)) {
+		vmlinux_name = symbol_conf.vmlinux_name;
+		if (!vmlinux_name)
+			vmlinux_name = "[kernel.kallsyms]";
+
+		kernel = dso__kernel_findnew(machine, vmlinux_name,
+					     "[kernel]",
+					     DSO_TYPE_KERNEL);
+	} else {
+		char bf[PATH_MAX];
+
+		if (machine__is_default_guest(machine))
+			vmlinux_name = symbol_conf.default_guest_vmlinux_name;
+		if (!vmlinux_name)
+			vmlinux_name = machine__mmap_name(machine, bf,
+							  sizeof(bf));
+
+		kernel = dso__kernel_findnew(machine, vmlinux_name,
+					     "[guest.kernel]",
+					     DSO_TYPE_GUEST_KERNEL);
+	}
+
+	if (kernel != NULL && (!kernel->has_build_id))
+		dso__read_running_kernel_build_id(kernel, machine);
+
+	return kernel;
+}
+
+struct process_args {
+	u64 start;
+};
+
+static void machine__get_kallsyms_filename(struct machine *machine, char *buf,
+					   size_t bufsz)
+{
+	if (machine__is_default_guest(machine))
+		scnprintf(buf, bufsz, "%s", symbol_conf.default_guest_kallsyms);
+	else
+		scnprintf(buf, bufsz, "%s/proc/kallsyms", machine->root_dir);
+}
+
+const char *ref_reloc_sym_names[] = {"_text", "_stext", NULL};
+
+/* Figure out the start address of kernel map from /proc/kallsyms.
+ * Returns the name of the start symbol in *symbol_name. Pass in NULL as
+ * symbol_name if it's not that important.
+ */
+static u64 machine__get_kernel_start_addr(struct machine *machine,
+					  const char **symbol_name)
+{
+	char filename[PATH_MAX];
+	int i;
+	const char *name;
+	u64 addr = 0;
+
+	machine__get_kallsyms_filename(machine, filename, PATH_MAX);
+
+	if (symbol__restricted_filename(filename, "/proc/kallsyms"))
+		return 0;
+
+	for (i = 0; (name = ref_reloc_sym_names[i]) != NULL; i++) {
+		addr = kallsyms__get_function_start(filename, name);
+		if (addr)
+			break;
+	}
+
+	if (symbol_name)
+		*symbol_name = name;
+
+	return addr;
+}
+
+int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
+{
+	enum map_type type;
+	u64 start = machine__get_kernel_start_addr(machine, NULL);
+
+	for (type = 0; type < MAP__NR_TYPES; ++type) {
+		struct kmap *kmap;
+
+		machine->vmlinux_maps[type] = map__new2(start, kernel, type);
+		if (machine->vmlinux_maps[type] == NULL)
+			return -1;
+
+		machine->vmlinux_maps[type]->map_ip =
+			machine->vmlinux_maps[type]->unmap_ip =
+				identity__map_ip;
+		kmap = map__kmap(machine->vmlinux_maps[type]);
+		kmap->kmaps = &machine->kmaps;
+		map_groups__insert(&machine->kmaps,
+				   machine->vmlinux_maps[type]);
+	}
+
+	return 0;
+}
+
+void machine__destroy_kernel_maps(struct machine *machine)
+{
+	enum map_type type;
+
+	for (type = 0; type < MAP__NR_TYPES; ++type) {
+		struct kmap *kmap;
+
+		if (machine->vmlinux_maps[type] == NULL)
+			continue;
+
+		kmap = map__kmap(machine->vmlinux_maps[type]);
+		map_groups__remove(&machine->kmaps,
+				   machine->vmlinux_maps[type]);
+		if (kmap->ref_reloc_sym) {
+			/*
+			 * ref_reloc_sym is shared among all maps, so free just
+			 * on one of them.
+			 */
+			if (type == MAP__FUNCTION) {
+				zfree((char **)&kmap->ref_reloc_sym->name);
+				zfree(&kmap->ref_reloc_sym);
+			} else
+				kmap->ref_reloc_sym = NULL;
+		}
+
+		map__delete(machine->vmlinux_maps[type]);
+		machine->vmlinux_maps[type] = NULL;
+	}
+}
+
+int machines__create_guest_kernel_maps(struct machines *machines)
+{
+	int ret = 0;
+	struct dirent **namelist = NULL;
+	int i, items = 0;
+	char path[PATH_MAX];
+	pid_t pid;
+	char *endp;
+
+	if (symbol_conf.default_guest_vmlinux_name ||
+	    symbol_conf.default_guest_modules ||
+	    symbol_conf.default_guest_kallsyms) {
+		machines__create_kernel_maps(machines, DEFAULT_GUEST_KERNEL_ID);
+	}
+
+	if (symbol_conf.guestmount) {
+		items = scandir(symbol_conf.guestmount, &namelist, NULL, NULL);
+		if (items <= 0)
+			return -ENOENT;
+		for (i = 0; i < items; i++) {
+			if (!isdigit(namelist[i]->d_name[0])) {
+				/* Filter out . and .. */
+				continue;
+			}
+			pid = (pid_t)strtol(namelist[i]->d_name, &endp, 10);
+			if ((*endp != '\0') ||
+			    (endp == namelist[i]->d_name) ||
+			    (errno == ERANGE)) {
+				pr_debug("invalid directory (%s). Skipping.\n",
+					 namelist[i]->d_name);
+				continue;
+			}
+			sprintf(path, "%s/%s/proc/kallsyms",
+				symbol_conf.guestmount,
+				namelist[i]->d_name);
+			ret = access(path, R_OK);
+			if (ret) {
+				pr_debug("Can't access file %s\n", path);
+				goto failure;
+			}
+			machines__create_kernel_maps(machines, pid);
+		}
+failure:
+		free(namelist);
+	}
+
+	return ret;
+}
+
+void machines__destroy_kernel_maps(struct machines *machines)
+{
+	struct rb_node *next = rb_first(&machines->guests);
+
+	machine__destroy_kernel_maps(&machines->host);
+
+	while (next) {
+		struct machine *pos = rb_entry(next, struct machine, rb_node);
+
+		next = rb_next(&pos->rb_node);
+		rb_erase(&pos->rb_node, &machines->guests);
+		machine__delete(pos);
+	}
+}
+
+int machines__create_kernel_maps(struct machines *machines, pid_t pid)
+{
+	struct machine *machine = machines__findnew(machines, pid);
+
+	if (machine == NULL)
+		return -1;
+
+	return machine__create_kernel_maps(machine);
+}
+
+int machine__load_kallsyms(struct machine *machine, const char *filename,
+			   enum map_type type, symbol_filter_t filter)
+{
+	struct map *map = machine->vmlinux_maps[type];
+	int ret = dso__load_kallsyms(map->dso, filename, map, filter);
+
+	if (ret > 0) {
+		dso__set_loaded(map->dso, type);
+		/*
+		 * Since /proc/kallsyms will have multiple sessions for the
+		 * kernel, with modules between them, fixup the end of all
+		 * sections.
+		 */
+		__map_groups__fixup_end(&machine->kmaps, type);
+	}
+
+	return ret;
+}
+
+int machine__load_vmlinux_path(struct machine *machine, enum map_type type,
+			       symbol_filter_t filter)
+{
+	struct map *map = machine->vmlinux_maps[type];
+	int ret = dso__load_vmlinux_path(map->dso, map, filter);
+
+	if (ret > 0)
+		dso__set_loaded(map->dso, type);
+
+	return ret;
+}
+
+static void map_groups__fixup_end(struct map_groups *mg)
+{
+	int i;
+	for (i = 0; i < MAP__NR_TYPES; ++i)
+		__map_groups__fixup_end(mg, i);
+}
+
+static char *get_kernel_version(const char *root_dir)
+{
+	char version[PATH_MAX];
+	FILE *file;
+	char *name, *tmp;
+	const char *prefix = "Linux version ";
+
+	sprintf(version, "%s/proc/version", root_dir);
+	file = fopen(version, "r");
+	if (!file)
+		return NULL;
+
+	version[0] = '\0';
+	tmp = fgets(version, sizeof(version), file);
+	fclose(file);
+
+	name = strstr(version, prefix);
+	if (!name)
+		return NULL;
+	name += strlen(prefix);
+	tmp = strchr(name, ' ');
+	if (tmp)
+		*tmp = '\0';
+
+	return strdup(name);
+}
+
+static int map_groups__set_modules_path_dir(struct map_groups *mg,
+				const char *dir_name, int depth)
+{
+	struct dirent *dent;
+	DIR *dir = opendir(dir_name);
+	int ret = 0;
+
+	if (!dir) {
+		pr_debug("%s: cannot open %s dir\n", __func__, dir_name);
+		return -1;
+	}
+
+	while ((dent = readdir(dir)) != NULL) {
+		char path[PATH_MAX];
+		struct stat st;
+
+		/*sshfs might return bad dent->d_type, so we have to stat*/
+		snprintf(path, sizeof(path), "%s/%s", dir_name, dent->d_name);
+		if (stat(path, &st))
+			continue;
+
+		if (S_ISDIR(st.st_mode)) {
+			if (!strcmp(dent->d_name, ".") ||
+			    !strcmp(dent->d_name, ".."))
+				continue;
+
+			/* Do not follow top-level source and build symlinks */
+			if (depth == 0) {
+				if (!strcmp(dent->d_name, "source") ||
+				    !strcmp(dent->d_name, "build"))
+					continue;
+			}
+
+			ret = map_groups__set_modules_path_dir(mg, path,
+							       depth + 1);
+			if (ret < 0)
+				goto out;
+		} else {
+			char *dot = strrchr(dent->d_name, '.'),
+			     dso_name[PATH_MAX];
+			struct map *map;
+			char *long_name;
+
+			if (dot == NULL || strcmp(dot, ".ko"))
+				continue;
+			snprintf(dso_name, sizeof(dso_name), "[%.*s]",
+				 (int)(dot - dent->d_name), dent->d_name);
+
+			strxfrchar(dso_name, '-', '_');
+			map = map_groups__find_by_name(mg, MAP__FUNCTION,
+						       dso_name);
+			if (map == NULL)
+				continue;
+
+			long_name = strdup(path);
+			if (long_name == NULL) {
+				ret = -1;
+				goto out;
+			}
+			dso__set_long_name(map->dso, long_name, true);
+			dso__kernel_module_get_build_id(map->dso, "");
+		}
+	}
+
+out:
+	closedir(dir);
+	return ret;
+}
+
+static int machine__set_modules_path(struct machine *machine)
+{
+	char *version;
+	char modules_path[PATH_MAX];
+
+	version = get_kernel_version(machine->root_dir);
+	if (!version)
+		return -1;
+
+	snprintf(modules_path, sizeof(modules_path), "%s/lib/modules/%s",
+		 machine->root_dir, version);
+	free(version);
+
+	return map_groups__set_modules_path_dir(&machine->kmaps, modules_path, 0);
+}
+
+static int machine__create_module(void *arg, const char *name, u64 start)
+{
+	struct machine *machine = arg;
+	struct map *map;
+
+	map = machine__new_module(machine, start, name);
+	if (map == NULL)
+		return -1;
+
+	dso__kernel_module_get_build_id(map->dso, machine->root_dir);
+
+	return 0;
+}
+
+static int machine__create_modules(struct machine *machine)
+{
+	const char *modules;
+	char path[PATH_MAX];
+
+	if (machine__is_default_guest(machine)) {
+		modules = symbol_conf.default_guest_modules;
+	} else {
+		snprintf(path, PATH_MAX, "%s/proc/modules", machine->root_dir);
+		modules = path;
+	}
+
+	if (symbol__restricted_filename(modules, "/proc/modules"))
+		return -1;
+
+	if (modules__parse(modules, machine, machine__create_module))
+		return -1;
+
+	if (!machine__set_modules_path(machine))
+		return 0;
+
+	pr_debug("Problems setting modules path maps, continuing anyway...\n");
+
+	return 0;
+}
+
+int machine__create_kernel_maps(struct machine *machine)
+{
+	struct dso *kernel = machine__get_kernel(machine);
+	const char *name;
+	u64 addr = machine__get_kernel_start_addr(machine, &name);
+	if (!addr)
+		return -1;
+
+	if (kernel == NULL ||
+	    __machine__create_kernel_maps(machine, kernel) < 0)
+		return -1;
+
+	if (symbol_conf.use_modules && machine__create_modules(machine) < 0) {
+		if (machine__is_host(machine))
+			pr_debug("Problems creating module maps, "
+				 "continuing anyway...\n");
+		else
+			pr_debug("Problems creating module maps for guest %d, "
+				 "continuing anyway...\n", machine->pid);
+	}
+
+	/*
+	 * Now that we have all the maps created, just set the ->end of them:
+	 */
+	map_groups__fixup_end(&machine->kmaps);
+
+	if (maps__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps, name,
+					     addr)) {
+		machine__destroy_kernel_maps(machine);
+		return -1;
+	}
+
+	return 0;
+}
+
+static void machine__set_kernel_mmap_len(struct machine *machine,
+					 union perf_event *event)
+{
+	int i;
+
+	for (i = 0; i < MAP__NR_TYPES; i++) {
+		machine->vmlinux_maps[i]->start = event->mmap.start;
+		machine->vmlinux_maps[i]->end   = (event->mmap.start +
+						   event->mmap.len);
+		/*
+		 * Be a bit paranoid here, some perf.data file came with
+		 * a zero sized synthesized MMAP event for the kernel.
+		 */
+		if (machine->vmlinux_maps[i]->end == 0)
+			machine->vmlinux_maps[i]->end = ~0ULL;
+	}
+}
+
+static bool machine__uses_kcore(struct machine *machine)
+{
+	struct dso *dso;
+
+	list_for_each_entry(dso, &machine->kernel_dsos, node) {
+		if (dso__is_kcore(dso))
+			return true;
+	}
+
+	return false;
+}
+
+static int machine__process_kernel_mmap_event(struct machine *machine,
+					      union perf_event *event)
+{
+	struct map *map;
+	char kmmap_prefix[PATH_MAX];
+	enum dso_kernel_type kernel_type;
+	bool is_kernel_mmap;
+
+	/* If we have maps from kcore then we do not need or want any others */
+	if (machine__uses_kcore(machine))
+		return 0;
+
+	machine__mmap_name(machine, kmmap_prefix, sizeof(kmmap_prefix));
+	if (machine__is_host(machine))
+		kernel_type = DSO_TYPE_KERNEL;
+	else
+		kernel_type = DSO_TYPE_GUEST_KERNEL;
+
+	is_kernel_mmap = memcmp(event->mmap.filename,
+				kmmap_prefix,
+				strlen(kmmap_prefix) - 1) == 0;
+	if (event->mmap.filename[0] == '/' ||
+	    (!is_kernel_mmap && event->mmap.filename[0] == '[')) {
+
+		char short_module_name[1024];
+		char *name, *dot;
+
+		if (event->mmap.filename[0] == '/') {
+			name = strrchr(event->mmap.filename, '/');
+			if (name == NULL)
+				goto out_problem;
+
+			++name; /* skip / */
+			dot = strrchr(name, '.');
+			if (dot == NULL)
+				goto out_problem;
+			snprintf(short_module_name, sizeof(short_module_name),
+					"[%.*s]", (int)(dot - name), name);
+			strxfrchar(short_module_name, '-', '_');
+		} else
+			strcpy(short_module_name, event->mmap.filename);
+
+		map = machine__new_module(machine, event->mmap.start,
+					  event->mmap.filename);
+		if (map == NULL)
+			goto out_problem;
+
+		name = strdup(short_module_name);
+		if (name == NULL)
+			goto out_problem;
+
+		dso__set_short_name(map->dso, name, true);
+		map->end = map->start + event->mmap.len;
+	} else if (is_kernel_mmap) {
+		const char *symbol_name = (event->mmap.filename +
+				strlen(kmmap_prefix));
+		/*
+		 * Should be there already, from the build-id table in
+		 * the header.
+		 */
+		struct dso *kernel = __dsos__findnew(&machine->kernel_dsos,
+						     kmmap_prefix);
+		if (kernel == NULL)
+			goto out_problem;
+
+		kernel->kernel = kernel_type;
+		if (__machine__create_kernel_maps(machine, kernel) < 0)
+			goto out_problem;
+
+		machine__set_kernel_mmap_len(machine, event);
+
+		/*
+		 * Avoid using a zero address (kptr_restrict) for the ref reloc
+		 * symbol. Effectively having zero here means that at record
+		 * time /proc/sys/kernel/kptr_restrict was non zero.
+		 */
+		if (event->mmap.pgoff != 0) {
+			maps__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps,
+							 symbol_name,
+							 event->mmap.pgoff);
+		}
+
+		if (machine__is_default_guest(machine)) {
+			/*
+			 * preload dso of guest kernel and modules
+			 */
+			dso__load(kernel, machine->vmlinux_maps[MAP__FUNCTION],
+				  NULL);
+		}
+	}
+	return 0;
+out_problem:
+	return -1;
+}
+
+int machine__process_mmap2_event(struct machine *machine,
+				 union perf_event *event,
+				 struct perf_sample *sample __maybe_unused)
+{
+	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+	struct thread *thread;
+	struct map *map;
+	enum map_type type;
+	int ret = 0;
+
+	if (dump_trace)
+		perf_event__fprintf_mmap2(event, stdout);
+
+	if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL ||
+	    cpumode == PERF_RECORD_MISC_KERNEL) {
+		ret = machine__process_kernel_mmap_event(machine, event);
+		if (ret < 0)
+			goto out_problem;
+		return 0;
+	}
+
+	thread = machine__findnew_thread(machine, event->mmap2.pid,
+					event->mmap2.tid);
+	if (thread == NULL)
+		goto out_problem;
+
+	if (event->header.misc & PERF_RECORD_MISC_MMAP_DATA)
+		type = MAP__VARIABLE;
+	else
+		type = MAP__FUNCTION;
+
+	map = map__new(&machine->user_dsos, event->mmap2.start,
+			event->mmap2.len, event->mmap2.pgoff,
+			event->mmap2.pid, event->mmap2.maj,
+			event->mmap2.min, event->mmap2.ino,
+			event->mmap2.ino_generation,
+			event->mmap2.prot,
+			event->mmap2.flags,
+			event->mmap2.filename, type);
+
+	if (map == NULL)
+		goto out_problem;
+
+	thread__insert_map(thread, map);
+	return 0;
+
+out_problem:
+	dump_printf("problem processing PERF_RECORD_MMAP2, skipping event.\n");
+	return 0;
+}
+
+int machine__process_mmap_event(struct machine *machine, union perf_event *event,
+				struct perf_sample *sample __maybe_unused)
+{
+	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+	struct thread *thread;
+	struct map *map;
+	enum map_type type;
+	int ret = 0;
+
+	if (dump_trace)
+		perf_event__fprintf_mmap(event, stdout);
+
+	if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL ||
+	    cpumode == PERF_RECORD_MISC_KERNEL) {
+		ret = machine__process_kernel_mmap_event(machine, event);
+		if (ret < 0)
+			goto out_problem;
+		return 0;
+	}
+
+	thread = machine__findnew_thread(machine, event->mmap.pid,
+					 event->mmap.tid);
+	if (thread == NULL)
+		goto out_problem;
+
+	if (event->header.misc & PERF_RECORD_MISC_MMAP_DATA)
+		type = MAP__VARIABLE;
+	else
+		type = MAP__FUNCTION;
+
+	map = map__new(&machine->user_dsos, event->mmap.start,
+			event->mmap.len, event->mmap.pgoff,
+			event->mmap.pid, 0, 0, 0, 0, 0, 0,
+			event->mmap.filename,
+			type);
+
+	if (map == NULL)
+		goto out_problem;
+
+	thread__insert_map(thread, map);
+	return 0;
+
+out_problem:
+	dump_printf("problem processing PERF_RECORD_MMAP, skipping event.\n");
+	return 0;
+}
+
+static void machine__remove_thread(struct machine *machine, struct thread *th)
+{
+	machine->last_match = NULL;
+	rb_erase(&th->rb_node, &machine->threads);
+	/*
+	 * We may have references to this thread, for instance in some hist_entry
+	 * instances, so just move them to a separate list.
+	 */
+	list_add_tail(&th->node, &machine->dead_threads);
+}
+
+int machine__process_fork_event(struct machine *machine, union perf_event *event,
+				struct perf_sample *sample)
+{
+	struct thread *thread = machine__find_thread(machine,
+						     event->fork.pid,
+						     event->fork.tid);
+	struct thread *parent = machine__findnew_thread(machine,
+							event->fork.ppid,
+							event->fork.ptid);
+
+	/* if a thread currently exists for the thread id remove it */
+	if (thread != NULL)
+		machine__remove_thread(machine, thread);
+
+	thread = machine__findnew_thread(machine, event->fork.pid,
+					 event->fork.tid);
+	if (dump_trace)
+		perf_event__fprintf_task(event, stdout);
+
+	if (thread == NULL || parent == NULL ||
+	    thread__fork(thread, parent, sample->time) < 0) {
+		dump_printf("problem processing PERF_RECORD_FORK, skipping event.\n");
+		return -1;
+	}
+
+	return 0;
+}
+
+int machine__process_exit_event(struct machine *machine, union perf_event *event,
+				struct perf_sample *sample __maybe_unused)
+{
+	struct thread *thread = machine__find_thread(machine,
+						     event->fork.pid,
+						     event->fork.tid);
+
+	if (dump_trace)
+		perf_event__fprintf_task(event, stdout);
+
+	if (thread != NULL)
+		thread__exited(thread);
+
+	return 0;
+}
+
+int machine__process_event(struct machine *machine, union perf_event *event,
+			   struct perf_sample *sample)
+{
+	int ret;
+
+	switch (event->header.type) {
+	case PERF_RECORD_COMM:
+		ret = machine__process_comm_event(machine, event, sample); break;
+	case PERF_RECORD_MMAP:
+		ret = machine__process_mmap_event(machine, event, sample); break;
+	case PERF_RECORD_MMAP2:
+		ret = machine__process_mmap2_event(machine, event, sample); break;
+	case PERF_RECORD_FORK:
+		ret = machine__process_fork_event(machine, event, sample); break;
+	case PERF_RECORD_EXIT:
+		ret = machine__process_exit_event(machine, event, sample); break;
+	case PERF_RECORD_LOST:
+		ret = machine__process_lost_event(machine, event, sample); break;
+	default:
+		ret = -1;
+		break;
+	}
+
+	return ret;
+}
+
+static bool symbol__match_regex(struct symbol *sym, regex_t *regex)
+{
+	if (sym->name && !regexec(regex, sym->name, 0, NULL, 0))
+		return 1;
+	return 0;
+}
+
+static void ip__resolve_ams(struct machine *machine, struct thread *thread,
+			    struct addr_map_symbol *ams,
+			    u64 ip)
+{
+	struct addr_location al;
+
+	memset(&al, 0, sizeof(al));
+	/*
+	 * We cannot use the header.misc hint to determine whether a
+	 * branch stack address is user, kernel, guest, hypervisor.
+	 * Branches may straddle the kernel/user/hypervisor boundaries.
+	 * Thus, we have to try consecutively until we find a match
+	 * or else, the symbol is unknown
+	 */
+	thread__find_cpumode_addr_location(thread, machine, MAP__FUNCTION, ip, &al);
+
+	ams->addr = ip;
+	ams->al_addr = al.addr;
+	ams->sym = al.sym;
+	ams->map = al.map;
+}
+
+static void ip__resolve_data(struct machine *machine, struct thread *thread,
+			     u8 m, struct addr_map_symbol *ams, u64 addr)
+{
+	struct addr_location al;
+
+	memset(&al, 0, sizeof(al));
+
+	thread__find_addr_location(thread, machine, m, MAP__VARIABLE, addr,
+				   &al);
+	ams->addr = addr;
+	ams->al_addr = al.addr;
+	ams->sym = al.sym;
+	ams->map = al.map;
+}
+
+struct mem_info *sample__resolve_mem(struct perf_sample *sample,
+				     struct addr_location *al)
+{
+	struct mem_info *mi = zalloc(sizeof(*mi));
+
+	if (!mi)
+		return NULL;
+
+	ip__resolve_ams(al->machine, al->thread, &mi->iaddr, sample->ip);
+	ip__resolve_data(al->machine, al->thread, al->cpumode,
+			 &mi->daddr, sample->addr);
+	mi->data_src.val = sample->data_src;
+
+	return mi;
+}
+
+struct branch_info *sample__resolve_bstack(struct perf_sample *sample,
+					   struct addr_location *al)
+{
+	unsigned int i;
+	const struct branch_stack *bs = sample->branch_stack;
+	struct branch_info *bi = calloc(bs->nr, sizeof(struct branch_info));
+
+	if (!bi)
+		return NULL;
+
+	for (i = 0; i < bs->nr; i++) {
+		ip__resolve_ams(al->machine, al->thread, &bi[i].to, bs->entries[i].to);
+		ip__resolve_ams(al->machine, al->thread, &bi[i].from, bs->entries[i].from);
+		bi[i].flags = bs->entries[i].flags;
+	}
+	return bi;
+}
+
+static int machine__resolve_callchain_sample(struct machine *machine,
+					     struct thread *thread,
+					     struct ip_callchain *chain,
+					     struct symbol **parent,
+					     struct addr_location *root_al,
+					     int max_stack)
+{
+	u8 cpumode = PERF_RECORD_MISC_USER;
+	int chain_nr = min(max_stack, (int)chain->nr);
+	int i;
+	int err;
+
+	callchain_cursor_reset(&callchain_cursor);
+
+	if (chain->nr > PERF_MAX_STACK_DEPTH) {
+		pr_warning("corrupted callchain. skipping...\n");
+		return 0;
+	}
+
+	for (i = 0; i < chain_nr; i++) {
+		u64 ip;
+		struct addr_location al;
+
+		if (callchain_param.order == ORDER_CALLEE)
+			ip = chain->ips[i];
+		else
+			ip = chain->ips[chain->nr - i - 1];
+
+		if (ip >= PERF_CONTEXT_MAX) {
+			switch (ip) {
+			case PERF_CONTEXT_HV:
+				cpumode = PERF_RECORD_MISC_HYPERVISOR;
+				break;
+			case PERF_CONTEXT_KERNEL:
+				cpumode = PERF_RECORD_MISC_KERNEL;
+				break;
+			case PERF_CONTEXT_USER:
+				cpumode = PERF_RECORD_MISC_USER;
+				break;
+			default:
+				pr_debug("invalid callchain context: "
+					 "%"PRId64"\n", (s64) ip);
+				/*
+				 * It seems the callchain is corrupted.
+				 * Discard all.
+				 */
+				callchain_cursor_reset(&callchain_cursor);
+				return 0;
+			}
+			continue;
+		}
+
+		al.filtered = 0;
+		thread__find_addr_location(thread, machine, cpumode,
+					   MAP__FUNCTION, ip, &al);
+		if (al.sym != NULL) {
+			if (sort__has_parent && !*parent &&
+			    symbol__match_regex(al.sym, &parent_regex))
+				*parent = al.sym;
+			else if (have_ignore_callees && root_al &&
+			  symbol__match_regex(al.sym, &ignore_callees_regex)) {
+				/* Treat this symbol as the root,
+				   forgetting its callees. */
+				*root_al = al;
+				callchain_cursor_reset(&callchain_cursor);
+			}
+		}
+
+		err = callchain_cursor_append(&callchain_cursor,
+					      ip, al.map, al.sym);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int unwind_entry(struct unwind_entry *entry, void *arg)
+{
+	struct callchain_cursor *cursor = arg;
+	return callchain_cursor_append(cursor, entry->ip,
+				       entry->map, entry->sym);
+}
+
+int machine__resolve_callchain(struct machine *machine,
+			       struct perf_evsel *evsel,
+			       struct thread *thread,
+			       struct perf_sample *sample,
+			       struct symbol **parent,
+			       struct addr_location *root_al,
+			       int max_stack)
+{
+	int ret;
+
+	ret = machine__resolve_callchain_sample(machine, thread,
+						sample->callchain, parent,
+						root_al, max_stack);
+	if (ret)
+		return ret;
+
+	/* Can we do dwarf post unwind? */
+	if (!((evsel->attr.sample_type & PERF_SAMPLE_REGS_USER) &&
+	      (evsel->attr.sample_type & PERF_SAMPLE_STACK_USER)))
+		return 0;
+
+	/* Bail out if nothing was captured. */
+	if ((!sample->user_regs.regs) ||
+	    (!sample->user_stack.size))
+		return 0;
+
+	return unwind__get_entries(unwind_entry, &callchain_cursor, machine,
+				   thread, sample, max_stack);
+
+}
+
+int machine__for_each_thread(struct machine *machine,
+			     int (*fn)(struct thread *thread, void *p),
+			     void *priv)
+{
+	struct rb_node *nd;
+	struct thread *thread;
+	int rc = 0;
+
+	for (nd = rb_first(&machine->threads); nd; nd = rb_next(nd)) {
+		thread = rb_entry(nd, struct thread, rb_node);
+		rc = fn(thread, priv);
+		if (rc != 0)
+			return rc;
+	}
+
+	list_for_each_entry(thread, &machine->dead_threads, node) {
+		rc = fn(thread, priv);
+		if (rc != 0)
+			return rc;
+	}
+	return rc;
+}
+
+int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool,
+				  struct target *target, struct thread_map *threads,
+				  perf_event__handler_t process, bool data_mmap)
+{
+	if (target__has_task(target))
+		return perf_event__synthesize_thread_map(tool, threads, process, machine, data_mmap);
+	else if (target__has_cpu(target))
+		return perf_event__synthesize_threads(tool, process, machine, data_mmap);
+	/* command specified */
+	return 0;
+}
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
new file mode 100644
index 00000000000..c8c74a11939
--- /dev/null
+++ b/tools/perf/util/machine.h
@@ -0,0 +1,194 @@
+#ifndef __PERF_MACHINE_H
+#define __PERF_MACHINE_H
+
+#include <sys/types.h>
+#include <linux/rbtree.h>
+#include "map.h"
+#include "event.h"
+
+struct addr_location;
+struct branch_stack;
+struct perf_evsel;
+struct perf_sample;
+struct symbol;
+struct thread;
+union perf_event;
+
+/* Native host kernel uses -1 as pid index in machine */
+#define	HOST_KERNEL_ID			(-1)
+#define	DEFAULT_GUEST_KERNEL_ID		(0)
+
+extern const char *ref_reloc_sym_names[];
+
+struct machine {
+	struct rb_node	  rb_node;
+	pid_t		  pid;
+	u16		  id_hdr_size;
+	char		  *root_dir;
+	struct rb_root	  threads;
+	struct list_head  dead_threads;
+	struct thread	  *last_match;
+	struct list_head  user_dsos;
+	struct list_head  kernel_dsos;
+	struct map_groups kmaps;
+	struct map	  *vmlinux_maps[MAP__NR_TYPES];
+	symbol_filter_t	  symbol_filter;
+};
+
+static inline
+struct map *machine__kernel_map(struct machine *machine, enum map_type type)
+{
+	return machine->vmlinux_maps[type];
+}
+
+struct thread *machine__find_thread(struct machine *machine, pid_t pid,
+				    pid_t tid);
+
+int machine__process_comm_event(struct machine *machine, union perf_event *event,
+				struct perf_sample *sample);
+int machine__process_exit_event(struct machine *machine, union perf_event *event,
+				struct perf_sample *sample);
+int machine__process_fork_event(struct machine *machine, union perf_event *event,
+				struct perf_sample *sample);
+int machine__process_lost_event(struct machine *machine, union perf_event *event,
+				struct perf_sample *sample);
+int machine__process_mmap_event(struct machine *machine, union perf_event *event,
+				struct perf_sample *sample);
+int machine__process_mmap2_event(struct machine *machine, union perf_event *event,
+				 struct perf_sample *sample);
+int machine__process_event(struct machine *machine, union perf_event *event,
+				struct perf_sample *sample);
+
+typedef void (*machine__process_t)(struct machine *machine, void *data);
+
+struct machines {
+	struct machine host;
+	struct rb_root guests;
+	symbol_filter_t symbol_filter;
+};
+
+void machines__init(struct machines *machines);
+void machines__exit(struct machines *machines);
+
+void machines__process_guests(struct machines *machines,
+			      machine__process_t process, void *data);
+
+struct machine *machines__add(struct machines *machines, pid_t pid,
+			      const char *root_dir);
+struct machine *machines__find_host(struct machines *machines);
+struct machine *machines__find(struct machines *machines, pid_t pid);
+struct machine *machines__findnew(struct machines *machines, pid_t pid);
+
+void machines__set_id_hdr_size(struct machines *machines, u16 id_hdr_size);
+char *machine__mmap_name(struct machine *machine, char *bf, size_t size);
+
+void machines__set_symbol_filter(struct machines *machines,
+				 symbol_filter_t symbol_filter);
+
+struct machine *machine__new_host(void);
+int machine__init(struct machine *machine, const char *root_dir, pid_t pid);
+void machine__exit(struct machine *machine);
+void machine__delete_dead_threads(struct machine *machine);
+void machine__delete_threads(struct machine *machine);
+void machine__delete(struct machine *machine);
+
+struct branch_info *sample__resolve_bstack(struct perf_sample *sample,
+					   struct addr_location *al);
+struct mem_info *sample__resolve_mem(struct perf_sample *sample,
+				     struct addr_location *al);
+int machine__resolve_callchain(struct machine *machine,
+			       struct perf_evsel *evsel,
+			       struct thread *thread,
+			       struct perf_sample *sample,
+			       struct symbol **parent,
+			       struct addr_location *root_al,
+			       int max_stack);
+
+/*
+ * Default guest kernel is defined by parameter --guestkallsyms
+ * and --guestmodules
+ */
+static inline bool machine__is_default_guest(struct machine *machine)
+{
+	return machine ? machine->pid == DEFAULT_GUEST_KERNEL_ID : false;
+}
+
+static inline bool machine__is_host(struct machine *machine)
+{
+	return machine ? machine->pid == HOST_KERNEL_ID : false;
+}
+
+struct thread *machine__findnew_thread(struct machine *machine, pid_t pid,
+				       pid_t tid);
+
+size_t machine__fprintf(struct machine *machine, FILE *fp);
+
+static inline
+struct symbol *machine__find_kernel_symbol(struct machine *machine,
+					   enum map_type type, u64 addr,
+					   struct map **mapp,
+					   symbol_filter_t filter)
+{
+	return map_groups__find_symbol(&machine->kmaps, type, addr,
+				       mapp, filter);
+}
+
+static inline
+struct symbol *machine__find_kernel_function(struct machine *machine, u64 addr,
+					     struct map **mapp,
+					     symbol_filter_t filter)
+{
+	return machine__find_kernel_symbol(machine, MAP__FUNCTION, addr,
+					   mapp, filter);
+}
+
+static inline
+struct symbol *machine__find_kernel_function_by_name(struct machine *machine,
+						     const char *name,
+						     struct map **mapp,
+						     symbol_filter_t filter)
+{
+	return map_groups__find_function_by_name(&machine->kmaps, name, mapp,
+						 filter);
+}
+
+struct map *machine__new_module(struct machine *machine, u64 start,
+				const char *filename);
+
+int machine__load_kallsyms(struct machine *machine, const char *filename,
+			   enum map_type type, symbol_filter_t filter);
+int machine__load_vmlinux_path(struct machine *machine, enum map_type type,
+			       symbol_filter_t filter);
+
+size_t machine__fprintf_dsos_buildid(struct machine *machine, FILE *fp,
+				     bool (skip)(struct dso *dso, int parm), int parm);
+size_t machines__fprintf_dsos(struct machines *machines, FILE *fp);
+size_t machines__fprintf_dsos_buildid(struct machines *machines, FILE *fp,
+				     bool (skip)(struct dso *dso, int parm), int parm);
+
+void machine__destroy_kernel_maps(struct machine *machine);
+int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel);
+int machine__create_kernel_maps(struct machine *machine);
+
+int machines__create_kernel_maps(struct machines *machines, pid_t pid);
+int machines__create_guest_kernel_maps(struct machines *machines);
+void machines__destroy_kernel_maps(struct machines *machines);
+
+size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp);
+
+int machine__for_each_thread(struct machine *machine,
+			     int (*fn)(struct thread *thread, void *p),
+			     void *priv);
+
+int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool,
+				  struct target *target, struct thread_map *threads,
+				  perf_event__handler_t process, bool data_mmap);
+static inline
+int machine__synthesize_threads(struct machine *machine, struct target *target,
+				struct thread_map *threads, bool data_mmap)
+{
+	return __machine__synthesize_threads(machine, NULL, target, threads,
+					     perf_event__process, data_mmap);
+}
+
+#endif /* __PERF_MACHINE_H */
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index e672f2fef65..25c571f4cba 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -1,11 +1,18 @@
 #include "symbol.h"
 #include <errno.h>
+#include <inttypes.h>
 #include <limits.h>
 #include <stdlib.h>
 #include <string.h>
 #include <stdio.h>
 #include <unistd.h>
 #include "map.h"
+#include "thread.h"
+#include "strlist.h"
+#include "vdso.h"
+#include "build-id.h"
+#include "util.h"
+#include <linux/string.h>
 
 const char *map_type__name[MAP__NR_TYPES] = {
 	[MAP__FUNCTION] = "Functions",
@@ -14,123 +21,245 @@ const char *map_type__name[MAP__NR_TYPES] = {
 
 static inline int is_anon_memory(const char *filename)
 {
-	return strcmp(filename, "//anon") == 0;
+	return !strcmp(filename, "//anon") ||
+	       !strcmp(filename, "/dev/zero (deleted)") ||
+	       !strcmp(filename, "/anon_hugepage (deleted)");
 }
 
-static int strcommon(const char *pathname, char *cwd, int cwdlen)
+static inline int is_no_dso_memory(const char *filename)
 {
-	int n = 0;
+	return !strncmp(filename, "[stack", 6) ||
+	       !strcmp(filename, "[heap]");
+}
+
+static inline int is_android_lib(const char *filename)
+{
+	return !strncmp(filename, "/data/app-lib", 13) ||
+	       !strncmp(filename, "/system/lib", 11);
+}
+
+static inline bool replace_android_lib(const char *filename, char *newfilename)
+{
+	const char *libname;
+	char *app_abi;
+	size_t app_abi_length, new_length;
+	size_t lib_length = 0;
+
+	libname  = strrchr(filename, '/');
+	if (libname)
+		lib_length = strlen(libname);
+
+	app_abi = getenv("APP_ABI");
+	if (!app_abi)
+		return false;
+
+	app_abi_length = strlen(app_abi);
+
+	if (!strncmp(filename, "/data/app-lib", 13)) {
+		char *apk_path;
+
+		if (!app_abi_length)
+			return false;
+
+		new_length = 7 + app_abi_length + lib_length;
+
+		apk_path = getenv("APK_PATH");
+		if (apk_path) {
+			new_length += strlen(apk_path) + 1;
+			if (new_length > PATH_MAX)
+				return false;
+			snprintf(newfilename, new_length,
+				 "%s/libs/%s/%s", apk_path, app_abi, libname);
+		} else {
+			if (new_length > PATH_MAX)
+				return false;
+			snprintf(newfilename, new_length,
+				 "libs/%s/%s", app_abi, libname);
+		}
+		return true;
+	}
+
+	if (!strncmp(filename, "/system/lib/", 11)) {
+		char *ndk, *app;
+		const char *arch;
+		size_t ndk_length;
+		size_t app_length;
+
+		ndk = getenv("NDK_ROOT");
+		app = getenv("APP_PLATFORM");
+
+		if (!(ndk && app))
+			return false;
+
+		ndk_length = strlen(ndk);
+		app_length = strlen(app);
+
+		if (!(ndk_length && app_length && app_abi_length))
+			return false;
+
+		arch = !strncmp(app_abi, "arm", 3) ? "arm" :
+		       !strncmp(app_abi, "mips", 4) ? "mips" :
+		       !strncmp(app_abi, "x86", 3) ? "x86" : NULL;
+
+		if (!arch)
+			return false;
 
-	while (n < cwdlen && pathname[n] == cwd[n])
-		++n;
+		new_length = 27 + ndk_length +
+			     app_length + lib_length
+			   + strlen(arch);
 
-	return n;
+		if (new_length > PATH_MAX)
+			return false;
+		snprintf(newfilename, new_length,
+			"%s/platforms/%s/arch-%s/usr/lib/%s",
+			ndk, app, arch, libname);
+
+		return true;
+	}
+	return false;
 }
 
-void map__init(struct map *self, enum map_type type,
+void map__init(struct map *map, enum map_type type,
 	       u64 start, u64 end, u64 pgoff, struct dso *dso)
 {
-	self->type     = type;
-	self->start    = start;
-	self->end      = end;
-	self->pgoff    = pgoff;
-	self->dso      = dso;
-	self->map_ip   = map__map_ip;
-	self->unmap_ip = map__unmap_ip;
-	RB_CLEAR_NODE(&self->rb_node);
-	self->groups   = NULL;
+	map->type     = type;
+	map->start    = start;
+	map->end      = end;
+	map->pgoff    = pgoff;
+	map->reloc    = 0;
+	map->dso      = dso;
+	map->map_ip   = map__map_ip;
+	map->unmap_ip = map__unmap_ip;
+	RB_CLEAR_NODE(&map->rb_node);
+	map->groups   = NULL;
+	map->referenced = false;
+	map->erange_warned = false;
 }
 
 struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
-		     u64 pgoff, u32 pid, char *filename,
-		     enum map_type type, char *cwd, int cwdlen)
+		     u64 pgoff, u32 pid, u32 d_maj, u32 d_min, u64 ino,
+		     u64 ino_gen, u32 prot, u32 flags, char *filename,
+		     enum map_type type)
 {
-	struct map *self = malloc(sizeof(*self));
+	struct map *map = malloc(sizeof(*map));
 
-	if (self != NULL) {
+	if (map != NULL) {
 		char newfilename[PATH_MAX];
 		struct dso *dso;
-		int anon;
-
-		if (cwd) {
-			int n = strcommon(filename, cwd, cwdlen);
-
-			if (n == cwdlen) {
-				snprintf(newfilename, sizeof(newfilename),
-					 ".%s", filename + n);
-				filename = newfilename;
-			}
-		}
+		int anon, no_dso, vdso, android;
 
+		android = is_android_lib(filename);
 		anon = is_anon_memory(filename);
+		vdso = is_vdso_map(filename);
+		no_dso = is_no_dso_memory(filename);
+
+		map->maj = d_maj;
+		map->min = d_min;
+		map->ino = ino;
+		map->ino_generation = ino_gen;
+		map->prot = prot;
+		map->flags = flags;
 
-		if (anon) {
+		if ((anon || no_dso) && type == MAP__FUNCTION) {
 			snprintf(newfilename, sizeof(newfilename), "/tmp/perf-%d.map", pid);
 			filename = newfilename;
 		}
 
-		dso = __dsos__findnew(dsos__list, filename);
+		if (android) {
+			if (replace_android_lib(filename, newfilename))
+				filename = newfilename;
+		}
+
+		if (vdso) {
+			pgoff = 0;
+			dso = vdso__dso_findnew(dsos__list);
+		} else
+			dso = __dsos__findnew(dsos__list, filename);
+
 		if (dso == NULL)
 			goto out_delete;
 
-		map__init(self, type, start, start + len, pgoff, dso);
+		map__init(map, type, start, start + len, pgoff, dso);
+
+		if (anon || no_dso) {
+			map->map_ip = map->unmap_ip = identity__map_ip;
 
-		if (anon) {
-set_identity:
-			self->map_ip = self->unmap_ip = identity__map_ip;
-		} else if (strcmp(filename, "[vdso]") == 0) {
-			dso__set_loaded(dso, self->type);
-			goto set_identity;
+			/*
+			 * Set memory without DSO as loaded. All map__find_*
+			 * functions still return NULL, and we avoid the
+			 * unnecessary map__load warning.
+			 */
+			if (type != MAP__FUNCTION)
+				dso__set_loaded(dso, map->type);
 		}
 	}
-	return self;
+	return map;
 out_delete:
-	free(self);
+	free(map);
 	return NULL;
 }
 
-void map__delete(struct map *self)
+/*
+ * Constructor variant for modules (where we know from /proc/modules where
+ * they are loaded) and for vmlinux, where only after we load all the
+ * symbols we'll know where it starts and ends.
+ */
+struct map *map__new2(u64 start, struct dso *dso, enum map_type type)
+{
+	struct map *map = calloc(1, (sizeof(*map) +
+				     (dso->kernel ? sizeof(struct kmap) : 0)));
+	if (map != NULL) {
+		/*
+		 * ->end will be filled after we load all the symbols
+		 */
+		map__init(map, type, start, 0, 0, dso);
+	}
+
+	return map;
+}
+
+void map__delete(struct map *map)
 {
-	free(self);
+	free(map);
 }
 
-void map__fixup_start(struct map *self)
+void map__fixup_start(struct map *map)
 {
-	struct rb_root *symbols = &self->dso->symbols[self->type];
+	struct rb_root *symbols = &map->dso->symbols[map->type];
 	struct rb_node *nd = rb_first(symbols);
 	if (nd != NULL) {
 		struct symbol *sym = rb_entry(nd, struct symbol, rb_node);
-		self->start = sym->start;
+		map->start = sym->start;
 	}
 }
 
-void map__fixup_end(struct map *self)
+void map__fixup_end(struct map *map)
 {
-	struct rb_root *symbols = &self->dso->symbols[self->type];
+	struct rb_root *symbols = &map->dso->symbols[map->type];
 	struct rb_node *nd = rb_last(symbols);
 	if (nd != NULL) {
 		struct symbol *sym = rb_entry(nd, struct symbol, rb_node);
-		self->end = sym->end;
+		map->end = sym->end;
 	}
 }
 
 #define DSO__DELETED "(deleted)"
 
-int map__load(struct map *self, symbol_filter_t filter)
+int map__load(struct map *map, symbol_filter_t filter)
 {
-	const char *name = self->dso->long_name;
+	const char *name = map->dso->long_name;
 	int nr;
 
-	if (dso__loaded(self->dso, self->type))
+	if (dso__loaded(map->dso, map->type))
 		return 0;
 
-	nr = dso__load(self->dso, self, filter);
+	nr = dso__load(map->dso, map, filter);
 	if (nr < 0) {
-		if (self->dso->has_build_id) {
+		if (map->dso->has_build_id) {
 			char sbuild_id[BUILD_ID_SIZE * 2 + 1];
 
-			build_id__sprintf(self->dso->build_id,
-					  sizeof(self->dso->build_id),
+			build_id__sprintf(map->dso->build_id,
+					  sizeof(map->dso->build_id),
 					  sbuild_id);
 			pr_warning("%s with build id %s not found",
 				   name, sbuild_id);
@@ -140,62 +269,50 @@ int map__load(struct map *self, symbol_filter_t filter)
 		pr_warning(", continuing without symbols\n");
 		return -1;
 	} else if (nr == 0) {
+#ifdef HAVE_LIBELF_SUPPORT
 		const size_t len = strlen(name);
 		const size_t real_len = len - sizeof(DSO__DELETED);
 
 		if (len > sizeof(DSO__DELETED) &&
 		    strcmp(name + real_len + 1, DSO__DELETED) == 0) {
-			pr_warning("%.*s was updated, restart the long "
-				   "running apps that use it!\n",
+			pr_warning("%.*s was updated (is prelink enabled?). "
+				"Restart the long running apps that use it!\n",
 				   (int)real_len, name);
 		} else {
 			pr_warning("no symbols found in %s, maybe install "
 				   "a debug package?\n", name);
 		}
-
+#endif
 		return -1;
 	}
-	/*
-	 * Only applies to the kernel, as its symtabs aren't relative like the
-	 * module ones.
-	 */
-	if (self->dso->kernel)
-		map__reloc_vmlinux(self);
 
 	return 0;
 }
 
-struct symbol *map__find_symbol(struct map *self, u64 addr,
+struct symbol *map__find_symbol(struct map *map, u64 addr,
 				symbol_filter_t filter)
 {
-	if (map__load(self, filter) < 0)
+	if (map__load(map, filter) < 0)
 		return NULL;
 
-	return dso__find_symbol(self->dso, self->type, addr);
+	return dso__find_symbol(map->dso, map->type, addr);
 }
 
-struct symbol *map__find_symbol_by_name(struct map *self, const char *name,
+struct symbol *map__find_symbol_by_name(struct map *map, const char *name,
 					symbol_filter_t filter)
 {
-	if (map__load(self, filter) < 0)
+	if (map__load(map, filter) < 0)
 		return NULL;
 
-	if (!dso__sorted_by_name(self->dso, self->type))
-		dso__sort_by_name(self->dso, self->type);
+	if (!dso__sorted_by_name(map->dso, map->type))
+		dso__sort_by_name(map->dso, map->type);
 
-	return dso__find_symbol_by_name(self->dso, self->type, name);
+	return dso__find_symbol_by_name(map->dso, map->type, name);
 }
 
-struct map *map__clone(struct map *self)
+struct map *map__clone(struct map *map)
 {
-	struct map *map = malloc(sizeof(*self));
-
-	if (!map)
-		return NULL;
-
-	memcpy(map, self, sizeof(*self));
-
-	return map;
+	return memdup(map, sizeof(*map));
 }
 
 int map__overlap(struct map *l, struct map *r)
@@ -212,48 +329,159 @@ int map__overlap(struct map *l, struct map *r)
 	return 0;
 }
 
-size_t map__fprintf(struct map *self, FILE *fp)
+size_t map__fprintf(struct map *map, FILE *fp)
 {
-	return fprintf(fp, " %Lx-%Lx %Lx %s\n",
-		       self->start, self->end, self->pgoff, self->dso->name);
+	return fprintf(fp, " %" PRIx64 "-%" PRIx64 " %" PRIx64 " %s\n",
+		       map->start, map->end, map->pgoff, map->dso->name);
 }
 
-/*
+size_t map__fprintf_dsoname(struct map *map, FILE *fp)
+{
+	const char *dsoname = "[unknown]";
+
+	if (map && map->dso && (map->dso->name || map->dso->long_name)) {
+		if (symbol_conf.show_kernel_path && map->dso->long_name)
+			dsoname = map->dso->long_name;
+		else if (map->dso->name)
+			dsoname = map->dso->name;
+	}
+
+	return fprintf(fp, "%s", dsoname);
+}
+
+int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix,
+			 FILE *fp)
+{
+	char *srcline;
+	int ret = 0;
+
+	if (map && map->dso) {
+		srcline = get_srcline(map->dso,
+				      map__rip_2objdump(map, addr));
+		if (srcline != SRCLINE_UNKNOWN)
+			ret = fprintf(fp, "%s%s", prefix, srcline);
+		free_srcline(srcline);
+	}
+	return ret;
+}
+
+/**
+ * map__rip_2objdump - convert symbol start address to objdump address.
+ * @map: memory map
+ * @rip: symbol start address
+ *
  * objdump wants/reports absolute IPs for ET_EXEC, and RIPs for ET_DYN.
- * map->dso->adjust_symbols==1 for ET_EXEC-like cases.
+ * map->dso->adjust_symbols==1 for ET_EXEC-like cases except ET_REL which is
+ * relative to section start.
+ *
+ * Return: Address suitable for passing to "objdump --start-address="
  */
 u64 map__rip_2objdump(struct map *map, u64 rip)
 {
-	u64 addr = map->dso->adjust_symbols ?
-			map->unmap_ip(map, rip) :	/* RIP -> IP */
-			rip;
-	return addr;
+	if (!map->dso->adjust_symbols)
+		return rip;
+
+	if (map->dso->rel)
+		return rip - map->pgoff;
+
+	return map->unmap_ip(map, rip) - map->reloc;
+}
+
+/**
+ * map__objdump_2mem - convert objdump address to a memory address.
+ * @map: memory map
+ * @ip: objdump address
+ *
+ * Closely related to map__rip_2objdump(), this function takes an address from
+ * objdump and converts it to a memory address.  Note this assumes that @map
+ * contains the address.  To be sure the result is valid, check it forwards
+ * e.g. map__rip_2objdump(map->map_ip(map, map__objdump_2mem(map, ip))) == ip
+ *
+ * Return: Memory address.
+ */
+u64 map__objdump_2mem(struct map *map, u64 ip)
+{
+	if (!map->dso->adjust_symbols)
+		return map->unmap_ip(map, ip);
+
+	if (map->dso->rel)
+		return map->unmap_ip(map, ip + map->pgoff);
+
+	return ip + map->reloc;
+}
+
+void map_groups__init(struct map_groups *mg)
+{
+	int i;
+	for (i = 0; i < MAP__NR_TYPES; ++i) {
+		mg->maps[i] = RB_ROOT;
+		INIT_LIST_HEAD(&mg->removed_maps[i]);
+	}
+	mg->machine = NULL;
+	mg->refcnt = 1;
+}
+
+static void maps__delete(struct rb_root *maps)
+{
+	struct rb_node *next = rb_first(maps);
+
+	while (next) {
+		struct map *pos = rb_entry(next, struct map, rb_node);
+
+		next = rb_next(&pos->rb_node);
+		rb_erase(&pos->rb_node, maps);
+		map__delete(pos);
+	}
 }
 
-u64 map__objdump_2ip(struct map *map, u64 addr)
+static void maps__delete_removed(struct list_head *maps)
 {
-	u64 ip = map->dso->adjust_symbols ?
-			addr :
-			map->unmap_ip(map, addr);	/* RIP -> IP */
-	return ip;
+	struct map *pos, *n;
+
+	list_for_each_entry_safe(pos, n, maps, node) {
+		list_del(&pos->node);
+		map__delete(pos);
+	}
 }
 
-void map_groups__init(struct map_groups *self)
+void map_groups__exit(struct map_groups *mg)
 {
 	int i;
+
 	for (i = 0; i < MAP__NR_TYPES; ++i) {
-		self->maps[i] = RB_ROOT;
-		INIT_LIST_HEAD(&self->removed_maps[i]);
+		maps__delete(&mg->maps[i]);
+		maps__delete_removed(&mg->removed_maps[i]);
 	}
-	self->machine = NULL;
 }
 
-void map_groups__flush(struct map_groups *self)
+struct map_groups *map_groups__new(void)
+{
+	struct map_groups *mg = malloc(sizeof(*mg));
+
+	if (mg != NULL)
+		map_groups__init(mg);
+
+	return mg;
+}
+
+void map_groups__delete(struct map_groups *mg)
+{
+	map_groups__exit(mg);
+	free(mg);
+}
+
+void map_groups__put(struct map_groups *mg)
+{
+	if (--mg->refcnt == 0)
+		map_groups__delete(mg);
+}
+
+void map_groups__flush(struct map_groups *mg)
 {
 	int type;
 
 	for (type = 0; type < MAP__NR_TYPES; type++) {
-		struct rb_root *root = &self->maps[type];
+		struct rb_root *root = &mg->maps[type];
 		struct rb_node *next = rb_first(root);
 
 		while (next) {
@@ -265,19 +493,20 @@ void map_groups__flush(struct map_groups *self)
 			 * instance in some hist_entry instances, so
 			 * just move them to a separate list.
 			 */
-			list_add_tail(&pos->node, &self->removed_maps[pos->type]);
+			list_add_tail(&pos->node, &mg->removed_maps[pos->type]);
 		}
 	}
 }
 
-struct symbol *map_groups__find_symbol(struct map_groups *self,
+struct symbol *map_groups__find_symbol(struct map_groups *mg,
 				       enum map_type type, u64 addr,
 				       struct map **mapp,
 				       symbol_filter_t filter)
 {
-	struct map *map = map_groups__find(self, type, addr);
+	struct map *map = map_groups__find(mg, type, addr);
 
-	if (map != NULL) {
+	/* Ensure map is loaded before using map->map_ip */
+	if (map != NULL && map__load(map, filter) >= 0) {
 		if (mapp != NULL)
 			*mapp = map;
 		return map__find_symbol(map, map->map_ip(map, addr), filter);
@@ -286,7 +515,7 @@ struct symbol *map_groups__find_symbol(struct map_groups *self,
 	return NULL;
 }
 
-struct symbol *map_groups__find_symbol_by_name(struct map_groups *self,
+struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg,
 					       enum map_type type,
 					       const char *name,
 					       struct map **mapp,
@@ -294,7 +523,7 @@ struct symbol *map_groups__find_symbol_by_name(struct map_groups *self,
 {
 	struct rb_node *nd;
 
-	for (nd = rb_first(&self->maps[type]); nd; nd = rb_next(nd)) {
+	for (nd = rb_first(&mg->maps[type]); nd; nd = rb_next(nd)) {
 		struct map *pos = rb_entry(nd, struct map, rb_node);
 		struct symbol *sym = map__find_symbol_by_name(pos, name, filter);
 
@@ -308,13 +537,30 @@ struct symbol *map_groups__find_symbol_by_name(struct map_groups *self,
 	return NULL;
 }
 
-size_t __map_groups__fprintf_maps(struct map_groups *self,
+int map_groups__find_ams(struct addr_map_symbol *ams, symbol_filter_t filter)
+{
+	if (ams->addr < ams->map->start || ams->addr > ams->map->end) {
+		if (ams->map->groups == NULL)
+			return -1;
+		ams->map = map_groups__find(ams->map->groups, ams->map->type,
+					    ams->addr);
+		if (ams->map == NULL)
+			return -1;
+	}
+
+	ams->al_addr = ams->map->map_ip(ams->map, ams->addr);
+	ams->sym = map__find_symbol(ams->map, ams->al_addr, filter);
+
+	return ams->sym ? 0 : -1;
+}
+
+size_t __map_groups__fprintf_maps(struct map_groups *mg,
 				  enum map_type type, int verbose, FILE *fp)
 {
 	size_t printed = fprintf(fp, "%s:\n", map_type__name[type]);
 	struct rb_node *nd;
 
-	for (nd = rb_first(&self->maps[type]); nd; nd = rb_next(nd)) {
+	for (nd = rb_first(&mg->maps[type]); nd; nd = rb_next(nd)) {
 		struct map *pos = rb_entry(nd, struct map, rb_node);
 		printed += fprintf(fp, "Map:");
 		printed += map__fprintf(pos, fp);
@@ -327,22 +573,22 @@ size_t __map_groups__fprintf_maps(struct map_groups *self,
 	return printed;
 }
 
-size_t map_groups__fprintf_maps(struct map_groups *self, int verbose, FILE *fp)
+size_t map_groups__fprintf_maps(struct map_groups *mg, int verbose, FILE *fp)
 {
 	size_t printed = 0, i;
 	for (i = 0; i < MAP__NR_TYPES; ++i)
-		printed += __map_groups__fprintf_maps(self, i, verbose, fp);
+		printed += __map_groups__fprintf_maps(mg, i, verbose, fp);
 	return printed;
 }
 
-static size_t __map_groups__fprintf_removed_maps(struct map_groups *self,
+static size_t __map_groups__fprintf_removed_maps(struct map_groups *mg,
 						 enum map_type type,
 						 int verbose, FILE *fp)
 {
 	struct map *pos;
 	size_t printed = 0;
 
-	list_for_each_entry(pos, &self->removed_maps[type], node) {
+	list_for_each_entry(pos, &mg->removed_maps[type], node) {
 		printed += fprintf(fp, "Map:");
 		printed += map__fprintf(pos, fp);
 		if (verbose > 1) {
@@ -353,27 +599,28 @@ static size_t __map_groups__fprintf_removed_maps(struct map_groups *self,
 	return printed;
 }
 
-static size_t map_groups__fprintf_removed_maps(struct map_groups *self,
+static size_t map_groups__fprintf_removed_maps(struct map_groups *mg,
 					       int verbose, FILE *fp)
 {
 	size_t printed = 0, i;
 	for (i = 0; i < MAP__NR_TYPES; ++i)
-		printed += __map_groups__fprintf_removed_maps(self, i, verbose, fp);
+		printed += __map_groups__fprintf_removed_maps(mg, i, verbose, fp);
 	return printed;
 }
 
-size_t map_groups__fprintf(struct map_groups *self, int verbose, FILE *fp)
+size_t map_groups__fprintf(struct map_groups *mg, int verbose, FILE *fp)
 {
-	size_t printed = map_groups__fprintf_maps(self, verbose, fp);
+	size_t printed = map_groups__fprintf_maps(mg, verbose, fp);
 	printed += fprintf(fp, "Removed maps:\n");
-	return printed + map_groups__fprintf_removed_maps(self, verbose, fp);
+	return printed + map_groups__fprintf_removed_maps(mg, verbose, fp);
 }
 
-int map_groups__fixup_overlappings(struct map_groups *self, struct map *map,
+int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
 				   int verbose, FILE *fp)
 {
-	struct rb_root *root = &self->maps[map->type];
+	struct rb_root *root = &mg->maps[map->type];
 	struct rb_node *next = rb_first(root);
+	int err = 0;
 
 	while (next) {
 		struct map *pos = rb_entry(next, struct map, rb_node);
@@ -390,23 +637,19 @@ int map_groups__fixup_overlappings(struct map_groups *self, struct map *map,
 
 		rb_erase(&pos->rb_node, root);
 		/*
-		 * We may have references to this map, for instance in some
-		 * hist_entry instances, so just move them to a separate
-		 * list.
-		 */
-		list_add_tail(&pos->node, &self->removed_maps[map->type]);
-		/*
 		 * Now check if we need to create new maps for areas not
 		 * overlapped by the new map:
 		 */
 		if (map->start > pos->start) {
 			struct map *before = map__clone(pos);
 
-			if (before == NULL)
-				return -ENOMEM;
+			if (before == NULL) {
+				err = -ENOMEM;
+				goto move_map;
+			}
 
 			before->end = map->start - 1;
-			map_groups__insert(self, before);
+			map_groups__insert(mg, before);
 			if (verbose >= 2)
 				map__fprintf(before, fp);
 		}
@@ -414,14 +657,27 @@ int map_groups__fixup_overlappings(struct map_groups *self, struct map *map,
 		if (map->end < pos->end) {
 			struct map *after = map__clone(pos);
 
-			if (after == NULL)
-				return -ENOMEM;
+			if (after == NULL) {
+				err = -ENOMEM;
+				goto move_map;
+			}
 
 			after->start = map->end + 1;
-			map_groups__insert(self, after);
+			map_groups__insert(mg, after);
 			if (verbose >= 2)
 				map__fprintf(after, fp);
 		}
+move_map:
+		/*
+		 * If we have references, just move them to a separate list.
+		 */
+		if (pos->referenced)
+			list_add_tail(&pos->node, &mg->removed_maps[map->type]);
+		else
+			map__delete(pos);
+
+		if (err)
+			return err;
 	}
 
 	return 0;
@@ -430,7 +686,7 @@ int map_groups__fixup_overlappings(struct map_groups *self, struct map *map,
 /*
  * XXX This should not really _copy_ te maps, but refcount them.
  */
-int map_groups__clone(struct map_groups *self,
+int map_groups__clone(struct map_groups *mg,
 		      struct map_groups *parent, enum map_type type)
 {
 	struct rb_node *nd;
@@ -439,40 +695,11 @@ int map_groups__clone(struct map_groups *self,
 		struct map *new = map__clone(map);
 		if (new == NULL)
 			return -ENOMEM;
-		map_groups__insert(self, new);
+		map_groups__insert(mg, new);
 	}
 	return 0;
 }
 
-static u64 map__reloc_map_ip(struct map *map, u64 ip)
-{
-	return ip + (s64)map->pgoff;
-}
-
-static u64 map__reloc_unmap_ip(struct map *map, u64 ip)
-{
-	return ip - (s64)map->pgoff;
-}
-
-void map__reloc_vmlinux(struct map *self)
-{
-	struct kmap *kmap = map__kmap(self);
-	s64 reloc;
-
-	if (!kmap->ref_reloc_sym || !kmap->ref_reloc_sym->unrelocated_addr)
-		return;
-
-	reloc = (kmap->ref_reloc_sym->unrelocated_addr -
-		 kmap->ref_reloc_sym->addr);
-
-	if (!reloc)
-		return;
-
-	self->map_ip   = map__reloc_map_ip;
-	self->unmap_ip = map__reloc_unmap_ip;
-	self->pgoff    = reloc;
-}
-
 void maps__insert(struct rb_root *maps, struct map *map)
 {
 	struct rb_node **p = &maps->rb_node;
@@ -493,6 +720,11 @@ void maps__insert(struct rb_root *maps, struct map *map)
 	rb_insert_color(&map->rb_node, maps);
 }
 
+void maps__remove(struct rb_root *maps, struct map *map)
+{
+	rb_erase(&map->rb_node, maps);
+}
+
 struct map *maps__find(struct rb_root *maps, u64 ip)
 {
 	struct rb_node **p = &maps->rb_node;
@@ -513,116 +745,20 @@ struct map *maps__find(struct rb_root *maps, u64 ip)
 	return NULL;
 }
 
-int machine__init(struct machine *self, const char *root_dir, pid_t pid)
+struct map *maps__first(struct rb_root *maps)
 {
-	map_groups__init(&self->kmaps);
-	RB_CLEAR_NODE(&self->rb_node);
-	INIT_LIST_HEAD(&self->user_dsos);
-	INIT_LIST_HEAD(&self->kernel_dsos);
+	struct rb_node *first = rb_first(maps);
 
-	self->kmaps.machine = self;
-	self->pid	    = pid;
-	self->root_dir      = strdup(root_dir);
-	return self->root_dir == NULL ? -ENOMEM : 0;
-}
-
-struct machine *machines__add(struct rb_root *self, pid_t pid,
-			      const char *root_dir)
-{
-	struct rb_node **p = &self->rb_node;
-	struct rb_node *parent = NULL;
-	struct machine *pos, *machine = malloc(sizeof(*machine));
-
-	if (!machine)
-		return NULL;
-
-	if (machine__init(machine, root_dir, pid) != 0) {
-		free(machine);
-		return NULL;
-	}
-
-	while (*p != NULL) {
-		parent = *p;
-		pos = rb_entry(parent, struct machine, rb_node);
-		if (pid < pos->pid)
-			p = &(*p)->rb_left;
-		else
-			p = &(*p)->rb_right;
-	}
-
-	rb_link_node(&machine->rb_node, parent, p);
-	rb_insert_color(&machine->rb_node, self);
-
-	return machine;
-}
-
-struct machine *machines__find(struct rb_root *self, pid_t pid)
-{
-	struct rb_node **p = &self->rb_node;
-	struct rb_node *parent = NULL;
-	struct machine *machine;
-	struct machine *default_machine = NULL;
-
-	while (*p != NULL) {
-		parent = *p;
-		machine = rb_entry(parent, struct machine, rb_node);
-		if (pid < machine->pid)
-			p = &(*p)->rb_left;
-		else if (pid > machine->pid)
-			p = &(*p)->rb_right;
-		else
-			return machine;
-		if (!machine->pid)
-			default_machine = machine;
-	}
-
-	return default_machine;
-}
-
-struct machine *machines__findnew(struct rb_root *self, pid_t pid)
-{
-	char path[PATH_MAX];
-	const char *root_dir;
-	struct machine *machine = machines__find(self, pid);
-
-	if (!machine || machine->pid != pid) {
-		if (pid == HOST_KERNEL_ID || pid == DEFAULT_GUEST_KERNEL_ID)
-			root_dir = "";
-		else {
-			if (!symbol_conf.guestmount)
-				goto out;
-			sprintf(path, "%s/%d", symbol_conf.guestmount, pid);
-			if (access(path, R_OK)) {
-				pr_err("Can't access file %s\n", path);
-				goto out;
-			}
-			root_dir = path;
-		}
-		machine = machines__add(self, pid, root_dir);
-	}
-
-out:
-	return machine;
-}
-
-void machines__process(struct rb_root *self, machine__process_t process, void *data)
-{
-	struct rb_node *nd;
-
-	for (nd = rb_first(self); nd; nd = rb_next(nd)) {
-		struct machine *pos = rb_entry(nd, struct machine, rb_node);
-		process(pos, data);
-	}
+	if (first)
+		return rb_entry(first, struct map, rb_node);
+	return NULL;
 }
 
-char *machine__mmap_name(struct machine *self, char *bf, size_t size)
+struct map *maps__next(struct map *map)
 {
-	if (machine__is_host(self))
-		snprintf(bf, size, "[%s]", "kernel.kallsyms");
-	else if (machine__is_default_guest(self))
-		snprintf(bf, size, "[%s]", "guest.kernel.kallsyms");
-	else
-		snprintf(bf, size, "[%s.%d]", "guest.kernel.kallsyms", self->pid);
+	struct rb_node *next = rb_next(&map->rb_node);
 
-	return bf;
+	if (next)
+		return rb_entry(next, struct map, rb_node);
+	return NULL;
 }
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index f3913451282..7758c72522e 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -6,7 +6,7 @@
 #include <linux/rbtree.h>
 #include <stdio.h>
 #include <stdbool.h>
-#include "types.h"
+#include <linux/types.h>
 
 enum map_type {
 	MAP__FUNCTION = 0,
@@ -18,9 +18,11 @@ enum map_type {
 extern const char *map_type__name[MAP__NR_TYPES];
 
 struct dso;
+struct ip_callchain;
 struct ref_reloc_sym;
 struct map_groups;
 struct machine;
+struct perf_evsel;
 
 struct map {
 	union {
@@ -29,9 +31,17 @@ struct map {
 	};
 	u64			start;
 	u64			end;
-	enum map_type		type;
+	u8 /* enum map_type */	type;
+	bool			referenced;
+	bool			erange_warned;
 	u32			priv;
+	u32			prot;
+	u32			flags;
 	u64			pgoff;
+	u64			reloc;
+	u32			maj, min; /* only valid for MMAP2 record */
+	u64			ino;      /* only valid for MMAP2 record */
+	u64			ino_generation;/* only valid for MMAP2 record */
 
 	/* ip -> dso rip */
 	u64			(*map_ip)(struct map *, u64);
@@ -51,31 +61,23 @@ struct map_groups {
 	struct rb_root	 maps[MAP__NR_TYPES];
 	struct list_head removed_maps[MAP__NR_TYPES];
 	struct machine	 *machine;
+	int		 refcnt;
 };
 
-/* Native host kernel uses -1 as pid index in machine */
-#define	HOST_KERNEL_ID			(-1)
-#define	DEFAULT_GUEST_KERNEL_ID		(0)
-
-struct machine {
-	struct rb_node	  rb_node;
-	pid_t		  pid;
-	char		  *root_dir;
-	struct list_head  user_dsos;
-	struct list_head  kernel_dsos;
-	struct map_groups kmaps;
-	struct map	  *vmlinux_maps[MAP__NR_TYPES];
-};
+struct map_groups *map_groups__new(void);
+void map_groups__delete(struct map_groups *mg);
 
-static inline
-struct map *machine__kernel_map(struct machine *self, enum map_type type)
+static inline struct map_groups *map_groups__get(struct map_groups *mg)
 {
-	return self->vmlinux_maps[type];
+	++mg->refcnt;
+	return mg;
 }
 
-static inline struct kmap *map__kmap(struct map *self)
+void map_groups__put(struct map_groups *mg);
+
+static inline struct kmap *map__kmap(struct map *map)
 {
-	return (struct kmap *)(self + 1);
+	return (struct kmap *)(map + 1);
 }
 
 static inline u64 map__map_ip(struct map *map, u64 ip)
@@ -88,7 +90,7 @@ static inline u64 map__unmap_ip(struct map *map, u64 ip)
 	return ip + map->start - map->pgoff;
 }
 
-static inline u64 identity__map_ip(struct map *map __used, u64 ip)
+static inline u64 identity__map_ip(struct map *map __maybe_unused, u64 ip)
 {
 	return ip;
 }
@@ -96,122 +98,123 @@ static inline u64 identity__map_ip(struct map *map __used, u64 ip)
 
 /* rip/ip <-> addr suitable for passing to `objdump --start-address=` */
 u64 map__rip_2objdump(struct map *map, u64 rip);
-u64 map__objdump_2ip(struct map *map, u64 addr);
+
+/* objdump address -> memory address */
+u64 map__objdump_2mem(struct map *map, u64 ip);
 
 struct symbol;
 
+/* map__for_each_symbol - iterate over the symbols in the given map
+ *
+ * @map: the 'struct map *' in which symbols itereated
+ * @pos: the 'struct symbol *' to use as a loop cursor
+ * @n: the 'struct rb_node *' to use as a temporary storage
+ * Note: caller must ensure map->dso is not NULL (map is loaded).
+ */
+#define map__for_each_symbol(map, pos, n)	\
+	dso__for_each_symbol(map->dso, pos, n, map->type)
+
 typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym);
 
-void map__init(struct map *self, enum map_type type,
+void map__init(struct map *map, enum map_type type,
 	       u64 start, u64 end, u64 pgoff, struct dso *dso);
 struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
-		     u64 pgoff, u32 pid, char *filename,
-		     enum map_type type, char *cwd, int cwdlen);
-void map__delete(struct map *self);
-struct map *map__clone(struct map *self);
+		     u64 pgoff, u32 pid, u32 d_maj, u32 d_min, u64 ino,
+		     u64 ino_gen, u32 prot, u32 flags,
+		     char *filename, enum map_type type);
+struct map *map__new2(u64 start, struct dso *dso, enum map_type type);
+void map__delete(struct map *map);
+struct map *map__clone(struct map *map);
 int map__overlap(struct map *l, struct map *r);
-size_t map__fprintf(struct map *self, FILE *fp);
+size_t map__fprintf(struct map *map, FILE *fp);
+size_t map__fprintf_dsoname(struct map *map, FILE *fp);
+int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix,
+			 FILE *fp);
 
-int map__load(struct map *self, symbol_filter_t filter);
-struct symbol *map__find_symbol(struct map *self,
+int map__load(struct map *map, symbol_filter_t filter);
+struct symbol *map__find_symbol(struct map *map,
 				u64 addr, symbol_filter_t filter);
-struct symbol *map__find_symbol_by_name(struct map *self, const char *name,
+struct symbol *map__find_symbol_by_name(struct map *map, const char *name,
 					symbol_filter_t filter);
-void map__fixup_start(struct map *self);
-void map__fixup_end(struct map *self);
+void map__fixup_start(struct map *map);
+void map__fixup_end(struct map *map);
 
-void map__reloc_vmlinux(struct map *self);
+void map__reloc_vmlinux(struct map *map);
 
-size_t __map_groups__fprintf_maps(struct map_groups *self,
+size_t __map_groups__fprintf_maps(struct map_groups *mg,
 				  enum map_type type, int verbose, FILE *fp);
 void maps__insert(struct rb_root *maps, struct map *map);
+void maps__remove(struct rb_root *maps, struct map *map);
 struct map *maps__find(struct rb_root *maps, u64 addr);
-void map_groups__init(struct map_groups *self);
-int map_groups__clone(struct map_groups *self,
+struct map *maps__first(struct rb_root *maps);
+struct map *maps__next(struct map *map);
+void map_groups__init(struct map_groups *mg);
+void map_groups__exit(struct map_groups *mg);
+int map_groups__clone(struct map_groups *mg,
 		      struct map_groups *parent, enum map_type type);
-size_t map_groups__fprintf(struct map_groups *self, int verbose, FILE *fp);
-size_t map_groups__fprintf_maps(struct map_groups *self, int verbose, FILE *fp);
-
-typedef void (*machine__process_t)(struct machine *self, void *data);
-
-void machines__process(struct rb_root *self, machine__process_t process, void *data);
-struct machine *machines__add(struct rb_root *self, pid_t pid,
-			      const char *root_dir);
-struct machine *machines__find_host(struct rb_root *self);
-struct machine *machines__find(struct rb_root *self, pid_t pid);
-struct machine *machines__findnew(struct rb_root *self, pid_t pid);
-char *machine__mmap_name(struct machine *self, char *bf, size_t size);
-int machine__init(struct machine *self, const char *root_dir, pid_t pid);
-
-/*
- * Default guest kernel is defined by parameter --guestkallsyms
- * and --guestmodules
- */
-static inline bool machine__is_default_guest(struct machine *self)
+size_t map_groups__fprintf(struct map_groups *mg, int verbose, FILE *fp);
+size_t map_groups__fprintf_maps(struct map_groups *mg, int verbose, FILE *fp);
+
+int maps__set_kallsyms_ref_reloc_sym(struct map **maps, const char *symbol_name,
+				     u64 addr);
+
+static inline void map_groups__insert(struct map_groups *mg, struct map *map)
+{
+	maps__insert(&mg->maps[map->type], map);
+	map->groups = mg;
+}
+
+static inline void map_groups__remove(struct map_groups *mg, struct map *map)
 {
-	return self ? self->pid == DEFAULT_GUEST_KERNEL_ID : false;
+	maps__remove(&mg->maps[map->type], map);
 }
 
-static inline bool machine__is_host(struct machine *self)
+static inline struct map *map_groups__find(struct map_groups *mg,
+					   enum map_type type, u64 addr)
 {
-	return self ? self->pid == HOST_KERNEL_ID : false;
+	return maps__find(&mg->maps[type], addr);
 }
 
-static inline void map_groups__insert(struct map_groups *self, struct map *map)
+static inline struct map *map_groups__first(struct map_groups *mg,
+					    enum map_type type)
 {
-	maps__insert(&self->maps[map->type], map);
-	map->groups = self;
+	return maps__first(&mg->maps[type]);
 }
 
-static inline struct map *map_groups__find(struct map_groups *self,
-					   enum map_type type, u64 addr)
+static inline struct map *map_groups__next(struct map *map)
 {
-	return maps__find(&self->maps[type], addr);
+	return maps__next(map);
 }
 
-struct symbol *map_groups__find_symbol(struct map_groups *self,
+struct symbol *map_groups__find_symbol(struct map_groups *mg,
 				       enum map_type type, u64 addr,
 				       struct map **mapp,
 				       symbol_filter_t filter);
 
-struct symbol *map_groups__find_symbol_by_name(struct map_groups *self,
+struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg,
 					       enum map_type type,
 					       const char *name,
 					       struct map **mapp,
 					       symbol_filter_t filter);
 
-static inline
-struct symbol *machine__find_kernel_symbol(struct machine *self,
-					   enum map_type type, u64 addr,
-					   struct map **mapp,
-					   symbol_filter_t filter)
-{
-	return map_groups__find_symbol(&self->kmaps, type, addr, mapp, filter);
-}
+struct addr_map_symbol;
 
-static inline
-struct symbol *machine__find_kernel_function(struct machine *self, u64 addr,
-					     struct map **mapp,
-					     symbol_filter_t filter)
-{
-	return machine__find_kernel_symbol(self, MAP__FUNCTION, addr, mapp, filter);
-}
+int map_groups__find_ams(struct addr_map_symbol *ams, symbol_filter_t filter);
 
 static inline
-struct symbol *map_groups__find_function_by_name(struct map_groups *self,
+struct symbol *map_groups__find_function_by_name(struct map_groups *mg,
 						 const char *name, struct map **mapp,
 						 symbol_filter_t filter)
 {
-	return map_groups__find_symbol_by_name(self, MAP__FUNCTION, name, mapp, filter);
+	return map_groups__find_symbol_by_name(mg, MAP__FUNCTION, name, mapp, filter);
 }
 
-int map_groups__fixup_overlappings(struct map_groups *self, struct map *map,
+int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
 				   int verbose, FILE *fp);
 
-struct map *map_groups__find_by_name(struct map_groups *self,
+struct map *map_groups__find_by_name(struct map_groups *mg,
 				     enum map_type type, const char *name);
-struct map *machine__new_module(struct machine *self, u64 start, const char *filename);
 
-void map_groups__flush(struct map_groups *self);
+void map_groups__flush(struct map_groups *mg);
 
 #endif /* __PERF_MAP_H */
diff --git a/tools/perf/util/newt.c b/tools/perf/util/newt.c
deleted file mode 100644
index 7537ca15900..00000000000
--- a/tools/perf/util/newt.c
+++ /dev/null
@@ -1,1178 +0,0 @@
-#define _GNU_SOURCE
-#include <stdio.h>
-#undef _GNU_SOURCE
-/*
- * slang versions <= 2.0.6 have a "#if HAVE_LONG_LONG" that breaks
- * the build if it isn't defined. Use the equivalent one that glibc
- * has on features.h.
- */
-#include <features.h>
-#ifndef HAVE_LONG_LONG
-#define HAVE_LONG_LONG __GLIBC_HAVE_LONG_LONG
-#endif
-#include <slang.h>
-#include <stdlib.h>
-#include <newt.h>
-#include <sys/ttydefaults.h>
-
-#include "cache.h"
-#include "hist.h"
-#include "pstack.h"
-#include "session.h"
-#include "sort.h"
-#include "symbol.h"
-
-#if SLANG_VERSION < 20104
-#define slsmg_printf(msg, args...) SLsmg_printf((char *)msg, ##args)
-#define slsmg_write_nstring(msg, len) SLsmg_write_nstring((char *)msg, len)
-#define sltt_set_color(obj, name, fg, bg) SLtt_set_color(obj,(char *)name,\
-							 (char *)fg, (char *)bg)
-#else
-#define slsmg_printf SLsmg_printf
-#define slsmg_write_nstring SLsmg_write_nstring
-#define sltt_set_color SLtt_set_color
-#endif
-
-struct ui_progress {
-	newtComponent form, scale;
-};
-
-struct ui_progress *ui_progress__new(const char *title, u64 total)
-{
-	struct ui_progress *self = malloc(sizeof(*self));
-
-	if (self != NULL) {
-		int cols;
-
-		if (use_browser <= 0)	
-			return self;
-		newtGetScreenSize(&cols, NULL);
-		cols -= 4;
-		newtCenteredWindow(cols, 1, title);
-		self->form  = newtForm(NULL, NULL, 0);
-		if (self->form == NULL)
-			goto out_free_self;
-		self->scale = newtScale(0, 0, cols, total);
-		if (self->scale == NULL)
-			goto out_free_form;
-		newtFormAddComponent(self->form, self->scale);
-		newtRefresh();
-	}
-
-	return self;
-
-out_free_form:
-	newtFormDestroy(self->form);
-out_free_self:
-	free(self);
-	return NULL;
-}
-
-void ui_progress__update(struct ui_progress *self, u64 curr)
-{
-	/*
-	 * FIXME: We should have a per UI backend way of showing progress,
-	 * stdio will just show a percentage as NN%, etc.
-	 */
-	if (use_browser <= 0)
-		return;
-	newtScaleSet(self->scale, curr);
-	newtRefresh();
-}
-
-void ui_progress__delete(struct ui_progress *self)
-{
-	if (use_browser > 0) {
-		newtFormDestroy(self->form);
-		newtPopWindow();
-	}
-	free(self);
-}
-
-static void ui_helpline__pop(void)
-{
-	newtPopHelpLine();
-}
-
-static void ui_helpline__push(const char *msg)
-{
-	newtPushHelpLine(msg);
-}
-
-static void ui_helpline__vpush(const char *fmt, va_list ap)
-{
-	char *s;
-
-	if (vasprintf(&s, fmt, ap) < 0)
-		vfprintf(stderr, fmt, ap);
-	else {
-		ui_helpline__push(s);
-		free(s);
-	}
-}
-
-static void ui_helpline__fpush(const char *fmt, ...)
-{
-	va_list ap;
-
-	va_start(ap, fmt);
-	ui_helpline__vpush(fmt, ap);
-	va_end(ap);
-}
-
-static void ui_helpline__puts(const char *msg)
-{
-	ui_helpline__pop();
-	ui_helpline__push(msg);
-}
-
-static char browser__last_msg[1024];
-
-int browser__show_help(const char *format, va_list ap)
-{
-	int ret;
-	static int backlog;
-
-        ret = vsnprintf(browser__last_msg + backlog,
-			sizeof(browser__last_msg) - backlog, format, ap);
-	backlog += ret;
-
-	if (browser__last_msg[backlog - 1] == '\n') {
-		ui_helpline__puts(browser__last_msg);
-		newtRefresh();
-		backlog = 0;
-	}
-
-	return ret;
-}
-
-static void newt_form__set_exit_keys(newtComponent self)
-{
-	newtFormAddHotKey(self, NEWT_KEY_LEFT);
-	newtFormAddHotKey(self, NEWT_KEY_ESCAPE);
-	newtFormAddHotKey(self, 'Q');
-	newtFormAddHotKey(self, 'q');
-	newtFormAddHotKey(self, CTRL('c'));
-}
-
-static newtComponent newt_form__new(void)
-{
-	newtComponent self = newtForm(NULL, NULL, 0);
-	if (self)
-		newt_form__set_exit_keys(self);
-	return self;
-}
-
-static int popup_menu(int argc, char * const argv[])
-{
-	struct newtExitStruct es;
-	int i, rc = -1, max_len = 5;
-	newtComponent listbox, form = newt_form__new();
-
-	if (form == NULL)
-		return -1;
-
-	listbox = newtListbox(0, 0, argc, NEWT_FLAG_RETURNEXIT);
-	if (listbox == NULL)
-		goto out_destroy_form;
-
-	newtFormAddComponent(form, listbox);
-
-	for (i = 0; i < argc; ++i) {
-		int len = strlen(argv[i]);
-		if (len > max_len)
-			max_len = len;
-		if (newtListboxAddEntry(listbox, argv[i], (void *)(long)i))
-			goto out_destroy_form;
-	}
-
-	newtCenteredWindow(max_len, argc, NULL);
-	newtFormRun(form, &es);
-	rc = newtListboxGetCurrent(listbox) - NULL;
-	if (es.reason == NEWT_EXIT_HOTKEY)
-		rc = -1;
-	newtPopWindow();
-out_destroy_form:
-	newtFormDestroy(form);
-	return rc;
-}
-
-static int ui__help_window(const char *text)
-{
-	struct newtExitStruct es;
-	newtComponent tb, form = newt_form__new();
-	int rc = -1;
-	int max_len = 0, nr_lines = 0;
-	const char *t;
-
-	if (form == NULL)
-		return -1;
-
-	t = text;
-	while (1) {
-		const char *sep = strchr(t, '\n');
-		int len;
-
-		if (sep == NULL)
-			sep = strchr(t, '\0');
-		len = sep - t;
-		if (max_len < len)
-			max_len = len;
-		++nr_lines;
-		if (*sep == '\0')
-			break;
-		t = sep + 1;
-	}
-
-	tb = newtTextbox(0, 0, max_len, nr_lines, 0);
-	if (tb == NULL)
-		goto out_destroy_form;
-
-	newtTextboxSetText(tb, text);
-	newtFormAddComponent(form, tb);
-	newtCenteredWindow(max_len, nr_lines, NULL);
-	newtFormRun(form, &es);
-	newtPopWindow();
-	rc = 0;
-out_destroy_form:
-	newtFormDestroy(form);
-	return rc;
-}
-
-static bool dialog_yesno(const char *msg)
-{
-	/* newtWinChoice should really be accepting const char pointers... */
-	char yes[] = "Yes", no[] = "No";
-	return newtWinChoice(NULL, yes, no, (char *)msg) == 1;
-}
-
-static void ui__error_window(const char *fmt, ...)
-{
-	va_list ap;
-
-	va_start(ap, fmt);
-	newtWinMessagev((char *)"Error", (char *)"Ok", (char *)fmt, ap);
-	va_end(ap);
-}
-
-#define HE_COLORSET_TOP		50
-#define HE_COLORSET_MEDIUM	51
-#define HE_COLORSET_NORMAL	52
-#define HE_COLORSET_SELECTED	53
-#define HE_COLORSET_CODE	54
-
-static int ui_browser__percent_color(double percent, bool current)
-{
-	if (current)
-		return HE_COLORSET_SELECTED;
-	if (percent >= MIN_RED)
-		return HE_COLORSET_TOP;
-	if (percent >= MIN_GREEN)
-		return HE_COLORSET_MEDIUM;
-	return HE_COLORSET_NORMAL;
-}
-
-struct ui_browser {
-	newtComponent	form, sb;
-	u64		index, first_visible_entry_idx;
-	void		*first_visible_entry, *entries;
-	u16		top, left, width, height;
-	void		*priv;
-	u32		nr_entries;
-};
-
-static void ui_browser__refresh_dimensions(struct ui_browser *self)
-{
-	int cols, rows;
-	newtGetScreenSize(&cols, &rows);
-
-	if (self->width > cols - 4)
-		self->width = cols - 4;
-	self->height = rows - 5;
-	if (self->height > self->nr_entries)
-		self->height = self->nr_entries;
-	self->top  = (rows - self->height) / 2;
-	self->left = (cols - self->width) / 2;
-}
-
-static void ui_browser__reset_index(struct ui_browser *self)
-{
-        self->index = self->first_visible_entry_idx = 0;
-        self->first_visible_entry = NULL;
-}
-
-static int objdump_line__show(struct objdump_line *self, struct list_head *head,
-			      int width, struct hist_entry *he, int len,
-			      bool current_entry)
-{
-	if (self->offset != -1) {
-		struct symbol *sym = he->ms.sym;
-		unsigned int hits = 0;
-		double percent = 0.0;
-		int color;
-		struct sym_priv *priv = symbol__priv(sym);
-		struct sym_ext *sym_ext = priv->ext;
-		struct sym_hist *h = priv->hist;
-		s64 offset = self->offset;
-		struct objdump_line *next = objdump__get_next_ip_line(head, self);
-
-		while (offset < (s64)len &&
-		       (next == NULL || offset < next->offset)) {
-			if (sym_ext) {
-				percent += sym_ext[offset].percent;
-			} else
-				hits += h->ip[offset];
-
-			++offset;
-		}
-
-		if (sym_ext == NULL && h->sum)
-			percent = 100.0 * hits / h->sum;
-
-		color = ui_browser__percent_color(percent, current_entry);
-		SLsmg_set_color(color);
-		slsmg_printf(" %7.2f ", percent);
-		if (!current_entry)
-			SLsmg_set_color(HE_COLORSET_CODE);
-	} else {
-		int color = ui_browser__percent_color(0, current_entry);
-		SLsmg_set_color(color);
-		slsmg_write_nstring(" ", 9);
-	}
-
-	SLsmg_write_char(':');
-	slsmg_write_nstring(" ", 8);
-	if (!*self->line)
-		slsmg_write_nstring(" ", width - 18);
-	else
-		slsmg_write_nstring(self->line, width - 18);
-
-	return 0;
-}
-
-static int ui_browser__refresh_entries(struct ui_browser *self)
-{
-	struct objdump_line *pos;
-	struct list_head *head = self->entries;
-	struct hist_entry *he = self->priv;
-	int row = 0;
-	int len = he->ms.sym->end - he->ms.sym->start;
-
-	if (self->first_visible_entry == NULL || self->first_visible_entry == self->entries)
-                self->first_visible_entry = head->next;
-
-	pos = list_entry(self->first_visible_entry, struct objdump_line, node);
-
-	list_for_each_entry_from(pos, head, node) {
-		bool current_entry = (self->first_visible_entry_idx + row) == self->index;
-		SLsmg_gotorc(self->top + row, self->left);
-		objdump_line__show(pos, head, self->width,
-				   he, len, current_entry);
-		if (++row == self->height)
-			break;
-	}
-
-	SLsmg_set_color(HE_COLORSET_NORMAL);
-	SLsmg_fill_region(self->top + row, self->left,
-			  self->height - row, self->width, ' ');
-
-	return 0;
-}
-
-static int ui_browser__run(struct ui_browser *self, const char *title,
-			   struct newtExitStruct *es)
-{
-	if (self->form) {
-		newtFormDestroy(self->form);
-		newtPopWindow();
-	}
-
-	ui_browser__refresh_dimensions(self);
-	newtCenteredWindow(self->width + 2, self->height, title);
-	self->form = newt_form__new();
-	if (self->form == NULL)
-		return -1;
-
-	self->sb = newtVerticalScrollbar(self->width + 1, 0, self->height,
-					 HE_COLORSET_NORMAL,
-					 HE_COLORSET_SELECTED);
-	if (self->sb == NULL)
-		return -1;
-
-	newtFormAddHotKey(self->form, NEWT_KEY_UP);
-	newtFormAddHotKey(self->form, NEWT_KEY_DOWN);
-	newtFormAddHotKey(self->form, NEWT_KEY_PGUP);
-	newtFormAddHotKey(self->form, NEWT_KEY_PGDN);
-	newtFormAddHotKey(self->form, ' ');
-	newtFormAddHotKey(self->form, NEWT_KEY_HOME);
-	newtFormAddHotKey(self->form, NEWT_KEY_END);
-	newtFormAddHotKey(self->form, NEWT_KEY_TAB);
-	newtFormAddHotKey(self->form, NEWT_KEY_RIGHT);
-
-	if (ui_browser__refresh_entries(self) < 0)
-		return -1;
-	newtFormAddComponent(self->form, self->sb);
-
-	while (1) {
-		unsigned int offset;
-
-		newtFormRun(self->form, es);
-
-		if (es->reason != NEWT_EXIT_HOTKEY)
-			break;
-		if (is_exit_key(es->u.key))
-			return es->u.key;
-		switch (es->u.key) {
-		case NEWT_KEY_DOWN:
-			if (self->index == self->nr_entries - 1)
-				break;
-			++self->index;
-			if (self->index == self->first_visible_entry_idx + self->height) {
-				struct list_head *pos = self->first_visible_entry;
-				++self->first_visible_entry_idx;
-				self->first_visible_entry = pos->next;
-			}
-			break;
-		case NEWT_KEY_UP:
-			if (self->index == 0)
-				break;
-			--self->index;
-			if (self->index < self->first_visible_entry_idx) {
-				struct list_head *pos = self->first_visible_entry;
-				--self->first_visible_entry_idx;
-				self->first_visible_entry = pos->prev;
-			}
-			break;
-		case NEWT_KEY_PGDN:
-		case ' ':
-			if (self->first_visible_entry_idx + self->height > self->nr_entries - 1)
-				break;
-
-			offset = self->height;
-			if (self->index + offset > self->nr_entries - 1)
-				offset = self->nr_entries - 1 - self->index;
-			self->index += offset;
-			self->first_visible_entry_idx += offset;
-
-			while (offset--) {
-				struct list_head *pos = self->first_visible_entry;
-				self->first_visible_entry = pos->next;
-			}
-
-			break;
-		case NEWT_KEY_PGUP:
-			if (self->first_visible_entry_idx == 0)
-				break;
-
-			if (self->first_visible_entry_idx < self->height)
-				offset = self->first_visible_entry_idx;
-			else
-				offset = self->height;
-
-			self->index -= offset;
-			self->first_visible_entry_idx -= offset;
-
-			while (offset--) {
-				struct list_head *pos = self->first_visible_entry;
-				self->first_visible_entry = pos->prev;
-			}
-			break;
-		case NEWT_KEY_HOME:
-			ui_browser__reset_index(self);
-			break;
-		case NEWT_KEY_END: {
-			struct list_head *head = self->entries;
-			offset = self->height - 1;
-
-			if (offset > self->nr_entries)
-				offset = self->nr_entries;
-
-			self->index = self->first_visible_entry_idx = self->nr_entries - 1 - offset;
-			self->first_visible_entry = head->prev;
-			while (offset-- != 0) {
-				struct list_head *pos = self->first_visible_entry;
-				self->first_visible_entry = pos->prev;
-			}
-		}
-			break;
-		case NEWT_KEY_RIGHT:
-		case NEWT_KEY_LEFT:
-		case NEWT_KEY_TAB:
-			return es->u.key;
-		default:
-			continue;
-		}
-		if (ui_browser__refresh_entries(self) < 0)
-			return -1;
-	}
-	return 0;
-}
-
-/*
- * When debugging newt problems it was useful to be able to "unroll"
- * the calls to newtCheckBoxTreeAdd{Array,Item}, so that we can generate
- * a source file with the sequence of calls to these methods, to then
- * tweak the arrays to get the intended results, so I'm keeping this code
- * here, may be useful again in the future.
- */
-#undef NEWT_DEBUG
-
-static void newt_checkbox_tree__add(newtComponent tree, const char *str,
-				    void *priv, int *indexes)
-{
-#ifdef NEWT_DEBUG
-	/* Print the newtCheckboxTreeAddArray to tinker with its index arrays */
-	int i = 0, len = 40 - strlen(str);
-
-	fprintf(stderr,
-		"\tnewtCheckboxTreeAddItem(tree, %*.*s\"%s\", (void *)%p, 0, ",
-		len, len, " ", str, priv);
-	while (indexes[i] != NEWT_ARG_LAST) {
-		if (indexes[i] != NEWT_ARG_APPEND)
-			fprintf(stderr, " %d,", indexes[i]);
-		else
-			fprintf(stderr, " %s,", "NEWT_ARG_APPEND");
-		++i;
-	}
-	fprintf(stderr, " %s", " NEWT_ARG_LAST);\n");
-	fflush(stderr);
-#endif
-	newtCheckboxTreeAddArray(tree, str, priv, 0, indexes);
-}
-
-static char *callchain_list__sym_name(struct callchain_list *self,
-				      char *bf, size_t bfsize)
-{
-	if (self->ms.sym)
-		return self->ms.sym->name;
-
-	snprintf(bf, bfsize, "%#Lx", self->ip);
-	return bf;
-}
-
-static void __callchain__append_graph_browser(struct callchain_node *self,
-					      newtComponent tree, u64 total,
-					      int *indexes, int depth)
-{
-	struct rb_node *node;
-	u64 new_total, remaining;
-	int idx = 0;
-
-	if (callchain_param.mode == CHAIN_GRAPH_REL)
-		new_total = self->children_hit;
-	else
-		new_total = total;
-
-	remaining = new_total;
-	node = rb_first(&self->rb_root);
-	while (node) {
-		struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
-		struct rb_node *next = rb_next(node);
-		u64 cumul = cumul_hits(child);
-		struct callchain_list *chain;
-		int first = true, printed = 0;
-		int chain_idx = -1;
-		remaining -= cumul;
-
-		indexes[depth] = NEWT_ARG_APPEND;
-		indexes[depth + 1] = NEWT_ARG_LAST;
-
-		list_for_each_entry(chain, &child->val, list) {
-			char ipstr[BITS_PER_LONG / 4 + 1],
-			     *alloc_str = NULL;
-			const char *str = callchain_list__sym_name(chain, ipstr, sizeof(ipstr));
-
-			if (first) {
-				double percent = cumul * 100.0 / new_total;
-
-				first = false;
-				if (asprintf(&alloc_str, "%2.2f%% %s", percent, str) < 0)
-					str = "Not enough memory!";
-				else
-					str = alloc_str;
-			} else {
-				indexes[depth] = idx;
-				indexes[depth + 1] = NEWT_ARG_APPEND;
-				indexes[depth + 2] = NEWT_ARG_LAST;
-				++chain_idx;
-			}
-			newt_checkbox_tree__add(tree, str, &chain->ms, indexes);
-			free(alloc_str);
-			++printed;
-		}
-
-		indexes[depth] = idx;
-		if (chain_idx != -1)
-			indexes[depth + 1] = chain_idx;
-		if (printed != 0)
-			++idx;
-		__callchain__append_graph_browser(child, tree, new_total, indexes,
-						  depth + (chain_idx != -1 ? 2 : 1));
-		node = next;
-	}
-}
-
-static void callchain__append_graph_browser(struct callchain_node *self,
-					    newtComponent tree, u64 total,
-					    int *indexes, int parent_idx)
-{
-	struct callchain_list *chain;
-	int i = 0;
-
-	indexes[1] = NEWT_ARG_APPEND;
-	indexes[2] = NEWT_ARG_LAST;
-
-	list_for_each_entry(chain, &self->val, list) {
-		char ipstr[BITS_PER_LONG / 4 + 1], *str;
-
-		if (chain->ip >= PERF_CONTEXT_MAX)
-			continue;
-
-		if (!i++ && sort__first_dimension == SORT_SYM)
-			continue;
-
-		str = callchain_list__sym_name(chain, ipstr, sizeof(ipstr));
-		newt_checkbox_tree__add(tree, str, &chain->ms, indexes);
-	}
-
-	indexes[1] = parent_idx;
-	indexes[2] = NEWT_ARG_APPEND;
-	indexes[3] = NEWT_ARG_LAST;
-	__callchain__append_graph_browser(self, tree, total, indexes, 2);
-}
-
-static void hist_entry__append_callchain_browser(struct hist_entry *self,
-						 newtComponent tree, u64 total, int parent_idx)
-{
-	struct rb_node *rb_node;
-	int indexes[1024] = { [0] = parent_idx, };
-	int idx = 0;
-	struct callchain_node *chain;
-
-	rb_node = rb_first(&self->sorted_chain);
-	while (rb_node) {
-		chain = rb_entry(rb_node, struct callchain_node, rb_node);
-		switch (callchain_param.mode) {
-		case CHAIN_FLAT:
-			break;
-		case CHAIN_GRAPH_ABS: /* falldown */
-		case CHAIN_GRAPH_REL:
-			callchain__append_graph_browser(chain, tree, total, indexes, idx++);
-			break;
-		case CHAIN_NONE:
-		default:
-			break;
-		}
-		rb_node = rb_next(rb_node);
-	}
-}
-
-static size_t hist_entry__append_browser(struct hist_entry *self,
-					 newtComponent tree, u64 total)
-{
-	char s[256];
-	size_t ret;
-
-	if (symbol_conf.exclude_other && !self->parent)
-		return 0;
-
-	ret = hist_entry__snprintf(self, s, sizeof(s), NULL,
-				   false, 0, false, total);
-	if (symbol_conf.use_callchain) {
-		int indexes[2];
-
-		indexes[0] = NEWT_ARG_APPEND;
-		indexes[1] = NEWT_ARG_LAST;
-		newt_checkbox_tree__add(tree, s, &self->ms, indexes);
-	} else
-		newtListboxAppendEntry(tree, s, &self->ms);
-
-	return ret;
-}
-
-int hist_entry__tui_annotate(struct hist_entry *self)
-{
-	struct ui_browser browser;
-	struct newtExitStruct es;
-	struct objdump_line *pos, *n;
-	LIST_HEAD(head);
-	int ret;
-
-	if (self->ms.sym == NULL)
-		return -1;
-
-	if (self->ms.map->dso->annotate_warned)
-		return -1;
-
-	if (hist_entry__annotate(self, &head) < 0) {
-		ui__error_window(browser__last_msg);
-		return -1;
-	}
-
-	ui_helpline__push("Press <- or ESC to exit");
-
-	memset(&browser, 0, sizeof(browser));
-	browser.entries = &head;
-	browser.priv = self;
-	list_for_each_entry(pos, &head, node) {
-		size_t line_len = strlen(pos->line);
-		if (browser.width < line_len)
-			browser.width = line_len;
-		++browser.nr_entries;
-	}
-
-	browser.width += 18; /* Percentage */
-	ret = ui_browser__run(&browser, self->ms.sym->name, &es);
-	newtFormDestroy(browser.form);
-	newtPopWindow();
-	list_for_each_entry_safe(pos, n, &head, node) {
-		list_del(&pos->node);
-		objdump_line__free(pos);
-	}
-	ui_helpline__pop();
-	return ret;
-}
-
-static const void *newt__symbol_tree_get_current(newtComponent self)
-{
-	if (symbol_conf.use_callchain)
-		return newtCheckboxTreeGetCurrent(self);
-	return newtListboxGetCurrent(self);
-}
-
-static void hist_browser__selection(newtComponent self, void *data)
-{
-	const struct map_symbol **symbol_ptr = data;
-	*symbol_ptr = newt__symbol_tree_get_current(self);
-}
-
-struct hist_browser {
-	newtComponent		form, tree;
-	const struct map_symbol *selection;
-};
-
-static struct hist_browser *hist_browser__new(void)
-{
-	struct hist_browser *self = malloc(sizeof(*self));
-
-	if (self != NULL)
-		self->form = NULL;
-
-	return self;
-}
-
-static void hist_browser__delete(struct hist_browser *self)
-{
-	newtFormDestroy(self->form);
-	newtPopWindow();
-	free(self);
-}
-
-static int hist_browser__populate(struct hist_browser *self, struct hists *hists,
-				  const char *title)
-{
-	int max_len = 0, idx, cols, rows;
-	struct ui_progress *progress;
-	struct rb_node *nd;
-	u64 curr_hist = 0;
-	char seq[] = ".", unit;
-	char str[256];
-	unsigned long nr_events = hists->stats.nr_events[PERF_RECORD_SAMPLE];
-
-	if (self->form) {
-		newtFormDestroy(self->form);
-		newtPopWindow();
-	}
-
-	nr_events = convert_unit(nr_events, &unit);
-	snprintf(str, sizeof(str), "Events: %lu%c                            ",
-		 nr_events, unit);
-	newtDrawRootText(0, 0, str);
-
-	newtGetScreenSize(NULL, &rows);
-
-	if (symbol_conf.use_callchain)
-		self->tree = newtCheckboxTreeMulti(0, 0, rows - 5, seq,
-						   NEWT_FLAG_SCROLL);
-	else
-		self->tree = newtListbox(0, 0, rows - 5,
-					(NEWT_FLAG_SCROLL |
-					 NEWT_FLAG_RETURNEXIT));
-
-	newtComponentAddCallback(self->tree, hist_browser__selection,
-				 &self->selection);
-
-	progress = ui_progress__new("Adding entries to the browser...",
-				    hists->nr_entries);
-	if (progress == NULL)
-		return -1;
-
-	idx = 0;
-	for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
-		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
-		int len;
-
-		if (h->filtered)
-			continue;
-
-		len = hist_entry__append_browser(h, self->tree, hists->stats.total_period);
-		if (len > max_len)
-			max_len = len;
-		if (symbol_conf.use_callchain)
-			hist_entry__append_callchain_browser(h, self->tree,
-							     hists->stats.total_period, idx++);
-		++curr_hist;
-		if (curr_hist % 5)
-			ui_progress__update(progress, curr_hist);
-	}
-
-	ui_progress__delete(progress);
-
-	newtGetScreenSize(&cols, &rows);
-
-	if (max_len > cols)
-		max_len = cols - 3;
-
-	if (!symbol_conf.use_callchain)
-		newtListboxSetWidth(self->tree, max_len);
-
-	newtCenteredWindow(max_len + (symbol_conf.use_callchain ? 5 : 0),
-			   rows - 5, title);
-	self->form = newt_form__new();
-	if (self->form == NULL)
-		return -1;
-
-	newtFormAddHotKey(self->form, 'A');
-	newtFormAddHotKey(self->form, 'a');
-	newtFormAddHotKey(self->form, 'D');
-	newtFormAddHotKey(self->form, 'd');
-	newtFormAddHotKey(self->form, 'T');
-	newtFormAddHotKey(self->form, 't');
-	newtFormAddHotKey(self->form, '?');
-	newtFormAddHotKey(self->form, 'H');
-	newtFormAddHotKey(self->form, 'h');
-	newtFormAddHotKey(self->form, NEWT_KEY_F1);
-	newtFormAddHotKey(self->form, NEWT_KEY_RIGHT);
-	newtFormAddHotKey(self->form, NEWT_KEY_TAB);
-	newtFormAddHotKey(self->form, NEWT_KEY_UNTAB);
-	newtFormAddComponents(self->form, self->tree, NULL);
-	self->selection = newt__symbol_tree_get_current(self->tree);
-
-	return 0;
-}
-
-static struct hist_entry *hist_browser__selected_entry(struct hist_browser *self)
-{
-	int *indexes;
-
-	if (!symbol_conf.use_callchain)
-		goto out;
-
-	indexes = newtCheckboxTreeFindItem(self->tree, (void *)self->selection);
-	if (indexes) {
-		bool is_hist_entry = indexes[1] == NEWT_ARG_LAST;
-		free(indexes);
-		if (is_hist_entry)
-			goto out;
-	}
-	return NULL;
-out:
-	return container_of(self->selection, struct hist_entry, ms);
-}
-
-static struct thread *hist_browser__selected_thread(struct hist_browser *self)
-{
-	struct hist_entry *he = hist_browser__selected_entry(self);
-	return he ? he->thread : NULL;
-}
-
-static int hist_browser__title(char *bf, size_t size, const char *ev_name,
-			       const struct dso *dso, const struct thread *thread)
-{
-	int printed = 0;
-
-	if (thread)
-		printed += snprintf(bf + printed, size - printed,
-				    "Thread: %s(%d)",
-				    (thread->comm_set ?  thread->comm : ""),
-				    thread->pid);
-	if (dso)
-		printed += snprintf(bf + printed, size - printed,
-				    "%sDSO: %s", thread ? " " : "",
-				    dso->short_name);
-	return printed ?: snprintf(bf, size, "Event: %s", ev_name);
-}
-
-int hists__browse(struct hists *self, const char *helpline, const char *ev_name)
-{
-	struct hist_browser *browser = hist_browser__new();
-	struct pstack *fstack;
-	const struct thread *thread_filter = NULL;
-	const struct dso *dso_filter = NULL;
-	struct newtExitStruct es;
-	char msg[160];
-	int key = -1;
-
-	if (browser == NULL)
-		return -1;
-
-	fstack = pstack__new(2);
-	if (fstack == NULL)
-		goto out;
-
-	ui_helpline__push(helpline);
-
-	hist_browser__title(msg, sizeof(msg), ev_name,
-			    dso_filter, thread_filter);
-	if (hist_browser__populate(browser, self, msg) < 0)
-		goto out_free_stack;
-
-	while (1) {
-		const struct thread *thread;
-		const struct dso *dso;
-		char *options[16];
-		int nr_options = 0, choice = 0, i,
-		    annotate = -2, zoom_dso = -2, zoom_thread = -2;
-
-		newtFormRun(browser->form, &es);
-
-		thread = hist_browser__selected_thread(browser);
-		dso = browser->selection->map ? browser->selection->map->dso : NULL;
-
-		if (es.reason == NEWT_EXIT_HOTKEY) {
-			key = es.u.key;
-
-			switch (key) {
-			case NEWT_KEY_F1:
-				goto do_help;
-			case NEWT_KEY_TAB:
-			case NEWT_KEY_UNTAB:
-				/*
-				 * Exit the browser, let hists__browser_tree
-				 * go to the next or previous
-				 */
-				goto out_free_stack;
-			default:;
-			}
-
-			key = toupper(key);
-			switch (key) {
-			case 'A':
-				if (browser->selection->map == NULL &&
-				    browser->selection->map->dso->annotate_warned)
-					continue;
-				goto do_annotate;
-			case 'D':
-				goto zoom_dso;
-			case 'T':
-				goto zoom_thread;
-			case 'H':
-			case '?':
-do_help:
-				ui__help_window("->        Zoom into DSO/Threads & Annotate current symbol\n"
-						"<-        Zoom out\n"
-						"a         Annotate current symbol\n"
-						"h/?/F1    Show this window\n"
-						"d         Zoom into current DSO\n"
-						"t         Zoom into current Thread\n"
-						"q/CTRL+C  Exit browser");
-				continue;
-			default:;
-			}
-			if (is_exit_key(key)) {
-				if (key == NEWT_KEY_ESCAPE) {
-					if (dialog_yesno("Do you really want to exit?"))
-						break;
-					else
-						continue;
-				} else
-					break;
-			}
-
-			if (es.u.key == NEWT_KEY_LEFT) {
-				const void *top;
-
-				if (pstack__empty(fstack))
-					continue;
-				top = pstack__pop(fstack);
-				if (top == &dso_filter)
-					goto zoom_out_dso;
-				if (top == &thread_filter)
-					goto zoom_out_thread;
-				continue;
-			}
-		}
-
-		if (browser->selection->sym != NULL &&
-		    !browser->selection->map->dso->annotate_warned &&
-		    asprintf(&options[nr_options], "Annotate %s",
-			     browser->selection->sym->name) > 0)
-			annotate = nr_options++;
-
-		if (thread != NULL &&
-		    asprintf(&options[nr_options], "Zoom %s %s(%d) thread",
-			     (thread_filter ? "out of" : "into"),
-			     (thread->comm_set ? thread->comm : ""),
-			     thread->pid) > 0)
-			zoom_thread = nr_options++;
-
-		if (dso != NULL &&
-		    asprintf(&options[nr_options], "Zoom %s %s DSO",
-			     (dso_filter ? "out of" : "into"),
-			     (dso->kernel ? "the Kernel" : dso->short_name)) > 0)
-			zoom_dso = nr_options++;
-
-		options[nr_options++] = (char *)"Exit";
-
-		choice = popup_menu(nr_options, options);
-
-		for (i = 0; i < nr_options - 1; ++i)
-			free(options[i]);
-
-		if (choice == nr_options - 1)
-			break;
-
-		if (choice == -1)
-			continue;
-
-		if (choice == annotate) {
-			struct hist_entry *he;
-do_annotate:
-			if (browser->selection->map->dso->origin == DSO__ORIG_KERNEL) {
-				browser->selection->map->dso->annotate_warned = 1;
-				ui_helpline__puts("No vmlinux file found, can't "
-						 "annotate with just a "
-						 "kallsyms file");
-				continue;
-			}
-
-			he = hist_browser__selected_entry(browser);
-			if (he == NULL)
-				continue;
-
-			hist_entry__tui_annotate(he);
-		} else if (choice == zoom_dso) {
-zoom_dso:
-			if (dso_filter) {
-				pstack__remove(fstack, &dso_filter);
-zoom_out_dso:
-				ui_helpline__pop();
-				dso_filter = NULL;
-			} else {
-				if (dso == NULL)
-					continue;
-				ui_helpline__fpush("To zoom out press <- or -> + \"Zoom out of %s DSO\"",
-						   dso->kernel ? "the Kernel" : dso->short_name);
-				dso_filter = dso;
-				pstack__push(fstack, &dso_filter);
-			}
-			hists__filter_by_dso(self, dso_filter);
-			hist_browser__title(msg, sizeof(msg), ev_name,
-					    dso_filter, thread_filter);
-			if (hist_browser__populate(browser, self, msg) < 0)
-				goto out;
-		} else if (choice == zoom_thread) {
-zoom_thread:
-			if (thread_filter) {
-				pstack__remove(fstack, &thread_filter);
-zoom_out_thread:
-				ui_helpline__pop();
-				thread_filter = NULL;
-			} else {
-				ui_helpline__fpush("To zoom out press <- or -> + \"Zoom out of %s(%d) thread\"",
-						   thread->comm_set ? thread->comm : "",
-						   thread->pid);
-				thread_filter = thread;
-				pstack__push(fstack, &thread_filter);
-			}
-			hists__filter_by_thread(self, thread_filter);
-			hist_browser__title(msg, sizeof(msg), ev_name,
-					    dso_filter, thread_filter);
-			if (hist_browser__populate(browser, self, msg) < 0)
-				goto out;
-		}
-	}
-out_free_stack:
-	pstack__delete(fstack);
-out:
-	hist_browser__delete(browser);
-	return key;
-}
-
-int hists__tui_browse_tree(struct rb_root *self, const char *help)
-{
-	struct rb_node *first = rb_first(self), *nd = first, *next;
-	int key = 0;
-
-	while (nd) {
-		struct hists *hists = rb_entry(nd, struct hists, rb_node);
-		const char *ev_name = __event_name(hists->type, hists->config);
-
-		key = hists__browse(hists, help, ev_name);
-
-		if (is_exit_key(key))
-			break;
-
-		switch (key) {
-		case NEWT_KEY_TAB:
-			next = rb_next(nd);
-			if (next)
-				nd = next;
-			break;
-		case NEWT_KEY_UNTAB:
-			if (nd == first)
-				continue;
-			nd = rb_prev(nd);
-		default:
-			break;
-		}
-	}
-
-	return key;
-}
-
-static struct newtPercentTreeColors {
-	const char *topColorFg, *topColorBg;
-	const char *mediumColorFg, *mediumColorBg;
-	const char *normalColorFg, *normalColorBg;
-	const char *selColorFg, *selColorBg;
-	const char *codeColorFg, *codeColorBg;
-} defaultPercentTreeColors = {
-	"red",       "lightgray",
-	"green",     "lightgray",
-	"black",     "lightgray",
-	"lightgray", "magenta",
-	"blue",	     "lightgray",
-};
-
-void setup_browser(void)
-{
-	struct newtPercentTreeColors *c = &defaultPercentTreeColors;
-
-	if (!isatty(1) || !use_browser || dump_trace) {
-		use_browser = 0;
-		setup_pager();
-		return;
-	}
-
-	use_browser = 1;
-	newtInit();
-	newtCls();
-	ui_helpline__puts(" ");
-	sltt_set_color(HE_COLORSET_TOP, NULL, c->topColorFg, c->topColorBg);
-	sltt_set_color(HE_COLORSET_MEDIUM, NULL, c->mediumColorFg, c->mediumColorBg);
-	sltt_set_color(HE_COLORSET_NORMAL, NULL, c->normalColorFg, c->normalColorBg);
-	sltt_set_color(HE_COLORSET_SELECTED, NULL, c->selColorFg, c->selColorBg);
-	sltt_set_color(HE_COLORSET_CODE, NULL, c->codeColorFg, c->codeColorBg);
-}
-
-void exit_browser(bool wait_for_ok)
-{
-	if (use_browser > 0) {
-		if (wait_for_ok) {
-			char title[] = "Fatal Error", ok[] = "Ok";
-			newtWinMessage(title, ok, browser__last_msg);
-		}
-		newtFinished();
-	}
-}
diff --git a/tools/perf/util/pager.c b/tools/perf/util/pager.c
index 1915de20dca..31ee02d4e98 100644
--- a/tools/perf/util/pager.c
+++ b/tools/perf/util/pager.c
@@ -57,9 +57,13 @@ void setup_pager(void)
 	}
 	if (!pager)
 		pager = getenv("PAGER");
+	if (!(pager || access("/usr/bin/pager", X_OK)))
+		pager = "/usr/bin/pager";
+	if (!(pager || access("/usr/bin/less", X_OK)))
+		pager = "/usr/bin/less";
 	if (!pager)
-		pager = "less";
-	else if (!*pager || !strcmp(pager, "cat"))
+		pager = "cat";
+	if (!*pager || !strcmp(pager, "cat"))
 		return;
 
 	spawned_pager = 1; /* means we are emitting to terminal */
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 9bf0f402ca7..1e15df10a88 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1,130 +1,128 @@
-#include "../../../include/linux/hw_breakpoint.h"
+#include <linux/hw_breakpoint.h>
 #include "util.h"
 #include "../perf.h"
+#include "evlist.h"
+#include "evsel.h"
 #include "parse-options.h"
 #include "parse-events.h"
 #include "exec_cmd.h"
-#include "string.h"
+#include "linux/string.h"
 #include "symbol.h"
 #include "cache.h"
 #include "header.h"
-#include "debugfs.h"
+#include <api/fs/debugfs.h>
+#include "parse-events-bison.h"
+#define YY_EXTRA_TYPE int
+#include "parse-events-flex.h"
+#include "pmu.h"
+#include "thread_map.h"
 
-int				nr_counters;
-
-struct perf_event_attr		attrs[MAX_COUNTERS];
-char				*filters[MAX_COUNTERS];
+#define MAX_NAME_LEN 100
 
 struct event_symbol {
-	u8		type;
-	u64		config;
 	const char	*symbol;
 	const char	*alias;
 };
 
-enum event_result {
-	EVT_FAILED,
-	EVT_HANDLED,
-	EVT_HANDLED_ALL
+#ifdef PARSER_DEBUG
+extern int parse_events_debug;
+#endif
+int parse_events_parse(void *data, void *scanner);
+
+static struct event_symbol event_symbols_hw[PERF_COUNT_HW_MAX] = {
+	[PERF_COUNT_HW_CPU_CYCLES] = {
+		.symbol = "cpu-cycles",
+		.alias  = "cycles",
+	},
+	[PERF_COUNT_HW_INSTRUCTIONS] = {
+		.symbol = "instructions",
+		.alias  = "",
+	},
+	[PERF_COUNT_HW_CACHE_REFERENCES] = {
+		.symbol = "cache-references",
+		.alias  = "",
+	},
+	[PERF_COUNT_HW_CACHE_MISSES] = {
+		.symbol = "cache-misses",
+		.alias  = "",
+	},
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = {
+		.symbol = "branch-instructions",
+		.alias  = "branches",
+	},
+	[PERF_COUNT_HW_BRANCH_MISSES] = {
+		.symbol = "branch-misses",
+		.alias  = "",
+	},
+	[PERF_COUNT_HW_BUS_CYCLES] = {
+		.symbol = "bus-cycles",
+		.alias  = "",
+	},
+	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = {
+		.symbol = "stalled-cycles-frontend",
+		.alias  = "idle-cycles-frontend",
+	},
+	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = {
+		.symbol = "stalled-cycles-backend",
+		.alias  = "idle-cycles-backend",
+	},
+	[PERF_COUNT_HW_REF_CPU_CYCLES] = {
+		.symbol = "ref-cycles",
+		.alias  = "",
+	},
 };
 
-char debugfs_path[MAXPATHLEN];
-
-#define CHW(x) .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_##x
-#define CSW(x) .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_##x
-
-static struct event_symbol event_symbols[] = {
-  { CHW(CPU_CYCLES),		"cpu-cycles",		"cycles"	},
-  { CHW(INSTRUCTIONS),		"instructions",		""		},
-  { CHW(CACHE_REFERENCES),	"cache-references",	""		},
-  { CHW(CACHE_MISSES),		"cache-misses",		""		},
-  { CHW(BRANCH_INSTRUCTIONS),	"branch-instructions",	"branches"	},
-  { CHW(BRANCH_MISSES),		"branch-misses",	""		},
-  { CHW(BUS_CYCLES),		"bus-cycles",		""		},
-
-  { CSW(CPU_CLOCK),		"cpu-clock",		""		},
-  { CSW(TASK_CLOCK),		"task-clock",		""		},
-  { CSW(PAGE_FAULTS),		"page-faults",		"faults"	},
-  { CSW(PAGE_FAULTS_MIN),	"minor-faults",		""		},
-  { CSW(PAGE_FAULTS_MAJ),	"major-faults",		""		},
-  { CSW(CONTEXT_SWITCHES),	"context-switches",	"cs"		},
-  { CSW(CPU_MIGRATIONS),	"cpu-migrations",	"migrations"	},
-  { CSW(ALIGNMENT_FAULTS),	"alignment-faults",	""		},
-  { CSW(EMULATION_FAULTS),	"emulation-faults",	""		},
+static struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = {
+	[PERF_COUNT_SW_CPU_CLOCK] = {
+		.symbol = "cpu-clock",
+		.alias  = "",
+	},
+	[PERF_COUNT_SW_TASK_CLOCK] = {
+		.symbol = "task-clock",
+		.alias  = "",
+	},
+	[PERF_COUNT_SW_PAGE_FAULTS] = {
+		.symbol = "page-faults",
+		.alias  = "faults",
+	},
+	[PERF_COUNT_SW_CONTEXT_SWITCHES] = {
+		.symbol = "context-switches",
+		.alias  = "cs",
+	},
+	[PERF_COUNT_SW_CPU_MIGRATIONS] = {
+		.symbol = "cpu-migrations",
+		.alias  = "migrations",
+	},
+	[PERF_COUNT_SW_PAGE_FAULTS_MIN] = {
+		.symbol = "minor-faults",
+		.alias  = "",
+	},
+	[PERF_COUNT_SW_PAGE_FAULTS_MAJ] = {
+		.symbol = "major-faults",
+		.alias  = "",
+	},
+	[PERF_COUNT_SW_ALIGNMENT_FAULTS] = {
+		.symbol = "alignment-faults",
+		.alias  = "",
+	},
+	[PERF_COUNT_SW_EMULATION_FAULTS] = {
+		.symbol = "emulation-faults",
+		.alias  = "",
+	},
+	[PERF_COUNT_SW_DUMMY] = {
+		.symbol = "dummy",
+		.alias  = "",
+	},
 };
 
 #define __PERF_EVENT_FIELD(config, name) \
 	((config & PERF_EVENT_##name##_MASK) >> PERF_EVENT_##name##_SHIFT)
 
-#define PERF_EVENT_RAW(config)	__PERF_EVENT_FIELD(config, RAW)
+#define PERF_EVENT_RAW(config)		__PERF_EVENT_FIELD(config, RAW)
 #define PERF_EVENT_CONFIG(config)	__PERF_EVENT_FIELD(config, CONFIG)
-#define PERF_EVENT_TYPE(config)	__PERF_EVENT_FIELD(config, TYPE)
+#define PERF_EVENT_TYPE(config)		__PERF_EVENT_FIELD(config, TYPE)
 #define PERF_EVENT_ID(config)		__PERF_EVENT_FIELD(config, EVENT)
 
-static const char *hw_event_names[] = {
-	"cycles",
-	"instructions",
-	"cache-references",
-	"cache-misses",
-	"branches",
-	"branch-misses",
-	"bus-cycles",
-};
-
-static const char *sw_event_names[] = {
-	"cpu-clock-msecs",
-	"task-clock-msecs",
-	"page-faults",
-	"context-switches",
-	"CPU-migrations",
-	"minor-faults",
-	"major-faults",
-	"alignment-faults",
-	"emulation-faults",
-};
-
-#define MAX_ALIASES 8
-
-static const char *hw_cache[][MAX_ALIASES] = {
- { "L1-dcache",	"l1-d",		"l1d",		"L1-data",		},
- { "L1-icache",	"l1-i",		"l1i",		"L1-instruction",	},
- { "LLC",	"L2"							},
- { "dTLB",	"d-tlb",	"Data-TLB",				},
- { "iTLB",	"i-tlb",	"Instruction-TLB",			},
- { "branch",	"branches",	"bpu",		"btb",		"bpc",	},
-};
-
-static const char *hw_cache_op[][MAX_ALIASES] = {
- { "load",	"loads",	"read",					},
- { "store",	"stores",	"write",				},
- { "prefetch",	"prefetches",	"speculative-read", "speculative-load",	},
-};
-
-static const char *hw_cache_result[][MAX_ALIASES] = {
- { "refs",	"Reference",	"ops",		"access",		},
- { "misses",	"miss",							},
-};
-
-#define C(x)		PERF_COUNT_HW_CACHE_##x
-#define CACHE_READ	(1 << C(OP_READ))
-#define CACHE_WRITE	(1 << C(OP_WRITE))
-#define CACHE_PREFETCH	(1 << C(OP_PREFETCH))
-#define COP(x)		(1 << x)
-
-/*
- * cache operartion stat
- * L1I : Read and prefetch only
- * ITLB and BPU : Read-only
- */
-static unsigned long hw_cache_stat[C(MAX)] = {
- [C(L1D)]	= (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH),
- [C(L1I)]	= (CACHE_READ | CACHE_PREFETCH),
- [C(LL)]	= (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH),
- [C(DTLB)]	= (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH),
- [C(ITLB)]	= (CACHE_READ),
- [C(BPU)]	= (CACHE_READ),
-};
-
 #define for_each_subsystem(sys_dir, sys_dirent, sys_next)	       \
 	while (!readdir_r(sys_dir, &sys_dirent, &sys_next) && sys_next)	       \
 	if (sys_dirent.d_type == DT_DIR &&				       \
@@ -136,7 +134,7 @@ static int tp_event_has_id(struct dirent *sys_dir, struct dirent *evt_dir)
 	char evt_path[MAXPATHLEN];
 	int fd;
 
-	snprintf(evt_path, MAXPATHLEN, "%s/%s/%s/id", debugfs_path,
+	snprintf(evt_path, MAXPATHLEN, "%s/%s/%s/id", tracing_events_path,
 			sys_dir->d_name, evt_dir->d_name);
 	fd = open(evt_path, O_RDONLY);
 	if (fd < 0)
@@ -161,22 +159,22 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config)
 	struct tracepoint_path *path = NULL;
 	DIR *sys_dir, *evt_dir;
 	struct dirent *sys_next, *evt_next, sys_dirent, evt_dirent;
-	char id_buf[4];
+	char id_buf[24];
 	int fd;
 	u64 id;
 	char evt_path[MAXPATHLEN];
 	char dir_path[MAXPATHLEN];
 
-	if (debugfs_valid_mountpoint(debugfs_path))
+	if (debugfs_valid_mountpoint(tracing_events_path))
 		return NULL;
 
-	sys_dir = opendir(debugfs_path);
+	sys_dir = opendir(tracing_events_path);
 	if (!sys_dir)
 		return NULL;
 
 	for_each_subsystem(sys_dir, sys_dirent, sys_next) {
 
-		snprintf(dir_path, MAXPATHLEN, "%s/%s", debugfs_path,
+		snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path,
 			 sys_dirent.d_name);
 		evt_dir = opendir(dir_path);
 		if (!evt_dir)
@@ -206,7 +204,7 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config)
 				}
 				path->name = malloc(MAX_EVENT_LENGTH);
 				if (!path->name) {
-					free(path->system);
+					zfree(&path->system);
 					free(path);
 					return NULL;
 				}
@@ -224,99 +222,43 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config)
 	return NULL;
 }
 
-#define TP_PATH_LEN (MAX_EVENT_LENGTH * 2 + 1)
-static const char *tracepoint_id_to_name(u64 config)
+struct tracepoint_path *tracepoint_name_to_path(const char *name)
 {
-	static char buf[TP_PATH_LEN];
-	struct tracepoint_path *path;
+	struct tracepoint_path *path = zalloc(sizeof(*path));
+	char *str = strchr(name, ':');
 
-	path = tracepoint_id_to_path(config);
-	if (path) {
-		snprintf(buf, TP_PATH_LEN, "%s:%s", path->system, path->name);
-		free(path->name);
-		free(path->system);
+	if (path == NULL || str == NULL) {
 		free(path);
-	} else
-		snprintf(buf, TP_PATH_LEN, "%s:%s", "unknown", "unknown");
-
-	return buf;
-}
-
-static int is_cache_op_valid(u8 cache_type, u8 cache_op)
-{
-	if (hw_cache_stat[cache_type] & COP(cache_op))
-		return 1;	/* valid */
-	else
-		return 0;	/* invalid */
-}
-
-static char *event_cache_name(u8 cache_type, u8 cache_op, u8 cache_result)
-{
-	static char name[50];
-
-	if (cache_result) {
-		sprintf(name, "%s-%s-%s", hw_cache[cache_type][0],
-			hw_cache_op[cache_op][0],
-			hw_cache_result[cache_result][0]);
-	} else {
-		sprintf(name, "%s-%s", hw_cache[cache_type][0],
-			hw_cache_op[cache_op][1]);
+		return NULL;
 	}
 
-	return name;
-}
+	path->system = strndup(name, str - name);
+	path->name = strdup(str+1);
 
-const char *event_name(int counter)
-{
-	u64 config = attrs[counter].config;
-	int type = attrs[counter].type;
+	if (path->system == NULL || path->name == NULL) {
+		zfree(&path->system);
+		zfree(&path->name);
+		free(path);
+		path = NULL;
+	}
 
-	return __event_name(type, config);
+	return path;
 }
 
-const char *__event_name(int type, u64 config)
+const char *event_type(int type)
 {
-	static char buf[32];
-
-	if (type == PERF_TYPE_RAW) {
-		sprintf(buf, "raw 0x%llx", config);
-		return buf;
-	}
-
 	switch (type) {
 	case PERF_TYPE_HARDWARE:
-		if (config < PERF_COUNT_HW_MAX)
-			return hw_event_names[config];
-		return "unknown-hardware";
-
-	case PERF_TYPE_HW_CACHE: {
-		u8 cache_type, cache_op, cache_result;
-
-		cache_type   = (config >>  0) & 0xff;
-		if (cache_type > PERF_COUNT_HW_CACHE_MAX)
-			return "unknown-ext-hardware-cache-type";
-
-		cache_op     = (config >>  8) & 0xff;
-		if (cache_op > PERF_COUNT_HW_CACHE_OP_MAX)
-			return "unknown-ext-hardware-cache-op";
-
-		cache_result = (config >> 16) & 0xff;
-		if (cache_result > PERF_COUNT_HW_CACHE_RESULT_MAX)
-			return "unknown-ext-hardware-cache-result";
-
-		if (!is_cache_op_valid(cache_type, cache_op))
-			return "invalid-cache";
-
-		return event_cache_name(cache_type, cache_op, cache_result);
-	}
+		return "hardware";
 
 	case PERF_TYPE_SOFTWARE:
-		if (config < PERF_COUNT_SW_MAX)
-			return sw_event_names[config];
-		return "unknown-software";
+		return "software";
 
 	case PERF_TYPE_TRACEPOINT:
-		return tracepoint_id_to_name(config);
+		return "tracepoint";
+
+	case PERF_TYPE_HW_CACHE:
+		return "hardware-cache";
 
 	default:
 		break;
@@ -325,66 +267,93 @@ const char *__event_name(int type, u64 config)
 	return "unknown";
 }
 
-static int parse_aliases(const char **str, const char *names[][MAX_ALIASES], int size)
+
+
+static struct perf_evsel *
+__add_event(struct list_head *list, int *idx,
+	    struct perf_event_attr *attr,
+	    char *name, struct cpu_map *cpus)
+{
+	struct perf_evsel *evsel;
+
+	event_attr_init(attr);
+
+	evsel = perf_evsel__new_idx(attr, (*idx)++);
+	if (!evsel)
+		return NULL;
+
+	evsel->cpus = cpus;
+	if (name)
+		evsel->name = strdup(name);
+	list_add_tail(&evsel->node, list);
+	return evsel;
+}
+
+static int add_event(struct list_head *list, int *idx,
+		     struct perf_event_attr *attr, char *name)
+{
+	return __add_event(list, idx, attr, name, NULL) ? 0 : -ENOMEM;
+}
+
+static int parse_aliases(char *str, const char *names[][PERF_EVSEL__MAX_ALIASES], int size)
 {
 	int i, j;
 	int n, longest = -1;
 
 	for (i = 0; i < size; i++) {
-		for (j = 0; j < MAX_ALIASES && names[i][j]; j++) {
+		for (j = 0; j < PERF_EVSEL__MAX_ALIASES && names[i][j]; j++) {
 			n = strlen(names[i][j]);
-			if (n > longest && !strncasecmp(*str, names[i][j], n))
+			if (n > longest && !strncasecmp(str, names[i][j], n))
 				longest = n;
 		}
-		if (longest > 0) {
-			*str += longest;
+		if (longest > 0)
 			return i;
-		}
 	}
 
 	return -1;
 }
 
-static enum event_result
-parse_generic_hw_event(const char **str, struct perf_event_attr *attr)
+int parse_events_add_cache(struct list_head *list, int *idx,
+			   char *type, char *op_result1, char *op_result2)
 {
-	const char *s = *str;
+	struct perf_event_attr attr;
+	char name[MAX_NAME_LEN];
 	int cache_type = -1, cache_op = -1, cache_result = -1;
+	char *op_result[2] = { op_result1, op_result2 };
+	int i, n;
 
-	cache_type = parse_aliases(&s, hw_cache, PERF_COUNT_HW_CACHE_MAX);
 	/*
 	 * No fallback - if we cannot get a clear cache type
 	 * then bail out:
 	 */
+	cache_type = parse_aliases(type, perf_evsel__hw_cache,
+				   PERF_COUNT_HW_CACHE_MAX);
 	if (cache_type == -1)
-		return EVT_FAILED;
+		return -EINVAL;
+
+	n = snprintf(name, MAX_NAME_LEN, "%s", type);
+
+	for (i = 0; (i < 2) && (op_result[i]); i++) {
+		char *str = op_result[i];
 
-	while ((cache_op == -1 || cache_result == -1) && *s == '-') {
-		++s;
+		n += snprintf(name + n, MAX_NAME_LEN - n, "-%s", str);
 
 		if (cache_op == -1) {
-			cache_op = parse_aliases(&s, hw_cache_op,
-						PERF_COUNT_HW_CACHE_OP_MAX);
+			cache_op = parse_aliases(str, perf_evsel__hw_cache_op,
+						 PERF_COUNT_HW_CACHE_OP_MAX);
 			if (cache_op >= 0) {
-				if (!is_cache_op_valid(cache_type, cache_op))
-					return 0;
+				if (!perf_evsel__is_cache_op_valid(cache_type, cache_op))
+					return -EINVAL;
 				continue;
 			}
 		}
 
 		if (cache_result == -1) {
-			cache_result = parse_aliases(&s, hw_cache_result,
-						PERF_COUNT_HW_CACHE_RESULT_MAX);
+			cache_result = parse_aliases(str, perf_evsel__hw_cache_result,
+						     PERF_COUNT_HW_CACHE_RESULT_MAX);
 			if (cache_result >= 0)
 				continue;
 		}
-
-		/*
-		 * Can't parse this as a cache op or result, so back up
-		 * to the '-'.
-		 */
-		--s;
-		break;
 	}
 
 	/*
@@ -399,300 +368,361 @@ parse_generic_hw_event(const char **str, struct perf_event_attr *attr)
 	if (cache_result == -1)
 		cache_result = PERF_COUNT_HW_CACHE_RESULT_ACCESS;
 
-	attr->config = cache_type | (cache_op << 8) | (cache_result << 16);
-	attr->type = PERF_TYPE_HW_CACHE;
-
-	*str = s;
-	return EVT_HANDLED;
+	memset(&attr, 0, sizeof(attr));
+	attr.config = cache_type | (cache_op << 8) | (cache_result << 16);
+	attr.type = PERF_TYPE_HW_CACHE;
+	return add_event(list, idx, &attr, name);
 }
 
-static enum event_result
-parse_single_tracepoint_event(char *sys_name,
-			      const char *evt_name,
-			      unsigned int evt_length,
-			      struct perf_event_attr *attr,
-			      const char **strp)
+static int add_tracepoint(struct list_head *list, int *idx,
+			  char *sys_name, char *evt_name)
 {
-	char evt_path[MAXPATHLEN];
-	char id_buf[4];
-	u64 id;
-	int fd;
-
-	snprintf(evt_path, MAXPATHLEN, "%s/%s/%s/id", debugfs_path,
-		 sys_name, evt_name);
-
-	fd = open(evt_path, O_RDONLY);
-	if (fd < 0)
-		return EVT_FAILED;
-
-	if (read(fd, id_buf, sizeof(id_buf)) < 0) {
-		close(fd);
-		return EVT_FAILED;
-	}
-
-	close(fd);
-	id = atoll(id_buf);
-	attr->config = id;
-	attr->type = PERF_TYPE_TRACEPOINT;
-	*strp = evt_name + evt_length;
+	struct perf_evsel *evsel;
 
-	attr->sample_type |= PERF_SAMPLE_RAW;
-	attr->sample_type |= PERF_SAMPLE_TIME;
-	attr->sample_type |= PERF_SAMPLE_CPU;
+	evsel = perf_evsel__newtp_idx(sys_name, evt_name, (*idx)++);
+	if (!evsel)
+		return -ENOMEM;
 
-	attr->sample_period = 1;
+	list_add_tail(&evsel->node, list);
 
-
-	return EVT_HANDLED;
+	return 0;
 }
 
-/* sys + ':' + event + ':' + flags*/
-#define MAX_EVOPT_LEN	(MAX_EVENT_LENGTH * 2 + 2 + 128)
-static enum event_result
-parse_multiple_tracepoint_event(char *sys_name, const char *evt_exp,
-				char *flags)
+static int add_tracepoint_multi_event(struct list_head *list, int *idx,
+				      char *sys_name, char *evt_name)
 {
 	char evt_path[MAXPATHLEN];
 	struct dirent *evt_ent;
 	DIR *evt_dir;
+	int ret = 0;
 
-	snprintf(evt_path, MAXPATHLEN, "%s/%s", debugfs_path, sys_name);
+	snprintf(evt_path, MAXPATHLEN, "%s/%s", tracing_events_path, sys_name);
 	evt_dir = opendir(evt_path);
-
 	if (!evt_dir) {
 		perror("Can't open event dir");
-		return EVT_FAILED;
+		return -1;
 	}
 
-	while ((evt_ent = readdir(evt_dir))) {
-		char event_opt[MAX_EVOPT_LEN + 1];
-		int len;
-
+	while (!ret && (evt_ent = readdir(evt_dir))) {
 		if (!strcmp(evt_ent->d_name, ".")
 		    || !strcmp(evt_ent->d_name, "..")
 		    || !strcmp(evt_ent->d_name, "enable")
 		    || !strcmp(evt_ent->d_name, "filter"))
 			continue;
 
-		if (!strglobmatch(evt_ent->d_name, evt_exp))
+		if (!strglobmatch(evt_ent->d_name, evt_name))
 			continue;
 
-		len = snprintf(event_opt, MAX_EVOPT_LEN, "%s:%s%s%s", sys_name,
-			       evt_ent->d_name, flags ? ":" : "",
-			       flags ?: "");
-		if (len < 0)
-			return EVT_FAILED;
-
-		if (parse_events(NULL, event_opt, 0))
-			return EVT_FAILED;
+		ret = add_tracepoint(list, idx, sys_name, evt_ent->d_name);
 	}
 
-	return EVT_HANDLED_ALL;
+	closedir(evt_dir);
+	return ret;
 }
 
-
-static enum event_result parse_tracepoint_event(const char **strp,
-				    struct perf_event_attr *attr)
+static int add_tracepoint_event(struct list_head *list, int *idx,
+				char *sys_name, char *evt_name)
 {
-	const char *evt_name;
-	char *flags;
-	char sys_name[MAX_EVENT_LENGTH];
-	unsigned int sys_length, evt_length;
+	return strpbrk(evt_name, "*?") ?
+	       add_tracepoint_multi_event(list, idx, sys_name, evt_name) :
+	       add_tracepoint(list, idx, sys_name, evt_name);
+}
 
