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

Pull perf events changes for v3.4 from Ingo Molnar:

 - New "hardware based branch profiling" feature both on the kernel and
   the tooling side, on CPUs that support it.  (modern x86 Intel CPUs
   with the 'LBR' hardware feature currently.)

   This new feature is basically a sophisticated 'magnifying glass' for
   branch execution - something that is pretty difficult to extract from
   regular, function histogram centric profiles.

   The simplest mode is activated via 'perf record -b', and the result
   looks like this in perf report:

	$ perf record -b any_call,u -e cycles:u branchy

	$ perf report -b --sort=symbol
	    52.34%  [.] main                   [.] f1
	    24.04%  [.] f1                     [.] f3
	    23.60%  [.] f1                     [.] f2
	     0.01%  [k] _IO_new_file_xsputn    [k] _IO_file_overflow
	     0.01%  [k] _IO_vfprintf_internal  [k] _IO_new_file_xsputn
	     0.01%  [k] _IO_vfprintf_internal  [k] strchrnul
	     0.01%  [k] __printf               [k] _IO_vfprintf_internal
	     0.01%  [k] main                   [k] __printf

   This output shows from/to branch columns and shows the highest
   percentage (from,to) jump combinations - i.e.  the most likely taken
   branches in the system.  "branches" can also include function calls
   and any other synchronous and asynchronous transitions of the
   instruction pointer that are not 'next instruction' - such as system
   calls, traps, interrupts, etc.

   This feature comes with (hopefully intuitive) flat ascii and TUI
   support in perf report.

 - Various 'perf annotate' visual improvements for us assembly junkies.
   It will now recognize function calls in the TUI and by hitting enter
   you can follow the call (recursively) and back, amongst other
   improvements.

 - Multiple threads/processes recording support in perf record, perf
   stat, perf top - which is activated via a comma-list of PIDs:

	perf top -p 21483,21485
	perf stat -p 21483,21485 -ddd
	perf record -p 21483,21485

 - Support for per UID views, via the --uid paramter to perf top, perf
   report, etc.  For example 'perf top --uid mingo' will only show the
   tasks that I am running, excluding other users, root, etc.

 - Jump label restructurings and improvements - this includes the
   factoring out of the (hopefully much clearer) include/linux/static_key.h
   generic facility:

	struct static_key key = STATIC_KEY_INIT_FALSE;

	...

	if (static_key_false(&key))
	        do unlikely code
	else
	        do likely code

	...
	static_key_slow_inc();
	...
	static_key_slow_inc();
	...

   The static_key_false() branch will be generated into the code with as
   little impact to the likely code path as possible.  the
   static_key_slow_*() APIs flip the branch via live kernel code patching.

   This facility can now be used more widely within the kernel to
   micro-optimize hot branches whose likelihood matches the static-key
   usage and fast/slow cost patterns.

 - SW function tracer improvements: perf support and filtering support.

 - Various hardenings of the perf.data ABI, to make older perf.data's
   smoother on newer tool versions, to make new features integrate more
   smoothly, to support cross-endian recording/analyzing workflows
   better, etc.

 - Restructuring of the kprobes code, the splitting out of 'optprobes',
   and a corner case bugfix.

 - Allow the tracing of kernel console output (printk).

 - Improvements/fixes to user-space RDPMC support, allowing user-space
   self-profiling code to extract PMU counts without performing any
   system calls, while playing nice with the kernel side.

 - 'perf bench' improvements

 - ... and lots of internal restructurings, cleanups and fixes that made
   these features possible.  And, as usual this list is incomplete as
   there were also lots of other improvements

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (120 commits)
  perf report: Fix annotate double quit issue in branch view mode
  perf report: Remove duplicate annotate choice in branch view mode
  perf/x86: Prettify pmu config literals
  perf report: Enable TUI in branch view mode
  perf report: Auto-detect branch stack sampling mode
  perf record: Add HEADER_BRANCH_STACK tag
  perf record: Provide default branch stack sampling mode option
  perf tools: Make perf able to read files from older ABIs
  perf tools: Fix ABI compatibility bug in print_event_desc()
  perf tools: Enable reading of perf.data files from different ABI rev
  perf: Add ABI reference sizes
  perf report: Add support for taken branch sampling
  perf record: Add support for sampling taken branch
  perf tools: Add code to support PERF_SAMPLE_BRANCH_STACK
  x86/kprobes: Split out optprobe related code to kprobes-opt.c
  x86/kprobes: Fix a bug which can modify kernel code permanently
  x86/kprobes: Fix instruction recovery on optimized path
  perf: Add callback to flush branch_stack on context switch
  perf: Disable PERF_SAMPLE_BRANCH_* when not supported
  perf/x86: Add LBR software filter support for Intel CPUs
  ...

74 files changed, 2632 insertions, 710 deletions

diff --git a/tools/perf/Documentation/Makefile b/tools/perf/Documentation/Makefile
index 4626a398836a..ca600e09c8d4 100644
--- a/tools/perf/Documentation/Makefile
+++ b/tools/perf/Documentation/Makefile
@@ -1,3 +1,10 @@
+OUTPUT := ./
+ifeq ("$(origin O)", "command line")
+  ifneq ($(O),)
+        OUTPUT := $(O)/
+  endif
+endif
+
 MAN1_TXT= \
         $(filter-out $(addsuffix .txt, $(ARTICLES) $(SP_ARTICLES)), \
                 $(wildcard perf-*.txt)) \
@@ -6,10 +13,11 @@ 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 +26,17 @@ 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
@@ -150,9 +164,9 @@ 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
 
@@ -166,7 +180,7 @@ install-man: man
 
 install-info: info
         $(INSTALL) -d -m 755 $(DESTDIR)$(infodir)
-        $(INSTALL) -m 644 perf.info perfman.info $(DESTDIR)$(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 ;\
@@ -176,7 +190,7 @@ install-info: info
 
 install-pdf: pdf
         $(INSTALL) -d -m 755 $(DESTDIR)$(pdfdir)
-        $(INSTALL) -m 644 user-manual.pdf $(DESTDIR)$(pdfdir)
+        $(INSTALL) -m 644 $(OUTPUT)user-manual.pdf $(DESTDIR)$(pdfdir)
 
 #install-html: html
 #       '$(SHELL_PATH_SQ)' ./install-webdoc.sh $(DESTDIR)$(htmldir)
@@ -189,14 +203,14 @@ install-pdf: pdf
 #
 # 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 +219,36 @@ 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:
-        $(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) $(cmds_txt) *.made
-
-$(MAN_HTML): %.html : %.txt
+        $(RM) $(MAN_XML) $(addsuffix +,$(MAN_XML))
+        $(RM) $(MAN_HTML) $(addsuffix +,$(MAN_HTML))
+        $(RM) $(DOC_HTML) $(DOC_MAN1) $(DOC_MAN5) $(DOC_MAN7)
+        $(RM) $(OUTPUT)*.texi $(OUTPUT)*.texi+ $(OUTPUT)*.texi++
+        $(RM) $(OUTPUT)perf.info $(OUTPUT)perfman.info
+        $(RM) $(OUTPUT)howto-index.txt $(OUTPUT)howto/*.html $(OUTPUT)doc.dep
+        $(RM) $(OUTPUT)technical/api-*.html $(OUTPUT)technical/api-index.txt
+        $(RM) $(cmds_txt) $(OUTPUT)*.made
+
+$(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 +257,25 @@ $(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 +283,7 @@ 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
diff --git a/tools/perf/Documentation/perf-lock.txt b/tools/perf/Documentation/perf-lock.txt
index d6b2a4f2108b..c7f5f55634ac 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 +20,13 @@ 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
 --------------
 
@@ -47,6 +50,17 @@ REPORT OPTIONS
         Sorting key. Possible values: acquired (default), contended,
         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-record.txt b/tools/perf/Documentation/perf-record.txt
index 2937f7e14bb7..a1386b2fff00 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -52,11 +52,15 @@ OPTIONS
 
 -p::
 --pid=::
-        Record events on existing process ID.
+        Record events on existing process ID (comma separated list).
 
 -t::
 --tid=::
-        Record events on existing thread ID.
+        Record events on existing thread ID (comma separated list).
+
+-u::
+--uid=::
+        Record events in threads owned by uid. Name or number.
 
 -r::
 --realtime=::
@@ -148,6 +152,36 @@ an empty cgroup (monitor all the time) using, e.g., -G foo,,bar. Cgroups must ha
 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
+        - any_ind: 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
+
++
+The option requires at least one branch type among any, any_call, any_ret, ind_call.
+The privilege levels may be ommitted, 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.
+
 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 9b430e98712e..87feeee8b90c 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -153,6 +153,16 @@ OPTIONS
         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.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-annotate[1]
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 2f6cef43da25..e9cbfcddfa3f 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -115,7 +115,7 @@ OPTIONS
 -f::
 --fields::
         Comma separated list of fields to print. Options are:
-        comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr.
+        comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff.
         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
@@ -200,6 +200,9 @@ OPTIONS
         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]
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-script-perl[1],
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 8966b9ab2014..2fa173b51970 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -35,11 +35,11 @@ OPTIONS
         child tasks do not inherit counters
 -p::
 --pid=<pid>::
-        stat events on existing process id
+        stat events on existing process id (comma separated list)
 
 -t::
 --tid=<tid>::
-        stat events on existing thread id
+        stat events on existing thread id (comma separated list)
 
 
 -a::
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index b1a5bbbfebef..4a5680cb242e 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -72,11 +72,15 @@ Default is to monitor all CPUS.
 
 -p <pid>::
 --pid=<pid>::
-        Profile events on existing Process ID.
+        Profile events on existing Process ID (comma separated list).
 
 -t <tid>::
 --tid=<tid>::
-        Profile events on existing thread ID.
+        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>::
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 1078c5fadd5b..5476bc0a1eac 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -9,6 +9,7 @@ lib/rbtree.c
 include/linux/swab.h
 arch/*/include/asm/unistd*.h
 arch/*/lib/memcpy*.S
+arch/*/lib/memset*.S
 include/linux/poison.h
 include/linux/magic.h
 include/linux/hw_breakpoint.h
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 8a4b9bccf8b2..74fd7f89208a 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -15,6 +15,16 @@ endif
 
 # Define V to have a more verbose compile.
 #
+# 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
 #
@@ -32,6 +42,10 @@ endif
 # 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.
+#
+# Define NO_DEMANGLE if you do not want C++ symbol demangling.
 
 $(OUTPUT)PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE
         @$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT)
@@ -61,7 +75,7 @@ ifeq ($(ARCH),x86_64)
         ifeq (${IS_X86_64}, 1)
                 RAW_ARCH := x86_64
                 ARCH_CFLAGS := -DARCH_X86_64
-                ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S
+                ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memset_64.S
         endif
 endif
 
@@ -183,7 +197,10 @@ SCRIPT_SH += perf-archive.sh
 grep-libs = $(filter -l%,$(1))
 strip-libs = $(filter-out -l%,$(1))
 
-$(OUTPUT)python/perf.so: $(PYRF_OBJS)
+PYTHON_EXT_SRCS := $(shell grep -v ^\# util/python-ext-sources)
+PYTHON_EXT_DEPS := util/python-ext-sources util/setup.py
+
+$(OUTPUT)python/perf.so: $(PYRF_OBJS) $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS)
         $(QUIET_GEN)CFLAGS='$(BASIC_CFLAGS)' $(PYTHON_WORD) util/setup.py \
           --quiet build_ext; \
         mkdir -p $(OUTPUT)python && \
@@ -258,6 +275,7 @@ LIB_H += util/callchain.h
 LIB_H += util/build-id.h
 LIB_H += util/debug.h
 LIB_H += util/debugfs.h
+LIB_H += util/sysfs.h
 LIB_H += util/event.h
 LIB_H += util/evsel.h
 LIB_H += util/evlist.h
@@ -304,6 +322,7 @@ LIB_OBJS += $(OUTPUT)util/build-id.o
 LIB_OBJS += $(OUTPUT)util/config.o
 LIB_OBJS += $(OUTPUT)util/ctype.o
 LIB_OBJS += $(OUTPUT)util/debugfs.o
+LIB_OBJS += $(OUTPUT)util/sysfs.o
 LIB_OBJS += $(OUTPUT)util/environment.o
 LIB_OBJS += $(OUTPUT)util/event.o
 LIB_OBJS += $(OUTPUT)util/evlist.o
@@ -361,8 +380,10 @@ 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)builtin-diff.o
 BUILTIN_OBJS += $(OUTPUT)builtin-evlist.o
@@ -794,7 +815,6 @@ help:
         @echo '  quick-install-html     - install the html documentation quickly'
         @echo ''
         @echo 'Perf maintainer targets:'
-        @echo '  distclean              - alias to clean'
         @echo '  clean                  - clean all binary objects and build output'
 
 doc:
diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h
index f7781c6267c0..a09bece6dad2 100644
--- a/tools/perf/bench/bench.h
+++ b/tools/perf/bench/bench.h
@@ -4,6 +4,7 @@
 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_memset(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/mem-memcpy-x86-64-asm-def.h b/tools/perf/bench/mem-memcpy-x86-64-asm-def.h
index d588b87696fc..d66ab799b35f 100644
--- a/tools/perf/bench/mem-memcpy-x86-64-asm-def.h
+++ b/tools/perf/bench/mem-memcpy-x86-64-asm-def.h
@@ -2,3 +2,11 @@
 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
index 185a96d66dd1..fcd9cf00600a 100644
--- a/tools/perf/bench/mem-memcpy-x86-64-asm.S
+++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S
@@ -1,4 +1,8 @@
-
+#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
diff --git a/tools/perf/bench/mem-memcpy.c b/tools/perf/bench/mem-memcpy.c
index db82021f4b91..71557225bf92 100644
--- a/tools/perf/bench/mem-memcpy.c
+++ b/tools/perf/bench/mem-memcpy.c
@@ -5,7 +5,6 @@
  *
  * Written by Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp>
  */
-#include <ctype.h>
 
 #include "../perf.h"
 #include "../util/util.h"
@@ -24,6 +23,7 @@
 
 static const char       *length_str     = "1MB";
 static const char       *routine        = "default";
+static int              iterations      = 1;
 static bool             use_clock;
 static int              clock_fd;
 static bool             only_prefault;
@@ -35,6 +35,8 @@ static const struct option options[] = {
                     "available unit: B, MB, GB (upper and lower)"),
         OPT_STRING('r', "routine", &routine, "default",
                     "Specify routine to copy"),
+        OPT_INTEGER('i', "iterations", &iterations,
+                    "repeat memcpy() invocation this number of times"),
         OPT_BOOLEAN('c', "clock", &use_clock,
                     "Use CPU clock for measuring"),
         OPT_BOOLEAN('o', "only-prefault", &only_prefault,
@@ -121,6 +123,7 @@ static u64 do_memcpy_clock(memcpy_t fn, size_t len, bool prefault)
 {
         u64 clock_start = 0ULL, clock_end = 0ULL;
         void *src = NULL, *dst = NULL;
+        int i;
 
         alloc_mem(&src, &dst, len);
 
@@ -128,7 +131,8 @@ static u64 do_memcpy_clock(memcpy_t fn, size_t len, bool prefault)
                 fn(dst, src, len);
 
         clock_start = get_clock();
-        fn(dst, src, len);
+        for (i = 0; i < iterations; ++i)
+                fn(dst, src, len);
         clock_end = get_clock();
 
         free(src);
@@ -140,6 +144,7 @@ static double do_memcpy_gettimeofday(memcpy_t fn, size_t len, bool prefault)
 {
         struct timeval tv_start, tv_end, tv_diff;
         void *src = NULL, *dst = NULL;
+        int i;
 
         alloc_mem(&src, &dst, len);
 
@@ -147,7 +152,8 @@ static double do_memcpy_gettimeofday(memcpy_t fn, size_t len, bool prefault)
                 fn(dst, src, len);
 