-	if (debugfs_valid_mountpoint(debugfs_path))
-		return 0;
+static int add_tracepoint_multi_sys(struct list_head *list, int *idx,
+				    char *sys_name, char *evt_name)
+{
+	struct dirent *events_ent;
+	DIR *events_dir;
+	int ret = 0;
 
-	evt_name = strchr(*strp, ':');
-	if (!evt_name)
-		return EVT_FAILED;
+	events_dir = opendir(tracing_events_path);
+	if (!events_dir) {
+		perror("Can't open event dir");
+		return -1;
+	}
 
-	sys_length = evt_name - *strp;
-	if (sys_length >= MAX_EVENT_LENGTH)
-		return 0;
+	while (!ret && (events_ent = readdir(events_dir))) {
+		if (!strcmp(events_ent->d_name, ".")
+		    || !strcmp(events_ent->d_name, "..")
+		    || !strcmp(events_ent->d_name, "enable")
+		    || !strcmp(events_ent->d_name, "header_event")
+		    || !strcmp(events_ent->d_name, "header_page"))
+			continue;
 
-	strncpy(sys_name, *strp, sys_length);
-	sys_name[sys_length] = '\0';
-	evt_name = evt_name + 1;
+		if (!strglobmatch(events_ent->d_name, sys_name))
+			continue;
 
-	flags = strchr(evt_name, ':');
-	if (flags) {
-		/* split it out: */
-		evt_name = strndup(evt_name, flags - evt_name);
-		flags++;
+		ret = add_tracepoint_event(list, idx, events_ent->d_name,
+					   evt_name);
 	}
 
-	evt_length = strlen(evt_name);
-	if (evt_length >= MAX_EVENT_LENGTH)
-		return EVT_FAILED;
+	closedir(events_dir);
+	return ret;
+}
+
+int parse_events_add_tracepoint(struct list_head *list, int *idx,
+				char *sys, char *event)
+{
+	int ret;
+
+	ret = debugfs_valid_mountpoint(tracing_events_path);
+	if (ret)
+		return ret;
 
-	if (strpbrk(evt_name, "*?")) {
-		*strp = evt_name + evt_length;
-		return parse_multiple_tracepoint_event(sys_name, evt_name,
-						       flags);
-	} else
-		return parse_single_tracepoint_event(sys_name, evt_name,
-						     evt_length, attr, strp);
+	if (strpbrk(sys, "*?"))
+		return add_tracepoint_multi_sys(list, idx, sys, event);
+	else
+		return add_tracepoint_event(list, idx, sys, event);
 }
 
-static enum event_result
-parse_breakpoint_type(const char *type, const char **strp,
-		      struct perf_event_attr *attr)
+static int
+parse_breakpoint_type(const char *type, struct perf_event_attr *attr)
 {
 	int i;
 
 	for (i = 0; i < 3; i++) {
-		if (!type[i])
+		if (!type || !type[i])
 			break;
 
+#define CHECK_SET_TYPE(bit)		\
+do {					\
+	if (attr->bp_type & bit)	\
+		return -EINVAL;		\
+	else				\
+		attr->bp_type |= bit;	\
+} while (0)
+
 		switch (type[i]) {
 		case 'r':
-			attr->bp_type |= HW_BREAKPOINT_R;
+			CHECK_SET_TYPE(HW_BREAKPOINT_R);
 			break;
 		case 'w':
-			attr->bp_type |= HW_BREAKPOINT_W;
+			CHECK_SET_TYPE(HW_BREAKPOINT_W);
 			break;
 		case 'x':
-			attr->bp_type |= HW_BREAKPOINT_X;
+			CHECK_SET_TYPE(HW_BREAKPOINT_X);
 			break;
 		default:
-			return EVT_FAILED;
+			return -EINVAL;
 		}
 	}
+
+#undef CHECK_SET_TYPE
+
 	if (!attr->bp_type) /* Default */
 		attr->bp_type = HW_BREAKPOINT_R | HW_BREAKPOINT_W;
 
-	*strp = type + i;
-
-	return EVT_HANDLED;
+	return 0;
 }
 
-static enum event_result
-parse_breakpoint_event(const char **strp, struct perf_event_attr *attr)
+int parse_events_add_breakpoint(struct list_head *list, int *idx,
+				void *ptr, char *type)
 {
-	const char *target;
-	const char *type;
-	char *endaddr;
-	u64 addr;
-	enum event_result err;
-
-	target = strchr(*strp, ':');
-	if (!target)
-		return EVT_FAILED;
+	struct perf_event_attr attr;
 
-	if (strncmp(*strp, "mem", target - *strp) != 0)
-		return EVT_FAILED;
+	memset(&attr, 0, sizeof(attr));
+	attr.bp_addr = (unsigned long) ptr;
 
-	target++;
+	if (parse_breakpoint_type(type, &attr))
+		return -EINVAL;
 
-	addr = strtoull(target, &endaddr, 0);
-	if (target == endaddr)
-		return EVT_FAILED;
+	/*
+	 * We should find a nice way to override the access length
+	 * Provide some defaults for now
+	 */
+	if (attr.bp_type == HW_BREAKPOINT_X)
+		attr.bp_len = sizeof(long);
+	else
+		attr.bp_len = HW_BREAKPOINT_LEN_4;
 
-	attr->bp_addr = addr;
-	*strp = endaddr;
+	attr.type = PERF_TYPE_BREAKPOINT;
+	attr.sample_period = 1;
 
-	type = strchr(target, ':');
+	return add_event(list, idx, &attr, NULL);
+}
 
-	/* If no type is defined, just rw as default */
-	if (!type) {
-		attr->bp_type = HW_BREAKPOINT_R | HW_BREAKPOINT_W;
-	} else {
-		err = parse_breakpoint_type(++type, strp, attr);
-		if (err == EVT_FAILED)
-			return EVT_FAILED;
+static int config_term(struct perf_event_attr *attr,
+		       struct parse_events_term *term)
+{
+#define CHECK_TYPE_VAL(type)					\
+do {								\
+	if (PARSE_EVENTS__TERM_TYPE_ ## type != term->type_val)	\
+		return -EINVAL;					\
+} while (0)
+
+	switch (term->type_term) {
+	case PARSE_EVENTS__TERM_TYPE_CONFIG:
+		CHECK_TYPE_VAL(NUM);
+		attr->config = term->val.num;
+		break;
+	case PARSE_EVENTS__TERM_TYPE_CONFIG1:
+		CHECK_TYPE_VAL(NUM);
+		attr->config1 = term->val.num;
+		break;
+	case PARSE_EVENTS__TERM_TYPE_CONFIG2:
+		CHECK_TYPE_VAL(NUM);
+		attr->config2 = term->val.num;
+		break;
+	case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD:
+		CHECK_TYPE_VAL(NUM);
+		attr->sample_period = term->val.num;
+		break;
+	case PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE:
+		/*
+		 * TODO uncomment when the field is available
+		 * attr->branch_sample_type = term->val.num;
+		 */
+		break;
+	case PARSE_EVENTS__TERM_TYPE_NAME:
+		CHECK_TYPE_VAL(STR);
+		break;
+	default:
+		return -EINVAL;
 	}
 
-	/* We should find a nice way to override the access type */
-	attr->bp_len = HW_BREAKPOINT_LEN_4;
-	attr->type = PERF_TYPE_BREAKPOINT;
-
-	return EVT_HANDLED;
+	return 0;
+#undef CHECK_TYPE_VAL
 }
 
-static int check_events(const char *str, unsigned int i)
+static int config_attr(struct perf_event_attr *attr,
+		       struct list_head *head, int fail)
 {
-	int n;
+	struct parse_events_term *term;
 
-	n = strlen(event_symbols[i].symbol);
-	if (!strncmp(str, event_symbols[i].symbol, n))
-		return n;
+	list_for_each_entry(term, head, list)
+		if (config_term(attr, term) && fail)
+			return -EINVAL;
 
-	n = strlen(event_symbols[i].alias);
-	if (n)
-		if (!strncmp(str, event_symbols[i].alias, n))
-			return n;
 	return 0;
 }
 
-static enum event_result
-parse_symbolic_event(const char **strp, struct perf_event_attr *attr)
+int parse_events_add_numeric(struct list_head *list, int *idx,
+			     u32 type, u64 config,
+			     struct list_head *head_config)
 {
-	const char *str = *strp;
-	unsigned int i;
-	int n;
+	struct perf_event_attr attr;
 
-	for (i = 0; i < ARRAY_SIZE(event_symbols); i++) {
-		n = check_events(str, i);
-		if (n > 0) {
-			attr->type = event_symbols[i].type;
-			attr->config = event_symbols[i].config;
-			*strp = str + n;
-			return EVT_HANDLED;
-		}
-	}
-	return EVT_FAILED;
+	memset(&attr, 0, sizeof(attr));
+	attr.type = type;
+	attr.config = config;
+
+	if (head_config &&
+	    config_attr(&attr, head_config, 1))
+		return -EINVAL;
+
+	return add_event(list, idx, &attr, NULL);
+}
+
+static int parse_events__is_name_term(struct parse_events_term *term)
+{
+	return term->type_term == PARSE_EVENTS__TERM_TYPE_NAME;
 }
 
-static enum event_result
-parse_raw_event(const char **strp, struct perf_event_attr *attr)
+static char *pmu_event_name(struct list_head *head_terms)
 {
-	const char *str = *strp;
-	u64 config;
-	int n;
+	struct parse_events_term *term;
 
-	if (*str != 'r')
-		return EVT_FAILED;
-	n = hex2u64(str + 1, &config);
-	if (n > 0) {
-		*strp = str + n + 1;
-		attr->type = PERF_TYPE_RAW;
-		attr->config = config;
-		return EVT_HANDLED;
-	}
-	return EVT_FAILED;
+	list_for_each_entry(term, head_terms, list)
+		if (parse_events__is_name_term(term))
+			return term->val.str;
+
+	return NULL;
 }
 
-static enum event_result
-parse_numeric_event(const char **strp, struct perf_event_attr *attr)
+int parse_events_add_pmu(struct list_head *list, int *idx,
+			 char *name, struct list_head *head_config)
 {
-	const char *str = *strp;
-	char *endp;
-	unsigned long type;
-	u64 config;
+	struct perf_event_attr attr;
+	struct perf_pmu *pmu;
+	struct perf_evsel *evsel;
+	const char *unit;
+	double scale;
 
-	type = strtoul(str, &endp, 0);
-	if (endp > str && type < PERF_TYPE_MAX && *endp == ':') {
-		str = endp + 1;
-		config = strtoul(str, &endp, 0);
-		if (endp > str) {
-			attr->type = type;
-			attr->config = config;
-			*strp = endp;
-			return EVT_HANDLED;
-		}
+	pmu = perf_pmu__find(name);
+	if (!pmu)
+		return -EINVAL;
+
+	memset(&attr, 0, sizeof(attr));
+
+	if (perf_pmu__check_alias(pmu, head_config, &unit, &scale))
+		return -EINVAL;
+
+	/*
+	 * Configure hardcoded terms first, no need to check
+	 * return value when called with fail == 0 ;)
+	 */
+	config_attr(&attr, head_config, 0);
+
+	if (perf_pmu__config(pmu, &attr, head_config))
+		return -EINVAL;
+
+	evsel = __add_event(list, idx, &attr, pmu_event_name(head_config),
+			    pmu->cpus);
+	if (evsel) {
+		evsel->unit = unit;
+		evsel->scale = scale;
 	}
-	return EVT_FAILED;
+
+	return evsel ? 0 : -ENOMEM;
 }
 
-static enum event_result
-parse_event_modifier(const char **strp, struct perf_event_attr *attr)
+int parse_events__modifier_group(struct list_head *list,
+				 char *event_mod)
 {
-	const char *str = *strp;
-	int exclude = 0;
-	int eu = 0, ek = 0, eh = 0, precise = 0;
+	return parse_events__modifier_event(list, event_mod, true);
+}
+
+void parse_events__set_leader(char *name, struct list_head *list)
+{
+	struct perf_evsel *leader;
+
+	__perf_evlist__set_leader(list);
+	leader = list_entry(list->next, struct perf_evsel, node);
+	leader->group_name = name ? strdup(name) : NULL;
+}
+
+/* list_event is assumed to point to malloc'ed memory */
+void parse_events_update_lists(struct list_head *list_event,
+			       struct list_head *list_all)
+{
+	/*
+	 * Called for single event definition. Update the
+	 * 'all event' list, and reinit the 'single event'
+	 * list, for next event definition.
+	 */
+	list_splice_tail(list_event, list_all);
+	free(list_event);
+}
+
+struct event_modifier {
+	int eu;
+	int ek;
+	int eh;
+	int eH;
+	int eG;
+	int precise;
+	int exclude_GH;
+	int sample_read;
+	int pinned;
+};
+
+static int get_event_modifier(struct event_modifier *mod, char *str,
+			       struct perf_evsel *evsel)
+{
+	int eu = evsel ? evsel->attr.exclude_user : 0;
+	int ek = evsel ? evsel->attr.exclude_kernel : 0;
+	int eh = evsel ? evsel->attr.exclude_hv : 0;
+	int eH = evsel ? evsel->attr.exclude_host : 0;
+	int eG = evsel ? evsel->attr.exclude_guest : 0;
+	int precise = evsel ? evsel->attr.precise_ip : 0;
+	int sample_read = 0;
+	int pinned = evsel ? evsel->attr.pinned : 0;
+
+	int exclude = eu | ek | eh;
+	int exclude_GH = evsel ? evsel->exclude_GH : 0;
+
+	memset(mod, 0, sizeof(*mod));
 
-	if (*str++ != ':')
-		return 0;
 	while (*str) {
 		if (*str == 'u') {
 			if (!exclude)
@@ -706,148 +736,252 @@ parse_event_modifier(const char **strp, struct perf_event_attr *attr)
 			if (!exclude)
 				exclude = eu = ek = eh = 1;
 			eh = 0;
+		} else if (*str == 'G') {
+			if (!exclude_GH)
+				exclude_GH = eG = eH = 1;
+			eG = 0;
+		} else if (*str == 'H') {
+			if (!exclude_GH)
+				exclude_GH = eG = eH = 1;
+			eH = 0;
 		} else if (*str == 'p') {
 			precise++;
+			/* use of precise requires exclude_guest */
+			if (!exclude_GH)
+				eG = 1;
+		} else if (*str == 'S') {
+			sample_read = 1;
+		} else if (*str == 'D') {
+			pinned = 1;
 		} else
 			break;
 
 		++str;
 	}
-	if (str >= *strp + 2) {
-		*strp = str;
-		attr->exclude_user   = eu;
-		attr->exclude_kernel = ek;
-		attr->exclude_hv     = eh;
-		attr->precise_ip     = precise;
-		return 1;
-	}
+
+	/*
+	 * precise ip:
+	 *
+	 *  0 - SAMPLE_IP can have arbitrary skid
+	 *  1 - SAMPLE_IP must have constant skid
+	 *  2 - SAMPLE_IP requested to have 0 skid
+	 *  3 - SAMPLE_IP must have 0 skid
+	 *
+	 *  See also PERF_RECORD_MISC_EXACT_IP
+	 */
+	if (precise > 3)
+		return -EINVAL;
+
+	mod->eu = eu;
+	mod->ek = ek;
+	mod->eh = eh;
+	mod->eH = eH;
+	mod->eG = eG;
+	mod->precise = precise;
+	mod->exclude_GH = exclude_GH;
+	mod->sample_read = sample_read;
+	mod->pinned = pinned;
+
 	return 0;
 }
 
 /*
- * Each event can have multiple symbolic names.
- * Symbolic names are (almost) exactly matched.
+ * Basic modifier sanity check to validate it contains only one
+ * instance of any modifier (apart from 'p') present.
  */
-static enum event_result
-parse_event_symbols(const char **str, struct perf_event_attr *attr)
+static int check_modifier(char *str)
 {
-	enum event_result ret;
+	char *p = str;
 
-	ret = parse_tracepoint_event(str, attr);
-	if (ret != EVT_FAILED)
-		goto modifier;
+	/* The sizeof includes 0 byte as well. */
+	if (strlen(str) > (sizeof("ukhGHpppSD") - 1))
+		return -1;
 
-	ret = parse_raw_event(str, attr);
-	if (ret != EVT_FAILED)
-		goto modifier;
+	while (*p) {
+		if (*p != 'p' && strchr(p + 1, *p))
+			return -1;
+		p++;
+	}
 
-	ret = parse_numeric_event(str, attr);
-	if (ret != EVT_FAILED)
-		goto modifier;
+	return 0;
+}
 
-	ret = parse_symbolic_event(str, attr);
-	if (ret != EVT_FAILED)
-		goto modifier;
+int parse_events__modifier_event(struct list_head *list, char *str, bool add)
+{
+	struct perf_evsel *evsel;
+	struct event_modifier mod;
 
-	ret = parse_generic_hw_event(str, attr);
-	if (ret != EVT_FAILED)
-		goto modifier;
+	if (str == NULL)
+		return 0;
 
-	ret = parse_breakpoint_event(str, attr);
-	if (ret != EVT_FAILED)
-		goto modifier;
+	if (check_modifier(str))
+		return -EINVAL;
 
-	fprintf(stderr, "invalid or unsupported event: '%s'\n", *str);
-	fprintf(stderr, "Run 'perf list' for a list of valid events\n");
-	return EVT_FAILED;
+	if (!add && get_event_modifier(&mod, str, NULL))
+		return -EINVAL;
 
-modifier:
-	parse_event_modifier(str, attr);
+	__evlist__for_each(list, evsel) {
+		if (add && get_event_modifier(&mod, str, evsel))
+			return -EINVAL;
+
+		evsel->attr.exclude_user   = mod.eu;
+		evsel->attr.exclude_kernel = mod.ek;
+		evsel->attr.exclude_hv     = mod.eh;
+		evsel->attr.precise_ip     = mod.precise;
+		evsel->attr.exclude_host   = mod.eH;
+		evsel->attr.exclude_guest  = mod.eG;
+		evsel->exclude_GH          = mod.exclude_GH;
+		evsel->sample_read         = mod.sample_read;
+
+		if (perf_evsel__is_group_leader(evsel))
+			evsel->attr.pinned = mod.pinned;
+	}
 
-	return ret;
+	return 0;
 }
 
-static int store_event_type(const char *orgname)
+int parse_events_name(struct list_head *list, char *name)
 {
-	char filename[PATH_MAX], *c;
-	FILE *file;
-	int id, n;
+	struct perf_evsel *evsel;
 
-	sprintf(filename, "%s/", debugfs_path);
-	strncat(filename, orgname, strlen(orgname));
-	strcat(filename, "/id");
+	__evlist__for_each(list, evsel) {
+		if (!evsel->name)
+			evsel->name = strdup(name);
+	}
 
-	c = strchr(filename, ':');
-	if (c)
-		*c = '/';
+	return 0;
+}
 
-	file = fopen(filename, "r");
-	if (!file)
-		return 0;
-	n = fscanf(file, "%i", &id);
-	fclose(file);
-	if (n < 1) {
-		pr_err("cannot store event ID\n");
-		return -EINVAL;
+static int parse_events__scanner(const char *str, void *data, int start_token);
+
+static int parse_events_fixup(int ret, const char *str, void *data,
+			      int start_token)
+{
+	char *o = strdup(str);
+	char *s = NULL;
+	char *t = o;
+	char *p;
+	int len = 0;
+
+	if (!o)
+		return ret;
+	while ((p = strsep(&t, ",")) != NULL) {
+		if (s)
+			str_append(&s, &len, ",");
+		str_append(&s, &len, "cpu/");
+		str_append(&s, &len, p);
+		str_append(&s, &len, "/");
 	}
-	return perf_header__push_event(id, orgname);
+	free(o);
+	if (!s)
+		return -ENOMEM;
+	return parse_events__scanner(s, data, start_token);
 }
 
-int parse_events(const struct option *opt __used, const char *str, int unset __used)
+static int parse_events__scanner(const char *str, void *data, int start_token)
 {
-	struct perf_event_attr attr;
-	enum event_result ret;
+	YY_BUFFER_STATE buffer;
+	void *scanner;
+	int ret;
+
+	ret = parse_events_lex_init_extra(start_token, &scanner);
+	if (ret)
+		return ret;
+
+	buffer = parse_events__scan_string(str, scanner);
+
+#ifdef PARSER_DEBUG
+	parse_events_debug = 1;
+#endif
+	ret = parse_events_parse(data, scanner);
+
+	parse_events__flush_buffer(buffer, scanner);
+	parse_events__delete_buffer(buffer, scanner);
+	parse_events_lex_destroy(scanner);
+	if (ret && !strchr(str, '/'))
+		ret = parse_events_fixup(ret, str, data, start_token);
+	return ret;
+}
 
-	if (strchr(str, ':'))
-		if (store_event_type(str) < 0)
-			return -1;
+/*
+ * parse event config string, return a list of event terms.
+ */
+int parse_events_terms(struct list_head *terms, const char *str)
+{
+	struct parse_events_terms data = {
+		.terms = NULL,
+	};
+	int ret;
+
+	ret = parse_events__scanner(str, &data, PE_START_TERMS);
+	if (!ret) {
+		list_splice(data.terms, terms);
+		zfree(&data.terms);
+		return 0;
+	}
 
-	for (;;) {
-		if (nr_counters == MAX_COUNTERS)
-			return -1;
+	if (data.terms)
+		parse_events__free_terms(data.terms);
+	return ret;
+}
 
-		memset(&attr, 0, sizeof(attr));
-		ret = parse_event_symbols(&str, &attr);
-		if (ret == EVT_FAILED)
-			return -1;
+int parse_events(struct perf_evlist *evlist, const char *str)
+{
+	struct parse_events_evlist data = {
+		.list = LIST_HEAD_INIT(data.list),
+		.idx  = evlist->nr_entries,
+	};
+	int ret;
+
+	ret = parse_events__scanner(str, &data, PE_START_EVENTS);
+	if (!ret) {
+		int entries = data.idx - evlist->nr_entries;
+		perf_evlist__splice_list_tail(evlist, &data.list, entries);
+		evlist->nr_groups += data.nr_groups;
+		return 0;
+	}
 
-		if (!(*str == 0 || *str == ',' || isspace(*str)))
-			return -1;
+	/*
+	 * There are 2 users - builtin-record and builtin-test objects.
+	 * Both call perf_evlist__delete in case of error, so we dont
+	 * need to bother.
+	 */
+	return ret;
+}
 
-		if (ret != EVT_HANDLED_ALL) {
-			attrs[nr_counters] = attr;
-			nr_counters++;
-		}
+int parse_events_option(const struct option *opt, const char *str,
+			int unset __maybe_unused)
+{
+	struct perf_evlist *evlist = *(struct perf_evlist **)opt->value;
+	int ret = parse_events(evlist, str);
 
-		if (*str == 0)
-			break;
-		if (*str == ',')
-			++str;
-		while (isspace(*str))
-			++str;
+	if (ret) {
+		fprintf(stderr, "invalid or unsupported event: '%s'\n", str);
+		fprintf(stderr, "Run 'perf list' for a list of valid events\n");
 	}
-
-	return 0;
+	return ret;
 }
 
-int parse_filter(const struct option *opt __used, const char *str,
-		 int unset __used)
+int parse_filter(const struct option *opt, const char *str,
+		 int unset __maybe_unused)
 {
-	int i = nr_counters - 1;
-	int len = strlen(str);
+	struct perf_evlist *evlist = *(struct perf_evlist **)opt->value;
+	struct perf_evsel *last = NULL;
 
-	if (i < 0 || attrs[i].type != PERF_TYPE_TRACEPOINT) {
+	if (evlist->nr_entries > 0)
+		last = perf_evlist__last(evlist);
+
+	if (last == NULL || last->attr.type != PERF_TYPE_TRACEPOINT) {
 		fprintf(stderr,
 			"-F option should follow a -e tracepoint option\n");
 		return -1;
 	}
 
-	filters[i] = malloc(len + 1);
-	if (!filters[i]) {
+	last->filter = strdup(str);
+	if (last->filter == NULL) {
 		fprintf(stderr, "not enough memory to hold filter string\n");
 		return -1;
 	}
-	strcpy(filters[i], str);
 
 	return 0;
 }
@@ -865,32 +999,47 @@ static const char * const event_type_descriptors[] = {
  * Print the events from <debugfs_mount_point>/tracing/events
  */
 
-static void print_tracepoint_events(void)
+void print_tracepoint_events(const char *subsys_glob, const char *event_glob,
+			     bool name_only)
 {
 	DIR *sys_dir, *evt_dir;
 	struct dirent *sys_next, *evt_next, sys_dirent, evt_dirent;
 	char evt_path[MAXPATHLEN];
 	char dir_path[MAXPATHLEN];
 
-	if (debugfs_valid_mountpoint(debugfs_path))
+	if (debugfs_valid_mountpoint(tracing_events_path)) {
+		printf("  [ Tracepoints not available: %s ]\n", strerror(errno));
 		return;
+	}
 
-	sys_dir = opendir(debugfs_path);
+	sys_dir = opendir(tracing_events_path);
 	if (!sys_dir)
 		return;
 
 	for_each_subsystem(sys_dir, sys_dirent, sys_next) {
+		if (subsys_glob != NULL && 
+		    !strglobmatch(sys_dirent.d_name, subsys_glob))
+			continue;
 
-		snprintf(dir_path, MAXPATHLEN, "%s/%s", debugfs_path,
+		snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path,
 			 sys_dirent.d_name);
 		evt_dir = opendir(dir_path);
 		if (!evt_dir)
 			continue;
 
 		for_each_event(sys_dirent, evt_dir, evt_dirent, evt_next) {
+			if (event_glob != NULL && 
+			    !strglobmatch(evt_dirent.d_name, event_glob))
+				continue;
+
+			if (name_only) {
+				printf("%s:%s ", sys_dirent.d_name, evt_dirent.d_name);
+				continue;
+			}
+
 			snprintf(evt_path, MAXPATHLEN, "%s:%s",
 				 sys_dirent.d_name, evt_dirent.d_name);
-			printf("  %-42s [%s]\n", evt_path,
+			printf("  %-50s [%s]\n", evt_path,
 				event_type_descriptors[PERF_TYPE_TRACEPOINT]);
 		}
 		closedir(evt_dir);
@@ -899,60 +1048,307 @@ static void print_tracepoint_events(void)
 }
 
 /*
- * Print the help text for the event symbols:
+ * Check whether event is in <debugfs_mount_point>/tracing/events
  */
-void print_events(void)
+
+int is_valid_tracepoint(const char *event_string)
 {
-	struct event_symbol *syms = event_symbols;
-	unsigned int i, type, op, prev_type = -1;
-	char name[40];
+	DIR *sys_dir, *evt_dir;
+	struct dirent *sys_next, *evt_next, sys_dirent, evt_dirent;
+	char evt_path[MAXPATHLEN];
+	char dir_path[MAXPATHLEN];
+
+	if (debugfs_valid_mountpoint(tracing_events_path))
+		return 0;
 
-	printf("\n");
-	printf("List of pre-defined events (to be used in -e):\n");
+	sys_dir = opendir(tracing_events_path);
+	if (!sys_dir)
+		return 0;
 
-	for (i = 0; i < ARRAY_SIZE(event_symbols); i++, syms++) {
-		type = syms->type;
+	for_each_subsystem(sys_dir, sys_dirent, sys_next) {
 
-		if (type != prev_type)
-			printf("\n");
+		snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path,
+			 sys_dirent.d_name);
+		evt_dir = opendir(dir_path);
+		if (!evt_dir)
+			continue;
+
+		for_each_event(sys_dirent, evt_dir, evt_dirent, evt_next) {
+			snprintf(evt_path, MAXPATHLEN, "%s:%s",
+				 sys_dirent.d_name, evt_dirent.d_name);
+			if (!strcmp(evt_path, event_string)) {
+				closedir(evt_dir);
+				closedir(sys_dir);
+				return 1;
+			}
+		}
+		closedir(evt_dir);
+	}
+	closedir(sys_dir);
+	return 0;
+}
+
+static bool is_event_supported(u8 type, unsigned config)
+{
+	bool ret = true;
+	int open_return;
+	struct perf_evsel *evsel;
+	struct perf_event_attr attr = {
+		.type = type,
+		.config = config,
+		.disabled = 1,
+	};
+	struct {
+		struct thread_map map;
+		int threads[1];
+	} tmap = {
+		.map.nr	 = 1,
+		.threads = { 0 },
+	};
+
+	evsel = perf_evsel__new(&attr);
+	if (evsel) {
+		open_return = perf_evsel__open(evsel, NULL, &tmap.map);
+		ret = open_return >= 0;
+
+		if (open_return == -EACCES) {
+			/*
+			 * This happens if the paranoid value
+			 * /proc/sys/kernel/perf_event_paranoid is set to 2
+			 * Re-run with exclude_kernel set; we don't do that
+			 * by default as some ARM machines do not support it.
+			 *
+			 */
+			evsel->attr.exclude_kernel = 1;
+			ret = perf_evsel__open(evsel, NULL, &tmap.map) >= 0;
+		}
+		perf_evsel__delete(evsel);
+	}
+
+	return ret;
+}
+
+static void __print_events_type(u8 type, struct event_symbol *syms,
+				unsigned max)
+{
+	char name[64];
+	unsigned i;
+
+	for (i = 0; i < max ; i++, syms++) {
+		if (!is_event_supported(type, i))
+			continue;
 
 		if (strlen(syms->alias))
-			sprintf(name, "%s OR %s", syms->symbol, syms->alias);
+			snprintf(name, sizeof(name),  "%s OR %s",
+				 syms->symbol, syms->alias);
 		else
-			strcpy(name, syms->symbol);
-		printf("  %-42s [%s]\n", name,
-			event_type_descriptors[type]);
+			snprintf(name, sizeof(name), "%s", syms->symbol);
 
-		prev_type = type;
+		printf("  %-50s [%s]\n", name, event_type_descriptors[type]);
 	}
+}
+
+void print_events_type(u8 type)
+{
+	if (type == PERF_TYPE_SOFTWARE)
+		__print_events_type(type, event_symbols_sw, PERF_COUNT_SW_MAX);
+	else
+		__print_events_type(type, event_symbols_hw, PERF_COUNT_HW_MAX);
+}
+
+int print_hwcache_events(const char *event_glob, bool name_only)
+{
+	unsigned int type, op, i, printed = 0;
+	char name[64];
 
-	printf("\n");
 	for (type = 0; type < PERF_COUNT_HW_CACHE_MAX; type++) {
 		for (op = 0; op < PERF_COUNT_HW_CACHE_OP_MAX; op++) {
 			/* skip invalid cache type */
-			if (!is_cache_op_valid(type, op))
+			if (!perf_evsel__is_cache_op_valid(type, op))
 				continue;
 
 			for (i = 0; i < PERF_COUNT_HW_CACHE_RESULT_MAX; i++) {
-				printf("  %-42s [%s]\n",
-					event_cache_name(type, op, i),
-					event_type_descriptors[PERF_TYPE_HW_CACHE]);
+				__perf_evsel__hw_cache_type_op_res_name(type, op, i,
+									name, sizeof(name));
+				if (event_glob != NULL && !strglobmatch(name, event_glob))
+					continue;
+
+				if (!is_event_supported(PERF_TYPE_HW_CACHE,
+							type | (op << 8) | (i << 16)))
+					continue;
+
+				if (name_only)
+					printf("%s ", name);
+				else
+					printf("  %-50s [%s]\n", name,
+					       event_type_descriptors[PERF_TYPE_HW_CACHE]);
+				++printed;
 			}
 		}
 	}
 
-	printf("\n");
-	printf("  %-42s [%s]\n",
-		"rNNN (see 'perf list --help' on how to encode it)",
-	       event_type_descriptors[PERF_TYPE_RAW]);
-	printf("\n");
+	if (printed)
+		printf("\n");
+	return printed;
+}
+
+static void print_symbol_events(const char *event_glob, unsigned type,
+				struct event_symbol *syms, unsigned max,
+				bool name_only)
+{
+	unsigned i, printed = 0;
+	char name[MAX_NAME_LEN];
+
+	for (i = 0; i < max; i++, syms++) {
+
+		if (event_glob != NULL && 
+		    !(strglobmatch(syms->symbol, event_glob) ||
+		      (syms->alias && strglobmatch(syms->alias, event_glob))))
+			continue;
+
+		if (!is_event_supported(type, i))
+			continue;
+
+		if (name_only) {
+			printf("%s ", syms->symbol);
+			continue;
+		}
+
+		if (strlen(syms->alias))
+			snprintf(name, MAX_NAME_LEN, "%s OR %s", syms->symbol, syms->alias);
+		else
+			strncpy(name, syms->symbol, MAX_NAME_LEN);
+
+		printf("  %-50s [%s]\n", name, event_type_descriptors[type]);
+
+		printed++;
+	}
+
+	if (printed)
+		printf("\n");
+}
+
+/*
+ * Print the help text for the event symbols:
+ */
+void print_events(const char *event_glob, bool name_only)
+{
+	if (!name_only) {
+		printf("\n");
+		printf("List of pre-defined events (to be used in -e):\n");
+	}
+
+	print_symbol_events(event_glob, PERF_TYPE_HARDWARE,
+			    event_symbols_hw, PERF_COUNT_HW_MAX, name_only);
+
+	print_symbol_events(event_glob, PERF_TYPE_SOFTWARE,
+			    event_symbols_sw, PERF_COUNT_SW_MAX, name_only);
 
-	printf("  %-42s [%s]\n",
-			"mem:<addr>[:access]",
+	print_hwcache_events(event_glob, name_only);
+
+	print_pmu_events(event_glob, name_only);
+
+	if (event_glob != NULL)
+		return;
+
+	if (!name_only) {
+		printf("  %-50s [%s]\n",
+		       "rNNN",
+		       event_type_descriptors[PERF_TYPE_RAW]);
+		printf("  %-50s [%s]\n",
+		       "cpu/t1=v1[,t2=v2,t3 ...]/modifier",
+		       event_type_descriptors[PERF_TYPE_RAW]);
+		printf("   (see 'man perf-list' on how to encode it)\n");
+		printf("\n");
+
+		printf("  %-50s [%s]\n",
+		       "mem:<addr>[:access]",
 			event_type_descriptors[PERF_TYPE_BREAKPOINT]);
-	printf("\n");
+		printf("\n");
+	}
+
+	print_tracepoint_events(NULL, NULL, name_only);
+}
+
+int parse_events__is_hardcoded_term(struct parse_events_term *term)
+{
+	return term->type_term != PARSE_EVENTS__TERM_TYPE_USER;
+}
+
+static int new_term(struct parse_events_term **_term, int type_val,
+		    int type_term, char *config,
+		    char *str, u64 num)
+{
+	struct parse_events_term *term;
+
+	term = zalloc(sizeof(*term));
+	if (!term)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&term->list);
+	term->type_val  = type_val;
+	term->type_term = type_term;
+	term->config = config;
+
+	switch (type_val) {
+	case PARSE_EVENTS__TERM_TYPE_NUM:
+		term->val.num = num;
+		break;
+	case PARSE_EVENTS__TERM_TYPE_STR:
+		term->val.str = str;
+		break;
+	default:
+		free(term);
+		return -EINVAL;
+	}
+
+	*_term = term;
+	return 0;
+}
+
+int parse_events_term__num(struct parse_events_term **term,
+			   int type_term, char *config, u64 num)
+{
+	return new_term(term, PARSE_EVENTS__TERM_TYPE_NUM, type_term,
+			config, NULL, num);
+}
+
+int parse_events_term__str(struct parse_events_term **term,
+			   int type_term, char *config, char *str)
+{
+	return new_term(term, PARSE_EVENTS__TERM_TYPE_STR, type_term,
+			config, str, 0);
+}
 
-	print_tracepoint_events();
+int parse_events_term__sym_hw(struct parse_events_term **term,
+			      char *config, unsigned idx)
+{
+	struct event_symbol *sym;
+
+	BUG_ON(idx >= PERF_COUNT_HW_MAX);
+	sym = &event_symbols_hw[idx];
+
+	if (config)
+		return new_term(term, PARSE_EVENTS__TERM_TYPE_STR,
+				PARSE_EVENTS__TERM_TYPE_USER, config,
+				(char *) sym->symbol, 0);
+	else
+		return new_term(term, PARSE_EVENTS__TERM_TYPE_STR,
+				PARSE_EVENTS__TERM_TYPE_USER,
+				(char *) "event", (char *) sym->symbol, 0);
+}
+
+int parse_events_term__clone(struct parse_events_term **new,
+			     struct parse_events_term *term)
+{
+	return new_term(new, term->type_val, term->type_term, term->config,
+			term->val.str, term->val.num);
+}
+
+void parse_events__free_terms(struct list_head *terms)
+{
+	struct parse_events_term *term, *h;
 
-	exit(129);
+	list_for_each_entry_safe(term, h, terms, list)
+		free(term);
 }
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index fc4ab3fe877..df094b4ed5e 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -4,6 +4,15 @@
  * Parse symbolic events/counts passed in as options:
  */
 
+#include <linux/list.h>
+#include <stdbool.h>
+#include <linux/types.h>
+#include <linux/perf_event.h>
+
+struct list_head;
+struct perf_evsel;
+struct perf_evlist;
+
 struct option;
 
 struct tracepoint_path {
@@ -13,25 +22,91 @@ struct tracepoint_path {
 };
 
 extern struct tracepoint_path *tracepoint_id_to_path(u64 config);
-extern bool have_tracepoints(struct perf_event_attr *pattrs, int nb_events);
-
-extern int			nr_counters;
-
-extern struct perf_event_attr attrs[MAX_COUNTERS];
-extern char *filters[MAX_COUNTERS];
+extern struct tracepoint_path *tracepoint_name_to_path(const char *name);
+extern bool have_tracepoints(struct list_head *evlist);
 
-extern const char *event_name(int ctr);
-extern const char *__event_name(int type, u64 config);
+const char *event_type(int type);
 
-extern int parse_events(const struct option *opt, const char *str, int unset);
+extern int parse_events_option(const struct option *opt, const char *str,
+			       int unset);
+extern int parse_events(struct perf_evlist *evlist, const char *str);
+extern int parse_events_terms(struct list_head *terms, const char *str);
 extern int parse_filter(const struct option *opt, const char *str, int unset);
 
 #define EVENTS_HELP_MAX (128*1024)
 
-extern void print_events(void);
+enum {
+	PARSE_EVENTS__TERM_TYPE_NUM,
+	PARSE_EVENTS__TERM_TYPE_STR,
+};
 
-extern char debugfs_path[];
-extern int valid_debugfs_mount(const char *debugfs);
+enum {
+	PARSE_EVENTS__TERM_TYPE_USER,
+	PARSE_EVENTS__TERM_TYPE_CONFIG,
+	PARSE_EVENTS__TERM_TYPE_CONFIG1,
+	PARSE_EVENTS__TERM_TYPE_CONFIG2,
+	PARSE_EVENTS__TERM_TYPE_NAME,
+	PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD,
+	PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE,
+};
+
+struct parse_events_term {
+	char *config;
+	union {
+		char *str;
+		u64  num;
+	} val;
+	int type_val;
+	int type_term;
+	struct list_head list;
+};
+
+struct parse_events_evlist {
+	struct list_head list;
+	int idx;
+	int nr_groups;
+};
+
+struct parse_events_terms {
+	struct list_head *terms;
+};
+
+int parse_events__is_hardcoded_term(struct parse_events_term *term);
+int parse_events_term__num(struct parse_events_term **_term,
+			   int type_term, char *config, u64 num);
+int parse_events_term__str(struct parse_events_term **_term,
+			   int type_term, char *config, char *str);
+int parse_events_term__sym_hw(struct parse_events_term **term,
+			      char *config, unsigned idx);
+int parse_events_term__clone(struct parse_events_term **new,
+			     struct parse_events_term *term);
+void parse_events__free_terms(struct list_head *terms);
+int parse_events__modifier_event(struct list_head *list, char *str, bool add);
+int parse_events__modifier_group(struct list_head *list, char *event_mod);
+int parse_events_name(struct list_head *list, char *name);
+int parse_events_add_tracepoint(struct list_head *list, int *idx,
+				char *sys, char *event);
+int parse_events_add_numeric(struct list_head *list, int *idx,
+			     u32 type, u64 config,
+			     struct list_head *head_config);
+int parse_events_add_cache(struct list_head *list, int *idx,
+			   char *type, char *op_result1, char *op_result2);
+int parse_events_add_breakpoint(struct list_head *list, int *idx,
+				void *ptr, char *type);
+int parse_events_add_pmu(struct list_head *list, int *idx,
+			 char *pmu , struct list_head *head_config);
+void parse_events__set_leader(char *name, struct list_head *list);
+void parse_events_update_lists(struct list_head *list_event,
+			       struct list_head *list_all);
+void parse_events_error(void *data, void *scanner, char const *msg);
 
+void print_events(const char *event_glob, bool name_only);
+void print_events_type(u8 type);
+void print_tracepoint_events(const char *subsys_glob, const char *event_glob,
+			     bool name_only);
+int print_hwcache_events(const char *event_glob, bool name_only);
+extern int is_valid_tracepoint(const char *event_string);
+
+extern int valid_debugfs_mount(const char *debugfs);
 
 #endif /* __PERF_PARSE_EVENTS_H */
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
new file mode 100644
index 00000000000..343299575b3
--- /dev/null
+++ b/tools/perf/util/parse-events.l
@@ -0,0 +1,218 @@
+
+%option reentrant
+%option bison-bridge
+%option prefix="parse_events_"
+%option stack
+
+%{
+#include <errno.h>
+#include "../perf.h"
+#include "parse-events-bison.h"
+#include "parse-events.h"
+
+char *parse_events_get_text(yyscan_t yyscanner);
+YYSTYPE *parse_events_get_lval(yyscan_t yyscanner);
+
+static int __value(YYSTYPE *yylval, char *str, int base, int token)
+{
+	u64 num;
+
+	errno = 0;
+	num = strtoull(str, NULL, base);
+	if (errno)
+		return PE_ERROR;
+
+	yylval->num = num;
+	return token;
+}
+
+static int value(yyscan_t scanner, int base)
+{
+	YYSTYPE *yylval = parse_events_get_lval(scanner);
+	char *text = parse_events_get_text(scanner);
+
+	return __value(yylval, text, base, PE_VALUE);
+}
+
+static int raw(yyscan_t scanner)
+{
+	YYSTYPE *yylval = parse_events_get_lval(scanner);
+	char *text = parse_events_get_text(scanner);
+
+	return __value(yylval, text + 1, 16, PE_RAW);
+}
+
+static int str(yyscan_t scanner, int token)
+{
+	YYSTYPE *yylval = parse_events_get_lval(scanner);
+	char *text = parse_events_get_text(scanner);
+
+	yylval->str = strdup(text);
+	return token;
+}
+
+static int sym(yyscan_t scanner, int type, int config)
+{
+	YYSTYPE *yylval = parse_events_get_lval(scanner);
+
+	yylval->num = (type << 16) + config;
+	return type == PERF_TYPE_HARDWARE ? PE_VALUE_SYM_HW : PE_VALUE_SYM_SW;
+}
+
+static int term(yyscan_t scanner, int type)
+{
+	YYSTYPE *yylval = parse_events_get_lval(scanner);
+
+	yylval->num = type;
+	return PE_TERM;
+}
+
+%}
+
+%x mem
+%s config
+%x event
+
+group		[^,{}/]*[{][^}]*[}][^,{}/]*
+event_pmu	[^,{}/]+[/][^/]*[/][^,{}/]*
+event		[^,{}/]+
+
+num_dec		[0-9]+
+num_hex		0x[a-fA-F0-9]+
+num_raw_hex	[a-fA-F0-9]+
+name		[a-zA-Z_*?][a-zA-Z0-9_*?]*
+name_minus	[a-zA-Z_*?][a-zA-Z0-9\-_*?]*
+/* If you add a modifier you need to update check_modifier() */
+modifier_event	[ukhpGHSD]+
+modifier_bp	[rwx]{1,3}
+
+%%
+
+%{
+	{
+		int start_token;
+
+		start_token = parse_events_get_extra(yyscanner);
+
+		if (start_token == PE_START_TERMS)
+			BEGIN(config);
+		else if (start_token == PE_START_EVENTS)
+			BEGIN(event);
+
+		if (start_token) {
+			parse_events_set_extra(NULL, yyscanner);
+			return start_token;
+		}
+         }
+%}
+
+<event>{
+
+{group}		{
+			BEGIN(INITIAL); yyless(0);
+		}
+
+{event_pmu}	|
+{event}		{
+			str(yyscanner, PE_EVENT_NAME);
+			BEGIN(INITIAL); yyless(0);
+			return PE_EVENT_NAME;
+		}
+
+.		|
+<<EOF>>		{
+			BEGIN(INITIAL); yyless(0);
+		}
+
+}
+
+<config>{
+config			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG); }
+config1			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG1); }
+config2			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG2); }
+name			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NAME); }
+period			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD); }
+branch_type		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE); }
+,			{ return ','; }
+"/"			{ BEGIN(INITIAL); return '/'; }
+{name_minus}		{ return str(yyscanner, PE_NAME); }
+}
+
+<mem>{
+{modifier_bp}		{ return str(yyscanner, PE_MODIFIER_BP); }
+:			{ return ':'; }
+{num_dec}		{ return value(yyscanner, 10); }
+{num_hex}		{ return value(yyscanner, 16); }
+	/*
+	 * We need to separate 'mem:' scanner part, in order to get specific
+	 * modifier bits parsed out. Otherwise we would need to handle PE_NAME
+	 * and we'd need to parse it manually. During the escape from <mem>
+	 * state we need to put the escaping char back, so we dont miss it.
+	 */
+.			{ unput(*yytext); BEGIN(INITIAL); }
+	/*
+	 * We destroy the scanner after reaching EOF,
+	 * but anyway just to be sure get back to INIT state.
+	 */
+<<EOF>>			{ BEGIN(INITIAL); }
+}
+
+cpu-cycles|cycles				{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_CPU_CYCLES); }
+stalled-cycles-frontend|idle-cycles-frontend	{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND); }
+stalled-cycles-backend|idle-cycles-backend	{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_STALLED_CYCLES_BACKEND); }
+instructions					{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_INSTRUCTIONS); }
+cache-references				{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_CACHE_REFERENCES); }
+cache-misses					{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_CACHE_MISSES); }
+branch-instructions|branches			{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_BRANCH_INSTRUCTIONS); }
+branch-misses					{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_BRANCH_MISSES); }
+bus-cycles					{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_BUS_CYCLES); }
+ref-cycles					{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_REF_CPU_CYCLES); }
+cpu-clock					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CPU_CLOCK); }
+task-clock					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_TASK_CLOCK); }
+page-faults|faults				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS); }
+minor-faults					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS_MIN); }
+major-faults					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS_MAJ); }
+context-switches|cs				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CONTEXT_SWITCHES); }
+cpu-migrations|migrations			{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CPU_MIGRATIONS); }
+alignment-faults				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_ALIGNMENT_FAULTS); }
+emulation-faults				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EMULATION_FAULTS); }
+dummy						{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); }
+
+L1-dcache|l1-d|l1d|L1-data		|
+L1-icache|l1-i|l1i|L1-instruction	|
+LLC|L2					|
+dTLB|d-tlb|Data-TLB			|
+iTLB|i-tlb|Instruction-TLB		|
+branch|branches|bpu|btb|bpc		|
+node					{ return str(yyscanner, PE_NAME_CACHE_TYPE); }
+
+load|loads|read				|
+store|stores|write			|
+prefetch|prefetches			|
+speculative-read|speculative-load	|
+refs|Reference|ops|access		|
+misses|miss				{ return str(yyscanner, PE_NAME_CACHE_OP_RESULT); }
+
+mem:			{ BEGIN(mem); return PE_PREFIX_MEM; }
+r{num_raw_hex}		{ return raw(yyscanner); }
+{num_dec}		{ return value(yyscanner, 10); }
+{num_hex}		{ return value(yyscanner, 16); }
+
+{modifier_event}	{ return str(yyscanner, PE_MODIFIER_EVENT); }
+{name}			{ return str(yyscanner, PE_NAME); }
+"/"			{ BEGIN(config); return '/'; }
+-			{ return '-'; }
+,			{ BEGIN(event); return ','; }
+:			{ return ':'; }
+"{"			{ BEGIN(event); return '{'; }
+"}"			{ return '}'; }
+=			{ return '='; }
+\n			{ }
+.			{ }
+
+%%
+
+int parse_events_wrap(void *scanner __maybe_unused)
+{
+	return 1;
+}
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
new file mode 100644
index 00000000000..0bc87ba46bf
--- /dev/null
+++ b/tools/perf/util/parse-events.y
@@ -0,0 +1,454 @@
+%pure-parser
+%parse-param {void *_data}
+%parse-param {void *scanner}
+%lex-param {void* scanner}
+
+%{
+
+#define YYDEBUG 1
+
+#include <linux/compiler.h>
+#include <linux/list.h>
+#include <linux/types.h>
+#include "util.h"
+#include "parse-events.h"
+#include "parse-events-bison.h"
+
+extern int parse_events_lex (YYSTYPE* lvalp, void* scanner);
+
+#define ABORT_ON(val) \
+do { \
+	if (val) \
+		YYABORT; \
+} while (0)
+
+#define ALLOC_LIST(list) \
+do { \
+	list = malloc(sizeof(*list)); \
+	ABORT_ON(!list);              \
+	INIT_LIST_HEAD(list);         \
+} while (0)
+
+static inc_group_count(struct list_head *list,
+		       struct parse_events_evlist *data)
+{
+	/* Count groups only have more than 1 members */
+	if (!list_is_last(list->next, list))
+		data->nr_groups++;
+}
+
+%}
+
+%token PE_START_EVENTS PE_START_TERMS
+%token PE_VALUE PE_VALUE_SYM_HW PE_VALUE_SYM_SW PE_RAW PE_TERM
+%token PE_EVENT_NAME
+%token PE_NAME
+%token PE_MODIFIER_EVENT PE_MODIFIER_BP
+%token PE_NAME_CACHE_TYPE PE_NAME_CACHE_OP_RESULT
+%token PE_PREFIX_MEM PE_PREFIX_RAW PE_PREFIX_GROUP
+%token PE_ERROR
+%type <num> PE_VALUE
+%type <num> PE_VALUE_SYM_HW
+%type <num> PE_VALUE_SYM_SW
+%type <num> PE_RAW
+%type <num> PE_TERM
+%type <str> PE_NAME
+%type <str> PE_NAME_CACHE_TYPE
+%type <str> PE_NAME_CACHE_OP_RESULT
+%type <str> PE_MODIFIER_EVENT
+%type <str> PE_MODIFIER_BP
+%type <str> PE_EVENT_NAME
+%type <num> value_sym
+%type <head> event_config
+%type <term> event_term
+%type <head> event_pmu
+%type <head> event_legacy_symbol
+%type <head> event_legacy_cache
+%type <head> event_legacy_mem
+%type <head> event_legacy_tracepoint
+%type <head> event_legacy_numeric
+%type <head> event_legacy_raw
+%type <head> event_def
+%type <head> event_mod
+%type <head> event_name
+%type <head> event
+%type <head> events
+%type <head> group_def
+%type <head> group
+%type <head> groups
+
+%union
+{
+	char *str;
+	u64 num;
+	struct list_head *head;
+	struct parse_events_term *term;
+}
+%%
+
+start:
+PE_START_EVENTS start_events
+|
+PE_START_TERMS  start_terms
+
+start_events: groups
+{
+	struct parse_events_evlist *data = _data;
+
+	parse_events_update_lists($1, &data->list);
+}
+
+groups:
+groups ',' group
+{
+	struct list_head *list  = $1;
+	struct list_head *group = $3;
+
+	parse_events_update_lists(group, list);
+	$$ = list;
+}
+|
+groups ',' event
+{
+	struct list_head *list  = $1;
+	struct list_head *event = $3;
+
+	parse_events_update_lists(event, list);
+	$$ = list;
+}
+|
+group
+|
+event
+
+group:
+group_def ':' PE_MODIFIER_EVENT
+{
+	struct list_head *list = $1;
+
+	ABORT_ON(parse_events__modifier_group(list, $3));
+	$$ = list;
+}
+|
+group_def
+
+group_def:
+PE_NAME '{' events '}'
+{
+	struct list_head *list = $3;
+
+	inc_group_count(list, _data);
+	parse_events__set_leader($1, list);
+	$$ = list;
+}
+|
+'{' events '}'
+{
+	struct list_head *list = $2;
+
+	inc_group_count(list, _data);
+	parse_events__set_leader(NULL, list);
+	$$ = list;
+}
+
+events:
+events ',' event
+{
+	struct list_head *event = $3;
+	struct list_head *list  = $1;
+
+	parse_events_update_lists(event, list);
+	$$ = list;
+}
+|
+event
+
+event: event_mod
+
+event_mod:
+event_name PE_MODIFIER_EVENT
+{
+	struct list_head *list = $1;
+
+	/*
+	 * Apply modifier on all events added by single event definition
+	 * (there could be more events added for multiple tracepoint
+	 * definitions via '*?'.
+	 */
+	ABORT_ON(parse_events__modifier_event(list, $2, false));
+	$$ = list;
+}
+|
+event_name
+
+event_name:
+PE_EVENT_NAME event_def
+{
+	ABORT_ON(parse_events_name($2, $1));
+	free($1);
+	$$ = $2;
+}
+|
+event_def
+
+event_def: event_pmu |
+	   event_legacy_symbol |
+	   event_legacy_cache sep_dc |
+	   event_legacy_mem |
+	   event_legacy_tracepoint sep_dc |
+	   event_legacy_numeric sep_dc |
+	   event_legacy_raw sep_dc
+
+event_pmu:
+PE_NAME '/' event_config '/'
+{
+	struct parse_events_evlist *data = _data;
+	struct list_head *list;
+
+	ALLOC_LIST(list);
+	ABORT_ON(parse_events_add_pmu(list, &data->idx, $1, $3));
+	parse_events__free_terms($3);
+	$$ = list;
+}
+
+value_sym:
+PE_VALUE_SYM_HW
+|
+PE_VALUE_SYM_SW
+
+event_legacy_symbol:
+value_sym '/' event_config '/'
+{
+	struct parse_events_evlist *data = _data;
+	struct list_head *list;
+	int type = $1 >> 16;
+	int config = $1 & 255;
+
+	ALLOC_LIST(list);
+	ABORT_ON(parse_events_add_numeric(list, &data->idx,
+					  type, config, $3));
+	parse_events__free_terms($3);
+	$$ = list;
+}
+|
+value_sym sep_slash_dc
+{
+	struct parse_events_evlist *data = _data;
+	struct list_head *list;
+	int type = $1 >> 16;
+	int config = $1 & 255;
+
+	ALLOC_LIST(list);
+	ABORT_ON(parse_events_add_numeric(list, &data->idx,
+					  type, config, NULL));
+	$$ = list;
+}
+
+event_legacy_cache:
+PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT '-' PE_NAME_CACHE_OP_RESULT
+{
+	struct parse_events_evlist *data = _data;
+	struct list_head *list;
+
+	ALLOC_LIST(list);
+	ABORT_ON(parse_events_add_cache(list, &data->idx, $1, $3, $5));
+	$$ = list;
+}
+|
+PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT
+{
+	struct parse_events_evlist *data = _data;
+	struct list_head *list;
+
+	ALLOC_LIST(list);
+	ABORT_ON(parse_events_add_cache(list, &data->idx, $1, $3, NULL));
+	$$ = list;
+}
+|
+PE_NAME_CACHE_TYPE
+{
+	struct parse_events_evlist *data = _data;
+	struct list_head *list;
+
+	ALLOC_LIST(list);
+	ABORT_ON(parse_events_add_cache(list, &data->idx, $1, NULL, NULL));
+	$$ = list;
+}
+
+event_legacy_mem:
+PE_PREFIX_MEM PE_VALUE ':' PE_MODIFIER_BP sep_dc
+{
+	struct parse_events_evlist *data = _data;
+	struct list_head *list;
+
+	ALLOC_LIST(list);
+	ABORT_ON(parse_events_add_breakpoint(list, &data->idx,
+					     (void *) $2, $4));
+	$$ = list;
+}
+|
+PE_PREFIX_MEM PE_VALUE sep_dc
+{
+	struct parse_events_evlist *data = _data;
+	struct list_head *list;
+
+	ALLOC_LIST(list);
+	ABORT_ON(parse_events_add_breakpoint(list, &data->idx,
+					     (void *) $2, NULL));
+	$$ = list;
+}
+
+event_legacy_tracepoint:
+PE_NAME '-' PE_NAME ':' PE_NAME
+{
+	struct parse_events_evlist *data = _data;
+	struct list_head *list;
+	char sys_name[128];
+	snprintf(&sys_name, 128, "%s-%s", $1, $3);
+
+	ALLOC_LIST(list);
+	ABORT_ON(parse_events_add_tracepoint(list, &data->idx, &sys_name, $5));
+	$$ = list;
+}
+|
+PE_NAME ':' PE_NAME
+{
+	struct parse_events_evlist *data = _data;
+	struct list_head *list;
+
+	ALLOC_LIST(list);
+	ABORT_ON(parse_events_add_tracepoint(list, &data->idx, $1, $3));
+	$$ = list;
+}
+
+event_legacy_numeric:
+PE_VALUE ':' PE_VALUE
+{
+	struct parse_events_evlist *data = _data;
+	struct list_head *list;
+
+	ALLOC_LIST(list);
+	ABORT_ON(parse_events_add_numeric(list, &data->idx, (u32)$1, $3, NULL));
+	$$ = list;
+}
+
+event_legacy_raw:
+PE_RAW
+{
+	struct parse_events_evlist *data = _data;
+	struct list_head *list;
+
+	ALLOC_LIST(list);
+	ABORT_ON(parse_events_add_numeric(list, &data->idx,
+					  PERF_TYPE_RAW, $1, NULL));
+	$$ = list;
+}
+
+start_terms: event_config
+{
+	struct parse_events_terms *data = _data;
+	data->terms = $1;
+}
+
+event_config:
+event_config ',' event_term
+{
+	struct list_head *head = $1;
+	struct parse_events_term *term = $3;
+
+	ABORT_ON(!head);
+	list_add_tail(&term->list, head);
+	$$ = $1;
+}
+|
+event_term
+{
+	struct list_head *head = malloc(sizeof(*head));
+	struct parse_events_term *term = $1;
+
+	ABORT_ON(!head);
+	INIT_LIST_HEAD(head);
+	list_add_tail(&term->list, head);
+	$$ = head;
+}
+
+event_term:
+PE_NAME '=' PE_NAME
+{
+	struct parse_events_term *term;
+
+	ABORT_ON(parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER,
+					$1, $3));
+	$$ = term;
+}
+|
+PE_NAME '=' PE_VALUE
+{
+	struct parse_events_term *term;
+
+	ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
+					$1, $3));
+	$$ = term;
+}
+|
+PE_NAME '=' PE_VALUE_SYM_HW
+{
+	struct parse_events_term *term;
+	int config = $3 & 255;
+
+	ABORT_ON(parse_events_term__sym_hw(&term, $1, config));
+	$$ = term;
+}
+|
+PE_NAME
+{
+	struct parse_events_term *term;
+
+	ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
+					$1, 1));
+	$$ = term;
+}
+|
+PE_VALUE_SYM_HW
+{
+	struct parse_events_term *term;
+	int config = $1 & 255;
+
+	ABORT_ON(parse_events_term__sym_hw(&term, NULL, config));
+	$$ = term;
+}
+|
+PE_TERM '=' PE_NAME
+{
+	struct parse_events_term *term;
+
+	ABORT_ON(parse_events_term__str(&term, (int)$1, NULL, $3));
+	$$ = term;
+}
+|
+PE_TERM '=' PE_VALUE
+{
+	struct parse_events_term *term;
+
+	ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, $3));
+	$$ = term;
+}
+|
+PE_TERM
+{
+	struct parse_events_term *term;
+
+	ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, 1));
+	$$ = term;
+}
+
+sep_dc: ':' |
+
+sep_slash_dc: '/' | ':' |
+
+%%
+
+void parse_events_error(void *data __maybe_unused, void *scanner __maybe_unused,
+			char const *msg __maybe_unused)
+{
+}
diff --git a/tools/perf/util/parse-options.c b/tools/perf/util/parse-options.c
index 99d02aa57db..bf48092983c 100644
--- a/tools/perf/util/parse-options.c
+++ b/tools/perf/util/parse-options.c
@@ -1,6 +1,7 @@
 #include "util.h"
 #include "parse-options.h"
 #include "cache.h"
+#include "header.h"
 
 #define OPT_SHORT 1
 #define OPT_UNSET 2
@@ -77,6 +78,8 @@ static int get_value(struct parse_opt_ctx_t *p,
 
 	case OPTION_BOOLEAN:
 		*(bool *)opt->value = unset ? false : true;
+		if (opt->set)
+			*(bool *)opt->set = true;
 		return 0;
 
 	case OPTION_INCR:
@@ -223,6 +226,24 @@ static int parse_long_opt(struct parse_opt_ctx_t *p, const char *arg,
 			return 0;
 		}
 		if (!rest) {
+			if (!prefixcmp(options->long_name, "no-")) {
+				/*
+				 * The long name itself starts with "no-", so
+				 * accept the option without "no-" so that users
+				 * do not have to enter "no-no-" to get the
+				 * negation.
+				 */
+				rest = skip_prefix(arg, options->long_name + 3);
+				if (rest) {
+					flags |= OPT_UNSET;
+					goto match;
+				}
+				/* Abbreviated case */
+				if (!prefixcmp(options->long_name + 3, arg)) {
+					flags |= OPT_UNSET;
+					goto is_abbreviated;
+				}
+			}
 			/* abbreviated? */
 			if (!strncmp(options->long_name, arg, arg_end - arg)) {
 is_abbreviated:
@@ -258,6 +279,7 @@ is_abbreviated:
 			if (!rest)
 				continue;
 		}
+match:
 		if (*rest) {
 			if (*rest != '=')
 				continue;
@@ -338,10 +360,10 @@ int parse_options_step(struct parse_opt_ctx_t *ctx,
 		if (arg[1] != '-') {
 			ctx->opt = arg + 1;
 			if (internal_help && *ctx->opt == 'h')
-				return parse_options_usage(usagestr, options);
+				return usage_with_options_internal(usagestr, options, 0);
 			switch (parse_short_opt(ctx, options)) {
 			case -1:
-				return parse_options_usage(usagestr, options);
+				return parse_options_usage(usagestr, options, arg + 1, 1);
 			case -2:
 				goto unknown;
 			default:
@@ -351,10 +373,11 @@ int parse_options_step(struct parse_opt_ctx_t *ctx,
 				check_typos(arg + 1, options);
 			while (ctx->opt) {
 				if (internal_help && *ctx->opt == 'h')
-					return parse_options_usage(usagestr, options);
+					return usage_with_options_internal(usagestr, options, 0);
+				arg = ctx->opt;
 				switch (parse_short_opt(ctx, options)) {
 				case -1:
-					return parse_options_usage(usagestr, options);
+					return parse_options_usage(usagestr, options, arg, 1);
 				case -2:
 					/* fake a short option thing to hide the fact that we may have
 					 * started to parse aggregated stuff
@@ -382,10 +405,14 @@ int parse_options_step(struct parse_opt_ctx_t *ctx,
 		if (internal_help && !strcmp(arg + 2, "help-all"))
 			return usage_with_options_internal(usagestr, options, 1);
 		if (internal_help && !strcmp(arg + 2, "help"))
-			return parse_options_usage(usagestr, options);
+			return usage_with_options_internal(usagestr, options, 0);
+		if (!strcmp(arg + 2, "list-opts"))
+			return PARSE_OPT_LIST_OPTS;
+		if (!strcmp(arg + 2, "list-cmds"))
+			return PARSE_OPT_LIST_SUBCMDS;
 		switch (parse_long_opt(ctx, arg + 2, options)) {
 		case -1:
-			return parse_options_usage(usagestr, options);
+			return parse_options_usage(usagestr, options, arg + 2, 0);
 		case -2:
 			goto unknown;
 		default:
@@ -408,17 +435,45 @@ int parse_options_end(struct parse_opt_ctx_t *ctx)
 	return ctx->cpidx + ctx->argc;
 }
 
-int parse_options(int argc, const char **argv, const struct option *options,
-		  const char * const usagestr[], int flags)
+int parse_options_subcommand(int argc, const char **argv, const struct option *options,
+			const char *const subcommands[], const char *usagestr[], int flags)
 {
 	struct parse_opt_ctx_t ctx;
 
+	perf_header__set_cmdline(argc, argv);
+
+	/* build usage string if it's not provided */
+	if (subcommands && !usagestr[0]) {
+		struct strbuf buf = STRBUF_INIT;
+
+		strbuf_addf(&buf, "perf %s [<options>] {", argv[0]);
+		for (int i = 0; subcommands[i]; i++) {
+			if (i)
+				strbuf_addstr(&buf, "|");
+			strbuf_addstr(&buf, subcommands[i]);
+		}
+		strbuf_addstr(&buf, "}");
+
+		usagestr[0] = strdup(buf.buf);
+		strbuf_release(&buf);
+	}
+
 	parse_options_start(&ctx, argc, argv, flags);
 	switch (parse_options_step(&ctx, options, usagestr)) {
 	case PARSE_OPT_HELP:
 		exit(129);
 	case PARSE_OPT_DONE:
 		break;
+	case PARSE_OPT_LIST_OPTS:
+		while (options->type != OPTION_END) {
+			printf("--%s ", options->long_name);
+			options++;
+		}
+		exit(130);
+	case PARSE_OPT_LIST_SUBCMDS:
+		for (int i = 0; subcommands[i]; i++)
+			printf("%s ", subcommands[i]);
+		exit(130);
 	default: /* PARSE_OPT_UNKNOWN */
 		if (ctx.argv[0][1] == '-') {
 			error("unknown option `%s'", ctx.argv[0] + 2);
@@ -431,9 +486,99 @@ int parse_options(int argc, const char **argv, const struct option *options,
 	return parse_options_end(&ctx);
 }
 
+int parse_options(int argc, const char **argv, const struct option *options,
+		  const char * const usagestr[], int flags)
+{
+	return parse_options_subcommand(argc, argv, options, NULL,
+					(const char **) usagestr, flags);
+}
+
 #define USAGE_OPTS_WIDTH 24
 #define USAGE_GAP         2
 
+static void print_option_help(const struct option *opts, int full)
+{
+	size_t pos;
+	int pad;
+
+	if (opts->type == OPTION_GROUP) {
+		fputc('\n', stderr);
+		if (*opts->help)
+			fprintf(stderr, "%s\n", opts->help);
+		return;
+	}
+	if (!full && (opts->flags & PARSE_OPT_HIDDEN))
+		return;
+
+	pos = fprintf(stderr, "    ");
+	if (opts->short_name)
+		pos += fprintf(stderr, "-%c", opts->short_name);
+	else
+		pos += fprintf(stderr, "    ");
+
+	if (opts->long_name && opts->short_name)
+		pos += fprintf(stderr, ", ");
+	if (opts->long_name)
+		pos += fprintf(stderr, "--%s", opts->long_name);
+
+	switch (opts->type) {
+	case OPTION_ARGUMENT:
+		break;
+	case OPTION_LONG:
+	case OPTION_U64:
+	case OPTION_INTEGER:
+	case OPTION_UINTEGER:
+		if (opts->flags & PARSE_OPT_OPTARG)
+			if (opts->long_name)
+				pos += fprintf(stderr, "[=<n>]");
+			else
+				pos += fprintf(stderr, "[<n>]");
+		else
+			pos += fprintf(stderr, " <n>");
+		break;
+	case OPTION_CALLBACK:
+		if (opts->flags & PARSE_OPT_NOARG)
+			break;
+		/* FALLTHROUGH */
+	case OPTION_STRING:
+		if (opts->argh) {
+			if (opts->flags & PARSE_OPT_OPTARG)
+				if (opts->long_name)
+					pos += fprintf(stderr, "[=<%s>]", opts->argh);
+				else
+					pos += fprintf(stderr, "[<%s>]", opts->argh);
+			else
+				pos += fprintf(stderr, " <%s>", opts->argh);
+		} else {
+			if (opts->flags & PARSE_OPT_OPTARG)
+				if (opts->long_name)
+					pos += fprintf(stderr, "[=...]");
+				else
+					pos += fprintf(stderr, "[...]");
+			else
+				pos += fprintf(stderr, " ...");
+		}
+		break;
+	default: /* OPTION_{BIT,BOOLEAN,SET_UINT,SET_PTR} */
+	case OPTION_END:
+	case OPTION_GROUP:
+	case OPTION_BIT:
+	case OPTION_BOOLEAN:
+	case OPTION_INCR:
+	case OPTION_SET_UINT:
+	case OPTION_SET_PTR:
+		break;
+	}
+
+	if (pos <= USAGE_OPTS_WIDTH)
+		pad = USAGE_OPTS_WIDTH - pos;
+	else {
+		fputc('\n', stderr);
+		pad = USAGE_OPTS_WIDTH;
+	}
+	fprintf(stderr, "%*s%s\n", pad + USAGE_GAP, "", opts->help);
+}
+
 int usage_with_options_internal(const char * const *usagestr,
 				const struct option *opts, int full)
 {
@@ -453,87 +598,9 @@ int usage_with_options_internal(const char * const *usagestr,
 	if (opts->type != OPTION_GROUP)
 		fputc('\n', stderr);
 
-	for (; opts->type != OPTION_END; opts++) {
-		size_t pos;
-		int pad;
+	for (  ; opts->type != OPTION_END; opts++)
+		print_option_help(opts, full);
 
-		if (opts->type == OPTION_GROUP) {
-			fputc('\n', stderr);
-			if (*opts->help)
-				fprintf(stderr, "%s\n", opts->help);
-			continue;
-		}
-		if (!full && (opts->flags & PARSE_OPT_HIDDEN))
-			continue;
-
-		pos = fprintf(stderr, "    ");
-		if (opts->short_name)
-			pos += fprintf(stderr, "-%c", opts->short_name);
-		else
-			pos += fprintf(stderr, "    ");
-
-		if (opts->long_name && opts->short_name)
-			pos += fprintf(stderr, ", ");
-		if (opts->long_name)
-			pos += fprintf(stderr, "--%s", opts->long_name);
-
-		switch (opts->type) {
-		case OPTION_ARGUMENT:
-			break;
-		case OPTION_LONG:
-		case OPTION_U64:
-		case OPTION_INTEGER:
-		case OPTION_UINTEGER:
-			if (opts->flags & PARSE_OPT_OPTARG)
-				if (opts->long_name)
-					pos += fprintf(stderr, "[=<n>]");
-				else
-					pos += fprintf(stderr, "[<n>]");
-			else
-				pos += fprintf(stderr, " <n>");
-			break;
-		case OPTION_CALLBACK:
-			if (opts->flags & PARSE_OPT_NOARG)
-				break;
-			/* FALLTHROUGH */
-		case OPTION_STRING:
-			if (opts->argh) {
-				if (opts->flags & PARSE_OPT_OPTARG)
-					if (opts->long_name)
-						pos += fprintf(stderr, "[=<%s>]", opts->argh);
-					else
-						pos += fprintf(stderr, "[<%s>]", opts->argh);
-				else
-					pos += fprintf(stderr, " <%s>", opts->argh);
-			} else {
-				if (opts->flags & PARSE_OPT_OPTARG)
-					if (opts->long_name)
-						pos += fprintf(stderr, "[=...]");
-					else
-						pos += fprintf(stderr, "[...]");
-				else
-					pos += fprintf(stderr, " ...");
-			}
-			break;
-		default: /* OPTION_{BIT,BOOLEAN,SET_UINT,SET_PTR} */
-		case OPTION_END:
-		case OPTION_GROUP:
-		case OPTION_BIT:
-		case OPTION_BOOLEAN:
-		case OPTION_INCR:
-		case OPTION_SET_UINT:
-		case OPTION_SET_PTR:
-			break;
-		}
-
-		if (pos <= USAGE_OPTS_WIDTH)
-			pad = USAGE_OPTS_WIDTH - pos;
-		else {
-			fputc('\n', stderr);
-			pad = USAGE_OPTS_WIDTH;
-		}
-		fprintf(stderr, "%*s%s\n", pad + USAGE_GAP, "", opts->help);
-	}
 	fputc('\n', stderr);
 
 	return PARSE_OPT_HELP;
@@ -548,13 +615,50 @@ void usage_with_options(const char * const *usagestr,
 }
 
 int parse_options_usage(const char * const *usagestr,
-			const struct option *opts)
+			const struct option *opts,
+			const char *optstr, bool short_opt)
 {
-	return usage_with_options_internal(usagestr, opts, 0);
+	if (!usagestr)
+		goto opt;
+
+	fprintf(stderr, "\n usage: %s\n", *usagestr++);
+	while (*usagestr && **usagestr)
+		fprintf(stderr, "    or: %s\n", *usagestr++);
+	while (*usagestr) {
+		fprintf(stderr, "%s%s\n",
+				**usagestr ? "    " : "",
+				*usagestr);
+		usagestr++;
+	}
+	fputc('\n', stderr);
+
+opt:
+	for (  ; opts->type != OPTION_END; opts++) {
+		if (short_opt) {
+			if (opts->short_name == *optstr)
+				break;
+			continue;
+		}
+
+		if (opts->long_name == NULL)
+			continue;
+
+		if (!prefixcmp(optstr, opts->long_name))
+			break;
+		if (!prefixcmp(optstr, "no-") &&
+		    !prefixcmp(optstr + 3, opts->long_name))
+			break;
+	}
+
+	if (opts->type != OPTION_END)
+		print_option_help(opts, 0);
+
+	return PARSE_OPT_HELP;
 }
 
 
-int parse_opt_verbosity_cb(const struct option *opt, const char *arg __used,
+int parse_opt_verbosity_cb(const struct option *opt,
+			   const char *arg __maybe_unused,
 			   int unset)
 {
 	int *target = opt->value;
diff --git a/tools/perf/util/parse-options.h b/tools/perf/util/parse-options.h
index c7d72dce54b..d8dac8ac5f3 100644
--- a/tools/perf/util/parse-options.h
+++ b/tools/perf/util/parse-options.h
@@ -82,6 +82,9 @@ typedef int parse_opt_cb(const struct option *, const char *arg, int unset);
  *   OPTION_{BIT,SET_UINT,SET_PTR} store the {mask,integer,pointer} to put in
  *   the value when met.
  *   CALLBACKS can use it like they want.
+ *
+ * `set`::
+ *   whether an option was set by the user
  */
 struct option {
 	enum parse_opt_type type;
@@ -94,6 +97,7 @@ struct option {
 	int flags;
 	parse_opt_cb *callback;
 	intptr_t defval;
+	bool *set;
 };
 
 #define check_vtype(v, type) ( BUILD_BUG_ON_ZERO(!__builtin_types_compatible_p(typeof(v), type)) + v )
@@ -103,6 +107,10 @@ struct option {
 #define OPT_GROUP(h)                { .type = OPTION_GROUP, .help = (h) }
 #define OPT_BIT(s, l, v, h, b)      { .type = OPTION_BIT, .short_name = (s), .long_name = (l), .value = check_vtype(v, int *), .help = (h), .defval = (b) }
 #define OPT_BOOLEAN(s, l, v, h)     { .type = OPTION_BOOLEAN, .short_name = (s), .long_name = (l), .value = check_vtype(v, bool *), .help = (h) }
+#define OPT_BOOLEAN_SET(s, l, v, os, h) \
+	{ .type = OPTION_BOOLEAN, .short_name = (s), .long_name = (l), \
+	.value = check_vtype(v, bool *), .help = (h), \
+	.set = check_vtype(os, bool *)}
 #define OPT_INCR(s, l, v, h)        { .type = OPTION_INCR, .short_name = (s), .long_name = (l), .value = check_vtype(v, int *), .help = (h) }
 #define OPT_SET_UINT(s, l, v, h, i)  { .type = OPTION_SET_UINT, .short_name = (s), .long_name = (l), .value = check_vtype(v, unsigned int *), .help = (h), .defval = (i) }
 #define OPT_SET_PTR(s, l, v, h, p)  { .type = OPTION_SET_PTR, .short_name = (s), .long_name = (l), .value = (v), .help = (h), .defval = (p) }
@@ -119,6 +127,10 @@ struct option {
 	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), (a), .help = (h), .callback = (f), .flags = PARSE_OPT_NOARG }
 #define OPT_CALLBACK_DEFAULT(s, l, v, a, h, f, d) \
 	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), (a), .help = (h), .callback = (f), .defval = (intptr_t)d, .flags = PARSE_OPT_LASTARG_DEFAULT }
+#define OPT_CALLBACK_DEFAULT_NOOPT(s, l, v, a, h, f, d) \
+	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l),\
+	.value = (v), (a), .help = (h), .callback = (f), .defval = (intptr_t)d,\
+	.flags = PARSE_OPT_LASTARG_DEFAULT | PARSE_OPT_NOARG}
 
 /* parse_options() will filter out the processed options and leave the
  * non-option argments in argv[].
@@ -128,6 +140,11 @@ extern int parse_options(int argc, const char **argv,
                          const struct option *options,
                          const char * const usagestr[], int flags);
 
+extern int parse_options_subcommand(int argc, const char **argv,
+				const struct option *options,
+				const char *const subcommands[],
+				const char *usagestr[], int flags);
+
 extern NORETURN void usage_with_options(const char * const *usagestr,
                                         const struct option *options);
 
@@ -136,6 +153,8 @@ extern NORETURN void usage_with_options(const char * const *usagestr,
 enum {
 	PARSE_OPT_HELP = -1,
 	PARSE_OPT_DONE,
+	PARSE_OPT_LIST_OPTS,
+	PARSE_OPT_LIST_SUBCMDS,
 	PARSE_OPT_UNKNOWN,
 };
 
@@ -153,7 +172,9 @@ struct parse_opt_ctx_t {
 };
 
 extern int parse_options_usage(const char * const *usagestr,
-			       const struct option *opts);
+			       const struct option *opts,
+			       const char *optstr,
+			       bool short_opt);
 
 extern void parse_options_start(struct parse_opt_ctx_t *ctx,
 				int argc, const char **argv, int flags);
diff --git a/tools/perf/util/path.c b/tools/perf/util/path.c
index 58a470d036d..5d13cb45b31 100644
--- a/tools/perf/util/path.c
+++ b/tools/perf/util/path.c
@@ -22,19 +22,24 @@ static const char *get_perf_dir(void)
 	return ".";
 }
 
-size_t strlcpy(char *dest, const char *src, size_t size)
+/*
+ * If libc has strlcpy() then that version will override this
+ * implementation:
+ */
+size_t __weak strlcpy(char *dest, const char *src, size_t size)
 {
 	size_t ret = strlen(src);
 
 	if (size) {
 		size_t len = (ret >= size) ? size - 1 : ret;
+
 		memcpy(dest, src, len);
 		dest[len] = '\0';
 	}
+
 	return ret;
 }
 
-
 static char *get_pathname(void)
 {
 	static char pathname_array[4][PATH_MAX];
diff --git a/tools/perf/util/perf_regs.c b/tools/perf/util/perf_regs.c
new file mode 100644
index 00000000000..43168fb0d9a
--- /dev/null
+++ b/tools/perf/util/perf_regs.c
@@ -0,0 +1,27 @@
+#include <errno.h>
+#include "perf_regs.h"
+#include "event.h"
+
+int perf_reg_value(u64 *valp, struct regs_dump *regs, int id)
+{
+	int i, idx = 0;
+	u64 mask = regs->mask;
+
+	if (regs->cache_mask & (1 << id))
+		goto out;
+
+	if (!(mask & (1 << id)))
+		return -EINVAL;
+
+	for (i = 0; i < id; i++) {
+		if (mask & (1 << i))
+			idx++;
+	}
+
+	regs->cache_mask |= (1 << id);
+	regs->cache_regs[id] = regs->regs[idx];
+
+out:
+	*valp = regs->cache_regs[id];
+	return 0;
+}
diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h
new file mode 100644
index 00000000000..980dbf76bc9
--- /dev/null
+++ b/tools/perf/util/perf_regs.h
@@ -0,0 +1,29 @@
+#ifndef __PERF_REGS_H
+#define __PERF_REGS_H
+
+#include <linux/types.h>
+
+struct regs_dump;
+
+#ifdef HAVE_PERF_REGS_SUPPORT
+#include <perf_regs.h>
+
+int perf_reg_value(u64 *valp, struct regs_dump *regs, int id);
+
+#else
+#define PERF_REGS_MASK	0
+#define PERF_REGS_MAX	0
+
+static inline const char *perf_reg_name(int id __maybe_unused)
+{
+	return NULL;
+}
+
+static inline int perf_reg_value(u64 *valp __maybe_unused,
+				 struct regs_dump *regs __maybe_unused,
+				 int id __maybe_unused)
+{
+	return 0;
+}
+#endif /* HAVE_PERF_REGS_SUPPORT */
+#endif /* __PERF_REGS_H */
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
new file mode 100644
index 00000000000..7a811eb61f7
--- /dev/null
+++ b/tools/perf/util/pmu.c
@@ -0,0 +1,796 @@
+#include <linux/list.h>
+#include <sys/types.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <dirent.h>
+#include <api/fs/fs.h>
+#include <locale.h>
+#include "util.h"
+#include "pmu.h"
+#include "parse-events.h"
+#include "cpumap.h"
+
+#define UNIT_MAX_LEN	31 /* max length for event unit name */
+
+struct perf_pmu_alias {
+	char *name;
+	struct list_head terms;
+	struct list_head list;
+	char unit[UNIT_MAX_LEN+1];
+	double scale;
+};
+
+struct perf_pmu_format {
+	char *name;
+	int value;
+	DECLARE_BITMAP(bits, PERF_PMU_FORMAT_BITS);
+	struct list_head list;
+};
+
+#define EVENT_SOURCE_DEVICE_PATH "/bus/event_source/devices/"
+
+int perf_pmu_parse(struct list_head *list, char *name);
+extern FILE *perf_pmu_in;
+
+static LIST_HEAD(pmus);
+
+/*
+ * Parse & process all the sysfs attributes located under
+ * the directory specified in 'dir' parameter.
+ */
+int perf_pmu__format_parse(char *dir, struct list_head *head)
+{
+	struct dirent *evt_ent;
+	DIR *format_dir;
+	int ret = 0;
+
+	format_dir = opendir(dir);
+	if (!format_dir)
+		return -EINVAL;
+
+	while (!ret && (evt_ent = readdir(format_dir))) {
+		char path[PATH_MAX];
+		char *name = evt_ent->d_name;
+		FILE *file;
+
+		if (!strcmp(name, ".") || !strcmp(name, ".."))
+			continue;
+
+		snprintf(path, PATH_MAX, "%s/%s", dir, name);
+
+		ret = -EINVAL;
+		file = fopen(path, "r");
+		if (!file)
+			break;
+
+		perf_pmu_in = file;
+		ret = perf_pmu_parse(head, name);
+		fclose(file);
+	}
+
+	closedir(format_dir);
+	return ret;
+}
+
+/*
+ * Reading/parsing the default pmu format definition, which should be
+ * located at:
+ * /sys/bus/event_source/devices/<dev>/format as sysfs group attributes.
+ */
+static int pmu_format(const char *name, struct list_head *format)
+{
+	struct stat st;
+	char path[PATH_MAX];
+	const char *sysfs = sysfs__mountpoint();
+
+	if (!sysfs)
+		return -1;
+
+	snprintf(path, PATH_MAX,
+		 "%s" EVENT_SOURCE_DEVICE_PATH "%s/format", sysfs, name);
+
+	if (stat(path, &st) < 0)
+		return 0;	/* no error if format does not exist */
+
+	if (perf_pmu__format_parse(path, format))
+		return -1;
+
+	return 0;
+}
+
+static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *name)
+{
+	struct stat st;
+	ssize_t sret;
+	char scale[128];
+	int fd, ret = -1;
+	char path[PATH_MAX];
+	const char *lc;
+
+	snprintf(path, PATH_MAX, "%s/%s.scale", dir, name);
+
+	fd = open(path, O_RDONLY);
+	if (fd == -1)
+		return -1;
+
+	if (fstat(fd, &st) < 0)
+		goto error;
+
+	sret = read(fd, scale, sizeof(scale)-1);
+	if (sret < 0)
+		goto error;
+
+	scale[sret] = '\0';
+	/*
+	 * save current locale
+	 */
+	lc = setlocale(LC_NUMERIC, NULL);
+
+	/*
+	 * force to C locale to ensure kernel
+	 * scale string is converted correctly.
+	 * kernel uses default C locale.
+	 */
+	setlocale(LC_NUMERIC, "C");
+
+	alias->scale = strtod(scale, NULL);
+
+	/* restore locale */
+	setlocale(LC_NUMERIC, lc);
+
+	ret = 0;
+error:
+	close(fd);
+	return ret;
+}
+
+static int perf_pmu__parse_unit(struct perf_pmu_alias *alias, char *dir, char *name)
+{
+	char path[PATH_MAX];
+	ssize_t sret;
+	int fd;
+
+	snprintf(path, PATH_MAX, "%s/%s.unit", dir, name);
+
+	fd = open(path, O_RDONLY);
+	if (fd == -1)
+		return -1;
+
+		sret = read(fd, alias->unit, UNIT_MAX_LEN);
+	if (sret < 0)
+		goto error;
+
+	close(fd);
+
+	alias->unit[sret] = '\0';
+
+	return 0;
+error:
+	close(fd);
+	alias->unit[0] = '\0';
+	return -1;
+}
+
+static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FILE *file)
+{
+	struct perf_pmu_alias *alias;
+	char buf[256];
+	int ret;
+
+	ret = fread(buf, 1, sizeof(buf), file);
+	if (ret == 0)
+		return -EINVAL;
+	buf[ret] = 0;
+
+	alias = malloc(sizeof(*alias));
+	if (!alias)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&alias->terms);
+	alias->scale = 1.0;
+	alias->unit[0] = '\0';
+
+	ret = parse_events_terms(&alias->terms, buf);
+	if (ret) {
+		free(alias);
+		return ret;
+	}
+
+	alias->name = strdup(name);
+	/*
+	 * load unit name and scale if available
+	 */
+	perf_pmu__parse_unit(alias, dir, name);
+	perf_pmu__parse_scale(alias, dir, name);
+
+	list_add_tail(&alias->list, list);
+
+	return 0;
+}
+
+/*
+ * Process all the sysfs attributes located under the directory
+ * specified in 'dir' parameter.
+ */
+static int pmu_aliases_parse(char *dir, struct list_head *head)
+{
+	struct dirent *evt_ent;
+	DIR *event_dir;
+	size_t len;
+	int ret = 0;
+
+	event_dir = opendir(dir);
+	if (!event_dir)
+		return -EINVAL;
+
+	while (!ret && (evt_ent = readdir(event_dir))) {
+		char path[PATH_MAX];
+		char *name = evt_ent->d_name;
+		FILE *file;
+
+		if (!strcmp(name, ".") || !strcmp(name, ".."))
+			continue;
+
+		/*
+		 * skip .unit and .scale info files
+		 * parsed in perf_pmu__new_alias()
+		 */
+		len = strlen(name);
+		if (len > 5 && !strcmp(name + len - 5, ".unit"))
+			continue;
+		if (len > 6 && !strcmp(name + len - 6, ".scale"))
+			continue;
+
+		snprintf(path, PATH_MAX, "%s/%s", dir, name);
+
+		ret = -EINVAL;
+		file = fopen(path, "r");
+		if (!file)
+			break;
+
+		ret = perf_pmu__new_alias(head, dir, name, file);
+		fclose(file);
+	}
+
+	closedir(event_dir);
+	return ret;
+}
+
+/*
+ * Reading the pmu event aliases definition, which should be located at:
+ * /sys/bus/event_source/devices/<dev>/events as sysfs group attributes.
+ */
+static int pmu_aliases(const char *name, struct list_head *head)
+{
+	struct stat st;
+	char path[PATH_MAX];
+	const char *sysfs = sysfs__mountpoint();
+
+	if (!sysfs)
+		return -1;
+
+	snprintf(path, PATH_MAX,
+		 "%s/bus/event_source/devices/%s/events", sysfs, name);
+
+	if (stat(path, &st) < 0)
+		return 0;	 /* no error if 'events' does not exist */
+
+	if (pmu_aliases_parse(path, head))
+		return -1;
+
+	return 0;
+}
+
+static int pmu_alias_terms(struct perf_pmu_alias *alias,
+			   struct list_head *terms)
+{
+	struct parse_events_term *term, *cloned;
+	LIST_HEAD(list);
+	int ret;
+
+	list_for_each_entry(term, &alias->terms, list) {
+		ret = parse_events_term__clone(&cloned, term);
+		if (ret) {
+			parse_events__free_terms(&list);
+			return ret;
+		}
+		list_add_tail(&cloned->list, &list);
+	}
+	list_splice(&list, terms);
+	return 0;
+}
+
+/*
+ * Reading/parsing the default pmu type value, which should be
+ * located at:
+ * /sys/bus/event_source/devices/<dev>/type as sysfs attribute.
+ */
+static int pmu_type(const char *name, __u32 *type)
+{
+	struct stat st;
+	char path[PATH_MAX];
+	FILE *file;
+	int ret = 0;
+	const char *sysfs = sysfs__mountpoint();
+
+	if (!sysfs)
+		return -1;
+
+	snprintf(path, PATH_MAX,
+		 "%s" EVENT_SOURCE_DEVICE_PATH "%s/type", sysfs, name);
+
+	if (stat(path, &st) < 0)
+		return -1;
+
+	file = fopen(path, "r");
+	if (!file)
+		return -EINVAL;
+
+	if (1 != fscanf(file, "%u", type))
+		ret = -1;
+
+	fclose(file);
+	return ret;
+}
+
+/* Add all pmus in sysfs to pmu list: */
+static void pmu_read_sysfs(void)
+{
+	char path[PATH_MAX];
+	DIR *dir;
+	struct dirent *dent;
+	const char *sysfs = sysfs__mountpoint();
+
+	if (!sysfs)
+		return;
+
+	snprintf(path, PATH_MAX,
+		 "%s" EVENT_SOURCE_DEVICE_PATH, sysfs);
+
+	dir = opendir(path);
+	if (!dir)
+		return;
+
+	while ((dent = readdir(dir))) {
+		if (!strcmp(dent->d_name, ".") || !strcmp(dent->d_name, ".."))
+			continue;
+		/* add to static LIST_HEAD(pmus): */
+		perf_pmu__find(dent->d_name);
+	}
+
+	closedir(dir);
+}
+
+static struct cpu_map *pmu_cpumask(const char *name)
+{
+	struct stat st;
+	char path[PATH_MAX];
+	FILE *file;
+	struct cpu_map *cpus;
+	const char *sysfs = sysfs__mountpoint();
+
+	if (!sysfs)
+		return NULL;
+
+	snprintf(path, PATH_MAX,
+		 "%s/bus/event_source/devices/%s/cpumask", sysfs, name);
+
+	if (stat(path, &st) < 0)
+		return NULL;
+
+	file = fopen(path, "r");
+	if (!file)
+		return NULL;
+
+	cpus = cpu_map__read(file);
+	fclose(file);
+	return cpus;
+}
+
+static struct perf_pmu *pmu_lookup(const char *name)
+{
+	struct perf_pmu *pmu;
+	LIST_HEAD(format);
+	LIST_HEAD(aliases);
+	__u32 type;
+
+	/*
+	 * The pmu data we store & need consists of the pmu
+	 * type value and format definitions. Load both right
+	 * now.
+	 */
+	if (pmu_format(name, &format))
+		return NULL;
+
+	if (pmu_aliases(name, &aliases))
+		return NULL;
+
+	if (pmu_type(name, &type))
+		return NULL;
+
+	pmu = zalloc(sizeof(*pmu));
+	if (!pmu)
+		return NULL;
+
+	pmu->cpus = pmu_cpumask(name);
+
+	INIT_LIST_HEAD(&pmu->format);
+	INIT_LIST_HEAD(&pmu->aliases);
+	list_splice(&format, &pmu->format);
+	list_splice(&aliases, &pmu->aliases);
+	pmu->name = strdup(name);
+	pmu->type = type;
+	list_add_tail(&pmu->list, &pmus);
+	return pmu;
+}
+
+static struct perf_pmu *pmu_find(const char *name)
+{
+	struct perf_pmu *pmu;
+
+	list_for_each_entry(pmu, &pmus, list)
+		if (!strcmp(pmu->name, name))
+			return pmu;
+
+	return NULL;
+}
+
+struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu)
+{
+	/*
+	 * pmu iterator: If pmu is NULL, we start at the begin,
+	 * otherwise return the next pmu. Returns NULL on end.
+	 */
+	if (!pmu) {
+		pmu_read_sysfs();
+		pmu = list_prepare_entry(pmu, &pmus, list);
+	}
+	list_for_each_entry_continue(pmu, &pmus, list)
+		return pmu;
+	return NULL;
+}
+
+struct perf_pmu *perf_pmu__find(const char *name)
+{
+	struct perf_pmu *pmu;
+
+	/*
+	 * Once PMU is loaded it stays in the list,
+	 * so we keep us from multiple reading/parsing
+	 * the pmu format definitions.
+	 */
+	pmu = pmu_find(name);
+	if (pmu)
+		return pmu;
+
+	return pmu_lookup(name);
+}
+
+static struct perf_pmu_format *
+pmu_find_format(struct list_head *formats, char *name)
+{
+	struct perf_pmu_format *format;
+
+	list_for_each_entry(format, formats, list)
+		if (!strcmp(format->name, name))
+			return format;
+
+	return NULL;
+}
+
+/*
+ * Returns value based on the format definition (format parameter)
+ * and unformated value (value parameter).
+ *
+ * TODO maybe optimize a little ;)
+ */
+static __u64 pmu_format_value(unsigned long *format, __u64 value)
+{
+	unsigned long fbit, vbit;
+	__u64 v = 0;
+
+	for (fbit = 0, vbit = 0; fbit < PERF_PMU_FORMAT_BITS; fbit++) {
+
+		if (!test_bit(fbit, format))
+			continue;
+
+		if (!(value & (1llu << vbit++)))
+			continue;
+
+		v |= (1llu << fbit);
+	}
+
+	return v;
+}
+
+/*
+ * Setup one of config[12] attr members based on the
+ * user input data - term parameter.
+ */
+static int pmu_config_term(struct list_head *formats,
+			   struct perf_event_attr *attr,
+			   struct parse_events_term *term)
+{
+	struct perf_pmu_format *format;
+	__u64 *vp;
+
+	/*
+	 * Support only for hardcoded and numnerial terms.
+	 * Hardcoded terms should be already in, so nothing
+	 * to be done for them.
+	 */
+	if (parse_events__is_hardcoded_term(term))
+		return 0;
+
+	if (term->type_val != PARSE_EVENTS__TERM_TYPE_NUM)
+		return -EINVAL;
+
+	format = pmu_find_format(formats, term->config);
+	if (!format)
+		return -EINVAL;
+
+	switch (format->value) {
+	case PERF_PMU_FORMAT_VALUE_CONFIG:
+		vp = &attr->config;
+		break;
+	case PERF_PMU_FORMAT_VALUE_CONFIG1:
+		vp = &attr->config1;
+		break;
+	case PERF_PMU_FORMAT_VALUE_CONFIG2:
+		vp = &attr->config2;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/*
+	 * XXX If we ever decide to go with string values for
+	 * non-hardcoded terms, here's the place to translate
+	 * them into value.
+	 */
+	*vp |= pmu_format_value(format->bits, term->val.num);
+	return 0;
+}
+
+int perf_pmu__config_terms(struct list_head *formats,
+			   struct perf_event_attr *attr,
+			   struct list_head *head_terms)
+{
+	struct parse_events_term *term;
+
+	list_for_each_entry(term, head_terms, list)
+		if (pmu_config_term(formats, attr, term))
+			return -EINVAL;
+
+	return 0;
+}
+
+/*
+ * Configures event's 'attr' parameter based on the:
+ * 1) users input - specified in terms parameter
+ * 2) pmu format definitions - specified by pmu parameter
+ */
+int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
+		     struct list_head *head_terms)
+{
+	attr->type = pmu->type;
+	return perf_pmu__config_terms(&pmu->format, attr, head_terms);
+}
+
+static struct perf_pmu_alias *pmu_find_alias(struct perf_pmu *pmu,
+					     struct parse_events_term *term)
+{
+	struct perf_pmu_alias *alias;
+	char *name;
+
+	if (parse_events__is_hardcoded_term(term))
+		return NULL;
+
+	if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM) {
+		if (term->val.num != 1)
+			return NULL;
+		if (pmu_find_format(&pmu->format, term->config))
+			return NULL;
+		name = term->config;
+	} else if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR) {
+		if (strcasecmp(term->config, "event"))
+			return NULL;
+		name = term->val.str;
+	} else {
+		return NULL;
+	}
+
+	list_for_each_entry(alias, &pmu->aliases, list) {
+		if (!strcasecmp(alias->name, name))
+			return alias;
+	}
+	return NULL;
+}
+
+
+static int check_unit_scale(struct perf_pmu_alias *alias,
+			    const char **unit, double *scale)
+{
+	/*
+	 * Only one term in event definition can
+	 * define unit and scale, fail if there's
+	 * more than one.
+	 */
+	if ((*unit && alias->unit) ||
+	    (*scale && alias->scale))
+		return -EINVAL;
+
+	if (alias->unit)
+		*unit = alias->unit;
+
+	if (alias->scale)
+		*scale = alias->scale;
+
+	return 0;
+}
+
+/*
+ * Find alias in the terms list and replace it with the terms
+ * defined for the alias
+ */
+int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
+			  const char **unit, double *scale)
+{
+	struct parse_events_term *term, *h;
+	struct perf_pmu_alias *alias;
+	int ret;
+
+	/*
+	 * Mark unit and scale as not set
+	 * (different from default values, see below)
+	 */
+	*unit   = NULL;
+	*scale  = 0.0;
+
+	list_for_each_entry_safe(term, h, head_terms, list) {
+		alias = pmu_find_alias(pmu, term);
+		if (!alias)
+			continue;
+		ret = pmu_alias_terms(alias, &term->list);
+		if (ret)
+			return ret;
+
+		ret = check_unit_scale(alias, unit, scale);
+		if (ret)
+			return ret;
+
+		list_del(&term->list);
+		free(term);
+	}
+
+	/*
+	 * if no unit or scale foundin aliases, then
+	 * set defaults as for evsel
+	 * unit cannot left to NULL
+	 */
+	if (*unit == NULL)
+		*unit   = "";
+
+	if (*scale == 0.0)
+		*scale  = 1.0;
+
+	return 0;
+}
+
+int perf_pmu__new_format(struct list_head *list, char *name,
+			 int config, unsigned long *bits)
+{
+	struct perf_pmu_format *format;
+
+	format = zalloc(sizeof(*format));
+	if (!format)
+		return -ENOMEM;
+
+	format->name = strdup(name);
+	format->value = config;
+	memcpy(format->bits, bits, sizeof(format->bits));
+
+	list_add_tail(&format->list, list);
+	return 0;
+}
+
+void perf_pmu__set_format(unsigned long *bits, long from, long to)
+{
+	long b;
+
+	if (!to)
+		to = from;
+
+	memset(bits, 0, BITS_TO_BYTES(PERF_PMU_FORMAT_BITS));
+	for (b = from; b <= to; b++)
+		set_bit(b, bits);
+}
+
+static char *format_alias(char *buf, int len, struct perf_pmu *pmu,
+			  struct perf_pmu_alias *alias)
+{
+	snprintf(buf, len, "%s/%s/", pmu->name, alias->name);
+	return buf;
+}
+
+static char *format_alias_or(char *buf, int len, struct perf_pmu *pmu,
+			     struct perf_pmu_alias *alias)
+{
+	snprintf(buf, len, "%s OR %s/%s/", alias->name, pmu->name, alias->name);
+	return buf;
+}
+
+static int cmp_string(const void *a, const void *b)
+{
+	const char * const *as = a;
+	const char * const *bs = b;
+	return strcmp(*as, *bs);
+}
+
+void print_pmu_events(const char *event_glob, bool name_only)
+{
+	struct perf_pmu *pmu;
+	struct perf_pmu_alias *alias;
+	char buf[1024];
+	int printed = 0;
+	int len, j;
+	char **aliases;
+
+	pmu = NULL;
+	len = 0;
+	while ((pmu = perf_pmu__scan(pmu)) != NULL)
+		list_for_each_entry(alias, &pmu->aliases, list)
+			len++;
+	aliases = malloc(sizeof(char *) * len);
+	if (!aliases)
+		return;
+	pmu = NULL;
+	j = 0;
+	while ((pmu = perf_pmu__scan(pmu)) != NULL)
+		list_for_each_entry(alias, &pmu->aliases, list) {
+			char *name = format_alias(buf, sizeof(buf), pmu, alias);
+			bool is_cpu = !strcmp(pmu->name, "cpu");
+
+			if (event_glob != NULL &&
+			    !(strglobmatch(name, event_glob) ||
+			      (!is_cpu && strglobmatch(alias->name,
+						       event_glob))))
+				continue;
+			aliases[j] = name;
+			if (is_cpu && !name_only)
+				aliases[j] = format_alias_or(buf, sizeof(buf),
+							      pmu, alias);
+			aliases[j] = strdup(aliases[j]);
+			j++;
+		}
+	len = j;
+	qsort(aliases, len, sizeof(char *), cmp_string);
+	for (j = 0; j < len; j++) {
+		if (name_only) {
+			printf("%s ", aliases[j]);
+			continue;
+		}
+		printf("  %-50s [Kernel PMU event]\n", aliases[j]);
+		zfree(&aliases[j]);
+		printed++;
+	}
+	if (printed)
+		printf("\n");
+	free(aliases);
+}
+
+bool pmu_have_event(const char *pname, const char *name)
+{
+	struct perf_pmu *pmu;
+	struct perf_pmu_alias *alias;
+
+	pmu = NULL;
+	while ((pmu = perf_pmu__scan(pmu)) != NULL) {
+		if (strcmp(pname, pmu->name))
+			continue;
+		list_for_each_entry(alias, &pmu->aliases, list)
+			if (!strcmp(alias->name, name))
+				return true;
+	}
+	return false;
+}
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
new file mode 100644
index 00000000000..c14a543ce1f
--- /dev/null
+++ b/tools/perf/util/pmu.h
@@ -0,0 +1,49 @@
+#ifndef __PMU_H
+#define __PMU_H
+
+#include <linux/bitmap.h>
+#include <linux/perf_event.h>
+#include <stdbool.h>
+
+enum {
+	PERF_PMU_FORMAT_VALUE_CONFIG,
+	PERF_PMU_FORMAT_VALUE_CONFIG1,
+	PERF_PMU_FORMAT_VALUE_CONFIG2,
+};
+
+#define PERF_PMU_FORMAT_BITS 64
+
+struct perf_pmu {
+	char *name;
+	__u32 type;
+	struct cpu_map *cpus;
+	struct list_head format;
+	struct list_head aliases;
+	struct list_head list;
+};
+
+struct perf_pmu *perf_pmu__find(const char *name);
+int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
+		     struct list_head *head_terms);
+int perf_pmu__config_terms(struct list_head *formats,
+			   struct perf_event_attr *attr,
+			   struct list_head *head_terms);
+int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
+			  const char **unit, double *scale);
+struct list_head *perf_pmu__alias(struct perf_pmu *pmu,
+				  struct list_head *head_terms);
+int perf_pmu_wrap(void);
+void perf_pmu_error(struct list_head *list, char *name, char const *msg);
+
+int perf_pmu__new_format(struct list_head *list, char *name,
+			 int config, unsigned long *bits);
+void perf_pmu__set_format(unsigned long *bits, long from, long to);
+int perf_pmu__format_parse(char *dir, struct list_head *head);
+
+struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu);
+
+void print_pmu_events(const char *event_glob, bool name_only);
+bool pmu_have_event(const char *pname, const char *name);
+
+int perf_pmu__test(void);
+#endif /* __PMU_H */
diff --git a/tools/perf/util/pmu.l b/tools/perf/util/pmu.l
new file mode 100644
index 00000000000..a15d9fbd7c0
--- /dev/null
+++ b/tools/perf/util/pmu.l
@@ -0,0 +1,43 @@
+%option prefix="perf_pmu_"
+
+%{
+#include <stdlib.h>
+#include <linux/bitops.h>
+#include "pmu.h"
+#include "pmu-bison.h"
+
+static int value(int base)
+{
+	long num;
+
+	errno = 0;
+	num = strtoul(perf_pmu_text, NULL, base);
+	if (errno)
+		return PP_ERROR;
+
+	perf_pmu_lval.num = num;
+	return PP_VALUE;
+}
+
+%}
+
+num_dec         [0-9]+
+
+%%
+
+{num_dec}	{ return value(10); }
+config		{ return PP_CONFIG; }
+config1		{ return PP_CONFIG1; }
+config2		{ return PP_CONFIG2; }
+-		{ return '-'; }
+:		{ return ':'; }
+,		{ return ','; }
+.		{ ; }
+\n		{ ; }
+
+%%
+
+int perf_pmu_wrap(void)
+{
+	return 1;
+}
diff --git a/tools/perf/util/pmu.y b/tools/perf/util/pmu.y
new file mode 100644
index 00000000000..bfd7e850986
--- /dev/null
+++ b/tools/perf/util/pmu.y
@@ -0,0 +1,92 @@
+
+%parse-param {struct list_head *format}
+%parse-param {char *name}
+
+%{
+
+#include <linux/compiler.h>
+#include <linux/list.h>
+#include <linux/bitmap.h>
+#include <string.h>
+#include "pmu.h"
+
+extern int perf_pmu_lex (void);
+
+#define ABORT_ON(val) \
+do { \
+        if (val) \
+                YYABORT; \
+} while (0)
+
+%}
+
+%token PP_CONFIG PP_CONFIG1 PP_CONFIG2
+%token PP_VALUE PP_ERROR
+%type <num> PP_VALUE
+%type <bits> bit_term
+%type <bits> bits
+
+%union
+{
+	unsigned long num;
+	DECLARE_BITMAP(bits, PERF_PMU_FORMAT_BITS);
+}
+
+%%
+
+format:
+format format_term
+|
+format_term
+
+format_term:
+PP_CONFIG ':' bits
+{
+	ABORT_ON(perf_pmu__new_format(format, name,
+				      PERF_PMU_FORMAT_VALUE_CONFIG,
+				      $3));
+}
+|
+PP_CONFIG1 ':' bits
+{
+	ABORT_ON(perf_pmu__new_format(format, name,
+				      PERF_PMU_FORMAT_VALUE_CONFIG1,
+				      $3));
+}
+|
+PP_CONFIG2 ':' bits
+{
+	ABORT_ON(perf_pmu__new_format(format, name,
+				      PERF_PMU_FORMAT_VALUE_CONFIG2,
+				      $3));
+}
+
+bits:
+bits ',' bit_term
+{
+	bitmap_or($$, $1, $3, 64);
+}
+|
+bit_term
+{
+	memcpy($$, $1, sizeof($1));
+}
+
+bit_term:
+PP_VALUE '-' PP_VALUE
+{
+	perf_pmu__set_format($$, $1, $3);
+}
+|
+PP_VALUE
+{
+	perf_pmu__set_format($$, $1, 0);
+}
+
+%%
+
+void perf_pmu_error(struct list_head *list __maybe_unused,
+		    char *name __maybe_unused,
+		    char const *msg __maybe_unused)
+{
+}
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 914c67095d9..9a0a1839a37 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -1,5 +1,5 @@
 /*
- * probe-event.c : perf-probe definition to kprobe_events format converter
+ * probe-event.c : perf-probe definition to probe_events format converter
  *
  * Written by Masami Hiramatsu <mhiramat@redhat.com>
  *
@@ -19,7 +19,6 @@
  *
  */
 
-#define _GNU_SOURCE
 #include <sys/utsname.h>
 #include <sys/types.h>
 #include <sys/stat.h>
@@ -31,24 +30,23 @@
 #include <string.h>
 #include <stdarg.h>
 #include <limits.h>
+#include <elf.h>
 
-#undef _GNU_SOURCE
 #include "util.h"
 #include "event.h"
-#include "string.h"
 #include "strlist.h"
 #include "debug.h"
 #include "cache.h"
 #include "color.h"
 #include "symbol.h"
 #include "thread.h"
-#include "debugfs.h"
-#include "trace-event.h"	/* For __unused */
+#include <api/fs/debugfs.h>
+#include "trace-event.h"	/* For __maybe_unused */
 #include "probe-event.h"
 #include "probe-finder.h"
+#include "session.h"
 
 #define MAX_CMDLEN 256
-#define MAX_PROBE_ARGS 128
 #define PERFPROBE_GROUP "probe"
 
 bool probe_event_dry_run;	/* Dry run flag */
@@ -72,109 +70,419 @@ static int e_snprintf(char *str, size_t size, const char *format, ...)
 }
 
 static char *synthesize_perf_probe_point(struct perf_probe_point *pp);
-static struct machine machine;
+static void clear_probe_trace_event(struct probe_trace_event *tev);
+static struct machine *host_machine;
 
-/* Initialize symbol maps and path of vmlinux */
-static int init_vmlinux(void)
+/* Initialize symbol maps and path of vmlinux/modules */
+static int init_symbol_maps(bool user_only)
 {
-	struct dso *kernel;
 	int ret;
 
 	symbol_conf.sort_by_name = true;
-	if (symbol_conf.vmlinux_name == NULL)
-		symbol_conf.try_vmlinux_path = true;
-	else
-		pr_debug("Use vmlinux: %s\n", symbol_conf.vmlinux_name);
 	ret = symbol__init();
 	if (ret < 0) {
 		pr_debug("Failed to init symbol map.\n");
 		goto out;
 	}
 
-	ret = machine__init(&machine, "/", 0);
-	if (ret < 0)
-		goto out;
-
-	kernel = dso__new_kernel(symbol_conf.vmlinux_name);
-	if (kernel == NULL)
-		die("Failed to create kernel dso.");
+	if (host_machine || user_only)	/* already initialized */
+		return 0;
 
-	ret = __machine__create_kernel_maps(&machine, kernel);
-	if (ret < 0)
-		pr_debug("Failed to create kernel maps.\n");
+	if (symbol_conf.vmlinux_name)
+		pr_debug("Use vmlinux: %s\n", symbol_conf.vmlinux_name);
 
+	host_machine = machine__new_host();
+	if (!host_machine) {
+		pr_debug("machine__new_host() failed.\n");
+		symbol__exit();
+		ret = -1;
+	}
 out:
 	if (ret < 0)
 		pr_warning("Failed to init vmlinux path.\n");
 	return ret;
 }
 
-#ifdef DWARF_SUPPORT
-static int open_vmlinux(void)
+static void exit_symbol_maps(void)
 {
-	if (map__load(machine.vmlinux_maps[MAP__FUNCTION], NULL) < 0) {
-		pr_debug("Failed to load kernel map.\n");
-		return -EINVAL;
+	if (host_machine) {
+		machine__delete(host_machine);
+		host_machine = NULL;
 	}
-	pr_debug("Try to open %s\n", machine.vmlinux_maps[MAP__FUNCTION]->dso->long_name);
-	return open(machine.vmlinux_maps[MAP__FUNCTION]->dso->long_name, O_RDONLY);
+	symbol__exit();
+}
+
+static struct symbol *__find_kernel_function_by_name(const char *name,
+						     struct map **mapp)
+{
+	return machine__find_kernel_function_by_name(host_machine, name, mapp,
+						     NULL);
+}
+
+static struct symbol *__find_kernel_function(u64 addr, struct map **mapp)
+{
+	return machine__find_kernel_function(host_machine, addr, mapp, NULL);
+}
+
+static struct ref_reloc_sym *kernel_get_ref_reloc_sym(void)
+{
+	/* kmap->ref_reloc_sym should be set if host_machine is initialized */
+	struct kmap *kmap;
+
+	if (map__load(host_machine->vmlinux_maps[MAP__FUNCTION], NULL) < 0)
+		return NULL;
+
+	kmap = map__kmap(host_machine->vmlinux_maps[MAP__FUNCTION]);
+	return kmap->ref_reloc_sym;
 }
 
-/* Convert trace point to probe point with debuginfo */
-static int convert_to_perf_probe_point(struct kprobe_trace_point *tp,
-				       struct perf_probe_point *pp)
+static u64 kernel_get_symbol_address_by_name(const char *name, bool reloc)
 {
+	struct ref_reloc_sym *reloc_sym;
 	struct symbol *sym;
+	struct map *map;
+
+	/* ref_reloc_sym is just a label. Need a special fix*/
+	reloc_sym = kernel_get_ref_reloc_sym();
+	if (reloc_sym && strcmp(name, reloc_sym->name) == 0)
+		return (reloc) ? reloc_sym->addr : reloc_sym->unrelocated_addr;
+	else {
+		sym = __find_kernel_function_by_name(name, &map);
+		if (sym)
+			return map->unmap_ip(map, sym->start) -
+				(reloc) ? 0 : map->reloc;
+	}
+	return 0;
+}
+
+static struct map *kernel_get_module_map(const char *module)
+{
+	struct rb_node *nd;
+	struct map_groups *grp = &host_machine->kmaps;
+
+	/* A file path -- this is an offline module */
+	if (module && strchr(module, '/'))
+		return machine__new_module(host_machine, 0, module);
+
+	if (!module)
+		module = "kernel";
+
+	for (nd = rb_first(&grp->maps[MAP__FUNCTION]); nd; nd = rb_next(nd)) {
+		struct map *pos = rb_entry(nd, struct map, rb_node);
+		if (strncmp(pos->dso->short_name + 1, module,
+			    pos->dso->short_name_len - 2) == 0) {
+			return pos;
+		}
+	}
+	return NULL;
+}
+
+static struct dso *kernel_get_module_dso(const char *module)
+{
+	struct dso *dso;
+	struct map *map;
+	const char *vmlinux_name;
+
+	if (module) {
+		list_for_each_entry(dso, &host_machine->kernel_dsos, node) {
+			if (strncmp(dso->short_name + 1, module,
+				    dso->short_name_len - 2) == 0)
+				goto found;
+		}
+		pr_debug("Failed to find module %s.\n", module);
+		return NULL;
+	}
+
+	map = host_machine->vmlinux_maps[MAP__FUNCTION];
+	dso = map->dso;
+
+	vmlinux_name = symbol_conf.vmlinux_name;
+	if (vmlinux_name) {
+		if (dso__load_vmlinux(dso, map, vmlinux_name, false, NULL) <= 0)
+			return NULL;
+	} else {
+		if (dso__load_vmlinux_path(dso, map, NULL) <= 0) {
+			pr_debug("Failed to load kernel map.\n");
+			return NULL;
+		}
+	}
+found:
+	return dso;
+}
+
+const char *kernel_get_module_path(const char *module)
+{
+	struct dso *dso = kernel_get_module_dso(module);
+	return (dso) ? dso->long_name : NULL;
+}
+
+static int convert_exec_to_group(const char *exec, char **result)
+{
+	char *ptr1, *ptr2, *exec_copy;
+	char buf[64];
+	int ret;
+
+	exec_copy = strdup(exec);
+	if (!exec_copy)
+		return -ENOMEM;
+
+	ptr1 = basename(exec_copy);
+	if (!ptr1) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	ptr2 = strpbrk(ptr1, "-._");
+	if (ptr2)
+		*ptr2 = '\0';
+	ret = e_snprintf(buf, 64, "%s_%s", PERFPROBE_GROUP, ptr1);
+	if (ret < 0)
+		goto out;
+
+	*result = strdup(buf);
+	ret = *result ? 0 : -ENOMEM;
+
+out:
+	free(exec_copy);
+	return ret;
+}
+
+static void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs)
+{
+	int i;
+
+	for (i = 0; i < ntevs; i++)
+		clear_probe_trace_event(tevs + i);
+}
+
+#ifdef HAVE_DWARF_SUPPORT
+
+/* Open new debuginfo of given module */
+static struct debuginfo *open_debuginfo(const char *module)
+{
+	const char *path = module;
+
+	if (!module || !strchr(module, '/')) {
+		path = kernel_get_module_path(module);
+		if (!path) {
+			pr_err("Failed to find path of %s module.\n",
+			       module ?: "kernel");
+			return NULL;
+		}
+	}
+	return debuginfo__new(path);
+}
+
+static int get_text_start_address(const char *exec, unsigned long *address)
+{
+	Elf *elf;
+	GElf_Ehdr ehdr;
+	GElf_Shdr shdr;
 	int fd, ret = -ENOENT;
 
-	sym = map__find_symbol_by_name(machine.vmlinux_maps[MAP__FUNCTION],
-				       tp->symbol, NULL);
-	if (sym) {
-		fd = open_vmlinux();
-		if (fd >= 0) {
-			ret = find_perf_probe_point(fd,
-						 sym->start + tp->offset, pp);
-			close(fd);
+	fd = open(exec, O_RDONLY);
+	if (fd < 0)
+		return -errno;
+
+	elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
+	if (elf == NULL)
+		return -EINVAL;
+
+	if (gelf_getehdr(elf, &ehdr) == NULL)
+		goto out;
+
+	if (!elf_section_by_name(elf, &ehdr, &shdr, ".text", NULL))
+		goto out;
+
+	*address = shdr.sh_addr - shdr.sh_offset;
+	ret = 0;
+out:
+	elf_end(elf);
+	return ret;
+}
+
+/*
+ * Convert trace point to probe point with debuginfo
+ */
+static int find_perf_probe_point_from_dwarf(struct probe_trace_point *tp,
+					    struct perf_probe_point *pp,
+					    bool is_kprobe)
+{
+	struct debuginfo *dinfo = NULL;
+	unsigned long stext = 0;
+	u64 addr = tp->address;
+	int ret = -ENOENT;
+
+	/* convert the address to dwarf address */
+	if (!is_kprobe) {
+		if (!addr) {
+			ret = -EINVAL;
+			goto error;
 		}
+		ret = get_text_start_address(tp->module, &stext);
+		if (ret < 0)
+			goto error;
+		addr += stext;
+	} else {
+		addr = kernel_get_symbol_address_by_name(tp->symbol, false);
+		if (addr == 0)
+			goto error;
+		addr += tp->offset;
 	}
-	if (ret <= 0) {
-		pr_debug("Failed to find corresponding probes from "
-			 "debuginfo. Use kprobe event information.\n");
-		pp->function = strdup(tp->symbol);
-		if (pp->function == NULL)
+
+	pr_debug("try to find information at %" PRIx64 " in %s\n", addr,
+		 tp->module ? : "kernel");
+
+	dinfo = open_debuginfo(tp->module);
+	if (dinfo) {
+		ret = debuginfo__find_probe_point(dinfo,
+						 (unsigned long)addr, pp);
+		debuginfo__delete(dinfo);
+	} else {
+		pr_debug("Failed to open debuginfo at 0x%" PRIx64 "\n", addr);
+		ret = -ENOENT;
+	}
+
+	if (ret > 0) {
+		pp->retprobe = tp->retprobe;
+		return 0;
+	}
+error:
+	pr_debug("Failed to find corresponding probes from debuginfo.\n");
+	return ret ? : -ENOENT;
+}
+
+static int add_exec_to_probe_trace_events(struct probe_trace_event *tevs,
+					  int ntevs, const char *exec)
+{
+	int i, ret = 0;
+	unsigned long stext = 0;
+
+	if (!exec)
+		return 0;
+
+	ret = get_text_start_address(exec, &stext);
+	if (ret < 0)
+		return ret;
+
+	for (i = 0; i < ntevs && ret >= 0; i++) {
+		/* point.address is the addres of point.symbol + point.offset */
+		tevs[i].point.address -= stext;
+		tevs[i].point.module = strdup(exec);
+		if (!tevs[i].point.module) {
+			ret = -ENOMEM;
+			break;
+		}
+		tevs[i].uprobes = true;
+	}
+
+	return ret;
+}
+
+static int add_module_to_probe_trace_events(struct probe_trace_event *tevs,
+					    int ntevs, const char *module)
+{
+	int i, ret = 0;
+	char *tmp;
+
+	if (!module)
+		return 0;
+
+	tmp = strrchr(module, '/');
+	if (tmp) {
+		/* This is a module path -- get the module name */
+		module = strdup(tmp + 1);
+		if (!module)
 			return -ENOMEM;
-		pp->offset = tp->offset;
+		tmp = strchr(module, '.');
+		if (tmp)
+			*tmp = '\0';
+		tmp = (char *)module;	/* For free() */
 	}
-	pp->retprobe = tp->retprobe;
 
+	for (i = 0; i < ntevs; i++) {
+		tevs[i].point.module = strdup(module);
+		if (!tevs[i].point.module) {
+			ret = -ENOMEM;
+			break;
+		}
+	}
+
+	free(tmp);
+	return ret;
+}
+
+/* Post processing the probe events */
+static int post_process_probe_trace_events(struct probe_trace_event *tevs,
+					   int ntevs, const char *module,
+					   bool uprobe)
+{
+	struct ref_reloc_sym *reloc_sym;
+	char *tmp;
+	int i;
+
+	if (uprobe)
+		return add_exec_to_probe_trace_events(tevs, ntevs, module);
+
+	/* Note that currently ref_reloc_sym based probe is not for drivers */
+	if (module)
+		return add_module_to_probe_trace_events(tevs, ntevs, module);
+
+	reloc_sym = kernel_get_ref_reloc_sym();
+	if (!reloc_sym) {
+		pr_warning("Relocated base symbol is not found!\n");
+		return -EINVAL;
+	}
+
+	for (i = 0; i < ntevs; i++) {
+		if (tevs[i].point.address) {
+			tmp = strdup(reloc_sym->name);
+			if (!tmp)
+				return -ENOMEM;
+			free(tevs[i].point.symbol);
+			tevs[i].point.symbol = tmp;
+			tevs[i].point.offset = tevs[i].point.address -
+					       reloc_sym->unrelocated_addr;
+		}
+	}
 	return 0;
 }
 
 /* Try to find perf_probe_event with debuginfo */
-static int try_to_find_kprobe_trace_events(struct perf_probe_event *pev,
-					   struct kprobe_trace_event **tevs,
-					   int max_tevs)
+static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
+					  struct probe_trace_event **tevs,
+					  int max_tevs, const char *target)
 {
 	bool need_dwarf = perf_probe_event_need_dwarf(pev);
-	int fd, ntevs;
+	struct debuginfo *dinfo;
+	int ntevs, ret = 0;
 
-	fd = open_vmlinux();
-	if (fd < 0) {
+	dinfo = open_debuginfo(target);
+
+	if (!dinfo) {
 		if (need_dwarf) {
 			pr_warning("Failed to open debuginfo file.\n");
-			return fd;
+			return -ENOENT;
 		}
-		pr_debug("Could not open vmlinux. Try to use symbols.\n");
+		pr_debug("Could not open debuginfo. Try to use symbols.\n");
 		return 0;
 	}
 
-	/* Searching trace events corresponding to probe event */
-	ntevs = find_kprobe_trace_events(fd, pev, tevs, max_tevs);
-	close(fd);
+	pr_debug("Try to find probe point from debuginfo.\n");
+	/* Searching trace events corresponding to a probe event */
+	ntevs = debuginfo__find_trace_events(dinfo, pev, tevs, max_tevs);
+
+	debuginfo__delete(dinfo);
 
 	if (ntevs > 0) {	/* Succeeded to find trace events */
-		pr_debug("find %d kprobe_trace_events.\n", ntevs);
-		return ntevs;
+		pr_debug("Found %d probe_trace_events.\n", ntevs);
+		ret = post_process_probe_trace_events(*tevs, ntevs,
+							target, pev->uprobes);
+		if (ret < 0) {
+			clear_probe_trace_events(*tevs, ntevs);
+			zfree(tevs);
+		}
+		return ret < 0 ? ret : ntevs;
 	}
 
 	if (ntevs == 0)	{	/* No error but failed to find probe point. */
@@ -188,91 +496,162 @@ static int try_to_find_kprobe_trace_events(struct perf_probe_event *pev,
 		pr_warning("Warning: No dwarf info found in the vmlinux - "
 			"please rebuild kernel with CONFIG_DEBUG_INFO=y.\n");
 		if (!need_dwarf) {
-			pr_debug("Trying to use symbols.\nn");
+			pr_debug("Trying to use symbols.\n");
 			return 0;
 		}
 	}
 	return ntevs;
 }
 
+/*
+ * Find a src file from a DWARF tag path. Prepend optional source path prefix
+ * and chop off leading directories that do not exist. Result is passed back as
+ * a newly allocated path on success.
+ * Return 0 if file was found and readable, -errno otherwise.
+ */
+static int get_real_path(const char *raw_path, const char *comp_dir,
+			 char **new_path)
+{
+	const char *prefix = symbol_conf.source_prefix;
+
+	if (!prefix) {
+		if (raw_path[0] != '/' && comp_dir)
+			/* If not an absolute path, try to use comp_dir */
+			prefix = comp_dir;
+		else {
+			if (access(raw_path, R_OK) == 0) {
+				*new_path = strdup(raw_path);
+				return 0;
+			} else
+				return -errno;
+		}
+	}
+
+	*new_path = malloc((strlen(prefix) + strlen(raw_path) + 2));
+	if (!*new_path)
+		return -ENOMEM;
+
+	for (;;) {
+		sprintf(*new_path, "%s/%s", prefix, raw_path);
+
+		if (access(*new_path, R_OK) == 0)
+			return 0;
+
+		if (!symbol_conf.source_prefix)
+			/* In case of searching comp_dir, don't retry */
+			return -errno;
+
+		switch (errno) {
+		case ENAMETOOLONG:
+		case ENOENT:
+		case EROFS:
+		case EFAULT:
+			raw_path = strchr(++raw_path, '/');
+			if (!raw_path) {
+				zfree(new_path);
+				return -ENOENT;
+			}
+			continue;
+
+		default:
+			zfree(new_path);
+			return -errno;
+		}
+	}
+}
+
 #define LINEBUF_SIZE 256
 #define NR_ADDITIONAL_LINES 2
 
-static int show_one_line(FILE *fp, int l, bool skip, bool show_num)
+static int __show_one_line(FILE *fp, int l, bool skip, bool show_num)
 {
 	char buf[LINEBUF_SIZE];
-	const char *color = PERF_COLOR_BLUE;
-
-	if (fgets(buf, LINEBUF_SIZE, fp) == NULL)
-		goto error;
-	if (!skip) {
-		if (show_num)
-			fprintf(stdout, "%7d  %s", l, buf);
-		else
-			color_fprintf(stdout, color, "         %s", buf);
-	}
+	const char *color = show_num ? "" : PERF_COLOR_BLUE;
+	const char *prefix = NULL;
 
-	while (strlen(buf) == LINEBUF_SIZE - 1 &&
-	       buf[LINEBUF_SIZE - 2] != '\n') {
+	do {
 		if (fgets(buf, LINEBUF_SIZE, fp) == NULL)
 			goto error;
-		if (!skip) {
-			if (show_num)
-				fprintf(stdout, "%s", buf);
-			else
-				color_fprintf(stdout, color, "%s", buf);
+		if (skip)
+			continue;
+		if (!prefix) {
+			prefix = show_num ? "%7d  " : "         ";
+			color_fprintf(stdout, color, prefix, l);
 		}
-	}
+		color_fprintf(stdout, color, "%s", buf);
 
-	return 0;
+	} while (strchr(buf, '\n') == NULL);
+
+	return 1;
 error:
-	if (feof(fp))
-		pr_warning("Source file is shorter than expected.\n");
-	else
+	if (ferror(fp)) {
 		pr_warning("File read error: %s\n", strerror(errno));
+		return -1;
+	}
+	return 0;
+}
 
-	return -1;
+static int _show_one_line(FILE *fp, int l, bool skip, bool show_num)
+{
+	int rv = __show_one_line(fp, l, skip, show_num);
+	if (rv == 0) {
+		pr_warning("Source file is shorter than expected.\n");
+		rv = -1;
+	}
+	return rv;
 }
 
+#define show_one_line_with_num(f,l)	_show_one_line(f,l,false,true)
+#define show_one_line(f,l)		_show_one_line(f,l,false,false)
+#define skip_one_line(f,l)		_show_one_line(f,l,true,false)
+#define show_one_line_or_eof(f,l)	__show_one_line(f,l,false,false)
+
 /*
  * Show line-range always requires debuginfo to find source file and
  * line number.
  */
-int show_line_range(struct line_range *lr)
+static int __show_line_range(struct line_range *lr, const char *module)
 {
 	int l = 1;
-	struct line_node *ln;
+	struct int_node *ln;
+	struct debuginfo *dinfo;
 	FILE *fp;
-	int fd, ret;
+	int ret;
+	char *tmp;
 
 	/* Search a line range */
-	ret = init_vmlinux();
-	if (ret < 0)
-		return ret;
-
-	fd = open_vmlinux();
-	if (fd < 0) {
+	dinfo = open_debuginfo(module);
+	if (!dinfo) {
 		pr_warning("Failed to open debuginfo file.\n");
-		return fd;
+		return -ENOENT;
 	}
 
-	ret = find_line_range(fd, lr);
-	close(fd);
-	if (ret == 0) {
+	ret = debuginfo__find_line_range(dinfo, lr);
+	debuginfo__delete(dinfo);
+	if (ret == 0 || ret == -ENOENT) {
 		pr_warning("Specified source line is not found.\n");
 		return -ENOENT;
 	} else if (ret < 0) {
-		pr_warning("Debuginfo analysis failed. (%d)\n", ret);
+		pr_warning("Debuginfo analysis failed.\n");
+		return ret;
+	}
+
+	/* Convert source file path */
+	tmp = lr->path;
+	ret = get_real_path(tmp, lr->comp_dir, &lr->path);
+	free(tmp);	/* Free old path */
+	if (ret < 0) {
+		pr_warning("Failed to find source file path.\n");
 		return ret;
 	}
 
 	setup_pager();
 
 	if (lr->function)
-		fprintf(stdout, "<%s:%d>\n", lr->function,
+		fprintf(stdout, "<%s@%s:%d>\n", lr->function, lr->path,
 			lr->start - lr->offset);
 	else
-		fprintf(stdout, "<%s:%d>\n", lr->file, lr->start);
+		fprintf(stdout, "<%s:%d>\n", lr->path, lr->start);
 
 	fp = fopen(lr->path, "r");
 	if (fp == NULL) {
@@ -281,114 +660,288 @@ int show_line_range(struct line_range *lr)
 		return -errno;
 	}
 	/* Skip to starting line number */
-	while (l < lr->start && ret >= 0)
-		ret = show_one_line(fp, l++, true, false);
-	if (ret < 0)
-		goto end;
+	while (l < lr->start) {
+		ret = skip_one_line(fp, l++);
+		if (ret < 0)
+			goto end;
+	}
 
-	list_for_each_entry(ln, &lr->line_list, list) {
-		while (ln->line > l && ret >= 0)
-			ret = show_one_line(fp, (l++) - lr->offset,
-					    false, false);
-		if (ret >= 0)
-			ret = show_one_line(fp, (l++) - lr->offset,
-					    false, true);
+	intlist__for_each(ln, lr->line_list) {
+		for (; ln->i > l; l++) {
+			ret = show_one_line(fp, l - lr->offset);
+			if (ret < 0)
+				goto end;
+		}
+		ret = show_one_line_with_num(fp, l++ - lr->offset);
 		if (ret < 0)
 			goto end;
 	}
 
 	if (lr->end == INT_MAX)
 		lr->end = l + NR_ADDITIONAL_LINES;
-	while (l <= lr->end && !feof(fp) && ret >= 0)
-		ret = show_one_line(fp, (l++) - lr->offset, false, false);
+	while (l <= lr->end) {
+		ret = show_one_line_or_eof(fp, l++ - lr->offset);
+		if (ret <= 0)
+			break;
+	}
 end:
 	fclose(fp);
 	return ret;
 }
 
-#else	/* !DWARF_SUPPORT */
+int show_line_range(struct line_range *lr, const char *module)
+{
+	int ret;
+
+	ret = init_symbol_maps(false);
+	if (ret < 0)
+		return ret;
+	ret = __show_line_range(lr, module);
+	exit_symbol_maps();
 
-static int convert_to_perf_probe_point(struct kprobe_trace_point *tp,
-					struct perf_probe_point *pp)
+	return ret;
+}
+
+static int show_available_vars_at(struct debuginfo *dinfo,
+				  struct perf_probe_event *pev,
+				  int max_vls, struct strfilter *_filter,
+				  bool externs)
 {
-	pp->function = strdup(tp->symbol);
-	if (pp->function == NULL)
-		return -ENOMEM;
-	pp->offset = tp->offset;
-	pp->retprobe = tp->retprobe;
+	char *buf;
+	int ret, i, nvars;
+	struct str_node *node;
+	struct variable_list *vls = NULL, *vl;
+	const char *var;
 
-	return 0;
+	buf = synthesize_perf_probe_point(&pev->point);
+	if (!buf)
+		return -EINVAL;
+	pr_debug("Searching variables at %s\n", buf);
+
+	ret = debuginfo__find_available_vars_at(dinfo, pev, &vls,
+						max_vls, externs);
+	if (ret <= 0) {
+		if (ret == 0 || ret == -ENOENT) {
+			pr_err("Failed to find the address of %s\n", buf);
+			ret = -ENOENT;
+		} else
+			pr_warning("Debuginfo analysis failed.\n");
+		goto end;
+	}
+
+	/* Some variables are found */
+	fprintf(stdout, "Available variables at %s\n", buf);
+	for (i = 0; i < ret; i++) {
+		vl = &vls[i];
+		/*
+		 * A probe point might be converted to
+		 * several trace points.
+		 */
+		fprintf(stdout, "\t@<%s+%lu>\n", vl->point.symbol,
+			vl->point.offset);
+		zfree(&vl->point.symbol);
+		nvars = 0;
+		if (vl->vars) {
+			strlist__for_each(node, vl->vars) {
+				var = strchr(node->s, '\t') + 1;
+				if (strfilter__compare(_filter, var)) {
+					fprintf(stdout, "\t\t%s\n", node->s);
+					nvars++;
+				}
+			}
+			strlist__delete(vl->vars);
+		}
+		if (nvars == 0)
+			fprintf(stdout, "\t\t(No matched variables)\n");
+	}
+	free(vls);
+end:
+	free(buf);
+	return ret;
 }
 
-static int try_to_find_kprobe_trace_events(struct perf_probe_event *pev,
-				struct kprobe_trace_event **tevs __unused,
-				int max_tevs __unused)
+/* Show available variables on given probe point */
+int show_available_vars(struct perf_probe_event *pevs, int npevs,
+			int max_vls, const char *module,
+			struct strfilter *_filter, bool externs)
+{
+	int i, ret = 0;
+	struct debuginfo *dinfo;
+
+	ret = init_symbol_maps(false);
+	if (ret < 0)
+		return ret;
+
+	dinfo = open_debuginfo(module);
+	if (!dinfo) {
+		pr_warning("Failed to open debuginfo file.\n");
+		ret = -ENOENT;
+		goto out;
+	}
+
+	setup_pager();
+
+	for (i = 0; i < npevs && ret >= 0; i++)
+		ret = show_available_vars_at(dinfo, &pevs[i], max_vls, _filter,
+					     externs);
+
+	debuginfo__delete(dinfo);
+out:
+	exit_symbol_maps();
+	return ret;
+}
+
+#else	/* !HAVE_DWARF_SUPPORT */
+
+static int
+find_perf_probe_point_from_dwarf(struct probe_trace_point *tp __maybe_unused,
+				 struct perf_probe_point *pp __maybe_unused,
+				 bool is_kprobe __maybe_unused)
+{
+	return -ENOSYS;
+}
+
+static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
+				struct probe_trace_event **tevs __maybe_unused,
+				int max_tevs __maybe_unused,
+				const char *target __maybe_unused)
 {
 	if (perf_probe_event_need_dwarf(pev)) {
 		pr_warning("Debuginfo-analysis is not supported.\n");
 		return -ENOSYS;
 	}
+
 	return 0;
 }
 
-int show_line_range(struct line_range *lr __unused)
+int show_line_range(struct line_range *lr __maybe_unused,
+		    const char *module __maybe_unused)
 {
 	pr_warning("Debuginfo-analysis is not supported.\n");
 	return -ENOSYS;
 }
 
+int show_available_vars(struct perf_probe_event *pevs __maybe_unused,
+			int npevs __maybe_unused, int max_vls __maybe_unused,
+			const char *module __maybe_unused,
+			struct strfilter *filter __maybe_unused,
+			bool externs __maybe_unused)
+{
+	pr_warning("Debuginfo-analysis is not supported.\n");
+	return -ENOSYS;
+}
 #endif
 
+void line_range__clear(struct line_range *lr)
+{
+	free(lr->function);
+	free(lr->file);
+	free(lr->path);
+	free(lr->comp_dir);
+	intlist__delete(lr->line_list);
+	memset(lr, 0, sizeof(*lr));
+}
+
+int line_range__init(struct line_range *lr)
+{
+	memset(lr, 0, sizeof(*lr));
+	lr->line_list = intlist__new(NULL);
+	if (!lr->line_list)
+		return -ENOMEM;
+	else
+		return 0;
+}
+
+static int parse_line_num(char **ptr, int *val, const char *what)
+{
+	const char *start = *ptr;
+
+	errno = 0;
+	*val = strtol(*ptr, ptr, 0);
+	if (errno || *ptr == start) {
+		semantic_error("'%s' is not a valid number.\n", what);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+/*
+ * Stuff 'lr' according to the line range described by 'arg'.
+ * The line range syntax is described by:
+ *
+ *         SRC[:SLN[+NUM|-ELN]]
+ *         FNC[@SRC][:SLN[+NUM|-ELN]]
+ */
 int parse_line_range_desc(const char *arg, struct line_range *lr)
 {
-	const char *ptr;
-	char *tmp;
-	/*
-	 * <Syntax>
-	 * SRC:SLN[+NUM|-ELN]
-	 * FUNC[:SLN[+NUM|-ELN]]
-	 */
-	ptr = strchr(arg, ':');
-	if (ptr) {
-		lr->start = (int)strtoul(ptr + 1, &tmp, 0);
-		if (*tmp == '+') {
-			lr->end = lr->start + (int)strtoul(tmp + 1, &tmp, 0);
-			lr->end--;	/*
-					 * Adjust the number of lines here.
-					 * If the number of lines == 1, the
-					 * the end of line should be equal to
-					 * the start of line.
-					 */
-		} else if (*tmp == '-')
-			lr->end = (int)strtoul(tmp + 1, &tmp, 0);
-		else
-			lr->end = INT_MAX;
+	char *range, *file, *name = strdup(arg);
+	int err;
+
+	if (!name)
+		return -ENOMEM;
+
+	lr->start = 0;
+	lr->end = INT_MAX;
+
+	range = strchr(name, ':');
+	if (range) {
+		*range++ = '\0';
+
+		err = parse_line_num(&range, &lr->start, "start line");
+		if (err)
+			goto err;
+
+		if (*range == '+' || *range == '-') {
+			const char c = *range++;
+
+			err = parse_line_num(&range, &lr->end, "end line");
+			if (err)
+				goto err;
+
+			if (c == '+') {
+				lr->end += lr->start;
+				/*
+				 * Adjust the number of lines here.
+				 * If the number of lines == 1, the
+				 * the end of line should be equal to
+				 * the start of line.
+				 */
+				lr->end--;
+			}
+		}
+
 		pr_debug("Line range is %d to %d\n", lr->start, lr->end);
+
+		err = -EINVAL;
 		if (lr->start > lr->end) {
 			semantic_error("Start line must be smaller"
 				       " than end line.\n");
-			return -EINVAL;
+			goto err;
 		}
-		if (*tmp != '\0') {
-			semantic_error("Tailing with invalid character '%d'.\n",
-				       *tmp);
-			return -EINVAL;
+		if (*range != '\0') {
+			semantic_error("Tailing with invalid str '%s'.\n", range);
+			goto err;
 		}
-		tmp = strndup(arg, (ptr - arg));
-	} else {
-		tmp = strdup(arg);
-		lr->end = INT_MAX;
 	}
 
-	if (tmp == NULL)
-		return -ENOMEM;
-
-	if (strchr(tmp, '.'))
-		lr->file = tmp;
+	file = strchr(name, '@');
+	if (file) {
+		*file = '\0';
+		lr->file = strdup(++file);
+		if (lr->file == NULL) {
+			err = -ENOMEM;
+			goto err;
+		}
+		lr->function = name;
+	} else if (strchr(name, '.'))
+		lr->file = name;
 	else
-		lr->function = tmp;
+		lr->function = name;
 
 	return 0;
+err:
+	free(name);
+	return err;
 }
 
 /* Check the name is good for event/group */
@@ -512,39 +1065,40 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
 