         BUG_ON(gettimeofday(&tv_start, NULL));
-        fn(dst, src, len);
+        for (i = 0; i < iterations; ++i)
+                fn(dst, src, len);
         BUG_ON(gettimeofday(&tv_end, NULL));
 
         timersub(&tv_end, &tv_start, &tv_diff);
diff --git a/tools/perf/bench/mem-memset-arch.h b/tools/perf/bench/mem-memset-arch.h
new file mode 100644
index 000000000000..a040fa77665b
--- /dev/null
+++ b/tools/perf/bench/mem-memset-arch.h
@@ -0,0 +1,12 @@
+
+#ifdef ARCH_X86_64
+
+#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 000000000000..a71dff97c1f5
--- /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 000000000000..9e5af89ed13a
--- /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 000000000000..e9079185bd72
--- /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_clock;
+static int              clock_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)"),
+        OPT_STRING('r', "routine", &routine, "default",
+                    "Specify routine to copy"),
+        OPT_INTEGER('i', "iterations", &iterations,
+                    "repeat memset() invocation this number of times"),
+        OPT_BOOLEAN('c', "clock", &use_clock,
+                    "Use CPU clock 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 ARCH_X86_64
+
+#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 clock_attr = {
+        .type           = PERF_TYPE_HARDWARE,
+        .config         = PERF_COUNT_HW_CPU_CYCLES
+};
+
+static void init_clock(void)
+{
+        clock_fd = sys_perf_event_open(&clock_attr, getpid(), -1, -1, 0);
+
+        if (clock_fd < 0 && errno == ENOSYS)
+                die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
+        else
+                BUG_ON(clock_fd < 0);
+}
+
+static u64 get_clock(void)
+{
+        int ret;
+        u64 clk;
+
+        ret = read(clock_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_clock(memset_t fn, size_t len, bool prefault)
+{
+        u64 clock_start = 0ULL, clock_end = 0ULL;
+        void *dst = NULL;
+        int i;
+
+        alloc_mem(&dst, len);
+
+        if (prefault)
+                fn(dst, -1, len);
+
+        clock_start = get_clock();
+        for (i = 0; i < iterations; ++i)
+                fn(dst, i, len);
+        clock_end = get_clock();
+
+        free(dst);
+        return clock_end - clock_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 __used)
+{
+        int i;
+        size_t len;
+        double result_bps[2];
+        u64 result_clock[2];
+
+        argc = parse_options(argc, argv, options,
+                             bench_mem_memset_usage, 0);
+
+        if (use_clock)
+                init_clock();
+
+        len = (size_t)perf_atoll((char *)length_str);
+
+        result_clock[0] = result_clock[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_clock) {
+                        result_clock[0] =
+                                do_memset_clock(routines[i].fn, len, false);
+                        result_clock[1] =
+                                do_memset_clock(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_clock) {
+                        result_clock[pf] =
+                                do_memset_clock(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_clock) {
+                                printf(" %14lf Clock/Byte\n",
+                                        (double)result_clock[0]
+                                        / (double)len);
+                                printf(" %14lf Clock/Byte (with prefault)\n ",
+                                        (double)result_clock[1]
+                                        / (double)len);
+                        } else {
+                                print_bps(result_bps[0]);
+                                printf("\n");
+                                print_bps(result_bps[1]);
+                                printf(" (with prefault)\n");
+                        }
+                } else {
+                        if (use_clock) {
+                                printf(" %14lf Clock/Byte",
+                                        (double)result_clock[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_clock) {
+                                printf("%lf %lf\n",
+                                        (double)result_clock[0] / (double)len,
+                                        (double)result_clock[1] / (double)len);
+                        } else {
+                                printf("%lf %lf\n",
+                                        result_bps[0], result_bps[1]);
+                        }
+                } else {
+                        if (use_clock) {
+                                printf("%lf\n", (double)result_clock[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/builtin-bench.c b/tools/perf/builtin-bench.c
index fcb96269852a..b0e74ab2d7a2 100644
--- a/tools/perf/builtin-bench.c
+++ b/tools/perf/builtin-bench.c
@@ -52,6 +52,9 @@ static struct bench_suite mem_suites[] = {
         { "memcpy",
           "Simple memory copy in various ways",
           bench_mem_memcpy },
+        { "memset",
+          "Simple memory set in various ways",
+          bench_mem_memset },
         suite_all,
         { NULL,
           NULL,
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index 2296c391d0f5..12c814838993 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -922,12 +922,12 @@ 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)"),
+                    "map of lock instances (address:name table)"),
         OPT_END()
 };
 
 static const char * const lock_usage[] = {
-        "perf lock [<options>] {record|trace|report}",
+        "perf lock [<options>] {record|report|script|info}",
         NULL
 };
 
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index fb8566181f27..4935c09dd5b5 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -58,7 +58,7 @@ static struct {
         struct perf_probe_event events[MAX_PROBES];
         struct strlist *dellist;
         struct line_range line_range;
-        const char *target_module;
+        const char *target;
         int max_probe_points;
         struct strfilter *filter;
 } params;
@@ -246,7 +246,7 @@ static const struct option options[] = {
                    "file", "vmlinux pathname"),
         OPT_STRING('s', "source", &symbol_conf.source_prefix,
                    "directory", "path to kernel source"),
-        OPT_STRING('m', "module", &params.target_module,
+        OPT_STRING('m', "module", &params.target,
                    "modname|path",
                    "target module name (for online) or path (for offline)"),
 #endif
@@ -333,7 +333,7 @@ int cmd_probe(int argc, const char **argv, const char *prefix __used)
                 if (!params.filter)
                         params.filter = strfilter__new(DEFAULT_FUNC_FILTER,
                                                        NULL);
-                ret = show_available_funcs(params.target_module,
+                ret = show_available_funcs(params.target,
                                            params.filter);
                 strfilter__delete(params.filter);
                 if (ret < 0)
@@ -354,7 +354,7 @@ int cmd_probe(int argc, const char **argv, const char *prefix __used)
                         usage_with_options(probe_usage, options);
                 }
 
-                ret = show_line_range(&params.line_range, params.target_module);
+                ret = show_line_range(&params.line_range, params.target);
                 if (ret < 0)
                         pr_err("  Error: Failed to show lines. (%d)\n", ret);
                 return ret;
@@ -371,7 +371,7 @@ int cmd_probe(int argc, const char **argv, const char *prefix __used)
 
                 ret = show_available_vars(params.events, params.nevents,
                                           params.max_probe_points,
-                                          params.target_module,
+                                          params.target,
                                           params.filter,
                                           params.show_ext_vars);
                 strfilter__delete(params.filter);
@@ -393,7 +393,7 @@ int cmd_probe(int argc, const char **argv, const char *prefix __used)
         if (params.nevents) {
                 ret = add_perf_probe_events(params.events, params.nevents,
                                             params.max_probe_points,
-                                            params.target_module,
+                                            params.target,
                                             params.force_add);
                 if (ret < 0) {
                         pr_err("  Error: Failed to add events. (%d)\n", ret);
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 227b6ae99785..be4e1eee782e 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -44,6 +44,7 @@ struct perf_record {
         struct perf_evlist      *evlist;
         struct perf_session     *session;
         const char              *progname;
+        const char              *uid_str;
         int                     output;
         unsigned int            page_size;
         int                     realtime_prio;
@@ -208,7 +209,7 @@ fallback_missing_features:
                 if (opts->exclude_guest_missing)
                         attr->exclude_guest = attr->exclude_host = 0;
 retry_sample_id:
-                attr->sample_id_all = opts->sample_id_all_avail ? 1 : 0;
+                attr->sample_id_all = opts->sample_id_all_missing ? 0 : 1;
 try_again:
                 if (perf_evsel__open(pos, evlist->cpus, evlist->threads,
                                      opts->group, group_fd) < 0) {
@@ -227,11 +228,11 @@ try_again:
                                                  "guest or host samples.\n");
                                         opts->exclude_guest_missing = true;
                                         goto fallback_missing_features;
-                                } else if (opts->sample_id_all_avail) {
+                                } else if (!opts->sample_id_all_missing) {
                                         /*
                                          * Old kernel, no attr->sample_id_type_all field
                                          */
-                                        opts->sample_id_all_avail = false;
+                                        opts->sample_id_all_missing = true;
                                         if (!opts->sample_time && !opts->raw_samples && !time_needed)
                                                 attr->sample_type &= ~PERF_SAMPLE_TIME;
 
@@ -396,7 +397,7 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
 {
         struct stat st;
         int flags;
-        int err, output;
+        int err, output, feat;
         unsigned long waking = 0;
         const bool forks = argc > 0;
         struct machine *machine;
@@ -463,8 +464,17 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
 
         rec->session = session;
 
-        if (!rec->no_buildid)
-                perf_header__set_feat(&session->header, HEADER_BUILD_ID);
+        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(&evsel_list->entries))
+                perf_header__clear_feat(&session->header, HEADER_TRACE_INFO);
+
+        if (!rec->opts.branch_stack)
+                perf_header__clear_feat(&session->header, HEADER_BRANCH_STACK);
 
         if (!rec->file_new) {
                 err = perf_session__read_header(session, output);
@@ -472,22 +482,6 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
                         goto out_delete_session;
         }
 
-        if (have_tracepoints(&evsel_list->entries))
-                perf_header__set_feat(&session->header, HEADER_TRACE_INFO);
-
-        perf_header__set_feat(&session->header, HEADER_HOSTNAME);
-        perf_header__set_feat(&session->header, HEADER_OSRELEASE);
-        perf_header__set_feat(&session->header, HEADER_ARCH);
-        perf_header__set_feat(&session->header, HEADER_CPUDESC);
-        perf_header__set_feat(&session->header, HEADER_NRCPUS);
-        perf_header__set_feat(&session->header, HEADER_EVENT_DESC);
-        perf_header__set_feat(&session->header, HEADER_CMDLINE);
-        perf_header__set_feat(&session->header, HEADER_VERSION);
-        perf_header__set_feat(&session->header, HEADER_CPU_TOPOLOGY);
-        perf_header__set_feat(&session->header, HEADER_TOTAL_MEM);
-        perf_header__set_feat(&session->header, HEADER_NUMA_TOPOLOGY);
-        perf_header__set_feat(&session->header, HEADER_CPUID);
-
         if (forks) {
                 err = perf_evlist__prepare_workload(evsel_list, opts, argv);
                 if (err < 0) {
@@ -647,6 +641,90 @@ out_delete_session:
         return err;
 }
 
+#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_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;
+
+        /*
+         * cannot set it twice, -b + --branch-filter for instance
+         */
+        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;
+}
+
 static const char * const record_usage[] = {
         "perf record [<options>] [<command>]",
         "perf record [<options>] -- <command> [<options>]",
@@ -665,13 +743,10 @@ static const char * const record_usage[] = {
  */
 static struct perf_record record = {
         .opts = {
-                .target_pid          = -1,
-                .target_tid          = -1,
                 .mmap_pages          = UINT_MAX,
                 .user_freq           = UINT_MAX,
                 .user_interval       = ULLONG_MAX,
                 .freq                = 1000,
-                .sample_id_all_avail = true,
         },
         .write_mode = WRITE_FORCE,
         .file_new   = true,
@@ -690,9 +765,9 @@ const struct option record_options[] = {
                      parse_events_option),
         OPT_CALLBACK(0, "filter", &record.evlist, "filter",
                      "event filter", parse_filter),
-        OPT_INTEGER('p', "pid", &record.opts.target_pid,
+        OPT_STRING('p', "pid", &record.opts.target_pid, "pid",
                     "record events on existing process id"),
-        OPT_INTEGER('t', "tid", &record.opts.target_tid,
+        OPT_STRING('t', "tid", &record.opts.target_tid, "tid",
                     "record events on existing thread id"),
         OPT_INTEGER('r', "realtime", &record.realtime_prio,
                     "collect data with this RT SCHED_FIFO priority"),
@@ -738,6 +813,15 @@ const struct option record_options[] = {
         OPT_CALLBACK('G', "cgroup", &record.evlist, "name",
                      "monitor event in cgroup name only",
                      parse_cgroups),
+        OPT_STRING('u', "uid", &record.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_END()
 };
 
@@ -758,8 +842,8 @@ int cmd_record(int argc, const char **argv, const char *prefix __used)
 
         argc = parse_options(argc, argv, record_options, record_usage,
                             PARSE_OPT_STOP_AT_NON_OPTION);
-        if (!argc && rec->opts.target_pid == -1 && rec->opts.target_tid == -1 &&
-                !rec->opts.system_wide && !rec->opts.cpu_list)
+        if (!argc && !rec->opts.target_pid && !rec->opts.target_tid &&
+                !rec->opts.system_wide && !rec->opts.cpu_list && !rec->uid_str)
                 usage_with_options(record_usage, record_options);
 
         if (rec->force && rec->append_file) {
@@ -799,11 +883,17 @@ int cmd_record(int argc, const char **argv, const char *prefix __used)
                 goto out_symbol_exit;
         }
 
-        if (rec->opts.target_pid != -1)
+        rec->opts.uid = parse_target_uid(rec->uid_str, rec->opts.target_tid,
+                                         rec->opts.target_pid);
+        if (rec->uid_str != NULL && rec->opts.uid == UINT_MAX - 1)
+                goto out_free_fd;
+
+        if (rec->opts.target_pid)
                 rec->opts.target_tid = rec->opts.target_pid;
 
         if (perf_evlist__create_maps(evsel_list, rec->opts.target_pid,
-                                     rec->opts.target_tid, rec->opts.cpu_list) < 0)
+                                     rec->opts.target_tid, rec->opts.uid,
+                                     rec->opts.cpu_list) < 0)
                 usage_with_options(record_usage, record_options);
 
         list_for_each_entry(pos, &evsel_list->entries, node) {
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 25d34d483e49..8e91c6eba18a 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -53,6 +53,82 @@ struct perf_report {
         DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 };
 
+static int perf_report__add_branch_hist_entry(struct perf_tool *tool,
+                                        struct addr_location *al,
+                                        struct perf_sample *sample,
+                                        struct perf_evsel *evsel,
+                                      struct machine *machine)
+{
+        struct perf_report *rep = container_of(tool, struct perf_report, tool);
+        struct symbol *parent = NULL;
+        int err = 0;
+        unsigned i;
+        struct hist_entry *he;
+        struct branch_info *bi, *bx;
+
+        if ((sort__has_parent || symbol_conf.use_callchain)
+            && sample->callchain) {
+                err = machine__resolve_callchain(machine, evsel, al->thread,
+                                                 sample->callchain, &parent);
+                if (err)
+                        return err;
+        }
+
+        bi = machine__resolve_bstack(machine, al->thread,
+                                     sample->branch_stack);
+        if (!bi)
+                return -ENOMEM;
+
+        for (i = 0; i < sample->branch_stack->nr; i++) {
+                if (rep->hide_unresolved && !(bi[i].from.sym && bi[i].to.sym))
+                        continue;
+                /*
+                 * The report shows the percentage of total branches captured
+                 * and not events sampled. Thus we use a pseudo period of 1.
+                 */
+                he = __hists__add_branch_entry(&evsel->hists, al, parent,
+                                &bi[i], 1);
+                if (he) {
+                        struct annotation *notes;
+                        err = -ENOMEM;
+                        bx = he->branch_info;
+                        if (bx->from.sym && use_browser > 0) {
+                                notes = symbol__annotation(bx->from.sym);
+                                if (!notes->src
+                                    && symbol__alloc_hist(bx->from.sym) < 0)
+                                        goto out;
+
+                                err = symbol__inc_addr_samples(bx->from.sym,
+                                                               bx->from.map,
+                                                               evsel->idx,
+                                                               bx->from.al_addr);
+                                if (err)
+                                        goto out;
+                        }
+
+                        if (bx->to.sym && use_browser > 0) {
+                                notes = symbol__annotation(bx->to.sym);
+                                if (!notes->src
+                                    && symbol__alloc_hist(bx->to.sym) < 0)
+                                        goto out;
+
+                                err = symbol__inc_addr_samples(bx->to.sym,
+                                                               bx->to.map,
+                                                               evsel->idx,
+                                                               bx->to.al_addr);
+                                if (err)
+                                        goto out;
+                        }
+                        evsel->hists.stats.total_period += 1;
+                        hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
+                        err = 0;
+                } else
+                        return -ENOMEM;
+        }
+out:
+        return err;
+}
+
 static int perf_evsel__add_hist_entry(struct perf_evsel *evsel,
                                       struct addr_location *al,
                                       struct perf_sample *sample,
@@ -126,14 +202,21 @@ static int process_sample_event(struct perf_tool *tool,
         if (rep->cpu_list && !test_bit(sample->cpu, rep->cpu_bitmap))
                 return 0;
 
-        if (al.map != NULL)
-                al.map->dso->hit = 1;
+        if (sort__branch_mode == 1) {
+                if (perf_report__add_branch_hist_entry(tool, &al, sample,
+                                                       evsel, machine)) {
+                        pr_debug("problem adding lbr entry, skipping event\n");
+                        return -1;
+                }
+        } else {
+                if (al.map != NULL)
+                        al.map->dso->hit = 1;
 