 	/* Exclusion check */
 	if (pp->lazy_line && pp->line) {
-		semantic_error("Lazy pattern can't be used with line number.");
+		semantic_error("Lazy pattern can't be used with"
+			       " line number.\n");
 		return -EINVAL;
 	}
 
 	if (pp->lazy_line && pp->offset) {
-		semantic_error("Lazy pattern can't be used with offset.");
+		semantic_error("Lazy pattern can't be used with offset.\n");
 		return -EINVAL;
 	}
 
 	if (pp->line && pp->offset) {
-		semantic_error("Offset can't be used with line number.");
+		semantic_error("Offset can't be used with line number.\n");
 		return -EINVAL;
 	}
 
 	if (!pp->line && !pp->lazy_line && pp->file && !pp->function) {
 		semantic_error("File always requires line number or "
-			       "lazy pattern.");
+			       "lazy pattern.\n");
 		return -EINVAL;
 	}
 
 	if (pp->offset && !pp->function) {
-		semantic_error("Offset requires an entry function.");
+		semantic_error("Offset requires an entry function.\n");
 		return -EINVAL;
 	}
 
 	if (pp->retprobe && !pp->function) {
-		semantic_error("Return probe requires an entry function.");
+		semantic_error("Return probe requires an entry function.\n");
 		return -EINVAL;
 	}
 
 	if ((pp->offset || pp->line || pp->lazy_line) && pp->retprobe) {
 		semantic_error("Offset/Line/Lazy pattern can't be used with "
-			       "return probe.");
+			       "return probe.\n");
 		return -EINVAL;
 	}
 
@@ -557,7 +1111,7 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
 /* Parse perf-probe event argument */
 static int parse_perf_probe_arg(char *str, struct perf_probe_arg *arg)
 {
-	char *tmp;
+	char *tmp, *goodname;
 	struct perf_probe_arg_field **fieldp;
 
 	pr_debug("parsing arg: %s into ", str);
@@ -580,7 +1134,7 @@ static int parse_perf_probe_arg(char *str, struct perf_probe_arg *arg)
 		pr_debug("type:%s ", arg->type);
 	}
 
-	tmp = strpbrk(str, "-.");
+	tmp = strpbrk(str, "-.[");
 	if (!is_c_varname(str) || !tmp) {
 		/* A variable, register, symbol or special value */
 		arg->var = strdup(str);
@@ -590,10 +1144,11 @@ static int parse_perf_probe_arg(char *str, struct perf_probe_arg *arg)
 		return 0;
 	}
 
-	/* Structure fields */
+	/* Structure fields or array element */
 	arg->var = strndup(str, tmp - str);
 	if (arg->var == NULL)
 		return -ENOMEM;
+	goodname = arg->var;
 	pr_debug("%s, ", arg->var);
 	fieldp = &arg->field;
 
@@ -601,22 +1156,38 @@ static int parse_perf_probe_arg(char *str, struct perf_probe_arg *arg)
 		*fieldp = zalloc(sizeof(struct perf_probe_arg_field));
 		if (*fieldp == NULL)
 			return -ENOMEM;
-		if (*tmp == '.') {
-			str = tmp + 1;
-			(*fieldp)->ref = false;
-		} else if (tmp[1] == '>') {
-			str = tmp + 2;
+		if (*tmp == '[') {	/* Array */
+			str = tmp;
+			(*fieldp)->index = strtol(str + 1, &tmp, 0);
 			(*fieldp)->ref = true;
-		} else {
-			semantic_error("Argument parse error: %s\n", str);
-			return -EINVAL;
+			if (*tmp != ']' || tmp == str + 1) {
+				semantic_error("Array index must be a"
+						" number.\n");
+				return -EINVAL;
+			}
+			tmp++;
+			if (*tmp == '\0')
+				tmp = NULL;
+		} else {		/* Structure */
+			if (*tmp == '.') {
+				str = tmp + 1;
+				(*fieldp)->ref = false;
+			} else if (tmp[1] == '>') {
+				str = tmp + 2;
+				(*fieldp)->ref = true;
+			} else {
+				semantic_error("Argument parse error: %s\n",
+					       str);
+				return -EINVAL;
+			}
+			tmp = strpbrk(str, "-.[");
 		}
-
-		tmp = strpbrk(str, "-.");
 		if (tmp) {
 			(*fieldp)->name = strndup(str, tmp - str);
 			if ((*fieldp)->name == NULL)
 				return -ENOMEM;
+			if (*str != '[')
+				goodname = (*fieldp)->name;
 			pr_debug("%s(%d), ", (*fieldp)->name, (*fieldp)->ref);
 			fieldp = &(*fieldp)->next;
 		}
@@ -624,11 +1195,13 @@ static int parse_perf_probe_arg(char *str, struct perf_probe_arg *arg)
 	(*fieldp)->name = strdup(str);
 	if ((*fieldp)->name == NULL)
 		return -ENOMEM;
+	if (*str != '[')
+		goodname = (*fieldp)->name;
 	pr_debug("%s(%d)\n", (*fieldp)->name, (*fieldp)->ref);
 
-	/* If no name is specified, set the last field name */
+	/* If no name is specified, set the last field name (not array index)*/
 	if (!arg->name) {
-		arg->name = strdup((*fieldp)->name);
+		arg->name = strdup(goodname);
 		if (arg->name == NULL)
 			return -ENOMEM;
 	}
@@ -693,16 +1266,18 @@ bool perf_probe_event_need_dwarf(struct perf_probe_event *pev)
 	return false;
 }
 
-/* Parse kprobe_events event into struct probe_point */
-int parse_kprobe_trace_command(const char *cmd, struct kprobe_trace_event *tev)
+/* Parse probe_events event into struct probe_point */
+static int parse_probe_trace_command(const char *cmd,
+				     struct probe_trace_event *tev)
 {
-	struct kprobe_trace_point *tp = &tev->point;
+	struct probe_trace_point *tp = &tev->point;
 	char pr;
 	char *p;
+	char *argv0_str = NULL, *fmt, *fmt1_str, *fmt2_str, *fmt3_str;
 	int ret, i, argc;
 	char **argv;
 
-	pr_debug("Parsing kprobe_events: %s\n", cmd);
+	pr_debug("Parsing probe_events: %s\n", cmd);
 	argv = argv_split(cmd, &argc);
 	if (!argv) {
 		pr_debug("Failed to split arguments.\n");
@@ -715,26 +1290,57 @@ int parse_kprobe_trace_command(const char *cmd, struct kprobe_trace_event *tev)
 	}
 
 	/* Scan event and group name. */
-	ret = sscanf(argv[0], "%c:%a[^/ \t]/%a[^ \t]",
-		     &pr, (float *)(void *)&tev->group,
-		     (float *)(void *)&tev->event);
-	if (ret != 3) {
+	argv0_str = strdup(argv[0]);
+	if (argv0_str == NULL) {
+		ret = -ENOMEM;
+		goto out;
+	}
+	fmt1_str = strtok_r(argv0_str, ":", &fmt);
+	fmt2_str = strtok_r(NULL, "/", &fmt);
+	fmt3_str = strtok_r(NULL, " \t", &fmt);
+	if (fmt1_str == NULL || strlen(fmt1_str) != 1 || fmt2_str == NULL
+	    || fmt3_str == NULL) {
 		semantic_error("Failed to parse event name: %s\n", argv[0]);
 		ret = -EINVAL;
 		goto out;
 	}
+	pr = fmt1_str[0];
+	tev->group = strdup(fmt2_str);
+	tev->event = strdup(fmt3_str);
+	if (tev->group == NULL || tev->event == NULL) {
+		ret = -ENOMEM;
+		goto out;
+	}
 	pr_debug("Group:%s Event:%s probe:%c\n", tev->group, tev->event, pr);
 
 	tp->retprobe = (pr == 'r');
 
-	/* Scan function name and offset */
-	ret = sscanf(argv[1], "%a[^+]+%lu", (float *)(void *)&tp->symbol,
-		     &tp->offset);
-	if (ret == 1)
-		tp->offset = 0;
+	/* Scan module name(if there), function name and offset */
+	p = strchr(argv[1], ':');
+	if (p) {
+		tp->module = strndup(argv[1], p - argv[1]);
+		p++;
+	} else
+		p = argv[1];
+	fmt1_str = strtok_r(p, "+", &fmt);
+	if (fmt1_str[0] == '0')	/* only the address started with 0x */
+		tp->address = strtoul(fmt1_str, NULL, 0);
+	else {
+		/* Only the symbol-based probe has offset */
+		tp->symbol = strdup(fmt1_str);
+		if (tp->symbol == NULL) {
+			ret = -ENOMEM;
+			goto out;
+		}
+		fmt2_str = strtok_r(NULL, "", &fmt);
+		if (fmt2_str == NULL)
+			tp->offset = 0;
+		else
+			tp->offset = strtoul(fmt2_str, NULL, 10);
+	}
 
 	tev->nargs = argc - 2;
-	tev->args = zalloc(sizeof(struct kprobe_trace_arg) * tev->nargs);
+	tev->args = zalloc(sizeof(struct probe_trace_arg) * tev->nargs);
 	if (tev->args == NULL) {
 		ret = -ENOMEM;
 		goto out;
@@ -755,6 +1361,7 @@ int parse_kprobe_trace_command(const char *cmd, struct kprobe_trace_event *tev)
 	}
 	ret = 0;
 out:
+	free(argv0_str);
 	argv_free(argv);
 	return ret;
 }
@@ -776,8 +1383,11 @@ int synthesize_perf_probe_arg(struct perf_probe_arg *pa, char *buf, size_t len)
 	len -= ret;
 
 	while (field) {
-		ret = e_snprintf(tmp, len, "%s%s", field->ref ? "->" : ".",
-				 field->name);
+		if (field->name[0] == '[')
+			ret = e_snprintf(tmp, len, "%s", field->name);
+		else
+			ret = e_snprintf(tmp, len, "%s%s",
+					 field->ref ? "->" : ".", field->name);
 		if (ret <= 0)
 			goto error;
 		tmp += ret;
@@ -795,7 +1405,7 @@ int synthesize_perf_probe_arg(struct perf_probe_arg *pa, char *buf, size_t len)
 
 	return tmp - buf;
 error:
-	pr_debug("Failed to synthesize perf probe argument: %s",
+	pr_debug("Failed to synthesize perf probe argument: %s\n",
 		 strerror(-ret));
 	return ret;
 }
@@ -823,13 +1433,13 @@ static char *synthesize_perf_probe_point(struct perf_probe_point *pp)
 			goto error;
 	}
 	if (pp->file) {
-		len = strlen(pp->file) - 31;
-		if (len < 0)
-			len = 0;
-		tmp = strchr(pp->file + len, '/');
-		if (!tmp)
-			tmp = pp->file + len;
-		ret = e_snprintf(file, 32, "@%s", tmp + 1);
+		tmp = pp->file;
+		len = strlen(tmp);
+		if (len > 30) {
+			tmp = strchr(pp->file + len - 30, '/');
+			tmp = tmp ? tmp + 1 : pp->file + len - 30;
+		}
+		ret = e_snprintf(file, 32, "@%s", tmp);
 		if (ret <= 0)
 			goto error;
 	}
@@ -845,10 +1455,9 @@ static char *synthesize_perf_probe_point(struct perf_probe_point *pp)
 
 	return buf;
 error:
-	pr_debug("Failed to synthesize perf probe point: %s",
+	pr_debug("Failed to synthesize perf probe point: %s\n",
 		 strerror(-ret));
-	if (buf)
-		free(buf);
+	free(buf);
 	return NULL;
 }
 
@@ -877,13 +1486,13 @@ char *synthesize_perf_probe_command(struct perf_probe_event *pev)
 }
 #endif
 
-static int __synthesize_kprobe_trace_arg_ref(struct kprobe_trace_arg_ref *ref,
+static int __synthesize_probe_trace_arg_ref(struct probe_trace_arg_ref *ref,
 					     char **buf, size_t *buflen,
 					     int depth)
 {
 	int ret;
 	if (ref->next) {
-		depth = __synthesize_kprobe_trace_arg_ref(ref->next, buf,
+		depth = __synthesize_probe_trace_arg_ref(ref->next, buf,
 							 buflen, depth + 1);
 		if (depth < 0)
 			goto out;
@@ -901,9 +1510,10 @@ out:
 
 }
 
-static int synthesize_kprobe_trace_arg(struct kprobe_trace_arg *arg,
+static int synthesize_probe_trace_arg(struct probe_trace_arg *arg,
 				       char *buf, size_t buflen)
 {
+	struct probe_trace_arg_ref *ref = arg->ref;
 	int ret, depth = 0;
 	char *tmp = buf;
 
@@ -917,16 +1527,24 @@ static int synthesize_kprobe_trace_arg(struct kprobe_trace_arg *arg,
 	buf += ret;
 	buflen -= ret;
 
+	/* Special case: @XXX */
+	if (arg->value[0] == '@' && arg->ref)
+			ref = ref->next;
+
 	/* Dereferencing arguments */
-	if (arg->ref) {
-		depth = __synthesize_kprobe_trace_arg_ref(arg->ref, &buf,
+	if (ref) {
+		depth = __synthesize_probe_trace_arg_ref(ref, &buf,
 							  &buflen, 1);
 		if (depth < 0)
 			return depth;
 	}
 
 	/* Print argument value */
-	ret = e_snprintf(buf, buflen, "%s", arg->value);
+	if (arg->value[0] == '@' && arg->ref)
+		ret = e_snprintf(buf, buflen, "%s%+ld", arg->value,
+				 arg->ref->offset);
+	else
+		ret = e_snprintf(buf, buflen, "%s", arg->value);
 	if (ret < 0)
 		return ret;
 	buf += ret;
@@ -951,9 +1569,9 @@ static int synthesize_kprobe_trace_arg(struct kprobe_trace_arg *arg,
 	return buf - tmp;
 }
 
-char *synthesize_kprobe_trace_command(struct kprobe_trace_event *tev)
+char *synthesize_probe_trace_command(struct probe_trace_event *tev)
 {
-	struct kprobe_trace_point *tp = &tev->point;
+	struct probe_trace_point *tp = &tev->point;
 	char *buf;
 	int i, len, ret;
 
@@ -961,15 +1579,30 @@ char *synthesize_kprobe_trace_command(struct kprobe_trace_event *tev)
 	if (buf == NULL)
 		return NULL;
 
-	len = e_snprintf(buf, MAX_CMDLEN, "%c:%s/%s %s+%lu",
-			 tp->retprobe ? 'r' : 'p',
-			 tev->group, tev->event,
-			 tp->symbol, tp->offset);
+	len = e_snprintf(buf, MAX_CMDLEN, "%c:%s/%s ", tp->retprobe ? 'r' : 'p',
+			 tev->group, tev->event);
 	if (len <= 0)
 		goto error;
 
+	/* Uprobes must have tp->address and tp->module */
+	if (tev->uprobes && (!tp->address || !tp->module))
+		goto error;
+
+	/* Use the tp->address for uprobes */
+	if (tev->uprobes)
+		ret = e_snprintf(buf + len, MAX_CMDLEN - len, "%s:0x%lx",
+				 tp->module, tp->address);
+	else
+		ret = e_snprintf(buf + len, MAX_CMDLEN - len, "%s%s%s+%lu",
+				 tp->module ?: "", tp->module ? ":" : "",
+				 tp->symbol, tp->offset);
+
+	if (ret <= 0)
+		goto error;
+	len += ret;
+
 	for (i = 0; i < tev->nargs; i++) {
-		ret = synthesize_kprobe_trace_arg(&tev->args[i], buf + len,
+		ret = synthesize_probe_trace_arg(&tev->args[i], buf + len,
 						  MAX_CMDLEN - len);
 		if (ret <= 0)
 			goto error;
@@ -982,8 +1615,81 @@ error:
 	return NULL;
 }
 
-int convert_to_perf_probe_event(struct kprobe_trace_event *tev,
-				struct perf_probe_event *pev)
+static int find_perf_probe_point_from_map(struct probe_trace_point *tp,
+					  struct perf_probe_point *pp,
+					  bool is_kprobe)
+{
+	struct symbol *sym = NULL;
+	struct map *map;
+	u64 addr;
+	int ret = -ENOENT;
+
+	if (!is_kprobe) {
+		map = dso__new_map(tp->module);
+		if (!map)
+			goto out;
+		addr = tp->address;
+		sym = map__find_symbol(map, addr, NULL);
+	} else {
+		addr = kernel_get_symbol_address_by_name(tp->symbol, true);
+		if (addr) {
+			addr += tp->offset;
+			sym = __find_kernel_function(addr, &map);
+		}
+	}
+	if (!sym)
+		goto out;
+
+	pp->retprobe = tp->retprobe;
+	pp->offset = addr - map->unmap_ip(map, sym->start);
+	pp->function = strdup(sym->name);
+	ret = pp->function ? 0 : -ENOMEM;
+
+out:
+	if (map && !is_kprobe) {
+		dso__delete(map->dso);
+		map__delete(map);
+	}
+
+	return ret;
+}
+
+static int convert_to_perf_probe_point(struct probe_trace_point *tp,
+					struct perf_probe_point *pp,
+					bool is_kprobe)
+{
+	char buf[128];
+	int ret;
+
+	ret = find_perf_probe_point_from_dwarf(tp, pp, is_kprobe);
+	if (!ret)
+		return 0;
+	ret = find_perf_probe_point_from_map(tp, pp, is_kprobe);
+	if (!ret)
+		return 0;
+
+	pr_debug("Failed to find probe point from both of dwarf and map.\n");
+
+	if (tp->symbol) {
+		pp->function = strdup(tp->symbol);
+		pp->offset = tp->offset;
+	} else if (!tp->module && !is_kprobe) {
+		ret = e_snprintf(buf, 128, "0x%" PRIx64, (u64)tp->address);
+		if (ret < 0)
+			return ret;
+		pp->function = strdup(buf);
+		pp->offset = 0;
+	}
+	if (pp->function == NULL)
+		return -ENOMEM;
+
+	pp->retprobe = tp->retprobe;
+
+	return 0;
+}
+
+static int convert_to_perf_probe_event(struct probe_trace_event *tev,
+			       struct perf_probe_event *pev, bool is_kprobe)
 {
 	char buf[64] = "";
 	int i, ret;
@@ -995,7 +1701,7 @@ int convert_to_perf_probe_event(struct kprobe_trace_event *tev,
 		return -ENOMEM;
 
 	/* Convert trace_point to probe_point */
-	ret = convert_to_perf_probe_point(&tev->point, &pev->point);
+	ret = convert_to_perf_probe_point(&tev->point, &pev->point, is_kprobe);
 	if (ret < 0)
 		return ret;
 
@@ -1008,7 +1714,7 @@ int convert_to_perf_probe_event(struct kprobe_trace_event *tev,
 		if (tev->args[i].name)
 			pev->args[i].name = strdup(tev->args[i].name);
 		else {
-			ret = synthesize_kprobe_trace_arg(&tev->args[i],
+			ret = synthesize_probe_trace_arg(&tev->args[i],
 							  buf, 64);
 			pev->args[i].name = strdup(buf);
 		}
@@ -1028,55 +1734,41 @@ void clear_perf_probe_event(struct perf_probe_event *pev)
 	struct perf_probe_arg_field *field, *next;
 	int i;
 
-	if (pev->event)
-		free(pev->event);
-	if (pev->group)
-		free(pev->group);
-	if (pp->file)
-		free(pp->file);
-	if (pp->function)
-		free(pp->function);
-	if (pp->lazy_line)
-		free(pp->lazy_line);
+	free(pev->event);
+	free(pev->group);
+	free(pp->file);
+	free(pp->function);
+	free(pp->lazy_line);
+
 	for (i = 0; i < pev->nargs; i++) {
-		if (pev->args[i].name)
-			free(pev->args[i].name);
-		if (pev->args[i].var)
-			free(pev->args[i].var);
-		if (pev->args[i].type)
-			free(pev->args[i].type);
+		free(pev->args[i].name);
+		free(pev->args[i].var);
+		free(pev->args[i].type);
 		field = pev->args[i].field;
 		while (field) {
 			next = field->next;
-			if (field->name)
-				free(field->name);
+			zfree(&field->name);
 			free(field);
 			field = next;
 		}
 	}
-	if (pev->args)
-		free(pev->args);
+	free(pev->args);
 	memset(pev, 0, sizeof(*pev));
 }
 
-void clear_kprobe_trace_event(struct kprobe_trace_event *tev)
+static void clear_probe_trace_event(struct probe_trace_event *tev)
 {
-	struct kprobe_trace_arg_ref *ref, *next;
+	struct probe_trace_arg_ref *ref, *next;
 	int i;
 
-	if (tev->event)
-		free(tev->event);
-	if (tev->group)
-		free(tev->group);
-	if (tev->point.symbol)
-		free(tev->point.symbol);
+	free(tev->event);
+	free(tev->group);
+	free(tev->point.symbol);
+	free(tev->point.module);
 	for (i = 0; i < tev->nargs; i++) {
-		if (tev->args[i].name)
-			free(tev->args[i].name);
-		if (tev->args[i].value)
-			free(tev->args[i].value);
-		if (tev->args[i].type)
-			free(tev->args[i].type);
+		free(tev->args[i].name);
+		free(tev->args[i].value);
+		free(tev->args[i].type);
 		ref = tev->args[i].ref;
 		while (ref) {
 			next = ref->next;
@@ -1084,12 +1776,30 @@ void clear_kprobe_trace_event(struct kprobe_trace_event *tev)
 			ref = next;
 		}
 	}
-	if (tev->args)
-		free(tev->args);
+	free(tev->args);
 	memset(tev, 0, sizeof(*tev));
 }
 
-static int open_kprobe_events(bool readwrite)
+static void print_warn_msg(const char *file, bool is_kprobe)
+{
+
+	if (errno == ENOENT) {
+		const char *config;
+
+		if (!is_kprobe)
+			config = "CONFIG_UPROBE_EVENTS";
+		else
+			config = "CONFIG_KPROBE_EVENTS";
+
+		pr_warning("%s file does not exist - please rebuild kernel"
+				" with %s.\n", file, config);
+	} else
+		pr_warning("Failed to open %s file: %s\n", file,
+				strerror(errno));
+}
+
+static int open_probe_events(const char *trace_file, bool readwrite,
+				bool is_kprobe)
 {
 	char buf[PATH_MAX];
 	const char *__debugfs;
@@ -1101,28 +1811,32 @@ static int open_kprobe_events(bool readwrite)
 		return -ENOENT;
 	}
 
-	ret = e_snprintf(buf, PATH_MAX, "%stracing/kprobe_events", __debugfs);
+	ret = e_snprintf(buf, PATH_MAX, "%s/%s", __debugfs, trace_file);
 	if (ret >= 0) {
 		pr_debug("Opening %s write=%d\n", buf, readwrite);
 		if (readwrite && !probe_event_dry_run)
 			ret = open(buf, O_RDWR, O_APPEND);
 		else
 			ret = open(buf, O_RDONLY, 0);
-	}
 
-	if (ret < 0) {
-		if (errno == ENOENT)
-			pr_warning("kprobe_events file does not exist - please"
-				 " rebuild kernel with CONFIG_KPROBE_EVENT.\n");
-		else
-			pr_warning("Failed to open kprobe_events file: %s\n",
-				   strerror(errno));
+		if (ret < 0)
+			print_warn_msg(buf, is_kprobe);
 	}
 	return ret;
 }
 
-/* Get raw string list of current kprobe_events */
-static struct strlist *get_kprobe_trace_command_rawlist(int fd)
+static int open_kprobe_events(bool readwrite)
+{
+	return open_probe_events("tracing/kprobe_events", readwrite, true);
+}
+
+static int open_uprobe_events(bool readwrite)
+{
+	return open_probe_events("tracing/uprobe_events", readwrite, false);
+}
+
+/* Get raw string list of current kprobe_events  or uprobe_events */
+static struct strlist *get_probe_trace_command_rawlist(int fd)
 {
 	int ret, idx;
 	FILE *fp;
@@ -1154,7 +1868,8 @@ static struct strlist *get_kprobe_trace_command_rawlist(int fd)
 }
 
 /* Show an event */
-static int show_perf_probe_event(struct perf_probe_event *pev)
+static int show_perf_probe_event(struct perf_probe_event *pev,
+				 const char *module)
 {
 	int i, ret;
 	char buf[128];
@@ -1170,6 +1885,8 @@ static int show_perf_probe_event(struct perf_probe_event *pev)
 		return ret;
 
 	printf("  %-20s (on %s", buf, place);
+	if (module)
+		printf(" in %s", module);
 
 	if (pev->nargs > 0) {
 		printf(" with");
@@ -1186,41 +1903,32 @@ static int show_perf_probe_event(struct perf_probe_event *pev)
 	return ret;
 }
 
-/* List up current perf-probe events */
-int show_perf_probe_events(void)
+static int __show_perf_probe_events(int fd, bool is_kprobe)
 {
-	int fd, ret;
-	struct kprobe_trace_event tev;
+	int ret = 0;
+	struct probe_trace_event tev;
 	struct perf_probe_event pev;
 	struct strlist *rawlist;
 	struct str_node *ent;
 
-	setup_pager();
-	ret = init_vmlinux();
-	if (ret < 0)
-		return ret;
-
 	memset(&tev, 0, sizeof(tev));
 	memset(&pev, 0, sizeof(pev));
 
-	fd = open_kprobe_events(false);
-	if (fd < 0)
-		return fd;
-
-	rawlist = get_kprobe_trace_command_rawlist(fd);
-	close(fd);
+	rawlist = get_probe_trace_command_rawlist(fd);
 	if (!rawlist)
 		return -ENOENT;
 
 	strlist__for_each(ent, rawlist) {
-		ret = parse_kprobe_trace_command(ent->s, &tev);
+		ret = parse_probe_trace_command(ent->s, &tev);
 		if (ret >= 0) {
-			ret = convert_to_perf_probe_event(&tev, &pev);
+			ret = convert_to_perf_probe_event(&tev, &pev,
+								is_kprobe);
 			if (ret >= 0)
-				ret = show_perf_probe_event(&pev);
+				ret = show_perf_probe_event(&pev,
+							    tev.point.module);
 		}
 		clear_perf_probe_event(&pev);
-		clear_kprobe_trace_event(&tev);
+		clear_probe_trace_event(&tev);
 		if (ret < 0)
 			break;
 	}
@@ -1229,21 +1937,48 @@ int show_perf_probe_events(void)
 	return ret;
 }
 
+/* List up current perf-probe events */
+int show_perf_probe_events(void)
+{
+	int fd, ret;
+
+	setup_pager();
+	fd = open_kprobe_events(false);
+
+	if (fd < 0)
+		return fd;
+
+	ret = init_symbol_maps(false);
+	if (ret < 0)
+		return ret;
+
+	ret = __show_perf_probe_events(fd, true);
+	close(fd);
+
+	fd = open_uprobe_events(false);
+	if (fd >= 0) {
+		ret = __show_perf_probe_events(fd, false);
+		close(fd);
+	}
+
+	exit_symbol_maps();
+	return ret;
+}
+
 /* Get current perf-probe event names */
-static struct strlist *get_kprobe_trace_event_names(int fd, bool include_group)
+static struct strlist *get_probe_trace_event_names(int fd, bool include_group)
 {
 	char buf[128];
 	struct strlist *sl, *rawlist;
 	struct str_node *ent;
-	struct kprobe_trace_event tev;
+	struct probe_trace_event tev;
 	int ret = 0;
 
 	memset(&tev, 0, sizeof(tev));
-
-	rawlist = get_kprobe_trace_command_rawlist(fd);
+	rawlist = get_probe_trace_command_rawlist(fd);
 	sl = strlist__new(true, NULL);
 	strlist__for_each(ent, rawlist) {
-		ret = parse_kprobe_trace_command(ent->s, &tev);
+		ret = parse_probe_trace_command(ent->s, &tev);
 		if (ret < 0)
 			break;
 		if (include_group) {
@@ -1253,7 +1988,7 @@ static struct strlist *get_kprobe_trace_event_names(int fd, bool include_group)
 				ret = strlist__add(sl, buf);
 		} else
 			ret = strlist__add(sl, tev.event);
-		clear_kprobe_trace_event(&tev);
+		clear_probe_trace_event(&tev);
 		if (ret < 0)
 			break;
 	}
@@ -1266,13 +2001,13 @@ static struct strlist *get_kprobe_trace_event_names(int fd, bool include_group)
 	return sl;
 }
 
-static int write_kprobe_trace_event(int fd, struct kprobe_trace_event *tev)
+static int write_probe_trace_event(int fd, struct probe_trace_event *tev)
 {
 	int ret = 0;
-	char *buf = synthesize_kprobe_trace_command(tev);
+	char *buf = synthesize_probe_trace_command(tev);
 
 	if (!buf) {
-		pr_debug("Failed to synthesize kprobe trace event.\n");
+		pr_debug("Failed to synthesize probe trace event.\n");
 		return -EINVAL;
 	}
 
@@ -1325,28 +2060,32 @@ static int get_new_event_name(char *buf, size_t len, const char *base,
 	return ret;
 }
 
-static int __add_kprobe_trace_events(struct perf_probe_event *pev,
-				     struct kprobe_trace_event *tevs,
+static int __add_probe_trace_events(struct perf_probe_event *pev,
+				     struct probe_trace_event *tevs,
 				     int ntevs, bool allow_suffix)
 {
 	int i, fd, ret;
-	struct kprobe_trace_event *tev = NULL;
+	struct probe_trace_event *tev = NULL;
 	char buf[64];
 	const char *event, *group;
 	struct strlist *namelist;
 
-	fd = open_kprobe_events(true);
+	if (pev->uprobes)
+		fd = open_uprobe_events(true);
+	else
+		fd = open_kprobe_events(true);
+
 	if (fd < 0)
 		return fd;
 	/* Get current event names */
-	namelist = get_kprobe_trace_event_names(fd, false);
+	namelist = get_probe_trace_event_names(fd, false);
 	if (!namelist) {
 		pr_debug("Failed to get current event list.\n");
 		return -EIO;
 	}
 
 	ret = 0;
-	printf("Add new event%s\n", (ntevs > 1) ? "s:" : ":");
+	printf("Added new event%s\n", (ntevs > 1) ? "s:" : ":");
 	for (i = 0; i < ntevs; i++) {
 		tev = &tevs[i];
 		if (pev->event)
@@ -1374,7 +2113,7 @@ static int __add_kprobe_trace_events(struct perf_probe_event *pev,
 			ret = -ENOMEM;
 			break;
 		}
-		ret = write_kprobe_trace_event(fd, tev);
+		ret = write_probe_trace_event(fd, tev);
 		if (ret < 0)
 			break;
 		/* Add added event name to namelist */
@@ -1385,7 +2124,7 @@ static int __add_kprobe_trace_events(struct perf_probe_event *pev,
 		group = pev->group;
 		pev->event = tev->event;
 		pev->group = tev->group;
-		show_perf_probe_event(pev);
+		show_perf_probe_event(pev, tev->point.module);
 		/* Trick here - restore current event/group */
 		pev->event = (char *)event;
 		pev->group = (char *)group;
@@ -1401,7 +2140,7 @@ static int __add_kprobe_trace_events(struct perf_probe_event *pev,
 
 	if (ret >= 0) {
 		/* Show how to use the event. */
-		printf("\nYou can now use it on all perf tools, such as:\n\n");
+		printf("\nYou can now use it in all perf tools, such as:\n\n");
 		printf("\tperf record -e %s:%s -aR sleep 1\n\n", tev->group,
 			 tev->event);
 	}
@@ -1411,132 +2150,241 @@ static int __add_kprobe_trace_events(struct perf_probe_event *pev,
 	return ret;
 }
 
-static int convert_to_kprobe_trace_events(struct perf_probe_event *pev,
-					  struct kprobe_trace_event **tevs,
-					  int max_tevs)
+static char *looking_function_name;
+static int num_matched_functions;
+
+static int probe_function_filter(struct map *map __maybe_unused,
+				      struct symbol *sym)
 {
+	if ((sym->binding == STB_GLOBAL || sym->binding == STB_LOCAL) &&
+	    strcmp(looking_function_name, sym->name) == 0) {
+		num_matched_functions++;
+		return 0;
+	}
+	return 1;
+}
+
+#define strdup_or_goto(str, label)	\
+	({ char *__p = strdup(str); if (!__p) goto label; __p; })
+
+/*
+ * Find probe function addresses from map.
+ * Return an error or the number of found probe_trace_event
+ */
+static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
+					    struct probe_trace_event **tevs,
+					    int max_tevs, const char *target)
+{
+	struct map *map = NULL;
+	struct kmap *kmap = NULL;
+	struct ref_reloc_sym *reloc_sym = NULL;
 	struct symbol *sym;
-	int ret = 0, i;
-	struct kprobe_trace_event *tev;
+	struct rb_node *nd;
+	struct probe_trace_event *tev;
+	struct perf_probe_point *pp = &pev->point;
+	struct probe_trace_point *tp;
+	int ret, i;
 
-	/* Convert perf_probe_event with debuginfo */
-	ret = try_to_find_kprobe_trace_events(pev, tevs, max_tevs);
-	if (ret != 0)
-		return ret;
+	/* Init maps of given executable or kernel */
+	if (pev->uprobes)
+		map = dso__new_map(target);
+	else
+		map = kernel_get_module_map(target);
+	if (!map) {
+		ret = -EINVAL;
+		goto out;
+	}
 
-	/* Allocate trace event buffer */
-	tev = *tevs = zalloc(sizeof(struct kprobe_trace_event));
-	if (tev == NULL)
-		return -ENOMEM;
+	/*
+	 * Load matched symbols: Since the different local symbols may have
+	 * same name but different addresses, this lists all the symbols.
+	 */
+	num_matched_functions = 0;
+	looking_function_name = pp->function;
+	ret = map__load(map, probe_function_filter);
+	if (ret || num_matched_functions == 0) {
+		pr_err("Failed to find symbol %s in %s\n", pp->function,
+			target ? : "kernel");
+		ret = -ENOENT;
+		goto out;
+	} else if (num_matched_functions > max_tevs) {
+		pr_err("Too many functions matched in %s\n",
+			target ? : "kernel");
+		ret = -E2BIG;
+		goto out;
+	}
 
-	/* Copy parameters */
-	tev->point.symbol = strdup(pev->point.function);
-	if (tev->point.symbol == NULL) {
+	if (!pev->uprobes) {
+		kmap = map__kmap(map);
+		reloc_sym = kmap->ref_reloc_sym;
+		if (!reloc_sym) {
+			pr_warning("Relocated base symbol is not found!\n");
+			ret = -EINVAL;
+			goto out;
+		}
+	}
+
+	/* Setup result trace-probe-events */
+	*tevs = zalloc(sizeof(*tev) * num_matched_functions);
+	if (!*tevs) {
 		ret = -ENOMEM;
-		goto error;
+		goto out;
 	}
-	tev->point.offset = pev->point.offset;
-	tev->nargs = pev->nargs;
-	if (tev->nargs) {
-		tev->args = zalloc(sizeof(struct kprobe_trace_arg)
-				   * tev->nargs);
-		if (tev->args == NULL) {
-			ret = -ENOMEM;
-			goto error;
+
+	ret = 0;
+	map__for_each_symbol(map, sym, nd) {
+		tev = (*tevs) + ret;
+		tp = &tev->point;
+		if (ret == num_matched_functions) {
+			pr_warning("Too many symbols are listed. Skip it.\n");
+			break;
+		}
+		ret++;
+
+		if (pp->offset > sym->end - sym->start) {
+			pr_warning("Offset %ld is bigger than the size of %s\n",
+				   pp->offset, sym->name);
+			ret = -ENOENT;
+			goto err_out;
+		}
+		/* Add one probe point */
+		tp->address = map->unmap_ip(map, sym->start) + pp->offset;
+		if (reloc_sym) {
+			tp->symbol = strdup_or_goto(reloc_sym->name, nomem_out);
+			tp->offset = tp->address - reloc_sym->addr;
+		} else {
+			tp->symbol = strdup_or_goto(sym->name, nomem_out);
+			tp->offset = pp->offset;
+		}
+		tp->retprobe = pp->retprobe;
+		if (target)
+			tev->point.module = strdup_or_goto(target, nomem_out);
+		tev->uprobes = pev->uprobes;
+		tev->nargs = pev->nargs;
+		if (tev->nargs) {
+			tev->args = zalloc(sizeof(struct probe_trace_arg) *
+					   tev->nargs);
+			if (tev->args == NULL)
+				goto nomem_out;
 		}
 		for (i = 0; i < tev->nargs; i++) {
-			if (pev->args[i].name) {
-				tev->args[i].name = strdup(pev->args[i].name);
-				if (tev->args[i].name == NULL) {
-					ret = -ENOMEM;
-					goto error;
-				}
-			}
-			tev->args[i].value = strdup(pev->args[i].var);
-			if (tev->args[i].value == NULL) {
-				ret = -ENOMEM;
-				goto error;
-			}
-			if (pev->args[i].type) {
-				tev->args[i].type = strdup(pev->args[i].type);
-				if (tev->args[i].type == NULL) {
-					ret = -ENOMEM;
-					goto error;
-				}
-			}
+			if (pev->args[i].name)
+				tev->args[i].name =
+					strdup_or_goto(pev->args[i].name,
+							nomem_out);
+
+			tev->args[i].value = strdup_or_goto(pev->args[i].var,
+							    nomem_out);
+			if (pev->args[i].type)
+				tev->args[i].type =
+					strdup_or_goto(pev->args[i].type,
+							nomem_out);
 		}
 	}
 
-	/* Currently just checking function name from symbol map */
-	sym = map__find_symbol_by_name(machine.vmlinux_maps[MAP__FUNCTION],
-				       tev->point.symbol, NULL);
-	if (!sym) {
-		pr_warning("Kernel symbol \'%s\' not found.\n",
-			   tev->point.symbol);
-		ret = -ENOENT;
-		goto error;
+out:
+	if (map && pev->uprobes) {
+		/* Only when using uprobe(exec) map needs to be released */
+		dso__delete(map->dso);
+		map__delete(map);
 	}
-
-	return 1;
-error:
-	clear_kprobe_trace_event(tev);
-	free(tev);
-	*tevs = NULL;
 	return ret;
+
+nomem_out:
+	ret = -ENOMEM;
+err_out:
+	clear_probe_trace_events(*tevs, num_matched_functions);
+	zfree(tevs);
+	goto out;
+}
+
+static int convert_to_probe_trace_events(struct perf_probe_event *pev,
+					  struct probe_trace_event **tevs,
+					  int max_tevs, const char *target)
+{
+	int ret;
+
+	if (pev->uprobes && !pev->group) {
+		/* Replace group name if not given */
+		ret = convert_exec_to_group(target, &pev->group);
+		if (ret != 0) {
+			pr_warning("Failed to make a group name.\n");
+			return ret;
+		}
+	}
+
+	/* Convert perf_probe_event with debuginfo */
+	ret = try_to_find_probe_trace_events(pev, tevs, max_tevs, target);
+	if (ret != 0)
+		return ret;	/* Found in debuginfo or got an error */
+
+	return find_probe_trace_events_from_map(pev, tevs, max_tevs, target);
 }
 
 struct __event_package {
 	struct perf_probe_event		*pev;
-	struct kprobe_trace_event	*tevs;
+	struct probe_trace_event	*tevs;
 	int				ntevs;
 };
 
 int add_perf_probe_events(struct perf_probe_event *pevs, int npevs,
-			  bool force_add, int max_tevs)
+			  int max_tevs, const char *target, bool force_add)
 {
 	int i, j, ret;
 	struct __event_package *pkgs;
 
+	ret = 0;
 	pkgs = zalloc(sizeof(struct __event_package) * npevs);
+
 	if (pkgs == NULL)
 		return -ENOMEM;
 
-	/* Init vmlinux path */
-	ret = init_vmlinux();
-	if (ret < 0)
+	ret = init_symbol_maps(pevs->uprobes);
+	if (ret < 0) {
+		free(pkgs);
 		return ret;
+	}
 
 	/* Loop 1: convert all events */
 	for (i = 0; i < npevs; i++) {
 		pkgs[i].pev = &pevs[i];
 		/* Convert with or without debuginfo */
-		ret  = convert_to_kprobe_trace_events(pkgs[i].pev,
-						      &pkgs[i].tevs, max_tevs);
+		ret  = convert_to_probe_trace_events(pkgs[i].pev,
+						     &pkgs[i].tevs,
+						     max_tevs,
+						     target);
 		if (ret < 0)
 			goto end;
 		pkgs[i].ntevs = ret;
 	}
 
 	/* Loop 2: add all events */
-	for (i = 0; i < npevs && ret >= 0; i++)
-		ret = __add_kprobe_trace_events(pkgs[i].pev, pkgs[i].tevs,
+	for (i = 0; i < npevs; i++) {
+		ret = __add_probe_trace_events(pkgs[i].pev, pkgs[i].tevs,
 						pkgs[i].ntevs, force_add);
+		if (ret < 0)
+			break;
+	}
 end:
-	/* Loop 3: cleanup trace events  */
-	for (i = 0; i < npevs; i++)
+	/* Loop 3: cleanup and free trace events  */
+	for (i = 0; i < npevs; i++) {
 		for (j = 0; j < pkgs[i].ntevs; j++)
-			clear_kprobe_trace_event(&pkgs[i].tevs[j]);
+			clear_probe_trace_event(&pkgs[i].tevs[j]);
+		zfree(&pkgs[i].tevs);
+	}
+	free(pkgs);
+	exit_symbol_maps();
 
 	return ret;
 }
 
-static int __del_trace_kprobe_event(int fd, struct str_node *ent)
+static int __del_trace_probe_event(int fd, struct str_node *ent)
 {
 	char *p;
 	char buf[128];
 	int ret;
 
-	/* Convert from perf-probe event to trace-kprobe event */
+	/* Convert from perf-probe event to trace-probe event */
 	ret = e_snprintf(buf, 128, "-:%s", ent->s);
 	if (ret < 0)
 		goto error;
@@ -1552,34 +2400,28 @@ static int __del_trace_kprobe_event(int fd, struct str_node *ent)
 
 	pr_debug("Writing event: %s\n", buf);
 	ret = write(fd, buf, strlen(buf));
-	if (ret < 0)
+	if (ret < 0) {
+		ret = -errno;
 		goto error;
+	}
 
-	printf("Remove event: %s\n", ent->s);
+	printf("Removed event: %s\n", ent->s);
 	return 0;
 error:
 	pr_warning("Failed to delete event: %s\n", strerror(-ret));
 	return ret;
 }
 
-static int del_trace_kprobe_event(int fd, const char *group,
-				  const char *event, struct strlist *namelist)
+static int del_trace_probe_event(int fd, const char *buf,
+						  struct strlist *namelist)
 {
-	char buf[128];
 	struct str_node *ent, *n;
-	int found = 0, ret = 0;
-
-	ret = e_snprintf(buf, 128, "%s:%s", group, event);
-	if (ret < 0) {
-		pr_err("Failed to copy event.");
-		return ret;
-	}
+	int ret = -1;
 
 	if (strpbrk(buf, "*?")) { /* Glob-exp */
 		strlist__for_each_safe(ent, n, namelist)
 			if (strglobmatch(ent->s, buf)) {
-				found++;
-				ret = __del_trace_kprobe_event(fd, ent);
+				ret = __del_trace_probe_event(fd, ent);
 				if (ret < 0)
 					break;
 				strlist__remove(namelist, ent);
@@ -1587,40 +2429,43 @@ static int del_trace_kprobe_event(int fd, const char *group,
 	} else {
 		ent = strlist__find(namelist, buf);
 		if (ent) {
-			found++;
-			ret = __del_trace_kprobe_event(fd, ent);
+			ret = __del_trace_probe_event(fd, ent);
 			if (ret >= 0)
 				strlist__remove(namelist, ent);
 		}
 	}
-	if (found == 0 && ret >= 0)
-		pr_info("Info: Event \"%s\" does not exist.\n", buf);
 
 	return ret;
 }
 
 int del_perf_probe_events(struct strlist *dellist)
 {
-	int fd, ret = 0;
+	int ret = -1, ufd = -1, kfd = -1;
+	char buf[128];
 	const char *group, *event;
 	char *p, *str;
 	struct str_node *ent;
-	struct strlist *namelist;
-
-	fd = open_kprobe_events(true);
-	if (fd < 0)
-		return fd;
+	struct strlist *namelist = NULL, *unamelist = NULL;
 
 	/* Get current event names */
-	namelist = get_kprobe_trace_event_names(fd, true);
-	if (namelist == NULL)
-		return -EINVAL;
+	kfd = open_kprobe_events(true);
+	if (kfd < 0)
+		return kfd;
+
+	namelist = get_probe_trace_event_names(kfd, true);
+	ufd = open_uprobe_events(true);
+
+	if (ufd >= 0)
+		unamelist = get_probe_trace_event_names(ufd, true);
+
+	if (namelist == NULL && unamelist == NULL)
+		goto error;
 
 	strlist__for_each(ent, dellist) {
 		str = strdup(ent->s);
 		if (str == NULL) {
 			ret = -ENOMEM;
-			break;
+			goto error;
 		}
 		pr_debug("Parsing: %s\n", str);
 		p = strchr(str, ':');
@@ -1632,14 +2477,96 @@ int del_perf_probe_events(struct strlist *dellist)
 			group = "*";
 			event = str;
 		}
+
+		ret = e_snprintf(buf, 128, "%s:%s", group, event);
+		if (ret < 0) {
+			pr_err("Failed to copy event.");
+			free(str);
+			goto error;
+		}
+
 		pr_debug("Group: %s, Event: %s\n", group, event);
-		ret = del_trace_kprobe_event(fd, group, event, namelist);
+
+		if (namelist)
+			ret = del_trace_probe_event(kfd, buf, namelist);
+
+		if (unamelist && ret != 0)
+			ret = del_trace_probe_event(ufd, buf, unamelist);
+
+		if (ret != 0)
+			pr_info("Info: Event \"%s\" does not exist.\n", buf);
+
 		free(str);
-		if (ret < 0)
-			break;
 	}
-	strlist__delete(namelist);
-	close(fd);
+
+error:
+	if (kfd >= 0) {
+		strlist__delete(namelist);
+		close(kfd);
+	}
+
+	if (ufd >= 0) {
+		strlist__delete(unamelist);
+		close(ufd);
+	}
+
+	return ret;
+}
+
+/* TODO: don't use a global variable for filter ... */
+static struct strfilter *available_func_filter;
+
+/*
+ * If a symbol corresponds to a function with global binding and
+ * matches filter return 0. For all others return 1.
+ */
+static int filter_available_functions(struct map *map __maybe_unused,
+				      struct symbol *sym)
+{
+	if ((sym->binding == STB_GLOBAL || sym->binding == STB_LOCAL) &&
+	    strfilter__compare(available_func_filter, sym->name))
+		return 0;
+	return 1;
+}
+
+int show_available_funcs(const char *target, struct strfilter *_filter,
+					bool user)
+{
+	struct map *map;
+	int ret;
+
+	ret = init_symbol_maps(user);
+	if (ret < 0)
+		return ret;
+
+	/* Get a symbol map */
+	if (user)
+		map = dso__new_map(target);
+	else
+		map = kernel_get_module_map(target);
+	if (!map) {
+		pr_err("Failed to get a map for %s\n", (target) ? : "kernel");
+		return -EINVAL;
+	}
+
+	/* Load symbols with given filter */
+	available_func_filter = _filter;
+	if (map__load(map, filter_available_functions)) {
+		pr_err("Failed to load symbols in %s\n", (target) ? : "kernel");
+		goto end;
+	}
+	if (!dso__sorted_by_name(map->dso, map->type))
+		dso__sort_by_name(map->dso, map->type);
+
+	/* Show all (filtered) symbols */
+	setup_pager();
+	dso__fprintf_symbols_by_name(map->dso, map->type, stdout);
+end:
+	if (user) {
+		dso__delete(map->dso);
+		map__delete(map);
+	}
+	exit_symbol_maps();
 
 	return ret;
 }
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index e9db1a214ca..776c9347a3b 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -2,38 +2,43 @@
 #define _PROBE_EVENT_H
 
 #include <stdbool.h>
+#include "intlist.h"
 #include "strlist.h"
+#include "strfilter.h"
 
 extern bool probe_event_dry_run;
 
-/* kprobe-tracer tracing point */
-struct kprobe_trace_point {
+/* kprobe-tracer and uprobe-tracer tracing point */
+struct probe_trace_point {
 	char		*symbol;	/* Base symbol */
+	char		*module;	/* Module name */
 	unsigned long	offset;		/* Offset from symbol */
+	unsigned long	address;	/* Actual address of the trace point */
 	bool		retprobe;	/* Return probe flag */
 };
 
-/* kprobe-tracer tracing argument referencing offset */
-struct kprobe_trace_arg_ref {
-	struct kprobe_trace_arg_ref	*next;	/* Next reference */
+/* probe-tracer tracing argument referencing offset */
+struct probe_trace_arg_ref {
+	struct probe_trace_arg_ref	*next;	/* Next reference */
 	long				offset;	/* Offset value */
 };
 
-/* kprobe-tracer tracing argument */
-struct kprobe_trace_arg {
+/* kprobe-tracer and uprobe-tracer tracing argument */
+struct probe_trace_arg {
 	char				*name;	/* Argument name */
 	char				*value;	/* Base value */
 	char				*type;	/* Type name */
-	struct kprobe_trace_arg_ref	*ref;	/* Referencing offset */
+	struct probe_trace_arg_ref	*ref;	/* Referencing offset */
 };
 
-/* kprobe-tracer tracing event (point + arg) */
-struct kprobe_trace_event {
+/* kprobe-tracer and uprobe-tracer tracing event (point + arg) */
+struct probe_trace_event {
 	char				*event;	/* Event name */
 	char				*group;	/* Group name */
-	struct kprobe_trace_point	point;	/* Trace point */
+	struct probe_trace_point	point;	/* Trace point */
 	int				nargs;	/* Number of args */
-	struct kprobe_trace_arg		*args;	/* Arguments */
+	bool				uprobes;	/* uprobes only */
+	struct probe_trace_arg		*args;	/* Arguments */
 };
 
 /* Perf probe probing point */
@@ -50,6 +55,7 @@ struct perf_probe_point {
 struct perf_probe_arg_field {
 	struct perf_probe_arg_field	*next;	/* Next field */
 	char				*name;	/* Name of the field */
+	long				index;	/* Array index number */
 	bool				ref;	/* Referencing flag */
 };
 
@@ -67,16 +73,10 @@ struct perf_probe_event {
 	char			*group;	/* Group name */
 	struct perf_probe_point	point;	/* Probe point */
 	int			nargs;	/* Number of arguments */
+	bool			uprobes;
 	struct perf_probe_arg	*args;	/* Arguments */
 };
 
-
-/* Line number container */
-struct line_node {
-	struct list_head	list;
-	int			line;
-};
-
 /* Line range */
 struct line_range {
 	char			*file;		/* File name */
@@ -85,42 +85,55 @@ struct line_range {
 	int			end;		/* End line number */
 	int			offset;		/* Start line offset */
 	char			*path;		/* Real path name */
-	struct list_head	line_list;	/* Visible lines */
+	char			*comp_dir;	/* Compile directory */
+	struct intlist		*line_list;	/* Visible lines */
+};
+
+/* List of variables */
+struct variable_list {
+	struct probe_trace_point	point;	/* Actual probepoint */
+	struct strlist			*vars;	/* Available variables */
 };
 
 /* Command string to events */
 extern int parse_perf_probe_command(const char *cmd,
 				    struct perf_probe_event *pev);
-extern int parse_kprobe_trace_command(const char *cmd,
-				      struct kprobe_trace_event *tev);
 
 /* Events to command string */
 extern char *synthesize_perf_probe_command(struct perf_probe_event *pev);
-extern char *synthesize_kprobe_trace_command(struct kprobe_trace_event *tev);
+extern char *synthesize_probe_trace_command(struct probe_trace_event *tev);
 extern int synthesize_perf_probe_arg(struct perf_probe_arg *pa, char *buf,
 				     size_t len);
 
 /* Check the perf_probe_event needs debuginfo */
 extern bool perf_probe_event_need_dwarf(struct perf_probe_event *pev);
 
-/* Convert from kprobe_trace_event to perf_probe_event */
-extern int convert_to_perf_probe_event(struct kprobe_trace_event *tev,
-				       struct perf_probe_event *pev);
-
 /* Release event contents */
 extern void clear_perf_probe_event(struct perf_probe_event *pev);
-extern void clear_kprobe_trace_event(struct kprobe_trace_event *tev);
 
 /* Command string to line-range */
 extern int parse_line_range_desc(const char *cmd, struct line_range *lr);
 
+/* Release line range members */
+extern void line_range__clear(struct line_range *lr);
+
+/* Initialize line range */
+extern int line_range__init(struct line_range *lr);
+
+/* Internal use: Return kernel/module path */
+extern const char *kernel_get_module_path(const char *module);
 
 extern int add_perf_probe_events(struct perf_probe_event *pevs, int npevs,
-				 bool force_add, int max_probe_points);
+				 int max_probe_points, const char *module,
+				 bool force_add);
 extern int del_perf_probe_events(struct strlist *dellist);
 extern int show_perf_probe_events(void);
-extern int show_line_range(struct line_range *lr);
-
+extern int show_line_range(struct line_range *lr, const char *module);
+extern int show_available_vars(struct perf_probe_event *pevs, int npevs,
+			       int max_probe_points, const char *module,
+			       struct strfilter *filter, bool externs);
+extern int show_available_funcs(const char *module, struct strfilter *filter,
+				bool user);
 
 /* Maximum index number of event-name postfix */
 #define MAX_EVENT_INDEX	1024
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index d964cb199c6..98e30476641 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -30,351 +30,207 @@
 #include <stdlib.h>
 #include <string.h>
 #include <stdarg.h>
-#include <ctype.h>
 #include <dwarf-regs.h>
 
-#include "string.h"
+#include <linux/bitops.h>
 #include "event.h"
+#include "dso.h"
 #include "debug.h"
+#include "intlist.h"
 #include "util.h"
+#include "symbol.h"
 #include "probe-finder.h"
 
 /* Kprobe tracer basic type is up to u64 */
 #define MAX_BASIC_TYPE_BITS	64
 
-/*
- * Compare the tail of two strings.
- * Return 0 if whole of either string is same as another's tail part.
- */
-static int strtailcmp(const char *s1, const char *s2)
-{
-	int i1 = strlen(s1);
-	int i2 = strlen(s2);
-	while (--i1 >= 0 && --i2 >= 0) {
-		if (s1[i1] != s2[i2])
-			return s1[i1] - s2[i2];
-	}
-	return 0;
-}
-
-/* Line number list operations */
-
-/* Add a line to line number list */
-static int line_list__add_line(struct list_head *head, int line)
-{
-	struct line_node *ln;
-	struct list_head *p;
-
-	/* Reverse search, because new line will be the last one */
-	list_for_each_entry_reverse(ln, head, list) {
-		if (ln->line < line) {
-			p = &ln->list;
-			goto found;
-		} else if (ln->line == line)	/* Already exist */
-			return 1;
-	}
-	/* List is empty, or the smallest entry */
-	p = head;
-found:
-	pr_debug("line list: add a line %u\n", line);
-	ln = zalloc(sizeof(struct line_node));
-	if (ln == NULL)
-		return -ENOMEM;
-	ln->line = line;
-	INIT_LIST_HEAD(&ln->list);
-	list_add(&ln->list, p);
-	return 0;
-}
-
-/* Check if the line in line number list */
-static int line_list__has_line(struct list_head *head, int line)
-{
-	struct line_node *ln;
-
-	/* Reverse search, because new line will be the last one */
-	list_for_each_entry(ln, head, list)
-		if (ln->line == line)
-			return 1;
-
-	return 0;
-}
-
-/* Init line number list */
-static void line_list__init(struct list_head *head)
-{
-	INIT_LIST_HEAD(head);
-}
-
-/* Free line number list */
-static void line_list__free(struct list_head *head)
-{
-	struct line_node *ln;
-	while (!list_empty(head)) {
-		ln = list_first_entry(head, struct line_node, list);
-		list_del(&ln->list);
-		free(ln);
-	}
-}
-
-/* Dwarf wrappers */
-
-/* Find the realpath of the target file. */
-static const char *cu_find_realpath(Dwarf_Die *cu_die, const char *fname)
-{
-	Dwarf_Files *files;
-	size_t nfiles, i;
-	const char *src = NULL;
-	int ret;
-
-	if (!fname)
-		return NULL;
+/* Dwarf FL wrappers */
+static char *debuginfo_path;	/* Currently dummy */
 
-	ret = dwarf_getsrcfiles(cu_die, &files, &nfiles);
-	if (ret != 0)
-		return NULL;
-
-	for (i = 0; i < nfiles; i++) {
-		src = dwarf_filesrc(files, i, NULL, NULL);
-		if (strtailcmp(src, fname) == 0)
-			break;
-	}
-	if (i == nfiles)
-		return NULL;
-	return src;
-}
-
-/* Compare diename and tname */
-static bool die_compare_name(Dwarf_Die *dw_die, const char *tname)
-{
-	const char *name;
-	name = dwarf_diename(dw_die);
-	return name ? strcmp(tname, name) : -1;
-}
+static const Dwfl_Callbacks offline_callbacks = {
+	.find_debuginfo = dwfl_standard_find_debuginfo,
+	.debuginfo_path = &debuginfo_path,
 
-/* Get type die, but skip qualifiers and typedef */
-static Dwarf_Die *die_get_real_type(Dwarf_Die *vr_die, Dwarf_Die *die_mem)
-{
-	Dwarf_Attribute attr;
-	int tag;
-
-	do {
-		if (dwarf_attr(vr_die, DW_AT_type, &attr) == NULL ||
-		    dwarf_formref_die(&attr, die_mem) == NULL)
-			return NULL;
-
-		tag = dwarf_tag(die_mem);
-		vr_die = die_mem;
-	} while (tag == DW_TAG_const_type ||
-		 tag == DW_TAG_restrict_type ||
-		 tag == DW_TAG_volatile_type ||
-		 tag == DW_TAG_shared_type ||
-		 tag == DW_TAG_typedef);
+	.section_address = dwfl_offline_section_address,
 
-	return die_mem;
-}
-
-static bool die_is_signed_type(Dwarf_Die *tp_die)
-{
-	Dwarf_Attribute attr;
-	Dwarf_Word ret;
-
-	if (dwarf_attr(tp_die, DW_AT_encoding, &attr) == NULL ||
-	    dwarf_formudata(&attr, &ret) != 0)
-		return false;
-
-	return (ret == DW_ATE_signed_char || ret == DW_ATE_signed ||
-		ret == DW_ATE_signed_fixed);
-}
+	/* We use this table for core files too.  */
+	.find_elf = dwfl_build_id_find_elf,
+};
 
-static int die_get_byte_size(Dwarf_Die *tp_die)
+/* Get a Dwarf from offline image */
+static int debuginfo__init_offline_dwarf(struct debuginfo *dbg,
+					 const char *path)
 {
-	Dwarf_Attribute attr;
-	Dwarf_Word ret;
+	int fd;
 
-	if (dwarf_attr(tp_die, DW_AT_byte_size, &attr) == NULL ||
-	    dwarf_formudata(&attr, &ret) != 0)
-		return 0;
-
-	return (int)ret;
-}
+	fd = open(path, O_RDONLY);
+	if (fd < 0)
+		return fd;
 
-/* Get data_member_location offset */
-static int die_get_data_member_location(Dwarf_Die *mb_die, Dwarf_Word *offs)
-{
-	Dwarf_Attribute attr;
-	Dwarf_Op *expr;
-	size_t nexpr;
-	int ret;
+	dbg->dwfl = dwfl_begin(&offline_callbacks);
+	if (!dbg->dwfl)
+		goto error;
 
-	if (dwarf_attr(mb_die, DW_AT_data_member_location, &attr) == NULL)
-		return -ENOENT;
+	dbg->mod = dwfl_report_offline(dbg->dwfl, "", "", fd);
+	if (!dbg->mod)
+		goto error;
 
-	if (dwarf_formudata(&attr, offs) != 0) {
-		/* DW_AT_data_member_location should be DW_OP_plus_uconst */
-		ret = dwarf_getlocation(&attr, &expr, &nexpr);
-		if (ret < 0 || nexpr == 0)
-			return -ENOENT;
+	dbg->dbg = dwfl_module_getdwarf(dbg->mod, &dbg->bias);
+	if (!dbg->dbg)
+		goto error;
 
-		if (expr[0].atom != DW_OP_plus_uconst || nexpr != 1) {
-			pr_debug("Unable to get offset:Unexpected OP %x (%zd)\n",
-				 expr[0].atom, nexpr);
-			return -ENOTSUP;
-		}
-		*offs = (Dwarf_Word)expr[0].number;
-	}
 	return 0;
-}
+error:
+	if (dbg->dwfl)
+		dwfl_end(dbg->dwfl);
+	else
+		close(fd);
+	memset(dbg, 0, sizeof(*dbg));
 
-/* Return values for die_find callbacks */
-enum {
-	DIE_FIND_CB_FOUND = 0,		/* End of Search */
-	DIE_FIND_CB_CHILD = 1,		/* Search only children */
-	DIE_FIND_CB_SIBLING = 2,	/* Search only siblings */
-	DIE_FIND_CB_CONTINUE = 3,	/* Search children and siblings */
-};
+	return -ENOENT;
+}
 
-/* Search a child die */
-static Dwarf_Die *die_find_child(Dwarf_Die *rt_die,
-				 int (*callback)(Dwarf_Die *, void *),
-				 void *data, Dwarf_Die *die_mem)
+static struct debuginfo *__debuginfo__new(const char *path)
 {
-	Dwarf_Die child_die;
-	int ret;
-
-	ret = dwarf_child(rt_die, die_mem);
-	if (ret != 0)
+	struct debuginfo *dbg = zalloc(sizeof(*dbg));
+	if (!dbg)
 		return NULL;
 
-	do {
-		ret = callback(die_mem, data);
-		if (ret == DIE_FIND_CB_FOUND)
-			return die_mem;
-
-		if ((ret & DIE_FIND_CB_CHILD) &&
-		    die_find_child(die_mem, callback, data, &child_die)) {
-			memcpy(die_mem, &child_die, sizeof(Dwarf_Die));
-			return die_mem;
-		}
-	} while ((ret & DIE_FIND_CB_SIBLING) &&
-		 dwarf_siblingof(die_mem, die_mem) == 0);
-
-	return NULL;
+	if (debuginfo__init_offline_dwarf(dbg, path) < 0)
+		zfree(&dbg);
+	if (dbg)
+		pr_debug("Open Debuginfo file: %s\n", path);
+	return dbg;
 }
 
-struct __addr_die_search_param {
-	Dwarf_Addr	addr;
-	Dwarf_Die	*die_mem;
+enum dso_binary_type distro_dwarf_types[] = {
+	DSO_BINARY_TYPE__FEDORA_DEBUGINFO,
+	DSO_BINARY_TYPE__UBUNTU_DEBUGINFO,
+	DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO,
+	DSO_BINARY_TYPE__BUILDID_DEBUGINFO,
+	DSO_BINARY_TYPE__NOT_FOUND,
 };
 
-static int __die_search_func_cb(Dwarf_Die *fn_die, void *data)
+struct debuginfo *debuginfo__new(const char *path)
 {
-	struct __addr_die_search_param *ad = data;
-
-	if (dwarf_tag(fn_die) == DW_TAG_subprogram &&
-	    dwarf_haspc(fn_die, ad->addr)) {
-		memcpy(ad->die_mem, fn_die, sizeof(Dwarf_Die));
-		return DWARF_CB_ABORT;
+	enum dso_binary_type *type;
+	char buf[PATH_MAX], nil = '\0';
+	struct dso *dso;
+	struct debuginfo *dinfo = NULL;
+
+	/* Try to open distro debuginfo files */
+	dso = dso__new(path);
+	if (!dso)
+		goto out;
+
+	for (type = distro_dwarf_types;
+	     !dinfo && *type != DSO_BINARY_TYPE__NOT_FOUND;
+	     type++) {
+		if (dso__read_binary_type_filename(dso, *type, &nil,
+						   buf, PATH_MAX) < 0)
+			continue;
+		dinfo = __debuginfo__new(buf);
 	}
-	return DWARF_CB_OK;
-}
-
-/* Search a real subprogram including this line, */
-static Dwarf_Die *die_find_real_subprogram(Dwarf_Die *cu_die, Dwarf_Addr addr,
-					   Dwarf_Die *die_mem)
-{
-	struct __addr_die_search_param ad;
-	ad.addr = addr;
-	ad.die_mem = die_mem;
-	/* dwarf_getscopes can't find subprogram. */
-	if (!dwarf_getfuncs(cu_die, __die_search_func_cb, &ad, 0))
-		return NULL;
-	else
-		return die_mem;
-}
-
-/* die_find callback for inline function search */
-static int __die_find_inline_cb(Dwarf_Die *die_mem, void *data)
-{
-	Dwarf_Addr *addr = data;
-
-	if (dwarf_tag(die_mem) == DW_TAG_inlined_subroutine &&
-	    dwarf_haspc(die_mem, *addr))
-		return DIE_FIND_CB_FOUND;
-
-	return DIE_FIND_CB_CONTINUE;
-}
-
-/* Similar to dwarf_getfuncs, but returns inlined_subroutine if exists. */
-static Dwarf_Die *die_find_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
-				      Dwarf_Die *die_mem)
-{
-	return die_find_child(sp_die, __die_find_inline_cb, &addr, die_mem);
-}
-
-static int __die_find_variable_cb(Dwarf_Die *die_mem, void *data)
-{
-	const char *name = data;
-	int tag;
+	dso__delete(dso);
 
-	tag = dwarf_tag(die_mem);
-	if ((tag == DW_TAG_formal_parameter ||
-	     tag == DW_TAG_variable) &&
-	    (die_compare_name(die_mem, name) == 0))
-		return DIE_FIND_CB_FOUND;
-
-	return DIE_FIND_CB_CONTINUE;
+out:
+	/* if failed to open all distro debuginfo, open given binary */
+	return dinfo ? : __debuginfo__new(path);
 }
 
-/* Find a variable called 'name' */
-static Dwarf_Die *die_find_variable(Dwarf_Die *sp_die, const char *name,
-				    Dwarf_Die *die_mem)
+void debuginfo__delete(struct debuginfo *dbg)
 {
-	return die_find_child(sp_die, __die_find_variable_cb, (void *)name,
-			      die_mem);
+	if (dbg) {
+		if (dbg->dwfl)
+			dwfl_end(dbg->dwfl);
+		free(dbg);
+	}
 }
 
-static int __die_find_member_cb(Dwarf_Die *die_mem, void *data)
-{
-	const char *name = data;
-
-	if ((dwarf_tag(die_mem) == DW_TAG_member) &&
-	    (die_compare_name(die_mem, name) == 0))
-		return DIE_FIND_CB_FOUND;
-
-	return DIE_FIND_CB_SIBLING;
-}
+/*
+ * Probe finder related functions
+ */
 
-/* Find a member called 'name' */
-static Dwarf_Die *die_find_member(Dwarf_Die *st_die, const char *name,
-				  Dwarf_Die *die_mem)
+static struct probe_trace_arg_ref *alloc_trace_arg_ref(long offs)
 {
-	return die_find_child(st_die, __die_find_member_cb, (void *)name,
-			      die_mem);
+	struct probe_trace_arg_ref *ref;
+	ref = zalloc(sizeof(struct probe_trace_arg_ref));
+	if (ref != NULL)
+		ref->offset = offs;
+	return ref;
 }
 
 /*
- * Probe finder related functions
+ * Convert a location into trace_arg.
+ * If tvar == NULL, this just checks variable can be converted.
+ * If fentry == true and vr_die is a parameter, do huristic search
+ * for the location fuzzed by function entry mcount.
  */
-
-/* Show a location */
-static int convert_location(Dwarf_Op *op, struct probe_finder *pf)
+static int convert_variable_location(Dwarf_Die *vr_die, Dwarf_Addr addr,
+				     Dwarf_Op *fb_ops, Dwarf_Die *sp_die,
+				     struct probe_trace_arg *tvar)
 {
+	Dwarf_Attribute attr;
+	Dwarf_Addr tmp = 0;
+	Dwarf_Op *op;
+	size_t nops;
 	unsigned int regn;
 	Dwarf_Word offs = 0;
 	bool ref = false;
 	const char *regs;
-	struct kprobe_trace_arg *tvar = pf->tvar;
+	int ret;
+
+	if (dwarf_attr(vr_die, DW_AT_external, &attr) != NULL)
+		goto static_var;
+
+	/* TODO: handle more than 1 exprs */
+	if (dwarf_attr(vr_die, DW_AT_location, &attr) == NULL)
+		return -EINVAL;	/* Broken DIE ? */
+	if (dwarf_getlocation_addr(&attr, addr, &op, &nops, 1) <= 0) {
+		ret = dwarf_entrypc(sp_die, &tmp);
+		if (ret || addr != tmp ||
+		    dwarf_tag(vr_die) != DW_TAG_formal_parameter ||
+		    dwarf_highpc(sp_die, &tmp))
+			return -ENOENT;
+		/*
+		 * This is fuzzed by fentry mcount. We try to find the
+		 * parameter location at the earliest address.
+		 */
+		for (addr += 1; addr <= tmp; addr++) {
+			if (dwarf_getlocation_addr(&attr, addr, &op,
+						   &nops, 1) > 0)
+				goto found;
+		}
+		return -ENOENT;
+	}
+found:
+	if (nops == 0)
+		/* TODO: Support const_value */
+		return -ENOENT;
+
+	if (op->atom == DW_OP_addr) {
+static_var:
+		if (!tvar)
+			return 0;
+		/* Static variables on memory (not stack), make @varname */
+		ret = strlen(dwarf_diename(vr_die));
+		tvar->value = zalloc(ret + 2);
+		if (tvar->value == NULL)
+			return -ENOMEM;
+		snprintf(tvar->value, ret + 2, "@%s", dwarf_diename(vr_die));
+		tvar->ref = alloc_trace_arg_ref((long)offs);
+		if (tvar->ref == NULL)
+			return -ENOMEM;
+		return 0;
+	}
 
 	/* If this is based on frame buffer, set the offset */
 	if (op->atom == DW_OP_fbreg) {
-		if (pf->fb_ops == NULL) {
-			pr_warning("The attribute of frame base is not "
-				   "supported.\n");
+		if (fb_ops == NULL)
 			return -ENOTSUP;
-		}
 		ref = true;
 		offs = op->number;
-		op = &pf->fb_ops[0];
+		op = &fb_ops[0];
 	}
 
 	if (op->atom >= DW_OP_breg0 && op->atom <= DW_OP_breg31) {
@@ -390,13 +246,18 @@ static int convert_location(Dwarf_Op *op, struct probe_finder *pf)
 	} else if (op->atom == DW_OP_regx) {
 		regn = op->number;
 	} else {
-		pr_warning("DW_OP %x is not supported.\n", op->atom);
+		pr_debug("DW_OP %x is not supported.\n", op->atom);
 		return -ENOTSUP;
 	}
 
+	if (!tvar)
+		return 0;
+
 	regs = get_arch_regstr(regn);
 	if (!regs) {
-		pr_warning("Mapping for DWARF register number %u missing on this architecture.", regn);
+		/* This should be a bug in DWARF or this tool */
+		pr_warning("Mapping for the register number %u "
+			   "missing on this architecture.\n", regn);
 		return -ERANGE;
 	}
 
@@ -405,71 +266,163 @@ static int convert_location(Dwarf_Op *op, struct probe_finder *pf)
 		return -ENOMEM;
 
 	if (ref) {
-		tvar->ref = zalloc(sizeof(struct kprobe_trace_arg_ref));
+		tvar->ref = alloc_trace_arg_ref((long)offs);
 		if (tvar->ref == NULL)
 			return -ENOMEM;
-		tvar->ref->offset = (long)offs;
 	}
 	return 0;
 }
 
+#define BYTES_TO_BITS(nb)	((nb) * BITS_PER_LONG / sizeof(long))
+
 static int convert_variable_type(Dwarf_Die *vr_die,
-				 struct kprobe_trace_arg *targ)
+				 struct probe_trace_arg *tvar,
+				 const char *cast)
 {
+	struct probe_trace_arg_ref **ref_ptr = &tvar->ref;
 	Dwarf_Die type;
 	char buf[16];
+	int bsize, boffs, total;
 	int ret;
 
+	/* TODO: check all types */
+	if (cast && strcmp(cast, "string") != 0) {
+		/* Non string type is OK */
+		tvar->type = strdup(cast);
+		return (tvar->type == NULL) ? -ENOMEM : 0;
+	}
+
+	bsize = dwarf_bitsize(vr_die);
+	if (bsize > 0) {
+		/* This is a bitfield */
+		boffs = dwarf_bitoffset(vr_die);
+		total = dwarf_bytesize(vr_die);
+		if (boffs < 0 || total < 0)
+			return -ENOENT;
+		ret = snprintf(buf, 16, "b%d@%d/%zd", bsize, boffs,
+				BYTES_TO_BITS(total));
+		goto formatted;
+	}
+
 	if (die_get_real_type(vr_die, &type) == NULL) {
 		pr_warning("Failed to get a type information of %s.\n",
 			   dwarf_diename(vr_die));
 		return -ENOENT;
 	}
 
-	ret = die_get_byte_size(&type) * 8;
-	if (ret) {
-		/* Check the bitwidth */
-		if (ret > MAX_BASIC_TYPE_BITS) {
-			pr_info("%s exceeds max-bitwidth."
-				" Cut down to %d bits.\n",
-				dwarf_diename(&type), MAX_BASIC_TYPE_BITS);
-			ret = MAX_BASIC_TYPE_BITS;
-		}
+	pr_debug("%s type is %s.\n",
+		 dwarf_diename(vr_die), dwarf_diename(&type));
 
-		ret = snprintf(buf, 16, "%c%d",
-			       die_is_signed_type(&type) ? 's' : 'u', ret);
-		if (ret < 0 || ret >= 16) {
-			if (ret >= 16)
-				ret = -E2BIG;
-			pr_warning("Failed to convert variable type: %s\n",
-				   strerror(-ret));
-			return ret;
+	if (cast && strcmp(cast, "string") == 0) {	/* String type */
+		ret = dwarf_tag(&type);
+		if (ret != DW_TAG_pointer_type &&
+		    ret != DW_TAG_array_type) {
+			pr_warning("Failed to cast into string: "
+				   "%s(%s) is not a pointer nor array.\n",
+				   dwarf_diename(vr_die), dwarf_diename(&type));
+			return -EINVAL;
 		}
-		targ->type = strdup(buf);
-		if (targ->type == NULL)
-			return -ENOMEM;
+		if (die_get_real_type(&type, &type) == NULL) {
+			pr_warning("Failed to get a type"
+				   " information.\n");
+			return -ENOENT;
+		}
+		if (ret == DW_TAG_pointer_type) {
+			while (*ref_ptr)
+				ref_ptr = &(*ref_ptr)->next;
+			/* Add new reference with offset +0 */
+			*ref_ptr = zalloc(sizeof(struct probe_trace_arg_ref));
+			if (*ref_ptr == NULL) {
+				pr_warning("Out of memory error\n");
+				return -ENOMEM;
+			}
+		}
+		if (!die_compare_name(&type, "char") &&
+		    !die_compare_name(&type, "unsigned char")) {
+			pr_warning("Failed to cast into string: "
+				   "%s is not (unsigned) char *.\n",
+				   dwarf_diename(vr_die));
+			return -EINVAL;
+		}
+		tvar->type = strdup(cast);
+		return (tvar->type == NULL) ? -ENOMEM : 0;
+	}
+
+	ret = dwarf_bytesize(&type);
+	if (ret <= 0)
+		/* No size ... try to use default type */
+		return 0;
+	ret = BYTES_TO_BITS(ret);
+
+	/* Check the bitwidth */
+	if (ret > MAX_BASIC_TYPE_BITS) {
+		pr_info("%s exceeds max-bitwidth. Cut down to %d bits.\n",
+			dwarf_diename(&type), MAX_BASIC_TYPE_BITS);
+		ret = MAX_BASIC_TYPE_BITS;
 	}
+	ret = snprintf(buf, 16, "%c%d",
+		       die_is_signed_type(&type) ? 's' : 'u', ret);
+
+formatted:
+	if (ret < 0 || ret >= 16) {
+		if (ret >= 16)
+			ret = -E2BIG;
+		pr_warning("Failed to convert variable type: %s\n",
+			   strerror(-ret));
+		return ret;
+	}
+	tvar->type = strdup(buf);
+	if (tvar->type == NULL)
+		return -ENOMEM;
 	return 0;
 }
 
 static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname,
 				    struct perf_probe_arg_field *field,
-				    struct kprobe_trace_arg_ref **ref_ptr,
+				    struct probe_trace_arg_ref **ref_ptr,
 				    Dwarf_Die *die_mem)
 {
-	struct kprobe_trace_arg_ref *ref = *ref_ptr;
+	struct probe_trace_arg_ref *ref = *ref_ptr;
 	Dwarf_Die type;
 	Dwarf_Word offs;
-	int ret;
+	int ret, tag;
 
 	pr_debug("converting %s in %s\n", field->name, varname);
 	if (die_get_real_type(vr_die, &type) == NULL) {
 		pr_warning("Failed to get the type of %s.\n", varname);
 		return -ENOENT;
 	}
-
-	/* Check the pointer and dereference */
-	if (dwarf_tag(&type) == DW_TAG_pointer_type) {
+	pr_debug2("Var real type: (%x)\n", (unsigned)dwarf_dieoffset(&type));
+	tag = dwarf_tag(&type);
+
+	if (field->name[0] == '[' &&
+	    (tag == DW_TAG_array_type || tag == DW_TAG_pointer_type)) {
+		if (field->next)
+			/* Save original type for next field */
+			memcpy(die_mem, &type, sizeof(*die_mem));
+		/* Get the type of this array */
+		if (die_get_real_type(&type, &type) == NULL) {
+			pr_warning("Failed to get the type of %s.\n", varname);
+			return -ENOENT;
+		}
+		pr_debug2("Array real type: (%x)\n",
+			 (unsigned)dwarf_dieoffset(&type));
+		if (tag == DW_TAG_pointer_type) {
+			ref = zalloc(sizeof(struct probe_trace_arg_ref));
+			if (ref == NULL)
+				return -ENOMEM;
+			if (*ref_ptr)
+				(*ref_ptr)->next = ref;
+			else
+				*ref_ptr = ref;
+		}
+		ref->offset += dwarf_bytesize(&type) * field->index;
+		if (!field->next)
+			/* Save vr_die for converting types */
+			memcpy(die_mem, vr_die, sizeof(*die_mem));
+		goto next;
+	} else if (tag == DW_TAG_pointer_type) {
+		/* Check the pointer and dereference */
 		if (!field->ref) {
 			pr_err("Semantic error: %s must be referred by '->'\n",
 			       field->name);
@@ -481,12 +434,14 @@ static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname,
 			return -ENOENT;
 		}
 		/* Verify it is a data structure  */
-		if (dwarf_tag(&type) != DW_TAG_structure_type) {
-			pr_warning("%s is not a data structure.\n", varname);
+		tag = dwarf_tag(&type);
+		if (tag != DW_TAG_structure_type && tag != DW_TAG_union_type) {
+			pr_warning("%s is not a data structure nor an union.\n",
+				   varname);
 			return -EINVAL;
 		}
 
-		ref = zalloc(sizeof(struct kprobe_trace_arg_ref));
+		ref = zalloc(sizeof(struct probe_trace_arg_ref));
 		if (ref == NULL)
 			return -ENOMEM;
 		if (*ref_ptr)
@@ -495,8 +450,14 @@ static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname,
 			*ref_ptr = ref;
 	} else {
 		/* Verify it is a data structure  */
-		if (dwarf_tag(&type) != DW_TAG_structure_type) {
-			pr_warning("%s is not a data structure.\n", varname);
+		if (tag != DW_TAG_structure_type && tag != DW_TAG_union_type) {
+			pr_warning("%s is not a data structure nor an union.\n",
+				   varname);
+			return -EINVAL;
+		}
+		if (field->name[0] == '[') {
+			pr_err("Semantic error: %s is not a pointor"
+			       " nor array.\n", varname);
 			return -EINVAL;
 		}
 		if (field->ref) {
@@ -512,19 +473,25 @@ static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname,
 	}
 
 	if (die_find_member(&type, field->name, die_mem) == NULL) {
-		pr_warning("%s(tyep:%s) has no member %s.\n", varname,
+		pr_warning("%s(type:%s) has no member %s.\n", varname,
 			   dwarf_diename(&type), field->name);
 		return -EINVAL;
 	}
 
 	/* Get the offset of the field */
-	ret = die_get_data_member_location(die_mem, &offs);
-	if (ret < 0) {
-		pr_warning("Failed to get the offset of %s.\n", field->name);
-		return ret;
+	if (tag == DW_TAG_union_type) {
+		offs = 0;
+	} else {
+		ret = die_get_data_member_location(die_mem, &offs);
+		if (ret < 0) {
+			pr_warning("Failed to get the offset of %s.\n",
+				   field->name);
+			return ret;
+		}
 	}
 	ref->offset += (long)offs;
 
+next:
 	/* Converting next field */
 	if (field->next)
 		return convert_variable_fields(die_mem, field->name,
@@ -536,51 +503,57 @@ static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname,
 /* Show a variables in kprobe event format */
 static int convert_variable(Dwarf_Die *vr_die, struct probe_finder *pf)
 {
-	Dwarf_Attribute attr;
 	Dwarf_Die die_mem;
-	Dwarf_Op *expr;
-	size_t nexpr;
 	int ret;
 
-	if (dwarf_attr(vr_die, DW_AT_location, &attr) == NULL)
-		goto error;
-	/* TODO: handle more than 1 exprs */
-	ret = dwarf_getlocation_addr(&attr, pf->addr, &expr, &nexpr, 1);
-	if (ret <= 0 || nexpr == 0)
-		goto error;
-
-	ret = convert_location(expr, pf);
-	if (ret == 0 && pf->pvar->field) {
+	pr_debug("Converting variable %s into trace event.\n",
+		 dwarf_diename(vr_die));
+
+	ret = convert_variable_location(vr_die, pf->addr, pf->fb_ops,
+					&pf->sp_die, pf->tvar);
+	if (ret == -ENOENT || ret == -EINVAL)
+		pr_err("Failed to find the location of %s at this address.\n"
+		       " Perhaps, it has been optimized out.\n", pf->pvar->var);
+	else if (ret == -ENOTSUP)
+		pr_err("Sorry, we don't support this variable location yet.\n");
+	else if (ret == 0 && pf->pvar->field) {
 		ret = convert_variable_fields(vr_die, pf->pvar->var,
 					      pf->pvar->field, &pf->tvar->ref,
 					      &die_mem);
 		vr_die = &die_mem;
 	}
-	if (ret == 0) {
-		if (pf->pvar->type) {
-			pf->tvar->type = strdup(pf->pvar->type);
-			if (pf->tvar->type == NULL)
-				ret = -ENOMEM;
-		} else
-			ret = convert_variable_type(vr_die, pf->tvar);
-	}
+	if (ret == 0)
+		ret = convert_variable_type(vr_die, pf->tvar, pf->pvar->type);
 	/* *expr will be cached in libdw. Don't free it. */
 	return ret;
-error:
-	/* TODO: Support const_value */
-	pr_err("Failed to find the location of %s at this address.\n"
-	       " Perhaps, it has been optimized out.\n", pf->pvar->var);
-	return -ENOENT;
 }
 
-/* Find a variable in a subprogram die */
-static int find_variable(Dwarf_Die *sp_die, struct probe_finder *pf)
+/* Find a variable in a scope DIE */
+static int find_variable(Dwarf_Die *sc_die, struct probe_finder *pf)
 {
 	Dwarf_Die vr_die;
 	char buf[32], *ptr;
-	int ret;
+	int ret = 0;
+
+	if (!is_c_varname(pf->pvar->var)) {
+		/* Copy raw parameters */
+		pf->tvar->value = strdup(pf->pvar->var);
+		if (pf->tvar->value == NULL)
+			return -ENOMEM;
+		if (pf->pvar->type) {
+			pf->tvar->type = strdup(pf->pvar->type);
+			if (pf->tvar->type == NULL)
+				return -ENOMEM;
+		}
+		if (pf->pvar->name) {
+			pf->tvar->name = strdup(pf->pvar->name);
+			if (pf->tvar->name == NULL)
+				return -ENOMEM;
+		} else
+			pf->tvar->name = NULL;
+		return 0;
+	}
 
-	/* TODO: Support arrays */
 	if (pf->pvar->name)
 		pf->tvar->name = strdup(pf->pvar->name);
 	else {
@@ -595,76 +568,97 @@ static int find_variable(Dwarf_Die *sp_die, struct probe_finder *pf)
 	if (pf->tvar->name == NULL)
 		return -ENOMEM;
 
-	if (!is_c_varname(pf->pvar->var)) {
-		/* Copy raw parameters */
-		pf->tvar->value = strdup(pf->pvar->var);
-		if (pf->tvar->value == NULL)
-			return -ENOMEM;
-		else
-			return 0;
+	pr_debug("Searching '%s' variable in context.\n", pf->pvar->var);
+	/* Search child die for local variables and parameters. */
+	if (!die_find_variable_at(sc_die, pf->pvar->var, pf->addr, &vr_die)) {
+		/* Search again in global variables */
+		if (!die_find_variable_at(&pf->cu_die, pf->pvar->var, 0, &vr_die))
+			pr_warning("Failed to find '%s' in this function.\n",
+				   pf->pvar->var);
+			ret = -ENOENT;
 	}
+	if (ret >= 0)
+		ret = convert_variable(&vr_die, pf);
 
-	pr_debug("Searching '%s' variable in context.\n",
-		 pf->pvar->var);
-	/* Search child die for local variables and parameters. */
-	if (!die_find_variable(sp_die, pf->pvar->var, &vr_die)) {
-		pr_warning("Failed to find '%s' in this function.\n",
-			   pf->pvar->var);
+	return ret;
+}
+
+/* Convert subprogram DIE to trace point */
+static int convert_to_trace_point(Dwarf_Die *sp_die, Dwfl_Module *mod,
+				  Dwarf_Addr paddr, bool retprobe,
+				  struct probe_trace_point *tp)
+{
+	Dwarf_Addr eaddr, highaddr;
+	GElf_Sym sym;
+	const char *symbol;
+
+	/* Verify the address is correct */
+	if (dwarf_entrypc(sp_die, &eaddr) != 0) {
+		pr_warning("Failed to get entry address of %s\n",
+			   dwarf_diename(sp_die));
 		return -ENOENT;
 	}
-	return convert_variable(&vr_die, pf);
+	if (dwarf_highpc(sp_die, &highaddr) != 0) {
+		pr_warning("Failed to get end address of %s\n",
+			   dwarf_diename(sp_die));
+		return -ENOENT;
+	}
+	if (paddr > highaddr) {
+		pr_warning("Offset specified is greater than size of %s\n",
+			   dwarf_diename(sp_die));
+		return -EINVAL;
+	}
+
+	/* Get an appropriate symbol from symtab */
+	symbol = dwfl_module_addrsym(mod, paddr, &sym, NULL);
+	if (!symbol) {
+		pr_warning("Failed to find symbol at 0x%lx\n",
+			   (unsigned long)paddr);
+		return -ENOENT;
+	}
+	tp->offset = (unsigned long)(paddr - sym.st_value);
+	tp->address = (unsigned long)paddr;
+	tp->symbol = strdup(symbol);
+	if (!tp->symbol)
+		return -ENOMEM;
+
+	/* Return probe must be on the head of a subprogram */
+	if (retprobe) {
+		if (eaddr != paddr) {
+			pr_warning("Return probe must be on the head of"
+				   " a real function.\n");
+			return -EINVAL;
+		}
+		tp->retprobe = true;
+	}
+
+	return 0;
 }
 
-/* Show a probe point to output buffer */
-static int convert_probe_point(Dwarf_Die *sp_die, struct probe_finder *pf)
+/* Call probe_finder callback with scope DIE */
+static int call_probe_finder(Dwarf_Die *sc_die, struct probe_finder *pf)
 {
-	struct kprobe_trace_event *tev;
-	Dwarf_Addr eaddr;
-	Dwarf_Die die_mem;
-	const char *name;
-	int ret, i;
 	Dwarf_Attribute fb_attr;
 	size_t nops;
+	int ret;
 
-	if (pf->ntevs == pf->max_tevs) {
-		pr_warning("Too many( > %d) probe point found.\n",
-			   pf->max_tevs);
-		return -ERANGE;
+	if (!sc_die) {
+		pr_err("Caller must pass a scope DIE. Program error.\n");
+		return -EINVAL;
 	}
-	tev = &pf->tevs[pf->ntevs++];
 
-	/* If no real subprogram, find a real one */
-	if (!sp_die || dwarf_tag(sp_die) != DW_TAG_subprogram) {
-		sp_die = die_find_real_subprogram(&pf->cu_die,
-						 pf->addr, &die_mem);
-		if (!sp_die) {
+	/* If not a real subprogram, find a real one */
+	if (!die_is_func_def(sc_die)) {
+		if (!die_find_realfunc(&pf->cu_die, pf->addr, &pf->sp_die)) {
 			pr_warning("Failed to find probe point in any "
 				   "functions.\n");
 			return -ENOENT;
 		}
-	}
-
-	/* Copy the name of probe point */
-	name = dwarf_diename(sp_die);
-	if (name) {
-		if (dwarf_entrypc(sp_die, &eaddr) != 0) {
-			pr_warning("Failed to get entry pc of %s\n",
-				   dwarf_diename(sp_die));
-			return -ENOENT;
-		}
-		tev->point.symbol = strdup(name);
-		if (tev->point.symbol == NULL)
-			return -ENOMEM;
-		tev->point.offset = (unsigned long)(pf->addr - eaddr);
 	} else
-		/* This function has no name. */
-		tev->point.offset = (unsigned long)pf->addr;
+		memcpy(&pf->sp_die, sc_die, sizeof(Dwarf_Die));
 
-	pr_debug("Probe point found: %s+%lu\n", tev->point.symbol,
-		 tev->point.offset);
-
-	/* Get the frame base attribute/ops */
-	dwarf_attr(sp_die, DW_AT_frame_base, &fb_attr);
+	/* Get the frame base attribute/ops from subprogram */
+	dwarf_attr(&pf->sp_die, DW_AT_frame_base, &fb_attr);
 	ret = dwarf_getlocation_addr(&fb_attr, pf->addr, &pf->fb_ops, &nops, 1);
 	if (ret <= 0 || nops == 0) {
 		pf->fb_ops = NULL;
@@ -674,220 +668,226 @@ static int convert_probe_point(Dwarf_Die *sp_die, struct probe_finder *pf)
 		Dwarf_Frame *frame;
 		if (dwarf_cfi_addrframe(pf->cfi, pf->addr, &frame) != 0 ||
 		    dwarf_frame_cfa(frame, &pf->fb_ops, &nops) != 0) {
-			pr_warning("Failed to get CFA on 0x%jx\n",
+			pr_warning("Failed to get call frame on 0x%jx\n",
 				   (uintmax_t)pf->addr);
 			return -ENOENT;
 		}
 #endif
 	}
 
-	/* Find each argument */
-	tev->nargs = pf->pev->nargs;
-	tev->args = zalloc(sizeof(struct kprobe_trace_arg) * tev->nargs);
-	if (tev->args == NULL)
-		return -ENOMEM;
-	for (i = 0; i < pf->pev->nargs; i++) {
-		pf->pvar = &pf->pev->args[i];
-		pf->tvar = &tev->args[i];
-		ret = find_variable(sp_die, pf);
-		if (ret != 0)
-			return ret;
-	}
+	/* Call finder's callback handler */
+	ret = pf->callback(sc_die, pf);
 
 	/* *pf->fb_ops will be cached in libdw. Don't free it. */
 	pf->fb_ops = NULL;
+
+	return ret;
+}
+
+struct find_scope_param {
+	const char *function;
+	const char *file;
+	int line;
+	int diff;
+	Dwarf_Die *die_mem;
+	bool found;
+};
+
+static int find_best_scope_cb(Dwarf_Die *fn_die, void *data)
+{
+	struct find_scope_param *fsp = data;
+	const char *file;
+	int lno;
+
+	/* Skip if declared file name does not match */
+	if (fsp->file) {
+		file = dwarf_decl_file(fn_die);
+		if (!file || strcmp(fsp->file, file) != 0)
+			return 0;
+	}
+	/* If the function name is given, that's what user expects */
+	if (fsp->function) {
+		if (die_compare_name(fn_die, fsp->function)) {
+			memcpy(fsp->die_mem, fn_die, sizeof(Dwarf_Die));
+			fsp->found = true;
+			return 1;
+		}
+	} else {
+		/* With the line number, find the nearest declared DIE */
+		dwarf_decl_line(fn_die, &lno);
+		if (lno < fsp->line && fsp->diff > fsp->line - lno) {
+			/* Keep a candidate and continue */
+			fsp->diff = fsp->line - lno;
+			memcpy(fsp->die_mem, fn_die, sizeof(Dwarf_Die));
+			fsp->found = true;
+		}
+	}
 	return 0;
 }
 
-/* Find probe point from its line number */
-static int find_probe_point_by_line(struct probe_finder *pf)
+/* Find an appropriate scope fits to given conditions */
+static Dwarf_Die *find_best_scope(struct probe_finder *pf, Dwarf_Die *die_mem)
 {
-	Dwarf_Lines *lines;
-	Dwarf_Line *line;
-	size_t nlines, i;
-	Dwarf_Addr addr;
-	int lineno;
-	int ret = 0;
+	struct find_scope_param fsp = {
+		.function = pf->pev->point.function,
+		.file = pf->fname,
+		.line = pf->lno,
+		.diff = INT_MAX,
+		.die_mem = die_mem,
+		.found = false,
+	};
+
+	cu_walk_functions_at(&pf->cu_die, pf->addr, find_best_scope_cb, &fsp);
+
+	return fsp.found ? die_mem : NULL;
+}
+
+static int probe_point_line_walker(const char *fname, int lineno,
+				   Dwarf_Addr addr, void *data)
+{
+	struct probe_finder *pf = data;
+	Dwarf_Die *sc_die, die_mem;
+	int ret;
 
-	if (dwarf_getsrclines(&pf->cu_die, &lines, &nlines) != 0) {
-		pr_warning("No source lines found in this CU.\n");
+	if (lineno != pf->lno || strtailcmp(fname, pf->fname) != 0)
+		return 0;
+
+	pf->addr = addr;
+	sc_die = find_best_scope(pf, &die_mem);
+	if (!sc_die) {
+		pr_warning("Failed to find scope of probe point.\n");
 		return -ENOENT;
 	}
 
-	for (i = 0; i < nlines && ret == 0; i++) {
-		line = dwarf_onesrcline(lines, i);
-		if (dwarf_lineno(line, &lineno) != 0 ||
-		    lineno != pf->lno)
-			continue;
-
-		/* TODO: Get fileno from line, but how? */
-		if (strtailcmp(dwarf_linesrc(line, NULL, NULL), pf->fname) != 0)
-			continue;
+	ret = call_probe_finder(sc_die, pf);
 
-		if (dwarf_lineaddr(line, &addr) != 0) {
-			pr_warning("Failed to get the address of the line.\n");
-			return -ENOENT;
-		}
-		pr_debug("Probe line found: line[%d]:%d addr:0x%jx\n",
-			 (int)i, lineno, (uintmax_t)addr);
-		pf->addr = addr;
+	/* Continue if no error, because the line will be in inline function */
+	return ret < 0 ? ret : 0;
+}
 
-		ret = convert_probe_point(NULL, pf);
-		/* Continuing, because target line might be inlined. */
-	}
-	return ret;
+/* Find probe point from its line number */
+static int find_probe_point_by_line(struct probe_finder *pf)
+{
+	return die_walk_lines(&pf->cu_die, probe_point_line_walker, pf);
 }
 
 /* Find lines which match lazy pattern */
-static int find_lazy_match_lines(struct list_head *head,
+static int find_lazy_match_lines(struct intlist *list,
 				 const char *fname, const char *pat)
 {
-	char *fbuf, *p1, *p2;
-	int fd, line, nlines = -1;
-	struct stat st;
-
-	fd = open(fname, O_RDONLY);
-	if (fd < 0) {
-		pr_warning("Failed to open %s: %s\n", fname, strerror(-fd));
+	FILE *fp;
+	char *line = NULL;
+	size_t line_len;
+	ssize_t len;
+	int count = 0, linenum = 1;
+
+	fp = fopen(fname, "r");
+	if (!fp) {
+		pr_warning("Failed to open %s: %s\n", fname, strerror(errno));
 		return -errno;
 	}
 
-	if (fstat(fd, &st) < 0) {
-		pr_warning("Failed to get the size of %s: %s\n",
-			   fname, strerror(errno));
-		nlines = -errno;
-		goto out_close;
-	}
+	while ((len = getline(&line, &line_len, fp)) > 0) {
 
-	nlines = -ENOMEM;
-	fbuf = malloc(st.st_size + 2);
-	if (fbuf == NULL)
-		goto out_close;
-	if (read(fd, fbuf, st.st_size) < 0) {
-		pr_warning("Failed to read %s: %s\n", fname, strerror(errno));
-		nlines = -errno;
-		goto out_free_fbuf;
-	}
-	fbuf[st.st_size] = '\n';	/* Dummy line */
-	fbuf[st.st_size + 1] = '\0';
-	p1 = fbuf;
-	line = 1;
-	nlines = 0;
-	while ((p2 = strchr(p1, '\n')) != NULL) {
-		*p2 = '\0';
-		if (strlazymatch(p1, pat)) {
-			line_list__add_line(head, line);
-			nlines++;
+		if (line[len - 1] == '\n')
+			line[len - 1] = '\0';
+
+		if (strlazymatch(line, pat)) {
+			intlist__add(list, linenum);
+			count++;
 		}
-		line++;
-		p1 = p2 + 1;
+		linenum++;
 	}
-out_free_fbuf:
-	free(fbuf);
-out_close:
-	close(fd);
-	return nlines;
+
+	if (ferror(fp))
+		count = -errno;
+	free(line);
+	fclose(fp);
+
+	if (count == 0)
+		pr_debug("No matched lines found in %s.\n", fname);
+	return count;
 }
 
-/* Find probe points from lazy pattern  */
-static int find_probe_point_lazy(Dwarf_Die *sp_die, struct probe_finder *pf)
+static int probe_point_lazy_walker(const char *fname, int lineno,
+				   Dwarf_Addr addr, void *data)
 {
-	Dwarf_Lines *lines;
-	Dwarf_Line *line;
-	size_t nlines, i;
-	Dwarf_Addr addr;
-	Dwarf_Die die_mem;
-	int lineno;
-	int ret = 0;
+	struct probe_finder *pf = data;
+	Dwarf_Die *sc_die, die_mem;
+	int ret;
 
-	if (list_empty(&pf->lcache)) {
-		/* Matching lazy line pattern */
-		ret = find_lazy_match_lines(&pf->lcache, pf->fname,
-					    pf->pev->point.lazy_line);
-		if (ret == 0) {
-			pr_debug("No matched lines found in %s.\n", pf->fname);
-			return 0;
-		} else if (ret < 0)
-			return ret;
-	}
+	if (!intlist__has_entry(pf->lcache, lineno) ||
+	    strtailcmp(fname, pf->fname) != 0)
+		return 0;
 
-	if (dwarf_getsrclines(&pf->cu_die, &lines, &nlines) != 0) {
-		pr_warning("No source lines found in this CU.\n");
+	pr_debug("Probe line found: line:%d addr:0x%llx\n",
+		 lineno, (unsigned long long)addr);
+	pf->addr = addr;
+	pf->lno = lineno;
+	sc_die = find_best_scope(pf, &die_mem);
+	if (!sc_die) {
+		pr_warning("Failed to find scope of probe point.\n");
 		return -ENOENT;
 	}
 
-	for (i = 0; i < nlines && ret >= 0; i++) {
-		line = dwarf_onesrcline(lines, i);
-
-		if (dwarf_lineno(line, &lineno) != 0 ||
-		    !line_list__has_line(&pf->lcache, lineno))
-			continue;
-
-		/* TODO: Get fileno from line, but how? */
-		if (strtailcmp(dwarf_linesrc(line, NULL, NULL), pf->fname) != 0)
-			continue;
+	ret = call_probe_finder(sc_die, pf);
 
-		if (dwarf_lineaddr(line, &addr) != 0) {
-			pr_debug("Failed to get the address of line %d.\n",
-				 lineno);
-			continue;
-		}
-		if (sp_die) {
-			/* Address filtering 1: does sp_die include addr? */
-			if (!dwarf_haspc(sp_die, addr))
-				continue;
-			/* Address filtering 2: No child include addr? */
-			if (die_find_inlinefunc(sp_die, addr, &die_mem))
-				continue;
-		}
+	/*
+	 * Continue if no error, because the lazy pattern will match
+	 * to other lines
+	 */
+	return ret < 0 ? ret : 0;
+}
 
-		pr_debug("Probe line found: line[%d]:%d addr:0x%llx\n",
-			 (int)i, lineno, (unsigned long long)addr);
-		pf->addr = addr;
+/* Find probe points from lazy pattern  */
+static int find_probe_point_lazy(Dwarf_Die *sp_die, struct probe_finder *pf)
+{
+	int ret = 0;
 
-		ret = convert_probe_point(sp_die, pf);
-		/* Continuing, because target line might be inlined. */
+	if (intlist__empty(pf->lcache)) {
+		/* Matching lazy line pattern */
+		ret = find_lazy_match_lines(pf->lcache, pf->fname,
+					    pf->pev->point.lazy_line);
+		if (ret <= 0)
+			return ret;
 	}
-	/* TODO: deallocate lines, but how? */
-	return ret;
-}
 
-/* Callback parameter with return value */
-struct dwarf_callback_param {
-	void *data;
-	int retval;
-};
+	return die_walk_lines(sp_die, probe_point_lazy_walker, pf);
+}
 
 static int probe_point_inline_cb(Dwarf_Die *in_die, void *data)
 {
-	struct dwarf_callback_param *param = data;
-	struct probe_finder *pf = param->data;
+	struct probe_finder *pf = data;
 	struct perf_probe_point *pp = &pf->pev->point;
 	Dwarf_Addr addr;
+	int ret;
 
 	if (pp->lazy_line)
-		param->retval = find_probe_point_lazy(in_die, pf);
+		ret = find_probe_point_lazy(in_die, pf);
 	else {
 		/* Get probe address */
 		if (dwarf_entrypc(in_die, &addr) != 0) {
-			pr_warning("Failed to get entry pc of %s.\n",
+			pr_warning("Failed to get entry address of %s.\n",
 				   dwarf_diename(in_die));
-			param->retval = -ENOENT;
-			return DWARF_CB_ABORT;
+			return -ENOENT;
 		}
 		pf->addr = addr;
 		pf->addr += pp->offset;
 		pr_debug("found inline addr: 0x%jx\n",
 			 (uintmax_t)pf->addr);
 
-		param->retval = convert_probe_point(in_die, pf);
-		if (param->retval < 0)
-			return DWARF_CB_ABORT;
+		ret = call_probe_finder(in_die, pf);
 	}
 
-	return DWARF_CB_OK;
+	return ret;
 }
 
+/* Callback parameter with return value for libdw */
+struct dwarf_callback_param {
+	void *data;
+	int retval;
+};
+
 /* Search function from function name */
 static int probe_point_search_cb(Dwarf_Die *sp_die, void *data)
 {
@@ -896,8 +896,12 @@ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data)
 	struct perf_probe_point *pp = &pf->pev->point;
 
 	/* Check tag and diename */
-	if (dwarf_tag(sp_die) != DW_TAG_subprogram ||
-	    die_compare_name(sp_die, pp->function) != 0)
+	if (!die_is_func_def(sp_die) ||
+	    !die_compare_name(sp_die, pp->function))
+		return DWARF_CB_OK;
+
+	/* Check declared file */
+	if (pp->file && strtailcmp(pp->file, dwarf_decl_file(sp_die)))
 		return DWARF_CB_OK;
 
 	pf->fname = dwarf_decl_file(sp_die);
@@ -911,23 +915,19 @@ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data)
 			param->retval = find_probe_point_lazy(sp_die, pf);
 		else {
 			if (dwarf_entrypc(sp_die, &pf->addr) != 0) {
-				pr_warning("Failed to get entry pc of %s.\n",
-					   dwarf_diename(sp_die));
+				pr_warning("Failed to get entry address of "
+					   "%s.\n", dwarf_diename(sp_die));
 				param->retval = -ENOENT;
 				return DWARF_CB_ABORT;
 			}
 			pf->addr += pp->offset;
 			/* TODO: Check the address in this function */
-			param->retval = convert_probe_point(sp_die, pf);
+			param->retval = call_probe_finder(sp_die, pf);
 		}
-	} else {
-		struct dwarf_callback_param _param = {.data = (void *)pf,
-						      .retval = 0};
+	} else
 		/* Inlined function: search instances */
-		dwarf_func_inline_instances(sp_die, probe_point_inline_cb,
-					    &_param);
-		param->retval = _param.retval;
-	}
+		param->retval = die_walk_instances(sp_die,
+					probe_point_inline_cb, (void *)pf);
 
 	return DWARF_CB_ABORT; /* Exit; no same symbol in this CU. */
 }
@@ -940,155 +940,489 @@ static int find_probe_point_by_func(struct probe_finder *pf)
 	return _param.retval;
 }
 
-/* Find kprobe_trace_events specified by perf_probe_event from debuginfo */
-int find_kprobe_trace_events(int fd, struct perf_probe_event *pev,
-			     struct kprobe_trace_event **tevs, int max_tevs)
+struct pubname_callback_param {
+	char *function;
+	char *file;
+	Dwarf_Die *cu_die;
+	Dwarf_Die *sp_die;
+	int found;
+};
+
+static int pubname_search_cb(Dwarf *dbg, Dwarf_Global *gl, void *data)
 {
-	struct probe_finder pf = {.pev = pev, .max_tevs = max_tevs};
-	struct perf_probe_point *pp = &pev->point;
+	struct pubname_callback_param *param = data;
+
+	if (dwarf_offdie(dbg, gl->die_offset, param->sp_die)) {
+		if (dwarf_tag(param->sp_die) != DW_TAG_subprogram)
+			return DWARF_CB_OK;
+
+		if (die_compare_name(param->sp_die, param->function)) {
+			if (!dwarf_offdie(dbg, gl->cu_offset, param->cu_die))
+				return DWARF_CB_OK;
+
+			if (param->file &&
+			    strtailcmp(param->file, dwarf_decl_file(param->sp_die)))
+				return DWARF_CB_OK;
+
+			param->found = 1;
+			return DWARF_CB_ABORT;
+		}
+	}
+
+	return DWARF_CB_OK;
+}
+
+/* Find probe points from debuginfo */
+static int debuginfo__find_probes(struct debuginfo *dbg,
+				  struct probe_finder *pf)
+{
+	struct perf_probe_point *pp = &pf->pev->point;
 	Dwarf_Off off, noff;
 	size_t cuhl;
 	Dwarf_Die *diep;
-	Dwarf *dbg;
 	int ret = 0;
 
-	pf.tevs = zalloc(sizeof(struct kprobe_trace_event) * max_tevs);
-	if (pf.tevs == NULL)
-		return -ENOMEM;
-	*tevs = pf.tevs;
-	pf.ntevs = 0;
-
-	dbg = dwarf_begin(fd, DWARF_C_READ);
-	if (!dbg) {
-		pr_warning("No dwarf info found in the vmlinux - "
-			"please rebuild with CONFIG_DEBUG_INFO=y.\n");
-		free(pf.tevs);
-		*tevs = NULL;
-		return -EBADF;
-	}
-
 #if _ELFUTILS_PREREQ(0, 142)
 	/* Get the call frame information from this dwarf */
-	pf.cfi = dwarf_getcfi(dbg);
+	pf->cfi = dwarf_getcfi_elf(dwarf_getelf(dbg->dbg));
 #endif
 
 	off = 0;
-	line_list__init(&pf.lcache);
+	pf->lcache = intlist__new(NULL);
+	if (!pf->lcache)
+		return -ENOMEM;
+
+	/* Fastpath: lookup by function name from .debug_pubnames section */
+	if (pp->function) {
+		struct pubname_callback_param pubname_param = {
+			.function = pp->function,
+			.file	  = pp->file,
+			.cu_die	  = &pf->cu_die,
+			.sp_die	  = &pf->sp_die,
+			.found	  = 0,
+		};
+		struct dwarf_callback_param probe_param = {
+			.data = pf,
+		};
+
+		dwarf_getpubnames(dbg->dbg, pubname_search_cb,
+				  &pubname_param, 0);
+		if (pubname_param.found) {
+			ret = probe_point_search_cb(&pf->sp_die, &probe_param);
+			if (ret)
+				goto found;
+		}
+	}
+
 	/* Loop on CUs (Compilation Unit) */
-	while (!dwarf_nextcu(dbg, off, &noff, &cuhl, NULL, NULL, NULL) &&
-	       ret >= 0) {
+	while (!dwarf_nextcu(dbg->dbg, off, &noff, &cuhl, NULL, NULL, NULL)) {
 		/* Get the DIE(Debugging Information Entry) of this CU */
-		diep = dwarf_offdie(dbg, off + cuhl, &pf.cu_die);
+		diep = dwarf_offdie(dbg->dbg, off + cuhl, &pf->cu_die);
 		if (!diep)
 			continue;
 
 		/* Check if target file is included. */
 		if (pp->file)
-			pf.fname = cu_find_realpath(&pf.cu_die, pp->file);
+			pf->fname = cu_find_realpath(&pf->cu_die, pp->file);
 		else
-			pf.fname = NULL;
+			pf->fname = NULL;
 
-		if (!pp->file || pf.fname) {
+		if (!pp->file || pf->fname) {
 			if (pp->function)
-				ret = find_probe_point_by_func(&pf);
+				ret = find_probe_point_by_func(pf);
 			else if (pp->lazy_line)
-				ret = find_probe_point_lazy(NULL, &pf);
+				ret = find_probe_point_lazy(NULL, pf);
 			else {
-				pf.lno = pp->line;
-				ret = find_probe_point_by_line(&pf);
+				pf->lno = pp->line;
+				ret = find_probe_point_by_line(pf);
 			}
+			if (ret < 0)
+				break;
 		}
 		off = noff;
 	}
-	line_list__free(&pf.lcache);
-	dwarf_end(dbg);
 
-	return (ret < 0) ? ret : pf.ntevs;
+found:
+	intlist__delete(pf->lcache);
+	pf->lcache = NULL;
+
+	return ret;
+}
+
+struct local_vars_finder {
+	struct probe_finder *pf;
+	struct perf_probe_arg *args;
+	int max_args;
+	int nargs;
+	int ret;
+};
+
+/* Collect available variables in this scope */
+static int copy_variables_cb(Dwarf_Die *die_mem, void *data)
+{
+	struct local_vars_finder *vf = data;
+	struct probe_finder *pf = vf->pf;
+	int tag;
+
+	tag = dwarf_tag(die_mem);
+	if (tag == DW_TAG_formal_parameter ||
+	    tag == DW_TAG_variable) {
+		if (convert_variable_location(die_mem, vf->pf->addr,
+					      vf->pf->fb_ops, &pf->sp_die,
+					      NULL) == 0) {
+			vf->args[vf->nargs].var = (char *)dwarf_diename(die_mem);
+			if (vf->args[vf->nargs].var == NULL) {
+				vf->ret = -ENOMEM;
+				return DIE_FIND_CB_END;
+			}
+			pr_debug(" %s", vf->args[vf->nargs].var);
+			vf->nargs++;
+		}
+	}
+
+	if (dwarf_haspc(die_mem, vf->pf->addr))
+		return DIE_FIND_CB_CONTINUE;
+	else
+		return DIE_FIND_CB_SIBLING;
+}
+
+static int expand_probe_args(Dwarf_Die *sc_die, struct probe_finder *pf,
+			     struct perf_probe_arg *args)
+{
+	Dwarf_Die die_mem;
+	int i;
+	int n = 0;
+	struct local_vars_finder vf = {.pf = pf, .args = args,
+				.max_args = MAX_PROBE_ARGS, .ret = 0};
+
+	for (i = 0; i < pf->pev->nargs; i++) {
+		/* var never be NULL */
+		if (strcmp(pf->pev->args[i].var, "$vars") == 0) {
+			pr_debug("Expanding $vars into:");
+			vf.nargs = n;
+			/* Special local variables */
+			die_find_child(sc_die, copy_variables_cb, (void *)&vf,
+				       &die_mem);
+			pr_debug(" (%d)\n", vf.nargs - n);
+			if (vf.ret < 0)
+				return vf.ret;
+			n = vf.nargs;
+		} else {
+			/* Copy normal argument */
+			args[n] = pf->pev->args[i];
+			n++;
+		}
+	}
+	return n;
+}
+
+/* Add a found probe point into trace event list */
+static int add_probe_trace_event(Dwarf_Die *sc_die, struct probe_finder *pf)
+{
+	struct trace_event_finder *tf =
+			container_of(pf, struct trace_event_finder, pf);
+	struct probe_trace_event *tev;
+	struct perf_probe_arg *args;
+	int ret, i;
+
+	/* Check number of tevs */
+	if (tf->ntevs == tf->max_tevs) {
+		pr_warning("Too many( > %d) probe point found.\n",
+			   tf->max_tevs);
+		return -ERANGE;
+	}
+	tev = &tf->tevs[tf->ntevs++];
+
+	/* Trace point should be converted from subprogram DIE */
+	ret = convert_to_trace_point(&pf->sp_die, tf->mod, pf->addr,
+				     pf->pev->point.retprobe, &tev->point);
+	if (ret < 0)
+		return ret;
+
+	pr_debug("Probe point found: %s+%lu\n", tev->point.symbol,
+		 tev->point.offset);
+
+	/* Expand special probe argument if exist */
+	args = zalloc(sizeof(struct perf_probe_arg) * MAX_PROBE_ARGS);
+	if (args == NULL)
+		return -ENOMEM;
+
+	ret = expand_probe_args(sc_die, pf, args);
+	if (ret < 0)
+		goto end;
+
+	tev->nargs = ret;
+	tev->args = zalloc(sizeof(struct probe_trace_arg) * tev->nargs);
+	if (tev->args == NULL) {
+		ret = -ENOMEM;
+		goto end;
+	}
+
+	/* Find each argument */
+	for (i = 0; i < tev->nargs; i++) {
+		pf->pvar = &args[i];
+		pf->tvar = &tev->args[i];
+		/* Variable should be found from scope DIE */
+		ret = find_variable(sc_die, pf);
+		if (ret != 0)
+			break;
+	}
+
+end:
+	free(args);
+	return ret;
+}
+
+/* Find probe_trace_events specified by perf_probe_event from debuginfo */
+int debuginfo__find_trace_events(struct debuginfo *dbg,
+				 struct perf_probe_event *pev,
+				 struct probe_trace_event **tevs, int max_tevs)
+{
+	struct trace_event_finder tf = {
+			.pf = {.pev = pev, .callback = add_probe_trace_event},
+			.mod = dbg->mod, .max_tevs = max_tevs};
+	int ret;
+
+	/* Allocate result tevs array */
+	*tevs = zalloc(sizeof(struct probe_trace_event) * max_tevs);
+	if (*tevs == NULL)
+		return -ENOMEM;
+
+	tf.tevs = *tevs;
+	tf.ntevs = 0;
+
+	ret = debuginfo__find_probes(dbg, &tf.pf);
+	if (ret < 0) {
+		zfree(tevs);
+		return ret;
+	}
+
+	return (ret < 0) ? ret : tf.ntevs;
+}
+
+#define MAX_VAR_LEN 64
+
+/* Collect available variables in this scope */
+static int collect_variables_cb(Dwarf_Die *die_mem, void *data)
+{
+	struct available_var_finder *af = data;
+	struct variable_list *vl;
+	char buf[MAX_VAR_LEN];
+	int tag, ret;
+
+	vl = &af->vls[af->nvls - 1];
+
+	tag = dwarf_tag(die_mem);
+	if (tag == DW_TAG_formal_parameter ||
+	    tag == DW_TAG_variable) {
+		ret = convert_variable_location(die_mem, af->pf.addr,
+						af->pf.fb_ops, &af->pf.sp_die,
+						NULL);
+		if (ret == 0) {
+			ret = die_get_varname(die_mem, buf, MAX_VAR_LEN);
+			pr_debug2("Add new var: %s\n", buf);
+			if (ret > 0)
+				strlist__add(vl->vars, buf);
+		}
+	}
+
+	if (af->child && dwarf_haspc(die_mem, af->pf.addr))
+		return DIE_FIND_CB_CONTINUE;
+	else
+		return DIE_FIND_CB_SIBLING;
+}
+
+/* Add a found vars into available variables list */
+static int add_available_vars(Dwarf_Die *sc_die, struct probe_finder *pf)
+{
+	struct available_var_finder *af =
+			container_of(pf, struct available_var_finder, pf);
+	struct variable_list *vl;
+	Dwarf_Die die_mem;
+	int ret;
+
+	/* Check number of tevs */
+	if (af->nvls == af->max_vls) {
+		pr_warning("Too many( > %d) probe point found.\n", af->max_vls);
+		return -ERANGE;
+	}
+	vl = &af->vls[af->nvls++];
+
+	/* Trace point should be converted from subprogram DIE */
+	ret = convert_to_trace_point(&pf->sp_die, af->mod, pf->addr,
+				     pf->pev->point.retprobe, &vl->point);
+	if (ret < 0)
+		return ret;
+
+	pr_debug("Probe point found: %s+%lu\n", vl->point.symbol,
+		 vl->point.offset);
+
+	/* Find local variables */
+	vl->vars = strlist__new(true, NULL);
+	if (vl->vars == NULL)
+		return -ENOMEM;
+	af->child = true;
+	die_find_child(sc_die, collect_variables_cb, (void *)af, &die_mem);
+
+	/* Find external variables */
+	if (!af->externs)
+		goto out;
+	/* Don't need to search child DIE for externs. */
+	af->child = false;
+	die_find_child(&pf->cu_die, collect_variables_cb, (void *)af, &die_mem);
+
+out:
+	if (strlist__empty(vl->vars)) {
+		strlist__delete(vl->vars);
+		vl->vars = NULL;
+	}
+
+	return ret;
+}
+
+/*
+ * Find available variables at given probe point
+ * Return the number of found probe points. Return 0 if there is no
+ * matched probe point. Return <0 if an error occurs.
+ */
+int debuginfo__find_available_vars_at(struct debuginfo *dbg,
+				      struct perf_probe_event *pev,
+				      struct variable_list **vls,
+				      int max_vls, bool externs)
+{
+	struct available_var_finder af = {
+			.pf = {.pev = pev, .callback = add_available_vars},
+			.mod = dbg->mod,
+			.max_vls = max_vls, .externs = externs};
+	int ret;
+
+	/* Allocate result vls array */
+	*vls = zalloc(sizeof(struct variable_list) * max_vls);
+	if (*vls == NULL)
+		return -ENOMEM;
+
+	af.vls = *vls;
+	af.nvls = 0;
+
+	ret = debuginfo__find_probes(dbg, &af.pf);
+	if (ret < 0) {
+		/* Free vlist for error */
+		while (af.nvls--) {
+			zfree(&af.vls[af.nvls].point.symbol);
+			strlist__delete(af.vls[af.nvls].vars);
+		}
+		zfree(vls);
+		return ret;
+	}
+
+	return (ret < 0) ? ret : af.nvls;
 }
 
 /* Reverse search */
-int find_perf_probe_point(int fd, unsigned long addr,
-			  struct perf_probe_point *ppt)
+int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr,
+				struct perf_probe_point *ppt)
 {
 	Dwarf_Die cudie, spdie, indie;
-	Dwarf *dbg;
-	Dwarf_Line *line;
-	Dwarf_Addr laddr, eaddr;
-	const char *tmp;
-	int lineno, ret = 0;
-	bool found = false;
-
-	dbg = dwarf_begin(fd, DWARF_C_READ);
-	if (!dbg)
-		return -EBADF;
+	Dwarf_Addr _addr = 0, baseaddr = 0;
+	const char *fname = NULL, *func = NULL, *basefunc = NULL, *tmp;
+	int baseline = 0, lineno = 0, ret = 0;
+
+	/* Adjust address with bias */
+	addr += dbg->bias;
 
 	/* Find cu die */
-	if (!dwarf_addrdie(dbg, (Dwarf_Addr)addr, &cudie)) {
+	if (!dwarf_addrdie(dbg->dbg, (Dwarf_Addr)addr - dbg->bias, &cudie)) {
+		pr_warning("Failed to find debug information for address %lx\n",
+			   addr);
 		ret = -EINVAL;
 		goto end;
 	}
 
-	/* Find a corresponding line */
-	line = dwarf_getsrc_die(&cudie, (Dwarf_Addr)addr);
-	if (line) {
-		if (dwarf_lineaddr(line, &laddr) == 0 &&
-		    (Dwarf_Addr)addr == laddr &&
-		    dwarf_lineno(line, &lineno) == 0) {
-			tmp = dwarf_linesrc(line, NULL, NULL);
-			if (tmp) {
-				ppt->line = lineno;
-				ppt->file = strdup(tmp);
-				if (ppt->file == NULL) {
-					ret = -ENOMEM;
-					goto end;
-				}
-				found = true;
-			}
+	/* Find a corresponding line (filename and lineno) */
+	cu_find_lineinfo(&cudie, addr, &fname, &lineno);
+	/* Don't care whether it failed or not */
+
+	/* Find a corresponding function (name, baseline and baseaddr) */
+	if (die_find_realfunc(&cudie, (Dwarf_Addr)addr, &spdie)) {
+		/* Get function entry information */
+		func = basefunc = dwarf_diename(&spdie);
+		if (!func ||
+		    dwarf_entrypc(&spdie, &baseaddr) != 0 ||
+		    dwarf_decl_line(&spdie, &baseline) != 0) {
+			lineno = 0;
+			goto post;
 		}
-	}
 
-	/* Find a corresponding function */
-	if (die_find_real_subprogram(&cudie, (Dwarf_Addr)addr, &spdie)) {
-		tmp = dwarf_diename(&spdie);
-		if (!tmp || dwarf_entrypc(&spdie, &eaddr) != 0)
-			goto end;
+		fname = dwarf_decl_file(&spdie);
+		if (addr == (unsigned long)baseaddr) {
+			/* Function entry - Relative line number is 0 */
+			lineno = baseline;
+			goto post;
+		}
 
-		if (ppt->line) {
-			if (die_find_inlinefunc(&spdie, (Dwarf_Addr)addr,
+		/* Track down the inline functions step by step */
+		while (die_find_top_inlinefunc(&spdie, (Dwarf_Addr)addr,
 						&indie)) {
-				/* addr in an inline function */
-				tmp = dwarf_diename(&indie);
-				if (!tmp)
-					goto end;
-				ret = dwarf_decl_line(&indie, &lineno);
+			/* There is an inline function */
+			if (dwarf_entrypc(&indie, &_addr) == 0 &&
+			    _addr == addr) {
+				/*
+				 * addr is at an inline function entry.
+				 * In this case, lineno should be the call-site
+				 * line number. (overwrite lineinfo)
+				 */
+				lineno = die_get_call_lineno(&indie);
+				fname = die_get_call_file(&indie);
+				break;
 			} else {
-				if (eaddr == addr) {	/* Function entry */
-					lineno = ppt->line;
-					ret = 0;
-				} else
-					ret = dwarf_decl_line(&spdie, &lineno);
-			}
-			if (ret == 0) {
-				/* Make a relative line number */
-				ppt->line -= lineno;
-				goto found;
+				/*
+				 * addr is in an inline function body.
+				 * Since lineno points one of the lines
+				 * of the inline function, baseline should
+				 * be the entry line of the inline function.
+				 */
+				tmp = dwarf_diename(&indie);
+				if (!tmp ||
+				    dwarf_decl_line(&indie, &baseline) != 0)
+					break;
+				func = tmp;
+				spdie = indie;
 			}
 		}
-		/* We don't have a line number, let's use offset */
-		ppt->offset = addr - (unsigned long)eaddr;
-found:
-		ppt->function = strdup(tmp);
+		/* Verify the lineno and baseline are in a same file */
+		tmp = dwarf_decl_file(&spdie);
+		if (!tmp || strcmp(tmp, fname) != 0)
+			lineno = 0;
+	}
+
+post:
+	/* Make a relative line number or an offset */
+	if (lineno)
+		ppt->line = lineno - baseline;
+	else if (basefunc) {
+		ppt->offset = addr - (unsigned long)baseaddr;
+		func = basefunc;
+	}
+
+	/* Duplicate strings */
+	if (func) {
+		ppt->function = strdup(func);
 		if (ppt->function == NULL) {
 			ret = -ENOMEM;
 			goto end;
 		}
-		found = true;
 	}
-
+	if (fname) {
+		ppt->file = strdup(fname);
+		if (ppt->file == NULL) {
+			zfree(&ppt->function);
+			ret = -ENOMEM;
+			goto end;
+		}
+	}
 end:
-	dwarf_end(dbg);
-	if (ret >= 0)
-		ret = found ? 1 : 0;
+	if (ret == 0 && (fname || func))
+		ret = 1;	/* Found a point */
 	return ret;
 }
 
@@ -1096,131 +1430,78 @@ end:
 static int line_range_add_line(const char *src, unsigned int lineno,
 			       struct line_range *lr)
 {
-	/* Copy real path */
+	/* Copy source path */
 	if (!lr->path) {
 		lr->path = strdup(src);
 		if (lr->path == NULL)
 			return -ENOMEM;
 	}
-	return line_list__add_line(&lr->line_list, lineno);
+	return intlist__add(lr->line_list, lineno);
 }
 
-/* Search function declaration lines */
-static int line_range_funcdecl_cb(Dwarf_Die *sp_die, void *data)
+static int line_range_walk_cb(const char *fname, int lineno,
+			      Dwarf_Addr addr __maybe_unused,
+			      void *data)
 {
-	struct dwarf_callback_param *param = data;
-	struct line_finder *lf = param->data;
-	const char *src;
-	int lineno;
+	struct line_finder *lf = data;
+	int err;
 
-	src = dwarf_decl_file(sp_die);
-	if (src && strtailcmp(src, lf->fname) != 0)
-		return DWARF_CB_OK;
-
-	if (dwarf_decl_line(sp_die, &lineno) != 0 ||
+	if ((strtailcmp(fname, lf->fname) != 0) ||
 	    (lf->lno_s > lineno || lf->lno_e < lineno))
-		return DWARF_CB_OK;
+		return 0;
 
-	param->retval = line_range_add_line(src, lineno, lf->lr);
-	if (param->retval < 0)
-		return DWARF_CB_ABORT;
-	return DWARF_CB_OK;
-}
+	err = line_range_add_line(fname, lineno, lf->lr);
+	if (err < 0 && err != -EEXIST)
+		return err;
 
-static int find_line_range_func_decl_lines(struct line_finder *lf)
-{
-	struct dwarf_callback_param param = {.data = (void *)lf, .retval = 0};
-	dwarf_getfuncs(&lf->cu_die, line_range_funcdecl_cb, &param, 0);
-	return param.retval;
+	return 0;
 }
 
 /* Find line range from its line number */
 static int find_line_range_by_line(Dwarf_Die *sp_die, struct line_finder *lf)
 {
-	Dwarf_Lines *lines;
-	Dwarf_Line *line;
-	size_t nlines, i;
-	Dwarf_Addr addr;
-	int lineno, ret = 0;
-	const char *src;
-	Dwarf_Die die_mem;
-
-	line_list__init(&lf->lr->line_list);
-	if (dwarf_getsrclines(&lf->cu_die, &lines, &nlines) != 0) {
-		pr_warning("No source lines found in this CU.\n");
-		return -ENOENT;
-	}
-
-	/* Search probable lines on lines list */
-	for (i = 0; i < nlines; i++) {
-		line = dwarf_onesrcline(lines, i);
-		if (dwarf_lineno(line, &lineno) != 0 ||
-		    (lf->lno_s > lineno || lf->lno_e < lineno))
-			continue;
-
-		if (sp_die) {
-			/* Address filtering 1: does sp_die include addr? */
-			if (dwarf_lineaddr(line, &addr) != 0 ||
-			    !dwarf_haspc(sp_die, addr))
-				continue;
-
-			/* Address filtering 2: No child include addr? */
-			if (die_find_inlinefunc(sp_die, addr, &die_mem))
-				continue;
-		}
-
-		/* TODO: Get fileno from line, but how? */
-		src = dwarf_linesrc(line, NULL, NULL);
-		if (strtailcmp(src, lf->fname) != 0)
-			continue;
-
-		ret = line_range_add_line(src, lineno, lf->lr);
-		if (ret < 0)
-			return ret;
-	}
+	int ret;
 
-	/*
-	 * Dwarf lines doesn't include function declarations. We have to
-	 * check functions list or given function.
-	 */
-	if (sp_die) {
-		src = dwarf_decl_file(sp_die);
-		if (src && dwarf_decl_line(sp_die, &lineno) == 0 &&
-		    (lf->lno_s <= lineno && lf->lno_e >= lineno))
-			ret = line_range_add_line(src, lineno, lf->lr);
-	} else
-		ret = find_line_range_func_decl_lines(lf);
+	ret = die_walk_lines(sp_die ?: &lf->cu_die, line_range_walk_cb, lf);
 
 	/* Update status */
 	if (ret >= 0)
-		if (!list_empty(&lf->lr->line_list))
+		if (!intlist__empty(lf->lr->line_list))
 			ret = lf->found = 1;
 		else
 			ret = 0;	/* Lines are not found */
 	else {
-		free(lf->lr->path);
-		lf->lr->path = NULL;
+		zfree(&lf->lr->path);
 	}
 	return ret;
 }
 
 static int line_range_inline_cb(Dwarf_Die *in_die, void *data)
 {
-	struct dwarf_callback_param *param = data;
+	int ret = find_line_range_by_line(in_die, data);
 
-	param->retval = find_line_range_by_line(in_die, param->data);
-	return DWARF_CB_ABORT;	/* No need to find other instances */
+	/*
+	 * We have to check all instances of inlined function, because
+	 * some execution paths can be optimized out depends on the
+	 * function argument of instances. However, if an error occurs,
+	 * it should be handled by the caller.
+	 */
+	return ret < 0 ? ret : 0;
 }
 
-/* Search function from function name */
+/* Search function definition from function name */
 static int line_range_search_cb(Dwarf_Die *sp_die, void *data)
 {
 	struct dwarf_callback_param *param = data;
 	struct line_finder *lf = param->data;
 	struct line_range *lr = lf->lr;
 
-	if (dwarf_tag(sp_die) == DW_TAG_subprogram &&
-	    die_compare_name(sp_die, lr->function) == 0) {
+	/* Check declared file */
+	if (lr->file && strtailcmp(lr->file, dwarf_decl_file(sp_die)))
+		return DWARF_CB_OK;
+
+	if (die_is_func_def(sp_die) &&
+	    die_compare_name(sp_die, lr->function)) {
 		lf->fname = dwarf_decl_file(sp_die);
 		dwarf_decl_line(sp_die, &lr->offset);
 		pr_debug("fname: %s, lineno:%d\n", lf->fname, lr->offset);
@@ -1233,15 +1514,10 @@ static int line_range_search_cb(Dwarf_Die *sp_die, void *data)
 		pr_debug("New line range: %d to %d\n", lf->lno_s, lf->lno_e);
 		lr->start = lf->lno_s;
 		lr->end = lf->lno_e;
-		if (dwarf_func_inline(sp_die)) {
-			struct dwarf_callback_param _param;
-			_param.data = (void *)lf;
-			_param.retval = 0;
-			dwarf_func_inline_instances(sp_die,
-						    line_range_inline_cb,
-						    &_param);
-			param->retval = _param.retval;
-		} else
+		if (dwarf_func_inline(sp_die))
+			param->retval = die_walk_instances(sp_die,
+						line_range_inline_cb, lf);
+		else
 			param->retval = find_line_range_by_line(sp_die, lf);
 		return DWARF_CB_ABORT;
 	}
@@ -1255,29 +1531,40 @@ static int find_line_range_by_func(struct line_finder *lf)
 	return param.retval;
 }
 
-int find_line_range(int fd, struct line_range *lr)
+int debuginfo__find_line_range(struct debuginfo *dbg, struct line_range *lr)
 {
 	struct line_finder lf = {.lr = lr, .found = 0};
 	int ret = 0;
 	Dwarf_Off off = 0, noff;
 	size_t cuhl;
 	Dwarf_Die *diep;
-	Dwarf *dbg;
-
-	dbg = dwarf_begin(fd, DWARF_C_READ);
-	if (!dbg) {
-		pr_warning("No dwarf info found in the vmlinux - "
-			"please rebuild with CONFIG_DEBUG_INFO=y.\n");
-		return -EBADF;
+	const char *comp_dir;
+
+	/* Fastpath: lookup by function name from .debug_pubnames section */
+	if (lr->function) {
+		struct pubname_callback_param pubname_param = {
+			.function = lr->function, .file = lr->file,
+			.cu_die = &lf.cu_die, .sp_die = &lf.sp_die, .found = 0};
+		struct dwarf_callback_param line_range_param = {
+			.data = (void *)&lf, .retval = 0};
+
+		dwarf_getpubnames(dbg->dbg, pubname_search_cb,
+				  &pubname_param, 0);
+		if (pubname_param.found) {
+			line_range_search_cb(&lf.sp_die, &line_range_param);
+			if (lf.found)
+				goto found;
+		}
 	}
 
 	/* Loop on CUs (Compilation Unit) */
 	while (!lf.found && ret >= 0) {
-		if (dwarf_nextcu(dbg, off, &noff, &cuhl, NULL, NULL, NULL) != 0)
+		if (dwarf_nextcu(dbg->dbg, off, &noff, &cuhl,
+				 NULL, NULL, NULL) != 0)
 			break;
 
 		/* Get the DIE(Debugging Information Entry) of this CU */
-		diep = dwarf_offdie(dbg, off + cuhl, &lf.cu_die);
+		diep = dwarf_offdie(dbg->dbg, off + cuhl, &lf.cu_die);
 		if (!diep)
 			continue;
 
@@ -1298,9 +1585,19 @@ int find_line_range(int fd, struct line_range *lr)
 		}
 		off = noff;
 	}
-	pr_debug("path: %lx\n", (unsigned long)lr->path);
-	dwarf_end(dbg);
 
+found:
+	/* Store comp_dir */
+	if (lf.found) {
+		comp_dir = cu_get_comp_dir(&lf.cu_die);
+		if (comp_dir) {
+			lr->comp_dir = strdup(comp_dir);
+			if (!lr->comp_dir)
+				ret = -ENOMEM;
+		}
+	}
+
+	pr_debug("path: %s\n", lr->path);
 	return (ret < 0) ? ret : lf.found;
 }
 
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index e1f61dcd18f..92590b2c7e1 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -3,11 +3,12 @@
 
 #include <stdbool.h>
 #include "util.h"
+#include "intlist.h"
 #include "probe-event.h"
 
-#define MAX_PATH_LEN		 256
 #define MAX_PROBE_BUFFER	1024
 #define MAX_PROBES		 128
+#define MAX_PROBE_ARGS		 128
 
 static inline int is_c_varname(const char *name)
 {
@@ -15,34 +16,58 @@ static inline int is_c_varname(const char *name)
 	return isalpha(name[0]) || name[0] == '_';
 }
 
-#ifdef DWARF_SUPPORT
-/* Find kprobe_trace_events specified by perf_probe_event from debuginfo */
-extern int find_kprobe_trace_events(int fd, struct perf_probe_event *pev,
-				    struct kprobe_trace_event **tevs,
-				    int max_tevs);
+#ifdef HAVE_DWARF_SUPPORT
+
+#include "dwarf-aux.h"
+
+/* TODO: export debuginfo data structure even if no dwarf support */
+
+/* debug information structure */
+struct debuginfo {
+	Dwarf		*dbg;
+	Dwfl_Module	*mod;
+	Dwfl		*dwfl;
+	Dwarf_Addr	bias;
+};
+
+/* This also tries to open distro debuginfo */
+extern struct debuginfo *debuginfo__new(const char *path);
+extern void debuginfo__delete(struct debuginfo *dbg);
+
+/* Find probe_trace_events specified by perf_probe_event from debuginfo */
+extern int debuginfo__find_trace_events(struct debuginfo *dbg,
+					struct perf_probe_event *pev,
+					struct probe_trace_event **tevs,
+					int max_tevs);
 
 /* Find a perf_probe_point from debuginfo */
-extern int find_perf_probe_point(int fd, unsigned long addr,
-				 struct perf_probe_point *ppt);
+extern int debuginfo__find_probe_point(struct debuginfo *dbg,
+				       unsigned long addr,
+				       struct perf_probe_point *ppt);
 
-extern int find_line_range(int fd, struct line_range *lr);
+/* Find a line range */
+extern int debuginfo__find_line_range(struct debuginfo *dbg,
+				      struct line_range *lr);
 
-#include <dwarf.h>
-#include <libdw.h>
-#include <version.h>
+/* Find available variables */
+extern int debuginfo__find_available_vars_at(struct debuginfo *dbg,
+					     struct perf_probe_event *pev,
+					     struct variable_list **vls,
+					     int max_points, bool externs);
 
 struct probe_finder {
 	struct perf_probe_event	*pev;		/* Target probe event */
-	struct kprobe_trace_event *tevs;	/* Result trace events */
-	int			ntevs;		/* Number of trace events */
-	int			max_tevs;	/* Max number of trace events */
+
+	/* Callback when a probe point is found */
+	int (*callback)(Dwarf_Die *sc_die, struct probe_finder *pf);
 
 	/* For function searching */
 	int			lno;		/* Line number */
 	Dwarf_Addr		addr;		/* Address */
 	const char		*fname;		/* Real file name */
 	Dwarf_Die		cu_die;		/* Current CU */
-	struct list_head	lcache;		/* Line cache for lazy match */
+	Dwarf_Die		sp_die;
+	struct intlist		*lcache;	/* Line cache for lazy match */
 
 	/* For variable searching */
 #if _ELFUTILS_PREREQ(0, 142)
@@ -50,7 +75,25 @@ struct probe_finder {
 #endif
 	Dwarf_Op		*fb_ops;	/* Frame base attribute */
 	struct perf_probe_arg	*pvar;		/* Current target variable */
-	struct kprobe_trace_arg	*tvar;		/* Current result variable */
+	struct probe_trace_arg	*tvar;		/* Current result variable */
+};
+
+struct trace_event_finder {
+	struct probe_finder	pf;
+	Dwfl_Module		*mod;		/* For solving symbols */
+	struct probe_trace_event *tevs;		/* Found trace events */
+	int			ntevs;		/* Number of trace events */
+	int			max_tevs;	/* Max number of trace events */
+};
+
+struct available_var_finder {
+	struct probe_finder	pf;
+	Dwfl_Module		*mod;		/* For solving symbols */
+	struct variable_list	*vls;		/* Found variable lists */
+	int			nvls;		/* Number of variable lists */
+	int			max_vls;	/* Max no. of variable lists */
+	bool			externs;	/* Find external vars too */
+	bool			child;		/* Search child scopes */
 };
 
 struct line_finder {
@@ -60,9 +103,10 @@ struct line_finder {
 	int			lno_s;		/* Start line number */
 	int			lno_e;		/* End line number */
 	Dwarf_Die		cu_die;		/* Current CU */
+	Dwarf_Die		sp_die;
 	int			found;
 };
 
-#endif /* DWARF_SUPPORT */
+#endif /* HAVE_DWARF_SUPPORT */
 
 #endif /*_PROBE_FINDER_H */
diff --git a/tools/perf/util/pstack.c b/tools/perf/util/pstack.c
index 13d36faf64e..daa17aeb6c6 100644
--- a/tools/perf/util/pstack.c
+++ b/tools/perf/util/pstack.c
@@ -17,59 +17,59 @@ struct pstack {
 
 struct pstack *pstack__new(unsigned short max_nr_entries)
 {
-	struct pstack *self = zalloc((sizeof(*self) +
-				     max_nr_entries * sizeof(void *)));
-	if (self != NULL)
-		self->max_nr_entries = max_nr_entries;
-	return self;
+	struct pstack *pstack = zalloc((sizeof(*pstack) +
+				       max_nr_entries * sizeof(void *)));
+	if (pstack != NULL)
+		pstack->max_nr_entries = max_nr_entries;
+	return pstack;
 }
 
-void pstack__delete(struct pstack *self)
+void pstack__delete(struct pstack *pstack)
 {
-	free(self);
+	free(pstack);
 }
 
-bool pstack__empty(const struct pstack *self)
+bool pstack__empty(const struct pstack *pstack)
 {
-	return self->top == 0;
+	return pstack->top == 0;
 }
 
-void pstack__remove(struct pstack *self, void *key)
+void pstack__remove(struct pstack *pstack, void *key)
 {
-	unsigned short i = self->top, last_index = self->top - 1;
+	unsigned short i = pstack->top, last_index = pstack->top - 1;
 
 	while (i-- != 0) {
-		if (self->entries[i] == key) {
+		if (pstack->entries[i] == key) {
 			if (i < last_index)
-				memmove(self->entries + i,
-					self->entries + i + 1,
+				memmove(pstack->entries + i,
+					pstack->entries + i + 1,
 					(last_index - i) * sizeof(void *));
-			--self->top;
+			--pstack->top;
 			return;
 		}
 	}
 	pr_err("%s: %p not on the pstack!\n", __func__, key);
 }
 
-void pstack__push(struct pstack *self, void *key)
+void pstack__push(struct pstack *pstack, void *key)
 {
-	if (self->top == self->max_nr_entries) {
-		pr_err("%s: top=%d, overflow!\n", __func__, self->top);
+	if (pstack->top == pstack->max_nr_entries) {
+		pr_err("%s: top=%d, overflow!\n", __func__, pstack->top);
 		return;
 	}
-	self->entries[self->top++] = key;
+	pstack->entries[pstack->top++] = key;
 }
 