-        if (perf_evsel__add_hist_entry(evsel, &al, sample, machine)) {
-                pr_debug("problem incrementing symbol period, skipping event\n");
-                return -1;
+                if (perf_evsel__add_hist_entry(evsel, &al, sample, machine)) {
+                        pr_debug("problem incrementing symbol period, skipping event\n");
+                        return -1;
+                }
         }
-
         return 0;
 }
 
@@ -188,6 +271,15 @@ static int perf_report__setup_sample_type(struct perf_report *rep)
                         }
         }
 
+        if (sort__branch_mode == 1) {
+                if (!(self->sample_type & PERF_SAMPLE_BRANCH_STACK)) {
+                        fprintf(stderr, "selected -b but no branch data."
+                                        " Did you call perf record without"
+                                        " -b?\n");
+                        return -1;
+                }
+        }
+
         return 0;
 }
 
@@ -246,7 +338,7 @@ static int __cmd_report(struct perf_report *rep)
 {
         int ret = -EINVAL;
         u64 nr_samples;
-        struct perf_session *session;
+        struct perf_session *session = rep->session;
         struct perf_evsel *pos;
         struct map *kernel_map;
         struct kmap *kernel_kmap;
@@ -254,13 +346,6 @@ static int __cmd_report(struct perf_report *rep)
 
         signal(SIGINT, sig_handler);
 
-        session = perf_session__new(rep->input_name, O_RDONLY,
-                                    rep->force, false, &rep->tool);
-        if (session == NULL)
-                return -ENOMEM;
-
-        rep->session = session;
-
         if (rep->cpu_list) {
                 ret = perf_session__cpu_bitmap(session, rep->cpu_list,
                                                rep->cpu_bitmap);
@@ -427,9 +512,19 @@ setup:
         return 0;
 }
 
+static int
+parse_branch_mode(const struct option *opt __used, const char *str __used, int unset)
+{
+        sort__branch_mode = !unset;
+        return 0;
+}
+
 int cmd_report(int argc, const char **argv, const char *prefix __used)
 {
+        struct perf_session *session;
         struct stat st;
+        bool has_br_stack = false;
+        int ret = -1;
         char callchain_default_opt[] = "fractal,0.5,callee";
         const char * const report_usage[] = {
                 "perf report [<options>]",
@@ -477,7 +572,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __used)
         OPT_BOOLEAN(0, "stdio", &report.use_stdio,
                     "Use the stdio interface"),
         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, dso_to,"
+                   " dso_from, symbol_to, symbol_from, mispredict"),
         OPT_BOOLEAN(0, "showcpuutilization", &symbol_conf.show_cpu_utilization,
                     "Show sample percentage for different cpu modes"),
         OPT_STRING('p', "parent", &parent_pattern, "regex",
@@ -517,6 +613,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __used)
                    "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_CALLBACK_NOOPT('b', "branch-stack", &sort__branch_mode, "",
+                    "use branch records for histogram filling", parse_branch_mode),
         OPT_END()
         };
 
@@ -536,11 +634,36 @@ int cmd_report(int argc, const char **argv, const char *prefix __used)
                 else
                         report.input_name = "perf.data";
         }
+        session = perf_session__new(report.input_name, O_RDONLY,
+                                    report.force, false, &report.tool);
+        if (session == NULL)
+                return -ENOMEM;
 
-        if (strcmp(report.input_name, "-") != 0)
+        report.session = session;
+
+        has_br_stack = perf_header__has_feat(&session->header,
+                                             HEADER_BRANCH_STACK);
+
+        if (sort__branch_mode == -1 && has_br_stack)
+                sort__branch_mode = 1;
+
+        /* sort__branch_mode could be 0 if --no-branch-stack */
+        if (sort__branch_mode == 1) {
+                /*
+                 * if no sort_order is provided, then specify
+                 * branch-mode specific order
+                 */
+                if (sort_order == default_sort_order)
+                        sort_order = "comm,dso_from,symbol_from,"
+                                     "dso_to,symbol_to";
+
+        }
+
+        if (strcmp(report.input_name, "-") != 0) {
                 setup_browser(true);
-        else
+        } else {
                 use_browser = 0;
+        }
 
         /*
          * Only in the newt browser we are doing integrated annotation,
@@ -568,13 +691,13 @@ int cmd_report(int argc, const char **argv, const char *prefix __used)
         }
 
         if (symbol__init() < 0)
-                return -1;
+                goto error;
 
         setup_sorting(report_usage, options);
 
         if (parent_pattern != default_parent_pattern) {
                 if (sort_dimension__add("parent") < 0)
-                        return -1;
+                        goto error;
 
                 /*
                  * Only show the parent fields if we explicitly
@@ -592,9 +715,20 @@ int cmd_report(int argc, const char **argv, const char *prefix __used)
         if (argc)
                 usage_with_options(report_usage, options);
 
-        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);
 
-        return __cmd_report(&report);
+        if (sort__branch_mode == 1) {
+                sort_entry__setup_elide(&sort_dso_from, symbol_conf.dso_from_list, "dso_from", stdout);
+                sort_entry__setup_elide(&sort_dso_to, symbol_conf.dso_to_list, "dso_to", stdout);
+                sort_entry__setup_elide(&sort_sym_from, symbol_conf.sym_from_list, "sym_from", stdout);
+                sort_entry__setup_elide(&sort_sym_to, symbol_conf.sym_to_list, "sym_to", stdout);
+        } else {
+                sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "dso", stdout);
+                sort_entry__setup_elide(&sort_sym, symbol_conf.sym_list, "symbol", stdout);
+        }
+
+        ret = __cmd_report(&report);
+error:
+        perf_session__delete(session);
+        return ret;
 }
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index bb68ddf257b7..d4ce733b9eba 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -40,6 +40,7 @@ enum perf_output_field {
         PERF_OUTPUT_SYM             = 1U << 8,
         PERF_OUTPUT_DSO             = 1U << 9,
         PERF_OUTPUT_ADDR            = 1U << 10,
+        PERF_OUTPUT_SYMOFFSET       = 1U << 11,
 };
 
 struct output_option {
@@ -57,6 +58,7 @@ struct output_option {
         {.str = "sym",   .field = PERF_OUTPUT_SYM},
         {.str = "dso",   .field = PERF_OUTPUT_DSO},
         {.str = "addr",  .field = PERF_OUTPUT_ADDR},
+        {.str = "symoff", .field = PERF_OUTPUT_SYMOFFSET},
 };
 
 /* default set to maintain compatibility with current format */
@@ -193,6 +195,11 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
                        "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 "
@@ -300,10 +307,17 @@ static void print_sample_start(struct perf_sample *sample,
                 } else
                         evname = __event_name(attr->type, attr->config);
 
-                printf("%s: ", evname ? evname : "(unknown)");
+                printf("%s: ", evname ? evname : "[unknown]");
         }
 }
 
+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) &&
@@ -312,6 +326,9 @@ static bool sample_addr_correlates_sym(struct perf_event_attr *attr)
              (attr->config == PERF_COUNT_SW_PAGE_FAULTS_MAJ)))
                 return true;
 
+        if (is_bts_event(attr))
+                return true;
+
         return false;
 }
 
@@ -323,7 +340,6 @@ static void print_sample_addr(union perf_event *event,
 {
         struct addr_location al;
         u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
-        const char *symname, *dsoname;
 
         printf("%16" PRIx64, sample->addr);
 
@@ -343,22 +359,46 @@ static void print_sample_addr(union perf_event *event,
                 al.sym = map__find_symbol(al.map, al.addr, NULL);
 
         if (PRINT_FIELD(SYM)) {
-                if (al.sym && al.sym->name)
-                        symname = al.sym->name;
+                printf(" ");
+                if (PRINT_FIELD(SYMOFFSET))
+                        symbol__fprintf_symname_offs(al.sym, &al, stdout);
                 else
-                        symname = "";
-
-                printf(" %16s", symname);
+                        symbol__fprintf_symname(al.sym, stdout);
         }
 
         if (PRINT_FIELD(DSO)) {
-                if (al.map && al.map->dso && al.map->dso->name)
-                        dsoname = al.map->dso->name;
-                else
-                        dsoname = "";
+                printf(" (");
+                map__fprintf_dsoname(al.map, stdout);
+                printf(")");
+        }
+}
 
-                printf(" (%s)", dsoname);
+static void print_sample_bts(union perf_event *event,
+                             struct perf_sample *sample,
+                             struct perf_evsel *evsel,
+                             struct machine *machine,
+                             struct thread *thread)
+{
+        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_event__print_ip(event, sample, machine, evsel,
+                                     PRINT_FIELD(SYM), PRINT_FIELD(DSO),
+                                     PRINT_FIELD(SYMOFFSET));
         }
+
+        printf(" => ");
+
+        /* print branch_to information */
+        if (PRINT_FIELD(ADDR))
+                print_sample_addr(event, sample, machine, thread, attr);
+
+        printf("\n");
 }
 
 static void process_event(union perf_event *event __unused,
@@ -374,6 +414,11 @@ static void process_event(union perf_event *event __unused,
 
         print_sample_start(sample, thread, attr);
 
+        if (is_bts_event(attr)) {
+                print_sample_bts(event, sample, evsel, machine, thread);
+                return;
+        }
+
         if (PRINT_FIELD(TRACE))
                 print_trace_event(sample->cpu, sample->raw_data,
                                   sample->raw_size);
@@ -387,7 +432,8 @@ static void process_event(union perf_event *event __unused,
                 else
                         printf("\n");
                 perf_event__print_ip(event, sample, machine, evsel,
-                                     PRINT_FIELD(SYM), PRINT_FIELD(DSO));
+                                     PRINT_FIELD(SYM), PRINT_FIELD(DSO),
+                                     PRINT_FIELD(SYMOFFSET));
         }
 
         printf("\n");
@@ -1097,7 +1143,10 @@ static const struct option options[] = {
         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",
+                     "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"),
@@ -1106,6 +1155,9 @@ static const struct option options[] = {
                    "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_END()
 };
 
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index f5d2a63eba66..ea40e4e8b227 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -182,8 +182,8 @@ static int			run_count			=  1;
 static bool                     no_inherit                      = false;
 static bool                     scale                           =  true;
 static bool                     no_aggr                         = false;
-static pid_t                    target_pid                      = -1;
-static pid_t                    target_tid                      = -1;
+static const char               *target_pid;
+static const char               *target_tid;
 static pid_t                    child_pid                       = -1;
 static bool                     null_run                        =  false;
 static int                      detailed_run                    =  0;
@@ -296,7 +296,7 @@ static int create_perf_stat_counter(struct perf_evsel *evsel,
         if (system_wide)
                 return perf_evsel__open_per_cpu(evsel, evsel_list->cpus,
                                                 group, group_fd);
-        if (target_pid == -1 && target_tid == -1) {
+        if (!target_pid && !target_tid) {
                 attr->disabled = 1;
                 attr->enable_on_exec = 1;
         }
@@ -446,7 +446,7 @@ static int run_perf_stat(int argc __used, const char **argv)
                         exit(-1);
                 }
 
-                if (target_tid == -1 && target_pid == -1 && !system_wide)
+                if (!target_tid && !target_pid && !system_wide)
                         evsel_list->threads->map[0] = child_pid;
 
                 /*
@@ -576,6 +576,8 @@ static void nsec_printout(int cpu, struct perf_evsel *evsel, double avg)
         if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK))
                 fprintf(output, " # %8.3f CPUs utilized          ",
                         avg / avg_stats(&walltime_nsecs_stats));
+        else
+                fprintf(output, "                                   ");
 }
 
 /* used for get_ratio_color() */
@@ -844,12 +846,18 @@ static void abs_printout(int cpu, struct perf_evsel *evsel, double avg)
 
                 fprintf(output, " # %8.3f GHz                    ", 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(output, " # %8.3f M/sec                  ", ratio);
+                fprintf(output, " # %8.3f %c/sec                  ", ratio, unit);
         } else {
                 fprintf(output, "                                   ");
         }
@@ -960,14 +968,14 @@ static void print_stat(int argc, const char **argv)
         if (!csv_output) {
                 fprintf(output, "\n");
                 fprintf(output, " Performance counter stats for ");
-                if(target_pid == -1 && target_tid == -1) {
+                if (!target_pid && !target_tid) {
                         fprintf(output, "\'%s", argv[0]);
                         for (i = 1; i < argc; i++)
                                 fprintf(output, " %s", argv[i]);
-                } else if (target_pid != -1)
-                        fprintf(output, "process id \'%d", target_pid);
+                } else if (target_pid)
+                        fprintf(output, "process id \'%s", target_pid);
                 else
-                        fprintf(output, "thread id \'%d", target_tid);
+                        fprintf(output, "thread id \'%s", target_tid);
 
                 fprintf(output, "\'");
                 if (run_count > 1)
@@ -1041,10 +1049,10 @@ static const struct option options[] = {
                      "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_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", &system_wide,
                     "system-wide collection from all CPUs"),
         OPT_BOOLEAN('g', "group", &group,
@@ -1182,7 +1190,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used)
         } else if (big_num_opt == 0) /* User passed --no-big-num */
                 big_num = false;
 
-        if (!argc && target_pid == -1 && target_tid == -1)
+        if (!argc && !target_pid && !target_tid)
                 usage_with_options(stat_usage, options);
         if (run_count <= 0)
                 usage_with_options(stat_usage, options);
@@ -1198,10 +1206,11 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used)
         if (add_default_attributes())
                 goto out;
 
-        if (target_pid != -1)
+        if (target_pid)
                 target_tid = target_pid;
 
-        evsel_list->threads = thread_map__new(target_pid, target_tid);
+        evsel_list->threads = thread_map__new_str(target_pid,
+                                                  target_tid, UINT_MAX);
         if (evsel_list->threads == NULL) {
                 pr_err("Problems finding threads of monitor\n");
                 usage_with_options(stat_usage, options);
diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c
index 3854e869dce1..3e087ce8daa6 100644
--- a/tools/perf/builtin-test.c
+++ b/tools/perf/builtin-test.c
@@ -15,6 +15,8 @@
 #include "util/thread_map.h"
 #include "../../include/linux/hw_breakpoint.h"
 
+#include <sys/mman.h>
+
 static int vmlinux_matches_kallsyms_filter(struct map *map __used, struct symbol *sym)
 {
         bool *visited = symbol__priv(sym);
@@ -276,7 +278,7 @@ static int test__open_syscall_event(void)
                 return -1;
         }
 
-        threads = thread_map__new(-1, getpid());
+        threads = thread_map__new(-1, getpid(), UINT_MAX);
         if (threads == NULL) {
                 pr_debug("thread_map__new\n");
                 return -1;
@@ -342,7 +344,7 @@ static int test__open_syscall_event_on_all_cpus(void)
                 return -1;
         }
 
-        threads = thread_map__new(-1, getpid());
+        threads = thread_map__new(-1, getpid(), UINT_MAX);
         if (threads == NULL) {
                 pr_debug("thread_map__new\n");
                 return -1;
@@ -490,7 +492,7 @@ static int test__basic_mmap(void)
                 expected_nr_events[i] = random() % 257;
         }
 
-        threads = thread_map__new(-1, getpid());
+        threads = thread_map__new(-1, getpid(), UINT_MAX);
         if (threads == NULL) {
                 pr_debug("thread_map__new\n");
                 return -1;
@@ -1008,12 +1010,9 @@ realloc:
 static int test__PERF_RECORD(void)
 {
         struct perf_record_opts opts = {
-                .target_pid = -1,
-                .target_tid = -1,
                 .no_delay   = true,
                 .freq       = 10,
                 .mmap_pages = 256,
-                .sample_id_all_avail = true,
         };
         cpu_set_t *cpu_mask = NULL;
         size_t cpu_mask_size = 0;
@@ -1054,7 +1053,7 @@ static int test__PERF_RECORD(void)
          * we're monitoring, the one forked there.
          */
         err = perf_evlist__create_maps(evlist, opts.target_pid,
-                                       opts.target_tid, opts.cpu_list);
+                                       opts.target_tid, UINT_MAX, opts.cpu_list);
         if (err < 0) {
                 pr_debug("Not enough memory to create thread/cpu maps\n");
                 goto out_delete_evlist;
@@ -1296,6 +1295,173 @@ out:
         return (err < 0 || errs > 0) ? -1 : 0;
 }
 