-void *pstack__pop(struct pstack *self)
+void *pstack__pop(struct pstack *pstack)
 {
 	void *ret;
 
-	if (self->top == 0) {
+	if (pstack->top == 0) {
 		pr_err("%s: underflow!\n", __func__);
 		return NULL;
 	}
 
-	ret = self->entries[--self->top];
-	self->entries[self->top] = NULL;
+	ret = pstack->entries[--pstack->top];
+	pstack->entries[pstack->top] = NULL;
 	return ret;
 }
diff --git a/tools/perf/util/pstack.h b/tools/perf/util/pstack.h
index 5ad07023504..c3cb6584d52 100644
--- a/tools/perf/util/pstack.h
+++ b/tools/perf/util/pstack.h
@@ -1,12 +1,14 @@
 #ifndef _PERF_PSTACK_
 #define _PERF_PSTACK_
 
+#include <stdbool.h>
+
 struct pstack;
 struct pstack *pstack__new(unsigned short max_nr_entries);
-void pstack__delete(struct pstack *self);
-bool pstack__empty(const struct pstack *self);
-void pstack__remove(struct pstack *self, void *key);
-void pstack__push(struct pstack *self, void *key);
-void *pstack__pop(struct pstack *self);
+void pstack__delete(struct pstack *pstack);
+bool pstack__empty(const struct pstack *pstack);
+void pstack__remove(struct pstack *pstack, void *key);
+void pstack__push(struct pstack *pstack, void *key);
+void *pstack__pop(struct pstack *pstack);
 
 #endif /* _PERF_PSTACK_ */
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
new file mode 100644
index 00000000000..16a475a7d49
--- /dev/null
+++ b/tools/perf/util/python-ext-sources
@@ -0,0 +1,22 @@
+#
+# List of files needed by perf python extension
+#
+# Each source file must be placed on its own line so that it can be
+# processed by Makefile and util/setup.py accordingly.
+#
+
+util/python.c
+util/ctype.c
+util/evlist.c
+util/evsel.c
+util/cpumap.c
+util/hweight.c
+util/thread_map.c
+util/util.c
+util/xyarray.c
+util/cgroup.c
+util/rblist.c
+util/strlist.c
+../lib/api/fs/fs.c
+util/trace-event.c
+../../lib/rbtree.c
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
new file mode 100644
index 00000000000..122669c18ff
--- /dev/null
+++ b/tools/perf/util/python.c
@@ -0,0 +1,1074 @@
+#include <Python.h>
+#include <structmember.h>
+#include <inttypes.h>
+#include <poll.h>
+#include "evlist.h"
+#include "evsel.h"
+#include "event.h"
+#include "cpumap.h"
+#include "thread_map.h"
+
+/*
+ * Support debug printing even though util/debug.c is not linked.  That means
+ * implementing 'verbose' and 'eprintf'.
+ */
+int verbose;
+
+int eprintf(int level, const char *fmt, ...)
+{
+	va_list args;
+	int ret = 0;
+
+	if (verbose >= level) {
+		va_start(args, fmt);
+		ret = vfprintf(stderr, fmt, args);
+		va_end(args);
+	}
+
+	return ret;
+}
+
+/* Define PyVarObject_HEAD_INIT for python 2.5 */
+#ifndef PyVarObject_HEAD_INIT
+# define PyVarObject_HEAD_INIT(type, size) PyObject_HEAD_INIT(type) size,
+#endif
+
+PyMODINIT_FUNC initperf(void);
+
+#define member_def(type, member, ptype, help) \
+	{ #member, ptype, \
+	  offsetof(struct pyrf_event, event) + offsetof(struct type, member), \
+	  0, help }
+
+#define sample_member_def(name, member, ptype, help) \
+	{ #name, ptype, \
+	  offsetof(struct pyrf_event, sample) + offsetof(struct perf_sample, member), \
+	  0, help }
+
+struct pyrf_event {
+	PyObject_HEAD
+	struct perf_sample sample;
+	union perf_event   event;
+};
+
+#define sample_members \
+	sample_member_def(sample_ip, ip, T_ULONGLONG, "event type"),			 \
+	sample_member_def(sample_pid, pid, T_INT, "event pid"),			 \
+	sample_member_def(sample_tid, tid, T_INT, "event tid"),			 \
+	sample_member_def(sample_time, time, T_ULONGLONG, "event timestamp"),		 \
+	sample_member_def(sample_addr, addr, T_ULONGLONG, "event addr"),		 \
+	sample_member_def(sample_id, id, T_ULONGLONG, "event id"),			 \
+	sample_member_def(sample_stream_id, stream_id, T_ULONGLONG, "event stream id"), \
+	sample_member_def(sample_period, period, T_ULONGLONG, "event period"),		 \
+	sample_member_def(sample_cpu, cpu, T_UINT, "event cpu"),
+
+static char pyrf_mmap_event__doc[] = PyDoc_STR("perf mmap event object.");
+
+static PyMemberDef pyrf_mmap_event__members[] = {
+	sample_members
+	member_def(perf_event_header, type, T_UINT, "event type"),
+	member_def(mmap_event, pid, T_UINT, "event pid"),
+	member_def(mmap_event, tid, T_UINT, "event tid"),
+	member_def(mmap_event, start, T_ULONGLONG, "start of the map"),
+	member_def(mmap_event, len, T_ULONGLONG, "map length"),
+	member_def(mmap_event, pgoff, T_ULONGLONG, "page offset"),
+	member_def(mmap_event, filename, T_STRING_INPLACE, "backing store"),
+	{ .name = NULL, },
+};
+
+static PyObject *pyrf_mmap_event__repr(struct pyrf_event *pevent)
+{
+	PyObject *ret;
+	char *s;
+
+	if (asprintf(&s, "{ type: mmap, pid: %u, tid: %u, start: %#" PRIx64 ", "
+			 "length: %#" PRIx64 ", offset: %#" PRIx64 ", "
+			 "filename: %s }",
+		     pevent->event.mmap.pid, pevent->event.mmap.tid,
+		     pevent->event.mmap.start, pevent->event.mmap.len,
+		     pevent->event.mmap.pgoff, pevent->event.mmap.filename) < 0) {
+		ret = PyErr_NoMemory();
+	} else {
+		ret = PyString_FromString(s);
+		free(s);
+	}
+	return ret;
+}
+
+static PyTypeObject pyrf_mmap_event__type = {
+	PyVarObject_HEAD_INIT(NULL, 0)
+	.tp_name	= "perf.mmap_event",
+	.tp_basicsize	= sizeof(struct pyrf_event),
+	.tp_flags	= Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
+	.tp_doc		= pyrf_mmap_event__doc,
+	.tp_members	= pyrf_mmap_event__members,
+	.tp_repr	= (reprfunc)pyrf_mmap_event__repr,
+};
+
+static char pyrf_task_event__doc[] = PyDoc_STR("perf task (fork/exit) event object.");
+
+static PyMemberDef pyrf_task_event__members[] = {
+	sample_members
+	member_def(perf_event_header, type, T_UINT, "event type"),
+	member_def(fork_event, pid, T_UINT, "event pid"),
+	member_def(fork_event, ppid, T_UINT, "event ppid"),
+	member_def(fork_event, tid, T_UINT, "event tid"),
+	member_def(fork_event, ptid, T_UINT, "event ptid"),
+	member_def(fork_event, time, T_ULONGLONG, "timestamp"),
+	{ .name = NULL, },
+};
+
+static PyObject *pyrf_task_event__repr(struct pyrf_event *pevent)
+{
+	return PyString_FromFormat("{ type: %s, pid: %u, ppid: %u, tid: %u, "
+				   "ptid: %u, time: %" PRIu64 "}",
+				   pevent->event.header.type == PERF_RECORD_FORK ? "fork" : "exit",
+				   pevent->event.fork.pid,
+				   pevent->event.fork.ppid,
+				   pevent->event.fork.tid,
+				   pevent->event.fork.ptid,
+				   pevent->event.fork.time);
+}
+
+static PyTypeObject pyrf_task_event__type = {
+	PyVarObject_HEAD_INIT(NULL, 0)
+	.tp_name	= "perf.task_event",
+	.tp_basicsize	= sizeof(struct pyrf_event),
+	.tp_flags	= Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
+	.tp_doc		= pyrf_task_event__doc,
+	.tp_members	= pyrf_task_event__members,
+	.tp_repr	= (reprfunc)pyrf_task_event__repr,
+};
+
+static char pyrf_comm_event__doc[] = PyDoc_STR("perf comm event object.");
+
+static PyMemberDef pyrf_comm_event__members[] = {
+	sample_members
+	member_def(perf_event_header, type, T_UINT, "event type"),
+	member_def(comm_event, pid, T_UINT, "event pid"),
+	member_def(comm_event, tid, T_UINT, "event tid"),
+	member_def(comm_event, comm, T_STRING_INPLACE, "process name"),
+	{ .name = NULL, },
+};
+
+static PyObject *pyrf_comm_event__repr(struct pyrf_event *pevent)
+{
+	return PyString_FromFormat("{ type: comm, pid: %u, tid: %u, comm: %s }",
+				   pevent->event.comm.pid,
+				   pevent->event.comm.tid,
+				   pevent->event.comm.comm);
+}
+
+static PyTypeObject pyrf_comm_event__type = {
+	PyVarObject_HEAD_INIT(NULL, 0)
+	.tp_name	= "perf.comm_event",
+	.tp_basicsize	= sizeof(struct pyrf_event),
+	.tp_flags	= Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
+	.tp_doc		= pyrf_comm_event__doc,
+	.tp_members	= pyrf_comm_event__members,
+	.tp_repr	= (reprfunc)pyrf_comm_event__repr,
+};
+
+static char pyrf_throttle_event__doc[] = PyDoc_STR("perf throttle event object.");
+
+static PyMemberDef pyrf_throttle_event__members[] = {
+	sample_members
+	member_def(perf_event_header, type, T_UINT, "event type"),
+	member_def(throttle_event, time, T_ULONGLONG, "timestamp"),
+	member_def(throttle_event, id, T_ULONGLONG, "event id"),
+	member_def(throttle_event, stream_id, T_ULONGLONG, "event stream id"),
+	{ .name = NULL, },
+};
+
+static PyObject *pyrf_throttle_event__repr(struct pyrf_event *pevent)
+{
+	struct throttle_event *te = (struct throttle_event *)(&pevent->event.header + 1);
+
+	return PyString_FromFormat("{ type: %sthrottle, time: %" PRIu64 ", id: %" PRIu64
+				   ", stream_id: %" PRIu64 " }",
+				   pevent->event.header.type == PERF_RECORD_THROTTLE ? "" : "un",
+				   te->time, te->id, te->stream_id);
+}
+
+static PyTypeObject pyrf_throttle_event__type = {
+	PyVarObject_HEAD_INIT(NULL, 0)
+	.tp_name	= "perf.throttle_event",
+	.tp_basicsize	= sizeof(struct pyrf_event),
+	.tp_flags	= Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
+	.tp_doc		= pyrf_throttle_event__doc,
+	.tp_members	= pyrf_throttle_event__members,
+	.tp_repr	= (reprfunc)pyrf_throttle_event__repr,
+};
+
+static char pyrf_lost_event__doc[] = PyDoc_STR("perf lost event object.");
+
+static PyMemberDef pyrf_lost_event__members[] = {
+	sample_members
+	member_def(lost_event, id, T_ULONGLONG, "event id"),
+	member_def(lost_event, lost, T_ULONGLONG, "number of lost events"),
+	{ .name = NULL, },
+};
+
+static PyObject *pyrf_lost_event__repr(struct pyrf_event *pevent)
+{
+	PyObject *ret;
+	char *s;
+
+	if (asprintf(&s, "{ type: lost, id: %#" PRIx64 ", "
+			 "lost: %#" PRIx64 " }",
+		     pevent->event.lost.id, pevent->event.lost.lost) < 0) {
+		ret = PyErr_NoMemory();
+	} else {
+		ret = PyString_FromString(s);
+		free(s);
+	}
+	return ret;
+}
+
+static PyTypeObject pyrf_lost_event__type = {
+	PyVarObject_HEAD_INIT(NULL, 0)
+	.tp_name	= "perf.lost_event",
+	.tp_basicsize	= sizeof(struct pyrf_event),
+	.tp_flags	= Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
+	.tp_doc		= pyrf_lost_event__doc,
+	.tp_members	= pyrf_lost_event__members,
+	.tp_repr	= (reprfunc)pyrf_lost_event__repr,
+};
+
+static char pyrf_read_event__doc[] = PyDoc_STR("perf read event object.");
+
+static PyMemberDef pyrf_read_event__members[] = {
+	sample_members
+	member_def(read_event, pid, T_UINT, "event pid"),
+	member_def(read_event, tid, T_UINT, "event tid"),
+	{ .name = NULL, },
+};
+
+static PyObject *pyrf_read_event__repr(struct pyrf_event *pevent)
+{
+	return PyString_FromFormat("{ type: read, pid: %u, tid: %u }",
+				   pevent->event.read.pid,
+				   pevent->event.read.tid);
+	/*
+ 	 * FIXME: return the array of read values,
+ 	 * making this method useful ;-)
+ 	 */
+}
+
+static PyTypeObject pyrf_read_event__type = {
+	PyVarObject_HEAD_INIT(NULL, 0)
+	.tp_name	= "perf.read_event",
+	.tp_basicsize	= sizeof(struct pyrf_event),
+	.tp_flags	= Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
+	.tp_doc		= pyrf_read_event__doc,
+	.tp_members	= pyrf_read_event__members,
+	.tp_repr	= (reprfunc)pyrf_read_event__repr,
+};
+
+static char pyrf_sample_event__doc[] = PyDoc_STR("perf sample event object.");
+
+static PyMemberDef pyrf_sample_event__members[] = {
+	sample_members
+	member_def(perf_event_header, type, T_UINT, "event type"),
+	{ .name = NULL, },
+};
+
+static PyObject *pyrf_sample_event__repr(struct pyrf_event *pevent)
+{
+	PyObject *ret;
+	char *s;
+
+	if (asprintf(&s, "{ type: sample }") < 0) {
+		ret = PyErr_NoMemory();
+	} else {
+		ret = PyString_FromString(s);
+		free(s);
+	}
+	return ret;
+}
+
+static PyTypeObject pyrf_sample_event__type = {
+	PyVarObject_HEAD_INIT(NULL, 0)
+	.tp_name	= "perf.sample_event",
+	.tp_basicsize	= sizeof(struct pyrf_event),
+	.tp_flags	= Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
+	.tp_doc		= pyrf_sample_event__doc,
+	.tp_members	= pyrf_sample_event__members,
+	.tp_repr	= (reprfunc)pyrf_sample_event__repr,
+};
+
+static int pyrf_event__setup_types(void)
+{
+	int err;
+	pyrf_mmap_event__type.tp_new =
+	pyrf_task_event__type.tp_new =
+	pyrf_comm_event__type.tp_new =
+	pyrf_lost_event__type.tp_new =
+	pyrf_read_event__type.tp_new =
+	pyrf_sample_event__type.tp_new =
+	pyrf_throttle_event__type.tp_new = PyType_GenericNew;
+	err = PyType_Ready(&pyrf_mmap_event__type);
+	if (err < 0)
+		goto out;
+	err = PyType_Ready(&pyrf_lost_event__type);
+	if (err < 0)
+		goto out;
+	err = PyType_Ready(&pyrf_task_event__type);
+	if (err < 0)
+		goto out;
+	err = PyType_Ready(&pyrf_comm_event__type);
+	if (err < 0)
+		goto out;
+	err = PyType_Ready(&pyrf_throttle_event__type);
+	if (err < 0)
+		goto out;
+	err = PyType_Ready(&pyrf_read_event__type);
+	if (err < 0)
+		goto out;
+	err = PyType_Ready(&pyrf_sample_event__type);
+	if (err < 0)
+		goto out;
+out:
+	return err;
+}
+
+static PyTypeObject *pyrf_event__type[] = {
+	[PERF_RECORD_MMAP]	 = &pyrf_mmap_event__type,
+	[PERF_RECORD_LOST]	 = &pyrf_lost_event__type,
+	[PERF_RECORD_COMM]	 = &pyrf_comm_event__type,
+	[PERF_RECORD_EXIT]	 = &pyrf_task_event__type,
+	[PERF_RECORD_THROTTLE]	 = &pyrf_throttle_event__type,
+	[PERF_RECORD_UNTHROTTLE] = &pyrf_throttle_event__type,
+	[PERF_RECORD_FORK]	 = &pyrf_task_event__type,
+	[PERF_RECORD_READ]	 = &pyrf_read_event__type,
+	[PERF_RECORD_SAMPLE]	 = &pyrf_sample_event__type,
+};
+
+static PyObject *pyrf_event__new(union perf_event *event)
+{
+	struct pyrf_event *pevent;
+	PyTypeObject *ptype;
+
+	if (event->header.type < PERF_RECORD_MMAP ||
+	    event->header.type > PERF_RECORD_SAMPLE)
+		return NULL;
+
+	ptype = pyrf_event__type[event->header.type];
+	pevent = PyObject_New(struct pyrf_event, ptype);
+	if (pevent != NULL)
+		memcpy(&pevent->event, event, event->header.size);
+	return (PyObject *)pevent;
+}
+
+struct pyrf_cpu_map {
+	PyObject_HEAD
+
+	struct cpu_map *cpus;
+};
+
+static int pyrf_cpu_map__init(struct pyrf_cpu_map *pcpus,
+			      PyObject *args, PyObject *kwargs)
+{
+	static char *kwlist[] = { "cpustr", NULL };
+	char *cpustr = NULL;
+
+	if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|s",
+					 kwlist, &cpustr))
+		return -1;
+
+	pcpus->cpus = cpu_map__new(cpustr);
+	if (pcpus->cpus == NULL)
+		return -1;
+	return 0;
+}
+
+static void pyrf_cpu_map__delete(struct pyrf_cpu_map *pcpus)
+{
+	cpu_map__delete(pcpus->cpus);
+	pcpus->ob_type->tp_free((PyObject*)pcpus);
+}
+
+static Py_ssize_t pyrf_cpu_map__length(PyObject *obj)
+{
+	struct pyrf_cpu_map *pcpus = (void *)obj;
+
+	return pcpus->cpus->nr;
+}
+
+static PyObject *pyrf_cpu_map__item(PyObject *obj, Py_ssize_t i)
+{
+	struct pyrf_cpu_map *pcpus = (void *)obj;
+
+	if (i >= pcpus->cpus->nr)
+		return NULL;
+
+	return Py_BuildValue("i", pcpus->cpus->map[i]);
+}
+
+static PySequenceMethods pyrf_cpu_map__sequence_methods = {
+	.sq_length = pyrf_cpu_map__length,
+	.sq_item   = pyrf_cpu_map__item,
+};
+
+static char pyrf_cpu_map__doc[] = PyDoc_STR("cpu map object.");
+
+static PyTypeObject pyrf_cpu_map__type = {
+	PyVarObject_HEAD_INIT(NULL, 0)
+	.tp_name	= "perf.cpu_map",
+	.tp_basicsize	= sizeof(struct pyrf_cpu_map),
+	.tp_dealloc	= (destructor)pyrf_cpu_map__delete,
+	.tp_flags	= Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
+	.tp_doc		= pyrf_cpu_map__doc,
+	.tp_as_sequence	= &pyrf_cpu_map__sequence_methods,
+	.tp_init	= (initproc)pyrf_cpu_map__init,
+};
+
+static int pyrf_cpu_map__setup_types(void)
+{
+	pyrf_cpu_map__type.tp_new = PyType_GenericNew;
+	return PyType_Ready(&pyrf_cpu_map__type);
+}
+
+struct pyrf_thread_map {
+	PyObject_HEAD
+
+	struct thread_map *threads;
+};
+
+static int pyrf_thread_map__init(struct pyrf_thread_map *pthreads,
+				 PyObject *args, PyObject *kwargs)
+{
+	static char *kwlist[] = { "pid", "tid", "uid", NULL };
+	int pid = -1, tid = -1, uid = UINT_MAX;
+
+	if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|iii",
+					 kwlist, &pid, &tid, &uid))
+		return -1;
+
+	pthreads->threads = thread_map__new(pid, tid, uid);
+	if (pthreads->threads == NULL)
+		return -1;
+	return 0;
+}
+
+static void pyrf_thread_map__delete(struct pyrf_thread_map *pthreads)
+{
+	thread_map__delete(pthreads->threads);
+	pthreads->ob_type->tp_free((PyObject*)pthreads);
+}
+
+static Py_ssize_t pyrf_thread_map__length(PyObject *obj)
+{
+	struct pyrf_thread_map *pthreads = (void *)obj;
+
+	return pthreads->threads->nr;
+}
+
+static PyObject *pyrf_thread_map__item(PyObject *obj, Py_ssize_t i)
+{
+	struct pyrf_thread_map *pthreads = (void *)obj;
+
+	if (i >= pthreads->threads->nr)
+		return NULL;
+
+	return Py_BuildValue("i", pthreads->threads->map[i]);
+}
+
+static PySequenceMethods pyrf_thread_map__sequence_methods = {
+	.sq_length = pyrf_thread_map__length,
+	.sq_item   = pyrf_thread_map__item,
+};
+
+static char pyrf_thread_map__doc[] = PyDoc_STR("thread map object.");
+
+static PyTypeObject pyrf_thread_map__type = {
+	PyVarObject_HEAD_INIT(NULL, 0)
+	.tp_name	= "perf.thread_map",
+	.tp_basicsize	= sizeof(struct pyrf_thread_map),
+	.tp_dealloc	= (destructor)pyrf_thread_map__delete,
+	.tp_flags	= Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
+	.tp_doc		= pyrf_thread_map__doc,
+	.tp_as_sequence	= &pyrf_thread_map__sequence_methods,
+	.tp_init	= (initproc)pyrf_thread_map__init,
+};
+
+static int pyrf_thread_map__setup_types(void)
+{
+	pyrf_thread_map__type.tp_new = PyType_GenericNew;
+	return PyType_Ready(&pyrf_thread_map__type);
+}
+
+struct pyrf_evsel {
+	PyObject_HEAD
+
+	struct perf_evsel evsel;
+};
+
+static int pyrf_evsel__init(struct pyrf_evsel *pevsel,
+			    PyObject *args, PyObject *kwargs)
+{
+	struct perf_event_attr attr = {
+		.type = PERF_TYPE_HARDWARE,
+		.config = PERF_COUNT_HW_CPU_CYCLES,
+		.sample_type = PERF_SAMPLE_PERIOD | PERF_SAMPLE_TID,
+	};
+	static char *kwlist[] = {
+		"type",
+		"config",
+		"sample_freq",
+		"sample_period",
+		"sample_type",
+		"read_format",
+		"disabled",
+		"inherit",
+		"pinned",
+		"exclusive",
+		"exclude_user",
+		"exclude_kernel",
+		"exclude_hv",
+		"exclude_idle",
+		"mmap",
+		"comm",
+		"freq",
+		"inherit_stat",
+		"enable_on_exec",
+		"task",
+		"watermark",
+		"precise_ip",
+		"mmap_data",
+		"sample_id_all",
+		"wakeup_events",
+		"bp_type",
+		"bp_addr",
+		"bp_len",
+		 NULL
+	};
+	u64 sample_period = 0;
+	u32 disabled = 0,
+	    inherit = 0,
+	    pinned = 0,
+	    exclusive = 0,
+	    exclude_user = 0,
+	    exclude_kernel = 0,
+	    exclude_hv = 0,
+	    exclude_idle = 0,
+	    mmap = 0,
+	    comm = 0,
+	    freq = 1,
+	    inherit_stat = 0,
+	    enable_on_exec = 0,
+	    task = 0,
+	    watermark = 0,
+	    precise_ip = 0,
+	    mmap_data = 0,
+	    sample_id_all = 1;
+	int idx = 0;
+
+	if (!PyArg_ParseTupleAndKeywords(args, kwargs,
+					 "|iKiKKiiiiiiiiiiiiiiiiiiiiiKK", kwlist,
+					 &attr.type, &attr.config, &attr.sample_freq,
+					 &sample_period, &attr.sample_type,
+					 &attr.read_format, &disabled, &inherit,
+					 &pinned, &exclusive, &exclude_user,
+					 &exclude_kernel, &exclude_hv, &exclude_idle,
+					 &mmap, &comm, &freq, &inherit_stat,
+					 &enable_on_exec, &task, &watermark,
+					 &precise_ip, &mmap_data, &sample_id_all,
+					 &attr.wakeup_events, &attr.bp_type,
+					 &attr.bp_addr, &attr.bp_len, &idx))
+		return -1;
+
+	/* union... */
+	if (sample_period != 0) {
+		if (attr.sample_freq != 0)
+			return -1; /* FIXME: throw right exception */
+		attr.sample_period = sample_period;
+	}
+
+	/* Bitfields */
+	attr.disabled	    = disabled;
+	attr.inherit	    = inherit;
+	attr.pinned	    = pinned;
+	attr.exclusive	    = exclusive;
+	attr.exclude_user   = exclude_user;
+	attr.exclude_kernel = exclude_kernel;
+	attr.exclude_hv	    = exclude_hv;
+	attr.exclude_idle   = exclude_idle;
+	attr.mmap	    = mmap;
+	attr.comm	    = comm;
+	attr.freq	    = freq;
+	attr.inherit_stat   = inherit_stat;
+	attr.enable_on_exec = enable_on_exec;
+	attr.task	    = task;
+	attr.watermark	    = watermark;
+	attr.precise_ip	    = precise_ip;
+	attr.mmap_data	    = mmap_data;
+	attr.sample_id_all  = sample_id_all;
+
+	perf_evsel__init(&pevsel->evsel, &attr, idx);
+	return 0;
+}
+
+static void pyrf_evsel__delete(struct pyrf_evsel *pevsel)
+{
+	perf_evsel__exit(&pevsel->evsel);
+	pevsel->ob_type->tp_free((PyObject*)pevsel);
+}
+
+static PyObject *pyrf_evsel__open(struct pyrf_evsel *pevsel,
+				  PyObject *args, PyObject *kwargs)
+{
+	struct perf_evsel *evsel = &pevsel->evsel;
+	struct cpu_map *cpus = NULL;
+	struct thread_map *threads = NULL;
+	PyObject *pcpus = NULL, *pthreads = NULL;
+	int group = 0, inherit = 0;
+	static char *kwlist[] = { "cpus", "threads", "group", "inherit", NULL };
+
+	if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|OOii", kwlist,
+					 &pcpus, &pthreads, &group, &inherit))
+		return NULL;
+
+	if (pthreads != NULL)
+		threads = ((struct pyrf_thread_map *)pthreads)->threads;
+
+	if (pcpus != NULL)
+		cpus = ((struct pyrf_cpu_map *)pcpus)->cpus;
+
+	evsel->attr.inherit = inherit;
+	/*
+	 * This will group just the fds for this single evsel, to group
+	 * multiple events, use evlist.open().
+	 */
+	if (perf_evsel__open(evsel, cpus, threads) < 0) {
+		PyErr_SetFromErrno(PyExc_OSError);
+		return NULL;
+	}
+
+	Py_INCREF(Py_None);
+	return Py_None;
+}
+
+static PyMethodDef pyrf_evsel__methods[] = {
+	{
+		.ml_name  = "open",
+		.ml_meth  = (PyCFunction)pyrf_evsel__open,
+		.ml_flags = METH_VARARGS | METH_KEYWORDS,
+		.ml_doc	  = PyDoc_STR("open the event selector file descriptor table.")
+	},
+	{ .ml_name = NULL, }
+};
+
+static char pyrf_evsel__doc[] = PyDoc_STR("perf event selector list object.");
+
+static PyTypeObject pyrf_evsel__type = {
+	PyVarObject_HEAD_INIT(NULL, 0)
+	.tp_name	= "perf.evsel",
+	.tp_basicsize	= sizeof(struct pyrf_evsel),
+	.tp_dealloc	= (destructor)pyrf_evsel__delete,
+	.tp_flags	= Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
+	.tp_doc		= pyrf_evsel__doc,
+	.tp_methods	= pyrf_evsel__methods,
+	.tp_init	= (initproc)pyrf_evsel__init,
+};
+
+static int pyrf_evsel__setup_types(void)
+{
+	pyrf_evsel__type.tp_new = PyType_GenericNew;
+	return PyType_Ready(&pyrf_evsel__type);
+}
+
+struct pyrf_evlist {
+	PyObject_HEAD
+
+	struct perf_evlist evlist;
+};
+
+static int pyrf_evlist__init(struct pyrf_evlist *pevlist,
+			     PyObject *args, PyObject *kwargs __maybe_unused)
+{
+	PyObject *pcpus = NULL, *pthreads = NULL;
+	struct cpu_map *cpus;
+	struct thread_map *threads;
+
+	if (!PyArg_ParseTuple(args, "OO", &pcpus, &pthreads))
+		return -1;
+
+	threads = ((struct pyrf_thread_map *)pthreads)->threads;
+	cpus = ((struct pyrf_cpu_map *)pcpus)->cpus;
+	perf_evlist__init(&pevlist->evlist, cpus, threads);
+	return 0;
+}
+
+static void pyrf_evlist__delete(struct pyrf_evlist *pevlist)
+{
+	perf_evlist__exit(&pevlist->evlist);
+	pevlist->ob_type->tp_free((PyObject*)pevlist);
+}
+
+static PyObject *pyrf_evlist__mmap(struct pyrf_evlist *pevlist,
+				   PyObject *args, PyObject *kwargs)
+{
+	struct perf_evlist *evlist = &pevlist->evlist;
+	static char *kwlist[] = { "pages", "overwrite", NULL };
+	int pages = 128, overwrite = false;
+
+	if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|ii", kwlist,
+					 &pages, &overwrite))
+		return NULL;
+
+	if (perf_evlist__mmap(evlist, pages, overwrite) < 0) {
+		PyErr_SetFromErrno(PyExc_OSError);
+		return NULL;
+	}
+
+	Py_INCREF(Py_None);
+	return Py_None;
+}
+
+static PyObject *pyrf_evlist__poll(struct pyrf_evlist *pevlist,
+				   PyObject *args, PyObject *kwargs)
+{
+	struct perf_evlist *evlist = &pevlist->evlist;
+	static char *kwlist[] = { "timeout", NULL };
+	int timeout = -1, n;
+
+	if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|i", kwlist, &timeout))
+		return NULL;
+
+	n = poll(evlist->pollfd, evlist->nr_fds, timeout);
+	if (n < 0) {
+		PyErr_SetFromErrno(PyExc_OSError);
+		return NULL;
+	}
+
+	return Py_BuildValue("i", n);
+}
+
+static PyObject *pyrf_evlist__get_pollfd(struct pyrf_evlist *pevlist,
+					 PyObject *args __maybe_unused,
+					 PyObject *kwargs __maybe_unused)
+{
+	struct perf_evlist *evlist = &pevlist->evlist;
+        PyObject *list = PyList_New(0);
+	int i;
+
+	for (i = 0; i < evlist->nr_fds; ++i) {
+		PyObject *file;
+		FILE *fp = fdopen(evlist->pollfd[i].fd, "r");
+
+		if (fp == NULL)
+			goto free_list;
+
+		file = PyFile_FromFile(fp, "perf", "r", NULL);
+		if (file == NULL)
+			goto free_list;
+
+		if (PyList_Append(list, file) != 0) {
+			Py_DECREF(file);
+			goto free_list;
+		}
+			
+		Py_DECREF(file);
+	}
+
+	return list;
+free_list:
+	return PyErr_NoMemory();
+}
+
+
+static PyObject *pyrf_evlist__add(struct pyrf_evlist *pevlist,
+				  PyObject *args,
+				  PyObject *kwargs __maybe_unused)
+{
+	struct perf_evlist *evlist = &pevlist->evlist;
+	PyObject *pevsel;
+	struct perf_evsel *evsel;
+
+	if (!PyArg_ParseTuple(args, "O", &pevsel))
+		return NULL;
+
+	Py_INCREF(pevsel);
+	evsel = &((struct pyrf_evsel *)pevsel)->evsel;
+	evsel->idx = evlist->nr_entries;
+	perf_evlist__add(evlist, evsel);
+
+	return Py_BuildValue("i", evlist->nr_entries);
+}
+
+static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
+					  PyObject *args, PyObject *kwargs)
+{
+	struct perf_evlist *evlist = &pevlist->evlist;
+	union perf_event *event;
+	int sample_id_all = 1, cpu;
+	static char *kwlist[] = { "cpu", "sample_id_all", NULL };
+	int err;
+
+	if (!PyArg_ParseTupleAndKeywords(args, kwargs, "i|i", kwlist,
+					 &cpu, &sample_id_all))
+		return NULL;
+
+	event = perf_evlist__mmap_read(evlist, cpu);
+	if (event != NULL) {
+		PyObject *pyevent = pyrf_event__new(event);
+		struct pyrf_event *pevent = (struct pyrf_event *)pyevent;
+
+		perf_evlist__mmap_consume(evlist, cpu);
+
+		if (pyevent == NULL)
+			return PyErr_NoMemory();
+
+		err = perf_evlist__parse_sample(evlist, event, &pevent->sample);
+		if (err)
+			return PyErr_Format(PyExc_OSError,
+					    "perf: can't parse sample, err=%d", err);
+		return pyevent;
+	}
+
+	Py_INCREF(Py_None);
+	return Py_None;
+}
+
+static PyObject *pyrf_evlist__open(struct pyrf_evlist *pevlist,
+				   PyObject *args, PyObject *kwargs)
+{
+	struct perf_evlist *evlist = &pevlist->evlist;
+	int group = 0;
+	static char *kwlist[] = { "group", NULL };
+
+	if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|OOii", kwlist, &group))
+		return NULL;
+
+	if (group)
+		perf_evlist__set_leader(evlist);
+
+	if (perf_evlist__open(evlist) < 0) {
+		PyErr_SetFromErrno(PyExc_OSError);
+		return NULL;
+	}
+
+	Py_INCREF(Py_None);
+	return Py_None;
+}
+
+static PyMethodDef pyrf_evlist__methods[] = {
+	{
+		.ml_name  = "mmap",
+		.ml_meth  = (PyCFunction)pyrf_evlist__mmap,
+		.ml_flags = METH_VARARGS | METH_KEYWORDS,
+		.ml_doc	  = PyDoc_STR("mmap the file descriptor table.")
+	},
+	{
+		.ml_name  = "open",
+		.ml_meth  = (PyCFunction)pyrf_evlist__open,
+		.ml_flags = METH_VARARGS | METH_KEYWORDS,
+		.ml_doc	  = PyDoc_STR("open the file descriptors.")
+	},
+	{
+		.ml_name  = "poll",
+		.ml_meth  = (PyCFunction)pyrf_evlist__poll,
+		.ml_flags = METH_VARARGS | METH_KEYWORDS,
+		.ml_doc	  = PyDoc_STR("poll the file descriptor table.")
+	},
+	{
+		.ml_name  = "get_pollfd",
+		.ml_meth  = (PyCFunction)pyrf_evlist__get_pollfd,
+		.ml_flags = METH_VARARGS | METH_KEYWORDS,
+		.ml_doc	  = PyDoc_STR("get the poll file descriptor table.")
+	},
+	{
+		.ml_name  = "add",
+		.ml_meth  = (PyCFunction)pyrf_evlist__add,
+		.ml_flags = METH_VARARGS | METH_KEYWORDS,
+		.ml_doc	  = PyDoc_STR("adds an event selector to the list.")
+	},
+	{
+		.ml_name  = "read_on_cpu",
+		.ml_meth  = (PyCFunction)pyrf_evlist__read_on_cpu,
+		.ml_flags = METH_VARARGS | METH_KEYWORDS,
+		.ml_doc	  = PyDoc_STR("reads an event.")
+	},
+	{ .ml_name = NULL, }
+};
+
+static Py_ssize_t pyrf_evlist__length(PyObject *obj)
+{
+	struct pyrf_evlist *pevlist = (void *)obj;
+
+	return pevlist->evlist.nr_entries;
+}
+
+static PyObject *pyrf_evlist__item(PyObject *obj, Py_ssize_t i)
+{
+	struct pyrf_evlist *pevlist = (void *)obj;
+	struct perf_evsel *pos;
+
+	if (i >= pevlist->evlist.nr_entries)
+		return NULL;
+
+	evlist__for_each(&pevlist->evlist, pos) {
+		if (i-- == 0)
+			break;
+	}
+
+	return Py_BuildValue("O", container_of(pos, struct pyrf_evsel, evsel));
+}
+
+static PySequenceMethods pyrf_evlist__sequence_methods = {
+	.sq_length = pyrf_evlist__length,
+	.sq_item   = pyrf_evlist__item,
+};
+
+static char pyrf_evlist__doc[] = PyDoc_STR("perf event selector list object.");
+
+static PyTypeObject pyrf_evlist__type = {
+	PyVarObject_HEAD_INIT(NULL, 0)
+	.tp_name	= "perf.evlist",
+	.tp_basicsize	= sizeof(struct pyrf_evlist),
+	.tp_dealloc	= (destructor)pyrf_evlist__delete,
+	.tp_flags	= Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
+	.tp_as_sequence	= &pyrf_evlist__sequence_methods,
+	.tp_doc		= pyrf_evlist__doc,
+	.tp_methods	= pyrf_evlist__methods,
+	.tp_init	= (initproc)pyrf_evlist__init,
+};
+
+static int pyrf_evlist__setup_types(void)
+{
+	pyrf_evlist__type.tp_new = PyType_GenericNew;
+	return PyType_Ready(&pyrf_evlist__type);
+}
+
+static struct {
+	const char *name;
+	int	    value;
+} perf__constants[] = {
+	{ "TYPE_HARDWARE",   PERF_TYPE_HARDWARE },
+	{ "TYPE_SOFTWARE",   PERF_TYPE_SOFTWARE },
+	{ "TYPE_TRACEPOINT", PERF_TYPE_TRACEPOINT },
+	{ "TYPE_HW_CACHE",   PERF_TYPE_HW_CACHE },
+	{ "TYPE_RAW",	     PERF_TYPE_RAW },
+	{ "TYPE_BREAKPOINT", PERF_TYPE_BREAKPOINT },
+
+	{ "COUNT_HW_CPU_CYCLES",	  PERF_COUNT_HW_CPU_CYCLES },
+	{ "COUNT_HW_INSTRUCTIONS",	  PERF_COUNT_HW_INSTRUCTIONS },
+	{ "COUNT_HW_CACHE_REFERENCES",	  PERF_COUNT_HW_CACHE_REFERENCES },
+	{ "COUNT_HW_CACHE_MISSES",	  PERF_COUNT_HW_CACHE_MISSES },
+	{ "COUNT_HW_BRANCH_INSTRUCTIONS", PERF_COUNT_HW_BRANCH_INSTRUCTIONS },
+	{ "COUNT_HW_BRANCH_MISSES",	  PERF_COUNT_HW_BRANCH_MISSES },
+	{ "COUNT_HW_BUS_CYCLES",	  PERF_COUNT_HW_BUS_CYCLES },
+	{ "COUNT_HW_CACHE_L1D",		  PERF_COUNT_HW_CACHE_L1D },
+	{ "COUNT_HW_CACHE_L1I",		  PERF_COUNT_HW_CACHE_L1I },
+	{ "COUNT_HW_CACHE_LL",	  	  PERF_COUNT_HW_CACHE_LL },
+	{ "COUNT_HW_CACHE_DTLB",	  PERF_COUNT_HW_CACHE_DTLB },
+	{ "COUNT_HW_CACHE_ITLB",	  PERF_COUNT_HW_CACHE_ITLB },
+	{ "COUNT_HW_CACHE_BPU",		  PERF_COUNT_HW_CACHE_BPU },
+	{ "COUNT_HW_CACHE_OP_READ",	  PERF_COUNT_HW_CACHE_OP_READ },
+	{ "COUNT_HW_CACHE_OP_WRITE",	  PERF_COUNT_HW_CACHE_OP_WRITE },
+	{ "COUNT_HW_CACHE_OP_PREFETCH",	  PERF_COUNT_HW_CACHE_OP_PREFETCH },
+	{ "COUNT_HW_CACHE_RESULT_ACCESS", PERF_COUNT_HW_CACHE_RESULT_ACCESS },
+	{ "COUNT_HW_CACHE_RESULT_MISS",   PERF_COUNT_HW_CACHE_RESULT_MISS },
+
+	{ "COUNT_HW_STALLED_CYCLES_FRONTEND",	  PERF_COUNT_HW_STALLED_CYCLES_FRONTEND },
+	{ "COUNT_HW_STALLED_CYCLES_BACKEND",	  PERF_COUNT_HW_STALLED_CYCLES_BACKEND },
+
+	{ "COUNT_SW_CPU_CLOCK",	       PERF_COUNT_SW_CPU_CLOCK },
+	{ "COUNT_SW_TASK_CLOCK",       PERF_COUNT_SW_TASK_CLOCK },
+	{ "COUNT_SW_PAGE_FAULTS",      PERF_COUNT_SW_PAGE_FAULTS },
+	{ "COUNT_SW_CONTEXT_SWITCHES", PERF_COUNT_SW_CONTEXT_SWITCHES },
+	{ "COUNT_SW_CPU_MIGRATIONS",   PERF_COUNT_SW_CPU_MIGRATIONS },
+	{ "COUNT_SW_PAGE_FAULTS_MIN",  PERF_COUNT_SW_PAGE_FAULTS_MIN },
+	{ "COUNT_SW_PAGE_FAULTS_MAJ",  PERF_COUNT_SW_PAGE_FAULTS_MAJ },
+	{ "COUNT_SW_ALIGNMENT_FAULTS", PERF_COUNT_SW_ALIGNMENT_FAULTS },
+	{ "COUNT_SW_EMULATION_FAULTS", PERF_COUNT_SW_EMULATION_FAULTS },
+	{ "COUNT_SW_DUMMY",            PERF_COUNT_SW_DUMMY },
+
+	{ "SAMPLE_IP",	      PERF_SAMPLE_IP },
+	{ "SAMPLE_TID",	      PERF_SAMPLE_TID },
+	{ "SAMPLE_TIME",      PERF_SAMPLE_TIME },
+	{ "SAMPLE_ADDR",      PERF_SAMPLE_ADDR },
+	{ "SAMPLE_READ",      PERF_SAMPLE_READ },
+	{ "SAMPLE_CALLCHAIN", PERF_SAMPLE_CALLCHAIN },
+	{ "SAMPLE_ID",	      PERF_SAMPLE_ID },
+	{ "SAMPLE_CPU",	      PERF_SAMPLE_CPU },
+	{ "SAMPLE_PERIOD",    PERF_SAMPLE_PERIOD },
+	{ "SAMPLE_STREAM_ID", PERF_SAMPLE_STREAM_ID },
+	{ "SAMPLE_RAW",	      PERF_SAMPLE_RAW },
+
+	{ "FORMAT_TOTAL_TIME_ENABLED", PERF_FORMAT_TOTAL_TIME_ENABLED },
+	{ "FORMAT_TOTAL_TIME_RUNNING", PERF_FORMAT_TOTAL_TIME_RUNNING },
+	{ "FORMAT_ID",		       PERF_FORMAT_ID },
+	{ "FORMAT_GROUP",	       PERF_FORMAT_GROUP },
+
+	{ "RECORD_MMAP",       PERF_RECORD_MMAP },
+	{ "RECORD_LOST",       PERF_RECORD_LOST },
+	{ "RECORD_COMM",       PERF_RECORD_COMM },
+	{ "RECORD_EXIT",       PERF_RECORD_EXIT },
+	{ "RECORD_THROTTLE",   PERF_RECORD_THROTTLE },
+	{ "RECORD_UNTHROTTLE", PERF_RECORD_UNTHROTTLE },
+	{ "RECORD_FORK",       PERF_RECORD_FORK },
+	{ "RECORD_READ",       PERF_RECORD_READ },
+	{ "RECORD_SAMPLE",     PERF_RECORD_SAMPLE },
+	{ .name = NULL, },
+};
+
+static PyMethodDef perf__methods[] = {
+	{ .ml_name = NULL, }
+};
+
+PyMODINIT_FUNC initperf(void)
+{
+	PyObject *obj;
+	int i;
+	PyObject *dict, *module = Py_InitModule("perf", perf__methods);
+
+	if (module == NULL ||
+	    pyrf_event__setup_types() < 0 ||
+	    pyrf_evlist__setup_types() < 0 ||
+	    pyrf_evsel__setup_types() < 0 ||
+	    pyrf_thread_map__setup_types() < 0 ||
+	    pyrf_cpu_map__setup_types() < 0)
+		return;
+
+	/* The page_size is placed in util object. */
+	page_size = sysconf(_SC_PAGE_SIZE);
+
+	Py_INCREF(&pyrf_evlist__type);
+	PyModule_AddObject(module, "evlist", (PyObject*)&pyrf_evlist__type);
+
+	Py_INCREF(&pyrf_evsel__type);
+	PyModule_AddObject(module, "evsel", (PyObject*)&pyrf_evsel__type);
+
+	Py_INCREF(&pyrf_thread_map__type);
+	PyModule_AddObject(module, "thread_map", (PyObject*)&pyrf_thread_map__type);
+
+	Py_INCREF(&pyrf_cpu_map__type);
+	PyModule_AddObject(module, "cpu_map", (PyObject*)&pyrf_cpu_map__type);
+
+	dict = PyModule_GetDict(module);
+	if (dict == NULL)
+		goto error;
+
+	for (i = 0; perf__constants[i].name != NULL; i++) {
+		obj = PyInt_FromLong(perf__constants[i].value);
+		if (obj == NULL)
+			goto error;
+		PyDict_SetItemString(dict, perf__constants[i].name, obj);
+		Py_DECREF(obj);
+	}
+
+error:
+	if (PyErr_Occurred())
+		PyErr_SetString(PyExc_ImportError, "perf: Init failed!");
+}
+
+/*
+ * Dummy, to avoid dragging all the test_attr infrastructure in the python
+ * binding.
+ */
+void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu,
+                     int fd, int group_fd, unsigned long flags)
+{
+}
diff --git a/tools/perf/util/rblist.c b/tools/perf/util/rblist.c
new file mode 100644
index 00000000000..0dfe27d9945
--- /dev/null
+++ b/tools/perf/util/rblist.c
@@ -0,0 +1,128 @@
+/*
+ * Based on strlist.c by:
+ * (c) 2009 Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Licensed under the GPLv2.
+ */
+
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+
+#include "rblist.h"
+
+int rblist__add_node(struct rblist *rblist, const void *new_entry)
+{
+	struct rb_node **p = &rblist->entries.rb_node;
+	struct rb_node *parent = NULL, *new_node;
+
+	while (*p != NULL) {
+		int rc;
+
+		parent = *p;
+
+		rc = rblist->node_cmp(parent, new_entry);
+		if (rc > 0)
+			p = &(*p)->rb_left;
+		else if (rc < 0)
+			p = &(*p)->rb_right;
+		else
+			return -EEXIST;
+	}
+
+	new_node = rblist->node_new(rblist, new_entry);
+	if (new_node == NULL)
+		return -ENOMEM;
+
+	rb_link_node(new_node, parent, p);
+	rb_insert_color(new_node, &rblist->entries);
+	++rblist->nr_entries;
+
+	return 0;
+}
+
+void rblist__remove_node(struct rblist *rblist, struct rb_node *rb_node)
+{
+	rb_erase(rb_node, &rblist->entries);
+	--rblist->nr_entries;
+	rblist->node_delete(rblist, rb_node);
+}
+
+static struct rb_node *__rblist__findnew(struct rblist *rblist,
+					 const void *entry,
+					 bool create)
+{
+	struct rb_node **p = &rblist->entries.rb_node;
+	struct rb_node *parent = NULL, *new_node = NULL;
+
+	while (*p != NULL) {
+		int rc;
+
+		parent = *p;
+
+		rc = rblist->node_cmp(parent, entry);
+		if (rc > 0)
+			p = &(*p)->rb_left;
+		else if (rc < 0)
+			p = &(*p)->rb_right;
+		else
+			return parent;
+	}
+
+	if (create) {
+		new_node = rblist->node_new(rblist, entry);
+		if (new_node) {
+			rb_link_node(new_node, parent, p);
+			rb_insert_color(new_node, &rblist->entries);
+			++rblist->nr_entries;
+		}
+	}
+
+	return new_node;
+}
+
+struct rb_node *rblist__find(struct rblist *rblist, const void *entry)
+{
+	return __rblist__findnew(rblist, entry, false);
+}
+
+struct rb_node *rblist__findnew(struct rblist *rblist, const void *entry)
+{
+	return __rblist__findnew(rblist, entry, true);
+}
+
+void rblist__init(struct rblist *rblist)
+{
+	if (rblist != NULL) {
+		rblist->entries	 = RB_ROOT;
+		rblist->nr_entries = 0;
+	}
+
+	return;
+}
+
+void rblist__delete(struct rblist *rblist)
+{
+	if (rblist != NULL) {
+		struct rb_node *pos, *next = rb_first(&rblist->entries);
+
+		while (next) {
+			pos = next;
+			next = rb_next(pos);
+			rblist__remove_node(rblist, pos);
+		}
+		free(rblist);
+	}
+}
+
+struct rb_node *rblist__entry(const struct rblist *rblist, unsigned int idx)
+{
+	struct rb_node *node;
+
+	for (node = rb_first(&rblist->entries); node; node = rb_next(node)) {
+		if (!idx--)
+			return node;
+	}
+
+	return NULL;
+}
diff --git a/tools/perf/util/rblist.h b/tools/perf/util/rblist.h
new file mode 100644
index 00000000000..ff9913b994c
--- /dev/null
+++ b/tools/perf/util/rblist.h
@@ -0,0 +1,48 @@
+#ifndef __PERF_RBLIST_H
+#define __PERF_RBLIST_H
+
+#include <linux/rbtree.h>
+#include <stdbool.h>
+
+/*
+ * create node structs of the form:
+ * struct my_node {
+ *     struct rb_node rb_node;
+ *     ... my data ...
+ * };
+ *
+ * create list structs of the form:
+ * struct mylist {
+ *     struct rblist rblist;
+ *     ... my data ...
+ * };
+ */
+
+struct rblist {
+	struct rb_root entries;
+	unsigned int   nr_entries;
+
+	int (*node_cmp)(struct rb_node *rbn, const void *entry);
+	struct rb_node *(*node_new)(struct rblist *rlist, const void *new_entry);
+	void (*node_delete)(struct rblist *rblist, struct rb_node *rb_node);
+};
+
+void rblist__init(struct rblist *rblist);
+void rblist__delete(struct rblist *rblist);
+int rblist__add_node(struct rblist *rblist, const void *new_entry);
+void rblist__remove_node(struct rblist *rblist, struct rb_node *rb_node);
+struct rb_node *rblist__find(struct rblist *rblist, const void *entry);
+struct rb_node *rblist__findnew(struct rblist *rblist, const void *entry);
+struct rb_node *rblist__entry(const struct rblist *rblist, unsigned int idx);
+
+static inline bool rblist__empty(const struct rblist *rblist)
+{
+	return rblist->nr_entries == 0;
+}
+
+static inline unsigned int rblist__nr_entries(const struct rblist *rblist)
+{
+	return rblist->nr_entries;
+}
+
+#endif /* __PERF_RBLIST_H */
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
new file mode 100644
index 00000000000..049e0a09ccd
--- /dev/null
+++ b/tools/perf/util/record.c
@@ -0,0 +1,215 @@
+#include "evlist.h"
+#include "evsel.h"
+#include "cpumap.h"
+#include "parse-events.h"
+#include <api/fs/fs.h>
+#include "util.h"
+
+typedef void (*setup_probe_fn_t)(struct perf_evsel *evsel);
+
+static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str)
+{
+	struct perf_evlist *evlist;
+	struct perf_evsel *evsel;
+	int err = -EAGAIN, fd;
+
+	evlist = perf_evlist__new();
+	if (!evlist)
+		return -ENOMEM;
+
+	if (parse_events(evlist, str))
+		goto out_delete;
+
+	evsel = perf_evlist__first(evlist);
+
+	fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1, 0);
+	if (fd < 0)
+		goto out_delete;
+	close(fd);
+
+	fn(evsel);
+
+	fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1, 0);
+	if (fd < 0) {
+		if (errno == EINVAL)
+			err = -EINVAL;
+		goto out_delete;
+	}
+	close(fd);
+	err = 0;
+
+out_delete:
+	perf_evlist__delete(evlist);
+	return err;
+}
+
+static bool perf_probe_api(setup_probe_fn_t fn)
+{
+	const char *try[] = {"cycles:u", "instructions:u", "cpu-clock", NULL};
+	struct cpu_map *cpus;
+	int cpu, ret, i = 0;
+
+	cpus = cpu_map__new(NULL);
+	if (!cpus)
+		return false;
+	cpu = cpus->map[0];
+	cpu_map__delete(cpus);
+
+	do {
+		ret = perf_do_probe_api(fn, cpu, try[i++]);
+		if (!ret)
+			return true;
+	} while (ret == -EAGAIN && try[i]);
+
+	return false;
+}
+
+static void perf_probe_sample_identifier(struct perf_evsel *evsel)
+{
+	evsel->attr.sample_type |= PERF_SAMPLE_IDENTIFIER;
+}
+
+bool perf_can_sample_identifier(void)
+{
+	return perf_probe_api(perf_probe_sample_identifier);
+}
+
+void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts)
+{
+	struct perf_evsel *evsel;
+	bool use_sample_identifier = false;
+
+	/*
+	 * Set the evsel leader links before we configure attributes,
+	 * since some might depend on this info.
+	 */
+	if (opts->group)
+		perf_evlist__set_leader(evlist);
+
+	if (evlist->cpus->map[0] < 0)
+		opts->no_inherit = true;
+
+	evlist__for_each(evlist, evsel)
+		perf_evsel__config(evsel, opts);
+
+	if (evlist->nr_entries > 1) {
+		struct perf_evsel *first = perf_evlist__first(evlist);
+
+		evlist__for_each(evlist, evsel) {
+			if (evsel->attr.sample_type == first->attr.sample_type)
+				continue;
+			use_sample_identifier = perf_can_sample_identifier();
+			break;
+		}
+		evlist__for_each(evlist, evsel)
+			perf_evsel__set_sample_id(evsel, use_sample_identifier);
+	}
+
+	perf_evlist__set_id_pos(evlist);
+}
+
+static int get_max_rate(unsigned int *rate)
+{
+	char path[PATH_MAX];
+	const char *procfs = procfs__mountpoint();
+
+	if (!procfs)
+		return -1;
+
+	snprintf(path, PATH_MAX,
+		 "%s/sys/kernel/perf_event_max_sample_rate", procfs);
+
+	return filename__read_int(path, (int *) rate);
+}
+
+static int record_opts__config_freq(struct record_opts *opts)
+{
+	bool user_freq = opts->user_freq != UINT_MAX;
+	unsigned int max_rate;
+
+	if (opts->user_interval != ULLONG_MAX)
+		opts->default_interval = opts->user_interval;
+	if (user_freq)
+		opts->freq = opts->user_freq;
+
+	/*
+	 * User specified count overrides default frequency.
+	 */
+	if (opts->default_interval)
+		opts->freq = 0;
+	else if (opts->freq) {
+		opts->default_interval = opts->freq;
+	} else {
+		pr_err("frequency and count are zero, aborting\n");
+		return -1;
+	}
+
+	if (get_max_rate(&max_rate))
+		return 0;
+
+	/*
+	 * User specified frequency is over current maximum.
+	 */
+	if (user_freq && (max_rate < opts->freq)) {
+		pr_err("Maximum frequency rate (%u) reached.\n"
+		   "Please use -F freq option with lower value or consider\n"
+		   "tweaking /proc/sys/kernel/perf_event_max_sample_rate.\n",
+		   max_rate);
+		return -1;
+	}
+
+	/*
+	 * Default frequency is over current maximum.
+	 */
+	if (max_rate < opts->freq) {
+		pr_warning("Lowering default frequency rate to %u.\n"
+			   "Please consider tweaking "
+			   "/proc/sys/kernel/perf_event_max_sample_rate.\n",
+			   max_rate);
+		opts->freq = max_rate;
+	}
+
+	return 0;
+}
+
+int record_opts__config(struct record_opts *opts)
+{
+	return record_opts__config_freq(opts);
+}
+
+bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str)
+{
+	struct perf_evlist *temp_evlist;
+	struct perf_evsel *evsel;
+	int err, fd, cpu;
+	bool ret = false;
+
+	temp_evlist = perf_evlist__new();
+	if (!temp_evlist)
+		return false;
+
+	err = parse_events(temp_evlist, str);
+	if (err)
+		goto out_delete;
+
+	evsel = perf_evlist__last(temp_evlist);
+
+	if (!evlist || cpu_map__empty(evlist->cpus)) {
+		struct cpu_map *cpus = cpu_map__new(NULL);
+
+		cpu =  cpus ? cpus->map[0] : 0;
+		cpu_map__delete(cpus);
+	} else {
+		cpu = evlist->cpus->map[0];
+	}
+
+	fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1, 0);
+	if (fd >= 0) {
+		close(fd);
+		ret = true;
+	}
+
+out_delete:
+	perf_evlist__delete(temp_evlist);
+	return ret;
+}
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index b059dc50cc2..af7da565a75 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -1,5 +1,5 @@
 /*
- * trace-event-perl.  Feed perf trace events to an embedded Perl interpreter.
+ * trace-event-perl.  Feed perf script events to an embedded Perl interpreter.
  *
  * Copyright (C) 2009 Tom Zanussi <tzanussi@gmail.com>
  *
@@ -25,13 +25,16 @@
 #include <ctype.h>
 #include <errno.h>
 
-#include "../../perf.h"
 #include "../util.h"
-#include "../trace-event.h"
-
 #include <EXTERN.h>
 #include <perl.h>
 
+#include "../../perf.h"
+#include "../thread.h"
+#include "../event.h"
+#include "../trace-event.h"
+#include "../evsel.h"
+
 void boot_Perf__Trace__Context(pTHX_ CV *cv);
 void boot_DynaLoader(pTHX_ CV *cv);
 typedef PerlInterpreter * INTERP;
@@ -53,7 +56,7 @@ INTERP my_perl;
 #define FTRACE_MAX_EVENT				\
 	((1 << (sizeof(unsigned short) * 8)) - 1)
 
-struct event *events[FTRACE_MAX_EVENT];
+struct event_format *events[FTRACE_MAX_EVENT];
 
 extern struct scripting_context *scripting_context;
 
@@ -178,7 +181,7 @@ static void define_flag_field(const char *ev_name,
 	LEAVE;
 }
 
-static void define_event_symbols(struct event *event,
+static void define_event_symbols(struct event_format *event,
 				 const char *ev_name,
 				 struct print_arg *args)
 {
@@ -191,8 +194,7 @@ static void define_event_symbols(struct event *event,
 		zero_flag_atom = 0;
 		break;
 	case PRINT_FIELD:
-		if (cur_field_name)
-			free(cur_field_name);
+		free(cur_field_name);
 		cur_field_name = strdup(args->field.name);
 		break;
 	case PRINT_FLAGS:
@@ -206,7 +208,14 @@ static void define_event_symbols(struct event *event,
 		define_symbolic_values(args->symbol.symbols, ev_name,
 				       cur_field_name);
 		break;
+	case PRINT_HEX:
+		define_event_symbols(event, ev_name, args->hex.field);
+		define_event_symbols(event, ev_name, args->hex.size);
+		break;
+	case PRINT_BSTRING:
+	case PRINT_DYNAMIC_ARRAY:
 	case PRINT_STRING:
+	case PRINT_BITMASK:
 		break;
 	case PRINT_TYPE:
 		define_event_symbols(event, ev_name, args->typecast.item);
@@ -217,7 +226,9 @@ static void define_event_symbols(struct event *event,
 		define_event_symbols(event, ev_name, args->op.left);
 		define_event_symbols(event, ev_name, args->op.right);
 		break;
+	case PRINT_FUNC:
 	default:
+		pr_err("Unsupported print arg type\n");
 		/* we should warn... */
 		return;
 	}
@@ -226,15 +237,16 @@ static void define_event_symbols(struct event *event,
 		define_event_symbols(event, ev_name, args->next);
 }
 
-static inline struct event *find_cache_event(int type)
+static inline struct event_format *find_cache_event(struct perf_evsel *evsel)
 {
 	static char ev_name[256];
-	struct event *event;
+	struct event_format *event;
+	int type = evsel->attr.config;
 
 	if (events[type])
 		return events[type];
 
-	events[type] = event = trace_find_event(type);
+	events[type] = event = evsel->tp_format;
 	if (!event)
 		return NULL;
 
@@ -245,27 +257,31 @@ static inline struct event *find_cache_event(int type)
 	return event;
 }
 
-static void perl_process_event(int cpu, void *data,
-			       int size __unused,
-			       unsigned long long nsecs, char *comm)
+static void perl_process_tracepoint(struct perf_sample *sample,
+				    struct perf_evsel *evsel,
+				    struct thread *thread)
 {
 	struct format_field *field;
 	static char handler[256];
 	unsigned long long val;
 	unsigned long s, ns;
-	struct event *event;
-	int type;
+	struct event_format *event;
 	int pid;
+	int cpu = sample->cpu;
+	void *data = sample->raw_data;
+	unsigned long long nsecs = sample->time;
+	const char *comm = thread__comm_str(thread);
 
 	dSP;
 
-	type = trace_parse_common_type(data);
+	if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
+		return;
 
-	event = find_cache_event(type);
+	event = find_cache_event(evsel);
 	if (!event)
-		die("ug! no event found for type %d", type);
+		die("ug! no event found for type %" PRIu64, (u64)evsel->attr.config);
 
-	pid = trace_parse_common_pid(data);
+	pid = raw_field_value(event, "common_pid", data);
 
 	sprintf(handler, "%s::%s", event->system, event->name);
 
@@ -273,6 +289,7 @@ static void perl_process_event(int cpu, void *data,
 	ns = nsecs - s * NSECS_PER_SEC;
 
 	scripting_context->event_data = data;
+	scripting_context->pevent = evsel->tp_format->pevent;
 
 	ENTER;
 	SAVETMPS;
@@ -298,7 +315,8 @@ static void perl_process_event(int cpu, void *data,
 				offset = field->offset;
 			XPUSHs(sv_2mortal(newSVpv((char *)data + offset, 0)));
 		} else { /* FIELD_IS_NUMERIC */
-			val = read_size(data + field->offset, field->size);
+			val = read_size(event, data + field->offset,
+					field->size);
 			if (field->flags & FIELD_IS_SIGNED) {
 				XPUSHs(sv_2mortal(newSViv(val)));
 			} else {
@@ -326,6 +344,40 @@ static void perl_process_event(int cpu, void *data,
 	LEAVE;
 }
 
+static void perl_process_event_generic(union perf_event *event,
+				       struct perf_sample *sample,
+				       struct perf_evsel *evsel)
+{
+	dSP;
+
+	if (!get_cv("process_event", 0))
+		return;
+
+	ENTER;
+	SAVETMPS;
+	PUSHMARK(SP);
+	XPUSHs(sv_2mortal(newSVpvn((const char *)event, event->header.size)));
+	XPUSHs(sv_2mortal(newSVpvn((const char *)&evsel->attr, sizeof(evsel->attr))));
+	XPUSHs(sv_2mortal(newSVpvn((const char *)sample, sizeof(*sample))));
+	XPUSHs(sv_2mortal(newSVpvn((const char *)sample->raw_data, sample->raw_size)));
+	PUTBACK;
+	call_pv("process_event", G_SCALAR);
+	SPAGAIN;
+	PUTBACK;
+	FREETMPS;
+	LEAVE;
+}
+
+static void perl_process_event(union perf_event *event,
+			       struct perf_sample *sample,
+			       struct perf_evsel *evsel,
+			       struct thread *thread,
+			       struct addr_location *al __maybe_unused)
+{
+	perl_process_tracepoint(sample, evsel, thread);
+	perl_process_event_generic(event, sample, evsel);
+}
+
 static void run_start_sub(void)
 {
 	dSP; /* access to Perl stack */
@@ -396,9 +448,9 @@ static int perl_stop_script(void)
 	return 0;
 }
 
-static int perl_generate_script(const char *outfile)
+static int perl_generate_script(struct pevent *pevent, const char *outfile)
 {
-	struct event *event = NULL;
+	struct event_format *event = NULL;
 	struct format_field *f;
 	char fname[PATH_MAX];
 	int not_first, count;
@@ -411,8 +463,8 @@ static int perl_generate_script(const char *outfile)
 		return -1;
 	}
 
-	fprintf(ofp, "# perf trace event handlers, "
-		"generated by perf trace -g perl\n");
+	fprintf(ofp, "# perf script event handlers, "
+		"generated by perf script -g perl\n");
 
 	fprintf(ofp, "# Licensed under the terms of the GNU GPL"
 		" License version 2\n\n");
@@ -443,7 +495,7 @@ static int perl_generate_script(const char *outfile)
 	fprintf(ofp, "sub trace_begin\n{\n\t# optional\n}\n\n");
 	fprintf(ofp, "sub trace_end\n{\n\t# optional\n}\n\n");
 
-	while ((event = trace_find_next_event(event))) {
+	while ((event = trace_find_next_event(pevent, event))) {
 		fprintf(ofp, "sub %s::%s\n{\n", event->system, event->name);
 		fprintf(ofp, "\tmy (");
 
@@ -547,7 +599,28 @@ static int perl_generate_script(const char *outfile)
 	fprintf(ofp, "sub print_header\n{\n"
 		"\tmy ($event_name, $cpu, $secs, $nsecs, $pid, $comm) = @_;\n\n"
 		"\tprintf(\"%%-20s %%5u %%05u.%%09u %%8u %%-20s \",\n\t       "
-		"$event_name, $cpu, $secs, $nsecs, $pid, $comm);\n}");
+		"$event_name, $cpu, $secs, $nsecs, $pid, $comm);\n}\n");
+
+	fprintf(ofp,
+		"\n# Packed byte string args of process_event():\n"
+		"#\n"
+		"# $event:\tunion perf_event\tutil/event.h\n"
+		"# $attr:\tstruct perf_event_attr\tlinux/perf_event.h\n"
+		"# $sample:\tstruct perf_sample\tutil/event.h\n"
+		"# $raw_data:\tperf_sample->raw_data\tutil/event.h\n"
+		"\n"
+		"sub process_event\n"
+		"{\n"
+		"\tmy ($event, $attr, $sample, $raw_data) = @_;\n"
+		"\n"
+		"\tmy @event\t= unpack(\"LSS\", $event);\n"
+		"\tmy @attr\t= unpack(\"LLQQQQQLLQQ\", $attr);\n"
+		"\tmy @sample\t= unpack(\"QLLQQQQQLL\", $sample);\n"
+		"\tmy @raw_data\t= unpack(\"C*\", $raw_data);\n"
+		"\n"
+		"\tuse Data::Dumper;\n"
+		"\tprint Dumper \\@event, \\@attr, \\@sample, \\@raw_data;\n"
+		"}\n");
 
 	fclose(ofp);
 
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 33a63252374..1c419321f70 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -24,11 +24,13 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
-#include <ctype.h>
 #include <errno.h>
 
 #include "../../perf.h"
+#include "../evsel.h"
 #include "../util.h"
+#include "../event.h"
+#include "../thread.h"
 #include "../trace-event.h"
 
 PyMODINIT_FUNC initperf_trace_context(void);
@@ -36,7 +38,7 @@ PyMODINIT_FUNC initperf_trace_context(void);
 #define FTRACE_MAX_EVENT				\
 	((1 << (sizeof(unsigned short) * 8)) - 1)
 
-struct event *events[FTRACE_MAX_EVENT];
+struct event_format *events[FTRACE_MAX_EVENT];
 
 #define MAX_FIELDS	64
 #define N_COMMON_FIELDS	7
@@ -54,6 +56,17 @@ static void handler_call_die(const char *handler_name)
 	Py_FatalError("problem in Python trace event handler");
 }
 
+/*
+ * Insert val into into the dictionary and decrement the reference counter.
+ * This is necessary for dictionaries since PyDict_SetItemString() does not 
+ * steal a reference, as opposed to PyTuple_SetItem().
+ */
+static void pydict_set_item_string_decref(PyObject *dict, const char *key, PyObject *val)
+{
+	PyDict_SetItemString(dict, key, val);
+	Py_DECREF(val);
+}
+
 static void define_value(enum print_arg_type field_type,
 			 const char *ev_name,
 			 const char *field_name,
@@ -135,7 +148,7 @@ static void define_field(enum print_arg_type field_type,
 	Py_DECREF(t);
 }
 
-static void define_event_symbols(struct event *event,
+static void define_event_symbols(struct event_format *event,
 				 const char *ev_name,
 				 struct print_arg *args)
 {
@@ -148,8 +161,7 @@ static void define_event_symbols(struct event *event,
 		zero_flag_atom = 0;
 		break;
 	case PRINT_FIELD:
-		if (cur_field_name)
-			free(cur_field_name);
+		free(cur_field_name);
 		cur_field_name = strdup(args->field.name);
 		break;
 	case PRINT_FLAGS:
@@ -165,6 +177,10 @@ static void define_event_symbols(struct event *event,
 		define_values(PRINT_SYMBOL, args->symbol.symbols, ev_name,
 			      cur_field_name);
 		break;
+	case PRINT_HEX:
+		define_event_symbols(event, ev_name, args->hex.field);
+		define_event_symbols(event, ev_name, args->hex.size);
+		break;
 	case PRINT_STRING:
 		break;
 	case PRINT_TYPE:
@@ -177,6 +193,11 @@ static void define_event_symbols(struct event *event,
 		define_event_symbols(event, ev_name, args->op.right);
 		break;
 	default:
+		/* gcc warns for these? */
+	case PRINT_BSTRING:
+	case PRINT_DYNAMIC_ARRAY:
+	case PRINT_FUNC:
+	case PRINT_BITMASK:
 		/* we should warn... */
 		return;
 	}
@@ -185,15 +206,21 @@ static void define_event_symbols(struct event *event,
 		define_event_symbols(event, ev_name, args->next);
 }
 
-static inline struct event *find_cache_event(int type)
+static inline struct event_format *find_cache_event(struct perf_evsel *evsel)
 {
 	static char ev_name[256];
-	struct event *event;
-
+	struct event_format *event;
+	int type = evsel->attr.config;
+
+	/*
+ 	 * XXX: Do we really need to cache this since now we have evsel->tp_format
+ 	 * cached already? Need to re-read this "cache" routine that as well calls
+ 	 * define_event_symbols() :-\
+ 	 */
 	if (events[type])
 		return events[type];
 
-	events[type] = event = trace_find_event(type);
+	events[type] = event = evsel->tp_format;
 	if (!event)
 		return NULL;
 
@@ -204,31 +231,33 @@ static inline struct event *find_cache_event(int type)
 	return event;
 }
 
-static void python_process_event(int cpu, void *data,
-				 int size __unused,
-				 unsigned long long nsecs, char *comm)
+static void python_process_tracepoint(struct perf_sample *sample,
+				      struct perf_evsel *evsel,
+				      struct thread *thread,
+				      struct addr_location *al)
 {
 	PyObject *handler, *retval, *context, *t, *obj, *dict = NULL;
 	static char handler_name[256];
 	struct format_field *field;
 	unsigned long long val;
 	unsigned long s, ns;
-	struct event *event;
+	struct event_format *event;
 	unsigned n = 0;
-	int type;
 	int pid;
+	int cpu = sample->cpu;
+	void *data = sample->raw_data;
+	unsigned long long nsecs = sample->time;
+	const char *comm = thread__comm_str(thread);
 
 	t = PyTuple_New(MAX_FIELDS);
 	if (!t)
 		Py_FatalError("couldn't create Python tuple");
 
-	type = trace_parse_common_type(data);
-
-	event = find_cache_event(type);
+	event = find_cache_event(evsel);
 	if (!event)
-		die("ug! no event found for type %d", type);
+		die("ug! no event found for type %d", (int)evsel->attr.config);
 
-	pid = trace_parse_common_pid(data);
+	pid = raw_field_value(event, "common_pid", data);
 
 	sprintf(handler_name, "%s__%s", event->system, event->name);
 
@@ -244,12 +273,12 @@ static void python_process_event(int cpu, void *data,
 	ns = nsecs - s * NSECS_PER_SEC;
 
 	scripting_context->event_data = data;
+	scripting_context->pevent = evsel->tp_format->pevent;
 
 	context = PyCObject_FromVoidPtr(scripting_context, NULL);
 
 	PyTuple_SetItem(t, n++, PyString_FromString(handler_name));
-	PyTuple_SetItem(t, n++,
-			PyCObject_FromVoidPtr(scripting_context, NULL));
+	PyTuple_SetItem(t, n++, context);
 
 	if (handler) {
 		PyTuple_SetItem(t, n++, PyInt_FromLong(cpu));
@@ -258,11 +287,11 @@ static void python_process_event(int cpu, void *data,
 		PyTuple_SetItem(t, n++, PyInt_FromLong(pid));
 		PyTuple_SetItem(t, n++, PyString_FromString(comm));
 	} else {
-		PyDict_SetItemString(dict, "common_cpu", PyInt_FromLong(cpu));
-		PyDict_SetItemString(dict, "common_s", PyInt_FromLong(s));
-		PyDict_SetItemString(dict, "common_ns", PyInt_FromLong(ns));
-		PyDict_SetItemString(dict, "common_pid", PyInt_FromLong(pid));
-		PyDict_SetItemString(dict, "common_comm", PyString_FromString(comm));
+		pydict_set_item_string_decref(dict, "common_cpu", PyInt_FromLong(cpu));
+		pydict_set_item_string_decref(dict, "common_s", PyInt_FromLong(s));
+		pydict_set_item_string_decref(dict, "common_ns", PyInt_FromLong(ns));
+		pydict_set_item_string_decref(dict, "common_pid", PyInt_FromLong(pid));
+		pydict_set_item_string_decref(dict, "common_comm", PyString_FromString(comm));
 	}
 	for (field = event->format.fields; field; field = field->next) {
 		if (field->flags & FIELD_IS_STRING) {
@@ -274,7 +303,8 @@ static void python_process_event(int cpu, void *data,
 				offset = field->offset;
 			obj = PyString_FromString((char *)data + offset);
 		} else { /* FIELD_IS_NUMERIC */
-			val = read_size(data + field->offset, field->size);
+			val = read_size(event, data + field->offset,
+					field->size);
 			if (field->flags & FIELD_IS_SIGNED) {
 				if ((long long)val >= LONG_MIN &&
 				    (long long)val <= LONG_MAX)
@@ -291,7 +321,7 @@ static void python_process_event(int cpu, void *data,
 		if (handler)
 			PyTuple_SetItem(t, n++, obj);
 		else
-			PyDict_SetItemString(dict, field->name, obj);
+			pydict_set_item_string_decref(dict, field->name, obj);
 
 	}
 	if (!handler)
@@ -318,6 +348,79 @@ static void python_process_event(int cpu, void *data,
 	Py_DECREF(t);
 }
 
+static void python_process_general_event(struct perf_sample *sample,
+					 struct perf_evsel *evsel,
+					 struct thread *thread,
+					 struct addr_location *al)
+{
+	PyObject *handler, *retval, *t, *dict;
+	static char handler_name[64];
+	unsigned n = 0;
+
+	/*
+	 * Use the MAX_FIELDS to make the function expandable, though
+	 * currently there is only one item for the tuple.
+	 */
+	t = PyTuple_New(MAX_FIELDS);
+	if (!t)
+		Py_FatalError("couldn't create Python tuple");
+
+	dict = PyDict_New();
+	if (!dict)
+		Py_FatalError("couldn't create Python dictionary");
+
+	snprintf(handler_name, sizeof(handler_name), "%s", "process_event");
+
+	handler = PyDict_GetItemString(main_dict, handler_name);
+	if (!handler || !PyCallable_Check(handler))
+		goto exit;
+
+	pydict_set_item_string_decref(dict, "ev_name", PyString_FromString(perf_evsel__name(evsel)));
+	pydict_set_item_string_decref(dict, "attr", PyString_FromStringAndSize(
+			(const char *)&evsel->attr, sizeof(evsel->attr)));
+	pydict_set_item_string_decref(dict, "sample", PyString_FromStringAndSize(
+			(const char *)sample, sizeof(*sample)));
+	pydict_set_item_string_decref(dict, "raw_buf", PyString_FromStringAndSize(
+			(const char *)sample->raw_data, sample->raw_size));
+	pydict_set_item_string_decref(dict, "comm",
+			PyString_FromString(thread__comm_str(thread)));
+	if (al->map) {
+		pydict_set_item_string_decref(dict, "dso",
+			PyString_FromString(al->map->dso->name));
+	}
+	if (al->sym) {
+		pydict_set_item_string_decref(dict, "symbol",
+			PyString_FromString(al->sym->name));
+	}
+
+	PyTuple_SetItem(t, n++, dict);
+	if (_PyTuple_Resize(&t, n) == -1)
+		Py_FatalError("error resizing Python tuple");
+
+	retval = PyObject_CallObject(handler, t);
+	if (retval == NULL)
+		handler_call_die(handler_name);
+exit:
+	Py_DECREF(dict);
+	Py_DECREF(t);
+}
+
+static void python_process_event(union perf_event *event __maybe_unused,
+				 struct perf_sample *sample,
+				 struct perf_evsel *evsel,
+				 struct thread *thread,
+				 struct addr_location *al)
+{
+	switch (evsel->attr.type) {
+	case PERF_TYPE_TRACEPOINT:
+		python_process_tracepoint(sample, evsel, thread, al);
+		break;
+	/* Reserve for future process_hw/sw/raw APIs */
+	default:
+		python_process_general_event(sample, evsel, thread, al);
+	}
+}
+
 static int run_start_sub(void)
 {
 	PyObject *handler, *retval;
@@ -428,9 +531,9 @@ out:
 	return err;
 }
 
-static int python_generate_script(const char *outfile)
+static int python_generate_script(struct pevent *pevent, const char *outfile)
 {
-	struct event *event = NULL;
+	struct event_format *event = NULL;
 	struct format_field *f;
 	char fname[PATH_MAX];
 	int not_first, count;
@@ -442,8 +545,8 @@ static int python_generate_script(const char *outfile)
 		fprintf(stderr, "couldn't open %s\n", fname);
 		return -1;
 	}
-	fprintf(ofp, "# perf trace event handlers, "
-		"generated by perf trace -g python\n");
+	fprintf(ofp, "# perf script event handlers, "
+		"generated by perf script -g python\n");
 
 	fprintf(ofp, "# Licensed under the terms of the GNU GPL"
 		" License version 2\n\n");
@@ -477,7 +580,7 @@ static int python_generate_script(const char *outfile)
 	fprintf(ofp, "def trace_end():\n");
 	fprintf(ofp, "\tprint \"in trace_end\"\n\n");
 
-	while ((event = trace_find_next_event(event))) {
+	while ((event = trace_find_next_event(pevent, event))) {
 		fprintf(ofp, "def %s__%s(", event->system, event->name);
 		fprintf(ofp, "event_name, ");
 		fprintf(ofp, "context, ");
@@ -520,6 +623,7 @@ static int python_generate_script(const char *outfile)
 			fprintf(ofp, "%s=", f->name);
 			if (f->flags & FIELD_IS_STRING ||
 			    f->flags & FIELD_IS_FLAG ||
+			    f->flags & FIELD_IS_ARRAY ||
 			    f->flags & FIELD_IS_SYMBOLIC)
 				fprintf(ofp, "%%s");
 			else if (f->flags & FIELD_IS_SIGNED)
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index c422cd67631..64a186edc7b 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1,386 +1,531 @@
-#define _FILE_OFFSET_BITS 64
-
 #include <linux/kernel.h>
+#include <traceevent/event-parse.h>
 
 #include <byteswap.h>
 #include <unistd.h>
 #include <sys/types.h>
 #include <sys/mman.h>
 
+#include "evlist.h"
+#include "evsel.h"
 #include "session.h"
+#include "tool.h"
 #include "sort.h"
 #include "util.h"
+#include "cpumap.h"
+#include "perf_regs.h"
+#include "vdso.h"
 
-static int perf_session__open(struct perf_session *self, bool force)
+static int perf_session__open(struct perf_session *session)
 {
-	struct stat input_stat;
-
-	if (!strcmp(self->filename, "-")) {
-		self->fd_pipe = true;
-		self->fd = STDIN_FILENO;
+	struct perf_data_file *file = session->file;
 
-		if (perf_header__read(self, self->fd) < 0)
-			pr_err("incompatible file format");
-
-		return 0;
-	}
-
-	self->fd = open(self->filename, O_RDONLY);
-	if (self->fd < 0) {
-		pr_err("failed to open file: %s", self->filename);
-		if (!strcmp(self->filename, "perf.data"))
-			pr_err("  (try 'perf record' first)");
-		pr_err("\n");
-		return -errno;
+	if (perf_session__read_header(session) < 0) {
+		pr_err("incompatible file format (rerun with -v to learn more)");
+		return -1;
 	}
 
-	if (fstat(self->fd, &input_stat) < 0)
-		goto out_close;
+	if (perf_data_file__is_pipe(file))
+		return 0;
 
-	if (!force && input_stat.st_uid && (input_stat.st_uid != geteuid())) {
-		pr_err("file %s not owned by current user or root\n",
-		       self->filename);
-		goto out_close;
+	if (!perf_evlist__valid_sample_type(session->evlist)) {
+		pr_err("non matching sample_type");
+		return -1;
 	}
 
-	if (!input_stat.st_size) {
-		pr_info("zero-sized file (%s), nothing to do!\n",
-			self->filename);
-		goto out_close;
+	if (!perf_evlist__valid_sample_id_all(session->evlist)) {
+		pr_err("non matching sample_id_all");
+		return -1;
 	}
 
-	if (perf_header__read(self, self->fd) < 0) {
-		pr_err("incompatible file format");
-		goto out_close;
+	if (!perf_evlist__valid_read_format(session->evlist)) {
+		pr_err("non matching read_format");
+		return -1;
 	}
 
-	self->size = input_stat.st_size;
 	return 0;
-
-out_close:
-	close(self->fd);
-	self->fd = -1;
-	return -1;
 }
 
-void perf_session__update_sample_type(struct perf_session *self)
+void perf_session__set_id_hdr_size(struct perf_session *session)
 {
-	self->sample_type = perf_header__sample_type(&self->header);
+	u16 id_hdr_size = perf_evlist__id_hdr_size(session->evlist);
+
+	machines__set_id_hdr_size(&session->machines, id_hdr_size);
 }
 
-int perf_session__create_kernel_maps(struct perf_session *self)
+int perf_session__create_kernel_maps(struct perf_session *session)
 {
-	int ret = machine__create_kernel_maps(&self->host_machine);
+	int ret = machine__create_kernel_maps(&session->machines.host);
 
 	if (ret >= 0)
-		ret = machines__create_guest_kernel_maps(&self->machines);
+		ret = machines__create_guest_kernel_maps(&session->machines);
 	return ret;
 }
 
-struct perf_session *perf_session__new(const char *filename, int mode, bool force, bool repipe)
+static void perf_session__destroy_kernel_maps(struct perf_session *session)
 {
-	size_t len = filename ? strlen(filename) + 1 : 0;
-	struct perf_session *self = zalloc(sizeof(*self) + len);
+	machines__destroy_kernel_maps(&session->machines);
+}
+
+struct perf_session *perf_session__new(struct perf_data_file *file,
+				       bool repipe, struct perf_tool *tool)
+{
+	struct perf_session *session = zalloc(sizeof(*session));
 
-	if (self == NULL)
+	if (!session)
 		goto out;
 
-	if (perf_header__init(&self->header) < 0)
-		goto out_free;
-
-	memcpy(self->filename, filename, len);
-	self->threads = RB_ROOT;
-	INIT_LIST_HEAD(&self->dead_threads);
-	self->hists_tree = RB_ROOT;
-	self->last_match = NULL;
-	self->mmap_window = 32;
-	self->cwd = NULL;
-	self->cwdlen = 0;
-	self->machines = RB_ROOT;
-	self->repipe = repipe;
-	INIT_LIST_HEAD(&self->ordered_samples.samples_head);
-	machine__init(&self->host_machine, "", HOST_KERNEL_ID);
-
-	if (mode == O_RDONLY) {
-		if (perf_session__open(self, force) < 0)
+	session->repipe = repipe;
+	INIT_LIST_HEAD(&session->ordered_samples.samples);
+	INIT_LIST_HEAD(&session->ordered_samples.sample_cache);
+	INIT_LIST_HEAD(&session->ordered_samples.to_free);
+	machines__init(&session->machines);
+
+	if (file) {
+		if (perf_data_file__open(file))
 			goto out_delete;
-	} else if (mode == O_WRONLY) {
+
+		session->file = file;
+
+		if (perf_data_file__is_read(file)) {
+			if (perf_session__open(session) < 0)
+				goto out_close;
+
+			perf_session__set_id_hdr_size(session);
+		}
+	}
+
+	if (!file || perf_data_file__is_write(file)) {
 		/*
 		 * In O_RDONLY mode this will be performed when reading the
-		 * kernel MMAP event, in event__process_mmap().
+		 * kernel MMAP event, in perf_event__process_mmap().
 		 */
-		if (perf_session__create_kernel_maps(self) < 0)
+		if (perf_session__create_kernel_maps(session) < 0)
 			goto out_delete;
 	}
 
-	perf_session__update_sample_type(self);
-out:
-	return self;
-out_free:
-	free(self);
-	return NULL;
-out_delete:
-	perf_session__delete(self);
+	if (tool && tool->ordering_requires_timestamps &&
+	    tool->ordered_samples && !perf_evlist__sample_id_all(session->evlist)) {
+		dump_printf("WARNING: No sample_id_all support, falling back to unordered processing\n");
+		tool->ordered_samples = false;
+	}
+
+	return session;
+
+ out_close:
+	perf_data_file__close(file);
+ out_delete:
+	perf_session__delete(session);
+ out:
 	return NULL;
 }
 
-void perf_session__delete(struct perf_session *self)
+static void perf_session__delete_dead_threads(struct perf_session *session)
 {
-	perf_header__exit(&self->header);
-	close(self->fd);
-	free(self->cwd);
-	free(self);
+	machine__delete_dead_threads(&session->machines.host);
 }
 
-void perf_session__remove_thread(struct perf_session *self, struct thread *th)
+static void perf_session__delete_threads(struct perf_session *session)
 {
-	rb_erase(&th->rb_node, &self->threads);
-	/*
-	 * We may have references to this thread, for instance in some hist_entry
-	 * instances, so just move them to a separate list.
-	 */
-	list_add_tail(&th->node, &self->dead_threads);
+	machine__delete_threads(&session->machines.host);
 }
 
-static bool symbol__match_parent_regex(struct symbol *sym)
+static void perf_session_env__delete(struct perf_session_env *env)
 {
-	if (sym->name && !regexec(&parent_regex, sym->name, 0, NULL, 0))
-		return 1;
-
-	return 0;
+	zfree(&env->hostname);
+	zfree(&env->os_release);
+	zfree(&env->version);
+	zfree(&env->arch);
+	zfree(&env->cpu_desc);
+	zfree(&env->cpuid);
+
+	zfree(&env->cmdline);
+	zfree(&env->sibling_cores);
+	zfree(&env->sibling_threads);
+	zfree(&env->numa_nodes);
+	zfree(&env->pmu_mappings);
 }
 
-struct map_symbol *perf_session__resolve_callchain(struct perf_session *self,
-						   struct thread *thread,
-						   struct ip_callchain *chain,
-						   struct symbol **parent)
+void perf_session__delete(struct perf_session *session)
 {
-	u8 cpumode = PERF_RECORD_MISC_USER;
-	unsigned int i;
-	struct map_symbol *syms = calloc(chain->nr, sizeof(*syms));
-
-	if (!syms)
-		return NULL;
+	perf_session__destroy_kernel_maps(session);
+	perf_session__delete_dead_threads(session);
+	perf_session__delete_threads(session);
+	perf_session_env__delete(&session->header.env);
+	machines__exit(&session->machines);
+	if (session->file)
+		perf_data_file__close(session->file);
+	free(session);
+	vdso__exit();
+}
 
-	for (i = 0; i < chain->nr; i++) {
-		u64 ip = chain->ips[i];
-		struct addr_location al;
-
-		if (ip >= PERF_CONTEXT_MAX) {
-			switch (ip) {
-			case PERF_CONTEXT_HV:
-				cpumode = PERF_RECORD_MISC_HYPERVISOR;	break;
-			case PERF_CONTEXT_KERNEL:
-				cpumode = PERF_RECORD_MISC_KERNEL;	break;
-			case PERF_CONTEXT_USER:
-				cpumode = PERF_RECORD_MISC_USER;	break;
-			default:
-				break;
-			}
-			continue;
-		}
+static int process_event_synth_tracing_data_stub(struct perf_tool *tool
+						 __maybe_unused,
+						 union perf_event *event
+						 __maybe_unused,
+						 struct perf_session *session
+						__maybe_unused)
+{
+	dump_printf(": unhandled!\n");
+	return 0;
+}
 
-		al.filtered = false;
-		thread__find_addr_location(thread, self, cpumode,
-				MAP__FUNCTION, thread->pid, ip, &al, NULL);
-		if (al.sym != NULL) {
-			if (sort__has_parent && !*parent &&
-			    symbol__match_parent_regex(al.sym))
-				*parent = al.sym;
-			if (!symbol_conf.use_callchain)
-				break;
-			syms[i].map = al.map;
-			syms[i].sym = al.sym;
-		}
-	}
+static int process_event_synth_attr_stub(struct perf_tool *tool __maybe_unused,
+					 union perf_event *event __maybe_unused,
+					 struct perf_evlist **pevlist
+					 __maybe_unused)
+{
+	dump_printf(": unhandled!\n");
+	return 0;
+}
 
-	return syms;
+static int process_event_sample_stub(struct perf_tool *tool __maybe_unused,
+				     union perf_event *event __maybe_unused,
+				     struct perf_sample *sample __maybe_unused,
+				     struct perf_evsel *evsel __maybe_unused,
+				     struct machine *machine __maybe_unused)
+{
+	dump_printf(": unhandled!\n");
+	return 0;
 }
 
-static int process_event_stub(event_t *event __used,
-			      struct perf_session *session __used)
+static int process_event_stub(struct perf_tool *tool __maybe_unused,
+			      union perf_event *event __maybe_unused,
+			      struct perf_sample *sample __maybe_unused,
+			      struct machine *machine __maybe_unused)
 {
 	dump_printf(": unhandled!\n");
 	return 0;
 }
 
-static int process_finished_round_stub(event_t *event __used,
-				       struct perf_session *session __used,
-				       struct perf_event_ops *ops __used)
+static int process_finished_round_stub(struct perf_tool *tool __maybe_unused,
+				       union perf_event *event __maybe_unused,
+				       struct perf_session *perf_session
+				       __maybe_unused)
 {
 	dump_printf(": unhandled!\n");
 	return 0;
 }
 
-static int process_finished_round(event_t *event,
-				  struct perf_session *session,
-				  struct perf_event_ops *ops);
-
-static void perf_event_ops__fill_defaults(struct perf_event_ops *handler)
-{
-	if (handler->sample == NULL)
-		handler->sample = process_event_stub;
-	if (handler->mmap == NULL)
-		handler->mmap = process_event_stub;
-	if (handler->comm == NULL)
-		handler->comm = process_event_stub;
-	if (handler->fork == NULL)
-		handler->fork = process_event_stub;
-	if (handler->exit == NULL)
-		handler->exit = process_event_stub;
-	if (handler->lost == NULL)
-		handler->lost = process_event_stub;
-	if (handler->read == NULL)
-		handler->read = process_event_stub;
-	if (handler->throttle == NULL)
-		handler->throttle = process_event_stub;
-	if (handler->unthrottle == NULL)
-		handler->unthrottle = process_event_stub;
-	if (handler->attr == NULL)
-		handler->attr = process_event_stub;
-	if (handler->event_type == NULL)
-		handler->event_type = process_event_stub;
-	if (handler->tracing_data == NULL)
-		handler->tracing_data = process_event_stub;
-	if (handler->build_id == NULL)
-		handler->build_id = process_event_stub;
-	if (handler->finished_round == NULL) {
-		if (handler->ordered_samples)
-			handler->finished_round = process_finished_round;
+static int process_finished_round(struct perf_tool *tool,
+				  union perf_event *event,
+				  struct perf_session *session);
+
+void perf_tool__fill_defaults(struct perf_tool *tool)
+{
+	if (tool->sample == NULL)
+		tool->sample = process_event_sample_stub;
+	if (tool->mmap == NULL)
+		tool->mmap = process_event_stub;
+	if (tool->mmap2 == NULL)
+		tool->mmap2 = process_event_stub;
+	if (tool->comm == NULL)
+		tool->comm = process_event_stub;
+	if (tool->fork == NULL)
+		tool->fork = process_event_stub;
+	if (tool->exit == NULL)
+		tool->exit = process_event_stub;
+	if (tool->lost == NULL)
+		tool->lost = perf_event__process_lost;
+	if (tool->read == NULL)
+		tool->read = process_event_sample_stub;
+	if (tool->throttle == NULL)
+		tool->throttle = process_event_stub;
+	if (tool->unthrottle == NULL)
+		tool->unthrottle = process_event_stub;
+	if (tool->attr == NULL)
+		tool->attr = process_event_synth_attr_stub;
+	if (tool->tracing_data == NULL)
+		tool->tracing_data = process_event_synth_tracing_data_stub;
+	if (tool->build_id == NULL)
+		tool->build_id = process_finished_round_stub;
+	if (tool->finished_round == NULL) {
+		if (tool->ordered_samples)
+			tool->finished_round = process_finished_round;
 		else
-			handler->finished_round = process_finished_round_stub;
+			tool->finished_round = process_finished_round_stub;
 	}
 }
+ 
+static void swap_sample_id_all(union perf_event *event, void *data)
+{
+	void *end = (void *) event + event->header.size;
+	int size = end - data;
+
+	BUG_ON(size % sizeof(u64));
+	mem_bswap_64(data, size);
+}
 
-void mem_bswap_64(void *src, int byte_size)
+static void perf_event__all64_swap(union perf_event *event,
+				   bool sample_id_all __maybe_unused)
 {
-	u64 *m = src;
+	struct perf_event_header *hdr = &event->header;
+	mem_bswap_64(hdr + 1, event->header.size - sizeof(*hdr));
+}
+
+static void perf_event__comm_swap(union perf_event *event, bool sample_id_all)
+{
+	event->comm.pid = bswap_32(event->comm.pid);
+	event->comm.tid = bswap_32(event->comm.tid);
 
-	while (byte_size > 0) {
-		*m = bswap_64(*m);
-		byte_size -= sizeof(u64);
-		++m;
+	if (sample_id_all) {
+		void *data = &event->comm.comm;
+
+		data += PERF_ALIGN(strlen(data) + 1, sizeof(u64));
+		swap_sample_id_all(event, data);
 	}
 }
 
-static void event__all64_swap(event_t *self)
+static void perf_event__mmap_swap(union perf_event *event,
+				  bool sample_id_all)
 {
-	struct perf_event_header *hdr = &self->header;
-	mem_bswap_64(hdr + 1, self->header.size - sizeof(*hdr));
+	event->mmap.pid	  = bswap_32(event->mmap.pid);
+	event->mmap.tid	  = bswap_32(event->mmap.tid);
+	event->mmap.start = bswap_64(event->mmap.start);
+	event->mmap.len	  = bswap_64(event->mmap.len);
+	event->mmap.pgoff = bswap_64(event->mmap.pgoff);
+
+	if (sample_id_all) {
+		void *data = &event->mmap.filename;
+
+		data += PERF_ALIGN(strlen(data) + 1, sizeof(u64));
+		swap_sample_id_all(event, data);
+	}
 }
 
-static void event__comm_swap(event_t *self)
+static void perf_event__mmap2_swap(union perf_event *event,
+				  bool sample_id_all)
+{
+	event->mmap2.pid   = bswap_32(event->mmap2.pid);
+	event->mmap2.tid   = bswap_32(event->mmap2.tid);
+	event->mmap2.start = bswap_64(event->mmap2.start);
+	event->mmap2.len   = bswap_64(event->mmap2.len);
+	event->mmap2.pgoff = bswap_64(event->mmap2.pgoff);
+	event->mmap2.maj   = bswap_32(event->mmap2.maj);
+	event->mmap2.min   = bswap_32(event->mmap2.min);
+	event->mmap2.ino   = bswap_64(event->mmap2.ino);
+
+	if (sample_id_all) {
+		void *data = &event->mmap2.filename;
+
+		data += PERF_ALIGN(strlen(data) + 1, sizeof(u64));
+		swap_sample_id_all(event, data);
+	}
+}
+static void perf_event__task_swap(union perf_event *event, bool sample_id_all)
 {
-	self->comm.pid = bswap_32(self->comm.pid);
-	self->comm.tid = bswap_32(self->comm.tid);
+	event->fork.pid	 = bswap_32(event->fork.pid);
+	event->fork.tid	 = bswap_32(event->fork.tid);
+	event->fork.ppid = bswap_32(event->fork.ppid);
+	event->fork.ptid = bswap_32(event->fork.ptid);
+	event->fork.time = bswap_64(event->fork.time);
+
+	if (sample_id_all)
+		swap_sample_id_all(event, &event->fork + 1);
 }
 
-static void event__mmap_swap(event_t *self)
+static void perf_event__read_swap(union perf_event *event, bool sample_id_all)
 {
-	self->mmap.pid	 = bswap_32(self->mmap.pid);
-	self->mmap.tid	 = bswap_32(self->mmap.tid);
-	self->mmap.start = bswap_64(self->mmap.start);
-	self->mmap.len	 = bswap_64(self->mmap.len);
-	self->mmap.pgoff = bswap_64(self->mmap.pgoff);
+	event->read.pid		 = bswap_32(event->read.pid);
+	event->read.tid		 = bswap_32(event->read.tid);
+	event->read.value	 = bswap_64(event->read.value);
+	event->read.time_enabled = bswap_64(event->read.time_enabled);
+	event->read.time_running = bswap_64(event->read.time_running);
+	event->read.id		 = bswap_64(event->read.id);
+
+	if (sample_id_all)
+		swap_sample_id_all(event, &event->read + 1);
 }
 
-static void event__task_swap(event_t *self)
+static void perf_event__throttle_swap(union perf_event *event,
+				      bool sample_id_all)
 {
-	self->fork.pid	= bswap_32(self->fork.pid);
-	self->fork.tid	= bswap_32(self->fork.tid);
-	self->fork.ppid	= bswap_32(self->fork.ppid);
-	self->fork.ptid	= bswap_32(self->fork.ptid);
-	self->fork.time	= bswap_64(self->fork.time);
+	event->throttle.time	  = bswap_64(event->throttle.time);
+	event->throttle.id	  = bswap_64(event->throttle.id);
+	event->throttle.stream_id = bswap_64(event->throttle.stream_id);
+
+	if (sample_id_all)
+		swap_sample_id_all(event, &event->throttle + 1);
 }
 
-static void event__read_swap(event_t *self)
+static u8 revbyte(u8 b)
 {
-	self->read.pid		= bswap_32(self->read.pid);
-	self->read.tid		= bswap_32(self->read.tid);
-	self->read.value	= bswap_64(self->read.value);
-	self->read.time_enabled	= bswap_64(self->read.time_enabled);
-	self->read.time_running	= bswap_64(self->read.time_running);
-	self->read.id		= bswap_64(self->read.id);
+	int rev = (b >> 4) | ((b & 0xf) << 4);
+	rev = ((rev & 0xcc) >> 2) | ((rev & 0x33) << 2);
+	rev = ((rev & 0xaa) >> 1) | ((rev & 0x55) << 1);
+	return (u8) rev;
 }
 
-static void event__attr_swap(event_t *self)
+/*
+ * XXX this is hack in attempt to carry flags bitfield
+ * throught endian village. ABI says:
+ *
+ * Bit-fields are allocated from right to left (least to most significant)
+ * on little-endian implementations and from left to right (most to least
+ * significant) on big-endian implementations.
+ *
+ * The above seems to be byte specific, so we need to reverse each
+ * byte of the bitfield. 'Internet' also says this might be implementation
+ * specific and we probably need proper fix and carry perf_event_attr
+ * bitfield flags in separate data file FEAT_ section. Thought this seems
+ * to work for now.
+ */
+static void swap_bitfield(u8 *p, unsigned len)
 {
-	size_t size;
+	unsigned i;
 
-	self->attr.attr.type		= bswap_32(self->attr.attr.type);
-	self->attr.attr.size		= bswap_32(self->attr.attr.size);
-	self->attr.attr.config		= bswap_64(self->attr.attr.config);
-	self->attr.attr.sample_period	= bswap_64(self->attr.attr.sample_period);
-	self->attr.attr.sample_type	= bswap_64(self->attr.attr.sample_type);
-	self->attr.attr.read_format	= bswap_64(self->attr.attr.read_format);
-	self->attr.attr.wakeup_events	= bswap_32(self->attr.attr.wakeup_events);
-	self->attr.attr.bp_type		= bswap_32(self->attr.attr.bp_type);
-	self->attr.attr.bp_addr		= bswap_64(self->attr.attr.bp_addr);
-	self->attr.attr.bp_len		= bswap_64(self->attr.attr.bp_len);
+	for (i = 0; i < len; i++) {
+		*p = revbyte(*p);
+		p++;
+	}
+}
 
-	size = self->header.size;
-	size -= (void *)&self->attr.id - (void *)self;
-	mem_bswap_64(self->attr.id, size);
+/* exported for swapping attributes in file header */
+void perf_event__attr_swap(struct perf_event_attr *attr)
+{
+	attr->type		= bswap_32(attr->type);
+	attr->size		= bswap_32(attr->size);
+	attr->config		= bswap_64(attr->config);
+	attr->sample_period	= bswap_64(attr->sample_period);
+	attr->sample_type	= bswap_64(attr->sample_type);
+	attr->read_format	= bswap_64(attr->read_format);
+	attr->wakeup_events	= bswap_32(attr->wakeup_events);
+	attr->bp_type		= bswap_32(attr->bp_type);
+	attr->bp_addr		= bswap_64(attr->bp_addr);
+	attr->bp_len		= bswap_64(attr->bp_len);
+	attr->branch_sample_type = bswap_64(attr->branch_sample_type);
+	attr->sample_regs_user	 = bswap_64(attr->sample_regs_user);
+	attr->sample_stack_user  = bswap_32(attr->sample_stack_user);
+
+	swap_bitfield((u8 *) (&attr->read_format + 1), sizeof(u64));
 }
 
-static void event__event_type_swap(event_t *self)
+static void perf_event__hdr_attr_swap(union perf_event *event,
+				      bool sample_id_all __maybe_unused)
 {
-	self->event_type.event_type.event_id =
-		bswap_64(self->event_type.event_type.event_id);
+	size_t size;
+
+	perf_event__attr_swap(&event->attr.attr);
+
+	size = event->header.size;
+	size -= (void *)&event->attr.id - (void *)event;
+	mem_bswap_64(event->attr.id, size);
 }
 
-static void event__tracing_data_swap(event_t *self)
+static void perf_event__event_type_swap(union perf_event *event,
+					bool sample_id_all __maybe_unused)
 {
-	self->tracing_data.size = bswap_32(self->tracing_data.size);
+	event->event_type.event_type.event_id =
+		bswap_64(event->event_type.event_type.event_id);
 }
 
-typedef void (*event__swap_op)(event_t *self);
+static void perf_event__tracing_data_swap(union perf_event *event,
+					  bool sample_id_all __maybe_unused)
+{
+	event->tracing_data.size = bswap_32(event->tracing_data.size);
+}
 
-static event__swap_op event__swap_ops[] = {
-	[PERF_RECORD_MMAP]   = event__mmap_swap,
-	[PERF_RECORD_COMM]   = event__comm_swap,
-	[PERF_RECORD_FORK]   = event__task_swap,
-	[PERF_RECORD_EXIT]   = event__task_swap,
-	[PERF_RECORD_LOST]   = event__all64_swap,
-	[PERF_RECORD_READ]   = event__read_swap,
-	[PERF_RECORD_SAMPLE] = event__all64_swap,
-	[PERF_RECORD_HEADER_ATTR]   = event__attr_swap,
-	[PERF_RECORD_HEADER_EVENT_TYPE]   = event__event_type_swap,
-	[PERF_RECORD_HEADER_TRACING_DATA]   = event__tracing_data_swap,
-	[PERF_RECORD_HEADER_BUILD_ID]   = NULL,
-	[PERF_RECORD_HEADER_MAX]    = NULL,
+typedef void (*perf_event__swap_op)(union perf_event *event,
+				    bool sample_id_all);
+
+static perf_event__swap_op perf_event__swap_ops[] = {
+	[PERF_RECORD_MMAP]		  = perf_event__mmap_swap,
+	[PERF_RECORD_MMAP2]		  = perf_event__mmap2_swap,
+	[PERF_RECORD_COMM]		  = perf_event__comm_swap,
+	[PERF_RECORD_FORK]		  = perf_event__task_swap,
+	[PERF_RECORD_EXIT]		  = perf_event__task_swap,
+	[PERF_RECORD_LOST]		  = perf_event__all64_swap,
+	[PERF_RECORD_READ]		  = perf_event__read_swap,
+	[PERF_RECORD_THROTTLE]		  = perf_event__throttle_swap,
+	[PERF_RECORD_UNTHROTTLE]	  = perf_event__throttle_swap,
+	[PERF_RECORD_SAMPLE]		  = perf_event__all64_swap,
+	[PERF_RECORD_HEADER_ATTR]	  = perf_event__hdr_attr_swap,
+	[PERF_RECORD_HEADER_EVENT_TYPE]	  = perf_event__event_type_swap,
+	[PERF_RECORD_HEADER_TRACING_DATA] = perf_event__tracing_data_swap,
+	[PERF_RECORD_HEADER_BUILD_ID]	  = NULL,
+	[PERF_RECORD_HEADER_MAX]	  = NULL,
 };
 
 struct sample_queue {
 	u64			timestamp;
-	struct sample_event	*event;
+	u64			file_offset;
+	union perf_event	*event;
 	struct list_head	list;
 };
 
-static void flush_sample_queue(struct perf_session *s,
-			       struct perf_event_ops *ops)
+static void perf_session_free_sample_buffers(struct perf_session *session)
+{
+	struct ordered_samples *os = &session->ordered_samples;
+
+	while (!list_empty(&os->to_free)) {
+		struct sample_queue *sq;
+
+		sq = list_entry(os->to_free.next, struct sample_queue, list);
+		list_del(&sq->list);
+		free(sq);
+	}
+}
+
+static int perf_session_deliver_event(struct perf_session *session,
+				      union perf_event *event,
+				      struct perf_sample *sample,
+				      struct perf_tool *tool,
+				      u64 file_offset);
+
+static int flush_sample_queue(struct perf_session *s,
+		       struct perf_tool *tool)
 {
-	struct list_head *head = &s->ordered_samples.samples_head;
-	u64 limit = s->ordered_samples.next_flush;
+	struct ordered_samples *os = &s->ordered_samples;
+	struct list_head *head = &os->samples;
 	struct sample_queue *tmp, *iter;
+	struct perf_sample sample;
+	u64 limit = os->next_flush;
+	u64 last_ts = os->last_sample ? os->last_sample->timestamp : 0ULL;
+	bool show_progress = limit == ULLONG_MAX;
+	struct ui_progress prog;
+	int ret;
+
+	if (!tool->ordered_samples || !limit)
+		return 0;
 
-	if (!ops->ordered_samples || !limit)
-		return;
+	if (show_progress)
+		ui_progress__init(&prog, os->nr_samples, "Processing time ordered events...");
 
 	list_for_each_entry_safe(iter, tmp, head, list) {
+		if (session_done())
+			return 0;
+
 		if (iter->timestamp > limit)
-			return;
+			break;
+
+		ret = perf_evlist__parse_sample(s->evlist, iter->event, &sample);
+		if (ret)
+			pr_err("Can't parse sample, err = %d\n", ret);
+		else {
+			ret = perf_session_deliver_event(s, iter->event, &sample, tool,
+							 iter->file_offset);
+			if (ret)
+				return ret;
+		}
 
-		if (iter == s->ordered_samples.last_inserted)
-			s->ordered_samples.last_inserted = NULL;
+		os->last_flush = iter->timestamp;
+		list_del(&iter->list);
+		list_add(&iter->list, &os->sample_cache);
 
-		ops->sample((event_t *)iter->event, s);
+		if (show_progress)
+			ui_progress__update(&prog, 1);
+	}
 
-		s->ordered_samples.last_flush = iter->timestamp;
-		list_del(&iter->list);
-		free(iter->event);
-		free(iter);
+	if (list_empty(head)) {
+		os->last_sample = NULL;
+	} else if (last_ts <= limit) {
+		os->last_sample =
+			list_entry(head->prev, struct sample_queue, list);
 	}
+
+	os->nr_samples = 0;
+
+	return 0;
 }
 
 /*
@@ -422,200 +567,530 @@ static void flush_sample_queue(struct perf_session *s,
  *      Flush every events below timestamp 7
  *      etc...
  */
-static int process_finished_round(event_t *event __used,
-				  struct perf_session *session,
-				  struct perf_event_ops *ops)
+static int process_finished_round(struct perf_tool *tool,
+				  union perf_event *event __maybe_unused,
+				  struct perf_session *session)
 {
-	flush_sample_queue(session, ops);
-	session->ordered_samples.next_flush = session->ordered_samples.max_timestamp;
+	int ret = flush_sample_queue(session, tool);
+	if (!ret)
+		session->ordered_samples.next_flush = session->ordered_samples.max_timestamp;
 
-	return 0;
+	return ret;
 }
 
-static void __queue_sample_end(struct sample_queue *new, struct list_head *head)
+/* The queue is ordered by time */
+static void __queue_event(struct sample_queue *new, struct perf_session *s)
 {
-	struct sample_queue *iter;
+	struct ordered_samples *os = &s->ordered_samples;
+	struct sample_queue *sample = os->last_sample;
+	u64 timestamp = new->timestamp;
+	struct list_head *p;
 
-	list_for_each_entry_reverse(iter, head, list) {
-		if (iter->timestamp < new->timestamp) {
-			list_add(&new->list, &iter->list);
-			return;
-		}
+	++os->nr_samples;
+	os->last_sample = new;
+
+	if (!sample) {
+		list_add(&new->list, &os->samples);
+		os->max_timestamp = timestamp;
+		return;
 	}
 
-	list_add(&new->list, head);
+	/*
+	 * last_sample might point to some random place in the list as it's
+	 * the last queued event. We expect that the new event is close to
+	 * this.
+	 */
+	if (sample->timestamp <= timestamp) {
+		while (sample->timestamp <= timestamp) {
+			p = sample->list.next;
+			if (p == &os->samples) {
+				list_add_tail(&new->list, &os->samples);
+				os->max_timestamp = timestamp;
+				return;
+			}
+			sample = list_entry(p, struct sample_queue, list);
+		}
+		list_add_tail(&new->list, &sample->list);
+	} else {
+		while (sample->timestamp > timestamp) {
+			p = sample->list.prev;
+			if (p == &os->samples) {
+				list_add(&new->list, &os->samples);
+				return;
+			}
+			sample = list_entry(p, struct sample_queue, list);
+		}
+		list_add(&new->list, &sample->list);
+	}
 }
 
-static void __queue_sample_before(struct sample_queue *new,
-				  struct sample_queue *iter,
-				  struct list_head *head)
+#define MAX_SAMPLE_BUFFER	(64 * 1024 / sizeof(struct sample_queue))
+
+int perf_session_queue_event(struct perf_session *s, union perf_event *event,
+				    struct perf_sample *sample, u64 file_offset)
 {
-	list_for_each_entry_continue_reverse(iter, head, list) {
-		if (iter->timestamp < new->timestamp) {
-			list_add(&new->list, &iter->list);
-			return;
-		}
+	struct ordered_samples *os = &s->ordered_samples;
+	struct list_head *sc = &os->sample_cache;
+	u64 timestamp = sample->time;
+	struct sample_queue *new;
+
+	if (!timestamp || timestamp == ~0ULL)
+		return -ETIME;
+
+	if (timestamp < s->ordered_samples.last_flush) {
+		printf("Warning: Timestamp below last timeslice flush\n");
+		return -EINVAL;
 	}
 
-	list_add(&new->list, head);
+	if (!list_empty(sc)) {
+		new = list_entry(sc->next, struct sample_queue, list);
+		list_del(&new->list);
+	} else if (os->sample_buffer) {
+		new = os->sample_buffer + os->sample_buffer_idx;
+		if (++os->sample_buffer_idx == MAX_SAMPLE_BUFFER)
+			os->sample_buffer = NULL;
+	} else {
+		os->sample_buffer = malloc(MAX_SAMPLE_BUFFER * sizeof(*new));
+		if (!os->sample_buffer)
+			return -ENOMEM;
+		list_add(&os->sample_buffer->list, &os->to_free);
+		os->sample_buffer_idx = 2;
+		new = os->sample_buffer + 1;
+	}
+
+	new->timestamp = timestamp;
+	new->file_offset = file_offset;
+	new->event = event;
+
+	__queue_event(new, s);
+
+	return 0;
 }
 
-static void __queue_sample_after(struct sample_queue *new,
-				 struct sample_queue *iter,
-				 struct list_head *head)
+static void callchain__printf(struct perf_sample *sample)
 {
-	list_for_each_entry_continue(iter, head, list) {
-		if (iter->timestamp > new->timestamp) {
-			list_add_tail(&new->list, &iter->list);
-			return;
-		}
+	unsigned int i;
+
+	printf("... chain: nr:%" PRIu64 "\n", sample->callchain->nr);
+
+	for (i = 0; i < sample->callchain->nr; i++)
+		printf("..... %2d: %016" PRIx64 "\n",
+		       i, sample->callchain->ips[i]);
+}
+
+static void branch_stack__printf(struct perf_sample *sample)
+{
+	uint64_t i;
+
+	printf("... branch stack: nr:%" PRIu64 "\n", sample->branch_stack->nr);
+
+	for (i = 0; i < sample->branch_stack->nr; i++)
+		printf("..... %2"PRIu64": %016" PRIx64 " -> %016" PRIx64 "\n",
+			i, sample->branch_stack->entries[i].from,
+			sample->branch_stack->entries[i].to);
+}
+
+static void regs_dump__printf(u64 mask, u64 *regs)
+{
+	unsigned rid, i = 0;
+
+	for_each_set_bit(rid, (unsigned long *) &mask, sizeof(mask) * 8) {
+		u64 val = regs[i++];
+
+		printf(".... %-5s 0x%" PRIx64 "\n",
+		       perf_reg_name(rid), val);
 	}
-	list_add_tail(&new->list, head);
 }
 
-/* The queue is ordered by time */
-static void __queue_sample_event(struct sample_queue *new,
-				 struct perf_session *s)
+static void regs_user__printf(struct perf_sample *sample)
 {
-	struct sample_queue *last_inserted = s->ordered_samples.last_inserted;
-	struct list_head *head = &s->ordered_samples.samples_head;
+	struct regs_dump *user_regs = &sample->user_regs;
 
+	if (user_regs->regs) {
+		u64 mask = user_regs->mask;
+		printf("... user regs: mask 0x%" PRIx64 "\n", mask);
+		regs_dump__printf(mask, user_regs->regs);
+	}
+}
 
-	if (!last_inserted) {
-		__queue_sample_end(new, head);
+static void stack_user__printf(struct stack_dump *dump)
+{
+	printf("... ustack: size %" PRIu64 ", offset 0x%x\n",
+	       dump->size, dump->offset);
+}
+
+static void perf_session__print_tstamp(struct perf_session *session,
+				       union perf_event *event,
+				       struct perf_sample *sample)
+{
+	u64 sample_type = __perf_evlist__combined_sample_type(session->evlist);
+
+	if (event->header.type != PERF_RECORD_SAMPLE &&
+	    !perf_evlist__sample_id_all(session->evlist)) {
+		fputs("-1 -1 ", stdout);
 		return;
 	}
 
-	/*
-	 * Most of the time the current event has a timestamp
-	 * very close to the last event inserted, unless we just switched
-	 * to another event buffer. Having a sorting based on a list and
-	 * on the last inserted event that is close to the current one is
-	 * probably more efficient than an rbtree based sorting.
-	 */
-	if (last_inserted->timestamp >= new->timestamp)
-		__queue_sample_before(new, last_inserted, head);
-	else
-		__queue_sample_after(new, last_inserted, head);
+	if ((sample_type & PERF_SAMPLE_CPU))
+		printf("%u ", sample->cpu);
+
+	if (sample_type & PERF_SAMPLE_TIME)
+		printf("%" PRIu64 " ", sample->time);
 }
 
-static int queue_sample_event(event_t *event, struct sample_data *data,
-			      struct perf_session *s)
+static void sample_read__printf(struct perf_sample *sample, u64 read_format)
 {
-	u64 timestamp = data->time;
-	struct sample_queue *new;
+	printf("... sample_read:\n");
 
+	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+		printf("...... time enabled %016" PRIx64 "\n",
+		       sample->read.time_enabled);
 
-	if (timestamp < s->ordered_samples.last_flush) {
-		printf("Warning: Timestamp below last timeslice flush\n");
-		return -EINVAL;
-	}
+	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+		printf("...... time running %016" PRIx64 "\n",
+		       sample->read.time_running);
 
-	new = malloc(sizeof(*new));
-	if (!new)
-		return -ENOMEM;
+	if (read_format & PERF_FORMAT_GROUP) {
+		u64 i;
 
-	new->timestamp = timestamp;
+		printf(".... group nr %" PRIu64 "\n", sample->read.group.nr);
 
-	new->event = malloc(event->header.size);
-	if (!new->event) {
-		free(new);
-		return -ENOMEM;
-	}
+		for (i = 0; i < sample->read.group.nr; i++) {
+			struct sample_read_value *value;
+
+			value = &sample->read.group.values[i];
+			printf("..... id %016" PRIx64
+			       ", value %016" PRIx64 "\n",
+			       value->id, value->value);
+		}
+	} else
+		printf("..... id %016" PRIx64 ", value %016" PRIx64 "\n",
+			sample->read.one.id, sample->read.one.value);
+}
 
-	memcpy(new->event, event, event->header.size);
+static void dump_event(struct perf_session *session, union perf_event *event,
+		       u64 file_offset, struct perf_sample *sample)
+{
+	if (!dump_trace)
+		return;
 
-	__queue_sample_event(new, s);
-	s->ordered_samples.last_inserted = new;
+	printf("\n%#" PRIx64 " [%#x]: event: %d\n",
+	       file_offset, event->header.size, event->header.type);
 
-	if (new->timestamp > s->ordered_samples.max_timestamp)
-		s->ordered_samples.max_timestamp = new->timestamp;
+	trace_event(event);
 
-	return 0;
+	if (sample)
+		perf_session__print_tstamp(session, event, sample);
+
+	printf("%#" PRIx64 " [%#x]: PERF_RECORD_%s", file_offset,
+	       event->header.size, perf_event__name(event->header.type));
 }
 
-static int perf_session__process_sample(event_t *event, struct perf_session *s,
-					struct perf_event_ops *ops)
+static void dump_sample(struct perf_evsel *evsel, union perf_event *event,
+			struct perf_sample *sample)
 {
-	struct sample_data data;
+	u64 sample_type;
 
-	if (!ops->ordered_samples)
-		return ops->sample(event, s);
+	if (!dump_trace)
+		return;
 
-	bzero(&data, sizeof(struct sample_data));
-	event__parse_sample(event, s->sample_type, &data);
+	printf("(IP, 0x%x): %d/%d: %#" PRIx64 " period: %" PRIu64 " addr: %#" PRIx64 "\n",
+	       event->header.misc, sample->pid, sample->tid, sample->ip,
+	       sample->period, sample->addr);
 
-	queue_sample_event(event, &data, s);
+	sample_type = evsel->attr.sample_type;
 
-	return 0;
+	if (sample_type & PERF_SAMPLE_CALLCHAIN)
+		callchain__printf(sample);
+
+	if (sample_type & PERF_SAMPLE_BRANCH_STACK)
+		branch_stack__printf(sample);
+
+	if (sample_type & PERF_SAMPLE_REGS_USER)
+		regs_user__printf(sample);
+
+	if (sample_type & PERF_SAMPLE_STACK_USER)
+		stack_user__printf(&sample->user_stack);
+
+	if (sample_type & PERF_SAMPLE_WEIGHT)
+		printf("... weight: %" PRIu64 "\n", sample->weight);
+
+	if (sample_type & PERF_SAMPLE_DATA_SRC)
+		printf(" . data_src: 0x%"PRIx64"\n", sample->data_src);
+
+	if (sample_type & PERF_SAMPLE_TRANSACTION)
+		printf("... transaction: %" PRIx64 "\n", sample->transaction);
+
+	if (sample_type & PERF_SAMPLE_READ)
+		sample_read__printf(sample, evsel->attr.read_format);
 }
 
-static int perf_session__process_event(struct perf_session *self,
-				       event_t *event,
-				       struct perf_event_ops *ops,
-				       u64 offset, u64 head)
+static struct machine *
+	perf_session__find_machine_for_cpumode(struct perf_session *session,
+					       union perf_event *event,
+					       struct perf_sample *sample)
 {
-	trace_event(event);
+	const u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+	struct machine *machine;
+
+	if (perf_guest &&
+	    ((cpumode == PERF_RECORD_MISC_GUEST_KERNEL) ||
+	     (cpumode == PERF_RECORD_MISC_GUEST_USER))) {
+		u32 pid;
+
+		if (event->header.type == PERF_RECORD_MMAP
+		    || event->header.type == PERF_RECORD_MMAP2)
+			pid = event->mmap.pid;
+		else
+			pid = sample->pid;
+
+		machine = perf_session__find_machine(session, pid);
+		if (!machine)
+			machine = perf_session__findnew_machine(session,
+						DEFAULT_GUEST_KERNEL_ID);
+		return machine;
+	}
+
+	return &session->machines.host;
+}
+
+static int deliver_sample_value(struct perf_session *session,
+				struct perf_tool *tool,
+				union perf_event *event,
+				struct perf_sample *sample,
+				struct sample_read_value *v,
+				struct machine *machine)
+{
+	struct perf_sample_id *sid;
+
+	sid = perf_evlist__id2sid(session->evlist, v->id);
+	if (sid) {
+		sample->id     = v->id;
+		sample->period = v->value - sid->period;
+		sid->period    = v->value;
+	}
 
-	if (event->header.type < PERF_RECORD_HEADER_MAX) {
-		dump_printf("%#Lx [%#x]: PERF_RECORD_%s",
-			    offset + head, event->header.size,
-			    event__name[event->header.type]);
-		hists__inc_nr_events(&self->hists, event->header.type);
+	if (!sid || sid->evsel == NULL) {
+		++session->stats.nr_unknown_id;
+		return 0;
 	}
 
-	if (self->header.needs_swap && event__swap_ops[event->header.type])
-		event__swap_ops[event->header.type](event);
+	return tool->sample(tool, event, sample, sid->evsel, machine);
+}
+
+static int deliver_sample_group(struct perf_session *session,
+				struct perf_tool *tool,
+				union  perf_event *event,
+				struct perf_sample *sample,
+				struct machine *machine)
+{
+	int ret = -EINVAL;
+	u64 i;
+
+	for (i = 0; i < sample->read.group.nr; i++) {
+		ret = deliver_sample_value(session, tool, event, sample,
+					   &sample->read.group.values[i],
+					   machine);
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+
+static int
+perf_session__deliver_sample(struct perf_session *session,
+			     struct perf_tool *tool,
+			     union  perf_event *event,
+			     struct perf_sample *sample,
+			     struct perf_evsel *evsel,
+			     struct machine *machine)
+{
+	/* We know evsel != NULL. */
+	u64 sample_type = evsel->attr.sample_type;
+	u64 read_format = evsel->attr.read_format;
+
+	/* Standard sample delievery. */
+	if (!(sample_type & PERF_SAMPLE_READ))
+		return tool->sample(tool, event, sample, evsel, machine);
+
+	/* For PERF_SAMPLE_READ we have either single or group mode. */
+	if (read_format & PERF_FORMAT_GROUP)
+		return deliver_sample_group(session, tool, event, sample,
+					    machine);
+	else
+		return deliver_sample_value(session, tool, event, sample,
+					    &sample->read.one, machine);
+}
+
+static int perf_session_deliver_event(struct perf_session *session,
+				      union perf_event *event,
+				      struct perf_sample *sample,
+				      struct perf_tool *tool,
+				      u64 file_offset)
+{
+	struct perf_evsel *evsel;
+	struct machine *machine;
+
+	dump_event(session, event, file_offset, sample);
+
+	evsel = perf_evlist__id2evsel(session->evlist, sample->id);
+	if (evsel != NULL && event->header.type != PERF_RECORD_SAMPLE) {
+		/*
+		 * XXX We're leaving PERF_RECORD_SAMPLE unnacounted here
+		 * because the tools right now may apply filters, discarding
+		 * some of the samples. For consistency, in the future we
+		 * should have something like nr_filtered_samples and remove
+		 * the sample->period from total_sample_period, etc, KISS for
+		 * now tho.
+		 *
+		 * Also testing against NULL allows us to handle files without
+		 * attr.sample_id_all and/or without PERF_SAMPLE_ID. In the
+		 * future probably it'll be a good idea to restrict event
+		 * processing via perf_session to files with both set.
+		 */
+		hists__inc_nr_events(&evsel->hists, event->header.type);
+	}
+
+	machine = perf_session__find_machine_for_cpumode(session, event,
+							 sample);
 
 	switch (event->header.type) {
 	case PERF_RECORD_SAMPLE:
-		return perf_session__process_sample(event, self, ops);
+		dump_sample(evsel, event, sample);
+		if (evsel == NULL) {
+			++session->stats.nr_unknown_id;
+			return 0;
+		}
+		if (machine == NULL) {
+			++session->stats.nr_unprocessable_samples;
+			return 0;
+		}
+		return perf_session__deliver_sample(session, tool, event,
+						    sample, evsel, machine);
 	case PERF_RECORD_MMAP:
-		return ops->mmap(event, self);
+		return tool->mmap(tool, event, sample, machine);
+	case PERF_RECORD_MMAP2:
+		return tool->mmap2(tool, event, sample, machine);
 	case PERF_RECORD_COMM:
-		return ops->comm(event, self);
+		return tool->comm(tool, event, sample, machine);
 	case PERF_RECORD_FORK:
-		return ops->fork(event, self);
+		return tool->fork(tool, event, sample, machine);
 	case PERF_RECORD_EXIT:
-		return ops->exit(event, self);
+		return tool->exit(tool, event, sample, machine);
 	case PERF_RECORD_LOST:
-		return ops->lost(event, self);
+		if (tool->lost == perf_event__process_lost)
+			session->stats.total_lost += event->lost.lost;
+		return tool->lost(tool, event, sample, machine);
 	case PERF_RECORD_READ:
-		return ops->read(event, self);
+		return tool->read(tool, event, sample, evsel, machine);
 	case PERF_RECORD_THROTTLE:
-		return ops->throttle(event, self);
+		return tool->throttle(tool, event, sample, machine);
 	case PERF_RECORD_UNTHROTTLE:
-		return ops->unthrottle(event, self);
+		return tool->unthrottle(tool, event, sample, machine);
+	default:
+		++session->stats.nr_unknown_events;
+		return -1;
+	}
+}
+
+static int perf_session__process_user_event(struct perf_session *session, union perf_event *event,
+					    struct perf_tool *tool, u64 file_offset)
+{
+	int fd = perf_data_file__fd(session->file);
+	int err;
+
+	dump_event(session, event, file_offset, NULL);
+
+	/* These events are processed right away */
+	switch (event->header.type) {
 	case PERF_RECORD_HEADER_ATTR:
-		return ops->attr(event, self);
+		err = tool->attr(tool, event, &session->evlist);
+		if (err == 0)
+			perf_session__set_id_hdr_size(session);
+		return err;
 	case PERF_RECORD_HEADER_EVENT_TYPE:
-		return ops->event_type(event, self);
+		/*
+		 * Depreceated, but we need to handle it for sake
+		 * of old data files create in pipe mode.
+		 */
+		return 0;
 	case PERF_RECORD_HEADER_TRACING_DATA:
 		/* setup for reading amidst mmap */
-		lseek(self->fd, offset + head, SEEK_SET);
-		return ops->tracing_data(event, self);
+		lseek(fd, file_offset, SEEK_SET);
+		return tool->tracing_data(tool, event, session);
 	case PERF_RECORD_HEADER_BUILD_ID:
-		return ops->build_id(event, self);
+		return tool->build_id(tool, event, session);
 	case PERF_RECORD_FINISHED_ROUND:
-		return ops->finished_round(event, self, ops);
+		return tool->finished_round(tool, event, session);
 	default:
-		++self->hists.stats.nr_unknown_events;
-		return -1;
+		return -EINVAL;
 	}
 }
 
-void perf_event_header__bswap(struct perf_event_header *self)
+static void event_swap(union perf_event *event, bool sample_id_all)
 {
-	self->type = bswap_32(self->type);
-	self->misc = bswap_16(self->misc);
-	self->size = bswap_16(self->size);
+	perf_event__swap_op swap;
+
+	swap = perf_event__swap_ops[event->header.type];
+	if (swap)
+		swap(event, sample_id_all);
 }
 
-static struct thread *perf_session__register_idle_thread(struct perf_session *self)
+static int perf_session__process_event(struct perf_session *session,
+				       union perf_event *event,
+				       struct perf_tool *tool,
+				       u64 file_offset)
 {
-	struct thread *thread = perf_session__findnew(self, 0);
+	struct perf_sample sample;
+	int ret;
+
+	if (session->header.needs_swap)
+		event_swap(event, perf_evlist__sample_id_all(session->evlist));
 
-	if (thread == NULL || thread__set_comm(thread, "swapper")) {
+	if (event->header.type >= PERF_RECORD_HEADER_MAX)
+		return -EINVAL;
+
+	events_stats__inc(&session->stats, event->header.type);
+
+	if (event->header.type >= PERF_RECORD_USER_TYPE_START)
+		return perf_session__process_user_event(session, event, tool, file_offset);
+
+	/*
+	 * For all kernel events we get the sample data
+	 */
+	ret = perf_evlist__parse_sample(session->evlist, event, &sample);
+	if (ret)
+		return ret;
+
+	if (tool->ordered_samples) {
+		ret = perf_session_queue_event(session, event, &sample,
+					       file_offset);
+		if (ret != -ETIME)
+			return ret;
+	}
+
+	return perf_session_deliver_event(session, event, &sample, tool,
+					  file_offset);
+}
+
+void perf_event_header__bswap(struct perf_event_header *hdr)
+{
+	hdr->type = bswap_32(hdr->type);
+	hdr->misc = bswap_16(hdr->misc);
+	hdr->size = bswap_16(hdr->size);
+}
+
+struct thread *perf_session__findnew(struct perf_session *session, pid_t pid)
+{
+	return machine__findnew_thread(&session->machines.host, 0, pid);
+}
+
+static struct thread *perf_session__register_idle_thread(struct perf_session *session)
+{
+	struct thread *thread = perf_session__findnew(session, 0);
+
+	if (thread == NULL || thread__set_comm(thread, "swapper", 0)) {
 		pr_err("problem inserting idle task.\n");
 		thread = NULL;
 	}
@@ -623,41 +1098,71 @@ static struct thread *perf_session__register_idle_thread(struct perf_session *se
 	return thread;
 }
 
-int do_read(int fd, void *buf, size_t size)
+static void perf_session__warn_about_errors(const struct perf_session *session,
+					    const struct perf_tool *tool)
 {
-	void *buf_start = buf;
-
-	while (size) {
-		int ret = read(fd, buf, size);
+	if (tool->lost == perf_event__process_lost &&
+	    session->stats.nr_events[PERF_RECORD_LOST] != 0) {
+		ui__warning("Processed %d events and lost %d chunks!\n\n"
+			    "Check IO/CPU overload!\n\n",
+			    session->stats.nr_events[0],
+			    session->stats.nr_events[PERF_RECORD_LOST]);
+	}
 
-		if (ret <= 0)
-			return ret;
+	if (session->stats.nr_unknown_events != 0) {
+		ui__warning("Found %u unknown events!\n\n"
+			    "Is this an older tool processing a perf.data "
+			    "file generated by a more recent tool?\n\n"
+			    "If that is not the case, consider "
+			    "reporting to linux-kernel@vger.kernel.org.\n\n",
+			    session->stats.nr_unknown_events);
+	}
 
-		size -= ret;
-		buf += ret;
+	if (session->stats.nr_unknown_id != 0) {
+		ui__warning("%u samples with id not present in the header\n",
+			    session->stats.nr_unknown_id);
 	}
 
-	return buf - buf_start;
+ 	if (session->stats.nr_invalid_chains != 0) {
+ 		ui__warning("Found invalid callchains!\n\n"
+ 			    "%u out of %u events were discarded for this reason.\n\n"
+ 			    "Consider reporting to linux-kernel@vger.kernel.org.\n\n",
+ 			    session->stats.nr_invalid_chains,
+ 			    session->stats.nr_events[PERF_RECORD_SAMPLE]);
+ 	}
+
+	if (session->stats.nr_unprocessable_samples != 0) {
+		ui__warning("%u unprocessable samples recorded.\n"
+			    "Do you have a KVM guest running and not using 'perf kvm'?\n",
+			    session->stats.nr_unprocessable_samples);
+	}
 }
 
-#define session_done()	(*(volatile int *)(&session_done))
 volatile int session_done;
 
-static int __perf_session__process_pipe_events(struct perf_session *self,
-					       struct perf_event_ops *ops)
+static int __perf_session__process_pipe_events(struct perf_session *session,
+					       struct perf_tool *tool)
 {
-	event_t event;
-	uint32_t size;
+	int fd = perf_data_file__fd(session->file);
+	union perf_event *event;
+	uint32_t size, cur_size = 0;
+	void *buf = NULL;
 	int skip = 0;
 	u64 head;
-	int err;
+	ssize_t err;
 	void *p;
 
-	perf_event_ops__fill_defaults(ops);
+	perf_tool__fill_defaults(tool);
 
 	head = 0;
+	cur_size = sizeof(union perf_event);
+
+	buf = malloc(cur_size);
+	if (!buf)
+		return -errno;
 more:
-	err = do_read(self->fd, &event, sizeof(struct perf_event_header));
+	event = buf;
+	err = readn(fd, event, sizeof(struct perf_event_header));
 	if (err <= 0) {
 		if (err == 0)
 			goto done;
@@ -666,19 +1171,30 @@ more:
 		goto out_err;
 	}
 
-	if (self->header.needs_swap)
-		perf_event_header__bswap(&event.header);
+	if (session->header.needs_swap)
+		perf_event_header__bswap(&event->header);
 
-	size = event.header.size;
-	if (size == 0)
-		size = 8;
+	size = event->header.size;
+	if (size < sizeof(struct perf_event_header)) {
+		pr_err("bad event header size\n");
+		goto out_err;
+	}
 
-	p = &event;
+	if (size > cur_size) {
+		void *new = realloc(buf, size);
+		if (!new) {
+			pr_err("failed to allocate memory to read event\n");
+			goto out_err;
+		}
+		buf = new;
+		cur_size = size;
+		event = buf;
+	}
+	p = event;
 	p += sizeof(struct perf_event_header);
 
 	if (size - sizeof(struct perf_event_header)) {
-		err = do_read(self->fd, p,
-			      size - sizeof(struct perf_event_header));
+		err = readn(fd, p, size - sizeof(struct perf_event_header));
 		if (err <= 0) {
 			if (err == 0) {
 				pr_err("unexpected end of event stream\n");
@@ -690,187 +1206,202 @@ more:
 		}
 	}
 
-	if (size == 0 ||
-	    (skip = perf_session__process_event(self, &event, ops,
-						0, head)) < 0) {
-		dump_printf("%#Lx [%#x]: skipping unknown header type: %d\n",
-			    head, event.header.size, event.header.type);
-		/*
-		 * assume we lost track of the stream, check alignment, and
-		 * increment a single u64 in the hope to catch on again 'soon'.
-		 */
-		if (unlikely(head & 7))
-			head &= ~7ULL;
-
-		size = 8;
+	if ((skip = perf_session__process_event(session, event, tool, head)) < 0) {
+		pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n",
+		       head, event->header.size, event->header.type);
+		err = -EINVAL;
+		goto out_err;
 	}
 
 	head += size;
 
-	dump_printf("\n%#Lx [%#x]: event: %d\n",
-		    head, event.header.size, event.header.type);
-
 	if (skip > 0)
 		head += skip;
 
 	if (!session_done())
 		goto more;
 done:
-	err = 0;
+	/* do the final flush for ordered samples */
+	session->ordered_samples.next_flush = ULLONG_MAX;
+	err = flush_sample_queue(session, tool);
 out_err:
+	free(buf);
+	perf_session__warn_about_errors(session, tool);
+	perf_session_free_sample_buffers(session);
 	return err;
 }
 
-int __perf_session__process_events(struct perf_session *self,
+static union perf_event *
+fetch_mmaped_event(struct perf_session *session,
+		   u64 head, size_t mmap_size, char *buf)
+{
+	union perf_event *event;
+
+	/*
+	 * Ensure we have enough space remaining to read
+	 * the size of the event in the headers.
+	 */
+	if (head + sizeof(event->header) > mmap_size)
+		return NULL;
+
+	event = (union perf_event *)(buf + head);
+
+	if (session->header.needs_swap)
+		perf_event_header__bswap(&event->header);
+
+	if (head + event->header.size > mmap_size) {
+		/* We're not fetching the event so swap back again */
+		if (session->header.needs_swap)
+			perf_event_header__bswap(&event->header);
+		return NULL;
+	}
+
+	return event;
+}
+
+/*
+ * On 64bit we can mmap the data file in one go. No need for tiny mmap
+ * slices. On 32bit we use 32MB.
+ */
+#if BITS_PER_LONG == 64
+#define MMAP_SIZE ULLONG_MAX
+#define NUM_MMAPS 1
+#else
+#define MMAP_SIZE (32 * 1024 * 1024ULL)
+#define NUM_MMAPS 128
+#endif
+
+int __perf_session__process_events(struct perf_session *session,
 				   u64 data_offset, u64 data_size,
-				   u64 file_size, struct perf_event_ops *ops)
+				   u64 file_size, struct perf_tool *tool)
 {
-	int err, mmap_prot, mmap_flags;
-	u64 head, shift;
-	u64 offset = 0;
-	size_t	page_size;
-	event_t *event;
+	int fd = perf_data_file__fd(session->file);
+	u64 head, page_offset, file_offset, file_pos;
+	int err, mmap_prot, mmap_flags, map_idx = 0;
+	size_t	mmap_size;
+	char *buf, *mmaps[NUM_MMAPS];
+	union perf_event *event;
 	uint32_t size;
-	char *buf;
-	struct ui_progress *progress = ui_progress__new("Processing events...",
-							self->size);
-	if (progress == NULL)
-		return -1;
+	struct ui_progress prog;
 
-	perf_event_ops__fill_defaults(ops);
+	perf_tool__fill_defaults(tool);
 
-	page_size = sysconf(_SC_PAGESIZE);
+	page_offset = page_size * (data_offset / page_size);
+	file_offset = page_offset;
+	head = data_offset - page_offset;
 
-	head = data_offset;
-	shift = page_size * (head / page_size);
-	offset += shift;
-	head -= shift;
+	if (data_size && (data_offset + data_size < file_size))
+		file_size = data_offset + data_size;
+
+	ui_progress__init(&prog, file_size, "Processing events...");
+
+	mmap_size = MMAP_SIZE;
+	if (mmap_size > file_size)
+		mmap_size = file_size;
+
+	memset(mmaps, 0, sizeof(mmaps));
 
 	mmap_prot  = PROT_READ;
 	mmap_flags = MAP_SHARED;
 
-	if (self->header.needs_swap) {
+	if (session->header.needs_swap) {
 		mmap_prot  |= PROT_WRITE;
 		mmap_flags = MAP_PRIVATE;
 	}
 remap:
-	buf = mmap(NULL, page_size * self->mmap_window, mmap_prot,
-		   mmap_flags, self->fd, offset);
+	buf = mmap(NULL, mmap_size, mmap_prot, mmap_flags, fd,
+		   file_offset);
 	if (buf == MAP_FAILED) {
 		pr_err("failed to mmap file\n");
 		err = -errno;
 		goto out_err;
 	}
+	mmaps[map_idx] = buf;
+	map_idx = (map_idx + 1) & (ARRAY_SIZE(mmaps) - 1);
+	file_pos = file_offset + head;
 
 more:
-	event = (event_t *)(buf + head);
-	ui_progress__update(progress, offset);
-
-	if (self->header.needs_swap)
-		perf_event_header__bswap(&event->header);
-	size = event->header.size;
-	if (size == 0)
-		size = 8;
-
-	if (head + event->header.size >= page_size * self->mmap_window) {
-		int munmap_ret;
-
-		shift = page_size * (head / page_size);
-
-		munmap_ret = munmap(buf, page_size * self->mmap_window);
-		assert(munmap_ret == 0);
+	event = fetch_mmaped_event(session, head, mmap_size, buf);
+	if (!event) {
+		if (mmaps[map_idx]) {
+			munmap(mmaps[map_idx], mmap_size);
+			mmaps[map_idx] = NULL;
+		}
 