+
+#if defined(__x86_64__) || defined(__i386__)
+
+#define barrier() asm volatile("" ::: "memory")
+
+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 __used, siginfo_t *info __used, void *uc __used)
+{
+        exit(-1);
+}
+
+static int __test__rdpmc(void)
+{
+        long page_size = sysconf(_SC_PAGE_SIZE);
+        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);
+
+        fprintf(stderr, "\n\n");
+
+        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));
+        }
+
+        addr = mmap(NULL, page_size, PROT_READ, MAP_SHARED, fd, 0);
+        if (addr == (void *)(-1)) {
+                die("Error: mmap() syscall returned "
+                    "with (%s)\n", strerror(errno));
+        }
+
+        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;
+                fprintf(stderr, "%14d: %14Lu\n", n, (long long)delta);
+
+                delta_sum += delta;
+        }
+
+        munmap(addr, page_size);
+        close(fd);
+
+        fprintf(stderr, "   ");
+
+        if (!delta_sum)
+                return -1;
+
+        return 0;
+}
+
+static 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
+
 static struct test {
         const char *desc;
         int (*func)(void);
@@ -1320,6 +1486,12 @@ static struct test {
                 .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,
@@ -1412,7 +1584,5 @@ int cmd_test(int argc, const char **argv, const char *prefix __used)
         if (symbol__init() < 0)
                 return -1;
 
-        setup_pager();
-
         return __cmd_test(argc, argv);
 }
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index ecff31257eb3..e3c63aef8efc 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -64,7 +64,6 @@
 #include <linux/unistd.h>
 #include <linux/types.h>
 
-
 void get_term_dimensions(struct winsize *ws)
 {
         char *s = getenv("LINES");
@@ -544,10 +543,20 @@ static void perf_top__sort_new_samples(void *arg)
 
 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";
 
         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.
+         */
+        list_for_each_entry(pos, &top->evlist->entries, node)
+                pos->hists.uid_filter_str = top->uid_str;
+
         perf_evlist__tui_browse_hists(top->evlist, help,
                                       perf_top__sort_new_samples,
                                       top, top->delay_secs);
@@ -668,6 +677,12 @@ static void perf_event__process_sample(struct perf_tool *tool,
                 return;
         }
 
+        if (!machine) {
+                pr_err("%u unprocessable samples recorded.",
+                       top->session->hists.stats.nr_unprocessable_samples++);
+                return;
+        }
+
         if (event->header.misc & PERF_RECORD_MISC_EXACT_IP)
                 top->exact_samples++;
 
@@ -861,7 +876,7 @@ fallback_missing_features:
                 if (top->exclude_guest_missing)
                         attr->exclude_guest = attr->exclude_host = 0;
 retry_sample_id:
-                attr->sample_id_all = top->sample_id_all_avail ? 1 : 0;
+                attr->sample_id_all = top->sample_id_all_missing ? 0 : 1;
 try_again:
                 if (perf_evsel__open(counter, top->evlist->cpus,
                                      top->evlist->threads, top->group,
@@ -878,11 +893,11 @@ try_again:
                                                  "guest or host samples.\n");
                                         top->exclude_guest_missing = true;
                                         goto fallback_missing_features;
-                                } else if (top->sample_id_all_avail) {
+                                } else if (!top->sample_id_all_missing) {
                                         /*
                                          * Old kernel, no attr->sample_id_type_all field
                                          */
-                                        top->sample_id_all_avail = false;
+                                        top->sample_id_all_missing = true;
                                         goto retry_sample_id;
                                 }
                         }
@@ -967,7 +982,7 @@ static int __cmd_top(struct perf_top *top)
         if (ret)
                 goto out_delete;
 
-        if (top->target_tid != -1)
+        if (top->target_tid || top->uid != UINT_MAX)
                 perf_event__synthesize_thread_map(&top->tool, top->evlist->threads,
                                                   perf_event__process,
                                                   &top->session->host_machine);
@@ -1105,10 +1120,8 @@ int cmd_top(int argc, const char **argv, const char *prefix __used)
         struct perf_top top = {
                 .count_filter        = 5,
                 .delay_secs          = 2,
-                .target_pid          = -1,
-                .target_tid          = -1,
+                .uid                 = UINT_MAX,
                 .freq                = 1000, /* 1 KHz */
-                .sample_id_all_avail = true,
                 .mmap_pages          = 128,
                 .sym_pcnt_filter     = 5,
         };
@@ -1119,9 +1132,9 @@ int cmd_top(int argc, const char **argv, const char *prefix __used)
                      parse_events_option),
         OPT_INTEGER('c', "count", &top.default_interval,
                     "event period to sample"),
-        OPT_INTEGER('p', "pid", &top.target_pid,
+        OPT_STRING('p', "pid", &top.target_pid, "pid",
                     "profile events on existing process id"),
-        OPT_INTEGER('t', "tid", &top.target_tid,
+        OPT_STRING('t', "tid", &top.target_tid, "tid",
                     "profile events on existing thread id"),
         OPT_BOOLEAN('a', "all-cpus", &top.system_wide,
                             "system-wide collection from all CPUs"),
@@ -1180,6 +1193,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __used)
                     "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('u', "uid", &top.uid_str, "user", "user to profile"),
         OPT_END()
         };
 
@@ -1205,18 +1219,22 @@ int cmd_top(int argc, const char **argv, const char *prefix __used)
 
         setup_browser(false);
 
+        top.uid = parse_target_uid(top.uid_str, top.target_tid, top.target_pid);
+        if (top.uid_str != NULL && top.uid == UINT_MAX - 1)
+                goto out_delete_evlist;
+
         /* CPU and PID are mutually exclusive */
-        if (top.target_tid > 0 && top.cpu_list) {
+        if (top.target_tid && top.cpu_list) {
                 printf("WARNING: PID switch overriding CPU\n");
                 sleep(1);
                 top.cpu_list = NULL;
         }
 
-        if (top.target_pid != -1)
+        if (top.target_pid)
                 top.target_tid = top.target_pid;
 
         if (perf_evlist__create_maps(top.evlist, top.target_pid,
-                                     top.target_tid, top.cpu_list) < 0)
+                                     top.target_tid, top.uid, top.cpu_list) < 0)
                 usage_with_options(top_usage, options);
 
         if (!top.evlist->nr_entries &&
@@ -1280,6 +1298,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __used)
 
         status = __cmd_top(&top);
 
+out_delete_evlist:
         perf_evlist__delete(top.evlist);
 
         return status;
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 3afa39ac1d40..89e3355ab173 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -173,7 +173,6 @@ 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);
 }
@@ -186,14 +185,32 @@ struct ip_callchain {
         u64 ips[0];
 };
 
+struct branch_flags {
+        u64 mispred:1;
+        u64 predicted:1;
+        u64 reserved:62;
+};
+
+struct branch_entry {
+        u64                             from;
+        u64                             to;
+        struct branch_flags flags;
+};
+
+struct branch_stack {
+        u64                             nr;
+        struct branch_entry     entries[0];
+};
+
 extern bool perf_host, perf_guest;
 extern const char perf_version_string[];
 
 void pthread__unblock_sigwinch(void);
 
 struct perf_record_opts {
-        pid_t        target_pid;
-        pid_t        target_tid;
+        const char   *target_pid;
+        const char   *target_tid;
+        uid_t        uid;
         bool         call_graph;
         bool         group;
         bool         inherit_stat;
@@ -204,13 +221,14 @@ struct perf_record_opts {
         bool         raw_samples;
         bool         sample_address;
         bool         sample_time;
-        bool         sample_id_all_avail;
+        bool         sample_id_all_missing;
         bool         exclude_guest_missing;
         bool         system_wide;
         bool         period;
         unsigned int freq;
         unsigned int mmap_pages;
         unsigned int user_freq;
+        int          branch_stack;
         u64          default_interval;
         u64          user_interval;
         const char   *cpu_list;
diff --git a/tools/perf/python/twatch.py b/tools/perf/python/twatch.py
index df638c438a9f..b11cca584238 100755
--- a/tools/perf/python/twatch.py
+++ b/tools/perf/python/twatch.py
@@ -19,7 +19,7 @@ def main():
         cpus = perf.cpu_map()
         threads = perf.thread_map()
         evsel = perf.evsel(task = 1, comm = 1, mmap = 0,
-                           wakeup_events = 1, sample_period = 1,
+                           wakeup_events = 1, watermark = 1,
                            sample_id_all = 1,
                            sample_type = perf.SAMPLE_PERIOD | perf.SAMPLE_TID | perf.SAMPLE_CPU | perf.SAMPLE_TID)
         evsel.open(cpus = cpus, threads = threads);
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 011ed2676604..e5a462f1d07c 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -315,7 +315,7 @@ fallback:
                        "Please use:\n\n"
                        "  perf buildid-cache -av vmlinux\n\n"
                        "or:\n\n"
-                       "  --vmlinux vmlinux",
+                       "  --vmlinux vmlinux\n",
                        sym->name, build_id_msg ?: "");
                 goto out_free_filename;
         }
diff --git a/tools/perf/util/bitmap.c b/tools/perf/util/bitmap.c
index 5e230acae1e9..0a1adc1111fd 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/cpumap.c b/tools/perf/util/cpumap.c
index 6893eec693ab..adc72f09914d 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -166,6 +166,17 @@ 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));
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index 072c0a374794..c41518573c6a 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -1,6 +1,8 @@
 #ifndef __PERF_CPUMAP_H
 #define __PERF_CPUMAP_H
 
+#include <stdio.h>
+
 struct cpu_map {
         int nr;
         int map[];
@@ -10,4 +12,6 @@ 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);
 
+size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp);
+
 #endif /* __PERF_CPUMAP_H */
diff --git a/tools/perf/util/ctype.c b/tools/perf/util/ctype.c
index 35073621e5de..aada3ac5e891 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/debugfs.c b/tools/perf/util/debugfs.c
index ffc35e748e89..dd8b19319c03 100644
--- a/tools/perf/util/debugfs.c
+++ b/tools/perf/util/debugfs.c
@@ -15,32 +15,6 @@ static const char *debugfs_known_mountpoints[] = {
         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 */
@@ -97,17 +71,6 @@ int debugfs_valid_mountpoint(const char *debugfs)
         return 0;
 }
 
-
-int debugfs_valid_entry(const char *path)
-{
-        struct stat st;
-
-        if (stat(path, &st))
-                return -errno;
-
-        return 0;
-}
-
 static void debugfs_set_tracing_events_path(const char *mountpoint)
 {
         snprintf(tracing_events_path, sizeof(tracing_events_path), "%s/%s",
@@ -149,107 +112,3 @@ void debugfs_set_path(const char *mountpoint)
         snprintf(debugfs_mountpoint, sizeof(debugfs_mountpoint), "%s", mountpoint);
         debugfs_set_tracing_events_path(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[PATH_MAX + 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[PATH_MAX + 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
index 4a878f735eb0..68f3e87ec57f 100644
--- a/tools/perf/util/debugfs.h
+++ b/tools/perf/util/debugfs.h
@@ -3,14 +3,8 @@
 
 const char *debugfs_find_mountpoint(void);
 int debugfs_valid_mountpoint(const char *debugfs);
-int debugfs_valid_entry(const char *path);
 char *debugfs_mount(const char *mountpoint);
-int debugfs_umount(void);
 void debugfs_set_path(const char *mountpoint);
-int debugfs_write(const char *entry, const char *value);
-int debugfs_read(const char *entry, char *buffer, size_t size);
-void debugfs_force_cleanup(void);
-int debugfs_make_path(const char *element, char *buffer, int size);
 
 extern char debugfs_mountpoint[];
 extern char tracing_events_path[];
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index cbdeaad9c5e5..1b197280c621 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -81,6 +81,7 @@ struct perf_sample {
         u32 raw_size;
         void *raw_data;
         struct ip_callchain *callchain;
+        struct branch_stack *branch_stack;
 };
 
 #define BUILD_ID_SIZE 20
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index ea32a061f1c8..159263d17c2d 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -97,9 +97,9 @@ void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry)
         ++evlist->nr_entries;
 }
 
-static void perf_evlist__splice_list_tail(struct perf_evlist *evlist,
-                                          struct list_head *list,
-                                          int nr_entries)
+void perf_evlist__splice_list_tail(struct perf_evlist *evlist,
+                                   struct list_head *list,
+                                   int nr_entries)
 {
         list_splice_tail(list, &evlist->entries);
         evlist->nr_entries += nr_entries;
@@ -597,15 +597,15 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
         return perf_evlist__mmap_per_cpu(evlist, prot, mask);
 }
 
-int perf_evlist__create_maps(struct perf_evlist *evlist, pid_t target_pid,
-                             pid_t target_tid, const char *cpu_list)
+int perf_evlist__create_maps(struct perf_evlist *evlist, const char *target_pid,
+                             const char *target_tid, uid_t uid, const char *cpu_list)
 {
-        evlist->threads = thread_map__new(target_pid, target_tid);
+        evlist->threads = thread_map__new_str(target_pid, target_tid, uid);
 
         if (evlist->threads == NULL)
                 return -1;
 
-        if (cpu_list == NULL && target_tid != -1)
+        if (uid != UINT_MAX || (cpu_list == NULL && target_tid))
                 evlist->cpus = cpu_map__dummy_new();
         else
                 evlist->cpus = cpu_map__new(cpu_list);
@@ -765,6 +765,7 @@ out_err:
         list_for_each_entry_reverse(evsel, &evlist->entries, node)
                 perf_evsel__close(evsel, ncpus, nthreads);
 
+        errno = -err;
         return err;
 }
 
@@ -824,7 +825,7 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist,
                 exit(-1);
         }
 
-        if (!opts->system_wide && opts->target_tid == -1 && opts->target_pid == -1)
+        if (!opts->system_wide && !opts->target_tid && !opts->target_pid)
                 evlist->threads->map[0] = evlist->workload.pid;
 
         close(child_ready_pipe[1]);
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 8922aeed0467..21f1c9e57f13 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -106,8 +106,8 @@ static inline void perf_evlist__set_maps(struct perf_evlist *evlist,
         evlist->threads = threads;
 }
 
-int perf_evlist__create_maps(struct perf_evlist *evlist, pid_t target_pid,
-                             pid_t target_tid, const char *cpu_list);
+int perf_evlist__create_maps(struct perf_evlist *evlist, const char *target_pid,
+                             const char *tid, uid_t uid, const char *cpu_list);
 void perf_evlist__delete_maps(struct perf_evlist *evlist);
 int perf_evlist__set_filters(struct perf_evlist *evlist);
 
@@ -117,4 +117,9 @@ u16 perf_evlist__id_hdr_size(const struct perf_evlist *evlist);
 
 bool perf_evlist__valid_sample_type(const struct perf_evlist *evlist);
 bool perf_evlist__valid_sample_id_all(const struct perf_evlist *evlist);
+
+void perf_evlist__splice_list_tail(struct perf_evlist *evlist,
+                                   struct list_head *list,
+                                   int nr_entries);
+
 #endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 7132ee834e0e..f421f7cbc0d3 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -68,7 +68,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts)
         struct perf_event_attr *attr = &evsel->attr;
         int track = !evsel->idx; /* only the first counter needs these */
 
-        attr->sample_id_all = opts->sample_id_all_avail ? 1 : 0;
+        attr->sample_id_all = opts->sample_id_all_missing ? 0 : 1;
         attr->inherit       = !opts->no_inherit;
         attr->read_format   = PERF_FORMAT_TOTAL_TIME_ENABLED |
                               PERF_FORMAT_TOTAL_TIME_RUNNING |
@@ -111,7 +111,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts)
         if (opts->period)
                 attr->sample_type       |= PERF_SAMPLE_PERIOD;
 
-        if (opts->sample_id_all_avail &&
+        if (!opts->sample_id_all_missing &&
             (opts->sample_time || opts->system_wide ||
              !opts->no_inherit || opts->cpu_list))
                 attr->sample_type       |= PERF_SAMPLE_TIME;
@@ -126,11 +126,15 @@ void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts)
                 attr->watermark = 0;
                 attr->wakeup_events = 1;
         }
+        if (opts->branch_stack) {
+                attr->sample_type       |= PERF_SAMPLE_BRANCH_STACK;
+                attr->branch_sample_type = opts->branch_stack;
+        }
 
         attr->mmap = track;
         attr->comm = track;
 
-        if (opts->target_pid == -1 && opts->target_tid == -1 && !opts->system_wide) {
+        if (!opts->target_pid && !opts->target_tid && !opts->system_wide) {
                 attr->disabled = 1;
                 attr->enable_on_exec = 1;
         }
@@ -536,7 +540,7 @@ int perf_event__parse_sample(const union perf_event *event, u64 type,
         }
 
         if (type & PERF_SAMPLE_READ) {
-                fprintf(stderr, "PERF_SAMPLE_READ is unsuported for now\n");
+                fprintf(stderr, "PERF_SAMPLE_READ is unsupported for now\n");
                 return -1;
         }
 
@@ -576,6 +580,16 @@ int perf_event__parse_sample(const union perf_event *event, u64 type,
                 data->raw_data = (void *) pdata;
         }
 
+        if (type & PERF_SAMPLE_BRANCH_STACK) {
+                u64 sz;
+
+                data->branch_stack = (struct branch_stack *)array;
+                array++; /* nr */
+
+                sz = data->branch_stack->nr * sizeof(struct branch_entry);
+                sz /= sizeof(u64);
+                array += sz;
+        }
         return 0;
 }
 
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 14bb035c5fd9..fcd9cf3ea63e 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -63,9 +63,20 @@ char *perf_header__find_event(u64 id)
         return NULL;
 }
 
-static const char *__perf_magic = "PERFFILE";
+/*
+ * 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.
+ */
+static const char *__perf_magic1 = "PERFFILE";
+static const u64 __perf_magic2    = 0x32454c4946524550ULL;
+static const u64 __perf_magic2_sw = 0x50455246494c4532ULL;
 
-#define PERF_MAGIC      (*(u64 *)__perf_magic)
+#define PERF_MAGIC      __perf_magic2
 
 struct perf_file_attr {
         struct perf_event_attr  attr;
@@ -1012,6 +1023,12 @@ write_it:
         return do_write_string(fd, buffer);
 }
 
+static int write_branch_stack(int fd __used, struct perf_header *h __used,
+                       struct perf_evlist *evlist __used)
+{
+        return 0;
+}
+
 static void print_hostname(struct perf_header *ph, int fd, FILE *fp)
 {
         char *str = do_read_string(fd, ph);
@@ -1133,8 +1150,9 @@ static void print_event_desc(struct perf_header *ph, int fd, FILE *fp)
         uint64_t id;
         void *buf = NULL;
         char *str;
-        u32 nre, sz, nr, i, j, msz;
-        int ret;
+        u32 nre, sz, nr, i, j;
+        ssize_t ret;
+        size_t msz;
 
         /* number of events */
         ret = read(fd, &nre, sizeof(nre));
@@ -1151,25 +1169,23 @@ static void print_event_desc(struct perf_header *ph, int fd, FILE *fp)
         if (ph->needs_swap)
                 sz = bswap_32(sz);
 
-        /*
-         * ensure it is at least to our ABI rev
-         */
-        if (sz < (u32)sizeof(attr))
-                goto error;
-
         memset(&attr, 0, sizeof(attr));
 
-        /* read entire region to sync up to next field */
+        /* buffer to hold on file attr struct */
         buf = malloc(sz);
         if (!buf)
                 goto error;
 
         msz = sizeof(attr);
-        if (sz < msz)
+        if (sz < (ssize_t)msz)
                 msz = sz;
 
         for (i = 0 ; i < nre; i++) {
 
+                /*
+                 * must read entire on-file attr struct to
+                 * sync up with layout.
+                 */
                 ret = read(fd, buf, sz);
                 if (ret != (ssize_t)sz)
                         goto error;
@@ -1305,25 +1321,204 @@ static void print_cpuid(struct perf_header *ph, int fd, FILE *fp)
         free(str);
 }
 
+static void print_branch_stack(struct perf_header *ph __used, int fd __used,
+                               FILE *fp)
+{
+        fprintf(fp, "# contains samples with branch stack\n");
+}
+
+static int __event_process_build_id(struct build_id_event *bev,
+                                    char *filename,
+                                    struct perf_session *session)
+{
+        int err = -1;
+        struct list_head *head;
+        struct machine *machine;
+        u16 misc;
+        struct dso *dso;
+        enum dso_kernel_type dso_type;
+
+        machine = perf_session__findnew_machine(session, bev->pid);
+        if (!machine)
+                goto out;
+
+        misc = bev->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+
+        switch (misc) {
+        case PERF_RECORD_MISC_KERNEL:
+                dso_type = DSO_TYPE_KERNEL;
+                head = &machine->kernel_dsos;
+                break;
+        case PERF_RECORD_MISC_GUEST_KERNEL:
+                dso_type = DSO_TYPE_GUEST_KERNEL;
+                head = &machine->kernel_dsos;
+                break;
+        case PERF_RECORD_MISC_USER:
+        case PERF_RECORD_MISC_GUEST_USER:
+                dso_type = DSO_TYPE_USER;
+                head = &machine->user_dsos;
+                break;
+        default:
+                goto out;
+        }
+
+        dso = __dsos__findnew(head, filename);
+        if (dso != NULL) {
+                char sbuild_id[BUILD_ID_SIZE * 2 + 1];
+
+                dso__set_build_id(dso, &bev->build_id);
+
+                if (filename[0] == '[')
+                        dso->kernel = dso_type;
+
+                build_id__sprintf(dso->build_id, sizeof(dso->build_id),
+                                  sbuild_id);
+                pr_debug("build id event received for %s: %s\n",
+                         dso->long_name, sbuild_id);
+        }
+
+        err = 0;
+out:
+        return err;
+}
+
+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(header, struct perf_session, header);
+        struct {
+                struct perf_event_header   header;
+                u8                         build_id[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 (read(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 (read(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))
+                        goto out;
+
+                if (header->needs_swap)
+                        perf_event_header__bswap(&bev.header);
+
+                len = bev.header.size - sizeof(bev);
+                if (read(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);
+
+                offset += bev.header.size;
+        }
+        err = 0;
+out:
+        return err;
+}
+
+static int process_trace_info(struct perf_file_section *section __unused,
+                              struct perf_header *ph __unused,
+                              int feat __unused, int fd)
+{
+        trace_report(fd, false);
+        return 0;
+}
+
+static int process_build_id(struct perf_file_section *section,
+                            struct perf_header *ph,
+                            int feat __unused, int fd)
+{
+        if (perf_header__read_build_ids(ph, fd, section->offset, section->size))
+                pr_debug("Failed to read buildids, continuing...\n");
+        return 0;
+}
+
 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 feat, int fd);
         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, .full_only = true }
+        [n] = { .name = #n, .write = write_##func, .print = print_##func, \
+                .full_only = true }
 
 /* feature_ops not implemented: */
 #define print_trace_info                NULL
 #define print_build_id                  NULL
 
 static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
-        FEAT_OPA(HEADER_TRACE_INFO,     trace_info),
-        FEAT_OPA(HEADER_BUILD_ID,       build_id),
+        FEAT_OPP(HEADER_TRACE_INFO,     trace_info),
+        FEAT_OPP(HEADER_BUILD_ID,       build_id),
         FEAT_OPA(HEADER_HOSTNAME,       hostname),
         FEAT_OPA(HEADER_OSRELEASE,      osrelease),
         FEAT_OPA(HEADER_VERSION,        version),
@@ -1336,6 +1531,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
         FEAT_OPA(HEADER_CMDLINE,        cmdline),
         FEAT_OPF(HEADER_CPU_TOPOLOGY,   cpu_topology),
         FEAT_OPF(HEADER_NUMA_TOPOLOGY,  numa_topology),
+        FEAT_OPA(HEADER_BRANCH_STACK,   branch_stack),
 };
 
 struct header_print_data {
@@ -1620,24 +1816,128 @@ out_free:
         return err;
 }
 
+static const int attr_file_abi_sizes[] = {
+        [0] = PERF_ATTR_SIZE_VER0,
+        [1] = PERF_ATTR_SIZE_VER1,
+        0,
+};
+
+/*
+ * 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;
+}
+
+#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;
+}
+
+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) {
+                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);
+        }
+        /*
+         * the new magic number serves two purposes:
+         * - unique number to identify actual perf.data files
+         * - encode endianness of file
+         */
+
+        /* check magic number with one endianness */
+        if (magic == __perf_magic2)
+                return 0;
+
+        /* check magic number with opposite endianness */
+        if (magic != __perf_magic2_sw)
+                return -1;
+
+        ph->needs_swap = true;
+
+        return 0;
+}
+
 int perf_file_header__read(struct perf_file_header *header,
                            struct perf_header *ph, int fd)
 {
+        int ret;
+
         lseek(fd, 0, SEEK_SET);
 
-        if (readn(fd, header, sizeof(*header)) <= 0 ||
-            memcmp(&header->magic, __perf_magic, sizeof(header->magic)))
+        ret = readn(fd, header, sizeof(*header));
+        if (ret <= 0)
                 return -1;
 
-        if (header->attr_size != sizeof(struct perf_file_attr)) {
-                u64 attr_size = bswap_64(header->attr_size);
-
-                if (attr_size != sizeof(struct perf_file_attr))
-                        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));
-                ph->needs_swap = true;
+                             adds_features));
         }
 
         if (header->size != sizeof(*header)) {
@@ -1689,156 +1989,6 @@ int perf_file_header__read(struct perf_file_header *header,
         return 0;
 }
 
-static int __event_process_build_id(struct build_id_event *bev,
-                                    char *filename,
-                                    struct perf_session *session)
-{
-        int err = -1;
-        struct list_head *head;
-        struct machine *machine;
-        u16 misc;
-        struct dso *dso;
-        enum dso_kernel_type dso_type;
-
-        machine = perf_session__findnew_machine(session, bev->pid);
-        if (!machine)
-                goto out;
-
-        misc = bev->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
-
-        switch (misc) {
-        case PERF_RECORD_MISC_KERNEL:
-                dso_type = DSO_TYPE_KERNEL;
-                head = &machine->kernel_dsos;
-                break;
-        case PERF_RECORD_MISC_GUEST_KERNEL:
-                dso_type = DSO_TYPE_GUEST_KERNEL;
-                head = &machine->kernel_dsos;
-                break;
-        case PERF_RECORD_MISC_USER:
-        case PERF_RECORD_MISC_GUEST_USER:
-                dso_type = DSO_TYPE_USER;
-                head = &machine->user_dsos;
-                break;
-        default:
-                goto out;
-        }
-
-        dso = __dsos__findnew(head, filename);
-        if (dso != NULL) {
-                char sbuild_id[BUILD_ID_SIZE * 2 + 1];
-
-                dso__set_build_id(dso, &bev->build_id);
-
-                if (filename[0] == '[')
-                        dso->kernel = dso_type;
-
-                build_id__sprintf(dso->build_id, sizeof(dso->build_id),
-                                  sbuild_id);
-                pr_debug("build id event received for %s: %s\n",
-                         dso->long_name, sbuild_id);
-        }
-
-        err = 0;
-out:
-        return err;
-}
-
-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(header, struct perf_session, header);
-        struct {
-                struct perf_event_header   header;
-                u8                         build_id[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 (read(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 (read(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))
-                        goto out;
-
-                if (header->needs_swap)
-                        perf_event_header__bswap(&bev.header);
-
-                len = bev.header.size - sizeof(bev);
-                if (read(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);
-
-                offset += bev.header.size;
-        }
-        err = 0;
-out:
-        return err;
-}
-
 static int perf_file_section__process(struct perf_file_section *section,
                                       struct perf_header *ph,
                                       int feat, int fd, void *data __used)
@@ -1854,40 +2004,32 @@ static int perf_file_section__process(struct perf_file_section *section,
                 return 0;
         }
 
-        switch (feat) {
-        case HEADER_TRACE_INFO:
-                trace_report(fd, false);
-                break;
-        case HEADER_BUILD_ID:
-                if (perf_header__read_build_ids(ph, fd, section->offset, section->size))
-                        pr_debug("Failed to read buildids, continuing...\n");
-                break;
-        default:
-                break;
-        }
+        if (!feat_ops[feat].process)
+                return 0;
 
-        return 0;
+        return feat_ops[feat].process(section, ph, feat, fd);
 }
 
 static int perf_file_header__read_pipe(struct perf_pipe_file_header *header,
                                        struct perf_header *ph, int fd,
                                        bool repipe)
 {
-        if (readn(fd, header, sizeof(*header)) <= 0 ||
-            memcmp(&header->magic, __perf_magic, sizeof(header->magic)))
-                return -1;
+        int ret;
 
-        if (repipe && do_write(STDOUT_FILENO, header, sizeof(*header)) < 0)
+        ret = readn(fd, header, sizeof(*header));
+        if (ret <= 0)
                 return -1;
 
-        if (header->size != sizeof(*header)) {
-                u64 size = bswap_64(header->size);
+        if (check_magic_endian(header->magic, header->size, true, ph) < 0) {
+                pr_debug("endian/magic failed\n");
+                return -1;
+        }
 
-                if (size != sizeof(*header))
-                        return -1;
+        if (ph->needs_swap)
+                header->size = bswap_64(header->size);
 
-                ph->needs_swap = true;
-        }
+        if (repipe && do_write(STDOUT_FILENO, header, sizeof(*header)) < 0)
+                return -1;
 
         return 0;
 }
@@ -1908,6 +2050,52 @@ static int perf_header__read_pipe(struct perf_session *session, int fd)
         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);
+        int 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;
+        }
+
+        /* 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 perf_session__read_header(struct perf_session *session, int fd)
 {
         struct perf_header *header = &session->header;
@@ -1923,19 +2111,17 @@ int perf_session__read_header(struct perf_session *session, int fd)
         if (session->fd_pipe)
                 return perf_header__read_pipe(session, fd);
 
-        if (perf_file_header__read(&f_header, header, fd) < 0) {
-                pr_debug("incompatible file format\n");
+        if (perf_file_header__read(&f_header, header, fd) < 0)
                 return -EINVAL;
-        }
 
-        nr_attrs = f_header.attrs.size / sizeof(f_attr);
+        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 (readn(fd, &f_attr, sizeof(f_attr)) <= 0)
+                if (read_attr(fd, header, &f_attr) < 0)
                         goto out_errno;
 
                 if (header->needs_swap)
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index ac4ec956024e..21a6be09c129 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -11,6 +11,7 @@
 
 enum {
         HEADER_RESERVED         = 0,    /* always cleared */
+        HEADER_FIRST_FEATURE    = 1,
         HEADER_TRACE_INFO       = 1,
         HEADER_BUILD_ID,
 
@@ -26,7 +27,7 @@ enum {
         HEADER_EVENT_DESC,
         HEADER_CPU_TOPOLOGY,
         HEADER_NUMA_TOPOLOGY,
-
+        HEADER_BRANCH_STACK,
         HEADER_LAST_FEATURE,
         HEADER_FEAT_BITS        = 256,
 };
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index e11e482bd185..3dc99a9b71f5 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -50,21 +50,25 @@ static void hists__reset_col_len(struct hists *hists)
                 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);
+}
+
 static void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 {
+        const unsigned int unresolved_col_width = BITS_PER_LONG / 4;
         u16 len;
 
         if (h->ms.sym)
-                hists__new_col_len(hists, HISTC_SYMBOL, h->ms.sym->namelen);
-        else {
-                const unsigned int unresolved_col_width = BITS_PER_LONG / 4;
-
-                if (hists__col_len(hists, HISTC_DSO) < unresolved_col_width &&
-                    !symbol_conf.col_width_list_str && !symbol_conf.field_sep &&
-                    !symbol_conf.dso_list)
-                        hists__set_col_len(hists, HISTC_DSO,
-                                           unresolved_col_width);
-        }
+                hists__new_col_len(hists, HISTC_SYMBOL, h->ms.sym->namelen + 4);
+        else
+                hists__set_unres_dso_col_len(hists, HISTC_DSO);
 
         len = thread__comm_len(h->thread);
         if (hists__new_col_len(hists, HISTC_COMM, len))
@@ -74,6 +78,37 @@ static void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
                 len = dso__name_len(h->ms.map->dso);
                 hists__new_col_len(hists, HISTC_DSO, len);
         }
+
+        if (h->branch_info) {
+                int symlen;
+                /*
+                 * +4 accounts for '[x] ' priv level info
+                 * +2 account of 0x prefix on raw addresses
+                 */
+                if (h->branch_info->from.sym) {
+                        symlen = (int)h->branch_info->from.sym->namelen + 4;
+                        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;
+                        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);
+                }
+        }
 }
 
 static void hist_entry__add_cpumode_period(struct hist_entry *he,
@@ -195,26 +230,14 @@ static u8 symbol__parent_filter(const struct symbol *parent)
         return 0;
 }
 
-struct hist_entry *__hists__add_entry(struct hists *hists,
+static struct hist_entry *add_hist_entry(struct hists *hists,
+                                      struct hist_entry *entry,
                                       struct addr_location *al,
-                                      struct symbol *sym_parent, u64 period)
+                                      u64 period)
 {
         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,
-                },
-                .cpu    = al->cpu,
-                .ip     = al->addr,
-                .level  = al->level,
-                .period = period,
-                .parent = sym_parent,
-                .filtered = symbol__parent_filter(sym_parent),
-        };
         int cmp;
 
         pthread_mutex_lock(&hists->lock);
@@ -225,7 +248,7 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
                 parent = *p;
                 he = rb_entry(parent, struct hist_entry, rb_node_in);
 