-		offset += shift;
-		head -= shift;
+		page_offset = page_size * (head / page_size);
+		file_offset += page_offset;
+		head -= page_offset;
 		goto remap;
 	}
 
 	size = event->header.size;
 
-	dump_printf("\n%#Lx [%#x]: event: %d\n",
-		    offset + head, event->header.size, event->header.type);
-
-	if (size == 0 ||
-	    perf_session__process_event(self, event, ops, offset, head) < 0) {
-		dump_printf("%#Lx [%#x]: skipping unknown header type: %d\n",
-			    offset + head, event->header.size,
-			    event->header.type);
-		/*
-		 * assume we lost track of the stream, check alignment, and
-		 * increment a single u64 in the hope to catch on again 'soon'.
-		 */
-		if (unlikely(head & 7))
-			head &= ~7ULL;
-
-		size = 8;
+	if (size < sizeof(struct perf_event_header) ||
+	    perf_session__process_event(session, event, tool, file_pos) < 0) {
+		pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n",
+		       file_offset + head, event->header.size,
+		       event->header.type);
+		err = -EINVAL;
+		goto out_err;
 	}
 
 	head += size;
+	file_pos += size;
+
+	ui_progress__update(&prog, size);
 
-	if (offset + head >= data_offset + data_size)
-		goto done;
+	if (session_done())
+		goto out;
 
-	if (offset + head < file_size)
+	if (file_pos < file_size)
 		goto more;
-done:
-	err = 0;
+
+out:
 	/* do the final flush for ordered samples */
-	self->ordered_samples.next_flush = ULLONG_MAX;
-	flush_sample_queue(self, ops);
+	session->ordered_samples.next_flush = ULLONG_MAX;
+	err = flush_sample_queue(session, tool);
 out_err:
-	ui_progress__delete(progress);
+	ui_progress__finish();
+	perf_session__warn_about_errors(session, tool);
+	perf_session_free_sample_buffers(session);
 	return err;
 }
 
-int perf_session__process_events(struct perf_session *self,
-				 struct perf_event_ops *ops)
+int perf_session__process_events(struct perf_session *session,
+				 struct perf_tool *tool)
 {
+	u64 size = perf_data_file__size(session->file);
 	int err;
 
-	if (perf_session__register_idle_thread(self) == NULL)
+	if (perf_session__register_idle_thread(session) == NULL)
 		return -ENOMEM;
 
-	if (!symbol_conf.full_paths) {
-		char bf[PATH_MAX];
-
-		if (getcwd(bf, sizeof(bf)) == NULL) {
-			err = -errno;
-out_getcwd_err:
-			pr_err("failed to get the current directory\n");
-			goto out_err;
-		}
-		self->cwd = strdup(bf);
-		if (self->cwd == NULL) {
-			err = -ENOMEM;
-			goto out_getcwd_err;
-		}
-		self->cwdlen = strlen(self->cwd);
-	}
-
-	if (!self->fd_pipe)
-		err = __perf_session__process_events(self,
-						     self->header.data_offset,
-						     self->header.data_size,
-						     self->size, ops);
+	if (!perf_data_file__is_pipe(session->file))
+		err = __perf_session__process_events(session,
+						     session->header.data_offset,
+						     session->header.data_size,
+						     size, tool);
 	else
-		err = __perf_session__process_pipe_events(self, ops);
-out_err:
+		err = __perf_session__process_pipe_events(session, tool);
+
 	return err;
 }
 
-bool perf_session__has_traces(struct perf_session *self, const char *msg)
+bool perf_session__has_traces(struct perf_session *session, const char *msg)
 {
-	if (!(self->sample_type & PERF_SAMPLE_RAW)) {
-		pr_err("No trace sample to read. Did you call 'perf %s'?\n", msg);
-		return false;
+	struct perf_evsel *evsel;
+
+	evlist__for_each(session->evlist, evsel) {
+		if (evsel->attr.type == PERF_TYPE_TRACEPOINT)
+			return true;
 	}
 
-	return true;
+	pr_err("No trace sample to read. Did you call 'perf %s'?\n", msg);
+	return false;
 }
 
-int perf_session__set_kallsyms_ref_reloc_sym(struct map **maps,
-					     const char *symbol_name,
-					     u64 addr)
+int maps__set_kallsyms_ref_reloc_sym(struct map **maps,
+				     const char *symbol_name, u64 addr)
 {
 	char *bracket;
 	enum map_type i;
@@ -900,16 +1431,243 @@ int perf_session__set_kallsyms_ref_reloc_sym(struct map **maps,
 	return 0;
 }
 
-size_t perf_session__fprintf_dsos(struct perf_session *self, FILE *fp)
+size_t perf_session__fprintf_dsos(struct perf_session *session, FILE *fp)
+{
+	return machines__fprintf_dsos(&session->machines, fp);
+}
+
+size_t perf_session__fprintf_dsos_buildid(struct perf_session *session, FILE *fp,
+					  bool (skip)(struct dso *dso, int parm), int parm)
+{
+	return machines__fprintf_dsos_buildid(&session->machines, fp, skip, parm);
+}
+
+size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp)
+{
+	struct perf_evsel *pos;
+	size_t ret = fprintf(fp, "Aggregated stats:\n");
+
+	ret += events_stats__fprintf(&session->stats, fp);
+
+	evlist__for_each(session->evlist, pos) {
+		ret += fprintf(fp, "%s stats:\n", perf_evsel__name(pos));
+		ret += events_stats__fprintf(&pos->hists.stats, fp);
+	}
+
+	return ret;
+}
+
+size_t perf_session__fprintf(struct perf_session *session, FILE *fp)
+{
+	/*
+	 * FIXME: Here we have to actually print all the machines in this
+	 * session, not just the host...
+	 */
+	return machine__fprintf(&session->machines.host, fp);
+}
+
+struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
+					      unsigned int type)
+{
+	struct perf_evsel *pos;
+
+	evlist__for_each(session->evlist, pos) {
+		if (pos->attr.type == type)
+			return pos;
+	}
+	return NULL;
+}
+
+void perf_evsel__print_ip(struct perf_evsel *evsel, struct perf_sample *sample,
+			  struct addr_location *al,
+			  unsigned int print_opts, unsigned int stack_depth)
+{
+	struct callchain_cursor_node *node;
+	int print_ip = print_opts & PRINT_IP_OPT_IP;
+	int print_sym = print_opts & PRINT_IP_OPT_SYM;
+	int print_dso = print_opts & PRINT_IP_OPT_DSO;
+	int print_symoffset = print_opts & PRINT_IP_OPT_SYMOFFSET;
+	int print_oneline = print_opts & PRINT_IP_OPT_ONELINE;
+	int print_srcline = print_opts & PRINT_IP_OPT_SRCLINE;
+	char s = print_oneline ? ' ' : '\t';
+
+	if (symbol_conf.use_callchain && sample->callchain) {
+		struct addr_location node_al;
+
+		if (machine__resolve_callchain(al->machine, evsel, al->thread,
+					       sample, NULL, NULL,
+					       PERF_MAX_STACK_DEPTH) != 0) {
+			if (verbose)
+				error("Failed to resolve callchain. Skipping\n");
+			return;
+		}
+		callchain_cursor_commit(&callchain_cursor);
+
+		if (print_symoffset)
+			node_al = *al;
+
+		while (stack_depth) {
+			u64 addr = 0;
+
+			node = callchain_cursor_current(&callchain_cursor);
+			if (!node)
+				break;
+
+			if (node->sym && node->sym->ignore)
+				goto next;
+
+			if (print_ip)
+				printf("%c%16" PRIx64, s, node->ip);
+
+			if (node->map)
+				addr = node->map->map_ip(node->map, node->ip);
+
+			if (print_sym) {
+				printf(" ");
+				if (print_symoffset) {
+					node_al.addr = addr;
+					node_al.map  = node->map;
+					symbol__fprintf_symname_offs(node->sym, &node_al, stdout);
+				} else
+					symbol__fprintf_symname(node->sym, stdout);
+			}
+
+			if (print_dso) {
+				printf(" (");
+				map__fprintf_dsoname(node->map, stdout);
+				printf(")");
+			}
+
+			if (print_srcline)
+				map__fprintf_srcline(node->map, addr, "\n  ",
+						     stdout);
+
+			if (!print_oneline)
+				printf("\n");
+
+			stack_depth--;
+next:
+			callchain_cursor_advance(&callchain_cursor);
+		}
+
+	} else {
+		if (al->sym && al->sym->ignore)
+			return;
+
+		if (print_ip)
+			printf("%16" PRIx64, sample->ip);
+
+		if (print_sym) {
+			printf(" ");
+			if (print_symoffset)
+				symbol__fprintf_symname_offs(al->sym, al,
+							     stdout);
+			else
+				symbol__fprintf_symname(al->sym, stdout);
+		}
+
+		if (print_dso) {
+			printf(" (");
+			map__fprintf_dsoname(al->map, stdout);
+			printf(")");
+		}
+
+		if (print_srcline)
+			map__fprintf_srcline(al->map, al->addr, "\n  ", stdout);
+	}
+}
+
+int perf_session__cpu_bitmap(struct perf_session *session,
+			     const char *cpu_list, unsigned long *cpu_bitmap)
+{
+	int i, err = -1;
+	struct cpu_map *map;
+
+	for (i = 0; i < PERF_TYPE_MAX; ++i) {
+		struct perf_evsel *evsel;
+
+		evsel = perf_session__find_first_evtype(session, i);
+		if (!evsel)
+			continue;
+
+		if (!(evsel->attr.sample_type & PERF_SAMPLE_CPU)) {
+			pr_err("File does not contain CPU events. "
+			       "Remove -c option to proceed.\n");
+			return -1;
+		}
+	}
+
+	map = cpu_map__new(cpu_list);
+	if (map == NULL) {
+		pr_err("Invalid cpu_list\n");
+		return -1;
+	}
+
+	for (i = 0; i < map->nr; i++) {
+		int cpu = map->map[i];
+
+		if (cpu >= MAX_NR_CPUS) {
+			pr_err("Requested CPU %d too large. "
+			       "Consider raising MAX_NR_CPUS\n", cpu);
+			goto out_delete_map;
+		}
+
+		set_bit(cpu, cpu_bitmap);
+	}
+
+	err = 0;
+
+out_delete_map:
+	cpu_map__delete(map);
+	return err;
+}
+
+void perf_session__fprintf_info(struct perf_session *session, FILE *fp,
+				bool full)
 {
-	return __dsos__fprintf(&self->host_machine.kernel_dsos, fp) +
-	       __dsos__fprintf(&self->host_machine.user_dsos, fp) +
-	       machines__fprintf_dsos(&self->machines, fp);
+	struct stat st;
+	int fd, ret;
+
+	if (session == NULL || fp == NULL)
+		return;
+
+	fd = perf_data_file__fd(session->file);
+
+	ret = fstat(fd, &st);
+	if (ret == -1)
+		return;
+
+	fprintf(fp, "# ========\n");
+	fprintf(fp, "# captured on: %s", ctime(&st.st_ctime));
+	perf_header__fprintf_info(session, fp, full);
+	fprintf(fp, "# ========\n#\n");
 }
 
-size_t perf_session__fprintf_dsos_buildid(struct perf_session *self, FILE *fp,
-					  bool with_hits)
+
+int __perf_session__set_tracepoints_handlers(struct perf_session *session,
+					     const struct perf_evsel_str_handler *assocs,
+					     size_t nr_assocs)
 {
-	size_t ret = machine__fprintf_dsos_buildid(&self->host_machine, fp, with_hits);
-	return ret + machines__fprintf_dsos_buildid(&self->machines, fp, with_hits);
+	struct perf_evsel *evsel;
+	size_t i;
+	int err;
+
+	for (i = 0; i < nr_assocs; i++) {
+		/*
+		 * Adding a handler for an event not in the session,
+		 * just ignore it.
+		 */
+		evsel = perf_evlist__find_tracepoint_by_name(session->evlist, assocs[i].name);
+		if (evsel == NULL)
+			continue;
+
+		err = -EEXIST;
+		if (evsel->handler != NULL)
+			goto out;
+		evsel->handler = assocs[i].handler;
+	}
+
+	err = 0;
+out:
+	return err;
 }
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 9fa0fc2a863..3140f8ae614 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -1,13 +1,16 @@
 #ifndef __PERF_SESSION_H
 #define __PERF_SESSION_H
 
+#include "trace-event.h"
 #include "hist.h"
 #include "event.h"
 #include "header.h"
+#include "machine.h"
 #include "symbol.h"
 #include "thread.h"
+#include "data.h"
 #include <linux/rbtree.h>
-#include "../../../include/linux/perf_event.h"
+#include <linux/perf_event.h>
 
 struct sample_queue;
 struct ip_callchain;
@@ -17,129 +20,110 @@ struct ordered_samples {
 	u64			last_flush;
 	u64			next_flush;
 	u64			max_timestamp;
-	struct list_head	samples_head;
-	struct sample_queue	*last_inserted;
+	struct list_head	samples;
+	struct list_head	sample_cache;
+	struct list_head	to_free;
+	struct sample_queue	*sample_buffer;
+	struct sample_queue	*last_sample;
+	int			sample_buffer_idx;
+	unsigned int		nr_samples;
 };
 
 struct perf_session {
 	struct perf_header	header;
-	unsigned long		size;
-	unsigned long		mmap_window;
-	struct rb_root		threads;
-	struct list_head	dead_threads;
-	struct thread		*last_match;
-	struct machine		host_machine;
-	struct rb_root		machines;
-	struct rb_root		hists_tree;
-	/*
-	 * FIXME: should point to the first entry in hists_tree and
-	 *        be a hists instance. Right now its only 'report'
-	 *        that is using ->hists_tree while all the rest use
-	 *        ->hists.
-	 */
-	struct hists		hists;
-	u64			sample_type;
-	int			fd;
-	bool			fd_pipe;
+	struct machines		machines;
+	struct perf_evlist	*evlist;
+	struct trace_event	tevent;
+	struct events_stats	stats;
 	bool			repipe;
-	int			cwdlen;
-	char			*cwd;
 	struct ordered_samples	ordered_samples;
-	char filename[0];
+	struct perf_data_file	*file;
 };
 
-struct perf_event_ops;
-
-typedef int (*event_op)(event_t *self, struct perf_session *session);
-typedef int (*event_op2)(event_t *self, struct perf_session *session,
-			 struct perf_event_ops *ops);
-
-struct perf_event_ops {
-	event_op	sample,
-			mmap,
-			comm,
-			fork,
-			exit,
-			lost,
-			read,
-			throttle,
-			unthrottle,
-			attr,
-			event_type,
-			tracing_data,
-			build_id;
-	event_op2	finished_round;
-	bool		ordered_samples;
-};
+#define PRINT_IP_OPT_IP		(1<<0)
+#define PRINT_IP_OPT_SYM		(1<<1)
+#define PRINT_IP_OPT_DSO		(1<<2)
+#define PRINT_IP_OPT_SYMOFFSET	(1<<3)
+#define PRINT_IP_OPT_ONELINE	(1<<4)
+#define PRINT_IP_OPT_SRCLINE	(1<<5)
+
+struct perf_tool;
 
-struct perf_session *perf_session__new(const char *filename, int mode, bool force, bool repipe);
-void perf_session__delete(struct perf_session *self);
+struct perf_session *perf_session__new(struct perf_data_file *file,
+				       bool repipe, struct perf_tool *tool);
+void perf_session__delete(struct perf_session *session);
 
-void perf_event_header__bswap(struct perf_event_header *self);
+void perf_event_header__bswap(struct perf_event_header *hdr);
 
-int __perf_session__process_events(struct perf_session *self,
+int __perf_session__process_events(struct perf_session *session,
 				   u64 data_offset, u64 data_size, u64 size,
-				   struct perf_event_ops *ops);
-int perf_session__process_events(struct perf_session *self,
-				 struct perf_event_ops *event_ops);
+				   struct perf_tool *tool);
+int perf_session__process_events(struct perf_session *session,
+				 struct perf_tool *tool);
 
-struct map_symbol *perf_session__resolve_callchain(struct perf_session *self,
-						   struct thread *thread,
-						   struct ip_callchain *chain,
-						   struct symbol **parent);
+int perf_session_queue_event(struct perf_session *s, union perf_event *event,
+			     struct perf_sample *sample, u64 file_offset);
 
-bool perf_session__has_traces(struct perf_session *self, const char *msg);
+void perf_tool__fill_defaults(struct perf_tool *tool);
 
-int perf_session__set_kallsyms_ref_reloc_sym(struct map **maps,
-					     const char *symbol_name,
-					     u64 addr);
+int perf_session__resolve_callchain(struct perf_session *session,
+				    struct perf_evsel *evsel,
+				    struct thread *thread,
+				    struct ip_callchain *chain,
+				    struct symbol **parent);
 
-void mem_bswap_64(void *src, int byte_size);
+bool perf_session__has_traces(struct perf_session *session, const char *msg);
 
-int perf_session__create_kernel_maps(struct perf_session *self);
+void perf_event__attr_swap(struct perf_event_attr *attr);
 
-int do_read(int fd, void *buf, size_t size);
-void perf_session__update_sample_type(struct perf_session *self);
-void perf_session__remove_thread(struct perf_session *self, struct thread *th);
+int perf_session__create_kernel_maps(struct perf_session *session);
 
-static inline
-struct machine *perf_session__find_host_machine(struct perf_session *self)
-{
-	return &self->host_machine;
-}
+void perf_session__set_id_hdr_size(struct perf_session *session);
 
 static inline
-struct machine *perf_session__find_machine(struct perf_session *self, pid_t pid)
+struct machine *perf_session__find_machine(struct perf_session *session, pid_t pid)
 {
-	if (pid == HOST_KERNEL_ID)
-		return &self->host_machine;
-	return machines__find(&self->machines, pid);
+	return machines__find(&session->machines, pid);
 }
 
 static inline
-struct machine *perf_session__findnew_machine(struct perf_session *self, pid_t pid)
+struct machine *perf_session__findnew_machine(struct perf_session *session, pid_t pid)
 {
-	if (pid == HOST_KERNEL_ID)
-		return &self->host_machine;
-	return machines__findnew(&self->machines, pid);
+	return machines__findnew(&session->machines, pid);
 }
 
-static inline
-void perf_session__process_machines(struct perf_session *self,
-				    machine__process_t process)
-{
-	process(&self->host_machine, self);
-	return machines__process(&self->machines, process, self);
-}
+struct thread *perf_session__findnew(struct perf_session *session, pid_t pid);
+size_t perf_session__fprintf(struct perf_session *session, FILE *fp);
 
-size_t perf_session__fprintf_dsos(struct perf_session *self, FILE *fp);
+size_t perf_session__fprintf_dsos(struct perf_session *session, FILE *fp);
 
-size_t perf_session__fprintf_dsos_buildid(struct perf_session *self,
-					  FILE *fp, bool with_hits);
+size_t perf_session__fprintf_dsos_buildid(struct perf_session *session, FILE *fp,
+					  bool (fn)(struct dso *dso, int parm), int parm);
 
-static inline
-size_t perf_session__fprintf_nr_events(struct perf_session *self, FILE *fp)
-{
-	return hists__fprintf_nr_events(&self->hists, fp);
-}
+size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp);
+
+struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
+					    unsigned int type);
+
+void perf_evsel__print_ip(struct perf_evsel *evsel, struct perf_sample *sample,
+			  struct addr_location *al,
+			  unsigned int print_opts, unsigned int stack_depth);
+
+int perf_session__cpu_bitmap(struct perf_session *session,
+			     const char *cpu_list, unsigned long *cpu_bitmap);
+
+void perf_session__fprintf_info(struct perf_session *s, FILE *fp, bool full);
+
+struct perf_evsel_str_handler;
+
+int __perf_session__set_tracepoints_handlers(struct perf_session *session,
+					     const struct perf_evsel_str_handler *assocs,
+					     size_t nr_assocs);
+
+#define perf_session__set_tracepoints_handlers(session, array) \
+	__perf_session__set_tracepoints_handlers(session, array, ARRAY_SIZE(array))
+
+extern volatile int session_done;
+
+#define session_done()	(*(volatile int *)(&session_done))
 #endif /* __PERF_SESSION_H */
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
new file mode 100644
index 00000000000..d0aee4b9dfd
--- /dev/null
+++ b/tools/perf/util/setup.py
@@ -0,0 +1,48 @@
+#!/usr/bin/python2
+
+from distutils.core import setup, Extension
+from os import getenv
+
+from distutils.command.build_ext   import build_ext   as _build_ext
+from distutils.command.install_lib import install_lib as _install_lib
+
+class build_ext(_build_ext):
+    def finalize_options(self):
+        _build_ext.finalize_options(self)
+        self.build_lib  = build_lib
+        self.build_temp = build_tmp
+
+class install_lib(_install_lib):
+    def finalize_options(self):
+        _install_lib.finalize_options(self)
+        self.build_dir = build_lib
+
+
+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')
+libtraceevent = getenv('LIBTRACEEVENT')
+libapikfs = getenv('LIBAPIKFS')
+
+ext_sources = [f.strip() for f in file('util/python-ext-sources')
+				if len(f.strip()) > 0 and f[0] != '#']
+
+perf = Extension('perf',
+		  sources = ext_sources,
+		  include_dirs = ['util/include'],
+		  extra_compile_args = cflags,
+		  extra_objects = [libtraceevent, libapikfs],
+                 )
+
+setup(name='perf',
+      version='0.1',
+      description='Interface with the Linux profiling infrastructure',
+      author='Arnaldo Carvalho de Melo',
+      author_email='acme@redhat.com',
+      license='GPLv2',
+      url='http://perf.wiki.kernel.org',
+      ext_modules=[perf],
+      cmdclass={'build_ext': build_ext, 'install_lib': install_lib})
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 2316cb5a411..1ec57dd8228 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -1,263 +1,1359 @@
+#include <sys/mman.h>
 #include "sort.h"
+#include "hist.h"
+#include "comm.h"
+#include "symbol.h"
+#include "evsel.h"
 
 regex_t		parent_regex;
 const char	default_parent_pattern[] = "^sys_|^do_page_fault";
 const char	*parent_pattern = default_parent_pattern;
 const char	default_sort_order[] = "comm,dso,symbol";
-const char	*sort_order = default_sort_order;
+const char	default_branch_sort_order[] = "comm,dso_from,symbol_from,dso_to,symbol_to";
+const char	default_mem_sort_order[] = "local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked";
+const char	default_top_sort_order[] = "dso,symbol";
+const char	default_diff_sort_order[] = "dso,symbol";
+const char	*sort_order;
+const char	*field_order;
+regex_t		ignore_callees_regex;
+int		have_ignore_callees = 0;
 int		sort__need_collapse = 0;
 int		sort__has_parent = 0;
+int		sort__has_sym = 0;
+int		sort__has_dso = 0;
+enum sort_mode	sort__mode = SORT_MODE__NORMAL;
 
-enum sort_type	sort__first_dimension;
 
-unsigned int dsos__col_width;
-unsigned int comms__col_width;
-unsigned int threads__col_width;
-static unsigned int parent_symbol__col_width;
-char * field_sep;
+static int repsep_snprintf(char *bf, size_t size, const char *fmt, ...)
+{
+	int n;
+	va_list ap;
+
+	va_start(ap, fmt);
+	n = vsnprintf(bf, size, fmt, ap);
+	if (symbol_conf.field_sep && n > 0) {
+		char *sep = bf;
+
+		while (1) {
+			sep = strchr(sep, *symbol_conf.field_sep);
+			if (sep == NULL)
+				break;
+			*sep = '.';
+		}
+	}
+	va_end(ap);
+
+	if (n >= (int)size)
+		return size - 1;
+	return n;
+}
+
+static int64_t cmp_null(const void *l, const void *r)
+{
+	if (!l && !r)
+		return 0;
+	else if (!l)
+		return -1;
+	else
+		return 1;
+}
 
-LIST_HEAD(hist_entry__sort_list);
+/* --sort pid */
 
-static int hist_entry__thread_snprintf(struct hist_entry *self, char *bf,
-				       size_t size, unsigned int width);
-static int hist_entry__comm_snprintf(struct hist_entry *self, char *bf,
-				     size_t size, unsigned int width);
-static int hist_entry__dso_snprintf(struct hist_entry *self, char *bf,
-				    size_t size, unsigned int width);
-static int hist_entry__sym_snprintf(struct hist_entry *self, char *bf,
-				    size_t size, unsigned int width);
-static int hist_entry__parent_snprintf(struct hist_entry *self, char *bf,
-				       size_t size, unsigned int width);
+static int64_t
+sort__thread_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	return right->thread->tid - left->thread->tid;
+}
+
+static int hist_entry__thread_snprintf(struct hist_entry *he, char *bf,
+				       size_t size, unsigned int width)
+{
+	const char *comm = thread__comm_str(he->thread);
+	return repsep_snprintf(bf, size, "%*s:%5d", width - 6,
+			       comm ?: "", he->thread->tid);
+}
 
 struct sort_entry sort_thread = {
 	.se_header	= "Command:  Pid",
 	.se_cmp		= sort__thread_cmp,
 	.se_snprintf	= hist_entry__thread_snprintf,
-	.se_width	= &threads__col_width,
+	.se_width_idx	= HISTC_THREAD,
 };
 
+/* --sort comm */
+
+static int64_t
+sort__comm_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	/* Compare the addr that should be unique among comm */
+	return comm__str(right->comm) - comm__str(left->comm);
+}
+
+static int64_t
+sort__comm_collapse(struct hist_entry *left, struct hist_entry *right)
+{
+	/* Compare the addr that should be unique among comm */
+	return comm__str(right->comm) - comm__str(left->comm);
+}
+
+static int64_t
+sort__comm_sort(struct hist_entry *left, struct hist_entry *right)
+{
+	return strcmp(comm__str(right->comm), comm__str(left->comm));
+}
+
+static int hist_entry__comm_snprintf(struct hist_entry *he, char *bf,
+				     size_t size, unsigned int width)
+{
+	return repsep_snprintf(bf, size, "%*s", width, comm__str(he->comm));
+}
+
 struct sort_entry sort_comm = {
 	.se_header	= "Command",
 	.se_cmp		= sort__comm_cmp,
 	.se_collapse	= sort__comm_collapse,
+	.se_sort	= sort__comm_sort,
 	.se_snprintf	= hist_entry__comm_snprintf,
-	.se_width	= &comms__col_width,
+	.se_width_idx	= HISTC_COMM,
 };
 
+/* --sort dso */
+
+static int64_t _sort__dso_cmp(struct map *map_l, struct map *map_r)
+{
+	struct dso *dso_l = map_l ? map_l->dso : NULL;
+	struct dso *dso_r = map_r ? map_r->dso : NULL;
+	const char *dso_name_l, *dso_name_r;
+
+	if (!dso_l || !dso_r)
+		return cmp_null(dso_r, dso_l);
+
+	if (verbose) {
+		dso_name_l = dso_l->long_name;
+		dso_name_r = dso_r->long_name;
+	} else {
+		dso_name_l = dso_l->short_name;
+		dso_name_r = dso_r->short_name;
+	}
+
+	return strcmp(dso_name_l, dso_name_r);
+}
+
+static int64_t
+sort__dso_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	return _sort__dso_cmp(right->ms.map, left->ms.map);
+}
+
+static int _hist_entry__dso_snprintf(struct map *map, char *bf,
+				     size_t size, unsigned int width)
+{
+	if (map && map->dso) {
+		const char *dso_name = !verbose ? map->dso->short_name :
+			map->dso->long_name;
+		return repsep_snprintf(bf, size, "%-*s", width, dso_name);
+	}
+
+	return repsep_snprintf(bf, size, "%-*s", width, "[unknown]");
+}
+
+static int hist_entry__dso_snprintf(struct hist_entry *he, char *bf,
+				    size_t size, unsigned int width)
+{
+	return _hist_entry__dso_snprintf(he->ms.map, bf, size, width);
+}
+
 struct sort_entry sort_dso = {
 	.se_header	= "Shared Object",
 	.se_cmp		= sort__dso_cmp,
 	.se_snprintf	= hist_entry__dso_snprintf,
-	.se_width	= &dsos__col_width,
+	.se_width_idx	= HISTC_DSO,
 };
 
+/* --sort symbol */
+
+static int64_t _sort__addr_cmp(u64 left_ip, u64 right_ip)
+{
+	return (int64_t)(right_ip - left_ip);
+}
+
+static int64_t _sort__sym_cmp(struct symbol *sym_l, struct symbol *sym_r)
+{
+	u64 ip_l, ip_r;
+
+	if (!sym_l || !sym_r)
+		return cmp_null(sym_l, sym_r);
+
+	if (sym_l == sym_r)
+		return 0;
+
+	ip_l = sym_l->start;
+	ip_r = sym_r->start;
+
+	return (int64_t)(ip_r - ip_l);
+}
+
+static int64_t
+sort__sym_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	int64_t ret;
+
+	if (!left->ms.sym && !right->ms.sym)
+		return _sort__addr_cmp(left->ip, right->ip);
+
+	/*
+	 * comparing symbol address alone is not enough since it's a
+	 * relative address within a dso.
+	 */
+	if (!sort__has_dso) {
+		ret = sort__dso_cmp(left, right);
+		if (ret != 0)
+			return ret;
+	}
+
+	return _sort__sym_cmp(left->ms.sym, right->ms.sym);
+}
+
+static int64_t
+sort__sym_sort(struct hist_entry *left, struct hist_entry *right)
+{
+	if (!left->ms.sym || !right->ms.sym)
+		return cmp_null(left->ms.sym, right->ms.sym);
+
+	return strcmp(right->ms.sym->name, left->ms.sym->name);
+}
+
+static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym,
+				     u64 ip, char level, char *bf, size_t size,
+				     unsigned int width)
+{
+	size_t ret = 0;
+
+	if (verbose) {
+		char o = map ? dso__symtab_origin(map->dso) : '!';
+		ret += repsep_snprintf(bf, size, "%-#*llx %c ",
+				       BITS_PER_LONG / 4 + 2, ip, o);
+	}
+
+	ret += repsep_snprintf(bf + ret, size - ret, "[%c] ", level);
+	if (sym && map) {
+		if (map->type == MAP__VARIABLE) {
+			ret += repsep_snprintf(bf + ret, size - ret, "%s", sym->name);
+			ret += repsep_snprintf(bf + ret, size - ret, "+0x%llx",
+					ip - map->unmap_ip(map, sym->start));
+			ret += repsep_snprintf(bf + ret, size - ret, "%-*s",
+				       width - ret, "");
+		} else {
+			ret += repsep_snprintf(bf + ret, size - ret, "%-*s",
+					       width - ret,
+					       sym->name);
+		}
+	} else {
+		size_t len = BITS_PER_LONG / 4;
+		ret += repsep_snprintf(bf + ret, size - ret, "%-#.*llx",
+				       len, ip);
+		ret += repsep_snprintf(bf + ret, size - ret, "%-*s",
+				       width - ret, "");
+	}
+
+	return ret;
+}
+
+static int hist_entry__sym_snprintf(struct hist_entry *he, char *bf,
+				    size_t size, unsigned int width)
+{
+	return _hist_entry__sym_snprintf(he->ms.map, he->ms.sym, he->ip,
+					 he->level, bf, size, width);
+}
+
 struct sort_entry sort_sym = {
 	.se_header	= "Symbol",
 	.se_cmp		= sort__sym_cmp,
+	.se_sort	= sort__sym_sort,
 	.se_snprintf	= hist_entry__sym_snprintf,
+	.se_width_idx	= HISTC_SYMBOL,
 };
 
+/* --sort srcline */
+
+static int64_t
+sort__srcline_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	if (!left->srcline) {
+		if (!left->ms.map)
+			left->srcline = SRCLINE_UNKNOWN;
+		else {
+			struct map *map = left->ms.map;
+			left->srcline = get_srcline(map->dso,
+					    map__rip_2objdump(map, left->ip));
+		}
+	}
+	if (!right->srcline) {
+		if (!right->ms.map)
+			right->srcline = SRCLINE_UNKNOWN;
+		else {
+			struct map *map = right->ms.map;
+			right->srcline = get_srcline(map->dso,
+					    map__rip_2objdump(map, right->ip));
+		}
+	}
+	return strcmp(right->srcline, left->srcline);
+}
+
+static int hist_entry__srcline_snprintf(struct hist_entry *he, char *bf,
+					size_t size,
+					unsigned int width __maybe_unused)
+{
+	return repsep_snprintf(bf, size, "%s", he->srcline);
+}
+
+struct sort_entry sort_srcline = {
+	.se_header	= "Source:Line",
+	.se_cmp		= sort__srcline_cmp,
+	.se_snprintf	= hist_entry__srcline_snprintf,
+	.se_width_idx	= HISTC_SRCLINE,
+};
+
+/* --sort parent */
+
+static int64_t
+sort__parent_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	struct symbol *sym_l = left->parent;
+	struct symbol *sym_r = right->parent;
+
+	if (!sym_l || !sym_r)
+		return cmp_null(sym_l, sym_r);
+
+	return strcmp(sym_r->name, sym_l->name);
+}
+
+static int hist_entry__parent_snprintf(struct hist_entry *he, char *bf,
+				       size_t size, unsigned int width)
+{
+	return repsep_snprintf(bf, size, "%-*s", width,
+			      he->parent ? he->parent->name : "[other]");
+}
+
 struct sort_entry sort_parent = {
 	.se_header	= "Parent symbol",
 	.se_cmp		= sort__parent_cmp,
 	.se_snprintf	= hist_entry__parent_snprintf,
-	.se_width	= &parent_symbol__col_width,
+	.se_width_idx	= HISTC_PARENT,
 };
 
-struct sort_dimension {
-	const char		*name;
-	struct sort_entry	*entry;
-	int			taken;
+/* --sort cpu */
+
+static int64_t
+sort__cpu_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	return right->cpu - left->cpu;
+}
+
+static int hist_entry__cpu_snprintf(struct hist_entry *he, char *bf,
+				    size_t size, unsigned int width)
+{
+	return repsep_snprintf(bf, size, "%*d", width, he->cpu);
+}
+
+struct sort_entry sort_cpu = {
+	.se_header      = "CPU",
+	.se_cmp	        = sort__cpu_cmp,
+	.se_snprintf    = hist_entry__cpu_snprintf,
+	.se_width_idx	= HISTC_CPU,
 };
 
-static struct sort_dimension sort_dimensions[] = {
-	{ .name = "pid",	.entry = &sort_thread,	},
-	{ .name = "comm",	.entry = &sort_comm,	},
-	{ .name = "dso",	.entry = &sort_dso,	},
-	{ .name = "symbol",	.entry = &sort_sym,	},
-	{ .name = "parent",	.entry = &sort_parent,	},
+/* sort keys for branch stacks */
+
+static int64_t
+sort__dso_from_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	return _sort__dso_cmp(left->branch_info->from.map,
+			      right->branch_info->from.map);
+}
+
+static int hist_entry__dso_from_snprintf(struct hist_entry *he, char *bf,
+				    size_t size, unsigned int width)
+{
+	return _hist_entry__dso_snprintf(he->branch_info->from.map,
+					 bf, size, width);
+}
+
+static int64_t
+sort__dso_to_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	return _sort__dso_cmp(left->branch_info->to.map,
+			      right->branch_info->to.map);
+}
+
+static int hist_entry__dso_to_snprintf(struct hist_entry *he, char *bf,
+				       size_t size, unsigned int width)
+{
+	return _hist_entry__dso_snprintf(he->branch_info->to.map,
+					 bf, size, width);
+}
+
+static int64_t
+sort__sym_from_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	struct addr_map_symbol *from_l = &left->branch_info->from;
+	struct addr_map_symbol *from_r = &right->branch_info->from;
+
+	if (!from_l->sym && !from_r->sym)
+		return _sort__addr_cmp(from_l->addr, from_r->addr);
+
+	return _sort__sym_cmp(from_l->sym, from_r->sym);
+}
+
+static int64_t
+sort__sym_to_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	struct addr_map_symbol *to_l = &left->branch_info->to;
+	struct addr_map_symbol *to_r = &right->branch_info->to;
+
+	if (!to_l->sym && !to_r->sym)
+		return _sort__addr_cmp(to_l->addr, to_r->addr);
+
+	return _sort__sym_cmp(to_l->sym, to_r->sym);
+}
+
+static int hist_entry__sym_from_snprintf(struct hist_entry *he, char *bf,
+					 size_t size, unsigned int width)
+{
+	struct addr_map_symbol *from = &he->branch_info->from;
+	return _hist_entry__sym_snprintf(from->map, from->sym, from->addr,
+					 he->level, bf, size, width);
+
+}
+
+static int hist_entry__sym_to_snprintf(struct hist_entry *he, char *bf,
+				       size_t size, unsigned int width)
+{
+	struct addr_map_symbol *to = &he->branch_info->to;
+	return _hist_entry__sym_snprintf(to->map, to->sym, to->addr,
+					 he->level, bf, size, width);
+
+}
+
+struct sort_entry sort_dso_from = {
+	.se_header	= "Source Shared Object",
+	.se_cmp		= sort__dso_from_cmp,
+	.se_snprintf	= hist_entry__dso_from_snprintf,
+	.se_width_idx	= HISTC_DSO_FROM,
 };
 
-int64_t cmp_null(void *l, void *r)
+struct sort_entry sort_dso_to = {
+	.se_header	= "Target Shared Object",
+	.se_cmp		= sort__dso_to_cmp,
+	.se_snprintf	= hist_entry__dso_to_snprintf,
+	.se_width_idx	= HISTC_DSO_TO,
+};
+
+struct sort_entry sort_sym_from = {
+	.se_header	= "Source Symbol",
+	.se_cmp		= sort__sym_from_cmp,
+	.se_snprintf	= hist_entry__sym_from_snprintf,
+	.se_width_idx	= HISTC_SYMBOL_FROM,
+};
+
+struct sort_entry sort_sym_to = {
+	.se_header	= "Target Symbol",
+	.se_cmp		= sort__sym_to_cmp,
+	.se_snprintf	= hist_entry__sym_to_snprintf,
+	.se_width_idx	= HISTC_SYMBOL_TO,
+};
+
+static int64_t
+sort__mispredict_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-	if (!l && !r)
-		return 0;
-	else if (!l)
-		return -1;
+	const unsigned char mp = left->branch_info->flags.mispred !=
+					right->branch_info->flags.mispred;
+	const unsigned char p = left->branch_info->flags.predicted !=
+					right->branch_info->flags.predicted;
+
+	return mp || p;
+}
+
+static int hist_entry__mispredict_snprintf(struct hist_entry *he, char *bf,
+				    size_t size, unsigned int width){
+	static const char *out = "N/A";
+
+	if (he->branch_info->flags.predicted)
+		out = "N";
+	else if (he->branch_info->flags.mispred)
+		out = "Y";
+
+	return repsep_snprintf(bf, size, "%-*s", width, out);
+}
+
+/* --sort daddr_sym */
+static int64_t
+sort__daddr_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	uint64_t l = 0, r = 0;
+
+	if (left->mem_info)
+		l = left->mem_info->daddr.addr;
+	if (right->mem_info)
+		r = right->mem_info->daddr.addr;
+
+	return (int64_t)(r - l);
+}
+
+static int hist_entry__daddr_snprintf(struct hist_entry *he, char *bf,
+				    size_t size, unsigned int width)
+{
+	uint64_t addr = 0;
+	struct map *map = NULL;
+	struct symbol *sym = NULL;
+
+	if (he->mem_info) {
+		addr = he->mem_info->daddr.addr;
+		map = he->mem_info->daddr.map;
+		sym = he->mem_info->daddr.sym;
+	}
+	return _hist_entry__sym_snprintf(map, sym, addr, he->level, bf, size,
+					 width);
+}
+
+static int64_t
+sort__dso_daddr_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	struct map *map_l = NULL;
+	struct map *map_r = NULL;
+
+	if (left->mem_info)
+		map_l = left->mem_info->daddr.map;
+	if (right->mem_info)
+		map_r = right->mem_info->daddr.map;
+
+	return _sort__dso_cmp(map_l, map_r);
+}
+
+static int hist_entry__dso_daddr_snprintf(struct hist_entry *he, char *bf,
+				    size_t size, unsigned int width)
+{
+	struct map *map = NULL;
+
+	if (he->mem_info)
+		map = he->mem_info->daddr.map;
+
+	return _hist_entry__dso_snprintf(map, bf, size, width);
+}
+
+static int64_t
+sort__locked_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	union perf_mem_data_src data_src_l;
+	union perf_mem_data_src data_src_r;
+
+	if (left->mem_info)
+		data_src_l = left->mem_info->data_src;
 	else
-		return 1;
+		data_src_l.mem_lock = PERF_MEM_LOCK_NA;
+
+	if (right->mem_info)
+		data_src_r = right->mem_info->data_src;
+	else
+		data_src_r.mem_lock = PERF_MEM_LOCK_NA;
+
+	return (int64_t)(data_src_r.mem_lock - data_src_l.mem_lock);
 }
 
-/* --sort pid */
+static int hist_entry__locked_snprintf(struct hist_entry *he, char *bf,
+				    size_t size, unsigned int width)
+{
+	const char *out;
+	u64 mask = PERF_MEM_LOCK_NA;
 
-int64_t
-sort__thread_cmp(struct hist_entry *left, struct hist_entry *right)
+	if (he->mem_info)
+		mask = he->mem_info->data_src.mem_lock;
+
+	if (mask & PERF_MEM_LOCK_NA)
+		out = "N/A";
+	else if (mask & PERF_MEM_LOCK_LOCKED)
+		out = "Yes";
+	else
+		out = "No";
+
+	return repsep_snprintf(bf, size, "%-*s", width, out);
+}
+
+static int64_t
+sort__tlb_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-	return right->thread->pid - left->thread->pid;
+	union perf_mem_data_src data_src_l;
+	union perf_mem_data_src data_src_r;
+
+	if (left->mem_info)
+		data_src_l = left->mem_info->data_src;
+	else
+		data_src_l.mem_dtlb = PERF_MEM_TLB_NA;
+
+	if (right->mem_info)
+		data_src_r = right->mem_info->data_src;
+	else
+		data_src_r.mem_dtlb = PERF_MEM_TLB_NA;
+
+	return (int64_t)(data_src_r.mem_dtlb - data_src_l.mem_dtlb);
 }
 
-static int repsep_snprintf(char *bf, size_t size, const char *fmt, ...)
+static const char * const tlb_access[] = {
+	"N/A",
+	"HIT",
+	"MISS",
+	"L1",
+	"L2",
+	"Walker",
+	"Fault",
+};
+#define NUM_TLB_ACCESS (sizeof(tlb_access)/sizeof(const char *))
+
+static int hist_entry__tlb_snprintf(struct hist_entry *he, char *bf,
+				    size_t size, unsigned int width)
 {
-	int n;
-	va_list ap;
+	char out[64];
+	size_t sz = sizeof(out) - 1; /* -1 for null termination */
+	size_t l = 0, i;
+	u64 m = PERF_MEM_TLB_NA;
+	u64 hit, miss;
 
-	va_start(ap, fmt);
-	n = vsnprintf(bf, size, fmt, ap);
-	if (field_sep && n > 0) {
-		char *sep = bf;
+	out[0] = '\0';
 
-		while (1) {
-			sep = strchr(sep, *field_sep);
-			if (sep == NULL)
-				break;
-			*sep = '.';
+	if (he->mem_info)
+		m = he->mem_info->data_src.mem_dtlb;
+
+	hit = m & PERF_MEM_TLB_HIT;
+	miss = m & PERF_MEM_TLB_MISS;
+
+	/* already taken care of */
+	m &= ~(PERF_MEM_TLB_HIT|PERF_MEM_TLB_MISS);
+
+	for (i = 0; m && i < NUM_TLB_ACCESS; i++, m >>= 1) {
+		if (!(m & 0x1))
+			continue;
+		if (l) {
+			strcat(out, " or ");
+			l += 4;
 		}
+		strncat(out, tlb_access[i], sz - l);
+		l += strlen(tlb_access[i]);
 	}
-	va_end(ap);
-	return n;
+	if (*out == '\0')
+		strcpy(out, "N/A");
+	if (hit)
+		strncat(out, " hit", sz - l);
+	if (miss)
+		strncat(out, " miss", sz - l);
+
+	return repsep_snprintf(bf, size, "%-*s", width, out);
 }
 
-static int hist_entry__thread_snprintf(struct hist_entry *self, char *bf,
-				       size_t size, unsigned int width)
+static int64_t
+sort__lvl_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	union perf_mem_data_src data_src_l;
+	union perf_mem_data_src data_src_r;
+
+	if (left->mem_info)
+		data_src_l = left->mem_info->data_src;
+	else
+		data_src_l.mem_lvl = PERF_MEM_LVL_NA;
+
+	if (right->mem_info)
+		data_src_r = right->mem_info->data_src;
+	else
+		data_src_r.mem_lvl = PERF_MEM_LVL_NA;
+
+	return (int64_t)(data_src_r.mem_lvl - data_src_l.mem_lvl);
+}
+
+static const char * const mem_lvl[] = {
+	"N/A",
+	"HIT",
+	"MISS",
+	"L1",
+	"LFB",
+	"L2",
+	"L3",
+	"Local RAM",
+	"Remote RAM (1 hop)",
+	"Remote RAM (2 hops)",
+	"Remote Cache (1 hop)",
+	"Remote Cache (2 hops)",
+	"I/O",
+	"Uncached",
+};
+#define NUM_MEM_LVL (sizeof(mem_lvl)/sizeof(const char *))
+
+static int hist_entry__lvl_snprintf(struct hist_entry *he, char *bf,
+				    size_t size, unsigned int width)
 {
-	return repsep_snprintf(bf, size, "%*s:%5d", width,
-			      self->thread->comm ?: "", self->thread->pid);
+	char out[64];
+	size_t sz = sizeof(out) - 1; /* -1 for null termination */
+	size_t i, l = 0;
+	u64 m =  PERF_MEM_LVL_NA;
+	u64 hit, miss;
+
+	if (he->mem_info)
+		m  = he->mem_info->data_src.mem_lvl;
+
+	out[0] = '\0';
+
+	hit = m & PERF_MEM_LVL_HIT;
+	miss = m & PERF_MEM_LVL_MISS;
+
+	/* already taken care of */
+	m &= ~(PERF_MEM_LVL_HIT|PERF_MEM_LVL_MISS);
+
+	for (i = 0; m && i < NUM_MEM_LVL; i++, m >>= 1) {
+		if (!(m & 0x1))
+			continue;
+		if (l) {
+			strcat(out, " or ");
+			l += 4;
+		}
+		strncat(out, mem_lvl[i], sz - l);
+		l += strlen(mem_lvl[i]);
+	}
+	if (*out == '\0')
+		strcpy(out, "N/A");
+	if (hit)
+		strncat(out, " hit", sz - l);
+	if (miss)
+		strncat(out, " miss", sz - l);
+
+	return repsep_snprintf(bf, size, "%-*s", width, out);
 }
 
-static int hist_entry__comm_snprintf(struct hist_entry *self, char *bf,
-				     size_t size, unsigned int width)
+static int64_t
+sort__snoop_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-	return repsep_snprintf(bf, size, "%*s", width, self->thread->comm);
+	union perf_mem_data_src data_src_l;
+	union perf_mem_data_src data_src_r;
+
+	if (left->mem_info)
+		data_src_l = left->mem_info->data_src;
+	else
+		data_src_l.mem_snoop = PERF_MEM_SNOOP_NA;
+
+	if (right->mem_info)
+		data_src_r = right->mem_info->data_src;
+	else
+		data_src_r.mem_snoop = PERF_MEM_SNOOP_NA;
+
+	return (int64_t)(data_src_r.mem_snoop - data_src_l.mem_snoop);
 }
 
-/* --sort dso */
+static const char * const snoop_access[] = {
+	"N/A",
+	"None",
+	"Miss",
+	"Hit",
+	"HitM",
+};
+#define NUM_SNOOP_ACCESS (sizeof(snoop_access)/sizeof(const char *))
 
-int64_t
-sort__dso_cmp(struct hist_entry *left, struct hist_entry *right)
+static int hist_entry__snoop_snprintf(struct hist_entry *he, char *bf,
+				    size_t size, unsigned int width)
 {
-	struct dso *dso_l = left->ms.map ? left->ms.map->dso : NULL;
-	struct dso *dso_r = right->ms.map ? right->ms.map->dso : NULL;
-	const char *dso_name_l, *dso_name_r;
+	char out[64];
+	size_t sz = sizeof(out) - 1; /* -1 for null termination */
+	size_t i, l = 0;
+	u64 m = PERF_MEM_SNOOP_NA;
 
-	if (!dso_l || !dso_r)
-		return cmp_null(dso_l, dso_r);
+	out[0] = '\0';
 
-	if (verbose) {
-		dso_name_l = dso_l->long_name;
-		dso_name_r = dso_r->long_name;
-	} else {
-		dso_name_l = dso_l->short_name;
-		dso_name_r = dso_r->short_name;
+	if (he->mem_info)
+		m = he->mem_info->data_src.mem_snoop;
+
+	for (i = 0; m && i < NUM_SNOOP_ACCESS; i++, m >>= 1) {
+		if (!(m & 0x1))
+			continue;
+		if (l) {
+			strcat(out, " or ");
+			l += 4;
+		}
+		strncat(out, snoop_access[i], sz - l);
+		l += strlen(snoop_access[i]);
 	}
 
-	return strcmp(dso_name_l, dso_name_r);
+	if (*out == '\0')
+		strcpy(out, "N/A");
+
+	return repsep_snprintf(bf, size, "%-*s", width, out);
 }
 
-static int hist_entry__dso_snprintf(struct hist_entry *self, char *bf,
+static inline  u64 cl_address(u64 address)
+{
+	/* return the cacheline of the address */
+	return (address & ~(cacheline_size - 1));
+}
+
+static int64_t
+sort__dcacheline_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	u64 l, r;
+	struct map *l_map, *r_map;
+
+	if (!left->mem_info)  return -1;
+	if (!right->mem_info) return 1;
+
+	/* group event types together */
+	if (left->cpumode > right->cpumode) return -1;
+	if (left->cpumode < right->cpumode) return 1;
+
+	l_map = left->mem_info->daddr.map;
+	r_map = right->mem_info->daddr.map;
+
+	/* if both are NULL, jump to sort on al_addr instead */
+	if (!l_map && !r_map)
+		goto addr;
+
+	if (!l_map) return -1;
+	if (!r_map) return 1;
+
+	if (l_map->maj > r_map->maj) return -1;
+	if (l_map->maj < r_map->maj) return 1;
+
+	if (l_map->min > r_map->min) return -1;
+	if (l_map->min < r_map->min) return 1;
+
+	if (l_map->ino > r_map->ino) return -1;
+	if (l_map->ino < r_map->ino) return 1;
+
+	if (l_map->ino_generation > r_map->ino_generation) return -1;
+	if (l_map->ino_generation < r_map->ino_generation) return 1;
+
+	/*
+	 * Addresses with no major/minor numbers are assumed to be
+	 * anonymous in userspace.  Sort those on pid then address.
+	 *
+	 * The kernel and non-zero major/minor mapped areas are
+	 * assumed to be unity mapped.  Sort those on address.
+	 */
+
+	if ((left->cpumode != PERF_RECORD_MISC_KERNEL) &&
+	    (!(l_map->flags & MAP_SHARED)) &&
+	    !l_map->maj && !l_map->min && !l_map->ino &&
+	    !l_map->ino_generation) {
+		/* userspace anonymous */
+
+		if (left->thread->pid_ > right->thread->pid_) return -1;
+		if (left->thread->pid_ < right->thread->pid_) return 1;
+	}
+
+addr:
+	/* al_addr does all the right addr - start + offset calculations */
+	l = cl_address(left->mem_info->daddr.al_addr);
+	r = cl_address(right->mem_info->daddr.al_addr);
+
+	if (l > r) return -1;
+	if (l < r) return 1;
+
+	return 0;
+}
+
+static int hist_entry__dcacheline_snprintf(struct hist_entry *he, char *bf,
+					  size_t size, unsigned int width)
+{
+
+	uint64_t addr = 0;
+	struct map *map = NULL;
+	struct symbol *sym = NULL;
+	char level = he->level;
+
+	if (he->mem_info) {
+		addr = cl_address(he->mem_info->daddr.al_addr);
+		map = he->mem_info->daddr.map;
+		sym = he->mem_info->daddr.sym;
+
+		/* print [s] for shared data mmaps */
+		if ((he->cpumode != PERF_RECORD_MISC_KERNEL) &&
+		     map && (map->type == MAP__VARIABLE) &&
+		    (map->flags & MAP_SHARED) &&
+		    (map->maj || map->min || map->ino ||
+		     map->ino_generation))
+			level = 's';
+		else if (!map)
+			level = 'X';
+	}
+	return _hist_entry__sym_snprintf(map, sym, addr, level, bf, size,
+					 width);
+}
+
+struct sort_entry sort_mispredict = {
+	.se_header	= "Branch Mispredicted",
+	.se_cmp		= sort__mispredict_cmp,
+	.se_snprintf	= hist_entry__mispredict_snprintf,
+	.se_width_idx	= HISTC_MISPREDICT,
+};
+
+static u64 he_weight(struct hist_entry *he)
+{
+	return he->stat.nr_events ? he->stat.weight / he->stat.nr_events : 0;
+}
+
+static int64_t
+sort__local_weight_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	return he_weight(left) - he_weight(right);
+}
+
+static int hist_entry__local_weight_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width)
 {
-	if (self->ms.map && self->ms.map->dso) {
-		const char *dso_name = !verbose ? self->ms.map->dso->short_name :
-						  self->ms.map->dso->long_name;
-		return repsep_snprintf(bf, size, "%-*s", width, dso_name);
+	return repsep_snprintf(bf, size, "%-*llu", width, he_weight(he));
+}
+
+struct sort_entry sort_local_weight = {
+	.se_header	= "Local Weight",
+	.se_cmp		= sort__local_weight_cmp,
+	.se_snprintf	= hist_entry__local_weight_snprintf,
+	.se_width_idx	= HISTC_LOCAL_WEIGHT,
+};
+
+static int64_t
+sort__global_weight_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	return left->stat.weight - right->stat.weight;
+}
+
+static int hist_entry__global_weight_snprintf(struct hist_entry *he, char *bf,
+					      size_t size, unsigned int width)
+{
+	return repsep_snprintf(bf, size, "%-*llu", width, he->stat.weight);
+}
+
+struct sort_entry sort_global_weight = {
+	.se_header	= "Weight",
+	.se_cmp		= sort__global_weight_cmp,
+	.se_snprintf	= hist_entry__global_weight_snprintf,
+	.se_width_idx	= HISTC_GLOBAL_WEIGHT,
+};
+
+struct sort_entry sort_mem_daddr_sym = {
+	.se_header	= "Data Symbol",
+	.se_cmp		= sort__daddr_cmp,
+	.se_snprintf	= hist_entry__daddr_snprintf,
+	.se_width_idx	= HISTC_MEM_DADDR_SYMBOL,
+};
+
+struct sort_entry sort_mem_daddr_dso = {
+	.se_header	= "Data Object",
+	.se_cmp		= sort__dso_daddr_cmp,
+	.se_snprintf	= hist_entry__dso_daddr_snprintf,
+	.se_width_idx	= HISTC_MEM_DADDR_SYMBOL,
+};
+
+struct sort_entry sort_mem_locked = {
+	.se_header	= "Locked",
+	.se_cmp		= sort__locked_cmp,
+	.se_snprintf	= hist_entry__locked_snprintf,
+	.se_width_idx	= HISTC_MEM_LOCKED,
+};
+
+struct sort_entry sort_mem_tlb = {
+	.se_header	= "TLB access",
+	.se_cmp		= sort__tlb_cmp,
+	.se_snprintf	= hist_entry__tlb_snprintf,
+	.se_width_idx	= HISTC_MEM_TLB,
+};
+
+struct sort_entry sort_mem_lvl = {
+	.se_header	= "Memory access",
+	.se_cmp		= sort__lvl_cmp,
+	.se_snprintf	= hist_entry__lvl_snprintf,
+	.se_width_idx	= HISTC_MEM_LVL,
+};
+
+struct sort_entry sort_mem_snoop = {
+	.se_header	= "Snoop",
+	.se_cmp		= sort__snoop_cmp,
+	.se_snprintf	= hist_entry__snoop_snprintf,
+	.se_width_idx	= HISTC_MEM_SNOOP,
+};
+
+struct sort_entry sort_mem_dcacheline = {
+	.se_header	= "Data Cacheline",
+	.se_cmp		= sort__dcacheline_cmp,
+	.se_snprintf	= hist_entry__dcacheline_snprintf,
+	.se_width_idx	= HISTC_MEM_DCACHELINE,
+};
+
+static int64_t
+sort__abort_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	return left->branch_info->flags.abort !=
+		right->branch_info->flags.abort;
+}
+
+static int hist_entry__abort_snprintf(struct hist_entry *he, char *bf,
+				    size_t size, unsigned int width)
+{
+	static const char *out = ".";
+
+	if (he->branch_info->flags.abort)
+		out = "A";
+	return repsep_snprintf(bf, size, "%-*s", width, out);
+}
+
+struct sort_entry sort_abort = {
+	.se_header	= "Transaction abort",
+	.se_cmp		= sort__abort_cmp,
+	.se_snprintf	= hist_entry__abort_snprintf,
+	.se_width_idx	= HISTC_ABORT,
+};
+
+static int64_t
+sort__in_tx_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	return left->branch_info->flags.in_tx !=
+		right->branch_info->flags.in_tx;
+}
+
+static int hist_entry__in_tx_snprintf(struct hist_entry *he, char *bf,
+				    size_t size, unsigned int width)
+{
+	static const char *out = ".";
+
+	if (he->branch_info->flags.in_tx)
+		out = "T";
+
+	return repsep_snprintf(bf, size, "%-*s", width, out);
+}
+
+struct sort_entry sort_in_tx = {
+	.se_header	= "Branch in transaction",
+	.se_cmp		= sort__in_tx_cmp,
+	.se_snprintf	= hist_entry__in_tx_snprintf,
+	.se_width_idx	= HISTC_IN_TX,
+};
+
+static int64_t
+sort__transaction_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	return left->transaction - right->transaction;
+}
+
+static inline char *add_str(char *p, const char *str)
+{
+	strcpy(p, str);
+	return p + strlen(str);
+}
+
+static struct txbit {
+	unsigned flag;
+	const char *name;
+	int skip_for_len;
+} txbits[] = {
+	{ PERF_TXN_ELISION,        "EL ",        0 },
+	{ PERF_TXN_TRANSACTION,    "TX ",        1 },
+	{ PERF_TXN_SYNC,           "SYNC ",      1 },
+	{ PERF_TXN_ASYNC,          "ASYNC ",     0 },
+	{ PERF_TXN_RETRY,          "RETRY ",     0 },
+	{ PERF_TXN_CONFLICT,       "CON ",       0 },
+	{ PERF_TXN_CAPACITY_WRITE, "CAP-WRITE ", 1 },
+	{ PERF_TXN_CAPACITY_READ,  "CAP-READ ",  0 },
+	{ 0, NULL, 0 }
+};
+
+int hist_entry__transaction_len(void)
+{
+	int i;
+	int len = 0;
+
+	for (i = 0; txbits[i].name; i++) {
+		if (!txbits[i].skip_for_len)
+			len += strlen(txbits[i].name);
+	}
+	len += 4; /* :XX<space> */
+	return len;
+}
+
+static int hist_entry__transaction_snprintf(struct hist_entry *he, char *bf,
+					    size_t size, unsigned int width)
+{
+	u64 t = he->transaction;
+	char buf[128];
+	char *p = buf;
+	int i;
+
+	buf[0] = 0;
+	for (i = 0; txbits[i].name; i++)
+		if (txbits[i].flag & t)
+			p = add_str(p, txbits[i].name);
+	if (t && !(t & (PERF_TXN_SYNC|PERF_TXN_ASYNC)))
+		p = add_str(p, "NEITHER ");
+	if (t & PERF_TXN_ABORT_MASK) {
+		sprintf(p, ":%" PRIx64,
+			(t & PERF_TXN_ABORT_MASK) >>
+			PERF_TXN_ABORT_SHIFT);
+		p += strlen(p);
 	}
 
-	return repsep_snprintf(bf, size, "%*Lx", width, self->ip);
+	return repsep_snprintf(bf, size, "%-*s", width, buf);
 }
 
-/* --sort symbol */
+struct sort_entry sort_transaction = {
+	.se_header	= "Transaction                ",
+	.se_cmp		= sort__transaction_cmp,
+	.se_snprintf	= hist_entry__transaction_snprintf,
+	.se_width_idx	= HISTC_TRANSACTION,
+};
 
-int64_t
-sort__sym_cmp(struct hist_entry *left, struct hist_entry *right)
+struct sort_dimension {
+	const char		*name;
+	struct sort_entry	*entry;
+	int			taken;
+};
+
+#define DIM(d, n, func) [d] = { .name = n, .entry = &(func) }
+
+static struct sort_dimension common_sort_dimensions[] = {
+	DIM(SORT_PID, "pid", sort_thread),
+	DIM(SORT_COMM, "comm", sort_comm),
+	DIM(SORT_DSO, "dso", sort_dso),
+	DIM(SORT_SYM, "symbol", sort_sym),
+	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_TRANSACTION, "transaction", sort_transaction),
+};
+
+#undef DIM
+
+#define DIM(d, n, func) [d - __SORT_BRANCH_STACK] = { .name = n, .entry = &(func) }
+
+static struct sort_dimension bstack_sort_dimensions[] = {
+	DIM(SORT_DSO_FROM, "dso_from", sort_dso_from),
+	DIM(SORT_DSO_TO, "dso_to", sort_dso_to),
+	DIM(SORT_SYM_FROM, "symbol_from", sort_sym_from),
+	DIM(SORT_SYM_TO, "symbol_to", sort_sym_to),
+	DIM(SORT_MISPREDICT, "mispredict", sort_mispredict),
+	DIM(SORT_IN_TX, "in_tx", sort_in_tx),
+	DIM(SORT_ABORT, "abort", sort_abort),
+};
+
+#undef DIM
+
+#define DIM(d, n, func) [d - __SORT_MEMORY_MODE] = { .name = n, .entry = &(func) }
+
+static struct sort_dimension memory_sort_dimensions[] = {
+	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),
+	DIM(SORT_MEM_DCACHELINE, "dcacheline", sort_mem_dcacheline),
+};
+
+#undef DIM
+
+struct hpp_dimension {
+	const char		*name;
+	struct perf_hpp_fmt	*fmt;
+	int			taken;
+};
+
+#define DIM(d, n) { .name = n, .fmt = &perf_hpp__format[d], }
+
+static struct hpp_dimension hpp_sort_dimensions[] = {
+	DIM(PERF_HPP__OVERHEAD, "overhead"),
+	DIM(PERF_HPP__OVERHEAD_SYS, "overhead_sys"),
+	DIM(PERF_HPP__OVERHEAD_US, "overhead_us"),
+	DIM(PERF_HPP__OVERHEAD_GUEST_SYS, "overhead_guest_sys"),
+	DIM(PERF_HPP__OVERHEAD_GUEST_US, "overhead_guest_us"),
+	DIM(PERF_HPP__OVERHEAD_ACC, "overhead_children"),
+	DIM(PERF_HPP__SAMPLES, "sample"),
+	DIM(PERF_HPP__PERIOD, "period"),
+};
+
+#undef DIM
+
+struct hpp_sort_entry {
+	struct perf_hpp_fmt hpp;
+	struct sort_entry *se;
+};
+
+bool perf_hpp__same_sort_entry(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b)
 {
-	u64 ip_l, ip_r;
+	struct hpp_sort_entry *hse_a;
+	struct hpp_sort_entry *hse_b;
 
-	if (left->ms.sym == right->ms.sym)
-		return 0;
+	if (!perf_hpp__is_sort_entry(a) || !perf_hpp__is_sort_entry(b))
+		return false;
 
-	ip_l = left->ms.sym ? left->ms.sym->start : left->ip;
-	ip_r = right->ms.sym ? right->ms.sym->start : right->ip;
+	hse_a = container_of(a, struct hpp_sort_entry, hpp);
+	hse_b = container_of(b, struct hpp_sort_entry, hpp);
 
-	return (int64_t)(ip_r - ip_l);
+	return hse_a->se == hse_b->se;
 }
 
-static int hist_entry__sym_snprintf(struct hist_entry *self, char *bf,
-				    size_t size, unsigned int width __used)
+void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists)
 {
-	size_t ret = 0;
+	struct hpp_sort_entry *hse;
 
-	if (verbose) {
-		char o = self->ms.map ? dso__symtab_origin(self->ms.map->dso) : '!';
-		ret += repsep_snprintf(bf, size, "%#018llx %c ", self->ip, o);
+	if (!perf_hpp__is_sort_entry(fmt))
+		return;
+
+	hse = container_of(fmt, struct hpp_sort_entry, hpp);
+	hists__new_col_len(hists, hse->se->se_width_idx,
+			   strlen(hse->se->se_header));
+}
+
+static int __sort__hpp_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+			      struct perf_evsel *evsel)
+{
+	struct hpp_sort_entry *hse;
+	size_t len;
+
+	hse = container_of(fmt, struct hpp_sort_entry, hpp);
+	len = hists__col_len(&evsel->hists, hse->se->se_width_idx);
+
+	return scnprintf(hpp->buf, hpp->size, "%*s", len, hse->se->se_header);
+}
+
+static int __sort__hpp_width(struct perf_hpp_fmt *fmt,
+			     struct perf_hpp *hpp __maybe_unused,
+			     struct perf_evsel *evsel)
+{
+	struct hpp_sort_entry *hse;
+
+	hse = container_of(fmt, struct hpp_sort_entry, hpp);
+
+	return hists__col_len(&evsel->hists, hse->se->se_width_idx);
+}
+
+static int __sort__hpp_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+			     struct hist_entry *he)
+{
+	struct hpp_sort_entry *hse;
+	size_t len;
+
+	hse = container_of(fmt, struct hpp_sort_entry, hpp);
+	len = hists__col_len(he->hists, hse->se->se_width_idx);
+
+	return hse->se->se_snprintf(he, hpp->buf, hpp->size, len);
+}
+
+static struct hpp_sort_entry *
+__sort_dimension__alloc_hpp(struct sort_dimension *sd)
+{
+	struct hpp_sort_entry *hse;
+
+	hse = malloc(sizeof(*hse));
+	if (hse == NULL) {
+		pr_err("Memory allocation failed\n");
+		return NULL;
 	}
 
-	ret += repsep_snprintf(bf + ret, size - ret, "[%c] ", self->level);
-	if (self->ms.sym)
-		ret += repsep_snprintf(bf + ret, size - ret, "%s",
-				       self->ms.sym->name);
-	else
-		ret += repsep_snprintf(bf + ret, size - ret, "%#016llx", self->ip);
+	hse->se = sd->entry;
+	hse->hpp.header = __sort__hpp_header;
+	hse->hpp.width = __sort__hpp_width;
+	hse->hpp.entry = __sort__hpp_entry;
+	hse->hpp.color = NULL;
 
-	return ret;
+	hse->hpp.cmp = sd->entry->se_cmp;
+	hse->hpp.collapse = sd->entry->se_collapse ? : sd->entry->se_cmp;
+	hse->hpp.sort = sd->entry->se_sort ? : hse->hpp.collapse;
+
+	INIT_LIST_HEAD(&hse->hpp.list);
+	INIT_LIST_HEAD(&hse->hpp.sort_list);
+	hse->hpp.elide = false;
+
+	return hse;
 }
 
-/* --sort comm */
+bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format)
+{
+	return format->header == __sort__hpp_header;
+}
 
-int64_t
-sort__comm_cmp(struct hist_entry *left, struct hist_entry *right)
+static int __sort_dimension__add_hpp_sort(struct sort_dimension *sd)
+{
+	struct hpp_sort_entry *hse = __sort_dimension__alloc_hpp(sd);
+
+	if (hse == NULL)
+		return -1;
+
+	perf_hpp__register_sort_field(&hse->hpp);
+	return 0;
+}
+
+static int __sort_dimension__add_hpp_output(struct sort_dimension *sd)
 {
-	return right->thread->pid - left->thread->pid;
+	struct hpp_sort_entry *hse = __sort_dimension__alloc_hpp(sd);
+
+	if (hse == NULL)
+		return -1;
+
+	perf_hpp__column_register(&hse->hpp);
+	return 0;
 }
 
-int64_t
-sort__comm_collapse(struct hist_entry *left, struct hist_entry *right)
+static int __sort_dimension__add(struct sort_dimension *sd)
 {
-	char *comm_l = left->thread->comm;
-	char *comm_r = right->thread->comm;
+	if (sd->taken)
+		return 0;
 
-	if (!comm_l || !comm_r)
-		return cmp_null(comm_l, comm_r);
+	if (__sort_dimension__add_hpp_sort(sd) < 0)
+		return -1;
 
-	return strcmp(comm_l, comm_r);
+	if (sd->entry->se_collapse)
+		sort__need_collapse = 1;
+
+	sd->taken = 1;
+
+	return 0;
 }
 
-/* --sort parent */
+static int __hpp_dimension__add(struct hpp_dimension *hd)
+{
+	if (!hd->taken) {
+		hd->taken = 1;
 
-int64_t
-sort__parent_cmp(struct hist_entry *left, struct hist_entry *right)
+		perf_hpp__register_sort_field(hd->fmt);
+	}
+	return 0;
+}
+
+static int __sort_dimension__add_output(struct sort_dimension *sd)
 {
-	struct symbol *sym_l = left->parent;
-	struct symbol *sym_r = right->parent;
+	if (sd->taken)
+		return 0;
 
-	if (!sym_l || !sym_r)
-		return cmp_null(sym_l, sym_r);
+	if (__sort_dimension__add_hpp_output(sd) < 0)
+		return -1;
 
-	return strcmp(sym_l->name, sym_r->name);
+	sd->taken = 1;
+	return 0;
 }
 
-static int hist_entry__parent_snprintf(struct hist_entry *self, char *bf,
-				       size_t size, unsigned int width)
+static int __hpp_dimension__add_output(struct hpp_dimension *hd)
 {
-	return repsep_snprintf(bf, size, "%-*s", width,
-			      self->parent ? self->parent->name : "[other]");
+	if (!hd->taken) {
+		hd->taken = 1;
+
+		perf_hpp__column_register(hd->fmt);
+	}
+	return 0;
 }
 
 int sort_dimension__add(const char *tok)
 {
 	unsigned int i;
 
-	for (i = 0; i < ARRAY_SIZE(sort_dimensions); i++) {
-		struct sort_dimension *sd = &sort_dimensions[i];
-
-		if (sd->taken)
-			continue;
+	for (i = 0; i < ARRAY_SIZE(common_sort_dimensions); i++) {
+		struct sort_dimension *sd = &common_sort_dimensions[i];
 
 		if (strncasecmp(tok, sd->name, strlen(tok)))
 			continue;
 
-		if (sd->entry->se_collapse)
-			sort__need_collapse = 1;
-
 		if (sd->entry == &sort_parent) {
 			int ret = regcomp(&parent_regex, parent_pattern, REG_EXTENDED);
 			if (ret) {
@@ -268,52 +1364,343 @@ int sort_dimension__add(const char *tok)
 				return -EINVAL;
 			}
 			sort__has_parent = 1;
+		} else if (sd->entry == &sort_sym) {
+			sort__has_sym = 1;
+		} else if (sd->entry == &sort_dso) {
+			sort__has_dso = 1;
 		}
 
-		if (list_empty(&hist_entry__sort_list)) {
-			if (!strcmp(sd->name, "pid"))
-				sort__first_dimension = SORT_PID;
-			else if (!strcmp(sd->name, "comm"))
-				sort__first_dimension = SORT_COMM;
-			else if (!strcmp(sd->name, "dso"))
-				sort__first_dimension = SORT_DSO;
-			else if (!strcmp(sd->name, "symbol"))
-				sort__first_dimension = SORT_SYM;
-			else if (!strcmp(sd->name, "parent"))
-				sort__first_dimension = SORT_PARENT;
-		}
+		return __sort_dimension__add(sd);
+	}
+
+	for (i = 0; i < ARRAY_SIZE(hpp_sort_dimensions); i++) {
+		struct hpp_dimension *hd = &hpp_sort_dimensions[i];
+
+		if (strncasecmp(tok, hd->name, strlen(tok)))
+			continue;
 
-		list_add_tail(&sd->entry->list, &hist_entry__sort_list);
-		sd->taken = 1;
+		return __hpp_dimension__add(hd);
+	}
+
+	for (i = 0; i < ARRAY_SIZE(bstack_sort_dimensions); i++) {
+		struct sort_dimension *sd = &bstack_sort_dimensions[i];
+
+		if (strncasecmp(tok, sd->name, strlen(tok)))
+			continue;
 
+		if (sort__mode != SORT_MODE__BRANCH)
+			return -EINVAL;
+
+		if (sd->entry == &sort_sym_from || sd->entry == &sort_sym_to)
+			sort__has_sym = 1;
+
+		__sort_dimension__add(sd);
+		return 0;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(memory_sort_dimensions); i++) {
+		struct sort_dimension *sd = &memory_sort_dimensions[i];
+
+		if (strncasecmp(tok, sd->name, strlen(tok)))
+			continue;
+
+		if (sort__mode != SORT_MODE__MEMORY)
+			return -EINVAL;
+
+		if (sd->entry == &sort_mem_daddr_sym)
+			sort__has_sym = 1;
+
+		__sort_dimension__add(sd);
 		return 0;
 	}
 
 	return -ESRCH;
 }
 
-void setup_sorting(const char * const usagestr[], const struct option *opts)
+static const char *get_default_sort_order(void)
 {
-	char *tmp, *tok, *str = strdup(sort_order);
+	const char *default_sort_orders[] = {
+		default_sort_order,
+		default_branch_sort_order,
+		default_mem_sort_order,
+		default_top_sort_order,
+		default_diff_sort_order,
+	};
+
+	BUG_ON(sort__mode >= ARRAY_SIZE(default_sort_orders));
+
+	return default_sort_orders[sort__mode];
+}
+
+static int __setup_sorting(void)
+{
+	char *tmp, *tok, *str;
+	const char *sort_keys = sort_order;
+	int ret = 0;
+
+	if (sort_keys == NULL) {
+		if (field_order) {
+			/*
+			 * If user specified field order but no sort order,
+			 * we'll honor it and not add default sort orders.
+			 */
+			return 0;
+		}
+
+		sort_keys = get_default_sort_order();
+	}
+
+	str = strdup(sort_keys);
+	if (str == NULL) {
+		error("Not enough memory to setup sort keys");
+		return -ENOMEM;
+	}
 
 	for (tok = strtok_r(str, ", ", &tmp);
 			tok; tok = strtok_r(NULL, ", ", &tmp)) {
-		if (sort_dimension__add(tok) < 0) {
+		ret = sort_dimension__add(tok);
+		if (ret == -EINVAL) {
+			error("Invalid --sort key: `%s'", tok);
+			break;
+		} else if (ret == -ESRCH) {
 			error("Unknown --sort key: `%s'", tok);
-			usage_with_options(usagestr, opts);
+			break;
 		}
 	}
 
 	free(str);
+	return ret;
+}
+
+void perf_hpp__set_elide(int idx, bool elide)
+{
+	struct perf_hpp_fmt *fmt;
+	struct hpp_sort_entry *hse;
+
+	perf_hpp__for_each_format(fmt) {
+		if (!perf_hpp__is_sort_entry(fmt))
+			continue;
+
+		hse = container_of(fmt, struct hpp_sort_entry, hpp);
+		if (hse->se->se_width_idx == idx) {
+			fmt->elide = elide;
+			break;
+		}
+	}
 }
 
-void sort_entry__setup_elide(struct sort_entry *self, struct strlist *list,
-			     const char *list_name, FILE *fp)
+static bool __get_elide(struct strlist *list, const char *list_name, FILE *fp)
 {
 	if (list && strlist__nr_entries(list) == 1) {
 		if (fp != NULL)
 			fprintf(fp, "# %s: %s\n", list_name,
 				strlist__entry(list, 0)->s);
-		self->elide = true;
+		return true;
 	}
+	return false;
+}
+
+static bool get_elide(int idx, FILE *output)
+{
+	switch (idx) {
+	case HISTC_SYMBOL:
+		return __get_elide(symbol_conf.sym_list, "symbol", output);
+	case HISTC_DSO:
+		return __get_elide(symbol_conf.dso_list, "dso", output);
+	case HISTC_COMM:
+		return __get_elide(symbol_conf.comm_list, "comm", output);
+	default:
+		break;
+	}
+
+	if (sort__mode != SORT_MODE__BRANCH)
+		return false;
+
+	switch (idx) {
+	case HISTC_SYMBOL_FROM:
+		return __get_elide(symbol_conf.sym_from_list, "sym_from", output);
+	case HISTC_SYMBOL_TO:
+		return __get_elide(symbol_conf.sym_to_list, "sym_to", output);
+	case HISTC_DSO_FROM:
+		return __get_elide(symbol_conf.dso_from_list, "dso_from", output);
+	case HISTC_DSO_TO:
+		return __get_elide(symbol_conf.dso_to_list, "dso_to", output);
+	default:
+		break;
+	}
+
+	return false;
+}
+
+void sort__setup_elide(FILE *output)
+{
+	struct perf_hpp_fmt *fmt;
+	struct hpp_sort_entry *hse;
+
+	perf_hpp__for_each_format(fmt) {
+		if (!perf_hpp__is_sort_entry(fmt))
+			continue;
+
+		hse = container_of(fmt, struct hpp_sort_entry, hpp);
+		fmt->elide = get_elide(hse->se->se_width_idx, output);
+	}
+
+	/*
+	 * It makes no sense to elide all of sort entries.
+	 * Just revert them to show up again.
+	 */
+	perf_hpp__for_each_format(fmt) {
+		if (!perf_hpp__is_sort_entry(fmt))
+			continue;
+
+		if (!fmt->elide)
+			return;
+	}
+
+	perf_hpp__for_each_format(fmt) {
+		if (!perf_hpp__is_sort_entry(fmt))
+			continue;
+
+		fmt->elide = false;
+	}
+}
+
+static int output_field_add(char *tok)
+{
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(common_sort_dimensions); i++) {
+		struct sort_dimension *sd = &common_sort_dimensions[i];
+
+		if (strncasecmp(tok, sd->name, strlen(tok)))
+			continue;
+
+		return __sort_dimension__add_output(sd);
+	}
+
+	for (i = 0; i < ARRAY_SIZE(hpp_sort_dimensions); i++) {
+		struct hpp_dimension *hd = &hpp_sort_dimensions[i];
+
+		if (strncasecmp(tok, hd->name, strlen(tok)))
+			continue;
+
+		return __hpp_dimension__add_output(hd);
+	}
+
+	for (i = 0; i < ARRAY_SIZE(bstack_sort_dimensions); i++) {
+		struct sort_dimension *sd = &bstack_sort_dimensions[i];
+
+		if (strncasecmp(tok, sd->name, strlen(tok)))
+			continue;
+
+		return __sort_dimension__add_output(sd);
+	}
+
+	for (i = 0; i < ARRAY_SIZE(memory_sort_dimensions); i++) {
+		struct sort_dimension *sd = &memory_sort_dimensions[i];
+
+		if (strncasecmp(tok, sd->name, strlen(tok)))
+			continue;
+
+		return __sort_dimension__add_output(sd);
+	}
+
+	return -ESRCH;
+}
+
+static void reset_dimensions(void)
+{
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(common_sort_dimensions); i++)
+		common_sort_dimensions[i].taken = 0;
+
+	for (i = 0; i < ARRAY_SIZE(hpp_sort_dimensions); i++)
+		hpp_sort_dimensions[i].taken = 0;
+
+	for (i = 0; i < ARRAY_SIZE(bstack_sort_dimensions); i++)
+		bstack_sort_dimensions[i].taken = 0;
+
+	for (i = 0; i < ARRAY_SIZE(memory_sort_dimensions); i++)
+		memory_sort_dimensions[i].taken = 0;
+}
+
+static int __setup_output_field(void)
+{
+	char *tmp, *tok, *str;
+	int ret = 0;
+
+	if (field_order == NULL)
+		return 0;
+
+	reset_dimensions();
+
+	str = strdup(field_order);
+	if (str == NULL) {
+		error("Not enough memory to setup output fields");
+		return -ENOMEM;
+	}
+
+	for (tok = strtok_r(str, ", ", &tmp);
+			tok; tok = strtok_r(NULL, ", ", &tmp)) {
+		ret = output_field_add(tok);
+		if (ret == -EINVAL) {
+			error("Invalid --fields key: `%s'", tok);
+			break;
+		} else if (ret == -ESRCH) {
+			error("Unknown --fields key: `%s'", tok);
+			break;
+		}
+	}
+
+	free(str);
+	return ret;
+}
+
+int setup_sorting(void)
+{
+	int err;
+
+	err = __setup_sorting();
+	if (err < 0)
+		return err;
+
+	if (parent_pattern != default_parent_pattern) {
+		err = sort_dimension__add("parent");
+		if (err < 0)
+			return err;
+	}
+
+	reset_dimensions();
+
+	/*
+	 * perf diff doesn't use default hpp output fields.
+	 */
+	if (sort__mode != SORT_MODE__DIFF)
+		perf_hpp__init();
+
+	err = __setup_output_field();
+	if (err < 0)
+		return err;
+
+	/* copy sort keys to output fields */
+	perf_hpp__setup_output_field();
+	/* and then copy output fields to sort keys */
+	perf_hpp__append_sort_keys();
+
+	return 0;
+}
+
+void reset_output_field(void)
+{
+	sort__need_collapse = 0;
+	sort__has_parent = 0;
+	sort__has_sym = 0;
+	sort__has_dso = 0;
+
+	field_order = NULL;
+	sort_order = NULL;
+
+	reset_dimensions();
+	perf_hpp__reset_output_field();
 }
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 0d61c4082f4..041f0c9cea2 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -20,55 +20,173 @@
 
 #include "parse-options.h"
 #include "parse-events.h"
-
+#include "hist.h"
 #include "thread.h"
-#include "sort.h"
 
 extern regex_t parent_regex;
 extern const char *sort_order;
+extern const char *field_order;
 extern const char default_parent_pattern[];
 extern const char *parent_pattern;
 extern const char default_sort_order[];
+extern regex_t ignore_callees_regex;
+extern int have_ignore_callees;
 extern int sort__need_collapse;
 extern int sort__has_parent;
-extern char *field_sep;
+extern int sort__has_sym;
+extern enum sort_mode sort__mode;
 extern struct sort_entry sort_comm;
 extern struct sort_entry sort_dso;
 extern struct sort_entry sort_sym;
 extern struct sort_entry sort_parent;
-extern unsigned int dsos__col_width;
-extern unsigned int comms__col_width;
-extern unsigned int threads__col_width;
+extern struct sort_entry sort_dso_from;
+extern struct sort_entry sort_dso_to;
+extern struct sort_entry sort_sym_from;
+extern struct sort_entry sort_sym_to;
 extern enum sort_type sort__first_dimension;
 
-struct hist_entry {
-	struct rb_node		rb_node;
+struct he_stat {
 	u64			period;
 	u64			period_sys;
 	u64			period_us;
 	u64			period_guest_sys;
 	u64			period_guest_us;
+	u64			weight;
+	u32			nr_events;
+};
+
+struct hist_entry_diff {
+	bool	computed;
+
+	/* PERF_HPP__DELTA */
+	double	period_ratio_delta;
+
+	/* PERF_HPP__RATIO */
+	double	period_ratio;
+
+	/* HISTC_WEIGHTED_DIFF */
+	s64	wdiff;
+};
+
+/**
+ * struct hist_entry - histogram entry
+ *
+ * @row_offset - offset from the first callchain expanded to appear on screen
+ * @nr_rows - rows expanded in callchain, recalculated on folding/unfolding
+ */
+struct hist_entry {
+	struct rb_node		rb_node_in;
+	struct rb_node		rb_node;
+	union {
+		struct list_head node;
+		struct list_head head;
+	} pairs;
+	struct he_stat		stat;
+	struct he_stat		*stat_acc;
 	struct map_symbol	ms;
 	struct thread		*thread;
+	struct comm		*comm;
 	u64			ip;
-	u32			nr_events;
+	u64			transaction;
+	s32			cpu;
+	u8			cpumode;
+
+	struct hist_entry_diff	diff;
+
+	/* We are added by hists__add_dummy_entry. */
+	bool			dummy;
+
+	/* XXX These two should move to some tree widget lib */
+	u16			row_offset;
+	u16			nr_rows;
+
+	bool			init_have_children;
 	char			level;
+	bool			used;
 	u8			filtered;
+	char			*srcline;
 	struct symbol		*parent;
-	union {
-		unsigned long	  position;
-		struct hist_entry *pair;
-		struct rb_root	  sorted_chain;
-	};
-	struct callchain_node	callchain[0];
+	unsigned long		position;
+	struct rb_root		sorted_chain;
+	struct branch_info	*branch_info;
+	struct hists		*hists;
+	struct mem_info		*mem_info;
+	struct callchain_root	callchain[0]; /* must be last member */
+};
+
+static inline bool hist_entry__has_pairs(struct hist_entry *he)
+{
+	return !list_empty(&he->pairs.node);
+}
+
+static inline struct hist_entry *hist_entry__next_pair(struct hist_entry *he)
+{
+	if (hist_entry__has_pairs(he))
+		return list_entry(he->pairs.node.next, struct hist_entry, pairs.node);
+	return NULL;
+}
+
+static inline void hist_entry__add_pair(struct hist_entry *pair,
+					struct hist_entry *he)
+{
+	list_add_tail(&pair->pairs.node, &he->pairs.head);
+}
+
+static inline float hist_entry__get_percent_limit(struct hist_entry *he)
+{
+	u64 period = he->stat.period;
+	u64 total_period = hists__total_period(he->hists);
+
+	if (unlikely(total_period == 0))
+		return 0;
+
+	if (symbol_conf.cumulate_callchain)
+		period = he->stat_acc->period;
+
+	return period * 100.0 / total_period;
+}
+
+
+enum sort_mode {
+	SORT_MODE__NORMAL,
+	SORT_MODE__BRANCH,
+	SORT_MODE__MEMORY,
+	SORT_MODE__TOP,
+	SORT_MODE__DIFF,
 };
 
 enum sort_type {
+	/* common sort keys */
 	SORT_PID,
 	SORT_COMM,
 	SORT_DSO,
 	SORT_SYM,
-	SORT_PARENT
+	SORT_PARENT,
+	SORT_CPU,
+	SORT_SRCLINE,
+	SORT_LOCAL_WEIGHT,
+	SORT_GLOBAL_WEIGHT,
+	SORT_TRANSACTION,
+
+	/* branch stack specific sort keys */
+	__SORT_BRANCH_STACK,
+	SORT_DSO_FROM = __SORT_BRANCH_STACK,
+	SORT_DSO_TO,
+	SORT_SYM_FROM,
+	SORT_SYM_TO,
+	SORT_MISPREDICT,
+	SORT_ABORT,
+	SORT_IN_TX,
+
+	/* memory mode specific sort keys */
+	__SORT_MEMORY_MODE,
+	SORT_MEM_DADDR_SYMBOL = __SORT_MEMORY_MODE,
+	SORT_MEM_DADDR_DSO,
+	SORT_MEM_LOCKED,
+	SORT_MEM_TLB,
+	SORT_MEM_LVL,
+	SORT_MEM_SNOOP,
+	SORT_MEM_DCACHELINE,
 };
 
 /*
@@ -82,31 +200,22 @@ struct sort_entry {
 
 	int64_t (*se_cmp)(struct hist_entry *, struct hist_entry *);
 	int64_t (*se_collapse)(struct hist_entry *, struct hist_entry *);
-	int	(*se_snprintf)(struct hist_entry *self, char *bf, size_t size,
+	int64_t	(*se_sort)(struct hist_entry *, struct hist_entry *);
+	int	(*se_snprintf)(struct hist_entry *he, char *bf, size_t size,
 			       unsigned int width);
-	unsigned int *se_width;
-	bool	elide;
+	u8	se_width_idx;
 };
 
 extern struct sort_entry sort_thread;
 extern struct list_head hist_entry__sort_list;
 
-void setup_sorting(const char * const usagestr[], const struct option *opts);
-
-extern size_t sort__thread_print(FILE *, struct hist_entry *, unsigned int);
-extern size_t sort__comm_print(FILE *, struct hist_entry *, unsigned int);
-extern size_t sort__dso_print(FILE *, struct hist_entry *, unsigned int);
-extern size_t sort__sym_print(FILE *, struct hist_entry *, unsigned int __used);
-extern int64_t cmp_null(void *, void *);
-extern int64_t sort__thread_cmp(struct hist_entry *, struct hist_entry *);
-extern int64_t sort__comm_cmp(struct hist_entry *, struct hist_entry *);
-extern int64_t sort__comm_collapse(struct hist_entry *, struct hist_entry *);
-extern int64_t sort__dso_cmp(struct hist_entry *, struct hist_entry *);
-extern int64_t sort__sym_cmp(struct hist_entry *, struct hist_entry *);
-extern int64_t sort__parent_cmp(struct hist_entry *, struct hist_entry *);
-extern size_t sort__parent_print(FILE *, struct hist_entry *, unsigned int);
+int setup_sorting(void);
+int setup_output_field(void);
+void reset_output_field(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);
+void perf_hpp__set_elide(int idx, bool elide);
+
+int report_parse_ignore_callees_opt(const struct option *opt, const char *arg, int unset);
 
 #endif	/* __PERF_SORT_H */
diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c
new file mode 100644
index 00000000000..f3e4bc5fe5d
--- /dev/null
+++ b/tools/perf/util/srcline.c
@@ -0,0 +1,299 @@
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include <linux/kernel.h>
+
+#include "util/dso.h"
+#include "util/util.h"
+#include "util/debug.h"
+
+#ifdef HAVE_LIBBFD_SUPPORT
+
+/*
+ * Implement addr2line using libbfd.
+ */
+#define PACKAGE "perf"
+#include <bfd.h>
+
+struct a2l_data {
+	const char 	*input;
+	unsigned long 	addr;
+
+	bool 		found;
+	const char 	*filename;
+	const char 	*funcname;
+	unsigned 	line;
+
+	bfd 		*abfd;
+	asymbol 	**syms;
+};
+
+static int bfd_error(const char *string)
+{
+	const char *errmsg;
+
+	errmsg = bfd_errmsg(bfd_get_error());
+	fflush(stdout);
+
+	if (string)
+		pr_debug("%s: %s\n", string, errmsg);
+	else
+		pr_debug("%s\n", errmsg);
+
+	return -1;
+}
+
+static int slurp_symtab(bfd *abfd, struct a2l_data *a2l)
+{
+	long storage;
+	long symcount;
+	asymbol **syms;
+	bfd_boolean dynamic = FALSE;
+
+	if ((bfd_get_file_flags(abfd) & HAS_SYMS) == 0)
+		return bfd_error(bfd_get_filename(abfd));
+
+	storage = bfd_get_symtab_upper_bound(abfd);
+	if (storage == 0L) {
+		storage = bfd_get_dynamic_symtab_upper_bound(abfd);
+		dynamic = TRUE;
+	}
+	if (storage < 0L)
+		return bfd_error(bfd_get_filename(abfd));
+
+	syms = malloc(storage);
+	if (dynamic)
+		symcount = bfd_canonicalize_dynamic_symtab(abfd, syms);
+	else
+		symcount = bfd_canonicalize_symtab(abfd, syms);
+
+	if (symcount < 0) {
+		free(syms);
+		return bfd_error(bfd_get_filename(abfd));
+	}
+
+	a2l->syms = syms;
+	return 0;
+}
+
+static void find_address_in_section(bfd *abfd, asection *section, void *data)
+{
+	bfd_vma pc, vma;
+	bfd_size_type size;
+	struct a2l_data *a2l = data;
+
+	if (a2l->found)
+		return;
+
+	if ((bfd_get_section_flags(abfd, section) & SEC_ALLOC) == 0)
+		return;
+
+	pc = a2l->addr;
+	vma = bfd_get_section_vma(abfd, section);
+	size = bfd_get_section_size(section);
+
+	if (pc < vma || pc >= vma + size)
+		return;
+
+	a2l->found = bfd_find_nearest_line(abfd, section, a2l->syms, pc - vma,
+					   &a2l->filename, &a2l->funcname,
+					   &a2l->line);
+}
+
+static struct a2l_data *addr2line_init(const char *path)
+{
+	bfd *abfd;
+	struct a2l_data *a2l = NULL;
+
+	abfd = bfd_openr(path, NULL);
+	if (abfd == NULL)
+		return NULL;
+
+	if (!bfd_check_format(abfd, bfd_object))
+		goto out;
+
+	a2l = zalloc(sizeof(*a2l));
+	if (a2l == NULL)
+		goto out;
+
+	a2l->abfd = abfd;
+	a2l->input = strdup(path);
+	if (a2l->input == NULL)
+		goto out;
+
+	if (slurp_symtab(abfd, a2l))
+		goto out;
+
+	return a2l;
+
+out:
+	if (a2l) {
+		zfree((char **)&a2l->input);
+		free(a2l);
+	}
+	bfd_close(abfd);
+	return NULL;
+}
+
+static void addr2line_cleanup(struct a2l_data *a2l)
+{
+	if (a2l->abfd)
+		bfd_close(a2l->abfd);
+	zfree((char **)&a2l->input);
+	zfree(&a2l->syms);
+	free(a2l);
+}
+
+static int addr2line(const char *dso_name, unsigned long addr,
+		     char **file, unsigned int *line, struct dso *dso)
+{
+	int ret = 0;
+	struct a2l_data *a2l = dso->a2l;
+
+	if (!a2l) {
+		dso->a2l = addr2line_init(dso_name);
+		a2l = dso->a2l;
+	}
+
+	if (a2l == NULL) {
+		pr_warning("addr2line_init failed for %s\n", dso_name);
+		return 0;
+	}
+
+	a2l->addr = addr;
+	a2l->found = false;
+
+	bfd_map_over_sections(a2l->abfd, find_address_in_section, a2l);
+
+	if (a2l->found && a2l->filename) {
+		*file = strdup(a2l->filename);
+		*line = a2l->line;
+
+		if (*file)
+			ret = 1;
+	}
+
+	return ret;
+}
+
+void dso__free_a2l(struct dso *dso)
+{
+	struct a2l_data *a2l = dso->a2l;
+
+	if (!a2l)
+		return;
+
+	addr2line_cleanup(a2l);
+
+	dso->a2l = NULL;
+}
+
+#else /* HAVE_LIBBFD_SUPPORT */
+
+static int addr2line(const char *dso_name, unsigned long addr,
+		     char **file, unsigned int *line_nr,
+		     struct dso *dso __maybe_unused)
+{
+	FILE *fp;
+	char cmd[PATH_MAX];
+	char *filename = NULL;
+	size_t len;
+	char *sep;
+	int ret = 0;
+
+	scnprintf(cmd, sizeof(cmd), "addr2line -e %s %016"PRIx64,
+		  dso_name, addr);
+
+	fp = popen(cmd, "r");
+	if (fp == NULL) {
+		pr_warning("popen failed for %s\n", dso_name);
+		return 0;
+	}
+
+	if (getline(&filename, &len, fp) < 0 || !len) {
+		pr_warning("addr2line has no output for %s\n", dso_name);
+		goto out;
+	}
+
+	sep = strchr(filename, '\n');
+	if (sep)
+		*sep = '\0';
+
+	if (!strcmp(filename, "??:0")) {
+		pr_debug("no debugging info in %s\n", dso_name);
+		free(filename);
+		goto out;
+	}
+
+	sep = strchr(filename, ':');
+	if (sep) {
+		*sep++ = '\0';
+		*file = filename;
+		*line_nr = strtoul(sep, NULL, 0);
+		ret = 1;
+	}
+out:
+	pclose(fp);
+	return ret;
+}
+
+void dso__free_a2l(struct dso *dso __maybe_unused)
+{
+}
+
+#endif /* HAVE_LIBBFD_SUPPORT */
+
+/*
+ * Number of addr2line failures (without success) before disabling it for that
+ * dso.
+ */
+#define A2L_FAIL_LIMIT 123
+
+char *get_srcline(struct dso *dso, unsigned long addr)
+{
+	char *file = NULL;
+	unsigned line = 0;
+	char *srcline;
+	const char *dso_name;
+
+	if (!dso->has_srcline)
+		return SRCLINE_UNKNOWN;
+
+	if (dso->symsrc_filename)
+		dso_name = dso->symsrc_filename;
+	else
+		dso_name = dso->long_name;
+
+	if (dso_name[0] == '[')
+		goto out;
+
+	if (!strncmp(dso_name, "/tmp/perf-", 10))
+		goto out;
+
+	if (!addr2line(dso_name, addr, &file, &line, dso))
+		goto out;
+
+	if (asprintf(&srcline, "%s:%u", file, line) < 0) {
+		free(file);
+		goto out;
+	}
+
+	dso->a2l_fails = 0;
+
+	free(file);
+	return srcline;
+
+out:
+	if (dso->a2l_fails && ++dso->a2l_fails > A2L_FAIL_LIMIT) {
+		dso->has_srcline = 0;
+		dso__free_a2l(dso);
+	}
+	return SRCLINE_UNKNOWN;
+}
+
+void free_srcline(char *srcline)
+{
+	if (srcline && strcmp(srcline, SRCLINE_UNKNOWN) != 0)
+		free(srcline);
+}
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
new file mode 100644
index 00000000000..6506b3dfb60
--- /dev/null
+++ b/tools/perf/util/stat.c
@@ -0,0 +1,63 @@
+#include <math.h>
+
+#include "stat.h"
+
+void update_stats(struct stats *stats, u64 val)
+{
+	double delta;
+
+	stats->n++;
+	delta = val - stats->mean;
+	stats->mean += delta / stats->n;
+	stats->M2 += delta*(val - stats->mean);
+
+	if (val > stats->max)
+		stats->max = val;
+
+	if (val < stats->min)
+		stats->min = val;
+}
+
+double avg_stats(struct stats *stats)
+{
+	return stats->mean;
+}
+
+/*
+ * http://en.wikipedia.org/wiki/Algorithms_for_calculating_variance
+ *
+ *       (\Sum n_i^2) - ((\Sum n_i)^2)/n
+ * s^2 = -------------------------------
+ *                  n - 1
+ *
+ * http://en.wikipedia.org/wiki/Stddev
+ *
+ * The std dev of the mean is related to the std dev by:
+ *
+ *             s
+ * s_mean = -------
+ *          sqrt(n)
+ *
+ */
+double stddev_stats(struct stats *stats)
+{
+	double variance, variance_mean;
+
+	if (stats->n < 2)
+		return 0.0;
+
+	variance = stats->M2 / (stats->n - 1);
+	variance_mean = variance / stats->n;
+
+	return sqrt(variance_mean);
+}
+
+double rel_stddev_stats(double stddev, double avg)
+{
+	double pct = 0.0;
+
+	if (avg)
+		pct = 100.0 * stddev/avg;
+
+	return pct;
+}
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
new file mode 100644
index 00000000000..5667fc3e39c
--- /dev/null
+++ b/tools/perf/util/stat.h
@@ -0,0 +1,25 @@
+#ifndef __PERF_STATS_H
+#define __PERF_STATS_H
+
+#include <linux/types.h>
+
+struct stats
+{
+	double n, mean, M2;
+	u64 max, min;
+};
+
+void update_stats(struct stats *stats, u64 val);
+double avg_stats(struct stats *stats);
+double stddev_stats(struct stats *stats);
+double rel_stddev_stats(double stddev, double avg);
+
+static inline void init_stats(struct stats *stats)
+{
+	stats->n    = 0.0;
+	stats->mean = 0.0;
+	stats->M2   = 0.0;
+	stats->min  = (u64) -1;
+	stats->max  = 0;
+}
+#endif
diff --git a/tools/perf/util/strbuf.c b/tools/perf/util/strbuf.c
index 92e068517c1..4abe23550c7 100644
--- a/tools/perf/util/strbuf.c
+++ b/tools/perf/util/strbuf.c
@@ -1,4 +1,5 @@
 #include "cache.h"
+#include <linux/kernel.h>
 
 int prefixcmp(const char *str, const char *prefix)
 {
@@ -27,7 +28,7 @@ void strbuf_init(struct strbuf *sb, ssize_t hint)
 void strbuf_release(struct strbuf *sb)
 {
 	if (sb->alloc) {
-		free(sb->buf);
+		zfree(&sb->buf);
 		strbuf_init(sb, 0);
 	}
 }
@@ -99,7 +100,7 @@ void strbuf_addf(struct strbuf *sb, const char *fmt, ...)
 		len = vsnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap);
 		va_end(ap);
 		if (len > strbuf_avail(sb)) {
-			die("this should not happen, your snprintf is broken");
+			die("this should not happen, your vsnprintf is broken");
 		}
 	}
 	strbuf_setlen(sb, sb->len + len);
diff --git a/tools/perf/util/strfilter.c b/tools/perf/util/strfilter.c
new file mode 100644
index 00000000000..79a757a2a15
--- /dev/null
+++ b/tools/perf/util/strfilter.c
@@ -0,0 +1,199 @@
+#include "util.h"
+#include "string.h"
+#include "strfilter.h"
+
+/* Operators */
+static const char *OP_and	= "&";	/* Logical AND */
+static const char *OP_or	= "|";	/* Logical OR */
+static const char *OP_not	= "!";	/* Logical NOT */
+
+#define is_operator(c)	((c) == '|' || (c) == '&' || (c) == '!')
+#define is_separator(c)	(is_operator(c) || (c) == '(' || (c) == ')')
+
+static void strfilter_node__delete(struct strfilter_node *node)
+{
+	if (node) {
+		if (node->p && !is_operator(*node->p))
+			zfree((char **)&node->p);
+		strfilter_node__delete(node->l);
+		strfilter_node__delete(node->r);
+		free(node);
+	}
+}
+
+void strfilter__delete(struct strfilter *filter)
+{
+	if (filter) {
+		strfilter_node__delete(filter->root);
+		free(filter);
+	}
+}
+
+static const char *get_token(const char *s, const char **e)
+{
+	const char *p;
+
+	while (isspace(*s))	/* Skip spaces */
+		s++;
+
+	if (*s == '\0') {
+		p = s;
+		goto end;
+	}
+
+	p = s + 1;
+	if (!is_separator(*s)) {
+		/* End search */
+retry:
+		while (*p && !is_separator(*p) && !isspace(*p))
+			p++;
+		/* Escape and special case: '!' is also used in glob pattern */
+		if (*(p - 1) == '\\' || (*p == '!' && *(p - 1) == '[')) {
+			p++;
+			goto retry;
+		}
+	}
+end:
+	*e = p;
+	return s;
+}
+
+static struct strfilter_node *strfilter_node__alloc(const char *op,
+						    struct strfilter_node *l,
+						    struct strfilter_node *r)
+{
+	struct strfilter_node *node = zalloc(sizeof(*node));
+
+	if (node) {
+		node->p = op;
+		node->l = l;
+		node->r = r;
+	}
+
+	return node;
+}
+
+static struct strfilter_node *strfilter_node__new(const char *s,
+						  const char **ep)
+{
+	struct strfilter_node root, *cur, *last_op;
+	const char *e;
+
+	if (!s)
+		return NULL;
+
+	memset(&root, 0, sizeof(root));
+	last_op = cur = &root;
+
+	s = get_token(s, &e);
+	while (*s != '\0' && *s != ')') {
+		switch (*s) {
+		case '&':	/* Exchg last OP->r with AND */
+			if (!cur->r || !last_op->r)
+				goto error;
+			cur = strfilter_node__alloc(OP_and, last_op->r, NULL);
+			if (!cur)
+				goto nomem;
+			last_op->r = cur;
+			last_op = cur;
+			break;
+		case '|':	/* Exchg the root with OR */
+			if (!cur->r || !root.r)
+				goto error;
+			cur = strfilter_node__alloc(OP_or, root.r, NULL);
+			if (!cur)
+				goto nomem;
+			root.r = cur;
+			last_op = cur;
+			break;
+		case '!':	/* Add NOT as a leaf node */
+			if (cur->r)
+				goto error;
+			cur->r = strfilter_node__alloc(OP_not, NULL, NULL);
+			if (!cur->r)
+				goto nomem;
+			cur = cur->r;
+			break;
+		case '(':	/* Recursively parses inside the parenthesis */
+			if (cur->r)
+				goto error;
+			cur->r = strfilter_node__new(s + 1, &s);
+			if (!s)
+				goto nomem;
+			if (!cur->r || *s != ')')
+				goto error;
+			e = s + 1;
+			break;
+		default:
+			if (cur->r)
+				goto error;
+			cur->r = strfilter_node__alloc(NULL, NULL, NULL);
+			if (!cur->r)
+				goto nomem;
+			cur->r->p = strndup(s, e - s);
+			if (!cur->r->p)
+				goto nomem;
+		}
+		s = get_token(e, &e);
+	}
+	if (!cur->r)
+		goto error;
+	*ep = s;
+	return root.r;
+nomem:
+	s = NULL;
+error:
+	*ep = s;
+	strfilter_node__delete(root.r);
+	return NULL;
+}
+
+/*
+ * Parse filter rule and return new strfilter.
+ * Return NULL if fail, and *ep == NULL if memory allocation failed.
+ */
+struct strfilter *strfilter__new(const char *rules, const char **err)
+{
+	struct strfilter *filter = zalloc(sizeof(*filter));
+	const char *ep = NULL;
+
+	if (filter)
+		filter->root = strfilter_node__new(rules, &ep);
+
+	if (!filter || !filter->root || *ep != '\0') {
+		if (err)
+			*err = ep;
+		strfilter__delete(filter);
+		filter = NULL;
+	}
+
+	return filter;
+}
+
+static bool strfilter_node__compare(struct strfilter_node *node,
+				    const char *str)
+{
+	if (!node || !node->p)
+		return false;
+
+	switch (*node->p) {
+	case '|':	/* OR */
+		return strfilter_node__compare(node->l, str) ||
+			strfilter_node__compare(node->r, str);
+	case '&':	/* AND */
+		return strfilter_node__compare(node->l, str) &&
+			strfilter_node__compare(node->r, str);
+	case '!':	/* NOT */
+		return !strfilter_node__compare(node->r, str);
+	default:
+		return strglobmatch(str, node->p);
+	}
+}
+
+/* Return true if STR matches the filter rules */
+bool strfilter__compare(struct strfilter *filter, const char *str)
+{
+	if (!filter)
+		return false;
+	return strfilter_node__compare(filter->root, str);
+}
diff --git a/tools/perf/util/strfilter.h b/tools/perf/util/strfilter.h
new file mode 100644
index 00000000000..fe611f3c9e3
--- /dev/null
+++ b/tools/perf/util/strfilter.h
@@ -0,0 +1,48 @@
+#ifndef __PERF_STRFILTER_H
+#define __PERF_STRFILTER_H
+/* General purpose glob matching filter */
+
+#include <linux/list.h>
+#include <stdbool.h>
+
+/* A node of string filter */
+struct strfilter_node {
+	struct strfilter_node *l;	/* Tree left branche (for &,|) */
+	struct strfilter_node *r;	/* Tree right branche (for !,&,|) */
+	const char *p;		/* Operator or rule */
+};
+
+/* String filter */
+struct strfilter {
+	struct strfilter_node *root;
+};
+
+/**
+ * strfilter__new - Create a new string filter
+ * @rules: Filter rule, which is a combination of glob expressions.
+ * @err: Pointer which points an error detected on @rules
+ *
+ * Parse @rules and return new strfilter. Return NULL if an error detected.
+ * In that case, *@err will indicate where it is detected, and *@err is NULL
+ * if a memory allocation is failed.
+ */
+struct strfilter *strfilter__new(const char *rules, const char **err);
+
+/**
+ * strfilter__compare - compare given string and a string filter
+ * @filter: String filter
+ * @str: target string
+ *
+ * Compare @str and @filter. Return true if the str match the rule
+ */
+bool strfilter__compare(struct strfilter *filter, const char *str);
+
+/**
+ * strfilter__delete - delete a string filter
+ * @filter: String filter to delete
+ *
+ * Delete @filter.
+ */
+void strfilter__delete(struct strfilter *filter);
+
+#endif
diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c
index 0409fc7c005..2553e5b55b8 100644
--- a/tools/perf/util/string.c
+++ b/tools/perf/util/string.c
@@ -1,5 +1,5 @@
 #include "util.h"
-#include "string.h"
+#include "linux/string.h"
 
 #define K 1024LL
 /*
@@ -85,7 +85,7 @@ out:
 
 /*
  * Helper function for splitting a string into an argv-like array.
- * originaly copied from lib/argv_split.c
+ * originally copied from lib/argv_split.c
  */
 static const char *skip_sep(const char *cp)
 {
@@ -128,7 +128,7 @@ void argv_free(char **argv)
 {
 	char **p;
 	for (p = argv; *p; p++)
-		free(*p);
+		zfree(p);
 
 	free(argv);
 }
@@ -259,7 +259,7 @@ static bool __match_glob(const char *str, const char *pat, bool ignore_space)
 		if (!*pat)	/* Tail wild card matches all */
 			return true;
 		while (*str)
-			if (strglobmatch(str++, pat))
+			if (__match_glob(str++, pat, ignore_space))
 				return true;
 	}
 	return !*str && !*pat;
@@ -294,3 +294,120 @@ bool strlazymatch(const char *str, const char *pat)
 {
 	return __match_glob(str, pat, true);
 }
+
+/**
+ * strtailcmp - Compare the tail of two strings
+ * @s1: 1st string to be compared
+ * @s2: 2nd string to be compared
+ *
+ * Return 0 if whole of either string is same as another's tail part.
+ */
+int strtailcmp(const char *s1, const char *s2)
+{
+	int i1 = strlen(s1);
+	int i2 = strlen(s2);
+	while (--i1 >= 0 && --i2 >= 0) {
+		if (s1[i1] != s2[i2])
+			return s1[i1] - s2[i2];
+	}
+	return 0;
+}
+
+/**
+ * strxfrchar - Locate and replace character in @s
+ * @s:    The string to be searched/changed.
+ * @from: Source character to be replaced.
+ * @to:   Destination character.
+ *
+ * Return pointer to the changed string.
+ */
+char *strxfrchar(char *s, char from, char to)
+{
+	char *p = s;
+
+	while ((p = strchr(p, from)) != NULL)
+		*p++ = to;
+
+	return s;
+}
+
+/**
+ * ltrim - Removes leading whitespace from @s.
+ * @s: The string to be stripped.
+ *
+ * Return pointer to the first non-whitespace character in @s.
+ */
+char *ltrim(char *s)
+{
+	int len = strlen(s);
+
+	while (len && isspace(*s)) {
+		len--;
+		s++;
+	}
+
+	return s;
+}
+
+/**
+ * rtrim - Removes trailing whitespace from @s.
+ * @s: The string to be stripped.
+ *
+ * Note that the first trailing whitespace is replaced with a %NUL-terminator
+ * in the given string @s. Returns @s.
+ */
+char *rtrim(char *s)
+{
+	size_t size = strlen(s);
+	char *end;
+
+	if (!size)
+		return s;
+
+	end = s + size - 1;
+	while (end >= s && isspace(*end))
+		end--;
+	*(end + 1) = '\0';
+
+	return s;
+}
+
+/**
+ * memdup - duplicate region of memory
+ * @src: memory region to duplicate
+ * @len: memory region length
+ */
+void *memdup(const void *src, size_t len)
+{
+	void *p;
+
+	p = malloc(len);
+	if (p)
+		memcpy(p, src, len);
+
+	return p;
+}
+
+/**
+ * str_append - reallocate string and append another
+ * @s: pointer to string pointer
+ * @len: pointer to len (initialized)
+ * @a: string to append.
+ */
+int str_append(char **s, int *len, const char *a)
+{
+	int olen = *s ? strlen(*s) : 0;
+	int nlen = olen + strlen(a) + 1;
+	if (*len < nlen) {
+		*len = *len * 2;
+		if (*len < nlen)
+			*len = nlen;
+		*s = realloc(*s, *len);
+		if (!*s)
+			return -ENOMEM;
+		if (olen == 0)
+			**s = 0;
+	}
+	strcat(*s, a);
+	return 0;
+}
diff --git a/tools/perf/util/strlist.c b/tools/perf/util/strlist.c
index 6783a204355..71f9d102b96 100644
--- a/tools/perf/util/strlist.c
+++ b/tools/perf/util/strlist.c
@@ -5,71 +5,67 @@
  */
 
 #include "strlist.h"
+#include "util.h"
 #include <errno.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
 
-static struct str_node *str_node__new(const char *s, bool dupstr)
+static
+struct rb_node *strlist__node_new(struct rblist *rblist, const void *entry)
 {
-	struct str_node *self = malloc(sizeof(*self));
+	const char *s = entry;
+	struct rb_node *rc = NULL;
+	struct strlist *strlist = container_of(rblist, struct strlist, rblist);
+	struct str_node *snode = malloc(sizeof(*snode));
 
-	if (self != NULL) {
-		if (dupstr) {
+	if (snode != NULL) {
+		if (strlist->dupstr) {
 			s = strdup(s);
 			if (s == NULL)
 				goto out_delete;
 		}
-		self->s = s;
+		snode->s = s;
+		rc = &snode->rb_node;
 	}
 
-	return self;
+	return rc;
 
 out_delete:
-	free(self);
+	free(snode);
 	return NULL;
 }
 
-static void str_node__delete(struct str_node *self, bool dupstr)
+static void str_node__delete(struct str_node *snode, bool dupstr)
 {
 	if (dupstr)
-		free((void *)self->s);
-	free(self);
+		zfree((char **)&snode->s);
+	free(snode);
 }
 
-int strlist__add(struct strlist *self, const char *new_entry)
+static
+void strlist__node_delete(struct rblist *rblist, struct rb_node *rb_node)
 {
-	struct rb_node **p = &self->entries.rb_node;
-	struct rb_node *parent = NULL;
-	struct str_node *sn;
-
-	while (*p != NULL) {
-		int rc;
-
-		parent = *p;
-		sn = rb_entry(parent, struct str_node, rb_node);
-		rc = strcmp(sn->s, new_entry);
-
-		if (rc > 0)
-			p = &(*p)->rb_left;
-		else if (rc < 0)
-			p = &(*p)->rb_right;
-		else
-			return -EEXIST;
-	}
+	struct strlist *slist = container_of(rblist, struct strlist, rblist);
+	struct str_node *snode = container_of(rb_node, struct str_node, rb_node);
+
+	str_node__delete(snode, slist->dupstr);
+}
 
-	sn = str_node__new(new_entry, self->dupstr);
-	if (sn == NULL)
-		return -ENOMEM;
+static int strlist__node_cmp(struct rb_node *rb_node, const void *entry)
+{
+	const char *str = entry;
+	struct str_node *snode = container_of(rb_node, struct str_node, rb_node);
 
-	rb_link_node(&sn->rb_node, parent, p);
-	rb_insert_color(&sn->rb_node, &self->entries);
-	++self->nr_entries;
+	return strcmp(snode->s, str);
+}
 
-	return 0;
+int strlist__add(struct strlist *slist, const char *new_entry)
+{
+	return rblist__add_node(&slist->rblist, new_entry);
 }
 
-int strlist__load(struct strlist *self, const char *filename)
+int strlist__load(struct strlist *slist, const char *filename)
 {
 	char entry[1024];
 	int err;
@@ -85,7 +81,7 @@ int strlist__load(struct strlist *self, const char *filename)
 			continue;
 		entry[len - 1] = '\0';
 
-		err = strlist__add(self, entry);
+		err = strlist__add(slist, entry);
 		if (err != 0)
 			goto out;
 	}
@@ -96,105 +92,82 @@ out:
 	return err;
 }
 
-void strlist__remove(struct strlist *self, struct str_node *sn)
+void strlist__remove(struct strlist *slist, struct str_node *snode)
 {
-	rb_erase(&sn->rb_node, &self->entries);
-	str_node__delete(sn, self->dupstr);
+	rblist__remove_node(&slist->rblist, &snode->rb_node);
 }
 
-struct str_node *strlist__find(struct strlist *self, const char *entry)
+struct str_node *strlist__find(struct strlist *slist, const char *entry)
 {
-	struct rb_node **p = &self->entries.rb_node;
-	struct rb_node *parent = NULL;
-
-	while (*p != NULL) {
-		struct str_node *sn;
-		int rc;
-
-		parent = *p;
-		sn = rb_entry(parent, struct str_node, rb_node);
-		rc = strcmp(sn->s, entry);
-
-		if (rc > 0)
-			p = &(*p)->rb_left;
-		else if (rc < 0)
-			p = &(*p)->rb_right;
-		else
-			return sn;
-	}
+	struct str_node *snode = NULL;
+	struct rb_node *rb_node = rblist__find(&slist->rblist, entry);
 
-	return NULL;
+	if (rb_node)
+		snode = container_of(rb_node, struct str_node, rb_node);
+
+	return snode;
 }
 
-static int strlist__parse_list_entry(struct strlist *self, const char *s)
+static int strlist__parse_list_entry(struct strlist *slist, const char *s)
 {
 	if (strncmp(s, "file://", 7) == 0)
-		return strlist__load(self, s + 7);
+		return strlist__load(slist, s + 7);
 
-	return strlist__add(self, s);
+	return strlist__add(slist, s);
 }
 
-int strlist__parse_list(struct strlist *self, const char *s)
+int strlist__parse_list(struct strlist *slist, const char *s)
 {
 	char *sep;
 	int err;
 
 	while ((sep = strchr(s, ',')) != NULL) {
 		*sep = '\0';
-		err = strlist__parse_list_entry(self, s);
+		err = strlist__parse_list_entry(slist, s);
 		*sep = ',';
 		if (err != 0)
 			return err;
 		s = sep + 1;
 	}
 
-	return *s ? strlist__parse_list_entry(self, s) : 0;
+	return *s ? strlist__parse_list_entry(slist, s) : 0;
 }
 
-struct strlist *strlist__new(bool dupstr, const char *slist)
+struct strlist *strlist__new(bool dupstr, const char *list)
 {
-	struct strlist *self = malloc(sizeof(*self));
+	struct strlist *slist = malloc(sizeof(*slist));
+
+	if (slist != NULL) {
+		rblist__init(&slist->rblist);
+		slist->rblist.node_cmp    = strlist__node_cmp;
+		slist->rblist.node_new    = strlist__node_new;
+		slist->rblist.node_delete = strlist__node_delete;
 
-	if (self != NULL) {
-		self->entries	 = RB_ROOT;
-		self->dupstr	 = dupstr;
-		self->nr_entries = 0;
-		if (slist && strlist__parse_list(self, slist) != 0)
+		slist->dupstr	 = dupstr;
+		if (list && strlist__parse_list(slist, list) != 0)
 			goto out_error;
 	}
 
-	return self;
+	return slist;
 out_error:
-	free(self);
+	free(slist);
 	return NULL;
 }
 
-void strlist__delete(struct strlist *self)
+void strlist__delete(struct strlist *slist)
 {
-	if (self != NULL) {
-		struct str_node *pos;
-		struct rb_node *next = rb_first(&self->entries);
-
-		while (next) {
-			pos = rb_entry(next, struct str_node, rb_node);
-			next = rb_next(&pos->rb_node);
-			strlist__remove(self, pos);
-		}
-		self->entries = RB_ROOT;
-		free(self);
-	}
+	if (slist != NULL)
+		rblist__delete(&slist->rblist);
 }
 
-struct str_node *strlist__entry(const struct strlist *self, unsigned int idx)
+struct str_node *strlist__entry(const struct strlist *slist, unsigned int idx)
 {
-	struct rb_node *nd;
+	struct str_node *snode = NULL;
+	struct rb_node *rb_node;
 
-	for (nd = rb_first(&self->entries); nd; nd = rb_next(nd)) {
-		struct str_node *pos = rb_entry(nd, struct str_node, rb_node);
+	rb_node = rblist__entry(&slist->rblist, idx);
+	if (rb_node)
+		snode = container_of(rb_node, struct str_node, rb_node);
 
-		if (!idx--)
-			return pos;
-	}
-
-	return NULL;
+	return snode;
 }
diff --git a/tools/perf/util/strlist.h b/tools/perf/util/strlist.h
index 3ba839007d2..5c7f87069d9 100644
--- a/tools/perf/util/strlist.h
+++ b/tools/perf/util/strlist.h
@@ -4,46 +4,47 @@
 #include <linux/rbtree.h>
 #include <stdbool.h>
 
+#include "rblist.h"
+
 struct str_node {
 	struct rb_node rb_node;
 	const char     *s;
 };
 
 struct strlist {
-	struct rb_root entries;
-	unsigned int   nr_entries;
+	struct rblist rblist;
 	bool	       dupstr;
 };
 
 struct strlist *strlist__new(bool dupstr, const char *slist);
-void strlist__delete(struct strlist *self);
+void strlist__delete(struct strlist *slist);
 
-void strlist__remove(struct strlist *self, struct str_node *sn);
-int strlist__load(struct strlist *self, const char *filename);
-int strlist__add(struct strlist *self, const char *str);
+void strlist__remove(struct strlist *slist, struct str_node *sn);
+int strlist__load(struct strlist *slist, const char *filename);
+int strlist__add(struct strlist *slist, const char *str);
 
-struct str_node *strlist__entry(const struct strlist *self, unsigned int idx);
-struct str_node *strlist__find(struct strlist *self, const char *entry);
+struct str_node *strlist__entry(const struct strlist *slist, unsigned int idx);
+struct str_node *strlist__find(struct strlist *slist, const char *entry);
 
-static inline bool strlist__has_entry(struct strlist *self, const char *entry)
+static inline bool strlist__has_entry(struct strlist *slist, const char *entry)
 {
-	return strlist__find(self, entry) != NULL;
+	return strlist__find(slist, entry) != NULL;
 }
 
-static inline bool strlist__empty(const struct strlist *self)
+static inline bool strlist__empty(const struct strlist *slist)
 {
-	return self->nr_entries == 0;
+	return rblist__empty(&slist->rblist);
 }
 
-static inline unsigned int strlist__nr_entries(const struct strlist *self)
+static inline unsigned int strlist__nr_entries(const struct strlist *slist)
 {
-	return self->nr_entries;
+	return rblist__nr_entries(&slist->rblist);
 }
 
 /* For strlist iteration */
-static inline struct str_node *strlist__first(struct strlist *self)
+static inline struct str_node *strlist__first(struct strlist *slist)
 {
-	struct rb_node *rn = rb_first(&self->entries);
+	struct rb_node *rn = rb_first(&slist->rblist.entries);
 	return rn ? rb_entry(rn, struct str_node, rb_node) : NULL;
 }
 static inline struct str_node *strlist__next(struct str_node *sn)
@@ -58,21 +59,21 @@ static inline struct str_node *strlist__next(struct str_node *sn)
 /**
  * strlist_for_each      - iterate over a strlist
  * @pos:	the &struct str_node to use as a loop cursor.
- * @self:	the &struct strlist for loop.
+ * @slist:	the &struct strlist for loop.
  */
-#define strlist__for_each(pos, self)	\
-	for (pos = strlist__first(self); pos; pos = strlist__next(pos))
+#define strlist__for_each(pos, slist)	\
+	for (pos = strlist__first(slist); pos; pos = strlist__next(pos))
 
 /**
  * strlist_for_each_safe - iterate over a strlist safe against removal of
  *                         str_node
  * @pos:	the &struct str_node to use as a loop cursor.
  * @n:		another &struct str_node to use as temporary storage.
- * @self:	the &struct strlist for loop.
+ * @slist:	the &struct strlist for loop.
  */
-#define strlist__for_each_safe(pos, n, self)	\
-	for (pos = strlist__first(self), n = strlist__next(pos); pos;\
+#define strlist__for_each_safe(pos, n, slist)	\
+	for (pos = strlist__first(slist), n = strlist__next(pos); pos;\
 	     pos = n, n = strlist__next(n))
 
-int strlist__parse_list(struct strlist *self, const char *s);
+int strlist__parse_list(struct strlist *slist, const char *s);
 #endif /* __PERF_STRLIST_H */
diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c
index b3637db025a..6a0a13d07a2 100644
--- a/tools/perf/util/svghelper.c
+++ b/tools/perf/util/svghelper.c
@@ -12,12 +12,17 @@
  * of the License.
  */
 
+#include <inttypes.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <unistd.h>
 #include <string.h>
+#include <linux/bitmap.h>
 
+#include "perf.h"
 #include "svghelper.h"
+#include "util.h"
+#include "cpumap.h"
 
 static u64 first_time, last_time;
 static u64 turbo_frequency, max_freq;
@@ -27,6 +32,8 @@ static u64 turbo_frequency, max_freq;
 #define SLOT_HEIGHT 25.0
 
 int svg_page_width = 1000;
+u64 svg_highlight;
+const char *svg_highlight_name;
 
 #define MIN_TEXT_SIZE 0.01
 
@@ -38,16 +45,21 @@ static double cpu2slot(int cpu)
 	return 2 * cpu + 1;
 }
 
+static int *topology_map;
+
 static double cpu2y(int cpu)
 {
-	return cpu2slot(cpu) * SLOT_MULT;
+	if (topology_map)
+		return cpu2slot(topology_map[cpu]) * SLOT_MULT;
+	else
+		return cpu2slot(cpu) * SLOT_MULT;
 }
 
-static double time2pixels(u64 time)
+static double time2pixels(u64 __time)
 {
 	double X;
 
-	X = 1.0 * svg_page_width * (time - first_time) / (last_time - first_time);
+	X = 1.0 * svg_page_width * (__time - first_time) / (last_time - first_time);
 	return X;
 }
 
@@ -94,7 +106,8 @@ void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end)
 
 	total_height = (1 + rows + cpu2slot(cpus)) * SLOT_MULT;
 	fprintf(svgfile, "<?xml version=\"1.0\" standalone=\"no\"?> \n");
-	fprintf(svgfile, "<svg width=\"%i\" height=\"%llu\" version=\"1.1\" xmlns=\"http://www.w3.org/2000/svg\">\n", svg_page_width, total_height);
+	fprintf(svgfile, "<!DOCTYPE svg SYSTEM \"http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd\">\n");
+	fprintf(svgfile, "<svg width=\"%i\" height=\"%" PRIu64 "\" version=\"1.1\" xmlns=\"http://www.w3.org/2000/svg\">\n", svg_page_width, total_height);
 
 	fprintf(svgfile, "<defs>\n  <style type=\"text/css\">\n    <![CDATA[\n");
 
@@ -102,6 +115,7 @@ void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end)
 	fprintf(svgfile, "      rect.process  { fill:rgb(180,180,180); fill-opacity:0.9; stroke-width:1;   stroke:rgb(  0,  0,  0); } \n");
 	fprintf(svgfile, "      rect.process2 { fill:rgb(180,180,180); fill-opacity:0.9; stroke-width:0;   stroke:rgb(  0,  0,  0); } \n");
 	fprintf(svgfile, "      rect.sample   { fill:rgb(  0,  0,255); fill-opacity:0.8; stroke-width:0;   stroke:rgb(  0,  0,  0); } \n");
+	fprintf(svgfile, "      rect.sample_hi{ fill:rgb(255,128,  0); fill-opacity:0.8; stroke-width:0;   stroke:rgb(  0,  0,  0); } \n");
 	fprintf(svgfile, "      rect.blocked  { fill:rgb(255,  0,  0); fill-opacity:0.5; stroke-width:0;   stroke:rgb(  0,  0,  0); } \n");
 	fprintf(svgfile, "      rect.waiting  { fill:rgb(224,214,  0); fill-opacity:0.8; stroke-width:0;   stroke:rgb(  0,  0,  0); } \n");
 	fprintf(svgfile, "      rect.WAITING  { fill:rgb(255,214, 48); fill-opacity:0.6; stroke-width:0;   stroke:rgb(  0,  0,  0); } \n");
@@ -127,14 +141,42 @@ void svg_box(int Yslot, u64 start, u64 end, const char *type)
 		time2pixels(start), time2pixels(end)-time2pixels(start), Yslot * SLOT_MULT, SLOT_HEIGHT, type);
 }
 
-void svg_sample(int Yslot, int cpu, u64 start, u64 end)
+static char *time_to_string(u64 duration);
+void svg_blocked(int Yslot, int cpu, u64 start, u64 end, const char *backtrace)
+{
+	if (!svgfile)
+		return;
+
+	fprintf(svgfile, "<g>\n");
+	fprintf(svgfile, "<title>#%d blocked %s</title>\n", cpu,
+		time_to_string(end - start));
+	if (backtrace)
+		fprintf(svgfile, "<desc>Blocked on:\n%s</desc>\n", backtrace);
+	svg_box(Yslot, start, end, "blocked");
+	fprintf(svgfile, "</g>\n");
+}
+
+void svg_running(int Yslot, int cpu, u64 start, u64 end, const char *backtrace)
 {
 	double text_size;
+	const char *type;
+
 	if (!svgfile)
 		return;
 
-	fprintf(svgfile, "<rect x=\"%4.8f\" width=\"%4.8f\" y=\"%4.1f\" height=\"%4.1f\" class=\"sample\"/>\n",
-		time2pixels(start), time2pixels(end)-time2pixels(start), Yslot * SLOT_MULT, SLOT_HEIGHT);
+	if (svg_highlight && end - start > svg_highlight)
+		type = "sample_hi";
+	else
+		type = "sample";
+	fprintf(svgfile, "<g>\n");
+
+	fprintf(svgfile, "<title>#%d running %s</title>\n",
+		cpu, time_to_string(end - start));
+	if (backtrace)
+		fprintf(svgfile, "<desc>Switched because:\n%s</desc>\n", backtrace);
+	fprintf(svgfile, "<rect x=\"%4.8f\" width=\"%4.8f\" y=\"%4.1f\" height=\"%4.1f\" class=\"%s\"/>\n",
+		time2pixels(start), time2pixels(end)-time2pixels(start), Yslot * SLOT_MULT, SLOT_HEIGHT,
+		type);
 
 	text_size = (time2pixels(end)-time2pixels(start));
 	if (cpu > 9)
@@ -147,6 +189,7 @@ void svg_sample(int Yslot, int cpu, u64 start, u64 end)
 		fprintf(svgfile, "<text x=\"%1.8f\" y=\"%1.8f\" font-size=\"%1.8fpt\">%i</text>\n",
 			time2pixels(start), Yslot *  SLOT_MULT + SLOT_HEIGHT - 1, text_size,  cpu + 1);
 
+	fprintf(svgfile, "</g>\n");
 }
 
 static char *time_to_string(u64 duration)
@@ -167,7 +210,7 @@ static char *time_to_string(u64 duration)
 	return text;
 }
 
-void svg_waiting(int Yslot, u64 start, u64 end)
+void svg_waiting(int Yslot, int cpu, u64 start, u64 end, const char *backtrace)
 {
 	char *text;
 	const char *style;
@@ -191,6 +234,9 @@ void svg_waiting(int Yslot, u64 start, u64 end)
 	font_size = round_text_size(font_size);
 
 	fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\">\n", time2pixels(start), Yslot * SLOT_MULT);
+	fprintf(svgfile, "<title>#%d waiting %s</title>\n", cpu, time_to_string(end - start));
+	if (backtrace)
+		fprintf(svgfile, "<desc>Waiting on:\n%s</desc>\n", backtrace);
 	fprintf(svgfile, "<rect x=\"0\" width=\"%4.8f\" y=\"0\" height=\"%4.1f\" class=\"%s\"/>\n",
 		time2pixels(end)-time2pixels(start), SLOT_HEIGHT, style);
 	if (font_size > MIN_TEXT_SIZE)
@@ -241,28 +287,42 @@ void svg_cpu_box(int cpu, u64 __max_freq, u64 __turbo_freq)
 	max_freq = __max_freq;
 	turbo_frequency = __turbo_freq;
 
+	fprintf(svgfile, "<g>\n");
+
 	fprintf(svgfile, "<rect x=\"%4.8f\" width=\"%4.8f\" y=\"%4.1f\" height=\"%4.1f\" class=\"cpu\"/>\n",
 		time2pixels(first_time),
 		time2pixels(last_time)-time2pixels(first_time),
 		cpu2y(cpu), SLOT_MULT+SLOT_HEIGHT);
 
-	sprintf(cpu_string, "CPU %i", (int)cpu+1);
+	sprintf(cpu_string, "CPU %i", (int)cpu);
 	fprintf(svgfile, "<text x=\"%4.8f\" y=\"%4.8f\">%s</text>\n",
 		10+time2pixels(first_time), cpu2y(cpu) + SLOT_HEIGHT/2, cpu_string);
 
 	fprintf(svgfile, "<text transform=\"translate(%4.8f,%4.8f)\" font-size=\"1.25pt\">%s</text>\n",
 		10+time2pixels(first_time), cpu2y(cpu) + SLOT_MULT + SLOT_HEIGHT - 4, cpu_model());
+
+	fprintf(svgfile, "</g>\n");
 }
 
-void svg_process(int cpu, u64 start, u64 end, const char *type, const char *name)
+void svg_process(int cpu, u64 start, u64 end, int pid, const char *name, const char *backtrace)
 {
 	double width;
+	const char *type;
 
 	if (!svgfile)
 		return;
 
+	if (svg_highlight && end - start >= svg_highlight)
+		type = "sample_hi";
+	else if (svg_highlight_name && strstr(name, svg_highlight_name))
+		type = "sample_hi";
+	else
+		type = "sample";
 
 	fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\">\n", time2pixels(start), cpu2y(cpu));
+	fprintf(svgfile, "<title>%d %s running %s</title>\n", pid, name, time_to_string(end - start));
+	if (backtrace)
+		fprintf(svgfile, "<desc>Switched because:\n%s</desc>\n", backtrace);
 	fprintf(svgfile, "<rect x=\"0\" width=\"%4.8f\" y=\"0\" height=\"%4.1f\" class=\"%s\"/>\n",
 		time2pixels(end)-time2pixels(start), SLOT_MULT+SLOT_HEIGHT, type);
 	width = time2pixels(end)-time2pixels(start);
@@ -287,6 +347,8 @@ void svg_cstate(int cpu, u64 start, u64 end, int type)
 		return;
 
 
+	fprintf(svgfile, "<g>\n");
+
 	if (type > 6)
 		type = 6;
 	sprintf(style, "c%i", type);
@@ -305,6 +367,8 @@ void svg_cstate(int cpu, u64 start, u64 end, int type)
 	if (width > MIN_TEXT_SIZE)
 		fprintf(svgfile, "<text x=\"%4.8f\" y=\"%4.8f\" font-size=\"%3.8fpt\">C%i</text>\n",
 			time2pixels(start), cpu2y(cpu)+width, width, type);
+
+	fprintf(svgfile, "</g>\n");
 }
 
 static char *HzToHuman(unsigned long hz)
@@ -338,6 +402,8 @@ void svg_pstate(int cpu, u64 start, u64 end, u64 freq)
 	if (!svgfile)
 		return;
 
+	fprintf(svgfile, "<g>\n");
+
 	if (max_freq)
 		height = freq * 1.0 / max_freq * (SLOT_HEIGHT + SLOT_MULT);
 	height = 1 + cpu2y(cpu) + SLOT_MULT + SLOT_HEIGHT - height;
@@ -346,10 +412,11 @@ void svg_pstate(int cpu, u64 start, u64 end, u64 freq)
 	fprintf(svgfile, "<text x=\"%4.8f\" y=\"%4.8f\" font-size=\"0.25pt\">%s</text>\n",
 		time2pixels(start), height+0.9, HzToHuman(freq));
 
+	fprintf(svgfile, "</g>\n");
 }
 
 
-void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc2)
+void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc2, const char *backtrace)
 {
 	double height;
 
@@ -357,6 +424,15 @@ void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc
 		return;
 
 
+	fprintf(svgfile, "<g>\n");
+
+	fprintf(svgfile, "<title>%s wakes up %s</title>\n",
+		desc1 ? desc1 : "?",
+		desc2 ? desc2 : "?");
+
+	if (backtrace)
+		fprintf(svgfile, "<desc>%s</desc>\n", backtrace);
+
 	if (row1 < row2) {
 		if (row1) {
 			fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n",
@@ -394,9 +470,11 @@ void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc
 	if (row1)
 		fprintf(svgfile, "<circle  cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\"  style=\"fill:rgb(32,255,32)\"/>\n",
 			time2pixels(start), height);
+
+	fprintf(svgfile, "</g>\n");
 }
 
-void svg_wakeline(u64 start, int row1, int row2)
+void svg_wakeline(u64 start, int row1, int row2, const char *backtrace)
 {
 	double height;
 
@@ -404,6 +482,11 @@ void svg_wakeline(u64 start, int row1, int row2)
 		return;
 
 
+	fprintf(svgfile, "<g>\n");
+
+	if (backtrace)
+		fprintf(svgfile, "<desc>%s</desc>\n", backtrace);
+
 	if (row1 < row2)
 		fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n",
 			time2pixels(start), row1 * SLOT_MULT + SLOT_HEIGHT,  time2pixels(start), row2 * SLOT_MULT);
@@ -416,17 +499,28 @@ void svg_wakeline(u64 start, int row1, int row2)
 		height += SLOT_HEIGHT;
 	fprintf(svgfile, "<circle  cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\"  style=\"fill:rgb(32,255,32)\"/>\n",
 			time2pixels(start), height);
+
+	fprintf(svgfile, "</g>\n");
 }
 
-void svg_interrupt(u64 start, int row)
+void svg_interrupt(u64 start, int row, const char *backtrace)
 {
 	if (!svgfile)
 		return;
 
+	fprintf(svgfile, "<g>\n");
+
+	fprintf(svgfile, "<title>Wakeup from interrupt</title>\n");
+
+	if (backtrace)
+		fprintf(svgfile, "<desc>%s</desc>\n", backtrace);
+
 	fprintf(svgfile, "<circle  cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\"  style=\"fill:rgb(255,128,128)\"/>\n",
 			time2pixels(start), row * SLOT_MULT);
 	fprintf(svgfile, "<circle  cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\"  style=\"fill:rgb(255,128,128)\"/>\n",
 			time2pixels(start), row * SLOT_MULT + SLOT_HEIGHT);
+
+	fprintf(svgfile, "</g>\n");
 }
 
 void svg_text(int Yslot, u64 start, const char *text)
@@ -454,13 +548,15 @@ void svg_legenda(void)
 	if (!svgfile)
 		return;
 
+	fprintf(svgfile, "<g>\n");
 	svg_legenda_box(0,	"Running", "sample");
-	svg_legenda_box(100,	"Idle","rect.c1");
-	svg_legenda_box(200,	"Deeper Idle", "rect.c3");
-	svg_legenda_box(350,	"Deepest Idle", "rect.c6");
+	svg_legenda_box(100,	"Idle","c1");
+	svg_legenda_box(200,	"Deeper Idle", "c3");
+	svg_legenda_box(350,	"Deepest Idle", "c6");
 	svg_legenda_box(550,	"Sleeping", "process2");
 	svg_legenda_box(650,	"Waiting for cpu", "waiting");
 	svg_legenda_box(800,	"Blocked on IO", "blocked");
+	fprintf(svgfile, "</g>\n");
 }
 
 void svg_time_grid(void)
@@ -483,7 +579,7 @@ void svg_time_grid(void)
 			color = 128;
 		}
 
-		fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%llu\" style=\"stroke:rgb(%i,%i,%i);stroke-width:%1.3f\"/>\n",
+		fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%" PRIu64 "\" style=\"stroke:rgb(%i,%i,%i);stroke-width:%1.3f\"/>\n",
 			time2pixels(i), SLOT_MULT/2, time2pixels(i), total_height, color, color, color, thickness);
 
 		i += 10000000;
@@ -498,3 +594,123 @@ void svg_close(void)
 		svgfile = NULL;
 	}
 }
+
+#define cpumask_bits(maskp) ((maskp)->bits)
+typedef struct { DECLARE_BITMAP(bits, MAX_NR_CPUS); } cpumask_t;
+
+struct topology {
+	cpumask_t *sib_core;
+	int sib_core_nr;
+	cpumask_t *sib_thr;
+	int sib_thr_nr;
+};
+
+static void scan_thread_topology(int *map, struct topology *t, int cpu, int *pos)
+{
+	int i;
+	int thr;
+
+	for (i = 0; i < t->sib_thr_nr; i++) {
+		if (!test_bit(cpu, cpumask_bits(&t->sib_thr[i])))
+			continue;
+
+		for_each_set_bit(thr,
+				 cpumask_bits(&t->sib_thr[i]),
+				 MAX_NR_CPUS)
+			if (map[thr] == -1)
+				map[thr] = (*pos)++;
+	}
+}
+
+static void scan_core_topology(int *map, struct topology *t)
+{
+	int pos = 0;
+	int i;
+	int cpu;
+
+	for (i = 0; i < t->sib_core_nr; i++)
+		for_each_set_bit(cpu,
+				 cpumask_bits(&t->sib_core[i]),
+				 MAX_NR_CPUS)
+			scan_thread_topology(map, t, cpu, &pos);
+}
+
+static int str_to_bitmap(char *s, cpumask_t *b)
+{
+	int i;
+	int ret = 0;
+	struct cpu_map *m;
+	int c;
+
+	m = cpu_map__new(s);
+	if (!m)
+		return -1;
+
+	for (i = 0; i < m->nr; i++) {
+		c = m->map[i];
+		if (c >= MAX_NR_CPUS) {
+			ret = -1;
+			break;
+		}
+
+		set_bit(c, cpumask_bits(b));
+	}
+
+	cpu_map__delete(m);
+
+	return ret;
+}
+
+int svg_build_topology_map(char *sib_core, int sib_core_nr,
+			   char *sib_thr, int sib_thr_nr)
+{
+	int i;
+	struct topology t;
+
+	t.sib_core_nr = sib_core_nr;
+	t.sib_thr_nr = sib_thr_nr;
+	t.sib_core = calloc(sib_core_nr, sizeof(cpumask_t));
+	t.sib_thr = calloc(sib_thr_nr, sizeof(cpumask_t));
+
+	if (!t.sib_core || !t.sib_thr) {
+		fprintf(stderr, "topology: no memory\n");
+		goto exit;
+	}
+
+	for (i = 0; i < sib_core_nr; i++) {
+		if (str_to_bitmap(sib_core, &t.sib_core[i])) {
+			fprintf(stderr, "topology: can't parse siblings map\n");
+			goto exit;
+		}
+
+		sib_core += strlen(sib_core) + 1;
+	}
+
+	for (i = 0; i < sib_thr_nr; i++) {
+		if (str_to_bitmap(sib_thr, &t.sib_thr[i])) {
+			fprintf(stderr, "topology: can't parse siblings map\n");
+			goto exit;
+		}
+
+		sib_thr += strlen(sib_thr) + 1;
+	}
+
+	topology_map = malloc(sizeof(int) * MAX_NR_CPUS);
+	if (!topology_map) {
+		fprintf(stderr, "topology: no memory\n");
+		goto exit;
+	}
+
+	for (i = 0; i < MAX_NR_CPUS; i++)
+		topology_map[i] = -1;
+
+	scan_core_topology(topology_map, &t);
+
+	return 0;
+
+exit:
+	zfree(&t.sib_core);
+	zfree(&t.sib_thr);
+
+	return -1;
+}
diff --git a/tools/perf/util/svghelper.h b/tools/perf/util/svghelper.h
index e0781989cc3..e3aff5332e3 100644
--- a/tools/perf/util/svghelper.h
+++ b/tools/perf/util/svghelper.h
@@ -1,28 +1,33 @@
 #ifndef __PERF_SVGHELPER_H
 #define __PERF_SVGHELPER_H
 
-#include "types.h"
+#include <linux/types.h>
 
 extern void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end);
 extern void svg_box(int Yslot, u64 start, u64 end, const char *type);
-extern void svg_sample(int Yslot, int cpu, u64 start, u64 end);
-extern void svg_waiting(int Yslot, u64 start, u64 end);
+extern void svg_blocked(int Yslot, int cpu, u64 start, u64 end, const char *backtrace);
+extern void svg_running(int Yslot, int cpu, u64 start, u64 end, const char *backtrace);
+extern void svg_waiting(int Yslot, int cpu, u64 start, u64 end, const char *backtrace);
 extern void svg_cpu_box(int cpu, u64 max_frequency, u64 turbo_frequency);
 
 
-extern void svg_process(int cpu, u64 start, u64 end, const char *type, const char *name);
+extern void svg_process(int cpu, u64 start, u64 end, int pid, const char *name, const char *backtrace);
 extern void svg_cstate(int cpu, u64 start, u64 end, int type);
 extern void svg_pstate(int cpu, u64 start, u64 end, u64 freq);
 
 
 extern void svg_time_grid(void);
 extern void svg_legenda(void);
-extern void svg_wakeline(u64 start, int row1, int row2);
-extern void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc2);
-extern void svg_interrupt(u64 start, int row);
+extern void svg_wakeline(u64 start, int row1, int row2, const char *backtrace);
+extern void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc2, const char *backtrace);
+extern void svg_interrupt(u64 start, int row, const char *backtrace);
 extern void svg_text(int Yslot, u64 start, const char *text);
 extern void svg_close(void);
+extern int svg_build_topology_map(char *sib_core, int sib_core_nr,
+				  char *sib_thr, int sib_thr_nr);
 
 extern int svg_page_width;
+extern u64 svg_highlight;
+extern const char *svg_highlight_name;
 
 #endif /* __PERF_SVGHELPER_H */
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
new file mode 100644
index 00000000000..6864661a79d
--- /dev/null
+++ b/tools/perf/util/symbol-elf.c
@@ -0,0 +1,1625 @@
+#include <fcntl.h>
+#include <stdio.h>
+#include <errno.h>
+#include <string.h>
+#include <unistd.h>
+#include <inttypes.h>
+
+#include "symbol.h"
+#include "vdso.h"
+#include <symbol/kallsyms.h>
+#include "debug.h"
+
+#ifndef HAVE_ELF_GETPHDRNUM_SUPPORT
+static int elf_getphdrnum(Elf *elf, size_t *dst)
+{
+	GElf_Ehdr gehdr;
+	GElf_Ehdr *ehdr;
+
+	ehdr = gelf_getehdr(elf, &gehdr);
+	if (!ehdr)
+		return -1;
+
+	*dst = ehdr->e_phnum;
+
+	return 0;
+}
+#endif
+
+#ifndef NT_GNU_BUILD_ID
+#define NT_GNU_BUILD_ID 3
+#endif
+
+/**
+ * elf_symtab__for_each_symbol - iterate thru all the symbols
+ *
+ * @syms: struct elf_symtab instance to iterate
+ * @idx: uint32_t idx
+ * @sym: GElf_Sym iterator
+ */
+#define elf_symtab__for_each_symbol(syms, nr_syms, idx, sym) \
+	for (idx = 0, gelf_getsym(syms, idx, &sym);\
+	     idx < nr_syms; \
+	     idx++, gelf_getsym(syms, idx, &sym))
+
+static inline uint8_t elf_sym__type(const GElf_Sym *sym)
+{
+	return GELF_ST_TYPE(sym->st_info);
+}
+
+static inline int elf_sym__is_function(const GElf_Sym *sym)
+{
+	return elf_sym__type(sym) == STT_FUNC &&
+	       sym->st_name != 0 &&
+	       sym->st_shndx != SHN_UNDEF;
+}
+
+static inline bool elf_sym__is_object(const GElf_Sym *sym)
+{
+	return elf_sym__type(sym) == STT_OBJECT &&
+		sym->st_name != 0 &&
+		sym->st_shndx != SHN_UNDEF;
+}
+
+static inline int elf_sym__is_label(const GElf_Sym *sym)
+{
+	return elf_sym__type(sym) == STT_NOTYPE &&
+		sym->st_name != 0 &&
+		sym->st_shndx != SHN_UNDEF &&
+		sym->st_shndx != SHN_ABS;
+}
+
+static bool elf_sym__is_a(GElf_Sym *sym, enum map_type type)
+{
+	switch (type) {
+	case MAP__FUNCTION:
+		return elf_sym__is_function(sym);
+	case MAP__VARIABLE:
+		return elf_sym__is_object(sym);
+	default:
+		return false;
+	}
+}
+
+static inline const char *elf_sym__name(const GElf_Sym *sym,
+					const Elf_Data *symstrs)
+{
+	return symstrs->d_buf + sym->st_name;
+}
+
+static inline const char *elf_sec__name(const GElf_Shdr *shdr,
+					const Elf_Data *secstrs)
+{
+	return secstrs->d_buf + shdr->sh_name;
+}
+
+static inline int elf_sec__is_text(const GElf_Shdr *shdr,
+					const Elf_Data *secstrs)
+{
+	return strstr(elf_sec__name(shdr, secstrs), "text") != NULL;
+}
+
+static inline bool elf_sec__is_data(const GElf_Shdr *shdr,
+				    const Elf_Data *secstrs)
+{
+	return strstr(elf_sec__name(shdr, secstrs), "data") != NULL;
+}
+
+static bool elf_sec__is_a(GElf_Shdr *shdr, Elf_Data *secstrs,
+			  enum map_type type)
+{
+	switch (type) {
+	case MAP__FUNCTION:
+		return elf_sec__is_text(shdr, secstrs);
+	case MAP__VARIABLE:
+		return elf_sec__is_data(shdr, secstrs);
+	default:
+		return false;
+	}
+}
+
+static size_t elf_addr_to_index(Elf *elf, GElf_Addr addr)
+{
+	Elf_Scn *sec = NULL;
+	GElf_Shdr shdr;
+	size_t cnt = 1;
+
+	while ((sec = elf_nextscn(elf, sec)) != NULL) {
+		gelf_getshdr(sec, &shdr);
+
+		if ((addr >= shdr.sh_addr) &&
+		    (addr < (shdr.sh_addr + shdr.sh_size)))
+			return cnt;
+
+		++cnt;
+	}
+
+	return -1;
+}
+
+Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
+			     GElf_Shdr *shp, const char *name, size_t *idx)
+{
+	Elf_Scn *sec = NULL;
+	size_t cnt = 1;
+
+	/* Elf is corrupted/truncated, avoid calling elf_strptr. */
+	if (!elf_rawdata(elf_getscn(elf, ep->e_shstrndx), NULL))
+		return NULL;
+
+	while ((sec = elf_nextscn(elf, sec)) != NULL) {
+		char *str;
+
+		gelf_getshdr(sec, shp);
+		str = elf_strptr(elf, ep->e_shstrndx, shp->sh_name);
+		if (str && !strcmp(name, str)) {
+			if (idx)
+				*idx = cnt;
+			return sec;
+		}
+		++cnt;
+	}
+
+	return NULL;
+}
+
+#define elf_section__for_each_rel(reldata, pos, pos_mem, idx, nr_entries) \
+	for (idx = 0, pos = gelf_getrel(reldata, 0, &pos_mem); \
+	     idx < nr_entries; \
+	     ++idx, pos = gelf_getrel(reldata, idx, &pos_mem))
+
+#define elf_section__for_each_rela(reldata, pos, pos_mem, idx, nr_entries) \
+	for (idx = 0, pos = gelf_getrela(reldata, 0, &pos_mem); \
+	     idx < nr_entries; \
+	     ++idx, pos = gelf_getrela(reldata, idx, &pos_mem))
+
+/*
+ * We need to check if we have a .dynsym, so that we can handle the
+ * .plt, synthesizing its symbols, that aren't on the symtabs (be it
+ * .dynsym or .symtab).
+ * And always look at the original dso, not at debuginfo packages, that
+ * have the PLT data stripped out (shdr_rel_plt.sh_type == SHT_NOBITS).
+ */
+int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map *map,
+				symbol_filter_t filter)
+{
+	uint32_t nr_rel_entries, idx;
+	GElf_Sym sym;
+	u64 plt_offset;
+	GElf_Shdr shdr_plt;
+	struct symbol *f;
+	GElf_Shdr shdr_rel_plt, shdr_dynsym;
+	Elf_Data *reldata, *syms, *symstrs;
+	Elf_Scn *scn_plt_rel, *scn_symstrs, *scn_dynsym;
+	size_t dynsym_idx;
+	GElf_Ehdr ehdr;
+	char sympltname[1024];
+	Elf *elf;
+	int nr = 0, symidx, err = 0;
+
+	if (!ss->dynsym)
+		return 0;
+
+	elf = ss->elf;
+	ehdr = ss->ehdr;
+
+	scn_dynsym = ss->dynsym;
+	shdr_dynsym = ss->dynshdr;
+	dynsym_idx = ss->dynsym_idx;
+
+	if (scn_dynsym == NULL)
+		goto out_elf_end;
+
+	scn_plt_rel = elf_section_by_name(elf, &ehdr, &shdr_rel_plt,
+					  ".rela.plt", NULL);
+	if (scn_plt_rel == NULL) {
+		scn_plt_rel = elf_section_by_name(elf, &ehdr, &shdr_rel_plt,
+						  ".rel.plt", NULL);
+		if (scn_plt_rel == NULL)
+			goto out_elf_end;
+	}
+
+	err = -1;
+
+	if (shdr_rel_plt.sh_link != dynsym_idx)
+		goto out_elf_end;
+
+	if (elf_section_by_name(elf, &ehdr, &shdr_plt, ".plt", NULL) == NULL)
+		goto out_elf_end;
+
+	/*
+	 * Fetch the relocation section to find the idxes to the GOT
+	 * and the symbols in the .dynsym they refer to.
+	 */
+	reldata = elf_getdata(scn_plt_rel, NULL);
+	if (reldata == NULL)
+		goto out_elf_end;
+
+	syms = elf_getdata(scn_dynsym, NULL);
+	if (syms == NULL)
+		goto out_elf_end;
+
+	scn_symstrs = elf_getscn(elf, shdr_dynsym.sh_link);
+	if (scn_symstrs == NULL)
+		goto out_elf_end;
+
+	symstrs = elf_getdata(scn_symstrs, NULL);
+	if (symstrs == NULL)
+		goto out_elf_end;
+
+	if (symstrs->d_size == 0)
+		goto out_elf_end;
+
+	nr_rel_entries = shdr_rel_plt.sh_size / shdr_rel_plt.sh_entsize;
+	plt_offset = shdr_plt.sh_offset;
+
+	if (shdr_rel_plt.sh_type == SHT_RELA) {
+		GElf_Rela pos_mem, *pos;
+
+		elf_section__for_each_rela(reldata, pos, pos_mem, idx,
+					   nr_rel_entries) {
+			symidx = GELF_R_SYM(pos->r_info);
+			plt_offset += shdr_plt.sh_entsize;
+			gelf_getsym(syms, symidx, &sym);
+			snprintf(sympltname, sizeof(sympltname),
+				 "%s@plt", elf_sym__name(&sym, symstrs));
+
+			f = symbol__new(plt_offset, shdr_plt.sh_entsize,
+					STB_GLOBAL, sympltname);
+			if (!f)
+				goto out_elf_end;
+
+			if (filter && filter(map, f))
+				symbol__delete(f);
+			else {
+				symbols__insert(&dso->symbols[map->type], f);
+				++nr;
+			}
+		}
+	} else if (shdr_rel_plt.sh_type == SHT_REL) {
+		GElf_Rel pos_mem, *pos;
+		elf_section__for_each_rel(reldata, pos, pos_mem, idx,
+					  nr_rel_entries) {
+			symidx = GELF_R_SYM(pos->r_info);
+			plt_offset += shdr_plt.sh_entsize;
+			gelf_getsym(syms, symidx, &sym);
+			snprintf(sympltname, sizeof(sympltname),
+				 "%s@plt", elf_sym__name(&sym, symstrs));
+
+			f = symbol__new(plt_offset, shdr_plt.sh_entsize,
+					STB_GLOBAL, sympltname);
+			if (!f)
+				goto out_elf_end;
+
+			if (filter && filter(map, f))
+				symbol__delete(f);
+			else {
+				symbols__insert(&dso->symbols[map->type], f);
+				++nr;
+			}
+		}
+	}
+
+	err = 0;
+out_elf_end:
+	if (err == 0)
+		return nr;
+	pr_debug("%s: problems reading %s PLT info.\n",
+		 __func__, dso->long_name);
+	return 0;
+}
+
+/*
+ * Align offset to 4 bytes as needed for note name and descriptor data.
+ */
+#define NOTE_ALIGN(n) (((n) + 3) & -4U)
+
+static int elf_read_build_id(Elf *elf, void *bf, size_t size)
+{
+	int err = -1;
+	GElf_Ehdr ehdr;
+	GElf_Shdr shdr;
+	Elf_Data *data;
+	Elf_Scn *sec;
+	Elf_Kind ek;
+	void *ptr;
+
+	if (size < BUILD_ID_SIZE)
+		goto out;
+
+	ek = elf_kind(elf);
+	if (ek != ELF_K_ELF)
+		goto out;
+
+	if (gelf_getehdr(elf, &ehdr) == NULL) {
+		pr_err("%s: cannot get elf header.\n", __func__);
+		goto out;
+	}
+
+	/*
+	 * Check following sections for notes:
+	 *   '.note.gnu.build-id'
+	 *   '.notes'
+	 *   '.note' (VDSO specific)
+	 */
+	do {
+		sec = elf_section_by_name(elf, &ehdr, &shdr,
+					  ".note.gnu.build-id", NULL);
+		if (sec)
+			break;
+
+		sec = elf_section_by_name(elf, &ehdr, &shdr,
+					  ".notes", NULL);
+		if (sec)
+			break;
+
+		sec = elf_section_by_name(elf, &ehdr, &shdr,
+					  ".note", NULL);
+		if (sec)
+			break;
+
+		return err;
+
+	} while (0);
+
+	data = elf_getdata(sec, NULL);
+	if (data == NULL)
+		goto out;
+
+	ptr = data->d_buf;
+	while (ptr < (data->d_buf + data->d_size)) {
+		GElf_Nhdr *nhdr = ptr;
+		size_t namesz = NOTE_ALIGN(nhdr->n_namesz),
+		       descsz = NOTE_ALIGN(nhdr->n_descsz);
+		const char *name;
+
+		ptr += sizeof(*nhdr);
+		name = ptr;
+		ptr += namesz;
+		if (nhdr->n_type == NT_GNU_BUILD_ID &&
+		    nhdr->n_namesz == sizeof("GNU")) {
+			if (memcmp(name, "GNU", sizeof("GNU")) == 0) {
+				size_t sz = min(size, descsz);
+				memcpy(bf, ptr, sz);
+				memset(bf + sz, 0, size - sz);
+				err = descsz;
+				break;
+			}
+		}
+		ptr += descsz;
+	}
+
+out:
+	return err;
+}
+
+int filename__read_build_id(const char *filename, void *bf, size_t size)
+{
+	int fd, err = -1;
+	Elf *elf;
+
+	if (size < BUILD_ID_SIZE)
+		goto out;
+
+	fd = open(filename, O_RDONLY);
+	if (fd < 0)
+		goto out;
+
+	elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
+	if (elf == NULL) {
+		pr_debug2("%s: cannot read %s ELF file.\n", __func__, filename);
+		goto out_close;
+	}
+
+	err = elf_read_build_id(elf, bf, size);
+
+	elf_end(elf);
+out_close:
+	close(fd);
+out:
+	return err;
+}
+
+int sysfs__read_build_id(const char *filename, void *build_id, size_t size)
+{
+	int fd, err = -1;
+
+	if (size < BUILD_ID_SIZE)
+		goto out;
+
+	fd = open(filename, O_RDONLY);
+	if (fd < 0)
+		goto out;
+
+	while (1) {
+		char bf[BUFSIZ];
+		GElf_Nhdr nhdr;
+		size_t namesz, descsz;
+
+		if (read(fd, &nhdr, sizeof(nhdr)) != sizeof(nhdr))
+			break;
+
+		namesz = NOTE_ALIGN(nhdr.n_namesz);
+		descsz = NOTE_ALIGN(nhdr.n_descsz);
+		if (nhdr.n_type == NT_GNU_BUILD_ID &&
+		    nhdr.n_namesz == sizeof("GNU")) {
+			if (read(fd, bf, namesz) != (ssize_t)namesz)
+				break;
+			if (memcmp(bf, "GNU", sizeof("GNU")) == 0) {
+				size_t sz = min(descsz, size);
+				if (read(fd, build_id, sz) == (ssize_t)sz) {
+					memset(build_id + sz, 0, size - sz);
+					err = 0;
+					break;
+				}
+			} else if (read(fd, bf, descsz) != (ssize_t)descsz)
+				break;
+		} else {
+			int n = namesz + descsz;
+			if (read(fd, bf, n) != n)
+				break;
+		}
+	}
+	close(fd);
+out:
+	return err;
+}
+
+int filename__read_debuglink(const char *filename, char *debuglink,
+			     size_t size)
+{
+	int fd, err = -1;
+	Elf *elf;
+	GElf_Ehdr ehdr;
+	GElf_Shdr shdr;
+	Elf_Data *data;
+	Elf_Scn *sec;
+	Elf_Kind ek;
+
+	fd = open(filename, O_RDONLY);
+	if (fd < 0)
+		goto out;
+
+	elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
+	if (elf == NULL) {
+		pr_debug2("%s: cannot read %s ELF file.\n", __func__, filename);
+		goto out_close;
+	}
+
+	ek = elf_kind(elf);
+	if (ek != ELF_K_ELF)
+		goto out_elf_end;
+
+	if (gelf_getehdr(elf, &ehdr) == NULL) {
+		pr_err("%s: cannot get elf header.\n", __func__);
+		goto out_elf_end;
+	}
+
+	sec = elf_section_by_name(elf, &ehdr, &shdr,
+				  ".gnu_debuglink", NULL);
+	if (sec == NULL)
+		goto out_elf_end;
+
+	data = elf_getdata(sec, NULL);
+	if (data == NULL)
+		goto out_elf_end;
+
+	/* the start of this section is a zero-terminated string */
+	strncpy(debuglink, data->d_buf, size);
+
+	err = 0;
+
+out_elf_end:
+	elf_end(elf);
+out_close:
+	close(fd);
+out:
+	return err;
+}
+
+static int dso__swap_init(struct dso *dso, unsigned char eidata)
+{
+	static unsigned int const endian = 1;
+
+	dso->needs_swap = DSO_SWAP__NO;
+
+	switch (eidata) {
+	case ELFDATA2LSB:
+		/* We are big endian, DSO is little endian. */
+		if (*(unsigned char const *)&endian != 1)
+			dso->needs_swap = DSO_SWAP__YES;
+		break;
+
+	case ELFDATA2MSB:
+		/* We are little endian, DSO is big endian. */
+		if (*(unsigned char const *)&endian != 0)
+			dso->needs_swap = DSO_SWAP__YES;
+		break;
+
+	default:
+		pr_err("unrecognized DSO data encoding %d\n", eidata);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+bool symsrc__possibly_runtime(struct symsrc *ss)
+{
+	return ss->dynsym || ss->opdsec;
+}
+
+bool symsrc__has_symtab(struct symsrc *ss)
+{
+	return ss->symtab != NULL;
+}
+
+void symsrc__destroy(struct symsrc *ss)
+{
+	zfree(&ss->name);
+	elf_end(ss->elf);
+	close(ss->fd);
+}
+
+int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
+		 enum dso_binary_type type)
+{
+	int err = -1;
+	GElf_Ehdr ehdr;
+	Elf *elf;
+	int fd;
+
+	fd = open(name, O_RDONLY);
+	if (fd < 0)
+		return -1;
+
+	elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
+	if (elf == NULL) {
+		pr_debug("%s: cannot read %s ELF file.\n", __func__, name);
+		goto out_close;
+	}
+
+	if (gelf_getehdr(elf, &ehdr) == NULL) {
+		pr_debug("%s: cannot get elf header.\n", __func__);
+		goto out_elf_end;
+	}
+
+	if (dso__swap_init(dso, ehdr.e_ident[EI_DATA]))
+		goto out_elf_end;
+
+	/* Always reject images with a mismatched build-id: */
+	if (dso->has_build_id) {
+		u8 build_id[BUILD_ID_SIZE];
+
+		if (elf_read_build_id(elf, build_id, BUILD_ID_SIZE) < 0)
+			goto out_elf_end;
+
+		if (!dso__build_id_equal(dso, build_id))
+			goto out_elf_end;
+	}
+
+	ss->symtab = elf_section_by_name(elf, &ehdr, &ss->symshdr, ".symtab",
+			NULL);
+	if (ss->symshdr.sh_type != SHT_SYMTAB)
+		ss->symtab = NULL;
+
+	ss->dynsym_idx = 0;
+	ss->dynsym = elf_section_by_name(elf, &ehdr, &ss->dynshdr, ".dynsym",
+			&ss->dynsym_idx);
+	if (ss->dynshdr.sh_type != SHT_DYNSYM)
+		ss->dynsym = NULL;
+
+	ss->opdidx = 0;
+	ss->opdsec = elf_section_by_name(elf, &ehdr, &ss->opdshdr, ".opd",
+			&ss->opdidx);
+	if (ss->opdshdr.sh_type != SHT_PROGBITS)
+		ss->opdsec = NULL;
+
+	if (dso->kernel == DSO_TYPE_USER) {
+		GElf_Shdr shdr;
+		ss->adjust_symbols = (ehdr.e_type == ET_EXEC ||
+				ehdr.e_type == ET_REL ||
+				is_vdso_map(dso->short_name) ||
+				elf_section_by_name(elf, &ehdr, &shdr,
+						     ".gnu.prelink_undo",
+						     NULL) != NULL);
+	} else {
+		ss->adjust_symbols = ehdr.e_type == ET_EXEC ||
+				     ehdr.e_type == ET_REL;
+	}
+
+	ss->name   = strdup(name);
+	if (!ss->name)
+		goto out_elf_end;
+
+	ss->elf    = elf;
+	ss->fd     = fd;
+	ss->ehdr   = ehdr;
+	ss->type   = type;
+
+	return 0;
+
+out_elf_end:
+	elf_end(elf);
+out_close:
+	close(fd);
+	return err;
+}
+
+/**
+ * ref_reloc_sym_not_found - has kernel relocation symbol been found.
+ * @kmap: kernel maps and relocation reference symbol
+ *
+ * This function returns %true if we are dealing with the kernel maps and the
+ * relocation reference symbol has not yet been found.  Otherwise %false is
+ * returned.
+ */
+static bool ref_reloc_sym_not_found(struct kmap *kmap)
+{
+	return kmap && kmap->ref_reloc_sym && kmap->ref_reloc_sym->name &&
+	       !kmap->ref_reloc_sym->unrelocated_addr;
+}
+
+/**
+ * ref_reloc - kernel relocation offset.
+ * @kmap: kernel maps and relocation reference symbol
+ *
+ * This function returns the offset of kernel addresses as determined by using
+ * the relocation reference symbol i.e. if the kernel has not been relocated
+ * then the return value is zero.
+ */
+static u64 ref_reloc(struct kmap *kmap)
+{
+	if (kmap && kmap->ref_reloc_sym &&
+	    kmap->ref_reloc_sym->unrelocated_addr)
+		return kmap->ref_reloc_sym->addr -
+		       kmap->ref_reloc_sym->unrelocated_addr;
+	return 0;
+}
+
+int dso__load_sym(struct dso *dso, struct map *map,
+		  struct symsrc *syms_ss, struct symsrc *runtime_ss,
+		  symbol_filter_t filter, int kmodule)
+{
+	struct kmap *kmap = dso->kernel ? map__kmap(map) : NULL;
+	struct map *curr_map = map;
+	struct dso *curr_dso = dso;
+	Elf_Data *symstrs, *secstrs;
+	uint32_t nr_syms;
+	int err = -1;
+	uint32_t idx;
+	GElf_Ehdr ehdr;
+	GElf_Shdr shdr;
+	Elf_Data *syms, *opddata = NULL;
+	GElf_Sym sym;
+	Elf_Scn *sec, *sec_strndx;
+	Elf *elf;
+	int nr = 0;
+	bool remap_kernel = false, adjust_kernel_syms = false;
+
+	dso->symtab_type = syms_ss->type;
+	dso->rel = syms_ss->ehdr.e_type == ET_REL;
+
+	/*
+	 * Modules may already have symbols from kallsyms, but those symbols
+	 * have the wrong values for the dso maps, so remove them.
+	 */
+	if (kmodule && syms_ss->symtab)
+		symbols__delete(&dso->symbols[map->type]);
+
+	if (!syms_ss->symtab) {
+		syms_ss->symtab  = syms_ss->dynsym;
+		syms_ss->symshdr = syms_ss->dynshdr;
+	}
+
+	elf = syms_ss->elf;
+	ehdr = syms_ss->ehdr;
+	sec = syms_ss->symtab;
+	shdr = syms_ss->symshdr;
+
+	if (runtime_ss->opdsec)
+		opddata = elf_rawdata(runtime_ss->opdsec, NULL);
+
+	syms = elf_getdata(sec, NULL);
+	if (syms == NULL)
+		goto out_elf_end;
+
+	sec = elf_getscn(elf, shdr.sh_link);
+	if (sec == NULL)
+		goto out_elf_end;
+
+	symstrs = elf_getdata(sec, NULL);
+	if (symstrs == NULL)
+		goto out_elf_end;
+
+	sec_strndx = elf_getscn(elf, ehdr.e_shstrndx);
+	if (sec_strndx == NULL)
+		goto out_elf_end;
+
+	secstrs = elf_getdata(sec_strndx, NULL);
+	if (secstrs == NULL)
+		goto out_elf_end;
+
+	nr_syms = shdr.sh_size / shdr.sh_entsize;
+
+	memset(&sym, 0, sizeof(sym));
+
+	/*
+	 * The kernel relocation symbol is needed in advance in order to adjust
+	 * kernel maps correctly.
+	 */
+	if (ref_reloc_sym_not_found(kmap)) {
+		elf_symtab__for_each_symbol(syms, nr_syms, idx, sym) {
+			const char *elf_name = elf_sym__name(&sym, symstrs);
+
+			if (strcmp(elf_name, kmap->ref_reloc_sym->name))
+				continue;
+			kmap->ref_reloc_sym->unrelocated_addr = sym.st_value;
+			map->reloc = kmap->ref_reloc_sym->addr -
+				     kmap->ref_reloc_sym->unrelocated_addr;
+			break;
+		}
+	}
+
+	dso->adjust_symbols = runtime_ss->adjust_symbols || ref_reloc(kmap);
+	/*
+	 * Initial kernel and module mappings do not map to the dso.  For
+	 * function mappings, flag the fixups.
+	 */
+	if (map->type == MAP__FUNCTION && (dso->kernel || kmodule)) {
+		remap_kernel = true;
+		adjust_kernel_syms = dso->adjust_symbols;
+	}
+	elf_symtab__for_each_symbol(syms, nr_syms, idx, sym) {
+		struct symbol *f;
+		const char *elf_name = elf_sym__name(&sym, symstrs);
+		char *demangled = NULL;
+		int is_label = elf_sym__is_label(&sym);
+		const char *section_name;
+		bool used_opd = false;
+
+		if (!is_label && !elf_sym__is_a(&sym, map->type))
+			continue;
+
+		/* Reject ARM ELF "mapping symbols": these aren't unique and
+		 * don't identify functions, so will confuse the profile
+		 * output: */
+		if (ehdr.e_machine == EM_ARM) {
+			if (!strcmp(elf_name, "$a") ||
+			    !strcmp(elf_name, "$d") ||
+			    !strcmp(elf_name, "$t"))
+				continue;
+		}
+
+		if (runtime_ss->opdsec && sym.st_shndx == runtime_ss->opdidx) {
+			u32 offset = sym.st_value - syms_ss->opdshdr.sh_addr;
+			u64 *opd = opddata->d_buf + offset;
+			sym.st_value = DSO__SWAP(dso, u64, *opd);
+			sym.st_shndx = elf_addr_to_index(runtime_ss->elf,
+					sym.st_value);
+			used_opd = true;
+		}
+		/*
+		 * When loading symbols in a data mapping, ABS symbols (which
+		 * has a value of SHN_ABS in its st_shndx) failed at
+		 * elf_getscn().  And it marks the loading as a failure so
+		 * already loaded symbols cannot be fixed up.
+		 *
+		 * I'm not sure what should be done. Just ignore them for now.
+		 * - Namhyung Kim
+		 */
+		if (sym.st_shndx == SHN_ABS)
+			continue;
+
+		sec = elf_getscn(runtime_ss->elf, sym.st_shndx);
+		if (!sec)
+			goto out_elf_end;
+
+		gelf_getshdr(sec, &shdr);
+
+		if (is_label && !elf_sec__is_a(&shdr, secstrs, map->type))
+			continue;
+
+		section_name = elf_sec__name(&shdr, secstrs);
+
+		/* On ARM, symbols for thumb functions have 1 added to
+		 * the symbol address as a flag - remove it */
+		if ((ehdr.e_machine == EM_ARM) &&
+		    (map->type == MAP__FUNCTION) &&
+		    (sym.st_value & 1))
+			--sym.st_value;
+
+		if (dso->kernel || kmodule) {
+			char dso_name[PATH_MAX];
+
+			/* Adjust symbol to map to file offset */
+			if (adjust_kernel_syms)
+				sym.st_value -= shdr.sh_addr - shdr.sh_offset;
+
+			if (strcmp(section_name,
+				   (curr_dso->short_name +
+				    dso->short_name_len)) == 0)
+				goto new_symbol;
+
+			if (strcmp(section_name, ".text") == 0) {
+				/*
+				 * The initial kernel mapping is based on
+				 * kallsyms and identity maps.  Overwrite it to
+				 * map to the kernel dso.
+				 */
+				if (remap_kernel && dso->kernel) {
+					remap_kernel = false;
+					map->start = shdr.sh_addr +
+						     ref_reloc(kmap);
+					map->end = map->start + shdr.sh_size;
+					map->pgoff = shdr.sh_offset;
+					map->map_ip = map__map_ip;
+					map->unmap_ip = map__unmap_ip;
+					/* Ensure maps are correctly ordered */
+					map_groups__remove(kmap->kmaps, map);
+					map_groups__insert(kmap->kmaps, map);
+				}
+
+				/*
+				 * The initial module mapping is based on
+				 * /proc/modules mapped to offset zero.
+				 * Overwrite it to map to the module dso.
+				 */
+				if (remap_kernel && kmodule) {
+					remap_kernel = false;
+					map->pgoff = shdr.sh_offset;
+				}
+
+				curr_map = map;
+				curr_dso = dso;
+				goto new_symbol;
+			}
+
+			if (!kmap)
+				goto new_symbol;
+
+			snprintf(dso_name, sizeof(dso_name),
+				 "%s%s", dso->short_name, section_name);
+
+			curr_map = map_groups__find_by_name(kmap->kmaps, map->type, dso_name);
+			if (curr_map == NULL) {
+				u64 start = sym.st_value;
+
+				if (kmodule)
+					start += map->start + shdr.sh_offset;
+
+				curr_dso = dso__new(dso_name);
+				if (curr_dso == NULL)
+					goto out_elf_end;
+				curr_dso->kernel = dso->kernel;
+				curr_dso->long_name = dso->long_name;
+				curr_dso->long_name_len = dso->long_name_len;
+				curr_map = map__new2(start, curr_dso,
+						     map->type);
+				if (curr_map == NULL) {
+					dso__delete(curr_dso);
+					goto out_elf_end;
+				}
+				if (adjust_kernel_syms) {
+					curr_map->start = shdr.sh_addr +
+							  ref_reloc(kmap);
+					curr_map->end = curr_map->start +
+							shdr.sh_size;
+					curr_map->pgoff = shdr.sh_offset;
+				} else {
+					curr_map->map_ip = identity__map_ip;
+					curr_map->unmap_ip = identity__map_ip;
+				}
+				curr_dso->symtab_type = dso->symtab_type;
+				map_groups__insert(kmap->kmaps, curr_map);
+				dsos__add(&dso->node, curr_dso);
+				dso__set_loaded(curr_dso, map->type);
+			} else
+				curr_dso = curr_map->dso;
+
+			goto new_symbol;
+		}
+
+		if ((used_opd && runtime_ss->adjust_symbols)
+				|| (!used_opd && syms_ss->adjust_symbols)) {
+			pr_debug4("%s: adjusting symbol: st_value: %#" PRIx64 " "
+				  "sh_addr: %#" PRIx64 " sh_offset: %#" PRIx64 "\n", __func__,
+				  (u64)sym.st_value, (u64)shdr.sh_addr,
+				  (u64)shdr.sh_offset);
+			sym.st_value -= shdr.sh_addr - shdr.sh_offset;
+		}
+new_symbol:
+		/*
+		 * We need to figure out if the object was created from C++ sources
+		 * DWARF DW_compile_unit has this, but we don't always have access
+		 * to it...
+		 */
+		if (symbol_conf.demangle) {
+			demangled = bfd_demangle(NULL, elf_name,
+						 DMGL_PARAMS | DMGL_ANSI);
+			if (demangled != NULL)
+				elf_name = demangled;
+		}
+		f = symbol__new(sym.st_value, sym.st_size,
+				GELF_ST_BIND(sym.st_info), elf_name);
+		free(demangled);
+		if (!f)
+			goto out_elf_end;
+
+		if (filter && filter(curr_map, f))
+			symbol__delete(f);
+		else {
+			symbols__insert(&curr_dso->symbols[curr_map->type], f);
+			nr++;
+		}
+	}
+
+	/*
+	 * For misannotated, zeroed, ASM function sizes.
+	 */
+	if (nr > 0) {
+		symbols__fixup_duplicate(&dso->symbols[map->type]);
+		symbols__fixup_end(&dso->symbols[map->type]);
+		if (kmap) {
+			/*
+			 * We need to fixup this here too because we create new
+			 * maps here, for things like vsyscall sections.
+			 */
+			__map_groups__fixup_end(kmap->kmaps, map->type);
+		}
+	}
+	err = nr;
+out_elf_end:
+	return err;
+}
+
+static int elf_read_maps(Elf *elf, bool exe, mapfn_t mapfn, void *data)
+{
+	GElf_Phdr phdr;
+	size_t i, phdrnum;
+	int err;
+	u64 sz;
+
+	if (elf_getphdrnum(elf, &phdrnum))
+		return -1;
+
+	for (i = 0; i < phdrnum; i++) {
+		if (gelf_getphdr(elf, i, &phdr) == NULL)
+			return -1;
+		if (phdr.p_type != PT_LOAD)
+			continue;
+		if (exe) {
+			if (!(phdr.p_flags & PF_X))
+				continue;
+		} else {
+			if (!(phdr.p_flags & PF_R))
+				continue;
+		}
+		sz = min(phdr.p_memsz, phdr.p_filesz);
+		if (!sz)
+			continue;
+		err = mapfn(phdr.p_vaddr, sz, phdr.p_offset, data);
+		if (err)
+			return err;
+	}
+	return 0;
+}
+
+int file__read_maps(int fd, bool exe, mapfn_t mapfn, void *data,
+		    bool *is_64_bit)
+{
+	int err;
+	Elf *elf;
+
+	elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
+	if (elf == NULL)
+		return -1;
+
+	if (is_64_bit)
+		*is_64_bit = (gelf_getclass(elf) == ELFCLASS64);
+
+	err = elf_read_maps(elf, exe, mapfn, data);
+
+	elf_end(elf);
+	return err;
+}
+
+static int copy_bytes(int from, off_t from_offs, int to, off_t to_offs, u64 len)
+{
+	ssize_t r;
+	size_t n;
+	int err = -1;
+	char *buf = malloc(page_size);
+
+	if (buf == NULL)
+		return -1;
+
+	if (lseek(to, to_offs, SEEK_SET) != to_offs)
+		goto out;
+
+	if (lseek(from, from_offs, SEEK_SET) != from_offs)
+		goto out;
+
+	while (len) {
+		n = page_size;
+		if (len < n)
+			n = len;
+		/* Use read because mmap won't work on proc files */
+		r = read(from, buf, n);
+		if (r < 0)
+			goto out;
+		if (!r)
+			break;
+		n = r;
+		r = write(to, buf, n);
+		if (r < 0)
+			goto out;
+		if ((size_t)r != n)
+			goto out;
+		len -= n;
+	}
+
+	err = 0;
+out:
+	free(buf);
+	return err;
+}
+
+struct kcore {
+	int fd;
+	int elfclass;
+	Elf *elf;
+	GElf_Ehdr ehdr;
+};
+
+static int kcore__open(struct kcore *kcore, const char *filename)
+{
+	GElf_Ehdr *ehdr;
+
+	kcore->fd = open(filename, O_RDONLY);
+	if (kcore->fd == -1)
+		return -1;
+
+	kcore->elf = elf_begin(kcore->fd, ELF_C_READ, NULL);
+	if (!kcore->elf)
+		goto out_close;
+
+	kcore->elfclass = gelf_getclass(kcore->elf);
+	if (kcore->elfclass == ELFCLASSNONE)
+		goto out_end;
+
+	ehdr = gelf_getehdr(kcore->elf, &kcore->ehdr);
+	if (!ehdr)
+		goto out_end;
+
+	return 0;
+
+out_end:
+	elf_end(kcore->elf);
+out_close:
+	close(kcore->fd);
+	return -1;
+}
+
+static int kcore__init(struct kcore *kcore, char *filename, int elfclass,
+		       bool temp)
+{
+	GElf_Ehdr *ehdr;
+
+	kcore->elfclass = elfclass;
+
+	if (temp)
+		kcore->fd = mkstemp(filename);
+	else
+		kcore->fd = open(filename, O_WRONLY | O_CREAT | O_EXCL, 0400);
+	if (kcore->fd == -1)
+		return -1;
+
+	kcore->elf = elf_begin(kcore->fd, ELF_C_WRITE, NULL);
+	if (!kcore->elf)
+		goto out_close;
+
+	if (!gelf_newehdr(kcore->elf, elfclass))
+		goto out_end;
+
+	ehdr = gelf_getehdr(kcore->elf, &kcore->ehdr);
+	if (!ehdr)
+		goto out_end;
+
+	return 0;
+
+out_end:
+	elf_end(kcore->elf);
+out_close:
+	close(kcore->fd);
+	unlink(filename);
+	return -1;
+}
+
+static void kcore__close(struct kcore *kcore)
+{
+	elf_end(kcore->elf);
+	close(kcore->fd);
+}
+
+static int kcore__copy_hdr(struct kcore *from, struct kcore *to, size_t count)
+{
+	GElf_Ehdr *ehdr = &to->ehdr;
+	GElf_Ehdr *kehdr = &from->ehdr;
+
+	memcpy(ehdr->e_ident, kehdr->e_ident, EI_NIDENT);
+	ehdr->e_type      = kehdr->e_type;
+	ehdr->e_machine   = kehdr->e_machine;
+	ehdr->e_version   = kehdr->e_version;
+	ehdr->e_entry     = 0;
+	ehdr->e_shoff     = 0;
+	ehdr->e_flags     = kehdr->e_flags;
+	ehdr->e_phnum     = count;
+	ehdr->e_shentsize = 0;
+	ehdr->e_shnum     = 0;
+	ehdr->e_shstrndx  = 0;
+
+	if (from->elfclass == ELFCLASS32) {
+		ehdr->e_phoff     = sizeof(Elf32_Ehdr);
+		ehdr->e_ehsize    = sizeof(Elf32_Ehdr);
+		ehdr->e_phentsize = sizeof(Elf32_Phdr);
+	} else {
+		ehdr->e_phoff     = sizeof(Elf64_Ehdr);
+		ehdr->e_ehsize    = sizeof(Elf64_Ehdr);
+		ehdr->e_phentsize = sizeof(Elf64_Phdr);
+	}
+
+	if (!gelf_update_ehdr(to->elf, ehdr))
+		return -1;
+
+	if (!gelf_newphdr(to->elf, count))
+		return -1;
+
+	return 0;
+}
+
+static int kcore__add_phdr(struct kcore *kcore, int idx, off_t offset,
+			   u64 addr, u64 len)
+{
+	GElf_Phdr gphdr;
+	GElf_Phdr *phdr;
+
+	phdr = gelf_getphdr(kcore->elf, idx, &gphdr);
+	if (!phdr)
+		return -1;
+
+	phdr->p_type	= PT_LOAD;
+	phdr->p_flags	= PF_R | PF_W | PF_X;
+	phdr->p_offset	= offset;
+	phdr->p_vaddr	= addr;
+	phdr->p_paddr	= 0;
+	phdr->p_filesz	= len;
+	phdr->p_memsz	= len;
+	phdr->p_align	= page_size;
+
+	if (!gelf_update_phdr(kcore->elf, idx, phdr))
+		return -1;
+
+	return 0;
+}
+
+static off_t kcore__write(struct kcore *kcore)
+{
+	return elf_update(kcore->elf, ELF_C_WRITE);
+}
+
+struct phdr_data {
+	off_t offset;
+	u64 addr;
+	u64 len;
+};
+
+struct kcore_copy_info {
+	u64 stext;
+	u64 etext;
+	u64 first_symbol;
+	u64 last_symbol;
+	u64 first_module;
+	u64 last_module_symbol;
+	struct phdr_data kernel_map;
+	struct phdr_data modules_map;
+};
+
+static int kcore_copy__process_kallsyms(void *arg, const char *name, char type,
+					u64 start)
+{
+	struct kcore_copy_info *kci = arg;
+
+	if (!symbol_type__is_a(type, MAP__FUNCTION))
+		return 0;
+
+	if (strchr(name, '[')) {
+		if (start > kci->last_module_symbol)
+			kci->last_module_symbol = start;
+		return 0;
+	}
+
+	if (!kci->first_symbol || start < kci->first_symbol)
+		kci->first_symbol = start;
+
+	if (!kci->last_symbol || start > kci->last_symbol)
+		kci->last_symbol = start;
+
+	if (!strcmp(name, "_stext")) {
+		kci->stext = start;
+		return 0;
+	}
+
+	if (!strcmp(name, "_etext")) {
+		kci->etext = start;
+		return 0;
+	}
+
+	return 0;
+}
+
+static int kcore_copy__parse_kallsyms(struct kcore_copy_info *kci,
+				      const char *dir)
+{
+	char kallsyms_filename[PATH_MAX];
+
+	scnprintf(kallsyms_filename, PATH_MAX, "%s/kallsyms", dir);
+
+	if (symbol__restricted_filename(kallsyms_filename, "/proc/kallsyms"))
+		return -1;
+
+	if (kallsyms__parse(kallsyms_filename, kci,
+			    kcore_copy__process_kallsyms) < 0)
+		return -1;
+
+	return 0;
+}
+
+static int kcore_copy__process_modules(void *arg,
+				       const char *name __maybe_unused,
+				       u64 start)
+{
+	struct kcore_copy_info *kci = arg;
+
+	if (!kci->first_module || start < kci->first_module)
+		kci->first_module = start;
+
+	return 0;
+}
+
+static int kcore_copy__parse_modules(struct kcore_copy_info *kci,
+				     const char *dir)
+{
+	char modules_filename[PATH_MAX];
+
+	scnprintf(modules_filename, PATH_MAX, "%s/modules", dir);
+
+	if (symbol__restricted_filename(modules_filename, "/proc/modules"))
+		return -1;
+
+	if (modules__parse(modules_filename, kci,
+			   kcore_copy__process_modules) < 0)
+		return -1;
+
+	return 0;
+}
+
+static void kcore_copy__map(struct phdr_data *p, u64 start, u64 end, u64 pgoff,
+			    u64 s, u64 e)
+{
+	if (p->addr || s < start || s >= end)
+		return;
+
+	p->addr = s;
+	p->offset = (s - start) + pgoff;
+	p->len = e < end ? e - s : end - s;
+}
+
+static int kcore_copy__read_map(u64 start, u64 len, u64 pgoff, void *data)
+{
+	struct kcore_copy_info *kci = data;
+	u64 end = start + len;
+
+	kcore_copy__map(&kci->kernel_map, start, end, pgoff, kci->stext,
+			kci->etext);
+
+	kcore_copy__map(&kci->modules_map, start, end, pgoff, kci->first_module,
+			kci->last_module_symbol);
+
+	return 0;
+}
+
+static int kcore_copy__read_maps(struct kcore_copy_info *kci, Elf *elf)
+{
+	if (elf_read_maps(elf, true, kcore_copy__read_map, kci) < 0)
+		return -1;
+
+	return 0;
+}
+
+static int kcore_copy__calc_maps(struct kcore_copy_info *kci, const char *dir,
+				 Elf *elf)
+{
+	if (kcore_copy__parse_kallsyms(kci, dir))
+		return -1;
+
+	if (kcore_copy__parse_modules(kci, dir))
+		return -1;
+
+	if (kci->stext)
+		kci->stext = round_down(kci->stext, page_size);
+	else
+		kci->stext = round_down(kci->first_symbol, page_size);
+
+	if (kci->etext) {
+		kci->etext = round_up(kci->etext, page_size);
+	} else if (kci->last_symbol) {
+		kci->etext = round_up(kci->last_symbol, page_size);
+		kci->etext += page_size;
+	}
+
+	kci->first_module = round_down(kci->first_module, page_size);
+
+	if (kci->last_module_symbol) {
+		kci->last_module_symbol = round_up(kci->last_module_symbol,
+						   page_size);
+		kci->last_module_symbol += page_size;
+	}
+
+	if (!kci->stext || !kci->etext)
+		return -1;
+
+	if (kci->first_module && !kci->last_module_symbol)
+		return -1;
+
+	return kcore_copy__read_maps(kci, elf);
+}
+
+static int kcore_copy__copy_file(const char *from_dir, const char *to_dir,
+				 const char *name)
+{
+	char from_filename[PATH_MAX];
+	char to_filename[PATH_MAX];
+
+	scnprintf(from_filename, PATH_MAX, "%s/%s", from_dir, name);
+	scnprintf(to_filename, PATH_MAX, "%s/%s", to_dir, name);
+
+	return copyfile_mode(from_filename, to_filename, 0400);
+}
+
+static int kcore_copy__unlink(const char *dir, const char *name)
+{
+	char filename[PATH_MAX];
+
+	scnprintf(filename, PATH_MAX, "%s/%s", dir, name);
+
+	return unlink(filename);
+}
+
+static int kcore_copy__compare_fds(int from, int to)
+{
+	char *buf_from;
+	char *buf_to;
+	ssize_t ret;
+	size_t len;
+	int err = -1;
+
+	buf_from = malloc(page_size);
+	buf_to = malloc(page_size);
+	if (!buf_from || !buf_to)
+		goto out;
+
+	while (1) {
+		/* Use read because mmap won't work on proc files */
+		ret = read(from, buf_from, page_size);
+		if (ret < 0)
+			goto out;
+
+		if (!ret)
+			break;
+
+		len = ret;
+
+		if (readn(to, buf_to, len) != (int)len)
+			goto out;
+
+		if (memcmp(buf_from, buf_to, len))
+			goto out;
+	}
+
+	err = 0;
+out:
+	free(buf_to);
+	free(buf_from);
+	return err;
+}
+
+static int kcore_copy__compare_files(const char *from_filename,
+				     const char *to_filename)
+{
+	int from, to, err = -1;
+
+	from = open(from_filename, O_RDONLY);
+	if (from < 0)
+		return -1;
+
+	to = open(to_filename, O_RDONLY);
+	if (to < 0)
+		goto out_close_from;
+
+	err = kcore_copy__compare_fds(from, to);
+
+	close(to);
+out_close_from:
+	close(from);
+	return err;
+}
+
+static int kcore_copy__compare_file(const char *from_dir, const char *to_dir,
+				    const char *name)
+{
+	char from_filename[PATH_MAX];
+	char to_filename[PATH_MAX];
+
+	scnprintf(from_filename, PATH_MAX, "%s/%s", from_dir, name);
+	scnprintf(to_filename, PATH_MAX, "%s/%s", to_dir, name);
+
+	return kcore_copy__compare_files(from_filename, to_filename);
+}
+
+/**
+ * kcore_copy - copy kallsyms, modules and kcore from one directory to another.
+ * @from_dir: from directory
+ * @to_dir: to directory
+ *
+ * This function copies kallsyms, modules and kcore files from one directory to
+ * another.  kallsyms and modules are copied entirely.  Only code segments are
+ * copied from kcore.  It is assumed that two segments suffice: one for the
+ * kernel proper and one for all the modules.  The code segments are determined
+ * from kallsyms and modules files.  The kernel map starts at _stext or the
+ * lowest function symbol, and ends at _etext or the highest function symbol.
+ * The module map starts at the lowest module address and ends at the highest
+ * module symbol.  Start addresses are rounded down to the nearest page.  End
+ * addresses are rounded up to the nearest page.  An extra page is added to the
+ * highest kernel symbol and highest module symbol to, hopefully, encompass that
+ * symbol too.  Because it contains only code sections, the resulting kcore is
+ * unusual.  One significant peculiarity is that the mapping (start -> pgoff)
+ * is not the same for the kernel map and the modules map.  That happens because
+ * the data is copied adjacently whereas the original kcore has gaps.  Finally,
+ * kallsyms and modules files are compared with their copies to check that
+ * modules have not been loaded or unloaded while the copies were taking place.
+ *
+ * Return: %0 on success, %-1 on failure.
+ */
+int kcore_copy(const char *from_dir, const char *to_dir)
+{
+	struct kcore kcore;
+	struct kcore extract;
+	size_t count = 2;
+	int idx = 0, err = -1;
+	off_t offset = page_size, sz, modules_offset = 0;
+	struct kcore_copy_info kci = { .stext = 0, };
+	char kcore_filename[PATH_MAX];
+	char extract_filename[PATH_MAX];
+
+	if (kcore_copy__copy_file(from_dir, to_dir, "kallsyms"))
+		return -1;
+
+	if (kcore_copy__copy_file(from_dir, to_dir, "modules"))
+		goto out_unlink_kallsyms;
+
+	scnprintf(kcore_filename, PATH_MAX, "%s/kcore", from_dir);
+	scnprintf(extract_filename, PATH_MAX, "%s/kcore", to_dir);
+
+	if (kcore__open(&kcore, kcore_filename))
+		goto out_unlink_modules;
+
+	if (kcore_copy__calc_maps(&kci, from_dir, kcore.elf))
+		goto out_kcore_close;
+
+	if (kcore__init(&extract, extract_filename, kcore.elfclass, false))
+		goto out_kcore_close;
+
+	if (!kci.modules_map.addr)
+		count -= 1;
+
+	if (kcore__copy_hdr(&kcore, &extract, count))
+		goto out_extract_close;
+
+	if (kcore__add_phdr(&extract, idx++, offset, kci.kernel_map.addr,
+			    kci.kernel_map.len))
+		goto out_extract_close;
+
+	if (kci.modules_map.addr) {
+		modules_offset = offset + kci.kernel_map.len;
+		if (kcore__add_phdr(&extract, idx, modules_offset,
+				    kci.modules_map.addr, kci.modules_map.len))
+			goto out_extract_close;
+	}
+
+	sz = kcore__write(&extract);
+	if (sz < 0 || sz > offset)
+		goto out_extract_close;
+
+	if (copy_bytes(kcore.fd, kci.kernel_map.offset, extract.fd, offset,
+		       kci.kernel_map.len))
+		goto out_extract_close;
+
+	if (modules_offset && copy_bytes(kcore.fd, kci.modules_map.offset,
+					 extract.fd, modules_offset,
+					 kci.modules_map.len))
+		goto out_extract_close;
+
+	if (kcore_copy__compare_file(from_dir, to_dir, "modules"))
+		goto out_extract_close;
+
+	if (kcore_copy__compare_file(from_dir, to_dir, "kallsyms"))
+		goto out_extract_close;
+
+	err = 0;
+
+out_extract_close:
+	kcore__close(&extract);
+	if (err)
+		unlink(extract_filename);
+out_kcore_close:
+	kcore__close(&kcore);
+out_unlink_modules:
+	if (err)
+		kcore_copy__unlink(to_dir, "modules");
+out_unlink_kallsyms:
+	if (err)
+		kcore_copy__unlink(to_dir, "kallsyms");
+
+	return err;
+}
+
+int kcore_extract__create(struct kcore_extract *kce)
+{
+	struct kcore kcore;
+	struct kcore extract;
+	size_t count = 1;
+	int idx = 0, err = -1;
+	off_t offset = page_size, sz;
+
+	if (kcore__open(&kcore, kce->kcore_filename))
+		return -1;
+
+	strcpy(kce->extract_filename, PERF_KCORE_EXTRACT);
+	if (kcore__init(&extract, kce->extract_filename, kcore.elfclass, true))
+		goto out_kcore_close;
+
+	if (kcore__copy_hdr(&kcore, &extract, count))
+		goto out_extract_close;
+
+	if (kcore__add_phdr(&extract, idx, offset, kce->addr, kce->len))
+		goto out_extract_close;
+
+	sz = kcore__write(&extract);
+	if (sz < 0 || sz > offset)
+		goto out_extract_close;
+
+	if (copy_bytes(kcore.fd, kce->offs, extract.fd, offset, kce->len))
+		goto out_extract_close;
+
+	err = 0;
+
+out_extract_close:
+	kcore__close(&extract);
+	if (err)
+		unlink(kce->extract_filename);
+out_kcore_close:
+	kcore__close(&kcore);
+
+	return err;
+}
+
+void kcore_extract__delete(struct kcore_extract *kce)
+{
+	unlink(kce->extract_filename);
+}
+
+void symbol__elf_init(void)
+{
+	elf_version(EV_CURRENT);
+}
diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c
new file mode 100644
index 00000000000..bd15f490d04
--- /dev/null
+++ b/tools/perf/util/symbol-minimal.c
@@ -0,0 +1,330 @@
+#include "symbol.h"
+#include "util.h"
+
+#include <stdio.h>
+#include <fcntl.h>
+#include <string.h>
+#include <byteswap.h>
+#include <sys/stat.h>
+
+
+static bool check_need_swap(int file_endian)
+{
+	const int data = 1;
+	u8 *check = (u8 *)&data;
+	int host_endian;
+
+	if (check[0] == 1)
+		host_endian = ELFDATA2LSB;
+	else
+		host_endian = ELFDATA2MSB;
+
+	return host_endian != file_endian;
+}
+
+#define NOTE_ALIGN(sz) (((sz) + 3) & ~3)
+
+#define NT_GNU_BUILD_ID	3
+
+static int read_build_id(void *note_data, size_t note_len, void *bf,
+			 size_t size, bool need_swap)
+{
+	struct {
+		u32 n_namesz;
+		u32 n_descsz;
+		u32 n_type;
+	} *nhdr;
+	void *ptr;
+
+	ptr = note_data;
+	while (ptr < (note_data + note_len)) {
+		const char *name;
+		size_t namesz, descsz;
+
+		nhdr = ptr;
+		if (need_swap) {
+			nhdr->n_namesz = bswap_32(nhdr->n_namesz);
+			nhdr->n_descsz = bswap_32(nhdr->n_descsz);
+			nhdr->n_type = bswap_32(nhdr->n_type);
+		}
+
+		namesz = NOTE_ALIGN(nhdr->n_namesz);
+		descsz = NOTE_ALIGN(nhdr->n_descsz);
+
+		ptr += sizeof(*nhdr);
+		name = ptr;
+		ptr += namesz;
+		if (nhdr->n_type == NT_GNU_BUILD_ID &&
+		    nhdr->n_namesz == sizeof("GNU")) {
+			if (memcmp(name, "GNU", sizeof("GNU")) == 0) {
+				size_t sz = min(size, descsz);
+				memcpy(bf, ptr, sz);
+				memset(bf + sz, 0, size - sz);
+				return 0;
+			}
+		}
+		ptr += descsz;
+	}
+
+	return -1;
+}
+
+int filename__read_debuglink(const char *filename __maybe_unused,
+			     char *debuglink __maybe_unused,
+			     size_t size __maybe_unused)
+{
+	return -1;
+}
+
+/*
+ * Just try PT_NOTE header otherwise fails
+ */
+int filename__read_build_id(const char *filename, void *bf, size_t size)
+{
+	FILE *fp;
+	int ret = -1;
+	bool need_swap = false;
+	u8 e_ident[EI_NIDENT];
+	size_t buf_size;
+	void *buf;
+	int i;
+
+	fp = fopen(filename, "r");
+	if (fp == NULL)
+		return -1;
+
+	if (fread(e_ident, sizeof(e_ident), 1, fp) != 1)
+		goto out;
+
+	if (memcmp(e_ident, ELFMAG, SELFMAG) ||
+	    e_ident[EI_VERSION] != EV_CURRENT)
+		goto out;
+
+	need_swap = check_need_swap(e_ident[EI_DATA]);
+
+	/* for simplicity */
+	fseek(fp, 0, SEEK_SET);
+
+	if (e_ident[EI_CLASS] == ELFCLASS32) {
+		Elf32_Ehdr ehdr;
+		Elf32_Phdr *phdr;
+
+		if (fread(&ehdr, sizeof(ehdr), 1, fp) != 1)
+			goto out;
+
+		if (need_swap) {
+			ehdr.e_phoff = bswap_32(ehdr.e_phoff);
+			ehdr.e_phentsize = bswap_16(ehdr.e_phentsize);
+			ehdr.e_phnum = bswap_16(ehdr.e_phnum);
+		}
+
+		buf_size = ehdr.e_phentsize * ehdr.e_phnum;
+		buf = malloc(buf_size);
+		if (buf == NULL)
+			goto out;
+
+		fseek(fp, ehdr.e_phoff, SEEK_SET);
+		if (fread(buf, buf_size, 1, fp) != 1)
+			goto out_free;
+
+		for (i = 0, phdr = buf; i < ehdr.e_phnum; i++, phdr++) {
+			void *tmp;
+
+			if (need_swap) {
+				phdr->p_type = bswap_32(phdr->p_type);
+				phdr->p_offset = bswap_32(phdr->p_offset);
+				phdr->p_filesz = bswap_32(phdr->p_filesz);
+			}
+
+			if (phdr->p_type != PT_NOTE)
+				continue;
+
+			buf_size = phdr->p_filesz;
+			tmp = realloc(buf, buf_size);
+			if (tmp == NULL)
+				goto out_free;
+
+			buf = tmp;
+			fseek(fp, phdr->p_offset, SEEK_SET);
+			if (fread(buf, buf_size, 1, fp) != 1)
+				goto out_free;
+
+			ret = read_build_id(buf, buf_size, bf, size, need_swap);
+			if (ret == 0)
+				ret = size;
+			break;
+		}
+	} else {
+		Elf64_Ehdr ehdr;
+		Elf64_Phdr *phdr;
+
+		if (fread(&ehdr, sizeof(ehdr), 1, fp) != 1)
+			goto out;
+
+		if (need_swap) {
+			ehdr.e_phoff = bswap_64(ehdr.e_phoff);
+			ehdr.e_phentsize = bswap_16(ehdr.e_phentsize);
+			ehdr.e_phnum = bswap_16(ehdr.e_phnum);
+		}
+
+		buf_size = ehdr.e_phentsize * ehdr.e_phnum;
+		buf = malloc(buf_size);
+		if (buf == NULL)
+			goto out;
+
+		fseek(fp, ehdr.e_phoff, SEEK_SET);
+		if (fread(buf, buf_size, 1, fp) != 1)
+			goto out_free;
+
+		for (i = 0, phdr = buf; i < ehdr.e_phnum; i++, phdr++) {
+			void *tmp;
+
+			if (need_swap) {
+				phdr->p_type = bswap_32(phdr->p_type);
+				phdr->p_offset = bswap_64(phdr->p_offset);
+				phdr->p_filesz = bswap_64(phdr->p_filesz);
+			}
+
+			if (phdr->p_type != PT_NOTE)
+				continue;
+
+			buf_size = phdr->p_filesz;
+			tmp = realloc(buf, buf_size);
+			if (tmp == NULL)
+				goto out_free;
+
+			buf = tmp;
+			fseek(fp, phdr->p_offset, SEEK_SET);
+			if (fread(buf, buf_size, 1, fp) != 1)
+				goto out_free;
+
+			ret = read_build_id(buf, buf_size, bf, size, need_swap);
+			if (ret == 0)
+				ret = size;
+			break;
+		}
+	}
+out_free:
+	free(buf);
+out:
+	fclose(fp);
+	return ret;
+}
+
+int sysfs__read_build_id(const char *filename, void *build_id, size_t size)
+{
+	int fd;
+	int ret = -1;
+	struct stat stbuf;
+	size_t buf_size;
+	void *buf;
+
+	fd = open(filename, O_RDONLY);
+	if (fd < 0)
+		return -1;
+
+	if (fstat(fd, &stbuf) < 0)
+		goto out;
+
+	buf_size = stbuf.st_size;
+	buf = malloc(buf_size);
+	if (buf == NULL)
+		goto out;
+
+	if (read(fd, buf, buf_size) != (ssize_t) buf_size)
+		goto out_free;
+
+	ret = read_build_id(buf, buf_size, build_id, size, false);
+out_free:
+	free(buf);
+out:
+	close(fd);
+	return ret;
+}
+
+int symsrc__init(struct symsrc *ss, struct dso *dso __maybe_unused,
+		 const char *name,
+	         enum dso_binary_type type)
+{
+	int fd = open(name, O_RDONLY);
+	if (fd < 0)
+		return -1;
+
+	ss->name = strdup(name);
+	if (!ss->name)
+		goto out_close;
+
+	ss->fd = fd;
+	ss->type = type;
+
+	return 0;
+out_close:
+	close(fd);
+	return -1;
+}
+
+bool symsrc__possibly_runtime(struct symsrc *ss __maybe_unused)
+{
+	/* Assume all sym sources could be a runtime image. */
+	return true;
+}
+
+bool symsrc__has_symtab(struct symsrc *ss __maybe_unused)
+{
+	return false;
+}
+
+void symsrc__destroy(struct symsrc *ss)
+{
+	zfree(&ss->name);
+	close(ss->fd);
+}
+
+int dso__synthesize_plt_symbols(struct dso *dso __maybe_unused,
+				struct symsrc *ss __maybe_unused,
+				struct map *map __maybe_unused,
+				symbol_filter_t filter __maybe_unused)
+{
+	return 0;
+}
+
+int dso__load_sym(struct dso *dso, struct map *map __maybe_unused,
+		  struct symsrc *ss,
+		  struct symsrc *runtime_ss __maybe_unused,
+		  symbol_filter_t filter __maybe_unused,
+		  int kmodule __maybe_unused)
+{
+	unsigned char *build_id[BUILD_ID_SIZE];
+
+	if (filename__read_build_id(ss->name, build_id, BUILD_ID_SIZE) > 0) {
+		dso__set_build_id(dso, build_id);
+		return 1;
+	}
+	return 0;
+}
+
+int file__read_maps(int fd __maybe_unused, bool exe __maybe_unused,
+		    mapfn_t mapfn __maybe_unused, void *data __maybe_unused,
+		    bool *is_64_bit __maybe_unused)
+{
+	return -1;
+}
+
+int kcore_extract__create(struct kcore_extract *kce __maybe_unused)
+{
+	return -1;
+}
+
+void kcore_extract__delete(struct kcore_extract *kce __maybe_unused)
+{
+}
+
+int kcore_copy(const char *from_dir __maybe_unused,
+	       const char *to_dir __maybe_unused)
+{
+	return -1;
+}
+
+void symbol__elf_init(void)
+{
+}
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index b63e5713849..7b9096f29cd 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1,8 +1,5 @@
-#define _GNU_SOURCE
-#include <ctype.h>
 #include <dirent.h>
 #include <errno.h>
-#include <libgen.h>
 #include <stdlib.h>
 #include <stdio.h>
 #include <string.h>
@@ -11,65 +8,169 @@
 #include <sys/param.h>
 #include <fcntl.h>
 #include <unistd.h>
+#include <inttypes.h>
 #include "build-id.h"
+#include "util.h"
+#include "debug.h"
+#include "machine.h"
 #include "symbol.h"
 #include "strlist.h"
 
-#include <libelf.h>
-#include <gelf.h>
 #include <elf.h>
 #include <limits.h>
+#include <symbol/kallsyms.h>
 #include <sys/utsname.h>
 
-#ifndef NT_GNU_BUILD_ID
-#define NT_GNU_BUILD_ID 3
-#endif
-
-static void dsos__add(struct list_head *head, struct dso *dso);
-static struct map *map__new2(u64 start, struct dso *dso, enum map_type type);
-static int dso__load_kernel_sym(struct dso *self, struct map *map,
+static int dso__load_kernel_sym(struct dso *dso, struct map *map,
 				symbol_filter_t filter);
-static int dso__load_guest_kernel_sym(struct dso *self, struct map *map,
+static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map,
 			symbol_filter_t filter);
-static int vmlinux_path__nr_entries;
-static char **vmlinux_path;
+int vmlinux_path__nr_entries;
+char **vmlinux_path;
 
 struct symbol_conf symbol_conf = {
-	.exclude_other	  = true,
-	.use_modules	  = true,
-	.try_vmlinux_path = true,
+	.use_modules		= true,
+	.try_vmlinux_path	= true,
+	.annotate_src		= true,
+	.demangle		= true,
+	.cumulate_callchain	= true,
+	.symfs			= "",
 };
 
-bool dso__loaded(const struct dso *self, enum map_type type)
-{
-	return self->loaded & (1 << type);
-}
-
-bool dso__sorted_by_name(const struct dso *self, enum map_type type)
-{
-	return self->sorted_by_name & (1 << type);
-}
+static enum dso_binary_type binary_type_symtab[] = {
+	DSO_BINARY_TYPE__KALLSYMS,
+	DSO_BINARY_TYPE__GUEST_KALLSYMS,
+	DSO_BINARY_TYPE__JAVA_JIT,
+	DSO_BINARY_TYPE__DEBUGLINK,
+	DSO_BINARY_TYPE__BUILD_ID_CACHE,
+	DSO_BINARY_TYPE__FEDORA_DEBUGINFO,
+	DSO_BINARY_TYPE__UBUNTU_DEBUGINFO,
+	DSO_BINARY_TYPE__BUILDID_DEBUGINFO,
+	DSO_BINARY_TYPE__SYSTEM_PATH_DSO,
+	DSO_BINARY_TYPE__GUEST_KMODULE,
+	DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE,
+	DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO,
+	DSO_BINARY_TYPE__NOT_FOUND,
+};
 
-static void dso__set_sorted_by_name(struct dso *self, enum map_type type)
-{
-	self->sorted_by_name |= (1 << type);
-}
+#define DSO_BINARY_TYPE__SYMTAB_CNT ARRAY_SIZE(binary_type_symtab)
 
 bool symbol_type__is_a(char symbol_type, enum map_type map_type)
 {
+	symbol_type = toupper(symbol_type);
+
 	switch (map_type) {
 	case MAP__FUNCTION:
 		return symbol_type == 'T' || symbol_type == 'W';
 	case MAP__VARIABLE:
-		return symbol_type == 'D' || symbol_type == 'd';
+		return symbol_type == 'D';
 	default:
 		return false;
 	}
 }
 
-static void symbols__fixup_end(struct rb_root *self)
+static int prefix_underscores_count(const char *str)
+{
+	const char *tail = str;
+
+	while (*tail == '_')
+		tail++;
+
+	return tail - str;
+}
+
+#define SYMBOL_A 0
+#define SYMBOL_B 1
+
+static int choose_best_symbol(struct symbol *syma, struct symbol *symb)
+{
+	s64 a;
+	s64 b;
+	size_t na, nb;
+
+	/* Prefer a symbol with non zero length */
+	a = syma->end - syma->start;
+	b = symb->end - symb->start;
+	if ((b == 0) && (a > 0))
+		return SYMBOL_A;
+	else if ((a == 0) && (b > 0))
+		return SYMBOL_B;
+
+	/* Prefer a non weak symbol over a weak one */
+	a = syma->binding == STB_WEAK;
+	b = symb->binding == STB_WEAK;
+	if (b && !a)
+		return SYMBOL_A;
+	if (a && !b)
+		return SYMBOL_B;
+
+	/* Prefer a global symbol over a non global one */
+	a = syma->binding == STB_GLOBAL;
+	b = symb->binding == STB_GLOBAL;
+	if (a && !b)
+		return SYMBOL_A;
+	if (b && !a)
+		return SYMBOL_B;
+
+	/* Prefer a symbol with less underscores */
+	a = prefix_underscores_count(syma->name);
+	b = prefix_underscores_count(symb->name);
+	if (b > a)
+		return SYMBOL_A;
+	else if (a > b)
+		return SYMBOL_B;
+
+	/* Choose the symbol with the longest name */
+	na = strlen(syma->name);
+	nb = strlen(symb->name);
+	if (na > nb)
+		return SYMBOL_A;
+	else if (na < nb)
+		return SYMBOL_B;
+
+	/* Avoid "SyS" kernel syscall aliases */
+	if (na >= 3 && !strncmp(syma->name, "SyS", 3))
+		return SYMBOL_B;
+	if (na >= 10 && !strncmp(syma->name, "compat_SyS", 10))
+		return SYMBOL_B;
+
+	return SYMBOL_A;
+}
+
+void symbols__fixup_duplicate(struct rb_root *symbols)
+{
+	struct rb_node *nd;
+	struct symbol *curr, *next;
+
+	nd = rb_first(symbols);
+
+	while (nd) {
+		curr = rb_entry(nd, struct symbol, rb_node);
+again:
+		nd = rb_next(&curr->rb_node);
+		next = rb_entry(nd, struct symbol, rb_node);
+
+		if (!nd)
+			break;
+
+		if (curr->start != next->start)
+			continue;
+
+		if (choose_best_symbol(curr, next) == SYMBOL_A) {
+			rb_erase(&next->rb_node, symbols);
+			symbol__delete(next);
+			goto again;
+		} else {
+			nd = rb_next(&curr->rb_node);
+			rb_erase(&curr->rb_node, symbols);
+			symbol__delete(curr);
+		}
+	}
+}
+
+void symbols__fixup_end(struct rb_root *symbols)
 {
-	struct rb_node *nd, *prevnd = rb_first(self);
+	struct rb_node *nd, *prevnd = rb_first(symbols);
 	struct symbol *curr, *prev;
 
 	if (prevnd == NULL)
@@ -81,7 +182,7 @@ static void symbols__fixup_end(struct rb_root *self)
 		prev = curr;
 		curr = rb_entry(nd, struct symbol, rb_node);
 
-		if (prev->end == prev->start)
+		if (prev->end == prev->start && prev->end != curr->start)
 			prev->end = curr->start - 1;
 	}
 
@@ -90,10 +191,10 @@ static void symbols__fixup_end(struct rb_root *self)
 		curr->end = roundup(curr->start, 4096);
 }
 
-static void __map_groups__fixup_end(struct map_groups *self, enum map_type type)
+void __map_groups__fixup_end(struct map_groups *mg, enum map_type type)
 {
 	struct map *prev, *curr;
-	struct rb_node *nd, *prevnd = rb_first(&self->maps[type]);
+	struct rb_node *nd, *prevnd = rb_first(&mg->maps[type]);
 
 	if (prevnd == NULL)
 		return;
@@ -110,125 +211,87 @@ static void __map_groups__fixup_end(struct map_groups *self, enum map_type type)
 	 * We still haven't the actual symbols, so guess the
 	 * last map final address.
 	 */
-	curr->end = ~0UL;
-}
-
-static void map_groups__fixup_end(struct map_groups *self)
-{
-	int i;
-	for (i = 0; i < MAP__NR_TYPES; ++i)
-		__map_groups__fixup_end(self, i);
+	curr->end = ~0ULL;
 }
 
-static struct symbol *symbol__new(u64 start, u64 len, const char *name)
+struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name)
 {
 	size_t namelen = strlen(name) + 1;
-	struct symbol *self = calloc(1, (symbol_conf.priv_size +
-					 sizeof(*self) + namelen));
-	if (self == NULL)
+	struct symbol *sym = calloc(1, (symbol_conf.priv_size +
+					sizeof(*sym) + namelen));
+	if (sym == NULL)
 		return NULL;
 
 	if (symbol_conf.priv_size)
-		self = ((void *)self) + symbol_conf.priv_size;
+		sym = ((void *)sym) + symbol_conf.priv_size;
 
-	self->start   = start;
-	self->end     = len ? start + len - 1 : start;
-	self->namelen = namelen - 1;
+	sym->start   = start;
+	sym->end     = len ? start + len - 1 : start;
+	sym->binding = binding;
+	sym->namelen = namelen - 1;
 
-	pr_debug4("%s: %s %#Lx-%#Lx\n", __func__, name, start, self->end);
-
-	memcpy(self->name, name, namelen);
-
-	return self;
-}
+	pr_debug4("%s: %s %#" PRIx64 "-%#" PRIx64 "\n",
+		  __func__, name, start, sym->end);
+	memcpy(sym->name, name, namelen);
 
-void symbol__delete(struct symbol *self)
-{
-	free(((void *)self) - symbol_conf.priv_size);
+	return sym;
 }
 
-static size_t symbol__fprintf(struct symbol *self, FILE *fp)
+void symbol__delete(struct symbol *sym)
 {
-	return fprintf(fp, " %llx-%llx %s\n",
-		       self->start, self->end, self->name);
+	free(((void *)sym) - symbol_conf.priv_size);
 }
 
-void dso__set_long_name(struct dso *self, char *name)
+size_t symbol__fprintf(struct symbol *sym, FILE *fp)
 {
-	if (name == NULL)
-		return;
-	self->long_name = name;
-	self->long_name_len = strlen(name);
+	return fprintf(fp, " %" PRIx64 "-%" PRIx64 " %c %s\n",
+		       sym->start, sym->end,
+		       sym->binding == STB_GLOBAL ? 'g' :
+		       sym->binding == STB_LOCAL  ? 'l' : 'w',
+		       sym->name);
 }
 
-static void dso__set_short_name(struct dso *self, const char *name)
+size_t symbol__fprintf_symname_offs(const struct symbol *sym,
+				    const struct addr_location *al, FILE *fp)
 {
-	if (name == NULL)
-		return;
-	self->short_name = name;
-	self->short_name_len = strlen(name);
-}
+	unsigned long offset;
+	size_t length;
 
-static void dso__set_basename(struct dso *self)
-{
-	dso__set_short_name(self, basename(self->long_name));
+	if (sym && sym->name) {
+		length = fprintf(fp, "%s", sym->name);
+		if (al) {
+			if (al->addr < sym->end)
+				offset = al->addr - sym->start;
+			else
+				offset = al->addr - al->map->start - sym->start;
+			length += fprintf(fp, "+0x%lx", offset);
+		}
+		return length;
+	} else
+		return fprintf(fp, "[unknown]");
 }
 
-struct dso *dso__new(const char *name)
+size_t symbol__fprintf_symname(const struct symbol *sym, FILE *fp)
 {
-	struct dso *self = calloc(1, sizeof(*self) + strlen(name) + 1);
-
-	if (self != NULL) {
-		int i;
-		strcpy(self->name, name);
-		dso__set_long_name(self, self->name);
-		dso__set_short_name(self, self->name);
-		for (i = 0; i < MAP__NR_TYPES; ++i)
-			self->symbols[i] = self->symbol_names[i] = RB_ROOT;
-		self->slen_calculated = 0;
-		self->origin = DSO__ORIG_NOT_FOUND;
-		self->loaded = 0;
-		self->sorted_by_name = 0;
-		self->has_build_id = 0;
-		self->kernel = DSO_TYPE_USER;
-		INIT_LIST_HEAD(&self->node);
-	}
-
-	return self;
+	return symbol__fprintf_symname_offs(sym, NULL, fp);
 }
 
-static void symbols__delete(struct rb_root *self)
+void symbols__delete(struct rb_root *symbols)
 {
 	struct symbol *pos;
-	struct rb_node *next = rb_first(self);
+	struct rb_node *next = rb_first(symbols);
 
 	while (next) {
 		pos = rb_entry(next, struct symbol, rb_node);
 		next = rb_next(&pos->rb_node);
-		rb_erase(&pos->rb_node, self);
+		rb_erase(&pos->rb_node, symbols);
 		symbol__delete(pos);
 	}
 }
 
-void dso__delete(struct dso *self)
-{
-	int i;
-	for (i = 0; i < MAP__NR_TYPES; ++i)
-		symbols__delete(&self->symbols[i]);
-	if (self->long_name != self->name)
-		free(self->long_name);
-	free(self);
-}
-
-void dso__set_build_id(struct dso *self, void *build_id)
-{
-	memcpy(self->build_id, build_id, sizeof(self->build_id));
-	self->has_build_id = 1;
-}
-
-static void symbols__insert(struct rb_root *self, struct symbol *sym)
+void symbols__insert(struct rb_root *symbols, struct symbol *sym)
 {
-	struct rb_node **p = &self->rb_node;
+	struct rb_node **p = &symbols->rb_node;
 	struct rb_node *parent = NULL;
 	const u64 ip = sym->start;
 	struct symbol *s;
@@ -242,17 +305,17 @@ static void symbols__insert(struct rb_root *self, struct symbol *sym)
 			p = &(*p)->rb_right;
 	}
 	rb_link_node(&sym->rb_node, parent, p);
-	rb_insert_color(&sym->rb_node, self);
+	rb_insert_color(&sym->rb_node, symbols);
 }
 
-static struct symbol *symbols__find(struct rb_root *self, u64 ip)
+static struct symbol *symbols__find(struct rb_root *symbols, u64 ip)
 {
 	struct rb_node *n;
 
-	if (self == NULL)
+	if (symbols == NULL)
 		return NULL;
 
-	n = self->rb_node;
+	n = symbols->rb_node;
 
 	while (n) {
 		struct symbol *s = rb_entry(n, struct symbol, rb_node);
@@ -268,16 +331,28 @@ static struct symbol *symbols__find(struct rb_root *self, u64 ip)
 	return NULL;
 }
 
+static struct symbol *symbols__first(struct rb_root *symbols)
+{
+	struct rb_node *n = rb_first(symbols);
+
+	if (n)
+		return rb_entry(n, struct symbol, rb_node);
+
+	return NULL;
+}
+
 struct symbol_name_rb_node {
 	struct rb_node	rb_node;
 	struct symbol	sym;
 };
 
-static void symbols__insert_by_name(struct rb_root *self, struct symbol *sym)
+static void symbols__insert_by_name(struct rb_root *symbols, struct symbol *sym)
 {
-	struct rb_node **p = &self->rb_node;
+	struct rb_node **p = &symbols->rb_node;
 	struct rb_node *parent = NULL;
-	struct symbol_name_rb_node *symn = ((void *)sym) - sizeof(*parent), *s;
+	struct symbol_name_rb_node *symn, *s;
+
+	symn = container_of(sym, struct symbol_name_rb_node, sym);
 
 	while (*p != NULL) {
 		parent = *p;
@@ -288,27 +363,29 @@ static void symbols__insert_by_name(struct rb_root *self, struct symbol *sym)
 			p = &(*p)->rb_right;
 	}
 	rb_link_node(&symn->rb_node, parent, p);
-	rb_insert_color(&symn->rb_node, self);
+	rb_insert_color(&symn->rb_node, symbols);
 }
 
-static void symbols__sort_by_name(struct rb_root *self, struct rb_root *source)
+static void symbols__sort_by_name(struct rb_root *symbols,
+				  struct rb_root *source)
 {
 	struct rb_node *nd;
 
 	for (nd = rb_first(source); nd; nd = rb_next(nd)) {
 		struct symbol *pos = rb_entry(nd, struct symbol, rb_node);
-		symbols__insert_by_name(self, pos);
+		symbols__insert_by_name(symbols, pos);
 	}
 }
 
-static struct symbol *symbols__find_by_name(struct rb_root *self, const char *name)
+static struct symbol *symbols__find_by_name(struct rb_root *symbols,
+					    const char *name)
 {
 	struct rb_node *n;
 
-	if (self == NULL)
+	if (symbols == NULL)
 		return NULL;
 
-	n = self->rb_node;
+	n = symbols->rb_node;
 
 	while (n) {
 		struct symbol_name_rb_node *s;
@@ -328,111 +405,101 @@ static struct symbol *symbols__find_by_name(struct rb_root *self, const char *na
 	return NULL;
 }
 
-struct symbol *dso__find_symbol(struct dso *self,
+struct symbol *dso__find_symbol(struct dso *dso,
 				enum map_type type, u64 addr)
 {
-	return symbols__find(&self->symbols[type], addr);
+	return symbols__find(&dso->symbols[type], addr);
 }
 
-struct symbol *dso__find_symbol_by_name(struct dso *self, enum map_type type,
-					const char *name)
+static struct symbol *dso__first_symbol(struct dso *dso, enum map_type type)
 {
-	return symbols__find_by_name(&self->symbol_names[type], name);
+	return symbols__first(&dso->symbols[type]);
 }
 
-void dso__sort_by_name(struct dso *self, enum map_type type)
-{
-	dso__set_sorted_by_name(self, type);
-	return symbols__sort_by_name(&self->symbol_names[type],
-				     &self->symbols[type]);
-}
-
-int build_id__sprintf(const u8 *self, int len, char *bf)
+struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type,
+					const char *name)
 {
-	char *bid = bf;
-	const u8 *raw = self;
-	int i;
-
-	for (i = 0; i < len; ++i) {
-		sprintf(bid, "%02x", *raw);
-		++raw;
-		bid += 2;
-	}
-
-	return raw - self;
+	return symbols__find_by_name(&dso->symbol_names[type], name);
 }
 
-size_t dso__fprintf_buildid(struct dso *self, FILE *fp)
+void dso__sort_by_name(struct dso *dso, enum map_type type)
 {
-	char sbuild_id[BUILD_ID_SIZE * 2 + 1];
-
-	build_id__sprintf(self->build_id, sizeof(self->build_id), sbuild_id);
-	return fprintf(fp, "%s", sbuild_id);
+	dso__set_sorted_by_name(dso, type);
+	return symbols__sort_by_name(&dso->symbol_names[type],
+				     &dso->symbols[type]);
 }
 
-size_t dso__fprintf(struct dso *self, enum map_type type, FILE *fp)
+size_t dso__fprintf_symbols_by_name(struct dso *dso,
+				    enum map_type type, FILE *fp)
 {
+	size_t ret = 0;
 	struct rb_node *nd;
-	size_t ret = fprintf(fp, "dso: %s (", self->short_name);
-
-	if (self->short_name != self->long_name)
-		ret += fprintf(fp, "%s, ", self->long_name);
-	ret += fprintf(fp, "%s, %sloaded, ", map_type__name[type],
-		       self->loaded ? "" : "NOT ");
-	ret += dso__fprintf_buildid(self, fp);
-	ret += fprintf(fp, ")\n");
-	for (nd = rb_first(&self->symbols[type]); nd; nd = rb_next(nd)) {
-		struct symbol *pos = rb_entry(nd, struct symbol, rb_node);
-		ret += symbol__fprintf(pos, fp);
+	struct symbol_name_rb_node *pos;
+
+	for (nd = rb_first(&dso->symbol_names[type]); nd; nd = rb_next(nd)) {
+		pos = rb_entry(nd, struct symbol_name_rb_node, rb_node);
+		fprintf(fp, "%s\n", pos->sym.name);
 	}
 
 	return ret;
 }
 
-int kallsyms__parse(const char *filename, void *arg,
-		    int (*process_symbol)(void *arg, const char *name,
-						     char type, u64 start))
+int modules__parse(const char *filename, void *arg,
+		   int (*process_module)(void *arg, const char *name,
+					 u64 start))
 {
 	char *line = NULL;
 	size_t n;
+	FILE *file;
 	int err = 0;
-	FILE *file = fopen(filename, "r");
 
+	file = fopen(filename, "r");
 	if (file == NULL)
-		goto out_failure;
+		return -1;
 
-	while (!feof(file)) {
+	while (1) {
+		char name[PATH_MAX];
 		u64 start;
-		int line_len, len;
-		char symbol_type;
-		char *symbol_name;
+		char *sep;
+		ssize_t line_len;
 
 		line_len = getline(&line, &n, file);
-		if (line_len < 0 || !line)
-			break;
+		if (line_len < 0) {
+			if (feof(file))
+				break;
+			err = -1;
+			goto out;
+		}
+
+		if (!line) {
+			err = -1;
+			goto out;
+		}
 
 		line[--line_len] = '\0'; /* \n */
 
-		len = hex2u64(line, &start);
+		sep = strrchr(line, 'x');
+		if (sep == NULL)
+			continue;
 
-		len++;
-		if (len + 2 >= line_len)
+		hex2u64(sep + 1, &start);
+
+		sep = strchr(line, ' ');
+		if (sep == NULL)
 			continue;
 
-		symbol_type = toupper(line[len]);
-		symbol_name = line + len + 2;
+		*sep = '\0';
 
-		err = process_symbol(arg, symbol_name, symbol_type, start);
+		scnprintf(name, sizeof(name), "[%s]", line);
+
+		err = process_module(arg, name, start);
 		if (err)
 			break;
 	}
-
+out:
 	free(line);
 	fclose(file);
 	return err;
-
-out_failure:
-	return -1;
 }
 
 struct process_kallsyms_args {
@@ -440,6 +507,36 @@ struct process_kallsyms_args {
 	struct dso *dso;
 };
 
+bool symbol__is_idle(struct symbol *sym)
+{
+	const char * const idle_symbols[] = {
+		"cpu_idle",
+		"intel_idle",
+		"default_idle",
+		"native_safe_halt",
+		"enter_idle",
+		"exit_idle",
+		"mwait_idle",
+		"mwait_idle_with_hints",
+		"poll_idle",
+		"ppc64_runlatch_off",
+		"pseries_dedicated_idle_sleep",
+		NULL
+	};
+
+	int i;
+
+	if (!sym)
+		return false;
+
+	for (i = 0; idle_symbols[i]; i++) {
+		if (!strcmp(idle_symbols[i], sym->name))
+			return true;
+	}
+
+	return false;
+}
+
 static int map__process_kallsym_symbol(void *arg, const char *name,
 				       char type, u64 start)
 {
@@ -451,10 +548,11 @@ static int map__process_kallsym_symbol(void *arg, const char *name,
 		return 0;
 
 	/*
-	 * Will fix up the end later, when we have all symbols sorted.
+	 * module symbols are not sorted so we add all
+	 * symbols, setting length to 0, and rely on
+	 * symbols__fixup_end() to fix it up.
 	 */
-	sym = symbol__new(start, 0, name);
-
+	sym = symbol__new(start, 0, kallsyms2elf_type(type), name);
 	if (sym == NULL)
 		return -ENOMEM;
 	/*
@@ -471,27 +569,74 @@ static int map__process_kallsym_symbol(void *arg, const char *name,
  * so that we can in the next step set the symbol ->end address and then
  * call kernel_maps__split_kallsyms.
  */
-static int dso__load_all_kallsyms(struct dso *self, const char *filename,
+static int dso__load_all_kallsyms(struct dso *dso, const char *filename,
 				  struct map *map)
 {
-	struct process_kallsyms_args args = { .map = map, .dso = self, };
+	struct process_kallsyms_args args = { .map = map, .dso = dso, };
 	return kallsyms__parse(filename, &args, map__process_kallsym_symbol);
 }
 
+static int dso__split_kallsyms_for_kcore(struct dso *dso, struct map *map,
+					 symbol_filter_t filter)
+{
+	struct map_groups *kmaps = map__kmap(map)->kmaps;
+	struct map *curr_map;
+	struct symbol *pos;
+	int count = 0, moved = 0;
+	struct rb_root *root = &dso->symbols[map->type];
+	struct rb_node *next = rb_first(root);
+
+	while (next) {
+		char *module;
+
+		pos = rb_entry(next, struct symbol, rb_node);
+		next = rb_next(&pos->rb_node);
+
+		module = strchr(pos->name, '\t');
+		if (module)
+			*module = '\0';
+
+		curr_map = map_groups__find(kmaps, map->type, pos->start);
+
+		if (!curr_map || (filter && filter(curr_map, pos))) {
+			rb_erase(&pos->rb_node, root);
+			symbol__delete(pos);
+		} else {
+			pos->start -= curr_map->start - curr_map->pgoff;
+			if (pos->end)
+				pos->end -= curr_map->start - curr_map->pgoff;
+			if (curr_map != map) {
+				rb_erase(&pos->rb_node, root);
+				symbols__insert(
+					&curr_map->dso->symbols[curr_map->type],
+					pos);
+				++moved;
+			} else {
+				++count;
+			}
+		}
+	}
+
+	/* Symbols have been adjusted */
+	dso->adjust_symbols = 1;
+
+	return count + moved;
+}
+
 /*
  * Split the symbols into maps, making sure there are no overlaps, i.e. the
  * kernel range is broken in several maps, named [kernel].N, as we don't have
  * the original ELF section names vmlinux have.
  */
-static int dso__split_kallsyms(struct dso *self, struct map *map,
+static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta,
 			       symbol_filter_t filter)
 {
 	struct map_groups *kmaps = map__kmap(map)->kmaps;
 	struct machine *machine = kmaps->machine;
 	struct map *curr_map = map;
 	struct symbol *pos;
-	int count = 0;
-	struct rb_root *root = &self->symbols[map->type];
+	int count = 0, moved = 0;	
+	struct rb_root *root = &dso->symbols[map->type];
 	struct rb_node *next = rb_first(root);
 	int kernel_range = 0;
 
@@ -510,7 +655,7 @@ static int dso__split_kallsyms(struct dso *self, struct map *map,
 
 			if (strcmp(curr_map->dso->short_name, module)) {
 				if (curr_map != map &&
-				    self->kernel == DSO_TYPE_GUEST_KERNEL &&
+				    dso->kernel == DSO_TYPE_GUEST_KERNEL &&
 				    machine__is_default_guest(machine)) {
 					/*
 					 * We assume all symbols of a module are
@@ -546,9 +691,20 @@ static int dso__split_kallsyms(struct dso *self, struct map *map,
 			pos->end   = curr_map->map_ip(curr_map, pos->end);
 		} else if (curr_map != map) {
 			char dso_name[PATH_MAX];
-			struct dso *dso;
+			struct dso *ndso;
 
-			if (self->kernel == DSO_TYPE_GUEST_KERNEL)
+			if (delta) {
+				/* Kernel was relocated at boot time */
+				pos->start -= delta;
+				pos->end -= delta;
+			}
+
+			if (count == 0) {
+				curr_map = map;
+				goto filter_symbol;
+			}
+
+			if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
 				snprintf(dso_name, sizeof(dso_name),
 					"[guest.kernel].%d",
 					kernel_range++);
@@ -557,23 +713,27 @@ static int dso__split_kallsyms(struct dso *self, struct map *map,
 					"[kernel].%d",
 					kernel_range++);
 
-			dso = dso__new(dso_name);
-			if (dso == NULL)
+			ndso = dso__new(dso_name);
+			if (ndso == NULL)
 				return -1;
 
-			dso->kernel = self->kernel;
+			ndso->kernel = dso->kernel;
 
-			curr_map = map__new2(pos->start, dso, map->type);
+			curr_map = map__new2(pos->start, ndso, map->type);
 			if (curr_map == NULL) {
-				dso__delete(dso);
+				dso__delete(ndso);
 				return -1;
 			}
 
 			curr_map->map_ip = curr_map->unmap_ip = identity__map_ip;
 			map_groups__insert(kmaps, curr_map);
 			++kernel_range;
+		} else if (delta) {
+			/* Kernel was relocated at boot time */
+			pos->start -= delta;
+			pos->end -= delta;
 		}
-
+filter_symbol:
 		if (filter && filter(curr_map, pos)) {
 discard_symbol:		rb_erase(&pos->rb_node, root);
 			symbol__delete(pos);
@@ -581,833 +741,695 @@ discard_symbol:		rb_erase(&pos->rb_node, root);
 			if (curr_map != map) {
 				rb_erase(&pos->rb_node, root);
 				symbols__insert(&curr_map->dso->symbols[curr_map->type], pos);
-			}
-			count++;
+				++moved;
+			} else
+				++count;
 		}
 	}
 
 	if (curr_map != map &&
-	    self->kernel == DSO_TYPE_GUEST_KERNEL &&
+	    dso->kernel == DSO_TYPE_GUEST_KERNEL &&
 	    machine__is_default_guest(kmaps->machine)) {
 		dso__set_loaded(curr_map->dso, curr_map->type);
 	}
 
-	return count;
+	return count + moved;
 }
 
-int dso__load_kallsyms(struct dso *self, const char *filename,
-		       struct map *map, symbol_filter_t filter)
+bool symbol__restricted_filename(const char *filename,
+				 const char *restricted_filename)
 {
-	if (dso__load_all_kallsyms(self, filename, map) < 0)
-		return -1;
+	bool restricted = false;
 
-	symbols__fixup_end(&self->symbols[map->type]);
-	if (self->kernel == DSO_TYPE_GUEST_KERNEL)
-		self->origin = DSO__ORIG_GUEST_KERNEL;
-	else
-		self->origin = DSO__ORIG_KERNEL;
+	if (symbol_conf.kptr_restrict) {
+		char *r = realpath(filename, NULL);
+
+		if (r != NULL) {
+			restricted = strcmp(r, restricted_filename) == 0;
+			free(r);
+			return restricted;
+		}
+	}
 
-	return dso__split_kallsyms(self, map, filter);
+	return restricted;
 }
 
-static int dso__load_perf_map(struct dso *self, struct map *map,
-			      symbol_filter_t filter)
-{
-	char *line = NULL;
-	size_t n;
-	FILE *file;
-	int nr_syms = 0;
+struct module_info {
+	struct rb_node rb_node;
+	char *name;
+	u64 start;
+};
 
-	file = fopen(self->long_name, "r");
-	if (file == NULL)
-		goto out_failure;
+static void add_module(struct module_info *mi, struct rb_root *modules)
+{
+	struct rb_node **p = &modules->rb_node;
+	struct rb_node *parent = NULL;
+	struct module_info *m;
 
-	while (!feof(file)) {
-		u64 start, size;
-		struct symbol *sym;
-		int line_len, len;
+	while (*p != NULL) {
+		parent = *p;
+		m = rb_entry(parent, struct module_info, rb_node);
+		if (strcmp(mi->name, m->name) < 0)
+			p = &(*p)->rb_left;
+		else
+			p = &(*p)->rb_right;
+	}
+	rb_link_node(&mi->rb_node, parent, p);
+	rb_insert_color(&mi->rb_node, modules);
+}
 
-		line_len = getline(&line, &n, file);
-		if (line_len < 0)
-			break;
+static void delete_modules(struct rb_root *modules)
+{
+	struct module_info *mi;
+	struct rb_node *next = rb_first(modules);
 
-		if (!line)
-			goto out_failure;
+	while (next) {
+		mi = rb_entry(next, struct module_info, rb_node);
+		next = rb_next(&mi->rb_node);
+		rb_erase(&mi->rb_node, modules);
+		zfree(&mi->name);
+		free(mi);
+	}
+}
 
-		line[--line_len] = '\0'; /* \n */
+static struct module_info *find_module(const char *name,
+				       struct rb_root *modules)
+{
+	struct rb_node *n = modules->rb_node;
 
-		len = hex2u64(line, &start);
+	while (n) {
+		struct module_info *m;
+		int cmp;
 
-		len++;
-		if (len + 2 >= line_len)
-			continue;
+		m = rb_entry(n, struct module_info, rb_node);
+		cmp = strcmp(name, m->name);
+		if (cmp < 0)
+			n = n->rb_left;
+		else if (cmp > 0)
+			n = n->rb_right;
+		else
+			return m;
+	}
 
-		len += hex2u64(line + len, &size);
+	return NULL;
+}
 
-		len++;
-		if (len + 2 >= line_len)
-			continue;
+static int __read_proc_modules(void *arg, const char *name, u64 start)
+{
+	struct rb_root *modules = arg;
+	struct module_info *mi;
 
-		sym = symbol__new(start, size, line + len);
+	mi = zalloc(sizeof(struct module_info));
+	if (!mi)
+		return -ENOMEM;
 
-		if (sym == NULL)
-			goto out_delete_line;
+	mi->name = strdup(name);
+	mi->start = start;
 
-		if (filter && filter(map, sym))
-			symbol__delete(sym);
-		else {
-			symbols__insert(&self->symbols[map->type], sym);
-			nr_syms++;
-		}
+	if (!mi->name) {
+		free(mi);
+		return -ENOMEM;
 	}
 
-	free(line);
-	fclose(file);
-
-	return nr_syms;
-
-out_delete_line:
-	free(line);
-out_failure:
-	return -1;
-}
-
-/**
- * elf_symtab__for_each_symbol - iterate thru all the symbols
- *
- * @self: struct elf_symtab instance to iterate
- * @idx: uint32_t idx
- * @sym: GElf_Sym iterator
- */
-#define elf_symtab__for_each_symbol(syms, nr_syms, idx, sym) \
-	for (idx = 0, gelf_getsym(syms, idx, &sym);\
-	     idx < nr_syms; \
-	     idx++, gelf_getsym(syms, idx, &sym))
-
-static inline uint8_t elf_sym__type(const GElf_Sym *sym)
-{
-	return GELF_ST_TYPE(sym->st_info);
-}
+	add_module(mi, modules);
 
-static inline int elf_sym__is_function(const GElf_Sym *sym)
-{
-	return elf_sym__type(sym) == STT_FUNC &&
-	       sym->st_name != 0 &&
-	       sym->st_shndx != SHN_UNDEF;
+	return 0;
 }
 
-static inline bool elf_sym__is_object(const GElf_Sym *sym)
+static int read_proc_modules(const char *filename, struct rb_root *modules)
 {
-	return elf_sym__type(sym) == STT_OBJECT &&
-		sym->st_name != 0 &&
-		sym->st_shndx != SHN_UNDEF;
-}
+	if (symbol__restricted_filename(filename, "/proc/modules"))
+		return -1;
 
-static inline int elf_sym__is_label(const GElf_Sym *sym)
-{
-	return elf_sym__type(sym) == STT_NOTYPE &&
-		sym->st_name != 0 &&
-		sym->st_shndx != SHN_UNDEF &&
-		sym->st_shndx != SHN_ABS;
-}
+	if (modules__parse(filename, modules, __read_proc_modules)) {
+		delete_modules(modules);
+		return -1;
+	}
 
-static inline const char *elf_sec__name(const GElf_Shdr *shdr,
-					const Elf_Data *secstrs)
-{
-	return secstrs->d_buf + shdr->sh_name;
+	return 0;
 }
 
-static inline int elf_sec__is_text(const GElf_Shdr *shdr,
-					const Elf_Data *secstrs)
+int compare_proc_modules(const char *from, const char *to)
 {
-	return strstr(elf_sec__name(shdr, secstrs), "text") != NULL;
-}
+	struct rb_root from_modules = RB_ROOT;
+	struct rb_root to_modules = RB_ROOT;
+	struct rb_node *from_node, *to_node;
+	struct module_info *from_m, *to_m;
+	int ret = -1;
 
-static inline bool elf_sec__is_data(const GElf_Shdr *shdr,
-				    const Elf_Data *secstrs)
-{
-	return strstr(elf_sec__name(shdr, secstrs), "data") != NULL;
-}
+	if (read_proc_modules(from, &from_modules))
+		return -1;
 
-static inline const char *elf_sym__name(const GElf_Sym *sym,
-					const Elf_Data *symstrs)
-{
-	return symstrs->d_buf + sym->st_name;
-}
+	if (read_proc_modules(to, &to_modules))
+		goto out_delete_from;
 
-static Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
-				    GElf_Shdr *shp, const char *name,
-				    size_t *idx)
-{
-	Elf_Scn *sec = NULL;
-	size_t cnt = 1;
+	from_node = rb_first(&from_modules);
+	to_node = rb_first(&to_modules);
+	while (from_node) {
+		if (!to_node)
+			break;
 
-	while ((sec = elf_nextscn(elf, sec)) != NULL) {
-		char *str;
+		from_m = rb_entry(from_node, struct module_info, rb_node);
+		to_m = rb_entry(to_node, struct module_info, rb_node);
 
-		gelf_getshdr(sec, shp);
-		str = elf_strptr(elf, ep->e_shstrndx, shp->sh_name);
-		if (!strcmp(name, str)) {
-			if (idx)
-				*idx = cnt;
+		if (from_m->start != to_m->start ||
+		    strcmp(from_m->name, to_m->name))
 			break;
-		}
-		++cnt;
+
+		from_node = rb_next(from_node);
+		to_node = rb_next(to_node);
 	}
 
-	return sec;
-}
+	if (!from_node && !to_node)
+		ret = 0;
 
-#define elf_section__for_each_rel(reldata, pos, pos_mem, idx, nr_entries) \
-	for (idx = 0, pos = gelf_getrel(reldata, 0, &pos_mem); \
-	     idx < nr_entries; \
-	     ++idx, pos = gelf_getrel(reldata, idx, &pos_mem))
+	delete_modules(&to_modules);
+out_delete_from:
+	delete_modules(&from_modules);
 
-#define elf_section__for_each_rela(reldata, pos, pos_mem, idx, nr_entries) \
-	for (idx = 0, pos = gelf_getrela(reldata, 0, &pos_mem); \
-	     idx < nr_entries; \
-	     ++idx, pos = gelf_getrela(reldata, idx, &pos_mem))
+	return ret;
+}
 
-/*
- * We need to check if we have a .dynsym, so that we can handle the
- * .plt, synthesizing its symbols, that aren't on the symtabs (be it
- * .dynsym or .symtab).
- * And always look at the original dso, not at debuginfo packages, that
- * have the PLT data stripped out (shdr_rel_plt.sh_type == SHT_NOBITS).
- */
-static int dso__synthesize_plt_symbols(struct  dso *self, struct map *map,
-				       symbol_filter_t filter)
+static int do_validate_kcore_modules(const char *filename, struct map *map,
+				  struct map_groups *kmaps)
 {
-	uint32_t nr_rel_entries, idx;
-	GElf_Sym sym;
-	u64 plt_offset;
-	GElf_Shdr shdr_plt;
-	struct symbol *f;
-	GElf_Shdr shdr_rel_plt, shdr_dynsym;
-	Elf_Data *reldata, *syms, *symstrs;
-	Elf_Scn *scn_plt_rel, *scn_symstrs, *scn_dynsym;
-	size_t dynsym_idx;
-	GElf_Ehdr ehdr;
-	char sympltname[1024];
-	Elf *elf;
-	int nr = 0, symidx, fd, err = 0;
-
-	fd = open(self->long_name, O_RDONLY);
-	if (fd < 0)
-		goto out;
-
-	elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
-	if (elf == NULL)
-		goto out_close;
-
-	if (gelf_getehdr(elf, &ehdr) == NULL)
-		goto out_elf_end;
-
-	scn_dynsym = elf_section_by_name(elf, &ehdr, &shdr_dynsym,
-					 ".dynsym", &dynsym_idx);
-	if (scn_dynsym == NULL)
-		goto out_elf_end;
-
-	scn_plt_rel = elf_section_by_name(elf, &ehdr, &shdr_rel_plt,
-					  ".rela.plt", NULL);
-	if (scn_plt_rel == NULL) {
-		scn_plt_rel = elf_section_by_name(elf, &ehdr, &shdr_rel_plt,
-						  ".rel.plt", NULL);
-		if (scn_plt_rel == NULL)
-			goto out_elf_end;
-	}
-
-	err = -1;
+	struct rb_root modules = RB_ROOT;
+	struct map *old_map;
+	int err;
 
-	if (shdr_rel_plt.sh_link != dynsym_idx)
-		goto out_elf_end;
+	err = read_proc_modules(filename, &modules);
+	if (err)
+		return err;
 
-	if (elf_section_by_name(elf, &ehdr, &shdr_plt, ".plt", NULL) == NULL)
-		goto out_elf_end;
+	old_map = map_groups__first(kmaps, map->type);
+	while (old_map) {
+		struct map *next = map_groups__next(old_map);
+		struct module_info *mi;
 
-	/*
-	 * Fetch the relocation section to find the idxes to the GOT
-	 * and the symbols in the .dynsym they refer to.
-	 */
-	reldata = elf_getdata(scn_plt_rel, NULL);
-	if (reldata == NULL)
-		goto out_elf_end;
-
-	syms = elf_getdata(scn_dynsym, NULL);
-	if (syms == NULL)
-		goto out_elf_end;
-
-	scn_symstrs = elf_getscn(elf, shdr_dynsym.sh_link);
-	if (scn_symstrs == NULL)
-		goto out_elf_end;
-
-	symstrs = elf_getdata(scn_symstrs, NULL);
-	if (symstrs == NULL)
-		goto out_elf_end;
-
-	nr_rel_entries = shdr_rel_plt.sh_size / shdr_rel_plt.sh_entsize;
-	plt_offset = shdr_plt.sh_offset;
-
-	if (shdr_rel_plt.sh_type == SHT_RELA) {
-		GElf_Rela pos_mem, *pos;
-
-		elf_section__for_each_rela(reldata, pos, pos_mem, idx,
-					   nr_rel_entries) {
-			symidx = GELF_R_SYM(pos->r_info);
-			plt_offset += shdr_plt.sh_entsize;
-			gelf_getsym(syms, symidx, &sym);
-			snprintf(sympltname, sizeof(sympltname),
-				 "%s@plt", elf_sym__name(&sym, symstrs));
-
-			f = symbol__new(plt_offset, shdr_plt.sh_entsize,
-					sympltname);
-			if (!f)
-				goto out_elf_end;
-
-			if (filter && filter(map, f))
-				symbol__delete(f);
-			else {
-				symbols__insert(&self->symbols[map->type], f);
-				++nr;
-			}
-		}
-	} else if (shdr_rel_plt.sh_type == SHT_REL) {
-		GElf_Rel pos_mem, *pos;
-		elf_section__for_each_rel(reldata, pos, pos_mem, idx,
-					  nr_rel_entries) {
-			symidx = GELF_R_SYM(pos->r_info);
-			plt_offset += shdr_plt.sh_entsize;
-			gelf_getsym(syms, symidx, &sym);
-			snprintf(sympltname, sizeof(sympltname),
-				 "%s@plt", elf_sym__name(&sym, symstrs));
-
-			f = symbol__new(plt_offset, shdr_plt.sh_entsize,
-					sympltname);
-			if (!f)
-				goto out_elf_end;
-
-			if (filter && filter(map, f))
-				symbol__delete(f);
-			else {
-				symbols__insert(&self->symbols[map->type], f);
-				++nr;
-			}
+		if (old_map == map || old_map->start == map->start) {
+			/* The kernel map */
+			old_map = next;
+			continue;
 		}
-	}
 
-	err = 0;
-out_elf_end:
-	elf_end(elf);
-out_close:
-	close(fd);
+		/* Module must be in memory at the same address */
+		mi = find_module(old_map->dso->short_name, &modules);
+		if (!mi || mi->start != old_map->start) {
+			err = -EINVAL;
+			goto out;
+		}
 
-	if (err == 0)
-		return nr;
+		old_map = next;
+	}
 out:
-	pr_debug("%s: problems reading %s PLT info.\n",
-		 __func__, self->long_name);
-	return 0;
+	delete_modules(&modules);
+	return err;
 }
 
-static bool elf_sym__is_a(GElf_Sym *self, enum map_type type)
+/*
+ * If kallsyms is referenced by name then we look for filename in the same
+ * directory.
+ */
+static bool filename_from_kallsyms_filename(char *filename,
+					    const char *base_name,
+					    const char *kallsyms_filename)
 {
-	switch (type) {
-	case MAP__FUNCTION:
-		return elf_sym__is_function(self);
-	case MAP__VARIABLE:
-		return elf_sym__is_object(self);
-	default:
-		return false;
-	}
-}
+	char *name;
 
-static bool elf_sec__is_a(GElf_Shdr *self, Elf_Data *secstrs, enum map_type type)
-{
-	switch (type) {
-	case MAP__FUNCTION:
-		return elf_sec__is_text(self, secstrs);
-	case MAP__VARIABLE:
-		return elf_sec__is_data(self, secstrs);
-	default:
+	strcpy(filename, kallsyms_filename);
+	name = strrchr(filename, '/');
+	if (!name)
 		return false;
+
+	name += 1;
+
+	if (!strcmp(name, "kallsyms")) {
+		strcpy(name, base_name);
+		return true;
 	}
+
+	return false;
 }
 
-static int dso__load_sym(struct dso *self, struct map *map, const char *name,
-			 int fd, symbol_filter_t filter, int kmodule)
+static int validate_kcore_modules(const char *kallsyms_filename,
+				  struct map *map)
 {
-	struct kmap *kmap = self->kernel ? map__kmap(map) : NULL;
-	struct map *curr_map = map;
-	struct dso *curr_dso = self;
-	Elf_Data *symstrs, *secstrs;
-	uint32_t nr_syms;
-	int err = -1;
-	uint32_t idx;
-	GElf_Ehdr ehdr;
-	GElf_Shdr shdr;
-	Elf_Data *syms;
-	GElf_Sym sym;
-	Elf_Scn *sec, *sec_strndx;
-	Elf *elf;
-	int nr = 0;
-
-	elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
-	if (elf == NULL) {
-		pr_err("%s: cannot read %s ELF file.\n", __func__, name);
-		goto out_close;
-	}
+	struct map_groups *kmaps = map__kmap(map)->kmaps;
+	char modules_filename[PATH_MAX];
 
-	if (gelf_getehdr(elf, &ehdr) == NULL) {
-		pr_err("%s: cannot get elf header.\n", __func__);
-		goto out_elf_end;
-	}
+	if (!filename_from_kallsyms_filename(modules_filename, "modules",
+					     kallsyms_filename))
+		return -EINVAL;
 
-	sec = elf_section_by_name(elf, &ehdr, &shdr, ".symtab", NULL);
-	if (sec == NULL) {
-		sec = elf_section_by_name(elf, &ehdr, &shdr, ".dynsym", NULL);
-		if (sec == NULL)
-			goto out_elf_end;
-	}
+	if (do_validate_kcore_modules(modules_filename, map, kmaps))
+		return -EINVAL;
 
-	syms = elf_getdata(sec, NULL);
-	if (syms == NULL)
-		goto out_elf_end;
+	return 0;
+}
 
-	sec = elf_getscn(elf, shdr.sh_link);
-	if (sec == NULL)
-		goto out_elf_end;
+static int validate_kcore_addresses(const char *kallsyms_filename,
+				    struct map *map)
+{
+	struct kmap *kmap = map__kmap(map);
 
-	symstrs = elf_getdata(sec, NULL);
-	if (symstrs == NULL)
-		goto out_elf_end;
+	if (kmap->ref_reloc_sym && kmap->ref_reloc_sym->name) {
+		u64 start;
 
-	sec_strndx = elf_getscn(elf, ehdr.e_shstrndx);
-	if (sec_strndx == NULL)
-		goto out_elf_end;
+		start = kallsyms__get_function_start(kallsyms_filename,
+						     kmap->ref_reloc_sym->name);
+		if (start != kmap->ref_reloc_sym->addr)
+			return -EINVAL;
+	}
 
-	secstrs = elf_getdata(sec_strndx, NULL);
-	if (secstrs == NULL)
-		goto out_elf_end;
+	return validate_kcore_modules(kallsyms_filename, map);
+}
 
-	nr_syms = shdr.sh_size / shdr.sh_entsize;
+struct kcore_mapfn_data {
+	struct dso *dso;
+	enum map_type type;
+	struct list_head maps;
+};
 
-	memset(&sym, 0, sizeof(sym));
-	if (self->kernel == DSO_TYPE_USER) {
-		self->adjust_symbols = (ehdr.e_type == ET_EXEC ||
-				elf_section_by_name(elf, &ehdr, &shdr,
-						     ".gnu.prelink_undo",
-						     NULL) != NULL);
-	} else self->adjust_symbols = 0;
+static int kcore_mapfn(u64 start, u64 len, u64 pgoff, void *data)
+{
+	struct kcore_mapfn_data *md = data;
+	struct map *map;
 
-	elf_symtab__for_each_symbol(syms, nr_syms, idx, sym) {
-		struct symbol *f;
-		const char *elf_name = elf_sym__name(&sym, symstrs);
-		char *demangled = NULL;
-		int is_label = elf_sym__is_label(&sym);
-		const char *section_name;
+	map = map__new2(start, md->dso, md->type);
+	if (map == NULL)
+		return -ENOMEM;
 
-		if (kmap && kmap->ref_reloc_sym && kmap->ref_reloc_sym->name &&
-		    strcmp(elf_name, kmap->ref_reloc_sym->name) == 0)
-			kmap->ref_reloc_sym->unrelocated_addr = sym.st_value;
+	map->end = map->start + len;
+	map->pgoff = pgoff;
 
-		if (!is_label && !elf_sym__is_a(&sym, map->type))
-			continue;
+	list_add(&map->node, &md->maps);
 
-		sec = elf_getscn(elf, sym.st_shndx);
-		if (!sec)
-			goto out_elf_end;
+	return 0;
+}
 
-		gelf_getshdr(sec, &shdr);
+static int dso__load_kcore(struct dso *dso, struct map *map,
+			   const char *kallsyms_filename)
+{
+	struct map_groups *kmaps = map__kmap(map)->kmaps;
+	struct machine *machine = kmaps->machine;
+	struct kcore_mapfn_data md;
+	struct map *old_map, *new_map, *replacement_map = NULL;
+	bool is_64_bit;
+	int err, fd;
+	char kcore_filename[PATH_MAX];
+	struct symbol *sym;
 
-		if (is_label && !elf_sec__is_a(&shdr, secstrs, map->type))
-			continue;
+	/* This function requires that the map is the kernel map */
+	if (map != machine->vmlinux_maps[map->type])
+		return -EINVAL;
 
-		section_name = elf_sec__name(&shdr, secstrs);
+	if (!filename_from_kallsyms_filename(kcore_filename, "kcore",
+					     kallsyms_filename))
+		return -EINVAL;
 
-		if (self->kernel != DSO_TYPE_USER || kmodule) {
-			char dso_name[PATH_MAX];
+	/* Modules and kernel must be present at their original addresses */
+	if (validate_kcore_addresses(kallsyms_filename, map))
+		return -EINVAL;
 
-			if (strcmp(section_name,
-				   (curr_dso->short_name +
-				    self->short_name_len)) == 0)
-				goto new_symbol;
+	md.dso = dso;
+	md.type = map->type;
+	INIT_LIST_HEAD(&md.maps);
 
-			if (strcmp(section_name, ".text") == 0) {
-				curr_map = map;
-				curr_dso = self;
-				goto new_symbol;
-			}
+	fd = open(kcore_filename, O_RDONLY);
+	if (fd < 0)
+		return -EINVAL;
 
-			snprintf(dso_name, sizeof(dso_name),
-				 "%s%s", self->short_name, section_name);
+	/* Read new maps into temporary lists */
+	err = file__read_maps(fd, md.type == MAP__FUNCTION, kcore_mapfn, &md,
+			      &is_64_bit);
+	if (err)
+		goto out_err;
 
-			curr_map = map_groups__find_by_name(kmap->kmaps, map->type, dso_name);
-			if (curr_map == NULL) {
-				u64 start = sym.st_value;
+	if (list_empty(&md.maps)) {
+		err = -EINVAL;
+		goto out_err;
+	}
 
-				if (kmodule)
-					start += map->start + shdr.sh_offset;
+	/* Remove old maps */
+	old_map = map_groups__first(kmaps, map->type);
+	while (old_map) {
+		struct map *next = map_groups__next(old_map);
 
-				curr_dso = dso__new(dso_name);
-				if (curr_dso == NULL)
-					goto out_elf_end;
-				curr_dso->kernel = self->kernel;
-				curr_map = map__new2(start, curr_dso,
-						     map->type);
-				if (curr_map == NULL) {
-					dso__delete(curr_dso);
-					goto out_elf_end;
-				}
-				curr_map->map_ip = identity__map_ip;
-				curr_map->unmap_ip = identity__map_ip;
-				curr_dso->origin = self->origin;
-				map_groups__insert(kmap->kmaps, curr_map);
-				dsos__add(&self->node, curr_dso);
-				dso__set_loaded(curr_dso, map->type);
-			} else
-				curr_dso = curr_map->dso;
+		if (old_map != map)
+			map_groups__remove(kmaps, old_map);
+		old_map = next;
+	}
 
-			goto new_symbol;
+	/* Find the kernel map using the first symbol */
+	sym = dso__first_symbol(dso, map->type);
+	list_for_each_entry(new_map, &md.maps, node) {
+		if (sym && sym->start >= new_map->start &&
+		    sym->start < new_map->end) {
+			replacement_map = new_map;
+			break;
 		}
+	}
 
-		if (curr_dso->adjust_symbols) {
-			pr_debug4("%s: adjusting symbol: st_value: %#Lx "
-				  "sh_addr: %#Lx sh_offset: %#Lx\n", __func__,
-				  (u64)sym.st_value, (u64)shdr.sh_addr,
-				  (u64)shdr.sh_offset);
-			sym.st_value -= shdr.sh_addr - shdr.sh_offset;
-		}
-		/*
-		 * We need to figure out if the object was created from C++ sources
-		 * DWARF DW_compile_unit has this, but we don't always have access
-		 * to it...
-		 */
-		demangled = bfd_demangle(NULL, elf_name, DMGL_PARAMS | DMGL_ANSI);
-		if (demangled != NULL)
-			elf_name = demangled;
-new_symbol:
-		f = symbol__new(sym.st_value, sym.st_size, elf_name);
-		free(demangled);
-		if (!f)
-			goto out_elf_end;
-
-		if (filter && filter(curr_map, f))
-			symbol__delete(f);
-		else {
-			symbols__insert(&curr_dso->symbols[curr_map->type], f);
-			nr++;
+	if (!replacement_map)
+		replacement_map = list_entry(md.maps.next, struct map, node);
+
+	/* Add new maps */
+	while (!list_empty(&md.maps)) {
+		new_map = list_entry(md.maps.next, struct map, node);
+		list_del(&new_map->node);
+		if (new_map == replacement_map) {
+			map->start	= new_map->start;
+			map->end	= new_map->end;
+			map->pgoff	= new_map->pgoff;
+			map->map_ip	= new_map->map_ip;
+			map->unmap_ip	= new_map->unmap_ip;
+			map__delete(new_map);
+			/* Ensure maps are correctly ordered */
+			map_groups__remove(kmaps, map);
+			map_groups__insert(kmaps, map);
+		} else {
+			map_groups__insert(kmaps, new_map);
 		}
 	}
 
 	/*
-	 * For misannotated, zeroed, ASM function sizes.
+	 * Set the data type and long name so that kcore can be read via
+	 * dso__data_read_addr().
 	 */
-	if (nr > 0) {
-		symbols__fixup_end(&self->symbols[map->type]);
-		if (kmap) {
-			/*
-			 * We need to fixup this here too because we create new
-			 * maps here, for things like vsyscall sections.
-			 */
-			__map_groups__fixup_end(kmap->kmaps, map->type);
-		}
-	}
-	err = nr;
-out_elf_end:
-	elf_end(elf);
-out_close:
-	return err;
-}
+	if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
+		dso->binary_type = DSO_BINARY_TYPE__GUEST_KCORE;
+	else
+		dso->binary_type = DSO_BINARY_TYPE__KCORE;
+	dso__set_long_name(dso, strdup(kcore_filename), true);
 
-static bool dso__build_id_equal(const struct dso *self, u8 *build_id)
-{
-	return memcmp(self->build_id, build_id, sizeof(self->build_id)) == 0;
-}
+	close(fd);
 
-bool __dsos__read_build_ids(struct list_head *head, bool with_hits)
-{
-	bool have_build_id = false;
-	struct dso *pos;
+	if (map->type == MAP__FUNCTION)
+		pr_debug("Using %s for kernel object code\n", kcore_filename);
+	else
+		pr_debug("Using %s for kernel data\n", kcore_filename);
 
-	list_for_each_entry(pos, head, node) {
-		if (with_hits && !pos->hit)
-			continue;
-		if (pos->has_build_id) {
-			have_build_id = true;
-			continue;
-		}
-		if (filename__read_build_id(pos->long_name, pos->build_id,
-					    sizeof(pos->build_id)) > 0) {
-			have_build_id	  = true;
-			pos->has_build_id = true;
-		}
-	}
+	return 0;
 
-	return have_build_id;
+out_err:
+	while (!list_empty(&md.maps)) {
+		map = list_entry(md.maps.next, struct map, node);
+		list_del(&map->node);
+		map__delete(map);
+	}
+	close(fd);
+	return -EINVAL;
 }
 
 /*
- * Align offset to 4 bytes as needed for note name and descriptor data.
+ * If the kernel is relocated at boot time, kallsyms won't match.  Compute the
+ * delta based on the relocation reference symbol.
  */
-#define NOTE_ALIGN(n) (((n) + 3) & -4U)
+static int kallsyms__delta(struct map *map, const char *filename, u64 *delta)
+{
+	struct kmap *kmap = map__kmap(map);
+	u64 addr;
+
+	if (!kmap->ref_reloc_sym || !kmap->ref_reloc_sym->name)
+		return 0;
+
+	addr = kallsyms__get_function_start(filename,
+					    kmap->ref_reloc_sym->name);
+	if (!addr)
+		return -1;
+
+	*delta = addr - kmap->ref_reloc_sym->addr;
+	return 0;
+}
 
-int filename__read_build_id(const char *filename, void *bf, size_t size)
+int dso__load_kallsyms(struct dso *dso, const char *filename,
+		       struct map *map, symbol_filter_t filter)
 {
-	int fd, err = -1;
-	GElf_Ehdr ehdr;
-	GElf_Shdr shdr;
-	Elf_Data *data;
-	Elf_Scn *sec;
-	Elf_Kind ek;
-	void *ptr;
-	Elf *elf;
-
-	if (size < BUILD_ID_SIZE)
-		goto out;
-
-	fd = open(filename, O_RDONLY);
-	if (fd < 0)
-		goto out;
+	u64 delta = 0;
 
-	elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
-	if (elf == NULL) {
-		pr_debug2("%s: cannot read %s ELF file.\n", __func__, filename);
-		goto out_close;
-	}
+	if (symbol__restricted_filename(filename, "/proc/kallsyms"))
+		return -1;
 
-	ek = elf_kind(elf);
-	if (ek != ELF_K_ELF)
-		goto out_elf_end;
+	if (dso__load_all_kallsyms(dso, filename, map) < 0)
+		return -1;
 
-	if (gelf_getehdr(elf, &ehdr) == NULL) {
-		pr_err("%s: cannot get elf header.\n", __func__);
-		goto out_elf_end;
-	}
+	if (kallsyms__delta(map, filename, &delta))
+		return -1;
 
-	sec = elf_section_by_name(elf, &ehdr, &shdr,
-				  ".note.gnu.build-id", NULL);
-	if (sec == NULL) {
-		sec = elf_section_by_name(elf, &ehdr, &shdr,
-					  ".notes", NULL);
-		if (sec == NULL)
-			goto out_elf_end;
-	}
+	symbols__fixup_duplicate(&dso->symbols[map->type]);
+	symbols__fixup_end(&dso->symbols[map->type]);
 
-	data = elf_getdata(sec, NULL);
-	if (data == NULL)
-		goto out_elf_end;
-
-	ptr = data->d_buf;
-	while (ptr < (data->d_buf + data->d_size)) {
-		GElf_Nhdr *nhdr = ptr;
-		int namesz = NOTE_ALIGN(nhdr->n_namesz),
-		    descsz = NOTE_ALIGN(nhdr->n_descsz);
-		const char *name;
-
-		ptr += sizeof(*nhdr);
-		name = ptr;
-		ptr += namesz;
-		if (nhdr->n_type == NT_GNU_BUILD_ID &&
-		    nhdr->n_namesz == sizeof("GNU")) {
-			if (memcmp(name, "GNU", sizeof("GNU")) == 0) {
-				memcpy(bf, ptr, BUILD_ID_SIZE);
-				err = BUILD_ID_SIZE;
-				break;
-			}
-		}
-		ptr += descsz;
-	}
-out_elf_end:
-	elf_end(elf);
-out_close:
-	close(fd);
-out:
-	return err;
+	if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
+		dso->symtab_type = DSO_BINARY_TYPE__GUEST_KALLSYMS;
+	else
+		dso->symtab_type = DSO_BINARY_TYPE__KALLSYMS;
+
+	if (!dso__load_kcore(dso, map, filename))
+		return dso__split_kallsyms_for_kcore(dso, map, filter);
+	else
+		return dso__split_kallsyms(dso, map, delta, filter);
 }
 
-int sysfs__read_build_id(const char *filename, void *build_id, size_t size)
+static int dso__load_perf_map(struct dso *dso, struct map *map,
+			      symbol_filter_t filter)
 {
-	int fd, err = -1;
-
-	if (size < BUILD_ID_SIZE)
-		goto out;
+	char *line = NULL;
+	size_t n;
+	FILE *file;
+	int nr_syms = 0;
 
-	fd = open(filename, O_RDONLY);
-	if (fd < 0)
-		goto out;
+	file = fopen(dso->long_name, "r");
+	if (file == NULL)
+		goto out_failure;
 
-	while (1) {
-		char bf[BUFSIZ];
-		GElf_Nhdr nhdr;
-		int namesz, descsz;
+	while (!feof(file)) {
+		u64 start, size;
+		struct symbol *sym;
+		int line_len, len;
 
-		if (read(fd, &nhdr, sizeof(nhdr)) != sizeof(nhdr))
+		line_len = getline(&line, &n, file);
+		if (line_len < 0)
 			break;
 
-		namesz = NOTE_ALIGN(nhdr.n_namesz);
-		descsz = NOTE_ALIGN(nhdr.n_descsz);
-		if (nhdr.n_type == NT_GNU_BUILD_ID &&
-		    nhdr.n_namesz == sizeof("GNU")) {
-			if (read(fd, bf, namesz) != namesz)
-				break;
-			if (memcmp(bf, "GNU", sizeof("GNU")) == 0) {
-				if (read(fd, build_id,
-				    BUILD_ID_SIZE) == BUILD_ID_SIZE) {
-					err = 0;
-					break;
-				}
-			} else if (read(fd, bf, descsz) != descsz)
-				break;
-		} else {
-			int n = namesz + descsz;
-			if (read(fd, bf, n) != n)
-				break;
+		if (!line)
+			goto out_failure;
+
+		line[--line_len] = '\0'; /* \n */
+
+		len = hex2u64(line, &start);
+
+		len++;
+		if (len + 2 >= line_len)
+			continue;
+
+		len += hex2u64(line + len, &size);
+
+		len++;
+		if (len + 2 >= line_len)
+			continue;
+
+		sym = symbol__new(start, size, STB_GLOBAL, line + len);
+
+		if (sym == NULL)
+			goto out_delete_line;
+
+		if (filter && filter(map, sym))
+			symbol__delete(sym);
+		else {
+			symbols__insert(&dso->symbols[map->type], sym);
+			nr_syms++;
 		}
 	}
-	close(fd);
-out:
-	return err;
+
+	free(line);
+	fclose(file);
+
+	return nr_syms;
+
+out_delete_line:
+	free(line);
+out_failure:
+	return -1;
 }
 
-char dso__symtab_origin(const struct dso *self)
+static bool dso__is_compatible_symtab_type(struct dso *dso, bool kmod,
+					   enum dso_binary_type type)
 {
-	static const char origin[] = {
-		[DSO__ORIG_KERNEL] =   'k',
-		[DSO__ORIG_JAVA_JIT] = 'j',
-		[DSO__ORIG_BUILD_ID_CACHE] = 'B',
-		[DSO__ORIG_FEDORA] =   'f',
-		[DSO__ORIG_UBUNTU] =   'u',
-		[DSO__ORIG_BUILDID] =  'b',
-		[DSO__ORIG_DSO] =      'd',
-		[DSO__ORIG_KMODULE] =  'K',
-		[DSO__ORIG_GUEST_KERNEL] =  'g',
-		[DSO__ORIG_GUEST_KMODULE] =  'G',
-	};
+	switch (type) {
+	case DSO_BINARY_TYPE__JAVA_JIT:
+	case DSO_BINARY_TYPE__DEBUGLINK:
+	case DSO_BINARY_TYPE__SYSTEM_PATH_DSO:
+	case DSO_BINARY_TYPE__FEDORA_DEBUGINFO:
+	case DSO_BINARY_TYPE__UBUNTU_DEBUGINFO:
+	case DSO_BINARY_TYPE__BUILDID_DEBUGINFO:
+	case DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO:
+		return !kmod && dso->kernel == DSO_TYPE_USER;
+
+	case DSO_BINARY_TYPE__KALLSYMS:
+	case DSO_BINARY_TYPE__VMLINUX:
+	case DSO_BINARY_TYPE__KCORE:
+		return dso->kernel == DSO_TYPE_KERNEL;
+
+	case DSO_BINARY_TYPE__GUEST_KALLSYMS:
+	case DSO_BINARY_TYPE__GUEST_VMLINUX:
+	case DSO_BINARY_TYPE__GUEST_KCORE:
+		return dso->kernel == DSO_TYPE_GUEST_KERNEL;
+
+	case DSO_BINARY_TYPE__GUEST_KMODULE:
+	case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE:
+		/*
+		 * kernel modules know their symtab type - it's set when
+		 * creating a module dso in machine__new_module().
+		 */
+		return kmod && dso->symtab_type == type;
 
-	if (self == NULL || self->origin == DSO__ORIG_NOT_FOUND)
-		return '!';
-	return origin[self->origin];
+	case DSO_BINARY_TYPE__BUILD_ID_CACHE:
+		return true;
+
+	case DSO_BINARY_TYPE__NOT_FOUND:
+	default:
+		return false;
+	}
 }
 
-int dso__load(struct dso *self, struct map *map, symbol_filter_t filter)
+int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 {
-	int size = PATH_MAX;
 	char *name;
-	u8 build_id[BUILD_ID_SIZE];
 	int ret = -1;
-	int fd;
+	u_int i;
 	struct machine *machine;
-	const char *root_dir;
+	char *root_dir = (char *) "";
+	int ss_pos = 0;
+	struct symsrc ss_[2];
+	struct symsrc *syms_ss = NULL, *runtime_ss = NULL;
+	bool kmod;
 
-	dso__set_loaded(self, map->type);
+	dso__set_loaded(dso, map->type);
 
-	if (self->kernel == DSO_TYPE_KERNEL)
-		return dso__load_kernel_sym(self, map, filter);
-	else if (self->kernel == DSO_TYPE_GUEST_KERNEL)
-		return dso__load_guest_kernel_sym(self, map, filter);
+	if (dso->kernel == DSO_TYPE_KERNEL)
+		return dso__load_kernel_sym(dso, map, filter);
+	else if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
+		return dso__load_guest_kernel_sym(dso, map, filter);
 
 	if (map->groups && map->groups->machine)
 		machine = map->groups->machine;
 	else
 		machine = NULL;
 
-	name = malloc(size);
-	if (!name)
-		return -1;
+	dso->adjust_symbols = 0;
+
+	if (strncmp(dso->name, "/tmp/perf-", 10) == 0) {
+		struct stat st;
 
-	self->adjust_symbols = 0;
+		if (lstat(dso->name, &st) < 0)
+			return -1;
+
+		if (st.st_uid && (st.st_uid != geteuid())) {
+			pr_warning("File %s not owned by current user or root, "
+				"ignoring it.\n", dso->name);
+			return -1;
+		}
 
-	if (strncmp(self->name, "/tmp/perf-", 10) == 0) {
-		ret = dso__load_perf_map(self, map, filter);
-		self->origin = ret > 0 ? DSO__ORIG_JAVA_JIT :
-					 DSO__ORIG_NOT_FOUND;
+		ret = dso__load_perf_map(dso, map, filter);
+		dso->symtab_type = ret > 0 ? DSO_BINARY_TYPE__JAVA_JIT :
+					     DSO_BINARY_TYPE__NOT_FOUND;
 		return ret;
 	}
 
-	self->origin = DSO__ORIG_BUILD_ID_CACHE;
-	if (dso__build_id_filename(self, name, size) != NULL)
-		goto open_file;
-more:
-	do {
-		self->origin++;
-		switch (self->origin) {
-		case DSO__ORIG_FEDORA:
-			snprintf(name, size, "/usr/lib/debug%s.debug",
-				 self->long_name);
-			break;
-		case DSO__ORIG_UBUNTU:
-			snprintf(name, size, "/usr/lib/debug%s",
-				 self->long_name);
-			break;
-		case DSO__ORIG_BUILDID:
-			if (filename__read_build_id(self->long_name, build_id,
-						    sizeof(build_id))) {
-				char build_id_hex[BUILD_ID_SIZE * 2 + 1];
-				build_id__sprintf(build_id, sizeof(build_id),
-						  build_id_hex);
-				snprintf(name, size,
-					 "/usr/lib/debug/.build-id/%.2s/%s.debug",
-					build_id_hex, build_id_hex + 2);
-				if (self->has_build_id)
-					goto compare_build_id;
-				break;
-			}
-			self->origin++;
-			/* Fall thru */
-		case DSO__ORIG_DSO:
-			snprintf(name, size, "%s", self->long_name);
-			break;
-		case DSO__ORIG_GUEST_KMODULE:
-			if (map->groups && map->groups->machine)
-				root_dir = map->groups->machine->root_dir;
-			else
-				root_dir = "";
-			snprintf(name, size, "%s%s", root_dir, self->long_name);
-			break;
+	if (machine)
+		root_dir = machine->root_dir;
 
-		default:
-			goto out;
+	name = malloc(PATH_MAX);
+	if (!name)
+		return -1;
+
+	kmod = dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE ||
+		dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE;
+
+	/*
+	 * Iterate over candidate debug images.
+	 * Keep track of "interesting" ones (those which have a symtab, dynsym,
+	 * and/or opd section) for processing.
+	 */
+	for (i = 0; i < DSO_BINARY_TYPE__SYMTAB_CNT; i++) {
+		struct symsrc *ss = &ss_[ss_pos];
+		bool next_slot = false;
+
+		enum dso_binary_type symtab_type = binary_type_symtab[i];
+
+		if (!dso__is_compatible_symtab_type(dso, kmod, symtab_type))
+			continue;
+
+		if (dso__read_binary_type_filename(dso, symtab_type,
+						   root_dir, name, PATH_MAX))
+			continue;
+
+		/* Name is now the name of the next image to try */
+		if (symsrc__init(ss, dso, name, symtab_type) < 0)
+			continue;
+
+		if (!syms_ss && symsrc__has_symtab(ss)) {
+			syms_ss = ss;
+			next_slot = true;
+			if (!dso->symsrc_filename)
+				dso->symsrc_filename = strdup(name);
 		}
 
-		if (self->has_build_id) {
-			if (filename__read_build_id(name, build_id,
-						    sizeof(build_id)) < 0)
-				goto more;
-compare_build_id:
-			if (!dso__build_id_equal(self, build_id))
-				goto more;
+		if (!runtime_ss && symsrc__possibly_runtime(ss)) {
+			runtime_ss = ss;
+			next_slot = true;
 		}
-open_file:
-		fd = open(name, O_RDONLY);
-	} while (fd < 0);
 
-	ret = dso__load_sym(self, map, name, fd, filter, 0);
-	close(fd);
+		if (next_slot) {
+			ss_pos++;
 
-	/*
-	 * Some people seem to have debuginfo files _WITHOUT_ debug info!?!?
-	 */
-	if (!ret)
-		goto more;
+			if (syms_ss && runtime_ss)
+				break;
+		} else {
+			symsrc__destroy(ss);
+		}
+
+	}
+
+	if (!runtime_ss && !syms_ss)
+		goto out_free;
+
+	if (runtime_ss && !syms_ss) {
+		syms_ss = runtime_ss;
+	}
+
+	/* We'll have to hope for the best */
+	if (!runtime_ss && syms_ss)
+		runtime_ss = syms_ss;
+
+	if (syms_ss)
+		ret = dso__load_sym(dso, map, syms_ss, runtime_ss, filter, kmod);
+	else
+		ret = -1;
 
 	if (ret > 0) {
-		int nr_plt = dso__synthesize_plt_symbols(self, map, filter);
+		int nr_plt;
+
+		nr_plt = dso__synthesize_plt_symbols(dso, runtime_ss, map, filter);
 		if (nr_plt > 0)
 			ret += nr_plt;
 	}
-out:
+
+	for (; ss_pos > 0; ss_pos--)
+		symsrc__destroy(&ss_[ss_pos - 1]);
+out_free:
 	free(name);
-	if (ret < 0 && strstr(self->name, " (deleted)") != NULL)
+	if (ret < 0 && strstr(dso->name, " (deleted)") != NULL)
 		return 0;
 	return ret;
 }
 
-struct map *map_groups__find_by_name(struct map_groups *self,
+struct map *map_groups__find_by_name(struct map_groups *mg,
 				     enum map_type type, const char *name)
 {
 	struct rb_node *nd;
 
-	for (nd = rb_first(&self->maps[type]); nd; nd = rb_next(nd)) {
+	for (nd = rb_first(&mg->maps[type]); nd; nd = rb_next(nd)) {
 		struct map *map = rb_entry(nd, struct map, rb_node);
 
 		if (map->dso && strcmp(map->dso->short_name, name) == 0)
@@ -1417,319 +1439,184 @@ struct map *map_groups__find_by_name(struct map_groups *self,
 	return NULL;
 }
 
-static int dso__kernel_module_get_build_id(struct dso *self,
-				const char *root_dir)
+int dso__load_vmlinux(struct dso *dso, struct map *map,
+		      const char *vmlinux, bool vmlinux_allocated,
+		      symbol_filter_t filter)
 {
-	char filename[PATH_MAX];
-	/*
-	 * kernel module short names are of the form "[module]" and
-	 * we need just "module" here.
-	 */
-	const char *name = self->short_name + 1;
-
-	snprintf(filename, sizeof(filename),
-		 "%s/sys/module/%.*s/notes/.note.gnu.build-id",
-		 root_dir, (int)strlen(name) - 1, name);
-
-	if (sysfs__read_build_id(filename, self->build_id,
-				 sizeof(self->build_id)) == 0)
-		self->has_build_id = true;
+	int err = -1;
+	struct symsrc ss;
+	char symfs_vmlinux[PATH_MAX];
+	enum dso_binary_type symtab_type;
 
-	return 0;
-}
+	if (vmlinux[0] == '/')
+		snprintf(symfs_vmlinux, sizeof(symfs_vmlinux), "%s", vmlinux);
+	else
+		snprintf(symfs_vmlinux, sizeof(symfs_vmlinux), "%s%s",
+			 symbol_conf.symfs, vmlinux);
 