-                cmp = hist_entry__cmp(&entry, he);
+                cmp = hist_entry__cmp(entry, he);
 
                 if (!cmp) {
                         he->period += period;
@@ -239,7 +262,7 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
                         p = &(*p)->rb_right;
         }
 
-        he = hist_entry__new(&entry);
+        he = hist_entry__new(entry);
         if (!he)
                 goto out_unlock;
 
@@ -252,6 +275,51 @@ out_unlock:
         return he;
 }
 
+struct hist_entry *__hists__add_branch_entry(struct hists *self,
+                                             struct addr_location *al,
+                                             struct symbol *sym_parent,
+                                             struct branch_info *bi,
+                                             u64 period)
+{
+        struct hist_entry entry = {
+                .thread = al->thread,
+                .ms = {
+                        .map    = bi->to.map,
+                        .sym    = bi->to.sym,
+                },
+                .cpu    = al->cpu,
+                .ip     = bi->to.addr,
+                .level  = al->level,
+                .period = period,
+                .parent = sym_parent,
+                .filtered = symbol__parent_filter(sym_parent),
+                .branch_info = bi,
+        };
+
+        return add_hist_entry(self, &entry, al, period);
+}
+
+struct hist_entry *__hists__add_entry(struct hists *self,
+                                      struct addr_location *al,
+                                      struct symbol *sym_parent, u64 period)
+{
+        struct hist_entry entry = {
+                .thread = al->thread,
+                .ms = {
+                        .map    = al->map,
+                        .sym    = al->sym,
+                },
+                .cpu    = al->cpu,
+                .ip     = al->addr,
+                .level  = al->level,
+                .period = period,
+                .parent = sym_parent,
+                .filtered = symbol__parent_filter(sym_parent),
+        };
+
+        return add_hist_entry(self, &entry, al, period);
+}
+
 int64_t
 hist_entry__cmp(struct hist_entry *left, struct hist_entry *right)
 {
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index f55f0a8d1f81..9413f3e31fea 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -32,6 +32,7 @@ struct events_stats {
         u32 nr_unknown_events;
         u32 nr_invalid_chains;
         u32 nr_unknown_id;
+        u32 nr_unprocessable_samples;
 };
 
 enum hist_column {
@@ -41,6 +42,11 @@ enum hist_column {
         HISTC_COMM,
         HISTC_PARENT,
         HISTC_CPU,
+        HISTC_MISPREDICT,
+        HISTC_SYMBOL_FROM,
+        HISTC_SYMBOL_TO,
+        HISTC_DSO_FROM,
+        HISTC_DSO_TO,
         HISTC_NR_COLS, /* Last entry */
 };
 
@@ -55,6 +61,7 @@ struct hists {
         u64                     nr_entries;
         const struct thread     *thread_filter;
         const struct dso        *dso_filter;
+        const char              *uid_filter_str;
         pthread_mutex_t         lock;
         struct events_stats     stats;
         u64                     event_stream;
@@ -72,6 +79,12 @@ int hist_entry__snprintf(struct hist_entry *self, char *bf, size_t size,
                          struct hists *hists);
 void hist_entry__free(struct hist_entry *);
 
+struct hist_entry *__hists__add_branch_entry(struct hists *self,
+                                             struct addr_location *al,
+                                             struct symbol *sym_parent,
+                                             struct branch_info *bi,
+                                             u64 period);
+
 void hists__output_resort(struct hists *self);
 void hists__output_resort_threaded(struct hists *hists);
 void hists__collapse_resort(struct hists *self);
diff --git a/tools/perf/util/include/asm/dwarf2.h b/tools/perf/util/include/asm/dwarf2.h
index bb4198e7837a..afe38199e922 100644
--- a/tools/perf/util/include/asm/dwarf2.h
+++ b/tools/perf/util/include/asm/dwarf2.h
@@ -2,10 +2,12 @@
 #ifndef PERF_DWARF2_H
 #define PERF_DWARF2_H
 
-/* dwarf2.h ... dummy header file for including arch/x86/lib/memcpy_64.S */
+/* 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/linux/bitmap.h b/tools/perf/util/include/linux/bitmap.h
index eda4416efa0a..bb162e40c76c 100644
--- a/tools/perf/util/include/linux/bitmap.h
+++ b/tools/perf/util/include/linux/bitmap.h
@@ -5,6 +5,8 @@
 #include <linux/bitops.h>
 
 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 +34,13 @@ 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/map.c b/tools/perf/util/map.c
index 316aa0ab7122..dea6d1c1a954 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -212,6 +212,21 @@ size_t map__fprintf(struct map *self, FILE *fp)
                        self->start, self->end, self->pgoff, self->dso->name);
 }
 
+size_t map__fprintf_dsoname(struct map *map, FILE *fp)
+{
+        const char *dsoname;
+
+        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;
+        } else
+                dsoname = "[unknown]";
+
+        return fprintf(fp, "%s", dsoname);
+}
+
 /*
  * objdump wants/reports absolute IPs for ET_EXEC, and RIPs for ET_DYN.
  * map->dso->adjust_symbols==1 for ET_EXEC-like cases.
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 2b8017f8a930..b100c20b7f94 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -118,6 +118,7 @@ void map__delete(struct map *self);
 struct map *map__clone(struct map *self);
 int map__overlap(struct map *l, struct map *r);
 size_t map__fprintf(struct map *self, FILE *fp);
+size_t map__fprintf_dsoname(struct map *map, FILE *fp);
 
 int map__load(struct map *self, symbol_filter_t filter);
 struct symbol *map__find_symbol(struct map *self,
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index e33554a562b3..8a8ee64e72d1 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -34,7 +34,6 @@
 
 #include "util.h"
 #include "event.h"
-#include "string.h"
 #include "strlist.h"
 #include "debug.h"
 #include "cache.h"
@@ -273,10 +272,10 @@ static int add_module_to_probe_trace_events(struct probe_trace_event *tevs,
 /* Try to find perf_probe_event with debuginfo */
 static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
                                           struct probe_trace_event **tevs,
-                                          int max_tevs, const char *module)
+                                          int max_tevs, const char *target)
 {
         bool need_dwarf = perf_probe_event_need_dwarf(pev);
-        struct debuginfo *dinfo = open_debuginfo(module);
+        struct debuginfo *dinfo = open_debuginfo(target);
         int ntevs, ret = 0;
 
         if (!dinfo) {
@@ -295,9 +294,9 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
 
         if (ntevs > 0) {        /* Succeeded to find trace events */
                 pr_debug("find %d probe_trace_events.\n", ntevs);
-                if (module)
+                if (target)
                         ret = add_module_to_probe_trace_events(*tevs, ntevs,
-                                                               module);
+                                                               target);
                 return ret < 0 ? ret : ntevs;
         }
 
@@ -1729,7 +1728,7 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
         }
 
         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)
@@ -1784,7 +1783,7 @@ static int __add_probe_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);
         }
@@ -1796,14 +1795,14 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
 
 static int convert_to_probe_trace_events(struct perf_probe_event *pev,
                                           struct probe_trace_event **tevs,
-                                          int max_tevs, const char *module)
+                                          int max_tevs, const char *target)
 {
         struct symbol *sym;
         int ret = 0, i;
         struct probe_trace_event *tev;
 
         /* Convert perf_probe_event with debuginfo */
-        ret = try_to_find_probe_trace_events(pev, tevs, max_tevs, module);
+        ret = try_to_find_probe_trace_events(pev, tevs, max_tevs, target);
         if (ret != 0)
                 return ret;     /* Found in debuginfo or got an error */
 
@@ -1819,8 +1818,8 @@ static int convert_to_probe_trace_events(struct perf_probe_event *pev,
                 goto error;
         }
 
-        if (module) {
-                tev->point.module = strdup(module);
+        if (target) {
+                tev->point.module = strdup(target);
                 if (tev->point.module == NULL) {
                         ret = -ENOMEM;
                         goto error;
@@ -1890,7 +1889,7 @@ struct __event_package {
 };
 
 int add_perf_probe_events(struct perf_probe_event *pevs, int npevs,
-                          int max_tevs, const char *module, bool force_add)
+                          int max_tevs, const char *target, bool force_add)
 {
         int i, j, ret;
         struct __event_package *pkgs;
@@ -1913,7 +1912,7 @@ int add_perf_probe_events(struct perf_probe_event *pevs, int npevs,
                 ret  = convert_to_probe_trace_events(pkgs[i].pev,
                                                      &pkgs[i].tevs,
                                                      max_tevs,
-                                                     module);
+                                                     target);
                 if (ret < 0)
                         goto end;
                 pkgs[i].ntevs = ret;
@@ -1965,7 +1964,7 @@ static int __del_trace_probe_event(int fd, struct str_node *ent)
                 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));
@@ -2069,7 +2068,7 @@ static int filter_available_functions(struct map *map __unused,
         return 1;
 }
 
-int show_available_funcs(const char *module, struct strfilter *_filter)
+int show_available_funcs(const char *target, struct strfilter *_filter)
 {
         struct map *map;
         int ret;
@@ -2080,9 +2079,9 @@ int show_available_funcs(const char *module, struct strfilter *_filter)
         if (ret < 0)
                 return ret;
 
-        map = kernel_get_module_map(module);
+        map = kernel_get_module_map(target);
         if (!map) {
-                pr_err("Failed to find %s map.\n", (module) ? : "kernel");
+                pr_err("Failed to find %s map.\n", (target) ? : "kernel");
                 return -EINVAL;
         }
         available_func_filter = _filter;
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 74bd2e63c4b4..2cc162d3b78c 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -30,7 +30,6 @@
 #include <stdlib.h>
 #include <string.h>
 #include <stdarg.h>
-#include <ctype.h>
 #include <dwarf-regs.h>
 
 #include <linux/bitops.h>
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
new file mode 100644
index 000000000000..2884e67ee625
--- /dev/null
+++ b/tools/perf/util/python-ext-sources
@@ -0,0 +1,19 @@
+#
+# List of files needed by perf python extention
+#
+# 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/thread_map.c
+util/util.c
+util/xyarray.c
+util/cgroup.c
+util/debugfs.c
+util/strlist.c
+../../lib/rbtree.c
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 9dd47a4f2596..e03b58a48424 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -425,14 +425,14 @@ struct pyrf_thread_map {
 static int pyrf_thread_map__init(struct pyrf_thread_map *pthreads,
                                  PyObject *args, PyObject *kwargs)
 {
-        static char *kwlist[] = { "pid", "tid", NULL };
-        int pid = -1, tid = -1;
+        static char *kwlist[] = { "pid", "tid", "uid", NULL };
+        int pid = -1, tid = -1, uid = UINT_MAX;
 
-        if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|ii",
-                                         kwlist, &pid, &tid))
+        if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|iii",
+                                         kwlist, &pid, &tid, &uid))
                 return -1;
 
-        pthreads->threads = thread_map__new(pid, tid);
+        pthreads->threads = thread_map__new(pid, tid, uid);
         if (pthreads->threads == NULL)
                 return -1;
         return 0;
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 0b2a48783172..c2623c6f9b51 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -24,7 +24,6 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
-#include <ctype.h>
 #include <errno.h>
 
 #include "../../perf.h"
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index b5ca2558c7bb..002ebbf59f48 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -24,7 +24,7 @@ static int perf_session__open(struct perf_session *self, bool force)
                 self->fd = STDIN_FILENO;
 
                 if (perf_session__read_header(self, self->fd) < 0)
-                        pr_err("incompatible file format");
+                        pr_err("incompatible file format (rerun with -v to learn more)");
 
                 return 0;
         }
@@ -56,7 +56,7 @@ static int perf_session__open(struct perf_session *self, bool force)
         }
 
         if (perf_session__read_header(self, self->fd) < 0) {
-                pr_err("incompatible file format");
+                pr_err("incompatible file format (rerun with -v to learn more)");
                 goto out_close;
         }
 
@@ -229,6 +229,64 @@ static bool symbol__match_parent_regex(struct symbol *sym)
         return 0;
 }
 
+static const u8 cpumodes[] = {
+        PERF_RECORD_MISC_USER,
+        PERF_RECORD_MISC_KERNEL,
+        PERF_RECORD_MISC_GUEST_USER,
+        PERF_RECORD_MISC_GUEST_KERNEL
+};
+#define NCPUMODES (sizeof(cpumodes)/sizeof(u8))
+
+static void ip__resolve_ams(struct machine *self, struct thread *thread,
+                            struct addr_map_symbol *ams,
+                            u64 ip)
+{
+        struct addr_location al;
+        size_t i;
+        u8 m;
+
+        memset(&al, 0, sizeof(al));
+
+        for (i = 0; i < NCPUMODES; i++) {
+                m = cpumodes[i];
+                /*
+                 * 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_addr_location(thread, self, m, MAP__FUNCTION,
+                                ip, &al, NULL);
+                if (al.sym)
+                        goto found;
+        }
+found:
+        ams->addr = ip;
+        ams->al_addr = al.addr;
+        ams->sym = al.sym;
+        ams->map = al.map;
+}
+
+struct branch_info *machine__resolve_bstack(struct machine *self,
+                                            struct thread *thr,
+                                            struct branch_stack *bs)
+{
+        struct branch_info *bi;
+        unsigned int i;
+
+        bi = calloc(bs->nr, sizeof(struct branch_info));
+        if (!bi)
+                return NULL;
+
+        for (i = 0; i < bs->nr; i++) {
+                ip__resolve_ams(self, thr, &bi[i].to, bs->entries[i].to);
+                ip__resolve_ams(self, thr, &bi[i].from, bs->entries[i].from);
+                bi[i].flags = bs->entries[i].flags;
+        }
+        return bi;
+}
+
 int machine__resolve_callchain(struct machine *self, struct perf_evsel *evsel,
                                struct thread *thread,
                                struct ip_callchain *chain,
@@ -697,6 +755,18 @@ static void callchain__printf(struct perf_sample *sample)
                        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 perf_session__print_tstamp(struct perf_session *session,
                                        union perf_event *event,
                                        struct perf_sample *sample)
@@ -744,6 +814,9 @@ static void dump_sample(struct perf_session *session, union perf_event *event,
 
         if (session->sample_type & PERF_SAMPLE_CALLCHAIN)
                 callchain__printf(sample);
+
+        if (session->sample_type & PERF_SAMPLE_BRANCH_STACK)
+                branch_stack__printf(sample);
 }
 
 static struct machine *
@@ -796,6 +869,10 @@ static int perf_session_deliver_event(struct perf_session *session,
                         ++session->hists.stats.nr_unknown_id;
                         return -1;
                 }
+                if (machine == NULL) {
+                        ++session->hists.stats.nr_unprocessable_samples;
+                        return -1;
+                }
                 return tool->sample(tool, event, sample, evsel, machine);
         case PERF_RECORD_MMAP:
                 return tool->mmap(tool, event, sample, machine);
@@ -964,6 +1041,12 @@ static void perf_session__warn_about_errors(const struct perf_session *session,
                             session->hists.stats.nr_invalid_chains,
                             session->hists.stats.nr_events[PERF_RECORD_SAMPLE]);
         }
+
+        if (session->hists.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->hists.stats.nr_unprocessable_samples);
+        }
 }
 
 #define session_done()  (*(volatile int *)(&session_done))
@@ -1293,10 +1376,9 @@ struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
 
 void perf_event__print_ip(union perf_event *event, struct perf_sample *sample,
                           struct machine *machine, struct perf_evsel *evsel,
-                          int print_sym, int print_dso)
+                          int print_sym, int print_dso, int print_symoffset)
 {
         struct addr_location al;
-        const char *symname, *dsoname;
         struct callchain_cursor *cursor = &evsel->hists.callchain_cursor;
         struct callchain_cursor_node *node;
 
@@ -1324,20 +1406,13 @@ void perf_event__print_ip(union perf_event *event, struct perf_sample *sample,
 
                         printf("\t%16" PRIx64, node->ip);
                         if (print_sym) {
-                                if (node->sym && node->sym->name)
-                                        symname = node->sym->name;
-                                else
-                                        symname = "";
-
-                                printf(" %s", symname);
+                                printf(" ");
+                                symbol__fprintf_symname(node->sym, stdout);
                         }
                         if (print_dso) {
-                                if (node->map && node->map->dso && node->map->dso->name)
-                                        dsoname = node->map->dso->name;
-                                else
-                                        dsoname = "";
-
-                                printf(" (%s)", dsoname);
+                                printf(" (");
+                                map__fprintf_dsoname(al.map, stdout);
+                                printf(")");
                         }
                         printf("\n");
 