-static int map_groups__set_modules_path_dir(struct map_groups *self,
-				const char *dir_name)
-{
-	struct dirent *dent;
-	DIR *dir = opendir(dir_name);
+	if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
+		symtab_type = DSO_BINARY_TYPE__GUEST_VMLINUX;
+	else
+		symtab_type = DSO_BINARY_TYPE__VMLINUX;
 
-	if (!dir) {
-		pr_debug("%s: cannot open %s dir\n", __func__, dir_name);
+	if (symsrc__init(&ss, dso, symfs_vmlinux, symtab_type))
 		return -1;
-	}
 
-	while ((dent = readdir(dir)) != NULL) {
-		char path[PATH_MAX];
-		struct stat st;
+	err = dso__load_sym(dso, map, &ss, &ss, filter, 0);
+	symsrc__destroy(&ss);
 
-		/*sshfs might return bad dent->d_type, so we have to stat*/
-		sprintf(path, "%s/%s", dir_name, dent->d_name);
-		if (stat(path, &st))
-			continue;
-
-		if (S_ISDIR(st.st_mode)) {
-			if (!strcmp(dent->d_name, ".") ||
-			    !strcmp(dent->d_name, ".."))
-				continue;
-
-			snprintf(path, sizeof(path), "%s/%s",
-				 dir_name, dent->d_name);
-			if (map_groups__set_modules_path_dir(self, path) < 0)
-				goto failure;
-		} else {
-			char *dot = strrchr(dent->d_name, '.'),
-			     dso_name[PATH_MAX];
-			struct map *map;
-			char *long_name;
-
-			if (dot == NULL || strcmp(dot, ".ko"))
-				continue;
-			snprintf(dso_name, sizeof(dso_name), "[%.*s]",
-				 (int)(dot - dent->d_name), dent->d_name);
-
-			strxfrchar(dso_name, '-', '_');
-			map = map_groups__find_by_name(self, MAP__FUNCTION, dso_name);
-			if (map == NULL)
-				continue;
-
-			snprintf(path, sizeof(path), "%s/%s",
-				 dir_name, dent->d_name);
-
-			long_name = strdup(path);
-			if (long_name == NULL)
-				goto failure;
-			dso__set_long_name(map->dso, long_name);
-			dso__kernel_module_get_build_id(map->dso, "");
-		}
+	if (err > 0) {
+		if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
+			dso->binary_type = DSO_BINARY_TYPE__GUEST_VMLINUX;
+		else
+			dso->binary_type = DSO_BINARY_TYPE__VMLINUX;
+		dso__set_long_name(dso, vmlinux, vmlinux_allocated);
+		dso__set_loaded(dso, map->type);
+		pr_debug("Using %s for symbols\n", symfs_vmlinux);
 	}
 
-	return 0;
-failure:
-	closedir(dir);
-	return -1;
+	return err;
 }
 
-static char *get_kernel_version(const char *root_dir)
+int dso__load_vmlinux_path(struct dso *dso, struct map *map,
+			   symbol_filter_t filter)
 {
-	char version[PATH_MAX];
-	FILE *file;
-	char *name, *tmp;
-	const char *prefix = "Linux version ";
-
-	sprintf(version, "%s/proc/version", root_dir);
-	file = fopen(version, "r");
-	if (!file)
-		return NULL;
+	int i, err = 0;
+	char *filename;
 
-	version[0] = '\0';
-	tmp = fgets(version, sizeof(version), file);
-	fclose(file);
+	pr_debug("Looking at the vmlinux_path (%d entries long)\n",
+		 vmlinux_path__nr_entries + 1);
 
-	name = strstr(version, prefix);
-	if (!name)
-		return NULL;
-	name += strlen(prefix);
-	tmp = strchr(name, ' ');
-	if (tmp)
-		*tmp = '\0';
+	filename = dso__build_id_filename(dso, NULL, 0);
+	if (filename != NULL) {
+		err = dso__load_vmlinux(dso, map, filename, true, filter);
+		if (err > 0)
+			goto out;
+		free(filename);
+	}
 
-	return strdup(name);
+	for (i = 0; i < vmlinux_path__nr_entries; ++i) {
+		err = dso__load_vmlinux(dso, map, vmlinux_path[i], false, filter);
+		if (err > 0)
+			break;
+	}
+out:
+	return err;
 }
 
-static int machine__set_modules_path(struct machine *self)
+static int find_matching_kcore(struct map *map, char *dir, size_t dir_sz)
 {
-	char *version;
-	char modules_path[PATH_MAX];
+	char kallsyms_filename[PATH_MAX];
+	struct dirent *dent;
+	int ret = -1;
+	DIR *d;
 
-	version = get_kernel_version(self->root_dir);
-	if (!version)
+	d = opendir(dir);
+	if (!d)
 		return -1;
 
-	snprintf(modules_path, sizeof(modules_path), "%s/lib/modules/%s/kernel",
-		 self->root_dir, version);
-	free(version);
-
-	return map_groups__set_modules_path_dir(&self->kmaps, modules_path);
-}
-
-/*
- * Constructor variant for modules (where we know from /proc/modules where
- * they are loaded) and for vmlinux, where only after we load all the
- * symbols we'll know where it starts and ends.
- */
-static struct map *map__new2(u64 start, struct dso *dso, enum map_type type)
-{
-	struct map *self = calloc(1, (sizeof(*self) +
-				      (dso->kernel ? sizeof(struct kmap) : 0)));
-	if (self != NULL) {
-		/*
-		 * ->end will be filled after we load all the symbols
-		 */
-		map__init(self, type, start, 0, 0, dso);
+	while (1) {
+		dent = readdir(d);
+		if (!dent)
+			break;
+		if (dent->d_type != DT_DIR)
+			continue;
+		scnprintf(kallsyms_filename, sizeof(kallsyms_filename),
+			  "%s/%s/kallsyms", dir, dent->d_name);
+		if (!validate_kcore_addresses(kallsyms_filename, map)) {
+			strlcpy(dir, kallsyms_filename, dir_sz);
+			ret = 0;
+			break;
+		}
 	}
 
-	return self;
-}
-
-struct map *machine__new_module(struct machine *self, u64 start,
-				const char *filename)
-{
-	struct map *map;
-	struct dso *dso = __dsos__findnew(&self->kernel_dsos, filename);
-
-	if (dso == NULL)
-		return NULL;
-
-	map = map__new2(start, dso, MAP__FUNCTION);
-	if (map == NULL)
-		return NULL;
+	closedir(d);
 
-	if (machine__is_host(self))
-		dso->origin = DSO__ORIG_KMODULE;
-	else
-		dso->origin = DSO__ORIG_GUEST_KMODULE;
-	map_groups__insert(&self->kmaps, map);
-	return map;
+	return ret;
 }
 
-static int machine__create_modules(struct machine *self)
+static char *dso__find_kallsyms(struct dso *dso, struct map *map)
 {
-	char *line = NULL;
-	size_t n;
-	FILE *file;
-	struct map *map;
-	const char *modules;
+	u8 host_build_id[BUILD_ID_SIZE];
+	char sbuild_id[BUILD_ID_SIZE * 2 + 1];
+	bool is_host = false;
 	char path[PATH_MAX];
 
-	if (machine__is_default_guest(self))
-		modules = symbol_conf.default_guest_modules;
-	else {
-		sprintf(path, "%s/proc/modules", self->root_dir);
-		modules = path;
+	if (!dso->has_build_id) {
+		/*
+		 * Last resort, if we don't have a build-id and couldn't find
+		 * any vmlinux file, try the running kernel kallsyms table.
+		 */
+		goto proc_kallsyms;
 	}
 
-	file = fopen(modules, "r");
-	if (file == NULL)
-		return -1;
-
-	while (!feof(file)) {
-		char name[PATH_MAX];
-		u64 start;
-		char *sep;
-		int line_len;
-
-		line_len = getline(&line, &n, file);
-		if (line_len < 0)
-			break;
+	if (sysfs__read_build_id("/sys/kernel/notes", host_build_id,
+				 sizeof(host_build_id)) == 0)
+		is_host = dso__build_id_equal(dso, host_build_id);
 
-		if (!line)
-			goto out_failure;
+	build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id);
 
-		line[--line_len] = '\0'; /* \n */
+	scnprintf(path, sizeof(path), "%s/[kernel.kcore]/%s", buildid_dir,
+		  sbuild_id);
 
-		sep = strrchr(line, 'x');
-		if (sep == NULL)
-			continue;
+	/* Use /proc/kallsyms if possible */
+	if (is_host) {
+		DIR *d;
+		int fd;
 
-		hex2u64(sep + 1, &start);
+		/* If no cached kcore go with /proc/kallsyms */
+		d = opendir(path);
+		if (!d)
+			goto proc_kallsyms;
+		closedir(d);
 
-		sep = strchr(line, ' ');
-		if (sep == NULL)
-			continue;
+		/*
+		 * Do not check the build-id cache, until we know we cannot use
+		 * /proc/kcore.
+		 */
+		fd = open("/proc/kcore", O_RDONLY);
+		if (fd != -1) {
+			close(fd);
+			/* If module maps match go with /proc/kallsyms */
+			if (!validate_kcore_addresses("/proc/kallsyms", map))
+				goto proc_kallsyms;
+		}
 
-		*sep = '\0';
+		/* Find kallsyms in build-id cache with kcore */
+		if (!find_matching_kcore(map, path, sizeof(path)))
+			return strdup(path);
 
-		snprintf(name, sizeof(name), "[%s]", line);
-		map = machine__new_module(self, start, name);
-		if (map == NULL)
-			goto out_delete_line;
-		dso__kernel_module_get_build_id(map->dso, self->root_dir);
+		goto proc_kallsyms;
 	}
 
-	free(line);
-	fclose(file);
-
-	return machine__set_modules_path(self);
-
-out_delete_line:
-	free(line);
-out_failure:
-	return -1;
-}
-
-static int dso__load_vmlinux(struct dso *self, struct map *map,
-			     const char *vmlinux, symbol_filter_t filter)
-{
-	int err = -1, fd;
+	/* Find kallsyms in build-id cache with kcore */
+	if (!find_matching_kcore(map, path, sizeof(path)))
+		return strdup(path);
 
-	if (self->has_build_id) {
-		u8 build_id[BUILD_ID_SIZE];
+	scnprintf(path, sizeof(path), "%s/[kernel.kallsyms]/%s",
+		  buildid_dir, sbuild_id);
 
-		if (filename__read_build_id(vmlinux, build_id,
-					    sizeof(build_id)) < 0) {
-			pr_debug("No build_id in %s, ignoring it\n", vmlinux);
-			return -1;
-		}
-		if (!dso__build_id_equal(self, build_id)) {
-			char expected_build_id[BUILD_ID_SIZE * 2 + 1],
-			     vmlinux_build_id[BUILD_ID_SIZE * 2 + 1];
-
-			build_id__sprintf(self->build_id,
-					  sizeof(self->build_id),
-					  expected_build_id);
-			build_id__sprintf(build_id, sizeof(build_id),
-					  vmlinux_build_id);
-			pr_debug("build_id in %s is %s while expected is %s, "
-				 "ignoring it\n", vmlinux, vmlinux_build_id,
-				 expected_build_id);
-			return -1;
-		}
+	if (access(path, F_OK)) {
+		pr_err("No kallsyms or vmlinux with build-id %s was found\n",
+		       sbuild_id);
+		return NULL;
 	}
 
-	fd = open(vmlinux, O_RDONLY);
-	if (fd < 0)
-		return -1;
-
-	dso__set_loaded(self, map->type);
-	err = dso__load_sym(self, map, vmlinux, fd, filter, 0);
-	close(fd);
+	return strdup(path);
 
-	if (err > 0)
-		pr_debug("Using %s for symbols\n", vmlinux);
-
-	return err;
+proc_kallsyms:
+	return strdup("/proc/kallsyms");
 }
 
-int dso__load_vmlinux_path(struct dso *self, struct map *map,
-			   symbol_filter_t filter)
-{
-	int i, err = 0;
-	char *filename;
-
-	pr_debug("Looking at the vmlinux_path (%d entries long)\n",
-		 vmlinux_path__nr_entries + 1);
-
-	filename = dso__build_id_filename(self, NULL, 0);
-	if (filename != NULL) {
-		err = dso__load_vmlinux(self, map, filename, filter);
-		if (err > 0) {
-			dso__set_long_name(self, filename);
-			goto out;
-		}
-		free(filename);
-	}
-
-	for (i = 0; i < vmlinux_path__nr_entries; ++i) {
-		err = dso__load_vmlinux(self, map, vmlinux_path[i], filter);
-		if (err > 0) {
-			dso__set_long_name(self, strdup(vmlinux_path[i]));
-			break;
-		}
-	}
-out:
-	return err;
-}
-
-static int dso__load_kernel_sym(struct dso *self, struct map *map,
+static int dso__load_kernel_sym(struct dso *dso, struct map *map,
 				symbol_filter_t filter)
 {
 	int err;
 	const char *kallsyms_filename = NULL;
 	char *kallsyms_allocated_filename = NULL;
 	/*
-	 * Step 1: if the user specified a vmlinux filename, use it and only
-	 * it, reporting errors to the user if it cannot be used.
+	 * Step 1: if the user specified a kallsyms or vmlinux filename, use
+	 * it and only it, reporting errors to the user if it cannot be used.
 	 *
 	 * For instance, try to analyse an ARM perf.data file _without_ a
 	 * build-id, or if the user specifies the wrong path to the right
@@ -1742,79 +1629,40 @@ static int dso__load_kernel_sym(struct dso *self, struct map *map,
 	 * validation in dso__load_vmlinux and will bail out if they don't
 	 * match.
 	 */
-	if (symbol_conf.vmlinux_name != NULL) {
-		err = dso__load_vmlinux(self, map,
-					symbol_conf.vmlinux_name, filter);
-		if (err > 0) {
-			dso__set_long_name(self,
-					   strdup(symbol_conf.vmlinux_name));
-			goto out_fixup;
-		}
-		return err;
+	if (symbol_conf.kallsyms_name != NULL) {
+		kallsyms_filename = symbol_conf.kallsyms_name;
+		goto do_kallsyms;
 	}
 
-	if (vmlinux_path != NULL) {
-		err = dso__load_vmlinux_path(self, map, filter);
-		if (err > 0)
-			goto out_fixup;
+	if (!symbol_conf.ignore_vmlinux && symbol_conf.vmlinux_name != NULL) {
+		return dso__load_vmlinux(dso, map, symbol_conf.vmlinux_name,
+					 false, filter);
 	}
 
-	/*
-	 * Say the kernel DSO was created when processing the build-id header table,
-	 * we have a build-id, so check if it is the same as the running kernel,
-	 * using it if it is.
-	 */
-	if (self->has_build_id) {
-		u8 kallsyms_build_id[BUILD_ID_SIZE];
-		char sbuild_id[BUILD_ID_SIZE * 2 + 1];
-
-		if (sysfs__read_build_id("/sys/kernel/notes", kallsyms_build_id,
-					 sizeof(kallsyms_build_id)) == 0) {
-			if (dso__build_id_equal(self, kallsyms_build_id)) {
-				kallsyms_filename = "/proc/kallsyms";
-				goto do_kallsyms;
-			}
-		}
-		/*
-		 * Now look if we have it on the build-id cache in
-		 * $HOME/.debug/[kernel.kallsyms].
-		 */
-		build_id__sprintf(self->build_id, sizeof(self->build_id),
-				  sbuild_id);
+	if (!symbol_conf.ignore_vmlinux && vmlinux_path != NULL) {
+		err = dso__load_vmlinux_path(dso, map, filter);
+		if (err > 0)
+			return err;
+	}
 
-		if (asprintf(&kallsyms_allocated_filename,
-			     "%s/.debug/[kernel.kallsyms]/%s",
-			     getenv("HOME"), sbuild_id) == -1) {
-			pr_err("Not enough memory for kallsyms file lookup\n");
-			return -1;
-		}
+	/* do not try local files if a symfs was given */
+	if (symbol_conf.symfs[0] != 0)
+		return -1;
 
-		kallsyms_filename = kallsyms_allocated_filename;
+	kallsyms_allocated_filename = dso__find_kallsyms(dso, map);
+	if (!kallsyms_allocated_filename)
+		return -1;
 
-		if (access(kallsyms_filename, F_OK)) {
-			pr_err("No kallsyms or vmlinux with build-id %s "
-			       "was found\n", sbuild_id);
-			free(kallsyms_allocated_filename);
-			return -1;
-		}
-	} else {
-		/*
-		 * Last resort, if we don't have a build-id and couldn't find
-		 * any vmlinux file, try the running kernel kallsyms table.
-		 */
-		kallsyms_filename = "/proc/kallsyms";
-	}
+	kallsyms_filename = kallsyms_allocated_filename;
 
 do_kallsyms:
-	err = dso__load_kallsyms(self, kallsyms_filename, map, filter);
+	err = dso__load_kallsyms(dso, kallsyms_filename, map, filter);
 	if (err > 0)
 		pr_debug("Using %s for symbols\n", kallsyms_filename);
 	free(kallsyms_allocated_filename);
 
-	if (err > 0) {
-out_fixup:
-		if (kallsyms_filename != NULL)
-			dso__set_long_name(self, strdup("[kernel.kallsyms]"));
+	if (err > 0 && !dso__is_kcore(dso)) {
+		dso__set_long_name(dso, "[kernel.kallsyms]", false);
 		map__fixup_start(map);
 		map__fixup_end(map);
 	}
@@ -1822,8 +1670,8 @@ out_fixup:
 	return err;
 }
 
-static int dso__load_guest_kernel_sym(struct dso *self, struct map *map,
-				symbol_filter_t filter)
+static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map,
+				      symbol_filter_t filter)
 {
 	int err;
 	const char *kallsyms_filename = NULL;
@@ -1843,9 +1691,10 @@ static int dso__load_guest_kernel_sym(struct dso *self, struct map *map,
 		 * Or use file guest_kallsyms inputted by user on commandline
 		 */
 		if (symbol_conf.default_guest_vmlinux_name != NULL) {
-			err = dso__load_vmlinux(self, map,
-				symbol_conf.default_guest_vmlinux_name, filter);
-			goto out_try_fixup;
+			err = dso__load_vmlinux(dso, map,
+						symbol_conf.default_guest_vmlinux_name,
+						false, filter);
+			return err;
 		}
 
 		kallsyms_filename = symbol_conf.default_guest_kallsyms;
@@ -1856,16 +1705,12 @@ static int dso__load_guest_kernel_sym(struct dso *self, struct map *map,
 		kallsyms_filename = path;
 	}
 
-	err = dso__load_kallsyms(self, kallsyms_filename, map, filter);
+	err = dso__load_kallsyms(dso, kallsyms_filename, map, filter);
 	if (err > 0)
 		pr_debug("Using %s for symbols\n", kallsyms_filename);
-
-out_try_fixup:
-	if (err > 0) {
-		if (kallsyms_filename != NULL) {
-			machine__mmap_name(machine, path, sizeof(path));
-			dso__set_long_name(self, strdup(path));
-		}
+	if (err > 0 && !dso__is_kcore(dso)) {
+		machine__mmap_name(machine, path, sizeof(path));
+		dso__set_long_name(dso, strdup(path), true);
 		map__fixup_start(map);
 		map__fixup_end(map);
 	}
@@ -1873,204 +1718,12 @@ out_try_fixup:
 	return err;
 }
 
-static void dsos__add(struct list_head *head, struct dso *dso)
-{
-	list_add_tail(&dso->node, head);
-}
-
-static struct dso *dsos__find(struct list_head *head, const char *name)
-{
-	struct dso *pos;
-
-	list_for_each_entry(pos, head, node)
-		if (strcmp(pos->long_name, name) == 0)
-			return pos;
-	return NULL;
-}
-
-struct dso *__dsos__findnew(struct list_head *head, const char *name)
-{
-	struct dso *dso = dsos__find(head, name);
-
-	if (!dso) {
-		dso = dso__new(name);
-		if (dso != NULL) {
-			dsos__add(head, dso);
-			dso__set_basename(dso);
-		}
-	}
-
-	return dso;
-}
-
-size_t __dsos__fprintf(struct list_head *head, FILE *fp)
-{
-	struct dso *pos;
-	size_t ret = 0;
-
-	list_for_each_entry(pos, head, node) {
-		int i;
-		for (i = 0; i < MAP__NR_TYPES; ++i)
-			ret += dso__fprintf(pos, i, fp);
-	}
-
-	return ret;
-}
-
-size_t machines__fprintf_dsos(struct rb_root *self, FILE *fp)
-{
-	struct rb_node *nd;
-	size_t ret = 0;
-
-	for (nd = rb_first(self); nd; nd = rb_next(nd)) {
-		struct machine *pos = rb_entry(nd, struct machine, rb_node);
-		ret += __dsos__fprintf(&pos->kernel_dsos, fp);
-		ret += __dsos__fprintf(&pos->user_dsos, fp);
-	}
-
-	return ret;
-}
-
-static size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp,
-				      bool with_hits)
-{
-	struct dso *pos;
-	size_t ret = 0;
-
-	list_for_each_entry(pos, head, node) {
-		if (with_hits && !pos->hit)
-			continue;
-		ret += dso__fprintf_buildid(pos, fp);
-		ret += fprintf(fp, " %s\n", pos->long_name);
-	}
-	return ret;
-}
-
-size_t machine__fprintf_dsos_buildid(struct machine *self, FILE *fp, bool with_hits)
-{
-	return __dsos__fprintf_buildid(&self->kernel_dsos, fp, with_hits) +
-	       __dsos__fprintf_buildid(&self->user_dsos, fp, with_hits);
-}
-
-size_t machines__fprintf_dsos_buildid(struct rb_root *self, FILE *fp, bool with_hits)
-{
-	struct rb_node *nd;
-	size_t ret = 0;
-
-	for (nd = rb_first(self); nd; nd = rb_next(nd)) {
-		struct machine *pos = rb_entry(nd, struct machine, rb_node);
-		ret += machine__fprintf_dsos_buildid(pos, fp, with_hits);
-	}
-	return ret;
-}
-
-struct dso *dso__new_kernel(const char *name)
-{
-	struct dso *self = dso__new(name ?: "[kernel.kallsyms]");
-
-	if (self != NULL) {
-		dso__set_short_name(self, "[kernel]");
-		self->kernel = DSO_TYPE_KERNEL;
-	}
-
-	return self;
-}
-
-static struct dso *dso__new_guest_kernel(struct machine *machine,
-					const char *name)
-{
-	char bf[PATH_MAX];
-	struct dso *self = dso__new(name ?: machine__mmap_name(machine, bf, sizeof(bf)));
-
-	if (self != NULL) {
-		dso__set_short_name(self, "[guest.kernel]");
-		self->kernel = DSO_TYPE_GUEST_KERNEL;
-	}
-
-	return self;
-}
-
-void dso__read_running_kernel_build_id(struct dso *self, struct machine *machine)
-{
-	char path[PATH_MAX];
-
-	if (machine__is_default_guest(machine))
-		return;
-	sprintf(path, "%s/sys/kernel/notes", machine->root_dir);
-	if (sysfs__read_build_id(path, self->build_id,
-				 sizeof(self->build_id)) == 0)
-		self->has_build_id = true;
-}
-
-static struct dso *machine__create_kernel(struct machine *self)
-{
-	const char *vmlinux_name = NULL;
-	struct dso *kernel;
-
-	if (machine__is_host(self)) {
-		vmlinux_name = symbol_conf.vmlinux_name;
-		kernel = dso__new_kernel(vmlinux_name);
-	} else {
-		if (machine__is_default_guest(self))
-			vmlinux_name = symbol_conf.default_guest_vmlinux_name;
-		kernel = dso__new_guest_kernel(self, vmlinux_name);
-	}
-
-	if (kernel != NULL) {
-		dso__read_running_kernel_build_id(kernel, self);
-		dsos__add(&self->kernel_dsos, kernel);
-	}
-	return kernel;
-}
-
-int __machine__create_kernel_maps(struct machine *self, struct dso *kernel)
-{
-	enum map_type type;
-
-	for (type = 0; type < MAP__NR_TYPES; ++type) {
-		struct kmap *kmap;
-
-		self->vmlinux_maps[type] = map__new2(0, kernel, type);
-		if (self->vmlinux_maps[type] == NULL)
-			return -1;
-
-		self->vmlinux_maps[type]->map_ip =
-			self->vmlinux_maps[type]->unmap_ip = identity__map_ip;
-
-		kmap = map__kmap(self->vmlinux_maps[type]);
-		kmap->kmaps = &self->kmaps;
-		map_groups__insert(&self->kmaps, self->vmlinux_maps[type]);
-	}
-
-	return 0;
-}
-
-int machine__create_kernel_maps(struct machine *self)
-{
-	struct dso *kernel = machine__create_kernel(self);
-
-	if (kernel == NULL ||
-	    __machine__create_kernel_maps(self, kernel) < 0)
-		return -1;
-
-	if (symbol_conf.use_modules && machine__create_modules(self) < 0)
-		pr_debug("Problems creating module maps, continuing anyway...\n");
-	/*
-	 * Now that we have all the maps created, just set the ->end of them:
-	 */
-	map_groups__fixup_end(&self->kmaps);
-	return 0;
-}
-
 static void vmlinux_path__exit(void)
 {
-	while (--vmlinux_path__nr_entries >= 0) {
-		free(vmlinux_path[vmlinux_path__nr_entries]);
-		vmlinux_path[vmlinux_path__nr_entries] = NULL;
-	}
+	while (--vmlinux_path__nr_entries >= 0)
+		zfree(&vmlinux_path[vmlinux_path__nr_entries]);
 
-	free(vmlinux_path);
-	vmlinux_path = NULL;
+	zfree(&vmlinux_path);
 }
 
 static int vmlinux_path__init(void)
@@ -2078,9 +1731,6 @@ static int vmlinux_path__init(void)
 	struct utsname uts;
 	char bf[PATH_MAX];
 
-	if (uname(&uts) < 0)
-		return -1;
-
 	vmlinux_path = malloc(sizeof(char *) * 5);
 	if (vmlinux_path == NULL)
 		return -1;
@@ -2093,6 +1743,14 @@ static int vmlinux_path__init(void)
 	if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
 		goto out_fail;
 	++vmlinux_path__nr_entries;
+
+	/* only try running kernel version if no symfs was given */
+	if (symbol_conf.symfs[0] != 0)
+		return 0;
+
+	if (uname(&uts) < 0)
+		return -1;
+
 	snprintf(bf, sizeof(bf), "/boot/vmlinux-%s", uts.release);
 	vmlinux_path[vmlinux_path__nr_entries] = strdup(bf);
 	if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
@@ -2117,26 +1775,7 @@ out_fail:
 	return -1;
 }
 
-size_t machine__fprintf_vmlinux_path(struct machine *self, FILE *fp)
-{
-	int i;
-	size_t printed = 0;
-	struct dso *kdso = self->vmlinux_maps[MAP__FUNCTION]->dso;
-
-	if (kdso->has_build_id) {
-		char filename[PATH_MAX];
-		if (dso__build_id_filename(kdso, filename, sizeof(filename)))
-			printed += fprintf(fp, "[0] %s\n", filename);
-	}
-
-	for (i = 0; i < vmlinux_path__nr_entries; ++i)
-		printed += fprintf(fp, "[%d] %s\n",
-				   i + kdso->has_build_id, vmlinux_path[i]);
-
-	return printed;
-}
-
-static int setup_list(struct strlist **list, const char *list_str,
+int setup_list(struct strlist **list, const char *list_str,
 		      const char *list_name)
 {
 	if (list_str == NULL)
@@ -2150,9 +1789,36 @@ static int setup_list(struct strlist **list, const char *list_str,
 	return 0;
 }
 
+static bool symbol__read_kptr_restrict(void)
+{
+	bool value = false;
+
+	if (geteuid() != 0) {
+		FILE *fp = fopen("/proc/sys/kernel/kptr_restrict", "r");
+		if (fp != NULL) {
+			char line[8];
+
+			if (fgets(line, sizeof(line), fp) != NULL)
+				value = atoi(line) != 0;
+
+			fclose(fp);
+		}
+	}
+
+	return value;
+}
+
 int symbol__init(void)
 {
-	elf_version(EV_CURRENT);
+	const char *symfs;
+
+	if (symbol_conf.initialized)
+		return 0;
+
+	symbol_conf.priv_size = PERF_ALIGN(symbol_conf.priv_size, sizeof(u64));
+
+	symbol__elf_init();
+
 	if (symbol_conf.sort_by_name)
 		symbol_conf.priv_size += (sizeof(struct symbol_name_rb_node) -
 					  sizeof(struct symbol));
@@ -2177,138 +1843,38 @@ int symbol__init(void)
 		       symbol_conf.sym_list_str, "symbol") < 0)
 		goto out_free_comm_list;
 
+	/*
+	 * A path to symbols of "/" is identical to ""
+	 * reset here for simplicity.
+	 */
+	symfs = realpath(symbol_conf.symfs, NULL);
+	if (symfs == NULL)
+		symfs = symbol_conf.symfs;
+	if (strcmp(symfs, "/") == 0)
+		symbol_conf.symfs = "";
+	if (symfs != symbol_conf.symfs)
+		free((void *)symfs);
+
+	symbol_conf.kptr_restrict = symbol__read_kptr_restrict();
+
+	symbol_conf.initialized = true;
 	return 0;
 
-out_free_dso_list:
-	strlist__delete(symbol_conf.dso_list);
 out_free_comm_list:
 	strlist__delete(symbol_conf.comm_list);
+out_free_dso_list:
+	strlist__delete(symbol_conf.dso_list);
 	return -1;
 }
 
-int machines__create_kernel_maps(struct rb_root *self, pid_t pid)
-{
-	struct machine *machine = machines__findnew(self, pid);
-
-	if (machine == NULL)
-		return -1;
-
-	return machine__create_kernel_maps(machine);
-}
-
-static int hex(char ch)
-{
-	if ((ch >= '0') && (ch <= '9'))
-		return ch - '0';
-	if ((ch >= 'a') && (ch <= 'f'))
-		return ch - 'a' + 10;
-	if ((ch >= 'A') && (ch <= 'F'))
-		return ch - 'A' + 10;
-	return -1;
-}
-
-/*
- * While we find nice hex chars, build a long_val.
- * Return number of chars processed.
- */
-int hex2u64(const char *ptr, u64 *long_val)
-{
-	const char *p = ptr;
-	*long_val = 0;
-
-	while (*p) {
-		const int hex_val = hex(*p);
-
-		if (hex_val < 0)
-			break;
-
-		*long_val = (*long_val << 4) | hex_val;
-		p++;
-	}
-
-	return p - ptr;
-}
-
-char *strxfrchar(char *s, char from, char to)
-{
-	char *p = s;
-
-	while ((p = strchr(p, from)) != NULL)
-		*p++ = to;
-
-	return s;
-}
-
-int machines__create_guest_kernel_maps(struct rb_root *self)
+void symbol__exit(void)
 {
-	int ret = 0;
-	struct dirent **namelist = NULL;
-	int i, items = 0;
-	char path[PATH_MAX];
-	pid_t pid;
-
-	if (symbol_conf.default_guest_vmlinux_name ||
-	    symbol_conf.default_guest_modules ||
-	    symbol_conf.default_guest_kallsyms) {
-		machines__create_kernel_maps(self, DEFAULT_GUEST_KERNEL_ID);
-	}
-
-	if (symbol_conf.guestmount) {
-		items = scandir(symbol_conf.guestmount, &namelist, NULL, NULL);
-		if (items <= 0)
-			return -ENOENT;
-		for (i = 0; i < items; i++) {
-			if (!isdigit(namelist[i]->d_name[0])) {
-				/* Filter out . and .. */
-				continue;
-			}
-			pid = atoi(namelist[i]->d_name);
-			sprintf(path, "%s/%s/proc/kallsyms",
-				symbol_conf.guestmount,
-				namelist[i]->d_name);
-			ret = access(path, R_OK);
-			if (ret) {
-				pr_debug("Can't access file %s\n", path);
-				goto failure;
-			}
-			machines__create_kernel_maps(self, pid);
-		}
-failure:
-		free(namelist);
-	}
-
-	return ret;
-}
-
-int machine__load_kallsyms(struct machine *self, const char *filename,
-			   enum map_type type, symbol_filter_t filter)
-{
-	struct map *map = self->vmlinux_maps[type];
-	int ret = dso__load_kallsyms(map->dso, filename, map, filter);
-
-	if (ret > 0) {
-		dso__set_loaded(map->dso, type);
-		/*
-		 * Since /proc/kallsyms will have multiple sessions for the
-		 * kernel, with modules between them, fixup the end of all
-		 * sections.
-		 */
-		__map_groups__fixup_end(&self->kmaps, type);
-	}
-
-	return ret;
-}
-
-int machine__load_vmlinux_path(struct machine *self, enum map_type type,
-			       symbol_filter_t filter)
-{
-	struct map *map = self->vmlinux_maps[type];
-	int ret = dso__load_vmlinux_path(map->dso, map, filter);
-
-	if (ret > 0) {
-		dso__set_loaded(map->dso, type);
-		map__reloc_vmlinux(map);
-	}
-
-	return ret;
+	if (!symbol_conf.initialized)
+		return;
+	strlist__delete(symbol_conf.sym_list);
+	strlist__delete(symbol_conf.dso_list);
+	strlist__delete(symbol_conf.comm_list);
+	vmlinux_path__exit();
+	symbol_conf.sym_list = symbol_conf.dso_list = symbol_conf.comm_list = NULL;
+	symbol_conf.initialized = false;
 }
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 5e02d2c1715..615c752dd76 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -5,42 +5,57 @@
 #include <stdbool.h>
 #include <stdint.h>
 #include "map.h"
+#include "../perf.h"
 #include <linux/list.h>
 #include <linux/rbtree.h>
 #include <stdio.h>
+#include <byteswap.h>
+#include <libgen.h>
+#include "build-id.h"
+#include "event.h"
+
+#ifdef HAVE_LIBELF_SUPPORT
+#include <libelf.h>
+#include <gelf.h>
+#endif
+#include <elf.h>
 
-#define DEBUG_CACHE_DIR ".debug"
+#include "dso.h"
 
-#ifdef HAVE_CPLUS_DEMANGLE
+#ifdef HAVE_CPLUS_DEMANGLE_SUPPORT
 extern char *cplus_demangle(const char *, int);
 
-static inline char *bfd_demangle(void __used *v, const char *c, int i)
+static inline char *bfd_demangle(void __maybe_unused *v, const char *c, int i)
 {
 	return cplus_demangle(c, i);
 }
 #else
 #ifdef NO_DEMANGLE
-static inline char *bfd_demangle(void __used *v, const char __used *c,
-				 int __used i)
+static inline char *bfd_demangle(void __maybe_unused *v,
+				 const char __maybe_unused *c,
+				 int __maybe_unused i)
 {
 	return NULL;
 }
 #else
+#define PACKAGE 'perf'
 #include <bfd.h>
 #endif
 #endif
 
-int hex2u64(const char *ptr, u64 *val);
-char *strxfrchar(char *s, char from, char to);
-
 /*
  * libelf 0.8.x and earlier do not support ELF_C_READ_MMAP;
  * for newer versions we can use mmap to reduce memory usage:
  */
-#ifdef LIBELF_NO_MMAP
-# define PERF_ELF_C_READ_MMAP ELF_C_READ
-#else
+#ifdef HAVE_LIBELF_MMAP_SUPPORT
 # define PERF_ELF_C_READ_MMAP ELF_C_READ_MMAP
+#else
+# define PERF_ELF_C_READ_MMAP ELF_C_READ
+#endif
+
+#ifdef HAVE_LIBELF_SUPPORT
+extern Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
+				GElf_Shdr *shp, const char *name, size_t *idx);
 #endif
 
 #ifndef DMGL_PARAMS
@@ -48,31 +63,65 @@ char *strxfrchar(char *s, char from, char to);
 #define DMGL_ANSI        (1 << 1)       /* Include const, volatile, etc */
 #endif
 
-#define BUILD_ID_SIZE 20
-
+/** struct symbol - symtab entry
+ *
+ * @ignore - resolvable but tools ignore it (e.g. idle routines)
+ */
 struct symbol {
 	struct rb_node	rb_node;
 	u64		start;
 	u64		end;
 	u16		namelen;
+	u8		binding;
+	bool		ignore;
 	char		name[0];
 };
 
-void symbol__delete(struct symbol *self);
+void symbol__delete(struct symbol *sym);
+void symbols__delete(struct rb_root *symbols);
+
+/* symbols__for_each_entry - iterate over symbols (rb_root)
+ *
+ * @symbols: the rb_root of symbols
+ * @pos: the 'struct symbol *' to use as a loop cursor
+ * @nd: the 'struct rb_node *' to use as a temporary storage
+ */
+#define symbols__for_each_entry(symbols, pos, nd)			\
+	for (nd = rb_first(symbols);					\
+	     nd && (pos = rb_entry(nd, struct symbol, rb_node));	\
+	     nd = rb_next(nd))
+
+static inline size_t symbol__size(const struct symbol *sym)
+{
+	return sym->end - sym->start + 1;
+}
 
 struct strlist;
 
 struct symbol_conf {
 	unsigned short	priv_size;
+	unsigned short	nr_events;
 	bool		try_vmlinux_path,
+			ignore_vmlinux,
+			show_kernel_path,
 			use_modules,
 			sort_by_name,
 			show_nr_samples,
+			show_total_period,
 			use_callchain,
+			cumulate_callchain,
 			exclude_other,
-			full_paths,
-			show_cpu_utilization;
+			show_cpu_utilization,
+			initialized,
+			kptr_restrict,
+			annotate_asm_raw,
+			annotate_src,
+			event_group,
+			demangle,
+			filter_relative;
 	const char	*vmlinux_name,
+			*kallsyms_name,
+			*source_prefix,
 			*field_sep;
 	const char	*default_guest_vmlinux_name,
 			*default_guest_kallsyms,
@@ -84,14 +133,21 @@ struct symbol_conf {
 			*col_width_list_str;
        struct strlist	*dso_list,
 			*comm_list,
-			*sym_list;
+			*sym_list,
+			*dso_from_list,
+			*dso_to_list,
+			*sym_from_list,
+			*sym_to_list;
+	const char	*symfs;
 };
 
 extern struct symbol_conf symbol_conf;
+extern int vmlinux_path__nr_entries;
+extern char **vmlinux_path;
 
-static inline void *symbol__priv(struct symbol *self)
+static inline void *symbol__priv(struct symbol *sym)
 {
-	return ((void *)self) - symbol_conf.priv_size;
+	return ((void *)sym) - symbol_conf.priv_size;
 }
 
 struct ref_reloc_sym {
@@ -103,119 +159,139 @@ struct ref_reloc_sym {
 struct map_symbol {
 	struct map    *map;
 	struct symbol *sym;
+	bool	      unfolded;
+	bool	      has_children;
 };
 
-struct addr_location {
-	struct thread *thread;
+struct addr_map_symbol {
 	struct map    *map;
 	struct symbol *sym;
 	u64	      addr;
-	char	      level;
-	bool	      filtered;
-	unsigned int  cpumode;
+	u64	      al_addr;
 };
 
-enum dso_kernel_type {
-	DSO_TYPE_USER = 0,
-	DSO_TYPE_KERNEL,
-	DSO_TYPE_GUEST_KERNEL
+struct branch_info {
+	struct addr_map_symbol from;
+	struct addr_map_symbol to;
+	struct branch_flags flags;
 };
 
-struct dso {
-	struct list_head node;
-	struct rb_root	 symbols[MAP__NR_TYPES];
-	struct rb_root	 symbol_names[MAP__NR_TYPES];
-	u8		 adjust_symbols:1;
-	u8		 slen_calculated:1;
-	u8		 has_build_id:1;
-	enum dso_kernel_type	kernel;
-	u8		 hit:1;
-	u8		 annotate_warned:1;
-	unsigned char	 origin;
-	u8		 sorted_by_name;
-	u8		 loaded;
-	u8		 build_id[BUILD_ID_SIZE];
-	const char	 *short_name;
-	char	 	 *long_name;
-	u16		 long_name_len;
-	u16		 short_name_len;
-	char		 name[0];
+struct mem_info {
+	struct addr_map_symbol iaddr;
+	struct addr_map_symbol daddr;
+	union perf_mem_data_src data_src;
 };
 
-struct dso *dso__new(const char *name);
-struct dso *dso__new_kernel(const char *name);
-void dso__delete(struct dso *self);
+struct addr_location {
+	struct machine *machine;
+	struct thread *thread;
+	struct map    *map;
+	struct symbol *sym;
+	u64	      addr;
+	char	      level;
+	u8	      filtered;
+	u8	      cpumode;
+	s32	      cpu;
+};
 
-bool dso__loaded(const struct dso *self, enum map_type type);
-bool dso__sorted_by_name(const struct dso *self, enum map_type type);
+struct symsrc {
+	char *name;
+	int fd;
+	enum dso_binary_type type;
 
-static inline void dso__set_loaded(struct dso *self, enum map_type type)
-{
-	self->loaded |= (1 << type);
-}
+#ifdef HAVE_LIBELF_SUPPORT
+	Elf *elf;
+	GElf_Ehdr ehdr;
+
+	Elf_Scn *opdsec;
+	size_t opdidx;
+	GElf_Shdr opdshdr;
 
-void dso__sort_by_name(struct dso *self, enum map_type type);
+	Elf_Scn *symtab;
+	GElf_Shdr symshdr;
 
-struct dso *__dsos__findnew(struct list_head *head, const char *name);
+	Elf_Scn *dynsym;
+	size_t dynsym_idx;
+	GElf_Shdr dynshdr;
 
-int dso__load(struct dso *self, struct map *map, symbol_filter_t filter);
-int dso__load_vmlinux_path(struct dso *self, struct map *map,
+	bool adjust_symbols;
+#endif
+};
+
+void symsrc__destroy(struct symsrc *ss);
+int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
+		 enum dso_binary_type type);
+bool symsrc__has_symtab(struct symsrc *ss);
+bool symsrc__possibly_runtime(struct symsrc *ss);
+
+int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter);
+int dso__load_vmlinux(struct dso *dso, struct map *map,
+		      const char *vmlinux, bool vmlinux_allocated,
+		      symbol_filter_t filter);
+int dso__load_vmlinux_path(struct dso *dso, struct map *map,
 			   symbol_filter_t filter);
-int dso__load_kallsyms(struct dso *self, const char *filename, struct map *map,
+int dso__load_kallsyms(struct dso *dso, const char *filename, struct map *map,
 		       symbol_filter_t filter);
-int machine__load_kallsyms(struct machine *self, const char *filename,
-			   enum map_type type, symbol_filter_t filter);
-int machine__load_vmlinux_path(struct machine *self, enum map_type type,
-			       symbol_filter_t filter);
-
-size_t __dsos__fprintf(struct list_head *head, FILE *fp);
-
-size_t machine__fprintf_dsos_buildid(struct machine *self, FILE *fp, bool with_hits);
-size_t machines__fprintf_dsos(struct rb_root *self, FILE *fp);
-size_t machines__fprintf_dsos_buildid(struct rb_root *self, FILE *fp, bool with_hits);
-
-size_t dso__fprintf_buildid(struct dso *self, FILE *fp);
-size_t dso__fprintf(struct dso *self, enum map_type type, FILE *fp);
-
-enum dso_origin {
-	DSO__ORIG_KERNEL = 0,
-	DSO__ORIG_GUEST_KERNEL,
-	DSO__ORIG_JAVA_JIT,
-	DSO__ORIG_BUILD_ID_CACHE,
-	DSO__ORIG_FEDORA,
-	DSO__ORIG_UBUNTU,
-	DSO__ORIG_BUILDID,
-	DSO__ORIG_DSO,
-	DSO__ORIG_GUEST_KMODULE,
-	DSO__ORIG_KMODULE,
-	DSO__ORIG_NOT_FOUND,
-};
 
-char dso__symtab_origin(const struct dso *self);
-void dso__set_long_name(struct dso *self, char *name);
-void dso__set_build_id(struct dso *self, void *build_id);
-void dso__read_running_kernel_build_id(struct dso *self, struct machine *machine);
-struct symbol *dso__find_symbol(struct dso *self, enum map_type type, u64 addr);
-struct symbol *dso__find_symbol_by_name(struct dso *self, enum map_type type,
+struct symbol *dso__find_symbol(struct dso *dso, enum map_type type,
+				u64 addr);
+struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type,
 					const char *name);
 
 int filename__read_build_id(const char *filename, void *bf, size_t size);
 int sysfs__read_build_id(const char *filename, void *bf, size_t size);
-bool __dsos__read_build_ids(struct list_head *head, bool with_hits);
-int build_id__sprintf(const u8 *self, int len, char *bf);
-int kallsyms__parse(const char *filename, void *arg,
-		    int (*process_symbol)(void *arg, const char *name,
-					  char type, u64 start));
-
-int __machine__create_kernel_maps(struct machine *self, struct dso *kernel);
-int machine__create_kernel_maps(struct machine *self);
-
-int machines__create_kernel_maps(struct rb_root *self, pid_t pid);
-int machines__create_guest_kernel_maps(struct rb_root *self);
+int modules__parse(const char *filename, void *arg,
+		   int (*process_module)(void *arg, const char *name,
+					 u64 start));
+int filename__read_debuglink(const char *filename, char *debuglink,
+			     size_t size);
 
 int symbol__init(void);
+void symbol__exit(void);
+void symbol__elf_init(void);
+struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name);
+size_t symbol__fprintf_symname_offs(const struct symbol *sym,
+				    const struct addr_location *al, FILE *fp);
+size_t symbol__fprintf_symname(const struct symbol *sym, FILE *fp);
+size_t symbol__fprintf(struct symbol *sym, FILE *fp);
 bool symbol_type__is_a(char symbol_type, enum map_type map_type);
+bool symbol__restricted_filename(const char *filename,
+				 const char *restricted_filename);
+bool symbol__is_idle(struct symbol *sym);
+
+int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
+		  struct symsrc *runtime_ss, symbol_filter_t filter,
+		  int kmodule);
+int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss,
+				struct map *map, symbol_filter_t filter);
+
+void symbols__insert(struct rb_root *symbols, struct symbol *sym);
+void symbols__fixup_duplicate(struct rb_root *symbols);
+void symbols__fixup_end(struct rb_root *symbols);
+void __map_groups__fixup_end(struct map_groups *mg, enum map_type type);
+
+typedef int (*mapfn_t)(u64 start, u64 len, u64 pgoff, void *data);
+int file__read_maps(int fd, bool exe, mapfn_t mapfn, void *data,
+		    bool *is_64_bit);
+
+#define PERF_KCORE_EXTRACT "/tmp/perf-kcore-XXXXXX"
+
+struct kcore_extract {
+	char *kcore_filename;
+	u64 addr;
+	u64 offs;
+	u64 len;
+	char extract_filename[sizeof(PERF_KCORE_EXTRACT)];
+	int fd;
+};
+
+int kcore_extract__create(struct kcore_extract *kce);
+void kcore_extract__delete(struct kcore_extract *kce);
+
+int kcore_copy(const char *from_dir, const char *to_dir);
+int compare_proc_modules(const char *from, const char *to);
 
-size_t machine__fprintf_vmlinux_path(struct machine *self, FILE *fp);
+int setup_list(struct strlist **list, const char *list_str,
+	       const char *list_name);
 
 #endif /* __PERF_SYMBOL */
diff --git a/tools/perf/util/target.c b/tools/perf/util/target.c
new file mode 100644
index 00000000000..e74c5963dc7
--- /dev/null
+++ b/tools/perf/util/target.c
@@ -0,0 +1,158 @@
+/*
+ * Helper functions for handling target threads/cpus
+ *
+ * Copyright (C) 2012, LG Electronics, Namhyung Kim <namhyung.kim@lge.com>
+ *
+ * Released under the GPL v2.
+ */
+
+#include "target.h"
+#include "debug.h"
+
+#include <pwd.h>
+#include <string.h>
+
+
+enum target_errno target__validate(struct target *target)
+{
+	enum target_errno ret = TARGET_ERRNO__SUCCESS;
+
+	if (target->pid)
+		target->tid = target->pid;
+
+	/* CPU and PID are mutually exclusive */
+	if (target->tid && target->cpu_list) {
+		target->cpu_list = NULL;
+		if (ret == TARGET_ERRNO__SUCCESS)
+			ret = TARGET_ERRNO__PID_OVERRIDE_CPU;
+	}
+
+	/* UID and PID are mutually exclusive */
+	if (target->tid && target->uid_str) {
+		target->uid_str = NULL;
+		if (ret == TARGET_ERRNO__SUCCESS)
+			ret = TARGET_ERRNO__PID_OVERRIDE_UID;
+	}
+
+	/* UID and CPU are mutually exclusive */
+	if (target->uid_str && target->cpu_list) {
+		target->cpu_list = NULL;
+		if (ret == TARGET_ERRNO__SUCCESS)
+			ret = TARGET_ERRNO__UID_OVERRIDE_CPU;
+	}
+
+	/* PID and SYSTEM are mutually exclusive */
+	if (target->tid && target->system_wide) {
+		target->system_wide = false;
+		if (ret == TARGET_ERRNO__SUCCESS)
+			ret = TARGET_ERRNO__PID_OVERRIDE_SYSTEM;
+	}
+
+	/* UID and SYSTEM are mutually exclusive */
+	if (target->uid_str && target->system_wide) {
+		target->system_wide = false;
+		if (ret == TARGET_ERRNO__SUCCESS)
+			ret = TARGET_ERRNO__UID_OVERRIDE_SYSTEM;
+	}
+
+	/* THREAD and SYSTEM/CPU are mutually exclusive */
+	if (target->per_thread && (target->system_wide || target->cpu_list)) {
+		target->per_thread = false;
+		if (ret == TARGET_ERRNO__SUCCESS)
+			ret = TARGET_ERRNO__SYSTEM_OVERRIDE_THREAD;
+	}
+
+	return ret;
+}
+
+enum target_errno target__parse_uid(struct target *target)
+{
+	struct passwd pwd, *result;
+	char buf[1024];
+	const char *str = target->uid_str;
+
+	target->uid = UINT_MAX;
+	if (str == NULL)
+		return TARGET_ERRNO__SUCCESS;
+
+	/* Try user name first */
+	getpwnam_r(str, &pwd, buf, sizeof(buf), &result);
+
+	if (result == NULL) {
+		/*
+		 * The user name not found. Maybe it's a UID number.
+		 */
+		char *endptr;
+		int uid = strtol(str, &endptr, 10);
+
+		if (*endptr != '\0')
+			return TARGET_ERRNO__INVALID_UID;
+
+		getpwuid_r(uid, &pwd, buf, sizeof(buf), &result);
+
+		if (result == NULL)
+			return TARGET_ERRNO__USER_NOT_FOUND;
+	}
+
+	target->uid = result->pw_uid;
+	return TARGET_ERRNO__SUCCESS;
+}
+
+/*
+ * This must have a same ordering as the enum target_errno.
+ */
+static const char *target__error_str[] = {
+	"PID/TID switch overriding CPU",
+	"PID/TID switch overriding UID",
+	"UID switch overriding CPU",
+	"PID/TID switch overriding SYSTEM",
+	"UID switch overriding SYSTEM",
+	"SYSTEM/CPU switch overriding PER-THREAD",
+	"Invalid User: %s",
+	"Problems obtaining information for user %s",
+};
+
+int target__strerror(struct target *target, int errnum,
+			  char *buf, size_t buflen)
+{
+	int idx;
+	const char *msg;
+
+	BUG_ON(buflen == 0);
+
+	if (errnum >= 0) {
+		const char *err = strerror_r(errnum, buf, buflen);
+
+		if (err != buf) {
+			size_t len = strlen(err);
+			memcpy(buf, err, min(buflen - 1, len));
+			*(buf + min(buflen - 1, len)) = '\0';
+		}
+
+		return 0;
+	}
+
+	if (errnum <  __TARGET_ERRNO__START || errnum >= __TARGET_ERRNO__END)
+		return -1;
+
+	idx = errnum - __TARGET_ERRNO__START;
+	msg = target__error_str[idx];
+
+	switch (errnum) {
+	case TARGET_ERRNO__PID_OVERRIDE_CPU ...
+	     TARGET_ERRNO__SYSTEM_OVERRIDE_THREAD:
+		snprintf(buf, buflen, "%s", msg);
+		break;
+
+	case TARGET_ERRNO__INVALID_UID:
+	case TARGET_ERRNO__USER_NOT_FOUND:
+		snprintf(buf, buflen, msg, target->uid_str);
+		break;
+
+	default:
+		/* cannot reach here */
+		break;
+	}
+
+	return 0;
+}
diff --git a/tools/perf/util/target.h b/tools/perf/util/target.h
new file mode 100644
index 00000000000..7381b1ca404
--- /dev/null
+++ b/tools/perf/util/target.h
@@ -0,0 +1,79 @@
+#ifndef _PERF_TARGET_H
+#define _PERF_TARGET_H
+
+#include <stdbool.h>
+#include <sys/types.h>
+
+struct target {
+	const char   *pid;
+	const char   *tid;
+	const char   *cpu_list;
+	const char   *uid_str;
+	uid_t	     uid;
+	bool	     system_wide;
+	bool	     uses_mmap;
+	bool	     default_per_cpu;
+	bool	     per_thread;
+};
+
+enum target_errno {
+	TARGET_ERRNO__SUCCESS		= 0,
+
+	/*
+	 * Choose an arbitrary negative big number not to clash with standard
+	 * errno since SUS requires the errno has distinct positive values.
+	 * See 'Issue 6' in the link below.
+	 *
+	 * http://pubs.opengroup.org/onlinepubs/9699919799/basedefs/errno.h.html
+	 */
+	__TARGET_ERRNO__START		= -10000,
+
+	/* for target__validate() */
+	TARGET_ERRNO__PID_OVERRIDE_CPU	= __TARGET_ERRNO__START,
+	TARGET_ERRNO__PID_OVERRIDE_UID,
+	TARGET_ERRNO__UID_OVERRIDE_CPU,
+	TARGET_ERRNO__PID_OVERRIDE_SYSTEM,
+	TARGET_ERRNO__UID_OVERRIDE_SYSTEM,
+	TARGET_ERRNO__SYSTEM_OVERRIDE_THREAD,
+
+	/* for target__parse_uid() */
+	TARGET_ERRNO__INVALID_UID,
+	TARGET_ERRNO__USER_NOT_FOUND,
+
+	__TARGET_ERRNO__END,
+};
+
+enum target_errno target__validate(struct target *target);
+enum target_errno target__parse_uid(struct target *target);
+
+int target__strerror(struct target *target, int errnum, char *buf, size_t buflen);
+
+static inline bool target__has_task(struct target *target)
+{
+	return target->tid || target->pid || target->uid_str;
+}
+
+static inline bool target__has_cpu(struct target *target)
+{
+	return target->system_wide || target->cpu_list;
+}
+
+static inline bool target__none(struct target *target)
+{
+	return !target__has_task(target) && !target__has_cpu(target);
+}
+
+static inline bool target__uses_dummy_map(struct target *target)
+{
+	bool use_dummy = false;
+
+	if (target->default_per_cpu)
+		use_dummy = target->per_thread ? true : false;
+	else if (target__has_task(target) ||
+	         (!target__has_cpu(target) && !target->uses_mmap))
+		use_dummy = true;
+
+	return use_dummy;
+}
+
+#endif /* _PERF_TARGET_H */
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 9a448b47400..2fde0d5e40b 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -6,168 +6,188 @@
 #include "thread.h"
 #include "util.h"
 #include "debug.h"
+#include "comm.h"
 
-/* Skip "." and ".." directories */
-static int filter(const struct dirent *dir)
+int thread__init_map_groups(struct thread *thread, struct machine *machine)
 {
-	if (dir->d_name[0] == '.')
-		return 0;
-	else
-		return 1;
+	struct thread *leader;
+	pid_t pid = thread->pid_;
+
+	if (pid == thread->tid) {
+		thread->mg = map_groups__new();
+	} else {
+		leader = machine__findnew_thread(machine, pid, pid);
+		if (leader)
+			thread->mg = map_groups__get(leader->mg);
+	}
+
+	return thread->mg ? 0 : -1;
 }
 
-int find_all_tid(int pid, pid_t ** all_tid)
+struct thread *thread__new(pid_t pid, pid_t tid)
 {
-	char name[256];
-	int items;
-	struct dirent **namelist = NULL;
-	int ret = 0;
-	int i;
-
-	sprintf(name, "/proc/%d/task", pid);
-	items = scandir(name, &namelist, filter, NULL);
-	if (items <= 0)
-                return -ENOENT;
-	*all_tid = malloc(sizeof(pid_t) * items);
-	if (!*all_tid) {
-		ret = -ENOMEM;
-		goto failure;
+	char *comm_str;
+	struct comm *comm;
+	struct thread *thread = zalloc(sizeof(*thread));
+
+	if (thread != NULL) {
+		thread->pid_ = pid;
+		thread->tid = tid;
+		thread->ppid = -1;
+		INIT_LIST_HEAD(&thread->comm_list);
+
+		comm_str = malloc(32);
+		if (!comm_str)
+			goto err_thread;
+
+		snprintf(comm_str, 32, ":%d", tid);
+		comm = comm__new(comm_str, 0);
+		free(comm_str);
+		if (!comm)
+			goto err_thread;
+
+		list_add(&comm->list, &thread->comm_list);
 	}
 
-	for (i = 0; i < items; i++)
-		(*all_tid)[i] = atoi(namelist[i]->d_name);
+	return thread;
 
-	ret = items;
-
-failure:
-	for (i=0; i<items; i++)
-		free(namelist[i]);
-	free(namelist);
-
-	return ret;
+err_thread:
+	free(thread);
+	return NULL;
 }
 
-static struct thread *thread__new(pid_t pid)
+void thread__delete(struct thread *thread)
 {
-	struct thread *self = zalloc(sizeof(*self));
-
-	if (self != NULL) {
-		map_groups__init(&self->mg);
-		self->pid = pid;
-		self->comm = malloc(32);
-		if (self->comm)
-			snprintf(self->comm, 32, ":%d", self->pid);
+	struct comm *comm, *tmp;
+
+	map_groups__put(thread->mg);
+	thread->mg = NULL;
+	list_for_each_entry_safe(comm, tmp, &thread->comm_list, list) {
+		list_del(&comm->list);
+		comm__free(comm);
 	}
 
-	return self;
+	free(thread);
 }
 
-int thread__set_comm(struct thread *self, const char *comm)
+struct comm *thread__comm(const struct thread *thread)
 {
-	int err;
+	if (list_empty(&thread->comm_list))
+		return NULL;
 
-	if (self->comm)
-		free(self->comm);
-	self->comm = strdup(comm);
-	err = self->comm == NULL ? -ENOMEM : 0;
-	if (!err) {
-		self->comm_set = true;
-		map_groups__flush(&self->mg);
-	}
-	return err;
+	return list_first_entry(&thread->comm_list, struct comm, list);
 }
 
-int thread__comm_len(struct thread *self)
+/* CHECKME: time should always be 0 if event aren't ordered */
+int thread__set_comm(struct thread *thread, const char *str, u64 timestamp)
 {
-	if (!self->comm_len) {
-		if (!self->comm)
-			return 0;
-		self->comm_len = strlen(self->comm);
+	struct comm *new, *curr = thread__comm(thread);
+	int err;
+
+	/* Override latest entry if it had no specific time coverage */
+	if (!curr->start) {
+		err = comm__override(curr, str, timestamp);
+		if (err)
+			return err;
+	} else {
+		new = comm__new(str, timestamp);
+		if (!new)
+			return -ENOMEM;
+		list_add(&new->list, &thread->comm_list);
 	}
 
-	return self->comm_len;
+	thread->comm_set = true;
+
+	return 0;
 }
 
-static size_t thread__fprintf(struct thread *self, FILE *fp)
+const char *thread__comm_str(const struct thread *thread)
 {
-	return fprintf(fp, "Thread %d %s\n", self->pid, self->comm) +
-	       map_groups__fprintf(&self->mg, verbose, fp);
+	const struct comm *comm = thread__comm(thread);
+
+	if (!comm)
+		return NULL;
+
+	return comm__str(comm);
 }
 
-struct thread *perf_session__findnew(struct perf_session *self, pid_t pid)
+/* CHECKME: it should probably better return the max comm len from its comm list */
+int thread__comm_len(struct thread *thread)
 {
-	struct rb_node **p = &self->threads.rb_node;
-	struct rb_node *parent = NULL;
-	struct thread *th;
-
-	/*
-	 * Font-end cache - PID lookups come in blocks,
-	 * so most of the time we dont have to look up
-	 * the full rbtree:
-	 */
-	if (self->last_match && self->last_match->pid == pid)
-		return self->last_match;
-
-	while (*p != NULL) {
-		parent = *p;
-		th = rb_entry(parent, struct thread, rb_node);
-
-		if (th->pid == pid) {
-			self->last_match = th;
-			return th;
-		}
-
-		if (pid < th->pid)
-			p = &(*p)->rb_left;
-		else
-			p = &(*p)->rb_right;
+	if (!thread->comm_len) {
+		const char *comm = thread__comm_str(thread);
+		if (!comm)
+			return 0;
+		thread->comm_len = strlen(comm);
 	}
 
-	th = thread__new(pid);
-	if (th != NULL) {
-		rb_link_node(&th->rb_node, parent, p);
-		rb_insert_color(&th->rb_node, &self->threads);
-		self->last_match = th;
-	}
+	return thread->comm_len;
+}
 
-	return th;
+size_t thread__fprintf(struct thread *thread, FILE *fp)
+{
+	return fprintf(fp, "Thread %d %s\n", thread->tid, thread__comm_str(thread)) +
+	       map_groups__fprintf(thread->mg, verbose, fp);
 }
 
-void thread__insert_map(struct thread *self, struct map *map)
+void thread__insert_map(struct thread *thread, struct map *map)
 {
-	map_groups__fixup_overlappings(&self->mg, map, verbose, stderr);
-	map_groups__insert(&self->mg, map);
+	map_groups__fixup_overlappings(thread->mg, map, verbose, stderr);
+	map_groups__insert(thread->mg, map);
 }
 
-int thread__fork(struct thread *self, struct thread *parent)
+static int thread__clone_map_groups(struct thread *thread,
+				    struct thread *parent)
 {
 	int i;
 
-	if (parent->comm_set) {
-		if (self->comm)
-			free(self->comm);
-		self->comm = strdup(parent->comm);
-		if (!self->comm)
-			return -ENOMEM;
-		self->comm_set = true;
-	}
+	/* This is new thread, we share map groups for process. */
+	if (thread->pid_ == parent->pid_)
+		return 0;
 
+	/* But this one is new process, copy maps. */
 	for (i = 0; i < MAP__NR_TYPES; ++i)
-		if (map_groups__clone(&self->mg, &parent->mg, i) < 0)
+		if (map_groups__clone(thread->mg, parent->mg, i) < 0)
 			return -ENOMEM;
+
 	return 0;
 }
 
-size_t perf_session__fprintf(struct perf_session *self, FILE *fp)
+int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp)
 {
-	size_t ret = 0;
-	struct rb_node *nd;
-
-	for (nd = rb_first(&self->threads); nd; nd = rb_next(nd)) {
-		struct thread *pos = rb_entry(nd, struct thread, rb_node);
+	int err;
 
-		ret += thread__fprintf(pos, fp);
+	if (parent->comm_set) {
+		const char *comm = thread__comm_str(parent);
+		if (!comm)
+			return -ENOMEM;
+		err = thread__set_comm(thread, comm, timestamp);
+		if (err)
+			return err;
+		thread->comm_set = true;
 	}
 
-	return ret;
+	thread->ppid = parent->tid;
+	return thread__clone_map_groups(thread, parent);
+}
+
+void thread__find_cpumode_addr_location(struct thread *thread,
+					struct machine *machine,
+					enum map_type type, u64 addr,
+					struct addr_location *al)
+{
+	size_t i;
+	const u8 const cpumodes[] = {
+		PERF_RECORD_MISC_USER,
+		PERF_RECORD_MISC_KERNEL,
+		PERF_RECORD_MISC_GUEST_USER,
+		PERF_RECORD_MISC_GUEST_KERNEL
+	};
+
+	for (i = 0; i < ARRAY_SIZE(cpumodes); i++) {
+		thread__find_addr_location(thread, machine, cpumodes[i], type,
+					   addr, al);
+		if (al->map)
+			break;
+	}
 }
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index ee6bbcf277c..3c0c2724f82 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -2,46 +2,80 @@
 #define __PERF_THREAD_H
 
 #include <linux/rbtree.h>
+#include <linux/list.h>
 #include <unistd.h>
+#include <sys/types.h>
 #include "symbol.h"
+#include <strlist.h>
 
 struct thread {
 	union {
 		struct rb_node	 rb_node;
 		struct list_head node;
 	};
-	struct map_groups	mg;
-	pid_t			pid;
+	struct map_groups	*mg;
+	pid_t			pid_; /* Not all tools update this */
+	pid_t			tid;
+	pid_t			ppid;
 	char			shortname[3];
 	bool			comm_set;
-	char			*comm;
+	bool			dead; /* if set thread has exited */
+	struct list_head	comm_list;
 	int			comm_len;
-};
 
-struct perf_session;
+	void			*priv;
+};
 
-int find_all_tid(int pid, pid_t ** all_tid);
-int thread__set_comm(struct thread *self, const char *comm);
-int thread__comm_len(struct thread *self);
-struct thread *perf_session__findnew(struct perf_session *self, pid_t pid);
-void thread__insert_map(struct thread *self, struct map *map);
-int thread__fork(struct thread *self, struct thread *parent);
-size_t perf_session__fprintf(struct perf_session *self, FILE *fp);
+struct machine;
+struct comm;
 
-static inline struct map *thread__find_map(struct thread *self,
-					   enum map_type type, u64 addr)
+struct thread *thread__new(pid_t pid, pid_t tid);
+int thread__init_map_groups(struct thread *thread, struct machine *machine);
+void thread__delete(struct thread *thread);
+static inline void thread__exited(struct thread *thread)
 {
-	return self ? map_groups__find(&self->mg, type, addr) : NULL;
+	thread->dead = true;
 }
 
-void thread__find_addr_map(struct thread *self,
-			   struct perf_session *session, u8 cpumode,
-			   enum map_type type, pid_t pid, u64 addr,
+int thread__set_comm(struct thread *thread, const char *comm, u64 timestamp);
+int thread__comm_len(struct thread *thread);
+struct comm *thread__comm(const struct thread *thread);
+const char *thread__comm_str(const struct thread *thread);
+void thread__insert_map(struct thread *thread, struct map *map);
+int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp);
+size_t thread__fprintf(struct thread *thread, FILE *fp);
+
+void thread__find_addr_map(struct thread *thread, struct machine *machine,
+			   u8 cpumode, enum map_type type, u64 addr,
 			   struct addr_location *al);
 
-void thread__find_addr_location(struct thread *self,
-				struct perf_session *session, u8 cpumode,
-				enum map_type type, pid_t pid, u64 addr,
-				struct addr_location *al,
-				symbol_filter_t filter);
+void thread__find_addr_location(struct thread *thread, struct machine *machine,
+				u8 cpumode, enum map_type type, u64 addr,
+				struct addr_location *al);
+
+void thread__find_cpumode_addr_location(struct thread *thread,
+					struct machine *machine,
+					enum map_type type, u64 addr,
+					struct addr_location *al);
+
+static inline void *thread__priv(struct thread *thread)
+{
+	return thread->priv;
+}
+
+static inline void thread__set_priv(struct thread *thread, void *p)
+{
+	thread->priv = p;
+}
+
+static inline bool thread__is_filtered(struct thread *thread)
+{
+	if (symbol_conf.comm_list &&
+	    !strlist__has_entry(symbol_conf.comm_list, thread__comm_str(thread))) {
+		return true;
+	}
+
+	return false;
+}
+
 #endif	/* __PERF_THREAD_H */
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
new file mode 100644
index 00000000000..5d321591210
--- /dev/null
+++ b/tools/perf/util/thread_map.c
@@ -0,0 +1,294 @@
+#include <dirent.h>
+#include <limits.h>
+#include <stdbool.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+#include "strlist.h"
+#include <string.h>
+#include "thread_map.h"
+#include "util.h"
+
+/* Skip "." and ".." directories */
+static int filter(const struct dirent *dir)
+{
+	if (dir->d_name[0] == '.')
+		return 0;
+	else
+		return 1;
+}
+
+struct thread_map *thread_map__new_by_pid(pid_t pid)
+{
+	struct thread_map *threads;
+	char name[256];
+	int items;
+	struct dirent **namelist = NULL;
+	int i;
+
+	sprintf(name, "/proc/%d/task", pid);
+	items = scandir(name, &namelist, filter, NULL);
+	if (items <= 0)
+		return NULL;
+
+	threads = malloc(sizeof(*threads) + sizeof(pid_t) * items);
+	if (threads != NULL) {
+		for (i = 0; i < items; i++)
+			threads->map[i] = atoi(namelist[i]->d_name);
+		threads->nr = items;
+	}
+
+	for (i=0; i<items; i++)
+		zfree(&namelist[i]);
+	free(namelist);
+
+	return threads;
+}
+
+struct thread_map *thread_map__new_by_tid(pid_t tid)
+{
+	struct thread_map *threads = malloc(sizeof(*threads) + sizeof(pid_t));
+
+	if (threads != NULL) {
+		threads->map[0] = tid;
+		threads->nr	= 1;
+	}
+
+	return threads;
+}
+
+struct thread_map *thread_map__new_by_uid(uid_t uid)
+{
+	DIR *proc;
+	int max_threads = 32, items, i;
+	char path[256];
+	struct dirent dirent, *next, **namelist = NULL;
+	struct thread_map *threads = malloc(sizeof(*threads) +
+					    max_threads * sizeof(pid_t));
+	if (threads == NULL)
+		goto out;
+
+	proc = opendir("/proc");
+	if (proc == NULL)
+		goto out_free_threads;
+
+	threads->nr = 0;
+
+	while (!readdir_r(proc, &dirent, &next) && next) {
+		char *end;
+		bool grow = false;
+		struct stat st;
+		pid_t pid = strtol(dirent.d_name, &end, 10);
+
+		if (*end) /* only interested in proper numerical dirents */
+			continue;
+
+		snprintf(path, sizeof(path), "/proc/%s", dirent.d_name);
+
+		if (stat(path, &st) != 0)
+			continue;
+
+		if (st.st_uid != uid)
+			continue;
+
+		snprintf(path, sizeof(path), "/proc/%d/task", pid);
+		items = scandir(path, &namelist, filter, NULL);
+		if (items <= 0)
+			goto out_free_closedir;
+
+		while (threads->nr + items >= max_threads) {
+			max_threads *= 2;
+			grow = true;
+		}
+
+		if (grow) {
+			struct thread_map *tmp;
+
+			tmp = realloc(threads, (sizeof(*threads) +
+						max_threads * sizeof(pid_t)));
+			if (tmp == NULL)
+				goto out_free_namelist;
+
+			threads = tmp;
+		}
+
+		for (i = 0; i < items; i++)
+			threads->map[threads->nr + i] = atoi(namelist[i]->d_name);
+
+		for (i = 0; i < items; i++)
+			zfree(&namelist[i]);
+		free(namelist);
+
+		threads->nr += items;
+	}
+
+out_closedir:
+	closedir(proc);
+out:
+	return threads;
+
+out_free_threads:
+	free(threads);
+	return NULL;
+
+out_free_namelist:
+	for (i = 0; i < items; i++)
+		zfree(&namelist[i]);
+	free(namelist);
+
+out_free_closedir:
+	zfree(&threads);
+	goto out_closedir;
+}
+
+struct thread_map *thread_map__new(pid_t pid, pid_t tid, uid_t uid)
+{
+	if (pid != -1)
+		return thread_map__new_by_pid(pid);
+
+	if (tid == -1 && uid != UINT_MAX)
+		return thread_map__new_by_uid(uid);
+
+	return thread_map__new_by_tid(tid);
+}
+
+static struct thread_map *thread_map__new_by_pid_str(const char *pid_str)
+{
+	struct thread_map *threads = NULL, *nt;
+	char name[256];
+	int items, total_tasks = 0;
+	struct dirent **namelist = NULL;
+	int i, j = 0;
+	pid_t pid, prev_pid = INT_MAX;
+	char *end_ptr;
+	struct str_node *pos;
+	struct strlist *slist = strlist__new(false, pid_str);
+
+	if (!slist)
+		return NULL;
+
+	strlist__for_each(pos, slist) {
+		pid = strtol(pos->s, &end_ptr, 10);
+
+		if (pid == INT_MIN || pid == INT_MAX ||
+		    (*end_ptr != '\0' && *end_ptr != ','))
+			goto out_free_threads;
+
+		if (pid == prev_pid)
+			continue;
+
+		sprintf(name, "/proc/%d/task", pid);
+		items = scandir(name, &namelist, filter, NULL);
+		if (items <= 0)
+			goto out_free_threads;
+
+		total_tasks += items;
+		nt = realloc(threads, (sizeof(*threads) +
+				       sizeof(pid_t) * total_tasks));
+		if (nt == NULL)
+			goto out_free_namelist;
+
+		threads = nt;
+
+		for (i = 0; i < items; i++) {
+			threads->map[j++] = atoi(namelist[i]->d_name);
+			zfree(&namelist[i]);
+		}
+		threads->nr = total_tasks;
+		free(namelist);
+	}
+
+out:
+	strlist__delete(slist);
+	return threads;
+
+out_free_namelist:
+	for (i = 0; i < items; i++)
+		zfree(&namelist[i]);
+	free(namelist);
+
+out_free_threads:
+	zfree(&threads);
+	goto out;
+}
+
+static struct thread_map *thread_map__new_by_tid_str(const char *tid_str)
+{
+	struct thread_map *threads = NULL, *nt;
+	int ntasks = 0;
+	pid_t tid, prev_tid = INT_MAX;
+	char *end_ptr;
+	struct str_node *pos;
+	struct strlist *slist;
+
+	/* perf-stat expects threads to be generated even if tid not given */
+	if (!tid_str) {
+		threads = malloc(sizeof(*threads) + sizeof(pid_t));
+		if (threads != NULL) {
+			threads->map[0] = -1;
+			threads->nr	= 1;
+		}
+		return threads;
+	}
+
+	slist = strlist__new(false, tid_str);
+	if (!slist)
+		return NULL;
+
+	strlist__for_each(pos, slist) {
+		tid = strtol(pos->s, &end_ptr, 10);
+
+		if (tid == INT_MIN || tid == INT_MAX ||
+		    (*end_ptr != '\0' && *end_ptr != ','))
+			goto out_free_threads;
+
+		if (tid == prev_tid)
+			continue;
+
+		ntasks++;
+		nt = realloc(threads, sizeof(*threads) + sizeof(pid_t) * ntasks);
+
+		if (nt == NULL)
+			goto out_free_threads;
+
+		threads = nt;
+		threads->map[ntasks - 1] = tid;
+		threads->nr		 = ntasks;
+	}
+out:
+	return threads;
+
+out_free_threads:
+	zfree(&threads);
+	goto out;
+}
+
+struct thread_map *thread_map__new_str(const char *pid, const char *tid,
+				       uid_t uid)
+{
+	if (pid)
+		return thread_map__new_by_pid_str(pid);
+
+	if (!tid && uid != UINT_MAX)
+		return thread_map__new_by_uid(uid);
+
+	return thread_map__new_by_tid_str(tid);
+}
+
+void thread_map__delete(struct thread_map *threads)
+{
+	free(threads);
+}
+
+size_t thread_map__fprintf(struct thread_map *threads, FILE *fp)
+{
+	int i;
+	size_t printed = fprintf(fp, "%d thread%s: ",
+				 threads->nr, threads->nr > 1 ? "s" : "");
+	for (i = 0; i < threads->nr; ++i)
+		printed += fprintf(fp, "%s%d", i ? ", " : "", threads->map[i]);
+
+	return printed + fprintf(fp, "\n");
+}
diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h
new file mode 100644
index 00000000000..0cd8b310808
--- /dev/null
+++ b/tools/perf/util/thread_map.h
@@ -0,0 +1,29 @@
+#ifndef __PERF_THREAD_MAP_H
+#define __PERF_THREAD_MAP_H
+
+#include <sys/types.h>
+#include <stdio.h>
+
+struct thread_map {
+	int nr;
+	pid_t map[];
+};
+
+struct thread_map *thread_map__new_by_pid(pid_t pid);
+struct thread_map *thread_map__new_by_tid(pid_t tid);
+struct thread_map *thread_map__new_by_uid(uid_t uid);
+struct thread_map *thread_map__new(pid_t pid, pid_t tid, uid_t uid);
+
+struct thread_map *thread_map__new_str(const char *pid,
+		const char *tid, uid_t uid);
+
+void thread_map__delete(struct thread_map *threads);
+
+size_t thread_map__fprintf(struct thread_map *threads, FILE *fp);
+
+static inline int thread_map__nr(struct thread_map *threads)
+{
+	return threads ? threads->nr : 1;
+}
+
+#endif	/* __PERF_THREAD_MAP_H */
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
new file mode 100644
index 00000000000..4385816d3d4
--- /dev/null
+++ b/tools/perf/util/tool.h
@@ -0,0 +1,47 @@
+#ifndef __PERF_TOOL_H
+#define __PERF_TOOL_H
+
+#include <stdbool.h>
+
+struct perf_session;
+union perf_event;
+struct perf_evlist;
+struct perf_evsel;
+struct perf_sample;
+struct perf_tool;
+struct machine;
+
+typedef int (*event_sample)(struct perf_tool *tool, union perf_event *event,
+			    struct perf_sample *sample,
+			    struct perf_evsel *evsel, struct machine *machine);
+
+typedef int (*event_op)(struct perf_tool *tool, union perf_event *event,
+			struct perf_sample *sample, struct machine *machine);
+
+typedef int (*event_attr_op)(struct perf_tool *tool,
+			     union perf_event *event,
+			     struct perf_evlist **pevlist);
+
+typedef int (*event_op2)(struct perf_tool *tool, union perf_event *event,
+			 struct perf_session *session);
+
+struct perf_tool {
+	event_sample	sample,
+			read;
+	event_op	mmap,
+			mmap2,
+			comm,
+			fork,
+			exit,
+			lost,
+			throttle,
+			unthrottle;
+	event_attr_op	attr;
+	event_op2	tracing_data;
+	event_op2	finished_round,
+			build_id;
+	bool		ordered_samples;
+	bool		ordering_requires_timestamps;
+};
+
+#endif /* __PERF_TOOL_H */
diff --git a/tools/perf/util/top.c b/tools/perf/util/top.c
new file mode 100644
index 00000000000..8e517def925
--- /dev/null
+++ b/tools/perf/util/top.c
@@ -0,0 +1,117 @@
+/*
+ * Copyright (C) 2011, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Refactored from builtin-top.c, see that files for further copyright notes.
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+
+#include "cpumap.h"
+#include "event.h"
+#include "evlist.h"
+#include "evsel.h"
+#include "parse-events.h"
+#include "symbol.h"
+#include "top.h"
+#include <inttypes.h>
+
+#define SNPRINTF(buf, size, fmt, args...) \
+({ \
+	size_t r = snprintf(buf, size, fmt, ## args); \
+	r > size ?  size : r; \
+})
+
+size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size)
+{
+	float samples_per_sec;
+	float ksamples_per_sec;
+	float esamples_percent;
+	struct record_opts *opts = &top->record_opts;
+	struct 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,
+			       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;
+		float guest_us_samples_per_sec = top->guest_us_samples / top->delay_secs;
+
+		ret = SNPRINTF(bf, size,
+			       "   PerfTop:%8.0f irqs/sec  kernel:%4.1f%% us:%4.1f%%"
+			       " guest kernel:%4.1f%% guest us:%4.1f%%"
+			       " exact: %4.1f%% [", samples_per_sec,
+			       100.0 - (100.0 * ((samples_per_sec - ksamples_per_sec) /
+						 samples_per_sec)),
+			       100.0 - (100.0 * ((samples_per_sec - us_samples_per_sec) /
+						 samples_per_sec)),
+			       100.0 - (100.0 * ((samples_per_sec -
+						  guest_kernel_samples_per_sec) /
+						 samples_per_sec)),
+			       100.0 - (100.0 * ((samples_per_sec -
+						  guest_us_samples_per_sec) /
+						 samples_per_sec)),
+			       esamples_percent);
+	}
+
+	if (top->evlist->nr_entries == 1) {
+		struct perf_evsel *first = perf_evlist__first(top->evlist);
+		ret += SNPRINTF(bf + ret, size - ret, "%" PRIu64 "%s ",
+				(uint64_t)first->attr.sample_period,
+				opts->freq ? "Hz" : "");
+	}
+
+	ret += SNPRINTF(bf + ret, size - ret, "%s", perf_evsel__name(top->sym_evsel));
+
+	ret += SNPRINTF(bf + ret, size - ret, "], ");
+
+	if (target->pid)
+		ret += SNPRINTF(bf + ret, size - ret, " (target_pid: %s",
+				target->pid);
+	else if (target->tid)
+		ret += SNPRINTF(bf + ret, size - ret, " (target_tid: %s",
+				target->tid);
+	else if (target->uid_str != NULL)
+		ret += SNPRINTF(bf + ret, size - ret, " (uid: %s",
+				target->uid_str);
+	else
+		ret += SNPRINTF(bf + ret, size - ret, " (all");
+
+	if (target->cpu_list)
+		ret += SNPRINTF(bf + ret, size - ret, ", CPU%s: %s)",
+				top->evlist->cpus->nr > 1 ? "s" : "",
+				target->cpu_list);
+	else {
+		if (target->tid)
+			ret += SNPRINTF(bf + ret, size - ret, ")");
+		else
+			ret += SNPRINTF(bf + ret, size - ret, ", %d CPU%s)",
+					top->evlist->cpus->nr,
+					top->evlist->cpus->nr > 1 ? "s" : "");
+	}
+
+	return ret;
+}
+
+void perf_top__reset_sample_counters(struct perf_top *top)
+{
+	top->samples = top->us_samples = top->kernel_samples =
+	top->exact_samples = top->guest_kernel_samples =
+	top->guest_us_samples = 0;
+}
diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h
new file mode 100644
index 00000000000..f92c37abb0a
--- /dev/null
+++ b/tools/perf/util/top.h
@@ -0,0 +1,47 @@
+#ifndef __PERF_TOP_H
+#define __PERF_TOP_H 1
+
+#include "tool.h"
+#include <linux/types.h>
+#include <stddef.h>
+#include <stdbool.h>
+#include <termios.h>
+
+struct perf_evlist;
+struct perf_evsel;
+struct perf_session;
+
+struct perf_top {
+	struct perf_tool   tool;
+	struct perf_evlist *evlist;
+	struct record_opts record_opts;
+	/*
+	 * Symbols will be added here in perf_event__process_sample and will
+	 * get out after decayed.
+	 */
+	u64		   samples;
+	u64		   kernel_samples, us_samples;
+	u64		   exact_samples;
+	u64		   guest_us_samples, guest_kernel_samples;
+	int		   print_entries, count_filter, delay_secs;
+	int		   max_stack;
+	bool		   hide_kernel_symbols, hide_user_symbols, zero;
+	bool		   use_tui, use_stdio;
+	bool		   kptr_restrict_warned;
+	bool		   vmlinux_warned;
+	bool		   dump_symtab;
+	struct hist_entry  *sym_filter_entry;
+	struct perf_evsel  *sym_evsel;
+	struct perf_session *session;
+	struct winsize	   winsize;
+	int		   realtime_prio;
+	int		   sym_pcnt_filter;
+	const char	   *sym_filter;
+	float		   min_percent;
+};
+
+#define CONSOLE_CLEAR ""
+
+size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size);
+void perf_top__reset_sample_counters(struct perf_top *top);
+#endif /* __PERF_TOP_H */
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index b1572601286..7e6fcfe8b43 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -18,7 +18,7 @@
  *
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
-#define _GNU_SOURCE
+#include "util.h"
 #include <dirent.h>
 #include <mntent.h>
 #include <stdio.h>
@@ -31,146 +31,20 @@
 #include <pthread.h>
 #include <fcntl.h>
 #include <unistd.h>
-#include <ctype.h>
 #include <errno.h>
 #include <stdbool.h>
+#include <linux/list.h>
 #include <linux/kernel.h>
 
 #include "../perf.h"
 #include "trace-event.h"
-#include "debugfs.h"
+#include <api/fs/debugfs.h>
+#include "evsel.h"
 
 #define VERSION "0.5"
 
-#define _STR(x) #x
-#define STR(x) _STR(x)
-#define MAX_PATH 256
-
-#define TRACE_CTRL	"tracing_on"
-#define TRACE		"trace"
-#define AVAILABLE	"available_tracers"
-#define CURRENT		"current_tracer"
-#define ITER_CTRL	"trace_options"
-#define MAX_LATENCY	"tracing_max_latency"
-
-unsigned int page_size;
-
-static const char *output_file = "trace.info";
 static int output_fd;
 
-struct event_list {
-	struct event_list *next;
-	const char *event;
-};
-
-struct events {
-	struct events *sibling;
-	struct events *children;
-	struct events *next;
-	char *name;
-};
-
-
-
-static void die(const char *fmt, ...)
-{
-	va_list ap;
-	int ret = errno;
-
-	if (errno)
-		perror("trace-cmd");
-	else
-		ret = -1;
-
-	va_start(ap, fmt);
-	fprintf(stderr, "  ");
-	vfprintf(stderr, fmt, ap);
-	va_end(ap);
-
-	fprintf(stderr, "\n");
-	exit(ret);
-}
-
-void *malloc_or_die(unsigned int size)
-{
-	void *data;
-
-	data = malloc(size);
-	if (!data)
-		die("malloc");
-	return data;
-}
-
-static const char *find_debugfs(void)
-{
-	const char *path = debugfs_mount(NULL);
-
-	if (!path)
-		die("Your kernel not support debugfs filesystem");
-
-	return path;
-}
-
-/*
- * Finds the path to the debugfs/tracing
- * Allocates the string and stores it.
- */
-static const char *find_tracing_dir(void)
-{
-	static char *tracing;
-	static int tracing_found;
-	const char *debugfs;
-
-	if (tracing_found)
-		return tracing;
-
-	debugfs = find_debugfs();
-
-	tracing = malloc_or_die(strlen(debugfs) + 9);
-
-	sprintf(tracing, "%s/tracing", debugfs);
-
-	tracing_found = 1;
-	return tracing;
-}
-
-static char *get_tracing_file(const char *name)
-{
-	const char *tracing;
-	char *file;
-
-	tracing = find_tracing_dir();
-	if (!tracing)
-		return NULL;
-
-	file = malloc_or_die(strlen(tracing) + strlen(name) + 2);
-
-	sprintf(file, "%s/%s", tracing, name);
-	return file;
-}
-
-static void put_tracing_file(char *file)
-{
-	free(file);
-}
-
-static ssize_t calc_data_size;
-
-static ssize_t write_or_die(const void *buf, size_t len)
-{
-	int ret;
-
-	if (calc_data_size) {
-		calc_data_size += len;
-		return len;
-	}
-
-	ret = write(output_fd, buf, len);
-	if (ret < 0)
-		die("writing to '%s'", output_file);
-
-	return ret;
-}
 
 int bigendian(void)
 {
@@ -181,106 +55,107 @@ int bigendian(void)
 	return *ptr == 0x01020304;
 }
 
-static unsigned long long copy_file_fd(int fd)
+/* unfortunately, you can not stat debugfs or proc files for size */
+static int record_file(const char *file, ssize_t hdr_sz)
 {
 	unsigned long long size = 0;
-	char buf[BUFSIZ];
-	int r;
-
-	do {
-		r = read(fd, buf, BUFSIZ);
-		if (r > 0) {
-			size += r;
-			write_or_die(buf, r);
-		}
-	} while (r > 0);
-
-	return size;
-}
-
-static unsigned long long copy_file(const char *file)
-{
-	unsigned long long size = 0;
-	int fd;
+	char buf[BUFSIZ], *sizep;
+	off_t hdr_pos = lseek(output_fd, 0, SEEK_CUR);
+	int r, fd;
+	int err = -EIO;
 
 	fd = open(file, O_RDONLY);
-	if (fd < 0)
-		die("Can't read '%s'", file);
-	size = copy_file_fd(fd);
-	close(fd);
-
-	return size;
-}
+	if (fd < 0) {
+		pr_debug("Can't read '%s'", file);
+		return -errno;
+	}
 
-static unsigned long get_size_fd(int fd)
-{
-	unsigned long long size = 0;
-	char buf[BUFSIZ];
-	int r;
+	/* put in zeros for file size, then fill true size later */
+	if (hdr_sz) {
+		if (write(output_fd, &size, hdr_sz) != hdr_sz)
+			goto out;
+	}
 
 	do {
 		r = read(fd, buf, BUFSIZ);
-		if (r > 0)
+		if (r > 0) {
 			size += r;
+			if (write(output_fd, buf, r) != r)
+				goto out;
+		}
 	} while (r > 0);
 
-	lseek(fd, 0, SEEK_SET);
-
-	return size;
-}
+	/* ugh, handle big-endian hdr_size == 4 */
+	sizep = (char*)&size;
+	if (bigendian())
+		sizep += sizeof(u64) - hdr_sz;
 
-static unsigned long get_size(const char *file)
-{
-	unsigned long long size = 0;
-	int fd;
+	if (hdr_sz && pwrite(output_fd, sizep, hdr_sz, hdr_pos) < 0) {
+		pr_debug("writing file size failed\n");
+		goto out;
+	}
 
-	fd = open(file, O_RDONLY);
-	if (fd < 0)
-		die("Can't read '%s'", file);
-	size = get_size_fd(fd);
+	err = 0;
+out:
 	close(fd);
-
-	return size;
+	return err;
 }
 
-static void read_header_files(void)
+static int record_header_files(void)
 {
-	unsigned long long size, check_size;
 	char *path;
-	int fd;
+	struct stat st;
+	int err = -EIO;
 
 	path = get_tracing_file("events/header_page");
-	fd = open(path, O_RDONLY);
-	if (fd < 0)
-		die("can't read '%s'", path);
+	if (!path) {
+		pr_debug("can't get tracing/events/header_page");
+		return -ENOMEM;
+	}
+
+	if (stat(path, &st) < 0) {
+		pr_debug("can't read '%s'", path);
+		goto out;
+	}
 
-	/* unfortunately, you can not stat debugfs files for size */
-	size = get_size_fd(fd);
+	if (write(output_fd, "header_page", 12) != 12) {
+		pr_debug("can't write header_page\n");
+		goto out;
+	}
 
-	write_or_die("header_page", 12);
-	write_or_die(&size, 8);
-	check_size = copy_file_fd(fd);
-	close(fd);
+	if (record_file(path, 8) < 0) {
+		pr_debug("can't record header_page file\n");
+		goto out;
+	}
 
-	if (size != check_size)
-		die("wrong size for '%s' size=%lld read=%lld",
-		    path, size, check_size);
 	put_tracing_file(path);
 
 	path = get_tracing_file("events/header_event");
-	fd = open(path, O_RDONLY);
-	if (fd < 0)
-		die("can't read '%s'", path);
+	if (!path) {
+		pr_debug("can't get tracing/events/header_event");
+		err = -ENOMEM;
+		goto out;
+	}
 
-	size = get_size_fd(fd);
+	if (stat(path, &st) < 0) {
+		pr_debug("can't read '%s'", path);
+		goto out;
+	}
 
-	write_or_die("header_event", 13);
-	write_or_die(&size, 8);
-	check_size = copy_file_fd(fd);
-	if (size != check_size)
-		die("wrong size for '%s'", path);
+	if (write(output_fd, "header_event", 13) != 13) {
+		pr_debug("can't write header_event\n");
+		goto out;
+	}
+
+	if (record_file(path, 8) < 0) {
+		pr_debug("can't record header_event file\n");
+		goto out;
+	}
+
+	err = 0;
+out:
 	put_tracing_file(path);
-	close(fd);
+	return err;
 }
 
 static bool name_in_tp_list(char *sys, struct tracepoint_path *tps)
@@ -294,19 +169,21 @@ static bool name_in_tp_list(char *sys, struct tracepoint_path *tps)
 	return false;
 }
 
-static void copy_event_system(const char *sys, struct tracepoint_path *tps)
+static int copy_event_system(const char *sys, struct tracepoint_path *tps)
 {
-	unsigned long long size, check_size;
 	struct dirent *dent;
 	struct stat st;
 	char *format;
 	DIR *dir;
 	int count = 0;
 	int ret;
+	int err;
 
 	dir = opendir(sys);
-	if (!dir)
-		die("can't read directory '%s'", sys);
+	if (!dir) {
+		pr_debug("can't read directory '%s'", sys);
+		return -errno;
+	}
 
 	while ((dent = readdir(dir))) {
 		if (dent->d_type != DT_DIR ||
@@ -314,7 +191,11 @@ static void copy_event_system(const char *sys, struct tracepoint_path *tps)
 		    strcmp(dent->d_name, "..") == 0 ||
 		    !name_in_tp_list(dent->d_name, tps))
 			continue;
-		format = malloc_or_die(strlen(sys) + strlen(dent->d_name) + 10);
+		format = malloc(strlen(sys) + strlen(dent->d_name) + 10);
+		if (!format) {
+			err = -ENOMEM;
+			goto out;
+		}
 		sprintf(format, "%s/%s/format", sys, dent->d_name);
 		ret = stat(format, &st);
 		free(format);
@@ -323,7 +204,11 @@ static void copy_event_system(const char *sys, struct tracepoint_path *tps)
 		count++;
 	}
 
-	write_or_die(&count, 4);
+	if (write(output_fd, &count, 4) != 4) {
+		err = -EIO;
+		pr_debug("can't write count\n");
+		goto out;
+	}
 
 	rewinddir(dir);
 	while ((dent = readdir(dir))) {
@@ -332,33 +217,45 @@ static void copy_event_system(const char *sys, struct tracepoint_path *tps)
 		    strcmp(dent->d_name, "..") == 0 ||
 		    !name_in_tp_list(dent->d_name, tps))
 			continue;
-		format = malloc_or_die(strlen(sys) + strlen(dent->d_name) + 10);
+		format = malloc(strlen(sys) + strlen(dent->d_name) + 10);
+		if (!format) {
+			err = -ENOMEM;
+			goto out;
+		}
 		sprintf(format, "%s/%s/format", sys, dent->d_name);
 		ret = stat(format, &st);
 
 		if (ret >= 0) {
-			/* unfortunately, you can not stat debugfs files for size */
-			size = get_size(format);
-			write_or_die(&size, 8);
-			check_size = copy_file(format);
-			if (size != check_size)
-				die("error in size of file '%s'", format);
+			err = record_file(format, 8);
+			if (err) {
+				free(format);
+				goto out;
+			}
 		}
-
 		free(format);
 	}
+	err = 0;
+out:
 	closedir(dir);
+	return err;
 }
 
-static void read_ftrace_files(struct tracepoint_path *tps)
+static int record_ftrace_files(struct tracepoint_path *tps)
 {
 	char *path;
+	int ret;
 
 	path = get_tracing_file("events/ftrace");
+	if (!path) {
+		pr_debug("can't get tracing/events/ftrace");
+		return -ENOMEM;
+	}
 
-	copy_event_system(path, tps);
+	ret = copy_event_system(path, tps);
 
 	put_tracing_file(path);
+
+	return ret;
 }
 
 static bool system_in_tp_list(char *sys, struct tracepoint_path *tps)
@@ -372,7 +269,7 @@ static bool system_in_tp_list(char *sys, struct tracepoint_path *tps)
 	return false;
 }
 
-static void read_event_files(struct tracepoint_path *tps)
+static int record_event_files(struct tracepoint_path *tps)
 {
 	struct dirent *dent;
 	struct stat st;
@@ -381,12 +278,20 @@ static void read_event_files(struct tracepoint_path *tps)
 	DIR *dir;
 	int count = 0;
 	int ret;
+	int err;
 
 	path = get_tracing_file("events");
+	if (!path) {
+		pr_debug("can't get tracing/events");
+		return -ENOMEM;
+	}
 
 	dir = opendir(path);
-	if (!dir)
-		die("can't read directory '%s'", path);
+	if (!dir) {
+		err = -errno;
+		pr_debug("can't read directory '%s'", path);
+		goto out;
+	}
 
 	while ((dent = readdir(dir))) {
 		if (dent->d_type != DT_DIR ||
@@ -398,7 +303,11 @@ static void read_event_files(struct tracepoint_path *tps)
 		count++;
 	}
 
-	write_or_die(&count, 4);
+	if (write(output_fd, &count, 4) != 4) {
+		err = -EIO;
+		pr_debug("can't write count\n");
+		goto out;
+	}
 
 	rewinddir(dir);
 	while ((dent = readdir(dir))) {
@@ -408,117 +317,158 @@ static void read_event_files(struct tracepoint_path *tps)
 		    strcmp(dent->d_name, "ftrace") == 0 ||
 		    !system_in_tp_list(dent->d_name, tps))
 			continue;
-		sys = malloc_or_die(strlen(path) + strlen(dent->d_name) + 2);
+		sys = malloc(strlen(path) + strlen(dent->d_name) + 2);
+		if (!sys) {
+			err = -ENOMEM;
+			goto out;
+		}
 		sprintf(sys, "%s/%s", path, dent->d_name);
 		ret = stat(sys, &st);
 		if (ret >= 0) {
-			write_or_die(dent->d_name, strlen(dent->d_name) + 1);
-			copy_event_system(sys, tps);
+			ssize_t size = strlen(dent->d_name) + 1;
+
+			if (write(output_fd, dent->d_name, size) != size ||
+			    copy_event_system(sys, tps) < 0) {
+				err = -EIO;
+				free(sys);
+				goto out;
+			}
 		}
 		free(sys);
 	}
-
+	err = 0;
+out:
 	closedir(dir);
 	put_tracing_file(path);
+
+	return err;
 }
 
-static void read_proc_kallsyms(void)
+static int record_proc_kallsyms(void)
 {
-	unsigned int size, check_size;
+	unsigned int size;
 	const char *path = "/proc/kallsyms";
 	struct stat st;
-	int ret;
+	int ret, err = 0;
 
 	ret = stat(path, &st);
 	if (ret < 0) {
 		/* not found */
 		size = 0;
-		write_or_die(&size, 4);
-		return;
+		if (write(output_fd, &size, 4) != 4)
+			err = -EIO;
+		return err;
 	}
-	size = get_size(path);
-	write_or_die(&size, 4);
-	check_size = copy_file(path);
-	if (size != check_size)
-		die("error in size of file '%s'", path);
-
+	return record_file(path, 4);
 }
 
-static void read_ftrace_printk(void)
+static int record_ftrace_printk(void)
 {
-	unsigned int size, check_size;
+	unsigned int size;
 	char *path;
 	struct stat st;
-	int ret;
+	int ret, err = 0;
 
 	path = get_tracing_file("printk_formats");
+	if (!path) {
+		pr_debug("can't get tracing/printk_formats");
+		return -ENOMEM;
+	}
+
 	ret = stat(path, &st);
 	if (ret < 0) {
 		/* not found */
 		size = 0;
-		write_or_die(&size, 4);
+		if (write(output_fd, &size, 4) != 4)
+			err = -EIO;
 		goto out;
 	}
-	size = get_size(path);
-	write_or_die(&size, 4);
-	check_size = copy_file(path);
-	if (size != check_size)
-		die("error in size of file '%s'", path);
+	err = record_file(path, 4);
+
 out:
 	put_tracing_file(path);
+	return err;
+}
+
+static void
+put_tracepoints_path(struct tracepoint_path *tps)
+{
+	while (tps) {
+		struct tracepoint_path *t = tps;
+
+		tps = tps->next;
+		zfree(&t->name);
+		zfree(&t->system);
+		free(t);
+	}
 }
 
 static struct tracepoint_path *
-get_tracepoints_path(struct perf_event_attr *pattrs, int nb_events)
+get_tracepoints_path(struct list_head *pattrs)
 {
 	struct tracepoint_path path, *ppath = &path;
-	int i, nr_tracepoints = 0;
+	struct perf_evsel *pos;
+	int nr_tracepoints = 0;
 
-	for (i = 0; i < nb_events; i++) {
-		if (pattrs[i].type != PERF_TYPE_TRACEPOINT)
+	list_for_each_entry(pos, pattrs, node) {
+		if (pos->attr.type != PERF_TYPE_TRACEPOINT)
 			continue;
 		++nr_tracepoints;
-		ppath->next = tracepoint_id_to_path(pattrs[i].config);
-		if (!ppath->next)
-			die("%s\n", "No memory to alloc tracepoints list");
+
+		if (pos->name) {
+			ppath->next = tracepoint_name_to_path(pos->name);
+			if (ppath->next)
+				goto next;
+
+			if (strchr(pos->name, ':') == NULL)
+				goto try_id;
+
+			goto error;
+		}
+
+try_id:
+		ppath->next = tracepoint_id_to_path(pos->attr.config);
+		if (!ppath->next) {
+error:
+			pr_debug("No memory to alloc tracepoints list\n");
+			put_tracepoints_path(&path);
+			return NULL;
+		}
+next:
 		ppath = ppath->next;
 	}
 
 	return nr_tracepoints > 0 ? path.next : NULL;
 }
 
-bool have_tracepoints(struct perf_event_attr *pattrs, int nb_events)
+bool have_tracepoints(struct list_head *pattrs)
 {
-	int i;
+	struct perf_evsel *pos;
 
-	for (i = 0; i < nb_events; i++)
-		if (pattrs[i].type == PERF_TYPE_TRACEPOINT)
+	list_for_each_entry(pos, pattrs, node)
+		if (pos->attr.type == PERF_TYPE_TRACEPOINT)
 			return true;
 
 	return false;
 }
 
-int read_tracing_data(int fd, struct perf_event_attr *pattrs, int nb_events)
+static int tracing_data_header(void)
 {
-	char buf[BUFSIZ];
-	struct tracepoint_path *tps = get_tracepoints_path(pattrs, nb_events);
-
-	/*
-	 * What? No tracepoints? No sense writing anything here, bail out.
-	 */
-	if (tps == NULL)
-		return -1;
-
-	output_fd = fd;
+	char buf[20];
+	ssize_t size;
 
+	/* just guessing this is someone's birthday.. ;) */
 	buf[0] = 23;
 	buf[1] = 8;
 	buf[2] = 68;
 	memcpy(buf + 3, "tracing", 7);
 
-	write_or_die(buf, 10);
+	if (write(output_fd, buf, 10) != 10)
+		return -1;
 
-	write_or_die(VERSION, strlen(VERSION) + 1);
+	size = strlen(VERSION) + 1;
+	if (write(output_fd, VERSION, size) != size)
+		return -1;
 
 	/* save endian */
 	if (bigendian())
@@ -526,38 +476,125 @@ int read_tracing_data(int fd, struct perf_event_attr *pattrs, int nb_events)
 	else
 		buf[0] = 0;
 
-	write_or_die(buf, 1);
+	if (write(output_fd, buf, 1) != 1)
+		return -1;
 
 	/* save size of long */
 	buf[0] = sizeof(long);
-	write_or_die(buf, 1);
+	if (write(output_fd, buf, 1) != 1)
+		return -1;
 
 	/* save page_size */
-	page_size = sysconf(_SC_PAGESIZE);
-	write_or_die(&page_size, 4);
-
-	read_header_files();
-	read_ftrace_files(tps);
-	read_event_files(tps);
-	read_proc_kallsyms();
-	read_ftrace_printk();
+	if (write(output_fd, &page_size, 4) != 4)
+		return -1;
 
 	return 0;
 }
 
-ssize_t read_tracing_data_size(int fd, struct perf_event_attr *pattrs,
-			       int nb_events)
+struct tracing_data *tracing_data_get(struct list_head *pattrs,
+				      int fd, bool temp)
+{
+	struct tracepoint_path *tps;
+	struct tracing_data *tdata;
+	int err;
+
+	output_fd = fd;
+
+	tps = get_tracepoints_path(pattrs);
+	if (!tps)
+		return NULL;
+
+	tdata = malloc(sizeof(*tdata));
+	if (!tdata)
+		return NULL;
+
+	tdata->temp = temp;
+	tdata->size = 0;
+
+	if (temp) {
+		int temp_fd;
+
+		snprintf(tdata->temp_file, sizeof(tdata->temp_file),
+			 "/tmp/perf-XXXXXX");
+		if (!mkstemp(tdata->temp_file)) {
+			pr_debug("Can't make temp file");
+			return NULL;
+		}
+
+		temp_fd = open(tdata->temp_file, O_RDWR);
+		if (temp_fd < 0) {
+			pr_debug("Can't read '%s'", tdata->temp_file);
+			return NULL;
+		}
+
+		/*
+		 * Set the temp file the default output, so all the
+		 * tracing data are stored into it.
+		 */
+		output_fd = temp_fd;
+	}
+
+	err = tracing_data_header();
+	if (err)
+		goto out;
+	err = record_header_files();
+	if (err)
+		goto out;
+	err = record_ftrace_files(tps);
+	if (err)
+		goto out;
+	err = record_event_files(tps);
+	if (err)
+		goto out;
+	err = record_proc_kallsyms();
+	if (err)
+		goto out;
+	err = record_ftrace_printk();
+
+out:
+	/*
+	 * All tracing data are stored by now, we can restore
+	 * the default output file in case we used temp file.
+	 */
+	if (temp) {
+		tdata->size = lseek(output_fd, 0, SEEK_CUR);
+		close(output_fd);
+		output_fd = fd;
+	}
+
+	if (err)
+		zfree(&tdata);
+
+	put_tracepoints_path(tps);
+	return tdata;
+}
+
+int tracing_data_put(struct tracing_data *tdata)
 {
-	ssize_t size;
 	int err = 0;
 
-	calc_data_size = 1;
-	err = read_tracing_data(fd, pattrs, nb_events);
-	size = calc_data_size - 1;
-	calc_data_size = 0;
+	if (tdata->temp) {
+		err = record_file(tdata->temp_file, 0);
+		unlink(tdata->temp_file);
+	}
 
-	if (err < 0)
-		return err;
+	free(tdata);
+	return err;
+}
+
+int read_tracing_data(int fd, struct list_head *pattrs)
+{
+	int err;
+	struct tracing_data *tdata;
+
+	/*
+	 * We work over the real file, so we can write data
+	 * directly, no temp file is needed.
+	 */
+	tdata = tracing_data_get(pattrs, fd, false);
+	if (!tdata)
+		return -ENOMEM;
 
-	return size;
+	err = tracing_data_put(tdata);
+	return err;
 }
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index 73a02223c62..c36636fd825 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -17,2161 +17,211 @@
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  *
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- *
- *  The parts for function graph printing was taken and modified from the
- *  Linux Kernel that were written by Frederic Weisbecker.
  */
-#define _GNU_SOURCE
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
 #include <ctype.h>
 #include <errno.h>
 
-#undef _GNU_SOURCE
 #include "../perf.h"
 #include "util.h"
 #include "trace-event.h"
 
-int header_page_ts_offset;
-int header_page_ts_size;
-int header_page_size_offset;
-int header_page_size_size;
-int header_page_overwrite_offset;
-int header_page_overwrite_size;
-int header_page_data_offset;
-int header_page_data_size;
-
-bool latency_format;
-
-static char *input_buf;
-static unsigned long long input_buf_ptr;
-static unsigned long long input_buf_siz;
-
-static int cpus;
-static int long_size;
-static int is_flag_field;
-static int is_symbolic_field;
-
-static struct format_field *
-find_any_field(struct event *event, const char *name);
-
-static void init_input_buf(char *buf, unsigned long long size)
-{
-	input_buf = buf;
-	input_buf_siz = size;
-	input_buf_ptr = 0;
-}
-
-struct cmdline {
-	char *comm;
-	int pid;
-};
-
-static struct cmdline *cmdlines;
-static int cmdline_count;
-
-static int cmdline_cmp(const void *a, const void *b)
-{
-	const struct cmdline *ca = a;
-	const struct cmdline *cb = b;
-
-	if (ca->pid < cb->pid)
-		return -1;
-	if (ca->pid > cb->pid)
-		return 1;
-
-	return 0;
-}
-
-void parse_cmdlines(char *file, int size __unused)
+static int get_common_field(struct scripting_context *context,
+			    int *offset, int *size, const char *type)
 {
-	struct cmdline_list {
-		struct cmdline_list	*next;
-		char			*comm;
-		int			pid;
-	} *list = NULL, *item;
-	char *line;
-	char *next = NULL;
-	int i;
-
-	line = strtok_r(file, "\n", &next);
-	while (line) {
-		item = malloc_or_die(sizeof(*item));
-		sscanf(line, "%d %as", &item->pid,
-		       (float *)(void *)&item->comm); /* workaround gcc warning */
-		item->next = list;
-		list = item;
-		line = strtok_r(NULL, "\n", &next);
-		cmdline_count++;
-	}
+	struct pevent *pevent = context->pevent;
+	struct event_format *event;
+	struct format_field *field;
 
-	cmdlines = malloc_or_die(sizeof(*cmdlines) * cmdline_count);
+	if (!*size) {
+		if (!pevent->events)
+			return 0;
 
-	i = 0;
-	while (list) {
-		cmdlines[i].pid = list->pid;
-		cmdlines[i].comm = list->comm;
-		i++;
-		item = list;
-		list = list->next;
-		free(item);
+		event = pevent->events[0];
+		field = pevent_find_common_field(event, type);
+		if (!field)
+			return 0;
+		*offset = field->offset;
+		*size = field->size;
 	}
 
-	qsort(cmdlines, cmdline_count, sizeof(*cmdlines), cmdline_cmp);
+	return pevent_read_number(pevent, context->event_data + *offset, *size);
 }
 
-static struct func_map {
-	unsigned long long		addr;
-	char				*func;
-	char				*mod;
-} *func_list;
-static unsigned int func_count;
-
-static int func_cmp(const void *a, const void *b)
+int common_lock_depth(struct scripting_context *context)
 {
-	const struct func_map *fa = a;
-	const struct func_map *fb = b;
+	static int offset;
+	static int size;
+	int ret;
 
-	if (fa->addr < fb->addr)
+	ret = get_common_field(context, &size, &offset,
+			       "common_lock_depth");
+	if (ret < 0)
 		return -1;
-	if (fa->addr > fb->addr)
-		return 1;
 
-	return 0;
+	return ret;
 }
 
-void parse_proc_kallsyms(char *file, unsigned int size __unused)
+int common_flags(struct scripting_context *context)
 {
-	struct func_list {
-		struct func_list	*next;
-		unsigned long long	addr;
-		char			*func;
-		char			*mod;
-	} *list = NULL, *item;
-	char *line;
-	char *next = NULL;
-	char *addr_str;
-	char ch;
+	static int offset;
+	static int size;
 	int ret;
-	int i;
-
-	line = strtok_r(file, "\n", &next);
-	while (line) {
-		item = malloc_or_die(sizeof(*item));
-		item->mod = NULL;
-		ret = sscanf(line, "%as %c %as\t[%as",
-			     (float *)(void *)&addr_str, /* workaround gcc warning */
-			     &ch,
-			     (float *)(void *)&item->func,
-			     (float *)(void *)&item->mod);
-		item->addr = strtoull(addr_str, NULL, 16);
-		free(addr_str);
-
-		/* truncate the extra ']' */
-		if (item->mod)
-			item->mod[strlen(item->mod) - 1] = 0;
 
+	ret = get_common_field(context, &size, &offset,
+			       "common_flags");
+	if (ret < 0)
+		return -1;
 
-		item->next = list;
-		list = item;
-		line = strtok_r(NULL, "\n", &next);
-		func_count++;
-	}
-
-	func_list = malloc_or_die(sizeof(*func_list) * (func_count + 1));
-
-	i = 0;
-	while (list) {
-		func_list[i].func = list->func;
-		func_list[i].addr = list->addr;
-		func_list[i].mod = list->mod;
-		i++;
-		item = list;
-		list = list->next;
-		free(item);
-	}
-
-	qsort(func_list, func_count, sizeof(*func_list), func_cmp);
-
-	/*
-	 * Add a special record at the end.
-	 */
-	func_list[func_count].func = NULL;
-	func_list[func_count].addr = 0;
-	func_list[func_count].mod = NULL;
+	return ret;
 }
 
-/*
- * We are searching for a record in between, not an exact
- * match.
- */
-static int func_bcmp(const void *a, const void *b)
+int common_pc(struct scripting_context *context)
 {
-	const struct func_map *fa = a;
-	const struct func_map *fb = b;
-
-	if ((fa->addr == fb->addr) ||
-
-	    (fa->addr > fb->addr &&
-	     fa->addr < (fb+1)->addr))
-		return 0;
+	static int offset;
+	static int size;
+	int ret;
 
-	if (fa->addr < fb->addr)
+	ret = get_common_field(context, &size, &offset,
+			       "common_preempt_count");
+	if (ret < 0)
 		return -1;
 
-	return 1;
+	return ret;
 }
 
-static struct func_map *find_func(unsigned long long addr)
+unsigned long long
+raw_field_value(struct event_format *event, const char *name, void *data)
 {
-	struct func_map *func;
-	struct func_map key;
+	struct format_field *field;
+	unsigned long long val;
 
-	key.addr = addr;
+	field = pevent_find_any_field(event, name);
+	if (!field)
+		return 0ULL;
 
-	func = bsearch(&key, func_list, func_count, sizeof(*func_list),
-		       func_bcmp);
+	pevent_read_number_field(field, data, &val);
 
-	return func;
+	return val;
 }
 
-void print_funcs(void)
+unsigned long long read_size(struct event_format *event, void *ptr, int size)
 {
-	int i;
-
-	for (i = 0; i < (int)func_count; i++) {
-		printf("%016llx %s",
-		       func_list[i].addr,
-		       func_list[i].func);
-		if (func_list[i].mod)
-			printf(" [%s]\n", func_list[i].mod);
-		else
-			printf("\n");
-	}
+	return pevent_read_number(event->pevent, ptr, size);
 }
 
-static struct printk_map {
-	unsigned long long		addr;
-	char				*printk;
-} *printk_list;
-static unsigned int printk_count;
-
-static int printk_cmp(const void *a, const void *b)
+void event_format__print(struct event_format *event,
+			 int cpu, void *data, int size)
 {
-	const struct func_map *fa = a;
-	const struct func_map *fb = b;
+	struct pevent_record record;
+	struct trace_seq s;
 
-	if (fa->addr < fb->addr)
-		return -1;
-	if (fa->addr > fb->addr)
-		return 1;
+	memset(&record, 0, sizeof(record));
+	record.cpu = cpu;
+	record.size = size;
+	record.data = data;
 
-	return 0;
+	trace_seq_init(&s);
+	pevent_event_info(&s, event, &record);
+	trace_seq_do_printf(&s);
+	trace_seq_destroy(&s);
 }
 
-static struct printk_map *find_printk(unsigned long long addr)
+void parse_proc_kallsyms(struct pevent *pevent,
+			 char *file, unsigned int size __maybe_unused)
 {
-	struct printk_map *printk;
-	struct printk_map key;
-
-	key.addr = addr;
+	unsigned long long addr;
+	char *func;
+	char *line;
+	char *next = NULL;
+	char *addr_str;
+	char *mod;
+	char *fmt = NULL;
 
-	printk = bsearch(&key, printk_list, printk_count, sizeof(*printk_list),
-			 printk_cmp);
+	line = strtok_r(file, "\n", &next);
+	while (line) {
+		mod = NULL;
+		addr_str = strtok_r(line, " ", &fmt);
+		addr = strtoull(addr_str, NULL, 16);
+		/* skip character */
+		strtok_r(NULL, " ", &fmt);
+		func = strtok_r(NULL, "\t", &fmt);
+		mod = strtok_r(NULL, "]", &fmt);
+		/* truncate the extra '[' */
+		if (mod)
+			mod = mod + 1;
+
+		pevent_register_function(pevent, func, addr, mod);
 
-	return printk;
+		line = strtok_r(NULL, "\n", &next);
+	}
 }
 
-void parse_ftrace_printk(char *file, unsigned int size __unused)
+void parse_ftrace_printk(struct pevent *pevent,
+			 char *file, unsigned int size __maybe_unused)
 {
-	struct printk_list {
-		struct printk_list	*next;
-		unsigned long long	addr;
-		char			*printk;
-	} *list = NULL, *item;
+	unsigned long long addr;
+	char *printk;
 	char *line;
 	char *next = NULL;
 	char *addr_str;
-	int i;
+	char *fmt;
 
 	line = strtok_r(file, "\n", &next);
 	while (line) {
-		addr_str = strsep(&line, ":");
-		if (!line) {
-			warning("error parsing print strings");
+		addr_str = strtok_r(line, ":", &fmt);
+		if (!addr_str) {
+			warning("printk format with empty entry");
 			break;
 		}
-		item = malloc_or_die(sizeof(*item));
-		item->addr = strtoull(addr_str, NULL, 16);
+		addr = strtoull(addr_str, NULL, 16);
 		/* fmt still has a space, skip it */
-		item->printk = strdup(line+1);
-		item->next = list;
-		list = item;
+		printk = strdup(fmt+1);
 		line = strtok_r(NULL, "\n", &next);
-		printk_count++;
-	}
-
-	printk_list = malloc_or_die(sizeof(*printk_list) * printk_count + 1);
-
-	i = 0;
-	while (list) {
-		printk_list[i].printk = list->printk;
-		printk_list[i].addr = list->addr;
-		i++;
-		item = list;
-		list = list->next;
-		free(item);
-	}
-
-	qsort(printk_list, printk_count, sizeof(*printk_list), printk_cmp);
-}
-
-void print_printk(void)
-{
-	int i;
-
-	for (i = 0; i < (int)printk_count; i++) {
-		printf("%016llx %s\n",
-		       printk_list[i].addr,
-		       printk_list[i].printk);
-	}
-}
-
-static struct event *alloc_event(void)
-{
-	struct event *event;
-
-	event = malloc_or_die(sizeof(*event));
-	memset(event, 0, sizeof(*event));
-
-	return event;
-}
-
-enum event_type {
-	EVENT_ERROR,
-	EVENT_NONE,
-	EVENT_SPACE,
-	EVENT_NEWLINE,
-	EVENT_OP,
-	EVENT_DELIM,
-	EVENT_ITEM,
-	EVENT_DQUOTE,
-	EVENT_SQUOTE,
-};
-
-static struct event *event_list;
-
-static void add_event(struct event *event)
-{
-	event->next = event_list;
-	event_list = event;
-}
-
-static int event_item_type(enum event_type type)
-{
-	switch (type) {
-	case EVENT_ITEM ... EVENT_SQUOTE:
-		return 1;
-	case EVENT_ERROR ... EVENT_DELIM:
-	default:
-		return 0;
-	}
-}
-
-static void free_arg(struct print_arg *arg)
-{
-	if (!arg)
-		return;
-
-	switch (arg->type) {
-	case PRINT_ATOM:
-		if (arg->atom.atom)
-			free(arg->atom.atom);
-		break;
-	case PRINT_NULL:
-	case PRINT_FIELD ... PRINT_OP:
-	default:
-		/* todo */
-		break;
-	}
-
-	free(arg);
-}
-
-static enum event_type get_type(int ch)
-{
-	if (ch == '\n')
-		return EVENT_NEWLINE;
-	if (isspace(ch))
-		return EVENT_SPACE;
-	if (isalnum(ch) || ch == '_')
-		return EVENT_ITEM;
-	if (ch == '\'')
-		return EVENT_SQUOTE;
-	if (ch == '"')
-		return EVENT_DQUOTE;
-	if (!isprint(ch))
-		return EVENT_NONE;
-	if (ch == '(' || ch == ')' || ch == ',')
-		return EVENT_DELIM;
-
-	return EVENT_OP;
-}
-
-static int __read_char(void)
-{
-	if (input_buf_ptr >= input_buf_siz)
-		return -1;
-
-	return input_buf[input_buf_ptr++];
-}
-
-static int __peek_char(void)
-{
-	if (input_buf_ptr >= input_buf_siz)
-		return -1;
-
-	return input_buf[input_buf_ptr];
-}
-
-static enum event_type __read_token(char **tok)
-{
-	char buf[BUFSIZ];
-	int ch, last_ch, quote_ch, next_ch;
-	int i = 0;
-	int tok_size = 0;
-	enum event_type type;
-
-	*tok = NULL;
-
-
-	ch = __read_char();
-	if (ch < 0)
-		return EVENT_NONE;
-
-	type = get_type(ch);
-	if (type == EVENT_NONE)
-		return type;
-
-	buf[i++] = ch;
-
-	switch (type) {
-	case EVENT_NEWLINE:
-	case EVENT_DELIM:
-		*tok = malloc_or_die(2);
-		(*tok)[0] = ch;
-		(*tok)[1] = 0;
-		return type;
-
-	case EVENT_OP:
-		switch (ch) {
-		case '-':
-			next_ch = __peek_char();
-			if (next_ch == '>') {
-				buf[i++] = __read_char();
-				break;
-			}
-			/* fall through */
-		case '+':
-		case '|':
-		case '&':
-		case '>':
-		case '<':
-			last_ch = ch;
-			ch = __peek_char();
-			if (ch != last_ch)
-				goto test_equal;
-			buf[i++] = __read_char();
-			switch (last_ch) {
-			case '>':
-			case '<':
-				goto test_equal;
-			default:
-				break;
-			}
-			break;
-		case '!':
-		case '=':
-			goto test_equal;
-		default: /* what should we do instead? */
-			break;
-		}
-		buf[i] = 0;
-		*tok = strdup(buf);
-		return type;
-
- test_equal:
-		ch = __peek_char();
-		if (ch == '=')
-			buf[i++] = __read_char();
-		break;
-
-	case EVENT_DQUOTE:
-	case EVENT_SQUOTE:
-		/* don't keep quotes */
-		i--;
-		quote_ch = ch;
-		last_ch = 0;
-		do {
-			if (i == (BUFSIZ - 1)) {
-				buf[i] = 0;
-				if (*tok) {
-					*tok = realloc(*tok, tok_size + BUFSIZ);
-					if (!*tok)
-						return EVENT_NONE;
-					strcat(*tok, buf);
-				} else
-					*tok = strdup(buf);
-
-				if (!*tok)
-					return EVENT_NONE;
-				tok_size += BUFSIZ;
-				i = 0;
-			}
-			last_ch = ch;
-			ch = __read_char();
-			buf[i++] = ch;
-			/* the '\' '\' will cancel itself */
-			if (ch == '\\' && last_ch == '\\')
-				last_ch = 0;
-		} while (ch != quote_ch || last_ch == '\\');
-		/* remove the last quote */
-		i--;
-		goto out;
-
-	case EVENT_ERROR ... EVENT_SPACE:
-	case EVENT_ITEM:
-	default:
-		break;
-	}
-
-	while (get_type(__peek_char()) == type) {
-		if (i == (BUFSIZ - 1)) {
-			buf[i] = 0;
-			if (*tok) {
-				*tok = realloc(*tok, tok_size + BUFSIZ);
-				if (!*tok)
-					return EVENT_NONE;
-				strcat(*tok, buf);
-			} else
-				*tok = strdup(buf);
-
-			if (!*tok)
-				return EVENT_NONE;
-			tok_size += BUFSIZ;
-			i = 0;
-		}
-		ch = __read_char();
-		buf[i++] = ch;
-	}
-
- out:
-	buf[i] = 0;
-	if (*tok) {
-		*tok = realloc(*tok, tok_size + i);
-		if (!*tok)
-			return EVENT_NONE;
-		strcat(*tok, buf);
-	} else
-		*tok = strdup(buf);
-	if (!*tok)
-		return EVENT_NONE;
-
-	return type;
-}
-
-static void free_token(char *tok)
-{
-	if (tok)
-		free(tok);
-}
-
-static enum event_type read_token(char **tok)
-{
-	enum event_type type;
-
-	for (;;) {
-		type = __read_token(tok);
-		if (type != EVENT_SPACE)
-			return type;
-
-		free_token(*tok);
+		pevent_register_print_string(pevent, printk, addr);
 	}
-
-	/* not reached */
-	return EVENT_NONE;
 }
 
-/* no newline */
-static enum event_type read_token_item(char **tok)
+int parse_ftrace_file(struct pevent *pevent, char *buf, unsigned long size)
 {
-	enum event_type type;
-
-	for (;;) {
-		type = __read_token(tok);
-		if (type != EVENT_SPACE && type != EVENT_NEWLINE)
-			return type;
-
-		free_token(*tok);
-	}
-
-	/* not reached */
-	return EVENT_NONE;
+	return pevent_parse_event(pevent, buf, size, "ftrace");
 }
 
-static int test_type(enum event_type type, enum event_type expect)
+int parse_event_file(struct pevent *pevent,
+		     char *buf, unsigned long size, char *sys)
 {
-	if (type != expect) {
-		warning("Error: expected type %d but read %d",
-		    expect, type);
-		return -1;
-	}
-	return 0;
+	return pevent_parse_event(pevent, buf, size, sys);
 }
 
-static int __test_type_token(enum event_type type, char *token,
-			     enum event_type expect, const char *expect_tok,
-			     bool warn)
+struct event_format *trace_find_next_event(struct pevent *pevent,
+					   struct event_format *event)
 {
-	if (type != expect) {
-		if (warn)
-			warning("Error: expected type %d but read %d",
-				expect, type);
-		return -1;
-	}
+	static int idx;
 
-	if (strcmp(token, expect_tok) != 0) {
-		if (warn)
-			warning("Error: expected '%s' but read '%s'",
-				expect_tok, token);
-		return -1;
-	}
-	return 0;
-}
-
-static int test_type_token(enum event_type type, char *token,
-			   enum event_type expect, const char *expect_tok)
-{
-	return __test_type_token(type, token, expect, expect_tok, true);
-}
-
-static int __read_expect_type(enum event_type expect, char **tok, int newline_ok)
-{
-	enum event_type type;
-
-	if (newline_ok)
-		type = read_token(tok);
-	else
-		type = read_token_item(tok);
-	return test_type(type, expect);
-}
-
-static int read_expect_type(enum event_type expect, char **tok)
-{
-	return __read_expect_type(expect, tok, 1);
-}
-
-static int __read_expected(enum event_type expect, const char *str,
-			   int newline_ok, bool warn)
-{
-	enum event_type type;
-	char *token;
-	int ret;
-
-	if (newline_ok)
-		type = read_token(&token);
-	else
-		type = read_token_item(&token);
-
-	ret = __test_type_token(type, token, expect, str, warn);
-
-	free_token(token);
-
-	return ret;
-}
-
-static int read_expected(enum event_type expect, const char *str)
-{
-	return __read_expected(expect, str, 1, true);
-}
-
-static int read_expected_item(enum event_type expect, const char *str)
-{
-	return __read_expected(expect, str, 0, true);
-}
-
-static char *event_read_name(void)
-{
-	char *token;
-
-	if (read_expected(EVENT_ITEM, "name") < 0)
+	if (!pevent || !pevent->events)
 		return NULL;
 
-	if (read_expected(EVENT_OP, ":") < 0)
-		return NULL;
-
-	if (read_expect_type(EVENT_ITEM, &token) < 0)
-		goto fail;
-
-	return token;
-
- fail:
-	free_token(token);
-	return NULL;
-}
-
-static int event_read_id(void)
-{
-	char *token;
-	int id;
-
-	if (read_expected_item(EVENT_ITEM, "ID") < 0)
-		return -1;
-
-	if (read_expected(EVENT_OP, ":") < 0)
-		return -1;
-
-	if (read_expect_type(EVENT_ITEM, &token) < 0)
-		goto fail;
-
-	id = strtoul(token, NULL, 0);
-	free_token(token);
-	return id;
-
- fail:
-	free_token(token);
-	return -1;
-}
-
-static int field_is_string(struct format_field *field)
-{
-	if ((field->flags & FIELD_IS_ARRAY) &&
-	    (!strstr(field->type, "char") || !strstr(field->type, "u8") ||
-	     !strstr(field->type, "s8")))
-		return 1;
-
-	return 0;
-}
-
-static int field_is_dynamic(struct format_field *field)
-{
-	if (!strncmp(field->type, "__data_loc", 10))
-		return 1;
-
-	return 0;
-}
-
-static int event_read_fields(struct event *event, struct format_field **fields)
-{
-	struct format_field *field = NULL;
-	enum event_type type;
-	char *token;
-	char *last_token;
-	int count = 0;
-
-	do {
-		type = read_token(&token);
-		if (type == EVENT_NEWLINE) {
-			free_token(token);
-			return count;
-		}
-
-		count++;
-
-		if (test_type_token(type, token, EVENT_ITEM, "field"))
-			goto fail;
-		free_token(token);
-
-		type = read_token(&token);
-		/*
-		 * The ftrace fields may still use the "special" name.
-		 * Just ignore it.
-		 */
-		if (event->flags & EVENT_FL_ISFTRACE &&
-		    type == EVENT_ITEM && strcmp(token, "special") == 0) {
-			free_token(token);
-			type = read_token(&token);
-		}
-
-		if (test_type_token(type, token, EVENT_OP, ":") < 0)
-			return -1;
-
-		if (read_expect_type(EVENT_ITEM, &token) < 0)
-			goto fail;
-
-		last_token = token;
-
-		field = malloc_or_die(sizeof(*field));
-		memset(field, 0, sizeof(*field));
-
-		/* read the rest of the type */
-		for (;;) {
-			type = read_token(&token);
-			if (type == EVENT_ITEM ||
-			    (type == EVENT_OP && strcmp(token, "*") == 0) ||
-			    /*
-			     * Some of the ftrace fields are broken and have
-			     * an illegal "." in them.
-			     */
-			    (event->flags & EVENT_FL_ISFTRACE &&
-			     type == EVENT_OP && strcmp(token, ".") == 0)) {
-
-				if (strcmp(token, "*") == 0)
-					field->flags |= FIELD_IS_POINTER;
-
-				if (field->type) {
-					field->type = realloc(field->type,
-							      strlen(field->type) +
-							      strlen(last_token) + 2);
-					strcat(field->type, " ");
-					strcat(field->type, last_token);
-				} else
-					field->type = last_token;
-				last_token = token;
-				continue;
-			}
-
-			break;
-		}
-
-		if (!field->type) {
-			die("no type found");
-			goto fail;
-		}
-		field->name = last_token;
-
-		if (test_type(type, EVENT_OP))
-			goto fail;
-
-		if (strcmp(token, "[") == 0) {
-			enum event_type last_type = type;
-			char *brackets = token;
-			int len;
-
-			field->flags |= FIELD_IS_ARRAY;
-
-			type = read_token(&token);
-		        while (strcmp(token, "]") != 0) {
-				if (last_type == EVENT_ITEM &&
-				    type == EVENT_ITEM)
-					len = 2;
-				else
-					len = 1;
-				last_type = type;
-
-				brackets = realloc(brackets,
-						   strlen(brackets) +
-						   strlen(token) + len);
-				if (len == 2)
-					strcat(brackets, " ");
-				strcat(brackets, token);
-				free_token(token);
-				type = read_token(&token);
-				if (type == EVENT_NONE) {
-					die("failed to find token");
-					goto fail;
-				}
-			}
-
-			free_token(token);
-
-			brackets = realloc(brackets, strlen(brackets) + 2);
-			strcat(brackets, "]");
-
-			/* add brackets to type */
-
-			type = read_token(&token);
-			/*
-			 * If the next token is not an OP, then it is of
-			 * the format: type [] item;
-			 */
-			if (type == EVENT_ITEM) {
-				field->type = realloc(field->type,
-						      strlen(field->type) +
-						      strlen(field->name) +
-						      strlen(brackets) + 2);
-				strcat(field->type, " ");
-				strcat(field->type, field->name);
-				free_token(field->name);
-				strcat(field->type, brackets);
-				field->name = token;
-				type = read_token(&token);
-			} else {
-				field->type = realloc(field->type,
-						      strlen(field->type) +
-						      strlen(brackets) + 1);
-				strcat(field->type, brackets);
-			}
-			free(brackets);
-		}
-
-		if (field_is_string(field)) {
-			field->flags |= FIELD_IS_STRING;
-			if (field_is_dynamic(field))
-				field->flags |= FIELD_IS_DYNAMIC;
-		}
-
-		if (test_type_token(type, token,  EVENT_OP, ";"))
-			goto fail;
-		free_token(token);
-
-		if (read_expected(EVENT_ITEM, "offset") < 0)
-			goto fail_expect;
-
-		if (read_expected(EVENT_OP, ":") < 0)
-			goto fail_expect;
-
-		if (read_expect_type(EVENT_ITEM, &token))
-			goto fail;
-		field->offset = strtoul(token, NULL, 0);
-		free_token(token);
-
-		if (read_expected(EVENT_OP, ";") < 0)
-			goto fail_expect;
-
-		if (read_expected(EVENT_ITEM, "size") < 0)
-			goto fail_expect;
-
-		if (read_expected(EVENT_OP, ":") < 0)
-			goto fail_expect;
-
-		if (read_expect_type(EVENT_ITEM, &token))
-			goto fail;
-		field->size = strtoul(token, NULL, 0);
-		free_token(token);
-
-		if (read_expected(EVENT_OP, ";") < 0)
-			goto fail_expect;
-
-		type = read_token(&token);
-		if (type != EVENT_NEWLINE) {
-			/* newer versions of the kernel have a "signed" type */
-			if (test_type_token(type, token, EVENT_ITEM, "signed"))
-				goto fail;
-
-			free_token(token);
-
-			if (read_expected(EVENT_OP, ":") < 0)
-				goto fail_expect;
-
-			if (read_expect_type(EVENT_ITEM, &token))
-				goto fail;
-
-			if (strtoul(token, NULL, 0))
-				field->flags |= FIELD_IS_SIGNED;
-
-			free_token(token);
-			if (read_expected(EVENT_OP, ";") < 0)
-				goto fail_expect;
-
-			if (read_expect_type(EVENT_NEWLINE, &token))
-				goto fail;
-		}
-
-		free_token(token);
-
-		*fields = field;
-		fields = &field->next;
-
-	} while (1);
-
-	return 0;
-
-fail:
-	free_token(token);
-fail_expect:
-	if (field)
-		free(field);
-	return -1;
-}
-
-static int event_read_format(struct event *event)
-{
-	char *token;
-	int ret;
-
-	if (read_expected_item(EVENT_ITEM, "format") < 0)
-		return -1;
-
-	if (read_expected(EVENT_OP, ":") < 0)
-		return -1;
-
-	if (read_expect_type(EVENT_NEWLINE, &token))
-		goto fail;
-	free_token(token);
-
-	ret = event_read_fields(event, &event->format.common_fields);
-	if (ret < 0)
-		return ret;
-	event->format.nr_common = ret;
-
-	ret = event_read_fields(event, &event->format.fields);
-	if (ret < 0)
-		return ret;
-	event->format.nr_fields = ret;
-
-	return 0;
-
- fail:
-	free_token(token);
-	return -1;
-}
-
-enum event_type
-process_arg_token(struct event *event, struct print_arg *arg,
-		  char **tok, enum event_type type);
-
-static enum event_type
-process_arg(struct event *event, struct print_arg *arg, char **tok)
-{
-	enum event_type type;
-	char *token;
-
-	type = read_token(&token);
-	*tok = token;
-
-	return process_arg_token(event, arg, tok, type);
-}
-
-static enum event_type
-process_cond(struct event *event, struct print_arg *top, char **tok)
-{
-	struct print_arg *arg, *left, *right;
-	enum event_type type;
-	char *token = NULL;
-
-	arg = malloc_or_die(sizeof(*arg));
-	memset(arg, 0, sizeof(*arg));
-
-	left = malloc_or_die(sizeof(*left));
-
-	right = malloc_or_die(sizeof(*right));
-
-	arg->type = PRINT_OP;
-	arg->op.left = left;
-	arg->op.right = right;
-
-	*tok = NULL;
-	type = process_arg(event, left, &token);
-	if (test_type_token(type, token, EVENT_OP, ":"))
-		goto out_free;
-
-	arg->op.op = token;
-
-	type = process_arg(event, right, &token);
-
-	top->op.right = arg;
-
-	*tok = token;
-	return type;
-
-out_free:
-	free_token(*tok);
-	free(right);
-	free(left);
-	free_arg(arg);
-	return EVENT_ERROR;
-}
-
-static enum event_type
-process_array(struct event *event, struct print_arg *top, char **tok)
-{
-	struct print_arg *arg;
-	enum event_type type;
-	char *token = NULL;
-
-	arg = malloc_or_die(sizeof(*arg));
-	memset(arg, 0, sizeof(*arg));
-
-	*tok = NULL;
-	type = process_arg(event, arg, &token);
-	if (test_type_token(type, token, EVENT_OP, "]"))
-		goto out_free;
-
-	top->op.right = arg;
-
-	free_token(token);
-	type = read_token_item(&token);
-	*tok = token;
-
-	return type;
-
-out_free:
-	free_token(*tok);
-	free_arg(arg);
-	return EVENT_ERROR;
-}
-
-static int get_op_prio(char *op)
-{
-	if (!op[1]) {
-		switch (op[0]) {
-		case '*':
-		case '/':
-		case '%':
-			return 6;
-		case '+':
-		case '-':
-			return 7;
-			/* '>>' and '<<' are 8 */
-		case '<':
-		case '>':
-			return 9;
-			/* '==' and '!=' are 10 */
-		case '&':
-			return 11;
-		case '^':
-			return 12;
-		case '|':
-			return 13;
-		case '?':
-			return 16;
-		default:
-			die("unknown op '%c'", op[0]);
-			return -1;
-		}
-	} else {
-		if (strcmp(op, "++") == 0 ||
-		    strcmp(op, "--") == 0) {
-			return 3;
-		} else if (strcmp(op, ">>") == 0 ||
-			   strcmp(op, "<<") == 0) {
-			return 8;
-		} else if (strcmp(op, ">=") == 0 ||
-			   strcmp(op, "<=") == 0) {
-			return 9;
-		} else if (strcmp(op, "==") == 0 ||
-			   strcmp(op, "!=") == 0) {
-			return 10;
-		} else if (strcmp(op, "&&") == 0) {
-			return 14;
-		} else if (strcmp(op, "||") == 0) {
-			return 15;
-		} else {
-			die("unknown op '%s'", op);
-			return -1;
-		}
-	}
-}
-
-static void set_op_prio(struct print_arg *arg)
-{
-
-	/* single ops are the greatest */
-	if (!arg->op.left || arg->op.left->type == PRINT_NULL) {
-		arg->op.prio = 0;
-		return;
-	}
-
-	arg->op.prio = get_op_prio(arg->op.op);
-}
-
-static enum event_type
-process_op(struct event *event, struct print_arg *arg, char **tok)
-{
-	struct print_arg *left, *right = NULL;
-	enum event_type type;
-	char *token;
-
-	/* the op is passed in via tok */
-	token = *tok;
-
-	if (arg->type == PRINT_OP && !arg->op.left) {
-		/* handle single op */
-		if (token[1]) {
-			die("bad op token %s", token);
-			return EVENT_ERROR;
-		}
-		switch (token[0]) {
-		case '!':
-		case '+':
-		case '-':
-			break;
-		default:
-			die("bad op token %s", token);
-			return EVENT_ERROR;
-		}
-
-		/* make an empty left */
-		left = malloc_or_die(sizeof(*left));
-		left->type = PRINT_NULL;
-		arg->op.left = left;
-
-		right = malloc_or_die(sizeof(*right));
-		arg->op.right = right;
-
-		type = process_arg(event, right, tok);
-
-	} else if (strcmp(token, "?") == 0) {
-
-		left = malloc_or_die(sizeof(*left));
-		/* copy the top arg to the left */
-		*left = *arg;
-
-		arg->type = PRINT_OP;
-		arg->op.op = token;
-		arg->op.left = left;
-		arg->op.prio = 0;
-
-		type = process_cond(event, arg, tok);
-
-	} else if (strcmp(token, ">>") == 0 ||
-		   strcmp(token, "<<") == 0 ||
-		   strcmp(token, "&") == 0 ||
-		   strcmp(token, "|") == 0 ||
-		   strcmp(token, "&&") == 0 ||
-		   strcmp(token, "||") == 0 ||
-		   strcmp(token, "-") == 0 ||
-		   strcmp(token, "+") == 0 ||
-		   strcmp(token, "*") == 0 ||
-		   strcmp(token, "^") == 0 ||
-		   strcmp(token, "/") == 0 ||
-		   strcmp(token, "<") == 0 ||
-		   strcmp(token, ">") == 0 ||
-		   strcmp(token, "==") == 0 ||
-		   strcmp(token, "!=") == 0) {
-
-		left = malloc_or_die(sizeof(*left));
-
-		/* copy the top arg to the left */
-		*left = *arg;
-
-		arg->type = PRINT_OP;
-		arg->op.op = token;
-		arg->op.left = left;
-
-		set_op_prio(arg);
-
-		right = malloc_or_die(sizeof(*right));
-
-		type = read_token_item(&token);
-		*tok = token;
-
-		/* could just be a type pointer */
-		if ((strcmp(arg->op.op, "*") == 0) &&
-		    type == EVENT_DELIM && (strcmp(token, ")") == 0)) {
-			if (left->type != PRINT_ATOM)
-				die("bad pointer type");
-			left->atom.atom = realloc(left->atom.atom,
-					    sizeof(left->atom.atom) + 3);
-			strcat(left->atom.atom, " *");
-			*arg = *left;
-			free(arg);
-
-			return type;
-		}
-
-		type = process_arg_token(event, right, tok, type);
-
-		arg->op.right = right;
-
-	} else if (strcmp(token, "[") == 0) {
-
-		left = malloc_or_die(sizeof(*left));
-		*left = *arg;
-
-		arg->type = PRINT_OP;
-		arg->op.op = token;
-		arg->op.left = left;
-
-		arg->op.prio = 0;
-		type = process_array(event, arg, tok);
-
-	} else {
-		warning("unknown op '%s'", token);
-		event->flags |= EVENT_FL_FAILED;
-		/* the arg is now the left side */
-		return EVENT_NONE;
-	}
-
-	if (type == EVENT_OP) {
-		int prio;
-
-		/* higher prios need to be closer to the root */
-		prio = get_op_prio(*tok);
-
-		if (prio > arg->op.prio)
-			return process_op(event, arg, tok);
-
-		return process_op(event, right, tok);
-	}
-
-	return type;
-}
-
-static enum event_type
-process_entry(struct event *event __unused, struct print_arg *arg,
-	      char **tok)
-{
-	enum event_type type;
-	char *field;
-	char *token;
-
-	if (read_expected(EVENT_OP, "->") < 0)
-		return EVENT_ERROR;
-
-	if (read_expect_type(EVENT_ITEM, &token) < 0)
-		goto fail;
-	field = token;
-
-	arg->type = PRINT_FIELD;
-	arg->field.name = field;
-
-	if (is_flag_field) {
-		arg->field.field = find_any_field(event, arg->field.name);
-		arg->field.field->flags |= FIELD_IS_FLAG;
-		is_flag_field = 0;
-	} else if (is_symbolic_field) {
-		arg->field.field = find_any_field(event, arg->field.name);
-		arg->field.field->flags |= FIELD_IS_SYMBOLIC;
-		is_symbolic_field = 0;
+	if (!event) {
+		idx = 0;
+		return pevent->events[0];
 	}
 