@@ -1347,21 +1422,18 @@ void perf_event__print_ip(union perf_event *event, struct perf_sample *sample,
         } else {
                 printf("%16" PRIx64, sample->ip);
                 if (print_sym) {
-                        if (al.sym && al.sym->name)
-                                symname = al.sym->name;
+                        printf(" ");
+                        if (print_symoffset)
+                                symbol__fprintf_symname_offs(al.sym, &al,
+                                                             stdout);
                         else
-                                symname = "";
-
-                        printf(" %s", symname);
+                                symbol__fprintf_symname(al.sym, stdout);
                 }
 
                 if (print_dso) {
-                        if (al.map && al.map->dso && al.map->dso->name)
-                                dsoname = al.map->dso->name;
-                        else
-                                dsoname = "";
-
-                        printf(" (%s)", dsoname);
+                        printf(" (");
+                        map__fprintf_dsoname(al.map, stdout);
+                        printf(")");
                 }
         }
 }
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 37bc38381fb6..7a5434c00565 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -73,6 +73,10 @@ int perf_session__resolve_callchain(struct perf_session *self, struct perf_evsel
                                     struct ip_callchain *chain,
                                     struct symbol **parent);
 
+struct branch_info *machine__resolve_bstack(struct machine *self,
+                                            struct thread *thread,
+                                            struct branch_stack *bs);
+
 bool perf_session__has_traces(struct perf_session *self, const char *msg);
 
 void mem_bswap_64(void *src, int byte_size);
@@ -147,7 +151,7 @@ struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
 
 void perf_event__print_ip(union perf_event *event, struct perf_sample *sample,
                           struct machine *machine, struct perf_evsel *evsel,
-                          int print_sym, int print_dso);
+                          int print_sym, int print_dso, int print_symoffset);
 
 int perf_session__cpu_bitmap(struct perf_session *session,
                              const char *cpu_list, unsigned long *cpu_bitmap);
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index 36d4c5619575..d0f9f29cf181 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -24,11 +24,11 @@ cflags += getenv('CFLAGS', '').split()
 build_lib = getenv('PYTHON_EXTBUILD_LIB')
 build_tmp = getenv('PYTHON_EXTBUILD_TMP')
 
+ext_sources = [f.strip() for f in file('util/python-ext-sources')
+                                if len(f.strip()) > 0 and f[0] != '#']
+
 perf = Extension('perf',
-                  sources = ['util/python.c', 'util/ctype.c', 'util/evlist.c',
-                             'util/evsel.c', 'util/cpumap.c', 'util/thread_map.c',
-                             'util/util.c', 'util/xyarray.c', 'util/cgroup.c',
-                             'util/debugfs.c'],
+                  sources = ext_sources,
                   include_dirs = ['util/include'],
                   extra_compile_args = cflags,
                  )
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 076c9d4e1ea4..a27237430c5f 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -8,6 +8,7 @@ const char	default_sort_order[] = "comm,dso,symbol";
 const char      *sort_order = default_sort_order;
 int             sort__need_collapse = 0;
 int             sort__has_parent = 0;
+int             sort__branch_mode = -1; /* -1 = means not set */
 
 enum sort_type  sort__first_dimension;
 
@@ -97,6 +98,26 @@ static int hist_entry__comm_snprintf(struct hist_entry *self, char *bf,
         return repsep_snprintf(bf, size, "%*s", width, self->thread->comm);
 }
 
+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_l, dso_r);
+
+        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);
+}
+
 struct sort_entry sort_comm = {
         .se_header      = "Command",
         .se_cmp         = sort__comm_cmp,
@@ -110,36 +131,74 @@ struct sort_entry sort_comm = {
 static int64_t
 sort__dso_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-        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;
+        return _sort__dso_cmp(left->ms.map, right->ms.map);
+}
 
-        if (!dso_l || !dso_r)
-                return cmp_null(dso_l, dso_r);
 
-        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;
+static int64_t _sort__sym_cmp(struct symbol *sym_l, struct symbol *sym_r,
+                              u64 ip_l, u64 ip_r)
+{
+        if (!sym_l || !sym_r)
+                return cmp_null(sym_l, sym_r);
+
+        if (sym_l == sym_r)
+                return 0;
+
+        if (sym_l)
+                ip_l = sym_l->start;
+        if (sym_r)
+                ip_r = sym_r->start;
+
+        return (int64_t)(ip_r - ip_l);
+}
+
+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 strcmp(dso_name_l, dso_name_r);
+        return repsep_snprintf(bf, size, "%-*s", width, "[unknown]");
 }
 
 static int hist_entry__dso_snprintf(struct hist_entry *self, 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 _hist_entry__dso_snprintf(self->ms.map, bf, size, width);
+}
+
+static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym,
+                                     u64 ip, char level, char *bf, size_t size,
+                                     unsigned int width __used)
+{
+        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, ip, o);
         }
 
-        return repsep_snprintf(bf, size, "%-*s", width, "[unknown]");
+        ret += repsep_snprintf(bf + ret, size - ret, "[%c] ", level);
+        if (sym)
+                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;
 }
 
+
 struct sort_entry sort_dso = {
         .se_header      = "Shared Object",
         .se_cmp         = sort__dso_cmp,
@@ -147,8 +206,14 @@ struct sort_entry sort_dso = {
         .se_width_idx   = HISTC_DSO,
 };
 
-/* --sort symbol */
+static int hist_entry__sym_snprintf(struct hist_entry *self, char *bf,
+                                    size_t size, unsigned int width __used)
+{
+        return _hist_entry__sym_snprintf(self->ms.map, self->ms.sym, self->ip,
+                                         self->level, bf, size, width);
+}
 
+/* --sort symbol */
 static int64_t
 sort__sym_cmp(struct hist_entry *left, struct hist_entry *right)
 {
@@ -166,31 +231,7 @@ sort__sym_cmp(struct hist_entry *left, struct hist_entry *right)
         ip_l = left->ms.sym->start;
         ip_r = right->ms.sym->start;
 
-        return (int64_t)(ip_r - ip_l);
-}
-
-static int hist_entry__sym_snprintf(struct hist_entry *self, char *bf,
-                                    size_t size, unsigned int width __used)
-{
-        size_t ret = 0;
-
-        if (verbose) {
-                char o = self->ms.map ? dso__symtab_origin(self->ms.map->dso) : '!';
-                ret += repsep_snprintf(bf, size, "%-#*llx %c ",
-                                       BITS_PER_LONG / 4, self->ip, o);
-        }
-
-        if (!sort_dso.elide)
-                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, "%-#*llx",
-                                       BITS_PER_LONG / 4, self->ip);
-
-        return ret;
+        return _sort__sym_cmp(left->ms.sym, right->ms.sym, ip_l, ip_r);
 }
 
 struct sort_entry sort_sym = {
@@ -249,19 +290,155 @@ struct sort_entry sort_cpu = {
         .se_width_idx   = HISTC_CPU,
 };
 
+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 *self, char *bf,
+                                    size_t size, unsigned int width)
+{
+        return _hist_entry__dso_snprintf(self->branch_info->from.map,
+                                         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,
+};
+
+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 *self, char *bf,
+                                       size_t size, unsigned int width)
+{
+        return _hist_entry__dso_snprintf(self->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 right->level - left->level;
+
+        return _sort__sym_cmp(from_l->sym, from_r->sym, from_l->addr,
+                             from_r->addr);
+}
+
+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 right->level - left->level;
+
+        return _sort__sym_cmp(to_l->sym, to_r->sym, to_l->addr, to_r->addr);
+}
+
+static int hist_entry__sym_from_snprintf(struct hist_entry *self, char *bf,
+                                    size_t size, unsigned int width __used)
+{
+        struct addr_map_symbol *from = &self->branch_info->from;
+        return _hist_entry__sym_snprintf(from->map, from->sym, from->addr,
+                                         self->level, bf, size, width);
+
+}
+
+static int hist_entry__sym_to_snprintf(struct hist_entry *self, char *bf,
+                                    size_t size, unsigned int width __used)
+{
+        struct addr_map_symbol *to = &self->branch_info->to;
+        return _hist_entry__sym_snprintf(to->map, to->sym, to->addr,
+                                         self->level, bf, size, width);
+
+}
+
+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)
+{
+        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 *self, char *bf,
+                                    size_t size, unsigned int width){
+        static const char *out = "N/A";
+
+        if (self->branch_info->flags.predicted)
+                out = "N";
+        else if (self->branch_info->flags.mispred)
+                out = "Y";
+
+        return repsep_snprintf(bf, size, "%-*s", width, out);
+}
+
+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,
+};
+
 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 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,  },
-        { .name = "cpu",        .entry = &sort_cpu,     },
+        DIM(SORT_PID, "pid", sort_thread),
+        DIM(SORT_COMM, "comm", sort_comm),
+        DIM(SORT_DSO, "dso", sort_dso),
+        DIM(SORT_DSO_FROM, "dso_from", sort_dso_from),
+        DIM(SORT_DSO_TO, "dso_to", sort_dso_to),
+        DIM(SORT_SYM, "symbol", sort_sym),
+        DIM(SORT_SYM_TO, "symbol_from", sort_sym_from),
+        DIM(SORT_SYM_FROM, "symbol_to", sort_sym_to),
+        DIM(SORT_PARENT, "parent", sort_parent),
+        DIM(SORT_CPU, "cpu", sort_cpu),
+        DIM(SORT_MISPREDICT, "mispredict", sort_mispredict),
 };
 
 int sort_dimension__add(const char *tok)
@@ -273,7 +450,6 @@ int sort_dimension__add(const char *tok)
 
                 if (strncasecmp(tok, sd->name, strlen(tok)))
                         continue;
-
                 if (sd->entry == &sort_parent) {
                         int ret = regcomp(&parent_regex, parent_pattern, REG_EXTENDED);
                         if (ret) {
@@ -305,6 +481,16 @@ int sort_dimension__add(const char *tok)
                                 sort__first_dimension = SORT_PARENT;
                         else if (!strcmp(sd->name, "cpu"))
                                 sort__first_dimension = SORT_CPU;
+                        else if (!strcmp(sd->name, "symbol_from"))
+                                sort__first_dimension = SORT_SYM_FROM;
+                        else if (!strcmp(sd->name, "symbol_to"))
+                                sort__first_dimension = SORT_SYM_TO;
+                        else if (!strcmp(sd->name, "dso_from"))
+                                sort__first_dimension = SORT_DSO_FROM;
+                        else if (!strcmp(sd->name, "dso_to"))
+                                sort__first_dimension = SORT_DSO_TO;
+                        else if (!strcmp(sd->name, "mispredict"))
+                                sort__first_dimension = SORT_MISPREDICT;
                 }
 
                 list_add_tail(&sd->entry->list, &hist_entry__sort_list);
@@ -312,7 +498,6 @@ int sort_dimension__add(const char *tok)
 
                 return 0;
         }
-
         return -ESRCH;
 }
 
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 3f67ae395752..472aa5a63a58 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -31,11 +31,16 @@ extern const char *parent_pattern;
 extern const char default_sort_order[];
 extern int sort__need_collapse;
 extern int sort__has_parent;
+extern int sort__branch_mode;
 extern char *field_sep;
 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 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;
 
 /**
@@ -72,6 +77,7 @@ struct hist_entry {
                 struct hist_entry *pair;
                 struct rb_root    sorted_chain;
         };
+        struct branch_info      *branch_info;
         struct callchain_root   callchain[0];
 };
 
@@ -82,6 +88,11 @@ enum sort_type {
         SORT_SYM,
         SORT_PARENT,
         SORT_CPU,
+        SORT_DSO_FROM,
+        SORT_DSO_TO,
+        SORT_SYM_FROM,
+        SORT_SYM_TO,
+        SORT_MISPREDICT,
 };
 
 /*
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 0975438c3e72..5dd83c3e2c0c 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1,4 +1,3 @@
-#include <ctype.h>
 #include <dirent.h>
 #include <errno.h>
 #include <libgen.h>
@@ -12,6 +11,7 @@
 #include <unistd.h>
 #include <inttypes.h>
 #include "build-id.h"
+#include "util.h"
 #include "debug.h"
 #include "symbol.h"
 #include "strlist.h"
@@ -263,6 +263,28 @@ static size_t symbol__fprintf(struct symbol *sym, FILE *fp)
                        sym->name);
 }
 
+size_t symbol__fprintf_symname_offs(const struct symbol *sym,
+                                    const struct addr_location *al, FILE *fp)
+{
+        unsigned long offset;
+        size_t length;
+
+        if (sym && sym->name) {
+                length = fprintf(fp, "%s", sym->name);
+                if (al) {
+                        offset = al->addr - sym->start;
+                        length += fprintf(fp, "+0x%lx", offset);
+                }
+                return length;
+        } else
+                return fprintf(fp, "[unknown]");
+}
+
+size_t symbol__fprintf_symname(const struct symbol *sym, FILE *fp)
+{
+        return symbol__fprintf_symname_offs(sym, NULL, fp);
+}
+
 void dso__set_long_name(struct dso *dso, char *name)
 {
         if (name == NULL)
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 123c2e14353e..ac49ef208a5f 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -5,6 +5,7 @@
 #include <stdbool.h>
 #include <stdint.h>
 #include "map.h"
+#include "../perf.h"
 #include <linux/list.h>
 #include <linux/rbtree.h>
 #include <stdio.h>
@@ -70,6 +71,7 @@ struct symbol_conf {
         unsigned short  priv_size;
         unsigned short  nr_events;
         bool            try_vmlinux_path,
+                        show_kernel_path,
                         use_modules,
                         sort_by_name,
                         show_nr_samples,
@@ -95,7 +97,11 @@ 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;
 };
 
@@ -119,6 +125,19 @@ struct map_symbol {
         bool          has_children;
 };
 
+struct addr_map_symbol {
+        struct map    *map;
+        struct symbol *sym;
+        u64           addr;
+        u64           al_addr;
+};
+
+struct branch_info {
+        struct addr_map_symbol from;
+        struct addr_map_symbol to;
+        struct branch_flags flags;
+};
+
 struct addr_location {
         struct thread *thread;
         struct map    *map;
@@ -241,6 +260,9 @@ void machines__destroy_guest_kernel_maps(struct rb_root *machines);
 
 int symbol__init(void);
 void symbol__exit(void);
+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);
 bool symbol_type__is_a(char symbol_type, enum map_type map_type);
 
 size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp);
diff --git a/tools/perf/util/sysfs.c b/tools/perf/util/sysfs.c
new file mode 100644
index 000000000000..48c6902e749f
--- /dev/null
+++ b/tools/perf/util/sysfs.c
@@ -0,0 +1,60 @@
+
+#include "util.h"
+#include "sysfs.h"
+
+static const char * const sysfs_known_mountpoints[] = {
+        "/sys",
+        0,
+};
+
+static int sysfs_found;
+char sysfs_mountpoint[PATH_MAX];
+
+static int sysfs_valid_mountpoint(const char *sysfs)
+{
+        struct statfs st_fs;
+
+        if (statfs(sysfs, &st_fs) < 0)
+                return -ENOENT;
+        else if (st_fs.f_type != (long) SYSFS_MAGIC)
+                return -ENOENT;
+
+        return 0;
+}
+
+const char *sysfs_find_mountpoint(void)
+{
+        const char * const *ptr;
+        char type[100];
+        FILE *fp;
+
+        if (sysfs_found)
+                return (const char *) sysfs_mountpoint;
+
+        ptr = sysfs_known_mountpoints;
+        while (*ptr) {
+                if (sysfs_valid_mountpoint(*ptr) == 0) {
+                        sysfs_found = 1;
+                        strcpy(sysfs_mountpoint, *ptr);
+                        return sysfs_mountpoint;
+                }
+                ptr++;
+        }
+
+        /* give up and parse /proc/mounts */
+        fp = fopen("/proc/mounts", "r");
+        if (fp == NULL)
+                return NULL;
+
+        while (!sysfs_found &&
+               fscanf(fp, "%*s %" STR(PATH_MAX) "s %99s %*s %*d %*d\n",
+                      sysfs_mountpoint, type) == 2) {
+
+                if (strcmp(type, "sysfs") == 0)
+                        sysfs_found = 1;
+        }
+
+        fclose(fp);
+
+        return sysfs_found ? sysfs_mountpoint : NULL;
+}
diff --git a/tools/perf/util/sysfs.h b/tools/perf/util/sysfs.h
new file mode 100644
index 000000000000..a813b7203938
--- /dev/null
+++ b/tools/perf/util/sysfs.h
@@ -0,0 +1,6 @@
+#ifndef __SYSFS_H__
+#define __SYSFS_H__
+
+const char *sysfs_find_mountpoint(void);
+
+#endif /* __DEBUGFS_H__ */
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index a5df131b77c3..84d9bd782004 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -1,6 +1,13 @@
 #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"
 