-	type = read_token(&token);
-	*tok = token;
-
-	return type;
-
-fail:
-	free_token(token);
-	return EVENT_ERROR;
-}
-
-static char *arg_eval (struct print_arg *arg);
-
-static long long arg_num_eval(struct print_arg *arg)
-{
-	long long left, right;
-	long long val = 0;
-
-	switch (arg->type) {
-	case PRINT_ATOM:
-		val = strtoll(arg->atom.atom, NULL, 0);
-		break;
-	case PRINT_TYPE:
-		val = arg_num_eval(arg->typecast.item);
-		break;
-	case PRINT_OP:
-		switch (arg->op.op[0]) {
-		case '|':
-			left = arg_num_eval(arg->op.left);
-			right = arg_num_eval(arg->op.right);
-			if (arg->op.op[1])
-				val = left || right;
-			else
-				val = left | right;
-			break;
-		case '&':
-			left = arg_num_eval(arg->op.left);
-			right = arg_num_eval(arg->op.right);
-			if (arg->op.op[1])
-				val = left && right;
-			else
-				val = left & right;
-			break;
-		case '<':
-			left = arg_num_eval(arg->op.left);
-			right = arg_num_eval(arg->op.right);
-			switch (arg->op.op[1]) {
-			case 0:
-				val = left < right;
-				break;
-			case '<':
-				val = left << right;
-				break;
-			case '=':
-				val = left <= right;
-				break;
-			default:
-				die("unknown op '%s'", arg->op.op);
-			}
-			break;
-		case '>':
-			left = arg_num_eval(arg->op.left);
-			right = arg_num_eval(arg->op.right);
-			switch (arg->op.op[1]) {
-			case 0:
-				val = left > right;
-				break;
-			case '>':
-				val = left >> right;
-				break;
-			case '=':
-				val = left >= right;
-				break;
-			default:
-				die("unknown op '%s'", arg->op.op);
-			}
-			break;
-		case '=':
-			left = arg_num_eval(arg->op.left);
-			right = arg_num_eval(arg->op.right);
-
-			if (arg->op.op[1] != '=')
-				die("unknown op '%s'", arg->op.op);
-
-			val = left == right;
-			break;
-		case '!':
-			left = arg_num_eval(arg->op.left);
-			right = arg_num_eval(arg->op.right);
-
-			switch (arg->op.op[1]) {
-			case '=':
-				val = left != right;
-				break;
-			default:
-				die("unknown op '%s'", arg->op.op);
-			}
-			break;
-		default:
-			die("unknown op '%s'", arg->op.op);
-		}
-		break;
-
-	case PRINT_NULL:
-	case PRINT_FIELD ... PRINT_SYMBOL:
-	case PRINT_STRING:
-	default:
-		die("invalid eval type %d", arg->type);
-
+	if (idx < pevent->nr_events && event == pevent->events[idx]) {
+		idx++;
+		if (idx == pevent->nr_events)
+			return NULL;
+		return pevent->events[idx];
 	}
-	return val;
-}
-
-static char *arg_eval (struct print_arg *arg)
-{
-	long long val;
-	static char buf[20];
-
-	switch (arg->type) {
-	case PRINT_ATOM:
-		return arg->atom.atom;
-	case PRINT_TYPE:
-		return arg_eval(arg->typecast.item);
-	case PRINT_OP:
-		val = arg_num_eval(arg);
-		sprintf(buf, "%lld", val);
-		return buf;
 
-	case PRINT_NULL:
-	case PRINT_FIELD ... PRINT_SYMBOL:
-	case PRINT_STRING:
-	default:
-		die("invalid eval type %d", arg->type);
-		break;
+	for (idx = 1; idx < pevent->nr_events; idx++) {
+		if (event == pevent->events[idx - 1])
+			return pevent->events[idx];
 	}
-
 	return NULL;
 }
 
-static enum event_type
-process_fields(struct event *event, struct print_flag_sym **list, char **tok)
-{
-	enum event_type type;
-	struct print_arg *arg = NULL;
-	struct print_flag_sym *field;
-	char *token = NULL;
-	char *value;
-
-	do {
-		free_token(token);
-		type = read_token_item(&token);
-		if (test_type_token(type, token, EVENT_OP, "{"))
-			break;
-
-		arg = malloc_or_die(sizeof(*arg));
-
-		free_token(token);
-		type = process_arg(event, arg, &token);
-		if (test_type_token(type, token, EVENT_DELIM, ","))
-			goto out_free;
-
-		field = malloc_or_die(sizeof(*field));
-		memset(field, 0, sizeof(*field));
-
-		value = arg_eval(arg);
-		field->value = strdup(value);
-
-		free_token(token);
-		type = process_arg(event, arg, &token);
-		if (test_type_token(type, token, EVENT_OP, "}"))
-			goto out_free;
-
-		value = arg_eval(arg);
-		field->str = strdup(value);
-		free_arg(arg);
-		arg = NULL;
-
-		*list = field;
-		list = &field->next;
-
-		free_token(token);
-		type = read_token_item(&token);
-	} while (type == EVENT_DELIM && strcmp(token, ",") == 0);
-
-	*tok = token;
-	return type;
-
-out_free:
-	free_arg(arg);
-	free_token(token);
-
-	return EVENT_ERROR;
-}
-
-static enum event_type
-process_flags(struct event *event, struct print_arg *arg, char **tok)
-{
-	struct print_arg *field;
-	enum event_type type;
-	char *token;
-
-	memset(arg, 0, sizeof(*arg));
-	arg->type = PRINT_FLAGS;
-
-	if (read_expected_item(EVENT_DELIM, "(") < 0)
-		return EVENT_ERROR;
-
-	field = malloc_or_die(sizeof(*field));
-
-	type = process_arg(event, field, &token);
-	if (test_type_token(type, token, EVENT_DELIM, ","))
-		goto out_free;
-
-	arg->flags.field = field;
-
-	type = read_token_item(&token);
-	if (event_item_type(type)) {
-		arg->flags.delim = token;
-		type = read_token_item(&token);
-	}
-
-	if (test_type_token(type, token, EVENT_DELIM, ","))
-		goto out_free;
-
-	type = process_fields(event, &arg->flags.flags, &token);
-	if (test_type_token(type, token, EVENT_DELIM, ")"))
-		goto out_free;
-
-	free_token(token);
-	type = read_token_item(tok);
-	return type;
-
-out_free:
-	free_token(token);
-	return EVENT_ERROR;
-}
-
-static enum event_type
-process_symbols(struct event *event, struct print_arg *arg, char **tok)
-{
-	struct print_arg *field;
-	enum event_type type;
-	char *token;
-
-	memset(arg, 0, sizeof(*arg));
-	arg->type = PRINT_SYMBOL;
-
-	if (read_expected_item(EVENT_DELIM, "(") < 0)
-		return EVENT_ERROR;
-
-	field = malloc_or_die(sizeof(*field));
-
-	type = process_arg(event, field, &token);
-	if (test_type_token(type, token, EVENT_DELIM, ","))
-		goto out_free;
-
-	arg->symbol.field = field;
-
-	type = process_fields(event, &arg->symbol.symbols, &token);
-	if (test_type_token(type, token, EVENT_DELIM, ")"))
-		goto out_free;
-
-	free_token(token);
-	type = read_token_item(tok);
-	return type;
-
-out_free:
-	free_token(token);
-	return EVENT_ERROR;
-}
-
-static enum event_type
-process_paren(struct event *event, struct print_arg *arg, char **tok)
-{
-	struct print_arg *item_arg;
-	enum event_type type;
-	char *token;
-
-	type = process_arg(event, arg, &token);
-
-	if (type == EVENT_ERROR)
-		return EVENT_ERROR;
-
-	if (type == EVENT_OP)
-		type = process_op(event, arg, &token);
-
-	if (type == EVENT_ERROR)
-		return EVENT_ERROR;
-
-	if (test_type_token(type, token, EVENT_DELIM, ")")) {
-		free_token(token);
-		return EVENT_ERROR;
-	}
-
-	free_token(token);
-	type = read_token_item(&token);
-
-	/*
-	 * If the next token is an item or another open paren, then
-	 * this was a typecast.
-	 */
-	if (event_item_type(type) ||
-	    (type == EVENT_DELIM && strcmp(token, "(") == 0)) {
-
-		/* make this a typecast and contine */
-
-		/* prevous must be an atom */
-		if (arg->type != PRINT_ATOM)
-			die("previous needed to be PRINT_ATOM");
-
-		item_arg = malloc_or_die(sizeof(*item_arg));
-
-		arg->type = PRINT_TYPE;
-		arg->typecast.type = arg->atom.atom;
-		arg->typecast.item = item_arg;
-		type = process_arg_token(event, item_arg, &token, type);
-
-	}
-
-	*tok = token;
-	return type;
-}
-
-
-static enum event_type
-process_str(struct event *event __unused, struct print_arg *arg, char **tok)
-{
-	enum event_type type;
-	char *token;
-
-	if (read_expected(EVENT_DELIM, "(") < 0)
-		return EVENT_ERROR;
-
-	if (read_expect_type(EVENT_ITEM, &token) < 0)
-		goto fail;
-
-	arg->type = PRINT_STRING;
-	arg->string.string = token;
-	arg->string.offset = -1;
-
-	if (read_expected(EVENT_DELIM, ")") < 0)
-		return EVENT_ERROR;
-
-	type = read_token(&token);
-	*tok = token;
-
-	return type;
-fail:
-	free_token(token);
-	return EVENT_ERROR;
-}
-
-enum event_type
-process_arg_token(struct event *event, struct print_arg *arg,
-		  char **tok, enum event_type type)
-{
-	char *token;
-	char *atom;
-
-	token = *tok;
-
-	switch (type) {
-	case EVENT_ITEM:
-		if (strcmp(token, "REC") == 0) {
-			free_token(token);
-			type = process_entry(event, arg, &token);
-		} else if (strcmp(token, "__print_flags") == 0) {
-			free_token(token);
-			is_flag_field = 1;
-			type = process_flags(event, arg, &token);
-		} else if (strcmp(token, "__print_symbolic") == 0) {
-			free_token(token);
-			is_symbolic_field = 1;
-			type = process_symbols(event, arg, &token);
-		} else if (strcmp(token, "__get_str") == 0) {
-			free_token(token);
-			type = process_str(event, arg, &token);
-		} else {
-			atom = token;
-			/* test the next token */
-			type = read_token_item(&token);
-
-			/* atoms can be more than one token long */
-			while (type == EVENT_ITEM) {
-				atom = realloc(atom, strlen(atom) + strlen(token) + 2);
-				strcat(atom, " ");
-				strcat(atom, token);
-				free_token(token);
-				type = read_token_item(&token);
-			}
-
-			/* todo, test for function */
-
-			arg->type = PRINT_ATOM;
-			arg->atom.atom = atom;
-		}
-		break;
-	case EVENT_DQUOTE:
-	case EVENT_SQUOTE:
-		arg->type = PRINT_ATOM;
-		arg->atom.atom = token;
-		type = read_token_item(&token);
-		break;
-	case EVENT_DELIM:
-		if (strcmp(token, "(") == 0) {
-			free_token(token);
-			type = process_paren(event, arg, &token);
-			break;
-		}
-	case EVENT_OP:
-		/* handle single ops */
-		arg->type = PRINT_OP;
-		arg->op.op = token;
-		arg->op.left = NULL;
-		type = process_op(event, arg, &token);
-
-		break;
-
-	case EVENT_ERROR ... EVENT_NEWLINE:
-	default:
-		die("unexpected type %d", type);
-	}
-	*tok = token;
-
-	return type;
-}
-
-static int event_read_print_args(struct event *event, struct print_arg **list)
-{
-	enum event_type type = EVENT_ERROR;
-	struct print_arg *arg;
-	char *token;
-	int args = 0;
-
-	do {
-		if (type == EVENT_NEWLINE) {
-			free_token(token);
-			type = read_token_item(&token);
-			continue;
-		}
-
-		arg = malloc_or_die(sizeof(*arg));
-		memset(arg, 0, sizeof(*arg));
-
-		type = process_arg(event, arg, &token);
-
-		if (type == EVENT_ERROR) {
-			free_arg(arg);
-			return -1;
-		}
-
-		*list = arg;
-		args++;
-
-		if (type == EVENT_OP) {
-			type = process_op(event, arg, &token);
-			list = &arg->next;
-			continue;
-		}
-
-		if (type == EVENT_DELIM && strcmp(token, ",") == 0) {
-			free_token(token);
-			*list = arg;
-			list = &arg->next;
-			continue;
-		}
-		break;
-	} while (type != EVENT_NONE);
-
-	if (type != EVENT_NONE)
-		free_token(token);
-
-	return args;
-}
-
-static int event_read_print(struct event *event)
-{
-	enum event_type type;
-	char *token;
-	int ret;
-
-	if (read_expected_item(EVENT_ITEM, "print") < 0)
-		return -1;
-
-	if (read_expected(EVENT_ITEM, "fmt") < 0)
-		return -1;
-
-	if (read_expected(EVENT_OP, ":") < 0)
-		return -1;
-
-	if (read_expect_type(EVENT_DQUOTE, &token) < 0)
-		goto fail;
-
- concat:
-	event->print_fmt.format = token;
-	event->print_fmt.args = NULL;
-
-	/* ok to have no arg */
-	type = read_token_item(&token);
-
-	if (type == EVENT_NONE)
-		return 0;
-
-	/* Handle concatination of print lines */
-	if (type == EVENT_DQUOTE) {
-		char *cat;
-
-		cat = malloc_or_die(strlen(event->print_fmt.format) +
-				    strlen(token) + 1);
-		strcpy(cat, event->print_fmt.format);
-		strcat(cat, token);
-		free_token(token);
-		free_token(event->print_fmt.format);
-		event->print_fmt.format = NULL;
-		token = cat;
-		goto concat;
-	}
-
-	if (test_type_token(type, token, EVENT_DELIM, ","))
-		goto fail;
-
-	free_token(token);
-
-	ret = event_read_print_args(event, &event->print_fmt.args);
-	if (ret < 0)
-		return -1;
-
-	return ret;
-
- fail:
-	free_token(token);
-	return -1;
-}
-
-static struct format_field *
-find_common_field(struct event *event, const char *name)
-{
-	struct format_field *format;
-
-	for (format = event->format.common_fields;
-	     format; format = format->next) {
-		if (strcmp(format->name, name) == 0)
-			break;
-	}
-
-	return format;
-}
-
-static struct format_field *
-find_field(struct event *event, const char *name)
-{
-	struct format_field *format;
-
-	for (format = event->format.fields;
-	     format; format = format->next) {
-		if (strcmp(format->name, name) == 0)
-			break;
-	}
-
-	return format;
-}
-
-static struct format_field *
-find_any_field(struct event *event, const char *name)
-{
-	struct format_field *format;
-
-	format = find_common_field(event, name);
-	if (format)
-		return format;
-	return find_field(event, name);
-}
-
-unsigned long long read_size(void *ptr, int size)
-{
-	switch (size) {
-	case 1:
-		return *(unsigned char *)ptr;
-	case 2:
-		return data2host2(ptr);
-	case 4:
-		return data2host4(ptr);
-	case 8:
-		return data2host8(ptr);
-	default:
-		/* BUG! */
-		return 0;
-	}
-}
-
-unsigned long long
-raw_field_value(struct event *event, const char *name, void *data)
-{
-	struct format_field *field;
-
-	field = find_any_field(event, name);
-	if (!field)
-		return 0ULL;
-
-	return read_size(data + field->offset, field->size);
-}
-
-void *raw_field_ptr(struct event *event, const char *name, void *data)
-{
-	struct format_field *field;
-
-	field = find_any_field(event, name);
-	if (!field)
-		return NULL;
-
-	if (field->flags & FIELD_IS_DYNAMIC) {
-		int offset;
-
-		offset = *(int *)(data + field->offset);
-		offset &= 0xffff;
-
-		return data + offset;
-	}
-
-	return data + field->offset;
-}
-
-static int get_common_info(const char *type, int *offset, int *size)
-{
-	struct event *event;
-	struct format_field *field;
-
-	/*
-	 * All events should have the same common elements.
-	 * Pick any event to find where the type is;
-	 */
-	if (!event_list)
-		die("no event_list!");
-
-	event = event_list;
-	field = find_common_field(event, type);
-	if (!field)
-		die("field '%s' not found", type);
-
-	*offset = field->offset;
-	*size = field->size;
-
-	return 0;
-}
-
-static int __parse_common(void *data, int *size, int *offset,
-			  const char *name)
-{
-	int ret;
-
-	if (!*size) {
-		ret = get_common_info(name, offset, size);
-		if (ret < 0)
-			return ret;
-	}
-	return read_size(data + *offset, *size);
-}
-
-int trace_parse_common_type(void *data)
-{
-	static int type_offset;
-	static int type_size;
-
-	return __parse_common(data, &type_size, &type_offset,
-			      "common_type");
-}
-
-int trace_parse_common_pid(void *data)
-{
-	static int pid_offset;
-	static int pid_size;
-
-	return __parse_common(data, &pid_size, &pid_offset,
-			      "common_pid");
-}
-
-int parse_common_pc(void *data)
-{
-	static int pc_offset;
-	static int pc_size;
-
-	return __parse_common(data, &pc_size, &pc_offset,
-			      "common_preempt_count");
-}
-
-int parse_common_flags(void *data)
-{
-	static int flags_offset;
-	static int flags_size;
-
-	return __parse_common(data, &flags_size, &flags_offset,
-			      "common_flags");
-}
-
-int parse_common_lock_depth(void *data)
-{
-	static int ld_offset;
-	static int ld_size;
-	int ret;
-
-	ret = __parse_common(data, &ld_size, &ld_offset,
-			     "common_lock_depth");
-	if (ret < 0)
-		return -1;
-
-	return ret;
-}
-
-struct event *trace_find_event(int id)
-{
-	struct event *event;
-
-	for (event = event_list; event; event = event->next) {
-		if (event->id == id)
-			break;
-	}
-	return event;
-}
-
-struct event *trace_find_next_event(struct event *event)
-{
-	if (!event)
-		return event_list;
-
-	return event->next;
-}
-
-static unsigned long long eval_num_arg(void *data, int size,
-				   struct event *event, struct print_arg *arg)
-{
-	unsigned long long val = 0;
-	unsigned long long left, right;
-	struct print_arg *larg;
-
-	switch (arg->type) {
-	case PRINT_NULL:
-		/* ?? */
-		return 0;
-	case PRINT_ATOM:
-		return strtoull(arg->atom.atom, NULL, 0);
-	case PRINT_FIELD:
-		if (!arg->field.field) {
-			arg->field.field = find_any_field(event, arg->field.name);
-			if (!arg->field.field)
-				die("field %s not found", arg->field.name);
-		}
-		/* must be a number */
-		val = read_size(data + arg->field.field->offset,
-				arg->field.field->size);
-		break;
-	case PRINT_FLAGS:
-	case PRINT_SYMBOL:
-		break;
-	case PRINT_TYPE:
-		return eval_num_arg(data, size, event, arg->typecast.item);
-	case PRINT_STRING:
-		return 0;
-		break;
-	case PRINT_OP:
-		if (strcmp(arg->op.op, "[") == 0) {
-			/*
-			 * Arrays are special, since we don't want
-			 * to read the arg as is.
-			 */
-			if (arg->op.left->type != PRINT_FIELD)
-				goto default_op; /* oops, all bets off */
-			larg = arg->op.left;
-			if (!larg->field.field) {
-				larg->field.field =
-					find_any_field(event, larg->field.name);
-				if (!larg->field.field)
-					die("field %s not found", larg->field.name);
-			}
-			right = eval_num_arg(data, size, event, arg->op.right);
-			val = read_size(data + larg->field.field->offset +
-					right * long_size, long_size);
-			break;
-		}
- default_op:
-		left = eval_num_arg(data, size, event, arg->op.left);
-		right = eval_num_arg(data, size, event, arg->op.right);
-		switch (arg->op.op[0]) {
-		case '|':
-			if (arg->op.op[1])
-				val = left || right;
-			else
-				val = left | right;
-			break;
-		case '&':
-			if (arg->op.op[1])
-				val = left && right;
-			else
-				val = left & right;
-			break;
-		case '<':
-			switch (arg->op.op[1]) {
-			case 0:
-				val = left < right;
-				break;
-			case '<':
-				val = left << right;
-				break;
-			case '=':
-				val = left <= right;
-				break;
-			default:
-				die("unknown op '%s'", arg->op.op);
-			}
-			break;
-		case '>':
-			switch (arg->op.op[1]) {
-			case 0:
-				val = left > right;
-				break;
-			case '>':
-				val = left >> right;
-				break;
-			case '=':
-				val = left >= right;
-				break;
-			default:
-				die("unknown op '%s'", arg->op.op);
-			}
-			break;
-		case '=':
-			if (arg->op.op[1] != '=')
-				die("unknown op '%s'", arg->op.op);
-			val = left == right;
-			break;
-		case '-':
-			val = left - right;
-			break;
-		case '+':
-			val = left + right;
-			break;
-		default:
-			die("unknown op '%s'", arg->op.op);
-		}
-		break;
-	default: /* not sure what to do there */
-		return 0;
-	}
-	return val;
-}
-
 struct flag {
 	const char *name;
 	unsigned long long value;
@@ -2211,1023 +261,3 @@ unsigned long long eval_flag(const char *flag)
 
 	return 0;
 }
-
-static void print_str_arg(void *data, int size,
-			  struct event *event, struct print_arg *arg)
-{
-	struct print_flag_sym *flag;
-	unsigned long long val, fval;
-	char *str;
-	int print;
-
-	switch (arg->type) {
-	case PRINT_NULL:
-		/* ?? */
-		return;
-	case PRINT_ATOM:
-		printf("%s", arg->atom.atom);
-		return;
-	case PRINT_FIELD:
-		if (!arg->field.field) {
-			arg->field.field = find_any_field(event, arg->field.name);
-			if (!arg->field.field)
-				die("field %s not found", arg->field.name);
-		}
-		str = malloc_or_die(arg->field.field->size + 1);
-		memcpy(str, data + arg->field.field->offset,
-		       arg->field.field->size);
-		str[arg->field.field->size] = 0;
-		printf("%s", str);
-		free(str);
-		break;
-	case PRINT_FLAGS:
-		val = eval_num_arg(data, size, event, arg->flags.field);
-		print = 0;
-		for (flag = arg->flags.flags; flag; flag = flag->next) {
-			fval = eval_flag(flag->value);
-			if (!val && !fval) {
-				printf("%s", flag->str);
-				break;
-			}
-			if (fval && (val & fval) == fval) {
-				if (print && arg->flags.delim)
-					printf("%s", arg->flags.delim);
-				printf("%s", flag->str);
-				print = 1;
-				val &= ~fval;
-			}
-		}
-		break;
-	case PRINT_SYMBOL:
-		val = eval_num_arg(data, size, event, arg->symbol.field);
-		for (flag = arg->symbol.symbols; flag; flag = flag->next) {
-			fval = eval_flag(flag->value);
-			if (val == fval) {
-				printf("%s", flag->str);
-				break;
-			}
-		}
-		break;
-
-	case PRINT_TYPE:
-		break;
-	case PRINT_STRING: {
-		int str_offset;
-
-		if (arg->string.offset == -1) {
-			struct format_field *f;
-
-			f = find_any_field(event, arg->string.string);
-			arg->string.offset = f->offset;
-		}
-		str_offset = *(int *)(data + arg->string.offset);
-		str_offset &= 0xffff;
-		printf("%s", ((char *)data) + str_offset);
-		break;
-	}
-	case PRINT_OP:
-		/*
-		 * The only op for string should be ? :
-		 */
-		if (arg->op.op[0] != '?')
-			return;
-		val = eval_num_arg(data, size, event, arg->op.left);
-		if (val)
-			print_str_arg(data, size, event, arg->op.right->op.left);
-		else
-			print_str_arg(data, size, event, arg->op.right->op.right);
-		break;
-	default:
-		/* well... */
-		break;
-	}
-}
-
-static struct print_arg *make_bprint_args(char *fmt, void *data, int size, struct event *event)
-{
-	static struct format_field *field, *ip_field;
-	struct print_arg *args, *arg, **next;
-	unsigned long long ip, val;
-	char *ptr;
-	void *bptr;
-
-	if (!field) {
-		field = find_field(event, "buf");
-		if (!field)
-			die("can't find buffer field for binary printk");
-		ip_field = find_field(event, "ip");
-		if (!ip_field)
-			die("can't find ip field for binary printk");
-	}
-
-	ip = read_size(data + ip_field->offset, ip_field->size);
-
-	/*
-	 * The first arg is the IP pointer.
-	 */
-	args = malloc_or_die(sizeof(*args));
-	arg = args;
-	arg->next = NULL;
-	next = &arg->next;
-
-	arg->type = PRINT_ATOM;
-	arg->atom.atom = malloc_or_die(32);
-	sprintf(arg->atom.atom, "%lld", ip);
-
-	/* skip the first "%pf : " */
-	for (ptr = fmt + 6, bptr = data + field->offset;
-	     bptr < data + size && *ptr; ptr++) {
-		int ls = 0;
-
-		if (*ptr == '%') {
- process_again:
-			ptr++;
-			switch (*ptr) {
-			case '%':
-				break;
-			case 'l':
-				ls++;
-				goto process_again;
-			case 'L':
-				ls = 2;
-				goto process_again;
-			case '0' ... '9':
-				goto process_again;
-			case 'p':
-				ls = 1;
-				/* fall through */
-			case 'd':
-			case 'u':
-			case 'x':
-			case 'i':
-				/* the pointers are always 4 bytes aligned */
-				bptr = (void *)(((unsigned long)bptr + 3) &
-						~3);
-				switch (ls) {
-				case 0:
-				case 1:
-					ls = long_size;
-					break;
-				case 2:
-					ls = 8;
-				default:
-					break;
-				}
-				val = read_size(bptr, ls);
-				bptr += ls;
-				arg = malloc_or_die(sizeof(*arg));
-				arg->next = NULL;
-				arg->type = PRINT_ATOM;
-				arg->atom.atom = malloc_or_die(32);
-				sprintf(arg->atom.atom, "%lld", val);
-				*next = arg;
-				next = &arg->next;
-				break;
-			case 's':
-				arg = malloc_or_die(sizeof(*arg));
-				arg->next = NULL;
-				arg->type = PRINT_STRING;
-				arg->string.string = strdup(bptr);
-				bptr += strlen(bptr) + 1;
-				*next = arg;
-				next = &arg->next;
-			default:
-				break;
-			}
-		}
-	}
-
-	return args;
-}
-
-static void free_args(struct print_arg *args)
-{
-	struct print_arg *next;
-
-	while (args) {
-		next = args->next;
-
-		if (args->type == PRINT_ATOM)
-			free(args->atom.atom);
-		else
-			free(args->string.string);
-		free(args);
-		args = next;
-	}
-}
-
-static char *get_bprint_format(void *data, int size __unused, struct event *event)
-{
-	unsigned long long addr;
-	static struct format_field *field;
-	struct printk_map *printk;
-	char *format;
-	char *p;
-
-	if (!field) {
-		field = find_field(event, "fmt");
-		if (!field)
-			die("can't find format field for binary printk");
-		printf("field->offset = %d size=%d\n", field->offset, field->size);
-	}
-
-	addr = read_size(data + field->offset, field->size);
-
-	printk = find_printk(addr);
-	if (!printk) {
-		format = malloc_or_die(45);
-		sprintf(format, "%%pf : (NO FORMAT FOUND at %llx)\n",
-			addr);
-		return format;
-	}
-
-	p = printk->printk;
-	/* Remove any quotes. */
-	if (*p == '"')
-		p++;
-	format = malloc_or_die(strlen(p) + 10);
-	sprintf(format, "%s : %s", "%pf", p);
-	/* remove ending quotes and new line since we will add one too */
-	p = format + strlen(format) - 1;
-	if (*p == '"')
-		*p = 0;
-
-	p -= 2;
-	if (strcmp(p, "\\n") == 0)
-		*p = 0;
-
-	return format;
-}
-
-static void pretty_print(void *data, int size, struct event *event)
-{
-	struct print_fmt *print_fmt = &event->print_fmt;
-	struct print_arg *arg = print_fmt->args;
-	struct print_arg *args = NULL;
-	const char *ptr = print_fmt->format;
-	unsigned long long val;
-	struct func_map *func;
-	const char *saveptr;
-	char *bprint_fmt = NULL;
-	char format[32];
-	int show_func;
-	int len;
-	int ls;
-
-	if (event->flags & EVENT_FL_ISFUNC)
-		ptr = " %pF <-- %pF";
-
-	if (event->flags & EVENT_FL_ISBPRINT) {
-		bprint_fmt = get_bprint_format(data, size, event);
-		args = make_bprint_args(bprint_fmt, data, size, event);
-		arg = args;
-		ptr = bprint_fmt;
-	}
-
-	for (; *ptr; ptr++) {
-		ls = 0;
-		if (*ptr == '\\') {
-			ptr++;
-			switch (*ptr) {
-			case 'n':
-				printf("\n");
-				break;
-			case 't':
-				printf("\t");
-				break;
-			case 'r':
-				printf("\r");
-				break;
-			case '\\':
-				printf("\\");
-				break;
-			default:
-				printf("%c", *ptr);
-				break;
-			}
-
-		} else if (*ptr == '%') {
-			saveptr = ptr;
-			show_func = 0;
- cont_process:
-			ptr++;
-			switch (*ptr) {
-			case '%':
-				printf("%%");
-				break;
-			case 'l':
-				ls++;
-				goto cont_process;
-			case 'L':
-				ls = 2;
-				goto cont_process;
-			case 'z':
-			case 'Z':
-			case '0' ... '9':
-				goto cont_process;
-			case 'p':
-				if (long_size == 4)
-					ls = 1;
-				else
-					ls = 2;
-
-				if (*(ptr+1) == 'F' ||
-				    *(ptr+1) == 'f') {
-					ptr++;
-					show_func = *ptr;
-				}
-
-				/* fall through */
-			case 'd':
-			case 'i':
-			case 'x':
-			case 'X':
-			case 'u':
-				if (!arg)
-					die("no argument match");
-
-				len = ((unsigned long)ptr + 1) -
-					(unsigned long)saveptr;
-
-				/* should never happen */
-				if (len > 32)
-					die("bad format!");
-
-				memcpy(format, saveptr, len);
-				format[len] = 0;
-
-				val = eval_num_arg(data, size, event, arg);
-				arg = arg->next;
-
-				if (show_func) {
-					func = find_func(val);
-					if (func) {
-						printf("%s", func->func);
-						if (show_func == 'F')
-							printf("+0x%llx",
-							       val - func->addr);
-						break;
-					}
-				}
-				switch (ls) {
-				case 0:
-					printf(format, (int)val);
-					break;
-				case 1:
-					printf(format, (long)val);
-					break;
-				case 2:
-					printf(format, (long long)val);
-					break;
-				default:
-					die("bad count (%d)", ls);
-				}
-				break;
-			case 's':
-				if (!arg)
-					die("no matching argument");
-
-				print_str_arg(data, size, event, arg);
-				arg = arg->next;
-				break;
-			default:
-				printf(">%c<", *ptr);
-
-			}
-		} else
-			printf("%c", *ptr);
-	}
-
-	if (args) {
-		free_args(args);
-		free(bprint_fmt);
-	}
-}
-
-static inline int log10_cpu(int nb)
-{
-	if (nb / 100)
-		return 3;
-	if (nb / 10)
-		return 2;
-	return 1;
-}
-
-static void print_lat_fmt(void *data, int size __unused)
-{
-	unsigned int lat_flags;
-	unsigned int pc;
-	int lock_depth;
-	int hardirq;
-	int softirq;
-
-	lat_flags = parse_common_flags(data);
-	pc = parse_common_pc(data);
-	lock_depth = parse_common_lock_depth(data);
-
-	hardirq = lat_flags & TRACE_FLAG_HARDIRQ;
-	softirq = lat_flags & TRACE_FLAG_SOFTIRQ;
-
-	printf("%c%c%c",
-	       (lat_flags & TRACE_FLAG_IRQS_OFF) ? 'd' :
-	       (lat_flags & TRACE_FLAG_IRQS_NOSUPPORT) ?
-	       'X' : '.',
-	       (lat_flags & TRACE_FLAG_NEED_RESCHED) ?
-	       'N' : '.',
-	       (hardirq && softirq) ? 'H' :
-	       hardirq ? 'h' : softirq ? 's' : '.');
-
-	if (pc)
-		printf("%x", pc);
-	else
-		printf(".");
-
-	if (lock_depth < 0)
-		printf(".");
-	else
-		printf("%d", lock_depth);
-}
-
-/* taken from Linux, written by Frederic Weisbecker */
-static void print_graph_cpu(int cpu)
-{
-	int i;
-	int log10_this = log10_cpu(cpu);
-	int log10_all = log10_cpu(cpus);
-
-
-	/*
-	 * Start with a space character - to make it stand out
-	 * to the right a bit when trace output is pasted into
-	 * email:
-	 */
-	printf(" ");
-
-	/*
-	 * Tricky - we space the CPU field according to the max
-	 * number of online CPUs. On a 2-cpu system it would take
-	 * a maximum of 1 digit - on a 128 cpu system it would
-	 * take up to 3 digits:
-	 */
-	for (i = 0; i < log10_all - log10_this; i++)
-		printf(" ");
-
-	printf("%d) ", cpu);
-}
-
-#define TRACE_GRAPH_PROCINFO_LENGTH	14
-#define TRACE_GRAPH_INDENT	2
-
-static void print_graph_proc(int pid, const char *comm)
-{
-	/* sign + log10(MAX_INT) + '\0' */
-	char pid_str[11];
-	int spaces = 0;
-	int len;
-	int i;
-
-	sprintf(pid_str, "%d", pid);
-
-	/* 1 stands for the "-" character */
-	len = strlen(comm) + strlen(pid_str) + 1;
-
-	if (len < TRACE_GRAPH_PROCINFO_LENGTH)
-		spaces = TRACE_GRAPH_PROCINFO_LENGTH - len;
-
-	/* First spaces to align center */
-	for (i = 0; i < spaces / 2; i++)
-		printf(" ");
-
-	printf("%s-%s", comm, pid_str);
-
-	/* Last spaces to align center */
-	for (i = 0; i < spaces - (spaces / 2); i++)
-		printf(" ");
-}
-
-static struct record *
-get_return_for_leaf(int cpu, int cur_pid, unsigned long long cur_func,
-		    struct record *next)
-{
-	struct format_field *field;
-	struct event *event;
-	unsigned long val;
-	int type;
-	int pid;
-
-	type = trace_parse_common_type(next->data);
-	event = trace_find_event(type);
-	if (!event)
-		return NULL;
-
-	if (!(event->flags & EVENT_FL_ISFUNCRET))
-		return NULL;
-
-	pid = trace_parse_common_pid(next->data);
-	field = find_field(event, "func");
-	if (!field)
-		die("function return does not have field func");
-
-	val = read_size(next->data + field->offset, field->size);
-
-	if (cur_pid != pid || cur_func != val)
-		return NULL;
-
-	/* this is a leaf, now advance the iterator */
-	return trace_read_data(cpu);
-}
-
-/* Signal a overhead of time execution to the output */
-static void print_graph_overhead(unsigned long long duration)
-{
-	/* Non nested entry or return */
-	if (duration == ~0ULL)
-		return (void)printf("  ");
-
-	/* Duration exceeded 100 msecs */
-	if (duration > 100000ULL)
-		return (void)printf("! ");
-
-	/* Duration exceeded 10 msecs */
-	if (duration > 10000ULL)
-		return (void)printf("+ ");
-
-	printf("  ");
-}
-
-static void print_graph_duration(unsigned long long duration)
-{
-	unsigned long usecs = duration / 1000;
-	unsigned long nsecs_rem = duration % 1000;
-	/* log10(ULONG_MAX) + '\0' */
-	char msecs_str[21];
-	char nsecs_str[5];
-	int len;
-	int i;
-
-	sprintf(msecs_str, "%lu", usecs);
-
-	/* Print msecs */
-	len = printf("%lu", usecs);
-
-	/* Print nsecs (we don't want to exceed 7 numbers) */
-	if (len < 7) {
-		snprintf(nsecs_str, 8 - len, "%03lu", nsecs_rem);
-		len += printf(".%s", nsecs_str);
-	}
-
-	printf(" us ");
-
-	/* Print remaining spaces to fit the row's width */
-	for (i = len; i < 7; i++)
-		printf(" ");
-
-	printf("|  ");
-}
-
-static void
-print_graph_entry_leaf(struct event *event, void *data, struct record *ret_rec)
-{
-	unsigned long long rettime, calltime;
-	unsigned long long duration, depth;
-	unsigned long long val;
-	struct format_field *field;
-	struct func_map *func;
-	struct event *ret_event;
-	int type;
-	int i;
-
-	type = trace_parse_common_type(ret_rec->data);
-	ret_event = trace_find_event(type);
-
-	field = find_field(ret_event, "rettime");
-	if (!field)
-		die("can't find rettime in return graph");
-	rettime = read_size(ret_rec->data + field->offset, field->size);
-
-	field = find_field(ret_event, "calltime");
-	if (!field)
-		die("can't find rettime in return graph");
-	calltime = read_size(ret_rec->data + field->offset, field->size);
-
-	duration = rettime - calltime;
-
-	/* Overhead */
-	print_graph_overhead(duration);
-
-	/* Duration */
-	print_graph_duration(duration);
-
-	field = find_field(event, "depth");
-	if (!field)
-		die("can't find depth in entry graph");
-	depth = read_size(data + field->offset, field->size);
-
-	/* Function */
-	for (i = 0; i < (int)(depth * TRACE_GRAPH_INDENT); i++)
-		printf(" ");
-
-	field = find_field(event, "func");
-	if (!field)
-		die("can't find func in entry graph");
-	val = read_size(data + field->offset, field->size);
-	func = find_func(val);
-
-	if (func)
-		printf("%s();", func->func);
-	else
-		printf("%llx();", val);
-}
-
-static void print_graph_nested(struct event *event, void *data)
-{
-	struct format_field *field;
-	unsigned long long depth;
-	unsigned long long val;
-	struct func_map *func;
-	int i;
-
-	/* No overhead */
-	print_graph_overhead(-1);
-
-	/* No time */
-	printf("           |  ");
-
-	field = find_field(event, "depth");
-	if (!field)
-		die("can't find depth in entry graph");
-	depth = read_size(data + field->offset, field->size);
-
-	/* Function */
-	for (i = 0; i < (int)(depth * TRACE_GRAPH_INDENT); i++)
-		printf(" ");
-
-	field = find_field(event, "func");
-	if (!field)
-		die("can't find func in entry graph");
-	val = read_size(data + field->offset, field->size);
-	func = find_func(val);
-
-	if (func)
-		printf("%s() {", func->func);
-	else
-		printf("%llx() {", val);
-}
-
-static void
-pretty_print_func_ent(void *data, int size, struct event *event,
-		      int cpu, int pid, const char *comm,
-		      unsigned long secs, unsigned long usecs)
-{
-	struct format_field *field;
-	struct record *rec;
-	void *copy_data;
-	unsigned long val;
-
-	printf("%5lu.%06lu |  ", secs, usecs);
-
-	print_graph_cpu(cpu);
-	print_graph_proc(pid, comm);
-
-	printf(" | ");
-
-	if (latency_format) {
-		print_lat_fmt(data, size);
-		printf(" | ");
-	}
-
-	field = find_field(event, "func");
-	if (!field)
-		die("function entry does not have func field");
-
-	val = read_size(data + field->offset, field->size);
-
-	/*
-	 * peek_data may unmap the data pointer. Copy it first.
-	 */
-	copy_data = malloc_or_die(size);
-	memcpy(copy_data, data, size);
-	data = copy_data;
-
-	rec = trace_peek_data(cpu);
-	if (rec) {
-		rec = get_return_for_leaf(cpu, pid, val, rec);
-		if (rec) {
-			print_graph_entry_leaf(event, data, rec);
-			goto out_free;
-		}
-	}
-	print_graph_nested(event, data);
-out_free:
-	free(data);
-}
-
-static void
-pretty_print_func_ret(void *data, int size __unused, struct event *event,
-		      int cpu, int pid, const char *comm,
-		      unsigned long secs, unsigned long usecs)
-{
-	unsigned long long rettime, calltime;
-	unsigned long long duration, depth;
-	struct format_field *field;
-	int i;
-
-	printf("%5lu.%06lu |  ", secs, usecs);
-
-	print_graph_cpu(cpu);
-	print_graph_proc(pid, comm);
-
-	printf(" | ");
-
-	if (latency_format) {
-		print_lat_fmt(data, size);
-		printf(" | ");
-	}
-
-	field = find_field(event, "rettime");
-	if (!field)
-		die("can't find rettime in return graph");
-	rettime = read_size(data + field->offset, field->size);
-
-	field = find_field(event, "calltime");
-	if (!field)
-		die("can't find calltime in return graph");
-	calltime = read_size(data + field->offset, field->size);
-
-	duration = rettime - calltime;
-
-	/* Overhead */
-	print_graph_overhead(duration);
-
-	/* Duration */
-	print_graph_duration(duration);
-
-	field = find_field(event, "depth");
-	if (!field)
-		die("can't find depth in entry graph");
-	depth = read_size(data + field->offset, field->size);
-
-	/* Function */
-	for (i = 0; i < (int)(depth * TRACE_GRAPH_INDENT); i++)
-		printf(" ");
-
-	printf("}");
-}
-
-static void
-pretty_print_func_graph(void *data, int size, struct event *event,
-			int cpu, int pid, const char *comm,
-			unsigned long secs, unsigned long usecs)
-{
-	if (event->flags & EVENT_FL_ISFUNCENT)
-		pretty_print_func_ent(data, size, event,
-				      cpu, pid, comm, secs, usecs);
-	else if (event->flags & EVENT_FL_ISFUNCRET)
-		pretty_print_func_ret(data, size, event,
-				      cpu, pid, comm, secs, usecs);
-	printf("\n");
-}
-
-void print_event(int cpu, void *data, int size, unsigned long long nsecs,
-		  char *comm)
-{
-	struct event *event;
-	unsigned long secs;
-	unsigned long usecs;
-	int type;
-	int pid;
-
-	secs = nsecs / NSECS_PER_SEC;
-	nsecs -= secs * NSECS_PER_SEC;
-	usecs = nsecs / NSECS_PER_USEC;
-
-	type = trace_parse_common_type(data);
-
-	event = trace_find_event(type);
-	if (!event) {
-		warning("ug! no event found for type %d", type);
-		return;
-	}
-
-	pid = trace_parse_common_pid(data);
-
-	if (event->flags & (EVENT_FL_ISFUNCENT | EVENT_FL_ISFUNCRET))
-		return pretty_print_func_graph(data, size, event, cpu,
-					       pid, comm, secs, usecs);
-
-	if (latency_format) {
-		printf("%8.8s-%-5d %3d",
-		       comm, pid, cpu);
-		print_lat_fmt(data, size);
-	} else
-		printf("%16s-%-5d [%03d]", comm, pid,  cpu);
-
-	printf(" %5lu.%06lu: %s: ", secs, usecs, event->name);
-
-	if (event->flags & EVENT_FL_FAILED) {
-		printf("EVENT '%s' FAILED TO PARSE\n",
-		       event->name);
-		return;
-	}
-
-	pretty_print(data, size, event);
-	printf("\n");
-}
-
-static void print_fields(struct print_flag_sym *field)
-{
-	printf("{ %s, %s }", field->value, field->str);
-	if (field->next) {
-		printf(", ");
-		print_fields(field->next);
-	}
-}
-
-static void print_args(struct print_arg *args)
-{
-	int print_paren = 1;
-
-	switch (args->type) {
-	case PRINT_NULL:
-		printf("null");
-		break;
-	case PRINT_ATOM:
-		printf("%s", args->atom.atom);
-		break;
-	case PRINT_FIELD:
-		printf("REC->%s", args->field.name);
-		break;
-	case PRINT_FLAGS:
-		printf("__print_flags(");
-		print_args(args->flags.field);
-		printf(", %s, ", args->flags.delim);
-		print_fields(args->flags.flags);
-		printf(")");
-		break;
-	case PRINT_SYMBOL:
-		printf("__print_symbolic(");
-		print_args(args->symbol.field);
-		printf(", ");
-		print_fields(args->symbol.symbols);
-		printf(")");
-		break;
-	case PRINT_STRING:
-		printf("__get_str(%s)", args->string.string);
-		break;
-	case PRINT_TYPE:
-		printf("(%s)", args->typecast.type);
-		print_args(args->typecast.item);
-		break;
-	case PRINT_OP:
-		if (strcmp(args->op.op, ":") == 0)
-			print_paren = 0;
-		if (print_paren)
-			printf("(");
-		print_args(args->op.left);
-		printf(" %s ", args->op.op);
-		print_args(args->op.right);
-		if (print_paren)
-			printf(")");
-		break;
-	default:
-		/* we should warn... */
-		return;
-	}
-	if (args->next) {
-		printf("\n");
-		print_args(args->next);
-	}
-}
-
-int parse_ftrace_file(char *buf, unsigned long size)
-{
-	struct format_field *field;
-	struct print_arg *arg, **list;
-	struct event *event;
-	int ret;
-
-	init_input_buf(buf, size);
-
-	event = alloc_event();
-	if (!event)
-		return -ENOMEM;
-
-	event->flags |= EVENT_FL_ISFTRACE;
-
-	event->name = event_read_name();
-	if (!event->name)
-		die("failed to read ftrace event name");
-
-	if (strcmp(event->name, "function") == 0)
-		event->flags |= EVENT_FL_ISFUNC;
-
-	else if (strcmp(event->name, "funcgraph_entry") == 0)
-		event->flags |= EVENT_FL_ISFUNCENT;
-
-	else if (strcmp(event->name, "funcgraph_exit") == 0)
-		event->flags |= EVENT_FL_ISFUNCRET;
-
-	else if (strcmp(event->name, "bprint") == 0)
-		event->flags |= EVENT_FL_ISBPRINT;
-
-	event->id = event_read_id();
-	if (event->id < 0)
-		die("failed to read ftrace event id");
-
-	add_event(event);
-
-	ret = event_read_format(event);
-	if (ret < 0)
-		die("failed to read ftrace event format");
-
-	ret = event_read_print(event);
-	if (ret < 0)
-		die("failed to read ftrace event print fmt");
-
-	/* New ftrace handles args */
-	if (ret > 0)
-		return 0;
-	/*
-	 * The arguments for ftrace files are parsed by the fields.
-	 * Set up the fields as their arguments.
-	 */
-	list = &event->print_fmt.args;
-	for (field = event->format.fields; field; field = field->next) {
-		arg = malloc_or_die(sizeof(*arg));
-		memset(arg, 0, sizeof(*arg));
-		*list = arg;
-		list = &arg->next;
-		arg->type = PRINT_FIELD;
-		arg->field.name = field->name;
-		arg->field.field = field;
-	}
-	return 0;
-}
-
-int parse_event_file(char *buf, unsigned long size, char *sys)
-{
-	struct event *event;
-	int ret;
-
-	init_input_buf(buf, size);
-
-	event = alloc_event();
-	if (!event)
-		return -ENOMEM;
-
-	event->name = event_read_name();
-	if (!event->name)
-		die("failed to read event name");
-
-	event->id = event_read_id();
-	if (event->id < 0)
-		die("failed to read event id");
-
-	ret = event_read_format(event);
-	if (ret < 0) {
-		warning("failed to read event format for %s", event->name);
-		goto event_failed;
-	}
-
-	ret = event_read_print(event);
-	if (ret < 0) {
-		warning("failed to read event print fmt for %s", event->name);
-		goto event_failed;
-	}
-
-	event->system = strdup(sys);
-
-#define PRINT_ARGS 0
-	if (PRINT_ARGS && event->print_fmt.args)
-		print_args(event->print_fmt.args);
-
-	add_event(event);
-	return 0;
-
- event_failed:
-	event->flags |= EVENT_FL_FAILED;
-	/* still add it even if it failed */
-	add_event(event);
-	return -1;
-}
-
-void parse_set_info(int nr_cpus, int long_sz)
-{
-	cpus = nr_cpus;
-	long_size = long_sz;
-}
-
-int common_pc(struct scripting_context *context)
-{
-	return parse_common_pc(context->event_data);
-}
-
-int common_flags(struct scripting_context *context)
-{
-	return parse_common_flags(context->event_data);
-}
-
-int common_lock_depth(struct scripting_context *context)
-{
-	return parse_common_lock_depth(context->event_data);
-}
diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index f55cc3a765a..e113e180c48 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -18,8 +18,6 @@
  *
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
-#define _FILE_OFFSET_BITS 64
-
 #include <dirent.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -33,7 +31,6 @@
 #include <pthread.h>
 #include <fcntl.h>
 #include <unistd.h>
-#include <ctype.h>
 #include <errno.h>
 
 #include "../perf.h"
@@ -42,18 +39,10 @@
 
 static int input_fd;
 
-static int read_page;
-
-int file_bigendian;
-int host_bigendian;
-static int long_size;
-
-static unsigned long	page_size;
-
-static ssize_t calc_data_size;
+static ssize_t trace_data_size;
 static bool repipe;
 
-static int do_read(int fd, void *buf, int size)
+static int __do_read(int fd, void *buf, int size)
 {
 	int rsize = size;
 
@@ -66,8 +55,10 @@ static int do_read(int fd, void *buf, int size)
 		if (repipe) {
 			int retw = write(STDOUT_FILENO, buf, ret);
 
-			if (retw <= 0 || retw != ret)
-				die("repiping input file");
+			if (retw <= 0 || retw != ret) {
+				pr_debug("repiping input file");
+				return -1;
+			}
 		}
 
 		size -= ret;
@@ -77,17 +68,18 @@ static int do_read(int fd, void *buf, int size)
 	return rsize;
 }
 
-static int read_or_die(void *data, int size)
+static int do_read(void *data, int size)
 {
 	int r;
 
-	r = do_read(input_fd, data, size);
-	if (r <= 0)
-		die("reading input file (size expected=%d received=%d)",
-		    size, r);
+	r = __do_read(input_fd, data, size);
+	if (r <= 0) {
+		pr_debug("reading input file (size expected=%d received=%d)",
+			 size, r);
+		return -1;
+	}
 
-	if (calc_data_size)
-		calc_data_size += r;
+	trace_data_size += r;
 
 	return r;
 }
@@ -100,25 +92,27 @@ static void skip(int size)
 
 	while (size) {
 		r = size > BUFSIZ ? BUFSIZ : size;
-		read_or_die(buf, r);
+		do_read(buf, r);
 		size -= r;
 	};
 }
 
-static unsigned int read4(void)
+static unsigned int read4(struct pevent *pevent)
 {
 	unsigned int data;
 
-	read_or_die(&data, 4);
-	return __data2host4(data);
+	if (do_read(&data, 4) < 0)
+		return 0;
+	return __data2host4(pevent, data);
 }
 
-static unsigned long long read8(void)
+static unsigned long long read8(struct pevent *pevent)
 {
 	unsigned long long data;
 
-	read_or_die(&data, 8);
-	return __data2host8(data);
+	if (do_read(&data, 8) < 0)
+		return 0;
+	return __data2host8(pevent, data);
 }
 
 static char *read_string(void)
@@ -131,17 +125,23 @@ static char *read_string(void)
 
 	for (;;) {
 		r = read(input_fd, &c, 1);
-		if (r < 0)
-			die("reading input file");
+		if (r < 0) {
+			pr_debug("reading input file");
+			goto out;
+		}
 
-		if (!r)
-			die("no data");
+		if (!r) {
+			pr_debug("no data");
+			goto out;
+		}
 
 		if (repipe) {
 			int retw = write(STDOUT_FILENO, &c, 1);
 
-			if (retw <= 0 || retw != r)
-				die("repiping input file string");
+			if (retw <= 0 || retw != r) {
+				pr_debug("repiping input file string");
+				goto out;
+			}
 		}
 
 		buf[size++] = c;
@@ -150,335 +150,200 @@ static char *read_string(void)
 			break;
 	}
 
-	if (calc_data_size)
-		calc_data_size += size;
-
-	str = malloc_or_die(size);
-	memcpy(str, buf, size);
+	trace_data_size += size;
 
+	str = malloc(size);
+	if (str)
+		memcpy(str, buf, size);
+out:
 	return str;
 }
 
-static void read_proc_kallsyms(void)
+static int read_proc_kallsyms(struct pevent *pevent)
 {
 	unsigned int size;
 	char *buf;
 
-	size = read4();
+	size = read4(pevent);
 	if (!size)
-		return;
+		return 0;
+
+	buf = malloc(size + 1);
+	if (buf == NULL)
+		return -1;
 
-	buf = malloc_or_die(size + 1);
-	read_or_die(buf, size);
+	if (do_read(buf, size) < 0) {
+		free(buf);
+		return -1;
+	}
 	buf[size] = '\0';
 
-	parse_proc_kallsyms(buf, size);
+	parse_proc_kallsyms(pevent, buf, size);
 
 	free(buf);
+	return 0;
 }
 
-static void read_ftrace_printk(void)
+static int read_ftrace_printk(struct pevent *pevent)
 {
 	unsigned int size;
 	char *buf;
 
-	size = read4();
+	/* it can have 0 size */
+	size = read4(pevent);
 	if (!size)
-		return;
+		return 0;
+
+	buf = malloc(size);
+	if (buf == NULL)
+		return -1;
 
-	buf = malloc_or_die(size);
-	read_or_die(buf, size);
+	if (do_read(buf, size) < 0) {
+		free(buf);
+		return -1;
+	}
 
-	parse_ftrace_printk(buf, size);
+	parse_ftrace_printk(pevent, buf, size);
 
 	free(buf);
+	return 0;
 }
 
-static void read_header_files(void)
+static int read_header_files(struct pevent *pevent)
 {
 	unsigned long long size;
-	char *header_event;
+	char *header_page;
 	char buf[BUFSIZ];
+	int ret = 0;
 
-	read_or_die(buf, 12);
+	if (do_read(buf, 12) < 0)
+		return -1;
 
-	if (memcmp(buf, "header_page", 12) != 0)
-		die("did not read header page");
+	if (memcmp(buf, "header_page", 12) != 0) {
+		pr_debug("did not read header page");
+		return -1;
+	}
 
-	size = read8();
-	skip(size);
+	size = read8(pevent);
+
+	header_page = malloc(size);
+	if (header_page == NULL)
+		return -1;
 
-	/*
-	 * The size field in the page is of type long,
-	 * use that instead, since it represents the kernel.
-	 */
-	long_size = header_page_size_size;
+	if (do_read(header_page, size) < 0) {
+		pr_debug("did not read header page");
+		free(header_page);
+		return -1;
+	}
+
+	if (!pevent_parse_header_page(pevent, header_page, size,
+				      pevent_get_long_size(pevent))) {
+		/*
+		 * The commit field in the page is of type long,
+		 * use that instead, since it represents the kernel.
+		 */
+		pevent_set_long_size(pevent, pevent->header_page_size_size);
+	}
+	free(header_page);
 
-	read_or_die(buf, 13);
-	if (memcmp(buf, "header_event", 13) != 0)
-		die("did not read header event");
+	if (do_read(buf, 13) < 0)
+		return -1;
 
-	size = read8();
-	header_event = malloc_or_die(size);
-	read_or_die(header_event, size);
-	free(header_event);
+	if (memcmp(buf, "header_event", 13) != 0) {
+		pr_debug("did not read header event");
+		return -1;
+	}
+
+	size = read8(pevent);
+	skip(size);
+
+	return ret;
 }
 
-static void read_ftrace_file(unsigned long long size)
+static int read_ftrace_file(struct pevent *pevent, unsigned long long size)
 {
 	char *buf;
 
-	buf = malloc_or_die(size);
-	read_or_die(buf, size);
-	parse_ftrace_file(buf, size);
+	buf = malloc(size);
+	if (buf == NULL)
+		return -1;
+
+	if (do_read(buf, size) < 0) {
+		free(buf);
+		return -1;
+	}
+
+	parse_ftrace_file(pevent, buf, size);
 	free(buf);
+	return 0;
 }
 
-static void read_event_file(char *sys, unsigned long long size)
+static int read_event_file(struct pevent *pevent, char *sys,
+			    unsigned long long size)
 {
 	char *buf;
 
-	buf = malloc_or_die(size);
-	read_or_die(buf, size);
-	parse_event_file(buf, size, sys);
+	buf = malloc(size);
+	if (buf == NULL)
+		return -1;
+
+	if (do_read(buf, size) < 0) {
+		free(buf);
+		return -1;
+	}
+
+	parse_event_file(pevent, buf, size, sys);
 	free(buf);
+	return 0;
 }
 
-static void read_ftrace_files(void)
+static int read_ftrace_files(struct pevent *pevent)
 {
 	unsigned long long size;
 	int count;
 	int i;
+	int ret;
 
-	count = read4();
+	count = read4(pevent);
 
 	for (i = 0; i < count; i++) {
-		size = read8();
-		read_ftrace_file(size);
+		size = read8(pevent);
+		ret = read_ftrace_file(pevent, size);
+		if (ret)
+			return ret;
 	}
+	return 0;
 }
 
-static void read_event_files(void)
+static int read_event_files(struct pevent *pevent)
 {
 	unsigned long long size;
 	char *sys;
 	int systems;
 	int count;
 	int i,x;
+	int ret;
 
-	systems = read4();
+	systems = read4(pevent);
 
 	for (i = 0; i < systems; i++) {
 		sys = read_string();
+		if (sys == NULL)
+			return -1;
 
-		count = read4();
-		for (x=0; x < count; x++) {
-			size = read8();
-			read_event_file(sys, size);
-		}
-	}
-}
-
-struct cpu_data {
-	unsigned long long	offset;
-	unsigned long long	size;
-	unsigned long long	timestamp;
-	struct record		*next;
-	char			*page;
-	int			cpu;
-	int			index;
-	int			page_size;
-};
-
-static struct cpu_data *cpu_data;
-
-static void update_cpu_data_index(int cpu)
-{
-	cpu_data[cpu].offset += page_size;
-	cpu_data[cpu].size -= page_size;
-	cpu_data[cpu].index = 0;
-}
-
-static void get_next_page(int cpu)
-{
-	off_t save_seek;
-	off_t ret;
-
-	if (!cpu_data[cpu].page)
-		return;
-
-	if (read_page) {
-		if (cpu_data[cpu].size <= page_size) {
-			free(cpu_data[cpu].page);
-			cpu_data[cpu].page = NULL;
-			return;
-		}
-
-		update_cpu_data_index(cpu);
-
-		/* other parts of the code may expect the pointer to not move */
-		save_seek = lseek(input_fd, 0, SEEK_CUR);
-
-		ret = lseek(input_fd, cpu_data[cpu].offset, SEEK_SET);
-		if (ret == (off_t)-1)
-			die("failed to lseek");
-		ret = read(input_fd, cpu_data[cpu].page, page_size);
-		if (ret < 0)
-			die("failed to read page");
-
-		/* reset the file pointer back */
-		lseek(input_fd, save_seek, SEEK_SET);
-
-		return;
-	}
-
-	munmap(cpu_data[cpu].page, page_size);
-	cpu_data[cpu].page = NULL;
-
-	if (cpu_data[cpu].size <= page_size)
-		return;
-
-	update_cpu_data_index(cpu);
-
-	cpu_data[cpu].page = mmap(NULL, page_size, PROT_READ, MAP_PRIVATE,
-				  input_fd, cpu_data[cpu].offset);
-	if (cpu_data[cpu].page == MAP_FAILED)
-		die("failed to mmap cpu %d at offset 0x%llx",
-		    cpu, cpu_data[cpu].offset);
-}
-
-static unsigned int type_len4host(unsigned int type_len_ts)
-{
-	if (file_bigendian)
-		return (type_len_ts >> 27) & ((1 << 5) - 1);
-	else
-		return type_len_ts & ((1 << 5) - 1);
-}
-
-static unsigned int ts4host(unsigned int type_len_ts)
-{
-	if (file_bigendian)
-		return type_len_ts & ((1 << 27) - 1);
-	else
-		return type_len_ts >> 5;
-}
-
-static int calc_index(void *ptr, int cpu)
-{
-	return (unsigned long)ptr - (unsigned long)cpu_data[cpu].page;
-}
+		count = read4(pevent);
 
-struct record *trace_peek_data(int cpu)
-{
-	struct record *data;
-	void *page = cpu_data[cpu].page;
-	int idx = cpu_data[cpu].index;
-	void *ptr = page + idx;
-	unsigned long long extend;
-	unsigned int type_len_ts;
-	unsigned int type_len;
-	unsigned int delta;
-	unsigned int length = 0;
-
-	if (cpu_data[cpu].next)
-		return cpu_data[cpu].next;
-
-	if (!page)
-		return NULL;
-
-	if (!idx) {
-		/* FIXME: handle header page */
-		if (header_page_ts_size != 8)
-			die("expected a long long type for timestamp");
-		cpu_data[cpu].timestamp = data2host8(ptr);
-		ptr += 8;
-		switch (header_page_size_size) {
-		case 4:
-			cpu_data[cpu].page_size = data2host4(ptr);
-			ptr += 4;
-			break;
-		case 8:
-			cpu_data[cpu].page_size = data2host8(ptr);
-			ptr += 8;
-			break;
-		default:
-			die("bad long size");
+		for (x=0; x < count; x++) {
+			size = read8(pevent);
+			ret = read_event_file(pevent, sys, size);
+			if (ret)
+				return ret;
 		}
-		ptr = cpu_data[cpu].page + header_page_data_offset;
 	}
-
-read_again:
-	idx = calc_index(ptr, cpu);
-
-	if (idx >= cpu_data[cpu].page_size) {
-		get_next_page(cpu);
-		return trace_peek_data(cpu);
-	}
-
-	type_len_ts = data2host4(ptr);
-	ptr += 4;
-
-	type_len = type_len4host(type_len_ts);
-	delta = ts4host(type_len_ts);
-
-	switch (type_len) {
-	case RINGBUF_TYPE_PADDING:
-		if (!delta)
-			die("error, hit unexpected end of page");
-		length = data2host4(ptr);
-		ptr += 4;
-		length *= 4;
-		ptr += length;
-		goto read_again;
-
-	case RINGBUF_TYPE_TIME_EXTEND:
-		extend = data2host4(ptr);
-		ptr += 4;
-		extend <<= TS_SHIFT;
-		extend += delta;
-		cpu_data[cpu].timestamp += extend;
-		goto read_again;
-
-	case RINGBUF_TYPE_TIME_STAMP:
-		ptr += 12;
-		break;
-	case 0:
-		length = data2host4(ptr);
-		ptr += 4;
-		die("here! length=%d", length);
-		break;
-	default:
-		length = type_len * 4;
-		break;
-	}
-
-	cpu_data[cpu].timestamp += delta;
-
-	data = malloc_or_die(sizeof(*data));
-	memset(data, 0, sizeof(*data));
-
-	data->ts = cpu_data[cpu].timestamp;
-	data->size = length;
-	data->data = ptr;
-	ptr += length;
-
-	cpu_data[cpu].index = calc_index(ptr, cpu);
-	cpu_data[cpu].next = data;
-
-	return data;
-}
-
-struct record *trace_read_data(int cpu)
-{
-	struct record *data;
-
-	data = trace_peek_data(cpu);
-	cpu_data[cpu].next = NULL;
-
-	return data;
+	return 0;
 }
 
-ssize_t trace_report(int fd, bool __repipe)
+ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe)
 {
 	char buf[BUFSIZ];
 	char test[] = { 23, 8, 68 };
@@ -486,54 +351,94 @@ ssize_t trace_report(int fd, bool __repipe)
 	int show_version = 0;
 	int show_funcs = 0;
 	int show_printk = 0;
-	ssize_t size;
+	ssize_t size = -1;
+	int file_bigendian;
+	int host_bigendian;
+	int file_long_size;
+	int file_page_size;
+	struct pevent *pevent = NULL;
+	int err;
 
-	calc_data_size = 1;
 	repipe = __repipe;
-
 	input_fd = fd;
 
-	read_or_die(buf, 3);
-	if (memcmp(buf, test, 3) != 0)
-		die("no trace data in the file");
+	if (do_read(buf, 3) < 0)
+		return -1;
+	if (memcmp(buf, test, 3) != 0) {
+		pr_debug("no trace data in the file");
+		return -1;
+	}
 
-	read_or_die(buf, 7);
-	if (memcmp(buf, "tracing", 7) != 0)
-		die("not a trace file (missing 'tracing' tag)");
+	if (do_read(buf, 7) < 0)
+		return -1;
+	if (memcmp(buf, "tracing", 7) != 0) {
+		pr_debug("not a trace file (missing 'tracing' tag)");
+		return -1;
+	}
 
 	version = read_string();
+	if (version == NULL)
+		return -1;
 	if (show_version)
 		printf("version = %s\n", version);
 	free(version);
 
-	read_or_die(buf, 1);
+	if (do_read(buf, 1) < 0)
+		return -1;
 	file_bigendian = buf[0];
 	host_bigendian = bigendian();
 
-	read_or_die(buf, 1);
-	long_size = buf[0];
-
-	page_size = read4();
-
-	read_header_files();
-
-	read_ftrace_files();
-	read_event_files();
-	read_proc_kallsyms();
-	read_ftrace_printk();
+	if (trace_event__init(tevent)) {
+		pr_debug("trace_event__init failed");
+		goto out;
+	}
 
-	size = calc_data_size - 1;
-	calc_data_size = 0;
+	pevent = tevent->pevent;
+
+	pevent_set_flag(pevent, PEVENT_NSEC_OUTPUT);
+	pevent_set_file_bigendian(pevent, file_bigendian);
+	pevent_set_host_bigendian(pevent, host_bigendian);
+
+	if (do_read(buf, 1) < 0)
+		goto out;
+	file_long_size = buf[0];
+
+	file_page_size = read4(pevent);
+	if (!file_page_size)
+		goto out;
+
+	pevent_set_long_size(pevent, file_long_size);
+	pevent_set_page_size(pevent, file_page_size);
+
+	err = read_header_files(pevent);
+	if (err)
+		goto out;
+	err = read_ftrace_files(pevent);
+	if (err)
+		goto out;
+	err = read_event_files(pevent);
+	if (err)
+		goto out;
+	err = read_proc_kallsyms(pevent);
+	if (err)
+		goto out;
+	err = read_ftrace_printk(pevent);
+	if (err)
+		goto out;
+
+	size = trace_data_size;
 	repipe = false;
 
 	if (show_funcs) {
-		print_funcs();
-		return size;
-	}
-	if (show_printk) {
-		print_printk();
-		return size;
+		pevent_print_funcs(pevent);
+	} else if (show_printk) {
+		pevent_print_printk(pevent);
 	}
 
+	pevent = NULL;
+
+out:
+	if (pevent)
+		trace_event__cleanup(tevent);
 	return size;
 }
diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c
index 7ea983acfae..57aaccc1692 100644
--- a/tools/perf/util/trace-event-scripting.c
+++ b/tools/perf/util/trace-event-scripting.c
@@ -22,7 +22,6 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
-#include <ctype.h>
 #include <errno.h>
 
 #include "../perf.h"
@@ -36,11 +35,11 @@ static int stop_script_unsupported(void)
 	return 0;
 }
 
-static void process_event_unsupported(int cpu __unused,
-				      void *data __unused,
-				      int size __unused,
-				      unsigned long long nsecs __unused,
-				      char *comm __unused)
+static void process_event_unsupported(union perf_event *event __maybe_unused,
+				      struct perf_sample *sample __maybe_unused,
+				      struct perf_evsel *evsel __maybe_unused,
+				      struct thread *thread __maybe_unused,
+				      struct addr_location *al __maybe_unused)
 {
 }
 
@@ -53,16 +52,19 @@ static void print_python_unsupported_msg(void)
 		"\n  etc.\n");
 }
 
-static int python_start_script_unsupported(const char *script __unused,
-					   int argc __unused,
-					   const char **argv __unused)
+static int python_start_script_unsupported(const char *script __maybe_unused,
+					   int argc __maybe_unused,
+					   const char **argv __maybe_unused)
 {
 	print_python_unsupported_msg();
 
 	return -1;
 }
 
-static int python_generate_script_unsupported(const char *outfile __unused)
+static int python_generate_script_unsupported(struct pevent *pevent
+					      __maybe_unused,
+					      const char *outfile
+					      __maybe_unused)
 {
 	print_python_unsupported_msg();
 
@@ -97,7 +99,7 @@ void setup_python_scripting(void)
 	register_python_scripting(&python_scripting_unsupported_ops);
 }
 #else
-struct scripting_ops python_scripting_ops;
+extern struct scripting_ops python_scripting_ops;
 
 void setup_python_scripting(void)
 {
@@ -114,16 +116,18 @@ static void print_perl_unsupported_msg(void)
 		"\n  etc.\n");
 }
 
-static int perl_start_script_unsupported(const char *script __unused,
-					 int argc __unused,
-					 const char **argv __unused)
+static int perl_start_script_unsupported(const char *script __maybe_unused,
+					 int argc __maybe_unused,
+					 const char **argv __maybe_unused)
 {
 	print_perl_unsupported_msg();
 
 	return -1;
 }
 
-static int perl_generate_script_unsupported(const char *outfile __unused)
+static int perl_generate_script_unsupported(struct pevent *pevent
+					    __maybe_unused,
+					    const char *outfile __maybe_unused)
 {
 	print_perl_unsupported_msg();
 
@@ -158,7 +162,7 @@ void setup_perl_scripting(void)
 	register_perl_scripting(&perl_scripting_unsupported_ops);
 }
 #else
-struct scripting_ops perl_scripting_ops;
+extern struct scripting_ops perl_scripting_ops;
 
 void setup_perl_scripting(void)
 {
diff --git a/tools/perf/util/trace-event.c b/tools/perf/util/trace-event.c
new file mode 100644
index 00000000000..6322d37164c
--- /dev/null
+++ b/tools/perf/util/trace-event.c
@@ -0,0 +1,82 @@
+
+#include <stdio.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <errno.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <linux/kernel.h>
+#include <traceevent/event-parse.h>
+#include "trace-event.h"
+#include "util.h"
+
+/*
+ * global trace_event object used by trace_event__tp_format
+ *
+ * TODO There's no cleanup call for this. Add some sort of
+ * __exit function support and call trace_event__cleanup
+ * there.
+ */
+static struct trace_event tevent;
+
+int trace_event__init(struct trace_event *t)
+{
+	struct pevent *pevent = pevent_alloc();
+
+	if (pevent) {
+		t->plugin_list = traceevent_load_plugins(pevent);
+		t->pevent  = pevent;
+	}
+
+	return pevent ? 0 : -1;
+}
+
+void trace_event__cleanup(struct trace_event *t)
+{
+	traceevent_unload_plugins(t->plugin_list, t->pevent);
+	pevent_free(t->pevent);
+}
+
+static struct event_format*
+tp_format(const char *sys, const char *name)
+{
+	struct pevent *pevent = tevent.pevent;
+	struct event_format *event = NULL;
+	char path[PATH_MAX];
+	size_t size;
+	char *data;
+
+	scnprintf(path, PATH_MAX, "%s/%s/%s/format",
+		  tracing_events_path, sys, name);
+
+	if (filename__read_str(path, &data, &size))
+		return NULL;
+
+	pevent_parse_format(pevent, &event, data, size, sys);
+
+	free(data);
+	return event;
+}
+
+struct event_format*
+trace_event__tp_format(const char *sys, const char *name)
+{
+	static bool initialized;
+
+	if (!initialized) {
+		int be = traceevent_host_bigendian();
+		struct pevent *pevent;
+
+		if (trace_event__init(&tevent))
+			return NULL;
+
+		pevent = tevent.pevent;
+		pevent_set_flag(pevent, PEVENT_NSEC_OUTPUT);
+		pevent_set_file_bigendian(pevent, be);
+		pevent_set_host_bigendian(pevent, be);
+		initialized = true;
+	}
+
+	return tp_format(sys, name);
+}
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index b3e86b1e444..7b6d6868832 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -1,287 +1,76 @@
-#ifndef __PERF_TRACE_EVENTS_H
-#define __PERF_TRACE_EVENTS_H
+#ifndef _PERF_UTIL_TRACE_EVENT_H
+#define _PERF_UTIL_TRACE_EVENT_H
 
-#include <stdbool.h>
+#include <traceevent/event-parse.h>
 #include "parse-events.h"
 
-#define __unused __attribute__((unused))
+struct machine;
+struct perf_sample;
+union perf_event;
+struct perf_tool;
+struct thread;
+struct plugin_list;
 
-
-#ifndef PAGE_MASK
-#define PAGE_MASK (page_size - 1)
-#endif
-
-enum {
-	RINGBUF_TYPE_PADDING		= 29,
-	RINGBUF_TYPE_TIME_EXTEND	= 30,
-	RINGBUF_TYPE_TIME_STAMP		= 31,
-};
-
-#ifndef TS_SHIFT
-#define TS_SHIFT		27
-#endif
-
-#define NSECS_PER_SEC		1000000000ULL
-#define NSECS_PER_USEC		1000ULL
-
-enum format_flags {
-	FIELD_IS_ARRAY		= 1,
-	FIELD_IS_POINTER	= 2,
-	FIELD_IS_SIGNED		= 4,
-	FIELD_IS_STRING		= 8,
-	FIELD_IS_DYNAMIC	= 16,
-	FIELD_IS_FLAG		= 32,
-	FIELD_IS_SYMBOLIC	= 64,
-};
-
-struct format_field {
-	struct format_field	*next;
-	char			*type;
-	char			*name;
-	int			offset;
-	int			size;
-	unsigned long		flags;
+struct trace_event {
+	struct pevent		*pevent;
+	struct plugin_list	*plugin_list;
 };
 
-struct format {
-	int			nr_common;
-	int			nr_fields;
-	struct format_field	*common_fields;
-	struct format_field	*fields;
-};
-
-struct print_arg_atom {
-	char			*atom;
-};
-
-struct print_arg_string {
-	char			*string;
-	int			offset;
-};
-
-struct print_arg_field {
-	char			*name;
-	struct format_field	*field;
-};
-
-struct print_flag_sym {
-	struct print_flag_sym	*next;
-	char			*value;
-	char			*str;
-};
-
-struct print_arg_typecast {
-	char 			*type;
-	struct print_arg	*item;
-};
-
-struct print_arg_flags {
-	struct print_arg	*field;
-	char			*delim;
-	struct print_flag_sym	*flags;
-};
-
-struct print_arg_symbol {
-	struct print_arg	*field;
-	struct print_flag_sym	*symbols;
-};
-
-struct print_arg;
-
-struct print_arg_op {
-	char			*op;
-	int			prio;
-	struct print_arg	*left;
-	struct print_arg	*right;
-};
-
-struct print_arg_func {
-	char			*name;
-	struct print_arg	*args;
-};
-
-enum print_arg_type {
-	PRINT_NULL,
-	PRINT_ATOM,
-	PRINT_FIELD,
-	PRINT_FLAGS,
-	PRINT_SYMBOL,
-	PRINT_TYPE,
-	PRINT_STRING,
-	PRINT_OP,
-};
-
-struct print_arg {
-	struct print_arg		*next;
-	enum print_arg_type		type;
-	union {
-		struct print_arg_atom		atom;
-		struct print_arg_field		field;
-		struct print_arg_typecast	typecast;
-		struct print_arg_flags		flags;
-		struct print_arg_symbol		symbol;
-		struct print_arg_func		func;
-		struct print_arg_string		string;
-		struct print_arg_op		op;
-	};
-};
-
-struct print_fmt {
-	char			*format;
-	struct print_arg	*args;
-};
-
-struct event {
-	struct event		*next;
-	char			*name;
-	int			id;
-	int			flags;
-	struct format		format;
-	struct print_fmt	print_fmt;
-	char			*system;
-};
-
-enum {
-	EVENT_FL_ISFTRACE	= 0x01,
-	EVENT_FL_ISPRINT	= 0x02,
-	EVENT_FL_ISBPRINT	= 0x04,
-	EVENT_FL_ISFUNC		= 0x08,
-	EVENT_FL_ISFUNCENT	= 0x10,
-	EVENT_FL_ISFUNCRET	= 0x20,
-
-	EVENT_FL_FAILED		= 0x80000000
-};
-
-struct record {
-	unsigned long long ts;
-	int size;
-	void *data;
-};
-
-struct record *trace_peek_data(int cpu);
-struct record *trace_read_data(int cpu);
-
-void parse_set_info(int nr_cpus, int long_sz);
-
-ssize_t trace_report(int fd, bool repipe);
-
-void *malloc_or_die(unsigned int size);
-
-void parse_cmdlines(char *file, int size);
-void parse_proc_kallsyms(char *file, unsigned int size);
-void parse_ftrace_printk(char *file, unsigned int size);
-
-void print_funcs(void);
-void print_printk(void);
-
-int parse_ftrace_file(char *buf, unsigned long size);
-int parse_event_file(char *buf, unsigned long size, char *sys);
-void print_event(int cpu, void *data, int size, unsigned long long nsecs,
-		  char *comm);
-
-extern int file_bigendian;
-extern int host_bigendian;
+int trace_event__init(struct trace_event *t);
+void trace_event__cleanup(struct trace_event *t);
+struct event_format*
+trace_event__tp_format(const char *sys, const char *name);
 
 int bigendian(void);
 
-static inline unsigned short __data2host2(unsigned short data)
-{
-	unsigned short swap;
-
-	if (host_bigendian == file_bigendian)
-		return data;
-
-	swap = ((data & 0xffULL) << 8) |
-		((data & (0xffULL << 8)) >> 8);
-
-	return swap;
-}
-
-static inline unsigned int __data2host4(unsigned int data)
-{
-	unsigned int swap;
-
-	if (host_bigendian == file_bigendian)
-		return data;
+void event_format__print(struct event_format *event,
+			 int cpu, void *data, int size);
 
-	swap = ((data & 0xffULL) << 24) |
-		((data & (0xffULL << 8)) << 8) |
-		((data & (0xffULL << 16)) >> 8) |
-		((data & (0xffULL << 24)) >> 24);
+int parse_ftrace_file(struct pevent *pevent, char *buf, unsigned long size);
+int parse_event_file(struct pevent *pevent,
+		     char *buf, unsigned long size, char *sys);
 
-	return swap;
-}
+unsigned long long
+raw_field_value(struct event_format *event, const char *name, void *data);
 
-static inline unsigned long long __data2host8(unsigned long long data)
-{
-	unsigned long long swap;
+void parse_proc_kallsyms(struct pevent *pevent, char *file, unsigned int size);
+void parse_ftrace_printk(struct pevent *pevent, char *file, unsigned int size);
 
-	if (host_bigendian == file_bigendian)
-		return data;
+ssize_t trace_report(int fd, struct trace_event *tevent, bool repipe);
 
-	swap = ((data & 0xffULL) << 56) |
-		((data & (0xffULL << 8)) << 40) |
-		((data & (0xffULL << 16)) << 24) |
-		((data & (0xffULL << 24)) << 8) |
-		((data & (0xffULL << 32)) >> 8) |
-		((data & (0xffULL << 40)) >> 24) |
-		((data & (0xffULL << 48)) >> 40) |
-		((data & (0xffULL << 56)) >> 56);
+struct event_format *trace_find_next_event(struct pevent *pevent,
+					   struct event_format *event);
+unsigned long long read_size(struct event_format *event, void *ptr, int size);
+unsigned long long eval_flag(const char *flag);
 
-	return swap;
-}
+int read_tracing_data(int fd, struct list_head *pattrs);
 
-#define data2host2(ptr)		__data2host2(*(unsigned short *)ptr)
-#define data2host4(ptr)		__data2host4(*(unsigned int *)ptr)
-#define data2host8(ptr)		({				\
-	unsigned long long __val;				\
-								\
-	memcpy(&__val, (ptr), sizeof(unsigned long long));	\
-	__data2host8(__val);					\
-})
+struct tracing_data {
+	/* size is only valid if temp is 'true' */
+	ssize_t size;
+	bool temp;
+	char temp_file[50];
+};
 
-extern int header_page_ts_offset;
-extern int header_page_ts_size;
-extern int header_page_size_offset;
-extern int header_page_size_size;
-extern int header_page_data_offset;
-extern int header_page_data_size;
+struct tracing_data *tracing_data_get(struct list_head *pattrs,
+				      int fd, bool temp);
+int tracing_data_put(struct tracing_data *tdata);
 
-extern bool latency_format;
 
-int trace_parse_common_type(void *data);
-int trace_parse_common_pid(void *data);
-int parse_common_pc(void *data);
-int parse_common_flags(void *data);
-int parse_common_lock_depth(void *data);
-struct event *trace_find_event(int id);
-struct event *trace_find_next_event(struct event *event);
-unsigned long long read_size(void *ptr, int size);
-unsigned long long
-raw_field_value(struct event *event, const char *name, void *data);
-void *raw_field_ptr(struct event *event, const char *name, void *data);
-unsigned long long eval_flag(const char *flag);
-
-int read_tracing_data(int fd, struct perf_event_attr *pattrs, int nb_events);
-ssize_t read_tracing_data_size(int fd, struct perf_event_attr *pattrs,
-			       int nb_events);
+struct addr_location;
 
-/* taken from kernel/trace/trace.h */
-enum trace_flag_type {
-	TRACE_FLAG_IRQS_OFF		= 0x01,
-	TRACE_FLAG_IRQS_NOSUPPORT	= 0x02,
-	TRACE_FLAG_NEED_RESCHED		= 0x04,
-	TRACE_FLAG_HARDIRQ		= 0x08,
-	TRACE_FLAG_SOFTIRQ		= 0x10,
-};
+struct perf_session;
 
 struct scripting_ops {
 	const char *name;
 	int (*start_script) (const char *script, int argc, const char **argv);
 	int (*stop_script) (void);
-	void (*process_event) (int cpu, void *data, int size,
-			       unsigned long long nsecs, char *comm);
-	int (*generate_script) (const char *outfile);
+	void (*process_event) (union perf_event *event,
+			       struct perf_sample *sample,
+			       struct perf_evsel *evsel,
+			       struct thread *thread,
+				   struct addr_location *al);
+	int (*generate_script) (struct pevent *pevent, const char *outfile);
 };
 
 int script_spec_register(const char *spec, struct scripting_ops *ops);
@@ -290,6 +79,7 @@ void setup_perl_scripting(void);
 void setup_python_scripting(void);
 
 struct scripting_context {
+	struct pevent *pevent;
 	void *event_data;
 };
 
@@ -297,4 +87,4 @@ int common_pc(struct scripting_context *context);
 int common_flags(struct scripting_context *context);
 int common_lock_depth(struct scripting_context *context);
 
-#endif /* __PERF_TRACE_EVENTS_H */
+#endif /* _PERF_UTIL_TRACE_EVENT_H */
diff --git a/tools/perf/util/types.h b/tools/perf/util/types.h
deleted file mode 100644
index 7d6b8331f89..00000000000
--- a/tools/perf/util/types.h
+++ /dev/null
@@ -1,17 +0,0 @@
-#ifndef __PERF_TYPES_H
-#define __PERF_TYPES_H
-
-/*
- * We define u64 as unsigned long long for every architecture
- * so that we can print it with %Lx without getting warnings.
- */
-typedef unsigned long long u64;
-typedef signed long long   s64;
-typedef unsigned int	   u32;
-typedef signed int	   s32;
-typedef unsigned short	   u16;
-typedef signed short	   s16;
-typedef unsigned char	   u8;
-typedef signed char	   s8;
-
-#endif /* __PERF_TYPES_H */
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
new file mode 100644
index 00000000000..5ec80a575b5
--- /dev/null
+++ b/tools/perf/util/unwind-libdw.c
@@ -0,0 +1,210 @@
+#include <linux/compiler.h>
+#include <elfutils/libdw.h>
+#include <elfutils/libdwfl.h>
+#include <inttypes.h>
+#include <errno.h>
+#include "unwind.h"
+#include "unwind-libdw.h"
+#include "machine.h"
+#include "thread.h"
+#include <linux/types.h>
+#include "event.h"
+#include "perf_regs.h"
+
+static char *debuginfo_path;
+
+static const Dwfl_Callbacks offline_callbacks = {
+	.find_debuginfo		= dwfl_standard_find_debuginfo,
+	.debuginfo_path		= &debuginfo_path,
+	.section_address	= dwfl_offline_section_address,
+};
+
+static int __report_module(struct addr_location *al, u64 ip,
+			    struct unwind_info *ui)
+{
+	Dwfl_Module *mod;
+	struct dso *dso = NULL;
+
+	thread__find_addr_location(ui->thread, ui->machine,
+				   PERF_RECORD_MISC_USER,
+				   MAP__FUNCTION, ip, al);
+
+	if (al->map)
+		dso = al->map->dso;
+
+	if (!dso)
+		return 0;
+
+	mod = dwfl_addrmodule(ui->dwfl, ip);
+	if (!mod)
+		mod = dwfl_report_elf(ui->dwfl, dso->short_name,
+				      dso->long_name, -1, al->map->start,
+				      false);
+
+	return mod && dwfl_addrmodule(ui->dwfl, ip) == mod ? 0 : -1;
+}
+
+static int report_module(u64 ip, struct unwind_info *ui)
+{
+	struct addr_location al;
+
+	return __report_module(&al, ip, ui);
+}
+
+static int entry(u64 ip, struct unwind_info *ui)
+
+{
+	struct unwind_entry e;
+	struct addr_location al;
+
+	if (__report_module(&al, ip, ui))
+		return -1;
+
+	e.ip  = ip;
+	e.map = al.map;
+	e.sym = al.sym;
+
+	pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n",
+		 al.sym ? al.sym->name : "''",
+		 ip,
+		 al.map ? al.map->map_ip(al.map, ip) : (u64) 0);
+
+	return ui->cb(&e, ui->arg);
+}
+
+static pid_t next_thread(Dwfl *dwfl, void *arg, void **thread_argp)
+{
+	/* We want only single thread to be processed. */
+	if (*thread_argp != NULL)
+		return 0;
+
+	*thread_argp = arg;
+	return dwfl_pid(dwfl);
+}
+
+static int access_dso_mem(struct unwind_info *ui, Dwarf_Addr addr,
+			  Dwarf_Word *data)
+{
+	struct addr_location al;
+	ssize_t size;
+
+	thread__find_addr_map(ui->thread, ui->machine, PERF_RECORD_MISC_USER,
+			      MAP__FUNCTION, addr, &al);
+	if (!al.map) {
+		pr_debug("unwind: no map for %lx\n", (unsigned long)addr);
+		return -1;
+	}
+
+	if (!al.map->dso)
+		return -1;
+
+	size = dso__data_read_addr(al.map->dso, al.map, ui->machine,
+				   addr, (u8 *) data, sizeof(*data));
+
+	return !(size == sizeof(*data));
+}
+
+static bool memory_read(Dwfl *dwfl __maybe_unused, Dwarf_Addr addr, Dwarf_Word *result,
+			void *arg)
+{
+	struct unwind_info *ui = arg;
+	struct stack_dump *stack = &ui->sample->user_stack;
+	u64 start, end;
+	int offset;
+	int ret;
+
+	ret = perf_reg_value(&start, &ui->sample->user_regs, PERF_REG_SP);
+	if (ret)
+		return false;
+
+	end = start + stack->size;
+
+	/* Check overflow. */
+	if (addr + sizeof(Dwarf_Word) < addr)
+		return false;
+
+	if (addr < start || addr + sizeof(Dwarf_Word) > end) {
+		ret = access_dso_mem(ui, addr, result);
+		if (ret) {
+			pr_debug("unwind: access_mem 0x%" PRIx64 " not inside range"
+				 " 0x%" PRIx64 "-0x%" PRIx64 "\n",
+				addr, start, end);
+			return false;
+		}
+		return true;
+	}
+
+	offset  = addr - start;
+	*result = *(Dwarf_Word *)&stack->data[offset];
+	pr_debug("unwind: access_mem addr 0x%" PRIx64 ", val %lx, offset %d\n",
+		 addr, (unsigned long)*result, offset);
+	return true;
+}
+
+static const Dwfl_Thread_Callbacks callbacks = {
+	.next_thread		= next_thread,
+	.memory_read		= memory_read,
+	.set_initial_registers	= libdw__arch_set_initial_registers,
+};
+
+static int
+frame_callback(Dwfl_Frame *state, void *arg)
+{
+	struct unwind_info *ui = arg;
+	Dwarf_Addr pc;
+
+	if (!dwfl_frame_pc(state, &pc, NULL)) {
+		pr_err("%s", dwfl_errmsg(-1));
+		return DWARF_CB_ABORT;
+	}
+
+	return entry(pc, ui) || !(--ui->max_stack) ?
+	       DWARF_CB_ABORT : DWARF_CB_OK;
+}
+
+int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
+			struct machine *machine, struct thread *thread,
+			struct perf_sample *data,
+			int max_stack)
+{
+	struct unwind_info ui = {
+		.sample		= data,
+		.thread		= thread,
+		.machine	= machine,
+		.cb		= cb,
+		.arg		= arg,
+		.max_stack	= max_stack,
+	};
+	Dwarf_Word ip;
+	int err = -EINVAL;
+
+	if (!data->user_regs.regs)
+		return -EINVAL;
+
+	ui.dwfl = dwfl_begin(&offline_callbacks);
+	if (!ui.dwfl)
+		goto out;
+
+	err = perf_reg_value(&ip, &data->user_regs, PERF_REG_IP);
+	if (err)
+		goto out;
+
+	err = report_module(ip, &ui);
+	if (err)
+		goto out;
+
+	if (!dwfl_attach_state(ui.dwfl, EM_NONE, thread->tid, &callbacks, &ui))
+		goto out;
+
+	err = dwfl_getthread_frames(ui.dwfl, thread->tid, frame_callback, &ui);
+
+	if (err && !ui.max_stack)
+		err = 0;
+
+ out:
+	if (err)
+		pr_debug("unwind: failed with '%s'\n", dwfl_errmsg(-1));
+
+	dwfl_end(ui.dwfl);
+	return 0;
+}
diff --git a/tools/perf/util/unwind-libdw.h b/tools/perf/util/unwind-libdw.h
new file mode 100644
index 00000000000..417a1426f3a
--- /dev/null
+++ b/tools/perf/util/unwind-libdw.h
@@ -0,0 +1,21 @@
+#ifndef __PERF_UNWIND_LIBDW_H
+#define __PERF_UNWIND_LIBDW_H
+
+#include <elfutils/libdwfl.h>
+#include "event.h"
+#include "thread.h"
+#include "unwind.h"
+
+bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg);
+
+struct unwind_info {
+	Dwfl			*dwfl;
+	struct perf_sample      *sample;
+	struct machine          *machine;
+	struct thread           *thread;
+	unwind_entry_cb_t	cb;
+	void			*arg;
+	int			max_stack;
+};
+
+#endif /* __PERF_UNWIND_LIBDW_H */
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
new file mode 100644
index 00000000000..25578b98f5c
--- /dev/null
+++ b/tools/perf/util/unwind-libunwind.c
@@ -0,0 +1,579 @@
+/*
+ * Post mortem Dwarf CFI based unwinding on top of regs and stack dumps.
+ *
+ * Lots of this code have been borrowed or heavily inspired from parts of
+ * the libunwind 0.99 code which are (amongst other contributors I may have
+ * forgotten):
+ *
+ * Copyright (C) 2002-2007 Hewlett-Packard Co
+ *	Contributed by David Mosberger-Tang <davidm@hpl.hp.com>
+ *
+ * And the bugs have been added by:
+ *
+ * Copyright (C) 2010, Frederic Weisbecker <fweisbec@gmail.com>
+ * Copyright (C) 2012, Jiri Olsa <jolsa@redhat.com>
+ *
+ */
+
+#include <elf.h>
+#include <gelf.h>
+#include <fcntl.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/mman.h>
+#include <linux/list.h>
+#include <libunwind.h>
+#include <libunwind-ptrace.h>
+#include "thread.h"
+#include "session.h"
+#include "perf_regs.h"
+#include "unwind.h"
+#include "symbol.h"
+#include "util.h"
+
+extern int
+UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as,
+				    unw_word_t ip,
+				    unw_dyn_info_t *di,
+				    unw_proc_info_t *pi,
+				    int need_unwind_info, void *arg);
+
+#define dwarf_search_unwind_table UNW_OBJ(dwarf_search_unwind_table)
+
+extern int
+UNW_OBJ(dwarf_find_debug_frame) (int found, unw_dyn_info_t *di_debug,
+				 unw_word_t ip,
+				 unw_word_t segbase,
+				 const char *obj_name, unw_word_t start,
+				 unw_word_t end);
+
+#define dwarf_find_debug_frame UNW_OBJ(dwarf_find_debug_frame)
+
+#define DW_EH_PE_FORMAT_MASK	0x0f	/* format of the encoded value */
+#define DW_EH_PE_APPL_MASK	0x70	/* how the value is to be applied */
+
+/* Pointer-encoding formats: */
+#define DW_EH_PE_omit		0xff
+#define DW_EH_PE_ptr		0x00	/* pointer-sized unsigned value */
+#define DW_EH_PE_udata4		0x03	/* unsigned 32-bit value */
+#define DW_EH_PE_udata8		0x04	/* unsigned 64-bit value */
+#define DW_EH_PE_sdata4		0x0b	/* signed 32-bit value */
+#define DW_EH_PE_sdata8		0x0c	/* signed 64-bit value */
+
+/* Pointer-encoding application: */
+#define DW_EH_PE_absptr		0x00	/* absolute value */
+#define DW_EH_PE_pcrel		0x10	/* rel. to addr. of encoded value */
+
+/*
+ * The following are not documented by LSB v1.3, yet they are used by
+ * GCC, presumably they aren't documented by LSB since they aren't
+ * used on Linux:
+ */
+#define DW_EH_PE_funcrel	0x40	/* start-of-procedure-relative */
+#define DW_EH_PE_aligned	0x50	/* aligned pointer */
+
+/* Flags intentionaly not handled, since they're not needed:
+ * #define DW_EH_PE_indirect      0x80
+ * #define DW_EH_PE_uleb128       0x01
+ * #define DW_EH_PE_udata2        0x02
+ * #define DW_EH_PE_sleb128       0x09
+ * #define DW_EH_PE_sdata2        0x0a
+ * #define DW_EH_PE_textrel       0x20
+ * #define DW_EH_PE_datarel       0x30
+ */
+
+struct unwind_info {
+	struct perf_sample	*sample;
+	struct machine		*machine;
+	struct thread		*thread;
+};
+
+#define dw_read(ptr, type, end) ({	\
+	type *__p = (type *) ptr;	\
+	type  __v;			\
+	if ((__p + 1) > (type *) end)	\
+		return -EINVAL;		\
+	__v = *__p++;			\
+	ptr = (typeof(ptr)) __p;	\
+	__v;				\
+	})
+
+static int __dw_read_encoded_value(u8 **p, u8 *end, u64 *val,
+				   u8 encoding)
+{
+	u8 *cur = *p;
+	*val = 0;
+
+	switch (encoding) {
+	case DW_EH_PE_omit:
+		*val = 0;
+		goto out;
+	case DW_EH_PE_ptr:
+		*val = dw_read(cur, unsigned long, end);
+		goto out;
+	default:
+		break;
+	}
+
+	switch (encoding & DW_EH_PE_APPL_MASK) {
+	case DW_EH_PE_absptr:
+		break;
+	case DW_EH_PE_pcrel:
+		*val = (unsigned long) cur;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if ((encoding & 0x07) == 0x00)
+		encoding |= DW_EH_PE_udata4;
+
+	switch (encoding & DW_EH_PE_FORMAT_MASK) {
+	case DW_EH_PE_sdata4:
+		*val += dw_read(cur, s32, end);
+		break;
+	case DW_EH_PE_udata4:
+		*val += dw_read(cur, u32, end);
+		break;
+	case DW_EH_PE_sdata8:
+		*val += dw_read(cur, s64, end);
+		break;
+	case DW_EH_PE_udata8:
+		*val += dw_read(cur, u64, end);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+ out:
+	*p = cur;
+	return 0;
+}
+
+#define dw_read_encoded_value(ptr, end, enc) ({			\
+	u64 __v;						\
+	if (__dw_read_encoded_value(&ptr, end, &__v, enc)) {	\
+		return -EINVAL;                                 \
+	}                                                       \
+	__v;                                                    \
+	})
+
+static u64 elf_section_offset(int fd, const char *name)
+{
+	Elf *elf;
+	GElf_Ehdr ehdr;
+	GElf_Shdr shdr;
+	u64 offset = 0;
+
+	elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
+	if (elf == NULL)
+		return 0;
+
+	do {
+		if (gelf_getehdr(elf, &ehdr) == NULL)
+			break;
+
+		if (!elf_section_by_name(elf, &ehdr, &shdr, name, NULL))
+			break;
+
+		offset = shdr.sh_offset;
+	} while (0);
+
+	elf_end(elf);
+	return offset;
+}
+
+struct table_entry {
+	u32 start_ip_offset;
+	u32 fde_offset;
+};
+
+struct eh_frame_hdr {
+	unsigned char version;
+	unsigned char eh_frame_ptr_enc;
+	unsigned char fde_count_enc;
+	unsigned char table_enc;
+
+	/*
+	 * The rest of the header is variable-length and consists of the
+	 * following members:
+	 *
+	 *	encoded_t eh_frame_ptr;
+	 *	encoded_t fde_count;
+	 */
+
+	/* A single encoded pointer should not be more than 8 bytes. */
+	u64 enc[2];
+
+	/*
+	 * struct {
+	 *    encoded_t start_ip;
+	 *    encoded_t fde_addr;
+	 * } binary_search_table[fde_count];
+	 */
+	char data[0];
+} __packed;
+
+static int unwind_spec_ehframe(struct dso *dso, struct machine *machine,
+			       u64 offset, u64 *table_data, u64 *segbase,
+			       u64 *fde_count)
+{
+	struct eh_frame_hdr hdr;
+	u8 *enc = (u8 *) &hdr.enc;
+	u8 *end = (u8 *) &hdr.data;
+	ssize_t r;
+
+	r = dso__data_read_offset(dso, machine, offset,
+				  (u8 *) &hdr, sizeof(hdr));
+	if (r != sizeof(hdr))
+		return -EINVAL;
+
+	/* We dont need eh_frame_ptr, just skip it. */
+	dw_read_encoded_value(enc, end, hdr.eh_frame_ptr_enc);
+
+	*fde_count  = dw_read_encoded_value(enc, end, hdr.fde_count_enc);
+	*segbase    = offset;
+	*table_data = (enc - (u8 *) &hdr) + offset;
+	return 0;
+}
+
+static int read_unwind_spec_eh_frame(struct dso *dso, struct machine *machine,
+				     u64 *table_data, u64 *segbase,
+				     u64 *fde_count)
+{
+	int ret = -EINVAL, fd;
+	u64 offset;
+
+	fd = dso__data_fd(dso, machine);
+	if (fd < 0)
+		return -EINVAL;
+
+	/* Check the .eh_frame section for unwinding info */
+	offset = elf_section_offset(fd, ".eh_frame_hdr");
+
+	if (offset)
+		ret = unwind_spec_ehframe(dso, machine, offset,
+					  table_data, segbase,
+					  fde_count);
+
+	return ret;
+}
+
+#ifndef NO_LIBUNWIND_DEBUG_FRAME
+static int read_unwind_spec_debug_frame(struct dso *dso,
+					struct machine *machine, u64 *offset)
+{
+	int fd = dso__data_fd(dso, machine);
+
+	if (fd < 0)
+		return -EINVAL;
+
+	/* Check the .debug_frame section for unwinding info */
+	*offset = elf_section_offset(fd, ".debug_frame");
+
+	if (*offset)
+		return 0;
+
+	return -EINVAL;
+}
+#endif
+
+static struct map *find_map(unw_word_t ip, struct unwind_info *ui)
+{
+	struct addr_location al;
+
+	thread__find_addr_map(ui->thread, ui->machine, PERF_RECORD_MISC_USER,
+			      MAP__FUNCTION, ip, &al);
+	return al.map;
+}
+
+static int
+find_proc_info(unw_addr_space_t as, unw_word_t ip, unw_proc_info_t *pi,
+	       int need_unwind_info, void *arg)
+{
+	struct unwind_info *ui = arg;
+	struct map *map;
+	unw_dyn_info_t di;
+	u64 table_data, segbase, fde_count;
+
+	map = find_map(ip, ui);
+	if (!map || !map->dso)
+		return -EINVAL;
+
+	pr_debug("unwind: find_proc_info dso %s\n", map->dso->name);
+
+	/* Check the .eh_frame section for unwinding info */
+	if (!read_unwind_spec_eh_frame(map->dso, ui->machine,
+				       &table_data, &segbase, &fde_count)) {
+		memset(&di, 0, sizeof(di));
+		di.format   = UNW_INFO_FORMAT_REMOTE_TABLE;
+		di.start_ip = map->start;
+		di.end_ip   = map->end;
+		di.u.rti.segbase    = map->start + segbase;
+		di.u.rti.table_data = map->start + table_data;
+		di.u.rti.table_len  = fde_count * sizeof(struct table_entry)
+				      / sizeof(unw_word_t);
+		return dwarf_search_unwind_table(as, ip, &di, pi,
+						 need_unwind_info, arg);
+	}
+
+#ifndef NO_LIBUNWIND_DEBUG_FRAME
+	/* Check the .debug_frame section for unwinding info */
+	if (!read_unwind_spec_debug_frame(map->dso, ui->machine, &segbase)) {
+		memset(&di, 0, sizeof(di));
+		if (dwarf_find_debug_frame(0, &di, ip, 0, map->dso->name,
+					   map->start, map->end))
+			return dwarf_search_unwind_table(as, ip, &di, pi,
+							 need_unwind_info, arg);
+	}
+#endif
+
+	return -EINVAL;
+}
+
+static int access_fpreg(unw_addr_space_t __maybe_unused as,
+			unw_regnum_t __maybe_unused num,
+			unw_fpreg_t __maybe_unused *val,
+			int __maybe_unused __write,
+			void __maybe_unused *arg)
+{
+	pr_err("unwind: access_fpreg unsupported\n");
+	return -UNW_EINVAL;
+}
+
+static int get_dyn_info_list_addr(unw_addr_space_t __maybe_unused as,
+				  unw_word_t __maybe_unused *dil_addr,
+				  void __maybe_unused *arg)
+{
+	return -UNW_ENOINFO;
+}
+
+static int resume(unw_addr_space_t __maybe_unused as,
+		  unw_cursor_t __maybe_unused *cu,
+		  void __maybe_unused *arg)
+{
+	pr_err("unwind: resume unsupported\n");
+	return -UNW_EINVAL;
+}
+
+static int
+get_proc_name(unw_addr_space_t __maybe_unused as,
+	      unw_word_t __maybe_unused addr,
+		char __maybe_unused *bufp, size_t __maybe_unused buf_len,
+		unw_word_t __maybe_unused *offp, void __maybe_unused *arg)
+{
+	pr_err("unwind: get_proc_name unsupported\n");
+	return -UNW_EINVAL;
+}
+
+static int access_dso_mem(struct unwind_info *ui, unw_word_t addr,
+			  unw_word_t *data)
+{
+	struct addr_location al;
+	ssize_t size;
+
+	thread__find_addr_map(ui->thread, ui->machine, PERF_RECORD_MISC_USER,
+			      MAP__FUNCTION, addr, &al);
+	if (!al.map) {
+		pr_debug("unwind: no map for %lx\n", (unsigned long)addr);
+		return -1;
+	}
+
+	if (!al.map->dso)
+		return -1;
+
+	size = dso__data_read_addr(al.map->dso, al.map, ui->machine,
+				   addr, (u8 *) data, sizeof(*data));
+
+	return !(size == sizeof(*data));
+}
+
+static int access_mem(unw_addr_space_t __maybe_unused as,
+		      unw_word_t addr, unw_word_t *valp,
+		      int __write, void *arg)
+{
+	struct unwind_info *ui = arg;
+	struct stack_dump *stack = &ui->sample->user_stack;
+	u64 start, end;
+	int offset;
+	int ret;
+
+	/* Don't support write, probably not needed. */
+	if (__write || !stack || !ui->sample->user_regs.regs) {
+		*valp = 0;
+		return 0;
+	}
+
+	ret = perf_reg_value(&start, &ui->sample->user_regs, PERF_REG_SP);
+	if (ret)
+		return ret;
+
+	end = start + stack->size;
+
+	/* Check overflow. */
+	if (addr + sizeof(unw_word_t) < addr)
+		return -EINVAL;
+
+	if (addr < start || addr + sizeof(unw_word_t) >= end) {
+		ret = access_dso_mem(ui, addr, valp);
+		if (ret) {
+			pr_debug("unwind: access_mem %p not inside range"
+				 " 0x%" PRIx64 "-0x%" PRIx64 "\n",
+				 (void *) addr, start, end);
+			*valp = 0;
+			return ret;
+		}
+		return 0;
+	}
+
+	offset = addr - start;
+	*valp  = *(unw_word_t *)&stack->data[offset];
+	pr_debug("unwind: access_mem addr %p val %lx, offset %d\n",
+		 (void *) addr, (unsigned long)*valp, offset);
+	return 0;
+}
+
+static int access_reg(unw_addr_space_t __maybe_unused as,
+		      unw_regnum_t regnum, unw_word_t *valp,
+		      int __write, void *arg)
+{
+	struct unwind_info *ui = arg;
+	int id, ret;
+	u64 val;
+
+	/* Don't support write, I suspect we don't need it. */
+	if (__write) {
+		pr_err("unwind: access_reg w %d\n", regnum);
+		return 0;
+	}
+
+	if (!ui->sample->user_regs.regs) {
+		*valp = 0;
+		return 0;
+	}
+
+	id = libunwind__arch_reg_id(regnum);
+	if (id < 0)
+		return -EINVAL;
+
+	ret = perf_reg_value(&val, &ui->sample->user_regs, id);
+	if (ret) {
+		pr_err("unwind: can't read reg %d\n", regnum);
+		return ret;
+	}
+
+	*valp = (unw_word_t) val;
+	pr_debug("unwind: reg %d, val %lx\n", regnum, (unsigned long)*valp);
+	return 0;
+}
+
+static void put_unwind_info(unw_addr_space_t __maybe_unused as,
+			    unw_proc_info_t *pi __maybe_unused,
+			    void *arg __maybe_unused)
+{
+	pr_debug("unwind: put_unwind_info called\n");
+}
+
+static int entry(u64 ip, struct thread *thread, struct machine *machine,
+		 unwind_entry_cb_t cb, void *arg)
+{
+	struct unwind_entry e;
+	struct addr_location al;
+
+	thread__find_addr_location(thread, machine,
+				   PERF_RECORD_MISC_USER,
+				   MAP__FUNCTION, ip, &al);
+
+	e.ip = ip;
+	e.map = al.map;
+	e.sym = al.sym;
+
+	pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n",
+		 al.sym ? al.sym->name : "''",
+		 ip,
+		 al.map ? al.map->map_ip(al.map, ip) : (u64) 0);
+
+	return cb(&e, arg);
+}
+
+static void display_error(int err)
+{
+	switch (err) {
+	case UNW_EINVAL:
+		pr_err("unwind: Only supports local.\n");
+		break;
+	case UNW_EUNSPEC:
+		pr_err("unwind: Unspecified error.\n");
+		break;
+	case UNW_EBADREG:
+		pr_err("unwind: Register unavailable.\n");
+		break;
+	default:
+		break;
+	}
+}
+
+static unw_accessors_t accessors = {
+	.find_proc_info		= find_proc_info,
+	.put_unwind_info	= put_unwind_info,
+	.get_dyn_info_list_addr	= get_dyn_info_list_addr,
+	.access_mem		= access_mem,
+	.access_reg		= access_reg,
+	.access_fpreg		= access_fpreg,
+	.resume			= resume,
+	.get_proc_name		= get_proc_name,
+};
+
+static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
+		       void *arg, int max_stack)
+{
+	unw_addr_space_t addr_space;
+	unw_cursor_t c;
+	int ret;
+
+	addr_space = unw_create_addr_space(&accessors, 0);
+	if (!addr_space) {
+		pr_err("unwind: Can't create unwind address space.\n");
+		return -ENOMEM;
+	}
+
+	ret = unw_init_remote(&c, addr_space, ui);
+	if (ret)
+		display_error(ret);
+
+	while (!ret && (unw_step(&c) > 0) && max_stack--) {
+		unw_word_t ip;
+
+		unw_get_reg(&c, UNW_REG_IP, &ip);
+		ret = ip ? entry(ip, ui->thread, ui->machine, cb, arg) : 0;
+	}
+
+	unw_destroy_addr_space(addr_space);
+	return ret;
+}
+
+int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
+			struct machine *machine, struct thread *thread,
+			struct perf_sample *data, int max_stack)
+{
+	u64 ip;
+	struct unwind_info ui = {
+		.sample       = data,
+		.thread       = thread,
+		.machine      = machine,
+	};
+	int ret;
+
+	if (!data->user_regs.regs)
+		return -EINVAL;
+
+	ret = perf_reg_value(&ip, &data->user_regs, PERF_REG_IP);
+	if (ret)
+		return ret;
+
+	ret = entry(ip, thread, machine, cb, arg);
+	if (ret)
+		return -ENOMEM;
+
+	return --max_stack > 0 ? get_entries(&ui, cb, arg, max_stack) : 0;
+}
diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h
new file mode 100644
index 00000000000..f03061260b4
--- /dev/null
+++ b/tools/perf/util/unwind.h
@@ -0,0 +1,37 @@
+#ifndef __UNWIND_H
+#define __UNWIND_H
+
+#include <linux/types.h>
+#include "event.h"
+#include "symbol.h"
+
+struct unwind_entry {
+	struct map	*map;
+	struct symbol	*sym;
+	u64		ip;
+};
+
+typedef int (*unwind_entry_cb_t)(struct unwind_entry *entry, void *arg);
+
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
+int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
+			struct machine *machine,
+			struct thread *thread,
+			struct perf_sample *data, int max_stack);
+/* libunwind specific */
+#ifdef HAVE_LIBUNWIND_SUPPORT
+int libunwind__arch_reg_id(int regnum);
+#endif
+#else
+static inline int
+unwind__get_entries(unwind_entry_cb_t cb __maybe_unused,
+		    void *arg __maybe_unused,
+		    struct machine *machine __maybe_unused,
+		    struct thread *thread __maybe_unused,
+		    struct perf_sample *data __maybe_unused,
+		    int max_stack __maybe_unused)
+{
+	return 0;
+}
+#endif /* HAVE_DWARF_UNWIND_SUPPORT */
+#endif /* __UNWIND_H */
diff --git a/tools/perf/util/usage.c b/tools/perf/util/usage.c
index e16bf9a707e..4007aca8e0c 100644
--- a/tools/perf/util/usage.c
+++ b/tools/perf/util/usage.c
@@ -1,9 +1,13 @@
 /*
- * GIT - The information manager from hell
+ * usage.c
+ *
+ * Various reporting routines.
+ * Originally copied from GIT source.
  *
  * Copyright (C) Linus Torvalds, 2005
  */
 #include "util.h"
+#include "debug.h"
 
 static void report(const char *prefix, const char *err, va_list params)
 {
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 214265674dd..95aefa78bb0 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -1,5 +1,40 @@
+#include "../perf.h"
 #include "util.h"
+#include <api/fs/fs.h>
 #include <sys/mman.h>
+#ifdef HAVE_BACKTRACE_SUPPORT
+#include <execinfo.h>
+#endif
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+#include <limits.h>
+#include <byteswap.h>
+#include <linux/kernel.h>
+
+/*
+ * XXX We need to find a better place for these things...
+ */
+unsigned int page_size;
+int cacheline_size;
+
+bool test_attr__enabled;
+
+bool perf_host  = true;
+bool perf_guest = false;
+
+char tracing_events_path[PATH_MAX + 1] = "/sys/kernel/debug/tracing/events";
+
+void event_attr_init(struct perf_event_attr *attr)
+{
+	if (!perf_host)
+		attr->exclude_host  = 1;
+	if (!perf_guest)
+		attr->exclude_guest = 1;
+	/* to capture ABI version */
+	attr->size = sizeof(*attr);
+}
 
 int mkdir_p(char *path, mode_t mode)
 {
@@ -27,17 +62,20 @@ int mkdir_p(char *path, mode_t mode)
 	return (stat(path, &st) && mkdir(path, mode)) ? -1 : 0;
 }
 
-static int slow_copyfile(const char *from, const char *to)
+static int slow_copyfile(const char *from, const char *to, mode_t mode)
 {
-	int err = 0;
+	int err = -1;
 	char *line = NULL;
 	size_t n;
 	FILE *from_fp = fopen(from, "r"), *to_fp;
+	mode_t old_umask;
 
 	if (from_fp == NULL)
 		goto out;
 
+	old_umask = umask(mode ^ 0777);
 	to_fp = fopen(to, "w");
+	umask(old_umask);
 	if (to_fp == NULL)
 		goto out_fclose_from;
 
@@ -54,7 +92,7 @@ out:
 	return err;
 }
 
-int copyfile(const char *from, const char *to)
+int copyfile_mode(const char *from, const char *to, mode_t mode)
 {
 	int fromfd, tofd;
 	struct stat st;
@@ -65,13 +103,13 @@ int copyfile(const char *from, const char *to)
 		goto out;
 
 	if (st.st_size == 0) /* /proc? do it slowly... */
-		return slow_copyfile(from, to);
+		return slow_copyfile(from, to, mode);
 
 	fromfd = open(from, O_RDONLY);
 	if (fromfd < 0)
 		goto out;
 
-	tofd = creat(to, 0755);
+	tofd = creat(to, mode);
 	if (tofd < 0)
 		goto out_close_from;
 
@@ -93,6 +131,11 @@ out:
 	return err;
 }
 
+int copyfile(const char *from, const char *to)
+{
+	return copyfile_mode(from, to, 0755);
+}
+
 unsigned long convert_unit(unsigned long value, char *unit)
 {
 	*unit = ' ';
@@ -114,3 +157,386 @@ unsigned long convert_unit(unsigned long value, char *unit)
 
 	return value;
 }
+
+static ssize_t ion(bool is_read, int fd, void *buf, size_t n)
+{
+	void *buf_start = buf;
+	size_t left = n;
+
+	while (left) {
+		ssize_t ret = is_read ? read(fd, buf, left) :
+					write(fd, buf, left);
+
+		if (ret < 0 && errno == EINTR)
+			continue;
+		if (ret <= 0)
+			return ret;
+
+		left -= ret;
+		buf  += ret;
+	}
+
+	BUG_ON((size_t)(buf - buf_start) != n);
+	return n;
+}
+
+/*
+ * Read exactly 'n' bytes or return an error.
+ */
+ssize_t readn(int fd, void *buf, size_t n)
+{
+	return ion(true, fd, buf, n);
+}
+
+/*
+ * Write exactly 'n' bytes or return an error.
+ */
+ssize_t writen(int fd, void *buf, size_t n)
+{
+	return ion(false, fd, buf, n);
+}
+
+size_t hex_width(u64 v)
+{
+	size_t n = 1;
+
+	while ((v >>= 4))
+		++n;
+
+	return n;
+}
+
+static int hex(char ch)
+{
+	if ((ch >= '0') && (ch <= '9'))
+		return ch - '0';
+	if ((ch >= 'a') && (ch <= 'f'))
+		return ch - 'a' + 10;
+	if ((ch >= 'A') && (ch <= 'F'))
+		return ch - 'A' + 10;
+	return -1;
+}
+
+/*
+ * While we find nice hex chars, build a long_val.
+ * Return number of chars processed.
+ */
+int hex2u64(const char *ptr, u64 *long_val)
+{
+	const char *p = ptr;
+	*long_val = 0;
+
+	while (*p) {
+		const int hex_val = hex(*p);
+
+		if (hex_val < 0)
+			break;
+
+		*long_val = (*long_val << 4) | hex_val;
+		p++;
+	}
+
+	return p - ptr;
+}
+
+/* Obtain a backtrace and print it to stdout. */
+#ifdef HAVE_BACKTRACE_SUPPORT
+void dump_stack(void)
+{
+	void *array[16];
+	size_t size = backtrace(array, ARRAY_SIZE(array));
+	char **strings = backtrace_symbols(array, size);
+	size_t i;
+
+	printf("Obtained %zd stack frames.\n", size);
+
+	for (i = 0; i < size; i++)
+		printf("%s\n", strings[i]);
+
+	free(strings);
+}
+#else
+void dump_stack(void) {}
+#endif
+
+void get_term_dimensions(struct winsize *ws)
+{
+	char *s = getenv("LINES");
+
+	if (s != NULL) {
+		ws->ws_row = atoi(s);
+		s = getenv("COLUMNS");
+		if (s != NULL) {
+			ws->ws_col = atoi(s);
+			if (ws->ws_row && ws->ws_col)
+				return;
+		}
+	}
+#ifdef TIOCGWINSZ
+	if (ioctl(1, TIOCGWINSZ, ws) == 0 &&
+	    ws->ws_row && ws->ws_col)
+		return;
+#endif
+	ws->ws_row = 25;
+	ws->ws_col = 80;
+}
+
+static void set_tracing_events_path(const char *mountpoint)
+{
+	snprintf(tracing_events_path, sizeof(tracing_events_path), "%s/%s",
+		 mountpoint, "tracing/events");
+}
+
+const char *perf_debugfs_mount(const char *mountpoint)
+{
+	const char *mnt;
+
+	mnt = debugfs_mount(mountpoint);
+	if (!mnt)
+		return NULL;
+
+	set_tracing_events_path(mnt);
+
+	return mnt;
+}
+
+void perf_debugfs_set_path(const char *mntpt)
+{
+	snprintf(debugfs_mountpoint, strlen(debugfs_mountpoint), "%s", mntpt);
+	set_tracing_events_path(mntpt);
+}
+
+static const char *find_debugfs(void)
+{
+	const char *path = perf_debugfs_mount(NULL);
+
+	if (!path)
+		fprintf(stderr, "Your kernel does not support the debugfs filesystem");
+
+	return path;
+}
+
+/*
+ * Finds the path to the debugfs/tracing
+ * Allocates the string and stores it.
+ */
+const char *find_tracing_dir(void)
+{
+	static char *tracing;
+	static int tracing_found;
+	const char *debugfs;
+
+	if (tracing_found)
+		return tracing;
+
+	debugfs = find_debugfs();
+	if (!debugfs)
+		return NULL;
+
+	tracing = malloc(strlen(debugfs) + 9);
+	if (!tracing)
+		return NULL;
+
+	sprintf(tracing, "%s/tracing", debugfs);
+
+	tracing_found = 1;
+	return tracing;
+}
+
+char *get_tracing_file(const char *name)
+{
+	const char *tracing;
+	char *file;
+
+	tracing = find_tracing_dir();
+	if (!tracing)
+		return NULL;
+
+	file = malloc(strlen(tracing) + strlen(name) + 2);
+	if (!file)
+		return NULL;
+
+	sprintf(file, "%s/%s", tracing, name);
+	return file;
+}
+
+void put_tracing_file(char *file)
+{
+	free(file);
+}
+
+int parse_nsec_time(const char *str, u64 *ptime)
+{
+	u64 time_sec, time_nsec;
+	char *end;
+
+	time_sec = strtoul(str, &end, 10);
+	if (*end != '.' && *end != '\0')
+		return -1;
+
+	if (*end == '.') {
+		int i;
+		char nsec_buf[10];
+
+		if (strlen(++end) > 9)
+			return -1;
+
+		strncpy(nsec_buf, end, 9);
+		nsec_buf[9] = '\0';
+
+		/* make it nsec precision */
+		for (i = strlen(nsec_buf); i < 9; i++)
+			nsec_buf[i] = '0';
+
+		time_nsec = strtoul(nsec_buf, &end, 10);
+		if (*end != '\0')
+			return -1;
+	} else
+		time_nsec = 0;
+
+	*ptime = time_sec * NSEC_PER_SEC + time_nsec;
+	return 0;
+}
+
+unsigned long parse_tag_value(const char *str, struct parse_tag *tags)
+{
+	struct parse_tag *i = tags;
+
+	while (i->tag) {
+		char *s;
+
+		s = strchr(str, i->tag);
+		if (s) {
+			unsigned long int value;
+			char *endptr;
+
+			value = strtoul(str, &endptr, 10);
+			if (s != endptr)
+				break;
+
+			if (value > ULONG_MAX / i->mult)
+				break;
+			value *= i->mult;
+			return value;
+		}
+		i++;
+	}
+
+	return (unsigned long) -1;
+}
+
+int filename__read_int(const char *filename, int *value)
+{
+	char line[64];
+	int fd = open(filename, O_RDONLY), err = -1;
+
+	if (fd < 0)
+		return -1;
+
+	if (read(fd, line, sizeof(line)) > 0) {
+		*value = atoi(line);
+		err = 0;
+	}
+
+	close(fd);
+	return err;
+}
+
+int filename__read_str(const char *filename, char **buf, size_t *sizep)
+{
+	size_t size = 0, alloc_size = 0;
+	void *bf = NULL, *nbf;
+	int fd, n, err = 0;
+
+	fd = open(filename, O_RDONLY);
+	if (fd < 0)
+		return -errno;
+
+	do {
+		if (size == alloc_size) {
+			alloc_size += BUFSIZ;
+			nbf = realloc(bf, alloc_size);
+			if (!nbf) {
+				err = -ENOMEM;
+				break;
+			}
+
+			bf = nbf;
+		}
+
+		n = read(fd, bf + size, alloc_size - size);
+		if (n < 0) {
+			if (size) {
+				pr_warning("read failed %d: %s\n",
+					   errno, strerror(errno));
+				err = 0;
+			} else
+				err = -errno;
+
+			break;
+		}
+
+		size += n;
+	} while (n > 0);
+
+	if (!err) {
+		*sizep = size;
+		*buf   = bf;
+	} else
+		free(bf);
+
+	close(fd);
+	return err;
+}
+
+const char *get_filename_for_perf_kvm(void)
+{
+	const char *filename;
+
+	if (perf_host && !perf_guest)
+		filename = strdup("perf.data.host");
+	else if (!perf_host && perf_guest)
+		filename = strdup("perf.data.guest");
+	else
+		filename = strdup("perf.data.kvm");
+
+	return filename;
+}
+
+int perf_event_paranoid(void)
+{
+	char path[PATH_MAX];
+	const char *procfs = procfs__mountpoint();
+	int value;
+
+	if (!procfs)
+		return INT_MAX;
+
+	scnprintf(path, PATH_MAX, "%s/sys/kernel/perf_event_paranoid", procfs);
+
+	if (filename__read_int(path, &value))
+		return INT_MAX;
+
+	return value;
+}
+
+void mem_bswap_32(void *src, int byte_size)
+{
+	u32 *m = src;
+	while (byte_size > 0) {
+		*m = bswap_32(*m);
+		byte_size -= sizeof(u32);
+		++m;
+	}
+}
+
+void mem_bswap_64(void *src, int byte_size)
+{
+	u64 *m = src;
+
+	while (byte_size > 0) {
+		*m = bswap_64(*m);
+		byte_size -= sizeof(u64);
+		++m;
+	}
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 4e8b6b0c551..66864364ccb 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -1,8 +1,6 @@
 #ifndef GIT_COMPAT_UTIL_H
 #define GIT_COMPAT_UTIL_H
 
-#define _FILE_OFFSET_BITS 64
-
 #ifndef FLEX_ARRAY
 /*
  * See if our compiler is known to support flexible array members.
@@ -40,7 +38,6 @@
 #define decimal_length(x)	((int)(sizeof(x) * 2.56 + 0.5) + 1)
 
 #define _ALL_SOURCE 1
-#define _GNU_SOURCE 1
 #define _BSD_SOURCE 1
 #define HAS_BOOL
 
@@ -70,25 +67,23 @@
 #include <sys/poll.h>
 #include <sys/socket.h>
 #include <sys/ioctl.h>
-#ifndef NO_SYS_SELECT_H
-#include <sys/select.h>
-#endif
-#include <netinet/in.h>
-#include <netinet/tcp.h>
-#include <arpa/inet.h>
-#include <netdb.h>
-#include <pwd.h>
 #include <inttypes.h>
-#include "../../../include/linux/magic.h"
-#include "types.h"
+#include <linux/magic.h>
+#include <linux/types.h>
 #include <sys/ttydefaults.h>
-
-#ifndef NO_ICONV
-#include <iconv.h>
-#endif
+#include <api/fs/debugfs.h>
+#include <termios.h>
+#include <linux/bitops.h>
 
 extern const char *graph_line;
 extern const char *graph_dotted_line;
+extern char buildid_dir[];
+extern char tracing_events_path[];
+extern void perf_debugfs_set_path(const char *mountpoint);
+const char *perf_debugfs_mount(const char *mountpoint);
+const char *find_tracing_dir(void);
+char *get_tracing_file(const char *name);
+void put_tracing_file(char *file);
 
 /* On most systems <limits.h> would have given us this, but
  * not on some systems (e.g. GNU/Hurd).
@@ -134,6 +129,8 @@ extern const char *graph_dotted_line;
 #endif
 #endif
 
+#define PERF_GTK_DSO  "libperf-gtk.so"
+
 /* General helper functions */
 extern void usage(const char *err) NORETURN;
 extern void die(const char *err, ...) NORETURN __attribute__((format (printf, 1, 2)));
@@ -152,6 +149,8 @@ extern void warning(const char *err, ...) __attribute__((format (printf, 1, 2)))
 extern void set_die_routine(void (*routine)(const char *err, va_list params) NORETURN);
 
 extern int prefixcmp(const char *str, const char *prefix);
+extern void set_buildid_dir(void);
+extern void disable_buildid_cache(void);
 
 static inline const char *skip_prefix(const char *str, const char *prefix)
 {
@@ -187,6 +186,8 @@ static inline void *zalloc(size_t size)
 	return calloc(1, size);
 }
 
+#define zfree(ptr) ({ free(*ptr); *ptr = NULL; })
+
 static inline int has_extension(const char *filename, const char *ext)
 {
 	size_t len = strlen(filename);
@@ -203,9 +204,17 @@ static inline int has_extension(const char *filename, const char *ext)
 #undef isalpha
 #undef isprint
 #undef isalnum
+#undef islower
+#undef isupper
 #undef tolower
 #undef toupper
 
+#ifndef NSEC_PER_MSEC
+#define NSEC_PER_MSEC	1000000L
+#endif
+
+int parse_nsec_time(const char *str, u64 *ptime);
+
 extern unsigned char sane_ctype[256];
 #define GIT_SPACE		0x01
 #define GIT_DIGIT		0x02
@@ -223,6 +232,8 @@ 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) && (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)
 
@@ -233,50 +244,90 @@ static inline int sane_case(int x, int high)
 	return x;
 }
 
-#ifndef DIR_HAS_BSD_GROUP_SEMANTICS
-# define FORCE_DIR_SET_GID S_ISGID
-#else
-# define FORCE_DIR_SET_GID 0
-#endif
-
-#ifdef NO_NSEC
-#undef USE_NSEC
-#define ST_CTIME_NSEC(st) 0
-#define ST_MTIME_NSEC(st) 0
-#else
-#ifdef USE_ST_TIMESPEC
-#define ST_CTIME_NSEC(st) ((unsigned int)((st).st_ctimespec.tv_nsec))
-#define ST_MTIME_NSEC(st) ((unsigned int)((st).st_mtimespec.tv_nsec))
-#else
-#define ST_CTIME_NSEC(st) ((unsigned int)((st).st_ctim.tv_nsec))
-#define ST_MTIME_NSEC(st) ((unsigned int)((st).st_mtim.tv_nsec))
-#endif
-#endif
-
 int mkdir_p(char *path, mode_t mode);
 int copyfile(const char *from, const char *to);
+int copyfile_mode(const char *from, const char *to, mode_t mode);
 
 s64 perf_atoll(const char *str);
 char **argv_split(const char *str, int *argcp);
 void argv_free(char **argv);
 bool strglobmatch(const char *str, const char *pat);
 bool strlazymatch(const char *str, const char *pat);
+int strtailcmp(const char *s1, const char *s2);
+char *strxfrchar(char *s, char from, char to);
 unsigned long convert_unit(unsigned long value, char *unit);
+ssize_t readn(int fd, void *buf, size_t n);
+ssize_t writen(int fd, void *buf, size_t n);
 
-#ifndef ESC
-#define ESC 27
-#endif
+struct perf_event_attr;
 
-static inline bool is_exit_key(int key)
-{
-	char up;
-	if (key == CTRL('c') || key == ESC)
-		return true;
-	up = toupper(key);
-	return up == 'Q';
-}
+void event_attr_init(struct perf_event_attr *attr);
 
 #define _STR(x) #x
 #define STR(x) _STR(x)
 
+/*
+ *  Determine whether some value is a power of two, where zero is
+ * *not* considered a power of two.
+ */
+
+static inline __attribute__((const))
+bool is_power_of_2(unsigned long n)
+{
+	return (n != 0 && ((n & (n - 1)) == 0));
+}
+
+static inline unsigned next_pow2(unsigned x)
+{
+	if (!x)
+		return 1;
+	return 1ULL << (32 - __builtin_clz(x - 1));
+}
+
+static inline unsigned long next_pow2_l(unsigned long x)
+{
+#if BITS_PER_LONG == 64
+	if (x <= (1UL << 31))
+		return next_pow2(x);
+	return (unsigned long)next_pow2(x >> 32) << 32;
+#else
+	return next_pow2(x);
 #endif
+}
+
+size_t hex_width(u64 v);
+int hex2u64(const char *ptr, u64 *val);
+
+char *ltrim(char *s);
+char *rtrim(char *s);
+
+void dump_stack(void);
+
+extern unsigned int page_size;
+extern int cacheline_size;
+
+void get_term_dimensions(struct winsize *ws);
+
+struct parse_tag {
+	char tag;
+	int mult;
+};
+
+unsigned long parse_tag_value(const char *str, struct parse_tag *tags);
+
+#define SRCLINE_UNKNOWN  ((char *) "??:0")
+
+struct dso;
+
+char *get_srcline(struct dso *dso, unsigned long addr);
+void free_srcline(char *srcline);
+
+int filename__read_int(const char *filename, int *value);
+int filename__read_str(const char *filename, char **buf, size_t *sizep);
+int perf_event_paranoid(void);
+
+void mem_bswap_64(void *src, int byte_size);
+void mem_bswap_32(void *src, int byte_size);
+
+const char *get_filename_for_perf_kvm(void);
+#endif /* GIT_COMPAT_UTIL_H */
diff --git a/tools/perf/util/values.c b/tools/perf/util/values.c
index cfa55d686e3..0fb3c1fcd3e 100644
--- a/tools/perf/util/values.c
+++ b/tools/perf/util/values.c
@@ -31,13 +31,14 @@ void perf_read_values_destroy(struct perf_read_values *values)
 		return;
 
 	for (i = 0; i < values->threads; i++)
-		free(values->value[i]);
-	free(values->pid);
-	free(values->tid);
-	free(values->counterrawid);
+		zfree(&values->value[i]);
+	zfree(&values->value);
+	zfree(&values->pid);
+	zfree(&values->tid);
+	zfree(&values->counterrawid);
 	for (i = 0; i < values->counters; i++)
-		free(values->countername[i]);
-	free(values->countername);
+		zfree(&values->countername[i]);
+	zfree(&values->countername);
 }
 
 static void perf_read_values__enlarge_threads(struct perf_read_values *values)
@@ -150,7 +151,7 @@ static void perf_read_values__display_pretty(FILE *fp,
 		if (width > tidwidth)
 			tidwidth = width;
 		for (j = 0; j < values->counters; j++) {
-			width = snprintf(NULL, 0, "%Lu", values->value[i][j]);
+			width = snprintf(NULL, 0, "%" PRIu64, values->value[i][j]);
 			if (width > counterwidth[j])
 				counterwidth[j] = width;
 		}
@@ -165,7 +166,7 @@ static void perf_read_values__display_pretty(FILE *fp,
 		fprintf(fp, "  %*d  %*d", pidwidth, values->pid[i],
 			tidwidth, values->tid[i]);
 		for (j = 0; j < values->counters; j++)
-			fprintf(fp, "  %*Lu",
+			fprintf(fp, "  %*" PRIu64,
 				counterwidth[j], values->value[i][j]);
 		fprintf(fp, "\n");
 	}
@@ -196,13 +197,13 @@ static void perf_read_values__display_raw(FILE *fp,
 		width = strlen(values->countername[j]);
 		if (width > namewidth)
 			namewidth = width;
-		width = snprintf(NULL, 0, "%llx", values->counterrawid[j]);
+		width = snprintf(NULL, 0, "%" PRIx64, values->counterrawid[j]);
 		if (width > rawwidth)
 			rawwidth = width;
 	}
 	for (i = 0; i < values->threads; i++) {
 		for (j = 0; j < values->counters; j++) {
-			width = snprintf(NULL, 0, "%Lu", values->value[i][j]);
+			width = snprintf(NULL, 0, "%" PRIu64, values->value[i][j]);
 			if (width > countwidth)
 				countwidth = width;
 		}
@@ -214,7 +215,7 @@ static void perf_read_values__display_raw(FILE *fp,
 		countwidth, "Count");
 	for (i = 0; i < values->threads; i++)
 		for (j = 0; j < values->counters; j++)
-			fprintf(fp, "  %*d  %*d  %*s  %*llx  %*Lu\n",
+			fprintf(fp, "  %*d  %*d  %*s  %*" PRIx64 "  %*" PRIu64,
 				pidwidth, values->pid[i],
 				tidwidth, values->tid[i],
 				namewidth, values->countername[j],
diff --git a/tools/perf/util/values.h b/tools/perf/util/values.h
index 2fa967e1a88..b21a80c6cf8 100644
--- a/tools/perf/util/values.h
+++ b/tools/perf/util/values.h
@@ -1,7 +1,7 @@
 #ifndef __PERF_VALUES_H
 #define __PERF_VALUES_H
 
-#include "types.h"
+#include <linux/types.h>
 
 struct perf_read_values {
 	int threads;
diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
new file mode 100644
index 00000000000..0ddb3b8a89e
--- /dev/null
+++ b/tools/perf/util/vdso.c
@@ -0,0 +1,111 @@
+
+#include <unistd.h>
+#include <stdio.h>
+#include <string.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <stdlib.h>
+#include <linux/kernel.h>
+
+#include "vdso.h"
+#include "util.h"
+#include "symbol.h"
+#include "linux/string.h"
+
+static bool vdso_found;
+static char vdso_file[] = "/tmp/perf-vdso.so-XXXXXX";
+
+static int find_vdso_map(void **start, void **end)
+{
+	FILE *maps;
+	char line[128];
+	int found = 0;
+
+	maps = fopen("/proc/self/maps", "r");
+	if (!maps) {
+		pr_err("vdso: cannot open maps\n");
+		return -1;
+	}
+
+	while (!found && fgets(line, sizeof(line), maps)) {
+		int m = -1;
+
+		/* We care only about private r-x mappings. */
+		if (2 != sscanf(line, "%p-%p r-xp %*x %*x:%*x %*u %n",
+				start, end, &m))
+			continue;
+		if (m < 0)
+			continue;
+
+		if (!strncmp(&line[m], VDSO__MAP_NAME,
+			     sizeof(VDSO__MAP_NAME) - 1))
+			found = 1;
+	}
+
+	fclose(maps);
+	return !found;
+}
+
+static char *get_file(void)
+{
+	char *vdso = NULL;
+	char *buf = NULL;
+	void *start, *end;
+	size_t size;
+	int fd;
+
+	if (vdso_found)
+		return vdso_file;
+
+	if (find_vdso_map(&start, &end))
+		return NULL;
+
+	size = end - start;
+
+	buf = memdup(start, size);
+	if (!buf)
+		return NULL;
+
+	fd = mkstemp(vdso_file);
+	if (fd < 0)
+		goto out;
+
+	if (size == (size_t) write(fd, buf, size))
+		vdso = vdso_file;
+
+	close(fd);
+
+ out:
+	free(buf);
+
+	vdso_found = (vdso != NULL);
+	return vdso;
+}
+
+void vdso__exit(void)
+{
+	if (vdso_found)
+		unlink(vdso_file);
+}
+
+struct dso *vdso__dso_findnew(struct list_head *head)
+{
+	struct dso *dso = dsos__find(head, VDSO__MAP_NAME, true);
+
+	if (!dso) {
+		char *file;
+
+		file = get_file();
+		if (!file)
+			return NULL;
+
+		dso = dso__new(VDSO__MAP_NAME);
+		if (dso != NULL) {
+			dsos__add(head, dso);
+			dso__set_long_name(dso, file, false);
+		}
+	}
+
+	return dso;
+}
diff --git a/tools/perf/util/vdso.h b/tools/perf/util/vdso.h
new file mode 100644
index 00000000000..0f76e7caf6f
--- /dev/null
+++ b/tools/perf/util/vdso.h
@@ -0,0 +1,18 @@
+#ifndef __PERF_VDSO__
+#define __PERF_VDSO__
+
+#include <linux/types.h>
+#include <string.h>
+#include <stdbool.h>
+
+#define VDSO__MAP_NAME "[vdso]"
+
+static inline bool is_vdso_map(const char *filename)
+{
+	return !strcmp(filename, VDSO__MAP_NAME);
+}
+
+struct dso *vdso__dso_findnew(struct list_head *head);
+void vdso__exit(void);
+
+#endif /* __PERF_VDSO__ */
diff --git a/tools/perf/util/wrapper.c b/tools/perf/util/wrapper.c
index 73e900edb5a..19f15b65070 100644
--- a/tools/perf/util/wrapper.c
+++ b/tools/perf/util/wrapper.c
@@ -7,7 +7,8 @@
  * There's no pack memory to release - but stay close to the Git
  * version so wrap this away:
  */
-static inline void release_pack_memory(size_t size __used, int flag __used)
+static inline void release_pack_memory(size_t size __maybe_unused,
+				       int flag __maybe_unused)
 {
 }
 
diff --git a/tools/perf/util/xyarray.c b/tools/perf/util/xyarray.c
new file mode 100644
index 00000000000..22afbf6c536
--- /dev/null
+++ b/tools/perf/util/xyarray.c
@@ -0,0 +1,20 @@
+#include "xyarray.h"
+#include "util.h"
+
+struct xyarray *xyarray__new(int xlen, int ylen, size_t entry_size)
+{
+	size_t row_size = ylen * entry_size;
+	struct xyarray *xy = zalloc(sizeof(*xy) + xlen * row_size);
+
+	if (xy != NULL) {
+		xy->entry_size = entry_size;
+		xy->row_size   = row_size;
+	}
+
+	return xy;
+}
+
+void xyarray__delete(struct xyarray *xy)
+{
+	free(xy);
+}
diff --git a/tools/perf/util/xyarray.h b/tools/perf/util/xyarray.h
new file mode 100644
index 00000000000..c488a07275d
--- /dev/null
+++ b/tools/perf/util/xyarray.h
@@ -0,0 +1,20 @@
+#ifndef _PERF_XYARRAY_H_
+#define _PERF_XYARRAY_H_ 1
+
+#include <sys/types.h>
+
+struct xyarray {
+	size_t row_size;
+	size_t entry_size;
+	char contents[];
+};
+
+struct xyarray *xyarray__new(int xlen, int ylen, size_t entry_size);
+void xyarray__delete(struct xyarray *xy);
+
+static inline void *xyarray__entry(struct xyarray *xy, int x, int y)
+{
+	return &xy->contents[x * xy->row_size + y * xy->entry_size];
+}
+
+#endif /* _PERF_XYARRAY_H_ */