 /* Skip "." and ".." directories */
@@ -23,7 +30,7 @@ struct thread_map *thread_map__new_by_pid(pid_t pid)
         sprintf(name, "/proc/%d/task", pid);
         items = scandir(name, &namelist, filter, NULL);
         if (items <= 0)
-                return NULL;
+                return NULL;
 
         threads = malloc(sizeof(*threads) + sizeof(pid_t) * items);
         if (threads != NULL) {
@@ -51,14 +58,240 @@ struct thread_map *thread_map__new_by_tid(pid_t tid)
         return threads;
 }
 
-struct thread_map *thread_map__new(pid_t pid, pid_t tid)
+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++)
+                        free(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++)
+                free(namelist[i]);
+        free(namelist);
+
+out_free_closedir:
+        free(threads);
+        threads = NULL;
+        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_threads;
+
+                threads = nt;
+
+                if (threads) {
+                        for (i = 0; i < items; i++)
+                                threads->map[j++] = atoi(namelist[i]->d_name);
+                        threads->nr = total_tasks;
+                }
+
+                for (i = 0; i < items; i++)
+                        free(namelist[i]);
+                free(namelist);
+
+                if (!threads)
+                        break;
+        }
+
+out:
+        strlist__delete(slist);
+        return threads;
+
+out_free_threads:
+        free(threads);
+        threads = NULL;
+        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:
+        free(threads);
+        threads = NULL;
+        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
index 3cb907311409..7da80f14418b 100644
--- a/tools/perf/util/thread_map.h
+++ b/tools/perf/util/thread_map.h
@@ -2,6 +2,7 @@
 #define __PERF_THREAD_MAP_H
 
 #include <sys/types.h>
+#include <stdio.h>
 
 struct thread_map {
         int nr;
@@ -10,6 +11,14 @@ struct thread_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(pid_t pid, 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);
+
 #endif  /* __PERF_THREAD_MAP_H */
diff --git a/tools/perf/util/top.c b/tools/perf/util/top.c
index 500471dffa4f..09fe579ccafb 100644
--- a/tools/perf/util/top.c
+++ b/tools/perf/util/top.c
@@ -69,12 +69,15 @@ size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size)
 
         ret += SNPRINTF(bf + ret, size - ret, "], ");
 
-        if (top->target_pid != -1)
-                ret += SNPRINTF(bf + ret, size - ret, " (target_pid: %d",
+        if (top->target_pid)
+                ret += SNPRINTF(bf + ret, size - ret, " (target_pid: %s",
                                 top->target_pid);
-        else if (top->target_tid != -1)
-                ret += SNPRINTF(bf + ret, size - ret, " (target_tid: %d",
+        else if (top->target_tid)
+                ret += SNPRINTF(bf + ret, size - ret, " (target_tid: %s",
                                 top->target_tid);
+        else if (top->uid_str != NULL)
+                ret += SNPRINTF(bf + ret, size - ret, " (uid: %s",
+                                top->uid_str);
         else
                 ret += SNPRINTF(bf + ret, size - ret, " (all");
 
@@ -82,7 +85,7 @@ size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size)
                 ret += SNPRINTF(bf + ret, size - ret, ", CPU%s: %s)",
                                 top->evlist->cpus->nr > 1 ? "s" : "", top->cpu_list);
         else {
-                if (top->target_tid != -1)
+                if (top->target_tid)
                         ret += SNPRINTF(bf + ret, size - ret, ")");
                 else
                         ret += SNPRINTF(bf + ret, size - ret, ", %d CPU%s)",
diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h
index f2eab81435ae..ce61cb2d1acf 100644
--- a/tools/perf/util/top.h
+++ b/tools/perf/util/top.h
@@ -23,7 +23,8 @@ struct perf_top {
         u64                guest_us_samples, guest_kernel_samples;
         int                print_entries, count_filter, delay_secs;
         int                freq;
-        pid_t              target_pid, target_tid;
+        const char         *target_pid, *target_tid;
+        uid_t              uid;
         bool               hide_kernel_symbols, hide_user_symbols, zero;
         bool               system_wide;
         bool               use_tui, use_stdio;
@@ -33,7 +34,7 @@ struct perf_top {
         bool               vmlinux_warned;
         bool               inherit;
         bool               group;
-        bool               sample_id_all_avail;
+        bool               sample_id_all_missing;
         bool               exclude_guest_missing;
         bool               dump_symtab;
         const char         *cpu_list;
@@ -46,6 +47,7 @@ struct perf_top {
         int                realtime_prio;
         int                sym_pcnt_filter;
         const char         *sym_filter;
+        const char         *uid_str;
 };
 
 size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size);
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index 1a8d4dc4f386..a4088ced1e64 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -25,7 +25,6 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
-#include <ctype.h>
 #include <errno.h>
 
 #include "../perf.h"
@@ -1424,6 +1423,11 @@ static long long arg_num_eval(struct print_arg *arg)
                                 die("unknown op '%s'", arg->op.op);
                         }
                         break;
+                case '+':
+                        left = arg_num_eval(arg->op.left);
+                        right = arg_num_eval(arg->op.right);
+                        val = left + right;
+                        break;
                 default:
                         die("unknown op '%s'", arg->op.op);
                 }
@@ -1484,6 +1488,13 @@ process_fields(struct event *event, struct print_flag_sym **list, char **tok)
 
                 free_token(token);
                 type = process_arg(event, arg, &token);
+
+                if (type == EVENT_OP)
+                        type = process_op(event, arg, &token);
+
+                if (type == EVENT_ERROR)
+                        goto out_free;
+
                 if (test_type_token(type, token, EVENT_DELIM, ","))
                         goto out_free;
 
diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index f55cc3a765a1..b9592e0de8d7 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -33,7 +33,6 @@
 #include <pthread.h>
 #include <fcntl.h>
 #include <unistd.h>
-#include <ctype.h>
 #include <errno.h>
 
 #include "../perf.h"
diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c
index a3fdf55f317b..18ae6c1831d3 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"
diff --git a/tools/perf/util/ui/browsers/annotate.c b/tools/perf/util/ui/browsers/annotate.c
index 295a9c93f945..57a4c6ef3fd2 100644
--- a/tools/perf/util/ui/browsers/annotate.c
+++ b/tools/perf/util/ui/browsers/annotate.c
@@ -69,14 +69,17 @@ static void annotate_browser__write(struct ui_browser *self, void *entry, int ro
         if (!self->navkeypressed)
                 width += 1;
 
+        if (!ab->hide_src_code && ol->offset != -1)
+                if (!current_entry || (self->use_navkeypressed &&
+                                       !self->navkeypressed))
+                        ui_browser__set_color(self, HE_COLORSET_CODE);
+
         if (!*ol->line)
                 slsmg_write_nstring(" ", width - 18);
         else
                 slsmg_write_nstring(ol->line, width - 18);
 
-        if (!current_entry)
-                ui_browser__set_color(self, HE_COLORSET_CODE);
-        else
+        if (current_entry)
                 ab->selection = ol;
 }
 
@@ -230,9 +233,9 @@ static int annotate_browser__run(struct annotate_browser *self, int evidx,
         struct rb_node *nd = NULL;
         struct map_symbol *ms = self->b.priv;
         struct symbol *sym = ms->sym;
-        const char *help = "<-, ESC: exit, TAB/shift+TAB: cycle hottest lines, "
-                           "H: Hottest, -> Line action, S -> Toggle source "
-                           "code view";
+        const char *help = "<-/ESC: Exit, TAB/shift+TAB: Cycle hot lines, "
+                           "H: Go to hottest line, ->/ENTER: Line action, "
+                           "S: Toggle source code view";
         int key;
 
         if (ui_browser__show(&self->b, sym->name, help) < 0)
@@ -284,9 +287,11 @@ static int annotate_browser__run(struct annotate_browser *self, int evidx,
                                 nd = self->curr_hot;
                         break;
                 case 'H':
+                case 'h':
                         nd = self->curr_hot;
                         break;
                 case 'S':
+                case 's':
                         if (annotate_browser__toggle_source(self))
                                 ui_helpline__puts(help);
                         continue;
@@ -338,6 +343,7 @@ static int annotate_browser__run(struct annotate_browser *self, int evidx,
                                 pthread_mutex_unlock(&notes->lock);
                                 symbol__tui_annotate(target, ms->map, evidx,
                                                      timer, arg, delay_secs);
+                                ui_browser__show_title(&self->b, sym->name);
                         }
                         continue;
                 case K_LEFT:
diff --git a/tools/perf/util/ui/browsers/hists.c b/tools/perf/util/ui/browsers/hists.c
index bb9197c9c4a4..fa530fcc764a 100644
--- a/tools/perf/util/ui/browsers/hists.c
+++ b/tools/perf/util/ui/browsers/hists.c
@@ -805,8 +805,11 @@ static struct hist_browser *hist_browser__new(struct hists *hists)
                 self->hists = hists;
                 self->b.refresh = hist_browser__refresh;
                 self->b.seek = ui_browser__hists_seek;
-                self->b.use_navkeypressed = true,
-                self->has_symbols = sort_sym.list.next != NULL;
+                self->b.use_navkeypressed = true;
+                if (sort__branch_mode == 1)
+                        self->has_symbols = sort_sym_from.list.next != NULL;
+                else
+                        self->has_symbols = sort_sym.list.next != NULL;
         }
 
         return self;
@@ -839,6 +842,9 @@ static int hists__browser_title(struct hists *self, char *bf, size_t size,
         nr_events = convert_unit(nr_events, &unit);
         printed = scnprintf(bf, size, "Events: %lu%c %s", nr_events, unit, ev_name);
 
+        if (self->uid_filter_str)
+                printed += snprintf(bf + printed, size - printed,
+                                    ", UID: %s", self->uid_filter_str);
         if (thread)
                 printed += scnprintf(bf + printed, size - printed,
                                     ", Thread: %s(%d)",
@@ -850,6 +856,16 @@ static int hists__browser_title(struct hists *self, char *bf, size_t size,
         return printed;
 }
 
+static inline void free_popup_options(char **options, int n)
+{
+        int i;
+
+        for (i = 0; i < n; ++i) {
+                free(options[i]);
+                options[i] = NULL;
+        }
+}
+
 static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
                                     const char *helpline, const char *ev_name,
                                     bool left_exits,
@@ -858,7 +874,10 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 {
         struct hists *self = &evsel->hists;
         struct hist_browser *browser = hist_browser__new(self);
+        struct branch_info *bi;
         struct pstack *fstack;
+        char *options[16];
+        int nr_options = 0;
         int key = -1;
 
         if (browser == NULL)
@@ -870,13 +889,16 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 
         ui_helpline__push(helpline);
 
+        memset(options, 0, sizeof(options));
+
         while (1) {
                 const struct thread *thread = NULL;
                 const struct dso *dso = NULL;
-                char *options[16];
-                int nr_options = 0, choice = 0, i,
+                int choice = 0,
                     annotate = -2, zoom_dso = -2, zoom_thread = -2,
-                    browse_map = -2;
+                    annotate_f = -2, annotate_t = -2, browse_map = -2;
+
+                nr_options = 0;
 
                 key = hist_browser__run(browser, ev_name, timer, arg, delay_secs);
 
@@ -884,7 +906,6 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
                         thread = hist_browser__selected_thread(browser);
                         dso = browser->selection->map ? browser->selection->map->dso : NULL;
                 }
-
                 switch (key) {
                 case K_TAB:
                 case K_UNTAB:
@@ -899,7 +920,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
                         if (!browser->has_symbols) {
                                 ui_browser__warning(&browser->b, delay_secs * 2,
                         "Annotation is only available for symbolic views, "
-                        "include \"sym\" in --sort to use it.");
+                        "include \"sym*\" in --sort to use it.");
                                 continue;
                         }
 
@@ -969,12 +990,34 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
                 if (!browser->has_symbols)
                         goto add_exit_option;
 
-                if (browser->selection != NULL &&
-                    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 (sort__branch_mode == 1) {
+                        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 &&
+                                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",
@@ -995,25 +1038,39 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
                         browse_map = nr_options++;
 add_exit_option:
                 options[nr_options++] = (char *)"Exit";
-
+retry_popup_menu:
                 choice = ui__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)
+                if (choice == -1) {
+                        free_popup_options(options, nr_options - 1);
                         continue;
+                }
 
-                if (choice == annotate) {
+                if (choice == annotate || choice == annotate_t || choice == annotate_f) {
                         struct hist_entry *he;
                         int err;
 do_annotate:
                         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;
+                        }
+
                         /*
                          * Don't let this be freed, say, by hists__decay_entry.
                          */
@@ -1021,9 +1078,18 @@ do_annotate:
                         err = hist_entry__tui_annotate(he, evsel->idx,
                                                        timer, arg, delay_secs);
                         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) {
@@ -1069,6 +1135,7 @@ out_free_stack:
         pstack__delete(fstack);
 out:
         hist_browser__delete(browser);
+        free_popup_options(options, nr_options - 1);
         return key;
 }
 
diff --git a/tools/perf/util/ui/browsers/map.c b/tools/perf/util/ui/browsers/map.c
index 6905bcc8be2d..eca6575abfd0 100644
--- a/tools/perf/util/ui/browsers/map.c
+++ b/tools/perf/util/ui/browsers/map.c
@@ -3,9 +3,9 @@
 #include <newt.h>
 #include <inttypes.h>
 #include <sys/ttydefaults.h>
-#include <ctype.h>
 #include <string.h>
 #include <linux/bitops.h>
+#include "../../util.h"
 #include "../../debug.h"
 #include "../../symbol.h"
 #include "../browser.h"
diff --git a/tools/perf/util/usage.c b/tools/perf/util/usage.c
index d76d1c0ff98f..52bb07c6442a 100644
--- a/tools/perf/util/usage.c
+++ b/tools/perf/util/usage.c
@@ -7,6 +7,7 @@
  * Copyright (C) Linus Torvalds, 2005
  */
 #include "util.h"
+#include "debug.h"
 
 static void report(const char *prefix, const char *err, va_list params)
 {
@@ -81,3 +82,41 @@ void warning(const char *warn, ...)
         warn_routine(warn, params);
         va_end(params);
 }
+
+uid_t parse_target_uid(const char *str, const char *tid, const char *pid)
+{
+        struct passwd pwd, *result;
+        char buf[1024];
+
+        if (str == NULL)
+                return UINT_MAX;
+
+        /* UID and PID are mutually exclusive */
+        if (tid || pid) {
+                ui__warning("PID/TID switch overriding UID\n");
+                sleep(1);
+                return UINT_MAX;
+        }
+
+        getpwnam_r(str, &pwd, buf, sizeof(buf), &result);
+
+        if (result == NULL) {
+                char *endptr;
+                int uid = strtol(str, &endptr, 10);
+
+                if (*endptr != '\0') {
+                        ui__error("Invalid user %s\n", str);
+                        return UINT_MAX - 1;
+                }
+
+                getpwuid_r(uid, &pwd, buf, sizeof(buf), &result);
+
+                if (result == NULL) {
+                        ui__error("Problems obtaining information for user %s\n",
+                                  str);
+                        return UINT_MAX - 1;
+                }
+        }
+
+        return result->pw_uid;
+}
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index fb25d1329218..8109a907841e 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -14,6 +14,8 @@ void event_attr_init(struct perf_event_attr *attr)
                 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)
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index ecf9898169c8..0f99f394d8e0 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -199,6 +199,8 @@ 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
 
@@ -219,6 +221,8 @@ extern unsigned char sane_ctype[256];
 #define isalpha(x) sane_istest(x,GIT_ALPHA)
 #define isalnum(x) sane_istest(x,GIT_ALPHA | GIT_DIGIT)
 #define isprint(x) sane_istest(x,GIT_PRINT)
+#define islower(x) (sane_istest(x,GIT_ALPHA) && sane_istest(x,0x20))
+#define isupper(x) (sane_istest(x,GIT_ALPHA) && !sane_istest(x,0x20))
 #define tolower(x) sane_case((unsigned char)(x), 0x20)
 #define toupper(x) sane_case((unsigned char)(x), 0)
 
@@ -245,6 +249,8 @@ struct perf_event_attr;
 
 void event_attr_init(struct perf_event_attr *attr);
 
+uid_t parse_target_uid(const char *str, const char *tid, const char *pid);
+
 #define _STR(x) #x
 #define STR(x) _STR(x)